[2022-01-17 11:28:51 swin_tiny_patch4_window7_224] (main.py 309): INFO Full config saved to output/swin_tiny_patch4_window7_224/fix_ddp/config.json
[2022-01-17 11:28:51 swin_tiny_patch4_window7_224] (main.py 312): INFO AMP_OPT_LEVEL: ''
AUG:
  AUTO_AUGMENT: rand-m9-mstd0.5-inc1
  COLOR_JITTER: 0.4
  CUTMIX: 1.0
  CUTMIX_MINMAX: null
  MIXUP: 0.8
  MIXUP_MODE: batch
  MIXUP_PROB: 1.0
  MIXUP_SWITCH_PROB: 0.5
  RECOUNT: 1
  REMODE: pixel
  REPROB: 0.25
BASE:
- ''
DATA:
  BATCH_SIZE: 128
  CACHE_MODE: part
  DATASET: imagenet
  DATA_PATH: /dataset/7202515b/
  IMG_SIZE: 224
  INTERPOLATION: bicubic
  NUM_WORKERS: 8
  PIN_MEMORY: true
  ZIP_MODE: false
EVAL_MODE: false
LOCAL_RANK: 0
MODEL:
  DROP_PATH_RATE: 0.2
  DROP_RATE: 0.0
  LABEL_SMOOTHING: 0.1
  NAME: swin_tiny_patch4_window7_224
  NUM_CLASSES: 1000
  PRETRAINED: ''
  RESUME: ''
  SWIN:
    APE: false
    DEPTHS:
    - 2
    - 2
    - 6
    - 2
    EMBED_DIM: 96
    IN_CHANS: 3
    MLP_RATIO: 4.0
    NUM_HEADS:
    - 3
    - 6
    - 12
    - 24
    PATCH_NORM: true
    PATCH_SIZE: 4
    QKV_BIAS: true
    QK_SCALE: null
    WINDOW_SIZE: 7
  SWIN_MLP:
    APE: false
    DEPTHS:
    - 2
    - 2
    - 6
    - 2
    EMBED_DIM: 96
    IN_CHANS: 3
    MLP_RATIO: 4.0
    NUM_HEADS:
    - 3
    - 6
    - 12
    - 24
    PATCH_NORM: true
    PATCH_SIZE: 4
    WINDOW_SIZE: 7
  TYPE: swin
OUTPUT: output/swin_tiny_patch4_window7_224/fix_ddp
PRINT_FREQ: 10
SAVE_FREQ: 10
SEED: 0
TAG: fix_ddp
TEST:
  CROP: true
  SEQUENTIAL: false
THROUGHPUT_MODE: false
TRAIN:
  ACCUMULATION_STEPS: 0
  AUTO_RESUME: false
  BASE_LR: 0.001
  CLIP_GRAD: 5.0
  EPOCHS: 300
  LR_SCHEDULER:
    DECAY_EPOCHS: 30
    DECAY_RATE: 0.1
    NAME: cosine
  MIN_LR: 1.0e-05
  OPTIMIZER:
    BETAS:
    - 0.9
    - 0.999
    EPS: 1.0e-08
    MOMENTUM: 0.9
    NAME: adamw
  START_EPOCH: 0
  USE_CHECKPOINT: false
  WARMUP_EPOCHS: 20
  WARMUP_LR: 1.0e-06
  WEIGHT_DECAY: 0.05

[2022-01-17 11:28:57 swin_tiny_patch4_window7_224] (main.py 69): INFO Creating model:swin/swin_tiny_patch4_window7_224
[2022-01-17 11:29:05 swin_tiny_patch4_window7_224] (main.py 73): INFO SwinTransformer(
  (patch_embed): PatchEmbed(
    (proj): Conv2d(3, 96, kernel_size=(4, 4), stride=(4, 4))
    (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
  )
  (pos_drop): Dropout(p=0.0, inplace=False)
  (layers): ModuleList(
    (0): BasicLayer(
      (blocks): ModuleList(
        (0): SwinTransformerBlock(
          (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
          (attn): WindowAttention(
            (qkv): Linear(in_features=96, out_features=288, bias=True)
            (attn_drop): Dropout(p=0.0, inplace=False)
            (proj): Linear(in_features=96, out_features=96, bias=True)
            (proj_drop): Dropout(p=0.0, inplace=False)
            (softmax): Softmax(dim=-1)
          )
          (drop_path): Identity()
          (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=96, out_features=384, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=384, out_features=96, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): SwinTransformerBlock(
          (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
          (attn): WindowAttention(
            (qkv): Linear(in_features=96, out_features=288, bias=True)
            (attn_drop): Dropout(p=0.0, inplace=False)
            (proj): Linear(in_features=96, out_features=96, bias=True)
            (proj_drop): Dropout(p=0.0, inplace=False)
            (softmax): Softmax(dim=-1)
          )
          (drop_path): DropPath()
          (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=96, out_features=384, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=384, out_features=96, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (downsample): PatchMerging(
        (reduction): Linear(in_features=384, out_features=192, bias=False)
        (norm): LayerNorm((384,), eps=1e-05, elementwise_affine=True)
      )
    )
    (1): BasicLayer(
      (blocks): ModuleList(
        (0): SwinTransformerBlock(
          (norm1): LayerNorm((192,), eps=1e-05, elementwise_affine=True)
          (attn): WindowAttention(
            (qkv): Linear(in_features=192, out_features=576, bias=True)
            (attn_drop): Dropout(p=0.0, inplace=False)
            (proj): Linear(in_features=192, out_features=192, bias=True)
            (proj_drop): Dropout(p=0.0, inplace=False)
            (softmax): Softmax(dim=-1)
          )
          (drop_path): DropPath()
          (norm2): LayerNorm((192,), eps=1e-05, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=192, out_features=768, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=768, out_features=192, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): SwinTransformerBlock(
          (norm1): LayerNorm((192,), eps=1e-05, elementwise_affine=True)
          (attn): WindowAttention(
            (qkv): Linear(in_features=192, out_features=576, bias=True)
            (attn_drop): Dropout(p=0.0, inplace=False)
            (proj): Linear(in_features=192, out_features=192, bias=True)
            (proj_drop): Dropout(p=0.0, inplace=False)
            (softmax): Softmax(dim=-1)
          )
          (drop_path): DropPath()
          (norm2): LayerNorm((192,), eps=1e-05, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=192, out_features=768, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=768, out_features=192, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (downsample): PatchMerging(
        (reduction): Linear(in_features=768, out_features=384, bias=False)
        (norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
    )
    (2): BasicLayer(
      (blocks): ModuleList(
        (0): SwinTransformerBlock(
          (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True)
          (attn): WindowAttention(
            (qkv): Linear(in_features=384, out_features=1152, bias=True)
            (attn_drop): Dropout(p=0.0, inplace=False)
            (proj): Linear(in_features=384, out_features=384, bias=True)
            (proj_drop): Dropout(p=0.0, inplace=False)
            (softmax): Softmax(dim=-1)
          )
          (drop_path): DropPath()
          (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=384, out_features=1536, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1536, out_features=384, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): SwinTransformerBlock(
          (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True)
          (attn): WindowAttention(
            (qkv): Linear(in_features=384, out_features=1152, bias=True)
            (attn_drop): Dropout(p=0.0, inplace=False)
            (proj): Linear(in_features=384, out_features=384, bias=True)
            (proj_drop): Dropout(p=0.0, inplace=False)
            (softmax): Softmax(dim=-1)
          )
          (drop_path): DropPath()
          (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=384, out_features=1536, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1536, out_features=384, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (2): SwinTransformerBlock(
          (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True)
          (attn): WindowAttention(
            (qkv): Linear(in_features=384, out_features=1152, bias=True)
            (attn_drop): Dropout(p=0.0, inplace=False)
            (proj): Linear(in_features=384, out_features=384, bias=True)
            (proj_drop): Dropout(p=0.0, inplace=False)
            (softmax): Softmax(dim=-1)
          )
          (drop_path): DropPath()
          (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=384, out_features=1536, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1536, out_features=384, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (3): SwinTransformerBlock(
          (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True)
          (attn): WindowAttention(
            (qkv): Linear(in_features=384, out_features=1152, bias=True)
            (attn_drop): Dropout(p=0.0, inplace=False)
            (proj): Linear(in_features=384, out_features=384, bias=True)
            (proj_drop): Dropout(p=0.0, inplace=False)
            (softmax): Softmax(dim=-1)
          )
          (drop_path): DropPath()
          (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=384, out_features=1536, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1536, out_features=384, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (4): SwinTransformerBlock(
          (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True)
          (attn): WindowAttention(
            (qkv): Linear(in_features=384, out_features=1152, bias=True)
            (attn_drop): Dropout(p=0.0, inplace=False)
            (proj): Linear(in_features=384, out_features=384, bias=True)
            (proj_drop): Dropout(p=0.0, inplace=False)
            (softmax): Softmax(dim=-1)
          )
          (drop_path): DropPath()
          (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=384, out_features=1536, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1536, out_features=384, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (5): SwinTransformerBlock(
          (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True)
          (attn): WindowAttention(
            (qkv): Linear(in_features=384, out_features=1152, bias=True)
            (attn_drop): Dropout(p=0.0, inplace=False)
            (proj): Linear(in_features=384, out_features=384, bias=True)
            (proj_drop): Dropout(p=0.0, inplace=False)
            (softmax): Softmax(dim=-1)
          )
          (drop_path): DropPath()
          (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=384, out_features=1536, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1536, out_features=384, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (downsample): PatchMerging(
        (reduction): Linear(in_features=1536, out_features=768, bias=False)
        (norm): LayerNorm((1536,), eps=1e-05, elementwise_affine=True)
      )
    )
    (3): BasicLayer(
      (blocks): ModuleList(
        (0): SwinTransformerBlock(
          (norm1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (attn): WindowAttention(
            (qkv): Linear(in_features=768, out_features=2304, bias=True)
            (attn_drop): Dropout(p=0.0, inplace=False)
            (proj): Linear(in_features=768, out_features=768, bias=True)
            (proj_drop): Dropout(p=0.0, inplace=False)
            (softmax): Softmax(dim=-1)
          )
          (drop_path): DropPath()
          (norm2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): SwinTransformerBlock(
          (norm1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (attn): WindowAttention(
            (qkv): Linear(in_features=768, out_features=2304, bias=True)
            (attn_drop): Dropout(p=0.0, inplace=False)
            (proj): Linear(in_features=768, out_features=768, bias=True)
            (proj_drop): Dropout(p=0.0, inplace=False)
            (softmax): Softmax(dim=-1)
          )
          (drop_path): DropPath()
          (norm2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
    )
  )
  (norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
  (avgpool): AdaptiveAvgPool1d()
  (head): Linear(in_features=768, out_features=1000, bias=True)
)
[2022-01-17 11:29:05 swin_tiny_patch4_window7_224] (main.py 80): INFO number of params: 28288354
[2022-01-17 11:29:05 swin_tiny_patch4_window7_224] (main.py 120): INFO Start training
[2022-01-17 11:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][0/1251]	eta 8:14:19 lr 0.000001	time 23.7090 (23.7090)	loss 6.9591 (6.9591)	grad_norm 1.5338 (1.5338)	
[2022-01-17 11:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][10/1251]	eta 1:25:47 lr 0.000001	time 1.6167 (4.1481)	loss 6.9664 (6.9739)	grad_norm 1.3354 (1.3887)	
[2022-01-17 11:30:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][20/1251]	eta 1:05:33 lr 0.000002	time 2.0573 (3.1950)	loss 6.9705 (6.9737)	grad_norm 1.3590 (1.3789)	
[2022-01-17 11:30:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][30/1251]	eta 0:58:22 lr 0.000002	time 1.7046 (2.8682)	loss 6.9316 (6.9683)	grad_norm 1.4504 (1.3845)	
[2022-01-17 11:30:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][40/1251]	eta 0:54:53 lr 0.000003	time 3.6386 (2.7201)	loss 6.9641 (6.9653)	grad_norm 1.4252 (1.3853)	
[2022-01-17 11:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][50/1251]	eta 0:52:46 lr 0.000003	time 2.3246 (2.6364)	loss 6.9468 (6.9637)	grad_norm 1.3219 (1.3807)	
[2022-01-17 11:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][60/1251]	eta 0:51:28 lr 0.000003	time 2.0952 (2.5936)	loss 6.8956 (6.9613)	grad_norm 1.3488 (1.3724)	
[2022-01-17 11:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][70/1251]	eta 0:49:28 lr 0.000004	time 1.7146 (2.5134)	loss 6.9474 (6.9601)	grad_norm 1.4443 (1.3736)	
[2022-01-17 11:32:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][80/1251]	eta 0:48:05 lr 0.000004	time 2.0982 (2.4644)	loss 6.9309 (6.9565)	grad_norm 1.4097 (1.3698)	
[2022-01-17 11:32:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][90/1251]	eta 0:47:13 lr 0.000005	time 2.2248 (2.4406)	loss 6.9520 (6.9536)	grad_norm 1.2602 (1.3640)	
[2022-01-17 11:33:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][100/1251]	eta 0:46:18 lr 0.000005	time 2.1861 (2.4136)	loss 6.9148 (6.9518)	grad_norm 1.2911 (1.3604)	
[2022-01-17 11:33:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][110/1251]	eta 0:45:16 lr 0.000005	time 1.5310 (2.3812)	loss 6.9427 (6.9492)	grad_norm 1.2743 (1.3545)	
[2022-01-17 11:33:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][120/1251]	eta 0:44:38 lr 0.000006	time 2.7888 (2.3687)	loss 6.9050 (6.9471)	grad_norm 1.3613 (1.3491)	
[2022-01-17 11:34:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][130/1251]	eta 0:44:11 lr 0.000006	time 2.2436 (2.3654)	loss 6.9370 (6.9453)	grad_norm 1.3509 (1.3429)	
[2022-01-17 11:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][140/1251]	eta 0:43:50 lr 0.000007	time 3.2885 (2.3680)	loss 6.9527 (6.9443)	grad_norm 1.3150 (1.3372)	
[2022-01-17 11:35:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][150/1251]	eta 0:43:11 lr 0.000007	time 1.6337 (2.3542)	loss 6.9435 (6.9426)	grad_norm 1.2202 (1.3329)	
[2022-01-17 11:35:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][160/1251]	eta 0:42:45 lr 0.000007	time 2.9157 (2.3515)	loss 6.9406 (6.9414)	grad_norm 1.1487 (1.3264)	
[2022-01-17 11:35:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][170/1251]	eta 0:42:12 lr 0.000008	time 1.7008 (2.3426)	loss 6.9476 (6.9405)	grad_norm 1.2412 (1.3198)	
[2022-01-17 11:36:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][180/1251]	eta 0:41:40 lr 0.000008	time 2.9246 (2.3347)	loss 6.9286 (6.9388)	grad_norm 1.1802 (1.3135)	
[2022-01-17 11:36:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][190/1251]	eta 0:40:57 lr 0.000009	time 1.7108 (2.3164)	loss 6.8814 (6.9368)	grad_norm 1.1924 (1.3073)	
[2022-01-17 11:36:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][200/1251]	eta 0:40:19 lr 0.000009	time 2.2805 (2.3018)	loss 6.9090 (6.9358)	grad_norm 1.2007 (1.3024)	
[2022-01-17 11:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][210/1251]	eta 0:39:50 lr 0.000009	time 2.7545 (2.2962)	loss 6.9161 (6.9350)	grad_norm 1.1284 (1.2966)	
[2022-01-17 11:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][220/1251]	eta 0:39:26 lr 0.000010	time 3.2258 (2.2958)	loss 6.9212 (6.9339)	grad_norm 1.1965 (1.2901)	
[2022-01-17 11:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][230/1251]	eta 0:38:58 lr 0.000010	time 1.8291 (2.2906)	loss 6.9255 (6.9332)	grad_norm 1.1355 (1.2852)	
[2022-01-17 11:38:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][240/1251]	eta 0:38:38 lr 0.000011	time 2.1930 (2.2932)	loss 6.8518 (6.9321)	grad_norm 1.1651 (1.2790)	
[2022-01-17 11:38:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][250/1251]	eta 0:38:10 lr 0.000011	time 1.5601 (2.2877)	loss 6.9303 (6.9309)	grad_norm 1.0359 (1.2719)	
[2022-01-17 11:39:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][260/1251]	eta 0:37:51 lr 0.000011	time 3.0432 (2.2923)	loss 6.8686 (6.9296)	grad_norm 1.1278 (1.2656)	
[2022-01-17 11:39:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][270/1251]	eta 0:37:25 lr 0.000012	time 1.9524 (2.2894)	loss 6.8634 (6.9283)	grad_norm 1.1287 (1.2608)	
[2022-01-17 11:39:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][280/1251]	eta 0:36:54 lr 0.000012	time 2.0113 (2.2811)	loss 6.8901 (6.9276)	grad_norm 1.1212 (1.2539)	
[2022-01-17 11:40:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][290/1251]	eta 0:36:24 lr 0.000013	time 1.8850 (2.2735)	loss 6.9057 (6.9266)	grad_norm 1.0626 (1.2484)	
[2022-01-17 11:40:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][300/1251]	eta 0:35:57 lr 0.000013	time 2.7601 (2.2691)	loss 6.8604 (6.9256)	grad_norm 1.0971 (1.2418)	
[2022-01-17 11:40:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][310/1251]	eta 0:35:28 lr 0.000013	time 2.0511 (2.2618)	loss 6.9194 (6.9243)	grad_norm 1.0529 (1.2360)	
[2022-01-17 11:41:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][320/1251]	eta 0:34:56 lr 0.000014	time 1.5205 (2.2517)	loss 6.8925 (6.9232)	grad_norm 1.0277 (1.2298)	
[2022-01-17 11:41:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][330/1251]	eta 0:34:29 lr 0.000014	time 1.8905 (2.2471)	loss 6.8497 (6.9224)	grad_norm 1.0256 (1.2237)	
[2022-01-17 11:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][340/1251]	eta 0:34:08 lr 0.000015	time 3.4195 (2.2486)	loss 6.8789 (6.9215)	grad_norm 1.0006 (1.2172)	
[2022-01-17 11:42:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][350/1251]	eta 0:33:45 lr 0.000015	time 2.3929 (2.2477)	loss 6.8900 (6.9207)	grad_norm 0.9560 (1.2111)	
[2022-01-17 11:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][360/1251]	eta 0:33:25 lr 0.000015	time 2.5607 (2.2510)	loss 6.8438 (6.9196)	grad_norm 1.0424 (1.2058)	
[2022-01-17 11:42:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][370/1251]	eta 0:33:01 lr 0.000016	time 1.5288 (2.2487)	loss 6.8505 (6.9187)	grad_norm 1.0000 (1.2007)	
[2022-01-17 11:43:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][380/1251]	eta 0:32:39 lr 0.000016	time 3.3679 (2.2493)	loss 6.8811 (6.9178)	grad_norm 1.0357 (1.1956)	
[2022-01-17 11:43:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][390/1251]	eta 0:32:13 lr 0.000017	time 2.1786 (2.2453)	loss 6.8647 (6.9165)	grad_norm 1.0950 (1.1905)	
[2022-01-17 11:44:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][400/1251]	eta 0:31:48 lr 0.000017	time 1.9593 (2.2431)	loss 6.8844 (6.9153)	grad_norm 0.9684 (1.1851)	
[2022-01-17 11:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][410/1251]	eta 0:31:25 lr 0.000017	time 1.9704 (2.2415)	loss 6.9091 (6.9146)	grad_norm 0.9565 (1.1805)	
[2022-01-17 11:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][420/1251]	eta 0:31:01 lr 0.000018	time 2.9430 (2.2405)	loss 6.8457 (6.9136)	grad_norm 0.9210 (1.1752)	
[2022-01-17 11:45:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][430/1251]	eta 0:30:37 lr 0.000018	time 2.2175 (2.2386)	loss 6.8935 (6.9126)	grad_norm 0.9162 (1.1702)	
[2022-01-17 11:45:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][440/1251]	eta 0:30:16 lr 0.000019	time 2.7443 (2.2400)	loss 6.8535 (6.9116)	grad_norm 1.0036 (1.1653)	
[2022-01-17 11:45:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][450/1251]	eta 0:29:54 lr 0.000019	time 2.1767 (2.2408)	loss 6.8543 (6.9109)	grad_norm 0.9462 (1.1608)	
[2022-01-17 11:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][460/1251]	eta 0:29:32 lr 0.000019	time 2.6667 (2.2412)	loss 6.9135 (6.9102)	grad_norm 0.9527 (1.1564)	
[2022-01-17 11:46:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][470/1251]	eta 0:29:09 lr 0.000020	time 2.6146 (2.2397)	loss 6.8671 (6.9092)	grad_norm 0.9325 (1.1519)	
[2022-01-17 11:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][480/1251]	eta 0:28:47 lr 0.000020	time 2.1589 (2.2405)	loss 6.8627 (6.9082)	grad_norm 0.9458 (1.1482)	
[2022-01-17 11:47:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][490/1251]	eta 0:28:23 lr 0.000021	time 1.8796 (2.2383)	loss 6.8901 (6.9073)	grad_norm 0.9124 (1.1438)	
[2022-01-17 11:47:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][500/1251]	eta 0:28:01 lr 0.000021	time 3.1054 (2.2391)	loss 6.9039 (6.9061)	grad_norm 0.8742 (1.1396)	
[2022-01-17 11:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][510/1251]	eta 0:27:39 lr 0.000021	time 2.4146 (2.2394)	loss 6.9068 (6.9054)	grad_norm 0.9010 (1.1356)	
[2022-01-17 11:48:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][520/1251]	eta 0:27:14 lr 0.000022	time 1.7055 (2.2366)	loss 6.9178 (6.9048)	grad_norm 0.9040 (1.1317)	
[2022-01-17 11:48:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][530/1251]	eta 0:26:50 lr 0.000022	time 1.9295 (2.2341)	loss 6.8410 (6.9036)	grad_norm 0.8882 (1.1278)	
[2022-01-17 11:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][540/1251]	eta 0:26:26 lr 0.000023	time 2.9057 (2.2314)	loss 6.8498 (6.9028)	grad_norm 0.9363 (1.1243)	
[2022-01-17 11:49:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][550/1251]	eta 0:26:02 lr 0.000023	time 1.8359 (2.2292)	loss 6.8663 (6.9022)	grad_norm 0.9156 (1.1207)	
[2022-01-17 11:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][560/1251]	eta 0:25:40 lr 0.000023	time 2.1405 (2.2294)	loss 6.8778 (6.9016)	grad_norm 0.9706 (1.1171)	
[2022-01-17 11:50:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][570/1251]	eta 0:25:17 lr 0.000024	time 1.9113 (2.2284)	loss 6.8546 (6.9008)	grad_norm 0.9450 (1.1134)	
[2022-01-17 11:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][580/1251]	eta 0:24:55 lr 0.000024	time 2.9954 (2.2287)	loss 6.8734 (6.9002)	grad_norm 0.8815 (1.1097)	
[2022-01-17 11:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][590/1251]	eta 0:24:32 lr 0.000025	time 2.0931 (2.2270)	loss 6.8545 (6.8994)	grad_norm 0.8544 (1.1065)	
[2022-01-17 11:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][600/1251]	eta 0:24:09 lr 0.000025	time 1.8691 (2.2258)	loss 6.7979 (6.8986)	grad_norm 1.0288 (1.1038)	
[2022-01-17 11:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][610/1251]	eta 0:23:45 lr 0.000025	time 1.7421 (2.2238)	loss 6.8439 (6.8977)	grad_norm 0.8410 (1.1004)	
[2022-01-17 11:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][620/1251]	eta 0:23:23 lr 0.000026	time 2.5057 (2.2247)	loss 6.8291 (6.8971)	grad_norm 0.8921 (1.0972)	
[2022-01-17 11:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][630/1251]	eta 0:23:00 lr 0.000026	time 2.1208 (2.2228)	loss 6.8670 (6.8963)	grad_norm 0.8436 (1.0945)	
[2022-01-17 11:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][640/1251]	eta 0:22:36 lr 0.000027	time 1.8528 (2.2206)	loss 6.8374 (6.8952)	grad_norm 0.9028 (1.0917)	
[2022-01-17 11:53:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][650/1251]	eta 0:22:13 lr 0.000027	time 2.1536 (2.2190)	loss 6.8006 (6.8942)	grad_norm 0.9889 (1.0895)	
[2022-01-17 11:53:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][660/1251]	eta 0:21:51 lr 0.000027	time 2.5022 (2.2189)	loss 6.8358 (6.8934)	grad_norm 0.8757 (1.0872)	
[2022-01-17 11:53:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][670/1251]	eta 0:21:29 lr 0.000028	time 2.2938 (2.2187)	loss 6.8631 (6.8925)	grad_norm 0.8697 (1.0849)	
[2022-01-17 11:54:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][680/1251]	eta 0:21:07 lr 0.000028	time 2.0778 (2.2192)	loss 6.9164 (6.8919)	grad_norm 1.0107 (1.0825)	
[2022-01-17 11:54:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][690/1251]	eta 0:20:44 lr 0.000029	time 1.9756 (2.2181)	loss 6.8481 (6.8911)	grad_norm 0.8466 (1.0810)	
[2022-01-17 11:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][700/1251]	eta 0:20:22 lr 0.000029	time 2.6288 (2.2183)	loss 6.8645 (6.8903)	grad_norm 0.8750 (1.0794)	
[2022-01-17 11:55:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][710/1251]	eta 0:19:59 lr 0.000029	time 1.6494 (2.2178)	loss 6.7844 (6.8895)	grad_norm 1.1315 (1.0774)	
[2022-01-17 11:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][720/1251]	eta 0:19:37 lr 0.000030	time 1.5991 (2.2180)	loss 6.8541 (6.8885)	grad_norm 1.0213 (1.0763)	
[2022-01-17 11:56:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][730/1251]	eta 0:19:15 lr 0.000030	time 1.5563 (2.2182)	loss 6.8319 (6.8877)	grad_norm 0.9008 (1.0749)	
[2022-01-17 11:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][740/1251]	eta 0:18:53 lr 0.000031	time 2.2076 (2.2190)	loss 6.8469 (6.8872)	grad_norm 0.9865 (1.0743)	
[2022-01-17 11:56:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][750/1251]	eta 0:18:32 lr 0.000031	time 2.0824 (2.2201)	loss 6.8553 (6.8865)	grad_norm 1.0810 (1.0729)	
[2022-01-17 11:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][760/1251]	eta 0:18:10 lr 0.000031	time 2.4041 (2.2209)	loss 6.8075 (6.8858)	grad_norm 0.9251 (1.0724)	
[2022-01-17 11:57:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][770/1251]	eta 0:17:48 lr 0.000032	time 2.1594 (2.2213)	loss 6.8210 (6.8851)	grad_norm 1.1485 (1.0717)	
[2022-01-17 11:58:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][780/1251]	eta 0:17:26 lr 0.000032	time 2.1848 (2.2215)	loss 6.8383 (6.8843)	grad_norm 1.0887 (1.0732)	
[2022-01-17 11:58:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][790/1251]	eta 0:17:04 lr 0.000033	time 2.8497 (2.2225)	loss 6.8223 (6.8835)	grad_norm 1.0493 (1.0737)	
[2022-01-17 11:58:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][800/1251]	eta 0:16:42 lr 0.000033	time 1.9332 (2.2221)	loss 6.8146 (6.8827)	grad_norm 1.1546 (1.0744)	
[2022-01-17 11:59:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][810/1251]	eta 0:16:20 lr 0.000033	time 2.1941 (2.2226)	loss 6.7751 (6.8817)	grad_norm 1.0375 (1.0757)	
[2022-01-17 11:59:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][820/1251]	eta 0:15:58 lr 0.000034	time 2.4293 (2.2236)	loss 6.8330 (6.8812)	grad_norm 1.2627 (1.0772)	
[2022-01-17 11:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][830/1251]	eta 0:15:36 lr 0.000034	time 2.2033 (2.2240)	loss 6.7534 (6.8802)	grad_norm 1.0934 (1.0776)	
[2022-01-17 12:00:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][840/1251]	eta 0:15:13 lr 0.000035	time 1.8039 (2.2231)	loss 6.8131 (6.8792)	grad_norm 2.0714 (1.0807)	
[2022-01-17 12:00:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][850/1251]	eta 0:14:51 lr 0.000035	time 2.8826 (2.2233)	loss 6.7812 (6.8783)	grad_norm 1.5309 (1.0844)	
[2022-01-17 12:00:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][860/1251]	eta 0:14:29 lr 0.000035	time 2.7543 (2.2226)	loss 6.8058 (6.8775)	grad_norm 1.0255 (1.0867)	
[2022-01-17 12:01:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][870/1251]	eta 0:14:05 lr 0.000036	time 1.6550 (2.2203)	loss 6.8421 (6.8768)	grad_norm 1.1984 (1.0879)	
[2022-01-17 12:01:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][880/1251]	eta 0:13:43 lr 0.000036	time 2.1377 (2.2192)	loss 6.8419 (6.8759)	grad_norm 1.1787 (1.0892)	
[2022-01-17 12:02:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][890/1251]	eta 0:13:20 lr 0.000037	time 2.9004 (2.2183)	loss 6.7417 (6.8751)	grad_norm 1.2225 (1.0924)	
[2022-01-17 12:02:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][900/1251]	eta 0:12:58 lr 0.000037	time 3.4258 (2.2194)	loss 6.8294 (6.8744)	grad_norm 1.4333 (1.0965)	
[2022-01-17 12:02:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][910/1251]	eta 0:12:36 lr 0.000037	time 2.1932 (2.2188)	loss 6.7953 (6.8735)	grad_norm 1.0544 (1.0977)	
[2022-01-17 12:03:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][920/1251]	eta 0:12:14 lr 0.000038	time 2.0588 (2.2204)	loss 6.8895 (6.8727)	grad_norm 1.1856 (1.0998)	
[2022-01-17 12:03:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][930/1251]	eta 0:11:53 lr 0.000038	time 2.8616 (2.2215)	loss 6.8233 (6.8719)	grad_norm 1.7534 (1.1034)	
[2022-01-17 12:03:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][940/1251]	eta 0:11:31 lr 0.000039	time 3.1263 (2.2238)	loss 6.8382 (6.8710)	grad_norm 1.4340 (1.1072)	
[2022-01-17 12:04:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][950/1251]	eta 0:11:09 lr 0.000039	time 2.7877 (2.2236)	loss 6.7169 (6.8700)	grad_norm 1.3574 (1.1119)	
[2022-01-17 12:04:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][960/1251]	eta 0:10:46 lr 0.000039	time 1.7530 (2.2224)	loss 6.7775 (6.8691)	grad_norm 1.1108 (1.1138)	
[2022-01-17 12:05:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][970/1251]	eta 0:10:23 lr 0.000040	time 2.1626 (2.2203)	loss 6.7836 (6.8681)	grad_norm 1.5968 (1.1173)	
[2022-01-17 12:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][980/1251]	eta 0:10:01 lr 0.000040	time 2.7274 (2.2196)	loss 6.7743 (6.8671)	grad_norm 1.2598 (1.1233)	
[2022-01-17 12:05:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][990/1251]	eta 0:09:38 lr 0.000041	time 1.7763 (2.2171)	loss 6.7943 (6.8666)	grad_norm 1.6440 (1.1299)	
[2022-01-17 12:06:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1000/1251]	eta 0:09:16 lr 0.000041	time 2.5136 (2.2177)	loss 6.7863 (6.8656)	grad_norm 0.9712 (1.1307)	
[2022-01-17 12:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1010/1251]	eta 0:08:54 lr 0.000041	time 1.8259 (2.2175)	loss 6.8560 (6.8648)	grad_norm 1.7870 (1.1363)	
[2022-01-17 12:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1020/1251]	eta 0:08:32 lr 0.000042	time 3.9841 (2.2196)	loss 6.8207 (6.8639)	grad_norm 1.7343 (1.1416)	
[2022-01-17 12:07:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1030/1251]	eta 0:08:10 lr 0.000042	time 2.0335 (2.2202)	loss 6.7343 (6.8628)	grad_norm 1.1745 (1.1443)	
[2022-01-17 12:07:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1040/1251]	eta 0:07:48 lr 0.000043	time 2.1322 (2.2202)	loss 6.7476 (6.8621)	grad_norm 1.8067 (1.1486)	
[2022-01-17 12:07:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1050/1251]	eta 0:07:26 lr 0.000043	time 2.1899 (2.2204)	loss 6.6715 (6.8610)	grad_norm 1.4136 (1.1523)	
[2022-01-17 12:08:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1060/1251]	eta 0:07:04 lr 0.000043	time 3.0617 (2.2209)	loss 6.6952 (6.8605)	grad_norm 1.2754 (1.1560)	
[2022-01-17 12:08:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1070/1251]	eta 0:06:42 lr 0.000044	time 1.9870 (2.2217)	loss 6.7939 (6.8595)	grad_norm 1.4323 (1.1569)	
[2022-01-17 12:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1080/1251]	eta 0:06:19 lr 0.000044	time 1.6826 (2.2207)	loss 6.7150 (6.8585)	grad_norm 1.7152 (1.1621)	
[2022-01-17 12:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1090/1251]	eta 0:05:57 lr 0.000045	time 1.6357 (2.2199)	loss 6.7551 (6.8575)	grad_norm 1.4268 (1.1661)	
[2022-01-17 12:09:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1100/1251]	eta 0:05:35 lr 0.000045	time 3.0517 (2.2195)	loss 6.8059 (6.8566)	grad_norm 1.3021 (1.1688)	
[2022-01-17 12:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1110/1251]	eta 0:05:13 lr 0.000045	time 2.5030 (2.2202)	loss 6.7829 (6.8556)	grad_norm 1.4590 (1.1706)	
[2022-01-17 12:10:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1120/1251]	eta 0:04:50 lr 0.000046	time 1.4934 (2.2202)	loss 6.6909 (6.8546)	grad_norm 1.2447 (1.1725)	
[2022-01-17 12:10:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1130/1251]	eta 0:04:28 lr 0.000046	time 1.7937 (2.2188)	loss 6.8565 (6.8541)	grad_norm 1.3894 (1.1771)	
[2022-01-17 12:11:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1140/1251]	eta 0:04:06 lr 0.000047	time 2.8733 (2.2189)	loss 6.5588 (6.8527)	grad_norm 1.4423 (1.1802)	
[2022-01-17 12:11:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1150/1251]	eta 0:03:44 lr 0.000047	time 2.3480 (2.2180)	loss 6.8164 (6.8516)	grad_norm 1.4281 (1.1817)	
[2022-01-17 12:11:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1160/1251]	eta 0:03:21 lr 0.000047	time 1.8742 (2.2165)	loss 6.8289 (6.8507)	grad_norm 1.6903 (1.1854)	
[2022-01-17 12:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1170/1251]	eta 0:02:59 lr 0.000048	time 1.9249 (2.2169)	loss 6.6973 (6.8496)	grad_norm 1.4087 (1.1899)	
[2022-01-17 12:12:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1180/1251]	eta 0:02:37 lr 0.000048	time 2.6965 (2.2178)	loss 6.7267 (6.8489)	grad_norm 2.9372 (1.1944)	
[2022-01-17 12:13:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1190/1251]	eta 0:02:15 lr 0.000049	time 1.9806 (2.2168)	loss 6.5701 (6.8482)	grad_norm 1.3548 (1.1982)	
[2022-01-17 12:13:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1200/1251]	eta 0:01:53 lr 0.000049	time 2.5255 (2.2169)	loss 6.7145 (6.8473)	grad_norm 1.6568 (1.1998)	
[2022-01-17 12:13:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1210/1251]	eta 0:01:30 lr 0.000049	time 1.5416 (2.2168)	loss 6.6036 (6.8461)	grad_norm 1.2999 (1.2015)	
[2022-01-17 12:14:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1220/1251]	eta 0:01:08 lr 0.000050	time 2.2592 (2.2163)	loss 6.6313 (6.8450)	grad_norm 1.6643 (1.2042)	
[2022-01-17 12:14:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1230/1251]	eta 0:00:46 lr 0.000050	time 2.5745 (2.2159)	loss 6.7628 (6.8441)	grad_norm 1.8887 (1.2106)	
[2022-01-17 12:14:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1240/1251]	eta 0:00:24 lr 0.000051	time 1.2218 (2.2147)	loss 6.7208 (6.8431)	grad_norm 2.7623 (1.2150)	
[2022-01-17 12:15:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [0/300][1250/1251]	eta 0:00:02 lr 0.000051	time 1.1838 (2.2095)	loss 6.7677 (6.8421)	grad_norm 1.4611 (1.2196)	
[2022-01-17 12:15:09 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 0 training takes 0:46:04
[2022-01-17 12:15:09 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_0 saving......
[2022-01-17 12:15:21 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_0 saved !!!
[2022-01-17 12:15:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.328 (16.328)	Loss 6.3492 (6.3492)	Acc@1 1.953 (1.953)	Acc@5 6.250 (6.250)	
[2022-01-17 12:15:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.586 (3.007)	Loss 6.3661 (6.3587)	Acc@1 2.441 (2.051)	Acc@5 6.934 (6.507)	
[2022-01-17 12:16:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.978 (2.279)	Loss 6.3665 (6.3547)	Acc@1 1.367 (1.990)	Acc@5 5.664 (6.599)	
[2022-01-17 12:16:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.899 (2.097)	Loss 6.3838 (6.3562)	Acc@1 1.270 (1.985)	Acc@5 5.469 (6.483)	
[2022-01-17 12:16:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.184 (2.070)	Loss 6.3439 (6.3546)	Acc@1 1.953 (1.927)	Acc@5 6.348 (6.388)	
[2022-01-17 12:16:53 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 1.906 Acc@5 6.346
[2022-01-17 12:16:53 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 1.9%
[2022-01-17 12:16:53 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 1.91%
[2022-01-17 12:17:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][0/1251]	eta 7:24:35 lr 0.000051	time 21.3235 (21.3235)	loss 6.7374 (6.7374)	grad_norm 1.8688 (1.8688)	
[2022-01-17 12:17:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][10/1251]	eta 1:24:17 lr 0.000051	time 2.2308 (4.0753)	loss 6.6237 (6.7088)	grad_norm 1.8322 (1.5825)	
[2022-01-17 12:17:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][20/1251]	eta 1:04:33 lr 0.000052	time 1.5905 (3.1466)	loss 6.5549 (6.7139)	grad_norm 1.3604 (1.6713)	
[2022-01-17 12:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][30/1251]	eta 1:00:38 lr 0.000052	time 1.5332 (2.9795)	loss 6.7097 (6.7279)	grad_norm 2.0439 (1.6501)	
[2022-01-17 12:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][40/1251]	eta 0:56:47 lr 0.000053	time 3.5093 (2.8139)	loss 6.6690 (6.7261)	grad_norm 2.2199 (1.6924)	
[2022-01-17 12:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][50/1251]	eta 0:54:40 lr 0.000053	time 2.5981 (2.7311)	loss 6.6186 (6.7203)	grad_norm 1.3876 (1.7200)	
[2022-01-17 12:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][60/1251]	eta 0:52:05 lr 0.000053	time 2.5021 (2.6239)	loss 6.7613 (6.7142)	grad_norm 1.7797 (1.6893)	
[2022-01-17 12:19:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][70/1251]	eta 0:49:38 lr 0.000054	time 1.6947 (2.5224)	loss 6.6262 (6.7067)	grad_norm 2.1279 (1.7867)	
[2022-01-17 12:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][80/1251]	eta 0:48:02 lr 0.000054	time 2.2482 (2.4613)	loss 6.5988 (6.7066)	grad_norm 1.5068 (1.7919)	
[2022-01-17 12:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][90/1251]	eta 0:46:54 lr 0.000055	time 1.8603 (2.4239)	loss 6.5621 (6.7053)	grad_norm 1.8589 (1.7821)	
[2022-01-17 12:20:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][100/1251]	eta 0:45:55 lr 0.000055	time 2.2801 (2.3940)	loss 6.7421 (6.7057)	grad_norm 2.9994 (1.8267)	
[2022-01-17 12:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][110/1251]	eta 0:45:09 lr 0.000055	time 2.0827 (2.3750)	loss 6.8022 (6.7063)	grad_norm 1.8858 (1.8650)	
[2022-01-17 12:21:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][120/1251]	eta 0:44:34 lr 0.000056	time 2.4648 (2.3644)	loss 6.7584 (6.7082)	grad_norm 1.8662 (1.8515)	
[2022-01-17 12:22:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][130/1251]	eta 0:44:13 lr 0.000056	time 2.5075 (2.3670)	loss 6.8087 (6.7089)	grad_norm 2.0508 (1.8567)	
[2022-01-17 12:22:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][140/1251]	eta 0:43:39 lr 0.000057	time 2.4060 (2.3575)	loss 6.5757 (6.7047)	grad_norm 1.6304 (1.8451)	
[2022-01-17 12:22:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][150/1251]	eta 0:43:07 lr 0.000057	time 2.0634 (2.3504)	loss 6.7041 (6.7041)	grad_norm 2.7975 (1.8623)	
[2022-01-17 12:23:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][160/1251]	eta 0:42:31 lr 0.000057	time 2.2138 (2.3388)	loss 6.6063 (6.7034)	grad_norm 1.4713 (1.8532)	
[2022-01-17 12:23:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][170/1251]	eta 0:41:56 lr 0.000058	time 1.7341 (2.3280)	loss 6.7059 (6.7023)	grad_norm 2.2371 (1.8604)	
[2022-01-17 12:23:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][180/1251]	eta 0:41:20 lr 0.000058	time 2.4556 (2.3159)	loss 6.7055 (6.6991)	grad_norm 1.6281 (1.8659)	
[2022-01-17 12:24:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][190/1251]	eta 0:40:47 lr 0.000059	time 1.8922 (2.3065)	loss 6.7315 (6.6973)	grad_norm 1.9626 (1.8647)	
[2022-01-17 12:24:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][200/1251]	eta 0:40:21 lr 0.000059	time 2.5287 (2.3036)	loss 6.7818 (6.6966)	grad_norm 2.1222 (1.8711)	
[2022-01-17 12:24:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][210/1251]	eta 0:39:56 lr 0.000059	time 1.8036 (2.3021)	loss 6.7210 (6.6945)	grad_norm 2.3918 (1.8912)	
[2022-01-17 12:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][220/1251]	eta 0:39:22 lr 0.000060	time 2.2240 (2.2914)	loss 6.7320 (6.6931)	grad_norm 1.5225 (1.8999)	
[2022-01-17 12:25:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][230/1251]	eta 0:38:51 lr 0.000060	time 2.4306 (2.2839)	loss 6.5655 (6.6894)	grad_norm 1.5700 (1.8942)	
[2022-01-17 12:26:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][240/1251]	eta 0:38:24 lr 0.000061	time 2.5068 (2.2794)	loss 6.6697 (6.6860)	grad_norm 2.5611 (1.8929)	
[2022-01-17 12:26:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][250/1251]	eta 0:38:00 lr 0.000061	time 1.9089 (2.2782)	loss 6.6188 (6.6826)	grad_norm 1.7194 (1.8900)	
[2022-01-17 12:26:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][260/1251]	eta 0:37:33 lr 0.000061	time 1.8311 (2.2738)	loss 6.7247 (6.6830)	grad_norm 1.8150 (1.8830)	
[2022-01-17 12:27:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][270/1251]	eta 0:37:02 lr 0.000062	time 2.4796 (2.2656)	loss 6.6909 (6.6821)	grad_norm 1.7594 (1.8845)	
[2022-01-17 12:27:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][280/1251]	eta 0:36:31 lr 0.000062	time 1.6710 (2.2569)	loss 6.7474 (6.6804)	grad_norm 1.4361 (1.8844)	
[2022-01-17 12:27:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][290/1251]	eta 0:36:05 lr 0.000063	time 1.5355 (2.2537)	loss 6.7259 (6.6794)	grad_norm 2.1460 (1.8892)	
[2022-01-17 12:28:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][300/1251]	eta 0:35:44 lr 0.000063	time 2.1769 (2.2551)	loss 6.4646 (6.6766)	grad_norm 2.0584 (1.8957)	
[2022-01-17 12:28:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][310/1251]	eta 0:35:22 lr 0.000063	time 1.7907 (2.2552)	loss 6.4370 (6.6743)	grad_norm 2.3378 (1.9043)	
[2022-01-17 12:28:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][320/1251]	eta 0:35:02 lr 0.000064	time 2.9106 (2.2578)	loss 6.6244 (6.6720)	grad_norm 2.0840 (1.9184)	
[2022-01-17 12:29:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][330/1251]	eta 0:34:40 lr 0.000064	time 1.8833 (2.2586)	loss 6.6459 (6.6697)	grad_norm 1.8554 (1.9210)	
[2022-01-17 12:29:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][340/1251]	eta 0:34:12 lr 0.000065	time 1.5949 (2.2536)	loss 6.7895 (6.6690)	grad_norm 1.6985 (1.9167)	
[2022-01-17 12:30:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][350/1251]	eta 0:33:51 lr 0.000065	time 3.2500 (2.2548)	loss 6.6213 (6.6682)	grad_norm 1.8489 (1.9177)	
[2022-01-17 12:30:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][360/1251]	eta 0:33:21 lr 0.000065	time 1.6727 (2.2464)	loss 6.6045 (6.6671)	grad_norm 2.0142 (1.9231)	
[2022-01-17 12:30:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][370/1251]	eta 0:32:54 lr 0.000066	time 1.7744 (2.2413)	loss 6.6344 (6.6654)	grad_norm 1.9103 (1.9260)	
[2022-01-17 12:31:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][380/1251]	eta 0:32:27 lr 0.000066	time 2.2166 (2.2364)	loss 6.5872 (6.6637)	grad_norm 2.6303 (1.9408)	
[2022-01-17 12:31:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][390/1251]	eta 0:32:06 lr 0.000067	time 2.4127 (2.2370)	loss 6.5122 (6.6625)	grad_norm 3.0101 (1.9537)	
[2022-01-17 12:31:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][400/1251]	eta 0:31:45 lr 0.000067	time 2.1698 (2.2387)	loss 6.6114 (6.6588)	grad_norm 1.9767 (1.9637)	
[2022-01-17 12:32:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][410/1251]	eta 0:31:25 lr 0.000067	time 2.2635 (2.2417)	loss 6.5666 (6.6564)	grad_norm 3.0086 (1.9742)	
[2022-01-17 12:32:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][420/1251]	eta 0:31:02 lr 0.000068	time 2.2301 (2.2407)	loss 6.3926 (6.6546)	grad_norm 2.1585 (1.9852)	
[2022-01-17 12:32:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][430/1251]	eta 0:30:35 lr 0.000068	time 1.8102 (2.2360)	loss 6.4865 (6.6539)	grad_norm 1.9955 (1.9891)	
[2022-01-17 12:33:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][440/1251]	eta 0:30:08 lr 0.000069	time 1.9393 (2.2302)	loss 6.6906 (6.6530)	grad_norm 1.7463 (2.0005)	
[2022-01-17 12:33:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][450/1251]	eta 0:29:45 lr 0.000069	time 2.0240 (2.2294)	loss 6.7230 (6.6530)	grad_norm 1.4486 (1.9985)	
[2022-01-17 12:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][460/1251]	eta 0:29:22 lr 0.000069	time 2.6309 (2.2276)	loss 6.6551 (6.6513)	grad_norm 1.8890 (1.9912)	
[2022-01-17 12:34:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][470/1251]	eta 0:29:01 lr 0.000070	time 2.4721 (2.2293)	loss 6.6411 (6.6495)	grad_norm 1.3069 (1.9868)	
[2022-01-17 12:34:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][480/1251]	eta 0:28:40 lr 0.000070	time 2.1661 (2.2313)	loss 6.7133 (6.6494)	grad_norm 2.6059 (1.9889)	
[2022-01-17 12:35:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][490/1251]	eta 0:28:19 lr 0.000071	time 2.3997 (2.2339)	loss 6.6574 (6.6474)	grad_norm 2.1737 (1.9911)	
[2022-01-17 12:35:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][500/1251]	eta 0:27:56 lr 0.000071	time 1.8543 (2.2323)	loss 6.6171 (6.6451)	grad_norm 1.8693 (1.9953)	
[2022-01-17 12:35:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][510/1251]	eta 0:27:32 lr 0.000071	time 1.5683 (2.2303)	loss 6.8204 (6.6439)	grad_norm 2.4490 (1.9997)	
[2022-01-17 12:36:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][520/1251]	eta 0:27:06 lr 0.000072	time 1.5920 (2.2246)	loss 6.4726 (6.6431)	grad_norm 2.3710 (2.0035)	
[2022-01-17 12:36:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][530/1251]	eta 0:26:41 lr 0.000072	time 1.8932 (2.2205)	loss 6.5907 (6.6424)	grad_norm 3.7026 (2.0070)	
[2022-01-17 12:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][540/1251]	eta 0:26:15 lr 0.000073	time 1.8931 (2.2158)	loss 6.6089 (6.6406)	grad_norm 1.7950 (2.0086)	
[2022-01-17 12:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][550/1251]	eta 0:25:50 lr 0.000073	time 1.9453 (2.2113)	loss 6.5888 (6.6403)	grad_norm 1.5923 (2.0065)	
[2022-01-17 12:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][560/1251]	eta 0:25:25 lr 0.000073	time 1.9154 (2.2076)	loss 6.5787 (6.6387)	grad_norm 2.6024 (2.0070)	
[2022-01-17 12:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][570/1251]	eta 0:25:03 lr 0.000074	time 2.1835 (2.2083)	loss 6.3538 (6.6381)	grad_norm 2.0001 (2.0036)	
[2022-01-17 12:38:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][580/1251]	eta 0:24:41 lr 0.000074	time 2.3688 (2.2076)	loss 6.6621 (6.6374)	grad_norm 1.9791 (2.0054)	
[2022-01-17 12:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][590/1251]	eta 0:24:20 lr 0.000075	time 2.4740 (2.2093)	loss 6.4101 (6.6358)	grad_norm 2.5187 (2.0093)	
[2022-01-17 12:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][600/1251]	eta 0:23:58 lr 0.000075	time 2.2339 (2.2094)	loss 6.4303 (6.6332)	grad_norm 2.0469 (2.0135)	
[2022-01-17 12:39:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][610/1251]	eta 0:23:38 lr 0.000075	time 2.1297 (2.2134)	loss 6.6873 (6.6324)	grad_norm 1.7390 (2.0114)	
[2022-01-17 12:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][620/1251]	eta 0:23:17 lr 0.000076	time 2.4600 (2.2148)	loss 6.4341 (6.6299)	grad_norm 2.3526 (2.0118)	
[2022-01-17 12:40:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][630/1251]	eta 0:22:56 lr 0.000076	time 2.3920 (2.2160)	loss 6.7262 (6.6305)	grad_norm 1.8241 (2.0137)	
[2022-01-17 12:40:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][640/1251]	eta 0:22:34 lr 0.000077	time 2.6184 (2.2173)	loss 6.3369 (6.6280)	grad_norm 2.0823 (2.0144)	
[2022-01-17 12:40:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][650/1251]	eta 0:22:12 lr 0.000077	time 1.9021 (2.2175)	loss 6.6244 (6.6268)	grad_norm 2.5329 (2.0135)	
[2022-01-17 12:41:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][660/1251]	eta 0:21:49 lr 0.000077	time 2.5215 (2.2160)	loss 6.6058 (6.6261)	grad_norm 1.8910 (2.0136)	
[2022-01-17 12:41:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][670/1251]	eta 0:21:26 lr 0.000078	time 1.8871 (2.2143)	loss 6.5769 (6.6230)	grad_norm 2.3330 (2.0152)	
[2022-01-17 12:42:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][680/1251]	eta 0:21:04 lr 0.000078	time 2.6492 (2.2150)	loss 6.4053 (6.6217)	grad_norm 2.5586 (2.0176)	
[2022-01-17 12:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][690/1251]	eta 0:20:42 lr 0.000079	time 1.8468 (2.2154)	loss 6.6489 (6.6200)	grad_norm 2.6546 (2.0230)	
[2022-01-17 12:42:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][700/1251]	eta 0:20:20 lr 0.000079	time 2.5738 (2.2153)	loss 6.5779 (6.6178)	grad_norm 2.0137 (2.0237)	
[2022-01-17 12:43:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][710/1251]	eta 0:19:57 lr 0.000079	time 1.8670 (2.2128)	loss 6.7420 (6.6171)	grad_norm 1.7625 (2.0233)	
[2022-01-17 12:43:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][720/1251]	eta 0:19:34 lr 0.000080	time 2.1124 (2.2119)	loss 6.6187 (6.6150)	grad_norm 1.6568 (2.0231)	
[2022-01-17 12:43:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][730/1251]	eta 0:19:11 lr 0.000080	time 1.8959 (2.2111)	loss 6.4005 (6.6135)	grad_norm 2.3622 (2.0240)	
[2022-01-17 12:44:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][740/1251]	eta 0:18:49 lr 0.000080	time 2.5087 (2.2107)	loss 6.4866 (6.6121)	grad_norm 1.9049 (2.0283)	
[2022-01-17 12:44:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][750/1251]	eta 0:18:26 lr 0.000081	time 1.6922 (2.2093)	loss 6.3392 (6.6103)	grad_norm 2.8887 (2.0349)	
[2022-01-17 12:44:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][760/1251]	eta 0:18:03 lr 0.000081	time 1.7936 (2.2074)	loss 6.5721 (6.6102)	grad_norm 2.2989 (2.0378)	
[2022-01-17 12:45:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][770/1251]	eta 0:17:40 lr 0.000082	time 2.4050 (2.2052)	loss 6.6123 (6.6086)	grad_norm 1.8330 (2.0408)	
[2022-01-17 12:45:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][780/1251]	eta 0:17:18 lr 0.000082	time 2.2357 (2.2044)	loss 6.6570 (6.6080)	grad_norm 1.7335 (2.0389)	
[2022-01-17 12:45:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][790/1251]	eta 0:16:56 lr 0.000082	time 1.9873 (2.2040)	loss 6.5070 (6.6071)	grad_norm 2.1053 (2.0381)	
[2022-01-17 12:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][800/1251]	eta 0:16:33 lr 0.000083	time 1.9167 (2.2038)	loss 6.6985 (6.6057)	grad_norm 1.9108 (2.0388)	
[2022-01-17 12:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][810/1251]	eta 0:16:12 lr 0.000083	time 2.5270 (2.2053)	loss 6.2856 (6.6035)	grad_norm 1.4168 (2.0391)	
[2022-01-17 12:47:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][820/1251]	eta 0:15:50 lr 0.000084	time 2.7353 (2.2064)	loss 6.5686 (6.6031)	grad_norm 1.6949 (2.0404)	
[2022-01-17 12:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][830/1251]	eta 0:15:28 lr 0.000084	time 1.7085 (2.2062)	loss 6.2973 (6.6006)	grad_norm 3.0217 (2.0417)	
[2022-01-17 12:47:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][840/1251]	eta 0:15:07 lr 0.000084	time 2.4792 (2.2074)	loss 6.1724 (6.6000)	grad_norm 1.9837 (2.0427)	
[2022-01-17 12:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][850/1251]	eta 0:14:44 lr 0.000085	time 2.0323 (2.2049)	loss 6.5539 (6.5990)	grad_norm 2.4230 (2.0434)	
[2022-01-17 12:48:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][860/1251]	eta 0:14:21 lr 0.000085	time 3.0305 (2.2043)	loss 6.3338 (6.5982)	grad_norm 2.4156 (2.0439)	
[2022-01-17 12:48:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][870/1251]	eta 0:13:59 lr 0.000086	time 2.2192 (2.2034)	loss 6.3225 (6.5969)	grad_norm 2.1724 (2.0452)	
[2022-01-17 12:49:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][880/1251]	eta 0:13:37 lr 0.000086	time 2.2545 (2.2024)	loss 6.5542 (6.5961)	grad_norm 2.8476 (2.0486)	
[2022-01-17 12:49:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][890/1251]	eta 0:13:15 lr 0.000086	time 2.0136 (2.2031)	loss 6.6771 (6.5957)	grad_norm 1.9260 (2.0499)	
[2022-01-17 12:50:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][900/1251]	eta 0:12:54 lr 0.000087	time 3.1947 (2.2073)	loss 6.5893 (6.5945)	grad_norm 1.7046 (2.0510)	
[2022-01-17 12:50:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][910/1251]	eta 0:12:32 lr 0.000087	time 2.4176 (2.2075)	loss 6.5157 (6.5942)	grad_norm 2.9465 (2.0550)	
[2022-01-17 12:50:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][920/1251]	eta 0:12:10 lr 0.000088	time 2.8599 (2.2069)	loss 6.3053 (6.5931)	grad_norm 1.8315 (2.0564)	
[2022-01-17 12:51:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][930/1251]	eta 0:11:47 lr 0.000088	time 1.5964 (2.2043)	loss 6.5693 (6.5921)	grad_norm 1.6841 (2.0575)	
[2022-01-17 12:51:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][940/1251]	eta 0:11:25 lr 0.000088	time 2.1523 (2.2030)	loss 6.3091 (6.5918)	grad_norm 2.8240 (2.0623)	
[2022-01-17 12:51:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][950/1251]	eta 0:11:02 lr 0.000089	time 1.5519 (2.2022)	loss 6.5532 (6.5906)	grad_norm 1.6411 (2.0635)	
[2022-01-17 12:52:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][960/1251]	eta 0:10:40 lr 0.000089	time 2.3329 (2.2014)	loss 6.6207 (6.5887)	grad_norm 1.6457 (2.0634)	
[2022-01-17 12:52:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][970/1251]	eta 0:10:18 lr 0.000090	time 1.8332 (2.2021)	loss 6.4155 (6.5873)	grad_norm 2.2048 (2.0675)	
[2022-01-17 12:52:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][980/1251]	eta 0:09:57 lr 0.000090	time 2.9776 (2.2040)	loss 6.1376 (6.5857)	grad_norm 2.1471 (2.0687)	
[2022-01-17 12:53:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][990/1251]	eta 0:09:35 lr 0.000090	time 2.0184 (2.2053)	loss 6.5403 (6.5846)	grad_norm 2.3022 (2.0727)	
[2022-01-17 12:53:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1000/1251]	eta 0:09:13 lr 0.000091	time 2.8156 (2.2064)	loss 6.5444 (6.5828)	grad_norm 2.0627 (2.0720)	
[2022-01-17 12:54:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1010/1251]	eta 0:08:51 lr 0.000091	time 1.7147 (2.2060)	loss 6.4939 (6.5810)	grad_norm 2.0402 (2.0741)	
[2022-01-17 12:54:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1020/1251]	eta 0:08:29 lr 0.000092	time 1.9744 (2.2041)	loss 6.5488 (6.5799)	grad_norm 2.1957 (2.0745)	
[2022-01-17 12:54:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1030/1251]	eta 0:08:06 lr 0.000092	time 2.0804 (2.2017)	loss 6.6196 (6.5791)	grad_norm 1.8802 (2.0754)	
[2022-01-17 12:55:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1040/1251]	eta 0:07:44 lr 0.000092	time 2.0361 (2.2001)	loss 6.4635 (6.5775)	grad_norm 1.8814 (2.0742)	
[2022-01-17 12:55:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1050/1251]	eta 0:07:22 lr 0.000093	time 2.8057 (2.2013)	loss 6.2532 (6.5758)	grad_norm 1.7462 (2.0731)	
[2022-01-17 12:55:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1060/1251]	eta 0:07:00 lr 0.000093	time 1.9750 (2.2007)	loss 6.5543 (6.5745)	grad_norm 2.1956 (2.0737)	
[2022-01-17 12:56:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1070/1251]	eta 0:06:38 lr 0.000094	time 2.5649 (2.1998)	loss 6.5112 (6.5738)	grad_norm 2.4456 (2.0731)	
[2022-01-17 12:56:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1080/1251]	eta 0:06:16 lr 0.000094	time 1.9868 (2.2003)	loss 6.6772 (6.5732)	grad_norm 2.6420 (2.0734)	
[2022-01-17 12:56:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1090/1251]	eta 0:05:54 lr 0.000094	time 3.0991 (2.2028)	loss 6.5221 (6.5720)	grad_norm 2.9456 (2.0768)	
[2022-01-17 12:57:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1100/1251]	eta 0:05:32 lr 0.000095	time 2.1886 (2.2032)	loss 6.4451 (6.5708)	grad_norm 1.6719 (2.0781)	
[2022-01-17 12:57:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1110/1251]	eta 0:05:10 lr 0.000095	time 2.1863 (2.2027)	loss 6.4392 (6.5691)	grad_norm 1.5909 (2.0775)	
[2022-01-17 12:58:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1120/1251]	eta 0:04:48 lr 0.000096	time 1.7037 (2.2016)	loss 6.5028 (6.5678)	grad_norm 1.9155 (2.0775)	
[2022-01-17 12:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1130/1251]	eta 0:04:26 lr 0.000096	time 3.3649 (2.2009)	loss 6.5155 (6.5670)	grad_norm 1.8500 (2.0773)	
[2022-01-17 12:58:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1140/1251]	eta 0:04:04 lr 0.000096	time 2.0959 (2.2004)	loss 6.2647 (6.5650)	grad_norm 1.9159 (2.0795)	
[2022-01-17 12:59:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1150/1251]	eta 0:03:42 lr 0.000097	time 2.7886 (2.2005)	loss 6.7838 (6.5640)	grad_norm 2.2370 (2.0804)	
[2022-01-17 12:59:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1160/1251]	eta 0:03:20 lr 0.000097	time 2.2083 (2.2016)	loss 6.3367 (6.5634)	grad_norm 3.1751 (2.0843)	
[2022-01-17 12:59:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1170/1251]	eta 0:02:58 lr 0.000098	time 2.4838 (2.2015)	loss 6.1234 (6.5620)	grad_norm 2.1873 (2.0880)	
[2022-01-17 13:00:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1180/1251]	eta 0:02:36 lr 0.000098	time 1.9059 (2.2020)	loss 6.4147 (6.5615)	grad_norm 2.0800 (2.0885)	
[2022-01-17 13:00:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1190/1251]	eta 0:02:14 lr 0.000098	time 2.2381 (2.2004)	loss 6.3409 (6.5606)	grad_norm 1.6070 (2.0894)	
[2022-01-17 13:00:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1200/1251]	eta 0:01:52 lr 0.000099	time 1.5490 (2.1989)	loss 6.5680 (6.5597)	grad_norm 1.8068 (2.0874)	
[2022-01-17 13:01:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1210/1251]	eta 0:01:30 lr 0.000099	time 2.3943 (2.1980)	loss 5.9899 (6.5581)	grad_norm 2.0899 (2.0855)	
[2022-01-17 13:01:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1220/1251]	eta 0:01:08 lr 0.000100	time 2.2145 (2.1965)	loss 6.1918 (6.5568)	grad_norm 1.9121 (2.0855)	
[2022-01-17 13:01:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1230/1251]	eta 0:00:46 lr 0.000100	time 1.8032 (2.1962)	loss 6.2067 (6.5554)	grad_norm 2.5528 (2.0875)	
[2022-01-17 13:02:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1240/1251]	eta 0:00:24 lr 0.000100	time 1.8636 (2.1956)	loss 6.5622 (6.5552)	grad_norm 2.6270 (2.0896)	
[2022-01-17 13:02:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [1/300][1250/1251]	eta 0:00:02 lr 0.000101	time 1.1541 (2.1904)	loss 6.1182 (6.5538)	grad_norm 2.4095 (2.0899)	
[2022-01-17 13:02:33 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 1 training takes 0:45:40
[2022-01-17 13:02:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.066 (19.066)	Loss 5.5691 (5.5691)	Acc@1 6.055 (6.055)	Acc@5 18.457 (18.457)	
[2022-01-17 13:03:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.906 (3.481)	Loss 5.5324 (5.5855)	Acc@1 6.250 (5.975)	Acc@5 18.652 (17.241)	
[2022-01-17 13:03:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.622 (2.577)	Loss 5.5407 (5.5771)	Acc@1 5.469 (6.055)	Acc@5 16.699 (17.411)	
[2022-01-17 13:03:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.311 (2.239)	Loss 5.5345 (5.5758)	Acc@1 6.055 (6.127)	Acc@5 19.238 (17.566)	
[2022-01-17 13:04:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.247 (2.195)	Loss 5.5630 (5.5774)	Acc@1 6.934 (6.086)	Acc@5 19.043 (17.554)	
[2022-01-17 13:04:10 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 6.130 Acc@5 17.586
[2022-01-17 13:04:10 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 6.1%
[2022-01-17 13:04:10 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 6.13%
[2022-01-17 13:04:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][0/1251]	eta 7:26:28 lr 0.000101	time 21.4133 (21.4133)	loss 6.3458 (6.3458)	grad_norm 1.9607 (1.9607)	
[2022-01-17 13:04:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][10/1251]	eta 1:24:14 lr 0.000101	time 2.7715 (4.0728)	loss 6.0914 (6.3848)	grad_norm 1.8630 (1.9969)	
[2022-01-17 13:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][20/1251]	eta 1:03:06 lr 0.000102	time 1.6489 (3.0763)	loss 6.0360 (6.4134)	grad_norm 1.7637 (2.1185)	
[2022-01-17 13:05:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][30/1251]	eta 0:57:25 lr 0.000102	time 1.9747 (2.8215)	loss 6.2893 (6.4262)	grad_norm 2.2892 (2.2225)	
[2022-01-17 13:06:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][40/1251]	eta 0:54:56 lr 0.000102	time 3.9113 (2.7225)	loss 6.7766 (6.4287)	grad_norm 2.3902 (2.2425)	
[2022-01-17 13:06:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][50/1251]	eta 0:52:43 lr 0.000103	time 2.5142 (2.6343)	loss 6.5887 (6.4381)	grad_norm 2.1967 (2.2568)	
[2022-01-17 13:06:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][60/1251]	eta 0:50:36 lr 0.000103	time 1.8507 (2.5498)	loss 6.5163 (6.4596)	grad_norm 1.5956 (2.2305)	
[2022-01-17 13:07:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][70/1251]	eta 0:48:49 lr 0.000104	time 1.8646 (2.4801)	loss 6.3794 (6.4591)	grad_norm 2.3347 (2.2684)	
[2022-01-17 13:07:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][80/1251]	eta 0:47:47 lr 0.000104	time 3.1579 (2.4491)	loss 6.5605 (6.4605)	grad_norm 2.5240 (2.3062)	
[2022-01-17 13:07:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][90/1251]	eta 0:47:10 lr 0.000104	time 2.8214 (2.4383)	loss 6.5088 (6.4535)	grad_norm 1.7022 (2.2865)	
[2022-01-17 13:08:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][100/1251]	eta 0:46:39 lr 0.000105	time 1.8039 (2.4321)	loss 6.2612 (6.4522)	grad_norm 1.6106 (2.2680)	
[2022-01-17 13:08:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][110/1251]	eta 0:45:55 lr 0.000105	time 2.1984 (2.4148)	loss 6.2502 (6.4377)	grad_norm 2.7149 (2.2513)	
[2022-01-17 13:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][120/1251]	eta 0:45:15 lr 0.000106	time 2.8102 (2.4010)	loss 6.5874 (6.4430)	grad_norm 2.7745 (2.2589)	
[2022-01-17 13:09:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][130/1251]	eta 0:44:24 lr 0.000106	time 1.5179 (2.3771)	loss 6.6544 (6.4412)	grad_norm 2.7064 (2.2551)	
[2022-01-17 13:09:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][140/1251]	eta 0:43:53 lr 0.000106	time 2.2130 (2.3702)	loss 6.4211 (6.4444)	grad_norm 2.4028 (2.2518)	
[2022-01-17 13:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][150/1251]	eta 0:43:19 lr 0.000107	time 2.3115 (2.3610)	loss 6.0093 (6.4366)	grad_norm 2.1871 (2.2641)	
[2022-01-17 13:10:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][160/1251]	eta 0:42:50 lr 0.000107	time 3.1828 (2.3561)	loss 6.3227 (6.4368)	grad_norm 1.8329 (2.2388)	
[2022-01-17 13:10:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][170/1251]	eta 0:42:02 lr 0.000108	time 1.5574 (2.3338)	loss 6.4917 (6.4352)	grad_norm 3.8427 (2.2430)	
[2022-01-17 13:11:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][180/1251]	eta 0:41:15 lr 0.000108	time 1.9258 (2.3118)	loss 6.4134 (6.4353)	grad_norm 2.4982 (2.2411)	
[2022-01-17 13:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][190/1251]	eta 0:40:36 lr 0.000108	time 2.1747 (2.2963)	loss 6.2148 (6.4352)	grad_norm 1.7787 (2.2322)	
[2022-01-17 13:11:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][200/1251]	eta 0:40:03 lr 0.000109	time 2.6352 (2.2872)	loss 6.4968 (6.4371)	grad_norm 2.4927 (2.2210)	
[2022-01-17 13:12:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][210/1251]	eta 0:39:36 lr 0.000109	time 1.9597 (2.2827)	loss 6.2971 (6.4383)	grad_norm 2.0584 (2.2118)	
[2022-01-17 13:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][220/1251]	eta 0:39:08 lr 0.000110	time 1.8669 (2.2782)	loss 6.4006 (6.4332)	grad_norm 1.8240 (2.2049)	
[2022-01-17 13:12:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][230/1251]	eta 0:38:52 lr 0.000110	time 2.5718 (2.2844)	loss 6.6034 (6.4339)	grad_norm 1.8213 (2.2059)	
[2022-01-17 13:13:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][240/1251]	eta 0:38:25 lr 0.000110	time 2.9376 (2.2803)	loss 6.6177 (6.4270)	grad_norm 2.5815 (2.2068)	
[2022-01-17 13:13:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][250/1251]	eta 0:38:02 lr 0.000111	time 2.1807 (2.2804)	loss 6.0645 (6.4229)	grad_norm 2.9309 (2.1968)	
[2022-01-17 13:14:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][260/1251]	eta 0:37:37 lr 0.000111	time 1.8559 (2.2775)	loss 6.6067 (6.4202)	grad_norm 2.3140 (2.2012)	
[2022-01-17 13:14:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][270/1251]	eta 0:37:10 lr 0.000112	time 2.8528 (2.2734)	loss 6.5715 (6.4218)	grad_norm 2.0624 (2.2061)	
[2022-01-17 13:14:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][280/1251]	eta 0:36:41 lr 0.000112	time 2.2453 (2.2670)	loss 6.5644 (6.4186)	grad_norm 2.1359 (2.2039)	
[2022-01-17 13:15:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][290/1251]	eta 0:36:14 lr 0.000112	time 2.0607 (2.2627)	loss 6.2211 (6.4130)	grad_norm 2.1577 (2.2096)	
[2022-01-17 13:15:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][300/1251]	eta 0:35:46 lr 0.000113	time 1.7128 (2.2567)	loss 6.5551 (6.4130)	grad_norm 2.3243 (2.2131)	
[2022-01-17 13:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][310/1251]	eta 0:35:27 lr 0.000113	time 3.8468 (2.2610)	loss 6.4100 (6.4111)	grad_norm 2.1234 (2.2140)	
[2022-01-17 13:16:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][320/1251]	eta 0:34:59 lr 0.000114	time 2.2824 (2.2549)	loss 6.3793 (6.4104)	grad_norm 1.9561 (2.2127)	
[2022-01-17 13:16:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][330/1251]	eta 0:34:33 lr 0.000114	time 2.4237 (2.2508)	loss 6.4117 (6.4073)	grad_norm 2.1385 (2.2123)	
[2022-01-17 13:16:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][340/1251]	eta 0:34:08 lr 0.000114	time 1.8622 (2.2486)	loss 6.1039 (6.4036)	grad_norm 2.2297 (2.2085)	
[2022-01-17 13:17:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][350/1251]	eta 0:33:47 lr 0.000115	time 3.4931 (2.2507)	loss 6.3121 (6.4015)	grad_norm 1.8886 (2.2008)	
[2022-01-17 13:17:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][360/1251]	eta 0:33:24 lr 0.000115	time 2.5658 (2.2500)	loss 6.0480 (6.3926)	grad_norm 2.7371 (2.1970)	
[2022-01-17 13:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][370/1251]	eta 0:32:57 lr 0.000116	time 1.7652 (2.2443)	loss 6.4611 (6.3913)	grad_norm 2.6611 (2.2046)	
[2022-01-17 13:18:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][380/1251]	eta 0:32:32 lr 0.000116	time 1.8275 (2.2414)	loss 6.2759 (6.3905)	grad_norm 2.2976 (2.2074)	
[2022-01-17 13:18:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][390/1251]	eta 0:32:09 lr 0.000116	time 2.9100 (2.2405)	loss 6.5498 (6.3882)	grad_norm 2.2403 (2.2058)	
[2022-01-17 13:19:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][400/1251]	eta 0:31:40 lr 0.000117	time 1.6855 (2.2335)	loss 5.9851 (6.3878)	grad_norm 2.1233 (2.2033)	
[2022-01-17 13:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][410/1251]	eta 0:31:18 lr 0.000117	time 2.2001 (2.2340)	loss 6.6950 (6.3864)	grad_norm 2.0945 (2.2003)	
[2022-01-17 13:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][420/1251]	eta 0:30:56 lr 0.000118	time 2.6886 (2.2341)	loss 6.4724 (6.3859)	grad_norm 2.3738 (2.2057)	
[2022-01-17 13:20:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][430/1251]	eta 0:30:35 lr 0.000118	time 3.5313 (2.2354)	loss 6.1456 (6.3852)	grad_norm 2.0220 (2.2059)	
[2022-01-17 13:20:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][440/1251]	eta 0:30:10 lr 0.000118	time 1.6427 (2.2319)	loss 6.0655 (6.3860)	grad_norm 2.5804 (2.2002)	
[2022-01-17 13:20:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][450/1251]	eta 0:29:46 lr 0.000119	time 1.5559 (2.2305)	loss 6.4771 (6.3837)	grad_norm 1.9426 (2.1957)	
[2022-01-17 13:21:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][460/1251]	eta 0:29:22 lr 0.000119	time 2.2595 (2.2285)	loss 6.2103 (6.3814)	grad_norm 1.8235 (2.1940)	
[2022-01-17 13:21:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][470/1251]	eta 0:29:01 lr 0.000120	time 3.6258 (2.2303)	loss 6.0681 (6.3811)	grad_norm 2.7602 (2.2010)	
[2022-01-17 13:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][480/1251]	eta 0:28:38 lr 0.000120	time 1.7461 (2.2284)	loss 6.0721 (6.3791)	grad_norm 2.6739 (2.2097)	
[2022-01-17 13:22:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][490/1251]	eta 0:28:16 lr 0.000120	time 1.5978 (2.2291)	loss 6.4452 (6.3799)	grad_norm 1.9162 (2.2111)	
[2022-01-17 13:22:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][500/1251]	eta 0:27:53 lr 0.000121	time 1.8838 (2.2278)	loss 6.5470 (6.3783)	grad_norm 2.3179 (2.2157)	
[2022-01-17 13:23:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][510/1251]	eta 0:27:29 lr 0.000121	time 3.7673 (2.2266)	loss 6.5172 (6.3775)	grad_norm 2.5552 (2.2168)	
[2022-01-17 13:23:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][520/1251]	eta 0:27:04 lr 0.000122	time 1.5808 (2.2230)	loss 6.3721 (6.3760)	grad_norm 2.1845 (2.2142)	
[2022-01-17 13:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][530/1251]	eta 0:26:42 lr 0.000122	time 1.8921 (2.2220)	loss 6.3890 (6.3736)	grad_norm 2.1136 (2.2081)	
[2022-01-17 13:24:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][540/1251]	eta 0:26:19 lr 0.000122	time 1.7346 (2.2215)	loss 6.3629 (6.3729)	grad_norm 1.7970 (2.2045)	
[2022-01-17 13:24:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][550/1251]	eta 0:25:57 lr 0.000123	time 3.1474 (2.2218)	loss 6.2083 (6.3732)	grad_norm 2.2937 (2.2029)	
[2022-01-17 13:24:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][560/1251]	eta 0:25:34 lr 0.000123	time 2.3206 (2.2207)	loss 5.9915 (6.3709)	grad_norm 1.8549 (2.2024)	
[2022-01-17 13:25:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][570/1251]	eta 0:25:11 lr 0.000124	time 1.8540 (2.2197)	loss 6.4360 (6.3703)	grad_norm 2.0172 (2.2033)	
[2022-01-17 13:25:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][580/1251]	eta 0:24:48 lr 0.000124	time 1.8476 (2.2187)	loss 5.9684 (6.3684)	grad_norm 2.4215 (2.2082)	
[2022-01-17 13:26:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][590/1251]	eta 0:24:26 lr 0.000124	time 2.8373 (2.2182)	loss 6.3663 (6.3684)	grad_norm 2.4359 (2.2099)	
[2022-01-17 13:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][600/1251]	eta 0:24:03 lr 0.000125	time 1.8865 (2.2173)	loss 6.1042 (6.3674)	grad_norm 1.6850 (2.2052)	
[2022-01-17 13:26:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][610/1251]	eta 0:23:41 lr 0.000125	time 2.1892 (2.2183)	loss 6.0415 (6.3669)	grad_norm 1.9600 (2.2019)	
[2022-01-17 13:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][620/1251]	eta 0:23:19 lr 0.000126	time 2.4914 (2.2183)	loss 6.3459 (6.3667)	grad_norm 2.1736 (2.2014)	
[2022-01-17 13:27:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][630/1251]	eta 0:22:57 lr 0.000126	time 3.0355 (2.2175)	loss 6.5097 (6.3659)	grad_norm 2.4284 (2.2027)	
[2022-01-17 13:27:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][640/1251]	eta 0:22:34 lr 0.000126	time 1.8610 (2.2168)	loss 6.3689 (6.3622)	grad_norm 2.6940 (2.2025)	
[2022-01-17 13:28:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][650/1251]	eta 0:22:12 lr 0.000127	time 1.8851 (2.2163)	loss 6.6025 (6.3622)	grad_norm 3.4166 (2.2067)	
[2022-01-17 13:28:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][660/1251]	eta 0:21:48 lr 0.000127	time 1.8848 (2.2147)	loss 6.4497 (6.3604)	grad_norm 1.8841 (2.2092)	
[2022-01-17 13:28:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][670/1251]	eta 0:21:26 lr 0.000128	time 3.0473 (2.2140)	loss 6.4633 (6.3601)	grad_norm 2.7840 (2.2100)	
[2022-01-17 13:29:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][680/1251]	eta 0:21:03 lr 0.000128	time 1.7688 (2.2127)	loss 5.9140 (6.3591)	grad_norm 2.2367 (2.2128)	
[2022-01-17 13:29:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][690/1251]	eta 0:20:41 lr 0.000128	time 1.5538 (2.2130)	loss 6.3809 (6.3573)	grad_norm 1.9575 (2.2110)	
[2022-01-17 13:30:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][700/1251]	eta 0:20:18 lr 0.000129	time 1.9188 (2.2117)	loss 6.5380 (6.3575)	grad_norm 2.3468 (2.2124)	
[2022-01-17 13:30:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][710/1251]	eta 0:19:56 lr 0.000129	time 2.7906 (2.2108)	loss 6.2922 (6.3569)	grad_norm 1.8198 (2.2125)	
[2022-01-17 13:30:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][720/1251]	eta 0:19:33 lr 0.000130	time 1.6657 (2.2107)	loss 6.1224 (6.3551)	grad_norm 1.9828 (2.2106)	
[2022-01-17 13:31:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][730/1251]	eta 0:19:12 lr 0.000130	time 1.8487 (2.2112)	loss 6.3707 (6.3559)	grad_norm 2.3448 (2.2144)	
[2022-01-17 13:31:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][740/1251]	eta 0:18:49 lr 0.000130	time 2.8402 (2.2113)	loss 5.8608 (6.3563)	grad_norm 2.5428 (2.2183)	
[2022-01-17 13:31:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][750/1251]	eta 0:18:25 lr 0.000131	time 1.6320 (2.2073)	loss 5.8724 (6.3555)	grad_norm 2.6067 (2.2195)	
[2022-01-17 13:32:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][760/1251]	eta 0:18:03 lr 0.000131	time 2.1155 (2.2060)	loss 6.6096 (6.3554)	grad_norm 1.8600 (2.2182)	
[2022-01-17 13:32:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][770/1251]	eta 0:17:40 lr 0.000132	time 2.2403 (2.2052)	loss 6.2900 (6.3532)	grad_norm 1.8054 (2.2150)	
[2022-01-17 13:32:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][780/1251]	eta 0:17:19 lr 0.000132	time 2.9238 (2.2060)	loss 6.4764 (6.3521)	grad_norm 2.0401 (2.2138)	
[2022-01-17 13:33:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][790/1251]	eta 0:16:57 lr 0.000132	time 2.4944 (2.2068)	loss 6.3842 (6.3513)	grad_norm 2.0233 (2.2123)	
[2022-01-17 13:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][800/1251]	eta 0:16:34 lr 0.000133	time 1.8512 (2.2049)	loss 6.3549 (6.3506)	grad_norm 1.9245 (2.2093)	
[2022-01-17 13:33:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][810/1251]	eta 0:16:11 lr 0.000133	time 2.1493 (2.2040)	loss 6.2937 (6.3500)	grad_norm 2.0616 (2.2096)	
[2022-01-17 13:34:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][820/1251]	eta 0:15:50 lr 0.000134	time 2.6125 (2.2044)	loss 5.7162 (6.3486)	grad_norm 2.8874 (2.2130)	
[2022-01-17 13:34:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][830/1251]	eta 0:15:28 lr 0.000134	time 2.7984 (2.2056)	loss 6.2469 (6.3463)	grad_norm 2.6614 (2.2141)	
[2022-01-17 13:35:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][840/1251]	eta 0:15:06 lr 0.000134	time 1.8532 (2.2061)	loss 6.3413 (6.3440)	grad_norm 1.7807 (2.2135)	
[2022-01-17 13:35:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][850/1251]	eta 0:14:45 lr 0.000135	time 3.3415 (2.2086)	loss 6.5954 (6.3441)	grad_norm 2.6934 (2.2143)	
[2022-01-17 13:35:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][860/1251]	eta 0:14:23 lr 0.000135	time 1.8660 (2.2082)	loss 6.4170 (6.3422)	grad_norm 1.9757 (2.2146)	
[2022-01-17 13:36:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][870/1251]	eta 0:14:00 lr 0.000136	time 1.7709 (2.2056)	loss 6.0991 (6.3404)	grad_norm 2.5849 (2.2154)	
[2022-01-17 13:36:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][880/1251]	eta 0:13:37 lr 0.000136	time 1.9240 (2.2037)	loss 6.7088 (6.3407)	grad_norm 3.0104 (2.2175)	
[2022-01-17 13:36:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][890/1251]	eta 0:13:15 lr 0.000136	time 2.3135 (2.2036)	loss 6.1014 (6.3407)	grad_norm 2.1602 (2.2187)	
[2022-01-17 13:37:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][900/1251]	eta 0:12:53 lr 0.000137	time 1.8367 (2.2031)	loss 6.3978 (6.3384)	grad_norm 2.6030 (2.2186)	
[2022-01-17 13:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][910/1251]	eta 0:12:30 lr 0.000137	time 2.2345 (2.2020)	loss 6.1815 (6.3373)	grad_norm 2.3201 (2.2177)	
[2022-01-17 13:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][920/1251]	eta 0:12:08 lr 0.000138	time 1.8172 (2.2016)	loss 6.3407 (6.3372)	grad_norm 2.5882 (2.2212)	
[2022-01-17 13:38:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][930/1251]	eta 0:11:46 lr 0.000138	time 2.8589 (2.2013)	loss 6.5493 (6.3355)	grad_norm 2.0006 (2.2218)	
[2022-01-17 13:38:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][940/1251]	eta 0:11:25 lr 0.000138	time 2.0245 (2.2032)	loss 6.5600 (6.3335)	grad_norm 2.3538 (2.2224)	
[2022-01-17 13:39:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][950/1251]	eta 0:11:03 lr 0.000139	time 2.2558 (2.2034)	loss 6.4073 (6.3326)	grad_norm 2.2497 (2.2226)	
[2022-01-17 13:39:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][960/1251]	eta 0:10:40 lr 0.000139	time 1.5570 (2.2025)	loss 6.3890 (6.3316)	grad_norm 2.1832 (2.2246)	
[2022-01-17 13:39:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][970/1251]	eta 0:10:19 lr 0.000140	time 1.9293 (2.2038)	loss 6.2375 (6.3293)	grad_norm 1.9417 (2.2246)	
[2022-01-17 13:40:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][980/1251]	eta 0:09:57 lr 0.000140	time 1.8256 (2.2034)	loss 5.9037 (6.3277)	grad_norm 2.0373 (2.2245)	
[2022-01-17 13:40:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][990/1251]	eta 0:09:34 lr 0.000140	time 2.3321 (2.2030)	loss 6.3579 (6.3268)	grad_norm 2.3274 (2.2267)	
[2022-01-17 13:40:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1000/1251]	eta 0:09:12 lr 0.000141	time 1.8829 (2.2015)	loss 6.4169 (6.3255)	grad_norm 2.2872 (2.2257)	
[2022-01-17 13:41:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1010/1251]	eta 0:08:50 lr 0.000141	time 1.5974 (2.2004)	loss 6.3747 (6.3251)	grad_norm 2.2236 (2.2281)	
[2022-01-17 13:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1020/1251]	eta 0:08:28 lr 0.000142	time 1.6860 (2.2000)	loss 6.4066 (6.3235)	grad_norm 2.1206 (2.2289)	
[2022-01-17 13:41:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1030/1251]	eta 0:08:06 lr 0.000142	time 2.1875 (2.2008)	loss 6.6504 (6.3225)	grad_norm 2.7362 (2.2299)	
[2022-01-17 13:42:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1040/1251]	eta 0:07:44 lr 0.000142	time 2.0106 (2.2012)	loss 5.7401 (6.3208)	grad_norm 3.7649 (2.2338)	
[2022-01-17 13:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1050/1251]	eta 0:07:22 lr 0.000143	time 2.1712 (2.2018)	loss 6.4825 (6.3199)	grad_norm 2.0558 (2.2357)	
[2022-01-17 13:43:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1060/1251]	eta 0:07:00 lr 0.000143	time 2.1498 (2.2003)	loss 6.3656 (6.3202)	grad_norm 1.9924 (2.2353)	
[2022-01-17 13:43:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1070/1251]	eta 0:06:37 lr 0.000144	time 1.8045 (2.1985)	loss 6.3282 (6.3194)	grad_norm 2.2180 (2.2348)	
[2022-01-17 13:43:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1080/1251]	eta 0:06:15 lr 0.000144	time 2.6913 (2.1986)	loss 6.2320 (6.3191)	grad_norm 2.5113 (2.2325)	
[2022-01-17 13:44:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1090/1251]	eta 0:05:53 lr 0.000144	time 1.8828 (2.1985)	loss 5.9799 (6.3188)	grad_norm 2.4080 (2.2329)	
[2022-01-17 13:44:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1100/1251]	eta 0:05:32 lr 0.000145	time 2.3894 (2.1992)	loss 5.6663 (6.3169)	grad_norm 2.0688 (2.2326)	
[2022-01-17 13:44:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1110/1251]	eta 0:05:10 lr 0.000145	time 1.9477 (2.1987)	loss 6.3627 (6.3171)	grad_norm 2.2656 (2.2321)	
[2022-01-17 13:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1120/1251]	eta 0:04:47 lr 0.000146	time 1.8763 (2.1981)	loss 5.9737 (6.3165)	grad_norm 2.4729 (2.2341)	
[2022-01-17 13:45:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1130/1251]	eta 0:04:26 lr 0.000146	time 2.1201 (2.1994)	loss 6.2594 (6.3165)	grad_norm 2.1191 (2.2378)	
[2022-01-17 13:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1140/1251]	eta 0:04:04 lr 0.000146	time 1.8630 (2.1995)	loss 6.5172 (6.3162)	grad_norm 2.5112 (2.2429)	
[2022-01-17 13:46:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1150/1251]	eta 0:03:42 lr 0.000147	time 1.6268 (2.1997)	loss 6.5650 (6.3165)	grad_norm 2.0549 (2.2426)	
[2022-01-17 13:46:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1160/1251]	eta 0:03:20 lr 0.000147	time 1.9948 (2.1985)	loss 6.3185 (6.3153)	grad_norm 2.7013 (2.2420)	
[2022-01-17 13:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1170/1251]	eta 0:02:57 lr 0.000148	time 1.7581 (2.1971)	loss 6.1189 (6.3149)	grad_norm 1.9368 (2.2417)	
[2022-01-17 13:47:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1180/1251]	eta 0:02:35 lr 0.000148	time 2.0711 (2.1966)	loss 6.4042 (6.3145)	grad_norm 2.6818 (2.2437)	
[2022-01-17 13:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1190/1251]	eta 0:02:13 lr 0.000148	time 2.3210 (2.1962)	loss 5.9404 (6.3138)	grad_norm 2.9961 (2.2452)	
[2022-01-17 13:48:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1200/1251]	eta 0:01:52 lr 0.000149	time 2.1535 (2.1963)	loss 6.3976 (6.3128)	grad_norm 2.3617 (2.2461)	
[2022-01-17 13:48:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1210/1251]	eta 0:01:30 lr 0.000149	time 1.9704 (2.1957)	loss 6.5333 (6.3117)	grad_norm 2.2770 (2.2461)	
[2022-01-17 13:48:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1220/1251]	eta 0:01:08 lr 0.000150	time 2.1806 (2.1959)	loss 6.5249 (6.3114)	grad_norm 2.2905 (2.2471)	
[2022-01-17 13:49:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1230/1251]	eta 0:00:46 lr 0.000150	time 2.1570 (2.1963)	loss 6.1329 (6.3109)	grad_norm 1.8796 (2.2479)	
[2022-01-17 13:49:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1240/1251]	eta 0:00:24 lr 0.000150	time 2.1527 (2.1956)	loss 6.3660 (6.3107)	grad_norm 2.2804 (2.2481)	
[2022-01-17 13:49:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [2/300][1250/1251]	eta 0:00:02 lr 0.000151	time 1.1745 (2.1905)	loss 6.4508 (6.3094)	grad_norm 2.7020 (2.2492)	
[2022-01-17 13:49:51 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 2 training takes 0:45:40
[2022-01-17 13:50:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.020 (18.020)	Loss 4.9885 (4.9885)	Acc@1 10.449 (10.449)	Acc@5 28.809 (28.809)	
[2022-01-17 13:50:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.280 (3.439)	Loss 5.0477 (4.9506)	Acc@1 10.840 (11.737)	Acc@5 26.367 (28.240)	
[2022-01-17 13:50:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.959 (2.653)	Loss 4.8589 (4.9439)	Acc@1 11.719 (11.509)	Acc@5 29.883 (28.246)	
[2022-01-17 13:51:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.283 (2.412)	Loss 4.9251 (4.9462)	Acc@1 11.621 (11.505)	Acc@5 30.566 (28.393)	
[2022-01-17 13:51:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.070 (2.225)	Loss 4.9223 (4.9478)	Acc@1 12.012 (11.552)	Acc@5 28.027 (28.392)	
[2022-01-17 13:51:30 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 11.530 Acc@5 28.352
[2022-01-17 13:51:30 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 11.5%
[2022-01-17 13:51:30 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 11.53%
[2022-01-17 13:51:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][0/1251]	eta 7:23:50 lr 0.000151	time 21.2871 (21.2871)	loss 6.0097 (6.0097)	grad_norm 2.0064 (2.0064)	
[2022-01-17 13:52:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][10/1251]	eta 1:25:43 lr 0.000151	time 1.8978 (4.1448)	loss 6.3747 (6.2698)	grad_norm 1.9571 (2.1589)	
[2022-01-17 13:52:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][20/1251]	eta 1:04:47 lr 0.000152	time 2.1580 (3.1577)	loss 6.0820 (6.1987)	grad_norm 1.9198 (2.2122)	
[2022-01-17 13:52:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][30/1251]	eta 0:58:34 lr 0.000152	time 1.3574 (2.8787)	loss 6.2142 (6.2033)	grad_norm 1.6565 (2.1822)	
[2022-01-17 13:53:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][40/1251]	eta 0:55:21 lr 0.000152	time 3.5964 (2.7428)	loss 6.1281 (6.2112)	grad_norm 2.3326 (2.2308)	
[2022-01-17 13:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][50/1251]	eta 0:53:44 lr 0.000153	time 2.4623 (2.6848)	loss 6.1371 (6.2104)	grad_norm 2.3041 (2.2179)	
[2022-01-17 13:54:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][60/1251]	eta 0:51:34 lr 0.000153	time 2.2107 (2.5981)	loss 5.8695 (6.1886)	grad_norm 2.0006 (2.2369)	
[2022-01-17 13:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][70/1251]	eta 0:49:50 lr 0.000154	time 1.5964 (2.5320)	loss 6.4215 (6.1937)	grad_norm 2.0847 (2.2401)	
[2022-01-17 13:54:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][80/1251]	eta 0:48:34 lr 0.000154	time 2.5906 (2.4888)	loss 6.1552 (6.1971)	grad_norm 2.4675 (2.2321)	
[2022-01-17 13:55:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][90/1251]	eta 0:47:26 lr 0.000154	time 2.4537 (2.4515)	loss 5.9937 (6.1814)	grad_norm 2.7335 (2.2525)	
[2022-01-17 13:55:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][100/1251]	eta 0:46:09 lr 0.000155	time 2.1381 (2.4061)	loss 6.0341 (6.1922)	grad_norm 1.8578 (2.2329)	
[2022-01-17 13:55:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][110/1251]	eta 0:45:22 lr 0.000155	time 1.7436 (2.3862)	loss 6.1234 (6.1785)	grad_norm 2.2132 (2.2247)	
[2022-01-17 13:56:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][120/1251]	eta 0:44:51 lr 0.000156	time 3.1472 (2.3802)	loss 6.4798 (6.1783)	grad_norm 1.6719 (2.2259)	
[2022-01-17 13:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][130/1251]	eta 0:44:19 lr 0.000156	time 2.8288 (2.3724)	loss 6.3972 (6.1716)	grad_norm 2.4419 (2.2325)	
[2022-01-17 13:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][140/1251]	eta 0:43:46 lr 0.000156	time 2.2886 (2.3639)	loss 6.4262 (6.1688)	grad_norm 1.8211 (2.2361)	
[2022-01-17 13:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][150/1251]	eta 0:43:05 lr 0.000157	time 1.9281 (2.3484)	loss 6.1013 (6.1635)	grad_norm 2.0101 (2.2480)	
[2022-01-17 13:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][160/1251]	eta 0:42:29 lr 0.000157	time 2.1517 (2.3372)	loss 6.1051 (6.1621)	grad_norm 2.3908 (2.2569)	
[2022-01-17 13:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][170/1251]	eta 0:41:49 lr 0.000158	time 2.3543 (2.3215)	loss 6.3498 (6.1641)	grad_norm 2.5559 (2.2646)	
[2022-01-17 13:58:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][180/1251]	eta 0:41:13 lr 0.000158	time 2.9038 (2.3095)	loss 6.5323 (6.1614)	grad_norm 2.2003 (2.2604)	
[2022-01-17 13:58:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][190/1251]	eta 0:40:42 lr 0.000158	time 1.6886 (2.3020)	loss 6.2849 (6.1547)	grad_norm 1.9478 (2.2612)	
[2022-01-17 13:59:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][200/1251]	eta 0:40:05 lr 0.000159	time 1.7785 (2.2886)	loss 6.2449 (6.1476)	grad_norm 1.8590 (2.2731)	
[2022-01-17 13:59:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][210/1251]	eta 0:39:37 lr 0.000159	time 1.9478 (2.2837)	loss 6.3704 (6.1470)	grad_norm 2.1434 (2.2720)	
[2022-01-17 13:59:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][220/1251]	eta 0:39:19 lr 0.000160	time 3.6374 (2.2882)	loss 5.6570 (6.1479)	grad_norm 2.4561 (2.2820)	
[2022-01-17 14:00:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][230/1251]	eta 0:38:53 lr 0.000160	time 1.5384 (2.2854)	loss 6.1376 (6.1506)	grad_norm 1.9963 (2.2746)	
[2022-01-17 14:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][240/1251]	eta 0:38:25 lr 0.000160	time 1.7915 (2.2800)	loss 6.4952 (6.1514)	grad_norm 1.8643 (2.2691)	
[2022-01-17 14:01:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][250/1251]	eta 0:37:55 lr 0.000161	time 1.9041 (2.2733)	loss 6.4663 (6.1476)	grad_norm 2.0774 (2.2623)	
[2022-01-17 14:01:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][260/1251]	eta 0:37:30 lr 0.000161	time 2.5673 (2.2706)	loss 6.3394 (6.1432)	grad_norm 1.9328 (2.2648)	
[2022-01-17 14:01:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][270/1251]	eta 0:37:04 lr 0.000162	time 2.5464 (2.2674)	loss 5.9964 (6.1468)	grad_norm 1.9540 (2.2687)	
[2022-01-17 14:02:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][280/1251]	eta 0:36:37 lr 0.000162	time 2.0249 (2.2635)	loss 5.7188 (6.1414)	grad_norm 2.0964 (2.2646)	
[2022-01-17 14:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][290/1251]	eta 0:36:18 lr 0.000162	time 3.1784 (2.2673)	loss 6.3894 (6.1460)	grad_norm 2.1192 (2.2602)	
[2022-01-17 14:02:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][300/1251]	eta 0:35:55 lr 0.000163	time 2.7889 (2.2662)	loss 6.1261 (6.1499)	grad_norm 2.0289 (2.2643)	
[2022-01-17 14:03:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][310/1251]	eta 0:35:33 lr 0.000163	time 2.5092 (2.2672)	loss 5.6290 (6.1494)	grad_norm 1.9493 (2.2617)	
[2022-01-17 14:03:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][320/1251]	eta 0:35:05 lr 0.000164	time 1.5902 (2.2617)	loss 5.9704 (6.1426)	grad_norm 2.5550 (2.2606)	
[2022-01-17 14:03:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][330/1251]	eta 0:34:39 lr 0.000164	time 2.8421 (2.2579)	loss 5.6940 (6.1371)	grad_norm 1.7686 (2.2619)	
[2022-01-17 14:04:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][340/1251]	eta 0:34:08 lr 0.000164	time 1.7826 (2.2490)	loss 6.1059 (6.1366)	grad_norm 2.2012 (2.2646)	
[2022-01-17 14:04:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][350/1251]	eta 0:33:43 lr 0.000165	time 2.2565 (2.2460)	loss 6.2339 (6.1333)	grad_norm 2.2509 (2.2637)	
[2022-01-17 14:05:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][360/1251]	eta 0:33:19 lr 0.000165	time 2.2703 (2.2444)	loss 6.0390 (6.1320)	grad_norm 2.6841 (2.2686)	
[2022-01-17 14:05:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][370/1251]	eta 0:32:59 lr 0.000166	time 2.1678 (2.2474)	loss 6.3510 (6.1316)	grad_norm 3.3692 (2.2844)	
[2022-01-17 14:05:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][380/1251]	eta 0:32:36 lr 0.000166	time 1.8337 (2.2461)	loss 5.8134 (6.1302)	grad_norm 2.2934 (2.2848)	
[2022-01-17 14:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][390/1251]	eta 0:32:14 lr 0.000166	time 2.4361 (2.2464)	loss 5.5368 (6.1317)	grad_norm 3.5449 (2.2882)	
[2022-01-17 14:06:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][400/1251]	eta 0:31:50 lr 0.000167	time 2.2648 (2.2447)	loss 5.8317 (6.1314)	grad_norm 1.8783 (2.2859)	
[2022-01-17 14:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][410/1251]	eta 0:31:24 lr 0.000167	time 2.1019 (2.2410)	loss 6.3186 (6.1310)	grad_norm 2.3152 (2.2788)	
[2022-01-17 14:07:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][420/1251]	eta 0:30:58 lr 0.000168	time 1.5919 (2.2367)	loss 6.4693 (6.1331)	grad_norm 1.8544 (2.2748)	
[2022-01-17 14:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][430/1251]	eta 0:30:34 lr 0.000168	time 1.8894 (2.2339)	loss 6.3358 (6.1354)	grad_norm 2.7681 (2.2786)	
[2022-01-17 14:07:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][440/1251]	eta 0:30:08 lr 0.000168	time 1.9014 (2.2306)	loss 5.8665 (6.1321)	grad_norm 2.2588 (2.2833)	
[2022-01-17 14:08:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][450/1251]	eta 0:29:44 lr 0.000169	time 2.4998 (2.2282)	loss 5.9158 (6.1332)	grad_norm 2.1114 (2.2825)	
[2022-01-17 14:08:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][460/1251]	eta 0:29:20 lr 0.000169	time 1.9440 (2.2251)	loss 6.3590 (6.1337)	grad_norm 2.3514 (2.2798)	
[2022-01-17 14:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][470/1251]	eta 0:28:57 lr 0.000170	time 2.6695 (2.2244)	loss 5.5332 (6.1333)	grad_norm 2.2932 (2.2806)	
[2022-01-17 14:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][480/1251]	eta 0:28:37 lr 0.000170	time 2.0760 (2.2277)	loss 6.0885 (6.1300)	grad_norm 3.8088 (2.2904)	
[2022-01-17 14:09:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][490/1251]	eta 0:28:18 lr 0.000170	time 2.8315 (2.2315)	loss 6.2774 (6.1304)	grad_norm 2.3661 (2.2915)	
[2022-01-17 14:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][500/1251]	eta 0:27:54 lr 0.000171	time 1.4811 (2.2300)	loss 6.3756 (6.1297)	grad_norm 2.2356 (2.2909)	
[2022-01-17 14:10:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][510/1251]	eta 0:27:35 lr 0.000171	time 2.7174 (2.2341)	loss 5.5483 (6.1273)	grad_norm 1.7974 (2.2875)	
[2022-01-17 14:10:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][520/1251]	eta 0:27:15 lr 0.000172	time 1.9103 (2.2369)	loss 6.3786 (6.1265)	grad_norm 1.9507 (2.2863)	
[2022-01-17 14:11:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][530/1251]	eta 0:26:52 lr 0.000172	time 2.5225 (2.2358)	loss 5.4971 (6.1233)	grad_norm 2.0310 (2.2858)	
[2022-01-17 14:11:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][540/1251]	eta 0:26:26 lr 0.000172	time 1.7675 (2.2318)	loss 6.3464 (6.1242)	grad_norm 2.2552 (2.2862)	
[2022-01-17 14:11:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][550/1251]	eta 0:26:00 lr 0.000173	time 1.8439 (2.2260)	loss 6.0960 (6.1218)	grad_norm 2.0461 (2.2957)	
[2022-01-17 14:12:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][560/1251]	eta 0:25:36 lr 0.000173	time 1.8545 (2.2230)	loss 5.5725 (6.1231)	grad_norm 2.2646 (2.2978)	
[2022-01-17 14:12:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][570/1251]	eta 0:25:12 lr 0.000174	time 2.4635 (2.2209)	loss 6.1211 (6.1238)	grad_norm 2.4149 (2.2953)	
[2022-01-17 14:13:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][580/1251]	eta 0:24:50 lr 0.000174	time 2.8303 (2.2215)	loss 5.4782 (6.1218)	grad_norm 1.7298 (2.2930)	
[2022-01-17 14:13:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][590/1251]	eta 0:24:27 lr 0.000174	time 2.1312 (2.2197)	loss 5.6024 (6.1195)	grad_norm 2.5717 (2.2951)	
[2022-01-17 14:13:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][600/1251]	eta 0:24:03 lr 0.000175	time 1.9683 (2.2170)	loss 6.0519 (6.1187)	grad_norm 2.5573 (2.2947)	
[2022-01-17 14:14:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][610/1251]	eta 0:23:41 lr 0.000175	time 2.4964 (2.2174)	loss 5.6514 (6.1172)	grad_norm 2.1471 (2.2928)	
[2022-01-17 14:14:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][620/1251]	eta 0:23:20 lr 0.000176	time 3.1892 (2.2192)	loss 6.1238 (6.1176)	grad_norm 2.8079 (2.2909)	
[2022-01-17 14:14:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][630/1251]	eta 0:23:00 lr 0.000176	time 2.4368 (2.2225)	loss 5.9620 (6.1156)	grad_norm 1.9523 (2.2920)	
[2022-01-17 14:15:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][640/1251]	eta 0:22:37 lr 0.000176	time 1.6680 (2.2218)	loss 5.7415 (6.1152)	grad_norm 2.0432 (2.2882)	
[2022-01-17 14:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][650/1251]	eta 0:22:15 lr 0.000177	time 2.7810 (2.2217)	loss 6.2435 (6.1173)	grad_norm 2.0482 (2.2889)	
[2022-01-17 14:15:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][660/1251]	eta 0:21:51 lr 0.000177	time 2.6057 (2.2196)	loss 5.8187 (6.1159)	grad_norm 2.5451 (2.2945)	
[2022-01-17 14:16:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][670/1251]	eta 0:21:29 lr 0.000178	time 1.6502 (2.2194)	loss 5.8367 (6.1146)	grad_norm 2.6210 (2.2960)	
[2022-01-17 14:16:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][680/1251]	eta 0:21:06 lr 0.000178	time 2.2163 (2.2175)	loss 6.3137 (6.1132)	grad_norm 3.4712 (2.2996)	
[2022-01-17 14:17:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][690/1251]	eta 0:20:44 lr 0.000178	time 2.9723 (2.2189)	loss 6.1419 (6.1126)	grad_norm 2.1340 (2.2996)	
[2022-01-17 14:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][700/1251]	eta 0:20:21 lr 0.000179	time 1.9369 (2.2171)	loss 5.5182 (6.1120)	grad_norm 2.2031 (2.3010)	
[2022-01-17 14:17:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][710/1251]	eta 0:19:58 lr 0.000179	time 2.2403 (2.2160)	loss 6.3323 (6.1114)	grad_norm 2.3944 (2.3025)	
[2022-01-17 14:18:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][720/1251]	eta 0:19:36 lr 0.000180	time 2.5322 (2.2151)	loss 6.5265 (6.1134)	grad_norm 2.4589 (2.3050)	
[2022-01-17 14:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][730/1251]	eta 0:19:12 lr 0.000180	time 1.9336 (2.2128)	loss 6.3373 (6.1128)	grad_norm 2.7132 (2.3045)	
[2022-01-17 14:18:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][740/1251]	eta 0:18:50 lr 0.000180	time 1.5690 (2.2122)	loss 6.4019 (6.1094)	grad_norm 1.9602 (2.3052)	
[2022-01-17 14:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][750/1251]	eta 0:18:28 lr 0.000181	time 2.1005 (2.2116)	loss 5.7229 (6.1079)	grad_norm 2.2263 (2.3048)	
[2022-01-17 14:19:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][760/1251]	eta 0:18:05 lr 0.000181	time 1.8591 (2.2103)	loss 5.8076 (6.1086)	grad_norm 2.3324 (2.3073)	
[2022-01-17 14:19:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][770/1251]	eta 0:17:42 lr 0.000182	time 2.1360 (2.2089)	loss 6.2333 (6.1078)	grad_norm 2.1873 (2.3098)	
[2022-01-17 14:20:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][780/1251]	eta 0:17:19 lr 0.000182	time 1.8612 (2.2074)	loss 6.0347 (6.1075)	grad_norm 1.7231 (2.3095)	
[2022-01-17 14:20:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][790/1251]	eta 0:16:57 lr 0.000182	time 2.1504 (2.2068)	loss 6.2696 (6.1066)	grad_norm 2.2276 (2.3091)	
[2022-01-17 14:20:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][800/1251]	eta 0:16:34 lr 0.000183	time 2.0903 (2.2061)	loss 5.9116 (6.1062)	grad_norm 2.3976 (2.3120)	
[2022-01-17 14:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][810/1251]	eta 0:16:12 lr 0.000183	time 2.1244 (2.2059)	loss 6.3723 (6.1072)	grad_norm 3.2174 (2.3164)	
[2022-01-17 14:21:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][820/1251]	eta 0:15:50 lr 0.000184	time 1.8992 (2.2060)	loss 6.2117 (6.1070)	grad_norm 2.5056 (2.3174)	
[2022-01-17 14:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][830/1251]	eta 0:15:28 lr 0.000184	time 1.9459 (2.2054)	loss 5.7572 (6.1065)	grad_norm 2.2409 (2.3170)	
[2022-01-17 14:22:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][840/1251]	eta 0:15:06 lr 0.000184	time 2.3765 (2.2053)	loss 5.9276 (6.1068)	grad_norm 2.4654 (2.3162)	
[2022-01-17 14:22:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][850/1251]	eta 0:14:44 lr 0.000185	time 1.5583 (2.2056)	loss 6.1329 (6.1057)	grad_norm 2.9423 (2.3172)	
[2022-01-17 14:23:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][860/1251]	eta 0:14:22 lr 0.000185	time 1.8934 (2.2056)	loss 6.3728 (6.1040)	grad_norm 2.7588 (2.3193)	
[2022-01-17 14:23:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][870/1251]	eta 0:14:01 lr 0.000186	time 1.9604 (2.2077)	loss 6.2342 (6.1039)	grad_norm 2.0258 (2.3194)	
[2022-01-17 14:23:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][880/1251]	eta 0:13:39 lr 0.000186	time 2.0147 (2.2095)	loss 6.2682 (6.1028)	grad_norm 3.2340 (2.3219)	
[2022-01-17 14:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][890/1251]	eta 0:13:17 lr 0.000186	time 1.9060 (2.2086)	loss 5.9883 (6.1035)	grad_norm 1.7542 (2.3209)	
[2022-01-17 14:24:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][900/1251]	eta 0:12:54 lr 0.000187	time 2.2336 (2.2064)	loss 6.3075 (6.1030)	grad_norm 1.8386 (2.3199)	
[2022-01-17 14:24:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][910/1251]	eta 0:12:31 lr 0.000187	time 1.7788 (2.2051)	loss 5.6348 (6.1027)	grad_norm 2.1499 (2.3189)	
[2022-01-17 14:25:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][920/1251]	eta 0:12:09 lr 0.000188	time 2.1654 (2.2041)	loss 6.3529 (6.1028)	grad_norm 1.7184 (2.3188)	
[2022-01-17 14:25:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][930/1251]	eta 0:11:47 lr 0.000188	time 2.2141 (2.2035)	loss 6.5549 (6.1020)	grad_norm 2.5645 (2.3224)	
[2022-01-17 14:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][940/1251]	eta 0:11:25 lr 0.000188	time 2.5438 (2.2035)	loss 5.7912 (6.1024)	grad_norm 2.6526 (2.3247)	
[2022-01-17 14:26:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][950/1251]	eta 0:11:03 lr 0.000189	time 1.7824 (2.2029)	loss 6.3201 (6.1032)	grad_norm 2.2478 (2.3248)	
[2022-01-17 14:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][960/1251]	eta 0:10:41 lr 0.000189	time 2.4907 (2.2038)	loss 6.1153 (6.1008)	grad_norm 2.2569 (2.3250)	
[2022-01-17 14:27:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][970/1251]	eta 0:10:19 lr 0.000190	time 1.7545 (2.2049)	loss 5.7392 (6.1009)	grad_norm 2.4824 (2.3249)	
[2022-01-17 14:27:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][980/1251]	eta 0:09:58 lr 0.000190	time 2.9254 (2.2077)	loss 6.0865 (6.0993)	grad_norm 2.7844 (2.3282)	
[2022-01-17 14:27:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][990/1251]	eta 0:09:36 lr 0.000190	time 2.2198 (2.2071)	loss 5.4376 (6.0990)	grad_norm 2.7277 (2.3279)	
[2022-01-17 14:28:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1000/1251]	eta 0:09:13 lr 0.000191	time 1.8434 (2.2053)	loss 6.2447 (6.0978)	grad_norm 2.1804 (2.3273)	
[2022-01-17 14:28:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1010/1251]	eta 0:08:51 lr 0.000191	time 1.8778 (2.2037)	loss 6.1357 (6.0971)	grad_norm 1.9786 (2.3271)	
[2022-01-17 14:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1020/1251]	eta 0:08:29 lr 0.000192	time 1.8627 (2.2059)	loss 6.0870 (6.0952)	grad_norm 2.2274 (2.3283)	
[2022-01-17 14:29:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1030/1251]	eta 0:08:07 lr 0.000192	time 2.2647 (2.2047)	loss 6.1726 (6.0942)	grad_norm 2.1875 (2.3269)	
[2022-01-17 14:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1040/1251]	eta 0:07:45 lr 0.000192	time 1.7025 (2.2039)	loss 6.1862 (6.0938)	grad_norm 2.2143 (2.3274)	
[2022-01-17 14:30:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1050/1251]	eta 0:07:22 lr 0.000193	time 2.2509 (2.2030)	loss 6.2115 (6.0929)	grad_norm 2.9127 (2.3270)	
[2022-01-17 14:30:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1060/1251]	eta 0:07:01 lr 0.000193	time 2.8163 (2.2045)	loss 6.0770 (6.0915)	grad_norm 2.0729 (2.3298)	
[2022-01-17 14:30:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1070/1251]	eta 0:06:38 lr 0.000194	time 1.8787 (2.2036)	loss 5.7392 (6.0894)	grad_norm 2.1209 (2.3306)	
[2022-01-17 14:31:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1080/1251]	eta 0:06:16 lr 0.000194	time 1.8884 (2.2019)	loss 6.1325 (6.0895)	grad_norm 2.2392 (2.3318)	
[2022-01-17 14:31:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1090/1251]	eta 0:05:54 lr 0.000194	time 3.1259 (2.2020)	loss 6.2832 (6.0896)	grad_norm 2.3450 (2.3320)	
[2022-01-17 14:31:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1100/1251]	eta 0:05:32 lr 0.000195	time 2.4167 (2.2027)	loss 6.3593 (6.0879)	grad_norm 1.9940 (2.3310)	
[2022-01-17 14:32:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1110/1251]	eta 0:05:10 lr 0.000195	time 2.1240 (2.2019)	loss 5.6253 (6.0840)	grad_norm 2.4178 (2.3312)	
[2022-01-17 14:32:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1120/1251]	eta 0:04:48 lr 0.000196	time 1.9123 (2.2009)	loss 6.1448 (6.0819)	grad_norm 2.2747 (2.3355)	
[2022-01-17 14:32:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1130/1251]	eta 0:04:26 lr 0.000196	time 2.5019 (2.2010)	loss 5.3277 (6.0805)	grad_norm 2.8238 (2.3352)	
[2022-01-17 14:33:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1140/1251]	eta 0:04:04 lr 0.000196	time 2.9498 (2.2007)	loss 5.7339 (6.0793)	grad_norm 2.1329 (2.3353)	
[2022-01-17 14:33:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1150/1251]	eta 0:03:42 lr 0.000197	time 2.2906 (2.1994)	loss 5.7440 (6.0774)	grad_norm 3.3644 (2.3368)	
[2022-01-17 14:34:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1160/1251]	eta 0:03:20 lr 0.000197	time 1.8505 (2.1985)	loss 5.6558 (6.0764)	grad_norm 2.1883 (2.3374)	
[2022-01-17 14:34:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1170/1251]	eta 0:02:58 lr 0.000198	time 2.2977 (2.1991)	loss 5.6215 (6.0758)	grad_norm 2.2879 (2.3367)	
[2022-01-17 14:34:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1180/1251]	eta 0:02:36 lr 0.000198	time 3.2546 (2.2004)	loss 6.3528 (6.0760)	grad_norm 2.0585 (2.3389)	
[2022-01-17 14:35:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1190/1251]	eta 0:02:14 lr 0.000198	time 1.8794 (2.2013)	loss 6.0217 (6.0762)	grad_norm 2.5992 (2.3380)	
[2022-01-17 14:35:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1200/1251]	eta 0:01:52 lr 0.000199	time 1.7777 (2.2005)	loss 6.1013 (6.0758)	grad_norm 2.0397 (2.3404)	
[2022-01-17 14:35:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1210/1251]	eta 0:01:30 lr 0.000199	time 2.1528 (2.2000)	loss 5.8911 (6.0736)	grad_norm 2.0372 (2.3406)	
[2022-01-17 14:36:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1220/1251]	eta 0:01:08 lr 0.000200	time 2.1087 (2.1998)	loss 6.2322 (6.0734)	grad_norm 2.0959 (2.3405)	
[2022-01-17 14:36:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1230/1251]	eta 0:00:46 lr 0.000200	time 1.8939 (2.1982)	loss 6.1788 (6.0741)	grad_norm 2.3304 (2.3403)	
[2022-01-17 14:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1240/1251]	eta 0:00:24 lr 0.000200	time 1.5737 (2.1966)	loss 5.5231 (6.0725)	grad_norm 3.2249 (2.3408)	
[2022-01-17 14:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [3/300][1250/1251]	eta 0:00:02 lr 0.000201	time 1.1859 (2.1913)	loss 6.3238 (6.0733)	grad_norm 2.4387 (2.3411)	
[2022-01-17 14:37:11 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 3 training takes 0:45:41
[2022-01-17 14:37:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.026 (19.026)	Loss 4.4408 (4.4408)	Acc@1 18.164 (18.164)	Acc@5 38.379 (38.379)	
[2022-01-17 14:37:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.586 (3.436)	Loss 4.3675 (4.3836)	Acc@1 18.945 (18.475)	Acc@5 38.867 (39.249)	
[2022-01-17 14:38:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.576 (2.634)	Loss 4.4629 (4.3735)	Acc@1 18.848 (18.662)	Acc@5 38.086 (39.551)	
[2022-01-17 14:38:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.282 (2.212)	Loss 4.3712 (4.3682)	Acc@1 18.066 (18.662)	Acc@5 40.137 (39.664)	
[2022-01-17 14:38:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.033 (2.172)	Loss 4.4245 (4.3687)	Acc@1 17.969 (18.614)	Acc@5 38.574 (39.622)	
[2022-01-17 14:38:47 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 18.568 Acc@5 39.650
[2022-01-17 14:38:47 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 18.6%
[2022-01-17 14:38:47 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 18.57%
[2022-01-17 14:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][0/1251]	eta 7:21:32 lr 0.000201	time 21.1774 (21.1774)	loss 6.2718 (6.2718)	grad_norm 2.6312 (2.6312)	
[2022-01-17 14:39:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][10/1251]	eta 1:28:17 lr 0.000201	time 2.7629 (4.2687)	loss 6.3029 (5.9453)	grad_norm 2.2116 (2.2972)	
[2022-01-17 14:39:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][20/1251]	eta 1:06:41 lr 0.000202	time 1.2866 (3.2510)	loss 6.2943 (5.9107)	grad_norm 1.9509 (2.3350)	
[2022-01-17 14:40:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][30/1251]	eta 0:59:50 lr 0.000202	time 1.9214 (2.9408)	loss 5.4328 (5.8910)	grad_norm 2.3625 (2.3022)	
[2022-01-17 14:40:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][40/1251]	eta 0:57:30 lr 0.000202	time 5.4919 (2.8496)	loss 6.0907 (5.9167)	grad_norm 2.6740 (2.3353)	
[2022-01-17 14:41:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][50/1251]	eta 0:54:24 lr 0.000203	time 1.9371 (2.7184)	loss 5.9009 (5.9079)	grad_norm 2.1685 (2.2976)	
[2022-01-17 14:41:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][60/1251]	eta 0:51:44 lr 0.000203	time 1.8328 (2.6069)	loss 5.8822 (5.9294)	grad_norm 2.2910 (2.2920)	
[2022-01-17 14:41:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][70/1251]	eta 0:49:54 lr 0.000204	time 2.2987 (2.5353)	loss 6.0038 (5.9171)	grad_norm 1.9322 (2.3592)	
[2022-01-17 14:42:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][80/1251]	eta 0:49:16 lr 0.000204	time 3.8487 (2.5246)	loss 5.3857 (5.9102)	grad_norm 2.0881 (2.3784)	
[2022-01-17 14:42:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][90/1251]	eta 0:48:00 lr 0.000204	time 1.9648 (2.4810)	loss 5.8251 (5.9025)	grad_norm 3.0442 (2.4435)	
[2022-01-17 14:42:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][100/1251]	eta 0:47:08 lr 0.000205	time 1.6431 (2.4573)	loss 6.2658 (5.9167)	grad_norm 2.3421 (2.4525)	
[2022-01-17 14:43:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][110/1251]	eta 0:45:54 lr 0.000205	time 1.9094 (2.4140)	loss 6.0678 (5.9139)	grad_norm 2.0332 (2.4342)	
[2022-01-17 14:43:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][120/1251]	eta 0:45:46 lr 0.000206	time 3.6921 (2.4285)	loss 6.2449 (5.9110)	grad_norm 2.1988 (2.4244)	
[2022-01-17 14:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][130/1251]	eta 0:44:49 lr 0.000206	time 1.7676 (2.3994)	loss 6.1372 (5.9197)	grad_norm 2.7954 (2.4194)	
[2022-01-17 14:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][140/1251]	eta 0:43:53 lr 0.000206	time 1.8899 (2.3708)	loss 6.2534 (5.9306)	grad_norm 2.9169 (2.4326)	
[2022-01-17 14:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][150/1251]	eta 0:43:05 lr 0.000207	time 2.1115 (2.3480)	loss 5.8253 (5.9310)	grad_norm 1.9699 (2.4291)	
[2022-01-17 14:45:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][160/1251]	eta 0:42:31 lr 0.000207	time 2.9851 (2.3388)	loss 5.6339 (5.9387)	grad_norm 1.9392 (2.4360)	
[2022-01-17 14:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][170/1251]	eta 0:41:44 lr 0.000208	time 2.2435 (2.3167)	loss 6.0328 (5.9364)	grad_norm 2.3802 (2.4352)	
[2022-01-17 14:45:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][180/1251]	eta 0:41:05 lr 0.000208	time 2.1015 (2.3018)	loss 6.2266 (5.9414)	grad_norm 2.2204 (2.4300)	
[2022-01-17 14:46:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][190/1251]	eta 0:40:33 lr 0.000208	time 2.2124 (2.2936)	loss 5.3194 (5.9320)	grad_norm 2.3521 (2.4268)	
[2022-01-17 14:46:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][200/1251]	eta 0:40:03 lr 0.000209	time 2.1596 (2.2867)	loss 6.2802 (5.9370)	grad_norm 2.0728 (2.4311)	
[2022-01-17 14:46:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][210/1251]	eta 0:39:37 lr 0.000209	time 2.1387 (2.2840)	loss 6.2755 (5.9421)	grad_norm 1.9463 (2.4411)	
[2022-01-17 14:47:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][220/1251]	eta 0:39:13 lr 0.000210	time 2.5221 (2.2825)	loss 5.6586 (5.9430)	grad_norm 2.0784 (2.4298)	
[2022-01-17 14:47:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][230/1251]	eta 0:38:48 lr 0.000210	time 1.7283 (2.2807)	loss 6.1383 (5.9393)	grad_norm 3.3325 (2.4283)	
[2022-01-17 14:47:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][240/1251]	eta 0:38:32 lr 0.000210	time 2.2436 (2.2869)	loss 6.0617 (5.9472)	grad_norm 2.5919 (2.4233)	
[2022-01-17 14:48:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][250/1251]	eta 0:38:04 lr 0.000211	time 1.5095 (2.2820)	loss 6.4178 (5.9444)	grad_norm 2.3232 (2.4287)	
[2022-01-17 14:48:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][260/1251]	eta 0:37:44 lr 0.000211	time 3.4772 (2.2855)	loss 6.3593 (5.9433)	grad_norm 2.4988 (2.4246)	
[2022-01-17 14:49:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][270/1251]	eta 0:37:15 lr 0.000212	time 1.9085 (2.2785)	loss 5.9358 (5.9446)	grad_norm 2.6374 (2.4316)	
[2022-01-17 14:49:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][280/1251]	eta 0:36:46 lr 0.000212	time 1.6336 (2.2719)	loss 6.3087 (5.9472)	grad_norm 2.3847 (2.4384)	
[2022-01-17 14:49:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][290/1251]	eta 0:36:16 lr 0.000212	time 1.8737 (2.2647)	loss 5.1361 (5.9442)	grad_norm 2.3757 (2.4444)	
[2022-01-17 14:50:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][300/1251]	eta 0:35:46 lr 0.000213	time 2.3625 (2.2572)	loss 5.7528 (5.9469)	grad_norm 2.3074 (2.4403)	
[2022-01-17 14:50:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][310/1251]	eta 0:35:20 lr 0.000213	time 1.5552 (2.2537)	loss 6.0685 (5.9424)	grad_norm 2.2685 (2.4382)	
[2022-01-17 14:50:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][320/1251]	eta 0:34:59 lr 0.000214	time 2.2898 (2.2553)	loss 6.1636 (5.9416)	grad_norm 4.6780 (2.4547)	
[2022-01-17 14:51:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][330/1251]	eta 0:34:35 lr 0.000214	time 1.9583 (2.2534)	loss 5.5669 (5.9385)	grad_norm 2.5193 (2.4496)	
[2022-01-17 14:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][340/1251]	eta 0:34:12 lr 0.000214	time 2.7596 (2.2528)	loss 6.3442 (5.9406)	grad_norm 2.4231 (2.4413)	
[2022-01-17 14:51:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][350/1251]	eta 0:33:50 lr 0.000215	time 1.9375 (2.2531)	loss 6.1406 (5.9414)	grad_norm 2.4541 (2.4444)	
[2022-01-17 14:52:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][360/1251]	eta 0:33:27 lr 0.000215	time 2.4635 (2.2527)	loss 5.7336 (5.9377)	grad_norm 2.9118 (2.4539)	
[2022-01-17 14:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][370/1251]	eta 0:33:02 lr 0.000216	time 2.1318 (2.2500)	loss 6.0426 (5.9348)	grad_norm 2.5795 (2.4621)	
[2022-01-17 14:53:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][380/1251]	eta 0:32:38 lr 0.000216	time 2.1548 (2.2487)	loss 6.0633 (5.9327)	grad_norm 2.6426 (2.4757)	
[2022-01-17 14:53:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][390/1251]	eta 0:32:17 lr 0.000216	time 2.3929 (2.2502)	loss 6.1184 (5.9316)	grad_norm 2.4071 (2.4746)	
[2022-01-17 14:53:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][400/1251]	eta 0:31:53 lr 0.000217	time 2.1886 (2.2487)	loss 6.2946 (5.9327)	grad_norm 1.9945 (2.4670)	
[2022-01-17 14:54:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][410/1251]	eta 0:31:29 lr 0.000217	time 2.1242 (2.2467)	loss 5.9758 (5.9334)	grad_norm 2.1238 (2.4608)	
[2022-01-17 14:54:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][420/1251]	eta 0:31:04 lr 0.000218	time 1.6745 (2.2442)	loss 5.5585 (5.9296)	grad_norm 1.9542 (2.4543)	
[2022-01-17 14:54:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][430/1251]	eta 0:30:39 lr 0.000218	time 2.8505 (2.2406)	loss 6.0782 (5.9283)	grad_norm 2.1691 (2.4507)	
[2022-01-17 14:55:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][440/1251]	eta 0:30:12 lr 0.000218	time 1.8568 (2.2352)	loss 6.4025 (5.9290)	grad_norm 3.0672 (2.4558)	
[2022-01-17 14:55:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][450/1251]	eta 0:29:45 lr 0.000219	time 1.8565 (2.2296)	loss 5.6199 (5.9290)	grad_norm 2.7875 (2.4507)	
[2022-01-17 14:55:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][460/1251]	eta 0:29:22 lr 0.000219	time 2.1458 (2.2283)	loss 6.1315 (5.9294)	grad_norm 2.4290 (2.4478)	
[2022-01-17 14:56:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][470/1251]	eta 0:28:57 lr 0.000220	time 2.3146 (2.2241)	loss 6.1744 (5.9313)	grad_norm 1.9524 (2.4456)	
[2022-01-17 14:56:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][480/1251]	eta 0:28:31 lr 0.000220	time 1.8682 (2.2201)	loss 5.1625 (5.9265)	grad_norm 2.4111 (2.4440)	
[2022-01-17 14:56:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][490/1251]	eta 0:28:07 lr 0.000220	time 1.5581 (2.2169)	loss 6.1974 (5.9284)	grad_norm 2.2664 (2.4470)	
[2022-01-17 14:57:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][500/1251]	eta 0:27:48 lr 0.000221	time 2.6189 (2.2212)	loss 6.3074 (5.9273)	grad_norm 2.0738 (2.4429)	
[2022-01-17 14:57:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][510/1251]	eta 0:27:27 lr 0.000221	time 3.3982 (2.2237)	loss 5.8536 (5.9240)	grad_norm 2.2570 (2.4396)	
[2022-01-17 14:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][520/1251]	eta 0:27:07 lr 0.000222	time 2.5728 (2.2262)	loss 6.3870 (5.9251)	grad_norm 2.4193 (2.4471)	
[2022-01-17 14:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][530/1251]	eta 0:26:44 lr 0.000222	time 1.8904 (2.2260)	loss 5.2529 (5.9204)	grad_norm 2.3380 (2.4471)	
[2022-01-17 14:58:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][540/1251]	eta 0:26:23 lr 0.000222	time 1.8746 (2.2274)	loss 5.1564 (5.9191)	grad_norm 1.8018 (2.4475)	
[2022-01-17 14:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][550/1251]	eta 0:26:00 lr 0.000223	time 2.9230 (2.2254)	loss 5.9030 (5.9170)	grad_norm 2.2370 (2.4432)	
[2022-01-17 14:59:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][560/1251]	eta 0:25:34 lr 0.000223	time 2.0246 (2.2202)	loss 5.4848 (5.9164)	grad_norm 2.1840 (2.4414)	
[2022-01-17 14:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][570/1251]	eta 0:25:09 lr 0.000224	time 1.8687 (2.2166)	loss 5.3520 (5.9143)	grad_norm 3.1015 (2.4501)	
[2022-01-17 15:00:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][580/1251]	eta 0:24:46 lr 0.000224	time 1.6388 (2.2156)	loss 6.0989 (5.9143)	grad_norm 2.4149 (2.4498)	
[2022-01-17 15:00:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][590/1251]	eta 0:24:25 lr 0.000224	time 3.0031 (2.2167)	loss 6.3372 (5.9158)	grad_norm 2.0607 (2.4456)	
[2022-01-17 15:01:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][600/1251]	eta 0:24:04 lr 0.000225	time 2.5250 (2.2189)	loss 5.6192 (5.9129)	grad_norm 1.9967 (2.4422)	
[2022-01-17 15:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][610/1251]	eta 0:23:42 lr 0.000225	time 2.0396 (2.2196)	loss 6.1173 (5.9129)	grad_norm 2.6930 (2.4456)	
[2022-01-17 15:01:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][620/1251]	eta 0:23:21 lr 0.000226	time 2.2370 (2.2218)	loss 6.2961 (5.9126)	grad_norm 2.1905 (2.4421)	
[2022-01-17 15:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][630/1251]	eta 0:22:57 lr 0.000226	time 2.0107 (2.2188)	loss 6.2564 (5.9151)	grad_norm 3.1312 (2.4470)	
[2022-01-17 15:02:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][640/1251]	eta 0:22:34 lr 0.000226	time 2.4538 (2.2161)	loss 5.2417 (5.9135)	grad_norm 2.1105 (2.4471)	
[2022-01-17 15:02:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][650/1251]	eta 0:22:10 lr 0.000227	time 1.5732 (2.2136)	loss 5.9703 (5.9123)	grad_norm 1.6764 (2.4411)	
[2022-01-17 15:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][660/1251]	eta 0:21:48 lr 0.000227	time 1.9054 (2.2149)	loss 5.7126 (5.9103)	grad_norm 2.0236 (2.4412)	
[2022-01-17 15:03:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][670/1251]	eta 0:21:27 lr 0.000228	time 2.1723 (2.2153)	loss 6.5269 (5.9091)	grad_norm 3.4150 (2.4405)	
[2022-01-17 15:04:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][680/1251]	eta 0:21:09 lr 0.000228	time 7.2967 (2.2229)	loss 5.8336 (5.9101)	grad_norm 3.2457 (2.4381)	
[2022-01-17 15:04:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][690/1251]	eta 0:20:46 lr 0.000228	time 1.9197 (2.2215)	loss 5.0140 (5.9096)	grad_norm 2.0437 (2.4353)	
[2022-01-17 15:04:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][700/1251]	eta 0:20:23 lr 0.000229	time 1.5853 (2.2200)	loss 5.4935 (5.9103)	grad_norm 2.1996 (2.4297)	
[2022-01-17 15:05:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][710/1251]	eta 0:19:59 lr 0.000229	time 1.6723 (2.2168)	loss 6.1623 (5.9071)	grad_norm 2.3205 (2.4276)	
[2022-01-17 15:05:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][720/1251]	eta 0:19:36 lr 0.000230	time 2.8901 (2.2152)	loss 5.5641 (5.9037)	grad_norm 3.3519 (2.4253)	
[2022-01-17 15:05:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][730/1251]	eta 0:19:13 lr 0.000230	time 2.2934 (2.2138)	loss 6.0912 (5.9021)	grad_norm 3.1206 (2.4267)	
[2022-01-17 15:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][740/1251]	eta 0:18:50 lr 0.000230	time 1.9284 (2.2132)	loss 5.6659 (5.9008)	grad_norm 1.9270 (2.4254)	
[2022-01-17 15:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][750/1251]	eta 0:18:28 lr 0.000231	time 2.1903 (2.2131)	loss 5.8918 (5.9015)	grad_norm 2.4001 (2.4243)	
[2022-01-17 15:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][760/1251]	eta 0:18:06 lr 0.000231	time 2.5852 (2.2122)	loss 5.4428 (5.9016)	grad_norm 2.4777 (2.4234)	
[2022-01-17 15:07:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][770/1251]	eta 0:17:43 lr 0.000232	time 1.9418 (2.2105)	loss 5.1508 (5.8997)	grad_norm 3.4081 (2.4251)	
[2022-01-17 15:07:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][780/1251]	eta 0:17:21 lr 0.000232	time 2.2202 (2.2104)	loss 6.0610 (5.8993)	grad_norm 2.2918 (2.4251)	
[2022-01-17 15:07:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][790/1251]	eta 0:16:58 lr 0.000232	time 2.1419 (2.2093)	loss 6.3730 (5.8972)	grad_norm 3.1152 (2.4324)	
[2022-01-17 15:08:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][800/1251]	eta 0:16:37 lr 0.000233	time 2.5511 (2.2107)	loss 6.4012 (5.8963)	grad_norm 2.2193 (2.4355)	
[2022-01-17 15:08:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][810/1251]	eta 0:16:15 lr 0.000233	time 2.1979 (2.2120)	loss 5.6630 (5.8954)	grad_norm 2.0476 (2.4335)	
[2022-01-17 15:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][820/1251]	eta 0:15:54 lr 0.000234	time 2.6810 (2.2141)	loss 5.8260 (5.8966)	grad_norm 3.0775 (2.4335)	
[2022-01-17 15:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][830/1251]	eta 0:15:32 lr 0.000234	time 2.4367 (2.2139)	loss 6.0729 (5.8967)	grad_norm 2.1028 (2.4299)	
[2022-01-17 15:09:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][840/1251]	eta 0:15:10 lr 0.000234	time 3.7667 (2.2160)	loss 6.1733 (5.8963)	grad_norm 2.8335 (2.4305)	
[2022-01-17 15:10:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][850/1251]	eta 0:14:47 lr 0.000235	time 1.7529 (2.2141)	loss 6.0015 (5.8945)	grad_norm 2.1522 (2.4295)	
[2022-01-17 15:10:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][860/1251]	eta 0:14:25 lr 0.000235	time 2.5239 (2.2124)	loss 6.4188 (5.8967)	grad_norm 1.9125 (2.4276)	
[2022-01-17 15:10:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][870/1251]	eta 0:14:02 lr 0.000236	time 3.1455 (2.2105)	loss 6.3058 (5.8988)	grad_norm 1.9068 (2.4270)	
[2022-01-17 15:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][880/1251]	eta 0:13:39 lr 0.000236	time 1.8398 (2.2076)	loss 6.2396 (5.8991)	grad_norm 2.5846 (2.4271)	
[2022-01-17 15:11:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][890/1251]	eta 0:13:16 lr 0.000236	time 2.8510 (2.2071)	loss 5.6097 (5.8974)	grad_norm 2.2885 (2.4260)	
[2022-01-17 15:11:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][900/1251]	eta 0:12:54 lr 0.000237	time 2.5425 (2.2065)	loss 6.0994 (5.8946)	grad_norm 2.2819 (2.4249)	
[2022-01-17 15:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][910/1251]	eta 0:12:33 lr 0.000237	time 2.2271 (2.2101)	loss 5.5429 (5.8945)	grad_norm 2.5147 (2.4275)	
[2022-01-17 15:12:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][920/1251]	eta 0:12:12 lr 0.000238	time 1.8429 (2.2117)	loss 6.1743 (5.8949)	grad_norm 2.4093 (2.4268)	
[2022-01-17 15:13:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][930/1251]	eta 0:11:50 lr 0.000238	time 2.5766 (2.2129)	loss 6.1235 (5.8953)	grad_norm 2.2578 (2.4249)	
[2022-01-17 15:13:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][940/1251]	eta 0:11:28 lr 0.000238	time 1.9879 (2.2130)	loss 5.2546 (5.8962)	grad_norm 2.9661 (2.4238)	
[2022-01-17 15:13:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][950/1251]	eta 0:11:05 lr 0.000239	time 1.6886 (2.2113)	loss 5.6105 (5.8954)	grad_norm 2.4898 (2.4248)	
[2022-01-17 15:14:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][960/1251]	eta 0:10:42 lr 0.000239	time 2.0192 (2.2081)	loss 6.2279 (5.8937)	grad_norm 2.3842 (2.4228)	
[2022-01-17 15:14:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][970/1251]	eta 0:10:19 lr 0.000240	time 1.9246 (2.2060)	loss 5.8607 (5.8936)	grad_norm 2.5653 (2.4218)	
[2022-01-17 15:14:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][980/1251]	eta 0:09:57 lr 0.000240	time 2.4899 (2.2050)	loss 5.7865 (5.8938)	grad_norm 3.3007 (2.4214)	
[2022-01-17 15:15:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][990/1251]	eta 0:09:35 lr 0.000240	time 2.2527 (2.2064)	loss 6.0770 (5.8933)	grad_norm 3.1139 (2.4250)	
[2022-01-17 15:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1000/1251]	eta 0:09:13 lr 0.000241	time 1.3299 (2.2062)	loss 6.1032 (5.8927)	grad_norm 2.1883 (2.4228)	
[2022-01-17 15:16:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1010/1251]	eta 0:08:52 lr 0.000241	time 1.4935 (2.2102)	loss 5.9594 (5.8931)	grad_norm 1.9288 (2.4197)	
[2022-01-17 15:16:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1020/1251]	eta 0:08:30 lr 0.000242	time 3.9225 (2.2109)	loss 5.5846 (5.8911)	grad_norm 2.5344 (2.4192)	
[2022-01-17 15:16:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1030/1251]	eta 0:08:08 lr 0.000242	time 1.9275 (2.2094)	loss 5.8582 (5.8883)	grad_norm 2.7365 (2.4201)	
[2022-01-17 15:17:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1040/1251]	eta 0:07:45 lr 0.000242	time 2.0514 (2.2073)	loss 6.3006 (5.8870)	grad_norm 2.6867 (2.4210)	
[2022-01-17 15:17:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1050/1251]	eta 0:07:23 lr 0.000243	time 1.9051 (2.2053)	loss 5.9417 (5.8859)	grad_norm 2.7512 (2.4231)	
[2022-01-17 15:17:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1060/1251]	eta 0:07:01 lr 0.000243	time 2.1153 (2.2046)	loss 6.2573 (5.8861)	grad_norm 2.1002 (2.4231)	
[2022-01-17 15:18:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1070/1251]	eta 0:06:38 lr 0.000244	time 2.1702 (2.2040)	loss 6.3194 (5.8864)	grad_norm 2.6939 (2.4238)	
[2022-01-17 15:18:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1080/1251]	eta 0:06:16 lr 0.000244	time 2.1409 (2.2041)	loss 5.3330 (5.8857)	grad_norm 4.8270 (2.4262)	
[2022-01-17 15:18:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1090/1251]	eta 0:05:54 lr 0.000244	time 1.5340 (2.2048)	loss 5.3721 (5.8851)	grad_norm 2.4410 (2.4270)	
[2022-01-17 15:19:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1100/1251]	eta 0:05:32 lr 0.000245	time 2.5338 (2.2047)	loss 5.3314 (5.8843)	grad_norm 2.2475 (2.4277)	
[2022-01-17 15:19:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1110/1251]	eta 0:05:10 lr 0.000245	time 2.2259 (2.2051)	loss 6.1384 (5.8814)	grad_norm 2.1897 (2.4259)	
[2022-01-17 15:20:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1120/1251]	eta 0:04:49 lr 0.000246	time 2.7630 (2.2072)	loss 5.8807 (5.8815)	grad_norm 2.4380 (2.4251)	
[2022-01-17 15:20:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1130/1251]	eta 0:04:27 lr 0.000246	time 1.9315 (2.2066)	loss 5.3343 (5.8806)	grad_norm 2.4625 (2.4246)	
[2022-01-17 15:20:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1140/1251]	eta 0:04:04 lr 0.000246	time 1.7125 (2.2059)	loss 5.5830 (5.8778)	grad_norm 2.2427 (2.4248)	
[2022-01-17 15:21:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1150/1251]	eta 0:03:42 lr 0.000247	time 1.8880 (2.2037)	loss 6.1403 (5.8773)	grad_norm 2.0864 (2.4256)	
[2022-01-17 15:21:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1160/1251]	eta 0:03:20 lr 0.000247	time 1.9778 (2.2026)	loss 6.0812 (5.8762)	grad_norm 1.9479 (2.4244)	
[2022-01-17 15:21:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1170/1251]	eta 0:02:58 lr 0.000248	time 1.9441 (2.2016)	loss 6.1772 (5.8765)	grad_norm 1.9586 (2.4244)	
[2022-01-17 15:22:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1180/1251]	eta 0:02:36 lr 0.000248	time 2.2664 (2.2025)	loss 5.9483 (5.8754)	grad_norm 2.1045 (2.4267)	
[2022-01-17 15:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1190/1251]	eta 0:02:14 lr 0.000248	time 2.0938 (2.2030)	loss 5.4548 (5.8752)	grad_norm 2.1691 (2.4282)	
[2022-01-17 15:22:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1200/1251]	eta 0:01:52 lr 0.000249	time 2.1881 (2.2027)	loss 5.2244 (5.8752)	grad_norm 2.0910 (2.4287)	
[2022-01-17 15:23:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1210/1251]	eta 0:01:30 lr 0.000249	time 2.2517 (2.2021)	loss 5.2408 (5.8718)	grad_norm 2.3059 (2.4275)	
[2022-01-17 15:23:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1220/1251]	eta 0:01:08 lr 0.000250	time 2.2911 (2.2027)	loss 5.6506 (5.8717)	grad_norm 2.2740 (2.4249)	
[2022-01-17 15:23:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1230/1251]	eta 0:00:46 lr 0.000250	time 2.4120 (2.2030)	loss 5.9088 (5.8700)	grad_norm 2.4765 (2.4248)	
[2022-01-17 15:24:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1240/1251]	eta 0:00:24 lr 0.000250	time 1.4428 (2.2011)	loss 5.3789 (5.8701)	grad_norm 3.2412 (2.4271)	
[2022-01-17 15:24:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [4/300][1250/1251]	eta 0:00:02 lr 0.000251	time 1.1939 (2.1959)	loss 5.2699 (5.8709)	grad_norm 1.9052 (2.4255)	
[2022-01-17 15:24:35 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 4 training takes 0:45:47
[2022-01-17 15:24:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 21.206 (21.206)	Loss 3.9304 (3.9304)	Acc@1 24.121 (24.121)	Acc@5 48.438 (48.438)	
[2022-01-17 15:25:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.993 (3.467)	Loss 3.9135 (3.9179)	Acc@1 23.145 (24.325)	Acc@5 48.438 (47.567)	
[2022-01-17 15:25:32 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.971 (2.746)	Loss 3.8460 (3.8950)	Acc@1 26.172 (24.558)	Acc@5 49.512 (47.838)	
[2022-01-17 15:25:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.983 (2.390)	Loss 3.9851 (3.9065)	Acc@1 22.656 (24.181)	Acc@5 45.215 (47.628)	
[2022-01-17 15:26:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.732 (2.215)	Loss 3.9246 (3.9034)	Acc@1 20.996 (24.104)	Acc@5 45.117 (47.528)	
[2022-01-17 15:26:13 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 24.266 Acc@5 47.714
[2022-01-17 15:26:13 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 24.3%
[2022-01-17 15:26:13 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 24.27%
[2022-01-17 15:26:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][0/1251]	eta 6:45:29 lr 0.000251	time 19.4479 (19.4479)	loss 6.0224 (6.0224)	grad_norm 3.0411 (3.0411)	
[2022-01-17 15:26:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][10/1251]	eta 1:19:26 lr 0.000251	time 1.8640 (3.8408)	loss 6.0554 (5.9232)	grad_norm 2.2483 (2.4838)	
[2022-01-17 15:27:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][20/1251]	eta 1:05:12 lr 0.000252	time 2.3759 (3.1779)	loss 5.9189 (5.8541)	grad_norm 2.8394 (2.4562)	
[2022-01-17 15:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][30/1251]	eta 0:58:00 lr 0.000252	time 1.8528 (2.8506)	loss 5.2897 (5.8469)	grad_norm 1.9830 (2.5154)	
[2022-01-17 15:28:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][40/1251]	eta 0:54:59 lr 0.000252	time 3.4702 (2.7249)	loss 5.9929 (5.9120)	grad_norm 2.1941 (2.4499)	
[2022-01-17 15:28:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][50/1251]	eta 0:53:06 lr 0.000253	time 2.1640 (2.6532)	loss 6.0826 (5.9189)	grad_norm 2.5010 (2.4096)	
[2022-01-17 15:28:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][60/1251]	eta 0:51:18 lr 0.000253	time 1.7446 (2.5850)	loss 6.0264 (5.9088)	grad_norm 2.4593 (2.4747)	
[2022-01-17 15:29:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][70/1251]	eta 0:49:28 lr 0.000254	time 1.6932 (2.5137)	loss 5.2890 (5.9082)	grad_norm 3.2781 (2.4413)	
[2022-01-17 15:29:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][80/1251]	eta 0:48:17 lr 0.000254	time 2.7904 (2.4745)	loss 6.0208 (5.8909)	grad_norm 2.1545 (2.4736)	
[2022-01-17 15:29:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][90/1251]	eta 0:47:24 lr 0.000254	time 1.9036 (2.4499)	loss 6.0683 (5.8807)	grad_norm 2.0695 (2.4577)	
[2022-01-17 15:30:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][100/1251]	eta 0:46:07 lr 0.000255	time 1.8553 (2.4044)	loss 5.5676 (5.8601)	grad_norm 2.6133 (2.4390)	
[2022-01-17 15:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][110/1251]	eta 0:45:06 lr 0.000255	time 1.5265 (2.3724)	loss 6.3720 (5.8663)	grad_norm 1.7386 (2.4027)	
[2022-01-17 15:30:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][120/1251]	eta 0:44:18 lr 0.000256	time 2.1377 (2.3507)	loss 6.0705 (5.8712)	grad_norm 3.0779 (2.4107)	
[2022-01-17 15:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][130/1251]	eta 0:43:44 lr 0.000256	time 2.1727 (2.3412)	loss 6.1521 (5.8630)	grad_norm 2.6765 (2.4182)	
[2022-01-17 15:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][140/1251]	eta 0:43:06 lr 0.000256	time 2.2292 (2.3284)	loss 5.5152 (5.8570)	grad_norm 2.2857 (2.4099)	
[2022-01-17 15:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][150/1251]	eta 0:42:39 lr 0.000257	time 1.5238 (2.3245)	loss 6.2391 (5.8526)	grad_norm 2.9551 (2.4173)	
[2022-01-17 15:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][160/1251]	eta 0:42:08 lr 0.000257	time 2.1291 (2.3176)	loss 5.9970 (5.8484)	grad_norm 2.1334 (2.4154)	
[2022-01-17 15:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][170/1251]	eta 0:41:45 lr 0.000258	time 2.2014 (2.3180)	loss 5.6915 (5.8420)	grad_norm 2.7365 (2.4045)	
[2022-01-17 15:33:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][180/1251]	eta 0:41:15 lr 0.000258	time 2.1671 (2.3117)	loss 6.1744 (5.8257)	grad_norm 2.5360 (2.4087)	
[2022-01-17 15:33:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][190/1251]	eta 0:40:49 lr 0.000258	time 1.5817 (2.3087)	loss 5.1984 (5.8189)	grad_norm 2.2544 (2.4008)	
[2022-01-17 15:33:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][200/1251]	eta 0:40:18 lr 0.000259	time 1.9447 (2.3010)	loss 5.1591 (5.8142)	grad_norm 2.8550 (2.4174)	
[2022-01-17 15:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][210/1251]	eta 0:39:47 lr 0.000259	time 1.8658 (2.2932)	loss 5.0327 (5.8048)	grad_norm 2.4178 (2.4151)	
[2022-01-17 15:34:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][220/1251]	eta 0:39:10 lr 0.000260	time 1.7428 (2.2803)	loss 5.7383 (5.7927)	grad_norm 2.7204 (2.4185)	
[2022-01-17 15:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][230/1251]	eta 0:38:47 lr 0.000260	time 1.9148 (2.2796)	loss 6.1559 (5.7880)	grad_norm 2.9054 (2.4181)	
[2022-01-17 15:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][240/1251]	eta 0:38:25 lr 0.000260	time 1.5690 (2.2801)	loss 5.8985 (5.7875)	grad_norm 2.0965 (2.4165)	
[2022-01-17 15:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][250/1251]	eta 0:37:57 lr 0.000261	time 1.9055 (2.2753)	loss 5.9877 (5.7800)	grad_norm 1.9867 (2.4122)	
[2022-01-17 15:36:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][260/1251]	eta 0:37:30 lr 0.000261	time 1.9748 (2.2713)	loss 5.9258 (5.7820)	grad_norm 1.9658 (2.3989)	
[2022-01-17 15:36:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][270/1251]	eta 0:37:01 lr 0.000262	time 1.5707 (2.2650)	loss 6.0891 (5.7777)	grad_norm 2.5004 (2.4028)	
[2022-01-17 15:36:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][280/1251]	eta 0:36:37 lr 0.000262	time 1.8449 (2.2636)	loss 5.9378 (5.7770)	grad_norm 1.7696 (2.3944)	
[2022-01-17 15:37:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][290/1251]	eta 0:36:12 lr 0.000262	time 1.7473 (2.2610)	loss 6.0561 (5.7807)	grad_norm 2.0492 (2.3980)	
[2022-01-17 15:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][300/1251]	eta 0:35:52 lr 0.000263	time 1.8908 (2.2636)	loss 5.5026 (5.7789)	grad_norm 1.8008 (2.3978)	
[2022-01-17 15:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][310/1251]	eta 0:35:26 lr 0.000263	time 1.5581 (2.2598)	loss 5.6397 (5.7764)	grad_norm 2.4720 (2.3899)	
[2022-01-17 15:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][320/1251]	eta 0:34:58 lr 0.000264	time 1.5714 (2.2541)	loss 5.0320 (5.7764)	grad_norm 2.7693 (2.3907)	
[2022-01-17 15:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][330/1251]	eta 0:34:30 lr 0.000264	time 1.8878 (2.2481)	loss 5.8213 (5.7763)	grad_norm 2.0742 (2.3878)	
[2022-01-17 15:38:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][340/1251]	eta 0:34:05 lr 0.000264	time 1.9524 (2.2453)	loss 6.1008 (5.7766)	grad_norm 2.1977 (2.3818)	
[2022-01-17 15:39:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][350/1251]	eta 0:33:39 lr 0.000265	time 1.9584 (2.2411)	loss 4.8694 (5.7680)	grad_norm 3.0418 (2.3874)	
[2022-01-17 15:39:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][360/1251]	eta 0:33:17 lr 0.000265	time 1.8693 (2.2417)	loss 5.9239 (5.7668)	grad_norm 2.3950 (2.3972)	
[2022-01-17 15:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][370/1251]	eta 0:32:57 lr 0.000266	time 2.1389 (2.2447)	loss 5.8426 (5.7726)	grad_norm 2.0381 (2.3919)	
[2022-01-17 15:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][380/1251]	eta 0:32:40 lr 0.000266	time 2.6746 (2.2508)	loss 5.9706 (5.7693)	grad_norm 1.8355 (2.3904)	
[2022-01-17 15:40:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][390/1251]	eta 0:32:14 lr 0.000266	time 1.9014 (2.2467)	loss 6.0116 (5.7687)	grad_norm 2.1981 (2.3915)	
[2022-01-17 15:41:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][400/1251]	eta 0:31:46 lr 0.000267	time 1.5595 (2.2407)	loss 5.7714 (5.7637)	grad_norm 1.8630 (2.3950)	
[2022-01-17 15:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][410/1251]	eta 0:31:18 lr 0.000267	time 1.9280 (2.2333)	loss 6.0095 (5.7635)	grad_norm 2.2121 (2.3871)	
[2022-01-17 15:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][420/1251]	eta 0:30:53 lr 0.000268	time 2.2221 (2.2307)	loss 5.8148 (5.7593)	grad_norm 2.0596 (2.3867)	
[2022-01-17 15:42:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][430/1251]	eta 0:30:32 lr 0.000268	time 2.5326 (2.2325)	loss 5.5185 (5.7534)	grad_norm 1.9204 (2.3833)	
[2022-01-17 15:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][440/1251]	eta 0:30:11 lr 0.000268	time 2.4971 (2.2341)	loss 5.8988 (5.7503)	grad_norm 2.0517 (2.3817)	
[2022-01-17 15:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][450/1251]	eta 0:29:49 lr 0.000269	time 1.8632 (2.2336)	loss 6.1774 (5.7543)	grad_norm 2.3768 (2.3775)	
[2022-01-17 15:43:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][460/1251]	eta 0:29:29 lr 0.000269	time 1.6673 (2.2367)	loss 6.2480 (5.7553)	grad_norm 3.0520 (2.3734)	
[2022-01-17 15:43:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][470/1251]	eta 0:29:05 lr 0.000270	time 1.7472 (2.2353)	loss 5.0118 (5.7572)	grad_norm 2.0004 (2.3763)	
[2022-01-17 15:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][480/1251]	eta 0:28:41 lr 0.000270	time 1.8540 (2.2328)	loss 5.1098 (5.7553)	grad_norm 1.8082 (2.3733)	
[2022-01-17 15:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][490/1251]	eta 0:28:15 lr 0.000270	time 1.9383 (2.2277)	loss 5.2094 (5.7507)	grad_norm 2.3289 (2.3717)	
[2022-01-17 15:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][500/1251]	eta 0:27:51 lr 0.000271	time 2.0971 (2.2258)	loss 6.1950 (5.7499)	grad_norm 2.0303 (2.3669)	
[2022-01-17 15:45:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][510/1251]	eta 0:27:28 lr 0.000271	time 1.7754 (2.2245)	loss 5.5067 (5.7438)	grad_norm 2.3337 (2.3638)	
[2022-01-17 15:45:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][520/1251]	eta 0:27:10 lr 0.000272	time 2.6817 (2.2310)	loss 6.0399 (5.7448)	grad_norm 2.2912 (2.3654)	
[2022-01-17 15:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][530/1251]	eta 0:26:48 lr 0.000272	time 1.9308 (2.2303)	loss 5.5314 (5.7458)	grad_norm 2.2417 (2.3623)	
[2022-01-17 15:46:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][540/1251]	eta 0:26:25 lr 0.000272	time 2.2142 (2.2295)	loss 5.9567 (5.7492)	grad_norm 2.2516 (2.3667)	
[2022-01-17 15:46:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][550/1251]	eta 0:26:00 lr 0.000273	time 1.6941 (2.2254)	loss 4.9269 (5.7447)	grad_norm 2.7392 (2.3705)	
[2022-01-17 15:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][560/1251]	eta 0:25:38 lr 0.000273	time 2.7850 (2.2266)	loss 5.5517 (5.7453)	grad_norm 2.6486 (2.3806)	
[2022-01-17 15:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][570/1251]	eta 0:25:15 lr 0.000274	time 1.5864 (2.2248)	loss 5.7880 (5.7452)	grad_norm 1.8271 (2.3804)	
[2022-01-17 15:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][580/1251]	eta 0:24:52 lr 0.000274	time 1.8930 (2.2241)	loss 4.8881 (5.7435)	grad_norm 2.5434 (2.3762)	
[2022-01-17 15:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][590/1251]	eta 0:24:30 lr 0.000274	time 1.8140 (2.2242)	loss 6.0311 (5.7448)	grad_norm 1.9593 (2.3707)	
[2022-01-17 15:48:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][600/1251]	eta 0:24:10 lr 0.000275	time 2.8235 (2.2280)	loss 5.6644 (5.7388)	grad_norm 2.4366 (2.3706)	
[2022-01-17 15:48:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][610/1251]	eta 0:23:46 lr 0.000275	time 1.8642 (2.2248)	loss 5.4510 (5.7369)	grad_norm 2.6114 (2.3811)	
[2022-01-17 15:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][620/1251]	eta 0:23:21 lr 0.000276	time 1.8123 (2.2210)	loss 5.2509 (5.7378)	grad_norm 2.5723 (2.3777)	
[2022-01-17 15:49:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][630/1251]	eta 0:22:58 lr 0.000276	time 2.0698 (2.2201)	loss 6.2147 (5.7360)	grad_norm 1.7257 (2.3739)	
[2022-01-17 15:49:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][640/1251]	eta 0:22:36 lr 0.000276	time 3.1570 (2.2205)	loss 6.0428 (5.7351)	grad_norm 2.1645 (2.3710)	
[2022-01-17 15:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][650/1251]	eta 0:22:12 lr 0.000277	time 1.5646 (2.2178)	loss 4.9065 (5.7316)	grad_norm 2.2124 (2.3704)	
[2022-01-17 15:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][660/1251]	eta 0:21:50 lr 0.000277	time 1.9221 (2.2175)	loss 5.3014 (5.7312)	grad_norm 1.8974 (2.3649)	
[2022-01-17 15:50:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][670/1251]	eta 0:21:27 lr 0.000278	time 1.5428 (2.2160)	loss 5.1792 (5.7284)	grad_norm 2.0701 (2.3634)	
[2022-01-17 15:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][680/1251]	eta 0:21:05 lr 0.000278	time 2.0893 (2.2159)	loss 6.1828 (5.7299)	grad_norm 2.5025 (2.3629)	
[2022-01-17 15:51:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][690/1251]	eta 0:20:42 lr 0.000278	time 2.5343 (2.2140)	loss 5.9909 (5.7273)	grad_norm 3.3758 (2.3642)	
[2022-01-17 15:52:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][700/1251]	eta 0:20:20 lr 0.000279	time 2.8731 (2.2149)	loss 5.9146 (5.7243)	grad_norm 2.0846 (2.3604)	
[2022-01-17 15:52:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][710/1251]	eta 0:19:57 lr 0.000279	time 2.2004 (2.2135)	loss 5.4383 (5.7256)	grad_norm 2.4067 (2.3596)	
[2022-01-17 15:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][720/1251]	eta 0:19:36 lr 0.000279	time 1.9725 (2.2149)	loss 5.9692 (5.7236)	grad_norm 2.5024 (2.3623)	
[2022-01-17 15:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][730/1251]	eta 0:19:13 lr 0.000280	time 2.0194 (2.2146)	loss 5.3596 (5.7233)	grad_norm 2.1903 (2.3621)	
[2022-01-17 15:53:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][740/1251]	eta 0:18:52 lr 0.000280	time 3.0708 (2.2160)	loss 5.2196 (5.7217)	grad_norm 2.8078 (2.3668)	
[2022-01-17 15:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][750/1251]	eta 0:18:29 lr 0.000281	time 1.5723 (2.2141)	loss 5.3194 (5.7163)	grad_norm 1.9526 (2.3722)	
[2022-01-17 15:54:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][760/1251]	eta 0:18:07 lr 0.000281	time 1.9787 (2.2140)	loss 6.0995 (5.7174)	grad_norm 2.8381 (2.3717)	
[2022-01-17 15:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][770/1251]	eta 0:17:43 lr 0.000281	time 1.5758 (2.2120)	loss 6.0405 (5.7166)	grad_norm 1.9460 (2.3720)	
[2022-01-17 15:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][780/1251]	eta 0:17:22 lr 0.000282	time 3.1220 (2.2136)	loss 6.1353 (5.7162)	grad_norm 2.3367 (2.3712)	
[2022-01-17 15:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][790/1251]	eta 0:16:59 lr 0.000282	time 1.9054 (2.2125)	loss 5.9794 (5.7139)	grad_norm 2.2983 (2.3737)	
[2022-01-17 15:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][800/1251]	eta 0:16:37 lr 0.000283	time 1.9524 (2.2107)	loss 5.7590 (5.7121)	grad_norm 1.9144 (2.3746)	
[2022-01-17 15:56:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][810/1251]	eta 0:16:14 lr 0.000283	time 2.5951 (2.2088)	loss 5.5897 (5.7130)	grad_norm 2.1308 (2.3718)	
[2022-01-17 15:56:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][820/1251]	eta 0:15:51 lr 0.000283	time 2.2165 (2.2070)	loss 4.9747 (5.7107)	grad_norm 2.0915 (2.3713)	
[2022-01-17 15:56:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][830/1251]	eta 0:15:28 lr 0.000284	time 1.8477 (2.2064)	loss 5.3229 (5.7080)	grad_norm 2.0281 (2.3706)	
[2022-01-17 15:57:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][840/1251]	eta 0:15:07 lr 0.000284	time 3.3687 (2.2087)	loss 5.3743 (5.7087)	grad_norm 2.2207 (2.3681)	
[2022-01-17 15:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][850/1251]	eta 0:14:46 lr 0.000285	time 3.1788 (2.2107)	loss 5.3598 (5.7082)	grad_norm 2.2739 (2.3662)	
[2022-01-17 15:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][860/1251]	eta 0:14:24 lr 0.000285	time 2.1021 (2.2118)	loss 5.6329 (5.7069)	grad_norm 2.0069 (2.3630)	
[2022-01-17 15:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][870/1251]	eta 0:14:02 lr 0.000285	time 1.7527 (2.2117)	loss 6.0318 (5.7064)	grad_norm 1.9401 (2.3613)	
[2022-01-17 15:58:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][880/1251]	eta 0:13:40 lr 0.000286	time 1.8873 (2.2107)	loss 5.8030 (5.7061)	grad_norm 3.6187 (2.3685)	
[2022-01-17 15:59:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][890/1251]	eta 0:13:17 lr 0.000286	time 1.8911 (2.2084)	loss 6.1093 (5.7062)	grad_norm 1.8183 (2.3669)	
[2022-01-17 15:59:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][900/1251]	eta 0:12:54 lr 0.000287	time 2.5963 (2.2077)	loss 6.3258 (5.7097)	grad_norm 2.4584 (2.3654)	
[2022-01-17 15:59:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][910/1251]	eta 0:12:32 lr 0.000287	time 1.9705 (2.2074)	loss 5.3098 (5.7110)	grad_norm 1.8600 (2.3623)	
[2022-01-17 16:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][920/1251]	eta 0:12:10 lr 0.000287	time 1.8833 (2.2068)	loss 5.8743 (5.7117)	grad_norm 2.4657 (2.3621)	
[2022-01-17 16:00:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][930/1251]	eta 0:11:48 lr 0.000288	time 1.9065 (2.2083)	loss 5.4290 (5.7082)	grad_norm 2.1204 (2.3623)	
[2022-01-17 16:00:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][940/1251]	eta 0:11:27 lr 0.000288	time 2.5113 (2.2101)	loss 6.1273 (5.7071)	grad_norm 6.7107 (2.3695)	
[2022-01-17 16:01:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][950/1251]	eta 0:11:04 lr 0.000289	time 1.9093 (2.2090)	loss 5.1146 (5.7066)	grad_norm 1.7706 (2.3721)	
[2022-01-17 16:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][960/1251]	eta 0:10:41 lr 0.000289	time 1.7968 (2.2060)	loss 6.0876 (5.7054)	grad_norm 2.0927 (2.3718)	
[2022-01-17 16:01:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][970/1251]	eta 0:10:19 lr 0.000289	time 1.9206 (2.2048)	loss 5.7150 (5.7062)	grad_norm 2.3896 (2.3697)	
[2022-01-17 16:02:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][980/1251]	eta 0:09:57 lr 0.000290	time 2.1791 (2.2037)	loss 5.4255 (5.7055)	grad_norm 2.3115 (2.3677)	
[2022-01-17 16:02:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][990/1251]	eta 0:09:35 lr 0.000290	time 2.4919 (2.2046)	loss 5.2484 (5.7057)	grad_norm 3.4442 (2.3689)	
[2022-01-17 16:02:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1000/1251]	eta 0:09:13 lr 0.000291	time 1.7719 (2.2047)	loss 5.7221 (5.7039)	grad_norm 1.8781 (2.3693)	
[2022-01-17 16:03:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1010/1251]	eta 0:08:51 lr 0.000291	time 1.8682 (2.2056)	loss 5.9105 (5.7053)	grad_norm 1.7813 (2.3716)	
[2022-01-17 16:03:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1020/1251]	eta 0:08:29 lr 0.000291	time 2.6176 (2.2056)	loss 4.8789 (5.7053)	grad_norm 2.2658 (2.3740)	
[2022-01-17 16:04:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1030/1251]	eta 0:08:07 lr 0.000292	time 2.8278 (2.2054)	loss 5.8056 (5.7029)	grad_norm 2.6151 (2.3746)	
[2022-01-17 16:04:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1040/1251]	eta 0:07:44 lr 0.000292	time 1.6693 (2.2032)	loss 5.8491 (5.7029)	grad_norm 4.4444 (2.3797)	
[2022-01-17 16:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1050/1251]	eta 0:07:22 lr 0.000293	time 1.8803 (2.2026)	loss 5.2366 (5.7029)	grad_norm 2.3132 (2.3777)	
[2022-01-17 16:05:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1060/1251]	eta 0:07:00 lr 0.000293	time 1.6776 (2.2014)	loss 5.3220 (5.7029)	grad_norm 4.5584 (2.3779)	
[2022-01-17 16:05:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1070/1251]	eta 0:06:38 lr 0.000293	time 1.8525 (2.2009)	loss 5.0732 (5.7020)	grad_norm 2.4308 (2.3792)	
[2022-01-17 16:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1080/1251]	eta 0:06:16 lr 0.000294	time 2.5331 (2.1999)	loss 5.7745 (5.7008)	grad_norm 1.9473 (2.3760)	
[2022-01-17 16:06:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1090/1251]	eta 0:05:54 lr 0.000294	time 1.8966 (2.1992)	loss 6.4988 (5.7023)	grad_norm 2.4525 (2.3737)	
[2022-01-17 16:06:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1100/1251]	eta 0:05:32 lr 0.000295	time 1.7255 (2.1993)	loss 5.9702 (5.7019)	grad_norm 2.2560 (2.3711)	
[2022-01-17 16:06:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1110/1251]	eta 0:05:10 lr 0.000295	time 2.7734 (2.1993)	loss 5.6251 (5.7014)	grad_norm 1.8743 (2.3691)	
[2022-01-17 16:07:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1120/1251]	eta 0:04:48 lr 0.000295	time 2.7754 (2.1992)	loss 6.1316 (5.7002)	grad_norm 2.3936 (2.3674)	
[2022-01-17 16:07:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1130/1251]	eta 0:04:26 lr 0.000296	time 1.6826 (2.1995)	loss 5.6814 (5.6995)	grad_norm 1.8506 (2.3659)	
[2022-01-17 16:08:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1140/1251]	eta 0:04:04 lr 0.000296	time 1.7609 (2.2001)	loss 5.0043 (5.6991)	grad_norm 2.1873 (2.3657)	
[2022-01-17 16:08:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1150/1251]	eta 0:03:42 lr 0.000297	time 2.1154 (2.2006)	loss 5.5886 (5.6963)	grad_norm 2.5315 (2.3651)	
[2022-01-17 16:08:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1160/1251]	eta 0:03:20 lr 0.000297	time 2.6255 (2.2016)	loss 5.9483 (5.6962)	grad_norm 1.9622 (2.3651)	
[2022-01-17 16:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1170/1251]	eta 0:02:58 lr 0.000297	time 1.7864 (2.2019)	loss 5.7192 (5.6967)	grad_norm 1.7860 (2.3639)	
[2022-01-17 16:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1180/1251]	eta 0:02:36 lr 0.000298	time 1.9989 (2.2022)	loss 5.0546 (5.6951)	grad_norm 2.7388 (2.3630)	
[2022-01-17 16:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1190/1251]	eta 0:02:14 lr 0.000298	time 2.0429 (2.2022)	loss 5.5774 (5.6925)	grad_norm 2.2932 (2.3607)	
[2022-01-17 16:10:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1200/1251]	eta 0:01:52 lr 0.000299	time 2.2350 (2.2004)	loss 5.8520 (5.6919)	grad_norm 2.6439 (2.3605)	
[2022-01-17 16:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1210/1251]	eta 0:01:30 lr 0.000299	time 2.2368 (2.1990)	loss 5.4971 (5.6914)	grad_norm 2.2443 (2.3598)	
[2022-01-17 16:10:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1220/1251]	eta 0:01:08 lr 0.000299	time 1.8885 (2.1980)	loss 5.1881 (5.6912)	grad_norm 2.7189 (2.3608)	
[2022-01-17 16:11:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1230/1251]	eta 0:00:46 lr 0.000300	time 1.5721 (2.1976)	loss 5.3203 (5.6906)	grad_norm 2.1940 (2.3641)	
[2022-01-17 16:11:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1240/1251]	eta 0:00:24 lr 0.000300	time 1.2788 (2.1968)	loss 4.6206 (5.6892)	grad_norm 1.8406 (2.3618)	
[2022-01-17 16:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [5/300][1250/1251]	eta 0:00:02 lr 0.000301	time 1.1898 (2.1914)	loss 5.7076 (5.6891)	grad_norm 1.7871 (2.3591)	
[2022-01-17 16:11:54 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 5 training takes 0:45:41
[2022-01-17 16:12:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.980 (16.980)	Loss 3.5713 (3.5713)	Acc@1 27.637 (27.637)	Acc@5 54.297 (54.297)	
[2022-01-17 16:12:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.683 (3.358)	Loss 3.6069 (3.5118)	Acc@1 27.637 (29.395)	Acc@5 52.637 (54.714)	
[2022-01-17 16:12:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.623 (2.754)	Loss 3.5022 (3.5147)	Acc@1 30.566 (29.311)	Acc@5 54.395 (54.511)	
[2022-01-17 16:13:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.932 (2.313)	Loss 3.4529 (3.5254)	Acc@1 30.957 (29.338)	Acc@5 54.980 (54.256)	
[2022-01-17 16:13:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.976 (2.134)	Loss 3.3649 (3.5216)	Acc@1 30.957 (29.421)	Acc@5 57.031 (54.294)	
[2022-01-17 16:13:31 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 29.462 Acc@5 54.256
[2022-01-17 16:13:31 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 29.5%
[2022-01-17 16:13:31 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 29.46%
[2022-01-17 16:13:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][0/1251]	eta 7:12:24 lr 0.000301	time 20.7389 (20.7389)	loss 4.8401 (4.8401)	grad_norm 1.9478 (1.9478)	
[2022-01-17 16:14:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][10/1251]	eta 1:24:01 lr 0.000301	time 2.0276 (4.0626)	loss 5.4890 (5.4848)	grad_norm 1.9951 (1.9868)	
[2022-01-17 16:14:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][20/1251]	eta 1:05:09 lr 0.000301	time 2.2447 (3.1762)	loss 5.3681 (5.4613)	grad_norm 2.0714 (2.0977)	
[2022-01-17 16:14:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][30/1251]	eta 0:57:10 lr 0.000302	time 1.5881 (2.8098)	loss 5.5823 (5.4788)	grad_norm 2.2066 (2.3284)	
[2022-01-17 16:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][40/1251]	eta 0:53:48 lr 0.000302	time 3.2591 (2.6663)	loss 5.6912 (5.5324)	grad_norm 2.6967 (2.3506)	
[2022-01-17 16:15:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][50/1251]	eta 0:53:04 lr 0.000303	time 2.4018 (2.6515)	loss 4.8912 (5.5166)	grad_norm 1.9645 (2.3385)	
[2022-01-17 16:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][60/1251]	eta 0:51:06 lr 0.000303	time 1.7745 (2.5750)	loss 5.6205 (5.4876)	grad_norm 1.6853 (2.3067)	
[2022-01-17 16:16:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][70/1251]	eta 0:49:13 lr 0.000303	time 1.9153 (2.5005)	loss 5.5042 (5.5209)	grad_norm 2.1946 (2.3361)	
[2022-01-17 16:16:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][80/1251]	eta 0:48:19 lr 0.000304	time 2.2310 (2.4761)	loss 5.8043 (5.5481)	grad_norm 1.9639 (2.3269)	
[2022-01-17 16:17:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][90/1251]	eta 0:47:31 lr 0.000304	time 2.7826 (2.4564)	loss 5.9561 (5.5436)	grad_norm 1.9492 (2.3310)	
[2022-01-17 16:17:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][100/1251]	eta 0:46:42 lr 0.000305	time 1.4906 (2.4346)	loss 6.0848 (5.5573)	grad_norm 1.9930 (2.3056)	
[2022-01-17 16:17:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][110/1251]	eta 0:45:36 lr 0.000305	time 1.6241 (2.3985)	loss 6.1303 (5.5439)	grad_norm 1.6738 (2.3094)	
[2022-01-17 16:18:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][120/1251]	eta 0:45:17 lr 0.000305	time 3.4490 (2.4026)	loss 5.9923 (5.5510)	grad_norm 2.1739 (2.3001)	
[2022-01-17 16:18:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][130/1251]	eta 0:44:37 lr 0.000306	time 1.7649 (2.3888)	loss 5.2388 (5.5615)	grad_norm 3.5102 (2.3060)	
[2022-01-17 16:19:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][140/1251]	eta 0:43:58 lr 0.000306	time 1.9115 (2.3746)	loss 6.0087 (5.5612)	grad_norm 1.9206 (2.2893)	
[2022-01-17 16:19:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][150/1251]	eta 0:42:56 lr 0.000307	time 1.7220 (2.3403)	loss 5.7084 (5.5694)	grad_norm 2.6410 (2.2904)	
[2022-01-17 16:19:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][160/1251]	eta 0:42:08 lr 0.000307	time 1.8837 (2.3176)	loss 5.5754 (5.5840)	grad_norm 2.0437 (2.2837)	
[2022-01-17 16:20:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][170/1251]	eta 0:41:35 lr 0.000307	time 1.9241 (2.3082)	loss 5.4819 (5.5825)	grad_norm 2.1559 (2.2674)	
[2022-01-17 16:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][180/1251]	eta 0:41:10 lr 0.000308	time 2.9732 (2.3071)	loss 5.2171 (5.5788)	grad_norm 3.0965 (2.2764)	
[2022-01-17 16:20:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][190/1251]	eta 0:40:41 lr 0.000308	time 1.7154 (2.3011)	loss 5.3924 (5.5833)	grad_norm 2.0239 (2.2650)	
[2022-01-17 16:21:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][200/1251]	eta 0:40:18 lr 0.000309	time 2.7298 (2.3014)	loss 5.5659 (5.5883)	grad_norm 1.8069 (2.2547)	
[2022-01-17 16:21:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][210/1251]	eta 0:39:57 lr 0.000309	time 1.6082 (2.3027)	loss 6.1216 (5.5847)	grad_norm 2.8408 (2.2588)	
[2022-01-17 16:21:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][220/1251]	eta 0:39:23 lr 0.000309	time 1.5653 (2.2921)	loss 5.7034 (5.5650)	grad_norm 2.5757 (2.2613)	
[2022-01-17 16:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][230/1251]	eta 0:38:48 lr 0.000310	time 1.7433 (2.2808)	loss 5.9792 (5.5670)	grad_norm 3.9804 (2.2762)	
[2022-01-17 16:22:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][240/1251]	eta 0:38:14 lr 0.000310	time 1.8582 (2.2691)	loss 6.1605 (5.5658)	grad_norm 2.4373 (2.2894)	
[2022-01-17 16:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][250/1251]	eta 0:37:46 lr 0.000311	time 1.8656 (2.2646)	loss 5.6367 (5.5625)	grad_norm 2.4801 (2.2846)	
[2022-01-17 16:23:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][260/1251]	eta 0:37:22 lr 0.000311	time 2.2962 (2.2629)	loss 5.9826 (5.5624)	grad_norm 2.3115 (2.2816)	
[2022-01-17 16:23:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][270/1251]	eta 0:37:01 lr 0.000311	time 2.1584 (2.2647)	loss 6.0896 (5.5623)	grad_norm 1.9047 (2.2954)	
[2022-01-17 16:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][280/1251]	eta 0:36:32 lr 0.000312	time 1.5743 (2.2583)	loss 6.0004 (5.5569)	grad_norm 1.9236 (2.2942)	
[2022-01-17 16:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][290/1251]	eta 0:36:11 lr 0.000312	time 2.4880 (2.2601)	loss 5.7982 (5.5592)	grad_norm 2.3109 (2.2971)	
[2022-01-17 16:24:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][300/1251]	eta 0:35:42 lr 0.000313	time 1.5784 (2.2528)	loss 5.5137 (5.5552)	grad_norm 1.9628 (2.2905)	
[2022-01-17 16:25:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][310/1251]	eta 0:35:19 lr 0.000313	time 2.2019 (2.2522)	loss 5.8576 (5.5573)	grad_norm 2.1125 (2.2852)	
[2022-01-17 16:25:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][320/1251]	eta 0:34:53 lr 0.000313	time 1.6982 (2.2488)	loss 5.3123 (5.5535)	grad_norm 2.8586 (2.2905)	
[2022-01-17 16:25:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][330/1251]	eta 0:34:30 lr 0.000314	time 2.9036 (2.2481)	loss 6.1558 (5.5585)	grad_norm 2.9665 (2.2908)	
[2022-01-17 16:26:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][340/1251]	eta 0:34:01 lr 0.000314	time 1.9097 (2.2415)	loss 5.7998 (5.5562)	grad_norm 2.0023 (2.2881)	
[2022-01-17 16:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][350/1251]	eta 0:33:41 lr 0.000315	time 3.1477 (2.2433)	loss 5.8371 (5.5530)	grad_norm 1.7544 (2.2816)	
[2022-01-17 16:27:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][360/1251]	eta 0:33:19 lr 0.000315	time 1.9279 (2.2441)	loss 5.8916 (5.5585)	grad_norm 1.8633 (2.2749)	
[2022-01-17 16:27:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][370/1251]	eta 0:33:02 lr 0.000315	time 2.2874 (2.2504)	loss 5.6372 (5.5613)	grad_norm 2.1860 (2.2698)	
[2022-01-17 16:27:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][380/1251]	eta 0:32:39 lr 0.000316	time 2.3358 (2.2500)	loss 5.8891 (5.5596)	grad_norm 2.8021 (2.2782)	
[2022-01-17 16:28:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][390/1251]	eta 0:32:10 lr 0.000316	time 1.8126 (2.2419)	loss 5.4769 (5.5624)	grad_norm 2.2643 (2.2797)	
[2022-01-17 16:28:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][400/1251]	eta 0:31:38 lr 0.000317	time 2.0097 (2.2308)	loss 5.8063 (5.5679)	grad_norm 2.1462 (2.2766)	
[2022-01-17 16:28:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][410/1251]	eta 0:31:10 lr 0.000317	time 1.8987 (2.2238)	loss 4.8311 (5.5633)	grad_norm 2.2016 (2.2777)	
[2022-01-17 16:29:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][420/1251]	eta 0:30:45 lr 0.000317	time 2.5222 (2.2204)	loss 6.1600 (5.5633)	grad_norm 2.6601 (2.2781)	
[2022-01-17 16:29:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][430/1251]	eta 0:30:28 lr 0.000318	time 5.7390 (2.2267)	loss 5.8288 (5.5603)	grad_norm 1.8923 (2.2782)	
[2022-01-17 16:29:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][440/1251]	eta 0:30:07 lr 0.000318	time 1.7046 (2.2283)	loss 5.4962 (5.5631)	grad_norm 2.2100 (2.2829)	
[2022-01-17 16:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][450/1251]	eta 0:29:47 lr 0.000319	time 2.3662 (2.2316)	loss 5.7109 (5.5579)	grad_norm 1.7688 (2.2804)	
[2022-01-17 16:30:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][460/1251]	eta 0:29:24 lr 0.000319	time 1.9124 (2.2307)	loss 4.5377 (5.5551)	grad_norm 2.5391 (2.2778)	
[2022-01-17 16:31:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][470/1251]	eta 0:29:01 lr 0.000319	time 2.5527 (2.2303)	loss 5.6360 (5.5551)	grad_norm 2.4368 (2.2777)	
[2022-01-17 16:31:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][480/1251]	eta 0:28:39 lr 0.000320	time 1.9140 (2.2302)	loss 5.8408 (5.5531)	grad_norm 2.7659 (2.2798)	
[2022-01-17 16:31:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][490/1251]	eta 0:28:18 lr 0.000320	time 3.0783 (2.2318)	loss 4.8119 (5.5506)	grad_norm 3.7198 (2.2797)	
[2022-01-17 16:32:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][500/1251]	eta 0:27:53 lr 0.000321	time 1.6168 (2.2289)	loss 5.9015 (5.5497)	grad_norm 1.6967 (2.2886)	
[2022-01-17 16:32:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][510/1251]	eta 0:27:30 lr 0.000321	time 2.2750 (2.2272)	loss 5.2145 (5.5478)	grad_norm 2.3724 (2.2859)	
[2022-01-17 16:32:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][520/1251]	eta 0:27:07 lr 0.000321	time 1.8678 (2.2261)	loss 5.4198 (5.5434)	grad_norm 1.9990 (2.2816)	
[2022-01-17 16:33:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][530/1251]	eta 0:26:43 lr 0.000322	time 2.2348 (2.2244)	loss 5.8779 (5.5457)	grad_norm 1.7365 (2.2802)	
[2022-01-17 16:33:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][540/1251]	eta 0:26:20 lr 0.000322	time 1.8502 (2.2236)	loss 5.5697 (5.5427)	grad_norm 1.7414 (2.2764)	
[2022-01-17 16:33:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][550/1251]	eta 0:25:57 lr 0.000323	time 1.5814 (2.2223)	loss 4.9109 (5.5379)	grad_norm 2.1845 (2.2729)	
[2022-01-17 16:34:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][560/1251]	eta 0:25:36 lr 0.000323	time 1.9924 (2.2236)	loss 6.0560 (5.5386)	grad_norm 2.1874 (2.2764)	
[2022-01-17 16:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][570/1251]	eta 0:25:13 lr 0.000323	time 2.2410 (2.2225)	loss 6.0337 (5.5415)	grad_norm 3.0446 (2.2749)	
[2022-01-17 16:35:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][580/1251]	eta 0:24:48 lr 0.000324	time 2.2508 (2.2179)	loss 5.6033 (5.5411)	grad_norm 1.8585 (2.2758)	
[2022-01-17 16:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][590/1251]	eta 0:24:25 lr 0.000324	time 1.8740 (2.2173)	loss 5.7711 (5.5448)	grad_norm 1.9674 (2.2723)	
[2022-01-17 16:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][600/1251]	eta 0:24:03 lr 0.000325	time 2.2452 (2.2176)	loss 5.9988 (5.5417)	grad_norm 2.1219 (2.2730)	
[2022-01-17 16:36:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][610/1251]	eta 0:23:41 lr 0.000325	time 2.2411 (2.2183)	loss 5.1475 (5.5387)	grad_norm 2.2555 (2.2777)	
[2022-01-17 16:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][620/1251]	eta 0:23:19 lr 0.000325	time 2.3786 (2.2181)	loss 6.0069 (5.5405)	grad_norm 2.4435 (2.2769)	
[2022-01-17 16:36:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][630/1251]	eta 0:22:56 lr 0.000326	time 2.0125 (2.2158)	loss 5.3204 (5.5385)	grad_norm 2.2127 (2.2768)	
[2022-01-17 16:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][640/1251]	eta 0:22:33 lr 0.000326	time 2.2152 (2.2156)	loss 5.0552 (5.5398)	grad_norm 2.1375 (2.2780)	
[2022-01-17 16:37:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][650/1251]	eta 0:22:10 lr 0.000327	time 2.0289 (2.2143)	loss 5.5393 (5.5388)	grad_norm 1.9092 (2.2753)	
[2022-01-17 16:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][660/1251]	eta 0:21:49 lr 0.000327	time 2.5572 (2.2151)	loss 5.8101 (5.5370)	grad_norm 2.8929 (2.2758)	
[2022-01-17 16:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][670/1251]	eta 0:21:27 lr 0.000327	time 2.4246 (2.2159)	loss 5.7909 (5.5385)	grad_norm 2.0941 (2.2744)	
[2022-01-17 16:38:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][680/1251]	eta 0:21:04 lr 0.000328	time 1.6000 (2.2144)	loss 5.8570 (5.5406)	grad_norm 2.3653 (2.2750)	
[2022-01-17 16:38:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][690/1251]	eta 0:20:40 lr 0.000328	time 1.6076 (2.2112)	loss 5.6102 (5.5390)	grad_norm 2.0166 (2.2724)	
[2022-01-17 16:39:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][700/1251]	eta 0:20:17 lr 0.000329	time 2.5433 (2.2101)	loss 5.9363 (5.5399)	grad_norm 2.2933 (2.2758)	
[2022-01-17 16:39:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][710/1251]	eta 0:19:55 lr 0.000329	time 2.2780 (2.2099)	loss 5.8168 (5.5385)	grad_norm 1.9649 (2.2741)	
[2022-01-17 16:40:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][720/1251]	eta 0:19:32 lr 0.000329	time 2.2430 (2.2080)	loss 4.8964 (5.5355)	grad_norm 2.5557 (2.2739)	
[2022-01-17 16:40:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][730/1251]	eta 0:19:09 lr 0.000330	time 1.9061 (2.2067)	loss 4.9259 (5.5336)	grad_norm 1.9944 (2.2769)	
[2022-01-17 16:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][740/1251]	eta 0:18:47 lr 0.000330	time 2.1284 (2.2064)	loss 5.8784 (5.5340)	grad_norm 1.8842 (2.2755)	
[2022-01-17 16:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][750/1251]	eta 0:18:25 lr 0.000331	time 1.5774 (2.2070)	loss 6.0222 (5.5342)	grad_norm 1.8800 (2.2747)	
[2022-01-17 16:41:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][760/1251]	eta 0:18:04 lr 0.000331	time 2.7262 (2.2083)	loss 5.7142 (5.5371)	grad_norm 2.7140 (2.2740)	
[2022-01-17 16:41:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][770/1251]	eta 0:17:42 lr 0.000331	time 1.9203 (2.2085)	loss 6.0950 (5.5381)	grad_norm 2.4528 (2.2753)	
[2022-01-17 16:42:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][780/1251]	eta 0:17:20 lr 0.000332	time 1.8858 (2.2091)	loss 5.5456 (5.5375)	grad_norm 2.4756 (2.2776)	
[2022-01-17 16:42:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][790/1251]	eta 0:16:58 lr 0.000332	time 2.0100 (2.2096)	loss 5.5669 (5.5378)	grad_norm 1.8412 (2.2777)	
[2022-01-17 16:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][800/1251]	eta 0:16:36 lr 0.000333	time 2.5739 (2.2091)	loss 4.9090 (5.5350)	grad_norm 1.9994 (2.2772)	
[2022-01-17 16:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][810/1251]	eta 0:16:12 lr 0.000333	time 1.9027 (2.2056)	loss 5.6617 (5.5342)	grad_norm 2.3041 (2.2751)	
[2022-01-17 16:43:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][820/1251]	eta 0:15:49 lr 0.000333	time 1.9432 (2.2020)	loss 4.6357 (5.5344)	grad_norm 3.0800 (2.2751)	
[2022-01-17 16:44:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][830/1251]	eta 0:15:26 lr 0.000334	time 1.9398 (2.2010)	loss 5.4513 (5.5348)	grad_norm 1.9768 (2.2743)	
[2022-01-17 16:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][840/1251]	eta 0:15:04 lr 0.000334	time 2.0606 (2.2007)	loss 5.7631 (5.5322)	grad_norm 1.9251 (2.2734)	
[2022-01-17 16:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][850/1251]	eta 0:14:42 lr 0.000335	time 2.3305 (2.2000)	loss 5.9971 (5.5333)	grad_norm 2.8013 (2.2750)	
[2022-01-17 16:45:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][860/1251]	eta 0:14:20 lr 0.000335	time 2.8091 (2.2013)	loss 5.0790 (5.5334)	grad_norm 2.8112 (2.2743)	
[2022-01-17 16:45:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][870/1251]	eta 0:13:58 lr 0.000335	time 1.5357 (2.2021)	loss 5.5590 (5.5342)	grad_norm 2.2007 (2.2745)	
[2022-01-17 16:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][880/1251]	eta 0:13:36 lr 0.000336	time 1.8292 (2.2021)	loss 5.7645 (5.5354)	grad_norm 1.8195 (2.2715)	
[2022-01-17 16:46:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][890/1251]	eta 0:13:15 lr 0.000336	time 2.1658 (2.2045)	loss 5.2864 (5.5367)	grad_norm 1.7080 (2.2743)	
[2022-01-17 16:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][900/1251]	eta 0:12:54 lr 0.000337	time 2.6850 (2.2053)	loss 5.3490 (5.5369)	grad_norm 2.0005 (2.2741)	
[2022-01-17 16:46:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][910/1251]	eta 0:12:31 lr 0.000337	time 1.5958 (2.2042)	loss 5.3534 (5.5343)	grad_norm 2.1514 (2.2728)	
[2022-01-17 16:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][920/1251]	eta 0:12:08 lr 0.000337	time 1.7955 (2.2020)	loss 5.6516 (5.5340)	grad_norm 1.8866 (2.2738)	
[2022-01-17 16:47:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][930/1251]	eta 0:11:46 lr 0.000338	time 1.8316 (2.2011)	loss 6.0549 (5.5334)	grad_norm 2.3530 (2.2717)	
[2022-01-17 16:48:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][940/1251]	eta 0:11:24 lr 0.000338	time 1.7914 (2.2002)	loss 5.3071 (5.5351)	grad_norm 2.7803 (2.2751)	
[2022-01-17 16:48:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][950/1251]	eta 0:11:03 lr 0.000339	time 2.6026 (2.2031)	loss 5.7710 (5.5362)	grad_norm 2.5781 (2.2724)	
[2022-01-17 16:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][960/1251]	eta 0:10:41 lr 0.000339	time 2.5335 (2.2040)	loss 5.5571 (5.5360)	grad_norm 2.3728 (2.2711)	
[2022-01-17 16:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][970/1251]	eta 0:10:19 lr 0.000339	time 1.8494 (2.2052)	loss 5.3675 (5.5342)	grad_norm 3.2376 (2.2719)	
[2022-01-17 16:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][980/1251]	eta 0:09:57 lr 0.000340	time 1.8026 (2.2046)	loss 5.7792 (5.5314)	grad_norm 1.9636 (2.2706)	
[2022-01-17 16:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][990/1251]	eta 0:09:34 lr 0.000340	time 1.6504 (2.2023)	loss 5.9542 (5.5341)	grad_norm 2.5676 (2.2728)	
[2022-01-17 16:50:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1000/1251]	eta 0:09:12 lr 0.000341	time 1.6041 (2.1996)	loss 5.8801 (5.5342)	grad_norm 1.8692 (2.2698)	
[2022-01-17 16:50:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1010/1251]	eta 0:08:49 lr 0.000341	time 2.3381 (2.1984)	loss 4.5887 (5.5328)	grad_norm 1.8779 (2.2702)	
[2022-01-17 16:50:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1020/1251]	eta 0:08:27 lr 0.000341	time 2.9722 (2.1980)	loss 4.6826 (5.5330)	grad_norm 2.0678 (2.2703)	
[2022-01-17 16:51:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1030/1251]	eta 0:08:05 lr 0.000342	time 2.7292 (2.1972)	loss 5.3999 (5.5334)	grad_norm 1.8626 (2.2699)	
[2022-01-17 16:51:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1040/1251]	eta 0:07:43 lr 0.000342	time 2.2106 (2.1978)	loss 4.9076 (5.5341)	grad_norm 2.8893 (2.2719)	
[2022-01-17 16:52:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1050/1251]	eta 0:07:22 lr 0.000343	time 2.8005 (2.2007)	loss 5.6196 (5.5359)	grad_norm 2.0281 (2.2735)	
[2022-01-17 16:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1060/1251]	eta 0:07:00 lr 0.000343	time 2.1572 (2.2014)	loss 5.6966 (5.5360)	grad_norm 2.6518 (2.2710)	
[2022-01-17 16:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1070/1251]	eta 0:06:38 lr 0.000343	time 2.5326 (2.2014)	loss 5.0309 (5.5343)	grad_norm 2.1880 (2.2723)	
[2022-01-17 16:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1080/1251]	eta 0:06:16 lr 0.000344	time 1.8750 (2.2007)	loss 6.0496 (5.5330)	grad_norm 2.5213 (2.2700)	
[2022-01-17 16:53:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1090/1251]	eta 0:05:53 lr 0.000344	time 2.3688 (2.1987)	loss 4.9608 (5.5342)	grad_norm 2.2303 (2.2682)	
[2022-01-17 16:53:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1100/1251]	eta 0:05:31 lr 0.000345	time 2.1616 (2.1985)	loss 5.8436 (5.5345)	grad_norm 2.1690 (2.2653)	
[2022-01-17 16:54:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1110/1251]	eta 0:05:09 lr 0.000345	time 2.1008 (2.1975)	loss 5.4943 (5.5341)	grad_norm 2.1891 (2.2626)	
[2022-01-17 16:54:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1120/1251]	eta 0:04:47 lr 0.000345	time 2.1688 (2.1965)	loss 4.8863 (5.5338)	grad_norm 2.8013 (2.2619)	
[2022-01-17 16:54:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1130/1251]	eta 0:04:25 lr 0.000346	time 1.8803 (2.1961)	loss 5.0609 (5.5324)	grad_norm 2.9656 (2.2626)	
[2022-01-17 16:55:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1140/1251]	eta 0:04:03 lr 0.000346	time 2.5020 (2.1957)	loss 4.4019 (5.5328)	grad_norm 2.0776 (2.2635)	
[2022-01-17 16:55:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1150/1251]	eta 0:03:41 lr 0.000347	time 2.5033 (2.1947)	loss 4.8791 (5.5307)	grad_norm 1.7723 (2.2611)	
[2022-01-17 16:56:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1160/1251]	eta 0:03:19 lr 0.000347	time 2.1434 (2.1965)	loss 6.0802 (5.5297)	grad_norm 2.5291 (2.2603)	
[2022-01-17 16:56:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1170/1251]	eta 0:02:57 lr 0.000347	time 1.8844 (2.1968)	loss 4.9475 (5.5287)	grad_norm 1.9919 (2.2608)	
[2022-01-17 16:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1180/1251]	eta 0:02:36 lr 0.000348	time 2.6156 (2.1983)	loss 5.6080 (5.5268)	grad_norm 2.0328 (2.2582)	
[2022-01-17 16:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1190/1251]	eta 0:02:14 lr 0.000348	time 2.5049 (2.1982)	loss 4.9995 (5.5254)	grad_norm 1.8657 (2.2563)	
[2022-01-17 16:57:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1200/1251]	eta 0:01:52 lr 0.000349	time 1.9001 (2.1966)	loss 5.2344 (5.5258)	grad_norm 1.7630 (2.2572)	
[2022-01-17 16:57:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1210/1251]	eta 0:01:30 lr 0.000349	time 2.5508 (2.1954)	loss 5.3344 (5.5250)	grad_norm 1.9575 (2.2561)	
[2022-01-17 16:58:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1220/1251]	eta 0:01:08 lr 0.000349	time 2.1670 (2.1942)	loss 4.7634 (5.5249)	grad_norm 1.8831 (2.2557)	
[2022-01-17 16:58:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1230/1251]	eta 0:00:46 lr 0.000350	time 1.9660 (2.1930)	loss 6.1439 (5.5252)	grad_norm 2.0656 (2.2541)	
[2022-01-17 16:58:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1240/1251]	eta 0:00:24 lr 0.000350	time 1.7771 (2.1932)	loss 5.7630 (5.5259)	grad_norm 1.8911 (2.2530)	
[2022-01-17 16:59:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [6/300][1250/1251]	eta 0:00:02 lr 0.000351	time 1.1650 (2.1881)	loss 5.3130 (5.5265)	grad_norm 1.9578 (2.2545)	
[2022-01-17 16:59:09 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 6 training takes 0:45:37
[2022-01-17 16:59:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.667 (18.667)	Loss 3.2093 (3.2093)	Acc@1 34.180 (34.180)	Acc@5 59.863 (59.863)	
[2022-01-17 16:59:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.562 (3.403)	Loss 3.1572 (3.2280)	Acc@1 33.691 (33.958)	Acc@5 61.035 (59.482)	
[2022-01-17 17:00:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.611 (2.530)	Loss 3.2199 (3.2240)	Acc@1 35.645 (34.189)	Acc@5 60.449 (59.882)	
[2022-01-17 17:00:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.919 (2.304)	Loss 3.2568 (3.2263)	Acc@1 33.301 (34.249)	Acc@5 58.203 (59.939)	
[2022-01-17 17:00:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.898 (2.203)	Loss 3.1165 (3.2176)	Acc@1 36.328 (34.201)	Acc@5 61.426 (60.056)	
[2022-01-17 17:00:46 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 34.096 Acc@5 59.946
[2022-01-17 17:00:46 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 34.1%
[2022-01-17 17:00:46 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 34.10%
[2022-01-17 17:01:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][0/1251]	eta 7:36:34 lr 0.000351	time 21.8983 (21.8983)	loss 5.5266 (5.5266)	grad_norm 1.8854 (1.8854)	
[2022-01-17 17:01:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][10/1251]	eta 1:25:22 lr 0.000351	time 1.7810 (4.1276)	loss 6.0473 (5.5233)	grad_norm 1.8507 (1.9736)	
[2022-01-17 17:01:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][20/1251]	eta 1:04:23 lr 0.000351	time 1.4187 (3.1385)	loss 5.8783 (5.4609)	grad_norm 2.5489 (2.1482)	
[2022-01-17 17:02:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][30/1251]	eta 0:57:13 lr 0.000352	time 1.3888 (2.8118)	loss 5.7280 (5.4982)	grad_norm 2.1928 (2.1890)	
[2022-01-17 17:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][40/1251]	eta 0:55:11 lr 0.000352	time 6.2666 (2.7343)	loss 5.3535 (5.4989)	grad_norm 2.2627 (2.2440)	
[2022-01-17 17:03:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][50/1251]	eta 0:52:43 lr 0.000353	time 2.4684 (2.6337)	loss 5.2552 (5.4603)	grad_norm 2.7368 (2.2066)	
[2022-01-17 17:03:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][60/1251]	eta 0:51:32 lr 0.000353	time 2.0480 (2.5970)	loss 5.2292 (5.4635)	grad_norm 2.1253 (2.2074)	
[2022-01-17 17:03:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][70/1251]	eta 0:49:57 lr 0.000353	time 1.5624 (2.5379)	loss 5.6423 (5.4752)	grad_norm 2.0436 (2.2781)	
[2022-01-17 17:04:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][80/1251]	eta 0:49:09 lr 0.000354	time 3.8377 (2.5186)	loss 5.6898 (5.4830)	grad_norm 3.0381 (2.3027)	
[2022-01-17 17:04:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][90/1251]	eta 0:47:44 lr 0.000354	time 1.8839 (2.4673)	loss 4.6152 (5.4930)	grad_norm 1.8214 (2.3349)	
[2022-01-17 17:04:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][100/1251]	eta 0:46:43 lr 0.000355	time 2.4960 (2.4355)	loss 5.0862 (5.4941)	grad_norm 2.3008 (2.3134)	
[2022-01-17 17:05:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][110/1251]	eta 0:45:44 lr 0.000355	time 1.8368 (2.4053)	loss 5.3697 (5.4868)	grad_norm 2.4762 (2.3058)	
[2022-01-17 17:05:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][120/1251]	eta 0:45:06 lr 0.000355	time 3.1602 (2.3929)	loss 5.6393 (5.4906)	grad_norm 2.2454 (2.2812)	
[2022-01-17 17:05:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][130/1251]	eta 0:44:34 lr 0.000356	time 2.7548 (2.3861)	loss 5.8725 (5.4939)	grad_norm 1.9905 (2.2569)	
[2022-01-17 17:06:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][140/1251]	eta 0:43:48 lr 0.000356	time 2.1415 (2.3656)	loss 6.0148 (5.4797)	grad_norm 3.1178 (2.2757)	
[2022-01-17 17:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][150/1251]	eta 0:43:02 lr 0.000357	time 2.2030 (2.3456)	loss 5.6257 (5.4675)	grad_norm 2.0429 (2.2691)	
[2022-01-17 17:07:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][160/1251]	eta 0:42:32 lr 0.000357	time 3.0979 (2.3394)	loss 5.6296 (5.4748)	grad_norm 1.8074 (2.2668)	
[2022-01-17 17:07:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][170/1251]	eta 0:41:56 lr 0.000357	time 2.4079 (2.3277)	loss 5.3643 (5.4736)	grad_norm 1.9598 (2.2614)	
[2022-01-17 17:07:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][180/1251]	eta 0:41:29 lr 0.000358	time 1.7973 (2.3248)	loss 5.7103 (5.4799)	grad_norm 3.0605 (2.2530)	
[2022-01-17 17:08:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][190/1251]	eta 0:40:57 lr 0.000358	time 2.1838 (2.3166)	loss 5.5767 (5.4682)	grad_norm 2.3078 (2.2484)	
[2022-01-17 17:08:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][200/1251]	eta 0:40:32 lr 0.000359	time 2.6520 (2.3147)	loss 5.9169 (5.4633)	grad_norm 1.7405 (2.2426)	
[2022-01-17 17:08:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][210/1251]	eta 0:39:58 lr 0.000359	time 2.2319 (2.3040)	loss 5.7684 (5.4806)	grad_norm 2.5121 (2.2328)	
[2022-01-17 17:09:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][220/1251]	eta 0:39:23 lr 0.000359	time 1.9182 (2.2928)	loss 5.6110 (5.4723)	grad_norm 2.9584 (2.2374)	
[2022-01-17 17:09:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][230/1251]	eta 0:38:53 lr 0.000360	time 2.2909 (2.2856)	loss 6.0593 (5.4742)	grad_norm 5.1263 (2.2543)	
[2022-01-17 17:09:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][240/1251]	eta 0:38:26 lr 0.000360	time 2.6485 (2.2814)	loss 4.7800 (5.4647)	grad_norm 1.8752 (2.2610)	
[2022-01-17 17:10:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][250/1251]	eta 0:37:59 lr 0.000361	time 2.2074 (2.2775)	loss 4.9385 (5.4474)	grad_norm 2.2291 (2.2578)	
[2022-01-17 17:10:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][260/1251]	eta 0:37:38 lr 0.000361	time 1.9800 (2.2788)	loss 6.1781 (5.4483)	grad_norm 2.2163 (2.2529)	
[2022-01-17 17:11:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][270/1251]	eta 0:37:18 lr 0.000361	time 3.1063 (2.2820)	loss 6.2110 (5.4521)	grad_norm 1.7969 (2.2457)	
[2022-01-17 17:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][280/1251]	eta 0:36:48 lr 0.000362	time 1.9862 (2.2741)	loss 5.3255 (5.4513)	grad_norm 2.5355 (2.2382)	
[2022-01-17 17:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][290/1251]	eta 0:36:15 lr 0.000362	time 1.8410 (2.2641)	loss 4.5908 (5.4410)	grad_norm 1.6803 (2.2431)	
[2022-01-17 17:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][300/1251]	eta 0:35:50 lr 0.000363	time 1.9666 (2.2618)	loss 5.0327 (5.4395)	grad_norm 1.9022 (2.2367)	
[2022-01-17 17:12:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][310/1251]	eta 0:35:24 lr 0.000363	time 2.2721 (2.2576)	loss 5.8206 (5.4356)	grad_norm 1.7604 (2.2327)	
[2022-01-17 17:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][320/1251]	eta 0:34:55 lr 0.000363	time 2.4403 (2.2510)	loss 5.1082 (5.4375)	grad_norm 2.1551 (2.2256)	
[2022-01-17 17:13:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][330/1251]	eta 0:34:35 lr 0.000364	time 2.6472 (2.2530)	loss 4.7288 (5.4367)	grad_norm 1.8064 (2.2235)	
[2022-01-17 17:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][340/1251]	eta 0:34:15 lr 0.000364	time 2.0965 (2.2564)	loss 5.3749 (5.4349)	grad_norm 2.0920 (2.2194)	
[2022-01-17 17:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][350/1251]	eta 0:33:50 lr 0.000365	time 1.6939 (2.2539)	loss 5.8399 (5.4403)	grad_norm 1.9423 (2.2255)	
[2022-01-17 17:14:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][360/1251]	eta 0:33:26 lr 0.000365	time 2.4629 (2.2517)	loss 4.8237 (5.4353)	grad_norm 1.9727 (2.2238)	
[2022-01-17 17:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][370/1251]	eta 0:33:02 lr 0.000365	time 2.8110 (2.2498)	loss 5.7757 (5.4346)	grad_norm 1.7449 (2.2187)	
[2022-01-17 17:15:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][380/1251]	eta 0:32:40 lr 0.000366	time 1.8256 (2.2512)	loss 4.8397 (5.4338)	grad_norm 2.1042 (2.2177)	
[2022-01-17 17:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][390/1251]	eta 0:32:13 lr 0.000366	time 1.6988 (2.2461)	loss 5.4526 (5.4340)	grad_norm 1.9201 (2.2193)	
[2022-01-17 17:15:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][400/1251]	eta 0:31:47 lr 0.000367	time 1.9095 (2.2418)	loss 5.3999 (5.4300)	grad_norm 2.0381 (2.2155)	
[2022-01-17 17:16:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][410/1251]	eta 0:31:23 lr 0.000367	time 2.2363 (2.2397)	loss 5.7792 (5.4319)	grad_norm 3.0215 (2.2140)	
[2022-01-17 17:16:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][420/1251]	eta 0:31:01 lr 0.000367	time 2.9491 (2.2396)	loss 5.6025 (5.4254)	grad_norm 1.8805 (2.2186)	
[2022-01-17 17:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][430/1251]	eta 0:30:37 lr 0.000368	time 1.9373 (2.2385)	loss 5.7378 (5.4214)	grad_norm 2.3686 (2.2144)	
[2022-01-17 17:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][440/1251]	eta 0:30:13 lr 0.000368	time 2.1251 (2.2356)	loss 6.1038 (5.4232)	grad_norm 2.2896 (2.2145)	
[2022-01-17 17:17:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][450/1251]	eta 0:29:51 lr 0.000369	time 2.1642 (2.2363)	loss 5.5394 (5.4193)	grad_norm 2.2412 (2.2120)	
[2022-01-17 17:17:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][460/1251]	eta 0:29:30 lr 0.000369	time 2.9878 (2.2377)	loss 5.4733 (5.4243)	grad_norm 2.7141 (2.2121)	
[2022-01-17 17:18:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][470/1251]	eta 0:29:04 lr 0.000369	time 1.8475 (2.2333)	loss 5.6245 (5.4259)	grad_norm 2.0532 (2.2176)	
[2022-01-17 17:18:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][480/1251]	eta 0:28:40 lr 0.000370	time 2.2632 (2.2311)	loss 5.9142 (5.4234)	grad_norm 2.2980 (2.2174)	
[2022-01-17 17:19:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][490/1251]	eta 0:28:15 lr 0.000370	time 2.5109 (2.2280)	loss 5.1200 (5.4207)	grad_norm 2.5598 (2.2297)	
[2022-01-17 17:19:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][500/1251]	eta 0:27:50 lr 0.000371	time 2.6457 (2.2241)	loss 5.2831 (5.4217)	grad_norm 1.6177 (2.2284)	
[2022-01-17 17:19:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][510/1251]	eta 0:27:30 lr 0.000371	time 2.5199 (2.2279)	loss 5.9401 (5.4253)	grad_norm 2.2446 (2.2272)	
[2022-01-17 17:20:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][520/1251]	eta 0:27:10 lr 0.000371	time 2.7889 (2.2311)	loss 6.1537 (5.4266)	grad_norm 1.8328 (2.2257)	
[2022-01-17 17:20:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][530/1251]	eta 0:26:49 lr 0.000372	time 2.1823 (2.2327)	loss 5.2901 (5.4263)	grad_norm 1.9174 (2.2258)	
[2022-01-17 17:20:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][540/1251]	eta 0:26:24 lr 0.000372	time 1.7427 (2.2281)	loss 5.1853 (5.4227)	grad_norm 1.8727 (2.2229)	
[2022-01-17 17:21:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][550/1251]	eta 0:25:58 lr 0.000373	time 1.9541 (2.2226)	loss 5.5299 (5.4248)	grad_norm 2.3955 (2.2172)	
[2022-01-17 17:21:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][560/1251]	eta 0:25:33 lr 0.000373	time 2.7614 (2.2193)	loss 5.5926 (5.4219)	grad_norm 2.0179 (2.2174)	
[2022-01-17 17:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][570/1251]	eta 0:25:11 lr 0.000373	time 2.2440 (2.2191)	loss 4.8544 (5.4202)	grad_norm 2.6643 (2.2182)	
[2022-01-17 17:22:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][580/1251]	eta 0:24:47 lr 0.000374	time 1.8210 (2.2171)	loss 5.6430 (5.4174)	grad_norm 2.1367 (2.2167)	
[2022-01-17 17:22:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][590/1251]	eta 0:24:25 lr 0.000374	time 2.2017 (2.2172)	loss 5.6063 (5.4144)	grad_norm 2.1585 (2.2188)	
[2022-01-17 17:22:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][600/1251]	eta 0:24:03 lr 0.000375	time 2.4243 (2.2169)	loss 5.3329 (5.4147)	grad_norm 2.4486 (2.2232)	
[2022-01-17 17:23:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][610/1251]	eta 0:23:40 lr 0.000375	time 2.2218 (2.2167)	loss 5.7395 (5.4200)	grad_norm 2.0165 (2.2191)	
[2022-01-17 17:23:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][620/1251]	eta 0:23:18 lr 0.000375	time 1.7174 (2.2163)	loss 5.4722 (5.4157)	grad_norm 2.0385 (2.2181)	
[2022-01-17 17:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][630/1251]	eta 0:22:56 lr 0.000376	time 2.3469 (2.2173)	loss 5.3847 (5.4171)	grad_norm 2.3081 (2.2159)	
[2022-01-17 17:24:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][640/1251]	eta 0:22:34 lr 0.000376	time 2.7390 (2.2163)	loss 5.2629 (5.4195)	grad_norm 1.9600 (2.2120)	
[2022-01-17 17:24:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][650/1251]	eta 0:22:13 lr 0.000377	time 2.9566 (2.2187)	loss 5.9952 (5.4191)	grad_norm 1.7828 (2.2163)	
[2022-01-17 17:25:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][660/1251]	eta 0:21:51 lr 0.000377	time 2.1792 (2.2191)	loss 5.6583 (5.4208)	grad_norm 1.8115 (2.2127)	
[2022-01-17 17:25:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][670/1251]	eta 0:21:29 lr 0.000377	time 2.2417 (2.2192)	loss 5.3284 (5.4240)	grad_norm 2.5046 (2.2099)	
[2022-01-17 17:25:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][680/1251]	eta 0:21:06 lr 0.000378	time 2.5056 (2.2177)	loss 5.6837 (5.4237)	grad_norm 2.1611 (2.2097)	
[2022-01-17 17:26:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][690/1251]	eta 0:20:41 lr 0.000378	time 2.2766 (2.2132)	loss 5.8764 (5.4247)	grad_norm 1.8954 (2.2070)	
[2022-01-17 17:26:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][700/1251]	eta 0:20:18 lr 0.000379	time 2.1128 (2.2109)	loss 5.5106 (5.4222)	grad_norm 2.5637 (2.2081)	
[2022-01-17 17:26:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][710/1251]	eta 0:19:55 lr 0.000379	time 2.2146 (2.2103)	loss 4.6349 (5.4238)	grad_norm 1.8007 (2.2089)	
[2022-01-17 17:27:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][720/1251]	eta 0:19:33 lr 0.000379	time 2.7584 (2.2107)	loss 4.5463 (5.4243)	grad_norm 1.8357 (2.2081)	
[2022-01-17 17:27:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][730/1251]	eta 0:19:11 lr 0.000380	time 2.2435 (2.2103)	loss 5.7862 (5.4275)	grad_norm 2.0859 (2.2069)	
[2022-01-17 17:28:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][740/1251]	eta 0:18:48 lr 0.000380	time 1.7073 (2.2087)	loss 4.8839 (5.4275)	grad_norm 1.8117 (2.2042)	
[2022-01-17 17:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][750/1251]	eta 0:18:26 lr 0.000381	time 2.1957 (2.2077)	loss 5.0405 (5.4209)	grad_norm 2.2726 (2.2062)	
[2022-01-17 17:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][760/1251]	eta 0:18:03 lr 0.000381	time 2.2501 (2.2065)	loss 5.1383 (5.4162)	grad_norm 2.7400 (2.2085)	
[2022-01-17 17:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][770/1251]	eta 0:17:40 lr 0.000381	time 1.8287 (2.2058)	loss 5.7198 (5.4173)	grad_norm 2.4302 (2.2088)	
[2022-01-17 17:29:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][780/1251]	eta 0:17:18 lr 0.000382	time 2.0301 (2.2049)	loss 5.3555 (5.4196)	grad_norm 2.0128 (2.2094)	
[2022-01-17 17:29:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][790/1251]	eta 0:16:56 lr 0.000382	time 2.2443 (2.2054)	loss 5.2416 (5.4177)	grad_norm 2.2992 (2.2102)	
[2022-01-17 17:30:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][800/1251]	eta 0:16:35 lr 0.000383	time 2.1649 (2.2063)	loss 5.9582 (5.4175)	grad_norm 2.1207 (2.2130)	
[2022-01-17 17:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][810/1251]	eta 0:16:14 lr 0.000383	time 2.4659 (2.2088)	loss 4.6403 (5.4160)	grad_norm 2.2081 (2.2130)	
[2022-01-17 17:31:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][820/1251]	eta 0:15:51 lr 0.000383	time 2.2829 (2.2083)	loss 4.4594 (5.4152)	grad_norm 2.1385 (2.2114)	
[2022-01-17 17:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][830/1251]	eta 0:15:29 lr 0.000384	time 2.5321 (2.2090)	loss 5.3369 (5.4160)	grad_norm 1.8065 (2.2084)	
[2022-01-17 17:31:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][840/1251]	eta 0:15:07 lr 0.000384	time 2.7859 (2.2086)	loss 4.9165 (5.4120)	grad_norm 1.5879 (2.2066)	
[2022-01-17 17:32:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][850/1251]	eta 0:14:45 lr 0.000385	time 2.6057 (2.2077)	loss 5.3791 (5.4120)	grad_norm 2.2749 (2.2053)	
[2022-01-17 17:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][860/1251]	eta 0:14:22 lr 0.000385	time 1.6881 (2.2059)	loss 5.3986 (5.4093)	grad_norm 2.2140 (2.2065)	
[2022-01-17 17:32:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][870/1251]	eta 0:13:59 lr 0.000385	time 2.1143 (2.2047)	loss 4.2866 (5.4104)	grad_norm 1.8349 (2.2054)	
[2022-01-17 17:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][880/1251]	eta 0:13:38 lr 0.000386	time 3.5441 (2.2058)	loss 5.4977 (5.4097)	grad_norm 2.2714 (2.2038)	
[2022-01-17 17:33:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][890/1251]	eta 0:13:16 lr 0.000386	time 2.4842 (2.2054)	loss 5.7823 (5.4070)	grad_norm 2.2409 (2.2019)	
[2022-01-17 17:33:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][900/1251]	eta 0:12:53 lr 0.000387	time 1.8723 (2.2037)	loss 4.7079 (5.4074)	grad_norm 2.6323 (2.2035)	
[2022-01-17 17:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][910/1251]	eta 0:12:31 lr 0.000387	time 2.6462 (2.2039)	loss 5.6302 (5.4091)	grad_norm 2.0948 (2.2068)	
[2022-01-17 17:34:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][920/1251]	eta 0:12:09 lr 0.000387	time 3.1271 (2.2045)	loss 5.5020 (5.4106)	grad_norm 1.8911 (2.2068)	
[2022-01-17 17:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][930/1251]	eta 0:11:47 lr 0.000388	time 2.5310 (2.2047)	loss 5.5033 (5.4117)	grad_norm 1.5821 (2.2035)	
[2022-01-17 17:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][940/1251]	eta 0:11:25 lr 0.000388	time 1.7343 (2.2056)	loss 5.7339 (5.4118)	grad_norm 2.0920 (2.2035)	
[2022-01-17 17:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][950/1251]	eta 0:11:03 lr 0.000389	time 2.2310 (2.2053)	loss 5.3983 (5.4121)	grad_norm 2.0138 (2.2015)	
[2022-01-17 17:36:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][960/1251]	eta 0:10:41 lr 0.000389	time 3.3088 (2.2052)	loss 5.4104 (5.4125)	grad_norm 1.6609 (2.2001)	
[2022-01-17 17:36:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][970/1251]	eta 0:10:19 lr 0.000389	time 2.2554 (2.2034)	loss 4.8464 (5.4105)	grad_norm 3.0579 (2.2006)	
[2022-01-17 17:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][980/1251]	eta 0:09:56 lr 0.000390	time 1.8362 (2.2012)	loss 5.5330 (5.4097)	grad_norm 1.7557 (2.2005)	
[2022-01-17 17:37:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][990/1251]	eta 0:09:34 lr 0.000390	time 2.7762 (2.2012)	loss 5.5368 (5.4104)	grad_norm 2.4962 (2.2016)	
[2022-01-17 17:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1000/1251]	eta 0:09:12 lr 0.000391	time 2.6320 (2.2025)	loss 5.7143 (5.4083)	grad_norm 2.0663 (2.2020)	
[2022-01-17 17:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1010/1251]	eta 0:08:50 lr 0.000391	time 1.9094 (2.2023)	loss 6.0520 (5.4071)	grad_norm 2.7697 (2.2008)	
[2022-01-17 17:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1020/1251]	eta 0:08:28 lr 0.000391	time 2.5080 (2.2010)	loss 5.3017 (5.4058)	grad_norm 1.6845 (2.2009)	
[2022-01-17 17:38:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1030/1251]	eta 0:08:06 lr 0.000392	time 1.9101 (2.2005)	loss 5.4486 (5.4055)	grad_norm 1.9520 (2.2009)	
[2022-01-17 17:38:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1040/1251]	eta 0:07:44 lr 0.000392	time 2.2106 (2.1991)	loss 5.3071 (5.4047)	grad_norm 3.1788 (2.2032)	
[2022-01-17 17:39:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1050/1251]	eta 0:07:21 lr 0.000393	time 2.4731 (2.1980)	loss 5.1845 (5.4045)	grad_norm 2.6777 (2.2025)	
[2022-01-17 17:39:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1060/1251]	eta 0:06:59 lr 0.000393	time 1.5390 (2.1969)	loss 4.7150 (5.4030)	grad_norm 2.0363 (2.2028)	
[2022-01-17 17:39:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1070/1251]	eta 0:06:37 lr 0.000393	time 1.8674 (2.1961)	loss 5.5325 (5.4038)	grad_norm 1.7864 (2.2002)	
[2022-01-17 17:40:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1080/1251]	eta 0:06:15 lr 0.000394	time 3.1297 (2.1978)	loss 5.0519 (5.4025)	grad_norm 2.3255 (2.2019)	
[2022-01-17 17:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1090/1251]	eta 0:05:54 lr 0.000394	time 1.7682 (2.1990)	loss 5.6215 (5.4013)	grad_norm 2.2135 (2.2026)	
[2022-01-17 17:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1100/1251]	eta 0:05:32 lr 0.000395	time 2.1278 (2.2001)	loss 5.4985 (5.3984)	grad_norm 1.8017 (2.2028)	
[2022-01-17 17:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1110/1251]	eta 0:05:10 lr 0.000395	time 2.1780 (2.1996)	loss 4.9200 (5.3983)	grad_norm 1.8018 (2.2000)	
[2022-01-17 17:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1120/1251]	eta 0:04:48 lr 0.000395	time 2.6645 (2.1994)	loss 5.6971 (5.3979)	grad_norm 1.8259 (2.1994)	
[2022-01-17 17:42:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1130/1251]	eta 0:04:25 lr 0.000396	time 1.8818 (2.1977)	loss 5.5307 (5.3977)	grad_norm 1.7707 (2.2009)	
[2022-01-17 17:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1140/1251]	eta 0:04:04 lr 0.000396	time 1.8943 (2.1984)	loss 4.9883 (5.3966)	grad_norm 2.2883 (2.2013)	
[2022-01-17 17:42:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1150/1251]	eta 0:03:41 lr 0.000397	time 2.2264 (2.1976)	loss 5.0783 (5.3957)	grad_norm 1.9531 (2.1983)	
[2022-01-17 17:43:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1160/1251]	eta 0:03:19 lr 0.000397	time 2.3069 (2.1966)	loss 5.7720 (5.3970)	grad_norm 2.3118 (2.1993)	
[2022-01-17 17:43:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1170/1251]	eta 0:02:57 lr 0.000397	time 1.5861 (2.1946)	loss 5.7504 (5.3960)	grad_norm 2.1876 (2.2001)	
[2022-01-17 17:43:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1180/1251]	eta 0:02:35 lr 0.000398	time 1.8103 (2.1932)	loss 4.8857 (5.3955)	grad_norm 1.8828 (2.2030)	
[2022-01-17 17:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1190/1251]	eta 0:02:13 lr 0.000398	time 2.4143 (2.1927)	loss 4.7656 (5.3964)	grad_norm 2.2024 (2.2020)	
[2022-01-17 17:44:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1200/1251]	eta 0:01:51 lr 0.000399	time 2.2285 (2.1928)	loss 4.4077 (5.3944)	grad_norm 1.7749 (2.2002)	
[2022-01-17 17:45:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1210/1251]	eta 0:01:29 lr 0.000399	time 1.8403 (2.1921)	loss 5.5870 (5.3939)	grad_norm 2.3565 (2.1994)	
[2022-01-17 17:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1220/1251]	eta 0:01:07 lr 0.000399	time 2.7211 (2.1928)	loss 4.4041 (5.3931)	grad_norm 1.8609 (2.1986)	
[2022-01-17 17:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1230/1251]	eta 0:00:46 lr 0.000400	time 1.9464 (2.1933)	loss 5.6565 (5.3926)	grad_norm 1.7726 (2.1975)	
[2022-01-17 17:46:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1240/1251]	eta 0:00:24 lr 0.000400	time 1.9531 (2.1942)	loss 5.1949 (5.3908)	grad_norm 1.8552 (2.1972)	
[2022-01-17 17:46:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [7/300][1250/1251]	eta 0:00:02 lr 0.000401	time 1.1336 (2.1891)	loss 5.0588 (5.3906)	grad_norm 2.1447 (2.1954)	
[2022-01-17 17:46:25 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 7 training takes 0:45:38
[2022-01-17 17:46:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.156 (18.156)	Loss 2.9763 (2.9763)	Acc@1 39.258 (39.258)	Acc@5 65.137 (65.137)	
[2022-01-17 17:47:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.605 (3.471)	Loss 2.9139 (2.9876)	Acc@1 41.113 (37.855)	Acc@5 66.211 (64.142)	
[2022-01-17 17:47:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.281 (2.616)	Loss 2.9825 (2.9907)	Acc@1 39.062 (38.058)	Acc@5 63.477 (63.709)	
[2022-01-17 17:47:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.602 (2.266)	Loss 3.0276 (2.9984)	Acc@1 38.086 (37.954)	Acc@5 64.648 (63.697)	
[2022-01-17 17:47:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.816 (2.198)	Loss 3.0226 (3.0038)	Acc@1 37.207 (37.776)	Acc@5 62.402 (63.603)	
[2022-01-17 17:48:03 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 37.788 Acc@5 63.680
[2022-01-17 17:48:03 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 37.8%
[2022-01-17 17:48:03 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 37.79%
[2022-01-17 17:48:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][0/1251]	eta 7:14:04 lr 0.000401	time 20.8192 (20.8192)	loss 5.5628 (5.5628)	grad_norm 1.9724 (1.9724)	
[2022-01-17 17:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][10/1251]	eta 1:23:00 lr 0.000401	time 2.5947 (4.0133)	loss 5.1445 (5.5513)	grad_norm 1.7086 (1.9615)	
[2022-01-17 17:49:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][20/1251]	eta 1:04:09 lr 0.000401	time 1.3398 (3.1273)	loss 5.7965 (5.5646)	grad_norm 2.2825 (2.0620)	
[2022-01-17 17:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][30/1251]	eta 0:57:49 lr 0.000402	time 1.5572 (2.8412)	loss 5.9163 (5.5515)	grad_norm 2.0440 (2.2090)	
[2022-01-17 17:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][40/1251]	eta 0:55:11 lr 0.000402	time 3.6250 (2.7349)	loss 5.3108 (5.4327)	grad_norm 2.2362 (2.2047)	
[2022-01-17 17:50:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][50/1251]	eta 0:53:31 lr 0.000403	time 2.5030 (2.6743)	loss 5.9845 (5.4797)	grad_norm 2.2483 (2.1946)	
[2022-01-17 17:50:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][60/1251]	eta 0:51:39 lr 0.000403	time 1.5630 (2.6027)	loss 5.2644 (5.4578)	grad_norm 1.6895 (2.1881)	
[2022-01-17 17:51:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][70/1251]	eta 0:49:48 lr 0.000403	time 1.5917 (2.5303)	loss 5.3442 (5.4600)	grad_norm 1.9103 (2.1829)	
[2022-01-17 17:51:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][80/1251]	eta 0:48:27 lr 0.000404	time 2.2633 (2.4826)	loss 4.4144 (5.4417)	grad_norm 2.2170 (2.2037)	
[2022-01-17 17:51:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][90/1251]	eta 0:47:22 lr 0.000404	time 1.8965 (2.4485)	loss 5.7345 (5.4414)	grad_norm 1.9091 (2.2135)	
[2022-01-17 17:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][100/1251]	eta 0:46:08 lr 0.000405	time 2.2627 (2.4052)	loss 4.7701 (5.4099)	grad_norm 1.8791 (2.1901)	
[2022-01-17 17:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][110/1251]	eta 0:45:24 lr 0.000405	time 2.5159 (2.3880)	loss 5.5065 (5.4152)	grad_norm 1.5490 (2.1627)	
[2022-01-17 17:52:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][120/1251]	eta 0:44:43 lr 0.000405	time 1.7605 (2.3731)	loss 5.0336 (5.4030)	grad_norm 2.0659 (2.1475)	
[2022-01-17 17:53:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][130/1251]	eta 0:44:09 lr 0.000406	time 1.8680 (2.3634)	loss 5.7386 (5.4062)	grad_norm 1.9514 (2.1307)	
[2022-01-17 17:53:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][140/1251]	eta 0:43:28 lr 0.000406	time 3.0256 (2.3479)	loss 4.7255 (5.3821)	grad_norm 2.3540 (2.1229)	
[2022-01-17 17:53:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][150/1251]	eta 0:42:44 lr 0.000407	time 1.6419 (2.3293)	loss 4.5670 (5.3712)	grad_norm 2.2679 (2.1228)	
[2022-01-17 17:54:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][160/1251]	eta 0:42:03 lr 0.000407	time 1.8824 (2.3128)	loss 5.8444 (5.3780)	grad_norm 2.1255 (2.1277)	
[2022-01-17 17:54:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][170/1251]	eta 0:41:33 lr 0.000407	time 2.3409 (2.3063)	loss 5.5403 (5.3838)	grad_norm 1.9666 (2.1182)	
[2022-01-17 17:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][180/1251]	eta 0:41:11 lr 0.000408	time 2.5145 (2.3075)	loss 5.4374 (5.3734)	grad_norm 2.9272 (2.1262)	
[2022-01-17 17:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][190/1251]	eta 0:40:45 lr 0.000408	time 2.1140 (2.3049)	loss 5.9266 (5.3772)	grad_norm 2.1786 (2.1347)	
[2022-01-17 17:55:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][200/1251]	eta 0:40:16 lr 0.000409	time 1.5871 (2.2991)	loss 4.7279 (5.3818)	grad_norm 1.9954 (2.1286)	
[2022-01-17 17:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][210/1251]	eta 0:39:51 lr 0.000409	time 2.5316 (2.2976)	loss 4.3471 (5.3751)	grad_norm 1.9803 (2.1114)	
[2022-01-17 17:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][220/1251]	eta 0:39:17 lr 0.000409	time 1.8815 (2.2865)	loss 4.4958 (5.3613)	grad_norm 2.3220 (2.1125)	
[2022-01-17 17:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][230/1251]	eta 0:38:38 lr 0.000410	time 1.9559 (2.2708)	loss 4.3203 (5.3595)	grad_norm 2.7223 (2.1196)	
[2022-01-17 17:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][240/1251]	eta 0:38:10 lr 0.000410	time 1.9744 (2.2653)	loss 5.9232 (5.3665)	grad_norm 1.8491 (2.1274)	
[2022-01-17 17:57:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][250/1251]	eta 0:37:46 lr 0.000411	time 2.9762 (2.2640)	loss 5.7086 (5.3752)	grad_norm 2.0795 (2.1209)	
[2022-01-17 17:57:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][260/1251]	eta 0:37:22 lr 0.000411	time 1.5816 (2.2626)	loss 5.6786 (5.3762)	grad_norm 1.9752 (2.1168)	
[2022-01-17 17:58:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][270/1251]	eta 0:36:56 lr 0.000411	time 1.8856 (2.2595)	loss 5.8884 (5.3702)	grad_norm 1.6652 (2.1169)	
[2022-01-17 17:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][280/1251]	eta 0:36:36 lr 0.000412	time 2.6254 (2.2617)	loss 5.9944 (5.3697)	grad_norm 2.2313 (2.1267)	
[2022-01-17 17:59:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][290/1251]	eta 0:36:12 lr 0.000412	time 2.7339 (2.2602)	loss 5.6648 (5.3675)	grad_norm 1.8735 (2.1242)	
[2022-01-17 17:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][300/1251]	eta 0:35:49 lr 0.000413	time 1.6855 (2.2599)	loss 4.5615 (5.3709)	grad_norm 3.2572 (2.1287)	
[2022-01-17 17:59:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][310/1251]	eta 0:35:18 lr 0.000413	time 1.8657 (2.2512)	loss 5.1692 (5.3591)	grad_norm 1.8607 (2.1234)	
[2022-01-17 18:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][320/1251]	eta 0:34:56 lr 0.000413	time 3.2109 (2.2519)	loss 5.6570 (5.3565)	grad_norm 1.8569 (2.1221)	
[2022-01-17 18:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][330/1251]	eta 0:34:27 lr 0.000414	time 1.6038 (2.2446)	loss 5.8406 (5.3603)	grad_norm 1.7663 (2.1220)	
[2022-01-17 18:00:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][340/1251]	eta 0:34:02 lr 0.000414	time 2.2403 (2.2418)	loss 4.5779 (5.3615)	grad_norm 1.7823 (2.1189)	
[2022-01-17 18:01:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][350/1251]	eta 0:33:38 lr 0.000415	time 1.8128 (2.2407)	loss 5.6965 (5.3626)	grad_norm 2.3784 (2.1155)	
[2022-01-17 18:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][360/1251]	eta 0:33:19 lr 0.000415	time 3.8875 (2.2439)	loss 5.2899 (5.3661)	grad_norm 1.8885 (2.1108)	
[2022-01-17 18:01:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][370/1251]	eta 0:32:54 lr 0.000415	time 1.6417 (2.2409)	loss 4.6492 (5.3558)	grad_norm 4.6584 (2.1181)	
[2022-01-17 18:02:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][380/1251]	eta 0:32:32 lr 0.000416	time 1.8810 (2.2416)	loss 5.3441 (5.3513)	grad_norm 1.9520 (2.1179)	
[2022-01-17 18:02:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][390/1251]	eta 0:32:04 lr 0.000416	time 1.8427 (2.2347)	loss 4.7989 (5.3503)	grad_norm 2.5181 (2.1182)	
[2022-01-17 18:03:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][400/1251]	eta 0:31:45 lr 0.000417	time 3.7039 (2.2386)	loss 5.4667 (5.3431)	grad_norm 2.1536 (2.1156)	
[2022-01-17 18:03:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][410/1251]	eta 0:31:20 lr 0.000417	time 1.9870 (2.2363)	loss 5.1106 (5.3428)	grad_norm 3.7348 (2.1193)	
[2022-01-17 18:03:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][420/1251]	eta 0:30:57 lr 0.000417	time 1.8721 (2.2351)	loss 4.4868 (5.3354)	grad_norm 2.1869 (2.1319)	
[2022-01-17 18:04:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][430/1251]	eta 0:30:31 lr 0.000418	time 2.0046 (2.2309)	loss 4.5511 (5.3312)	grad_norm 1.8495 (2.1304)	
[2022-01-17 18:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][440/1251]	eta 0:30:10 lr 0.000418	time 3.6056 (2.2324)	loss 5.1911 (5.3331)	grad_norm 2.4764 (2.1311)	
[2022-01-17 18:04:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][450/1251]	eta 0:29:48 lr 0.000419	time 1.9911 (2.2331)	loss 5.0845 (5.3303)	grad_norm 1.7415 (2.1309)	
[2022-01-17 18:05:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][460/1251]	eta 0:29:25 lr 0.000419	time 2.2889 (2.2318)	loss 5.6094 (5.3295)	grad_norm 1.9346 (2.1309)	
[2022-01-17 18:05:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][470/1251]	eta 0:28:58 lr 0.000419	time 1.8560 (2.2259)	loss 5.1411 (5.3321)	grad_norm 2.8211 (2.1333)	
[2022-01-17 18:05:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][480/1251]	eta 0:28:37 lr 0.000420	time 3.0937 (2.2274)	loss 5.2125 (5.3305)	grad_norm 2.4568 (2.1325)	
[2022-01-17 18:06:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][490/1251]	eta 0:28:12 lr 0.000420	time 2.1813 (2.2246)	loss 5.8790 (5.3288)	grad_norm 1.9851 (2.1331)	
[2022-01-17 18:06:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][500/1251]	eta 0:27:48 lr 0.000421	time 2.5208 (2.2216)	loss 5.2296 (5.3293)	grad_norm 1.5706 (2.1305)	
[2022-01-17 18:06:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][510/1251]	eta 0:27:24 lr 0.000421	time 2.2864 (2.2193)	loss 5.3954 (5.3278)	grad_norm 1.5751 (2.1258)	
[2022-01-17 18:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][520/1251]	eta 0:27:03 lr 0.000421	time 3.0427 (2.2213)	loss 5.9323 (5.3296)	grad_norm 2.3820 (2.1283)	
[2022-01-17 18:07:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][530/1251]	eta 0:26:39 lr 0.000422	time 2.5278 (2.2191)	loss 4.0431 (5.3235)	grad_norm 2.1963 (2.1232)	
[2022-01-17 18:08:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][540/1251]	eta 0:26:18 lr 0.000422	time 2.4930 (2.2197)	loss 5.6995 (5.3243)	grad_norm 2.2151 (2.1247)	
[2022-01-17 18:08:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][550/1251]	eta 0:25:56 lr 0.000423	time 2.3922 (2.2204)	loss 4.2914 (5.3217)	grad_norm 1.7225 (2.1261)	
[2022-01-17 18:08:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][560/1251]	eta 0:25:35 lr 0.000423	time 2.6720 (2.2222)	loss 5.5879 (5.3144)	grad_norm 1.8014 (2.1253)	
[2022-01-17 18:09:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][570/1251]	eta 0:25:11 lr 0.000423	time 1.9145 (2.2193)	loss 5.8359 (5.3149)	grad_norm 5.6378 (2.1318)	
[2022-01-17 18:09:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][580/1251]	eta 0:24:48 lr 0.000424	time 2.3341 (2.2189)	loss 4.5287 (5.3152)	grad_norm 1.7880 (2.1300)	
[2022-01-17 18:09:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][590/1251]	eta 0:24:22 lr 0.000424	time 1.6025 (2.2131)	loss 5.2700 (5.3105)	grad_norm 1.7212 (2.1277)	
[2022-01-17 18:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][600/1251]	eta 0:23:59 lr 0.000425	time 1.8229 (2.2107)	loss 5.6889 (5.3092)	grad_norm 1.7780 (2.1227)	
[2022-01-17 18:10:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][610/1251]	eta 0:23:36 lr 0.000425	time 1.8071 (2.2097)	loss 5.5375 (5.3081)	grad_norm 2.5783 (2.1231)	
[2022-01-17 18:10:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][620/1251]	eta 0:23:13 lr 0.000425	time 1.9393 (2.2084)	loss 5.8313 (5.3064)	grad_norm 1.8766 (2.1178)	
[2022-01-17 18:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][630/1251]	eta 0:22:49 lr 0.000426	time 1.8800 (2.2055)	loss 4.9506 (5.3114)	grad_norm 1.9300 (2.1185)	
[2022-01-17 18:11:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][640/1251]	eta 0:22:27 lr 0.000426	time 1.6482 (2.2051)	loss 5.7765 (5.3088)	grad_norm 1.8936 (2.1141)	
[2022-01-17 18:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][650/1251]	eta 0:22:05 lr 0.000427	time 2.0978 (2.2063)	loss 5.1699 (5.3049)	grad_norm 1.7917 (2.1125)	
[2022-01-17 18:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][660/1251]	eta 0:21:44 lr 0.000427	time 1.8457 (2.2068)	loss 5.3753 (5.3050)	grad_norm 2.0543 (2.1143)	
[2022-01-17 18:12:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][670/1251]	eta 0:21:23 lr 0.000427	time 2.7241 (2.2096)	loss 5.5472 (5.3044)	grad_norm 1.9031 (2.1146)	
[2022-01-17 18:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][680/1251]	eta 0:21:03 lr 0.000428	time 1.8574 (2.2131)	loss 5.7091 (5.3073)	grad_norm 2.8383 (2.1129)	
[2022-01-17 18:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][690/1251]	eta 0:20:41 lr 0.000428	time 2.2474 (2.2134)	loss 5.3786 (5.3068)	grad_norm 2.7717 (2.1143)	
[2022-01-17 18:13:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][700/1251]	eta 0:20:18 lr 0.000429	time 2.5591 (2.2112)	loss 4.6759 (5.3066)	grad_norm 3.9178 (2.1200)	
[2022-01-17 18:14:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][710/1251]	eta 0:19:53 lr 0.000429	time 1.9549 (2.2057)	loss 4.1876 (5.3038)	grad_norm 1.8410 (2.1203)	
[2022-01-17 18:14:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][720/1251]	eta 0:19:29 lr 0.000429	time 2.2359 (2.2029)	loss 5.5216 (5.3029)	grad_norm 1.5908 (2.1161)	
[2022-01-17 18:14:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][730/1251]	eta 0:19:06 lr 0.000430	time 2.5212 (2.2015)	loss 5.8505 (5.3043)	grad_norm 1.8724 (2.1158)	
[2022-01-17 18:15:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][740/1251]	eta 0:18:44 lr 0.000430	time 2.1831 (2.2015)	loss 5.1429 (5.3051)	grad_norm 2.3534 (2.1150)	
[2022-01-17 18:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][750/1251]	eta 0:18:22 lr 0.000431	time 1.8513 (2.2013)	loss 4.8005 (5.3058)	grad_norm 1.9454 (2.1167)	
[2022-01-17 18:15:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][760/1251]	eta 0:18:01 lr 0.000431	time 2.9642 (2.2025)	loss 5.4066 (5.3052)	grad_norm 2.7779 (2.1158)	
[2022-01-17 18:16:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][770/1251]	eta 0:17:40 lr 0.000431	time 2.8331 (2.2055)	loss 5.2188 (5.3035)	grad_norm 2.5477 (2.1176)	
[2022-01-17 18:16:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][780/1251]	eta 0:17:19 lr 0.000432	time 2.1799 (2.2076)	loss 5.3899 (5.3042)	grad_norm 3.1013 (2.1175)	
[2022-01-17 18:17:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][790/1251]	eta 0:16:58 lr 0.000432	time 2.8891 (2.2097)	loss 4.5066 (5.3008)	grad_norm 1.8502 (2.1150)	
[2022-01-17 18:17:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][800/1251]	eta 0:16:35 lr 0.000433	time 2.0829 (2.2081)	loss 5.4354 (5.3000)	grad_norm 1.7208 (2.1110)	
[2022-01-17 18:17:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][810/1251]	eta 0:16:13 lr 0.000433	time 2.8471 (2.2070)	loss 5.7042 (5.3003)	grad_norm 1.5362 (2.1082)	
[2022-01-17 18:18:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][820/1251]	eta 0:15:50 lr 0.000433	time 1.7302 (2.2045)	loss 4.7655 (5.2976)	grad_norm 2.5030 (2.1120)	
[2022-01-17 18:18:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][830/1251]	eta 0:15:27 lr 0.000434	time 1.9038 (2.2037)	loss 5.5013 (5.2990)	grad_norm 2.2089 (2.1119)	
[2022-01-17 18:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][840/1251]	eta 0:15:05 lr 0.000434	time 2.0759 (2.2032)	loss 5.7253 (5.2996)	grad_norm 1.9560 (2.1100)	
[2022-01-17 18:19:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][850/1251]	eta 0:14:43 lr 0.000435	time 2.1979 (2.2034)	loss 5.3067 (5.2988)	grad_norm 1.9406 (2.1090)	
[2022-01-17 18:19:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][860/1251]	eta 0:14:22 lr 0.000435	time 2.5140 (2.2048)	loss 4.8393 (5.3001)	grad_norm 1.8430 (2.1079)	
[2022-01-17 18:20:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][870/1251]	eta 0:14:00 lr 0.000435	time 2.1546 (2.2064)	loss 6.0997 (5.2998)	grad_norm 2.2752 (2.1062)	
[2022-01-17 18:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][880/1251]	eta 0:13:38 lr 0.000436	time 1.5505 (2.2070)	loss 5.3549 (5.2995)	grad_norm 2.0163 (2.1057)	
[2022-01-17 18:20:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][890/1251]	eta 0:13:16 lr 0.000436	time 1.8643 (2.2057)	loss 5.1678 (5.2979)	grad_norm 1.9373 (2.1043)	
[2022-01-17 18:21:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][900/1251]	eta 0:12:52 lr 0.000437	time 2.0458 (2.2022)	loss 5.2826 (5.2976)	grad_norm 1.8937 (2.1025)	
[2022-01-17 18:21:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][910/1251]	eta 0:12:30 lr 0.000437	time 1.8283 (2.2006)	loss 5.6625 (5.2945)	grad_norm 1.9450 (2.1017)	
[2022-01-17 18:21:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][920/1251]	eta 0:12:08 lr 0.000437	time 2.5262 (2.2018)	loss 4.3446 (5.2924)	grad_norm 1.7055 (2.1046)	
[2022-01-17 18:22:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][930/1251]	eta 0:11:46 lr 0.000438	time 2.2285 (2.2008)	loss 4.4361 (5.2904)	grad_norm 2.5496 (2.1035)	
[2022-01-17 18:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][940/1251]	eta 0:11:24 lr 0.000438	time 2.1628 (2.2020)	loss 5.0219 (5.2915)	grad_norm 2.1964 (2.1016)	
[2022-01-17 18:22:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][950/1251]	eta 0:11:02 lr 0.000439	time 2.1631 (2.2027)	loss 4.0556 (5.2889)	grad_norm 1.8598 (2.0998)	
[2022-01-17 18:23:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][960/1251]	eta 0:10:41 lr 0.000439	time 2.2438 (2.2050)	loss 5.6669 (5.2913)	grad_norm 1.7127 (2.1034)	
[2022-01-17 18:23:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][970/1251]	eta 0:10:19 lr 0.000439	time 2.2359 (2.2040)	loss 5.6818 (5.2912)	grad_norm 1.6070 (2.1014)	
[2022-01-17 18:24:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][980/1251]	eta 0:09:56 lr 0.000440	time 1.8365 (2.2016)	loss 5.2792 (5.2898)	grad_norm 1.8699 (2.0991)	
[2022-01-17 18:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][990/1251]	eta 0:09:34 lr 0.000440	time 1.9512 (2.1995)	loss 4.3583 (5.2895)	grad_norm 1.6098 (2.0966)	
[2022-01-17 18:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1000/1251]	eta 0:09:11 lr 0.000441	time 2.5430 (2.1987)	loss 5.6016 (5.2911)	grad_norm 2.2795 (2.0948)	
[2022-01-17 18:25:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1010/1251]	eta 0:08:49 lr 0.000441	time 2.1772 (2.1979)	loss 5.2023 (5.2922)	grad_norm 1.9284 (2.0955)	
[2022-01-17 18:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1020/1251]	eta 0:08:27 lr 0.000441	time 2.1974 (2.1977)	loss 4.7625 (5.2921)	grad_norm 1.8518 (2.0935)	
[2022-01-17 18:25:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1030/1251]	eta 0:08:05 lr 0.000442	time 2.4873 (2.1982)	loss 5.1522 (5.2911)	grad_norm 2.2304 (2.0938)	
[2022-01-17 18:26:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1040/1251]	eta 0:07:43 lr 0.000442	time 2.0418 (2.1980)	loss 4.4449 (5.2921)	grad_norm 2.5548 (2.0927)	
[2022-01-17 18:26:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1050/1251]	eta 0:07:21 lr 0.000443	time 1.8229 (2.1983)	loss 5.6556 (5.2903)	grad_norm 2.4894 (2.0923)	
[2022-01-17 18:26:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1060/1251]	eta 0:06:59 lr 0.000443	time 2.3182 (2.1978)	loss 5.6164 (5.2928)	grad_norm 2.1165 (2.0929)	
[2022-01-17 18:27:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1070/1251]	eta 0:06:37 lr 0.000443	time 2.2156 (2.1982)	loss 5.1399 (5.2912)	grad_norm 2.5016 (2.0935)	
[2022-01-17 18:27:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1080/1251]	eta 0:06:15 lr 0.000444	time 1.9441 (2.1980)	loss 4.6964 (5.2900)	grad_norm 3.9567 (2.0974)	
[2022-01-17 18:28:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1090/1251]	eta 0:05:54 lr 0.000444	time 1.7011 (2.1996)	loss 5.5655 (5.2918)	grad_norm 1.5523 (2.0963)	
[2022-01-17 18:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1100/1251]	eta 0:05:32 lr 0.000445	time 1.5867 (2.1995)	loss 5.4535 (5.2885)	grad_norm 2.5345 (2.0963)	
[2022-01-17 18:28:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1110/1251]	eta 0:05:10 lr 0.000445	time 3.0076 (2.1998)	loss 5.3859 (5.2886)	grad_norm 1.7441 (2.0974)	
[2022-01-17 18:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1120/1251]	eta 0:04:48 lr 0.000445	time 1.9979 (2.1986)	loss 5.5300 (5.2889)	grad_norm 1.8961 (2.0984)	
[2022-01-17 18:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1130/1251]	eta 0:04:25 lr 0.000446	time 1.9794 (2.1977)	loss 5.5388 (5.2880)	grad_norm 2.0669 (2.0989)	
[2022-01-17 18:29:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1140/1251]	eta 0:04:03 lr 0.000446	time 1.9856 (2.1970)	loss 5.3701 (5.2895)	grad_norm 2.0799 (2.0983)	
[2022-01-17 18:30:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1150/1251]	eta 0:03:41 lr 0.000447	time 3.3147 (2.1967)	loss 5.2542 (5.2889)	grad_norm 2.4172 (2.0971)	
[2022-01-17 18:30:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1160/1251]	eta 0:03:19 lr 0.000447	time 1.9552 (2.1968)	loss 4.6776 (5.2880)	grad_norm 1.6691 (2.0959)	
[2022-01-17 18:30:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1170/1251]	eta 0:02:58 lr 0.000447	time 2.2093 (2.1978)	loss 4.9163 (5.2864)	grad_norm 1.6578 (2.0930)	
[2022-01-17 18:31:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1180/1251]	eta 0:02:36 lr 0.000448	time 2.1555 (2.1978)	loss 5.1922 (5.2841)	grad_norm 2.0454 (2.0933)	
[2022-01-17 18:31:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1190/1251]	eta 0:02:14 lr 0.000448	time 2.2614 (2.1974)	loss 5.8375 (5.2842)	grad_norm 1.6347 (2.0952)	
[2022-01-17 18:32:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1200/1251]	eta 0:01:52 lr 0.000449	time 1.9448 (2.1961)	loss 4.5235 (5.2832)	grad_norm 1.9785 (2.0959)	
[2022-01-17 18:32:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1210/1251]	eta 0:01:30 lr 0.000449	time 2.5782 (2.1964)	loss 5.4438 (5.2836)	grad_norm 1.7061 (2.0935)	
[2022-01-17 18:32:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1220/1251]	eta 0:01:08 lr 0.000449	time 2.6636 (2.1969)	loss 4.8801 (5.2820)	grad_norm 1.7133 (2.0911)	
[2022-01-17 18:33:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1230/1251]	eta 0:00:46 lr 0.000450	time 2.1913 (2.1969)	loss 5.3154 (5.2819)	grad_norm 1.8243 (2.0912)	
[2022-01-17 18:33:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1240/1251]	eta 0:00:24 lr 0.000450	time 1.2578 (2.1947)	loss 4.3879 (5.2796)	grad_norm 1.8748 (2.0903)	
[2022-01-17 18:33:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [8/300][1250/1251]	eta 0:00:02 lr 0.000451	time 1.1799 (2.1891)	loss 5.6961 (5.2805)	grad_norm 2.8228 (2.0894)	
[2022-01-17 18:33:42 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 8 training takes 0:45:38
[2022-01-17 18:34:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.493 (18.493)	Loss 2.8609 (2.8609)	Acc@1 40.039 (40.039)	Acc@5 67.969 (67.969)	
[2022-01-17 18:34:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.921 (3.318)	Loss 2.8328 (2.8226)	Acc@1 41.113 (40.536)	Acc@5 67.090 (66.859)	
[2022-01-17 18:34:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.918 (2.531)	Loss 2.8115 (2.8099)	Acc@1 41.992 (41.034)	Acc@5 66.992 (66.904)	
[2022-01-17 18:34:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.302 (2.221)	Loss 2.7857 (2.8144)	Acc@1 41.504 (41.022)	Acc@5 67.480 (66.611)	
[2022-01-17 18:35:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.622 (2.156)	Loss 2.7766 (2.8214)	Acc@1 43.066 (40.839)	Acc@5 67.969 (66.528)	
[2022-01-17 18:35:17 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 41.014 Acc@5 66.658
[2022-01-17 18:35:17 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 41.0%
[2022-01-17 18:35:17 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 41.01%
[2022-01-17 18:35:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][0/1251]	eta 7:37:56 lr 0.000451	time 21.9637 (21.9637)	loss 4.5415 (4.5415)	grad_norm 2.5014 (2.5014)	
[2022-01-17 18:36:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][10/1251]	eta 1:21:52 lr 0.000451	time 2.1494 (3.9584)	loss 4.8814 (5.0831)	grad_norm 1.8747 (2.1868)	
[2022-01-17 18:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][20/1251]	eta 1:03:43 lr 0.000451	time 1.2494 (3.1058)	loss 4.3637 (5.0250)	grad_norm 2.0127 (2.0643)	
[2022-01-17 18:36:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][30/1251]	eta 0:57:50 lr 0.000452	time 1.5462 (2.8422)	loss 4.8269 (5.1150)	grad_norm 2.4726 (2.0748)	
[2022-01-17 18:37:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][40/1251]	eta 0:54:30 lr 0.000452	time 3.1439 (2.7008)	loss 4.3419 (5.1378)	grad_norm 1.9904 (2.0902)	
[2022-01-17 18:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][50/1251]	eta 0:52:50 lr 0.000453	time 2.3982 (2.6399)	loss 4.5043 (5.1849)	grad_norm 2.1500 (2.0345)	
[2022-01-17 18:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][60/1251]	eta 0:50:52 lr 0.000453	time 2.2206 (2.5633)	loss 4.7024 (5.1752)	grad_norm 1.6325 (1.9923)	
[2022-01-17 18:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][70/1251]	eta 0:49:06 lr 0.000453	time 1.9041 (2.4951)	loss 5.2295 (5.2043)	grad_norm 1.7697 (1.9829)	
[2022-01-17 18:38:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][80/1251]	eta 0:47:58 lr 0.000454	time 2.8095 (2.4578)	loss 5.9089 (5.2119)	grad_norm 1.7773 (2.0295)	
[2022-01-17 18:38:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][90/1251]	eta 0:47:12 lr 0.000454	time 2.2479 (2.4401)	loss 5.7573 (5.2328)	grad_norm 2.0687 (2.0400)	
[2022-01-17 18:39:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][100/1251]	eta 0:46:10 lr 0.000455	time 2.0641 (2.4073)	loss 5.5723 (5.2451)	grad_norm 2.0016 (2.0499)	
[2022-01-17 18:39:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][110/1251]	eta 0:45:02 lr 0.000455	time 1.9125 (2.3686)	loss 5.1082 (5.2433)	grad_norm 2.2159 (2.0436)	
[2022-01-17 18:40:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][120/1251]	eta 0:44:18 lr 0.000455	time 2.2296 (2.3509)	loss 5.0525 (5.2493)	grad_norm 3.5442 (2.0532)	
[2022-01-17 18:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][130/1251]	eta 0:43:55 lr 0.000456	time 2.5817 (2.3508)	loss 5.5920 (5.2397)	grad_norm 2.4883 (2.0657)	
[2022-01-17 18:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][140/1251]	eta 0:43:10 lr 0.000456	time 1.5409 (2.3317)	loss 5.7184 (5.2338)	grad_norm 1.5897 (2.0451)	
[2022-01-17 18:41:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][150/1251]	eta 0:42:35 lr 0.000457	time 1.8693 (2.3212)	loss 4.2676 (5.2113)	grad_norm 1.8391 (2.0420)	
[2022-01-17 18:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][160/1251]	eta 0:42:06 lr 0.000457	time 1.8956 (2.3156)	loss 5.1754 (5.2355)	grad_norm 1.4126 (2.0166)	
[2022-01-17 18:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][170/1251]	eta 0:41:35 lr 0.000457	time 1.5545 (2.3089)	loss 5.4401 (5.2300)	grad_norm 3.1894 (2.0233)	
[2022-01-17 18:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][180/1251]	eta 0:41:00 lr 0.000458	time 1.6709 (2.2970)	loss 5.2653 (5.2313)	grad_norm 2.4206 (2.0509)	
[2022-01-17 18:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][190/1251]	eta 0:40:29 lr 0.000458	time 1.8026 (2.2900)	loss 5.5852 (5.2301)	grad_norm 1.9843 (2.0480)	
[2022-01-17 18:42:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][200/1251]	eta 0:40:07 lr 0.000459	time 2.7751 (2.2907)	loss 5.1448 (5.2352)	grad_norm 1.8443 (2.0358)	
[2022-01-17 18:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][210/1251]	eta 0:39:40 lr 0.000459	time 1.9530 (2.2864)	loss 4.3849 (5.2370)	grad_norm 1.8546 (2.0290)	
[2022-01-17 18:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][220/1251]	eta 0:39:04 lr 0.000459	time 1.7851 (2.2741)	loss 5.6867 (5.2350)	grad_norm 2.1588 (2.0179)	
[2022-01-17 18:44:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][230/1251]	eta 0:38:31 lr 0.000460	time 1.9260 (2.2639)	loss 5.4197 (5.2444)	grad_norm 2.1531 (2.0081)	
[2022-01-17 18:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][240/1251]	eta 0:38:02 lr 0.000460	time 1.8908 (2.2576)	loss 5.4142 (5.2559)	grad_norm 1.9440 (2.0059)	
[2022-01-17 18:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][250/1251]	eta 0:37:43 lr 0.000461	time 1.8434 (2.2613)	loss 5.3067 (5.2646)	grad_norm 1.9977 (2.0051)	
[2022-01-17 18:45:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][260/1251]	eta 0:37:15 lr 0.000461	time 2.1739 (2.2555)	loss 4.1743 (5.2612)	grad_norm 2.8144 (2.0109)	
[2022-01-17 18:45:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][270/1251]	eta 0:36:52 lr 0.000461	time 2.1534 (2.2550)	loss 4.1820 (5.2538)	grad_norm 1.7603 (2.0120)	
[2022-01-17 18:45:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][280/1251]	eta 0:36:27 lr 0.000462	time 2.1333 (2.2525)	loss 5.6931 (5.2547)	grad_norm 1.4853 (2.0081)	
[2022-01-17 18:46:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][290/1251]	eta 0:36:01 lr 0.000462	time 2.4573 (2.2488)	loss 5.3936 (5.2591)	grad_norm 1.8483 (2.0011)	
[2022-01-17 18:46:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][300/1251]	eta 0:35:33 lr 0.000463	time 2.0605 (2.2434)	loss 4.6754 (5.2510)	grad_norm 1.6205 (2.0008)	
[2022-01-17 18:46:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][310/1251]	eta 0:35:08 lr 0.000463	time 2.2070 (2.2402)	loss 4.7316 (5.2461)	grad_norm 1.9207 (2.0016)	
[2022-01-17 18:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][320/1251]	eta 0:34:43 lr 0.000463	time 2.3355 (2.2377)	loss 5.5101 (5.2403)	grad_norm 2.4554 (1.9997)	
[2022-01-17 18:47:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][330/1251]	eta 0:34:19 lr 0.000464	time 1.5667 (2.2362)	loss 4.5936 (5.2346)	grad_norm 1.8717 (1.9979)	
[2022-01-17 18:48:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][340/1251]	eta 0:33:57 lr 0.000464	time 2.1499 (2.2367)	loss 5.4448 (5.2348)	grad_norm 1.7902 (2.0035)	
[2022-01-17 18:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][350/1251]	eta 0:33:32 lr 0.000465	time 2.0741 (2.2331)	loss 5.3991 (5.2339)	grad_norm 1.8873 (2.0045)	
[2022-01-17 18:48:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][360/1251]	eta 0:33:11 lr 0.000465	time 2.4698 (2.2353)	loss 5.5373 (5.2322)	grad_norm 2.1506 (2.0042)	
[2022-01-17 18:49:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][370/1251]	eta 0:32:49 lr 0.000465	time 1.7894 (2.2350)	loss 5.1615 (5.2243)	grad_norm 2.1282 (2.0085)	
[2022-01-17 18:49:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][380/1251]	eta 0:32:23 lr 0.000466	time 1.6496 (2.2311)	loss 5.9180 (5.2255)	grad_norm 1.6671 (2.0047)	
[2022-01-17 18:49:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][390/1251]	eta 0:31:57 lr 0.000466	time 1.8887 (2.2268)	loss 5.5775 (5.2229)	grad_norm 3.0157 (2.0160)	
[2022-01-17 18:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][400/1251]	eta 0:31:32 lr 0.000467	time 2.3616 (2.2241)	loss 4.6722 (5.2237)	grad_norm 2.0513 (2.0136)	
[2022-01-17 18:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][410/1251]	eta 0:31:07 lr 0.000467	time 2.0026 (2.2208)	loss 4.4352 (5.2201)	grad_norm 2.2872 (2.0103)	
[2022-01-17 18:50:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][420/1251]	eta 0:30:51 lr 0.000467	time 1.9867 (2.2277)	loss 4.2777 (5.2229)	grad_norm 1.9043 (2.0071)	
[2022-01-17 18:51:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][430/1251]	eta 0:30:29 lr 0.000468	time 2.5033 (2.2286)	loss 4.8280 (5.2195)	grad_norm 1.7578 (2.0080)	
[2022-01-17 18:51:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][440/1251]	eta 0:30:03 lr 0.000468	time 1.8466 (2.2238)	loss 5.1887 (5.2198)	grad_norm 2.0887 (2.0082)	
[2022-01-17 18:51:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][450/1251]	eta 0:29:39 lr 0.000469	time 2.6170 (2.2212)	loss 5.3344 (5.2210)	grad_norm 1.8277 (2.0040)	
[2022-01-17 18:52:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][460/1251]	eta 0:29:14 lr 0.000469	time 1.8246 (2.2176)	loss 4.3736 (5.2131)	grad_norm 2.2417 (2.0039)	
[2022-01-17 18:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][470/1251]	eta 0:28:51 lr 0.000469	time 2.8548 (2.2174)	loss 5.4019 (5.2084)	grad_norm 3.2262 (2.0106)	
[2022-01-17 18:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][480/1251]	eta 0:28:27 lr 0.000470	time 1.9638 (2.2140)	loss 6.1071 (5.2076)	grad_norm 1.9513 (2.0078)	
[2022-01-17 18:53:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][490/1251]	eta 0:28:04 lr 0.000470	time 2.1386 (2.2129)	loss 4.1250 (5.2025)	grad_norm 1.9680 (2.0031)	
[2022-01-17 18:53:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][500/1251]	eta 0:27:43 lr 0.000471	time 2.1317 (2.2149)	loss 5.4528 (5.2006)	grad_norm 1.6571 (2.0049)	
[2022-01-17 18:54:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][510/1251]	eta 0:27:22 lr 0.000471	time 2.7806 (2.2163)	loss 5.3278 (5.2019)	grad_norm 1.7088 (2.0040)	
[2022-01-17 18:54:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][520/1251]	eta 0:27:02 lr 0.000471	time 2.9078 (2.2192)	loss 5.5019 (5.2037)	grad_norm 1.9208 (2.0016)	
[2022-01-17 18:54:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][530/1251]	eta 0:26:40 lr 0.000472	time 1.8735 (2.2202)	loss 4.6598 (5.2025)	grad_norm 2.5772 (1.9993)	
[2022-01-17 18:55:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][540/1251]	eta 0:26:15 lr 0.000472	time 1.6913 (2.2164)	loss 5.2775 (5.1984)	grad_norm 2.1922 (2.0028)	
[2022-01-17 18:55:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][550/1251]	eta 0:25:50 lr 0.000473	time 1.9701 (2.2121)	loss 5.7256 (5.2023)	grad_norm 1.8360 (2.0005)	
[2022-01-17 18:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][560/1251]	eta 0:25:25 lr 0.000473	time 1.9805 (2.2077)	loss 4.2623 (5.2030)	grad_norm 1.9614 (1.9984)	
[2022-01-17 18:56:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][570/1251]	eta 0:25:01 lr 0.000473	time 2.1496 (2.2050)	loss 4.7678 (5.2021)	grad_norm 3.2944 (1.9980)	
[2022-01-17 18:56:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][580/1251]	eta 0:24:38 lr 0.000474	time 2.5057 (2.2041)	loss 5.0907 (5.2024)	grad_norm 1.7745 (1.9988)	
[2022-01-17 18:56:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][590/1251]	eta 0:24:15 lr 0.000474	time 1.9520 (2.2014)	loss 5.8780 (5.2040)	grad_norm 1.6602 (1.9979)	
[2022-01-17 18:57:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][600/1251]	eta 0:23:53 lr 0.000475	time 2.0860 (2.2014)	loss 4.8665 (5.2015)	grad_norm 1.5087 (1.9997)	
[2022-01-17 18:57:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][610/1251]	eta 0:23:31 lr 0.000475	time 2.8740 (2.2017)	loss 5.6810 (5.2019)	grad_norm 1.5307 (2.0016)	
[2022-01-17 18:58:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][620/1251]	eta 0:23:09 lr 0.000475	time 1.8835 (2.2025)	loss 5.5812 (5.1998)	grad_norm 1.8688 (1.9991)	
[2022-01-17 18:58:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][630/1251]	eta 0:22:47 lr 0.000476	time 2.1450 (2.2016)	loss 5.7638 (5.1956)	grad_norm 1.6451 (1.9966)	
[2022-01-17 18:58:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][640/1251]	eta 0:22:26 lr 0.000476	time 2.4599 (2.2036)	loss 5.8646 (5.2005)	grad_norm 1.4986 (1.9905)	
[2022-01-17 18:59:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][650/1251]	eta 0:22:04 lr 0.000477	time 2.5678 (2.2039)	loss 4.9775 (5.2004)	grad_norm 2.3776 (1.9913)	
[2022-01-17 18:59:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][660/1251]	eta 0:21:43 lr 0.000477	time 2.5496 (2.2052)	loss 4.9538 (5.1994)	grad_norm 1.6333 (1.9892)	
[2022-01-17 18:59:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][670/1251]	eta 0:21:21 lr 0.000477	time 2.5118 (2.2055)	loss 4.8380 (5.2007)	grad_norm 3.1847 (1.9921)	
[2022-01-17 19:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][680/1251]	eta 0:20:59 lr 0.000478	time 2.0156 (2.2060)	loss 4.6794 (5.1983)	grad_norm 1.7014 (1.9870)	
[2022-01-17 19:00:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][690/1251]	eta 0:20:37 lr 0.000478	time 1.9368 (2.2058)	loss 5.3749 (5.1993)	grad_norm 1.6344 (1.9847)	
[2022-01-17 19:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][700/1251]	eta 0:20:14 lr 0.000478	time 2.2143 (2.2048)	loss 5.7138 (5.1971)	grad_norm 2.0673 (1.9848)	
[2022-01-17 19:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][710/1251]	eta 0:19:51 lr 0.000479	time 1.8303 (2.2029)	loss 4.7301 (5.1962)	grad_norm 2.1038 (1.9863)	
[2022-01-17 19:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][720/1251]	eta 0:19:29 lr 0.000479	time 1.9941 (2.2015)	loss 5.6660 (5.1965)	grad_norm 2.1348 (1.9876)	
[2022-01-17 19:02:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][730/1251]	eta 0:19:06 lr 0.000480	time 2.1882 (2.2009)	loss 4.1450 (5.1930)	grad_norm 1.8875 (1.9848)	
[2022-01-17 19:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][740/1251]	eta 0:18:45 lr 0.000480	time 2.6260 (2.2018)	loss 5.4553 (5.1923)	grad_norm 3.4694 (1.9914)	
[2022-01-17 19:02:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][750/1251]	eta 0:18:22 lr 0.000480	time 2.5720 (2.2005)	loss 5.0753 (5.1942)	grad_norm 2.2795 (1.9959)	
[2022-01-17 19:03:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][760/1251]	eta 0:18:00 lr 0.000481	time 1.9138 (2.2000)	loss 4.8786 (5.1938)	grad_norm 1.8405 (1.9964)	
[2022-01-17 19:03:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][770/1251]	eta 0:17:37 lr 0.000481	time 2.3687 (2.1990)	loss 4.6848 (5.1923)	grad_norm 2.9259 (1.9983)	
[2022-01-17 19:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][780/1251]	eta 0:17:14 lr 0.000482	time 2.1994 (2.1969)	loss 4.1642 (5.1925)	grad_norm 2.3306 (1.9978)	
[2022-01-17 19:04:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][790/1251]	eta 0:16:52 lr 0.000482	time 2.8285 (2.1965)	loss 5.2801 (5.1922)	grad_norm 1.8102 (1.9981)	
[2022-01-17 19:04:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][800/1251]	eta 0:16:30 lr 0.000482	time 1.9347 (2.1962)	loss 4.1299 (5.1919)	grad_norm 1.4778 (1.9954)	
[2022-01-17 19:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][810/1251]	eta 0:16:09 lr 0.000483	time 3.4233 (2.1974)	loss 5.8092 (5.1938)	grad_norm 1.9078 (1.9977)	
[2022-01-17 19:05:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][820/1251]	eta 0:15:46 lr 0.000483	time 1.8673 (2.1966)	loss 4.7965 (5.1939)	grad_norm 1.8365 (1.9956)	
[2022-01-17 19:05:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][830/1251]	eta 0:15:25 lr 0.000484	time 2.9309 (2.1982)	loss 4.4083 (5.1925)	grad_norm 1.8125 (1.9944)	
[2022-01-17 19:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][840/1251]	eta 0:15:03 lr 0.000484	time 1.7982 (2.1983)	loss 4.9991 (5.1882)	grad_norm 2.5841 (1.9924)	
[2022-01-17 19:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][850/1251]	eta 0:14:41 lr 0.000484	time 2.6371 (2.1991)	loss 5.1269 (5.1872)	grad_norm 1.9994 (1.9932)	
[2022-01-17 19:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][860/1251]	eta 0:14:19 lr 0.000485	time 1.9660 (2.1990)	loss 4.9221 (5.1847)	grad_norm 1.7953 (1.9923)	
[2022-01-17 19:07:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][870/1251]	eta 0:13:58 lr 0.000485	time 2.7085 (2.2019)	loss 5.3705 (5.1823)	grad_norm 1.4319 (1.9904)	
[2022-01-17 19:07:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][880/1251]	eta 0:13:36 lr 0.000486	time 1.9170 (2.2021)	loss 5.0000 (5.1801)	grad_norm 2.2004 (1.9935)	
[2022-01-17 19:08:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][890/1251]	eta 0:13:15 lr 0.000486	time 2.8882 (2.2032)	loss 5.4842 (5.1802)	grad_norm 2.7869 (1.9959)	
[2022-01-17 19:08:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][900/1251]	eta 0:12:52 lr 0.000486	time 1.6897 (2.2004)	loss 5.7445 (5.1787)	grad_norm 2.1347 (1.9967)	
[2022-01-17 19:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][910/1251]	eta 0:12:29 lr 0.000487	time 1.9309 (2.1977)	loss 5.4725 (5.1791)	grad_norm 1.7296 (1.9958)	
[2022-01-17 19:09:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][920/1251]	eta 0:12:06 lr 0.000487	time 2.3853 (2.1956)	loss 5.1966 (5.1765)	grad_norm 1.7511 (1.9971)	
[2022-01-17 19:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][930/1251]	eta 0:11:44 lr 0.000488	time 2.4835 (2.1950)	loss 5.2242 (5.1731)	grad_norm 1.8075 (1.9945)	
[2022-01-17 19:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][940/1251]	eta 0:11:23 lr 0.000488	time 2.1628 (2.1962)	loss 4.0961 (5.1697)	grad_norm 2.6773 (1.9952)	
[2022-01-17 19:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][950/1251]	eta 0:11:01 lr 0.000488	time 1.9688 (2.1973)	loss 5.5854 (5.1689)	grad_norm 1.9586 (1.9950)	
[2022-01-17 19:10:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][960/1251]	eta 0:10:40 lr 0.000489	time 3.2957 (2.2008)	loss 4.7857 (5.1675)	grad_norm 1.8403 (1.9929)	
[2022-01-17 19:10:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][970/1251]	eta 0:10:18 lr 0.000489	time 2.4582 (2.2008)	loss 5.4494 (5.1669)	grad_norm 2.5086 (1.9946)	
[2022-01-17 19:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][980/1251]	eta 0:09:55 lr 0.000490	time 1.6495 (2.1984)	loss 5.5378 (5.1669)	grad_norm 1.7303 (1.9960)	
[2022-01-17 19:11:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][990/1251]	eta 0:09:33 lr 0.000490	time 2.3736 (2.1977)	loss 5.5886 (5.1661)	grad_norm 1.4856 (1.9953)	
[2022-01-17 19:11:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1000/1251]	eta 0:09:11 lr 0.000490	time 3.4135 (2.1983)	loss 5.8134 (5.1668)	grad_norm 2.2392 (1.9938)	
[2022-01-17 19:12:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1010/1251]	eta 0:08:49 lr 0.000491	time 2.1668 (2.1981)	loss 3.6887 (5.1656)	grad_norm 1.7201 (1.9926)	
[2022-01-17 19:12:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1020/1251]	eta 0:08:27 lr 0.000491	time 2.5641 (2.1986)	loss 5.7009 (5.1637)	grad_norm 1.8996 (1.9913)	
[2022-01-17 19:13:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1030/1251]	eta 0:08:05 lr 0.000492	time 2.2476 (2.1980)	loss 5.3391 (5.1648)	grad_norm 2.1671 (1.9900)	
[2022-01-17 19:13:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1040/1251]	eta 0:07:43 lr 0.000492	time 2.4752 (2.1972)	loss 6.1494 (5.1664)	grad_norm 2.2567 (1.9901)	
[2022-01-17 19:13:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1050/1251]	eta 0:07:21 lr 0.000492	time 1.6290 (2.1953)	loss 5.1354 (5.1653)	grad_norm 1.5269 (1.9880)	
[2022-01-17 19:14:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1060/1251]	eta 0:06:59 lr 0.000493	time 2.3062 (2.1961)	loss 5.6298 (5.1658)	grad_norm 2.1726 (1.9862)	
[2022-01-17 19:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1070/1251]	eta 0:06:37 lr 0.000493	time 3.3641 (2.1986)	loss 5.2242 (5.1664)	grad_norm 1.8549 (1.9849)	
[2022-01-17 19:14:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1080/1251]	eta 0:06:16 lr 0.000494	time 2.3991 (2.1997)	loss 5.6443 (5.1650)	grad_norm 1.9919 (1.9847)	
[2022-01-17 19:15:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1090/1251]	eta 0:05:54 lr 0.000494	time 1.6193 (2.1991)	loss 5.0961 (5.1658)	grad_norm 1.9027 (1.9851)	
[2022-01-17 19:15:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1100/1251]	eta 0:05:31 lr 0.000494	time 1.9558 (2.1977)	loss 4.9320 (5.1646)	grad_norm 1.8241 (1.9840)	
[2022-01-17 19:15:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1110/1251]	eta 0:05:09 lr 0.000495	time 2.4897 (2.1976)	loss 4.1306 (5.1600)	grad_norm 2.1897 (1.9839)	
[2022-01-17 19:16:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1120/1251]	eta 0:04:47 lr 0.000495	time 2.8712 (2.1976)	loss 5.5497 (5.1596)	grad_norm 1.7212 (1.9838)	
[2022-01-17 19:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1130/1251]	eta 0:04:25 lr 0.000496	time 2.7270 (2.1970)	loss 5.0047 (5.1590)	grad_norm 1.9053 (1.9852)	
[2022-01-17 19:17:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1140/1251]	eta 0:04:03 lr 0.000496	time 2.4587 (2.1961)	loss 4.7167 (5.1565)	grad_norm 1.6284 (1.9841)	
[2022-01-17 19:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1150/1251]	eta 0:03:41 lr 0.000496	time 2.0736 (2.1952)	loss 5.7132 (5.1579)	grad_norm 1.6047 (1.9819)	
[2022-01-17 19:17:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1160/1251]	eta 0:03:19 lr 0.000497	time 2.1898 (2.1951)	loss 5.7970 (5.1555)	grad_norm 2.2070 (1.9807)	
[2022-01-17 19:18:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1170/1251]	eta 0:02:57 lr 0.000497	time 1.5050 (2.1935)	loss 4.4161 (5.1546)	grad_norm 2.1643 (1.9789)	
[2022-01-17 19:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1180/1251]	eta 0:02:35 lr 0.000498	time 2.3443 (2.1928)	loss 4.7013 (5.1524)	grad_norm 1.8213 (1.9791)	
[2022-01-17 19:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1190/1251]	eta 0:02:13 lr 0.000498	time 1.6924 (2.1923)	loss 4.1842 (5.1523)	grad_norm 1.8700 (1.9808)	
[2022-01-17 19:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1200/1251]	eta 0:01:51 lr 0.000498	time 1.5990 (2.1919)	loss 4.2942 (5.1505)	grad_norm 1.8842 (1.9806)	
[2022-01-17 19:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1210/1251]	eta 0:01:29 lr 0.000499	time 2.5512 (2.1933)	loss 5.0737 (5.1518)	grad_norm 1.6297 (1.9794)	
[2022-01-17 19:19:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1220/1251]	eta 0:01:07 lr 0.000499	time 1.8279 (2.1932)	loss 5.1243 (5.1511)	grad_norm 1.7060 (1.9788)	
[2022-01-17 19:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1230/1251]	eta 0:00:46 lr 0.000500	time 1.5222 (2.1949)	loss 5.3118 (5.1503)	grad_norm 2.0585 (1.9780)	
[2022-01-17 19:20:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1240/1251]	eta 0:00:24 lr 0.000500	time 2.1775 (2.1944)	loss 4.0731 (5.1502)	grad_norm 1.9927 (1.9777)	
[2022-01-17 19:20:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [9/300][1250/1251]	eta 0:00:02 lr 0.000500	time 1.1631 (2.1890)	loss 5.3733 (5.1501)	grad_norm 1.9684 (1.9762)	
[2022-01-17 19:20:56 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 9 training takes 0:45:38
[2022-01-17 19:21:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.001 (19.001)	Loss 2.6528 (2.6528)	Acc@1 42.871 (42.871)	Acc@5 69.336 (69.336)	
[2022-01-17 19:21:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.950 (3.328)	Loss 2.6160 (2.5977)	Acc@1 44.727 (44.656)	Acc@5 71.387 (70.162)	
[2022-01-17 19:21:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.277 (2.604)	Loss 2.6056 (2.5947)	Acc@1 42.285 (44.513)	Acc@5 70.996 (70.392)	
[2022-01-17 19:22:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.923 (2.279)	Loss 2.6127 (2.5932)	Acc@1 43.555 (44.383)	Acc@5 68.652 (70.284)	
[2022-01-17 19:22:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.829 (2.145)	Loss 2.5416 (2.5975)	Acc@1 44.629 (44.388)	Acc@5 72.656 (70.203)	
[2022-01-17 19:22:32 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 44.454 Acc@5 70.008
[2022-01-17 19:22:32 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 44.5%
[2022-01-17 19:22:32 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 44.45%
[2022-01-17 19:22:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][0/1251]	eta 8:20:28 lr 0.000501	time 24.0034 (24.0034)	loss 5.4168 (5.4168)	grad_norm 2.0246 (2.0246)	
[2022-01-17 19:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][10/1251]	eta 1:27:54 lr 0.000501	time 1.7833 (4.2504)	loss 5.4682 (5.3458)	grad_norm 1.6959 (1.6999)	
[2022-01-17 19:23:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][20/1251]	eta 1:05:40 lr 0.000501	time 2.3475 (3.2008)	loss 4.3084 (5.2579)	grad_norm 2.0126 (1.9757)	
[2022-01-17 19:24:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][30/1251]	eta 0:57:25 lr 0.000502	time 1.6101 (2.8222)	loss 5.6825 (5.1792)	grad_norm 1.7280 (2.0071)	
[2022-01-17 19:24:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][40/1251]	eta 0:55:23 lr 0.000502	time 5.1558 (2.7448)	loss 5.2530 (5.1667)	grad_norm 1.4089 (1.9336)	
[2022-01-17 19:24:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][50/1251]	eta 0:52:38 lr 0.000502	time 1.5867 (2.6299)	loss 4.4181 (5.1272)	grad_norm 1.6151 (1.8903)	
[2022-01-17 19:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][60/1251]	eta 0:50:58 lr 0.000503	time 2.5842 (2.5680)	loss 5.4288 (5.1066)	grad_norm 1.4568 (1.9061)	
[2022-01-17 19:25:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][70/1251]	eta 0:49:23 lr 0.000503	time 1.8648 (2.5094)	loss 4.1796 (5.1255)	grad_norm 1.9496 (1.8830)	
[2022-01-17 19:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][80/1251]	eta 0:48:07 lr 0.000504	time 2.4645 (2.4661)	loss 5.3466 (5.1446)	grad_norm 1.6945 (1.8653)	
[2022-01-17 19:26:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][90/1251]	eta 0:47:00 lr 0.000504	time 1.8047 (2.4290)	loss 5.6257 (5.1343)	grad_norm 1.6891 (1.8598)	
[2022-01-17 19:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][100/1251]	eta 0:45:52 lr 0.000504	time 1.8890 (2.3913)	loss 4.9382 (5.1198)	grad_norm 2.5551 (1.8652)	
[2022-01-17 19:26:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][110/1251]	eta 0:45:06 lr 0.000505	time 2.1980 (2.3718)	loss 4.6675 (5.1255)	grad_norm 1.4110 (1.8780)	
[2022-01-17 19:27:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][120/1251]	eta 0:44:36 lr 0.000505	time 3.0320 (2.3664)	loss 5.2596 (5.1237)	grad_norm 2.1104 (1.8629)	
[2022-01-17 19:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][130/1251]	eta 0:44:23 lr 0.000506	time 2.7501 (2.3758)	loss 5.3856 (5.1158)	grad_norm 2.3337 (1.8639)	
[2022-01-17 19:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][140/1251]	eta 0:43:39 lr 0.000506	time 1.6289 (2.3578)	loss 5.1034 (5.1177)	grad_norm 2.0685 (1.8642)	
[2022-01-17 19:28:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][150/1251]	eta 0:43:02 lr 0.000506	time 2.2520 (2.3453)	loss 5.5077 (5.1239)	grad_norm 2.0923 (1.8659)	
[2022-01-17 19:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][160/1251]	eta 0:42:14 lr 0.000507	time 1.9148 (2.3229)	loss 5.4836 (5.1322)	grad_norm 1.5840 (1.8553)	
[2022-01-17 19:29:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][170/1251]	eta 0:41:30 lr 0.000507	time 2.2439 (2.3040)	loss 5.2089 (5.1412)	grad_norm 1.8646 (1.8671)	
[2022-01-17 19:29:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][180/1251]	eta 0:40:55 lr 0.000508	time 2.0061 (2.2924)	loss 5.5924 (5.1409)	grad_norm 3.6918 (1.8773)	
[2022-01-17 19:29:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][190/1251]	eta 0:40:25 lr 0.000508	time 2.2140 (2.2863)	loss 5.5742 (5.1456)	grad_norm 2.0162 (1.8865)	
[2022-01-17 19:30:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][200/1251]	eta 0:39:57 lr 0.000508	time 1.7814 (2.2811)	loss 5.4420 (5.1400)	grad_norm 1.5619 (1.8832)	
[2022-01-17 19:30:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][210/1251]	eta 0:39:32 lr 0.000509	time 2.2964 (2.2789)	loss 5.7731 (5.1482)	grad_norm 1.4316 (1.8811)	
[2022-01-17 19:30:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][220/1251]	eta 0:39:02 lr 0.000509	time 1.7095 (2.2721)	loss 4.3089 (5.1494)	grad_norm 1.7147 (1.8860)	
[2022-01-17 19:31:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][230/1251]	eta 0:38:30 lr 0.000510	time 2.5912 (2.2633)	loss 5.8170 (5.1474)	grad_norm 2.0540 (1.8924)	
[2022-01-17 19:31:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][240/1251]	eta 0:37:57 lr 0.000510	time 1.7705 (2.2530)	loss 4.4293 (5.1290)	grad_norm 1.6257 (1.9060)	
[2022-01-17 19:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][250/1251]	eta 0:37:34 lr 0.000510	time 2.5494 (2.2522)	loss 4.4057 (5.1311)	grad_norm 1.8246 (1.9107)	
[2022-01-17 19:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][260/1251]	eta 0:37:10 lr 0.000511	time 2.2989 (2.2503)	loss 5.8675 (5.1406)	grad_norm 1.6160 (1.9027)	
[2022-01-17 19:32:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][270/1251]	eta 0:36:50 lr 0.000511	time 4.2768 (2.2535)	loss 4.9454 (5.1289)	grad_norm 1.8344 (1.9016)	
[2022-01-17 19:33:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][280/1251]	eta 0:36:29 lr 0.000512	time 2.2431 (2.2553)	loss 5.4647 (5.1215)	grad_norm 1.5893 (1.8939)	
[2022-01-17 19:33:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][290/1251]	eta 0:36:07 lr 0.000512	time 1.8018 (2.2556)	loss 5.1832 (5.1168)	grad_norm 1.8544 (1.8939)	
[2022-01-17 19:33:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][300/1251]	eta 0:35:41 lr 0.000512	time 1.7916 (2.2520)	loss 5.5586 (5.1120)	grad_norm 1.6710 (1.9030)	
[2022-01-17 19:34:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][310/1251]	eta 0:35:18 lr 0.000513	time 3.1925 (2.2514)	loss 5.4507 (5.1165)	grad_norm 1.8924 (1.9038)	
[2022-01-17 19:34:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][320/1251]	eta 0:34:49 lr 0.000513	time 2.3288 (2.2447)	loss 4.7863 (5.1151)	grad_norm 1.6263 (1.9036)	
[2022-01-17 19:34:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][330/1251]	eta 0:34:25 lr 0.000514	time 1.7350 (2.2422)	loss 4.5480 (5.1118)	grad_norm 1.4829 (1.8989)	
[2022-01-17 19:35:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][340/1251]	eta 0:34:00 lr 0.000514	time 1.5388 (2.2395)	loss 5.0582 (5.1182)	grad_norm 1.6102 (1.8936)	
[2022-01-17 19:35:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][350/1251]	eta 0:33:35 lr 0.000514	time 2.2512 (2.2373)	loss 4.6530 (5.1133)	grad_norm 1.6267 (1.8928)	
[2022-01-17 19:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][360/1251]	eta 0:33:08 lr 0.000515	time 2.2572 (2.2314)	loss 5.3797 (5.1185)	grad_norm 1.9705 (1.8995)	
[2022-01-17 19:36:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][370/1251]	eta 0:32:42 lr 0.000515	time 1.8927 (2.2277)	loss 5.2782 (5.1182)	grad_norm 2.1021 (1.8969)	
[2022-01-17 19:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][380/1251]	eta 0:32:15 lr 0.000516	time 1.9582 (2.2227)	loss 5.4509 (5.1161)	grad_norm 1.7405 (1.8943)	
[2022-01-17 19:37:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][390/1251]	eta 0:31:53 lr 0.000516	time 2.5365 (2.2226)	loss 5.6366 (5.1185)	grad_norm 3.0777 (1.8984)	
[2022-01-17 19:37:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][400/1251]	eta 0:31:35 lr 0.000516	time 3.4580 (2.2279)	loss 3.8405 (5.1208)	grad_norm 1.3089 (1.8993)	
[2022-01-17 19:37:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][410/1251]	eta 0:31:14 lr 0.000517	time 1.9338 (2.2292)	loss 5.3973 (5.1278)	grad_norm 1.9283 (1.8983)	
[2022-01-17 19:38:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][420/1251]	eta 0:30:53 lr 0.000517	time 1.9099 (2.2302)	loss 4.7672 (5.1225)	grad_norm 1.7013 (1.8939)	
[2022-01-17 19:38:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][430/1251]	eta 0:30:30 lr 0.000518	time 2.2393 (2.2297)	loss 5.3344 (5.1197)	grad_norm 1.5830 (1.8925)	
[2022-01-17 19:38:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][440/1251]	eta 0:30:08 lr 0.000518	time 2.2528 (2.2296)	loss 5.4369 (5.1192)	grad_norm 1.9153 (1.8954)	
[2022-01-17 19:39:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][450/1251]	eta 0:29:46 lr 0.000518	time 1.6830 (2.2307)	loss 5.3707 (5.1211)	grad_norm 1.5280 (1.8960)	
[2022-01-17 19:39:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][460/1251]	eta 0:29:22 lr 0.000519	time 1.9250 (2.2276)	loss 4.1474 (5.1219)	grad_norm 2.1646 (1.8920)	
[2022-01-17 19:39:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][470/1251]	eta 0:28:55 lr 0.000519	time 1.6274 (2.2216)	loss 4.1201 (5.1195)	grad_norm 1.9755 (1.8928)	
[2022-01-17 19:40:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][480/1251]	eta 0:28:29 lr 0.000520	time 1.8477 (2.2179)	loss 5.3826 (5.1129)	grad_norm 1.8127 (1.8916)	
[2022-01-17 19:40:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][490/1251]	eta 0:28:08 lr 0.000520	time 2.5322 (2.2183)	loss 4.2630 (5.1090)	grad_norm 1.8006 (1.8915)	
[2022-01-17 19:41:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][500/1251]	eta 0:27:47 lr 0.000520	time 2.1301 (2.2202)	loss 5.3499 (5.1120)	grad_norm 1.5408 (1.8892)	
[2022-01-17 19:41:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][510/1251]	eta 0:27:25 lr 0.000521	time 1.6698 (2.2203)	loss 5.4858 (5.1164)	grad_norm 1.9398 (1.8883)	
[2022-01-17 19:41:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][520/1251]	eta 0:27:05 lr 0.000521	time 1.8514 (2.2235)	loss 4.3055 (5.1178)	grad_norm 2.1184 (1.8881)	
[2022-01-17 19:42:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][530/1251]	eta 0:26:43 lr 0.000522	time 2.4696 (2.2247)	loss 5.0327 (5.1207)	grad_norm 1.8775 (1.8904)	
[2022-01-17 19:42:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][540/1251]	eta 0:26:19 lr 0.000522	time 1.9587 (2.2220)	loss 5.0070 (5.1223)	grad_norm 1.9260 (1.8920)	
[2022-01-17 19:42:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][550/1251]	eta 0:25:55 lr 0.000522	time 1.9278 (2.2186)	loss 4.0917 (5.1209)	grad_norm 3.9105 (1.8979)	
[2022-01-17 19:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][560/1251]	eta 0:25:31 lr 0.000523	time 1.8414 (2.2167)	loss 4.8504 (5.1181)	grad_norm 2.3968 (1.9031)	
[2022-01-17 19:43:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][570/1251]	eta 0:25:08 lr 0.000523	time 1.9151 (2.2146)	loss 4.9168 (5.1133)	grad_norm 2.2516 (1.9021)	
[2022-01-17 19:43:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][580/1251]	eta 0:24:46 lr 0.000524	time 1.8312 (2.2152)	loss 4.0989 (5.1155)	grad_norm 1.7527 (1.9011)	
[2022-01-17 19:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][590/1251]	eta 0:24:25 lr 0.000524	time 2.4190 (2.2176)	loss 5.5379 (5.1182)	grad_norm 1.5982 (1.8983)	
[2022-01-17 19:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][600/1251]	eta 0:24:04 lr 0.000524	time 1.8330 (2.2187)	loss 4.9632 (5.1194)	grad_norm 1.8680 (1.8951)	
[2022-01-17 19:45:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][610/1251]	eta 0:23:41 lr 0.000525	time 1.6280 (2.2174)	loss 5.6356 (5.1164)	grad_norm 2.2935 (1.8959)	
[2022-01-17 19:45:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][620/1251]	eta 0:23:16 lr 0.000525	time 1.8206 (2.2133)	loss 4.1243 (5.1159)	grad_norm 2.1450 (1.8982)	
[2022-01-17 19:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][630/1251]	eta 0:22:51 lr 0.000526	time 1.7771 (2.2081)	loss 4.1240 (5.1153)	grad_norm 1.5578 (1.8942)	
[2022-01-17 19:46:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][640/1251]	eta 0:22:27 lr 0.000526	time 1.6317 (2.2054)	loss 5.4125 (5.1199)	grad_norm 1.5849 (1.8895)	
[2022-01-17 19:46:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][650/1251]	eta 0:22:06 lr 0.000526	time 2.2865 (2.2068)	loss 5.0700 (5.1181)	grad_norm 1.6617 (1.8888)	
[2022-01-17 19:46:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][660/1251]	eta 0:21:43 lr 0.000527	time 1.8559 (2.2059)	loss 4.4762 (5.1142)	grad_norm 1.7317 (1.8872)	
[2022-01-17 19:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][670/1251]	eta 0:21:24 lr 0.000527	time 3.2970 (2.2105)	loss 5.6637 (5.1171)	grad_norm 1.5081 (1.8849)	
[2022-01-17 19:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][680/1251]	eta 0:21:04 lr 0.000528	time 3.4465 (2.2153)	loss 4.6139 (5.1144)	grad_norm 2.0975 (1.8826)	
[2022-01-17 19:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][690/1251]	eta 0:20:42 lr 0.000528	time 1.7659 (2.2145)	loss 5.1968 (5.1138)	grad_norm 2.7694 (1.8828)	
[2022-01-17 19:48:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][700/1251]	eta 0:20:19 lr 0.000528	time 2.0463 (2.2125)	loss 5.8393 (5.1154)	grad_norm 2.8350 (1.8854)	
[2022-01-17 19:48:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][710/1251]	eta 0:19:55 lr 0.000529	time 1.9861 (2.2101)	loss 4.6742 (5.1174)	grad_norm 2.2997 (1.8862)	
[2022-01-17 19:49:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][720/1251]	eta 0:19:33 lr 0.000529	time 2.8032 (2.2105)	loss 5.5761 (5.1174)	grad_norm 1.8707 (1.8869)	
[2022-01-17 19:49:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][730/1251]	eta 0:19:10 lr 0.000530	time 1.8699 (2.2092)	loss 4.2267 (5.1145)	grad_norm 1.8015 (1.8852)	
[2022-01-17 19:49:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][740/1251]	eta 0:18:47 lr 0.000530	time 2.5074 (2.2072)	loss 5.1355 (5.1109)	grad_norm 2.3661 (1.8869)	
[2022-01-17 19:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][750/1251]	eta 0:18:25 lr 0.000530	time 2.2449 (2.2057)	loss 5.0286 (5.1100)	grad_norm 1.9301 (1.8875)	
[2022-01-17 19:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][760/1251]	eta 0:18:02 lr 0.000531	time 2.5408 (2.2043)	loss 4.1015 (5.1076)	grad_norm 1.9946 (1.8877)	
[2022-01-17 19:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][770/1251]	eta 0:17:40 lr 0.000531	time 2.5404 (2.2048)	loss 5.7528 (5.1060)	grad_norm 3.5680 (1.8902)	
[2022-01-17 19:51:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][780/1251]	eta 0:17:18 lr 0.000532	time 2.5814 (2.2049)	loss 5.2800 (5.1076)	grad_norm 1.9871 (1.8906)	
[2022-01-17 19:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][790/1251]	eta 0:16:56 lr 0.000532	time 2.1288 (2.2048)	loss 4.9708 (5.1062)	grad_norm 1.6049 (1.8905)	
[2022-01-17 19:51:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][800/1251]	eta 0:16:34 lr 0.000532	time 2.7264 (2.2062)	loss 4.0541 (5.0998)	grad_norm 1.7549 (1.8871)	
[2022-01-17 19:52:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][810/1251]	eta 0:16:13 lr 0.000533	time 2.8522 (2.2077)	loss 5.3143 (5.0980)	grad_norm 1.4661 (1.8853)	
[2022-01-17 19:52:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][820/1251]	eta 0:15:51 lr 0.000533	time 2.1573 (2.2076)	loss 5.9012 (5.0989)	grad_norm 1.7365 (1.8846)	
[2022-01-17 19:53:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][830/1251]	eta 0:15:29 lr 0.000534	time 2.2651 (2.2077)	loss 5.6748 (5.0976)	grad_norm 1.3424 (1.8839)	
[2022-01-17 19:53:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][840/1251]	eta 0:15:07 lr 0.000534	time 2.7787 (2.2080)	loss 4.9245 (5.0980)	grad_norm 1.5892 (1.8830)	
[2022-01-17 19:53:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][850/1251]	eta 0:14:44 lr 0.000534	time 2.2037 (2.2064)	loss 4.0791 (5.0973)	grad_norm 1.8603 (1.8805)	
[2022-01-17 19:54:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][860/1251]	eta 0:14:21 lr 0.000535	time 1.9085 (2.2045)	loss 5.4625 (5.0996)	grad_norm 1.5780 (1.8779)	
[2022-01-17 19:54:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][870/1251]	eta 0:13:59 lr 0.000535	time 2.5874 (2.2045)	loss 5.5752 (5.1031)	grad_norm 1.7732 (1.8779)	
[2022-01-17 19:54:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][880/1251]	eta 0:13:38 lr 0.000536	time 3.6669 (2.2065)	loss 5.1711 (5.1027)	grad_norm 1.4089 (1.8759)	
[2022-01-17 19:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][890/1251]	eta 0:13:16 lr 0.000536	time 1.7280 (2.2076)	loss 4.2832 (5.0976)	grad_norm 3.1899 (1.8772)	
[2022-01-17 19:55:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][900/1251]	eta 0:12:54 lr 0.000536	time 1.5966 (2.2071)	loss 4.1316 (5.0910)	grad_norm 1.6868 (1.8797)	
[2022-01-17 19:56:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][910/1251]	eta 0:12:32 lr 0.000537	time 1.6009 (2.2055)	loss 5.1179 (5.0906)	grad_norm 1.5535 (1.8782)	
[2022-01-17 19:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][920/1251]	eta 0:12:09 lr 0.000537	time 2.6202 (2.2047)	loss 5.1654 (5.0913)	grad_norm 1.8714 (1.8791)	
[2022-01-17 19:56:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][930/1251]	eta 0:11:47 lr 0.000538	time 2.2496 (2.2031)	loss 4.6360 (5.0948)	grad_norm 1.9532 (1.8788)	
[2022-01-17 19:57:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][940/1251]	eta 0:11:24 lr 0.000538	time 1.9103 (2.2022)	loss 4.4339 (5.0955)	grad_norm 2.0513 (1.8787)	
[2022-01-17 19:57:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][950/1251]	eta 0:11:02 lr 0.000538	time 2.2156 (2.2013)	loss 4.4525 (5.0930)	grad_norm 1.6939 (1.8765)	
[2022-01-17 19:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][960/1251]	eta 0:10:40 lr 0.000539	time 2.3903 (2.2017)	loss 5.2421 (5.0938)	grad_norm 1.4171 (1.8762)	
[2022-01-17 19:58:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][970/1251]	eta 0:10:18 lr 0.000539	time 2.2478 (2.2027)	loss 4.5668 (5.0922)	grad_norm 1.8630 (1.8753)	
[2022-01-17 19:58:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][980/1251]	eta 0:09:57 lr 0.000540	time 1.5148 (2.2031)	loss 5.3223 (5.0910)	grad_norm 2.4777 (1.8752)	
[2022-01-17 19:58:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][990/1251]	eta 0:09:35 lr 0.000540	time 2.5043 (2.2040)	loss 5.4697 (5.0911)	grad_norm 1.8991 (1.8754)	
[2022-01-17 19:59:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1000/1251]	eta 0:09:12 lr 0.000540	time 1.7164 (2.2028)	loss 5.6417 (5.0920)	grad_norm 2.3582 (1.8747)	
[2022-01-17 19:59:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1010/1251]	eta 0:08:50 lr 0.000541	time 1.8846 (2.2013)	loss 3.8931 (5.0875)	grad_norm 1.5904 (1.8740)	
[2022-01-17 19:59:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1020/1251]	eta 0:08:28 lr 0.000541	time 1.8811 (2.2008)	loss 5.1364 (5.0858)	grad_norm 1.7411 (1.8738)	
[2022-01-17 20:00:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1030/1251]	eta 0:08:06 lr 0.000542	time 2.5705 (2.2002)	loss 4.8850 (5.0852)	grad_norm 1.7266 (1.8728)	
[2022-01-17 20:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1040/1251]	eta 0:07:44 lr 0.000542	time 2.1233 (2.2020)	loss 4.3191 (5.0843)	grad_norm 1.9336 (1.8723)	
[2022-01-17 20:01:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1050/1251]	eta 0:07:23 lr 0.000542	time 1.8119 (2.2042)	loss 5.1386 (5.0841)	grad_norm 1.7876 (1.8701)	
[2022-01-17 20:01:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1060/1251]	eta 0:07:00 lr 0.000543	time 1.8852 (2.2031)	loss 4.8949 (5.0819)	grad_norm 2.0027 (1.8683)	
[2022-01-17 20:01:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1070/1251]	eta 0:06:38 lr 0.000543	time 2.2541 (2.2017)	loss 5.2355 (5.0812)	grad_norm 1.5705 (1.8685)	
[2022-01-17 20:02:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1080/1251]	eta 0:06:16 lr 0.000544	time 1.5431 (2.1993)	loss 4.7441 (5.0808)	grad_norm 1.8832 (1.8729)	
[2022-01-17 20:02:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1090/1251]	eta 0:05:54 lr 0.000544	time 2.7532 (2.1992)	loss 4.0283 (5.0783)	grad_norm 2.4471 (1.8732)	
[2022-01-17 20:02:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1100/1251]	eta 0:05:32 lr 0.000544	time 2.1274 (2.1991)	loss 5.2798 (5.0775)	grad_norm 1.5092 (1.8727)	
[2022-01-17 20:03:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1110/1251]	eta 0:05:10 lr 0.000545	time 2.4946 (2.1991)	loss 5.3757 (5.0770)	grad_norm 1.5714 (1.8711)	
[2022-01-17 20:03:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1120/1251]	eta 0:04:47 lr 0.000545	time 1.9142 (2.1980)	loss 5.1009 (5.0787)	grad_norm 1.8975 (1.8699)	
[2022-01-17 20:03:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1130/1251]	eta 0:04:26 lr 0.000546	time 2.4556 (2.1988)	loss 4.7028 (5.0765)	grad_norm 1.5485 (1.8708)	
[2022-01-17 20:04:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1140/1251]	eta 0:04:04 lr 0.000546	time 2.2820 (2.1985)	loss 5.0517 (5.0729)	grad_norm 1.9271 (1.8697)	
[2022-01-17 20:04:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1150/1251]	eta 0:03:42 lr 0.000546	time 2.0153 (2.1983)	loss 4.4267 (5.0709)	grad_norm 1.8336 (1.8689)	
[2022-01-17 20:05:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1160/1251]	eta 0:03:19 lr 0.000547	time 1.9275 (2.1975)	loss 4.7978 (5.0717)	grad_norm 2.3725 (1.8720)	
[2022-01-17 20:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1170/1251]	eta 0:02:58 lr 0.000547	time 1.7876 (2.1977)	loss 5.2331 (5.0729)	grad_norm 1.4987 (1.8700)	
[2022-01-17 20:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1180/1251]	eta 0:02:35 lr 0.000548	time 1.8430 (2.1970)	loss 4.2583 (5.0709)	grad_norm 1.7620 (1.8699)	
[2022-01-17 20:06:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1190/1251]	eta 0:02:14 lr 0.000548	time 2.0002 (2.1972)	loss 4.5608 (5.0705)	grad_norm 1.6634 (1.8679)	
[2022-01-17 20:06:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1200/1251]	eta 0:01:52 lr 0.000548	time 2.7119 (2.1972)	loss 5.6972 (5.0708)	grad_norm 2.0948 (1.8664)	
[2022-01-17 20:06:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1210/1251]	eta 0:01:30 lr 0.000549	time 3.1715 (2.2006)	loss 5.0411 (5.0705)	grad_norm 1.7640 (1.8673)	
[2022-01-17 20:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1220/1251]	eta 0:01:08 lr 0.000549	time 2.0530 (2.2011)	loss 5.3663 (5.0696)	grad_norm 1.3978 (1.8678)	
[2022-01-17 20:07:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1230/1251]	eta 0:00:46 lr 0.000550	time 1.5586 (2.2007)	loss 4.5191 (5.0686)	grad_norm 1.6626 (1.8668)	
[2022-01-17 20:08:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1240/1251]	eta 0:00:24 lr 0.000550	time 1.8662 (2.1999)	loss 5.3928 (5.0699)	grad_norm 1.9416 (1.8653)	
[2022-01-17 20:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [10/300][1250/1251]	eta 0:00:02 lr 0.000550	time 1.3919 (2.1942)	loss 5.2028 (5.0704)	grad_norm 1.8790 (1.8645)	
[2022-01-17 20:08:18 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 10 training takes 0:45:45
[2022-01-17 20:08:18 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_10 saving......
[2022-01-17 20:08:29 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_10 saved !!!
[2022-01-17 20:08:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 15.974 (15.974)	Loss 2.4638 (2.4638)	Acc@1 45.801 (45.801)	Acc@5 72.559 (72.559)	
[2022-01-17 20:09:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.351 (2.846)	Loss 2.4573 (2.4743)	Acc@1 47.656 (46.786)	Acc@5 72.266 (72.656)	
[2022-01-17 20:09:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.999 (2.263)	Loss 2.4580 (2.4721)	Acc@1 47.070 (47.080)	Acc@5 73.535 (72.889)	
[2022-01-17 20:09:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.879 (2.000)	Loss 2.5693 (2.4769)	Acc@1 45.605 (46.947)	Acc@5 71.582 (72.792)	
[2022-01-17 20:09:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.082 (1.967)	Loss 2.5405 (2.4839)	Acc@1 44.531 (46.768)	Acc@5 71.582 (72.699)	
[2022-01-17 20:09:57 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 46.794 Acc@5 72.584
[2022-01-17 20:09:57 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 46.8%
[2022-01-17 20:09:57 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 46.79%
[2022-01-17 20:10:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][0/1251]	eta 7:34:18 lr 0.000550	time 21.7890 (21.7890)	loss 5.6197 (5.6197)	grad_norm 1.6785 (1.6785)	
[2022-01-17 20:10:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][10/1251]	eta 1:24:09 lr 0.000551	time 1.8479 (4.0688)	loss 5.6782 (5.1328)	grad_norm 1.8198 (1.6923)	
[2022-01-17 20:11:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][20/1251]	eta 1:04:14 lr 0.000551	time 1.8353 (3.1314)	loss 5.3752 (5.2600)	grad_norm 1.7087 (1.8273)	
[2022-01-17 20:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][30/1251]	eta 0:56:24 lr 0.000552	time 1.5571 (2.7721)	loss 4.8581 (5.1608)	grad_norm 2.0707 (1.8981)	
[2022-01-17 20:11:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][40/1251]	eta 0:53:53 lr 0.000552	time 4.0250 (2.6701)	loss 4.6736 (5.1217)	grad_norm 1.9527 (1.8499)	
[2022-01-17 20:12:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][50/1251]	eta 0:52:25 lr 0.000552	time 3.4631 (2.6188)	loss 4.9191 (5.0624)	grad_norm 1.3823 (1.8221)	
[2022-01-17 20:12:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][60/1251]	eta 0:50:38 lr 0.000553	time 1.8660 (2.5513)	loss 5.7285 (5.0393)	grad_norm 1.6403 (1.8183)	
[2022-01-17 20:12:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][70/1251]	eta 0:49:00 lr 0.000553	time 1.5426 (2.4899)	loss 4.0142 (5.0144)	grad_norm 1.5978 (1.8032)	
[2022-01-17 20:13:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][80/1251]	eta 0:48:19 lr 0.000554	time 3.8539 (2.4761)	loss 5.6469 (5.0410)	grad_norm 1.9900 (1.8174)	
[2022-01-17 20:13:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][90/1251]	eta 0:47:30 lr 0.000554	time 3.2698 (2.4551)	loss 5.1108 (5.0359)	grad_norm 1.7845 (1.8224)	
[2022-01-17 20:14:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][100/1251]	eta 0:46:16 lr 0.000554	time 1.8479 (2.4123)	loss 4.7927 (5.0432)	grad_norm 2.0515 (1.8177)	
[2022-01-17 20:14:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][110/1251]	eta 0:45:15 lr 0.000555	time 1.9378 (2.3798)	loss 5.1845 (5.0492)	grad_norm 2.2115 (1.8141)	
[2022-01-17 20:14:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][120/1251]	eta 0:44:19 lr 0.000555	time 1.9494 (2.3515)	loss 5.4678 (5.0298)	grad_norm 1.8207 (1.8505)	
[2022-01-17 20:15:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][130/1251]	eta 0:43:44 lr 0.000556	time 2.7794 (2.3409)	loss 5.6689 (5.0385)	grad_norm 1.4216 (1.8378)	
[2022-01-17 20:15:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][140/1251]	eta 0:43:08 lr 0.000556	time 1.9767 (2.3297)	loss 4.7702 (5.0285)	grad_norm 1.4190 (1.8330)	
[2022-01-17 20:15:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][150/1251]	eta 0:42:42 lr 0.000556	time 2.1784 (2.3270)	loss 5.2073 (5.0336)	grad_norm 1.5646 (1.8401)	
[2022-01-17 20:16:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][160/1251]	eta 0:42:20 lr 0.000557	time 2.8266 (2.3287)	loss 5.5114 (5.0269)	grad_norm 1.6413 (1.8360)	
[2022-01-17 20:16:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][170/1251]	eta 0:41:43 lr 0.000557	time 2.2172 (2.3158)	loss 5.0396 (5.0218)	grad_norm 2.3529 (1.8334)	
[2022-01-17 20:16:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][180/1251]	eta 0:41:10 lr 0.000558	time 2.5600 (2.3065)	loss 4.8058 (5.0152)	grad_norm 1.9846 (1.8287)	
[2022-01-17 20:17:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][190/1251]	eta 0:40:34 lr 0.000558	time 1.6594 (2.2948)	loss 5.3128 (5.0000)	grad_norm 1.4004 (1.8345)	
[2022-01-17 20:17:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][200/1251]	eta 0:40:03 lr 0.000558	time 2.2019 (2.2865)	loss 4.5258 (4.9975)	grad_norm 2.0706 (1.8336)	
[2022-01-17 20:17:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][210/1251]	eta 0:39:30 lr 0.000559	time 1.8580 (2.2767)	loss 4.7700 (4.9988)	grad_norm 1.5142 (1.8310)	
[2022-01-17 20:18:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][220/1251]	eta 0:38:58 lr 0.000559	time 2.8378 (2.2681)	loss 5.2763 (4.9932)	grad_norm 1.9429 (1.8407)	
[2022-01-17 20:18:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][230/1251]	eta 0:38:32 lr 0.000560	time 2.1569 (2.2646)	loss 5.8048 (5.0069)	grad_norm 1.8010 (1.8367)	
[2022-01-17 20:19:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][240/1251]	eta 0:38:08 lr 0.000560	time 2.5422 (2.2640)	loss 5.8228 (5.0146)	grad_norm 2.1778 (1.8440)	
[2022-01-17 20:19:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][250/1251]	eta 0:37:44 lr 0.000560	time 1.6923 (2.2625)	loss 5.0355 (5.0188)	grad_norm 2.0616 (1.8465)	
[2022-01-17 20:19:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][260/1251]	eta 0:37:27 lr 0.000561	time 3.3480 (2.2679)	loss 4.8162 (5.0161)	grad_norm 1.5701 (1.8503)	
[2022-01-17 20:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][270/1251]	eta 0:37:06 lr 0.000561	time 2.4305 (2.2694)	loss 4.2028 (5.0179)	grad_norm 1.4303 (1.8490)	
[2022-01-17 20:20:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][280/1251]	eta 0:36:34 lr 0.000562	time 1.8850 (2.2603)	loss 4.7620 (5.0159)	grad_norm 1.7654 (1.8447)	
[2022-01-17 20:20:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][290/1251]	eta 0:35:58 lr 0.000562	time 1.9151 (2.2465)	loss 5.1370 (5.0201)	grad_norm 1.7916 (1.8477)	
[2022-01-17 20:21:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][300/1251]	eta 0:35:26 lr 0.000562	time 1.8389 (2.2362)	loss 5.4785 (5.0135)	grad_norm 1.6077 (1.8458)	
[2022-01-17 20:21:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][310/1251]	eta 0:34:57 lr 0.000563	time 2.1531 (2.2288)	loss 5.5142 (5.0244)	grad_norm 1.8264 (1.8384)	
[2022-01-17 20:21:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][320/1251]	eta 0:34:33 lr 0.000563	time 1.8714 (2.2272)	loss 5.7032 (5.0277)	grad_norm 1.5527 (1.8299)	
[2022-01-17 20:22:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][330/1251]	eta 0:34:09 lr 0.000564	time 2.2845 (2.2248)	loss 4.6305 (5.0343)	grad_norm 1.7156 (1.8276)	
[2022-01-17 20:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][340/1251]	eta 0:33:44 lr 0.000564	time 1.8818 (2.2224)	loss 5.5230 (5.0330)	grad_norm 1.8057 (1.8283)	
[2022-01-17 20:22:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][350/1251]	eta 0:33:22 lr 0.000564	time 2.3071 (2.2221)	loss 4.1759 (5.0236)	grad_norm 2.0857 (1.8284)	
[2022-01-17 20:23:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][360/1251]	eta 0:33:04 lr 0.000565	time 2.3006 (2.2270)	loss 5.1659 (5.0219)	grad_norm 1.6729 (1.8279)	
[2022-01-17 20:23:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][370/1251]	eta 0:32:48 lr 0.000565	time 2.4337 (2.2339)	loss 4.6026 (5.0213)	grad_norm 1.4557 (1.8253)	
[2022-01-17 20:24:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][380/1251]	eta 0:32:25 lr 0.000566	time 1.8807 (2.2332)	loss 5.4785 (5.0227)	grad_norm 2.0475 (1.8267)	
[2022-01-17 20:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][390/1251]	eta 0:32:01 lr 0.000566	time 2.3371 (2.2316)	loss 5.4974 (5.0289)	grad_norm 1.6208 (1.8297)	
[2022-01-17 20:24:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][400/1251]	eta 0:31:38 lr 0.000566	time 1.6197 (2.2304)	loss 5.3745 (5.0291)	grad_norm 2.1453 (1.8317)	
[2022-01-17 20:25:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][410/1251]	eta 0:31:14 lr 0.000567	time 3.5283 (2.2289)	loss 5.3928 (5.0260)	grad_norm 2.3811 (1.8310)	
[2022-01-17 20:25:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][420/1251]	eta 0:30:48 lr 0.000567	time 2.0952 (2.2248)	loss 5.3464 (5.0228)	grad_norm 1.4246 (1.8269)	
[2022-01-17 20:25:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][430/1251]	eta 0:30:24 lr 0.000568	time 2.4701 (2.2227)	loss 5.5545 (5.0269)	grad_norm 2.0601 (1.8251)	
[2022-01-17 20:26:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][440/1251]	eta 0:30:02 lr 0.000568	time 2.2202 (2.2227)	loss 4.2339 (5.0288)	grad_norm 2.1499 (1.8264)	
[2022-01-17 20:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][450/1251]	eta 0:29:38 lr 0.000568	time 2.8024 (2.2209)	loss 4.7265 (5.0192)	grad_norm 1.3523 (1.8237)	
[2022-01-17 20:27:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][460/1251]	eta 0:29:17 lr 0.000569	time 2.5730 (2.2215)	loss 5.4001 (5.0169)	grad_norm 1.8415 (1.8250)	
[2022-01-17 20:27:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][470/1251]	eta 0:28:55 lr 0.000569	time 3.1052 (2.2216)	loss 5.6689 (5.0151)	grad_norm 1.6269 (1.8233)	
[2022-01-17 20:27:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][480/1251]	eta 0:28:32 lr 0.000570	time 2.1168 (2.2206)	loss 5.4935 (5.0160)	grad_norm 1.6274 (1.8232)	
[2022-01-17 20:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][490/1251]	eta 0:28:08 lr 0.000570	time 2.1976 (2.2194)	loss 5.5379 (5.0187)	grad_norm 1.8161 (1.8241)	
[2022-01-17 20:28:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][500/1251]	eta 0:27:44 lr 0.000570	time 1.7085 (2.2166)	loss 5.0248 (5.0161)	grad_norm 1.5370 (1.8226)	
[2022-01-17 20:28:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][510/1251]	eta 0:27:24 lr 0.000571	time 2.9855 (2.2195)	loss 5.3986 (5.0127)	grad_norm 1.6615 (1.8221)	
[2022-01-17 20:29:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][520/1251]	eta 0:27:03 lr 0.000571	time 2.8757 (2.2212)	loss 5.5003 (5.0106)	grad_norm 2.0240 (1.8220)	
[2022-01-17 20:29:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][530/1251]	eta 0:26:40 lr 0.000572	time 2.6168 (2.2197)	loss 4.8692 (5.0120)	grad_norm 1.7423 (1.8164)	
[2022-01-17 20:29:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][540/1251]	eta 0:26:15 lr 0.000572	time 1.6320 (2.2157)	loss 4.7437 (5.0118)	grad_norm 1.7441 (1.8115)	
[2022-01-17 20:30:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][550/1251]	eta 0:25:54 lr 0.000572	time 2.9119 (2.2178)	loss 5.2592 (5.0077)	grad_norm 1.7275 (1.8106)	
[2022-01-17 20:30:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][560/1251]	eta 0:25:32 lr 0.000573	time 2.1970 (2.2183)	loss 5.1533 (5.0095)	grad_norm 1.8183 (1.8113)	
[2022-01-17 20:31:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][570/1251]	eta 0:25:10 lr 0.000573	time 2.2370 (2.2174)	loss 5.1805 (5.0101)	grad_norm 2.0784 (1.8117)	
[2022-01-17 20:31:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][580/1251]	eta 0:24:46 lr 0.000574	time 1.4887 (2.2151)	loss 5.5223 (5.0097)	grad_norm 1.5315 (1.8119)	
[2022-01-17 20:31:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][590/1251]	eta 0:24:21 lr 0.000574	time 2.2332 (2.2111)	loss 5.3949 (5.0106)	grad_norm 1.7552 (1.8126)	
[2022-01-17 20:32:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][600/1251]	eta 0:23:58 lr 0.000574	time 1.5701 (2.2089)	loss 5.6219 (5.0091)	grad_norm 1.5864 (1.8138)	
[2022-01-17 20:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][610/1251]	eta 0:23:35 lr 0.000575	time 2.7680 (2.2081)	loss 4.7451 (5.0108)	grad_norm 1.9006 (1.8164)	
[2022-01-17 20:32:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][620/1251]	eta 0:23:12 lr 0.000575	time 2.3959 (2.2064)	loss 4.4924 (5.0110)	grad_norm 2.8447 (1.8165)	
[2022-01-17 20:33:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][630/1251]	eta 0:22:49 lr 0.000576	time 2.1245 (2.2047)	loss 5.4418 (5.0117)	grad_norm 1.8929 (1.8178)	
[2022-01-17 20:33:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][640/1251]	eta 0:22:25 lr 0.000576	time 1.7216 (2.2023)	loss 4.4732 (5.0142)	grad_norm 1.5509 (1.8149)	
[2022-01-17 20:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][650/1251]	eta 0:22:05 lr 0.000576	time 2.6323 (2.2060)	loss 5.4734 (5.0153)	grad_norm 1.5895 (1.8105)	
[2022-01-17 20:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][660/1251]	eta 0:21:42 lr 0.000577	time 2.1239 (2.2046)	loss 5.2880 (5.0127)	grad_norm 1.6238 (1.8111)	
[2022-01-17 20:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][670/1251]	eta 0:21:22 lr 0.000577	time 1.9680 (2.2076)	loss 4.6505 (5.0161)	grad_norm 1.5893 (1.8108)	
[2022-01-17 20:35:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][680/1251]	eta 0:21:01 lr 0.000578	time 1.6201 (2.2091)	loss 5.0954 (5.0150)	grad_norm 1.7321 (1.8116)	
[2022-01-17 20:35:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][690/1251]	eta 0:20:40 lr 0.000578	time 2.7899 (2.2116)	loss 5.2752 (5.0155)	grad_norm 1.2743 (1.8089)	
[2022-01-17 20:35:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][700/1251]	eta 0:20:17 lr 0.000578	time 1.9018 (2.2102)	loss 5.5323 (5.0172)	grad_norm 1.4157 (1.8082)	
[2022-01-17 20:36:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][710/1251]	eta 0:19:54 lr 0.000579	time 1.8698 (2.2089)	loss 5.5114 (5.0225)	grad_norm 1.9404 (1.8083)	
[2022-01-17 20:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][720/1251]	eta 0:19:31 lr 0.000579	time 1.5963 (2.2062)	loss 5.1895 (5.0224)	grad_norm 1.5454 (1.8061)	
[2022-01-17 20:36:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][730/1251]	eta 0:19:08 lr 0.000580	time 2.4369 (2.2041)	loss 5.9034 (5.0266)	grad_norm 1.4518 (1.8041)	
[2022-01-17 20:37:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][740/1251]	eta 0:18:46 lr 0.000580	time 2.1658 (2.2040)	loss 5.4352 (5.0261)	grad_norm 1.5677 (1.8019)	
[2022-01-17 20:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][750/1251]	eta 0:18:23 lr 0.000580	time 2.3433 (2.2033)	loss 5.1653 (5.0241)	grad_norm 1.3459 (1.8023)	
[2022-01-17 20:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][760/1251]	eta 0:18:02 lr 0.000581	time 2.0460 (2.2045)	loss 4.7687 (5.0264)	grad_norm 1.3987 (1.8022)	
[2022-01-17 20:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][770/1251]	eta 0:17:40 lr 0.000581	time 1.6436 (2.2041)	loss 5.4975 (5.0264)	grad_norm 1.4913 (1.8019)	
[2022-01-17 20:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][780/1251]	eta 0:17:18 lr 0.000582	time 2.4410 (2.2041)	loss 4.0251 (5.0250)	grad_norm 2.2780 (1.8017)	
[2022-01-17 20:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][790/1251]	eta 0:16:56 lr 0.000582	time 1.9388 (2.2044)	loss 5.4271 (5.0247)	grad_norm 2.6367 (1.8034)	
[2022-01-17 20:39:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][800/1251]	eta 0:16:34 lr 0.000582	time 1.9190 (2.2041)	loss 5.2430 (5.0260)	grad_norm 1.5488 (1.8023)	
[2022-01-17 20:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][810/1251]	eta 0:16:12 lr 0.000583	time 2.2158 (2.2044)	loss 4.6898 (5.0231)	grad_norm 2.0971 (1.8007)	
[2022-01-17 20:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][820/1251]	eta 0:15:49 lr 0.000583	time 1.8584 (2.2022)	loss 5.5972 (5.0237)	grad_norm 1.7556 (1.8004)	
[2022-01-17 20:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][830/1251]	eta 0:15:26 lr 0.000584	time 1.8480 (2.2000)	loss 5.8227 (5.0238)	grad_norm 1.9272 (1.8056)	
[2022-01-17 20:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][840/1251]	eta 0:15:03 lr 0.000584	time 1.9540 (2.1990)	loss 5.6593 (5.0246)	grad_norm 1.5297 (1.8041)	
[2022-01-17 20:41:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][850/1251]	eta 0:14:41 lr 0.000584	time 2.0784 (2.1987)	loss 5.2510 (5.0280)	grad_norm 1.3162 (1.8020)	
[2022-01-17 20:41:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][860/1251]	eta 0:14:19 lr 0.000585	time 2.4085 (2.1993)	loss 4.0801 (5.0286)	grad_norm 1.9889 (1.8000)	
[2022-01-17 20:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][870/1251]	eta 0:13:58 lr 0.000585	time 2.1278 (2.1997)	loss 4.6103 (5.0283)	grad_norm 1.9190 (1.7997)	
[2022-01-17 20:42:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][880/1251]	eta 0:13:36 lr 0.000586	time 2.3104 (2.1997)	loss 5.1475 (5.0239)	grad_norm 1.8159 (1.7991)	
[2022-01-17 20:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][890/1251]	eta 0:13:14 lr 0.000586	time 2.5302 (2.2006)	loss 4.3461 (5.0216)	grad_norm 1.6073 (1.7994)	
[2022-01-17 20:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][900/1251]	eta 0:12:52 lr 0.000586	time 2.8521 (2.2018)	loss 4.0830 (5.0226)	grad_norm 1.7150 (1.8000)	
[2022-01-17 20:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][910/1251]	eta 0:12:30 lr 0.000587	time 1.4777 (2.2001)	loss 5.5411 (5.0209)	grad_norm 1.4570 (1.7992)	
[2022-01-17 20:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][920/1251]	eta 0:12:07 lr 0.000587	time 2.1079 (2.1985)	loss 5.1542 (5.0174)	grad_norm 2.2001 (1.8027)	
[2022-01-17 20:44:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][930/1251]	eta 0:11:45 lr 0.000588	time 1.6087 (2.1972)	loss 4.2056 (5.0148)	grad_norm 1.7200 (1.8015)	
[2022-01-17 20:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][940/1251]	eta 0:11:22 lr 0.000588	time 1.8492 (2.1952)	loss 5.4781 (5.0102)	grad_norm 1.5861 (1.8018)	
[2022-01-17 20:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][950/1251]	eta 0:11:00 lr 0.000588	time 1.5430 (2.1929)	loss 4.9880 (5.0088)	grad_norm 1.6852 (1.8021)	
[2022-01-17 20:45:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][960/1251]	eta 0:10:37 lr 0.000589	time 1.8329 (2.1923)	loss 4.0395 (5.0054)	grad_norm 1.5104 (1.8020)	
[2022-01-17 20:45:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][970/1251]	eta 0:10:16 lr 0.000589	time 2.1120 (2.1924)	loss 5.2278 (5.0058)	grad_norm 2.3357 (1.8036)	
[2022-01-17 20:45:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][980/1251]	eta 0:09:54 lr 0.000590	time 2.2951 (2.1938)	loss 4.3957 (5.0054)	grad_norm 1.7219 (1.8022)	
[2022-01-17 20:46:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][990/1251]	eta 0:09:33 lr 0.000590	time 2.8285 (2.1964)	loss 4.9045 (5.0050)	grad_norm 2.0119 (1.8013)	
[2022-01-17 20:46:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1000/1251]	eta 0:09:11 lr 0.000590	time 1.8387 (2.1964)	loss 5.1034 (5.0027)	grad_norm 2.1508 (1.8015)	
[2022-01-17 20:46:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1010/1251]	eta 0:08:49 lr 0.000591	time 2.4234 (2.1962)	loss 3.7496 (4.9996)	grad_norm 1.9764 (1.8018)	
[2022-01-17 20:47:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1020/1251]	eta 0:08:26 lr 0.000591	time 1.9126 (2.1943)	loss 5.3450 (4.9977)	grad_norm 1.5745 (1.8020)	
[2022-01-17 20:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1030/1251]	eta 0:08:04 lr 0.000592	time 2.4028 (2.1943)	loss 5.4795 (4.9996)	grad_norm 1.6980 (1.8000)	
[2022-01-17 20:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1040/1251]	eta 0:07:43 lr 0.000592	time 1.4975 (2.1956)	loss 5.0285 (5.0002)	grad_norm 1.9895 (1.7991)	
[2022-01-17 20:48:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1050/1251]	eta 0:07:21 lr 0.000592	time 2.4216 (2.1972)	loss 4.6927 (4.9994)	grad_norm 3.3980 (1.7996)	
[2022-01-17 20:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1060/1251]	eta 0:06:59 lr 0.000593	time 2.2324 (2.1977)	loss 3.9505 (4.9968)	grad_norm 1.6302 (1.8000)	
[2022-01-17 20:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1070/1251]	eta 0:06:37 lr 0.000593	time 3.1191 (2.1988)	loss 3.9214 (4.9956)	grad_norm 1.9748 (1.7999)	
[2022-01-17 20:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1080/1251]	eta 0:06:15 lr 0.000594	time 1.9080 (2.1967)	loss 4.7031 (4.9970)	grad_norm 2.2418 (1.7996)	
[2022-01-17 20:49:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1090/1251]	eta 0:05:53 lr 0.000594	time 1.7278 (2.1937)	loss 4.5325 (4.9976)	grad_norm 2.4121 (1.7986)	
[2022-01-17 20:50:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1100/1251]	eta 0:05:31 lr 0.000594	time 1.5899 (2.1923)	loss 5.6618 (4.9979)	grad_norm 1.9672 (1.7984)	
[2022-01-17 20:50:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1110/1251]	eta 0:05:09 lr 0.000595	time 2.8111 (2.1917)	loss 4.7507 (4.9975)	grad_norm 1.4382 (1.7977)	
[2022-01-17 20:50:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1120/1251]	eta 0:04:47 lr 0.000595	time 1.9559 (2.1909)	loss 5.6679 (4.9980)	grad_norm 1.3732 (1.7964)	
[2022-01-17 20:51:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1130/1251]	eta 0:04:25 lr 0.000596	time 2.4983 (2.1917)	loss 5.5068 (4.9986)	grad_norm 1.8462 (1.7957)	
[2022-01-17 20:51:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1140/1251]	eta 0:04:03 lr 0.000596	time 2.6725 (2.1918)	loss 4.0395 (4.9969)	grad_norm 1.2241 (1.7939)	
[2022-01-17 20:52:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1150/1251]	eta 0:03:41 lr 0.000596	time 2.1074 (2.1924)	loss 5.2818 (4.9978)	grad_norm 1.5191 (1.7921)	
[2022-01-17 20:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1160/1251]	eta 0:03:19 lr 0.000597	time 2.7791 (2.1945)	loss 5.1727 (4.9988)	grad_norm 1.8068 (1.7922)	
[2022-01-17 20:52:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1170/1251]	eta 0:02:57 lr 0.000597	time 2.0200 (2.1947)	loss 4.7047 (4.9960)	grad_norm 1.4664 (1.7923)	
[2022-01-17 20:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1180/1251]	eta 0:02:35 lr 0.000598	time 1.5149 (2.1952)	loss 4.3357 (4.9969)	grad_norm 1.3188 (1.7913)	
[2022-01-17 20:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1190/1251]	eta 0:02:13 lr 0.000598	time 1.9718 (2.1952)	loss 5.8207 (4.9978)	grad_norm 1.4482 (1.7921)	
[2022-01-17 20:53:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1200/1251]	eta 0:01:51 lr 0.000598	time 2.8999 (2.1942)	loss 4.7735 (4.9973)	grad_norm 1.4800 (1.7914)	
[2022-01-17 20:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1210/1251]	eta 0:01:29 lr 0.000599	time 1.9520 (2.1923)	loss 3.9405 (4.9959)	grad_norm 1.6771 (1.7914)	
[2022-01-17 20:54:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1220/1251]	eta 0:01:07 lr 0.000599	time 1.8342 (2.1925)	loss 5.4783 (4.9957)	grad_norm 1.5555 (1.7921)	
[2022-01-17 20:54:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1230/1251]	eta 0:00:46 lr 0.000600	time 2.2494 (2.1921)	loss 5.3947 (4.9959)	grad_norm 1.6010 (1.7921)	
[2022-01-17 20:55:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1240/1251]	eta 0:00:24 lr 0.000600	time 2.3976 (2.1925)	loss 5.1842 (4.9969)	grad_norm 1.4775 (1.7922)	
[2022-01-17 20:55:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [11/300][1250/1251]	eta 0:00:02 lr 0.000600	time 1.1377 (2.1874)	loss 5.1650 (4.9971)	grad_norm 1.5394 (1.7905)	
[2022-01-17 20:55:34 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 11 training takes 0:45:36
[2022-01-17 20:55:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.925 (18.925)	Loss 2.3702 (2.3702)	Acc@1 47.754 (47.754)	Acc@5 73.145 (73.145)	
[2022-01-17 20:56:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.143 (3.374)	Loss 2.3520 (2.3711)	Acc@1 49.609 (49.237)	Acc@5 74.219 (74.299)	
[2022-01-17 20:56:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.599 (2.556)	Loss 2.3591 (2.3635)	Acc@1 50.000 (49.042)	Acc@5 73.828 (74.484)	
[2022-01-17 20:56:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.237 (2.313)	Loss 2.5057 (2.3594)	Acc@1 46.582 (49.017)	Acc@5 70.605 (74.414)	
[2022-01-17 20:57:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.152 (2.204)	Loss 2.3418 (2.3656)	Acc@1 47.656 (48.778)	Acc@5 75.195 (74.271)	
[2022-01-17 20:57:12 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 48.850 Acc@5 74.352
[2022-01-17 20:57:12 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 48.8%
[2022-01-17 20:57:12 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 48.85%
[2022-01-17 20:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][0/1251]	eta 7:37:58 lr 0.000600	time 21.9653 (21.9653)	loss 5.8233 (5.8233)	grad_norm 1.7651 (1.7651)	
[2022-01-17 20:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][10/1251]	eta 1:23:46 lr 0.000601	time 2.1429 (4.0507)	loss 4.5824 (4.7987)	grad_norm 1.6522 (1.7366)	
[2022-01-17 20:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][20/1251]	eta 1:04:26 lr 0.000601	time 1.5378 (3.1406)	loss 4.9947 (4.8290)	grad_norm 1.8291 (1.7127)	
[2022-01-17 20:58:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][30/1251]	eta 0:57:40 lr 0.000602	time 1.7514 (2.8337)	loss 5.5359 (4.8975)	grad_norm 2.3178 (1.7544)	
[2022-01-17 20:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][40/1251]	eta 0:55:19 lr 0.000602	time 3.5920 (2.7414)	loss 5.6649 (4.8667)	grad_norm 1.7018 (1.7699)	
[2022-01-17 20:59:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][50/1251]	eta 0:54:57 lr 0.000602	time 2.8166 (2.7460)	loss 5.0611 (4.8461)	grad_norm 2.4435 (1.7907)	
[2022-01-17 20:59:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][60/1251]	eta 0:52:33 lr 0.000603	time 1.9155 (2.6476)	loss 5.4128 (4.8199)	grad_norm 1.8152 (1.7928)	
[2022-01-17 21:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][70/1251]	eta 0:51:01 lr 0.000603	time 1.7214 (2.5922)	loss 5.1393 (4.8603)	grad_norm 1.9557 (1.7805)	
[2022-01-17 21:00:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][80/1251]	eta 0:49:16 lr 0.000604	time 1.9929 (2.5251)	loss 5.4213 (4.8721)	grad_norm 1.7167 (1.7826)	
[2022-01-17 21:01:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][90/1251]	eta 0:48:30 lr 0.000604	time 1.9234 (2.5069)	loss 5.4164 (4.8732)	grad_norm 1.8729 (1.7980)	
[2022-01-17 21:01:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][100/1251]	eta 0:47:08 lr 0.000604	time 1.6166 (2.4578)	loss 4.7028 (4.8851)	grad_norm 1.4103 (1.7845)	
[2022-01-17 21:01:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][110/1251]	eta 0:46:11 lr 0.000605	time 1.5528 (2.4293)	loss 5.2979 (4.9026)	grad_norm 1.3293 (1.7729)	
[2022-01-17 21:02:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][120/1251]	eta 0:45:19 lr 0.000605	time 1.9571 (2.4042)	loss 4.9536 (4.8900)	grad_norm 1.8003 (1.7704)	
[2022-01-17 21:02:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][130/1251]	eta 0:44:45 lr 0.000606	time 2.2245 (2.3959)	loss 4.8863 (4.9027)	grad_norm 2.3675 (1.7622)	
[2022-01-17 21:02:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][140/1251]	eta 0:43:53 lr 0.000606	time 2.0325 (2.3701)	loss 5.2227 (4.9313)	grad_norm 1.6021 (1.7584)	
[2022-01-17 21:03:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][150/1251]	eta 0:43:15 lr 0.000606	time 2.1559 (2.3576)	loss 4.8228 (4.9251)	grad_norm 1.4314 (1.7564)	
[2022-01-17 21:03:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][160/1251]	eta 0:42:38 lr 0.000607	time 1.9733 (2.3448)	loss 5.1732 (4.9237)	grad_norm 1.7767 (1.7557)	
[2022-01-17 21:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][170/1251]	eta 0:42:17 lr 0.000607	time 2.5189 (2.3475)	loss 4.8124 (4.9344)	grad_norm 1.5441 (1.7541)	
[2022-01-17 21:04:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][180/1251]	eta 0:41:47 lr 0.000608	time 2.2142 (2.3414)	loss 4.1026 (4.9257)	grad_norm 2.0489 (1.7525)	
[2022-01-17 21:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][190/1251]	eta 0:41:12 lr 0.000608	time 1.9005 (2.3306)	loss 4.5916 (4.9212)	grad_norm 1.7231 (1.7497)	
[2022-01-17 21:04:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][200/1251]	eta 0:40:32 lr 0.000608	time 1.6747 (2.3149)	loss 5.1727 (4.9241)	grad_norm 1.3700 (1.7583)	
[2022-01-17 21:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][210/1251]	eta 0:40:19 lr 0.000609	time 1.9165 (2.3244)	loss 5.0642 (4.9245)	grad_norm 1.6396 (1.7534)	
[2022-01-17 21:05:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][220/1251]	eta 0:39:43 lr 0.000609	time 1.6095 (2.3119)	loss 5.2940 (4.9268)	grad_norm 1.5740 (1.7586)	
[2022-01-17 21:06:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][230/1251]	eta 0:39:10 lr 0.000610	time 2.3192 (2.3017)	loss 3.9966 (4.9222)	grad_norm 1.9316 (1.7523)	
[2022-01-17 21:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][240/1251]	eta 0:38:36 lr 0.000610	time 1.5969 (2.2915)	loss 4.0155 (4.9296)	grad_norm 1.4019 (1.7438)	
[2022-01-17 21:06:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][250/1251]	eta 0:38:20 lr 0.000610	time 2.0236 (2.2979)	loss 5.1954 (4.9273)	grad_norm 1.6053 (1.7381)	
[2022-01-17 21:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][260/1251]	eta 0:37:49 lr 0.000611	time 2.2463 (2.2906)	loss 5.3214 (4.9272)	grad_norm 3.0237 (1.7422)	
[2022-01-17 21:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][270/1251]	eta 0:37:25 lr 0.000611	time 1.9008 (2.2887)	loss 5.3473 (4.9347)	grad_norm 1.8986 (1.7445)	
[2022-01-17 21:07:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][280/1251]	eta 0:36:58 lr 0.000612	time 1.8317 (2.2843)	loss 5.7517 (4.9366)	grad_norm 1.4124 (1.7451)	
[2022-01-17 21:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][290/1251]	eta 0:36:37 lr 0.000612	time 2.8802 (2.2862)	loss 4.3106 (4.9336)	grad_norm 1.5729 (1.7495)	
[2022-01-17 21:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][300/1251]	eta 0:36:09 lr 0.000612	time 2.3643 (2.2817)	loss 5.2522 (4.9315)	grad_norm 1.7712 (1.7503)	
[2022-01-17 21:08:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][310/1251]	eta 0:35:37 lr 0.000613	time 2.2060 (2.2717)	loss 5.1338 (4.9248)	grad_norm 1.6232 (1.7578)	
[2022-01-17 21:09:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][320/1251]	eta 0:35:07 lr 0.000613	time 1.7615 (2.2636)	loss 5.2130 (4.9159)	grad_norm 1.9197 (1.7515)	
[2022-01-17 21:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][330/1251]	eta 0:34:37 lr 0.000614	time 1.4609 (2.2556)	loss 5.3101 (4.9156)	grad_norm 1.5664 (1.7525)	
[2022-01-17 21:10:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][340/1251]	eta 0:34:12 lr 0.000614	time 2.2226 (2.2525)	loss 5.4586 (4.9188)	grad_norm 1.8929 (1.7486)	
[2022-01-17 21:10:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][350/1251]	eta 0:33:44 lr 0.000614	time 2.0985 (2.2469)	loss 4.8596 (4.9214)	grad_norm 1.4411 (1.7440)	
[2022-01-17 21:10:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][360/1251]	eta 0:33:18 lr 0.000615	time 2.0296 (2.2427)	loss 4.7910 (4.9283)	grad_norm 1.6994 (1.7466)	
[2022-01-17 21:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][370/1251]	eta 0:32:54 lr 0.000615	time 1.5883 (2.2417)	loss 4.9925 (4.9307)	grad_norm 2.2944 (1.7484)	
[2022-01-17 21:11:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][380/1251]	eta 0:32:36 lr 0.000616	time 3.3814 (2.2463)	loss 3.9776 (4.9181)	grad_norm 1.6251 (1.7487)	
[2022-01-17 21:11:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][390/1251]	eta 0:32:14 lr 0.000616	time 1.7361 (2.2464)	loss 5.7065 (4.9184)	grad_norm 1.7988 (1.7469)	
[2022-01-17 21:12:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][400/1251]	eta 0:31:47 lr 0.000616	time 1.8352 (2.2419)	loss 5.1652 (4.9210)	grad_norm 1.6089 (1.7458)	
[2022-01-17 21:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][410/1251]	eta 0:31:26 lr 0.000617	time 1.6256 (2.2433)	loss 4.6263 (4.9210)	grad_norm 1.8823 (1.7449)	
[2022-01-17 21:12:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][420/1251]	eta 0:31:03 lr 0.000617	time 2.6950 (2.2427)	loss 3.8730 (4.9133)	grad_norm 2.8152 (1.7489)	
[2022-01-17 21:13:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][430/1251]	eta 0:30:43 lr 0.000618	time 2.6112 (2.2457)	loss 4.7135 (4.9139)	grad_norm 1.5768 (1.7522)	
[2022-01-17 21:13:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][440/1251]	eta 0:30:19 lr 0.000618	time 1.5684 (2.2438)	loss 4.0728 (4.9142)	grad_norm 2.2395 (1.7532)	
[2022-01-17 21:14:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][450/1251]	eta 0:29:56 lr 0.000618	time 2.5033 (2.2428)	loss 4.6419 (4.9125)	grad_norm 1.4324 (1.7494)	
[2022-01-17 21:14:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][460/1251]	eta 0:29:31 lr 0.000619	time 1.8899 (2.2394)	loss 5.5697 (4.9059)	grad_norm 1.8197 (1.7502)	
[2022-01-17 21:14:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][470/1251]	eta 0:29:09 lr 0.000619	time 2.2362 (2.2398)	loss 4.7907 (4.9062)	grad_norm 1.5703 (1.7451)	
[2022-01-17 21:15:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][480/1251]	eta 0:28:44 lr 0.000620	time 1.9927 (2.2366)	loss 5.5174 (4.9133)	grad_norm 2.1136 (1.7443)	
[2022-01-17 21:15:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][490/1251]	eta 0:28:21 lr 0.000620	time 2.4110 (2.2360)	loss 5.3828 (4.9122)	grad_norm 1.4541 (1.7458)	
[2022-01-17 21:15:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][500/1251]	eta 0:27:57 lr 0.000620	time 1.8497 (2.2340)	loss 5.7959 (4.9104)	grad_norm 1.8546 (1.7456)	
[2022-01-17 21:16:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][510/1251]	eta 0:27:34 lr 0.000621	time 1.9130 (2.2325)	loss 4.8052 (4.9162)	grad_norm 2.4167 (1.7480)	
[2022-01-17 21:16:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][520/1251]	eta 0:27:10 lr 0.000621	time 1.9096 (2.2302)	loss 4.5266 (4.9144)	grad_norm 1.5110 (1.7454)	
[2022-01-17 21:16:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][530/1251]	eta 0:26:47 lr 0.000622	time 2.3059 (2.2294)	loss 5.2598 (4.9162)	grad_norm 1.6878 (1.7461)	
[2022-01-17 21:17:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][540/1251]	eta 0:26:24 lr 0.000622	time 2.5509 (2.2281)	loss 4.9531 (4.9165)	grad_norm 1.8849 (1.7433)	
[2022-01-17 21:17:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][550/1251]	eta 0:26:02 lr 0.000622	time 1.6017 (2.2287)	loss 5.1919 (4.9185)	grad_norm 1.3409 (1.7415)	
[2022-01-17 21:18:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][560/1251]	eta 0:25:38 lr 0.000623	time 1.9606 (2.2263)	loss 5.5335 (4.9222)	grad_norm 1.4764 (1.7382)	
[2022-01-17 21:18:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][570/1251]	eta 0:25:15 lr 0.000623	time 2.2154 (2.2258)	loss 4.3901 (4.9208)	grad_norm 1.6120 (1.7351)	
[2022-01-17 21:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][580/1251]	eta 0:24:53 lr 0.000624	time 2.0349 (2.2262)	loss 4.3468 (4.9185)	grad_norm 1.7892 (1.7344)	
[2022-01-17 21:19:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][590/1251]	eta 0:24:32 lr 0.000624	time 2.1139 (2.2279)	loss 5.1411 (4.9163)	grad_norm 1.5064 (1.7343)	
[2022-01-17 21:19:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][600/1251]	eta 0:24:09 lr 0.000624	time 1.5878 (2.2258)	loss 5.2778 (4.9187)	grad_norm 1.5809 (1.7326)	
[2022-01-17 21:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][610/1251]	eta 0:23:45 lr 0.000625	time 1.9995 (2.2244)	loss 5.0939 (4.9212)	grad_norm 1.9628 (1.7325)	
[2022-01-17 21:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][620/1251]	eta 0:23:22 lr 0.000625	time 2.0030 (2.2227)	loss 4.9208 (4.9232)	grad_norm 1.7788 (1.7307)	
[2022-01-17 21:20:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][630/1251]	eta 0:22:59 lr 0.000626	time 2.1231 (2.2212)	loss 4.4169 (4.9209)	grad_norm 1.3021 (1.7276)	
[2022-01-17 21:20:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][640/1251]	eta 0:22:36 lr 0.000626	time 2.2802 (2.2202)	loss 4.6614 (4.9173)	grad_norm 1.8733 (1.7275)	
[2022-01-17 21:21:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][650/1251]	eta 0:22:13 lr 0.000626	time 1.9295 (2.2192)	loss 3.8921 (4.9190)	grad_norm 1.3228 (1.7261)	
[2022-01-17 21:21:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][660/1251]	eta 0:21:53 lr 0.000627	time 2.1894 (2.2220)	loss 5.3372 (4.9191)	grad_norm 1.6791 (1.7290)	
[2022-01-17 21:22:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][670/1251]	eta 0:21:34 lr 0.000627	time 3.2095 (2.2275)	loss 5.2492 (4.9176)	grad_norm 1.3035 (1.7276)	
[2022-01-17 21:22:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][680/1251]	eta 0:21:11 lr 0.000628	time 1.6622 (2.2262)	loss 5.5922 (4.9155)	grad_norm 1.5821 (1.7274)	
[2022-01-17 21:22:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][690/1251]	eta 0:20:47 lr 0.000628	time 1.6179 (2.2242)	loss 5.4937 (4.9166)	grad_norm 1.3383 (1.7240)	
[2022-01-17 21:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][700/1251]	eta 0:20:24 lr 0.000628	time 2.0262 (2.2221)	loss 4.9034 (4.9167)	grad_norm 1.5119 (1.7204)	
[2022-01-17 21:23:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][710/1251]	eta 0:20:00 lr 0.000629	time 2.1868 (2.2194)	loss 4.9214 (4.9171)	grad_norm 1.3999 (1.7198)	
[2022-01-17 21:23:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][720/1251]	eta 0:19:38 lr 0.000629	time 2.7430 (2.2194)	loss 5.5206 (4.9177)	grad_norm 1.4290 (1.7187)	
[2022-01-17 21:24:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][730/1251]	eta 0:19:16 lr 0.000630	time 2.5729 (2.2201)	loss 5.2697 (4.9170)	grad_norm 1.5183 (1.7180)	
[2022-01-17 21:24:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][740/1251]	eta 0:18:54 lr 0.000630	time 2.4849 (2.2199)	loss 5.3562 (4.9176)	grad_norm 1.6115 (1.7156)	
[2022-01-17 21:24:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][750/1251]	eta 0:18:32 lr 0.000630	time 1.9493 (2.2197)	loss 4.9075 (4.9177)	grad_norm 2.4522 (1.7182)	
[2022-01-17 21:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][760/1251]	eta 0:18:09 lr 0.000631	time 2.4187 (2.2192)	loss 4.8775 (4.9166)	grad_norm 1.5779 (1.7199)	
[2022-01-17 21:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][770/1251]	eta 0:17:46 lr 0.000631	time 1.9531 (2.2175)	loss 4.3040 (4.9143)	grad_norm 2.2366 (1.7234)	
[2022-01-17 21:26:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][780/1251]	eta 0:17:23 lr 0.000632	time 2.2826 (2.2152)	loss 5.5227 (4.9160)	grad_norm 1.8026 (1.7226)	
[2022-01-17 21:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][790/1251]	eta 0:17:00 lr 0.000632	time 2.1487 (2.2136)	loss 4.8808 (4.9170)	grad_norm 1.4905 (1.7215)	
[2022-01-17 21:26:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][800/1251]	eta 0:16:38 lr 0.000632	time 2.2511 (2.2130)	loss 4.1215 (4.9137)	grad_norm 1.4322 (1.7227)	
[2022-01-17 21:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][810/1251]	eta 0:16:16 lr 0.000633	time 2.1422 (2.2143)	loss 5.6413 (4.9171)	grad_norm 1.6577 (1.7228)	
[2022-01-17 21:27:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][820/1251]	eta 0:15:55 lr 0.000633	time 3.2076 (2.2170)	loss 5.7096 (4.9198)	grad_norm 1.6298 (1.7258)	
[2022-01-17 21:27:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][830/1251]	eta 0:15:34 lr 0.000634	time 3.6064 (2.2193)	loss 5.3044 (4.9214)	grad_norm 1.5534 (1.7270)	
[2022-01-17 21:28:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][840/1251]	eta 0:15:12 lr 0.000634	time 1.8339 (2.2194)	loss 4.0042 (4.9186)	grad_norm 1.4509 (1.7264)	
[2022-01-17 21:28:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][850/1251]	eta 0:14:48 lr 0.000634	time 1.8176 (2.2169)	loss 4.9133 (4.9206)	grad_norm 1.7707 (1.7275)	
[2022-01-17 21:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][860/1251]	eta 0:14:25 lr 0.000635	time 2.2763 (2.2138)	loss 4.2922 (4.9210)	grad_norm 1.4336 (1.7261)	
[2022-01-17 21:29:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][870/1251]	eta 0:14:02 lr 0.000635	time 2.0106 (2.2113)	loss 4.5260 (4.9239)	grad_norm 1.7380 (1.7255)	
[2022-01-17 21:29:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][880/1251]	eta 0:13:39 lr 0.000636	time 2.5609 (2.2097)	loss 5.3798 (4.9256)	grad_norm 1.4193 (1.7243)	
[2022-01-17 21:30:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][890/1251]	eta 0:13:18 lr 0.000636	time 3.2482 (2.2112)	loss 3.8230 (4.9234)	grad_norm 1.5262 (1.7217)	
[2022-01-17 21:30:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][900/1251]	eta 0:12:56 lr 0.000636	time 2.1948 (2.2120)	loss 5.2135 (4.9221)	grad_norm 1.5703 (1.7221)	
[2022-01-17 21:30:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][910/1251]	eta 0:12:34 lr 0.000637	time 1.2604 (2.2118)	loss 5.5421 (4.9199)	grad_norm 1.4571 (1.7193)	
[2022-01-17 21:31:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][920/1251]	eta 0:12:11 lr 0.000637	time 1.4571 (2.2112)	loss 4.4169 (4.9136)	grad_norm 1.5971 (1.7180)	
[2022-01-17 21:31:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][930/1251]	eta 0:11:50 lr 0.000638	time 2.7601 (2.2131)	loss 5.3899 (4.9143)	grad_norm 1.4459 (1.7174)	
[2022-01-17 21:31:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][940/1251]	eta 0:11:28 lr 0.000638	time 1.9316 (2.2131)	loss 4.9425 (4.9125)	grad_norm 1.9588 (1.7191)	
[2022-01-17 21:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][950/1251]	eta 0:11:06 lr 0.000638	time 1.8384 (2.2149)	loss 5.6849 (4.9131)	grad_norm 2.1994 (1.7194)	
[2022-01-17 21:32:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][960/1251]	eta 0:10:44 lr 0.000639	time 1.9716 (2.2133)	loss 5.3461 (4.9118)	grad_norm 1.7945 (1.7204)	
[2022-01-17 21:33:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][970/1251]	eta 0:10:21 lr 0.000639	time 2.6273 (2.2120)	loss 4.3009 (4.9105)	grad_norm 2.1487 (1.7230)	
[2022-01-17 21:33:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][980/1251]	eta 0:09:58 lr 0.000640	time 1.9271 (2.2096)	loss 5.0925 (4.9085)	grad_norm 1.8430 (1.7230)	
[2022-01-17 21:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][990/1251]	eta 0:09:36 lr 0.000640	time 2.3715 (2.2076)	loss 5.3193 (4.9108)	grad_norm 1.6918 (1.7225)	
[2022-01-17 21:34:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1000/1251]	eta 0:09:14 lr 0.000640	time 2.5313 (2.2073)	loss 4.8947 (4.9085)	grad_norm 1.5705 (1.7226)	
[2022-01-17 21:34:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1010/1251]	eta 0:08:52 lr 0.000641	time 2.0978 (2.2082)	loss 3.9359 (4.9084)	grad_norm 1.5675 (1.7202)	
[2022-01-17 21:34:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1020/1251]	eta 0:08:30 lr 0.000641	time 2.5865 (2.2081)	loss 5.4479 (4.9076)	grad_norm 1.5607 (1.7188)	
[2022-01-17 21:35:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1030/1251]	eta 0:08:08 lr 0.000642	time 2.8984 (2.2088)	loss 4.6147 (4.9080)	grad_norm 1.6403 (1.7173)	
[2022-01-17 21:35:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1040/1251]	eta 0:07:46 lr 0.000642	time 1.9266 (2.2100)	loss 4.2632 (4.9073)	grad_norm 1.5816 (1.7164)	
[2022-01-17 21:35:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1050/1251]	eta 0:07:24 lr 0.000642	time 1.7939 (2.2100)	loss 5.5411 (4.9065)	grad_norm 1.6602 (1.7162)	
[2022-01-17 21:36:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1060/1251]	eta 0:07:02 lr 0.000643	time 2.7769 (2.2105)	loss 5.3449 (4.9073)	grad_norm 2.1830 (1.7165)	
[2022-01-17 21:36:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1070/1251]	eta 0:06:39 lr 0.000643	time 1.7683 (2.2087)	loss 5.6387 (4.9091)	grad_norm 1.3045 (1.7164)	
[2022-01-17 21:36:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1080/1251]	eta 0:06:17 lr 0.000644	time 2.0350 (2.2073)	loss 4.0079 (4.9079)	grad_norm 1.8019 (1.7154)	
[2022-01-17 21:37:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1090/1251]	eta 0:05:55 lr 0.000644	time 2.1865 (2.2079)	loss 5.2117 (4.9054)	grad_norm 1.5691 (1.7159)	
[2022-01-17 21:37:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1100/1251]	eta 0:05:33 lr 0.000644	time 3.0334 (2.2096)	loss 4.6569 (4.9048)	grad_norm 1.4170 (1.7141)	
[2022-01-17 21:38:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1110/1251]	eta 0:05:11 lr 0.000645	time 2.6733 (2.2104)	loss 3.7992 (4.9045)	grad_norm 2.6436 (1.7132)	
[2022-01-17 21:38:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1120/1251]	eta 0:04:49 lr 0.000645	time 1.9029 (2.2092)	loss 4.4586 (4.9033)	grad_norm 1.5772 (1.7148)	
[2022-01-17 21:38:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1130/1251]	eta 0:04:26 lr 0.000646	time 1.7868 (2.2066)	loss 4.3464 (4.9055)	grad_norm 2.0362 (1.7159)	
[2022-01-17 21:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1140/1251]	eta 0:04:04 lr 0.000646	time 1.8264 (2.2056)	loss 4.0554 (4.9065)	grad_norm 1.7191 (1.7165)	
[2022-01-17 21:39:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1150/1251]	eta 0:03:42 lr 0.000646	time 2.5726 (2.2046)	loss 4.1600 (4.9062)	grad_norm 1.5205 (1.7138)	
[2022-01-17 21:39:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1160/1251]	eta 0:03:20 lr 0.000647	time 1.6749 (2.2047)	loss 4.9247 (4.9049)	grad_norm 1.8223 (1.7134)	
[2022-01-17 21:40:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1170/1251]	eta 0:02:58 lr 0.000647	time 2.5809 (2.2057)	loss 4.6940 (4.9016)	grad_norm 2.1207 (1.7141)	
[2022-01-17 21:40:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1180/1251]	eta 0:02:36 lr 0.000648	time 1.5445 (2.2060)	loss 5.1544 (4.9022)	grad_norm 1.2579 (1.7131)	
[2022-01-17 21:41:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1190/1251]	eta 0:02:14 lr 0.000648	time 2.7396 (2.2071)	loss 5.5959 (4.9042)	grad_norm 1.4800 (1.7117)	
[2022-01-17 21:41:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1200/1251]	eta 0:01:52 lr 0.000648	time 2.2512 (2.2083)	loss 4.0195 (4.9047)	grad_norm 1.5651 (1.7126)	
[2022-01-17 21:41:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1210/1251]	eta 0:01:30 lr 0.000649	time 2.1543 (2.2090)	loss 5.2395 (4.9038)	grad_norm 1.6019 (1.7113)	
[2022-01-17 21:42:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1220/1251]	eta 0:01:08 lr 0.000649	time 1.9094 (2.2082)	loss 5.1103 (4.9043)	grad_norm 1.3456 (1.7100)	
[2022-01-17 21:42:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1230/1251]	eta 0:00:46 lr 0.000650	time 1.9346 (2.2066)	loss 4.5565 (4.9016)	grad_norm 1.7696 (1.7083)	
[2022-01-17 21:42:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1240/1251]	eta 0:00:24 lr 0.000650	time 2.1056 (2.2053)	loss 4.2257 (4.9016)	grad_norm 1.5638 (1.7080)	
[2022-01-17 21:43:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [12/300][1250/1251]	eta 0:00:02 lr 0.000650	time 1.3623 (2.2000)	loss 5.0979 (4.9017)	grad_norm 1.6644 (1.7082)	
[2022-01-17 21:43:05 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 12 training takes 0:45:52
[2022-01-17 21:43:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.738 (18.738)	Loss 2.3526 (2.3526)	Acc@1 48.926 (48.926)	Acc@5 75.195 (75.195)	
[2022-01-17 21:43:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.256 (3.291)	Loss 2.2856 (2.2948)	Acc@1 50.098 (50.550)	Acc@5 76.660 (75.755)	
[2022-01-17 21:44:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.299 (2.643)	Loss 2.3534 (2.2768)	Acc@1 50.488 (50.781)	Acc@5 73.535 (75.730)	
[2022-01-17 21:44:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.312 (2.206)	Loss 2.2246 (2.2762)	Acc@1 51.953 (50.643)	Acc@5 77.051 (75.892)	
[2022-01-17 21:44:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.864 (2.148)	Loss 2.2886 (2.2795)	Acc@1 50.879 (50.638)	Acc@5 75.977 (75.793)	
[2022-01-17 21:44:40 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 50.770 Acc@5 75.810
[2022-01-17 21:44:40 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 50.8%
[2022-01-17 21:44:40 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 50.77%
[2022-01-17 21:45:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][0/1251]	eta 7:30:31 lr 0.000650	time 21.6079 (21.6079)	loss 3.4350 (3.4350)	grad_norm 1.7505 (1.7505)	
[2022-01-17 21:45:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][10/1251]	eta 1:20:14 lr 0.000651	time 1.4500 (3.8795)	loss 3.8366 (4.5579)	grad_norm 1.5426 (1.6614)	
[2022-01-17 21:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][20/1251]	eta 1:03:51 lr 0.000651	time 2.4017 (3.1128)	loss 5.4153 (4.7367)	grad_norm 1.6530 (1.7188)	
[2022-01-17 21:46:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][30/1251]	eta 0:56:51 lr 0.000652	time 1.4726 (2.7936)	loss 4.8120 (4.7389)	grad_norm 1.7297 (1.7071)	
[2022-01-17 21:46:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][40/1251]	eta 0:54:39 lr 0.000652	time 4.6527 (2.7085)	loss 5.3073 (4.7320)	grad_norm 1.4660 (1.7092)	
[2022-01-17 21:46:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][50/1251]	eta 0:52:07 lr 0.000652	time 1.4738 (2.6039)	loss 5.1074 (4.7656)	grad_norm 1.6826 (1.7064)	
[2022-01-17 21:47:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][60/1251]	eta 0:50:26 lr 0.000653	time 1.4867 (2.5411)	loss 4.7317 (4.8017)	grad_norm 1.8034 (1.7092)	
[2022-01-17 21:47:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][70/1251]	eta 0:49:09 lr 0.000653	time 1.5666 (2.4971)	loss 4.3774 (4.8054)	grad_norm 1.5704 (1.7038)	
[2022-01-17 21:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][80/1251]	eta 0:48:38 lr 0.000654	time 3.6400 (2.4921)	loss 3.6792 (4.8107)	grad_norm 1.6293 (1.6979)	
[2022-01-17 21:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][90/1251]	eta 0:47:49 lr 0.000654	time 1.7868 (2.4719)	loss 3.8104 (4.7893)	grad_norm 2.2803 (1.7039)	
[2022-01-17 21:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][100/1251]	eta 0:47:14 lr 0.000654	time 1.9311 (2.4626)	loss 3.9397 (4.7838)	grad_norm 1.7651 (1.6961)	
[2022-01-17 21:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][110/1251]	eta 0:45:56 lr 0.000655	time 1.8683 (2.4162)	loss 5.1173 (4.7867)	grad_norm 1.7489 (1.7037)	
[2022-01-17 21:49:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][120/1251]	eta 0:44:43 lr 0.000655	time 2.1744 (2.3727)	loss 4.8906 (4.7846)	grad_norm 1.8253 (1.6890)	
[2022-01-17 21:49:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][130/1251]	eta 0:43:53 lr 0.000656	time 2.2581 (2.3488)	loss 5.4756 (4.7962)	grad_norm 2.4642 (1.7036)	
[2022-01-17 21:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][140/1251]	eta 0:43:06 lr 0.000656	time 1.8593 (2.3276)	loss 5.4880 (4.7952)	grad_norm 1.7579 (1.7128)	
[2022-01-17 21:50:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][150/1251]	eta 0:42:43 lr 0.000656	time 2.8921 (2.3283)	loss 5.3085 (4.8077)	grad_norm 1.4313 (1.7155)	
[2022-01-17 21:50:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][160/1251]	eta 0:42:14 lr 0.000657	time 2.2207 (2.3231)	loss 4.4689 (4.7977)	grad_norm 1.5189 (1.7105)	
[2022-01-17 21:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][170/1251]	eta 0:41:36 lr 0.000657	time 1.8591 (2.3093)	loss 4.1498 (4.7969)	grad_norm 1.5166 (1.7117)	
[2022-01-17 21:51:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][180/1251]	eta 0:41:04 lr 0.000658	time 1.9192 (2.3015)	loss 4.8572 (4.8217)	grad_norm 1.6963 (1.7103)	
[2022-01-17 21:52:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][190/1251]	eta 0:40:39 lr 0.000658	time 2.3036 (2.2991)	loss 3.8395 (4.8091)	grad_norm 1.5121 (1.7148)	
[2022-01-17 21:52:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][200/1251]	eta 0:40:18 lr 0.000658	time 2.4440 (2.3010)	loss 4.4462 (4.8049)	grad_norm 1.5516 (1.7135)	
[2022-01-17 21:52:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][210/1251]	eta 0:40:01 lr 0.000659	time 2.2805 (2.3070)	loss 5.2753 (4.8143)	grad_norm 1.7276 (1.7126)	
[2022-01-17 21:53:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][220/1251]	eta 0:39:33 lr 0.000659	time 2.5459 (2.3025)	loss 5.0960 (4.8104)	grad_norm 1.5920 (1.7075)	
[2022-01-17 21:53:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][230/1251]	eta 0:38:57 lr 0.000660	time 2.0310 (2.2895)	loss 5.3223 (4.8078)	grad_norm 1.3499 (1.7023)	
[2022-01-17 21:53:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][240/1251]	eta 0:38:23 lr 0.000660	time 1.8685 (2.2787)	loss 4.8004 (4.8193)	grad_norm 1.8051 (1.6993)	
[2022-01-17 21:54:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][250/1251]	eta 0:37:51 lr 0.000660	time 2.0855 (2.2688)	loss 4.9211 (4.8273)	grad_norm 1.4615 (1.6901)	
[2022-01-17 21:54:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][260/1251]	eta 0:37:25 lr 0.000661	time 2.8923 (2.2658)	loss 5.3431 (4.8232)	grad_norm 1.3999 (1.6895)	
[2022-01-17 21:54:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][270/1251]	eta 0:37:04 lr 0.000661	time 1.7395 (2.2679)	loss 4.3896 (4.8175)	grad_norm 1.2454 (1.6911)	
[2022-01-17 21:55:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][280/1251]	eta 0:36:42 lr 0.000662	time 2.7734 (2.2681)	loss 4.8875 (4.8133)	grad_norm 2.1266 (1.6966)	
[2022-01-17 21:55:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][290/1251]	eta 0:36:16 lr 0.000662	time 2.1947 (2.2651)	loss 5.1804 (4.8072)	grad_norm 1.2688 (1.6921)	
[2022-01-17 21:56:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][300/1251]	eta 0:35:47 lr 0.000662	time 2.5663 (2.2581)	loss 5.0649 (4.7996)	grad_norm 1.5966 (1.6885)	
[2022-01-17 21:56:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][310/1251]	eta 0:35:21 lr 0.000663	time 1.8187 (2.2549)	loss 4.9685 (4.7998)	grad_norm 1.1798 (1.6812)	
[2022-01-17 21:56:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][320/1251]	eta 0:34:59 lr 0.000663	time 2.0003 (2.2551)	loss 5.7142 (4.8055)	grad_norm 1.6186 (1.6775)	
[2022-01-17 21:57:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][330/1251]	eta 0:34:34 lr 0.000664	time 2.0254 (2.2522)	loss 5.6907 (4.8107)	grad_norm 1.2445 (1.6783)	
[2022-01-17 21:57:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][340/1251]	eta 0:34:08 lr 0.000664	time 2.3360 (2.2491)	loss 4.7336 (4.8054)	grad_norm 1.4078 (1.6705)	
[2022-01-17 21:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][350/1251]	eta 0:33:40 lr 0.000664	time 1.7314 (2.2430)	loss 4.4999 (4.8037)	grad_norm 2.0129 (1.6719)	
[2022-01-17 21:58:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][360/1251]	eta 0:33:16 lr 0.000665	time 2.4672 (2.2403)	loss 4.6119 (4.8023)	grad_norm 1.8771 (1.6747)	
[2022-01-17 21:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][370/1251]	eta 0:32:48 lr 0.000665	time 1.6911 (2.2338)	loss 4.5806 (4.8105)	grad_norm 2.1465 (1.6756)	
[2022-01-17 21:58:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][380/1251]	eta 0:32:25 lr 0.000666	time 2.8540 (2.2334)	loss 5.3273 (4.8109)	grad_norm 1.7415 (1.6794)	
[2022-01-17 21:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][390/1251]	eta 0:32:03 lr 0.000666	time 2.5005 (2.2339)	loss 5.0078 (4.8080)	grad_norm 1.8462 (1.6748)	
[2022-01-17 21:59:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][400/1251]	eta 0:31:39 lr 0.000666	time 2.2160 (2.2326)	loss 5.3794 (4.8100)	grad_norm 1.8158 (1.6780)	
[2022-01-17 21:59:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][410/1251]	eta 0:31:18 lr 0.000667	time 1.9436 (2.2333)	loss 3.6613 (4.8060)	grad_norm 1.4996 (1.6787)	
[2022-01-17 22:00:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][420/1251]	eta 0:30:58 lr 0.000667	time 3.5709 (2.2365)	loss 4.1495 (4.8059)	grad_norm 1.6661 (1.6756)	
[2022-01-17 22:00:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][430/1251]	eta 0:30:33 lr 0.000668	time 1.9329 (2.2331)	loss 4.5889 (4.8086)	grad_norm 1.5264 (1.6752)	
[2022-01-17 22:01:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][440/1251]	eta 0:30:09 lr 0.000668	time 1.9024 (2.2312)	loss 4.7891 (4.8153)	grad_norm 1.5849 (1.6709)	
[2022-01-17 22:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][450/1251]	eta 0:29:46 lr 0.000668	time 1.9147 (2.2304)	loss 5.2800 (4.8200)	grad_norm 1.3186 (1.6675)	
[2022-01-17 22:01:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][460/1251]	eta 0:29:29 lr 0.000669	time 3.6334 (2.2372)	loss 5.0489 (4.8152)	grad_norm 1.9154 (1.6660)	
[2022-01-17 22:02:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][470/1251]	eta 0:29:06 lr 0.000669	time 1.8234 (2.2358)	loss 5.0809 (4.8119)	grad_norm 1.6030 (1.6633)	
[2022-01-17 22:02:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][480/1251]	eta 0:28:40 lr 0.000670	time 1.6199 (2.2311)	loss 5.3942 (4.8131)	grad_norm 1.6755 (1.6624)	
[2022-01-17 22:02:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][490/1251]	eta 0:28:11 lr 0.000670	time 1.6374 (2.2234)	loss 5.7192 (4.8203)	grad_norm 1.7653 (1.6682)	
[2022-01-17 22:03:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][500/1251]	eta 0:27:46 lr 0.000670	time 1.8636 (2.2194)	loss 5.7028 (4.8252)	grad_norm 1.4947 (1.6675)	
[2022-01-17 22:03:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][510/1251]	eta 0:27:24 lr 0.000671	time 2.4627 (2.2193)	loss 5.0563 (4.8332)	grad_norm 1.3515 (1.6649)	
[2022-01-17 22:03:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][520/1251]	eta 0:27:02 lr 0.000671	time 2.0932 (2.2191)	loss 5.0853 (4.8341)	grad_norm 1.8420 (1.6643)	
[2022-01-17 22:04:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][530/1251]	eta 0:26:39 lr 0.000672	time 2.3347 (2.2180)	loss 5.2244 (4.8263)	grad_norm 1.4654 (1.6630)	
[2022-01-17 22:04:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][540/1251]	eta 0:26:17 lr 0.000672	time 2.4182 (2.2194)	loss 5.1257 (4.8251)	grad_norm 1.5325 (1.6631)	
[2022-01-17 22:05:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][550/1251]	eta 0:25:56 lr 0.000672	time 2.1652 (2.2203)	loss 5.2465 (4.8210)	grad_norm 1.5942 (1.6616)	
[2022-01-17 22:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][560/1251]	eta 0:25:34 lr 0.000673	time 2.3783 (2.2201)	loss 4.5546 (4.8192)	grad_norm 1.4443 (1.6620)	
[2022-01-17 22:05:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][570/1251]	eta 0:25:11 lr 0.000673	time 2.2196 (2.2197)	loss 4.3481 (4.8221)	grad_norm 2.0199 (1.6617)	
[2022-01-17 22:06:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][580/1251]	eta 0:24:50 lr 0.000674	time 2.4753 (2.2213)	loss 4.7156 (4.8259)	grad_norm 1.7162 (1.6588)	
[2022-01-17 22:06:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][590/1251]	eta 0:24:26 lr 0.000674	time 1.8479 (2.2181)	loss 5.0829 (4.8296)	grad_norm 1.6781 (1.6573)	
[2022-01-17 22:06:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][600/1251]	eta 0:24:03 lr 0.000674	time 2.2820 (2.2168)	loss 5.4801 (4.8276)	grad_norm 1.9964 (1.6601)	
[2022-01-17 22:07:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][610/1251]	eta 0:23:40 lr 0.000675	time 2.5439 (2.2164)	loss 5.2891 (4.8290)	grad_norm 1.8006 (1.6596)	
[2022-01-17 22:07:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][620/1251]	eta 0:23:18 lr 0.000675	time 1.6591 (2.2171)	loss 5.4869 (4.8298)	grad_norm 1.3032 (1.6569)	
[2022-01-17 22:07:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][630/1251]	eta 0:22:56 lr 0.000676	time 1.9186 (2.2163)	loss 4.5137 (4.8278)	grad_norm 1.5927 (1.6563)	
[2022-01-17 22:08:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][640/1251]	eta 0:22:31 lr 0.000676	time 1.5358 (2.2124)	loss 5.5386 (4.8248)	grad_norm 1.5535 (1.6563)	
[2022-01-17 22:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][650/1251]	eta 0:22:08 lr 0.000676	time 1.6382 (2.2100)	loss 4.9693 (4.8206)	grad_norm 1.2865 (1.6549)	
[2022-01-17 22:09:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][660/1251]	eta 0:21:48 lr 0.000677	time 2.2944 (2.2133)	loss 4.6345 (4.8223)	grad_norm 1.6356 (1.6569)	
[2022-01-17 22:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][670/1251]	eta 0:21:27 lr 0.000677	time 2.1736 (2.2153)	loss 3.7426 (4.8194)	grad_norm 1.7017 (1.6581)	
[2022-01-17 22:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][680/1251]	eta 0:21:05 lr 0.000678	time 1.7238 (2.2160)	loss 5.2655 (4.8196)	grad_norm 1.6759 (1.6591)	
[2022-01-17 22:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][690/1251]	eta 0:20:42 lr 0.000678	time 1.7864 (2.2150)	loss 3.7108 (4.8221)	grad_norm 1.8983 (1.6585)	
[2022-01-17 22:10:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][700/1251]	eta 0:20:19 lr 0.000678	time 1.9267 (2.2132)	loss 5.7713 (4.8232)	grad_norm 1.5947 (1.6565)	
[2022-01-17 22:10:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][710/1251]	eta 0:19:55 lr 0.000679	time 1.9057 (2.2100)	loss 5.2175 (4.8212)	grad_norm 1.3025 (1.6556)	
[2022-01-17 22:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][720/1251]	eta 0:19:32 lr 0.000679	time 2.1871 (2.2081)	loss 4.6399 (4.8201)	grad_norm 1.6977 (1.6540)	
[2022-01-17 22:11:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][730/1251]	eta 0:19:10 lr 0.000679	time 1.9787 (2.2077)	loss 4.5567 (4.8195)	grad_norm 1.6709 (1.6540)	
[2022-01-17 22:11:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][740/1251]	eta 0:18:48 lr 0.000680	time 1.8560 (2.2092)	loss 4.6860 (4.8222)	grad_norm 1.3177 (1.6524)	
[2022-01-17 22:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][750/1251]	eta 0:18:27 lr 0.000680	time 2.6523 (2.2107)	loss 4.2373 (4.8209)	grad_norm 1.2905 (1.6549)	
[2022-01-17 22:12:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][760/1251]	eta 0:18:06 lr 0.000681	time 2.2175 (2.2126)	loss 5.3730 (4.8170)	grad_norm 1.6346 (1.6554)	
[2022-01-17 22:13:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][770/1251]	eta 0:17:43 lr 0.000681	time 1.5915 (2.2111)	loss 4.2387 (4.8147)	grad_norm 1.4011 (1.6525)	
[2022-01-17 22:13:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][780/1251]	eta 0:17:19 lr 0.000681	time 1.8535 (2.2081)	loss 5.1045 (4.8147)	grad_norm 1.7626 (1.6558)	
[2022-01-17 22:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][790/1251]	eta 0:16:56 lr 0.000682	time 1.7330 (2.2044)	loss 4.0964 (4.8126)	grad_norm 1.4607 (1.6565)	
[2022-01-17 22:14:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][800/1251]	eta 0:16:34 lr 0.000682	time 2.0169 (2.2046)	loss 4.6454 (4.8152)	grad_norm 1.6108 (1.6549)	
[2022-01-17 22:14:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][810/1251]	eta 0:16:12 lr 0.000683	time 2.2473 (2.2048)	loss 4.9768 (4.8139)	grad_norm 1.5663 (1.6568)	
[2022-01-17 22:14:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][820/1251]	eta 0:15:50 lr 0.000683	time 2.2738 (2.2049)	loss 5.0937 (4.8144)	grad_norm 1.6385 (1.6567)	
[2022-01-17 22:15:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][830/1251]	eta 0:15:28 lr 0.000683	time 2.6998 (2.2054)	loss 5.0943 (4.8149)	grad_norm 1.5801 (1.6573)	
[2022-01-17 22:15:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][840/1251]	eta 0:15:06 lr 0.000684	time 2.1909 (2.2049)	loss 5.2250 (4.8177)	grad_norm 1.6167 (1.6579)	
[2022-01-17 22:15:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][850/1251]	eta 0:14:44 lr 0.000684	time 2.4277 (2.2046)	loss 5.1935 (4.8165)	grad_norm 1.4363 (1.6567)	
[2022-01-17 22:16:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][860/1251]	eta 0:14:21 lr 0.000685	time 2.1961 (2.2042)	loss 5.1070 (4.8200)	grad_norm 1.5491 (1.6559)	
[2022-01-17 22:16:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][870/1251]	eta 0:14:00 lr 0.000685	time 3.0659 (2.2051)	loss 5.5415 (4.8191)	grad_norm 1.2975 (1.6563)	
[2022-01-17 22:17:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][880/1251]	eta 0:13:37 lr 0.000685	time 1.5235 (2.2039)	loss 3.8661 (4.8184)	grad_norm 2.0039 (1.6552)	
[2022-01-17 22:17:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][890/1251]	eta 0:13:16 lr 0.000686	time 3.1563 (2.2050)	loss 4.4634 (4.8199)	grad_norm 1.7531 (1.6573)	
[2022-01-17 22:17:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][900/1251]	eta 0:12:54 lr 0.000686	time 1.5794 (2.2052)	loss 4.0845 (4.8221)	grad_norm 1.5316 (1.6584)	
[2022-01-17 22:18:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][910/1251]	eta 0:12:32 lr 0.000687	time 2.8258 (2.2068)	loss 5.4422 (4.8234)	grad_norm 1.6239 (1.6574)	
[2022-01-17 22:18:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][920/1251]	eta 0:12:09 lr 0.000687	time 1.6141 (2.2051)	loss 5.3347 (4.8202)	grad_norm 1.5194 (1.6556)	
[2022-01-17 22:18:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][930/1251]	eta 0:11:47 lr 0.000687	time 2.7162 (2.2050)	loss 4.7140 (4.8164)	grad_norm 1.7668 (1.6539)	
[2022-01-17 22:19:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][940/1251]	eta 0:11:25 lr 0.000688	time 2.3163 (2.2048)	loss 4.6990 (4.8183)	grad_norm 1.6731 (1.6539)	
[2022-01-17 22:19:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][950/1251]	eta 0:11:03 lr 0.000688	time 2.3935 (2.2053)	loss 4.7417 (4.8178)	grad_norm 1.5821 (1.6533)	
[2022-01-17 22:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][960/1251]	eta 0:10:41 lr 0.000689	time 1.8444 (2.2060)	loss 5.2823 (4.8160)	grad_norm 1.2379 (1.6529)	
[2022-01-17 22:20:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][970/1251]	eta 0:10:19 lr 0.000689	time 2.3187 (2.2052)	loss 3.9770 (4.8142)	grad_norm 1.6574 (1.6516)	
[2022-01-17 22:20:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][980/1251]	eta 0:09:56 lr 0.000689	time 1.9615 (2.2028)	loss 5.2252 (4.8165)	grad_norm 1.5389 (1.6500)	
[2022-01-17 22:21:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][990/1251]	eta 0:09:34 lr 0.000690	time 2.4783 (2.2017)	loss 4.3912 (4.8164)	grad_norm 1.7936 (1.6486)	
[2022-01-17 22:21:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1000/1251]	eta 0:09:12 lr 0.000690	time 2.2790 (2.2026)	loss 4.7791 (4.8178)	grad_norm 1.5560 (1.6504)	
[2022-01-17 22:21:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1010/1251]	eta 0:08:50 lr 0.000691	time 1.5615 (2.2012)	loss 5.4681 (4.8167)	grad_norm 1.3099 (1.6502)	
[2022-01-17 22:22:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1020/1251]	eta 0:08:28 lr 0.000691	time 1.6843 (2.2016)	loss 5.6487 (4.8167)	grad_norm 1.7940 (1.6499)	
[2022-01-17 22:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1030/1251]	eta 0:08:06 lr 0.000691	time 2.7286 (2.2027)	loss 5.1430 (4.8174)	grad_norm 1.9672 (1.6493)	
[2022-01-17 22:22:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1040/1251]	eta 0:07:45 lr 0.000692	time 3.1567 (2.2044)	loss 5.2627 (4.8180)	grad_norm 1.3989 (1.6488)	
[2022-01-17 22:23:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1050/1251]	eta 0:07:22 lr 0.000692	time 1.5896 (2.2037)	loss 4.6716 (4.8190)	grad_norm 1.5238 (1.6479)	
[2022-01-17 22:23:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1060/1251]	eta 0:07:00 lr 0.000693	time 1.8980 (2.2020)	loss 5.5106 (4.8189)	grad_norm 1.3243 (1.6471)	
[2022-01-17 22:23:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1070/1251]	eta 0:06:38 lr 0.000693	time 1.8974 (2.2017)	loss 4.9087 (4.8202)	grad_norm 1.4961 (1.6465)	
[2022-01-17 22:24:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1080/1251]	eta 0:06:16 lr 0.000693	time 3.1623 (2.2018)	loss 5.0398 (4.8175)	grad_norm 1.5248 (1.6457)	
[2022-01-17 22:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1090/1251]	eta 0:05:54 lr 0.000694	time 2.4552 (2.2023)	loss 5.1680 (4.8186)	grad_norm 1.2864 (1.6449)	
[2022-01-17 22:25:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1100/1251]	eta 0:05:32 lr 0.000694	time 1.8956 (2.2025)	loss 5.3682 (4.8174)	grad_norm 1.9819 (1.6458)	
[2022-01-17 22:25:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1110/1251]	eta 0:05:10 lr 0.000695	time 1.9002 (2.2024)	loss 5.5448 (4.8168)	grad_norm 1.6558 (1.6452)	
[2022-01-17 22:25:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1120/1251]	eta 0:04:48 lr 0.000695	time 2.8430 (2.2031)	loss 4.8878 (4.8142)	grad_norm 2.7003 (1.6488)	
[2022-01-17 22:26:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1130/1251]	eta 0:04:26 lr 0.000695	time 1.8757 (2.2019)	loss 5.0023 (4.8159)	grad_norm 1.4904 (1.6502)	
[2022-01-17 22:26:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1140/1251]	eta 0:04:04 lr 0.000696	time 1.9994 (2.2004)	loss 4.5248 (4.8167)	grad_norm 1.4410 (1.6488)	
[2022-01-17 22:26:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1150/1251]	eta 0:03:42 lr 0.000696	time 2.5718 (2.1994)	loss 5.1475 (4.8175)	grad_norm 1.8741 (1.6496)	
[2022-01-17 22:27:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1160/1251]	eta 0:03:20 lr 0.000697	time 2.2252 (2.1999)	loss 4.7691 (4.8197)	grad_norm 1.4205 (1.6489)	
[2022-01-17 22:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1170/1251]	eta 0:02:58 lr 0.000697	time 2.5997 (2.2008)	loss 4.6358 (4.8196)	grad_norm 1.3901 (1.6482)	
[2022-01-17 22:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1180/1251]	eta 0:02:36 lr 0.000697	time 1.7577 (2.2001)	loss 5.0899 (4.8188)	grad_norm 1.7647 (1.6490)	
[2022-01-17 22:28:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1190/1251]	eta 0:02:14 lr 0.000698	time 1.7698 (2.1987)	loss 5.0711 (4.8157)	grad_norm 2.1116 (1.6490)	
[2022-01-17 22:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1200/1251]	eta 0:01:52 lr 0.000698	time 2.6320 (2.1988)	loss 4.6894 (4.8142)	grad_norm 1.4872 (1.6484)	
[2022-01-17 22:29:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1210/1251]	eta 0:01:30 lr 0.000699	time 2.6371 (2.1988)	loss 4.8952 (4.8144)	grad_norm 1.2335 (1.6476)	
[2022-01-17 22:29:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1220/1251]	eta 0:01:08 lr 0.000699	time 2.1667 (2.1983)	loss 5.3942 (4.8143)	grad_norm 1.3810 (1.6466)	
[2022-01-17 22:29:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1230/1251]	eta 0:00:46 lr 0.000699	time 1.6306 (2.1976)	loss 4.7717 (4.8141)	grad_norm 1.3877 (1.6474)	
[2022-01-17 22:30:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1240/1251]	eta 0:00:24 lr 0.000700	time 1.5125 (2.1963)	loss 4.5147 (4.8110)	grad_norm 1.6771 (1.6486)	
[2022-01-17 22:30:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [13/300][1250/1251]	eta 0:00:02 lr 0.000700	time 1.1912 (2.1909)	loss 4.8077 (4.8121)	grad_norm 1.4767 (1.6494)	
[2022-01-17 22:30:22 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 13 training takes 0:45:41
[2022-01-17 22:30:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.447 (18.447)	Loss 2.0841 (2.0841)	Acc@1 53.613 (53.613)	Acc@5 77.246 (77.246)	
[2022-01-17 22:31:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.666 (3.569)	Loss 2.1463 (2.1542)	Acc@1 51.074 (52.459)	Acc@5 78.516 (77.290)	
[2022-01-17 22:31:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.591 (2.609)	Loss 2.1923 (2.1489)	Acc@1 52.930 (52.618)	Acc@5 76.465 (77.646)	
[2022-01-17 22:31:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.993 (2.332)	Loss 2.2026 (2.1541)	Acc@1 53.027 (52.593)	Acc@5 77.441 (77.577)	
[2022-01-17 22:31:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.272 (2.178)	Loss 2.1868 (2.1523)	Acc@1 53.809 (52.780)	Acc@5 77.051 (77.703)	
[2022-01-17 22:31:58 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 52.758 Acc@5 77.754
[2022-01-17 22:31:58 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 52.8%
[2022-01-17 22:31:58 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 52.76%
[2022-01-17 22:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][0/1251]	eta 7:30:41 lr 0.000700	time 21.6159 (21.6159)	loss 5.1464 (5.1464)	grad_norm 1.5118 (1.5118)	
[2022-01-17 22:32:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][10/1251]	eta 1:25:02 lr 0.000701	time 2.8760 (4.1115)	loss 5.2567 (4.9261)	grad_norm 1.5558 (1.7024)	
[2022-01-17 22:33:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][20/1251]	eta 1:03:55 lr 0.000701	time 1.5870 (3.1159)	loss 4.2377 (4.7741)	grad_norm 1.4374 (1.6654)	
[2022-01-17 22:33:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][30/1251]	eta 0:57:11 lr 0.000701	time 1.5379 (2.8106)	loss 4.3499 (4.8341)	grad_norm 1.3574 (1.6229)	
[2022-01-17 22:33:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][40/1251]	eta 0:54:12 lr 0.000702	time 3.6387 (2.6858)	loss 4.5426 (4.7675)	grad_norm 1.3057 (1.6662)	
[2022-01-17 22:34:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][50/1251]	eta 0:52:35 lr 0.000702	time 2.1645 (2.6277)	loss 5.1063 (4.7489)	grad_norm 1.7105 (1.6720)	
[2022-01-17 22:34:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][60/1251]	eta 0:50:54 lr 0.000703	time 1.6752 (2.5649)	loss 4.6324 (4.7819)	grad_norm 1.7996 (1.6709)	
[2022-01-17 22:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][70/1251]	eta 0:48:46 lr 0.000703	time 1.9141 (2.4777)	loss 3.8566 (4.7794)	grad_norm 1.1329 (1.6961)	
[2022-01-17 22:35:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][80/1251]	eta 0:47:50 lr 0.000703	time 3.6362 (2.4509)	loss 4.2360 (4.7951)	grad_norm 1.6293 (1.6824)	
[2022-01-17 22:35:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][90/1251]	eta 0:47:31 lr 0.000704	time 1.7107 (2.4565)	loss 5.0819 (4.8090)	grad_norm 1.5050 (1.7034)	
[2022-01-17 22:36:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][100/1251]	eta 0:46:33 lr 0.000704	time 1.5945 (2.4271)	loss 4.3935 (4.8128)	grad_norm 1.3119 (1.7065)	
[2022-01-17 22:36:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][110/1251]	eta 0:45:49 lr 0.000705	time 1.9039 (2.4095)	loss 4.8158 (4.8084)	grad_norm 1.4470 (1.6933)	
[2022-01-17 22:36:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][120/1251]	eta 0:45:08 lr 0.000705	time 2.8606 (2.3949)	loss 4.7730 (4.7982)	grad_norm 1.7588 (1.6841)	
[2022-01-17 22:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][130/1251]	eta 0:44:41 lr 0.000705	time 1.9109 (2.3923)	loss 4.0197 (4.8046)	grad_norm 1.9259 (1.6686)	
[2022-01-17 22:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][140/1251]	eta 0:43:44 lr 0.000706	time 1.8247 (2.3626)	loss 5.1219 (4.7994)	grad_norm 1.4958 (1.6686)	
[2022-01-17 22:37:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][150/1251]	eta 0:42:54 lr 0.000706	time 1.7260 (2.3381)	loss 4.6580 (4.8011)	grad_norm 1.7176 (1.6629)	
[2022-01-17 22:38:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][160/1251]	eta 0:42:22 lr 0.000707	time 2.5093 (2.3309)	loss 5.4090 (4.8190)	grad_norm 1.3723 (1.6625)	
[2022-01-17 22:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][170/1251]	eta 0:42:04 lr 0.000707	time 2.1976 (2.3357)	loss 3.8572 (4.7984)	grad_norm 1.4275 (1.6586)	
[2022-01-17 22:39:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][180/1251]	eta 0:41:37 lr 0.000707	time 2.4284 (2.3320)	loss 4.4711 (4.7678)	grad_norm 2.6555 (1.6581)	
[2022-01-17 22:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][190/1251]	eta 0:41:02 lr 0.000708	time 1.7635 (2.3212)	loss 5.0304 (4.7872)	grad_norm 1.3476 (1.6533)	
[2022-01-17 22:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][200/1251]	eta 0:40:20 lr 0.000708	time 1.9340 (2.3027)	loss 5.0752 (4.7822)	grad_norm 1.6596 (1.6520)	
[2022-01-17 22:39:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][210/1251]	eta 0:39:35 lr 0.000709	time 1.9495 (2.2821)	loss 4.8158 (4.7755)	grad_norm 1.3858 (1.6506)	
[2022-01-17 22:40:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][220/1251]	eta 0:39:07 lr 0.000709	time 1.8191 (2.2767)	loss 4.0399 (4.7710)	grad_norm 2.0063 (1.6510)	
[2022-01-17 22:40:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][230/1251]	eta 0:38:37 lr 0.000709	time 2.0243 (2.2703)	loss 4.8088 (4.7763)	grad_norm 1.6186 (1.6488)	
[2022-01-17 22:41:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][240/1251]	eta 0:38:19 lr 0.000710	time 2.2051 (2.2748)	loss 5.2476 (4.7887)	grad_norm 1.6324 (1.6458)	
[2022-01-17 22:41:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][250/1251]	eta 0:37:53 lr 0.000710	time 2.0004 (2.2712)	loss 5.7430 (4.7874)	grad_norm 1.3228 (1.6439)	
[2022-01-17 22:41:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][260/1251]	eta 0:37:42 lr 0.000711	time 3.0762 (2.2828)	loss 4.2583 (4.7866)	grad_norm 1.7619 (1.6470)	
[2022-01-17 22:42:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][270/1251]	eta 0:37:23 lr 0.000711	time 1.8180 (2.2868)	loss 4.1498 (4.7812)	grad_norm 1.4478 (1.6440)	
[2022-01-17 22:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][280/1251]	eta 0:36:51 lr 0.000711	time 1.8821 (2.2776)	loss 4.9653 (4.7824)	grad_norm 1.4600 (1.6448)	
[2022-01-17 22:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][290/1251]	eta 0:36:17 lr 0.000712	time 1.8937 (2.2656)	loss 5.1286 (4.7805)	grad_norm 1.6320 (1.6426)	
[2022-01-17 22:43:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][300/1251]	eta 0:35:44 lr 0.000712	time 2.0202 (2.2552)	loss 4.6579 (4.7803)	grad_norm 1.4879 (1.6380)	
[2022-01-17 22:43:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][310/1251]	eta 0:35:13 lr 0.000713	time 1.9390 (2.2459)	loss 4.5156 (4.7734)	grad_norm 1.2618 (1.6355)	
[2022-01-17 22:43:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][320/1251]	eta 0:34:44 lr 0.000713	time 1.9196 (2.2390)	loss 5.0526 (4.7722)	grad_norm 1.5533 (1.6377)	
[2022-01-17 22:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][330/1251]	eta 0:34:19 lr 0.000713	time 1.8473 (2.2361)	loss 4.8763 (4.7750)	grad_norm 1.5037 (1.6375)	
[2022-01-17 22:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][340/1251]	eta 0:34:01 lr 0.000714	time 2.0815 (2.2406)	loss 4.7721 (4.7699)	grad_norm 1.3386 (1.6334)	
[2022-01-17 22:45:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][350/1251]	eta 0:33:50 lr 0.000714	time 2.5732 (2.2538)	loss 4.0680 (4.7699)	grad_norm 1.5934 (1.6283)	
[2022-01-17 22:45:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][360/1251]	eta 0:33:31 lr 0.000715	time 2.1061 (2.2578)	loss 5.4786 (4.7729)	grad_norm 1.5349 (1.6273)	
[2022-01-17 22:45:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][370/1251]	eta 0:33:07 lr 0.000715	time 1.9289 (2.2565)	loss 5.1421 (4.7668)	grad_norm 2.0405 (1.6259)	
[2022-01-17 22:46:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][380/1251]	eta 0:32:39 lr 0.000715	time 1.7691 (2.2497)	loss 4.3143 (4.7687)	grad_norm 1.6982 (1.6269)	
[2022-01-17 22:46:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][390/1251]	eta 0:32:10 lr 0.000716	time 1.8108 (2.2427)	loss 5.3962 (4.7681)	grad_norm 1.5413 (1.6313)	
[2022-01-17 22:46:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][400/1251]	eta 0:31:45 lr 0.000716	time 2.1839 (2.2397)	loss 5.0374 (4.7721)	grad_norm 1.4674 (1.6285)	
[2022-01-17 22:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][410/1251]	eta 0:31:19 lr 0.000717	time 2.0381 (2.2348)	loss 5.5047 (4.7752)	grad_norm 1.5635 (1.6253)	
[2022-01-17 22:47:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][420/1251]	eta 0:30:53 lr 0.000717	time 1.8583 (2.2308)	loss 4.0484 (4.7695)	grad_norm 1.4700 (1.6244)	
[2022-01-17 22:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][430/1251]	eta 0:30:31 lr 0.000717	time 2.1655 (2.2309)	loss 4.8412 (4.7723)	grad_norm 1.7352 (1.6267)	
[2022-01-17 22:48:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][440/1251]	eta 0:30:12 lr 0.000718	time 3.4656 (2.2349)	loss 5.3247 (4.7659)	grad_norm 1.4932 (1.6278)	
[2022-01-17 22:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][450/1251]	eta 0:29:51 lr 0.000718	time 2.0387 (2.2366)	loss 4.7148 (4.7654)	grad_norm 1.1768 (1.6232)	
[2022-01-17 22:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][460/1251]	eta 0:29:32 lr 0.000719	time 1.8957 (2.2404)	loss 5.1366 (4.7688)	grad_norm 1.7944 (1.6249)	
[2022-01-17 22:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][470/1251]	eta 0:29:08 lr 0.000719	time 2.1979 (2.2389)	loss 5.6355 (4.7619)	grad_norm 1.4284 (1.6205)	
[2022-01-17 22:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][480/1251]	eta 0:28:44 lr 0.000719	time 2.4467 (2.2372)	loss 4.2773 (4.7588)	grad_norm 1.4964 (1.6192)	
[2022-01-17 22:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][490/1251]	eta 0:28:19 lr 0.000720	time 1.9005 (2.2336)	loss 4.9601 (4.7609)	grad_norm 1.6389 (1.6180)	
[2022-01-17 22:50:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][500/1251]	eta 0:27:56 lr 0.000720	time 2.5513 (2.2319)	loss 5.5764 (4.7634)	grad_norm 1.5124 (1.6218)	
[2022-01-17 22:50:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][510/1251]	eta 0:27:33 lr 0.000721	time 2.3734 (2.2308)	loss 3.8566 (4.7648)	grad_norm 1.7414 (1.6255)	
[2022-01-17 22:51:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][520/1251]	eta 0:27:12 lr 0.000721	time 3.3329 (2.2330)	loss 5.0749 (4.7635)	grad_norm 1.4870 (1.6239)	
[2022-01-17 22:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][530/1251]	eta 0:26:48 lr 0.000721	time 2.4078 (2.2313)	loss 4.9822 (4.7635)	grad_norm 1.8157 (1.6218)	
[2022-01-17 22:52:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][540/1251]	eta 0:26:24 lr 0.000722	time 2.5775 (2.2288)	loss 3.8987 (4.7605)	grad_norm 1.4422 (1.6205)	
[2022-01-17 22:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][550/1251]	eta 0:26:00 lr 0.000722	time 1.9956 (2.2261)	loss 3.5749 (4.7608)	grad_norm 1.3264 (1.6156)	
[2022-01-17 22:52:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][560/1251]	eta 0:25:37 lr 0.000723	time 2.1978 (2.2252)	loss 4.4724 (4.7645)	grad_norm 1.5563 (1.6152)	
[2022-01-17 22:53:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][570/1251]	eta 0:25:12 lr 0.000723	time 1.8791 (2.2216)	loss 4.6629 (4.7658)	grad_norm 1.5218 (1.6141)	
[2022-01-17 22:53:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][580/1251]	eta 0:24:53 lr 0.000723	time 2.7346 (2.2255)	loss 5.8026 (4.7720)	grad_norm 1.3012 (1.6127)	
[2022-01-17 22:53:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][590/1251]	eta 0:24:30 lr 0.000724	time 2.4068 (2.2244)	loss 4.1132 (4.7775)	grad_norm 1.4460 (1.6110)	
[2022-01-17 22:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][600/1251]	eta 0:24:07 lr 0.000724	time 2.1961 (2.2234)	loss 4.8387 (4.7782)	grad_norm 1.4325 (1.6096)	
[2022-01-17 22:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][610/1251]	eta 0:23:45 lr 0.000725	time 2.4568 (2.2233)	loss 5.1196 (4.7766)	grad_norm 1.5625 (1.6099)	
[2022-01-17 22:54:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][620/1251]	eta 0:23:23 lr 0.000725	time 2.8382 (2.2235)	loss 4.4660 (4.7737)	grad_norm 1.6390 (1.6089)	
[2022-01-17 22:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][630/1251]	eta 0:22:58 lr 0.000725	time 1.8418 (2.2200)	loss 5.5457 (4.7759)	grad_norm 1.7205 (1.6099)	
[2022-01-17 22:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][640/1251]	eta 0:22:37 lr 0.000726	time 1.8858 (2.2214)	loss 4.8427 (4.7742)	grad_norm 1.5663 (1.6081)	
[2022-01-17 22:56:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][650/1251]	eta 0:22:15 lr 0.000726	time 1.7937 (2.2221)	loss 4.0033 (4.7720)	grad_norm 1.4720 (1.6088)	
[2022-01-17 22:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][660/1251]	eta 0:21:53 lr 0.000727	time 3.4132 (2.2228)	loss 4.2616 (4.7755)	grad_norm 1.4664 (1.6051)	
[2022-01-17 22:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][670/1251]	eta 0:21:29 lr 0.000727	time 1.6119 (2.2193)	loss 4.2368 (4.7744)	grad_norm 2.1559 (1.6054)	
[2022-01-17 22:57:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][680/1251]	eta 0:21:06 lr 0.000727	time 2.2728 (2.2181)	loss 3.9989 (4.7743)	grad_norm 1.5583 (1.6068)	
[2022-01-17 22:57:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][690/1251]	eta 0:20:44 lr 0.000728	time 1.9287 (2.2182)	loss 4.5546 (4.7749)	grad_norm 1.5561 (1.6057)	
[2022-01-17 22:57:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][700/1251]	eta 0:20:23 lr 0.000728	time 2.8628 (2.2207)	loss 5.0375 (4.7772)	grad_norm 2.0321 (1.6043)	
[2022-01-17 22:58:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][710/1251]	eta 0:20:00 lr 0.000729	time 1.7764 (2.2197)	loss 3.7258 (4.7773)	grad_norm 1.9131 (1.6033)	
[2022-01-17 22:58:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][720/1251]	eta 0:19:37 lr 0.000729	time 1.9811 (2.2176)	loss 5.2149 (4.7793)	grad_norm 1.4511 (1.6053)	
[2022-01-17 22:58:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][730/1251]	eta 0:19:13 lr 0.000729	time 2.2703 (2.2141)	loss 4.9451 (4.7810)	grad_norm 1.6248 (1.6065)	
[2022-01-17 22:59:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][740/1251]	eta 0:18:51 lr 0.000730	time 2.1292 (2.2144)	loss 5.3266 (4.7832)	grad_norm 1.4692 (1.6074)	
[2022-01-17 22:59:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][750/1251]	eta 0:18:29 lr 0.000730	time 1.9217 (2.2147)	loss 4.8365 (4.7858)	grad_norm 1.4626 (1.6076)	
[2022-01-17 23:00:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][760/1251]	eta 0:18:07 lr 0.000731	time 2.8319 (2.2140)	loss 4.0831 (4.7876)	grad_norm 1.5993 (1.6075)	
[2022-01-17 23:00:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][770/1251]	eta 0:17:44 lr 0.000731	time 1.9401 (2.2126)	loss 5.2240 (4.7903)	grad_norm 1.6000 (1.6068)	
[2022-01-17 23:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][780/1251]	eta 0:17:21 lr 0.000731	time 1.8863 (2.2110)	loss 4.6509 (4.7879)	grad_norm 1.8965 (1.6111)	
[2022-01-17 23:01:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][790/1251]	eta 0:16:59 lr 0.000732	time 2.5460 (2.2114)	loss 5.4776 (4.7905)	grad_norm 1.2082 (1.6113)	
[2022-01-17 23:01:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][800/1251]	eta 0:16:37 lr 0.000732	time 2.4982 (2.2117)	loss 3.6896 (4.7893)	grad_norm 1.7249 (1.6122)	
[2022-01-17 23:01:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][810/1251]	eta 0:16:15 lr 0.000733	time 2.5076 (2.2109)	loss 5.1397 (4.7924)	grad_norm 1.4085 (1.6116)	
[2022-01-17 23:02:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][820/1251]	eta 0:15:52 lr 0.000733	time 2.6633 (2.2102)	loss 5.3630 (4.7929)	grad_norm 1.4418 (1.6123)	
[2022-01-17 23:02:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][830/1251]	eta 0:15:30 lr 0.000733	time 2.5467 (2.2103)	loss 4.9133 (4.7908)	grad_norm 1.7111 (1.6111)	
[2022-01-17 23:02:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][840/1251]	eta 0:15:07 lr 0.000734	time 1.9685 (2.2088)	loss 3.5048 (4.7876)	grad_norm 1.4060 (1.6100)	
[2022-01-17 23:03:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][850/1251]	eta 0:14:46 lr 0.000734	time 2.5613 (2.2100)	loss 4.7432 (4.7866)	grad_norm 1.4767 (1.6081)	
[2022-01-17 23:03:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][860/1251]	eta 0:14:24 lr 0.000735	time 1.5635 (2.2103)	loss 5.3529 (4.7865)	grad_norm 1.3529 (1.6068)	
[2022-01-17 23:04:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][870/1251]	eta 0:14:02 lr 0.000735	time 1.9520 (2.2102)	loss 5.4854 (4.7889)	grad_norm 1.5494 (1.6051)	
[2022-01-17 23:04:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][880/1251]	eta 0:13:39 lr 0.000735	time 2.1792 (2.2102)	loss 3.6118 (4.7882)	grad_norm 1.8476 (1.6068)	
[2022-01-17 23:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][890/1251]	eta 0:13:17 lr 0.000736	time 2.1601 (2.2101)	loss 4.9819 (4.7905)	grad_norm 1.9590 (1.6094)	
[2022-01-17 23:05:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][900/1251]	eta 0:12:55 lr 0.000736	time 1.6147 (2.2089)	loss 4.3175 (4.7921)	grad_norm 1.6117 (1.6096)	
[2022-01-17 23:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][910/1251]	eta 0:12:32 lr 0.000737	time 2.1563 (2.2078)	loss 4.0680 (4.7912)	grad_norm 1.6676 (1.6080)	
[2022-01-17 23:05:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][920/1251]	eta 0:12:10 lr 0.000737	time 1.7221 (2.2068)	loss 3.8459 (4.7890)	grad_norm 1.6591 (1.6076)	
[2022-01-17 23:06:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][930/1251]	eta 0:11:47 lr 0.000737	time 2.1538 (2.2055)	loss 5.1069 (4.7858)	grad_norm 1.4568 (1.6068)	
[2022-01-17 23:06:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][940/1251]	eta 0:11:26 lr 0.000738	time 2.1565 (2.2063)	loss 4.6717 (4.7846)	grad_norm 1.8427 (1.6060)	
[2022-01-17 23:06:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][950/1251]	eta 0:11:04 lr 0.000738	time 2.2220 (2.2065)	loss 4.2720 (4.7834)	grad_norm 1.2712 (1.6053)	
[2022-01-17 23:07:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][960/1251]	eta 0:10:42 lr 0.000739	time 1.9293 (2.2063)	loss 5.2352 (4.7851)	grad_norm 1.3900 (1.6035)	
[2022-01-17 23:07:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][970/1251]	eta 0:10:19 lr 0.000739	time 1.7685 (2.2059)	loss 3.7884 (4.7845)	grad_norm 1.2033 (1.6021)	
[2022-01-17 23:08:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][980/1251]	eta 0:09:57 lr 0.000739	time 2.0147 (2.2053)	loss 5.6192 (4.7856)	grad_norm 2.1002 (1.6025)	
[2022-01-17 23:08:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][990/1251]	eta 0:09:35 lr 0.000740	time 2.1286 (2.2055)	loss 3.9180 (4.7865)	grad_norm 1.4700 (1.6008)	
[2022-01-17 23:08:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1000/1251]	eta 0:09:13 lr 0.000740	time 1.8257 (2.2046)	loss 4.3475 (4.7854)	grad_norm 1.7035 (1.6011)	
[2022-01-17 23:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1010/1251]	eta 0:08:50 lr 0.000741	time 2.4012 (2.2032)	loss 4.0255 (4.7864)	grad_norm 1.5458 (1.5995)	
[2022-01-17 23:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1020/1251]	eta 0:08:28 lr 0.000741	time 2.0163 (2.2024)	loss 3.5106 (4.7857)	grad_norm 1.5514 (1.6005)	
[2022-01-17 23:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1030/1251]	eta 0:08:06 lr 0.000741	time 2.2057 (2.2025)	loss 4.9130 (4.7804)	grad_norm 1.2326 (1.5997)	
[2022-01-17 23:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1040/1251]	eta 0:07:44 lr 0.000742	time 2.5959 (2.2025)	loss 5.5391 (4.7823)	grad_norm 1.6907 (1.6001)	
[2022-01-17 23:10:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1050/1251]	eta 0:07:22 lr 0.000742	time 1.7306 (2.2028)	loss 3.7635 (4.7807)	grad_norm 1.9641 (1.5989)	
[2022-01-17 23:10:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1060/1251]	eta 0:07:00 lr 0.000743	time 2.0059 (2.2029)	loss 3.8004 (4.7804)	grad_norm 1.5569 (1.5980)	
[2022-01-17 23:11:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1070/1251]	eta 0:06:38 lr 0.000743	time 2.2197 (2.2032)	loss 4.5503 (4.7797)	grad_norm 1.6468 (1.5962)	
[2022-01-17 23:11:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1080/1251]	eta 0:06:16 lr 0.000743	time 2.0721 (2.2021)	loss 3.9162 (4.7788)	grad_norm 1.6717 (1.5955)	
[2022-01-17 23:12:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1090/1251]	eta 0:05:54 lr 0.000744	time 1.8684 (2.2014)	loss 4.3687 (4.7791)	grad_norm 1.3867 (1.5946)	
[2022-01-17 23:12:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1100/1251]	eta 0:05:32 lr 0.000744	time 1.5883 (2.1996)	loss 5.0859 (4.7788)	grad_norm 1.5441 (1.5932)	
[2022-01-17 23:12:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1110/1251]	eta 0:05:10 lr 0.000745	time 1.8482 (2.1995)	loss 4.3566 (4.7756)	grad_norm 1.7642 (1.5924)	
[2022-01-17 23:13:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1120/1251]	eta 0:04:48 lr 0.000745	time 1.5440 (2.1988)	loss 4.8998 (4.7733)	grad_norm 1.2117 (1.5919)	
[2022-01-17 23:13:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1130/1251]	eta 0:04:26 lr 0.000745	time 2.5435 (2.1996)	loss 5.1463 (4.7751)	grad_norm 1.9655 (1.5915)	
[2022-01-17 23:13:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1140/1251]	eta 0:04:04 lr 0.000746	time 3.0489 (2.2023)	loss 4.8872 (4.7739)	grad_norm 1.4621 (1.5913)	
[2022-01-17 23:14:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1150/1251]	eta 0:03:42 lr 0.000746	time 2.0636 (2.2025)	loss 5.0717 (4.7739)	grad_norm 1.7637 (1.5908)	
[2022-01-17 23:14:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1160/1251]	eta 0:03:20 lr 0.000747	time 2.1094 (2.2028)	loss 3.6153 (4.7724)	grad_norm 1.5093 (1.5903)	
[2022-01-17 23:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1170/1251]	eta 0:02:58 lr 0.000747	time 2.0122 (2.2016)	loss 3.5619 (4.7723)	grad_norm 1.4999 (1.5894)	
[2022-01-17 23:15:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1180/1251]	eta 0:02:36 lr 0.000747	time 1.6274 (2.1987)	loss 5.2969 (4.7747)	grad_norm 1.5610 (1.5892)	
[2022-01-17 23:15:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1190/1251]	eta 0:02:14 lr 0.000748	time 2.9492 (2.1972)	loss 4.1710 (4.7738)	grad_norm 1.3704 (1.5889)	
[2022-01-17 23:15:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1200/1251]	eta 0:01:52 lr 0.000748	time 1.6448 (2.1986)	loss 4.8347 (4.7720)	grad_norm 1.3829 (1.5890)	
[2022-01-17 23:16:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1210/1251]	eta 0:01:30 lr 0.000749	time 2.5297 (2.1989)	loss 4.5808 (4.7710)	grad_norm 1.4241 (1.5869)	
[2022-01-17 23:16:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1220/1251]	eta 0:01:08 lr 0.000749	time 1.8682 (2.1999)	loss 5.0036 (4.7685)	grad_norm 1.2223 (1.5851)	
[2022-01-17 23:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1230/1251]	eta 0:00:46 lr 0.000749	time 3.3796 (2.2012)	loss 4.4488 (4.7664)	grad_norm 1.4865 (1.5851)	
[2022-01-17 23:17:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1240/1251]	eta 0:00:24 lr 0.000750	time 1.2257 (2.1990)	loss 4.8822 (4.7656)	grad_norm 1.8207 (1.5845)	
[2022-01-17 23:17:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [14/300][1250/1251]	eta 0:00:02 lr 0.000750	time 1.2087 (2.1934)	loss 5.0946 (4.7639)	grad_norm 1.2766 (1.5837)	
[2022-01-17 23:17:42 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 14 training takes 0:45:44
[2022-01-17 23:18:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.413 (18.413)	Loss 2.0620 (2.0620)	Acc@1 55.664 (55.664)	Acc@5 79.199 (79.199)	
[2022-01-17 23:18:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.640 (3.290)	Loss 2.0729 (2.0976)	Acc@1 55.957 (54.181)	Acc@5 78.125 (78.995)	
[2022-01-17 23:18:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.962 (2.538)	Loss 2.0862 (2.0991)	Acc@1 53.320 (54.367)	Acc@5 79.199 (78.664)	
[2022-01-17 23:18:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.928 (2.206)	Loss 2.1783 (2.1031)	Acc@1 52.539 (54.177)	Acc@5 77.539 (78.456)	
[2022-01-17 23:19:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 5.162 (2.165)	Loss 2.0440 (2.0981)	Acc@1 55.078 (54.185)	Acc@5 78.809 (78.582)	
[2022-01-17 23:19:18 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 54.102 Acc@5 78.530
[2022-01-17 23:19:18 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 54.1%
[2022-01-17 23:19:18 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 54.10%
[2022-01-17 23:19:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][0/1251]	eta 7:41:14 lr 0.000750	time 22.1219 (22.1219)	loss 5.0432 (5.0432)	grad_norm 1.4553 (1.4553)	
[2022-01-17 23:20:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][10/1251]	eta 1:26:27 lr 0.000751	time 2.7898 (4.1799)	loss 4.9842 (4.9506)	grad_norm 1.2969 (1.5350)	
[2022-01-17 23:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][20/1251]	eta 1:08:59 lr 0.000751	time 1.9815 (3.3629)	loss 5.0798 (4.8954)	grad_norm 1.5564 (1.4991)	
[2022-01-17 23:20:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][30/1251]	eta 1:00:51 lr 0.000751	time 1.9919 (2.9903)	loss 5.0260 (4.8239)	grad_norm 2.1419 (1.5654)	
[2022-01-17 23:21:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][40/1251]	eta 0:57:17 lr 0.000752	time 2.6041 (2.8389)	loss 3.9327 (4.7850)	grad_norm 1.2632 (1.5436)	
[2022-01-17 23:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][50/1251]	eta 0:53:46 lr 0.000752	time 2.2613 (2.6869)	loss 5.1684 (4.8075)	grad_norm 2.1854 (1.5708)	
[2022-01-17 23:21:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][60/1251]	eta 0:51:00 lr 0.000753	time 1.8105 (2.5693)	loss 5.1927 (4.7798)	grad_norm 1.7572 (1.5873)	
[2022-01-17 23:22:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][70/1251]	eta 0:49:10 lr 0.000753	time 2.0403 (2.4982)	loss 3.4987 (4.7494)	grad_norm 1.3505 (1.5820)	
[2022-01-17 23:22:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][80/1251]	eta 0:48:06 lr 0.000753	time 2.8491 (2.4646)	loss 4.8864 (4.7303)	grad_norm 1.8720 (1.5860)	
[2022-01-17 23:22:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][90/1251]	eta 0:46:52 lr 0.000754	time 1.7618 (2.4227)	loss 5.1777 (4.7070)	grad_norm 1.6753 (1.6110)	
[2022-01-17 23:23:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][100/1251]	eta 0:45:57 lr 0.000754	time 1.9816 (2.3957)	loss 5.1543 (4.7362)	grad_norm 1.5577 (1.6023)	
[2022-01-17 23:23:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][110/1251]	eta 0:45:11 lr 0.000755	time 1.8849 (2.3762)	loss 4.9138 (4.7266)	grad_norm 1.1512 (1.5930)	
[2022-01-17 23:24:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][120/1251]	eta 0:44:39 lr 0.000755	time 2.5979 (2.3692)	loss 4.7689 (4.7341)	grad_norm 1.7176 (1.5950)	
[2022-01-17 23:24:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][130/1251]	eta 0:44:14 lr 0.000755	time 3.1629 (2.3680)	loss 4.8962 (4.7591)	grad_norm 1.5994 (1.5856)	
[2022-01-17 23:24:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][140/1251]	eta 0:43:36 lr 0.000756	time 2.4263 (2.3550)	loss 4.9866 (4.7589)	grad_norm 1.7430 (1.5797)	
[2022-01-17 23:25:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][150/1251]	eta 0:43:03 lr 0.000756	time 2.4780 (2.3463)	loss 5.0276 (4.7494)	grad_norm 1.7388 (1.5759)	
[2022-01-17 23:25:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][160/1251]	eta 0:42:23 lr 0.000757	time 2.3268 (2.3310)	loss 5.2150 (4.7532)	grad_norm 1.4495 (1.5661)	
[2022-01-17 23:25:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][170/1251]	eta 0:41:41 lr 0.000757	time 1.9582 (2.3144)	loss 5.1645 (4.7469)	grad_norm 1.4514 (1.5693)	
[2022-01-17 23:26:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][180/1251]	eta 0:41:05 lr 0.000757	time 2.2144 (2.3023)	loss 4.7807 (4.7351)	grad_norm 1.3979 (1.5648)	
[2022-01-17 23:26:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][190/1251]	eta 0:40:34 lr 0.000758	time 1.8269 (2.2948)	loss 4.3547 (4.7155)	grad_norm 1.3629 (1.5738)	
[2022-01-17 23:26:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][200/1251]	eta 0:40:10 lr 0.000758	time 2.4519 (2.2935)	loss 5.4049 (4.7184)	grad_norm 1.7722 (1.5794)	
[2022-01-17 23:27:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][210/1251]	eta 0:39:39 lr 0.000759	time 2.6056 (2.2857)	loss 5.4527 (4.7351)	grad_norm 1.7362 (1.5892)	
[2022-01-17 23:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][220/1251]	eta 0:39:08 lr 0.000759	time 1.8654 (2.2778)	loss 4.0049 (4.7266)	grad_norm 2.1260 (1.5877)	
[2022-01-17 23:28:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][230/1251]	eta 0:38:41 lr 0.000759	time 2.1959 (2.2735)	loss 5.0750 (4.7236)	grad_norm 1.7940 (1.5910)	
[2022-01-17 23:28:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][240/1251]	eta 0:38:15 lr 0.000760	time 2.1715 (2.2704)	loss 4.0609 (4.7218)	grad_norm 1.1222 (1.5921)	
[2022-01-17 23:28:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][250/1251]	eta 0:37:49 lr 0.000760	time 2.4978 (2.2672)	loss 4.8100 (4.7216)	grad_norm 1.4057 (1.5827)	
[2022-01-17 23:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][260/1251]	eta 0:37:19 lr 0.000761	time 2.0249 (2.2598)	loss 3.6104 (4.7188)	grad_norm 1.7486 (1.5811)	
[2022-01-17 23:29:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][270/1251]	eta 0:36:57 lr 0.000761	time 1.9671 (2.2604)	loss 4.2613 (4.7132)	grad_norm 1.4869 (1.5842)	
[2022-01-17 23:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][280/1251]	eta 0:36:29 lr 0.000761	time 1.8912 (2.2552)	loss 4.7207 (4.7042)	grad_norm 1.7046 (1.5868)	
[2022-01-17 23:30:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][290/1251]	eta 0:36:03 lr 0.000762	time 2.1562 (2.2517)	loss 4.8800 (4.7062)	grad_norm 1.7747 (1.5847)	
[2022-01-17 23:30:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][300/1251]	eta 0:35:38 lr 0.000762	time 2.8113 (2.2489)	loss 5.2174 (4.7100)	grad_norm 1.2533 (1.5868)	
[2022-01-17 23:30:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][310/1251]	eta 0:35:15 lr 0.000763	time 1.9030 (2.2487)	loss 5.5372 (4.7122)	grad_norm 1.3439 (1.5815)	
[2022-01-17 23:31:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][320/1251]	eta 0:34:48 lr 0.000763	time 1.5870 (2.2430)	loss 4.8194 (4.7189)	grad_norm 1.4937 (1.5825)	
[2022-01-17 23:31:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][330/1251]	eta 0:34:25 lr 0.000763	time 1.6720 (2.2422)	loss 5.5118 (4.7152)	grad_norm 1.4212 (1.5757)	
[2022-01-17 23:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][340/1251]	eta 0:34:04 lr 0.000764	time 2.7583 (2.2441)	loss 5.1542 (4.7229)	grad_norm 1.1215 (1.5689)	
[2022-01-17 23:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][350/1251]	eta 0:33:41 lr 0.000764	time 1.5290 (2.2438)	loss 3.2718 (4.7252)	grad_norm 1.6095 (1.5679)	
[2022-01-17 23:32:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][360/1251]	eta 0:33:16 lr 0.000765	time 2.2547 (2.2407)	loss 5.3766 (4.7243)	grad_norm 1.2387 (1.5688)	
[2022-01-17 23:33:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][370/1251]	eta 0:32:52 lr 0.000765	time 2.1544 (2.2387)	loss 4.5587 (4.7135)	grad_norm 1.5025 (1.5666)	
[2022-01-17 23:33:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][380/1251]	eta 0:32:31 lr 0.000765	time 2.8323 (2.2403)	loss 5.2501 (4.7155)	grad_norm 1.5630 (1.5690)	
[2022-01-17 23:33:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][390/1251]	eta 0:32:09 lr 0.000766	time 1.8764 (2.2406)	loss 4.3045 (4.7147)	grad_norm 1.9070 (1.5662)	
[2022-01-17 23:34:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][400/1251]	eta 0:31:44 lr 0.000766	time 1.8692 (2.2375)	loss 4.3728 (4.7139)	grad_norm 1.3413 (1.5635)	
[2022-01-17 23:34:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][410/1251]	eta 0:31:16 lr 0.000767	time 2.1250 (2.2317)	loss 5.1385 (4.7227)	grad_norm 1.3706 (1.5591)	
[2022-01-17 23:34:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][420/1251]	eta 0:30:54 lr 0.000767	time 2.7989 (2.2317)	loss 4.7283 (4.7244)	grad_norm 1.2130 (1.5562)	
[2022-01-17 23:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][430/1251]	eta 0:30:32 lr 0.000767	time 1.9718 (2.2323)	loss 4.9640 (4.7240)	grad_norm 1.3001 (1.5544)	
[2022-01-17 23:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][440/1251]	eta 0:30:08 lr 0.000768	time 1.6114 (2.2302)	loss 5.2421 (4.7258)	grad_norm 1.5714 (1.5532)	
[2022-01-17 23:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][450/1251]	eta 0:29:45 lr 0.000768	time 1.8521 (2.2294)	loss 5.1678 (4.7310)	grad_norm 1.4733 (1.5491)	
[2022-01-17 23:36:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][460/1251]	eta 0:29:23 lr 0.000769	time 2.2247 (2.2290)	loss 5.0124 (4.7357)	grad_norm 1.6670 (1.5484)	
[2022-01-17 23:36:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][470/1251]	eta 0:29:00 lr 0.000769	time 1.7026 (2.2284)	loss 5.5415 (4.7403)	grad_norm 1.2135 (1.5515)	
[2022-01-17 23:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][480/1251]	eta 0:28:36 lr 0.000769	time 1.5968 (2.2260)	loss 3.6695 (4.7368)	grad_norm 1.2337 (1.5494)	
[2022-01-17 23:37:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][490/1251]	eta 0:28:12 lr 0.000770	time 1.7894 (2.2237)	loss 3.5709 (4.7332)	grad_norm 1.5477 (1.5488)	
[2022-01-17 23:37:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][500/1251]	eta 0:27:47 lr 0.000770	time 1.9493 (2.2207)	loss 4.2472 (4.7311)	grad_norm 1.3929 (1.5482)	
[2022-01-17 23:38:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][510/1251]	eta 0:27:23 lr 0.000771	time 1.8839 (2.2183)	loss 3.3614 (4.7269)	grad_norm 1.1390 (1.5435)	
[2022-01-17 23:38:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][520/1251]	eta 0:27:00 lr 0.000771	time 2.2034 (2.2174)	loss 5.2450 (4.7255)	grad_norm 1.6947 (1.5460)	
[2022-01-17 23:38:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][530/1251]	eta 0:26:36 lr 0.000771	time 1.9620 (2.2148)	loss 4.9563 (4.7283)	grad_norm 1.7046 (1.5460)	
[2022-01-17 23:39:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][540/1251]	eta 0:26:13 lr 0.000772	time 1.7960 (2.2126)	loss 4.4572 (4.7265)	grad_norm 1.2479 (1.5456)	
[2022-01-17 23:39:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][550/1251]	eta 0:25:48 lr 0.000772	time 1.8912 (2.2088)	loss 3.9067 (4.7256)	grad_norm 1.4712 (1.5462)	
[2022-01-17 23:39:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][560/1251]	eta 0:25:26 lr 0.000773	time 2.1492 (2.2085)	loss 3.7760 (4.7212)	grad_norm 1.4521 (1.5452)	
[2022-01-17 23:40:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][570/1251]	eta 0:25:02 lr 0.000773	time 1.2497 (2.2068)	loss 4.8884 (4.7194)	grad_norm 1.5274 (1.5453)	
[2022-01-17 23:40:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][580/1251]	eta 0:24:41 lr 0.000773	time 2.4971 (2.2076)	loss 4.7170 (4.7235)	grad_norm 1.4878 (1.5427)	
[2022-01-17 23:41:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][590/1251]	eta 0:24:19 lr 0.000774	time 2.4102 (2.2077)	loss 3.6953 (4.7225)	grad_norm 1.3900 (1.5414)	
[2022-01-17 23:41:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][600/1251]	eta 0:23:59 lr 0.000774	time 2.9265 (2.2116)	loss 4.3757 (4.7251)	grad_norm 1.2782 (1.5415)	
[2022-01-17 23:41:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][610/1251]	eta 0:23:38 lr 0.000775	time 2.2907 (2.2134)	loss 5.2342 (4.7215)	grad_norm 1.4936 (1.5410)	
[2022-01-17 23:42:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][620/1251]	eta 0:23:17 lr 0.000775	time 3.1273 (2.2154)	loss 3.9500 (4.7181)	grad_norm 1.4419 (1.5401)	
[2022-01-17 23:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][630/1251]	eta 0:22:56 lr 0.000775	time 2.0408 (2.2167)	loss 4.4883 (4.7128)	grad_norm 1.3985 (1.5402)	
[2022-01-17 23:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][640/1251]	eta 0:22:35 lr 0.000776	time 2.2051 (2.2184)	loss 5.0059 (4.7160)	grad_norm 1.3054 (1.5387)	
[2022-01-17 23:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][650/1251]	eta 0:22:11 lr 0.000776	time 1.8470 (2.2153)	loss 5.3694 (4.7183)	grad_norm 1.1863 (1.5375)	
[2022-01-17 23:43:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][660/1251]	eta 0:21:48 lr 0.000777	time 2.6406 (2.2135)	loss 4.7757 (4.7238)	grad_norm 1.4372 (1.5372)	
[2022-01-17 23:44:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][670/1251]	eta 0:21:24 lr 0.000777	time 2.2238 (2.2104)	loss 5.0250 (4.7238)	grad_norm 1.4180 (1.5375)	
[2022-01-17 23:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][680/1251]	eta 0:21:01 lr 0.000777	time 2.2486 (2.2085)	loss 4.0113 (4.7244)	grad_norm 1.9440 (1.5384)	
[2022-01-17 23:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][690/1251]	eta 0:20:39 lr 0.000778	time 2.4079 (2.2099)	loss 4.3430 (4.7265)	grad_norm 1.2410 (1.5350)	
[2022-01-17 23:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][700/1251]	eta 0:20:18 lr 0.000778	time 1.8146 (2.2114)	loss 5.1150 (4.7270)	grad_norm 1.2952 (1.5346)	
[2022-01-17 23:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][710/1251]	eta 0:19:57 lr 0.000779	time 3.0411 (2.2126)	loss 4.9784 (4.7275)	grad_norm 1.7790 (1.5372)	
[2022-01-17 23:45:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][720/1251]	eta 0:19:35 lr 0.000779	time 3.3505 (2.2140)	loss 5.2845 (4.7298)	grad_norm 1.9409 (1.5400)	
[2022-01-17 23:46:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][730/1251]	eta 0:19:11 lr 0.000779	time 2.1741 (2.2101)	loss 5.0422 (4.7293)	grad_norm 1.4690 (1.5394)	
[2022-01-17 23:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][740/1251]	eta 0:18:48 lr 0.000780	time 2.0774 (2.2078)	loss 4.0719 (4.7268)	grad_norm 1.3436 (1.5376)	
[2022-01-17 23:46:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][750/1251]	eta 0:18:24 lr 0.000780	time 2.1620 (2.2050)	loss 4.8930 (4.7262)	grad_norm 1.4095 (1.5405)	
[2022-01-17 23:47:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][760/1251]	eta 0:18:01 lr 0.000781	time 2.2039 (2.2035)	loss 5.0866 (4.7261)	grad_norm 1.4487 (1.5408)	
[2022-01-17 23:47:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][770/1251]	eta 0:17:40 lr 0.000781	time 2.6202 (2.2048)	loss 5.0125 (4.7264)	grad_norm 1.7388 (1.5404)	
[2022-01-17 23:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][780/1251]	eta 0:17:17 lr 0.000781	time 1.8282 (2.2033)	loss 5.4831 (4.7273)	grad_norm 1.6174 (1.5410)	
[2022-01-17 23:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][790/1251]	eta 0:16:55 lr 0.000782	time 2.2156 (2.2031)	loss 3.8902 (4.7255)	grad_norm 1.6103 (1.5431)	
[2022-01-17 23:48:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][800/1251]	eta 0:16:34 lr 0.000782	time 1.9071 (2.2058)	loss 4.5689 (4.7270)	grad_norm 1.2196 (1.5416)	
[2022-01-17 23:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][810/1251]	eta 0:16:13 lr 0.000783	time 1.8323 (2.2079)	loss 3.7356 (4.7281)	grad_norm 1.0502 (1.5404)	
[2022-01-17 23:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][820/1251]	eta 0:15:51 lr 0.000783	time 1.8985 (2.2087)	loss 4.2185 (4.7285)	grad_norm 1.8320 (1.5421)	
[2022-01-17 23:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][830/1251]	eta 0:15:29 lr 0.000783	time 2.4405 (2.2075)	loss 4.9247 (4.7300)	grad_norm 1.2941 (1.5417)	
[2022-01-17 23:50:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][840/1251]	eta 0:15:06 lr 0.000784	time 2.1709 (2.2063)	loss 5.1387 (4.7308)	grad_norm 1.2492 (1.5410)	
[2022-01-17 23:50:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][850/1251]	eta 0:14:44 lr 0.000784	time 1.6952 (2.2046)	loss 4.0684 (4.7295)	grad_norm 1.9011 (1.5395)	
[2022-01-17 23:50:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][860/1251]	eta 0:14:21 lr 0.000785	time 1.8549 (2.2042)	loss 5.3766 (4.7306)	grad_norm 1.4766 (1.5411)	
[2022-01-17 23:51:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][870/1251]	eta 0:13:59 lr 0.000785	time 2.1326 (2.2041)	loss 3.7143 (4.7287)	grad_norm 1.5871 (1.5409)	
[2022-01-17 23:51:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][880/1251]	eta 0:13:37 lr 0.000785	time 1.8768 (2.2029)	loss 4.5595 (4.7282)	grad_norm 1.3594 (1.5384)	
[2022-01-17 23:51:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][890/1251]	eta 0:13:14 lr 0.000786	time 2.1389 (2.2012)	loss 3.6451 (4.7242)	grad_norm 1.6052 (1.5380)	
[2022-01-17 23:52:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][900/1251]	eta 0:12:52 lr 0.000786	time 1.9006 (2.2011)	loss 4.1865 (4.7222)	grad_norm 1.3232 (1.5384)	
[2022-01-17 23:52:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][910/1251]	eta 0:12:30 lr 0.000787	time 2.0903 (2.2022)	loss 5.3957 (4.7228)	grad_norm 1.4880 (1.5362)	
[2022-01-17 23:53:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][920/1251]	eta 0:12:08 lr 0.000787	time 2.4954 (2.2017)	loss 5.1400 (4.7233)	grad_norm 1.5673 (1.5370)	
[2022-01-17 23:53:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][930/1251]	eta 0:11:46 lr 0.000787	time 2.1413 (2.2021)	loss 5.0849 (4.7219)	grad_norm 1.6249 (1.5364)	
[2022-01-17 23:53:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][940/1251]	eta 0:11:24 lr 0.000788	time 2.2107 (2.2021)	loss 5.1830 (4.7247)	grad_norm 1.6152 (1.5367)	
[2022-01-17 23:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][950/1251]	eta 0:11:02 lr 0.000788	time 2.2069 (2.2023)	loss 3.7856 (4.7208)	grad_norm 1.9300 (1.5361)	
[2022-01-17 23:54:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][960/1251]	eta 0:10:40 lr 0.000789	time 1.7000 (2.2016)	loss 4.9942 (4.7229)	grad_norm 1.0498 (1.5334)	
[2022-01-17 23:54:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][970/1251]	eta 0:10:18 lr 0.000789	time 1.8333 (2.2000)	loss 5.4014 (4.7240)	grad_norm 1.4149 (1.5308)	
[2022-01-17 23:55:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][980/1251]	eta 0:09:55 lr 0.000789	time 1.8262 (2.1990)	loss 4.3364 (4.7229)	grad_norm 1.4648 (1.5295)	
[2022-01-17 23:55:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][990/1251]	eta 0:09:33 lr 0.000790	time 2.1182 (2.1981)	loss 4.9662 (4.7228)	grad_norm 1.5507 (1.5284)	
[2022-01-17 23:55:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1000/1251]	eta 0:09:11 lr 0.000790	time 2.0085 (2.1976)	loss 5.0817 (4.7234)	grad_norm 1.3357 (1.5269)	
[2022-01-17 23:56:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1010/1251]	eta 0:08:49 lr 0.000791	time 1.9225 (2.1967)	loss 5.4245 (4.7213)	grad_norm 1.3141 (1.5279)	
[2022-01-17 23:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1020/1251]	eta 0:08:27 lr 0.000791	time 2.2466 (2.1960)	loss 4.3593 (4.7189)	grad_norm 1.5300 (1.5269)	
[2022-01-17 23:57:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1030/1251]	eta 0:08:05 lr 0.000791	time 2.7264 (2.1963)	loss 4.9632 (4.7182)	grad_norm 1.5421 (1.5292)	
[2022-01-17 23:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1040/1251]	eta 0:07:43 lr 0.000792	time 2.6393 (2.1972)	loss 4.0793 (4.7173)	grad_norm 1.6522 (1.5305)	
[2022-01-17 23:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1050/1251]	eta 0:07:21 lr 0.000792	time 1.7292 (2.1961)	loss 3.8503 (4.7145)	grad_norm 1.6052 (1.5303)	
[2022-01-17 23:58:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1060/1251]	eta 0:06:59 lr 0.000793	time 2.1376 (2.1974)	loss 3.3542 (4.7126)	grad_norm 1.2799 (1.5290)	
[2022-01-17 23:58:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1070/1251]	eta 0:06:37 lr 0.000793	time 2.2145 (2.1986)	loss 4.3818 (4.7141)	grad_norm 1.3367 (1.5277)	
[2022-01-17 23:58:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1080/1251]	eta 0:06:15 lr 0.000793	time 2.5319 (2.1986)	loss 3.7696 (4.7148)	grad_norm 1.3766 (1.5266)	
[2022-01-17 23:59:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1090/1251]	eta 0:05:53 lr 0.000794	time 2.2628 (2.1986)	loss 4.5053 (4.7116)	grad_norm 1.4705 (1.5262)	
[2022-01-17 23:59:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1100/1251]	eta 0:05:31 lr 0.000794	time 1.8852 (2.1981)	loss 5.2643 (4.7136)	grad_norm 1.5371 (1.5258)	
[2022-01-18 00:00:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1110/1251]	eta 0:05:09 lr 0.000795	time 2.1851 (2.1976)	loss 4.1049 (4.7130)	grad_norm 1.3614 (1.5250)	
[2022-01-18 00:00:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1120/1251]	eta 0:04:47 lr 0.000795	time 2.4103 (2.1973)	loss 4.8622 (4.7141)	grad_norm 1.7617 (1.5254)	
[2022-01-18 00:00:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1130/1251]	eta 0:04:25 lr 0.000795	time 2.2782 (2.1971)	loss 5.0689 (4.7148)	grad_norm 2.0358 (1.5256)	
[2022-01-18 00:01:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1140/1251]	eta 0:04:03 lr 0.000796	time 1.7267 (2.1969)	loss 3.6810 (4.7141)	grad_norm 1.3528 (1.5246)	
[2022-01-18 00:01:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1150/1251]	eta 0:03:42 lr 0.000796	time 3.5875 (2.1992)	loss 5.6370 (4.7147)	grad_norm 1.4846 (1.5241)	
[2022-01-18 00:01:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1160/1251]	eta 0:03:20 lr 0.000797	time 2.1837 (2.1985)	loss 5.6614 (4.7157)	grad_norm 1.1985 (1.5229)	
[2022-01-18 00:02:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1170/1251]	eta 0:02:57 lr 0.000797	time 1.7890 (2.1969)	loss 5.3195 (4.7170)	grad_norm 1.6370 (1.5228)	
[2022-01-18 00:02:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1180/1251]	eta 0:02:35 lr 0.000797	time 2.2381 (2.1967)	loss 5.0002 (4.7161)	grad_norm 1.5145 (1.5241)	
[2022-01-18 00:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1190/1251]	eta 0:02:13 lr 0.000798	time 2.2230 (2.1954)	loss 5.3776 (4.7171)	grad_norm 1.4851 (1.5235)	
[2022-01-18 00:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1200/1251]	eta 0:01:51 lr 0.000798	time 2.2581 (2.1949)	loss 5.6512 (4.7167)	grad_norm 1.6110 (1.5238)	
[2022-01-18 00:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1210/1251]	eta 0:01:29 lr 0.000799	time 1.7863 (2.1938)	loss 5.3396 (4.7149)	grad_norm 1.4388 (1.5230)	
[2022-01-18 00:03:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1220/1251]	eta 0:01:08 lr 0.000799	time 1.7960 (2.1937)	loss 4.9137 (4.7133)	grad_norm 1.2842 (1.5219)	
[2022-01-18 00:04:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1230/1251]	eta 0:00:46 lr 0.000799	time 3.0062 (2.1941)	loss 4.5071 (4.7127)	grad_norm 1.3732 (1.5223)	
[2022-01-18 00:04:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1240/1251]	eta 0:00:24 lr 0.000800	time 2.4589 (2.1950)	loss 4.2409 (4.7133)	grad_norm 1.8985 (1.5225)	
[2022-01-18 00:04:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [15/300][1250/1251]	eta 0:00:02 lr 0.000800	time 1.1569 (2.1899)	loss 5.2142 (4.7119)	grad_norm 1.5014 (1.5217)	
[2022-01-18 00:04:58 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 15 training takes 0:45:39
[2022-01-18 00:05:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.023 (18.023)	Loss 2.0922 (2.0922)	Acc@1 52.832 (52.832)	Acc@5 78.613 (78.613)	
[2022-01-18 00:05:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.580 (3.284)	Loss 2.0884 (2.0462)	Acc@1 53.125 (55.016)	Acc@5 78.027 (79.474)	
[2022-01-18 00:05:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.211 (2.574)	Loss 1.9919 (2.0530)	Acc@1 55.566 (54.757)	Acc@5 80.273 (79.455)	
[2022-01-18 00:06:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.910 (2.231)	Loss 2.0257 (2.0552)	Acc@1 53.516 (54.653)	Acc@5 79.883 (79.404)	
[2022-01-18 00:06:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.263 (2.149)	Loss 2.1249 (2.0538)	Acc@1 52.637 (54.761)	Acc@5 78.223 (79.402)	
[2022-01-18 00:06:33 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 54.802 Acc@5 79.334
[2022-01-18 00:06:33 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 54.8%
[2022-01-18 00:06:33 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 54.80%
[2022-01-18 00:06:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][0/1251]	eta 7:31:26 lr 0.000800	time 21.6517 (21.6517)	loss 4.7752 (4.7752)	grad_norm 1.7346 (1.7346)	
[2022-01-18 00:07:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][10/1251]	eta 1:22:45 lr 0.000801	time 2.2046 (4.0012)	loss 4.7257 (4.6383)	grad_norm 1.4727 (1.5154)	
[2022-01-18 00:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][20/1251]	eta 1:09:02 lr 0.000801	time 2.4603 (3.3654)	loss 4.1866 (4.8034)	grad_norm 1.5114 (1.4647)	
[2022-01-18 00:08:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][30/1251]	eta 1:00:28 lr 0.000801	time 1.8554 (2.9713)	loss 4.7825 (4.8131)	grad_norm 2.2937 (1.5042)	
[2022-01-18 00:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][40/1251]	eta 0:57:19 lr 0.000802	time 3.8714 (2.8403)	loss 4.3637 (4.7984)	grad_norm 1.3984 (1.5362)	
[2022-01-18 00:08:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][50/1251]	eta 0:54:45 lr 0.000802	time 2.1084 (2.7357)	loss 3.6492 (4.7865)	grad_norm 1.3966 (1.5081)	
[2022-01-18 00:09:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][60/1251]	eta 0:52:41 lr 0.000803	time 2.1650 (2.6548)	loss 5.3940 (4.8002)	grad_norm 1.5809 (1.5035)	
[2022-01-18 00:09:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][70/1251]	eta 0:50:14 lr 0.000803	time 1.8395 (2.5527)	loss 3.8775 (4.7873)	grad_norm 1.2616 (1.5085)	
[2022-01-18 00:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][80/1251]	eta 0:48:33 lr 0.000803	time 2.5292 (2.4877)	loss 4.6067 (4.8047)	grad_norm 1.2733 (1.4895)	
[2022-01-18 00:10:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][90/1251]	eta 0:47:19 lr 0.000804	time 2.8317 (2.4460)	loss 3.9986 (4.7904)	grad_norm 1.4473 (1.4940)	
[2022-01-18 00:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][100/1251]	eta 0:46:20 lr 0.000804	time 1.8278 (2.4160)	loss 4.5203 (4.7542)	grad_norm 1.3711 (1.5004)	
[2022-01-18 00:11:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][110/1251]	eta 0:45:37 lr 0.000805	time 2.1620 (2.3994)	loss 4.8107 (4.7408)	grad_norm 1.6758 (1.4943)	
[2022-01-18 00:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][120/1251]	eta 0:44:54 lr 0.000805	time 2.9236 (2.3824)	loss 4.6616 (4.7206)	grad_norm 1.8821 (1.5026)	
[2022-01-18 00:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][130/1251]	eta 0:44:28 lr 0.000805	time 3.0697 (2.3802)	loss 4.6617 (4.7166)	grad_norm 1.4861 (1.5020)	
[2022-01-18 00:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][140/1251]	eta 0:43:59 lr 0.000806	time 2.5065 (2.3756)	loss 4.6478 (4.7238)	grad_norm 1.4686 (1.5063)	
[2022-01-18 00:12:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][150/1251]	eta 0:43:11 lr 0.000806	time 1.9452 (2.3538)	loss 5.0647 (4.7109)	grad_norm 2.0187 (1.5166)	
[2022-01-18 00:12:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][160/1251]	eta 0:42:36 lr 0.000807	time 3.4615 (2.3429)	loss 4.0214 (4.7045)	grad_norm 1.2511 (1.5190)	
[2022-01-18 00:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][170/1251]	eta 0:41:55 lr 0.000807	time 1.8536 (2.3269)	loss 5.4215 (4.6811)	grad_norm 1.7162 (1.5151)	
[2022-01-18 00:13:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][180/1251]	eta 0:41:26 lr 0.000807	time 2.0436 (2.3215)	loss 4.0523 (4.6766)	grad_norm 2.6702 (1.5175)	
[2022-01-18 00:13:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][190/1251]	eta 0:40:53 lr 0.000808	time 1.4750 (2.3125)	loss 5.5216 (4.6739)	grad_norm 1.2621 (1.5176)	
[2022-01-18 00:14:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][200/1251]	eta 0:40:25 lr 0.000808	time 2.5398 (2.3083)	loss 5.0398 (4.6702)	grad_norm 1.6577 (1.5147)	
[2022-01-18 00:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][210/1251]	eta 0:39:59 lr 0.000809	time 2.2005 (2.3047)	loss 5.3272 (4.6764)	grad_norm 1.1173 (1.5192)	
[2022-01-18 00:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][220/1251]	eta 0:39:31 lr 0.000809	time 2.0051 (2.3006)	loss 4.9266 (4.6767)	grad_norm 1.5678 (1.5188)	
[2022-01-18 00:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][230/1251]	eta 0:39:08 lr 0.000809	time 2.4414 (2.2999)	loss 4.5721 (4.6831)	grad_norm 1.1911 (1.5115)	
[2022-01-18 00:15:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][240/1251]	eta 0:38:40 lr 0.000810	time 2.7281 (2.2952)	loss 4.9054 (4.6666)	grad_norm 1.4637 (1.5121)	
[2022-01-18 00:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][250/1251]	eta 0:38:11 lr 0.000810	time 2.8508 (2.2891)	loss 5.0074 (4.6671)	grad_norm 1.6528 (1.5174)	
[2022-01-18 00:16:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][260/1251]	eta 0:37:35 lr 0.000811	time 1.9140 (2.2760)	loss 5.0988 (4.6663)	grad_norm 1.4828 (1.5147)	
[2022-01-18 00:16:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][270/1251]	eta 0:37:06 lr 0.000811	time 2.1226 (2.2697)	loss 4.8996 (4.6761)	grad_norm 1.5292 (1.5098)	
[2022-01-18 00:17:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][280/1251]	eta 0:36:40 lr 0.000811	time 1.9271 (2.2665)	loss 5.5425 (4.6873)	grad_norm 1.6128 (1.5102)	
[2022-01-18 00:17:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][290/1251]	eta 0:36:17 lr 0.000812	time 3.3281 (2.2661)	loss 3.8859 (4.6736)	grad_norm 1.6924 (1.5074)	
[2022-01-18 00:17:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][300/1251]	eta 0:35:51 lr 0.000812	time 1.9293 (2.2625)	loss 4.8007 (4.6763)	grad_norm 1.2699 (1.5034)	
[2022-01-18 00:18:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][310/1251]	eta 0:35:27 lr 0.000813	time 2.1180 (2.2605)	loss 4.7074 (4.6732)	grad_norm 1.4016 (1.5051)	
[2022-01-18 00:18:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][320/1251]	eta 0:35:06 lr 0.000813	time 3.4591 (2.2624)	loss 5.3798 (4.6796)	grad_norm 1.4070 (1.5053)	
[2022-01-18 00:19:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][330/1251]	eta 0:34:42 lr 0.000813	time 3.3213 (2.2615)	loss 3.5930 (4.6677)	grad_norm 1.6103 (1.5038)	
[2022-01-18 00:19:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][340/1251]	eta 0:34:16 lr 0.000814	time 2.3127 (2.2572)	loss 3.9799 (4.6622)	grad_norm 1.6449 (1.5014)	
[2022-01-18 00:19:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][350/1251]	eta 0:33:50 lr 0.000814	time 2.8697 (2.2539)	loss 4.9509 (4.6609)	grad_norm 1.3487 (1.4995)	
[2022-01-18 00:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][360/1251]	eta 0:33:26 lr 0.000815	time 2.4403 (2.2525)	loss 4.5140 (4.6646)	grad_norm 1.6755 (1.5051)	
[2022-01-18 00:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][370/1251]	eta 0:32:58 lr 0.000815	time 1.6073 (2.2463)	loss 4.4713 (4.6623)	grad_norm 2.5470 (1.5074)	
[2022-01-18 00:20:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][380/1251]	eta 0:32:37 lr 0.000815	time 2.2724 (2.2471)	loss 5.0453 (4.6652)	grad_norm 1.3067 (1.5051)	
[2022-01-18 00:21:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][390/1251]	eta 0:32:12 lr 0.000816	time 2.1911 (2.2451)	loss 5.0092 (4.6607)	grad_norm 1.3904 (1.5037)	
[2022-01-18 00:21:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][400/1251]	eta 0:31:49 lr 0.000816	time 2.7942 (2.2437)	loss 4.8799 (4.6593)	grad_norm 1.7756 (1.5048)	
[2022-01-18 00:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][410/1251]	eta 0:31:23 lr 0.000817	time 1.9181 (2.2400)	loss 4.5579 (4.6665)	grad_norm 1.7455 (1.5054)	
[2022-01-18 00:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][420/1251]	eta 0:31:00 lr 0.000817	time 2.5482 (2.2386)	loss 4.6435 (4.6689)	grad_norm 1.1594 (1.5037)	
[2022-01-18 00:22:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][430/1251]	eta 0:30:37 lr 0.000817	time 2.1094 (2.2377)	loss 4.6973 (4.6638)	grad_norm 1.8083 (1.5046)	
[2022-01-18 00:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][440/1251]	eta 0:30:13 lr 0.000818	time 2.2868 (2.2365)	loss 5.4182 (4.6639)	grad_norm 1.3860 (1.5008)	
[2022-01-18 00:23:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][450/1251]	eta 0:29:50 lr 0.000818	time 1.6393 (2.2357)	loss 4.6662 (4.6647)	grad_norm 1.4017 (1.4999)	
[2022-01-18 00:23:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][460/1251]	eta 0:29:26 lr 0.000819	time 2.2178 (2.2335)	loss 5.7059 (4.6678)	grad_norm 1.6076 (1.5035)	
[2022-01-18 00:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][470/1251]	eta 0:29:05 lr 0.000819	time 2.4716 (2.2352)	loss 4.6578 (4.6721)	grad_norm 1.8497 (1.5057)	
[2022-01-18 00:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][480/1251]	eta 0:28:44 lr 0.000819	time 2.5079 (2.2369)	loss 5.0259 (4.6698)	grad_norm 1.5536 (1.5064)	
[2022-01-18 00:24:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][490/1251]	eta 0:28:20 lr 0.000820	time 1.7534 (2.2340)	loss 5.0782 (4.6709)	grad_norm 1.2640 (1.5037)	
[2022-01-18 00:25:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][500/1251]	eta 0:27:54 lr 0.000820	time 1.8807 (2.2293)	loss 4.9907 (4.6714)	grad_norm 1.6683 (1.5051)	
[2022-01-18 00:25:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][510/1251]	eta 0:27:30 lr 0.000821	time 1.9184 (2.2274)	loss 5.1303 (4.6717)	grad_norm 1.2359 (1.5038)	
[2022-01-18 00:25:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][520/1251]	eta 0:27:07 lr 0.000821	time 2.5479 (2.2264)	loss 5.2289 (4.6727)	grad_norm 1.4903 (1.5018)	
[2022-01-18 00:26:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][530/1251]	eta 0:26:46 lr 0.000821	time 2.0866 (2.2282)	loss 5.1166 (4.6742)	grad_norm 1.3185 (1.5012)	
[2022-01-18 00:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][540/1251]	eta 0:26:24 lr 0.000822	time 2.8099 (2.2279)	loss 4.0114 (4.6705)	grad_norm 1.4924 (1.5038)	
[2022-01-18 00:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][550/1251]	eta 0:26:00 lr 0.000822	time 1.6026 (2.2254)	loss 5.0743 (4.6745)	grad_norm 1.3309 (1.5021)	
[2022-01-18 00:27:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][560/1251]	eta 0:25:36 lr 0.000823	time 2.6535 (2.2235)	loss 5.5393 (4.6757)	grad_norm 1.4501 (1.5012)	
[2022-01-18 00:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][570/1251]	eta 0:25:12 lr 0.000823	time 1.5924 (2.2206)	loss 4.8889 (4.6796)	grad_norm 1.4793 (1.4990)	
[2022-01-18 00:28:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][580/1251]	eta 0:24:49 lr 0.000823	time 2.1860 (2.2197)	loss 4.8432 (4.6788)	grad_norm 1.4489 (1.4990)	
[2022-01-18 00:28:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][590/1251]	eta 0:24:26 lr 0.000824	time 2.1588 (2.2184)	loss 4.3723 (4.6807)	grad_norm 1.6948 (1.5000)	
[2022-01-18 00:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][600/1251]	eta 0:24:03 lr 0.000824	time 1.9643 (2.2173)	loss 5.0151 (4.6867)	grad_norm 1.2146 (1.5010)	
[2022-01-18 00:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][610/1251]	eta 0:23:40 lr 0.000825	time 1.8873 (2.2158)	loss 4.0862 (4.6862)	grad_norm 1.5426 (1.5012)	
[2022-01-18 00:29:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][620/1251]	eta 0:23:18 lr 0.000825	time 2.4974 (2.2156)	loss 4.1948 (4.6841)	grad_norm 1.2701 (1.4988)	
[2022-01-18 00:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][630/1251]	eta 0:22:56 lr 0.000825	time 2.5329 (2.2166)	loss 5.2073 (4.6829)	grad_norm 1.7093 (1.4993)	
[2022-01-18 00:30:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][640/1251]	eta 0:22:34 lr 0.000826	time 2.1338 (2.2172)	loss 5.2047 (4.6864)	grad_norm 1.1537 (1.4969)	
[2022-01-18 00:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][650/1251]	eta 0:22:13 lr 0.000826	time 2.1671 (2.2191)	loss 3.6127 (4.6852)	grad_norm 1.6961 (1.4950)	
[2022-01-18 00:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][660/1251]	eta 0:21:51 lr 0.000827	time 1.9673 (2.2195)	loss 5.4492 (4.6859)	grad_norm 1.2568 (1.4935)	
[2022-01-18 00:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][670/1251]	eta 0:21:28 lr 0.000827	time 1.8882 (2.2176)	loss 4.6144 (4.6865)	grad_norm 1.5168 (1.4933)	
[2022-01-18 00:31:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][680/1251]	eta 0:21:04 lr 0.000827	time 2.0153 (2.2150)	loss 4.8640 (4.6878)	grad_norm 1.2456 (1.4937)	
[2022-01-18 00:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][690/1251]	eta 0:20:42 lr 0.000828	time 2.0741 (2.2153)	loss 4.1631 (4.6870)	grad_norm 1.5893 (1.4921)	
[2022-01-18 00:32:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][700/1251]	eta 0:20:20 lr 0.000828	time 2.3303 (2.2155)	loss 5.0128 (4.6875)	grad_norm 1.5892 (1.4919)	
[2022-01-18 00:32:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][710/1251]	eta 0:19:58 lr 0.000829	time 1.9223 (2.2148)	loss 5.1033 (4.6876)	grad_norm 1.5411 (1.4903)	
[2022-01-18 00:33:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][720/1251]	eta 0:19:36 lr 0.000829	time 2.8373 (2.2151)	loss 4.7246 (4.6844)	grad_norm 1.2046 (1.4891)	
[2022-01-18 00:33:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][730/1251]	eta 0:19:13 lr 0.000829	time 2.4613 (2.2148)	loss 4.0336 (4.6853)	grad_norm 1.5675 (1.4903)	
[2022-01-18 00:33:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][740/1251]	eta 0:18:52 lr 0.000830	time 2.6283 (2.2153)	loss 5.1337 (4.6858)	grad_norm 1.6760 (1.4902)	
[2022-01-18 00:34:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][750/1251]	eta 0:18:29 lr 0.000830	time 2.2173 (2.2144)	loss 4.3715 (4.6853)	grad_norm 1.3727 (1.4895)	
[2022-01-18 00:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][760/1251]	eta 0:18:06 lr 0.000831	time 1.8743 (2.2136)	loss 4.8570 (4.6854)	grad_norm 1.2252 (1.4876)	
[2022-01-18 00:35:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][770/1251]	eta 0:17:45 lr 0.000831	time 2.1418 (2.2146)	loss 5.2249 (4.6885)	grad_norm 1.7310 (1.4861)	
[2022-01-18 00:35:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][780/1251]	eta 0:17:21 lr 0.000831	time 1.5660 (2.2114)	loss 3.7261 (4.6849)	grad_norm 1.2215 (1.4885)	
[2022-01-18 00:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][790/1251]	eta 0:16:58 lr 0.000832	time 1.9342 (2.2085)	loss 4.4402 (4.6837)	grad_norm 1.6990 (1.4885)	
[2022-01-18 00:36:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][800/1251]	eta 0:16:35 lr 0.000832	time 2.0372 (2.2069)	loss 4.9858 (4.6858)	grad_norm 1.1821 (1.4888)	
[2022-01-18 00:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][810/1251]	eta 0:16:13 lr 0.000833	time 2.1840 (2.2068)	loss 4.1766 (4.6845)	grad_norm 1.3103 (1.4871)	
[2022-01-18 00:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][820/1251]	eta 0:15:51 lr 0.000833	time 2.3520 (2.2072)	loss 5.6634 (4.6869)	grad_norm 1.8244 (1.4867)	
[2022-01-18 00:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][830/1251]	eta 0:15:29 lr 0.000833	time 1.9131 (2.2082)	loss 3.9900 (4.6884)	grad_norm 1.0761 (1.4856)	
[2022-01-18 00:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][840/1251]	eta 0:15:08 lr 0.000834	time 2.3910 (2.2102)	loss 5.0751 (4.6871)	grad_norm 1.2012 (1.4849)	
[2022-01-18 00:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][850/1251]	eta 0:14:46 lr 0.000834	time 2.2166 (2.2095)	loss 3.5651 (4.6822)	grad_norm 1.6566 (1.4836)	
[2022-01-18 00:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][860/1251]	eta 0:14:22 lr 0.000835	time 1.5783 (2.2070)	loss 5.0023 (4.6837)	grad_norm 1.2278 (1.4842)	
[2022-01-18 00:38:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][870/1251]	eta 0:14:00 lr 0.000835	time 1.5898 (2.2056)	loss 4.6957 (4.6799)	grad_norm 1.1157 (1.4826)	
[2022-01-18 00:38:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][880/1251]	eta 0:13:38 lr 0.000835	time 2.1894 (2.2053)	loss 5.0290 (4.6813)	grad_norm 1.1673 (1.4823)	
[2022-01-18 00:39:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][890/1251]	eta 0:13:16 lr 0.000836	time 1.4632 (2.2050)	loss 4.2776 (4.6818)	grad_norm 2.0065 (1.4824)	
[2022-01-18 00:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][900/1251]	eta 0:12:54 lr 0.000836	time 1.6698 (2.2054)	loss 4.8943 (4.6820)	grad_norm 1.0777 (1.4823)	
[2022-01-18 00:40:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][910/1251]	eta 0:12:32 lr 0.000837	time 1.6347 (2.2071)	loss 3.5183 (4.6811)	grad_norm 1.3184 (1.4809)	
[2022-01-18 00:40:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][920/1251]	eta 0:12:11 lr 0.000837	time 2.7742 (2.2094)	loss 4.5815 (4.6801)	grad_norm 1.6887 (1.4803)	
[2022-01-18 00:40:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][930/1251]	eta 0:11:48 lr 0.000837	time 1.5084 (2.2077)	loss 3.7734 (4.6758)	grad_norm 1.7159 (1.4809)	
[2022-01-18 00:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][940/1251]	eta 0:11:25 lr 0.000838	time 1.8912 (2.2058)	loss 4.5618 (4.6788)	grad_norm 1.7319 (1.4806)	
[2022-01-18 00:41:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][950/1251]	eta 0:11:03 lr 0.000838	time 2.2850 (2.2032)	loss 5.0525 (4.6782)	grad_norm 1.3955 (1.4803)	
[2022-01-18 00:41:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][960/1251]	eta 0:10:41 lr 0.000839	time 1.7348 (2.2029)	loss 3.6373 (4.6757)	grad_norm 1.4985 (1.4815)	
[2022-01-18 00:42:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][970/1251]	eta 0:10:18 lr 0.000839	time 2.0992 (2.2014)	loss 4.5816 (4.6743)	grad_norm 1.4777 (1.4805)	
[2022-01-18 00:42:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][980/1251]	eta 0:09:56 lr 0.000839	time 1.8463 (2.2012)	loss 4.8170 (4.6760)	grad_norm 1.3426 (1.4795)	
[2022-01-18 00:42:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][990/1251]	eta 0:09:34 lr 0.000840	time 2.1727 (2.2013)	loss 4.6706 (4.6766)	grad_norm 2.1142 (1.4794)	
[2022-01-18 00:43:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1000/1251]	eta 0:09:12 lr 0.000840	time 2.2207 (2.2009)	loss 4.9863 (4.6746)	grad_norm 1.3872 (1.4790)	
[2022-01-18 00:43:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1010/1251]	eta 0:08:50 lr 0.000841	time 1.9585 (2.2008)	loss 5.3237 (4.6727)	grad_norm 1.4890 (1.4784)	
[2022-01-18 00:44:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1020/1251]	eta 0:08:28 lr 0.000841	time 2.1090 (2.2008)	loss 5.0852 (4.6726)	grad_norm 1.2842 (1.4793)	
[2022-01-18 00:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1030/1251]	eta 0:08:06 lr 0.000841	time 1.7744 (2.2031)	loss 4.2300 (4.6729)	grad_norm 1.6222 (1.4780)	
[2022-01-18 00:44:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1040/1251]	eta 0:07:44 lr 0.000842	time 2.8233 (2.2036)	loss 4.8987 (4.6710)	grad_norm 1.8074 (1.4784)	
[2022-01-18 00:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1050/1251]	eta 0:07:22 lr 0.000842	time 1.9023 (2.2019)	loss 5.3604 (4.6722)	grad_norm 1.4868 (1.4766)	
[2022-01-18 00:45:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1060/1251]	eta 0:07:00 lr 0.000843	time 2.3479 (2.2005)	loss 4.9435 (4.6698)	grad_norm 2.0075 (1.4777)	
[2022-01-18 00:45:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1070/1251]	eta 0:06:38 lr 0.000843	time 2.2088 (2.1994)	loss 5.4066 (4.6695)	grad_norm 1.2370 (1.4772)	
[2022-01-18 00:46:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1080/1251]	eta 0:06:15 lr 0.000843	time 2.6147 (2.1987)	loss 4.8334 (4.6682)	grad_norm 2.0402 (1.4782)	
[2022-01-18 00:46:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1090/1251]	eta 0:05:53 lr 0.000844	time 2.9079 (2.1983)	loss 3.6419 (4.6674)	grad_norm 1.6636 (1.4778)	
[2022-01-18 00:46:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1100/1251]	eta 0:05:31 lr 0.000844	time 2.5771 (2.1977)	loss 4.8405 (4.6661)	grad_norm 1.1488 (1.4767)	
[2022-01-18 00:47:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1110/1251]	eta 0:05:09 lr 0.000845	time 1.5318 (2.1972)	loss 4.5289 (4.6641)	grad_norm 1.2577 (1.4764)	
[2022-01-18 00:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1120/1251]	eta 0:04:48 lr 0.000845	time 2.5078 (2.1994)	loss 3.9523 (4.6627)	grad_norm 1.7222 (1.4764)	
[2022-01-18 00:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1130/1251]	eta 0:04:26 lr 0.000845	time 2.9163 (2.2007)	loss 5.0682 (4.6643)	grad_norm 1.7995 (1.4761)	
[2022-01-18 00:48:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1140/1251]	eta 0:04:04 lr 0.000846	time 2.1452 (2.1995)	loss 4.5953 (4.6648)	grad_norm 1.2955 (1.4758)	
[2022-01-18 00:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1150/1251]	eta 0:03:42 lr 0.000846	time 1.6702 (2.1981)	loss 4.4528 (4.6646)	grad_norm 1.4162 (1.4762)	
[2022-01-18 00:49:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1160/1251]	eta 0:03:19 lr 0.000847	time 2.2333 (2.1978)	loss 3.8461 (4.6633)	grad_norm 1.4840 (1.4765)	
[2022-01-18 00:49:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1170/1251]	eta 0:02:58 lr 0.000847	time 3.1148 (2.1980)	loss 5.2391 (4.6641)	grad_norm 1.4962 (1.4771)	
[2022-01-18 00:49:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1180/1251]	eta 0:02:36 lr 0.000847	time 2.2661 (2.1984)	loss 4.2617 (4.6667)	grad_norm 1.2927 (1.4760)	
[2022-01-18 00:50:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1190/1251]	eta 0:02:14 lr 0.000848	time 1.8371 (2.1995)	loss 4.4810 (4.6667)	grad_norm 1.2444 (1.4760)	
[2022-01-18 00:50:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1200/1251]	eta 0:01:52 lr 0.000848	time 1.6963 (2.1995)	loss 4.7755 (4.6684)	grad_norm 1.2436 (1.4753)	
[2022-01-18 00:50:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1210/1251]	eta 0:01:30 lr 0.000849	time 2.8833 (2.1998)	loss 4.9988 (4.6685)	grad_norm 1.0504 (1.4745)	
[2022-01-18 00:51:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1220/1251]	eta 0:01:08 lr 0.000849	time 1.5431 (2.1984)	loss 4.2520 (4.6680)	grad_norm 1.4868 (1.4742)	
[2022-01-18 00:51:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1230/1251]	eta 0:00:46 lr 0.000849	time 1.6049 (2.1984)	loss 4.9997 (4.6693)	grad_norm 1.8838 (1.4750)	
[2022-01-18 00:52:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1240/1251]	eta 0:00:24 lr 0.000850	time 1.6958 (2.1967)	loss 5.0184 (4.6689)	grad_norm 1.4305 (1.4741)	
[2022-01-18 00:52:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [16/300][1250/1251]	eta 0:00:02 lr 0.000850	time 1.1942 (2.1910)	loss 4.6567 (4.6678)	grad_norm 1.3638 (1.4744)	
[2022-01-18 00:52:15 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 16 training takes 0:45:41
[2022-01-18 00:52:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.610 (18.610)	Loss 2.0033 (2.0033)	Acc@1 58.301 (58.301)	Acc@5 80.566 (80.566)	
[2022-01-18 00:52:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.904 (3.210)	Loss 1.9448 (1.9654)	Acc@1 58.301 (57.564)	Acc@5 80.176 (80.655)	
[2022-01-18 00:53:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.991 (2.428)	Loss 1.8988 (1.9532)	Acc@1 58.691 (57.264)	Acc@5 81.055 (80.864)	
[2022-01-18 00:53:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.956 (2.241)	Loss 2.0656 (1.9489)	Acc@1 53.906 (57.079)	Acc@5 78.027 (80.954)	
[2022-01-18 00:53:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.193 (2.159)	Loss 2.0099 (1.9534)	Acc@1 57.031 (56.967)	Acc@5 79.785 (80.881)	
[2022-01-18 00:53:51 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 56.938 Acc@5 80.810
[2022-01-18 00:53:51 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 56.9%
[2022-01-18 00:53:51 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 56.94%
[2022-01-18 00:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][0/1251]	eta 7:28:37 lr 0.000850	time 21.5165 (21.5165)	loss 4.3923 (4.3923)	grad_norm 1.4780 (1.4780)	
[2022-01-18 00:54:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][10/1251]	eta 1:20:43 lr 0.000851	time 1.5417 (3.9028)	loss 5.3574 (4.7830)	grad_norm 1.5579 (1.4299)	
[2022-01-18 00:54:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][20/1251]	eta 1:02:46 lr 0.000851	time 1.2984 (3.0598)	loss 4.4356 (4.7393)	grad_norm 1.5198 (1.4552)	
[2022-01-18 00:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][30/1251]	eta 0:57:57 lr 0.000851	time 2.0272 (2.8480)	loss 4.2812 (4.6217)	grad_norm 1.4557 (1.5167)	
[2022-01-18 00:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][40/1251]	eta 0:55:15 lr 0.000852	time 3.8056 (2.7382)	loss 4.0507 (4.5320)	grad_norm 1.3849 (1.5175)	
[2022-01-18 00:56:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][50/1251]	eta 0:53:39 lr 0.000852	time 1.7697 (2.6808)	loss 4.8164 (4.4419)	grad_norm 1.5280 (1.5136)	
[2022-01-18 00:56:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][60/1251]	eta 0:51:46 lr 0.000853	time 1.7245 (2.6082)	loss 3.9061 (4.4807)	grad_norm 1.2611 (1.4979)	
[2022-01-18 00:56:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][70/1251]	eta 0:50:03 lr 0.000853	time 1.7953 (2.5434)	loss 4.6387 (4.5220)	grad_norm 2.0611 (1.4929)	
[2022-01-18 00:57:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][80/1251]	eta 0:48:54 lr 0.000853	time 3.5798 (2.5058)	loss 4.6214 (4.5498)	grad_norm 1.2284 (1.5000)	
[2022-01-18 00:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][90/1251]	eta 0:47:20 lr 0.000854	time 2.2081 (2.4462)	loss 4.9754 (4.5782)	grad_norm 1.1945 (1.4912)	
[2022-01-18 00:57:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][100/1251]	eta 0:46:22 lr 0.000854	time 2.5806 (2.4178)	loss 4.8767 (4.6030)	grad_norm 1.4305 (1.4899)	
[2022-01-18 00:58:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][110/1251]	eta 0:45:38 lr 0.000855	time 1.7995 (2.4005)	loss 3.9928 (4.6026)	grad_norm 1.1180 (1.4791)	
[2022-01-18 00:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][120/1251]	eta 0:45:17 lr 0.000855	time 2.6750 (2.4025)	loss 5.5714 (4.6023)	grad_norm 1.5629 (1.4769)	
[2022-01-18 00:59:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][130/1251]	eta 0:44:46 lr 0.000855	time 1.8950 (2.3965)	loss 5.2000 (4.6070)	grad_norm 1.5329 (1.4719)	
[2022-01-18 00:59:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][140/1251]	eta 0:43:55 lr 0.000856	time 1.9076 (2.3725)	loss 4.9228 (4.5999)	grad_norm 1.8888 (1.4646)	
[2022-01-18 00:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][150/1251]	eta 0:43:00 lr 0.000856	time 1.8891 (2.3442)	loss 4.2210 (4.5876)	grad_norm 2.3102 (1.4727)	
[2022-01-18 01:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][160/1251]	eta 0:42:11 lr 0.000857	time 1.9431 (2.3203)	loss 4.9976 (4.5945)	grad_norm 1.4026 (1.4698)	
[2022-01-18 01:00:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][170/1251]	eta 0:41:42 lr 0.000857	time 2.5201 (2.3151)	loss 4.1678 (4.5874)	grad_norm 1.2186 (1.4607)	
[2022-01-18 01:00:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][180/1251]	eta 0:41:05 lr 0.000857	time 1.8539 (2.3024)	loss 5.3204 (4.5856)	grad_norm 1.0605 (1.4512)	
[2022-01-18 01:01:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][190/1251]	eta 0:40:41 lr 0.000858	time 2.2038 (2.3016)	loss 4.6078 (4.5788)	grad_norm 1.3828 (1.4420)	
[2022-01-18 01:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][200/1251]	eta 0:40:15 lr 0.000858	time 1.4669 (2.2982)	loss 5.0195 (4.5724)	grad_norm 1.3021 (1.4376)	
[2022-01-18 01:01:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][210/1251]	eta 0:39:56 lr 0.000859	time 2.2632 (2.3020)	loss 5.3962 (4.5796)	grad_norm 1.2713 (1.4348)	
[2022-01-18 01:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][220/1251]	eta 0:39:34 lr 0.000859	time 1.9132 (2.3029)	loss 3.9543 (4.5776)	grad_norm 1.2532 (1.4345)	
[2022-01-18 01:02:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][230/1251]	eta 0:39:08 lr 0.000859	time 1.8645 (2.3003)	loss 4.9792 (4.5693)	grad_norm 1.8939 (1.4351)	
[2022-01-18 01:03:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][240/1251]	eta 0:38:39 lr 0.000860	time 2.1592 (2.2948)	loss 4.8927 (4.5623)	grad_norm 1.2053 (1.4386)	
[2022-01-18 01:03:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][250/1251]	eta 0:38:04 lr 0.000860	time 1.8536 (2.2820)	loss 3.6799 (4.5559)	grad_norm 1.3843 (1.4397)	
[2022-01-18 01:03:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][260/1251]	eta 0:37:31 lr 0.000861	time 2.0464 (2.2717)	loss 4.9816 (4.5666)	grad_norm 1.9929 (1.4426)	
[2022-01-18 01:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][270/1251]	eta 0:37:01 lr 0.000861	time 2.2404 (2.2649)	loss 5.4005 (4.5592)	grad_norm 1.4542 (1.4488)	
[2022-01-18 01:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][280/1251]	eta 0:36:36 lr 0.000861	time 2.8077 (2.2617)	loss 4.9545 (4.5537)	grad_norm 1.5265 (1.4444)	
[2022-01-18 01:04:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][290/1251]	eta 0:36:12 lr 0.000862	time 2.2824 (2.2606)	loss 4.7371 (4.5470)	grad_norm 1.5492 (1.4474)	
[2022-01-18 01:05:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][300/1251]	eta 0:35:59 lr 0.000862	time 2.2696 (2.2704)	loss 4.6679 (4.5516)	grad_norm 1.3490 (1.4486)	
[2022-01-18 01:05:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][310/1251]	eta 0:35:39 lr 0.000863	time 2.4669 (2.2735)	loss 5.3377 (4.5569)	grad_norm 1.6038 (1.4461)	
[2022-01-18 01:06:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][320/1251]	eta 0:35:14 lr 0.000863	time 1.9748 (2.2709)	loss 5.0964 (4.5592)	grad_norm 1.3171 (1.4445)	
[2022-01-18 01:06:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][330/1251]	eta 0:34:49 lr 0.000863	time 2.0386 (2.2688)	loss 3.8124 (4.5470)	grad_norm 1.9399 (1.4442)	
[2022-01-18 01:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][340/1251]	eta 0:34:16 lr 0.000864	time 1.6137 (2.2575)	loss 5.6731 (4.5482)	grad_norm 1.3517 (1.4410)	
[2022-01-18 01:07:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][350/1251]	eta 0:33:47 lr 0.000864	time 1.8499 (2.2503)	loss 4.9590 (4.5373)	grad_norm 1.4704 (1.4422)	
[2022-01-18 01:07:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][360/1251]	eta 0:33:18 lr 0.000865	time 1.6896 (2.2434)	loss 3.3364 (4.5424)	grad_norm 1.7030 (1.4439)	
[2022-01-18 01:07:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][370/1251]	eta 0:32:54 lr 0.000865	time 2.2205 (2.2413)	loss 4.7126 (4.5493)	grad_norm 1.5040 (1.4457)	
[2022-01-18 01:08:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][380/1251]	eta 0:32:27 lr 0.000865	time 2.2255 (2.2359)	loss 5.0225 (4.5536)	grad_norm 1.2867 (1.4457)	
[2022-01-18 01:08:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][390/1251]	eta 0:32:03 lr 0.000866	time 2.2226 (2.2341)	loss 4.2441 (4.5529)	grad_norm 2.0653 (1.4469)	
[2022-01-18 01:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][400/1251]	eta 0:31:42 lr 0.000866	time 3.2174 (2.2352)	loss 5.3062 (4.5531)	grad_norm 1.3278 (1.4480)	
[2022-01-18 01:09:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][410/1251]	eta 0:31:20 lr 0.000867	time 1.9523 (2.2355)	loss 4.5027 (4.5576)	grad_norm 1.5842 (1.4479)	
[2022-01-18 01:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][420/1251]	eta 0:31:00 lr 0.000867	time 2.1520 (2.2385)	loss 5.4453 (4.5629)	grad_norm 1.7716 (1.4544)	
[2022-01-18 01:09:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][430/1251]	eta 0:30:41 lr 0.000867	time 3.2400 (2.2430)	loss 4.6510 (4.5674)	grad_norm 1.2581 (1.4560)	
[2022-01-18 01:10:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][440/1251]	eta 0:30:20 lr 0.000868	time 2.6822 (2.2444)	loss 4.2726 (4.5658)	grad_norm 1.1860 (1.4583)	
[2022-01-18 01:10:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][450/1251]	eta 0:29:56 lr 0.000868	time 1.8297 (2.2422)	loss 4.7524 (4.5701)	grad_norm 1.3099 (1.4577)	
[2022-01-18 01:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][460/1251]	eta 0:29:32 lr 0.000869	time 1.6470 (2.2402)	loss 4.8602 (4.5738)	grad_norm 1.4621 (1.4588)	
[2022-01-18 01:11:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][470/1251]	eta 0:29:08 lr 0.000869	time 3.0642 (2.2384)	loss 3.5679 (4.5735)	grad_norm 1.5573 (1.4615)	
[2022-01-18 01:11:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][480/1251]	eta 0:28:43 lr 0.000869	time 1.9013 (2.2357)	loss 4.7593 (4.5736)	grad_norm 1.2757 (1.4605)	
[2022-01-18 01:12:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][490/1251]	eta 0:28:22 lr 0.000870	time 2.6579 (2.2378)	loss 5.1105 (4.5757)	grad_norm 1.0947 (1.4580)	
[2022-01-18 01:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][500/1251]	eta 0:28:03 lr 0.000870	time 2.2027 (2.2410)	loss 4.1422 (4.5818)	grad_norm 1.1230 (1.4575)	
[2022-01-18 01:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][510/1251]	eta 0:27:41 lr 0.000871	time 3.3714 (2.2429)	loss 3.9055 (4.5779)	grad_norm 1.2745 (1.4566)	
[2022-01-18 01:13:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][520/1251]	eta 0:27:17 lr 0.000871	time 1.7674 (2.2400)	loss 4.7706 (4.5820)	grad_norm 1.1833 (1.4542)	
[2022-01-18 01:13:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][530/1251]	eta 0:26:52 lr 0.000871	time 2.2744 (2.2369)	loss 4.2256 (4.5758)	grad_norm 1.6143 (1.4546)	
[2022-01-18 01:13:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][540/1251]	eta 0:26:27 lr 0.000872	time 2.2431 (2.2334)	loss 4.8615 (4.5815)	grad_norm 1.5049 (1.4580)	
[2022-01-18 01:14:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][550/1251]	eta 0:26:04 lr 0.000872	time 2.4634 (2.2312)	loss 4.2177 (4.5868)	grad_norm 1.4273 (1.4576)	
[2022-01-18 01:14:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][560/1251]	eta 0:25:40 lr 0.000873	time 2.3390 (2.2292)	loss 5.0433 (4.5926)	grad_norm 1.3909 (1.4604)	
[2022-01-18 01:15:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][570/1251]	eta 0:25:18 lr 0.000873	time 2.8712 (2.2300)	loss 4.3288 (4.5911)	grad_norm 1.3948 (1.4582)	
[2022-01-18 01:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][580/1251]	eta 0:24:54 lr 0.000873	time 1.7558 (2.2277)	loss 4.8596 (4.5924)	grad_norm 1.4505 (1.4569)	
[2022-01-18 01:15:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][590/1251]	eta 0:24:33 lr 0.000874	time 2.4618 (2.2286)	loss 5.5002 (4.5885)	grad_norm 1.1770 (1.4547)	
[2022-01-18 01:16:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][600/1251]	eta 0:24:10 lr 0.000874	time 2.6221 (2.2281)	loss 5.3856 (4.5926)	grad_norm 1.5005 (1.4552)	
[2022-01-18 01:16:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][610/1251]	eta 0:23:48 lr 0.000875	time 2.5265 (2.2281)	loss 4.3717 (4.5958)	grad_norm 1.3719 (1.4556)	
[2022-01-18 01:16:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][620/1251]	eta 0:23:25 lr 0.000875	time 1.8357 (2.2282)	loss 4.6836 (4.5915)	grad_norm 1.2961 (1.4569)	
[2022-01-18 01:17:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][630/1251]	eta 0:23:04 lr 0.000875	time 2.4393 (2.2301)	loss 4.9217 (4.5979)	grad_norm 2.1908 (1.4573)	
[2022-01-18 01:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][640/1251]	eta 0:22:41 lr 0.000876	time 2.2063 (2.2283)	loss 4.4402 (4.5995)	grad_norm 1.1965 (1.4537)	
[2022-01-18 01:17:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][650/1251]	eta 0:22:16 lr 0.000876	time 2.1186 (2.2246)	loss 4.5126 (4.5983)	grad_norm 1.7401 (1.4526)	
[2022-01-18 01:18:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][660/1251]	eta 0:21:53 lr 0.000877	time 2.0041 (2.2223)	loss 5.0585 (4.6023)	grad_norm 1.5452 (1.4519)	
[2022-01-18 01:18:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][670/1251]	eta 0:21:30 lr 0.000877	time 2.3666 (2.2204)	loss 4.2523 (4.6017)	grad_norm 1.3863 (1.4521)	
[2022-01-18 01:19:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][680/1251]	eta 0:21:07 lr 0.000877	time 1.8130 (2.2196)	loss 4.9753 (4.6030)	grad_norm 1.6633 (1.4535)	
[2022-01-18 01:19:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][690/1251]	eta 0:20:45 lr 0.000878	time 2.2693 (2.2196)	loss 5.3751 (4.6015)	grad_norm 1.2688 (1.4541)	
[2022-01-18 01:19:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][700/1251]	eta 0:20:24 lr 0.000878	time 2.1429 (2.2215)	loss 4.7583 (4.5996)	grad_norm 1.2929 (1.4515)	
[2022-01-18 01:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][710/1251]	eta 0:20:03 lr 0.000878	time 2.5998 (2.2241)	loss 4.0605 (4.6030)	grad_norm 1.3522 (1.4510)	
[2022-01-18 01:20:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][720/1251]	eta 0:19:41 lr 0.000879	time 2.4563 (2.2247)	loss 4.7401 (4.6040)	grad_norm 1.4749 (1.4499)	
[2022-01-18 01:20:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][730/1251]	eta 0:19:18 lr 0.000879	time 2.2368 (2.2232)	loss 3.6077 (4.6024)	grad_norm 1.3925 (1.4485)	
[2022-01-18 01:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][740/1251]	eta 0:18:54 lr 0.000880	time 2.1999 (2.2196)	loss 5.3429 (4.6084)	grad_norm 1.4022 (1.4479)	
[2022-01-18 01:21:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][750/1251]	eta 0:18:30 lr 0.000880	time 1.6090 (2.2169)	loss 3.8723 (4.6073)	grad_norm 1.2974 (1.4474)	
[2022-01-18 01:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][760/1251]	eta 0:18:08 lr 0.000880	time 2.3480 (2.2162)	loss 4.8950 (4.6058)	grad_norm 1.5867 (1.4498)	
[2022-01-18 01:22:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][770/1251]	eta 0:17:46 lr 0.000881	time 2.1552 (2.2165)	loss 4.3208 (4.6023)	grad_norm 1.5496 (1.4517)	
[2022-01-18 01:22:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][780/1251]	eta 0:17:24 lr 0.000881	time 2.5252 (2.2169)	loss 5.1191 (4.6045)	grad_norm 1.3585 (1.4522)	
[2022-01-18 01:23:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][790/1251]	eta 0:17:01 lr 0.000882	time 1.9678 (2.2164)	loss 4.8112 (4.6062)	grad_norm 1.2768 (1.4512)	
[2022-01-18 01:23:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][800/1251]	eta 0:16:39 lr 0.000882	time 1.9364 (2.2170)	loss 4.7767 (4.6075)	grad_norm 1.2570 (1.4511)	
[2022-01-18 01:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][810/1251]	eta 0:16:18 lr 0.000882	time 2.4617 (2.2194)	loss 4.0819 (4.6050)	grad_norm 1.1690 (1.4506)	
[2022-01-18 01:24:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][820/1251]	eta 0:15:56 lr 0.000883	time 2.1247 (2.2195)	loss 3.7052 (4.6046)	grad_norm 1.4382 (1.4492)	
[2022-01-18 01:24:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][830/1251]	eta 0:15:33 lr 0.000883	time 1.8392 (2.2171)	loss 4.0978 (4.6039)	grad_norm 1.4161 (1.4468)	
[2022-01-18 01:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][840/1251]	eta 0:15:10 lr 0.000884	time 1.8458 (2.2143)	loss 4.4496 (4.6062)	grad_norm 1.4743 (1.4467)	
[2022-01-18 01:25:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][850/1251]	eta 0:14:46 lr 0.000884	time 1.7656 (2.2114)	loss 4.9770 (4.6023)	grad_norm 1.3415 (1.4466)	
[2022-01-18 01:25:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][860/1251]	eta 0:14:24 lr 0.000884	time 2.1828 (2.2100)	loss 5.2570 (4.6017)	grad_norm 1.2369 (1.4461)	
[2022-01-18 01:25:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][870/1251]	eta 0:14:02 lr 0.000885	time 2.5444 (2.2101)	loss 4.2271 (4.6010)	grad_norm 1.6748 (1.4482)	
[2022-01-18 01:26:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][880/1251]	eta 0:13:39 lr 0.000885	time 1.7841 (2.2091)	loss 5.4237 (4.6015)	grad_norm 1.5480 (1.4498)	
[2022-01-18 01:26:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][890/1251]	eta 0:13:17 lr 0.000886	time 2.1770 (2.2098)	loss 5.0782 (4.6023)	grad_norm 2.1887 (1.4501)	
[2022-01-18 01:27:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][900/1251]	eta 0:12:56 lr 0.000886	time 2.2361 (2.2111)	loss 5.1518 (4.6010)	grad_norm 1.3144 (1.4500)	
[2022-01-18 01:27:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][910/1251]	eta 0:12:35 lr 0.000886	time 2.8098 (2.2164)	loss 5.2331 (4.6030)	grad_norm 1.5244 (1.4495)	
[2022-01-18 01:27:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][920/1251]	eta 0:12:13 lr 0.000887	time 1.8926 (2.2166)	loss 5.0756 (4.6072)	grad_norm 1.2361 (1.4495)	
[2022-01-18 01:28:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][930/1251]	eta 0:11:50 lr 0.000887	time 1.8941 (2.2144)	loss 3.7388 (4.6028)	grad_norm 1.8762 (1.4500)	
[2022-01-18 01:28:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][940/1251]	eta 0:11:28 lr 0.000888	time 1.8514 (2.2129)	loss 3.7545 (4.6031)	grad_norm 1.3356 (1.4494)	
[2022-01-18 01:28:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][950/1251]	eta 0:11:06 lr 0.000888	time 1.9676 (2.2131)	loss 4.7546 (4.6024)	grad_norm 1.4298 (1.4493)	
[2022-01-18 01:29:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][960/1251]	eta 0:10:43 lr 0.000888	time 2.5026 (2.2127)	loss 5.3963 (4.6043)	grad_norm 1.2103 (1.4504)	
[2022-01-18 01:29:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][970/1251]	eta 0:10:21 lr 0.000889	time 2.1402 (2.2113)	loss 5.2471 (4.6032)	grad_norm 1.4434 (1.4498)	
[2022-01-18 01:29:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][980/1251]	eta 0:09:58 lr 0.000889	time 2.0508 (2.2088)	loss 5.1606 (4.6034)	grad_norm 1.3730 (1.4486)	
[2022-01-18 01:30:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][990/1251]	eta 0:09:36 lr 0.000890	time 1.8095 (2.2081)	loss 5.2475 (4.6051)	grad_norm 1.7307 (1.4487)	
[2022-01-18 01:30:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1000/1251]	eta 0:09:14 lr 0.000890	time 2.1947 (2.2078)	loss 4.9272 (4.6086)	grad_norm 1.0594 (1.4471)	
[2022-01-18 01:31:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1010/1251]	eta 0:08:52 lr 0.000890	time 2.8381 (2.2097)	loss 4.4294 (4.6110)	grad_norm 1.2758 (1.4465)	
[2022-01-18 01:31:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1020/1251]	eta 0:08:30 lr 0.000891	time 1.9748 (2.2107)	loss 4.1258 (4.6106)	grad_norm 1.3642 (1.4458)	
[2022-01-18 01:31:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1030/1251]	eta 0:08:08 lr 0.000891	time 2.2296 (2.2121)	loss 4.5290 (4.6101)	grad_norm 1.3121 (1.4448)	
[2022-01-18 01:32:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1040/1251]	eta 0:07:46 lr 0.000892	time 1.8499 (2.2120)	loss 4.8640 (4.6097)	grad_norm 1.4701 (1.4439)	
[2022-01-18 01:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1050/1251]	eta 0:07:24 lr 0.000892	time 3.2909 (2.2114)	loss 4.5377 (4.6113)	grad_norm 1.4170 (1.4434)	
[2022-01-18 01:32:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1060/1251]	eta 0:07:01 lr 0.000892	time 1.6448 (2.2091)	loss 5.5715 (4.6130)	grad_norm 1.2516 (1.4418)	
[2022-01-18 01:33:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1070/1251]	eta 0:06:39 lr 0.000893	time 1.7042 (2.2081)	loss 4.1835 (4.6160)	grad_norm 1.2750 (1.4415)	
[2022-01-18 01:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1080/1251]	eta 0:06:17 lr 0.000893	time 1.9014 (2.2066)	loss 4.0452 (4.6174)	grad_norm 1.5520 (1.4407)	
[2022-01-18 01:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1090/1251]	eta 0:05:55 lr 0.000894	time 3.7935 (2.2075)	loss 4.7342 (4.6165)	grad_norm 1.2793 (1.4401)	
[2022-01-18 01:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1100/1251]	eta 0:05:33 lr 0.000894	time 2.4600 (2.2081)	loss 4.7788 (4.6184)	grad_norm 1.4922 (1.4390)	
[2022-01-18 01:34:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1110/1251]	eta 0:05:11 lr 0.000894	time 1.9309 (2.2078)	loss 5.3074 (4.6181)	grad_norm 1.4324 (1.4391)	
[2022-01-18 01:35:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1120/1251]	eta 0:04:49 lr 0.000895	time 2.1506 (2.2093)	loss 5.0278 (4.6197)	grad_norm 1.1936 (1.4392)	
[2022-01-18 01:35:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1130/1251]	eta 0:04:27 lr 0.000895	time 2.7373 (2.2083)	loss 4.3462 (4.6206)	grad_norm 1.4043 (1.4380)	
[2022-01-18 01:35:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1140/1251]	eta 0:04:05 lr 0.000896	time 2.6787 (2.2080)	loss 3.7523 (4.6201)	grad_norm 1.0767 (1.4375)	
[2022-01-18 01:36:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1150/1251]	eta 0:03:42 lr 0.000896	time 2.2037 (2.2075)	loss 4.8741 (4.6215)	grad_norm 1.4549 (1.4379)	
[2022-01-18 01:36:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1160/1251]	eta 0:03:20 lr 0.000896	time 1.8275 (2.2076)	loss 4.6442 (4.6196)	grad_norm 1.0514 (1.4375)	
[2022-01-18 01:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1170/1251]	eta 0:02:58 lr 0.000897	time 2.8955 (2.2072)	loss 4.8572 (4.6211)	grad_norm 1.4508 (1.4362)	
[2022-01-18 01:37:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1180/1251]	eta 0:02:36 lr 0.000897	time 2.8151 (2.2069)	loss 4.9835 (4.6242)	grad_norm 1.1948 (1.4362)	
[2022-01-18 01:37:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1190/1251]	eta 0:02:14 lr 0.000898	time 1.8840 (2.2057)	loss 4.7725 (4.6235)	grad_norm 1.4795 (1.4364)	
[2022-01-18 01:38:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1200/1251]	eta 0:01:52 lr 0.000898	time 1.9447 (2.2061)	loss 5.1260 (4.6255)	grad_norm 1.3507 (1.4364)	
[2022-01-18 01:38:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1210/1251]	eta 0:01:30 lr 0.000898	time 1.8896 (2.2043)	loss 4.5982 (4.6237)	grad_norm 1.2900 (1.4357)	
[2022-01-18 01:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1220/1251]	eta 0:01:08 lr 0.000899	time 2.5276 (2.2035)	loss 4.4403 (4.6233)	grad_norm 1.6785 (1.4354)	
[2022-01-18 01:39:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1230/1251]	eta 0:00:46 lr 0.000899	time 2.2059 (2.2024)	loss 4.7932 (4.6223)	grad_norm 1.5036 (1.4351)	
[2022-01-18 01:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1240/1251]	eta 0:00:24 lr 0.000900	time 2.1973 (2.2021)	loss 5.3336 (4.6238)	grad_norm 1.2859 (1.4348)	
[2022-01-18 01:39:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [17/300][1250/1251]	eta 0:00:02 lr 0.000900	time 1.2894 (2.1973)	loss 5.0061 (4.6272)	grad_norm 1.4052 (1.4348)	
[2022-01-18 01:39:40 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 17 training takes 0:45:49
[2022-01-18 01:39:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.160 (18.160)	Loss 1.9148 (1.9148)	Acc@1 58.008 (58.008)	Acc@5 82.031 (82.031)	
[2022-01-18 01:40:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.044 (3.531)	Loss 1.9640 (1.9142)	Acc@1 56.250 (57.013)	Acc@5 81.445 (81.934)	
[2022-01-18 01:40:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.612 (2.769)	Loss 1.9785 (1.9177)	Acc@1 57.617 (57.487)	Acc@5 81.348 (81.901)	
[2022-01-18 01:40:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.613 (2.341)	Loss 1.9125 (1.9252)	Acc@1 58.301 (57.245)	Acc@5 82.910 (81.823)	
[2022-01-18 01:41:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.984 (2.223)	Loss 1.9220 (1.9308)	Acc@1 57.129 (57.191)	Acc@5 82.520 (81.781)	
[2022-01-18 01:41:19 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 57.186 Acc@5 81.596
[2022-01-18 01:41:19 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 57.2%
[2022-01-18 01:41:19 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 57.19%
[2022-01-18 01:41:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][0/1251]	eta 7:31:28 lr 0.000900	time 21.6534 (21.6534)	loss 4.4726 (4.4726)	grad_norm 1.4513 (1.4513)	
[2022-01-18 01:42:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][10/1251]	eta 1:23:10 lr 0.000900	time 2.3545 (4.0217)	loss 5.3842 (4.6343)	grad_norm 1.1580 (1.4104)	
[2022-01-18 01:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][20/1251]	eta 1:02:55 lr 0.000901	time 1.5345 (3.0672)	loss 4.1452 (4.5158)	grad_norm 1.6024 (1.4023)	
[2022-01-18 01:42:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][30/1251]	eta 0:56:15 lr 0.000901	time 1.9305 (2.7641)	loss 4.6268 (4.4644)	grad_norm 1.1835 (1.3905)	
[2022-01-18 01:43:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][40/1251]	eta 0:53:59 lr 0.000902	time 5.9651 (2.6754)	loss 4.6232 (4.5176)	grad_norm 1.3071 (1.4069)	
[2022-01-18 01:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][50/1251]	eta 0:51:46 lr 0.000902	time 2.8509 (2.5866)	loss 3.9597 (4.4418)	grad_norm 1.2660 (1.3914)	
[2022-01-18 01:43:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][60/1251]	eta 0:49:24 lr 0.000902	time 1.5175 (2.4891)	loss 4.9737 (4.5093)	grad_norm 1.1787 (1.3898)	
[2022-01-18 01:44:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][70/1251]	eta 0:48:12 lr 0.000903	time 1.9097 (2.4490)	loss 3.4668 (4.4972)	grad_norm 1.4009 (1.3872)	
[2022-01-18 01:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][80/1251]	eta 0:47:30 lr 0.000903	time 3.5517 (2.4343)	loss 4.8355 (4.4936)	grad_norm 1.4476 (1.3925)	
[2022-01-18 01:45:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][90/1251]	eta 0:47:08 lr 0.000904	time 4.5112 (2.4359)	loss 4.8611 (4.5121)	grad_norm 1.1833 (1.4073)	
[2022-01-18 01:45:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][100/1251]	eta 0:46:14 lr 0.000904	time 1.9299 (2.4104)	loss 4.3033 (4.5132)	grad_norm 1.5060 (1.4073)	
[2022-01-18 01:45:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][110/1251]	eta 0:45:26 lr 0.000904	time 1.9339 (2.3899)	loss 4.3448 (4.5483)	grad_norm 1.3068 (1.4037)	
[2022-01-18 01:46:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][120/1251]	eta 0:44:49 lr 0.000905	time 3.4720 (2.3777)	loss 5.0873 (4.5584)	grad_norm 1.6857 (1.4012)	
[2022-01-18 01:46:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][130/1251]	eta 0:44:19 lr 0.000905	time 3.3658 (2.3720)	loss 4.5456 (4.5559)	grad_norm 1.3797 (1.3976)	
[2022-01-18 01:46:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][140/1251]	eta 0:43:44 lr 0.000906	time 1.4905 (2.3618)	loss 4.9642 (4.5753)	grad_norm 1.3751 (1.3846)	
[2022-01-18 01:47:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][150/1251]	eta 0:43:10 lr 0.000906	time 1.7915 (2.3530)	loss 4.8370 (4.5778)	grad_norm 1.2736 (1.3896)	
[2022-01-18 01:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][160/1251]	eta 0:42:49 lr 0.000906	time 3.0351 (2.3551)	loss 5.2354 (4.5606)	grad_norm 1.1262 (1.3985)	
[2022-01-18 01:48:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][170/1251]	eta 0:42:15 lr 0.000907	time 3.3645 (2.3455)	loss 4.7525 (4.5340)	grad_norm 1.3996 (1.3991)	
[2022-01-18 01:48:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][180/1251]	eta 0:41:30 lr 0.000907	time 1.6908 (2.3259)	loss 4.1261 (4.5207)	grad_norm 1.4367 (1.3984)	
[2022-01-18 01:48:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][190/1251]	eta 0:40:45 lr 0.000908	time 1.5595 (2.3045)	loss 4.8226 (4.5142)	grad_norm 1.2555 (1.4027)	
[2022-01-18 01:49:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][200/1251]	eta 0:40:15 lr 0.000908	time 2.0367 (2.2981)	loss 5.2278 (4.5267)	grad_norm 1.2482 (1.3979)	
[2022-01-18 01:49:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][210/1251]	eta 0:39:46 lr 0.000908	time 2.5761 (2.2926)	loss 4.4490 (4.5262)	grad_norm 1.6077 (1.3976)	
[2022-01-18 01:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][220/1251]	eta 0:39:20 lr 0.000909	time 1.7908 (2.2893)	loss 4.5269 (4.5343)	grad_norm 1.3832 (1.3957)	
[2022-01-18 01:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][230/1251]	eta 0:39:00 lr 0.000909	time 2.5590 (2.2922)	loss 5.0845 (4.5364)	grad_norm 1.5723 (1.3987)	
[2022-01-18 01:50:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][240/1251]	eta 0:38:35 lr 0.000910	time 1.5116 (2.2900)	loss 3.3504 (4.5452)	grad_norm 1.3398 (1.3960)	
[2022-01-18 01:50:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][250/1251]	eta 0:38:07 lr 0.000910	time 2.2647 (2.2853)	loss 4.0634 (4.5557)	grad_norm 1.6531 (1.3936)	
[2022-01-18 01:51:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][260/1251]	eta 0:37:38 lr 0.000910	time 2.4690 (2.2793)	loss 4.9298 (4.5566)	grad_norm 1.0912 (1.3910)	
[2022-01-18 01:51:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][270/1251]	eta 0:37:08 lr 0.000911	time 2.4476 (2.2718)	loss 3.7011 (4.5639)	grad_norm 1.5926 (1.3952)	
[2022-01-18 01:51:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][280/1251]	eta 0:36:37 lr 0.000911	time 1.9526 (2.2635)	loss 5.5385 (4.5709)	grad_norm 1.0535 (1.3979)	
[2022-01-18 01:52:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][290/1251]	eta 0:36:08 lr 0.000912	time 2.4232 (2.2564)	loss 5.4007 (4.5813)	grad_norm 1.2770 (1.3972)	
[2022-01-18 01:52:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][300/1251]	eta 0:35:46 lr 0.000912	time 2.2098 (2.2566)	loss 4.7092 (4.5771)	grad_norm 1.2501 (1.3938)	
[2022-01-18 01:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][310/1251]	eta 0:35:25 lr 0.000912	time 1.9035 (2.2590)	loss 4.3543 (4.5664)	grad_norm 1.6675 (1.3941)	
[2022-01-18 01:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][320/1251]	eta 0:35:04 lr 0.000913	time 2.0098 (2.2608)	loss 3.8536 (4.5661)	grad_norm 1.4908 (1.3906)	
[2022-01-18 01:53:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][330/1251]	eta 0:34:43 lr 0.000913	time 2.2195 (2.2627)	loss 4.9048 (4.5733)	grad_norm 1.2230 (1.3915)	
[2022-01-18 01:54:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][340/1251]	eta 0:34:21 lr 0.000914	time 2.4684 (2.2628)	loss 4.1884 (4.5701)	grad_norm 1.2968 (1.3903)	
[2022-01-18 01:54:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][350/1251]	eta 0:33:54 lr 0.000914	time 2.5807 (2.2576)	loss 5.6138 (4.5712)	grad_norm 1.2092 (1.3911)	
[2022-01-18 01:54:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][360/1251]	eta 0:33:23 lr 0.000914	time 1.5585 (2.2484)	loss 3.8435 (4.5559)	grad_norm 1.1767 (1.3917)	
[2022-01-18 01:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][370/1251]	eta 0:32:55 lr 0.000915	time 2.1064 (2.2427)	loss 4.9667 (4.5587)	grad_norm 1.2729 (1.3954)	
[2022-01-18 01:55:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][380/1251]	eta 0:32:32 lr 0.000915	time 2.1842 (2.2419)	loss 3.9642 (4.5583)	grad_norm 1.2960 (1.3975)	
[2022-01-18 01:55:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][390/1251]	eta 0:32:07 lr 0.000916	time 1.5380 (2.2385)	loss 5.2215 (4.5609)	grad_norm 1.5988 (1.3997)	
[2022-01-18 01:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][400/1251]	eta 0:31:44 lr 0.000916	time 2.1870 (2.2381)	loss 4.9617 (4.5665)	grad_norm 1.5910 (1.4022)	
[2022-01-18 01:56:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][410/1251]	eta 0:31:21 lr 0.000916	time 2.2672 (2.2367)	loss 3.8030 (4.5641)	grad_norm 1.1357 (1.4049)	
[2022-01-18 01:57:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][420/1251]	eta 0:31:00 lr 0.000917	time 1.8373 (2.2385)	loss 4.8071 (4.5664)	grad_norm 1.4415 (1.4066)	
[2022-01-18 01:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][430/1251]	eta 0:30:37 lr 0.000917	time 1.9289 (2.2383)	loss 4.0852 (4.5641)	grad_norm 1.5138 (1.4054)	
[2022-01-18 01:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][440/1251]	eta 0:30:13 lr 0.000918	time 1.7845 (2.2365)	loss 5.3689 (4.5664)	grad_norm 1.8616 (1.4054)	
[2022-01-18 01:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][450/1251]	eta 0:29:49 lr 0.000918	time 2.0653 (2.2343)	loss 4.7372 (4.5666)	grad_norm 1.1850 (1.4051)	
[2022-01-18 01:58:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][460/1251]	eta 0:29:29 lr 0.000918	time 2.1657 (2.2368)	loss 5.0479 (4.5651)	grad_norm 1.7847 (1.4066)	
[2022-01-18 01:58:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][470/1251]	eta 0:29:05 lr 0.000919	time 2.6003 (2.2351)	loss 4.6185 (4.5671)	grad_norm 1.3978 (1.4056)	
[2022-01-18 01:59:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][480/1251]	eta 0:28:39 lr 0.000919	time 1.5633 (2.2297)	loss 3.5258 (4.5653)	grad_norm 1.1950 (1.4034)	
[2022-01-18 01:59:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][490/1251]	eta 0:28:14 lr 0.000920	time 2.3797 (2.2272)	loss 4.8901 (4.5689)	grad_norm 1.2406 (1.4024)	
[2022-01-18 01:59:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][500/1251]	eta 0:27:50 lr 0.000920	time 1.6607 (2.2239)	loss 4.7861 (4.5722)	grad_norm 1.3727 (1.4071)	
[2022-01-18 02:00:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][510/1251]	eta 0:27:25 lr 0.000920	time 1.8758 (2.2213)	loss 4.7682 (4.5699)	grad_norm 1.0682 (1.4039)	
[2022-01-18 02:00:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][520/1251]	eta 0:27:03 lr 0.000921	time 2.4712 (2.2208)	loss 4.6511 (4.5682)	grad_norm 1.2351 (1.4036)	
[2022-01-18 02:00:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][530/1251]	eta 0:26:42 lr 0.000921	time 2.5491 (2.2221)	loss 3.5018 (4.5623)	grad_norm 1.4161 (1.4036)	
[2022-01-18 02:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][540/1251]	eta 0:26:22 lr 0.000922	time 1.8896 (2.2259)	loss 5.4103 (4.5591)	grad_norm 1.1647 (1.4021)	
[2022-01-18 02:01:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][550/1251]	eta 0:26:01 lr 0.000922	time 2.1672 (2.2273)	loss 4.9945 (4.5587)	grad_norm 1.5094 (1.4026)	
[2022-01-18 02:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][560/1251]	eta 0:25:38 lr 0.000922	time 2.0834 (2.2258)	loss 5.5315 (4.5584)	grad_norm 1.5419 (1.4033)	
[2022-01-18 02:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][570/1251]	eta 0:25:13 lr 0.000923	time 1.8208 (2.2225)	loss 4.3659 (4.5600)	grad_norm 1.2981 (1.4047)	
[2022-01-18 02:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][580/1251]	eta 0:24:47 lr 0.000923	time 1.8919 (2.2166)	loss 5.1021 (4.5613)	grad_norm 1.2379 (1.4026)	
[2022-01-18 02:03:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][590/1251]	eta 0:24:23 lr 0.000924	time 2.2126 (2.2137)	loss 4.7674 (4.5649)	grad_norm 1.5599 (1.4017)	
[2022-01-18 02:03:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][600/1251]	eta 0:23:59 lr 0.000924	time 1.9444 (2.2106)	loss 5.2398 (4.5602)	grad_norm 1.3243 (1.4030)	
[2022-01-18 02:03:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][610/1251]	eta 0:23:36 lr 0.000924	time 2.4019 (2.2099)	loss 4.4038 (4.5614)	grad_norm 1.3471 (1.4053)	
[2022-01-18 02:04:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][620/1251]	eta 0:23:14 lr 0.000925	time 1.8497 (2.2104)	loss 5.1704 (4.5598)	grad_norm 1.2968 (1.4039)	
[2022-01-18 02:04:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][630/1251]	eta 0:22:53 lr 0.000925	time 2.3066 (2.2120)	loss 5.0111 (4.5614)	grad_norm 1.3306 (1.4055)	
[2022-01-18 02:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][640/1251]	eta 0:22:32 lr 0.000926	time 2.8193 (2.2138)	loss 4.8165 (4.5625)	grad_norm 1.1911 (1.4038)	
[2022-01-18 02:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][650/1251]	eta 0:22:09 lr 0.000926	time 1.5613 (2.2120)	loss 3.3659 (4.5587)	grad_norm 1.2553 (1.4037)	
[2022-01-18 02:05:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][660/1251]	eta 0:21:46 lr 0.000926	time 1.5628 (2.2115)	loss 5.2917 (4.5595)	grad_norm 1.0458 (1.4022)	
[2022-01-18 02:06:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][670/1251]	eta 0:21:24 lr 0.000927	time 2.5142 (2.2101)	loss 4.6670 (4.5571)	grad_norm 1.4490 (1.4029)	
[2022-01-18 02:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][680/1251]	eta 0:21:03 lr 0.000927	time 2.2018 (2.2131)	loss 5.2518 (4.5606)	grad_norm 1.4995 (1.4023)	
[2022-01-18 02:06:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][690/1251]	eta 0:20:41 lr 0.000928	time 1.8672 (2.2127)	loss 5.4491 (4.5598)	grad_norm 1.5489 (1.4027)	
[2022-01-18 02:07:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][700/1251]	eta 0:20:19 lr 0.000928	time 1.8747 (2.2134)	loss 4.9080 (4.5594)	grad_norm 1.1559 (1.4009)	
[2022-01-18 02:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][710/1251]	eta 0:19:57 lr 0.000928	time 2.2604 (2.2136)	loss 4.9915 (4.5612)	grad_norm 1.4315 (1.4016)	
[2022-01-18 02:07:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][720/1251]	eta 0:19:34 lr 0.000929	time 1.5492 (2.2112)	loss 4.5562 (4.5621)	grad_norm 1.3346 (1.3999)	
[2022-01-18 02:08:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][730/1251]	eta 0:19:10 lr 0.000929	time 2.3374 (2.2088)	loss 4.4643 (4.5608)	grad_norm 1.6053 (1.4010)	
[2022-01-18 02:08:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][740/1251]	eta 0:18:48 lr 0.000930	time 2.2431 (2.2080)	loss 4.8011 (4.5609)	grad_norm 1.4192 (1.4020)	
[2022-01-18 02:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][750/1251]	eta 0:18:26 lr 0.000930	time 2.4029 (2.2077)	loss 4.1211 (4.5648)	grad_norm 1.4656 (1.4018)	
[2022-01-18 02:09:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][760/1251]	eta 0:18:03 lr 0.000930	time 1.9124 (2.2068)	loss 5.4521 (4.5655)	grad_norm 1.4044 (1.4010)	
[2022-01-18 02:09:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][770/1251]	eta 0:17:40 lr 0.000931	time 2.8080 (2.2053)	loss 3.6310 (4.5599)	grad_norm 1.4225 (1.4009)	
[2022-01-18 02:10:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][780/1251]	eta 0:17:19 lr 0.000931	time 2.1942 (2.2060)	loss 3.4926 (4.5598)	grad_norm 1.3058 (1.4019)	
[2022-01-18 02:10:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][790/1251]	eta 0:16:56 lr 0.000932	time 1.5197 (2.2048)	loss 5.0333 (4.5623)	grad_norm 1.3011 (1.4019)	
[2022-01-18 02:10:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][800/1251]	eta 0:16:34 lr 0.000932	time 2.1762 (2.2044)	loss 4.3621 (4.5651)	grad_norm 1.2694 (1.4010)	
[2022-01-18 02:11:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][810/1251]	eta 0:16:11 lr 0.000932	time 2.2283 (2.2025)	loss 5.1283 (4.5655)	grad_norm 1.2761 (1.4019)	
[2022-01-18 02:11:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][820/1251]	eta 0:15:49 lr 0.000933	time 2.1984 (2.2020)	loss 3.8229 (4.5629)	grad_norm 1.4280 (1.4017)	
[2022-01-18 02:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][830/1251]	eta 0:15:27 lr 0.000933	time 2.1748 (2.2036)	loss 5.1179 (4.5657)	grad_norm 1.7988 (1.4020)	
[2022-01-18 02:12:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][840/1251]	eta 0:15:06 lr 0.000934	time 1.7995 (2.2050)	loss 4.3811 (4.5648)	grad_norm 1.3504 (1.4027)	
[2022-01-18 02:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][850/1251]	eta 0:14:44 lr 0.000934	time 1.9411 (2.2059)	loss 4.9364 (4.5656)	grad_norm 1.6834 (1.4026)	
[2022-01-18 02:13:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][860/1251]	eta 0:14:23 lr 0.000934	time 2.3982 (2.2082)	loss 4.8706 (4.5641)	grad_norm 1.1319 (1.4021)	
[2022-01-18 02:13:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][870/1251]	eta 0:14:01 lr 0.000935	time 1.5396 (2.2099)	loss 3.9529 (4.5627)	grad_norm 1.3388 (1.4005)	
[2022-01-18 02:13:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][880/1251]	eta 0:13:39 lr 0.000935	time 1.5933 (2.2096)	loss 4.6518 (4.5612)	grad_norm 1.5303 (1.4000)	
[2022-01-18 02:14:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][890/1251]	eta 0:13:16 lr 0.000936	time 1.5471 (2.2071)	loss 4.3087 (4.5588)	grad_norm 1.6183 (1.4016)	
[2022-01-18 02:14:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][900/1251]	eta 0:12:53 lr 0.000936	time 2.3694 (2.2039)	loss 4.7861 (4.5566)	grad_norm 1.2069 (1.4032)	
[2022-01-18 02:14:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][910/1251]	eta 0:12:30 lr 0.000936	time 2.1214 (2.2023)	loss 4.9402 (4.5550)	grad_norm 1.3477 (1.4018)	
[2022-01-18 02:15:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][920/1251]	eta 0:12:08 lr 0.000937	time 2.2568 (2.2018)	loss 3.1572 (4.5543)	grad_norm 1.2052 (1.4000)	
[2022-01-18 02:15:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][930/1251]	eta 0:11:46 lr 0.000937	time 2.4573 (2.2012)	loss 5.4623 (4.5568)	grad_norm 1.1527 (1.3990)	
[2022-01-18 02:15:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][940/1251]	eta 0:11:24 lr 0.000938	time 1.8948 (2.2014)	loss 4.0712 (4.5580)	grad_norm 1.5295 (1.3978)	
[2022-01-18 02:16:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][950/1251]	eta 0:11:03 lr 0.000938	time 1.5345 (2.2032)	loss 4.9455 (4.5588)	grad_norm 1.7289 (1.3965)	
[2022-01-18 02:16:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][960/1251]	eta 0:10:41 lr 0.000938	time 2.0193 (2.2045)	loss 5.1197 (4.5601)	grad_norm 1.2519 (1.3966)	
[2022-01-18 02:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][970/1251]	eta 0:10:19 lr 0.000939	time 1.7320 (2.2036)	loss 4.6853 (4.5595)	grad_norm 1.5269 (1.3955)	
[2022-01-18 02:17:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][980/1251]	eta 0:09:57 lr 0.000939	time 2.7793 (2.2044)	loss 4.7073 (4.5562)	grad_norm 1.2593 (1.3949)	
[2022-01-18 02:17:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][990/1251]	eta 0:09:35 lr 0.000940	time 2.4913 (2.2064)	loss 4.9235 (4.5565)	grad_norm 1.6855 (1.3948)	
[2022-01-18 02:18:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1000/1251]	eta 0:09:13 lr 0.000940	time 1.5784 (2.2064)	loss 4.8472 (4.5574)	grad_norm 1.2088 (1.3942)	
[2022-01-18 02:18:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1010/1251]	eta 0:08:51 lr 0.000940	time 1.6590 (2.2044)	loss 3.7502 (4.5554)	grad_norm 1.5008 (1.3935)	
[2022-01-18 02:18:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1020/1251]	eta 0:08:28 lr 0.000941	time 1.9078 (2.2030)	loss 3.1952 (4.5566)	grad_norm 1.4248 (1.3928)	
[2022-01-18 02:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1030/1251]	eta 0:08:06 lr 0.000941	time 2.2196 (2.2021)	loss 4.8658 (4.5574)	grad_norm 1.4531 (1.3920)	
[2022-01-18 02:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1040/1251]	eta 0:07:44 lr 0.000942	time 2.2724 (2.2029)	loss 4.5531 (4.5586)	grad_norm 1.9704 (1.3920)	
[2022-01-18 02:19:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1050/1251]	eta 0:07:22 lr 0.000942	time 2.4056 (2.2022)	loss 4.3851 (4.5603)	grad_norm 1.0555 (1.3918)	
[2022-01-18 02:20:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1060/1251]	eta 0:07:00 lr 0.000942	time 2.2647 (2.2020)	loss 4.1207 (4.5623)	grad_norm 1.8290 (1.3922)	
[2022-01-18 02:20:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1070/1251]	eta 0:06:38 lr 0.000943	time 2.5203 (2.2001)	loss 4.7787 (4.5618)	grad_norm 1.0586 (1.3916)	
[2022-01-18 02:20:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1080/1251]	eta 0:06:16 lr 0.000943	time 2.4979 (2.2001)	loss 4.7860 (4.5635)	grad_norm 1.4185 (1.3904)	
[2022-01-18 02:21:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1090/1251]	eta 0:05:54 lr 0.000944	time 1.9093 (2.2000)	loss 5.2697 (4.5663)	grad_norm 1.2736 (1.3892)	
[2022-01-18 02:21:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1100/1251]	eta 0:05:32 lr 0.000944	time 2.1277 (2.2001)	loss 4.9341 (4.5680)	grad_norm 1.3129 (1.3886)	
[2022-01-18 02:22:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1110/1251]	eta 0:05:10 lr 0.000944	time 2.0062 (2.1994)	loss 5.1294 (4.5693)	grad_norm 1.3202 (1.3873)	
[2022-01-18 02:22:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1120/1251]	eta 0:04:48 lr 0.000945	time 2.8628 (2.1997)	loss 3.9459 (4.5686)	grad_norm 1.1649 (1.3878)	
[2022-01-18 02:22:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1130/1251]	eta 0:04:26 lr 0.000945	time 2.0196 (2.1992)	loss 4.0853 (4.5668)	grad_norm 1.6689 (1.3882)	
[2022-01-18 02:23:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1140/1251]	eta 0:04:03 lr 0.000946	time 2.0078 (2.1977)	loss 5.0415 (4.5667)	grad_norm 1.5058 (1.3883)	
[2022-01-18 02:23:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1150/1251]	eta 0:03:41 lr 0.000946	time 1.8651 (2.1970)	loss 4.4020 (4.5672)	grad_norm 1.3880 (1.3882)	
[2022-01-18 02:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1160/1251]	eta 0:03:19 lr 0.000946	time 2.5373 (2.1968)	loss 4.4579 (4.5698)	grad_norm 1.4673 (1.3895)	
[2022-01-18 02:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1170/1251]	eta 0:02:57 lr 0.000947	time 1.5473 (2.1955)	loss 5.3604 (4.5687)	grad_norm 1.3080 (1.3904)	
[2022-01-18 02:24:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1180/1251]	eta 0:02:35 lr 0.000947	time 1.9002 (2.1955)	loss 4.2464 (4.5693)	grad_norm 1.2730 (1.3898)	
[2022-01-18 02:24:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1190/1251]	eta 0:02:13 lr 0.000948	time 2.1250 (2.1952)	loss 4.9906 (4.5690)	grad_norm 1.3829 (1.3885)	
[2022-01-18 02:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1200/1251]	eta 0:01:51 lr 0.000948	time 2.4539 (2.1951)	loss 5.4183 (4.5702)	grad_norm 1.2548 (1.3875)	
[2022-01-18 02:25:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1210/1251]	eta 0:01:29 lr 0.000948	time 1.7287 (2.1946)	loss 3.2489 (4.5686)	grad_norm 1.2098 (1.3870)	
[2022-01-18 02:25:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1220/1251]	eta 0:01:08 lr 0.000949	time 1.8893 (2.1947)	loss 4.3378 (4.5694)	grad_norm 1.1960 (1.3860)	
[2022-01-18 02:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1230/1251]	eta 0:00:46 lr 0.000949	time 2.1772 (2.1960)	loss 4.1521 (4.5684)	grad_norm 1.1451 (1.3853)	
[2022-01-18 02:26:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1240/1251]	eta 0:00:24 lr 0.000950	time 1.9381 (2.1965)	loss 4.4860 (4.5668)	grad_norm 1.5847 (1.3851)	
[2022-01-18 02:27:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [18/300][1250/1251]	eta 0:00:02 lr 0.000950	time 1.1841 (2.1916)	loss 4.1286 (4.5682)	grad_norm 1.3897 (1.3851)	
[2022-01-18 02:27:02 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 18 training takes 0:45:42
[2022-01-18 02:27:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.446 (18.446)	Loss 1.9751 (1.9751)	Acc@1 56.738 (56.738)	Acc@5 81.250 (81.250)	
[2022-01-18 02:27:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.868 (3.199)	Loss 2.0019 (1.9462)	Acc@1 56.836 (57.218)	Acc@5 79.102 (81.232)	
[2022-01-18 02:27:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.272 (2.626)	Loss 1.9708 (1.9320)	Acc@1 55.762 (57.082)	Acc@5 81.543 (81.464)	
[2022-01-18 02:28:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.939 (2.293)	Loss 1.9886 (1.9170)	Acc@1 56.836 (57.277)	Acc@5 79.785 (81.726)	
[2022-01-18 02:28:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 5.128 (2.159)	Loss 1.8659 (1.9163)	Acc@1 59.180 (57.460)	Acc@5 82.227 (81.650)	
[2022-01-18 02:28:37 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 57.618 Acc@5 81.662
[2022-01-18 02:28:37 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 57.6%
[2022-01-18 02:28:37 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 57.62%
[2022-01-18 02:28:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][0/1251]	eta 7:33:02 lr 0.000950	time 21.7285 (21.7285)	loss 4.4236 (4.4236)	grad_norm 1.2324 (1.2324)	
[2022-01-18 02:29:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][10/1251]	eta 1:23:59 lr 0.000950	time 1.3619 (4.0612)	loss 4.7862 (4.5174)	grad_norm 1.2908 (1.3194)	
[2022-01-18 02:29:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][20/1251]	eta 1:06:13 lr 0.000951	time 1.9029 (3.2282)	loss 5.0726 (4.3819)	grad_norm 1.3189 (1.3349)	
[2022-01-18 02:30:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][30/1251]	eta 0:58:31 lr 0.000951	time 1.8957 (2.8755)	loss 5.1269 (4.4198)	grad_norm 1.7272 (1.3495)	
[2022-01-18 02:30:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][40/1251]	eta 0:54:47 lr 0.000952	time 2.8330 (2.7149)	loss 5.0703 (4.4118)	grad_norm 1.4602 (1.3790)	
[2022-01-18 02:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][50/1251]	eta 0:52:46 lr 0.000952	time 2.1488 (2.6366)	loss 4.4655 (4.4021)	grad_norm 1.5010 (1.4002)	
[2022-01-18 02:31:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][60/1251]	eta 0:51:20 lr 0.000952	time 2.5368 (2.5864)	loss 4.9597 (4.4350)	grad_norm 1.3659 (1.3838)	
[2022-01-18 02:31:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][70/1251]	eta 0:49:53 lr 0.000953	time 1.9339 (2.5343)	loss 3.9276 (4.4586)	grad_norm 1.1932 (1.3932)	
[2022-01-18 02:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][80/1251]	eta 0:48:24 lr 0.000953	time 2.1940 (2.4808)	loss 5.0989 (4.4292)	grad_norm 1.4012 (1.4120)	
[2022-01-18 02:32:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][90/1251]	eta 0:47:38 lr 0.000954	time 2.1903 (2.4617)	loss 5.3143 (4.4495)	grad_norm 1.2940 (1.4045)	
[2022-01-18 02:32:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][100/1251]	eta 0:46:25 lr 0.000954	time 1.8864 (2.4201)	loss 4.9881 (4.4874)	grad_norm 1.5778 (1.4163)	
[2022-01-18 02:33:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][110/1251]	eta 0:45:33 lr 0.000954	time 2.3866 (2.3957)	loss 5.0078 (4.4757)	grad_norm 1.2575 (1.4198)	
[2022-01-18 02:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][120/1251]	eta 0:44:38 lr 0.000955	time 1.7096 (2.3685)	loss 5.1116 (4.4906)	grad_norm 1.1148 (1.4045)	
[2022-01-18 02:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][130/1251]	eta 0:44:02 lr 0.000955	time 1.8281 (2.3569)	loss 3.9760 (4.4896)	grad_norm 1.4717 (1.4033)	
[2022-01-18 02:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][140/1251]	eta 0:43:31 lr 0.000956	time 2.8624 (2.3508)	loss 4.9071 (4.4981)	grad_norm 1.5209 (1.3918)	
[2022-01-18 02:34:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][150/1251]	eta 0:42:39 lr 0.000956	time 1.7594 (2.3243)	loss 4.8679 (4.5047)	grad_norm 1.7304 (1.3966)	
[2022-01-18 02:34:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][160/1251]	eta 0:42:07 lr 0.000956	time 2.5041 (2.3169)	loss 4.8433 (4.5079)	grad_norm 1.1510 (1.3888)	
[2022-01-18 02:35:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][170/1251]	eta 0:41:45 lr 0.000957	time 1.5470 (2.3174)	loss 4.3758 (4.5147)	grad_norm 1.3058 (1.3796)	
[2022-01-18 02:35:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][180/1251]	eta 0:41:25 lr 0.000957	time 2.8367 (2.3208)	loss 4.7628 (4.5113)	grad_norm 1.3938 (1.3735)	
[2022-01-18 02:36:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][190/1251]	eta 0:40:59 lr 0.000958	time 1.7922 (2.3183)	loss 5.2266 (4.5186)	grad_norm 1.4039 (1.3740)	
[2022-01-18 02:36:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][200/1251]	eta 0:40:31 lr 0.000958	time 2.5717 (2.3134)	loss 3.5529 (4.5210)	grad_norm 1.4706 (1.3749)	
[2022-01-18 02:36:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][210/1251]	eta 0:39:55 lr 0.000958	time 1.7846 (2.3009)	loss 3.7267 (4.5205)	grad_norm 1.3371 (1.3759)	
[2022-01-18 02:37:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][220/1251]	eta 0:39:21 lr 0.000959	time 2.2089 (2.2901)	loss 4.4845 (4.5241)	grad_norm 1.3765 (1.3746)	
[2022-01-18 02:37:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][230/1251]	eta 0:38:47 lr 0.000959	time 2.5861 (2.2793)	loss 4.7741 (4.5214)	grad_norm 1.6721 (1.3853)	
[2022-01-18 02:37:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][240/1251]	eta 0:38:15 lr 0.000960	time 2.1926 (2.2703)	loss 4.6820 (4.5371)	grad_norm 1.4128 (1.3879)	
[2022-01-18 02:38:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][250/1251]	eta 0:37:43 lr 0.000960	time 1.8620 (2.2616)	loss 3.9658 (4.5331)	grad_norm 1.6478 (1.3929)	
[2022-01-18 02:38:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][260/1251]	eta 0:37:18 lr 0.000960	time 2.5411 (2.2586)	loss 4.9592 (4.5303)	grad_norm 1.2044 (1.3913)	
[2022-01-18 02:38:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][270/1251]	eta 0:36:57 lr 0.000961	time 1.7542 (2.2601)	loss 3.8747 (4.5214)	grad_norm 1.1952 (1.3956)	
[2022-01-18 02:39:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][280/1251]	eta 0:36:31 lr 0.000961	time 2.5824 (2.2570)	loss 5.3297 (4.5286)	grad_norm 1.1263 (1.3911)	
[2022-01-18 02:39:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][290/1251]	eta 0:36:06 lr 0.000962	time 1.8975 (2.2549)	loss 5.0470 (4.5292)	grad_norm 1.1397 (1.3888)	
[2022-01-18 02:39:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][300/1251]	eta 0:35:42 lr 0.000962	time 1.8898 (2.2528)	loss 3.6027 (4.5200)	grad_norm 1.0376 (1.3860)	
[2022-01-18 02:40:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][310/1251]	eta 0:35:22 lr 0.000962	time 2.1900 (2.2553)	loss 3.5806 (4.5210)	grad_norm 1.3879 (1.3831)	
[2022-01-18 02:40:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][320/1251]	eta 0:34:57 lr 0.000963	time 2.6301 (2.2532)	loss 4.4691 (4.5224)	grad_norm 1.2869 (1.3843)	
[2022-01-18 02:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][330/1251]	eta 0:34:39 lr 0.000963	time 3.1374 (2.2579)	loss 4.3931 (4.5298)	grad_norm 1.0516 (1.3808)	
[2022-01-18 02:41:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][340/1251]	eta 0:34:13 lr 0.000964	time 1.8878 (2.2546)	loss 4.9525 (4.5303)	grad_norm 1.1198 (1.3828)	
[2022-01-18 02:41:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][350/1251]	eta 0:33:48 lr 0.000964	time 2.5461 (2.2509)	loss 4.6934 (4.5283)	grad_norm 1.1276 (1.3792)	
[2022-01-18 02:42:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][360/1251]	eta 0:33:19 lr 0.000964	time 2.7742 (2.2442)	loss 4.1152 (4.5203)	grad_norm 1.3621 (1.3782)	
[2022-01-18 02:42:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][370/1251]	eta 0:32:52 lr 0.000965	time 1.7399 (2.2390)	loss 5.0426 (4.5287)	grad_norm 1.7103 (1.3815)	
[2022-01-18 02:42:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][380/1251]	eta 0:32:25 lr 0.000965	time 1.7481 (2.2339)	loss 4.2939 (4.5336)	grad_norm 1.4788 (1.3839)	
[2022-01-18 02:43:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][390/1251]	eta 0:32:02 lr 0.000966	time 2.1528 (2.2329)	loss 5.3112 (4.5409)	grad_norm 1.3790 (1.3820)	
[2022-01-18 02:43:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][400/1251]	eta 0:31:42 lr 0.000966	time 3.0463 (2.2351)	loss 3.6083 (4.5446)	grad_norm 1.1975 (1.3824)	
[2022-01-18 02:43:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][410/1251]	eta 0:31:21 lr 0.000966	time 2.7804 (2.2368)	loss 4.7628 (4.5414)	grad_norm 1.4894 (1.3799)	
[2022-01-18 02:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][420/1251]	eta 0:30:56 lr 0.000967	time 1.6033 (2.2341)	loss 4.7843 (4.5441)	grad_norm 1.6577 (1.3849)	
[2022-01-18 02:44:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][430/1251]	eta 0:30:34 lr 0.000967	time 2.5837 (2.2343)	loss 4.7523 (4.5450)	grad_norm 1.2517 (1.3825)	
[2022-01-18 02:45:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][440/1251]	eta 0:30:10 lr 0.000968	time 1.4777 (2.2320)	loss 4.9605 (4.5479)	grad_norm 1.3188 (1.3828)	
[2022-01-18 02:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][450/1251]	eta 0:29:48 lr 0.000968	time 2.4936 (2.2324)	loss 4.9478 (4.5467)	grad_norm 1.0541 (1.3845)	
[2022-01-18 02:45:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][460/1251]	eta 0:29:22 lr 0.000968	time 1.4462 (2.2287)	loss 3.8964 (4.5438)	grad_norm 1.2874 (1.3848)	
[2022-01-18 02:46:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][470/1251]	eta 0:29:00 lr 0.000969	time 2.3876 (2.2285)	loss 4.0160 (4.5414)	grad_norm 1.7449 (1.3834)	
[2022-01-18 02:46:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][480/1251]	eta 0:28:35 lr 0.000969	time 1.5046 (2.2248)	loss 4.2973 (4.5450)	grad_norm 1.6822 (1.3838)	
[2022-01-18 02:46:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][490/1251]	eta 0:28:14 lr 0.000970	time 2.2002 (2.2263)	loss 5.4072 (4.5452)	grad_norm 1.1694 (1.3822)	
[2022-01-18 02:47:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][500/1251]	eta 0:27:54 lr 0.000970	time 1.5786 (2.2295)	loss 4.5174 (4.5470)	grad_norm 1.4631 (1.3811)	
[2022-01-18 02:47:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][510/1251]	eta 0:27:33 lr 0.000970	time 2.0877 (2.2315)	loss 5.0789 (4.5498)	grad_norm 1.2118 (1.3804)	
[2022-01-18 02:47:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][520/1251]	eta 0:27:08 lr 0.000971	time 1.7750 (2.2283)	loss 4.2929 (4.5451)	grad_norm 1.5401 (1.3786)	
[2022-01-18 02:48:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][530/1251]	eta 0:26:44 lr 0.000971	time 1.8720 (2.2249)	loss 4.9364 (4.5464)	grad_norm 1.5778 (1.3775)	
[2022-01-18 02:48:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][540/1251]	eta 0:26:21 lr 0.000972	time 1.9846 (2.2240)	loss 3.8333 (4.5513)	grad_norm 1.4727 (1.3779)	
[2022-01-18 02:49:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][550/1251]	eta 0:25:56 lr 0.000972	time 1.5806 (2.2209)	loss 4.4913 (4.5545)	grad_norm 1.7969 (1.3779)	
[2022-01-18 02:49:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][560/1251]	eta 0:25:33 lr 0.000972	time 2.0933 (2.2186)	loss 4.8440 (4.5530)	grad_norm 1.8361 (1.3793)	
[2022-01-18 02:49:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][570/1251]	eta 0:25:09 lr 0.000973	time 1.9269 (2.2165)	loss 4.9361 (4.5541)	grad_norm 1.8751 (1.3797)	
[2022-01-18 02:50:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][580/1251]	eta 0:24:46 lr 0.000973	time 1.5070 (2.2157)	loss 5.0075 (4.5537)	grad_norm 1.3094 (1.3778)	
[2022-01-18 02:50:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][590/1251]	eta 0:24:25 lr 0.000974	time 1.9763 (2.2165)	loss 3.3715 (4.5485)	grad_norm 1.3354 (1.3747)	
[2022-01-18 02:50:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][600/1251]	eta 0:24:03 lr 0.000974	time 1.5956 (2.2180)	loss 4.4340 (4.5476)	grad_norm 1.3445 (1.3737)	
[2022-01-18 02:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][610/1251]	eta 0:23:44 lr 0.000974	time 2.6993 (2.2221)	loss 3.5839 (4.5444)	grad_norm 1.3442 (1.3725)	
[2022-01-18 02:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][620/1251]	eta 0:23:21 lr 0.000975	time 1.5301 (2.2212)	loss 5.3671 (4.5433)	grad_norm 1.3381 (1.3715)	
[2022-01-18 02:51:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][630/1251]	eta 0:22:57 lr 0.000975	time 1.9301 (2.2184)	loss 5.0148 (4.5446)	grad_norm 1.1290 (1.3694)	
[2022-01-18 02:52:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][640/1251]	eta 0:22:34 lr 0.000976	time 1.9169 (2.2162)	loss 4.9426 (4.5472)	grad_norm 1.0251 (1.3673)	
[2022-01-18 02:52:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][650/1251]	eta 0:22:11 lr 0.000976	time 2.8514 (2.2152)	loss 5.1503 (4.5470)	grad_norm 1.4524 (1.3665)	
[2022-01-18 02:53:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][660/1251]	eta 0:21:48 lr 0.000976	time 1.7209 (2.2140)	loss 4.4468 (4.5412)	grad_norm 1.1791 (1.3657)	
[2022-01-18 02:53:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][670/1251]	eta 0:21:26 lr 0.000977	time 1.9107 (2.2143)	loss 3.9993 (4.5413)	grad_norm 1.3407 (1.3643)	
[2022-01-18 02:53:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][680/1251]	eta 0:21:04 lr 0.000977	time 2.2544 (2.2147)	loss 3.8541 (4.5346)	grad_norm 1.2753 (1.3632)	
[2022-01-18 02:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][690/1251]	eta 0:20:42 lr 0.000978	time 2.2058 (2.2139)	loss 4.7765 (4.5349)	grad_norm 1.5110 (1.3629)	
[2022-01-18 02:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][700/1251]	eta 0:20:19 lr 0.000978	time 2.2656 (2.2136)	loss 4.5949 (4.5350)	grad_norm 1.4847 (1.3620)	
[2022-01-18 02:54:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][710/1251]	eta 0:19:56 lr 0.000978	time 1.8343 (2.2114)	loss 4.9014 (4.5370)	grad_norm 0.9549 (1.3603)	
[2022-01-18 02:55:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][720/1251]	eta 0:19:34 lr 0.000979	time 2.7203 (2.2110)	loss 4.9681 (4.5366)	grad_norm 1.5581 (1.3632)	
[2022-01-18 02:55:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][730/1251]	eta 0:19:11 lr 0.000979	time 2.1814 (2.2109)	loss 4.9703 (4.5355)	grad_norm 1.4375 (1.3642)	
[2022-01-18 02:55:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][740/1251]	eta 0:18:48 lr 0.000980	time 1.6416 (2.2090)	loss 4.5747 (4.5355)	grad_norm 1.2119 (1.3627)	
[2022-01-18 02:56:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][750/1251]	eta 0:18:26 lr 0.000980	time 1.5331 (2.2079)	loss 4.5510 (4.5356)	grad_norm 1.4080 (1.3651)	
[2022-01-18 02:56:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][760/1251]	eta 0:18:04 lr 0.000980	time 2.7650 (2.2095)	loss 4.3782 (4.5345)	grad_norm 1.2916 (1.3648)	
[2022-01-18 02:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][770/1251]	eta 0:17:42 lr 0.000981	time 1.8773 (2.2099)	loss 4.7131 (4.5388)	grad_norm 1.6331 (1.3640)	
[2022-01-18 02:57:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][780/1251]	eta 0:17:21 lr 0.000981	time 1.6109 (2.2104)	loss 3.6773 (4.5416)	grad_norm 1.4984 (1.3662)	
[2022-01-18 02:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][790/1251]	eta 0:16:59 lr 0.000982	time 1.5924 (2.2113)	loss 3.2550 (4.5398)	grad_norm 1.3710 (1.3663)	
[2022-01-18 02:58:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][800/1251]	eta 0:16:37 lr 0.000982	time 2.7444 (2.2116)	loss 4.5750 (4.5407)	grad_norm 1.0743 (1.3646)	
[2022-01-18 02:58:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][810/1251]	eta 0:16:14 lr 0.000982	time 1.8379 (2.2102)	loss 4.5708 (4.5426)	grad_norm 1.1409 (1.3632)	
[2022-01-18 02:58:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][820/1251]	eta 0:15:51 lr 0.000983	time 1.5306 (2.2075)	loss 4.5281 (4.5421)	grad_norm 1.4621 (1.3648)	
[2022-01-18 02:59:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][830/1251]	eta 0:15:29 lr 0.000983	time 2.1171 (2.2068)	loss 4.3598 (4.5408)	grad_norm 1.1201 (1.3642)	
[2022-01-18 02:59:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][840/1251]	eta 0:15:06 lr 0.000984	time 2.3423 (2.2049)	loss 4.5791 (4.5394)	grad_norm 1.1347 (1.3637)	
[2022-01-18 02:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][850/1251]	eta 0:14:44 lr 0.000984	time 2.0058 (2.2048)	loss 5.2749 (4.5386)	grad_norm 1.1613 (1.3624)	
[2022-01-18 03:00:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][860/1251]	eta 0:14:21 lr 0.000984	time 1.4624 (2.2032)	loss 3.4951 (4.5407)	grad_norm 1.1876 (1.3623)	
[2022-01-18 03:00:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][870/1251]	eta 0:14:00 lr 0.000985	time 2.4656 (2.2058)	loss 4.2036 (4.5402)	grad_norm 1.1096 (1.3613)	
[2022-01-18 03:01:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][880/1251]	eta 0:13:38 lr 0.000985	time 1.9526 (2.2066)	loss 4.5010 (4.5419)	grad_norm 1.3257 (1.3616)	
[2022-01-18 03:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][890/1251]	eta 0:13:16 lr 0.000986	time 2.1152 (2.2068)	loss 3.3720 (4.5437)	grad_norm 1.9192 (1.3609)	
[2022-01-18 03:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][900/1251]	eta 0:12:54 lr 0.000986	time 1.8476 (2.2059)	loss 4.6294 (4.5453)	grad_norm 1.3367 (1.3617)	
[2022-01-18 03:02:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][910/1251]	eta 0:12:31 lr 0.000986	time 1.5507 (2.2033)	loss 5.0396 (4.5448)	grad_norm 1.3806 (1.3628)	
[2022-01-18 03:02:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][920/1251]	eta 0:12:08 lr 0.000987	time 2.2050 (2.2015)	loss 4.8385 (4.5454)	grad_norm 1.1520 (1.3626)	
[2022-01-18 03:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][930/1251]	eta 0:11:46 lr 0.000987	time 1.7012 (2.2016)	loss 4.2210 (4.5467)	grad_norm 1.3168 (1.3618)	
[2022-01-18 03:03:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][940/1251]	eta 0:11:24 lr 0.000988	time 2.0471 (2.2025)	loss 4.7784 (4.5470)	grad_norm 1.6914 (1.3624)	
[2022-01-18 03:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][950/1251]	eta 0:11:04 lr 0.000988	time 3.5665 (2.2062)	loss 5.3265 (4.5481)	grad_norm 1.3518 (1.3618)	
[2022-01-18 03:03:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][960/1251]	eta 0:10:42 lr 0.000988	time 2.2414 (2.2081)	loss 5.0539 (4.5485)	grad_norm 1.0354 (1.3613)	
[2022-01-18 03:04:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][970/1251]	eta 0:10:20 lr 0.000989	time 1.5512 (2.2067)	loss 5.4154 (4.5535)	grad_norm 1.4794 (1.3604)	
[2022-01-18 03:04:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][980/1251]	eta 0:09:57 lr 0.000989	time 2.0136 (2.2057)	loss 4.7126 (4.5565)	grad_norm 1.0759 (1.3606)	
[2022-01-18 03:05:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][990/1251]	eta 0:09:36 lr 0.000990	time 2.5338 (2.2069)	loss 4.2097 (4.5567)	grad_norm 1.9835 (1.3616)	
[2022-01-18 03:05:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1000/1251]	eta 0:09:14 lr 0.000990	time 1.8589 (2.2081)	loss 4.7286 (4.5574)	grad_norm 1.2052 (1.3620)	
[2022-01-18 03:05:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1010/1251]	eta 0:08:51 lr 0.000990	time 1.5921 (2.2066)	loss 3.2403 (4.5567)	grad_norm 1.3119 (1.3614)	
[2022-01-18 03:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1020/1251]	eta 0:08:29 lr 0.000991	time 1.5795 (2.2049)	loss 5.1598 (4.5512)	grad_norm 1.3092 (1.3603)	
[2022-01-18 03:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1030/1251]	eta 0:08:06 lr 0.000991	time 1.8921 (2.2035)	loss 4.7072 (4.5505)	grad_norm 1.2244 (1.3602)	
[2022-01-18 03:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1040/1251]	eta 0:07:44 lr 0.000992	time 2.6326 (2.2035)	loss 5.2713 (4.5492)	grad_norm 1.2332 (1.3593)	
[2022-01-18 03:07:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1050/1251]	eta 0:07:22 lr 0.000992	time 1.9523 (2.2025)	loss 5.0670 (4.5505)	grad_norm 1.3526 (1.3595)	
[2022-01-18 03:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1060/1251]	eta 0:07:00 lr 0.000992	time 2.8756 (2.2015)	loss 4.1627 (4.5482)	grad_norm 1.1274 (1.3597)	
[2022-01-18 03:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1070/1251]	eta 0:06:38 lr 0.000993	time 2.2790 (2.2021)	loss 3.3762 (4.5475)	grad_norm 1.3243 (1.3595)	
[2022-01-18 03:08:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1080/1251]	eta 0:06:16 lr 0.000993	time 2.5288 (2.2024)	loss 5.0719 (4.5494)	grad_norm 1.5190 (1.3594)	
[2022-01-18 03:08:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1090/1251]	eta 0:05:54 lr 0.000994	time 1.6171 (2.2030)	loss 4.8391 (4.5508)	grad_norm 1.6585 (1.3606)	
[2022-01-18 03:09:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1100/1251]	eta 0:05:32 lr 0.000994	time 2.3013 (2.2029)	loss 5.4834 (4.5528)	grad_norm 1.6167 (1.3602)	
[2022-01-18 03:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1110/1251]	eta 0:05:10 lr 0.000994	time 1.9300 (2.2025)	loss 3.9820 (4.5519)	grad_norm 1.1595 (1.3596)	
[2022-01-18 03:09:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1120/1251]	eta 0:04:48 lr 0.000995	time 2.7010 (2.2022)	loss 3.9145 (4.5539)	grad_norm 1.2574 (1.3583)	
[2022-01-18 03:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1130/1251]	eta 0:04:26 lr 0.000995	time 1.7483 (2.2018)	loss 3.7903 (4.5512)	grad_norm 1.4225 (1.3585)	
[2022-01-18 03:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1140/1251]	eta 0:04:04 lr 0.000996	time 1.9112 (2.2016)	loss 3.7771 (4.5505)	grad_norm 1.5646 (1.3586)	
[2022-01-18 03:10:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1150/1251]	eta 0:03:42 lr 0.000996	time 2.2347 (2.2016)	loss 4.4218 (4.5489)	grad_norm 1.2272 (1.3580)	
[2022-01-18 03:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1160/1251]	eta 0:03:20 lr 0.000996	time 3.0277 (2.2024)	loss 3.2858 (4.5488)	grad_norm 1.1135 (1.3578)	
[2022-01-18 03:11:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1170/1251]	eta 0:02:58 lr 0.000997	time 1.9512 (2.2038)	loss 4.9121 (4.5496)	grad_norm 1.2215 (1.3571)	
[2022-01-18 03:12:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1180/1251]	eta 0:02:36 lr 0.000997	time 1.6640 (2.2036)	loss 4.5060 (4.5505)	grad_norm 1.0829 (1.3558)	
[2022-01-18 03:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1190/1251]	eta 0:02:14 lr 0.000998	time 2.2796 (2.2028)	loss 4.6174 (4.5535)	grad_norm 1.2879 (1.3554)	
[2022-01-18 03:12:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1200/1251]	eta 0:01:52 lr 0.000998	time 2.3062 (2.2007)	loss 4.8450 (4.5525)	grad_norm 1.5468 (1.3557)	
[2022-01-18 03:13:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1210/1251]	eta 0:01:30 lr 0.000998	time 1.9730 (2.1989)	loss 3.6910 (4.5557)	grad_norm 1.2215 (1.3558)	
[2022-01-18 03:13:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1220/1251]	eta 0:01:08 lr 0.000999	time 2.5118 (2.1989)	loss 3.3549 (4.5532)	grad_norm 1.2125 (1.3559)	
[2022-01-18 03:13:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1230/1251]	eta 0:00:46 lr 0.000999	time 2.4732 (2.1995)	loss 4.7267 (4.5542)	grad_norm 1.2418 (1.3559)	
[2022-01-18 03:14:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1240/1251]	eta 0:00:24 lr 0.001000	time 1.8339 (2.1988)	loss 4.0747 (4.5547)	grad_norm 1.2792 (1.3555)	
[2022-01-18 03:14:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [19/300][1250/1251]	eta 0:00:02 lr 0.001000	time 1.1993 (2.1932)	loss 5.0036 (4.5538)	grad_norm 1.1278 (1.3548)	
[2022-01-18 03:14:21 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 19 training takes 0:45:44
[2022-01-18 03:14:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.958 (17.958)	Loss 1.8532 (1.8532)	Acc@1 58.105 (58.105)	Acc@5 82.227 (82.227)	
[2022-01-18 03:14:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.613 (3.327)	Loss 1.8179 (1.8100)	Acc@1 58.887 (59.553)	Acc@5 82.812 (82.812)	
[2022-01-18 03:15:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.922 (2.586)	Loss 1.9512 (1.8360)	Acc@1 55.469 (59.003)	Acc@5 80.469 (82.375)	
[2022-01-18 03:15:32 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.626 (2.287)	Loss 1.7876 (1.8384)	Acc@1 59.766 (58.959)	Acc@5 84.082 (82.353)	
[2022-01-18 03:15:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.588 (2.160)	Loss 1.8069 (1.8382)	Acc@1 60.742 (59.013)	Acc@5 83.008 (82.389)	
[2022-01-18 03:15:58 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 58.988 Acc@5 82.560
[2022-01-18 03:15:58 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 59.0%
[2022-01-18 03:15:58 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 58.99%
[2022-01-18 03:16:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][0/1251]	eta 7:20:01 lr 0.000989	time 21.1041 (21.1041)	loss 4.3490 (4.3490)	grad_norm 1.2131 (1.2131)	
[2022-01-18 03:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][10/1251]	eta 1:22:12 lr 0.000989	time 1.8092 (3.9747)	loss 3.9874 (4.5802)	grad_norm 1.3414 (1.3378)	
[2022-01-18 03:17:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][20/1251]	eta 1:05:12 lr 0.000989	time 1.4633 (3.1785)	loss 3.3249 (4.5802)	grad_norm 1.1736 (1.3360)	
[2022-01-18 03:17:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][30/1251]	eta 0:57:34 lr 0.000989	time 1.5673 (2.8290)	loss 5.4867 (4.5550)	grad_norm 1.2265 (1.2967)	
[2022-01-18 03:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][40/1251]	eta 0:54:47 lr 0.000989	time 3.6873 (2.7150)	loss 3.7357 (4.4543)	grad_norm 1.2428 (1.2850)	
[2022-01-18 03:18:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][50/1251]	eta 0:53:24 lr 0.000989	time 2.4485 (2.6679)	loss 3.5934 (4.4377)	grad_norm 1.6444 (1.3186)	
[2022-01-18 03:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][60/1251]	eta 0:51:40 lr 0.000989	time 1.4800 (2.6033)	loss 4.2683 (4.4451)	grad_norm 1.0312 (1.3207)	
[2022-01-18 03:18:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][70/1251]	eta 0:49:41 lr 0.000989	time 1.8537 (2.5242)	loss 4.5832 (4.4764)	grad_norm 1.3020 (1.3318)	
[2022-01-18 03:19:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][80/1251]	eta 0:48:17 lr 0.000989	time 3.2768 (2.4742)	loss 5.0064 (4.4791)	grad_norm 1.4359 (1.3524)	
[2022-01-18 03:19:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][90/1251]	eta 0:47:09 lr 0.000989	time 1.9281 (2.4371)	loss 4.0656 (4.4594)	grad_norm 2.1249 (1.3702)	
[2022-01-18 03:20:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][100/1251]	eta 0:46:26 lr 0.000989	time 2.2045 (2.4209)	loss 4.2083 (4.4198)	grad_norm 1.5033 (1.3822)	
[2022-01-18 03:20:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][110/1251]	eta 0:45:45 lr 0.000989	time 2.2410 (2.4065)	loss 5.4515 (4.4293)	grad_norm 1.1034 (1.3705)	
[2022-01-18 03:20:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][120/1251]	eta 0:45:12 lr 0.000989	time 2.8725 (2.3984)	loss 5.1375 (4.4313)	grad_norm 1.3459 (1.3626)	
[2022-01-18 03:21:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][130/1251]	eta 0:44:42 lr 0.000989	time 2.1535 (2.3932)	loss 3.9341 (4.4251)	grad_norm 1.2217 (1.3604)	
[2022-01-18 03:21:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][140/1251]	eta 0:43:55 lr 0.000989	time 1.8992 (2.3722)	loss 4.4444 (4.4254)	grad_norm 1.2591 (1.3601)	
[2022-01-18 03:21:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][150/1251]	eta 0:43:09 lr 0.000989	time 2.0714 (2.3521)	loss 4.2721 (4.4430)	grad_norm 1.1744 (1.3580)	
[2022-01-18 03:22:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][160/1251]	eta 0:42:17 lr 0.000989	time 2.3259 (2.3263)	loss 5.0394 (4.4544)	grad_norm 1.4334 (1.3539)	
[2022-01-18 03:22:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][170/1251]	eta 0:41:38 lr 0.000989	time 2.1498 (2.3114)	loss 4.0710 (4.4377)	grad_norm 1.3168 (1.3511)	
[2022-01-18 03:22:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][180/1251]	eta 0:41:08 lr 0.000989	time 2.2126 (2.3050)	loss 5.0287 (4.4534)	grad_norm 1.1780 (1.3401)	
[2022-01-18 03:23:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][190/1251]	eta 0:40:44 lr 0.000989	time 2.4124 (2.3038)	loss 4.4503 (4.4683)	grad_norm 1.3012 (1.3363)	
[2022-01-18 03:23:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][200/1251]	eta 0:40:17 lr 0.000989	time 2.2001 (2.3005)	loss 4.3132 (4.4836)	grad_norm 1.3157 (1.3313)	
[2022-01-18 03:24:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][210/1251]	eta 0:40:00 lr 0.000989	time 2.3853 (2.3058)	loss 4.4379 (4.5005)	grad_norm 1.2863 (1.3234)	
[2022-01-18 03:24:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][220/1251]	eta 0:39:33 lr 0.000989	time 2.2332 (2.3023)	loss 3.2421 (4.5031)	grad_norm 1.4003 (1.3235)	
[2022-01-18 03:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][230/1251]	eta 0:38:58 lr 0.000989	time 1.7994 (2.2908)	loss 4.4038 (4.5088)	grad_norm 1.0251 (1.3216)	
[2022-01-18 03:25:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][240/1251]	eta 0:38:23 lr 0.000989	time 2.1224 (2.2785)	loss 3.6048 (4.5051)	grad_norm 1.3013 (1.3272)	
[2022-01-18 03:25:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][250/1251]	eta 0:37:48 lr 0.000989	time 1.8705 (2.2661)	loss 4.4091 (4.5016)	grad_norm 1.2742 (1.3242)	
[2022-01-18 03:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][260/1251]	eta 0:37:20 lr 0.000989	time 2.1331 (2.2608)	loss 4.8725 (4.5013)	grad_norm 2.3956 (1.3299)	
[2022-01-18 03:26:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][270/1251]	eta 0:36:56 lr 0.000989	time 2.2441 (2.2595)	loss 3.9529 (4.5038)	grad_norm 1.1306 (1.3378)	
[2022-01-18 03:26:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][280/1251]	eta 0:36:30 lr 0.000989	time 2.6714 (2.2557)	loss 3.8989 (4.5099)	grad_norm 1.1384 (1.3337)	
[2022-01-18 03:26:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][290/1251]	eta 0:36:05 lr 0.000989	time 2.4979 (2.2530)	loss 4.0866 (4.5064)	grad_norm 1.9094 (1.3386)	
[2022-01-18 03:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][300/1251]	eta 0:35:42 lr 0.000989	time 2.1690 (2.2532)	loss 3.4925 (4.5046)	grad_norm 1.0898 (1.3369)	
[2022-01-18 03:27:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][310/1251]	eta 0:35:18 lr 0.000989	time 2.1966 (2.2509)	loss 5.0977 (4.5025)	grad_norm 1.7375 (1.3380)	
[2022-01-18 03:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][320/1251]	eta 0:34:51 lr 0.000989	time 1.8183 (2.2469)	loss 4.9338 (4.5099)	grad_norm 1.8075 (1.3373)	
[2022-01-18 03:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][330/1251]	eta 0:34:34 lr 0.000989	time 3.1404 (2.2520)	loss 4.8558 (4.5108)	grad_norm 1.2601 (1.3365)	
[2022-01-18 03:28:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][340/1251]	eta 0:34:08 lr 0.000989	time 1.6185 (2.2491)	loss 4.5871 (4.5166)	grad_norm 1.2651 (1.3337)	
[2022-01-18 03:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][350/1251]	eta 0:33:45 lr 0.000989	time 2.3461 (2.2477)	loss 5.1920 (4.5137)	grad_norm 1.3818 (1.3317)	
[2022-01-18 03:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][360/1251]	eta 0:33:19 lr 0.000989	time 2.5882 (2.2436)	loss 4.6357 (4.5063)	grad_norm 1.1682 (1.3282)	
[2022-01-18 03:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][370/1251]	eta 0:32:54 lr 0.000989	time 2.3744 (2.2409)	loss 4.2295 (4.5077)	grad_norm 1.2928 (1.3266)	
[2022-01-18 03:30:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][380/1251]	eta 0:32:28 lr 0.000989	time 1.8500 (2.2366)	loss 4.8767 (4.5055)	grad_norm 1.3539 (1.3292)	
[2022-01-18 03:30:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][390/1251]	eta 0:32:04 lr 0.000989	time 2.3103 (2.2351)	loss 3.8622 (4.5022)	grad_norm 1.6188 (1.3296)	
[2022-01-18 03:30:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][400/1251]	eta 0:31:41 lr 0.000989	time 2.4833 (2.2342)	loss 5.0967 (4.5004)	grad_norm 1.2141 (1.3285)	
[2022-01-18 03:31:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][410/1251]	eta 0:31:20 lr 0.000989	time 2.7180 (2.2365)	loss 5.2363 (4.4976)	grad_norm 1.5551 (1.3274)	
[2022-01-18 03:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][420/1251]	eta 0:30:56 lr 0.000989	time 1.6221 (2.2339)	loss 4.7529 (4.5096)	grad_norm 1.3681 (1.3273)	
[2022-01-18 03:32:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][430/1251]	eta 0:30:31 lr 0.000989	time 2.1253 (2.2309)	loss 5.1136 (4.5172)	grad_norm 1.4016 (1.3291)	
[2022-01-18 03:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][440/1251]	eta 0:30:05 lr 0.000989	time 2.2286 (2.2265)	loss 4.5585 (4.5095)	grad_norm 1.4347 (1.3319)	
[2022-01-18 03:32:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][450/1251]	eta 0:29:40 lr 0.000989	time 1.9975 (2.2228)	loss 5.1827 (4.5021)	grad_norm 1.0367 (1.3299)	
[2022-01-18 03:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][460/1251]	eta 0:29:15 lr 0.000989	time 1.8686 (2.2189)	loss 4.7894 (4.5050)	grad_norm 1.2798 (1.3284)	
[2022-01-18 03:33:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][470/1251]	eta 0:28:55 lr 0.000989	time 2.8833 (2.2216)	loss 4.0162 (4.5040)	grad_norm 1.0960 (1.3254)	
[2022-01-18 03:33:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][480/1251]	eta 0:28:33 lr 0.000989	time 2.7864 (2.2229)	loss 3.4572 (4.4976)	grad_norm 1.4374 (1.3226)	
[2022-01-18 03:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][490/1251]	eta 0:28:10 lr 0.000989	time 2.0188 (2.2219)	loss 4.7026 (4.4947)	grad_norm 1.4035 (1.3208)	
[2022-01-18 03:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][500/1251]	eta 0:27:49 lr 0.000989	time 2.2017 (2.2226)	loss 4.6487 (4.4896)	grad_norm 1.2575 (1.3242)	
[2022-01-18 03:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][510/1251]	eta 0:27:27 lr 0.000989	time 2.7671 (2.2230)	loss 4.2354 (4.4807)	grad_norm 1.2240 (1.3252)	
[2022-01-18 03:35:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][520/1251]	eta 0:27:03 lr 0.000989	time 1.6218 (2.2208)	loss 5.0205 (4.4783)	grad_norm 1.3738 (1.3257)	
[2022-01-18 03:35:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][530/1251]	eta 0:26:39 lr 0.000989	time 2.1973 (2.2191)	loss 4.6266 (4.4801)	grad_norm 1.2180 (1.3239)	
[2022-01-18 03:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][540/1251]	eta 0:26:16 lr 0.000989	time 2.5365 (2.2179)	loss 5.1054 (4.4772)	grad_norm 1.1233 (1.3247)	
[2022-01-18 03:36:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][550/1251]	eta 0:25:56 lr 0.000989	time 3.6420 (2.2201)	loss 4.2501 (4.4780)	grad_norm 1.9424 (1.3262)	
[2022-01-18 03:36:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][560/1251]	eta 0:25:32 lr 0.000989	time 2.0986 (2.2182)	loss 5.2891 (4.4776)	grad_norm 1.2806 (1.3256)	
[2022-01-18 03:37:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][570/1251]	eta 0:25:10 lr 0.000989	time 1.8749 (2.2182)	loss 4.4989 (4.4802)	grad_norm 1.6563 (1.3245)	
[2022-01-18 03:37:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][580/1251]	eta 0:24:47 lr 0.000989	time 2.1799 (2.2163)	loss 5.0469 (4.4788)	grad_norm 1.4202 (1.3244)	
[2022-01-18 03:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][590/1251]	eta 0:24:24 lr 0.000989	time 3.5694 (2.2160)	loss 4.6890 (4.4793)	grad_norm 1.7677 (1.3246)	
[2022-01-18 03:38:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][600/1251]	eta 0:24:02 lr 0.000989	time 2.1236 (2.2156)	loss 4.9381 (4.4847)	grad_norm 1.1396 (1.3249)	
[2022-01-18 03:38:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][610/1251]	eta 0:23:41 lr 0.000989	time 2.1486 (2.2172)	loss 4.7375 (4.4852)	grad_norm 1.2909 (1.3269)	
[2022-01-18 03:38:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][620/1251]	eta 0:23:18 lr 0.000989	time 2.0734 (2.2159)	loss 4.6225 (4.4820)	grad_norm 1.2159 (1.3291)	
[2022-01-18 03:39:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][630/1251]	eta 0:22:54 lr 0.000989	time 2.4977 (2.2140)	loss 5.0704 (4.4806)	grad_norm 1.3897 (1.3300)	
[2022-01-18 03:39:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][640/1251]	eta 0:22:31 lr 0.000989	time 1.5835 (2.2112)	loss 4.6610 (4.4817)	grad_norm 1.1364 (1.3265)	
[2022-01-18 03:39:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][650/1251]	eta 0:22:07 lr 0.000989	time 1.9871 (2.2090)	loss 5.1494 (4.4806)	grad_norm 1.5620 (1.3267)	
[2022-01-18 03:40:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][660/1251]	eta 0:21:45 lr 0.000989	time 2.1187 (2.2094)	loss 4.9935 (4.4795)	grad_norm 1.1650 (1.3255)	
[2022-01-18 03:40:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][670/1251]	eta 0:21:23 lr 0.000989	time 2.2059 (2.2097)	loss 4.9913 (4.4763)	grad_norm 1.2410 (1.3252)	
[2022-01-18 03:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][680/1251]	eta 0:21:02 lr 0.000989	time 1.5449 (2.2115)	loss 4.5210 (4.4735)	grad_norm 1.4732 (1.3253)	
[2022-01-18 03:41:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][690/1251]	eta 0:20:41 lr 0.000989	time 2.3433 (2.2133)	loss 4.6196 (4.4768)	grad_norm 1.1649 (1.3250)	
[2022-01-18 03:41:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][700/1251]	eta 0:20:18 lr 0.000989	time 2.1592 (2.2119)	loss 5.2878 (4.4817)	grad_norm 1.1577 (1.3231)	
[2022-01-18 03:42:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][710/1251]	eta 0:19:56 lr 0.000989	time 2.1602 (2.2114)	loss 5.5002 (4.4820)	grad_norm 1.1134 (1.3218)	
[2022-01-18 03:42:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][720/1251]	eta 0:19:33 lr 0.000989	time 1.8746 (2.2108)	loss 5.0898 (4.4848)	grad_norm 1.5811 (1.3226)	
[2022-01-18 03:42:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][730/1251]	eta 0:19:11 lr 0.000989	time 1.8654 (2.2100)	loss 4.9984 (4.4816)	grad_norm 1.1787 (1.3220)	
[2022-01-18 03:43:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][740/1251]	eta 0:18:48 lr 0.000989	time 2.2645 (2.2091)	loss 5.1410 (4.4840)	grad_norm 1.2986 (1.3209)	
[2022-01-18 03:43:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][750/1251]	eta 0:18:26 lr 0.000989	time 1.9474 (2.2083)	loss 5.1106 (4.4787)	grad_norm 1.2537 (1.3203)	
[2022-01-18 03:44:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][760/1251]	eta 0:18:05 lr 0.000989	time 1.9593 (2.2101)	loss 4.1957 (4.4772)	grad_norm 1.5034 (1.3217)	
[2022-01-18 03:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][770/1251]	eta 0:17:43 lr 0.000989	time 1.6515 (2.2104)	loss 4.9948 (4.4777)	grad_norm 1.3672 (1.3225)	
[2022-01-18 03:44:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][780/1251]	eta 0:17:20 lr 0.000989	time 2.2565 (2.2099)	loss 4.6649 (4.4790)	grad_norm 0.9632 (1.3215)	
[2022-01-18 03:45:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][790/1251]	eta 0:16:58 lr 0.000988	time 2.2485 (2.2095)	loss 4.7298 (4.4805)	grad_norm 1.1549 (1.3198)	
[2022-01-18 03:45:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][800/1251]	eta 0:16:36 lr 0.000988	time 2.1199 (2.2098)	loss 4.1477 (4.4801)	grad_norm 1.2752 (1.3177)	
[2022-01-18 03:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][810/1251]	eta 0:16:14 lr 0.000988	time 2.4890 (2.2108)	loss 3.5534 (4.4791)	grad_norm 1.5820 (1.3168)	
[2022-01-18 03:46:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][820/1251]	eta 0:15:52 lr 0.000988	time 2.1319 (2.2096)	loss 5.1120 (4.4793)	grad_norm 1.1506 (1.3183)	
[2022-01-18 03:46:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][830/1251]	eta 0:15:28 lr 0.000988	time 1.6741 (2.2059)	loss 4.4780 (4.4826)	grad_norm 1.3212 (1.3183)	
[2022-01-18 03:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][840/1251]	eta 0:15:05 lr 0.000988	time 1.5990 (2.2036)	loss 4.7765 (4.4846)	grad_norm 1.0951 (1.3179)	
[2022-01-18 03:47:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][850/1251]	eta 0:14:43 lr 0.000988	time 2.3883 (2.2022)	loss 4.5611 (4.4868)	grad_norm 1.3733 (1.3178)	
[2022-01-18 03:47:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][860/1251]	eta 0:14:21 lr 0.000988	time 2.5383 (2.2023)	loss 3.5089 (4.4827)	grad_norm 1.5054 (1.3173)	
[2022-01-18 03:47:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][870/1251]	eta 0:13:58 lr 0.000988	time 1.9000 (2.2017)	loss 3.7102 (4.4781)	grad_norm 1.2702 (1.3183)	
[2022-01-18 03:48:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][880/1251]	eta 0:13:36 lr 0.000988	time 2.3459 (2.2018)	loss 3.7457 (4.4774)	grad_norm 1.0788 (1.3181)	
[2022-01-18 03:48:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][890/1251]	eta 0:13:15 lr 0.000988	time 2.0083 (2.2026)	loss 4.2739 (4.4728)	grad_norm 1.7223 (1.3178)	
[2022-01-18 03:49:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][900/1251]	eta 0:12:53 lr 0.000988	time 2.6198 (2.2032)	loss 4.6892 (4.4735)	grad_norm 1.1601 (1.3165)	
[2022-01-18 03:49:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][910/1251]	eta 0:12:31 lr 0.000988	time 1.5188 (2.2027)	loss 5.0197 (4.4749)	grad_norm 1.1636 (1.3158)	
[2022-01-18 03:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][920/1251]	eta 0:12:09 lr 0.000988	time 3.4890 (2.2050)	loss 4.6245 (4.4749)	grad_norm 1.2951 (1.3145)	
[2022-01-18 03:50:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][930/1251]	eta 0:11:47 lr 0.000988	time 1.6212 (2.2055)	loss 3.8762 (4.4722)	grad_norm 1.3452 (1.3135)	
[2022-01-18 03:50:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][940/1251]	eta 0:11:26 lr 0.000988	time 2.1028 (2.2060)	loss 4.6980 (4.4716)	grad_norm 1.7122 (1.3132)	
[2022-01-18 03:50:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][950/1251]	eta 0:11:03 lr 0.000988	time 1.5426 (2.2052)	loss 4.3501 (4.4702)	grad_norm 1.3802 (1.3119)	
[2022-01-18 03:51:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][960/1251]	eta 0:10:41 lr 0.000988	time 2.4691 (2.2046)	loss 4.4542 (4.4692)	grad_norm 1.0279 (1.3108)	
[2022-01-18 03:51:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][970/1251]	eta 0:10:18 lr 0.000988	time 2.0044 (2.2023)	loss 3.5715 (4.4670)	grad_norm 1.1433 (1.3101)	
[2022-01-18 03:51:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][980/1251]	eta 0:09:56 lr 0.000988	time 1.8762 (2.2006)	loss 3.9944 (4.4657)	grad_norm 1.3993 (1.3106)	
[2022-01-18 03:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][990/1251]	eta 0:09:34 lr 0.000988	time 2.8294 (2.2009)	loss 4.6688 (4.4662)	grad_norm 1.4125 (1.3113)	
[2022-01-18 03:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1000/1251]	eta 0:09:12 lr 0.000988	time 2.5820 (2.2015)	loss 4.9571 (4.4655)	grad_norm 1.1060 (1.3100)	
[2022-01-18 03:53:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1010/1251]	eta 0:08:51 lr 0.000988	time 2.5104 (2.2041)	loss 4.6479 (4.4657)	grad_norm 1.4106 (1.3090)	
[2022-01-18 03:53:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1020/1251]	eta 0:08:29 lr 0.000988	time 1.5695 (2.2051)	loss 3.9225 (4.4656)	grad_norm 1.5325 (1.3091)	
[2022-01-18 03:53:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1030/1251]	eta 0:08:07 lr 0.000988	time 2.2149 (2.2051)	loss 4.3192 (4.4646)	grad_norm 1.5144 (1.3099)	
[2022-01-18 03:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1040/1251]	eta 0:07:45 lr 0.000988	time 1.9750 (2.2038)	loss 3.5483 (4.4645)	grad_norm 1.1696 (1.3089)	
[2022-01-18 03:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1050/1251]	eta 0:07:23 lr 0.000988	time 2.2144 (2.2051)	loss 4.8807 (4.4630)	grad_norm 1.6789 (1.3092)	
[2022-01-18 03:54:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1060/1251]	eta 0:07:01 lr 0.000988	time 1.9165 (2.2051)	loss 4.0076 (4.4624)	grad_norm 1.1636 (1.3084)	
[2022-01-18 03:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1070/1251]	eta 0:06:38 lr 0.000988	time 2.1621 (2.2042)	loss 4.2222 (4.4645)	grad_norm 1.4802 (1.3074)	
[2022-01-18 03:55:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1080/1251]	eta 0:06:16 lr 0.000988	time 1.5837 (2.2021)	loss 4.9408 (4.4636)	grad_norm 1.6003 (1.3082)	
[2022-01-18 03:56:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1090/1251]	eta 0:05:54 lr 0.000988	time 2.2874 (2.2029)	loss 4.8116 (4.4643)	grad_norm 1.6730 (1.3085)	
[2022-01-18 03:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1100/1251]	eta 0:05:32 lr 0.000988	time 2.2216 (2.2020)	loss 4.5081 (4.4615)	grad_norm 1.1693 (1.3080)	
[2022-01-18 03:56:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1110/1251]	eta 0:05:10 lr 0.000988	time 1.6615 (2.2007)	loss 5.4046 (4.4615)	grad_norm 1.1072 (1.3069)	
[2022-01-18 03:57:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1120/1251]	eta 0:04:48 lr 0.000988	time 2.4589 (2.2004)	loss 5.2943 (4.4625)	grad_norm 1.3047 (1.3070)	
[2022-01-18 03:57:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1130/1251]	eta 0:04:26 lr 0.000988	time 1.8633 (2.2004)	loss 4.2047 (4.4606)	grad_norm 1.2849 (1.3061)	
[2022-01-18 03:57:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1140/1251]	eta 0:04:04 lr 0.000988	time 3.1151 (2.2010)	loss 4.8547 (4.4589)	grad_norm 1.3358 (1.3055)	
[2022-01-18 03:58:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1150/1251]	eta 0:03:42 lr 0.000988	time 1.9211 (2.2011)	loss 5.3541 (4.4614)	grad_norm 1.3197 (1.3065)	
[2022-01-18 03:58:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1160/1251]	eta 0:03:20 lr 0.000988	time 2.3314 (2.2009)	loss 3.8021 (4.4612)	grad_norm 1.3579 (1.3056)	
[2022-01-18 03:58:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1170/1251]	eta 0:02:58 lr 0.000988	time 2.2572 (2.2007)	loss 4.8398 (4.4605)	grad_norm 1.2373 (1.3047)	
[2022-01-18 03:59:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1180/1251]	eta 0:02:36 lr 0.000988	time 2.2436 (2.1988)	loss 4.6629 (4.4614)	grad_norm 1.1640 (1.3054)	
[2022-01-18 03:59:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1190/1251]	eta 0:02:14 lr 0.000988	time 2.0468 (2.1972)	loss 5.1922 (4.4598)	grad_norm 1.5116 (1.3059)	
[2022-01-18 03:59:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1200/1251]	eta 0:01:52 lr 0.000988	time 2.3560 (2.1961)	loss 4.3503 (4.4617)	grad_norm 1.2208 (1.3058)	
[2022-01-18 04:00:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1210/1251]	eta 0:01:30 lr 0.000988	time 2.1598 (2.1962)	loss 5.0886 (4.4609)	grad_norm 1.0622 (1.3054)	
[2022-01-18 04:00:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1220/1251]	eta 0:01:08 lr 0.000988	time 2.1033 (2.1966)	loss 4.5227 (4.4605)	grad_norm 1.3586 (1.3046)	
[2022-01-18 04:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1230/1251]	eta 0:00:46 lr 0.000988	time 1.9162 (2.1964)	loss 5.3529 (4.4617)	grad_norm 1.0493 (1.3044)	
[2022-01-18 04:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1240/1251]	eta 0:00:24 lr 0.000988	time 2.2179 (2.1957)	loss 5.1310 (4.4642)	grad_norm 1.1290 (1.3043)	
[2022-01-18 04:01:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [20/300][1250/1251]	eta 0:00:02 lr 0.000988	time 1.1428 (2.1906)	loss 4.5435 (4.4641)	grad_norm 1.0950 (1.3035)	
[2022-01-18 04:01:39 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 20 training takes 0:45:40
[2022-01-18 04:01:39 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_20 saving......
[2022-01-18 04:01:50 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_20 saved !!!
[2022-01-18 04:02:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.915 (16.915)	Loss 1.7822 (1.7822)	Acc@1 61.035 (61.035)	Acc@5 83.594 (83.594)	
[2022-01-18 04:02:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.969 (2.983)	Loss 1.7964 (1.7983)	Acc@1 61.621 (60.396)	Acc@5 84.570 (83.620)	
[2022-01-18 04:02:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.678 (2.383)	Loss 1.8233 (1.8042)	Acc@1 58.398 (60.231)	Acc@5 83.398 (83.570)	
[2022-01-18 04:02:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.348 (2.079)	Loss 1.8022 (1.7989)	Acc@1 60.840 (60.396)	Acc@5 83.594 (83.783)	
[2022-01-18 04:03:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.718 (1.998)	Loss 1.8684 (1.8089)	Acc@1 60.059 (60.101)	Acc@5 82.031 (83.572)	
[2022-01-18 04:03:20 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 60.100 Acc@5 83.542
[2022-01-18 04:03:20 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 60.1%
[2022-01-18 04:03:20 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 60.10%
[2022-01-18 04:03:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][0/1251]	eta 7:33:47 lr 0.000988	time 21.7649 (21.7649)	loss 3.9121 (3.9121)	grad_norm 1.1757 (1.1757)	
[2022-01-18 04:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][10/1251]	eta 1:25:09 lr 0.000988	time 2.2577 (4.1174)	loss 4.6986 (4.5951)	grad_norm 1.2648 (1.2655)	
[2022-01-18 04:04:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][20/1251]	eta 1:04:23 lr 0.000988	time 1.6599 (3.1382)	loss 4.4730 (4.5979)	grad_norm 1.5209 (1.3271)	
[2022-01-18 04:04:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][30/1251]	eta 0:56:26 lr 0.000988	time 1.4936 (2.7738)	loss 4.9773 (4.5854)	grad_norm 1.3746 (1.3283)	
[2022-01-18 04:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][40/1251]	eta 0:54:17 lr 0.000988	time 3.4829 (2.6899)	loss 4.3814 (4.5054)	grad_norm 1.2213 (1.3400)	
[2022-01-18 04:05:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][50/1251]	eta 0:53:03 lr 0.000988	time 4.5933 (2.6511)	loss 4.7779 (4.5134)	grad_norm 1.2858 (1.3270)	
[2022-01-18 04:05:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][60/1251]	eta 0:51:44 lr 0.000988	time 2.4669 (2.6065)	loss 3.6242 (4.4869)	grad_norm 1.3259 (1.3218)	
[2022-01-18 04:06:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][70/1251]	eta 0:50:12 lr 0.000988	time 1.4638 (2.5509)	loss 4.3267 (4.5144)	grad_norm 1.2549 (1.3225)	
[2022-01-18 04:06:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][80/1251]	eta 0:48:41 lr 0.000988	time 2.4911 (2.4951)	loss 3.3922 (4.4874)	grad_norm 1.2143 (1.3141)	
[2022-01-18 04:07:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][90/1251]	eta 0:47:31 lr 0.000988	time 1.9344 (2.4564)	loss 4.9467 (4.5029)	grad_norm 1.1208 (1.3041)	
[2022-01-18 04:07:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][100/1251]	eta 0:46:18 lr 0.000988	time 1.9194 (2.4138)	loss 4.7786 (4.5020)	grad_norm 1.2175 (1.3039)	
[2022-01-18 04:07:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][110/1251]	eta 0:45:20 lr 0.000988	time 1.6439 (2.3840)	loss 4.2817 (4.5111)	grad_norm 1.5165 (1.2986)	
[2022-01-18 04:08:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][120/1251]	eta 0:44:37 lr 0.000988	time 2.0218 (2.3669)	loss 4.1884 (4.5117)	grad_norm 1.2767 (1.2942)	
[2022-01-18 04:08:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][130/1251]	eta 0:44:00 lr 0.000988	time 2.2205 (2.3559)	loss 3.6665 (4.5074)	grad_norm 1.7155 (1.3046)	
[2022-01-18 04:08:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][140/1251]	eta 0:43:21 lr 0.000988	time 1.9065 (2.3415)	loss 3.7943 (4.4977)	grad_norm 1.1384 (1.3135)	
[2022-01-18 04:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][150/1251]	eta 0:42:41 lr 0.000988	time 1.8396 (2.3265)	loss 5.0808 (4.5223)	grad_norm 1.1033 (1.3105)	
[2022-01-18 04:09:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][160/1251]	eta 0:42:03 lr 0.000988	time 2.2754 (2.3130)	loss 5.3250 (4.5176)	grad_norm 1.1316 (1.3078)	
[2022-01-18 04:09:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][170/1251]	eta 0:41:27 lr 0.000988	time 2.3227 (2.3007)	loss 4.6552 (4.5189)	grad_norm 1.3025 (1.3100)	
[2022-01-18 04:10:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][180/1251]	eta 0:41:01 lr 0.000988	time 2.4011 (2.2985)	loss 5.0519 (4.5197)	grad_norm 1.3053 (1.3017)	
[2022-01-18 04:10:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][190/1251]	eta 0:40:34 lr 0.000988	time 1.6900 (2.2942)	loss 5.2263 (4.5230)	grad_norm 1.4326 (1.3007)	
[2022-01-18 04:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][200/1251]	eta 0:40:12 lr 0.000988	time 2.1797 (2.2950)	loss 4.3859 (4.5145)	grad_norm 1.3025 (1.3012)	
[2022-01-18 04:11:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][210/1251]	eta 0:39:50 lr 0.000988	time 2.2846 (2.2966)	loss 3.9491 (4.4992)	grad_norm 1.4764 (1.3038)	
[2022-01-18 04:11:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][220/1251]	eta 0:39:26 lr 0.000988	time 2.5375 (2.2958)	loss 4.6897 (4.4946)	grad_norm 1.5002 (1.3066)	
[2022-01-18 04:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][230/1251]	eta 0:38:47 lr 0.000988	time 1.5780 (2.2797)	loss 4.4418 (4.4941)	grad_norm 1.2323 (1.3087)	
[2022-01-18 04:12:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][240/1251]	eta 0:38:13 lr 0.000988	time 1.9331 (2.2683)	loss 4.1509 (4.4897)	grad_norm 1.1370 (1.3079)	
[2022-01-18 04:12:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][250/1251]	eta 0:37:39 lr 0.000988	time 1.9267 (2.2573)	loss 4.6214 (4.4861)	grad_norm 1.6499 (1.3078)	
[2022-01-18 04:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][260/1251]	eta 0:37:20 lr 0.000988	time 2.7591 (2.2607)	loss 4.2586 (4.4840)	grad_norm 1.4432 (1.3069)	
[2022-01-18 04:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][270/1251]	eta 0:36:53 lr 0.000988	time 1.9237 (2.2568)	loss 4.8625 (4.4956)	grad_norm 1.1655 (1.3068)	
[2022-01-18 04:13:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][280/1251]	eta 0:36:34 lr 0.000988	time 2.8657 (2.2602)	loss 4.9704 (4.4981)	grad_norm 1.3477 (1.3089)	
[2022-01-18 04:14:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][290/1251]	eta 0:36:10 lr 0.000988	time 2.1030 (2.2581)	loss 4.0119 (4.4946)	grad_norm 1.1874 (1.3086)	
[2022-01-18 04:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][300/1251]	eta 0:35:49 lr 0.000988	time 2.8300 (2.2606)	loss 4.4207 (4.5011)	grad_norm 1.0867 (1.3080)	
[2022-01-18 04:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][310/1251]	eta 0:35:24 lr 0.000988	time 1.8089 (2.2578)	loss 4.9079 (4.5005)	grad_norm 1.4041 (1.3105)	
[2022-01-18 04:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][320/1251]	eta 0:34:57 lr 0.000988	time 1.9799 (2.2532)	loss 4.6522 (4.5010)	grad_norm 1.3379 (1.3102)	
[2022-01-18 04:15:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][330/1251]	eta 0:34:30 lr 0.000988	time 2.2549 (2.2486)	loss 4.0366 (4.4961)	grad_norm 1.6832 (1.3110)	
[2022-01-18 04:16:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][340/1251]	eta 0:34:07 lr 0.000988	time 2.4841 (2.2475)	loss 4.7135 (4.4906)	grad_norm 1.2097 (1.3111)	
[2022-01-18 04:16:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][350/1251]	eta 0:33:45 lr 0.000988	time 2.1750 (2.2484)	loss 3.8968 (4.4826)	grad_norm 1.3226 (1.3099)	
[2022-01-18 04:16:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][360/1251]	eta 0:33:23 lr 0.000988	time 1.9852 (2.2482)	loss 4.8193 (4.4806)	grad_norm 1.4340 (1.3081)	
[2022-01-18 04:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][370/1251]	eta 0:32:56 lr 0.000988	time 1.7856 (2.2438)	loss 4.0276 (4.4693)	grad_norm 1.4233 (1.3111)	
[2022-01-18 04:17:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][380/1251]	eta 0:32:31 lr 0.000988	time 2.2068 (2.2401)	loss 4.8239 (4.4745)	grad_norm 1.4615 (1.3123)	
[2022-01-18 04:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][390/1251]	eta 0:32:05 lr 0.000988	time 1.9710 (2.2364)	loss 5.0612 (4.4818)	grad_norm 1.4498 (1.3165)	
[2022-01-18 04:18:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][400/1251]	eta 0:31:42 lr 0.000988	time 2.2248 (2.2354)	loss 3.9327 (4.4835)	grad_norm 1.1497 (1.3123)	
[2022-01-18 04:18:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][410/1251]	eta 0:31:19 lr 0.000988	time 1.8794 (2.2354)	loss 4.3502 (4.4875)	grad_norm 1.1637 (1.3088)	
[2022-01-18 04:19:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][420/1251]	eta 0:30:55 lr 0.000988	time 1.9434 (2.2329)	loss 4.6232 (4.4868)	grad_norm 1.1021 (1.3053)	
[2022-01-18 04:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][430/1251]	eta 0:30:32 lr 0.000988	time 2.3210 (2.2325)	loss 3.5573 (4.4867)	grad_norm 1.3503 (1.3027)	
[2022-01-18 04:19:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][440/1251]	eta 0:30:07 lr 0.000988	time 1.6501 (2.2288)	loss 4.3561 (4.4889)	grad_norm 1.3500 (1.3029)	
[2022-01-18 04:20:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][450/1251]	eta 0:29:43 lr 0.000988	time 1.5796 (2.2262)	loss 4.9330 (4.4910)	grad_norm 1.2532 (1.3063)	
[2022-01-18 04:20:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][460/1251]	eta 0:29:21 lr 0.000988	time 1.4821 (2.2267)	loss 3.7146 (4.4900)	grad_norm 1.3190 (1.3073)	
[2022-01-18 04:20:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][470/1251]	eta 0:29:01 lr 0.000988	time 2.9177 (2.2303)	loss 3.9689 (4.4879)	grad_norm 1.4011 (1.3060)	
[2022-01-18 04:21:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][480/1251]	eta 0:28:40 lr 0.000988	time 2.3841 (2.2319)	loss 4.8577 (4.4883)	grad_norm 1.0403 (1.3030)	
[2022-01-18 04:21:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][490/1251]	eta 0:28:15 lr 0.000988	time 1.6033 (2.2274)	loss 4.1097 (4.4814)	grad_norm 1.2260 (1.3039)	
[2022-01-18 04:21:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][500/1251]	eta 0:27:48 lr 0.000988	time 1.9224 (2.2219)	loss 4.7993 (4.4826)	grad_norm 1.0538 (1.3050)	
[2022-01-18 04:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][510/1251]	eta 0:27:23 lr 0.000988	time 2.4177 (2.2183)	loss 4.4238 (4.4826)	grad_norm 1.1980 (1.3037)	
[2022-01-18 04:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][520/1251]	eta 0:27:00 lr 0.000988	time 2.4541 (2.2171)	loss 3.3701 (4.4839)	grad_norm 0.9681 (1.3026)	
[2022-01-18 04:22:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][530/1251]	eta 0:26:38 lr 0.000988	time 1.9601 (2.2168)	loss 4.9293 (4.4865)	grad_norm 1.1417 (1.3000)	
[2022-01-18 04:23:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][540/1251]	eta 0:26:17 lr 0.000988	time 3.6883 (2.2182)	loss 5.2219 (4.4906)	grad_norm 0.9968 (1.2993)	
[2022-01-18 04:23:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][550/1251]	eta 0:25:58 lr 0.000988	time 1.8649 (2.2239)	loss 4.4828 (4.4888)	grad_norm 1.1462 (1.2975)	
[2022-01-18 04:24:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][560/1251]	eta 0:25:37 lr 0.000988	time 1.5690 (2.2253)	loss 3.3040 (4.4892)	grad_norm 1.7551 (1.2965)	
[2022-01-18 04:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][570/1251]	eta 0:25:13 lr 0.000988	time 1.9707 (2.2229)	loss 3.6167 (4.4832)	grad_norm 1.1410 (1.2965)	
[2022-01-18 04:24:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][580/1251]	eta 0:24:49 lr 0.000988	time 2.5037 (2.2205)	loss 4.4422 (4.4841)	grad_norm 1.1181 (1.2956)	
[2022-01-18 04:25:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][590/1251]	eta 0:24:26 lr 0.000988	time 2.3538 (2.2181)	loss 4.7014 (4.4882)	grad_norm 1.5234 (1.2978)	
[2022-01-18 04:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][600/1251]	eta 0:24:02 lr 0.000988	time 1.9617 (2.2154)	loss 5.2589 (4.4901)	grad_norm 1.5719 (1.2993)	
[2022-01-18 04:25:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][610/1251]	eta 0:23:39 lr 0.000988	time 2.1751 (2.2143)	loss 4.8471 (4.4914)	grad_norm 1.4733 (1.2989)	
[2022-01-18 04:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][620/1251]	eta 0:23:16 lr 0.000988	time 1.9687 (2.2133)	loss 5.2132 (4.4891)	grad_norm 1.1672 (1.2971)	
[2022-01-18 04:26:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][630/1251]	eta 0:22:55 lr 0.000988	time 2.4064 (2.2149)	loss 4.5984 (4.4916)	grad_norm 1.6418 (1.2966)	
[2022-01-18 04:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][640/1251]	eta 0:22:33 lr 0.000987	time 2.7510 (2.2150)	loss 4.5590 (4.4911)	grad_norm 1.4610 (1.2963)	
[2022-01-18 04:27:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][650/1251]	eta 0:22:10 lr 0.000987	time 2.0266 (2.2133)	loss 4.9269 (4.4922)	grad_norm 1.1996 (1.2965)	
[2022-01-18 04:27:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][660/1251]	eta 0:21:47 lr 0.000987	time 1.8042 (2.2120)	loss 4.6548 (4.4885)	grad_norm 1.2486 (1.2955)	
[2022-01-18 04:28:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][670/1251]	eta 0:21:24 lr 0.000987	time 2.1573 (2.2112)	loss 4.1353 (4.4884)	grad_norm 1.2282 (1.2951)	
[2022-01-18 04:28:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][680/1251]	eta 0:21:03 lr 0.000987	time 2.8904 (2.2120)	loss 4.8949 (4.4910)	grad_norm 1.5944 (1.2972)	
[2022-01-18 04:28:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][690/1251]	eta 0:20:41 lr 0.000987	time 1.8290 (2.2123)	loss 4.7396 (4.4920)	grad_norm 1.1946 (1.2954)	
[2022-01-18 04:29:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][700/1251]	eta 0:20:18 lr 0.000987	time 2.3111 (2.2109)	loss 3.8297 (4.4906)	grad_norm 1.0804 (1.2934)	
[2022-01-18 04:29:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][710/1251]	eta 0:19:57 lr 0.000987	time 3.3762 (2.2133)	loss 3.5686 (4.4877)	grad_norm 1.4577 (1.2935)	
[2022-01-18 04:29:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][720/1251]	eta 0:19:34 lr 0.000987	time 2.0943 (2.2123)	loss 5.3587 (4.4865)	grad_norm 1.4198 (1.2924)	
[2022-01-18 04:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][730/1251]	eta 0:19:11 lr 0.000987	time 1.5419 (2.2111)	loss 3.8117 (4.4866)	grad_norm 1.1256 (1.2910)	
[2022-01-18 04:30:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][740/1251]	eta 0:18:48 lr 0.000987	time 2.2850 (2.2091)	loss 4.5917 (4.4834)	grad_norm 1.1216 (1.2910)	
[2022-01-18 04:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][750/1251]	eta 0:18:27 lr 0.000987	time 2.7783 (2.2114)	loss 4.8485 (4.4831)	grad_norm 1.0803 (1.2906)	
[2022-01-18 04:31:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][760/1251]	eta 0:18:05 lr 0.000987	time 1.6353 (2.2118)	loss 3.6786 (4.4830)	grad_norm 1.3289 (1.2911)	
[2022-01-18 04:31:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][770/1251]	eta 0:17:43 lr 0.000987	time 1.9547 (2.2110)	loss 4.8519 (4.4820)	grad_norm 1.1408 (1.2916)	
[2022-01-18 04:32:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][780/1251]	eta 0:17:21 lr 0.000987	time 2.5764 (2.2106)	loss 4.2997 (4.4842)	grad_norm 1.3456 (1.2928)	
[2022-01-18 04:32:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][790/1251]	eta 0:16:58 lr 0.000987	time 1.6225 (2.2087)	loss 4.2548 (4.4825)	grad_norm 1.1969 (1.2923)	
[2022-01-18 04:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][800/1251]	eta 0:16:35 lr 0.000987	time 1.8983 (2.2081)	loss 3.5947 (4.4823)	grad_norm 1.0977 (1.2909)	
[2022-01-18 04:33:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][810/1251]	eta 0:16:13 lr 0.000987	time 2.1508 (2.2084)	loss 4.8760 (4.4818)	grad_norm 1.3232 (1.2908)	
[2022-01-18 04:33:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][820/1251]	eta 0:15:51 lr 0.000987	time 2.7236 (2.2087)	loss 4.7591 (4.4868)	grad_norm 1.6113 (1.2930)	
[2022-01-18 04:33:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][830/1251]	eta 0:15:29 lr 0.000987	time 2.1769 (2.2075)	loss 4.3561 (4.4862)	grad_norm 1.1279 (1.2927)	
[2022-01-18 04:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][840/1251]	eta 0:15:07 lr 0.000987	time 1.8539 (2.2072)	loss 4.6414 (4.4884)	grad_norm 1.1075 (1.2911)	
[2022-01-18 04:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][850/1251]	eta 0:14:44 lr 0.000987	time 1.5913 (2.2065)	loss 4.2941 (4.4890)	grad_norm 1.1569 (1.2920)	
[2022-01-18 04:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][860/1251]	eta 0:14:22 lr 0.000987	time 2.2628 (2.2059)	loss 3.2098 (4.4881)	grad_norm 1.2608 (1.2925)	
[2022-01-18 04:35:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][870/1251]	eta 0:14:00 lr 0.000987	time 2.1129 (2.2053)	loss 4.7014 (4.4873)	grad_norm 1.3643 (1.2912)	
[2022-01-18 04:35:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][880/1251]	eta 0:13:38 lr 0.000987	time 2.2481 (2.2055)	loss 5.1343 (4.4889)	grad_norm 1.1378 (1.2914)	
[2022-01-18 04:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][890/1251]	eta 0:13:15 lr 0.000987	time 1.9170 (2.2040)	loss 5.1373 (4.4921)	grad_norm 1.2423 (1.2919)	
[2022-01-18 04:36:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][900/1251]	eta 0:12:53 lr 0.000987	time 1.8478 (2.2035)	loss 4.1525 (4.4897)	grad_norm 1.2837 (1.2928)	
[2022-01-18 04:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][910/1251]	eta 0:12:30 lr 0.000987	time 1.8494 (2.2020)	loss 4.8674 (4.4894)	grad_norm 1.3524 (1.2917)	
[2022-01-18 04:37:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][920/1251]	eta 0:12:09 lr 0.000987	time 3.3236 (2.2025)	loss 4.9890 (4.4874)	grad_norm 1.1408 (1.2909)	
[2022-01-18 04:37:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][930/1251]	eta 0:11:46 lr 0.000987	time 1.9110 (2.2021)	loss 4.5595 (4.4893)	grad_norm 1.6099 (1.2911)	
[2022-01-18 04:37:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][940/1251]	eta 0:11:24 lr 0.000987	time 2.4714 (2.2022)	loss 3.6752 (4.4849)	grad_norm 1.1638 (1.2917)	
[2022-01-18 04:38:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][950/1251]	eta 0:11:02 lr 0.000987	time 1.6595 (2.2001)	loss 2.9371 (4.4831)	grad_norm 1.1853 (1.2916)	
[2022-01-18 04:38:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][960/1251]	eta 0:10:40 lr 0.000987	time 1.9578 (2.1999)	loss 4.9770 (4.4778)	grad_norm 0.9573 (1.2913)	
[2022-01-18 04:38:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][970/1251]	eta 0:10:17 lr 0.000987	time 1.9247 (2.1988)	loss 3.6298 (4.4768)	grad_norm 1.4168 (1.2910)	
[2022-01-18 04:39:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][980/1251]	eta 0:09:56 lr 0.000987	time 2.1490 (2.1994)	loss 4.1241 (4.4744)	grad_norm 1.2374 (1.2897)	
[2022-01-18 04:39:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][990/1251]	eta 0:09:34 lr 0.000987	time 1.7543 (2.2001)	loss 4.3154 (4.4773)	grad_norm 0.9243 (1.2889)	
[2022-01-18 04:40:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1000/1251]	eta 0:09:12 lr 0.000987	time 2.9255 (2.2016)	loss 4.6864 (4.4785)	grad_norm 0.8895 (1.2877)	
[2022-01-18 04:40:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1010/1251]	eta 0:08:50 lr 0.000987	time 2.1066 (2.2015)	loss 4.8539 (4.4778)	grad_norm 1.0685 (1.2870)	
[2022-01-18 04:40:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1020/1251]	eta 0:08:28 lr 0.000987	time 2.6273 (2.2014)	loss 4.6928 (4.4785)	grad_norm 1.3491 (1.2873)	
[2022-01-18 04:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1030/1251]	eta 0:08:06 lr 0.000987	time 1.8503 (2.2009)	loss 4.5302 (4.4767)	grad_norm 1.0725 (1.2868)	
[2022-01-18 04:41:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1040/1251]	eta 0:07:44 lr 0.000987	time 2.5891 (2.2007)	loss 4.1870 (4.4744)	grad_norm 1.1525 (1.2866)	
[2022-01-18 04:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1050/1251]	eta 0:07:22 lr 0.000987	time 2.5001 (2.2006)	loss 4.9806 (4.4760)	grad_norm 1.2333 (1.2849)	
[2022-01-18 04:42:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1060/1251]	eta 0:07:00 lr 0.000987	time 2.1837 (2.2013)	loss 4.6994 (4.4772)	grad_norm 1.2859 (1.2839)	
[2022-01-18 04:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1070/1251]	eta 0:06:38 lr 0.000987	time 2.7555 (2.2014)	loss 3.4890 (4.4739)	grad_norm 1.1429 (1.2835)	
[2022-01-18 04:42:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1080/1251]	eta 0:06:16 lr 0.000987	time 2.5708 (2.2009)	loss 3.4402 (4.4740)	grad_norm 1.1896 (1.2830)	
[2022-01-18 04:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1090/1251]	eta 0:05:54 lr 0.000987	time 1.9047 (2.2009)	loss 4.4782 (4.4744)	grad_norm 1.2363 (1.2831)	
[2022-01-18 04:43:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1100/1251]	eta 0:05:32 lr 0.000987	time 2.4665 (2.2017)	loss 5.5757 (4.4734)	grad_norm 1.1056 (1.2826)	
[2022-01-18 04:44:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1110/1251]	eta 0:05:10 lr 0.000987	time 1.8595 (2.2001)	loss 4.0800 (4.4733)	grad_norm 1.1179 (1.2814)	
[2022-01-18 04:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1120/1251]	eta 0:04:48 lr 0.000987	time 2.5082 (2.1994)	loss 4.8438 (4.4754)	grad_norm 1.3805 (1.2803)	
[2022-01-18 04:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1130/1251]	eta 0:04:25 lr 0.000987	time 2.1475 (2.1978)	loss 4.3235 (4.4756)	grad_norm 0.9371 (1.2800)	
[2022-01-18 04:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1140/1251]	eta 0:04:03 lr 0.000987	time 2.1364 (2.1978)	loss 5.1464 (4.4751)	grad_norm 1.0958 (1.2795)	
[2022-01-18 04:45:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1150/1251]	eta 0:03:41 lr 0.000987	time 2.5549 (2.1975)	loss 4.3314 (4.4736)	grad_norm 1.0390 (1.2785)	
[2022-01-18 04:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1160/1251]	eta 0:03:19 lr 0.000987	time 2.6429 (2.1977)	loss 4.7501 (4.4725)	grad_norm 1.2637 (1.2784)	
[2022-01-18 04:46:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1170/1251]	eta 0:02:58 lr 0.000987	time 2.4097 (2.1980)	loss 4.3921 (4.4732)	grad_norm 0.9862 (1.2778)	
[2022-01-18 04:46:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1180/1251]	eta 0:02:36 lr 0.000987	time 2.2473 (2.1982)	loss 4.4353 (4.4721)	grad_norm 1.4315 (1.2785)	
[2022-01-18 04:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1190/1251]	eta 0:02:14 lr 0.000987	time 1.9760 (2.2006)	loss 4.2086 (4.4707)	grad_norm 1.3798 (1.2792)	
[2022-01-18 04:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1200/1251]	eta 0:01:52 lr 0.000987	time 2.8490 (2.2007)	loss 4.5021 (4.4696)	grad_norm 1.0568 (1.2783)	
[2022-01-18 04:47:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1210/1251]	eta 0:01:30 lr 0.000987	time 2.2655 (2.1985)	loss 4.9236 (4.4710)	grad_norm 1.3367 (1.2782)	
[2022-01-18 04:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1220/1251]	eta 0:01:08 lr 0.000987	time 2.1548 (2.1964)	loss 4.9145 (4.4707)	grad_norm 0.9935 (1.2772)	
[2022-01-18 04:48:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1230/1251]	eta 0:00:46 lr 0.000987	time 1.9214 (2.1960)	loss 3.6770 (4.4706)	grad_norm 1.1450 (1.2769)	
[2022-01-18 04:48:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1240/1251]	eta 0:00:24 lr 0.000987	time 1.7154 (2.1964)	loss 4.7247 (4.4691)	grad_norm 0.9685 (1.2765)	
[2022-01-18 04:49:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [21/300][1250/1251]	eta 0:00:02 lr 0.000987	time 1.1904 (2.1910)	loss 3.9526 (4.4672)	grad_norm 1.3159 (1.2763)	
[2022-01-18 04:49:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 21 training takes 0:45:41
[2022-01-18 04:49:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 20.684 (20.684)	Loss 1.7309 (1.7309)	Acc@1 61.133 (61.133)	Acc@5 84.570 (84.570)	
[2022-01-18 04:49:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.023 (3.589)	Loss 1.7952 (1.7598)	Acc@1 58.984 (60.369)	Acc@5 81.836 (83.700)	
[2022-01-18 04:50:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.893 (2.801)	Loss 1.7437 (1.7515)	Acc@1 61.328 (60.654)	Acc@5 83.984 (83.626)	
[2022-01-18 04:50:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.618 (2.295)	Loss 1.7930 (1.7604)	Acc@1 59.961 (60.745)	Acc@5 83.887 (83.616)	
[2022-01-18 04:50:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.250 (2.237)	Loss 1.7647 (1.7569)	Acc@1 61.816 (60.799)	Acc@5 84.668 (83.791)	
[2022-01-18 04:50:41 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 60.790 Acc@5 83.754
[2022-01-18 04:50:41 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 60.8%
[2022-01-18 04:50:41 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 60.79%
[2022-01-18 04:51:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][0/1251]	eta 7:21:04 lr 0.000987	time 21.1546 (21.1546)	loss 5.1383 (5.1383)	grad_norm 1.1799 (1.1799)	
[2022-01-18 04:51:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][10/1251]	eta 1:22:35 lr 0.000987	time 2.1403 (3.9931)	loss 4.8175 (4.5241)	grad_norm 1.0273 (1.1279)	
[2022-01-18 04:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][20/1251]	eta 1:01:56 lr 0.000987	time 1.7540 (3.0194)	loss 3.1742 (4.6194)	grad_norm 1.1275 (1.1538)	
[2022-01-18 04:52:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][30/1251]	eta 0:55:08 lr 0.000987	time 1.3265 (2.7094)	loss 3.3158 (4.5746)	grad_norm 1.6251 (1.1986)	
[2022-01-18 04:52:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][40/1251]	eta 0:53:56 lr 0.000987	time 6.4931 (2.6727)	loss 4.6342 (4.5554)	grad_norm 0.9999 (1.2155)	
[2022-01-18 04:52:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][50/1251]	eta 0:52:28 lr 0.000987	time 2.5116 (2.6218)	loss 4.4553 (4.4828)	grad_norm 1.3383 (1.2226)	
[2022-01-18 04:53:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][60/1251]	eta 0:50:41 lr 0.000987	time 2.4218 (2.5538)	loss 4.3613 (4.4605)	grad_norm 1.4345 (1.2205)	
[2022-01-18 04:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][70/1251]	eta 0:49:15 lr 0.000987	time 2.0826 (2.5023)	loss 3.5482 (4.4498)	grad_norm 1.0844 (1.2149)	
[2022-01-18 04:54:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][80/1251]	eta 0:48:31 lr 0.000987	time 3.7964 (2.4864)	loss 5.1141 (4.4464)	grad_norm 1.2989 (1.2359)	
[2022-01-18 04:54:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][90/1251]	eta 0:47:57 lr 0.000987	time 2.4821 (2.4782)	loss 4.6642 (4.4430)	grad_norm 1.7603 (1.2539)	
[2022-01-18 04:54:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][100/1251]	eta 0:46:49 lr 0.000987	time 1.6853 (2.4406)	loss 4.6628 (4.4068)	grad_norm 1.2636 (1.2707)	
[2022-01-18 04:55:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][110/1251]	eta 0:45:49 lr 0.000987	time 1.8905 (2.4094)	loss 3.8955 (4.4211)	grad_norm 1.3501 (1.2678)	
[2022-01-18 04:55:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][120/1251]	eta 0:45:05 lr 0.000987	time 2.4969 (2.3925)	loss 4.0750 (4.4061)	grad_norm 1.2077 (1.2673)	
[2022-01-18 04:55:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][130/1251]	eta 0:44:16 lr 0.000987	time 1.7286 (2.3699)	loss 5.2854 (4.4057)	grad_norm 1.1950 (1.2600)	
[2022-01-18 04:56:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][140/1251]	eta 0:43:27 lr 0.000987	time 2.1792 (2.3472)	loss 4.3545 (4.4240)	grad_norm 1.4458 (1.2654)	
[2022-01-18 04:56:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][150/1251]	eta 0:42:50 lr 0.000987	time 2.0496 (2.3351)	loss 3.6511 (4.4268)	grad_norm 1.1444 (1.2696)	
[2022-01-18 04:56:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][160/1251]	eta 0:42:20 lr 0.000987	time 2.4867 (2.3290)	loss 3.4111 (4.4114)	grad_norm 1.1622 (1.2716)	
[2022-01-18 04:57:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][170/1251]	eta 0:41:47 lr 0.000987	time 1.7486 (2.3195)	loss 3.3963 (4.4116)	grad_norm 1.8257 (1.2754)	
[2022-01-18 04:57:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][180/1251]	eta 0:41:20 lr 0.000987	time 2.2772 (2.3162)	loss 4.5033 (4.4185)	grad_norm 1.2914 (1.2778)	
[2022-01-18 04:58:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][190/1251]	eta 0:41:01 lr 0.000987	time 1.9027 (2.3195)	loss 3.0192 (4.4088)	grad_norm 1.4616 (1.2798)	
[2022-01-18 04:58:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][200/1251]	eta 0:40:32 lr 0.000987	time 2.8230 (2.3145)	loss 4.3313 (4.4099)	grad_norm 1.1198 (1.2853)	
[2022-01-18 04:58:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][210/1251]	eta 0:39:55 lr 0.000987	time 1.9430 (2.3008)	loss 4.0318 (4.4128)	grad_norm 1.0391 (1.2876)	
[2022-01-18 04:59:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][220/1251]	eta 0:39:18 lr 0.000987	time 2.2433 (2.2878)	loss 5.1985 (4.3991)	grad_norm 1.2949 (1.2911)	
[2022-01-18 04:59:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][230/1251]	eta 0:38:47 lr 0.000987	time 2.0394 (2.2796)	loss 3.4283 (4.3982)	grad_norm 1.2804 (1.2892)	
[2022-01-18 04:59:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][240/1251]	eta 0:38:16 lr 0.000987	time 2.1826 (2.2720)	loss 4.6744 (4.4000)	grad_norm 1.0739 (1.2894)	
[2022-01-18 05:00:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][250/1251]	eta 0:37:52 lr 0.000987	time 1.8998 (2.2706)	loss 4.2841 (4.3989)	grad_norm 1.2071 (1.2884)	
[2022-01-18 05:00:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][260/1251]	eta 0:37:36 lr 0.000987	time 2.4729 (2.2772)	loss 4.4191 (4.3955)	grad_norm 1.1545 (1.2847)	
[2022-01-18 05:00:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][270/1251]	eta 0:37:15 lr 0.000987	time 1.8576 (2.2785)	loss 4.0217 (4.3916)	grad_norm 1.1628 (1.2823)	
[2022-01-18 05:01:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][280/1251]	eta 0:36:49 lr 0.000987	time 2.1419 (2.2757)	loss 5.2274 (4.3989)	grad_norm 1.0983 (1.2811)	
[2022-01-18 05:01:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][290/1251]	eta 0:36:13 lr 0.000987	time 1.6672 (2.2617)	loss 4.7026 (4.4001)	grad_norm 1.0850 (1.2803)	
[2022-01-18 05:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][300/1251]	eta 0:35:46 lr 0.000987	time 1.8324 (2.2567)	loss 4.4534 (4.4040)	grad_norm 0.9545 (1.2765)	
[2022-01-18 05:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][310/1251]	eta 0:35:22 lr 0.000987	time 1.8822 (2.2554)	loss 3.2475 (4.4010)	grad_norm 1.1684 (1.2748)	
[2022-01-18 05:02:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][320/1251]	eta 0:34:59 lr 0.000987	time 2.6629 (2.2552)	loss 5.0199 (4.4077)	grad_norm 1.2186 (1.2722)	
[2022-01-18 05:03:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][330/1251]	eta 0:34:36 lr 0.000987	time 1.7863 (2.2543)	loss 5.1343 (4.4147)	grad_norm 1.2850 (1.2705)	
[2022-01-18 05:03:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][340/1251]	eta 0:34:16 lr 0.000987	time 2.0259 (2.2570)	loss 4.0139 (4.4147)	grad_norm 1.0755 (1.2697)	
[2022-01-18 05:03:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][350/1251]	eta 0:33:49 lr 0.000987	time 1.9885 (2.2528)	loss 3.7848 (4.4209)	grad_norm 1.2060 (1.2693)	
[2022-01-18 05:04:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][360/1251]	eta 0:33:28 lr 0.000987	time 2.0643 (2.2545)	loss 3.4713 (4.4227)	grad_norm 1.0656 (1.2689)	
[2022-01-18 05:04:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][370/1251]	eta 0:33:03 lr 0.000987	time 1.9176 (2.2515)	loss 3.5444 (4.4207)	grad_norm 1.8621 (1.2715)	
[2022-01-18 05:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][380/1251]	eta 0:32:41 lr 0.000987	time 1.7316 (2.2523)	loss 4.3163 (4.4138)	grad_norm 1.1499 (1.2719)	
[2022-01-18 05:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][390/1251]	eta 0:32:16 lr 0.000987	time 2.0252 (2.2491)	loss 4.5479 (4.4089)	grad_norm 1.4427 (1.2730)	
[2022-01-18 05:05:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][400/1251]	eta 0:31:52 lr 0.000987	time 1.8803 (2.2477)	loss 4.6505 (4.4104)	grad_norm 1.3252 (1.2723)	
[2022-01-18 05:06:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][410/1251]	eta 0:31:27 lr 0.000987	time 1.9425 (2.2445)	loss 5.0818 (4.4131)	grad_norm 1.0706 (1.2681)	
[2022-01-18 05:06:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][420/1251]	eta 0:31:03 lr 0.000987	time 1.5998 (2.2424)	loss 4.8881 (4.4060)	grad_norm 1.1515 (1.2681)	
[2022-01-18 05:06:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][430/1251]	eta 0:30:37 lr 0.000987	time 1.9059 (2.2383)	loss 3.8662 (4.4087)	grad_norm 1.4506 (1.2672)	
[2022-01-18 05:07:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][440/1251]	eta 0:30:12 lr 0.000987	time 1.5556 (2.2346)	loss 4.4437 (4.4085)	grad_norm 1.7023 (1.2673)	
[2022-01-18 05:07:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][450/1251]	eta 0:29:47 lr 0.000986	time 2.5527 (2.2320)	loss 4.2785 (4.4141)	grad_norm 1.3167 (1.2666)	
[2022-01-18 05:07:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][460/1251]	eta 0:29:22 lr 0.000986	time 2.1265 (2.2283)	loss 3.6047 (4.4104)	grad_norm 1.3451 (1.2658)	
[2022-01-18 05:08:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][470/1251]	eta 0:29:00 lr 0.000986	time 2.8402 (2.2281)	loss 4.6308 (4.4106)	grad_norm 1.2094 (1.2656)	
[2022-01-18 05:08:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][480/1251]	eta 0:28:37 lr 0.000986	time 1.7408 (2.2278)	loss 4.8178 (4.4137)	grad_norm 1.4973 (1.2632)	
[2022-01-18 05:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][490/1251]	eta 0:28:15 lr 0.000986	time 2.8368 (2.2284)	loss 4.6228 (4.4094)	grad_norm 1.3078 (1.2603)	
[2022-01-18 05:09:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][500/1251]	eta 0:27:54 lr 0.000986	time 2.4092 (2.2302)	loss 4.6627 (4.4102)	grad_norm 1.0210 (1.2601)	
[2022-01-18 05:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][510/1251]	eta 0:27:31 lr 0.000986	time 1.8660 (2.2285)	loss 3.7609 (4.4068)	grad_norm 1.1840 (1.2595)	
[2022-01-18 05:10:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][520/1251]	eta 0:27:08 lr 0.000986	time 2.2763 (2.2271)	loss 4.4053 (4.4085)	grad_norm 1.2811 (1.2602)	
[2022-01-18 05:10:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][530/1251]	eta 0:26:44 lr 0.000986	time 2.7298 (2.2254)	loss 5.2593 (4.4079)	grad_norm 1.2588 (1.2581)	
[2022-01-18 05:10:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][540/1251]	eta 0:26:20 lr 0.000986	time 2.0552 (2.2236)	loss 4.6227 (4.4060)	grad_norm 1.1443 (1.2586)	
[2022-01-18 05:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][550/1251]	eta 0:25:56 lr 0.000986	time 2.2052 (2.2209)	loss 3.7135 (4.4030)	grad_norm 1.1507 (1.2584)	
[2022-01-18 05:11:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][560/1251]	eta 0:25:35 lr 0.000986	time 2.1836 (2.2217)	loss 4.6815 (4.4086)	grad_norm 1.2196 (1.2582)	
[2022-01-18 05:11:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][570/1251]	eta 0:25:15 lr 0.000986	time 3.4602 (2.2257)	loss 4.1735 (4.4140)	grad_norm 1.3061 (1.2578)	
[2022-01-18 05:12:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][580/1251]	eta 0:24:54 lr 0.000986	time 1.7634 (2.2278)	loss 3.7948 (4.4054)	grad_norm 1.1064 (1.2586)	
[2022-01-18 05:12:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][590/1251]	eta 0:24:33 lr 0.000986	time 2.1522 (2.2292)	loss 4.3245 (4.4096)	grad_norm 1.3287 (1.2583)	
[2022-01-18 05:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][600/1251]	eta 0:24:09 lr 0.000986	time 1.8243 (2.2263)	loss 4.6130 (4.4080)	grad_norm 1.1304 (1.2578)	
[2022-01-18 05:13:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][610/1251]	eta 0:23:45 lr 0.000986	time 1.9045 (2.2233)	loss 3.2512 (4.4024)	grad_norm 1.2190 (1.2570)	
[2022-01-18 05:13:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][620/1251]	eta 0:23:19 lr 0.000986	time 1.8846 (2.2178)	loss 4.5500 (4.4008)	grad_norm 1.2120 (1.2573)	
[2022-01-18 05:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][630/1251]	eta 0:22:54 lr 0.000986	time 2.2124 (2.2141)	loss 4.6146 (4.4061)	grad_norm 1.2004 (1.2580)	
[2022-01-18 05:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][640/1251]	eta 0:22:31 lr 0.000986	time 2.0244 (2.2115)	loss 3.5688 (4.4021)	grad_norm 1.1301 (1.2570)	
[2022-01-18 05:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][650/1251]	eta 0:22:09 lr 0.000986	time 2.4087 (2.2127)	loss 5.0353 (4.4043)	grad_norm 1.1403 (1.2553)	
[2022-01-18 05:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][660/1251]	eta 0:21:46 lr 0.000986	time 1.8058 (2.2102)	loss 4.7027 (4.4050)	grad_norm 1.1943 (1.2563)	
[2022-01-18 05:15:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][670/1251]	eta 0:21:24 lr 0.000986	time 2.1697 (2.2107)	loss 3.3953 (4.4004)	grad_norm 1.2947 (1.2558)	
[2022-01-18 05:15:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][680/1251]	eta 0:21:03 lr 0.000986	time 2.1538 (2.2120)	loss 5.2544 (4.4023)	grad_norm 1.1632 (1.2565)	
[2022-01-18 05:16:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][690/1251]	eta 0:20:43 lr 0.000986	time 2.5348 (2.2158)	loss 4.0565 (4.4003)	grad_norm 1.0440 (1.2562)	
[2022-01-18 05:16:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][700/1251]	eta 0:20:22 lr 0.000986	time 1.9977 (2.2184)	loss 4.9262 (4.4008)	grad_norm 1.2273 (1.2554)	
[2022-01-18 05:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][710/1251]	eta 0:20:00 lr 0.000986	time 2.2517 (2.2197)	loss 4.4210 (4.4041)	grad_norm 1.2868 (1.2572)	
[2022-01-18 05:17:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][720/1251]	eta 0:19:38 lr 0.000986	time 2.2330 (2.2195)	loss 3.6370 (4.4000)	grad_norm 1.4130 (1.2565)	
[2022-01-18 05:17:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][730/1251]	eta 0:19:14 lr 0.000986	time 1.6155 (2.2162)	loss 4.6125 (4.4015)	grad_norm 1.4913 (1.2559)	
[2022-01-18 05:18:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][740/1251]	eta 0:18:50 lr 0.000986	time 1.7889 (2.2131)	loss 4.6004 (4.4053)	grad_norm 1.4274 (1.2574)	
[2022-01-18 05:18:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][750/1251]	eta 0:18:28 lr 0.000986	time 1.8938 (2.2124)	loss 3.3855 (4.4045)	grad_norm 1.3446 (1.2579)	
[2022-01-18 05:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][760/1251]	eta 0:18:06 lr 0.000986	time 2.2185 (2.2131)	loss 3.4448 (4.4041)	grad_norm 1.0671 (1.2580)	
[2022-01-18 05:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][770/1251]	eta 0:17:44 lr 0.000986	time 1.5513 (2.2125)	loss 4.3806 (4.4048)	grad_norm 1.4216 (1.2584)	
[2022-01-18 05:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][780/1251]	eta 0:17:21 lr 0.000986	time 1.9357 (2.2123)	loss 4.4420 (4.4043)	grad_norm 0.9154 (1.2568)	
[2022-01-18 05:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][790/1251]	eta 0:16:59 lr 0.000986	time 1.7691 (2.2116)	loss 4.6879 (4.4079)	grad_norm 1.3199 (1.2565)	
[2022-01-18 05:20:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][800/1251]	eta 0:16:36 lr 0.000986	time 2.0165 (2.2098)	loss 4.4258 (4.4060)	grad_norm 0.9970 (1.2562)	
[2022-01-18 05:20:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][810/1251]	eta 0:16:14 lr 0.000986	time 1.9367 (2.2108)	loss 4.2283 (4.4042)	grad_norm 1.3304 (1.2548)	
[2022-01-18 05:20:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][820/1251]	eta 0:15:53 lr 0.000986	time 2.0943 (2.2124)	loss 3.8165 (4.4032)	grad_norm 1.1334 (1.2550)	
[2022-01-18 05:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][830/1251]	eta 0:15:31 lr 0.000986	time 1.6346 (2.2120)	loss 4.6836 (4.3995)	grad_norm 0.9799 (1.2562)	
[2022-01-18 05:21:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][840/1251]	eta 0:15:08 lr 0.000986	time 1.8855 (2.2099)	loss 4.6621 (4.4025)	grad_norm 0.9254 (1.2545)	
[2022-01-18 05:22:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][850/1251]	eta 0:14:45 lr 0.000986	time 2.0349 (2.2087)	loss 4.0180 (4.4024)	grad_norm 1.0373 (1.2525)	
[2022-01-18 05:22:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][860/1251]	eta 0:14:23 lr 0.000986	time 1.8076 (2.2078)	loss 4.5867 (4.4023)	grad_norm 1.2670 (1.2523)	
[2022-01-18 05:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][870/1251]	eta 0:14:01 lr 0.000986	time 1.6031 (2.2077)	loss 4.3023 (4.3993)	grad_norm 1.2349 (1.2521)	
[2022-01-18 05:23:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][880/1251]	eta 0:13:39 lr 0.000986	time 2.0677 (2.2080)	loss 5.0550 (4.3999)	grad_norm 1.3233 (1.2536)	
[2022-01-18 05:23:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][890/1251]	eta 0:13:17 lr 0.000986	time 1.9590 (2.2095)	loss 4.8526 (4.3995)	grad_norm 1.3995 (1.2535)	
[2022-01-18 05:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][900/1251]	eta 0:12:55 lr 0.000986	time 2.2079 (2.2090)	loss 4.6579 (4.3984)	grad_norm 1.1165 (1.2526)	
[2022-01-18 05:24:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][910/1251]	eta 0:12:33 lr 0.000986	time 1.5409 (2.2091)	loss 3.6519 (4.3980)	grad_norm 1.3549 (1.2519)	
[2022-01-18 05:24:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][920/1251]	eta 0:12:11 lr 0.000986	time 1.9545 (2.2090)	loss 4.9921 (4.3963)	grad_norm 1.3994 (1.2529)	
[2022-01-18 05:24:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][930/1251]	eta 0:11:49 lr 0.000986	time 1.4924 (2.2098)	loss 3.9411 (4.3954)	grad_norm 1.2768 (1.2526)	
[2022-01-18 05:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][940/1251]	eta 0:11:26 lr 0.000986	time 2.3197 (2.2088)	loss 4.3893 (4.3966)	grad_norm 2.0169 (1.2537)	
[2022-01-18 05:25:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][950/1251]	eta 0:11:04 lr 0.000986	time 2.0061 (2.2066)	loss 4.5563 (4.3959)	grad_norm 1.2782 (1.2536)	
[2022-01-18 05:26:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][960/1251]	eta 0:10:42 lr 0.000986	time 1.9217 (2.2070)	loss 4.4731 (4.3946)	grad_norm 1.0066 (1.2530)	
[2022-01-18 05:26:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][970/1251]	eta 0:10:20 lr 0.000986	time 2.2064 (2.2081)	loss 4.0708 (4.3956)	grad_norm 1.4055 (1.2526)	
[2022-01-18 05:26:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][980/1251]	eta 0:09:58 lr 0.000986	time 1.8525 (2.2076)	loss 4.9452 (4.3962)	grad_norm 1.0879 (1.2517)	
[2022-01-18 05:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][990/1251]	eta 0:09:36 lr 0.000986	time 1.6887 (2.2069)	loss 4.4728 (4.3984)	grad_norm 1.2195 (1.2511)	
[2022-01-18 05:27:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1000/1251]	eta 0:09:13 lr 0.000986	time 2.1991 (2.2052)	loss 4.6658 (4.3978)	grad_norm 1.3335 (1.2509)	
[2022-01-18 05:27:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1010/1251]	eta 0:08:51 lr 0.000986	time 2.3308 (2.2042)	loss 4.6845 (4.3969)	grad_norm 1.2051 (1.2503)	
[2022-01-18 05:28:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1020/1251]	eta 0:08:28 lr 0.000986	time 1.8284 (2.2027)	loss 5.2659 (4.3976)	grad_norm 1.2353 (1.2507)	
[2022-01-18 05:28:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1030/1251]	eta 0:08:06 lr 0.000986	time 1.9167 (2.2024)	loss 5.1308 (4.3972)	grad_norm 1.1830 (1.2512)	
[2022-01-18 05:28:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1040/1251]	eta 0:07:45 lr 0.000986	time 4.2502 (2.2059)	loss 4.4360 (4.3997)	grad_norm 1.9304 (1.2511)	
[2022-01-18 05:29:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1050/1251]	eta 0:07:23 lr 0.000986	time 2.2470 (2.2075)	loss 4.8196 (4.3975)	grad_norm 1.2291 (1.2519)	
[2022-01-18 05:29:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1060/1251]	eta 0:07:01 lr 0.000986	time 1.5106 (2.2077)	loss 4.5384 (4.3989)	grad_norm 1.1018 (1.2509)	
[2022-01-18 05:30:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1070/1251]	eta 0:06:39 lr 0.000986	time 1.7458 (2.2062)	loss 4.7402 (4.3985)	grad_norm 1.1574 (1.2504)	
[2022-01-18 05:30:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1080/1251]	eta 0:06:17 lr 0.000986	time 3.1442 (2.2058)	loss 4.9797 (4.3990)	grad_norm 1.0856 (1.2495)	
[2022-01-18 05:30:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1090/1251]	eta 0:05:55 lr 0.000986	time 2.2535 (2.2052)	loss 5.1031 (4.4007)	grad_norm 1.3501 (1.2494)	
[2022-01-18 05:31:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1100/1251]	eta 0:05:32 lr 0.000986	time 2.1512 (2.2040)	loss 5.2031 (4.4045)	grad_norm 1.2993 (1.2491)	
[2022-01-18 05:31:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1110/1251]	eta 0:05:10 lr 0.000986	time 1.9607 (2.2032)	loss 4.7534 (4.4042)	grad_norm 1.0620 (1.2494)	
[2022-01-18 05:31:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1120/1251]	eta 0:04:48 lr 0.000986	time 2.8698 (2.2031)	loss 3.3813 (4.4046)	grad_norm 1.2208 (1.2496)	
[2022-01-18 05:32:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1130/1251]	eta 0:04:26 lr 0.000986	time 2.5026 (2.2022)	loss 3.4959 (4.4050)	grad_norm 1.0450 (1.2498)	
[2022-01-18 05:32:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1140/1251]	eta 0:04:04 lr 0.000986	time 2.2455 (2.2011)	loss 4.0146 (4.4067)	grad_norm 1.1213 (1.2494)	
[2022-01-18 05:32:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1150/1251]	eta 0:03:42 lr 0.000986	time 1.8943 (2.2018)	loss 4.0113 (4.4049)	grad_norm 1.2068 (1.2494)	
[2022-01-18 05:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1160/1251]	eta 0:03:20 lr 0.000986	time 1.5937 (2.2020)	loss 4.4810 (4.4057)	grad_norm 1.4026 (1.2501)	
[2022-01-18 05:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1170/1251]	eta 0:02:58 lr 0.000986	time 2.7654 (2.2027)	loss 4.8038 (4.4062)	grad_norm 1.5190 (1.2509)	
[2022-01-18 05:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1180/1251]	eta 0:02:36 lr 0.000986	time 2.6144 (2.2036)	loss 5.0737 (4.4077)	grad_norm 1.1270 (1.2514)	
[2022-01-18 05:34:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1190/1251]	eta 0:02:14 lr 0.000986	time 1.5282 (2.2042)	loss 3.8382 (4.4080)	grad_norm 1.2106 (1.2510)	
[2022-01-18 05:34:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1200/1251]	eta 0:01:52 lr 0.000986	time 1.8636 (2.2033)	loss 4.4966 (4.4094)	grad_norm 1.0448 (1.2503)	
[2022-01-18 05:35:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1210/1251]	eta 0:01:30 lr 0.000986	time 2.3156 (2.2012)	loss 5.4461 (4.4108)	grad_norm 1.0249 (1.2496)	
[2022-01-18 05:35:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1220/1251]	eta 0:01:08 lr 0.000986	time 2.1510 (2.1984)	loss 3.5225 (4.4093)	grad_norm 1.1103 (1.2493)	
[2022-01-18 05:35:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1230/1251]	eta 0:00:46 lr 0.000986	time 2.2746 (2.1981)	loss 4.4516 (4.4108)	grad_norm 1.0862 (1.2485)	
[2022-01-18 05:36:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1240/1251]	eta 0:00:24 lr 0.000986	time 1.9158 (2.1979)	loss 4.6680 (4.4096)	grad_norm 1.3739 (1.2492)	
[2022-01-18 05:36:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [22/300][1250/1251]	eta 0:00:02 lr 0.000986	time 1.1634 (2.1932)	loss 4.2929 (4.4069)	grad_norm 1.2637 (1.2503)	
[2022-01-18 05:36:25 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 22 training takes 0:45:44
[2022-01-18 05:36:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.795 (18.795)	Loss 1.7729 (1.7729)	Acc@1 59.668 (59.668)	Acc@5 83.496 (83.496)	
[2022-01-18 05:37:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.305 (3.280)	Loss 1.7216 (1.7032)	Acc@1 61.719 (61.905)	Acc@5 84.570 (85.032)	
[2022-01-18 05:37:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.607 (2.591)	Loss 1.6803 (1.7164)	Acc@1 61.816 (61.444)	Acc@5 84.082 (84.594)	
[2022-01-18 05:37:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.630 (2.314)	Loss 1.7332 (1.7129)	Acc@1 61.133 (61.555)	Acc@5 85.742 (84.699)	
[2022-01-18 05:37:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.507 (2.187)	Loss 1.6486 (1.7110)	Acc@1 64.648 (61.662)	Acc@5 85.352 (84.668)	
[2022-01-18 05:38:01 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 61.604 Acc@5 84.678
[2022-01-18 05:38:01 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 61.6%
[2022-01-18 05:38:01 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 61.60%
[2022-01-18 05:38:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][0/1251]	eta 7:33:49 lr 0.000986	time 21.7662 (21.7662)	loss 3.7346 (3.7346)	grad_norm 1.2457 (1.2457)	
[2022-01-18 05:38:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][10/1251]	eta 1:24:55 lr 0.000986	time 1.8248 (4.1063)	loss 3.6961 (4.1799)	grad_norm 1.0516 (1.2308)	
[2022-01-18 05:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][20/1251]	eta 1:05:40 lr 0.000986	time 1.5266 (3.2012)	loss 4.1131 (4.3493)	grad_norm 1.0952 (1.2330)	
[2022-01-18 05:39:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][30/1251]	eta 0:58:07 lr 0.000986	time 1.9821 (2.8562)	loss 4.4830 (4.3615)	grad_norm 1.1087 (1.2147)	
[2022-01-18 05:39:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][40/1251]	eta 0:55:25 lr 0.000986	time 3.9186 (2.7460)	loss 4.3896 (4.3487)	grad_norm 1.0565 (1.2235)	
[2022-01-18 05:40:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][50/1251]	eta 0:53:08 lr 0.000986	time 1.9433 (2.6547)	loss 4.6203 (4.3327)	grad_norm 1.4816 (1.2255)	
[2022-01-18 05:40:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][60/1251]	eta 0:51:21 lr 0.000986	time 1.6872 (2.5874)	loss 2.9745 (4.3293)	grad_norm 1.3036 (1.2211)	
[2022-01-18 05:41:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][70/1251]	eta 0:50:02 lr 0.000986	time 1.7087 (2.5422)	loss 4.5548 (4.3248)	grad_norm 1.1816 (1.2680)	
[2022-01-18 05:41:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][80/1251]	eta 0:49:20 lr 0.000986	time 3.1932 (2.5280)	loss 5.0753 (4.3375)	grad_norm 1.1194 (1.2681)	
[2022-01-18 05:41:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][90/1251]	eta 0:48:14 lr 0.000986	time 1.8479 (2.4929)	loss 4.9180 (4.3691)	grad_norm 1.0528 (1.2554)	
[2022-01-18 05:42:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][100/1251]	eta 0:47:00 lr 0.000986	time 1.6103 (2.4502)	loss 4.2712 (4.3988)	grad_norm 1.0547 (1.2486)	
[2022-01-18 05:42:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][110/1251]	eta 0:45:36 lr 0.000986	time 1.9329 (2.3981)	loss 4.8706 (4.3920)	grad_norm 1.2752 (1.2561)	
[2022-01-18 05:42:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][120/1251]	eta 0:44:45 lr 0.000986	time 3.3229 (2.3743)	loss 4.9620 (4.3657)	grad_norm 1.2041 (1.2566)	
[2022-01-18 05:43:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][130/1251]	eta 0:44:02 lr 0.000986	time 1.9528 (2.3569)	loss 4.7716 (4.3542)	grad_norm 1.2729 (1.2521)	
[2022-01-18 05:43:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][140/1251]	eta 0:43:27 lr 0.000986	time 2.5649 (2.3467)	loss 5.1953 (4.3459)	grad_norm 1.0905 (1.2451)	
[2022-01-18 05:43:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][150/1251]	eta 0:43:02 lr 0.000986	time 2.3754 (2.3456)	loss 3.6762 (4.3427)	grad_norm 1.1118 (1.2472)	
[2022-01-18 05:44:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][160/1251]	eta 0:42:45 lr 0.000986	time 2.9041 (2.3512)	loss 3.9064 (4.3422)	grad_norm 1.1796 (1.2477)	
[2022-01-18 05:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][170/1251]	eta 0:42:18 lr 0.000986	time 1.7905 (2.3481)	loss 3.9143 (4.3351)	grad_norm 1.3342 (1.2441)	
[2022-01-18 05:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][180/1251]	eta 0:41:44 lr 0.000986	time 2.1234 (2.3385)	loss 4.4472 (4.3217)	grad_norm 1.1871 (1.2406)	
[2022-01-18 05:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][190/1251]	eta 0:40:59 lr 0.000986	time 1.5294 (2.3178)	loss 4.6140 (4.3352)	grad_norm 1.2764 (1.2401)	
[2022-01-18 05:45:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][200/1251]	eta 0:40:21 lr 0.000986	time 2.4723 (2.3040)	loss 4.3081 (4.3425)	grad_norm 1.1581 (1.2339)	
[2022-01-18 05:46:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][210/1251]	eta 0:39:42 lr 0.000986	time 1.9793 (2.2891)	loss 4.4074 (4.3464)	grad_norm 1.4624 (1.2342)	
[2022-01-18 05:46:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][220/1251]	eta 0:39:16 lr 0.000985	time 1.8481 (2.2854)	loss 4.5429 (4.3489)	grad_norm 1.1029 (1.2373)	
[2022-01-18 05:46:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][230/1251]	eta 0:38:52 lr 0.000985	time 2.1532 (2.2844)	loss 4.9066 (4.3475)	grad_norm 1.2149 (1.2392)	
[2022-01-18 05:47:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][240/1251]	eta 0:38:22 lr 0.000985	time 1.9529 (2.2774)	loss 4.0514 (4.3466)	grad_norm 0.9950 (1.2399)	
[2022-01-18 05:47:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][250/1251]	eta 0:38:08 lr 0.000985	time 3.2903 (2.2866)	loss 4.3731 (4.3455)	grad_norm 1.1290 (1.2345)	
[2022-01-18 05:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][260/1251]	eta 0:37:48 lr 0.000985	time 2.5572 (2.2889)	loss 3.7641 (4.3488)	grad_norm 1.1743 (1.2377)	
[2022-01-18 05:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][270/1251]	eta 0:37:21 lr 0.000985	time 1.5031 (2.2847)	loss 4.5497 (4.3479)	grad_norm 1.0119 (1.2386)	
[2022-01-18 05:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][280/1251]	eta 0:36:55 lr 0.000985	time 1.9241 (2.2816)	loss 4.5204 (4.3483)	grad_norm 1.0252 (1.2383)	
[2022-01-18 05:49:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][290/1251]	eta 0:36:21 lr 0.000985	time 1.6572 (2.2703)	loss 4.8583 (4.3542)	grad_norm 1.0118 (1.2353)	
[2022-01-18 05:49:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][300/1251]	eta 0:35:50 lr 0.000985	time 2.4709 (2.2616)	loss 4.3358 (4.3476)	grad_norm 1.2111 (1.2355)	
[2022-01-18 05:49:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][310/1251]	eta 0:35:25 lr 0.000985	time 2.1313 (2.2585)	loss 4.8668 (4.3575)	grad_norm 0.8883 (1.2302)	
[2022-01-18 05:50:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][320/1251]	eta 0:34:59 lr 0.000985	time 1.8016 (2.2546)	loss 4.9174 (4.3581)	grad_norm 1.5540 (1.2309)	
[2022-01-18 05:50:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][330/1251]	eta 0:34:35 lr 0.000985	time 1.9882 (2.2533)	loss 4.6966 (4.3574)	grad_norm 1.3364 (1.2312)	
[2022-01-18 05:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][340/1251]	eta 0:34:09 lr 0.000985	time 2.2848 (2.2502)	loss 4.0397 (4.3559)	grad_norm 1.3344 (1.2331)	
[2022-01-18 05:51:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][350/1251]	eta 0:33:43 lr 0.000985	time 2.2495 (2.2463)	loss 2.9354 (4.3493)	grad_norm 1.0722 (1.2347)	
[2022-01-18 05:51:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][360/1251]	eta 0:33:23 lr 0.000985	time 2.6720 (2.2481)	loss 4.9573 (4.3465)	grad_norm 1.3305 (1.2360)	
[2022-01-18 05:51:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][370/1251]	eta 0:33:00 lr 0.000985	time 2.6332 (2.2485)	loss 4.5785 (4.3520)	grad_norm 1.2106 (1.2394)	
[2022-01-18 05:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][380/1251]	eta 0:32:36 lr 0.000985	time 2.5808 (2.2464)	loss 4.5114 (4.3573)	grad_norm 1.1171 (1.2390)	
[2022-01-18 05:52:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][390/1251]	eta 0:32:10 lr 0.000985	time 1.8892 (2.2426)	loss 4.3044 (4.3587)	grad_norm 1.9294 (1.2420)	
[2022-01-18 05:52:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][400/1251]	eta 0:31:44 lr 0.000985	time 2.0469 (2.2381)	loss 5.0138 (4.3584)	grad_norm 1.1881 (1.2410)	
[2022-01-18 05:53:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][410/1251]	eta 0:31:25 lr 0.000985	time 2.5193 (2.2418)	loss 5.1397 (4.3587)	grad_norm 1.1662 (1.2423)	
[2022-01-18 05:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][420/1251]	eta 0:31:04 lr 0.000985	time 2.1322 (2.2436)	loss 3.1408 (4.3508)	grad_norm 1.2262 (1.2460)	
[2022-01-18 05:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][430/1251]	eta 0:30:42 lr 0.000985	time 1.6866 (2.2439)	loss 4.6906 (4.3511)	grad_norm 1.1425 (1.2461)	
[2022-01-18 05:54:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][440/1251]	eta 0:30:17 lr 0.000985	time 2.1162 (2.2413)	loss 3.8503 (4.3499)	grad_norm 1.0941 (1.2452)	
[2022-01-18 05:54:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][450/1251]	eta 0:29:56 lr 0.000985	time 2.2854 (2.2429)	loss 3.4595 (4.3509)	grad_norm 0.9871 (1.2430)	
[2022-01-18 05:55:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][460/1251]	eta 0:29:29 lr 0.000985	time 2.0394 (2.2372)	loss 4.7916 (4.3525)	grad_norm 1.4786 (1.2430)	
[2022-01-18 05:55:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][470/1251]	eta 0:29:02 lr 0.000985	time 1.5637 (2.2311)	loss 3.3875 (4.3505)	grad_norm 0.9739 (1.2421)	
[2022-01-18 05:55:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][480/1251]	eta 0:28:38 lr 0.000985	time 1.8370 (2.2290)	loss 4.9431 (4.3558)	grad_norm 1.5368 (1.2416)	
[2022-01-18 05:56:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][490/1251]	eta 0:28:16 lr 0.000985	time 2.6143 (2.2289)	loss 4.1188 (4.3522)	grad_norm 1.4276 (1.2408)	
[2022-01-18 05:56:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][500/1251]	eta 0:27:54 lr 0.000985	time 2.0038 (2.2293)	loss 4.5381 (4.3532)	grad_norm 1.0929 (1.2388)	
[2022-01-18 05:57:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][510/1251]	eta 0:27:33 lr 0.000985	time 2.3881 (2.2311)	loss 4.4434 (4.3614)	grad_norm 1.2488 (1.2399)	
[2022-01-18 05:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][520/1251]	eta 0:27:11 lr 0.000985	time 1.8497 (2.2319)	loss 4.6147 (4.3697)	grad_norm 1.2538 (1.2401)	
[2022-01-18 05:57:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][530/1251]	eta 0:26:47 lr 0.000985	time 1.6652 (2.2297)	loss 4.9333 (4.3704)	grad_norm 1.1750 (1.2386)	
[2022-01-18 05:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][540/1251]	eta 0:26:24 lr 0.000985	time 1.9097 (2.2290)	loss 4.1021 (4.3710)	grad_norm 1.0752 (1.2380)	
[2022-01-18 05:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][550/1251]	eta 0:26:01 lr 0.000985	time 2.0855 (2.2276)	loss 4.0846 (4.3709)	grad_norm 1.1486 (1.2376)	
[2022-01-18 05:58:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][560/1251]	eta 0:25:43 lr 0.000985	time 1.8429 (2.2332)	loss 4.4413 (4.3738)	grad_norm 1.2227 (1.2375)	
[2022-01-18 05:59:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][570/1251]	eta 0:25:18 lr 0.000985	time 1.6573 (2.2300)	loss 4.2684 (4.3797)	grad_norm 2.0495 (1.2394)	
[2022-01-18 05:59:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][580/1251]	eta 0:24:52 lr 0.000985	time 1.7237 (2.2250)	loss 3.0775 (4.3821)	grad_norm 1.2814 (1.2396)	
[2022-01-18 05:59:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][590/1251]	eta 0:24:32 lr 0.000985	time 1.9205 (2.2280)	loss 4.7678 (4.3788)	grad_norm 1.1442 (1.2380)	
[2022-01-18 06:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][600/1251]	eta 0:24:09 lr 0.000985	time 1.7486 (2.2272)	loss 5.1163 (4.3797)	grad_norm 1.3916 (1.2384)	
[2022-01-18 06:00:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][610/1251]	eta 0:23:46 lr 0.000985	time 1.5654 (2.2249)	loss 3.5936 (4.3755)	grad_norm 1.4775 (1.2388)	
[2022-01-18 06:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][620/1251]	eta 0:23:23 lr 0.000985	time 2.4128 (2.2243)	loss 5.0051 (4.3789)	grad_norm 1.6178 (1.2381)	
[2022-01-18 06:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][630/1251]	eta 0:22:59 lr 0.000985	time 1.5797 (2.2209)	loss 4.8693 (4.3803)	grad_norm 1.1882 (1.2379)	
[2022-01-18 06:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][640/1251]	eta 0:22:36 lr 0.000985	time 1.9585 (2.2208)	loss 4.9907 (4.3792)	grad_norm 1.3093 (1.2367)	
[2022-01-18 06:02:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][650/1251]	eta 0:22:13 lr 0.000985	time 1.8509 (2.2192)	loss 4.6178 (4.3790)	grad_norm 1.0930 (1.2372)	
[2022-01-18 06:02:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][660/1251]	eta 0:21:53 lr 0.000985	time 2.8794 (2.2228)	loss 5.1969 (4.3773)	grad_norm 1.2600 (1.2365)	
[2022-01-18 06:02:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][670/1251]	eta 0:21:32 lr 0.000985	time 2.8184 (2.2239)	loss 3.2138 (4.3756)	grad_norm 1.2325 (1.2367)	
[2022-01-18 06:03:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][680/1251]	eta 0:21:09 lr 0.000985	time 1.7508 (2.2237)	loss 4.5651 (4.3721)	grad_norm 1.1653 (1.2374)	
[2022-01-18 06:03:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][690/1251]	eta 0:20:45 lr 0.000985	time 1.6338 (2.2203)	loss 4.7542 (4.3729)	grad_norm 1.0101 (1.2366)	
[2022-01-18 06:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][700/1251]	eta 0:20:21 lr 0.000985	time 2.2324 (2.2164)	loss 4.7584 (4.3730)	grad_norm 1.4820 (1.2371)	
[2022-01-18 06:04:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][710/1251]	eta 0:19:57 lr 0.000985	time 1.9963 (2.2141)	loss 4.9147 (4.3774)	grad_norm 1.0250 (1.2365)	
[2022-01-18 06:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][720/1251]	eta 0:19:35 lr 0.000985	time 1.8032 (2.2129)	loss 5.0612 (4.3776)	grad_norm 1.0996 (1.2371)	
[2022-01-18 06:05:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][730/1251]	eta 0:19:13 lr 0.000985	time 2.2554 (2.2137)	loss 3.3350 (4.3784)	grad_norm 1.3043 (1.2366)	
[2022-01-18 06:05:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][740/1251]	eta 0:18:51 lr 0.000985	time 1.9832 (2.2152)	loss 3.8050 (4.3816)	grad_norm 1.0327 (1.2360)	
[2022-01-18 06:05:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][750/1251]	eta 0:18:30 lr 0.000985	time 3.0557 (2.2159)	loss 4.4977 (4.3778)	grad_norm 1.0669 (1.2357)	
[2022-01-18 06:06:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][760/1251]	eta 0:18:06 lr 0.000985	time 1.7786 (2.2122)	loss 4.4800 (4.3734)	grad_norm 1.2985 (1.2363)	
[2022-01-18 06:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][770/1251]	eta 0:17:43 lr 0.000985	time 1.7205 (2.2120)	loss 4.4509 (4.3764)	grad_norm 1.1643 (1.2364)	
[2022-01-18 06:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][780/1251]	eta 0:17:22 lr 0.000985	time 3.1657 (2.2137)	loss 3.3605 (4.3740)	grad_norm 1.0789 (1.2363)	
[2022-01-18 06:07:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][790/1251]	eta 0:17:00 lr 0.000985	time 2.2306 (2.2133)	loss 4.7959 (4.3770)	grad_norm 1.3212 (1.2382)	
[2022-01-18 06:07:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][800/1251]	eta 0:16:38 lr 0.000985	time 1.8667 (2.2136)	loss 4.6509 (4.3782)	grad_norm 1.0905 (1.2379)	
[2022-01-18 06:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][810/1251]	eta 0:16:15 lr 0.000985	time 2.0194 (2.2126)	loss 3.0207 (4.3772)	grad_norm 1.1303 (1.2374)	
[2022-01-18 06:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][820/1251]	eta 0:15:53 lr 0.000985	time 2.4946 (2.2113)	loss 3.3404 (4.3746)	grad_norm 1.4165 (1.2378)	
[2022-01-18 06:08:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][830/1251]	eta 0:15:30 lr 0.000985	time 1.8160 (2.2095)	loss 4.4163 (4.3736)	grad_norm 1.2608 (1.2374)	
[2022-01-18 06:08:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][840/1251]	eta 0:15:07 lr 0.000985	time 1.8727 (2.2091)	loss 3.5461 (4.3711)	grad_norm 1.1274 (1.2373)	
[2022-01-18 06:09:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][850/1251]	eta 0:14:46 lr 0.000985	time 2.2653 (2.2104)	loss 3.5264 (4.3677)	grad_norm 1.1959 (1.2371)	
[2022-01-18 06:09:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][860/1251]	eta 0:14:24 lr 0.000985	time 2.4769 (2.2107)	loss 5.0979 (4.3673)	grad_norm 1.3599 (1.2369)	
[2022-01-18 06:10:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][870/1251]	eta 0:14:01 lr 0.000985	time 1.9329 (2.2093)	loss 4.5201 (4.3686)	grad_norm 1.2564 (1.2368)	
[2022-01-18 06:10:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][880/1251]	eta 0:13:39 lr 0.000985	time 1.8938 (2.2081)	loss 4.6219 (4.3710)	grad_norm 1.1945 (1.2370)	
[2022-01-18 06:10:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][890/1251]	eta 0:13:17 lr 0.000985	time 2.1001 (2.2086)	loss 3.4272 (4.3696)	grad_norm 0.9915 (1.2364)	
[2022-01-18 06:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][900/1251]	eta 0:12:55 lr 0.000985	time 1.6821 (2.2088)	loss 4.5852 (4.3719)	grad_norm 0.9373 (1.2365)	
[2022-01-18 06:11:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][910/1251]	eta 0:12:33 lr 0.000985	time 2.5887 (2.2091)	loss 5.1803 (4.3741)	grad_norm 1.1741 (1.2357)	
[2022-01-18 06:11:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][920/1251]	eta 0:12:10 lr 0.000985	time 2.4612 (2.2083)	loss 5.0072 (4.3749)	grad_norm 0.9817 (1.2353)	
[2022-01-18 06:12:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][930/1251]	eta 0:11:48 lr 0.000985	time 2.1986 (2.2068)	loss 4.5334 (4.3754)	grad_norm 1.2240 (1.2348)	
[2022-01-18 06:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][940/1251]	eta 0:11:25 lr 0.000985	time 1.7111 (2.2054)	loss 4.5302 (4.3742)	grad_norm 1.1833 (1.2354)	
[2022-01-18 06:13:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][950/1251]	eta 0:11:04 lr 0.000985	time 2.8654 (2.2067)	loss 4.9662 (4.3767)	grad_norm 1.1422 (1.2352)	
[2022-01-18 06:13:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][960/1251]	eta 0:10:42 lr 0.000985	time 1.8879 (2.2071)	loss 3.0880 (4.3735)	grad_norm 1.0739 (1.2344)	
[2022-01-18 06:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][970/1251]	eta 0:10:20 lr 0.000985	time 1.8544 (2.2064)	loss 4.3139 (4.3733)	grad_norm 1.0743 (1.2339)	
[2022-01-18 06:14:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][980/1251]	eta 0:09:57 lr 0.000985	time 1.8001 (2.2061)	loss 4.5103 (4.3734)	grad_norm 1.2583 (1.2336)	
[2022-01-18 06:14:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][990/1251]	eta 0:09:35 lr 0.000985	time 2.8303 (2.2049)	loss 4.6320 (4.3711)	grad_norm 1.6232 (1.2342)	
[2022-01-18 06:14:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1000/1251]	eta 0:09:13 lr 0.000985	time 2.2192 (2.2044)	loss 3.5464 (4.3707)	grad_norm 0.9677 (1.2329)	
[2022-01-18 06:15:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1010/1251]	eta 0:08:51 lr 0.000985	time 1.8571 (2.2050)	loss 4.5987 (4.3688)	grad_norm 1.1967 (1.2327)	
[2022-01-18 06:15:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1020/1251]	eta 0:08:29 lr 0.000985	time 2.0415 (2.2037)	loss 4.6276 (4.3692)	grad_norm 1.2444 (1.2327)	
[2022-01-18 06:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1030/1251]	eta 0:08:07 lr 0.000985	time 1.8976 (2.2037)	loss 4.8222 (4.3706)	grad_norm 1.3379 (1.2323)	
[2022-01-18 06:16:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1040/1251]	eta 0:07:44 lr 0.000985	time 1.9103 (2.2027)	loss 5.0405 (4.3716)	grad_norm 1.3682 (1.2329)	
[2022-01-18 06:16:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1050/1251]	eta 0:07:22 lr 0.000985	time 2.0576 (2.2016)	loss 5.2704 (4.3726)	grad_norm 1.5203 (1.2327)	
[2022-01-18 06:16:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1060/1251]	eta 0:07:00 lr 0.000985	time 2.4716 (2.2007)	loss 4.7342 (4.3729)	grad_norm 1.3823 (1.2334)	
[2022-01-18 06:17:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1070/1251]	eta 0:06:38 lr 0.000985	time 1.9182 (2.2001)	loss 3.6909 (4.3723)	grad_norm 1.1512 (1.2335)	
[2022-01-18 06:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1080/1251]	eta 0:06:16 lr 0.000985	time 1.8966 (2.1997)	loss 3.2792 (4.3721)	grad_norm 1.2678 (1.2332)	
[2022-01-18 06:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1090/1251]	eta 0:05:54 lr 0.000985	time 2.8158 (2.2010)	loss 3.6753 (4.3721)	grad_norm 1.1320 (1.2317)	
[2022-01-18 06:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1100/1251]	eta 0:05:32 lr 0.000985	time 2.1334 (2.2010)	loss 5.0020 (4.3728)	grad_norm 1.4425 (1.2304)	
[2022-01-18 06:18:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1110/1251]	eta 0:05:10 lr 0.000985	time 2.1332 (2.2008)	loss 3.3427 (4.3714)	grad_norm 1.1481 (1.2307)	
[2022-01-18 06:19:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1120/1251]	eta 0:04:48 lr 0.000985	time 1.9773 (2.2002)	loss 3.4840 (4.3696)	grad_norm 1.5343 (1.2318)	
[2022-01-18 06:19:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1130/1251]	eta 0:04:26 lr 0.000985	time 2.8031 (2.2002)	loss 4.6545 (4.3697)	grad_norm 1.0789 (1.2311)	
[2022-01-18 06:19:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1140/1251]	eta 0:04:04 lr 0.000985	time 2.8999 (2.2009)	loss 3.1982 (4.3686)	grad_norm 1.2281 (1.2308)	
[2022-01-18 06:20:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1150/1251]	eta 0:03:42 lr 0.000985	time 2.3019 (2.2001)	loss 4.4923 (4.3681)	grad_norm 1.1892 (1.2303)	
[2022-01-18 06:20:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1160/1251]	eta 0:03:20 lr 0.000985	time 1.8595 (2.1997)	loss 4.6972 (4.3673)	grad_norm 1.2919 (1.2298)	
[2022-01-18 06:20:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1170/1251]	eta 0:02:58 lr 0.000985	time 2.6397 (2.1988)	loss 3.8694 (4.3675)	grad_norm 1.2256 (1.2301)	
[2022-01-18 06:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1180/1251]	eta 0:02:36 lr 0.000985	time 2.1447 (2.1990)	loss 4.7758 (4.3697)	grad_norm 1.0969 (1.2303)	
[2022-01-18 06:21:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1190/1251]	eta 0:02:14 lr 0.000985	time 1.5186 (2.1989)	loss 5.0667 (4.3710)	grad_norm 1.2274 (1.2303)	
[2022-01-18 06:22:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1200/1251]	eta 0:01:52 lr 0.000985	time 2.1376 (2.2005)	loss 2.9760 (4.3717)	grad_norm 1.1426 (1.2300)	
[2022-01-18 06:22:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1210/1251]	eta 0:01:30 lr 0.000984	time 2.7148 (2.2007)	loss 2.8298 (4.3693)	grad_norm 1.0432 (1.2298)	
[2022-01-18 06:22:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1220/1251]	eta 0:01:08 lr 0.000984	time 2.3528 (2.1999)	loss 5.3470 (4.3715)	grad_norm 1.1603 (1.2286)	
[2022-01-18 06:23:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1230/1251]	eta 0:00:46 lr 0.000984	time 1.9066 (2.1983)	loss 4.5015 (4.3716)	grad_norm 1.2627 (1.2289)	
[2022-01-18 06:23:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1240/1251]	eta 0:00:24 lr 0.000984	time 1.7642 (2.1969)	loss 4.3883 (4.3721)	grad_norm 1.2203 (1.2286)	
[2022-01-18 06:23:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [23/300][1250/1251]	eta 0:00:02 lr 0.000984	time 1.1874 (2.1907)	loss 3.5428 (4.3711)	grad_norm 1.2174 (1.2283)	
[2022-01-18 06:23:43 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 23 training takes 0:45:41
[2022-01-18 06:24:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.690 (18.690)	Loss 1.7633 (1.7633)	Acc@1 59.766 (59.766)	Acc@5 84.180 (84.180)	
[2022-01-18 06:24:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.632 (3.399)	Loss 1.6820 (1.7353)	Acc@1 63.281 (61.887)	Acc@5 85.449 (84.695)	
[2022-01-18 06:24:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.895 (2.633)	Loss 1.7488 (1.7296)	Acc@1 62.695 (62.267)	Acc@5 83.691 (84.868)	
[2022-01-18 06:24:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.619 (2.340)	Loss 1.7028 (1.7321)	Acc@1 63.770 (62.333)	Acc@5 84.863 (84.851)	
[2022-01-18 06:25:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.174 (2.125)	Loss 1.7477 (1.7279)	Acc@1 60.742 (62.438)	Acc@5 84.082 (84.892)	
[2022-01-18 06:25:19 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 62.412 Acc@5 84.894
[2022-01-18 06:25:19 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 62.4%
[2022-01-18 06:25:19 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 62.41%
[2022-01-18 06:25:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][0/1251]	eta 7:32:23 lr 0.000984	time 21.6972 (21.6972)	loss 4.8168 (4.8168)	grad_norm 1.0208 (1.0208)	
[2022-01-18 06:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][10/1251]	eta 1:21:33 lr 0.000984	time 1.9110 (3.9431)	loss 3.1807 (4.3055)	grad_norm 1.0321 (1.1431)	
[2022-01-18 06:26:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][20/1251]	eta 1:03:34 lr 0.000984	time 1.3330 (3.0987)	loss 4.5295 (4.3405)	grad_norm 0.9593 (1.1824)	
[2022-01-18 06:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][30/1251]	eta 0:55:47 lr 0.000984	time 1.8699 (2.7415)	loss 4.8739 (4.3751)	grad_norm 1.2021 (1.2103)	
[2022-01-18 06:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][40/1251]	eta 0:54:38 lr 0.000984	time 4.7116 (2.7074)	loss 4.4455 (4.3699)	grad_norm 1.4976 (1.2156)	
[2022-01-18 06:27:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][50/1251]	eta 0:52:45 lr 0.000984	time 2.4973 (2.6353)	loss 4.9316 (4.3795)	grad_norm 1.1078 (1.1997)	
[2022-01-18 06:27:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][60/1251]	eta 0:50:37 lr 0.000984	time 1.3812 (2.5505)	loss 4.5965 (4.3324)	grad_norm 1.0674 (1.1933)	
[2022-01-18 06:28:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][70/1251]	eta 0:49:20 lr 0.000984	time 2.2302 (2.5064)	loss 4.3403 (4.3255)	grad_norm 1.1145 (1.1851)	
[2022-01-18 06:28:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][80/1251]	eta 0:48:28 lr 0.000984	time 3.3781 (2.4836)	loss 4.0957 (4.3646)	grad_norm 1.3822 (1.1960)	
[2022-01-18 06:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][90/1251]	eta 0:47:28 lr 0.000984	time 2.2241 (2.4531)	loss 3.5079 (4.3927)	grad_norm 0.9911 (1.1985)	
[2022-01-18 06:29:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][100/1251]	eta 0:46:20 lr 0.000984	time 1.9228 (2.4159)	loss 4.9660 (4.3973)	grad_norm 1.2457 (1.2007)	
[2022-01-18 06:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][110/1251]	eta 0:45:24 lr 0.000984	time 2.1665 (2.3880)	loss 4.5318 (4.4192)	grad_norm 1.0005 (1.1930)	
[2022-01-18 06:30:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][120/1251]	eta 0:44:54 lr 0.000984	time 3.5905 (2.3826)	loss 4.0151 (4.4085)	grad_norm 1.1244 (1.1932)	
[2022-01-18 06:30:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][130/1251]	eta 0:44:13 lr 0.000984	time 2.3688 (2.3667)	loss 4.7654 (4.4175)	grad_norm 1.5091 (1.1938)	
[2022-01-18 06:30:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][140/1251]	eta 0:43:38 lr 0.000984	time 1.5292 (2.3568)	loss 3.3849 (4.4007)	grad_norm 1.1786 (1.1883)	
[2022-01-18 06:31:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][150/1251]	eta 0:43:02 lr 0.000984	time 1.8437 (2.3456)	loss 4.9320 (4.4122)	grad_norm 1.1673 (1.1830)	
[2022-01-18 06:31:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][160/1251]	eta 0:42:31 lr 0.000984	time 2.5135 (2.3388)	loss 4.7870 (4.3980)	grad_norm 1.1605 (1.1804)	
[2022-01-18 06:31:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][170/1251]	eta 0:41:48 lr 0.000984	time 1.9452 (2.3210)	loss 4.0520 (4.4005)	grad_norm 1.6178 (1.1818)	
[2022-01-18 06:32:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][180/1251]	eta 0:41:10 lr 0.000984	time 2.0776 (2.3071)	loss 4.5262 (4.4052)	grad_norm 1.6420 (1.1802)	
[2022-01-18 06:32:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][190/1251]	eta 0:40:29 lr 0.000984	time 2.0171 (2.2900)	loss 4.0041 (4.4018)	grad_norm 1.2869 (1.1806)	
[2022-01-18 06:32:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][200/1251]	eta 0:39:56 lr 0.000984	time 2.4262 (2.2801)	loss 3.5614 (4.3814)	grad_norm 1.4754 (1.1832)	
[2022-01-18 06:33:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][210/1251]	eta 0:39:21 lr 0.000984	time 1.9167 (2.2689)	loss 4.6140 (4.3690)	grad_norm 1.1107 (1.1920)	
[2022-01-18 06:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][220/1251]	eta 0:38:55 lr 0.000984	time 1.8708 (2.2654)	loss 4.1533 (4.3719)	grad_norm 1.1971 (1.1957)	
[2022-01-18 06:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][230/1251]	eta 0:38:34 lr 0.000984	time 2.1377 (2.2673)	loss 4.7471 (4.3871)	grad_norm 1.3145 (1.1994)	
[2022-01-18 06:34:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][240/1251]	eta 0:38:16 lr 0.000984	time 2.4717 (2.2711)	loss 4.5089 (4.3883)	grad_norm 1.1628 (1.2088)	
[2022-01-18 06:34:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][250/1251]	eta 0:37:51 lr 0.000984	time 1.9833 (2.2697)	loss 3.7669 (4.3813)	grad_norm 0.9960 (1.2070)	
[2022-01-18 06:35:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][260/1251]	eta 0:37:37 lr 0.000984	time 2.3811 (2.2776)	loss 3.5833 (4.3768)	grad_norm 1.3803 (1.2099)	
[2022-01-18 06:35:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][270/1251]	eta 0:37:11 lr 0.000984	time 2.1797 (2.2747)	loss 4.3669 (4.3720)	grad_norm 1.0512 (1.2137)	
[2022-01-18 06:35:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][280/1251]	eta 0:36:44 lr 0.000984	time 1.9078 (2.2702)	loss 3.2605 (4.3723)	grad_norm 0.9407 (1.2112)	
[2022-01-18 06:36:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][290/1251]	eta 0:36:16 lr 0.000984	time 1.8726 (2.2647)	loss 4.0265 (4.3704)	grad_norm 1.3465 (1.2121)	
[2022-01-18 06:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][300/1251]	eta 0:35:47 lr 0.000984	time 1.8402 (2.2584)	loss 4.2939 (4.3756)	grad_norm 1.1008 (1.2129)	
[2022-01-18 06:37:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][310/1251]	eta 0:35:23 lr 0.000984	time 2.1518 (2.2570)	loss 3.8170 (4.3748)	grad_norm 1.1208 (1.2149)	
[2022-01-18 06:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][320/1251]	eta 0:34:58 lr 0.000984	time 1.8629 (2.2544)	loss 4.3763 (4.3753)	grad_norm 1.1589 (1.2151)	
[2022-01-18 06:37:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][330/1251]	eta 0:34:37 lr 0.000984	time 1.9707 (2.2560)	loss 3.7114 (4.3705)	grad_norm 1.4043 (1.2190)	
[2022-01-18 06:38:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][340/1251]	eta 0:34:09 lr 0.000984	time 1.9286 (2.2499)	loss 3.8219 (4.3764)	grad_norm 1.0497 (1.2187)	
[2022-01-18 06:38:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][350/1251]	eta 0:33:43 lr 0.000984	time 2.3079 (2.2456)	loss 3.6494 (4.3738)	grad_norm 1.1925 (1.2223)	
[2022-01-18 06:38:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][360/1251]	eta 0:33:15 lr 0.000984	time 1.9347 (2.2396)	loss 3.6354 (4.3730)	grad_norm 1.7462 (1.2232)	
[2022-01-18 06:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][370/1251]	eta 0:32:52 lr 0.000984	time 2.1773 (2.2388)	loss 4.9781 (4.3729)	grad_norm 1.3369 (1.2251)	
[2022-01-18 06:39:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][380/1251]	eta 0:32:29 lr 0.000984	time 2.3564 (2.2384)	loss 4.7450 (4.3657)	grad_norm 0.9942 (1.2245)	
[2022-01-18 06:39:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][390/1251]	eta 0:32:04 lr 0.000984	time 2.1936 (2.2349)	loss 4.1116 (4.3589)	grad_norm 1.2666 (1.2267)	
[2022-01-18 06:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][400/1251]	eta 0:31:38 lr 0.000984	time 1.9874 (2.2309)	loss 4.4386 (4.3644)	grad_norm 1.0232 (1.2281)	
[2022-01-18 06:40:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][410/1251]	eta 0:31:14 lr 0.000984	time 1.8338 (2.2288)	loss 4.7152 (4.3671)	grad_norm 1.2235 (1.2274)	
[2022-01-18 06:40:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][420/1251]	eta 0:30:53 lr 0.000984	time 2.8713 (2.2301)	loss 4.3017 (4.3694)	grad_norm 1.0938 (1.2249)	
[2022-01-18 06:41:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][430/1251]	eta 0:30:31 lr 0.000984	time 2.1520 (2.2307)	loss 4.5135 (4.3616)	grad_norm 0.9225 (1.2243)	
[2022-01-18 06:41:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][440/1251]	eta 0:30:11 lr 0.000984	time 2.2419 (2.2335)	loss 4.6645 (4.3622)	grad_norm 1.3602 (1.2250)	
[2022-01-18 06:42:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][450/1251]	eta 0:29:49 lr 0.000984	time 1.8449 (2.2339)	loss 4.5438 (4.3614)	grad_norm 1.3970 (1.2236)	
[2022-01-18 06:42:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][460/1251]	eta 0:29:24 lr 0.000984	time 2.4330 (2.2308)	loss 5.3681 (4.3654)	grad_norm 1.1584 (1.2238)	
[2022-01-18 06:42:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][470/1251]	eta 0:28:57 lr 0.000984	time 1.8570 (2.2241)	loss 3.7502 (4.3644)	grad_norm 1.4626 (1.2252)	
[2022-01-18 06:43:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][480/1251]	eta 0:28:31 lr 0.000984	time 2.0494 (2.2205)	loss 5.1333 (4.3638)	grad_norm 1.0857 (1.2236)	
[2022-01-18 06:43:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][490/1251]	eta 0:28:09 lr 0.000984	time 2.3184 (2.2206)	loss 4.7876 (4.3565)	grad_norm 1.2852 (1.2228)	
[2022-01-18 06:43:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][500/1251]	eta 0:27:49 lr 0.000984	time 3.0656 (2.2232)	loss 3.2616 (4.3505)	grad_norm 1.1166 (1.2256)	
[2022-01-18 06:44:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][510/1251]	eta 0:27:27 lr 0.000984	time 1.5217 (2.2232)	loss 4.8198 (4.3448)	grad_norm 1.4135 (1.2243)	
[2022-01-18 06:44:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][520/1251]	eta 0:27:03 lr 0.000984	time 1.6430 (2.2211)	loss 4.4144 (4.3455)	grad_norm 1.1844 (1.2223)	
[2022-01-18 06:44:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][530/1251]	eta 0:26:40 lr 0.000984	time 2.4568 (2.2192)	loss 4.6103 (4.3466)	grad_norm 1.2109 (1.2216)	
[2022-01-18 06:45:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][540/1251]	eta 0:26:17 lr 0.000984	time 3.1643 (2.2190)	loss 3.7825 (4.3412)	grad_norm 1.1120 (1.2229)	
[2022-01-18 06:45:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][550/1251]	eta 0:25:56 lr 0.000984	time 1.8980 (2.2201)	loss 4.8046 (4.3359)	grad_norm 1.1221 (1.2223)	
[2022-01-18 06:46:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][560/1251]	eta 0:25:33 lr 0.000984	time 1.9195 (2.2189)	loss 4.5653 (4.3375)	grad_norm 1.1869 (1.2213)	
[2022-01-18 06:46:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][570/1251]	eta 0:25:10 lr 0.000984	time 2.3247 (2.2183)	loss 4.6288 (4.3394)	grad_norm 1.6368 (1.2228)	
[2022-01-18 06:46:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][580/1251]	eta 0:24:48 lr 0.000984	time 2.4277 (2.2177)	loss 3.2906 (4.3396)	grad_norm 1.1824 (1.2227)	
[2022-01-18 06:47:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][590/1251]	eta 0:24:25 lr 0.000984	time 1.7863 (2.2164)	loss 5.1554 (4.3402)	grad_norm 1.3316 (1.2217)	
[2022-01-18 06:47:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][600/1251]	eta 0:24:02 lr 0.000984	time 2.1223 (2.2155)	loss 4.0157 (4.3414)	grad_norm 1.0926 (1.2210)	
[2022-01-18 06:47:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][610/1251]	eta 0:23:41 lr 0.000984	time 2.1793 (2.2174)	loss 3.2805 (4.3401)	grad_norm 1.0052 (1.2204)	
[2022-01-18 06:48:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][620/1251]	eta 0:23:17 lr 0.000984	time 1.8816 (2.2145)	loss 3.5209 (4.3391)	grad_norm 1.6115 (1.2198)	
[2022-01-18 06:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][630/1251]	eta 0:22:54 lr 0.000984	time 2.4574 (2.2127)	loss 4.5190 (4.3426)	grad_norm 1.6144 (1.2209)	
[2022-01-18 06:48:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][640/1251]	eta 0:22:30 lr 0.000984	time 2.1917 (2.2105)	loss 4.7494 (4.3454)	grad_norm 1.2655 (1.2204)	
[2022-01-18 06:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][650/1251]	eta 0:22:07 lr 0.000984	time 1.8880 (2.2093)	loss 5.0939 (4.3431)	grad_norm 0.9280 (1.2199)	
[2022-01-18 06:49:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][660/1251]	eta 0:21:44 lr 0.000984	time 1.8640 (2.2077)	loss 3.8618 (4.3375)	grad_norm 1.2223 (1.2190)	
[2022-01-18 06:50:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][670/1251]	eta 0:21:23 lr 0.000984	time 2.8018 (2.2097)	loss 3.7140 (4.3347)	grad_norm 1.3852 (1.2206)	
[2022-01-18 06:50:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][680/1251]	eta 0:21:00 lr 0.000984	time 1.9200 (2.2071)	loss 3.6672 (4.3357)	grad_norm 1.3507 (1.2211)	
[2022-01-18 06:50:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][690/1251]	eta 0:20:39 lr 0.000984	time 2.5135 (2.2086)	loss 4.2403 (4.3353)	grad_norm 1.1753 (1.2206)	
[2022-01-18 06:51:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][700/1251]	eta 0:20:17 lr 0.000984	time 1.8520 (2.2096)	loss 4.7406 (4.3360)	grad_norm 1.4528 (1.2193)	
[2022-01-18 06:51:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][710/1251]	eta 0:19:57 lr 0.000984	time 3.3550 (2.2127)	loss 3.6565 (4.3374)	grad_norm 1.0734 (1.2195)	
[2022-01-18 06:51:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][720/1251]	eta 0:19:34 lr 0.000984	time 1.8549 (2.2124)	loss 4.6986 (4.3358)	grad_norm 1.0894 (1.2188)	
[2022-01-18 06:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][730/1251]	eta 0:19:13 lr 0.000984	time 2.9343 (2.2132)	loss 3.9840 (4.3388)	grad_norm 1.2066 (1.2199)	
[2022-01-18 06:52:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][740/1251]	eta 0:18:49 lr 0.000984	time 1.6147 (2.2101)	loss 3.4773 (4.3404)	grad_norm 1.2678 (1.2204)	
[2022-01-18 06:52:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][750/1251]	eta 0:18:26 lr 0.000984	time 2.7547 (2.2085)	loss 4.6747 (4.3453)	grad_norm 1.0860 (1.2220)	
[2022-01-18 06:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][760/1251]	eta 0:18:03 lr 0.000984	time 2.0555 (2.2069)	loss 4.6285 (4.3450)	grad_norm 1.0802 (1.2214)	
[2022-01-18 06:53:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][770/1251]	eta 0:17:42 lr 0.000984	time 3.7202 (2.2097)	loss 4.5816 (4.3477)	grad_norm 1.0053 (1.2197)	
[2022-01-18 06:54:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][780/1251]	eta 0:17:21 lr 0.000984	time 2.0620 (2.2103)	loss 3.7468 (4.3481)	grad_norm 1.2572 (1.2190)	
[2022-01-18 06:54:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][790/1251]	eta 0:16:59 lr 0.000984	time 2.7805 (2.2107)	loss 4.8624 (4.3540)	grad_norm 1.3125 (1.2192)	
[2022-01-18 06:54:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][800/1251]	eta 0:16:36 lr 0.000984	time 2.0142 (2.2093)	loss 4.4311 (4.3571)	grad_norm 1.1168 (1.2177)	
[2022-01-18 06:55:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][810/1251]	eta 0:16:13 lr 0.000984	time 2.6007 (2.2072)	loss 3.3247 (4.3585)	grad_norm 1.6412 (1.2169)	
[2022-01-18 06:55:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][820/1251]	eta 0:15:50 lr 0.000984	time 1.8652 (2.2050)	loss 3.8868 (4.3583)	grad_norm 1.0535 (1.2171)	
[2022-01-18 06:55:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][830/1251]	eta 0:15:28 lr 0.000984	time 2.2324 (2.2046)	loss 3.5296 (4.3580)	grad_norm 1.1562 (1.2170)	
[2022-01-18 06:56:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][840/1251]	eta 0:15:05 lr 0.000984	time 2.2979 (2.2029)	loss 4.7135 (4.3610)	grad_norm 1.4054 (1.2179)	
[2022-01-18 06:56:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][850/1251]	eta 0:14:43 lr 0.000984	time 2.3724 (2.2027)	loss 3.9634 (4.3632)	grad_norm 1.2234 (1.2183)	
[2022-01-18 06:56:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][860/1251]	eta 0:14:21 lr 0.000984	time 1.8745 (2.2025)	loss 4.1970 (4.3622)	grad_norm 1.0414 (1.2184)	
[2022-01-18 06:57:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][870/1251]	eta 0:13:58 lr 0.000984	time 1.7475 (2.2007)	loss 3.2846 (4.3609)	grad_norm 1.0376 (1.2169)	
[2022-01-18 06:57:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][880/1251]	eta 0:13:36 lr 0.000984	time 2.0595 (2.2002)	loss 4.5402 (4.3610)	grad_norm 1.3581 (1.2172)	
[2022-01-18 06:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][890/1251]	eta 0:13:14 lr 0.000984	time 2.4761 (2.1997)	loss 3.8562 (4.3625)	grad_norm 1.2310 (1.2170)	
[2022-01-18 06:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][900/1251]	eta 0:12:52 lr 0.000984	time 2.1851 (2.2005)	loss 3.5424 (4.3598)	grad_norm 1.3377 (1.2167)	
[2022-01-18 06:58:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][910/1251]	eta 0:12:30 lr 0.000983	time 1.8255 (2.2014)	loss 4.2056 (4.3633)	grad_norm 0.9400 (1.2162)	
[2022-01-18 06:59:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][920/1251]	eta 0:12:08 lr 0.000983	time 1.8548 (2.2007)	loss 3.4788 (4.3587)	grad_norm 1.1661 (1.2174)	
[2022-01-18 06:59:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][930/1251]	eta 0:11:46 lr 0.000983	time 2.8236 (2.2015)	loss 3.2979 (4.3553)	grad_norm 1.1401 (1.2173)	
[2022-01-18 06:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][940/1251]	eta 0:11:25 lr 0.000983	time 1.8087 (2.2035)	loss 5.1566 (4.3567)	grad_norm 1.3726 (1.2175)	
[2022-01-18 07:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][950/1251]	eta 0:11:03 lr 0.000983	time 1.8613 (2.2052)	loss 4.3259 (4.3552)	grad_norm 1.1019 (1.2173)	
[2022-01-18 07:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][960/1251]	eta 0:10:41 lr 0.000983	time 1.8862 (2.2055)	loss 4.1856 (4.3547)	grad_norm 1.0952 (1.2164)	
[2022-01-18 07:00:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][970/1251]	eta 0:10:19 lr 0.000983	time 2.2244 (2.2042)	loss 4.0825 (4.3533)	grad_norm 1.3350 (1.2169)	
[2022-01-18 07:01:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][980/1251]	eta 0:09:57 lr 0.000983	time 1.7453 (2.2031)	loss 3.2440 (4.3530)	grad_norm 1.2644 (1.2167)	
[2022-01-18 07:01:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][990/1251]	eta 0:09:34 lr 0.000983	time 1.9343 (2.2015)	loss 4.4060 (4.3534)	grad_norm 1.1325 (1.2163)	
[2022-01-18 07:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1000/1251]	eta 0:09:12 lr 0.000983	time 2.1637 (2.2009)	loss 5.1819 (4.3522)	grad_norm 1.0884 (1.2157)	
[2022-01-18 07:02:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1010/1251]	eta 0:08:50 lr 0.000983	time 2.5819 (2.2004)	loss 4.6862 (4.3522)	grad_norm 1.0743 (1.2152)	
[2022-01-18 07:02:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1020/1251]	eta 0:08:28 lr 0.000983	time 1.8545 (2.1996)	loss 4.6688 (4.3548)	grad_norm 1.2900 (1.2159)	
[2022-01-18 07:03:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1030/1251]	eta 0:08:06 lr 0.000983	time 1.9196 (2.1997)	loss 3.5327 (4.3562)	grad_norm 1.2911 (1.2153)	
[2022-01-18 07:03:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1040/1251]	eta 0:07:44 lr 0.000983	time 1.5788 (2.1993)	loss 4.1005 (4.3586)	grad_norm 1.2571 (1.2154)	
[2022-01-18 07:03:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1050/1251]	eta 0:07:22 lr 0.000983	time 1.9253 (2.1996)	loss 3.3615 (4.3583)	grad_norm 1.2755 (1.2154)	
[2022-01-18 07:04:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1060/1251]	eta 0:07:00 lr 0.000983	time 2.7768 (2.2003)	loss 3.8216 (4.3595)	grad_norm 1.2560 (1.2160)	
[2022-01-18 07:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1070/1251]	eta 0:06:38 lr 0.000983	time 1.7010 (2.2015)	loss 4.9271 (4.3609)	grad_norm 1.1388 (1.2157)	
[2022-01-18 07:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1080/1251]	eta 0:06:16 lr 0.000983	time 2.0945 (2.2013)	loss 4.7596 (4.3620)	grad_norm 1.3412 (1.2157)	
[2022-01-18 07:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1090/1251]	eta 0:05:54 lr 0.000983	time 1.9245 (2.2003)	loss 3.7006 (4.3615)	grad_norm 1.4504 (1.2169)	
[2022-01-18 07:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1100/1251]	eta 0:05:31 lr 0.000983	time 2.5156 (2.1982)	loss 4.6220 (4.3617)	grad_norm 1.3654 (1.2171)	
[2022-01-18 07:06:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1110/1251]	eta 0:05:09 lr 0.000983	time 2.5729 (2.1984)	loss 4.5375 (4.3636)	grad_norm 1.0544 (1.2169)	
[2022-01-18 07:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1120/1251]	eta 0:04:47 lr 0.000983	time 2.1210 (2.1984)	loss 4.6092 (4.3645)	grad_norm 1.1796 (1.2167)	
[2022-01-18 07:06:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1130/1251]	eta 0:04:26 lr 0.000983	time 1.8857 (2.1999)	loss 4.9133 (4.3652)	grad_norm 1.1724 (1.2165)	
[2022-01-18 07:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1140/1251]	eta 0:04:04 lr 0.000983	time 2.2104 (2.2010)	loss 4.5321 (4.3641)	grad_norm 1.2098 (1.2164)	
[2022-01-18 07:07:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1150/1251]	eta 0:03:42 lr 0.000983	time 2.7081 (2.2023)	loss 5.2532 (4.3645)	grad_norm 1.2952 (1.2163)	
[2022-01-18 07:07:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1160/1251]	eta 0:03:20 lr 0.000983	time 1.7807 (2.2011)	loss 4.1148 (4.3631)	grad_norm 1.1777 (1.2167)	
[2022-01-18 07:08:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1170/1251]	eta 0:02:58 lr 0.000983	time 1.6061 (2.1984)	loss 3.4640 (4.3607)	grad_norm 1.1697 (1.2162)	
[2022-01-18 07:08:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1180/1251]	eta 0:02:35 lr 0.000983	time 1.9566 (2.1970)	loss 4.4032 (4.3592)	grad_norm 1.2795 (1.2165)	
[2022-01-18 07:08:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1190/1251]	eta 0:02:14 lr 0.000983	time 1.8669 (2.1968)	loss 4.4654 (4.3587)	grad_norm 1.2632 (1.2158)	
[2022-01-18 07:09:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1200/1251]	eta 0:01:52 lr 0.000983	time 2.2019 (2.1965)	loss 4.2604 (4.3570)	grad_norm 1.3439 (1.2152)	
[2022-01-18 07:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1210/1251]	eta 0:01:30 lr 0.000983	time 1.8741 (2.1968)	loss 4.6995 (4.3577)	grad_norm 1.1112 (1.2148)	
[2022-01-18 07:10:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1220/1251]	eta 0:01:08 lr 0.000983	time 2.1592 (2.1983)	loss 4.2699 (4.3579)	grad_norm 1.3781 (1.2154)	
[2022-01-18 07:10:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1230/1251]	eta 0:00:46 lr 0.000983	time 2.1116 (2.2009)	loss 4.0255 (4.3584)	grad_norm 1.0322 (1.2146)	
[2022-01-18 07:10:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1240/1251]	eta 0:00:24 lr 0.000983	time 1.3782 (2.1997)	loss 4.6780 (4.3595)	grad_norm 1.3362 (1.2150)	
[2022-01-18 07:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [24/300][1250/1251]	eta 0:00:02 lr 0.000983	time 1.1901 (2.1943)	loss 3.6236 (4.3575)	grad_norm 1.6117 (1.2148)	
[2022-01-18 07:11:05 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 24 training takes 0:45:45
[2022-01-18 07:11:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.643 (18.643)	Loss 1.7029 (1.7029)	Acc@1 62.793 (62.793)	Acc@5 84.570 (84.570)	
[2022-01-18 07:11:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.214 (3.574)	Loss 1.7417 (1.6621)	Acc@1 60.938 (62.695)	Acc@5 83.398 (85.369)	
[2022-01-18 07:12:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.492 (2.714)	Loss 1.7036 (1.6555)	Acc@1 62.598 (62.821)	Acc@5 86.523 (85.575)	
[2022-01-18 07:12:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.269 (2.397)	Loss 1.7253 (1.6560)	Acc@1 60.547 (63.073)	Acc@5 85.352 (85.654)	
[2022-01-18 07:12:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.099 (2.211)	Loss 1.6768 (1.6557)	Acc@1 62.305 (63.048)	Acc@5 86.914 (85.706)	
[2022-01-18 07:12:43 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 63.136 Acc@5 85.740
[2022-01-18 07:12:43 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 63.1%
[2022-01-18 07:12:43 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 63.14%
[2022-01-18 07:13:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][0/1251]	eta 7:27:00 lr 0.000983	time 21.4389 (21.4389)	loss 5.1893 (5.1893)	grad_norm 1.3376 (1.3376)	
[2022-01-18 07:13:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][10/1251]	eta 1:24:42 lr 0.000983	time 1.5256 (4.0959)	loss 4.4762 (4.4706)	grad_norm 0.9195 (1.1187)	
[2022-01-18 07:13:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][20/1251]	eta 1:06:26 lr 0.000983	time 2.8257 (3.2381)	loss 4.5761 (4.3138)	grad_norm 1.0572 (1.1112)	
[2022-01-18 07:14:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][30/1251]	eta 0:58:35 lr 0.000983	time 1.3484 (2.8790)	loss 4.6676 (4.2203)	grad_norm 1.3222 (1.1895)	
[2022-01-18 07:14:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][40/1251]	eta 0:55:08 lr 0.000983	time 3.9126 (2.7324)	loss 4.2088 (4.2567)	grad_norm 1.1693 (1.2286)	
[2022-01-18 07:14:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][50/1251]	eta 0:52:42 lr 0.000983	time 1.7186 (2.6334)	loss 3.6456 (4.2161)	grad_norm 1.3486 (1.2305)	
[2022-01-18 07:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][60/1251]	eta 0:51:04 lr 0.000983	time 2.1476 (2.5729)	loss 5.0354 (4.3051)	grad_norm 1.2978 (1.2275)	
[2022-01-18 07:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][70/1251]	eta 0:49:25 lr 0.000983	time 1.6226 (2.5107)	loss 3.0978 (4.3038)	grad_norm 1.1531 (1.2245)	
[2022-01-18 07:16:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][80/1251]	eta 0:48:23 lr 0.000983	time 3.0147 (2.4796)	loss 3.2796 (4.2899)	grad_norm 1.3841 (1.2266)	
[2022-01-18 07:16:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][90/1251]	eta 0:47:15 lr 0.000983	time 1.7147 (2.4424)	loss 5.1058 (4.3219)	grad_norm 1.2957 (1.2396)	
[2022-01-18 07:16:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][100/1251]	eta 0:46:25 lr 0.000983	time 1.6602 (2.4199)	loss 4.9859 (4.3198)	grad_norm 1.0576 (1.2308)	
[2022-01-18 07:17:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][110/1251]	eta 0:45:35 lr 0.000983	time 2.0892 (2.3972)	loss 5.0741 (4.3175)	grad_norm 1.2915 (1.2271)	
[2022-01-18 07:17:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][120/1251]	eta 0:44:54 lr 0.000983	time 2.7646 (2.3826)	loss 3.7661 (4.3170)	grad_norm 1.6730 (1.2354)	
[2022-01-18 07:17:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][130/1251]	eta 0:44:13 lr 0.000983	time 1.8888 (2.3674)	loss 4.6486 (4.3126)	grad_norm 1.2146 (1.2343)	
[2022-01-18 07:18:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][140/1251]	eta 0:43:31 lr 0.000983	time 1.5775 (2.3504)	loss 4.5650 (4.3052)	grad_norm 1.1181 (1.2359)	
[2022-01-18 07:18:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][150/1251]	eta 0:42:54 lr 0.000983	time 2.5029 (2.3379)	loss 4.4783 (4.3275)	grad_norm 1.4455 (1.2439)	
[2022-01-18 07:19:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][160/1251]	eta 0:42:32 lr 0.000983	time 3.7303 (2.3391)	loss 4.8094 (4.3392)	grad_norm 0.9452 (1.2446)	
[2022-01-18 07:19:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][170/1251]	eta 0:41:56 lr 0.000983	time 1.6226 (2.3283)	loss 3.9695 (4.3315)	grad_norm 1.3054 (1.2397)	
[2022-01-18 07:19:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][180/1251]	eta 0:41:19 lr 0.000983	time 2.0567 (2.3155)	loss 4.4556 (4.3268)	grad_norm 1.1317 (1.2373)	
[2022-01-18 07:20:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][190/1251]	eta 0:40:33 lr 0.000983	time 1.6192 (2.2938)	loss 3.9344 (4.3290)	grad_norm 1.2046 (1.2306)	
[2022-01-18 07:20:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][200/1251]	eta 0:40:03 lr 0.000983	time 2.9208 (2.2867)	loss 4.7422 (4.3363)	grad_norm 1.0929 (1.2269)	
[2022-01-18 07:20:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][210/1251]	eta 0:39:31 lr 0.000983	time 1.5010 (2.2783)	loss 4.8084 (4.3361)	grad_norm 1.2482 (1.2230)	
[2022-01-18 07:21:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][220/1251]	eta 0:39:03 lr 0.000983	time 2.1829 (2.2729)	loss 4.0921 (4.3325)	grad_norm 1.3518 (1.2229)	
[2022-01-18 07:21:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][230/1251]	eta 0:38:40 lr 0.000983	time 2.0063 (2.2730)	loss 4.2161 (4.3327)	grad_norm 1.2186 (1.2245)	
[2022-01-18 07:21:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][240/1251]	eta 0:38:23 lr 0.000983	time 3.1810 (2.2780)	loss 4.6384 (4.3332)	grad_norm 1.0054 (1.2232)	
[2022-01-18 07:22:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][250/1251]	eta 0:38:00 lr 0.000983	time 2.2169 (2.2785)	loss 4.2753 (4.3350)	grad_norm 1.1519 (1.2235)	
[2022-01-18 07:22:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][260/1251]	eta 0:37:36 lr 0.000983	time 2.6469 (2.2765)	loss 4.6128 (4.3338)	grad_norm 0.9808 (1.2209)	
[2022-01-18 07:22:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][270/1251]	eta 0:37:08 lr 0.000983	time 1.6048 (2.2714)	loss 3.3320 (4.3170)	grad_norm 1.0851 (1.2209)	
[2022-01-18 07:23:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][280/1251]	eta 0:36:39 lr 0.000983	time 2.4691 (2.2652)	loss 4.6585 (4.3134)	grad_norm 1.1530 (1.2174)	
[2022-01-18 07:23:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][290/1251]	eta 0:36:06 lr 0.000983	time 1.8693 (2.2542)	loss 4.4573 (4.3100)	grad_norm 1.4298 (1.2199)	
[2022-01-18 07:24:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][300/1251]	eta 0:35:38 lr 0.000983	time 1.8735 (2.2490)	loss 4.8764 (4.3181)	grad_norm 0.9437 (1.2161)	
[2022-01-18 07:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][310/1251]	eta 0:35:14 lr 0.000983	time 2.0357 (2.2473)	loss 4.2086 (4.3229)	grad_norm 1.1149 (1.2170)	
[2022-01-18 07:24:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][320/1251]	eta 0:34:51 lr 0.000983	time 2.6041 (2.2464)	loss 3.5282 (4.3294)	grad_norm 1.1913 (1.2169)	
[2022-01-18 07:25:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][330/1251]	eta 0:34:27 lr 0.000983	time 1.8381 (2.2447)	loss 3.6851 (4.3249)	grad_norm 1.1628 (1.2177)	
[2022-01-18 07:25:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][340/1251]	eta 0:34:09 lr 0.000983	time 2.5502 (2.2496)	loss 4.7024 (4.3252)	grad_norm 1.2872 (1.2170)	
[2022-01-18 07:25:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][350/1251]	eta 0:33:47 lr 0.000983	time 1.6564 (2.2498)	loss 5.0788 (4.3224)	grad_norm 1.1522 (1.2141)	
[2022-01-18 07:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][360/1251]	eta 0:33:22 lr 0.000983	time 2.2685 (2.2471)	loss 4.3928 (4.3170)	grad_norm 1.3082 (1.2129)	
[2022-01-18 07:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][370/1251]	eta 0:32:53 lr 0.000983	time 2.1965 (2.2398)	loss 4.4453 (4.3172)	grad_norm 1.5854 (1.2152)	
[2022-01-18 07:26:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][380/1251]	eta 0:32:25 lr 0.000983	time 1.9681 (2.2332)	loss 4.7852 (4.3210)	grad_norm 1.4042 (1.2169)	
[2022-01-18 07:27:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][390/1251]	eta 0:32:00 lr 0.000983	time 2.2082 (2.2307)	loss 3.7817 (4.3188)	grad_norm 1.1635 (1.2163)	
[2022-01-18 07:27:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][400/1251]	eta 0:31:38 lr 0.000983	time 3.0427 (2.2314)	loss 5.0537 (4.3233)	grad_norm 1.1820 (1.2172)	
[2022-01-18 07:28:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][410/1251]	eta 0:31:16 lr 0.000983	time 2.4710 (2.2311)	loss 3.6097 (4.3250)	grad_norm 1.4294 (1.2182)	
[2022-01-18 07:28:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][420/1251]	eta 0:30:55 lr 0.000983	time 1.8799 (2.2325)	loss 4.2950 (4.3216)	grad_norm 1.2311 (1.2202)	
[2022-01-18 07:28:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][430/1251]	eta 0:30:32 lr 0.000983	time 2.6516 (2.2326)	loss 4.7279 (4.3266)	grad_norm 1.0680 (1.2193)	
[2022-01-18 07:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][440/1251]	eta 0:30:09 lr 0.000983	time 3.0613 (2.2316)	loss 4.9805 (4.3279)	grad_norm 1.3859 (1.2205)	
[2022-01-18 07:29:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][450/1251]	eta 0:29:45 lr 0.000983	time 1.5670 (2.2297)	loss 4.8159 (4.3297)	grad_norm 1.1517 (1.2231)	
[2022-01-18 07:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][460/1251]	eta 0:29:22 lr 0.000983	time 1.8764 (2.2279)	loss 4.1266 (4.3216)	grad_norm 1.2797 (1.2244)	
[2022-01-18 07:30:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][470/1251]	eta 0:29:00 lr 0.000983	time 2.4136 (2.2280)	loss 5.1203 (4.3224)	grad_norm 1.3921 (1.2253)	
[2022-01-18 07:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][480/1251]	eta 0:28:39 lr 0.000983	time 3.9299 (2.2308)	loss 3.8144 (4.3221)	grad_norm 1.1999 (1.2246)	
[2022-01-18 07:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][490/1251]	eta 0:28:18 lr 0.000983	time 1.6070 (2.2313)	loss 4.5787 (4.3264)	grad_norm 1.1027 (1.2234)	
[2022-01-18 07:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][500/1251]	eta 0:27:53 lr 0.000983	time 2.1220 (2.2280)	loss 4.6132 (4.3315)	grad_norm 1.0780 (1.2228)	
[2022-01-18 07:31:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][510/1251]	eta 0:27:27 lr 0.000983	time 1.9783 (2.2238)	loss 3.8734 (4.3327)	grad_norm 1.2007 (1.2212)	
[2022-01-18 07:32:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][520/1251]	eta 0:27:03 lr 0.000983	time 2.8069 (2.2212)	loss 4.4047 (4.3379)	grad_norm 1.1900 (1.2198)	
[2022-01-18 07:32:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][530/1251]	eta 0:26:40 lr 0.000983	time 1.8536 (2.2194)	loss 4.3020 (4.3367)	grad_norm 1.3017 (1.2193)	
[2022-01-18 07:32:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][540/1251]	eta 0:26:18 lr 0.000983	time 3.1035 (2.2203)	loss 4.5163 (4.3360)	grad_norm 0.9303 (1.2212)	
[2022-01-18 07:33:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][550/1251]	eta 0:25:56 lr 0.000983	time 2.0916 (2.2198)	loss 3.7105 (4.3323)	grad_norm 1.0744 (1.2200)	
[2022-01-18 07:33:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][560/1251]	eta 0:25:34 lr 0.000983	time 2.4618 (2.2205)	loss 3.3951 (4.3334)	grad_norm 1.1958 (1.2187)	
[2022-01-18 07:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][570/1251]	eta 0:25:14 lr 0.000983	time 1.8109 (2.2241)	loss 3.9361 (4.3326)	grad_norm 1.7807 (1.2190)	
[2022-01-18 07:34:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][580/1251]	eta 0:24:55 lr 0.000983	time 3.5879 (2.2282)	loss 3.2290 (4.3263)	grad_norm 1.4370 (1.2178)	
[2022-01-18 07:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][590/1251]	eta 0:24:32 lr 0.000982	time 2.1517 (2.2284)	loss 4.7340 (4.3288)	grad_norm 1.0334 (1.2186)	
[2022-01-18 07:35:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][600/1251]	eta 0:24:09 lr 0.000982	time 1.8429 (2.2264)	loss 4.5340 (4.3287)	grad_norm 1.1273 (1.2182)	
[2022-01-18 07:35:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][610/1251]	eta 0:23:44 lr 0.000982	time 2.0363 (2.2225)	loss 4.0042 (4.3245)	grad_norm 1.1384 (1.2180)	
[2022-01-18 07:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][620/1251]	eta 0:23:19 lr 0.000982	time 2.2682 (2.2175)	loss 3.3477 (4.3209)	grad_norm 1.1177 (1.2182)	
[2022-01-18 07:36:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][630/1251]	eta 0:22:55 lr 0.000982	time 2.2464 (2.2149)	loss 4.3598 (4.3211)	grad_norm 1.2764 (1.2168)	
[2022-01-18 07:36:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][640/1251]	eta 0:22:32 lr 0.000982	time 2.1061 (2.2130)	loss 4.4260 (4.3225)	grad_norm 1.2091 (1.2174)	
[2022-01-18 07:36:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][650/1251]	eta 0:22:10 lr 0.000982	time 2.0020 (2.2141)	loss 4.4489 (4.3258)	grad_norm 1.1745 (1.2165)	
[2022-01-18 07:37:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][660/1251]	eta 0:21:49 lr 0.000982	time 2.1677 (2.2153)	loss 3.9457 (4.3263)	grad_norm 1.1564 (1.2157)	
[2022-01-18 07:37:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][670/1251]	eta 0:21:27 lr 0.000982	time 2.1161 (2.2156)	loss 3.9026 (4.3284)	grad_norm 0.9327 (1.2149)	
[2022-01-18 07:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][680/1251]	eta 0:21:06 lr 0.000982	time 2.5228 (2.2183)	loss 3.7408 (4.3291)	grad_norm 1.3051 (1.2155)	
[2022-01-18 07:38:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][690/1251]	eta 0:20:45 lr 0.000982	time 2.3287 (2.2202)	loss 3.4659 (4.3265)	grad_norm 1.2292 (1.2153)	
[2022-01-18 07:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][700/1251]	eta 0:20:24 lr 0.000982	time 2.4522 (2.2223)	loss 3.3169 (4.3247)	grad_norm 1.5643 (1.2149)	
[2022-01-18 07:39:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][710/1251]	eta 0:20:01 lr 0.000982	time 1.8844 (2.2216)	loss 4.7840 (4.3198)	grad_norm 1.1017 (1.2144)	
[2022-01-18 07:39:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][720/1251]	eta 0:19:37 lr 0.000982	time 1.6103 (2.2174)	loss 4.4155 (4.3196)	grad_norm 1.2669 (1.2139)	
[2022-01-18 07:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][730/1251]	eta 0:19:12 lr 0.000982	time 1.5633 (2.2127)	loss 3.7162 (4.3196)	grad_norm 1.2821 (1.2151)	
[2022-01-18 07:40:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][740/1251]	eta 0:18:49 lr 0.000982	time 2.4990 (2.2104)	loss 4.5712 (4.3172)	grad_norm 0.8729 (1.2136)	
[2022-01-18 07:40:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][750/1251]	eta 0:18:26 lr 0.000982	time 1.6815 (2.2081)	loss 3.5129 (4.3172)	grad_norm 1.1695 (1.2124)	
[2022-01-18 07:40:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][760/1251]	eta 0:18:03 lr 0.000982	time 1.9090 (2.2073)	loss 3.4701 (4.3160)	grad_norm 1.5955 (1.2117)	
[2022-01-18 07:41:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][770/1251]	eta 0:17:42 lr 0.000982	time 2.1557 (2.2081)	loss 4.8406 (4.3156)	grad_norm 1.3011 (1.2125)	
[2022-01-18 07:41:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][780/1251]	eta 0:17:20 lr 0.000982	time 2.0058 (2.2084)	loss 3.9581 (4.3136)	grad_norm 1.3134 (1.2137)	
[2022-01-18 07:41:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][790/1251]	eta 0:16:58 lr 0.000982	time 2.4945 (2.2096)	loss 4.7141 (4.3148)	grad_norm 1.3187 (1.2147)	
[2022-01-18 07:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][800/1251]	eta 0:16:36 lr 0.000982	time 2.5077 (2.2090)	loss 4.5759 (4.3156)	grad_norm 1.0240 (1.2147)	
[2022-01-18 07:42:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][810/1251]	eta 0:16:15 lr 0.000982	time 2.9746 (2.2111)	loss 4.9115 (4.3168)	grad_norm 1.3809 (1.2148)	
[2022-01-18 07:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][820/1251]	eta 0:15:52 lr 0.000982	time 1.9597 (2.2095)	loss 4.1146 (4.3163)	grad_norm 1.3485 (1.2150)	
[2022-01-18 07:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][830/1251]	eta 0:15:30 lr 0.000982	time 1.8986 (2.2100)	loss 4.9987 (4.3185)	grad_norm 1.1946 (1.2146)	
[2022-01-18 07:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][840/1251]	eta 0:15:08 lr 0.000982	time 2.9438 (2.2104)	loss 4.9643 (4.3185)	grad_norm 0.9803 (1.2144)	
[2022-01-18 07:44:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][850/1251]	eta 0:14:46 lr 0.000982	time 1.7904 (2.2096)	loss 3.5810 (4.3209)	grad_norm 1.5144 (1.2143)	
[2022-01-18 07:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][860/1251]	eta 0:14:23 lr 0.000982	time 1.8517 (2.2083)	loss 3.9755 (4.3200)	grad_norm 1.2748 (1.2138)	
[2022-01-18 07:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][870/1251]	eta 0:14:02 lr 0.000982	time 2.7715 (2.2115)	loss 4.4016 (4.3212)	grad_norm 1.4447 (1.2145)	
[2022-01-18 07:45:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][880/1251]	eta 0:13:41 lr 0.000982	time 3.3109 (2.2136)	loss 4.7279 (4.3243)	grad_norm 1.2551 (1.2146)	
[2022-01-18 07:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][890/1251]	eta 0:13:19 lr 0.000982	time 1.8176 (2.2140)	loss 4.4922 (4.3256)	grad_norm 1.0743 (1.2151)	
[2022-01-18 07:45:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][900/1251]	eta 0:12:56 lr 0.000982	time 1.6960 (2.2116)	loss 4.3924 (4.3271)	grad_norm 1.0070 (1.2146)	
[2022-01-18 07:46:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][910/1251]	eta 0:12:33 lr 0.000982	time 2.1886 (2.2089)	loss 5.0666 (4.3281)	grad_norm 1.4035 (1.2145)	
[2022-01-18 07:46:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][920/1251]	eta 0:12:10 lr 0.000982	time 1.9930 (2.2072)	loss 4.2785 (4.3297)	grad_norm 1.3629 (1.2148)	
[2022-01-18 07:46:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][930/1251]	eta 0:11:48 lr 0.000982	time 1.9485 (2.2082)	loss 4.4278 (4.3296)	grad_norm 1.1176 (1.2148)	
[2022-01-18 07:47:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][940/1251]	eta 0:11:27 lr 0.000982	time 2.1608 (2.2095)	loss 4.2661 (4.3313)	grad_norm 1.1564 (1.2152)	
[2022-01-18 07:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][950/1251]	eta 0:11:05 lr 0.000982	time 2.8280 (2.2106)	loss 3.9905 (4.3306)	grad_norm 1.0082 (1.2140)	
[2022-01-18 07:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][960/1251]	eta 0:10:43 lr 0.000982	time 1.9995 (2.2099)	loss 5.0988 (4.3274)	grad_norm 1.1021 (1.2128)	
[2022-01-18 07:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][970/1251]	eta 0:10:20 lr 0.000982	time 2.0160 (2.2086)	loss 4.4019 (4.3294)	grad_norm 1.2908 (1.2120)	
[2022-01-18 07:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][980/1251]	eta 0:09:58 lr 0.000982	time 2.2975 (2.2082)	loss 4.4625 (4.3288)	grad_norm 1.0342 (1.2107)	
[2022-01-18 07:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][990/1251]	eta 0:09:36 lr 0.000982	time 2.5096 (2.2083)	loss 5.0939 (4.3294)	grad_norm 1.7452 (1.2112)	
[2022-01-18 07:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1000/1251]	eta 0:09:13 lr 0.000982	time 1.6251 (2.2068)	loss 3.7742 (4.3285)	grad_norm 0.9561 (1.2103)	
[2022-01-18 07:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1010/1251]	eta 0:08:51 lr 0.000982	time 2.2498 (2.2069)	loss 3.0827 (4.3288)	grad_norm 1.2834 (1.2097)	
[2022-01-18 07:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1020/1251]	eta 0:08:29 lr 0.000982	time 2.2103 (2.2066)	loss 4.5122 (4.3276)	grad_norm 1.2746 (1.2096)	
[2022-01-18 07:50:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1030/1251]	eta 0:08:07 lr 0.000982	time 1.6637 (2.2070)	loss 4.9039 (4.3291)	grad_norm 1.2969 (1.2084)	
[2022-01-18 07:51:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1040/1251]	eta 0:07:45 lr 0.000982	time 2.1763 (2.2059)	loss 4.8855 (4.3310)	grad_norm 1.1373 (1.2083)	
[2022-01-18 07:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1050/1251]	eta 0:07:23 lr 0.000982	time 2.1199 (2.2063)	loss 3.4750 (4.3323)	grad_norm 1.2945 (1.2074)	
[2022-01-18 07:51:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1060/1251]	eta 0:07:01 lr 0.000982	time 2.4902 (2.2071)	loss 4.7607 (4.3354)	grad_norm 1.0207 (1.2067)	
[2022-01-18 07:52:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1070/1251]	eta 0:06:39 lr 0.000982	time 1.9066 (2.2084)	loss 3.4468 (4.3368)	grad_norm 1.0065 (1.2078)	
[2022-01-18 07:52:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1080/1251]	eta 0:06:17 lr 0.000982	time 1.6902 (2.2067)	loss 3.4207 (4.3369)	grad_norm 1.7157 (1.2084)	
[2022-01-18 07:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1090/1251]	eta 0:05:55 lr 0.000982	time 2.2324 (2.2055)	loss 3.7104 (4.3356)	grad_norm 1.8304 (1.2087)	
[2022-01-18 07:53:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1100/1251]	eta 0:05:32 lr 0.000982	time 1.8138 (2.2028)	loss 3.6840 (4.3343)	grad_norm 1.0785 (1.2088)	
[2022-01-18 07:53:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1110/1251]	eta 0:05:10 lr 0.000982	time 2.0857 (2.2012)	loss 4.1529 (4.3345)	grad_norm 1.2506 (1.2080)	
[2022-01-18 07:53:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1120/1251]	eta 0:04:48 lr 0.000982	time 1.9103 (2.2003)	loss 4.0962 (4.3339)	grad_norm 1.0257 (1.2073)	
[2022-01-18 07:54:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1130/1251]	eta 0:04:26 lr 0.000982	time 2.2426 (2.1997)	loss 5.0033 (4.3353)	grad_norm 1.2452 (1.2077)	
[2022-01-18 07:54:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1140/1251]	eta 0:04:04 lr 0.000982	time 2.2512 (2.1994)	loss 4.3035 (4.3336)	grad_norm 1.6186 (1.2070)	
[2022-01-18 07:54:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1150/1251]	eta 0:03:42 lr 0.000982	time 2.0235 (2.1997)	loss 3.7999 (4.3345)	grad_norm 1.0080 (1.2064)	
[2022-01-18 07:55:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1160/1251]	eta 0:03:20 lr 0.000982	time 1.6102 (2.1989)	loss 4.1263 (4.3333)	grad_norm 1.2252 (1.2064)	
[2022-01-18 07:55:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1170/1251]	eta 0:02:58 lr 0.000982	time 3.2356 (2.2007)	loss 4.6921 (4.3365)	grad_norm 1.0005 (1.2068)	
[2022-01-18 07:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1180/1251]	eta 0:02:36 lr 0.000982	time 2.1065 (2.2033)	loss 3.4305 (4.3330)	grad_norm 1.3440 (1.2075)	
[2022-01-18 07:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1190/1251]	eta 0:02:14 lr 0.000982	time 2.1445 (2.2047)	loss 3.2020 (4.3333)	grad_norm 1.1898 (1.2078)	
[2022-01-18 07:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1200/1251]	eta 0:01:52 lr 0.000982	time 2.2002 (2.2045)	loss 4.9723 (4.3337)	grad_norm 0.9407 (1.2069)	
[2022-01-18 07:57:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1210/1251]	eta 0:01:30 lr 0.000982	time 2.4427 (2.2047)	loss 4.6741 (4.3313)	grad_norm 1.1462 (1.2067)	
[2022-01-18 07:57:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1220/1251]	eta 0:01:08 lr 0.000982	time 1.6864 (2.2032)	loss 4.2395 (4.3304)	grad_norm 1.3165 (1.2065)	
[2022-01-18 07:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1230/1251]	eta 0:00:46 lr 0.000982	time 1.8435 (2.2017)	loss 4.3490 (4.3302)	grad_norm 0.9379 (1.2065)	
[2022-01-18 07:58:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1240/1251]	eta 0:00:24 lr 0.000982	time 2.1039 (2.2021)	loss 4.0753 (4.3282)	grad_norm 1.0527 (1.2056)	
[2022-01-18 07:58:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [25/300][1250/1251]	eta 0:00:02 lr 0.000982	time 1.1915 (2.1969)	loss 4.6941 (4.3285)	grad_norm 1.1391 (1.2047)	
[2022-01-18 07:58:32 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 25 training takes 0:45:48
[2022-01-18 07:58:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.118 (18.118)	Loss 1.6671 (1.6671)	Acc@1 62.207 (62.207)	Acc@5 84.473 (84.473)	
[2022-01-18 07:59:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.226 (3.322)	Loss 1.5306 (1.6370)	Acc@1 64.062 (63.175)	Acc@5 87.598 (85.609)	
[2022-01-18 07:59:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 2.025 (2.584)	Loss 1.5226 (1.6191)	Acc@1 65.723 (63.709)	Acc@5 86.230 (85.826)	
[2022-01-18 07:59:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.898 (2.314)	Loss 1.6365 (1.6240)	Acc@1 62.793 (63.477)	Acc@5 85.156 (85.774)	
[2022-01-18 08:00:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.613 (2.149)	Loss 1.6634 (1.6244)	Acc@1 62.402 (63.353)	Acc@5 85.840 (85.783)	
[2022-01-18 08:00:07 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 63.484 Acc@5 85.894
[2022-01-18 08:00:07 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 63.5%
[2022-01-18 08:00:07 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 63.48%
[2022-01-18 08:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][0/1251]	eta 7:34:01 lr 0.000982	time 21.7760 (21.7760)	loss 4.2873 (4.2873)	grad_norm 1.1431 (1.1431)	
[2022-01-18 08:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][10/1251]	eta 1:22:04 lr 0.000982	time 1.4653 (3.9678)	loss 3.7084 (4.0993)	grad_norm 0.9691 (1.1234)	
[2022-01-18 08:01:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][20/1251]	eta 1:02:53 lr 0.000982	time 1.4300 (3.0654)	loss 4.0452 (4.1590)	grad_norm 1.2984 (1.1622)	
[2022-01-18 08:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][30/1251]	eta 0:56:40 lr 0.000982	time 1.2438 (2.7854)	loss 4.6503 (4.1340)	grad_norm 1.1563 (1.1799)	
[2022-01-18 08:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][40/1251]	eta 0:54:51 lr 0.000982	time 5.3755 (2.7181)	loss 4.9975 (4.2497)	grad_norm 1.1433 (1.1928)	
[2022-01-18 08:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][50/1251]	eta 0:52:00 lr 0.000982	time 1.3280 (2.5987)	loss 4.9397 (4.2705)	grad_norm 1.0978 (1.1737)	
[2022-01-18 08:02:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][60/1251]	eta 0:49:49 lr 0.000982	time 1.8967 (2.5098)	loss 4.4375 (4.2807)	grad_norm 1.1875 (1.1756)	
[2022-01-18 08:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][70/1251]	eta 0:48:48 lr 0.000982	time 1.4328 (2.4800)	loss 5.2077 (4.2793)	grad_norm 1.2218 (1.2160)	
[2022-01-18 08:03:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][80/1251]	eta 0:48:22 lr 0.000982	time 4.2698 (2.4786)	loss 4.3524 (4.2749)	grad_norm 1.4066 (1.2116)	
[2022-01-18 08:03:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][90/1251]	eta 0:47:17 lr 0.000982	time 1.4590 (2.4436)	loss 3.7651 (4.2693)	grad_norm 1.3781 (1.2110)	
[2022-01-18 08:04:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][100/1251]	eta 0:46:14 lr 0.000982	time 1.7240 (2.4106)	loss 4.9652 (4.2569)	grad_norm 1.2440 (1.2166)	
[2022-01-18 08:04:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][110/1251]	eta 0:45:20 lr 0.000982	time 1.9744 (2.3847)	loss 4.6212 (4.2601)	grad_norm 1.0621 (1.2024)	
[2022-01-18 08:04:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][120/1251]	eta 0:44:52 lr 0.000982	time 3.5148 (2.3803)	loss 3.6042 (4.2743)	grad_norm 1.4700 (1.2043)	
[2022-01-18 08:05:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][130/1251]	eta 0:44:14 lr 0.000982	time 1.5415 (2.3682)	loss 4.4810 (4.2705)	grad_norm 1.2696 (1.2047)	
[2022-01-18 08:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][140/1251]	eta 0:43:23 lr 0.000982	time 2.2083 (2.3432)	loss 3.8490 (4.2698)	grad_norm 1.2862 (1.1985)	
[2022-01-18 08:05:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][150/1251]	eta 0:42:45 lr 0.000982	time 1.9189 (2.3301)	loss 3.1682 (4.2770)	grad_norm 0.9745 (1.1973)	
[2022-01-18 08:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][160/1251]	eta 0:42:03 lr 0.000982	time 2.0329 (2.3129)	loss 3.5584 (4.2838)	grad_norm 1.1248 (1.1968)	
[2022-01-18 08:06:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][170/1251]	eta 0:41:40 lr 0.000982	time 2.5393 (2.3131)	loss 4.5141 (4.2762)	grad_norm 1.1450 (1.1939)	
[2022-01-18 08:07:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][180/1251]	eta 0:41:10 lr 0.000982	time 2.1037 (2.3067)	loss 4.7122 (4.2593)	grad_norm 1.7814 (1.1998)	
[2022-01-18 08:07:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][190/1251]	eta 0:40:43 lr 0.000982	time 1.7961 (2.3030)	loss 4.5382 (4.2737)	grad_norm 1.1516 (1.2019)	
[2022-01-18 08:07:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][200/1251]	eta 0:40:14 lr 0.000982	time 2.4925 (2.2971)	loss 4.6933 (4.2812)	grad_norm 1.0633 (1.1967)	
[2022-01-18 08:08:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][210/1251]	eta 0:39:47 lr 0.000982	time 2.4979 (2.2931)	loss 4.2965 (4.2927)	grad_norm 1.0751 (1.1941)	
[2022-01-18 08:08:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][220/1251]	eta 0:39:11 lr 0.000982	time 2.1983 (2.2803)	loss 4.2025 (4.2861)	grad_norm 1.1974 (1.1987)	
[2022-01-18 08:08:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][230/1251]	eta 0:38:43 lr 0.000982	time 2.0379 (2.2757)	loss 4.5284 (4.2808)	grad_norm 1.5863 (1.2033)	
[2022-01-18 08:09:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][240/1251]	eta 0:38:15 lr 0.000981	time 2.6381 (2.2707)	loss 4.5869 (4.2819)	grad_norm 1.0937 (1.2080)	
[2022-01-18 08:09:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][250/1251]	eta 0:37:47 lr 0.000981	time 1.9033 (2.2649)	loss 4.4634 (4.2902)	grad_norm 0.9539 (1.2084)	
[2022-01-18 08:09:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][260/1251]	eta 0:37:14 lr 0.000981	time 2.1059 (2.2548)	loss 4.7405 (4.2928)	grad_norm 1.0636 (1.2109)	
[2022-01-18 08:10:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][270/1251]	eta 0:36:47 lr 0.000981	time 1.9304 (2.2505)	loss 4.4715 (4.2954)	grad_norm 1.0704 (1.2075)	
[2022-01-18 08:10:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][280/1251]	eta 0:36:23 lr 0.000981	time 2.7695 (2.2483)	loss 4.4222 (4.2867)	grad_norm 1.2074 (1.2064)	
[2022-01-18 08:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][290/1251]	eta 0:35:59 lr 0.000981	time 2.2199 (2.2472)	loss 4.5428 (4.2953)	grad_norm 1.1419 (1.2064)	
[2022-01-18 08:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][300/1251]	eta 0:35:34 lr 0.000981	time 2.1467 (2.2448)	loss 5.1282 (4.3031)	grad_norm 1.1435 (1.2062)	
[2022-01-18 08:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][310/1251]	eta 0:35:11 lr 0.000981	time 1.6768 (2.2439)	loss 4.8884 (4.3063)	grad_norm 1.1026 (1.2057)	
[2022-01-18 08:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][320/1251]	eta 0:34:49 lr 0.000981	time 2.4693 (2.2447)	loss 4.7441 (4.3062)	grad_norm 1.1420 (1.2038)	
[2022-01-18 08:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][330/1251]	eta 0:34:27 lr 0.000981	time 2.2793 (2.2443)	loss 5.0782 (4.3198)	grad_norm 1.1254 (1.2051)	
[2022-01-18 08:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][340/1251]	eta 0:34:03 lr 0.000981	time 2.2188 (2.2433)	loss 3.6487 (4.3231)	grad_norm 1.4043 (1.2061)	
[2022-01-18 08:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][350/1251]	eta 0:33:41 lr 0.000981	time 2.1418 (2.2436)	loss 3.3212 (4.3149)	grad_norm 1.1902 (1.2033)	
[2022-01-18 08:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][360/1251]	eta 0:33:17 lr 0.000981	time 2.8607 (2.2413)	loss 4.2399 (4.3092)	grad_norm 1.4591 (1.2040)	
[2022-01-18 08:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][370/1251]	eta 0:32:53 lr 0.000981	time 2.1665 (2.2405)	loss 4.2119 (4.3018)	grad_norm 1.3265 (1.2037)	
[2022-01-18 08:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][380/1251]	eta 0:32:26 lr 0.000981	time 2.2641 (2.2347)	loss 3.4913 (4.2987)	grad_norm 1.1949 (1.2061)	
[2022-01-18 08:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][390/1251]	eta 0:32:01 lr 0.000981	time 1.8964 (2.2314)	loss 3.5610 (4.3006)	grad_norm 1.4113 (1.2095)	
[2022-01-18 08:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][400/1251]	eta 0:31:40 lr 0.000981	time 2.4355 (2.2327)	loss 4.4033 (4.2964)	grad_norm 1.2146 (1.2096)	
[2022-01-18 08:15:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][410/1251]	eta 0:31:17 lr 0.000981	time 1.7445 (2.2320)	loss 5.0514 (4.2984)	grad_norm 1.0457 (1.2091)	
[2022-01-18 08:15:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][420/1251]	eta 0:30:55 lr 0.000981	time 2.3253 (2.2332)	loss 4.7951 (4.3004)	grad_norm 1.2579 (1.2067)	
[2022-01-18 08:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][430/1251]	eta 0:30:30 lr 0.000981	time 2.1433 (2.2290)	loss 4.6821 (4.2980)	grad_norm 1.4630 (1.2091)	
[2022-01-18 08:16:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][440/1251]	eta 0:30:08 lr 0.000981	time 2.7249 (2.2302)	loss 4.7284 (4.2948)	grad_norm 1.2697 (1.2087)	
[2022-01-18 08:16:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][450/1251]	eta 0:29:44 lr 0.000981	time 1.7671 (2.2284)	loss 4.1935 (4.2948)	grad_norm 1.0366 (1.2095)	
[2022-01-18 08:17:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][460/1251]	eta 0:29:20 lr 0.000981	time 1.6080 (2.2254)	loss 4.5418 (4.2846)	grad_norm 1.0386 (1.2082)	
[2022-01-18 08:17:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][470/1251]	eta 0:28:55 lr 0.000981	time 1.8375 (2.2225)	loss 4.4733 (4.2841)	grad_norm 1.1262 (1.2063)	
[2022-01-18 08:17:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][480/1251]	eta 0:28:31 lr 0.000981	time 2.3371 (2.2200)	loss 4.5807 (4.2847)	grad_norm 1.2901 (1.2033)	
[2022-01-18 08:18:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][490/1251]	eta 0:28:08 lr 0.000981	time 1.9408 (2.2190)	loss 4.5557 (4.2835)	grad_norm 1.1164 (1.2023)	
[2022-01-18 08:18:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][500/1251]	eta 0:27:44 lr 0.000981	time 1.9478 (2.2167)	loss 4.5796 (4.2909)	grad_norm 1.3129 (1.2044)	
[2022-01-18 08:19:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][510/1251]	eta 0:27:24 lr 0.000981	time 3.3198 (2.2193)	loss 4.6274 (4.2903)	grad_norm 1.3642 (1.2036)	
[2022-01-18 08:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][520/1251]	eta 0:27:01 lr 0.000981	time 2.1722 (2.2175)	loss 4.5087 (4.2942)	grad_norm 1.1002 (1.2017)	
[2022-01-18 08:19:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][530/1251]	eta 0:26:39 lr 0.000981	time 1.9054 (2.2187)	loss 4.9992 (4.2977)	grad_norm 1.3262 (1.2007)	
[2022-01-18 08:20:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][540/1251]	eta 0:26:16 lr 0.000981	time 1.7731 (2.2168)	loss 4.2752 (4.2988)	grad_norm 1.0957 (1.2010)	
[2022-01-18 08:20:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][550/1251]	eta 0:25:55 lr 0.000981	time 2.1906 (2.2195)	loss 4.5387 (4.2961)	grad_norm 1.0688 (1.2018)	
[2022-01-18 08:20:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][560/1251]	eta 0:25:33 lr 0.000981	time 2.1299 (2.2198)	loss 4.4799 (4.2982)	grad_norm 1.1799 (1.2008)	
[2022-01-18 08:21:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][570/1251]	eta 0:25:12 lr 0.000981	time 2.1912 (2.2206)	loss 3.5646 (4.2967)	grad_norm 1.1447 (1.2000)	
[2022-01-18 08:21:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][580/1251]	eta 0:24:48 lr 0.000981	time 2.0333 (2.2179)	loss 4.8164 (4.2964)	grad_norm 1.1369 (1.1996)	
[2022-01-18 08:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][590/1251]	eta 0:24:25 lr 0.000981	time 2.0192 (2.2170)	loss 4.1084 (4.3010)	grad_norm 1.2847 (1.1984)	
[2022-01-18 08:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][600/1251]	eta 0:23:59 lr 0.000981	time 1.9316 (2.2108)	loss 4.7263 (4.3030)	grad_norm 1.0485 (1.1969)	
[2022-01-18 08:22:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][610/1251]	eta 0:23:35 lr 0.000981	time 1.9603 (2.2077)	loss 3.8644 (4.3032)	grad_norm 1.1680 (1.1975)	
[2022-01-18 08:22:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][620/1251]	eta 0:23:11 lr 0.000981	time 1.9194 (2.2058)	loss 3.1862 (4.2953)	grad_norm 1.1979 (1.1971)	
[2022-01-18 08:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][630/1251]	eta 0:22:49 lr 0.000981	time 2.1021 (2.2059)	loss 4.4459 (4.2941)	grad_norm 1.2150 (1.1959)	
[2022-01-18 08:23:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][640/1251]	eta 0:22:29 lr 0.000981	time 2.6538 (2.2093)	loss 3.9118 (4.2950)	grad_norm 1.3945 (1.1947)	
[2022-01-18 08:24:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][650/1251]	eta 0:22:08 lr 0.000981	time 1.7906 (2.2111)	loss 4.6072 (4.2928)	grad_norm 1.0045 (1.1932)	
[2022-01-18 08:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][660/1251]	eta 0:21:48 lr 0.000981	time 2.2028 (2.2134)	loss 4.7598 (4.2928)	grad_norm 1.3429 (1.1931)	
[2022-01-18 08:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][670/1251]	eta 0:21:26 lr 0.000981	time 2.1471 (2.2141)	loss 4.5060 (4.2937)	grad_norm 0.9801 (1.1928)	
[2022-01-18 08:25:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][680/1251]	eta 0:21:04 lr 0.000981	time 1.8437 (2.2144)	loss 4.1272 (4.2953)	grad_norm 1.1245 (1.1924)	
[2022-01-18 08:25:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][690/1251]	eta 0:20:41 lr 0.000981	time 1.8868 (2.2130)	loss 4.7376 (4.2923)	grad_norm 1.1948 (1.1917)	
[2022-01-18 08:25:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][700/1251]	eta 0:20:18 lr 0.000981	time 2.4029 (2.2109)	loss 4.9872 (4.2902)	grad_norm 1.3074 (1.1922)	
[2022-01-18 08:26:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][710/1251]	eta 0:19:55 lr 0.000981	time 2.3177 (2.2090)	loss 4.6451 (4.2908)	grad_norm 1.1681 (1.1918)	
[2022-01-18 08:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][720/1251]	eta 0:19:32 lr 0.000981	time 1.8029 (2.2085)	loss 4.8492 (4.2948)	grad_norm 1.4260 (1.1909)	
[2022-01-18 08:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][730/1251]	eta 0:19:10 lr 0.000981	time 1.8353 (2.2087)	loss 4.2466 (4.2907)	grad_norm 1.1759 (1.1910)	
[2022-01-18 08:27:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][740/1251]	eta 0:18:49 lr 0.000981	time 2.7141 (2.2099)	loss 4.8576 (4.2938)	grad_norm 1.0445 (1.1929)	
[2022-01-18 08:27:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][750/1251]	eta 0:18:27 lr 0.000981	time 1.9007 (2.2115)	loss 3.4561 (4.2947)	grad_norm 1.1383 (1.1936)	
[2022-01-18 08:28:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][760/1251]	eta 0:18:05 lr 0.000981	time 1.5668 (2.2114)	loss 4.0556 (4.2970)	grad_norm 1.0232 (1.1928)	
[2022-01-18 08:28:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][770/1251]	eta 0:17:42 lr 0.000981	time 1.8902 (2.2091)	loss 3.4937 (4.2975)	grad_norm 1.4062 (1.1928)	
[2022-01-18 08:28:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][780/1251]	eta 0:17:19 lr 0.000981	time 2.5312 (2.2074)	loss 4.9375 (4.2987)	grad_norm 1.1870 (1.1948)	
[2022-01-18 08:29:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][790/1251]	eta 0:16:56 lr 0.000981	time 2.1454 (2.2061)	loss 4.8567 (4.2996)	grad_norm 1.3138 (1.1956)	
[2022-01-18 08:29:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][800/1251]	eta 0:16:34 lr 0.000981	time 2.1873 (2.2040)	loss 4.8801 (4.3011)	grad_norm 1.1335 (1.1957)	
[2022-01-18 08:29:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][810/1251]	eta 0:16:11 lr 0.000981	time 1.8617 (2.2032)	loss 4.6526 (4.3027)	grad_norm 1.2661 (1.1961)	
[2022-01-18 08:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][820/1251]	eta 0:15:49 lr 0.000981	time 2.7666 (2.2037)	loss 4.8031 (4.3032)	grad_norm 1.5269 (1.1970)	
[2022-01-18 08:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][830/1251]	eta 0:15:27 lr 0.000981	time 2.1935 (2.2028)	loss 3.9560 (4.3052)	grad_norm 1.0956 (1.1962)	
[2022-01-18 08:31:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][840/1251]	eta 0:15:05 lr 0.000981	time 2.1373 (2.2030)	loss 3.2375 (4.2999)	grad_norm 1.1679 (1.1966)	
[2022-01-18 08:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][850/1251]	eta 0:14:43 lr 0.000981	time 1.8514 (2.2034)	loss 4.4852 (4.3012)	grad_norm 0.9960 (1.1967)	
[2022-01-18 08:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][860/1251]	eta 0:14:20 lr 0.000981	time 2.5298 (2.2020)	loss 4.3981 (4.3022)	grad_norm 1.0513 (1.1966)	
[2022-01-18 08:32:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][870/1251]	eta 0:13:58 lr 0.000981	time 2.5054 (2.2018)	loss 4.0787 (4.3009)	grad_norm 1.1902 (1.1961)	
[2022-01-18 08:32:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][880/1251]	eta 0:13:36 lr 0.000981	time 1.8258 (2.2017)	loss 4.5760 (4.2987)	grad_norm 1.3192 (1.1981)	
[2022-01-18 08:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][890/1251]	eta 0:13:15 lr 0.000981	time 2.2566 (2.2022)	loss 4.4965 (4.2955)	grad_norm 1.5770 (1.1990)	
[2022-01-18 08:33:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][900/1251]	eta 0:12:53 lr 0.000981	time 2.6634 (2.2034)	loss 4.7861 (4.2946)	grad_norm 1.0540 (1.1997)	
[2022-01-18 08:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][910/1251]	eta 0:12:31 lr 0.000981	time 2.4121 (2.2047)	loss 3.8644 (4.2902)	grad_norm 1.2988 (1.1992)	
[2022-01-18 08:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][920/1251]	eta 0:12:10 lr 0.000981	time 1.9589 (2.2066)	loss 4.4539 (4.2898)	grad_norm 1.2173 (1.1990)	
[2022-01-18 08:34:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][930/1251]	eta 0:11:48 lr 0.000981	time 1.8400 (2.2062)	loss 3.6748 (4.2893)	grad_norm 1.4039 (1.1991)	
[2022-01-18 08:34:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][940/1251]	eta 0:11:25 lr 0.000981	time 1.8796 (2.2045)	loss 4.3113 (4.2900)	grad_norm 1.3810 (1.1981)	
[2022-01-18 08:35:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][950/1251]	eta 0:11:02 lr 0.000981	time 1.6181 (2.2006)	loss 4.7708 (4.2939)	grad_norm 1.2422 (1.1983)	
[2022-01-18 08:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][960/1251]	eta 0:10:39 lr 0.000981	time 1.8457 (2.1988)	loss 3.6778 (4.2956)	grad_norm 1.1953 (1.1976)	
[2022-01-18 08:35:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][970/1251]	eta 0:10:17 lr 0.000981	time 2.2535 (2.1975)	loss 4.4597 (4.2945)	grad_norm 1.4447 (1.1975)	
[2022-01-18 08:36:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][980/1251]	eta 0:09:55 lr 0.000981	time 1.8354 (2.1974)	loss 3.8233 (4.2970)	grad_norm 1.1042 (1.1966)	
[2022-01-18 08:36:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][990/1251]	eta 0:09:33 lr 0.000981	time 2.0526 (2.1965)	loss 4.5120 (4.2994)	grad_norm 1.2176 (1.1964)	
[2022-01-18 08:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1000/1251]	eta 0:09:11 lr 0.000981	time 1.9300 (2.1970)	loss 4.7303 (4.2996)	grad_norm 1.2543 (1.1963)	
[2022-01-18 08:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1010/1251]	eta 0:08:49 lr 0.000981	time 3.0864 (2.1979)	loss 4.4869 (4.3006)	grad_norm 0.9711 (1.1961)	
[2022-01-18 08:37:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1020/1251]	eta 0:08:27 lr 0.000981	time 1.8956 (2.1966)	loss 3.9539 (4.3014)	grad_norm 1.4404 (1.1963)	
[2022-01-18 08:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1030/1251]	eta 0:08:05 lr 0.000981	time 2.4960 (2.1984)	loss 4.4852 (4.3004)	grad_norm 1.2149 (1.1959)	
[2022-01-18 08:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1040/1251]	eta 0:07:43 lr 0.000981	time 1.7906 (2.1989)	loss 3.3911 (4.3004)	grad_norm 1.8635 (1.1964)	
[2022-01-18 08:38:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1050/1251]	eta 0:07:22 lr 0.000981	time 2.8334 (2.1995)	loss 3.5322 (4.3018)	grad_norm 1.3027 (1.1969)	
[2022-01-18 08:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1060/1251]	eta 0:07:00 lr 0.000981	time 2.2908 (2.1993)	loss 4.8459 (4.3022)	grad_norm 1.2164 (1.1970)	
[2022-01-18 08:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1070/1251]	eta 0:06:38 lr 0.000981	time 2.1192 (2.2004)	loss 4.8585 (4.3036)	grad_norm 1.1123 (1.1964)	
[2022-01-18 08:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1080/1251]	eta 0:06:16 lr 0.000981	time 2.2556 (2.1996)	loss 5.0925 (4.3040)	grad_norm 1.0887 (1.1961)	
[2022-01-18 08:40:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1090/1251]	eta 0:05:53 lr 0.000981	time 2.4423 (2.1987)	loss 4.6760 (4.3063)	grad_norm 1.1683 (1.1958)	
[2022-01-18 08:40:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1100/1251]	eta 0:05:31 lr 0.000981	time 1.9776 (2.1977)	loss 4.5161 (4.3063)	grad_norm 1.5463 (1.1959)	
[2022-01-18 08:40:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1110/1251]	eta 0:05:09 lr 0.000981	time 2.2319 (2.1971)	loss 3.8371 (4.3047)	grad_norm 1.1556 (1.1964)	
[2022-01-18 08:41:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1120/1251]	eta 0:04:47 lr 0.000980	time 1.9254 (2.1953)	loss 4.7653 (4.3023)	grad_norm 1.4850 (1.1965)	
[2022-01-18 08:41:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1130/1251]	eta 0:04:25 lr 0.000980	time 1.8561 (2.1947)	loss 4.7450 (4.3013)	grad_norm 1.0477 (1.1965)	
[2022-01-18 08:41:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1140/1251]	eta 0:04:03 lr 0.000980	time 1.9971 (2.1945)	loss 3.5500 (4.2988)	grad_norm 1.3345 (1.1961)	
[2022-01-18 08:42:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1150/1251]	eta 0:03:41 lr 0.000980	time 1.5888 (2.1951)	loss 3.2382 (4.2982)	grad_norm 1.4572 (1.1961)	
[2022-01-18 08:42:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1160/1251]	eta 0:03:19 lr 0.000980	time 1.8982 (2.1952)	loss 4.2434 (4.2977)	grad_norm 1.1576 (1.1963)	
[2022-01-18 08:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1170/1251]	eta 0:02:57 lr 0.000980	time 1.9042 (2.1950)	loss 4.5845 (4.2969)	grad_norm 1.2363 (1.1961)	
[2022-01-18 08:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1180/1251]	eta 0:02:35 lr 0.000980	time 1.8980 (2.1960)	loss 4.6436 (4.2954)	grad_norm 1.1013 (1.1958)	
[2022-01-18 08:43:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1190/1251]	eta 0:02:14 lr 0.000980	time 1.9520 (2.1970)	loss 4.4341 (4.2949)	grad_norm 0.8864 (1.1958)	
[2022-01-18 08:44:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1200/1251]	eta 0:01:52 lr 0.000980	time 2.7362 (2.1966)	loss 4.3601 (4.2910)	grad_norm 1.3692 (1.1962)	
[2022-01-18 08:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1210/1251]	eta 0:01:29 lr 0.000980	time 1.8693 (2.1947)	loss 4.1900 (4.2904)	grad_norm 1.1435 (1.1959)	
[2022-01-18 08:44:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1220/1251]	eta 0:01:08 lr 0.000980	time 2.3953 (2.1949)	loss 4.1553 (4.2926)	grad_norm 1.3729 (1.1958)	
[2022-01-18 08:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1230/1251]	eta 0:00:46 lr 0.000980	time 1.8222 (2.1939)	loss 3.8689 (4.2906)	grad_norm 0.8681 (1.1956)	
[2022-01-18 08:45:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1240/1251]	eta 0:00:24 lr 0.000980	time 2.3990 (2.1936)	loss 3.5126 (4.2895)	grad_norm 1.2166 (1.1955)	
[2022-01-18 08:45:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [26/300][1250/1251]	eta 0:00:02 lr 0.000980	time 1.1496 (2.1878)	loss 4.6415 (4.2899)	grad_norm 1.1331 (1.1947)	
[2022-01-18 08:45:44 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 26 training takes 0:45:37
[2022-01-18 08:46:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.634 (17.634)	Loss 1.5907 (1.5907)	Acc@1 63.770 (63.770)	Acc@5 86.426 (86.426)	
[2022-01-18 08:46:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.579 (3.220)	Loss 1.5321 (1.5704)	Acc@1 64.258 (63.947)	Acc@5 87.012 (86.009)	
[2022-01-18 08:46:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.631 (2.561)	Loss 1.5260 (1.5702)	Acc@1 65.430 (63.881)	Acc@5 86.914 (85.989)	
[2022-01-18 08:46:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.316 (2.360)	Loss 1.5820 (1.5602)	Acc@1 65.137 (64.056)	Acc@5 85.156 (86.230)	
[2022-01-18 08:47:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.505 (2.192)	Loss 1.5684 (1.5577)	Acc@1 65.723 (64.074)	Acc@5 84.863 (86.290)	
[2022-01-18 08:47:21 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 64.182 Acc@5 86.372
[2022-01-18 08:47:21 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 64.2%
[2022-01-18 08:47:21 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 64.18%
[2022-01-18 08:47:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][0/1251]	eta 7:55:20 lr 0.000980	time 22.7982 (22.7982)	loss 4.7274 (4.7274)	grad_norm 1.1391 (1.1391)	
[2022-01-18 08:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][10/1251]	eta 1:25:19 lr 0.000980	time 1.6967 (4.1257)	loss 3.0297 (3.8580)	grad_norm 0.9486 (1.1762)	
[2022-01-18 08:48:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][20/1251]	eta 1:06:43 lr 0.000980	time 2.1631 (3.2526)	loss 4.6893 (4.0580)	grad_norm 1.0082 (1.1824)	
[2022-01-18 08:48:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][30/1251]	eta 0:58:58 lr 0.000980	time 1.8809 (2.8980)	loss 4.4438 (4.2453)	grad_norm 1.0201 (1.1702)	
[2022-01-18 08:49:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][40/1251]	eta 0:55:23 lr 0.000980	time 2.9497 (2.7442)	loss 4.6005 (4.2692)	grad_norm 1.0320 (1.1558)	
[2022-01-18 08:49:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][50/1251]	eta 0:53:17 lr 0.000980	time 2.4072 (2.6621)	loss 4.0470 (4.2507)	grad_norm 1.3074 (1.1609)	
[2022-01-18 08:49:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][60/1251]	eta 0:50:56 lr 0.000980	time 1.7123 (2.5665)	loss 3.4263 (4.2592)	grad_norm 1.0515 (1.1478)	
[2022-01-18 08:50:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][70/1251]	eta 0:49:22 lr 0.000980	time 2.1922 (2.5088)	loss 4.1506 (4.2715)	grad_norm 1.1455 (1.1626)	
[2022-01-18 08:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][80/1251]	eta 0:48:36 lr 0.000980	time 3.6005 (2.4910)	loss 4.7628 (4.2954)	grad_norm 1.1908 (1.1721)	
[2022-01-18 08:51:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][90/1251]	eta 0:47:47 lr 0.000980	time 3.2116 (2.4702)	loss 4.5016 (4.3272)	grad_norm 1.1012 (1.1718)	
[2022-01-18 08:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][100/1251]	eta 0:46:42 lr 0.000980	time 1.7169 (2.4344)	loss 4.4281 (4.3441)	grad_norm 1.2470 (1.1675)	
[2022-01-18 08:51:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][110/1251]	eta 0:45:39 lr 0.000980	time 1.4866 (2.4007)	loss 5.1733 (4.3357)	grad_norm 1.3363 (1.1693)	
[2022-01-18 08:52:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][120/1251]	eta 0:45:01 lr 0.000980	time 3.2110 (2.3887)	loss 4.9490 (4.3498)	grad_norm 1.2487 (1.1775)	
[2022-01-18 08:52:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][130/1251]	eta 0:44:26 lr 0.000980	time 2.1882 (2.3789)	loss 3.5169 (4.3138)	grad_norm 1.1711 (1.1718)	
[2022-01-18 08:52:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][140/1251]	eta 0:43:33 lr 0.000980	time 1.8890 (2.3522)	loss 4.4056 (4.2909)	grad_norm 1.0332 (1.1649)	
[2022-01-18 08:53:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][150/1251]	eta 0:42:57 lr 0.000980	time 2.1587 (2.3409)	loss 4.5516 (4.2876)	grad_norm 1.3088 (1.1639)	
[2022-01-18 08:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][160/1251]	eta 0:42:32 lr 0.000980	time 3.1647 (2.3399)	loss 3.5028 (4.2871)	grad_norm 1.1204 (1.1614)	
[2022-01-18 08:54:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][170/1251]	eta 0:41:56 lr 0.000980	time 1.9158 (2.3284)	loss 4.8722 (4.2793)	grad_norm 1.1749 (1.1662)	
[2022-01-18 08:54:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][180/1251]	eta 0:41:19 lr 0.000980	time 2.2154 (2.3156)	loss 4.9204 (4.2493)	grad_norm 0.9728 (1.1658)	
[2022-01-18 08:54:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][190/1251]	eta 0:40:50 lr 0.000980	time 2.8330 (2.3092)	loss 4.4132 (4.2528)	grad_norm 1.1341 (1.1649)	
[2022-01-18 08:55:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][200/1251]	eta 0:40:24 lr 0.000980	time 2.6411 (2.3067)	loss 4.6431 (4.2599)	grad_norm 1.1907 (1.1633)	
[2022-01-18 08:55:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][210/1251]	eta 0:39:59 lr 0.000980	time 2.1789 (2.3054)	loss 4.8087 (4.2516)	grad_norm 1.0156 (1.1690)	
[2022-01-18 08:55:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][220/1251]	eta 0:39:27 lr 0.000980	time 2.0606 (2.2963)	loss 3.7167 (4.2403)	grad_norm 1.1367 (1.1692)	
[2022-01-18 08:56:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][230/1251]	eta 0:38:56 lr 0.000980	time 2.5918 (2.2882)	loss 4.0029 (4.2438)	grad_norm 1.7379 (1.1752)	
[2022-01-18 08:56:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][240/1251]	eta 0:38:26 lr 0.000980	time 2.3775 (2.2812)	loss 3.3643 (4.2430)	grad_norm 1.1421 (1.1763)	
[2022-01-18 08:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][250/1251]	eta 0:37:51 lr 0.000980	time 2.0711 (2.2688)	loss 3.7373 (4.2429)	grad_norm 1.0443 (1.1781)	
[2022-01-18 08:57:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][260/1251]	eta 0:37:25 lr 0.000980	time 2.0733 (2.2658)	loss 4.5202 (4.2459)	grad_norm 1.2515 (1.1792)	
[2022-01-18 08:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][270/1251]	eta 0:36:58 lr 0.000980	time 2.1443 (2.2616)	loss 4.0815 (4.2436)	grad_norm 1.1862 (1.1820)	
[2022-01-18 08:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][280/1251]	eta 0:36:37 lr 0.000980	time 3.3844 (2.2630)	loss 4.1318 (4.2376)	grad_norm 1.0915 (1.1841)	
[2022-01-18 08:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][290/1251]	eta 0:36:11 lr 0.000980	time 2.2506 (2.2596)	loss 4.4370 (4.2479)	grad_norm 1.0547 (1.1794)	
[2022-01-18 08:58:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][300/1251]	eta 0:35:41 lr 0.000980	time 2.1522 (2.2516)	loss 4.0806 (4.2508)	grad_norm 1.1248 (1.1778)	
[2022-01-18 08:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][310/1251]	eta 0:35:15 lr 0.000980	time 2.3268 (2.2482)	loss 4.3351 (4.2412)	grad_norm 1.0355 (1.1763)	
[2022-01-18 08:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][320/1251]	eta 0:34:54 lr 0.000980	time 2.4794 (2.2500)	loss 4.8631 (4.2475)	grad_norm 1.1144 (1.1749)	
[2022-01-18 08:59:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][330/1251]	eta 0:34:34 lr 0.000980	time 2.5948 (2.2524)	loss 3.6521 (4.2431)	grad_norm 1.2725 (1.1730)	
[2022-01-18 09:00:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][340/1251]	eta 0:34:09 lr 0.000980	time 1.8025 (2.2497)	loss 4.7691 (4.2422)	grad_norm 0.9676 (1.1723)	
[2022-01-18 09:00:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][350/1251]	eta 0:33:45 lr 0.000980	time 2.5414 (2.2483)	loss 3.3911 (4.2429)	grad_norm 1.4347 (1.1718)	
[2022-01-18 09:00:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][360/1251]	eta 0:33:21 lr 0.000980	time 1.7821 (2.2466)	loss 4.7184 (4.2483)	grad_norm 1.2460 (1.1764)	
[2022-01-18 09:01:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][370/1251]	eta 0:32:57 lr 0.000980	time 2.0172 (2.2445)	loss 3.0067 (4.2426)	grad_norm 1.0393 (1.1778)	
[2022-01-18 09:01:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][380/1251]	eta 0:32:34 lr 0.000980	time 2.2010 (2.2444)	loss 4.4659 (4.2451)	grad_norm 1.2675 (1.1805)	
[2022-01-18 09:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][390/1251]	eta 0:32:13 lr 0.000980	time 2.8224 (2.2457)	loss 3.0539 (4.2479)	grad_norm 1.2962 (1.1813)	
[2022-01-18 09:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][400/1251]	eta 0:31:51 lr 0.000980	time 2.2510 (2.2465)	loss 3.8242 (4.2369)	grad_norm 1.0143 (1.1823)	
[2022-01-18 09:02:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][410/1251]	eta 0:31:25 lr 0.000980	time 1.7740 (2.2418)	loss 4.2875 (4.2443)	grad_norm 0.9612 (1.1828)	
[2022-01-18 09:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][420/1251]	eta 0:30:59 lr 0.000980	time 1.6474 (2.2376)	loss 3.8551 (4.2336)	grad_norm 1.2995 (1.1839)	
[2022-01-18 09:03:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][430/1251]	eta 0:30:35 lr 0.000980	time 2.7879 (2.2355)	loss 4.3143 (4.2285)	grad_norm 0.9675 (1.1840)	
[2022-01-18 09:03:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][440/1251]	eta 0:30:12 lr 0.000980	time 1.8806 (2.2353)	loss 4.8603 (4.2259)	grad_norm 1.1537 (1.1839)	
[2022-01-18 09:04:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][450/1251]	eta 0:29:49 lr 0.000980	time 2.2676 (2.2335)	loss 4.0763 (4.2148)	grad_norm 1.1930 (1.1837)	
[2022-01-18 09:04:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][460/1251]	eta 0:29:25 lr 0.000980	time 2.2007 (2.2319)	loss 4.8343 (4.2192)	grad_norm 1.2083 (1.1840)	
[2022-01-18 09:04:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][470/1251]	eta 0:29:02 lr 0.000980	time 2.2826 (2.2309)	loss 3.4337 (4.2180)	grad_norm 1.2676 (1.1836)	
[2022-01-18 09:05:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][480/1251]	eta 0:28:38 lr 0.000980	time 2.1699 (2.2288)	loss 3.3101 (4.2165)	grad_norm 1.4466 (1.1829)	
[2022-01-18 09:05:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][490/1251]	eta 0:28:12 lr 0.000980	time 2.5111 (2.2243)	loss 5.3108 (4.2143)	grad_norm 1.1157 (1.1834)	
[2022-01-18 09:05:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][500/1251]	eta 0:27:48 lr 0.000980	time 1.9498 (2.2216)	loss 4.2004 (4.2196)	grad_norm 1.1417 (1.1831)	
[2022-01-18 09:06:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][510/1251]	eta 0:27:26 lr 0.000980	time 2.6489 (2.2214)	loss 5.1816 (4.2250)	grad_norm 1.0988 (1.1824)	
[2022-01-18 09:06:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][520/1251]	eta 0:27:04 lr 0.000980	time 2.5668 (2.2223)	loss 4.9212 (4.2250)	grad_norm 1.0739 (1.1829)	
[2022-01-18 09:07:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][530/1251]	eta 0:26:43 lr 0.000980	time 2.5269 (2.2239)	loss 4.8125 (4.2314)	grad_norm 1.1942 (1.1823)	
[2022-01-18 09:07:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][540/1251]	eta 0:26:20 lr 0.000980	time 1.9173 (2.2229)	loss 4.9836 (4.2310)	grad_norm 1.1452 (1.1846)	
[2022-01-18 09:07:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][550/1251]	eta 0:25:57 lr 0.000980	time 2.1964 (2.2223)	loss 4.2761 (4.2351)	grad_norm 1.0417 (1.1836)	
[2022-01-18 09:08:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][560/1251]	eta 0:25:36 lr 0.000980	time 2.9641 (2.2238)	loss 3.5291 (4.2343)	grad_norm 1.4050 (1.1855)	
[2022-01-18 09:08:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][570/1251]	eta 0:25:13 lr 0.000980	time 2.5052 (2.2230)	loss 3.9512 (4.2267)	grad_norm 1.3505 (1.1886)	
[2022-01-18 09:08:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][580/1251]	eta 0:24:48 lr 0.000980	time 1.6903 (2.2183)	loss 4.4397 (4.2296)	grad_norm 1.0641 (1.1882)	
[2022-01-18 09:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][590/1251]	eta 0:24:24 lr 0.000980	time 2.4393 (2.2152)	loss 4.6090 (4.2333)	grad_norm 1.1086 (1.1884)	
[2022-01-18 09:09:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][600/1251]	eta 0:24:01 lr 0.000980	time 2.5865 (2.2143)	loss 4.5313 (4.2396)	grad_norm 1.1116 (1.1895)	
[2022-01-18 09:09:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][610/1251]	eta 0:23:39 lr 0.000980	time 2.1340 (2.2137)	loss 5.0956 (4.2410)	grad_norm 1.0827 (1.1894)	
[2022-01-18 09:10:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][620/1251]	eta 0:23:18 lr 0.000980	time 2.0128 (2.2156)	loss 4.9765 (4.2404)	grad_norm 1.2878 (1.1897)	
[2022-01-18 09:10:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][630/1251]	eta 0:22:56 lr 0.000980	time 1.5688 (2.2163)	loss 4.7969 (4.2425)	grad_norm 1.1526 (1.1883)	
[2022-01-18 09:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][640/1251]	eta 0:22:35 lr 0.000980	time 2.6360 (2.2190)	loss 3.4754 (4.2416)	grad_norm 1.2014 (1.1880)	
[2022-01-18 09:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][650/1251]	eta 0:22:13 lr 0.000980	time 2.0114 (2.2190)	loss 3.8181 (4.2377)	grad_norm 1.2633 (1.1880)	
[2022-01-18 09:11:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][660/1251]	eta 0:21:51 lr 0.000980	time 3.5598 (2.2199)	loss 4.2597 (4.2368)	grad_norm 1.0352 (1.1873)	
[2022-01-18 09:12:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][670/1251]	eta 0:21:29 lr 0.000980	time 1.9733 (2.2191)	loss 4.7170 (4.2398)	grad_norm 1.1321 (1.1851)	
[2022-01-18 09:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][680/1251]	eta 0:21:04 lr 0.000980	time 1.8797 (2.2153)	loss 4.1948 (4.2399)	grad_norm 1.0838 (1.1843)	
[2022-01-18 09:12:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][690/1251]	eta 0:20:40 lr 0.000980	time 1.6967 (2.2118)	loss 4.2319 (4.2364)	grad_norm 1.1253 (1.1843)	
[2022-01-18 09:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][700/1251]	eta 0:20:17 lr 0.000980	time 1.9429 (2.2102)	loss 4.0132 (4.2360)	grad_norm 1.0558 (1.1841)	
[2022-01-18 09:13:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][710/1251]	eta 0:19:54 lr 0.000980	time 2.0715 (2.2079)	loss 4.4659 (4.2412)	grad_norm 0.9116 (1.1843)	
[2022-01-18 09:13:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][720/1251]	eta 0:19:31 lr 0.000980	time 2.5290 (2.2058)	loss 4.0278 (4.2419)	grad_norm 0.9947 (1.1828)	
[2022-01-18 09:14:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][730/1251]	eta 0:19:08 lr 0.000979	time 2.2601 (2.2047)	loss 3.8522 (4.2418)	grad_norm 1.1339 (1.1821)	
[2022-01-18 09:14:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][740/1251]	eta 0:18:47 lr 0.000979	time 2.3782 (2.2057)	loss 4.2676 (4.2412)	grad_norm 1.5532 (1.1818)	
[2022-01-18 09:14:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][750/1251]	eta 0:18:25 lr 0.000979	time 1.6617 (2.2072)	loss 3.8842 (4.2403)	grad_norm 0.9227 (1.1816)	
[2022-01-18 09:15:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][760/1251]	eta 0:18:04 lr 0.000979	time 2.7726 (2.2082)	loss 3.8946 (4.2400)	grad_norm 1.1050 (1.1811)	
[2022-01-18 09:15:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][770/1251]	eta 0:17:42 lr 0.000979	time 2.2678 (2.2097)	loss 5.0822 (4.2388)	grad_norm 1.6124 (1.1810)	
[2022-01-18 09:16:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][780/1251]	eta 0:17:20 lr 0.000979	time 2.2096 (2.2092)	loss 4.7312 (4.2399)	grad_norm 1.2042 (1.1814)	
[2022-01-18 09:16:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][790/1251]	eta 0:16:58 lr 0.000979	time 2.5799 (2.2100)	loss 3.9616 (4.2398)	grad_norm 1.3048 (1.1820)	
[2022-01-18 09:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][800/1251]	eta 0:16:36 lr 0.000979	time 2.7771 (2.2092)	loss 4.2784 (4.2412)	grad_norm 1.1611 (1.1829)	
[2022-01-18 09:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][810/1251]	eta 0:16:13 lr 0.000979	time 1.8551 (2.2082)	loss 4.0055 (4.2420)	grad_norm 1.1712 (1.1831)	
[2022-01-18 09:17:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][820/1251]	eta 0:15:51 lr 0.000979	time 2.1616 (2.2083)	loss 4.1254 (4.2394)	grad_norm 0.9692 (1.1823)	
[2022-01-18 09:17:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][830/1251]	eta 0:15:29 lr 0.000979	time 2.1512 (2.2090)	loss 3.2094 (4.2386)	grad_norm 1.1986 (1.1814)	
[2022-01-18 09:18:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][840/1251]	eta 0:15:07 lr 0.000979	time 2.4594 (2.2087)	loss 5.0707 (4.2364)	grad_norm 1.2172 (1.1802)	
[2022-01-18 09:18:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][850/1251]	eta 0:14:45 lr 0.000979	time 1.6616 (2.2081)	loss 5.1059 (4.2346)	grad_norm 1.1704 (1.1795)	
[2022-01-18 09:19:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][860/1251]	eta 0:14:22 lr 0.000979	time 2.2595 (2.2058)	loss 3.7537 (4.2329)	grad_norm 1.2148 (1.1801)	
[2022-01-18 09:19:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][870/1251]	eta 0:14:01 lr 0.000979	time 1.8578 (2.2083)	loss 4.7367 (4.2306)	grad_norm 1.0172 (1.1802)	
[2022-01-18 09:19:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][880/1251]	eta 0:13:38 lr 0.000979	time 1.9653 (2.2070)	loss 3.3161 (4.2285)	grad_norm 1.1841 (1.1803)	
[2022-01-18 09:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][890/1251]	eta 0:13:16 lr 0.000979	time 1.6087 (2.2058)	loss 4.7852 (4.2306)	grad_norm 1.0694 (1.1806)	
[2022-01-18 09:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][900/1251]	eta 0:12:53 lr 0.000979	time 1.8988 (2.2033)	loss 3.3242 (4.2284)	grad_norm 1.0544 (1.1823)	
[2022-01-18 09:20:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][910/1251]	eta 0:12:31 lr 0.000979	time 2.1256 (2.2028)	loss 4.1497 (4.2299)	grad_norm 1.1779 (1.1821)	
[2022-01-18 09:21:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][920/1251]	eta 0:12:09 lr 0.000979	time 2.2040 (2.2029)	loss 4.1074 (4.2340)	grad_norm 1.2217 (1.1816)	
[2022-01-18 09:21:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][930/1251]	eta 0:11:47 lr 0.000979	time 1.8612 (2.2042)	loss 4.4881 (4.2390)	grad_norm 0.9862 (1.1797)	
[2022-01-18 09:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][940/1251]	eta 0:11:25 lr 0.000979	time 2.1769 (2.2046)	loss 4.2849 (4.2412)	grad_norm 1.3091 (1.1796)	
[2022-01-18 09:22:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][950/1251]	eta 0:11:03 lr 0.000979	time 2.3159 (2.2052)	loss 4.0202 (4.2399)	grad_norm 1.0591 (1.1796)	
[2022-01-18 09:22:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][960/1251]	eta 0:10:41 lr 0.000979	time 2.7339 (2.2052)	loss 4.1439 (4.2387)	grad_norm 1.1068 (1.1788)	
[2022-01-18 09:23:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][970/1251]	eta 0:10:19 lr 0.000979	time 1.8551 (2.2044)	loss 4.1336 (4.2380)	grad_norm 1.1882 (1.1780)	
[2022-01-18 09:23:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][980/1251]	eta 0:09:56 lr 0.000979	time 1.9463 (2.2018)	loss 2.9708 (4.2389)	grad_norm 0.9536 (1.1777)	
[2022-01-18 09:23:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][990/1251]	eta 0:09:34 lr 0.000979	time 2.0355 (2.2011)	loss 4.8828 (4.2413)	grad_norm 1.4336 (1.1774)	
[2022-01-18 09:24:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1000/1251]	eta 0:09:12 lr 0.000979	time 2.3329 (2.2007)	loss 4.8896 (4.2433)	grad_norm 1.2333 (1.1773)	
[2022-01-18 09:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1010/1251]	eta 0:08:51 lr 0.000979	time 2.5773 (2.2039)	loss 3.7716 (4.2417)	grad_norm 0.9421 (1.1778)	
[2022-01-18 09:24:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1020/1251]	eta 0:08:29 lr 0.000979	time 1.5251 (2.2042)	loss 3.6548 (4.2415)	grad_norm 1.3255 (1.1769)	
[2022-01-18 09:25:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1030/1251]	eta 0:08:07 lr 0.000979	time 1.9315 (2.2052)	loss 4.5335 (4.2401)	grad_norm 1.2932 (1.1772)	
[2022-01-18 09:25:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1040/1251]	eta 0:07:45 lr 0.000979	time 2.1133 (2.2052)	loss 4.1666 (4.2408)	grad_norm 1.1201 (1.1771)	
[2022-01-18 09:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1050/1251]	eta 0:07:23 lr 0.000979	time 1.5759 (2.2042)	loss 4.2235 (4.2399)	grad_norm 0.9734 (1.1767)	
[2022-01-18 09:26:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1060/1251]	eta 0:07:00 lr 0.000979	time 2.1766 (2.2023)	loss 4.7646 (4.2433)	grad_norm 1.2694 (1.1773)	
[2022-01-18 09:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1070/1251]	eta 0:06:38 lr 0.000979	time 1.8849 (2.2012)	loss 3.0818 (4.2414)	grad_norm 1.3405 (1.1780)	
[2022-01-18 09:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1080/1251]	eta 0:06:16 lr 0.000979	time 2.0713 (2.2006)	loss 3.8888 (4.2435)	grad_norm 1.3035 (1.1788)	
[2022-01-18 09:27:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1090/1251]	eta 0:05:54 lr 0.000979	time 1.7434 (2.2005)	loss 4.4474 (4.2442)	grad_norm 1.2727 (1.1791)	
[2022-01-18 09:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1100/1251]	eta 0:05:32 lr 0.000979	time 1.8633 (2.1999)	loss 3.6983 (4.2458)	grad_norm 1.0688 (1.1790)	
[2022-01-18 09:28:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1110/1251]	eta 0:05:10 lr 0.000979	time 2.2398 (2.2004)	loss 4.5389 (4.2434)	grad_norm 1.2259 (1.1789)	
[2022-01-18 09:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1120/1251]	eta 0:04:48 lr 0.000979	time 2.2801 (2.2016)	loss 4.4610 (4.2418)	grad_norm 1.0887 (1.1787)	
[2022-01-18 09:28:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1130/1251]	eta 0:04:26 lr 0.000979	time 2.1582 (2.2044)	loss 4.0540 (4.2427)	grad_norm 1.3267 (1.1790)	
[2022-01-18 09:29:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1140/1251]	eta 0:04:04 lr 0.000979	time 1.6315 (2.2036)	loss 3.4716 (4.2432)	grad_norm 1.1895 (1.1782)	
[2022-01-18 09:29:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1150/1251]	eta 0:03:42 lr 0.000979	time 1.8691 (2.2033)	loss 3.9483 (4.2439)	grad_norm 0.9579 (1.1778)	
[2022-01-18 09:29:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1160/1251]	eta 0:03:20 lr 0.000979	time 1.8397 (2.2021)	loss 4.1279 (4.2438)	grad_norm 1.2009 (1.1775)	
[2022-01-18 09:30:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1170/1251]	eta 0:02:58 lr 0.000979	time 1.8421 (2.2020)	loss 5.1490 (4.2455)	grad_norm 1.0502 (1.1768)	
[2022-01-18 09:30:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1180/1251]	eta 0:02:36 lr 0.000979	time 2.6381 (2.2018)	loss 3.4539 (4.2471)	grad_norm 1.0549 (1.1761)	
[2022-01-18 09:31:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1190/1251]	eta 0:02:14 lr 0.000979	time 1.8818 (2.2010)	loss 4.4144 (4.2484)	grad_norm 1.3213 (1.1770)	
[2022-01-18 09:31:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1200/1251]	eta 0:01:52 lr 0.000979	time 1.9239 (2.1992)	loss 3.5648 (4.2479)	grad_norm 1.4216 (1.1773)	
[2022-01-18 09:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1210/1251]	eta 0:01:30 lr 0.000979	time 1.8579 (2.1975)	loss 3.5436 (4.2446)	grad_norm 1.2433 (1.1779)	
[2022-01-18 09:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1220/1251]	eta 0:01:08 lr 0.000979	time 1.8747 (2.1973)	loss 4.2708 (4.2447)	grad_norm 1.2669 (1.1778)	
[2022-01-18 09:32:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1230/1251]	eta 0:00:46 lr 0.000979	time 2.2200 (2.1962)	loss 4.5321 (4.2451)	grad_norm 1.2252 (1.1775)	
[2022-01-18 09:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1240/1251]	eta 0:00:24 lr 0.000979	time 2.4908 (2.1975)	loss 5.2396 (4.2434)	grad_norm 1.3920 (1.1779)	
[2022-01-18 09:33:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [27/300][1250/1251]	eta 0:00:02 lr 0.000979	time 1.2101 (2.1917)	loss 3.1719 (4.2418)	grad_norm 1.3639 (1.1776)	
[2022-01-18 09:33:04 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 27 training takes 0:45:42
[2022-01-18 09:33:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.857 (17.857)	Loss 1.5607 (1.5607)	Acc@1 63.672 (63.672)	Acc@5 87.402 (87.402)	
[2022-01-18 09:33:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.307 (3.525)	Loss 1.5588 (1.5707)	Acc@1 64.551 (64.187)	Acc@5 87.598 (86.923)	
[2022-01-18 09:33:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.601 (2.572)	Loss 1.5738 (1.5524)	Acc@1 63.379 (64.541)	Acc@5 86.035 (86.886)	
[2022-01-18 09:34:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.992 (2.334)	Loss 1.4961 (1.5448)	Acc@1 66.016 (64.604)	Acc@5 88.379 (87.018)	
[2022-01-18 09:34:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.732 (2.188)	Loss 1.5000 (1.5489)	Acc@1 65.527 (64.615)	Acc@5 87.695 (86.819)	
[2022-01-18 09:34:41 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 64.610 Acc@5 86.710
[2022-01-18 09:34:41 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 64.6%
[2022-01-18 09:34:41 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 64.61%
[2022-01-18 09:35:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][0/1251]	eta 7:22:05 lr 0.000979	time 21.2031 (21.2031)	loss 4.4217 (4.4217)	grad_norm 1.1129 (1.1129)	
[2022-01-18 09:35:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][10/1251]	eta 1:24:05 lr 0.000979	time 2.5926 (4.0654)	loss 4.6177 (4.3869)	grad_norm 0.9870 (1.2083)	
[2022-01-18 09:35:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][20/1251]	eta 1:03:13 lr 0.000979	time 1.5040 (3.0819)	loss 3.0984 (4.1792)	grad_norm 1.2394 (1.2407)	
[2022-01-18 09:36:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][30/1251]	eta 0:56:04 lr 0.000979	time 1.8197 (2.7557)	loss 3.9136 (4.1980)	grad_norm 1.3477 (1.2211)	
[2022-01-18 09:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][40/1251]	eta 0:53:07 lr 0.000979	time 3.6153 (2.6325)	loss 3.5941 (4.2246)	grad_norm 1.1753 (1.2020)	
[2022-01-18 09:36:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][50/1251]	eta 0:51:22 lr 0.000979	time 2.2718 (2.5667)	loss 3.0348 (4.1663)	grad_norm 1.4151 (1.1912)	
[2022-01-18 09:37:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][60/1251]	eta 0:50:24 lr 0.000979	time 1.9524 (2.5394)	loss 5.0420 (4.2031)	grad_norm 1.2448 (1.2030)	
[2022-01-18 09:37:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][70/1251]	eta 0:49:23 lr 0.000979	time 2.2052 (2.5090)	loss 4.8280 (4.2068)	grad_norm 1.1572 (1.2096)	
[2022-01-18 09:38:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][80/1251]	eta 0:48:22 lr 0.000979	time 2.8423 (2.4786)	loss 3.2893 (4.1806)	grad_norm 1.2143 (1.2009)	
[2022-01-18 09:38:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][90/1251]	eta 0:47:29 lr 0.000979	time 2.6581 (2.4543)	loss 3.9671 (4.2192)	grad_norm 1.3724 (1.2108)	
[2022-01-18 09:38:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][100/1251]	eta 0:46:26 lr 0.000979	time 1.8574 (2.4208)	loss 4.9421 (4.2432)	grad_norm 1.1386 (1.2098)	
[2022-01-18 09:39:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][110/1251]	eta 0:45:30 lr 0.000979	time 1.8812 (2.3935)	loss 3.6096 (4.2734)	grad_norm 1.2642 (1.2090)	
[2022-01-18 09:39:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][120/1251]	eta 0:44:43 lr 0.000979	time 2.3835 (2.3729)	loss 4.3000 (4.2645)	grad_norm 1.6162 (1.2051)	
[2022-01-18 09:39:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][130/1251]	eta 0:44:22 lr 0.000979	time 2.7994 (2.3753)	loss 3.5117 (4.2667)	grad_norm 1.3056 (1.1974)	
[2022-01-18 09:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][140/1251]	eta 0:43:43 lr 0.000979	time 1.7881 (2.3616)	loss 4.5185 (4.2763)	grad_norm 1.0609 (1.1961)	
[2022-01-18 09:40:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][150/1251]	eta 0:43:09 lr 0.000979	time 1.8888 (2.3520)	loss 4.4095 (4.2805)	grad_norm 1.1979 (1.1928)	
[2022-01-18 09:40:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][160/1251]	eta 0:42:17 lr 0.000979	time 2.3075 (2.3254)	loss 4.4273 (4.3006)	grad_norm 1.1155 (1.1899)	
[2022-01-18 09:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][170/1251]	eta 0:41:35 lr 0.000979	time 2.5331 (2.3087)	loss 4.1821 (4.2996)	grad_norm 1.1713 (1.1853)	
[2022-01-18 09:41:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][180/1251]	eta 0:40:55 lr 0.000979	time 2.0129 (2.2930)	loss 4.9994 (4.3112)	grad_norm 1.5182 (1.1839)	
[2022-01-18 09:41:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][190/1251]	eta 0:40:20 lr 0.000979	time 2.2671 (2.2811)	loss 3.7443 (4.3082)	grad_norm 1.0625 (1.1846)	
[2022-01-18 09:42:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][200/1251]	eta 0:39:52 lr 0.000979	time 1.8926 (2.2767)	loss 4.0403 (4.3049)	grad_norm 1.2970 (1.1877)	
[2022-01-18 09:42:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][210/1251]	eta 0:39:24 lr 0.000979	time 1.6469 (2.2711)	loss 3.9567 (4.2975)	grad_norm 1.1061 (1.1821)	
[2022-01-18 09:43:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][220/1251]	eta 0:39:10 lr 0.000979	time 1.7907 (2.2796)	loss 5.1697 (4.3146)	grad_norm 0.9835 (1.1788)	
[2022-01-18 09:43:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][230/1251]	eta 0:38:45 lr 0.000979	time 2.2213 (2.2777)	loss 4.7342 (4.3213)	grad_norm 1.2855 (1.1803)	
[2022-01-18 09:43:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][240/1251]	eta 0:38:24 lr 0.000979	time 2.2776 (2.2793)	loss 4.5277 (4.3216)	grad_norm 1.1647 (1.1839)	
[2022-01-18 09:44:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][250/1251]	eta 0:37:53 lr 0.000979	time 2.2795 (2.2714)	loss 4.0967 (4.3078)	grad_norm 1.3202 (1.1838)	
[2022-01-18 09:44:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][260/1251]	eta 0:37:22 lr 0.000979	time 1.5446 (2.2632)	loss 3.2986 (4.2935)	grad_norm 1.0583 (1.1814)	
[2022-01-18 09:44:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][270/1251]	eta 0:36:53 lr 0.000979	time 2.3462 (2.2568)	loss 4.5452 (4.2904)	grad_norm 1.2691 (1.1838)	
[2022-01-18 09:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][280/1251]	eta 0:36:29 lr 0.000979	time 1.9179 (2.2553)	loss 4.6948 (4.2900)	grad_norm 1.1991 (1.1826)	
[2022-01-18 09:45:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][290/1251]	eta 0:36:12 lr 0.000979	time 2.4899 (2.2610)	loss 3.3673 (4.2840)	grad_norm 1.1840 (1.1882)	
[2022-01-18 09:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][300/1251]	eta 0:35:46 lr 0.000979	time 1.6647 (2.2575)	loss 3.5125 (4.2810)	grad_norm 1.1869 (1.1877)	
[2022-01-18 09:46:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][310/1251]	eta 0:35:19 lr 0.000979	time 2.2058 (2.2527)	loss 3.7843 (4.2775)	grad_norm 1.2893 (1.1898)	
[2022-01-18 09:46:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][320/1251]	eta 0:34:59 lr 0.000978	time 2.5945 (2.2548)	loss 4.4333 (4.2704)	grad_norm 1.2059 (1.1886)	
[2022-01-18 09:47:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][330/1251]	eta 0:34:31 lr 0.000978	time 1.6434 (2.2494)	loss 3.8777 (4.2591)	grad_norm 1.3392 (1.1902)	
[2022-01-18 09:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][340/1251]	eta 0:34:03 lr 0.000978	time 1.8575 (2.2434)	loss 4.7138 (4.2600)	grad_norm 1.1525 (1.1918)	
[2022-01-18 09:47:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][350/1251]	eta 0:33:39 lr 0.000978	time 2.5978 (2.2416)	loss 2.8776 (4.2503)	grad_norm 1.1968 (1.1893)	
[2022-01-18 09:48:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][360/1251]	eta 0:33:18 lr 0.000978	time 1.8712 (2.2430)	loss 4.3096 (4.2505)	grad_norm 1.0749 (1.1855)	
[2022-01-18 09:48:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][370/1251]	eta 0:32:56 lr 0.000978	time 2.5331 (2.2432)	loss 4.7179 (4.2381)	grad_norm 1.2328 (1.1833)	
[2022-01-18 09:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][380/1251]	eta 0:32:27 lr 0.000978	time 1.9167 (2.2364)	loss 4.3598 (4.2336)	grad_norm 1.1297 (1.1841)	
[2022-01-18 09:49:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][390/1251]	eta 0:32:05 lr 0.000978	time 2.8822 (2.2358)	loss 2.9906 (4.2358)	grad_norm 1.8402 (1.1873)	
[2022-01-18 09:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][400/1251]	eta 0:31:46 lr 0.000978	time 2.1349 (2.2399)	loss 3.8816 (4.2376)	grad_norm 1.0775 (1.1859)	
[2022-01-18 09:50:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][410/1251]	eta 0:31:27 lr 0.000978	time 2.5054 (2.2445)	loss 4.3855 (4.2398)	grad_norm 1.4584 (1.1872)	
[2022-01-18 09:50:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][420/1251]	eta 0:31:03 lr 0.000978	time 1.8947 (2.2420)	loss 4.2389 (4.2361)	grad_norm 1.0775 (1.1860)	
[2022-01-18 09:50:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][430/1251]	eta 0:30:34 lr 0.000978	time 1.9726 (2.2341)	loss 4.1726 (4.2330)	grad_norm 1.3621 (1.1868)	
[2022-01-18 09:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][440/1251]	eta 0:30:08 lr 0.000978	time 1.7945 (2.2296)	loss 5.0439 (4.2387)	grad_norm 1.0850 (1.1878)	
[2022-01-18 09:51:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][450/1251]	eta 0:29:56 lr 0.000978	time 1.8720 (2.2425)	loss 4.5846 (4.2408)	grad_norm 1.2251 (1.1877)	
[2022-01-18 09:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][460/1251]	eta 0:29:33 lr 0.000978	time 1.9362 (2.2427)	loss 4.3211 (4.2418)	grad_norm 1.0929 (1.1887)	
[2022-01-18 09:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][470/1251]	eta 0:29:12 lr 0.000978	time 2.0854 (2.2434)	loss 4.5216 (4.2426)	grad_norm 0.9795 (1.1874)	
[2022-01-18 09:52:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][480/1251]	eta 0:28:46 lr 0.000978	time 1.7752 (2.2393)	loss 4.6179 (4.2388)	grad_norm 1.2405 (1.1859)	
[2022-01-18 09:53:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][490/1251]	eta 0:28:23 lr 0.000978	time 1.9033 (2.2383)	loss 5.1198 (4.2443)	grad_norm 0.9630 (1.1835)	
[2022-01-18 09:53:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][500/1251]	eta 0:28:01 lr 0.000978	time 1.9386 (2.2393)	loss 3.7447 (4.2403)	grad_norm 0.9973 (1.1852)	
[2022-01-18 09:53:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][510/1251]	eta 0:27:38 lr 0.000978	time 2.2368 (2.2378)	loss 4.8846 (4.2347)	grad_norm 1.2582 (1.1845)	
[2022-01-18 09:54:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][520/1251]	eta 0:27:12 lr 0.000978	time 2.0095 (2.2337)	loss 3.8374 (4.2372)	grad_norm 1.2180 (1.1857)	
[2022-01-18 09:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][530/1251]	eta 0:26:53 lr 0.000978	time 1.8890 (2.2378)	loss 3.8935 (4.2372)	grad_norm 1.2725 (1.1862)	
[2022-01-18 09:54:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][540/1251]	eta 0:26:28 lr 0.000978	time 1.5685 (2.2338)	loss 3.8886 (4.2385)	grad_norm 1.1293 (1.1870)	
[2022-01-18 09:55:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][550/1251]	eta 0:26:04 lr 0.000978	time 1.6399 (2.2324)	loss 4.3996 (4.2411)	grad_norm 0.9624 (1.1870)	
[2022-01-18 09:55:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][560/1251]	eta 0:25:39 lr 0.000978	time 1.9944 (2.2284)	loss 3.9243 (4.2409)	grad_norm 1.0996 (1.1877)	
[2022-01-18 09:55:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][570/1251]	eta 0:25:17 lr 0.000978	time 1.9611 (2.2281)	loss 4.7400 (4.2447)	grad_norm 1.4052 (1.1890)	
[2022-01-18 09:56:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][580/1251]	eta 0:24:55 lr 0.000978	time 1.6740 (2.2283)	loss 4.5776 (4.2511)	grad_norm 1.0353 (1.1880)	
[2022-01-18 09:56:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][590/1251]	eta 0:24:33 lr 0.000978	time 2.3105 (2.2285)	loss 4.7492 (4.2476)	grad_norm 1.1715 (1.1874)	
[2022-01-18 09:56:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][600/1251]	eta 0:24:09 lr 0.000978	time 1.7180 (2.2272)	loss 4.4967 (4.2533)	grad_norm 0.9738 (1.1855)	
[2022-01-18 09:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][610/1251]	eta 0:23:50 lr 0.000978	time 1.9071 (2.2314)	loss 4.6536 (4.2514)	grad_norm 1.3131 (1.1864)	
[2022-01-18 09:57:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][620/1251]	eta 0:23:25 lr 0.000978	time 1.6026 (2.2275)	loss 4.1449 (4.2438)	grad_norm 1.0725 (1.1852)	
[2022-01-18 09:58:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][630/1251]	eta 0:23:01 lr 0.000978	time 1.7956 (2.2244)	loss 4.5988 (4.2463)	grad_norm 1.0582 (1.1857)	
[2022-01-18 09:58:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][640/1251]	eta 0:22:37 lr 0.000978	time 1.8783 (2.2225)	loss 3.2354 (4.2413)	grad_norm 0.9864 (1.1856)	
[2022-01-18 09:58:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][650/1251]	eta 0:22:18 lr 0.000978	time 2.2875 (2.2271)	loss 3.5647 (4.2400)	grad_norm 1.1101 (1.1849)	
[2022-01-18 09:59:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][660/1251]	eta 0:21:54 lr 0.000978	time 1.7710 (2.2244)	loss 3.1050 (4.2379)	grad_norm 1.2181 (1.1840)	
[2022-01-18 09:59:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][670/1251]	eta 0:21:32 lr 0.000978	time 2.1594 (2.2244)	loss 4.2892 (4.2403)	grad_norm 1.1479 (1.1829)	
[2022-01-18 09:59:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][680/1251]	eta 0:21:08 lr 0.000978	time 1.5703 (2.2217)	loss 4.5487 (4.2391)	grad_norm 1.3038 (1.1828)	
[2022-01-18 10:00:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][690/1251]	eta 0:20:47 lr 0.000978	time 1.9270 (2.2235)	loss 3.2625 (4.2323)	grad_norm 1.2385 (1.1819)	
[2022-01-18 10:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][700/1251]	eta 0:20:24 lr 0.000978	time 1.8316 (2.2222)	loss 4.1939 (4.2349)	grad_norm 1.2359 (1.1817)	
[2022-01-18 10:01:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][710/1251]	eta 0:20:01 lr 0.000978	time 2.2441 (2.2209)	loss 3.9045 (4.2299)	grad_norm 1.2899 (1.1824)	
[2022-01-18 10:01:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][720/1251]	eta 0:19:38 lr 0.000978	time 1.7835 (2.2189)	loss 4.4749 (4.2318)	grad_norm 1.1338 (1.1808)	
[2022-01-18 10:01:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][730/1251]	eta 0:19:16 lr 0.000978	time 2.2546 (2.2205)	loss 3.4569 (4.2363)	grad_norm 1.1181 (1.1813)	
[2022-01-18 10:02:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][740/1251]	eta 0:18:54 lr 0.000978	time 2.1168 (2.2209)	loss 3.5814 (4.2291)	grad_norm 1.1249 (1.1798)	
[2022-01-18 10:02:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][750/1251]	eta 0:18:32 lr 0.000978	time 2.3097 (2.2201)	loss 4.0419 (4.2290)	grad_norm 1.1069 (1.1800)	
[2022-01-18 10:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][760/1251]	eta 0:18:08 lr 0.000978	time 2.1914 (2.2179)	loss 4.4189 (4.2303)	grad_norm 1.1346 (1.1805)	
[2022-01-18 10:03:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][770/1251]	eta 0:17:46 lr 0.000978	time 1.6631 (2.2175)	loss 4.6835 (4.2342)	grad_norm 1.0907 (1.1803)	
[2022-01-18 10:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][780/1251]	eta 0:17:24 lr 0.000978	time 2.0225 (2.2168)	loss 4.1244 (4.2329)	grad_norm 1.1262 (1.1794)	
[2022-01-18 10:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][790/1251]	eta 0:17:01 lr 0.000978	time 1.9381 (2.2158)	loss 3.8201 (4.2319)	grad_norm 1.1653 (1.1791)	
[2022-01-18 10:04:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][800/1251]	eta 0:16:39 lr 0.000978	time 2.4918 (2.2153)	loss 4.3189 (4.2328)	grad_norm 0.9728 (1.1777)	
[2022-01-18 10:04:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][810/1251]	eta 0:16:15 lr 0.000978	time 1.6913 (2.2130)	loss 4.4205 (4.2338)	grad_norm 1.0627 (1.1775)	
[2022-01-18 10:04:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][820/1251]	eta 0:15:53 lr 0.000978	time 2.4101 (2.2116)	loss 3.6382 (4.2347)	grad_norm 1.2906 (1.1778)	
[2022-01-18 10:05:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][830/1251]	eta 0:15:30 lr 0.000978	time 2.7024 (2.2106)	loss 4.3578 (4.2317)	grad_norm 1.2891 (1.1792)	
[2022-01-18 10:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][840/1251]	eta 0:15:08 lr 0.000978	time 2.5699 (2.2099)	loss 3.5214 (4.2292)	grad_norm 1.0407 (1.1797)	
[2022-01-18 10:06:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][850/1251]	eta 0:14:45 lr 0.000978	time 1.9415 (2.2082)	loss 3.1831 (4.2297)	grad_norm 1.2553 (1.1783)	
[2022-01-18 10:06:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][860/1251]	eta 0:14:23 lr 0.000978	time 2.6257 (2.2089)	loss 4.5015 (4.2260)	grad_norm 1.0711 (1.1784)	
[2022-01-18 10:06:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][870/1251]	eta 0:14:01 lr 0.000978	time 2.4707 (2.2088)	loss 4.6510 (4.2218)	grad_norm 1.1168 (1.1768)	
[2022-01-18 10:07:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][880/1251]	eta 0:13:39 lr 0.000978	time 2.8140 (2.2091)	loss 4.4958 (4.2239)	grad_norm 1.1274 (1.1773)	
[2022-01-18 10:07:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][890/1251]	eta 0:13:17 lr 0.000978	time 1.5704 (2.2096)	loss 5.1542 (4.2223)	grad_norm 1.2450 (1.1772)	
[2022-01-18 10:07:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][900/1251]	eta 0:12:55 lr 0.000978	time 2.2282 (2.2085)	loss 4.6355 (4.2225)	grad_norm 1.1065 (1.1771)	
[2022-01-18 10:08:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][910/1251]	eta 0:12:32 lr 0.000978	time 2.7933 (2.2082)	loss 4.7753 (4.2228)	grad_norm 1.0816 (1.1764)	
[2022-01-18 10:08:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][920/1251]	eta 0:12:10 lr 0.000978	time 2.5236 (2.2073)	loss 4.5122 (4.2230)	grad_norm 1.0707 (1.1769)	
[2022-01-18 10:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][930/1251]	eta 0:11:48 lr 0.000978	time 1.6495 (2.2070)	loss 4.2783 (4.2254)	grad_norm 1.1936 (1.1758)	
[2022-01-18 10:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][940/1251]	eta 0:11:27 lr 0.000978	time 3.0159 (2.2102)	loss 3.7289 (4.2233)	grad_norm 1.3952 (1.1768)	
[2022-01-18 10:09:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][950/1251]	eta 0:11:05 lr 0.000978	time 1.8829 (2.2107)	loss 3.4842 (4.2191)	grad_norm 1.0744 (1.1768)	
[2022-01-18 10:10:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][960/1251]	eta 0:10:44 lr 0.000978	time 2.7537 (2.2132)	loss 4.3876 (4.2170)	grad_norm 1.1816 (1.1761)	
[2022-01-18 10:10:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][970/1251]	eta 0:10:21 lr 0.000978	time 1.9145 (2.2113)	loss 4.9696 (4.2166)	grad_norm 1.4305 (1.1767)	
[2022-01-18 10:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][980/1251]	eta 0:09:58 lr 0.000978	time 2.1272 (2.2095)	loss 3.4182 (4.2157)	grad_norm 1.0941 (1.1781)	
[2022-01-18 10:11:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][990/1251]	eta 0:09:36 lr 0.000978	time 2.2813 (2.2072)	loss 4.0961 (4.2165)	grad_norm 1.4437 (1.1785)	
[2022-01-18 10:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1000/1251]	eta 0:09:13 lr 0.000978	time 2.1752 (2.2059)	loss 3.7932 (4.2160)	grad_norm 1.1003 (1.1790)	
[2022-01-18 10:11:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1010/1251]	eta 0:08:51 lr 0.000978	time 2.0129 (2.2047)	loss 4.1949 (4.2162)	grad_norm 1.1288 (1.1783)	
[2022-01-18 10:12:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1020/1251]	eta 0:08:29 lr 0.000978	time 2.2816 (2.2040)	loss 4.8793 (4.2198)	grad_norm 1.5462 (1.1792)	
[2022-01-18 10:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1030/1251]	eta 0:08:07 lr 0.000978	time 2.8195 (2.2051)	loss 4.5593 (4.2182)	grad_norm 1.2977 (1.1788)	
[2022-01-18 10:12:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1040/1251]	eta 0:07:45 lr 0.000978	time 2.8976 (2.2068)	loss 4.8488 (4.2198)	grad_norm 1.9145 (1.1791)	
[2022-01-18 10:13:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1050/1251]	eta 0:07:23 lr 0.000978	time 3.0403 (2.2082)	loss 4.4028 (4.2180)	grad_norm 1.1631 (1.1790)	
[2022-01-18 10:13:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1060/1251]	eta 0:07:01 lr 0.000978	time 2.1748 (2.2076)	loss 4.8586 (4.2170)	grad_norm 1.1805 (1.1784)	
[2022-01-18 10:14:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1070/1251]	eta 0:06:39 lr 0.000978	time 2.4077 (2.2074)	loss 3.3842 (4.2156)	grad_norm 1.7196 (1.1790)	
[2022-01-18 10:14:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1080/1251]	eta 0:06:17 lr 0.000978	time 2.1579 (2.2073)	loss 4.9934 (4.2145)	grad_norm 1.2880 (1.1792)	
[2022-01-18 10:14:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1090/1251]	eta 0:05:55 lr 0.000978	time 2.5338 (2.2063)	loss 4.3721 (4.2131)	grad_norm 0.9919 (1.1785)	
[2022-01-18 10:15:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1100/1251]	eta 0:05:33 lr 0.000978	time 2.2044 (2.2058)	loss 4.2934 (4.2130)	grad_norm 0.9796 (1.1775)	
[2022-01-18 10:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1110/1251]	eta 0:05:11 lr 0.000978	time 2.2949 (2.2059)	loss 4.7854 (4.2130)	grad_norm 1.1604 (1.1768)	
[2022-01-18 10:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1120/1251]	eta 0:04:49 lr 0.000978	time 3.0551 (2.2064)	loss 4.2458 (4.2117)	grad_norm 1.0578 (1.1760)	
[2022-01-18 10:16:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1130/1251]	eta 0:04:27 lr 0.000977	time 2.7987 (2.2069)	loss 3.8182 (4.2134)	grad_norm 1.3727 (1.1754)	
[2022-01-18 10:16:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1140/1251]	eta 0:04:04 lr 0.000977	time 2.3408 (2.2066)	loss 4.4714 (4.2133)	grad_norm 1.0634 (1.1748)	
[2022-01-18 10:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1150/1251]	eta 0:03:42 lr 0.000977	time 1.7876 (2.2052)	loss 3.8517 (4.2140)	grad_norm 1.0766 (1.1745)	
[2022-01-18 10:17:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1160/1251]	eta 0:03:20 lr 0.000977	time 3.1667 (2.2055)	loss 4.0258 (4.2135)	grad_norm 1.0843 (1.1742)	
[2022-01-18 10:17:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1170/1251]	eta 0:02:58 lr 0.000977	time 2.2065 (2.2049)	loss 4.9484 (4.2135)	grad_norm 1.2201 (1.1738)	
[2022-01-18 10:18:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1180/1251]	eta 0:02:36 lr 0.000977	time 1.7578 (2.2044)	loss 4.4281 (4.2135)	grad_norm 1.1455 (1.1740)	
[2022-01-18 10:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1190/1251]	eta 0:02:14 lr 0.000977	time 1.9084 (2.2031)	loss 3.3641 (4.2124)	grad_norm 1.0742 (1.1748)	
[2022-01-18 10:18:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1200/1251]	eta 0:01:52 lr 0.000977	time 2.8495 (2.2037)	loss 4.3732 (4.2111)	grad_norm 1.2260 (1.1744)	
[2022-01-18 10:19:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1210/1251]	eta 0:01:30 lr 0.000977	time 2.5024 (2.2037)	loss 3.4537 (4.2102)	grad_norm 1.2485 (1.1746)	
[2022-01-18 10:19:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1220/1251]	eta 0:01:08 lr 0.000977	time 1.7912 (2.2037)	loss 3.9366 (4.2113)	grad_norm 1.1742 (1.1751)	
[2022-01-18 10:19:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1230/1251]	eta 0:00:46 lr 0.000977	time 2.4760 (2.2039)	loss 4.6416 (4.2118)	grad_norm 1.0417 (1.1742)	
[2022-01-18 10:20:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1240/1251]	eta 0:00:24 lr 0.000977	time 1.5133 (2.2021)	loss 4.6937 (4.2135)	grad_norm 0.8788 (1.1734)	
[2022-01-18 10:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [28/300][1250/1251]	eta 0:00:02 lr 0.000977	time 1.2143 (2.1969)	loss 3.9600 (4.2157)	grad_norm 1.3942 (1.1733)	
[2022-01-18 10:20:30 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 28 training takes 0:45:48
[2022-01-18 10:20:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.364 (18.364)	Loss 1.6176 (1.6176)	Acc@1 63.672 (63.672)	Acc@5 86.523 (86.523)	
[2022-01-18 10:21:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.470 (3.363)	Loss 1.5846 (1.5558)	Acc@1 64.453 (65.057)	Acc@5 87.109 (87.012)	
[2022-01-18 10:21:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.967 (2.555)	Loss 1.4927 (1.5454)	Acc@1 65.820 (65.007)	Acc@5 86.523 (87.058)	
[2022-01-18 10:21:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.320 (2.357)	Loss 1.5134 (1.5348)	Acc@1 65.137 (65.354)	Acc@5 87.207 (87.172)	
[2022-01-18 10:21:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.618 (2.184)	Loss 1.5809 (1.5432)	Acc@1 65.137 (65.046)	Acc@5 86.816 (87.036)	
[2022-01-18 10:22:07 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 65.086 Acc@5 87.026
[2022-01-18 10:22:07 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 65.1%
[2022-01-18 10:22:07 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 65.09%
[2022-01-18 10:22:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][0/1251]	eta 7:34:07 lr 0.000977	time 21.7808 (21.7808)	loss 4.5887 (4.5887)	grad_norm 1.0561 (1.0561)	
[2022-01-18 10:22:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][10/1251]	eta 1:22:54 lr 0.000977	time 2.2470 (4.0088)	loss 4.2140 (4.3482)	grad_norm 1.1759 (1.0693)	
[2022-01-18 10:23:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][20/1251]	eta 1:05:05 lr 0.000977	time 1.9305 (3.1724)	loss 4.4178 (4.1151)	grad_norm 1.3344 (1.1484)	
[2022-01-18 10:23:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][30/1251]	eta 0:57:54 lr 0.000977	time 1.4104 (2.8459)	loss 3.9203 (4.1397)	grad_norm 0.9752 (1.1295)	
[2022-01-18 10:23:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][40/1251]	eta 0:55:08 lr 0.000977	time 3.7262 (2.7323)	loss 4.9926 (4.1256)	grad_norm 1.0834 (1.1539)	
[2022-01-18 10:24:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][50/1251]	eta 0:52:40 lr 0.000977	time 1.7242 (2.6312)	loss 3.0520 (4.1108)	grad_norm 1.1770 (1.1469)	
[2022-01-18 10:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][60/1251]	eta 0:50:43 lr 0.000977	time 2.3386 (2.5551)	loss 4.5249 (4.0751)	grad_norm 0.9661 (1.1458)	
[2022-01-18 10:25:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][70/1251]	eta 0:49:00 lr 0.000977	time 1.7202 (2.4902)	loss 3.5798 (4.0751)	grad_norm 1.1521 (1.1482)	
[2022-01-18 10:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][80/1251]	eta 0:47:57 lr 0.000977	time 3.0468 (2.4572)	loss 4.8652 (4.1023)	grad_norm 1.1379 (1.1603)	
[2022-01-18 10:25:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][90/1251]	eta 0:46:45 lr 0.000977	time 1.5745 (2.4165)	loss 4.3879 (4.1036)	grad_norm 1.1266 (1.1675)	
[2022-01-18 10:26:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][100/1251]	eta 0:45:35 lr 0.000977	time 2.2530 (2.3766)	loss 4.7167 (4.1107)	grad_norm 1.1888 (1.1703)	
[2022-01-18 10:26:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][110/1251]	eta 0:44:51 lr 0.000977	time 2.5103 (2.3593)	loss 3.6944 (4.0960)	grad_norm 1.2332 (1.1731)	
[2022-01-18 10:26:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][120/1251]	eta 0:44:14 lr 0.000977	time 3.1068 (2.3469)	loss 4.7103 (4.1283)	grad_norm 1.2585 (1.1709)	
[2022-01-18 10:27:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][130/1251]	eta 0:43:36 lr 0.000977	time 1.7881 (2.3343)	loss 4.8951 (4.1416)	grad_norm 1.1381 (1.1680)	
[2022-01-18 10:27:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][140/1251]	eta 0:43:03 lr 0.000977	time 1.6664 (2.3255)	loss 5.0359 (4.1249)	grad_norm 1.4293 (1.1633)	
[2022-01-18 10:27:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][150/1251]	eta 0:42:29 lr 0.000977	time 1.9096 (2.3158)	loss 4.2355 (4.1293)	grad_norm 1.1855 (1.1633)	
[2022-01-18 10:28:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][160/1251]	eta 0:42:04 lr 0.000977	time 2.9632 (2.3135)	loss 4.4774 (4.1558)	grad_norm 1.1201 (1.1597)	
[2022-01-18 10:28:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][170/1251]	eta 0:41:28 lr 0.000977	time 1.6809 (2.3022)	loss 3.1318 (4.1590)	grad_norm 1.5816 (1.1618)	
[2022-01-18 10:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][180/1251]	eta 0:40:56 lr 0.000977	time 1.8933 (2.2937)	loss 3.4121 (4.1583)	grad_norm 1.2676 (1.1670)	
[2022-01-18 10:29:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][190/1251]	eta 0:40:30 lr 0.000977	time 2.4295 (2.2906)	loss 4.6886 (4.1502)	grad_norm 1.1018 (1.1661)	
[2022-01-18 10:29:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][200/1251]	eta 0:40:06 lr 0.000977	time 2.0780 (2.2896)	loss 3.3021 (4.1353)	grad_norm 0.9962 (1.1613)	
[2022-01-18 10:30:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][210/1251]	eta 0:39:44 lr 0.000977	time 1.8020 (2.2902)	loss 3.5424 (4.1378)	grad_norm 1.0140 (1.1585)	
[2022-01-18 10:30:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][220/1251]	eta 0:39:19 lr 0.000977	time 2.5946 (2.2884)	loss 3.2195 (4.1482)	grad_norm 0.9759 (1.1570)	
[2022-01-18 10:30:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][230/1251]	eta 0:38:46 lr 0.000977	time 1.5800 (2.2783)	loss 4.1973 (4.1562)	grad_norm 1.5202 (1.1588)	
[2022-01-18 10:31:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][240/1251]	eta 0:38:12 lr 0.000977	time 1.8762 (2.2675)	loss 4.3171 (4.1667)	grad_norm 1.1485 (1.1585)	
[2022-01-18 10:31:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][250/1251]	eta 0:37:38 lr 0.000977	time 2.2662 (2.2563)	loss 4.3101 (4.1676)	grad_norm 1.1357 (1.1590)	
[2022-01-18 10:31:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][260/1251]	eta 0:37:08 lr 0.000977	time 2.3169 (2.2490)	loss 4.4325 (4.1631)	grad_norm 0.8490 (1.1579)	
[2022-01-18 10:32:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][270/1251]	eta 0:36:40 lr 0.000977	time 2.7812 (2.2427)	loss 3.9574 (4.1683)	grad_norm 0.9961 (1.1582)	
[2022-01-18 10:32:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][280/1251]	eta 0:36:21 lr 0.000977	time 3.1337 (2.2470)	loss 3.0934 (4.1605)	grad_norm 1.2235 (1.1612)	
[2022-01-18 10:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][290/1251]	eta 0:35:59 lr 0.000977	time 2.9059 (2.2476)	loss 4.8080 (4.1622)	grad_norm 1.0743 (1.1637)	
[2022-01-18 10:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][300/1251]	eta 0:35:39 lr 0.000977	time 2.5564 (2.2502)	loss 4.2447 (4.1613)	grad_norm 0.8855 (1.1637)	
[2022-01-18 10:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][310/1251]	eta 0:35:15 lr 0.000977	time 2.0434 (2.2486)	loss 4.8455 (4.1713)	grad_norm 1.1026 (1.1627)	
[2022-01-18 10:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][320/1251]	eta 0:34:53 lr 0.000977	time 2.4365 (2.2488)	loss 4.9958 (4.1744)	grad_norm 1.3304 (1.1627)	
[2022-01-18 10:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][330/1251]	eta 0:34:33 lr 0.000977	time 2.6359 (2.2517)	loss 4.6648 (4.1784)	grad_norm 1.5318 (1.1634)	
[2022-01-18 10:34:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][340/1251]	eta 0:34:08 lr 0.000977	time 2.2946 (2.2482)	loss 3.9036 (4.1780)	grad_norm 1.4305 (1.1644)	
[2022-01-18 10:35:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][350/1251]	eta 0:33:41 lr 0.000977	time 2.1587 (2.2434)	loss 4.4470 (4.1742)	grad_norm 1.0771 (1.1634)	
[2022-01-18 10:35:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][360/1251]	eta 0:33:12 lr 0.000977	time 2.7259 (2.2359)	loss 5.0809 (4.1779)	grad_norm 1.3145 (1.1638)	
[2022-01-18 10:35:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][370/1251]	eta 0:32:43 lr 0.000977	time 1.9463 (2.2290)	loss 5.0513 (4.1761)	grad_norm 1.2422 (1.1617)	
[2022-01-18 10:36:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][380/1251]	eta 0:32:18 lr 0.000977	time 2.1708 (2.2254)	loss 4.2362 (4.1837)	grad_norm 1.1074 (1.1615)	
[2022-01-18 10:36:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][390/1251]	eta 0:31:52 lr 0.000977	time 1.9952 (2.2214)	loss 4.4979 (4.1881)	grad_norm 1.1098 (1.1622)	
[2022-01-18 10:36:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][400/1251]	eta 0:31:30 lr 0.000977	time 1.8999 (2.2210)	loss 4.0129 (4.1829)	grad_norm 1.2205 (1.1629)	
[2022-01-18 10:37:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][410/1251]	eta 0:31:03 lr 0.000977	time 1.9010 (2.2164)	loss 4.8145 (4.1836)	grad_norm 1.0154 (1.1623)	
[2022-01-18 10:37:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][420/1251]	eta 0:30:43 lr 0.000977	time 2.5646 (2.2184)	loss 4.6867 (4.1799)	grad_norm 1.0576 (1.1600)	
[2022-01-18 10:38:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][430/1251]	eta 0:30:24 lr 0.000977	time 2.2370 (2.2219)	loss 4.5373 (4.1795)	grad_norm 1.0441 (1.1594)	
[2022-01-18 10:38:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][440/1251]	eta 0:30:08 lr 0.000977	time 2.0786 (2.2301)	loss 3.4277 (4.1764)	grad_norm 1.1325 (1.1579)	
[2022-01-18 10:38:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][450/1251]	eta 0:29:47 lr 0.000977	time 2.2702 (2.2320)	loss 3.1500 (4.1771)	grad_norm 0.9470 (1.1558)	
[2022-01-18 10:39:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][460/1251]	eta 0:29:26 lr 0.000977	time 2.4149 (2.2333)	loss 4.2625 (4.1741)	grad_norm 1.1121 (1.1565)	
[2022-01-18 10:39:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][470/1251]	eta 0:29:03 lr 0.000977	time 1.7596 (2.2319)	loss 5.1004 (4.1755)	grad_norm 1.1842 (1.1579)	
[2022-01-18 10:39:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][480/1251]	eta 0:28:36 lr 0.000977	time 1.8610 (2.2258)	loss 4.6357 (4.1843)	grad_norm 1.7451 (1.1617)	
[2022-01-18 10:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][490/1251]	eta 0:28:08 lr 0.000977	time 1.8762 (2.2192)	loss 3.9913 (4.1866)	grad_norm 1.1573 (1.1631)	
[2022-01-18 10:40:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][500/1251]	eta 0:27:43 lr 0.000977	time 1.5474 (2.2150)	loss 3.4490 (4.1848)	grad_norm 0.9732 (1.1642)	
[2022-01-18 10:40:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][510/1251]	eta 0:27:20 lr 0.000977	time 2.2825 (2.2144)	loss 4.7759 (4.1840)	grad_norm 1.1363 (1.1627)	
[2022-01-18 10:41:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][520/1251]	eta 0:26:58 lr 0.000977	time 2.1809 (2.2140)	loss 4.7679 (4.1803)	grad_norm 1.0425 (1.1611)	
[2022-01-18 10:41:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][530/1251]	eta 0:26:36 lr 0.000977	time 2.1618 (2.2139)	loss 4.3910 (4.1791)	grad_norm 0.9405 (1.1604)	
[2022-01-18 10:42:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][540/1251]	eta 0:26:15 lr 0.000977	time 2.9169 (2.2161)	loss 4.3146 (4.1750)	grad_norm 1.0887 (1.1616)	
[2022-01-18 10:42:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][550/1251]	eta 0:25:54 lr 0.000977	time 2.5347 (2.2176)	loss 3.3959 (4.1787)	grad_norm 1.2009 (1.1603)	
[2022-01-18 10:42:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][560/1251]	eta 0:25:31 lr 0.000977	time 1.8556 (2.2164)	loss 4.5366 (4.1781)	grad_norm 1.2837 (1.1631)	
[2022-01-18 10:43:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][570/1251]	eta 0:25:11 lr 0.000977	time 2.6274 (2.2198)	loss 4.5452 (4.1799)	grad_norm 1.7134 (1.1643)	
[2022-01-18 10:43:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][580/1251]	eta 0:24:49 lr 0.000977	time 2.1702 (2.2193)	loss 3.9166 (4.1776)	grad_norm 1.3577 (1.1644)	
[2022-01-18 10:43:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][590/1251]	eta 0:24:26 lr 0.000977	time 2.2611 (2.2190)	loss 3.6528 (4.1812)	grad_norm 1.3343 (1.1641)	
[2022-01-18 10:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][600/1251]	eta 0:24:04 lr 0.000977	time 2.1884 (2.2195)	loss 4.5066 (4.1820)	grad_norm 0.9909 (1.1644)	
[2022-01-18 10:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][610/1251]	eta 0:23:41 lr 0.000977	time 2.3275 (2.2183)	loss 5.0940 (4.1863)	grad_norm 1.2648 (1.1664)	
[2022-01-18 10:45:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][620/1251]	eta 0:23:17 lr 0.000977	time 1.9588 (2.2144)	loss 4.4217 (4.1839)	grad_norm 1.0958 (1.1646)	
[2022-01-18 10:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][630/1251]	eta 0:22:54 lr 0.000977	time 2.2363 (2.2140)	loss 4.0554 (4.1821)	grad_norm 1.3536 (1.1652)	
[2022-01-18 10:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][640/1251]	eta 0:22:32 lr 0.000977	time 1.8985 (2.2138)	loss 3.4594 (4.1830)	grad_norm 1.2318 (1.1654)	
[2022-01-18 10:46:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][650/1251]	eta 0:22:10 lr 0.000977	time 2.3531 (2.2141)	loss 5.2508 (4.1836)	grad_norm 1.1226 (1.1664)	
[2022-01-18 10:46:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][660/1251]	eta 0:21:49 lr 0.000977	time 2.2095 (2.2152)	loss 3.6283 (4.1860)	grad_norm 1.2329 (1.1679)	
[2022-01-18 10:46:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][670/1251]	eta 0:21:27 lr 0.000977	time 1.8863 (2.2152)	loss 3.9771 (4.1828)	grad_norm 1.2046 (1.1685)	
[2022-01-18 10:47:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][680/1251]	eta 0:21:04 lr 0.000976	time 1.9866 (2.2141)	loss 5.0303 (4.1868)	grad_norm 1.2487 (1.1680)	
[2022-01-18 10:47:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][690/1251]	eta 0:20:41 lr 0.000976	time 2.2667 (2.2126)	loss 3.7860 (4.1889)	grad_norm 1.2281 (1.1681)	
[2022-01-18 10:47:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][700/1251]	eta 0:20:17 lr 0.000976	time 1.9437 (2.2103)	loss 4.7352 (4.1900)	grad_norm 1.0480 (1.1664)	
[2022-01-18 10:48:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][710/1251]	eta 0:19:54 lr 0.000976	time 1.5448 (2.2083)	loss 4.3589 (4.1928)	grad_norm 1.0073 (1.1649)	
[2022-01-18 10:48:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][720/1251]	eta 0:19:32 lr 0.000976	time 2.2049 (2.2089)	loss 4.2560 (4.1934)	grad_norm 1.0369 (1.1649)	
[2022-01-18 10:49:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][730/1251]	eta 0:19:11 lr 0.000976	time 2.1398 (2.2094)	loss 3.1366 (4.1933)	grad_norm 1.4303 (1.1658)	
[2022-01-18 10:49:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][740/1251]	eta 0:18:48 lr 0.000976	time 1.8133 (2.2084)	loss 4.2351 (4.1921)	grad_norm 1.1188 (1.1667)	
[2022-01-18 10:49:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][750/1251]	eta 0:18:27 lr 0.000976	time 2.5104 (2.2111)	loss 4.8904 (4.1905)	grad_norm 1.2725 (1.1668)	
[2022-01-18 10:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][760/1251]	eta 0:18:05 lr 0.000976	time 1.5974 (2.2107)	loss 3.7168 (4.1920)	grad_norm 1.4125 (1.1668)	
[2022-01-18 10:50:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][770/1251]	eta 0:17:43 lr 0.000976	time 2.0981 (2.2110)	loss 4.4941 (4.1907)	grad_norm 1.4506 (1.1665)	
[2022-01-18 10:50:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][780/1251]	eta 0:17:19 lr 0.000976	time 1.6478 (2.2079)	loss 4.9591 (4.1924)	grad_norm 1.1982 (1.1666)	
[2022-01-18 10:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][790/1251]	eta 0:16:56 lr 0.000976	time 1.8468 (2.2053)	loss 4.1635 (4.1906)	grad_norm 1.1649 (1.1672)	
[2022-01-18 10:51:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][800/1251]	eta 0:16:32 lr 0.000976	time 1.5562 (2.2013)	loss 4.5412 (4.1936)	grad_norm 1.0727 (1.1664)	
[2022-01-18 10:51:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][810/1251]	eta 0:16:10 lr 0.000976	time 1.8623 (2.2004)	loss 4.7834 (4.1926)	grad_norm 1.0569 (1.1650)	
[2022-01-18 10:52:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][820/1251]	eta 0:15:48 lr 0.000976	time 1.7698 (2.2002)	loss 4.8152 (4.1919)	grad_norm 1.0613 (1.1662)	
[2022-01-18 10:52:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][830/1251]	eta 0:15:27 lr 0.000976	time 2.4833 (2.2031)	loss 3.6378 (4.1917)	grad_norm 1.0000 (1.1644)	
[2022-01-18 10:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][840/1251]	eta 0:15:06 lr 0.000976	time 1.8535 (2.2060)	loss 4.4310 (4.1922)	grad_norm 0.8716 (1.1636)	
[2022-01-18 10:53:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][850/1251]	eta 0:14:44 lr 0.000976	time 1.7743 (2.2053)	loss 4.4426 (4.1904)	grad_norm 1.3152 (1.1624)	
[2022-01-18 10:53:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][860/1251]	eta 0:14:21 lr 0.000976	time 1.7443 (2.2044)	loss 4.0417 (4.1931)	grad_norm 1.1528 (1.1621)	
[2022-01-18 10:54:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][870/1251]	eta 0:13:59 lr 0.000976	time 1.8790 (2.2040)	loss 4.5442 (4.1914)	grad_norm 1.3588 (1.1615)	
[2022-01-18 10:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][880/1251]	eta 0:13:37 lr 0.000976	time 1.9759 (2.2042)	loss 3.4069 (4.1924)	grad_norm 1.0560 (1.1617)	
[2022-01-18 10:54:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][890/1251]	eta 0:13:15 lr 0.000976	time 1.8241 (2.2036)	loss 4.6851 (4.1925)	grad_norm 0.9996 (1.1616)	
[2022-01-18 10:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][900/1251]	eta 0:12:53 lr 0.000976	time 1.9355 (2.2030)	loss 4.8213 (4.1962)	grad_norm 1.0486 (1.1609)	
[2022-01-18 10:55:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][910/1251]	eta 0:12:30 lr 0.000976	time 2.1561 (2.2011)	loss 3.8583 (4.1945)	grad_norm 1.2058 (1.1610)	
[2022-01-18 10:55:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][920/1251]	eta 0:12:08 lr 0.000976	time 2.6833 (2.2015)	loss 4.3259 (4.1917)	grad_norm 1.0692 (1.1611)	
[2022-01-18 10:56:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][930/1251]	eta 0:11:47 lr 0.000976	time 2.1441 (2.2032)	loss 4.1353 (4.1879)	grad_norm 1.3846 (1.1610)	
[2022-01-18 10:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][940/1251]	eta 0:11:25 lr 0.000976	time 1.8439 (2.2045)	loss 3.6429 (4.1892)	grad_norm 1.4698 (1.1621)	
[2022-01-18 10:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][950/1251]	eta 0:11:03 lr 0.000976	time 1.9115 (2.2040)	loss 3.7231 (4.1891)	grad_norm 1.3234 (1.1619)	
[2022-01-18 10:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][960/1251]	eta 0:10:41 lr 0.000976	time 2.5611 (2.2030)	loss 4.6683 (4.1899)	grad_norm 1.1605 (1.1622)	
[2022-01-18 10:57:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][970/1251]	eta 0:10:18 lr 0.000976	time 1.6629 (2.2000)	loss 5.0217 (4.1894)	grad_norm 0.9570 (1.1622)	
[2022-01-18 10:58:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][980/1251]	eta 0:09:55 lr 0.000976	time 1.7281 (2.1982)	loss 5.0180 (4.1895)	grad_norm 1.1121 (1.1613)	
[2022-01-18 10:58:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][990/1251]	eta 0:09:33 lr 0.000976	time 2.0271 (2.1969)	loss 4.8587 (4.1896)	grad_norm 1.4481 (1.1626)	
[2022-01-18 10:58:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1000/1251]	eta 0:09:11 lr 0.000976	time 2.1979 (2.1982)	loss 5.2169 (4.1912)	grad_norm 1.3638 (1.1636)	
[2022-01-18 10:59:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1010/1251]	eta 0:08:49 lr 0.000976	time 1.5901 (2.1975)	loss 4.3641 (4.1923)	grad_norm 0.9760 (1.1637)	
[2022-01-18 10:59:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1020/1251]	eta 0:08:27 lr 0.000976	time 1.8209 (2.1976)	loss 3.7568 (4.1912)	grad_norm 1.2257 (1.1637)	
[2022-01-18 10:59:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1030/1251]	eta 0:08:06 lr 0.000976	time 2.3527 (2.1995)	loss 4.9606 (4.1932)	grad_norm 1.3054 (1.1650)	
[2022-01-18 11:00:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1040/1251]	eta 0:07:44 lr 0.000976	time 1.8403 (2.2008)	loss 3.5810 (4.1943)	grad_norm 1.1952 (1.1656)	
[2022-01-18 11:00:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1050/1251]	eta 0:07:22 lr 0.000976	time 1.5729 (2.2007)	loss 4.9873 (4.1975)	grad_norm 1.0091 (1.1658)	
[2022-01-18 11:01:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1060/1251]	eta 0:07:00 lr 0.000976	time 1.8977 (2.1994)	loss 4.5602 (4.1948)	grad_norm 1.0865 (1.1657)	
[2022-01-18 11:01:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1070/1251]	eta 0:06:38 lr 0.000976	time 3.0418 (2.1993)	loss 4.2021 (4.1969)	grad_norm 1.1166 (1.1647)	
[2022-01-18 11:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1080/1251]	eta 0:06:16 lr 0.000976	time 1.8367 (2.1998)	loss 4.2337 (4.1975)	grad_norm 1.2781 (1.1645)	
[2022-01-18 11:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1090/1251]	eta 0:05:54 lr 0.000976	time 1.7933 (2.2005)	loss 3.7646 (4.1960)	grad_norm 1.4554 (1.1651)	
[2022-01-18 11:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1100/1251]	eta 0:05:32 lr 0.000976	time 1.9816 (2.1998)	loss 4.1625 (4.1944)	grad_norm 1.1457 (1.1641)	
[2022-01-18 11:02:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1110/1251]	eta 0:05:10 lr 0.000976	time 2.4997 (2.1999)	loss 4.7579 (4.1965)	grad_norm 1.1263 (1.1640)	
[2022-01-18 11:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1120/1251]	eta 0:04:47 lr 0.000976	time 1.8108 (2.1981)	loss 3.3650 (4.1972)	grad_norm 1.3705 (1.1640)	
[2022-01-18 11:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1130/1251]	eta 0:04:25 lr 0.000976	time 1.7224 (2.1975)	loss 4.4851 (4.1973)	grad_norm 1.0045 (1.1636)	
[2022-01-18 11:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1140/1251]	eta 0:04:04 lr 0.000976	time 2.7079 (2.1986)	loss 5.1332 (4.1984)	grad_norm 1.1630 (1.1634)	
[2022-01-18 11:04:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1150/1251]	eta 0:03:41 lr 0.000976	time 1.7518 (2.1975)	loss 3.6012 (4.1976)	grad_norm 1.2782 (1.1635)	
[2022-01-18 11:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1160/1251]	eta 0:03:19 lr 0.000976	time 1.8894 (2.1969)	loss 4.9452 (4.1969)	grad_norm 1.4336 (1.1637)	
[2022-01-18 11:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1170/1251]	eta 0:02:57 lr 0.000976	time 2.1001 (2.1967)	loss 2.9813 (4.1963)	grad_norm 1.1794 (1.1632)	
[2022-01-18 11:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1180/1251]	eta 0:02:36 lr 0.000976	time 2.9688 (2.1977)	loss 4.4067 (4.1958)	grad_norm 1.0676 (1.1633)	
[2022-01-18 11:05:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1190/1251]	eta 0:02:14 lr 0.000976	time 1.9159 (2.1983)	loss 3.4832 (4.1956)	grad_norm 1.2882 (1.1624)	
[2022-01-18 11:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1200/1251]	eta 0:01:52 lr 0.000976	time 2.2187 (2.1972)	loss 4.5748 (4.1949)	grad_norm 1.1143 (1.1621)	
[2022-01-18 11:06:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1210/1251]	eta 0:01:30 lr 0.000976	time 2.3329 (2.1960)	loss 3.0770 (4.1948)	grad_norm 1.0895 (1.1623)	
[2022-01-18 11:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1220/1251]	eta 0:01:08 lr 0.000976	time 2.2055 (2.1973)	loss 3.8765 (4.1931)	grad_norm 1.4732 (1.1630)	
[2022-01-18 11:07:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1230/1251]	eta 0:00:46 lr 0.000976	time 1.7161 (2.1981)	loss 5.2459 (4.1937)	grad_norm 1.2970 (1.1634)	
[2022-01-18 11:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1240/1251]	eta 0:00:24 lr 0.000976	time 1.9346 (2.1964)	loss 4.7413 (4.1934)	grad_norm 0.9264 (1.1630)	
[2022-01-18 11:07:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [29/300][1250/1251]	eta 0:00:02 lr 0.000976	time 1.1735 (2.1901)	loss 4.6124 (4.1932)	grad_norm 1.1593 (1.1621)	
[2022-01-18 11:07:47 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 29 training takes 0:45:40
[2022-01-18 11:08:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.620 (18.620)	Loss 1.5340 (1.5340)	Acc@1 66.895 (66.895)	Acc@5 86.816 (86.816)	
[2022-01-18 11:08:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.615 (3.299)	Loss 1.5557 (1.5529)	Acc@1 65.918 (65.243)	Acc@5 87.402 (87.118)	
[2022-01-18 11:08:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.618 (2.549)	Loss 1.4893 (1.5447)	Acc@1 67.676 (65.485)	Acc@5 88.086 (87.384)	
[2022-01-18 11:08:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.933 (2.263)	Loss 1.5947 (1.5496)	Acc@1 65.332 (65.427)	Acc@5 86.426 (87.210)	
[2022-01-18 11:09:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.437 (2.149)	Loss 1.5835 (1.5456)	Acc@1 63.477 (65.518)	Acc@5 86.621 (87.314)	
[2022-01-18 11:09:22 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 65.656 Acc@5 87.426
[2022-01-18 11:09:22 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 65.7%
[2022-01-18 11:09:22 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 65.66%
[2022-01-18 11:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][0/1251]	eta 7:36:16 lr 0.000976	time 21.8835 (21.8835)	loss 4.9265 (4.9265)	grad_norm 1.1341 (1.1341)	
[2022-01-18 11:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][10/1251]	eta 1:23:43 lr 0.000976	time 1.8670 (4.0483)	loss 4.7184 (4.2486)	grad_norm 1.2265 (1.1089)	
[2022-01-18 11:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][20/1251]	eta 1:05:03 lr 0.000976	time 1.3747 (3.1707)	loss 4.5807 (4.2173)	grad_norm 1.0478 (1.1170)	
[2022-01-18 11:10:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][30/1251]	eta 0:58:24 lr 0.000976	time 1.9647 (2.8704)	loss 4.1840 (4.2126)	grad_norm 1.1258 (1.0985)	
[2022-01-18 11:11:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][40/1251]	eta 0:55:23 lr 0.000976	time 3.8804 (2.7442)	loss 2.9362 (4.1613)	grad_norm 1.0078 (1.1068)	
[2022-01-18 11:11:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][50/1251]	eta 0:52:32 lr 0.000976	time 2.0481 (2.6249)	loss 4.3181 (4.2029)	grad_norm 1.4279 (1.1332)	
[2022-01-18 11:11:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][60/1251]	eta 0:50:21 lr 0.000976	time 1.9289 (2.5371)	loss 4.9457 (4.2255)	grad_norm 0.9137 (1.1304)	
[2022-01-18 11:12:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][70/1251]	eta 0:48:51 lr 0.000976	time 2.2633 (2.4825)	loss 4.0085 (4.1708)	grad_norm 1.1714 (1.1521)	
[2022-01-18 11:12:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][80/1251]	eta 0:47:57 lr 0.000976	time 4.9827 (2.4571)	loss 4.4216 (4.1933)	grad_norm 1.1439 (1.1545)	
[2022-01-18 11:13:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][90/1251]	eta 0:47:02 lr 0.000976	time 1.4986 (2.4311)	loss 4.1200 (4.1712)	grad_norm 1.1623 (1.1600)	
[2022-01-18 11:13:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][100/1251]	eta 0:46:08 lr 0.000976	time 2.1176 (2.4055)	loss 3.3358 (4.1667)	grad_norm 1.0304 (1.1570)	
[2022-01-18 11:13:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][110/1251]	eta 0:45:18 lr 0.000976	time 2.1948 (2.3824)	loss 4.4873 (4.1952)	grad_norm 1.3383 (1.1613)	
[2022-01-18 11:14:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][120/1251]	eta 0:44:45 lr 0.000976	time 3.8981 (2.3741)	loss 3.3892 (4.2120)	grad_norm 2.2792 (1.1758)	
[2022-01-18 11:14:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][130/1251]	eta 0:44:00 lr 0.000976	time 1.6069 (2.3555)	loss 4.2494 (4.2131)	grad_norm 1.1542 (1.1734)	
[2022-01-18 11:14:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][140/1251]	eta 0:43:18 lr 0.000976	time 1.9097 (2.3389)	loss 4.5511 (4.2110)	grad_norm 1.1989 (1.1783)	
[2022-01-18 11:15:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][150/1251]	eta 0:42:54 lr 0.000976	time 2.7767 (2.3380)	loss 3.6520 (4.1934)	grad_norm 1.2512 (1.1796)	
[2022-01-18 11:15:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][160/1251]	eta 0:42:38 lr 0.000976	time 5.4882 (2.3448)	loss 4.2644 (4.2052)	grad_norm 0.9330 (1.1816)	
[2022-01-18 11:16:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][170/1251]	eta 0:42:09 lr 0.000976	time 1.8464 (2.3397)	loss 4.3741 (4.2085)	grad_norm 1.1399 (1.1801)	
[2022-01-18 11:16:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][180/1251]	eta 0:41:23 lr 0.000976	time 1.8987 (2.3186)	loss 3.3702 (4.2057)	grad_norm 1.1045 (1.1710)	
[2022-01-18 11:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][190/1251]	eta 0:40:41 lr 0.000976	time 1.5951 (2.3013)	loss 3.8300 (4.2174)	grad_norm 1.1279 (1.1725)	
[2022-01-18 11:17:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][200/1251]	eta 0:40:24 lr 0.000976	time 2.4060 (2.3069)	loss 5.1335 (4.2146)	grad_norm 1.3925 (1.1682)	
[2022-01-18 11:17:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][210/1251]	eta 0:39:51 lr 0.000976	time 2.2883 (2.2972)	loss 3.2791 (4.2062)	grad_norm 0.9007 (1.1674)	
[2022-01-18 11:17:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][220/1251]	eta 0:39:13 lr 0.000975	time 1.6770 (2.2823)	loss 3.0061 (4.1826)	grad_norm 1.0529 (1.1673)	
[2022-01-18 11:18:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][230/1251]	eta 0:38:42 lr 0.000975	time 2.2880 (2.2744)	loss 3.0912 (4.1806)	grad_norm 1.1453 (1.1647)	
[2022-01-18 11:18:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][240/1251]	eta 0:38:27 lr 0.000975	time 2.7217 (2.2819)	loss 3.6836 (4.1844)	grad_norm 1.1242 (1.1626)	
[2022-01-18 11:18:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][250/1251]	eta 0:38:05 lr 0.000975	time 2.2314 (2.2831)	loss 3.6480 (4.1838)	grad_norm 1.0481 (1.1622)	
[2022-01-18 11:19:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][260/1251]	eta 0:37:40 lr 0.000975	time 1.6515 (2.2809)	loss 4.4477 (4.1790)	grad_norm 1.4850 (1.1636)	
[2022-01-18 11:19:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][270/1251]	eta 0:37:14 lr 0.000975	time 2.2102 (2.2776)	loss 4.4795 (4.1931)	grad_norm 0.9825 (1.1680)	
[2022-01-18 11:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][280/1251]	eta 0:36:44 lr 0.000975	time 1.9027 (2.2704)	loss 4.6842 (4.1832)	grad_norm 1.1505 (1.1671)	
[2022-01-18 11:20:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][290/1251]	eta 0:36:12 lr 0.000975	time 1.9183 (2.2609)	loss 4.0060 (4.1808)	grad_norm 0.9714 (1.1655)	
[2022-01-18 11:20:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][300/1251]	eta 0:35:45 lr 0.000975	time 1.6779 (2.2562)	loss 4.0669 (4.1762)	grad_norm 1.1436 (1.1653)	
[2022-01-18 11:21:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][310/1251]	eta 0:35:19 lr 0.000975	time 1.9458 (2.2525)	loss 3.2848 (4.1722)	grad_norm 1.1105 (1.1662)	
[2022-01-18 11:21:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][320/1251]	eta 0:34:54 lr 0.000975	time 1.8927 (2.2498)	loss 3.7943 (4.1751)	grad_norm 0.9847 (1.1644)	
[2022-01-18 11:21:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][330/1251]	eta 0:34:27 lr 0.000975	time 2.1427 (2.2451)	loss 3.2482 (4.1835)	grad_norm 0.9708 (1.1611)	
[2022-01-18 11:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][340/1251]	eta 0:34:01 lr 0.000975	time 1.8898 (2.2411)	loss 4.5786 (4.1791)	grad_norm 0.9349 (1.1580)	
[2022-01-18 11:22:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][350/1251]	eta 0:33:42 lr 0.000975	time 2.5378 (2.2446)	loss 3.8910 (4.1844)	grad_norm 1.4271 (1.1610)	
[2022-01-18 11:22:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][360/1251]	eta 0:33:19 lr 0.000975	time 2.2759 (2.2442)	loss 4.8908 (4.1882)	grad_norm 1.0381 (1.1594)	
[2022-01-18 11:23:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][370/1251]	eta 0:32:57 lr 0.000975	time 1.7853 (2.2444)	loss 3.0574 (4.1822)	grad_norm 1.2201 (1.1622)	
[2022-01-18 11:23:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][380/1251]	eta 0:32:32 lr 0.000975	time 1.9576 (2.2421)	loss 3.3765 (4.1848)	grad_norm 1.1633 (1.1643)	
[2022-01-18 11:23:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][390/1251]	eta 0:32:08 lr 0.000975	time 2.2469 (2.2400)	loss 4.6697 (4.1860)	grad_norm 1.6022 (1.1675)	
[2022-01-18 11:24:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][400/1251]	eta 0:31:48 lr 0.000975	time 2.2297 (2.2423)	loss 4.5608 (4.1884)	grad_norm 1.0485 (1.1708)	
[2022-01-18 11:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][410/1251]	eta 0:31:24 lr 0.000975	time 1.8552 (2.2411)	loss 3.5872 (4.1812)	grad_norm 1.5330 (1.1688)	
[2022-01-18 11:25:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][420/1251]	eta 0:30:57 lr 0.000975	time 1.9201 (2.2357)	loss 4.5039 (4.1756)	grad_norm 0.9853 (1.1694)	
[2022-01-18 11:25:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][430/1251]	eta 0:30:31 lr 0.000975	time 2.2430 (2.2304)	loss 4.3293 (4.1742)	grad_norm 1.0136 (1.1681)	
[2022-01-18 11:25:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][440/1251]	eta 0:30:05 lr 0.000975	time 1.9670 (2.2268)	loss 4.1873 (4.1750)	grad_norm 1.2441 (1.1679)	
[2022-01-18 11:26:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][450/1251]	eta 0:29:52 lr 0.000975	time 2.4619 (2.2381)	loss 3.1809 (4.1732)	grad_norm 1.2172 (1.1668)	
[2022-01-18 11:26:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][460/1251]	eta 0:29:27 lr 0.000975	time 1.9329 (2.2347)	loss 3.9035 (4.1719)	grad_norm 1.3684 (1.1678)	
[2022-01-18 11:26:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][470/1251]	eta 0:29:04 lr 0.000975	time 1.8479 (2.2334)	loss 3.0703 (4.1737)	grad_norm 1.0645 (1.1674)	
[2022-01-18 11:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][480/1251]	eta 0:28:42 lr 0.000975	time 1.8892 (2.2336)	loss 4.3002 (4.1719)	grad_norm 0.9480 (1.1671)	
[2022-01-18 11:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][490/1251]	eta 0:28:23 lr 0.000975	time 1.7631 (2.2385)	loss 4.6979 (4.1710)	grad_norm 1.0275 (1.1648)	
[2022-01-18 11:28:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][500/1251]	eta 0:27:55 lr 0.000975	time 1.6078 (2.2312)	loss 3.0303 (4.1675)	grad_norm 1.0522 (1.1649)	
[2022-01-18 11:28:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][510/1251]	eta 0:27:32 lr 0.000975	time 1.9668 (2.2295)	loss 3.3485 (4.1659)	grad_norm 1.1537 (1.1658)	
[2022-01-18 11:28:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][520/1251]	eta 0:27:10 lr 0.000975	time 1.5973 (2.2307)	loss 3.3212 (4.1666)	grad_norm 1.2776 (1.1651)	
[2022-01-18 11:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][530/1251]	eta 0:26:49 lr 0.000975	time 1.9339 (2.2327)	loss 4.2908 (4.1672)	grad_norm 1.0525 (1.1627)	
[2022-01-18 11:29:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][540/1251]	eta 0:26:25 lr 0.000975	time 2.2092 (2.2304)	loss 4.7984 (4.1628)	grad_norm 1.0321 (1.1629)	
[2022-01-18 11:29:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][550/1251]	eta 0:25:59 lr 0.000975	time 2.0386 (2.2250)	loss 2.9739 (4.1618)	grad_norm 1.1003 (1.1628)	
[2022-01-18 11:30:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][560/1251]	eta 0:25:35 lr 0.000975	time 1.8425 (2.2218)	loss 5.1582 (4.1642)	grad_norm 1.0097 (1.1619)	
[2022-01-18 11:30:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][570/1251]	eta 0:25:14 lr 0.000975	time 1.5860 (2.2240)	loss 4.3913 (4.1696)	grad_norm 1.2015 (1.1611)	
[2022-01-18 11:30:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][580/1251]	eta 0:24:51 lr 0.000975	time 1.5861 (2.2235)	loss 4.7438 (4.1722)	grad_norm 1.1836 (1.1606)	
[2022-01-18 11:31:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][590/1251]	eta 0:24:29 lr 0.000975	time 1.8067 (2.2232)	loss 5.0148 (4.1741)	grad_norm 1.4856 (1.1615)	
[2022-01-18 11:31:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][600/1251]	eta 0:24:06 lr 0.000975	time 1.5482 (2.2224)	loss 2.9948 (4.1750)	grad_norm 1.1668 (1.1610)	
[2022-01-18 11:32:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][610/1251]	eta 0:23:45 lr 0.000975	time 1.6858 (2.2233)	loss 4.2886 (4.1760)	grad_norm 1.2784 (1.1619)	
[2022-01-18 11:32:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][620/1251]	eta 0:23:22 lr 0.000975	time 1.9254 (2.2222)	loss 4.7079 (4.1784)	grad_norm 1.3819 (1.1629)	
[2022-01-18 11:32:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][630/1251]	eta 0:22:59 lr 0.000975	time 1.7857 (2.2212)	loss 3.5216 (4.1801)	grad_norm 1.6295 (1.1638)	
[2022-01-18 11:33:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][640/1251]	eta 0:22:37 lr 0.000975	time 2.8474 (2.2215)	loss 4.0008 (4.1802)	grad_norm 1.1394 (1.1628)	
[2022-01-18 11:33:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][650/1251]	eta 0:22:14 lr 0.000975	time 2.5287 (2.2213)	loss 2.7636 (4.1769)	grad_norm 1.1864 (1.1626)	
[2022-01-18 11:33:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][660/1251]	eta 0:21:51 lr 0.000975	time 1.6402 (2.2192)	loss 4.5214 (4.1811)	grad_norm 0.9034 (1.1632)	
[2022-01-18 11:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][670/1251]	eta 0:21:28 lr 0.000975	time 1.8150 (2.2171)	loss 4.1884 (4.1803)	grad_norm 1.1200 (1.1623)	
[2022-01-18 11:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][680/1251]	eta 0:21:06 lr 0.000975	time 2.8054 (2.2172)	loss 4.0248 (4.1848)	grad_norm 1.1220 (1.1622)	
[2022-01-18 11:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][690/1251]	eta 0:20:43 lr 0.000975	time 1.8533 (2.2172)	loss 4.7020 (4.1831)	grad_norm 1.0684 (1.1632)	
[2022-01-18 11:35:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][700/1251]	eta 0:20:22 lr 0.000975	time 2.5399 (2.2179)	loss 3.9769 (4.1817)	grad_norm 1.4236 (1.1624)	
[2022-01-18 11:35:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][710/1251]	eta 0:19:59 lr 0.000975	time 2.2362 (2.2176)	loss 4.3461 (4.1845)	grad_norm 1.2069 (1.1617)	
[2022-01-18 11:36:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][720/1251]	eta 0:19:38 lr 0.000975	time 3.7462 (2.2193)	loss 3.9460 (4.1811)	grad_norm 1.1704 (1.1623)	
[2022-01-18 11:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][730/1251]	eta 0:19:15 lr 0.000975	time 1.8306 (2.2171)	loss 3.8419 (4.1854)	grad_norm 1.3540 (1.1627)	
[2022-01-18 11:36:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][740/1251]	eta 0:18:51 lr 0.000975	time 1.6673 (2.2141)	loss 4.9836 (4.1868)	grad_norm 0.9981 (1.1610)	
[2022-01-18 11:37:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][750/1251]	eta 0:18:27 lr 0.000975	time 1.9928 (2.2108)	loss 3.7963 (4.1875)	grad_norm 1.4879 (1.1613)	
[2022-01-18 11:37:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][760/1251]	eta 0:18:05 lr 0.000975	time 2.7755 (2.2113)	loss 3.5974 (4.1878)	grad_norm 1.5536 (1.1612)	
[2022-01-18 11:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][770/1251]	eta 0:17:43 lr 0.000975	time 2.5167 (2.2120)	loss 4.6320 (4.1855)	grad_norm 1.1821 (1.1618)	
[2022-01-18 11:38:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][780/1251]	eta 0:17:22 lr 0.000975	time 2.3585 (2.2139)	loss 4.0694 (4.1792)	grad_norm 0.9923 (1.1618)	
[2022-01-18 11:38:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][790/1251]	eta 0:17:00 lr 0.000975	time 1.5649 (2.2145)	loss 3.9312 (4.1780)	grad_norm 0.9722 (1.1615)	
[2022-01-18 11:38:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][800/1251]	eta 0:16:39 lr 0.000975	time 2.5787 (2.2158)	loss 4.2431 (4.1772)	grad_norm 0.9531 (1.1616)	
[2022-01-18 11:39:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][810/1251]	eta 0:16:16 lr 0.000975	time 2.5571 (2.2143)	loss 3.3730 (4.1771)	grad_norm 1.4161 (1.1624)	
[2022-01-18 11:39:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][820/1251]	eta 0:15:53 lr 0.000975	time 2.3548 (2.2120)	loss 4.2087 (4.1757)	grad_norm 1.2767 (1.1634)	
[2022-01-18 11:39:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][830/1251]	eta 0:15:30 lr 0.000975	time 2.2724 (2.2102)	loss 3.8527 (4.1762)	grad_norm 0.9529 (1.1617)	
[2022-01-18 11:40:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][840/1251]	eta 0:15:08 lr 0.000975	time 1.9559 (2.2095)	loss 4.0408 (4.1763)	grad_norm 1.2436 (1.1619)	
[2022-01-18 11:40:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][850/1251]	eta 0:14:45 lr 0.000975	time 2.4656 (2.2094)	loss 3.1348 (4.1754)	grad_norm 1.0609 (1.1620)	
[2022-01-18 11:41:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][860/1251]	eta 0:14:23 lr 0.000975	time 1.8641 (2.2096)	loss 4.7813 (4.1790)	grad_norm 1.0327 (1.1618)	
[2022-01-18 11:41:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][870/1251]	eta 0:14:01 lr 0.000975	time 2.0708 (2.2088)	loss 3.2447 (4.1763)	grad_norm 1.1923 (1.1614)	
[2022-01-18 11:41:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][880/1251]	eta 0:13:38 lr 0.000975	time 1.6868 (2.2069)	loss 4.2978 (4.1772)	grad_norm 1.1874 (1.1619)	
[2022-01-18 11:42:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][890/1251]	eta 0:13:16 lr 0.000975	time 2.1250 (2.2074)	loss 4.5123 (4.1754)	grad_norm 0.9917 (1.1625)	
[2022-01-18 11:42:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][900/1251]	eta 0:12:54 lr 0.000975	time 1.9442 (2.2071)	loss 3.7908 (4.1797)	grad_norm 1.0984 (1.1635)	
[2022-01-18 11:42:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][910/1251]	eta 0:12:32 lr 0.000975	time 2.1477 (2.2072)	loss 4.4631 (4.1805)	grad_norm 1.3143 (1.1636)	
[2022-01-18 11:43:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][920/1251]	eta 0:12:10 lr 0.000975	time 1.8847 (2.2068)	loss 3.8935 (4.1777)	grad_norm 1.0156 (1.1629)	
[2022-01-18 11:43:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][930/1251]	eta 0:11:48 lr 0.000975	time 1.7528 (2.2064)	loss 3.7750 (4.1763)	grad_norm 1.0938 (1.1628)	
[2022-01-18 11:43:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][940/1251]	eta 0:11:26 lr 0.000975	time 1.5576 (2.2065)	loss 4.1843 (4.1769)	grad_norm 1.1617 (1.1628)	
[2022-01-18 11:44:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][950/1251]	eta 0:11:05 lr 0.000975	time 2.6077 (2.2099)	loss 3.9103 (4.1782)	grad_norm 1.0025 (1.1621)	
[2022-01-18 11:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][960/1251]	eta 0:10:42 lr 0.000975	time 1.9249 (2.2094)	loss 4.6243 (4.1775)	grad_norm 1.5991 (1.1628)	
[2022-01-18 11:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][970/1251]	eta 0:10:20 lr 0.000975	time 1.7381 (2.2073)	loss 4.3238 (4.1768)	grad_norm 1.3013 (1.1630)	
[2022-01-18 11:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][980/1251]	eta 0:09:57 lr 0.000975	time 1.5099 (2.2042)	loss 4.7675 (4.1774)	grad_norm 1.1486 (1.1629)	
[2022-01-18 11:45:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][990/1251]	eta 0:09:35 lr 0.000974	time 2.1636 (2.2032)	loss 4.5426 (4.1808)	grad_norm 1.4047 (1.1631)	
[2022-01-18 11:46:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1000/1251]	eta 0:09:13 lr 0.000974	time 2.3717 (2.2048)	loss 4.2496 (4.1815)	grad_norm 0.9331 (1.1623)	
[2022-01-18 11:46:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1010/1251]	eta 0:08:51 lr 0.000974	time 1.8791 (2.2054)	loss 4.4932 (4.1794)	grad_norm 1.0102 (1.1620)	
[2022-01-18 11:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1020/1251]	eta 0:08:29 lr 0.000974	time 2.1138 (2.2065)	loss 4.0411 (4.1770)	grad_norm 1.1541 (1.1628)	
[2022-01-18 11:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1030/1251]	eta 0:08:08 lr 0.000974	time 2.6535 (2.2089)	loss 4.5940 (4.1771)	grad_norm 1.1656 (1.1628)	
[2022-01-18 11:47:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1040/1251]	eta 0:07:46 lr 0.000974	time 1.6030 (2.2096)	loss 4.1900 (4.1770)	grad_norm 1.4506 (1.1636)	
[2022-01-18 11:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1050/1251]	eta 0:07:23 lr 0.000974	time 1.8815 (2.2074)	loss 4.8732 (4.1776)	grad_norm 1.1442 (1.1633)	
[2022-01-18 11:48:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1060/1251]	eta 0:07:00 lr 0.000974	time 1.8980 (2.2039)	loss 4.5525 (4.1760)	grad_norm 1.1947 (1.1635)	
[2022-01-18 11:48:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1070/1251]	eta 0:06:38 lr 0.000974	time 1.8420 (2.2017)	loss 4.3824 (4.1743)	grad_norm 1.0437 (1.1638)	
[2022-01-18 11:49:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1080/1251]	eta 0:06:16 lr 0.000974	time 2.0394 (2.2020)	loss 3.9883 (4.1743)	grad_norm 1.0339 (1.1641)	
[2022-01-18 11:49:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1090/1251]	eta 0:05:54 lr 0.000974	time 2.1849 (2.2024)	loss 4.3888 (4.1759)	grad_norm 1.2625 (1.1644)	
[2022-01-18 11:49:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1100/1251]	eta 0:05:32 lr 0.000974	time 1.9527 (2.2035)	loss 4.1423 (4.1732)	grad_norm 1.3584 (1.1641)	
[2022-01-18 11:50:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1110/1251]	eta 0:05:10 lr 0.000974	time 2.8869 (2.2048)	loss 3.9612 (4.1733)	grad_norm 1.0627 (1.1641)	
[2022-01-18 11:50:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1120/1251]	eta 0:04:48 lr 0.000974	time 1.8838 (2.2059)	loss 3.6001 (4.1720)	grad_norm 0.9261 (1.1636)	
[2022-01-18 11:50:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1130/1251]	eta 0:04:26 lr 0.000974	time 1.5519 (2.2055)	loss 3.5840 (4.1716)	grad_norm 1.7391 (1.1649)	
[2022-01-18 11:51:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1140/1251]	eta 0:04:04 lr 0.000974	time 1.9560 (2.2047)	loss 4.1742 (4.1703)	grad_norm 1.1376 (1.1648)	
[2022-01-18 11:51:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1150/1251]	eta 0:03:42 lr 0.000974	time 1.8866 (2.2033)	loss 3.9899 (4.1702)	grad_norm 1.1359 (1.1642)	
[2022-01-18 11:52:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1160/1251]	eta 0:03:20 lr 0.000974	time 1.8965 (2.2030)	loss 4.7973 (4.1703)	grad_norm 1.1270 (1.1638)	
[2022-01-18 11:52:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1170/1251]	eta 0:02:58 lr 0.000974	time 2.0598 (2.2024)	loss 3.5107 (4.1700)	grad_norm 1.1473 (1.1641)	
[2022-01-18 11:52:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1180/1251]	eta 0:02:36 lr 0.000974	time 2.5148 (2.2024)	loss 4.3818 (4.1715)	grad_norm 1.4698 (1.1648)	
[2022-01-18 11:53:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1190/1251]	eta 0:02:14 lr 0.000974	time 2.1904 (2.2023)	loss 3.4576 (4.1709)	grad_norm 1.1825 (1.1646)	
[2022-01-18 11:53:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1200/1251]	eta 0:01:52 lr 0.000974	time 1.8080 (2.2023)	loss 4.4011 (4.1716)	grad_norm 1.1112 (1.1641)	
[2022-01-18 11:53:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1210/1251]	eta 0:01:30 lr 0.000974	time 1.6237 (2.2012)	loss 4.2193 (4.1730)	grad_norm 1.0748 (1.1637)	
[2022-01-18 11:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1220/1251]	eta 0:01:08 lr 0.000974	time 2.5577 (2.2005)	loss 3.4690 (4.1734)	grad_norm 1.1490 (1.1640)	
[2022-01-18 11:54:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1230/1251]	eta 0:00:46 lr 0.000974	time 1.9455 (2.2000)	loss 3.2299 (4.1716)	grad_norm 1.3148 (1.1641)	
[2022-01-18 11:54:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1240/1251]	eta 0:00:24 lr 0.000974	time 1.9918 (2.2003)	loss 3.7161 (4.1706)	grad_norm 1.0441 (1.1639)	
[2022-01-18 11:55:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [30/300][1250/1251]	eta 0:00:02 lr 0.000974	time 1.1552 (2.1945)	loss 4.1716 (4.1707)	grad_norm 1.2085 (1.1633)	
[2022-01-18 11:55:08 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 30 training takes 0:45:45
[2022-01-18 11:55:08 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_30 saving......
[2022-01-18 11:55:19 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_30 saved !!!
[2022-01-18 11:55:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 11.748 (11.748)	Loss 1.4883 (1.4883)	Acc@1 67.773 (67.773)	Acc@5 87.695 (87.695)	
[2022-01-18 11:55:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 5.076 (2.826)	Loss 1.5598 (1.4982)	Acc@1 63.477 (66.042)	Acc@5 86.426 (87.500)	
[2022-01-18 11:56:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.611 (2.289)	Loss 1.5181 (1.5039)	Acc@1 65.234 (65.718)	Acc@5 88.281 (87.505)	
[2022-01-18 11:56:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.654 (2.153)	Loss 1.5033 (1.4994)	Acc@1 66.406 (65.902)	Acc@5 87.207 (87.437)	
[2022-01-18 11:56:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.951 (2.020)	Loss 1.5325 (1.5001)	Acc@1 65.137 (65.873)	Acc@5 88.379 (87.524)	
[2022-01-18 11:56:49 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 66.042 Acc@5 87.628
[2022-01-18 11:56:49 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 66.0%
[2022-01-18 11:56:49 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 66.04%
[2022-01-18 11:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][0/1251]	eta 7:35:23 lr 0.000974	time 21.8417 (21.8417)	loss 3.2145 (3.2145)	grad_norm 1.1015 (1.1015)	
[2022-01-18 11:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][10/1251]	eta 1:23:41 lr 0.000974	time 2.7429 (4.0461)	loss 4.5842 (4.2757)	grad_norm 1.0823 (1.1538)	
[2022-01-18 11:57:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][20/1251]	eta 1:05:26 lr 0.000974	time 1.4791 (3.1900)	loss 3.6072 (4.1796)	grad_norm 1.2405 (1.1479)	
[2022-01-18 11:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][30/1251]	eta 0:58:19 lr 0.000974	time 1.9123 (2.8661)	loss 4.6701 (4.1197)	grad_norm 1.1008 (1.1511)	
[2022-01-18 11:58:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][40/1251]	eta 0:54:47 lr 0.000974	time 3.5122 (2.7150)	loss 3.0476 (4.0252)	grad_norm 1.0328 (1.1714)	
[2022-01-18 11:59:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][50/1251]	eta 0:53:31 lr 0.000974	time 2.7602 (2.6743)	loss 4.5075 (4.0034)	grad_norm 0.9638 (1.1641)	
[2022-01-18 11:59:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][60/1251]	eta 0:51:18 lr 0.000974	time 1.6023 (2.5848)	loss 4.4377 (3.9838)	grad_norm 1.7713 (1.1742)	
[2022-01-18 11:59:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][70/1251]	eta 0:49:40 lr 0.000974	time 1.6028 (2.5237)	loss 4.6450 (3.9753)	grad_norm 1.1835 (1.1762)	
[2022-01-18 12:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][80/1251]	eta 0:48:29 lr 0.000974	time 3.3786 (2.4847)	loss 5.0926 (3.9736)	grad_norm 1.2785 (1.1701)	
[2022-01-18 12:00:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][90/1251]	eta 0:47:28 lr 0.000974	time 2.0118 (2.4533)	loss 4.9282 (4.0077)	grad_norm 1.2824 (1.1663)	
[2022-01-18 12:00:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][100/1251]	eta 0:46:05 lr 0.000974	time 2.0985 (2.4029)	loss 4.3926 (4.0525)	grad_norm 1.2248 (1.1610)	
[2022-01-18 12:01:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][110/1251]	eta 0:45:04 lr 0.000974	time 2.1024 (2.3700)	loss 4.5117 (4.0833)	grad_norm 1.1827 (1.1530)	
[2022-01-18 12:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][120/1251]	eta 0:44:17 lr 0.000974	time 2.7404 (2.3496)	loss 5.0228 (4.1086)	grad_norm 1.3691 (1.1520)	
[2022-01-18 12:01:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][130/1251]	eta 0:43:45 lr 0.000974	time 1.8809 (2.3422)	loss 4.7303 (4.1212)	grad_norm 1.4010 (1.1604)	
[2022-01-18 12:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][140/1251]	eta 0:43:28 lr 0.000974	time 2.1243 (2.3482)	loss 3.0251 (4.1063)	grad_norm 1.4545 (1.1669)	
[2022-01-18 12:02:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][150/1251]	eta 0:43:02 lr 0.000974	time 2.7401 (2.3457)	loss 3.7051 (4.1064)	grad_norm 1.0226 (1.1670)	
[2022-01-18 12:03:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][160/1251]	eta 0:42:32 lr 0.000974	time 3.0518 (2.3393)	loss 3.2754 (4.0928)	grad_norm 1.0228 (1.1653)	
[2022-01-18 12:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][170/1251]	eta 0:41:48 lr 0.000974	time 1.6126 (2.3209)	loss 5.0405 (4.1103)	grad_norm 0.8383 (1.1630)	
[2022-01-18 12:03:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][180/1251]	eta 0:41:17 lr 0.000974	time 1.9113 (2.3135)	loss 2.9595 (4.1297)	grad_norm 1.0903 (1.1579)	
[2022-01-18 12:04:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][190/1251]	eta 0:40:41 lr 0.000974	time 1.8908 (2.3010)	loss 3.6304 (4.1183)	grad_norm 0.9601 (1.1566)	
[2022-01-18 12:04:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][200/1251]	eta 0:40:05 lr 0.000974	time 1.8186 (2.2886)	loss 4.4079 (4.1284)	grad_norm 1.3541 (1.1526)	
[2022-01-18 12:04:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][210/1251]	eta 0:39:36 lr 0.000974	time 1.8618 (2.2831)	loss 4.6838 (4.1323)	grad_norm 1.1855 (1.1523)	
[2022-01-18 12:05:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][220/1251]	eta 0:39:12 lr 0.000974	time 2.2912 (2.2817)	loss 3.7584 (4.1272)	grad_norm 1.1589 (1.1561)	
[2022-01-18 12:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][230/1251]	eta 0:38:53 lr 0.000974	time 2.4588 (2.2855)	loss 2.8542 (4.1171)	grad_norm 1.3056 (1.1582)	
[2022-01-18 12:05:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][240/1251]	eta 0:38:27 lr 0.000974	time 1.8801 (2.2826)	loss 4.6080 (4.1139)	grad_norm 0.9168 (1.1585)	
[2022-01-18 12:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][250/1251]	eta 0:37:53 lr 0.000974	time 1.8856 (2.2714)	loss 4.4690 (4.1150)	grad_norm 0.9945 (1.1585)	
[2022-01-18 12:06:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][260/1251]	eta 0:37:19 lr 0.000974	time 1.8895 (2.2599)	loss 3.6409 (4.1138)	grad_norm 1.1267 (1.1650)	
[2022-01-18 12:07:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][270/1251]	eta 0:36:56 lr 0.000974	time 2.5623 (2.2595)	loss 3.1437 (4.1275)	grad_norm 1.0823 (1.1686)	
[2022-01-18 12:07:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][280/1251]	eta 0:36:28 lr 0.000974	time 1.5103 (2.2538)	loss 4.6091 (4.1299)	grad_norm 0.9579 (1.1643)	
[2022-01-18 12:07:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][290/1251]	eta 0:35:59 lr 0.000974	time 1.4917 (2.2469)	loss 3.2217 (4.1342)	grad_norm 1.1000 (1.1601)	
[2022-01-18 12:08:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][300/1251]	eta 0:35:31 lr 0.000974	time 1.8542 (2.2415)	loss 3.8807 (4.1430)	grad_norm 1.1209 (1.1598)	
[2022-01-18 12:08:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][310/1251]	eta 0:35:11 lr 0.000974	time 2.7761 (2.2434)	loss 5.3311 (4.1513)	grad_norm 1.1215 (1.1585)	
[2022-01-18 12:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][320/1251]	eta 0:34:41 lr 0.000974	time 1.8122 (2.2358)	loss 4.5917 (4.1430)	grad_norm 1.0623 (1.1566)	
[2022-01-18 12:09:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][330/1251]	eta 0:34:17 lr 0.000974	time 2.2208 (2.2341)	loss 4.5657 (4.1505)	grad_norm 1.0474 (1.1570)	
[2022-01-18 12:09:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][340/1251]	eta 0:33:53 lr 0.000974	time 2.0456 (2.2316)	loss 4.4036 (4.1505)	grad_norm 1.0218 (1.1554)	
[2022-01-18 12:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][350/1251]	eta 0:33:37 lr 0.000974	time 2.8796 (2.2394)	loss 3.8010 (4.1486)	grad_norm 1.2334 (1.1559)	
[2022-01-18 12:10:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][360/1251]	eta 0:33:18 lr 0.000974	time 2.2161 (2.2425)	loss 3.9001 (4.1449)	grad_norm 1.0808 (1.1578)	
[2022-01-18 12:10:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][370/1251]	eta 0:33:00 lr 0.000974	time 2.1976 (2.2483)	loss 3.2452 (4.1383)	grad_norm 1.2545 (1.1595)	
[2022-01-18 12:11:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][380/1251]	eta 0:32:41 lr 0.000974	time 1.9103 (2.2520)	loss 3.5691 (4.1375)	grad_norm 1.2700 (1.1627)	
[2022-01-18 12:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][390/1251]	eta 0:32:18 lr 0.000974	time 1.9037 (2.2513)	loss 3.4383 (4.1378)	grad_norm 1.0740 (1.1626)	
[2022-01-18 12:11:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][400/1251]	eta 0:31:49 lr 0.000974	time 1.8533 (2.2444)	loss 3.9059 (4.1506)	grad_norm 1.0717 (1.1625)	
[2022-01-18 12:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][410/1251]	eta 0:31:21 lr 0.000974	time 2.0269 (2.2368)	loss 4.5557 (4.1528)	grad_norm 1.5605 (1.1614)	
[2022-01-18 12:12:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][420/1251]	eta 0:30:55 lr 0.000974	time 1.8355 (2.2331)	loss 4.6447 (4.1572)	grad_norm 1.0986 (1.1605)	
[2022-01-18 12:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][430/1251]	eta 0:30:33 lr 0.000974	time 2.4292 (2.2334)	loss 5.0625 (4.1582)	grad_norm 1.0139 (1.1610)	
[2022-01-18 12:13:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][440/1251]	eta 0:30:10 lr 0.000974	time 2.4100 (2.2320)	loss 3.7357 (4.1586)	grad_norm 1.2122 (1.1620)	
[2022-01-18 12:13:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][450/1251]	eta 0:29:46 lr 0.000974	time 1.6211 (2.2305)	loss 4.3756 (4.1596)	grad_norm 0.9050 (1.1643)	
[2022-01-18 12:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][460/1251]	eta 0:29:25 lr 0.000974	time 1.5521 (2.2316)	loss 5.0241 (4.1586)	grad_norm 1.2649 (1.1630)	
[2022-01-18 12:14:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][470/1251]	eta 0:29:03 lr 0.000974	time 2.6754 (2.2322)	loss 4.7306 (4.1554)	grad_norm 1.6349 (1.1636)	
[2022-01-18 12:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][480/1251]	eta 0:28:37 lr 0.000974	time 1.9646 (2.2282)	loss 3.6846 (4.1582)	grad_norm 1.1116 (1.1629)	
[2022-01-18 12:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][490/1251]	eta 0:28:14 lr 0.000973	time 1.6962 (2.2268)	loss 3.5658 (4.1542)	grad_norm 1.4154 (1.1614)	
[2022-01-18 12:15:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][500/1251]	eta 0:27:51 lr 0.000973	time 2.1744 (2.2257)	loss 3.7322 (4.1552)	grad_norm 0.8881 (1.1613)	
[2022-01-18 12:15:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][510/1251]	eta 0:27:28 lr 0.000973	time 2.4088 (2.2249)	loss 3.8828 (4.1521)	grad_norm 0.9339 (1.1599)	
[2022-01-18 12:16:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][520/1251]	eta 0:27:04 lr 0.000973	time 2.0956 (2.2223)	loss 5.1347 (4.1522)	grad_norm 1.0632 (1.1598)	
[2022-01-18 12:16:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][530/1251]	eta 0:26:41 lr 0.000973	time 1.4610 (2.2213)	loss 3.1596 (4.1523)	grad_norm 1.2208 (1.1582)	
[2022-01-18 12:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][540/1251]	eta 0:26:19 lr 0.000973	time 1.8738 (2.2210)	loss 4.4667 (4.1528)	grad_norm 1.1594 (1.1595)	
[2022-01-18 12:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][550/1251]	eta 0:25:56 lr 0.000973	time 1.5350 (2.2201)	loss 3.4298 (4.1457)	grad_norm 1.1888 (1.1600)	
[2022-01-18 12:17:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][560/1251]	eta 0:25:35 lr 0.000973	time 2.7552 (2.2215)	loss 3.0005 (4.1448)	grad_norm 1.1310 (1.1589)	
[2022-01-18 12:17:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][570/1251]	eta 0:25:13 lr 0.000973	time 1.5030 (2.2225)	loss 3.3840 (4.1467)	grad_norm 1.3441 (1.1592)	
[2022-01-18 12:18:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][580/1251]	eta 0:24:51 lr 0.000973	time 1.9053 (2.2227)	loss 4.7357 (4.1493)	grad_norm 0.9277 (1.1577)	
[2022-01-18 12:18:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][590/1251]	eta 0:24:27 lr 0.000973	time 1.5912 (2.2195)	loss 2.9852 (4.1494)	grad_norm 1.2967 (1.1575)	
[2022-01-18 12:19:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][600/1251]	eta 0:24:04 lr 0.000973	time 2.8510 (2.2186)	loss 4.8249 (4.1491)	grad_norm 1.3688 (1.1593)	
[2022-01-18 12:19:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][610/1251]	eta 0:23:41 lr 0.000973	time 2.4049 (2.2178)	loss 3.5748 (4.1496)	grad_norm 1.0464 (1.1602)	
[2022-01-18 12:19:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][620/1251]	eta 0:23:20 lr 0.000973	time 2.0257 (2.2195)	loss 4.8289 (4.1569)	grad_norm 0.9563 (1.1600)	
[2022-01-18 12:20:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][630/1251]	eta 0:22:59 lr 0.000973	time 2.5433 (2.2210)	loss 4.5951 (4.1571)	grad_norm 1.1278 (1.1596)	
[2022-01-18 12:20:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][640/1251]	eta 0:22:36 lr 0.000973	time 2.2175 (2.2197)	loss 4.7395 (4.1576)	grad_norm 1.1898 (1.1577)	
[2022-01-18 12:20:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][650/1251]	eta 0:22:11 lr 0.000973	time 1.9979 (2.2158)	loss 2.9974 (4.1580)	grad_norm 0.9871 (1.1574)	
[2022-01-18 12:21:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][660/1251]	eta 0:21:48 lr 0.000973	time 2.2625 (2.2143)	loss 4.6905 (4.1566)	grad_norm 1.3698 (1.1582)	
[2022-01-18 12:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][670/1251]	eta 0:21:26 lr 0.000973	time 2.8446 (2.2139)	loss 3.1244 (4.1580)	grad_norm 1.1260 (1.1583)	
[2022-01-18 12:21:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][680/1251]	eta 0:21:04 lr 0.000973	time 2.5835 (2.2154)	loss 4.5284 (4.1586)	grad_norm 1.2151 (1.1590)	
[2022-01-18 12:22:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][690/1251]	eta 0:20:41 lr 0.000973	time 2.1739 (2.2138)	loss 3.5777 (4.1585)	grad_norm 1.0064 (1.1597)	
[2022-01-18 12:22:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][700/1251]	eta 0:20:19 lr 0.000973	time 2.2743 (2.2141)	loss 4.3858 (4.1613)	grad_norm 1.2879 (1.1590)	
[2022-01-18 12:23:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][710/1251]	eta 0:19:58 lr 0.000973	time 3.4184 (2.2155)	loss 3.7677 (4.1584)	grad_norm 1.0578 (1.1589)	
[2022-01-18 12:23:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][720/1251]	eta 0:19:36 lr 0.000973	time 2.8162 (2.2149)	loss 4.4884 (4.1602)	grad_norm 1.1282 (1.1580)	
[2022-01-18 12:23:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][730/1251]	eta 0:19:12 lr 0.000973	time 1.7679 (2.2129)	loss 3.4107 (4.1588)	grad_norm 1.2437 (1.1586)	
[2022-01-18 12:24:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][740/1251]	eta 0:18:49 lr 0.000973	time 1.9373 (2.2113)	loss 4.5488 (4.1636)	grad_norm 1.3097 (1.1612)	
[2022-01-18 12:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][750/1251]	eta 0:18:28 lr 0.000973	time 2.9332 (2.2121)	loss 4.9054 (4.1643)	grad_norm 1.2464 (1.1614)	
[2022-01-18 12:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][760/1251]	eta 0:18:06 lr 0.000973	time 3.3323 (2.2132)	loss 4.2609 (4.1607)	grad_norm 1.0389 (1.1622)	
[2022-01-18 12:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][770/1251]	eta 0:17:45 lr 0.000973	time 1.9927 (2.2142)	loss 2.9610 (4.1578)	grad_norm 1.0177 (1.1610)	
[2022-01-18 12:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][780/1251]	eta 0:17:22 lr 0.000973	time 1.7682 (2.2139)	loss 3.2790 (4.1559)	grad_norm 0.9769 (1.1614)	
[2022-01-18 12:26:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][790/1251]	eta 0:17:01 lr 0.000973	time 3.6948 (2.2157)	loss 4.1878 (4.1582)	grad_norm 1.4328 (1.1628)	
[2022-01-18 12:26:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][800/1251]	eta 0:16:38 lr 0.000973	time 1.8632 (2.2133)	loss 4.1220 (4.1628)	grad_norm 1.0693 (1.1621)	
[2022-01-18 12:26:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][810/1251]	eta 0:16:14 lr 0.000973	time 1.9059 (2.2102)	loss 4.4737 (4.1645)	grad_norm 1.3198 (1.1633)	
[2022-01-18 12:27:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][820/1251]	eta 0:15:52 lr 0.000973	time 1.5302 (2.2095)	loss 4.2286 (4.1657)	grad_norm 1.3924 (1.1637)	
[2022-01-18 12:27:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][830/1251]	eta 0:15:30 lr 0.000973	time 2.7381 (2.2098)	loss 4.3440 (4.1635)	grad_norm 1.1589 (1.1643)	
[2022-01-18 12:27:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][840/1251]	eta 0:15:08 lr 0.000973	time 2.0460 (2.2104)	loss 3.7516 (4.1648)	grad_norm 1.0430 (1.1631)	
[2022-01-18 12:28:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][850/1251]	eta 0:14:46 lr 0.000973	time 1.8437 (2.2100)	loss 3.2456 (4.1662)	grad_norm 1.1909 (1.1620)	
[2022-01-18 12:28:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][860/1251]	eta 0:14:23 lr 0.000973	time 2.4839 (2.2095)	loss 3.1577 (4.1656)	grad_norm 0.9483 (1.1605)	
[2022-01-18 12:28:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][870/1251]	eta 0:14:01 lr 0.000973	time 2.8367 (2.2090)	loss 4.6755 (4.1666)	grad_norm 1.1516 (1.1591)	
[2022-01-18 12:29:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][880/1251]	eta 0:13:39 lr 0.000973	time 2.1767 (2.2078)	loss 4.5690 (4.1674)	grad_norm 1.1073 (1.1589)	
[2022-01-18 12:29:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][890/1251]	eta 0:13:16 lr 0.000973	time 1.8151 (2.2054)	loss 4.6810 (4.1672)	grad_norm 0.9117 (1.1580)	
[2022-01-18 12:29:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][900/1251]	eta 0:12:53 lr 0.000973	time 2.2901 (2.2046)	loss 4.6172 (4.1679)	grad_norm 0.9214 (1.1568)	
[2022-01-18 12:30:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][910/1251]	eta 0:12:31 lr 0.000973	time 2.5051 (2.2040)	loss 5.1101 (4.1700)	grad_norm 1.3874 (1.1574)	
[2022-01-18 12:30:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][920/1251]	eta 0:12:09 lr 0.000973	time 2.5700 (2.2041)	loss 3.1005 (4.1701)	grad_norm 1.1769 (1.1582)	
[2022-01-18 12:31:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][930/1251]	eta 0:11:47 lr 0.000973	time 1.5662 (2.2025)	loss 4.9347 (4.1698)	grad_norm 1.0419 (1.1577)	
[2022-01-18 12:31:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][940/1251]	eta 0:11:25 lr 0.000973	time 2.8785 (2.2042)	loss 4.2497 (4.1696)	grad_norm 1.4335 (1.1584)	
[2022-01-18 12:31:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][950/1251]	eta 0:11:03 lr 0.000973	time 1.9763 (2.2049)	loss 3.8109 (4.1710)	grad_norm 0.9994 (1.1570)	
[2022-01-18 12:32:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][960/1251]	eta 0:10:41 lr 0.000973	time 2.5407 (2.2058)	loss 4.6851 (4.1710)	grad_norm 1.1640 (1.1567)	
[2022-01-18 12:32:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][970/1251]	eta 0:10:19 lr 0.000973	time 1.7067 (2.2051)	loss 3.0192 (4.1717)	grad_norm 1.1322 (1.1565)	
[2022-01-18 12:32:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][980/1251]	eta 0:09:57 lr 0.000973	time 3.0740 (2.2049)	loss 4.4993 (4.1736)	grad_norm 1.5254 (1.1565)	
[2022-01-18 12:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][990/1251]	eta 0:09:35 lr 0.000973	time 2.0835 (2.2044)	loss 4.1657 (4.1724)	grad_norm 1.3716 (1.1566)	
[2022-01-18 12:33:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1000/1251]	eta 0:09:13 lr 0.000973	time 2.5593 (2.2040)	loss 4.4384 (4.1699)	grad_norm 1.1037 (1.1561)	
[2022-01-18 12:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1010/1251]	eta 0:08:51 lr 0.000973	time 1.9193 (2.2037)	loss 2.6556 (4.1680)	grad_norm 1.1303 (1.1560)	
[2022-01-18 12:34:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1020/1251]	eta 0:08:29 lr 0.000973	time 2.2945 (2.2039)	loss 4.0488 (4.1673)	grad_norm 1.2197 (1.1550)	
[2022-01-18 12:34:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1030/1251]	eta 0:08:06 lr 0.000973	time 1.7392 (2.2032)	loss 4.6666 (4.1676)	grad_norm 1.6274 (1.1551)	
[2022-01-18 12:35:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1040/1251]	eta 0:07:44 lr 0.000973	time 2.5138 (2.2011)	loss 3.9136 (4.1691)	grad_norm 1.3614 (1.1549)	
[2022-01-18 12:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1050/1251]	eta 0:07:22 lr 0.000973	time 2.2117 (2.2009)	loss 4.2807 (4.1699)	grad_norm 1.0722 (1.1539)	
[2022-01-18 12:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1060/1251]	eta 0:07:00 lr 0.000973	time 2.1042 (2.2011)	loss 3.7971 (4.1684)	grad_norm 1.1876 (1.1544)	
[2022-01-18 12:36:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1070/1251]	eta 0:06:38 lr 0.000973	time 1.8764 (2.2019)	loss 3.6352 (4.1671)	grad_norm 1.0029 (1.1537)	
[2022-01-18 12:36:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1080/1251]	eta 0:06:16 lr 0.000973	time 2.9151 (2.2022)	loss 4.2821 (4.1685)	grad_norm 0.9313 (1.1530)	
[2022-01-18 12:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1090/1251]	eta 0:05:54 lr 0.000973	time 1.9090 (2.2019)	loss 3.8750 (4.1693)	grad_norm 1.2842 (1.1539)	
[2022-01-18 12:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1100/1251]	eta 0:05:32 lr 0.000973	time 1.8335 (2.1998)	loss 3.3087 (4.1678)	grad_norm 0.9785 (1.1531)	
[2022-01-18 12:37:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1110/1251]	eta 0:05:10 lr 0.000973	time 2.2393 (2.1999)	loss 4.9111 (4.1657)	grad_norm 1.1122 (1.1523)	
[2022-01-18 12:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1120/1251]	eta 0:04:48 lr 0.000973	time 2.9928 (2.1995)	loss 2.9519 (4.1658)	grad_norm 1.0614 (1.1518)	
[2022-01-18 12:38:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1130/1251]	eta 0:04:25 lr 0.000973	time 1.7908 (2.1977)	loss 4.3474 (4.1657)	grad_norm 1.0764 (1.1519)	
[2022-01-18 12:38:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1140/1251]	eta 0:04:03 lr 0.000973	time 1.8933 (2.1969)	loss 4.0289 (4.1668)	grad_norm 1.0402 (1.1514)	
[2022-01-18 12:38:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1150/1251]	eta 0:03:41 lr 0.000973	time 2.4375 (2.1964)	loss 4.4869 (4.1650)	grad_norm 1.1772 (1.1517)	
[2022-01-18 12:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1160/1251]	eta 0:03:20 lr 0.000973	time 3.2252 (2.1979)	loss 4.3803 (4.1670)	grad_norm 1.0970 (1.1510)	
[2022-01-18 12:39:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1170/1251]	eta 0:02:58 lr 0.000973	time 1.5678 (2.1979)	loss 3.1342 (4.1674)	grad_norm 1.3912 (1.1509)	
[2022-01-18 12:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1180/1251]	eta 0:02:36 lr 0.000973	time 1.9648 (2.1979)	loss 2.9402 (4.1650)	grad_norm 1.0703 (1.1511)	
[2022-01-18 12:40:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1190/1251]	eta 0:02:14 lr 0.000973	time 1.8999 (2.1984)	loss 3.2877 (4.1654)	grad_norm 0.9328 (1.1504)	
[2022-01-18 12:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1200/1251]	eta 0:01:52 lr 0.000973	time 2.6090 (2.1986)	loss 4.4217 (4.1666)	grad_norm 0.9436 (1.1492)	
[2022-01-18 12:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1210/1251]	eta 0:01:30 lr 0.000973	time 1.9175 (2.1967)	loss 4.4429 (4.1695)	grad_norm 1.1645 (1.1489)	
[2022-01-18 12:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1220/1251]	eta 0:01:08 lr 0.000973	time 2.2199 (2.1956)	loss 4.4069 (4.1681)	grad_norm 0.9563 (1.1484)	
[2022-01-18 12:41:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1230/1251]	eta 0:00:46 lr 0.000972	time 1.9165 (2.1944)	loss 4.2396 (4.1683)	grad_norm 1.0610 (1.1482)	
[2022-01-18 12:42:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1240/1251]	eta 0:00:24 lr 0.000972	time 2.2070 (2.1941)	loss 4.4443 (4.1665)	grad_norm 1.4533 (1.1482)	
[2022-01-18 12:42:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [31/300][1250/1251]	eta 0:00:02 lr 0.000972	time 1.1203 (2.1888)	loss 3.7037 (4.1644)	grad_norm 1.0449 (1.1479)	
[2022-01-18 12:42:28 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 31 training takes 0:45:38
[2022-01-18 12:42:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.572 (18.572)	Loss 1.4121 (1.4121)	Acc@1 67.871 (67.871)	Acc@5 89.062 (89.062)	
[2022-01-18 12:43:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.900 (3.484)	Loss 1.4523 (1.4712)	Acc@1 66.895 (66.921)	Acc@5 87.402 (87.518)	
[2022-01-18 12:43:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.973 (2.639)	Loss 1.5286 (1.4782)	Acc@1 65.137 (66.574)	Acc@5 85.449 (87.463)	
[2022-01-18 12:43:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.551 (2.273)	Loss 1.4891 (1.4822)	Acc@1 66.992 (66.372)	Acc@5 87.695 (87.513)	
[2022-01-18 12:43:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.871 (2.150)	Loss 1.4832 (1.4841)	Acc@1 63.965 (66.232)	Acc@5 88.281 (87.583)	
[2022-01-18 12:44:04 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 66.212 Acc@5 87.622
[2022-01-18 12:44:04 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 66.2%
[2022-01-18 12:44:04 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 66.21%
[2022-01-18 12:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][0/1251]	eta 7:23:08 lr 0.000972	time 21.2534 (21.2534)	loss 3.9801 (3.9801)	grad_norm 1.3080 (1.3080)	
[2022-01-18 12:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][10/1251]	eta 1:25:02 lr 0.000972	time 2.1642 (4.1119)	loss 4.1678 (3.9777)	grad_norm 1.0175 (1.1090)	
[2022-01-18 12:45:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][20/1251]	eta 1:05:57 lr 0.000972	time 1.6262 (3.2146)	loss 4.6152 (4.0334)	grad_norm 1.0023 (1.0919)	
[2022-01-18 12:45:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][30/1251]	eta 0:59:54 lr 0.000972	time 1.4142 (2.9436)	loss 4.3490 (4.0348)	grad_norm 1.3395 (1.1273)	
[2022-01-18 12:45:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][40/1251]	eta 0:56:32 lr 0.000972	time 3.2924 (2.8011)	loss 4.8563 (4.0885)	grad_norm 0.9666 (1.1802)	
[2022-01-18 12:46:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][50/1251]	eta 0:55:04 lr 0.000972	time 2.7508 (2.7517)	loss 4.4675 (4.1021)	grad_norm 1.2187 (1.1664)	
[2022-01-18 12:46:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][60/1251]	eta 0:52:06 lr 0.000972	time 1.6135 (2.6247)	loss 4.9610 (4.1570)	grad_norm 1.1226 (1.1717)	
[2022-01-18 12:47:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][70/1251]	eta 0:50:46 lr 0.000972	time 1.9639 (2.5797)	loss 3.9556 (4.1105)	grad_norm 1.1256 (1.1777)	
[2022-01-18 12:47:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][80/1251]	eta 0:49:00 lr 0.000972	time 1.6206 (2.5113)	loss 4.6327 (4.1184)	grad_norm 1.1900 (1.1742)	
[2022-01-18 12:47:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][90/1251]	eta 0:47:49 lr 0.000972	time 2.2842 (2.4719)	loss 3.9885 (4.0982)	grad_norm 1.0524 (1.1720)	
[2022-01-18 12:48:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][100/1251]	eta 0:46:52 lr 0.000972	time 1.7295 (2.4435)	loss 3.7553 (4.1011)	grad_norm 1.4610 (1.1729)	
[2022-01-18 12:48:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][110/1251]	eta 0:46:14 lr 0.000972	time 2.5577 (2.4314)	loss 4.1119 (4.1192)	grad_norm 1.1416 (1.1662)	
[2022-01-18 12:48:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][120/1251]	eta 0:45:10 lr 0.000972	time 1.6413 (2.3965)	loss 3.1244 (4.1256)	grad_norm 1.4825 (1.1632)	
[2022-01-18 12:49:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][130/1251]	eta 0:44:29 lr 0.000972	time 2.0084 (2.3813)	loss 3.1610 (4.1202)	grad_norm 1.5634 (1.1623)	
[2022-01-18 12:49:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][140/1251]	eta 0:43:45 lr 0.000972	time 2.0210 (2.3633)	loss 4.3503 (4.1244)	grad_norm 1.3728 (1.1609)	
[2022-01-18 12:49:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][150/1251]	eta 0:43:04 lr 0.000972	time 1.7722 (2.3474)	loss 4.6159 (4.1246)	grad_norm 0.9693 (1.1614)	
[2022-01-18 12:50:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][160/1251]	eta 0:42:31 lr 0.000972	time 2.5299 (2.3386)	loss 3.7161 (4.1084)	grad_norm 0.9533 (1.1626)	
[2022-01-18 12:50:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][170/1251]	eta 0:41:50 lr 0.000972	time 1.9356 (2.3227)	loss 4.8420 (4.1170)	grad_norm 1.0748 (1.1654)	
[2022-01-18 12:51:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][180/1251]	eta 0:41:21 lr 0.000972	time 2.8072 (2.3166)	loss 4.8878 (4.1100)	grad_norm 1.3136 (1.1602)	
[2022-01-18 12:51:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][190/1251]	eta 0:40:46 lr 0.000972	time 1.4536 (2.3054)	loss 4.6445 (4.1151)	grad_norm 1.1788 (1.1564)	
[2022-01-18 12:51:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][200/1251]	eta 0:40:18 lr 0.000972	time 2.3300 (2.3011)	loss 4.0031 (4.1238)	grad_norm 0.9941 (1.1564)	
[2022-01-18 12:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][210/1251]	eta 0:39:41 lr 0.000972	time 2.1495 (2.2877)	loss 3.7303 (4.1076)	grad_norm 1.1128 (1.1543)	
[2022-01-18 12:52:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][220/1251]	eta 0:39:22 lr 0.000972	time 2.2051 (2.2919)	loss 4.0873 (4.1056)	grad_norm 1.0730 (1.1546)	
[2022-01-18 12:52:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][230/1251]	eta 0:38:59 lr 0.000972	time 1.5416 (2.2911)	loss 5.0264 (4.1164)	grad_norm 1.3788 (1.1527)	
[2022-01-18 12:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][240/1251]	eta 0:38:42 lr 0.000972	time 1.6466 (2.2970)	loss 4.3915 (4.1266)	grad_norm 1.0686 (1.1538)	
[2022-01-18 12:53:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][250/1251]	eta 0:38:14 lr 0.000972	time 1.9355 (2.2924)	loss 4.2109 (4.1355)	grad_norm 1.3246 (1.1546)	
[2022-01-18 12:54:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][260/1251]	eta 0:37:51 lr 0.000972	time 1.8863 (2.2917)	loss 4.1077 (4.1513)	grad_norm 1.1028 (1.1561)	
[2022-01-18 12:54:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][270/1251]	eta 0:37:20 lr 0.000972	time 1.5996 (2.2837)	loss 4.5555 (4.1578)	grad_norm 1.1976 (1.1556)	
[2022-01-18 12:54:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][280/1251]	eta 0:36:49 lr 0.000972	time 2.0385 (2.2755)	loss 4.2326 (4.1623)	grad_norm 1.1114 (1.1564)	
[2022-01-18 12:55:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][290/1251]	eta 0:36:23 lr 0.000972	time 1.8798 (2.2726)	loss 4.2359 (4.1567)	grad_norm 1.2964 (1.1588)	
[2022-01-18 12:55:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][300/1251]	eta 0:36:02 lr 0.000972	time 2.1850 (2.2734)	loss 4.4526 (4.1548)	grad_norm 1.3012 (1.1599)	
[2022-01-18 12:55:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][310/1251]	eta 0:35:31 lr 0.000972	time 1.6551 (2.2646)	loss 4.3889 (4.1533)	grad_norm 1.3761 (1.1603)	
[2022-01-18 12:56:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][320/1251]	eta 0:35:10 lr 0.000972	time 1.9244 (2.2672)	loss 4.2597 (4.1457)	grad_norm 1.1093 (1.1577)	
[2022-01-18 12:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][330/1251]	eta 0:34:43 lr 0.000972	time 1.6061 (2.2625)	loss 4.7276 (4.1409)	grad_norm 1.1957 (1.1576)	
[2022-01-18 12:56:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][340/1251]	eta 0:34:16 lr 0.000972	time 1.6379 (2.2573)	loss 4.9647 (4.1449)	grad_norm 0.9943 (1.1555)	
[2022-01-18 12:57:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][350/1251]	eta 0:33:47 lr 0.000972	time 1.6775 (2.2508)	loss 4.9394 (4.1480)	grad_norm 0.9882 (1.1536)	
[2022-01-18 12:57:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][360/1251]	eta 0:33:22 lr 0.000972	time 2.0192 (2.2473)	loss 3.7980 (4.1475)	grad_norm 0.9928 (1.1540)	
[2022-01-18 12:57:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][370/1251]	eta 0:32:57 lr 0.000972	time 1.6343 (2.2443)	loss 3.2639 (4.1443)	grad_norm 1.3697 (1.1545)	
[2022-01-18 12:58:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][380/1251]	eta 0:32:31 lr 0.000972	time 1.8803 (2.2411)	loss 3.9771 (4.1435)	grad_norm 1.5497 (1.1566)	
[2022-01-18 12:58:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][390/1251]	eta 0:32:08 lr 0.000972	time 2.1058 (2.2403)	loss 4.1921 (4.1447)	grad_norm 1.1718 (1.1591)	
[2022-01-18 12:59:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][400/1251]	eta 0:31:48 lr 0.000972	time 2.7539 (2.2425)	loss 3.3803 (4.1421)	grad_norm 1.1313 (1.1574)	
[2022-01-18 12:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][410/1251]	eta 0:31:23 lr 0.000972	time 1.9161 (2.2392)	loss 4.0699 (4.1407)	grad_norm 1.3132 (1.1571)	
[2022-01-18 12:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][420/1251]	eta 0:30:58 lr 0.000972	time 1.8208 (2.2359)	loss 4.4110 (4.1485)	grad_norm 1.1489 (1.1579)	
[2022-01-18 13:00:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][430/1251]	eta 0:30:38 lr 0.000972	time 3.5049 (2.2396)	loss 4.7060 (4.1533)	grad_norm 1.0092 (1.1563)	
[2022-01-18 13:00:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][440/1251]	eta 0:30:15 lr 0.000972	time 1.9773 (2.2385)	loss 4.9571 (4.1580)	grad_norm 1.1445 (1.1553)	
[2022-01-18 13:00:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][450/1251]	eta 0:29:53 lr 0.000972	time 1.9578 (2.2392)	loss 5.0006 (4.1632)	grad_norm 1.0303 (1.1541)	
[2022-01-18 13:01:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][460/1251]	eta 0:29:30 lr 0.000972	time 1.7684 (2.2379)	loss 4.7895 (4.1619)	grad_norm 1.2667 (1.1538)	
[2022-01-18 13:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][470/1251]	eta 0:29:08 lr 0.000972	time 3.1414 (2.2390)	loss 4.1161 (4.1640)	grad_norm 1.2645 (1.1536)	
[2022-01-18 13:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][480/1251]	eta 0:28:44 lr 0.000972	time 2.5108 (2.2363)	loss 4.5680 (4.1634)	grad_norm 1.4713 (1.1548)	
[2022-01-18 13:02:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][490/1251]	eta 0:28:18 lr 0.000972	time 2.2254 (2.2314)	loss 4.5919 (4.1689)	grad_norm 1.2699 (1.1537)	
[2022-01-18 13:02:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][500/1251]	eta 0:27:53 lr 0.000972	time 1.8040 (2.2280)	loss 3.9249 (4.1671)	grad_norm 1.3794 (1.1568)	
[2022-01-18 13:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][510/1251]	eta 0:27:33 lr 0.000972	time 3.8387 (2.2308)	loss 3.7010 (4.1600)	grad_norm 1.0892 (1.1561)	
[2022-01-18 13:03:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][520/1251]	eta 0:27:12 lr 0.000972	time 2.7593 (2.2331)	loss 4.7481 (4.1582)	grad_norm 1.2953 (1.1549)	
[2022-01-18 13:03:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][530/1251]	eta 0:26:51 lr 0.000972	time 2.3153 (2.2350)	loss 5.0444 (4.1539)	grad_norm 1.2555 (1.1533)	
[2022-01-18 13:04:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][540/1251]	eta 0:26:26 lr 0.000972	time 1.7393 (2.2314)	loss 4.1459 (4.1578)	grad_norm 1.1249 (1.1550)	
[2022-01-18 13:04:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][550/1251]	eta 0:26:01 lr 0.000972	time 2.7114 (2.2281)	loss 3.2198 (4.1570)	grad_norm 1.0218 (1.1550)	
[2022-01-18 13:04:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][560/1251]	eta 0:25:37 lr 0.000972	time 2.5991 (2.2252)	loss 4.9157 (4.1567)	grad_norm 1.1475 (1.1544)	
[2022-01-18 13:05:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][570/1251]	eta 0:25:15 lr 0.000972	time 2.2220 (2.2247)	loss 4.0716 (4.1562)	grad_norm 1.0757 (1.1538)	
[2022-01-18 13:05:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][580/1251]	eta 0:24:51 lr 0.000972	time 2.5244 (2.2225)	loss 2.7852 (4.1521)	grad_norm 0.9909 (1.1535)	
[2022-01-18 13:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][590/1251]	eta 0:24:28 lr 0.000972	time 2.9291 (2.2220)	loss 3.3468 (4.1547)	grad_norm 1.0122 (1.1541)	
[2022-01-18 13:06:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][600/1251]	eta 0:24:07 lr 0.000972	time 2.2675 (2.2233)	loss 3.1815 (4.1485)	grad_norm 1.2000 (1.1558)	
[2022-01-18 13:06:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][610/1251]	eta 0:23:46 lr 0.000972	time 1.4858 (2.2254)	loss 4.8696 (4.1520)	grad_norm 1.1070 (1.1568)	
[2022-01-18 13:07:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][620/1251]	eta 0:23:24 lr 0.000972	time 1.9353 (2.2255)	loss 4.2151 (4.1504)	grad_norm 1.0502 (1.1560)	
[2022-01-18 13:07:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][630/1251]	eta 0:23:00 lr 0.000972	time 1.6737 (2.2234)	loss 4.8799 (4.1498)	grad_norm 1.3917 (1.1564)	
[2022-01-18 13:07:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][640/1251]	eta 0:22:38 lr 0.000972	time 2.8692 (2.2233)	loss 4.8722 (4.1529)	grad_norm 1.0393 (1.1557)	
[2022-01-18 13:08:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][650/1251]	eta 0:22:15 lr 0.000972	time 1.5495 (2.2225)	loss 3.3132 (4.1494)	grad_norm 0.9899 (1.1542)	
[2022-01-18 13:08:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][660/1251]	eta 0:21:53 lr 0.000972	time 1.5641 (2.2220)	loss 3.8943 (4.1450)	grad_norm 1.1650 (1.1537)	
[2022-01-18 13:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][670/1251]	eta 0:21:31 lr 0.000972	time 2.1270 (2.2229)	loss 4.6965 (4.1439)	grad_norm 1.3281 (1.1529)	
[2022-01-18 13:09:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][680/1251]	eta 0:21:09 lr 0.000972	time 3.0885 (2.2241)	loss 4.1417 (4.1420)	grad_norm 1.1259 (1.1539)	
[2022-01-18 13:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][690/1251]	eta 0:20:46 lr 0.000972	time 1.9181 (2.2216)	loss 4.6470 (4.1456)	grad_norm 0.9893 (1.1524)	
[2022-01-18 13:09:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][700/1251]	eta 0:20:22 lr 0.000972	time 2.5643 (2.2194)	loss 3.9715 (4.1453)	grad_norm 1.2100 (1.1521)	
[2022-01-18 13:10:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][710/1251]	eta 0:20:00 lr 0.000971	time 1.8709 (2.2188)	loss 3.5836 (4.1446)	grad_norm 1.4584 (1.1533)	
[2022-01-18 13:10:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][720/1251]	eta 0:19:39 lr 0.000971	time 3.1722 (2.2219)	loss 3.8485 (4.1443)	grad_norm 1.1513 (1.1527)	
[2022-01-18 13:11:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][730/1251]	eta 0:19:17 lr 0.000971	time 2.2167 (2.2220)	loss 3.9306 (4.1425)	grad_norm 1.6917 (1.1548)	
[2022-01-18 13:11:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][740/1251]	eta 0:18:55 lr 0.000971	time 1.9447 (2.2230)	loss 4.0761 (4.1403)	grad_norm 1.3498 (1.1570)	
[2022-01-18 13:11:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][750/1251]	eta 0:18:32 lr 0.000971	time 1.7017 (2.2214)	loss 4.6073 (4.1402)	grad_norm 1.2169 (1.1576)	
[2022-01-18 13:12:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][760/1251]	eta 0:18:09 lr 0.000971	time 2.0975 (2.2187)	loss 3.7906 (4.1380)	grad_norm 1.1623 (1.1584)	
[2022-01-18 13:12:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][770/1251]	eta 0:17:45 lr 0.000971	time 1.9048 (2.2161)	loss 4.0411 (4.1362)	grad_norm 1.3308 (1.1600)	
[2022-01-18 13:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][780/1251]	eta 0:17:22 lr 0.000971	time 2.1576 (2.2131)	loss 4.3563 (4.1368)	grad_norm 0.9595 (1.1596)	
[2022-01-18 13:13:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][790/1251]	eta 0:16:59 lr 0.000971	time 1.9279 (2.2109)	loss 3.7548 (4.1365)	grad_norm 1.1126 (1.1591)	
[2022-01-18 13:13:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][800/1251]	eta 0:16:36 lr 0.000971	time 2.1721 (2.2106)	loss 3.9514 (4.1330)	grad_norm 0.9956 (1.1588)	
[2022-01-18 13:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][810/1251]	eta 0:16:15 lr 0.000971	time 2.4812 (2.2118)	loss 3.7814 (4.1303)	grad_norm 1.2197 (1.1588)	
[2022-01-18 13:14:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][820/1251]	eta 0:15:52 lr 0.000971	time 2.4848 (2.2111)	loss 4.3385 (4.1286)	grad_norm 1.2286 (1.1587)	
[2022-01-18 13:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][830/1251]	eta 0:15:31 lr 0.000971	time 2.2917 (2.2116)	loss 4.6254 (4.1322)	grad_norm 1.0240 (1.1590)	
[2022-01-18 13:15:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][840/1251]	eta 0:15:08 lr 0.000971	time 1.8860 (2.2109)	loss 3.4788 (4.1336)	grad_norm 1.0259 (1.1595)	
[2022-01-18 13:15:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][850/1251]	eta 0:14:47 lr 0.000971	time 2.7048 (2.2126)	loss 4.4891 (4.1335)	grad_norm 1.3962 (1.1598)	
[2022-01-18 13:15:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][860/1251]	eta 0:14:25 lr 0.000971	time 2.4986 (2.2128)	loss 4.0345 (4.1309)	grad_norm 1.1620 (1.1595)	
[2022-01-18 13:16:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][870/1251]	eta 0:14:03 lr 0.000971	time 1.6783 (2.2139)	loss 4.7981 (4.1342)	grad_norm 1.2355 (1.1599)	
[2022-01-18 13:16:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][880/1251]	eta 0:13:40 lr 0.000971	time 1.9883 (2.2127)	loss 4.7193 (4.1318)	grad_norm 1.2231 (1.1624)	
[2022-01-18 13:16:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][890/1251]	eta 0:13:18 lr 0.000971	time 1.8317 (2.2107)	loss 4.0314 (4.1327)	grad_norm 1.1974 (1.1623)	
[2022-01-18 13:17:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][900/1251]	eta 0:12:55 lr 0.000971	time 2.4822 (2.2095)	loss 4.5033 (4.1334)	grad_norm 1.0363 (1.1626)	
[2022-01-18 13:17:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][910/1251]	eta 0:12:33 lr 0.000971	time 1.8275 (2.2101)	loss 3.4804 (4.1305)	grad_norm 1.3183 (1.1629)	
[2022-01-18 13:17:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][920/1251]	eta 0:12:11 lr 0.000971	time 1.9140 (2.2093)	loss 4.2352 (4.1297)	grad_norm 1.2390 (1.1632)	
[2022-01-18 13:18:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][930/1251]	eta 0:11:49 lr 0.000971	time 2.1216 (2.2092)	loss 4.6929 (4.1291)	grad_norm 1.3338 (1.1638)	
[2022-01-18 13:18:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][940/1251]	eta 0:11:27 lr 0.000971	time 2.1569 (2.2100)	loss 4.6989 (4.1294)	grad_norm 1.1665 (1.1647)	
[2022-01-18 13:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][950/1251]	eta 0:11:05 lr 0.000971	time 2.4552 (2.2122)	loss 4.8455 (4.1299)	grad_norm 1.1259 (1.1656)	
[2022-01-18 13:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][960/1251]	eta 0:10:43 lr 0.000971	time 2.2049 (2.2117)	loss 4.7278 (4.1300)	grad_norm 1.0819 (1.1645)	
[2022-01-18 13:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][970/1251]	eta 0:10:21 lr 0.000971	time 2.0147 (2.2112)	loss 4.3549 (4.1296)	grad_norm 1.2945 (1.1647)	
[2022-01-18 13:20:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][980/1251]	eta 0:09:58 lr 0.000971	time 1.7805 (2.2090)	loss 4.3255 (4.1300)	grad_norm 1.0692 (1.1643)	
[2022-01-18 13:20:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][990/1251]	eta 0:09:36 lr 0.000971	time 1.8572 (2.2077)	loss 4.2611 (4.1304)	grad_norm 1.1775 (1.1646)	
[2022-01-18 13:20:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1000/1251]	eta 0:09:13 lr 0.000971	time 1.9620 (2.2062)	loss 4.2525 (4.1327)	grad_norm 1.0241 (1.1645)	
[2022-01-18 13:21:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1010/1251]	eta 0:08:51 lr 0.000971	time 2.1523 (2.2065)	loss 4.4115 (4.1322)	grad_norm 1.1047 (1.1645)	
[2022-01-18 13:21:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1020/1251]	eta 0:08:29 lr 0.000971	time 2.0198 (2.2063)	loss 3.8318 (4.1334)	grad_norm 1.1576 (1.1651)	
[2022-01-18 13:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1030/1251]	eta 0:08:07 lr 0.000971	time 2.3301 (2.2055)	loss 4.0072 (4.1331)	grad_norm 1.0366 (1.1641)	
[2022-01-18 13:22:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1040/1251]	eta 0:07:45 lr 0.000971	time 1.9607 (2.2048)	loss 4.0674 (4.1345)	grad_norm 1.4962 (1.1634)	
[2022-01-18 13:22:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1050/1251]	eta 0:07:23 lr 0.000971	time 2.4148 (2.2043)	loss 3.3478 (4.1354)	grad_norm 1.4461 (1.1633)	
[2022-01-18 13:23:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1060/1251]	eta 0:07:01 lr 0.000971	time 1.7992 (2.2048)	loss 4.4500 (4.1369)	grad_norm 1.2548 (1.1634)	
[2022-01-18 13:23:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1070/1251]	eta 0:06:39 lr 0.000971	time 1.8768 (2.2047)	loss 3.5773 (4.1384)	grad_norm 1.0753 (1.1636)	
[2022-01-18 13:23:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1080/1251]	eta 0:06:17 lr 0.000971	time 2.2619 (2.2057)	loss 4.4517 (4.1397)	grad_norm 1.2110 (1.1636)	
[2022-01-18 13:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1090/1251]	eta 0:05:55 lr 0.000971	time 3.0966 (2.2065)	loss 3.2429 (4.1415)	grad_norm 1.2057 (1.1631)	
[2022-01-18 13:24:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1100/1251]	eta 0:05:33 lr 0.000971	time 3.2869 (2.2075)	loss 4.3896 (4.1434)	grad_norm 1.1582 (1.1624)	
[2022-01-18 13:24:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1110/1251]	eta 0:05:11 lr 0.000971	time 1.9753 (2.2071)	loss 3.2952 (4.1466)	grad_norm 1.2118 (1.1619)	
[2022-01-18 13:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1120/1251]	eta 0:04:48 lr 0.000971	time 1.6058 (2.2057)	loss 4.4021 (4.1482)	grad_norm 1.4022 (1.1621)	
[2022-01-18 13:25:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1130/1251]	eta 0:04:26 lr 0.000971	time 2.3580 (2.2047)	loss 4.5202 (4.1482)	grad_norm 1.1972 (1.1619)	
[2022-01-18 13:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1140/1251]	eta 0:04:04 lr 0.000971	time 2.1497 (2.2039)	loss 3.1266 (4.1478)	grad_norm 1.2835 (1.1620)	
[2022-01-18 13:26:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1150/1251]	eta 0:03:42 lr 0.000971	time 1.8367 (2.2038)	loss 3.9491 (4.1474)	grad_norm 1.0178 (1.1610)	
[2022-01-18 13:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1160/1251]	eta 0:03:20 lr 0.000971	time 2.4861 (2.2052)	loss 4.4783 (4.1474)	grad_norm 0.9711 (1.1606)	
[2022-01-18 13:27:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1170/1251]	eta 0:02:58 lr 0.000971	time 2.4966 (2.2066)	loss 4.2156 (4.1473)	grad_norm 1.1064 (1.1607)	
[2022-01-18 13:27:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1180/1251]	eta 0:02:36 lr 0.000971	time 2.4130 (2.2063)	loss 3.6044 (4.1478)	grad_norm 1.0297 (1.1603)	
[2022-01-18 13:27:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1190/1251]	eta 0:02:14 lr 0.000971	time 1.8300 (2.2049)	loss 4.1193 (4.1474)	grad_norm 1.1176 (1.1603)	
[2022-01-18 13:28:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1200/1251]	eta 0:01:52 lr 0.000971	time 1.9548 (2.2036)	loss 4.8475 (4.1455)	grad_norm 0.8977 (1.1602)	
[2022-01-18 13:28:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1210/1251]	eta 0:01:30 lr 0.000971	time 2.1594 (2.2034)	loss 4.2870 (4.1426)	grad_norm 0.9516 (1.1600)	
[2022-01-18 13:28:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1220/1251]	eta 0:01:08 lr 0.000971	time 1.8884 (2.2028)	loss 4.3906 (4.1426)	grad_norm 1.3184 (1.1600)	
[2022-01-18 13:29:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1230/1251]	eta 0:00:46 lr 0.000971	time 2.2323 (2.2025)	loss 4.3719 (4.1419)	grad_norm 1.1184 (1.1595)	
[2022-01-18 13:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1240/1251]	eta 0:00:24 lr 0.000971	time 1.2978 (2.2011)	loss 4.0606 (4.1425)	grad_norm 1.1366 (1.1592)	
[2022-01-18 13:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [32/300][1250/1251]	eta 0:00:02 lr 0.000971	time 1.1676 (2.1957)	loss 4.6542 (4.1441)	grad_norm 1.0625 (1.1584)	
[2022-01-18 13:29:51 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 32 training takes 0:45:47
[2022-01-18 13:30:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.902 (18.902)	Loss 1.4771 (1.4771)	Acc@1 66.602 (66.602)	Acc@5 88.184 (88.184)	
[2022-01-18 13:30:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.306 (3.369)	Loss 1.4585 (1.4957)	Acc@1 66.504 (66.460)	Acc@5 88.965 (87.695)	
[2022-01-18 13:30:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.279 (2.573)	Loss 1.4792 (1.4966)	Acc@1 68.359 (66.592)	Acc@5 86.816 (87.649)	
[2022-01-18 13:31:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.881 (2.300)	Loss 1.5213 (1.4861)	Acc@1 66.699 (66.885)	Acc@5 87.402 (87.828)	
[2022-01-18 13:31:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.088 (2.148)	Loss 1.5194 (1.4788)	Acc@1 65.430 (66.904)	Acc@5 87.695 (88.048)	
[2022-01-18 13:31:27 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 66.884 Acc@5 88.148
[2022-01-18 13:31:27 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 66.9%
[2022-01-18 13:31:27 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 66.88%
[2022-01-18 13:31:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][0/1251]	eta 7:32:22 lr 0.000971	time 21.6969 (21.6969)	loss 4.5727 (4.5727)	grad_norm 0.9827 (0.9827)	
[2022-01-18 13:32:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][10/1251]	eta 1:23:15 lr 0.000971	time 1.7952 (4.0252)	loss 3.8949 (4.4103)	grad_norm 0.8347 (1.0204)	
[2022-01-18 13:32:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][20/1251]	eta 1:03:50 lr 0.000971	time 1.8638 (3.1118)	loss 4.6029 (4.3118)	grad_norm 1.1368 (1.0692)	
[2022-01-18 13:32:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][30/1251]	eta 0:57:55 lr 0.000971	time 1.8957 (2.8465)	loss 4.7611 (4.2233)	grad_norm 1.1219 (1.0933)	
[2022-01-18 13:33:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][40/1251]	eta 0:55:35 lr 0.000971	time 3.7235 (2.7544)	loss 4.3249 (4.1670)	grad_norm 1.7582 (1.1457)	
[2022-01-18 13:33:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][50/1251]	eta 0:53:09 lr 0.000971	time 2.4667 (2.6559)	loss 3.2188 (4.1324)	grad_norm 1.2123 (1.1481)	
[2022-01-18 13:34:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][60/1251]	eta 0:51:12 lr 0.000971	time 1.8658 (2.5802)	loss 4.6325 (4.0848)	grad_norm 1.1577 (1.1531)	
[2022-01-18 13:34:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][70/1251]	eta 0:49:46 lr 0.000971	time 1.8436 (2.5284)	loss 4.3714 (4.0887)	grad_norm 1.1229 (1.1634)	
[2022-01-18 13:34:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][80/1251]	eta 0:48:54 lr 0.000971	time 3.6534 (2.5056)	loss 4.3455 (4.1084)	grad_norm 1.3272 (1.1765)	
[2022-01-18 13:35:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][90/1251]	eta 0:47:39 lr 0.000971	time 1.8353 (2.4631)	loss 4.4249 (4.1192)	grad_norm 1.0847 (1.1769)	
[2022-01-18 13:35:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][100/1251]	eta 0:46:23 lr 0.000971	time 1.7979 (2.4179)	loss 4.3121 (4.1249)	grad_norm 1.1847 (1.1885)	
[2022-01-18 13:35:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][110/1251]	eta 0:45:40 lr 0.000971	time 1.7304 (2.4017)	loss 4.3934 (4.1285)	grad_norm 1.1484 (1.1840)	
[2022-01-18 13:36:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][120/1251]	eta 0:45:11 lr 0.000971	time 3.4511 (2.3976)	loss 4.6340 (4.1302)	grad_norm 1.2628 (1.1810)	
[2022-01-18 13:36:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][130/1251]	eta 0:44:27 lr 0.000971	time 2.2257 (2.3794)	loss 4.6907 (4.1256)	grad_norm 1.2973 (1.1777)	
[2022-01-18 13:36:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][140/1251]	eta 0:43:34 lr 0.000971	time 1.8372 (2.3532)	loss 3.7658 (4.1050)	grad_norm 1.1938 (1.1698)	
[2022-01-18 13:37:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][150/1251]	eta 0:42:50 lr 0.000971	time 1.9223 (2.3349)	loss 3.8280 (4.1073)	grad_norm 1.2993 (1.1733)	
[2022-01-18 13:37:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][160/1251]	eta 0:42:20 lr 0.000971	time 2.7502 (2.3285)	loss 4.4621 (4.1098)	grad_norm 1.1125 (1.1723)	
[2022-01-18 13:38:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][170/1251]	eta 0:41:50 lr 0.000970	time 2.2517 (2.3226)	loss 4.5271 (4.1124)	grad_norm 1.0197 (1.1683)	
[2022-01-18 13:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][180/1251]	eta 0:41:16 lr 0.000970	time 1.6759 (2.3127)	loss 4.4537 (4.1029)	grad_norm 1.4221 (1.1667)	
[2022-01-18 13:38:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][190/1251]	eta 0:40:36 lr 0.000970	time 1.8613 (2.2965)	loss 4.1691 (4.0971)	grad_norm 1.1944 (1.1625)	
[2022-01-18 13:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][200/1251]	eta 0:40:15 lr 0.000970	time 3.0357 (2.2983)	loss 3.2804 (4.0945)	grad_norm 1.0872 (1.1591)	
[2022-01-18 13:39:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][210/1251]	eta 0:39:46 lr 0.000970	time 2.1153 (2.2923)	loss 4.5674 (4.0954)	grad_norm 0.9602 (1.1584)	
[2022-01-18 13:39:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][220/1251]	eta 0:39:13 lr 0.000970	time 2.0092 (2.2826)	loss 4.3137 (4.0821)	grad_norm 1.2530 (1.1620)	
[2022-01-18 13:40:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][230/1251]	eta 0:38:42 lr 0.000970	time 1.5550 (2.2752)	loss 4.9311 (4.0875)	grad_norm 1.2002 (1.1614)	
[2022-01-18 13:40:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][240/1251]	eta 0:38:26 lr 0.000970	time 2.8123 (2.2818)	loss 3.6086 (4.0886)	grad_norm 1.0631 (1.1599)	
[2022-01-18 13:40:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][250/1251]	eta 0:38:00 lr 0.000970	time 2.4478 (2.2780)	loss 4.2889 (4.0849)	grad_norm 0.9904 (1.1605)	
[2022-01-18 13:41:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][260/1251]	eta 0:37:33 lr 0.000970	time 3.0946 (2.2737)	loss 3.1760 (4.0797)	grad_norm 1.0986 (1.1595)	
[2022-01-18 13:41:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][270/1251]	eta 0:37:05 lr 0.000970	time 1.8892 (2.2689)	loss 4.1212 (4.0808)	grad_norm 1.0888 (1.1570)	
[2022-01-18 13:42:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][280/1251]	eta 0:36:44 lr 0.000970	time 2.6462 (2.2701)	loss 4.4690 (4.0901)	grad_norm 1.2416 (1.1561)	
[2022-01-18 13:42:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][290/1251]	eta 0:36:20 lr 0.000970	time 1.9316 (2.2690)	loss 3.7856 (4.0962)	grad_norm 1.1462 (1.1537)	
[2022-01-18 13:42:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][300/1251]	eta 0:35:59 lr 0.000970	time 2.4329 (2.2709)	loss 4.4059 (4.1030)	grad_norm 1.0284 (1.1550)	
[2022-01-18 13:43:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][310/1251]	eta 0:35:29 lr 0.000970	time 1.8750 (2.2634)	loss 4.3814 (4.1029)	grad_norm 1.2108 (1.1537)	
[2022-01-18 13:43:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][320/1251]	eta 0:35:02 lr 0.000970	time 2.2288 (2.2579)	loss 3.1605 (4.1020)	grad_norm 1.1074 (1.1543)	
[2022-01-18 13:43:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][330/1251]	eta 0:34:32 lr 0.000970	time 1.5477 (2.2497)	loss 3.0555 (4.0967)	grad_norm 1.1271 (1.1585)	
[2022-01-18 13:44:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][340/1251]	eta 0:34:06 lr 0.000970	time 2.6301 (2.2468)	loss 4.4189 (4.1000)	grad_norm 1.1108 (1.1576)	
[2022-01-18 13:44:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][350/1251]	eta 0:33:41 lr 0.000970	time 2.3102 (2.2437)	loss 3.2989 (4.0984)	grad_norm 1.2919 (1.1590)	
[2022-01-18 13:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][360/1251]	eta 0:33:18 lr 0.000970	time 2.2751 (2.2432)	loss 3.5127 (4.0916)	grad_norm 1.1242 (1.1575)	
[2022-01-18 13:45:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][370/1251]	eta 0:32:57 lr 0.000970	time 2.1098 (2.2445)	loss 3.3939 (4.0907)	grad_norm 1.1998 (1.1571)	
[2022-01-18 13:45:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][380/1251]	eta 0:32:40 lr 0.000970	time 2.7193 (2.2510)	loss 4.7007 (4.0928)	grad_norm 1.3384 (1.1585)	
[2022-01-18 13:46:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][390/1251]	eta 0:32:17 lr 0.000970	time 1.8940 (2.2508)	loss 4.5990 (4.0930)	grad_norm 1.2609 (1.1602)	
[2022-01-18 13:46:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][400/1251]	eta 0:32:00 lr 0.000970	time 2.5682 (2.2564)	loss 3.3483 (4.0870)	grad_norm 1.4366 (1.1619)	
[2022-01-18 13:46:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][410/1251]	eta 0:31:34 lr 0.000970	time 2.2427 (2.2523)	loss 3.8763 (4.0893)	grad_norm 1.3909 (1.1598)	
[2022-01-18 13:47:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][420/1251]	eta 0:31:07 lr 0.000970	time 1.6726 (2.2474)	loss 3.8275 (4.0850)	grad_norm 0.9178 (1.1583)	
[2022-01-18 13:47:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][430/1251]	eta 0:30:40 lr 0.000970	time 1.9459 (2.2417)	loss 3.3159 (4.0858)	grad_norm 1.0387 (1.1599)	
[2022-01-18 13:47:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][440/1251]	eta 0:30:14 lr 0.000970	time 1.9225 (2.2380)	loss 3.4814 (4.0799)	grad_norm 1.2860 (1.1604)	
[2022-01-18 13:48:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][450/1251]	eta 0:29:50 lr 0.000970	time 1.6051 (2.2353)	loss 4.5767 (4.0815)	grad_norm 1.2276 (1.1642)	
[2022-01-18 13:48:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][460/1251]	eta 0:29:28 lr 0.000970	time 1.9062 (2.2360)	loss 4.0359 (4.0809)	grad_norm 1.1834 (1.1647)	
[2022-01-18 13:49:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][470/1251]	eta 0:29:05 lr 0.000970	time 1.7880 (2.2353)	loss 3.2873 (4.0767)	grad_norm 0.9829 (1.1645)	
[2022-01-18 13:49:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][480/1251]	eta 0:28:44 lr 0.000970	time 2.5710 (2.2368)	loss 3.6051 (4.0811)	grad_norm 1.1785 (1.1626)	
[2022-01-18 13:49:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][490/1251]	eta 0:28:21 lr 0.000970	time 2.0539 (2.2354)	loss 3.1633 (4.0755)	grad_norm 1.0987 (1.1614)	
[2022-01-18 13:50:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][500/1251]	eta 0:27:59 lr 0.000970	time 2.1681 (2.2361)	loss 4.3056 (4.0787)	grad_norm 1.0508 (1.1607)	
[2022-01-18 13:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][510/1251]	eta 0:27:37 lr 0.000970	time 2.0098 (2.2369)	loss 4.3954 (4.0816)	grad_norm 1.0853 (1.1600)	
[2022-01-18 13:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][520/1251]	eta 0:27:15 lr 0.000970	time 2.3263 (2.2369)	loss 3.2841 (4.0814)	grad_norm 1.0969 (1.1589)	
[2022-01-18 13:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][530/1251]	eta 0:26:53 lr 0.000970	time 2.6324 (2.2372)	loss 3.4031 (4.0827)	grad_norm 0.9662 (1.1592)	
[2022-01-18 13:51:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][540/1251]	eta 0:26:27 lr 0.000970	time 2.2189 (2.2334)	loss 4.3479 (4.0797)	grad_norm 1.0386 (1.1591)	
[2022-01-18 13:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][550/1251]	eta 0:26:02 lr 0.000970	time 1.7450 (2.2285)	loss 4.8644 (4.0781)	grad_norm 1.0067 (1.1587)	
[2022-01-18 13:52:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][560/1251]	eta 0:25:38 lr 0.000970	time 1.8565 (2.2263)	loss 4.3371 (4.0728)	grad_norm 1.2208 (1.1603)	
[2022-01-18 13:52:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][570/1251]	eta 0:25:14 lr 0.000970	time 2.5265 (2.2242)	loss 3.9498 (4.0741)	grad_norm 1.3432 (1.1605)	
[2022-01-18 13:52:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][580/1251]	eta 0:24:51 lr 0.000970	time 2.1701 (2.2228)	loss 3.0819 (4.0731)	grad_norm 1.1805 (1.1615)	
[2022-01-18 13:53:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][590/1251]	eta 0:24:30 lr 0.000970	time 2.9594 (2.2248)	loss 3.9302 (4.0752)	grad_norm 1.4267 (1.1618)	
[2022-01-18 13:53:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][600/1251]	eta 0:24:07 lr 0.000970	time 1.9422 (2.2231)	loss 3.5404 (4.0765)	grad_norm 1.1131 (1.1622)	
[2022-01-18 13:54:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][610/1251]	eta 0:23:44 lr 0.000970	time 1.9168 (2.2228)	loss 4.3154 (4.0776)	grad_norm 1.0139 (1.1617)	
[2022-01-18 13:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][620/1251]	eta 0:23:24 lr 0.000970	time 2.8452 (2.2258)	loss 4.4913 (4.0802)	grad_norm 1.1391 (1.1617)	
[2022-01-18 13:54:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][630/1251]	eta 0:23:02 lr 0.000970	time 3.6218 (2.2267)	loss 3.3628 (4.0871)	grad_norm 1.4060 (1.1626)	
[2022-01-18 13:55:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][640/1251]	eta 0:22:40 lr 0.000970	time 2.3277 (2.2272)	loss 4.0860 (4.0821)	grad_norm 1.2047 (1.1631)	
[2022-01-18 13:55:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][650/1251]	eta 0:22:16 lr 0.000970	time 1.9489 (2.2241)	loss 4.0886 (4.0802)	grad_norm 1.0915 (1.1630)	
[2022-01-18 13:55:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][660/1251]	eta 0:21:52 lr 0.000970	time 1.5025 (2.2216)	loss 3.6932 (4.0819)	grad_norm 0.8815 (1.1642)	
[2022-01-18 13:56:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][670/1251]	eta 0:21:31 lr 0.000970	time 2.8902 (2.2223)	loss 4.8238 (4.0873)	grad_norm 1.4051 (1.1647)	
[2022-01-18 13:56:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][680/1251]	eta 0:21:08 lr 0.000970	time 1.8972 (2.2213)	loss 3.5383 (4.0906)	grad_norm 1.2522 (1.1647)	
[2022-01-18 13:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][690/1251]	eta 0:20:46 lr 0.000970	time 2.4979 (2.2226)	loss 4.2976 (4.0891)	grad_norm 1.1364 (1.1633)	
[2022-01-18 13:57:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][700/1251]	eta 0:20:23 lr 0.000970	time 1.6301 (2.2207)	loss 4.7513 (4.0924)	grad_norm 1.4391 (1.1627)	
[2022-01-18 13:57:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][710/1251]	eta 0:20:02 lr 0.000970	time 3.1799 (2.2222)	loss 3.5800 (4.0939)	grad_norm 1.1902 (1.1618)	
[2022-01-18 13:58:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][720/1251]	eta 0:19:39 lr 0.000970	time 1.7981 (2.2217)	loss 4.2547 (4.0950)	grad_norm 1.0091 (1.1625)	
[2022-01-18 13:58:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][730/1251]	eta 0:19:17 lr 0.000970	time 2.5847 (2.2226)	loss 4.4509 (4.0949)	grad_norm 1.3620 (1.1626)	
[2022-01-18 13:58:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][740/1251]	eta 0:18:54 lr 0.000970	time 1.6804 (2.2203)	loss 3.2620 (4.0927)	grad_norm 1.0326 (1.1611)	
[2022-01-18 13:59:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][750/1251]	eta 0:18:31 lr 0.000970	time 2.8679 (2.2179)	loss 4.6534 (4.0941)	grad_norm 1.1087 (1.1605)	
[2022-01-18 13:59:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][760/1251]	eta 0:18:08 lr 0.000970	time 1.9227 (2.2159)	loss 4.3914 (4.0971)	grad_norm 1.2474 (1.1625)	
[2022-01-18 13:59:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][770/1251]	eta 0:17:45 lr 0.000970	time 2.6852 (2.2151)	loss 4.7164 (4.0987)	grad_norm 1.0193 (1.1612)	
[2022-01-18 14:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][780/1251]	eta 0:17:22 lr 0.000970	time 1.8514 (2.2142)	loss 3.4912 (4.0987)	grad_norm 1.0866 (1.1605)	
[2022-01-18 14:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][790/1251]	eta 0:17:01 lr 0.000970	time 3.0733 (2.2157)	loss 3.2864 (4.1008)	grad_norm 1.0619 (1.1605)	
[2022-01-18 14:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][800/1251]	eta 0:16:40 lr 0.000970	time 1.9323 (2.2174)	loss 3.2144 (4.0982)	grad_norm 0.9280 (1.1604)	
[2022-01-18 14:01:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][810/1251]	eta 0:16:17 lr 0.000970	time 2.2414 (2.2170)	loss 4.9665 (4.0968)	grad_norm 1.1388 (1.1615)	
[2022-01-18 14:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][820/1251]	eta 0:15:55 lr 0.000970	time 1.5793 (2.2163)	loss 4.4410 (4.0974)	grad_norm 1.0337 (1.1615)	
[2022-01-18 14:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][830/1251]	eta 0:15:32 lr 0.000970	time 2.2740 (2.2152)	loss 3.8140 (4.0965)	grad_norm 1.3575 (1.1613)	
[2022-01-18 14:02:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][840/1251]	eta 0:15:10 lr 0.000970	time 1.7390 (2.2165)	loss 3.9848 (4.0994)	grad_norm 1.0361 (1.1601)	
[2022-01-18 14:02:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][850/1251]	eta 0:14:48 lr 0.000970	time 1.8265 (2.2157)	loss 4.0380 (4.0988)	grad_norm 1.0741 (1.1594)	
[2022-01-18 14:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][860/1251]	eta 0:14:26 lr 0.000970	time 1.9748 (2.2157)	loss 4.5871 (4.1006)	grad_norm 1.3238 (1.1595)	
[2022-01-18 14:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][870/1251]	eta 0:14:03 lr 0.000970	time 1.6050 (2.2137)	loss 3.7943 (4.0980)	grad_norm 1.4368 (1.1590)	
[2022-01-18 14:03:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][880/1251]	eta 0:13:42 lr 0.000969	time 1.8864 (2.2161)	loss 3.7587 (4.0969)	grad_norm 1.2949 (1.1601)	
[2022-01-18 14:04:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][890/1251]	eta 0:13:20 lr 0.000969	time 2.4217 (2.2162)	loss 4.7363 (4.0987)	grad_norm 1.2452 (1.1611)	
[2022-01-18 14:04:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][900/1251]	eta 0:12:58 lr 0.000969	time 1.9099 (2.2166)	loss 3.3638 (4.1026)	grad_norm 0.9355 (1.1620)	
[2022-01-18 14:05:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][910/1251]	eta 0:12:35 lr 0.000969	time 1.9476 (2.2161)	loss 4.5823 (4.1042)	grad_norm 0.9284 (1.1614)	
[2022-01-18 14:05:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][920/1251]	eta 0:12:13 lr 0.000969	time 1.5926 (2.2155)	loss 4.0003 (4.1062)	grad_norm 1.2941 (1.1607)	
[2022-01-18 14:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][930/1251]	eta 0:11:50 lr 0.000969	time 1.8660 (2.2133)	loss 4.5756 (4.1055)	grad_norm 1.2381 (1.1605)	
[2022-01-18 14:06:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][940/1251]	eta 0:11:28 lr 0.000969	time 2.4222 (2.2124)	loss 4.4024 (4.1057)	grad_norm 1.0286 (1.1602)	
[2022-01-18 14:06:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][950/1251]	eta 0:11:05 lr 0.000969	time 2.1900 (2.2121)	loss 4.8895 (4.1065)	grad_norm 0.9733 (1.1599)	
[2022-01-18 14:06:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][960/1251]	eta 0:10:43 lr 0.000969	time 1.7009 (2.2114)	loss 3.4928 (4.1054)	grad_norm 0.9265 (1.1590)	
[2022-01-18 14:07:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][970/1251]	eta 0:10:21 lr 0.000969	time 1.8729 (2.2111)	loss 4.7499 (4.1069)	grad_norm 1.0222 (1.1590)	
[2022-01-18 14:07:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][980/1251]	eta 0:09:59 lr 0.000969	time 2.2406 (2.2109)	loss 3.3798 (4.1083)	grad_norm 0.9584 (1.1572)	
[2022-01-18 14:07:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][990/1251]	eta 0:09:36 lr 0.000969	time 2.2428 (2.2106)	loss 4.0324 (4.1049)	grad_norm 1.2809 (1.1560)	
[2022-01-18 14:08:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1000/1251]	eta 0:09:15 lr 0.000969	time 2.5376 (2.2122)	loss 4.2953 (4.1058)	grad_norm 1.1634 (1.1559)	
[2022-01-18 14:08:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1010/1251]	eta 0:08:53 lr 0.000969	time 2.5142 (2.2132)	loss 3.4361 (4.1030)	grad_norm 0.9559 (1.1566)	
[2022-01-18 14:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1020/1251]	eta 0:08:30 lr 0.000969	time 1.7111 (2.2116)	loss 3.7812 (4.1050)	grad_norm 1.1330 (1.1571)	
[2022-01-18 14:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1030/1251]	eta 0:08:08 lr 0.000969	time 2.4875 (2.2110)	loss 4.0483 (4.1062)	grad_norm 1.1285 (1.1569)	
[2022-01-18 14:09:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1040/1251]	eta 0:07:46 lr 0.000969	time 1.5986 (2.2101)	loss 4.4711 (4.1083)	grad_norm 1.6228 (1.1572)	
[2022-01-18 14:10:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1050/1251]	eta 0:07:24 lr 0.000969	time 2.2131 (2.2101)	loss 4.3498 (4.1102)	grad_norm 1.0878 (1.1572)	
[2022-01-18 14:10:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1060/1251]	eta 0:07:01 lr 0.000969	time 2.2102 (2.2092)	loss 4.2809 (4.1115)	grad_norm 1.1050 (1.1576)	
[2022-01-18 14:10:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1070/1251]	eta 0:06:39 lr 0.000969	time 2.5061 (2.2095)	loss 3.6791 (4.1090)	grad_norm 1.0265 (1.1574)	
[2022-01-18 14:11:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1080/1251]	eta 0:06:17 lr 0.000969	time 1.7009 (2.2078)	loss 4.0615 (4.1091)	grad_norm 1.0496 (1.1577)	
[2022-01-18 14:11:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1090/1251]	eta 0:05:55 lr 0.000969	time 1.9621 (2.2083)	loss 3.8030 (4.1087)	grad_norm 0.9470 (1.1571)	
[2022-01-18 14:12:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1100/1251]	eta 0:05:33 lr 0.000969	time 2.0661 (2.2100)	loss 4.0583 (4.1066)	grad_norm 0.9978 (1.1566)	
[2022-01-18 14:12:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1110/1251]	eta 0:05:11 lr 0.000969	time 2.1014 (2.2100)	loss 4.2636 (4.1073)	grad_norm 0.9090 (1.1556)	
[2022-01-18 14:12:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1120/1251]	eta 0:04:49 lr 0.000969	time 1.7677 (2.2089)	loss 4.8289 (4.1081)	grad_norm 0.9811 (1.1545)	
[2022-01-18 14:13:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1130/1251]	eta 0:04:27 lr 0.000969	time 2.5323 (2.2087)	loss 2.9514 (4.1086)	grad_norm 0.9944 (1.1543)	
[2022-01-18 14:13:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1140/1251]	eta 0:04:05 lr 0.000969	time 2.2655 (2.2094)	loss 3.8009 (4.1073)	grad_norm 0.8813 (1.1534)	
[2022-01-18 14:13:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1150/1251]	eta 0:03:43 lr 0.000969	time 1.9258 (2.2091)	loss 2.9052 (4.1081)	grad_norm 1.0580 (1.1536)	
[2022-01-18 14:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1160/1251]	eta 0:03:20 lr 0.000969	time 2.0508 (2.2081)	loss 4.4285 (4.1077)	grad_norm 1.1769 (1.1534)	
[2022-01-18 14:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1170/1251]	eta 0:02:58 lr 0.000969	time 2.4190 (2.2080)	loss 3.6812 (4.1082)	grad_norm 1.0747 (1.1529)	
[2022-01-18 14:14:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1180/1251]	eta 0:02:36 lr 0.000969	time 2.4292 (2.2079)	loss 4.1742 (4.1087)	grad_norm 1.2176 (1.1526)	
[2022-01-18 14:15:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1190/1251]	eta 0:02:14 lr 0.000969	time 1.5578 (2.2073)	loss 4.8978 (4.1088)	grad_norm 1.0381 (1.1524)	
[2022-01-18 14:15:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1200/1251]	eta 0:01:52 lr 0.000969	time 2.0104 (2.2065)	loss 4.6711 (4.1094)	grad_norm 1.0204 (1.1526)	
[2022-01-18 14:15:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1210/1251]	eta 0:01:30 lr 0.000969	time 2.1710 (2.2051)	loss 3.2414 (4.1082)	grad_norm 1.1962 (1.1523)	
[2022-01-18 14:16:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1220/1251]	eta 0:01:08 lr 0.000969	time 1.5436 (2.2038)	loss 5.0274 (4.1121)	grad_norm 1.1956 (1.1516)	
[2022-01-18 14:16:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1230/1251]	eta 0:00:46 lr 0.000969	time 2.3315 (2.2034)	loss 3.6423 (4.1124)	grad_norm 0.9143 (1.1506)	
[2022-01-18 14:17:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1240/1251]	eta 0:00:24 lr 0.000969	time 2.2928 (2.2025)	loss 3.6472 (4.1128)	grad_norm 0.9138 (1.1499)	
[2022-01-18 14:17:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [33/300][1250/1251]	eta 0:00:02 lr 0.000969	time 1.1667 (2.1973)	loss 4.1765 (4.1119)	grad_norm 1.0041 (1.1497)	
[2022-01-18 14:17:16 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 33 training takes 0:45:49
[2022-01-18 14:17:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 20.018 (20.018)	Loss 1.4483 (1.4483)	Acc@1 66.504 (66.504)	Acc@5 87.402 (87.402)	
[2022-01-18 14:17:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.314 (3.353)	Loss 1.3978 (1.4313)	Acc@1 69.629 (67.525)	Acc@5 89.258 (88.299)	
[2022-01-18 14:18:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.335 (2.666)	Loss 1.4040 (1.4347)	Acc@1 66.992 (67.192)	Acc@5 88.574 (88.188)	
[2022-01-18 14:18:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.279 (2.291)	Loss 1.4250 (1.4318)	Acc@1 66.211 (67.080)	Acc@5 88.867 (88.259)	
[2022-01-18 14:18:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.418 (2.209)	Loss 1.4182 (1.4330)	Acc@1 67.188 (67.023)	Acc@5 88.477 (88.269)	
[2022-01-18 14:18:54 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 67.000 Acc@5 88.266
[2022-01-18 14:18:54 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 67.0%
[2022-01-18 14:18:54 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 67.00%
[2022-01-18 14:19:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][0/1251]	eta 7:29:11 lr 0.000969	time 21.5442 (21.5442)	loss 4.4437 (4.4437)	grad_norm 1.1077 (1.1077)	
[2022-01-18 14:19:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][10/1251]	eta 1:25:10 lr 0.000969	time 1.9356 (4.1182)	loss 4.5749 (4.1090)	grad_norm 1.1293 (1.1381)	
[2022-01-18 14:20:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][20/1251]	eta 1:05:55 lr 0.000969	time 2.1413 (3.2133)	loss 4.3376 (4.0567)	grad_norm 1.0253 (1.1281)	
[2022-01-18 14:20:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][30/1251]	eta 0:57:37 lr 0.000969	time 1.4439 (2.8319)	loss 4.1563 (3.9053)	grad_norm 1.2623 (1.1712)	
[2022-01-18 14:20:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][40/1251]	eta 0:54:44 lr 0.000969	time 4.0611 (2.7126)	loss 4.3681 (4.0036)	grad_norm 1.0477 (1.1723)	
[2022-01-18 14:21:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][50/1251]	eta 0:53:32 lr 0.000969	time 3.4268 (2.6752)	loss 4.3959 (4.0212)	grad_norm 1.0847 (1.1590)	
[2022-01-18 14:21:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][60/1251]	eta 0:51:35 lr 0.000969	time 1.6941 (2.5993)	loss 4.7158 (4.0356)	grad_norm 0.9910 (1.1670)	
[2022-01-18 14:21:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][70/1251]	eta 0:49:41 lr 0.000969	time 1.9471 (2.5245)	loss 3.4961 (3.9943)	grad_norm 0.9992 (1.1709)	
[2022-01-18 14:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][80/1251]	eta 0:48:47 lr 0.000969	time 3.3426 (2.5002)	loss 3.9488 (3.9841)	grad_norm 1.0910 (1.1831)	
[2022-01-18 14:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][90/1251]	eta 0:47:54 lr 0.000969	time 1.5594 (2.4763)	loss 3.1670 (3.9878)	grad_norm 1.6252 (1.1756)	
[2022-01-18 14:22:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][100/1251]	eta 0:46:36 lr 0.000969	time 1.8175 (2.4300)	loss 4.4482 (4.0181)	grad_norm 1.4283 (1.1722)	
[2022-01-18 14:23:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][110/1251]	eta 0:45:43 lr 0.000969	time 2.0548 (2.4045)	loss 4.7434 (4.0394)	grad_norm 0.9534 (1.1783)	
[2022-01-18 14:23:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][120/1251]	eta 0:45:14 lr 0.000969	time 3.1906 (2.3998)	loss 2.8424 (4.0509)	grad_norm 1.3040 (1.1751)	
[2022-01-18 14:24:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][130/1251]	eta 0:44:39 lr 0.000969	time 1.8965 (2.3907)	loss 2.9006 (4.0389)	grad_norm 1.1054 (1.1691)	
[2022-01-18 14:24:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][140/1251]	eta 0:43:50 lr 0.000969	time 2.0499 (2.3677)	loss 4.5838 (4.0406)	grad_norm 1.3099 (1.1665)	
[2022-01-18 14:24:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][150/1251]	eta 0:43:02 lr 0.000969	time 1.9692 (2.3460)	loss 4.7617 (4.0351)	grad_norm 1.0166 (1.1646)	
[2022-01-18 14:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][160/1251]	eta 0:42:21 lr 0.000969	time 2.3581 (2.3298)	loss 2.8184 (4.0182)	grad_norm 1.1384 (1.1627)	
[2022-01-18 14:25:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][170/1251]	eta 0:41:47 lr 0.000969	time 2.4168 (2.3194)	loss 3.7054 (4.0232)	grad_norm 1.1949 (1.1599)	
[2022-01-18 14:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][180/1251]	eta 0:41:14 lr 0.000969	time 2.1589 (2.3100)	loss 4.8543 (4.0299)	grad_norm 1.1450 (1.1601)	
[2022-01-18 14:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][190/1251]	eta 0:40:44 lr 0.000969	time 2.1769 (2.3036)	loss 3.9575 (4.0243)	grad_norm 0.9899 (1.1561)	
[2022-01-18 14:26:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][200/1251]	eta 0:40:13 lr 0.000969	time 1.9368 (2.2967)	loss 4.4732 (4.0459)	grad_norm 1.1604 (1.1530)	
[2022-01-18 14:26:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][210/1251]	eta 0:39:51 lr 0.000969	time 1.9006 (2.2973)	loss 4.7443 (4.0579)	grad_norm 1.1751 (1.1506)	
[2022-01-18 14:27:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][220/1251]	eta 0:39:27 lr 0.000969	time 1.6397 (2.2961)	loss 2.7103 (4.0520)	grad_norm 1.1290 (1.1494)	
[2022-01-18 14:27:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][230/1251]	eta 0:38:56 lr 0.000969	time 2.0442 (2.2882)	loss 4.4008 (4.0552)	grad_norm 1.3001 (1.1551)	
[2022-01-18 14:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][240/1251]	eta 0:38:32 lr 0.000969	time 1.6148 (2.2869)	loss 4.3033 (4.0546)	grad_norm 0.8886 (1.1545)	
[2022-01-18 14:28:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][250/1251]	eta 0:38:03 lr 0.000969	time 1.8834 (2.2815)	loss 4.6199 (4.0443)	grad_norm 1.3534 (1.1555)	
[2022-01-18 14:28:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][260/1251]	eta 0:37:32 lr 0.000969	time 1.6107 (2.2733)	loss 4.0451 (4.0484)	grad_norm 1.2382 (1.1580)	
[2022-01-18 14:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][270/1251]	eta 0:37:02 lr 0.000969	time 1.8651 (2.2651)	loss 4.4684 (4.0590)	grad_norm 1.0129 (1.1589)	
[2022-01-18 14:29:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][280/1251]	eta 0:36:36 lr 0.000969	time 1.9038 (2.2622)	loss 3.3006 (4.0548)	grad_norm 1.4391 (1.1594)	
[2022-01-18 14:29:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][290/1251]	eta 0:36:20 lr 0.000969	time 2.0595 (2.2686)	loss 4.3184 (4.0642)	grad_norm 1.2540 (1.1588)	
[2022-01-18 14:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][300/1251]	eta 0:35:54 lr 0.000969	time 2.4423 (2.2658)	loss 4.1584 (4.0606)	grad_norm 1.2517 (1.1577)	
[2022-01-18 14:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][310/1251]	eta 0:35:30 lr 0.000969	time 2.2765 (2.2641)	loss 4.3172 (4.0624)	grad_norm 0.8933 (1.1550)	
[2022-01-18 14:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][320/1251]	eta 0:35:04 lr 0.000968	time 2.2139 (2.2606)	loss 4.6616 (4.0619)	grad_norm 1.2637 (1.1551)	
[2022-01-18 14:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][330/1251]	eta 0:34:39 lr 0.000968	time 1.5945 (2.2580)	loss 3.8271 (4.0693)	grad_norm 0.9611 (1.1585)	
[2022-01-18 14:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][340/1251]	eta 0:34:10 lr 0.000968	time 1.8112 (2.2505)	loss 4.7886 (4.0746)	grad_norm 1.2635 (1.1571)	
[2022-01-18 14:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][350/1251]	eta 0:33:45 lr 0.000968	time 2.5519 (2.2482)	loss 4.3516 (4.0731)	grad_norm 1.0096 (1.1590)	
[2022-01-18 14:32:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][360/1251]	eta 0:33:21 lr 0.000968	time 1.8268 (2.2460)	loss 3.1544 (4.0647)	grad_norm 1.1363 (1.1592)	
[2022-01-18 14:32:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][370/1251]	eta 0:33:00 lr 0.000968	time 1.9357 (2.2484)	loss 5.1382 (4.0709)	grad_norm 1.1290 (1.1581)	
[2022-01-18 14:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][380/1251]	eta 0:32:37 lr 0.000968	time 2.2713 (2.2473)	loss 4.8226 (4.0751)	grad_norm 0.9985 (1.1560)	
[2022-01-18 14:33:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][390/1251]	eta 0:32:12 lr 0.000968	time 2.5484 (2.2444)	loss 4.9485 (4.0692)	grad_norm 1.1135 (1.1608)	
[2022-01-18 14:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][400/1251]	eta 0:31:47 lr 0.000968	time 2.1672 (2.2419)	loss 3.4273 (4.0656)	grad_norm 1.0210 (1.1613)	
[2022-01-18 14:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][410/1251]	eta 0:31:27 lr 0.000968	time 2.4699 (2.2444)	loss 3.1738 (4.0590)	grad_norm 1.2323 (1.1616)	
[2022-01-18 14:34:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][420/1251]	eta 0:31:00 lr 0.000968	time 1.9229 (2.2394)	loss 4.3837 (4.0593)	grad_norm 0.9252 (1.1606)	
[2022-01-18 14:34:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][430/1251]	eta 0:30:35 lr 0.000968	time 1.9186 (2.2351)	loss 3.8884 (4.0565)	grad_norm 0.9767 (1.1590)	
[2022-01-18 14:35:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][440/1251]	eta 0:30:08 lr 0.000968	time 2.1087 (2.2304)	loss 2.7442 (4.0577)	grad_norm 1.3938 (1.1576)	
[2022-01-18 14:35:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][450/1251]	eta 0:29:45 lr 0.000968	time 2.4114 (2.2290)	loss 3.6458 (4.0605)	grad_norm 1.1021 (1.1579)	
[2022-01-18 14:36:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][460/1251]	eta 0:29:22 lr 0.000968	time 2.1203 (2.2285)	loss 2.9224 (4.0542)	grad_norm 1.1211 (1.1587)	
[2022-01-18 14:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][470/1251]	eta 0:28:59 lr 0.000968	time 1.9183 (2.2268)	loss 3.6056 (4.0588)	grad_norm 1.1031 (1.1582)	
[2022-01-18 14:36:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][480/1251]	eta 0:28:36 lr 0.000968	time 1.8587 (2.2258)	loss 4.2389 (4.0612)	grad_norm 1.0530 (1.1582)	
[2022-01-18 14:37:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][490/1251]	eta 0:28:13 lr 0.000968	time 2.5731 (2.2248)	loss 4.4845 (4.0587)	grad_norm 1.1399 (1.1572)	
[2022-01-18 14:37:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][500/1251]	eta 0:27:48 lr 0.000968	time 2.2594 (2.2220)	loss 4.3884 (4.0640)	grad_norm 1.0300 (1.1555)	
[2022-01-18 14:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][510/1251]	eta 0:27:24 lr 0.000968	time 1.9224 (2.2191)	loss 4.4524 (4.0659)	grad_norm 1.3363 (1.1554)	
[2022-01-18 14:38:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][520/1251]	eta 0:27:00 lr 0.000968	time 1.6325 (2.2163)	loss 4.9637 (4.0661)	grad_norm 1.1862 (1.1536)	
[2022-01-18 14:38:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][530/1251]	eta 0:26:40 lr 0.000968	time 3.4910 (2.2200)	loss 4.6855 (4.0690)	grad_norm 1.0390 (1.1533)	
[2022-01-18 14:38:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][540/1251]	eta 0:26:21 lr 0.000968	time 2.5276 (2.2236)	loss 3.4419 (4.0701)	grad_norm 1.1024 (1.1542)	
[2022-01-18 14:39:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][550/1251]	eta 0:26:00 lr 0.000968	time 2.7119 (2.2255)	loss 4.9899 (4.0770)	grad_norm 1.1407 (1.1543)	
[2022-01-18 14:39:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][560/1251]	eta 0:25:37 lr 0.000968	time 1.5950 (2.2251)	loss 3.9006 (4.0809)	grad_norm 0.9670 (1.1545)	
[2022-01-18 14:40:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][570/1251]	eta 0:25:12 lr 0.000968	time 1.8854 (2.2206)	loss 4.5114 (4.0812)	grad_norm 1.0494 (1.1537)	
[2022-01-18 14:40:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][580/1251]	eta 0:24:47 lr 0.000968	time 2.0699 (2.2168)	loss 4.1378 (4.0838)	grad_norm 1.3970 (1.1517)	
[2022-01-18 14:40:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][590/1251]	eta 0:24:24 lr 0.000968	time 1.7024 (2.2160)	loss 3.0635 (4.0841)	grad_norm 1.2862 (1.1514)	
[2022-01-18 14:41:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][600/1251]	eta 0:24:02 lr 0.000968	time 2.2945 (2.2151)	loss 3.7276 (4.0777)	grad_norm 1.0267 (1.1513)	
[2022-01-18 14:41:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][610/1251]	eta 0:23:39 lr 0.000968	time 1.8425 (2.2145)	loss 4.1989 (4.0754)	grad_norm 1.0640 (1.1516)	
[2022-01-18 14:41:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][620/1251]	eta 0:23:17 lr 0.000968	time 2.0348 (2.2154)	loss 4.6902 (4.0739)	grad_norm 1.0766 (1.1526)	
[2022-01-18 14:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][630/1251]	eta 0:22:57 lr 0.000968	time 1.9013 (2.2175)	loss 2.9035 (4.0730)	grad_norm 1.2393 (1.1522)	
[2022-01-18 14:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][640/1251]	eta 0:22:36 lr 0.000968	time 2.1757 (2.2200)	loss 4.2185 (4.0762)	grad_norm 0.9970 (1.1513)	
[2022-01-18 14:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][650/1251]	eta 0:22:15 lr 0.000968	time 2.0881 (2.2221)	loss 4.3385 (4.0813)	grad_norm 0.9573 (1.1499)	
[2022-01-18 14:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][660/1251]	eta 0:21:51 lr 0.000968	time 1.6365 (2.2185)	loss 4.0673 (4.0795)	grad_norm 1.0273 (1.1494)	
[2022-01-18 14:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][670/1251]	eta 0:21:27 lr 0.000968	time 1.9590 (2.2157)	loss 3.8514 (4.0811)	grad_norm 1.1501 (1.1475)	
[2022-01-18 14:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][680/1251]	eta 0:21:04 lr 0.000968	time 1.9381 (2.2144)	loss 3.8198 (4.0846)	grad_norm 1.3625 (1.1469)	
[2022-01-18 14:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][690/1251]	eta 0:20:42 lr 0.000968	time 2.7618 (2.2156)	loss 4.5189 (4.0854)	grad_norm 1.1353 (1.1473)	
[2022-01-18 14:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][700/1251]	eta 0:20:22 lr 0.000968	time 1.7003 (2.2178)	loss 4.4748 (4.0880)	grad_norm 1.1873 (1.1470)	
[2022-01-18 14:45:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][710/1251]	eta 0:19:58 lr 0.000968	time 2.2435 (2.2162)	loss 4.9108 (4.0923)	grad_norm 0.9534 (1.1475)	
[2022-01-18 14:45:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][720/1251]	eta 0:19:35 lr 0.000968	time 1.7269 (2.2134)	loss 4.3292 (4.0959)	grad_norm 0.9641 (1.1463)	
[2022-01-18 14:45:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][730/1251]	eta 0:19:11 lr 0.000968	time 1.4887 (2.2104)	loss 3.6471 (4.0956)	grad_norm 1.3665 (1.1466)	
[2022-01-18 14:46:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][740/1251]	eta 0:18:48 lr 0.000968	time 1.8830 (2.2083)	loss 4.4310 (4.0980)	grad_norm 1.2487 (1.1468)	
[2022-01-18 14:46:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][750/1251]	eta 0:18:26 lr 0.000968	time 2.2026 (2.2088)	loss 3.9405 (4.1004)	grad_norm 1.2649 (1.1466)	
[2022-01-18 14:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][760/1251]	eta 0:18:04 lr 0.000968	time 1.8478 (2.2096)	loss 2.9472 (4.1031)	grad_norm 1.1556 (1.1455)	
[2022-01-18 14:47:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][770/1251]	eta 0:17:42 lr 0.000968	time 2.1163 (2.2097)	loss 3.4323 (4.0976)	grad_norm 1.1918 (1.1455)	
[2022-01-18 14:47:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][780/1251]	eta 0:17:21 lr 0.000968	time 2.2941 (2.2105)	loss 4.3683 (4.1005)	grad_norm 0.9128 (1.1444)	
[2022-01-18 14:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][790/1251]	eta 0:16:58 lr 0.000968	time 1.8847 (2.2098)	loss 4.4222 (4.0992)	grad_norm 1.1098 (1.1442)	
[2022-01-18 14:48:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][800/1251]	eta 0:16:36 lr 0.000968	time 2.3694 (2.2087)	loss 4.0404 (4.1003)	grad_norm 0.9144 (1.1450)	
[2022-01-18 14:48:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][810/1251]	eta 0:16:13 lr 0.000968	time 1.9263 (2.2076)	loss 4.8337 (4.1026)	grad_norm 1.3547 (1.1451)	
[2022-01-18 14:49:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][820/1251]	eta 0:15:51 lr 0.000968	time 2.7189 (2.2088)	loss 3.2240 (4.1012)	grad_norm 1.1837 (1.1454)	
[2022-01-18 14:49:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][830/1251]	eta 0:15:28 lr 0.000968	time 1.8720 (2.2065)	loss 4.8201 (4.1002)	grad_norm 1.0236 (1.1435)	
[2022-01-18 14:49:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][840/1251]	eta 0:15:06 lr 0.000968	time 2.6189 (2.2049)	loss 3.5286 (4.1022)	grad_norm 0.9679 (1.1424)	
[2022-01-18 14:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][850/1251]	eta 0:14:43 lr 0.000968	time 1.8781 (2.2037)	loss 5.0520 (4.1046)	grad_norm 1.2624 (1.1420)	
[2022-01-18 14:50:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][860/1251]	eta 0:14:21 lr 0.000968	time 3.0227 (2.2037)	loss 4.1260 (4.1040)	grad_norm 1.0294 (1.1413)	
[2022-01-18 14:50:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][870/1251]	eta 0:13:59 lr 0.000968	time 2.2276 (2.2032)	loss 4.4691 (4.1057)	grad_norm 0.9981 (1.1411)	
[2022-01-18 14:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][880/1251]	eta 0:13:37 lr 0.000968	time 2.4164 (2.2035)	loss 4.2943 (4.1061)	grad_norm 1.1536 (1.1423)	
[2022-01-18 14:51:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][890/1251]	eta 0:13:15 lr 0.000968	time 1.8452 (2.2039)	loss 4.9021 (4.1081)	grad_norm 0.9081 (1.1426)	
[2022-01-18 14:52:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][900/1251]	eta 0:12:53 lr 0.000968	time 3.4449 (2.2045)	loss 4.2754 (4.1094)	grad_norm 1.2020 (1.1440)	
[2022-01-18 14:52:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][910/1251]	eta 0:12:31 lr 0.000968	time 1.5747 (2.2035)	loss 4.0420 (4.1113)	grad_norm 1.0633 (1.1446)	
[2022-01-18 14:52:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][920/1251]	eta 0:12:09 lr 0.000968	time 2.3348 (2.2039)	loss 3.5213 (4.1127)	grad_norm 0.9275 (1.1440)	
[2022-01-18 14:53:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][930/1251]	eta 0:11:46 lr 0.000968	time 1.9587 (2.2021)	loss 3.0242 (4.1126)	grad_norm 1.2654 (1.1434)	
[2022-01-18 14:53:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][940/1251]	eta 0:11:24 lr 0.000968	time 2.7956 (2.2022)	loss 4.9151 (4.1114)	grad_norm 1.2615 (1.1443)	
[2022-01-18 14:53:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][950/1251]	eta 0:11:02 lr 0.000968	time 1.8237 (2.2009)	loss 4.2304 (4.1121)	grad_norm 1.2008 (1.1449)	
[2022-01-18 14:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][960/1251]	eta 0:10:40 lr 0.000968	time 2.7793 (2.2011)	loss 3.2440 (4.1083)	grad_norm 1.0273 (1.1440)	
[2022-01-18 14:54:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][970/1251]	eta 0:10:18 lr 0.000968	time 1.8971 (2.2004)	loss 3.4794 (4.1079)	grad_norm 1.1603 (1.1437)	
[2022-01-18 14:54:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][980/1251]	eta 0:09:56 lr 0.000968	time 3.1933 (2.2005)	loss 3.4750 (4.1087)	grad_norm 0.9646 (1.1430)	
[2022-01-18 14:55:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][990/1251]	eta 0:09:34 lr 0.000968	time 2.6564 (2.2011)	loss 4.5625 (4.1093)	grad_norm 1.2816 (1.1424)	
[2022-01-18 14:55:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1000/1251]	eta 0:09:12 lr 0.000967	time 2.1824 (2.2007)	loss 4.4134 (4.1067)	grad_norm 1.1742 (1.1430)	
[2022-01-18 14:55:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1010/1251]	eta 0:08:50 lr 0.000967	time 2.1238 (2.2006)	loss 4.1426 (4.1069)	grad_norm 0.9987 (1.1429)	
[2022-01-18 14:56:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1020/1251]	eta 0:08:28 lr 0.000967	time 3.9936 (2.2019)	loss 4.2788 (4.1085)	grad_norm 0.9401 (1.1420)	
[2022-01-18 14:56:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1030/1251]	eta 0:08:06 lr 0.000967	time 1.8705 (2.2014)	loss 4.3441 (4.1075)	grad_norm 1.8210 (1.1425)	
[2022-01-18 14:57:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1040/1251]	eta 0:07:44 lr 0.000967	time 1.9314 (2.2011)	loss 3.3892 (4.1074)	grad_norm 1.8632 (1.1433)	
[2022-01-18 14:57:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1050/1251]	eta 0:07:22 lr 0.000967	time 1.8933 (2.2008)	loss 3.1783 (4.1054)	grad_norm 1.1687 (1.1429)	
[2022-01-18 14:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1060/1251]	eta 0:07:00 lr 0.000967	time 2.6334 (2.1999)	loss 4.8973 (4.1062)	grad_norm 1.0926 (1.1425)	
[2022-01-18 14:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1070/1251]	eta 0:06:37 lr 0.000967	time 2.1828 (2.1981)	loss 3.3673 (4.1087)	grad_norm 1.1987 (1.1422)	
[2022-01-18 14:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1080/1251]	eta 0:06:15 lr 0.000967	time 1.9049 (2.1971)	loss 3.7000 (4.1078)	grad_norm 1.3752 (1.1421)	
[2022-01-18 14:58:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1090/1251]	eta 0:05:53 lr 0.000967	time 2.0279 (2.1962)	loss 3.5391 (4.1052)	grad_norm 1.1832 (1.1418)	
[2022-01-18 14:59:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1100/1251]	eta 0:05:32 lr 0.000967	time 4.2534 (2.2000)	loss 3.7334 (4.1067)	grad_norm 1.1159 (1.1414)	
[2022-01-18 14:59:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1110/1251]	eta 0:05:10 lr 0.000967	time 2.3108 (2.2006)	loss 4.3517 (4.1053)	grad_norm 1.0261 (1.1409)	
[2022-01-18 15:00:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1120/1251]	eta 0:04:48 lr 0.000967	time 2.4877 (2.1999)	loss 5.0666 (4.1071)	grad_norm 1.1192 (1.1402)	
[2022-01-18 15:00:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1130/1251]	eta 0:04:26 lr 0.000967	time 2.2705 (2.1994)	loss 3.8788 (4.1074)	grad_norm 1.0936 (1.1400)	
[2022-01-18 15:00:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1140/1251]	eta 0:04:04 lr 0.000967	time 3.2230 (2.1989)	loss 3.6315 (4.1079)	grad_norm 1.3475 (1.1405)	
[2022-01-18 15:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1150/1251]	eta 0:03:41 lr 0.000967	time 1.8671 (2.1978)	loss 4.3595 (4.1096)	grad_norm 1.3613 (1.1404)	
[2022-01-18 15:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1160/1251]	eta 0:03:19 lr 0.000967	time 2.0693 (2.1966)	loss 4.1061 (4.1110)	grad_norm 1.2956 (1.1405)	
[2022-01-18 15:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1170/1251]	eta 0:02:57 lr 0.000967	time 1.9334 (2.1968)	loss 3.4038 (4.1092)	grad_norm 1.1911 (1.1405)	
[2022-01-18 15:02:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1180/1251]	eta 0:02:36 lr 0.000967	time 3.3812 (2.1973)	loss 4.6191 (4.1100)	grad_norm 1.3053 (1.1410)	
[2022-01-18 15:02:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1190/1251]	eta 0:02:13 lr 0.000967	time 1.7102 (2.1964)	loss 2.9634 (4.1111)	grad_norm 1.0924 (1.1402)	
[2022-01-18 15:02:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1200/1251]	eta 0:01:52 lr 0.000967	time 2.3524 (2.1967)	loss 4.7926 (4.1078)	grad_norm 1.0112 (1.1407)	
[2022-01-18 15:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1210/1251]	eta 0:01:30 lr 0.000967	time 1.7511 (2.1970)	loss 3.6982 (4.1101)	grad_norm 1.1649 (1.1407)	
[2022-01-18 15:03:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1220/1251]	eta 0:01:08 lr 0.000967	time 3.4057 (2.1976)	loss 3.8588 (4.1107)	grad_norm 1.0784 (1.1401)	
[2022-01-18 15:03:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1230/1251]	eta 0:00:46 lr 0.000967	time 2.1890 (2.1965)	loss 4.2984 (4.1098)	grad_norm 1.0634 (1.1399)	
[2022-01-18 15:04:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1240/1251]	eta 0:00:24 lr 0.000967	time 1.2258 (2.1949)	loss 3.3808 (4.1069)	grad_norm 1.1026 (1.1404)	
[2022-01-18 15:04:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [34/300][1250/1251]	eta 0:00:02 lr 0.000967	time 1.1720 (2.1895)	loss 4.3056 (4.1073)	grad_norm 1.3234 (1.1405)	
[2022-01-18 15:04:33 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 34 training takes 0:45:39
[2022-01-18 15:04:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 20.712 (20.712)	Loss 1.4278 (1.4278)	Acc@1 66.309 (66.309)	Acc@5 88.379 (88.379)	
[2022-01-18 15:05:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.240 (3.345)	Loss 1.4910 (1.4172)	Acc@1 66.211 (66.886)	Acc@5 87.305 (88.015)	
[2022-01-18 15:05:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.919 (2.480)	Loss 1.3642 (1.4152)	Acc@1 69.141 (67.025)	Acc@5 89.258 (88.188)	
[2022-01-18 15:05:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.202 (2.279)	Loss 1.2798 (1.4250)	Acc@1 69.043 (66.954)	Acc@5 91.504 (88.158)	
[2022-01-18 15:06:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.331 (2.141)	Loss 1.3480 (1.4242)	Acc@1 68.652 (67.056)	Acc@5 89.648 (88.088)	
[2022-01-18 15:06:08 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 67.076 Acc@5 88.094
[2022-01-18 15:06:08 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 67.1%
[2022-01-18 15:06:08 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 67.08%
[2022-01-18 15:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][0/1251]	eta 7:20:14 lr 0.000967	time 21.1150 (21.1150)	loss 4.3892 (4.3892)	grad_norm 1.1641 (1.1641)	
[2022-01-18 15:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][10/1251]	eta 1:21:54 lr 0.000967	time 1.3101 (3.9599)	loss 3.5356 (4.0279)	grad_norm 1.0431 (1.1050)	
[2022-01-18 15:07:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][20/1251]	eta 1:01:35 lr 0.000967	time 1.5089 (3.0023)	loss 4.3870 (3.8962)	grad_norm 0.9263 (1.0726)	
[2022-01-18 15:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][30/1251]	eta 0:55:51 lr 0.000967	time 1.8393 (2.7450)	loss 3.8670 (3.9441)	grad_norm 0.9591 (1.0790)	
[2022-01-18 15:07:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][40/1251]	eta 0:53:36 lr 0.000967	time 6.8634 (2.6559)	loss 4.2217 (4.0295)	grad_norm 0.9718 (1.1049)	
[2022-01-18 15:08:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][50/1251]	eta 0:51:44 lr 0.000967	time 1.5126 (2.5851)	loss 3.1882 (4.0174)	grad_norm 1.3960 (1.1200)	
[2022-01-18 15:08:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][60/1251]	eta 0:49:54 lr 0.000967	time 1.8612 (2.5141)	loss 4.5507 (4.0430)	grad_norm 0.9353 (1.1151)	
[2022-01-18 15:09:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][70/1251]	eta 0:48:26 lr 0.000967	time 2.1720 (2.4612)	loss 4.3594 (4.0648)	grad_norm 1.1343 (1.1200)	
[2022-01-18 15:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][80/1251]	eta 0:47:47 lr 0.000967	time 4.2877 (2.4485)	loss 4.1532 (4.0489)	grad_norm 1.0027 (1.1315)	
[2022-01-18 15:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][90/1251]	eta 0:47:01 lr 0.000967	time 2.4036 (2.4299)	loss 3.7355 (4.0374)	grad_norm 1.4468 (1.1400)	
[2022-01-18 15:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][100/1251]	eta 0:46:09 lr 0.000967	time 1.8435 (2.4061)	loss 3.0104 (4.0414)	grad_norm 1.1518 (1.1393)	
[2022-01-18 15:10:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][110/1251]	eta 0:45:06 lr 0.000967	time 1.9113 (2.3720)	loss 3.6987 (4.0195)	grad_norm 1.1082 (1.1333)	
[2022-01-18 15:10:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][120/1251]	eta 0:44:33 lr 0.000967	time 4.2158 (2.3634)	loss 4.6762 (4.0398)	grad_norm 1.6000 (1.1423)	
[2022-01-18 15:11:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][130/1251]	eta 0:43:54 lr 0.000967	time 2.4688 (2.3499)	loss 3.8977 (4.0440)	grad_norm 1.0432 (1.1366)	
[2022-01-18 15:11:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][140/1251]	eta 0:43:05 lr 0.000967	time 1.7229 (2.3273)	loss 3.0906 (4.0552)	grad_norm 1.1373 (1.1353)	
[2022-01-18 15:11:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][150/1251]	eta 0:42:29 lr 0.000967	time 1.8251 (2.3154)	loss 4.3244 (4.0719)	grad_norm 1.2650 (1.1461)	
[2022-01-18 15:12:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][160/1251]	eta 0:42:15 lr 0.000967	time 3.5404 (2.3244)	loss 3.5158 (4.0624)	grad_norm 0.9222 (1.1463)	
[2022-01-18 15:12:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][170/1251]	eta 0:41:36 lr 0.000967	time 1.7831 (2.3096)	loss 4.4607 (4.0654)	grad_norm 1.2701 (1.1469)	
[2022-01-18 15:13:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][180/1251]	eta 0:41:11 lr 0.000967	time 2.0034 (2.3076)	loss 4.3373 (4.0633)	grad_norm 1.0881 (1.1485)	
[2022-01-18 15:13:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][190/1251]	eta 0:40:32 lr 0.000967	time 2.1881 (2.2925)	loss 4.4519 (4.0699)	grad_norm 1.0918 (1.1469)	
[2022-01-18 15:13:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][200/1251]	eta 0:40:02 lr 0.000967	time 3.0096 (2.2859)	loss 3.0967 (4.0672)	grad_norm 0.9812 (1.1459)	
[2022-01-18 15:14:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][210/1251]	eta 0:39:27 lr 0.000967	time 2.4859 (2.2745)	loss 4.0983 (4.0758)	grad_norm 0.9968 (1.1473)	
[2022-01-18 15:14:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][220/1251]	eta 0:38:59 lr 0.000967	time 1.9112 (2.2694)	loss 4.2279 (4.0835)	grad_norm 1.0072 (1.1461)	
[2022-01-18 15:14:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][230/1251]	eta 0:38:35 lr 0.000967	time 3.0547 (2.2682)	loss 4.0865 (4.0741)	grad_norm 0.9882 (1.1401)	
[2022-01-18 15:15:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][240/1251]	eta 0:38:08 lr 0.000967	time 1.8768 (2.2635)	loss 4.6357 (4.0706)	grad_norm 1.4260 (1.1406)	
[2022-01-18 15:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][250/1251]	eta 0:37:44 lr 0.000967	time 2.7861 (2.2618)	loss 4.0244 (4.0806)	grad_norm 1.0525 (1.1399)	
[2022-01-18 15:15:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][260/1251]	eta 0:37:14 lr 0.000967	time 2.1836 (2.2548)	loss 2.9930 (4.0808)	grad_norm 1.0237 (1.1368)	
[2022-01-18 15:16:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][270/1251]	eta 0:36:50 lr 0.000967	time 2.7510 (2.2532)	loss 4.1578 (4.0920)	grad_norm 1.0910 (1.1388)	
[2022-01-18 15:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][280/1251]	eta 0:36:31 lr 0.000967	time 2.0148 (2.2565)	loss 4.5647 (4.0858)	grad_norm 0.9748 (1.1379)	
[2022-01-18 15:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][290/1251]	eta 0:36:05 lr 0.000967	time 1.5673 (2.2531)	loss 4.4592 (4.0897)	grad_norm 1.2392 (1.1382)	
[2022-01-18 15:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][300/1251]	eta 0:35:37 lr 0.000967	time 1.7903 (2.2477)	loss 4.7112 (4.0899)	grad_norm 1.2411 (1.1405)	
[2022-01-18 15:17:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][310/1251]	eta 0:35:12 lr 0.000967	time 2.8764 (2.2451)	loss 4.1750 (4.0845)	grad_norm 1.1880 (1.1417)	
[2022-01-18 15:18:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][320/1251]	eta 0:34:46 lr 0.000967	time 2.0569 (2.2406)	loss 3.2766 (4.0854)	grad_norm 1.0282 (1.1390)	
[2022-01-18 15:18:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][330/1251]	eta 0:34:21 lr 0.000967	time 2.0935 (2.2383)	loss 3.4067 (4.0988)	grad_norm 0.9810 (1.1377)	
[2022-01-18 15:18:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][340/1251]	eta 0:33:55 lr 0.000967	time 1.9677 (2.2339)	loss 4.4201 (4.1073)	grad_norm 1.0202 (1.1386)	
[2022-01-18 15:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][350/1251]	eta 0:33:31 lr 0.000967	time 2.6088 (2.2323)	loss 3.3323 (4.1043)	grad_norm 0.9675 (1.1425)	
[2022-01-18 15:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][360/1251]	eta 0:33:06 lr 0.000967	time 1.8873 (2.2300)	loss 4.4272 (4.1037)	grad_norm 0.9417 (1.1392)	
[2022-01-18 15:19:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][370/1251]	eta 0:32:44 lr 0.000967	time 2.1495 (2.2302)	loss 4.6664 (4.1076)	grad_norm 0.9851 (1.1388)	
[2022-01-18 15:20:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][380/1251]	eta 0:32:20 lr 0.000967	time 1.8900 (2.2275)	loss 4.6992 (4.1113)	grad_norm 1.2523 (1.1407)	
[2022-01-18 15:20:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][390/1251]	eta 0:32:00 lr 0.000967	time 2.0786 (2.2300)	loss 4.4990 (4.1132)	grad_norm 1.3493 (1.1406)	
[2022-01-18 15:21:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][400/1251]	eta 0:31:35 lr 0.000967	time 1.8914 (2.2272)	loss 4.6950 (4.1154)	grad_norm 1.1277 (1.1416)	
[2022-01-18 15:21:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][410/1251]	eta 0:31:13 lr 0.000967	time 2.1552 (2.2283)	loss 4.9256 (4.1215)	grad_norm 0.9835 (1.1420)	
[2022-01-18 15:21:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][420/1251]	eta 0:30:50 lr 0.000966	time 2.3677 (2.2268)	loss 3.9094 (4.1242)	grad_norm 1.0046 (1.1386)	
[2022-01-18 15:22:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][430/1251]	eta 0:30:26 lr 0.000966	time 1.5908 (2.2249)	loss 4.1200 (4.1203)	grad_norm 1.0020 (1.1353)	
[2022-01-18 15:22:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][440/1251]	eta 0:30:03 lr 0.000966	time 2.2979 (2.2244)	loss 4.6629 (4.1214)	grad_norm 1.3384 (1.1354)	
[2022-01-18 15:22:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][450/1251]	eta 0:29:40 lr 0.000966	time 2.1059 (2.2229)	loss 3.8863 (4.1208)	grad_norm 0.9542 (1.1326)	
[2022-01-18 15:23:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][460/1251]	eta 0:29:18 lr 0.000966	time 2.1130 (2.2234)	loss 4.7117 (4.1219)	grad_norm 1.1356 (1.1324)	
[2022-01-18 15:23:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][470/1251]	eta 0:28:55 lr 0.000966	time 2.5666 (2.2216)	loss 4.3175 (4.1253)	grad_norm 0.9521 (1.1335)	
[2022-01-18 15:23:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][480/1251]	eta 0:28:32 lr 0.000966	time 2.3680 (2.2206)	loss 4.7970 (4.1232)	grad_norm 1.0928 (1.1326)	
[2022-01-18 15:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][490/1251]	eta 0:28:07 lr 0.000966	time 1.8487 (2.2176)	loss 3.8365 (4.1251)	grad_norm 1.0224 (1.1334)	
[2022-01-18 15:24:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][500/1251]	eta 0:27:45 lr 0.000966	time 2.2613 (2.2182)	loss 4.1183 (4.1201)	grad_norm 1.1138 (1.1339)	
[2022-01-18 15:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][510/1251]	eta 0:27:22 lr 0.000966	time 2.5605 (2.2168)	loss 4.4304 (4.1200)	grad_norm 1.3192 (1.1348)	
[2022-01-18 15:25:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][520/1251]	eta 0:26:59 lr 0.000966	time 2.8173 (2.2155)	loss 4.4724 (4.1216)	grad_norm 1.1729 (1.1363)	
[2022-01-18 15:25:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][530/1251]	eta 0:26:36 lr 0.000966	time 1.8622 (2.2140)	loss 3.8627 (4.1215)	grad_norm 1.0569 (1.1345)	
[2022-01-18 15:26:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][540/1251]	eta 0:26:14 lr 0.000966	time 1.8599 (2.2145)	loss 4.9327 (4.1198)	grad_norm 0.9115 (1.1338)	
[2022-01-18 15:26:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][550/1251]	eta 0:25:52 lr 0.000966	time 2.6729 (2.2149)	loss 3.4605 (4.1211)	grad_norm 0.9588 (1.1318)	
[2022-01-18 15:26:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][560/1251]	eta 0:25:28 lr 0.000966	time 2.2386 (2.2118)	loss 4.0772 (4.1216)	grad_norm 1.0929 (1.1315)	
[2022-01-18 15:27:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][570/1251]	eta 0:25:05 lr 0.000966	time 1.5657 (2.2112)	loss 3.3109 (4.1256)	grad_norm 1.2423 (1.1313)	
[2022-01-18 15:27:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][580/1251]	eta 0:24:43 lr 0.000966	time 1.9177 (2.2103)	loss 3.6416 (4.1285)	grad_norm 0.9855 (1.1314)	
[2022-01-18 15:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][590/1251]	eta 0:24:21 lr 0.000966	time 3.1876 (2.2104)	loss 4.7027 (4.1278)	grad_norm 1.2485 (1.1325)	
[2022-01-18 15:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][600/1251]	eta 0:23:57 lr 0.000966	time 1.8548 (2.2082)	loss 3.8637 (4.1289)	grad_norm 1.0935 (1.1332)	
[2022-01-18 15:28:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][610/1251]	eta 0:23:33 lr 0.000966	time 1.5795 (2.2055)	loss 4.2395 (4.1297)	grad_norm 0.9945 (1.1332)	
[2022-01-18 15:28:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][620/1251]	eta 0:23:12 lr 0.000966	time 2.5729 (2.2074)	loss 3.5649 (4.1283)	grad_norm 1.4261 (1.1333)	
[2022-01-18 15:29:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][630/1251]	eta 0:22:51 lr 0.000966	time 2.7684 (2.2090)	loss 3.0960 (4.1217)	grad_norm 1.2737 (1.1331)	
[2022-01-18 15:29:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][640/1251]	eta 0:22:28 lr 0.000966	time 1.8915 (2.2067)	loss 3.6376 (4.1191)	grad_norm 0.9933 (1.1321)	
[2022-01-18 15:30:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][650/1251]	eta 0:22:06 lr 0.000966	time 1.8061 (2.2068)	loss 4.4178 (4.1202)	grad_norm 0.9516 (1.1307)	
[2022-01-18 15:30:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][660/1251]	eta 0:21:45 lr 0.000966	time 3.1135 (2.2091)	loss 4.1577 (4.1181)	grad_norm 0.9528 (1.1303)	
[2022-01-18 15:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][670/1251]	eta 0:21:24 lr 0.000966	time 2.2052 (2.2115)	loss 4.1866 (4.1148)	grad_norm 1.0728 (1.1298)	
[2022-01-18 15:31:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][680/1251]	eta 0:21:01 lr 0.000966	time 1.7268 (2.2096)	loss 4.2992 (4.1162)	grad_norm 1.1006 (1.1296)	
[2022-01-18 15:31:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][690/1251]	eta 0:20:38 lr 0.000966	time 1.6965 (2.2075)	loss 4.3161 (4.1131)	grad_norm 1.2606 (1.1289)	
[2022-01-18 15:31:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][700/1251]	eta 0:20:15 lr 0.000966	time 3.0182 (2.2065)	loss 4.1986 (4.1109)	grad_norm 1.1326 (1.1304)	
[2022-01-18 15:32:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][710/1251]	eta 0:19:53 lr 0.000966	time 2.5400 (2.2054)	loss 4.1629 (4.1128)	grad_norm 1.2096 (1.1312)	
[2022-01-18 15:32:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][720/1251]	eta 0:19:31 lr 0.000966	time 2.3627 (2.2063)	loss 4.4619 (4.1116)	grad_norm 1.2223 (1.1311)	
[2022-01-18 15:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][730/1251]	eta 0:19:09 lr 0.000966	time 1.9053 (2.2068)	loss 4.9450 (4.1104)	grad_norm 1.0330 (1.1305)	
[2022-01-18 15:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][740/1251]	eta 0:18:48 lr 0.000966	time 2.8620 (2.2079)	loss 4.2314 (4.1058)	grad_norm 1.1442 (1.1321)	
[2022-01-18 15:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][750/1251]	eta 0:18:25 lr 0.000966	time 1.8684 (2.2073)	loss 3.4130 (4.1015)	grad_norm 1.0408 (1.1328)	
[2022-01-18 15:34:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][760/1251]	eta 0:18:03 lr 0.000966	time 1.8923 (2.2065)	loss 4.4317 (4.1067)	grad_norm 1.0552 (1.1343)	
[2022-01-18 15:34:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][770/1251]	eta 0:17:39 lr 0.000966	time 1.7500 (2.2020)	loss 3.0683 (4.1036)	grad_norm 1.1675 (1.1349)	
[2022-01-18 15:34:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][780/1251]	eta 0:17:16 lr 0.000966	time 1.8824 (2.2008)	loss 4.7361 (4.1040)	grad_norm 1.1129 (1.1366)	
[2022-01-18 15:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][790/1251]	eta 0:16:53 lr 0.000966	time 2.1149 (2.1989)	loss 3.1863 (4.1023)	grad_norm 0.8906 (1.1368)	
[2022-01-18 15:35:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][800/1251]	eta 0:16:32 lr 0.000966	time 2.8865 (2.2006)	loss 4.4958 (4.1043)	grad_norm 1.0646 (1.1361)	
[2022-01-18 15:35:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][810/1251]	eta 0:16:10 lr 0.000966	time 2.2423 (2.2016)	loss 4.1341 (4.1055)	grad_norm 1.0055 (1.1369)	
[2022-01-18 15:36:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][820/1251]	eta 0:15:49 lr 0.000966	time 2.3554 (2.2033)	loss 4.4566 (4.1066)	grad_norm 1.2100 (1.1385)	
[2022-01-18 15:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][830/1251]	eta 0:15:27 lr 0.000966	time 1.9487 (2.2036)	loss 3.4031 (4.1068)	grad_norm 0.9072 (1.1373)	
[2022-01-18 15:37:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][840/1251]	eta 0:15:05 lr 0.000966	time 3.1502 (2.2041)	loss 4.6651 (4.1075)	grad_norm 1.2063 (1.1370)	
[2022-01-18 15:37:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][850/1251]	eta 0:14:43 lr 0.000966	time 1.5595 (2.2020)	loss 4.1995 (4.1067)	grad_norm 1.0863 (1.1372)	
[2022-01-18 15:37:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][860/1251]	eta 0:14:21 lr 0.000966	time 2.5765 (2.2021)	loss 4.7284 (4.1088)	grad_norm 1.0593 (1.1374)	
[2022-01-18 15:38:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][870/1251]	eta 0:13:58 lr 0.000966	time 1.8820 (2.2006)	loss 4.6547 (4.1100)	grad_norm 1.1037 (1.1369)	
[2022-01-18 15:38:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][880/1251]	eta 0:13:36 lr 0.000966	time 2.3916 (2.2003)	loss 4.9890 (4.1097)	grad_norm 0.9923 (1.1380)	
[2022-01-18 15:38:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][890/1251]	eta 0:13:13 lr 0.000966	time 1.9407 (2.1993)	loss 4.0299 (4.1075)	grad_norm 0.8748 (1.1380)	
[2022-01-18 15:39:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][900/1251]	eta 0:12:52 lr 0.000966	time 3.2326 (2.2009)	loss 3.3666 (4.1062)	grad_norm 1.0522 (1.1375)	
[2022-01-18 15:39:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][910/1251]	eta 0:12:30 lr 0.000966	time 1.8611 (2.1996)	loss 3.8108 (4.1053)	grad_norm 0.8443 (1.1369)	
[2022-01-18 15:39:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][920/1251]	eta 0:12:08 lr 0.000966	time 2.5849 (2.2009)	loss 4.6088 (4.1050)	grad_norm 1.0482 (1.1361)	
[2022-01-18 15:40:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][930/1251]	eta 0:11:46 lr 0.000966	time 2.3281 (2.2021)	loss 4.4185 (4.1066)	grad_norm 1.4379 (1.1368)	
[2022-01-18 15:40:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][940/1251]	eta 0:11:24 lr 0.000966	time 3.1128 (2.2025)	loss 3.9392 (4.1091)	grad_norm 1.0028 (1.1366)	
[2022-01-18 15:41:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][950/1251]	eta 0:11:02 lr 0.000966	time 1.9804 (2.2005)	loss 4.4603 (4.1112)	grad_norm 1.1758 (1.1375)	
[2022-01-18 15:41:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][960/1251]	eta 0:10:39 lr 0.000966	time 1.7664 (2.1986)	loss 4.2620 (4.1105)	grad_norm 0.8925 (1.1374)	
[2022-01-18 15:41:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][970/1251]	eta 0:10:17 lr 0.000966	time 1.8365 (2.1979)	loss 4.2885 (4.1101)	grad_norm 1.3288 (1.1372)	
[2022-01-18 15:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][980/1251]	eta 0:09:55 lr 0.000966	time 3.1327 (2.1968)	loss 3.9089 (4.1091)	grad_norm 0.9960 (1.1375)	
[2022-01-18 15:42:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][990/1251]	eta 0:09:33 lr 0.000966	time 2.3556 (2.1967)	loss 4.8262 (4.1097)	grad_norm 1.0123 (1.1376)	
[2022-01-18 15:42:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1000/1251]	eta 0:09:11 lr 0.000966	time 1.7347 (2.1957)	loss 3.9697 (4.1097)	grad_norm 1.0087 (1.1372)	
[2022-01-18 15:43:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1010/1251]	eta 0:08:49 lr 0.000966	time 2.0631 (2.1965)	loss 3.9586 (4.1099)	grad_norm 0.9964 (1.1375)	
[2022-01-18 15:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1020/1251]	eta 0:08:27 lr 0.000966	time 2.5580 (2.1965)	loss 4.3894 (4.1126)	grad_norm 1.1595 (1.1378)	
[2022-01-18 15:43:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1030/1251]	eta 0:08:05 lr 0.000966	time 2.1266 (2.1957)	loss 3.7629 (4.1099)	grad_norm 1.0595 (1.1375)	
[2022-01-18 15:44:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1040/1251]	eta 0:07:43 lr 0.000966	time 1.8069 (2.1949)	loss 3.7124 (4.1091)	grad_norm 0.9923 (1.1371)	
[2022-01-18 15:44:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1050/1251]	eta 0:07:21 lr 0.000966	time 1.7482 (2.1947)	loss 4.0980 (4.1109)	grad_norm 1.0975 (1.1368)	
[2022-01-18 15:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1060/1251]	eta 0:06:59 lr 0.000966	time 2.3087 (2.1954)	loss 4.0414 (4.1082)	grad_norm 1.3374 (1.1372)	
[2022-01-18 15:45:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1070/1251]	eta 0:06:37 lr 0.000966	time 1.5420 (2.1948)	loss 3.8332 (4.1074)	grad_norm 1.2570 (1.1366)	
[2022-01-18 15:45:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1080/1251]	eta 0:06:15 lr 0.000965	time 2.1615 (2.1945)	loss 3.2196 (4.1047)	grad_norm 1.1364 (1.1354)	
[2022-01-18 15:46:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1090/1251]	eta 0:05:53 lr 0.000965	time 1.5479 (2.1964)	loss 3.9068 (4.1032)	grad_norm 1.1628 (1.1353)	
[2022-01-18 15:46:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1100/1251]	eta 0:05:31 lr 0.000965	time 2.1514 (2.1976)	loss 4.7375 (4.1042)	grad_norm 1.0969 (1.1356)	
[2022-01-18 15:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1110/1251]	eta 0:05:10 lr 0.000965	time 2.7570 (2.1988)	loss 4.4972 (4.1055)	grad_norm 0.9398 (1.1361)	
[2022-01-18 15:47:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1120/1251]	eta 0:04:47 lr 0.000965	time 1.6381 (2.1974)	loss 3.2344 (4.1037)	grad_norm 1.2703 (1.1369)	
[2022-01-18 15:47:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1130/1251]	eta 0:04:25 lr 0.000965	time 1.5956 (2.1945)	loss 3.7103 (4.1039)	grad_norm 1.3465 (1.1368)	
[2022-01-18 15:47:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1140/1251]	eta 0:04:03 lr 0.000965	time 1.9496 (2.1937)	loss 3.0554 (4.1027)	grad_norm 1.1442 (1.1366)	
[2022-01-18 15:48:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1150/1251]	eta 0:03:41 lr 0.000965	time 2.1132 (2.1935)	loss 4.4105 (4.1026)	grad_norm 0.9409 (1.1361)	
[2022-01-18 15:48:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1160/1251]	eta 0:03:19 lr 0.000965	time 2.8342 (2.1926)	loss 4.5408 (4.1034)	grad_norm 1.1322 (1.1362)	
[2022-01-18 15:48:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1170/1251]	eta 0:02:57 lr 0.000965	time 1.4932 (2.1915)	loss 5.0177 (4.1053)	grad_norm 1.2684 (1.1370)	
[2022-01-18 15:49:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1180/1251]	eta 0:02:35 lr 0.000965	time 3.0254 (2.1944)	loss 3.3748 (4.1047)	grad_norm 0.9921 (1.1370)	
[2022-01-18 15:49:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1190/1251]	eta 0:02:13 lr 0.000965	time 3.0621 (2.1964)	loss 3.9663 (4.1059)	grad_norm 1.2940 (1.1372)	
[2022-01-18 15:50:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1200/1251]	eta 0:01:52 lr 0.000965	time 2.2738 (2.1972)	loss 3.0481 (4.1038)	grad_norm 1.0825 (1.1368)	
[2022-01-18 15:50:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1210/1251]	eta 0:01:30 lr 0.000965	time 1.6749 (2.1962)	loss 4.1596 (4.1039)	grad_norm 1.0617 (1.1369)	
[2022-01-18 15:50:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1220/1251]	eta 0:01:08 lr 0.000965	time 1.8222 (2.1948)	loss 3.8814 (4.1057)	grad_norm 0.9966 (1.1367)	
[2022-01-18 15:51:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1230/1251]	eta 0:00:46 lr 0.000965	time 1.6555 (2.1931)	loss 3.0691 (4.1060)	grad_norm 1.0804 (1.1364)	
[2022-01-18 15:51:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1240/1251]	eta 0:00:24 lr 0.000965	time 2.1309 (2.1923)	loss 3.5335 (4.1049)	grad_norm 1.3182 (1.1364)	
[2022-01-18 15:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [35/300][1250/1251]	eta 0:00:02 lr 0.000965	time 1.1586 (2.1868)	loss 3.9041 (4.1057)	grad_norm 1.2291 (1.1365)	
[2022-01-18 15:51:44 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 35 training takes 0:45:36
[2022-01-18 15:52:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.578 (18.578)	Loss 1.3750 (1.3750)	Acc@1 68.848 (68.848)	Acc@5 88.379 (88.379)	
[2022-01-18 15:52:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.311 (3.397)	Loss 1.3830 (1.4063)	Acc@1 67.969 (67.685)	Acc@5 89.258 (88.521)	
[2022-01-18 15:52:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.225 (2.708)	Loss 1.3843 (1.4066)	Acc@1 68.164 (67.680)	Acc@5 88.477 (88.472)	
[2022-01-18 15:52:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.622 (2.315)	Loss 1.4857 (1.4108)	Acc@1 66.016 (67.597)	Acc@5 87.402 (88.423)	
[2022-01-18 15:53:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.756 (2.216)	Loss 1.4371 (1.4111)	Acc@1 66.211 (67.492)	Acc@5 87.598 (88.415)	
[2022-01-18 15:53:22 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 67.500 Acc@5 88.364
[2022-01-18 15:53:22 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 67.5%
[2022-01-18 15:53:22 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 67.50%
[2022-01-18 15:53:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][0/1251]	eta 7:26:07 lr 0.000965	time 21.3969 (21.3969)	loss 4.4021 (4.4021)	grad_norm 1.4995 (1.4995)	
[2022-01-18 15:54:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][10/1251]	eta 1:20:59 lr 0.000965	time 1.3741 (3.9155)	loss 3.9507 (4.0690)	grad_norm 1.2544 (1.2662)	
[2022-01-18 15:54:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][20/1251]	eta 1:04:09 lr 0.000965	time 1.9923 (3.1272)	loss 4.5592 (4.0632)	grad_norm 1.1105 (1.2375)	
[2022-01-18 15:54:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][30/1251]	eta 0:56:31 lr 0.000965	time 1.5730 (2.7780)	loss 3.9032 (4.0787)	grad_norm 1.1690 (1.2233)	
[2022-01-18 15:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][40/1251]	eta 0:54:09 lr 0.000965	time 4.1850 (2.6833)	loss 3.5035 (4.1033)	grad_norm 1.1114 (1.2197)	
[2022-01-18 15:55:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][50/1251]	eta 0:52:29 lr 0.000965	time 1.7967 (2.6225)	loss 4.5936 (4.1938)	grad_norm 1.3549 (1.1944)	
[2022-01-18 15:55:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][60/1251]	eta 0:51:06 lr 0.000965	time 2.4702 (2.5746)	loss 4.1728 (4.1905)	grad_norm 1.2683 (1.1827)	
[2022-01-18 15:56:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][70/1251]	eta 0:49:39 lr 0.000965	time 1.7287 (2.5232)	loss 4.7628 (4.1804)	grad_norm 1.0882 (1.1846)	
[2022-01-18 15:56:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][80/1251]	eta 0:48:39 lr 0.000965	time 2.8547 (2.4930)	loss 3.2420 (4.1595)	grad_norm 1.0398 (1.1761)	
[2022-01-18 15:57:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][90/1251]	eta 0:47:19 lr 0.000965	time 1.6710 (2.4455)	loss 4.2406 (4.1479)	grad_norm 1.1289 (1.1786)	
[2022-01-18 15:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][100/1251]	eta 0:46:13 lr 0.000965	time 1.6651 (2.4092)	loss 4.3403 (4.1512)	grad_norm 1.1577 (1.1699)	
[2022-01-18 15:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][110/1251]	eta 0:45:14 lr 0.000965	time 1.9026 (2.3787)	loss 4.1728 (4.1395)	grad_norm 1.0440 (1.1623)	
[2022-01-18 15:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][120/1251]	eta 0:44:27 lr 0.000965	time 2.5538 (2.3586)	loss 3.2161 (4.1268)	grad_norm 1.3115 (1.1713)	
[2022-01-18 15:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][130/1251]	eta 0:43:46 lr 0.000965	time 2.1453 (2.3427)	loss 4.4211 (4.1214)	grad_norm 1.4009 (1.1747)	
[2022-01-18 15:58:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][140/1251]	eta 0:43:15 lr 0.000965	time 2.2115 (2.3366)	loss 4.2015 (4.1182)	grad_norm 1.0594 (1.1684)	
[2022-01-18 15:59:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][150/1251]	eta 0:42:41 lr 0.000965	time 1.5606 (2.3264)	loss 3.7498 (4.1288)	grad_norm 1.1909 (1.1653)	
[2022-01-18 15:59:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][160/1251]	eta 0:42:11 lr 0.000965	time 2.7963 (2.3203)	loss 3.4729 (4.1083)	grad_norm 1.2256 (1.1688)	
[2022-01-18 15:59:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][170/1251]	eta 0:41:42 lr 0.000965	time 1.8332 (2.3154)	loss 4.4586 (4.1101)	grad_norm 1.2659 (1.1705)	
[2022-01-18 16:00:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][180/1251]	eta 0:41:20 lr 0.000965	time 2.6856 (2.3160)	loss 3.8657 (4.1070)	grad_norm 1.0404 (1.1624)	
[2022-01-18 16:00:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][190/1251]	eta 0:40:51 lr 0.000965	time 1.8298 (2.3108)	loss 4.7790 (4.1073)	grad_norm 1.1097 (1.1638)	
[2022-01-18 16:01:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][200/1251]	eta 0:40:20 lr 0.000965	time 2.2425 (2.3033)	loss 5.0115 (4.1119)	grad_norm 1.1851 (1.1676)	
[2022-01-18 16:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][210/1251]	eta 0:39:45 lr 0.000965	time 1.9031 (2.2914)	loss 4.0612 (4.1043)	grad_norm 1.1710 (1.1697)	
[2022-01-18 16:01:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][220/1251]	eta 0:39:21 lr 0.000965	time 2.3760 (2.2904)	loss 3.9402 (4.1004)	grad_norm 1.0642 (1.1649)	
[2022-01-18 16:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][230/1251]	eta 0:38:44 lr 0.000965	time 1.9159 (2.2771)	loss 4.2560 (4.1037)	grad_norm 1.2427 (1.1626)	
[2022-01-18 16:02:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][240/1251]	eta 0:38:09 lr 0.000965	time 2.0816 (2.2649)	loss 3.7199 (4.1005)	grad_norm 0.9702 (1.1613)	
[2022-01-18 16:02:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][250/1251]	eta 0:37:38 lr 0.000965	time 2.3590 (2.2562)	loss 4.0984 (4.1064)	grad_norm 1.1103 (1.1592)	
[2022-01-18 16:03:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][260/1251]	eta 0:37:13 lr 0.000965	time 1.8847 (2.2542)	loss 4.6426 (4.1107)	grad_norm 1.0832 (1.1604)	
[2022-01-18 16:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][270/1251]	eta 0:36:59 lr 0.000965	time 2.8305 (2.2621)	loss 3.8935 (4.1228)	grad_norm 1.0548 (1.1584)	
[2022-01-18 16:03:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][280/1251]	eta 0:36:40 lr 0.000965	time 2.1290 (2.2658)	loss 4.7928 (4.1281)	grad_norm 1.2093 (1.1576)	
[2022-01-18 16:04:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][290/1251]	eta 0:36:23 lr 0.000965	time 2.1191 (2.2722)	loss 4.3542 (4.1203)	grad_norm 1.2242 (1.1562)	
[2022-01-18 16:04:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][300/1251]	eta 0:35:59 lr 0.000965	time 1.9888 (2.2711)	loss 4.4865 (4.1117)	grad_norm 1.3028 (1.1550)	
[2022-01-18 16:05:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][310/1251]	eta 0:35:33 lr 0.000965	time 2.2836 (2.2672)	loss 3.5216 (4.1133)	grad_norm 1.1891 (1.1554)	
[2022-01-18 16:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][320/1251]	eta 0:34:58 lr 0.000965	time 1.9702 (2.2539)	loss 3.4126 (4.0952)	grad_norm 1.1028 (1.1542)	
[2022-01-18 16:05:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][330/1251]	eta 0:34:27 lr 0.000965	time 2.0066 (2.2451)	loss 3.7936 (4.0956)	grad_norm 0.9981 (1.1507)	
[2022-01-18 16:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][340/1251]	eta 0:34:02 lr 0.000965	time 3.1897 (2.2417)	loss 2.9508 (4.0899)	grad_norm 1.0330 (1.1497)	
[2022-01-18 16:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][350/1251]	eta 0:33:35 lr 0.000965	time 1.8506 (2.2371)	loss 4.1344 (4.0886)	grad_norm 1.0213 (1.1503)	
[2022-01-18 16:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][360/1251]	eta 0:33:14 lr 0.000965	time 2.2613 (2.2381)	loss 3.7648 (4.0936)	grad_norm 1.0267 (1.1517)	
[2022-01-18 16:07:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][370/1251]	eta 0:32:52 lr 0.000965	time 1.5038 (2.2384)	loss 4.4075 (4.0946)	grad_norm 1.2860 (1.1544)	
[2022-01-18 16:07:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][380/1251]	eta 0:32:28 lr 0.000965	time 2.1772 (2.2366)	loss 4.4668 (4.0945)	grad_norm 1.1597 (1.1545)	
[2022-01-18 16:07:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][390/1251]	eta 0:32:05 lr 0.000965	time 2.1633 (2.2365)	loss 4.7036 (4.0975)	grad_norm 1.1486 (1.1546)	
[2022-01-18 16:08:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][400/1251]	eta 0:31:43 lr 0.000965	time 2.4412 (2.2363)	loss 4.6992 (4.0971)	grad_norm 1.1216 (1.1558)	
[2022-01-18 16:08:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][410/1251]	eta 0:31:23 lr 0.000965	time 1.8453 (2.2392)	loss 4.0871 (4.0946)	grad_norm 1.1673 (1.1540)	
[2022-01-18 16:09:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][420/1251]	eta 0:30:59 lr 0.000965	time 2.5228 (2.2383)	loss 4.2881 (4.0924)	grad_norm 1.0636 (1.1527)	
[2022-01-18 16:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][430/1251]	eta 0:30:38 lr 0.000965	time 1.9906 (2.2389)	loss 4.9625 (4.0920)	grad_norm 1.1768 (1.1521)	
[2022-01-18 16:09:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][440/1251]	eta 0:30:15 lr 0.000965	time 3.1036 (2.2391)	loss 4.3446 (4.0893)	grad_norm 1.2147 (1.1517)	
[2022-01-18 16:10:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][450/1251]	eta 0:29:57 lr 0.000965	time 1.8436 (2.2439)	loss 4.8522 (4.0975)	grad_norm 0.9835 (1.1497)	
[2022-01-18 16:10:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][460/1251]	eta 0:29:32 lr 0.000965	time 2.0068 (2.2413)	loss 4.7224 (4.0926)	grad_norm 1.2518 (1.1485)	
[2022-01-18 16:10:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][470/1251]	eta 0:29:08 lr 0.000965	time 1.9605 (2.2390)	loss 4.4997 (4.0942)	grad_norm 0.9725 (1.1474)	
[2022-01-18 16:11:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][480/1251]	eta 0:28:45 lr 0.000965	time 3.3869 (2.2380)	loss 4.5163 (4.0874)	grad_norm 0.9572 (1.1469)	
[2022-01-18 16:11:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][490/1251]	eta 0:28:20 lr 0.000964	time 1.9140 (2.2349)	loss 4.1514 (4.0852)	grad_norm 1.3126 (1.1496)	
[2022-01-18 16:12:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][500/1251]	eta 0:27:57 lr 0.000964	time 1.9032 (2.2332)	loss 3.7343 (4.0747)	grad_norm 0.9315 (1.1498)	
[2022-01-18 16:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][510/1251]	eta 0:27:32 lr 0.000964	time 1.8237 (2.2296)	loss 4.3974 (4.0775)	grad_norm 1.0779 (1.1483)	
[2022-01-18 16:12:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][520/1251]	eta 0:27:06 lr 0.000964	time 2.2946 (2.2251)	loss 4.3860 (4.0787)	grad_norm 1.4031 (1.1481)	
[2022-01-18 16:13:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][530/1251]	eta 0:26:42 lr 0.000964	time 2.1999 (2.2228)	loss 4.4382 (4.0777)	grad_norm 1.0828 (1.1462)	
[2022-01-18 16:13:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][540/1251]	eta 0:26:20 lr 0.000964	time 2.9410 (2.2227)	loss 4.5629 (4.0746)	grad_norm 0.9769 (1.1456)	
[2022-01-18 16:13:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][550/1251]	eta 0:25:58 lr 0.000964	time 2.1381 (2.2233)	loss 4.7140 (4.0743)	grad_norm 0.9397 (1.1458)	
[2022-01-18 16:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][560/1251]	eta 0:25:36 lr 0.000964	time 2.5292 (2.2238)	loss 3.9368 (4.0766)	grad_norm 1.2172 (1.1447)	
[2022-01-18 16:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][570/1251]	eta 0:25:14 lr 0.000964	time 1.9386 (2.2234)	loss 3.7440 (4.0763)	grad_norm 1.2585 (1.1440)	
[2022-01-18 16:14:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][580/1251]	eta 0:24:52 lr 0.000964	time 2.2489 (2.2236)	loss 4.1211 (4.0759)	grad_norm 1.0596 (1.1444)	
[2022-01-18 16:15:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][590/1251]	eta 0:24:29 lr 0.000964	time 1.7827 (2.2228)	loss 4.4393 (4.0737)	grad_norm 1.0296 (1.1443)	
[2022-01-18 16:15:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][600/1251]	eta 0:24:07 lr 0.000964	time 2.1025 (2.2236)	loss 4.4812 (4.0726)	grad_norm 0.8997 (1.1440)	
[2022-01-18 16:16:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][610/1251]	eta 0:23:45 lr 0.000964	time 2.1710 (2.2235)	loss 3.9554 (4.0673)	grad_norm 1.2203 (1.1458)	
[2022-01-18 16:16:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][620/1251]	eta 0:23:22 lr 0.000964	time 1.5649 (2.2222)	loss 4.9953 (4.0672)	grad_norm 1.5841 (1.1459)	
[2022-01-18 16:16:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][630/1251]	eta 0:22:59 lr 0.000964	time 2.2962 (2.2211)	loss 4.6556 (4.0689)	grad_norm 1.7529 (1.1482)	
[2022-01-18 16:17:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][640/1251]	eta 0:22:35 lr 0.000964	time 1.9330 (2.2193)	loss 4.3287 (4.0742)	grad_norm 1.1726 (1.1483)	
[2022-01-18 16:17:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][650/1251]	eta 0:22:13 lr 0.000964	time 2.2034 (2.2195)	loss 4.1212 (4.0762)	grad_norm 1.0195 (1.1472)	
[2022-01-18 16:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][660/1251]	eta 0:21:51 lr 0.000964	time 1.9578 (2.2185)	loss 4.5726 (4.0775)	grad_norm 0.9881 (1.1467)	
[2022-01-18 16:18:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][670/1251]	eta 0:21:29 lr 0.000964	time 2.0889 (2.2188)	loss 3.0835 (4.0765)	grad_norm 1.0293 (1.1459)	
[2022-01-18 16:18:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][680/1251]	eta 0:21:06 lr 0.000964	time 1.6419 (2.2184)	loss 4.4322 (4.0749)	grad_norm 1.0977 (1.1452)	
[2022-01-18 16:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][690/1251]	eta 0:20:45 lr 0.000964	time 2.8832 (2.2194)	loss 4.4824 (4.0790)	grad_norm 0.9437 (1.1432)	
[2022-01-18 16:19:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][700/1251]	eta 0:20:24 lr 0.000964	time 2.2214 (2.2217)	loss 4.4038 (4.0761)	grad_norm 1.2439 (1.1426)	
[2022-01-18 16:19:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][710/1251]	eta 0:20:00 lr 0.000964	time 1.9051 (2.2199)	loss 3.8859 (4.0761)	grad_norm 1.2022 (1.1437)	
[2022-01-18 16:20:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][720/1251]	eta 0:19:37 lr 0.000964	time 1.8172 (2.2171)	loss 3.5073 (4.0723)	grad_norm 1.0204 (1.1438)	
[2022-01-18 16:20:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][730/1251]	eta 0:19:13 lr 0.000964	time 2.0880 (2.2132)	loss 2.8762 (4.0733)	grad_norm 0.9904 (1.1425)	
[2022-01-18 16:20:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][740/1251]	eta 0:18:50 lr 0.000964	time 2.2241 (2.2117)	loss 4.4048 (4.0765)	grad_norm 1.2362 (1.1416)	
[2022-01-18 16:21:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][750/1251]	eta 0:18:28 lr 0.000964	time 2.8631 (2.2126)	loss 4.2110 (4.0781)	grad_norm 1.0582 (1.1414)	
[2022-01-18 16:21:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][760/1251]	eta 0:18:07 lr 0.000964	time 1.8555 (2.2153)	loss 4.3736 (4.0762)	grad_norm 1.0710 (1.1409)	
[2022-01-18 16:21:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][770/1251]	eta 0:17:45 lr 0.000964	time 2.4949 (2.2161)	loss 3.9749 (4.0709)	grad_norm 1.2791 (1.1427)	
[2022-01-18 16:22:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][780/1251]	eta 0:17:23 lr 0.000964	time 2.4535 (2.2162)	loss 4.2280 (4.0704)	grad_norm 1.1395 (1.1423)	
[2022-01-18 16:22:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][790/1251]	eta 0:17:00 lr 0.000964	time 1.9150 (2.2138)	loss 4.4896 (4.0730)	grad_norm 1.0777 (1.1419)	
[2022-01-18 16:22:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][800/1251]	eta 0:16:37 lr 0.000964	time 2.1124 (2.2126)	loss 3.6238 (4.0733)	grad_norm 1.2348 (1.1421)	
[2022-01-18 16:23:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][810/1251]	eta 0:16:15 lr 0.000964	time 2.0178 (2.2123)	loss 4.1687 (4.0711)	grad_norm 1.0851 (1.1416)	
[2022-01-18 16:23:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][820/1251]	eta 0:15:53 lr 0.000964	time 2.6726 (2.2118)	loss 2.9999 (4.0682)	grad_norm 1.0906 (1.1411)	
[2022-01-18 16:24:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][830/1251]	eta 0:15:31 lr 0.000964	time 2.7092 (2.2136)	loss 3.0458 (4.0647)	grad_norm 0.9480 (1.1413)	
[2022-01-18 16:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][840/1251]	eta 0:15:09 lr 0.000964	time 1.9274 (2.2129)	loss 4.3069 (4.0639)	grad_norm 1.1421 (1.1423)	
[2022-01-18 16:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][850/1251]	eta 0:14:46 lr 0.000964	time 1.6081 (2.2103)	loss 4.4534 (4.0634)	grad_norm 1.0834 (1.1420)	
[2022-01-18 16:25:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][860/1251]	eta 0:14:23 lr 0.000964	time 1.9322 (2.2097)	loss 4.8689 (4.0639)	grad_norm 1.0715 (1.1425)	
[2022-01-18 16:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][870/1251]	eta 0:14:01 lr 0.000964	time 2.2157 (2.2086)	loss 3.7546 (4.0627)	grad_norm 1.2301 (1.1419)	
[2022-01-18 16:25:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][880/1251]	eta 0:13:39 lr 0.000964	time 3.2544 (2.2101)	loss 4.6054 (4.0633)	grad_norm 1.2944 (1.1424)	
[2022-01-18 16:26:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][890/1251]	eta 0:13:17 lr 0.000964	time 1.8925 (2.2087)	loss 4.3798 (4.0638)	grad_norm 1.1014 (1.1431)	
[2022-01-18 16:26:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][900/1251]	eta 0:12:55 lr 0.000964	time 2.4272 (2.2095)	loss 3.5824 (4.0641)	grad_norm 0.9689 (1.1421)	
[2022-01-18 16:26:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][910/1251]	eta 0:12:33 lr 0.000964	time 1.6616 (2.2097)	loss 4.1744 (4.0696)	grad_norm 0.9001 (1.1419)	
[2022-01-18 16:27:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][920/1251]	eta 0:12:11 lr 0.000964	time 3.0552 (2.2112)	loss 4.3724 (4.0702)	grad_norm 0.9044 (1.1414)	
[2022-01-18 16:27:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][930/1251]	eta 0:11:49 lr 0.000964	time 1.8499 (2.2102)	loss 4.8872 (4.0706)	grad_norm 1.0494 (1.1410)	
[2022-01-18 16:28:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][940/1251]	eta 0:11:27 lr 0.000964	time 1.9320 (2.2090)	loss 3.5448 (4.0714)	grad_norm 1.1142 (1.1414)	
[2022-01-18 16:28:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][950/1251]	eta 0:11:04 lr 0.000964	time 1.9420 (2.2067)	loss 4.2253 (4.0706)	grad_norm 0.9445 (1.1406)	
[2022-01-18 16:28:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][960/1251]	eta 0:10:42 lr 0.000964	time 3.2413 (2.2072)	loss 4.1635 (4.0710)	grad_norm 0.9540 (1.1397)	
[2022-01-18 16:29:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][970/1251]	eta 0:10:20 lr 0.000964	time 1.7549 (2.2070)	loss 4.2485 (4.0729)	grad_norm 1.2004 (1.1402)	
[2022-01-18 16:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][980/1251]	eta 0:09:58 lr 0.000964	time 1.9042 (2.2078)	loss 4.0808 (4.0716)	grad_norm 0.9021 (1.1405)	
[2022-01-18 16:29:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][990/1251]	eta 0:09:35 lr 0.000964	time 1.9692 (2.2060)	loss 4.0973 (4.0726)	grad_norm 1.4860 (1.1412)	
[2022-01-18 16:30:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1000/1251]	eta 0:09:13 lr 0.000964	time 2.8247 (2.2060)	loss 3.1707 (4.0729)	grad_norm 1.1343 (1.1414)	
[2022-01-18 16:30:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1010/1251]	eta 0:08:51 lr 0.000964	time 2.1397 (2.2048)	loss 4.1957 (4.0721)	grad_norm 0.9986 (1.1414)	
[2022-01-18 16:30:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1020/1251]	eta 0:08:29 lr 0.000964	time 2.8982 (2.2044)	loss 3.0143 (4.0721)	grad_norm 1.1455 (1.1414)	
[2022-01-18 16:31:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1030/1251]	eta 0:08:07 lr 0.000964	time 2.2305 (2.2044)	loss 4.9030 (4.0737)	grad_norm 1.2795 (1.1404)	
[2022-01-18 16:31:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1040/1251]	eta 0:07:44 lr 0.000964	time 2.9745 (2.2033)	loss 3.9884 (4.0716)	grad_norm 1.2915 (1.1392)	
[2022-01-18 16:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1050/1251]	eta 0:07:22 lr 0.000964	time 2.0717 (2.2031)	loss 3.6550 (4.0724)	grad_norm 1.1355 (1.1389)	
[2022-01-18 16:32:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1060/1251]	eta 0:07:00 lr 0.000964	time 2.8207 (2.2026)	loss 3.8079 (4.0733)	grad_norm 1.3303 (1.1398)	
[2022-01-18 16:32:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1070/1251]	eta 0:06:38 lr 0.000964	time 2.1209 (2.2015)	loss 3.9510 (4.0729)	grad_norm 1.0427 (1.1392)	
[2022-01-18 16:33:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1080/1251]	eta 0:06:16 lr 0.000964	time 2.9247 (2.2019)	loss 4.9308 (4.0745)	grad_norm 1.0819 (1.1394)	
[2022-01-18 16:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1090/1251]	eta 0:05:54 lr 0.000964	time 1.6902 (2.2013)	loss 4.3633 (4.0751)	grad_norm 1.1760 (1.1394)	
[2022-01-18 16:33:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1100/1251]	eta 0:05:32 lr 0.000964	time 2.4371 (2.2005)	loss 3.9857 (4.0743)	grad_norm 0.9883 (1.1392)	
[2022-01-18 16:34:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1110/1251]	eta 0:05:10 lr 0.000964	time 1.9535 (2.2007)	loss 4.8011 (4.0761)	grad_norm 0.8948 (1.1396)	
[2022-01-18 16:34:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1120/1251]	eta 0:04:48 lr 0.000964	time 3.1771 (2.2027)	loss 3.5086 (4.0759)	grad_norm 1.2570 (1.1402)	
[2022-01-18 16:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1130/1251]	eta 0:04:26 lr 0.000963	time 2.2052 (2.2033)	loss 2.9076 (4.0757)	grad_norm 0.9977 (1.1398)	
[2022-01-18 16:35:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1140/1251]	eta 0:04:04 lr 0.000963	time 3.3447 (2.2054)	loss 3.9916 (4.0784)	grad_norm 1.0237 (1.1390)	
[2022-01-18 16:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1150/1251]	eta 0:03:42 lr 0.000963	time 2.0091 (2.2047)	loss 4.7073 (4.0783)	grad_norm 1.0748 (1.1397)	
[2022-01-18 16:35:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1160/1251]	eta 0:03:20 lr 0.000963	time 1.8623 (2.2022)	loss 4.7075 (4.0814)	grad_norm 1.0142 (1.1395)	
[2022-01-18 16:36:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1170/1251]	eta 0:02:58 lr 0.000963	time 2.2701 (2.2013)	loss 4.7424 (4.0804)	grad_norm 1.0471 (1.1394)	
[2022-01-18 16:36:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1180/1251]	eta 0:02:36 lr 0.000963	time 2.4874 (2.2017)	loss 3.6642 (4.0807)	grad_norm 1.0706 (1.1390)	
[2022-01-18 16:37:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1190/1251]	eta 0:02:14 lr 0.000963	time 1.8999 (2.2013)	loss 4.3279 (4.0809)	grad_norm 1.1691 (1.1388)	
[2022-01-18 16:37:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1200/1251]	eta 0:01:52 lr 0.000963	time 2.2690 (2.2012)	loss 4.1879 (4.0806)	grad_norm 1.2599 (1.1385)	
[2022-01-18 16:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1210/1251]	eta 0:01:30 lr 0.000963	time 1.9142 (2.2014)	loss 3.9403 (4.0791)	grad_norm 1.1499 (1.1385)	
[2022-01-18 16:38:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1220/1251]	eta 0:01:08 lr 0.000963	time 1.9275 (2.2017)	loss 4.6655 (4.0797)	grad_norm 0.9038 (1.1379)	
[2022-01-18 16:38:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1230/1251]	eta 0:00:46 lr 0.000963	time 1.5760 (2.2008)	loss 2.9148 (4.0799)	grad_norm 1.0586 (1.1377)	
[2022-01-18 16:38:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1240/1251]	eta 0:00:24 lr 0.000963	time 1.4651 (2.1996)	loss 4.7877 (4.0795)	grad_norm 1.2558 (1.1382)	
[2022-01-18 16:39:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [36/300][1250/1251]	eta 0:00:02 lr 0.000963	time 1.1854 (2.1945)	loss 4.1804 (4.0811)	grad_norm 1.1952 (1.1385)	
[2022-01-18 16:39:08 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 36 training takes 0:45:45
[2022-01-18 16:39:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.334 (18.334)	Loss 1.4202 (1.4202)	Acc@1 69.824 (69.824)	Acc@5 88.477 (88.477)	
[2022-01-18 16:39:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.731 (3.547)	Loss 1.4392 (1.4475)	Acc@1 67.969 (67.773)	Acc@5 88.184 (87.962)	
[2022-01-18 16:40:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.306 (2.578)	Loss 1.3583 (1.4190)	Acc@1 68.848 (67.983)	Acc@5 89.062 (88.458)	
[2022-01-18 16:40:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.309 (2.331)	Loss 1.4253 (1.4228)	Acc@1 66.504 (67.799)	Acc@5 88.770 (88.357)	
[2022-01-18 16:40:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.556 (2.194)	Loss 1.4606 (1.4186)	Acc@1 67.773 (67.833)	Acc@5 88.184 (88.500)	
[2022-01-18 16:40:45 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 67.700 Acc@5 88.470
[2022-01-18 16:40:45 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 67.7%
[2022-01-18 16:40:45 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 67.70%
[2022-01-18 16:41:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][0/1251]	eta 7:21:52 lr 0.000963	time 21.1929 (21.1929)	loss 4.2367 (4.2367)	grad_norm 1.0246 (1.0246)	
[2022-01-18 16:41:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][10/1251]	eta 1:21:25 lr 0.000963	time 1.7749 (3.9369)	loss 4.8905 (4.3225)	grad_norm 1.0096 (1.1483)	
[2022-01-18 16:41:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][20/1251]	eta 1:04:06 lr 0.000963	time 1.9088 (3.1243)	loss 3.7545 (4.0294)	grad_norm 1.1079 (1.1430)	
[2022-01-18 16:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][30/1251]	eta 0:57:19 lr 0.000963	time 1.5324 (2.8169)	loss 4.5786 (4.1578)	grad_norm 1.1956 (1.1568)	
[2022-01-18 16:42:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][40/1251]	eta 0:54:24 lr 0.000963	time 3.5200 (2.6957)	loss 3.3387 (4.1151)	grad_norm 1.0167 (1.1574)	
[2022-01-18 16:43:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][50/1251]	eta 0:53:29 lr 0.000963	time 2.7889 (2.6722)	loss 4.2135 (4.1425)	grad_norm 1.0517 (1.1365)	
[2022-01-18 16:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][60/1251]	eta 0:51:11 lr 0.000963	time 1.4930 (2.5792)	loss 3.9225 (4.1246)	grad_norm 1.0518 (1.1280)	
[2022-01-18 16:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][70/1251]	eta 0:49:06 lr 0.000963	time 1.7582 (2.4947)	loss 2.8350 (4.0874)	grad_norm 1.1207 (1.1451)	
[2022-01-18 16:44:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][80/1251]	eta 0:47:42 lr 0.000963	time 2.6159 (2.4443)	loss 4.5251 (4.1287)	grad_norm 1.0756 (1.1348)	
[2022-01-18 16:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][90/1251]	eta 0:46:42 lr 0.000963	time 2.1166 (2.4138)	loss 4.2621 (4.1197)	grad_norm 1.0371 (1.1411)	
[2022-01-18 16:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][100/1251]	eta 0:45:46 lr 0.000963	time 2.6283 (2.3862)	loss 4.7783 (4.1136)	grad_norm 1.2543 (1.1496)	
[2022-01-18 16:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][110/1251]	eta 0:45:05 lr 0.000963	time 2.4819 (2.3709)	loss 4.4479 (4.1140)	grad_norm 1.4709 (1.1466)	
[2022-01-18 16:45:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][120/1251]	eta 0:44:25 lr 0.000963	time 2.4480 (2.3570)	loss 4.4940 (4.1224)	grad_norm 1.1573 (1.1528)	
[2022-01-18 16:45:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][130/1251]	eta 0:44:19 lr 0.000963	time 2.4948 (2.3725)	loss 3.2913 (4.1217)	grad_norm 1.1935 (1.1522)	
[2022-01-18 16:46:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][140/1251]	eta 0:43:49 lr 0.000963	time 2.9748 (2.3671)	loss 4.2332 (4.1182)	grad_norm 1.2081 (1.1543)	
[2022-01-18 16:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][150/1251]	eta 0:43:11 lr 0.000963	time 1.9000 (2.3538)	loss 4.1674 (4.0980)	grad_norm 1.1820 (1.1612)	
[2022-01-18 16:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][160/1251]	eta 0:42:33 lr 0.000963	time 2.2357 (2.3404)	loss 4.4992 (4.0898)	grad_norm 1.5190 (1.1644)	
[2022-01-18 16:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][170/1251]	eta 0:41:57 lr 0.000963	time 2.1691 (2.3284)	loss 4.7292 (4.1011)	grad_norm 1.1226 (1.1614)	
[2022-01-18 16:47:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][180/1251]	eta 0:41:12 lr 0.000963	time 1.9211 (2.3086)	loss 3.7784 (4.0962)	grad_norm 1.1490 (1.1570)	
[2022-01-18 16:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][190/1251]	eta 0:40:35 lr 0.000963	time 2.1524 (2.2956)	loss 3.4129 (4.0860)	grad_norm 1.0100 (1.1576)	
[2022-01-18 16:48:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][200/1251]	eta 0:39:59 lr 0.000963	time 2.1124 (2.2829)	loss 4.7329 (4.0825)	grad_norm 1.1537 (1.1600)	
[2022-01-18 16:48:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][210/1251]	eta 0:39:30 lr 0.000963	time 2.2203 (2.2773)	loss 4.4328 (4.0773)	grad_norm 1.1611 (1.1615)	
[2022-01-18 16:49:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][220/1251]	eta 0:39:07 lr 0.000963	time 2.1446 (2.2768)	loss 4.5553 (4.0683)	grad_norm 1.1156 (1.1673)	
[2022-01-18 16:49:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][230/1251]	eta 0:38:41 lr 0.000963	time 2.2815 (2.2735)	loss 3.2175 (4.0620)	grad_norm 1.0940 (1.1676)	
[2022-01-18 16:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][240/1251]	eta 0:38:19 lr 0.000963	time 2.8251 (2.2748)	loss 4.5308 (4.0602)	grad_norm 1.4058 (1.1718)	
[2022-01-18 16:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][250/1251]	eta 0:37:56 lr 0.000963	time 1.8706 (2.2747)	loss 2.9643 (4.0578)	grad_norm 1.2552 (1.1694)	
[2022-01-18 16:50:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][260/1251]	eta 0:37:36 lr 0.000963	time 1.8019 (2.2766)	loss 4.5807 (4.0584)	grad_norm 1.0115 (1.1697)	
[2022-01-18 16:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][270/1251]	eta 0:37:07 lr 0.000963	time 2.3183 (2.2704)	loss 2.7476 (4.0556)	grad_norm 0.8271 (1.1695)	
[2022-01-18 16:51:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][280/1251]	eta 0:36:36 lr 0.000963	time 1.9039 (2.2621)	loss 4.9824 (4.0630)	grad_norm 1.0876 (1.1690)	
[2022-01-18 16:51:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][290/1251]	eta 0:36:08 lr 0.000963	time 2.7223 (2.2562)	loss 4.4037 (4.0655)	grad_norm 1.1513 (1.1663)	
[2022-01-18 16:52:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][300/1251]	eta 0:35:39 lr 0.000963	time 1.9019 (2.2498)	loss 3.2871 (4.0615)	grad_norm 1.1824 (1.1629)	
[2022-01-18 16:52:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][310/1251]	eta 0:35:10 lr 0.000963	time 1.8576 (2.2431)	loss 4.4005 (4.0643)	grad_norm 1.1647 (1.1633)	
[2022-01-18 16:52:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][320/1251]	eta 0:34:46 lr 0.000963	time 2.5387 (2.2414)	loss 4.4135 (4.0653)	grad_norm 1.0402 (1.1620)	
[2022-01-18 16:53:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][330/1251]	eta 0:34:25 lr 0.000963	time 2.8897 (2.2428)	loss 3.2078 (4.0594)	grad_norm 1.1252 (1.1605)	
[2022-01-18 16:53:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][340/1251]	eta 0:34:05 lr 0.000963	time 2.4710 (2.2457)	loss 4.3250 (4.0562)	grad_norm 1.0913 (1.1564)	
[2022-01-18 16:53:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][350/1251]	eta 0:33:51 lr 0.000963	time 3.5666 (2.2548)	loss 4.9064 (4.0639)	grad_norm 1.0441 (1.1563)	
[2022-01-18 16:54:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][360/1251]	eta 0:33:33 lr 0.000963	time 2.4809 (2.2594)	loss 4.1659 (4.0696)	grad_norm 0.9335 (1.1548)	
[2022-01-18 16:54:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][370/1251]	eta 0:33:09 lr 0.000963	time 2.1557 (2.2581)	loss 4.6680 (4.0685)	grad_norm 1.5270 (1.1539)	
[2022-01-18 16:55:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][380/1251]	eta 0:32:42 lr 0.000963	time 1.9473 (2.2529)	loss 4.2967 (4.0666)	grad_norm 1.2014 (1.1545)	
[2022-01-18 16:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][390/1251]	eta 0:32:12 lr 0.000963	time 1.9819 (2.2446)	loss 4.1953 (4.0706)	grad_norm 1.2649 (1.1540)	
[2022-01-18 16:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][400/1251]	eta 0:31:43 lr 0.000963	time 2.2637 (2.2372)	loss 4.1004 (4.0643)	grad_norm 1.1553 (1.1532)	
[2022-01-18 16:56:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][410/1251]	eta 0:31:15 lr 0.000963	time 1.9093 (2.2306)	loss 3.9733 (4.0663)	grad_norm 0.9893 (1.1512)	
[2022-01-18 16:56:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][420/1251]	eta 0:30:52 lr 0.000963	time 2.4375 (2.2297)	loss 3.1982 (4.0591)	grad_norm 0.9839 (1.1501)	
[2022-01-18 16:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][430/1251]	eta 0:30:31 lr 0.000963	time 2.7815 (2.2309)	loss 4.3288 (4.0611)	grad_norm 0.9834 (1.1481)	
[2022-01-18 16:57:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][440/1251]	eta 0:30:05 lr 0.000963	time 1.5674 (2.2265)	loss 3.3728 (4.0629)	grad_norm 1.2093 (1.1470)	
[2022-01-18 16:57:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][450/1251]	eta 0:29:42 lr 0.000963	time 2.0978 (2.2248)	loss 3.8916 (4.0588)	grad_norm 1.1738 (1.1460)	
[2022-01-18 16:57:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][460/1251]	eta 0:29:22 lr 0.000963	time 3.2064 (2.2279)	loss 3.7326 (4.0502)	grad_norm 1.3398 (1.1471)	
[2022-01-18 16:58:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][470/1251]	eta 0:29:04 lr 0.000963	time 2.8235 (2.2332)	loss 2.7854 (4.0477)	grad_norm 1.1667 (1.1464)	
[2022-01-18 16:58:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][480/1251]	eta 0:28:42 lr 0.000963	time 1.8241 (2.2341)	loss 4.3632 (4.0540)	grad_norm 1.0516 (1.1430)	
[2022-01-18 16:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][490/1251]	eta 0:28:18 lr 0.000963	time 1.9646 (2.2317)	loss 3.7200 (4.0583)	grad_norm 1.2576 (1.1431)	
[2022-01-18 16:59:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][500/1251]	eta 0:27:54 lr 0.000963	time 2.7918 (2.2294)	loss 3.3870 (4.0633)	grad_norm 0.9246 (1.1438)	
[2022-01-18 16:59:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][510/1251]	eta 0:27:30 lr 0.000963	time 2.8115 (2.2269)	loss 2.9266 (4.0696)	grad_norm 1.2949 (1.1446)	
[2022-01-18 17:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][520/1251]	eta 0:27:06 lr 0.000962	time 1.5234 (2.2256)	loss 4.5091 (4.0675)	grad_norm 0.9502 (1.1442)	
[2022-01-18 17:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][530/1251]	eta 0:26:43 lr 0.000962	time 1.9293 (2.2235)	loss 4.4276 (4.0686)	grad_norm 0.9808 (1.1441)	
[2022-01-18 17:00:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][540/1251]	eta 0:26:21 lr 0.000962	time 2.7865 (2.2241)	loss 3.5508 (4.0722)	grad_norm 0.9681 (1.1444)	
[2022-01-18 17:01:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][550/1251]	eta 0:25:59 lr 0.000962	time 2.2148 (2.2242)	loss 4.2648 (4.0741)	grad_norm 1.3158 (1.1451)	
[2022-01-18 17:01:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][560/1251]	eta 0:25:35 lr 0.000962	time 1.8970 (2.2223)	loss 4.3643 (4.0761)	grad_norm 0.9682 (1.1432)	
[2022-01-18 17:01:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][570/1251]	eta 0:25:12 lr 0.000962	time 1.8643 (2.2211)	loss 4.5131 (4.0760)	grad_norm 1.0900 (1.1464)	
[2022-01-18 17:02:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][580/1251]	eta 0:24:49 lr 0.000962	time 2.5457 (2.2204)	loss 4.3790 (4.0748)	grad_norm 1.1945 (1.1477)	
[2022-01-18 17:02:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][590/1251]	eta 0:24:26 lr 0.000962	time 1.8611 (2.2191)	loss 4.0723 (4.0720)	grad_norm 1.0168 (1.1472)	
[2022-01-18 17:03:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][600/1251]	eta 0:24:05 lr 0.000962	time 2.5850 (2.2201)	loss 4.7707 (4.0761)	grad_norm 1.0676 (1.1450)	
[2022-01-18 17:03:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][610/1251]	eta 0:23:41 lr 0.000962	time 1.9710 (2.2174)	loss 3.3476 (4.0738)	grad_norm 1.2684 (1.1455)	
[2022-01-18 17:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][620/1251]	eta 0:23:19 lr 0.000962	time 2.7175 (2.2183)	loss 3.5502 (4.0715)	grad_norm 1.0234 (1.1463)	
[2022-01-18 17:04:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][630/1251]	eta 0:22:58 lr 0.000962	time 1.5309 (2.2194)	loss 4.5406 (4.0668)	grad_norm 1.4931 (1.1470)	
[2022-01-18 17:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][640/1251]	eta 0:22:34 lr 0.000962	time 2.4461 (2.2176)	loss 4.5662 (4.0697)	grad_norm 0.9427 (1.1464)	
[2022-01-18 17:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][650/1251]	eta 0:22:11 lr 0.000962	time 1.8995 (2.2149)	loss 4.3655 (4.0724)	grad_norm 0.9243 (1.1454)	
[2022-01-18 17:05:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][660/1251]	eta 0:21:48 lr 0.000962	time 2.4690 (2.2132)	loss 3.6922 (4.0768)	grad_norm 0.9874 (1.1442)	
[2022-01-18 17:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][670/1251]	eta 0:21:25 lr 0.000962	time 1.6165 (2.2118)	loss 4.6768 (4.0789)	grad_norm 1.1922 (1.1440)	
[2022-01-18 17:05:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][680/1251]	eta 0:21:01 lr 0.000962	time 2.0998 (2.2100)	loss 4.3865 (4.0823)	grad_norm 1.1635 (1.1448)	
[2022-01-18 17:06:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][690/1251]	eta 0:20:40 lr 0.000962	time 2.2331 (2.2113)	loss 4.7614 (4.0797)	grad_norm 1.0806 (1.1447)	
[2022-01-18 17:06:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][700/1251]	eta 0:20:18 lr 0.000962	time 2.2580 (2.2112)	loss 3.1353 (4.0765)	grad_norm 1.3968 (1.1450)	
[2022-01-18 17:06:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][710/1251]	eta 0:19:56 lr 0.000962	time 1.9959 (2.2125)	loss 4.9554 (4.0771)	grad_norm 1.0585 (1.1453)	
[2022-01-18 17:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][720/1251]	eta 0:19:34 lr 0.000962	time 2.5306 (2.2113)	loss 4.8942 (4.0823)	grad_norm 1.0357 (1.1446)	
[2022-01-18 17:07:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][730/1251]	eta 0:19:11 lr 0.000962	time 2.2732 (2.2097)	loss 4.3742 (4.0828)	grad_norm 1.0102 (1.1445)	
[2022-01-18 17:08:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][740/1251]	eta 0:18:48 lr 0.000962	time 1.6769 (2.2079)	loss 4.6312 (4.0870)	grad_norm 1.0149 (1.1443)	
[2022-01-18 17:08:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][750/1251]	eta 0:18:25 lr 0.000962	time 2.6265 (2.2072)	loss 3.7299 (4.0880)	grad_norm 1.2686 (1.1446)	
[2022-01-18 17:08:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][760/1251]	eta 0:18:02 lr 0.000962	time 1.9080 (2.2053)	loss 4.5104 (4.0882)	grad_norm 1.2014 (1.1452)	
[2022-01-18 17:09:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][770/1251]	eta 0:17:41 lr 0.000962	time 3.1587 (2.2070)	loss 4.3513 (4.0866)	grad_norm 1.1318 (1.1449)	
[2022-01-18 17:09:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][780/1251]	eta 0:17:20 lr 0.000962	time 2.7614 (2.2091)	loss 3.9446 (4.0830)	grad_norm 1.1492 (1.1443)	
[2022-01-18 17:09:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][790/1251]	eta 0:16:59 lr 0.000962	time 3.7671 (2.2108)	loss 4.3708 (4.0832)	grad_norm 1.0395 (1.1441)	
[2022-01-18 17:10:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][800/1251]	eta 0:16:37 lr 0.000962	time 2.2092 (2.2113)	loss 3.8749 (4.0853)	grad_norm 0.8827 (1.1437)	
[2022-01-18 17:10:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][810/1251]	eta 0:16:15 lr 0.000962	time 2.7492 (2.2115)	loss 4.5057 (4.0832)	grad_norm 1.1163 (1.1436)	
[2022-01-18 17:11:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][820/1251]	eta 0:15:52 lr 0.000962	time 1.8414 (2.2104)	loss 4.7374 (4.0843)	grad_norm 1.0326 (1.1434)	
[2022-01-18 17:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][830/1251]	eta 0:15:30 lr 0.000962	time 2.8290 (2.2104)	loss 2.9533 (4.0842)	grad_norm 1.1102 (1.1437)	
[2022-01-18 17:11:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][840/1251]	eta 0:15:07 lr 0.000962	time 1.9415 (2.2071)	loss 4.3217 (4.0785)	grad_norm 0.9704 (1.1428)	
[2022-01-18 17:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][850/1251]	eta 0:14:45 lr 0.000962	time 2.8501 (2.2071)	loss 4.1940 (4.0802)	grad_norm 1.1387 (1.1421)	
[2022-01-18 17:12:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][860/1251]	eta 0:14:22 lr 0.000962	time 1.5138 (2.2068)	loss 3.8345 (4.0798)	grad_norm 1.1373 (1.1421)	
[2022-01-18 17:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][870/1251]	eta 0:14:00 lr 0.000962	time 2.8421 (2.2073)	loss 3.1791 (4.0798)	grad_norm 1.0950 (1.1416)	
[2022-01-18 17:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][880/1251]	eta 0:13:39 lr 0.000962	time 2.1285 (2.2079)	loss 3.9246 (4.0810)	grad_norm 1.5489 (1.1430)	
[2022-01-18 17:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][890/1251]	eta 0:13:16 lr 0.000962	time 2.4671 (2.2074)	loss 3.6067 (4.0809)	grad_norm 1.0656 (1.1426)	
[2022-01-18 17:13:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][900/1251]	eta 0:12:54 lr 0.000962	time 1.8966 (2.2054)	loss 4.1698 (4.0827)	grad_norm 1.1025 (1.1433)	
[2022-01-18 17:14:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][910/1251]	eta 0:12:31 lr 0.000962	time 2.1843 (2.2036)	loss 4.3761 (4.0781)	grad_norm 1.1013 (1.1426)	
[2022-01-18 17:14:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][920/1251]	eta 0:12:09 lr 0.000962	time 2.1825 (2.2041)	loss 3.3508 (4.0760)	grad_norm 1.0668 (1.1414)	
[2022-01-18 17:14:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][930/1251]	eta 0:11:47 lr 0.000962	time 2.2065 (2.2037)	loss 4.1765 (4.0772)	grad_norm 0.9563 (1.1405)	
[2022-01-18 17:15:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][940/1251]	eta 0:11:24 lr 0.000962	time 1.9533 (2.2020)	loss 4.7895 (4.0801)	grad_norm 1.1188 (1.1400)	
[2022-01-18 17:15:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][950/1251]	eta 0:11:02 lr 0.000962	time 2.7843 (2.2023)	loss 4.2830 (4.0794)	grad_norm 1.0308 (1.1397)	
[2022-01-18 17:16:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][960/1251]	eta 0:10:41 lr 0.000962	time 2.1746 (2.2038)	loss 4.0240 (4.0778)	grad_norm 0.9573 (1.1402)	
[2022-01-18 17:16:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][970/1251]	eta 0:10:19 lr 0.000962	time 2.1837 (2.2053)	loss 5.1337 (4.0794)	grad_norm 1.1530 (1.1402)	
[2022-01-18 17:16:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][980/1251]	eta 0:09:57 lr 0.000962	time 2.1461 (2.2058)	loss 4.2775 (4.0802)	grad_norm 1.0557 (1.1406)	
[2022-01-18 17:17:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][990/1251]	eta 0:09:35 lr 0.000962	time 1.5586 (2.2041)	loss 3.6870 (4.0824)	grad_norm 1.5165 (1.1423)	
[2022-01-18 17:17:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1000/1251]	eta 0:09:12 lr 0.000962	time 1.9524 (2.2015)	loss 4.2974 (4.0831)	grad_norm 1.1358 (1.1416)	
[2022-01-18 17:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1010/1251]	eta 0:08:50 lr 0.000962	time 2.1322 (2.1992)	loss 3.5334 (4.0806)	grad_norm 1.0208 (1.1414)	
[2022-01-18 17:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1020/1251]	eta 0:08:27 lr 0.000962	time 2.9215 (2.1989)	loss 4.6529 (4.0821)	grad_norm 1.0645 (1.1411)	
[2022-01-18 17:18:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1030/1251]	eta 0:08:06 lr 0.000962	time 3.0061 (2.2000)	loss 3.6337 (4.0812)	grad_norm 1.1255 (1.1410)	
[2022-01-18 17:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1040/1251]	eta 0:07:44 lr 0.000962	time 1.5369 (2.2003)	loss 4.4744 (4.0816)	grad_norm 1.5923 (1.1409)	
[2022-01-18 17:19:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1050/1251]	eta 0:07:22 lr 0.000962	time 1.9556 (2.2005)	loss 4.6876 (4.0807)	grad_norm 1.3454 (1.1411)	
[2022-01-18 17:19:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1060/1251]	eta 0:07:00 lr 0.000962	time 2.7114 (2.2027)	loss 3.0575 (4.0800)	grad_norm 0.9782 (1.1412)	
[2022-01-18 17:20:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1070/1251]	eta 0:06:38 lr 0.000962	time 2.1969 (2.2040)	loss 3.7405 (4.0831)	grad_norm 1.1495 (1.1407)	
[2022-01-18 17:20:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1080/1251]	eta 0:06:17 lr 0.000962	time 3.2631 (2.2057)	loss 5.0429 (4.0845)	grad_norm 1.0231 (1.1412)	
[2022-01-18 17:20:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1090/1251]	eta 0:05:54 lr 0.000962	time 1.8918 (2.2044)	loss 3.8548 (4.0828)	grad_norm 1.3721 (1.1413)	
[2022-01-18 17:21:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1100/1251]	eta 0:05:32 lr 0.000962	time 1.9438 (2.2033)	loss 4.6970 (4.0832)	grad_norm 1.0292 (1.1414)	
[2022-01-18 17:21:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1110/1251]	eta 0:05:10 lr 0.000962	time 1.9494 (2.2028)	loss 4.6255 (4.0836)	grad_norm 1.2017 (1.1410)	
[2022-01-18 17:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1120/1251]	eta 0:04:48 lr 0.000962	time 3.2788 (2.2047)	loss 3.8853 (4.0825)	grad_norm 1.1783 (1.1410)	
[2022-01-18 17:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1130/1251]	eta 0:04:26 lr 0.000962	time 1.9387 (2.2041)	loss 4.3000 (4.0847)	grad_norm 1.2405 (1.1410)	
[2022-01-18 17:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1140/1251]	eta 0:04:04 lr 0.000962	time 1.7730 (2.2032)	loss 3.5173 (4.0850)	grad_norm 1.3060 (1.1418)	
[2022-01-18 17:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1150/1251]	eta 0:03:42 lr 0.000961	time 1.7354 (2.2024)	loss 4.8519 (4.0872)	grad_norm 1.2273 (1.1418)	
[2022-01-18 17:23:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1160/1251]	eta 0:03:20 lr 0.000961	time 3.6077 (2.2047)	loss 4.8512 (4.0869)	grad_norm 1.2340 (1.1416)	
[2022-01-18 17:23:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1170/1251]	eta 0:02:58 lr 0.000961	time 1.5829 (2.2031)	loss 4.1839 (4.0848)	grad_norm 1.1250 (1.1412)	
[2022-01-18 17:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1180/1251]	eta 0:02:36 lr 0.000961	time 2.2168 (2.2022)	loss 4.9338 (4.0869)	grad_norm 1.1698 (1.1404)	
[2022-01-18 17:24:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1190/1251]	eta 0:02:14 lr 0.000961	time 2.2275 (2.2012)	loss 3.9699 (4.0893)	grad_norm 0.9767 (1.1409)	
[2022-01-18 17:24:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1200/1251]	eta 0:01:52 lr 0.000961	time 2.4730 (2.2013)	loss 4.8041 (4.0897)	grad_norm 1.2460 (1.1419)	
[2022-01-18 17:25:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1210/1251]	eta 0:01:30 lr 0.000961	time 1.9245 (2.2016)	loss 3.1533 (4.0876)	grad_norm 1.0677 (1.1412)	
[2022-01-18 17:25:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1220/1251]	eta 0:01:08 lr 0.000961	time 2.5625 (2.2031)	loss 3.9905 (4.0868)	grad_norm 1.0295 (1.1407)	
[2022-01-18 17:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1230/1251]	eta 0:00:46 lr 0.000961	time 1.8966 (2.2035)	loss 4.6076 (4.0849)	grad_norm 0.9940 (1.1403)	
[2022-01-18 17:26:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1240/1251]	eta 0:00:24 lr 0.000961	time 2.3233 (2.2031)	loss 3.8441 (4.0860)	grad_norm 0.8642 (1.1399)	
[2022-01-18 17:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [37/300][1250/1251]	eta 0:00:02 lr 0.000961	time 1.1722 (2.1970)	loss 4.3390 (4.0866)	grad_norm 1.1599 (1.1395)	
[2022-01-18 17:26:34 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 37 training takes 0:45:48
[2022-01-18 17:26:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.793 (17.793)	Loss 1.4490 (1.4490)	Acc@1 66.504 (66.504)	Acc@5 87.402 (87.402)	
[2022-01-18 17:27:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.579 (3.389)	Loss 1.3957 (1.4034)	Acc@1 65.918 (67.649)	Acc@5 89.160 (88.725)	
[2022-01-18 17:27:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.960 (2.461)	Loss 1.4577 (1.4094)	Acc@1 66.895 (67.653)	Acc@5 87.012 (88.509)	
[2022-01-18 17:27:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.605 (2.228)	Loss 1.4764 (1.4155)	Acc@1 66.992 (67.566)	Acc@5 87.988 (88.486)	
[2022-01-18 17:28:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.338 (2.135)	Loss 1.4593 (1.4195)	Acc@1 67.578 (67.488)	Acc@5 88.867 (88.393)	
[2022-01-18 17:28:09 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 67.544 Acc@5 88.420
[2022-01-18 17:28:09 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 67.5%
[2022-01-18 17:28:09 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 67.70%
[2022-01-18 17:28:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][0/1251]	eta 7:41:59 lr 0.000961	time 22.1575 (22.1575)	loss 4.2806 (4.2806)	grad_norm 1.5902 (1.5902)	
[2022-01-18 17:28:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][10/1251]	eta 1:21:34 lr 0.000961	time 2.1934 (3.9437)	loss 2.7417 (3.9995)	grad_norm 1.0200 (1.1806)	
[2022-01-18 17:29:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][20/1251]	eta 1:04:04 lr 0.000961	time 1.9296 (3.1228)	loss 3.8300 (4.1087)	grad_norm 1.3256 (1.1789)	
[2022-01-18 17:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][30/1251]	eta 0:56:39 lr 0.000961	time 1.2010 (2.7843)	loss 3.9972 (4.0643)	grad_norm 1.5999 (1.2204)	
[2022-01-18 17:30:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][40/1251]	eta 0:54:42 lr 0.000961	time 5.9068 (2.7104)	loss 4.2067 (4.0368)	grad_norm 1.1690 (1.2052)	
[2022-01-18 17:30:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][50/1251]	eta 0:52:09 lr 0.000961	time 2.8459 (2.6058)	loss 4.3119 (4.0275)	grad_norm 1.1282 (1.1856)	
[2022-01-18 17:30:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][60/1251]	eta 0:50:32 lr 0.000961	time 1.8575 (2.5460)	loss 4.6789 (4.0550)	grad_norm 1.0563 (1.1663)	
[2022-01-18 17:31:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][70/1251]	eta 0:48:52 lr 0.000961	time 1.9195 (2.4834)	loss 4.7629 (4.0809)	grad_norm 1.1498 (1.1626)	
[2022-01-18 17:31:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][80/1251]	eta 0:48:08 lr 0.000961	time 4.0167 (2.4669)	loss 4.6042 (4.0566)	grad_norm 1.2358 (1.1541)	
[2022-01-18 17:31:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][90/1251]	eta 0:47:22 lr 0.000961	time 3.5950 (2.4483)	loss 3.1198 (4.0373)	grad_norm 1.0434 (1.1473)	
[2022-01-18 17:32:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][100/1251]	eta 0:46:13 lr 0.000961	time 2.2176 (2.4092)	loss 3.1019 (4.0465)	grad_norm 1.1106 (1.1422)	
[2022-01-18 17:32:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][110/1251]	eta 0:45:14 lr 0.000961	time 1.6055 (2.3791)	loss 4.6003 (4.0638)	grad_norm 1.0893 (1.1442)	
[2022-01-18 17:32:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][120/1251]	eta 0:44:27 lr 0.000961	time 3.0241 (2.3583)	loss 4.2331 (4.0623)	grad_norm 1.4899 (1.1482)	
[2022-01-18 17:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][130/1251]	eta 0:43:53 lr 0.000961	time 3.4779 (2.3489)	loss 3.8444 (4.0675)	grad_norm 1.2167 (1.1468)	
[2022-01-18 17:33:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][140/1251]	eta 0:43:23 lr 0.000961	time 2.5015 (2.3433)	loss 4.2363 (4.0641)	grad_norm 1.3116 (1.1378)	
[2022-01-18 17:34:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][150/1251]	eta 0:42:52 lr 0.000961	time 2.1599 (2.3368)	loss 4.2505 (4.0673)	grad_norm 1.0568 (1.1319)	
[2022-01-18 17:34:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][160/1251]	eta 0:42:16 lr 0.000961	time 2.6635 (2.3254)	loss 3.7511 (4.0623)	grad_norm 0.9643 (1.1275)	
[2022-01-18 17:34:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][170/1251]	eta 0:41:31 lr 0.000961	time 1.8825 (2.3050)	loss 4.9262 (4.0701)	grad_norm 1.2693 (1.1289)	
[2022-01-18 17:35:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][180/1251]	eta 0:40:56 lr 0.000961	time 1.8657 (2.2933)	loss 4.5874 (4.0811)	grad_norm 1.2989 (1.1270)	
[2022-01-18 17:35:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][190/1251]	eta 0:40:17 lr 0.000961	time 1.8572 (2.2782)	loss 3.7289 (4.0773)	grad_norm 1.3458 (1.1271)	
[2022-01-18 17:35:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][200/1251]	eta 0:39:48 lr 0.000961	time 1.8419 (2.2723)	loss 4.3688 (4.0759)	grad_norm 1.1951 (1.1277)	
[2022-01-18 17:36:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][210/1251]	eta 0:39:28 lr 0.000961	time 2.0983 (2.2751)	loss 4.1454 (4.0812)	grad_norm 0.9219 (1.1243)	
[2022-01-18 17:36:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][220/1251]	eta 0:39:06 lr 0.000961	time 2.5061 (2.2762)	loss 4.5936 (4.0908)	grad_norm 0.9677 (1.1207)	
[2022-01-18 17:36:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][230/1251]	eta 0:38:43 lr 0.000961	time 2.2338 (2.2753)	loss 4.4991 (4.0889)	grad_norm 1.3237 (1.1263)	
[2022-01-18 17:37:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][240/1251]	eta 0:38:14 lr 0.000961	time 1.6406 (2.2699)	loss 3.9930 (4.0962)	grad_norm 1.0491 (1.1286)	
[2022-01-18 17:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][250/1251]	eta 0:37:42 lr 0.000961	time 1.8476 (2.2598)	loss 4.7767 (4.1023)	grad_norm 0.9194 (1.1281)	
[2022-01-18 17:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][260/1251]	eta 0:37:16 lr 0.000961	time 2.8683 (2.2569)	loss 4.2957 (4.1103)	grad_norm 1.0478 (1.1275)	
[2022-01-18 17:38:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][270/1251]	eta 0:36:49 lr 0.000961	time 2.0038 (2.2524)	loss 3.9939 (4.1014)	grad_norm 0.9081 (1.1253)	
[2022-01-18 17:38:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][280/1251]	eta 0:36:26 lr 0.000961	time 1.9865 (2.2516)	loss 4.4530 (4.0910)	grad_norm 1.1297 (1.1276)	
[2022-01-18 17:39:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][290/1251]	eta 0:36:03 lr 0.000961	time 2.2024 (2.2512)	loss 3.9464 (4.0931)	grad_norm 1.0808 (1.1307)	
[2022-01-18 17:39:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][300/1251]	eta 0:35:46 lr 0.000961	time 2.6227 (2.2569)	loss 3.8933 (4.0878)	grad_norm 0.9830 (1.1277)	
[2022-01-18 17:39:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][310/1251]	eta 0:35:27 lr 0.000961	time 2.4414 (2.2605)	loss 4.8632 (4.0868)	grad_norm 1.0769 (1.1281)	
[2022-01-18 17:40:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][320/1251]	eta 0:35:05 lr 0.000961	time 3.0782 (2.2616)	loss 3.0116 (4.0817)	grad_norm 1.0386 (1.1278)	
[2022-01-18 17:40:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][330/1251]	eta 0:34:37 lr 0.000961	time 1.9148 (2.2560)	loss 4.7738 (4.0903)	grad_norm 1.1244 (1.1261)	
[2022-01-18 17:40:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][340/1251]	eta 0:34:07 lr 0.000961	time 2.6635 (2.2471)	loss 4.8250 (4.0899)	grad_norm 0.9752 (1.1244)	
[2022-01-18 17:41:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][350/1251]	eta 0:33:37 lr 0.000961	time 2.1788 (2.2394)	loss 3.2096 (4.0872)	grad_norm 1.7472 (1.1257)	
[2022-01-18 17:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][360/1251]	eta 0:33:15 lr 0.000961	time 2.8191 (2.2396)	loss 4.2277 (4.0896)	grad_norm 1.0835 (1.1272)	
[2022-01-18 17:41:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][370/1251]	eta 0:32:51 lr 0.000961	time 2.2199 (2.2374)	loss 3.3180 (4.0921)	grad_norm 1.4738 (1.1286)	
[2022-01-18 17:42:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][380/1251]	eta 0:32:29 lr 0.000961	time 2.2266 (2.2379)	loss 4.1426 (4.0925)	grad_norm 1.1746 (1.1308)	
[2022-01-18 17:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][390/1251]	eta 0:32:06 lr 0.000961	time 2.4987 (2.2371)	loss 4.8120 (4.0883)	grad_norm 1.1624 (1.1319)	
[2022-01-18 17:43:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][400/1251]	eta 0:31:43 lr 0.000961	time 1.8668 (2.2365)	loss 4.5177 (4.0899)	grad_norm 1.1566 (1.1318)	
[2022-01-18 17:43:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][410/1251]	eta 0:31:20 lr 0.000961	time 2.1104 (2.2363)	loss 4.2469 (4.0872)	grad_norm 1.2722 (1.1323)	
[2022-01-18 17:43:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][420/1251]	eta 0:30:55 lr 0.000961	time 1.5289 (2.2325)	loss 4.5856 (4.0856)	grad_norm 1.3093 (1.1354)	
[2022-01-18 17:44:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][430/1251]	eta 0:30:33 lr 0.000961	time 2.1670 (2.2333)	loss 3.3319 (4.0808)	grad_norm 1.1651 (1.1351)	
[2022-01-18 17:44:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][440/1251]	eta 0:30:13 lr 0.000961	time 2.8313 (2.2361)	loss 4.1565 (4.0747)	grad_norm 1.2567 (1.1373)	
[2022-01-18 17:44:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][450/1251]	eta 0:29:52 lr 0.000961	time 2.4187 (2.2383)	loss 4.4631 (4.0789)	grad_norm 1.1730 (1.1370)	
[2022-01-18 17:45:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][460/1251]	eta 0:29:27 lr 0.000961	time 2.1983 (2.2351)	loss 3.0743 (4.0747)	grad_norm 1.1676 (1.1366)	
[2022-01-18 17:45:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][470/1251]	eta 0:29:00 lr 0.000961	time 1.9436 (2.2285)	loss 3.4458 (4.0779)	grad_norm 1.0672 (1.1364)	
[2022-01-18 17:45:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][480/1251]	eta 0:28:35 lr 0.000961	time 2.2144 (2.2254)	loss 4.2972 (4.0852)	grad_norm 1.0628 (1.1361)	
[2022-01-18 17:46:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][490/1251]	eta 0:28:11 lr 0.000961	time 1.5213 (2.2229)	loss 4.3271 (4.0836)	grad_norm 1.0808 (1.1367)	
[2022-01-18 17:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][500/1251]	eta 0:27:47 lr 0.000961	time 1.8991 (2.2200)	loss 4.2382 (4.0878)	grad_norm 1.0650 (1.1373)	
[2022-01-18 17:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][510/1251]	eta 0:27:25 lr 0.000960	time 1.7764 (2.2203)	loss 4.3347 (4.0886)	grad_norm 1.1507 (1.1375)	
[2022-01-18 17:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][520/1251]	eta 0:27:04 lr 0.000960	time 2.6835 (2.2218)	loss 4.9231 (4.0883)	grad_norm 1.1262 (1.1379)	
[2022-01-18 17:47:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][530/1251]	eta 0:26:42 lr 0.000960	time 1.6019 (2.2221)	loss 4.8553 (4.0887)	grad_norm 1.3569 (1.1381)	
[2022-01-18 17:48:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][540/1251]	eta 0:26:20 lr 0.000960	time 1.7852 (2.2233)	loss 3.1717 (4.0856)	grad_norm 0.8713 (1.1392)	
[2022-01-18 17:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][550/1251]	eta 0:25:59 lr 0.000960	time 1.8387 (2.2245)	loss 3.5404 (4.0843)	grad_norm 1.1727 (1.1398)	
[2022-01-18 17:48:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][560/1251]	eta 0:25:37 lr 0.000960	time 2.5689 (2.2244)	loss 3.0058 (4.0756)	grad_norm 1.4336 (1.1411)	
[2022-01-18 17:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][570/1251]	eta 0:25:12 lr 0.000960	time 1.5879 (2.2205)	loss 4.5228 (4.0771)	grad_norm 1.1025 (1.1410)	
[2022-01-18 17:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][580/1251]	eta 0:24:50 lr 0.000960	time 2.3242 (2.2206)	loss 4.7452 (4.0743)	grad_norm 1.3591 (1.1412)	
[2022-01-18 17:50:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][590/1251]	eta 0:24:26 lr 0.000960	time 1.8629 (2.2181)	loss 4.1531 (4.0785)	grad_norm 1.0769 (1.1399)	
[2022-01-18 17:50:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][600/1251]	eta 0:24:03 lr 0.000960	time 1.9315 (2.2171)	loss 4.7539 (4.0763)	grad_norm 1.2354 (1.1410)	
[2022-01-18 17:50:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][610/1251]	eta 0:23:39 lr 0.000960	time 2.4311 (2.2148)	loss 4.1523 (4.0741)	grad_norm 1.0828 (1.1405)	
[2022-01-18 17:51:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][620/1251]	eta 0:23:15 lr 0.000960	time 1.8089 (2.2109)	loss 5.0095 (4.0782)	grad_norm 1.1626 (1.1407)	
[2022-01-18 17:51:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][630/1251]	eta 0:22:51 lr 0.000960	time 2.2152 (2.2088)	loss 4.1710 (4.0788)	grad_norm 1.4069 (1.1416)	
[2022-01-18 17:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][640/1251]	eta 0:22:29 lr 0.000960	time 2.7892 (2.2082)	loss 3.3922 (4.0748)	grad_norm 1.2415 (1.1413)	
[2022-01-18 17:52:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][650/1251]	eta 0:22:08 lr 0.000960	time 5.1872 (2.2111)	loss 4.7880 (4.0782)	grad_norm 1.1033 (1.1410)	
[2022-01-18 17:52:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][660/1251]	eta 0:21:46 lr 0.000960	time 2.1844 (2.2115)	loss 4.0551 (4.0731)	grad_norm 1.1823 (1.1428)	
[2022-01-18 17:52:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][670/1251]	eta 0:21:25 lr 0.000960	time 2.3437 (2.2132)	loss 3.9493 (4.0741)	grad_norm 0.8892 (1.1418)	
[2022-01-18 17:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][680/1251]	eta 0:21:04 lr 0.000960	time 2.2628 (2.2145)	loss 3.5633 (4.0776)	grad_norm 1.2461 (1.1416)	
[2022-01-18 17:53:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][690/1251]	eta 0:20:42 lr 0.000960	time 2.9706 (2.2155)	loss 3.6941 (4.0789)	grad_norm 1.3066 (1.1415)	
[2022-01-18 17:54:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][700/1251]	eta 0:20:19 lr 0.000960	time 2.2336 (2.2126)	loss 4.9297 (4.0835)	grad_norm 1.3096 (1.1416)	
[2022-01-18 17:54:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][710/1251]	eta 0:19:55 lr 0.000960	time 1.7302 (2.2097)	loss 4.3185 (4.0861)	grad_norm 1.1373 (1.1402)	
[2022-01-18 17:54:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][720/1251]	eta 0:19:32 lr 0.000960	time 1.9359 (2.2074)	loss 4.2763 (4.0842)	grad_norm 1.1387 (1.1401)	
[2022-01-18 17:55:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][730/1251]	eta 0:19:10 lr 0.000960	time 2.1912 (2.2074)	loss 4.9540 (4.0803)	grad_norm 1.0364 (1.1405)	
[2022-01-18 17:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][740/1251]	eta 0:18:46 lr 0.000960	time 2.1962 (2.2051)	loss 3.5246 (4.0805)	grad_norm 1.1005 (1.1412)	
[2022-01-18 17:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][750/1251]	eta 0:18:23 lr 0.000960	time 1.8586 (2.2033)	loss 4.7629 (4.0862)	grad_norm 1.2828 (1.1407)	
[2022-01-18 17:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][760/1251]	eta 0:18:01 lr 0.000960	time 1.9094 (2.2022)	loss 3.4045 (4.0836)	grad_norm 1.2783 (1.1415)	
[2022-01-18 17:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][770/1251]	eta 0:17:39 lr 0.000960	time 1.9178 (2.2021)	loss 4.3013 (4.0804)	grad_norm 0.9648 (1.1405)	
[2022-01-18 17:56:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][780/1251]	eta 0:17:17 lr 0.000960	time 2.5616 (2.2021)	loss 4.1034 (4.0773)	grad_norm 1.1080 (1.1405)	
[2022-01-18 17:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][790/1251]	eta 0:16:55 lr 0.000960	time 2.1242 (2.2030)	loss 3.2339 (4.0761)	grad_norm 0.9929 (1.1402)	
[2022-01-18 17:57:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][800/1251]	eta 0:16:34 lr 0.000960	time 2.8473 (2.2044)	loss 4.0079 (4.0797)	grad_norm 1.0906 (1.1408)	
[2022-01-18 17:57:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][810/1251]	eta 0:16:12 lr 0.000960	time 2.4519 (2.2063)	loss 3.0361 (4.0785)	grad_norm 1.1898 (1.1429)	
[2022-01-18 17:58:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][820/1251]	eta 0:15:50 lr 0.000960	time 1.9488 (2.2058)	loss 3.9721 (4.0776)	grad_norm 1.1191 (1.1443)	
[2022-01-18 17:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][830/1251]	eta 0:15:28 lr 0.000960	time 2.2489 (2.2056)	loss 4.5573 (4.0795)	grad_norm 1.2102 (1.1448)	
[2022-01-18 17:59:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][840/1251]	eta 0:15:06 lr 0.000960	time 2.2269 (2.2052)	loss 3.3723 (4.0810)	grad_norm 1.2490 (1.1448)	
[2022-01-18 17:59:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][850/1251]	eta 0:14:44 lr 0.000960	time 2.7491 (2.2058)	loss 4.2912 (4.0809)	grad_norm 1.2232 (1.1444)	
[2022-01-18 17:59:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][860/1251]	eta 0:14:21 lr 0.000960	time 1.9461 (2.2044)	loss 4.3405 (4.0842)	grad_norm 1.1857 (1.1447)	
[2022-01-18 18:00:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][870/1251]	eta 0:13:58 lr 0.000960	time 1.9581 (2.2013)	loss 2.8597 (4.0838)	grad_norm 0.8910 (1.1439)	
[2022-01-18 18:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][880/1251]	eta 0:13:35 lr 0.000960	time 2.0190 (2.1994)	loss 4.8646 (4.0832)	grad_norm 0.9413 (1.1436)	
[2022-01-18 18:00:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][890/1251]	eta 0:13:14 lr 0.000960	time 2.2971 (2.2002)	loss 4.2518 (4.0809)	grad_norm 1.5510 (1.1445)	
[2022-01-18 18:01:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][900/1251]	eta 0:12:51 lr 0.000960	time 1.8838 (2.1988)	loss 3.9783 (4.0866)	grad_norm 1.0219 (1.1455)	
[2022-01-18 18:01:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][910/1251]	eta 0:12:29 lr 0.000960	time 2.4444 (2.1978)	loss 4.2365 (4.0893)	grad_norm 1.0629 (1.1452)	
[2022-01-18 18:01:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][920/1251]	eta 0:12:07 lr 0.000960	time 2.1239 (2.1983)	loss 2.8163 (4.0882)	grad_norm 0.9106 (1.1448)	
[2022-01-18 18:02:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][930/1251]	eta 0:11:46 lr 0.000960	time 2.6837 (2.2001)	loss 4.3115 (4.0878)	grad_norm 0.9464 (1.1436)	
[2022-01-18 18:02:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][940/1251]	eta 0:11:24 lr 0.000960	time 1.8106 (2.2020)	loss 4.1651 (4.0868)	grad_norm 1.0573 (1.1440)	
[2022-01-18 18:03:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][950/1251]	eta 0:11:02 lr 0.000960	time 2.4651 (2.2026)	loss 4.8513 (4.0875)	grad_norm 0.9727 (1.1441)	
[2022-01-18 18:03:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][960/1251]	eta 0:10:40 lr 0.000960	time 1.6137 (2.2007)	loss 3.6942 (4.0860)	grad_norm 0.9702 (1.1438)	
[2022-01-18 18:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][970/1251]	eta 0:10:17 lr 0.000960	time 2.3359 (2.1982)	loss 3.0498 (4.0876)	grad_norm 0.9436 (1.1442)	
[2022-01-18 18:04:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][980/1251]	eta 0:09:55 lr 0.000960	time 1.9238 (2.1973)	loss 3.2497 (4.0872)	grad_norm 0.9781 (1.1432)	
[2022-01-18 18:04:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][990/1251]	eta 0:09:33 lr 0.000960	time 2.8237 (2.1985)	loss 3.2404 (4.0854)	grad_norm 1.5387 (1.1435)	
[2022-01-18 18:04:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1000/1251]	eta 0:09:12 lr 0.000960	time 1.5118 (2.1999)	loss 4.7784 (4.0852)	grad_norm 1.1906 (1.1432)	
[2022-01-18 18:05:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1010/1251]	eta 0:08:51 lr 0.000960	time 3.9849 (2.2034)	loss 3.2201 (4.0809)	grad_norm 1.0723 (1.1435)	
[2022-01-18 18:05:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1020/1251]	eta 0:08:28 lr 0.000960	time 1.9051 (2.2034)	loss 4.5333 (4.0829)	grad_norm 1.0654 (1.1433)	
[2022-01-18 18:05:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1030/1251]	eta 0:08:06 lr 0.000960	time 1.9494 (2.2016)	loss 3.4294 (4.0821)	grad_norm 1.1843 (1.1433)	
[2022-01-18 18:06:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1040/1251]	eta 0:07:43 lr 0.000960	time 1.6209 (2.1983)	loss 4.0042 (4.0815)	grad_norm 1.1700 (1.1437)	
[2022-01-18 18:06:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1050/1251]	eta 0:07:21 lr 0.000960	time 2.1661 (2.1968)	loss 4.6151 (4.0827)	grad_norm 1.1531 (1.1431)	
[2022-01-18 18:06:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1060/1251]	eta 0:06:59 lr 0.000960	time 1.8282 (2.1951)	loss 3.5548 (4.0825)	grad_norm 1.1684 (1.1438)	
[2022-01-18 18:07:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1070/1251]	eta 0:06:37 lr 0.000960	time 2.2088 (2.1941)	loss 3.6549 (4.0822)	grad_norm 1.1767 (1.1431)	
[2022-01-18 18:07:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1080/1251]	eta 0:06:15 lr 0.000960	time 2.3659 (2.1945)	loss 3.8005 (4.0821)	grad_norm 1.0509 (1.1428)	
[2022-01-18 18:08:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1090/1251]	eta 0:05:53 lr 0.000960	time 2.2453 (2.1953)	loss 4.7621 (4.0834)	grad_norm 1.2368 (1.1424)	
[2022-01-18 18:08:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1100/1251]	eta 0:05:31 lr 0.000960	time 2.1209 (2.1947)	loss 2.8044 (4.0809)	grad_norm 1.1129 (1.1419)	
[2022-01-18 18:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1110/1251]	eta 0:05:09 lr 0.000960	time 1.5349 (2.1942)	loss 4.0125 (4.0825)	grad_norm 1.1483 (1.1414)	
[2022-01-18 18:09:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1120/1251]	eta 0:04:47 lr 0.000960	time 2.1496 (2.1950)	loss 4.0718 (4.0802)	grad_norm 1.4415 (1.1414)	
[2022-01-18 18:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1130/1251]	eta 0:04:25 lr 0.000959	time 2.8513 (2.1967)	loss 4.2353 (4.0781)	grad_norm 1.0400 (1.1409)	
[2022-01-18 18:09:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1140/1251]	eta 0:04:04 lr 0.000959	time 2.7492 (2.1988)	loss 4.2904 (4.0783)	grad_norm 1.2523 (1.1407)	
[2022-01-18 18:10:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1150/1251]	eta 0:03:41 lr 0.000959	time 1.6617 (2.1979)	loss 4.8394 (4.0803)	grad_norm 1.0393 (1.1409)	
[2022-01-18 18:10:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1160/1251]	eta 0:03:20 lr 0.000959	time 1.6329 (2.1981)	loss 3.4448 (4.0779)	grad_norm 1.0473 (1.1405)	
[2022-01-18 18:11:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1170/1251]	eta 0:02:58 lr 0.000959	time 2.1253 (2.1986)	loss 4.4677 (4.0772)	grad_norm 1.0077 (1.1399)	
[2022-01-18 18:11:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1180/1251]	eta 0:02:36 lr 0.000959	time 3.2578 (2.1999)	loss 4.3198 (4.0742)	grad_norm 0.9817 (1.1397)	
[2022-01-18 18:11:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1190/1251]	eta 0:02:14 lr 0.000959	time 1.7779 (2.1991)	loss 4.3783 (4.0743)	grad_norm 1.1448 (1.1398)	
[2022-01-18 18:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1200/1251]	eta 0:01:52 lr 0.000959	time 2.0384 (2.1973)	loss 3.6128 (4.0736)	grad_norm 1.3932 (1.1396)	
[2022-01-18 18:12:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1210/1251]	eta 0:01:30 lr 0.000959	time 1.9507 (2.1951)	loss 4.3861 (4.0737)	grad_norm 1.0869 (1.1396)	
[2022-01-18 18:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1220/1251]	eta 0:01:08 lr 0.000959	time 2.2145 (2.1939)	loss 3.2165 (4.0748)	grad_norm 0.9288 (1.1387)	
[2022-01-18 18:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1230/1251]	eta 0:00:46 lr 0.000959	time 3.5830 (2.1951)	loss 3.9938 (4.0760)	grad_norm 1.0808 (1.1383)	
[2022-01-18 18:13:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1240/1251]	eta 0:00:24 lr 0.000959	time 2.0107 (2.1949)	loss 3.9547 (4.0760)	grad_norm 1.0462 (1.1382)	
[2022-01-18 18:13:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [38/300][1250/1251]	eta 0:00:02 lr 0.000959	time 1.1693 (2.1891)	loss 4.8486 (4.0745)	grad_norm 1.2070 (1.1380)	
[2022-01-18 18:13:48 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 38 training takes 0:45:39
[2022-01-18 18:14:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.957 (18.957)	Loss 1.3691 (1.3691)	Acc@1 68.555 (68.555)	Acc@5 89.258 (89.258)	
[2022-01-18 18:14:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.320 (3.204)	Loss 1.3896 (1.3800)	Acc@1 67.090 (68.040)	Acc@5 88.281 (88.627)	
[2022-01-18 18:14:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.903 (2.543)	Loss 1.2441 (1.3525)	Acc@1 69.922 (68.345)	Acc@5 90.527 (89.160)	
[2022-01-18 18:14:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.964 (2.252)	Loss 1.3803 (1.3506)	Acc@1 66.406 (68.422)	Acc@5 88.965 (89.132)	
[2022-01-18 18:15:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.549 (2.187)	Loss 1.3653 (1.3591)	Acc@1 67.773 (68.236)	Acc@5 88.770 (88.982)	
[2022-01-18 18:15:25 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 68.270 Acc@5 88.998
[2022-01-18 18:15:25 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 68.3%
[2022-01-18 18:15:25 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 68.27%
[2022-01-18 18:15:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][0/1251]	eta 7:37:03 lr 0.000959	time 21.9212 (21.9212)	loss 3.8893 (3.8893)	grad_norm 1.0841 (1.0841)	
[2022-01-18 18:16:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][10/1251]	eta 1:23:09 lr 0.000959	time 2.2200 (4.0203)	loss 4.7712 (4.1353)	grad_norm 1.1400 (1.0739)	
[2022-01-18 18:16:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][20/1251]	eta 1:03:00 lr 0.000959	time 2.1653 (3.0714)	loss 4.3982 (4.1674)	grad_norm 1.0655 (1.1074)	
[2022-01-18 18:16:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][30/1251]	eta 0:55:43 lr 0.000959	time 1.4050 (2.7387)	loss 4.0332 (4.1514)	grad_norm 1.3284 (1.1147)	
[2022-01-18 18:17:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][40/1251]	eta 0:53:53 lr 0.000959	time 3.8621 (2.6699)	loss 3.4564 (4.0763)	grad_norm 1.1787 (1.1622)	
[2022-01-18 18:17:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][50/1251]	eta 0:51:35 lr 0.000959	time 2.2512 (2.5771)	loss 3.9982 (4.0580)	grad_norm 1.3717 (1.1637)	
[2022-01-18 18:18:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][60/1251]	eta 0:50:32 lr 0.000959	time 2.4515 (2.5462)	loss 4.4186 (4.0458)	grad_norm 1.0119 (1.1552)	
[2022-01-18 18:18:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][70/1251]	eta 0:48:58 lr 0.000959	time 2.8049 (2.4883)	loss 4.1374 (4.0243)	grad_norm 1.0635 (1.1650)	
[2022-01-18 18:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][80/1251]	eta 0:48:18 lr 0.000959	time 3.1320 (2.4752)	loss 3.4766 (4.0056)	grad_norm 1.1057 (1.1520)	
[2022-01-18 18:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][90/1251]	eta 0:47:20 lr 0.000959	time 2.5607 (2.4466)	loss 4.2812 (4.0239)	grad_norm 1.1456 (1.1524)	
[2022-01-18 18:19:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][100/1251]	eta 0:46:18 lr 0.000959	time 2.1818 (2.4142)	loss 3.5649 (4.0505)	grad_norm 1.2057 (1.1607)	
[2022-01-18 18:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][110/1251]	eta 0:45:36 lr 0.000959	time 2.9725 (2.3986)	loss 4.0898 (4.0700)	grad_norm 0.9117 (1.1593)	
[2022-01-18 18:20:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][120/1251]	eta 0:44:55 lr 0.000959	time 2.9642 (2.3834)	loss 4.4745 (4.0722)	grad_norm 1.3223 (1.1602)	
[2022-01-18 18:20:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][130/1251]	eta 0:44:06 lr 0.000959	time 2.3143 (2.3609)	loss 4.2329 (4.1019)	grad_norm 1.1783 (1.1628)	
[2022-01-18 18:20:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][140/1251]	eta 0:43:27 lr 0.000959	time 2.2373 (2.3474)	loss 3.9421 (4.0951)	grad_norm 1.2603 (1.1568)	
[2022-01-18 18:21:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][150/1251]	eta 0:42:50 lr 0.000959	time 2.3367 (2.3347)	loss 4.3533 (4.0953)	grad_norm 0.9203 (1.1569)	
[2022-01-18 18:21:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][160/1251]	eta 0:42:16 lr 0.000959	time 2.6101 (2.3245)	loss 4.7298 (4.0931)	grad_norm 0.9587 (1.1549)	
[2022-01-18 18:22:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][170/1251]	eta 0:41:41 lr 0.000959	time 2.9188 (2.3143)	loss 4.5078 (4.0848)	grad_norm 1.0276 (1.1490)	
[2022-01-18 18:22:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][180/1251]	eta 0:41:03 lr 0.000959	time 1.6552 (2.3000)	loss 4.1402 (4.0854)	grad_norm 1.3934 (1.1539)	
[2022-01-18 18:22:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][190/1251]	eta 0:40:24 lr 0.000959	time 1.9237 (2.2851)	loss 4.4510 (4.0965)	grad_norm 1.0107 (1.1595)	
[2022-01-18 18:23:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][200/1251]	eta 0:39:50 lr 0.000959	time 1.8229 (2.2740)	loss 3.2060 (4.0959)	grad_norm 0.9821 (1.1539)	
[2022-01-18 18:23:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][210/1251]	eta 0:39:31 lr 0.000959	time 3.0976 (2.2780)	loss 3.6648 (4.0870)	grad_norm 1.0749 (1.1520)	
[2022-01-18 18:23:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][220/1251]	eta 0:39:04 lr 0.000959	time 2.2227 (2.2741)	loss 4.1961 (4.0951)	grad_norm 1.0029 (1.1485)	
[2022-01-18 18:24:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][230/1251]	eta 0:38:37 lr 0.000959	time 1.8343 (2.2700)	loss 4.5053 (4.0936)	grad_norm 1.4684 (1.1507)	
[2022-01-18 18:24:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][240/1251]	eta 0:38:12 lr 0.000959	time 2.1644 (2.2679)	loss 4.0214 (4.0958)	grad_norm 1.1056 (1.1513)	
[2022-01-18 18:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][250/1251]	eta 0:37:46 lr 0.000959	time 2.3749 (2.2638)	loss 3.5241 (4.0814)	grad_norm 1.0860 (1.1535)	
[2022-01-18 18:25:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][260/1251]	eta 0:37:20 lr 0.000959	time 2.4302 (2.2610)	loss 4.6459 (4.0862)	grad_norm 1.0786 (1.1478)	
[2022-01-18 18:25:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][270/1251]	eta 0:36:51 lr 0.000959	time 1.7215 (2.2539)	loss 4.2915 (4.0875)	grad_norm 1.0455 (1.1481)	
[2022-01-18 18:25:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][280/1251]	eta 0:36:25 lr 0.000959	time 1.8755 (2.2506)	loss 3.5316 (4.0834)	grad_norm 0.9474 (1.1456)	
[2022-01-18 18:26:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][290/1251]	eta 0:36:01 lr 0.000959	time 2.4813 (2.2490)	loss 3.9581 (4.0732)	grad_norm 0.9611 (1.1429)	
[2022-01-18 18:26:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][300/1251]	eta 0:35:42 lr 0.000959	time 2.3620 (2.2528)	loss 4.8316 (4.0732)	grad_norm 1.0390 (1.1426)	
[2022-01-18 18:27:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][310/1251]	eta 0:35:22 lr 0.000959	time 1.9583 (2.2557)	loss 4.8591 (4.0739)	grad_norm 1.0456 (1.1388)	
[2022-01-18 18:27:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][320/1251]	eta 0:35:01 lr 0.000959	time 1.8983 (2.2569)	loss 4.5801 (4.0787)	grad_norm 0.9225 (1.1372)	
[2022-01-18 18:27:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][330/1251]	eta 0:34:33 lr 0.000959	time 1.9211 (2.2518)	loss 2.8390 (4.0758)	grad_norm 1.1359 (1.1377)	
[2022-01-18 18:28:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][340/1251]	eta 0:34:05 lr 0.000959	time 1.9126 (2.2448)	loss 4.4613 (4.0725)	grad_norm 1.0770 (1.1393)	
[2022-01-18 18:28:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][350/1251]	eta 0:33:36 lr 0.000959	time 1.8983 (2.2381)	loss 4.3013 (4.0740)	grad_norm 1.0503 (1.1412)	
[2022-01-18 18:28:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][360/1251]	eta 0:33:10 lr 0.000959	time 2.4640 (2.2337)	loss 3.4803 (4.0652)	grad_norm 1.4147 (1.1420)	
[2022-01-18 18:29:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][370/1251]	eta 0:32:45 lr 0.000959	time 2.1547 (2.2310)	loss 3.0975 (4.0678)	grad_norm 1.2656 (1.1433)	
[2022-01-18 18:29:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][380/1251]	eta 0:32:19 lr 0.000959	time 1.6546 (2.2269)	loss 3.7900 (4.0716)	grad_norm 1.1779 (1.1471)	
[2022-01-18 18:29:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][390/1251]	eta 0:31:57 lr 0.000959	time 1.9826 (2.2269)	loss 3.0132 (4.0705)	grad_norm 1.3449 (1.1470)	
[2022-01-18 18:30:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][400/1251]	eta 0:31:34 lr 0.000959	time 2.6369 (2.2259)	loss 4.4540 (4.0750)	grad_norm 1.0112 (1.1463)	
[2022-01-18 18:30:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][410/1251]	eta 0:31:16 lr 0.000959	time 2.1480 (2.2310)	loss 3.6751 (4.0760)	grad_norm 1.1367 (1.1452)	
[2022-01-18 18:31:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][420/1251]	eta 0:30:52 lr 0.000959	time 2.4432 (2.2294)	loss 3.3715 (4.0778)	grad_norm 1.1653 (1.1479)	
[2022-01-18 18:31:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][430/1251]	eta 0:30:29 lr 0.000959	time 1.6057 (2.2284)	loss 4.3734 (4.0826)	grad_norm 1.1358 (1.1478)	
[2022-01-18 18:31:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][440/1251]	eta 0:30:05 lr 0.000959	time 2.0038 (2.2266)	loss 3.2692 (4.0834)	grad_norm 1.5829 (1.1496)	
[2022-01-18 18:32:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][450/1251]	eta 0:29:44 lr 0.000959	time 2.5307 (2.2280)	loss 3.8490 (4.0775)	grad_norm 0.9140 (1.1494)	
[2022-01-18 18:32:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][460/1251]	eta 0:29:20 lr 0.000959	time 1.6852 (2.2258)	loss 2.8408 (4.0686)	grad_norm 1.6563 (1.1512)	
[2022-01-18 18:32:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][470/1251]	eta 0:28:59 lr 0.000959	time 1.5747 (2.2272)	loss 4.0097 (4.0717)	grad_norm 1.0135 (1.1506)	
[2022-01-18 18:33:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][480/1251]	eta 0:28:35 lr 0.000958	time 2.2478 (2.2257)	loss 3.9598 (4.0753)	grad_norm 0.9696 (1.1510)	
[2022-01-18 18:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][490/1251]	eta 0:28:12 lr 0.000958	time 2.1299 (2.2236)	loss 4.3136 (4.0784)	grad_norm 1.0881 (1.1534)	
[2022-01-18 18:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][500/1251]	eta 0:27:46 lr 0.000958	time 1.8801 (2.2195)	loss 4.3422 (4.0718)	grad_norm 0.8909 (1.1558)	
[2022-01-18 18:34:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][510/1251]	eta 0:27:23 lr 0.000958	time 2.3315 (2.2180)	loss 3.7610 (4.0730)	grad_norm 0.9455 (1.1547)	
[2022-01-18 18:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][520/1251]	eta 0:26:59 lr 0.000958	time 1.6233 (2.2151)	loss 4.8884 (4.0788)	grad_norm 1.1144 (1.1540)	
[2022-01-18 18:35:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][530/1251]	eta 0:26:38 lr 0.000958	time 2.3063 (2.2171)	loss 3.6721 (4.0749)	grad_norm 0.9570 (1.1533)	
[2022-01-18 18:35:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][540/1251]	eta 0:26:16 lr 0.000958	time 2.1102 (2.2170)	loss 4.3199 (4.0730)	grad_norm 1.0997 (1.1526)	
[2022-01-18 18:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][550/1251]	eta 0:25:56 lr 0.000958	time 2.2752 (2.2200)	loss 3.9576 (4.0739)	grad_norm 0.9100 (1.1507)	
[2022-01-18 18:36:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][560/1251]	eta 0:25:36 lr 0.000958	time 2.3871 (2.2234)	loss 2.7375 (4.0745)	grad_norm 1.0801 (1.1504)	
[2022-01-18 18:36:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][570/1251]	eta 0:25:13 lr 0.000958	time 1.9394 (2.2221)	loss 4.3871 (4.0782)	grad_norm 1.4162 (1.1504)	
[2022-01-18 18:36:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][580/1251]	eta 0:24:48 lr 0.000958	time 2.0602 (2.2187)	loss 4.1040 (4.0805)	grad_norm 1.1593 (1.1498)	
[2022-01-18 18:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][590/1251]	eta 0:24:24 lr 0.000958	time 2.5830 (2.2152)	loss 4.5630 (4.0824)	grad_norm 1.1198 (1.1493)	
[2022-01-18 18:37:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][600/1251]	eta 0:24:01 lr 0.000958	time 2.6831 (2.2142)	loss 4.6484 (4.0863)	grad_norm 1.0349 (1.1504)	
[2022-01-18 18:37:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][610/1251]	eta 0:23:38 lr 0.000958	time 1.9901 (2.2127)	loss 4.5786 (4.0928)	grad_norm 1.3965 (1.1508)	
[2022-01-18 18:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][620/1251]	eta 0:23:15 lr 0.000958	time 2.1589 (2.2118)	loss 4.1688 (4.0905)	grad_norm 1.4859 (1.1508)	
[2022-01-18 18:38:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][630/1251]	eta 0:22:52 lr 0.000958	time 2.1347 (2.2106)	loss 4.6968 (4.0907)	grad_norm 1.4435 (1.1525)	
[2022-01-18 18:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][640/1251]	eta 0:22:30 lr 0.000958	time 2.6365 (2.2103)	loss 3.6228 (4.0869)	grad_norm 1.0427 (1.1506)	
[2022-01-18 18:39:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][650/1251]	eta 0:22:09 lr 0.000958	time 2.5271 (2.2120)	loss 4.1562 (4.0863)	grad_norm 1.1377 (1.1498)	
[2022-01-18 18:39:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][660/1251]	eta 0:21:49 lr 0.000958	time 2.9938 (2.2152)	loss 3.5212 (4.0848)	grad_norm 0.9307 (1.1478)	
[2022-01-18 18:40:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][670/1251]	eta 0:21:28 lr 0.000958	time 2.8971 (2.2175)	loss 4.0427 (4.0895)	grad_norm 1.2021 (1.1462)	
[2022-01-18 18:40:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][680/1251]	eta 0:21:06 lr 0.000958	time 2.3056 (2.2183)	loss 2.6675 (4.0864)	grad_norm 1.0092 (1.1474)	
[2022-01-18 18:40:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][690/1251]	eta 0:20:43 lr 0.000958	time 1.7455 (2.2171)	loss 2.9885 (4.0834)	grad_norm 0.9088 (1.1467)	
[2022-01-18 18:41:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][700/1251]	eta 0:20:20 lr 0.000958	time 2.1721 (2.2147)	loss 3.6435 (4.0810)	grad_norm 1.5199 (1.1474)	
[2022-01-18 18:41:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][710/1251]	eta 0:19:55 lr 0.000958	time 2.1789 (2.2102)	loss 4.7146 (4.0822)	grad_norm 1.3464 (1.1478)	
[2022-01-18 18:41:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][720/1251]	eta 0:19:31 lr 0.000958	time 1.9640 (2.2064)	loss 4.1234 (4.0815)	grad_norm 1.0580 (1.1485)	
[2022-01-18 18:42:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][730/1251]	eta 0:19:08 lr 0.000958	time 1.8639 (2.2039)	loss 3.4999 (4.0833)	grad_norm 1.0371 (1.1475)	
[2022-01-18 18:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][740/1251]	eta 0:18:46 lr 0.000958	time 2.1101 (2.2039)	loss 3.8887 (4.0796)	grad_norm 0.9620 (1.1486)	
[2022-01-18 18:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][750/1251]	eta 0:18:24 lr 0.000958	time 2.5295 (2.2056)	loss 4.2909 (4.0791)	grad_norm 1.1689 (1.1485)	
[2022-01-18 18:43:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][760/1251]	eta 0:18:04 lr 0.000958	time 2.4596 (2.2079)	loss 3.0443 (4.0781)	grad_norm 1.2847 (1.1491)	
[2022-01-18 18:43:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][770/1251]	eta 0:17:42 lr 0.000958	time 1.8247 (2.2085)	loss 3.4654 (4.0774)	grad_norm 1.1153 (1.1487)	
[2022-01-18 18:44:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][780/1251]	eta 0:17:20 lr 0.000958	time 2.4949 (2.2100)	loss 4.7231 (4.0760)	grad_norm 1.1020 (1.1495)	
[2022-01-18 18:44:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][790/1251]	eta 0:16:59 lr 0.000958	time 2.4983 (2.2117)	loss 3.4433 (4.0736)	grad_norm 1.0227 (1.1484)	
[2022-01-18 18:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][800/1251]	eta 0:16:37 lr 0.000958	time 2.9709 (2.2127)	loss 4.5960 (4.0757)	grad_norm 0.8966 (1.1471)	
[2022-01-18 18:45:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][810/1251]	eta 0:16:14 lr 0.000958	time 1.8275 (2.2105)	loss 3.7162 (4.0749)	grad_norm 0.9304 (1.1470)	
[2022-01-18 18:45:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][820/1251]	eta 0:15:51 lr 0.000958	time 2.2926 (2.2075)	loss 4.5216 (4.0752)	grad_norm 1.2613 (1.1490)	
[2022-01-18 18:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][830/1251]	eta 0:15:28 lr 0.000958	time 1.8660 (2.2055)	loss 3.4442 (4.0730)	grad_norm 1.0397 (1.1486)	
[2022-01-18 18:46:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][840/1251]	eta 0:15:06 lr 0.000958	time 2.2392 (2.2044)	loss 3.0904 (4.0727)	grad_norm 1.1730 (1.1494)	
[2022-01-18 18:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][850/1251]	eta 0:14:44 lr 0.000958	time 2.6752 (2.2051)	loss 2.8051 (4.0704)	grad_norm 1.1140 (1.1491)	
[2022-01-18 18:47:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][860/1251]	eta 0:14:22 lr 0.000958	time 2.5688 (2.2057)	loss 4.6915 (4.0739)	grad_norm 0.9574 (1.1499)	
[2022-01-18 18:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][870/1251]	eta 0:14:00 lr 0.000958	time 2.1746 (2.2060)	loss 4.3201 (4.0746)	grad_norm 1.1512 (1.1503)	
[2022-01-18 18:47:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][880/1251]	eta 0:13:39 lr 0.000958	time 2.2056 (2.2085)	loss 4.5355 (4.0726)	grad_norm 1.1351 (1.1502)	
[2022-01-18 18:48:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][890/1251]	eta 0:13:17 lr 0.000958	time 1.9515 (2.2089)	loss 3.7819 (4.0725)	grad_norm 1.2068 (1.1503)	
[2022-01-18 18:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][900/1251]	eta 0:12:55 lr 0.000958	time 2.9994 (2.2088)	loss 3.9427 (4.0752)	grad_norm 0.9886 (1.1503)	
[2022-01-18 18:48:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][910/1251]	eta 0:12:32 lr 0.000958	time 1.9418 (2.2057)	loss 4.1269 (4.0746)	grad_norm 0.9187 (1.1493)	
[2022-01-18 18:49:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][920/1251]	eta 0:12:09 lr 0.000958	time 2.2983 (2.2046)	loss 3.4806 (4.0702)	grad_norm 1.0048 (1.1487)	
[2022-01-18 18:49:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][930/1251]	eta 0:11:46 lr 0.000958	time 1.9176 (2.2018)	loss 4.3262 (4.0687)	grad_norm 1.6248 (1.1489)	
[2022-01-18 18:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][940/1251]	eta 0:11:24 lr 0.000958	time 2.1897 (2.2005)	loss 4.3638 (4.0683)	grad_norm 1.4259 (1.1502)	
[2022-01-18 18:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][950/1251]	eta 0:11:02 lr 0.000958	time 2.9007 (2.2011)	loss 4.1049 (4.0705)	grad_norm 1.1557 (1.1513)	
[2022-01-18 18:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][960/1251]	eta 0:10:40 lr 0.000958	time 1.6165 (2.2007)	loss 3.7642 (4.0693)	grad_norm 0.8665 (1.1507)	
[2022-01-18 18:51:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][970/1251]	eta 0:10:18 lr 0.000958	time 1.9182 (2.2011)	loss 4.9558 (4.0683)	grad_norm 1.1867 (1.1507)	
[2022-01-18 18:51:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][980/1251]	eta 0:09:57 lr 0.000958	time 2.4402 (2.2031)	loss 3.2495 (4.0693)	grad_norm 1.1240 (1.1496)	
[2022-01-18 18:51:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][990/1251]	eta 0:09:35 lr 0.000958	time 2.3207 (2.2032)	loss 4.7823 (4.0684)	grad_norm 1.1643 (1.1489)	
[2022-01-18 18:52:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1000/1251]	eta 0:09:12 lr 0.000958	time 1.8731 (2.2029)	loss 3.8458 (4.0682)	grad_norm 1.2532 (1.1485)	
[2022-01-18 18:52:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1010/1251]	eta 0:08:51 lr 0.000958	time 2.1226 (2.2041)	loss 3.3757 (4.0663)	grad_norm 1.1045 (1.1491)	
[2022-01-18 18:52:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1020/1251]	eta 0:08:28 lr 0.000958	time 2.3253 (2.2027)	loss 3.4771 (4.0665)	grad_norm 1.4757 (1.1491)	
[2022-01-18 18:53:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1030/1251]	eta 0:08:06 lr 0.000958	time 2.2680 (2.2022)	loss 4.0585 (4.0689)	grad_norm 1.0028 (1.1491)	
[2022-01-18 18:53:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1040/1251]	eta 0:07:44 lr 0.000958	time 1.7436 (2.2015)	loss 3.7905 (4.0690)	grad_norm 0.9792 (1.1485)	
[2022-01-18 18:53:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1050/1251]	eta 0:07:22 lr 0.000958	time 2.3309 (2.2006)	loss 3.4942 (4.0685)	grad_norm 1.1417 (1.1481)	
[2022-01-18 18:54:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1060/1251]	eta 0:07:00 lr 0.000958	time 2.2562 (2.2001)	loss 3.0320 (4.0679)	grad_norm 0.9925 (1.1481)	
[2022-01-18 18:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1070/1251]	eta 0:06:37 lr 0.000958	time 1.8363 (2.1985)	loss 4.2658 (4.0653)	grad_norm 0.9736 (1.1476)	
[2022-01-18 18:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1080/1251]	eta 0:06:15 lr 0.000957	time 1.5845 (2.1973)	loss 4.7271 (4.0674)	grad_norm 1.0785 (1.1475)	
[2022-01-18 18:55:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1090/1251]	eta 0:05:53 lr 0.000957	time 2.8846 (2.1978)	loss 3.9986 (4.0686)	grad_norm 1.1860 (1.1472)	
[2022-01-18 18:55:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1100/1251]	eta 0:05:31 lr 0.000957	time 2.8024 (2.1983)	loss 4.0356 (4.0694)	grad_norm 1.0567 (1.1462)	
[2022-01-18 18:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1110/1251]	eta 0:05:09 lr 0.000957	time 1.5304 (2.1983)	loss 4.3610 (4.0715)	grad_norm 1.2161 (1.1463)	
[2022-01-18 18:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1120/1251]	eta 0:04:48 lr 0.000957	time 1.8976 (2.1988)	loss 4.1175 (4.0727)	grad_norm 1.0808 (1.1459)	
[2022-01-18 18:56:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1130/1251]	eta 0:04:26 lr 0.000957	time 3.6404 (2.1996)	loss 3.0747 (4.0728)	grad_norm 1.1263 (1.1466)	
[2022-01-18 18:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1140/1251]	eta 0:04:04 lr 0.000957	time 2.8976 (2.2000)	loss 4.7843 (4.0735)	grad_norm 1.0248 (1.1458)	
[2022-01-18 18:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1150/1251]	eta 0:03:42 lr 0.000957	time 1.5036 (2.1990)	loss 4.3774 (4.0761)	grad_norm 1.0606 (1.1452)	
[2022-01-18 18:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1160/1251]	eta 0:03:20 lr 0.000957	time 1.6238 (2.1983)	loss 3.9646 (4.0781)	grad_norm 1.0668 (1.1445)	
[2022-01-18 18:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1170/1251]	eta 0:02:58 lr 0.000957	time 2.2908 (2.1979)	loss 3.9728 (4.0760)	grad_norm 1.1524 (1.1444)	
[2022-01-18 18:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1180/1251]	eta 0:02:36 lr 0.000957	time 3.5977 (2.1992)	loss 3.0475 (4.0744)	grad_norm 1.1613 (1.1449)	
[2022-01-18 18:59:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1190/1251]	eta 0:02:14 lr 0.000957	time 1.9562 (2.1984)	loss 4.3455 (4.0769)	grad_norm 1.2690 (1.1447)	
[2022-01-18 18:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1200/1251]	eta 0:01:52 lr 0.000957	time 2.0704 (2.1970)	loss 4.2696 (4.0780)	grad_norm 0.9993 (1.1449)	
[2022-01-18 18:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1210/1251]	eta 0:01:30 lr 0.000957	time 2.2415 (2.1970)	loss 4.0963 (4.0756)	grad_norm 1.3387 (1.1447)	
[2022-01-18 19:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1220/1251]	eta 0:01:08 lr 0.000957	time 4.1003 (2.1991)	loss 4.0147 (4.0734)	grad_norm 0.9045 (1.1443)	
[2022-01-18 19:00:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1230/1251]	eta 0:00:46 lr 0.000957	time 1.5420 (2.1996)	loss 4.1268 (4.0726)	grad_norm 1.1326 (1.1450)	
[2022-01-18 19:00:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1240/1251]	eta 0:00:24 lr 0.000957	time 1.3593 (2.1983)	loss 3.4425 (4.0723)	grad_norm 1.4103 (1.1456)	
[2022-01-18 19:01:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [39/300][1250/1251]	eta 0:00:02 lr 0.000957	time 1.1751 (2.1929)	loss 3.0795 (4.0689)	grad_norm 1.0714 (1.1452)	
[2022-01-18 19:01:08 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 39 training takes 0:45:43
[2022-01-18 19:01:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.610 (18.610)	Loss 1.3957 (1.3957)	Acc@1 67.871 (67.871)	Acc@5 88.281 (88.281)	
[2022-01-18 19:01:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.653 (3.495)	Loss 1.3314 (1.3678)	Acc@1 69.531 (68.430)	Acc@5 89.355 (89.311)	
[2022-01-18 19:02:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 2.035 (2.669)	Loss 1.4798 (1.3671)	Acc@1 66.602 (68.694)	Acc@5 87.891 (89.235)	
[2022-01-18 19:02:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.585 (2.282)	Loss 1.2882 (1.3697)	Acc@1 70.801 (68.564)	Acc@5 89.453 (89.157)	
[2022-01-18 19:02:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.243 (2.214)	Loss 1.4574 (1.3776)	Acc@1 65.234 (68.467)	Acc@5 88.379 (88.998)	
[2022-01-18 19:02:46 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 68.434 Acc@5 89.086
[2022-01-18 19:02:46 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 68.4%
[2022-01-18 19:02:46 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 68.43%
[2022-01-18 19:03:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][0/1251]	eta 7:13:58 lr 0.000957	time 20.8138 (20.8138)	loss 2.9756 (2.9756)	grad_norm 1.2812 (1.2812)	
[2022-01-18 19:03:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][10/1251]	eta 1:24:34 lr 0.000957	time 2.1778 (4.0890)	loss 4.0547 (3.9154)	grad_norm 0.9999 (1.1261)	
[2022-01-18 19:03:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][20/1251]	eta 1:03:46 lr 0.000957	time 2.0111 (3.1084)	loss 4.0878 (4.0191)	grad_norm 1.0377 (1.1275)	
[2022-01-18 19:04:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][30/1251]	eta 0:56:52 lr 0.000957	time 1.6620 (2.7944)	loss 3.6880 (4.1120)	grad_norm 1.3633 (1.1456)	
[2022-01-18 19:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][40/1251]	eta 0:54:17 lr 0.000957	time 3.7353 (2.6897)	loss 4.8543 (4.0952)	grad_norm 1.0872 (1.1328)	
[2022-01-18 19:05:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][50/1251]	eta 0:52:36 lr 0.000957	time 2.1395 (2.6281)	loss 3.3893 (4.0649)	grad_norm 1.1522 (1.1184)	
[2022-01-18 19:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][60/1251]	eta 0:50:36 lr 0.000957	time 2.3417 (2.5498)	loss 2.7827 (4.0465)	grad_norm 1.0075 (1.1036)	
[2022-01-18 19:05:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][70/1251]	eta 0:48:57 lr 0.000957	time 1.5377 (2.4873)	loss 4.0968 (3.9826)	grad_norm 0.9660 (1.0924)	
[2022-01-18 19:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][80/1251]	eta 0:48:03 lr 0.000957	time 3.7900 (2.4623)	loss 4.2443 (4.0110)	grad_norm 1.0835 (1.0898)	
[2022-01-18 19:06:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][90/1251]	eta 0:47:35 lr 0.000957	time 2.3932 (2.4594)	loss 4.2998 (3.9643)	grad_norm 1.0144 (1.0887)	
[2022-01-18 19:06:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][100/1251]	eta 0:46:38 lr 0.000957	time 1.9247 (2.4314)	loss 4.6283 (3.9710)	grad_norm 1.1115 (1.0924)	
[2022-01-18 19:07:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][110/1251]	eta 0:45:33 lr 0.000957	time 1.7264 (2.3956)	loss 2.9613 (3.9626)	grad_norm 1.1302 (1.0978)	
[2022-01-18 19:07:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][120/1251]	eta 0:44:53 lr 0.000957	time 3.4836 (2.3818)	loss 5.0576 (3.9797)	grad_norm 1.5222 (1.1078)	
[2022-01-18 19:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][130/1251]	eta 0:44:12 lr 0.000957	time 2.7208 (2.3662)	loss 3.6867 (3.9755)	grad_norm 1.2269 (1.1108)	
[2022-01-18 19:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][140/1251]	eta 0:43:26 lr 0.000957	time 2.0212 (2.3457)	loss 4.1822 (3.9711)	grad_norm 1.3263 (1.1094)	
[2022-01-18 19:08:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][150/1251]	eta 0:42:45 lr 0.000957	time 1.9216 (2.3298)	loss 4.3493 (3.9886)	grad_norm 1.2195 (1.1129)	
[2022-01-18 19:09:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][160/1251]	eta 0:42:13 lr 0.000957	time 2.9568 (2.3224)	loss 4.2855 (3.9833)	grad_norm 1.1077 (1.1152)	
[2022-01-18 19:09:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][170/1251]	eta 0:41:44 lr 0.000957	time 2.6468 (2.3165)	loss 4.3797 (3.9909)	grad_norm 1.3584 (1.1194)	
[2022-01-18 19:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][180/1251]	eta 0:41:08 lr 0.000957	time 1.7820 (2.3051)	loss 3.8403 (3.9893)	grad_norm 1.0918 (1.1193)	
[2022-01-18 19:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][190/1251]	eta 0:40:45 lr 0.000957	time 2.2151 (2.3053)	loss 3.9192 (3.9924)	grad_norm 1.1022 (1.1195)	
[2022-01-18 19:10:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][200/1251]	eta 0:40:14 lr 0.000957	time 2.1406 (2.2978)	loss 4.0534 (3.9911)	grad_norm 1.0933 (1.1198)	
[2022-01-18 19:10:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][210/1251]	eta 0:39:48 lr 0.000957	time 2.5349 (2.2942)	loss 3.3651 (3.9969)	grad_norm 1.1236 (1.1174)	
[2022-01-18 19:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][220/1251]	eta 0:39:19 lr 0.000957	time 2.4611 (2.2888)	loss 4.3835 (3.9962)	grad_norm 1.1557 (1.1187)	
[2022-01-18 19:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][230/1251]	eta 0:38:49 lr 0.000957	time 2.0678 (2.2820)	loss 4.3370 (4.0012)	grad_norm 1.1302 (1.1217)	
[2022-01-18 19:11:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][240/1251]	eta 0:38:22 lr 0.000957	time 1.6872 (2.2777)	loss 4.7539 (4.0080)	grad_norm 1.0046 (1.1242)	
[2022-01-18 19:12:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][250/1251]	eta 0:37:48 lr 0.000957	time 2.2525 (2.2662)	loss 4.2879 (4.0160)	grad_norm 0.9831 (1.1220)	
[2022-01-18 19:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][260/1251]	eta 0:37:14 lr 0.000957	time 1.8734 (2.2552)	loss 3.9777 (4.0129)	grad_norm 1.1315 (1.1246)	
[2022-01-18 19:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][270/1251]	eta 0:36:52 lr 0.000957	time 1.8417 (2.2550)	loss 3.5807 (4.0066)	grad_norm 1.0391 (1.1240)	
[2022-01-18 19:13:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][280/1251]	eta 0:36:30 lr 0.000957	time 1.9028 (2.2562)	loss 3.5729 (4.0010)	grad_norm 1.0121 (1.1247)	
[2022-01-18 19:13:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][290/1251]	eta 0:36:07 lr 0.000957	time 2.1193 (2.2554)	loss 4.7233 (4.0077)	grad_norm 1.1595 (1.1254)	
[2022-01-18 19:14:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][300/1251]	eta 0:35:42 lr 0.000957	time 1.5870 (2.2524)	loss 4.5707 (4.0115)	grad_norm 1.1750 (1.1260)	
[2022-01-18 19:14:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][310/1251]	eta 0:35:17 lr 0.000957	time 2.0422 (2.2499)	loss 4.9125 (4.0196)	grad_norm 1.0278 (1.1248)	
[2022-01-18 19:14:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][320/1251]	eta 0:34:50 lr 0.000957	time 2.5684 (2.2458)	loss 4.2417 (4.0052)	grad_norm 1.2266 (1.1247)	
[2022-01-18 19:15:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][330/1251]	eta 0:34:24 lr 0.000957	time 1.7199 (2.2416)	loss 4.4236 (4.0048)	grad_norm 1.0385 (1.1255)	
[2022-01-18 19:15:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][340/1251]	eta 0:33:59 lr 0.000957	time 2.0311 (2.2387)	loss 4.5278 (4.0161)	grad_norm 1.0189 (1.1251)	
[2022-01-18 19:15:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][350/1251]	eta 0:33:37 lr 0.000957	time 2.6085 (2.2388)	loss 3.5665 (4.0134)	grad_norm 1.0015 (1.1257)	
[2022-01-18 19:16:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][360/1251]	eta 0:33:15 lr 0.000957	time 2.8309 (2.2398)	loss 4.8602 (4.0270)	grad_norm 0.9966 (1.1275)	
[2022-01-18 19:16:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][370/1251]	eta 0:32:50 lr 0.000957	time 1.5762 (2.2370)	loss 3.8793 (4.0343)	grad_norm 1.4003 (1.1306)	
[2022-01-18 19:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][380/1251]	eta 0:32:29 lr 0.000957	time 2.0874 (2.2387)	loss 4.4737 (4.0403)	grad_norm 1.0662 (1.1300)	
[2022-01-18 19:17:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][390/1251]	eta 0:32:08 lr 0.000957	time 2.4611 (2.2399)	loss 4.4105 (4.0476)	grad_norm 1.2509 (1.1303)	
[2022-01-18 19:17:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][400/1251]	eta 0:31:44 lr 0.000957	time 2.0219 (2.2381)	loss 4.9109 (4.0550)	grad_norm 0.9060 (1.1312)	
[2022-01-18 19:18:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][410/1251]	eta 0:31:19 lr 0.000957	time 1.6435 (2.2353)	loss 4.6350 (4.0551)	grad_norm 1.4133 (1.1314)	
[2022-01-18 19:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][420/1251]	eta 0:30:53 lr 0.000956	time 1.6150 (2.2302)	loss 4.2911 (4.0597)	grad_norm 1.0213 (1.1292)	
[2022-01-18 19:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][430/1251]	eta 0:30:26 lr 0.000956	time 2.3447 (2.2253)	loss 4.8279 (4.0647)	grad_norm 1.1765 (1.1275)	
[2022-01-18 19:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][440/1251]	eta 0:30:03 lr 0.000956	time 2.0494 (2.2243)	loss 2.6688 (4.0671)	grad_norm 1.4210 (1.1301)	
[2022-01-18 19:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][450/1251]	eta 0:29:39 lr 0.000956	time 1.9502 (2.2222)	loss 3.3255 (4.0573)	grad_norm 1.1260 (1.1303)	
[2022-01-18 19:19:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][460/1251]	eta 0:29:15 lr 0.000956	time 1.8661 (2.2189)	loss 3.6870 (4.0590)	grad_norm 1.2813 (1.1323)	
[2022-01-18 19:20:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][470/1251]	eta 0:28:51 lr 0.000956	time 2.0867 (2.2165)	loss 3.1070 (4.0563)	grad_norm 1.3678 (1.1350)	
[2022-01-18 19:20:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][480/1251]	eta 0:28:28 lr 0.000956	time 2.1762 (2.2160)	loss 3.7809 (4.0587)	grad_norm 1.3826 (1.1348)	
[2022-01-18 19:20:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][490/1251]	eta 0:28:06 lr 0.000956	time 2.1317 (2.2158)	loss 4.1601 (4.0568)	grad_norm 1.0111 (1.1340)	
[2022-01-18 19:21:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][500/1251]	eta 0:27:42 lr 0.000956	time 2.2932 (2.2134)	loss 4.7024 (4.0616)	grad_norm 1.2905 (1.1339)	
[2022-01-18 19:21:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][510/1251]	eta 0:27:21 lr 0.000956	time 1.7789 (2.2156)	loss 4.3027 (4.0631)	grad_norm 1.1330 (1.1348)	
[2022-01-18 19:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][520/1251]	eta 0:27:00 lr 0.000956	time 1.6165 (2.2173)	loss 4.5948 (4.0644)	grad_norm 1.1100 (1.1334)	
[2022-01-18 19:22:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][530/1251]	eta 0:26:38 lr 0.000956	time 2.1452 (2.2176)	loss 4.3481 (4.0683)	grad_norm 1.0794 (1.1332)	
[2022-01-18 19:22:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][540/1251]	eta 0:26:16 lr 0.000956	time 2.2222 (2.2171)	loss 2.9920 (4.0681)	grad_norm 0.9479 (1.1334)	
[2022-01-18 19:23:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][550/1251]	eta 0:25:53 lr 0.000956	time 1.7213 (2.2157)	loss 4.3668 (4.0693)	grad_norm 1.0504 (1.1326)	
[2022-01-18 19:23:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][560/1251]	eta 0:25:29 lr 0.000956	time 1.5352 (2.2136)	loss 4.6700 (4.0644)	grad_norm 1.3929 (1.1345)	
[2022-01-18 19:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][570/1251]	eta 0:25:07 lr 0.000956	time 2.6189 (2.2139)	loss 4.5532 (4.0636)	grad_norm 1.0332 (1.1341)	
[2022-01-18 19:24:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][580/1251]	eta 0:24:44 lr 0.000956	time 2.1534 (2.2128)	loss 4.1547 (4.0576)	grad_norm 1.0243 (1.1337)	
[2022-01-18 19:24:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][590/1251]	eta 0:24:21 lr 0.000956	time 1.9872 (2.2118)	loss 3.6465 (4.0507)	grad_norm 1.5966 (1.1357)	
[2022-01-18 19:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][600/1251]	eta 0:23:59 lr 0.000956	time 1.7179 (2.2105)	loss 4.1957 (4.0531)	grad_norm 1.4858 (1.1386)	
[2022-01-18 19:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][610/1251]	eta 0:23:36 lr 0.000956	time 2.2374 (2.2093)	loss 3.8942 (4.0514)	grad_norm 1.2084 (1.1378)	
[2022-01-18 19:25:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][620/1251]	eta 0:23:14 lr 0.000956	time 2.5322 (2.2099)	loss 4.4113 (4.0493)	grad_norm 1.1399 (1.1383)	
[2022-01-18 19:26:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][630/1251]	eta 0:22:53 lr 0.000956	time 2.4714 (2.2117)	loss 4.9008 (4.0535)	grad_norm 1.3899 (1.1392)	
[2022-01-18 19:26:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][640/1251]	eta 0:22:30 lr 0.000956	time 1.5133 (2.2111)	loss 4.5572 (4.0521)	grad_norm 1.1324 (1.1387)	
[2022-01-18 19:26:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][650/1251]	eta 0:22:08 lr 0.000956	time 1.8333 (2.2098)	loss 4.3280 (4.0569)	grad_norm 0.9782 (1.1373)	
[2022-01-18 19:27:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][660/1251]	eta 0:21:44 lr 0.000956	time 2.1140 (2.2080)	loss 4.0100 (4.0586)	grad_norm 1.0057 (1.1366)	
[2022-01-18 19:27:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][670/1251]	eta 0:21:22 lr 0.000956	time 1.5461 (2.2073)	loss 4.7501 (4.0580)	grad_norm 1.1833 (1.1360)	
[2022-01-18 19:27:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][680/1251]	eta 0:21:00 lr 0.000956	time 1.7123 (2.2070)	loss 3.3813 (4.0609)	grad_norm 1.2140 (1.1361)	
[2022-01-18 19:28:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][690/1251]	eta 0:20:38 lr 0.000956	time 2.0028 (2.2072)	loss 4.2789 (4.0639)	grad_norm 0.9698 (1.1360)	
[2022-01-18 19:28:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][700/1251]	eta 0:20:16 lr 0.000956	time 2.2012 (2.2083)	loss 4.1439 (4.0663)	grad_norm 1.6992 (1.1354)	
[2022-01-18 19:28:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][710/1251]	eta 0:19:54 lr 0.000956	time 2.1420 (2.2075)	loss 3.5000 (4.0618)	grad_norm 1.0523 (1.1361)	
[2022-01-18 19:29:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][720/1251]	eta 0:19:30 lr 0.000956	time 2.1080 (2.2053)	loss 4.4287 (4.0600)	grad_norm 1.1995 (1.1347)	
[2022-01-18 19:29:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][730/1251]	eta 0:19:08 lr 0.000956	time 2.1843 (2.2050)	loss 3.8549 (4.0595)	grad_norm 1.2904 (1.1339)	
[2022-01-18 19:30:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][740/1251]	eta 0:18:46 lr 0.000956	time 1.9028 (2.2051)	loss 4.4805 (4.0545)	grad_norm 0.8786 (1.1352)	
[2022-01-18 19:30:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][750/1251]	eta 0:18:24 lr 0.000956	time 2.2263 (2.2041)	loss 4.3169 (4.0517)	grad_norm 1.0965 (1.1354)	
[2022-01-18 19:30:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][760/1251]	eta 0:18:02 lr 0.000956	time 2.1552 (2.2044)	loss 2.7166 (4.0489)	grad_norm 1.0493 (1.1368)	
[2022-01-18 19:31:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][770/1251]	eta 0:17:40 lr 0.000956	time 1.9274 (2.2048)	loss 4.1063 (4.0505)	grad_norm 1.0814 (1.1374)	
[2022-01-18 19:31:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][780/1251]	eta 0:17:18 lr 0.000956	time 1.9054 (2.2042)	loss 4.6829 (4.0481)	grad_norm 1.0705 (1.1392)	
[2022-01-18 19:31:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][790/1251]	eta 0:16:55 lr 0.000956	time 2.2458 (2.2030)	loss 4.1720 (4.0504)	grad_norm 0.9927 (1.1385)	
[2022-01-18 19:32:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][800/1251]	eta 0:16:32 lr 0.000956	time 1.7976 (2.2015)	loss 3.4491 (4.0508)	grad_norm 1.0588 (1.1380)	
[2022-01-18 19:32:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][810/1251]	eta 0:16:11 lr 0.000956	time 2.2119 (2.2019)	loss 4.6593 (4.0530)	grad_norm 1.0651 (1.1384)	
[2022-01-18 19:32:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][820/1251]	eta 0:15:49 lr 0.000956	time 2.2100 (2.2039)	loss 4.5045 (4.0544)	grad_norm 1.0921 (1.1383)	
[2022-01-18 19:33:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][830/1251]	eta 0:15:28 lr 0.000956	time 2.1723 (2.2043)	loss 4.4266 (4.0574)	grad_norm 1.2014 (1.1376)	
[2022-01-18 19:33:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][840/1251]	eta 0:15:05 lr 0.000956	time 1.9666 (2.2031)	loss 4.5524 (4.0603)	grad_norm 1.4089 (1.1374)	
[2022-01-18 19:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][850/1251]	eta 0:14:42 lr 0.000956	time 1.8775 (2.2017)	loss 2.9771 (4.0597)	grad_norm 1.3931 (1.1382)	
[2022-01-18 19:34:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][860/1251]	eta 0:14:20 lr 0.000956	time 2.5425 (2.2012)	loss 3.4471 (4.0629)	grad_norm 1.1915 (1.1380)	
[2022-01-18 19:34:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][870/1251]	eta 0:13:57 lr 0.000956	time 1.9036 (2.1992)	loss 5.0066 (4.0632)	grad_norm 1.1167 (1.1382)	
[2022-01-18 19:35:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][880/1251]	eta 0:13:35 lr 0.000956	time 2.1963 (2.1969)	loss 4.2155 (4.0661)	grad_norm 1.0103 (1.1399)	
[2022-01-18 19:35:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][890/1251]	eta 0:13:12 lr 0.000956	time 1.7518 (2.1961)	loss 3.7176 (4.0649)	grad_norm 1.1793 (1.1394)	
[2022-01-18 19:35:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][900/1251]	eta 0:12:51 lr 0.000956	time 2.4188 (2.1967)	loss 4.2238 (4.0645)	grad_norm 1.0185 (1.1392)	
[2022-01-18 19:36:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][910/1251]	eta 0:12:29 lr 0.000956	time 1.8729 (2.1970)	loss 3.6309 (4.0653)	grad_norm 1.1574 (1.1389)	
[2022-01-18 19:36:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][920/1251]	eta 0:12:07 lr 0.000956	time 1.8512 (2.1983)	loss 3.9614 (4.0655)	grad_norm 1.1148 (1.1379)	
[2022-01-18 19:36:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][930/1251]	eta 0:11:46 lr 0.000956	time 1.5135 (2.2007)	loss 4.8723 (4.0653)	grad_norm 1.2291 (1.1373)	
[2022-01-18 19:37:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][940/1251]	eta 0:11:24 lr 0.000956	time 2.1176 (2.2012)	loss 4.2013 (4.0653)	grad_norm 0.9810 (1.1372)	
[2022-01-18 19:37:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][950/1251]	eta 0:11:02 lr 0.000956	time 2.8185 (2.2018)	loss 4.3602 (4.0609)	grad_norm 1.0255 (1.1370)	
[2022-01-18 19:38:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][960/1251]	eta 0:10:40 lr 0.000956	time 2.0704 (2.2004)	loss 4.4512 (4.0588)	grad_norm 1.0084 (1.1364)	
[2022-01-18 19:38:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][970/1251]	eta 0:10:18 lr 0.000956	time 1.7806 (2.2000)	loss 4.1858 (4.0579)	grad_norm 1.0716 (1.1364)	
[2022-01-18 19:38:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][980/1251]	eta 0:09:56 lr 0.000956	time 2.4442 (2.1996)	loss 3.4618 (4.0585)	grad_norm 1.0543 (1.1359)	
[2022-01-18 19:39:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][990/1251]	eta 0:09:33 lr 0.000956	time 2.2022 (2.1977)	loss 3.9595 (4.0578)	grad_norm 1.1921 (1.1357)	
[2022-01-18 19:39:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1000/1251]	eta 0:09:11 lr 0.000956	time 2.3219 (2.1971)	loss 4.1639 (4.0607)	grad_norm 1.0842 (1.1352)	
[2022-01-18 19:39:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1010/1251]	eta 0:08:49 lr 0.000955	time 2.2022 (2.1964)	loss 3.0805 (4.0599)	grad_norm 1.0689 (1.1355)	
[2022-01-18 19:40:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1020/1251]	eta 0:08:27 lr 0.000955	time 2.2119 (2.1965)	loss 3.9080 (4.0610)	grad_norm 1.0504 (1.1350)	
[2022-01-18 19:40:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1030/1251]	eta 0:08:05 lr 0.000955	time 2.2190 (2.1966)	loss 4.7036 (4.0589)	grad_norm 1.0695 (1.1355)	
[2022-01-18 19:40:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1040/1251]	eta 0:07:43 lr 0.000955	time 1.4732 (2.1974)	loss 4.5768 (4.0589)	grad_norm 1.6299 (1.1355)	
[2022-01-18 19:41:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1050/1251]	eta 0:07:21 lr 0.000955	time 3.3850 (2.1984)	loss 4.3291 (4.0600)	grad_norm 1.3828 (1.1357)	
[2022-01-18 19:41:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1060/1251]	eta 0:06:59 lr 0.000955	time 2.0560 (2.1975)	loss 4.2447 (4.0602)	grad_norm 1.3513 (1.1355)	
[2022-01-18 19:41:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1070/1251]	eta 0:06:37 lr 0.000955	time 2.2145 (2.1958)	loss 4.8853 (4.0600)	grad_norm 1.3964 (1.1354)	
[2022-01-18 19:42:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1080/1251]	eta 0:06:15 lr 0.000955	time 2.2741 (2.1945)	loss 4.4903 (4.0606)	grad_norm 1.4412 (1.1358)	
[2022-01-18 19:42:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1090/1251]	eta 0:05:53 lr 0.000955	time 2.7418 (2.1939)	loss 2.9222 (4.0560)	grad_norm 1.1770 (1.1356)	
[2022-01-18 19:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1100/1251]	eta 0:05:31 lr 0.000955	time 1.9090 (2.1931)	loss 4.1412 (4.0537)	grad_norm 1.1172 (1.1344)	
[2022-01-18 19:43:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1110/1251]	eta 0:05:09 lr 0.000955	time 2.4711 (2.1940)	loss 3.7796 (4.0528)	grad_norm 1.2792 (1.1337)	
[2022-01-18 19:43:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1120/1251]	eta 0:04:47 lr 0.000955	time 2.5366 (2.1968)	loss 4.4294 (4.0534)	grad_norm 1.1493 (1.1347)	
[2022-01-18 19:44:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1130/1251]	eta 0:04:25 lr 0.000955	time 2.5300 (2.1977)	loss 4.4201 (4.0552)	grad_norm 0.9382 (1.1348)	
[2022-01-18 19:44:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1140/1251]	eta 0:04:03 lr 0.000955	time 1.8737 (2.1965)	loss 4.1331 (4.0531)	grad_norm 0.9530 (1.1356)	
[2022-01-18 19:44:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1150/1251]	eta 0:03:41 lr 0.000955	time 2.1192 (2.1941)	loss 3.9897 (4.0538)	grad_norm 0.9969 (1.1350)	
[2022-01-18 19:45:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1160/1251]	eta 0:03:19 lr 0.000955	time 2.3065 (2.1932)	loss 4.4229 (4.0539)	grad_norm 1.2584 (1.1348)	
[2022-01-18 19:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1170/1251]	eta 0:02:57 lr 0.000955	time 3.5287 (2.1941)	loss 3.0547 (4.0511)	grad_norm 1.0309 (1.1346)	
[2022-01-18 19:45:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1180/1251]	eta 0:02:35 lr 0.000955	time 2.2698 (2.1951)	loss 2.7718 (4.0483)	grad_norm 1.2008 (1.1343)	
[2022-01-18 19:46:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1190/1251]	eta 0:02:13 lr 0.000955	time 1.6107 (2.1942)	loss 3.2876 (4.0452)	grad_norm 1.0300 (1.1348)	
[2022-01-18 19:46:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1200/1251]	eta 0:01:51 lr 0.000955	time 2.2269 (2.1944)	loss 4.7762 (4.0437)	grad_norm 0.9584 (1.1344)	
[2022-01-18 19:47:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1210/1251]	eta 0:01:29 lr 0.000955	time 3.0726 (2.1946)	loss 4.5655 (4.0401)	grad_norm 1.0527 (1.1344)	
[2022-01-18 19:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1220/1251]	eta 0:01:08 lr 0.000955	time 2.2883 (2.1946)	loss 4.1034 (4.0401)	grad_norm 1.0838 (1.1337)	
[2022-01-18 19:47:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1230/1251]	eta 0:00:46 lr 0.000955	time 1.5581 (2.1942)	loss 2.9391 (4.0400)	grad_norm 0.9306 (1.1330)	
[2022-01-18 19:48:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1240/1251]	eta 0:00:24 lr 0.000955	time 1.7376 (2.1931)	loss 4.3911 (4.0403)	grad_norm 1.1419 (1.1326)	
[2022-01-18 19:48:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [40/300][1250/1251]	eta 0:00:02 lr 0.000955	time 1.3489 (2.1877)	loss 4.0228 (4.0405)	grad_norm 1.1404 (1.1327)	
[2022-01-18 19:48:24 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 40 training takes 0:45:37
[2022-01-18 19:48:24 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_40 saving......
[2022-01-18 19:48:35 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_40 saved !!!
[2022-01-18 19:48:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 11.586 (11.586)	Loss 1.4743 (1.4743)	Acc@1 66.211 (66.211)	Acc@5 86.816 (86.816)	
[2022-01-18 19:49:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.837 (2.527)	Loss 1.4014 (1.3427)	Acc@1 66.895 (68.608)	Acc@5 88.477 (89.551)	
[2022-01-18 19:49:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.578 (2.093)	Loss 1.3565 (1.3531)	Acc@1 68.457 (68.694)	Acc@5 88.574 (89.160)	
[2022-01-18 19:49:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.013 (2.018)	Loss 1.3100 (1.3547)	Acc@1 68.164 (68.621)	Acc@5 89.746 (89.176)	
[2022-01-18 19:49:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.386 (1.936)	Loss 1.3980 (1.3474)	Acc@1 67.773 (68.683)	Acc@5 88.672 (89.194)	
[2022-01-18 19:50:01 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 68.608 Acc@5 89.218
[2022-01-18 19:50:01 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 68.6%
[2022-01-18 19:50:01 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 68.61%
[2022-01-18 19:50:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][0/1251]	eta 7:24:13 lr 0.000955	time 21.3059 (21.3059)	loss 4.4778 (4.4778)	grad_norm 0.9830 (0.9830)	
[2022-01-18 19:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][10/1251]	eta 1:29:10 lr 0.000955	time 2.2488 (4.3118)	loss 2.7976 (4.1066)	grad_norm 1.0932 (1.1470)	
[2022-01-18 19:51:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][20/1251]	eta 1:05:06 lr 0.000955	time 1.3200 (3.1732)	loss 4.2062 (4.0310)	grad_norm 1.1458 (1.1445)	
[2022-01-18 19:51:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][30/1251]	eta 0:58:22 lr 0.000955	time 1.8174 (2.8683)	loss 4.4972 (3.8570)	grad_norm 1.0995 (1.1982)	
[2022-01-18 19:51:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][40/1251]	eta 0:55:15 lr 0.000955	time 3.7129 (2.7381)	loss 4.5911 (3.9259)	grad_norm 1.0147 (1.2291)	
[2022-01-18 19:52:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][50/1251]	eta 0:52:51 lr 0.000955	time 2.8407 (2.6403)	loss 4.5473 (3.9824)	grad_norm 1.4211 (1.2158)	
[2022-01-18 19:52:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][60/1251]	eta 0:50:47 lr 0.000955	time 1.3243 (2.5592)	loss 3.5145 (3.9973)	grad_norm 1.2383 (1.1930)	
[2022-01-18 19:52:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][70/1251]	eta 0:48:59 lr 0.000955	time 2.3167 (2.4894)	loss 3.9032 (4.0406)	grad_norm 1.1830 (1.1862)	
[2022-01-18 19:53:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][80/1251]	eta 0:47:56 lr 0.000955	time 2.9817 (2.4566)	loss 4.1988 (4.0341)	grad_norm 1.2621 (1.1795)	
[2022-01-18 19:53:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][90/1251]	eta 0:47:06 lr 0.000955	time 3.4145 (2.4343)	loss 4.7869 (4.0100)	grad_norm 1.2756 (1.1824)	
[2022-01-18 19:54:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][100/1251]	eta 0:46:18 lr 0.000955	time 2.2291 (2.4144)	loss 4.0315 (4.0230)	grad_norm 1.1773 (1.1925)	
[2022-01-18 19:54:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][110/1251]	eta 0:45:41 lr 0.000955	time 2.7570 (2.4024)	loss 4.2012 (4.0210)	grad_norm 1.0755 (1.1806)	
[2022-01-18 19:54:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][120/1251]	eta 0:45:02 lr 0.000955	time 2.5252 (2.3898)	loss 4.4276 (4.0223)	grad_norm 1.1749 (1.1686)	
[2022-01-18 19:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][130/1251]	eta 0:44:15 lr 0.000955	time 2.4334 (2.3685)	loss 4.4255 (4.0372)	grad_norm 0.9487 (1.1678)	
[2022-01-18 19:55:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][140/1251]	eta 0:43:26 lr 0.000955	time 2.1844 (2.3464)	loss 3.4549 (4.0446)	grad_norm 1.3565 (1.1650)	
[2022-01-18 19:55:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][150/1251]	eta 0:42:37 lr 0.000955	time 1.9400 (2.3227)	loss 4.0114 (4.0511)	grad_norm 1.1215 (1.1677)	
[2022-01-18 19:56:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][160/1251]	eta 0:42:00 lr 0.000955	time 1.7897 (2.3101)	loss 3.2947 (4.0534)	grad_norm 1.0925 (1.1630)	
[2022-01-18 19:56:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][170/1251]	eta 0:41:33 lr 0.000955	time 2.4231 (2.3063)	loss 4.1184 (4.0483)	grad_norm 1.3006 (1.1616)	
[2022-01-18 19:56:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][180/1251]	eta 0:41:09 lr 0.000955	time 2.8071 (2.3054)	loss 3.4801 (4.0463)	grad_norm 1.3662 (1.1556)	
[2022-01-18 19:57:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][190/1251]	eta 0:40:41 lr 0.000955	time 1.5757 (2.3012)	loss 3.2393 (4.0262)	grad_norm 1.0638 (1.1586)	
[2022-01-18 19:57:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][200/1251]	eta 0:40:20 lr 0.000955	time 2.0996 (2.3029)	loss 4.3743 (4.0216)	grad_norm 1.0660 (1.1598)	
[2022-01-18 19:58:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][210/1251]	eta 0:39:51 lr 0.000955	time 1.8466 (2.2973)	loss 3.9069 (4.0303)	grad_norm 1.0765 (1.1586)	
[2022-01-18 19:58:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][220/1251]	eta 0:39:31 lr 0.000955	time 2.9388 (2.2998)	loss 4.7106 (4.0350)	grad_norm 1.4221 (1.1602)	
[2022-01-18 19:58:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][230/1251]	eta 0:38:51 lr 0.000955	time 1.9469 (2.2832)	loss 4.4265 (4.0366)	grad_norm 1.1154 (1.1572)	
[2022-01-18 19:59:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][240/1251]	eta 0:38:12 lr 0.000955	time 1.7441 (2.2678)	loss 3.5482 (4.0470)	grad_norm 1.1389 (1.1563)	
[2022-01-18 19:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][250/1251]	eta 0:37:41 lr 0.000955	time 2.0929 (2.2591)	loss 4.9391 (4.0584)	grad_norm 1.1456 (1.1563)	
[2022-01-18 19:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][260/1251]	eta 0:37:16 lr 0.000955	time 1.8709 (2.2564)	loss 4.7392 (4.0475)	grad_norm 1.2969 (1.1629)	
[2022-01-18 20:00:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][270/1251]	eta 0:36:49 lr 0.000955	time 1.7411 (2.2522)	loss 4.0386 (4.0524)	grad_norm 0.9710 (1.1589)	
[2022-01-18 20:00:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][280/1251]	eta 0:36:29 lr 0.000955	time 2.1828 (2.2550)	loss 3.9716 (4.0377)	grad_norm 1.2231 (1.1566)	
[2022-01-18 20:00:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][290/1251]	eta 0:36:11 lr 0.000955	time 2.6206 (2.2597)	loss 4.4051 (4.0405)	grad_norm 1.5344 (1.1567)	
[2022-01-18 20:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][300/1251]	eta 0:35:54 lr 0.000955	time 2.9187 (2.2651)	loss 4.7723 (4.0414)	grad_norm 1.2019 (1.1551)	
[2022-01-18 20:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][310/1251]	eta 0:35:31 lr 0.000955	time 1.5531 (2.2654)	loss 3.0203 (4.0410)	grad_norm 0.9784 (1.1524)	
[2022-01-18 20:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][320/1251]	eta 0:35:05 lr 0.000955	time 1.7493 (2.2619)	loss 4.4574 (4.0505)	grad_norm 1.0727 (1.1502)	
[2022-01-18 20:02:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][330/1251]	eta 0:34:38 lr 0.000955	time 1.9015 (2.2566)	loss 3.0467 (4.0511)	grad_norm 1.1503 (1.1483)	
[2022-01-18 20:02:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][340/1251]	eta 0:34:08 lr 0.000954	time 1.6153 (2.2490)	loss 3.9890 (4.0462)	grad_norm 0.9614 (1.1490)	
[2022-01-18 20:03:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][350/1251]	eta 0:33:40 lr 0.000954	time 2.2077 (2.2421)	loss 4.7211 (4.0582)	grad_norm 1.0540 (1.1458)	
[2022-01-18 20:03:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][360/1251]	eta 0:33:19 lr 0.000954	time 5.0560 (2.2438)	loss 4.0229 (4.0528)	grad_norm 0.9141 (1.1441)	
[2022-01-18 20:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][370/1251]	eta 0:33:02 lr 0.000954	time 2.8374 (2.2499)	loss 4.3010 (4.0475)	grad_norm 1.2733 (1.1437)	
[2022-01-18 20:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][380/1251]	eta 0:32:35 lr 0.000954	time 1.9445 (2.2449)	loss 4.2437 (4.0518)	grad_norm 1.0343 (1.1421)	
[2022-01-18 20:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][390/1251]	eta 0:32:08 lr 0.000954	time 1.9145 (2.2396)	loss 4.9319 (4.0553)	grad_norm 1.3394 (1.1446)	
[2022-01-18 20:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][400/1251]	eta 0:31:44 lr 0.000954	time 2.6474 (2.2375)	loss 4.7487 (4.0541)	grad_norm 1.0309 (1.1456)	
[2022-01-18 20:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][410/1251]	eta 0:31:18 lr 0.000954	time 1.9013 (2.2340)	loss 4.6238 (4.0477)	grad_norm 1.4185 (1.1473)	
[2022-01-18 20:05:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][420/1251]	eta 0:30:56 lr 0.000954	time 1.9982 (2.2339)	loss 3.1831 (4.0460)	grad_norm 1.0989 (1.1483)	
[2022-01-18 20:06:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][430/1251]	eta 0:30:33 lr 0.000954	time 2.1420 (2.2337)	loss 3.1233 (4.0413)	grad_norm 1.0869 (1.1463)	
[2022-01-18 20:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][440/1251]	eta 0:30:14 lr 0.000954	time 3.7285 (2.2368)	loss 4.1846 (4.0375)	grad_norm 1.7414 (1.1477)	
[2022-01-18 20:06:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][450/1251]	eta 0:29:49 lr 0.000954	time 2.0036 (2.2338)	loss 3.7957 (4.0402)	grad_norm 1.1035 (1.1485)	
[2022-01-18 20:07:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][460/1251]	eta 0:29:25 lr 0.000954	time 2.1908 (2.2325)	loss 4.3777 (4.0437)	grad_norm 1.3130 (1.1471)	
[2022-01-18 20:07:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][470/1251]	eta 0:29:00 lr 0.000954	time 1.8401 (2.2288)	loss 2.6308 (4.0377)	grad_norm 1.1768 (1.1473)	
[2022-01-18 20:07:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][480/1251]	eta 0:28:36 lr 0.000954	time 2.5192 (2.2264)	loss 4.3030 (4.0313)	grad_norm 1.0860 (1.1457)	
[2022-01-18 20:08:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][490/1251]	eta 0:28:12 lr 0.000954	time 1.8919 (2.2236)	loss 4.1461 (4.0311)	grad_norm 1.1331 (1.1452)	
[2022-01-18 20:08:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][500/1251]	eta 0:27:50 lr 0.000954	time 2.0989 (2.2249)	loss 2.8934 (4.0308)	grad_norm 0.9434 (1.1455)	
[2022-01-18 20:09:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][510/1251]	eta 0:27:30 lr 0.000954	time 2.4408 (2.2273)	loss 4.2058 (4.0297)	grad_norm 1.1421 (1.1451)	
[2022-01-18 20:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][520/1251]	eta 0:27:11 lr 0.000954	time 3.2511 (2.2312)	loss 3.9993 (4.0315)	grad_norm 1.1203 (1.1459)	
[2022-01-18 20:09:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][530/1251]	eta 0:26:48 lr 0.000954	time 2.2250 (2.2314)	loss 4.1682 (4.0283)	grad_norm 0.9553 (1.1449)	
[2022-01-18 20:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][540/1251]	eta 0:26:24 lr 0.000954	time 1.9266 (2.2285)	loss 3.2412 (4.0278)	grad_norm 1.0689 (1.1450)	
[2022-01-18 20:10:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][550/1251]	eta 0:26:00 lr 0.000954	time 1.9406 (2.2258)	loss 3.2885 (4.0273)	grad_norm 1.1172 (1.1434)	
[2022-01-18 20:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][560/1251]	eta 0:25:36 lr 0.000954	time 2.3130 (2.2229)	loss 4.6188 (4.0275)	grad_norm 1.1194 (1.1432)	
[2022-01-18 20:11:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][570/1251]	eta 0:25:10 lr 0.000954	time 1.9623 (2.2181)	loss 4.1022 (4.0273)	grad_norm 1.0873 (1.1428)	
[2022-01-18 20:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][580/1251]	eta 0:24:47 lr 0.000954	time 1.9358 (2.2169)	loss 3.5370 (4.0254)	grad_norm 1.0214 (1.1431)	
[2022-01-18 20:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][590/1251]	eta 0:24:24 lr 0.000954	time 1.9565 (2.2163)	loss 3.6050 (4.0233)	grad_norm 1.2001 (1.1438)	
[2022-01-18 20:12:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][600/1251]	eta 0:24:03 lr 0.000954	time 2.5471 (2.2172)	loss 4.5503 (4.0279)	grad_norm 0.9903 (1.1445)	
[2022-01-18 20:12:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][610/1251]	eta 0:23:41 lr 0.000954	time 2.3930 (2.2171)	loss 3.0754 (4.0294)	grad_norm 1.1902 (1.1436)	
[2022-01-18 20:12:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][620/1251]	eta 0:23:18 lr 0.000954	time 2.2185 (2.2171)	loss 4.2573 (4.0313)	grad_norm 0.9360 (1.1430)	
[2022-01-18 20:13:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][630/1251]	eta 0:22:56 lr 0.000954	time 1.8889 (2.2168)	loss 4.6234 (4.0339)	grad_norm 1.5197 (1.1420)	
[2022-01-18 20:13:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][640/1251]	eta 0:22:35 lr 0.000954	time 3.1029 (2.2177)	loss 3.5547 (4.0362)	grad_norm 1.2311 (1.1412)	
[2022-01-18 20:14:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][650/1251]	eta 0:22:11 lr 0.000954	time 1.9099 (2.2151)	loss 4.1003 (4.0381)	grad_norm 1.0210 (1.1407)	
[2022-01-18 20:14:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][660/1251]	eta 0:21:48 lr 0.000954	time 2.1485 (2.2143)	loss 4.8488 (4.0365)	grad_norm 0.9907 (1.1397)	
[2022-01-18 20:14:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][670/1251]	eta 0:21:27 lr 0.000954	time 2.7840 (2.2151)	loss 4.3288 (4.0375)	grad_norm 1.3101 (1.1392)	
[2022-01-18 20:15:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][680/1251]	eta 0:21:04 lr 0.000954	time 2.5541 (2.2152)	loss 4.4727 (4.0375)	grad_norm 1.1553 (1.1399)	
[2022-01-18 20:15:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][690/1251]	eta 0:20:41 lr 0.000954	time 1.9534 (2.2135)	loss 4.3314 (4.0378)	grad_norm 1.1107 (1.1398)	
[2022-01-18 20:15:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][700/1251]	eta 0:20:19 lr 0.000954	time 2.1821 (2.2139)	loss 3.9619 (4.0349)	grad_norm 1.3243 (1.1389)	
[2022-01-18 20:16:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][710/1251]	eta 0:19:57 lr 0.000954	time 2.1925 (2.2128)	loss 3.5215 (4.0352)	grad_norm 1.0379 (1.1389)	
[2022-01-18 20:16:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][720/1251]	eta 0:19:33 lr 0.000954	time 1.8345 (2.2105)	loss 4.8151 (4.0380)	grad_norm 1.1860 (1.1392)	
[2022-01-18 20:16:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][730/1251]	eta 0:19:11 lr 0.000954	time 2.3601 (2.2106)	loss 3.6182 (4.0369)	grad_norm 1.4389 (1.1400)	
[2022-01-18 20:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][740/1251]	eta 0:18:49 lr 0.000954	time 2.0928 (2.2101)	loss 2.9127 (4.0358)	grad_norm 1.1616 (1.1400)	
[2022-01-18 20:17:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][750/1251]	eta 0:18:26 lr 0.000954	time 2.2913 (2.2093)	loss 4.6244 (4.0389)	grad_norm 1.3053 (1.1406)	
[2022-01-18 20:18:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][760/1251]	eta 0:18:04 lr 0.000954	time 2.0544 (2.2080)	loss 4.3959 (4.0351)	grad_norm 1.1155 (1.1415)	
[2022-01-18 20:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][770/1251]	eta 0:17:42 lr 0.000954	time 3.4476 (2.2090)	loss 4.3083 (4.0352)	grad_norm 1.1133 (1.1419)	
[2022-01-18 20:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][780/1251]	eta 0:17:21 lr 0.000954	time 2.8299 (2.2103)	loss 4.3500 (4.0337)	grad_norm 1.0633 (1.1431)	
[2022-01-18 20:19:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][790/1251]	eta 0:16:57 lr 0.000954	time 1.7053 (2.2081)	loss 3.4038 (4.0362)	grad_norm 0.9756 (1.1429)	
[2022-01-18 20:19:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][800/1251]	eta 0:16:34 lr 0.000954	time 1.6792 (2.2059)	loss 3.3016 (4.0341)	grad_norm 0.9879 (1.1425)	
[2022-01-18 20:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][810/1251]	eta 0:16:12 lr 0.000954	time 2.2317 (2.2050)	loss 4.0857 (4.0352)	grad_norm 1.2047 (1.1423)	
[2022-01-18 20:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][820/1251]	eta 0:15:50 lr 0.000954	time 2.8494 (2.2048)	loss 4.0002 (4.0357)	grad_norm 1.1798 (1.1419)	
[2022-01-18 20:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][830/1251]	eta 0:15:27 lr 0.000954	time 2.1744 (2.2037)	loss 4.2220 (4.0370)	grad_norm 1.0793 (1.1408)	
[2022-01-18 20:20:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][840/1251]	eta 0:15:05 lr 0.000954	time 1.7738 (2.2033)	loss 3.8901 (4.0411)	grad_norm 1.0660 (1.1406)	
[2022-01-18 20:21:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][850/1251]	eta 0:14:43 lr 0.000954	time 2.7660 (2.2042)	loss 4.0758 (4.0428)	grad_norm 1.2396 (1.1412)	
[2022-01-18 20:21:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][860/1251]	eta 0:14:21 lr 0.000954	time 2.1832 (2.2045)	loss 4.1017 (4.0436)	grad_norm 1.2105 (1.1419)	
[2022-01-18 20:22:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][870/1251]	eta 0:13:59 lr 0.000954	time 2.1818 (2.2025)	loss 4.3687 (4.0458)	grad_norm 1.0601 (1.1399)	
[2022-01-18 20:22:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][880/1251]	eta 0:13:36 lr 0.000954	time 1.9099 (2.2012)	loss 4.3803 (4.0457)	grad_norm 1.1568 (1.1389)	
[2022-01-18 20:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][890/1251]	eta 0:13:15 lr 0.000954	time 1.9727 (2.2025)	loss 4.2563 (4.0460)	grad_norm 1.2426 (1.1392)	
[2022-01-18 20:23:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][900/1251]	eta 0:12:53 lr 0.000954	time 1.8866 (2.2034)	loss 3.8111 (4.0446)	grad_norm 1.1124 (1.1394)	
[2022-01-18 20:23:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][910/1251]	eta 0:12:31 lr 0.000953	time 1.6684 (2.2024)	loss 3.7494 (4.0437)	grad_norm 1.2355 (1.1392)	
[2022-01-18 20:23:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][920/1251]	eta 0:12:08 lr 0.000953	time 1.9196 (2.2014)	loss 4.3054 (4.0419)	grad_norm 1.2812 (1.1384)	
[2022-01-18 20:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][930/1251]	eta 0:11:46 lr 0.000953	time 2.1199 (2.2018)	loss 4.4085 (4.0432)	grad_norm 1.2208 (1.1394)	
[2022-01-18 20:24:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][940/1251]	eta 0:11:25 lr 0.000953	time 2.1970 (2.2033)	loss 4.7167 (4.0465)	grad_norm 1.4574 (1.1403)	
[2022-01-18 20:24:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][950/1251]	eta 0:11:02 lr 0.000953	time 1.9815 (2.2026)	loss 4.3685 (4.0456)	grad_norm 0.9653 (1.1400)	
[2022-01-18 20:25:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][960/1251]	eta 0:10:40 lr 0.000953	time 2.1764 (2.2016)	loss 4.2201 (4.0489)	grad_norm 0.9266 (1.1389)	
[2022-01-18 20:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][970/1251]	eta 0:10:18 lr 0.000953	time 1.8823 (2.2001)	loss 4.1081 (4.0475)	grad_norm 0.9111 (1.1382)	
[2022-01-18 20:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][980/1251]	eta 0:09:55 lr 0.000953	time 2.2517 (2.1986)	loss 2.8663 (4.0461)	grad_norm 1.3413 (1.1379)	
[2022-01-18 20:26:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][990/1251]	eta 0:09:33 lr 0.000953	time 2.2286 (2.1966)	loss 3.6288 (4.0445)	grad_norm 1.3726 (1.1382)	
[2022-01-18 20:26:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1000/1251]	eta 0:09:11 lr 0.000953	time 2.7212 (2.1968)	loss 3.5919 (4.0433)	grad_norm 1.0312 (1.1384)	
[2022-01-18 20:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1010/1251]	eta 0:08:49 lr 0.000953	time 1.8153 (2.1965)	loss 4.3528 (4.0435)	grad_norm 1.0370 (1.1378)	
[2022-01-18 20:27:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1020/1251]	eta 0:08:27 lr 0.000953	time 1.9403 (2.1966)	loss 4.6489 (4.0461)	grad_norm 1.2347 (1.1385)	
[2022-01-18 20:27:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1030/1251]	eta 0:08:05 lr 0.000953	time 2.3406 (2.1975)	loss 4.3450 (4.0461)	grad_norm 1.2402 (1.1385)	
[2022-01-18 20:28:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1040/1251]	eta 0:07:43 lr 0.000953	time 3.0710 (2.1984)	loss 4.5995 (4.0468)	grad_norm 1.1934 (1.1384)	
[2022-01-18 20:28:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1050/1251]	eta 0:07:21 lr 0.000953	time 2.1369 (2.1989)	loss 2.8100 (4.0446)	grad_norm 1.1906 (1.1381)	
[2022-01-18 20:28:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1060/1251]	eta 0:07:00 lr 0.000953	time 1.7019 (2.1995)	loss 3.3531 (4.0414)	grad_norm 1.1727 (1.1377)	
[2022-01-18 20:29:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1070/1251]	eta 0:06:38 lr 0.000953	time 3.2125 (2.2000)	loss 4.1597 (4.0411)	grad_norm 1.2142 (1.1371)	
[2022-01-18 20:29:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1080/1251]	eta 0:06:16 lr 0.000953	time 2.8682 (2.2003)	loss 4.3421 (4.0432)	grad_norm 1.0233 (1.1364)	
[2022-01-18 20:30:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1090/1251]	eta 0:05:54 lr 0.000953	time 1.6008 (2.2000)	loss 4.0228 (4.0436)	grad_norm 1.3955 (1.1367)	
[2022-01-18 20:30:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1100/1251]	eta 0:05:32 lr 0.000953	time 1.8751 (2.1997)	loss 3.4590 (4.0454)	grad_norm 0.9902 (1.1360)	
[2022-01-18 20:30:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1110/1251]	eta 0:05:10 lr 0.000953	time 3.5950 (2.2004)	loss 3.2038 (4.0444)	grad_norm 1.1934 (1.1353)	
[2022-01-18 20:31:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1120/1251]	eta 0:04:48 lr 0.000953	time 2.3005 (2.1989)	loss 3.6389 (4.0467)	grad_norm 1.1697 (1.1352)	
[2022-01-18 20:31:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1130/1251]	eta 0:04:25 lr 0.000953	time 1.6581 (2.1977)	loss 4.2279 (4.0478)	grad_norm 1.4070 (1.1352)	
[2022-01-18 20:31:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1140/1251]	eta 0:04:03 lr 0.000953	time 2.4121 (2.1972)	loss 3.9206 (4.0466)	grad_norm 1.0448 (1.1345)	
[2022-01-18 20:32:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1150/1251]	eta 0:03:41 lr 0.000953	time 2.1834 (2.1963)	loss 4.2257 (4.0480)	grad_norm 0.9333 (1.1339)	
[2022-01-18 20:32:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1160/1251]	eta 0:03:19 lr 0.000953	time 2.2821 (2.1948)	loss 4.5088 (4.0478)	grad_norm 1.2763 (1.1340)	
[2022-01-18 20:32:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1170/1251]	eta 0:02:57 lr 0.000953	time 2.1164 (2.1942)	loss 4.5202 (4.0487)	grad_norm 1.0297 (1.1337)	
[2022-01-18 20:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1180/1251]	eta 0:02:35 lr 0.000953	time 2.5125 (2.1949)	loss 4.5043 (4.0506)	grad_norm 1.4158 (1.1337)	
[2022-01-18 20:33:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1190/1251]	eta 0:02:13 lr 0.000953	time 2.4045 (2.1966)	loss 4.3276 (4.0490)	grad_norm 1.0941 (1.1330)	
[2022-01-18 20:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1200/1251]	eta 0:01:52 lr 0.000953	time 2.2341 (2.1966)	loss 3.2251 (4.0468)	grad_norm 1.0578 (1.1330)	
[2022-01-18 20:34:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1210/1251]	eta 0:01:30 lr 0.000953	time 1.9554 (2.1962)	loss 2.9413 (4.0455)	grad_norm 1.1541 (1.1330)	
[2022-01-18 20:34:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1220/1251]	eta 0:01:08 lr 0.000953	time 2.7546 (2.1964)	loss 4.8030 (4.0452)	grad_norm 1.1359 (1.1325)	
[2022-01-18 20:35:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1230/1251]	eta 0:00:46 lr 0.000953	time 2.7651 (2.1965)	loss 3.9898 (4.0454)	grad_norm 1.1377 (1.1330)	
[2022-01-18 20:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1240/1251]	eta 0:00:24 lr 0.000953	time 1.6804 (2.1952)	loss 3.4989 (4.0464)	grad_norm 1.2497 (1.1329)	
[2022-01-18 20:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [41/300][1250/1251]	eta 0:00:02 lr 0.000953	time 1.1560 (2.1893)	loss 4.2292 (4.0470)	grad_norm 1.1844 (1.1326)	
[2022-01-18 20:35:41 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 41 training takes 0:45:39
[2022-01-18 20:35:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.155 (18.155)	Loss 1.3978 (1.3978)	Acc@1 68.457 (68.457)	Acc@5 88.574 (88.574)	
[2022-01-18 20:36:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.205 (3.313)	Loss 1.3412 (1.3635)	Acc@1 67.969 (68.297)	Acc@5 90.723 (89.178)	
[2022-01-18 20:36:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.587 (2.586)	Loss 1.3467 (1.3675)	Acc@1 70.508 (68.606)	Acc@5 88.770 (89.100)	
[2022-01-18 20:36:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.644 (2.350)	Loss 1.2839 (1.3579)	Acc@1 70.312 (68.668)	Acc@5 90.723 (89.327)	
[2022-01-18 20:37:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.885 (2.187)	Loss 1.3678 (1.3555)	Acc@1 67.871 (68.667)	Acc@5 89.062 (89.332)	
[2022-01-18 20:37:18 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 68.746 Acc@5 89.286
[2022-01-18 20:37:18 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 68.7%
[2022-01-18 20:37:18 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 68.75%
[2022-01-18 20:37:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][0/1251]	eta 7:18:05 lr 0.000953	time 21.0112 (21.0112)	loss 3.9848 (3.9848)	grad_norm 1.1907 (1.1907)	
[2022-01-18 20:38:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][10/1251]	eta 1:25:11 lr 0.000953	time 3.1036 (4.1188)	loss 4.4352 (4.2233)	grad_norm 1.1753 (1.0659)	
[2022-01-18 20:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][20/1251]	eta 1:05:49 lr 0.000953	time 2.0597 (3.2087)	loss 4.3842 (4.1843)	grad_norm 1.2625 (1.1705)	
[2022-01-18 20:38:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][30/1251]	eta 0:58:19 lr 0.000953	time 1.5076 (2.8658)	loss 4.7462 (4.1665)	grad_norm 1.1216 (1.1582)	
[2022-01-18 20:39:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][40/1251]	eta 0:55:42 lr 0.000953	time 4.0170 (2.7600)	loss 4.1882 (4.1917)	grad_norm 1.1263 (1.1659)	
[2022-01-18 20:39:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][50/1251]	eta 0:53:34 lr 0.000953	time 2.4285 (2.6767)	loss 3.4097 (4.1715)	grad_norm 1.1829 (1.1598)	
[2022-01-18 20:39:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][60/1251]	eta 0:51:28 lr 0.000953	time 1.9527 (2.5933)	loss 4.2013 (4.1220)	grad_norm 1.0353 (1.1407)	
[2022-01-18 20:40:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][70/1251]	eta 0:49:54 lr 0.000953	time 1.5612 (2.5353)	loss 4.3546 (4.1271)	grad_norm 1.0948 (1.1607)	
[2022-01-18 20:40:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][80/1251]	eta 0:48:46 lr 0.000953	time 2.8785 (2.4990)	loss 3.3890 (4.1036)	grad_norm 1.1499 (1.1536)	
[2022-01-18 20:41:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][90/1251]	eta 0:47:51 lr 0.000953	time 2.1898 (2.4737)	loss 3.7543 (4.0651)	grad_norm 1.1634 (1.1499)	
[2022-01-18 20:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][100/1251]	eta 0:46:56 lr 0.000953	time 2.6165 (2.4468)	loss 4.7661 (4.0829)	grad_norm 0.9908 (1.1488)	
[2022-01-18 20:41:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][110/1251]	eta 0:45:47 lr 0.000953	time 1.7244 (2.4080)	loss 4.4471 (4.0560)	grad_norm 1.0515 (1.1398)	
[2022-01-18 20:42:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][120/1251]	eta 0:44:57 lr 0.000953	time 2.3029 (2.3846)	loss 2.9922 (4.0150)	grad_norm 1.2997 (1.1446)	
[2022-01-18 20:42:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][130/1251]	eta 0:44:10 lr 0.000953	time 1.5978 (2.3640)	loss 2.8773 (4.0017)	grad_norm 1.4634 (1.1514)	
[2022-01-18 20:42:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][140/1251]	eta 0:43:34 lr 0.000953	time 3.3547 (2.3532)	loss 2.9521 (3.9992)	grad_norm 1.0274 (1.1454)	
[2022-01-18 20:43:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][150/1251]	eta 0:43:00 lr 0.000953	time 1.9457 (2.3438)	loss 4.1046 (4.0004)	grad_norm 1.0078 (1.1438)	
[2022-01-18 20:43:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][160/1251]	eta 0:42:31 lr 0.000953	time 2.5830 (2.3390)	loss 4.5017 (4.0100)	grad_norm 0.9724 (1.1438)	
[2022-01-18 20:43:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][170/1251]	eta 0:41:56 lr 0.000953	time 1.6661 (2.3277)	loss 3.6826 (4.0037)	grad_norm 1.3237 (1.1465)	
[2022-01-18 20:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][180/1251]	eta 0:41:24 lr 0.000953	time 2.6205 (2.3200)	loss 4.1759 (4.0198)	grad_norm 0.9809 (1.1454)	
[2022-01-18 20:44:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][190/1251]	eta 0:40:48 lr 0.000953	time 1.9296 (2.3077)	loss 4.3729 (4.0168)	grad_norm 1.0662 (1.1426)	
[2022-01-18 20:45:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][200/1251]	eta 0:40:16 lr 0.000953	time 2.3604 (2.2988)	loss 3.3216 (4.0075)	grad_norm 0.9520 (1.1438)	
[2022-01-18 20:45:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][210/1251]	eta 0:39:47 lr 0.000953	time 2.3068 (2.2934)	loss 3.8711 (4.0147)	grad_norm 1.0578 (1.1396)	
[2022-01-18 20:45:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][220/1251]	eta 0:39:23 lr 0.000953	time 2.1735 (2.2920)	loss 3.3638 (4.0247)	grad_norm 1.2097 (1.1437)	
[2022-01-18 20:46:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][230/1251]	eta 0:38:52 lr 0.000952	time 1.9391 (2.2847)	loss 3.5966 (4.0151)	grad_norm 1.3224 (1.1446)	
[2022-01-18 20:46:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][240/1251]	eta 0:38:30 lr 0.000952	time 2.9531 (2.2852)	loss 3.7552 (4.0014)	grad_norm 1.1342 (1.1464)	
[2022-01-18 20:46:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][250/1251]	eta 0:38:02 lr 0.000952	time 2.2192 (2.2802)	loss 3.8652 (3.9992)	grad_norm 1.1378 (1.1492)	
[2022-01-18 20:47:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][260/1251]	eta 0:37:33 lr 0.000952	time 2.1656 (2.2738)	loss 3.2712 (3.9952)	grad_norm 0.9260 (1.1470)	
[2022-01-18 20:47:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][270/1251]	eta 0:37:02 lr 0.000952	time 2.0385 (2.2651)	loss 4.1571 (4.0021)	grad_norm 0.9952 (1.1485)	
[2022-01-18 20:47:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][280/1251]	eta 0:36:36 lr 0.000952	time 2.8902 (2.2624)	loss 4.2509 (3.9961)	grad_norm 1.0138 (1.1499)	
[2022-01-18 20:48:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][290/1251]	eta 0:36:07 lr 0.000952	time 2.1595 (2.2551)	loss 4.5467 (3.9981)	grad_norm 1.1801 (1.1472)	
[2022-01-18 20:48:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][300/1251]	eta 0:35:44 lr 0.000952	time 2.4018 (2.2553)	loss 4.2237 (3.9902)	grad_norm 0.9827 (1.1471)	
[2022-01-18 20:48:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][310/1251]	eta 0:35:18 lr 0.000952	time 2.0088 (2.2515)	loss 5.0068 (3.9906)	grad_norm 1.1963 (1.1464)	
[2022-01-18 20:49:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][320/1251]	eta 0:34:55 lr 0.000952	time 3.1781 (2.2512)	loss 4.3060 (3.9896)	grad_norm 1.1421 (1.1440)	
[2022-01-18 20:49:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][330/1251]	eta 0:34:32 lr 0.000952	time 2.4523 (2.2508)	loss 3.4251 (3.9903)	grad_norm 0.9167 (1.1422)	
[2022-01-18 20:50:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][340/1251]	eta 0:34:09 lr 0.000952	time 1.8704 (2.2492)	loss 4.2439 (3.9945)	grad_norm 1.0974 (1.1408)	
[2022-01-18 20:50:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][350/1251]	eta 0:33:42 lr 0.000952	time 1.5944 (2.2450)	loss 4.0471 (3.9957)	grad_norm 1.0989 (1.1398)	
[2022-01-18 20:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][360/1251]	eta 0:33:23 lr 0.000952	time 3.5943 (2.2488)	loss 4.1755 (3.9879)	grad_norm 0.8976 (1.1401)	
[2022-01-18 20:51:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][370/1251]	eta 0:33:03 lr 0.000952	time 3.0382 (2.2520)	loss 4.2798 (3.9797)	grad_norm 1.2000 (1.1431)	
[2022-01-18 20:51:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][380/1251]	eta 0:32:40 lr 0.000952	time 1.5648 (2.2506)	loss 4.1682 (3.9834)	grad_norm 0.9947 (1.1442)	
[2022-01-18 20:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][390/1251]	eta 0:32:13 lr 0.000952	time 1.7732 (2.2451)	loss 3.7686 (3.9843)	grad_norm 1.1258 (1.1417)	
[2022-01-18 20:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][400/1251]	eta 0:31:48 lr 0.000952	time 3.1265 (2.2426)	loss 3.7361 (3.9881)	grad_norm 1.2640 (1.1400)	
[2022-01-18 20:52:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][410/1251]	eta 0:31:21 lr 0.000952	time 2.3124 (2.2369)	loss 4.4593 (3.9868)	grad_norm 1.3128 (1.1413)	
[2022-01-18 20:52:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][420/1251]	eta 0:30:52 lr 0.000952	time 1.9302 (2.2298)	loss 2.6994 (3.9826)	grad_norm 0.8919 (1.1414)	
[2022-01-18 20:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][430/1251]	eta 0:30:27 lr 0.000952	time 1.8974 (2.2258)	loss 4.4679 (3.9807)	grad_norm 1.0016 (1.1418)	
[2022-01-18 20:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][440/1251]	eta 0:30:03 lr 0.000952	time 2.2545 (2.2233)	loss 4.1713 (3.9871)	grad_norm 1.1103 (1.1413)	
[2022-01-18 20:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][450/1251]	eta 0:29:38 lr 0.000952	time 2.0841 (2.2209)	loss 4.4778 (3.9878)	grad_norm 1.0583 (1.1409)	
[2022-01-18 20:54:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][460/1251]	eta 0:29:16 lr 0.000952	time 2.0061 (2.2200)	loss 4.6970 (3.9901)	grad_norm 1.0781 (1.1408)	
[2022-01-18 20:54:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][470/1251]	eta 0:28:51 lr 0.000952	time 2.1833 (2.2175)	loss 3.6586 (3.9896)	grad_norm 1.0044 (1.1394)	
[2022-01-18 20:55:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][480/1251]	eta 0:28:28 lr 0.000952	time 1.8961 (2.2159)	loss 4.1345 (3.9912)	grad_norm 1.0447 (1.1366)	
[2022-01-18 20:55:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][490/1251]	eta 0:28:10 lr 0.000952	time 2.0111 (2.2215)	loss 4.5498 (3.9948)	grad_norm 1.2798 (1.1378)	
[2022-01-18 20:55:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][500/1251]	eta 0:27:51 lr 0.000952	time 2.7580 (2.2258)	loss 3.8017 (3.9957)	grad_norm 1.1629 (1.1391)	
[2022-01-18 20:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][510/1251]	eta 0:27:32 lr 0.000952	time 2.3109 (2.2302)	loss 2.9702 (3.9929)	grad_norm 1.0847 (1.1383)	
[2022-01-18 20:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][520/1251]	eta 0:27:10 lr 0.000952	time 2.0977 (2.2309)	loss 4.3911 (3.9984)	grad_norm 1.2045 (1.1386)	
[2022-01-18 20:57:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][530/1251]	eta 0:26:48 lr 0.000952	time 1.8592 (2.2310)	loss 4.6270 (3.9941)	grad_norm 1.1797 (1.1382)	
[2022-01-18 20:57:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][540/1251]	eta 0:26:24 lr 0.000952	time 1.6039 (2.2280)	loss 3.7258 (3.9942)	grad_norm 1.0065 (1.1409)	
[2022-01-18 20:57:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][550/1251]	eta 0:25:58 lr 0.000952	time 1.6740 (2.2237)	loss 3.0815 (3.9902)	grad_norm 1.2162 (1.1419)	
[2022-01-18 20:58:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][560/1251]	eta 0:25:33 lr 0.000952	time 1.9552 (2.2187)	loss 4.4033 (3.9934)	grad_norm 1.0425 (1.1415)	
[2022-01-18 20:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][570/1251]	eta 0:25:07 lr 0.000952	time 2.1649 (2.2138)	loss 4.7299 (3.9933)	grad_norm 1.0648 (1.1418)	
[2022-01-18 20:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][580/1251]	eta 0:24:43 lr 0.000952	time 2.1654 (2.2106)	loss 4.5217 (3.9995)	grad_norm 0.9928 (1.1418)	
[2022-01-18 20:59:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][590/1251]	eta 0:24:21 lr 0.000952	time 2.4415 (2.2115)	loss 4.1270 (3.9974)	grad_norm 1.1576 (1.1415)	
[2022-01-18 20:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][600/1251]	eta 0:24:01 lr 0.000952	time 2.0283 (2.2141)	loss 3.5588 (3.9964)	grad_norm 1.3389 (1.1415)	
[2022-01-18 20:59:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][610/1251]	eta 0:23:40 lr 0.000952	time 2.4433 (2.2156)	loss 4.4342 (3.9987)	grad_norm 1.0496 (1.1423)	
[2022-01-18 21:00:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][620/1251]	eta 0:23:19 lr 0.000952	time 3.0907 (2.2182)	loss 4.6162 (4.0041)	grad_norm 1.2193 (1.1423)	
[2022-01-18 21:00:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][630/1251]	eta 0:22:58 lr 0.000952	time 1.5022 (2.2194)	loss 4.4552 (3.9983)	grad_norm 1.2925 (1.1423)	
[2022-01-18 21:01:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][640/1251]	eta 0:22:36 lr 0.000952	time 2.3936 (2.2205)	loss 4.2166 (3.9960)	grad_norm 1.1307 (1.1420)	
[2022-01-18 21:01:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][650/1251]	eta 0:22:13 lr 0.000952	time 1.9262 (2.2181)	loss 4.5781 (3.9981)	grad_norm 0.9545 (1.1419)	
[2022-01-18 21:01:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][660/1251]	eta 0:21:50 lr 0.000952	time 2.4636 (2.2176)	loss 4.4039 (3.9941)	grad_norm 1.1023 (1.1422)	
[2022-01-18 21:02:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][670/1251]	eta 0:21:27 lr 0.000952	time 1.8423 (2.2160)	loss 2.9505 (3.9908)	grad_norm 1.2154 (1.1425)	
[2022-01-18 21:02:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][680/1251]	eta 0:21:04 lr 0.000952	time 1.6952 (2.2144)	loss 4.5077 (3.9920)	grad_norm 1.4640 (1.1418)	
[2022-01-18 21:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][690/1251]	eta 0:20:42 lr 0.000952	time 2.2782 (2.2140)	loss 4.2869 (3.9918)	grad_norm 1.1228 (1.1412)	
[2022-01-18 21:03:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][700/1251]	eta 0:20:19 lr 0.000952	time 2.3769 (2.2128)	loss 3.5250 (3.9904)	grad_norm 0.9864 (1.1405)	
[2022-01-18 21:03:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][710/1251]	eta 0:19:56 lr 0.000952	time 2.4632 (2.2118)	loss 3.1237 (3.9895)	grad_norm 1.1493 (1.1392)	
[2022-01-18 21:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][720/1251]	eta 0:19:35 lr 0.000952	time 2.0409 (2.2133)	loss 3.1678 (3.9879)	grad_norm 1.3014 (1.1399)	
[2022-01-18 21:04:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][730/1251]	eta 0:19:13 lr 0.000952	time 2.3441 (2.2133)	loss 3.6243 (3.9871)	grad_norm 1.0046 (1.1397)	
[2022-01-18 21:04:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][740/1251]	eta 0:18:50 lr 0.000952	time 2.5561 (2.2116)	loss 3.3357 (3.9911)	grad_norm 0.9950 (1.1397)	
[2022-01-18 21:04:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][750/1251]	eta 0:18:26 lr 0.000952	time 1.9172 (2.2089)	loss 3.3604 (3.9896)	grad_norm 1.3873 (1.1397)	
[2022-01-18 21:05:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][760/1251]	eta 0:18:03 lr 0.000952	time 1.8427 (2.2073)	loss 3.9671 (3.9904)	grad_norm 1.1178 (1.1408)	
[2022-01-18 21:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][770/1251]	eta 0:17:41 lr 0.000952	time 2.1205 (2.2063)	loss 4.4333 (3.9909)	grad_norm 1.0105 (1.1402)	
[2022-01-18 21:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][780/1251]	eta 0:17:19 lr 0.000952	time 3.0878 (2.2071)	loss 3.4081 (3.9871)	grad_norm 0.9549 (1.1408)	
[2022-01-18 21:06:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][790/1251]	eta 0:16:57 lr 0.000951	time 1.6755 (2.2071)	loss 3.1366 (3.9855)	grad_norm 0.9448 (1.1404)	
[2022-01-18 21:06:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][800/1251]	eta 0:16:34 lr 0.000951	time 1.5277 (2.2060)	loss 3.3462 (3.9862)	grad_norm 1.0461 (1.1397)	
[2022-01-18 21:07:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][810/1251]	eta 0:16:13 lr 0.000951	time 2.8974 (2.2066)	loss 4.5068 (3.9866)	grad_norm 1.1948 (1.1387)	
[2022-01-18 21:07:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][820/1251]	eta 0:15:50 lr 0.000951	time 2.3319 (2.2061)	loss 4.4258 (3.9887)	grad_norm 1.4000 (1.1397)	
[2022-01-18 21:07:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][830/1251]	eta 0:15:28 lr 0.000951	time 1.8637 (2.2056)	loss 4.2380 (3.9891)	grad_norm 1.1430 (1.1393)	
[2022-01-18 21:08:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][840/1251]	eta 0:15:06 lr 0.000951	time 1.5492 (2.2051)	loss 3.0085 (3.9853)	grad_norm 1.0749 (1.1396)	
[2022-01-18 21:08:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][850/1251]	eta 0:14:44 lr 0.000951	time 2.9835 (2.2060)	loss 3.9059 (3.9839)	grad_norm 0.9944 (1.1395)	
[2022-01-18 21:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][860/1251]	eta 0:14:22 lr 0.000951	time 2.9900 (2.2064)	loss 3.4657 (3.9842)	grad_norm 1.1207 (1.1397)	
[2022-01-18 21:09:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][870/1251]	eta 0:14:00 lr 0.000951	time 1.8365 (2.2061)	loss 4.2477 (3.9856)	grad_norm 0.9645 (1.1392)	
[2022-01-18 21:09:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][880/1251]	eta 0:13:38 lr 0.000951	time 1.8076 (2.2059)	loss 3.8287 (3.9858)	grad_norm 1.4547 (1.1402)	
[2022-01-18 21:10:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][890/1251]	eta 0:13:16 lr 0.000951	time 2.9594 (2.2055)	loss 3.7314 (3.9849)	grad_norm 1.3012 (1.1410)	
[2022-01-18 21:10:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][900/1251]	eta 0:12:54 lr 0.000951	time 2.8200 (2.2058)	loss 4.7315 (3.9845)	grad_norm 1.0627 (1.1419)	
[2022-01-18 21:10:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][910/1251]	eta 0:12:32 lr 0.000951	time 2.1803 (2.2058)	loss 4.1178 (3.9852)	grad_norm 1.6361 (1.1429)	
[2022-01-18 21:11:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][920/1251]	eta 0:12:10 lr 0.000951	time 1.5349 (2.2063)	loss 4.7483 (3.9821)	grad_norm 1.3120 (1.1443)	
[2022-01-18 21:11:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][930/1251]	eta 0:11:47 lr 0.000951	time 1.9073 (2.2055)	loss 4.0271 (3.9835)	grad_norm 1.2849 (1.1438)	
[2022-01-18 21:11:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][940/1251]	eta 0:11:26 lr 0.000951	time 3.4977 (2.2059)	loss 4.0523 (3.9814)	grad_norm 1.3824 (1.1440)	
[2022-01-18 21:12:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][950/1251]	eta 0:11:03 lr 0.000951	time 1.9247 (2.2048)	loss 4.8932 (3.9850)	grad_norm 1.1029 (1.1450)	
[2022-01-18 21:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][960/1251]	eta 0:10:41 lr 0.000951	time 1.8966 (2.2054)	loss 4.5304 (3.9866)	grad_norm 1.0580 (1.1448)	
[2022-01-18 21:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][970/1251]	eta 0:10:19 lr 0.000951	time 1.6164 (2.2058)	loss 4.2111 (3.9867)	grad_norm 1.0973 (1.1441)	
[2022-01-18 21:13:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][980/1251]	eta 0:09:58 lr 0.000951	time 3.1927 (2.2075)	loss 4.4518 (3.9890)	grad_norm 1.2036 (1.1437)	
[2022-01-18 21:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][990/1251]	eta 0:09:35 lr 0.000951	time 1.6897 (2.2059)	loss 4.9745 (3.9922)	grad_norm 1.1653 (1.1434)	
[2022-01-18 21:14:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1000/1251]	eta 0:09:12 lr 0.000951	time 1.5559 (2.2031)	loss 3.3057 (3.9914)	grad_norm 0.9719 (1.1432)	
[2022-01-18 21:14:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1010/1251]	eta 0:08:50 lr 0.000951	time 1.9271 (2.2007)	loss 4.6971 (3.9934)	grad_norm 1.2020 (1.1425)	
[2022-01-18 21:14:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1020/1251]	eta 0:08:28 lr 0.000951	time 2.3382 (2.1994)	loss 4.2904 (3.9922)	grad_norm 1.0203 (1.1435)	
[2022-01-18 21:15:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1030/1251]	eta 0:08:06 lr 0.000951	time 2.3078 (2.1998)	loss 3.5583 (3.9930)	grad_norm 1.2590 (1.1433)	
[2022-01-18 21:15:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1040/1251]	eta 0:07:44 lr 0.000951	time 2.5541 (2.1999)	loss 3.2627 (3.9931)	grad_norm 1.3988 (1.1434)	
[2022-01-18 21:15:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1050/1251]	eta 0:07:22 lr 0.000951	time 1.9526 (2.2006)	loss 4.4710 (3.9960)	grad_norm 1.1536 (1.1428)	
[2022-01-18 21:16:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1060/1251]	eta 0:07:00 lr 0.000951	time 3.0254 (2.2019)	loss 4.8872 (3.9975)	grad_norm 1.1514 (1.1419)	
[2022-01-18 21:16:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1070/1251]	eta 0:06:38 lr 0.000951	time 1.9881 (2.2028)	loss 3.8984 (3.9975)	grad_norm 0.9712 (1.1422)	
[2022-01-18 21:17:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1080/1251]	eta 0:06:16 lr 0.000951	time 1.8538 (2.2035)	loss 4.2087 (3.9958)	grad_norm 1.3094 (1.1421)	
[2022-01-18 21:17:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1090/1251]	eta 0:05:54 lr 0.000951	time 2.1059 (2.2044)	loss 4.0983 (3.9952)	grad_norm 1.2129 (1.1420)	
[2022-01-18 21:17:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1100/1251]	eta 0:05:32 lr 0.000951	time 1.6025 (2.2036)	loss 4.0304 (3.9923)	grad_norm 1.0689 (1.1425)	
[2022-01-18 21:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1110/1251]	eta 0:05:10 lr 0.000951	time 1.6764 (2.2009)	loss 4.0905 (3.9934)	grad_norm 1.0610 (1.1426)	
[2022-01-18 21:18:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1120/1251]	eta 0:04:48 lr 0.000951	time 1.8510 (2.2005)	loss 3.2383 (3.9904)	grad_norm 1.1580 (1.1424)	
[2022-01-18 21:18:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1130/1251]	eta 0:04:26 lr 0.000951	time 2.2003 (2.2001)	loss 3.5756 (3.9888)	grad_norm 1.0938 (1.1416)	
[2022-01-18 21:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1140/1251]	eta 0:04:04 lr 0.000951	time 2.2144 (2.2023)	loss 4.1241 (3.9891)	grad_norm 0.9714 (1.1412)	
[2022-01-18 21:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1150/1251]	eta 0:03:42 lr 0.000951	time 2.1265 (2.2024)	loss 4.2532 (3.9908)	grad_norm 1.1008 (1.1406)	
[2022-01-18 21:19:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1160/1251]	eta 0:03:20 lr 0.000951	time 2.2235 (2.2015)	loss 4.7039 (3.9920)	grad_norm 1.0533 (1.1407)	
[2022-01-18 21:20:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1170/1251]	eta 0:02:58 lr 0.000951	time 2.1919 (2.2008)	loss 3.2061 (3.9920)	grad_norm 1.0476 (1.1410)	
[2022-01-18 21:20:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1180/1251]	eta 0:02:36 lr 0.000951	time 2.0979 (2.2016)	loss 3.8345 (3.9921)	grad_norm 1.1081 (1.1414)	
[2022-01-18 21:21:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1190/1251]	eta 0:02:14 lr 0.000951	time 2.1931 (2.2020)	loss 4.2418 (3.9926)	grad_norm 1.0850 (1.1411)	
[2022-01-18 21:21:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1200/1251]	eta 0:01:52 lr 0.000951	time 2.0681 (2.2016)	loss 4.4923 (3.9929)	grad_norm 1.2767 (1.1410)	
[2022-01-18 21:21:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1210/1251]	eta 0:01:30 lr 0.000951	time 1.6540 (2.2010)	loss 3.7638 (3.9925)	grad_norm 1.0841 (1.1403)	
[2022-01-18 21:22:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1220/1251]	eta 0:01:08 lr 0.000951	time 1.8641 (2.2001)	loss 4.5253 (3.9931)	grad_norm 1.0610 (1.1400)	
[2022-01-18 21:22:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1230/1251]	eta 0:00:46 lr 0.000951	time 1.9759 (2.1985)	loss 3.7971 (3.9931)	grad_norm 1.1965 (1.1401)	
[2022-01-18 21:22:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1240/1251]	eta 0:00:24 lr 0.000951	time 1.8868 (2.1983)	loss 2.9228 (3.9929)	grad_norm 1.1006 (1.1399)	
[2022-01-18 21:23:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [42/300][1250/1251]	eta 0:00:02 lr 0.000951	time 1.1454 (2.1931)	loss 2.9952 (3.9914)	grad_norm 1.1605 (1.1394)	
[2022-01-18 21:23:02 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 42 training takes 0:45:43
[2022-01-18 21:23:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.790 (17.790)	Loss 1.3903 (1.3903)	Acc@1 69.434 (69.434)	Acc@5 88.477 (88.477)	
[2022-01-18 21:23:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.990 (3.382)	Loss 1.2411 (1.3468)	Acc@1 73.340 (69.309)	Acc@5 90.430 (89.293)	
[2022-01-18 21:23:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.281 (2.597)	Loss 1.4850 (1.3587)	Acc@1 66.406 (68.936)	Acc@5 86.719 (89.128)	
[2022-01-18 21:24:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.636 (2.253)	Loss 1.4400 (1.3634)	Acc@1 66.406 (68.870)	Acc@5 88.965 (89.097)	
[2022-01-18 21:24:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.547 (2.155)	Loss 1.3164 (1.3601)	Acc@1 71.094 (69.112)	Acc@5 89.551 (89.191)	
[2022-01-18 21:24:37 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 69.014 Acc@5 89.202
[2022-01-18 21:24:37 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 69.0%
[2022-01-18 21:24:37 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 69.01%
[2022-01-18 21:24:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][0/1251]	eta 7:32:04 lr 0.000951	time 21.6821 (21.6821)	loss 4.2512 (4.2512)	grad_norm 1.1508 (1.1508)	
[2022-01-18 21:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][10/1251]	eta 1:22:25 lr 0.000951	time 1.6661 (3.9850)	loss 4.5987 (4.0199)	grad_norm 0.9506 (1.1872)	
[2022-01-18 21:25:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][20/1251]	eta 1:06:05 lr 0.000951	time 1.9381 (3.2210)	loss 3.3275 (4.0076)	grad_norm 0.9893 (1.1751)	
[2022-01-18 21:26:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][30/1251]	eta 0:58:04 lr 0.000951	time 1.4975 (2.8542)	loss 4.4458 (4.1382)	grad_norm 1.1440 (1.1563)	
[2022-01-18 21:26:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][40/1251]	eta 0:55:58 lr 0.000951	time 3.9621 (2.7737)	loss 4.2028 (4.1099)	grad_norm 1.1777 (1.1500)	
[2022-01-18 21:26:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][50/1251]	eta 0:53:51 lr 0.000951	time 2.3107 (2.6909)	loss 3.5246 (4.1095)	grad_norm 1.2804 (1.1352)	
[2022-01-18 21:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][60/1251]	eta 0:51:36 lr 0.000951	time 1.5597 (2.6001)	loss 3.4545 (4.0839)	grad_norm 0.9896 (1.1322)	
[2022-01-18 21:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][70/1251]	eta 0:49:38 lr 0.000951	time 1.6891 (2.5222)	loss 3.8173 (4.0495)	grad_norm 1.3959 (1.1465)	
[2022-01-18 21:28:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][80/1251]	eta 0:48:42 lr 0.000951	time 4.7821 (2.4958)	loss 3.4987 (4.0490)	grad_norm 1.1853 (1.1422)	
[2022-01-18 21:28:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][90/1251]	eta 0:47:05 lr 0.000950	time 2.1221 (2.4338)	loss 4.3513 (4.0718)	grad_norm 0.8887 (1.1265)	
[2022-01-18 21:28:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][100/1251]	eta 0:45:57 lr 0.000950	time 1.5219 (2.3956)	loss 4.1221 (4.0667)	grad_norm 1.1920 (1.1232)	
[2022-01-18 21:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][110/1251]	eta 0:45:18 lr 0.000950	time 2.3173 (2.3824)	loss 4.1131 (4.0700)	grad_norm 1.1496 (1.1270)	
[2022-01-18 21:29:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][120/1251]	eta 0:45:10 lr 0.000950	time 3.6389 (2.3965)	loss 4.4575 (4.0574)	grad_norm 1.1152 (1.1239)	
[2022-01-18 21:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][130/1251]	eta 0:44:30 lr 0.000950	time 1.9501 (2.3822)	loss 4.4553 (4.0351)	grad_norm 1.3800 (1.1252)	
[2022-01-18 21:30:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][140/1251]	eta 0:43:57 lr 0.000950	time 1.8451 (2.3740)	loss 4.2583 (4.0294)	grad_norm 1.1907 (1.1223)	
[2022-01-18 21:30:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][150/1251]	eta 0:43:16 lr 0.000950	time 1.7998 (2.3582)	loss 4.0949 (4.0452)	grad_norm 1.1657 (1.1190)	
[2022-01-18 21:30:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][160/1251]	eta 0:42:44 lr 0.000950	time 3.3845 (2.3507)	loss 4.4149 (4.0460)	grad_norm 1.3003 (1.1207)	
[2022-01-18 21:31:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][170/1251]	eta 0:42:03 lr 0.000950	time 2.0689 (2.3348)	loss 3.7855 (4.0376)	grad_norm 1.4061 (1.1183)	
[2022-01-18 21:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][180/1251]	eta 0:41:35 lr 0.000950	time 1.8474 (2.3297)	loss 4.2238 (4.0211)	grad_norm 1.3231 (1.1180)	
[2022-01-18 21:32:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][190/1251]	eta 0:41:06 lr 0.000950	time 2.2563 (2.3244)	loss 4.4535 (4.0107)	grad_norm 1.3126 (1.1179)	
[2022-01-18 21:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][200/1251]	eta 0:40:32 lr 0.000950	time 2.5780 (2.3146)	loss 4.4398 (4.0149)	grad_norm 1.2201 (1.1258)	
[2022-01-18 21:32:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][210/1251]	eta 0:39:54 lr 0.000950	time 1.6409 (2.3001)	loss 4.5637 (4.0079)	grad_norm 1.1425 (1.1269)	
[2022-01-18 21:33:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][220/1251]	eta 0:39:22 lr 0.000950	time 1.8754 (2.2919)	loss 4.4431 (4.0114)	grad_norm 1.0276 (1.1240)	
[2022-01-18 21:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][230/1251]	eta 0:38:47 lr 0.000950	time 2.0899 (2.2797)	loss 4.4096 (4.0080)	grad_norm 1.1189 (1.1225)	
[2022-01-18 21:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][240/1251]	eta 0:38:19 lr 0.000950	time 1.8927 (2.2745)	loss 3.6614 (4.0221)	grad_norm 0.9297 (1.1197)	
[2022-01-18 21:34:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][250/1251]	eta 0:37:52 lr 0.000950	time 2.4782 (2.2705)	loss 3.2580 (4.0168)	grad_norm 1.2115 (1.1198)	
[2022-01-18 21:34:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][260/1251]	eta 0:37:30 lr 0.000950	time 2.8150 (2.2711)	loss 3.2351 (4.0167)	grad_norm 1.0964 (1.1194)	
[2022-01-18 21:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][270/1251]	eta 0:37:11 lr 0.000950	time 1.8551 (2.2745)	loss 3.3174 (4.0219)	grad_norm 0.8577 (1.1158)	
[2022-01-18 21:35:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][280/1251]	eta 0:36:44 lr 0.000950	time 1.9529 (2.2704)	loss 4.5447 (4.0203)	grad_norm 1.1554 (1.1136)	
[2022-01-18 21:35:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][290/1251]	eta 0:36:16 lr 0.000950	time 1.9306 (2.2651)	loss 3.7518 (4.0245)	grad_norm 0.9261 (1.1111)	
[2022-01-18 21:35:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][300/1251]	eta 0:35:51 lr 0.000950	time 2.2605 (2.2625)	loss 4.0792 (4.0349)	grad_norm 0.9558 (1.1087)	
[2022-01-18 21:36:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][310/1251]	eta 0:35:22 lr 0.000950	time 1.9792 (2.2560)	loss 3.7794 (4.0200)	grad_norm 1.1270 (1.1090)	
[2022-01-18 21:36:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][320/1251]	eta 0:34:57 lr 0.000950	time 2.0944 (2.2531)	loss 3.6594 (4.0189)	grad_norm 1.1807 (1.1065)	
[2022-01-18 21:37:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][330/1251]	eta 0:34:32 lr 0.000950	time 1.9214 (2.2507)	loss 4.2750 (4.0073)	grad_norm 1.1620 (1.1051)	
[2022-01-18 21:37:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][340/1251]	eta 0:34:12 lr 0.000950	time 2.3977 (2.2534)	loss 4.5826 (4.0045)	grad_norm 1.1881 (1.1054)	
[2022-01-18 21:37:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][350/1251]	eta 0:33:46 lr 0.000950	time 1.7645 (2.2495)	loss 3.6291 (4.0073)	grad_norm 1.0299 (1.1051)	
[2022-01-18 21:38:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][360/1251]	eta 0:33:21 lr 0.000950	time 2.5443 (2.2469)	loss 3.3204 (4.0053)	grad_norm 0.8749 (1.1060)	
[2022-01-18 21:38:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][370/1251]	eta 0:32:59 lr 0.000950	time 1.5954 (2.2464)	loss 4.0847 (4.0007)	grad_norm 1.0886 (1.1085)	
[2022-01-18 21:38:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][380/1251]	eta 0:32:36 lr 0.000950	time 1.7945 (2.2466)	loss 4.0166 (4.0003)	grad_norm 1.1323 (1.1106)	
[2022-01-18 21:39:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][390/1251]	eta 0:32:13 lr 0.000950	time 1.9334 (2.2461)	loss 4.3358 (4.0012)	grad_norm 1.2656 (1.1116)	
[2022-01-18 21:39:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][400/1251]	eta 0:31:49 lr 0.000950	time 2.1687 (2.2442)	loss 3.0634 (4.0060)	grad_norm 1.0529 (1.1112)	
[2022-01-18 21:39:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][410/1251]	eta 0:31:22 lr 0.000950	time 1.8723 (2.2385)	loss 3.7715 (4.0118)	grad_norm 1.1427 (1.1103)	
[2022-01-18 21:40:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][420/1251]	eta 0:30:56 lr 0.000950	time 2.2223 (2.2346)	loss 4.2094 (4.0082)	grad_norm 0.9231 (1.1104)	
[2022-01-18 21:40:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][430/1251]	eta 0:30:35 lr 0.000950	time 1.9509 (2.2355)	loss 4.0717 (4.0094)	grad_norm 1.0269 (1.1116)	
[2022-01-18 21:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][440/1251]	eta 0:30:13 lr 0.000950	time 1.7630 (2.2365)	loss 4.3617 (4.0110)	grad_norm 1.3286 (1.1115)	
[2022-01-18 21:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][450/1251]	eta 0:29:49 lr 0.000950	time 1.7531 (2.2345)	loss 4.6912 (4.0147)	grad_norm 1.2222 (1.1140)	
[2022-01-18 21:41:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][460/1251]	eta 0:29:26 lr 0.000950	time 1.5783 (2.2336)	loss 3.8062 (4.0131)	grad_norm 1.4778 (1.1166)	
[2022-01-18 21:42:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][470/1251]	eta 0:29:03 lr 0.000950	time 1.5556 (2.2324)	loss 4.1298 (4.0184)	grad_norm 1.0953 (1.1170)	
[2022-01-18 21:42:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][480/1251]	eta 0:28:40 lr 0.000950	time 2.1531 (2.2321)	loss 4.8052 (4.0197)	grad_norm 1.2563 (1.1165)	
[2022-01-18 21:42:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][490/1251]	eta 0:28:16 lr 0.000950	time 1.8498 (2.2290)	loss 4.9035 (4.0225)	grad_norm 1.0552 (1.1192)	
[2022-01-18 21:43:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][500/1251]	eta 0:27:52 lr 0.000950	time 2.1897 (2.2273)	loss 3.7947 (4.0186)	grad_norm 1.0419 (1.1214)	
[2022-01-18 21:43:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][510/1251]	eta 0:27:28 lr 0.000950	time 1.7659 (2.2241)	loss 4.5966 (4.0192)	grad_norm 1.0388 (1.1197)	
[2022-01-18 21:43:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][520/1251]	eta 0:27:04 lr 0.000950	time 2.4671 (2.2224)	loss 3.8057 (4.0214)	grad_norm 1.2071 (1.1199)	
[2022-01-18 21:44:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][530/1251]	eta 0:26:41 lr 0.000950	time 2.1882 (2.2214)	loss 4.1727 (4.0211)	grad_norm 1.2208 (1.1194)	
[2022-01-18 21:44:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][540/1251]	eta 0:26:19 lr 0.000950	time 2.1102 (2.2212)	loss 3.6810 (4.0202)	grad_norm 0.9848 (1.1206)	
[2022-01-18 21:45:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][550/1251]	eta 0:25:55 lr 0.000950	time 2.2055 (2.2189)	loss 4.3235 (4.0191)	grad_norm 1.1309 (1.1207)	
[2022-01-18 21:45:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][560/1251]	eta 0:25:34 lr 0.000950	time 2.5480 (2.2200)	loss 3.8906 (4.0102)	grad_norm 0.9571 (1.1204)	
[2022-01-18 21:45:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][570/1251]	eta 0:25:14 lr 0.000950	time 3.0431 (2.2242)	loss 4.2288 (4.0104)	grad_norm 1.2931 (1.1221)	
[2022-01-18 21:46:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][580/1251]	eta 0:24:51 lr 0.000950	time 2.2024 (2.2233)	loss 4.8949 (4.0044)	grad_norm 1.1397 (1.1212)	
[2022-01-18 21:46:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][590/1251]	eta 0:24:26 lr 0.000950	time 1.6223 (2.2186)	loss 4.4898 (4.0085)	grad_norm 1.0127 (1.1204)	
[2022-01-18 21:46:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][600/1251]	eta 0:24:02 lr 0.000950	time 2.4807 (2.2163)	loss 3.8209 (4.0117)	grad_norm 1.0430 (1.1210)	
[2022-01-18 21:47:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][610/1251]	eta 0:23:38 lr 0.000950	time 2.1437 (2.2131)	loss 4.3558 (4.0057)	grad_norm 1.1383 (1.1220)	
[2022-01-18 21:47:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][620/1251]	eta 0:23:16 lr 0.000950	time 2.7700 (2.2128)	loss 4.7692 (4.0008)	grad_norm 1.3364 (1.1229)	
[2022-01-18 21:47:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][630/1251]	eta 0:22:53 lr 0.000950	time 2.2179 (2.2112)	loss 4.1431 (4.0008)	grad_norm 1.1286 (1.1227)	
[2022-01-18 21:48:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][640/1251]	eta 0:22:31 lr 0.000949	time 2.4379 (2.2118)	loss 4.6749 (4.0026)	grad_norm 1.1574 (1.1220)	
[2022-01-18 21:48:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][650/1251]	eta 0:22:09 lr 0.000949	time 2.3083 (2.2116)	loss 4.0844 (4.0015)	grad_norm 1.0117 (1.1224)	
[2022-01-18 21:49:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][660/1251]	eta 0:21:49 lr 0.000949	time 2.7898 (2.2161)	loss 4.2505 (3.9973)	grad_norm 0.9360 (1.1215)	
[2022-01-18 21:49:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][670/1251]	eta 0:21:27 lr 0.000949	time 2.5500 (2.2163)	loss 2.9278 (3.9980)	grad_norm 1.2896 (1.1224)	
[2022-01-18 21:49:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][680/1251]	eta 0:21:04 lr 0.000949	time 2.1549 (2.2153)	loss 4.4218 (4.0010)	grad_norm 1.0092 (1.1220)	
[2022-01-18 21:50:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][690/1251]	eta 0:20:40 lr 0.000949	time 1.8988 (2.2120)	loss 2.6660 (4.0000)	grad_norm 1.1855 (1.1217)	
[2022-01-18 21:50:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][700/1251]	eta 0:20:19 lr 0.000949	time 2.2174 (2.2132)	loss 4.7709 (3.9986)	grad_norm 1.0640 (1.1217)	
[2022-01-18 21:50:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][710/1251]	eta 0:19:56 lr 0.000949	time 1.9643 (2.2116)	loss 4.2807 (4.0013)	grad_norm 1.0415 (1.1225)	
[2022-01-18 21:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][720/1251]	eta 0:19:33 lr 0.000949	time 2.5262 (2.2106)	loss 4.0411 (3.9990)	grad_norm 1.1280 (1.1223)	
[2022-01-18 21:51:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][730/1251]	eta 0:19:11 lr 0.000949	time 2.2315 (2.2107)	loss 3.7231 (3.9986)	grad_norm 1.0769 (1.1222)	
[2022-01-18 21:51:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][740/1251]	eta 0:18:50 lr 0.000949	time 2.0493 (2.2116)	loss 3.3311 (3.9965)	grad_norm 1.1657 (1.1221)	
[2022-01-18 21:52:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][750/1251]	eta 0:18:27 lr 0.000949	time 2.2218 (2.2110)	loss 4.3958 (3.9961)	grad_norm 1.1301 (1.1226)	
[2022-01-18 21:52:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][760/1251]	eta 0:18:05 lr 0.000949	time 2.5379 (2.2116)	loss 4.5393 (3.9967)	grad_norm 1.0549 (1.1232)	
[2022-01-18 21:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][770/1251]	eta 0:17:43 lr 0.000949	time 1.5887 (2.2103)	loss 4.3794 (3.9992)	grad_norm 1.2441 (1.1237)	
[2022-01-18 21:53:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][780/1251]	eta 0:17:21 lr 0.000949	time 1.9299 (2.2112)	loss 4.7182 (4.0030)	grad_norm 1.3672 (1.1247)	
[2022-01-18 21:53:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][790/1251]	eta 0:16:58 lr 0.000949	time 1.8627 (2.2083)	loss 4.7388 (4.0052)	grad_norm 0.9583 (1.1252)	
[2022-01-18 21:54:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][800/1251]	eta 0:16:35 lr 0.000949	time 2.0844 (2.2080)	loss 4.8815 (4.0074)	grad_norm 1.2529 (1.1262)	
[2022-01-18 21:54:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][810/1251]	eta 0:16:13 lr 0.000949	time 2.2370 (2.2072)	loss 3.5832 (4.0090)	grad_norm 1.0227 (1.1256)	
[2022-01-18 21:54:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][820/1251]	eta 0:15:51 lr 0.000949	time 1.9313 (2.2066)	loss 3.5818 (4.0056)	grad_norm 1.1200 (1.1254)	
[2022-01-18 21:55:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][830/1251]	eta 0:15:28 lr 0.000949	time 2.1482 (2.2060)	loss 3.9779 (4.0062)	grad_norm 0.9362 (1.1243)	
[2022-01-18 21:55:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][840/1251]	eta 0:15:06 lr 0.000949	time 1.8852 (2.2053)	loss 4.4788 (4.0080)	grad_norm 0.9787 (1.1235)	
[2022-01-18 21:55:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][850/1251]	eta 0:14:44 lr 0.000949	time 2.0074 (2.2055)	loss 4.2011 (4.0059)	grad_norm 1.4146 (1.1234)	
[2022-01-18 21:56:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][860/1251]	eta 0:14:22 lr 0.000949	time 2.2604 (2.2053)	loss 4.2334 (4.0045)	grad_norm 0.9611 (1.1249)	
[2022-01-18 21:56:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][870/1251]	eta 0:13:59 lr 0.000949	time 1.9339 (2.2043)	loss 4.1765 (4.0041)	grad_norm 1.0510 (1.1243)	
[2022-01-18 21:56:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][880/1251]	eta 0:13:37 lr 0.000949	time 1.8548 (2.2041)	loss 5.0104 (4.0039)	grad_norm 1.0274 (1.1246)	
[2022-01-18 21:57:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][890/1251]	eta 0:13:16 lr 0.000949	time 2.2190 (2.2051)	loss 4.4080 (4.0049)	grad_norm 1.0704 (1.1256)	
[2022-01-18 21:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][900/1251]	eta 0:12:54 lr 0.000949	time 2.8051 (2.2069)	loss 4.1908 (4.0042)	grad_norm 0.9098 (1.1261)	
[2022-01-18 21:58:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][910/1251]	eta 0:12:31 lr 0.000949	time 1.7340 (2.2048)	loss 3.3520 (4.0003)	grad_norm 1.1055 (1.1262)	
[2022-01-18 21:58:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][920/1251]	eta 0:12:08 lr 0.000949	time 2.0444 (2.2018)	loss 4.6500 (3.9982)	grad_norm 0.9966 (1.1249)	
[2022-01-18 21:58:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][930/1251]	eta 0:11:45 lr 0.000949	time 2.3735 (2.1993)	loss 3.7687 (3.9982)	grad_norm 1.0186 (1.1239)	
[2022-01-18 21:59:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][940/1251]	eta 0:11:23 lr 0.000949	time 2.4265 (2.1988)	loss 3.5010 (3.9946)	grad_norm 1.0738 (1.1238)	
[2022-01-18 21:59:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][950/1251]	eta 0:11:02 lr 0.000949	time 3.2599 (2.2002)	loss 4.3049 (3.9924)	grad_norm 0.9877 (1.1237)	
[2022-01-18 21:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][960/1251]	eta 0:10:40 lr 0.000949	time 1.6581 (2.2008)	loss 4.6019 (3.9919)	grad_norm 1.1199 (1.1236)	
[2022-01-18 22:00:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][970/1251]	eta 0:10:19 lr 0.000949	time 2.6675 (2.2040)	loss 4.0481 (3.9901)	grad_norm 1.2026 (1.1234)	
[2022-01-18 22:00:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][980/1251]	eta 0:09:57 lr 0.000949	time 2.2189 (2.2053)	loss 4.4926 (3.9912)	grad_norm 0.9437 (1.1231)	
[2022-01-18 22:01:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][990/1251]	eta 0:09:35 lr 0.000949	time 3.0836 (2.2059)	loss 4.7935 (3.9917)	grad_norm 1.2930 (1.1231)	
[2022-01-18 22:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1000/1251]	eta 0:09:13 lr 0.000949	time 1.7178 (2.2042)	loss 3.2822 (3.9909)	grad_norm 1.0306 (1.1227)	
[2022-01-18 22:01:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1010/1251]	eta 0:08:50 lr 0.000949	time 2.0728 (2.2017)	loss 4.2032 (3.9911)	grad_norm 0.9641 (1.1233)	
[2022-01-18 22:02:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1020/1251]	eta 0:08:28 lr 0.000949	time 1.9814 (2.1993)	loss 4.4116 (3.9910)	grad_norm 0.8825 (1.1225)	
[2022-01-18 22:02:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1030/1251]	eta 0:08:06 lr 0.000949	time 2.6862 (2.1999)	loss 3.5473 (3.9900)	grad_norm 0.9181 (1.1212)	
[2022-01-18 22:02:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1040/1251]	eta 0:07:44 lr 0.000949	time 1.8065 (2.2005)	loss 4.4775 (3.9917)	grad_norm 1.1202 (1.1210)	
[2022-01-18 22:03:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1050/1251]	eta 0:07:22 lr 0.000949	time 2.4725 (2.2020)	loss 4.1397 (3.9894)	grad_norm 1.2897 (1.1207)	
[2022-01-18 22:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1060/1251]	eta 0:07:00 lr 0.000949	time 1.7227 (2.2029)	loss 4.2049 (3.9897)	grad_norm 1.0468 (1.1209)	
[2022-01-18 22:03:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1070/1251]	eta 0:06:38 lr 0.000949	time 3.2520 (2.2041)	loss 3.4821 (3.9901)	grad_norm 0.9584 (1.1202)	
[2022-01-18 22:04:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1080/1251]	eta 0:06:16 lr 0.000949	time 1.8632 (2.2031)	loss 4.0358 (3.9923)	grad_norm 1.3090 (1.1199)	
[2022-01-18 22:04:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1090/1251]	eta 0:05:54 lr 0.000949	time 1.8753 (2.2026)	loss 4.0175 (3.9943)	grad_norm 1.1661 (1.1196)	
[2022-01-18 22:05:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1100/1251]	eta 0:05:32 lr 0.000949	time 1.9272 (2.2017)	loss 4.4744 (3.9949)	grad_norm 1.1372 (1.1193)	
[2022-01-18 22:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1110/1251]	eta 0:05:10 lr 0.000949	time 5.0127 (2.2041)	loss 4.0842 (3.9978)	grad_norm 1.3386 (1.1199)	
[2022-01-18 22:05:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1120/1251]	eta 0:04:48 lr 0.000949	time 2.4933 (2.2050)	loss 4.1299 (3.9981)	grad_norm 1.2724 (1.1206)	
[2022-01-18 22:06:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1130/1251]	eta 0:04:26 lr 0.000949	time 1.9213 (2.2035)	loss 3.6781 (3.9971)	grad_norm 1.0234 (1.1203)	
[2022-01-18 22:06:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1140/1251]	eta 0:04:04 lr 0.000949	time 1.7177 (2.2026)	loss 4.0431 (3.9968)	grad_norm 1.1136 (1.1192)	
[2022-01-18 22:06:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1150/1251]	eta 0:03:42 lr 0.000949	time 3.6751 (2.2026)	loss 4.6109 (3.9980)	grad_norm 1.0543 (1.1194)	
[2022-01-18 22:07:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1160/1251]	eta 0:03:20 lr 0.000949	time 2.0894 (2.2028)	loss 4.1935 (3.9956)	grad_norm 1.3678 (1.1195)	
[2022-01-18 22:07:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1170/1251]	eta 0:02:58 lr 0.000949	time 1.7029 (2.2032)	loss 4.1385 (3.9952)	grad_norm 1.1596 (1.1190)	
[2022-01-18 22:07:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1180/1251]	eta 0:02:36 lr 0.000949	time 1.9037 (2.2020)	loss 3.0104 (3.9926)	grad_norm 1.3661 (1.1199)	
[2022-01-18 22:08:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1190/1251]	eta 0:02:14 lr 0.000948	time 3.7035 (2.2023)	loss 4.1154 (3.9938)	grad_norm 1.0254 (1.1202)	
[2022-01-18 22:08:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1200/1251]	eta 0:01:52 lr 0.000948	time 2.1487 (2.2018)	loss 3.0212 (3.9915)	grad_norm 1.1145 (1.1196)	
[2022-01-18 22:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1210/1251]	eta 0:01:30 lr 0.000948	time 2.1463 (2.2025)	loss 4.4490 (3.9918)	grad_norm 1.0369 (1.1197)	
[2022-01-18 22:09:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1220/1251]	eta 0:01:08 lr 0.000948	time 1.8618 (2.2012)	loss 3.2231 (3.9903)	grad_norm 0.9572 (1.1193)	
[2022-01-18 22:09:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1230/1251]	eta 0:00:46 lr 0.000948	time 3.5976 (2.2031)	loss 2.9599 (3.9919)	grad_norm 0.9949 (1.1188)	
[2022-01-18 22:10:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1240/1251]	eta 0:00:24 lr 0.000948	time 1.6486 (2.2013)	loss 4.0315 (3.9933)	grad_norm 0.9477 (1.1186)	
[2022-01-18 22:10:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [43/300][1250/1251]	eta 0:00:02 lr 0.000948	time 1.1957 (2.1951)	loss 4.1922 (3.9914)	grad_norm 1.2955 (1.1187)	
[2022-01-18 22:10:24 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 43 training takes 0:45:46
[2022-01-18 22:10:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.325 (18.325)	Loss 1.5358 (1.5358)	Acc@1 65.332 (65.332)	Acc@5 87.500 (87.500)	
[2022-01-18 22:11:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.620 (3.436)	Loss 1.2704 (1.3753)	Acc@1 71.973 (69.416)	Acc@5 91.016 (89.560)	
[2022-01-18 22:11:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.602 (2.640)	Loss 1.4000 (1.3920)	Acc@1 68.164 (69.220)	Acc@5 89.355 (89.365)	
[2022-01-18 22:11:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.579 (2.267)	Loss 1.4032 (1.3965)	Acc@1 69.336 (69.024)	Acc@5 88.867 (89.321)	
[2022-01-18 22:11:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.300 (2.202)	Loss 1.4003 (1.3938)	Acc@1 68.848 (69.100)	Acc@5 88.965 (89.332)	
[2022-01-18 22:12:02 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 69.124 Acc@5 89.418
[2022-01-18 22:12:02 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 69.1%
[2022-01-18 22:12:02 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 69.12%
[2022-01-18 22:12:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][0/1251]	eta 7:32:34 lr 0.000948	time 21.7059 (21.7059)	loss 3.6570 (3.6570)	grad_norm 1.1890 (1.1890)	
[2022-01-18 22:12:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][10/1251]	eta 1:24:13 lr 0.000948	time 2.2550 (4.0724)	loss 3.9789 (3.9210)	grad_norm 0.9953 (1.1331)	
[2022-01-18 22:13:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][20/1251]	eta 1:04:30 lr 0.000948	time 1.6593 (3.1444)	loss 4.1110 (3.9824)	grad_norm 1.0939 (1.1073)	
[2022-01-18 22:13:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][30/1251]	eta 0:56:55 lr 0.000948	time 1.8132 (2.7975)	loss 4.1240 (4.0871)	grad_norm 1.1696 (1.1053)	
[2022-01-18 22:13:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][40/1251]	eta 0:53:51 lr 0.000948	time 3.9648 (2.6684)	loss 4.1337 (4.0134)	grad_norm 1.1708 (1.1260)	
[2022-01-18 22:14:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][50/1251]	eta 0:52:00 lr 0.000948	time 2.0886 (2.5987)	loss 3.0501 (4.0314)	grad_norm 1.5813 (1.1205)	
[2022-01-18 22:14:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][60/1251]	eta 0:50:29 lr 0.000948	time 1.4311 (2.5439)	loss 4.5432 (4.0321)	grad_norm 1.2011 (1.1176)	
[2022-01-18 22:14:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][70/1251]	eta 0:48:48 lr 0.000948	time 1.7099 (2.4796)	loss 4.8395 (4.0271)	grad_norm 0.9990 (1.1299)	
[2022-01-18 22:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][80/1251]	eta 0:48:21 lr 0.000948	time 3.7526 (2.4780)	loss 4.5964 (4.0395)	grad_norm 1.2363 (1.1178)	
[2022-01-18 22:15:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][90/1251]	eta 0:47:40 lr 0.000948	time 2.6556 (2.4635)	loss 2.9310 (4.0032)	grad_norm 1.1532 (1.1057)	
[2022-01-18 22:16:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][100/1251]	eta 0:47:17 lr 0.000948	time 2.5370 (2.4657)	loss 4.1640 (4.0309)	grad_norm 1.1456 (1.1027)	
[2022-01-18 22:16:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][110/1251]	eta 0:46:19 lr 0.000948	time 1.6641 (2.4358)	loss 4.2187 (4.0066)	grad_norm 1.0367 (1.0993)	
[2022-01-18 22:16:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][120/1251]	eta 0:45:14 lr 0.000948	time 2.5233 (2.4002)	loss 3.7143 (4.0068)	grad_norm 1.1348 (1.1008)	
[2022-01-18 22:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][130/1251]	eta 0:44:08 lr 0.000948	time 1.9286 (2.3623)	loss 4.7521 (4.0104)	grad_norm 1.0819 (1.0994)	
[2022-01-18 22:17:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][140/1251]	eta 0:43:17 lr 0.000948	time 2.5422 (2.3384)	loss 3.1221 (3.9950)	grad_norm 1.2765 (1.1095)	
[2022-01-18 22:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][150/1251]	eta 0:42:43 lr 0.000948	time 2.6589 (2.3286)	loss 4.5092 (4.0122)	grad_norm 1.0317 (1.1124)	
[2022-01-18 22:18:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][160/1251]	eta 0:42:07 lr 0.000948	time 2.2192 (2.3165)	loss 4.5666 (4.0198)	grad_norm 0.9838 (1.1126)	
[2022-01-18 22:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][170/1251]	eta 0:41:37 lr 0.000948	time 2.5640 (2.3103)	loss 4.4151 (4.0106)	grad_norm 1.2993 (1.1109)	
[2022-01-18 22:19:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][180/1251]	eta 0:41:09 lr 0.000948	time 1.8567 (2.3058)	loss 4.1658 (4.0065)	grad_norm 1.3059 (1.1113)	
[2022-01-18 22:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][190/1251]	eta 0:40:42 lr 0.000948	time 2.3236 (2.3016)	loss 4.1722 (4.0075)	grad_norm 0.9545 (1.1068)	
[2022-01-18 22:19:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][200/1251]	eta 0:40:22 lr 0.000948	time 3.1815 (2.3046)	loss 3.0562 (3.9921)	grad_norm 1.1165 (1.1054)	
[2022-01-18 22:20:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][210/1251]	eta 0:39:57 lr 0.000948	time 2.5433 (2.3030)	loss 3.6635 (3.9997)	grad_norm 1.0760 (1.1009)	
[2022-01-18 22:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][220/1251]	eta 0:39:24 lr 0.000948	time 2.3081 (2.2939)	loss 3.2432 (3.9847)	grad_norm 1.1197 (1.1011)	
[2022-01-18 22:20:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][230/1251]	eta 0:38:55 lr 0.000948	time 2.4435 (2.2877)	loss 4.6236 (3.9834)	grad_norm 1.2593 (1.1005)	
[2022-01-18 22:21:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][240/1251]	eta 0:38:36 lr 0.000948	time 3.0627 (2.2913)	loss 4.4979 (3.9835)	grad_norm 0.9294 (1.1012)	
[2022-01-18 22:21:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][250/1251]	eta 0:38:06 lr 0.000948	time 1.9071 (2.2838)	loss 3.3660 (3.9771)	grad_norm 1.1328 (1.1034)	
[2022-01-18 22:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][260/1251]	eta 0:37:36 lr 0.000948	time 1.6425 (2.2768)	loss 4.2356 (3.9789)	grad_norm 1.0496 (1.1035)	
[2022-01-18 22:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][270/1251]	eta 0:37:09 lr 0.000948	time 2.1245 (2.2725)	loss 3.9269 (3.9787)	grad_norm 1.1479 (1.1042)	
[2022-01-18 22:22:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][280/1251]	eta 0:36:42 lr 0.000948	time 3.0817 (2.2681)	loss 4.0701 (3.9758)	grad_norm 1.1171 (1.1021)	
[2022-01-18 22:23:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][290/1251]	eta 0:36:18 lr 0.000948	time 2.2301 (2.2670)	loss 4.1996 (3.9822)	grad_norm 1.1421 (1.1019)	
[2022-01-18 22:23:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][300/1251]	eta 0:35:51 lr 0.000948	time 2.5108 (2.2623)	loss 4.0912 (3.9837)	grad_norm 0.9133 (1.1026)	
[2022-01-18 22:23:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][310/1251]	eta 0:35:26 lr 0.000948	time 2.2246 (2.2598)	loss 4.1188 (3.9841)	grad_norm 1.2913 (1.1044)	
[2022-01-18 22:24:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][320/1251]	eta 0:35:00 lr 0.000948	time 2.2520 (2.2566)	loss 4.1279 (3.9875)	grad_norm 0.9746 (1.1048)	
[2022-01-18 22:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][330/1251]	eta 0:34:36 lr 0.000948	time 2.0993 (2.2547)	loss 4.8794 (3.9977)	grad_norm 1.0742 (1.1044)	
[2022-01-18 22:24:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][340/1251]	eta 0:34:10 lr 0.000948	time 2.2137 (2.2504)	loss 3.7982 (3.9936)	grad_norm 1.2601 (1.1037)	
[2022-01-18 22:25:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][350/1251]	eta 0:33:44 lr 0.000948	time 2.1219 (2.2471)	loss 3.6339 (3.9924)	grad_norm 1.2184 (1.1027)	
[2022-01-18 22:25:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][360/1251]	eta 0:33:20 lr 0.000948	time 2.5789 (2.2454)	loss 3.9712 (3.9848)	grad_norm 0.9886 (1.1027)	
[2022-01-18 22:25:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][370/1251]	eta 0:32:56 lr 0.000948	time 1.9804 (2.2438)	loss 4.9133 (3.9896)	grad_norm 1.4341 (1.1034)	
[2022-01-18 22:26:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][380/1251]	eta 0:32:33 lr 0.000948	time 2.5303 (2.2423)	loss 4.0618 (3.9908)	grad_norm 1.2237 (1.1049)	
[2022-01-18 22:26:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][390/1251]	eta 0:32:12 lr 0.000948	time 2.1862 (2.2440)	loss 4.4403 (3.9908)	grad_norm 1.1838 (1.1071)	
[2022-01-18 22:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][400/1251]	eta 0:31:48 lr 0.000948	time 3.4968 (2.2425)	loss 3.9595 (3.9910)	grad_norm 0.9351 (1.1090)	
[2022-01-18 22:27:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][410/1251]	eta 0:31:26 lr 0.000948	time 2.1889 (2.2432)	loss 4.5072 (3.9910)	grad_norm 1.1115 (1.1081)	
[2022-01-18 22:27:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][420/1251]	eta 0:31:02 lr 0.000948	time 2.1857 (2.2407)	loss 4.0915 (3.9893)	grad_norm 1.2085 (1.1101)	
[2022-01-18 22:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][430/1251]	eta 0:30:37 lr 0.000948	time 1.7657 (2.2386)	loss 4.5189 (3.9898)	grad_norm 1.1959 (1.1099)	
[2022-01-18 22:28:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][440/1251]	eta 0:30:13 lr 0.000948	time 2.0532 (2.2358)	loss 4.5967 (3.9975)	grad_norm 1.1094 (1.1102)	
[2022-01-18 22:28:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][450/1251]	eta 0:29:47 lr 0.000948	time 1.6202 (2.2318)	loss 2.9741 (3.9992)	grad_norm 0.9179 (1.1101)	
[2022-01-18 22:29:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][460/1251]	eta 0:29:22 lr 0.000948	time 1.6714 (2.2287)	loss 4.3082 (3.9904)	grad_norm 1.0177 (1.1101)	
[2022-01-18 22:29:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][470/1251]	eta 0:29:02 lr 0.000948	time 2.2231 (2.2316)	loss 4.2503 (3.9949)	grad_norm 1.0734 (1.1130)	
[2022-01-18 22:29:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][480/1251]	eta 0:28:39 lr 0.000947	time 2.4752 (2.2299)	loss 3.7988 (3.9972)	grad_norm 1.1053 (1.1137)	
[2022-01-18 22:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][490/1251]	eta 0:28:14 lr 0.000947	time 1.5936 (2.2267)	loss 3.5481 (3.9981)	grad_norm 1.0534 (1.1123)	
[2022-01-18 22:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][500/1251]	eta 0:27:52 lr 0.000947	time 2.6085 (2.2266)	loss 2.9932 (3.9942)	grad_norm 0.9857 (1.1127)	
[2022-01-18 22:31:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][510/1251]	eta 0:27:29 lr 0.000947	time 1.8797 (2.2263)	loss 3.5173 (3.9936)	grad_norm 1.0960 (1.1112)	
[2022-01-18 22:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][520/1251]	eta 0:27:06 lr 0.000947	time 1.9793 (2.2244)	loss 4.3064 (3.9996)	grad_norm 1.1862 (1.1111)	
[2022-01-18 22:31:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][530/1251]	eta 0:26:41 lr 0.000947	time 2.3185 (2.2217)	loss 3.5816 (3.9953)	grad_norm 1.1318 (1.1113)	
[2022-01-18 22:32:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][540/1251]	eta 0:26:20 lr 0.000947	time 2.6179 (2.2224)	loss 4.4560 (3.9972)	grad_norm 0.9965 (1.1118)	
[2022-01-18 22:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][550/1251]	eta 0:25:56 lr 0.000947	time 2.1296 (2.2201)	loss 3.6357 (3.9993)	grad_norm 0.9809 (1.1105)	
[2022-01-18 22:32:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][560/1251]	eta 0:25:33 lr 0.000947	time 2.3213 (2.2187)	loss 4.1928 (4.0029)	grad_norm 1.0291 (1.1107)	
[2022-01-18 22:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][570/1251]	eta 0:25:11 lr 0.000947	time 2.2715 (2.2202)	loss 4.2048 (4.0035)	grad_norm 1.0220 (1.1095)	
[2022-01-18 22:33:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][580/1251]	eta 0:24:52 lr 0.000947	time 3.7509 (2.2244)	loss 4.5929 (4.0044)	grad_norm 0.9729 (1.1083)	
[2022-01-18 22:33:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][590/1251]	eta 0:24:31 lr 0.000947	time 2.7700 (2.2265)	loss 4.7746 (4.0063)	grad_norm 1.3355 (1.1081)	
[2022-01-18 22:34:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][600/1251]	eta 0:24:07 lr 0.000947	time 2.2298 (2.2239)	loss 3.8802 (4.0034)	grad_norm 0.9727 (1.1100)	
[2022-01-18 22:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][610/1251]	eta 0:23:41 lr 0.000947	time 1.6074 (2.2179)	loss 2.6022 (3.9982)	grad_norm 1.0779 (1.1119)	
[2022-01-18 22:34:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][620/1251]	eta 0:23:16 lr 0.000947	time 1.9321 (2.2138)	loss 3.7219 (3.9967)	grad_norm 1.0640 (1.1127)	
[2022-01-18 22:35:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][630/1251]	eta 0:22:52 lr 0.000947	time 2.0540 (2.2104)	loss 4.2882 (3.9940)	grad_norm 1.0864 (1.1133)	
[2022-01-18 22:35:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][640/1251]	eta 0:22:28 lr 0.000947	time 2.1985 (2.2077)	loss 3.0874 (3.9932)	grad_norm 1.1560 (1.1128)	
[2022-01-18 22:35:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][650/1251]	eta 0:22:06 lr 0.000947	time 2.1094 (2.2064)	loss 4.6291 (3.9953)	grad_norm 1.0190 (1.1131)	
[2022-01-18 22:36:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][660/1251]	eta 0:21:43 lr 0.000947	time 2.5708 (2.2053)	loss 3.7980 (3.9983)	grad_norm 1.0024 (1.1126)	
[2022-01-18 22:36:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][670/1251]	eta 0:21:21 lr 0.000947	time 2.1460 (2.2050)	loss 3.1467 (3.9931)	grad_norm 0.9477 (1.1117)	
[2022-01-18 22:37:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][680/1251]	eta 0:21:06 lr 0.000947	time 7.3580 (2.2173)	loss 4.2322 (3.9910)	grad_norm 1.0375 (1.1111)	
[2022-01-18 22:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][690/1251]	eta 0:20:43 lr 0.000947	time 2.1906 (2.2169)	loss 3.5145 (3.9888)	grad_norm 1.2602 (1.1100)	
[2022-01-18 22:37:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][700/1251]	eta 0:20:21 lr 0.000947	time 2.1207 (2.2173)	loss 2.7628 (3.9883)	grad_norm 1.3538 (1.1104)	
[2022-01-18 22:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][710/1251]	eta 0:19:59 lr 0.000947	time 1.9255 (2.2167)	loss 4.2846 (3.9928)	grad_norm 1.0993 (1.1095)	
[2022-01-18 22:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][720/1251]	eta 0:19:37 lr 0.000947	time 3.4028 (2.2168)	loss 3.7014 (3.9893)	grad_norm 0.9654 (1.1091)	
[2022-01-18 22:39:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][730/1251]	eta 0:19:12 lr 0.000947	time 1.6145 (2.2130)	loss 4.1587 (3.9874)	grad_norm 0.9822 (1.1090)	
[2022-01-18 22:39:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][740/1251]	eta 0:18:49 lr 0.000947	time 1.6259 (2.2099)	loss 4.4812 (3.9870)	grad_norm 1.2360 (1.1094)	
[2022-01-18 22:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][750/1251]	eta 0:18:26 lr 0.000947	time 1.8145 (2.2090)	loss 2.9996 (3.9877)	grad_norm 1.3273 (1.1085)	
[2022-01-18 22:40:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][760/1251]	eta 0:18:04 lr 0.000947	time 2.5024 (2.2079)	loss 4.3028 (3.9858)	grad_norm 1.0126 (1.1088)	
[2022-01-18 22:40:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][770/1251]	eta 0:17:41 lr 0.000947	time 2.0486 (2.2077)	loss 3.2734 (3.9858)	grad_norm 1.2569 (1.1092)	
[2022-01-18 22:40:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][780/1251]	eta 0:17:20 lr 0.000947	time 1.9071 (2.2081)	loss 2.8424 (3.9829)	grad_norm 1.1031 (1.1091)	
[2022-01-18 22:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][790/1251]	eta 0:16:58 lr 0.000947	time 1.8874 (2.2086)	loss 4.0875 (3.9819)	grad_norm 1.0224 (1.1098)	
[2022-01-18 22:41:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][800/1251]	eta 0:16:36 lr 0.000947	time 2.5104 (2.2087)	loss 3.6789 (3.9821)	grad_norm 1.1566 (1.1103)	
[2022-01-18 22:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][810/1251]	eta 0:16:13 lr 0.000947	time 1.9729 (2.2076)	loss 4.2894 (3.9790)	grad_norm 1.3587 (1.1110)	
[2022-01-18 22:42:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][820/1251]	eta 0:15:51 lr 0.000947	time 1.8098 (2.2066)	loss 4.6214 (3.9844)	grad_norm 1.2242 (1.1127)	
[2022-01-18 22:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][830/1251]	eta 0:15:28 lr 0.000947	time 2.2640 (2.2059)	loss 4.7444 (3.9858)	grad_norm 0.9222 (1.1127)	
[2022-01-18 22:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][840/1251]	eta 0:15:06 lr 0.000947	time 2.5591 (2.2051)	loss 2.7959 (3.9842)	grad_norm 1.1108 (1.1132)	
[2022-01-18 22:43:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][850/1251]	eta 0:14:43 lr 0.000947	time 1.6071 (2.2040)	loss 4.0550 (3.9843)	grad_norm 1.3039 (1.1147)	
[2022-01-18 22:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][860/1251]	eta 0:14:21 lr 0.000947	time 2.0991 (2.2044)	loss 3.3732 (3.9805)	grad_norm 1.0980 (1.1150)	
[2022-01-18 22:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][870/1251]	eta 0:13:59 lr 0.000947	time 1.9707 (2.2040)	loss 4.2337 (3.9826)	grad_norm 1.1088 (1.1147)	
[2022-01-18 22:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][880/1251]	eta 0:13:37 lr 0.000947	time 2.1855 (2.2033)	loss 4.0862 (3.9829)	grad_norm 0.9909 (1.1149)	
[2022-01-18 22:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][890/1251]	eta 0:13:15 lr 0.000947	time 2.6409 (2.2038)	loss 4.2430 (3.9871)	grad_norm 1.2704 (1.1149)	
[2022-01-18 22:45:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][900/1251]	eta 0:12:53 lr 0.000947	time 1.9484 (2.2031)	loss 3.5468 (3.9845)	grad_norm 0.9796 (1.1155)	
[2022-01-18 22:45:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][910/1251]	eta 0:12:30 lr 0.000947	time 2.2408 (2.2023)	loss 3.7964 (3.9871)	grad_norm 0.9898 (1.1152)	
[2022-01-18 22:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][920/1251]	eta 0:12:09 lr 0.000947	time 2.8587 (2.2031)	loss 4.0004 (3.9883)	grad_norm 0.9577 (1.1155)	
[2022-01-18 22:46:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][930/1251]	eta 0:11:47 lr 0.000947	time 2.5825 (2.2045)	loss 4.8514 (3.9892)	grad_norm 1.1664 (1.1153)	
[2022-01-18 22:46:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][940/1251]	eta 0:11:25 lr 0.000947	time 2.8220 (2.2041)	loss 4.2954 (3.9898)	grad_norm 1.3000 (1.1162)	
[2022-01-18 22:46:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][950/1251]	eta 0:11:02 lr 0.000947	time 2.0994 (2.2021)	loss 4.5364 (3.9916)	grad_norm 1.0106 (1.1164)	
[2022-01-18 22:47:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][960/1251]	eta 0:10:40 lr 0.000947	time 1.8969 (2.2001)	loss 4.0074 (3.9903)	grad_norm 1.0658 (1.1158)	
[2022-01-18 22:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][970/1251]	eta 0:10:18 lr 0.000947	time 2.4127 (2.2001)	loss 4.6946 (3.9917)	grad_norm 1.2399 (1.1148)	
[2022-01-18 22:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][980/1251]	eta 0:09:56 lr 0.000947	time 2.8950 (2.2011)	loss 4.4619 (3.9916)	grad_norm 1.2040 (1.1147)	
[2022-01-18 22:48:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][990/1251]	eta 0:09:34 lr 0.000947	time 2.7325 (2.2012)	loss 4.3655 (3.9910)	grad_norm 1.3445 (1.1143)	
[2022-01-18 22:48:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1000/1251]	eta 0:09:12 lr 0.000947	time 1.8751 (2.2012)	loss 4.0296 (3.9904)	grad_norm 1.2993 (1.1151)	
[2022-01-18 22:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1010/1251]	eta 0:08:50 lr 0.000947	time 2.6260 (2.2024)	loss 4.1774 (3.9906)	grad_norm 1.0711 (1.1146)	
[2022-01-18 22:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1020/1251]	eta 0:08:29 lr 0.000946	time 3.3163 (2.2049)	loss 4.1523 (3.9927)	grad_norm 1.1102 (1.1142)	
[2022-01-18 22:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1030/1251]	eta 0:08:07 lr 0.000946	time 1.7421 (2.2045)	loss 3.1866 (3.9913)	grad_norm 1.2028 (1.1141)	
[2022-01-18 22:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1040/1251]	eta 0:07:44 lr 0.000946	time 1.8858 (2.2021)	loss 4.8169 (3.9900)	grad_norm 1.2102 (1.1140)	
[2022-01-18 22:50:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1050/1251]	eta 0:07:22 lr 0.000946	time 2.4620 (2.1996)	loss 3.9112 (3.9896)	grad_norm 1.0113 (1.1135)	
[2022-01-18 22:50:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1060/1251]	eta 0:06:59 lr 0.000946	time 2.7889 (2.1989)	loss 4.5493 (3.9906)	grad_norm 1.0821 (1.1129)	
[2022-01-18 22:51:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1070/1251]	eta 0:06:38 lr 0.000946	time 2.1804 (2.1993)	loss 4.3018 (3.9908)	grad_norm 1.0758 (1.1122)	
[2022-01-18 22:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1080/1251]	eta 0:06:16 lr 0.000946	time 2.0811 (2.2001)	loss 4.4926 (3.9875)	grad_norm 1.0731 (1.1121)	
[2022-01-18 22:52:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1090/1251]	eta 0:05:54 lr 0.000946	time 2.1951 (2.2008)	loss 4.4803 (3.9862)	grad_norm 1.2510 (1.1126)	
[2022-01-18 22:52:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1100/1251]	eta 0:05:32 lr 0.000946	time 2.4904 (2.2016)	loss 4.4301 (3.9866)	grad_norm 1.1922 (1.1125)	
[2022-01-18 22:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1110/1251]	eta 0:05:10 lr 0.000946	time 1.8852 (2.2010)	loss 3.5814 (3.9844)	grad_norm 0.8959 (1.1126)	
[2022-01-18 22:53:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1120/1251]	eta 0:04:48 lr 0.000946	time 2.1401 (2.1994)	loss 4.0834 (3.9830)	grad_norm 1.1437 (1.1139)	
[2022-01-18 22:53:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1130/1251]	eta 0:04:26 lr 0.000946	time 1.8459 (2.1992)	loss 3.8210 (3.9834)	grad_norm 1.3703 (1.1144)	
[2022-01-18 22:53:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1140/1251]	eta 0:04:04 lr 0.000946	time 2.5112 (2.1991)	loss 3.2795 (3.9826)	grad_norm 1.0765 (1.1142)	
[2022-01-18 22:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1150/1251]	eta 0:03:42 lr 0.000946	time 2.2760 (2.1992)	loss 3.9762 (3.9845)	grad_norm 1.0449 (1.1147)	
[2022-01-18 22:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1160/1251]	eta 0:03:20 lr 0.000946	time 1.8294 (2.1998)	loss 3.4885 (3.9826)	grad_norm 1.1830 (1.1151)	
[2022-01-18 22:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1170/1251]	eta 0:02:58 lr 0.000946	time 1.8977 (2.2009)	loss 4.5988 (3.9839)	grad_norm 0.9694 (1.1151)	
[2022-01-18 22:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1180/1251]	eta 0:02:36 lr 0.000946	time 2.4246 (2.2017)	loss 3.9477 (3.9835)	grad_norm 1.2749 (1.1156)	
[2022-01-18 22:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1190/1251]	eta 0:02:14 lr 0.000946	time 2.1445 (2.2014)	loss 4.0931 (3.9829)	grad_norm 0.9366 (1.1152)	
[2022-01-18 22:56:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1200/1251]	eta 0:01:52 lr 0.000946	time 1.9300 (2.2010)	loss 3.8068 (3.9851)	grad_norm 1.0223 (1.1151)	
[2022-01-18 22:56:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1210/1251]	eta 0:01:30 lr 0.000946	time 1.6647 (2.1983)	loss 4.2319 (3.9845)	grad_norm 0.9593 (1.1148)	
[2022-01-18 22:56:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1220/1251]	eta 0:01:08 lr 0.000946	time 1.9002 (2.1968)	loss 4.6376 (3.9836)	grad_norm 1.2740 (1.1143)	
[2022-01-18 22:57:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1230/1251]	eta 0:00:46 lr 0.000946	time 2.4959 (2.1968)	loss 3.9199 (3.9859)	grad_norm 1.0832 (1.1144)	
[2022-01-18 22:57:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1240/1251]	eta 0:00:24 lr 0.000946	time 1.9086 (2.1970)	loss 3.2539 (3.9858)	grad_norm 1.1777 (1.1144)	
[2022-01-18 22:57:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [44/300][1250/1251]	eta 0:00:02 lr 0.000946	time 1.1728 (2.1919)	loss 3.4838 (3.9845)	grad_norm 1.5235 (1.1154)	
[2022-01-18 22:57:45 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 44 training takes 0:45:42
[2022-01-18 22:58:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.574 (18.574)	Loss 1.3134 (1.3134)	Acc@1 68.262 (68.262)	Acc@5 89.648 (89.648)	
[2022-01-18 22:58:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.597 (3.481)	Loss 1.2822 (1.2918)	Acc@1 71.680 (69.798)	Acc@5 88.379 (89.648)	
[2022-01-18 22:58:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.295 (2.687)	Loss 1.2120 (1.2965)	Acc@1 72.559 (69.843)	Acc@5 90.430 (89.565)	
[2022-01-18 22:58:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.301 (2.309)	Loss 1.2925 (1.2955)	Acc@1 68.555 (69.629)	Acc@5 89.551 (89.696)	
[2022-01-18 22:59:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.465 (2.177)	Loss 1.2596 (1.2908)	Acc@1 70.215 (69.708)	Acc@5 90.137 (89.796)	
[2022-01-18 22:59:21 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 69.654 Acc@5 89.778
[2022-01-18 22:59:21 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 69.7%
[2022-01-18 22:59:21 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 69.65%
[2022-01-18 22:59:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][0/1251]	eta 7:31:25 lr 0.000946	time 21.6514 (21.6514)	loss 4.5712 (4.5712)	grad_norm 1.0859 (1.0859)	
[2022-01-18 23:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][10/1251]	eta 1:22:36 lr 0.000946	time 1.4906 (3.9943)	loss 4.4490 (4.0733)	grad_norm 1.0185 (1.0292)	
[2022-01-18 23:00:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][20/1251]	eta 1:05:36 lr 0.000946	time 1.5411 (3.1976)	loss 4.6759 (4.1934)	grad_norm 1.0194 (1.0444)	
[2022-01-18 23:00:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][30/1251]	eta 0:57:10 lr 0.000946	time 1.5850 (2.8095)	loss 4.5644 (4.2240)	grad_norm 1.1500 (1.0600)	
[2022-01-18 23:01:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][40/1251]	eta 0:54:13 lr 0.000946	time 3.8342 (2.6867)	loss 4.1579 (4.1829)	grad_norm 0.9720 (1.0696)	
[2022-01-18 23:01:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][50/1251]	eta 0:53:16 lr 0.000946	time 2.8137 (2.6619)	loss 3.8250 (4.0851)	grad_norm 1.1225 (1.0756)	
[2022-01-18 23:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][60/1251]	eta 0:51:38 lr 0.000946	time 2.1330 (2.6018)	loss 4.6382 (4.0851)	grad_norm 1.3832 (1.0899)	
[2022-01-18 23:02:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][70/1251]	eta 0:49:44 lr 0.000946	time 2.2620 (2.5269)	loss 3.4435 (4.0803)	grad_norm 1.0990 (1.1196)	
[2022-01-18 23:02:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][80/1251]	eta 0:48:36 lr 0.000946	time 3.2334 (2.4902)	loss 4.8840 (4.0805)	grad_norm 1.1086 (1.1395)	
[2022-01-18 23:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][90/1251]	eta 0:47:32 lr 0.000946	time 2.2441 (2.4566)	loss 4.2020 (4.1162)	grad_norm 1.0603 (1.1408)	
[2022-01-18 23:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][100/1251]	eta 0:46:33 lr 0.000946	time 2.4008 (2.4268)	loss 4.0926 (4.0916)	grad_norm 1.0040 (1.1303)	
[2022-01-18 23:03:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][110/1251]	eta 0:45:33 lr 0.000946	time 2.4584 (2.3959)	loss 4.5064 (4.1017)	grad_norm 1.2703 (1.1335)	
[2022-01-18 23:04:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][120/1251]	eta 0:44:54 lr 0.000946	time 2.2616 (2.3824)	loss 4.5408 (4.0788)	grad_norm 1.2087 (1.1341)	
[2022-01-18 23:04:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][130/1251]	eta 0:44:10 lr 0.000946	time 2.2371 (2.3648)	loss 4.1146 (4.0898)	grad_norm 1.1956 (1.1311)	
[2022-01-18 23:04:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][140/1251]	eta 0:43:23 lr 0.000946	time 1.7733 (2.3434)	loss 3.5474 (4.0610)	grad_norm 1.2221 (1.1333)	
[2022-01-18 23:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][150/1251]	eta 0:42:58 lr 0.000946	time 2.7046 (2.3422)	loss 3.9731 (4.0588)	grad_norm 0.9699 (1.1394)	
[2022-01-18 23:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][160/1251]	eta 0:42:26 lr 0.000946	time 1.9778 (2.3345)	loss 3.3593 (4.0471)	grad_norm 1.0931 (1.1359)	
[2022-01-18 23:06:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][170/1251]	eta 0:42:00 lr 0.000946	time 2.8479 (2.3315)	loss 4.2818 (4.0355)	grad_norm 1.0494 (1.1354)	
[2022-01-18 23:06:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][180/1251]	eta 0:41:25 lr 0.000946	time 1.8210 (2.3212)	loss 4.0854 (4.0260)	grad_norm 1.0271 (1.1339)	
[2022-01-18 23:06:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][190/1251]	eta 0:40:54 lr 0.000946	time 3.1372 (2.3131)	loss 4.0354 (4.0364)	grad_norm 1.2162 (1.1375)	
[2022-01-18 23:07:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][200/1251]	eta 0:40:24 lr 0.000946	time 2.2701 (2.3071)	loss 4.5417 (4.0261)	grad_norm 1.0792 (1.1397)	
[2022-01-18 23:07:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][210/1251]	eta 0:39:57 lr 0.000946	time 2.4851 (2.3034)	loss 3.9303 (4.0359)	grad_norm 1.0570 (1.1401)	
[2022-01-18 23:07:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][220/1251]	eta 0:39:23 lr 0.000946	time 1.8916 (2.2928)	loss 4.7339 (4.0406)	grad_norm 1.2013 (1.1390)	
[2022-01-18 23:08:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][230/1251]	eta 0:38:48 lr 0.000946	time 2.0539 (2.2807)	loss 4.7717 (4.0491)	grad_norm 0.8982 (1.1380)	
[2022-01-18 23:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][240/1251]	eta 0:38:20 lr 0.000946	time 2.3550 (2.2758)	loss 4.4848 (4.0346)	grad_norm 1.1403 (1.1385)	
[2022-01-18 23:08:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][250/1251]	eta 0:37:53 lr 0.000946	time 2.2390 (2.2715)	loss 4.6824 (4.0331)	grad_norm 1.1825 (1.1375)	
[2022-01-18 23:09:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][260/1251]	eta 0:37:30 lr 0.000946	time 1.8889 (2.2706)	loss 3.7258 (4.0326)	grad_norm 1.0927 (1.1398)	
[2022-01-18 23:09:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][270/1251]	eta 0:37:04 lr 0.000946	time 1.9564 (2.2681)	loss 3.3101 (4.0269)	grad_norm 0.9667 (1.1394)	
[2022-01-18 23:09:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][280/1251]	eta 0:36:33 lr 0.000946	time 2.2733 (2.2593)	loss 4.1949 (4.0181)	grad_norm 1.0810 (1.1370)	
[2022-01-18 23:10:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][290/1251]	eta 0:36:03 lr 0.000946	time 1.9408 (2.2512)	loss 3.5962 (4.0157)	grad_norm 1.0966 (1.1353)	
[2022-01-18 23:10:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][300/1251]	eta 0:35:37 lr 0.000945	time 1.9027 (2.2481)	loss 3.5849 (4.0176)	grad_norm 0.9760 (1.1332)	
[2022-01-18 23:11:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][310/1251]	eta 0:35:13 lr 0.000945	time 1.8591 (2.2464)	loss 4.7277 (4.0184)	grad_norm 1.1527 (1.1319)	
[2022-01-18 23:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][320/1251]	eta 0:34:51 lr 0.000945	time 1.8153 (2.2463)	loss 4.5235 (4.0226)	grad_norm 1.0369 (1.1299)	
[2022-01-18 23:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][330/1251]	eta 0:34:26 lr 0.000945	time 1.8332 (2.2436)	loss 3.6238 (4.0187)	grad_norm 1.1745 (1.1311)	
[2022-01-18 23:12:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][340/1251]	eta 0:34:02 lr 0.000945	time 1.9728 (2.2416)	loss 4.1819 (4.0158)	grad_norm 0.9724 (1.1300)	
[2022-01-18 23:12:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][350/1251]	eta 0:33:37 lr 0.000945	time 2.7881 (2.2397)	loss 3.2810 (4.0147)	grad_norm 1.3773 (1.1315)	
[2022-01-18 23:12:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][360/1251]	eta 0:33:18 lr 0.000945	time 2.4714 (2.2425)	loss 3.4539 (4.0171)	grad_norm 1.1421 (1.1334)	
[2022-01-18 23:13:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][370/1251]	eta 0:32:55 lr 0.000945	time 2.2161 (2.2424)	loss 3.8978 (4.0161)	grad_norm 0.9260 (1.1338)	
[2022-01-18 23:13:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][380/1251]	eta 0:32:31 lr 0.000945	time 1.6572 (2.2408)	loss 3.7383 (4.0172)	grad_norm 1.0475 (1.1351)	
[2022-01-18 23:13:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][390/1251]	eta 0:32:05 lr 0.000945	time 2.5426 (2.2365)	loss 4.3840 (4.0186)	grad_norm 1.5712 (1.1377)	
[2022-01-18 23:14:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][400/1251]	eta 0:31:41 lr 0.000945	time 1.8817 (2.2346)	loss 4.2028 (4.0168)	grad_norm 1.1921 (1.1369)	
[2022-01-18 23:14:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][410/1251]	eta 0:31:15 lr 0.000945	time 1.6092 (2.2296)	loss 4.6143 (4.0154)	grad_norm 1.2065 (1.1368)	
[2022-01-18 23:15:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][420/1251]	eta 0:30:54 lr 0.000945	time 2.8672 (2.2314)	loss 4.5422 (4.0136)	grad_norm 1.3462 (1.1360)	
[2022-01-18 23:15:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][430/1251]	eta 0:30:34 lr 0.000945	time 3.1224 (2.2340)	loss 4.3408 (4.0153)	grad_norm 0.9711 (1.1346)	
[2022-01-18 23:15:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][440/1251]	eta 0:30:11 lr 0.000945	time 2.5114 (2.2338)	loss 3.2848 (4.0106)	grad_norm 1.0808 (1.1352)	
[2022-01-18 23:16:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][450/1251]	eta 0:29:45 lr 0.000945	time 1.7007 (2.2296)	loss 4.0205 (4.0084)	grad_norm 1.0699 (1.1349)	
[2022-01-18 23:16:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][460/1251]	eta 0:29:23 lr 0.000945	time 2.6163 (2.2292)	loss 3.0880 (4.0020)	grad_norm 1.1797 (1.1354)	
[2022-01-18 23:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][470/1251]	eta 0:29:01 lr 0.000945	time 3.6485 (2.2293)	loss 3.6518 (4.0024)	grad_norm 1.1761 (1.1362)	
[2022-01-18 23:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][480/1251]	eta 0:28:36 lr 0.000945	time 1.5493 (2.2268)	loss 4.8148 (4.0046)	grad_norm 1.0409 (1.1352)	
[2022-01-18 23:17:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][490/1251]	eta 0:28:12 lr 0.000945	time 1.9045 (2.2247)	loss 3.2362 (4.0051)	grad_norm 1.0710 (1.1355)	
[2022-01-18 23:17:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][500/1251]	eta 0:27:51 lr 0.000945	time 2.2295 (2.2261)	loss 2.7447 (4.0059)	grad_norm 1.0945 (1.1360)	
[2022-01-18 23:18:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][510/1251]	eta 0:27:32 lr 0.000945	time 3.6533 (2.2301)	loss 4.2579 (4.0055)	grad_norm 1.5341 (1.1372)	
[2022-01-18 23:18:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][520/1251]	eta 0:27:09 lr 0.000945	time 1.8220 (2.2291)	loss 4.5638 (4.0038)	grad_norm 1.0878 (1.1372)	
[2022-01-18 23:19:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][530/1251]	eta 0:26:45 lr 0.000945	time 1.6741 (2.2264)	loss 4.1834 (4.0068)	grad_norm 1.0301 (1.1373)	
[2022-01-18 23:19:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][540/1251]	eta 0:26:20 lr 0.000945	time 1.9412 (2.2235)	loss 4.6658 (4.0080)	grad_norm 1.2747 (1.1371)	
[2022-01-18 23:19:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][550/1251]	eta 0:25:56 lr 0.000945	time 2.8900 (2.2209)	loss 4.2656 (4.0126)	grad_norm 1.1747 (1.1358)	
[2022-01-18 23:20:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][560/1251]	eta 0:25:33 lr 0.000945	time 1.8627 (2.2187)	loss 3.7000 (4.0123)	grad_norm 1.4626 (1.1363)	
[2022-01-18 23:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][570/1251]	eta 0:25:09 lr 0.000945	time 1.5321 (2.2169)	loss 3.3732 (4.0113)	grad_norm 1.5295 (1.1388)	
[2022-01-18 23:20:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][580/1251]	eta 0:24:48 lr 0.000945	time 2.7239 (2.2183)	loss 4.1325 (4.0087)	grad_norm 1.1737 (1.1389)	
[2022-01-18 23:21:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][590/1251]	eta 0:24:29 lr 0.000945	time 3.3126 (2.2225)	loss 3.3608 (4.0105)	grad_norm 1.7741 (1.1411)	
[2022-01-18 23:21:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][600/1251]	eta 0:24:07 lr 0.000945	time 1.7422 (2.2230)	loss 4.1958 (4.0059)	grad_norm 1.1601 (1.1431)	
[2022-01-18 23:21:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][610/1251]	eta 0:23:44 lr 0.000945	time 2.3515 (2.2225)	loss 2.8486 (4.0087)	grad_norm 1.1331 (1.1447)	
[2022-01-18 23:22:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][620/1251]	eta 0:23:19 lr 0.000945	time 1.9461 (2.2185)	loss 3.6093 (4.0100)	grad_norm 0.9863 (1.1429)	
[2022-01-18 23:22:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][630/1251]	eta 0:22:54 lr 0.000945	time 1.8721 (2.2136)	loss 3.1156 (4.0095)	grad_norm 1.2922 (1.1424)	
[2022-01-18 23:22:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][640/1251]	eta 0:22:30 lr 0.000945	time 1.8907 (2.2110)	loss 4.6016 (4.0066)	grad_norm 0.9353 (1.1403)	
[2022-01-18 23:23:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][650/1251]	eta 0:22:08 lr 0.000945	time 2.1735 (2.2104)	loss 4.3981 (4.0062)	grad_norm 1.0142 (1.1393)	
[2022-01-18 23:23:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][660/1251]	eta 0:21:46 lr 0.000945	time 2.2267 (2.2102)	loss 4.3200 (4.0037)	grad_norm 1.0436 (1.1385)	
[2022-01-18 23:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][670/1251]	eta 0:21:25 lr 0.000945	time 2.3094 (2.2122)	loss 4.3183 (4.0040)	grad_norm 1.2233 (1.1384)	
[2022-01-18 23:24:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][680/1251]	eta 0:21:03 lr 0.000945	time 1.8024 (2.2121)	loss 4.0528 (4.0046)	grad_norm 1.1267 (1.1377)	
[2022-01-18 23:24:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][690/1251]	eta 0:20:41 lr 0.000945	time 2.5166 (2.2137)	loss 4.3128 (4.0067)	grad_norm 1.0741 (1.1389)	
[2022-01-18 23:25:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][700/1251]	eta 0:20:19 lr 0.000945	time 2.3384 (2.2133)	loss 4.2557 (4.0051)	grad_norm 1.1217 (1.1392)	
[2022-01-18 23:25:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][710/1251]	eta 0:19:56 lr 0.000945	time 1.8968 (2.2125)	loss 4.1588 (4.0010)	grad_norm 1.0950 (1.1401)	
[2022-01-18 23:25:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][720/1251]	eta 0:19:34 lr 0.000945	time 1.9755 (2.2110)	loss 2.9311 (4.0010)	grad_norm 0.9762 (1.1410)	
[2022-01-18 23:26:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][730/1251]	eta 0:19:11 lr 0.000945	time 1.8709 (2.2107)	loss 4.2838 (4.0002)	grad_norm 1.1728 (1.1407)	
[2022-01-18 23:26:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][740/1251]	eta 0:18:49 lr 0.000945	time 1.8292 (2.2109)	loss 3.4991 (3.9982)	grad_norm 0.9861 (1.1393)	
[2022-01-18 23:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][750/1251]	eta 0:18:27 lr 0.000945	time 2.5642 (2.2114)	loss 4.5645 (3.9980)	grad_norm 1.2196 (1.1395)	
[2022-01-18 23:27:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][760/1251]	eta 0:18:06 lr 0.000945	time 2.0038 (2.2125)	loss 3.3234 (3.9998)	grad_norm 1.0570 (1.1401)	
[2022-01-18 23:27:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][770/1251]	eta 0:17:44 lr 0.000945	time 2.3335 (2.2128)	loss 3.9955 (4.0033)	grad_norm 1.0194 (1.1393)	
[2022-01-18 23:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][780/1251]	eta 0:17:20 lr 0.000945	time 1.6859 (2.2098)	loss 4.1262 (3.9995)	grad_norm 1.4907 (1.1398)	
[2022-01-18 23:28:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][790/1251]	eta 0:16:57 lr 0.000945	time 1.8269 (2.2080)	loss 3.9343 (3.9976)	grad_norm 1.0625 (1.1398)	
[2022-01-18 23:28:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][800/1251]	eta 0:16:35 lr 0.000945	time 2.5544 (2.2083)	loss 4.4477 (3.9986)	grad_norm 1.0003 (1.1383)	
[2022-01-18 23:29:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][810/1251]	eta 0:16:12 lr 0.000945	time 2.0630 (2.2055)	loss 3.3473 (3.9997)	grad_norm 1.0067 (1.1384)	
[2022-01-18 23:29:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][820/1251]	eta 0:15:50 lr 0.000944	time 1.8648 (2.2050)	loss 3.4282 (3.9987)	grad_norm 1.1475 (1.1385)	
[2022-01-18 23:29:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][830/1251]	eta 0:15:28 lr 0.000944	time 1.7535 (2.2044)	loss 3.3807 (4.0006)	grad_norm 1.0915 (1.1374)	
[2022-01-18 23:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][840/1251]	eta 0:15:07 lr 0.000944	time 2.6235 (2.2076)	loss 2.9609 (3.9969)	grad_norm 1.0710 (1.1373)	
[2022-01-18 23:30:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][850/1251]	eta 0:14:45 lr 0.000944	time 2.2229 (2.2087)	loss 4.2072 (3.9962)	grad_norm 1.4291 (1.1369)	
[2022-01-18 23:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][860/1251]	eta 0:14:22 lr 0.000944	time 1.9127 (2.2064)	loss 4.4088 (3.9964)	grad_norm 0.9080 (1.1386)	
[2022-01-18 23:31:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][870/1251]	eta 0:14:00 lr 0.000944	time 2.3702 (2.2062)	loss 4.0644 (3.9959)	grad_norm 1.2232 (1.1382)	
[2022-01-18 23:31:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][880/1251]	eta 0:13:38 lr 0.000944	time 1.5792 (2.2050)	loss 2.8060 (3.9950)	grad_norm 1.1374 (1.1386)	
[2022-01-18 23:32:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][890/1251]	eta 0:13:15 lr 0.000944	time 2.4733 (2.2046)	loss 3.1657 (3.9907)	grad_norm 1.1657 (1.1383)	
[2022-01-18 23:32:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][900/1251]	eta 0:12:53 lr 0.000944	time 2.2113 (2.2050)	loss 3.5491 (3.9897)	grad_norm 0.8860 (1.1385)	
[2022-01-18 23:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][910/1251]	eta 0:12:31 lr 0.000944	time 2.8063 (2.2038)	loss 3.6293 (3.9920)	grad_norm 0.9995 (1.1385)	
[2022-01-18 23:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][920/1251]	eta 0:12:09 lr 0.000944	time 1.8019 (2.2028)	loss 3.4886 (3.9889)	grad_norm 0.9642 (1.1381)	
[2022-01-18 23:33:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][930/1251]	eta 0:11:47 lr 0.000944	time 2.8698 (2.2041)	loss 3.0376 (3.9874)	grad_norm 1.2863 (1.1373)	
[2022-01-18 23:33:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][940/1251]	eta 0:11:25 lr 0.000944	time 1.5731 (2.2042)	loss 3.3279 (3.9858)	grad_norm 1.1499 (1.1391)	
[2022-01-18 23:34:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][950/1251]	eta 0:11:04 lr 0.000944	time 3.1121 (2.2070)	loss 4.4979 (3.9833)	grad_norm 0.9415 (1.1396)	
[2022-01-18 23:34:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][960/1251]	eta 0:10:42 lr 0.000944	time 1.5238 (2.2065)	loss 4.5245 (3.9822)	grad_norm 1.0255 (1.1393)	
[2022-01-18 23:35:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][970/1251]	eta 0:10:19 lr 0.000944	time 2.0448 (2.2061)	loss 3.5922 (3.9837)	grad_norm 1.2243 (1.1396)	
[2022-01-18 23:35:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][980/1251]	eta 0:09:57 lr 0.000944	time 2.1937 (2.2048)	loss 3.7051 (3.9833)	grad_norm 1.0429 (1.1392)	
[2022-01-18 23:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][990/1251]	eta 0:09:34 lr 0.000944	time 1.6934 (2.2028)	loss 3.8363 (3.9833)	grad_norm 0.9364 (1.1384)	
[2022-01-18 23:36:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1000/1251]	eta 0:09:12 lr 0.000944	time 1.9043 (2.2014)	loss 4.4766 (3.9821)	grad_norm 1.0402 (1.1383)	
[2022-01-18 23:36:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1010/1251]	eta 0:08:50 lr 0.000944	time 2.2363 (2.2006)	loss 3.9118 (3.9833)	grad_norm 1.1937 (1.1395)	
[2022-01-18 23:36:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1020/1251]	eta 0:08:28 lr 0.000944	time 2.5491 (2.2011)	loss 4.3498 (3.9866)	grad_norm 1.0532 (1.1396)	
[2022-01-18 23:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1030/1251]	eta 0:08:06 lr 0.000944	time 2.8243 (2.2010)	loss 4.4740 (3.9888)	grad_norm 1.0768 (1.1385)	
[2022-01-18 23:37:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1040/1251]	eta 0:07:44 lr 0.000944	time 2.1912 (2.2011)	loss 3.9044 (3.9871)	grad_norm 1.2387 (1.1387)	
[2022-01-18 23:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1050/1251]	eta 0:07:22 lr 0.000944	time 1.9804 (2.2015)	loss 3.9248 (3.9889)	grad_norm 0.9082 (1.1382)	
[2022-01-18 23:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1060/1251]	eta 0:07:00 lr 0.000944	time 2.7862 (2.2024)	loss 4.1600 (3.9880)	grad_norm 1.2201 (1.1375)	
[2022-01-18 23:38:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1070/1251]	eta 0:06:38 lr 0.000944	time 2.1335 (2.2017)	loss 3.5238 (3.9875)	grad_norm 1.1856 (1.1369)	
[2022-01-18 23:39:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1080/1251]	eta 0:06:16 lr 0.000944	time 2.4162 (2.2025)	loss 4.4557 (3.9868)	grad_norm 1.0450 (1.1367)	
[2022-01-18 23:39:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1090/1251]	eta 0:05:54 lr 0.000944	time 2.7095 (2.2033)	loss 4.2285 (3.9879)	grad_norm 1.5442 (1.1370)	
[2022-01-18 23:39:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1100/1251]	eta 0:05:32 lr 0.000944	time 2.0570 (2.2027)	loss 3.0699 (3.9859)	grad_norm 1.0929 (1.1374)	
[2022-01-18 23:40:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1110/1251]	eta 0:05:10 lr 0.000944	time 1.9435 (2.2008)	loss 3.8723 (3.9846)	grad_norm 1.0394 (1.1371)	
[2022-01-18 23:40:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1120/1251]	eta 0:04:48 lr 0.000944	time 2.4681 (2.2000)	loss 4.2870 (3.9878)	grad_norm 1.2367 (1.1365)	
[2022-01-18 23:40:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1130/1251]	eta 0:04:25 lr 0.000944	time 2.1614 (2.1981)	loss 2.9498 (3.9858)	grad_norm 1.4687 (1.1374)	
[2022-01-18 23:41:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1140/1251]	eta 0:04:03 lr 0.000944	time 2.1674 (2.1964)	loss 3.8691 (3.9859)	grad_norm 1.0073 (1.1377)	
[2022-01-18 23:41:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1150/1251]	eta 0:03:41 lr 0.000944	time 1.9966 (2.1954)	loss 4.0144 (3.9855)	grad_norm 1.1413 (1.1378)	
[2022-01-18 23:41:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1160/1251]	eta 0:03:19 lr 0.000944	time 2.4713 (2.1943)	loss 2.9609 (3.9857)	grad_norm 1.0593 (1.1386)	
[2022-01-18 23:42:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1170/1251]	eta 0:02:57 lr 0.000944	time 1.8422 (2.1943)	loss 2.8216 (3.9825)	grad_norm 1.0252 (1.1386)	
[2022-01-18 23:42:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1180/1251]	eta 0:02:35 lr 0.000944	time 1.9287 (2.1949)	loss 4.2627 (3.9812)	grad_norm 1.1673 (1.1383)	
[2022-01-18 23:42:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1190/1251]	eta 0:02:13 lr 0.000944	time 2.5426 (2.1954)	loss 4.3934 (3.9808)	grad_norm 1.2459 (1.1390)	
[2022-01-18 23:43:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1200/1251]	eta 0:01:51 lr 0.000944	time 2.6562 (2.1960)	loss 4.6602 (3.9805)	grad_norm 0.9621 (1.1393)	
[2022-01-18 23:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1210/1251]	eta 0:01:30 lr 0.000944	time 2.5503 (2.1973)	loss 3.9119 (3.9800)	grad_norm 1.0197 (1.1392)	
[2022-01-18 23:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1220/1251]	eta 0:01:08 lr 0.000944	time 2.3263 (2.1999)	loss 3.8171 (3.9805)	grad_norm 1.1905 (1.1389)	
[2022-01-18 23:44:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1230/1251]	eta 0:00:46 lr 0.000944	time 1.8425 (2.2003)	loss 3.0688 (3.9791)	grad_norm 1.0489 (1.1387)	
[2022-01-18 23:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1240/1251]	eta 0:00:24 lr 0.000944	time 1.8230 (2.1980)	loss 4.0322 (3.9808)	grad_norm 1.2152 (1.1383)	
[2022-01-18 23:45:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [45/300][1250/1251]	eta 0:00:02 lr 0.000944	time 1.2122 (2.1913)	loss 4.2799 (3.9803)	grad_norm 1.1087 (1.1384)	
[2022-01-18 23:45:03 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 45 training takes 0:45:41
[2022-01-18 23:45:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.856 (18.856)	Loss 1.2752 (1.2752)	Acc@1 71.680 (71.680)	Acc@5 90.234 (90.234)	
[2022-01-18 23:45:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.308 (3.502)	Loss 1.2499 (1.3324)	Acc@1 72.949 (70.020)	Acc@5 90.820 (89.870)	
[2022-01-18 23:46:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.945 (2.736)	Loss 1.3490 (1.3340)	Acc@1 70.703 (69.950)	Acc@5 89.258 (89.946)	
[2022-01-18 23:46:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.586 (2.341)	Loss 1.3890 (1.3403)	Acc@1 70.508 (69.752)	Acc@5 87.988 (89.885)	
[2022-01-18 23:46:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.180 (2.238)	Loss 1.3740 (1.3472)	Acc@1 68.750 (69.507)	Acc@5 89.453 (89.753)	
[2022-01-18 23:46:42 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 69.424 Acc@5 89.672
[2022-01-18 23:46:42 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 69.4%
[2022-01-18 23:46:42 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 69.65%
[2022-01-18 23:47:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][0/1251]	eta 7:31:55 lr 0.000944	time 21.6748 (21.6748)	loss 2.8996 (2.8996)	grad_norm 0.9639 (0.9639)	
[2022-01-18 23:47:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][10/1251]	eta 1:27:54 lr 0.000944	time 2.2686 (4.2502)	loss 4.0115 (3.7016)	grad_norm 1.2400 (1.0408)	
[2022-01-18 23:47:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][20/1251]	eta 1:06:09 lr 0.000944	time 1.2403 (3.2245)	loss 4.0374 (3.7584)	grad_norm 1.1013 (1.0560)	
[2022-01-18 23:48:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][30/1251]	eta 1:00:22 lr 0.000944	time 1.5114 (2.9670)	loss 3.6137 (3.8627)	grad_norm 1.0405 (1.0372)	
[2022-01-18 23:48:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][40/1251]	eta 0:57:10 lr 0.000944	time 3.6366 (2.8331)	loss 4.2199 (3.9414)	grad_norm 0.9725 (1.0449)	
[2022-01-18 23:49:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][50/1251]	eta 0:54:27 lr 0.000944	time 3.0718 (2.7207)	loss 3.6250 (3.9633)	grad_norm 1.1274 (1.0497)	
[2022-01-18 23:49:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][60/1251]	eta 0:51:17 lr 0.000944	time 1.8964 (2.5843)	loss 4.8151 (4.0272)	grad_norm 1.1865 (1.0493)	
[2022-01-18 23:49:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][70/1251]	eta 0:49:24 lr 0.000944	time 2.1780 (2.5106)	loss 4.2247 (4.0522)	grad_norm 1.0219 (1.0659)	
[2022-01-18 23:50:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][80/1251]	eta 0:48:18 lr 0.000944	time 2.1538 (2.4751)	loss 3.1820 (4.0473)	grad_norm 1.0598 (1.0619)	
[2022-01-18 23:50:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][90/1251]	eta 0:47:28 lr 0.000943	time 2.8175 (2.4534)	loss 4.0888 (4.0737)	grad_norm 1.0778 (1.0716)	
[2022-01-18 23:50:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][100/1251]	eta 0:46:35 lr 0.000943	time 2.5380 (2.4285)	loss 4.3074 (4.0683)	grad_norm 1.0367 (1.0774)	
[2022-01-18 23:51:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][110/1251]	eta 0:45:30 lr 0.000943	time 1.7514 (2.3930)	loss 4.2479 (4.0347)	grad_norm 1.1093 (1.0827)	
[2022-01-18 23:51:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][120/1251]	eta 0:44:41 lr 0.000943	time 2.1933 (2.3711)	loss 4.0303 (4.0274)	grad_norm 1.0270 (1.0817)	
[2022-01-18 23:51:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][130/1251]	eta 0:44:01 lr 0.000943	time 2.5052 (2.3567)	loss 3.7666 (4.0251)	grad_norm 1.2352 (1.0820)	
[2022-01-18 23:52:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][140/1251]	eta 0:43:16 lr 0.000943	time 2.2113 (2.3374)	loss 4.6142 (4.0350)	grad_norm 1.6106 (1.0916)	
[2022-01-18 23:52:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][150/1251]	eta 0:42:33 lr 0.000943	time 2.1505 (2.3193)	loss 4.1169 (4.0386)	grad_norm 1.0708 (1.0923)	
[2022-01-18 23:52:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][160/1251]	eta 0:42:02 lr 0.000943	time 1.8811 (2.3119)	loss 4.0385 (4.0301)	grad_norm 1.3748 (1.0925)	
[2022-01-18 23:53:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][170/1251]	eta 0:41:43 lr 0.000943	time 3.0981 (2.3156)	loss 4.3639 (4.0211)	grad_norm 1.2814 (1.0945)	
[2022-01-18 23:53:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][180/1251]	eta 0:41:11 lr 0.000943	time 2.7011 (2.3080)	loss 4.3634 (4.0110)	grad_norm 1.1683 (1.0939)	
[2022-01-18 23:54:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][190/1251]	eta 0:40:42 lr 0.000943	time 1.7630 (2.3023)	loss 2.9199 (3.9976)	grad_norm 1.2025 (1.1004)	
[2022-01-18 23:54:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][200/1251]	eta 0:40:11 lr 0.000943	time 1.8832 (2.2943)	loss 4.3641 (4.0047)	grad_norm 1.1980 (1.1055)	
[2022-01-18 23:54:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][210/1251]	eta 0:39:44 lr 0.000943	time 2.4885 (2.2904)	loss 3.3582 (3.9977)	grad_norm 1.0928 (1.1059)	
[2022-01-18 23:55:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][220/1251]	eta 0:39:19 lr 0.000943	time 2.8239 (2.2886)	loss 4.0800 (4.0029)	grad_norm 1.2730 (1.1078)	
[2022-01-18 23:55:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][230/1251]	eta 0:38:46 lr 0.000943	time 2.2360 (2.2789)	loss 4.0289 (4.0037)	grad_norm 1.1025 (1.1089)	
[2022-01-18 23:55:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][240/1251]	eta 0:38:20 lr 0.000943	time 1.5406 (2.2753)	loss 4.3654 (4.0054)	grad_norm 1.0047 (1.1094)	
[2022-01-18 23:56:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][250/1251]	eta 0:37:59 lr 0.000943	time 2.4726 (2.2774)	loss 3.5326 (4.0071)	grad_norm 1.1356 (1.1092)	
[2022-01-18 23:56:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][260/1251]	eta 0:37:37 lr 0.000943	time 1.8995 (2.2781)	loss 3.1207 (4.0091)	grad_norm 1.1647 (1.1117)	
[2022-01-18 23:56:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][270/1251]	eta 0:37:07 lr 0.000943	time 1.7911 (2.2707)	loss 3.3331 (3.9963)	grad_norm 0.8673 (1.1120)	
[2022-01-18 23:57:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][280/1251]	eta 0:36:40 lr 0.000943	time 1.8663 (2.2658)	loss 3.1657 (3.9906)	grad_norm 1.4930 (1.1178)	
[2022-01-18 23:57:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][290/1251]	eta 0:36:15 lr 0.000943	time 2.3112 (2.2640)	loss 4.4735 (3.9932)	grad_norm 1.3726 (1.1206)	
[2022-01-18 23:58:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][300/1251]	eta 0:35:49 lr 0.000943	time 2.5525 (2.2601)	loss 4.2228 (3.9917)	grad_norm 1.0143 (1.1191)	
[2022-01-18 23:58:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][310/1251]	eta 0:35:23 lr 0.000943	time 1.5304 (2.2567)	loss 3.0127 (3.9831)	grad_norm 1.0927 (1.1172)	
[2022-01-18 23:58:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][320/1251]	eta 0:34:59 lr 0.000943	time 2.2074 (2.2552)	loss 3.5717 (3.9772)	grad_norm 1.1356 (1.1169)	
[2022-01-18 23:59:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][330/1251]	eta 0:34:37 lr 0.000943	time 2.6331 (2.2554)	loss 4.2676 (3.9644)	grad_norm 1.0519 (1.1178)	
[2022-01-18 23:59:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][340/1251]	eta 0:34:08 lr 0.000943	time 1.6020 (2.2482)	loss 4.4838 (3.9644)	grad_norm 1.1361 (1.1189)	
[2022-01-18 23:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][350/1251]	eta 0:33:42 lr 0.000943	time 1.7326 (2.2448)	loss 3.8025 (3.9653)	grad_norm 0.9672 (1.1185)	
[2022-01-19 00:00:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][360/1251]	eta 0:33:14 lr 0.000943	time 1.8993 (2.2389)	loss 3.9308 (3.9651)	grad_norm 1.0365 (1.1167)	
[2022-01-19 00:00:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][370/1251]	eta 0:32:53 lr 0.000943	time 1.6410 (2.2401)	loss 3.3147 (3.9614)	grad_norm 1.2946 (1.1169)	
[2022-01-19 00:00:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][380/1251]	eta 0:32:31 lr 0.000943	time 1.7493 (2.2406)	loss 4.1970 (3.9606)	grad_norm 1.0816 (1.1199)	
[2022-01-19 00:01:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][390/1251]	eta 0:32:10 lr 0.000943	time 1.5880 (2.2419)	loss 4.2142 (3.9576)	grad_norm 1.0551 (1.1206)	
[2022-01-19 00:01:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][400/1251]	eta 0:31:47 lr 0.000943	time 1.9140 (2.2409)	loss 4.4155 (3.9653)	grad_norm 1.2031 (1.1200)	
[2022-01-19 00:02:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][410/1251]	eta 0:31:23 lr 0.000943	time 1.8511 (2.2397)	loss 3.9790 (3.9651)	grad_norm 1.1553 (1.1204)	
[2022-01-19 00:02:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][420/1251]	eta 0:30:55 lr 0.000943	time 1.9031 (2.2334)	loss 4.7168 (3.9643)	grad_norm 1.0668 (1.1201)	
[2022-01-19 00:02:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][430/1251]	eta 0:30:32 lr 0.000943	time 1.8931 (2.2325)	loss 4.9844 (3.9653)	grad_norm 1.0742 (1.1216)	
[2022-01-19 00:03:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][440/1251]	eta 0:30:09 lr 0.000943	time 2.4776 (2.2318)	loss 4.0605 (3.9642)	grad_norm 1.6094 (1.1256)	
[2022-01-19 00:03:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][450/1251]	eta 0:29:48 lr 0.000943	time 2.1672 (2.2326)	loss 4.2286 (3.9612)	grad_norm 1.1716 (1.1261)	
[2022-01-19 00:03:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][460/1251]	eta 0:29:24 lr 0.000943	time 2.0502 (2.2310)	loss 3.8652 (3.9597)	grad_norm 1.1790 (1.1265)	
[2022-01-19 00:04:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][470/1251]	eta 0:29:00 lr 0.000943	time 1.7498 (2.2285)	loss 4.6421 (3.9623)	grad_norm 1.3766 (1.1274)	
[2022-01-19 00:04:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][480/1251]	eta 0:28:36 lr 0.000943	time 2.2979 (2.2267)	loss 3.9282 (3.9591)	grad_norm 0.9339 (1.1265)	
[2022-01-19 00:04:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][490/1251]	eta 0:28:13 lr 0.000943	time 2.4722 (2.2248)	loss 3.6280 (3.9611)	grad_norm 1.1814 (1.1261)	
[2022-01-19 00:05:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][500/1251]	eta 0:27:49 lr 0.000943	time 1.6634 (2.2225)	loss 4.8250 (3.9701)	grad_norm 0.9063 (1.1260)	
[2022-01-19 00:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][510/1251]	eta 0:27:24 lr 0.000943	time 1.9295 (2.2195)	loss 4.2362 (3.9740)	grad_norm 1.2659 (1.1262)	
[2022-01-19 00:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][520/1251]	eta 0:27:00 lr 0.000943	time 1.8089 (2.2169)	loss 3.9205 (3.9801)	grad_norm 1.0683 (1.1256)	
[2022-01-19 00:06:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][530/1251]	eta 0:26:38 lr 0.000943	time 1.9271 (2.2175)	loss 4.5720 (3.9840)	grad_norm 1.0902 (1.1265)	
[2022-01-19 00:06:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][540/1251]	eta 0:26:16 lr 0.000943	time 1.8618 (2.2168)	loss 3.7155 (3.9789)	grad_norm 1.0961 (1.1265)	
[2022-01-19 00:07:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][550/1251]	eta 0:25:55 lr 0.000943	time 2.4847 (2.2189)	loss 4.3360 (3.9794)	grad_norm 1.2627 (1.1282)	
[2022-01-19 00:07:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][560/1251]	eta 0:25:33 lr 0.000943	time 1.8155 (2.2192)	loss 4.6361 (3.9838)	grad_norm 1.0554 (1.1293)	
[2022-01-19 00:07:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][570/1251]	eta 0:25:09 lr 0.000943	time 1.8025 (2.2171)	loss 4.0332 (3.9847)	grad_norm 1.9343 (1.1314)	
[2022-01-19 00:08:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][580/1251]	eta 0:24:46 lr 0.000943	time 1.6959 (2.2150)	loss 4.0160 (3.9831)	grad_norm 1.1877 (1.1330)	
[2022-01-19 00:08:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][590/1251]	eta 0:24:24 lr 0.000943	time 2.2178 (2.2159)	loss 4.6893 (3.9829)	grad_norm 1.3899 (1.1334)	
[2022-01-19 00:08:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][600/1251]	eta 0:24:01 lr 0.000943	time 2.2269 (2.2144)	loss 3.7698 (3.9801)	grad_norm 1.0488 (1.1336)	
[2022-01-19 00:09:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][610/1251]	eta 0:23:39 lr 0.000942	time 2.1167 (2.2144)	loss 4.0296 (3.9751)	grad_norm 0.9716 (1.1336)	
[2022-01-19 00:09:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][620/1251]	eta 0:23:16 lr 0.000942	time 2.2095 (2.2136)	loss 2.5868 (3.9736)	grad_norm 1.1770 (1.1336)	
[2022-01-19 00:10:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][630/1251]	eta 0:22:55 lr 0.000942	time 2.3018 (2.2145)	loss 4.5266 (3.9698)	grad_norm 1.1547 (1.1329)	
[2022-01-19 00:10:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][640/1251]	eta 0:22:33 lr 0.000942	time 2.7961 (2.2154)	loss 4.3913 (3.9738)	grad_norm 1.1189 (1.1312)	
[2022-01-19 00:10:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][650/1251]	eta 0:22:11 lr 0.000942	time 1.7190 (2.2151)	loss 3.7616 (3.9709)	grad_norm 1.2223 (1.1298)	
[2022-01-19 00:11:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][660/1251]	eta 0:21:47 lr 0.000942	time 2.1866 (2.2130)	loss 4.5209 (3.9750)	grad_norm 1.1304 (1.1286)	
[2022-01-19 00:11:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][670/1251]	eta 0:21:23 lr 0.000942	time 2.2067 (2.2096)	loss 3.8303 (3.9735)	grad_norm 0.8823 (1.1281)	
[2022-01-19 00:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][680/1251]	eta 0:20:59 lr 0.000942	time 1.8738 (2.2062)	loss 4.5409 (3.9750)	grad_norm 1.1432 (1.1298)	
[2022-01-19 00:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][690/1251]	eta 0:20:38 lr 0.000942	time 2.4908 (2.2070)	loss 4.4788 (3.9764)	grad_norm 0.9188 (1.1285)	
[2022-01-19 00:12:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][700/1251]	eta 0:20:15 lr 0.000942	time 2.8071 (2.2053)	loss 3.9496 (3.9723)	grad_norm 1.3792 (1.1294)	
[2022-01-19 00:12:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][710/1251]	eta 0:19:52 lr 0.000942	time 1.8727 (2.2040)	loss 4.2593 (3.9711)	grad_norm 0.9785 (1.1295)	
[2022-01-19 00:13:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][720/1251]	eta 0:19:31 lr 0.000942	time 2.5384 (2.2061)	loss 3.7000 (3.9732)	grad_norm 1.0701 (1.1297)	
[2022-01-19 00:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][730/1251]	eta 0:19:09 lr 0.000942	time 2.7635 (2.2073)	loss 4.7985 (3.9752)	grad_norm 1.1124 (1.1296)	
[2022-01-19 00:14:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][740/1251]	eta 0:18:49 lr 0.000942	time 3.3523 (2.2111)	loss 3.8362 (3.9739)	grad_norm 1.0884 (1.1292)	
[2022-01-19 00:14:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][750/1251]	eta 0:18:28 lr 0.000942	time 2.1576 (2.2123)	loss 4.6560 (3.9708)	grad_norm 1.2041 (1.1296)	
[2022-01-19 00:14:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][760/1251]	eta 0:18:06 lr 0.000942	time 2.1197 (2.2136)	loss 2.9544 (3.9734)	grad_norm 1.4799 (1.1308)	
[2022-01-19 00:15:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][770/1251]	eta 0:17:43 lr 0.000942	time 2.1335 (2.2119)	loss 4.0623 (3.9758)	grad_norm 1.0059 (1.1296)	
[2022-01-19 00:15:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][780/1251]	eta 0:17:19 lr 0.000942	time 1.9505 (2.2073)	loss 4.3815 (3.9782)	grad_norm 1.0748 (1.1299)	
[2022-01-19 00:15:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][790/1251]	eta 0:16:56 lr 0.000942	time 2.1211 (2.2049)	loss 4.3575 (3.9799)	grad_norm 1.0516 (1.1292)	
[2022-01-19 00:16:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][800/1251]	eta 0:16:33 lr 0.000942	time 1.8836 (2.2030)	loss 4.2439 (3.9781)	grad_norm 1.1810 (1.1286)	
[2022-01-19 00:16:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][810/1251]	eta 0:16:11 lr 0.000942	time 2.0094 (2.2025)	loss 3.6148 (3.9752)	grad_norm 0.8444 (1.1286)	
[2022-01-19 00:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][820/1251]	eta 0:15:49 lr 0.000942	time 2.5671 (2.2027)	loss 4.3300 (3.9745)	grad_norm 1.4897 (1.1294)	
[2022-01-19 00:17:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][830/1251]	eta 0:15:27 lr 0.000942	time 2.6067 (2.2032)	loss 3.5666 (3.9715)	grad_norm 1.0656 (1.1287)	
[2022-01-19 00:17:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][840/1251]	eta 0:15:05 lr 0.000942	time 1.9921 (2.2039)	loss 4.7251 (3.9735)	grad_norm 1.0526 (1.1283)	
[2022-01-19 00:17:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][850/1251]	eta 0:14:44 lr 0.000942	time 2.9033 (2.2048)	loss 4.5927 (3.9703)	grad_norm 1.1368 (1.1288)	
[2022-01-19 00:18:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][860/1251]	eta 0:14:22 lr 0.000942	time 2.6307 (2.2060)	loss 4.7130 (3.9679)	grad_norm 1.2474 (1.1302)	
[2022-01-19 00:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][870/1251]	eta 0:14:00 lr 0.000942	time 2.7047 (2.2072)	loss 3.7670 (3.9665)	grad_norm 1.0734 (1.1304)	
[2022-01-19 00:19:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][880/1251]	eta 0:13:37 lr 0.000942	time 1.7981 (2.2045)	loss 4.1396 (3.9642)	grad_norm 1.0030 (1.1306)	
[2022-01-19 00:19:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][890/1251]	eta 0:13:15 lr 0.000942	time 2.0472 (2.2032)	loss 4.7053 (3.9700)	grad_norm 1.0103 (1.1302)	
[2022-01-19 00:19:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][900/1251]	eta 0:12:52 lr 0.000942	time 2.1704 (2.2022)	loss 4.1915 (3.9714)	grad_norm 0.9626 (1.1301)	
[2022-01-19 00:20:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][910/1251]	eta 0:12:30 lr 0.000942	time 2.2329 (2.2019)	loss 4.2886 (3.9700)	grad_norm 1.0511 (1.1310)	
[2022-01-19 00:20:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][920/1251]	eta 0:12:09 lr 0.000942	time 2.4215 (2.2037)	loss 4.1702 (3.9718)	grad_norm 1.0651 (1.1303)	
[2022-01-19 00:20:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][930/1251]	eta 0:11:47 lr 0.000942	time 1.9628 (2.2047)	loss 3.8689 (3.9729)	grad_norm 1.0502 (1.1297)	
[2022-01-19 00:21:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][940/1251]	eta 0:11:25 lr 0.000942	time 1.8453 (2.2043)	loss 2.8892 (3.9722)	grad_norm 1.0042 (1.1288)	
[2022-01-19 00:21:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][950/1251]	eta 0:11:03 lr 0.000942	time 1.9056 (2.2040)	loss 3.9266 (3.9740)	grad_norm 1.0097 (1.1281)	
[2022-01-19 00:22:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][960/1251]	eta 0:10:41 lr 0.000942	time 1.9135 (2.2049)	loss 4.4388 (3.9767)	grad_norm 1.1627 (1.1281)	
[2022-01-19 00:22:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][970/1251]	eta 0:10:18 lr 0.000942	time 1.7351 (2.2027)	loss 3.4892 (3.9755)	grad_norm 1.6761 (1.1283)	
[2022-01-19 00:22:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][980/1251]	eta 0:09:56 lr 0.000942	time 1.9515 (2.2025)	loss 4.6373 (3.9741)	grad_norm 1.0357 (1.1277)	
[2022-01-19 00:23:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][990/1251]	eta 0:09:34 lr 0.000942	time 1.9222 (2.2026)	loss 2.9427 (3.9733)	grad_norm 1.2601 (1.1273)	
[2022-01-19 00:23:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1000/1251]	eta 0:09:12 lr 0.000942	time 1.5727 (2.2031)	loss 3.2000 (3.9720)	grad_norm 1.3210 (1.1262)	
[2022-01-19 00:23:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1010/1251]	eta 0:08:50 lr 0.000942	time 1.7560 (2.2021)	loss 4.1887 (3.9700)	grad_norm 1.1968 (1.1267)	
[2022-01-19 00:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1020/1251]	eta 0:08:28 lr 0.000942	time 1.8149 (2.2010)	loss 3.2798 (3.9679)	grad_norm 1.1558 (1.1271)	
[2022-01-19 00:24:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1030/1251]	eta 0:08:06 lr 0.000942	time 1.8633 (2.2010)	loss 3.6465 (3.9672)	grad_norm 1.1455 (1.1273)	
[2022-01-19 00:24:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1040/1251]	eta 0:07:44 lr 0.000942	time 2.4326 (2.2037)	loss 4.6129 (3.9684)	grad_norm 1.6681 (1.1274)	
[2022-01-19 00:25:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1050/1251]	eta 0:07:22 lr 0.000942	time 1.7949 (2.2029)	loss 4.3842 (3.9680)	grad_norm 1.6263 (1.1274)	
[2022-01-19 00:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1060/1251]	eta 0:07:00 lr 0.000942	time 1.9293 (2.2015)	loss 4.0972 (3.9667)	grad_norm 1.0305 (1.1275)	
[2022-01-19 00:26:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1070/1251]	eta 0:06:38 lr 0.000942	time 2.2664 (2.2018)	loss 4.3598 (3.9669)	grad_norm 1.0070 (1.1272)	
[2022-01-19 00:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1080/1251]	eta 0:06:16 lr 0.000942	time 2.3506 (2.2020)	loss 4.7839 (3.9646)	grad_norm 1.0537 (1.1268)	
[2022-01-19 00:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1090/1251]	eta 0:05:54 lr 0.000942	time 2.2416 (2.2016)	loss 3.9759 (3.9640)	grad_norm 1.1645 (1.1265)	
[2022-01-19 00:27:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1100/1251]	eta 0:05:32 lr 0.000942	time 1.6711 (2.2004)	loss 2.7640 (3.9624)	grad_norm 1.2407 (1.1269)	
[2022-01-19 00:27:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1110/1251]	eta 0:05:10 lr 0.000942	time 2.4682 (2.1998)	loss 4.2111 (3.9631)	grad_norm 1.0847 (1.1269)	
[2022-01-19 00:27:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1120/1251]	eta 0:04:48 lr 0.000942	time 1.7553 (2.1990)	loss 4.1618 (3.9629)	grad_norm 1.2196 (1.1280)	
[2022-01-19 00:28:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1130/1251]	eta 0:04:26 lr 0.000941	time 2.7869 (2.2007)	loss 4.1456 (3.9660)	grad_norm 1.1597 (1.1283)	
[2022-01-19 00:28:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1140/1251]	eta 0:04:04 lr 0.000941	time 2.1322 (2.1995)	loss 4.3126 (3.9662)	grad_norm 0.9364 (1.1277)	
[2022-01-19 00:28:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1150/1251]	eta 0:03:42 lr 0.000941	time 2.4956 (2.1984)	loss 4.4099 (3.9672)	grad_norm 1.0795 (1.1276)	
[2022-01-19 00:29:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1160/1251]	eta 0:03:20 lr 0.000941	time 2.1180 (2.1988)	loss 4.1660 (3.9683)	grad_norm 1.0925 (1.1275)	
[2022-01-19 00:29:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1170/1251]	eta 0:02:58 lr 0.000941	time 2.1558 (2.1997)	loss 4.0576 (3.9686)	grad_norm 1.1359 (1.1272)	
[2022-01-19 00:30:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1180/1251]	eta 0:02:36 lr 0.000941	time 1.9133 (2.2010)	loss 4.3085 (3.9674)	grad_norm 1.0321 (1.1269)	
[2022-01-19 00:30:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1190/1251]	eta 0:02:14 lr 0.000941	time 2.1821 (2.2011)	loss 3.8153 (3.9665)	grad_norm 1.3239 (1.1283)	
[2022-01-19 00:30:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1200/1251]	eta 0:01:52 lr 0.000941	time 2.4277 (2.2002)	loss 4.4953 (3.9663)	grad_norm 1.0795 (1.1276)	
[2022-01-19 00:31:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1210/1251]	eta 0:01:30 lr 0.000941	time 1.6956 (2.1983)	loss 4.5688 (3.9679)	grad_norm 1.0143 (1.1271)	
[2022-01-19 00:31:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1220/1251]	eta 0:01:08 lr 0.000941	time 2.4004 (2.1966)	loss 3.6716 (3.9680)	grad_norm 1.0831 (1.1266)	
[2022-01-19 00:31:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1230/1251]	eta 0:00:46 lr 0.000941	time 1.9316 (2.1954)	loss 4.2710 (3.9689)	grad_norm 0.9673 (1.1261)	
[2022-01-19 00:32:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1240/1251]	eta 0:00:24 lr 0.000941	time 2.2877 (2.1960)	loss 3.4138 (3.9697)	grad_norm 0.9976 (1.1263)	
[2022-01-19 00:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [46/300][1250/1251]	eta 0:00:02 lr 0.000941	time 1.1669 (2.1908)	loss 4.1387 (3.9707)	grad_norm 1.2776 (1.1265)	
[2022-01-19 00:32:24 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 46 training takes 0:45:41
[2022-01-19 00:32:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 20.062 (20.062)	Loss 1.3609 (1.3609)	Acc@1 69.824 (69.824)	Acc@5 89.746 (89.746)	
[2022-01-19 00:32:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.254 (3.228)	Loss 1.3023 (1.3271)	Acc@1 70.996 (69.815)	Acc@5 89.648 (89.782)	
[2022-01-19 00:33:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.514 (2.527)	Loss 1.3483 (1.3252)	Acc@1 68.945 (69.666)	Acc@5 89.160 (89.816)	
[2022-01-19 00:33:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.340 (2.324)	Loss 1.3552 (1.3242)	Acc@1 69.824 (69.859)	Acc@5 89.160 (89.774)	
[2022-01-19 00:33:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.777 (2.175)	Loss 1.3691 (1.3283)	Acc@1 68.750 (69.691)	Acc@5 89.160 (89.741)	
[2022-01-19 00:34:00 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 69.576 Acc@5 89.708
[2022-01-19 00:34:00 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 69.6%
[2022-01-19 00:34:00 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 69.65%
[2022-01-19 00:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][0/1251]	eta 7:32:25 lr 0.000941	time 21.6989 (21.6989)	loss 4.5953 (4.5953)	grad_norm 1.2008 (1.2008)	
[2022-01-19 00:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][10/1251]	eta 1:24:50 lr 0.000941	time 2.1548 (4.1020)	loss 4.5597 (4.0885)	grad_norm 1.4734 (1.2242)	
[2022-01-19 00:35:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][20/1251]	eta 1:06:30 lr 0.000941	time 1.7382 (3.2416)	loss 3.5090 (3.8914)	grad_norm 1.1750 (1.1821)	
[2022-01-19 00:35:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][30/1251]	eta 0:58:31 lr 0.000941	time 1.6893 (2.8755)	loss 4.0561 (3.9229)	grad_norm 1.3077 (1.1658)	
[2022-01-19 00:35:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][40/1251]	eta 0:55:55 lr 0.000941	time 3.8985 (2.7707)	loss 3.8889 (3.8600)	grad_norm 0.9075 (1.1552)	
[2022-01-19 00:36:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][50/1251]	eta 0:53:27 lr 0.000941	time 2.5168 (2.6708)	loss 3.9306 (3.8670)	grad_norm 1.3220 (1.1569)	
[2022-01-19 00:36:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][60/1251]	eta 0:51:25 lr 0.000941	time 1.8461 (2.5907)	loss 4.7211 (3.8909)	grad_norm 1.1597 (1.1488)	
[2022-01-19 00:36:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][70/1251]	eta 0:49:33 lr 0.000941	time 1.5771 (2.5179)	loss 4.8595 (3.9210)	grad_norm 1.0647 (1.1488)	
[2022-01-19 00:37:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][80/1251]	eta 0:49:15 lr 0.000941	time 6.5625 (2.5239)	loss 4.2906 (3.9364)	grad_norm 1.0664 (1.1488)	
[2022-01-19 00:37:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][90/1251]	eta 0:47:52 lr 0.000941	time 1.8362 (2.4744)	loss 4.7623 (3.9676)	grad_norm 1.1290 (1.1478)	
[2022-01-19 00:38:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][100/1251]	eta 0:46:37 lr 0.000941	time 1.8924 (2.4304)	loss 3.4513 (3.9347)	grad_norm 1.0758 (1.1444)	
[2022-01-19 00:38:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][110/1251]	eta 0:45:27 lr 0.000941	time 1.8889 (2.3908)	loss 4.4853 (3.9293)	grad_norm 1.0093 (1.1431)	
[2022-01-19 00:38:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][120/1251]	eta 0:44:53 lr 0.000941	time 3.3647 (2.3814)	loss 4.4498 (3.9099)	grad_norm 1.2001 (1.1394)	
[2022-01-19 00:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][130/1251]	eta 0:44:13 lr 0.000941	time 2.2510 (2.3670)	loss 4.0575 (3.9256)	grad_norm 1.0541 (1.1381)	
[2022-01-19 00:39:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][140/1251]	eta 0:43:27 lr 0.000941	time 1.8508 (2.3472)	loss 3.4991 (3.9192)	grad_norm 0.9909 (1.1327)	
[2022-01-19 00:39:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][150/1251]	eta 0:42:53 lr 0.000941	time 1.9431 (2.3378)	loss 3.9948 (3.9114)	grad_norm 1.0579 (1.1336)	
[2022-01-19 00:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][160/1251]	eta 0:42:23 lr 0.000941	time 3.8023 (2.3317)	loss 4.6342 (3.9387)	grad_norm 0.9929 (1.1310)	
[2022-01-19 00:40:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][170/1251]	eta 0:41:46 lr 0.000941	time 1.8890 (2.3187)	loss 4.1665 (3.9507)	grad_norm 1.2616 (1.1305)	
[2022-01-19 00:40:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][180/1251]	eta 0:41:11 lr 0.000941	time 2.0320 (2.3075)	loss 4.6564 (3.9425)	grad_norm 1.3052 (1.1289)	
[2022-01-19 00:41:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][190/1251]	eta 0:40:51 lr 0.000941	time 3.1139 (2.3106)	loss 4.1176 (3.9517)	grad_norm 1.0984 (1.1242)	
[2022-01-19 00:41:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][200/1251]	eta 0:40:35 lr 0.000941	time 3.1501 (2.3176)	loss 4.2579 (3.9496)	grad_norm 1.1444 (1.1261)	
[2022-01-19 00:42:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][210/1251]	eta 0:40:03 lr 0.000941	time 1.8036 (2.3085)	loss 3.4618 (3.9399)	grad_norm 0.9473 (1.1249)	
[2022-01-19 00:42:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][220/1251]	eta 0:39:31 lr 0.000941	time 2.2238 (2.2998)	loss 3.9257 (3.9467)	grad_norm 1.1292 (1.1206)	
[2022-01-19 00:42:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][230/1251]	eta 0:38:59 lr 0.000941	time 2.9274 (2.2915)	loss 3.1926 (3.9400)	grad_norm 1.5533 (1.1213)	
[2022-01-19 00:43:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][240/1251]	eta 0:38:21 lr 0.000941	time 1.6110 (2.2761)	loss 4.0341 (3.9411)	grad_norm 0.9721 (1.1204)	
[2022-01-19 00:43:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][250/1251]	eta 0:37:48 lr 0.000941	time 1.9794 (2.2659)	loss 3.7605 (3.9520)	grad_norm 1.0491 (1.1229)	
[2022-01-19 00:43:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][260/1251]	eta 0:37:22 lr 0.000941	time 2.2679 (2.2625)	loss 4.2245 (3.9401)	grad_norm 1.0399 (1.1292)	
[2022-01-19 00:44:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][270/1251]	eta 0:36:58 lr 0.000941	time 2.5311 (2.2617)	loss 4.3200 (3.9375)	grad_norm 1.0119 (1.1269)	
[2022-01-19 00:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][280/1251]	eta 0:36:39 lr 0.000941	time 2.3797 (2.2650)	loss 4.5281 (3.9471)	grad_norm 1.0755 (1.1255)	
[2022-01-19 00:44:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][290/1251]	eta 0:36:16 lr 0.000941	time 2.4206 (2.2646)	loss 3.4966 (3.9459)	grad_norm 1.0709 (1.1234)	
[2022-01-19 00:45:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][300/1251]	eta 0:35:52 lr 0.000941	time 2.2425 (2.2632)	loss 4.2798 (3.9403)	grad_norm 1.0572 (1.1217)	
[2022-01-19 00:45:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][310/1251]	eta 0:35:23 lr 0.000941	time 2.1064 (2.2572)	loss 3.5361 (3.9359)	grad_norm 1.0879 (1.1227)	
[2022-01-19 00:46:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][320/1251]	eta 0:35:00 lr 0.000941	time 1.8729 (2.2558)	loss 3.4574 (3.9436)	grad_norm 1.2439 (1.1254)	
[2022-01-19 00:46:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][330/1251]	eta 0:34:37 lr 0.000941	time 1.9059 (2.2557)	loss 4.4494 (3.9525)	grad_norm 1.2423 (1.1259)	
[2022-01-19 00:46:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][340/1251]	eta 0:34:15 lr 0.000941	time 2.0610 (2.2564)	loss 3.5871 (3.9514)	grad_norm 1.0244 (1.1243)	
[2022-01-19 00:47:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][350/1251]	eta 0:33:47 lr 0.000941	time 2.0227 (2.2499)	loss 3.2407 (3.9473)	grad_norm 1.2019 (1.1246)	
[2022-01-19 00:47:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][360/1251]	eta 0:33:24 lr 0.000941	time 2.2537 (2.2498)	loss 3.8498 (3.9537)	grad_norm 1.2902 (1.1268)	
[2022-01-19 00:47:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][370/1251]	eta 0:33:00 lr 0.000941	time 1.9166 (2.2483)	loss 4.0755 (3.9533)	grad_norm 1.4410 (1.1256)	
[2022-01-19 00:48:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][380/1251]	eta 0:32:36 lr 0.000940	time 1.6794 (2.2459)	loss 3.2652 (3.9551)	grad_norm 1.0093 (1.1271)	
[2022-01-19 00:48:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][390/1251]	eta 0:32:12 lr 0.000940	time 2.8479 (2.2445)	loss 3.6367 (3.9459)	grad_norm 1.0828 (1.1276)	
[2022-01-19 00:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][400/1251]	eta 0:31:47 lr 0.000940	time 1.8492 (2.2414)	loss 4.3695 (3.9512)	grad_norm 1.0512 (1.1268)	
[2022-01-19 00:49:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][410/1251]	eta 0:31:25 lr 0.000940	time 2.0942 (2.2422)	loss 4.4329 (3.9540)	grad_norm 1.1537 (1.1272)	
[2022-01-19 00:49:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][420/1251]	eta 0:31:02 lr 0.000940	time 1.7591 (2.2410)	loss 4.4074 (3.9637)	grad_norm 0.9254 (1.1291)	
[2022-01-19 00:50:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][430/1251]	eta 0:30:41 lr 0.000940	time 3.4106 (2.2427)	loss 3.9342 (3.9673)	grad_norm 1.4301 (1.1287)	
[2022-01-19 00:50:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][440/1251]	eta 0:30:18 lr 0.000940	time 2.1093 (2.2421)	loss 4.3632 (3.9666)	grad_norm 1.0159 (1.1273)	
[2022-01-19 00:50:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][450/1251]	eta 0:29:56 lr 0.000940	time 2.5698 (2.2423)	loss 4.1907 (3.9618)	grad_norm 1.3109 (1.1278)	
[2022-01-19 00:51:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][460/1251]	eta 0:29:31 lr 0.000940	time 1.9011 (2.2398)	loss 3.8649 (3.9585)	grad_norm 1.4798 (1.1277)	
[2022-01-19 00:51:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][470/1251]	eta 0:29:07 lr 0.000940	time 2.8645 (2.2381)	loss 4.0789 (3.9618)	grad_norm 1.0541 (1.1296)	
[2022-01-19 00:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][480/1251]	eta 0:28:42 lr 0.000940	time 2.0040 (2.2344)	loss 3.1948 (3.9552)	grad_norm 1.0919 (1.1289)	
[2022-01-19 00:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][490/1251]	eta 0:28:19 lr 0.000940	time 2.1777 (2.2339)	loss 4.3606 (3.9521)	grad_norm 1.1373 (1.1285)	
[2022-01-19 00:52:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][500/1251]	eta 0:27:55 lr 0.000940	time 2.3172 (2.2314)	loss 3.6975 (3.9501)	grad_norm 0.9661 (1.1272)	
[2022-01-19 00:52:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][510/1251]	eta 0:27:30 lr 0.000940	time 1.8452 (2.2269)	loss 4.2370 (3.9544)	grad_norm 1.0858 (1.1284)	
[2022-01-19 00:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][520/1251]	eta 0:27:06 lr 0.000940	time 2.1695 (2.2248)	loss 4.7053 (3.9552)	grad_norm 1.0459 (1.1275)	
[2022-01-19 00:53:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][530/1251]	eta 0:26:44 lr 0.000940	time 2.0978 (2.2253)	loss 3.1875 (3.9569)	grad_norm 1.1042 (1.1270)	
[2022-01-19 00:54:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][540/1251]	eta 0:26:21 lr 0.000940	time 1.9169 (2.2247)	loss 3.2917 (3.9557)	grad_norm 1.0043 (1.1278)	
[2022-01-19 00:54:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][550/1251]	eta 0:26:00 lr 0.000940	time 2.8054 (2.2260)	loss 4.4343 (3.9600)	grad_norm 0.9476 (1.1289)	
[2022-01-19 00:54:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][560/1251]	eta 0:25:39 lr 0.000940	time 2.2131 (2.2283)	loss 4.3267 (3.9647)	grad_norm 1.0641 (1.1302)	
[2022-01-19 00:55:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][570/1251]	eta 0:25:18 lr 0.000940	time 1.5972 (2.2296)	loss 3.6153 (3.9673)	grad_norm 1.2396 (1.1324)	
[2022-01-19 00:55:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][580/1251]	eta 0:24:54 lr 0.000940	time 1.8717 (2.2277)	loss 3.5271 (3.9679)	grad_norm 1.2923 (1.1318)	
[2022-01-19 00:55:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][590/1251]	eta 0:24:28 lr 0.000940	time 1.9030 (2.2224)	loss 4.3736 (3.9690)	grad_norm 1.3988 (1.1319)	
[2022-01-19 00:56:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][600/1251]	eta 0:24:04 lr 0.000940	time 2.2259 (2.2189)	loss 3.8292 (3.9720)	grad_norm 1.0554 (1.1323)	
[2022-01-19 00:56:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][610/1251]	eta 0:23:40 lr 0.000940	time 2.1757 (2.2158)	loss 4.3193 (3.9726)	grad_norm 1.1336 (1.1315)	
[2022-01-19 00:56:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][620/1251]	eta 0:23:17 lr 0.000940	time 1.9974 (2.2145)	loss 3.3891 (3.9745)	grad_norm 1.3219 (1.1319)	
[2022-01-19 00:57:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][630/1251]	eta 0:22:55 lr 0.000940	time 2.1562 (2.2146)	loss 3.4479 (3.9759)	grad_norm 1.1299 (1.1316)	
[2022-01-19 00:57:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][640/1251]	eta 0:22:34 lr 0.000940	time 2.0520 (2.2161)	loss 4.4865 (3.9761)	grad_norm 1.4902 (1.1319)	
[2022-01-19 00:58:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][650/1251]	eta 0:22:11 lr 0.000940	time 2.0904 (2.2160)	loss 3.4451 (3.9783)	grad_norm 0.9258 (1.1311)	
[2022-01-19 00:58:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][660/1251]	eta 0:21:50 lr 0.000940	time 1.8541 (2.2176)	loss 4.0337 (3.9739)	grad_norm 1.1748 (1.1320)	
[2022-01-19 00:58:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][670/1251]	eta 0:21:28 lr 0.000940	time 1.9404 (2.2171)	loss 4.2038 (3.9701)	grad_norm 0.9151 (1.1321)	
[2022-01-19 00:59:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][680/1251]	eta 0:21:05 lr 0.000940	time 1.9081 (2.2171)	loss 4.1953 (3.9678)	grad_norm 1.1259 (1.1313)	
[2022-01-19 00:59:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][690/1251]	eta 0:20:43 lr 0.000940	time 2.1374 (2.2165)	loss 4.1700 (3.9665)	grad_norm 1.0135 (1.1300)	
[2022-01-19 00:59:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][700/1251]	eta 0:20:19 lr 0.000940	time 1.8706 (2.2140)	loss 4.2589 (3.9672)	grad_norm 1.4041 (1.1310)	
[2022-01-19 01:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][710/1251]	eta 0:20:01 lr 0.000940	time 6.9425 (2.2217)	loss 3.6183 (3.9692)	grad_norm 1.2481 (1.1329)	
[2022-01-19 01:00:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][720/1251]	eta 0:19:39 lr 0.000940	time 1.8138 (2.2220)	loss 4.4978 (3.9732)	grad_norm 1.1513 (1.1336)	
[2022-01-19 01:01:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][730/1251]	eta 0:19:17 lr 0.000940	time 1.6608 (2.2221)	loss 4.4423 (3.9758)	grad_norm 0.9888 (1.1350)	
[2022-01-19 01:01:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][740/1251]	eta 0:18:54 lr 0.000940	time 1.8226 (2.2199)	loss 4.1443 (3.9754)	grad_norm 1.0787 (1.1356)	
[2022-01-19 01:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][750/1251]	eta 0:18:31 lr 0.000940	time 3.2183 (2.2182)	loss 4.2605 (3.9727)	grad_norm 1.0448 (1.1380)	
[2022-01-19 01:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][760/1251]	eta 0:18:08 lr 0.000940	time 2.0078 (2.2164)	loss 3.8745 (3.9779)	grad_norm 1.1020 (1.1391)	
[2022-01-19 01:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][770/1251]	eta 0:17:45 lr 0.000940	time 2.9353 (2.2157)	loss 3.6550 (3.9772)	grad_norm 0.9174 (1.1380)	
[2022-01-19 01:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][780/1251]	eta 0:17:22 lr 0.000940	time 2.2818 (2.2130)	loss 4.7338 (3.9777)	grad_norm 0.9291 (1.1380)	
[2022-01-19 01:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][790/1251]	eta 0:17:00 lr 0.000940	time 2.2734 (2.2139)	loss 3.7325 (3.9760)	grad_norm 0.9557 (1.1373)	
[2022-01-19 01:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][800/1251]	eta 0:16:37 lr 0.000940	time 1.5102 (2.2122)	loss 4.4161 (3.9794)	grad_norm 1.2052 (1.1365)	
[2022-01-19 01:03:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][810/1251]	eta 0:16:15 lr 0.000940	time 2.2505 (2.2116)	loss 4.3601 (3.9788)	grad_norm 1.2394 (1.1363)	
[2022-01-19 01:04:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][820/1251]	eta 0:15:53 lr 0.000940	time 1.8909 (2.2113)	loss 3.4392 (3.9773)	grad_norm 1.0949 (1.1359)	
[2022-01-19 01:04:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][830/1251]	eta 0:15:31 lr 0.000940	time 3.0760 (2.2132)	loss 4.7887 (3.9796)	grad_norm 1.2964 (1.1358)	
[2022-01-19 01:05:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][840/1251]	eta 0:15:10 lr 0.000940	time 2.0768 (2.2144)	loss 4.1984 (3.9785)	grad_norm 1.1522 (1.1361)	
[2022-01-19 01:05:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][850/1251]	eta 0:14:48 lr 0.000940	time 2.5207 (2.2169)	loss 3.2031 (3.9773)	grad_norm 1.7542 (1.1374)	
[2022-01-19 01:05:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][860/1251]	eta 0:14:26 lr 0.000940	time 2.5878 (2.2174)	loss 3.1524 (3.9733)	grad_norm 0.8765 (1.1376)	
[2022-01-19 01:06:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][870/1251]	eta 0:14:03 lr 0.000940	time 1.7711 (2.2146)	loss 3.8876 (3.9714)	grad_norm 1.3534 (1.1371)	
[2022-01-19 01:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][880/1251]	eta 0:13:40 lr 0.000940	time 1.9755 (2.2117)	loss 4.3176 (3.9715)	grad_norm 1.0903 (1.1370)	
[2022-01-19 01:06:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][890/1251]	eta 0:13:17 lr 0.000939	time 2.2165 (2.2099)	loss 3.0946 (3.9701)	grad_norm 1.0818 (1.1370)	
[2022-01-19 01:07:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][900/1251]	eta 0:12:55 lr 0.000939	time 2.1705 (2.2103)	loss 2.7016 (3.9655)	grad_norm 0.9447 (1.1359)	
[2022-01-19 01:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][910/1251]	eta 0:12:33 lr 0.000939	time 1.8094 (2.2089)	loss 3.6249 (3.9656)	grad_norm 1.2843 (1.1364)	
[2022-01-19 01:07:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][920/1251]	eta 0:12:11 lr 0.000939	time 1.8933 (2.2088)	loss 4.3260 (3.9664)	grad_norm 1.2075 (1.1361)	
[2022-01-19 01:08:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][930/1251]	eta 0:11:49 lr 0.000939	time 3.2105 (2.2111)	loss 3.6480 (3.9653)	grad_norm 1.0824 (1.1360)	
[2022-01-19 01:08:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][940/1251]	eta 0:11:28 lr 0.000939	time 1.8931 (2.2127)	loss 4.0408 (3.9602)	grad_norm 1.4104 (1.1364)	
[2022-01-19 01:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][950/1251]	eta 0:11:06 lr 0.000939	time 2.0654 (2.2128)	loss 4.3507 (3.9633)	grad_norm 1.1726 (1.1363)	
[2022-01-19 01:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][960/1251]	eta 0:10:43 lr 0.000939	time 1.7922 (2.2128)	loss 4.6262 (3.9630)	grad_norm 1.0937 (1.1360)	
[2022-01-19 01:09:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][970/1251]	eta 0:10:21 lr 0.000939	time 3.2680 (2.2120)	loss 4.1517 (3.9623)	grad_norm 1.1722 (1.1359)	
[2022-01-19 01:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][980/1251]	eta 0:09:58 lr 0.000939	time 1.8207 (2.2092)	loss 3.6831 (3.9611)	grad_norm 0.9973 (1.1350)	
[2022-01-19 01:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][990/1251]	eta 0:09:36 lr 0.000939	time 2.2642 (2.2091)	loss 2.7496 (3.9595)	grad_norm 1.2479 (1.1357)	
[2022-01-19 01:10:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1000/1251]	eta 0:09:14 lr 0.000939	time 1.5947 (2.2086)	loss 4.5718 (3.9600)	grad_norm 1.0900 (1.1359)	
[2022-01-19 01:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1010/1251]	eta 0:08:52 lr 0.000939	time 3.5665 (2.2093)	loss 4.2886 (3.9636)	grad_norm 1.0602 (1.1360)	
[2022-01-19 01:11:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1020/1251]	eta 0:08:30 lr 0.000939	time 2.5701 (2.2093)	loss 4.7339 (3.9642)	grad_norm 1.1263 (1.1356)	
[2022-01-19 01:11:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1030/1251]	eta 0:08:07 lr 0.000939	time 2.2707 (2.2076)	loss 4.1454 (3.9649)	grad_norm 1.0249 (1.1350)	
[2022-01-19 01:12:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1040/1251]	eta 0:07:45 lr 0.000939	time 1.8303 (2.2065)	loss 3.7488 (3.9649)	grad_norm 1.1949 (1.1345)	
[2022-01-19 01:12:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1050/1251]	eta 0:07:23 lr 0.000939	time 2.8940 (2.2076)	loss 4.4623 (3.9626)	grad_norm 1.3957 (1.1352)	
[2022-01-19 01:13:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1060/1251]	eta 0:07:01 lr 0.000939	time 2.5767 (2.2079)	loss 4.3533 (3.9622)	grad_norm 1.2548 (1.1363)	
[2022-01-19 01:13:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1070/1251]	eta 0:06:39 lr 0.000939	time 2.1716 (2.2075)	loss 3.9416 (3.9643)	grad_norm 1.1220 (1.1360)	
[2022-01-19 01:13:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1080/1251]	eta 0:06:17 lr 0.000939	time 1.8728 (2.2067)	loss 4.4894 (3.9637)	grad_norm 0.9277 (1.1357)	
[2022-01-19 01:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1090/1251]	eta 0:05:55 lr 0.000939	time 2.9166 (2.2085)	loss 4.4262 (3.9637)	grad_norm 1.3101 (1.1356)	
[2022-01-19 01:14:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1100/1251]	eta 0:05:33 lr 0.000939	time 1.9062 (2.2072)	loss 4.4416 (3.9644)	grad_norm 1.1022 (1.1349)	
[2022-01-19 01:14:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1110/1251]	eta 0:05:11 lr 0.000939	time 1.6391 (2.2060)	loss 3.1017 (3.9645)	grad_norm 1.2709 (1.1354)	
[2022-01-19 01:15:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1120/1251]	eta 0:04:48 lr 0.000939	time 1.8318 (2.2051)	loss 3.1992 (3.9622)	grad_norm 1.1444 (1.1350)	
[2022-01-19 01:15:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1130/1251]	eta 0:04:27 lr 0.000939	time 3.1391 (2.2075)	loss 4.2082 (3.9620)	grad_norm 0.9644 (1.1344)	
[2022-01-19 01:15:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1140/1251]	eta 0:04:05 lr 0.000939	time 1.9624 (2.2077)	loss 3.5413 (3.9606)	grad_norm 1.0614 (1.1344)	
[2022-01-19 01:16:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1150/1251]	eta 0:03:42 lr 0.000939	time 1.9559 (2.2078)	loss 4.1279 (3.9632)	grad_norm 1.1382 (1.1340)	
[2022-01-19 01:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1160/1251]	eta 0:03:20 lr 0.000939	time 1.8759 (2.2070)	loss 4.4160 (3.9643)	grad_norm 1.6987 (1.1340)	
[2022-01-19 01:17:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1170/1251]	eta 0:02:58 lr 0.000939	time 5.5040 (2.2087)	loss 4.5947 (3.9655)	grad_norm 0.9802 (1.1334)	
[2022-01-19 01:17:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1180/1251]	eta 0:02:36 lr 0.000939	time 1.5192 (2.2075)	loss 4.4391 (3.9671)	grad_norm 1.0135 (1.1329)	
[2022-01-19 01:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1190/1251]	eta 0:02:14 lr 0.000939	time 2.5307 (2.2075)	loss 2.6197 (3.9642)	grad_norm 1.3451 (1.1328)	
[2022-01-19 01:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1200/1251]	eta 0:01:52 lr 0.000939	time 1.6299 (2.2063)	loss 4.1101 (3.9665)	grad_norm 1.0462 (1.1331)	
[2022-01-19 01:18:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1210/1251]	eta 0:01:30 lr 0.000939	time 3.6039 (2.2068)	loss 4.0043 (3.9645)	grad_norm 1.2624 (1.1330)	
[2022-01-19 01:18:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1220/1251]	eta 0:01:08 lr 0.000939	time 1.7929 (2.2061)	loss 4.4613 (3.9661)	grad_norm 1.0708 (1.1337)	
[2022-01-19 01:19:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1230/1251]	eta 0:00:46 lr 0.000939	time 2.5706 (2.2061)	loss 3.8095 (3.9652)	grad_norm 1.0801 (1.1341)	
[2022-01-19 01:19:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1240/1251]	eta 0:00:24 lr 0.000939	time 1.4667 (2.2045)	loss 3.5054 (3.9652)	grad_norm 1.1569 (1.1340)	
[2022-01-19 01:19:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [47/300][1250/1251]	eta 0:00:02 lr 0.000939	time 1.3019 (2.1995)	loss 3.4311 (3.9670)	grad_norm 1.0762 (1.1339)	
[2022-01-19 01:19:52 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 47 training takes 0:45:51
[2022-01-19 01:20:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.710 (18.710)	Loss 1.3986 (1.3986)	Acc@1 68.359 (68.359)	Acc@5 86.914 (86.914)	
[2022-01-19 01:20:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.946 (3.260)	Loss 1.3166 (1.3241)	Acc@1 71.094 (70.206)	Acc@5 89.941 (89.915)	
[2022-01-19 01:20:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.533 (2.518)	Loss 1.3990 (1.3295)	Acc@1 68.945 (69.908)	Acc@5 88.281 (89.746)	
[2022-01-19 01:21:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.650 (2.221)	Loss 1.2879 (1.3332)	Acc@1 69.238 (69.676)	Acc@5 89.746 (89.740)	
[2022-01-19 01:21:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.965 (2.120)	Loss 1.2982 (1.3368)	Acc@1 70.996 (69.603)	Acc@5 89.941 (89.665)	
[2022-01-19 01:21:27 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 69.582 Acc@5 89.666
[2022-01-19 01:21:27 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 69.6%
[2022-01-19 01:21:27 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 69.65%
[2022-01-19 01:21:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][0/1251]	eta 7:29:39 lr 0.000939	time 21.5664 (21.5664)	loss 4.3881 (4.3881)	grad_norm 1.3784 (1.3784)	
[2022-01-19 01:22:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][10/1251]	eta 1:22:30 lr 0.000939	time 2.2317 (3.9889)	loss 3.9406 (4.2316)	grad_norm 1.0416 (1.0916)	
[2022-01-19 01:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][20/1251]	eta 1:02:23 lr 0.000939	time 1.4875 (3.0410)	loss 3.9718 (4.0346)	grad_norm 1.1326 (1.1368)	
[2022-01-19 01:22:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][30/1251]	eta 0:56:59 lr 0.000939	time 1.6631 (2.8006)	loss 3.5443 (3.9830)	grad_norm 1.0698 (1.1232)	
[2022-01-19 01:23:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][40/1251]	eta 0:54:41 lr 0.000939	time 3.5830 (2.7097)	loss 4.5012 (4.0048)	grad_norm 1.0718 (1.1283)	
[2022-01-19 01:23:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][50/1251]	eta 0:53:25 lr 0.000939	time 2.8801 (2.6692)	loss 4.0451 (4.0023)	grad_norm 1.2097 (1.1296)	
[2022-01-19 01:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][60/1251]	eta 0:51:45 lr 0.000939	time 2.1894 (2.6076)	loss 3.8961 (3.9864)	grad_norm 0.9991 (1.1216)	
[2022-01-19 01:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][70/1251]	eta 0:49:38 lr 0.000939	time 1.6930 (2.5224)	loss 4.0126 (3.9996)	grad_norm 1.2063 (1.1351)	
[2022-01-19 01:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][80/1251]	eta 0:48:08 lr 0.000939	time 2.2887 (2.4670)	loss 3.1577 (3.9882)	grad_norm 1.5089 (1.1391)	
[2022-01-19 01:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][90/1251]	eta 0:47:16 lr 0.000939	time 2.0728 (2.4434)	loss 3.6529 (3.9980)	grad_norm 1.4396 (1.1449)	
[2022-01-19 01:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][100/1251]	eta 0:46:24 lr 0.000939	time 1.9701 (2.4189)	loss 3.0428 (3.9909)	grad_norm 1.0394 (1.1490)	
[2022-01-19 01:25:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][110/1251]	eta 0:45:32 lr 0.000939	time 2.2529 (2.3945)	loss 4.0826 (3.9945)	grad_norm 1.0284 (1.1394)	
[2022-01-19 01:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][120/1251]	eta 0:44:48 lr 0.000939	time 2.2581 (2.3773)	loss 3.2086 (3.9812)	grad_norm 1.3754 (1.1459)	
[2022-01-19 01:26:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][130/1251]	eta 0:44:05 lr 0.000939	time 2.4753 (2.3599)	loss 3.2545 (3.9761)	grad_norm 1.3208 (1.1443)	
[2022-01-19 01:26:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][140/1251]	eta 0:43:22 lr 0.000938	time 2.2988 (2.3428)	loss 4.5093 (3.9767)	grad_norm 1.0762 (1.1380)	
[2022-01-19 01:27:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][150/1251]	eta 0:42:41 lr 0.000938	time 1.6099 (2.3267)	loss 3.6074 (3.9552)	grad_norm 1.0162 (1.1395)	
[2022-01-19 01:27:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][160/1251]	eta 0:42:08 lr 0.000938	time 2.2850 (2.3175)	loss 3.9698 (3.9723)	grad_norm 1.0583 (1.1385)	
[2022-01-19 01:28:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][170/1251]	eta 0:41:44 lr 0.000938	time 2.8986 (2.3172)	loss 3.8374 (3.9904)	grad_norm 1.0128 (1.1402)	
[2022-01-19 01:28:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][180/1251]	eta 0:41:15 lr 0.000938	time 2.1717 (2.3113)	loss 3.8748 (3.9752)	grad_norm 1.1975 (1.1345)	
[2022-01-19 01:28:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][190/1251]	eta 0:40:43 lr 0.000938	time 1.8192 (2.3026)	loss 3.7503 (3.9814)	grad_norm 0.9817 (1.1329)	
[2022-01-19 01:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][200/1251]	eta 0:40:11 lr 0.000938	time 1.9300 (2.2942)	loss 4.4101 (3.9797)	grad_norm 0.9634 (1.1320)	
[2022-01-19 01:29:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][210/1251]	eta 0:39:41 lr 0.000938	time 3.0641 (2.2878)	loss 4.2041 (3.9754)	grad_norm 1.0613 (1.1287)	
[2022-01-19 01:29:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][220/1251]	eta 0:39:19 lr 0.000938	time 3.0564 (2.2885)	loss 2.7038 (3.9689)	grad_norm 1.0349 (1.1290)	
[2022-01-19 01:30:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][230/1251]	eta 0:38:56 lr 0.000938	time 1.9688 (2.2880)	loss 3.5923 (3.9651)	grad_norm 0.9673 (1.1245)	
[2022-01-19 01:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][240/1251]	eta 0:38:32 lr 0.000938	time 2.2842 (2.2871)	loss 4.0753 (3.9573)	grad_norm 1.0510 (1.1221)	
[2022-01-19 01:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][250/1251]	eta 0:38:08 lr 0.000938	time 2.7028 (2.2863)	loss 3.4948 (3.9642)	grad_norm 1.1524 (1.1207)	
[2022-01-19 01:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][260/1251]	eta 0:37:35 lr 0.000938	time 1.8162 (2.2756)	loss 3.0198 (3.9561)	grad_norm 1.2094 (1.1238)	
[2022-01-19 01:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][270/1251]	eta 0:36:56 lr 0.000938	time 1.8202 (2.2596)	loss 4.6095 (3.9516)	grad_norm 0.9703 (1.1250)	
[2022-01-19 01:32:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][280/1251]	eta 0:36:28 lr 0.000938	time 2.2422 (2.2534)	loss 4.2753 (3.9515)	grad_norm 1.0101 (1.1255)	
[2022-01-19 01:32:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][290/1251]	eta 0:35:59 lr 0.000938	time 2.1635 (2.2468)	loss 4.3929 (3.9453)	grad_norm 1.2175 (1.1286)	
[2022-01-19 01:32:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][300/1251]	eta 0:35:29 lr 0.000938	time 1.9098 (2.2396)	loss 4.3983 (3.9523)	grad_norm 1.0934 (1.1285)	
[2022-01-19 01:33:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][310/1251]	eta 0:35:04 lr 0.000938	time 2.4706 (2.2367)	loss 2.8706 (3.9501)	grad_norm 1.2645 (1.1295)	
[2022-01-19 01:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][320/1251]	eta 0:34:41 lr 0.000938	time 2.2021 (2.2359)	loss 3.6931 (3.9535)	grad_norm 1.0257 (1.1289)	
[2022-01-19 01:33:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][330/1251]	eta 0:34:22 lr 0.000938	time 2.5913 (2.2400)	loss 3.7785 (3.9452)	grad_norm 1.1209 (1.1289)	
[2022-01-19 01:34:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][340/1251]	eta 0:34:03 lr 0.000938	time 2.2386 (2.2430)	loss 3.9375 (3.9465)	grad_norm 0.9707 (1.1292)	
[2022-01-19 01:34:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][350/1251]	eta 0:33:42 lr 0.000938	time 2.2458 (2.2450)	loss 3.5905 (3.9468)	grad_norm 1.0850 (1.1285)	
[2022-01-19 01:34:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][360/1251]	eta 0:33:17 lr 0.000938	time 1.7344 (2.2413)	loss 4.0802 (3.9462)	grad_norm 1.0640 (1.1294)	
[2022-01-19 01:35:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][370/1251]	eta 0:32:55 lr 0.000938	time 1.9076 (2.2420)	loss 4.6246 (3.9447)	grad_norm 1.5994 (1.1311)	
[2022-01-19 01:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][380/1251]	eta 0:32:30 lr 0.000938	time 1.8012 (2.2395)	loss 4.1771 (3.9393)	grad_norm 1.0852 (1.1324)	
[2022-01-19 01:36:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][390/1251]	eta 0:32:08 lr 0.000938	time 3.0814 (2.2396)	loss 2.7446 (3.9478)	grad_norm 1.6771 (1.1341)	
[2022-01-19 01:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][400/1251]	eta 0:31:42 lr 0.000938	time 1.6052 (2.2360)	loss 4.1564 (3.9469)	grad_norm 1.1721 (1.1344)	
[2022-01-19 01:36:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][410/1251]	eta 0:31:18 lr 0.000938	time 1.8916 (2.2339)	loss 2.7681 (3.9447)	grad_norm 1.3307 (1.1349)	
[2022-01-19 01:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][420/1251]	eta 0:30:55 lr 0.000938	time 2.1328 (2.2326)	loss 3.4338 (3.9483)	grad_norm 1.0020 (1.1350)	
[2022-01-19 01:37:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][430/1251]	eta 0:30:35 lr 0.000938	time 3.2225 (2.2356)	loss 4.4661 (3.9428)	grad_norm 1.0102 (1.1321)	
[2022-01-19 01:37:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][440/1251]	eta 0:30:12 lr 0.000938	time 1.7912 (2.2345)	loss 3.8865 (3.9427)	grad_norm 1.5096 (1.1323)	
[2022-01-19 01:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][450/1251]	eta 0:29:49 lr 0.000938	time 2.0201 (2.2343)	loss 3.4878 (3.9379)	grad_norm 0.9789 (1.1316)	
[2022-01-19 01:38:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][460/1251]	eta 0:29:26 lr 0.000938	time 2.1308 (2.2335)	loss 4.3224 (3.9353)	grad_norm 1.2229 (1.1312)	
[2022-01-19 01:38:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][470/1251]	eta 0:29:05 lr 0.000938	time 2.8314 (2.2348)	loss 4.0193 (3.9403)	grad_norm 1.0592 (1.1292)	
[2022-01-19 01:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][480/1251]	eta 0:28:41 lr 0.000938	time 1.9504 (2.2325)	loss 4.3343 (3.9431)	grad_norm 1.3466 (1.1285)	
[2022-01-19 01:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][490/1251]	eta 0:28:15 lr 0.000938	time 1.6504 (2.2276)	loss 4.1881 (3.9484)	grad_norm 1.1520 (1.1286)	
[2022-01-19 01:40:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][500/1251]	eta 0:27:51 lr 0.000938	time 2.0587 (2.2255)	loss 4.0236 (3.9559)	grad_norm 1.0395 (1.1281)	
[2022-01-19 01:40:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][510/1251]	eta 0:27:27 lr 0.000938	time 2.2988 (2.2229)	loss 4.4519 (3.9579)	grad_norm 1.1774 (1.1266)	
[2022-01-19 01:40:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][520/1251]	eta 0:27:04 lr 0.000938	time 2.7667 (2.2223)	loss 2.8923 (3.9521)	grad_norm 1.1301 (1.1249)	
[2022-01-19 01:41:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][530/1251]	eta 0:26:40 lr 0.000938	time 1.5435 (2.2195)	loss 4.5183 (3.9511)	grad_norm 1.1725 (1.1241)	
[2022-01-19 01:41:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][540/1251]	eta 0:26:19 lr 0.000938	time 1.9656 (2.2213)	loss 4.1766 (3.9571)	grad_norm 1.0938 (1.1248)	
[2022-01-19 01:41:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][550/1251]	eta 0:25:55 lr 0.000938	time 2.1938 (2.2190)	loss 2.9503 (3.9584)	grad_norm 0.9329 (1.1239)	
[2022-01-19 01:42:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][560/1251]	eta 0:25:33 lr 0.000938	time 1.7947 (2.2196)	loss 4.7786 (3.9584)	grad_norm 1.3950 (1.1245)	
[2022-01-19 01:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][570/1251]	eta 0:25:12 lr 0.000938	time 2.4736 (2.2206)	loss 4.7355 (3.9620)	grad_norm 1.3477 (1.1256)	
[2022-01-19 01:42:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][580/1251]	eta 0:24:49 lr 0.000938	time 2.8982 (2.2194)	loss 3.3889 (3.9589)	grad_norm 1.1106 (1.1267)	
[2022-01-19 01:43:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][590/1251]	eta 0:24:26 lr 0.000938	time 2.4028 (2.2191)	loss 3.6171 (3.9630)	grad_norm 1.3079 (1.1288)	
[2022-01-19 01:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][600/1251]	eta 0:24:03 lr 0.000938	time 1.6288 (2.2180)	loss 4.0672 (3.9644)	grad_norm 1.0718 (1.1294)	
[2022-01-19 01:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][610/1251]	eta 0:23:41 lr 0.000938	time 1.8037 (2.2183)	loss 4.3635 (3.9646)	grad_norm 1.0987 (1.1292)	
[2022-01-19 01:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][620/1251]	eta 0:23:18 lr 0.000938	time 2.1454 (2.2169)	loss 4.4270 (3.9653)	grad_norm 0.9184 (1.1292)	
[2022-01-19 01:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][630/1251]	eta 0:22:55 lr 0.000938	time 2.8689 (2.2153)	loss 3.7741 (3.9665)	grad_norm 1.0292 (1.1312)	
[2022-01-19 01:45:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][640/1251]	eta 0:22:33 lr 0.000937	time 1.8935 (2.2154)	loss 4.6655 (3.9697)	grad_norm 1.1791 (1.1291)	
[2022-01-19 01:45:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][650/1251]	eta 0:22:12 lr 0.000937	time 1.9022 (2.2167)	loss 3.3533 (3.9699)	grad_norm 1.0140 (1.1287)	
[2022-01-19 01:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][660/1251]	eta 0:21:49 lr 0.000937	time 1.5357 (2.2158)	loss 4.6859 (3.9674)	grad_norm 1.1262 (1.1295)	
[2022-01-19 01:46:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][670/1251]	eta 0:21:26 lr 0.000937	time 2.5288 (2.2148)	loss 3.6818 (3.9672)	grad_norm 1.1737 (1.1308)	
[2022-01-19 01:46:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][680/1251]	eta 0:21:02 lr 0.000937	time 1.7932 (2.2110)	loss 3.9077 (3.9658)	grad_norm 0.9050 (1.1317)	
[2022-01-19 01:46:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][690/1251]	eta 0:20:39 lr 0.000937	time 2.0919 (2.2099)	loss 4.6132 (3.9704)	grad_norm 1.0950 (1.1309)	
[2022-01-19 01:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][700/1251]	eta 0:20:17 lr 0.000937	time 2.0254 (2.2097)	loss 3.9286 (3.9733)	grad_norm 1.3148 (1.1318)	
[2022-01-19 01:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][710/1251]	eta 0:19:55 lr 0.000937	time 2.2404 (2.2107)	loss 4.2180 (3.9766)	grad_norm 0.9790 (1.1305)	
[2022-01-19 01:48:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][720/1251]	eta 0:19:33 lr 0.000937	time 2.4558 (2.2109)	loss 3.0101 (3.9714)	grad_norm 1.0806 (1.1298)	
[2022-01-19 01:48:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][730/1251]	eta 0:19:12 lr 0.000937	time 1.9365 (2.2113)	loss 4.3800 (3.9705)	grad_norm 1.4148 (1.1300)	
[2022-01-19 01:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][740/1251]	eta 0:18:51 lr 0.000937	time 2.7823 (2.2138)	loss 4.3806 (3.9707)	grad_norm 1.3706 (1.1307)	
[2022-01-19 01:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][750/1251]	eta 0:18:30 lr 0.000937	time 2.2944 (2.2160)	loss 4.5368 (3.9717)	grad_norm 1.0868 (1.1312)	
[2022-01-19 01:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][760/1251]	eta 0:18:07 lr 0.000937	time 1.9007 (2.2145)	loss 4.3001 (3.9725)	grad_norm 1.0413 (1.1305)	
[2022-01-19 01:49:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][770/1251]	eta 0:17:42 lr 0.000937	time 1.8614 (2.2098)	loss 3.4516 (3.9717)	grad_norm 1.1452 (1.1306)	
[2022-01-19 01:50:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][780/1251]	eta 0:17:18 lr 0.000937	time 1.6855 (2.2058)	loss 4.4437 (3.9737)	grad_norm 1.1636 (1.1316)	
[2022-01-19 01:50:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][790/1251]	eta 0:16:56 lr 0.000937	time 2.1713 (2.2052)	loss 4.5193 (3.9774)	grad_norm 1.3691 (1.1325)	
[2022-01-19 01:50:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][800/1251]	eta 0:16:34 lr 0.000937	time 1.8145 (2.2053)	loss 4.0758 (3.9796)	grad_norm 1.0162 (1.1334)	
[2022-01-19 01:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][810/1251]	eta 0:16:12 lr 0.000937	time 2.1107 (2.2056)	loss 2.9256 (3.9755)	grad_norm 1.0905 (1.1345)	
[2022-01-19 01:51:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][820/1251]	eta 0:15:50 lr 0.000937	time 2.1588 (2.2059)	loss 4.3070 (3.9742)	grad_norm 1.6673 (1.1369)	
[2022-01-19 01:52:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][830/1251]	eta 0:15:28 lr 0.000937	time 1.9666 (2.2064)	loss 4.1510 (3.9747)	grad_norm 0.9665 (1.1372)	
[2022-01-19 01:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][840/1251]	eta 0:15:08 lr 0.000937	time 2.8510 (2.2092)	loss 4.0113 (3.9742)	grad_norm 0.9468 (1.1365)	
[2022-01-19 01:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][850/1251]	eta 0:14:46 lr 0.000937	time 1.8861 (2.2107)	loss 3.4577 (3.9710)	grad_norm 1.1757 (1.1362)	
[2022-01-19 01:53:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][860/1251]	eta 0:14:23 lr 0.000937	time 1.9232 (2.2092)	loss 4.2744 (3.9736)	grad_norm 1.1835 (1.1361)	
[2022-01-19 01:53:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][870/1251]	eta 0:14:01 lr 0.000937	time 1.9097 (2.2077)	loss 3.8059 (3.9734)	grad_norm 1.0662 (1.1356)	
[2022-01-19 01:53:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][880/1251]	eta 0:13:38 lr 0.000937	time 1.9449 (2.2067)	loss 3.1781 (3.9762)	grad_norm 1.0518 (1.1356)	
[2022-01-19 01:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][890/1251]	eta 0:13:16 lr 0.000937	time 3.0872 (2.2060)	loss 4.2747 (3.9732)	grad_norm 1.2216 (1.1350)	
[2022-01-19 01:54:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][900/1251]	eta 0:12:54 lr 0.000937	time 1.7374 (2.2054)	loss 4.1917 (3.9742)	grad_norm 1.0249 (1.1357)	
[2022-01-19 01:54:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][910/1251]	eta 0:12:31 lr 0.000937	time 1.5930 (2.2040)	loss 3.0647 (3.9743)	grad_norm 0.9297 (1.1349)	
[2022-01-19 01:55:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][920/1251]	eta 0:12:09 lr 0.000937	time 1.9731 (2.2037)	loss 4.8603 (3.9732)	grad_norm 0.9964 (1.1339)	
[2022-01-19 01:55:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][930/1251]	eta 0:11:47 lr 0.000937	time 2.7842 (2.2042)	loss 3.6260 (3.9745)	grad_norm 0.9973 (1.1331)	
[2022-01-19 01:56:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][940/1251]	eta 0:11:25 lr 0.000937	time 2.4658 (2.2044)	loss 3.9622 (3.9768)	grad_norm 1.1806 (1.1347)	
[2022-01-19 01:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][950/1251]	eta 0:11:03 lr 0.000937	time 1.6433 (2.2040)	loss 4.2556 (3.9753)	grad_norm 1.0334 (1.1348)	
[2022-01-19 01:56:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][960/1251]	eta 0:10:41 lr 0.000937	time 2.1785 (2.2032)	loss 3.6843 (3.9726)	grad_norm 0.9633 (1.1350)	
[2022-01-19 01:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][970/1251]	eta 0:10:19 lr 0.000937	time 3.0945 (2.2061)	loss 4.5446 (3.9723)	grad_norm 1.0118 (1.1351)	
[2022-01-19 01:57:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][980/1251]	eta 0:09:57 lr 0.000937	time 2.2250 (2.2053)	loss 4.0821 (3.9723)	grad_norm 1.0223 (1.1350)	
[2022-01-19 01:57:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][990/1251]	eta 0:09:35 lr 0.000937	time 1.8530 (2.2051)	loss 3.9706 (3.9752)	grad_norm 1.2123 (1.1339)	
[2022-01-19 01:58:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1000/1251]	eta 0:09:13 lr 0.000937	time 1.8506 (2.2034)	loss 3.5859 (3.9738)	grad_norm 1.2456 (1.1344)	
[2022-01-19 01:58:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1010/1251]	eta 0:08:50 lr 0.000937	time 1.5590 (2.2013)	loss 4.5054 (3.9738)	grad_norm 1.0451 (1.1346)	
[2022-01-19 01:58:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1020/1251]	eta 0:08:28 lr 0.000937	time 1.8937 (2.1997)	loss 4.2472 (3.9727)	grad_norm 1.0980 (1.1349)	
[2022-01-19 01:59:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1030/1251]	eta 0:08:06 lr 0.000937	time 3.2343 (2.1999)	loss 4.7933 (3.9714)	grad_norm 1.3071 (1.1347)	
[2022-01-19 01:59:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1040/1251]	eta 0:07:44 lr 0.000937	time 2.1838 (2.2003)	loss 3.2583 (3.9707)	grad_norm 1.4301 (1.1349)	
[2022-01-19 01:59:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1050/1251]	eta 0:07:22 lr 0.000937	time 1.8372 (2.2000)	loss 3.5671 (3.9689)	grad_norm 1.4237 (1.1343)	
[2022-01-19 02:00:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1060/1251]	eta 0:07:00 lr 0.000937	time 1.9167 (2.1998)	loss 3.7823 (3.9695)	grad_norm 1.1618 (1.1343)	
[2022-01-19 02:00:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1070/1251]	eta 0:06:38 lr 0.000937	time 2.4892 (2.2004)	loss 4.5032 (3.9700)	grad_norm 1.0411 (1.1341)	
[2022-01-19 02:01:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1080/1251]	eta 0:06:16 lr 0.000937	time 2.4236 (2.2025)	loss 4.2694 (3.9697)	grad_norm 1.0363 (1.1329)	
[2022-01-19 02:01:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1090/1251]	eta 0:05:54 lr 0.000937	time 1.5351 (2.2023)	loss 2.8571 (3.9684)	grad_norm 1.2746 (1.1323)	
[2022-01-19 02:01:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1100/1251]	eta 0:05:32 lr 0.000937	time 2.1209 (2.2022)	loss 4.2249 (3.9692)	grad_norm 1.0218 (1.1322)	
[2022-01-19 02:02:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1110/1251]	eta 0:05:10 lr 0.000937	time 1.8986 (2.2024)	loss 3.5220 (3.9683)	grad_norm 1.1946 (1.1319)	
[2022-01-19 02:02:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1120/1251]	eta 0:04:48 lr 0.000937	time 1.6822 (2.2029)	loss 3.7890 (3.9646)	grad_norm 0.9825 (1.1323)	
[2022-01-19 02:02:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1130/1251]	eta 0:04:26 lr 0.000936	time 1.9577 (2.2015)	loss 4.4033 (3.9651)	grad_norm 1.0372 (1.1326)	
[2022-01-19 02:03:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1140/1251]	eta 0:04:04 lr 0.000936	time 1.6893 (2.1998)	loss 3.6156 (3.9629)	grad_norm 1.2117 (1.1332)	
[2022-01-19 02:03:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1150/1251]	eta 0:03:42 lr 0.000936	time 2.0071 (2.1993)	loss 3.8976 (3.9622)	grad_norm 1.1228 (1.1331)	
[2022-01-19 02:03:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1160/1251]	eta 0:03:20 lr 0.000936	time 2.1897 (2.1987)	loss 4.3136 (3.9611)	grad_norm 0.8815 (1.1326)	
[2022-01-19 02:04:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1170/1251]	eta 0:02:58 lr 0.000936	time 1.9499 (2.1989)	loss 4.6467 (3.9625)	grad_norm 1.0754 (1.1321)	
[2022-01-19 02:04:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1180/1251]	eta 0:02:36 lr 0.000936	time 1.9019 (2.1988)	loss 4.3332 (3.9637)	grad_norm 1.0543 (1.1314)	
[2022-01-19 02:05:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1190/1251]	eta 0:02:14 lr 0.000936	time 2.1689 (2.1988)	loss 4.1698 (3.9643)	grad_norm 0.9711 (1.1313)	
[2022-01-19 02:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1200/1251]	eta 0:01:52 lr 0.000936	time 2.7018 (2.2001)	loss 3.5674 (3.9642)	grad_norm 1.1418 (1.1313)	
[2022-01-19 02:05:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1210/1251]	eta 0:01:30 lr 0.000936	time 1.9192 (2.1993)	loss 3.3566 (3.9648)	grad_norm 1.2463 (1.1317)	
[2022-01-19 02:06:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1220/1251]	eta 0:01:08 lr 0.000936	time 1.6255 (2.1971)	loss 4.4008 (3.9655)	grad_norm 1.0530 (1.1318)	
[2022-01-19 02:06:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1230/1251]	eta 0:00:46 lr 0.000936	time 1.8006 (2.1966)	loss 4.4096 (3.9680)	grad_norm 1.0067 (1.1309)	
[2022-01-19 02:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1240/1251]	eta 0:00:24 lr 0.000936	time 1.5470 (2.1953)	loss 4.0418 (3.9647)	grad_norm 1.0254 (1.1305)	
[2022-01-19 02:07:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [48/300][1250/1251]	eta 0:00:02 lr 0.000936	time 1.3500 (2.1903)	loss 3.8371 (3.9646)	grad_norm 1.2306 (1.1310)	
[2022-01-19 02:07:07 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 48 training takes 0:45:40
[2022-01-19 02:07:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.108 (18.108)	Loss 1.3008 (1.3008)	Acc@1 71.289 (71.289)	Acc@5 89.941 (89.941)	
[2022-01-19 02:07:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.597 (3.309)	Loss 1.2776 (1.3033)	Acc@1 69.727 (70.108)	Acc@5 90.137 (89.977)	
[2022-01-19 02:08:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.230 (2.584)	Loss 1.2395 (1.2899)	Acc@1 71.777 (70.396)	Acc@5 90.430 (90.109)	
[2022-01-19 02:08:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.528 (2.321)	Loss 1.2256 (1.3009)	Acc@1 71.094 (69.963)	Acc@5 91.309 (89.982)	
[2022-01-19 02:08:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.528 (2.191)	Loss 1.2487 (1.3015)	Acc@1 70.410 (69.865)	Acc@5 91.406 (90.006)	
[2022-01-19 02:08:45 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 69.950 Acc@5 90.076
[2022-01-19 02:08:45 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 70.0%
[2022-01-19 02:08:45 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 69.95%
[2022-01-19 02:09:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][0/1251]	eta 7:28:51 lr 0.000936	time 21.5281 (21.5281)	loss 4.1878 (4.1878)	grad_norm 1.2212 (1.2212)	
[2022-01-19 02:09:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][10/1251]	eta 1:21:34 lr 0.000936	time 2.4148 (3.9439)	loss 4.1610 (4.0672)	grad_norm 1.3482 (1.1691)	
[2022-01-19 02:09:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][20/1251]	eta 1:04:07 lr 0.000936	time 1.7007 (3.1255)	loss 2.7661 (3.9253)	grad_norm 1.1340 (1.1437)	
[2022-01-19 02:10:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][30/1251]	eta 0:57:25 lr 0.000936	time 1.9407 (2.8222)	loss 4.2671 (3.9006)	grad_norm 1.1873 (1.1294)	
[2022-01-19 02:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][40/1251]	eta 0:54:34 lr 0.000936	time 3.3926 (2.7040)	loss 4.2534 (3.9183)	grad_norm 0.9813 (1.1418)	
[2022-01-19 02:11:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][50/1251]	eta 0:53:13 lr 0.000936	time 2.5037 (2.6589)	loss 3.0012 (3.9529)	grad_norm 1.3201 (1.1342)	
[2022-01-19 02:11:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][60/1251]	eta 0:51:51 lr 0.000936	time 2.1358 (2.6123)	loss 4.1907 (3.8954)	grad_norm 1.1853 (1.1340)	
[2022-01-19 02:11:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][70/1251]	eta 0:50:28 lr 0.000936	time 2.0984 (2.5642)	loss 4.5962 (3.9290)	grad_norm 1.0417 (1.1352)	
[2022-01-19 02:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][80/1251]	eta 0:49:12 lr 0.000936	time 2.8808 (2.5215)	loss 3.2851 (3.9145)	grad_norm 1.1374 (1.1251)	
[2022-01-19 02:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][90/1251]	eta 0:47:57 lr 0.000936	time 2.2875 (2.4788)	loss 4.1474 (3.9216)	grad_norm 1.1931 (1.1205)	
[2022-01-19 02:12:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][100/1251]	eta 0:46:34 lr 0.000936	time 1.8221 (2.4280)	loss 3.5953 (3.8980)	grad_norm 1.2664 (1.1229)	
[2022-01-19 02:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][110/1251]	eta 0:45:26 lr 0.000936	time 1.7892 (2.3899)	loss 4.3642 (3.9026)	grad_norm 1.2548 (1.1235)	
[2022-01-19 02:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][120/1251]	eta 0:44:44 lr 0.000936	time 2.1781 (2.3732)	loss 3.7481 (3.9023)	grad_norm 1.3709 (1.1351)	
[2022-01-19 02:13:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][130/1251]	eta 0:43:54 lr 0.000936	time 2.1569 (2.3500)	loss 4.6295 (3.9017)	grad_norm 1.2235 (1.1317)	
[2022-01-19 02:14:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][140/1251]	eta 0:43:15 lr 0.000936	time 1.9811 (2.3360)	loss 4.4215 (3.8964)	grad_norm 1.2446 (1.1312)	
[2022-01-19 02:14:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][150/1251]	eta 0:42:38 lr 0.000936	time 2.1423 (2.3242)	loss 4.2578 (3.8967)	grad_norm 1.1923 (1.1296)	
[2022-01-19 02:14:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][160/1251]	eta 0:42:07 lr 0.000936	time 2.4179 (2.3168)	loss 3.9757 (3.9072)	grad_norm 0.9164 (1.1298)	
[2022-01-19 02:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][170/1251]	eta 0:41:39 lr 0.000936	time 1.9539 (2.3123)	loss 3.9316 (3.8928)	grad_norm 1.2943 (1.1317)	
[2022-01-19 02:15:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][180/1251]	eta 0:41:24 lr 0.000936	time 2.4310 (2.3198)	loss 2.7044 (3.8905)	grad_norm 1.4130 (1.1346)	
[2022-01-19 02:16:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][190/1251]	eta 0:40:56 lr 0.000936	time 1.8312 (2.3156)	loss 3.8224 (3.8931)	grad_norm 1.2125 (1.1339)	
[2022-01-19 02:16:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][200/1251]	eta 0:40:31 lr 0.000936	time 1.6501 (2.3140)	loss 4.0710 (3.8904)	grad_norm 1.1199 (1.1356)	
[2022-01-19 02:16:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][210/1251]	eta 0:40:03 lr 0.000936	time 2.2736 (2.3087)	loss 3.0521 (3.8769)	grad_norm 1.2400 (1.1365)	
[2022-01-19 02:17:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][220/1251]	eta 0:39:40 lr 0.000936	time 3.0903 (2.3091)	loss 4.1586 (3.8811)	grad_norm 1.1376 (1.1351)	
[2022-01-19 02:17:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][230/1251]	eta 0:39:06 lr 0.000936	time 1.8092 (2.2981)	loss 3.8884 (3.8864)	grad_norm 1.2792 (1.1384)	
[2022-01-19 02:17:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][240/1251]	eta 0:38:33 lr 0.000936	time 1.8794 (2.2885)	loss 4.2386 (3.8942)	grad_norm 0.8880 (1.1393)	
[2022-01-19 02:18:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][250/1251]	eta 0:38:12 lr 0.000936	time 2.8756 (2.2902)	loss 4.1390 (3.8881)	grad_norm 1.1997 (1.1408)	
[2022-01-19 02:18:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][260/1251]	eta 0:37:49 lr 0.000936	time 2.0120 (2.2901)	loss 4.0137 (3.8901)	grad_norm 1.0965 (1.1402)	
[2022-01-19 02:19:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][270/1251]	eta 0:37:18 lr 0.000936	time 1.9122 (2.2815)	loss 4.2196 (3.8873)	grad_norm 0.9116 (1.1391)	
[2022-01-19 02:19:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][280/1251]	eta 0:36:50 lr 0.000936	time 2.2751 (2.2764)	loss 4.2858 (3.8911)	grad_norm 1.0046 (1.1394)	
[2022-01-19 02:19:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][290/1251]	eta 0:36:21 lr 0.000936	time 2.2045 (2.2705)	loss 4.2009 (3.8914)	grad_norm 1.0445 (1.1366)	
[2022-01-19 02:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][300/1251]	eta 0:35:54 lr 0.000936	time 2.2241 (2.2655)	loss 3.8393 (3.8866)	grad_norm 1.1854 (1.1342)	
[2022-01-19 02:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][310/1251]	eta 0:35:31 lr 0.000936	time 2.2492 (2.2650)	loss 3.7005 (3.8864)	grad_norm 1.4536 (1.1341)	
[2022-01-19 02:20:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][320/1251]	eta 0:35:03 lr 0.000936	time 2.0231 (2.2593)	loss 2.8237 (3.8797)	grad_norm 1.0807 (1.1332)	
[2022-01-19 02:21:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][330/1251]	eta 0:34:34 lr 0.000936	time 2.2298 (2.2523)	loss 4.2455 (3.8859)	grad_norm 1.2066 (1.1335)	
[2022-01-19 02:21:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][340/1251]	eta 0:34:11 lr 0.000936	time 2.2659 (2.2515)	loss 3.3805 (3.8861)	grad_norm 1.1914 (1.1317)	
[2022-01-19 02:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][350/1251]	eta 0:33:45 lr 0.000936	time 1.8327 (2.2485)	loss 4.1184 (3.8848)	grad_norm 1.2155 (1.1294)	
[2022-01-19 02:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][360/1251]	eta 0:33:22 lr 0.000936	time 2.4746 (2.2480)	loss 4.7488 (3.8882)	grad_norm 1.1096 (1.1311)	
[2022-01-19 02:22:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][370/1251]	eta 0:32:59 lr 0.000935	time 2.5636 (2.2467)	loss 3.6354 (3.8922)	grad_norm 0.9041 (1.1292)	
[2022-01-19 02:23:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][380/1251]	eta 0:32:42 lr 0.000935	time 3.2547 (2.2536)	loss 4.6862 (3.8960)	grad_norm 0.9734 (1.1308)	
[2022-01-19 02:23:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][390/1251]	eta 0:32:21 lr 0.000935	time 2.7485 (2.2546)	loss 3.7343 (3.8916)	grad_norm 1.4429 (1.1321)	
[2022-01-19 02:23:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][400/1251]	eta 0:31:53 lr 0.000935	time 1.8800 (2.2487)	loss 3.8606 (3.9028)	grad_norm 1.0422 (1.1317)	
[2022-01-19 02:24:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][410/1251]	eta 0:31:28 lr 0.000935	time 1.7374 (2.2460)	loss 4.2599 (3.9008)	grad_norm 1.1093 (1.1295)	
[2022-01-19 02:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][420/1251]	eta 0:31:05 lr 0.000935	time 2.5610 (2.2452)	loss 4.2050 (3.9025)	grad_norm 0.9450 (1.1281)	
[2022-01-19 02:24:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][430/1251]	eta 0:30:39 lr 0.000935	time 1.8759 (2.2408)	loss 4.3475 (3.9006)	grad_norm 1.1417 (1.1293)	
[2022-01-19 02:25:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][440/1251]	eta 0:30:15 lr 0.000935	time 2.4460 (2.2390)	loss 4.4802 (3.9101)	grad_norm 1.1952 (1.1301)	
[2022-01-19 02:25:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][450/1251]	eta 0:29:48 lr 0.000935	time 1.8836 (2.2331)	loss 4.2554 (3.9143)	grad_norm 1.0657 (1.1284)	
[2022-01-19 02:25:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][460/1251]	eta 0:29:25 lr 0.000935	time 2.1379 (2.2318)	loss 3.0567 (3.9128)	grad_norm 1.2175 (1.1283)	
[2022-01-19 02:26:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][470/1251]	eta 0:29:01 lr 0.000935	time 2.1385 (2.2302)	loss 3.6294 (3.9088)	grad_norm 1.0271 (1.1282)	
[2022-01-19 02:26:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][480/1251]	eta 0:28:38 lr 0.000935	time 2.5253 (2.2295)	loss 4.6754 (3.9092)	grad_norm 1.1993 (1.1300)	
[2022-01-19 02:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][490/1251]	eta 0:28:17 lr 0.000935	time 2.2997 (2.2300)	loss 4.5230 (3.9141)	grad_norm 1.2576 (1.1316)	
[2022-01-19 02:27:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][500/1251]	eta 0:27:57 lr 0.000935	time 3.6978 (2.2333)	loss 3.3755 (3.9102)	grad_norm 0.9884 (1.1316)	
[2022-01-19 02:27:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][510/1251]	eta 0:27:36 lr 0.000935	time 2.8501 (2.2357)	loss 2.8374 (3.9093)	grad_norm 1.0537 (1.1301)	
[2022-01-19 02:28:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][520/1251]	eta 0:27:15 lr 0.000935	time 2.1642 (2.2368)	loss 4.9576 (3.9140)	grad_norm 1.1424 (1.1315)	
[2022-01-19 02:28:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][530/1251]	eta 0:26:52 lr 0.000935	time 1.5832 (2.2371)	loss 2.7455 (3.9109)	grad_norm 1.0065 (1.1307)	
[2022-01-19 02:28:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][540/1251]	eta 0:26:31 lr 0.000935	time 3.4189 (2.2391)	loss 3.8582 (3.9093)	grad_norm 1.0397 (1.1310)	
[2022-01-19 02:29:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][550/1251]	eta 0:26:05 lr 0.000935	time 1.9007 (2.2339)	loss 4.3397 (3.9069)	grad_norm 1.1939 (1.1315)	
[2022-01-19 02:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][560/1251]	eta 0:25:39 lr 0.000935	time 1.8056 (2.2280)	loss 4.2858 (3.9063)	grad_norm 1.2151 (1.1310)	
[2022-01-19 02:29:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][570/1251]	eta 0:25:16 lr 0.000935	time 2.7302 (2.2263)	loss 4.4422 (3.9093)	grad_norm 1.4134 (1.1318)	
[2022-01-19 02:30:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][580/1251]	eta 0:24:54 lr 0.000935	time 2.4738 (2.2269)	loss 3.5533 (3.9089)	grad_norm 1.1201 (1.1338)	
[2022-01-19 02:30:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][590/1251]	eta 0:24:32 lr 0.000935	time 2.3344 (2.2273)	loss 4.0294 (3.9104)	grad_norm 1.1601 (1.1341)	
[2022-01-19 02:31:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][600/1251]	eta 0:24:10 lr 0.000935	time 2.4846 (2.2282)	loss 4.2700 (3.9115)	grad_norm 0.8963 (1.1336)	
[2022-01-19 02:31:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][610/1251]	eta 0:23:46 lr 0.000935	time 1.9251 (2.2262)	loss 4.7624 (3.9144)	grad_norm 1.2034 (1.1342)	
[2022-01-19 02:31:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][620/1251]	eta 0:23:24 lr 0.000935	time 2.9699 (2.2263)	loss 4.4782 (3.9184)	grad_norm 1.0237 (1.1330)	
[2022-01-19 02:32:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][630/1251]	eta 0:23:00 lr 0.000935	time 1.9578 (2.2236)	loss 4.5161 (3.9209)	grad_norm 1.2102 (1.1328)	
[2022-01-19 02:32:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][640/1251]	eta 0:22:37 lr 0.000935	time 2.5206 (2.2223)	loss 3.2635 (3.9232)	grad_norm 1.0892 (1.1325)	
[2022-01-19 02:32:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][650/1251]	eta 0:22:15 lr 0.000935	time 2.2909 (2.2224)	loss 4.2846 (3.9264)	grad_norm 1.2009 (1.1322)	
[2022-01-19 02:33:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][660/1251]	eta 0:21:52 lr 0.000935	time 1.8423 (2.2200)	loss 3.3339 (3.9232)	grad_norm 1.2011 (1.1325)	
[2022-01-19 02:33:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][670/1251]	eta 0:21:30 lr 0.000935	time 2.3516 (2.2208)	loss 4.3134 (3.9248)	grad_norm 0.9821 (1.1315)	
[2022-01-19 02:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][680/1251]	eta 0:21:08 lr 0.000935	time 1.9440 (2.2210)	loss 4.0850 (3.9241)	grad_norm 0.9623 (1.1313)	
[2022-01-19 02:34:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][690/1251]	eta 0:20:45 lr 0.000935	time 1.9154 (2.2204)	loss 4.3867 (3.9228)	grad_norm 1.2233 (1.1308)	
[2022-01-19 02:34:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][700/1251]	eta 0:20:23 lr 0.000935	time 2.1781 (2.2214)	loss 4.1513 (3.9262)	grad_norm 1.4705 (1.1308)	
[2022-01-19 02:35:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][710/1251]	eta 0:20:01 lr 0.000935	time 2.4256 (2.2207)	loss 3.1564 (3.9268)	grad_norm 1.1077 (1.1324)	
[2022-01-19 02:35:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][720/1251]	eta 0:19:37 lr 0.000935	time 1.9068 (2.2173)	loss 3.7932 (3.9282)	grad_norm 1.2117 (1.1321)	
[2022-01-19 02:35:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][730/1251]	eta 0:19:13 lr 0.000935	time 1.8464 (2.2141)	loss 4.1902 (3.9302)	grad_norm 1.0045 (1.1327)	
[2022-01-19 02:36:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][740/1251]	eta 0:18:51 lr 0.000935	time 2.1098 (2.2136)	loss 3.8748 (3.9300)	grad_norm 1.1283 (1.1333)	
[2022-01-19 02:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][750/1251]	eta 0:18:29 lr 0.000935	time 2.2020 (2.2143)	loss 4.1407 (3.9316)	grad_norm 1.1672 (1.1324)	
[2022-01-19 02:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][760/1251]	eta 0:18:07 lr 0.000935	time 2.1129 (2.2157)	loss 4.1822 (3.9333)	grad_norm 1.0570 (1.1322)	
[2022-01-19 02:37:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][770/1251]	eta 0:17:45 lr 0.000935	time 1.8959 (2.2152)	loss 4.0675 (3.9325)	grad_norm 1.3665 (1.1326)	
[2022-01-19 02:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][780/1251]	eta 0:17:22 lr 0.000935	time 2.1528 (2.2143)	loss 2.9161 (3.9301)	grad_norm 0.9237 (1.1327)	
[2022-01-19 02:37:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][790/1251]	eta 0:17:00 lr 0.000935	time 1.8227 (2.2141)	loss 4.0783 (3.9309)	grad_norm 1.1676 (1.1332)	
[2022-01-19 02:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][800/1251]	eta 0:16:38 lr 0.000935	time 2.4830 (2.2141)	loss 4.2069 (3.9299)	grad_norm 0.9423 (1.1336)	
[2022-01-19 02:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][810/1251]	eta 0:16:15 lr 0.000935	time 1.8799 (2.2117)	loss 4.4517 (3.9268)	grad_norm 1.1523 (1.1340)	
[2022-01-19 02:39:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][820/1251]	eta 0:15:52 lr 0.000935	time 2.1895 (2.2105)	loss 4.5010 (3.9260)	grad_norm 1.2301 (1.1352)	
[2022-01-19 02:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][830/1251]	eta 0:15:30 lr 0.000935	time 1.9107 (2.2097)	loss 4.1234 (3.9242)	grad_norm 0.9730 (1.1358)	
[2022-01-19 02:39:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][840/1251]	eta 0:15:08 lr 0.000935	time 1.5989 (2.2102)	loss 4.2894 (3.9233)	grad_norm 1.3717 (1.1351)	
[2022-01-19 02:40:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][850/1251]	eta 0:14:46 lr 0.000935	time 2.1095 (2.2116)	loss 4.4210 (3.9241)	grad_norm 1.1763 (1.1346)	
[2022-01-19 02:40:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][860/1251]	eta 0:14:24 lr 0.000934	time 1.5941 (2.2112)	loss 4.1261 (3.9221)	grad_norm 1.0189 (1.1343)	
[2022-01-19 02:40:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][870/1251]	eta 0:14:02 lr 0.000934	time 1.8714 (2.2110)	loss 4.0976 (3.9237)	grad_norm 1.1177 (1.1334)	
[2022-01-19 02:41:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][880/1251]	eta 0:13:40 lr 0.000934	time 1.6057 (2.2117)	loss 4.2604 (3.9280)	grad_norm 1.1037 (1.1337)	
[2022-01-19 02:41:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][890/1251]	eta 0:13:18 lr 0.000934	time 1.5943 (2.2117)	loss 3.8442 (3.9297)	grad_norm 1.0278 (1.1332)	
[2022-01-19 02:41:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][900/1251]	eta 0:12:55 lr 0.000934	time 2.2424 (2.2097)	loss 2.8936 (3.9294)	grad_norm 1.1635 (1.1338)	
[2022-01-19 02:42:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][910/1251]	eta 0:12:32 lr 0.000934	time 1.8837 (2.2080)	loss 4.2412 (3.9282)	grad_norm 0.8922 (1.1336)	
[2022-01-19 02:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][920/1251]	eta 0:12:10 lr 0.000934	time 2.1236 (2.2068)	loss 4.3053 (3.9265)	grad_norm 0.9963 (1.1339)	
[2022-01-19 02:42:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][930/1251]	eta 0:11:48 lr 0.000934	time 2.5390 (2.2066)	loss 4.3632 (3.9265)	grad_norm 1.0545 (1.1338)	
[2022-01-19 02:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][940/1251]	eta 0:11:26 lr 0.000934	time 2.6755 (2.2083)	loss 2.6099 (3.9239)	grad_norm 1.1143 (1.1349)	
[2022-01-19 02:43:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][950/1251]	eta 0:11:04 lr 0.000934	time 1.8243 (2.2086)	loss 3.8278 (3.9257)	grad_norm 1.0477 (1.1342)	
[2022-01-19 02:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][960/1251]	eta 0:10:42 lr 0.000934	time 2.0224 (2.2070)	loss 4.1138 (3.9233)	grad_norm 1.1047 (1.1349)	
[2022-01-19 02:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][970/1251]	eta 0:10:20 lr 0.000934	time 2.1543 (2.2068)	loss 4.4118 (3.9244)	grad_norm 1.0883 (1.1353)	
[2022-01-19 02:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][980/1251]	eta 0:09:57 lr 0.000934	time 2.4866 (2.2066)	loss 4.6527 (3.9222)	grad_norm 1.0064 (1.1347)	
[2022-01-19 02:45:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][990/1251]	eta 0:09:36 lr 0.000934	time 2.1333 (2.2073)	loss 4.7623 (3.9230)	grad_norm 1.1661 (1.1340)	
[2022-01-19 02:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1000/1251]	eta 0:09:14 lr 0.000934	time 1.8079 (2.2086)	loss 4.7330 (3.9240)	grad_norm 1.1914 (1.1340)	
[2022-01-19 02:45:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1010/1251]	eta 0:08:52 lr 0.000934	time 1.9762 (2.2091)	loss 4.2172 (3.9248)	grad_norm 1.1136 (1.1341)	
[2022-01-19 02:46:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1020/1251]	eta 0:08:30 lr 0.000934	time 2.0632 (2.2080)	loss 3.6493 (3.9241)	grad_norm 1.2529 (1.1340)	
[2022-01-19 02:46:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1030/1251]	eta 0:08:07 lr 0.000934	time 2.6681 (2.2066)	loss 4.6365 (3.9251)	grad_norm 1.5383 (1.1347)	
[2022-01-19 02:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1040/1251]	eta 0:07:45 lr 0.000934	time 1.8627 (2.2054)	loss 4.3152 (3.9262)	grad_norm 1.0991 (1.1341)	
[2022-01-19 02:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1050/1251]	eta 0:07:23 lr 0.000934	time 1.8231 (2.2056)	loss 4.2301 (3.9257)	grad_norm 1.3427 (1.1339)	
[2022-01-19 02:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1060/1251]	eta 0:07:01 lr 0.000934	time 2.1662 (2.2057)	loss 4.3358 (3.9256)	grad_norm 1.2422 (1.1334)	
[2022-01-19 02:48:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1070/1251]	eta 0:06:39 lr 0.000934	time 1.9085 (2.2046)	loss 4.3220 (3.9282)	grad_norm 1.2014 (1.1334)	
[2022-01-19 02:48:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1080/1251]	eta 0:06:17 lr 0.000934	time 1.7661 (2.2052)	loss 3.4898 (3.9233)	grad_norm 1.3229 (1.1335)	
[2022-01-19 02:48:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1090/1251]	eta 0:05:55 lr 0.000934	time 2.4299 (2.2052)	loss 3.5374 (3.9248)	grad_norm 1.2142 (1.1340)	
[2022-01-19 02:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1100/1251]	eta 0:05:32 lr 0.000934	time 1.8679 (2.2042)	loss 4.0250 (3.9262)	grad_norm 1.0839 (1.1336)	
[2022-01-19 02:49:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1110/1251]	eta 0:05:10 lr 0.000934	time 2.1368 (2.2041)	loss 4.0575 (3.9260)	grad_norm 1.2224 (1.1338)	
[2022-01-19 02:49:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1120/1251]	eta 0:04:48 lr 0.000934	time 2.4832 (2.2045)	loss 4.2203 (3.9241)	grad_norm 1.2717 (1.1342)	
[2022-01-19 02:50:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1130/1251]	eta 0:04:26 lr 0.000934	time 2.0124 (2.2034)	loss 3.1950 (3.9235)	grad_norm 1.3172 (1.1344)	
[2022-01-19 02:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1140/1251]	eta 0:04:04 lr 0.000934	time 2.2016 (2.2029)	loss 4.2666 (3.9249)	grad_norm 0.9123 (1.1338)	
[2022-01-19 02:50:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1150/1251]	eta 0:03:42 lr 0.000934	time 1.8993 (2.2013)	loss 4.6637 (3.9269)	grad_norm 0.9537 (1.1328)	
[2022-01-19 02:51:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1160/1251]	eta 0:03:20 lr 0.000934	time 2.0281 (2.2005)	loss 2.9742 (3.9292)	grad_norm 1.1816 (1.1328)	
[2022-01-19 02:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1170/1251]	eta 0:02:58 lr 0.000934	time 2.3240 (2.2002)	loss 4.5107 (3.9286)	grad_norm 1.1923 (1.1323)	
[2022-01-19 02:52:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1180/1251]	eta 0:02:36 lr 0.000934	time 2.3310 (2.2009)	loss 3.7657 (3.9276)	grad_norm 1.1796 (1.1320)	
[2022-01-19 02:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1190/1251]	eta 0:02:14 lr 0.000934	time 2.0163 (2.2005)	loss 4.0883 (3.9271)	grad_norm 0.8697 (1.1313)	
[2022-01-19 02:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1200/1251]	eta 0:01:52 lr 0.000934	time 2.2204 (2.2011)	loss 4.6374 (3.9267)	grad_norm 1.0545 (1.1307)	
[2022-01-19 02:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1210/1251]	eta 0:01:30 lr 0.000934	time 2.5911 (2.2011)	loss 4.2636 (3.9284)	grad_norm 1.3327 (1.1303)	
[2022-01-19 02:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1220/1251]	eta 0:01:08 lr 0.000934	time 2.6754 (2.2011)	loss 3.6078 (3.9234)	grad_norm 1.0273 (1.1298)	
[2022-01-19 02:53:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1230/1251]	eta 0:00:46 lr 0.000934	time 2.5009 (2.2006)	loss 4.0202 (3.9238)	grad_norm 1.1113 (1.1296)	
[2022-01-19 02:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1240/1251]	eta 0:00:24 lr 0.000934	time 1.7324 (2.1993)	loss 4.3352 (3.9258)	grad_norm 1.3871 (1.1298)	
[2022-01-19 02:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [49/300][1250/1251]	eta 0:00:02 lr 0.000934	time 1.2018 (2.1934)	loss 4.3091 (3.9274)	grad_norm 1.1927 (1.1296)	
[2022-01-19 02:54:29 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 49 training takes 0:45:44
[2022-01-19 02:54:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.386 (18.386)	Loss 1.3106 (1.3106)	Acc@1 68.652 (68.652)	Acc@5 90.039 (90.039)	
[2022-01-19 02:55:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.308 (3.393)	Loss 1.2559 (1.2943)	Acc@1 70.801 (69.256)	Acc@5 89.160 (89.906)	
[2022-01-19 02:55:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.591 (2.542)	Loss 1.2265 (1.2917)	Acc@1 71.973 (69.550)	Acc@5 91.016 (90.030)	
[2022-01-19 02:55:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.943 (2.222)	Loss 1.2579 (1.2848)	Acc@1 71.094 (69.796)	Acc@5 90.625 (90.017)	
[2022-01-19 02:55:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.817 (2.159)	Loss 1.3471 (1.2848)	Acc@1 68.848 (69.958)	Acc@5 88.379 (89.972)	
[2022-01-19 02:56:05 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 70.104 Acc@5 90.006
[2022-01-19 02:56:05 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 70.1%
[2022-01-19 02:56:05 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 70.10%
[2022-01-19 02:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][0/1251]	eta 7:32:25 lr 0.000934	time 21.6989 (21.6989)	loss 3.4463 (3.4463)	grad_norm 1.2064 (1.2064)	
[2022-01-19 02:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][10/1251]	eta 1:26:02 lr 0.000934	time 2.1697 (4.1596)	loss 3.8591 (3.6924)	grad_norm 1.0401 (1.1975)	
[2022-01-19 02:57:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][20/1251]	eta 1:05:26 lr 0.000934	time 1.4007 (3.1897)	loss 2.6970 (3.7622)	grad_norm 1.0756 (1.1507)	
[2022-01-19 02:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][30/1251]	eta 0:58:20 lr 0.000934	time 1.9129 (2.8670)	loss 2.8457 (3.8272)	grad_norm 1.1987 (1.1731)	
[2022-01-19 02:57:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][40/1251]	eta 0:54:09 lr 0.000934	time 2.7774 (2.6831)	loss 3.5264 (3.8071)	grad_norm 0.9700 (1.1766)	
[2022-01-19 02:58:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][50/1251]	eta 0:52:00 lr 0.000934	time 1.5756 (2.5982)	loss 4.4329 (3.8097)	grad_norm 1.2047 (1.1697)	
[2022-01-19 02:58:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][60/1251]	eta 0:50:35 lr 0.000934	time 1.8073 (2.5491)	loss 4.0244 (3.8728)	grad_norm 1.0782 (1.1571)	
[2022-01-19 02:59:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][70/1251]	eta 0:49:01 lr 0.000934	time 1.5099 (2.4907)	loss 2.9709 (3.8604)	grad_norm 1.0558 (1.1537)	
[2022-01-19 02:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][80/1251]	eta 0:47:44 lr 0.000934	time 2.1462 (2.4464)	loss 4.6744 (3.8535)	grad_norm 1.1282 (1.1562)	
[2022-01-19 02:59:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][90/1251]	eta 0:46:56 lr 0.000933	time 1.9299 (2.4260)	loss 4.6312 (3.8811)	grad_norm 1.5214 (1.1552)	
[2022-01-19 03:00:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][100/1251]	eta 0:45:55 lr 0.000933	time 1.9168 (2.3944)	loss 4.1035 (3.8546)	grad_norm 1.1951 (1.1607)	
[2022-01-19 03:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][110/1251]	eta 0:45:13 lr 0.000933	time 1.8157 (2.3780)	loss 4.5316 (3.8735)	grad_norm 1.2352 (1.1554)	
[2022-01-19 03:00:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][120/1251]	eta 0:44:22 lr 0.000933	time 1.9354 (2.3539)	loss 4.5300 (3.9092)	grad_norm 1.0828 (1.1514)	
[2022-01-19 03:01:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][130/1251]	eta 0:43:23 lr 0.000933	time 1.5475 (2.3224)	loss 4.1788 (3.8967)	grad_norm 1.1938 (1.1410)	
[2022-01-19 03:01:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][140/1251]	eta 0:42:38 lr 0.000933	time 2.2546 (2.3026)	loss 4.6882 (3.9192)	grad_norm 1.2068 (1.1368)	
[2022-01-19 03:01:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][150/1251]	eta 0:42:01 lr 0.000933	time 2.1814 (2.2906)	loss 4.0584 (3.9282)	grad_norm 0.9440 (1.1324)	
[2022-01-19 03:02:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][160/1251]	eta 0:41:25 lr 0.000933	time 1.6323 (2.2784)	loss 4.7467 (3.9305)	grad_norm 1.1859 (1.1339)	
[2022-01-19 03:02:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][170/1251]	eta 0:41:12 lr 0.000933	time 2.5619 (2.2870)	loss 4.0207 (3.9386)	grad_norm 1.1766 (1.1282)	
[2022-01-19 03:02:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][180/1251]	eta 0:40:48 lr 0.000933	time 1.7294 (2.2862)	loss 3.8968 (3.9321)	grad_norm 1.1184 (1.1224)	
[2022-01-19 03:03:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][190/1251]	eta 0:40:32 lr 0.000933	time 2.7984 (2.2922)	loss 4.5355 (3.9428)	grad_norm 1.1787 (1.1249)	
[2022-01-19 03:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][200/1251]	eta 0:39:57 lr 0.000933	time 1.8176 (2.2816)	loss 3.9919 (3.9252)	grad_norm 1.2765 (1.1279)	
[2022-01-19 03:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][210/1251]	eta 0:39:26 lr 0.000933	time 1.5419 (2.2737)	loss 4.5789 (3.9236)	grad_norm 1.3986 (1.1334)	
[2022-01-19 03:04:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][220/1251]	eta 0:38:53 lr 0.000933	time 1.8422 (2.2637)	loss 3.1067 (3.9244)	grad_norm 1.0655 (1.1386)	
[2022-01-19 03:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][230/1251]	eta 0:38:27 lr 0.000933	time 2.2572 (2.2599)	loss 4.2774 (3.9256)	grad_norm 1.8081 (1.1422)	
[2022-01-19 03:05:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][240/1251]	eta 0:38:02 lr 0.000933	time 2.1596 (2.2575)	loss 4.0284 (3.9385)	grad_norm 1.2141 (1.1445)	
[2022-01-19 03:05:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][250/1251]	eta 0:37:47 lr 0.000933	time 2.7815 (2.2655)	loss 4.2817 (3.9331)	grad_norm 1.0857 (1.1422)	
[2022-01-19 03:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][260/1251]	eta 0:37:23 lr 0.000933	time 1.8845 (2.2643)	loss 4.8764 (3.9372)	grad_norm 1.2129 (1.1435)	
[2022-01-19 03:06:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][270/1251]	eta 0:36:58 lr 0.000933	time 1.9349 (2.2611)	loss 4.0875 (3.9389)	grad_norm 1.2939 (1.1456)	
[2022-01-19 03:06:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][280/1251]	eta 0:36:27 lr 0.000933	time 2.1715 (2.2529)	loss 4.3496 (3.9395)	grad_norm 1.0847 (1.1471)	
[2022-01-19 03:07:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][290/1251]	eta 0:36:03 lr 0.000933	time 1.9545 (2.2509)	loss 3.3035 (3.9336)	grad_norm 1.1287 (1.1447)	
[2022-01-19 03:07:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][300/1251]	eta 0:35:43 lr 0.000933	time 1.8683 (2.2542)	loss 2.9822 (3.9235)	grad_norm 1.0685 (1.1420)	
[2022-01-19 03:07:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][310/1251]	eta 0:35:23 lr 0.000933	time 1.9308 (2.2564)	loss 3.5646 (3.9361)	grad_norm 1.0790 (1.1396)	
[2022-01-19 03:08:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][320/1251]	eta 0:34:56 lr 0.000933	time 2.0473 (2.2519)	loss 4.1634 (3.9420)	grad_norm 1.0995 (1.1386)	
[2022-01-19 03:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][330/1251]	eta 0:34:28 lr 0.000933	time 2.1287 (2.2455)	loss 3.5681 (3.9502)	grad_norm 1.0076 (1.1386)	
[2022-01-19 03:08:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][340/1251]	eta 0:34:04 lr 0.000933	time 1.9866 (2.2446)	loss 4.4338 (3.9460)	grad_norm 1.1315 (1.1405)	
[2022-01-19 03:09:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][350/1251]	eta 0:33:39 lr 0.000933	time 2.2526 (2.2417)	loss 3.5812 (3.9589)	grad_norm 1.0532 (1.1440)	
[2022-01-19 03:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][360/1251]	eta 0:33:15 lr 0.000933	time 2.2073 (2.2398)	loss 2.8673 (3.9598)	grad_norm 1.0156 (1.1441)	
[2022-01-19 03:09:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][370/1251]	eta 0:32:52 lr 0.000933	time 2.7355 (2.2390)	loss 3.4167 (3.9542)	grad_norm 1.3806 (1.1433)	
[2022-01-19 03:10:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][380/1251]	eta 0:32:28 lr 0.000933	time 1.7886 (2.2373)	loss 3.4925 (3.9561)	grad_norm 1.0726 (1.1429)	
[2022-01-19 03:10:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][390/1251]	eta 0:32:04 lr 0.000933	time 1.4949 (2.2355)	loss 4.4787 (3.9543)	grad_norm 1.2319 (1.1438)	
[2022-01-19 03:11:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][400/1251]	eta 0:31:40 lr 0.000933	time 1.4263 (2.2334)	loss 3.7728 (3.9561)	grad_norm 1.3462 (1.1440)	
[2022-01-19 03:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][410/1251]	eta 0:31:16 lr 0.000933	time 2.3845 (2.2313)	loss 2.7913 (3.9523)	grad_norm 1.5025 (1.1436)	
[2022-01-19 03:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][420/1251]	eta 0:30:53 lr 0.000933	time 1.7068 (2.2306)	loss 4.0684 (3.9552)	grad_norm 0.9961 (1.1445)	
[2022-01-19 03:12:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][430/1251]	eta 0:30:28 lr 0.000933	time 2.1661 (2.2269)	loss 4.2278 (3.9631)	grad_norm 1.4755 (1.1441)	
[2022-01-19 03:12:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][440/1251]	eta 0:30:03 lr 0.000933	time 1.9387 (2.2237)	loss 3.8899 (3.9591)	grad_norm 1.0560 (1.1437)	
[2022-01-19 03:12:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][450/1251]	eta 0:29:39 lr 0.000933	time 1.6414 (2.2222)	loss 3.5590 (3.9573)	grad_norm 1.0525 (1.1425)	
[2022-01-19 03:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][460/1251]	eta 0:29:19 lr 0.000933	time 2.4302 (2.2240)	loss 4.7047 (3.9583)	grad_norm 1.3669 (1.1420)	
[2022-01-19 03:13:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][470/1251]	eta 0:28:58 lr 0.000933	time 1.5411 (2.2259)	loss 4.0614 (3.9573)	grad_norm 1.3846 (1.1410)	
[2022-01-19 03:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][480/1251]	eta 0:28:39 lr 0.000933	time 1.8652 (2.2302)	loss 3.4778 (3.9546)	grad_norm 1.3408 (1.1418)	
[2022-01-19 03:14:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][490/1251]	eta 0:28:20 lr 0.000933	time 1.9011 (2.2345)	loss 4.2899 (3.9512)	grad_norm 1.0893 (1.1400)	
[2022-01-19 03:14:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][500/1251]	eta 0:27:57 lr 0.000933	time 1.7594 (2.2338)	loss 4.0553 (3.9522)	grad_norm 1.0434 (1.1393)	
[2022-01-19 03:15:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][510/1251]	eta 0:27:31 lr 0.000933	time 1.8015 (2.2282)	loss 4.4161 (3.9525)	grad_norm 0.9780 (1.1376)	
[2022-01-19 03:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][520/1251]	eta 0:27:05 lr 0.000933	time 2.3247 (2.2237)	loss 3.9832 (3.9487)	grad_norm 1.1395 (1.1362)	
[2022-01-19 03:15:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][530/1251]	eta 0:26:40 lr 0.000933	time 1.9542 (2.2201)	loss 4.0260 (3.9518)	grad_norm 1.0167 (1.1352)	
[2022-01-19 03:16:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][540/1251]	eta 0:26:17 lr 0.000933	time 2.4343 (2.2188)	loss 3.9734 (3.9545)	grad_norm 1.0625 (1.1348)	
[2022-01-19 03:16:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][550/1251]	eta 0:25:53 lr 0.000933	time 1.8822 (2.2164)	loss 4.2085 (3.9599)	grad_norm 1.1898 (1.1339)	
[2022-01-19 03:16:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][560/1251]	eta 0:25:31 lr 0.000933	time 1.9471 (2.2171)	loss 3.0839 (3.9586)	grad_norm 1.3073 (1.1342)	
[2022-01-19 03:17:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][570/1251]	eta 0:25:10 lr 0.000932	time 2.1892 (2.2182)	loss 3.1601 (3.9607)	grad_norm 1.3342 (1.1342)	
[2022-01-19 03:17:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][580/1251]	eta 0:24:51 lr 0.000932	time 1.5361 (2.2221)	loss 4.0632 (3.9611)	grad_norm 1.0245 (1.1328)	
[2022-01-19 03:17:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][590/1251]	eta 0:24:29 lr 0.000932	time 2.3227 (2.2232)	loss 3.0750 (3.9578)	grad_norm 1.2223 (1.1322)	
[2022-01-19 03:18:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][600/1251]	eta 0:24:07 lr 0.000932	time 2.5624 (2.2228)	loss 3.8471 (3.9550)	grad_norm 1.0027 (1.1335)	
[2022-01-19 03:18:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][610/1251]	eta 0:23:44 lr 0.000932	time 1.6777 (2.2224)	loss 4.1895 (3.9507)	grad_norm 1.1345 (1.1348)	
[2022-01-19 03:19:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][620/1251]	eta 0:23:20 lr 0.000932	time 1.8967 (2.2196)	loss 4.0704 (3.9485)	grad_norm 1.3248 (1.1361)	
[2022-01-19 03:19:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][630/1251]	eta 0:22:57 lr 0.000932	time 1.5341 (2.2186)	loss 3.7630 (3.9480)	grad_norm 1.4820 (1.1365)	
[2022-01-19 03:19:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][640/1251]	eta 0:22:35 lr 0.000932	time 2.4468 (2.2186)	loss 3.3406 (3.9482)	grad_norm 1.0266 (1.1365)	
[2022-01-19 03:20:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][650/1251]	eta 0:22:15 lr 0.000932	time 2.0015 (2.2214)	loss 3.6583 (3.9470)	grad_norm 1.0013 (1.1370)	
[2022-01-19 03:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][660/1251]	eta 0:21:52 lr 0.000932	time 1.8330 (2.2205)	loss 4.3037 (3.9490)	grad_norm 1.2252 (1.1365)	
[2022-01-19 03:20:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][670/1251]	eta 0:21:28 lr 0.000932	time 1.9217 (2.2182)	loss 4.3182 (3.9477)	grad_norm 1.0500 (1.1367)	
[2022-01-19 03:21:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][680/1251]	eta 0:21:05 lr 0.000932	time 2.7851 (2.2167)	loss 3.3021 (3.9479)	grad_norm 1.6325 (1.1380)	
[2022-01-19 03:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][690/1251]	eta 0:20:42 lr 0.000932	time 2.2105 (2.2147)	loss 3.4860 (3.9494)	grad_norm 1.1107 (1.1373)	
[2022-01-19 03:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][700/1251]	eta 0:20:18 lr 0.000932	time 1.8490 (2.2123)	loss 3.4691 (3.9480)	grad_norm 1.0188 (1.1372)	
[2022-01-19 03:22:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][710/1251]	eta 0:19:56 lr 0.000932	time 2.1510 (2.2110)	loss 4.5731 (3.9499)	grad_norm 1.0419 (1.1373)	
[2022-01-19 03:22:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][720/1251]	eta 0:19:33 lr 0.000932	time 2.1672 (2.2100)	loss 4.5988 (3.9530)	grad_norm 1.3450 (1.1366)	
[2022-01-19 03:23:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][730/1251]	eta 0:19:11 lr 0.000932	time 2.6483 (2.2104)	loss 3.6804 (3.9503)	grad_norm 1.0039 (1.1367)	
[2022-01-19 03:23:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][740/1251]	eta 0:18:50 lr 0.000932	time 2.2198 (2.2115)	loss 3.5801 (3.9486)	grad_norm 0.9202 (1.1372)	
[2022-01-19 03:23:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][750/1251]	eta 0:18:28 lr 0.000932	time 2.2709 (2.2123)	loss 2.7312 (3.9460)	grad_norm 1.2745 (1.1370)	
[2022-01-19 03:24:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][760/1251]	eta 0:18:06 lr 0.000932	time 2.2287 (2.2136)	loss 3.3503 (3.9500)	grad_norm 0.9565 (1.1364)	
[2022-01-19 03:24:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][770/1251]	eta 0:17:45 lr 0.000932	time 2.2564 (2.2145)	loss 4.5616 (3.9502)	grad_norm 1.4077 (1.1365)	
[2022-01-19 03:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][780/1251]	eta 0:17:23 lr 0.000932	time 1.8741 (2.2148)	loss 4.1346 (3.9521)	grad_norm 0.9809 (1.1364)	
[2022-01-19 03:25:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][790/1251]	eta 0:17:01 lr 0.000932	time 2.9504 (2.2155)	loss 3.9725 (3.9566)	grad_norm 0.9368 (1.1368)	
[2022-01-19 03:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][800/1251]	eta 0:16:38 lr 0.000932	time 1.7219 (2.2140)	loss 2.9994 (3.9564)	grad_norm 0.9343 (1.1362)	
[2022-01-19 03:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][810/1251]	eta 0:16:15 lr 0.000932	time 2.4332 (2.2109)	loss 4.0675 (3.9547)	grad_norm 1.1096 (1.1363)	
[2022-01-19 03:26:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][820/1251]	eta 0:15:51 lr 0.000932	time 1.9355 (2.2084)	loss 4.3276 (3.9579)	grad_norm 1.0299 (1.1373)	
[2022-01-19 03:26:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][830/1251]	eta 0:15:28 lr 0.000932	time 1.8931 (2.2060)	loss 3.0961 (3.9578)	grad_norm 1.0815 (1.1373)	
[2022-01-19 03:27:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][840/1251]	eta 0:15:06 lr 0.000932	time 2.8086 (2.2065)	loss 3.3664 (3.9576)	grad_norm 0.9341 (1.1369)	
[2022-01-19 03:27:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][850/1251]	eta 0:14:44 lr 0.000932	time 1.8769 (2.2056)	loss 3.9374 (3.9581)	grad_norm 1.1378 (1.1367)	
[2022-01-19 03:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][860/1251]	eta 0:14:22 lr 0.000932	time 1.7917 (2.2061)	loss 2.9212 (3.9562)	grad_norm 1.1232 (1.1361)	
[2022-01-19 03:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][870/1251]	eta 0:14:00 lr 0.000932	time 2.3065 (2.2064)	loss 4.1153 (3.9560)	grad_norm 1.0793 (1.1361)	
[2022-01-19 03:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][880/1251]	eta 0:13:38 lr 0.000932	time 2.8213 (2.2069)	loss 4.3132 (3.9584)	grad_norm 0.8802 (1.1355)	
[2022-01-19 03:28:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][890/1251]	eta 0:13:16 lr 0.000932	time 2.3931 (2.2056)	loss 4.3920 (3.9587)	grad_norm 1.1010 (1.1348)	
[2022-01-19 03:29:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][900/1251]	eta 0:12:53 lr 0.000932	time 1.2183 (2.2050)	loss 4.7863 (3.9597)	grad_norm 0.9624 (1.1337)	
[2022-01-19 03:29:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][910/1251]	eta 0:12:32 lr 0.000932	time 2.4032 (2.2057)	loss 4.0621 (3.9582)	grad_norm 1.0249 (1.1331)	
[2022-01-19 03:29:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][920/1251]	eta 0:12:10 lr 0.000932	time 2.7844 (2.2080)	loss 3.4799 (3.9565)	grad_norm 1.1593 (1.1326)	
[2022-01-19 03:30:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][930/1251]	eta 0:11:49 lr 0.000932	time 1.8532 (2.2093)	loss 3.6517 (3.9564)	grad_norm 1.1348 (1.1323)	
[2022-01-19 03:30:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][940/1251]	eta 0:11:27 lr 0.000932	time 2.1592 (2.2107)	loss 4.1142 (3.9555)	grad_norm 1.1081 (1.1323)	
[2022-01-19 03:31:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][950/1251]	eta 0:11:05 lr 0.000932	time 1.9047 (2.2106)	loss 4.3240 (3.9556)	grad_norm 1.0830 (1.1325)	
[2022-01-19 03:31:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][960/1251]	eta 0:10:42 lr 0.000932	time 1.5823 (2.2066)	loss 4.6999 (3.9575)	grad_norm 0.9778 (1.1327)	
[2022-01-19 03:31:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][970/1251]	eta 0:10:19 lr 0.000932	time 1.8698 (2.2034)	loss 4.3154 (3.9550)	grad_norm 1.3698 (1.1331)	
[2022-01-19 03:32:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][980/1251]	eta 0:09:56 lr 0.000932	time 1.6226 (2.2022)	loss 3.9153 (3.9549)	grad_norm 1.1041 (1.1330)	
[2022-01-19 03:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][990/1251]	eta 0:09:34 lr 0.000932	time 1.6330 (2.2007)	loss 4.0300 (3.9559)	grad_norm 1.3886 (1.1334)	
[2022-01-19 03:32:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1000/1251]	eta 0:09:12 lr 0.000932	time 2.4745 (2.2004)	loss 3.1190 (3.9540)	grad_norm 1.5433 (1.1335)	
[2022-01-19 03:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1010/1251]	eta 0:08:50 lr 0.000932	time 2.2162 (2.2012)	loss 3.6396 (3.9541)	grad_norm 1.1669 (1.1339)	
[2022-01-19 03:33:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1020/1251]	eta 0:08:29 lr 0.000932	time 2.7065 (2.2037)	loss 4.4571 (3.9551)	grad_norm 1.0614 (1.1337)	
[2022-01-19 03:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1030/1251]	eta 0:08:07 lr 0.000932	time 2.2767 (2.2037)	loss 3.9398 (3.9537)	grad_norm 1.0409 (1.1328)	
[2022-01-19 03:34:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1040/1251]	eta 0:07:45 lr 0.000932	time 2.5348 (2.2052)	loss 3.7080 (3.9530)	grad_norm 1.2134 (1.1329)	
[2022-01-19 03:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1050/1251]	eta 0:07:23 lr 0.000931	time 2.5099 (2.2078)	loss 4.0283 (3.9507)	grad_norm 0.9539 (1.1334)	
[2022-01-19 03:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1060/1251]	eta 0:07:01 lr 0.000931	time 2.1999 (2.2074)	loss 4.1358 (3.9497)	grad_norm 1.0271 (1.1321)	
[2022-01-19 03:35:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1070/1251]	eta 0:06:39 lr 0.000931	time 1.8902 (2.2067)	loss 3.4451 (3.9498)	grad_norm 1.1429 (1.1308)	
[2022-01-19 03:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1080/1251]	eta 0:06:16 lr 0.000931	time 2.1949 (2.2044)	loss 4.7966 (3.9488)	grad_norm 1.2537 (1.1306)	
[2022-01-19 03:36:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1090/1251]	eta 0:05:54 lr 0.000931	time 1.8734 (2.2021)	loss 4.2201 (3.9496)	grad_norm 1.2354 (1.1311)	
[2022-01-19 03:36:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1100/1251]	eta 0:05:32 lr 0.000931	time 1.8302 (2.2003)	loss 3.6024 (3.9482)	grad_norm 1.0080 (1.1309)	
[2022-01-19 03:36:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1110/1251]	eta 0:05:10 lr 0.000931	time 2.7513 (2.1996)	loss 4.2419 (3.9480)	grad_norm 1.3862 (1.1318)	
[2022-01-19 03:37:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1120/1251]	eta 0:04:48 lr 0.000931	time 1.8964 (2.1993)	loss 3.7611 (3.9516)	grad_norm 0.9920 (1.1314)	
[2022-01-19 03:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1130/1251]	eta 0:04:26 lr 0.000931	time 3.1361 (2.2010)	loss 3.3953 (3.9515)	grad_norm 1.1392 (1.1310)	
[2022-01-19 03:37:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1140/1251]	eta 0:04:04 lr 0.000931	time 1.7432 (2.2018)	loss 3.3638 (3.9511)	grad_norm 0.9961 (1.1305)	
[2022-01-19 03:38:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1150/1251]	eta 0:03:42 lr 0.000931	time 2.7486 (2.2039)	loss 4.1675 (3.9509)	grad_norm 1.1720 (1.1302)	
[2022-01-19 03:38:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1160/1251]	eta 0:03:20 lr 0.000931	time 1.8900 (2.2028)	loss 3.7132 (3.9497)	grad_norm 1.0477 (1.1301)	
[2022-01-19 03:39:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1170/1251]	eta 0:02:58 lr 0.000931	time 1.7829 (2.2036)	loss 4.5630 (3.9500)	grad_norm 1.0281 (1.1295)	
[2022-01-19 03:39:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1180/1251]	eta 0:02:36 lr 0.000931	time 1.7398 (2.2050)	loss 2.9543 (3.9500)	grad_norm 1.3159 (1.1302)	
[2022-01-19 03:39:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1190/1251]	eta 0:02:14 lr 0.000931	time 2.1253 (2.2064)	loss 3.2482 (3.9502)	grad_norm 1.3294 (1.1305)	
[2022-01-19 03:40:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1200/1251]	eta 0:01:52 lr 0.000931	time 1.7971 (2.2063)	loss 3.3037 (3.9501)	grad_norm 0.9040 (1.1300)	
[2022-01-19 03:40:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1210/1251]	eta 0:01:30 lr 0.000931	time 1.9315 (2.2055)	loss 3.1600 (3.9503)	grad_norm 1.1026 (1.1304)	
[2022-01-19 03:40:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1220/1251]	eta 0:01:08 lr 0.000931	time 1.8643 (2.2036)	loss 4.4099 (3.9508)	grad_norm 0.9962 (1.1305)	
[2022-01-19 03:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1230/1251]	eta 0:00:46 lr 0.000931	time 1.8884 (2.2025)	loss 4.5699 (3.9501)	grad_norm 1.0814 (1.1302)	
[2022-01-19 03:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1240/1251]	eta 0:00:24 lr 0.000931	time 1.6157 (2.2013)	loss 4.0416 (3.9517)	grad_norm 1.2083 (1.1297)	
[2022-01-19 03:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [50/300][1250/1251]	eta 0:00:02 lr 0.000931	time 1.2124 (2.1957)	loss 4.3983 (3.9514)	grad_norm 1.2764 (1.1293)	
[2022-01-19 03:41:52 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 50 training takes 0:45:47
[2022-01-19 03:41:52 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_50 saving......
[2022-01-19 03:42:03 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_50 saved !!!
[2022-01-19 03:42:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 15.640 (15.640)	Loss 1.2268 (1.2268)	Acc@1 73.242 (73.242)	Acc@5 91.016 (91.016)	
[2022-01-19 03:42:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.650 (2.825)	Loss 1.2897 (1.2850)	Acc@1 69.531 (70.366)	Acc@5 88.965 (90.004)	
[2022-01-19 03:42:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.259 (2.403)	Loss 1.2706 (1.2982)	Acc@1 70.508 (70.117)	Acc@5 90.820 (89.900)	
[2022-01-19 03:43:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.690 (2.144)	Loss 1.3158 (1.3013)	Acc@1 69.629 (70.001)	Acc@5 90.039 (89.938)	
[2022-01-19 03:43:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 5.124 (2.000)	Loss 1.2679 (1.2958)	Acc@1 71.094 (70.181)	Acc@5 89.258 (90.025)	
[2022-01-19 03:43:32 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 70.298 Acc@5 90.116
[2022-01-19 03:43:32 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 70.3%
[2022-01-19 03:43:32 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 70.30%
[2022-01-19 03:43:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][0/1251]	eta 7:28:10 lr 0.000931	time 21.4954 (21.4954)	loss 2.8308 (2.8308)	grad_norm 1.2561 (1.2561)	
[2022-01-19 03:44:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][10/1251]	eta 1:23:46 lr 0.000931	time 2.1425 (4.0506)	loss 4.3521 (3.9533)	grad_norm 1.0669 (1.0505)	
[2022-01-19 03:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][20/1251]	eta 1:03:09 lr 0.000931	time 1.5297 (3.0787)	loss 4.3390 (3.9560)	grad_norm 1.3958 (1.1163)	
[2022-01-19 03:44:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][30/1251]	eta 0:56:00 lr 0.000931	time 1.8840 (2.7519)	loss 4.6354 (3.9856)	grad_norm 1.2776 (1.1389)	
[2022-01-19 03:45:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][40/1251]	eta 0:53:35 lr 0.000931	time 3.6514 (2.6549)	loss 3.8377 (3.9405)	grad_norm 0.8846 (1.1433)	
[2022-01-19 03:45:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][50/1251]	eta 0:51:45 lr 0.000931	time 3.1641 (2.5857)	loss 4.0360 (3.9826)	grad_norm 1.1906 (1.1395)	
[2022-01-19 03:46:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][60/1251]	eta 0:50:02 lr 0.000931	time 1.7933 (2.5210)	loss 4.2507 (3.9366)	grad_norm 1.1376 (1.1289)	
[2022-01-19 03:46:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][70/1251]	eta 0:48:40 lr 0.000931	time 2.1874 (2.4727)	loss 4.4099 (3.9850)	grad_norm 1.2965 (1.1449)	
[2022-01-19 03:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][80/1251]	eta 0:47:56 lr 0.000931	time 2.8731 (2.4561)	loss 4.6149 (3.9981)	grad_norm 0.9136 (1.1417)	
[2022-01-19 03:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][90/1251]	eta 0:47:37 lr 0.000931	time 3.6580 (2.4617)	loss 4.7129 (3.9931)	grad_norm 1.0161 (1.1381)	
[2022-01-19 03:47:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][100/1251]	eta 0:46:28 lr 0.000931	time 1.3883 (2.4226)	loss 3.2624 (4.0037)	grad_norm 1.1457 (1.1328)	
[2022-01-19 03:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][110/1251]	eta 0:45:37 lr 0.000931	time 1.6065 (2.3990)	loss 4.2684 (4.0042)	grad_norm 1.0259 (1.1247)	
[2022-01-19 03:48:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][120/1251]	eta 0:44:43 lr 0.000931	time 1.9368 (2.3723)	loss 4.2546 (3.9990)	grad_norm 1.5891 (1.1277)	
[2022-01-19 03:48:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][130/1251]	eta 0:44:10 lr 0.000931	time 2.2175 (2.3646)	loss 4.6297 (4.0006)	grad_norm 1.0329 (1.1246)	
[2022-01-19 03:49:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][140/1251]	eta 0:43:34 lr 0.000931	time 1.9097 (2.3536)	loss 3.5359 (3.9732)	grad_norm 1.1601 (1.1272)	
[2022-01-19 03:49:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][150/1251]	eta 0:42:52 lr 0.000931	time 2.2186 (2.3367)	loss 4.7429 (3.9613)	grad_norm 1.1115 (1.1289)	
[2022-01-19 03:49:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][160/1251]	eta 0:42:10 lr 0.000931	time 2.2345 (2.3191)	loss 3.2240 (3.9713)	grad_norm 0.9320 (1.1277)	
[2022-01-19 03:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][170/1251]	eta 0:41:46 lr 0.000931	time 2.5304 (2.3183)	loss 4.2996 (3.9690)	grad_norm 1.2573 (1.1282)	
[2022-01-19 03:50:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][180/1251]	eta 0:41:20 lr 0.000931	time 2.6930 (2.3163)	loss 4.5215 (3.9677)	grad_norm 1.1139 (1.1274)	
[2022-01-19 03:50:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][190/1251]	eta 0:40:51 lr 0.000931	time 2.4454 (2.3109)	loss 3.2784 (3.9655)	grad_norm 1.1077 (1.1240)	
[2022-01-19 03:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][200/1251]	eta 0:40:20 lr 0.000931	time 2.1631 (2.3033)	loss 4.5365 (3.9653)	grad_norm 1.2015 (1.1242)	
[2022-01-19 03:51:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][210/1251]	eta 0:39:49 lr 0.000931	time 1.9348 (2.2955)	loss 3.6929 (3.9696)	grad_norm 1.3168 (1.1253)	
[2022-01-19 03:51:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][220/1251]	eta 0:39:17 lr 0.000931	time 1.8653 (2.2863)	loss 4.5422 (3.9716)	grad_norm 1.0265 (1.1248)	
[2022-01-19 03:52:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][230/1251]	eta 0:38:56 lr 0.000931	time 2.0411 (2.2885)	loss 2.6745 (3.9535)	grad_norm 1.2122 (1.1234)	
[2022-01-19 03:52:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][240/1251]	eta 0:38:29 lr 0.000931	time 1.8462 (2.2845)	loss 4.2681 (3.9440)	grad_norm 1.2731 (1.1239)	
[2022-01-19 03:53:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][250/1251]	eta 0:38:01 lr 0.000931	time 1.7520 (2.2796)	loss 2.5234 (3.9373)	grad_norm 1.1669 (1.1233)	
[2022-01-19 03:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][260/1251]	eta 0:37:31 lr 0.000931	time 2.2141 (2.2723)	loss 4.6309 (3.9455)	grad_norm 1.1398 (1.1244)	
[2022-01-19 03:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][270/1251]	eta 0:37:01 lr 0.000930	time 2.3730 (2.2645)	loss 4.1354 (3.9481)	grad_norm 1.0347 (1.1221)	
[2022-01-19 03:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][280/1251]	eta 0:36:31 lr 0.000930	time 2.2326 (2.2570)	loss 4.3274 (3.9449)	grad_norm 1.0191 (1.1215)	
[2022-01-19 03:54:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][290/1251]	eta 0:36:10 lr 0.000930	time 2.2744 (2.2586)	loss 3.0902 (3.9387)	grad_norm 1.1596 (1.1227)	
[2022-01-19 03:54:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][300/1251]	eta 0:35:50 lr 0.000930	time 2.4153 (2.2614)	loss 4.1066 (3.9438)	grad_norm 1.0247 (1.1241)	
[2022-01-19 03:55:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][310/1251]	eta 0:35:26 lr 0.000930	time 2.5886 (2.2603)	loss 3.5944 (3.9405)	grad_norm 1.1542 (1.1228)	
[2022-01-19 03:55:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][320/1251]	eta 0:34:57 lr 0.000930	time 1.6266 (2.2527)	loss 4.9450 (3.9353)	grad_norm 1.1849 (1.1223)	
[2022-01-19 03:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][330/1251]	eta 0:34:28 lr 0.000930	time 2.2079 (2.2455)	loss 3.8362 (3.9290)	grad_norm 1.1975 (1.1210)	
[2022-01-19 03:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][340/1251]	eta 0:34:01 lr 0.000930	time 1.8162 (2.2412)	loss 4.6918 (3.9281)	grad_norm 0.9608 (1.1211)	
[2022-01-19 03:56:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][350/1251]	eta 0:33:39 lr 0.000930	time 1.9161 (2.2410)	loss 3.4255 (3.9290)	grad_norm 1.0959 (1.1203)	
[2022-01-19 03:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][360/1251]	eta 0:33:15 lr 0.000930	time 1.8327 (2.2395)	loss 3.2173 (3.9194)	grad_norm 1.1072 (1.1223)	
[2022-01-19 03:57:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][370/1251]	eta 0:32:53 lr 0.000930	time 2.4229 (2.2401)	loss 4.2456 (3.9230)	grad_norm 1.3866 (1.1243)	
[2022-01-19 03:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][380/1251]	eta 0:32:31 lr 0.000930	time 2.1421 (2.2407)	loss 4.6145 (3.9316)	grad_norm 0.9662 (1.1265)	
[2022-01-19 03:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][390/1251]	eta 0:32:09 lr 0.000930	time 1.8613 (2.2406)	loss 4.4618 (3.9244)	grad_norm 1.1444 (1.1284)	
[2022-01-19 03:58:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][400/1251]	eta 0:31:44 lr 0.000930	time 1.6912 (2.2382)	loss 3.7520 (3.9200)	grad_norm 1.1303 (1.1302)	
[2022-01-19 03:58:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][410/1251]	eta 0:31:19 lr 0.000930	time 2.1383 (2.2350)	loss 3.5363 (3.9177)	grad_norm 1.2802 (1.1327)	
[2022-01-19 03:59:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][420/1251]	eta 0:30:57 lr 0.000930	time 2.1710 (2.2349)	loss 3.8589 (3.9200)	grad_norm 1.0927 (1.1328)	
[2022-01-19 03:59:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][430/1251]	eta 0:30:33 lr 0.000930	time 1.8228 (2.2336)	loss 4.1653 (3.9202)	grad_norm 1.3063 (1.1339)	
[2022-01-19 03:59:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][440/1251]	eta 0:30:11 lr 0.000930	time 3.0159 (2.2333)	loss 4.4324 (3.9188)	grad_norm 1.2067 (1.1349)	
[2022-01-19 04:00:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][450/1251]	eta 0:29:48 lr 0.000930	time 1.8616 (2.2327)	loss 4.2837 (3.9217)	grad_norm 1.1221 (1.1333)	
[2022-01-19 04:00:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][460/1251]	eta 0:29:23 lr 0.000930	time 1.5636 (2.2294)	loss 2.6335 (3.9170)	grad_norm 1.4541 (1.1332)	
[2022-01-19 04:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][470/1251]	eta 0:29:00 lr 0.000930	time 2.8874 (2.2290)	loss 3.7538 (3.9155)	grad_norm 1.1098 (1.1325)	
[2022-01-19 04:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][480/1251]	eta 0:28:35 lr 0.000930	time 1.7911 (2.2251)	loss 2.4978 (3.9151)	grad_norm 1.0194 (1.1319)	
[2022-01-19 04:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][490/1251]	eta 0:28:13 lr 0.000930	time 1.9711 (2.2251)	loss 3.0558 (3.9153)	grad_norm 1.2541 (1.1323)	
[2022-01-19 04:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][500/1251]	eta 0:27:52 lr 0.000930	time 1.8237 (2.2276)	loss 4.5790 (3.9194)	grad_norm 0.9326 (1.1315)	
[2022-01-19 04:02:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][510/1251]	eta 0:27:30 lr 0.000930	time 2.1468 (2.2275)	loss 4.1603 (3.9209)	grad_norm 1.1418 (1.1309)	
[2022-01-19 04:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][520/1251]	eta 0:27:08 lr 0.000930	time 2.1927 (2.2274)	loss 4.2452 (3.9191)	grad_norm 1.0041 (1.1308)	
[2022-01-19 04:03:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][530/1251]	eta 0:26:45 lr 0.000930	time 2.2222 (2.2263)	loss 4.7377 (3.9233)	grad_norm 1.3241 (1.1322)	
[2022-01-19 04:03:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][540/1251]	eta 0:26:21 lr 0.000930	time 2.3181 (2.2250)	loss 4.2196 (3.9258)	grad_norm 0.8933 (1.1319)	
[2022-01-19 04:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][550/1251]	eta 0:25:57 lr 0.000930	time 1.6771 (2.2211)	loss 2.9993 (3.9270)	grad_norm 1.0181 (1.1308)	
[2022-01-19 04:04:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][560/1251]	eta 0:25:34 lr 0.000930	time 2.2651 (2.2209)	loss 2.9322 (3.9261)	grad_norm 1.2031 (1.1316)	
[2022-01-19 04:04:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][570/1251]	eta 0:25:12 lr 0.000930	time 1.8449 (2.2204)	loss 3.7327 (3.9251)	grad_norm 1.4238 (1.1344)	
[2022-01-19 04:05:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][580/1251]	eta 0:24:52 lr 0.000930	time 2.8415 (2.2239)	loss 3.6414 (3.9257)	grad_norm 1.0215 (1.1347)	
[2022-01-19 04:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][590/1251]	eta 0:24:28 lr 0.000930	time 1.8267 (2.2220)	loss 3.1409 (3.9266)	grad_norm 1.3287 (1.1351)	
[2022-01-19 04:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][600/1251]	eta 0:24:05 lr 0.000930	time 1.6613 (2.2207)	loss 3.8170 (3.9248)	grad_norm 0.9154 (1.1359)	
[2022-01-19 04:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][610/1251]	eta 0:23:40 lr 0.000930	time 1.8794 (2.2162)	loss 3.9047 (3.9280)	grad_norm 1.3311 (1.1370)	
[2022-01-19 04:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][620/1251]	eta 0:23:16 lr 0.000930	time 2.1769 (2.2133)	loss 3.9994 (3.9309)	grad_norm 1.2205 (1.1371)	
[2022-01-19 04:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][630/1251]	eta 0:22:55 lr 0.000930	time 2.6663 (2.2142)	loss 3.0805 (3.9255)	grad_norm 1.1265 (1.1365)	
[2022-01-19 04:07:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][640/1251]	eta 0:22:32 lr 0.000930	time 2.2023 (2.2130)	loss 3.8114 (3.9248)	grad_norm 1.2368 (1.1357)	
[2022-01-19 04:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][650/1251]	eta 0:22:08 lr 0.000930	time 1.8638 (2.2110)	loss 3.7148 (3.9260)	grad_norm 1.0074 (1.1367)	
[2022-01-19 04:07:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][660/1251]	eta 0:21:45 lr 0.000930	time 2.0675 (2.2094)	loss 4.2133 (3.9272)	grad_norm 1.2434 (1.1372)	
[2022-01-19 04:08:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][670/1251]	eta 0:21:23 lr 0.000930	time 2.5397 (2.2093)	loss 4.0044 (3.9280)	grad_norm 0.9476 (1.1369)	
[2022-01-19 04:08:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][680/1251]	eta 0:21:02 lr 0.000930	time 2.3695 (2.2110)	loss 4.8582 (3.9295)	grad_norm 1.2607 (1.1383)	
[2022-01-19 04:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][690/1251]	eta 0:20:41 lr 0.000930	time 2.2710 (2.2125)	loss 3.3596 (3.9281)	grad_norm 1.0962 (1.1380)	
[2022-01-19 04:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][700/1251]	eta 0:20:19 lr 0.000930	time 2.3923 (2.2139)	loss 3.2306 (3.9270)	grad_norm 1.1097 (1.1388)	
[2022-01-19 04:09:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][710/1251]	eta 0:19:57 lr 0.000930	time 1.9363 (2.2135)	loss 3.4118 (3.9242)	grad_norm 1.1788 (1.1392)	
[2022-01-19 04:10:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][720/1251]	eta 0:19:35 lr 0.000930	time 2.9714 (2.2133)	loss 3.8980 (3.9252)	grad_norm 1.0660 (1.1390)	
[2022-01-19 04:10:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][730/1251]	eta 0:19:11 lr 0.000930	time 2.0535 (2.2106)	loss 4.0817 (3.9212)	grad_norm 1.0332 (1.1375)	
[2022-01-19 04:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][740/1251]	eta 0:18:47 lr 0.000929	time 1.8563 (2.2069)	loss 4.7474 (3.9210)	grad_norm 1.1983 (1.1371)	
[2022-01-19 04:11:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][750/1251]	eta 0:18:24 lr 0.000929	time 2.1800 (2.2055)	loss 4.3072 (3.9208)	grad_norm 1.1268 (1.1384)	
[2022-01-19 04:11:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][760/1251]	eta 0:18:03 lr 0.000929	time 2.9031 (2.2069)	loss 2.7976 (3.9209)	grad_norm 1.2286 (1.1376)	
[2022-01-19 04:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][770/1251]	eta 0:17:41 lr 0.000929	time 2.2856 (2.2074)	loss 4.2771 (3.9195)	grad_norm 1.0794 (1.1373)	
[2022-01-19 04:12:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][780/1251]	eta 0:17:19 lr 0.000929	time 1.6749 (2.2080)	loss 3.1680 (3.9242)	grad_norm 1.0118 (1.1373)	
[2022-01-19 04:12:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][790/1251]	eta 0:16:57 lr 0.000929	time 2.2368 (2.2068)	loss 3.9577 (3.9215)	grad_norm 1.0064 (1.1380)	
[2022-01-19 04:13:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][800/1251]	eta 0:16:35 lr 0.000929	time 2.1551 (2.2064)	loss 3.4778 (3.9246)	grad_norm 1.0527 (1.1383)	
[2022-01-19 04:13:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][810/1251]	eta 0:16:12 lr 0.000929	time 2.2119 (2.2051)	loss 4.1061 (3.9293)	grad_norm 0.9745 (1.1374)	
[2022-01-19 04:13:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][820/1251]	eta 0:15:49 lr 0.000929	time 2.1734 (2.2041)	loss 3.3080 (3.9298)	grad_norm 1.1103 (1.1374)	
[2022-01-19 04:14:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][830/1251]	eta 0:15:27 lr 0.000929	time 2.6489 (2.2027)	loss 3.3773 (3.9296)	grad_norm 1.0355 (1.1369)	
[2022-01-19 04:14:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][840/1251]	eta 0:15:05 lr 0.000929	time 1.8061 (2.2021)	loss 4.0350 (3.9298)	grad_norm 1.2752 (1.1372)	
[2022-01-19 04:14:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][850/1251]	eta 0:14:42 lr 0.000929	time 1.6390 (2.2002)	loss 3.8657 (3.9280)	grad_norm 1.3014 (1.1375)	
[2022-01-19 04:15:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][860/1251]	eta 0:14:20 lr 0.000929	time 1.9708 (2.2010)	loss 3.0376 (3.9268)	grad_norm 1.1512 (1.1395)	
[2022-01-19 04:15:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][870/1251]	eta 0:13:59 lr 0.000929	time 2.6922 (2.2029)	loss 4.4451 (3.9238)	grad_norm 1.1244 (1.1387)	
[2022-01-19 04:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][880/1251]	eta 0:13:38 lr 0.000929	time 2.0884 (2.2052)	loss 4.4117 (3.9244)	grad_norm 1.1645 (1.1398)	
[2022-01-19 04:16:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][890/1251]	eta 0:13:16 lr 0.000929	time 1.9047 (2.2057)	loss 4.1359 (3.9257)	grad_norm 1.0398 (1.1405)	
[2022-01-19 04:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][900/1251]	eta 0:12:54 lr 0.000929	time 3.3305 (2.2078)	loss 3.9372 (3.9251)	grad_norm 0.9583 (1.1413)	
[2022-01-19 04:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][910/1251]	eta 0:12:32 lr 0.000929	time 1.8244 (2.2079)	loss 4.7227 (3.9257)	grad_norm 0.9525 (1.1408)	
[2022-01-19 04:17:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][920/1251]	eta 0:12:09 lr 0.000929	time 1.8797 (2.2053)	loss 2.8242 (3.9216)	grad_norm 0.9841 (1.1406)	
[2022-01-19 04:17:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][930/1251]	eta 0:11:47 lr 0.000929	time 1.9202 (2.2040)	loss 3.8310 (3.9215)	grad_norm 0.9594 (1.1402)	
[2022-01-19 04:18:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][940/1251]	eta 0:11:25 lr 0.000929	time 1.8685 (2.2032)	loss 4.5578 (3.9229)	grad_norm 1.0035 (1.1396)	
[2022-01-19 04:18:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][950/1251]	eta 0:11:03 lr 0.000929	time 2.2358 (2.2034)	loss 3.0077 (3.9240)	grad_norm 1.0968 (1.1388)	
[2022-01-19 04:18:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][960/1251]	eta 0:10:40 lr 0.000929	time 1.8317 (2.2022)	loss 3.8151 (3.9221)	grad_norm 0.9767 (1.1381)	
[2022-01-19 04:19:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][970/1251]	eta 0:10:18 lr 0.000929	time 1.8019 (2.2009)	loss 4.7824 (3.9218)	grad_norm 1.0383 (1.1384)	
[2022-01-19 04:19:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][980/1251]	eta 0:09:56 lr 0.000929	time 1.5003 (2.2008)	loss 3.2480 (3.9196)	grad_norm 1.3620 (1.1390)	
[2022-01-19 04:19:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][990/1251]	eta 0:09:34 lr 0.000929	time 2.0018 (2.2006)	loss 4.4208 (3.9214)	grad_norm 1.3171 (1.1394)	
[2022-01-19 04:20:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1000/1251]	eta 0:09:12 lr 0.000929	time 2.5016 (2.2011)	loss 3.2986 (3.9175)	grad_norm 1.3077 (1.1396)	
[2022-01-19 04:20:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1010/1251]	eta 0:08:50 lr 0.000929	time 2.3160 (2.2009)	loss 2.9040 (3.9166)	grad_norm 1.3401 (1.1404)	
[2022-01-19 04:21:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1020/1251]	eta 0:08:28 lr 0.000929	time 2.2267 (2.2020)	loss 4.4253 (3.9167)	grad_norm 0.9897 (1.1404)	
[2022-01-19 04:21:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1030/1251]	eta 0:08:06 lr 0.000929	time 1.5227 (2.2007)	loss 3.3626 (3.9144)	grad_norm 1.1027 (1.1400)	
[2022-01-19 04:21:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1040/1251]	eta 0:07:44 lr 0.000929	time 1.9500 (2.2002)	loss 3.2173 (3.9131)	grad_norm 0.9973 (1.1390)	
[2022-01-19 04:22:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1050/1251]	eta 0:07:22 lr 0.000929	time 2.5902 (2.2005)	loss 5.0145 (3.9143)	grad_norm 1.4670 (1.1388)	
[2022-01-19 04:22:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1060/1251]	eta 0:07:00 lr 0.000929	time 1.6648 (2.2009)	loss 3.7900 (3.9159)	grad_norm 0.9906 (1.1390)	
[2022-01-19 04:22:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1070/1251]	eta 0:06:38 lr 0.000929	time 1.8583 (2.2003)	loss 3.5605 (3.9173)	grad_norm 1.0249 (1.1380)	
[2022-01-19 04:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1080/1251]	eta 0:06:16 lr 0.000929	time 2.2382 (2.1990)	loss 4.7444 (3.9182)	grad_norm 1.0664 (1.1371)	
[2022-01-19 04:23:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1090/1251]	eta 0:05:53 lr 0.000929	time 2.5689 (2.1979)	loss 3.6182 (3.9197)	grad_norm 1.3508 (1.1376)	
[2022-01-19 04:23:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1100/1251]	eta 0:05:32 lr 0.000929	time 1.8475 (2.2003)	loss 4.3688 (3.9212)	grad_norm 1.1464 (1.1377)	
[2022-01-19 04:24:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1110/1251]	eta 0:05:10 lr 0.000929	time 1.8300 (2.2015)	loss 4.3912 (3.9210)	grad_norm 1.2213 (1.1377)	
[2022-01-19 04:24:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1120/1251]	eta 0:04:48 lr 0.000929	time 1.7392 (2.2024)	loss 3.5360 (3.9207)	grad_norm 1.1685 (1.1370)	
[2022-01-19 04:25:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1130/1251]	eta 0:04:26 lr 0.000929	time 1.9075 (2.2013)	loss 4.4209 (3.9237)	grad_norm 1.3532 (1.1366)	
[2022-01-19 04:25:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1140/1251]	eta 0:04:04 lr 0.000929	time 1.8777 (2.2019)	loss 3.4991 (3.9215)	grad_norm 1.2036 (1.1364)	
[2022-01-19 04:25:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1150/1251]	eta 0:03:42 lr 0.000929	time 2.0535 (2.2011)	loss 3.9862 (3.9225)	grad_norm 1.1318 (1.1364)	
[2022-01-19 04:26:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1160/1251]	eta 0:03:20 lr 0.000929	time 1.9168 (2.2000)	loss 3.3055 (3.9209)	grad_norm 1.2344 (1.1367)	
[2022-01-19 04:26:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1170/1251]	eta 0:02:58 lr 0.000929	time 1.5857 (2.1984)	loss 2.8221 (3.9200)	grad_norm 1.0961 (1.1365)	
[2022-01-19 04:26:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1180/1251]	eta 0:02:36 lr 0.000929	time 2.2006 (2.1980)	loss 4.3238 (3.9235)	grad_norm 1.0412 (1.1365)	
[2022-01-19 04:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1190/1251]	eta 0:02:13 lr 0.000929	time 1.7984 (2.1965)	loss 4.4187 (3.9234)	grad_norm 1.7038 (1.1382)	
[2022-01-19 04:27:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1200/1251]	eta 0:01:52 lr 0.000929	time 2.1195 (2.1977)	loss 3.4211 (3.9231)	grad_norm 1.0901 (1.1383)	
[2022-01-19 04:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1210/1251]	eta 0:01:30 lr 0.000928	time 2.1568 (2.1979)	loss 3.3395 (3.9224)	grad_norm 1.0582 (1.1383)	
[2022-01-19 04:28:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1220/1251]	eta 0:01:08 lr 0.000928	time 2.2906 (2.1991)	loss 4.0467 (3.9230)	grad_norm 0.9077 (1.1377)	
[2022-01-19 04:28:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1230/1251]	eta 0:00:46 lr 0.000928	time 2.0626 (2.1986)	loss 2.8530 (3.9233)	grad_norm 1.2764 (1.1369)	
[2022-01-19 04:28:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1240/1251]	eta 0:00:24 lr 0.000928	time 1.4395 (2.1974)	loss 4.2065 (3.9217)	grad_norm 0.9936 (1.1371)	
[2022-01-19 04:29:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [51/300][1250/1251]	eta 0:00:02 lr 0.000928	time 1.3575 (2.1916)	loss 4.1691 (3.9224)	grad_norm 0.9184 (1.1367)	
[2022-01-19 04:29:14 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 51 training takes 0:45:42
[2022-01-19 04:29:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.267 (18.267)	Loss 1.2371 (1.2371)	Acc@1 70.996 (70.996)	Acc@5 90.625 (90.625)	
[2022-01-19 04:29:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.595 (3.262)	Loss 1.2639 (1.2594)	Acc@1 69.824 (70.490)	Acc@5 90.137 (90.510)	
[2022-01-19 04:30:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.636 (2.506)	Loss 1.2844 (1.2689)	Acc@1 69.141 (70.373)	Acc@5 90.234 (90.369)	
[2022-01-19 04:30:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.586 (2.316)	Loss 1.2942 (1.2806)	Acc@1 70.312 (70.190)	Acc@5 89.648 (90.086)	
[2022-01-19 04:30:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.371 (2.199)	Loss 1.2704 (1.2788)	Acc@1 71.191 (70.415)	Acc@5 90.039 (90.130)	
[2022-01-19 04:30:52 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 70.382 Acc@5 90.078
[2022-01-19 04:30:52 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 70.4%
[2022-01-19 04:30:52 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 70.38%
[2022-01-19 04:31:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][0/1251]	eta 7:26:38 lr 0.000928	time 21.4216 (21.4216)	loss 3.8493 (3.8493)	grad_norm 1.2493 (1.2493)	
[2022-01-19 04:31:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][10/1251]	eta 1:24:28 lr 0.000928	time 2.9692 (4.0845)	loss 4.2144 (3.9480)	grad_norm 1.1202 (1.1552)	
[2022-01-19 04:31:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][20/1251]	eta 1:05:11 lr 0.000928	time 1.8698 (3.1773)	loss 4.1349 (3.9207)	grad_norm 1.1450 (1.1122)	
[2022-01-19 04:32:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][30/1251]	eta 0:57:04 lr 0.000928	time 1.6379 (2.8044)	loss 4.0807 (3.8870)	grad_norm 1.0059 (1.1432)	
[2022-01-19 04:32:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][40/1251]	eta 0:53:34 lr 0.000928	time 3.2609 (2.6546)	loss 4.0577 (3.9654)	grad_norm 0.9708 (1.1295)	
[2022-01-19 04:33:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][50/1251]	eta 0:52:05 lr 0.000928	time 2.5246 (2.6026)	loss 4.4900 (3.9218)	grad_norm 1.1609 (1.1379)	
[2022-01-19 04:33:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][60/1251]	eta 0:50:48 lr 0.000928	time 2.7371 (2.5595)	loss 4.1859 (3.9671)	grad_norm 1.0545 (1.1219)	
[2022-01-19 04:33:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][70/1251]	eta 0:49:27 lr 0.000928	time 1.8809 (2.5128)	loss 3.0062 (3.9524)	grad_norm 1.0676 (1.1282)	
[2022-01-19 04:34:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][80/1251]	eta 0:48:16 lr 0.000928	time 1.9793 (2.4735)	loss 3.5318 (3.9237)	grad_norm 1.0925 (1.1295)	
[2022-01-19 04:34:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][90/1251]	eta 0:47:24 lr 0.000928	time 2.3082 (2.4503)	loss 3.5785 (3.9173)	grad_norm 1.0396 (1.1287)	
[2022-01-19 04:34:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][100/1251]	eta 0:46:19 lr 0.000928	time 1.8957 (2.4145)	loss 4.7327 (3.9003)	grad_norm 1.0209 (1.1234)	
[2022-01-19 04:35:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][110/1251]	eta 0:45:27 lr 0.000928	time 2.1243 (2.3903)	loss 4.3810 (3.9083)	grad_norm 1.2051 (1.1214)	
[2022-01-19 04:35:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][120/1251]	eta 0:44:58 lr 0.000928	time 2.1522 (2.3861)	loss 4.4632 (3.9187)	grad_norm 1.1938 (1.1229)	
[2022-01-19 04:36:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][130/1251]	eta 0:44:43 lr 0.000928	time 3.3612 (2.3937)	loss 4.7831 (3.9407)	grad_norm 1.3963 (1.1278)	
[2022-01-19 04:36:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][140/1251]	eta 0:43:51 lr 0.000928	time 1.9069 (2.3690)	loss 4.2129 (3.9646)	grad_norm 1.3129 (1.1275)	
[2022-01-19 04:36:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][150/1251]	eta 0:43:04 lr 0.000928	time 1.5491 (2.3470)	loss 4.2937 (3.9770)	grad_norm 0.9453 (1.1300)	
[2022-01-19 04:37:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][160/1251]	eta 0:42:22 lr 0.000928	time 1.8038 (2.3307)	loss 4.4391 (3.9899)	grad_norm 1.0502 (1.1260)	
[2022-01-19 04:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][170/1251]	eta 0:42:04 lr 0.000928	time 3.6426 (2.3356)	loss 4.3036 (3.9703)	grad_norm 1.1934 (1.1253)	
[2022-01-19 04:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][180/1251]	eta 0:41:30 lr 0.000928	time 2.1197 (2.3254)	loss 4.5298 (3.9712)	grad_norm 1.0577 (1.1286)	
[2022-01-19 04:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][190/1251]	eta 0:40:53 lr 0.000928	time 1.8990 (2.3125)	loss 4.5964 (3.9633)	grad_norm 1.0353 (1.1272)	
[2022-01-19 04:38:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][200/1251]	eta 0:40:16 lr 0.000928	time 1.7806 (2.2990)	loss 3.7285 (3.9563)	grad_norm 1.0830 (1.1293)	
[2022-01-19 04:38:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][210/1251]	eta 0:39:50 lr 0.000928	time 3.5532 (2.2960)	loss 3.3667 (3.9544)	grad_norm 1.0142 (1.1289)	
[2022-01-19 04:39:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][220/1251]	eta 0:39:24 lr 0.000928	time 1.9373 (2.2930)	loss 3.6625 (3.9646)	grad_norm 1.0922 (1.1299)	
[2022-01-19 04:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][230/1251]	eta 0:38:57 lr 0.000928	time 2.2136 (2.2899)	loss 4.7616 (3.9692)	grad_norm 1.1453 (1.1269)	
[2022-01-19 04:40:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][240/1251]	eta 0:38:29 lr 0.000928	time 1.9444 (2.2839)	loss 4.3178 (3.9620)	grad_norm 0.9925 (1.1269)	
[2022-01-19 04:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][250/1251]	eta 0:38:03 lr 0.000928	time 2.9957 (2.2812)	loss 4.1625 (3.9449)	grad_norm 1.2591 (1.1284)	
[2022-01-19 04:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][260/1251]	eta 0:37:34 lr 0.000928	time 1.7388 (2.2745)	loss 4.1571 (3.9424)	grad_norm 1.1851 (1.1279)	
[2022-01-19 04:41:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][270/1251]	eta 0:37:10 lr 0.000928	time 1.8826 (2.2734)	loss 3.0307 (3.9427)	grad_norm 1.1588 (1.1291)	
[2022-01-19 04:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][280/1251]	eta 0:36:44 lr 0.000928	time 2.5488 (2.2707)	loss 3.9697 (3.9412)	grad_norm 1.2011 (1.1354)	
[2022-01-19 04:41:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][290/1251]	eta 0:36:26 lr 0.000928	time 3.5184 (2.2752)	loss 4.4311 (3.9262)	grad_norm 1.3019 (1.1384)	
[2022-01-19 04:42:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][300/1251]	eta 0:35:55 lr 0.000928	time 1.7956 (2.2665)	loss 4.1841 (3.9251)	grad_norm 1.1504 (1.1382)	
[2022-01-19 04:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][310/1251]	eta 0:35:24 lr 0.000928	time 1.9439 (2.2579)	loss 4.7284 (3.9218)	grad_norm 0.9876 (1.1361)	
[2022-01-19 04:42:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][320/1251]	eta 0:34:57 lr 0.000928	time 1.5485 (2.2530)	loss 4.3269 (3.9163)	grad_norm 0.9191 (1.1349)	
[2022-01-19 04:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][330/1251]	eta 0:34:41 lr 0.000928	time 5.1576 (2.2605)	loss 3.8266 (3.9185)	grad_norm 0.8941 (1.1328)	
[2022-01-19 04:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][340/1251]	eta 0:34:16 lr 0.000928	time 2.5149 (2.2579)	loss 4.5178 (3.9184)	grad_norm 0.9780 (1.1319)	
[2022-01-19 04:44:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][350/1251]	eta 0:33:53 lr 0.000928	time 2.2039 (2.2572)	loss 4.5653 (3.9209)	grad_norm 1.4347 (1.1373)	
[2022-01-19 04:44:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][360/1251]	eta 0:33:30 lr 0.000928	time 1.8700 (2.2562)	loss 3.8792 (3.9199)	grad_norm 0.9516 (1.1396)	
[2022-01-19 04:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][370/1251]	eta 0:33:04 lr 0.000928	time 2.8331 (2.2531)	loss 3.6914 (3.9278)	grad_norm 1.1846 (1.1384)	
[2022-01-19 04:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][380/1251]	eta 0:32:36 lr 0.000928	time 1.8893 (2.2464)	loss 3.3531 (3.9341)	grad_norm 1.1717 (1.1371)	
[2022-01-19 04:45:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][390/1251]	eta 0:32:11 lr 0.000928	time 2.1554 (2.2428)	loss 3.4325 (3.9405)	grad_norm 1.2691 (1.1359)	
[2022-01-19 04:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][400/1251]	eta 0:31:46 lr 0.000928	time 2.4582 (2.2400)	loss 4.3330 (3.9448)	grad_norm 1.3437 (1.1372)	
[2022-01-19 04:46:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][410/1251]	eta 0:31:22 lr 0.000928	time 2.5042 (2.2380)	loss 3.9779 (3.9481)	grad_norm 1.2079 (1.1360)	
[2022-01-19 04:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][420/1251]	eta 0:30:59 lr 0.000928	time 2.1890 (2.2376)	loss 2.5983 (3.9438)	grad_norm 1.1968 (1.1368)	
[2022-01-19 04:46:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][430/1251]	eta 0:30:38 lr 0.000927	time 2.7820 (2.2388)	loss 4.2823 (3.9455)	grad_norm 1.1259 (1.1390)	
[2022-01-19 04:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][440/1251]	eta 0:30:14 lr 0.000927	time 1.5329 (2.2374)	loss 4.1287 (3.9485)	grad_norm 1.1723 (1.1392)	
[2022-01-19 04:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][450/1251]	eta 0:29:51 lr 0.000927	time 2.5515 (2.2366)	loss 4.5094 (3.9512)	grad_norm 1.1685 (1.1387)	
[2022-01-19 04:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][460/1251]	eta 0:29:27 lr 0.000927	time 2.4985 (2.2346)	loss 2.9619 (3.9510)	grad_norm 1.1055 (1.1378)	
[2022-01-19 04:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][470/1251]	eta 0:29:04 lr 0.000927	time 3.2489 (2.2343)	loss 4.0426 (3.9517)	grad_norm 1.1866 (1.1386)	
[2022-01-19 04:48:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][480/1251]	eta 0:28:41 lr 0.000927	time 1.9357 (2.2322)	loss 4.7021 (3.9568)	grad_norm 1.4398 (1.1392)	
[2022-01-19 04:49:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][490/1251]	eta 0:28:17 lr 0.000927	time 2.1123 (2.2311)	loss 3.0279 (3.9582)	grad_norm 1.0785 (1.1400)	
[2022-01-19 04:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][500/1251]	eta 0:27:56 lr 0.000927	time 2.4445 (2.2328)	loss 4.6122 (3.9598)	grad_norm 1.0911 (1.1403)	
[2022-01-19 04:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][510/1251]	eta 0:27:33 lr 0.000927	time 2.1133 (2.2313)	loss 3.3457 (3.9591)	grad_norm 1.1748 (1.1392)	
[2022-01-19 04:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][520/1251]	eta 0:27:10 lr 0.000927	time 1.9001 (2.2308)	loss 4.4254 (3.9637)	grad_norm 1.0679 (1.1391)	
[2022-01-19 04:50:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][530/1251]	eta 0:26:48 lr 0.000927	time 2.4703 (2.2304)	loss 3.8365 (3.9608)	grad_norm 0.9485 (1.1384)	
[2022-01-19 04:50:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][540/1251]	eta 0:26:24 lr 0.000927	time 2.1712 (2.2290)	loss 3.2274 (3.9572)	grad_norm 1.1255 (1.1389)	
[2022-01-19 04:51:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][550/1251]	eta 0:26:00 lr 0.000927	time 2.1707 (2.2265)	loss 4.0709 (3.9530)	grad_norm 1.4239 (1.1391)	
[2022-01-19 04:51:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][560/1251]	eta 0:25:36 lr 0.000927	time 2.5659 (2.2241)	loss 3.6941 (3.9561)	grad_norm 1.2909 (1.1413)	
[2022-01-19 04:52:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][570/1251]	eta 0:25:14 lr 0.000927	time 1.7476 (2.2234)	loss 3.5448 (3.9524)	grad_norm 1.3563 (1.1416)	
[2022-01-19 04:52:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][580/1251]	eta 0:24:52 lr 0.000927	time 1.6564 (2.2237)	loss 4.1471 (3.9519)	grad_norm 1.1090 (1.1405)	
[2022-01-19 04:52:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][590/1251]	eta 0:24:29 lr 0.000927	time 2.7849 (2.2238)	loss 4.3472 (3.9516)	grad_norm 0.9968 (1.1391)	
[2022-01-19 04:53:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][600/1251]	eta 0:24:06 lr 0.000927	time 2.0427 (2.2220)	loss 3.6998 (3.9476)	grad_norm 0.9864 (1.1403)	
[2022-01-19 04:53:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][610/1251]	eta 0:23:42 lr 0.000927	time 1.8823 (2.2193)	loss 4.3128 (3.9448)	grad_norm 1.0372 (1.1402)	
[2022-01-19 04:53:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][620/1251]	eta 0:23:19 lr 0.000927	time 1.8572 (2.2172)	loss 4.2541 (3.9480)	grad_norm 1.2004 (1.1396)	
[2022-01-19 04:54:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][630/1251]	eta 0:22:55 lr 0.000927	time 2.2684 (2.2155)	loss 3.2676 (3.9470)	grad_norm 1.2183 (1.1394)	
[2022-01-19 04:54:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][640/1251]	eta 0:22:32 lr 0.000927	time 2.2850 (2.2144)	loss 2.9614 (3.9432)	grad_norm 1.0643 (1.1397)	
[2022-01-19 04:54:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][650/1251]	eta 0:22:09 lr 0.000927	time 2.2063 (2.2127)	loss 4.3984 (3.9435)	grad_norm 1.0571 (1.1383)	
[2022-01-19 04:55:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][660/1251]	eta 0:21:48 lr 0.000927	time 1.8782 (2.2146)	loss 3.8246 (3.9413)	grad_norm 1.0637 (1.1368)	
[2022-01-19 04:55:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][670/1251]	eta 0:21:25 lr 0.000927	time 1.7783 (2.2119)	loss 4.4260 (3.9427)	grad_norm 1.1306 (1.1366)	
[2022-01-19 04:55:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][680/1251]	eta 0:21:03 lr 0.000927	time 2.1086 (2.2130)	loss 3.3365 (3.9385)	grad_norm 1.1349 (1.1379)	
[2022-01-19 04:56:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][690/1251]	eta 0:20:42 lr 0.000927	time 1.2270 (2.2143)	loss 3.9801 (3.9368)	grad_norm 1.1518 (1.1374)	
[2022-01-19 04:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][700/1251]	eta 0:20:21 lr 0.000927	time 2.2009 (2.2177)	loss 4.0356 (3.9368)	grad_norm 1.2627 (1.1367)	
[2022-01-19 04:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][710/1251]	eta 0:19:59 lr 0.000927	time 2.4132 (2.2178)	loss 2.8621 (3.9392)	grad_norm 1.0925 (1.1360)	
[2022-01-19 04:57:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][720/1251]	eta 0:19:36 lr 0.000927	time 2.1451 (2.2160)	loss 4.3389 (3.9416)	grad_norm 1.2309 (1.1365)	
[2022-01-19 04:57:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][730/1251]	eta 0:19:13 lr 0.000927	time 2.1827 (2.2140)	loss 4.1198 (3.9362)	grad_norm 1.1654 (1.1376)	
[2022-01-19 04:58:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][740/1251]	eta 0:18:51 lr 0.000927	time 2.5372 (2.2142)	loss 4.1548 (3.9399)	grad_norm 1.2318 (1.1397)	
[2022-01-19 04:58:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][750/1251]	eta 0:18:28 lr 0.000927	time 1.9897 (2.2131)	loss 2.8962 (3.9398)	grad_norm 1.1181 (1.1394)	
[2022-01-19 04:58:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][760/1251]	eta 0:18:06 lr 0.000927	time 1.9277 (2.2127)	loss 2.7659 (3.9385)	grad_norm 1.2811 (1.1410)	
[2022-01-19 04:59:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][770/1251]	eta 0:17:43 lr 0.000927	time 2.2299 (2.2114)	loss 3.5433 (3.9340)	grad_norm 1.4028 (1.1427)	
[2022-01-19 04:59:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][780/1251]	eta 0:17:21 lr 0.000927	time 2.1108 (2.2106)	loss 3.4205 (3.9293)	grad_norm 1.0216 (1.1428)	
[2022-01-19 05:00:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][790/1251]	eta 0:16:58 lr 0.000927	time 1.5683 (2.2092)	loss 4.8174 (3.9291)	grad_norm 1.0480 (1.1433)	
[2022-01-19 05:00:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][800/1251]	eta 0:16:36 lr 0.000927	time 2.1830 (2.2105)	loss 4.3590 (3.9305)	grad_norm 1.0165 (1.1427)	
[2022-01-19 05:00:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][810/1251]	eta 0:16:13 lr 0.000927	time 1.8936 (2.2084)	loss 3.2552 (3.9307)	grad_norm 1.1928 (1.1425)	
[2022-01-19 05:01:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][820/1251]	eta 0:15:51 lr 0.000927	time 2.0366 (2.2066)	loss 4.0761 (3.9326)	grad_norm 1.3133 (1.1423)	
[2022-01-19 05:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][830/1251]	eta 0:15:28 lr 0.000927	time 1.5427 (2.2045)	loss 3.9820 (3.9340)	grad_norm 0.9431 (1.1412)	
[2022-01-19 05:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][840/1251]	eta 0:15:05 lr 0.000927	time 1.6869 (2.2035)	loss 3.2784 (3.9324)	grad_norm 1.0734 (1.1419)	
[2022-01-19 05:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][850/1251]	eta 0:14:43 lr 0.000927	time 2.3558 (2.2027)	loss 4.4976 (3.9322)	grad_norm 1.0962 (1.1426)	
[2022-01-19 05:02:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][860/1251]	eta 0:14:20 lr 0.000927	time 1.8312 (2.2008)	loss 4.6463 (3.9356)	grad_norm 1.0146 (1.1420)	
[2022-01-19 05:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][870/1251]	eta 0:13:58 lr 0.000927	time 1.8578 (2.2007)	loss 4.3218 (3.9355)	grad_norm 1.0771 (1.1414)	
[2022-01-19 05:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][880/1251]	eta 0:13:36 lr 0.000927	time 1.8911 (2.2003)	loss 2.9865 (3.9353)	grad_norm 1.2817 (1.1419)	
[2022-01-19 05:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][890/1251]	eta 0:13:15 lr 0.000926	time 2.6404 (2.2027)	loss 4.6856 (3.9383)	grad_norm 0.9509 (1.1423)	
[2022-01-19 05:03:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][900/1251]	eta 0:12:53 lr 0.000926	time 2.0785 (2.2043)	loss 4.2026 (3.9375)	grad_norm 0.9940 (1.1412)	
[2022-01-19 05:04:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][910/1251]	eta 0:12:32 lr 0.000926	time 2.0489 (2.2061)	loss 3.5981 (3.9371)	grad_norm 1.0041 (1.1407)	
[2022-01-19 05:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][920/1251]	eta 0:12:11 lr 0.000926	time 1.6226 (2.2094)	loss 4.4935 (3.9352)	grad_norm 0.9916 (1.1412)	
[2022-01-19 05:05:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][930/1251]	eta 0:11:48 lr 0.000926	time 1.8962 (2.2086)	loss 3.5665 (3.9320)	grad_norm 1.1028 (1.1411)	
[2022-01-19 05:05:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][940/1251]	eta 0:11:26 lr 0.000926	time 1.8768 (2.2074)	loss 4.2293 (3.9357)	grad_norm 0.9717 (1.1415)	
[2022-01-19 05:05:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][950/1251]	eta 0:11:03 lr 0.000926	time 1.9045 (2.2043)	loss 4.1946 (3.9352)	grad_norm 1.0061 (1.1416)	
[2022-01-19 05:06:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][960/1251]	eta 0:10:41 lr 0.000926	time 1.9275 (2.2032)	loss 4.1758 (3.9367)	grad_norm 1.0534 (1.1423)	
[2022-01-19 05:06:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][970/1251]	eta 0:10:18 lr 0.000926	time 1.5596 (2.2023)	loss 4.1104 (3.9351)	grad_norm 1.0231 (1.1421)	
[2022-01-19 05:06:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][980/1251]	eta 0:09:57 lr 0.000926	time 3.0397 (2.2031)	loss 3.0464 (3.9354)	grad_norm 0.9196 (1.1415)	
[2022-01-19 05:07:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][990/1251]	eta 0:09:35 lr 0.000926	time 1.8797 (2.2039)	loss 4.6689 (3.9359)	grad_norm 1.2320 (1.1415)	
[2022-01-19 05:07:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1000/1251]	eta 0:09:13 lr 0.000926	time 1.8946 (2.2053)	loss 4.1252 (3.9365)	grad_norm 1.0190 (1.1407)	
[2022-01-19 05:08:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1010/1251]	eta 0:08:51 lr 0.000926	time 1.8658 (2.2045)	loss 4.4094 (3.9350)	grad_norm 0.9141 (1.1406)	
[2022-01-19 05:08:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1020/1251]	eta 0:08:29 lr 0.000926	time 2.5692 (2.2039)	loss 4.0648 (3.9353)	grad_norm 1.0109 (1.1409)	
[2022-01-19 05:08:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1030/1251]	eta 0:08:06 lr 0.000926	time 1.9889 (2.2028)	loss 4.7250 (3.9376)	grad_norm 1.1401 (1.1404)	
[2022-01-19 05:09:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1040/1251]	eta 0:07:45 lr 0.000926	time 2.5353 (2.2046)	loss 3.6659 (3.9371)	grad_norm 1.0757 (1.1403)	
[2022-01-19 05:09:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1050/1251]	eta 0:07:22 lr 0.000926	time 1.9270 (2.2038)	loss 2.7231 (3.9377)	grad_norm 1.3471 (1.1404)	
[2022-01-19 05:09:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1060/1251]	eta 0:07:00 lr 0.000926	time 2.2270 (2.2035)	loss 3.8752 (3.9407)	grad_norm 1.0658 (1.1398)	
[2022-01-19 05:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1070/1251]	eta 0:06:38 lr 0.000926	time 1.9798 (2.2022)	loss 3.5637 (3.9388)	grad_norm 1.1711 (1.1398)	
[2022-01-19 05:10:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1080/1251]	eta 0:06:16 lr 0.000926	time 3.3612 (2.2032)	loss 3.5925 (3.9399)	grad_norm 1.4055 (1.1405)	
[2022-01-19 05:10:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1090/1251]	eta 0:05:54 lr 0.000926	time 1.4883 (2.2017)	loss 3.9218 (3.9405)	grad_norm 1.6308 (1.1413)	
[2022-01-19 05:11:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1100/1251]	eta 0:05:32 lr 0.000926	time 1.6621 (2.2023)	loss 3.9509 (3.9409)	grad_norm 1.2612 (1.1419)	
[2022-01-19 05:11:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1110/1251]	eta 0:05:10 lr 0.000926	time 1.7007 (2.2015)	loss 3.3485 (3.9431)	grad_norm 0.9934 (1.1410)	
[2022-01-19 05:12:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1120/1251]	eta 0:04:48 lr 0.000926	time 2.8150 (2.2023)	loss 3.4348 (3.9427)	grad_norm 1.1030 (1.1416)	
[2022-01-19 05:12:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1130/1251]	eta 0:04:26 lr 0.000926	time 1.7756 (2.2016)	loss 3.0864 (3.9424)	grad_norm 1.0384 (1.1416)	
[2022-01-19 05:12:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1140/1251]	eta 0:04:04 lr 0.000926	time 1.7554 (2.2017)	loss 3.7960 (3.9417)	grad_norm 1.0486 (1.1414)	
[2022-01-19 05:13:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1150/1251]	eta 0:03:42 lr 0.000926	time 1.8854 (2.2011)	loss 4.2458 (3.9439)	grad_norm 1.0493 (1.1412)	
[2022-01-19 05:13:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1160/1251]	eta 0:03:20 lr 0.000926	time 3.3090 (2.2032)	loss 3.5632 (3.9431)	grad_norm 1.0420 (1.1410)	
[2022-01-19 05:13:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1170/1251]	eta 0:02:58 lr 0.000926	time 1.6494 (2.2031)	loss 3.0238 (3.9400)	grad_norm 1.1049 (1.1407)	
[2022-01-19 05:14:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1180/1251]	eta 0:02:36 lr 0.000926	time 1.6103 (2.2024)	loss 4.6388 (3.9432)	grad_norm 1.0492 (1.1404)	
[2022-01-19 05:14:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1190/1251]	eta 0:02:14 lr 0.000926	time 1.8393 (2.2016)	loss 4.6591 (3.9443)	grad_norm 1.0793 (1.1398)	
[2022-01-19 05:14:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1200/1251]	eta 0:01:52 lr 0.000926	time 2.1389 (2.2006)	loss 3.7409 (3.9428)	grad_norm 1.1575 (1.1395)	
[2022-01-19 05:15:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1210/1251]	eta 0:01:30 lr 0.000926	time 2.0639 (2.1992)	loss 4.3514 (3.9422)	grad_norm 1.0077 (1.1390)	
[2022-01-19 05:15:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1220/1251]	eta 0:01:08 lr 0.000926	time 1.9133 (2.1989)	loss 3.7270 (3.9406)	grad_norm 1.0688 (1.1386)	
[2022-01-19 05:15:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1230/1251]	eta 0:00:46 lr 0.000926	time 2.0879 (2.1987)	loss 3.8129 (3.9397)	grad_norm 0.9563 (1.1384)	
[2022-01-19 05:16:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1240/1251]	eta 0:00:24 lr 0.000926	time 1.8065 (2.1988)	loss 3.9331 (3.9401)	grad_norm 1.0016 (1.1379)	
[2022-01-19 05:16:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [52/300][1250/1251]	eta 0:00:02 lr 0.000926	time 1.2777 (2.1939)	loss 4.2379 (3.9399)	grad_norm 1.0725 (1.1372)	
[2022-01-19 05:16:37 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 52 training takes 0:45:44
[2022-01-19 05:16:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.402 (18.402)	Loss 1.2946 (1.2946)	Acc@1 70.801 (70.801)	Acc@5 90.039 (90.039)	
[2022-01-19 05:17:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.977 (3.500)	Loss 1.2464 (1.2700)	Acc@1 71.289 (71.245)	Acc@5 90.918 (90.368)	
[2022-01-19 05:17:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.271 (2.489)	Loss 1.3191 (1.2818)	Acc@1 69.336 (70.764)	Acc@5 89.844 (90.299)	
[2022-01-19 05:17:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.966 (2.242)	Loss 1.3413 (1.2919)	Acc@1 69.434 (70.347)	Acc@5 89.551 (90.316)	
[2022-01-19 05:18:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.603 (2.151)	Loss 1.2795 (1.2864)	Acc@1 71.777 (70.262)	Acc@5 90.527 (90.396)	
[2022-01-19 05:18:12 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 70.296 Acc@5 90.300
[2022-01-19 05:18:12 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 70.3%
[2022-01-19 05:18:12 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 70.38%
[2022-01-19 05:18:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][0/1251]	eta 7:24:04 lr 0.000926	time 21.2988 (21.2988)	loss 4.2881 (4.2881)	grad_norm 1.0596 (1.0596)	
[2022-01-19 05:18:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][10/1251]	eta 1:24:59 lr 0.000926	time 2.0357 (4.1088)	loss 3.0355 (3.6219)	grad_norm 1.1637 (1.0738)	
[2022-01-19 05:19:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][20/1251]	eta 1:06:42 lr 0.000926	time 2.3353 (3.2518)	loss 2.6548 (3.6003)	grad_norm 1.1889 (1.0963)	
[2022-01-19 05:19:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][30/1251]	eta 0:59:15 lr 0.000926	time 1.9365 (2.9117)	loss 4.4287 (3.7167)	grad_norm 1.0598 (1.1051)	
[2022-01-19 05:20:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][40/1251]	eta 0:55:44 lr 0.000926	time 3.3282 (2.7617)	loss 4.8129 (3.7660)	grad_norm 1.0335 (1.1190)	
[2022-01-19 05:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][50/1251]	eta 0:52:44 lr 0.000926	time 1.5434 (2.6349)	loss 4.6331 (3.8176)	grad_norm 1.5880 (1.1383)	
[2022-01-19 05:20:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][60/1251]	eta 0:50:26 lr 0.000926	time 1.6701 (2.5414)	loss 4.4174 (3.8772)	grad_norm 1.1020 (1.1345)	
[2022-01-19 05:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][70/1251]	eta 0:48:52 lr 0.000926	time 2.2469 (2.4829)	loss 4.7411 (3.9321)	grad_norm 1.0308 (1.1292)	
[2022-01-19 05:21:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][80/1251]	eta 0:47:36 lr 0.000926	time 2.5002 (2.4393)	loss 4.8907 (3.9060)	grad_norm 1.2894 (1.1214)	
[2022-01-19 05:21:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][90/1251]	eta 0:46:51 lr 0.000926	time 1.9362 (2.4214)	loss 3.7366 (3.9077)	grad_norm 1.2454 (1.1147)	
[2022-01-19 05:22:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][100/1251]	eta 0:46:22 lr 0.000925	time 2.0105 (2.4177)	loss 3.6131 (3.9253)	grad_norm 1.0899 (1.1173)	
[2022-01-19 05:22:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][110/1251]	eta 0:45:48 lr 0.000925	time 2.2005 (2.4086)	loss 3.5658 (3.9221)	grad_norm 1.1574 (1.1162)	
[2022-01-19 05:23:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][120/1251]	eta 0:45:15 lr 0.000925	time 3.1092 (2.4012)	loss 2.7917 (3.9063)	grad_norm 1.1753 (1.1221)	
[2022-01-19 05:23:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][130/1251]	eta 0:44:21 lr 0.000925	time 1.5965 (2.3745)	loss 4.6022 (3.9271)	grad_norm 0.9860 (1.1248)	
[2022-01-19 05:23:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][140/1251]	eta 0:43:23 lr 0.000925	time 2.0140 (2.3432)	loss 2.5843 (3.9159)	grad_norm 1.3349 (1.1237)	
[2022-01-19 05:24:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][150/1251]	eta 0:42:43 lr 0.000925	time 2.7989 (2.3282)	loss 4.4565 (3.8889)	grad_norm 1.0667 (1.1351)	
[2022-01-19 05:24:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][160/1251]	eta 0:42:06 lr 0.000925	time 2.2665 (2.3155)	loss 4.2139 (3.8994)	grad_norm 0.9077 (1.1329)	
[2022-01-19 05:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][170/1251]	eta 0:41:32 lr 0.000925	time 1.8826 (2.3062)	loss 4.2763 (3.8898)	grad_norm 1.0070 (1.1353)	
[2022-01-19 05:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][180/1251]	eta 0:41:07 lr 0.000925	time 2.4770 (2.3039)	loss 4.2485 (3.8886)	grad_norm 1.2379 (1.1306)	
[2022-01-19 05:25:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][190/1251]	eta 0:40:47 lr 0.000925	time 2.9912 (2.3065)	loss 4.3978 (3.8876)	grad_norm 1.0487 (1.1289)	
[2022-01-19 05:25:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][200/1251]	eta 0:40:23 lr 0.000925	time 2.9890 (2.3058)	loss 4.9617 (3.8886)	grad_norm 1.0000 (1.1292)	
[2022-01-19 05:26:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][210/1251]	eta 0:39:48 lr 0.000925	time 1.8938 (2.2947)	loss 4.3141 (3.8884)	grad_norm 1.1204 (1.1278)	
[2022-01-19 05:26:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][220/1251]	eta 0:39:18 lr 0.000925	time 2.6508 (2.2875)	loss 4.1159 (3.9059)	grad_norm 1.0403 (1.1264)	
[2022-01-19 05:26:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][230/1251]	eta 0:38:46 lr 0.000925	time 2.4294 (2.2788)	loss 3.7169 (3.9012)	grad_norm 1.3063 (1.1262)	
[2022-01-19 05:27:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][240/1251]	eta 0:38:12 lr 0.000925	time 1.9154 (2.2679)	loss 3.7070 (3.9051)	grad_norm 1.0442 (1.1265)	
[2022-01-19 05:27:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][250/1251]	eta 0:37:41 lr 0.000925	time 1.5503 (2.2597)	loss 4.8466 (3.9011)	grad_norm 1.0584 (1.1271)	
[2022-01-19 05:28:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][260/1251]	eta 0:37:19 lr 0.000925	time 3.4561 (2.2601)	loss 3.5226 (3.9059)	grad_norm 1.0985 (1.1292)	
[2022-01-19 05:28:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][270/1251]	eta 0:36:56 lr 0.000925	time 2.7106 (2.2596)	loss 4.0834 (3.9044)	grad_norm 1.1158 (1.1308)	
[2022-01-19 05:28:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][280/1251]	eta 0:36:32 lr 0.000925	time 2.2149 (2.2580)	loss 4.0473 (3.9086)	grad_norm 1.2848 (1.1337)	
[2022-01-19 05:29:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][290/1251]	eta 0:36:13 lr 0.000925	time 2.1352 (2.2621)	loss 3.4476 (3.9055)	grad_norm 1.6429 (1.1364)	
[2022-01-19 05:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][300/1251]	eta 0:35:56 lr 0.000925	time 3.5484 (2.2678)	loss 2.8718 (3.9036)	grad_norm 1.0618 (1.1351)	
[2022-01-19 05:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][310/1251]	eta 0:35:31 lr 0.000925	time 2.5042 (2.2653)	loss 4.2557 (3.9023)	grad_norm 1.1634 (1.1327)	
[2022-01-19 05:30:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][320/1251]	eta 0:35:00 lr 0.000925	time 2.1959 (2.2565)	loss 3.8579 (3.8872)	grad_norm 1.0949 (1.1354)	
[2022-01-19 05:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][330/1251]	eta 0:34:29 lr 0.000925	time 1.9443 (2.2472)	loss 4.1269 (3.8945)	grad_norm 0.9703 (1.1338)	
[2022-01-19 05:30:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][340/1251]	eta 0:34:04 lr 0.000925	time 2.5099 (2.2444)	loss 4.4348 (3.8886)	grad_norm 0.9918 (1.1326)	
[2022-01-19 05:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][350/1251]	eta 0:33:39 lr 0.000925	time 1.8844 (2.2413)	loss 3.8387 (3.8929)	grad_norm 1.1000 (1.1310)	
[2022-01-19 05:31:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][360/1251]	eta 0:33:14 lr 0.000925	time 1.9702 (2.2382)	loss 4.4025 (3.8965)	grad_norm 1.1520 (1.1313)	
[2022-01-19 05:32:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][370/1251]	eta 0:32:49 lr 0.000925	time 2.9467 (2.2353)	loss 4.6704 (3.8985)	grad_norm 1.1400 (1.1310)	
[2022-01-19 05:32:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][380/1251]	eta 0:32:29 lr 0.000925	time 2.8900 (2.2382)	loss 4.1614 (3.9003)	grad_norm 1.0613 (1.1323)	
[2022-01-19 05:32:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][390/1251]	eta 0:32:03 lr 0.000925	time 1.5773 (2.2344)	loss 4.4525 (3.9012)	grad_norm 1.0609 (1.1331)	
[2022-01-19 05:33:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][400/1251]	eta 0:31:46 lr 0.000925	time 2.2707 (2.2403)	loss 4.2574 (3.9063)	grad_norm 1.0296 (1.1334)	
[2022-01-19 05:33:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][410/1251]	eta 0:31:19 lr 0.000925	time 1.9497 (2.2351)	loss 4.3547 (3.9086)	grad_norm 1.4141 (1.1327)	
[2022-01-19 05:33:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][420/1251]	eta 0:31:02 lr 0.000925	time 5.7344 (2.2412)	loss 3.8122 (3.9140)	grad_norm 0.8887 (1.1323)	
[2022-01-19 05:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][430/1251]	eta 0:30:36 lr 0.000925	time 1.7195 (2.2366)	loss 3.5559 (3.9135)	grad_norm 1.1096 (1.1310)	
[2022-01-19 05:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][440/1251]	eta 0:30:14 lr 0.000925	time 1.8577 (2.2373)	loss 4.1605 (3.9140)	grad_norm 1.3528 (1.1314)	
[2022-01-19 05:35:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][450/1251]	eta 0:29:48 lr 0.000925	time 1.9260 (2.2331)	loss 3.6235 (3.9164)	grad_norm 1.2206 (1.1306)	
[2022-01-19 05:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][460/1251]	eta 0:29:26 lr 0.000925	time 3.5720 (2.2328)	loss 3.9826 (3.9171)	grad_norm 1.4702 (1.1298)	
[2022-01-19 05:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][470/1251]	eta 0:29:00 lr 0.000925	time 1.8263 (2.2288)	loss 4.3938 (3.9210)	grad_norm 1.3000 (1.1302)	
[2022-01-19 05:36:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][480/1251]	eta 0:28:40 lr 0.000925	time 2.9660 (2.2313)	loss 4.3194 (3.9172)	grad_norm 1.3378 (1.1291)	
[2022-01-19 05:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][490/1251]	eta 0:28:18 lr 0.000925	time 2.4875 (2.2321)	loss 3.1108 (3.9182)	grad_norm 1.1608 (1.1281)	
[2022-01-19 05:36:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][500/1251]	eta 0:27:55 lr 0.000925	time 3.1479 (2.2312)	loss 4.2859 (3.9164)	grad_norm 1.0524 (1.1300)	
[2022-01-19 05:37:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][510/1251]	eta 0:27:31 lr 0.000925	time 1.9111 (2.2292)	loss 4.4602 (3.9213)	grad_norm 1.0865 (1.1307)	
[2022-01-19 05:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][520/1251]	eta 0:27:06 lr 0.000925	time 1.8766 (2.2253)	loss 4.3559 (3.9238)	grad_norm 1.1502 (1.1325)	
[2022-01-19 05:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][530/1251]	eta 0:26:44 lr 0.000925	time 2.4826 (2.2247)	loss 4.6657 (3.9284)	grad_norm 1.1662 (1.1331)	
[2022-01-19 05:38:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][540/1251]	eta 0:26:22 lr 0.000925	time 2.6654 (2.2264)	loss 3.4921 (3.9296)	grad_norm 1.0347 (1.1346)	
[2022-01-19 05:38:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][550/1251]	eta 0:26:02 lr 0.000924	time 2.8791 (2.2286)	loss 4.8679 (3.9379)	grad_norm 1.0660 (1.1334)	
[2022-01-19 05:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][560/1251]	eta 0:25:38 lr 0.000924	time 1.5930 (2.2260)	loss 3.4617 (3.9361)	grad_norm 1.0584 (1.1329)	
[2022-01-19 05:39:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][570/1251]	eta 0:25:15 lr 0.000924	time 2.2978 (2.2252)	loss 4.2759 (3.9345)	grad_norm 1.0799 (1.1324)	
[2022-01-19 05:39:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][580/1251]	eta 0:24:51 lr 0.000924	time 2.3729 (2.2225)	loss 4.5175 (3.9335)	grad_norm 1.0035 (1.1312)	
[2022-01-19 05:40:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][590/1251]	eta 0:24:27 lr 0.000924	time 2.0945 (2.2198)	loss 4.2521 (3.9331)	grad_norm 1.0651 (1.1308)	
[2022-01-19 05:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][600/1251]	eta 0:24:03 lr 0.000924	time 2.2256 (2.2179)	loss 4.4930 (3.9296)	grad_norm 1.2822 (1.1313)	
[2022-01-19 05:40:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][610/1251]	eta 0:23:40 lr 0.000924	time 2.4621 (2.2167)	loss 4.0247 (3.9296)	grad_norm 1.1898 (1.1320)	
[2022-01-19 05:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][620/1251]	eta 0:23:18 lr 0.000924	time 2.4931 (2.2160)	loss 4.4896 (3.9313)	grad_norm 1.1777 (1.1303)	
[2022-01-19 05:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][630/1251]	eta 0:22:55 lr 0.000924	time 2.7090 (2.2148)	loss 4.5711 (3.9321)	grad_norm 1.1396 (1.1305)	
[2022-01-19 05:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][640/1251]	eta 0:22:32 lr 0.000924	time 2.3485 (2.2138)	loss 3.0741 (3.9309)	grad_norm 1.2915 (1.1295)	
[2022-01-19 05:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][650/1251]	eta 0:22:10 lr 0.000924	time 1.5853 (2.2132)	loss 4.6929 (3.9348)	grad_norm 1.0337 (1.1283)	
[2022-01-19 05:42:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][660/1251]	eta 0:21:48 lr 0.000924	time 1.8685 (2.2141)	loss 3.1170 (3.9306)	grad_norm 1.1792 (1.1297)	
[2022-01-19 05:42:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][670/1251]	eta 0:21:26 lr 0.000924	time 2.6042 (2.2150)	loss 4.0697 (3.9330)	grad_norm 1.0996 (1.1308)	
[2022-01-19 05:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][680/1251]	eta 0:21:06 lr 0.000924	time 3.1901 (2.2177)	loss 3.6801 (3.9307)	grad_norm 1.2316 (1.1318)	
[2022-01-19 05:43:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][690/1251]	eta 0:20:44 lr 0.000924	time 1.5574 (2.2190)	loss 3.3162 (3.9305)	grad_norm 1.2495 (1.1323)	
[2022-01-19 05:44:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][700/1251]	eta 0:20:22 lr 0.000924	time 1.6536 (2.2187)	loss 3.1202 (3.9305)	grad_norm 1.0535 (1.1339)	
[2022-01-19 05:44:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][710/1251]	eta 0:19:59 lr 0.000924	time 2.3396 (2.2179)	loss 4.4486 (3.9292)	grad_norm 1.0174 (1.1335)	
[2022-01-19 05:44:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][720/1251]	eta 0:19:37 lr 0.000924	time 2.2127 (2.2166)	loss 3.0521 (3.9294)	grad_norm 1.1113 (1.1331)	
[2022-01-19 05:45:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][730/1251]	eta 0:19:12 lr 0.000924	time 1.6409 (2.2125)	loss 3.5588 (3.9258)	grad_norm 1.1224 (1.1339)	
[2022-01-19 05:45:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][740/1251]	eta 0:18:49 lr 0.000924	time 1.8665 (2.2095)	loss 3.5552 (3.9255)	grad_norm 1.0989 (1.1342)	
[2022-01-19 05:45:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][750/1251]	eta 0:18:26 lr 0.000924	time 2.4827 (2.2095)	loss 3.8258 (3.9235)	grad_norm 1.0473 (1.1337)	
[2022-01-19 05:46:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][760/1251]	eta 0:18:05 lr 0.000924	time 2.6581 (2.2098)	loss 4.2407 (3.9218)	grad_norm 1.1223 (1.1336)	
[2022-01-19 05:46:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][770/1251]	eta 0:17:42 lr 0.000924	time 2.0216 (2.2094)	loss 4.4353 (3.9245)	grad_norm 0.9992 (1.1330)	
[2022-01-19 05:46:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][780/1251]	eta 0:17:21 lr 0.000924	time 2.7414 (2.2106)	loss 3.8241 (3.9213)	grad_norm 1.1825 (1.1340)	
[2022-01-19 05:47:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][790/1251]	eta 0:16:58 lr 0.000924	time 2.6243 (2.2093)	loss 2.8143 (3.9213)	grad_norm 1.1110 (1.1332)	
[2022-01-19 05:47:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][800/1251]	eta 0:16:37 lr 0.000924	time 2.3579 (2.2113)	loss 3.3655 (3.9205)	grad_norm 1.4385 (1.1338)	
[2022-01-19 05:48:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][810/1251]	eta 0:16:16 lr 0.000924	time 1.5475 (2.2138)	loss 2.6879 (3.9169)	grad_norm 1.1164 (1.1342)	
[2022-01-19 05:48:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][820/1251]	eta 0:15:53 lr 0.000924	time 2.3839 (2.2134)	loss 4.6792 (3.9175)	grad_norm 1.2107 (1.1355)	
[2022-01-19 05:48:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][830/1251]	eta 0:15:31 lr 0.000924	time 2.1360 (2.2118)	loss 3.3879 (3.9180)	grad_norm 1.1136 (1.1354)	
[2022-01-19 05:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][840/1251]	eta 0:15:08 lr 0.000924	time 2.2553 (2.2103)	loss 3.3006 (3.9163)	grad_norm 1.0223 (1.1351)	
[2022-01-19 05:49:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][850/1251]	eta 0:14:46 lr 0.000924	time 1.6799 (2.2096)	loss 4.4079 (3.9182)	grad_norm 1.0463 (1.1352)	
[2022-01-19 05:49:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][860/1251]	eta 0:14:24 lr 0.000924	time 3.1797 (2.2104)	loss 3.5848 (3.9176)	grad_norm 1.0671 (1.1353)	
[2022-01-19 05:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][870/1251]	eta 0:14:02 lr 0.000924	time 2.3868 (2.2109)	loss 4.0749 (3.9201)	grad_norm 0.9457 (1.1352)	
[2022-01-19 05:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][880/1251]	eta 0:13:40 lr 0.000924	time 2.2642 (2.2107)	loss 4.2936 (3.9228)	grad_norm 1.1090 (1.1352)	
[2022-01-19 05:51:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][890/1251]	eta 0:13:17 lr 0.000924	time 1.6685 (2.2099)	loss 3.1129 (3.9225)	grad_norm 1.0030 (1.1350)	
[2022-01-19 05:51:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][900/1251]	eta 0:12:55 lr 0.000924	time 2.7315 (2.2099)	loss 3.9050 (3.9201)	grad_norm 1.0650 (1.1350)	
[2022-01-19 05:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][910/1251]	eta 0:12:32 lr 0.000924	time 1.5917 (2.2071)	loss 3.1171 (3.9194)	grad_norm 1.0795 (1.1340)	
[2022-01-19 05:52:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][920/1251]	eta 0:12:09 lr 0.000924	time 1.6247 (2.2049)	loss 3.5059 (3.9208)	grad_norm 1.1108 (1.1342)	
[2022-01-19 05:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][930/1251]	eta 0:11:47 lr 0.000924	time 1.9189 (2.2052)	loss 4.2502 (3.9205)	grad_norm 1.0224 (1.1345)	
[2022-01-19 05:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][940/1251]	eta 0:11:26 lr 0.000924	time 1.6006 (2.2061)	loss 3.3458 (3.9186)	grad_norm 1.1398 (1.1350)	
[2022-01-19 05:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][950/1251]	eta 0:11:04 lr 0.000924	time 2.3009 (2.2065)	loss 3.3104 (3.9154)	grad_norm 1.0180 (1.1355)	
[2022-01-19 05:53:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][960/1251]	eta 0:10:42 lr 0.000924	time 1.8719 (2.2068)	loss 3.1838 (3.9134)	grad_norm 1.0386 (1.1344)	
[2022-01-19 05:53:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][970/1251]	eta 0:10:20 lr 0.000924	time 2.2626 (2.2075)	loss 3.1400 (3.9129)	grad_norm 1.0419 (1.1344)	
[2022-01-19 05:54:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][980/1251]	eta 0:09:58 lr 0.000924	time 1.5435 (2.2067)	loss 4.2153 (3.9140)	grad_norm 0.9151 (1.1338)	
[2022-01-19 05:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][990/1251]	eta 0:09:35 lr 0.000924	time 1.9103 (2.2063)	loss 4.2909 (3.9171)	grad_norm 1.0967 (1.1338)	
[2022-01-19 05:54:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1000/1251]	eta 0:09:13 lr 0.000923	time 2.0179 (2.2048)	loss 2.9395 (3.9163)	grad_norm 1.1133 (1.1332)	
[2022-01-19 05:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1010/1251]	eta 0:08:50 lr 0.000923	time 2.2035 (2.2024)	loss 3.8890 (3.9148)	grad_norm 1.0246 (1.1329)	
[2022-01-19 05:55:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1020/1251]	eta 0:08:28 lr 0.000923	time 2.2270 (2.2016)	loss 4.2495 (3.9113)	grad_norm 1.0958 (1.1331)	
[2022-01-19 05:56:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1030/1251]	eta 0:08:06 lr 0.000923	time 1.8973 (2.2036)	loss 3.6781 (3.9102)	grad_norm 1.1082 (1.1327)	
[2022-01-19 05:56:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1040/1251]	eta 0:07:44 lr 0.000923	time 1.6049 (2.2031)	loss 4.1600 (3.9119)	grad_norm 1.5243 (1.1330)	
[2022-01-19 05:56:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1050/1251]	eta 0:07:22 lr 0.000923	time 1.9867 (2.2034)	loss 3.8068 (3.9121)	grad_norm 1.0183 (1.1327)	
[2022-01-19 05:57:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1060/1251]	eta 0:07:00 lr 0.000923	time 2.1669 (2.2033)	loss 4.2260 (3.9143)	grad_norm 1.3606 (1.1328)	
[2022-01-19 05:57:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1070/1251]	eta 0:06:38 lr 0.000923	time 1.9185 (2.2035)	loss 4.1872 (3.9141)	grad_norm 1.2670 (1.1322)	
[2022-01-19 05:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1080/1251]	eta 0:06:16 lr 0.000923	time 2.1859 (2.2030)	loss 3.8884 (3.9123)	grad_norm 1.1343 (1.1317)	
[2022-01-19 05:58:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1090/1251]	eta 0:05:54 lr 0.000923	time 1.9314 (2.2034)	loss 3.8880 (3.9133)	grad_norm 1.4073 (1.1316)	
[2022-01-19 05:58:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1100/1251]	eta 0:05:32 lr 0.000923	time 3.0040 (2.2047)	loss 3.8832 (3.9112)	grad_norm 0.9978 (1.1323)	
[2022-01-19 05:59:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1110/1251]	eta 0:05:10 lr 0.000923	time 1.5791 (2.2044)	loss 2.9996 (3.9119)	grad_norm 1.1674 (1.1332)	
[2022-01-19 05:59:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1120/1251]	eta 0:04:48 lr 0.000923	time 1.8710 (2.2031)	loss 4.1343 (3.9123)	grad_norm 1.2523 (1.1331)	
[2022-01-19 05:59:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1130/1251]	eta 0:04:26 lr 0.000923	time 1.9130 (2.2012)	loss 4.2589 (3.9115)	grad_norm 1.0167 (1.1328)	
[2022-01-19 06:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1140/1251]	eta 0:04:04 lr 0.000923	time 3.3647 (2.2010)	loss 4.1460 (3.9125)	grad_norm 1.0415 (1.1325)	
[2022-01-19 06:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1150/1251]	eta 0:03:42 lr 0.000923	time 2.2861 (2.2010)	loss 3.5060 (3.9104)	grad_norm 1.0616 (1.1317)	
[2022-01-19 06:00:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1160/1251]	eta 0:03:20 lr 0.000923	time 2.3997 (2.2016)	loss 2.6712 (3.9093)	grad_norm 1.0375 (1.1322)	
[2022-01-19 06:01:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1170/1251]	eta 0:02:58 lr 0.000923	time 1.8475 (2.2024)	loss 3.2077 (3.9103)	grad_norm 1.0797 (1.1319)	
[2022-01-19 06:01:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1180/1251]	eta 0:02:36 lr 0.000923	time 2.6029 (2.2025)	loss 4.2657 (3.9096)	grad_norm 1.1954 (1.1332)	
[2022-01-19 06:01:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1190/1251]	eta 0:02:14 lr 0.000923	time 2.1532 (2.2015)	loss 4.3803 (3.9088)	grad_norm 1.4591 (1.1337)	
[2022-01-19 06:02:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1200/1251]	eta 0:01:52 lr 0.000923	time 2.3826 (2.2007)	loss 4.2678 (3.9115)	grad_norm 1.1559 (1.1338)	
[2022-01-19 06:02:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1210/1251]	eta 0:01:30 lr 0.000923	time 1.8633 (2.1995)	loss 4.1973 (3.9102)	grad_norm 0.9364 (1.1334)	
[2022-01-19 06:02:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1220/1251]	eta 0:01:08 lr 0.000923	time 2.9590 (2.1997)	loss 3.8822 (3.9098)	grad_norm 1.2198 (1.1332)	
[2022-01-19 06:03:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1230/1251]	eta 0:00:46 lr 0.000923	time 2.2379 (2.2003)	loss 4.2828 (3.9063)	grad_norm 0.9873 (1.1330)	
[2022-01-19 06:03:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1240/1251]	eta 0:00:24 lr 0.000923	time 1.7540 (2.1996)	loss 4.5811 (3.9072)	grad_norm 1.1626 (1.1331)	
[2022-01-19 06:03:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [53/300][1250/1251]	eta 0:00:02 lr 0.000923	time 1.1794 (2.1945)	loss 3.6340 (3.9043)	grad_norm 1.1324 (1.1336)	
[2022-01-19 06:03:58 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 53 training takes 0:45:45
[2022-01-19 06:04:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.088 (18.088)	Loss 1.2155 (1.2155)	Acc@1 71.191 (71.191)	Acc@5 89.844 (89.844)	
[2022-01-19 06:04:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.307 (3.458)	Loss 1.2447 (1.2689)	Acc@1 70.898 (70.526)	Acc@5 90.430 (90.199)	
[2022-01-19 06:04:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.904 (2.679)	Loss 1.2549 (1.2661)	Acc@1 70.605 (70.596)	Acc@5 90.137 (90.197)	
[2022-01-19 06:05:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.210 (2.383)	Loss 1.2845 (1.2674)	Acc@1 69.531 (70.435)	Acc@5 90.723 (90.234)	
[2022-01-19 06:05:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.876 (2.260)	Loss 1.2648 (1.2615)	Acc@1 68.555 (70.541)	Acc@5 90.820 (90.261)	
[2022-01-19 06:05:38 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 70.584 Acc@5 90.224
[2022-01-19 06:05:38 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 70.6%
[2022-01-19 06:05:38 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 70.58%
[2022-01-19 06:06:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][0/1251]	eta 7:26:24 lr 0.000923	time 21.4103 (21.4103)	loss 2.7573 (2.7573)	grad_norm 1.2328 (1.2328)	
[2022-01-19 06:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][10/1251]	eta 1:25:23 lr 0.000923	time 2.1543 (4.1285)	loss 3.3754 (3.9807)	grad_norm 1.3200 (1.1591)	
[2022-01-19 06:06:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][20/1251]	eta 1:05:49 lr 0.000923	time 1.9192 (3.2086)	loss 3.9807 (4.0343)	grad_norm 0.9081 (1.1032)	
[2022-01-19 06:07:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][30/1251]	eta 0:59:03 lr 0.000923	time 1.8891 (2.9022)	loss 4.8062 (4.0049)	grad_norm 1.1501 (1.0905)	
[2022-01-19 06:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][40/1251]	eta 0:56:14 lr 0.000923	time 3.7900 (2.7868)	loss 3.5861 (3.9811)	grad_norm 1.2538 (1.1108)	
[2022-01-19 06:07:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][50/1251]	eta 0:53:44 lr 0.000923	time 1.6329 (2.6849)	loss 4.7626 (3.9626)	grad_norm 1.2422 (1.1261)	
[2022-01-19 06:08:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][60/1251]	eta 0:51:23 lr 0.000923	time 1.6757 (2.5889)	loss 4.3219 (3.9774)	grad_norm 1.0190 (1.1201)	
[2022-01-19 06:08:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][70/1251]	eta 0:49:35 lr 0.000923	time 1.9416 (2.5196)	loss 4.1758 (3.9789)	grad_norm 0.9167 (1.1089)	
[2022-01-19 06:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][80/1251]	eta 0:48:48 lr 0.000923	time 3.7277 (2.5008)	loss 3.8973 (3.9429)	grad_norm 1.4800 (1.1180)	
[2022-01-19 06:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][90/1251]	eta 0:48:02 lr 0.000923	time 2.5300 (2.4824)	loss 4.1987 (3.9545)	grad_norm 1.1386 (1.1216)	
[2022-01-19 06:09:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][100/1251]	eta 0:46:52 lr 0.000923	time 1.9264 (2.4439)	loss 4.0455 (3.9392)	grad_norm 1.1319 (1.1193)	
[2022-01-19 06:10:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][110/1251]	eta 0:45:46 lr 0.000923	time 1.8183 (2.4068)	loss 4.1812 (3.9475)	grad_norm 1.0273 (1.1171)	
[2022-01-19 06:10:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][120/1251]	eta 0:44:52 lr 0.000923	time 2.4472 (2.3805)	loss 3.9350 (3.9605)	grad_norm 1.2123 (1.1136)	
[2022-01-19 06:10:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][130/1251]	eta 0:44:03 lr 0.000923	time 1.8900 (2.3580)	loss 3.4167 (3.9578)	grad_norm 1.1643 (1.1174)	
[2022-01-19 06:11:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][140/1251]	eta 0:43:35 lr 0.000923	time 2.1383 (2.3545)	loss 4.8051 (3.9566)	grad_norm 1.3581 (1.1196)	
[2022-01-19 06:11:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][150/1251]	eta 0:42:55 lr 0.000923	time 1.9155 (2.3393)	loss 4.4631 (3.9685)	grad_norm 1.0179 (1.1201)	
[2022-01-19 06:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][160/1251]	eta 0:42:21 lr 0.000923	time 2.8435 (2.3291)	loss 4.4467 (3.9680)	grad_norm 1.0953 (1.1229)	
[2022-01-19 06:12:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][170/1251]	eta 0:41:35 lr 0.000923	time 1.9817 (2.3089)	loss 3.1114 (3.9440)	grad_norm 1.0309 (1.1236)	
[2022-01-19 06:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][180/1251]	eta 0:40:58 lr 0.000923	time 2.0557 (2.2956)	loss 4.6603 (3.9532)	grad_norm 0.9872 (1.1230)	
[2022-01-19 06:12:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][190/1251]	eta 0:40:25 lr 0.000923	time 2.0588 (2.2862)	loss 4.7022 (3.9409)	grad_norm 1.0846 (1.1238)	
[2022-01-19 06:13:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][200/1251]	eta 0:39:56 lr 0.000922	time 2.3663 (2.2807)	loss 4.0862 (3.9465)	grad_norm 1.0460 (1.1245)	
[2022-01-19 06:13:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][210/1251]	eta 0:39:21 lr 0.000922	time 2.2268 (2.2686)	loss 4.2489 (3.9438)	grad_norm 1.0056 (1.1235)	
[2022-01-19 06:14:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][220/1251]	eta 0:39:00 lr 0.000922	time 3.1301 (2.2705)	loss 4.5742 (3.9325)	grad_norm 1.4198 (1.1234)	
[2022-01-19 06:14:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][230/1251]	eta 0:38:39 lr 0.000922	time 2.6481 (2.2720)	loss 3.2384 (3.9251)	grad_norm 1.1669 (1.1309)	
[2022-01-19 06:14:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][240/1251]	eta 0:38:14 lr 0.000922	time 2.3063 (2.2694)	loss 3.1177 (3.9261)	grad_norm 1.3548 (1.1316)	
[2022-01-19 06:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][250/1251]	eta 0:37:40 lr 0.000922	time 1.8652 (2.2578)	loss 4.4694 (3.9415)	grad_norm 0.9798 (1.1314)	
[2022-01-19 06:15:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][260/1251]	eta 0:37:11 lr 0.000922	time 2.3234 (2.2521)	loss 4.6581 (3.9442)	grad_norm 1.3351 (1.1317)	
[2022-01-19 06:15:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][270/1251]	eta 0:36:53 lr 0.000922	time 3.3806 (2.2568)	loss 4.1196 (3.9409)	grad_norm 1.0786 (1.1328)	
[2022-01-19 06:16:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][280/1251]	eta 0:36:31 lr 0.000922	time 2.1849 (2.2565)	loss 4.6345 (3.9385)	grad_norm 1.0354 (1.1337)	
[2022-01-19 06:16:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][290/1251]	eta 0:36:07 lr 0.000922	time 1.8397 (2.2556)	loss 3.3225 (3.9335)	grad_norm 1.1343 (1.1358)	
[2022-01-19 06:16:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][300/1251]	eta 0:35:47 lr 0.000922	time 3.4798 (2.2581)	loss 3.4583 (3.9198)	grad_norm 1.1104 (1.1350)	
[2022-01-19 06:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][310/1251]	eta 0:35:20 lr 0.000922	time 2.6143 (2.2537)	loss 2.8770 (3.9122)	grad_norm 1.1068 (1.1323)	
[2022-01-19 06:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][320/1251]	eta 0:34:50 lr 0.000922	time 2.2674 (2.2460)	loss 3.9123 (3.9112)	grad_norm 1.1013 (1.1307)	
[2022-01-19 06:18:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][330/1251]	eta 0:34:23 lr 0.000922	time 1.5727 (2.2401)	loss 3.4555 (3.9157)	grad_norm 1.0154 (1.1295)	
[2022-01-19 06:18:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][340/1251]	eta 0:33:59 lr 0.000922	time 2.4627 (2.2390)	loss 2.7429 (3.9175)	grad_norm 1.1236 (1.1285)	
[2022-01-19 06:18:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][350/1251]	eta 0:33:34 lr 0.000922	time 2.5040 (2.2358)	loss 3.8073 (3.9202)	grad_norm 0.9853 (1.1261)	
[2022-01-19 06:19:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][360/1251]	eta 0:33:11 lr 0.000922	time 2.2896 (2.2347)	loss 3.9728 (3.9171)	grad_norm 1.3012 (1.1272)	
[2022-01-19 06:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][370/1251]	eta 0:32:51 lr 0.000922	time 2.4007 (2.2376)	loss 4.6175 (3.9185)	grad_norm 1.1603 (1.1289)	
[2022-01-19 06:19:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][380/1251]	eta 0:32:31 lr 0.000922	time 2.8011 (2.2404)	loss 4.5615 (3.9103)	grad_norm 1.0769 (1.1333)	
[2022-01-19 06:20:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][390/1251]	eta 0:32:08 lr 0.000922	time 3.0107 (2.2400)	loss 3.9315 (3.9109)	grad_norm 1.0706 (1.1343)	
[2022-01-19 06:20:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][400/1251]	eta 0:31:46 lr 0.000922	time 2.6184 (2.2397)	loss 4.3516 (3.9125)	grad_norm 1.1107 (1.1377)	
[2022-01-19 06:20:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][410/1251]	eta 0:31:17 lr 0.000922	time 1.9588 (2.2329)	loss 3.7291 (3.9119)	grad_norm 1.3434 (1.1380)	
[2022-01-19 06:21:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][420/1251]	eta 0:30:53 lr 0.000922	time 2.8155 (2.2308)	loss 2.4113 (3.9071)	grad_norm 0.9512 (1.1380)	
[2022-01-19 06:21:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][430/1251]	eta 0:30:30 lr 0.000922	time 2.4967 (2.2300)	loss 4.4518 (3.9124)	grad_norm 1.2042 (1.1369)	
[2022-01-19 06:22:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][440/1251]	eta 0:30:06 lr 0.000922	time 2.3635 (2.2281)	loss 3.8628 (3.9051)	grad_norm 1.0114 (1.1381)	
[2022-01-19 06:22:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][450/1251]	eta 0:29:42 lr 0.000922	time 2.1342 (2.2260)	loss 4.0431 (3.9082)	grad_norm 1.0910 (1.1424)	
[2022-01-19 06:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][460/1251]	eta 0:29:19 lr 0.000922	time 2.8920 (2.2243)	loss 4.0887 (3.9075)	grad_norm 1.2608 (1.1429)	
[2022-01-19 06:23:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][470/1251]	eta 0:28:55 lr 0.000922	time 2.2060 (2.2218)	loss 4.1575 (3.9047)	grad_norm 0.9018 (1.1411)	
[2022-01-19 06:23:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][480/1251]	eta 0:28:32 lr 0.000922	time 2.5977 (2.2211)	loss 4.6694 (3.9098)	grad_norm 0.9641 (1.1392)	
[2022-01-19 06:23:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][490/1251]	eta 0:28:09 lr 0.000922	time 1.9650 (2.2206)	loss 3.5136 (3.9071)	grad_norm 1.1965 (1.1397)	
[2022-01-19 06:24:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][500/1251]	eta 0:27:50 lr 0.000922	time 2.4459 (2.2243)	loss 2.8670 (3.9009)	grad_norm 1.1914 (1.1401)	
[2022-01-19 06:24:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][510/1251]	eta 0:27:26 lr 0.000922	time 2.1441 (2.2224)	loss 4.0459 (3.9031)	grad_norm 1.0540 (1.1409)	
[2022-01-19 06:24:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][520/1251]	eta 0:27:03 lr 0.000922	time 1.8968 (2.2210)	loss 3.4391 (3.9038)	grad_norm 0.9975 (1.1405)	
[2022-01-19 06:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][530/1251]	eta 0:26:38 lr 0.000922	time 1.9260 (2.2171)	loss 4.2325 (3.9005)	grad_norm 1.0187 (1.1391)	
[2022-01-19 06:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][540/1251]	eta 0:26:15 lr 0.000922	time 2.4692 (2.2163)	loss 3.3415 (3.9019)	grad_norm 1.2321 (1.1413)	
[2022-01-19 06:25:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][550/1251]	eta 0:25:52 lr 0.000922	time 2.2037 (2.2153)	loss 4.4959 (3.9094)	grad_norm 1.0994 (1.1400)	
[2022-01-19 06:26:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][560/1251]	eta 0:25:31 lr 0.000922	time 2.2631 (2.2161)	loss 4.3000 (3.9109)	grad_norm 0.9919 (1.1398)	
[2022-01-19 06:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][570/1251]	eta 0:25:09 lr 0.000922	time 1.5050 (2.2163)	loss 3.9317 (3.9059)	grad_norm 1.2515 (1.1400)	
[2022-01-19 06:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][580/1251]	eta 0:24:49 lr 0.000922	time 2.4723 (2.2199)	loss 3.9066 (3.9122)	grad_norm 0.9812 (1.1400)	
[2022-01-19 06:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][590/1251]	eta 0:24:28 lr 0.000922	time 2.1946 (2.2211)	loss 4.2595 (3.9127)	grad_norm 1.6982 (1.1418)	
[2022-01-19 06:27:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][600/1251]	eta 0:24:04 lr 0.000922	time 1.9134 (2.2182)	loss 3.8866 (3.9128)	grad_norm 1.1040 (1.1423)	
[2022-01-19 06:28:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][610/1251]	eta 0:23:40 lr 0.000922	time 1.6345 (2.2160)	loss 4.1204 (3.9093)	grad_norm 1.1321 (1.1430)	
[2022-01-19 06:28:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][620/1251]	eta 0:23:16 lr 0.000922	time 2.3753 (2.2139)	loss 4.3008 (3.9144)	grad_norm 1.0726 (1.1424)	
[2022-01-19 06:28:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][630/1251]	eta 0:22:52 lr 0.000922	time 1.8542 (2.2107)	loss 4.1092 (3.9192)	grad_norm 1.0301 (1.1424)	
[2022-01-19 06:29:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][640/1251]	eta 0:22:30 lr 0.000922	time 2.0593 (2.2101)	loss 4.5584 (3.9210)	grad_norm 1.1784 (1.1421)	
[2022-01-19 06:29:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][650/1251]	eta 0:22:07 lr 0.000921	time 1.9445 (2.2088)	loss 3.0712 (3.9232)	grad_norm 1.0125 (1.1420)	
[2022-01-19 06:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][660/1251]	eta 0:21:44 lr 0.000921	time 2.4573 (2.2070)	loss 2.7243 (3.9253)	grad_norm 1.0772 (1.1410)	
[2022-01-19 06:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][670/1251]	eta 0:21:21 lr 0.000921	time 1.8536 (2.2049)	loss 3.4614 (3.9271)	grad_norm 1.3371 (1.1416)	
[2022-01-19 06:30:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][680/1251]	eta 0:20:59 lr 0.000921	time 2.1441 (2.2060)	loss 4.1398 (3.9299)	grad_norm 1.1015 (1.1422)	
[2022-01-19 06:31:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][690/1251]	eta 0:20:37 lr 0.000921	time 2.2358 (2.2063)	loss 4.3311 (3.9301)	grad_norm 1.1705 (1.1420)	
[2022-01-19 06:31:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][700/1251]	eta 0:20:17 lr 0.000921	time 2.7761 (2.2088)	loss 4.0537 (3.9312)	grad_norm 1.0514 (1.1415)	
[2022-01-19 06:31:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][710/1251]	eta 0:19:56 lr 0.000921	time 1.4750 (2.2108)	loss 3.3234 (3.9327)	grad_norm 1.3184 (1.1423)	
[2022-01-19 06:32:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][720/1251]	eta 0:19:33 lr 0.000921	time 1.4550 (2.2107)	loss 3.9478 (3.9366)	grad_norm 1.0275 (1.1410)	
[2022-01-19 06:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][730/1251]	eta 0:19:12 lr 0.000921	time 3.0813 (2.2115)	loss 3.5399 (3.9331)	grad_norm 1.3288 (1.1406)	
[2022-01-19 06:32:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][740/1251]	eta 0:18:49 lr 0.000921	time 2.8728 (2.2113)	loss 3.2214 (3.9317)	grad_norm 1.0514 (1.1412)	
[2022-01-19 06:33:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][750/1251]	eta 0:18:26 lr 0.000921	time 1.8697 (2.2094)	loss 3.1688 (3.9343)	grad_norm 1.2226 (1.1423)	
[2022-01-19 06:33:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][760/1251]	eta 0:18:03 lr 0.000921	time 1.6912 (2.2071)	loss 4.3204 (3.9353)	grad_norm 1.3449 (1.1429)	
[2022-01-19 06:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][770/1251]	eta 0:17:41 lr 0.000921	time 2.1188 (2.2060)	loss 4.2423 (3.9365)	grad_norm 1.1474 (1.1436)	
[2022-01-19 06:34:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][780/1251]	eta 0:17:18 lr 0.000921	time 2.7367 (2.2050)	loss 3.2165 (3.9367)	grad_norm 1.0395 (1.1438)	
[2022-01-19 06:34:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][790/1251]	eta 0:16:56 lr 0.000921	time 1.6464 (2.2056)	loss 4.2998 (3.9395)	grad_norm 0.9587 (1.1434)	
[2022-01-19 06:35:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][800/1251]	eta 0:16:34 lr 0.000921	time 2.1598 (2.2054)	loss 4.1816 (3.9409)	grad_norm 0.9778 (1.1433)	
[2022-01-19 06:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][810/1251]	eta 0:16:11 lr 0.000921	time 2.4038 (2.2039)	loss 4.3749 (3.9430)	grad_norm 1.0653 (1.1429)	
[2022-01-19 06:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][820/1251]	eta 0:15:49 lr 0.000921	time 2.1352 (2.2036)	loss 4.2727 (3.9472)	grad_norm 1.2400 (1.1449)	
[2022-01-19 06:36:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][830/1251]	eta 0:15:27 lr 0.000921	time 2.4963 (2.2038)	loss 3.8696 (3.9475)	grad_norm 1.0230 (1.1453)	
[2022-01-19 06:36:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][840/1251]	eta 0:15:06 lr 0.000921	time 1.8131 (2.2046)	loss 3.8522 (3.9455)	grad_norm 1.0535 (1.1445)	
[2022-01-19 06:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][850/1251]	eta 0:14:44 lr 0.000921	time 2.1426 (2.2063)	loss 2.9779 (3.9475)	grad_norm 0.9738 (1.1444)	
[2022-01-19 06:37:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][860/1251]	eta 0:14:22 lr 0.000921	time 1.9152 (2.2065)	loss 4.6131 (3.9480)	grad_norm 1.1716 (1.1445)	
[2022-01-19 06:37:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][870/1251]	eta 0:13:59 lr 0.000921	time 1.7578 (2.2043)	loss 3.9806 (3.9458)	grad_norm 1.1345 (1.1450)	
[2022-01-19 06:37:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][880/1251]	eta 0:13:37 lr 0.000921	time 2.2682 (2.2030)	loss 4.5664 (3.9499)	grad_norm 1.2430 (1.1454)	
[2022-01-19 06:38:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][890/1251]	eta 0:13:15 lr 0.000921	time 2.2688 (2.2025)	loss 4.3071 (3.9534)	grad_norm 1.1930 (1.1456)	
[2022-01-19 06:38:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][900/1251]	eta 0:12:52 lr 0.000921	time 1.6324 (2.2012)	loss 4.3587 (3.9501)	grad_norm 1.0787 (1.1449)	
[2022-01-19 06:39:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][910/1251]	eta 0:12:30 lr 0.000921	time 2.8399 (2.2016)	loss 2.5691 (3.9520)	grad_norm 1.2348 (1.1447)	
[2022-01-19 06:39:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][920/1251]	eta 0:12:09 lr 0.000921	time 2.2074 (2.2041)	loss 4.1830 (3.9509)	grad_norm 1.1876 (1.1442)	
[2022-01-19 06:39:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][930/1251]	eta 0:11:47 lr 0.000921	time 2.0985 (2.2036)	loss 3.3483 (3.9492)	grad_norm 1.1487 (1.1442)	
[2022-01-19 06:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][940/1251]	eta 0:11:25 lr 0.000921	time 2.0258 (2.2056)	loss 4.2352 (3.9498)	grad_norm 1.0680 (1.1439)	
[2022-01-19 06:40:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][950/1251]	eta 0:11:04 lr 0.000921	time 2.2297 (2.2063)	loss 4.1832 (3.9468)	grad_norm 0.9952 (1.1438)	
[2022-01-19 06:40:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][960/1251]	eta 0:10:41 lr 0.000921	time 2.1354 (2.2047)	loss 3.1434 (3.9452)	grad_norm 1.0256 (1.1439)	
[2022-01-19 06:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][970/1251]	eta 0:10:18 lr 0.000921	time 1.8278 (2.2011)	loss 4.4489 (3.9449)	grad_norm 1.1998 (1.1441)	
[2022-01-19 06:41:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][980/1251]	eta 0:09:55 lr 0.000921	time 1.9201 (2.1986)	loss 4.2566 (3.9461)	grad_norm 1.0636 (1.1435)	
[2022-01-19 06:41:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][990/1251]	eta 0:09:33 lr 0.000921	time 1.8396 (2.1966)	loss 4.7645 (3.9485)	grad_norm 1.2143 (1.1437)	
[2022-01-19 06:42:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1000/1251]	eta 0:09:11 lr 0.000921	time 4.7510 (2.1971)	loss 4.0389 (3.9487)	grad_norm 1.0878 (1.1429)	
[2022-01-19 06:42:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1010/1251]	eta 0:08:50 lr 0.000921	time 2.8938 (2.1992)	loss 4.5449 (3.9513)	grad_norm 1.0561 (1.1424)	
[2022-01-19 06:43:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1020/1251]	eta 0:08:27 lr 0.000921	time 2.8399 (2.1986)	loss 3.6087 (3.9516)	grad_norm 1.1091 (1.1423)	
[2022-01-19 06:43:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1030/1251]	eta 0:08:06 lr 0.000921	time 2.2452 (2.1992)	loss 3.9486 (3.9496)	grad_norm 1.3737 (1.1421)	
[2022-01-19 06:43:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1040/1251]	eta 0:07:44 lr 0.000921	time 2.5093 (2.1997)	loss 3.3996 (3.9503)	grad_norm 1.4017 (1.1425)	
[2022-01-19 06:44:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1050/1251]	eta 0:07:22 lr 0.000921	time 2.7284 (2.2013)	loss 4.2968 (3.9482)	grad_norm 1.1663 (1.1427)	
[2022-01-19 06:44:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1060/1251]	eta 0:07:00 lr 0.000921	time 2.5052 (2.2010)	loss 3.8589 (3.9469)	grad_norm 0.9814 (1.1416)	
[2022-01-19 06:44:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1070/1251]	eta 0:06:38 lr 0.000921	time 1.8435 (2.1998)	loss 4.4372 (3.9491)	grad_norm 1.1348 (1.1409)	
[2022-01-19 06:45:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1080/1251]	eta 0:06:15 lr 0.000921	time 2.4042 (2.1982)	loss 4.0668 (3.9487)	grad_norm 1.1276 (1.1407)	
[2022-01-19 06:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1090/1251]	eta 0:05:53 lr 0.000921	time 2.1747 (2.1977)	loss 4.7124 (3.9499)	grad_norm 1.1124 (1.1408)	
[2022-01-19 06:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1100/1251]	eta 0:05:32 lr 0.000920	time 2.4414 (2.1993)	loss 4.6987 (3.9501)	grad_norm 1.0053 (1.1400)	
[2022-01-19 06:46:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1110/1251]	eta 0:05:10 lr 0.000920	time 1.8035 (2.1994)	loss 3.5808 (3.9502)	grad_norm 1.1636 (1.1397)	
[2022-01-19 06:46:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1120/1251]	eta 0:04:48 lr 0.000920	time 2.2784 (2.2008)	loss 3.2746 (3.9501)	grad_norm 0.9763 (1.1392)	
[2022-01-19 06:47:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1130/1251]	eta 0:04:26 lr 0.000920	time 2.1844 (2.2011)	loss 3.2898 (3.9473)	grad_norm 0.9912 (1.1392)	
[2022-01-19 06:47:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1140/1251]	eta 0:04:04 lr 0.000920	time 1.7951 (2.1991)	loss 4.1811 (3.9469)	grad_norm 1.2988 (1.1394)	
[2022-01-19 06:47:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1150/1251]	eta 0:03:41 lr 0.000920	time 1.9435 (2.1976)	loss 4.3342 (3.9449)	grad_norm 1.3915 (1.1393)	
[2022-01-19 06:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1160/1251]	eta 0:03:19 lr 0.000920	time 2.1519 (2.1964)	loss 4.2053 (3.9459)	grad_norm 1.0782 (1.1395)	
[2022-01-19 06:48:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1170/1251]	eta 0:02:57 lr 0.000920	time 1.9029 (2.1957)	loss 4.5327 (3.9486)	grad_norm 1.1310 (1.1391)	
[2022-01-19 06:48:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1180/1251]	eta 0:02:35 lr 0.000920	time 1.8421 (2.1951)	loss 3.0314 (3.9469)	grad_norm 1.0622 (1.1386)	
[2022-01-19 06:49:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1190/1251]	eta 0:02:13 lr 0.000920	time 2.8089 (2.1953)	loss 3.9032 (3.9475)	grad_norm 0.9024 (1.1388)	
[2022-01-19 06:49:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1200/1251]	eta 0:01:51 lr 0.000920	time 2.3736 (2.1956)	loss 4.3650 (3.9477)	grad_norm 1.0421 (1.1381)	
[2022-01-19 06:49:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1210/1251]	eta 0:01:30 lr 0.000920	time 2.7935 (2.1963)	loss 3.7454 (3.9446)	grad_norm 1.0718 (1.1380)	
[2022-01-19 06:50:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1220/1251]	eta 0:01:08 lr 0.000920	time 1.5049 (2.1960)	loss 4.2147 (3.9426)	grad_norm 1.0169 (1.1374)	
[2022-01-19 06:50:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1230/1251]	eta 0:00:46 lr 0.000920	time 3.0654 (2.1976)	loss 3.5492 (3.9410)	grad_norm 1.2050 (1.1377)	
[2022-01-19 06:51:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1240/1251]	eta 0:00:24 lr 0.000920	time 1.6943 (2.1969)	loss 4.3122 (3.9399)	grad_norm 1.0879 (1.1371)	
[2022-01-19 06:51:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [54/300][1250/1251]	eta 0:00:02 lr 0.000920	time 1.2057 (2.1914)	loss 3.5027 (3.9395)	grad_norm 1.1783 (1.1371)	
[2022-01-19 06:51:20 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 54 training takes 0:45:41
[2022-01-19 06:51:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.692 (16.692)	Loss 1.2295 (1.2295)	Acc@1 71.777 (71.777)	Acc@5 91.406 (91.406)	
[2022-01-19 06:51:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.925 (3.276)	Loss 1.3025 (1.2977)	Acc@1 70.117 (70.481)	Acc@5 90.137 (89.968)	
[2022-01-19 06:52:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.904 (2.434)	Loss 1.2462 (1.2910)	Acc@1 72.363 (70.838)	Acc@5 91.113 (90.132)	
[2022-01-19 06:52:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.934 (2.213)	Loss 1.2990 (1.2861)	Acc@1 70.996 (70.889)	Acc@5 91.602 (90.222)	
[2022-01-19 06:52:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.114 (2.141)	Loss 1.3235 (1.2893)	Acc@1 70.410 (70.660)	Acc@5 90.527 (90.277)	
[2022-01-19 06:52:55 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 70.790 Acc@5 90.278
[2022-01-19 06:52:55 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 70.8%
[2022-01-19 06:52:55 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 70.79%
[2022-01-19 06:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][0/1251]	eta 7:28:19 lr 0.000920	time 21.5025 (21.5025)	loss 3.7080 (3.7080)	grad_norm 1.1702 (1.1702)	
[2022-01-19 06:53:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][10/1251]	eta 1:24:58 lr 0.000920	time 2.5684 (4.1087)	loss 4.1766 (3.9279)	grad_norm 1.2354 (1.1395)	
[2022-01-19 06:54:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][20/1251]	eta 1:05:28 lr 0.000920	time 1.8408 (3.1913)	loss 4.4378 (3.9900)	grad_norm 1.1710 (1.1465)	
[2022-01-19 06:54:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][30/1251]	eta 0:59:03 lr 0.000920	time 2.4436 (2.9017)	loss 4.3832 (4.0563)	grad_norm 1.2684 (1.1472)	
[2022-01-19 06:54:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][40/1251]	eta 0:56:20 lr 0.000920	time 3.3445 (2.7916)	loss 4.2905 (3.9885)	grad_norm 1.1094 (1.1479)	
[2022-01-19 06:55:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][50/1251]	eta 0:54:01 lr 0.000920	time 2.4232 (2.6988)	loss 4.1139 (3.9427)	grad_norm 0.9901 (1.1361)	
[2022-01-19 06:55:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][60/1251]	eta 0:51:19 lr 0.000920	time 1.6771 (2.5855)	loss 3.8091 (3.8939)	grad_norm 1.0021 (1.1311)	
[2022-01-19 06:55:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][70/1251]	eta 0:49:23 lr 0.000920	time 1.8665 (2.5096)	loss 4.1279 (3.8699)	grad_norm 1.3930 (1.1384)	
[2022-01-19 06:56:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][80/1251]	eta 0:48:24 lr 0.000920	time 3.1264 (2.4806)	loss 4.8003 (3.8841)	grad_norm 1.3235 (1.1398)	
[2022-01-19 06:56:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][90/1251]	eta 0:47:21 lr 0.000920	time 2.8306 (2.4471)	loss 4.6516 (3.8990)	grad_norm 1.2359 (1.1437)	
[2022-01-19 06:57:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][100/1251]	eta 0:46:48 lr 0.000920	time 1.9053 (2.4401)	loss 4.2418 (3.8841)	grad_norm 1.1419 (1.1395)	
[2022-01-19 06:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][110/1251]	eta 0:46:08 lr 0.000920	time 2.1394 (2.4268)	loss 4.6189 (3.8916)	grad_norm 1.1623 (1.1384)	
[2022-01-19 06:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][120/1251]	eta 0:45:35 lr 0.000920	time 3.2442 (2.4184)	loss 3.3813 (3.9092)	grad_norm 1.2146 (1.1463)	
[2022-01-19 06:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][130/1251]	eta 0:44:39 lr 0.000920	time 1.9314 (2.3902)	loss 3.8608 (3.9135)	grad_norm 1.4694 (1.1435)	
[2022-01-19 06:58:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][140/1251]	eta 0:43:45 lr 0.000920	time 1.8555 (2.3636)	loss 4.3044 (3.9295)	grad_norm 0.9243 (1.1351)	
[2022-01-19 06:58:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][150/1251]	eta 0:43:06 lr 0.000920	time 2.1767 (2.3488)	loss 3.9582 (3.9220)	grad_norm 1.0784 (1.1351)	
[2022-01-19 06:59:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][160/1251]	eta 0:42:12 lr 0.000920	time 1.7404 (2.3209)	loss 4.0899 (3.9330)	grad_norm 1.0935 (1.1310)	
[2022-01-19 06:59:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][170/1251]	eta 0:41:32 lr 0.000920	time 1.8057 (2.3055)	loss 3.8688 (3.9303)	grad_norm 1.0704 (1.1297)	
[2022-01-19 06:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][180/1251]	eta 0:40:55 lr 0.000920	time 2.4697 (2.2926)	loss 3.4508 (3.9319)	grad_norm 1.3668 (1.1284)	
[2022-01-19 07:00:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][190/1251]	eta 0:40:26 lr 0.000920	time 1.6215 (2.2870)	loss 3.3576 (3.9307)	grad_norm 1.0975 (1.1295)	
[2022-01-19 07:00:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][200/1251]	eta 0:40:00 lr 0.000920	time 2.5230 (2.2843)	loss 4.2179 (3.9316)	grad_norm 1.4703 (1.1293)	
[2022-01-19 07:00:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][210/1251]	eta 0:39:37 lr 0.000920	time 1.7484 (2.2835)	loss 3.3861 (3.9291)	grad_norm 1.0955 (1.1312)	
[2022-01-19 07:01:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][220/1251]	eta 0:39:19 lr 0.000920	time 3.3488 (2.2890)	loss 3.4665 (3.9320)	grad_norm 1.2417 (1.1321)	
[2022-01-19 07:01:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][230/1251]	eta 0:38:52 lr 0.000920	time 1.8313 (2.2844)	loss 3.9018 (3.9281)	grad_norm 1.4700 (1.1341)	
[2022-01-19 07:02:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][240/1251]	eta 0:38:25 lr 0.000920	time 2.8547 (2.2804)	loss 4.3535 (3.9177)	grad_norm 1.3464 (1.1349)	
[2022-01-19 07:02:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][250/1251]	eta 0:37:52 lr 0.000920	time 1.9621 (2.2703)	loss 4.8155 (3.9332)	grad_norm 1.0924 (1.1332)	
[2022-01-19 07:02:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][260/1251]	eta 0:37:31 lr 0.000920	time 3.5436 (2.2722)	loss 3.1837 (3.9404)	grad_norm 1.2911 (1.1350)	
[2022-01-19 07:03:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][270/1251]	eta 0:37:04 lr 0.000920	time 1.5687 (2.2675)	loss 3.6625 (3.9279)	grad_norm 0.9362 (1.1343)	
[2022-01-19 07:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][280/1251]	eta 0:36:40 lr 0.000920	time 2.8732 (2.2664)	loss 4.6418 (3.9155)	grad_norm 1.0525 (1.1349)	
[2022-01-19 07:03:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][290/1251]	eta 0:36:16 lr 0.000919	time 1.8497 (2.2649)	loss 3.2666 (3.9040)	grad_norm 1.0014 (1.1346)	
[2022-01-19 07:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][300/1251]	eta 0:35:53 lr 0.000919	time 2.9800 (2.2645)	loss 3.5889 (3.9009)	grad_norm 1.4701 (1.1373)	
[2022-01-19 07:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][310/1251]	eta 0:35:24 lr 0.000919	time 1.9521 (2.2579)	loss 3.8231 (3.9048)	grad_norm 1.2206 (1.1371)	
[2022-01-19 07:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][320/1251]	eta 0:34:59 lr 0.000919	time 2.2571 (2.2548)	loss 4.4284 (3.8994)	grad_norm 1.0294 (1.1344)	
[2022-01-19 07:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][330/1251]	eta 0:34:31 lr 0.000919	time 2.1530 (2.2491)	loss 3.7201 (3.9003)	grad_norm 0.9440 (1.1329)	
[2022-01-19 07:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][340/1251]	eta 0:34:01 lr 0.000919	time 2.1814 (2.2411)	loss 3.6779 (3.8930)	grad_norm 1.0803 (1.1314)	
[2022-01-19 07:06:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][350/1251]	eta 0:33:34 lr 0.000919	time 1.9363 (2.2363)	loss 3.7542 (3.8954)	grad_norm 1.0377 (1.1295)	
[2022-01-19 07:06:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][360/1251]	eta 0:33:09 lr 0.000919	time 2.0335 (2.2332)	loss 4.1874 (3.8947)	grad_norm 1.1908 (1.1320)	
[2022-01-19 07:06:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][370/1251]	eta 0:32:49 lr 0.000919	time 3.1063 (2.2358)	loss 4.1046 (3.8986)	grad_norm 1.0575 (1.1327)	
[2022-01-19 07:07:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][380/1251]	eta 0:32:29 lr 0.000919	time 2.2690 (2.2377)	loss 3.0938 (3.8993)	grad_norm 1.1781 (1.1343)	
[2022-01-19 07:07:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][390/1251]	eta 0:32:08 lr 0.000919	time 1.5671 (2.2395)	loss 3.0617 (3.8948)	grad_norm 1.9976 (1.1402)	
[2022-01-19 07:07:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][400/1251]	eta 0:31:50 lr 0.000919	time 2.9093 (2.2445)	loss 2.7006 (3.8930)	grad_norm 1.1224 (1.1418)	
[2022-01-19 07:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][410/1251]	eta 0:31:26 lr 0.000919	time 2.1897 (2.2432)	loss 4.0581 (3.8964)	grad_norm 1.1231 (1.1412)	
[2022-01-19 07:08:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][420/1251]	eta 0:30:58 lr 0.000919	time 1.8896 (2.2366)	loss 4.1802 (3.8997)	grad_norm 1.0024 (1.1418)	
[2022-01-19 07:08:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][430/1251]	eta 0:30:30 lr 0.000919	time 2.2085 (2.2301)	loss 3.9365 (3.8986)	grad_norm 1.2962 (1.1408)	
[2022-01-19 07:09:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][440/1251]	eta 0:30:06 lr 0.000919	time 1.9498 (2.2274)	loss 4.3457 (3.8942)	grad_norm 1.0575 (1.1415)	
[2022-01-19 07:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][450/1251]	eta 0:29:42 lr 0.000919	time 2.5715 (2.2249)	loss 4.8010 (3.8924)	grad_norm 1.0828 (1.1409)	
[2022-01-19 07:10:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][460/1251]	eta 0:29:20 lr 0.000919	time 2.8174 (2.2255)	loss 3.9659 (3.8937)	grad_norm 0.9317 (1.1382)	
[2022-01-19 07:10:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][470/1251]	eta 0:28:59 lr 0.000919	time 2.8175 (2.2275)	loss 3.1317 (3.8923)	grad_norm 1.1515 (1.1366)	
[2022-01-19 07:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][480/1251]	eta 0:28:39 lr 0.000919	time 2.5142 (2.2297)	loss 4.5311 (3.8942)	grad_norm 1.4064 (1.1363)	
[2022-01-19 07:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][490/1251]	eta 0:28:19 lr 0.000919	time 2.9233 (2.2328)	loss 2.9625 (3.8952)	grad_norm 1.0259 (1.1353)	
[2022-01-19 07:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][500/1251]	eta 0:27:55 lr 0.000919	time 2.8611 (2.2311)	loss 2.9276 (3.8937)	grad_norm 0.9385 (1.1356)	
[2022-01-19 07:11:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][510/1251]	eta 0:27:30 lr 0.000919	time 1.6769 (2.2275)	loss 4.7547 (3.8951)	grad_norm 1.0895 (1.1369)	
[2022-01-19 07:12:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][520/1251]	eta 0:27:05 lr 0.000919	time 1.9075 (2.2239)	loss 4.0889 (3.8974)	grad_norm 1.0895 (1.1367)	
[2022-01-19 07:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][530/1251]	eta 0:26:41 lr 0.000919	time 2.2258 (2.2205)	loss 4.2564 (3.8979)	grad_norm 1.0215 (1.1351)	
[2022-01-19 07:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][540/1251]	eta 0:26:19 lr 0.000919	time 2.5002 (2.2210)	loss 3.8004 (3.8991)	grad_norm 1.0873 (1.1350)	
[2022-01-19 07:13:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][550/1251]	eta 0:25:57 lr 0.000919	time 1.9352 (2.2212)	loss 4.3210 (3.9043)	grad_norm 1.1605 (1.1340)	
[2022-01-19 07:13:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][560/1251]	eta 0:25:33 lr 0.000919	time 1.9032 (2.2187)	loss 3.6944 (3.9036)	grad_norm 0.8897 (1.1342)	
[2022-01-19 07:13:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][570/1251]	eta 0:25:07 lr 0.000919	time 2.3296 (2.2139)	loss 4.1425 (3.9029)	grad_norm 1.3353 (1.1343)	
[2022-01-19 07:14:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][580/1251]	eta 0:24:44 lr 0.000919	time 2.0969 (2.2125)	loss 4.5767 (3.9038)	grad_norm 1.3718 (1.1357)	
[2022-01-19 07:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][590/1251]	eta 0:24:20 lr 0.000919	time 2.0805 (2.2088)	loss 3.2166 (3.9012)	grad_norm 0.9545 (1.1358)	
[2022-01-19 07:15:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][600/1251]	eta 0:23:59 lr 0.000919	time 1.8246 (2.2109)	loss 3.6373 (3.8994)	grad_norm 1.1516 (1.1372)	
[2022-01-19 07:15:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][610/1251]	eta 0:23:37 lr 0.000919	time 2.2764 (2.2114)	loss 4.7840 (3.8982)	grad_norm 1.2052 (1.1366)	
[2022-01-19 07:15:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][620/1251]	eta 0:23:18 lr 0.000919	time 3.1365 (2.2163)	loss 4.2614 (3.9022)	grad_norm 1.1885 (1.1373)	
[2022-01-19 07:16:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][630/1251]	eta 0:22:59 lr 0.000919	time 1.8007 (2.2216)	loss 4.1715 (3.9064)	grad_norm 1.1439 (1.1382)	
[2022-01-19 07:16:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][640/1251]	eta 0:22:37 lr 0.000919	time 1.6289 (2.2221)	loss 4.1620 (3.9076)	grad_norm 1.0444 (1.1377)	
[2022-01-19 07:17:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][650/1251]	eta 0:22:14 lr 0.000919	time 2.1671 (2.2203)	loss 3.9291 (3.9080)	grad_norm 1.1520 (1.1362)	
[2022-01-19 07:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][660/1251]	eta 0:21:48 lr 0.000919	time 1.8647 (2.2147)	loss 4.1439 (3.9085)	grad_norm 1.2867 (1.1376)	
[2022-01-19 07:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][670/1251]	eta 0:21:24 lr 0.000919	time 1.5800 (2.2106)	loss 2.9917 (3.9031)	grad_norm 1.1365 (1.1380)	
[2022-01-19 07:18:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][680/1251]	eta 0:21:01 lr 0.000919	time 2.1595 (2.2096)	loss 4.7781 (3.9061)	grad_norm 1.0298 (1.1378)	
[2022-01-19 07:18:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][690/1251]	eta 0:20:39 lr 0.000919	time 2.1398 (2.2097)	loss 4.2343 (3.9037)	grad_norm 0.9558 (1.1382)	
[2022-01-19 07:18:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][700/1251]	eta 0:20:16 lr 0.000919	time 2.0972 (2.2080)	loss 4.9024 (3.9020)	grad_norm 1.5257 (1.1383)	
[2022-01-19 07:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][710/1251]	eta 0:19:55 lr 0.000919	time 2.9420 (2.2105)	loss 4.0861 (3.9013)	grad_norm 1.2980 (1.1387)	
[2022-01-19 07:19:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][720/1251]	eta 0:19:35 lr 0.000919	time 2.5967 (2.2145)	loss 2.9989 (3.9000)	grad_norm 1.1277 (1.1394)	
[2022-01-19 07:19:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][730/1251]	eta 0:19:14 lr 0.000918	time 1.8532 (2.2158)	loss 4.1565 (3.9021)	grad_norm 1.2678 (1.1410)	
[2022-01-19 07:20:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][740/1251]	eta 0:18:52 lr 0.000918	time 2.5169 (2.2172)	loss 4.3159 (3.9035)	grad_norm 1.0381 (1.1410)	
[2022-01-19 07:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][750/1251]	eta 0:18:31 lr 0.000918	time 2.6008 (2.2189)	loss 3.1602 (3.9034)	grad_norm 1.0993 (1.1403)	
[2022-01-19 07:21:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][760/1251]	eta 0:18:08 lr 0.000918	time 1.8673 (2.2162)	loss 4.4040 (3.9023)	grad_norm 1.1879 (1.1408)	
[2022-01-19 07:21:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][770/1251]	eta 0:17:43 lr 0.000918	time 1.9392 (2.2117)	loss 3.7174 (3.8975)	grad_norm 1.2756 (1.1407)	
[2022-01-19 07:21:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][780/1251]	eta 0:17:21 lr 0.000918	time 2.9231 (2.2118)	loss 2.9237 (3.8952)	grad_norm 1.1440 (1.1414)	
[2022-01-19 07:22:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][790/1251]	eta 0:16:58 lr 0.000918	time 1.9168 (2.2101)	loss 3.0289 (3.8948)	grad_norm 1.4002 (1.1413)	
[2022-01-19 07:22:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][800/1251]	eta 0:16:38 lr 0.000918	time 2.2295 (2.2132)	loss 3.1788 (3.8939)	grad_norm 0.9287 (1.1404)	
[2022-01-19 07:22:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][810/1251]	eta 0:16:17 lr 0.000918	time 2.2328 (2.2160)	loss 3.8251 (3.8955)	grad_norm 1.1212 (1.1399)	
[2022-01-19 07:23:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][820/1251]	eta 0:15:55 lr 0.000918	time 1.9565 (2.2165)	loss 4.6275 (3.8941)	grad_norm 1.1997 (1.1398)	
[2022-01-19 07:23:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][830/1251]	eta 0:15:32 lr 0.000918	time 1.9395 (2.2142)	loss 4.1048 (3.8934)	grad_norm 1.0686 (1.1389)	
[2022-01-19 07:23:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][840/1251]	eta 0:15:09 lr 0.000918	time 2.1408 (2.2128)	loss 3.8307 (3.8935)	grad_norm 1.1624 (1.1387)	
[2022-01-19 07:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][850/1251]	eta 0:14:46 lr 0.000918	time 1.8689 (2.2117)	loss 2.7258 (3.8916)	grad_norm 1.2753 (1.1389)	
[2022-01-19 07:24:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][860/1251]	eta 0:14:25 lr 0.000918	time 2.5945 (2.2123)	loss 3.7062 (3.8913)	grad_norm 1.2371 (1.1403)	
[2022-01-19 07:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][870/1251]	eta 0:14:02 lr 0.000918	time 2.6485 (2.2111)	loss 3.2331 (3.8902)	grad_norm 0.9098 (1.1391)	
[2022-01-19 07:25:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][880/1251]	eta 0:13:39 lr 0.000918	time 1.8824 (2.2102)	loss 3.9799 (3.8933)	grad_norm 1.0157 (1.1387)	
[2022-01-19 07:25:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][890/1251]	eta 0:13:17 lr 0.000918	time 2.6430 (2.2091)	loss 3.5232 (3.8934)	grad_norm 1.1879 (1.1382)	
[2022-01-19 07:26:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][900/1251]	eta 0:12:55 lr 0.000918	time 1.8112 (2.2098)	loss 4.0731 (3.8939)	grad_norm 1.0581 (1.1373)	
[2022-01-19 07:26:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][910/1251]	eta 0:12:33 lr 0.000918	time 2.1878 (2.2087)	loss 3.4768 (3.8954)	grad_norm 1.1538 (1.1375)	
[2022-01-19 07:26:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][920/1251]	eta 0:12:10 lr 0.000918	time 2.1362 (2.2083)	loss 3.6354 (3.8932)	grad_norm 1.1259 (1.1376)	
[2022-01-19 07:27:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][930/1251]	eta 0:11:49 lr 0.000918	time 2.4923 (2.2101)	loss 4.4422 (3.8960)	grad_norm 1.4242 (1.1386)	
[2022-01-19 07:27:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][940/1251]	eta 0:11:27 lr 0.000918	time 2.1969 (2.2104)	loss 4.1902 (3.8990)	grad_norm 0.9833 (1.1389)	
[2022-01-19 07:27:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][950/1251]	eta 0:11:05 lr 0.000918	time 2.3535 (2.2102)	loss 4.4487 (3.9008)	grad_norm 0.9900 (1.1380)	
[2022-01-19 07:28:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][960/1251]	eta 0:10:42 lr 0.000918	time 1.6329 (2.2089)	loss 4.6045 (3.9043)	grad_norm 0.9344 (1.1370)	
[2022-01-19 07:28:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][970/1251]	eta 0:10:20 lr 0.000918	time 2.0925 (2.2090)	loss 3.1234 (3.9031)	grad_norm 1.0770 (1.1363)	
[2022-01-19 07:29:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][980/1251]	eta 0:09:58 lr 0.000918	time 1.5947 (2.2074)	loss 2.8967 (3.9008)	grad_norm 0.9549 (1.1361)	
[2022-01-19 07:29:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][990/1251]	eta 0:09:35 lr 0.000918	time 1.8275 (2.2065)	loss 4.1705 (3.9015)	grad_norm 1.0365 (1.1355)	
[2022-01-19 07:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1000/1251]	eta 0:09:13 lr 0.000918	time 1.8323 (2.2061)	loss 4.2197 (3.9024)	grad_norm 1.1956 (1.1350)	
[2022-01-19 07:30:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1010/1251]	eta 0:08:51 lr 0.000918	time 2.0273 (2.2053)	loss 2.9247 (3.8990)	grad_norm 1.2548 (1.1351)	
[2022-01-19 07:30:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1020/1251]	eta 0:08:29 lr 0.000918	time 2.1587 (2.2057)	loss 3.1553 (3.9003)	grad_norm 1.0454 (1.1351)	
[2022-01-19 07:30:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1030/1251]	eta 0:08:07 lr 0.000918	time 2.3114 (2.2067)	loss 4.0355 (3.9007)	grad_norm 1.4046 (1.1350)	
[2022-01-19 07:31:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1040/1251]	eta 0:07:45 lr 0.000918	time 2.3265 (2.2068)	loss 4.1478 (3.9015)	grad_norm 1.2051 (1.1363)	
[2022-01-19 07:31:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1050/1251]	eta 0:07:23 lr 0.000918	time 1.7516 (2.2065)	loss 3.1111 (3.9005)	grad_norm 1.2630 (1.1364)	
[2022-01-19 07:31:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1060/1251]	eta 0:07:01 lr 0.000918	time 1.7893 (2.2064)	loss 3.7832 (3.9008)	grad_norm 0.9735 (1.1357)	
[2022-01-19 07:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1070/1251]	eta 0:06:39 lr 0.000918	time 1.8353 (2.2062)	loss 2.9722 (3.8963)	grad_norm 1.1385 (1.1361)	
[2022-01-19 07:32:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1080/1251]	eta 0:06:17 lr 0.000918	time 2.1545 (2.2051)	loss 2.7462 (3.8954)	grad_norm 1.2989 (1.1359)	
[2022-01-19 07:33:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1090/1251]	eta 0:05:55 lr 0.000918	time 2.8547 (2.2056)	loss 4.5461 (3.8961)	grad_norm 1.1761 (1.1357)	
[2022-01-19 07:33:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1100/1251]	eta 0:05:32 lr 0.000918	time 1.9184 (2.2048)	loss 4.0624 (3.8964)	grad_norm 1.1603 (1.1354)	
[2022-01-19 07:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1110/1251]	eta 0:05:11 lr 0.000918	time 1.8894 (2.2061)	loss 4.4365 (3.8982)	grad_norm 0.9873 (1.1352)	
[2022-01-19 07:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1120/1251]	eta 0:04:49 lr 0.000918	time 2.8735 (2.2065)	loss 4.2492 (3.8979)	grad_norm 1.0185 (1.1352)	
[2022-01-19 07:34:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1130/1251]	eta 0:04:26 lr 0.000918	time 2.1655 (2.2058)	loss 4.1985 (3.9000)	grad_norm 1.2142 (1.1354)	
[2022-01-19 07:34:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1140/1251]	eta 0:04:04 lr 0.000918	time 1.8226 (2.2032)	loss 4.2782 (3.9009)	grad_norm 1.0755 (1.1351)	
[2022-01-19 07:35:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1150/1251]	eta 0:03:42 lr 0.000918	time 2.3691 (2.2027)	loss 4.6649 (3.9010)	grad_norm 1.2905 (1.1353)	
[2022-01-19 07:35:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1160/1251]	eta 0:03:20 lr 0.000918	time 2.0979 (2.2011)	loss 2.8720 (3.8997)	grad_norm 0.9983 (1.1343)	
[2022-01-19 07:35:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1170/1251]	eta 0:02:58 lr 0.000917	time 1.9165 (2.2001)	loss 4.3936 (3.8996)	grad_norm 1.2133 (1.1336)	
[2022-01-19 07:36:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1180/1251]	eta 0:02:36 lr 0.000917	time 2.6895 (2.1996)	loss 2.7360 (3.8980)	grad_norm 1.0391 (1.1328)	
[2022-01-19 07:36:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1190/1251]	eta 0:02:14 lr 0.000917	time 2.0345 (2.1986)	loss 3.2875 (3.8972)	grad_norm 1.2150 (1.1326)	
[2022-01-19 07:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1200/1251]	eta 0:01:52 lr 0.000917	time 1.8316 (2.1986)	loss 2.7249 (3.8940)	grad_norm 1.0538 (1.1327)	
[2022-01-19 07:37:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1210/1251]	eta 0:01:30 lr 0.000917	time 2.1979 (2.1991)	loss 4.1109 (3.8955)	grad_norm 1.0587 (1.1322)	
[2022-01-19 07:37:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1220/1251]	eta 0:01:08 lr 0.000917	time 2.2148 (2.1996)	loss 4.3747 (3.8933)	grad_norm 1.0391 (1.1320)	
[2022-01-19 07:38:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1230/1251]	eta 0:00:46 lr 0.000917	time 2.2122 (2.2008)	loss 4.3545 (3.8923)	grad_norm 1.2998 (1.1317)	
[2022-01-19 07:38:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1240/1251]	eta 0:00:24 lr 0.000917	time 1.9400 (2.2018)	loss 4.2464 (3.8916)	grad_norm 1.2522 (1.1323)	
[2022-01-19 07:38:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [55/300][1250/1251]	eta 0:00:02 lr 0.000917	time 1.0832 (2.1968)	loss 4.3203 (3.8926)	grad_norm 1.2927 (1.1333)	
[2022-01-19 07:38:44 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 55 training takes 0:45:48
[2022-01-19 07:39:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.002 (18.002)	Loss 1.2802 (1.2802)	Acc@1 68.945 (68.945)	Acc@5 89.746 (89.746)	
[2022-01-19 07:39:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.261 (3.318)	Loss 1.1826 (1.2699)	Acc@1 72.461 (70.082)	Acc@5 92.090 (90.572)	
[2022-01-19 07:39:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.621 (2.479)	Loss 1.2348 (1.2758)	Acc@1 71.973 (70.140)	Acc@5 90.332 (90.397)	
[2022-01-19 07:39:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.288 (2.228)	Loss 1.2301 (1.2701)	Acc@1 71.582 (70.322)	Acc@5 92.285 (90.609)	
[2022-01-19 07:40:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.057 (2.162)	Loss 1.2529 (1.2702)	Acc@1 70.801 (70.363)	Acc@5 91.016 (90.580)	
[2022-01-19 07:40:20 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 70.426 Acc@5 90.504
[2022-01-19 07:40:20 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 70.4%
[2022-01-19 07:40:20 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 70.79%
[2022-01-19 07:40:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][0/1251]	eta 7:31:30 lr 0.000917	time 21.6550 (21.6550)	loss 3.5418 (3.5418)	grad_norm 1.1203 (1.1203)	
[2022-01-19 07:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][10/1251]	eta 1:23:57 lr 0.000917	time 2.2375 (4.0591)	loss 2.9551 (3.6693)	grad_norm 1.3213 (1.2343)	
[2022-01-19 07:41:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][20/1251]	eta 1:05:11 lr 0.000917	time 1.5574 (3.1775)	loss 4.5218 (3.9305)	grad_norm 1.1409 (1.1933)	
[2022-01-19 07:41:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][30/1251]	eta 0:57:45 lr 0.000917	time 1.6755 (2.8382)	loss 3.9828 (3.9326)	grad_norm 1.2707 (1.1796)	
[2022-01-19 07:42:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][40/1251]	eta 0:55:00 lr 0.000917	time 3.6684 (2.7251)	loss 3.8969 (3.8805)	grad_norm 1.1379 (1.1693)	
[2022-01-19 07:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][50/1251]	eta 0:53:45 lr 0.000917	time 3.3095 (2.6861)	loss 3.3430 (3.8384)	grad_norm 1.1399 (1.1608)	
[2022-01-19 07:42:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][60/1251]	eta 0:51:42 lr 0.000917	time 1.7780 (2.6047)	loss 3.8706 (3.8616)	grad_norm 1.3152 (1.1594)	
[2022-01-19 07:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][70/1251]	eta 0:50:00 lr 0.000917	time 1.6876 (2.5409)	loss 4.4755 (3.8695)	grad_norm 1.1570 (1.1691)	
[2022-01-19 07:43:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][80/1251]	eta 0:49:06 lr 0.000917	time 3.5459 (2.5160)	loss 4.5156 (3.8500)	grad_norm 1.0780 (1.1627)	
[2022-01-19 07:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][90/1251]	eta 0:48:07 lr 0.000917	time 2.2769 (2.4873)	loss 4.7846 (3.8510)	grad_norm 1.5422 (1.1692)	
[2022-01-19 07:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][100/1251]	eta 0:46:43 lr 0.000917	time 1.6858 (2.4359)	loss 3.3101 (3.8782)	grad_norm 1.0303 (1.1615)	
[2022-01-19 07:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][110/1251]	eta 0:45:27 lr 0.000917	time 1.8469 (2.3909)	loss 3.9647 (3.8916)	grad_norm 1.0301 (1.1537)	
[2022-01-19 07:45:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][120/1251]	eta 0:44:42 lr 0.000917	time 2.5162 (2.3721)	loss 2.7386 (3.8617)	grad_norm 1.1181 (1.1526)	
[2022-01-19 07:45:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][130/1251]	eta 0:44:04 lr 0.000917	time 1.8919 (2.3594)	loss 3.2909 (3.8704)	grad_norm 1.2142 (1.1556)	
[2022-01-19 07:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][140/1251]	eta 0:43:27 lr 0.000917	time 2.0635 (2.3473)	loss 4.3127 (3.8852)	grad_norm 1.3110 (1.1533)	
[2022-01-19 07:46:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][150/1251]	eta 0:42:55 lr 0.000917	time 2.1121 (2.3394)	loss 3.5852 (3.9053)	grad_norm 0.9360 (1.1527)	
[2022-01-19 07:46:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][160/1251]	eta 0:42:28 lr 0.000917	time 3.2770 (2.3355)	loss 3.8153 (3.8866)	grad_norm 1.0589 (1.1509)	
[2022-01-19 07:46:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][170/1251]	eta 0:41:53 lr 0.000917	time 2.2443 (2.3256)	loss 4.0183 (3.8726)	grad_norm 1.1889 (1.1479)	
[2022-01-19 07:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][180/1251]	eta 0:41:21 lr 0.000917	time 2.2042 (2.3166)	loss 3.1915 (3.8728)	grad_norm 1.2665 (1.1455)	
[2022-01-19 07:47:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][190/1251]	eta 0:40:58 lr 0.000917	time 2.1782 (2.3171)	loss 4.0563 (3.8791)	grad_norm 1.1276 (1.1450)	
[2022-01-19 07:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][200/1251]	eta 0:40:30 lr 0.000917	time 2.8827 (2.3130)	loss 3.3445 (3.8659)	grad_norm 1.1325 (1.1435)	
[2022-01-19 07:48:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][210/1251]	eta 0:39:49 lr 0.000917	time 1.5309 (2.2953)	loss 3.2735 (3.8744)	grad_norm 1.1950 (1.1409)	
[2022-01-19 07:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][220/1251]	eta 0:39:10 lr 0.000917	time 1.8723 (2.2803)	loss 4.9925 (3.8802)	grad_norm 1.1822 (1.1384)	
[2022-01-19 07:49:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][230/1251]	eta 0:38:37 lr 0.000917	time 1.8833 (2.2700)	loss 4.2037 (3.8761)	grad_norm 1.2185 (1.1380)	
[2022-01-19 07:49:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][240/1251]	eta 0:38:08 lr 0.000917	time 1.9973 (2.2633)	loss 3.7226 (3.8838)	grad_norm 1.1387 (1.1411)	
[2022-01-19 07:49:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][250/1251]	eta 0:37:39 lr 0.000917	time 2.1443 (2.2577)	loss 3.5898 (3.8815)	grad_norm 1.1378 (1.1394)	
[2022-01-19 07:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][260/1251]	eta 0:37:17 lr 0.000917	time 2.2028 (2.2574)	loss 4.2768 (3.8768)	grad_norm 1.4877 (1.1429)	
[2022-01-19 07:50:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][270/1251]	eta 0:36:54 lr 0.000917	time 2.0904 (2.2570)	loss 3.3533 (3.8746)	grad_norm 1.1332 (1.1431)	
[2022-01-19 07:50:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][280/1251]	eta 0:36:31 lr 0.000917	time 2.4782 (2.2572)	loss 4.2029 (3.8810)	grad_norm 1.0845 (1.1405)	
[2022-01-19 07:51:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][290/1251]	eta 0:36:07 lr 0.000917	time 2.0199 (2.2553)	loss 4.2193 (3.8891)	grad_norm 1.2908 (1.1397)	
[2022-01-19 07:51:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][300/1251]	eta 0:35:43 lr 0.000917	time 2.5812 (2.2541)	loss 4.6754 (3.8886)	grad_norm 1.0357 (1.1368)	
[2022-01-19 07:52:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][310/1251]	eta 0:35:24 lr 0.000917	time 3.6624 (2.2579)	loss 3.0609 (3.8845)	grad_norm 1.3983 (1.1372)	
[2022-01-19 07:52:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][320/1251]	eta 0:34:55 lr 0.000917	time 1.7324 (2.2513)	loss 3.8188 (3.8884)	grad_norm 1.2364 (1.1365)	
[2022-01-19 07:52:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][330/1251]	eta 0:34:32 lr 0.000917	time 1.6815 (2.2498)	loss 4.6254 (3.8963)	grad_norm 0.8836 (1.1367)	
[2022-01-19 07:53:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][340/1251]	eta 0:34:05 lr 0.000917	time 2.6229 (2.2451)	loss 4.0378 (3.8981)	grad_norm 1.0434 (1.1355)	
[2022-01-19 07:53:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][350/1251]	eta 0:33:42 lr 0.000916	time 3.1893 (2.2453)	loss 3.7876 (3.8996)	grad_norm 1.0764 (1.1373)	
[2022-01-19 07:53:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][360/1251]	eta 0:33:17 lr 0.000916	time 2.5752 (2.2415)	loss 2.9051 (3.9001)	grad_norm 1.4485 (1.1394)	
[2022-01-19 07:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][370/1251]	eta 0:32:50 lr 0.000916	time 2.1565 (2.2367)	loss 4.1350 (3.8994)	grad_norm 1.1751 (1.1413)	
[2022-01-19 07:54:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][380/1251]	eta 0:32:26 lr 0.000916	time 2.2626 (2.2351)	loss 4.2918 (3.9008)	grad_norm 1.0274 (1.1403)	
[2022-01-19 07:54:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][390/1251]	eta 0:32:03 lr 0.000916	time 3.3038 (2.2339)	loss 3.9260 (3.9027)	grad_norm 1.4265 (1.1416)	
[2022-01-19 07:55:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][400/1251]	eta 0:31:39 lr 0.000916	time 2.1321 (2.2326)	loss 4.4050 (3.9083)	grad_norm 1.1366 (1.1411)	
[2022-01-19 07:55:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][410/1251]	eta 0:31:16 lr 0.000916	time 1.9506 (2.2308)	loss 4.7820 (3.9071)	grad_norm 1.1517 (1.1405)	
[2022-01-19 07:55:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][420/1251]	eta 0:30:53 lr 0.000916	time 2.4936 (2.2307)	loss 4.5536 (3.9043)	grad_norm 0.9404 (1.1414)	
[2022-01-19 07:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][430/1251]	eta 0:30:35 lr 0.000916	time 4.0026 (2.2354)	loss 3.9481 (3.9035)	grad_norm 0.9950 (1.1410)	
[2022-01-19 07:56:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][440/1251]	eta 0:30:14 lr 0.000916	time 2.4555 (2.2369)	loss 4.3579 (3.8990)	grad_norm 1.2081 (1.1412)	
[2022-01-19 07:57:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][450/1251]	eta 0:29:47 lr 0.000916	time 2.2900 (2.2320)	loss 3.8136 (3.9046)	grad_norm 1.0122 (1.1417)	
[2022-01-19 07:57:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][460/1251]	eta 0:29:22 lr 0.000916	time 2.1968 (2.2280)	loss 4.5545 (3.9056)	grad_norm 1.2420 (1.1435)	
[2022-01-19 07:57:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][470/1251]	eta 0:29:04 lr 0.000916	time 3.6324 (2.2332)	loss 4.1055 (3.9048)	grad_norm 1.2150 (1.1432)	
[2022-01-19 07:58:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][480/1251]	eta 0:28:44 lr 0.000916	time 2.1432 (2.2364)	loss 3.8398 (3.9105)	grad_norm 1.0930 (1.1427)	
[2022-01-19 07:58:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][490/1251]	eta 0:28:21 lr 0.000916	time 1.8560 (2.2354)	loss 4.3253 (3.9075)	grad_norm 1.2011 (1.1431)	
[2022-01-19 07:58:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][500/1251]	eta 0:27:57 lr 0.000916	time 2.8444 (2.2334)	loss 4.3035 (3.9067)	grad_norm 1.1444 (1.1427)	
[2022-01-19 07:59:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][510/1251]	eta 0:27:31 lr 0.000916	time 1.5693 (2.2285)	loss 4.1210 (3.9045)	grad_norm 1.0514 (1.1418)	
[2022-01-19 07:59:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][520/1251]	eta 0:27:06 lr 0.000916	time 2.2543 (2.2252)	loss 3.3698 (3.9052)	grad_norm 1.0527 (1.1422)	
[2022-01-19 08:00:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][530/1251]	eta 0:26:42 lr 0.000916	time 2.1654 (2.2225)	loss 3.3470 (3.9026)	grad_norm 1.2497 (1.1430)	
[2022-01-19 08:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][540/1251]	eta 0:26:17 lr 0.000916	time 1.9491 (2.2186)	loss 4.2366 (3.9068)	grad_norm 1.0022 (1.1449)	
[2022-01-19 08:00:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][550/1251]	eta 0:25:54 lr 0.000916	time 1.6056 (2.2178)	loss 3.4028 (3.9114)	grad_norm 1.1005 (1.1446)	
[2022-01-19 08:01:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][560/1251]	eta 0:25:32 lr 0.000916	time 3.1088 (2.2178)	loss 2.9825 (3.9115)	grad_norm 0.9624 (1.1442)	
[2022-01-19 08:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][570/1251]	eta 0:25:10 lr 0.000916	time 2.2281 (2.2180)	loss 3.6523 (3.9111)	grad_norm 1.1515 (1.1452)	
[2022-01-19 08:01:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][580/1251]	eta 0:24:48 lr 0.000916	time 1.9329 (2.2186)	loss 4.5646 (3.9143)	grad_norm 0.9961 (1.1437)	
[2022-01-19 08:02:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][590/1251]	eta 0:24:27 lr 0.000916	time 2.1327 (2.2205)	loss 4.1316 (3.9120)	grad_norm 1.3222 (1.1438)	
[2022-01-19 08:02:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][600/1251]	eta 0:24:05 lr 0.000916	time 2.1375 (2.2205)	loss 3.9727 (3.9128)	grad_norm 1.0295 (1.1448)	
[2022-01-19 08:02:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][610/1251]	eta 0:23:43 lr 0.000916	time 2.5301 (2.2207)	loss 3.4117 (3.9169)	grad_norm 1.0686 (1.1443)	
[2022-01-19 08:03:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][620/1251]	eta 0:23:19 lr 0.000916	time 1.8422 (2.2181)	loss 3.9278 (3.9174)	grad_norm 1.0205 (1.1433)	
[2022-01-19 08:03:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][630/1251]	eta 0:22:56 lr 0.000916	time 2.1254 (2.2159)	loss 4.2794 (3.9182)	grad_norm 1.3240 (1.1437)	
[2022-01-19 08:04:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][640/1251]	eta 0:22:33 lr 0.000916	time 2.2429 (2.2156)	loss 4.3179 (3.9172)	grad_norm 1.2018 (1.1439)	
[2022-01-19 08:04:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][650/1251]	eta 0:22:11 lr 0.000916	time 2.6697 (2.2154)	loss 4.0706 (3.9203)	grad_norm 1.1535 (1.1430)	
[2022-01-19 08:04:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][660/1251]	eta 0:21:49 lr 0.000916	time 1.5805 (2.2150)	loss 4.0902 (3.9202)	grad_norm 1.0010 (1.1431)	
[2022-01-19 08:05:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][670/1251]	eta 0:21:25 lr 0.000916	time 1.6199 (2.2131)	loss 4.3727 (3.9219)	grad_norm 1.2682 (1.1436)	
[2022-01-19 08:05:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][680/1251]	eta 0:21:03 lr 0.000916	time 2.1341 (2.2131)	loss 3.7748 (3.9246)	grad_norm 1.1113 (1.1435)	
[2022-01-19 08:05:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][690/1251]	eta 0:20:41 lr 0.000916	time 2.2674 (2.2131)	loss 3.9926 (3.9229)	grad_norm 1.0756 (1.1441)	
[2022-01-19 08:06:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][700/1251]	eta 0:20:19 lr 0.000916	time 2.1622 (2.2127)	loss 3.1460 (3.9182)	grad_norm 1.0531 (1.1434)	
[2022-01-19 08:06:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][710/1251]	eta 0:19:57 lr 0.000916	time 1.8609 (2.2140)	loss 3.8241 (3.9182)	grad_norm 1.0593 (1.1426)	
[2022-01-19 08:06:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][720/1251]	eta 0:19:35 lr 0.000916	time 2.1090 (2.2128)	loss 4.5150 (3.9156)	grad_norm 1.0893 (1.1425)	
[2022-01-19 08:07:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][730/1251]	eta 0:19:12 lr 0.000916	time 2.4858 (2.2122)	loss 2.8707 (3.9159)	grad_norm 1.0815 (1.1424)	
[2022-01-19 08:07:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][740/1251]	eta 0:18:49 lr 0.000916	time 1.6818 (2.2097)	loss 4.1593 (3.9102)	grad_norm 0.9279 (1.1423)	
[2022-01-19 08:08:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][750/1251]	eta 0:18:27 lr 0.000916	time 2.3714 (2.2110)	loss 4.6671 (3.9100)	grad_norm 1.0070 (1.1423)	
[2022-01-19 08:08:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][760/1251]	eta 0:18:05 lr 0.000916	time 1.5462 (2.2101)	loss 4.1696 (3.9088)	grad_norm 1.1033 (1.1427)	
[2022-01-19 08:08:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][770/1251]	eta 0:17:43 lr 0.000916	time 2.5965 (2.2102)	loss 4.7381 (3.9105)	grad_norm 1.5198 (1.1437)	
[2022-01-19 08:09:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][780/1251]	eta 0:17:20 lr 0.000915	time 1.8336 (2.2083)	loss 4.2040 (3.9102)	grad_norm 1.0790 (1.1442)	
[2022-01-19 08:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][790/1251]	eta 0:16:57 lr 0.000915	time 1.7699 (2.2073)	loss 3.8190 (3.9080)	grad_norm 1.0964 (1.1444)	
[2022-01-19 08:09:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][800/1251]	eta 0:16:34 lr 0.000915	time 1.8946 (2.2050)	loss 4.0064 (3.9099)	grad_norm 0.9029 (1.1454)	
[2022-01-19 08:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][810/1251]	eta 0:16:11 lr 0.000915	time 2.4641 (2.2037)	loss 3.7567 (3.9123)	grad_norm 1.1893 (1.1462)	
[2022-01-19 08:10:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][820/1251]	eta 0:15:50 lr 0.000915	time 2.1883 (2.2048)	loss 3.8454 (3.9102)	grad_norm 1.2280 (1.1474)	
[2022-01-19 08:10:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][830/1251]	eta 0:15:29 lr 0.000915	time 2.1890 (2.2082)	loss 4.2466 (3.9083)	grad_norm 1.0589 (1.1465)	
[2022-01-19 08:11:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][840/1251]	eta 0:15:07 lr 0.000915	time 2.2377 (2.2078)	loss 4.4748 (3.9085)	grad_norm 1.0112 (1.1466)	
[2022-01-19 08:11:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][850/1251]	eta 0:14:44 lr 0.000915	time 1.8616 (2.2067)	loss 4.5095 (3.9083)	grad_norm 1.1743 (1.1466)	
[2022-01-19 08:11:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][860/1251]	eta 0:14:22 lr 0.000915	time 2.4193 (2.2052)	loss 3.6605 (3.9129)	grad_norm 0.9437 (1.1460)	
[2022-01-19 08:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][870/1251]	eta 0:14:00 lr 0.000915	time 1.7726 (2.2055)	loss 4.2685 (3.9122)	grad_norm 1.0155 (1.1454)	
[2022-01-19 08:12:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][880/1251]	eta 0:13:38 lr 0.000915	time 2.0041 (2.2056)	loss 3.7525 (3.9091)	grad_norm 1.0460 (1.1453)	
[2022-01-19 08:13:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][890/1251]	eta 0:13:16 lr 0.000915	time 2.4926 (2.2059)	loss 3.4125 (3.9115)	grad_norm 1.5430 (1.1451)	
[2022-01-19 08:13:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][900/1251]	eta 0:12:53 lr 0.000915	time 1.8584 (2.2042)	loss 3.9889 (3.9147)	grad_norm 1.2049 (1.1448)	
[2022-01-19 08:13:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][910/1251]	eta 0:12:31 lr 0.000915	time 1.6538 (2.2032)	loss 4.5249 (3.9168)	grad_norm 0.9836 (1.1447)	
[2022-01-19 08:14:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][920/1251]	eta 0:12:09 lr 0.000915	time 2.0287 (2.2029)	loss 3.6655 (3.9165)	grad_norm 1.2049 (1.1450)	
[2022-01-19 08:14:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][930/1251]	eta 0:11:48 lr 0.000915	time 1.7635 (2.2057)	loss 4.1697 (3.9165)	grad_norm 1.0865 (1.1448)	
[2022-01-19 08:14:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][940/1251]	eta 0:11:25 lr 0.000915	time 1.8852 (2.2037)	loss 3.5598 (3.9147)	grad_norm 1.1763 (1.1450)	
[2022-01-19 08:15:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][950/1251]	eta 0:11:03 lr 0.000915	time 1.9232 (2.2034)	loss 4.3307 (3.9138)	grad_norm 0.9380 (1.1440)	
[2022-01-19 08:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][960/1251]	eta 0:10:40 lr 0.000915	time 1.9234 (2.2021)	loss 4.4820 (3.9151)	grad_norm 1.0583 (1.1438)	
[2022-01-19 08:15:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][970/1251]	eta 0:10:18 lr 0.000915	time 2.1235 (2.2021)	loss 3.6071 (3.9155)	grad_norm 1.0444 (1.1437)	
[2022-01-19 08:16:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][980/1251]	eta 0:09:56 lr 0.000915	time 1.9913 (2.2023)	loss 3.4004 (3.9175)	grad_norm 0.9658 (1.1427)	
[2022-01-19 08:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][990/1251]	eta 0:09:34 lr 0.000915	time 1.8307 (2.2019)	loss 4.4401 (3.9207)	grad_norm 1.6090 (1.1427)	
[2022-01-19 08:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1000/1251]	eta 0:09:12 lr 0.000915	time 1.9353 (2.2027)	loss 4.3286 (3.9223)	grad_norm 1.1879 (1.1425)	
[2022-01-19 08:17:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1010/1251]	eta 0:08:51 lr 0.000915	time 2.8590 (2.2046)	loss 3.6336 (3.9189)	grad_norm 1.0320 (1.1420)	
[2022-01-19 08:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1020/1251]	eta 0:08:28 lr 0.000915	time 2.0242 (2.2033)	loss 3.8823 (3.9166)	grad_norm 1.1300 (1.1415)	
[2022-01-19 08:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1030/1251]	eta 0:08:06 lr 0.000915	time 1.9059 (2.2021)	loss 4.8598 (3.9162)	grad_norm 1.1142 (1.1413)	
[2022-01-19 08:18:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1040/1251]	eta 0:07:44 lr 0.000915	time 2.4461 (2.2020)	loss 3.9586 (3.9155)	grad_norm 1.2432 (1.1407)	
[2022-01-19 08:18:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1050/1251]	eta 0:07:22 lr 0.000915	time 2.3907 (2.2010)	loss 3.5226 (3.9129)	grad_norm 1.1583 (1.1402)	
[2022-01-19 08:19:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1060/1251]	eta 0:07:00 lr 0.000915	time 1.5978 (2.2008)	loss 4.2022 (3.9127)	grad_norm 1.0484 (1.1399)	
[2022-01-19 08:19:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1070/1251]	eta 0:06:38 lr 0.000915	time 1.8285 (2.2009)	loss 2.7346 (3.9137)	grad_norm 1.1338 (1.1396)	
[2022-01-19 08:19:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1080/1251]	eta 0:06:16 lr 0.000915	time 2.3311 (2.1996)	loss 4.3782 (3.9143)	grad_norm 1.5516 (1.1396)	
[2022-01-19 08:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1090/1251]	eta 0:05:54 lr 0.000915	time 2.0947 (2.1992)	loss 3.4698 (3.9125)	grad_norm 1.4433 (1.1400)	
[2022-01-19 08:20:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1100/1251]	eta 0:05:32 lr 0.000915	time 1.6103 (2.1987)	loss 3.1033 (3.9130)	grad_norm 1.1644 (1.1398)	
[2022-01-19 08:21:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1110/1251]	eta 0:05:10 lr 0.000915	time 2.2486 (2.1991)	loss 3.5547 (3.9127)	grad_norm 1.2883 (1.1406)	
[2022-01-19 08:21:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1120/1251]	eta 0:04:47 lr 0.000915	time 2.4865 (2.1984)	loss 3.5625 (3.9126)	grad_norm 1.3013 (1.1407)	
[2022-01-19 08:21:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1130/1251]	eta 0:04:25 lr 0.000915	time 1.8028 (2.1981)	loss 4.2609 (3.9143)	grad_norm 1.0233 (1.1402)	
[2022-01-19 08:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1140/1251]	eta 0:04:04 lr 0.000915	time 2.1203 (2.1992)	loss 2.8761 (3.9111)	grad_norm 0.9460 (1.1395)	
[2022-01-19 08:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1150/1251]	eta 0:03:42 lr 0.000915	time 1.9270 (2.1989)	loss 4.2103 (3.9102)	grad_norm 1.1848 (1.1392)	
[2022-01-19 08:22:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1160/1251]	eta 0:03:20 lr 0.000915	time 2.1491 (2.1988)	loss 4.1017 (3.9096)	grad_norm 1.1373 (1.1390)	
[2022-01-19 08:23:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1170/1251]	eta 0:02:58 lr 0.000915	time 1.5604 (2.1981)	loss 4.0037 (3.9090)	grad_norm 1.0027 (1.1388)	
[2022-01-19 08:23:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1180/1251]	eta 0:02:36 lr 0.000915	time 1.9486 (2.1985)	loss 4.0300 (3.9099)	grad_norm 1.1126 (1.1388)	
[2022-01-19 08:23:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1190/1251]	eta 0:02:14 lr 0.000915	time 3.1062 (2.1986)	loss 4.1227 (3.9136)	grad_norm 1.0350 (1.1387)	
[2022-01-19 08:24:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1200/1251]	eta 0:01:52 lr 0.000915	time 1.7992 (2.1973)	loss 3.2813 (3.9128)	grad_norm 1.0824 (1.1383)	
[2022-01-19 08:24:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1210/1251]	eta 0:01:30 lr 0.000915	time 2.1401 (2.1960)	loss 3.9901 (3.9125)	grad_norm 1.3246 (1.1390)	
[2022-01-19 08:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1220/1251]	eta 0:01:08 lr 0.000914	time 2.2922 (2.1963)	loss 4.4970 (3.9148)	grad_norm 1.1012 (1.1388)	
[2022-01-19 08:25:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1230/1251]	eta 0:00:46 lr 0.000914	time 3.5677 (2.1972)	loss 3.9428 (3.9128)	grad_norm 1.0210 (1.1396)	
[2022-01-19 08:25:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1240/1251]	eta 0:00:24 lr 0.000914	time 1.1834 (2.1964)	loss 3.8611 (3.9121)	grad_norm 1.1627 (1.1399)	
[2022-01-19 08:26:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [56/300][1250/1251]	eta 0:00:02 lr 0.000914	time 1.1823 (2.1911)	loss 4.2013 (3.9120)	grad_norm 1.1328 (1.1401)	
[2022-01-19 08:26:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 56 training takes 0:45:41
[2022-01-19 08:26:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.136 (18.136)	Loss 1.2248 (1.2248)	Acc@1 71.582 (71.582)	Acc@5 89.941 (89.941)	
[2022-01-19 08:26:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.332 (3.203)	Loss 1.2421 (1.2355)	Acc@1 70.410 (70.845)	Acc@5 90.527 (90.732)	
[2022-01-19 08:26:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.949 (2.513)	Loss 1.2729 (1.2469)	Acc@1 69.141 (70.736)	Acc@5 90.137 (90.402)	
[2022-01-19 08:27:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.933 (2.265)	Loss 1.2634 (1.2450)	Acc@1 70.117 (70.820)	Acc@5 89.941 (90.427)	
[2022-01-19 08:27:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.844 (2.158)	Loss 1.3025 (1.2426)	Acc@1 70.410 (70.965)	Acc@5 89.062 (90.494)	
[2022-01-19 08:27:37 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 70.934 Acc@5 90.542
[2022-01-19 08:27:37 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 70.9%
[2022-01-19 08:27:37 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 70.93%
[2022-01-19 08:27:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][0/1251]	eta 7:25:55 lr 0.000914	time 21.3872 (21.3872)	loss 3.0124 (3.0124)	grad_norm 1.1637 (1.1637)	
[2022-01-19 08:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][10/1251]	eta 1:22:10 lr 0.000914	time 2.2160 (3.9734)	loss 4.1881 (4.1118)	grad_norm 1.2275 (1.0946)	
[2022-01-19 08:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][20/1251]	eta 1:02:50 lr 0.000914	time 1.3912 (3.0630)	loss 3.2231 (3.7451)	grad_norm 1.0245 (1.1253)	
[2022-01-19 08:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][30/1251]	eta 0:56:10 lr 0.000914	time 1.5572 (2.7608)	loss 2.8776 (3.7234)	grad_norm 1.1887 (1.1425)	
[2022-01-19 08:29:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][40/1251]	eta 0:53:37 lr 0.000914	time 3.1523 (2.6566)	loss 4.2343 (3.7562)	grad_norm 0.9523 (1.1432)	
[2022-01-19 08:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][50/1251]	eta 0:52:22 lr 0.000914	time 2.6917 (2.6162)	loss 4.0097 (3.7322)	grad_norm 1.0564 (1.1327)	
[2022-01-19 08:30:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][60/1251]	eta 0:50:32 lr 0.000914	time 2.1981 (2.5462)	loss 3.1455 (3.7456)	grad_norm 1.0979 (1.1273)	
[2022-01-19 08:30:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][70/1251]	eta 0:49:13 lr 0.000914	time 1.6661 (2.5011)	loss 4.1976 (3.7539)	grad_norm 1.1150 (1.1361)	
[2022-01-19 08:30:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][80/1251]	eta 0:47:57 lr 0.000914	time 2.2082 (2.4572)	loss 4.4042 (3.7839)	grad_norm 0.9971 (1.1346)	
[2022-01-19 08:31:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][90/1251]	eta 0:47:05 lr 0.000914	time 2.3188 (2.4338)	loss 4.0657 (3.8106)	grad_norm 1.3390 (1.1372)	
[2022-01-19 08:31:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][100/1251]	eta 0:46:29 lr 0.000914	time 2.4135 (2.4239)	loss 4.2011 (3.8204)	grad_norm 1.3085 (1.1397)	
[2022-01-19 08:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][110/1251]	eta 0:45:52 lr 0.000914	time 1.9144 (2.4121)	loss 2.6304 (3.8333)	grad_norm 1.0869 (1.1400)	
[2022-01-19 08:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][120/1251]	eta 0:45:02 lr 0.000914	time 2.4529 (2.3896)	loss 4.3859 (3.8147)	grad_norm 1.2076 (1.1426)	
[2022-01-19 08:32:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][130/1251]	eta 0:44:20 lr 0.000914	time 1.9714 (2.3734)	loss 4.0377 (3.8287)	grad_norm 1.4457 (1.1449)	
[2022-01-19 08:33:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][140/1251]	eta 0:43:34 lr 0.000914	time 2.6837 (2.3532)	loss 4.0803 (3.8597)	grad_norm 1.1796 (1.1432)	
[2022-01-19 08:33:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][150/1251]	eta 0:42:53 lr 0.000914	time 2.3246 (2.3377)	loss 3.8829 (3.8668)	grad_norm 1.0258 (1.1414)	
[2022-01-19 08:33:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][160/1251]	eta 0:42:08 lr 0.000914	time 1.6929 (2.3176)	loss 4.3107 (3.8700)	grad_norm 1.0304 (1.1389)	
[2022-01-19 08:34:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][170/1251]	eta 0:41:37 lr 0.000914	time 1.3753 (2.3102)	loss 4.5521 (3.8789)	grad_norm 1.6153 (1.1390)	
[2022-01-19 08:34:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][180/1251]	eta 0:41:02 lr 0.000914	time 2.4364 (2.2989)	loss 3.2546 (3.8842)	grad_norm 1.2313 (1.1361)	
[2022-01-19 08:34:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][190/1251]	eta 0:40:33 lr 0.000914	time 2.0698 (2.2939)	loss 3.2702 (3.8856)	grad_norm 1.0702 (1.1360)	
[2022-01-19 08:35:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][200/1251]	eta 0:40:01 lr 0.000914	time 1.8914 (2.2847)	loss 3.2521 (3.8786)	grad_norm 1.0646 (1.1336)	
[2022-01-19 08:35:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][210/1251]	eta 0:39:40 lr 0.000914	time 1.9045 (2.2866)	loss 4.5255 (3.8706)	grad_norm 1.0164 (1.1325)	
[2022-01-19 08:36:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][220/1251]	eta 0:39:09 lr 0.000914	time 1.8907 (2.2790)	loss 3.6887 (3.8643)	grad_norm 1.1394 (1.1317)	
[2022-01-19 08:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][230/1251]	eta 0:38:44 lr 0.000914	time 2.5405 (2.2768)	loss 4.1935 (3.8649)	grad_norm 1.5451 (1.1321)	
[2022-01-19 08:36:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][240/1251]	eta 0:38:18 lr 0.000914	time 2.2339 (2.2735)	loss 4.5411 (3.8610)	grad_norm 1.1806 (1.1333)	
[2022-01-19 08:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][250/1251]	eta 0:38:00 lr 0.000914	time 2.0852 (2.2785)	loss 4.7103 (3.8581)	grad_norm 1.1772 (1.1338)	
[2022-01-19 08:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][260/1251]	eta 0:37:35 lr 0.000914	time 2.0601 (2.2757)	loss 4.2240 (3.8597)	grad_norm 1.1384 (1.1344)	
[2022-01-19 08:37:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][270/1251]	eta 0:37:06 lr 0.000914	time 2.2681 (2.2699)	loss 3.5825 (3.8560)	grad_norm 1.0211 (1.1366)	
[2022-01-19 08:38:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][280/1251]	eta 0:36:39 lr 0.000914	time 1.6299 (2.2647)	loss 4.4303 (3.8558)	grad_norm 0.9439 (1.1356)	
[2022-01-19 08:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][290/1251]	eta 0:36:19 lr 0.000914	time 2.1460 (2.2675)	loss 3.0305 (3.8547)	grad_norm 1.1345 (1.1331)	
[2022-01-19 08:38:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][300/1251]	eta 0:35:54 lr 0.000914	time 1.8963 (2.2654)	loss 3.3584 (3.8566)	grad_norm 1.0271 (1.1335)	
[2022-01-19 08:39:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][310/1251]	eta 0:35:28 lr 0.000914	time 2.2008 (2.2617)	loss 4.6728 (3.8632)	grad_norm 1.1432 (1.1315)	
[2022-01-19 08:39:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][320/1251]	eta 0:34:58 lr 0.000914	time 1.9140 (2.2543)	loss 4.6344 (3.8720)	grad_norm 1.3944 (1.1318)	
[2022-01-19 08:40:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][330/1251]	eta 0:34:36 lr 0.000914	time 2.0991 (2.2544)	loss 4.2283 (3.8742)	grad_norm 1.4080 (1.1337)	
[2022-01-19 08:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][340/1251]	eta 0:34:11 lr 0.000914	time 1.8687 (2.2519)	loss 3.2625 (3.8652)	grad_norm 1.2868 (1.1332)	
[2022-01-19 08:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][350/1251]	eta 0:33:47 lr 0.000914	time 1.9014 (2.2500)	loss 4.7330 (3.8675)	grad_norm 1.1166 (1.1322)	
[2022-01-19 08:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][360/1251]	eta 0:33:24 lr 0.000914	time 2.5402 (2.2493)	loss 4.2001 (3.8697)	grad_norm 1.3043 (1.1347)	
[2022-01-19 08:41:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][370/1251]	eta 0:33:02 lr 0.000914	time 1.9958 (2.2504)	loss 2.7323 (3.8715)	grad_norm 1.4544 (1.1361)	
[2022-01-19 08:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][380/1251]	eta 0:32:35 lr 0.000914	time 1.9141 (2.2446)	loss 4.4077 (3.8757)	grad_norm 1.0084 (1.1369)	
[2022-01-19 08:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][390/1251]	eta 0:32:10 lr 0.000913	time 1.9735 (2.2417)	loss 4.5002 (3.8821)	grad_norm 1.2546 (1.1383)	
[2022-01-19 08:42:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][400/1251]	eta 0:31:45 lr 0.000913	time 2.2964 (2.2387)	loss 4.1179 (3.8895)	grad_norm 1.1884 (1.1401)	
[2022-01-19 08:42:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][410/1251]	eta 0:31:24 lr 0.000913	time 2.1976 (2.2409)	loss 4.2966 (3.8870)	grad_norm 0.9608 (1.1403)	
[2022-01-19 08:43:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][420/1251]	eta 0:30:59 lr 0.000913	time 1.8343 (2.2373)	loss 4.4676 (3.8874)	grad_norm 0.9837 (1.1407)	
[2022-01-19 08:43:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][430/1251]	eta 0:30:31 lr 0.000913	time 1.5904 (2.2309)	loss 2.8860 (3.8859)	grad_norm 1.4324 (1.1450)	
[2022-01-19 08:43:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][440/1251]	eta 0:30:05 lr 0.000913	time 1.8658 (2.2266)	loss 4.3595 (3.8881)	grad_norm 1.1513 (1.1464)	
[2022-01-19 08:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][450/1251]	eta 0:29:43 lr 0.000913	time 2.4507 (2.2270)	loss 4.0025 (3.8966)	grad_norm 1.1210 (1.1466)	
[2022-01-19 08:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][460/1251]	eta 0:29:23 lr 0.000913	time 2.0981 (2.2295)	loss 4.4819 (3.8961)	grad_norm 0.9954 (1.1462)	
[2022-01-19 08:45:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][470/1251]	eta 0:29:01 lr 0.000913	time 2.1014 (2.2293)	loss 4.2617 (3.8990)	grad_norm 1.1011 (1.1444)	
[2022-01-19 08:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][480/1251]	eta 0:28:41 lr 0.000913	time 1.9319 (2.2331)	loss 3.6485 (3.8912)	grad_norm 1.0755 (1.1446)	
[2022-01-19 08:45:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][490/1251]	eta 0:28:18 lr 0.000913	time 2.5079 (2.2317)	loss 4.1202 (3.8873)	grad_norm 1.0977 (1.1430)	
[2022-01-19 08:46:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][500/1251]	eta 0:27:51 lr 0.000913	time 1.9485 (2.2261)	loss 4.2504 (3.8851)	grad_norm 1.0563 (1.1431)	
[2022-01-19 08:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][510/1251]	eta 0:27:29 lr 0.000913	time 1.7080 (2.2261)	loss 2.7610 (3.8848)	grad_norm 1.1438 (1.1442)	
[2022-01-19 08:46:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][520/1251]	eta 0:27:07 lr 0.000913	time 1.8777 (2.2258)	loss 4.0572 (3.8865)	grad_norm 1.1609 (1.1432)	
[2022-01-19 08:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][530/1251]	eta 0:26:45 lr 0.000913	time 2.2899 (2.2268)	loss 3.9798 (3.8863)	grad_norm 1.2154 (1.1424)	
[2022-01-19 08:47:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][540/1251]	eta 0:26:21 lr 0.000913	time 1.9378 (2.2247)	loss 4.4443 (3.8845)	grad_norm 1.0274 (1.1435)	
[2022-01-19 08:48:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][550/1251]	eta 0:25:58 lr 0.000913	time 2.1814 (2.2226)	loss 4.1958 (3.8845)	grad_norm 1.0739 (1.1455)	
[2022-01-19 08:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][560/1251]	eta 0:25:32 lr 0.000913	time 2.1409 (2.2183)	loss 2.7995 (3.8852)	grad_norm 1.3447 (1.1482)	
[2022-01-19 08:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][570/1251]	eta 0:25:09 lr 0.000913	time 2.2037 (2.2172)	loss 4.7685 (3.8856)	grad_norm 1.0635 (1.1491)	
[2022-01-19 08:49:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][580/1251]	eta 0:24:47 lr 0.000913	time 2.1902 (2.2175)	loss 3.7954 (3.8784)	grad_norm 1.0015 (1.1489)	
[2022-01-19 08:49:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][590/1251]	eta 0:24:26 lr 0.000913	time 2.1235 (2.2188)	loss 4.1938 (3.8789)	grad_norm 1.0925 (1.1476)	
[2022-01-19 08:49:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][600/1251]	eta 0:24:03 lr 0.000913	time 1.8480 (2.2180)	loss 3.0316 (3.8762)	grad_norm 1.1660 (1.1489)	
[2022-01-19 08:50:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][610/1251]	eta 0:23:42 lr 0.000913	time 2.1479 (2.2185)	loss 3.3061 (3.8768)	grad_norm 1.1316 (1.1488)	
[2022-01-19 08:50:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][620/1251]	eta 0:23:19 lr 0.000913	time 1.6928 (2.2173)	loss 3.1850 (3.8711)	grad_norm 1.2087 (1.1480)	
[2022-01-19 08:50:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][630/1251]	eta 0:22:57 lr 0.000913	time 2.8605 (2.2174)	loss 3.1390 (3.8734)	grad_norm 1.1397 (1.1482)	
[2022-01-19 08:51:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][640/1251]	eta 0:22:34 lr 0.000913	time 2.5222 (2.2165)	loss 4.1088 (3.8723)	grad_norm 0.9992 (1.1480)	
[2022-01-19 08:51:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][650/1251]	eta 0:22:11 lr 0.000913	time 1.8994 (2.2154)	loss 2.9176 (3.8741)	grad_norm 1.2063 (1.1480)	
[2022-01-19 08:52:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][660/1251]	eta 0:21:49 lr 0.000913	time 1.8768 (2.2156)	loss 4.7746 (3.8759)	grad_norm 0.9412 (1.1470)	
[2022-01-19 08:52:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][670/1251]	eta 0:21:28 lr 0.000913	time 2.5387 (2.2171)	loss 4.2858 (3.8778)	grad_norm 1.0547 (1.1473)	
[2022-01-19 08:52:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][680/1251]	eta 0:21:05 lr 0.000913	time 1.8255 (2.2164)	loss 3.4570 (3.8797)	grad_norm 1.3647 (1.1484)	
[2022-01-19 08:53:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][690/1251]	eta 0:20:41 lr 0.000913	time 1.8759 (2.2136)	loss 4.0765 (3.8796)	grad_norm 1.0590 (1.1485)	
[2022-01-19 08:53:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][700/1251]	eta 0:20:18 lr 0.000913	time 1.5488 (2.2109)	loss 4.8053 (3.8822)	grad_norm 1.0658 (1.1486)	
[2022-01-19 08:53:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][710/1251]	eta 0:19:55 lr 0.000913	time 1.9598 (2.2103)	loss 3.0889 (3.8853)	grad_norm 1.4611 (1.1502)	
[2022-01-19 08:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][720/1251]	eta 0:19:34 lr 0.000913	time 2.2359 (2.2119)	loss 3.6710 (3.8852)	grad_norm 1.0208 (1.1507)	
[2022-01-19 08:54:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][730/1251]	eta 0:19:13 lr 0.000913	time 2.6911 (2.2131)	loss 3.3090 (3.8857)	grad_norm 1.0398 (1.1502)	
[2022-01-19 08:54:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][740/1251]	eta 0:18:50 lr 0.000913	time 1.8880 (2.2124)	loss 3.4286 (3.8846)	grad_norm 1.2192 (1.1506)	
[2022-01-19 08:55:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][750/1251]	eta 0:18:27 lr 0.000913	time 1.9154 (2.2108)	loss 3.1388 (3.8814)	grad_norm 0.9550 (1.1505)	
[2022-01-19 08:55:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][760/1251]	eta 0:18:04 lr 0.000913	time 2.0385 (2.2080)	loss 3.3999 (3.8808)	grad_norm 1.6831 (1.1513)	
[2022-01-19 08:55:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][770/1251]	eta 0:17:40 lr 0.000913	time 1.9718 (2.2057)	loss 4.9127 (3.8835)	grad_norm 1.3901 (1.1519)	
[2022-01-19 08:56:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][780/1251]	eta 0:17:18 lr 0.000913	time 2.0890 (2.2050)	loss 3.7907 (3.8861)	grad_norm 1.2777 (1.1532)	
[2022-01-19 08:56:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][790/1251]	eta 0:16:57 lr 0.000913	time 2.8399 (2.2065)	loss 4.7957 (3.8878)	grad_norm 0.9538 (1.1521)	
[2022-01-19 08:57:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][800/1251]	eta 0:16:35 lr 0.000913	time 2.2254 (2.2075)	loss 3.5210 (3.8874)	grad_norm 1.1266 (1.1513)	
[2022-01-19 08:57:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][810/1251]	eta 0:16:14 lr 0.000913	time 1.9679 (2.2086)	loss 3.9313 (3.8921)	grad_norm 1.1186 (1.1523)	
[2022-01-19 08:57:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][820/1251]	eta 0:15:51 lr 0.000912	time 1.9925 (2.2082)	loss 3.7523 (3.8923)	grad_norm 1.1836 (1.1528)	
[2022-01-19 08:58:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][830/1251]	eta 0:15:29 lr 0.000912	time 2.4323 (2.2073)	loss 3.6992 (3.8891)	grad_norm 1.2450 (1.1528)	
[2022-01-19 08:58:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][840/1251]	eta 0:15:06 lr 0.000912	time 2.0377 (2.2060)	loss 4.5824 (3.8882)	grad_norm 1.0922 (1.1514)	
[2022-01-19 08:58:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][850/1251]	eta 0:14:43 lr 0.000912	time 2.4303 (2.2041)	loss 3.4625 (3.8856)	grad_norm 1.0497 (1.1509)	
[2022-01-19 08:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][860/1251]	eta 0:14:21 lr 0.000912	time 1.9411 (2.2031)	loss 4.1093 (3.8854)	grad_norm 0.9992 (1.1505)	
[2022-01-19 08:59:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][870/1251]	eta 0:13:59 lr 0.000912	time 2.4907 (2.2037)	loss 2.7692 (3.8832)	grad_norm 0.9962 (1.1495)	
[2022-01-19 08:59:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][880/1251]	eta 0:13:37 lr 0.000912	time 1.5431 (2.2026)	loss 3.1092 (3.8817)	grad_norm 1.2397 (1.1497)	
[2022-01-19 09:00:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][890/1251]	eta 0:13:15 lr 0.000912	time 2.1791 (2.2028)	loss 3.0091 (3.8788)	grad_norm 1.0473 (1.1488)	
[2022-01-19 09:00:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][900/1251]	eta 0:12:53 lr 0.000912	time 1.9967 (2.2027)	loss 4.1271 (3.8798)	grad_norm 1.1129 (1.1481)	
[2022-01-19 09:01:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][910/1251]	eta 0:12:31 lr 0.000912	time 2.3859 (2.2031)	loss 4.0984 (3.8830)	grad_norm 1.0589 (1.1476)	
[2022-01-19 09:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][920/1251]	eta 0:12:09 lr 0.000912	time 2.0613 (2.2035)	loss 3.3988 (3.8833)	grad_norm 0.9988 (1.1475)	
[2022-01-19 09:01:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][930/1251]	eta 0:11:47 lr 0.000912	time 1.5777 (2.2042)	loss 3.3424 (3.8851)	grad_norm 1.2130 (1.1469)	
[2022-01-19 09:02:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][940/1251]	eta 0:11:24 lr 0.000912	time 2.0433 (2.2017)	loss 4.4717 (3.8858)	grad_norm 1.2428 (1.1469)	
[2022-01-19 09:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][950/1251]	eta 0:11:02 lr 0.000912	time 2.2198 (2.1999)	loss 4.6941 (3.8861)	grad_norm 1.1921 (1.1467)	
[2022-01-19 09:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][960/1251]	eta 0:10:39 lr 0.000912	time 1.7514 (2.1978)	loss 2.6753 (3.8864)	grad_norm 1.0142 (1.1459)	
[2022-01-19 09:03:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][970/1251]	eta 0:10:17 lr 0.000912	time 2.6717 (2.1973)	loss 3.8962 (3.8886)	grad_norm 1.1822 (1.1455)	
[2022-01-19 09:03:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][980/1251]	eta 0:09:55 lr 0.000912	time 2.2445 (2.1981)	loss 4.2372 (3.8915)	grad_norm 1.2418 (1.1451)	
[2022-01-19 09:03:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][990/1251]	eta 0:09:34 lr 0.000912	time 2.5713 (2.2003)	loss 3.5681 (3.8914)	grad_norm 1.0076 (1.1448)	
[2022-01-19 09:04:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1000/1251]	eta 0:09:12 lr 0.000912	time 2.5183 (2.2012)	loss 3.6413 (3.8918)	grad_norm 1.2595 (1.1447)	
[2022-01-19 09:04:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1010/1251]	eta 0:08:50 lr 0.000912	time 1.5866 (2.2007)	loss 3.6851 (3.8926)	grad_norm 1.0236 (1.1449)	
[2022-01-19 09:05:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1020/1251]	eta 0:08:28 lr 0.000912	time 1.8833 (2.1999)	loss 3.2356 (3.8910)	grad_norm 1.0700 (1.1444)	
[2022-01-19 09:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1030/1251]	eta 0:08:06 lr 0.000912	time 3.0782 (2.2006)	loss 2.7865 (3.8906)	grad_norm 1.1869 (1.1441)	
[2022-01-19 09:05:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1040/1251]	eta 0:07:44 lr 0.000912	time 2.4144 (2.2006)	loss 4.0227 (3.8910)	grad_norm 1.1219 (1.1444)	
[2022-01-19 09:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1050/1251]	eta 0:07:22 lr 0.000912	time 1.6812 (2.1995)	loss 3.8016 (3.8885)	grad_norm 1.1790 (1.1442)	
[2022-01-19 09:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1060/1251]	eta 0:06:59 lr 0.000912	time 1.9668 (2.1977)	loss 2.7565 (3.8860)	grad_norm 1.1012 (1.1439)	
[2022-01-19 09:06:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1070/1251]	eta 0:06:37 lr 0.000912	time 2.2027 (2.1962)	loss 3.4887 (3.8863)	grad_norm 1.2185 (1.1433)	
[2022-01-19 09:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1080/1251]	eta 0:06:15 lr 0.000912	time 2.4995 (2.1952)	loss 4.0278 (3.8881)	grad_norm 1.1771 (1.1442)	
[2022-01-19 09:07:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1090/1251]	eta 0:05:53 lr 0.000912	time 1.7034 (2.1937)	loss 3.6230 (3.8884)	grad_norm 1.0583 (1.1438)	
[2022-01-19 09:07:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1100/1251]	eta 0:05:31 lr 0.000912	time 2.1732 (2.1930)	loss 4.2724 (3.8881)	grad_norm 0.9678 (1.1446)	
[2022-01-19 09:08:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1110/1251]	eta 0:05:09 lr 0.000912	time 3.0363 (2.1938)	loss 4.3931 (3.8888)	grad_norm 0.9743 (1.1450)	
[2022-01-19 09:08:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1120/1251]	eta 0:04:47 lr 0.000912	time 2.2151 (2.1938)	loss 3.0459 (3.8862)	grad_norm 1.1389 (1.1444)	
[2022-01-19 09:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1130/1251]	eta 0:04:25 lr 0.000912	time 2.0268 (2.1934)	loss 4.3847 (3.8851)	grad_norm 1.0775 (1.1444)	
[2022-01-19 09:09:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1140/1251]	eta 0:04:03 lr 0.000912	time 1.8640 (2.1931)	loss 4.0545 (3.8864)	grad_norm 0.9529 (1.1444)	
[2022-01-19 09:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1150/1251]	eta 0:03:41 lr 0.000912	time 2.9262 (2.1958)	loss 4.5575 (3.8880)	grad_norm 1.1133 (1.1442)	
[2022-01-19 09:10:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1160/1251]	eta 0:03:19 lr 0.000912	time 2.2842 (2.1959)	loss 4.6670 (3.8883)	grad_norm 1.1750 (1.1438)	
[2022-01-19 09:10:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1170/1251]	eta 0:02:57 lr 0.000912	time 1.9381 (2.1961)	loss 4.1882 (3.8877)	grad_norm 1.0218 (1.1439)	
[2022-01-19 09:10:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1180/1251]	eta 0:02:35 lr 0.000912	time 1.7671 (2.1955)	loss 3.2965 (3.8857)	grad_norm 1.1314 (1.1442)	
[2022-01-19 09:11:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1190/1251]	eta 0:02:13 lr 0.000912	time 1.9131 (2.1963)	loss 4.0132 (3.8851)	grad_norm 1.1199 (1.1447)	
[2022-01-19 09:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1200/1251]	eta 0:01:51 lr 0.000912	time 1.8715 (2.1950)	loss 4.3878 (3.8851)	grad_norm 1.2186 (1.1449)	
[2022-01-19 09:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1210/1251]	eta 0:01:29 lr 0.000912	time 2.4967 (2.1939)	loss 3.6943 (3.8819)	grad_norm 1.0697 (1.1446)	
[2022-01-19 09:12:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1220/1251]	eta 0:01:07 lr 0.000912	time 1.8952 (2.1925)	loss 3.8531 (3.8799)	grad_norm 0.9368 (1.1438)	
[2022-01-19 09:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1230/1251]	eta 0:00:46 lr 0.000912	time 1.5835 (2.1908)	loss 4.2239 (3.8790)	grad_norm 1.1537 (1.1433)	
[2022-01-19 09:12:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1240/1251]	eta 0:00:24 lr 0.000911	time 2.1770 (2.1898)	loss 4.4656 (3.8797)	grad_norm 1.3801 (1.1430)	
[2022-01-19 09:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [57/300][1250/1251]	eta 0:00:02 lr 0.000911	time 1.1801 (2.1854)	loss 3.7317 (3.8792)	grad_norm 1.1252 (1.1427)	
[2022-01-19 09:13:11 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 57 training takes 0:45:34
[2022-01-19 09:13:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.925 (17.925)	Loss 1.3115 (1.3115)	Acc@1 70.996 (70.996)	Acc@5 89.551 (89.551)	
[2022-01-19 09:13:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.714 (3.616)	Loss 1.2814 (1.2449)	Acc@1 70.996 (71.040)	Acc@5 89.941 (90.749)	
[2022-01-19 09:14:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.303 (2.651)	Loss 1.2653 (1.2399)	Acc@1 70.117 (71.084)	Acc@5 90.723 (90.802)	
[2022-01-19 09:14:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.648 (2.453)	Loss 1.2061 (1.2470)	Acc@1 70.703 (70.930)	Acc@5 91.602 (90.723)	
[2022-01-19 09:14:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.935 (2.217)	Loss 1.2525 (1.2440)	Acc@1 71.387 (71.025)	Acc@5 91.211 (90.727)	
[2022-01-19 09:14:49 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 70.946 Acc@5 90.730
[2022-01-19 09:14:49 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 70.9%
[2022-01-19 09:14:49 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 70.95%
[2022-01-19 09:15:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][0/1251]	eta 7:33:44 lr 0.000911	time 21.7619 (21.7619)	loss 4.1608 (4.1608)	grad_norm 1.0070 (1.0070)	
[2022-01-19 09:15:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][10/1251]	eta 1:25:40 lr 0.000911	time 2.8271 (4.1421)	loss 3.8331 (3.5847)	grad_norm 1.0821 (1.1501)	
[2022-01-19 09:15:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][20/1251]	eta 1:06:52 lr 0.000911	time 1.5076 (3.2593)	loss 3.2998 (3.6878)	grad_norm 1.1279 (1.1162)	
[2022-01-19 09:16:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][30/1251]	eta 0:59:10 lr 0.000911	time 1.8348 (2.9075)	loss 2.5559 (3.6745)	grad_norm 1.2693 (1.1133)	
[2022-01-19 09:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][40/1251]	eta 0:55:26 lr 0.000911	time 3.3606 (2.7465)	loss 3.0240 (3.7046)	grad_norm 1.2405 (1.1188)	
[2022-01-19 09:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][50/1251]	eta 0:53:05 lr 0.000911	time 2.9861 (2.6524)	loss 4.0849 (3.7079)	grad_norm 1.0510 (1.1100)	
[2022-01-19 09:17:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][60/1251]	eta 0:51:26 lr 0.000911	time 1.6814 (2.5916)	loss 2.8578 (3.6958)	grad_norm 1.1979 (1.1087)	
[2022-01-19 09:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][70/1251]	eta 0:49:50 lr 0.000911	time 1.8938 (2.5326)	loss 3.9902 (3.7183)	grad_norm 1.0034 (1.1184)	
[2022-01-19 09:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][80/1251]	eta 0:48:26 lr 0.000911	time 2.9086 (2.4818)	loss 4.4549 (3.7801)	grad_norm 1.1397 (1.1162)	
[2022-01-19 09:18:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][90/1251]	eta 0:47:14 lr 0.000911	time 2.0847 (2.4418)	loss 4.7638 (3.8268)	grad_norm 1.2557 (1.1266)	
[2022-01-19 09:18:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][100/1251]	eta 0:45:55 lr 0.000911	time 2.1917 (2.3943)	loss 4.5794 (3.8307)	grad_norm 1.0924 (1.1250)	
[2022-01-19 09:19:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][110/1251]	eta 0:45:19 lr 0.000911	time 2.1628 (2.3832)	loss 4.1607 (3.8240)	grad_norm 0.9492 (1.1195)	
[2022-01-19 09:19:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][120/1251]	eta 0:44:41 lr 0.000911	time 2.6953 (2.3713)	loss 2.9100 (3.8089)	grad_norm 1.4864 (1.1205)	
[2022-01-19 09:19:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][130/1251]	eta 0:44:08 lr 0.000911	time 2.1623 (2.3623)	loss 3.4834 (3.8173)	grad_norm 1.2845 (1.1244)	
[2022-01-19 09:20:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][140/1251]	eta 0:43:24 lr 0.000911	time 1.9183 (2.3440)	loss 4.5267 (3.8294)	grad_norm 1.2019 (1.1288)	
[2022-01-19 09:20:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][150/1251]	eta 0:43:04 lr 0.000911	time 1.9348 (2.3471)	loss 3.8864 (3.8449)	grad_norm 0.9875 (1.1301)	
[2022-01-19 09:21:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][160/1251]	eta 0:42:38 lr 0.000911	time 2.8251 (2.3449)	loss 4.6012 (3.8533)	grad_norm 1.2967 (1.1338)	
[2022-01-19 09:21:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][170/1251]	eta 0:41:59 lr 0.000911	time 1.8882 (2.3303)	loss 4.2527 (3.8654)	grad_norm 1.3315 (1.1351)	
[2022-01-19 09:21:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][180/1251]	eta 0:41:11 lr 0.000911	time 1.6862 (2.3081)	loss 3.3387 (3.8664)	grad_norm 1.1284 (1.1362)	
[2022-01-19 09:22:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][190/1251]	eta 0:40:39 lr 0.000911	time 2.7456 (2.2995)	loss 3.3810 (3.8658)	grad_norm 1.1628 (1.1379)	
[2022-01-19 09:22:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][200/1251]	eta 0:40:10 lr 0.000911	time 2.4836 (2.2936)	loss 3.5792 (3.8634)	grad_norm 1.1121 (1.1379)	
[2022-01-19 09:22:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][210/1251]	eta 0:39:34 lr 0.000911	time 1.8711 (2.2814)	loss 4.3634 (3.8649)	grad_norm 1.0544 (1.1364)	
[2022-01-19 09:23:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][220/1251]	eta 0:39:04 lr 0.000911	time 1.8819 (2.2742)	loss 3.6481 (3.8570)	grad_norm 1.0251 (1.1390)	
[2022-01-19 09:23:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][230/1251]	eta 0:38:42 lr 0.000911	time 3.4813 (2.2750)	loss 4.6168 (3.8455)	grad_norm 1.1352 (1.1402)	
[2022-01-19 09:23:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][240/1251]	eta 0:38:14 lr 0.000911	time 2.2267 (2.2699)	loss 2.9632 (3.8457)	grad_norm 1.2632 (1.1430)	
[2022-01-19 09:24:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][250/1251]	eta 0:37:49 lr 0.000911	time 1.8462 (2.2671)	loss 4.5754 (3.8359)	grad_norm 1.2591 (1.1456)	
[2022-01-19 09:24:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][260/1251]	eta 0:37:28 lr 0.000911	time 1.6842 (2.2692)	loss 3.9323 (3.8427)	grad_norm 1.3171 (1.1467)	
[2022-01-19 09:25:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][270/1251]	eta 0:37:08 lr 0.000911	time 2.7567 (2.2712)	loss 3.5522 (3.8423)	grad_norm 1.1251 (1.1461)	
[2022-01-19 09:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][280/1251]	eta 0:36:41 lr 0.000911	time 2.4227 (2.2670)	loss 4.5831 (3.8450)	grad_norm 1.2767 (1.1486)	
[2022-01-19 09:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][290/1251]	eta 0:36:16 lr 0.000911	time 1.9191 (2.2649)	loss 2.7270 (3.8458)	grad_norm 1.2554 (1.1511)	
[2022-01-19 09:26:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][300/1251]	eta 0:35:49 lr 0.000911	time 1.9266 (2.2607)	loss 4.3372 (3.8490)	grad_norm 0.9955 (1.1498)	
[2022-01-19 09:26:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][310/1251]	eta 0:35:22 lr 0.000911	time 2.5604 (2.2555)	loss 3.5684 (3.8488)	grad_norm 1.3076 (1.1491)	
[2022-01-19 09:26:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][320/1251]	eta 0:34:58 lr 0.000911	time 1.7962 (2.2535)	loss 3.7919 (3.8494)	grad_norm 1.3945 (1.1512)	
[2022-01-19 09:27:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][330/1251]	eta 0:34:34 lr 0.000911	time 1.8763 (2.2524)	loss 3.9771 (3.8579)	grad_norm 1.2005 (1.1509)	
[2022-01-19 09:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][340/1251]	eta 0:34:11 lr 0.000911	time 2.4957 (2.2521)	loss 3.4050 (3.8648)	grad_norm 0.9264 (1.1506)	
[2022-01-19 09:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][350/1251]	eta 0:33:46 lr 0.000911	time 2.4457 (2.2493)	loss 4.3320 (3.8677)	grad_norm 1.2870 (1.1485)	
[2022-01-19 09:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][360/1251]	eta 0:33:20 lr 0.000911	time 1.6160 (2.2456)	loss 2.9545 (3.8724)	grad_norm 1.0030 (1.1507)	
[2022-01-19 09:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][370/1251]	eta 0:32:56 lr 0.000911	time 1.9343 (2.2437)	loss 4.2218 (3.8696)	grad_norm 1.0867 (1.1506)	
[2022-01-19 09:29:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][380/1251]	eta 0:32:37 lr 0.000911	time 3.1061 (2.2470)	loss 3.7273 (3.8698)	grad_norm 0.9985 (1.1498)	
[2022-01-19 09:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][390/1251]	eta 0:32:14 lr 0.000911	time 2.2467 (2.2472)	loss 4.3182 (3.8715)	grad_norm 1.1692 (1.1499)	
[2022-01-19 09:29:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][400/1251]	eta 0:31:47 lr 0.000911	time 1.9953 (2.2420)	loss 3.7716 (3.8730)	grad_norm 1.1295 (1.1501)	
[2022-01-19 09:30:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][410/1251]	eta 0:31:22 lr 0.000910	time 1.9381 (2.2384)	loss 4.4588 (3.8741)	grad_norm 1.1585 (1.1493)	
[2022-01-19 09:30:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][420/1251]	eta 0:30:56 lr 0.000910	time 2.4430 (2.2346)	loss 3.0227 (3.8749)	grad_norm 1.1502 (1.1506)	
[2022-01-19 09:30:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][430/1251]	eta 0:30:33 lr 0.000910	time 1.9002 (2.2327)	loss 4.5817 (3.8850)	grad_norm 1.0876 (1.1500)	
[2022-01-19 09:31:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][440/1251]	eta 0:30:09 lr 0.000910	time 1.9564 (2.2314)	loss 4.0560 (3.8890)	grad_norm 1.1414 (1.1494)	
[2022-01-19 09:31:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][450/1251]	eta 0:29:47 lr 0.000910	time 2.7346 (2.2313)	loss 3.3170 (3.8884)	grad_norm 1.0136 (1.1471)	
[2022-01-19 09:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][460/1251]	eta 0:29:25 lr 0.000910	time 2.5834 (2.2321)	loss 4.7906 (3.8845)	grad_norm 1.2659 (1.1458)	
[2022-01-19 09:32:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][470/1251]	eta 0:29:04 lr 0.000910	time 2.1336 (2.2334)	loss 3.7943 (3.8846)	grad_norm 1.1112 (1.1439)	
[2022-01-19 09:32:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][480/1251]	eta 0:28:42 lr 0.000910	time 2.3954 (2.2345)	loss 4.6954 (3.8903)	grad_norm 1.1788 (1.1439)	
[2022-01-19 09:33:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][490/1251]	eta 0:28:21 lr 0.000910	time 2.2275 (2.2353)	loss 3.7326 (3.8885)	grad_norm 1.1083 (1.1441)	
[2022-01-19 09:33:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][500/1251]	eta 0:27:56 lr 0.000910	time 2.3837 (2.2323)	loss 2.8388 (3.8829)	grad_norm 1.0401 (1.1452)	
[2022-01-19 09:33:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][510/1251]	eta 0:27:29 lr 0.000910	time 1.9159 (2.2259)	loss 4.6927 (3.8894)	grad_norm 1.1720 (1.1444)	
[2022-01-19 09:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][520/1251]	eta 0:27:03 lr 0.000910	time 1.5831 (2.2207)	loss 4.5337 (3.8900)	grad_norm 1.1870 (1.1443)	
[2022-01-19 09:34:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][530/1251]	eta 0:26:39 lr 0.000910	time 2.1795 (2.2188)	loss 3.0449 (3.8906)	grad_norm 1.1955 (1.1441)	
[2022-01-19 09:34:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][540/1251]	eta 0:26:18 lr 0.000910	time 2.6100 (2.2195)	loss 4.6222 (3.8958)	grad_norm 1.0445 (1.1430)	
[2022-01-19 09:35:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][550/1251]	eta 0:25:54 lr 0.000910	time 1.8905 (2.2178)	loss 3.8920 (3.8918)	grad_norm 1.1200 (1.1427)	
[2022-01-19 09:35:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][560/1251]	eta 0:25:33 lr 0.000910	time 2.5877 (2.2199)	loss 4.4710 (3.8931)	grad_norm 1.2183 (1.1430)	
[2022-01-19 09:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][570/1251]	eta 0:25:13 lr 0.000910	time 2.4234 (2.2222)	loss 4.3963 (3.8967)	grad_norm 2.4072 (1.1465)	
[2022-01-19 09:36:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][580/1251]	eta 0:24:52 lr 0.000910	time 2.4824 (2.2248)	loss 4.2555 (3.9029)	grad_norm 1.1080 (1.1497)	
[2022-01-19 09:36:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][590/1251]	eta 0:24:30 lr 0.000910	time 1.9145 (2.2249)	loss 3.4615 (3.8987)	grad_norm 1.2468 (1.1501)	
[2022-01-19 09:37:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][600/1251]	eta 0:24:07 lr 0.000910	time 2.4867 (2.2242)	loss 4.4761 (3.9017)	grad_norm 1.0345 (1.1517)	
[2022-01-19 09:37:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][610/1251]	eta 0:23:44 lr 0.000910	time 2.0080 (2.2227)	loss 4.4886 (3.9016)	grad_norm 0.9501 (1.1516)	
[2022-01-19 09:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][620/1251]	eta 0:23:21 lr 0.000910	time 2.0951 (2.2204)	loss 4.0809 (3.9023)	grad_norm 1.1385 (1.1506)	
[2022-01-19 09:38:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][630/1251]	eta 0:22:57 lr 0.000910	time 1.8971 (2.2178)	loss 4.5085 (3.9007)	grad_norm 1.2363 (1.1498)	
[2022-01-19 09:38:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][640/1251]	eta 0:22:34 lr 0.000910	time 2.2007 (2.2174)	loss 3.8609 (3.9044)	grad_norm 1.0865 (1.1477)	
[2022-01-19 09:38:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][650/1251]	eta 0:22:13 lr 0.000910	time 2.4779 (2.2193)	loss 2.7922 (3.9069)	grad_norm 1.1583 (1.1472)	
[2022-01-19 09:39:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][660/1251]	eta 0:21:50 lr 0.000910	time 1.6763 (2.2175)	loss 4.3840 (3.9083)	grad_norm 0.9704 (1.1467)	
[2022-01-19 09:39:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][670/1251]	eta 0:21:28 lr 0.000910	time 1.9041 (2.2176)	loss 3.9926 (3.9099)	grad_norm 1.0560 (1.1471)	
[2022-01-19 09:39:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][680/1251]	eta 0:21:05 lr 0.000910	time 1.8849 (2.2163)	loss 4.4770 (3.9092)	grad_norm 1.0685 (1.1467)	
[2022-01-19 09:40:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][690/1251]	eta 0:20:44 lr 0.000910	time 2.6466 (2.2181)	loss 3.2830 (3.9062)	grad_norm 1.0220 (1.1465)	
[2022-01-19 09:40:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][700/1251]	eta 0:20:21 lr 0.000910	time 2.1094 (2.2164)	loss 4.0909 (3.9071)	grad_norm 1.0880 (1.1453)	
[2022-01-19 09:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][710/1251]	eta 0:19:58 lr 0.000910	time 1.8894 (2.2147)	loss 4.3474 (3.9089)	grad_norm 0.9173 (1.1454)	
[2022-01-19 09:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][720/1251]	eta 0:19:35 lr 0.000910	time 1.5299 (2.2140)	loss 2.8687 (3.9100)	grad_norm 1.3181 (1.1453)	
[2022-01-19 09:41:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][730/1251]	eta 0:19:13 lr 0.000910	time 1.7997 (2.2147)	loss 4.4932 (3.9111)	grad_norm 0.9229 (1.1453)	
[2022-01-19 09:42:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][740/1251]	eta 0:18:51 lr 0.000910	time 1.5935 (2.2137)	loss 3.3485 (3.9099)	grad_norm 0.9435 (1.1438)	
[2022-01-19 09:42:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][750/1251]	eta 0:18:29 lr 0.000910	time 2.0501 (2.2136)	loss 3.8123 (3.9111)	grad_norm 1.0869 (1.1437)	
[2022-01-19 09:42:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][760/1251]	eta 0:18:06 lr 0.000910	time 1.8525 (2.2124)	loss 4.3182 (3.9090)	grad_norm 1.3743 (1.1439)	
[2022-01-19 09:43:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][770/1251]	eta 0:17:43 lr 0.000910	time 1.8661 (2.2117)	loss 4.0142 (3.9083)	grad_norm 1.4116 (1.1440)	
[2022-01-19 09:43:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][780/1251]	eta 0:17:22 lr 0.000910	time 1.8704 (2.2127)	loss 4.3221 (3.9067)	grad_norm 1.0643 (1.1454)	
[2022-01-19 09:44:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][790/1251]	eta 0:17:00 lr 0.000910	time 2.5166 (2.2136)	loss 4.3413 (3.9075)	grad_norm 1.0085 (1.1452)	
[2022-01-19 09:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][800/1251]	eta 0:16:37 lr 0.000910	time 1.5719 (2.2128)	loss 2.7926 (3.9083)	grad_norm 0.9481 (1.1451)	
[2022-01-19 09:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][810/1251]	eta 0:16:15 lr 0.000910	time 1.8462 (2.2123)	loss 2.9986 (3.9079)	grad_norm 1.1911 (1.1454)	
[2022-01-19 09:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][820/1251]	eta 0:15:53 lr 0.000910	time 2.2400 (2.2121)	loss 3.8776 (3.9088)	grad_norm 1.0796 (1.1454)	
[2022-01-19 09:45:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][830/1251]	eta 0:15:31 lr 0.000909	time 1.5819 (2.2121)	loss 4.4066 (3.9093)	grad_norm 1.1002 (1.1458)	
[2022-01-19 09:45:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][840/1251]	eta 0:15:08 lr 0.000909	time 2.1735 (2.2099)	loss 3.7435 (3.9108)	grad_norm 1.1456 (1.1451)	
[2022-01-19 09:46:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][850/1251]	eta 0:14:45 lr 0.000909	time 1.9053 (2.2087)	loss 4.4838 (3.9081)	grad_norm 1.2635 (1.1445)	
[2022-01-19 09:46:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][860/1251]	eta 0:14:23 lr 0.000909	time 2.1016 (2.2080)	loss 3.8647 (3.9086)	grad_norm 1.0706 (1.1445)	
[2022-01-19 09:46:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][870/1251]	eta 0:14:00 lr 0.000909	time 2.0520 (2.2073)	loss 4.0757 (3.9072)	grad_norm 1.1621 (1.1447)	
[2022-01-19 09:47:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][880/1251]	eta 0:13:38 lr 0.000909	time 2.1278 (2.2058)	loss 4.0877 (3.9082)	grad_norm 0.9845 (1.1442)	
[2022-01-19 09:47:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][890/1251]	eta 0:13:17 lr 0.000909	time 2.4199 (2.2080)	loss 4.5580 (3.9067)	grad_norm 0.9741 (1.1431)	
[2022-01-19 09:48:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][900/1251]	eta 0:12:55 lr 0.000909	time 1.7763 (2.2100)	loss 3.8314 (3.9061)	grad_norm 0.9545 (1.1431)	
[2022-01-19 09:48:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][910/1251]	eta 0:12:33 lr 0.000909	time 1.9165 (2.2104)	loss 3.5847 (3.9034)	grad_norm 1.0175 (1.1432)	
[2022-01-19 09:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][920/1251]	eta 0:12:10 lr 0.000909	time 2.4200 (2.2082)	loss 4.0645 (3.9053)	grad_norm 1.1408 (1.1433)	
[2022-01-19 09:49:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][930/1251]	eta 0:11:48 lr 0.000909	time 2.0302 (2.2085)	loss 4.1129 (3.9070)	grad_norm 1.1615 (1.1440)	
[2022-01-19 09:49:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][940/1251]	eta 0:11:27 lr 0.000909	time 1.7881 (2.2092)	loss 4.2123 (3.9079)	grad_norm 1.1946 (1.1456)	
[2022-01-19 09:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][950/1251]	eta 0:11:04 lr 0.000909	time 2.2170 (2.2077)	loss 4.0400 (3.9060)	grad_norm 1.1610 (1.1461)	
[2022-01-19 09:50:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][960/1251]	eta 0:10:42 lr 0.000909	time 1.7398 (2.2071)	loss 4.4687 (3.9047)	grad_norm 1.1794 (1.1462)	
[2022-01-19 09:50:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][970/1251]	eta 0:10:20 lr 0.000909	time 1.7710 (2.2065)	loss 3.6866 (3.9055)	grad_norm 1.2485 (1.1465)	
[2022-01-19 09:50:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][980/1251]	eta 0:09:58 lr 0.000909	time 1.8252 (2.2082)	loss 4.3485 (3.9058)	grad_norm 1.1384 (1.1456)	
[2022-01-19 09:51:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][990/1251]	eta 0:09:36 lr 0.000909	time 1.8343 (2.2078)	loss 4.0869 (3.9046)	grad_norm 1.1304 (1.1456)	
[2022-01-19 09:51:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1000/1251]	eta 0:09:13 lr 0.000909	time 1.9435 (2.2063)	loss 3.7142 (3.9024)	grad_norm 1.0321 (1.1468)	
[2022-01-19 09:52:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1010/1251]	eta 0:08:51 lr 0.000909	time 2.7469 (2.2063)	loss 4.6196 (3.9028)	grad_norm 1.6214 (1.1478)	
[2022-01-19 09:52:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1020/1251]	eta 0:08:29 lr 0.000909	time 2.1428 (2.2051)	loss 2.7517 (3.9035)	grad_norm 1.2062 (1.1479)	
[2022-01-19 09:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1030/1251]	eta 0:08:07 lr 0.000909	time 2.1058 (2.2048)	loss 4.3532 (3.9026)	grad_norm 1.2992 (1.1473)	
[2022-01-19 09:53:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1040/1251]	eta 0:07:45 lr 0.000909	time 2.0682 (2.2043)	loss 2.8954 (3.9010)	grad_norm 1.2656 (1.1467)	
[2022-01-19 09:53:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1050/1251]	eta 0:07:23 lr 0.000909	time 2.2040 (2.2045)	loss 4.6533 (3.9033)	grad_norm 1.1564 (1.1465)	
[2022-01-19 09:53:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1060/1251]	eta 0:07:00 lr 0.000909	time 2.2133 (2.2039)	loss 4.1713 (3.9026)	grad_norm 1.2898 (1.1460)	
[2022-01-19 09:54:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1070/1251]	eta 0:06:39 lr 0.000909	time 2.2771 (2.2091)	loss 3.7812 (3.9037)	grad_norm 1.0842 (1.1452)	
[2022-01-19 09:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1080/1251]	eta 0:06:17 lr 0.000909	time 2.5511 (2.2101)	loss 3.9327 (3.9045)	grad_norm 1.0401 (1.1444)	
[2022-01-19 09:54:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1090/1251]	eta 0:05:55 lr 0.000909	time 1.8941 (2.2093)	loss 3.3340 (3.9030)	grad_norm 1.0596 (1.1446)	
[2022-01-19 09:55:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1100/1251]	eta 0:05:33 lr 0.000909	time 1.5354 (2.2078)	loss 3.9748 (3.9015)	grad_norm 1.0045 (1.1439)	
[2022-01-19 09:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1110/1251]	eta 0:05:11 lr 0.000909	time 1.6462 (2.2080)	loss 4.1328 (3.9010)	grad_norm 1.0132 (1.1432)	
[2022-01-19 09:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1120/1251]	eta 0:04:49 lr 0.000909	time 1.8535 (2.2067)	loss 4.6515 (3.9029)	grad_norm 1.1814 (1.1431)	
[2022-01-19 09:56:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1130/1251]	eta 0:04:26 lr 0.000909	time 2.3273 (2.2059)	loss 4.1817 (3.9014)	grad_norm 1.1794 (1.1431)	
[2022-01-19 09:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1140/1251]	eta 0:04:04 lr 0.000909	time 1.6804 (2.2065)	loss 4.4012 (3.8996)	grad_norm 1.0852 (1.1429)	
[2022-01-19 09:57:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1150/1251]	eta 0:03:42 lr 0.000909	time 1.8636 (2.2076)	loss 4.1391 (3.8976)	grad_norm 1.0853 (1.1430)	
[2022-01-19 09:57:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1160/1251]	eta 0:03:20 lr 0.000909	time 1.7808 (2.2076)	loss 4.5226 (3.8953)	grad_norm 1.1448 (1.1429)	
[2022-01-19 09:57:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1170/1251]	eta 0:02:58 lr 0.000909	time 1.8018 (2.2067)	loss 4.2666 (3.8954)	grad_norm 1.3067 (1.1430)	
[2022-01-19 09:58:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1180/1251]	eta 0:02:36 lr 0.000909	time 1.8977 (2.2058)	loss 4.4978 (3.8976)	grad_norm 1.1634 (1.1429)	
[2022-01-19 09:58:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1190/1251]	eta 0:02:14 lr 0.000909	time 1.8416 (2.2049)	loss 3.9766 (3.8974)	grad_norm 1.1904 (1.1432)	
[2022-01-19 09:58:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1200/1251]	eta 0:01:52 lr 0.000909	time 1.9258 (2.2041)	loss 3.9927 (3.8962)	grad_norm 1.0334 (1.1426)	
[2022-01-19 09:59:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1210/1251]	eta 0:01:30 lr 0.000909	time 1.8295 (2.2038)	loss 2.8226 (3.8953)	grad_norm 1.0751 (1.1429)	
[2022-01-19 09:59:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1220/1251]	eta 0:01:08 lr 0.000909	time 2.5091 (2.2046)	loss 3.1691 (3.8947)	grad_norm 1.1238 (1.1422)	
[2022-01-19 10:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1230/1251]	eta 0:00:46 lr 0.000909	time 1.9251 (2.2058)	loss 4.0502 (3.8944)	grad_norm 1.1548 (1.1423)	
[2022-01-19 10:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1240/1251]	eta 0:00:24 lr 0.000909	time 1.3948 (2.2051)	loss 4.1855 (3.8957)	grad_norm 1.2328 (1.1432)	
[2022-01-19 10:00:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [58/300][1250/1251]	eta 0:00:02 lr 0.000908	time 1.1875 (2.2002)	loss 2.7813 (3.8949)	grad_norm 1.0685 (1.1432)	
[2022-01-19 10:00:42 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 58 training takes 0:45:52
[2022-01-19 10:01:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.693 (18.693)	Loss 1.1635 (1.1635)	Acc@1 74.316 (74.316)	Acc@5 91.699 (91.699)	
[2022-01-19 10:01:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.637 (3.524)	Loss 1.1708 (1.2402)	Acc@1 73.145 (71.467)	Acc@5 91.309 (90.439)	
[2022-01-19 10:01:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.627 (2.661)	Loss 1.1963 (1.2358)	Acc@1 72.949 (71.475)	Acc@5 90.527 (90.630)	
[2022-01-19 10:01:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.631 (2.281)	Loss 1.2064 (1.2494)	Acc@1 71.680 (71.160)	Acc@5 91.406 (90.420)	
[2022-01-19 10:02:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.149 (2.229)	Loss 1.2420 (1.2445)	Acc@1 71.582 (71.313)	Acc@5 90.625 (90.573)	
[2022-01-19 10:02:20 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 71.278 Acc@5 90.550
[2022-01-19 10:02:20 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 71.3%
[2022-01-19 10:02:20 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 71.28%
[2022-01-19 10:02:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][0/1251]	eta 7:28:19 lr 0.000908	time 21.5021 (21.5021)	loss 4.3581 (4.3581)	grad_norm 1.0111 (1.0111)	
[2022-01-19 10:03:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][10/1251]	eta 1:22:01 lr 0.000908	time 1.8745 (3.9658)	loss 3.9637 (3.9840)	grad_norm 1.2828 (1.1227)	
[2022-01-19 10:03:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][20/1251]	eta 1:05:01 lr 0.000908	time 2.1711 (3.1694)	loss 4.1705 (3.8294)	grad_norm 1.0677 (1.1175)	
[2022-01-19 10:03:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][30/1251]	eta 0:58:15 lr 0.000908	time 1.8724 (2.8626)	loss 4.5448 (3.8917)	grad_norm 1.1575 (1.1119)	
[2022-01-19 10:04:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][40/1251]	eta 0:54:48 lr 0.000908	time 3.8798 (2.7156)	loss 4.0070 (3.9105)	grad_norm 0.8956 (1.1054)	
[2022-01-19 10:04:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][50/1251]	eta 0:52:39 lr 0.000908	time 2.2625 (2.6310)	loss 3.9609 (3.8804)	grad_norm 1.0194 (1.1064)	
[2022-01-19 10:04:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][60/1251]	eta 0:50:42 lr 0.000908	time 1.7197 (2.5548)	loss 2.6673 (3.8801)	grad_norm 1.0401 (1.1107)	
[2022-01-19 10:05:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][70/1251]	eta 0:49:37 lr 0.000908	time 2.0510 (2.5209)	loss 4.2199 (3.8491)	grad_norm 1.0751 (1.1120)	
[2022-01-19 10:05:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][80/1251]	eta 0:48:26 lr 0.000908	time 3.3393 (2.4824)	loss 4.8561 (3.8275)	grad_norm 1.0906 (1.1185)	
[2022-01-19 10:06:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][90/1251]	eta 0:47:39 lr 0.000908	time 2.1125 (2.4630)	loss 3.4299 (3.8235)	grad_norm 1.0406 (1.1173)	
[2022-01-19 10:06:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][100/1251]	eta 0:46:28 lr 0.000908	time 1.8915 (2.4228)	loss 3.3973 (3.8367)	grad_norm 0.9469 (1.1162)	
[2022-01-19 10:06:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][110/1251]	eta 0:45:23 lr 0.000908	time 1.7084 (2.3866)	loss 4.3779 (3.8688)	grad_norm 0.9534 (1.1143)	
[2022-01-19 10:07:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][120/1251]	eta 0:44:39 lr 0.000908	time 2.2128 (2.3688)	loss 4.5863 (3.8737)	grad_norm 1.1677 (1.1089)	
[2022-01-19 10:07:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][130/1251]	eta 0:44:09 lr 0.000908	time 2.1041 (2.3634)	loss 4.0917 (3.8415)	grad_norm 1.2964 (1.1088)	
[2022-01-19 10:07:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][140/1251]	eta 0:43:28 lr 0.000908	time 2.2349 (2.3481)	loss 2.6270 (3.8295)	grad_norm 1.3741 (1.1126)	
[2022-01-19 10:08:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][150/1251]	eta 0:42:48 lr 0.000908	time 1.9724 (2.3326)	loss 4.2674 (3.8198)	grad_norm 1.1835 (1.1218)	
[2022-01-19 10:08:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][160/1251]	eta 0:42:21 lr 0.000908	time 2.6207 (2.3297)	loss 3.9763 (3.8372)	grad_norm 1.0802 (1.1247)	
[2022-01-19 10:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][170/1251]	eta 0:41:50 lr 0.000908	time 1.9925 (2.3223)	loss 4.3007 (3.8418)	grad_norm 1.2680 (1.1278)	
[2022-01-19 10:09:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][180/1251]	eta 0:41:21 lr 0.000908	time 3.0512 (2.3167)	loss 3.8684 (3.8449)	grad_norm 1.4570 (1.1311)	
[2022-01-19 10:09:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][190/1251]	eta 0:40:55 lr 0.000908	time 1.8582 (2.3143)	loss 4.2048 (3.8519)	grad_norm 1.0360 (1.1299)	
[2022-01-19 10:10:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][200/1251]	eta 0:40:29 lr 0.000908	time 2.6637 (2.3114)	loss 4.3265 (3.8512)	grad_norm 1.1371 (1.1312)	
[2022-01-19 10:10:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][210/1251]	eta 0:39:58 lr 0.000908	time 1.8653 (2.3038)	loss 3.9449 (3.8554)	grad_norm 0.9825 (1.1319)	
[2022-01-19 10:10:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][220/1251]	eta 0:39:18 lr 0.000908	time 1.8809 (2.2873)	loss 3.8494 (3.8653)	grad_norm 1.2639 (1.1336)	
[2022-01-19 10:11:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][230/1251]	eta 0:38:42 lr 0.000908	time 1.6635 (2.2744)	loss 3.2472 (3.8619)	grad_norm 1.6423 (1.1359)	
[2022-01-19 10:11:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][240/1251]	eta 0:38:06 lr 0.000908	time 2.2020 (2.2620)	loss 3.7510 (3.8643)	grad_norm 1.0650 (1.1374)	
[2022-01-19 10:11:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][250/1251]	eta 0:37:37 lr 0.000908	time 2.5326 (2.2548)	loss 4.4885 (3.8611)	grad_norm 1.2210 (1.1382)	
[2022-01-19 10:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][260/1251]	eta 0:37:10 lr 0.000908	time 1.6538 (2.2507)	loss 3.6523 (3.8569)	grad_norm 1.0944 (1.1395)	
[2022-01-19 10:12:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][270/1251]	eta 0:36:54 lr 0.000908	time 2.1785 (2.2577)	loss 4.1330 (3.8632)	grad_norm 1.1805 (1.1405)	
[2022-01-19 10:12:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][280/1251]	eta 0:36:42 lr 0.000908	time 2.5136 (2.2686)	loss 3.0457 (3.8551)	grad_norm 1.1523 (1.1410)	
[2022-01-19 10:13:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][290/1251]	eta 0:36:20 lr 0.000908	time 1.7813 (2.2692)	loss 3.0244 (3.8532)	grad_norm 1.2175 (1.1419)	
[2022-01-19 10:13:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][300/1251]	eta 0:35:56 lr 0.000908	time 2.1358 (2.2674)	loss 4.2737 (3.8599)	grad_norm 1.1871 (1.1426)	
[2022-01-19 10:14:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][310/1251]	eta 0:35:36 lr 0.000908	time 2.5296 (2.2705)	loss 4.2334 (3.8732)	grad_norm 1.0131 (1.1407)	
[2022-01-19 10:14:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][320/1251]	eta 0:35:08 lr 0.000908	time 1.5763 (2.2649)	loss 4.1191 (3.8787)	grad_norm 1.1227 (1.1389)	
[2022-01-19 10:14:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][330/1251]	eta 0:34:36 lr 0.000908	time 1.5603 (2.2542)	loss 3.9430 (3.8739)	grad_norm 0.9699 (1.1393)	
[2022-01-19 10:15:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][340/1251]	eta 0:34:09 lr 0.000908	time 2.2218 (2.2500)	loss 2.9606 (3.8705)	grad_norm 1.2415 (1.1392)	
[2022-01-19 10:15:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][350/1251]	eta 0:33:39 lr 0.000908	time 1.5741 (2.2413)	loss 3.4927 (3.8733)	grad_norm 1.2938 (1.1394)	
[2022-01-19 10:15:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][360/1251]	eta 0:33:16 lr 0.000908	time 2.8558 (2.2412)	loss 3.9506 (3.8757)	grad_norm 1.3929 (1.1417)	
[2022-01-19 10:16:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][370/1251]	eta 0:32:55 lr 0.000908	time 2.2342 (2.2421)	loss 3.6995 (3.8681)	grad_norm 1.1643 (1.1448)	
[2022-01-19 10:16:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][380/1251]	eta 0:32:35 lr 0.000908	time 2.6063 (2.2455)	loss 4.2376 (3.8671)	grad_norm 1.2829 (1.1451)	
[2022-01-19 10:17:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][390/1251]	eta 0:32:18 lr 0.000908	time 2.0694 (2.2515)	loss 3.6674 (3.8708)	grad_norm 1.2989 (1.1440)	
[2022-01-19 10:17:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][400/1251]	eta 0:31:59 lr 0.000908	time 2.4116 (2.2561)	loss 3.2461 (3.8610)	grad_norm 1.1247 (1.1459)	
[2022-01-19 10:17:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][410/1251]	eta 0:31:36 lr 0.000908	time 2.1478 (2.2555)	loss 4.6246 (3.8551)	grad_norm 1.2531 (1.1445)	
[2022-01-19 10:18:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][420/1251]	eta 0:31:10 lr 0.000907	time 1.8568 (2.2515)	loss 3.0462 (3.8559)	grad_norm 0.9521 (1.1448)	
[2022-01-19 10:18:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][430/1251]	eta 0:30:43 lr 0.000907	time 1.8082 (2.2456)	loss 3.1684 (3.8526)	grad_norm 1.1331 (1.1462)	
[2022-01-19 10:18:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][440/1251]	eta 0:30:14 lr 0.000907	time 1.9165 (2.2370)	loss 3.9464 (3.8569)	grad_norm 1.3421 (1.1474)	
[2022-01-19 10:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][450/1251]	eta 0:29:47 lr 0.000907	time 1.9061 (2.2312)	loss 3.9160 (3.8512)	grad_norm 1.1413 (1.1474)	
[2022-01-19 10:19:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][460/1251]	eta 0:29:22 lr 0.000907	time 2.1699 (2.2277)	loss 4.1150 (3.8579)	grad_norm 1.1066 (1.1470)	
[2022-01-19 10:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][470/1251]	eta 0:29:00 lr 0.000907	time 2.2097 (2.2290)	loss 3.9016 (3.8594)	grad_norm 1.2756 (1.1470)	
[2022-01-19 10:20:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][480/1251]	eta 0:28:40 lr 0.000907	time 2.7325 (2.2313)	loss 4.2880 (3.8587)	grad_norm 1.2592 (1.1458)	
[2022-01-19 10:20:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][490/1251]	eta 0:28:19 lr 0.000907	time 2.5740 (2.2335)	loss 4.0485 (3.8610)	grad_norm 1.1941 (1.1449)	
[2022-01-19 10:20:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][500/1251]	eta 0:27:56 lr 0.000907	time 2.5329 (2.2326)	loss 3.4417 (3.8618)	grad_norm 0.9611 (1.1448)	
[2022-01-19 10:21:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][510/1251]	eta 0:27:37 lr 0.000907	time 2.1750 (2.2368)	loss 4.5951 (3.8629)	grad_norm 1.1485 (1.1448)	
[2022-01-19 10:21:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][520/1251]	eta 0:27:16 lr 0.000907	time 2.9079 (2.2384)	loss 4.1252 (3.8677)	grad_norm 1.1700 (1.1432)	
[2022-01-19 10:22:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][530/1251]	eta 0:26:51 lr 0.000907	time 1.9446 (2.2353)	loss 4.1076 (3.8705)	grad_norm 0.9997 (1.1418)	
[2022-01-19 10:22:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][540/1251]	eta 0:26:26 lr 0.000907	time 2.4850 (2.2313)	loss 4.0737 (3.8705)	grad_norm 1.2846 (1.1450)	
[2022-01-19 10:22:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][550/1251]	eta 0:26:00 lr 0.000907	time 2.0858 (2.2259)	loss 4.2838 (3.8777)	grad_norm 1.0535 (1.1444)	
[2022-01-19 10:23:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][560/1251]	eta 0:25:37 lr 0.000907	time 2.1546 (2.2251)	loss 3.8474 (3.8781)	grad_norm 1.0872 (1.1432)	
[2022-01-19 10:23:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][570/1251]	eta 0:25:16 lr 0.000907	time 2.6053 (2.2263)	loss 4.7178 (3.8770)	grad_norm 1.1575 (1.1437)	
[2022-01-19 10:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][580/1251]	eta 0:24:57 lr 0.000907	time 2.4258 (2.2318)	loss 3.6201 (3.8786)	grad_norm 1.0994 (1.1431)	
[2022-01-19 10:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][590/1251]	eta 0:24:37 lr 0.000907	time 2.1389 (2.2356)	loss 3.3073 (3.8817)	grad_norm 1.1231 (1.1432)	
[2022-01-19 10:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][600/1251]	eta 0:24:14 lr 0.000907	time 2.1712 (2.2347)	loss 4.1964 (3.8795)	grad_norm 1.0281 (1.1439)	
[2022-01-19 10:25:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][610/1251]	eta 0:23:49 lr 0.000907	time 1.5835 (2.2308)	loss 4.1614 (3.8771)	grad_norm 1.1134 (1.1444)	
[2022-01-19 10:25:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][620/1251]	eta 0:23:25 lr 0.000907	time 1.8699 (2.2271)	loss 3.2683 (3.8773)	grad_norm 1.1114 (1.1430)	
[2022-01-19 10:25:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][630/1251]	eta 0:23:02 lr 0.000907	time 1.8473 (2.2263)	loss 3.8686 (3.8754)	grad_norm 1.0880 (1.1426)	
[2022-01-19 10:26:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][640/1251]	eta 0:22:39 lr 0.000907	time 1.5971 (2.2249)	loss 2.9641 (3.8724)	grad_norm 0.9157 (1.1417)	
[2022-01-19 10:26:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][650/1251]	eta 0:22:17 lr 0.000907	time 2.1487 (2.2252)	loss 3.2716 (3.8723)	grad_norm 1.0854 (1.1406)	
[2022-01-19 10:26:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][660/1251]	eta 0:21:55 lr 0.000907	time 2.0906 (2.2264)	loss 4.6076 (3.8779)	grad_norm 1.1635 (1.1415)	
[2022-01-19 10:27:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][670/1251]	eta 0:21:35 lr 0.000907	time 2.8392 (2.2299)	loss 3.6626 (3.8785)	grad_norm 0.9168 (1.1414)	
[2022-01-19 10:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][680/1251]	eta 0:21:14 lr 0.000907	time 2.8336 (2.2325)	loss 4.2930 (3.8775)	grad_norm 1.2770 (1.1416)	
[2022-01-19 10:28:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][690/1251]	eta 0:20:51 lr 0.000907	time 2.2722 (2.2315)	loss 3.2373 (3.8780)	grad_norm 0.9728 (1.1405)	
[2022-01-19 10:28:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][700/1251]	eta 0:20:26 lr 0.000907	time 1.8591 (2.2266)	loss 4.3265 (3.8788)	grad_norm 1.1739 (1.1404)	
[2022-01-19 10:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][710/1251]	eta 0:20:02 lr 0.000907	time 1.9973 (2.2236)	loss 4.3630 (3.8789)	grad_norm 1.2096 (1.1408)	
[2022-01-19 10:29:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][720/1251]	eta 0:19:41 lr 0.000907	time 2.2450 (2.2241)	loss 3.4887 (3.8760)	grad_norm 1.3075 (1.1404)	
[2022-01-19 10:29:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][730/1251]	eta 0:19:19 lr 0.000907	time 2.8973 (2.2250)	loss 2.3685 (3.8772)	grad_norm 1.2026 (1.1409)	
[2022-01-19 10:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][740/1251]	eta 0:18:57 lr 0.000907	time 2.5568 (2.2262)	loss 4.0961 (3.8717)	grad_norm 1.0527 (1.1421)	
[2022-01-19 10:30:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][750/1251]	eta 0:18:35 lr 0.000907	time 2.8189 (2.2270)	loss 4.1397 (3.8740)	grad_norm 1.1478 (1.1431)	
[2022-01-19 10:30:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][760/1251]	eta 0:18:12 lr 0.000907	time 1.8698 (2.2243)	loss 4.7924 (3.8778)	grad_norm 1.1975 (1.1455)	
[2022-01-19 10:30:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][770/1251]	eta 0:17:49 lr 0.000907	time 3.0466 (2.2241)	loss 4.0887 (3.8781)	grad_norm 1.0532 (1.1451)	
[2022-01-19 10:31:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][780/1251]	eta 0:17:27 lr 0.000907	time 2.1188 (2.2231)	loss 4.3954 (3.8772)	grad_norm 1.0518 (1.1447)	
[2022-01-19 10:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][790/1251]	eta 0:17:04 lr 0.000907	time 2.3873 (2.2231)	loss 4.4837 (3.8801)	grad_norm 0.9708 (1.1436)	
[2022-01-19 10:32:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][800/1251]	eta 0:16:42 lr 0.000907	time 2.1414 (2.2226)	loss 3.0435 (3.8832)	grad_norm 0.9733 (1.1431)	
[2022-01-19 10:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][810/1251]	eta 0:16:20 lr 0.000907	time 3.3540 (2.2230)	loss 3.3171 (3.8801)	grad_norm 1.1137 (1.1424)	
[2022-01-19 10:32:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][820/1251]	eta 0:15:57 lr 0.000907	time 1.5510 (2.2222)	loss 3.8062 (3.8782)	grad_norm 1.2258 (1.1420)	
[2022-01-19 10:33:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][830/1251]	eta 0:15:35 lr 0.000906	time 2.2110 (2.2209)	loss 4.1732 (3.8835)	grad_norm 0.9531 (1.1414)	
[2022-01-19 10:33:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][840/1251]	eta 0:15:12 lr 0.000906	time 1.6826 (2.2196)	loss 4.3142 (3.8847)	grad_norm 1.2740 (1.1425)	
[2022-01-19 10:33:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][850/1251]	eta 0:14:49 lr 0.000906	time 2.7814 (2.2192)	loss 4.0477 (3.8865)	grad_norm 1.1530 (1.1427)	
[2022-01-19 10:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][860/1251]	eta 0:14:27 lr 0.000906	time 1.7491 (2.2178)	loss 4.0637 (3.8862)	grad_norm 1.2910 (1.1438)	
[2022-01-19 10:34:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][870/1251]	eta 0:14:04 lr 0.000906	time 2.1870 (2.2164)	loss 3.1540 (3.8870)	grad_norm 0.9065 (1.1436)	
[2022-01-19 10:34:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][880/1251]	eta 0:13:41 lr 0.000906	time 1.6121 (2.2154)	loss 4.1945 (3.8902)	grad_norm 1.2680 (1.1434)	
[2022-01-19 10:35:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][890/1251]	eta 0:13:19 lr 0.000906	time 2.5309 (2.2147)	loss 3.7227 (3.8907)	grad_norm 1.1626 (1.1435)	
[2022-01-19 10:35:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][900/1251]	eta 0:12:57 lr 0.000906	time 2.8437 (2.2162)	loss 3.6794 (3.8893)	grad_norm 1.1821 (1.1439)	
[2022-01-19 10:36:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][910/1251]	eta 0:12:36 lr 0.000906	time 2.1698 (2.2173)	loss 3.9985 (3.8910)	grad_norm 1.1022 (1.1438)	
[2022-01-19 10:36:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][920/1251]	eta 0:12:14 lr 0.000906	time 1.9791 (2.2190)	loss 4.2092 (3.8936)	grad_norm 1.1259 (1.1434)	
[2022-01-19 10:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][930/1251]	eta 0:11:52 lr 0.000906	time 2.1827 (2.2187)	loss 4.3773 (3.8976)	grad_norm 1.1601 (1.1429)	
[2022-01-19 10:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][940/1251]	eta 0:11:29 lr 0.000906	time 2.5409 (2.2174)	loss 3.8664 (3.8983)	grad_norm 1.3926 (1.1436)	
[2022-01-19 10:37:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][950/1251]	eta 0:11:06 lr 0.000906	time 2.0412 (2.2146)	loss 3.8084 (3.8974)	grad_norm 1.0682 (1.1439)	
[2022-01-19 10:37:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][960/1251]	eta 0:10:43 lr 0.000906	time 1.8749 (2.2117)	loss 4.1551 (3.8957)	grad_norm 1.1614 (1.1441)	
[2022-01-19 10:38:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][970/1251]	eta 0:10:21 lr 0.000906	time 2.5533 (2.2105)	loss 3.6993 (3.8956)	grad_norm 1.1764 (1.1436)	
[2022-01-19 10:38:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][980/1251]	eta 0:09:58 lr 0.000906	time 2.4365 (2.2102)	loss 3.9206 (3.8967)	grad_norm 1.0695 (1.1437)	
[2022-01-19 10:38:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][990/1251]	eta 0:09:36 lr 0.000906	time 2.3837 (2.2104)	loss 4.3532 (3.8989)	grad_norm 1.3142 (1.1441)	
[2022-01-19 10:39:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1000/1251]	eta 0:09:15 lr 0.000906	time 2.1723 (2.2116)	loss 3.3254 (3.8999)	grad_norm 1.0514 (1.1434)	
[2022-01-19 10:39:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1010/1251]	eta 0:08:53 lr 0.000906	time 2.5486 (2.2123)	loss 2.9551 (3.8997)	grad_norm 1.0240 (1.1430)	
[2022-01-19 10:39:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1020/1251]	eta 0:08:31 lr 0.000906	time 2.1386 (2.2127)	loss 4.0573 (3.8989)	grad_norm 1.1299 (1.1428)	
[2022-01-19 10:40:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1030/1251]	eta 0:08:09 lr 0.000906	time 1.9063 (2.2138)	loss 3.0367 (3.8978)	grad_norm 1.0300 (1.1418)	
[2022-01-19 10:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1040/1251]	eta 0:07:47 lr 0.000906	time 1.8691 (2.2145)	loss 4.2108 (3.8983)	grad_norm 1.7059 (1.1421)	
[2022-01-19 10:41:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1050/1251]	eta 0:07:24 lr 0.000906	time 2.4043 (2.2134)	loss 3.5693 (3.8999)	grad_norm 1.1910 (1.1421)	
[2022-01-19 10:41:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1060/1251]	eta 0:07:02 lr 0.000906	time 1.9630 (2.2116)	loss 4.0069 (3.9004)	grad_norm 1.1574 (1.1416)	
[2022-01-19 10:41:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1070/1251]	eta 0:06:40 lr 0.000906	time 2.0616 (2.2112)	loss 4.0398 (3.8987)	grad_norm 1.0656 (1.1412)	
[2022-01-19 10:42:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1080/1251]	eta 0:06:18 lr 0.000906	time 1.9421 (2.2125)	loss 4.0078 (3.8996)	grad_norm 1.1259 (1.1410)	
[2022-01-19 10:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1090/1251]	eta 0:05:56 lr 0.000906	time 2.8173 (2.2137)	loss 3.6631 (3.8993)	grad_norm 1.1193 (1.1407)	
[2022-01-19 10:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1100/1251]	eta 0:05:34 lr 0.000906	time 2.1254 (2.2130)	loss 3.8437 (3.9017)	grad_norm 1.5541 (1.1414)	
[2022-01-19 10:43:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1110/1251]	eta 0:05:11 lr 0.000906	time 1.9179 (2.2115)	loss 3.7173 (3.9003)	grad_norm 1.3110 (1.1413)	
[2022-01-19 10:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1120/1251]	eta 0:04:49 lr 0.000906	time 1.8535 (2.2116)	loss 3.0005 (3.9013)	grad_norm 1.2180 (1.1409)	
[2022-01-19 10:44:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1130/1251]	eta 0:04:27 lr 0.000906	time 2.6279 (2.2110)	loss 4.6765 (3.9017)	grad_norm 1.0259 (1.1405)	
[2022-01-19 10:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1140/1251]	eta 0:04:05 lr 0.000906	time 2.1238 (2.2107)	loss 4.0252 (3.9003)	grad_norm 1.1267 (1.1399)	
[2022-01-19 10:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1150/1251]	eta 0:03:43 lr 0.000906	time 1.5743 (2.2112)	loss 3.9499 (3.9011)	grad_norm 1.1815 (1.1398)	
[2022-01-19 10:45:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1160/1251]	eta 0:03:21 lr 0.000906	time 1.9608 (2.2107)	loss 3.1589 (3.8993)	grad_norm 1.1302 (1.1396)	
[2022-01-19 10:45:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1170/1251]	eta 0:02:58 lr 0.000906	time 1.6198 (2.2091)	loss 4.1934 (3.8993)	grad_norm 1.0121 (1.1391)	
[2022-01-19 10:45:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1180/1251]	eta 0:02:36 lr 0.000906	time 2.2749 (2.2080)	loss 4.6283 (3.8988)	grad_norm 1.2994 (1.1389)	
[2022-01-19 10:46:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1190/1251]	eta 0:02:14 lr 0.000906	time 2.0701 (2.2084)	loss 3.6397 (3.8966)	grad_norm 1.3599 (1.1391)	
[2022-01-19 10:46:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1200/1251]	eta 0:01:52 lr 0.000906	time 4.3798 (2.2087)	loss 4.1546 (3.8944)	grad_norm 1.0143 (1.1380)	
[2022-01-19 10:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1210/1251]	eta 0:01:30 lr 0.000906	time 1.9403 (2.2084)	loss 3.9986 (3.8937)	grad_norm 0.9812 (1.1375)	
[2022-01-19 10:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1220/1251]	eta 0:01:08 lr 0.000906	time 2.4136 (2.2079)	loss 4.4680 (3.8940)	grad_norm 1.0766 (1.1368)	
[2022-01-19 10:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1230/1251]	eta 0:00:46 lr 0.000906	time 2.2353 (2.2085)	loss 3.2055 (3.8925)	grad_norm 1.1882 (1.1367)	
[2022-01-19 10:48:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1240/1251]	eta 0:00:24 lr 0.000905	time 2.4204 (2.2081)	loss 4.2167 (3.8937)	grad_norm 1.0308 (1.1371)	
[2022-01-19 10:48:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [59/300][1250/1251]	eta 0:00:02 lr 0.000905	time 1.1492 (2.2022)	loss 4.6230 (3.8939)	grad_norm 1.2233 (1.1379)	
[2022-01-19 10:48:16 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 59 training takes 0:45:55
[2022-01-19 10:48:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.633 (18.633)	Loss 1.2471 (1.2471)	Acc@1 72.559 (72.559)	Acc@5 89.746 (89.746)	
[2022-01-19 10:48:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.518 (3.399)	Loss 1.2219 (1.2568)	Acc@1 72.363 (71.218)	Acc@5 91.504 (90.154)	
[2022-01-19 10:49:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.938 (2.672)	Loss 1.2188 (1.2421)	Acc@1 71.191 (71.447)	Acc@5 90.527 (90.453)	
[2022-01-19 10:49:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.645 (2.279)	Loss 1.2549 (1.2492)	Acc@1 71.387 (71.176)	Acc@5 90.723 (90.543)	
[2022-01-19 10:49:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 5.397 (2.181)	Loss 1.2652 (1.2449)	Acc@1 70.996 (71.225)	Acc@5 89.062 (90.644)	
[2022-01-19 10:49:52 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 71.080 Acc@5 90.598
[2022-01-19 10:49:52 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 71.1%
[2022-01-19 10:49:52 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 71.28%
[2022-01-19 10:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][0/1251]	eta 8:09:04 lr 0.000905	time 23.4566 (23.4566)	loss 3.7538 (3.7538)	grad_norm 1.3162 (1.3162)	
[2022-01-19 10:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][10/1251]	eta 1:29:30 lr 0.000905	time 1.8495 (4.3276)	loss 4.0114 (3.8008)	grad_norm 1.1703 (1.2156)	
[2022-01-19 10:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][20/1251]	eta 1:07:18 lr 0.000905	time 1.9029 (3.2810)	loss 3.3841 (3.7295)	grad_norm 1.3234 (1.1924)	
[2022-01-19 10:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][30/1251]	eta 0:59:22 lr 0.000905	time 1.9416 (2.9173)	loss 4.3795 (3.8754)	grad_norm 1.3181 (1.1790)	
[2022-01-19 10:51:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][40/1251]	eta 0:55:41 lr 0.000905	time 3.1309 (2.7596)	loss 3.4401 (3.8419)	grad_norm 1.0630 (1.1625)	
[2022-01-19 10:52:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][50/1251]	eta 0:53:19 lr 0.000905	time 3.1358 (2.6637)	loss 4.0362 (3.9005)	grad_norm 1.1627 (1.1689)	
[2022-01-19 10:52:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][60/1251]	eta 0:51:00 lr 0.000905	time 1.5808 (2.5694)	loss 4.2375 (3.9052)	grad_norm 0.9811 (1.1653)	
[2022-01-19 10:52:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][70/1251]	eta 0:49:31 lr 0.000905	time 2.0734 (2.5159)	loss 4.7408 (3.9144)	grad_norm 1.1154 (1.1659)	
[2022-01-19 10:53:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][80/1251]	eta 0:48:11 lr 0.000905	time 2.2723 (2.4696)	loss 4.0932 (3.9118)	grad_norm 1.2790 (1.1710)	
[2022-01-19 10:53:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][90/1251]	eta 0:47:09 lr 0.000905	time 1.8956 (2.4368)	loss 4.5472 (3.8927)	grad_norm 1.2828 (1.1688)	
[2022-01-19 10:53:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][100/1251]	eta 0:46:19 lr 0.000905	time 2.6391 (2.4150)	loss 4.7946 (3.8731)	grad_norm 1.0248 (1.1618)	
[2022-01-19 10:54:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][110/1251]	eta 0:45:37 lr 0.000905	time 2.1713 (2.3989)	loss 4.2991 (3.8809)	grad_norm 1.0347 (1.1577)	
[2022-01-19 10:54:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][120/1251]	eta 0:44:49 lr 0.000905	time 2.3113 (2.3778)	loss 3.9724 (3.8790)	grad_norm 1.4185 (1.1605)	
[2022-01-19 10:55:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][130/1251]	eta 0:44:09 lr 0.000905	time 1.9837 (2.3634)	loss 3.9951 (3.8783)	grad_norm 1.3738 (1.1571)	
[2022-01-19 10:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][140/1251]	eta 0:43:25 lr 0.000905	time 2.5901 (2.3455)	loss 4.5821 (3.8862)	grad_norm 1.9438 (1.1633)	
[2022-01-19 10:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][150/1251]	eta 0:42:41 lr 0.000905	time 2.5915 (2.3269)	loss 3.7014 (3.8878)	grad_norm 1.3747 (1.1659)	
[2022-01-19 10:56:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][160/1251]	eta 0:42:03 lr 0.000905	time 2.3587 (2.3126)	loss 3.4964 (3.8891)	grad_norm 1.3918 (1.1665)	
[2022-01-19 10:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][170/1251]	eta 0:41:39 lr 0.000905	time 2.0713 (2.3118)	loss 3.9815 (3.9094)	grad_norm 1.0379 (1.1632)	
[2022-01-19 10:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][180/1251]	eta 0:41:11 lr 0.000905	time 3.0509 (2.3077)	loss 3.1339 (3.8907)	grad_norm 1.3353 (1.1575)	
[2022-01-19 10:57:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][190/1251]	eta 0:40:46 lr 0.000905	time 1.7587 (2.3055)	loss 4.0336 (3.8965)	grad_norm 1.2512 (1.1561)	
[2022-01-19 10:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][200/1251]	eta 0:40:17 lr 0.000905	time 2.2264 (2.3006)	loss 4.1008 (3.8937)	grad_norm 1.1561 (1.1583)	
[2022-01-19 10:57:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][210/1251]	eta 0:39:48 lr 0.000905	time 1.8234 (2.2941)	loss 4.3903 (3.8869)	grad_norm 1.2211 (1.1568)	
[2022-01-19 10:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][220/1251]	eta 0:39:21 lr 0.000905	time 3.1149 (2.2903)	loss 3.7556 (3.8892)	grad_norm 0.9201 (1.1545)	
[2022-01-19 10:58:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][230/1251]	eta 0:38:57 lr 0.000905	time 2.9358 (2.2896)	loss 3.2139 (3.8874)	grad_norm 1.0456 (1.1544)	
[2022-01-19 10:59:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][240/1251]	eta 0:38:27 lr 0.000905	time 2.3011 (2.2820)	loss 4.8553 (3.8912)	grad_norm 1.2486 (1.1549)	
[2022-01-19 10:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][250/1251]	eta 0:37:58 lr 0.000905	time 2.4283 (2.2765)	loss 4.0887 (3.8955)	grad_norm 1.1476 (1.1576)	
[2022-01-19 10:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][260/1251]	eta 0:37:30 lr 0.000905	time 1.9927 (2.2709)	loss 3.6563 (3.8941)	grad_norm 1.1872 (1.1570)	
[2022-01-19 11:00:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][270/1251]	eta 0:37:02 lr 0.000905	time 2.5684 (2.2660)	loss 4.6081 (3.9006)	grad_norm 0.9865 (1.1546)	
[2022-01-19 11:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][280/1251]	eta 0:36:40 lr 0.000905	time 2.1811 (2.2658)	loss 3.1600 (3.9034)	grad_norm 1.1849 (1.1547)	
[2022-01-19 11:00:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][290/1251]	eta 0:36:13 lr 0.000905	time 2.1687 (2.2618)	loss 3.9641 (3.8991)	grad_norm 1.0430 (1.1583)	
[2022-01-19 11:01:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][300/1251]	eta 0:35:51 lr 0.000905	time 3.1155 (2.2618)	loss 4.4597 (3.8913)	grad_norm 1.1342 (1.1565)	
[2022-01-19 11:01:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][310/1251]	eta 0:35:28 lr 0.000905	time 2.6449 (2.2620)	loss 4.1344 (3.8899)	grad_norm 0.9717 (1.1531)	
[2022-01-19 11:01:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][320/1251]	eta 0:34:59 lr 0.000905	time 2.0183 (2.2555)	loss 3.1976 (3.8880)	grad_norm 1.2287 (1.1534)	
[2022-01-19 11:02:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][330/1251]	eta 0:34:35 lr 0.000905	time 2.4920 (2.2539)	loss 3.7817 (3.8787)	grad_norm 1.2113 (1.1557)	
[2022-01-19 11:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][340/1251]	eta 0:34:08 lr 0.000905	time 1.9534 (2.2483)	loss 3.8431 (3.8832)	grad_norm 1.2090 (1.1565)	
[2022-01-19 11:03:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][350/1251]	eta 0:33:43 lr 0.000905	time 3.0484 (2.2460)	loss 3.1696 (3.8884)	grad_norm 1.3163 (1.1565)	
[2022-01-19 11:03:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][360/1251]	eta 0:33:21 lr 0.000905	time 2.5882 (2.2459)	loss 4.3811 (3.8923)	grad_norm 0.9763 (1.1555)	
[2022-01-19 11:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][370/1251]	eta 0:32:54 lr 0.000905	time 1.6185 (2.2409)	loss 3.8617 (3.8940)	grad_norm 1.0199 (1.1577)	
[2022-01-19 11:04:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][380/1251]	eta 0:32:31 lr 0.000905	time 2.4859 (2.2401)	loss 2.9272 (3.8994)	grad_norm 1.1574 (1.1578)	
[2022-01-19 11:04:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][390/1251]	eta 0:32:07 lr 0.000905	time 2.7790 (2.2392)	loss 4.2320 (3.8981)	grad_norm 1.2051 (1.1577)	
[2022-01-19 11:04:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][400/1251]	eta 0:31:45 lr 0.000904	time 2.4438 (2.2392)	loss 4.6219 (3.9003)	grad_norm 0.9899 (1.1572)	
[2022-01-19 11:05:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][410/1251]	eta 0:31:21 lr 0.000904	time 2.7797 (2.2377)	loss 3.3902 (3.9017)	grad_norm 1.3852 (1.1567)	
[2022-01-19 11:05:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][420/1251]	eta 0:30:55 lr 0.000904	time 1.9950 (2.2332)	loss 4.4915 (3.8981)	grad_norm 1.4688 (1.1570)	
[2022-01-19 11:05:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][430/1251]	eta 0:30:34 lr 0.000904	time 2.8226 (2.2341)	loss 4.5213 (3.8992)	grad_norm 1.2436 (1.1576)	
[2022-01-19 11:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][440/1251]	eta 0:30:14 lr 0.000904	time 3.4608 (2.2369)	loss 4.1171 (3.8981)	grad_norm 1.2301 (1.1587)	
[2022-01-19 11:06:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][450/1251]	eta 0:29:47 lr 0.000904	time 1.8141 (2.2311)	loss 4.5119 (3.9005)	grad_norm 1.0662 (1.1561)	
[2022-01-19 11:07:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][460/1251]	eta 0:29:23 lr 0.000904	time 1.9620 (2.2291)	loss 4.3333 (3.9043)	grad_norm 1.2808 (1.1560)	
[2022-01-19 11:07:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][470/1251]	eta 0:28:58 lr 0.000904	time 2.6609 (2.2266)	loss 3.0134 (3.9032)	grad_norm 1.1517 (1.1541)	
[2022-01-19 11:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][480/1251]	eta 0:28:38 lr 0.000904	time 3.4308 (2.2285)	loss 4.2000 (3.9052)	grad_norm 1.2389 (1.1549)	
[2022-01-19 11:08:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][490/1251]	eta 0:28:17 lr 0.000904	time 2.8183 (2.2301)	loss 3.5747 (3.9016)	grad_norm 1.3611 (1.1556)	
[2022-01-19 11:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][500/1251]	eta 0:27:55 lr 0.000904	time 1.5338 (2.2313)	loss 4.0010 (3.9001)	grad_norm 1.0848 (1.1552)	
[2022-01-19 11:08:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][510/1251]	eta 0:27:34 lr 0.000904	time 3.1670 (2.2324)	loss 3.4119 (3.9020)	grad_norm 1.3514 (1.1559)	
[2022-01-19 11:09:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][520/1251]	eta 0:27:11 lr 0.000904	time 2.5715 (2.2315)	loss 4.5434 (3.9036)	grad_norm 1.1969 (1.1557)	
[2022-01-19 11:09:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][530/1251]	eta 0:26:47 lr 0.000904	time 2.1202 (2.2294)	loss 3.6895 (3.9084)	grad_norm 1.2273 (1.1569)	
[2022-01-19 11:09:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][540/1251]	eta 0:26:22 lr 0.000904	time 1.9555 (2.2262)	loss 3.8938 (3.9078)	grad_norm 0.9857 (1.1568)	
[2022-01-19 11:10:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][550/1251]	eta 0:26:00 lr 0.000904	time 3.4272 (2.2266)	loss 4.2998 (3.9108)	grad_norm 1.0759 (1.1556)	
[2022-01-19 11:10:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][560/1251]	eta 0:25:36 lr 0.000904	time 1.9628 (2.2232)	loss 4.3510 (3.9108)	grad_norm 1.1368 (1.1549)	
[2022-01-19 11:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][570/1251]	eta 0:25:13 lr 0.000904	time 1.5110 (2.2227)	loss 4.2862 (3.9107)	grad_norm 1.2312 (1.1550)	
[2022-01-19 11:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][580/1251]	eta 0:24:49 lr 0.000904	time 1.7478 (2.2196)	loss 3.3793 (3.9126)	grad_norm 1.0657 (1.1536)	
[2022-01-19 11:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][590/1251]	eta 0:24:27 lr 0.000904	time 2.8108 (2.2195)	loss 3.6937 (3.9138)	grad_norm 1.1503 (1.1522)	
[2022-01-19 11:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][600/1251]	eta 0:24:06 lr 0.000904	time 3.1228 (2.2215)	loss 3.6940 (3.9137)	grad_norm 1.0943 (1.1530)	
[2022-01-19 11:12:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][610/1251]	eta 0:23:42 lr 0.000904	time 1.9835 (2.2187)	loss 4.5215 (3.9154)	grad_norm 1.2121 (1.1534)	
[2022-01-19 11:12:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][620/1251]	eta 0:23:20 lr 0.000904	time 2.2271 (2.2188)	loss 2.7978 (3.9172)	grad_norm 1.2681 (1.1540)	
[2022-01-19 11:13:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][630/1251]	eta 0:22:58 lr 0.000904	time 2.3667 (2.2195)	loss 3.1715 (3.9168)	grad_norm 1.6116 (1.1550)	
[2022-01-19 11:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][640/1251]	eta 0:22:37 lr 0.000904	time 3.1448 (2.2211)	loss 4.6200 (3.9193)	grad_norm 1.0120 (1.1540)	
[2022-01-19 11:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][650/1251]	eta 0:22:14 lr 0.000904	time 1.8972 (2.2209)	loss 3.7410 (3.9190)	grad_norm 0.9115 (1.1529)	
[2022-01-19 11:14:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][660/1251]	eta 0:21:51 lr 0.000904	time 1.7728 (2.2200)	loss 4.4157 (3.9192)	grad_norm 1.0052 (1.1529)	
[2022-01-19 11:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][670/1251]	eta 0:21:28 lr 0.000904	time 1.7753 (2.2176)	loss 4.2579 (3.9185)	grad_norm 1.0684 (1.1547)	
[2022-01-19 11:15:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][680/1251]	eta 0:21:04 lr 0.000904	time 2.4250 (2.2152)	loss 4.3176 (3.9219)	grad_norm 1.4002 (1.1551)	
[2022-01-19 11:15:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][690/1251]	eta 0:20:41 lr 0.000904	time 1.9431 (2.2124)	loss 3.5871 (3.9187)	grad_norm 1.1593 (1.1548)	
[2022-01-19 11:15:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][700/1251]	eta 0:20:18 lr 0.000904	time 2.2630 (2.2116)	loss 3.9109 (3.9199)	grad_norm 1.0889 (1.1536)	
[2022-01-19 11:16:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][710/1251]	eta 0:19:57 lr 0.000904	time 2.5379 (2.2140)	loss 4.0368 (3.9214)	grad_norm 1.0797 (1.1526)	
[2022-01-19 11:16:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][720/1251]	eta 0:19:35 lr 0.000904	time 2.5254 (2.2138)	loss 4.2502 (3.9212)	grad_norm 1.0916 (1.1514)	
[2022-01-19 11:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][730/1251]	eta 0:19:14 lr 0.000904	time 2.8625 (2.2152)	loss 2.9823 (3.9195)	grad_norm 1.2440 (1.1507)	
[2022-01-19 11:17:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][740/1251]	eta 0:18:52 lr 0.000904	time 2.5146 (2.2153)	loss 3.8222 (3.9217)	grad_norm 1.1500 (1.1508)	
[2022-01-19 11:17:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][750/1251]	eta 0:18:30 lr 0.000904	time 2.5198 (2.2163)	loss 4.5936 (3.9180)	grad_norm 1.0803 (1.1510)	
[2022-01-19 11:17:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][760/1251]	eta 0:18:07 lr 0.000904	time 1.6152 (2.2139)	loss 4.1127 (3.9136)	grad_norm 1.1648 (1.1503)	
[2022-01-19 11:18:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][770/1251]	eta 0:17:43 lr 0.000904	time 1.8558 (2.2119)	loss 4.0464 (3.9144)	grad_norm 1.1618 (1.1506)	
[2022-01-19 11:18:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][780/1251]	eta 0:17:20 lr 0.000904	time 2.4680 (2.2096)	loss 3.8844 (3.9154)	grad_norm 1.1810 (1.1513)	
[2022-01-19 11:19:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][790/1251]	eta 0:16:58 lr 0.000904	time 2.5194 (2.2094)	loss 3.9709 (3.9160)	grad_norm 1.1575 (1.1519)	
[2022-01-19 11:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][800/1251]	eta 0:16:36 lr 0.000904	time 2.4876 (2.2100)	loss 2.9782 (3.9146)	grad_norm 0.9358 (1.1524)	
[2022-01-19 11:19:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][810/1251]	eta 0:16:15 lr 0.000903	time 2.8704 (2.2110)	loss 3.6606 (3.9130)	grad_norm 1.2340 (1.1535)	
[2022-01-19 11:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][820/1251]	eta 0:15:52 lr 0.000903	time 1.8667 (2.2106)	loss 3.7528 (3.9151)	grad_norm 1.2964 (1.1541)	
[2022-01-19 11:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][830/1251]	eta 0:15:30 lr 0.000903	time 2.0012 (2.2107)	loss 3.7683 (3.9122)	grad_norm 0.9316 (1.1530)	
[2022-01-19 11:20:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][840/1251]	eta 0:15:07 lr 0.000903	time 1.9363 (2.2084)	loss 4.0518 (3.9112)	grad_norm 1.0210 (1.1521)	
[2022-01-19 11:21:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][850/1251]	eta 0:14:45 lr 0.000903	time 1.9577 (2.2082)	loss 2.7385 (3.9100)	grad_norm 1.7675 (1.1524)	
[2022-01-19 11:21:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][860/1251]	eta 0:14:23 lr 0.000903	time 2.1438 (2.2089)	loss 4.4000 (3.9113)	grad_norm 1.0470 (1.1521)	
[2022-01-19 11:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][870/1251]	eta 0:14:01 lr 0.000903	time 2.2072 (2.2090)	loss 4.2596 (3.9079)	grad_norm 1.1233 (1.1517)	
[2022-01-19 11:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][880/1251]	eta 0:13:39 lr 0.000903	time 2.1025 (2.2088)	loss 2.6184 (3.9078)	grad_norm 1.1580 (1.1522)	
[2022-01-19 11:22:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][890/1251]	eta 0:13:17 lr 0.000903	time 2.2511 (2.2095)	loss 3.3320 (3.9087)	grad_norm 1.2379 (1.1519)	
[2022-01-19 11:23:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][900/1251]	eta 0:12:54 lr 0.000903	time 2.3455 (2.2075)	loss 2.6039 (3.9060)	grad_norm 1.1436 (1.1519)	
[2022-01-19 11:23:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][910/1251]	eta 0:12:31 lr 0.000903	time 1.8861 (2.2046)	loss 3.9367 (3.9058)	grad_norm 1.2892 (1.1521)	
[2022-01-19 11:23:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][920/1251]	eta 0:12:09 lr 0.000903	time 2.0965 (2.2039)	loss 4.3917 (3.9035)	grad_norm 1.1190 (1.1520)	
[2022-01-19 11:24:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][930/1251]	eta 0:11:46 lr 0.000903	time 2.1974 (2.2020)	loss 4.0446 (3.9023)	grad_norm 1.1867 (1.1516)	
[2022-01-19 11:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][940/1251]	eta 0:11:24 lr 0.000903	time 2.3318 (2.2013)	loss 3.8799 (3.9017)	grad_norm 1.2056 (1.1513)	
[2022-01-19 11:24:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][950/1251]	eta 0:11:02 lr 0.000903	time 1.9903 (2.2007)	loss 3.8642 (3.8994)	grad_norm 1.2341 (1.1525)	
[2022-01-19 11:25:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][960/1251]	eta 0:10:40 lr 0.000903	time 2.0624 (2.1999)	loss 4.1668 (3.8976)	grad_norm 1.6219 (1.1536)	
[2022-01-19 11:25:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][970/1251]	eta 0:10:18 lr 0.000903	time 2.4083 (2.1996)	loss 4.1595 (3.8995)	grad_norm 1.2911 (1.1544)	
[2022-01-19 11:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][980/1251]	eta 0:09:56 lr 0.000903	time 2.9942 (2.2021)	loss 3.3827 (3.8982)	grad_norm 1.0086 (1.1537)	
[2022-01-19 11:26:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][990/1251]	eta 0:09:35 lr 0.000903	time 1.8308 (2.2036)	loss 3.7589 (3.8981)	grad_norm 1.0709 (1.1532)	
[2022-01-19 11:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1000/1251]	eta 0:09:13 lr 0.000903	time 3.0928 (2.2052)	loss 3.1357 (3.8966)	grad_norm 0.9877 (1.1532)	
[2022-01-19 11:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1010/1251]	eta 0:08:51 lr 0.000903	time 2.2150 (2.2055)	loss 4.2090 (3.8968)	grad_norm 1.0279 (1.1527)	
[2022-01-19 11:27:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1020/1251]	eta 0:08:29 lr 0.000903	time 1.8330 (2.2047)	loss 2.8780 (3.8970)	grad_norm 1.0734 (1.1517)	
[2022-01-19 11:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1030/1251]	eta 0:08:07 lr 0.000903	time 2.3236 (2.2040)	loss 4.2481 (3.8993)	grad_norm 0.9927 (1.1515)	
[2022-01-19 11:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1040/1251]	eta 0:07:44 lr 0.000903	time 1.8340 (2.2027)	loss 4.0839 (3.8988)	grad_norm 1.0742 (1.1507)	
[2022-01-19 11:28:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1050/1251]	eta 0:07:22 lr 0.000903	time 2.2112 (2.2011)	loss 4.7658 (3.9003)	grad_norm 1.0647 (1.1501)	
[2022-01-19 11:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1060/1251]	eta 0:07:00 lr 0.000903	time 2.1730 (2.1995)	loss 4.6623 (3.9031)	grad_norm 1.0901 (1.1497)	
[2022-01-19 11:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1070/1251]	eta 0:06:38 lr 0.000903	time 2.3588 (2.1997)	loss 3.7783 (3.9042)	grad_norm 0.9809 (1.1491)	
[2022-01-19 11:29:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1080/1251]	eta 0:06:16 lr 0.000903	time 2.0749 (2.2000)	loss 4.8942 (3.9063)	grad_norm 1.2283 (1.1495)	
[2022-01-19 11:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1090/1251]	eta 0:05:54 lr 0.000903	time 2.2527 (2.1998)	loss 4.0425 (3.9057)	grad_norm 1.0491 (1.1491)	
[2022-01-19 11:30:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1100/1251]	eta 0:05:32 lr 0.000903	time 2.1661 (2.1997)	loss 2.6105 (3.9024)	grad_norm 1.1400 (1.1487)	
[2022-01-19 11:30:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1110/1251]	eta 0:05:10 lr 0.000903	time 1.9473 (2.2003)	loss 4.3744 (3.9036)	grad_norm 1.1570 (1.1480)	
[2022-01-19 11:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1120/1251]	eta 0:04:48 lr 0.000903	time 1.6843 (2.2004)	loss 3.3524 (3.9026)	grad_norm 1.5838 (1.1485)	
[2022-01-19 11:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1130/1251]	eta 0:04:26 lr 0.000903	time 3.0174 (2.2011)	loss 2.7252 (3.9022)	grad_norm 1.3295 (1.1492)	
[2022-01-19 11:31:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1140/1251]	eta 0:04:04 lr 0.000903	time 2.3700 (2.2012)	loss 4.1284 (3.9030)	grad_norm 1.4161 (1.1494)	
[2022-01-19 11:32:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1150/1251]	eta 0:03:42 lr 0.000903	time 2.1914 (2.2014)	loss 4.5631 (3.8993)	grad_norm 1.1556 (1.1500)	
[2022-01-19 11:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1160/1251]	eta 0:03:20 lr 0.000903	time 1.9036 (2.2001)	loss 4.3837 (3.9013)	grad_norm 1.0682 (1.1492)	
[2022-01-19 11:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1170/1251]	eta 0:02:58 lr 0.000903	time 2.7869 (2.2009)	loss 3.5221 (3.9021)	grad_norm 1.0602 (1.1489)	
[2022-01-19 11:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1180/1251]	eta 0:02:36 lr 0.000903	time 1.8839 (2.2001)	loss 3.8955 (3.9024)	grad_norm 1.1333 (1.1485)	
[2022-01-19 11:33:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1190/1251]	eta 0:02:14 lr 0.000903	time 2.6046 (2.1996)	loss 4.9202 (3.9025)	grad_norm 1.0495 (1.1490)	
[2022-01-19 11:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1200/1251]	eta 0:01:52 lr 0.000903	time 1.9383 (2.1989)	loss 4.5670 (3.9030)	grad_norm 1.1430 (1.1489)	
[2022-01-19 11:34:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1210/1251]	eta 0:01:30 lr 0.000902	time 2.5057 (2.1992)	loss 4.2665 (3.9026)	grad_norm 1.2423 (1.1491)	
[2022-01-19 11:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1220/1251]	eta 0:01:08 lr 0.000902	time 2.4235 (2.1998)	loss 4.3657 (3.9038)	grad_norm 1.0475 (1.1490)	
[2022-01-19 11:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1230/1251]	eta 0:00:46 lr 0.000902	time 2.0504 (2.1994)	loss 4.4958 (3.9028)	grad_norm 1.1519 (1.1488)	
[2022-01-19 11:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1240/1251]	eta 0:00:24 lr 0.000902	time 1.4479 (2.1982)	loss 3.0590 (3.9007)	grad_norm 1.0040 (1.1489)	
[2022-01-19 11:35:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [60/300][1250/1251]	eta 0:00:02 lr 0.000902	time 1.1677 (2.1930)	loss 4.1357 (3.9006)	grad_norm 1.0011 (1.1486)	
[2022-01-19 11:35:36 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 60 training takes 0:45:43
[2022-01-19 11:35:36 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_60 saving......
[2022-01-19 11:35:47 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_60 saved !!!
[2022-01-19 11:36:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 13.509 (13.509)	Loss 1.2100 (1.2100)	Acc@1 71.875 (71.875)	Acc@5 91.406 (91.406)	
[2022-01-19 11:36:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.086 (2.506)	Loss 1.2556 (1.2318)	Acc@1 69.727 (71.342)	Acc@5 90.430 (90.811)	
[2022-01-19 11:36:32 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.430 (2.133)	Loss 1.1997 (1.2134)	Acc@1 71.094 (71.610)	Acc@5 90.723 (90.992)	
[2022-01-19 11:36:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.980 (2.059)	Loss 1.2328 (1.2233)	Acc@1 72.363 (71.327)	Acc@5 91.113 (90.978)	
[2022-01-19 11:37:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.711 (1.916)	Loss 1.1780 (1.2263)	Acc@1 73.145 (71.394)	Acc@5 91.016 (90.923)	
[2022-01-19 11:37:14 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 71.448 Acc@5 90.886
[2022-01-19 11:37:14 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 71.4%
[2022-01-19 11:37:14 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 71.45%
[2022-01-19 11:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][0/1251]	eta 7:28:12 lr 0.000902	time 21.4969 (21.4969)	loss 4.3168 (4.3168)	grad_norm 1.0581 (1.0581)	
[2022-01-19 11:37:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][10/1251]	eta 1:24:22 lr 0.000902	time 1.4643 (4.0797)	loss 3.9479 (3.7114)	grad_norm 1.1270 (1.1475)	
[2022-01-19 11:38:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][20/1251]	eta 1:07:37 lr 0.000902	time 2.1634 (3.2962)	loss 3.2931 (3.7876)	grad_norm 1.0350 (1.1801)	
[2022-01-19 11:38:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][30/1251]	eta 0:59:42 lr 0.000902	time 1.5833 (2.9342)	loss 4.0747 (3.7888)	grad_norm 1.1567 (1.1748)	
[2022-01-19 11:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][40/1251]	eta 0:56:33 lr 0.000902	time 3.8068 (2.8022)	loss 3.7527 (3.8191)	grad_norm 1.1422 (1.1689)	
[2022-01-19 11:39:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][50/1251]	eta 0:53:30 lr 0.000902	time 1.5305 (2.6729)	loss 3.3355 (3.8161)	grad_norm 1.1169 (1.1547)	
[2022-01-19 11:39:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][60/1251]	eta 0:51:38 lr 0.000902	time 3.0045 (2.6018)	loss 3.6860 (3.7907)	grad_norm 1.1166 (1.1558)	
[2022-01-19 11:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][70/1251]	eta 0:49:58 lr 0.000902	time 1.8815 (2.5392)	loss 3.3721 (3.7881)	grad_norm 1.0310 (1.1710)	
[2022-01-19 11:40:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][80/1251]	eta 0:48:51 lr 0.000902	time 2.8116 (2.5037)	loss 4.0916 (3.7685)	grad_norm 1.0350 (1.1584)	
[2022-01-19 11:40:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][90/1251]	eta 0:47:50 lr 0.000902	time 2.2147 (2.4721)	loss 3.8483 (3.8139)	grad_norm 1.0184 (1.1584)	
[2022-01-19 11:41:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][100/1251]	eta 0:46:43 lr 0.000902	time 2.6454 (2.4361)	loss 4.4087 (3.8407)	grad_norm 1.2621 (1.1539)	
[2022-01-19 11:41:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][110/1251]	eta 0:45:44 lr 0.000902	time 1.8305 (2.4054)	loss 3.3077 (3.8164)	grad_norm 1.1914 (1.1575)	
[2022-01-19 11:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][120/1251]	eta 0:44:56 lr 0.000902	time 2.8527 (2.3846)	loss 4.5684 (3.8411)	grad_norm 1.1946 (1.1586)	
[2022-01-19 11:42:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][130/1251]	eta 0:44:26 lr 0.000902	time 2.4847 (2.3789)	loss 4.6280 (3.8508)	grad_norm 1.3582 (1.1586)	
[2022-01-19 11:42:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][140/1251]	eta 0:43:43 lr 0.000902	time 2.2098 (2.3614)	loss 4.1378 (3.8593)	grad_norm 1.1774 (1.1549)	
[2022-01-19 11:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][150/1251]	eta 0:43:01 lr 0.000902	time 1.7894 (2.3446)	loss 4.8196 (3.8544)	grad_norm 1.1874 (1.1601)	
[2022-01-19 11:43:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][160/1251]	eta 0:42:24 lr 0.000902	time 2.2181 (2.3327)	loss 4.3971 (3.8361)	grad_norm 1.1099 (1.1578)	
[2022-01-19 11:43:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][170/1251]	eta 0:42:00 lr 0.000902	time 2.1238 (2.3315)	loss 4.6087 (3.8404)	grad_norm 1.4816 (1.1587)	
[2022-01-19 11:44:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][180/1251]	eta 0:41:23 lr 0.000902	time 2.1286 (2.3193)	loss 4.3086 (3.8418)	grad_norm 1.0021 (1.1542)	
[2022-01-19 11:44:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][190/1251]	eta 0:40:56 lr 0.000902	time 2.1877 (2.3153)	loss 3.1431 (3.8415)	grad_norm 1.0564 (1.1540)	
[2022-01-19 11:44:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][200/1251]	eta 0:40:16 lr 0.000902	time 1.6130 (2.2996)	loss 3.6926 (3.8469)	grad_norm 1.0861 (1.1535)	
[2022-01-19 11:45:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][210/1251]	eta 0:39:53 lr 0.000902	time 2.3899 (2.2991)	loss 4.3525 (3.8521)	grad_norm 1.4738 (1.1572)	
[2022-01-19 11:45:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][220/1251]	eta 0:39:17 lr 0.000902	time 1.4904 (2.2869)	loss 4.3910 (3.8421)	grad_norm 1.1723 (1.1580)	
[2022-01-19 11:46:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][230/1251]	eta 0:38:50 lr 0.000902	time 2.1847 (2.2822)	loss 3.9984 (3.8624)	grad_norm 1.2938 (1.1598)	
[2022-01-19 11:46:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][240/1251]	eta 0:38:20 lr 0.000902	time 2.2020 (2.2758)	loss 4.2060 (3.8638)	grad_norm 1.1092 (1.1594)	
[2022-01-19 11:46:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][250/1251]	eta 0:37:56 lr 0.000902	time 1.5273 (2.2738)	loss 3.6726 (3.8556)	grad_norm 1.1476 (1.1599)	
[2022-01-19 11:47:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][260/1251]	eta 0:37:30 lr 0.000902	time 2.6786 (2.2708)	loss 3.5105 (3.8472)	grad_norm 1.0733 (1.1573)	
[2022-01-19 11:47:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][270/1251]	eta 0:37:10 lr 0.000902	time 2.0619 (2.2733)	loss 3.8449 (3.8515)	grad_norm 1.0043 (1.1576)	
[2022-01-19 11:47:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][280/1251]	eta 0:36:48 lr 0.000902	time 2.8714 (2.2742)	loss 3.5143 (3.8579)	grad_norm 1.0123 (1.1572)	
[2022-01-19 11:48:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][290/1251]	eta 0:36:25 lr 0.000902	time 1.8758 (2.2741)	loss 4.1802 (3.8592)	grad_norm 1.7383 (1.1608)	
[2022-01-19 11:48:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][300/1251]	eta 0:35:56 lr 0.000902	time 2.0899 (2.2676)	loss 4.3936 (3.8560)	grad_norm 1.0144 (1.1616)	
[2022-01-19 11:48:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][310/1251]	eta 0:35:27 lr 0.000902	time 1.5919 (2.2604)	loss 2.7052 (3.8527)	grad_norm 1.0005 (1.1569)	
[2022-01-19 11:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][320/1251]	eta 0:34:55 lr 0.000902	time 1.7424 (2.2508)	loss 4.3471 (3.8607)	grad_norm 1.0129 (1.1540)	
[2022-01-19 11:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][330/1251]	eta 0:34:32 lr 0.000902	time 2.8312 (2.2503)	loss 3.2400 (3.8568)	grad_norm 1.1861 (1.1542)	
[2022-01-19 11:50:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][340/1251]	eta 0:34:08 lr 0.000902	time 2.5267 (2.2483)	loss 4.7209 (3.8515)	grad_norm 1.0281 (1.1547)	
[2022-01-19 11:50:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][350/1251]	eta 0:33:41 lr 0.000902	time 1.9692 (2.2432)	loss 3.8596 (3.8500)	grad_norm 1.2049 (1.1532)	
[2022-01-19 11:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][360/1251]	eta 0:33:17 lr 0.000902	time 2.2375 (2.2413)	loss 3.5115 (3.8483)	grad_norm 1.1323 (1.1530)	
[2022-01-19 11:51:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][370/1251]	eta 0:32:53 lr 0.000901	time 2.8927 (2.2406)	loss 4.2566 (3.8543)	grad_norm 1.2138 (1.1534)	
[2022-01-19 11:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][380/1251]	eta 0:32:30 lr 0.000901	time 2.4242 (2.2391)	loss 3.4189 (3.8580)	grad_norm 1.1120 (1.1558)	
[2022-01-19 11:51:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][390/1251]	eta 0:32:05 lr 0.000901	time 2.1155 (2.2364)	loss 3.2082 (3.8578)	grad_norm 1.1639 (1.1572)	
[2022-01-19 11:52:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][400/1251]	eta 0:31:46 lr 0.000901	time 3.1519 (2.2406)	loss 4.2267 (3.8565)	grad_norm 1.1200 (1.1574)	
[2022-01-19 11:52:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][410/1251]	eta 0:31:24 lr 0.000901	time 2.3304 (2.2413)	loss 3.3803 (3.8548)	grad_norm 1.1149 (1.1564)	
[2022-01-19 11:52:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][420/1251]	eta 0:31:00 lr 0.000901	time 2.1504 (2.2392)	loss 3.0066 (3.8559)	grad_norm 1.1546 (1.1560)	
[2022-01-19 11:53:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][430/1251]	eta 0:30:36 lr 0.000901	time 2.2189 (2.2363)	loss 3.6949 (3.8538)	grad_norm 0.9655 (1.1540)	
[2022-01-19 11:53:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][440/1251]	eta 0:30:11 lr 0.000901	time 2.5939 (2.2331)	loss 3.3896 (3.8520)	grad_norm 1.2931 (1.1540)	
[2022-01-19 11:54:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][450/1251]	eta 0:29:46 lr 0.000901	time 2.1407 (2.2298)	loss 4.1094 (3.8509)	grad_norm 0.9886 (1.1528)	
[2022-01-19 11:54:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][460/1251]	eta 0:29:21 lr 0.000901	time 2.4750 (2.2275)	loss 4.1245 (3.8513)	grad_norm 1.3216 (1.1533)	
[2022-01-19 11:54:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][470/1251]	eta 0:29:00 lr 0.000901	time 1.9211 (2.2282)	loss 4.4651 (3.8543)	grad_norm 1.4047 (1.1525)	
[2022-01-19 11:55:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][480/1251]	eta 0:28:38 lr 0.000901	time 2.6997 (2.2287)	loss 2.8982 (3.8508)	grad_norm 1.2180 (1.1521)	
[2022-01-19 11:55:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][490/1251]	eta 0:28:14 lr 0.000901	time 1.7918 (2.2268)	loss 3.1665 (3.8542)	grad_norm 1.0057 (1.1510)	
[2022-01-19 11:55:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][500/1251]	eta 0:27:52 lr 0.000901	time 1.8703 (2.2274)	loss 2.5196 (3.8557)	grad_norm 1.0999 (1.1513)	
[2022-01-19 11:56:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][510/1251]	eta 0:27:30 lr 0.000901	time 2.1535 (2.2275)	loss 4.6815 (3.8587)	grad_norm 1.0693 (1.1505)	
[2022-01-19 11:56:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][520/1251]	eta 0:27:08 lr 0.000901	time 2.1524 (2.2279)	loss 4.6109 (3.8637)	grad_norm 1.2394 (1.1501)	
[2022-01-19 11:56:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][530/1251]	eta 0:26:45 lr 0.000901	time 2.2188 (2.2265)	loss 4.3279 (3.8647)	grad_norm 1.2241 (1.1514)	
[2022-01-19 11:57:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][540/1251]	eta 0:26:20 lr 0.000901	time 1.8981 (2.2229)	loss 3.6277 (3.8629)	grad_norm 1.2134 (1.1539)	
[2022-01-19 11:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][550/1251]	eta 0:25:55 lr 0.000901	time 1.8382 (2.2184)	loss 4.5403 (3.8665)	grad_norm 1.2789 (1.1541)	
[2022-01-19 11:57:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][560/1251]	eta 0:25:31 lr 0.000901	time 2.4624 (2.2165)	loss 4.6231 (3.8689)	grad_norm 1.3088 (1.1549)	
[2022-01-19 11:58:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][570/1251]	eta 0:25:09 lr 0.000901	time 2.4075 (2.2167)	loss 3.6307 (3.8706)	grad_norm 1.4447 (1.1550)	
[2022-01-19 11:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][580/1251]	eta 0:24:47 lr 0.000901	time 2.3151 (2.2165)	loss 3.8871 (3.8732)	grad_norm 1.1297 (1.1545)	
[2022-01-19 11:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][590/1251]	eta 0:24:25 lr 0.000901	time 2.1651 (2.2172)	loss 4.2146 (3.8738)	grad_norm 1.0907 (1.1539)	
[2022-01-19 11:59:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][600/1251]	eta 0:24:04 lr 0.000901	time 2.7077 (2.2185)	loss 3.4698 (3.8728)	grad_norm 0.8652 (1.1534)	
[2022-01-19 11:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][610/1251]	eta 0:23:42 lr 0.000901	time 2.0792 (2.2185)	loss 4.4968 (3.8727)	grad_norm 1.3478 (1.1544)	
[2022-01-19 12:00:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][620/1251]	eta 0:23:19 lr 0.000901	time 2.1310 (2.2178)	loss 3.7754 (3.8712)	grad_norm 1.3096 (1.1548)	
[2022-01-19 12:00:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][630/1251]	eta 0:22:56 lr 0.000901	time 2.6303 (2.2168)	loss 4.6114 (3.8739)	grad_norm 1.1465 (1.1559)	
[2022-01-19 12:00:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][640/1251]	eta 0:22:34 lr 0.000901	time 2.6685 (2.2160)	loss 3.3874 (3.8715)	grad_norm 1.0976 (1.1555)	
[2022-01-19 12:01:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][650/1251]	eta 0:22:11 lr 0.000901	time 2.2631 (2.2148)	loss 3.1313 (3.8705)	grad_norm 1.0696 (1.1555)	
[2022-01-19 12:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][660/1251]	eta 0:21:48 lr 0.000901	time 2.2771 (2.2143)	loss 2.9833 (3.8681)	grad_norm 1.0743 (1.1547)	
[2022-01-19 12:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][670/1251]	eta 0:21:25 lr 0.000901	time 1.8954 (2.2127)	loss 4.8433 (3.8651)	grad_norm 1.2175 (1.1548)	
[2022-01-19 12:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][680/1251]	eta 0:21:04 lr 0.000901	time 3.0213 (2.2144)	loss 4.1619 (3.8656)	grad_norm 1.0484 (1.1548)	
[2022-01-19 12:02:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][690/1251]	eta 0:20:42 lr 0.000901	time 2.6727 (2.2153)	loss 4.3543 (3.8644)	grad_norm 1.0090 (1.1536)	
[2022-01-19 12:03:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][700/1251]	eta 0:20:20 lr 0.000901	time 2.9862 (2.2154)	loss 3.3213 (3.8647)	grad_norm 1.0859 (1.1525)	
[2022-01-19 12:03:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][710/1251]	eta 0:19:57 lr 0.000901	time 2.2372 (2.2141)	loss 3.8420 (3.8642)	grad_norm 1.0072 (1.1522)	
[2022-01-19 12:03:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][720/1251]	eta 0:19:35 lr 0.000901	time 1.9871 (2.2129)	loss 3.6444 (3.8642)	grad_norm 1.2692 (1.1525)	
[2022-01-19 12:04:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][730/1251]	eta 0:19:11 lr 0.000901	time 2.0208 (2.2110)	loss 4.2435 (3.8647)	grad_norm 1.3119 (1.1528)	
[2022-01-19 12:04:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][740/1251]	eta 0:18:48 lr 0.000901	time 1.6053 (2.2090)	loss 4.5193 (3.8662)	grad_norm 1.1780 (1.1530)	
[2022-01-19 12:04:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][750/1251]	eta 0:18:26 lr 0.000901	time 1.9046 (2.2084)	loss 4.3918 (3.8646)	grad_norm 1.1165 (1.1529)	
[2022-01-19 12:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][760/1251]	eta 0:18:04 lr 0.000901	time 2.1272 (2.2095)	loss 4.2112 (3.8684)	grad_norm 1.2058 (1.1527)	
[2022-01-19 12:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][770/1251]	eta 0:17:42 lr 0.000900	time 2.2362 (2.2081)	loss 4.3234 (3.8708)	grad_norm 0.9701 (1.1520)	
[2022-01-19 12:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][780/1251]	eta 0:17:18 lr 0.000900	time 2.1995 (2.2059)	loss 3.6094 (3.8703)	grad_norm 1.2049 (1.1522)	
[2022-01-19 12:06:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][790/1251]	eta 0:16:56 lr 0.000900	time 1.4793 (2.2050)	loss 3.7723 (3.8723)	grad_norm 1.1671 (1.1532)	
[2022-01-19 12:06:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][800/1251]	eta 0:16:35 lr 0.000900	time 1.8543 (2.2073)	loss 4.1145 (3.8725)	grad_norm 1.0426 (1.1529)	
[2022-01-19 12:07:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][810/1251]	eta 0:16:13 lr 0.000900	time 2.7801 (2.2082)	loss 4.1003 (3.8735)	grad_norm 0.8765 (1.1522)	
[2022-01-19 12:07:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][820/1251]	eta 0:15:51 lr 0.000900	time 1.8269 (2.2078)	loss 3.4004 (3.8700)	grad_norm 1.6078 (1.1523)	
[2022-01-19 12:07:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][830/1251]	eta 0:15:29 lr 0.000900	time 1.8808 (2.2067)	loss 4.2470 (3.8714)	grad_norm 1.0250 (1.1531)	
[2022-01-19 12:08:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][840/1251]	eta 0:15:06 lr 0.000900	time 1.8930 (2.2058)	loss 3.7911 (3.8714)	grad_norm 1.1116 (1.1536)	
[2022-01-19 12:08:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][850/1251]	eta 0:14:44 lr 0.000900	time 2.7639 (2.2052)	loss 2.8022 (3.8720)	grad_norm 1.1588 (1.1537)	
[2022-01-19 12:08:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][860/1251]	eta 0:14:22 lr 0.000900	time 2.2660 (2.2066)	loss 3.9798 (3.8764)	grad_norm 1.4247 (1.1550)	
[2022-01-19 12:09:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][870/1251]	eta 0:14:00 lr 0.000900	time 1.9468 (2.2050)	loss 3.5420 (3.8781)	grad_norm 1.0109 (1.1545)	
[2022-01-19 12:09:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][880/1251]	eta 0:13:38 lr 0.000900	time 2.1569 (2.2054)	loss 4.5738 (3.8787)	grad_norm 1.1338 (1.1553)	
[2022-01-19 12:10:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][890/1251]	eta 0:13:16 lr 0.000900	time 2.6255 (2.2061)	loss 4.3348 (3.8801)	grad_norm 1.0931 (1.1558)	
[2022-01-19 12:10:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][900/1251]	eta 0:12:54 lr 0.000900	time 2.1027 (2.2066)	loss 4.3210 (3.8816)	grad_norm 1.0232 (1.1551)	
[2022-01-19 12:10:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][910/1251]	eta 0:12:31 lr 0.000900	time 1.6391 (2.2041)	loss 2.7728 (3.8795)	grad_norm 1.3606 (1.1549)	
[2022-01-19 12:11:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][920/1251]	eta 0:12:09 lr 0.000900	time 1.8329 (2.2030)	loss 4.8401 (3.8834)	grad_norm 1.1130 (1.1540)	
[2022-01-19 12:11:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][930/1251]	eta 0:11:46 lr 0.000900	time 1.5508 (2.2018)	loss 3.2139 (3.8828)	grad_norm 1.0747 (1.1536)	
[2022-01-19 12:11:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][940/1251]	eta 0:11:24 lr 0.000900	time 2.4301 (2.2017)	loss 2.8270 (3.8837)	grad_norm 1.1814 (1.1544)	
[2022-01-19 12:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][950/1251]	eta 0:11:02 lr 0.000900	time 1.8969 (2.2011)	loss 3.2745 (3.8832)	grad_norm 1.3303 (1.1543)	
[2022-01-19 12:12:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][960/1251]	eta 0:10:40 lr 0.000900	time 2.2214 (2.2008)	loss 3.2717 (3.8847)	grad_norm 0.9756 (1.1540)	
[2022-01-19 12:12:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][970/1251]	eta 0:10:18 lr 0.000900	time 1.8588 (2.2009)	loss 3.6979 (3.8848)	grad_norm 1.3730 (1.1539)	
[2022-01-19 12:13:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][980/1251]	eta 0:09:56 lr 0.000900	time 1.5476 (2.2002)	loss 4.3267 (3.8838)	grad_norm 1.0793 (1.1535)	
[2022-01-19 12:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][990/1251]	eta 0:09:33 lr 0.000900	time 1.9360 (2.1981)	loss 4.2302 (3.8843)	grad_norm 1.3090 (1.1534)	
[2022-01-19 12:13:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1000/1251]	eta 0:09:11 lr 0.000900	time 1.8573 (2.1977)	loss 4.1656 (3.8828)	grad_norm 1.1357 (1.1531)	
[2022-01-19 12:14:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1010/1251]	eta 0:08:49 lr 0.000900	time 1.8667 (2.1979)	loss 3.8352 (3.8835)	grad_norm 1.1505 (1.1528)	
[2022-01-19 12:14:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1020/1251]	eta 0:08:27 lr 0.000900	time 1.9135 (2.1978)	loss 3.7376 (3.8849)	grad_norm 1.2283 (1.1528)	
[2022-01-19 12:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1030/1251]	eta 0:08:06 lr 0.000900	time 2.1938 (2.1995)	loss 4.2872 (3.8851)	grad_norm 1.2436 (1.1532)	
[2022-01-19 12:15:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1040/1251]	eta 0:07:44 lr 0.000900	time 2.1768 (2.1993)	loss 4.6057 (3.8871)	grad_norm 1.2078 (1.1536)	
[2022-01-19 12:15:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1050/1251]	eta 0:07:22 lr 0.000900	time 1.5376 (2.1998)	loss 2.9335 (3.8878)	grad_norm 1.1042 (1.1527)	
[2022-01-19 12:16:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1060/1251]	eta 0:07:00 lr 0.000900	time 2.4166 (2.2010)	loss 3.1967 (3.8865)	grad_norm 1.1648 (1.1526)	
[2022-01-19 12:16:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1070/1251]	eta 0:06:38 lr 0.000900	time 2.2000 (2.2012)	loss 4.5560 (3.8866)	grad_norm 1.0905 (1.1522)	
[2022-01-19 12:16:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1080/1251]	eta 0:06:16 lr 0.000900	time 1.9517 (2.2006)	loss 3.9163 (3.8879)	grad_norm 1.2676 (1.1520)	
[2022-01-19 12:17:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1090/1251]	eta 0:05:54 lr 0.000900	time 1.8695 (2.1991)	loss 4.1180 (3.8891)	grad_norm 1.2169 (1.1514)	
[2022-01-19 12:17:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1100/1251]	eta 0:05:31 lr 0.000900	time 1.9334 (2.1974)	loss 3.4717 (3.8902)	grad_norm 1.1943 (1.1511)	
[2022-01-19 12:17:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1110/1251]	eta 0:05:09 lr 0.000900	time 2.1713 (2.1956)	loss 4.5161 (3.8917)	grad_norm 1.1079 (1.1507)	
[2022-01-19 12:18:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1120/1251]	eta 0:04:47 lr 0.000900	time 1.9781 (2.1947)	loss 3.7307 (3.8912)	grad_norm 1.2105 (1.1505)	
[2022-01-19 12:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1130/1251]	eta 0:04:25 lr 0.000900	time 2.3007 (2.1955)	loss 3.7517 (3.8871)	grad_norm 1.0006 (1.1500)	
[2022-01-19 12:19:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1140/1251]	eta 0:04:03 lr 0.000900	time 2.1418 (2.1963)	loss 4.3049 (3.8883)	grad_norm 1.0768 (1.1493)	
[2022-01-19 12:19:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1150/1251]	eta 0:03:41 lr 0.000900	time 2.3381 (2.1968)	loss 3.8811 (3.8879)	grad_norm 1.2857 (1.1487)	
[2022-01-19 12:19:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1160/1251]	eta 0:03:20 lr 0.000900	time 3.1583 (2.1981)	loss 4.0931 (3.8895)	grad_norm 1.1910 (1.1487)	
[2022-01-19 12:20:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1170/1251]	eta 0:02:58 lr 0.000899	time 2.1606 (2.1991)	loss 2.2840 (3.8895)	grad_norm 1.0022 (1.1484)	
[2022-01-19 12:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1180/1251]	eta 0:02:36 lr 0.000899	time 2.3756 (2.2002)	loss 4.2731 (3.8893)	grad_norm 1.0146 (1.1484)	
[2022-01-19 12:20:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1190/1251]	eta 0:02:14 lr 0.000899	time 2.3165 (2.2002)	loss 2.7472 (3.8887)	grad_norm 0.9484 (1.1486)	
[2022-01-19 12:21:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1200/1251]	eta 0:01:52 lr 0.000899	time 2.3145 (2.1992)	loss 2.6592 (3.8881)	grad_norm 1.3177 (1.1482)	
[2022-01-19 12:21:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1210/1251]	eta 0:01:30 lr 0.000899	time 3.1010 (2.1990)	loss 3.1522 (3.8871)	grad_norm 1.0486 (1.1478)	
[2022-01-19 12:21:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1220/1251]	eta 0:01:08 lr 0.000899	time 2.1909 (2.1978)	loss 3.1170 (3.8859)	grad_norm 1.0822 (1.1477)	
[2022-01-19 12:22:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1230/1251]	eta 0:00:46 lr 0.000899	time 2.4189 (2.1988)	loss 3.9217 (3.8848)	grad_norm 1.1880 (1.1477)	
[2022-01-19 12:22:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1240/1251]	eta 0:00:24 lr 0.000899	time 1.5734 (2.1972)	loss 4.0803 (3.8845)	grad_norm 1.0685 (1.1477)	
[2022-01-19 12:22:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [61/300][1250/1251]	eta 0:00:02 lr 0.000899	time 1.3234 (2.1922)	loss 3.6387 (3.8830)	grad_norm 1.2125 (1.1476)	
[2022-01-19 12:22:57 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 61 training takes 0:45:42
[2022-01-19 12:23:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.902 (18.902)	Loss 1.2485 (1.2485)	Acc@1 71.289 (71.289)	Acc@5 90.625 (90.625)	
[2022-01-19 12:23:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.528 (3.343)	Loss 1.2065 (1.1980)	Acc@1 72.070 (71.795)	Acc@5 91.406 (91.335)	
[2022-01-19 12:23:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.622 (2.598)	Loss 1.1573 (1.2140)	Acc@1 72.266 (71.666)	Acc@5 91.504 (91.095)	
[2022-01-19 12:24:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.963 (2.306)	Loss 1.2067 (1.2239)	Acc@1 72.852 (71.506)	Acc@5 90.918 (90.984)	
[2022-01-19 12:24:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.772 (2.216)	Loss 1.1629 (1.2304)	Acc@1 73.242 (71.470)	Acc@5 92.090 (90.873)	
[2022-01-19 12:24:35 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 71.460 Acc@5 90.812
[2022-01-19 12:24:35 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 71.5%
[2022-01-19 12:24:35 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 71.46%
[2022-01-19 12:24:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][0/1251]	eta 7:23:59 lr 0.000899	time 21.2946 (21.2946)	loss 3.9585 (3.9585)	grad_norm 1.1042 (1.1042)	
[2022-01-19 12:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][10/1251]	eta 1:22:30 lr 0.000899	time 2.1014 (3.9892)	loss 2.5480 (3.8261)	grad_norm 1.3124 (1.1711)	
[2022-01-19 12:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][20/1251]	eta 1:04:39 lr 0.000899	time 2.6030 (3.1519)	loss 2.7906 (3.7657)	grad_norm 1.2702 (1.1839)	
[2022-01-19 12:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][30/1251]	eta 0:57:27 lr 0.000899	time 1.8638 (2.8232)	loss 2.5354 (3.8479)	grad_norm 1.0976 (1.1653)	
[2022-01-19 12:26:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][40/1251]	eta 0:54:31 lr 0.000899	time 3.5922 (2.7016)	loss 4.2444 (3.8190)	grad_norm 0.9427 (1.1490)	
[2022-01-19 12:26:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][50/1251]	eta 0:52:13 lr 0.000899	time 2.0960 (2.6089)	loss 3.4325 (3.8502)	grad_norm 1.0509 (1.1430)	
[2022-01-19 12:27:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][60/1251]	eta 0:50:58 lr 0.000899	time 2.4356 (2.5684)	loss 4.2084 (3.8617)	grad_norm 1.0091 (1.1363)	
[2022-01-19 12:27:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][70/1251]	eta 0:49:28 lr 0.000899	time 1.5019 (2.5140)	loss 4.0489 (3.8614)	grad_norm 1.2562 (1.1345)	
[2022-01-19 12:27:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][80/1251]	eta 0:48:31 lr 0.000899	time 3.1225 (2.4862)	loss 2.8999 (3.8257)	grad_norm 1.3222 (1.1311)	
[2022-01-19 12:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][90/1251]	eta 0:47:47 lr 0.000899	time 2.5262 (2.4700)	loss 3.9580 (3.8127)	grad_norm 1.2461 (1.1380)	
[2022-01-19 12:28:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][100/1251]	eta 0:46:32 lr 0.000899	time 2.2427 (2.4261)	loss 4.3347 (3.7984)	grad_norm 1.0563 (1.1358)	
[2022-01-19 12:29:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][110/1251]	eta 0:45:20 lr 0.000899	time 1.9284 (2.3841)	loss 4.0549 (3.8012)	grad_norm 1.1008 (1.1333)	
[2022-01-19 12:29:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][120/1251]	eta 0:44:27 lr 0.000899	time 2.6818 (2.3590)	loss 3.6318 (3.8062)	grad_norm 1.5244 (1.1315)	
[2022-01-19 12:29:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][130/1251]	eta 0:43:40 lr 0.000899	time 1.9238 (2.3376)	loss 3.5929 (3.7856)	grad_norm 1.2473 (1.1327)	
[2022-01-19 12:30:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][140/1251]	eta 0:43:08 lr 0.000899	time 1.6664 (2.3297)	loss 4.3693 (3.7822)	grad_norm 1.1188 (1.1366)	
[2022-01-19 12:30:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][150/1251]	eta 0:42:48 lr 0.000899	time 1.8839 (2.3325)	loss 4.4429 (3.7799)	grad_norm 1.0993 (1.1372)	
[2022-01-19 12:30:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][160/1251]	eta 0:42:28 lr 0.000899	time 2.9830 (2.3356)	loss 4.7655 (3.7755)	grad_norm 1.2317 (1.1414)	
[2022-01-19 12:31:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][170/1251]	eta 0:42:05 lr 0.000899	time 2.3959 (2.3366)	loss 2.9240 (3.7616)	grad_norm 1.0696 (1.1390)	
[2022-01-19 12:31:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][180/1251]	eta 0:41:37 lr 0.000899	time 1.8439 (2.3324)	loss 4.5535 (3.7754)	grad_norm 1.1184 (1.1395)	
[2022-01-19 12:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][190/1251]	eta 0:41:00 lr 0.000899	time 1.9306 (2.3193)	loss 4.1461 (3.7670)	grad_norm 1.0403 (1.1439)	
[2022-01-19 12:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][200/1251]	eta 0:40:18 lr 0.000899	time 2.2476 (2.3009)	loss 4.1741 (3.7783)	grad_norm 1.0427 (1.1439)	
[2022-01-19 12:32:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][210/1251]	eta 0:39:37 lr 0.000899	time 2.2641 (2.2839)	loss 4.3164 (3.7968)	grad_norm 1.0451 (1.1445)	
[2022-01-19 12:32:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][220/1251]	eta 0:39:05 lr 0.000899	time 2.1574 (2.2745)	loss 3.2424 (3.7937)	grad_norm 1.1269 (1.1410)	
[2022-01-19 12:33:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][230/1251]	eta 0:38:35 lr 0.000899	time 2.1752 (2.2677)	loss 4.7997 (3.7996)	grad_norm 1.1914 (1.1403)	
[2022-01-19 12:33:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][240/1251]	eta 0:38:15 lr 0.000899	time 2.5214 (2.2700)	loss 3.4888 (3.8059)	grad_norm 1.1803 (1.1427)	
[2022-01-19 12:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][250/1251]	eta 0:37:54 lr 0.000899	time 2.4353 (2.2718)	loss 3.7629 (3.8015)	grad_norm 0.9776 (1.1406)	
[2022-01-19 12:34:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][260/1251]	eta 0:37:30 lr 0.000899	time 2.2779 (2.2712)	loss 4.0838 (3.8010)	grad_norm 1.1573 (1.1383)	
[2022-01-19 12:34:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][270/1251]	eta 0:37:09 lr 0.000899	time 1.6495 (2.2722)	loss 2.9850 (3.7915)	grad_norm 1.0245 (1.1385)	
[2022-01-19 12:35:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][280/1251]	eta 0:36:44 lr 0.000899	time 1.8319 (2.2701)	loss 3.6092 (3.7947)	grad_norm 1.1473 (1.1357)	
[2022-01-19 12:35:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][290/1251]	eta 0:36:19 lr 0.000899	time 1.9014 (2.2675)	loss 4.4413 (3.8006)	grad_norm 1.1227 (1.1333)	
[2022-01-19 12:35:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][300/1251]	eta 0:35:54 lr 0.000899	time 2.2764 (2.2659)	loss 4.0957 (3.8051)	grad_norm 1.1434 (1.1324)	
[2022-01-19 12:36:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][310/1251]	eta 0:35:31 lr 0.000899	time 2.5694 (2.2655)	loss 2.7337 (3.8088)	grad_norm 1.1346 (1.1322)	
[2022-01-19 12:36:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][320/1251]	eta 0:35:03 lr 0.000898	time 1.6096 (2.2598)	loss 3.3326 (3.8038)	grad_norm 1.1574 (1.1330)	
[2022-01-19 12:37:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][330/1251]	eta 0:34:40 lr 0.000898	time 1.6552 (2.2585)	loss 3.0819 (3.8046)	grad_norm 1.2084 (1.1339)	
[2022-01-19 12:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][340/1251]	eta 0:34:10 lr 0.000898	time 1.6066 (2.2508)	loss 3.8385 (3.8037)	grad_norm 1.0073 (1.1338)	
[2022-01-19 12:37:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][350/1251]	eta 0:33:46 lr 0.000898	time 1.8539 (2.2490)	loss 4.7512 (3.8045)	grad_norm 1.4304 (1.1382)	
[2022-01-19 12:38:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][360/1251]	eta 0:33:21 lr 0.000898	time 2.2146 (2.2469)	loss 4.2486 (3.8108)	grad_norm 1.3054 (1.1389)	
[2022-01-19 12:38:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][370/1251]	eta 0:32:58 lr 0.000898	time 2.2081 (2.2456)	loss 3.9637 (3.8183)	grad_norm 1.3640 (1.1388)	
[2022-01-19 12:38:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][380/1251]	eta 0:32:32 lr 0.000898	time 1.8567 (2.2415)	loss 3.9871 (3.8222)	grad_norm 1.1990 (1.1413)	
[2022-01-19 12:39:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][390/1251]	eta 0:32:12 lr 0.000898	time 2.2248 (2.2441)	loss 3.5625 (3.8220)	grad_norm 1.0114 (1.1428)	
[2022-01-19 12:39:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][400/1251]	eta 0:31:49 lr 0.000898	time 1.5453 (2.2435)	loss 4.2872 (3.8236)	grad_norm 1.0488 (1.1417)	
[2022-01-19 12:39:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][410/1251]	eta 0:31:25 lr 0.000898	time 1.8954 (2.2414)	loss 4.3324 (3.8242)	grad_norm 1.4664 (1.1431)	
[2022-01-19 12:40:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][420/1251]	eta 0:30:59 lr 0.000898	time 1.9830 (2.2380)	loss 4.6277 (3.8276)	grad_norm 1.0229 (1.1443)	
[2022-01-19 12:40:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][430/1251]	eta 0:30:37 lr 0.000898	time 2.0450 (2.2386)	loss 4.1789 (3.8252)	grad_norm 1.1751 (1.1424)	
[2022-01-19 12:41:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][440/1251]	eta 0:30:15 lr 0.000898	time 2.9664 (2.2384)	loss 3.0174 (3.8202)	grad_norm 1.1634 (1.1416)	
[2022-01-19 12:41:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][450/1251]	eta 0:29:49 lr 0.000898	time 2.0271 (2.2335)	loss 2.9081 (3.8176)	grad_norm 1.0511 (1.1424)	
[2022-01-19 12:41:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][460/1251]	eta 0:29:23 lr 0.000898	time 2.1561 (2.2296)	loss 3.5768 (3.8178)	grad_norm 1.1157 (1.1424)	
[2022-01-19 12:42:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][470/1251]	eta 0:29:03 lr 0.000898	time 2.7830 (2.2328)	loss 4.4912 (3.8212)	grad_norm 0.9695 (1.1422)	
[2022-01-19 12:42:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][480/1251]	eta 0:28:45 lr 0.000898	time 2.8263 (2.2377)	loss 3.8965 (3.8224)	grad_norm 1.1440 (1.1437)	
[2022-01-19 12:42:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][490/1251]	eta 0:28:21 lr 0.000898	time 1.8224 (2.2355)	loss 4.2901 (3.8247)	grad_norm 1.2358 (1.1429)	
[2022-01-19 12:43:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][500/1251]	eta 0:27:58 lr 0.000898	time 1.7175 (2.2356)	loss 3.8495 (3.8293)	grad_norm 1.1304 (1.1425)	
[2022-01-19 12:43:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][510/1251]	eta 0:27:35 lr 0.000898	time 2.2577 (2.2336)	loss 4.3242 (3.8281)	grad_norm 0.9567 (1.1427)	
[2022-01-19 12:43:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][520/1251]	eta 0:27:08 lr 0.000898	time 1.9385 (2.2284)	loss 4.3168 (3.8282)	grad_norm 1.0935 (1.1438)	
[2022-01-19 12:44:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][530/1251]	eta 0:26:43 lr 0.000898	time 1.5377 (2.2235)	loss 4.1940 (3.8290)	grad_norm 1.1847 (1.1451)	
[2022-01-19 12:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][540/1251]	eta 0:26:19 lr 0.000898	time 1.7460 (2.2212)	loss 3.5675 (3.8333)	grad_norm 1.1301 (1.1467)	
[2022-01-19 12:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][550/1251]	eta 0:25:54 lr 0.000898	time 1.4309 (2.2171)	loss 4.2359 (3.8338)	grad_norm 1.1007 (1.1459)	
[2022-01-19 12:45:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][560/1251]	eta 0:25:33 lr 0.000898	time 2.7068 (2.2199)	loss 4.3401 (3.8342)	grad_norm 1.1469 (1.1460)	
[2022-01-19 12:45:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][570/1251]	eta 0:25:12 lr 0.000898	time 2.5711 (2.2207)	loss 4.3958 (3.8365)	grad_norm 1.4250 (1.1469)	
[2022-01-19 12:46:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][580/1251]	eta 0:24:50 lr 0.000898	time 1.8973 (2.2215)	loss 3.2817 (3.8382)	grad_norm 1.0992 (1.1460)	
[2022-01-19 12:46:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][590/1251]	eta 0:24:28 lr 0.000898	time 1.4544 (2.2214)	loss 4.2775 (3.8390)	grad_norm 1.5843 (1.1465)	
[2022-01-19 12:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][600/1251]	eta 0:24:06 lr 0.000898	time 2.2728 (2.2219)	loss 3.5942 (3.8417)	grad_norm 1.0003 (1.1472)	
[2022-01-19 12:47:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][610/1251]	eta 0:23:43 lr 0.000898	time 2.7591 (2.2213)	loss 4.2771 (3.8467)	grad_norm 1.1156 (1.1487)	
[2022-01-19 12:47:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][620/1251]	eta 0:23:19 lr 0.000898	time 1.5538 (2.2183)	loss 2.5622 (3.8479)	grad_norm 1.2330 (1.1488)	
[2022-01-19 12:47:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][630/1251]	eta 0:22:57 lr 0.000898	time 2.2261 (2.2180)	loss 4.0993 (3.8518)	grad_norm 1.2458 (1.1487)	
[2022-01-19 12:48:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][640/1251]	eta 0:22:35 lr 0.000898	time 2.4803 (2.2177)	loss 3.2702 (3.8470)	grad_norm 1.1590 (1.1481)	
[2022-01-19 12:48:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][650/1251]	eta 0:22:13 lr 0.000898	time 2.3563 (2.2187)	loss 3.9938 (3.8463)	grad_norm 1.0167 (1.1474)	
[2022-01-19 12:49:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][660/1251]	eta 0:21:50 lr 0.000898	time 1.9921 (2.2182)	loss 3.8643 (3.8506)	grad_norm 1.0067 (1.1480)	
[2022-01-19 12:49:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][670/1251]	eta 0:21:28 lr 0.000898	time 1.6892 (2.2177)	loss 2.9792 (3.8506)	grad_norm 1.2261 (1.1485)	
[2022-01-19 12:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][680/1251]	eta 0:21:05 lr 0.000898	time 1.9403 (2.2169)	loss 4.7380 (3.8533)	grad_norm 1.5500 (1.1496)	
[2022-01-19 12:50:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][690/1251]	eta 0:20:43 lr 0.000898	time 2.2429 (2.2159)	loss 4.3644 (3.8483)	grad_norm 1.2219 (1.1500)	
[2022-01-19 12:50:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][700/1251]	eta 0:20:19 lr 0.000898	time 1.9373 (2.2130)	loss 4.0651 (3.8471)	grad_norm 1.2402 (1.1498)	
[2022-01-19 12:50:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][710/1251]	eta 0:19:56 lr 0.000897	time 2.1906 (2.2120)	loss 3.4589 (3.8455)	grad_norm 1.2121 (1.1503)	
[2022-01-19 12:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][720/1251]	eta 0:19:34 lr 0.000897	time 2.1435 (2.2127)	loss 4.2507 (3.8451)	grad_norm 1.3445 (1.1517)	
[2022-01-19 12:51:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][730/1251]	eta 0:19:12 lr 0.000897	time 2.2545 (2.2124)	loss 3.7973 (3.8441)	grad_norm 0.9898 (1.1520)	
[2022-01-19 12:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][740/1251]	eta 0:18:50 lr 0.000897	time 2.0905 (2.2130)	loss 3.6789 (3.8483)	grad_norm 1.1192 (1.1522)	
[2022-01-19 12:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][750/1251]	eta 0:18:28 lr 0.000897	time 1.9117 (2.2132)	loss 4.6891 (3.8493)	grad_norm 1.2506 (1.1535)	
[2022-01-19 12:52:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][760/1251]	eta 0:18:06 lr 0.000897	time 2.2807 (2.2124)	loss 4.3386 (3.8518)	grad_norm 1.0524 (1.1537)	
[2022-01-19 12:53:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][770/1251]	eta 0:17:43 lr 0.000897	time 1.8570 (2.2104)	loss 4.2246 (3.8527)	grad_norm 1.1694 (1.1532)	
[2022-01-19 12:53:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][780/1251]	eta 0:17:20 lr 0.000897	time 2.2258 (2.2095)	loss 4.1045 (3.8500)	grad_norm 1.0536 (1.1527)	
[2022-01-19 12:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][790/1251]	eta 0:17:00 lr 0.000897	time 2.5429 (2.2126)	loss 3.1117 (3.8485)	grad_norm 1.0604 (1.1527)	
[2022-01-19 12:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][800/1251]	eta 0:16:38 lr 0.000897	time 3.4353 (2.2146)	loss 2.7340 (3.8490)	grad_norm 1.0632 (1.1520)	
[2022-01-19 12:54:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][810/1251]	eta 0:16:16 lr 0.000897	time 1.9151 (2.2133)	loss 4.3140 (3.8522)	grad_norm 1.0306 (1.1513)	
[2022-01-19 12:54:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][820/1251]	eta 0:15:53 lr 0.000897	time 1.8531 (2.2116)	loss 4.0629 (3.8539)	grad_norm 1.1483 (1.1521)	
[2022-01-19 12:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][830/1251]	eta 0:15:30 lr 0.000897	time 2.1231 (2.2101)	loss 3.1712 (3.8511)	grad_norm 1.1071 (1.1535)	
[2022-01-19 12:55:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][840/1251]	eta 0:15:08 lr 0.000897	time 3.3980 (2.2106)	loss 3.4290 (3.8493)	grad_norm 1.1758 (1.1532)	
[2022-01-19 12:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][850/1251]	eta 0:14:46 lr 0.000897	time 2.1719 (2.2097)	loss 3.9913 (3.8511)	grad_norm 0.9752 (1.1529)	
[2022-01-19 12:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][860/1251]	eta 0:14:23 lr 0.000897	time 1.9139 (2.2085)	loss 4.0979 (3.8503)	grad_norm 1.1435 (1.1536)	
[2022-01-19 12:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][870/1251]	eta 0:14:02 lr 0.000897	time 2.2691 (2.2110)	loss 3.2229 (3.8433)	grad_norm 1.4547 (1.1536)	
[2022-01-19 12:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][880/1251]	eta 0:13:40 lr 0.000897	time 3.7336 (2.2110)	loss 4.1448 (3.8439)	grad_norm 1.2772 (1.1541)	
[2022-01-19 12:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][890/1251]	eta 0:13:18 lr 0.000897	time 1.7338 (2.2105)	loss 4.6572 (3.8455)	grad_norm 1.1494 (1.1538)	
[2022-01-19 12:57:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][900/1251]	eta 0:12:55 lr 0.000897	time 2.2392 (2.2108)	loss 3.3117 (3.8443)	grad_norm 1.0026 (1.1535)	
[2022-01-19 12:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][910/1251]	eta 0:12:33 lr 0.000897	time 2.1553 (2.2098)	loss 3.8490 (3.8446)	grad_norm 1.0794 (1.1531)	
[2022-01-19 12:58:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][920/1251]	eta 0:12:11 lr 0.000897	time 2.8204 (2.2102)	loss 4.3945 (3.8450)	grad_norm 1.1683 (1.1531)	
[2022-01-19 12:58:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][930/1251]	eta 0:11:48 lr 0.000897	time 1.8801 (2.2081)	loss 3.6610 (3.8438)	grad_norm 1.0326 (1.1533)	
[2022-01-19 12:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][940/1251]	eta 0:11:27 lr 0.000897	time 2.8812 (2.2094)	loss 3.8233 (3.8431)	grad_norm 1.2549 (1.1536)	
[2022-01-19 12:59:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][950/1251]	eta 0:11:04 lr 0.000897	time 1.5858 (2.2084)	loss 4.0701 (3.8442)	grad_norm 0.9268 (1.1531)	
[2022-01-19 12:59:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][960/1251]	eta 0:10:42 lr 0.000897	time 2.6126 (2.2086)	loss 3.3745 (3.8424)	grad_norm 1.0229 (1.1525)	
[2022-01-19 13:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][970/1251]	eta 0:10:20 lr 0.000897	time 1.8750 (2.2092)	loss 4.0903 (3.8451)	grad_norm 1.2498 (1.1528)	
[2022-01-19 13:00:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][980/1251]	eta 0:09:58 lr 0.000897	time 2.2547 (2.2100)	loss 3.8962 (3.8449)	grad_norm 1.3066 (1.1532)	
[2022-01-19 13:01:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][990/1251]	eta 0:09:36 lr 0.000897	time 1.8726 (2.2092)	loss 4.1094 (3.8463)	grad_norm 1.3664 (1.1537)	
[2022-01-19 13:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1000/1251]	eta 0:09:14 lr 0.000897	time 2.2298 (2.2081)	loss 3.7618 (3.8451)	grad_norm 1.1403 (1.1538)	
[2022-01-19 13:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1010/1251]	eta 0:08:51 lr 0.000897	time 2.0257 (2.2061)	loss 4.3675 (3.8458)	grad_norm 1.0150 (1.1533)	
[2022-01-19 13:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1020/1251]	eta 0:08:29 lr 0.000897	time 2.1541 (2.2065)	loss 4.2019 (3.8492)	grad_norm 1.1016 (1.1532)	
[2022-01-19 13:02:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1030/1251]	eta 0:08:07 lr 0.000897	time 1.5270 (2.2059)	loss 4.6778 (3.8521)	grad_norm 1.3454 (1.1526)	
[2022-01-19 13:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1040/1251]	eta 0:07:45 lr 0.000897	time 1.9580 (2.2069)	loss 4.7252 (3.8515)	grad_norm 1.4981 (1.1525)	
[2022-01-19 13:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1050/1251]	eta 0:07:23 lr 0.000897	time 2.0292 (2.2061)	loss 4.3434 (3.8500)	grad_norm 1.0866 (1.1531)	
[2022-01-19 13:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1060/1251]	eta 0:07:01 lr 0.000897	time 2.2907 (2.2048)	loss 2.5585 (3.8499)	grad_norm 1.2245 (1.1527)	
[2022-01-19 13:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1070/1251]	eta 0:06:38 lr 0.000897	time 1.5944 (2.2041)	loss 4.2109 (3.8487)	grad_norm 1.2160 (1.1526)	
[2022-01-19 13:04:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1080/1251]	eta 0:06:17 lr 0.000897	time 1.8555 (2.2048)	loss 3.7674 (3.8492)	grad_norm 1.4323 (1.1529)	
[2022-01-19 13:04:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1090/1251]	eta 0:05:54 lr 0.000897	time 2.5045 (2.2043)	loss 4.2983 (3.8504)	grad_norm 1.1403 (1.1524)	
[2022-01-19 13:05:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1100/1251]	eta 0:05:32 lr 0.000897	time 2.4312 (2.2043)	loss 3.9946 (3.8517)	grad_norm 1.2098 (1.1521)	
[2022-01-19 13:05:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1110/1251]	eta 0:05:10 lr 0.000896	time 2.5110 (2.2048)	loss 3.3578 (3.8525)	grad_norm 1.1838 (1.1518)	
[2022-01-19 13:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1120/1251]	eta 0:04:48 lr 0.000896	time 2.1665 (2.2053)	loss 3.8533 (3.8527)	grad_norm 1.2665 (1.1522)	
[2022-01-19 13:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1130/1251]	eta 0:04:26 lr 0.000896	time 1.9414 (2.2041)	loss 4.2620 (3.8539)	grad_norm 0.9945 (1.1527)	
[2022-01-19 13:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1140/1251]	eta 0:04:04 lr 0.000896	time 1.7508 (2.2024)	loss 4.2114 (3.8549)	grad_norm 1.0130 (1.1521)	
[2022-01-19 13:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1150/1251]	eta 0:03:42 lr 0.000896	time 1.8549 (2.2025)	loss 4.4813 (3.8543)	grad_norm 1.0324 (1.1522)	
[2022-01-19 13:07:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1160/1251]	eta 0:03:20 lr 0.000896	time 2.3739 (2.2034)	loss 2.7856 (3.8539)	grad_norm 1.2321 (1.1527)	
[2022-01-19 13:07:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1170/1251]	eta 0:02:58 lr 0.000896	time 1.6241 (2.2030)	loss 4.0293 (3.8553)	grad_norm 1.1661 (1.1520)	
[2022-01-19 13:07:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1180/1251]	eta 0:02:36 lr 0.000896	time 1.9050 (2.2029)	loss 2.5250 (3.8553)	grad_norm 1.0679 (1.1522)	
[2022-01-19 13:08:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1190/1251]	eta 0:02:14 lr 0.000896	time 2.3683 (2.2028)	loss 3.3517 (3.8575)	grad_norm 1.0832 (1.1520)	
[2022-01-19 13:08:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1200/1251]	eta 0:01:52 lr 0.000896	time 2.1141 (2.2023)	loss 4.3855 (3.8573)	grad_norm 1.1860 (1.1516)	
[2022-01-19 13:09:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1210/1251]	eta 0:01:30 lr 0.000896	time 2.1026 (2.2003)	loss 4.3420 (3.8577)	grad_norm 0.9656 (1.1516)	
[2022-01-19 13:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1220/1251]	eta 0:01:08 lr 0.000896	time 1.9844 (2.1993)	loss 4.1561 (3.8566)	grad_norm 1.0296 (1.1511)	
[2022-01-19 13:09:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1230/1251]	eta 0:00:46 lr 0.000896	time 2.2972 (2.1988)	loss 3.4477 (3.8543)	grad_norm 0.9741 (1.1506)	
[2022-01-19 13:10:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1240/1251]	eta 0:00:24 lr 0.000896	time 2.1072 (2.1986)	loss 4.7680 (3.8523)	grad_norm 1.0372 (1.1501)	
[2022-01-19 13:10:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [62/300][1250/1251]	eta 0:00:02 lr 0.000896	time 1.1710 (2.1935)	loss 4.1358 (3.8538)	grad_norm 1.0942 (1.1497)	
[2022-01-19 13:10:20 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 62 training takes 0:45:44
[2022-01-19 13:10:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.356 (18.356)	Loss 1.2660 (1.2660)	Acc@1 70.020 (70.020)	Acc@5 89.941 (89.941)	
[2022-01-19 13:10:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.593 (3.557)	Loss 1.1631 (1.2006)	Acc@1 72.754 (72.106)	Acc@5 92.090 (90.661)	
[2022-01-19 13:11:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.961 (2.759)	Loss 1.2729 (1.2270)	Acc@1 70.312 (71.647)	Acc@5 89.453 (90.402)	
[2022-01-19 13:11:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.013 (2.442)	Loss 1.1114 (1.2162)	Acc@1 73.926 (71.755)	Acc@5 91.016 (90.612)	
[2022-01-19 13:11:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.549 (2.209)	Loss 1.2330 (1.2164)	Acc@1 70.605 (71.668)	Acc@5 90.234 (90.663)	
[2022-01-19 13:11:57 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 71.532 Acc@5 90.762
[2022-01-19 13:11:57 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 71.5%
[2022-01-19 13:11:57 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 71.53%
[2022-01-19 13:12:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][0/1251]	eta 7:23:01 lr 0.000896	time 21.2479 (21.2479)	loss 4.0373 (4.0373)	grad_norm 1.1460 (1.1460)	
[2022-01-19 13:12:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][10/1251]	eta 1:24:31 lr 0.000896	time 1.8577 (4.0864)	loss 2.6073 (3.6368)	grad_norm 1.0581 (1.1278)	
[2022-01-19 13:13:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][20/1251]	eta 1:05:21 lr 0.000896	time 2.1888 (3.1860)	loss 3.1629 (3.7300)	grad_norm 0.9793 (1.1316)	
[2022-01-19 13:13:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][30/1251]	eta 0:56:39 lr 0.000896	time 1.5866 (2.7839)	loss 3.1166 (3.7923)	grad_norm 1.2634 (1.1433)	
[2022-01-19 13:13:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][40/1251]	eta 0:54:22 lr 0.000896	time 3.8180 (2.6937)	loss 3.2533 (3.8078)	grad_norm 1.0559 (1.1456)	
[2022-01-19 13:14:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][50/1251]	eta 0:51:45 lr 0.000896	time 2.0535 (2.5856)	loss 3.6410 (3.8179)	grad_norm 1.1287 (1.1562)	
[2022-01-19 13:14:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][60/1251]	eta 0:49:52 lr 0.000896	time 2.1995 (2.5128)	loss 3.0894 (3.8340)	grad_norm 0.9979 (1.1499)	
[2022-01-19 13:14:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][70/1251]	eta 0:48:39 lr 0.000896	time 1.6849 (2.4720)	loss 3.6498 (3.8181)	grad_norm 1.3498 (1.1694)	
[2022-01-19 13:15:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][80/1251]	eta 0:48:06 lr 0.000896	time 4.1427 (2.4646)	loss 2.9454 (3.7792)	grad_norm 1.2091 (1.1739)	
[2022-01-19 13:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][90/1251]	eta 0:47:32 lr 0.000896	time 2.0727 (2.4568)	loss 3.9386 (3.8068)	grad_norm 0.9980 (1.1693)	
[2022-01-19 13:16:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][100/1251]	eta 0:46:32 lr 0.000896	time 2.1142 (2.4266)	loss 4.2357 (3.8234)	grad_norm 1.1889 (1.1689)	
[2022-01-19 13:16:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][110/1251]	eta 0:45:42 lr 0.000896	time 1.6774 (2.4033)	loss 4.6225 (3.8423)	grad_norm 1.0798 (1.1693)	
[2022-01-19 13:16:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][120/1251]	eta 0:45:06 lr 0.000896	time 3.0602 (2.3930)	loss 2.7813 (3.8286)	grad_norm 1.4109 (1.1828)	
[2022-01-19 13:17:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][130/1251]	eta 0:44:24 lr 0.000896	time 1.5949 (2.3770)	loss 3.0842 (3.8213)	grad_norm 1.2436 (1.1788)	
[2022-01-19 13:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][140/1251]	eta 0:43:43 lr 0.000896	time 1.7826 (2.3618)	loss 4.3524 (3.8441)	grad_norm 1.5943 (1.1819)	
[2022-01-19 13:17:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][150/1251]	eta 0:43:01 lr 0.000896	time 1.8802 (2.3451)	loss 3.8058 (3.8315)	grad_norm 1.1906 (1.1826)	
[2022-01-19 13:18:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][160/1251]	eta 0:42:13 lr 0.000896	time 1.9154 (2.3223)	loss 4.2841 (3.8122)	grad_norm 1.2459 (1.1825)	
[2022-01-19 13:18:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][170/1251]	eta 0:41:31 lr 0.000896	time 1.6971 (2.3051)	loss 4.6130 (3.8136)	grad_norm 1.2085 (1.1867)	
[2022-01-19 13:18:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][180/1251]	eta 0:41:00 lr 0.000896	time 2.4993 (2.2972)	loss 3.8554 (3.8170)	grad_norm 1.2182 (1.1845)	
[2022-01-19 13:19:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][190/1251]	eta 0:40:19 lr 0.000896	time 1.5653 (2.2806)	loss 4.0411 (3.8136)	grad_norm 1.2594 (1.1834)	
[2022-01-19 13:19:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][200/1251]	eta 0:39:50 lr 0.000896	time 2.1912 (2.2747)	loss 3.8278 (3.8129)	grad_norm 1.1369 (1.1856)	
[2022-01-19 13:19:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][210/1251]	eta 0:39:30 lr 0.000896	time 1.8700 (2.2768)	loss 2.7744 (3.8154)	grad_norm 1.0896 (1.1853)	
[2022-01-19 13:20:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][220/1251]	eta 0:39:14 lr 0.000896	time 2.6278 (2.2839)	loss 4.6453 (3.8170)	grad_norm 1.0784 (1.1844)	
[2022-01-19 13:20:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][230/1251]	eta 0:38:55 lr 0.000896	time 2.8629 (2.2877)	loss 3.8918 (3.8284)	grad_norm 1.1310 (1.1850)	
[2022-01-19 13:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][240/1251]	eta 0:38:35 lr 0.000896	time 1.8674 (2.2900)	loss 4.3946 (3.8258)	grad_norm 1.1455 (1.1820)	
[2022-01-19 13:21:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][250/1251]	eta 0:38:17 lr 0.000895	time 2.3296 (2.2949)	loss 2.7090 (3.8282)	grad_norm 1.0811 (1.1804)	
[2022-01-19 13:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][260/1251]	eta 0:37:53 lr 0.000895	time 1.9622 (2.2946)	loss 3.2316 (3.8301)	grad_norm 1.1069 (1.1804)	
[2022-01-19 13:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][270/1251]	eta 0:37:20 lr 0.000895	time 1.8573 (2.2835)	loss 2.8168 (3.8241)	grad_norm 0.9486 (1.1800)	
[2022-01-19 13:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][280/1251]	eta 0:36:44 lr 0.000895	time 1.9498 (2.2699)	loss 3.9369 (3.8169)	grad_norm 0.9714 (1.1785)	
[2022-01-19 13:22:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][290/1251]	eta 0:36:15 lr 0.000895	time 2.2162 (2.2637)	loss 3.8653 (3.8073)	grad_norm 1.0251 (1.1762)	
[2022-01-19 13:23:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][300/1251]	eta 0:35:49 lr 0.000895	time 1.5499 (2.2604)	loss 3.2028 (3.8100)	grad_norm 1.0688 (1.1740)	
[2022-01-19 13:23:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][310/1251]	eta 0:35:27 lr 0.000895	time 1.8805 (2.2608)	loss 4.2104 (3.8115)	grad_norm 1.2069 (1.1745)	
[2022-01-19 13:24:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][320/1251]	eta 0:35:05 lr 0.000895	time 2.2739 (2.2615)	loss 4.6510 (3.8149)	grad_norm 1.5433 (1.1758)	
[2022-01-19 13:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][330/1251]	eta 0:34:42 lr 0.000895	time 1.8868 (2.2614)	loss 3.6117 (3.8138)	grad_norm 1.0531 (1.1772)	
[2022-01-19 13:24:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][340/1251]	eta 0:34:18 lr 0.000895	time 2.8728 (2.2601)	loss 3.5590 (3.8187)	grad_norm 1.0164 (1.1760)	
[2022-01-19 13:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][350/1251]	eta 0:33:53 lr 0.000895	time 1.4883 (2.2565)	loss 4.4526 (3.8226)	grad_norm 1.1965 (1.1741)	
[2022-01-19 13:25:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][360/1251]	eta 0:33:23 lr 0.000895	time 1.9516 (2.2490)	loss 3.9381 (3.8272)	grad_norm 1.0273 (1.1718)	
[2022-01-19 13:25:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][370/1251]	eta 0:32:59 lr 0.000895	time 2.6488 (2.2473)	loss 3.8606 (3.8256)	grad_norm 1.1932 (1.1721)	
[2022-01-19 13:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][380/1251]	eta 0:32:38 lr 0.000895	time 2.8162 (2.2484)	loss 4.0507 (3.8290)	grad_norm 1.1881 (1.1721)	
[2022-01-19 13:26:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][390/1251]	eta 0:32:15 lr 0.000895	time 1.9022 (2.2483)	loss 4.3686 (3.8330)	grad_norm 1.0779 (1.1728)	
[2022-01-19 13:26:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][400/1251]	eta 0:31:50 lr 0.000895	time 2.3806 (2.2449)	loss 3.6705 (3.8354)	grad_norm 1.0017 (1.1711)	
[2022-01-19 13:27:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][410/1251]	eta 0:31:22 lr 0.000895	time 1.7080 (2.2389)	loss 3.9254 (3.8425)	grad_norm 1.2245 (1.1702)	
[2022-01-19 13:27:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][420/1251]	eta 0:31:01 lr 0.000895	time 2.9373 (2.2397)	loss 3.4477 (3.8500)	grad_norm 1.2482 (1.1719)	
[2022-01-19 13:28:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][430/1251]	eta 0:30:37 lr 0.000895	time 1.9385 (2.2382)	loss 4.7521 (3.8518)	grad_norm 1.3888 (1.1728)	
[2022-01-19 13:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][440/1251]	eta 0:30:15 lr 0.000895	time 2.4748 (2.2380)	loss 4.1943 (3.8624)	grad_norm 1.9141 (1.1746)	
[2022-01-19 13:28:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][450/1251]	eta 0:29:53 lr 0.000895	time 2.1878 (2.2388)	loss 4.0451 (3.8622)	grad_norm 1.1653 (1.1761)	
[2022-01-19 13:29:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][460/1251]	eta 0:29:31 lr 0.000895	time 2.1485 (2.2391)	loss 2.6206 (3.8593)	grad_norm 1.2375 (1.1771)	
[2022-01-19 13:29:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][470/1251]	eta 0:29:07 lr 0.000895	time 1.6374 (2.2381)	loss 3.4250 (3.8584)	grad_norm 1.0942 (1.1746)	
[2022-01-19 13:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][480/1251]	eta 0:28:42 lr 0.000895	time 1.6099 (2.2338)	loss 2.8228 (3.8565)	grad_norm 1.3968 (1.1734)	
[2022-01-19 13:30:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][490/1251]	eta 0:28:15 lr 0.000895	time 2.1846 (2.2274)	loss 4.3270 (3.8579)	grad_norm 0.9386 (1.1739)	
[2022-01-19 13:30:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][500/1251]	eta 0:27:49 lr 0.000895	time 1.8705 (2.2235)	loss 3.8445 (3.8632)	grad_norm 0.9589 (1.1736)	
[2022-01-19 13:30:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][510/1251]	eta 0:27:26 lr 0.000895	time 2.2978 (2.2225)	loss 4.3008 (3.8622)	grad_norm 1.1010 (1.1728)	
[2022-01-19 13:31:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][520/1251]	eta 0:27:02 lr 0.000895	time 1.8882 (2.2195)	loss 4.7467 (3.8616)	grad_norm 0.9880 (1.1722)	
[2022-01-19 13:31:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][530/1251]	eta 0:26:41 lr 0.000895	time 2.5674 (2.2210)	loss 4.2296 (3.8644)	grad_norm 0.9966 (1.1700)	
[2022-01-19 13:31:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][540/1251]	eta 0:26:19 lr 0.000895	time 2.5147 (2.2210)	loss 4.3729 (3.8666)	grad_norm 1.1811 (1.1693)	
[2022-01-19 13:32:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][550/1251]	eta 0:25:56 lr 0.000895	time 3.2852 (2.2208)	loss 4.6184 (3.8724)	grad_norm 1.3092 (1.1696)	
[2022-01-19 13:32:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][560/1251]	eta 0:25:33 lr 0.000895	time 2.2315 (2.2195)	loss 3.9239 (3.8747)	grad_norm 1.1287 (1.1708)	
[2022-01-19 13:33:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][570/1251]	eta 0:25:13 lr 0.000895	time 2.7599 (2.2221)	loss 4.1551 (3.8702)	grad_norm 0.9953 (1.1704)	
[2022-01-19 13:33:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][580/1251]	eta 0:24:52 lr 0.000895	time 2.4472 (2.2237)	loss 3.0757 (3.8704)	grad_norm 1.1729 (1.1703)	
[2022-01-19 13:33:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][590/1251]	eta 0:24:33 lr 0.000895	time 3.6939 (2.2287)	loss 3.0818 (3.8667)	grad_norm 0.9822 (1.1683)	
[2022-01-19 13:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][600/1251]	eta 0:24:10 lr 0.000895	time 1.8594 (2.2278)	loss 3.1592 (3.8634)	grad_norm 1.1733 (1.1674)	
[2022-01-19 13:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][610/1251]	eta 0:23:47 lr 0.000895	time 1.7090 (2.2265)	loss 3.8768 (3.8662)	grad_norm 1.2853 (1.1662)	
[2022-01-19 13:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][620/1251]	eta 0:23:23 lr 0.000895	time 1.8465 (2.2240)	loss 4.2350 (3.8728)	grad_norm 1.1586 (1.1648)	
[2022-01-19 13:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][630/1251]	eta 0:23:00 lr 0.000895	time 2.8889 (2.2232)	loss 3.6562 (3.8726)	grad_norm 1.3323 (1.1644)	
[2022-01-19 13:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][640/1251]	eta 0:22:36 lr 0.000894	time 1.9292 (2.2196)	loss 3.9962 (3.8762)	grad_norm 1.3657 (1.1643)	
[2022-01-19 13:36:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][650/1251]	eta 0:22:12 lr 0.000894	time 1.5724 (2.2174)	loss 4.3468 (3.8779)	grad_norm 1.2428 (1.1648)	
[2022-01-19 13:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][660/1251]	eta 0:21:50 lr 0.000894	time 2.1768 (2.2175)	loss 3.3484 (3.8743)	grad_norm 1.0202 (1.1639)	
[2022-01-19 13:36:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][670/1251]	eta 0:21:29 lr 0.000894	time 3.6604 (2.2199)	loss 3.5578 (3.8766)	grad_norm 1.1390 (1.1648)	
[2022-01-19 13:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][680/1251]	eta 0:21:09 lr 0.000894	time 2.5159 (2.2229)	loss 4.2554 (3.8774)	grad_norm 1.4356 (1.1656)	
[2022-01-19 13:37:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][690/1251]	eta 0:20:46 lr 0.000894	time 1.9002 (2.2217)	loss 3.9464 (3.8737)	grad_norm 1.1503 (1.1658)	
[2022-01-19 13:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][700/1251]	eta 0:20:22 lr 0.000894	time 1.6085 (2.2184)	loss 4.2080 (3.8781)	grad_norm 1.1845 (1.1658)	
[2022-01-19 13:38:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][710/1251]	eta 0:19:58 lr 0.000894	time 2.0382 (2.2158)	loss 3.6959 (3.8772)	grad_norm 1.0564 (1.1654)	
[2022-01-19 13:38:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][720/1251]	eta 0:19:36 lr 0.000894	time 2.1844 (2.2155)	loss 4.6219 (3.8748)	grad_norm 1.1160 (1.1645)	
[2022-01-19 13:38:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][730/1251]	eta 0:19:15 lr 0.000894	time 2.0858 (2.2174)	loss 3.8718 (3.8707)	grad_norm 1.0187 (1.1637)	
[2022-01-19 13:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][740/1251]	eta 0:18:53 lr 0.000894	time 2.2360 (2.2186)	loss 3.0819 (3.8673)	grad_norm 1.1413 (1.1647)	
[2022-01-19 13:39:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][750/1251]	eta 0:18:31 lr 0.000894	time 1.8989 (2.2187)	loss 3.8296 (3.8691)	grad_norm 1.0179 (1.1643)	
[2022-01-19 13:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][760/1251]	eta 0:18:08 lr 0.000894	time 1.9513 (2.2173)	loss 3.7045 (3.8702)	grad_norm 1.1221 (1.1631)	
[2022-01-19 13:40:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][770/1251]	eta 0:17:46 lr 0.000894	time 2.7245 (2.2173)	loss 4.3442 (3.8702)	grad_norm 1.2030 (1.1628)	
[2022-01-19 13:40:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][780/1251]	eta 0:17:24 lr 0.000894	time 2.2596 (2.2167)	loss 3.7771 (3.8667)	grad_norm 1.0602 (1.1637)	
[2022-01-19 13:41:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][790/1251]	eta 0:17:02 lr 0.000894	time 2.1207 (2.2171)	loss 4.0276 (3.8676)	grad_norm 1.1532 (1.1629)	
[2022-01-19 13:41:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][800/1251]	eta 0:16:39 lr 0.000894	time 1.6933 (2.2158)	loss 4.3720 (3.8639)	grad_norm 1.2638 (1.1633)	
[2022-01-19 13:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][810/1251]	eta 0:16:16 lr 0.000894	time 2.6465 (2.2135)	loss 4.3674 (3.8661)	grad_norm 1.0028 (1.1627)	
[2022-01-19 13:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][820/1251]	eta 0:15:52 lr 0.000894	time 1.8855 (2.2109)	loss 4.4242 (3.8658)	grad_norm 1.1551 (1.1636)	
[2022-01-19 13:42:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][830/1251]	eta 0:15:29 lr 0.000894	time 2.4899 (2.2090)	loss 4.0676 (3.8634)	grad_norm 0.9778 (1.1642)	
[2022-01-19 13:42:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][840/1251]	eta 0:15:07 lr 0.000894	time 1.6600 (2.2081)	loss 4.5815 (3.8644)	grad_norm 1.0439 (1.1637)	
[2022-01-19 13:43:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][850/1251]	eta 0:14:46 lr 0.000894	time 2.1705 (2.2095)	loss 3.5916 (3.8614)	grad_norm 1.1446 (1.1644)	
[2022-01-19 13:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][860/1251]	eta 0:14:24 lr 0.000894	time 2.2697 (2.2102)	loss 3.7136 (3.8597)	grad_norm 1.0085 (1.1648)	
[2022-01-19 13:44:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][870/1251]	eta 0:14:02 lr 0.000894	time 1.8305 (2.2105)	loss 4.4195 (3.8593)	grad_norm 1.1077 (1.1647)	
[2022-01-19 13:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][880/1251]	eta 0:13:40 lr 0.000894	time 1.9914 (2.2117)	loss 3.9137 (3.8607)	grad_norm 1.2074 (1.1658)	
[2022-01-19 13:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][890/1251]	eta 0:13:18 lr 0.000894	time 2.2695 (2.2123)	loss 4.1432 (3.8574)	grad_norm 1.1619 (1.1654)	
[2022-01-19 13:45:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][900/1251]	eta 0:12:56 lr 0.000894	time 2.2481 (2.2121)	loss 3.6086 (3.8582)	grad_norm 1.0937 (1.1651)	
[2022-01-19 13:45:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][910/1251]	eta 0:12:33 lr 0.000894	time 1.6172 (2.2088)	loss 4.6727 (3.8577)	grad_norm 1.3149 (1.1655)	
[2022-01-19 13:45:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][920/1251]	eta 0:12:10 lr 0.000894	time 2.2623 (2.2074)	loss 4.2964 (3.8557)	grad_norm 1.2683 (1.1654)	
[2022-01-19 13:46:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][930/1251]	eta 0:11:48 lr 0.000894	time 1.8249 (2.2063)	loss 4.6046 (3.8584)	grad_norm 1.1256 (1.1647)	
[2022-01-19 13:46:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][940/1251]	eta 0:11:26 lr 0.000894	time 2.5128 (2.2081)	loss 4.0097 (3.8578)	grad_norm 1.2547 (1.1653)	
[2022-01-19 13:46:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][950/1251]	eta 0:11:04 lr 0.000894	time 1.5645 (2.2081)	loss 3.1232 (3.8565)	grad_norm 0.9628 (1.1648)	
[2022-01-19 13:47:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][960/1251]	eta 0:10:42 lr 0.000894	time 1.9469 (2.2083)	loss 3.4351 (3.8529)	grad_norm 1.0144 (1.1645)	
[2022-01-19 13:47:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][970/1251]	eta 0:10:20 lr 0.000894	time 2.3678 (2.2088)	loss 4.2864 (3.8535)	grad_norm 1.0622 (1.1635)	
[2022-01-19 13:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][980/1251]	eta 0:09:58 lr 0.000894	time 1.8611 (2.2079)	loss 4.4128 (3.8519)	grad_norm 1.0783 (1.1634)	
[2022-01-19 13:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][990/1251]	eta 0:09:36 lr 0.000894	time 1.9166 (2.2078)	loss 4.7107 (3.8528)	grad_norm 1.2063 (1.1632)	
[2022-01-19 13:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1000/1251]	eta 0:09:14 lr 0.000894	time 2.4531 (2.2076)	loss 4.3427 (3.8582)	grad_norm 1.0948 (1.1625)	
[2022-01-19 13:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1010/1251]	eta 0:08:52 lr 0.000894	time 2.4250 (2.2093)	loss 3.8458 (3.8565)	grad_norm 0.9950 (1.1626)	
[2022-01-19 13:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1020/1251]	eta 0:08:30 lr 0.000894	time 2.1235 (2.2087)	loss 3.5154 (3.8565)	grad_norm 1.0336 (1.1624)	
[2022-01-19 13:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1030/1251]	eta 0:08:08 lr 0.000893	time 1.9206 (2.2084)	loss 3.5916 (3.8550)	grad_norm 1.0992 (1.1620)	
[2022-01-19 13:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1040/1251]	eta 0:07:45 lr 0.000893	time 1.6318 (2.2081)	loss 3.8055 (3.8564)	grad_norm 1.4282 (1.1615)	
[2022-01-19 13:50:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1050/1251]	eta 0:07:23 lr 0.000893	time 1.7941 (2.2058)	loss 3.3213 (3.8549)	grad_norm 1.1188 (1.1617)	
[2022-01-19 13:50:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1060/1251]	eta 0:07:00 lr 0.000893	time 2.1603 (2.2035)	loss 3.9861 (3.8551)	grad_norm 0.9982 (1.1611)	
[2022-01-19 13:51:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1070/1251]	eta 0:06:38 lr 0.000893	time 2.2439 (2.2026)	loss 2.9231 (3.8540)	grad_norm 1.1642 (1.1610)	
[2022-01-19 13:51:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1080/1251]	eta 0:06:16 lr 0.000893	time 2.2205 (2.2018)	loss 4.1763 (3.8545)	grad_norm 1.2160 (1.1607)	
[2022-01-19 13:52:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1090/1251]	eta 0:05:54 lr 0.000893	time 2.2547 (2.2043)	loss 4.5367 (3.8560)	grad_norm 1.0950 (1.1610)	
[2022-01-19 13:52:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1100/1251]	eta 0:05:32 lr 0.000893	time 2.1375 (2.2041)	loss 3.5140 (3.8541)	grad_norm 1.2949 (1.1617)	
[2022-01-19 13:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1110/1251]	eta 0:05:11 lr 0.000893	time 3.0657 (2.2065)	loss 4.6148 (3.8551)	grad_norm 1.1242 (1.1609)	
[2022-01-19 13:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1120/1251]	eta 0:04:48 lr 0.000893	time 2.4136 (2.2056)	loss 4.1694 (3.8551)	grad_norm 1.1744 (1.1607)	
[2022-01-19 13:53:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1130/1251]	eta 0:04:26 lr 0.000893	time 1.9337 (2.2047)	loss 3.8306 (3.8552)	grad_norm 1.1973 (1.1610)	
[2022-01-19 13:53:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1140/1251]	eta 0:04:04 lr 0.000893	time 3.0969 (2.2029)	loss 4.1012 (3.8573)	grad_norm 1.2836 (1.1607)	
[2022-01-19 13:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1150/1251]	eta 0:03:42 lr 0.000893	time 2.2286 (2.2017)	loss 3.9803 (3.8565)	grad_norm 1.0508 (1.1600)	
[2022-01-19 13:54:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1160/1251]	eta 0:03:20 lr 0.000893	time 2.1636 (2.2009)	loss 4.0867 (3.8589)	grad_norm 1.1020 (1.1598)	
[2022-01-19 13:54:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1170/1251]	eta 0:02:58 lr 0.000893	time 1.8489 (2.2015)	loss 4.2556 (3.8603)	grad_norm 1.1308 (1.1600)	
[2022-01-19 13:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1180/1251]	eta 0:02:36 lr 0.000893	time 3.3946 (2.2029)	loss 4.0255 (3.8600)	grad_norm 1.0977 (1.1599)	
[2022-01-19 13:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1190/1251]	eta 0:02:14 lr 0.000893	time 2.2738 (2.2046)	loss 4.5809 (3.8605)	grad_norm 1.2932 (1.1605)	
[2022-01-19 13:56:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1200/1251]	eta 0:01:52 lr 0.000893	time 2.2326 (2.2056)	loss 3.1050 (3.8589)	grad_norm 1.1123 (1.1605)	
[2022-01-19 13:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1210/1251]	eta 0:01:30 lr 0.000893	time 2.2161 (2.2055)	loss 4.2392 (3.8606)	grad_norm 1.0975 (1.1604)	
[2022-01-19 13:56:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1220/1251]	eta 0:01:08 lr 0.000893	time 2.2100 (2.2033)	loss 2.8094 (3.8571)	grad_norm 1.0316 (1.1597)	
[2022-01-19 13:57:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1230/1251]	eta 0:00:46 lr 0.000893	time 1.9196 (2.2013)	loss 4.0049 (3.8573)	grad_norm 1.1257 (1.1592)	
[2022-01-19 13:57:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1240/1251]	eta 0:00:24 lr 0.000893	time 1.3599 (2.1995)	loss 2.6728 (3.8567)	grad_norm 1.2884 (1.1592)	
[2022-01-19 13:57:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [63/300][1250/1251]	eta 0:00:02 lr 0.000893	time 1.2224 (2.1939)	loss 3.0112 (3.8544)	grad_norm 1.3154 (1.1590)	
[2022-01-19 13:57:42 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 63 training takes 0:45:45
[2022-01-19 13:58:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.680 (18.680)	Loss 1.2637 (1.2637)	Acc@1 70.508 (70.508)	Acc@5 90.723 (90.723)	
[2022-01-19 13:58:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.310 (3.460)	Loss 1.2286 (1.2706)	Acc@1 71.094 (70.446)	Acc@5 92.383 (90.696)	
[2022-01-19 13:58:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.610 (2.648)	Loss 1.2689 (1.2576)	Acc@1 70.703 (70.861)	Acc@5 89.941 (90.695)	
[2022-01-19 13:58:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.610 (2.303)	Loss 1.1931 (1.2543)	Acc@1 73.242 (71.087)	Acc@5 91.797 (90.653)	
[2022-01-19 13:59:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.576 (2.182)	Loss 1.2684 (1.2512)	Acc@1 70.020 (71.160)	Acc@5 91.016 (90.711)	
[2022-01-19 13:59:19 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 71.220 Acc@5 90.756
[2022-01-19 13:59:19 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 71.2%
[2022-01-19 13:59:19 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 71.53%
[2022-01-19 13:59:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][0/1251]	eta 7:30:59 lr 0.000893	time 21.6307 (21.6307)	loss 3.9226 (3.9226)	grad_norm 1.1066 (1.1066)	
[2022-01-19 14:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][10/1251]	eta 1:26:43 lr 0.000893	time 2.5044 (4.1927)	loss 4.5285 (4.1094)	grad_norm 1.3617 (1.1158)	
[2022-01-19 14:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][20/1251]	eta 1:08:33 lr 0.000893	time 2.4841 (3.3416)	loss 3.9883 (3.9101)	grad_norm 0.9633 (1.1689)	
[2022-01-19 14:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][30/1251]	eta 1:00:35 lr 0.000893	time 2.1878 (2.9771)	loss 2.6538 (3.8751)	grad_norm 1.2599 (1.1854)	
[2022-01-19 14:01:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][40/1251]	eta 0:56:32 lr 0.000893	time 2.2571 (2.8013)	loss 3.4140 (3.7828)	grad_norm 1.0980 (1.1943)	
[2022-01-19 14:01:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][50/1251]	eta 0:54:12 lr 0.000893	time 1.5543 (2.7083)	loss 3.5940 (3.8440)	grad_norm 1.0667 (1.1848)	
[2022-01-19 14:01:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][60/1251]	eta 0:51:38 lr 0.000893	time 1.8988 (2.6020)	loss 4.3503 (3.8755)	grad_norm 1.1110 (1.1712)	
[2022-01-19 14:02:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][70/1251]	eta 0:49:32 lr 0.000893	time 2.5007 (2.5173)	loss 3.9180 (3.8826)	grad_norm 1.1365 (1.1924)	
[2022-01-19 14:02:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][80/1251]	eta 0:48:02 lr 0.000893	time 1.9579 (2.4615)	loss 4.2710 (3.8607)	grad_norm 1.1810 (1.1855)	
[2022-01-19 14:03:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][90/1251]	eta 0:47:01 lr 0.000893	time 1.8827 (2.4299)	loss 3.9934 (3.8407)	grad_norm 1.0865 (1.1819)	
[2022-01-19 14:03:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][100/1251]	eta 0:46:09 lr 0.000893	time 1.4857 (2.4058)	loss 4.0736 (3.8492)	grad_norm 1.1649 (1.1759)	
[2022-01-19 14:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][110/1251]	eta 0:45:10 lr 0.000893	time 2.3723 (2.3760)	loss 2.7064 (3.8101)	grad_norm 1.2185 (1.1675)	
[2022-01-19 14:04:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][120/1251]	eta 0:44:25 lr 0.000893	time 2.1807 (2.3567)	loss 4.0791 (3.7946)	grad_norm 1.4311 (1.1713)	
[2022-01-19 14:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][130/1251]	eta 0:43:55 lr 0.000893	time 1.9503 (2.3513)	loss 3.4790 (3.7876)	grad_norm 1.2022 (1.1689)	
[2022-01-19 14:04:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][140/1251]	eta 0:43:29 lr 0.000893	time 2.1808 (2.3490)	loss 3.9866 (3.7974)	grad_norm 1.5437 (1.1736)	
[2022-01-19 14:05:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][150/1251]	eta 0:43:06 lr 0.000893	time 2.7789 (2.3492)	loss 4.2558 (3.8086)	grad_norm 1.2266 (1.1752)	
[2022-01-19 14:05:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][160/1251]	eta 0:42:35 lr 0.000893	time 2.1231 (2.3424)	loss 4.2009 (3.8106)	grad_norm 1.0485 (1.1738)	
[2022-01-19 14:05:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][170/1251]	eta 0:42:01 lr 0.000892	time 2.0707 (2.3324)	loss 4.3422 (3.8232)	grad_norm 1.2113 (1.1685)	
[2022-01-19 14:06:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][180/1251]	eta 0:41:17 lr 0.000892	time 1.8976 (2.3129)	loss 4.1245 (3.8248)	grad_norm 1.0702 (1.1624)	
[2022-01-19 14:06:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][190/1251]	eta 0:40:41 lr 0.000892	time 2.1547 (2.3012)	loss 4.2152 (3.8338)	grad_norm 1.1483 (1.1605)	
[2022-01-19 14:07:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][200/1251]	eta 0:40:12 lr 0.000892	time 2.8233 (2.2953)	loss 3.5340 (3.8427)	grad_norm 1.1438 (1.1596)	
[2022-01-19 14:07:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][210/1251]	eta 0:39:42 lr 0.000892	time 1.9088 (2.2885)	loss 4.5755 (3.8411)	grad_norm 1.1935 (1.1577)	
[2022-01-19 14:07:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][220/1251]	eta 0:39:12 lr 0.000892	time 2.3014 (2.2817)	loss 4.5649 (3.8412)	grad_norm 1.1038 (1.1601)	
[2022-01-19 14:08:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][230/1251]	eta 0:38:34 lr 0.000892	time 1.9652 (2.2673)	loss 4.2886 (3.8378)	grad_norm 1.4854 (1.1594)	
[2022-01-19 14:08:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][240/1251]	eta 0:38:06 lr 0.000892	time 1.9591 (2.2620)	loss 4.0870 (3.8508)	grad_norm 1.0064 (1.1604)	
[2022-01-19 14:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][250/1251]	eta 0:37:43 lr 0.000892	time 2.0803 (2.2614)	loss 3.3943 (3.8437)	grad_norm 1.1150 (1.1594)	
[2022-01-19 14:09:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][260/1251]	eta 0:37:16 lr 0.000892	time 1.8987 (2.2567)	loss 4.5472 (3.8491)	grad_norm 1.1309 (1.1569)	
[2022-01-19 14:09:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][270/1251]	eta 0:36:52 lr 0.000892	time 2.8223 (2.2556)	loss 3.9024 (3.8628)	grad_norm 1.1238 (1.1567)	
[2022-01-19 14:09:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][280/1251]	eta 0:36:25 lr 0.000892	time 1.7171 (2.2508)	loss 4.4351 (3.8621)	grad_norm 1.1882 (1.1542)	
[2022-01-19 14:10:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][290/1251]	eta 0:36:06 lr 0.000892	time 2.4255 (2.2543)	loss 3.8345 (3.8555)	grad_norm 1.4660 (1.1559)	
[2022-01-19 14:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][300/1251]	eta 0:35:41 lr 0.000892	time 1.9252 (2.2520)	loss 3.6568 (3.8480)	grad_norm 1.1010 (1.1569)	
[2022-01-19 14:10:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][310/1251]	eta 0:35:18 lr 0.000892	time 2.9042 (2.2509)	loss 4.2090 (3.8435)	grad_norm 1.1215 (1.1546)	
[2022-01-19 14:11:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][320/1251]	eta 0:34:52 lr 0.000892	time 1.5269 (2.2480)	loss 3.1466 (3.8426)	grad_norm 1.1989 (1.1532)	
[2022-01-19 14:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][330/1251]	eta 0:34:32 lr 0.000892	time 2.4137 (2.2507)	loss 4.2133 (3.8520)	grad_norm 1.1450 (1.1524)	
[2022-01-19 14:12:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][340/1251]	eta 0:34:05 lr 0.000892	time 1.9835 (2.2455)	loss 4.0393 (3.8488)	grad_norm 1.2100 (1.1534)	
[2022-01-19 14:12:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][350/1251]	eta 0:33:43 lr 0.000892	time 2.5133 (2.2456)	loss 2.9359 (3.8529)	grad_norm 1.1241 (1.1519)	
[2022-01-19 14:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][360/1251]	eta 0:33:15 lr 0.000892	time 1.9328 (2.2402)	loss 3.6916 (3.8510)	grad_norm 1.2871 (1.1535)	
[2022-01-19 14:13:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][370/1251]	eta 0:32:57 lr 0.000892	time 3.2214 (2.2441)	loss 3.5891 (3.8502)	grad_norm 1.4230 (1.1567)	
[2022-01-19 14:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][380/1251]	eta 0:32:30 lr 0.000892	time 1.8486 (2.2393)	loss 3.9669 (3.8477)	grad_norm 1.0654 (1.1583)	
[2022-01-19 14:13:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][390/1251]	eta 0:32:07 lr 0.000892	time 2.5622 (2.2391)	loss 4.1211 (3.8459)	grad_norm 1.6915 (1.1614)	
[2022-01-19 14:14:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][400/1251]	eta 0:31:42 lr 0.000892	time 1.8363 (2.2358)	loss 3.7258 (3.8449)	grad_norm 1.3263 (1.1636)	
[2022-01-19 14:14:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][410/1251]	eta 0:31:22 lr 0.000892	time 2.9346 (2.2385)	loss 3.6782 (3.8453)	grad_norm 1.2394 (1.1644)	
[2022-01-19 14:15:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][420/1251]	eta 0:30:57 lr 0.000892	time 1.8114 (2.2347)	loss 3.2261 (3.8395)	grad_norm 1.1427 (1.1649)	
[2022-01-19 14:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][430/1251]	eta 0:30:30 lr 0.000892	time 1.9441 (2.2293)	loss 2.7178 (3.8394)	grad_norm 1.0724 (1.1650)	
[2022-01-19 14:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][440/1251]	eta 0:30:05 lr 0.000892	time 2.2994 (2.2266)	loss 3.9588 (3.8376)	grad_norm 1.2929 (1.1665)	
[2022-01-19 14:16:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][450/1251]	eta 0:29:45 lr 0.000892	time 2.8423 (2.2287)	loss 3.9345 (3.8433)	grad_norm 1.2302 (1.1667)	
[2022-01-19 14:16:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][460/1251]	eta 0:29:23 lr 0.000892	time 1.7724 (2.2294)	loss 4.2207 (3.8462)	grad_norm 1.0489 (1.1654)	
[2022-01-19 14:16:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][470/1251]	eta 0:29:00 lr 0.000892	time 2.1678 (2.2280)	loss 3.9740 (3.8464)	grad_norm 1.0392 (1.1652)	
[2022-01-19 14:17:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][480/1251]	eta 0:28:37 lr 0.000892	time 2.6156 (2.2278)	loss 3.6578 (3.8430)	grad_norm 1.2149 (1.1662)	
[2022-01-19 14:17:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][490/1251]	eta 0:28:15 lr 0.000892	time 2.7596 (2.2283)	loss 4.0411 (3.8400)	grad_norm 1.0141 (1.1666)	
[2022-01-19 14:17:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][500/1251]	eta 0:27:52 lr 0.000892	time 2.2581 (2.2272)	loss 3.6250 (3.8416)	grad_norm 1.0152 (1.1667)	
[2022-01-19 14:18:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][510/1251]	eta 0:27:27 lr 0.000892	time 1.9645 (2.2237)	loss 3.2969 (3.8442)	grad_norm 1.0800 (1.1646)	
[2022-01-19 14:18:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][520/1251]	eta 0:27:03 lr 0.000892	time 1.9399 (2.2209)	loss 4.4098 (3.8474)	grad_norm 0.9533 (1.1637)	
[2022-01-19 14:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][530/1251]	eta 0:26:37 lr 0.000892	time 1.8343 (2.2160)	loss 4.1014 (3.8478)	grad_norm 1.1125 (1.1652)	
[2022-01-19 14:19:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][540/1251]	eta 0:26:15 lr 0.000892	time 2.5412 (2.2161)	loss 2.7285 (3.8497)	grad_norm 1.1882 (1.1653)	
[2022-01-19 14:19:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][550/1251]	eta 0:25:52 lr 0.000892	time 1.8140 (2.2153)	loss 4.6848 (3.8529)	grad_norm 1.0682 (1.1648)	
[2022-01-19 14:20:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][560/1251]	eta 0:25:31 lr 0.000891	time 2.4036 (2.2157)	loss 4.4711 (3.8522)	grad_norm 1.6149 (1.1671)	
[2022-01-19 14:20:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][570/1251]	eta 0:25:10 lr 0.000891	time 2.2574 (2.2181)	loss 3.7608 (3.8492)	grad_norm 1.4850 (1.1676)	
[2022-01-19 14:20:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][580/1251]	eta 0:24:47 lr 0.000891	time 3.0026 (2.2173)	loss 4.5616 (3.8510)	grad_norm 1.1459 (1.1676)	
[2022-01-19 14:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][590/1251]	eta 0:24:23 lr 0.000891	time 1.5570 (2.2144)	loss 4.4639 (3.8545)	grad_norm 1.1226 (1.1694)	
[2022-01-19 14:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][600/1251]	eta 0:24:00 lr 0.000891	time 2.1252 (2.2127)	loss 4.6875 (3.8541)	grad_norm 1.0528 (1.1689)	
[2022-01-19 14:21:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][610/1251]	eta 0:23:38 lr 0.000891	time 1.8243 (2.2130)	loss 4.0332 (3.8534)	grad_norm 1.0808 (1.1684)	
[2022-01-19 14:22:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][620/1251]	eta 0:23:17 lr 0.000891	time 2.6353 (2.2152)	loss 3.8292 (3.8544)	grad_norm 1.2018 (1.1681)	
[2022-01-19 14:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][630/1251]	eta 0:22:57 lr 0.000891	time 2.8817 (2.2179)	loss 4.5428 (3.8550)	grad_norm 1.2674 (1.1675)	
[2022-01-19 14:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][640/1251]	eta 0:22:34 lr 0.000891	time 2.0385 (2.2171)	loss 3.1247 (3.8518)	grad_norm 1.0162 (1.1659)	
[2022-01-19 14:23:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][650/1251]	eta 0:22:10 lr 0.000891	time 2.1025 (2.2143)	loss 2.7995 (3.8470)	grad_norm 1.0899 (1.1652)	
[2022-01-19 14:23:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][660/1251]	eta 0:21:46 lr 0.000891	time 2.0726 (2.2106)	loss 4.1511 (3.8464)	grad_norm 1.0540 (1.1636)	
[2022-01-19 14:24:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][670/1251]	eta 0:21:23 lr 0.000891	time 2.2216 (2.2095)	loss 3.8999 (3.8477)	grad_norm 1.0918 (1.1634)	
[2022-01-19 14:24:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][680/1251]	eta 0:21:01 lr 0.000891	time 1.9227 (2.2094)	loss 3.8702 (3.8482)	grad_norm 1.5571 (1.1651)	
[2022-01-19 14:24:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][690/1251]	eta 0:20:39 lr 0.000891	time 2.1754 (2.2098)	loss 4.3015 (3.8494)	grad_norm 1.1017 (1.1655)	
[2022-01-19 14:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][700/1251]	eta 0:20:18 lr 0.000891	time 2.5326 (2.2115)	loss 3.5577 (3.8452)	grad_norm 1.1438 (1.1660)	
[2022-01-19 14:25:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][710/1251]	eta 0:19:57 lr 0.000891	time 1.8458 (2.2135)	loss 2.6176 (3.8427)	grad_norm 1.0017 (1.1656)	
[2022-01-19 14:25:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][720/1251]	eta 0:19:35 lr 0.000891	time 2.9250 (2.2144)	loss 4.2321 (3.8434)	grad_norm 1.0874 (1.1655)	
[2022-01-19 14:26:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][730/1251]	eta 0:19:12 lr 0.000891	time 1.6166 (2.2113)	loss 4.2766 (3.8418)	grad_norm 1.1773 (1.1643)	
[2022-01-19 14:26:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][740/1251]	eta 0:18:49 lr 0.000891	time 2.2307 (2.2107)	loss 3.3638 (3.8426)	grad_norm 1.1684 (1.1649)	
[2022-01-19 14:26:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][750/1251]	eta 0:18:26 lr 0.000891	time 2.1813 (2.2090)	loss 4.3290 (3.8447)	grad_norm 1.0701 (1.1650)	
[2022-01-19 14:27:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][760/1251]	eta 0:18:03 lr 0.000891	time 2.0911 (2.2075)	loss 4.7720 (3.8455)	grad_norm 1.2935 (1.1650)	
[2022-01-19 14:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][770/1251]	eta 0:17:41 lr 0.000891	time 2.0215 (2.2072)	loss 3.6185 (3.8467)	grad_norm 1.0382 (1.1649)	
[2022-01-19 14:28:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][780/1251]	eta 0:17:19 lr 0.000891	time 2.4988 (2.2067)	loss 4.3646 (3.8484)	grad_norm 1.0748 (1.1644)	
[2022-01-19 14:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][790/1251]	eta 0:16:56 lr 0.000891	time 1.8746 (2.2056)	loss 4.1228 (3.8500)	grad_norm 1.1462 (1.1633)	
[2022-01-19 14:28:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][800/1251]	eta 0:16:34 lr 0.000891	time 2.3251 (2.2045)	loss 4.7070 (3.8514)	grad_norm 1.2862 (1.1629)	
[2022-01-19 14:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][810/1251]	eta 0:16:12 lr 0.000891	time 2.4866 (2.2043)	loss 3.8937 (3.8494)	grad_norm 1.0193 (1.1621)	
[2022-01-19 14:29:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][820/1251]	eta 0:15:51 lr 0.000891	time 2.5278 (2.2073)	loss 3.5563 (3.8501)	grad_norm 1.2750 (1.1620)	
[2022-01-19 14:29:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][830/1251]	eta 0:15:30 lr 0.000891	time 3.2244 (2.2105)	loss 4.5064 (3.8525)	grad_norm 1.0012 (1.1621)	
[2022-01-19 14:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][840/1251]	eta 0:15:08 lr 0.000891	time 2.4563 (2.2107)	loss 4.2993 (3.8535)	grad_norm 1.0041 (1.1617)	
[2022-01-19 14:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][850/1251]	eta 0:14:45 lr 0.000891	time 1.9271 (2.2076)	loss 4.3227 (3.8536)	grad_norm 1.2197 (1.1619)	
[2022-01-19 14:30:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][860/1251]	eta 0:14:21 lr 0.000891	time 1.8073 (2.2045)	loss 3.3372 (3.8550)	grad_norm 1.0934 (1.1614)	
[2022-01-19 14:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][870/1251]	eta 0:13:59 lr 0.000891	time 1.8611 (2.2039)	loss 3.9115 (3.8576)	grad_norm 1.1961 (1.1608)	
[2022-01-19 14:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][880/1251]	eta 0:13:37 lr 0.000891	time 2.4677 (2.2041)	loss 4.7520 (3.8573)	grad_norm 1.0139 (1.1611)	
[2022-01-19 14:32:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][890/1251]	eta 0:13:15 lr 0.000891	time 1.6687 (2.2028)	loss 3.6494 (3.8607)	grad_norm 0.9216 (1.1604)	
[2022-01-19 14:32:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][900/1251]	eta 0:12:53 lr 0.000891	time 1.8654 (2.2029)	loss 4.4186 (3.8617)	grad_norm 1.2065 (1.1599)	
[2022-01-19 14:32:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][910/1251]	eta 0:12:31 lr 0.000891	time 2.7327 (2.2036)	loss 3.7277 (3.8640)	grad_norm 1.0801 (1.1595)	
[2022-01-19 14:33:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][920/1251]	eta 0:12:09 lr 0.000891	time 2.6419 (2.2046)	loss 3.4678 (3.8649)	grad_norm 1.3293 (1.1593)	
[2022-01-19 14:33:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][930/1251]	eta 0:11:47 lr 0.000891	time 1.5188 (2.2034)	loss 4.1242 (3.8670)	grad_norm 1.0271 (1.1589)	
[2022-01-19 14:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][940/1251]	eta 0:11:25 lr 0.000890	time 2.0830 (2.2044)	loss 4.6502 (3.8691)	grad_norm 1.2735 (1.1599)	
[2022-01-19 14:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][950/1251]	eta 0:11:03 lr 0.000890	time 2.0949 (2.2055)	loss 3.6263 (3.8696)	grad_norm 1.0138 (1.1598)	
[2022-01-19 14:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][960/1251]	eta 0:10:41 lr 0.000890	time 3.0487 (2.2054)	loss 3.6238 (3.8670)	grad_norm 0.9710 (1.1589)	
[2022-01-19 14:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][970/1251]	eta 0:10:19 lr 0.000890	time 1.6033 (2.2038)	loss 2.9956 (3.8653)	grad_norm 1.2921 (1.1583)	
[2022-01-19 14:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][980/1251]	eta 0:09:56 lr 0.000890	time 1.7929 (2.2023)	loss 4.7679 (3.8672)	grad_norm 1.1241 (1.1580)	
[2022-01-19 14:35:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][990/1251]	eta 0:09:34 lr 0.000890	time 2.0619 (2.2023)	loss 2.5942 (3.8651)	grad_norm 1.1382 (1.1580)	
[2022-01-19 14:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1000/1251]	eta 0:09:12 lr 0.000890	time 2.6151 (2.2026)	loss 3.8299 (3.8641)	grad_norm 1.0428 (1.1579)	
[2022-01-19 14:36:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1010/1251]	eta 0:08:50 lr 0.000890	time 2.1076 (2.2030)	loss 4.6668 (3.8662)	grad_norm 1.2647 (1.1578)	
[2022-01-19 14:36:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1020/1251]	eta 0:08:28 lr 0.000890	time 1.5691 (2.2030)	loss 4.1858 (3.8650)	grad_norm 1.0264 (1.1570)	
[2022-01-19 14:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1030/1251]	eta 0:08:06 lr 0.000890	time 1.8942 (2.2036)	loss 4.1367 (3.8650)	grad_norm 1.0032 (1.1562)	
[2022-01-19 14:37:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1040/1251]	eta 0:07:45 lr 0.000890	time 3.3084 (2.2052)	loss 4.1923 (3.8643)	grad_norm 1.2390 (1.1562)	
[2022-01-19 14:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1050/1251]	eta 0:07:23 lr 0.000890	time 1.5864 (2.2041)	loss 2.6875 (3.8616)	grad_norm 1.0198 (1.1554)	
[2022-01-19 14:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1060/1251]	eta 0:07:00 lr 0.000890	time 1.6400 (2.2024)	loss 4.2161 (3.8624)	grad_norm 1.0061 (1.1547)	
[2022-01-19 14:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1070/1251]	eta 0:06:38 lr 0.000890	time 1.7712 (2.2013)	loss 4.3373 (3.8616)	grad_norm 1.0998 (1.1536)	
[2022-01-19 14:38:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1080/1251]	eta 0:06:16 lr 0.000890	time 2.8519 (2.2015)	loss 2.6358 (3.8614)	grad_norm 1.1595 (1.1532)	
[2022-01-19 14:39:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1090/1251]	eta 0:05:54 lr 0.000890	time 2.2565 (2.2027)	loss 4.3375 (3.8646)	grad_norm 1.4812 (1.1531)	
[2022-01-19 14:39:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1100/1251]	eta 0:05:32 lr 0.000890	time 2.3478 (2.2025)	loss 3.6313 (3.8628)	grad_norm 1.2236 (1.1526)	
[2022-01-19 14:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1110/1251]	eta 0:05:10 lr 0.000890	time 1.9619 (2.2017)	loss 4.5588 (3.8639)	grad_norm 1.1107 (1.1528)	
[2022-01-19 14:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1120/1251]	eta 0:04:48 lr 0.000890	time 1.9755 (2.1995)	loss 4.2425 (3.8648)	grad_norm 1.3687 (1.1533)	
[2022-01-19 14:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1130/1251]	eta 0:04:26 lr 0.000890	time 2.0298 (2.1989)	loss 3.5651 (3.8636)	grad_norm 1.1852 (1.1533)	
[2022-01-19 14:41:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1140/1251]	eta 0:04:03 lr 0.000890	time 1.7439 (2.1981)	loss 4.1970 (3.8616)	grad_norm 1.3666 (1.1531)	
[2022-01-19 14:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1150/1251]	eta 0:03:42 lr 0.000890	time 3.3573 (2.1987)	loss 3.6134 (3.8619)	grad_norm 1.2407 (1.1529)	
[2022-01-19 14:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1160/1251]	eta 0:03:20 lr 0.000890	time 2.4302 (2.1993)	loss 3.7384 (3.8582)	grad_norm 1.2418 (1.1532)	
[2022-01-19 14:42:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1170/1251]	eta 0:02:58 lr 0.000890	time 1.8447 (2.2009)	loss 4.6553 (3.8597)	grad_norm 1.1560 (1.1537)	
[2022-01-19 14:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1180/1251]	eta 0:02:36 lr 0.000890	time 1.5659 (2.2009)	loss 2.8872 (3.8599)	grad_norm 1.0419 (1.1534)	
[2022-01-19 14:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1190/1251]	eta 0:02:14 lr 0.000890	time 3.4180 (2.2015)	loss 4.1164 (3.8586)	grad_norm 1.3461 (1.1537)	
[2022-01-19 14:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1200/1251]	eta 0:01:52 lr 0.000890	time 2.7912 (2.2012)	loss 4.0404 (3.8601)	grad_norm 0.9883 (1.1531)	
[2022-01-19 14:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1210/1251]	eta 0:01:30 lr 0.000890	time 2.0640 (2.1994)	loss 2.8858 (3.8572)	grad_norm 0.9689 (1.1527)	
[2022-01-19 14:44:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1220/1251]	eta 0:01:08 lr 0.000890	time 1.8750 (2.1984)	loss 3.3255 (3.8568)	grad_norm 1.2248 (1.1526)	
[2022-01-19 14:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1230/1251]	eta 0:00:46 lr 0.000890	time 3.3057 (2.1981)	loss 4.1316 (3.8582)	grad_norm 1.2515 (1.1528)	
[2022-01-19 14:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1240/1251]	eta 0:00:24 lr 0.000890	time 1.5535 (2.1972)	loss 3.1788 (3.8567)	grad_norm 1.1269 (1.1537)	
[2022-01-19 14:45:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [64/300][1250/1251]	eta 0:00:02 lr 0.000890	time 1.1521 (2.1920)	loss 3.6783 (3.8564)	grad_norm 1.1576 (1.1539)	
[2022-01-19 14:45:02 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 64 training takes 0:45:42
[2022-01-19 14:45:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.760 (18.760)	Loss 1.2430 (1.2430)	Acc@1 72.949 (72.949)	Acc@5 90.332 (90.332)	
[2022-01-19 14:45:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.863 (3.581)	Loss 1.2525 (1.2332)	Acc@1 70.703 (71.520)	Acc@5 90.234 (90.598)	
[2022-01-19 14:45:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.275 (2.747)	Loss 1.3071 (1.2236)	Acc@1 68.457 (71.661)	Acc@5 89.941 (90.834)	
[2022-01-19 14:46:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.591 (2.503)	Loss 1.2639 (1.2259)	Acc@1 70.312 (71.434)	Acc@5 91.113 (90.959)	
[2022-01-19 14:46:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.910 (2.236)	Loss 1.2971 (1.2254)	Acc@1 71.289 (71.406)	Acc@5 89.160 (90.939)	
[2022-01-19 14:46:41 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 71.442 Acc@5 90.898
[2022-01-19 14:46:41 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 71.4%
[2022-01-19 14:46:41 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 71.53%
[2022-01-19 14:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][0/1251]	eta 7:42:09 lr 0.000890	time 22.1659 (22.1659)	loss 3.4222 (3.4222)	grad_norm 1.1777 (1.1777)	
[2022-01-19 14:47:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][10/1251]	eta 1:22:53 lr 0.000890	time 2.1911 (4.0077)	loss 4.2362 (3.7988)	grad_norm 1.0047 (1.0857)	
[2022-01-19 14:47:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][20/1251]	eta 1:06:13 lr 0.000890	time 2.1473 (3.2276)	loss 3.8032 (3.7738)	grad_norm 1.2047 (1.1342)	
[2022-01-19 14:48:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][30/1251]	eta 0:58:46 lr 0.000890	time 1.9324 (2.8885)	loss 3.8392 (3.8410)	grad_norm 1.1955 (1.1475)	
[2022-01-19 14:48:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][40/1251]	eta 0:55:23 lr 0.000890	time 3.6469 (2.7442)	loss 3.8605 (3.8042)	grad_norm 1.1050 (1.1505)	
[2022-01-19 14:48:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][50/1251]	eta 0:52:55 lr 0.000890	time 2.9809 (2.6439)	loss 3.2297 (3.8204)	grad_norm 1.0880 (1.1385)	
[2022-01-19 14:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][60/1251]	eta 0:50:43 lr 0.000890	time 1.5561 (2.5557)	loss 4.4757 (3.8178)	grad_norm 1.2220 (1.1350)	
[2022-01-19 14:49:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][70/1251]	eta 0:48:57 lr 0.000890	time 1.6565 (2.4872)	loss 4.1852 (3.8275)	grad_norm 1.2657 (1.1428)	
[2022-01-19 14:49:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][80/1251]	eta 0:47:34 lr 0.000889	time 2.3516 (2.4380)	loss 3.0933 (3.7976)	grad_norm 1.1797 (1.1484)	
[2022-01-19 14:50:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][90/1251]	eta 0:46:51 lr 0.000889	time 2.2893 (2.4216)	loss 2.7646 (3.7746)	grad_norm 1.3622 (1.1586)	
[2022-01-19 14:50:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][100/1251]	eta 0:45:46 lr 0.000889	time 1.9233 (2.3865)	loss 4.4948 (3.7752)	grad_norm 1.1285 (1.1583)	
[2022-01-19 14:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][110/1251]	eta 0:45:03 lr 0.000889	time 1.9484 (2.3692)	loss 3.9269 (3.7842)	grad_norm 1.0596 (1.1613)	
[2022-01-19 14:51:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][120/1251]	eta 0:44:21 lr 0.000889	time 2.1335 (2.3530)	loss 3.5148 (3.7742)	grad_norm 1.3934 (1.1583)	
[2022-01-19 14:51:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][130/1251]	eta 0:43:40 lr 0.000889	time 2.2098 (2.3377)	loss 3.8975 (3.7788)	grad_norm 1.2100 (1.1523)	
[2022-01-19 14:52:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][140/1251]	eta 0:43:11 lr 0.000889	time 1.7992 (2.3329)	loss 2.6282 (3.7971)	grad_norm 1.0592 (1.1500)	
[2022-01-19 14:52:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][150/1251]	eta 0:42:36 lr 0.000889	time 1.9086 (2.3223)	loss 4.2231 (3.8126)	grad_norm 1.2654 (1.1542)	
[2022-01-19 14:52:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][160/1251]	eta 0:41:52 lr 0.000889	time 1.7190 (2.3030)	loss 4.1026 (3.8046)	grad_norm 1.2702 (1.1590)	
[2022-01-19 14:53:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][170/1251]	eta 0:41:21 lr 0.000889	time 2.1879 (2.2956)	loss 4.2191 (3.8105)	grad_norm 1.0625 (1.1599)	
[2022-01-19 14:53:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][180/1251]	eta 0:40:54 lr 0.000889	time 2.5253 (2.2922)	loss 4.2440 (3.7855)	grad_norm 1.4059 (1.1598)	
[2022-01-19 14:53:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][190/1251]	eta 0:40:24 lr 0.000889	time 2.1656 (2.2847)	loss 4.1419 (3.7704)	grad_norm 1.0010 (1.1615)	
[2022-01-19 14:54:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][200/1251]	eta 0:39:57 lr 0.000889	time 2.2454 (2.2815)	loss 4.6277 (3.7834)	grad_norm 1.1336 (1.1614)	
[2022-01-19 14:54:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][210/1251]	eta 0:39:32 lr 0.000889	time 1.8833 (2.2794)	loss 4.8784 (3.7913)	grad_norm 1.0499 (1.1597)	
[2022-01-19 14:55:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][220/1251]	eta 0:39:04 lr 0.000889	time 1.8898 (2.2737)	loss 3.5325 (3.7893)	grad_norm 1.1186 (1.1638)	
[2022-01-19 14:55:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][230/1251]	eta 0:38:46 lr 0.000889	time 1.9020 (2.2784)	loss 4.1909 (3.7817)	grad_norm 1.3270 (1.1651)	
[2022-01-19 14:55:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][240/1251]	eta 0:38:25 lr 0.000889	time 3.1133 (2.2803)	loss 3.8818 (3.7836)	grad_norm 0.9570 (1.1617)	
[2022-01-19 14:56:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][250/1251]	eta 0:37:56 lr 0.000889	time 1.6062 (2.2743)	loss 4.7891 (3.7822)	grad_norm 1.1448 (1.1606)	
[2022-01-19 14:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][260/1251]	eta 0:37:24 lr 0.000889	time 1.9360 (2.2649)	loss 2.9791 (3.7842)	grad_norm 0.9400 (1.1639)	
[2022-01-19 14:56:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][270/1251]	eta 0:36:54 lr 0.000889	time 2.4634 (2.2571)	loss 3.9778 (3.7858)	grad_norm 1.0027 (1.1647)	
[2022-01-19 14:57:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][280/1251]	eta 0:36:22 lr 0.000889	time 1.7226 (2.2472)	loss 4.5663 (3.7891)	grad_norm 1.0972 (1.1645)	
[2022-01-19 14:57:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][290/1251]	eta 0:36:00 lr 0.000889	time 1.8380 (2.2482)	loss 4.0494 (3.7886)	grad_norm 1.1505 (1.1615)	
[2022-01-19 14:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][300/1251]	eta 0:35:35 lr 0.000889	time 2.4277 (2.2456)	loss 3.7195 (3.7853)	grad_norm 1.1318 (1.1619)	
[2022-01-19 14:58:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][310/1251]	eta 0:35:15 lr 0.000889	time 3.7397 (2.2485)	loss 4.6380 (3.7916)	grad_norm 1.2682 (1.1619)	
[2022-01-19 14:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][320/1251]	eta 0:34:52 lr 0.000889	time 1.9547 (2.2480)	loss 4.0453 (3.8000)	grad_norm 1.0088 (1.1632)	
[2022-01-19 14:59:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][330/1251]	eta 0:34:31 lr 0.000889	time 1.7522 (2.2496)	loss 3.1486 (3.7958)	grad_norm 1.0974 (1.1631)	
[2022-01-19 14:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][340/1251]	eta 0:34:10 lr 0.000889	time 1.8632 (2.2510)	loss 4.2455 (3.7954)	grad_norm 1.1393 (1.1628)	
[2022-01-19 14:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][350/1251]	eta 0:33:46 lr 0.000889	time 2.3871 (2.2488)	loss 3.5596 (3.8059)	grad_norm 1.1377 (1.1634)	
[2022-01-19 15:00:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][360/1251]	eta 0:33:19 lr 0.000889	time 2.0757 (2.2440)	loss 2.7076 (3.8090)	grad_norm 1.0768 (1.1623)	
[2022-01-19 15:00:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][370/1251]	eta 0:32:50 lr 0.000889	time 1.8976 (2.2368)	loss 3.2124 (3.8083)	grad_norm 1.3040 (1.1619)	
[2022-01-19 15:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][380/1251]	eta 0:32:24 lr 0.000889	time 1.9213 (2.2324)	loss 4.4510 (3.8116)	grad_norm 1.0588 (1.1604)	
[2022-01-19 15:01:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][390/1251]	eta 0:32:01 lr 0.000889	time 2.0005 (2.2314)	loss 3.6295 (3.8104)	grad_norm 1.2529 (1.1595)	
[2022-01-19 15:01:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][400/1251]	eta 0:31:35 lr 0.000889	time 2.1976 (2.2275)	loss 2.9499 (3.8078)	grad_norm 1.2019 (1.1574)	
[2022-01-19 15:01:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][410/1251]	eta 0:31:15 lr 0.000889	time 2.2163 (2.2298)	loss 3.9423 (3.8076)	grad_norm 1.4290 (1.1560)	
[2022-01-19 15:02:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][420/1251]	eta 0:30:51 lr 0.000889	time 1.8800 (2.2281)	loss 3.7579 (3.8120)	grad_norm 1.0455 (1.1553)	
[2022-01-19 15:02:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][430/1251]	eta 0:30:27 lr 0.000889	time 2.2064 (2.2263)	loss 4.5640 (3.8117)	grad_norm 1.1185 (1.1564)	
[2022-01-19 15:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][440/1251]	eta 0:30:06 lr 0.000889	time 2.3588 (2.2269)	loss 3.2282 (3.8070)	grad_norm 1.3181 (1.1568)	
[2022-01-19 15:03:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][450/1251]	eta 0:29:44 lr 0.000889	time 2.2928 (2.2277)	loss 4.4617 (3.8079)	grad_norm 1.0360 (1.1569)	
[2022-01-19 15:03:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][460/1251]	eta 0:29:23 lr 0.000888	time 2.5498 (2.2292)	loss 3.2162 (3.8077)	grad_norm 1.2535 (1.1563)	
[2022-01-19 15:04:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][470/1251]	eta 0:29:00 lr 0.000888	time 1.5477 (2.2288)	loss 4.1212 (3.8099)	grad_norm 0.9774 (1.1556)	
[2022-01-19 15:04:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][480/1251]	eta 0:28:37 lr 0.000888	time 1.8986 (2.2281)	loss 4.3304 (3.8112)	grad_norm 1.4326 (1.1569)	
[2022-01-19 15:04:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][490/1251]	eta 0:28:11 lr 0.000888	time 1.7003 (2.2227)	loss 3.9742 (3.8141)	grad_norm 1.2622 (1.1573)	
[2022-01-19 15:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][500/1251]	eta 0:27:49 lr 0.000888	time 2.8788 (2.2234)	loss 2.8508 (3.8156)	grad_norm 1.1208 (1.1570)	
[2022-01-19 15:05:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][510/1251]	eta 0:27:26 lr 0.000888	time 1.9053 (2.2215)	loss 4.1886 (3.8177)	grad_norm 1.0121 (1.1565)	
[2022-01-19 15:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][520/1251]	eta 0:27:02 lr 0.000888	time 1.9200 (2.2202)	loss 3.1765 (3.8156)	grad_norm 1.0668 (1.1567)	
[2022-01-19 15:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][530/1251]	eta 0:26:39 lr 0.000888	time 1.7928 (2.2183)	loss 4.1740 (3.8211)	grad_norm 1.2862 (1.1577)	
[2022-01-19 15:06:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][540/1251]	eta 0:26:15 lr 0.000888	time 2.6012 (2.2162)	loss 3.4595 (3.8222)	grad_norm 1.0966 (1.1590)	
[2022-01-19 15:07:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][550/1251]	eta 0:25:53 lr 0.000888	time 2.5834 (2.2154)	loss 3.9991 (3.8259)	grad_norm 1.1325 (1.1573)	
[2022-01-19 15:07:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][560/1251]	eta 0:25:29 lr 0.000888	time 2.1915 (2.2133)	loss 3.4738 (3.8285)	grad_norm 1.3735 (1.1558)	
[2022-01-19 15:07:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][570/1251]	eta 0:25:08 lr 0.000888	time 1.9734 (2.2144)	loss 3.1867 (3.8258)	grad_norm 1.0892 (1.1556)	
[2022-01-19 15:08:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][580/1251]	eta 0:24:45 lr 0.000888	time 2.4356 (2.2134)	loss 4.4710 (3.8279)	grad_norm 1.1081 (1.1549)	
[2022-01-19 15:08:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][590/1251]	eta 0:24:23 lr 0.000888	time 2.5730 (2.2144)	loss 3.2288 (3.8329)	grad_norm 1.3297 (1.1561)	
[2022-01-19 15:08:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][600/1251]	eta 0:24:01 lr 0.000888	time 2.0569 (2.2144)	loss 4.1938 (3.8339)	grad_norm 1.0031 (1.1559)	
[2022-01-19 15:09:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][610/1251]	eta 0:23:39 lr 0.000888	time 2.1045 (2.2146)	loss 3.1548 (3.8307)	grad_norm 1.2284 (1.1558)	
[2022-01-19 15:09:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][620/1251]	eta 0:23:15 lr 0.000888	time 1.6868 (2.2123)	loss 4.0781 (3.8373)	grad_norm 1.0780 (1.1570)	
[2022-01-19 15:09:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][630/1251]	eta 0:22:55 lr 0.000888	time 3.2187 (2.2151)	loss 3.2334 (3.8347)	grad_norm 1.0818 (1.1570)	
[2022-01-19 15:10:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][640/1251]	eta 0:22:33 lr 0.000888	time 2.1948 (2.2144)	loss 4.1762 (3.8382)	grad_norm 1.0375 (1.1557)	
[2022-01-19 15:10:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][650/1251]	eta 0:22:11 lr 0.000888	time 2.2328 (2.2151)	loss 4.3821 (3.8391)	grad_norm 1.0677 (1.1549)	
[2022-01-19 15:11:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][660/1251]	eta 0:21:48 lr 0.000888	time 1.7169 (2.2146)	loss 4.7873 (3.8423)	grad_norm 1.1797 (1.1555)	
[2022-01-19 15:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][670/1251]	eta 0:21:26 lr 0.000888	time 2.9187 (2.2139)	loss 4.4663 (3.8451)	grad_norm 1.0387 (1.1545)	
[2022-01-19 15:11:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][680/1251]	eta 0:21:02 lr 0.000888	time 1.6917 (2.2107)	loss 3.9200 (3.8488)	grad_norm 1.0030 (1.1533)	
[2022-01-19 15:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][690/1251]	eta 0:20:39 lr 0.000888	time 2.2945 (2.2092)	loss 4.3524 (3.8499)	grad_norm 1.0576 (1.1522)	
[2022-01-19 15:12:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][700/1251]	eta 0:20:17 lr 0.000888	time 1.9188 (2.2090)	loss 4.2768 (3.8498)	grad_norm 1.2053 (1.1513)	
[2022-01-19 15:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][710/1251]	eta 0:19:55 lr 0.000888	time 2.5965 (2.2094)	loss 3.1273 (3.8535)	grad_norm 1.0162 (1.1505)	
[2022-01-19 15:13:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][720/1251]	eta 0:19:33 lr 0.000888	time 2.5126 (2.2096)	loss 3.8465 (3.8542)	grad_norm 1.0555 (1.1504)	
[2022-01-19 15:13:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][730/1251]	eta 0:19:10 lr 0.000888	time 2.0736 (2.2089)	loss 4.1026 (3.8571)	grad_norm 1.2220 (1.1511)	
[2022-01-19 15:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][740/1251]	eta 0:18:48 lr 0.000888	time 2.3069 (2.2078)	loss 4.0249 (3.8614)	grad_norm 1.2924 (1.1519)	
[2022-01-19 15:14:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][750/1251]	eta 0:18:26 lr 0.000888	time 2.7856 (2.2082)	loss 3.1084 (3.8639)	grad_norm 1.1489 (1.1518)	
[2022-01-19 15:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][760/1251]	eta 0:18:03 lr 0.000888	time 1.7561 (2.2068)	loss 3.8182 (3.8666)	grad_norm 1.2951 (1.1517)	
[2022-01-19 15:15:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][770/1251]	eta 0:17:40 lr 0.000888	time 1.9350 (2.2051)	loss 4.2744 (3.8710)	grad_norm 1.2209 (1.1518)	
[2022-01-19 15:15:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][780/1251]	eta 0:17:17 lr 0.000888	time 2.2293 (2.2032)	loss 4.3723 (3.8703)	grad_norm 1.0933 (1.1529)	
[2022-01-19 15:15:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][790/1251]	eta 0:16:55 lr 0.000888	time 2.1849 (2.2018)	loss 4.1427 (3.8717)	grad_norm 1.2101 (1.1555)	
[2022-01-19 15:16:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][800/1251]	eta 0:16:34 lr 0.000888	time 2.1418 (2.2043)	loss 3.4180 (3.8693)	grad_norm 0.9893 (1.1549)	
[2022-01-19 15:16:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][810/1251]	eta 0:16:12 lr 0.000888	time 2.5757 (2.2061)	loss 4.1454 (3.8726)	grad_norm 1.4000 (1.1552)	
[2022-01-19 15:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][820/1251]	eta 0:15:50 lr 0.000888	time 1.7359 (2.2049)	loss 3.1901 (3.8694)	grad_norm 1.1231 (1.1553)	
[2022-01-19 15:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][830/1251]	eta 0:15:27 lr 0.000888	time 1.6404 (2.2040)	loss 4.2019 (3.8716)	grad_norm 1.1866 (1.1545)	
[2022-01-19 15:17:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][840/1251]	eta 0:15:06 lr 0.000887	time 2.5029 (2.2054)	loss 2.9814 (3.8684)	grad_norm 1.1021 (1.1539)	
[2022-01-19 15:17:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][850/1251]	eta 0:14:44 lr 0.000887	time 2.1393 (2.2047)	loss 3.7364 (3.8670)	grad_norm 1.4155 (1.1536)	
[2022-01-19 15:18:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][860/1251]	eta 0:14:21 lr 0.000887	time 1.9644 (2.2023)	loss 3.4636 (3.8686)	grad_norm 1.2512 (1.1531)	
[2022-01-19 15:18:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][870/1251]	eta 0:13:58 lr 0.000887	time 1.9200 (2.2017)	loss 3.9023 (3.8652)	grad_norm 1.2507 (1.1538)	
[2022-01-19 15:19:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][880/1251]	eta 0:13:36 lr 0.000887	time 2.1522 (2.2008)	loss 4.7755 (3.8660)	grad_norm 0.9492 (1.1540)	
[2022-01-19 15:19:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][890/1251]	eta 0:13:13 lr 0.000887	time 2.4267 (2.1982)	loss 3.7118 (3.8678)	grad_norm 0.9726 (1.1528)	
[2022-01-19 15:19:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][900/1251]	eta 0:12:51 lr 0.000887	time 2.2989 (2.1973)	loss 3.3842 (3.8658)	grad_norm 1.0742 (1.1526)	
[2022-01-19 15:20:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][910/1251]	eta 0:12:29 lr 0.000887	time 2.4906 (2.1969)	loss 4.7407 (3.8658)	grad_norm 0.9999 (1.1517)	
[2022-01-19 15:20:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][920/1251]	eta 0:12:07 lr 0.000887	time 2.1100 (2.1976)	loss 3.1316 (3.8669)	grad_norm 1.2407 (1.1512)	
[2022-01-19 15:20:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][930/1251]	eta 0:11:45 lr 0.000887	time 1.5586 (2.1970)	loss 3.7428 (3.8656)	grad_norm 1.1650 (1.1517)	
[2022-01-19 15:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][940/1251]	eta 0:11:23 lr 0.000887	time 1.6696 (2.1970)	loss 3.8311 (3.8645)	grad_norm 1.3948 (1.1526)	
[2022-01-19 15:21:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][950/1251]	eta 0:11:02 lr 0.000887	time 2.7795 (2.1998)	loss 4.1103 (3.8653)	grad_norm 1.0862 (1.1542)	
[2022-01-19 15:21:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][960/1251]	eta 0:10:40 lr 0.000887	time 1.4916 (2.1996)	loss 2.7119 (3.8637)	grad_norm 1.1871 (1.1549)	
[2022-01-19 15:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][970/1251]	eta 0:10:17 lr 0.000887	time 1.9037 (2.1986)	loss 3.0696 (3.8630)	grad_norm 1.2531 (1.1553)	
[2022-01-19 15:22:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][980/1251]	eta 0:09:55 lr 0.000887	time 1.5823 (2.1966)	loss 4.3135 (3.8651)	grad_norm 1.1727 (1.1557)	
[2022-01-19 15:22:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][990/1251]	eta 0:09:33 lr 0.000887	time 2.4847 (2.1974)	loss 3.3902 (3.8647)	grad_norm 1.1955 (1.1555)	
[2022-01-19 15:23:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1000/1251]	eta 0:09:12 lr 0.000887	time 2.1243 (2.1992)	loss 2.6857 (3.8653)	grad_norm 1.0450 (1.1549)	
[2022-01-19 15:23:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1010/1251]	eta 0:08:50 lr 0.000887	time 1.8039 (2.2003)	loss 2.9134 (3.8633)	grad_norm 0.9921 (1.1543)	
[2022-01-19 15:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1020/1251]	eta 0:08:27 lr 0.000887	time 1.8109 (2.1991)	loss 4.0077 (3.8630)	grad_norm 1.2087 (1.1541)	
[2022-01-19 15:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1030/1251]	eta 0:08:05 lr 0.000887	time 2.0247 (2.1970)	loss 4.5016 (3.8631)	grad_norm 1.4035 (1.1546)	
[2022-01-19 15:24:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1040/1251]	eta 0:07:43 lr 0.000887	time 1.9660 (2.1954)	loss 4.5720 (3.8631)	grad_norm 1.2678 (1.1539)	
[2022-01-19 15:25:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1050/1251]	eta 0:07:21 lr 0.000887	time 2.5427 (2.1953)	loss 4.1472 (3.8630)	grad_norm 0.8966 (1.1537)	
[2022-01-19 15:25:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1060/1251]	eta 0:06:59 lr 0.000887	time 2.5887 (2.1951)	loss 3.4779 (3.8632)	grad_norm 1.1835 (1.1528)	
[2022-01-19 15:25:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1070/1251]	eta 0:06:37 lr 0.000887	time 2.1924 (2.1945)	loss 4.1960 (3.8631)	grad_norm 1.3226 (1.1524)	
[2022-01-19 15:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1080/1251]	eta 0:06:15 lr 0.000887	time 2.4946 (2.1957)	loss 2.4644 (3.8594)	grad_norm 1.3590 (1.1528)	
[2022-01-19 15:26:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1090/1251]	eta 0:05:53 lr 0.000887	time 2.1425 (2.1962)	loss 3.7450 (3.8586)	grad_norm 1.0965 (1.1531)	
[2022-01-19 15:26:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1100/1251]	eta 0:05:31 lr 0.000887	time 1.9483 (2.1958)	loss 3.6830 (3.8617)	grad_norm 1.1250 (1.1529)	
[2022-01-19 15:27:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1110/1251]	eta 0:05:09 lr 0.000887	time 1.5879 (2.1961)	loss 3.0258 (3.8621)	grad_norm 1.0082 (1.1531)	
[2022-01-19 15:27:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1120/1251]	eta 0:04:47 lr 0.000887	time 2.7835 (2.1964)	loss 3.9980 (3.8653)	grad_norm 1.1375 (1.1529)	
[2022-01-19 15:28:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1130/1251]	eta 0:04:25 lr 0.000887	time 2.1850 (2.1955)	loss 4.5677 (3.8647)	grad_norm 1.1376 (1.1532)	
[2022-01-19 15:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1140/1251]	eta 0:04:03 lr 0.000887	time 1.9708 (2.1941)	loss 3.4694 (3.8653)	grad_norm 0.9760 (1.1524)	
[2022-01-19 15:28:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1150/1251]	eta 0:03:41 lr 0.000887	time 1.8018 (2.1935)	loss 3.1573 (3.8642)	grad_norm 1.0323 (1.1523)	
[2022-01-19 15:29:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1160/1251]	eta 0:03:19 lr 0.000887	time 2.2450 (2.1923)	loss 4.3193 (3.8654)	grad_norm 1.1707 (1.1524)	
[2022-01-19 15:29:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1170/1251]	eta 0:02:57 lr 0.000887	time 2.4779 (2.1918)	loss 3.6060 (3.8634)	grad_norm 0.9955 (1.1521)	
[2022-01-19 15:29:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1180/1251]	eta 0:02:35 lr 0.000887	time 1.8823 (2.1914)	loss 3.7025 (3.8660)	grad_norm 1.2611 (1.1522)	
[2022-01-19 15:30:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1190/1251]	eta 0:02:13 lr 0.000887	time 1.8335 (2.1923)	loss 4.4629 (3.8675)	grad_norm 1.1465 (1.1517)	
[2022-01-19 15:30:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1200/1251]	eta 0:01:51 lr 0.000887	time 2.3294 (2.1926)	loss 4.3303 (3.8688)	grad_norm 1.1168 (1.1519)	
[2022-01-19 15:30:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1210/1251]	eta 0:01:29 lr 0.000887	time 2.8626 (2.1932)	loss 4.6280 (3.8666)	grad_norm 1.1027 (1.1513)	
[2022-01-19 15:31:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1220/1251]	eta 0:01:07 lr 0.000886	time 1.6081 (2.1920)	loss 4.2538 (3.8678)	grad_norm 1.1798 (1.1514)	
[2022-01-19 15:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1230/1251]	eta 0:00:46 lr 0.000886	time 1.9319 (2.1920)	loss 4.2288 (3.8693)	grad_norm 0.9551 (1.1516)	
[2022-01-19 15:32:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1240/1251]	eta 0:00:24 lr 0.000886	time 2.6004 (2.1925)	loss 3.6123 (3.8702)	grad_norm 1.0906 (1.1516)	
[2022-01-19 15:32:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [65/300][1250/1251]	eta 0:00:02 lr 0.000886	time 1.1689 (2.1870)	loss 4.0631 (3.8698)	grad_norm 0.9762 (1.1517)	
[2022-01-19 15:32:17 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 65 training takes 0:45:36
[2022-01-19 15:32:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.498 (18.498)	Loss 1.2459 (1.2459)	Acc@1 72.070 (72.070)	Acc@5 91.016 (91.016)	
[2022-01-19 15:32:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.565 (3.228)	Loss 1.1969 (1.2451)	Acc@1 74.121 (72.088)	Acc@5 92.188 (91.282)	
[2022-01-19 15:33:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.895 (2.505)	Loss 1.2774 (1.2526)	Acc@1 69.238 (71.731)	Acc@5 91.406 (91.062)	
[2022-01-19 15:33:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.301 (2.270)	Loss 1.2282 (1.2608)	Acc@1 72.461 (71.440)	Acc@5 90.820 (90.918)	
[2022-01-19 15:33:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.073 (2.150)	Loss 1.2407 (1.2567)	Acc@1 72.363 (71.499)	Acc@5 91.309 (90.932)	
[2022-01-19 15:33:53 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 71.698 Acc@5 91.018
[2022-01-19 15:33:53 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 71.7%
[2022-01-19 15:33:53 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 71.70%
[2022-01-19 15:34:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][0/1251]	eta 7:29:59 lr 0.000886	time 21.5823 (21.5823)	loss 3.1934 (3.1934)	grad_norm 1.0109 (1.0109)	
[2022-01-19 15:34:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][10/1251]	eta 1:21:36 lr 0.000886	time 1.6363 (3.9460)	loss 3.4308 (3.9958)	grad_norm 1.1064 (1.1690)	
[2022-01-19 15:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][20/1251]	eta 1:04:12 lr 0.000886	time 1.2326 (3.1296)	loss 3.1981 (3.9072)	grad_norm 1.1172 (1.1596)	
[2022-01-19 15:35:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][30/1251]	eta 0:57:37 lr 0.000886	time 1.5608 (2.8319)	loss 4.2226 (3.8925)	grad_norm 1.1286 (1.1628)	
[2022-01-19 15:35:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][40/1251]	eta 0:54:22 lr 0.000886	time 3.9947 (2.6941)	loss 4.4350 (3.9047)	grad_norm 1.1514 (1.1672)	
[2022-01-19 15:36:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][50/1251]	eta 0:52:02 lr 0.000886	time 1.7919 (2.6001)	loss 4.3386 (3.9592)	grad_norm 1.5237 (1.1725)	
[2022-01-19 15:36:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][60/1251]	eta 0:50:08 lr 0.000886	time 1.7874 (2.5260)	loss 3.7696 (3.9238)	grad_norm 1.1111 (1.1740)	
[2022-01-19 15:36:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][70/1251]	eta 0:49:01 lr 0.000886	time 2.3319 (2.4904)	loss 4.0230 (3.9007)	grad_norm 1.0612 (1.1878)	
[2022-01-19 15:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][80/1251]	eta 0:48:24 lr 0.000886	time 3.4300 (2.4808)	loss 4.5897 (3.8937)	grad_norm 1.2601 (1.1840)	
[2022-01-19 15:37:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][90/1251]	eta 0:47:43 lr 0.000886	time 1.6212 (2.4665)	loss 3.1582 (3.8931)	grad_norm 1.1110 (1.1810)	
[2022-01-19 15:37:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][100/1251]	eta 0:46:48 lr 0.000886	time 2.1987 (2.4400)	loss 3.6597 (3.8632)	grad_norm 1.1553 (1.1750)	
[2022-01-19 15:38:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][110/1251]	eta 0:45:42 lr 0.000886	time 1.8720 (2.4033)	loss 4.1394 (3.8645)	grad_norm 1.1270 (1.1720)	
[2022-01-19 15:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][120/1251]	eta 0:44:53 lr 0.000886	time 3.1425 (2.3814)	loss 2.8924 (3.8627)	grad_norm 1.3860 (1.1797)	
[2022-01-19 15:39:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][130/1251]	eta 0:44:12 lr 0.000886	time 1.8761 (2.3663)	loss 4.6973 (3.8874)	grad_norm 1.1874 (1.1816)	
[2022-01-19 15:39:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][140/1251]	eta 0:43:41 lr 0.000886	time 2.2591 (2.3596)	loss 4.2027 (3.8907)	grad_norm 1.2899 (1.1772)	
[2022-01-19 15:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][150/1251]	eta 0:43:06 lr 0.000886	time 2.2690 (2.3491)	loss 4.3410 (3.8946)	grad_norm 1.1185 (1.1763)	
[2022-01-19 15:40:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][160/1251]	eta 0:42:29 lr 0.000886	time 2.2105 (2.3369)	loss 2.9193 (3.8872)	grad_norm 1.2261 (1.1834)	
[2022-01-19 15:40:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][170/1251]	eta 0:41:54 lr 0.000886	time 3.1834 (2.3263)	loss 2.7139 (3.8722)	grad_norm 1.2182 (1.1781)	
[2022-01-19 15:40:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][180/1251]	eta 0:41:24 lr 0.000886	time 1.9479 (2.3196)	loss 2.5185 (3.8543)	grad_norm 1.1577 (1.1763)	
[2022-01-19 15:41:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][190/1251]	eta 0:40:47 lr 0.000886	time 2.0399 (2.3069)	loss 3.4373 (3.8653)	grad_norm 1.0521 (1.1744)	
[2022-01-19 15:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][200/1251]	eta 0:40:13 lr 0.000886	time 2.5870 (2.2960)	loss 2.9519 (3.8729)	grad_norm 1.1222 (1.1733)	
[2022-01-19 15:41:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][210/1251]	eta 0:39:39 lr 0.000886	time 2.2399 (2.2861)	loss 4.3578 (3.8756)	grad_norm 1.2802 (1.1770)	
[2022-01-19 15:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][220/1251]	eta 0:39:10 lr 0.000886	time 2.6030 (2.2801)	loss 2.7052 (3.8702)	grad_norm 1.1694 (1.1771)	
[2022-01-19 15:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][230/1251]	eta 0:38:41 lr 0.000886	time 2.2053 (2.2741)	loss 2.7583 (3.8677)	grad_norm 1.2324 (1.1740)	
[2022-01-19 15:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][240/1251]	eta 0:38:15 lr 0.000886	time 2.4632 (2.2709)	loss 4.1233 (3.8668)	grad_norm 1.0653 (1.1734)	
[2022-01-19 15:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][250/1251]	eta 0:37:51 lr 0.000886	time 1.8600 (2.2696)	loss 3.2749 (3.8495)	grad_norm 1.2451 (1.1732)	
[2022-01-19 15:43:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][260/1251]	eta 0:37:32 lr 0.000886	time 2.4639 (2.2730)	loss 3.9827 (3.8528)	grad_norm 1.0750 (1.1721)	
[2022-01-19 15:44:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][270/1251]	eta 0:37:06 lr 0.000886	time 1.8844 (2.2699)	loss 3.2477 (3.8567)	grad_norm 0.9914 (1.1729)	
[2022-01-19 15:44:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][280/1251]	eta 0:36:39 lr 0.000886	time 2.2607 (2.2650)	loss 4.2310 (3.8595)	grad_norm 1.0911 (1.1713)	
[2022-01-19 15:44:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][290/1251]	eta 0:36:09 lr 0.000886	time 1.9905 (2.2573)	loss 3.7419 (3.8668)	grad_norm 1.2159 (1.1714)	
[2022-01-19 15:45:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][300/1251]	eta 0:35:40 lr 0.000886	time 1.9094 (2.2511)	loss 3.9051 (3.8646)	grad_norm 1.1034 (1.1693)	
[2022-01-19 15:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][310/1251]	eta 0:35:15 lr 0.000886	time 2.2169 (2.2477)	loss 4.1636 (3.8630)	grad_norm 1.0266 (1.1703)	
[2022-01-19 15:45:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][320/1251]	eta 0:34:51 lr 0.000886	time 1.7662 (2.2461)	loss 3.5733 (3.8600)	grad_norm 1.1933 (1.1684)	
[2022-01-19 15:46:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][330/1251]	eta 0:34:29 lr 0.000886	time 2.8120 (2.2466)	loss 4.5618 (3.8640)	grad_norm 1.3347 (1.1687)	
[2022-01-19 15:46:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][340/1251]	eta 0:34:01 lr 0.000886	time 1.6735 (2.2413)	loss 4.6120 (3.8656)	grad_norm 1.1633 (1.1676)	
[2022-01-19 15:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][350/1251]	eta 0:33:40 lr 0.000885	time 2.3616 (2.2428)	loss 3.0928 (3.8583)	grad_norm 1.2004 (1.1662)	
[2022-01-19 15:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][360/1251]	eta 0:33:20 lr 0.000885	time 2.1424 (2.2449)	loss 4.6421 (3.8654)	grad_norm 1.1915 (1.1658)	
[2022-01-19 15:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][370/1251]	eta 0:32:58 lr 0.000885	time 2.0893 (2.2461)	loss 4.1422 (3.8708)	grad_norm 1.1623 (1.1672)	
[2022-01-19 15:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][380/1251]	eta 0:32:32 lr 0.000885	time 2.0481 (2.2420)	loss 4.3626 (3.8717)	grad_norm 1.0808 (1.1673)	
[2022-01-19 15:48:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][390/1251]	eta 0:32:05 lr 0.000885	time 1.9762 (2.2359)	loss 4.5557 (3.8697)	grad_norm 1.1251 (1.1694)	
[2022-01-19 15:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][400/1251]	eta 0:31:38 lr 0.000885	time 2.2137 (2.2306)	loss 4.3337 (3.8731)	grad_norm 1.0241 (1.1685)	
[2022-01-19 15:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][410/1251]	eta 0:31:13 lr 0.000885	time 1.8784 (2.2282)	loss 3.6205 (3.8661)	grad_norm 1.1644 (1.1694)	
[2022-01-19 15:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][420/1251]	eta 0:30:53 lr 0.000885	time 2.5334 (2.2301)	loss 3.4101 (3.8641)	grad_norm 1.0795 (1.1700)	
[2022-01-19 15:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][430/1251]	eta 0:30:29 lr 0.000885	time 2.9815 (2.2288)	loss 3.5937 (3.8623)	grad_norm 1.1635 (1.1710)	
[2022-01-19 15:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][440/1251]	eta 0:30:06 lr 0.000885	time 2.1502 (2.2279)	loss 2.8225 (3.8631)	grad_norm 1.0078 (1.1686)	
[2022-01-19 15:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][450/1251]	eta 0:29:45 lr 0.000885	time 1.8313 (2.2287)	loss 3.2700 (3.8602)	grad_norm 1.1982 (1.1684)	
[2022-01-19 15:51:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][460/1251]	eta 0:29:23 lr 0.000885	time 3.1082 (2.2289)	loss 4.4415 (3.8588)	grad_norm 1.2049 (1.1693)	
[2022-01-19 15:51:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][470/1251]	eta 0:29:00 lr 0.000885	time 2.7703 (2.2284)	loss 2.9594 (3.8562)	grad_norm 0.9874 (1.1695)	
[2022-01-19 15:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][480/1251]	eta 0:28:36 lr 0.000885	time 1.8051 (2.2259)	loss 3.8805 (3.8564)	grad_norm 1.3662 (1.1684)	
[2022-01-19 15:52:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][490/1251]	eta 0:28:11 lr 0.000885	time 1.9273 (2.2227)	loss 3.8401 (3.8516)	grad_norm 1.2254 (1.1687)	
[2022-01-19 15:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][500/1251]	eta 0:27:49 lr 0.000885	time 3.4457 (2.2234)	loss 3.9305 (3.8507)	grad_norm 1.0239 (1.1693)	
[2022-01-19 15:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][510/1251]	eta 0:27:25 lr 0.000885	time 2.5762 (2.2212)	loss 3.8874 (3.8540)	grad_norm 1.0929 (1.1676)	
[2022-01-19 15:53:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][520/1251]	eta 0:27:01 lr 0.000885	time 1.8448 (2.2189)	loss 3.5441 (3.8562)	grad_norm 1.3203 (1.1674)	
[2022-01-19 15:53:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][530/1251]	eta 0:26:38 lr 0.000885	time 1.7793 (2.2173)	loss 3.6522 (3.8581)	grad_norm 1.2157 (1.1674)	
[2022-01-19 15:53:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][540/1251]	eta 0:26:15 lr 0.000885	time 2.7954 (2.2165)	loss 2.6198 (3.8529)	grad_norm 1.1234 (1.1675)	
[2022-01-19 15:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][550/1251]	eta 0:25:53 lr 0.000885	time 2.4760 (2.2156)	loss 4.2040 (3.8564)	grad_norm 1.0059 (1.1660)	
[2022-01-19 15:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][560/1251]	eta 0:25:30 lr 0.000885	time 1.8671 (2.2151)	loss 4.0789 (3.8555)	grad_norm 1.4043 (1.1659)	
[2022-01-19 15:54:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][570/1251]	eta 0:25:10 lr 0.000885	time 2.2188 (2.2178)	loss 3.1529 (3.8586)	grad_norm 1.7887 (1.1688)	
[2022-01-19 15:55:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][580/1251]	eta 0:24:47 lr 0.000885	time 2.2600 (2.2170)	loss 3.2909 (3.8583)	grad_norm 1.0155 (1.1691)	
[2022-01-19 15:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][590/1251]	eta 0:24:24 lr 0.000885	time 2.1786 (2.2161)	loss 2.8965 (3.8583)	grad_norm 1.3956 (1.1685)	
[2022-01-19 15:56:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][600/1251]	eta 0:24:01 lr 0.000885	time 1.8694 (2.2148)	loss 3.7938 (3.8602)	grad_norm 1.1275 (1.1705)	
[2022-01-19 15:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][610/1251]	eta 0:23:40 lr 0.000885	time 2.4666 (2.2159)	loss 2.8416 (3.8596)	grad_norm 1.0850 (1.1706)	
[2022-01-19 15:56:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][620/1251]	eta 0:23:17 lr 0.000885	time 2.2737 (2.2144)	loss 3.8619 (3.8573)	grad_norm 0.9456 (1.1696)	
[2022-01-19 15:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][630/1251]	eta 0:22:53 lr 0.000885	time 2.1728 (2.2117)	loss 2.8024 (3.8579)	grad_norm 1.1784 (1.1694)	
[2022-01-19 15:57:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][640/1251]	eta 0:22:30 lr 0.000885	time 2.3552 (2.2111)	loss 4.1880 (3.8606)	grad_norm 1.2475 (1.1697)	
[2022-01-19 15:57:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][650/1251]	eta 0:22:09 lr 0.000885	time 2.4919 (2.2123)	loss 4.3073 (3.8614)	grad_norm 1.3444 (1.1708)	
[2022-01-19 15:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][660/1251]	eta 0:21:49 lr 0.000885	time 3.1818 (2.2158)	loss 3.5239 (3.8635)	grad_norm 1.1549 (1.1718)	
[2022-01-19 15:58:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][670/1251]	eta 0:21:27 lr 0.000885	time 2.3567 (2.2153)	loss 2.7831 (3.8628)	grad_norm 1.0994 (1.1713)	
[2022-01-19 15:59:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][680/1251]	eta 0:21:03 lr 0.000885	time 1.8551 (2.2134)	loss 3.3847 (3.8601)	grad_norm 1.4622 (1.1717)	
[2022-01-19 15:59:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][690/1251]	eta 0:20:40 lr 0.000885	time 1.9825 (2.2107)	loss 4.3959 (3.8587)	grad_norm 1.1296 (1.1717)	
[2022-01-19 15:59:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][700/1251]	eta 0:20:15 lr 0.000885	time 1.9139 (2.2064)	loss 3.1662 (3.8625)	grad_norm 1.7654 (1.1725)	
[2022-01-19 16:00:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][710/1251]	eta 0:19:52 lr 0.000885	time 2.1139 (2.2045)	loss 3.7636 (3.8630)	grad_norm 1.0704 (1.1734)	
[2022-01-19 16:00:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][720/1251]	eta 0:19:30 lr 0.000884	time 1.9398 (2.2042)	loss 4.2984 (3.8644)	grad_norm 1.2036 (1.1732)	
[2022-01-19 16:00:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][730/1251]	eta 0:19:09 lr 0.000884	time 2.7645 (2.2067)	loss 3.8195 (3.8619)	grad_norm 0.9923 (1.1722)	
[2022-01-19 16:01:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][740/1251]	eta 0:18:47 lr 0.000884	time 2.0808 (2.2072)	loss 4.1542 (3.8607)	grad_norm 1.1884 (1.1724)	
[2022-01-19 16:01:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][750/1251]	eta 0:18:26 lr 0.000884	time 2.2687 (2.2078)	loss 3.5717 (3.8628)	grad_norm 1.0527 (1.1725)	
[2022-01-19 16:01:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][760/1251]	eta 0:18:04 lr 0.000884	time 1.9196 (2.2089)	loss 2.8571 (3.8615)	grad_norm 1.0362 (1.1711)	
[2022-01-19 16:02:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][770/1251]	eta 0:17:42 lr 0.000884	time 2.0983 (2.2087)	loss 4.4271 (3.8602)	grad_norm 1.1613 (1.1702)	
[2022-01-19 16:02:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][780/1251]	eta 0:17:19 lr 0.000884	time 1.8869 (2.2069)	loss 3.9182 (3.8606)	grad_norm 1.2617 (1.1707)	
[2022-01-19 16:02:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][790/1251]	eta 0:16:56 lr 0.000884	time 2.0015 (2.2056)	loss 3.6359 (3.8607)	grad_norm 1.1967 (1.1697)	
[2022-01-19 16:03:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][800/1251]	eta 0:16:33 lr 0.000884	time 1.8885 (2.2034)	loss 3.4269 (3.8583)	grad_norm 1.0420 (1.1687)	
[2022-01-19 16:03:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][810/1251]	eta 0:16:11 lr 0.000884	time 2.2823 (2.2032)	loss 4.0779 (3.8572)	grad_norm 1.1040 (1.1680)	
[2022-01-19 16:04:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][820/1251]	eta 0:15:50 lr 0.000884	time 2.5150 (2.2042)	loss 4.0807 (3.8555)	grad_norm 1.0596 (1.1694)	
[2022-01-19 16:04:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][830/1251]	eta 0:15:27 lr 0.000884	time 1.7338 (2.2036)	loss 3.6460 (3.8557)	grad_norm 1.0687 (1.1692)	
[2022-01-19 16:04:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][840/1251]	eta 0:15:05 lr 0.000884	time 1.9004 (2.2032)	loss 4.1051 (3.8547)	grad_norm 0.9822 (1.1686)	
[2022-01-19 16:05:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][850/1251]	eta 0:14:43 lr 0.000884	time 2.0093 (2.2024)	loss 4.1044 (3.8557)	grad_norm 1.2709 (1.1684)	
[2022-01-19 16:05:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][860/1251]	eta 0:14:21 lr 0.000884	time 3.0782 (2.2041)	loss 2.6910 (3.8550)	grad_norm 1.0747 (1.1676)	
[2022-01-19 16:05:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][870/1251]	eta 0:13:59 lr 0.000884	time 1.4075 (2.2043)	loss 3.1904 (3.8516)	grad_norm 1.0768 (1.1666)	
[2022-01-19 16:06:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][880/1251]	eta 0:13:38 lr 0.000884	time 1.9369 (2.2072)	loss 4.4477 (3.8505)	grad_norm 1.0317 (1.1662)	
[2022-01-19 16:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][890/1251]	eta 0:13:17 lr 0.000884	time 2.6029 (2.2083)	loss 4.7768 (3.8538)	grad_norm 1.1679 (1.1666)	
[2022-01-19 16:07:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][900/1251]	eta 0:12:54 lr 0.000884	time 2.1709 (2.2067)	loss 3.0328 (3.8564)	grad_norm 1.0306 (1.1667)	
[2022-01-19 16:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][910/1251]	eta 0:12:31 lr 0.000884	time 1.6925 (2.2032)	loss 4.2919 (3.8581)	grad_norm 1.1476 (1.1667)	
[2022-01-19 16:07:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][920/1251]	eta 0:12:08 lr 0.000884	time 1.7762 (2.1999)	loss 4.1095 (3.8599)	grad_norm 0.9849 (1.1669)	
[2022-01-19 16:07:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][930/1251]	eta 0:11:45 lr 0.000884	time 1.6623 (2.1981)	loss 3.9349 (3.8584)	grad_norm 1.1266 (1.1654)	
[2022-01-19 16:08:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][940/1251]	eta 0:11:24 lr 0.000884	time 2.2451 (2.2011)	loss 3.2564 (3.8595)	grad_norm 1.1748 (1.1666)	
[2022-01-19 16:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][950/1251]	eta 0:11:02 lr 0.000884	time 2.4704 (2.2014)	loss 3.1715 (3.8570)	grad_norm 1.2578 (1.1667)	
[2022-01-19 16:09:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][960/1251]	eta 0:10:41 lr 0.000884	time 2.8778 (2.2029)	loss 3.5912 (3.8554)	grad_norm 1.0685 (1.1662)	
[2022-01-19 16:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][970/1251]	eta 0:10:19 lr 0.000884	time 1.7332 (2.2044)	loss 4.1835 (3.8563)	grad_norm 1.2273 (1.1661)	
[2022-01-19 16:09:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][980/1251]	eta 0:09:57 lr 0.000884	time 2.1754 (2.2051)	loss 4.1458 (3.8553)	grad_norm 0.9711 (1.1661)	
[2022-01-19 16:10:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][990/1251]	eta 0:09:35 lr 0.000884	time 1.9280 (2.2045)	loss 2.7978 (3.8537)	grad_norm 0.9981 (1.1656)	
[2022-01-19 16:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1000/1251]	eta 0:09:12 lr 0.000884	time 1.9068 (2.2023)	loss 2.9073 (3.8564)	grad_norm 1.1798 (1.1656)	
[2022-01-19 16:10:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1010/1251]	eta 0:08:50 lr 0.000884	time 1.8756 (2.2011)	loss 4.4812 (3.8575)	grad_norm 1.2791 (1.1660)	
[2022-01-19 16:11:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1020/1251]	eta 0:08:28 lr 0.000884	time 2.1705 (2.2001)	loss 3.5441 (3.8571)	grad_norm 1.2314 (1.1667)	
[2022-01-19 16:11:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1030/1251]	eta 0:08:06 lr 0.000884	time 2.3811 (2.1998)	loss 4.2870 (3.8598)	grad_norm 1.0713 (1.1660)	
[2022-01-19 16:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1040/1251]	eta 0:07:44 lr 0.000884	time 3.0754 (2.2004)	loss 4.6060 (3.8599)	grad_norm 1.5542 (1.1666)	
[2022-01-19 16:12:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1050/1251]	eta 0:07:22 lr 0.000884	time 2.3363 (2.2011)	loss 3.7373 (3.8604)	grad_norm 1.1368 (1.1660)	
[2022-01-19 16:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1060/1251]	eta 0:07:00 lr 0.000884	time 2.5412 (2.2014)	loss 3.8289 (3.8628)	grad_norm 1.2932 (1.1661)	
[2022-01-19 16:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1070/1251]	eta 0:06:38 lr 0.000884	time 1.9008 (2.2014)	loss 3.7550 (3.8615)	grad_norm 1.2111 (1.1654)	
[2022-01-19 16:13:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1080/1251]	eta 0:06:16 lr 0.000884	time 1.8173 (2.2021)	loss 3.7829 (3.8603)	grad_norm 1.1210 (1.1652)	
[2022-01-19 16:13:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1090/1251]	eta 0:05:54 lr 0.000884	time 3.0848 (2.2027)	loss 4.1599 (3.8598)	grad_norm 1.1772 (1.1646)	
[2022-01-19 16:14:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1100/1251]	eta 0:05:32 lr 0.000883	time 2.3141 (2.2017)	loss 4.1318 (3.8618)	grad_norm 0.9927 (1.1642)	
[2022-01-19 16:14:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1110/1251]	eta 0:05:10 lr 0.000883	time 2.0806 (2.1996)	loss 4.3142 (3.8642)	grad_norm 1.0582 (1.1638)	
[2022-01-19 16:14:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1120/1251]	eta 0:04:47 lr 0.000883	time 1.8707 (2.1983)	loss 3.9036 (3.8647)	grad_norm 1.1509 (1.1638)	
[2022-01-19 16:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1130/1251]	eta 0:04:26 lr 0.000883	time 3.0125 (2.1991)	loss 4.2947 (3.8653)	grad_norm 1.1137 (1.1637)	
[2022-01-19 16:15:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1140/1251]	eta 0:04:04 lr 0.000883	time 2.1079 (2.1993)	loss 2.6393 (3.8637)	grad_norm 1.3155 (1.1642)	
[2022-01-19 16:16:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1150/1251]	eta 0:03:42 lr 0.000883	time 2.8646 (2.2003)	loss 4.1468 (3.8620)	grad_norm 1.1434 (1.1642)	
[2022-01-19 16:16:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1160/1251]	eta 0:03:20 lr 0.000883	time 2.3216 (2.2003)	loss 3.1678 (3.8603)	grad_norm 0.9540 (1.1638)	
[2022-01-19 16:16:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1170/1251]	eta 0:02:58 lr 0.000883	time 1.8786 (2.2004)	loss 3.7507 (3.8593)	grad_norm 1.0693 (1.1630)	
[2022-01-19 16:17:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1180/1251]	eta 0:02:36 lr 0.000883	time 1.9423 (2.1988)	loss 3.7583 (3.8604)	grad_norm 1.0866 (1.1629)	
[2022-01-19 16:17:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1190/1251]	eta 0:02:14 lr 0.000883	time 1.8514 (2.1980)	loss 4.6458 (3.8615)	grad_norm 1.0907 (1.1635)	
[2022-01-19 16:17:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1200/1251]	eta 0:01:52 lr 0.000883	time 2.4728 (2.1977)	loss 3.9810 (3.8610)	grad_norm 1.0773 (1.1635)	
[2022-01-19 16:18:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1210/1251]	eta 0:01:30 lr 0.000883	time 2.2274 (2.1983)	loss 3.7557 (3.8615)	grad_norm 1.2673 (1.1635)	
[2022-01-19 16:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1220/1251]	eta 0:01:08 lr 0.000883	time 2.0691 (2.1980)	loss 4.3001 (3.8618)	grad_norm 1.2265 (1.1635)	
[2022-01-19 16:18:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1230/1251]	eta 0:00:46 lr 0.000883	time 2.1316 (2.1984)	loss 4.1334 (3.8612)	grad_norm 1.1072 (1.1642)	
[2022-01-19 16:19:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1240/1251]	eta 0:00:24 lr 0.000883	time 2.1022 (2.1975)	loss 2.9529 (3.8621)	grad_norm 1.1941 (1.1644)	
[2022-01-19 16:19:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [66/300][1250/1251]	eta 0:00:02 lr 0.000883	time 1.1780 (2.1927)	loss 4.0723 (3.8640)	grad_norm 1.0268 (1.1634)	
[2022-01-19 16:19:36 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 66 training takes 0:45:43
[2022-01-19 16:19:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.783 (18.783)	Loss 1.2677 (1.2677)	Acc@1 71.875 (71.875)	Acc@5 90.820 (90.820)	
[2022-01-19 16:20:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.933 (3.434)	Loss 1.2233 (1.2413)	Acc@1 72.949 (71.600)	Acc@5 91.309 (90.723)	
[2022-01-19 16:20:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.250 (2.578)	Loss 1.1833 (1.2331)	Acc@1 74.121 (71.735)	Acc@5 91.992 (90.946)	
[2022-01-19 16:20:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.856 (2.362)	Loss 1.2428 (1.2350)	Acc@1 72.266 (71.554)	Acc@5 90.918 (91.044)	
[2022-01-19 16:21:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.299 (2.189)	Loss 1.2897 (1.2338)	Acc@1 70.410 (71.601)	Acc@5 91.211 (91.063)	
[2022-01-19 16:21:13 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 71.552 Acc@5 90.992
[2022-01-19 16:21:13 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 71.6%
[2022-01-19 16:21:13 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 71.70%
[2022-01-19 16:21:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][0/1251]	eta 7:21:17 lr 0.000883	time 21.1652 (21.1652)	loss 3.7135 (3.7135)	grad_norm 1.1821 (1.1821)	
[2022-01-19 16:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][10/1251]	eta 1:22:52 lr 0.000883	time 3.0057 (4.0066)	loss 3.4832 (3.8675)	grad_norm 1.3010 (1.1895)	
[2022-01-19 16:22:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][20/1251]	eta 1:05:56 lr 0.000883	time 1.5393 (3.2139)	loss 4.1145 (3.7493)	grad_norm 1.3016 (1.1983)	
[2022-01-19 16:22:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][30/1251]	eta 0:57:35 lr 0.000883	time 1.5180 (2.8298)	loss 4.1800 (3.8311)	grad_norm 1.3615 (1.2182)	
[2022-01-19 16:23:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][40/1251]	eta 0:56:33 lr 0.000883	time 8.2855 (2.8023)	loss 3.7601 (3.7854)	grad_norm 1.1083 (1.2084)	
[2022-01-19 16:23:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][50/1251]	eta 0:54:28 lr 0.000883	time 2.2790 (2.7213)	loss 4.4393 (3.7785)	grad_norm 1.0496 (1.2009)	
[2022-01-19 16:23:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][60/1251]	eta 0:52:00 lr 0.000883	time 1.9892 (2.6202)	loss 4.8535 (3.8301)	grad_norm 1.0447 (1.1885)	
[2022-01-19 16:24:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][70/1251]	eta 0:49:59 lr 0.000883	time 1.5949 (2.5395)	loss 4.1173 (3.8418)	grad_norm 1.1831 (1.1852)	
[2022-01-19 16:24:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][80/1251]	eta 0:48:34 lr 0.000883	time 3.6211 (2.4888)	loss 3.5231 (3.8356)	grad_norm 1.2481 (1.1740)	
[2022-01-19 16:24:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][90/1251]	eta 0:47:28 lr 0.000883	time 2.2288 (2.4535)	loss 4.0404 (3.8132)	grad_norm 1.1127 (1.1713)	
[2022-01-19 16:25:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][100/1251]	eta 0:46:46 lr 0.000883	time 2.4994 (2.4379)	loss 3.0710 (3.7792)	grad_norm 1.4053 (1.1660)	
[2022-01-19 16:25:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][110/1251]	eta 0:45:42 lr 0.000883	time 1.6457 (2.4032)	loss 4.1153 (3.7905)	grad_norm 1.0686 (1.1625)	
[2022-01-19 16:26:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][120/1251]	eta 0:45:15 lr 0.000883	time 3.8674 (2.4008)	loss 4.4222 (3.8088)	grad_norm 1.2137 (1.1734)	
[2022-01-19 16:26:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][130/1251]	eta 0:44:38 lr 0.000883	time 2.2775 (2.3890)	loss 2.8112 (3.7938)	grad_norm 1.2270 (1.1755)	
[2022-01-19 16:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][140/1251]	eta 0:43:49 lr 0.000883	time 2.5775 (2.3669)	loss 3.8180 (3.7793)	grad_norm 1.0156 (1.1709)	
[2022-01-19 16:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][150/1251]	eta 0:43:09 lr 0.000883	time 1.9578 (2.3521)	loss 3.0932 (3.7824)	grad_norm 1.0761 (1.1664)	
[2022-01-19 16:27:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][160/1251]	eta 0:42:32 lr 0.000883	time 2.2109 (2.3394)	loss 3.8401 (3.7788)	grad_norm 1.1334 (1.1644)	
[2022-01-19 16:27:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][170/1251]	eta 0:42:17 lr 0.000883	time 1.9688 (2.3471)	loss 4.1864 (3.7734)	grad_norm 1.5997 (1.1621)	
[2022-01-19 16:28:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][180/1251]	eta 0:41:41 lr 0.000883	time 2.0341 (2.3352)	loss 3.8549 (3.7903)	grad_norm 1.0256 (1.1579)	
[2022-01-19 16:28:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][190/1251]	eta 0:41:03 lr 0.000883	time 1.6255 (2.3215)	loss 4.1941 (3.7874)	grad_norm 1.0620 (1.1555)	
[2022-01-19 16:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][200/1251]	eta 0:40:31 lr 0.000883	time 1.9432 (2.3135)	loss 4.2612 (3.8069)	grad_norm 1.0807 (1.1527)	
[2022-01-19 16:29:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][210/1251]	eta 0:40:04 lr 0.000883	time 2.2333 (2.3101)	loss 2.7703 (3.7988)	grad_norm 1.0917 (1.1538)	
[2022-01-19 16:29:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][220/1251]	eta 0:39:30 lr 0.000882	time 1.8699 (2.2990)	loss 3.9497 (3.8020)	grad_norm 1.1366 (1.1533)	
[2022-01-19 16:30:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][230/1251]	eta 0:38:58 lr 0.000882	time 2.0229 (2.2906)	loss 3.5135 (3.8101)	grad_norm 1.1188 (1.1526)	
[2022-01-19 16:30:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][240/1251]	eta 0:38:28 lr 0.000882	time 2.2552 (2.2837)	loss 3.8691 (3.8093)	grad_norm 1.1148 (1.1543)	
[2022-01-19 16:30:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][250/1251]	eta 0:38:05 lr 0.000882	time 2.2162 (2.2836)	loss 4.1421 (3.8006)	grad_norm 1.2373 (1.1526)	
[2022-01-19 16:31:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][260/1251]	eta 0:37:38 lr 0.000882	time 2.4994 (2.2793)	loss 3.5261 (3.7989)	grad_norm 1.1084 (1.1527)	
[2022-01-19 16:31:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][270/1251]	eta 0:37:09 lr 0.000882	time 1.8591 (2.2722)	loss 4.3860 (3.8077)	grad_norm 1.1826 (1.1552)	
[2022-01-19 16:31:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][280/1251]	eta 0:36:49 lr 0.000882	time 2.5343 (2.2753)	loss 4.1421 (3.8220)	grad_norm 1.4207 (1.1568)	
[2022-01-19 16:32:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][290/1251]	eta 0:36:23 lr 0.000882	time 1.9609 (2.2722)	loss 3.7107 (3.8208)	grad_norm 0.9676 (1.1556)	
[2022-01-19 16:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][300/1251]	eta 0:35:53 lr 0.000882	time 1.8658 (2.2640)	loss 4.2279 (3.8130)	grad_norm 0.9652 (1.1536)	
[2022-01-19 16:32:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][310/1251]	eta 0:35:23 lr 0.000882	time 2.5280 (2.2563)	loss 3.8002 (3.8127)	grad_norm 1.3138 (1.1524)	
[2022-01-19 16:33:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][320/1251]	eta 0:34:52 lr 0.000882	time 1.9105 (2.2475)	loss 4.1509 (3.8135)	grad_norm 1.1192 (1.1500)	
[2022-01-19 16:33:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][330/1251]	eta 0:34:22 lr 0.000882	time 2.0411 (2.2397)	loss 3.7996 (3.8179)	grad_norm 1.2186 (1.1493)	
[2022-01-19 16:33:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][340/1251]	eta 0:33:57 lr 0.000882	time 2.1991 (2.2369)	loss 4.5904 (3.8221)	grad_norm 1.0336 (1.1506)	
[2022-01-19 16:34:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][350/1251]	eta 0:33:36 lr 0.000882	time 2.5601 (2.2380)	loss 4.3872 (3.8273)	grad_norm 1.2207 (1.1510)	
[2022-01-19 16:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][360/1251]	eta 0:33:12 lr 0.000882	time 1.8836 (2.2359)	loss 3.9536 (3.8311)	grad_norm 1.3555 (1.1522)	
[2022-01-19 16:35:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][370/1251]	eta 0:32:51 lr 0.000882	time 1.8917 (2.2383)	loss 3.2129 (3.8302)	grad_norm 1.3021 (1.1522)	
[2022-01-19 16:35:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][380/1251]	eta 0:32:27 lr 0.000882	time 2.3416 (2.2364)	loss 3.6572 (3.8284)	grad_norm 1.1293 (1.1521)	
[2022-01-19 16:35:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][390/1251]	eta 0:32:04 lr 0.000882	time 2.3603 (2.2357)	loss 4.3642 (3.8331)	grad_norm 1.1800 (1.1513)	
[2022-01-19 16:36:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][400/1251]	eta 0:31:40 lr 0.000882	time 2.0800 (2.2329)	loss 3.4221 (3.8293)	grad_norm 1.1716 (1.1508)	
[2022-01-19 16:36:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][410/1251]	eta 0:31:15 lr 0.000882	time 1.9291 (2.2298)	loss 4.1298 (3.8336)	grad_norm 1.1752 (1.1496)	
[2022-01-19 16:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][420/1251]	eta 0:30:51 lr 0.000882	time 1.9558 (2.2278)	loss 4.5193 (3.8379)	grad_norm 0.9727 (1.1499)	
[2022-01-19 16:37:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][430/1251]	eta 0:30:31 lr 0.000882	time 3.1228 (2.2304)	loss 2.7893 (3.8335)	grad_norm 1.1749 (1.1505)	
[2022-01-19 16:37:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][440/1251]	eta 0:30:09 lr 0.000882	time 2.5034 (2.2306)	loss 4.2056 (3.8331)	grad_norm 1.4460 (1.1525)	
[2022-01-19 16:38:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][450/1251]	eta 0:29:50 lr 0.000882	time 1.6784 (2.2356)	loss 4.2833 (3.8337)	grad_norm 1.1324 (1.1533)	
[2022-01-19 16:38:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][460/1251]	eta 0:29:28 lr 0.000882	time 2.1724 (2.2355)	loss 3.7569 (3.8328)	grad_norm 1.2330 (1.1533)	
[2022-01-19 16:38:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][470/1251]	eta 0:29:05 lr 0.000882	time 2.9278 (2.2345)	loss 3.3248 (3.8353)	grad_norm 1.0644 (1.1532)	
[2022-01-19 16:39:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][480/1251]	eta 0:28:41 lr 0.000882	time 1.8348 (2.2324)	loss 4.0465 (3.8336)	grad_norm 1.1130 (1.1563)	
[2022-01-19 16:39:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][490/1251]	eta 0:28:16 lr 0.000882	time 1.9006 (2.2297)	loss 3.6540 (3.8367)	grad_norm 1.1780 (1.1563)	
[2022-01-19 16:39:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][500/1251]	eta 0:27:51 lr 0.000882	time 1.8750 (2.2260)	loss 3.8654 (3.8377)	grad_norm 1.0432 (1.1569)	
[2022-01-19 16:40:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][510/1251]	eta 0:27:28 lr 0.000882	time 2.8423 (2.2253)	loss 4.2750 (3.8422)	grad_norm 1.0449 (1.1584)	
[2022-01-19 16:40:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][520/1251]	eta 0:27:05 lr 0.000882	time 2.2161 (2.2238)	loss 3.9885 (3.8460)	grad_norm 1.0587 (1.1590)	
[2022-01-19 16:40:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][530/1251]	eta 0:26:44 lr 0.000882	time 3.0805 (2.2252)	loss 4.2621 (3.8449)	grad_norm 1.2255 (1.1611)	
[2022-01-19 16:41:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][540/1251]	eta 0:26:23 lr 0.000882	time 2.7197 (2.2268)	loss 3.6834 (3.8450)	grad_norm 1.2847 (1.1625)	
[2022-01-19 16:41:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][550/1251]	eta 0:26:01 lr 0.000882	time 2.6779 (2.2270)	loss 3.9762 (3.8490)	grad_norm 1.0575 (1.1627)	
[2022-01-19 16:42:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][560/1251]	eta 0:25:37 lr 0.000882	time 2.1592 (2.2247)	loss 2.6899 (3.8438)	grad_norm 1.1700 (1.1615)	
[2022-01-19 16:42:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][570/1251]	eta 0:25:14 lr 0.000882	time 3.1200 (2.2233)	loss 4.1880 (3.8455)	grad_norm 1.1810 (1.1614)	
[2022-01-19 16:42:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][580/1251]	eta 0:24:49 lr 0.000882	time 2.0990 (2.2203)	loss 3.9582 (3.8446)	grad_norm 1.1711 (1.1609)	
[2022-01-19 16:43:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][590/1251]	eta 0:24:27 lr 0.000881	time 2.2811 (2.2204)	loss 4.3125 (3.8436)	grad_norm 1.4003 (1.1618)	
[2022-01-19 16:43:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][600/1251]	eta 0:24:05 lr 0.000881	time 2.2612 (2.2204)	loss 4.3183 (3.8473)	grad_norm 1.1424 (1.1631)	
[2022-01-19 16:43:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][610/1251]	eta 0:23:45 lr 0.000881	time 3.8148 (2.2240)	loss 3.5767 (3.8458)	grad_norm 1.1864 (1.1643)	
[2022-01-19 16:44:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][620/1251]	eta 0:23:21 lr 0.000881	time 1.8816 (2.2218)	loss 3.8582 (3.8414)	grad_norm 1.4644 (1.1652)	
[2022-01-19 16:44:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][630/1251]	eta 0:22:58 lr 0.000881	time 1.9128 (2.2198)	loss 4.2513 (3.8401)	grad_norm 1.0574 (1.1642)	
[2022-01-19 16:44:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][640/1251]	eta 0:22:35 lr 0.000881	time 1.8060 (2.2189)	loss 3.3234 (3.8406)	grad_norm 1.0718 (1.1630)	
[2022-01-19 16:45:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][650/1251]	eta 0:22:14 lr 0.000881	time 3.3206 (2.2199)	loss 2.6438 (3.8426)	grad_norm 1.0705 (1.1617)	
[2022-01-19 16:45:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][660/1251]	eta 0:21:51 lr 0.000881	time 1.9618 (2.2185)	loss 4.1220 (3.8456)	grad_norm 1.1455 (1.1612)	
[2022-01-19 16:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][670/1251]	eta 0:21:27 lr 0.000881	time 1.9578 (2.2153)	loss 3.7269 (3.8442)	grad_norm 1.2443 (1.1618)	
[2022-01-19 16:46:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][680/1251]	eta 0:21:03 lr 0.000881	time 2.4053 (2.2128)	loss 4.7349 (3.8489)	grad_norm 0.8970 (1.1610)	
[2022-01-19 16:46:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][690/1251]	eta 0:20:41 lr 0.000881	time 1.9322 (2.2126)	loss 4.0489 (3.8512)	grad_norm 1.0486 (1.1599)	
[2022-01-19 16:47:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][700/1251]	eta 0:20:21 lr 0.000881	time 2.7502 (2.2167)	loss 3.7348 (3.8460)	grad_norm 1.4074 (1.1600)	
[2022-01-19 16:47:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][710/1251]	eta 0:19:58 lr 0.000881	time 1.5082 (2.2151)	loss 4.4541 (3.8482)	grad_norm 1.1414 (1.1602)	
[2022-01-19 16:47:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][720/1251]	eta 0:19:35 lr 0.000881	time 2.1125 (2.2143)	loss 3.9718 (3.8458)	grad_norm 1.2242 (1.1613)	
[2022-01-19 16:48:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][730/1251]	eta 0:19:13 lr 0.000881	time 2.0994 (2.2148)	loss 4.1893 (3.8452)	grad_norm 1.4501 (1.1614)	
[2022-01-19 16:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][740/1251]	eta 0:18:52 lr 0.000881	time 2.2116 (2.2156)	loss 3.9574 (3.8442)	grad_norm 0.9915 (1.1611)	
[2022-01-19 16:48:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][750/1251]	eta 0:18:29 lr 0.000881	time 1.5501 (2.2142)	loss 4.3475 (3.8430)	grad_norm 1.2074 (1.1616)	
[2022-01-19 16:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][760/1251]	eta 0:18:06 lr 0.000881	time 2.0724 (2.2130)	loss 4.3524 (3.8439)	grad_norm 1.1521 (1.1612)	
[2022-01-19 16:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][770/1251]	eta 0:17:44 lr 0.000881	time 1.8788 (2.2121)	loss 4.0285 (3.8462)	grad_norm 1.0996 (1.1611)	
[2022-01-19 16:50:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][780/1251]	eta 0:17:21 lr 0.000881	time 2.2901 (2.2122)	loss 4.5686 (3.8460)	grad_norm 0.9900 (1.1620)	
[2022-01-19 16:50:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][790/1251]	eta 0:16:58 lr 0.000881	time 2.4530 (2.2103)	loss 3.2946 (3.8472)	grad_norm 1.0785 (1.1621)	
[2022-01-19 16:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][800/1251]	eta 0:16:36 lr 0.000881	time 2.3504 (2.2094)	loss 2.7544 (3.8445)	grad_norm 0.9944 (1.1614)	
[2022-01-19 16:51:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][810/1251]	eta 0:16:14 lr 0.000881	time 2.1180 (2.2104)	loss 4.5653 (3.8449)	grad_norm 1.1214 (1.1630)	
[2022-01-19 16:51:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][820/1251]	eta 0:15:53 lr 0.000881	time 2.4152 (2.2132)	loss 4.1817 (3.8485)	grad_norm 1.1046 (1.1645)	
[2022-01-19 16:51:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][830/1251]	eta 0:15:31 lr 0.000881	time 1.6613 (2.2129)	loss 2.7260 (3.8491)	grad_norm 1.1887 (1.1644)	
[2022-01-19 16:52:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][840/1251]	eta 0:15:08 lr 0.000881	time 1.5798 (2.2107)	loss 4.3408 (3.8500)	grad_norm 1.0020 (1.1637)	
[2022-01-19 16:52:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][850/1251]	eta 0:14:45 lr 0.000881	time 1.6449 (2.2090)	loss 3.1118 (3.8506)	grad_norm 1.0886 (1.1636)	
[2022-01-19 16:52:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][860/1251]	eta 0:14:23 lr 0.000881	time 2.0601 (2.2075)	loss 4.5133 (3.8546)	grad_norm 1.0659 (1.1632)	
[2022-01-19 16:53:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][870/1251]	eta 0:14:00 lr 0.000881	time 2.2970 (2.2060)	loss 3.2849 (3.8577)	grad_norm 1.0102 (1.1622)	
[2022-01-19 16:53:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][880/1251]	eta 0:13:38 lr 0.000881	time 2.3848 (2.2066)	loss 3.8752 (3.8577)	grad_norm 1.1342 (1.1616)	
[2022-01-19 16:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][890/1251]	eta 0:13:16 lr 0.000881	time 1.9029 (2.2064)	loss 4.4367 (3.8577)	grad_norm 1.0440 (1.1604)	
[2022-01-19 16:54:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][900/1251]	eta 0:12:54 lr 0.000881	time 1.9835 (2.2078)	loss 2.9478 (3.8591)	grad_norm 1.0661 (1.1597)	
[2022-01-19 16:54:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][910/1251]	eta 0:12:33 lr 0.000881	time 1.5593 (2.2087)	loss 3.1025 (3.8595)	grad_norm 1.0747 (1.1590)	
[2022-01-19 16:55:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][920/1251]	eta 0:12:12 lr 0.000881	time 3.2061 (2.2120)	loss 4.0147 (3.8574)	grad_norm 1.1748 (1.1589)	
[2022-01-19 16:55:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][930/1251]	eta 0:11:49 lr 0.000881	time 1.8001 (2.2101)	loss 3.2101 (3.8577)	grad_norm 1.0445 (1.1583)	
[2022-01-19 16:55:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][940/1251]	eta 0:11:26 lr 0.000881	time 1.9567 (2.2074)	loss 4.4824 (3.8604)	grad_norm 1.5995 (1.1600)	
[2022-01-19 16:56:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][950/1251]	eta 0:11:03 lr 0.000881	time 2.0127 (2.2048)	loss 3.5805 (3.8563)	grad_norm 0.9945 (1.1603)	
[2022-01-19 16:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][960/1251]	eta 0:10:41 lr 0.000880	time 3.3384 (2.2049)	loss 3.1719 (3.8541)	grad_norm 0.9886 (1.1606)	
[2022-01-19 16:56:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][970/1251]	eta 0:10:19 lr 0.000880	time 1.9014 (2.2058)	loss 3.4022 (3.8525)	grad_norm 1.1308 (1.1606)	
[2022-01-19 16:57:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][980/1251]	eta 0:09:57 lr 0.000880	time 2.2337 (2.2059)	loss 4.1778 (3.8523)	grad_norm 1.0694 (1.1601)	
[2022-01-19 16:57:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][990/1251]	eta 0:09:35 lr 0.000880	time 2.1485 (2.2055)	loss 4.2285 (3.8560)	grad_norm 1.3881 (1.1607)	
[2022-01-19 16:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1000/1251]	eta 0:09:13 lr 0.000880	time 2.5234 (2.2034)	loss 3.5741 (3.8567)	grad_norm 1.3961 (1.1612)	
[2022-01-19 16:58:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1010/1251]	eta 0:08:51 lr 0.000880	time 2.5945 (2.2034)	loss 4.3182 (3.8565)	grad_norm 1.0891 (1.1610)	
[2022-01-19 16:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1020/1251]	eta 0:08:28 lr 0.000880	time 1.9067 (2.2022)	loss 3.7476 (3.8565)	grad_norm 1.1177 (1.1601)	
[2022-01-19 16:59:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1030/1251]	eta 0:08:07 lr 0.000880	time 2.4638 (2.2039)	loss 4.3348 (3.8601)	grad_norm 1.0652 (1.1607)	
[2022-01-19 16:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1040/1251]	eta 0:07:45 lr 0.000880	time 2.4771 (2.2047)	loss 4.0942 (3.8598)	grad_norm 1.2247 (1.1606)	
[2022-01-19 16:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1050/1251]	eta 0:07:23 lr 0.000880	time 2.4864 (2.2046)	loss 3.1278 (3.8589)	grad_norm 1.3233 (1.1601)	
[2022-01-19 17:00:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1060/1251]	eta 0:07:01 lr 0.000880	time 1.5586 (2.2042)	loss 3.2670 (3.8593)	grad_norm 1.4643 (1.1608)	
[2022-01-19 17:00:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1070/1251]	eta 0:06:38 lr 0.000880	time 1.9477 (2.2032)	loss 3.1635 (3.8580)	grad_norm 0.9861 (1.1610)	
[2022-01-19 17:00:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1080/1251]	eta 0:06:16 lr 0.000880	time 2.1960 (2.2018)	loss 4.0734 (3.8590)	grad_norm 1.3920 (1.1606)	
[2022-01-19 17:01:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1090/1251]	eta 0:05:54 lr 0.000880	time 1.7685 (2.2012)	loss 4.2948 (3.8583)	grad_norm 1.5268 (1.1605)	
[2022-01-19 17:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1100/1251]	eta 0:05:32 lr 0.000880	time 2.1961 (2.2019)	loss 4.0032 (3.8615)	grad_norm 1.3037 (1.1606)	
[2022-01-19 17:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1110/1251]	eta 0:05:10 lr 0.000880	time 1.7170 (2.2013)	loss 4.0504 (3.8628)	grad_norm 1.0220 (1.1603)	
[2022-01-19 17:02:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1120/1251]	eta 0:04:48 lr 0.000880	time 2.5078 (2.2034)	loss 4.3103 (3.8627)	grad_norm 1.3024 (1.1598)	
[2022-01-19 17:02:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1130/1251]	eta 0:04:26 lr 0.000880	time 2.4327 (2.2041)	loss 3.6169 (3.8643)	grad_norm 1.0250 (1.1594)	
[2022-01-19 17:03:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1140/1251]	eta 0:04:04 lr 0.000880	time 1.7373 (2.2035)	loss 3.4438 (3.8649)	grad_norm 1.1189 (1.1585)	
[2022-01-19 17:03:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1150/1251]	eta 0:03:42 lr 0.000880	time 1.6631 (2.2017)	loss 4.1286 (3.8640)	grad_norm 1.1818 (1.1586)	
[2022-01-19 17:03:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1160/1251]	eta 0:03:20 lr 0.000880	time 2.0027 (2.2018)	loss 4.5790 (3.8650)	grad_norm 1.0805 (1.1580)	
[2022-01-19 17:04:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1170/1251]	eta 0:02:58 lr 0.000880	time 2.0349 (2.2015)	loss 3.5887 (3.8621)	grad_norm 1.0059 (1.1574)	
[2022-01-19 17:04:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1180/1251]	eta 0:02:36 lr 0.000880	time 2.0159 (2.2009)	loss 3.9234 (3.8634)	grad_norm 1.1808 (1.1580)	
[2022-01-19 17:04:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1190/1251]	eta 0:02:14 lr 0.000880	time 1.8239 (2.2004)	loss 4.0269 (3.8644)	grad_norm 0.9845 (1.1577)	
[2022-01-19 17:05:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1200/1251]	eta 0:01:52 lr 0.000880	time 2.2631 (2.2008)	loss 4.4381 (3.8612)	grad_norm 1.0939 (1.1577)	
[2022-01-19 17:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1210/1251]	eta 0:01:30 lr 0.000880	time 1.9037 (2.1997)	loss 2.8778 (3.8589)	grad_norm 1.0498 (1.1578)	
[2022-01-19 17:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1220/1251]	eta 0:01:08 lr 0.000880	time 2.4445 (2.2016)	loss 3.9650 (3.8605)	grad_norm 1.1254 (1.1584)	
[2022-01-19 17:06:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1230/1251]	eta 0:00:46 lr 0.000880	time 1.9015 (2.2009)	loss 3.5544 (3.8605)	grad_norm 0.8904 (1.1585)	
[2022-01-19 17:06:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1240/1251]	eta 0:00:24 lr 0.000880	time 1.6748 (2.1991)	loss 3.2950 (3.8585)	grad_norm 1.2541 (1.1587)	
[2022-01-19 17:06:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [67/300][1250/1251]	eta 0:00:02 lr 0.000880	time 1.3495 (2.1938)	loss 4.2983 (3.8570)	grad_norm 1.4103 (1.1587)	
[2022-01-19 17:06:58 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 67 training takes 0:45:44
[2022-01-19 17:07:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.642 (18.642)	Loss 1.2078 (1.2078)	Acc@1 70.215 (70.215)	Acc@5 90.820 (90.820)	
[2022-01-19 17:07:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.931 (3.300)	Loss 1.1690 (1.2004)	Acc@1 71.973 (71.973)	Acc@5 91.016 (90.989)	
[2022-01-19 17:07:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.693 (2.482)	Loss 1.1746 (1.1862)	Acc@1 72.754 (72.214)	Acc@5 91.699 (91.127)	
[2022-01-19 17:08:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.964 (2.240)	Loss 1.2327 (1.1934)	Acc@1 70.215 (71.979)	Acc@5 91.602 (91.079)	
[2022-01-19 17:08:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.096 (2.182)	Loss 1.1154 (1.1969)	Acc@1 73.438 (71.901)	Acc@5 92.969 (91.078)	
[2022-01-19 17:08:35 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 71.960 Acc@5 91.110
[2022-01-19 17:08:35 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.0%
[2022-01-19 17:08:35 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 71.96%
[2022-01-19 17:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][0/1251]	eta 7:32:40 lr 0.000880	time 21.7107 (21.7107)	loss 4.8565 (4.8565)	grad_norm 1.2441 (1.2441)	
[2022-01-19 17:09:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][10/1251]	eta 1:25:47 lr 0.000880	time 3.0141 (4.1479)	loss 4.2140 (3.9006)	grad_norm 1.0854 (1.1172)	
[2022-01-19 17:09:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][20/1251]	eta 1:06:55 lr 0.000880	time 2.1266 (3.2620)	loss 3.6546 (3.7223)	grad_norm 1.1122 (1.1282)	
[2022-01-19 17:10:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][30/1251]	eta 0:59:10 lr 0.000880	time 1.8851 (2.9077)	loss 4.4660 (3.7978)	grad_norm 1.0964 (1.1241)	
[2022-01-19 17:10:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][40/1251]	eta 0:55:15 lr 0.000880	time 3.5506 (2.7381)	loss 3.9523 (3.8654)	grad_norm 1.1928 (1.1132)	
[2022-01-19 17:10:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][50/1251]	eta 0:53:06 lr 0.000880	time 2.6911 (2.6532)	loss 4.1277 (3.8315)	grad_norm 1.3906 (1.1255)	
[2022-01-19 17:11:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][60/1251]	eta 0:50:50 lr 0.000880	time 1.6329 (2.5611)	loss 4.4231 (3.8106)	grad_norm 1.1010 (1.1316)	
[2022-01-19 17:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][70/1251]	eta 0:49:22 lr 0.000880	time 2.5189 (2.5088)	loss 3.3679 (3.8319)	grad_norm 1.0365 (1.1327)	
[2022-01-19 17:11:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][80/1251]	eta 0:48:40 lr 0.000879	time 3.5904 (2.4943)	loss 4.3900 (3.8590)	grad_norm 1.1867 (1.1396)	
[2022-01-19 17:12:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][90/1251]	eta 0:47:43 lr 0.000879	time 2.7851 (2.4665)	loss 4.2397 (3.8630)	grad_norm 1.3279 (1.1387)	
[2022-01-19 17:12:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][100/1251]	eta 0:46:43 lr 0.000879	time 1.9215 (2.4361)	loss 2.6335 (3.8638)	grad_norm 1.1126 (1.1452)	
[2022-01-19 17:13:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][110/1251]	eta 0:45:31 lr 0.000879	time 1.7215 (2.3941)	loss 3.6553 (3.8802)	grad_norm 1.4027 (1.1442)	
[2022-01-19 17:13:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][120/1251]	eta 0:44:54 lr 0.000879	time 3.2389 (2.3825)	loss 3.7653 (3.8765)	grad_norm 1.2182 (1.1472)	
[2022-01-19 17:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][130/1251]	eta 0:44:08 lr 0.000879	time 1.9169 (2.3628)	loss 4.6670 (3.8560)	grad_norm 1.7069 (1.1556)	
[2022-01-19 17:14:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][140/1251]	eta 0:43:19 lr 0.000879	time 2.0089 (2.3402)	loss 4.4973 (3.8446)	grad_norm 1.2721 (1.1612)	
[2022-01-19 17:14:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][150/1251]	eta 0:42:36 lr 0.000879	time 1.6635 (2.3219)	loss 3.3369 (3.8473)	grad_norm 1.3080 (1.1595)	
[2022-01-19 17:14:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][160/1251]	eta 0:42:03 lr 0.000879	time 2.4337 (2.3130)	loss 3.0244 (3.8549)	grad_norm 1.0620 (1.1619)	
[2022-01-19 17:15:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][170/1251]	eta 0:41:31 lr 0.000879	time 1.8771 (2.3053)	loss 4.6604 (3.8609)	grad_norm 1.2253 (1.1677)	
[2022-01-19 17:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][180/1251]	eta 0:41:06 lr 0.000879	time 2.0562 (2.3029)	loss 3.4757 (3.8532)	grad_norm 1.1539 (1.1695)	
[2022-01-19 17:15:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][190/1251]	eta 0:40:30 lr 0.000879	time 1.9439 (2.2911)	loss 3.9179 (3.8514)	grad_norm 1.3176 (1.1710)	
[2022-01-19 17:16:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][200/1251]	eta 0:39:57 lr 0.000879	time 2.0636 (2.2807)	loss 3.1076 (3.8381)	grad_norm 1.0883 (1.1703)	
[2022-01-19 17:16:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][210/1251]	eta 0:39:35 lr 0.000879	time 1.8585 (2.2820)	loss 3.1247 (3.8367)	grad_norm 0.9791 (1.1713)	
[2022-01-19 17:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][220/1251]	eta 0:39:12 lr 0.000879	time 1.8530 (2.2817)	loss 4.3787 (3.8281)	grad_norm 1.3507 (1.1692)	
[2022-01-19 17:17:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][230/1251]	eta 0:38:41 lr 0.000879	time 1.8433 (2.2740)	loss 3.3651 (3.8257)	grad_norm 1.2261 (1.1711)	
[2022-01-19 17:17:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][240/1251]	eta 0:38:15 lr 0.000879	time 2.4816 (2.2707)	loss 3.2406 (3.8130)	grad_norm 1.2240 (1.1714)	
[2022-01-19 17:18:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][250/1251]	eta 0:38:01 lr 0.000879	time 3.6550 (2.2794)	loss 3.7329 (3.8231)	grad_norm 1.2629 (1.1687)	
[2022-01-19 17:18:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][260/1251]	eta 0:37:32 lr 0.000879	time 1.9263 (2.2726)	loss 3.6605 (3.8242)	grad_norm 1.2319 (1.1685)	
[2022-01-19 17:18:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][270/1251]	eta 0:37:01 lr 0.000879	time 1.8000 (2.2648)	loss 4.5319 (3.8282)	grad_norm 1.4080 (1.1712)	
[2022-01-19 17:19:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][280/1251]	eta 0:36:26 lr 0.000879	time 1.6684 (2.2521)	loss 4.1553 (3.8259)	grad_norm 0.9565 (1.1699)	
[2022-01-19 17:19:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][290/1251]	eta 0:36:02 lr 0.000879	time 3.3973 (2.2504)	loss 3.8151 (3.8328)	grad_norm 1.0630 (1.1676)	
[2022-01-19 17:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][300/1251]	eta 0:35:37 lr 0.000879	time 1.8825 (2.2479)	loss 4.7145 (3.8369)	grad_norm 1.0265 (1.1651)	
[2022-01-19 17:20:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][310/1251]	eta 0:35:15 lr 0.000879	time 2.0345 (2.2486)	loss 4.5292 (3.8275)	grad_norm 1.1467 (1.1633)	
[2022-01-19 17:20:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][320/1251]	eta 0:34:57 lr 0.000879	time 2.4013 (2.2533)	loss 4.6557 (3.8290)	grad_norm 1.0276 (1.1613)	
[2022-01-19 17:21:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][330/1251]	eta 0:34:37 lr 0.000879	time 3.0489 (2.2556)	loss 4.7238 (3.8279)	grad_norm 1.0817 (1.1615)	
[2022-01-19 17:21:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][340/1251]	eta 0:34:12 lr 0.000879	time 1.9809 (2.2535)	loss 3.8246 (3.8317)	grad_norm 1.1992 (1.1627)	
[2022-01-19 17:21:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][350/1251]	eta 0:33:48 lr 0.000879	time 2.0742 (2.2509)	loss 4.2898 (3.8240)	grad_norm 1.0818 (1.1613)	
[2022-01-19 17:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][360/1251]	eta 0:33:21 lr 0.000879	time 2.4381 (2.2466)	loss 2.7502 (3.8222)	grad_norm 1.2649 (1.1640)	
[2022-01-19 17:22:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][370/1251]	eta 0:32:58 lr 0.000879	time 3.1905 (2.2462)	loss 4.4525 (3.8354)	grad_norm 1.2106 (1.1648)	
[2022-01-19 17:22:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][380/1251]	eta 0:32:33 lr 0.000879	time 2.2256 (2.2429)	loss 3.8563 (3.8361)	grad_norm 1.0259 (1.1645)	
[2022-01-19 17:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][390/1251]	eta 0:32:08 lr 0.000879	time 1.8528 (2.2394)	loss 3.8820 (3.8365)	grad_norm 1.2166 (1.1667)	
[2022-01-19 17:23:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][400/1251]	eta 0:31:44 lr 0.000879	time 2.3578 (2.2374)	loss 4.2511 (3.8386)	grad_norm 1.2454 (1.1690)	
[2022-01-19 17:23:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][410/1251]	eta 0:31:20 lr 0.000879	time 2.2990 (2.2357)	loss 4.0645 (3.8411)	grad_norm 1.2763 (1.1683)	
[2022-01-19 17:24:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][420/1251]	eta 0:30:55 lr 0.000879	time 2.2181 (2.2334)	loss 4.4300 (3.8415)	grad_norm 1.2902 (1.1687)	
[2022-01-19 17:24:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][430/1251]	eta 0:30:33 lr 0.000879	time 2.8987 (2.2332)	loss 3.8669 (3.8402)	grad_norm 1.3322 (1.1685)	
[2022-01-19 17:24:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][440/1251]	eta 0:30:08 lr 0.000879	time 1.9079 (2.2296)	loss 4.3768 (3.8353)	grad_norm 1.1095 (1.1706)	
[2022-01-19 17:25:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][450/1251]	eta 0:29:44 lr 0.000878	time 2.2249 (2.2280)	loss 4.3856 (3.8328)	grad_norm 1.0562 (1.1710)	
[2022-01-19 17:25:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][460/1251]	eta 0:29:20 lr 0.000878	time 2.2830 (2.2252)	loss 4.2983 (3.8357)	grad_norm 1.2819 (1.1709)	
[2022-01-19 17:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][470/1251]	eta 0:28:58 lr 0.000878	time 2.0573 (2.2255)	loss 3.8711 (3.8339)	grad_norm 1.0780 (1.1701)	
[2022-01-19 17:26:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][480/1251]	eta 0:28:34 lr 0.000878	time 2.1237 (2.2241)	loss 3.9893 (3.8364)	grad_norm 1.2777 (1.1692)	
[2022-01-19 17:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][490/1251]	eta 0:28:12 lr 0.000878	time 2.0729 (2.2244)	loss 4.5683 (3.8405)	grad_norm 1.3345 (1.1697)	
[2022-01-19 17:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][500/1251]	eta 0:27:51 lr 0.000878	time 2.3946 (2.2263)	loss 3.9711 (3.8462)	grad_norm 1.0001 (1.1694)	
[2022-01-19 17:27:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][510/1251]	eta 0:27:30 lr 0.000878	time 2.1932 (2.2278)	loss 4.4951 (3.8471)	grad_norm 1.0980 (1.1690)	
[2022-01-19 17:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][520/1251]	eta 0:27:06 lr 0.000878	time 1.8276 (2.2254)	loss 3.8621 (3.8496)	grad_norm 1.1121 (1.1697)	
[2022-01-19 17:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][530/1251]	eta 0:26:42 lr 0.000878	time 2.2030 (2.2222)	loss 3.6699 (3.8525)	grad_norm 1.2349 (1.1714)	
[2022-01-19 17:28:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][540/1251]	eta 0:26:18 lr 0.000878	time 2.4029 (2.2203)	loss 3.6408 (3.8530)	grad_norm 0.9985 (1.1737)	
[2022-01-19 17:28:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][550/1251]	eta 0:25:54 lr 0.000878	time 2.2446 (2.2179)	loss 2.9221 (3.8507)	grad_norm 1.0334 (1.1721)	
[2022-01-19 17:29:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][560/1251]	eta 0:25:33 lr 0.000878	time 2.1959 (2.2195)	loss 4.0827 (3.8526)	grad_norm 1.2733 (1.1722)	
[2022-01-19 17:29:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][570/1251]	eta 0:25:10 lr 0.000878	time 1.8476 (2.2186)	loss 3.5831 (3.8517)	grad_norm 1.1565 (1.1726)	
[2022-01-19 17:30:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][580/1251]	eta 0:24:47 lr 0.000878	time 1.5086 (2.2162)	loss 3.8197 (3.8521)	grad_norm 1.0206 (1.1713)	
[2022-01-19 17:30:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][590/1251]	eta 0:24:24 lr 0.000878	time 2.2264 (2.2162)	loss 3.2490 (3.8547)	grad_norm 1.2654 (1.1713)	
[2022-01-19 17:30:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][600/1251]	eta 0:24:03 lr 0.000878	time 2.8997 (2.2180)	loss 3.3715 (3.8510)	grad_norm 1.2823 (1.1737)	
[2022-01-19 17:31:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][610/1251]	eta 0:23:40 lr 0.000878	time 1.8170 (2.2163)	loss 4.0451 (3.8490)	grad_norm 1.6433 (1.1746)	
[2022-01-19 17:31:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][620/1251]	eta 0:23:17 lr 0.000878	time 2.0214 (2.2152)	loss 3.2607 (3.8490)	grad_norm 1.1931 (1.1754)	
[2022-01-19 17:31:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][630/1251]	eta 0:22:54 lr 0.000878	time 2.2044 (2.2133)	loss 3.8798 (3.8501)	grad_norm 1.2688 (1.1746)	
[2022-01-19 17:32:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][640/1251]	eta 0:22:31 lr 0.000878	time 2.1678 (2.2118)	loss 3.2289 (3.8489)	grad_norm 1.2212 (1.1752)	
[2022-01-19 17:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][650/1251]	eta 0:22:09 lr 0.000878	time 1.6609 (2.2121)	loss 4.3518 (3.8517)	grad_norm 1.0427 (1.1746)	
[2022-01-19 17:32:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][660/1251]	eta 0:21:47 lr 0.000878	time 2.5585 (2.2123)	loss 4.2482 (3.8520)	grad_norm 1.1391 (1.1747)	
[2022-01-19 17:33:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][670/1251]	eta 0:21:24 lr 0.000878	time 1.7202 (2.2105)	loss 3.7757 (3.8494)	grad_norm 1.3110 (1.1745)	
[2022-01-19 17:33:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][680/1251]	eta 0:21:01 lr 0.000878	time 2.1337 (2.2093)	loss 3.9909 (3.8503)	grad_norm 1.0557 (1.1743)	
[2022-01-19 17:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][690/1251]	eta 0:20:38 lr 0.000878	time 1.8249 (2.2076)	loss 3.8966 (3.8534)	grad_norm 0.9819 (1.1731)	
[2022-01-19 17:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][700/1251]	eta 0:20:16 lr 0.000878	time 2.7642 (2.2074)	loss 4.3630 (3.8539)	grad_norm 1.2933 (1.1723)	
[2022-01-19 17:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][710/1251]	eta 0:19:54 lr 0.000878	time 1.9032 (2.2079)	loss 4.2408 (3.8548)	grad_norm 1.1003 (1.1729)	
[2022-01-19 17:35:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][720/1251]	eta 0:19:33 lr 0.000878	time 2.4770 (2.2091)	loss 4.5679 (3.8552)	grad_norm 1.2395 (1.1739)	
[2022-01-19 17:35:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][730/1251]	eta 0:19:11 lr 0.000878	time 1.8570 (2.2111)	loss 2.9366 (3.8530)	grad_norm 1.1716 (1.1739)	
[2022-01-19 17:35:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][740/1251]	eta 0:18:51 lr 0.000878	time 2.9539 (2.2143)	loss 4.2627 (3.8493)	grad_norm 1.0547 (1.1732)	
[2022-01-19 17:36:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][750/1251]	eta 0:18:29 lr 0.000878	time 1.8610 (2.2139)	loss 3.9164 (3.8514)	grad_norm 1.2674 (1.1734)	
[2022-01-19 17:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][760/1251]	eta 0:18:06 lr 0.000878	time 2.3226 (2.2130)	loss 4.1210 (3.8511)	grad_norm 1.0959 (1.1719)	
[2022-01-19 17:36:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][770/1251]	eta 0:17:42 lr 0.000878	time 1.8829 (2.2090)	loss 4.1235 (3.8512)	grad_norm 1.0812 (1.1716)	
[2022-01-19 17:37:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][780/1251]	eta 0:17:18 lr 0.000878	time 1.9872 (2.2055)	loss 4.8605 (3.8548)	grad_norm 1.1293 (1.1720)	
[2022-01-19 17:37:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][790/1251]	eta 0:16:56 lr 0.000878	time 2.1596 (2.2046)	loss 4.4732 (3.8591)	grad_norm 1.0986 (1.1719)	
[2022-01-19 17:38:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][800/1251]	eta 0:16:34 lr 0.000878	time 2.1678 (2.2053)	loss 2.9418 (3.8583)	grad_norm 1.1346 (1.1707)	
[2022-01-19 17:38:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][810/1251]	eta 0:16:12 lr 0.000878	time 3.0574 (2.2052)	loss 4.0530 (3.8584)	grad_norm 1.3597 (1.1704)	
[2022-01-19 17:38:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][820/1251]	eta 0:15:51 lr 0.000877	time 3.5712 (2.2075)	loss 4.0001 (3.8557)	grad_norm 1.0691 (1.1702)	
[2022-01-19 17:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][830/1251]	eta 0:15:29 lr 0.000877	time 1.8628 (2.2072)	loss 4.4533 (3.8538)	grad_norm 0.9870 (1.1692)	
[2022-01-19 17:39:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][840/1251]	eta 0:15:07 lr 0.000877	time 2.9863 (2.2080)	loss 3.3630 (3.8536)	grad_norm 1.0210 (1.1687)	
[2022-01-19 17:39:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][850/1251]	eta 0:14:44 lr 0.000877	time 1.8307 (2.2069)	loss 4.2628 (3.8524)	grad_norm 1.1860 (1.1697)	
[2022-01-19 17:40:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][860/1251]	eta 0:14:23 lr 0.000877	time 3.1641 (2.2095)	loss 2.6927 (3.8507)	grad_norm 0.9288 (1.1687)	
[2022-01-19 17:40:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][870/1251]	eta 0:14:02 lr 0.000877	time 2.4926 (2.2108)	loss 3.9004 (3.8482)	grad_norm 1.1543 (1.1683)	
[2022-01-19 17:41:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][880/1251]	eta 0:13:40 lr 0.000877	time 2.5817 (2.2104)	loss 3.5072 (3.8497)	grad_norm 1.0186 (1.1674)	
[2022-01-19 17:41:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][890/1251]	eta 0:13:17 lr 0.000877	time 1.8552 (2.2084)	loss 4.8614 (3.8500)	grad_norm 1.1071 (1.1665)	
[2022-01-19 17:41:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][900/1251]	eta 0:12:54 lr 0.000877	time 3.1161 (2.2065)	loss 3.7286 (3.8487)	grad_norm 1.1756 (1.1662)	
[2022-01-19 17:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][910/1251]	eta 0:12:31 lr 0.000877	time 1.6359 (2.2040)	loss 4.1465 (3.8499)	grad_norm 1.1037 (1.1658)	
[2022-01-19 17:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][920/1251]	eta 0:12:09 lr 0.000877	time 2.2841 (2.2032)	loss 4.1160 (3.8504)	grad_norm 0.9944 (1.1652)	
[2022-01-19 17:42:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][930/1251]	eta 0:11:46 lr 0.000877	time 1.9534 (2.2020)	loss 3.9614 (3.8514)	grad_norm 1.0372 (1.1651)	
[2022-01-19 17:43:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][940/1251]	eta 0:11:25 lr 0.000877	time 3.6821 (2.2026)	loss 4.0550 (3.8527)	grad_norm 1.1619 (1.1656)	
[2022-01-19 17:43:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][950/1251]	eta 0:11:03 lr 0.000877	time 2.8031 (2.2033)	loss 3.9875 (3.8531)	grad_norm 0.9846 (1.1647)	
[2022-01-19 17:43:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][960/1251]	eta 0:10:41 lr 0.000877	time 2.4865 (2.2039)	loss 3.7873 (3.8519)	grad_norm 1.1885 (1.1647)	
[2022-01-19 17:44:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][970/1251]	eta 0:10:19 lr 0.000877	time 2.1656 (2.2034)	loss 4.3588 (3.8510)	grad_norm 1.1828 (1.1646)	
[2022-01-19 17:44:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][980/1251]	eta 0:09:57 lr 0.000877	time 2.5413 (2.2034)	loss 3.9251 (3.8459)	grad_norm 1.1187 (1.1645)	
[2022-01-19 17:45:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][990/1251]	eta 0:09:35 lr 0.000877	time 3.0806 (2.2046)	loss 3.0044 (3.8465)	grad_norm 1.1886 (1.1643)	
[2022-01-19 17:45:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1000/1251]	eta 0:09:13 lr 0.000877	time 2.1883 (2.2038)	loss 4.7245 (3.8438)	grad_norm 1.1657 (1.1637)	
[2022-01-19 17:45:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1010/1251]	eta 0:08:50 lr 0.000877	time 2.2140 (2.2022)	loss 3.6258 (3.8431)	grad_norm 0.9997 (1.1637)	
[2022-01-19 17:46:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1020/1251]	eta 0:08:28 lr 0.000877	time 2.1843 (2.2032)	loss 3.4231 (3.8430)	grad_norm 0.9683 (1.1633)	
[2022-01-19 17:46:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1030/1251]	eta 0:08:07 lr 0.000877	time 2.7833 (2.2052)	loss 3.6886 (3.8441)	grad_norm 1.4712 (1.1637)	
[2022-01-19 17:46:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1040/1251]	eta 0:07:45 lr 0.000877	time 1.7904 (2.2044)	loss 3.1318 (3.8424)	grad_norm 1.2465 (1.1638)	
[2022-01-19 17:47:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1050/1251]	eta 0:07:23 lr 0.000877	time 2.9213 (2.2044)	loss 4.7104 (3.8430)	grad_norm 1.1542 (1.1633)	
[2022-01-19 17:47:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1060/1251]	eta 0:07:00 lr 0.000877	time 1.7674 (2.2024)	loss 4.5630 (3.8462)	grad_norm 1.1884 (1.1638)	
[2022-01-19 17:47:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1070/1251]	eta 0:06:38 lr 0.000877	time 2.8633 (2.2021)	loss 4.0829 (3.8430)	grad_norm 1.0116 (1.1637)	
[2022-01-19 17:48:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1080/1251]	eta 0:06:16 lr 0.000877	time 1.5606 (2.1997)	loss 4.0205 (3.8413)	grad_norm 1.4358 (1.1637)	
[2022-01-19 17:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1090/1251]	eta 0:05:54 lr 0.000877	time 1.9087 (2.1996)	loss 4.5728 (3.8425)	grad_norm 1.1111 (1.1636)	
[2022-01-19 17:48:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1100/1251]	eta 0:05:32 lr 0.000877	time 2.1768 (2.1991)	loss 2.8696 (3.8397)	grad_norm 1.2165 (1.1643)	
[2022-01-19 17:49:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1110/1251]	eta 0:05:10 lr 0.000877	time 2.2309 (2.1998)	loss 4.3180 (3.8408)	grad_norm 1.0393 (1.1649)	
[2022-01-19 17:49:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1120/1251]	eta 0:04:48 lr 0.000877	time 1.8345 (2.2004)	loss 4.1265 (3.8408)	grad_norm 0.9595 (1.1640)	
[2022-01-19 17:50:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1130/1251]	eta 0:04:26 lr 0.000877	time 2.0542 (2.2016)	loss 3.6405 (3.8406)	grad_norm 1.2564 (1.1646)	
[2022-01-19 17:50:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1140/1251]	eta 0:04:04 lr 0.000877	time 2.5165 (2.2019)	loss 4.3482 (3.8421)	grad_norm 1.1069 (1.1642)	
[2022-01-19 17:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1150/1251]	eta 0:03:42 lr 0.000877	time 3.1162 (2.2018)	loss 4.2227 (3.8413)	grad_norm 1.4262 (1.1644)	
[2022-01-19 17:51:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1160/1251]	eta 0:03:20 lr 0.000877	time 1.8534 (2.2009)	loss 4.0507 (3.8385)	grad_norm 1.1142 (1.1641)	
[2022-01-19 17:51:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1170/1251]	eta 0:02:58 lr 0.000877	time 1.6465 (2.1997)	loss 3.8264 (3.8367)	grad_norm 1.0936 (1.1638)	
[2022-01-19 17:51:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1180/1251]	eta 0:02:36 lr 0.000876	time 1.8281 (2.1985)	loss 3.6919 (3.8374)	grad_norm 1.2311 (1.1637)	
[2022-01-19 17:52:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1190/1251]	eta 0:02:14 lr 0.000876	time 2.6817 (2.1995)	loss 4.2288 (3.8382)	grad_norm 1.0236 (1.1637)	
[2022-01-19 17:52:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1200/1251]	eta 0:01:52 lr 0.000876	time 2.3116 (2.1994)	loss 2.7750 (3.8369)	grad_norm 1.2761 (1.1634)	
[2022-01-19 17:52:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1210/1251]	eta 0:01:30 lr 0.000876	time 2.5336 (2.2001)	loss 3.9231 (3.8346)	grad_norm 1.0789 (1.1632)	
[2022-01-19 17:53:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1220/1251]	eta 0:01:08 lr 0.000876	time 1.8551 (2.1997)	loss 3.0416 (3.8328)	grad_norm 1.1320 (1.1628)	
[2022-01-19 17:53:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1230/1251]	eta 0:00:46 lr 0.000876	time 3.0902 (2.2006)	loss 4.2913 (3.8353)	grad_norm 1.1509 (1.1627)	
[2022-01-19 17:54:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1240/1251]	eta 0:00:24 lr 0.000876	time 1.2855 (2.1980)	loss 4.0149 (3.8357)	grad_norm 1.1977 (1.1631)	
[2022-01-19 17:54:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [68/300][1250/1251]	eta 0:00:02 lr 0.000876	time 1.1860 (2.1928)	loss 2.9706 (3.8362)	grad_norm 1.2788 (1.1632)	
[2022-01-19 17:54:19 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 68 training takes 0:45:43
[2022-01-19 17:54:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.943 (17.943)	Loss 1.2786 (1.2786)	Acc@1 71.875 (71.875)	Acc@5 89.844 (89.844)	
[2022-01-19 17:54:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.077 (3.193)	Loss 1.2314 (1.2346)	Acc@1 70.898 (71.573)	Acc@5 90.625 (90.714)	
[2022-01-19 17:55:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.248 (2.588)	Loss 1.1694 (1.2290)	Acc@1 73.438 (71.731)	Acc@5 92.285 (90.839)	
[2022-01-19 17:55:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.960 (2.345)	Loss 1.1903 (1.2313)	Acc@1 72.852 (71.673)	Acc@5 91.699 (90.839)	
[2022-01-19 17:55:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.849 (2.152)	Loss 1.2500 (1.2274)	Acc@1 70.801 (71.684)	Acc@5 90.527 (90.899)	
[2022-01-19 17:55:54 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 71.644 Acc@5 90.944
[2022-01-19 17:55:54 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 71.6%
[2022-01-19 17:55:54 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 71.96%
[2022-01-19 17:56:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][0/1251]	eta 7:20:57 lr 0.000876	time 21.1488 (21.1488)	loss 3.3905 (3.3905)	grad_norm 1.0954 (1.0954)	
[2022-01-19 17:56:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][10/1251]	eta 1:23:59 lr 0.000876	time 2.8857 (4.0609)	loss 3.9018 (3.9317)	grad_norm 1.1315 (1.1472)	
[2022-01-19 17:56:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][20/1251]	eta 1:03:19 lr 0.000876	time 1.3635 (3.0866)	loss 4.6414 (3.9631)	grad_norm 1.1052 (1.1267)	
[2022-01-19 17:57:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][30/1251]	eta 0:56:26 lr 0.000876	time 1.5954 (2.7738)	loss 3.7203 (3.9002)	grad_norm 1.3022 (1.1342)	
[2022-01-19 17:57:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][40/1251]	eta 0:53:41 lr 0.000876	time 3.1695 (2.6603)	loss 3.5665 (3.8415)	grad_norm 1.0331 (1.1549)	
[2022-01-19 17:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][50/1251]	eta 0:52:18 lr 0.000876	time 2.6107 (2.6129)	loss 4.2086 (3.8282)	grad_norm 1.4668 (1.1623)	
[2022-01-19 17:58:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][60/1251]	eta 0:51:09 lr 0.000876	time 1.7809 (2.5776)	loss 3.9385 (3.8438)	grad_norm 1.0753 (1.1687)	
[2022-01-19 17:58:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][70/1251]	eta 0:49:58 lr 0.000876	time 2.5470 (2.5393)	loss 3.9221 (3.8334)	grad_norm 1.2410 (1.1792)	
[2022-01-19 17:59:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][80/1251]	eta 0:48:21 lr 0.000876	time 1.9295 (2.4780)	loss 4.5589 (3.8219)	grad_norm 1.1532 (1.1809)	
[2022-01-19 17:59:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][90/1251]	eta 0:47:08 lr 0.000876	time 2.2866 (2.4367)	loss 4.0810 (3.8152)	grad_norm 1.3015 (1.1825)	
[2022-01-19 17:59:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][100/1251]	eta 0:45:47 lr 0.000876	time 1.9379 (2.3872)	loss 4.0591 (3.8331)	grad_norm 1.0719 (1.1791)	
[2022-01-19 18:00:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][110/1251]	eta 0:44:36 lr 0.000876	time 1.7002 (2.3460)	loss 4.3956 (3.8380)	grad_norm 1.1521 (1.1767)	
[2022-01-19 18:00:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][120/1251]	eta 0:43:46 lr 0.000876	time 2.0756 (2.3221)	loss 4.1003 (3.8401)	grad_norm 1.5913 (1.1774)	
[2022-01-19 18:00:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][130/1251]	eta 0:43:11 lr 0.000876	time 2.0100 (2.3115)	loss 4.5051 (3.8658)	grad_norm 1.2564 (1.1724)	
[2022-01-19 18:01:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][140/1251]	eta 0:42:51 lr 0.000876	time 1.8930 (2.3142)	loss 4.2943 (3.8508)	grad_norm 1.0562 (1.1684)	
[2022-01-19 18:01:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][150/1251]	eta 0:42:32 lr 0.000876	time 2.5136 (2.3185)	loss 3.4489 (3.8503)	grad_norm 1.1990 (1.1667)	
[2022-01-19 18:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][160/1251]	eta 0:42:04 lr 0.000876	time 1.8142 (2.3142)	loss 3.7184 (3.8460)	grad_norm 1.1417 (1.1623)	
[2022-01-19 18:02:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][170/1251]	eta 0:41:43 lr 0.000876	time 2.1041 (2.3155)	loss 2.7625 (3.8340)	grad_norm 1.1271 (1.1598)	
[2022-01-19 18:02:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][180/1251]	eta 0:41:20 lr 0.000876	time 2.2377 (2.3161)	loss 2.5989 (3.8085)	grad_norm 1.0445 (1.1604)	
[2022-01-19 18:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][190/1251]	eta 0:40:42 lr 0.000876	time 1.8918 (2.3019)	loss 4.1925 (3.8057)	grad_norm 1.0431 (1.1564)	
[2022-01-19 18:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][200/1251]	eta 0:40:10 lr 0.000876	time 2.1044 (2.2934)	loss 4.3830 (3.8116)	grad_norm 1.1336 (1.1573)	
[2022-01-19 18:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][210/1251]	eta 0:39:35 lr 0.000876	time 1.5889 (2.2823)	loss 2.7426 (3.8143)	grad_norm 0.9974 (1.1586)	
[2022-01-19 18:04:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][220/1251]	eta 0:39:11 lr 0.000876	time 2.3113 (2.2809)	loss 4.4875 (3.8115)	grad_norm 1.2205 (1.1623)	
[2022-01-19 18:04:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][230/1251]	eta 0:38:47 lr 0.000876	time 1.9221 (2.2794)	loss 2.5863 (3.8144)	grad_norm 1.1794 (1.1660)	
[2022-01-19 18:05:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][240/1251]	eta 0:38:27 lr 0.000876	time 1.8852 (2.2819)	loss 3.9825 (3.8069)	grad_norm 1.1772 (1.1678)	
[2022-01-19 18:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][250/1251]	eta 0:38:01 lr 0.000876	time 2.1670 (2.2792)	loss 3.7050 (3.8007)	grad_norm 0.9623 (1.1667)	
[2022-01-19 18:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][260/1251]	eta 0:37:30 lr 0.000876	time 1.9993 (2.2708)	loss 3.4383 (3.8065)	grad_norm 0.9447 (1.1665)	
[2022-01-19 18:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][270/1251]	eta 0:36:58 lr 0.000876	time 1.8589 (2.2618)	loss 4.1619 (3.8041)	grad_norm 1.1212 (1.1668)	
[2022-01-19 18:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][280/1251]	eta 0:36:26 lr 0.000876	time 1.5817 (2.2517)	loss 4.1901 (3.8032)	grad_norm 1.1189 (1.1665)	
[2022-01-19 18:06:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][290/1251]	eta 0:35:58 lr 0.000876	time 1.9401 (2.2457)	loss 3.8014 (3.8039)	grad_norm 1.3155 (1.1661)	
[2022-01-19 18:07:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][300/1251]	eta 0:35:31 lr 0.000875	time 2.5341 (2.2412)	loss 4.1922 (3.8048)	grad_norm 1.1316 (1.1633)	
[2022-01-19 18:07:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][310/1251]	eta 0:35:04 lr 0.000875	time 2.1915 (2.2364)	loss 3.2388 (3.8027)	grad_norm 1.1109 (1.1634)	
[2022-01-19 18:07:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][320/1251]	eta 0:34:43 lr 0.000875	time 2.5575 (2.2382)	loss 4.2093 (3.8042)	grad_norm 1.0894 (1.1655)	
[2022-01-19 18:08:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][330/1251]	eta 0:34:16 lr 0.000875	time 1.3972 (2.2326)	loss 3.1082 (3.7987)	grad_norm 1.0865 (1.1667)	
[2022-01-19 18:08:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][340/1251]	eta 0:33:54 lr 0.000875	time 1.8846 (2.2331)	loss 4.7775 (3.8016)	grad_norm 1.4566 (1.1660)	
[2022-01-19 18:08:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][350/1251]	eta 0:33:33 lr 0.000875	time 2.4924 (2.2343)	loss 3.9690 (3.8012)	grad_norm 1.3718 (1.1660)	
[2022-01-19 18:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][360/1251]	eta 0:33:10 lr 0.000875	time 2.7428 (2.2344)	loss 4.1655 (3.7996)	grad_norm 1.2768 (1.1676)	
[2022-01-19 18:09:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][370/1251]	eta 0:32:53 lr 0.000875	time 1.5811 (2.2400)	loss 3.3756 (3.7972)	grad_norm 1.1605 (1.1689)	
[2022-01-19 18:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][380/1251]	eta 0:32:37 lr 0.000875	time 2.1933 (2.2471)	loss 3.7168 (3.7892)	grad_norm 0.9730 (1.1700)	
[2022-01-19 18:10:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][390/1251]	eta 0:32:16 lr 0.000875	time 2.4060 (2.2493)	loss 4.0932 (3.7949)	grad_norm 1.4111 (1.1723)	
[2022-01-19 18:10:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][400/1251]	eta 0:31:48 lr 0.000875	time 1.8508 (2.2432)	loss 3.8775 (3.7977)	grad_norm 1.1299 (1.1726)	
[2022-01-19 18:11:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][410/1251]	eta 0:31:18 lr 0.000875	time 2.1007 (2.2342)	loss 3.6387 (3.7964)	grad_norm 1.2998 (1.1719)	
[2022-01-19 18:11:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][420/1251]	eta 0:30:53 lr 0.000875	time 1.7060 (2.2308)	loss 3.8934 (3.7912)	grad_norm 1.1329 (1.1722)	
[2022-01-19 18:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][430/1251]	eta 0:30:28 lr 0.000875	time 2.2162 (2.2272)	loss 2.9038 (3.7932)	grad_norm 1.0656 (1.1708)	
[2022-01-19 18:12:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][440/1251]	eta 0:30:03 lr 0.000875	time 1.8227 (2.2233)	loss 4.2701 (3.7917)	grad_norm 1.2448 (1.1722)	
[2022-01-19 18:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][450/1251]	eta 0:29:39 lr 0.000875	time 2.4567 (2.2220)	loss 3.0316 (3.7877)	grad_norm 1.2919 (1.1762)	
[2022-01-19 18:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][460/1251]	eta 0:29:18 lr 0.000875	time 2.8169 (2.2233)	loss 3.8093 (3.7821)	grad_norm 1.0938 (1.1760)	
[2022-01-19 18:13:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][470/1251]	eta 0:28:55 lr 0.000875	time 2.0544 (2.2227)	loss 3.8061 (3.7897)	grad_norm 1.2366 (1.1748)	
[2022-01-19 18:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][480/1251]	eta 0:28:34 lr 0.000875	time 2.2864 (2.2232)	loss 3.5226 (3.7866)	grad_norm 1.1886 (1.1737)	
[2022-01-19 18:14:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][490/1251]	eta 0:28:14 lr 0.000875	time 2.8106 (2.2266)	loss 4.1229 (3.7853)	grad_norm 1.1237 (1.1715)	
[2022-01-19 18:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][500/1251]	eta 0:27:55 lr 0.000875	time 1.9560 (2.2317)	loss 3.8931 (3.7868)	grad_norm 1.1762 (1.1713)	
[2022-01-19 18:14:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][510/1251]	eta 0:27:34 lr 0.000875	time 2.2291 (2.2328)	loss 4.5468 (3.7941)	grad_norm 1.0853 (1.1710)	
[2022-01-19 18:15:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][520/1251]	eta 0:27:12 lr 0.000875	time 2.0981 (2.2331)	loss 4.4310 (3.7963)	grad_norm 1.0752 (1.1705)	
[2022-01-19 18:15:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][530/1251]	eta 0:26:49 lr 0.000875	time 2.8388 (2.2330)	loss 4.2032 (3.7969)	grad_norm 1.0565 (1.1692)	
[2022-01-19 18:16:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][540/1251]	eta 0:26:26 lr 0.000875	time 2.1935 (2.2314)	loss 3.9803 (3.7932)	grad_norm 1.2177 (1.1696)	
[2022-01-19 18:16:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][550/1251]	eta 0:26:01 lr 0.000875	time 1.8770 (2.2276)	loss 4.3369 (3.7932)	grad_norm 1.1208 (1.1693)	
[2022-01-19 18:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][560/1251]	eta 0:25:36 lr 0.000875	time 2.1877 (2.2242)	loss 3.3847 (3.7919)	grad_norm 1.0787 (1.1695)	
[2022-01-19 18:17:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][570/1251]	eta 0:25:13 lr 0.000875	time 2.3866 (2.2224)	loss 4.3317 (3.7965)	grad_norm 1.1072 (1.1687)	
[2022-01-19 18:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][580/1251]	eta 0:24:49 lr 0.000875	time 1.5745 (2.2204)	loss 3.7144 (3.7963)	grad_norm 1.2074 (1.1679)	
[2022-01-19 18:17:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][590/1251]	eta 0:24:28 lr 0.000875	time 2.6435 (2.2212)	loss 4.5191 (3.8041)	grad_norm 1.5100 (1.1687)	
[2022-01-19 18:18:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][600/1251]	eta 0:24:05 lr 0.000875	time 2.1420 (2.2201)	loss 4.1086 (3.8046)	grad_norm 1.2013 (1.1689)	
[2022-01-19 18:18:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][610/1251]	eta 0:23:42 lr 0.000875	time 2.6335 (2.2187)	loss 4.6164 (3.8083)	grad_norm 1.0657 (1.1692)	
[2022-01-19 18:18:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][620/1251]	eta 0:23:19 lr 0.000875	time 1.8830 (2.2183)	loss 4.3853 (3.8129)	grad_norm 1.0940 (1.1682)	
[2022-01-19 18:19:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][630/1251]	eta 0:22:57 lr 0.000875	time 2.8017 (2.2187)	loss 3.0437 (3.8106)	grad_norm 1.7869 (1.1680)	
[2022-01-19 18:19:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][640/1251]	eta 0:22:37 lr 0.000875	time 2.1746 (2.2212)	loss 3.7356 (3.8081)	grad_norm 1.0125 (1.1676)	
[2022-01-19 18:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][650/1251]	eta 0:22:14 lr 0.000875	time 2.7131 (2.2205)	loss 4.1948 (3.8067)	grad_norm 1.1273 (1.1678)	
[2022-01-19 18:20:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][660/1251]	eta 0:21:53 lr 0.000874	time 2.6041 (2.2221)	loss 3.6089 (3.8122)	grad_norm 1.0186 (1.1680)	
[2022-01-19 18:20:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][670/1251]	eta 0:21:30 lr 0.000874	time 2.7546 (2.2217)	loss 4.0563 (3.8159)	grad_norm 1.3212 (1.1688)	
[2022-01-19 18:21:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][680/1251]	eta 0:21:08 lr 0.000874	time 1.8486 (2.2210)	loss 4.2184 (3.8163)	grad_norm 0.9999 (1.1684)	
[2022-01-19 18:21:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][690/1251]	eta 0:20:44 lr 0.000874	time 2.1790 (2.2185)	loss 3.6245 (3.8116)	grad_norm 1.1818 (1.1686)	
[2022-01-19 18:21:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][700/1251]	eta 0:20:20 lr 0.000874	time 2.2041 (2.2159)	loss 3.8321 (3.8046)	grad_norm 1.2976 (1.1678)	
[2022-01-19 18:22:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][710/1251]	eta 0:19:57 lr 0.000874	time 1.9444 (2.2134)	loss 4.6048 (3.8076)	grad_norm 1.0966 (1.1676)	
[2022-01-19 18:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][720/1251]	eta 0:19:35 lr 0.000874	time 2.7090 (2.2145)	loss 3.6092 (3.8092)	grad_norm 1.0863 (1.1683)	
[2022-01-19 18:22:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][730/1251]	eta 0:19:13 lr 0.000874	time 1.8283 (2.2150)	loss 3.1148 (3.8105)	grad_norm 1.2225 (1.1690)	
[2022-01-19 18:23:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][740/1251]	eta 0:18:52 lr 0.000874	time 2.2550 (2.2159)	loss 3.8923 (3.8079)	grad_norm 1.2964 (1.1698)	
[2022-01-19 18:23:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][750/1251]	eta 0:18:30 lr 0.000874	time 1.9052 (2.2158)	loss 3.7027 (3.8096)	grad_norm 1.3530 (1.1704)	
[2022-01-19 18:24:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][760/1251]	eta 0:18:08 lr 0.000874	time 2.7251 (2.2173)	loss 4.3839 (3.8096)	grad_norm 1.1401 (1.1698)	
[2022-01-19 18:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][770/1251]	eta 0:17:46 lr 0.000874	time 1.4814 (2.2164)	loss 3.8053 (3.8075)	grad_norm 1.5977 (1.1693)	
[2022-01-19 18:24:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][780/1251]	eta 0:17:23 lr 0.000874	time 1.7149 (2.2152)	loss 3.9761 (3.8075)	grad_norm 1.0968 (1.1706)	
[2022-01-19 18:25:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][790/1251]	eta 0:17:00 lr 0.000874	time 1.5616 (2.2140)	loss 2.6863 (3.8052)	grad_norm 1.1449 (1.1704)	
[2022-01-19 18:25:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][800/1251]	eta 0:16:38 lr 0.000874	time 1.9248 (2.2138)	loss 4.4177 (3.8111)	grad_norm 0.9553 (1.1697)	
[2022-01-19 18:25:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][810/1251]	eta 0:16:15 lr 0.000874	time 2.1929 (2.2124)	loss 2.9677 (3.8106)	grad_norm 0.9963 (1.1691)	
[2022-01-19 18:26:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][820/1251]	eta 0:15:54 lr 0.000874	time 1.5602 (2.2135)	loss 3.7591 (3.8078)	grad_norm 1.0974 (1.1696)	
[2022-01-19 18:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][830/1251]	eta 0:15:31 lr 0.000874	time 1.5775 (2.2137)	loss 4.2971 (3.8072)	grad_norm 1.0799 (1.1692)	
[2022-01-19 18:26:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][840/1251]	eta 0:15:10 lr 0.000874	time 1.9476 (2.2152)	loss 4.1794 (3.8072)	grad_norm 0.9962 (1.1689)	
[2022-01-19 18:27:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][850/1251]	eta 0:14:47 lr 0.000874	time 2.0682 (2.2137)	loss 3.1123 (3.8049)	grad_norm 1.1766 (1.1684)	
[2022-01-19 18:27:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][860/1251]	eta 0:14:24 lr 0.000874	time 1.9208 (2.2105)	loss 3.5395 (3.8074)	grad_norm 1.3840 (1.1688)	
[2022-01-19 18:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][870/1251]	eta 0:14:01 lr 0.000874	time 1.6133 (2.2092)	loss 4.0579 (3.8111)	grad_norm 1.2906 (1.1683)	
[2022-01-19 18:28:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][880/1251]	eta 0:13:40 lr 0.000874	time 2.3517 (2.2114)	loss 3.4351 (3.8125)	grad_norm 1.0549 (1.1696)	
[2022-01-19 18:28:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][890/1251]	eta 0:13:18 lr 0.000874	time 2.2279 (2.2110)	loss 3.2793 (3.8103)	grad_norm 1.1821 (1.1691)	
[2022-01-19 18:29:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][900/1251]	eta 0:12:55 lr 0.000874	time 2.2613 (2.2106)	loss 3.4264 (3.8105)	grad_norm 0.9920 (1.1696)	
[2022-01-19 18:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][910/1251]	eta 0:12:33 lr 0.000874	time 1.9292 (2.2105)	loss 3.5345 (3.8114)	grad_norm 1.2426 (1.1691)	
[2022-01-19 18:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][920/1251]	eta 0:12:11 lr 0.000874	time 2.1937 (2.2101)	loss 4.1572 (3.8140)	grad_norm 1.1032 (1.1686)	
[2022-01-19 18:30:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][930/1251]	eta 0:11:49 lr 0.000874	time 1.7921 (2.2090)	loss 4.1691 (3.8154)	grad_norm 1.1471 (1.1673)	
[2022-01-19 18:30:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][940/1251]	eta 0:11:26 lr 0.000874	time 2.0041 (2.2078)	loss 4.5324 (3.8179)	grad_norm 1.3213 (1.1677)	
[2022-01-19 18:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][950/1251]	eta 0:11:03 lr 0.000874	time 1.5774 (2.2053)	loss 3.2881 (3.8199)	grad_norm 1.2142 (1.1684)	
[2022-01-19 18:31:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][960/1251]	eta 0:10:42 lr 0.000874	time 1.9090 (2.2063)	loss 3.0089 (3.8178)	grad_norm 1.3870 (1.1679)	
[2022-01-19 18:31:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][970/1251]	eta 0:10:20 lr 0.000874	time 1.7916 (2.2069)	loss 3.9629 (3.8199)	grad_norm 1.4815 (1.1678)	
[2022-01-19 18:32:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][980/1251]	eta 0:09:58 lr 0.000874	time 2.1683 (2.2084)	loss 3.6482 (3.8186)	grad_norm 1.1163 (1.1673)	
[2022-01-19 18:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][990/1251]	eta 0:09:36 lr 0.000874	time 2.1873 (2.2083)	loss 4.3216 (3.8211)	grad_norm 1.1602 (1.1672)	
[2022-01-19 18:32:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1000/1251]	eta 0:09:14 lr 0.000874	time 2.4753 (2.2084)	loss 3.9328 (3.8219)	grad_norm 1.0721 (1.1667)	
[2022-01-19 18:33:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1010/1251]	eta 0:08:51 lr 0.000874	time 1.7870 (2.2057)	loss 4.2751 (3.8232)	grad_norm 1.1758 (1.1664)	
[2022-01-19 18:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1020/1251]	eta 0:08:29 lr 0.000873	time 2.0014 (2.2036)	loss 3.7608 (3.8240)	grad_norm 1.2292 (1.1665)	
[2022-01-19 18:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1030/1251]	eta 0:08:06 lr 0.000873	time 2.2669 (2.2033)	loss 4.3884 (3.8226)	grad_norm 1.1345 (1.1658)	
[2022-01-19 18:34:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1040/1251]	eta 0:07:44 lr 0.000873	time 1.8417 (2.2024)	loss 3.3321 (3.8238)	grad_norm 1.7459 (1.1657)	
[2022-01-19 18:34:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1050/1251]	eta 0:07:22 lr 0.000873	time 2.3453 (2.2025)	loss 4.7116 (3.8277)	grad_norm 1.5090 (1.1662)	
[2022-01-19 18:34:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1060/1251]	eta 0:07:00 lr 0.000873	time 2.8147 (2.2034)	loss 2.7928 (3.8265)	grad_norm 1.1658 (1.1677)	
[2022-01-19 18:35:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1070/1251]	eta 0:06:38 lr 0.000873	time 2.0915 (2.2034)	loss 3.6695 (3.8263)	grad_norm 1.2374 (1.1679)	
[2022-01-19 18:35:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1080/1251]	eta 0:06:16 lr 0.000873	time 2.1712 (2.2032)	loss 3.0499 (3.8261)	grad_norm 1.1935 (1.1681)	
[2022-01-19 18:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1090/1251]	eta 0:05:54 lr 0.000873	time 2.6353 (2.2033)	loss 3.9667 (3.8257)	grad_norm 1.3531 (1.1674)	
[2022-01-19 18:36:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1100/1251]	eta 0:05:32 lr 0.000873	time 2.8370 (2.2037)	loss 3.5246 (3.8262)	grad_norm 0.9117 (1.1677)	
[2022-01-19 18:36:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1110/1251]	eta 0:05:10 lr 0.000873	time 1.9746 (2.2030)	loss 3.6647 (3.8280)	grad_norm 1.1973 (1.1678)	
[2022-01-19 18:37:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1120/1251]	eta 0:04:48 lr 0.000873	time 1.9448 (2.2014)	loss 2.8923 (3.8251)	grad_norm 1.3391 (1.1681)	
[2022-01-19 18:37:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1130/1251]	eta 0:04:26 lr 0.000873	time 2.1061 (2.2011)	loss 4.6405 (3.8277)	grad_norm 1.0680 (1.1682)	
[2022-01-19 18:37:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1140/1251]	eta 0:04:04 lr 0.000873	time 2.1587 (2.2006)	loss 4.0545 (3.8279)	grad_norm 1.1883 (1.1681)	
[2022-01-19 18:38:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1150/1251]	eta 0:03:42 lr 0.000873	time 2.4715 (2.2012)	loss 3.1111 (3.8273)	grad_norm 1.1254 (1.1676)	
[2022-01-19 18:38:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1160/1251]	eta 0:03:20 lr 0.000873	time 2.8726 (2.2023)	loss 3.5804 (3.8255)	grad_norm 1.3434 (1.1679)	
[2022-01-19 18:38:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1170/1251]	eta 0:02:58 lr 0.000873	time 1.5216 (2.2030)	loss 4.0106 (3.8262)	grad_norm 1.0588 (1.1677)	
[2022-01-19 18:39:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1180/1251]	eta 0:02:36 lr 0.000873	time 2.7551 (2.2040)	loss 4.2173 (3.8280)	grad_norm 1.1389 (1.1673)	
[2022-01-19 18:39:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1190/1251]	eta 0:02:14 lr 0.000873	time 1.8744 (2.2037)	loss 3.9668 (3.8245)	grad_norm 1.0758 (1.1678)	
[2022-01-19 18:39:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1200/1251]	eta 0:01:52 lr 0.000873	time 1.8547 (2.2021)	loss 3.0357 (3.8248)	grad_norm 1.0252 (1.1678)	
[2022-01-19 18:40:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1210/1251]	eta 0:01:30 lr 0.000873	time 1.9901 (2.2006)	loss 4.7462 (3.8268)	grad_norm 1.1311 (1.1674)	
[2022-01-19 18:40:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1220/1251]	eta 0:01:08 lr 0.000873	time 2.1738 (2.2002)	loss 2.8959 (3.8266)	grad_norm 1.0312 (1.1671)	
[2022-01-19 18:41:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1230/1251]	eta 0:00:46 lr 0.000873	time 2.1595 (2.2002)	loss 3.9961 (3.8270)	grad_norm 1.0021 (1.1667)	
[2022-01-19 18:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1240/1251]	eta 0:00:24 lr 0.000873	time 1.5434 (2.1999)	loss 3.3976 (3.8276)	grad_norm 1.0083 (1.1663)	
[2022-01-19 18:41:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [69/300][1250/1251]	eta 0:00:02 lr 0.000873	time 1.3537 (2.1953)	loss 4.3256 (3.8287)	grad_norm 1.2738 (1.1661)	
[2022-01-19 18:41:41 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 69 training takes 0:45:46
[2022-01-19 18:41:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.055 (18.055)	Loss 1.2438 (1.2438)	Acc@1 72.266 (72.266)	Acc@5 90.137 (90.137)	
[2022-01-19 18:42:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.328 (3.218)	Loss 1.2650 (1.2286)	Acc@1 72.168 (72.132)	Acc@5 90.039 (90.732)	
[2022-01-19 18:42:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.233 (2.596)	Loss 1.2310 (1.2149)	Acc@1 72.070 (72.145)	Acc@5 90.137 (90.974)	
[2022-01-19 18:42:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.213 (2.313)	Loss 1.1975 (1.2147)	Acc@1 71.289 (72.143)	Acc@5 91.992 (91.041)	
[2022-01-19 18:43:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.964 (2.163)	Loss 1.2014 (1.2161)	Acc@1 71.387 (72.025)	Acc@5 91.211 (90.978)	
[2022-01-19 18:43:17 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 71.996 Acc@5 91.026
[2022-01-19 18:43:17 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.0%
[2022-01-19 18:43:17 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.00%
[2022-01-19 18:43:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][0/1251]	eta 7:32:37 lr 0.000873	time 21.7090 (21.7090)	loss 4.0663 (4.0663)	grad_norm 1.1383 (1.1383)	
[2022-01-19 18:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][10/1251]	eta 1:24:00 lr 0.000873	time 2.2286 (4.0614)	loss 3.2290 (4.0304)	grad_norm 1.3083 (1.0809)	
[2022-01-19 18:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][20/1251]	eta 1:01:59 lr 0.000873	time 1.5688 (3.0219)	loss 3.9898 (3.8889)	grad_norm 1.1715 (1.0721)	
[2022-01-19 18:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][30/1251]	eta 0:57:46 lr 0.000873	time 1.5673 (2.8390)	loss 3.6633 (3.8640)	grad_norm 1.2204 (1.1013)	
[2022-01-19 18:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][40/1251]	eta 0:54:27 lr 0.000873	time 3.3223 (2.6983)	loss 4.2639 (3.9094)	grad_norm 1.1286 (1.1214)	
[2022-01-19 18:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][50/1251]	eta 0:52:53 lr 0.000873	time 2.8073 (2.6426)	loss 3.3341 (3.8235)	grad_norm 1.0099 (1.1216)	
[2022-01-19 18:45:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][60/1251]	eta 0:51:21 lr 0.000873	time 2.1739 (2.5875)	loss 4.2885 (3.8740)	grad_norm 1.0251 (1.1218)	
[2022-01-19 18:46:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][70/1251]	eta 0:49:41 lr 0.000873	time 1.9596 (2.5246)	loss 2.5479 (3.8386)	grad_norm 1.1684 (1.1254)	
[2022-01-19 18:46:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][80/1251]	eta 0:48:06 lr 0.000873	time 1.8385 (2.4650)	loss 2.7839 (3.8325)	grad_norm 1.2902 (1.1323)	
[2022-01-19 18:46:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][90/1251]	eta 0:47:00 lr 0.000873	time 1.7762 (2.4291)	loss 4.3650 (3.8257)	grad_norm 1.2490 (1.1426)	
[2022-01-19 18:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][100/1251]	eta 0:45:51 lr 0.000873	time 1.9061 (2.3905)	loss 3.2873 (3.8171)	grad_norm 1.0887 (1.1425)	
[2022-01-19 18:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][110/1251]	eta 0:44:47 lr 0.000873	time 1.9398 (2.3556)	loss 4.1109 (3.8182)	grad_norm 1.2078 (1.1471)	
[2022-01-19 18:48:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][120/1251]	eta 0:44:07 lr 0.000873	time 1.6902 (2.3407)	loss 3.3957 (3.7965)	grad_norm 1.1856 (1.1467)	
[2022-01-19 18:48:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][130/1251]	eta 0:43:39 lr 0.000872	time 2.6401 (2.3365)	loss 4.5332 (3.8132)	grad_norm 1.2316 (1.1530)	
[2022-01-19 18:48:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][140/1251]	eta 0:43:06 lr 0.000872	time 2.4873 (2.3284)	loss 4.1350 (3.7981)	grad_norm 1.2574 (1.1511)	
[2022-01-19 18:49:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][150/1251]	eta 0:42:35 lr 0.000872	time 2.5905 (2.3213)	loss 3.9922 (3.8076)	grad_norm 1.2004 (1.1582)	
[2022-01-19 18:49:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][160/1251]	eta 0:42:04 lr 0.000872	time 1.6786 (2.3137)	loss 4.1465 (3.8051)	grad_norm 1.0215 (1.1574)	
[2022-01-19 18:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][170/1251]	eta 0:41:43 lr 0.000872	time 2.5690 (2.3158)	loss 3.3058 (3.7974)	grad_norm 1.2229 (1.1566)	
[2022-01-19 18:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][180/1251]	eta 0:41:13 lr 0.000872	time 2.4159 (2.3094)	loss 4.1007 (3.8082)	grad_norm 1.1357 (1.1567)	
[2022-01-19 18:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][190/1251]	eta 0:40:49 lr 0.000872	time 2.2142 (2.3087)	loss 4.2170 (3.8113)	grad_norm 1.1966 (1.1570)	
[2022-01-19 18:51:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][200/1251]	eta 0:40:20 lr 0.000872	time 1.5632 (2.3027)	loss 3.3380 (3.8205)	grad_norm 1.4520 (1.1594)	
[2022-01-19 18:51:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][210/1251]	eta 0:39:45 lr 0.000872	time 1.6991 (2.2920)	loss 3.9940 (3.8159)	grad_norm 1.1229 (1.1556)	
[2022-01-19 18:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][220/1251]	eta 0:39:10 lr 0.000872	time 1.8915 (2.2799)	loss 4.2436 (3.8170)	grad_norm 1.1631 (1.1530)	
[2022-01-19 18:52:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][230/1251]	eta 0:38:44 lr 0.000872	time 2.7459 (2.2768)	loss 3.9805 (3.8173)	grad_norm 1.1553 (1.1544)	
[2022-01-19 18:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][240/1251]	eta 0:38:14 lr 0.000872	time 1.8978 (2.2698)	loss 4.5273 (3.8207)	grad_norm 1.0686 (1.1553)	
[2022-01-19 18:52:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][250/1251]	eta 0:37:44 lr 0.000872	time 1.9286 (2.2624)	loss 3.6799 (3.8143)	grad_norm 0.9932 (1.1547)	
[2022-01-19 18:53:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][260/1251]	eta 0:37:23 lr 0.000872	time 2.5149 (2.2638)	loss 4.0245 (3.8150)	grad_norm 1.2836 (1.1566)	
[2022-01-19 18:53:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][270/1251]	eta 0:37:01 lr 0.000872	time 3.1406 (2.2642)	loss 2.4008 (3.8119)	grad_norm 1.1424 (1.1573)	
[2022-01-19 18:53:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][280/1251]	eta 0:36:38 lr 0.000872	time 1.5634 (2.2644)	loss 4.0691 (3.8123)	grad_norm 1.1161 (1.1571)	
[2022-01-19 18:54:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][290/1251]	eta 0:36:19 lr 0.000872	time 2.4537 (2.2675)	loss 3.8929 (3.8066)	grad_norm 1.3240 (1.1617)	
[2022-01-19 18:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][300/1251]	eta 0:35:51 lr 0.000872	time 2.0801 (2.2626)	loss 4.3878 (3.8099)	grad_norm 1.2057 (1.1637)	
[2022-01-19 18:54:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][310/1251]	eta 0:35:21 lr 0.000872	time 2.2031 (2.2549)	loss 4.0407 (3.8191)	grad_norm 1.1777 (1.1646)	
[2022-01-19 18:55:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][320/1251]	eta 0:34:50 lr 0.000872	time 1.7560 (2.2452)	loss 3.7951 (3.8181)	grad_norm 1.2016 (1.1649)	
[2022-01-19 18:55:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][330/1251]	eta 0:34:23 lr 0.000872	time 2.0031 (2.2406)	loss 4.5286 (3.8151)	grad_norm 1.0858 (1.1643)	
[2022-01-19 18:55:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][340/1251]	eta 0:33:55 lr 0.000872	time 1.7322 (2.2345)	loss 3.9335 (3.8116)	grad_norm 1.1315 (1.1636)	
[2022-01-19 18:56:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][350/1251]	eta 0:33:27 lr 0.000872	time 1.8840 (2.2285)	loss 3.9251 (3.8075)	grad_norm 1.1230 (1.1621)	
[2022-01-19 18:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][360/1251]	eta 0:33:04 lr 0.000872	time 2.1558 (2.2270)	loss 3.5244 (3.8112)	grad_norm 1.0877 (1.1607)	
[2022-01-19 18:57:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][370/1251]	eta 0:32:43 lr 0.000872	time 2.8616 (2.2282)	loss 3.2117 (3.8090)	grad_norm 1.1789 (1.1627)	
[2022-01-19 18:57:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][380/1251]	eta 0:32:22 lr 0.000872	time 2.0941 (2.2302)	loss 3.8789 (3.8091)	grad_norm 1.1107 (1.1639)	
[2022-01-19 18:57:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][390/1251]	eta 0:32:03 lr 0.000872	time 2.5044 (2.2344)	loss 4.6116 (3.8142)	grad_norm 1.0615 (1.1650)	
[2022-01-19 18:58:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][400/1251]	eta 0:31:43 lr 0.000872	time 2.6294 (2.2368)	loss 4.1415 (3.8058)	grad_norm 1.1316 (1.1645)	
[2022-01-19 18:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][410/1251]	eta 0:31:23 lr 0.000872	time 2.8688 (2.2392)	loss 4.1585 (3.8147)	grad_norm 1.3277 (1.1656)	
[2022-01-19 18:58:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][420/1251]	eta 0:30:57 lr 0.000872	time 1.5407 (2.2353)	loss 4.5881 (3.8198)	grad_norm 1.0537 (1.1678)	
[2022-01-19 18:59:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][430/1251]	eta 0:30:32 lr 0.000872	time 1.9966 (2.2317)	loss 3.9269 (3.8175)	grad_norm 1.2140 (1.1687)	
[2022-01-19 18:59:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][440/1251]	eta 0:30:09 lr 0.000872	time 2.4638 (2.2313)	loss 3.9321 (3.8132)	grad_norm 1.1881 (1.1680)	
[2022-01-19 19:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][450/1251]	eta 0:29:47 lr 0.000872	time 2.4594 (2.2316)	loss 2.7947 (3.8075)	grad_norm 1.0297 (1.1667)	
[2022-01-19 19:00:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][460/1251]	eta 0:29:22 lr 0.000872	time 1.7088 (2.2288)	loss 3.8170 (3.8067)	grad_norm 1.3790 (1.1688)	
[2022-01-19 19:00:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][470/1251]	eta 0:28:59 lr 0.000872	time 2.4563 (2.2270)	loss 4.7189 (3.8100)	grad_norm 1.3470 (1.1704)	
[2022-01-19 19:01:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][480/1251]	eta 0:28:36 lr 0.000872	time 2.8409 (2.2266)	loss 4.3637 (3.8090)	grad_norm 1.3535 (1.1712)	
[2022-01-19 19:01:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][490/1251]	eta 0:28:15 lr 0.000871	time 2.2062 (2.2281)	loss 3.5136 (3.8044)	grad_norm 1.1303 (1.1699)	
[2022-01-19 19:01:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][500/1251]	eta 0:27:52 lr 0.000871	time 1.8974 (2.2275)	loss 3.6582 (3.8080)	grad_norm 0.9736 (1.1679)	
[2022-01-19 19:02:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][510/1251]	eta 0:27:29 lr 0.000871	time 2.3152 (2.2259)	loss 3.3145 (3.8039)	grad_norm 1.0802 (1.1668)	
[2022-01-19 19:02:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][520/1251]	eta 0:27:04 lr 0.000871	time 1.9064 (2.2225)	loss 4.1473 (3.8033)	grad_norm 1.3362 (1.1669)	
[2022-01-19 19:02:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][530/1251]	eta 0:26:41 lr 0.000871	time 2.3143 (2.2207)	loss 3.0382 (3.7997)	grad_norm 1.1637 (1.1657)	
[2022-01-19 19:03:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][540/1251]	eta 0:26:18 lr 0.000871	time 1.8029 (2.2203)	loss 4.0831 (3.8026)	grad_norm 1.0953 (1.1676)	
[2022-01-19 19:03:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][550/1251]	eta 0:25:55 lr 0.000871	time 1.8210 (2.2191)	loss 3.3108 (3.8006)	grad_norm 1.1292 (1.1666)	
[2022-01-19 19:04:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][560/1251]	eta 0:25:32 lr 0.000871	time 2.4161 (2.2177)	loss 4.3616 (3.7987)	grad_norm 1.0474 (1.1666)	
[2022-01-19 19:04:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][570/1251]	eta 0:25:10 lr 0.000871	time 2.8533 (2.2187)	loss 3.8471 (3.7940)	grad_norm 1.3063 (1.1671)	
[2022-01-19 19:04:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][580/1251]	eta 0:24:47 lr 0.000871	time 1.8065 (2.2175)	loss 4.5714 (3.7967)	grad_norm 1.1155 (1.1667)	
[2022-01-19 19:05:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][590/1251]	eta 0:24:23 lr 0.000871	time 1.9597 (2.2142)	loss 4.1805 (3.7978)	grad_norm 1.0972 (1.1680)	
[2022-01-19 19:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][600/1251]	eta 0:23:59 lr 0.000871	time 2.0581 (2.2106)	loss 4.2003 (3.7994)	grad_norm 1.0449 (1.1682)	
[2022-01-19 19:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][610/1251]	eta 0:23:35 lr 0.000871	time 2.2559 (2.2087)	loss 4.3427 (3.8003)	grad_norm 1.2657 (1.1690)	
[2022-01-19 19:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][620/1251]	eta 0:23:12 lr 0.000871	time 1.8293 (2.2069)	loss 3.1053 (3.8034)	grad_norm 1.1684 (1.1686)	
[2022-01-19 19:06:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][630/1251]	eta 0:22:50 lr 0.000871	time 1.9732 (2.2074)	loss 4.0280 (3.8058)	grad_norm 1.1885 (1.1680)	
[2022-01-19 19:06:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][640/1251]	eta 0:22:28 lr 0.000871	time 2.2468 (2.2072)	loss 3.1868 (3.8028)	grad_norm 1.1100 (1.1683)	
[2022-01-19 19:07:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][650/1251]	eta 0:22:06 lr 0.000871	time 1.8259 (2.2068)	loss 4.3876 (3.8050)	grad_norm 1.0736 (1.1679)	
[2022-01-19 19:07:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][660/1251]	eta 0:21:44 lr 0.000871	time 2.1318 (2.2080)	loss 3.9569 (3.7975)	grad_norm 1.2851 (1.1672)	
[2022-01-19 19:08:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][670/1251]	eta 0:21:23 lr 0.000871	time 2.2442 (2.2089)	loss 4.1989 (3.7987)	grad_norm 1.1903 (1.1672)	
[2022-01-19 19:08:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][680/1251]	eta 0:21:02 lr 0.000871	time 1.8861 (2.2109)	loss 4.4778 (3.7983)	grad_norm 1.1210 (1.1670)	
[2022-01-19 19:08:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][690/1251]	eta 0:20:40 lr 0.000871	time 2.4729 (2.2111)	loss 3.9306 (3.7972)	grad_norm 1.2410 (1.1665)	
[2022-01-19 19:09:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][700/1251]	eta 0:20:19 lr 0.000871	time 1.8588 (2.2134)	loss 3.8688 (3.8024)	grad_norm 1.2208 (1.1662)	
[2022-01-19 19:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][710/1251]	eta 0:19:58 lr 0.000871	time 3.0569 (2.2158)	loss 4.0788 (3.8019)	grad_norm 1.2196 (1.1657)	
[2022-01-19 19:09:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][720/1251]	eta 0:19:35 lr 0.000871	time 1.5207 (2.2146)	loss 3.4471 (3.8028)	grad_norm 1.2694 (1.1653)	
[2022-01-19 19:10:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][730/1251]	eta 0:19:11 lr 0.000871	time 1.5465 (2.2108)	loss 2.8545 (3.7993)	grad_norm 1.2003 (1.1657)	
[2022-01-19 19:10:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][740/1251]	eta 0:18:48 lr 0.000871	time 1.8688 (2.2080)	loss 3.2512 (3.8000)	grad_norm 1.1181 (1.1662)	
[2022-01-19 19:10:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][750/1251]	eta 0:18:25 lr 0.000871	time 2.8507 (2.2071)	loss 4.6196 (3.8026)	grad_norm 1.1273 (1.1674)	
[2022-01-19 19:11:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][760/1251]	eta 0:18:02 lr 0.000871	time 1.8724 (2.2054)	loss 2.9507 (3.8012)	grad_norm 1.1597 (1.1681)	
[2022-01-19 19:11:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][770/1251]	eta 0:17:41 lr 0.000871	time 2.4463 (2.2068)	loss 4.1601 (3.7992)	grad_norm 1.2490 (1.1677)	
[2022-01-19 19:12:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][780/1251]	eta 0:17:19 lr 0.000871	time 2.3345 (2.2079)	loss 3.2975 (3.7996)	grad_norm 1.1434 (1.1682)	
[2022-01-19 19:12:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][790/1251]	eta 0:16:58 lr 0.000871	time 3.0588 (2.2094)	loss 4.4658 (3.8035)	grad_norm 1.0016 (1.1685)	
[2022-01-19 19:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][800/1251]	eta 0:16:37 lr 0.000871	time 1.6054 (2.2119)	loss 4.2332 (3.8049)	grad_norm 0.9432 (1.1677)	
[2022-01-19 19:13:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][810/1251]	eta 0:16:16 lr 0.000871	time 2.0856 (2.2135)	loss 4.4615 (3.8076)	grad_norm 1.1639 (1.1676)	
[2022-01-19 19:13:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][820/1251]	eta 0:15:55 lr 0.000871	time 2.8161 (2.2160)	loss 4.3316 (3.8108)	grad_norm 1.1764 (1.1673)	
[2022-01-19 19:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][830/1251]	eta 0:15:32 lr 0.000871	time 2.5334 (2.2152)	loss 4.5302 (3.8121)	grad_norm 1.1166 (1.1669)	
[2022-01-19 19:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][840/1251]	eta 0:15:09 lr 0.000871	time 1.8022 (2.2122)	loss 4.1526 (3.8124)	grad_norm 1.2726 (1.1667)	
[2022-01-19 19:14:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][850/1251]	eta 0:14:45 lr 0.000870	time 1.9394 (2.2086)	loss 2.7084 (3.8115)	grad_norm 1.8276 (1.1670)	
[2022-01-19 19:14:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][860/1251]	eta 0:14:22 lr 0.000870	time 1.5621 (2.2062)	loss 4.1235 (3.8148)	grad_norm 1.0028 (1.1676)	
[2022-01-19 19:15:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][870/1251]	eta 0:13:59 lr 0.000870	time 2.0458 (2.2039)	loss 2.9019 (3.8151)	grad_norm 1.2209 (1.1669)	
[2022-01-19 19:15:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][880/1251]	eta 0:13:37 lr 0.000870	time 1.7664 (2.2032)	loss 4.3306 (3.8177)	grad_norm 1.2915 (1.1674)	
[2022-01-19 19:16:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][890/1251]	eta 0:13:15 lr 0.000870	time 2.9500 (2.2035)	loss 3.9997 (3.8185)	grad_norm 1.5759 (1.1682)	
[2022-01-19 19:16:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][900/1251]	eta 0:12:53 lr 0.000870	time 1.6454 (2.2023)	loss 4.3547 (3.8194)	grad_norm 1.1218 (1.1687)	
[2022-01-19 19:16:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][910/1251]	eta 0:12:31 lr 0.000870	time 2.0369 (2.2035)	loss 3.5662 (3.8219)	grad_norm 0.9695 (1.1677)	
[2022-01-19 19:17:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][920/1251]	eta 0:12:10 lr 0.000870	time 3.0791 (2.2067)	loss 4.3108 (3.8222)	grad_norm 1.1221 (1.1673)	
[2022-01-19 19:17:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][930/1251]	eta 0:11:50 lr 0.000870	time 2.2134 (2.2131)	loss 4.2469 (3.8229)	grad_norm 1.1494 (1.1668)	
[2022-01-19 19:18:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][940/1251]	eta 0:11:29 lr 0.000870	time 2.5121 (2.2156)	loss 2.8108 (3.8239)	grad_norm 1.2896 (1.1667)	
[2022-01-19 19:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][950/1251]	eta 0:11:07 lr 0.000870	time 1.7639 (2.2161)	loss 4.3706 (3.8232)	grad_norm 1.0556 (1.1669)	
[2022-01-19 19:18:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][960/1251]	eta 0:10:44 lr 0.000870	time 1.9733 (2.2145)	loss 3.5086 (3.8235)	grad_norm 0.9856 (1.1660)	
[2022-01-19 19:19:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][970/1251]	eta 0:10:21 lr 0.000870	time 1.8876 (2.2108)	loss 4.1652 (3.8246)	grad_norm 1.2360 (1.1658)	
[2022-01-19 19:19:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][980/1251]	eta 0:09:58 lr 0.000870	time 2.2235 (2.2088)	loss 4.5553 (3.8235)	grad_norm 1.0664 (1.1653)	
[2022-01-19 19:19:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][990/1251]	eta 0:09:36 lr 0.000870	time 2.7981 (2.2096)	loss 4.0540 (3.8244)	grad_norm 1.0787 (1.1654)	
[2022-01-19 19:20:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1000/1251]	eta 0:09:14 lr 0.000870	time 2.2591 (2.2093)	loss 4.4040 (3.8238)	grad_norm 1.1260 (1.1654)	
[2022-01-19 19:20:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1010/1251]	eta 0:08:52 lr 0.000870	time 2.5623 (2.2100)	loss 3.2832 (3.8226)	grad_norm 1.2045 (1.1653)	
[2022-01-19 19:20:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1020/1251]	eta 0:08:30 lr 0.000870	time 2.5349 (2.2103)	loss 4.6729 (3.8265)	grad_norm 1.1318 (1.1656)	
[2022-01-19 19:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1030/1251]	eta 0:08:08 lr 0.000870	time 1.9396 (2.2101)	loss 4.1193 (3.8290)	grad_norm 1.1448 (1.1656)	
[2022-01-19 19:21:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1040/1251]	eta 0:07:46 lr 0.000870	time 1.8776 (2.2104)	loss 3.7326 (3.8276)	grad_norm 1.2009 (1.1661)	
[2022-01-19 19:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1050/1251]	eta 0:07:24 lr 0.000870	time 3.1575 (2.2115)	loss 3.7984 (3.8303)	grad_norm 1.1482 (1.1659)	
[2022-01-19 19:22:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1060/1251]	eta 0:07:02 lr 0.000870	time 1.9603 (2.2110)	loss 4.1133 (3.8326)	grad_norm 1.0913 (1.1663)	
[2022-01-19 19:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1070/1251]	eta 0:06:39 lr 0.000870	time 2.2630 (2.2099)	loss 3.0849 (3.8321)	grad_norm 0.9529 (1.1656)	
[2022-01-19 19:23:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1080/1251]	eta 0:06:17 lr 0.000870	time 1.5582 (2.2097)	loss 4.8674 (3.8342)	grad_norm 1.3434 (1.1660)	
[2022-01-19 19:23:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1090/1251]	eta 0:05:55 lr 0.000870	time 2.4737 (2.2096)	loss 3.2146 (3.8339)	grad_norm 1.2427 (1.1664)	
[2022-01-19 19:23:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1100/1251]	eta 0:05:33 lr 0.000870	time 1.8891 (2.2087)	loss 4.5865 (3.8348)	grad_norm 1.1037 (1.1660)	
[2022-01-19 19:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1110/1251]	eta 0:05:11 lr 0.000870	time 2.9661 (2.2085)	loss 3.4667 (3.8347)	grad_norm 1.4781 (1.1663)	
[2022-01-19 19:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1120/1251]	eta 0:04:48 lr 0.000870	time 1.6738 (2.2060)	loss 4.3372 (3.8351)	grad_norm 1.2041 (1.1665)	
[2022-01-19 19:24:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1130/1251]	eta 0:04:26 lr 0.000870	time 2.4963 (2.2052)	loss 4.4843 (3.8366)	grad_norm 1.0108 (1.1660)	
[2022-01-19 19:25:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1140/1251]	eta 0:04:04 lr 0.000870	time 1.8758 (2.2049)	loss 3.7005 (3.8358)	grad_norm 1.1347 (1.1661)	
[2022-01-19 19:25:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1150/1251]	eta 0:03:42 lr 0.000870	time 2.4203 (2.2055)	loss 3.8334 (3.8361)	grad_norm 0.9971 (1.1656)	
[2022-01-19 19:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1160/1251]	eta 0:03:20 lr 0.000870	time 1.9387 (2.2056)	loss 3.0383 (3.8362)	grad_norm 1.0196 (1.1655)	
[2022-01-19 19:26:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1170/1251]	eta 0:02:58 lr 0.000870	time 2.8056 (2.2056)	loss 3.4445 (3.8333)	grad_norm 0.9987 (1.1664)	
[2022-01-19 19:26:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1180/1251]	eta 0:02:36 lr 0.000870	time 1.9082 (2.2052)	loss 3.3690 (3.8329)	grad_norm 1.1124 (1.1669)	
[2022-01-19 19:27:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1190/1251]	eta 0:02:14 lr 0.000870	time 2.4689 (2.2045)	loss 3.2743 (3.8325)	grad_norm 1.3044 (1.1668)	
[2022-01-19 19:27:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1200/1251]	eta 0:01:52 lr 0.000870	time 1.8218 (2.2041)	loss 3.8034 (3.8319)	grad_norm 1.1495 (1.1672)	
[2022-01-19 19:27:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1210/1251]	eta 0:01:30 lr 0.000869	time 1.7417 (2.2037)	loss 4.3265 (3.8301)	grad_norm 1.1603 (1.1672)	
[2022-01-19 19:28:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1220/1251]	eta 0:01:08 lr 0.000869	time 1.5365 (2.2034)	loss 4.3048 (3.8291)	grad_norm 1.1694 (1.1671)	
[2022-01-19 19:28:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1230/1251]	eta 0:00:46 lr 0.000869	time 2.9132 (2.2037)	loss 4.1900 (3.8297)	grad_norm 1.1508 (1.1668)	
[2022-01-19 19:28:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1240/1251]	eta 0:00:24 lr 0.000869	time 1.4347 (2.2023)	loss 4.0592 (3.8280)	grad_norm 1.2212 (1.1672)	
[2022-01-19 19:29:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [70/300][1250/1251]	eta 0:00:02 lr 0.000869	time 1.1240 (2.1973)	loss 4.0034 (3.8268)	grad_norm 1.2232 (1.1671)	
[2022-01-19 19:29:07 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 70 training takes 0:45:49
[2022-01-19 19:29:07 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_70 saving......
[2022-01-19 19:29:18 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_70 saved !!!
[2022-01-19 19:29:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.900 (16.900)	Loss 1.1781 (1.1781)	Acc@1 70.996 (70.996)	Acc@5 90.527 (90.527)	
[2022-01-19 19:29:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.660 (2.814)	Loss 1.1416 (1.2048)	Acc@1 73.145 (71.813)	Acc@5 91.992 (91.202)	
[2022-01-19 19:30:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.590 (2.388)	Loss 1.1710 (1.2042)	Acc@1 73.438 (71.917)	Acc@5 91.699 (91.090)	
[2022-01-19 19:30:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.264 (2.082)	Loss 1.2411 (1.2128)	Acc@1 71.484 (71.888)	Acc@5 90.332 (90.921)	
[2022-01-19 19:30:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.097 (2.045)	Loss 1.1573 (1.2098)	Acc@1 72.070 (71.858)	Acc@5 91.895 (90.994)	
[2022-01-19 19:30:50 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 71.784 Acc@5 91.102
[2022-01-19 19:30:50 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 71.8%
[2022-01-19 19:30:50 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.00%
[2022-01-19 19:31:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][0/1251]	eta 7:35:36 lr 0.000869	time 21.8515 (21.8515)	loss 3.2346 (3.2346)	grad_norm 1.2926 (1.2926)	
[2022-01-19 19:31:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][10/1251]	eta 1:23:12 lr 0.000869	time 2.6388 (4.0228)	loss 4.4890 (3.9898)	grad_norm 1.0160 (1.1168)	
[2022-01-19 19:31:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][20/1251]	eta 1:05:04 lr 0.000869	time 1.9521 (3.1715)	loss 3.8652 (3.9698)	grad_norm 1.1180 (1.1170)	
[2022-01-19 19:32:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][30/1251]	eta 1:00:22 lr 0.000869	time 1.4664 (2.9665)	loss 4.5333 (3.8351)	grad_norm 1.3712 (1.1502)	
[2022-01-19 19:32:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][40/1251]	eta 0:57:38 lr 0.000869	time 2.6944 (2.8557)	loss 3.5197 (3.8453)	grad_norm 1.0976 (1.1600)	
[2022-01-19 19:33:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][50/1251]	eta 0:55:19 lr 0.000869	time 3.4305 (2.7636)	loss 3.6979 (3.8539)	grad_norm 1.0455 (1.1432)	
[2022-01-19 19:33:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][60/1251]	eta 0:52:49 lr 0.000869	time 1.8778 (2.6610)	loss 3.8442 (3.8706)	grad_norm 1.0464 (1.1360)	
[2022-01-19 19:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][70/1251]	eta 0:50:55 lr 0.000869	time 2.0525 (2.5873)	loss 3.7958 (3.8752)	grad_norm 1.1404 (1.1430)	
[2022-01-19 19:34:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][80/1251]	eta 0:49:01 lr 0.000869	time 2.0163 (2.5118)	loss 3.9058 (3.8388)	grad_norm 1.3244 (1.1514)	
[2022-01-19 19:34:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][90/1251]	eta 0:47:37 lr 0.000869	time 2.5759 (2.4615)	loss 4.0603 (3.8379)	grad_norm 1.1234 (1.1545)	
[2022-01-19 19:34:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][100/1251]	eta 0:46:34 lr 0.000869	time 2.3263 (2.4276)	loss 4.1649 (3.8338)	grad_norm 1.0814 (1.1594)	
[2022-01-19 19:35:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][110/1251]	eta 0:45:44 lr 0.000869	time 2.2871 (2.4056)	loss 3.8489 (3.8388)	grad_norm 1.1690 (1.1646)	
[2022-01-19 19:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][120/1251]	eta 0:45:12 lr 0.000869	time 2.0878 (2.3982)	loss 4.1862 (3.8354)	grad_norm 1.2542 (1.1661)	
[2022-01-19 19:36:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][130/1251]	eta 0:44:37 lr 0.000869	time 2.1046 (2.3888)	loss 3.2743 (3.8073)	grad_norm 1.1748 (1.1630)	
[2022-01-19 19:36:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][140/1251]	eta 0:44:04 lr 0.000869	time 2.3081 (2.3804)	loss 4.5660 (3.8186)	grad_norm 1.2746 (1.1591)	
[2022-01-19 19:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][150/1251]	eta 0:43:18 lr 0.000869	time 1.8927 (2.3602)	loss 4.5595 (3.8144)	grad_norm 1.1895 (1.1599)	
[2022-01-19 19:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][160/1251]	eta 0:42:36 lr 0.000869	time 1.6023 (2.3430)	loss 3.2176 (3.8085)	grad_norm 0.9320 (1.1597)	
[2022-01-19 19:37:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][170/1251]	eta 0:41:51 lr 0.000869	time 1.7761 (2.3233)	loss 3.2463 (3.8120)	grad_norm 1.7075 (1.1675)	
[2022-01-19 19:37:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][180/1251]	eta 0:41:26 lr 0.000869	time 2.3080 (2.3215)	loss 3.8870 (3.8271)	grad_norm 1.1737 (1.1715)	
[2022-01-19 19:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][190/1251]	eta 0:41:10 lr 0.000869	time 2.1736 (2.3281)	loss 3.5050 (3.8178)	grad_norm 1.3416 (1.1784)	
[2022-01-19 19:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][200/1251]	eta 0:40:48 lr 0.000869	time 2.1846 (2.3301)	loss 3.8396 (3.7979)	grad_norm 1.0885 (1.1798)	
[2022-01-19 19:39:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][210/1251]	eta 0:40:19 lr 0.000869	time 1.9024 (2.3238)	loss 4.2950 (3.8039)	grad_norm 1.0353 (1.1776)	
[2022-01-19 19:39:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][220/1251]	eta 0:39:43 lr 0.000869	time 1.9406 (2.3115)	loss 2.7470 (3.8000)	grad_norm 1.1945 (1.1802)	
[2022-01-19 19:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][230/1251]	eta 0:39:07 lr 0.000869	time 1.8472 (2.2996)	loss 3.9792 (3.7953)	grad_norm 1.5844 (1.1799)	
[2022-01-19 19:40:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][240/1251]	eta 0:38:34 lr 0.000869	time 1.9281 (2.2891)	loss 3.9854 (3.8049)	grad_norm 1.0022 (1.1801)	
[2022-01-19 19:40:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][250/1251]	eta 0:38:07 lr 0.000869	time 2.1720 (2.2851)	loss 3.4298 (3.7859)	grad_norm 1.4263 (1.1789)	
[2022-01-19 19:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][260/1251]	eta 0:37:43 lr 0.000869	time 2.5586 (2.2840)	loss 3.7160 (3.7892)	grad_norm 1.1288 (1.1784)	
[2022-01-19 19:41:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][270/1251]	eta 0:37:14 lr 0.000869	time 1.9565 (2.2778)	loss 4.7694 (3.7862)	grad_norm 1.0858 (1.1783)	
[2022-01-19 19:41:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][280/1251]	eta 0:36:48 lr 0.000869	time 1.6688 (2.2740)	loss 3.5018 (3.7732)	grad_norm 0.9776 (1.1769)	
[2022-01-19 19:41:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][290/1251]	eta 0:36:25 lr 0.000869	time 2.5682 (2.2743)	loss 3.6301 (3.7773)	grad_norm 1.3155 (1.1796)	
[2022-01-19 19:42:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][300/1251]	eta 0:36:06 lr 0.000869	time 1.7777 (2.2778)	loss 4.3330 (3.7733)	grad_norm 1.2379 (1.1803)	
[2022-01-19 19:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][310/1251]	eta 0:35:44 lr 0.000868	time 1.9109 (2.2787)	loss 3.0865 (3.7756)	grad_norm 1.0941 (1.1797)	
[2022-01-19 19:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][320/1251]	eta 0:35:19 lr 0.000868	time 1.8600 (2.2764)	loss 4.2967 (3.7817)	grad_norm 1.0674 (1.1786)	
[2022-01-19 19:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][330/1251]	eta 0:34:47 lr 0.000868	time 1.7029 (2.2669)	loss 4.3509 (3.7810)	grad_norm 1.1205 (1.1777)	
[2022-01-19 19:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][340/1251]	eta 0:34:18 lr 0.000868	time 1.7603 (2.2592)	loss 3.1596 (3.7768)	grad_norm 1.1985 (1.1770)	
[2022-01-19 19:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][350/1251]	eta 0:33:53 lr 0.000868	time 1.9077 (2.2574)	loss 3.8543 (3.7668)	grad_norm 1.5024 (1.1815)	
[2022-01-19 19:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][360/1251]	eta 0:33:33 lr 0.000868	time 1.8610 (2.2596)	loss 2.5549 (3.7655)	grad_norm 1.4179 (1.1841)	
[2022-01-19 19:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][370/1251]	eta 0:33:10 lr 0.000868	time 2.8407 (2.2591)	loss 4.7445 (3.7732)	grad_norm 1.2719 (1.1829)	
[2022-01-19 19:45:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][380/1251]	eta 0:32:48 lr 0.000868	time 2.2477 (2.2596)	loss 3.7124 (3.7721)	grad_norm 1.1124 (1.1811)	
[2022-01-19 19:45:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][390/1251]	eta 0:32:24 lr 0.000868	time 2.1773 (2.2587)	loss 4.4787 (3.7755)	grad_norm 1.0056 (1.1801)	
[2022-01-19 19:45:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][400/1251]	eta 0:32:01 lr 0.000868	time 2.2918 (2.2574)	loss 3.2279 (3.7697)	grad_norm 1.1748 (1.1798)	
[2022-01-19 19:46:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][410/1251]	eta 0:31:36 lr 0.000868	time 2.5944 (2.2548)	loss 3.5123 (3.7682)	grad_norm 1.1092 (1.1799)	
[2022-01-19 19:46:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][420/1251]	eta 0:31:10 lr 0.000868	time 2.1705 (2.2506)	loss 2.7351 (3.7671)	grad_norm 1.0174 (1.1787)	
[2022-01-19 19:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][430/1251]	eta 0:30:49 lr 0.000868	time 2.2055 (2.2528)	loss 4.2278 (3.7639)	grad_norm 1.0406 (1.1774)	
[2022-01-19 19:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][440/1251]	eta 0:30:27 lr 0.000868	time 2.5581 (2.2534)	loss 3.2962 (3.7646)	grad_norm 1.2054 (1.1773)	
[2022-01-19 19:47:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][450/1251]	eta 0:30:02 lr 0.000868	time 1.9902 (2.2500)	loss 3.1918 (3.7659)	grad_norm 1.1878 (1.1776)	
[2022-01-19 19:48:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][460/1251]	eta 0:29:35 lr 0.000868	time 2.0210 (2.2450)	loss 4.4845 (3.7725)	grad_norm 1.2425 (1.1776)	
[2022-01-19 19:48:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][470/1251]	eta 0:29:11 lr 0.000868	time 1.8534 (2.2429)	loss 4.2378 (3.7760)	grad_norm 1.2848 (1.1775)	
[2022-01-19 19:48:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][480/1251]	eta 0:28:48 lr 0.000868	time 2.4928 (2.2413)	loss 2.7598 (3.7764)	grad_norm 1.3669 (1.1790)	
[2022-01-19 19:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][490/1251]	eta 0:28:24 lr 0.000868	time 1.6597 (2.2397)	loss 3.9954 (3.7797)	grad_norm 1.0464 (1.1805)	
[2022-01-19 19:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][500/1251]	eta 0:28:01 lr 0.000868	time 1.9012 (2.2386)	loss 3.5979 (3.7770)	grad_norm 0.9362 (1.1805)	
[2022-01-19 19:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][510/1251]	eta 0:27:40 lr 0.000868	time 2.6686 (2.2416)	loss 3.3322 (3.7774)	grad_norm 0.9668 (1.1798)	
[2022-01-19 19:50:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][520/1251]	eta 0:27:20 lr 0.000868	time 3.6605 (2.2438)	loss 4.7012 (3.7827)	grad_norm 1.1538 (1.1796)	
[2022-01-19 19:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][530/1251]	eta 0:26:56 lr 0.000868	time 2.3141 (2.2419)	loss 3.7901 (3.7780)	grad_norm 1.2135 (1.1790)	
[2022-01-19 19:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][540/1251]	eta 0:26:31 lr 0.000868	time 1.6575 (2.2388)	loss 4.4076 (3.7786)	grad_norm 1.1024 (1.1789)	
[2022-01-19 19:51:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][550/1251]	eta 0:26:06 lr 0.000868	time 1.8133 (2.2346)	loss 3.4172 (3.7770)	grad_norm 1.1076 (1.1786)	
[2022-01-19 19:51:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][560/1251]	eta 0:25:40 lr 0.000868	time 1.8789 (2.2296)	loss 3.3564 (3.7757)	grad_norm 1.3760 (1.1794)	
[2022-01-19 19:52:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][570/1251]	eta 0:25:16 lr 0.000868	time 2.1348 (2.2265)	loss 3.3520 (3.7791)	grad_norm 1.2398 (1.1790)	
[2022-01-19 19:52:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][580/1251]	eta 0:24:51 lr 0.000868	time 1.6921 (2.2231)	loss 3.7896 (3.7735)	grad_norm 1.0157 (1.1793)	
[2022-01-19 19:52:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][590/1251]	eta 0:24:29 lr 0.000868	time 1.8668 (2.2225)	loss 4.0599 (3.7778)	grad_norm 1.0599 (1.1784)	
[2022-01-19 19:53:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][600/1251]	eta 0:24:05 lr 0.000868	time 1.6613 (2.2211)	loss 3.0542 (3.7780)	grad_norm 1.1322 (1.1788)	
[2022-01-19 19:53:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][610/1251]	eta 0:23:43 lr 0.000868	time 2.4220 (2.2203)	loss 3.3036 (3.7845)	grad_norm 1.2819 (1.1783)	
[2022-01-19 19:53:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][620/1251]	eta 0:23:20 lr 0.000868	time 2.8951 (2.2197)	loss 4.3276 (3.7859)	grad_norm 1.2522 (1.1785)	
[2022-01-19 19:54:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][630/1251]	eta 0:22:58 lr 0.000868	time 1.6756 (2.2191)	loss 3.6783 (3.7886)	grad_norm 1.1436 (1.1786)	
[2022-01-19 19:54:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][640/1251]	eta 0:22:36 lr 0.000868	time 1.8678 (2.2200)	loss 3.5123 (3.7871)	grad_norm 0.9413 (1.1775)	
[2022-01-19 19:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][650/1251]	eta 0:22:15 lr 0.000868	time 1.5085 (2.2228)	loss 3.6600 (3.7887)	grad_norm 0.9765 (1.1769)	
[2022-01-19 19:55:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][660/1251]	eta 0:21:55 lr 0.000868	time 3.1080 (2.2258)	loss 4.4061 (3.7903)	grad_norm 1.2388 (1.1780)	
[2022-01-19 19:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][670/1251]	eta 0:21:32 lr 0.000867	time 1.9541 (2.2245)	loss 4.3063 (3.7934)	grad_norm 1.1226 (1.1776)	
[2022-01-19 19:56:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][680/1251]	eta 0:21:09 lr 0.000867	time 1.6650 (2.2235)	loss 4.3887 (3.7943)	grad_norm 1.0664 (1.1770)	
[2022-01-19 19:56:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][690/1251]	eta 0:20:45 lr 0.000867	time 2.2567 (2.2208)	loss 3.7620 (3.7969)	grad_norm 1.2916 (1.1761)	
[2022-01-19 19:56:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][700/1251]	eta 0:20:23 lr 0.000867	time 1.6874 (2.2196)	loss 4.0986 (3.7958)	grad_norm 1.1793 (1.1762)	
[2022-01-19 19:57:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][710/1251]	eta 0:20:00 lr 0.000867	time 1.9134 (2.2188)	loss 4.1320 (3.7934)	grad_norm 1.1116 (1.1756)	
[2022-01-19 19:57:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][720/1251]	eta 0:19:37 lr 0.000867	time 1.5615 (2.2182)	loss 3.9458 (3.7923)	grad_norm 1.2437 (1.1747)	
[2022-01-19 19:57:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][730/1251]	eta 0:19:14 lr 0.000867	time 1.7064 (2.2160)	loss 4.1225 (3.7927)	grad_norm 1.0751 (1.1752)	
[2022-01-19 19:58:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][740/1251]	eta 0:18:53 lr 0.000867	time 2.2651 (2.2173)	loss 3.5036 (3.7953)	grad_norm 1.1871 (1.1760)	
[2022-01-19 19:58:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][750/1251]	eta 0:18:32 lr 0.000867	time 3.1590 (2.2204)	loss 4.4783 (3.7948)	grad_norm 1.4758 (1.1766)	
[2022-01-19 19:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][760/1251]	eta 0:18:11 lr 0.000867	time 1.9828 (2.2223)	loss 4.0752 (3.7951)	grad_norm 1.1398 (1.1770)	
[2022-01-19 19:59:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][770/1251]	eta 0:17:48 lr 0.000867	time 1.5508 (2.2213)	loss 3.9787 (3.7990)	grad_norm 1.1746 (1.1764)	
[2022-01-19 19:59:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][780/1251]	eta 0:17:24 lr 0.000867	time 1.5580 (2.2186)	loss 4.0199 (3.8020)	grad_norm 1.0374 (1.1755)	
[2022-01-19 20:00:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][790/1251]	eta 0:17:02 lr 0.000867	time 2.2159 (2.2169)	loss 4.0203 (3.8040)	grad_norm 1.0999 (1.1749)	
[2022-01-19 20:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][800/1251]	eta 0:16:41 lr 0.000867	time 2.7076 (2.2216)	loss 4.4054 (3.8096)	grad_norm 1.2135 (1.1752)	
[2022-01-19 20:00:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][810/1251]	eta 0:16:18 lr 0.000867	time 1.9074 (2.2193)	loss 3.5409 (3.8062)	grad_norm 1.1608 (1.1763)	
[2022-01-19 20:01:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][820/1251]	eta 0:15:56 lr 0.000867	time 2.1793 (2.2184)	loss 3.0196 (3.8061)	grad_norm 0.9833 (1.1764)	
[2022-01-19 20:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][830/1251]	eta 0:15:33 lr 0.000867	time 1.9504 (2.2182)	loss 4.4660 (3.8106)	grad_norm 1.2209 (1.1759)	
[2022-01-19 20:01:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][840/1251]	eta 0:15:12 lr 0.000867	time 2.1323 (2.2193)	loss 4.1236 (3.8103)	grad_norm 1.0856 (1.1761)	
[2022-01-19 20:02:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][850/1251]	eta 0:14:49 lr 0.000867	time 1.9493 (2.2187)	loss 3.7882 (3.8101)	grad_norm 0.9892 (1.1755)	
[2022-01-19 20:02:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][860/1251]	eta 0:14:26 lr 0.000867	time 1.8499 (2.2160)	loss 3.3605 (3.8096)	grad_norm 1.0696 (1.1750)	
[2022-01-19 20:02:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][870/1251]	eta 0:14:03 lr 0.000867	time 1.5855 (2.2151)	loss 2.8317 (3.8079)	grad_norm 1.2214 (1.1745)	
[2022-01-19 20:03:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][880/1251]	eta 0:13:41 lr 0.000867	time 1.7068 (2.2136)	loss 3.9700 (3.8086)	grad_norm 1.2376 (1.1753)	
[2022-01-19 20:03:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][890/1251]	eta 0:13:19 lr 0.000867	time 2.1621 (2.2140)	loss 3.6627 (3.8069)	grad_norm 1.2377 (1.1753)	
[2022-01-19 20:04:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][900/1251]	eta 0:12:57 lr 0.000867	time 2.8254 (2.2157)	loss 2.8104 (3.8073)	grad_norm 1.1363 (1.1756)	
[2022-01-19 20:04:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][910/1251]	eta 0:12:35 lr 0.000867	time 2.8414 (2.2165)	loss 3.7138 (3.8065)	grad_norm 1.0030 (1.1746)	
[2022-01-19 20:04:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][920/1251]	eta 0:12:13 lr 0.000867	time 2.7612 (2.2163)	loss 2.9303 (3.8051)	grad_norm 1.0862 (1.1742)	
[2022-01-19 20:05:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][930/1251]	eta 0:11:51 lr 0.000867	time 1.5896 (2.2156)	loss 4.1356 (3.8062)	grad_norm 1.1506 (1.1739)	
[2022-01-19 20:05:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][940/1251]	eta 0:11:29 lr 0.000867	time 1.8312 (2.2158)	loss 4.0850 (3.8059)	grad_norm 1.1970 (1.1738)	
[2022-01-19 20:05:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][950/1251]	eta 0:11:06 lr 0.000867	time 1.8286 (2.2139)	loss 2.7811 (3.8085)	grad_norm 1.1353 (1.1742)	
[2022-01-19 20:06:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][960/1251]	eta 0:10:44 lr 0.000867	time 3.6203 (2.2147)	loss 3.7338 (3.8096)	grad_norm 1.2739 (1.1745)	
[2022-01-19 20:06:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][970/1251]	eta 0:10:21 lr 0.000867	time 2.0075 (2.2128)	loss 4.2322 (3.8085)	grad_norm 1.1601 (1.1749)	
[2022-01-19 20:06:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][980/1251]	eta 0:09:59 lr 0.000867	time 2.1185 (2.2106)	loss 3.7692 (3.8105)	grad_norm 1.0765 (1.1744)	
[2022-01-19 20:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][990/1251]	eta 0:09:36 lr 0.000867	time 2.4671 (2.2101)	loss 3.9322 (3.8121)	grad_norm 1.1290 (1.1735)	
[2022-01-19 20:07:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1000/1251]	eta 0:09:14 lr 0.000867	time 2.3897 (2.2097)	loss 3.8770 (3.8124)	grad_norm 1.0787 (1.1735)	
[2022-01-19 20:08:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1010/1251]	eta 0:08:52 lr 0.000867	time 1.8830 (2.2096)	loss 3.9509 (3.8133)	grad_norm 1.0374 (1.1729)	
[2022-01-19 20:08:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1020/1251]	eta 0:08:30 lr 0.000866	time 2.3067 (2.2093)	loss 3.1622 (3.8129)	grad_norm 1.1295 (1.1732)	
[2022-01-19 20:08:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1030/1251]	eta 0:08:08 lr 0.000866	time 3.0308 (2.2109)	loss 3.6015 (3.8109)	grad_norm 1.1290 (1.1736)	
[2022-01-19 20:09:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1040/1251]	eta 0:07:46 lr 0.000866	time 2.4496 (2.2115)	loss 3.0113 (3.8105)	grad_norm 1.1771 (1.1734)	
[2022-01-19 20:09:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1050/1251]	eta 0:07:24 lr 0.000866	time 2.2474 (2.2116)	loss 4.2337 (3.8090)	grad_norm 1.1017 (1.1724)	
[2022-01-19 20:09:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1060/1251]	eta 0:07:02 lr 0.000866	time 1.9240 (2.2118)	loss 3.4260 (3.8106)	grad_norm 1.3179 (1.1727)	
[2022-01-19 20:10:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1070/1251]	eta 0:06:40 lr 0.000866	time 1.9671 (2.2117)	loss 4.2205 (3.8101)	grad_norm 1.1437 (1.1725)	
[2022-01-19 20:10:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1080/1251]	eta 0:06:18 lr 0.000866	time 1.8152 (2.2109)	loss 3.1473 (3.8108)	grad_norm 1.3166 (1.1727)	
[2022-01-19 20:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1090/1251]	eta 0:05:55 lr 0.000866	time 1.8809 (2.2099)	loss 4.0565 (3.8141)	grad_norm 1.2411 (1.1726)	
[2022-01-19 20:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1100/1251]	eta 0:05:33 lr 0.000866	time 1.6303 (2.2092)	loss 3.9939 (3.8133)	grad_norm 1.1339 (1.1730)	
[2022-01-19 20:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1110/1251]	eta 0:05:11 lr 0.000866	time 1.8308 (2.2096)	loss 3.8222 (3.8097)	grad_norm 1.1548 (1.1728)	
[2022-01-19 20:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1120/1251]	eta 0:04:49 lr 0.000866	time 2.3925 (2.2105)	loss 4.4577 (3.8104)	grad_norm 1.4854 (1.1736)	
[2022-01-19 20:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1130/1251]	eta 0:04:27 lr 0.000866	time 1.7650 (2.2103)	loss 4.7231 (3.8123)	grad_norm 1.1000 (1.1735)	
[2022-01-19 20:12:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1140/1251]	eta 0:04:05 lr 0.000866	time 1.5322 (2.2095)	loss 3.3234 (3.8120)	grad_norm 1.2637 (1.1736)	
[2022-01-19 20:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1150/1251]	eta 0:03:43 lr 0.000866	time 1.8247 (2.2082)	loss 4.2170 (3.8137)	grad_norm 1.0966 (1.1734)	
[2022-01-19 20:13:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1160/1251]	eta 0:03:20 lr 0.000866	time 2.4104 (2.2083)	loss 3.0596 (3.8136)	grad_norm 0.9838 (1.1738)	
[2022-01-19 20:13:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1170/1251]	eta 0:02:58 lr 0.000866	time 1.8204 (2.2082)	loss 3.6817 (3.8122)	grad_norm 1.2538 (1.1743)	
[2022-01-19 20:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1180/1251]	eta 0:02:36 lr 0.000866	time 1.8362 (2.2085)	loss 3.7267 (3.8107)	grad_norm 1.1768 (1.1748)	
[2022-01-19 20:14:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1190/1251]	eta 0:02:14 lr 0.000866	time 2.2855 (2.2080)	loss 3.0385 (3.8079)	grad_norm 1.1421 (1.1746)	
[2022-01-19 20:15:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1200/1251]	eta 0:01:52 lr 0.000866	time 3.0515 (2.2068)	loss 4.1066 (3.8086)	grad_norm 1.2082 (1.1753)	
[2022-01-19 20:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1210/1251]	eta 0:01:30 lr 0.000866	time 1.6069 (2.2051)	loss 4.1130 (3.8079)	grad_norm 1.1006 (1.1751)	
[2022-01-19 20:15:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1220/1251]	eta 0:01:08 lr 0.000866	time 2.7740 (2.2053)	loss 4.0406 (3.8067)	grad_norm 1.3114 (1.1750)	
[2022-01-19 20:16:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1230/1251]	eta 0:00:46 lr 0.000866	time 2.2493 (2.2048)	loss 4.3000 (3.8063)	grad_norm 1.2062 (1.1753)	
[2022-01-19 20:16:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1240/1251]	eta 0:00:24 lr 0.000866	time 2.1610 (2.2040)	loss 3.9307 (3.8057)	grad_norm 1.1547 (1.1753)	
[2022-01-19 20:16:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [71/300][1250/1251]	eta 0:00:02 lr 0.000866	time 1.1682 (2.1983)	loss 2.4055 (3.8055)	grad_norm 1.0829 (1.1751)	
[2022-01-19 20:16:40 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 71 training takes 0:45:50
[2022-01-19 20:16:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.043 (19.043)	Loss 1.1913 (1.1913)	Acc@1 72.363 (72.363)	Acc@5 91.504 (91.504)	
[2022-01-19 20:17:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.647 (3.299)	Loss 1.2302 (1.1990)	Acc@1 72.168 (72.257)	Acc@5 92.188 (91.486)	
[2022-01-19 20:17:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.614 (2.552)	Loss 1.1183 (1.1874)	Acc@1 74.023 (72.307)	Acc@5 91.211 (91.443)	
[2022-01-19 20:17:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.569 (2.256)	Loss 1.2852 (1.1954)	Acc@1 69.629 (72.118)	Acc@5 89.746 (91.287)	
[2022-01-19 20:18:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.083 (2.145)	Loss 1.1356 (1.1993)	Acc@1 72.656 (71.913)	Acc@5 91.602 (91.278)	
[2022-01-19 20:18:16 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.034 Acc@5 91.282
[2022-01-19 20:18:16 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.0%
[2022-01-19 20:18:16 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.03%
[2022-01-19 20:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][0/1251]	eta 7:26:38 lr 0.000866	time 21.4214 (21.4214)	loss 4.2115 (4.2115)	grad_norm 1.0996 (1.0996)	
[2022-01-19 20:19:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][10/1251]	eta 1:25:00 lr 0.000866	time 2.5483 (4.1103)	loss 4.0010 (3.9890)	grad_norm 0.9866 (1.1075)	
[2022-01-19 20:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][20/1251]	eta 1:04:42 lr 0.000866	time 1.5253 (3.1543)	loss 4.5295 (3.8989)	grad_norm 1.0876 (1.1390)	
[2022-01-19 20:19:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][30/1251]	eta 0:58:17 lr 0.000866	time 1.5628 (2.8645)	loss 4.0125 (3.8639)	grad_norm 1.2708 (1.1399)	
[2022-01-19 20:20:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][40/1251]	eta 0:54:33 lr 0.000866	time 4.6078 (2.7032)	loss 3.8409 (3.9207)	grad_norm 1.1280 (1.1585)	
[2022-01-19 20:20:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][50/1251]	eta 0:52:46 lr 0.000866	time 2.8290 (2.6367)	loss 3.1700 (3.9173)	grad_norm 1.2767 (1.1686)	
[2022-01-19 20:20:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][60/1251]	eta 0:51:16 lr 0.000866	time 2.1864 (2.5829)	loss 4.6406 (3.9240)	grad_norm 1.2779 (1.1931)	
[2022-01-19 20:21:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][70/1251]	eta 0:49:43 lr 0.000866	time 1.8715 (2.5260)	loss 3.9485 (3.9121)	grad_norm 1.1656 (1.2148)	
[2022-01-19 20:21:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][80/1251]	eta 0:48:36 lr 0.000866	time 3.5816 (2.4905)	loss 3.9799 (3.8630)	grad_norm 1.1510 (1.2028)	
[2022-01-19 20:21:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][90/1251]	eta 0:47:27 lr 0.000866	time 2.6300 (2.4528)	loss 3.3785 (3.8087)	grad_norm 1.1029 (1.2022)	
[2022-01-19 20:22:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][100/1251]	eta 0:46:11 lr 0.000866	time 2.0355 (2.4076)	loss 2.8198 (3.8079)	grad_norm 1.5126 (1.2059)	
[2022-01-19 20:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][110/1251]	eta 0:45:04 lr 0.000866	time 1.8844 (2.3700)	loss 4.0579 (3.8340)	grad_norm 1.2101 (1.2068)	
[2022-01-19 20:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][120/1251]	eta 0:44:18 lr 0.000865	time 2.4976 (2.3507)	loss 4.2026 (3.8375)	grad_norm 1.5918 (1.2083)	
[2022-01-19 20:23:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][130/1251]	eta 0:43:47 lr 0.000865	time 3.1185 (2.3437)	loss 4.2479 (3.8263)	grad_norm 1.0542 (1.2025)	
[2022-01-19 20:23:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][140/1251]	eta 0:43:11 lr 0.000865	time 1.8574 (2.3323)	loss 3.6408 (3.8251)	grad_norm 1.0367 (1.1958)	
[2022-01-19 20:24:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][150/1251]	eta 0:42:47 lr 0.000865	time 2.3984 (2.3323)	loss 3.2623 (3.8048)	grad_norm 1.0406 (1.1920)	
[2022-01-19 20:24:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][160/1251]	eta 0:42:22 lr 0.000865	time 2.2985 (2.3301)	loss 4.2439 (3.8096)	grad_norm 0.9680 (1.1850)	
[2022-01-19 20:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][170/1251]	eta 0:42:05 lr 0.000865	time 3.7654 (2.3365)	loss 3.8557 (3.8026)	grad_norm 1.2768 (1.1796)	
[2022-01-19 20:25:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][180/1251]	eta 0:41:30 lr 0.000865	time 1.9461 (2.3256)	loss 3.6561 (3.8199)	grad_norm 1.1930 (1.1762)	
[2022-01-19 20:25:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][190/1251]	eta 0:40:49 lr 0.000865	time 1.7563 (2.3089)	loss 4.1938 (3.8254)	grad_norm 1.2035 (1.1765)	
[2022-01-19 20:25:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][200/1251]	eta 0:40:11 lr 0.000865	time 1.9595 (2.2947)	loss 4.7561 (3.8310)	grad_norm 1.1025 (1.1735)	
[2022-01-19 20:26:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][210/1251]	eta 0:39:42 lr 0.000865	time 2.3466 (2.2886)	loss 3.8897 (3.8337)	grad_norm 1.1564 (1.1710)	
[2022-01-19 20:26:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][220/1251]	eta 0:39:19 lr 0.000865	time 1.7024 (2.2887)	loss 3.0628 (3.8259)	grad_norm 1.3100 (1.1726)	
[2022-01-19 20:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][230/1251]	eta 0:38:48 lr 0.000865	time 1.5312 (2.2806)	loss 3.8500 (3.8165)	grad_norm 1.3940 (1.1734)	
[2022-01-19 20:27:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][240/1251]	eta 0:38:18 lr 0.000865	time 1.8720 (2.2734)	loss 2.9674 (3.8092)	grad_norm 1.2004 (1.1800)	
[2022-01-19 20:27:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][250/1251]	eta 0:37:54 lr 0.000865	time 1.8969 (2.2718)	loss 4.4582 (3.8079)	grad_norm 1.1520 (1.1792)	
[2022-01-19 20:28:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][260/1251]	eta 0:37:31 lr 0.000865	time 2.0166 (2.2721)	loss 3.8736 (3.8071)	grad_norm 1.1069 (1.1807)	
[2022-01-19 20:28:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][270/1251]	eta 0:37:06 lr 0.000865	time 2.7394 (2.2696)	loss 4.2270 (3.7974)	grad_norm 1.0374 (1.1802)	
[2022-01-19 20:28:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][280/1251]	eta 0:36:38 lr 0.000865	time 1.8128 (2.2640)	loss 3.3634 (3.8033)	grad_norm 1.1178 (1.1788)	
[2022-01-19 20:29:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][290/1251]	eta 0:36:11 lr 0.000865	time 2.1881 (2.2600)	loss 3.7746 (3.7956)	grad_norm 1.0135 (1.1826)	
[2022-01-19 20:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][300/1251]	eta 0:35:46 lr 0.000865	time 1.9443 (2.2576)	loss 4.3446 (3.8044)	grad_norm 1.2142 (1.1826)	
[2022-01-19 20:29:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][310/1251]	eta 0:35:26 lr 0.000865	time 3.1003 (2.2601)	loss 3.5826 (3.8030)	grad_norm 1.2870 (1.1809)	
[2022-01-19 20:30:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][320/1251]	eta 0:34:59 lr 0.000865	time 1.7838 (2.2548)	loss 3.9440 (3.8018)	grad_norm 1.0808 (1.1792)	
[2022-01-19 20:30:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][330/1251]	eta 0:34:36 lr 0.000865	time 1.6598 (2.2541)	loss 4.1230 (3.8009)	grad_norm 1.1633 (1.1761)	
[2022-01-19 20:31:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][340/1251]	eta 0:34:11 lr 0.000865	time 1.8491 (2.2520)	loss 4.1224 (3.8116)	grad_norm 1.0244 (1.1747)	
[2022-01-19 20:31:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][350/1251]	eta 0:33:47 lr 0.000865	time 2.5892 (2.2508)	loss 4.1088 (3.8141)	grad_norm 1.5631 (1.1744)	
[2022-01-19 20:31:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][360/1251]	eta 0:33:23 lr 0.000865	time 1.8112 (2.2483)	loss 4.4083 (3.8165)	grad_norm 1.3554 (1.1734)	
[2022-01-19 20:32:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][370/1251]	eta 0:33:01 lr 0.000865	time 1.8800 (2.2493)	loss 4.3158 (3.8215)	grad_norm 1.1270 (1.1743)	
[2022-01-19 20:32:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][380/1251]	eta 0:32:36 lr 0.000865	time 2.0458 (2.2468)	loss 3.5265 (3.8242)	grad_norm 0.9651 (1.1727)	
[2022-01-19 20:32:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][390/1251]	eta 0:32:13 lr 0.000865	time 3.0736 (2.2459)	loss 4.2082 (3.8145)	grad_norm 1.2729 (1.1750)	
[2022-01-19 20:33:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][400/1251]	eta 0:31:50 lr 0.000865	time 2.4574 (2.2447)	loss 4.5193 (3.8166)	grad_norm 0.9634 (1.1749)	
[2022-01-19 20:33:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][410/1251]	eta 0:31:25 lr 0.000865	time 2.4661 (2.2425)	loss 2.7052 (3.8200)	grad_norm 1.1766 (1.1741)	
[2022-01-19 20:33:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][420/1251]	eta 0:31:00 lr 0.000865	time 1.9104 (2.2392)	loss 3.9412 (3.8220)	grad_norm 1.0317 (1.1729)	
[2022-01-19 20:34:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][430/1251]	eta 0:30:38 lr 0.000865	time 3.4971 (2.2396)	loss 4.0682 (3.8226)	grad_norm 1.0469 (1.1720)	
[2022-01-19 20:34:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][440/1251]	eta 0:30:14 lr 0.000865	time 1.9193 (2.2374)	loss 4.2219 (3.8216)	grad_norm 1.4724 (1.1739)	
[2022-01-19 20:35:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][450/1251]	eta 0:29:51 lr 0.000865	time 1.8906 (2.2366)	loss 2.7544 (3.8153)	grad_norm 1.2908 (1.1738)	
[2022-01-19 20:35:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][460/1251]	eta 0:29:24 lr 0.000865	time 1.8960 (2.2312)	loss 3.7074 (3.8235)	grad_norm 1.1609 (1.1739)	
[2022-01-19 20:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][470/1251]	eta 0:29:05 lr 0.000865	time 2.7358 (2.2343)	loss 4.4297 (3.8255)	grad_norm 1.1269 (1.1740)	
[2022-01-19 20:36:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][480/1251]	eta 0:28:39 lr 0.000864	time 1.5643 (2.2299)	loss 3.9772 (3.8297)	grad_norm 1.1790 (1.1724)	
[2022-01-19 20:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][490/1251]	eta 0:28:14 lr 0.000864	time 1.9585 (2.2272)	loss 2.6817 (3.8285)	grad_norm 1.1399 (1.1730)	
[2022-01-19 20:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][500/1251]	eta 0:27:52 lr 0.000864	time 2.2119 (2.2265)	loss 3.1991 (3.8237)	grad_norm 1.2036 (1.1753)	
[2022-01-19 20:37:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][510/1251]	eta 0:27:31 lr 0.000864	time 3.3778 (2.2292)	loss 4.1783 (3.8198)	grad_norm 1.0950 (1.1761)	
[2022-01-19 20:37:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][520/1251]	eta 0:27:08 lr 0.000864	time 2.0415 (2.2282)	loss 3.9201 (3.8185)	grad_norm 1.2916 (1.1767)	
[2022-01-19 20:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][530/1251]	eta 0:26:45 lr 0.000864	time 1.6767 (2.2273)	loss 4.0781 (3.8186)	grad_norm 1.2338 (1.1784)	
[2022-01-19 20:38:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][540/1251]	eta 0:26:22 lr 0.000864	time 1.9287 (2.2262)	loss 4.0940 (3.8175)	grad_norm 1.2151 (1.1811)	
[2022-01-19 20:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][550/1251]	eta 0:25:58 lr 0.000864	time 2.6662 (2.2233)	loss 3.0159 (3.8139)	grad_norm 0.9479 (1.1808)	
[2022-01-19 20:39:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][560/1251]	eta 0:25:35 lr 0.000864	time 2.2979 (2.2217)	loss 4.0635 (3.8167)	grad_norm 1.0696 (1.1808)	
[2022-01-19 20:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][570/1251]	eta 0:25:12 lr 0.000864	time 1.8616 (2.2209)	loss 3.3534 (3.8112)	grad_norm 1.2940 (1.1825)	
[2022-01-19 20:39:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][580/1251]	eta 0:24:50 lr 0.000864	time 2.1475 (2.2215)	loss 4.0303 (3.8115)	grad_norm 1.1411 (1.1816)	
[2022-01-19 20:40:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][590/1251]	eta 0:24:30 lr 0.000864	time 3.6276 (2.2250)	loss 3.0772 (3.8082)	grad_norm 1.1155 (1.1824)	
[2022-01-19 20:40:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][600/1251]	eta 0:24:06 lr 0.000864	time 2.0430 (2.2219)	loss 3.9290 (3.8009)	grad_norm 1.0209 (1.1807)	
[2022-01-19 20:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][610/1251]	eta 0:23:40 lr 0.000864	time 2.2716 (2.2162)	loss 4.1283 (3.8029)	grad_norm 1.2013 (1.1813)	
[2022-01-19 20:41:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][620/1251]	eta 0:23:17 lr 0.000864	time 2.0319 (2.2152)	loss 4.0492 (3.8029)	grad_norm 1.1135 (1.1813)	
[2022-01-19 20:41:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][630/1251]	eta 0:22:54 lr 0.000864	time 2.1805 (2.2130)	loss 2.6918 (3.8066)	grad_norm 1.3555 (1.1800)	
[2022-01-19 20:41:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][640/1251]	eta 0:22:33 lr 0.000864	time 2.5520 (2.2147)	loss 4.4291 (3.8108)	grad_norm 1.0172 (1.1786)	
[2022-01-19 20:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][650/1251]	eta 0:22:10 lr 0.000864	time 1.8147 (2.2141)	loss 4.2942 (3.8142)	grad_norm 0.9754 (1.1778)	
[2022-01-19 20:42:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][660/1251]	eta 0:21:48 lr 0.000864	time 2.8686 (2.2146)	loss 2.9140 (3.8125)	grad_norm 1.1801 (1.1771)	
[2022-01-19 20:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][670/1251]	eta 0:21:25 lr 0.000864	time 2.0229 (2.2133)	loss 4.5910 (3.8108)	grad_norm 1.0932 (1.1765)	
[2022-01-19 20:43:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][680/1251]	eta 0:21:04 lr 0.000864	time 2.4620 (2.2144)	loss 3.9094 (3.8085)	grad_norm 1.2570 (1.1762)	
[2022-01-19 20:43:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][690/1251]	eta 0:20:42 lr 0.000864	time 2.1407 (2.2145)	loss 4.6035 (3.8094)	grad_norm 1.4487 (1.1770)	
[2022-01-19 20:44:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][700/1251]	eta 0:20:20 lr 0.000864	time 1.6621 (2.2146)	loss 4.3162 (3.8082)	grad_norm 1.2772 (1.1768)	
[2022-01-19 20:44:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][710/1251]	eta 0:19:57 lr 0.000864	time 1.7882 (2.2129)	loss 4.0810 (3.8106)	grad_norm 1.2466 (1.1786)	
[2022-01-19 20:44:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][720/1251]	eta 0:19:34 lr 0.000864	time 2.6085 (2.2116)	loss 3.9220 (3.8143)	grad_norm 0.9681 (1.1786)	
[2022-01-19 20:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][730/1251]	eta 0:19:13 lr 0.000864	time 3.2421 (2.2139)	loss 4.3262 (3.8116)	grad_norm 1.3488 (1.1784)	
[2022-01-19 20:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][740/1251]	eta 0:18:51 lr 0.000864	time 2.1836 (2.2141)	loss 2.8005 (3.8113)	grad_norm 1.0137 (1.1782)	
[2022-01-19 20:45:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][750/1251]	eta 0:18:27 lr 0.000864	time 2.1705 (2.2115)	loss 4.1629 (3.8111)	grad_norm 1.0308 (1.1776)	
[2022-01-19 20:46:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][760/1251]	eta 0:18:04 lr 0.000864	time 1.7702 (2.2083)	loss 4.3881 (3.8129)	grad_norm 1.2546 (1.1790)	
[2022-01-19 20:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][770/1251]	eta 0:17:42 lr 0.000864	time 1.9447 (2.2080)	loss 3.1903 (3.8120)	grad_norm 1.0723 (1.1787)	
[2022-01-19 20:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][780/1251]	eta 0:17:20 lr 0.000864	time 1.8897 (2.2084)	loss 2.9748 (3.8130)	grad_norm 1.1528 (1.1788)	
[2022-01-19 20:47:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][790/1251]	eta 0:16:58 lr 0.000864	time 2.7830 (2.2102)	loss 4.0284 (3.8165)	grad_norm 1.0760 (1.1786)	
[2022-01-19 20:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][800/1251]	eta 0:16:36 lr 0.000864	time 1.8250 (2.2101)	loss 4.1873 (3.8182)	grad_norm 1.1922 (1.1786)	
[2022-01-19 20:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][810/1251]	eta 0:16:13 lr 0.000864	time 1.5896 (2.2082)	loss 4.1010 (3.8211)	grad_norm 1.2065 (1.1805)	
[2022-01-19 20:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][820/1251]	eta 0:15:51 lr 0.000864	time 2.1819 (2.2069)	loss 2.8510 (3.8221)	grad_norm 1.1673 (1.1807)	
[2022-01-19 20:48:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][830/1251]	eta 0:15:28 lr 0.000863	time 1.9123 (2.2053)	loss 4.1925 (3.8221)	grad_norm 1.0679 (1.1796)	
[2022-01-19 20:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][840/1251]	eta 0:15:05 lr 0.000863	time 2.4084 (2.2041)	loss 4.1794 (3.8186)	grad_norm 1.0513 (1.1799)	
[2022-01-19 20:49:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][850/1251]	eta 0:14:43 lr 0.000863	time 1.9293 (2.2026)	loss 2.9513 (3.8199)	grad_norm 1.1930 (1.1802)	
[2022-01-19 20:49:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][860/1251]	eta 0:14:20 lr 0.000863	time 1.7149 (2.2011)	loss 4.6131 (3.8220)	grad_norm 1.1462 (1.1801)	
[2022-01-19 20:50:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][870/1251]	eta 0:13:59 lr 0.000863	time 2.1068 (2.2022)	loss 4.1658 (3.8212)	grad_norm 1.2272 (1.1795)	
[2022-01-19 20:50:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][880/1251]	eta 0:13:37 lr 0.000863	time 1.9318 (2.2033)	loss 3.9982 (3.8210)	grad_norm 1.0811 (1.1799)	
[2022-01-19 20:51:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][890/1251]	eta 0:13:15 lr 0.000863	time 2.1226 (2.2046)	loss 3.3112 (3.8216)	grad_norm 1.1882 (1.1797)	
[2022-01-19 20:51:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][900/1251]	eta 0:12:54 lr 0.000863	time 2.2140 (2.2057)	loss 4.0755 (3.8210)	grad_norm 1.3135 (1.1795)	
[2022-01-19 20:51:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][910/1251]	eta 0:12:32 lr 0.000863	time 2.1963 (2.2058)	loss 4.6214 (3.8198)	grad_norm 1.1399 (1.1787)	
[2022-01-19 20:52:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][920/1251]	eta 0:12:09 lr 0.000863	time 1.5736 (2.2051)	loss 4.1897 (3.8202)	grad_norm 1.4682 (1.1786)	
[2022-01-19 20:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][930/1251]	eta 0:11:47 lr 0.000863	time 2.1988 (2.2044)	loss 3.0718 (3.8182)	grad_norm 1.2588 (1.1782)	
[2022-01-19 20:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][940/1251]	eta 0:11:25 lr 0.000863	time 2.0069 (2.2032)	loss 3.3767 (3.8168)	grad_norm 1.3102 (1.1778)	
[2022-01-19 20:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][950/1251]	eta 0:11:03 lr 0.000863	time 2.2489 (2.2034)	loss 3.1317 (3.8130)	grad_norm 1.1018 (1.1781)	
[2022-01-19 20:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][960/1251]	eta 0:10:40 lr 0.000863	time 1.6780 (2.2026)	loss 3.1073 (3.8132)	grad_norm 1.2774 (1.1785)	
[2022-01-19 20:53:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][970/1251]	eta 0:10:18 lr 0.000863	time 1.8061 (2.2027)	loss 4.2987 (3.8129)	grad_norm 1.6981 (1.1784)	
[2022-01-19 20:54:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][980/1251]	eta 0:09:56 lr 0.000863	time 1.8833 (2.2023)	loss 4.3039 (3.8150)	grad_norm 1.4816 (1.1801)	
[2022-01-19 20:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][990/1251]	eta 0:09:34 lr 0.000863	time 2.1879 (2.2029)	loss 4.5892 (3.8151)	grad_norm 1.5731 (1.1812)	
[2022-01-19 20:54:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1000/1251]	eta 0:09:12 lr 0.000863	time 2.1192 (2.2015)	loss 3.7425 (3.8160)	grad_norm 1.2741 (1.1816)	
[2022-01-19 20:55:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1010/1251]	eta 0:08:50 lr 0.000863	time 2.1986 (2.2015)	loss 4.0479 (3.8165)	grad_norm 1.1486 (1.1808)	
[2022-01-19 20:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1020/1251]	eta 0:08:28 lr 0.000863	time 1.5630 (2.1997)	loss 4.1960 (3.8185)	grad_norm 1.5052 (1.1809)	
[2022-01-19 20:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1030/1251]	eta 0:08:05 lr 0.000863	time 1.8191 (2.1987)	loss 3.1500 (3.8150)	grad_norm 1.2139 (1.1813)	
[2022-01-19 20:56:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1040/1251]	eta 0:07:44 lr 0.000863	time 2.9452 (2.1997)	loss 4.7619 (3.8174)	grad_norm 1.4947 (1.1812)	
[2022-01-19 20:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1050/1251]	eta 0:07:22 lr 0.000863	time 2.2425 (2.2024)	loss 2.8678 (3.8151)	grad_norm 1.1568 (1.1801)	
[2022-01-19 20:57:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1060/1251]	eta 0:07:00 lr 0.000863	time 2.0607 (2.2017)	loss 4.2688 (3.8166)	grad_norm 1.3042 (1.1796)	
[2022-01-19 20:57:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1070/1251]	eta 0:06:38 lr 0.000863	time 1.6048 (2.2002)	loss 4.3262 (3.8194)	grad_norm 1.2995 (1.1795)	
[2022-01-19 20:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1080/1251]	eta 0:06:16 lr 0.000863	time 2.6693 (2.2004)	loss 3.9831 (3.8215)	grad_norm 1.1794 (1.1792)	
[2022-01-19 20:58:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1090/1251]	eta 0:05:54 lr 0.000863	time 2.6791 (2.1997)	loss 3.9104 (3.8219)	grad_norm 1.3411 (1.1793)	
[2022-01-19 20:58:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1100/1251]	eta 0:05:32 lr 0.000863	time 1.8760 (2.1991)	loss 4.5968 (3.8236)	grad_norm 1.3367 (1.1795)	
[2022-01-19 20:58:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1110/1251]	eta 0:05:10 lr 0.000863	time 2.0105 (2.1993)	loss 3.1272 (3.8233)	grad_norm 1.1556 (1.1791)	
[2022-01-19 20:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1120/1251]	eta 0:04:48 lr 0.000863	time 2.1878 (2.2012)	loss 4.2451 (3.8196)	grad_norm 1.1082 (1.1787)	
[2022-01-19 20:59:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1130/1251]	eta 0:04:26 lr 0.000863	time 2.6271 (2.2040)	loss 4.3141 (3.8222)	grad_norm 1.0417 (1.1783)	
[2022-01-19 21:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1140/1251]	eta 0:04:04 lr 0.000863	time 2.0452 (2.2038)	loss 2.6907 (3.8207)	grad_norm 1.1676 (1.1777)	
[2022-01-19 21:00:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1150/1251]	eta 0:03:42 lr 0.000863	time 2.0351 (2.2029)	loss 2.7521 (3.8174)	grad_norm 1.2344 (1.1774)	
[2022-01-19 21:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1160/1251]	eta 0:03:20 lr 0.000863	time 1.6273 (2.2006)	loss 3.7390 (3.8171)	grad_norm 1.1222 (1.1772)	
[2022-01-19 21:01:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1170/1251]	eta 0:02:58 lr 0.000863	time 1.6079 (2.2000)	loss 3.8205 (3.8162)	grad_norm 1.2175 (1.1772)	
[2022-01-19 21:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1180/1251]	eta 0:02:36 lr 0.000862	time 2.4024 (2.1995)	loss 4.0487 (3.8175)	grad_norm 1.4536 (1.1777)	
[2022-01-19 21:01:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1190/1251]	eta 0:02:14 lr 0.000862	time 2.1303 (2.1991)	loss 4.2759 (3.8189)	grad_norm 1.0884 (1.1782)	
[2022-01-19 21:02:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1200/1251]	eta 0:01:52 lr 0.000862	time 1.8431 (2.1988)	loss 3.0404 (3.8197)	grad_norm 1.0746 (1.1779)	
[2022-01-19 21:02:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1210/1251]	eta 0:01:30 lr 0.000862	time 1.6268 (2.2000)	loss 4.2045 (3.8186)	grad_norm 0.9482 (1.1769)	
[2022-01-19 21:03:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1220/1251]	eta 0:01:08 lr 0.000862	time 2.5507 (2.2003)	loss 3.8887 (3.8186)	grad_norm 1.3093 (1.1764)	
[2022-01-19 21:03:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1230/1251]	eta 0:00:46 lr 0.000862	time 1.9656 (2.1995)	loss 4.0202 (3.8205)	grad_norm 1.3022 (1.1764)	
[2022-01-19 21:03:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1240/1251]	eta 0:00:24 lr 0.000862	time 2.2331 (2.1988)	loss 4.1524 (3.8210)	grad_norm 1.3132 (1.1769)	
[2022-01-19 21:04:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [72/300][1250/1251]	eta 0:00:02 lr 0.000862	time 1.1842 (2.1934)	loss 4.0246 (3.8212)	grad_norm 1.0050 (1.1767)	
[2022-01-19 21:04:00 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 72 training takes 0:45:44
[2022-01-19 21:04:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.322 (18.322)	Loss 1.2328 (1.2328)	Acc@1 71.680 (71.680)	Acc@5 90.527 (90.527)	
[2022-01-19 21:04:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 3.014 (3.533)	Loss 1.1766 (1.2047)	Acc@1 73.047 (72.559)	Acc@5 92.188 (91.362)	
[2022-01-19 21:04:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.955 (2.740)	Loss 1.2063 (1.2033)	Acc@1 72.266 (72.684)	Acc@5 91.504 (91.406)	
[2022-01-19 21:05:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.571 (2.356)	Loss 1.2149 (1.2079)	Acc@1 71.973 (72.483)	Acc@5 90.723 (91.350)	
[2022-01-19 21:05:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.673 (2.169)	Loss 1.2475 (1.2087)	Acc@1 71.191 (72.401)	Acc@5 90.234 (91.318)	
[2022-01-19 21:05:37 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.296 Acc@5 91.338
[2022-01-19 21:05:37 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.3%
[2022-01-19 21:05:37 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.30%
[2022-01-19 21:05:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][0/1251]	eta 7:26:49 lr 0.000862	time 21.4308 (21.4308)	loss 4.2262 (4.2262)	grad_norm 1.2283 (1.2283)	
[2022-01-19 21:06:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][10/1251]	eta 1:25:23 lr 0.000862	time 2.6542 (4.1288)	loss 2.6190 (3.5913)	grad_norm 1.0482 (1.0861)	
[2022-01-19 21:06:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][20/1251]	eta 1:04:56 lr 0.000862	time 1.7586 (3.1656)	loss 3.7886 (3.6702)	grad_norm 1.0094 (1.1086)	
[2022-01-19 21:07:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][30/1251]	eta 0:58:17 lr 0.000862	time 1.9513 (2.8642)	loss 2.9879 (3.5905)	grad_norm 1.0419 (1.1374)	
[2022-01-19 21:07:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][40/1251]	eta 0:55:30 lr 0.000862	time 3.8722 (2.7503)	loss 3.3564 (3.5884)	grad_norm 1.0614 (1.1379)	
[2022-01-19 21:07:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][50/1251]	eta 0:53:37 lr 0.000862	time 3.4014 (2.6789)	loss 3.6452 (3.6275)	grad_norm 1.1109 (1.1497)	
[2022-01-19 21:08:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][60/1251]	eta 0:51:33 lr 0.000862	time 2.2784 (2.5973)	loss 3.9403 (3.6485)	grad_norm 1.2132 (1.1504)	
[2022-01-19 21:08:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][70/1251]	eta 0:49:48 lr 0.000862	time 1.8545 (2.5301)	loss 4.2337 (3.6631)	grad_norm 1.2528 (1.1694)	
[2022-01-19 21:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][80/1251]	eta 0:48:22 lr 0.000862	time 2.9269 (2.4787)	loss 3.1874 (3.6791)	grad_norm 1.1101 (1.1744)	
[2022-01-19 21:09:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][90/1251]	eta 0:47:00 lr 0.000862	time 1.8913 (2.4296)	loss 3.8373 (3.6819)	grad_norm 1.0923 (1.1797)	
[2022-01-19 21:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][100/1251]	eta 0:46:00 lr 0.000862	time 1.8317 (2.3984)	loss 3.4168 (3.6735)	grad_norm 1.1592 (1.1737)	
[2022-01-19 21:10:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][110/1251]	eta 0:45:33 lr 0.000862	time 1.8470 (2.3956)	loss 4.1931 (3.6841)	grad_norm 1.1159 (1.1668)	
[2022-01-19 21:10:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][120/1251]	eta 0:45:06 lr 0.000862	time 2.2020 (2.3929)	loss 4.3541 (3.6964)	grad_norm 1.1667 (1.1624)	
[2022-01-19 21:10:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][130/1251]	eta 0:44:20 lr 0.000862	time 2.2779 (2.3734)	loss 4.5468 (3.7246)	grad_norm 1.2798 (1.1604)	
[2022-01-19 21:11:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][140/1251]	eta 0:43:30 lr 0.000862	time 2.1802 (2.3499)	loss 3.2379 (3.7166)	grad_norm 1.2460 (1.1625)	
[2022-01-19 21:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][150/1251]	eta 0:42:49 lr 0.000862	time 1.8499 (2.3342)	loss 3.9729 (3.7307)	grad_norm 1.0818 (1.1617)	
[2022-01-19 21:11:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][160/1251]	eta 0:42:23 lr 0.000862	time 2.1773 (2.3315)	loss 2.6983 (3.7375)	grad_norm 1.0893 (1.1621)	
[2022-01-19 21:12:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][170/1251]	eta 0:41:47 lr 0.000862	time 2.1126 (2.3201)	loss 4.0589 (3.7329)	grad_norm 1.3012 (1.1672)	
[2022-01-19 21:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][180/1251]	eta 0:41:08 lr 0.000862	time 1.9281 (2.3051)	loss 4.2773 (3.7279)	grad_norm 1.5150 (1.1697)	
[2022-01-19 21:12:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][190/1251]	eta 0:40:31 lr 0.000862	time 1.5964 (2.2917)	loss 4.4285 (3.7186)	grad_norm 1.0022 (1.1731)	
[2022-01-19 21:13:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][200/1251]	eta 0:40:07 lr 0.000862	time 1.7493 (2.2902)	loss 3.3181 (3.7311)	grad_norm 1.1267 (1.1734)	
[2022-01-19 21:13:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][210/1251]	eta 0:39:32 lr 0.000862	time 1.7280 (2.2795)	loss 4.5018 (3.7406)	grad_norm 1.1844 (1.1769)	
[2022-01-19 21:14:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][220/1251]	eta 0:39:06 lr 0.000862	time 1.7613 (2.2760)	loss 3.8738 (3.7540)	grad_norm 1.1919 (1.1737)	
[2022-01-19 21:14:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][230/1251]	eta 0:38:42 lr 0.000862	time 1.4810 (2.2745)	loss 3.2923 (3.7500)	grad_norm 1.0459 (1.1707)	
[2022-01-19 21:14:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][240/1251]	eta 0:38:21 lr 0.000862	time 1.8835 (2.2760)	loss 2.9583 (3.7493)	grad_norm 1.0526 (1.1725)	
[2022-01-19 21:15:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][250/1251]	eta 0:37:58 lr 0.000862	time 1.5204 (2.2759)	loss 4.2046 (3.7640)	grad_norm 0.9955 (1.1672)	
[2022-01-19 21:15:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][260/1251]	eta 0:37:32 lr 0.000862	time 2.3027 (2.2731)	loss 4.1949 (3.7602)	grad_norm 1.1012 (1.1674)	
[2022-01-19 21:15:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][270/1251]	eta 0:37:06 lr 0.000861	time 1.8605 (2.2698)	loss 4.1517 (3.7633)	grad_norm 1.0488 (1.1724)	
[2022-01-19 21:16:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][280/1251]	eta 0:36:32 lr 0.000861	time 1.8823 (2.2584)	loss 3.9542 (3.7659)	grad_norm 1.2404 (1.1724)	
[2022-01-19 21:16:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][290/1251]	eta 0:36:04 lr 0.000861	time 1.8296 (2.2524)	loss 3.5092 (3.7603)	grad_norm 1.3299 (1.1726)	
[2022-01-19 21:16:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][300/1251]	eta 0:35:39 lr 0.000861	time 1.9042 (2.2493)	loss 3.6583 (3.7592)	grad_norm 1.1262 (1.1737)	
[2022-01-19 21:17:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][310/1251]	eta 0:35:15 lr 0.000861	time 2.3903 (2.2484)	loss 3.7855 (3.7659)	grad_norm 1.0092 (1.1719)	
[2022-01-19 21:17:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][320/1251]	eta 0:34:50 lr 0.000861	time 2.2635 (2.2456)	loss 4.2058 (3.7555)	grad_norm 1.1161 (1.1700)	
[2022-01-19 21:18:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][330/1251]	eta 0:34:30 lr 0.000861	time 2.5016 (2.2485)	loss 4.7563 (3.7650)	grad_norm 1.1085 (1.1692)	
[2022-01-19 21:18:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][340/1251]	eta 0:34:08 lr 0.000861	time 1.6394 (2.2489)	loss 4.1052 (3.7689)	grad_norm 1.1619 (1.1689)	
[2022-01-19 21:18:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][350/1251]	eta 0:33:46 lr 0.000861	time 2.5346 (2.2494)	loss 3.9641 (3.7620)	grad_norm 1.1235 (1.1677)	
[2022-01-19 21:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][360/1251]	eta 0:33:19 lr 0.000861	time 2.4420 (2.2436)	loss 4.2472 (3.7629)	grad_norm 1.2613 (1.1696)	
[2022-01-19 21:19:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][370/1251]	eta 0:32:50 lr 0.000861	time 1.8514 (2.2369)	loss 4.0055 (3.7642)	grad_norm 1.1590 (1.1698)	
[2022-01-19 21:19:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][380/1251]	eta 0:32:25 lr 0.000861	time 2.1355 (2.2333)	loss 3.2543 (3.7649)	grad_norm 1.1306 (1.1703)	
[2022-01-19 21:20:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][390/1251]	eta 0:31:59 lr 0.000861	time 2.2511 (2.2297)	loss 3.9697 (3.7670)	grad_norm 1.1770 (1.1722)	
[2022-01-19 21:20:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][400/1251]	eta 0:31:35 lr 0.000861	time 2.5664 (2.2276)	loss 3.4182 (3.7657)	grad_norm 1.0335 (1.1711)	
[2022-01-19 21:20:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][410/1251]	eta 0:31:15 lr 0.000861	time 2.5943 (2.2295)	loss 3.4868 (3.7650)	grad_norm 1.4859 (1.1754)	
[2022-01-19 21:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][420/1251]	eta 0:30:53 lr 0.000861	time 1.5751 (2.2309)	loss 2.6537 (3.7564)	grad_norm 1.1324 (1.1754)	
[2022-01-19 21:21:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][430/1251]	eta 0:30:34 lr 0.000861	time 2.9131 (2.2339)	loss 2.8803 (3.7601)	grad_norm 1.0693 (1.1762)	
[2022-01-19 21:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][440/1251]	eta 0:30:12 lr 0.000861	time 2.9577 (2.2345)	loss 3.3774 (3.7645)	grad_norm 1.4235 (1.1785)	
[2022-01-19 21:22:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][450/1251]	eta 0:29:46 lr 0.000861	time 1.9787 (2.2305)	loss 3.7380 (3.7562)	grad_norm 1.1622 (1.1799)	
[2022-01-19 21:22:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][460/1251]	eta 0:29:20 lr 0.000861	time 1.6644 (2.2251)	loss 4.5766 (3.7594)	grad_norm 1.5197 (1.1830)	
[2022-01-19 21:23:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][470/1251]	eta 0:28:56 lr 0.000861	time 2.1746 (2.2239)	loss 2.8326 (3.7594)	grad_norm 1.0778 (1.1817)	
[2022-01-19 21:23:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][480/1251]	eta 0:28:35 lr 0.000861	time 3.0663 (2.2252)	loss 2.8214 (3.7542)	grad_norm 1.1635 (1.1801)	
[2022-01-19 21:23:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][490/1251]	eta 0:28:12 lr 0.000861	time 1.8801 (2.2239)	loss 3.8903 (3.7571)	grad_norm 1.0536 (1.1797)	
[2022-01-19 21:24:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][500/1251]	eta 0:27:47 lr 0.000861	time 1.6076 (2.2202)	loss 4.2933 (3.7513)	grad_norm 1.0998 (1.1795)	
[2022-01-19 21:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][510/1251]	eta 0:27:24 lr 0.000861	time 2.5055 (2.2187)	loss 4.4241 (3.7546)	grad_norm 1.2534 (1.1791)	
[2022-01-19 21:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][520/1251]	eta 0:27:02 lr 0.000861	time 2.9426 (2.2191)	loss 4.1423 (3.7526)	grad_norm 1.1343 (1.1799)	
[2022-01-19 21:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][530/1251]	eta 0:26:41 lr 0.000861	time 2.3007 (2.2213)	loss 2.7374 (3.7494)	grad_norm 1.1387 (1.1798)	
[2022-01-19 21:25:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][540/1251]	eta 0:26:20 lr 0.000861	time 1.6662 (2.2222)	loss 4.3882 (3.7461)	grad_norm 1.1442 (1.1805)	
[2022-01-19 21:26:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][550/1251]	eta 0:25:56 lr 0.000861	time 1.5713 (2.2200)	loss 2.9952 (3.7468)	grad_norm 1.1723 (1.1802)	
[2022-01-19 21:26:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][560/1251]	eta 0:25:32 lr 0.000861	time 2.4977 (2.2181)	loss 4.1027 (3.7431)	grad_norm 1.1754 (1.1800)	
[2022-01-19 21:26:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][570/1251]	eta 0:25:09 lr 0.000861	time 1.8883 (2.2160)	loss 4.6589 (3.7467)	grad_norm 1.1437 (1.1791)	
[2022-01-19 21:27:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][580/1251]	eta 0:24:45 lr 0.000861	time 2.0931 (2.2145)	loss 4.7049 (3.7520)	grad_norm 1.0975 (1.1783)	
[2022-01-19 21:27:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][590/1251]	eta 0:24:22 lr 0.000861	time 1.8358 (2.2123)	loss 3.2846 (3.7500)	grad_norm 1.3703 (1.1786)	
[2022-01-19 21:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][600/1251]	eta 0:23:58 lr 0.000861	time 1.9652 (2.2091)	loss 3.4647 (3.7502)	grad_norm 1.0437 (1.1792)	
[2022-01-19 21:28:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][610/1251]	eta 0:23:35 lr 0.000861	time 1.7983 (2.2085)	loss 4.2116 (3.7471)	grad_norm 1.2848 (1.1799)	
[2022-01-19 21:28:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][620/1251]	eta 0:23:13 lr 0.000860	time 2.5034 (2.2091)	loss 2.9594 (3.7493)	grad_norm 1.4073 (1.1797)	
[2022-01-19 21:28:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][630/1251]	eta 0:22:51 lr 0.000860	time 1.4647 (2.2080)	loss 4.5180 (3.7492)	grad_norm 1.3957 (1.1810)	
[2022-01-19 21:29:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][640/1251]	eta 0:22:28 lr 0.000860	time 2.5580 (2.2073)	loss 4.4629 (3.7488)	grad_norm 1.2325 (1.1820)	
[2022-01-19 21:29:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][650/1251]	eta 0:22:05 lr 0.000860	time 1.7804 (2.2050)	loss 4.2769 (3.7517)	grad_norm 1.0385 (1.1819)	
[2022-01-19 21:29:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][660/1251]	eta 0:21:43 lr 0.000860	time 2.0630 (2.2048)	loss 4.1485 (3.7547)	grad_norm 1.1558 (1.1810)	
[2022-01-19 21:30:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][670/1251]	eta 0:21:21 lr 0.000860	time 1.6718 (2.2057)	loss 4.0250 (3.7547)	grad_norm 1.0916 (1.1811)	
[2022-01-19 21:30:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][680/1251]	eta 0:21:02 lr 0.000860	time 3.3692 (2.2115)	loss 2.8945 (3.7562)	grad_norm 1.4025 (1.1816)	
[2022-01-19 21:31:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][690/1251]	eta 0:20:43 lr 0.000860	time 2.0074 (2.2167)	loss 4.1802 (3.7588)	grad_norm 1.1167 (1.1803)	
[2022-01-19 21:31:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][700/1251]	eta 0:20:21 lr 0.000860	time 1.8625 (2.2163)	loss 4.3421 (3.7569)	grad_norm 1.2707 (1.1798)	
[2022-01-19 21:31:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][710/1251]	eta 0:19:58 lr 0.000860	time 2.1194 (2.2149)	loss 3.7251 (3.7533)	grad_norm 1.0402 (1.1795)	
[2022-01-19 21:32:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][720/1251]	eta 0:19:34 lr 0.000860	time 2.3288 (2.2115)	loss 3.7904 (3.7533)	grad_norm 1.1444 (1.1793)	
[2022-01-19 21:32:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][730/1251]	eta 0:19:10 lr 0.000860	time 1.5966 (2.2076)	loss 3.8150 (3.7515)	grad_norm 1.0758 (1.1781)	
[2022-01-19 21:32:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][740/1251]	eta 0:18:47 lr 0.000860	time 2.1540 (2.2065)	loss 4.1748 (3.7532)	grad_norm 0.9323 (1.1777)	
[2022-01-19 21:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][750/1251]	eta 0:18:25 lr 0.000860	time 1.6166 (2.2069)	loss 3.0281 (3.7563)	grad_norm 1.2124 (1.1787)	
[2022-01-19 21:33:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][760/1251]	eta 0:18:03 lr 0.000860	time 2.1934 (2.2076)	loss 4.2893 (3.7586)	grad_norm 1.0773 (1.1794)	
[2022-01-19 21:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][770/1251]	eta 0:17:42 lr 0.000860	time 1.8790 (2.2080)	loss 4.0126 (3.7562)	grad_norm 1.3256 (1.1795)	
[2022-01-19 21:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][780/1251]	eta 0:17:20 lr 0.000860	time 2.3371 (2.2086)	loss 4.0637 (3.7559)	grad_norm 1.3213 (1.1795)	
[2022-01-19 21:34:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][790/1251]	eta 0:16:57 lr 0.000860	time 1.5707 (2.2069)	loss 3.7043 (3.7537)	grad_norm 1.1359 (1.1804)	
[2022-01-19 21:35:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][800/1251]	eta 0:16:35 lr 0.000860	time 2.5094 (2.2075)	loss 4.1871 (3.7563)	grad_norm 1.1912 (1.1799)	
[2022-01-19 21:35:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][810/1251]	eta 0:16:13 lr 0.000860	time 2.1771 (2.2077)	loss 4.2728 (3.7555)	grad_norm 1.2836 (1.1799)	
[2022-01-19 21:35:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][820/1251]	eta 0:15:51 lr 0.000860	time 2.5273 (2.2081)	loss 3.9403 (3.7543)	grad_norm 1.1272 (1.1807)	
[2022-01-19 21:36:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][830/1251]	eta 0:15:29 lr 0.000860	time 2.0256 (2.2071)	loss 3.8344 (3.7567)	grad_norm 0.9404 (1.1797)	
[2022-01-19 21:36:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][840/1251]	eta 0:15:06 lr 0.000860	time 2.4580 (2.2064)	loss 3.7924 (3.7587)	grad_norm 1.1792 (1.1793)	
[2022-01-19 21:36:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][850/1251]	eta 0:14:44 lr 0.000860	time 2.0046 (2.2046)	loss 4.0298 (3.7622)	grad_norm 1.1480 (1.1788)	
[2022-01-19 21:37:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][860/1251]	eta 0:14:21 lr 0.000860	time 2.2230 (2.2044)	loss 3.3609 (3.7621)	grad_norm 1.0655 (1.1792)	
[2022-01-19 21:37:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][870/1251]	eta 0:13:59 lr 0.000860	time 1.9466 (2.2045)	loss 4.6502 (3.7613)	grad_norm 1.1136 (1.1789)	
[2022-01-19 21:38:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][880/1251]	eta 0:13:38 lr 0.000860	time 2.3505 (2.2063)	loss 3.6317 (3.7633)	grad_norm 1.0885 (1.1792)	
[2022-01-19 21:38:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][890/1251]	eta 0:13:16 lr 0.000860	time 1.7206 (2.2059)	loss 4.1404 (3.7642)	grad_norm 1.0976 (1.1786)	
[2022-01-19 21:38:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][900/1251]	eta 0:12:54 lr 0.000860	time 2.4476 (2.2068)	loss 4.4644 (3.7675)	grad_norm 1.3496 (1.1794)	
[2022-01-19 21:39:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][910/1251]	eta 0:12:31 lr 0.000860	time 1.6492 (2.2046)	loss 4.0348 (3.7661)	grad_norm 1.0616 (1.1784)	
[2022-01-19 21:39:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][920/1251]	eta 0:12:09 lr 0.000860	time 2.1859 (2.2031)	loss 3.8451 (3.7667)	grad_norm 1.0259 (1.1777)	
[2022-01-19 21:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][930/1251]	eta 0:11:46 lr 0.000860	time 1.6016 (2.2007)	loss 4.3490 (3.7687)	grad_norm 1.0766 (1.1774)	
[2022-01-19 21:40:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][940/1251]	eta 0:11:24 lr 0.000860	time 2.2015 (2.1999)	loss 4.2385 (3.7685)	grad_norm 1.1828 (1.1772)	
[2022-01-19 21:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][950/1251]	eta 0:11:02 lr 0.000860	time 2.2156 (2.2016)	loss 3.4262 (3.7710)	grad_norm 1.1051 (1.1764)	
[2022-01-19 21:40:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][960/1251]	eta 0:10:41 lr 0.000860	time 3.4988 (2.2028)	loss 2.6737 (3.7694)	grad_norm 1.1922 (1.1754)	
[2022-01-19 21:41:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][970/1251]	eta 0:10:19 lr 0.000859	time 1.8462 (2.2044)	loss 3.2308 (3.7663)	grad_norm 0.9938 (1.1750)	
[2022-01-19 21:41:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][980/1251]	eta 0:09:57 lr 0.000859	time 2.2493 (2.2042)	loss 2.9152 (3.7655)	grad_norm 1.2456 (1.1758)	
[2022-01-19 21:42:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][990/1251]	eta 0:09:35 lr 0.000859	time 2.1681 (2.2051)	loss 3.4106 (3.7661)	grad_norm 1.3223 (1.1762)	
[2022-01-19 21:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1000/1251]	eta 0:09:13 lr 0.000859	time 3.1748 (2.2051)	loss 4.1466 (3.7687)	grad_norm 1.1576 (1.1763)	
[2022-01-19 21:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1010/1251]	eta 0:08:50 lr 0.000859	time 1.8255 (2.2027)	loss 3.8217 (3.7674)	grad_norm 1.0865 (1.1765)	
[2022-01-19 21:43:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1020/1251]	eta 0:08:28 lr 0.000859	time 1.9959 (2.1996)	loss 3.5712 (3.7681)	grad_norm 1.1713 (1.1763)	
[2022-01-19 21:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1030/1251]	eta 0:08:05 lr 0.000859	time 1.8975 (2.1985)	loss 4.6921 (3.7691)	grad_norm 1.4269 (1.1764)	
[2022-01-19 21:43:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1040/1251]	eta 0:07:43 lr 0.000859	time 1.9826 (2.1977)	loss 3.0840 (3.7692)	grad_norm 1.2810 (1.1762)	
[2022-01-19 21:44:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1050/1251]	eta 0:07:22 lr 0.000859	time 2.5650 (2.1991)	loss 4.5597 (3.7682)	grad_norm 1.3166 (1.1755)	
[2022-01-19 21:44:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1060/1251]	eta 0:07:00 lr 0.000859	time 2.4911 (2.1992)	loss 3.9890 (3.7689)	grad_norm 1.2522 (1.1757)	
[2022-01-19 21:44:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1070/1251]	eta 0:06:38 lr 0.000859	time 2.5231 (2.1989)	loss 3.3258 (3.7694)	grad_norm 1.1265 (1.1753)	
[2022-01-19 21:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1080/1251]	eta 0:06:16 lr 0.000859	time 2.1414 (2.1996)	loss 3.3908 (3.7694)	grad_norm 1.0801 (1.1749)	
[2022-01-19 21:45:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1090/1251]	eta 0:05:54 lr 0.000859	time 2.2628 (2.2000)	loss 4.1259 (3.7706)	grad_norm 1.2352 (1.1745)	
[2022-01-19 21:45:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1100/1251]	eta 0:05:32 lr 0.000859	time 2.4303 (2.2004)	loss 4.1944 (3.7664)	grad_norm 1.2153 (1.1752)	
[2022-01-19 21:46:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1110/1251]	eta 0:05:10 lr 0.000859	time 2.5915 (2.2013)	loss 4.1218 (3.7658)	grad_norm 1.1707 (1.1765)	
[2022-01-19 21:46:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1120/1251]	eta 0:04:48 lr 0.000859	time 2.7413 (2.2029)	loss 4.3222 (3.7672)	grad_norm 1.1949 (1.1768)	
[2022-01-19 21:47:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1130/1251]	eta 0:04:26 lr 0.000859	time 1.7353 (2.2028)	loss 4.3198 (3.7677)	grad_norm 1.0908 (1.1763)	
[2022-01-19 21:47:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1140/1251]	eta 0:04:04 lr 0.000859	time 1.6752 (2.2003)	loss 2.8600 (3.7695)	grad_norm 1.2985 (1.1759)	
[2022-01-19 21:47:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1150/1251]	eta 0:03:42 lr 0.000859	time 2.0284 (2.1993)	loss 3.4681 (3.7697)	grad_norm 1.2727 (1.1754)	
[2022-01-19 21:48:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1160/1251]	eta 0:03:20 lr 0.000859	time 1.9546 (2.1991)	loss 2.6493 (3.7680)	grad_norm 1.1720 (1.1754)	
[2022-01-19 21:48:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1170/1251]	eta 0:02:58 lr 0.000859	time 1.9754 (2.2004)	loss 3.2712 (3.7679)	grad_norm 1.0316 (1.1754)	
[2022-01-19 21:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1180/1251]	eta 0:02:36 lr 0.000859	time 2.2010 (2.1986)	loss 3.4793 (3.7683)	grad_norm 1.3843 (1.1754)	
[2022-01-19 21:49:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1190/1251]	eta 0:02:14 lr 0.000859	time 1.8274 (2.1970)	loss 2.9352 (3.7682)	grad_norm 1.1437 (1.1751)	
[2022-01-19 21:49:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1200/1251]	eta 0:01:52 lr 0.000859	time 2.2476 (2.1968)	loss 2.9251 (3.7675)	grad_norm 1.0500 (1.1752)	
[2022-01-19 21:49:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1210/1251]	eta 0:01:30 lr 0.000859	time 1.5700 (2.1971)	loss 3.1020 (3.7679)	grad_norm 1.1254 (1.1747)	
[2022-01-19 21:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1220/1251]	eta 0:01:08 lr 0.000859	time 1.8632 (2.1960)	loss 4.8009 (3.7673)	grad_norm 1.0844 (1.1743)	
[2022-01-19 21:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1230/1251]	eta 0:00:46 lr 0.000859	time 2.1730 (2.1965)	loss 3.6277 (3.7676)	grad_norm 1.2440 (1.1746)	
[2022-01-19 21:51:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1240/1251]	eta 0:00:24 lr 0.000859	time 1.9051 (2.1970)	loss 3.6801 (3.7684)	grad_norm 1.2617 (1.1747)	
[2022-01-19 21:51:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [73/300][1250/1251]	eta 0:00:02 lr 0.000859	time 1.1408 (2.1920)	loss 3.7120 (3.7681)	grad_norm 1.1161 (1.1740)	
[2022-01-19 21:51:19 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 73 training takes 0:45:42
[2022-01-19 21:51:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.442 (18.442)	Loss 1.2187 (1.2187)	Acc@1 70.605 (70.605)	Acc@5 91.113 (91.113)	
[2022-01-19 21:51:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.259 (3.532)	Loss 1.2217 (1.1968)	Acc@1 72.070 (72.337)	Acc@5 91.895 (91.735)	
[2022-01-19 21:52:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.915 (2.489)	Loss 1.2880 (1.2162)	Acc@1 71.289 (71.931)	Acc@5 90.039 (91.527)	
[2022-01-19 21:52:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.016 (2.222)	Loss 1.2821 (1.2128)	Acc@1 69.727 (71.966)	Acc@5 90.918 (91.479)	
[2022-01-19 21:52:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.147 (2.135)	Loss 1.2889 (1.2174)	Acc@1 71.387 (71.982)	Acc@5 89.746 (91.328)	
[2022-01-19 21:52:54 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.022 Acc@5 91.300
[2022-01-19 21:52:54 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.0%
[2022-01-19 21:52:54 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.30%
[2022-01-19 21:53:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][0/1251]	eta 7:18:10 lr 0.000859	time 21.0156 (21.0156)	loss 3.6904 (3.6904)	grad_norm 1.5208 (1.5208)	
[2022-01-19 21:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][10/1251]	eta 1:23:53 lr 0.000859	time 2.5749 (4.0558)	loss 3.9285 (3.7807)	grad_norm 1.0184 (1.1312)	
[2022-01-19 21:54:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][20/1251]	eta 1:04:20 lr 0.000859	time 1.4198 (3.1361)	loss 3.2566 (3.5968)	grad_norm 1.1442 (1.1535)	
[2022-01-19 21:54:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][30/1251]	eta 0:57:12 lr 0.000859	time 1.6016 (2.8116)	loss 4.3932 (3.5627)	grad_norm 1.5111 (1.1830)	
[2022-01-19 21:54:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][40/1251]	eta 0:55:19 lr 0.000859	time 3.5058 (2.7410)	loss 4.4347 (3.6201)	grad_norm 1.0162 (1.1857)	
[2022-01-19 21:55:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][50/1251]	eta 0:53:19 lr 0.000859	time 2.7481 (2.6642)	loss 3.0339 (3.6524)	grad_norm 1.2267 (1.1750)	
[2022-01-19 21:55:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][60/1251]	eta 0:51:25 lr 0.000858	time 1.6017 (2.5910)	loss 3.6214 (3.6881)	grad_norm 1.1574 (1.1739)	
[2022-01-19 21:55:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][70/1251]	eta 0:49:52 lr 0.000858	time 1.8494 (2.5343)	loss 3.7972 (3.7189)	grad_norm 1.0360 (1.1805)	
[2022-01-19 21:56:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][80/1251]	eta 0:48:21 lr 0.000858	time 1.9650 (2.4778)	loss 4.1865 (3.7211)	grad_norm 1.2243 (1.1861)	
[2022-01-19 21:56:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][90/1251]	eta 0:46:57 lr 0.000858	time 2.3470 (2.4269)	loss 4.3681 (3.7288)	grad_norm 1.5669 (1.1914)	
[2022-01-19 21:56:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][100/1251]	eta 0:45:43 lr 0.000858	time 1.8734 (2.3837)	loss 3.8263 (3.7609)	grad_norm 1.2708 (1.1927)	
[2022-01-19 21:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][110/1251]	eta 0:44:49 lr 0.000858	time 2.0147 (2.3569)	loss 2.6949 (3.7329)	grad_norm 1.3292 (1.1912)	
[2022-01-19 21:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][120/1251]	eta 0:44:00 lr 0.000858	time 2.0330 (2.3347)	loss 3.4483 (3.7472)	grad_norm 1.3710 (1.1914)	
[2022-01-19 21:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][130/1251]	eta 0:43:34 lr 0.000858	time 3.2745 (2.3327)	loss 3.9933 (3.7607)	grad_norm 1.1215 (1.1903)	
[2022-01-19 21:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][140/1251]	eta 0:43:02 lr 0.000858	time 2.2589 (2.3244)	loss 3.9555 (3.7695)	grad_norm 1.2814 (1.1856)	
[2022-01-19 21:58:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][150/1251]	eta 0:42:37 lr 0.000858	time 2.2301 (2.3231)	loss 4.3152 (3.7796)	grad_norm 0.9490 (1.1808)	
[2022-01-19 21:59:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][160/1251]	eta 0:41:59 lr 0.000858	time 1.9495 (2.3093)	loss 4.1951 (3.7844)	grad_norm 1.0859 (1.1788)	
[2022-01-19 21:59:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][170/1251]	eta 0:41:34 lr 0.000858	time 2.6775 (2.3080)	loss 4.0470 (3.7835)	grad_norm 1.2933 (1.1814)	
[2022-01-19 21:59:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][180/1251]	eta 0:41:16 lr 0.000858	time 2.8351 (2.3119)	loss 4.4990 (3.7864)	grad_norm 1.6279 (1.1839)	
[2022-01-19 22:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][190/1251]	eta 0:40:56 lr 0.000858	time 2.4724 (2.3155)	loss 4.0550 (3.7934)	grad_norm 0.9799 (1.1819)	
[2022-01-19 22:00:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][200/1251]	eta 0:40:25 lr 0.000858	time 1.8090 (2.3079)	loss 2.6865 (3.7963)	grad_norm 1.1154 (1.1817)	
[2022-01-19 22:00:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][210/1251]	eta 0:39:52 lr 0.000858	time 2.4502 (2.2987)	loss 2.4074 (3.7878)	grad_norm 1.0470 (1.1784)	
[2022-01-19 22:01:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][220/1251]	eta 0:39:12 lr 0.000858	time 1.9296 (2.2820)	loss 2.5843 (3.7792)	grad_norm 1.7085 (1.1827)	
[2022-01-19 22:01:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][230/1251]	eta 0:38:43 lr 0.000858	time 2.2565 (2.2753)	loss 3.8447 (3.7823)	grad_norm 1.1641 (1.1836)	
[2022-01-19 22:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][240/1251]	eta 0:38:18 lr 0.000858	time 2.2449 (2.2735)	loss 3.4336 (3.7766)	grad_norm 1.2193 (1.1834)	
[2022-01-19 22:02:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][250/1251]	eta 0:37:55 lr 0.000858	time 2.5165 (2.2735)	loss 2.7783 (3.7673)	grad_norm 1.1381 (1.1822)	
[2022-01-19 22:02:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][260/1251]	eta 0:37:22 lr 0.000858	time 1.9249 (2.2625)	loss 4.0112 (3.7753)	grad_norm 1.0685 (1.1815)	
[2022-01-19 22:03:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][270/1251]	eta 0:36:55 lr 0.000858	time 2.2751 (2.2583)	loss 4.3314 (3.7757)	grad_norm 1.0307 (1.1807)	
[2022-01-19 22:03:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][280/1251]	eta 0:36:35 lr 0.000858	time 2.4377 (2.2614)	loss 4.0293 (3.7722)	grad_norm 0.9960 (1.1806)	
[2022-01-19 22:03:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][290/1251]	eta 0:36:12 lr 0.000858	time 1.9440 (2.2604)	loss 4.0064 (3.7710)	grad_norm 1.1243 (1.1800)	
[2022-01-19 22:04:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][300/1251]	eta 0:35:43 lr 0.000858	time 1.8962 (2.2539)	loss 4.4152 (3.7644)	grad_norm 1.1234 (1.1778)	
[2022-01-19 22:04:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][310/1251]	eta 0:35:15 lr 0.000858	time 2.2147 (2.2482)	loss 4.3496 (3.7642)	grad_norm 1.1323 (1.1762)	
[2022-01-19 22:04:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][320/1251]	eta 0:34:49 lr 0.000858	time 1.8326 (2.2439)	loss 4.1505 (3.7667)	grad_norm 1.6884 (1.1767)	
[2022-01-19 22:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][330/1251]	eta 0:34:23 lr 0.000858	time 1.9848 (2.2402)	loss 3.9385 (3.7677)	grad_norm 1.1570 (1.1762)	
[2022-01-19 22:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][340/1251]	eta 0:33:58 lr 0.000858	time 2.5242 (2.2374)	loss 4.0675 (3.7665)	grad_norm 1.3782 (1.1782)	
[2022-01-19 22:05:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][350/1251]	eta 0:33:33 lr 0.000858	time 1.9519 (2.2352)	loss 3.3561 (3.7734)	grad_norm 1.0682 (1.1770)	
[2022-01-19 22:06:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][360/1251]	eta 0:33:15 lr 0.000858	time 2.9176 (2.2394)	loss 4.4699 (3.7721)	grad_norm 1.0308 (1.1756)	
[2022-01-19 22:06:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][370/1251]	eta 0:32:51 lr 0.000858	time 1.4725 (2.2384)	loss 4.3968 (3.7833)	grad_norm 1.0338 (1.1757)	
[2022-01-19 22:07:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][380/1251]	eta 0:32:33 lr 0.000858	time 2.5270 (2.2424)	loss 4.4606 (3.7909)	grad_norm 1.1973 (1.1761)	
[2022-01-19 22:07:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][390/1251]	eta 0:32:11 lr 0.000858	time 1.7740 (2.2431)	loss 4.3980 (3.8018)	grad_norm 1.3090 (1.1762)	
[2022-01-19 22:07:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][400/1251]	eta 0:31:46 lr 0.000858	time 2.2428 (2.2405)	loss 3.7768 (3.7991)	grad_norm 1.1203 (1.1769)	
[2022-01-19 22:08:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][410/1251]	eta 0:31:19 lr 0.000857	time 1.7162 (2.2343)	loss 3.5781 (3.8042)	grad_norm 1.3950 (1.1757)	
[2022-01-19 22:08:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][420/1251]	eta 0:30:51 lr 0.000857	time 2.0591 (2.2281)	loss 4.2500 (3.8015)	grad_norm 1.0577 (1.1757)	
[2022-01-19 22:08:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][430/1251]	eta 0:30:24 lr 0.000857	time 1.5460 (2.2228)	loss 3.2075 (3.8013)	grad_norm 1.2031 (1.1751)	
[2022-01-19 22:09:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][440/1251]	eta 0:30:03 lr 0.000857	time 2.6401 (2.2243)	loss 4.1833 (3.8042)	grad_norm 1.0600 (1.1738)	
[2022-01-19 22:09:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][450/1251]	eta 0:29:41 lr 0.000857	time 2.0958 (2.2236)	loss 4.0880 (3.8140)	grad_norm 1.1566 (1.1723)	
[2022-01-19 22:09:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][460/1251]	eta 0:29:19 lr 0.000857	time 2.2294 (2.2239)	loss 3.9065 (3.8109)	grad_norm 1.3402 (1.1741)	
[2022-01-19 22:10:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][470/1251]	eta 0:28:56 lr 0.000857	time 2.2034 (2.2237)	loss 3.9453 (3.8084)	grad_norm 1.3269 (1.1742)	
[2022-01-19 22:10:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][480/1251]	eta 0:28:34 lr 0.000857	time 1.7557 (2.2235)	loss 3.7318 (3.8100)	grad_norm 1.0580 (1.1734)	
[2022-01-19 22:11:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][490/1251]	eta 0:28:12 lr 0.000857	time 2.2440 (2.2242)	loss 4.4266 (3.8055)	grad_norm 1.0276 (1.1728)	
[2022-01-19 22:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][500/1251]	eta 0:27:51 lr 0.000857	time 2.1677 (2.2256)	loss 3.3593 (3.7999)	grad_norm 1.1024 (1.1744)	
[2022-01-19 22:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][510/1251]	eta 0:27:29 lr 0.000857	time 2.7345 (2.2257)	loss 3.5963 (3.7990)	grad_norm 1.0724 (1.1750)	
[2022-01-19 22:12:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][520/1251]	eta 0:27:07 lr 0.000857	time 1.6722 (2.2258)	loss 4.0354 (3.8017)	grad_norm 1.3147 (1.1747)	
[2022-01-19 22:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][530/1251]	eta 0:26:43 lr 0.000857	time 1.9798 (2.2244)	loss 4.1560 (3.8051)	grad_norm 1.1660 (1.1738)	
[2022-01-19 22:12:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][540/1251]	eta 0:26:18 lr 0.000857	time 1.9324 (2.2198)	loss 4.0563 (3.8104)	grad_norm 1.2126 (1.1758)	
[2022-01-19 22:13:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][550/1251]	eta 0:25:52 lr 0.000857	time 2.0995 (2.2151)	loss 4.2428 (3.8133)	grad_norm 1.1876 (1.1762)	
[2022-01-19 22:13:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][560/1251]	eta 0:25:27 lr 0.000857	time 1.9277 (2.2108)	loss 4.2738 (3.8155)	grad_norm 1.1692 (1.1761)	
[2022-01-19 22:13:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][570/1251]	eta 0:25:04 lr 0.000857	time 2.4818 (2.2088)	loss 3.6401 (3.8178)	grad_norm 1.1074 (1.1763)	
[2022-01-19 22:14:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][580/1251]	eta 0:24:40 lr 0.000857	time 1.7597 (2.2060)	loss 4.3194 (3.8186)	grad_norm 1.0752 (1.1758)	
[2022-01-19 22:14:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][590/1251]	eta 0:24:17 lr 0.000857	time 1.9425 (2.2052)	loss 4.2910 (3.8150)	grad_norm 0.9953 (1.1748)	
[2022-01-19 22:15:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][600/1251]	eta 0:23:57 lr 0.000857	time 2.8492 (2.2074)	loss 3.0581 (3.8114)	grad_norm 1.1786 (1.1764)	
[2022-01-19 22:15:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][610/1251]	eta 0:23:34 lr 0.000857	time 1.9203 (2.2072)	loss 4.0613 (3.8132)	grad_norm 1.2189 (1.1769)	
[2022-01-19 22:15:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][620/1251]	eta 0:23:12 lr 0.000857	time 2.6243 (2.2072)	loss 3.2142 (3.8098)	grad_norm 1.3120 (1.1774)	
[2022-01-19 22:16:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][630/1251]	eta 0:22:50 lr 0.000857	time 2.3752 (2.2074)	loss 4.2241 (3.8078)	grad_norm 1.0595 (1.1776)	
[2022-01-19 22:16:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][640/1251]	eta 0:22:29 lr 0.000857	time 3.1357 (2.2093)	loss 4.2332 (3.8064)	grad_norm 0.9476 (1.1772)	
[2022-01-19 22:16:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][650/1251]	eta 0:22:09 lr 0.000857	time 2.7369 (2.2122)	loss 4.3360 (3.8049)	grad_norm 1.0375 (1.1757)	
[2022-01-19 22:17:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][660/1251]	eta 0:21:48 lr 0.000857	time 2.5378 (2.2149)	loss 4.3791 (3.8058)	grad_norm 1.3579 (1.1761)	
[2022-01-19 22:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][670/1251]	eta 0:21:25 lr 0.000857	time 2.4533 (2.2129)	loss 3.2841 (3.8020)	grad_norm 1.1481 (1.1778)	
[2022-01-19 22:17:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][680/1251]	eta 0:21:02 lr 0.000857	time 1.9519 (2.2103)	loss 3.9587 (3.8002)	grad_norm 1.1467 (1.1791)	
[2022-01-19 22:18:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][690/1251]	eta 0:20:39 lr 0.000857	time 2.5203 (2.2097)	loss 4.0850 (3.8038)	grad_norm 1.2484 (1.1782)	
[2022-01-19 22:18:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][700/1251]	eta 0:20:17 lr 0.000857	time 2.2554 (2.2105)	loss 4.1869 (3.8032)	grad_norm 1.2175 (1.1778)	
[2022-01-19 22:19:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][710/1251]	eta 0:19:56 lr 0.000857	time 2.2061 (2.2108)	loss 4.3109 (3.8049)	grad_norm 1.1406 (1.1777)	
[2022-01-19 22:19:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][720/1251]	eta 0:19:33 lr 0.000857	time 1.9270 (2.2104)	loss 3.0921 (3.8032)	grad_norm 1.2035 (1.1784)	
[2022-01-19 22:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][730/1251]	eta 0:19:11 lr 0.000857	time 2.4389 (2.2102)	loss 4.4144 (3.8023)	grad_norm 1.2791 (1.1791)	
[2022-01-19 22:20:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][740/1251]	eta 0:18:48 lr 0.000857	time 1.8795 (2.2074)	loss 3.7480 (3.7994)	grad_norm 1.0810 (1.1795)	
[2022-01-19 22:20:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][750/1251]	eta 0:18:25 lr 0.000856	time 2.5888 (2.2064)	loss 3.9402 (3.7994)	grad_norm 1.0699 (1.1782)	
[2022-01-19 22:20:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][760/1251]	eta 0:18:04 lr 0.000856	time 1.7616 (2.2079)	loss 3.1710 (3.8004)	grad_norm 1.6240 (1.1783)	
[2022-01-19 22:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][770/1251]	eta 0:17:41 lr 0.000856	time 2.5044 (2.2077)	loss 4.1180 (3.8032)	grad_norm 1.0152 (1.1777)	
[2022-01-19 22:21:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][780/1251]	eta 0:17:19 lr 0.000856	time 1.5800 (2.2067)	loss 3.3955 (3.8049)	grad_norm 1.1462 (1.1773)	
[2022-01-19 22:21:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][790/1251]	eta 0:16:57 lr 0.000856	time 2.2911 (2.2062)	loss 3.5812 (3.8030)	grad_norm 1.1079 (1.1774)	
[2022-01-19 22:22:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][800/1251]	eta 0:16:34 lr 0.000856	time 1.9097 (2.2058)	loss 4.4475 (3.8025)	grad_norm 1.0845 (1.1774)	
[2022-01-19 22:22:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][810/1251]	eta 0:16:12 lr 0.000856	time 2.0739 (2.2043)	loss 4.0135 (3.8018)	grad_norm 1.1688 (1.1786)	
[2022-01-19 22:23:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][820/1251]	eta 0:15:49 lr 0.000856	time 2.2473 (2.2033)	loss 2.7794 (3.7993)	grad_norm 1.2244 (1.1792)	
[2022-01-19 22:23:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][830/1251]	eta 0:15:27 lr 0.000856	time 2.1547 (2.2020)	loss 3.4899 (3.7985)	grad_norm 1.2359 (1.1801)	
[2022-01-19 22:23:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][840/1251]	eta 0:15:04 lr 0.000856	time 2.0684 (2.2017)	loss 3.6044 (3.7983)	grad_norm 1.0772 (1.1804)	
[2022-01-19 22:24:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][850/1251]	eta 0:14:42 lr 0.000856	time 2.6502 (2.2014)	loss 3.4136 (3.7976)	grad_norm 1.1087 (1.1801)	
[2022-01-19 22:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][860/1251]	eta 0:14:20 lr 0.000856	time 1.9045 (2.2010)	loss 4.1518 (3.7987)	grad_norm 1.1120 (1.1800)	
[2022-01-19 22:24:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][870/1251]	eta 0:13:58 lr 0.000856	time 1.7973 (2.2014)	loss 3.6885 (3.7996)	grad_norm 0.9855 (1.1790)	
[2022-01-19 22:25:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][880/1251]	eta 0:13:36 lr 0.000856	time 2.0015 (2.2007)	loss 3.8289 (3.8032)	grad_norm 1.1683 (1.1793)	
[2022-01-19 22:25:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][890/1251]	eta 0:13:15 lr 0.000856	time 2.8533 (2.2032)	loss 4.4090 (3.8047)	grad_norm 1.0175 (1.1784)	
[2022-01-19 22:25:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][900/1251]	eta 0:12:52 lr 0.000856	time 1.6108 (2.2014)	loss 4.2590 (3.8063)	grad_norm 1.0738 (1.1779)	
[2022-01-19 22:26:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][910/1251]	eta 0:12:30 lr 0.000856	time 1.9035 (2.2008)	loss 4.0819 (3.8084)	grad_norm 1.1917 (1.1779)	
[2022-01-19 22:26:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][920/1251]	eta 0:12:07 lr 0.000856	time 1.7662 (2.1983)	loss 4.1007 (3.8096)	grad_norm 1.2660 (1.1777)	
[2022-01-19 22:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][930/1251]	eta 0:11:45 lr 0.000856	time 2.5204 (2.1979)	loss 4.0680 (3.8082)	grad_norm 1.1974 (1.1777)	
[2022-01-19 22:27:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][940/1251]	eta 0:11:23 lr 0.000856	time 1.9289 (2.1978)	loss 4.1500 (3.8072)	grad_norm 1.3531 (1.1781)	
[2022-01-19 22:27:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][950/1251]	eta 0:11:01 lr 0.000856	time 1.6567 (2.1991)	loss 3.5112 (3.8076)	grad_norm 1.1646 (1.1783)	
[2022-01-19 22:28:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][960/1251]	eta 0:10:40 lr 0.000856	time 2.5362 (2.2013)	loss 3.7959 (3.8087)	grad_norm 1.0790 (1.1784)	
[2022-01-19 22:28:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][970/1251]	eta 0:10:18 lr 0.000856	time 2.7535 (2.2023)	loss 3.2791 (3.8066)	grad_norm 1.1689 (1.1785)	
[2022-01-19 22:28:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][980/1251]	eta 0:09:56 lr 0.000856	time 1.9456 (2.2021)	loss 3.6256 (3.8055)	grad_norm 1.2451 (1.1794)	
[2022-01-19 22:29:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][990/1251]	eta 0:09:34 lr 0.000856	time 1.7168 (2.2005)	loss 3.2844 (3.8049)	grad_norm 1.2503 (1.1794)	
[2022-01-19 22:29:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1000/1251]	eta 0:09:11 lr 0.000856	time 1.8287 (2.1980)	loss 4.1677 (3.8061)	grad_norm 1.0335 (1.1796)	
[2022-01-19 22:29:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1010/1251]	eta 0:08:49 lr 0.000856	time 1.9178 (2.1976)	loss 3.5367 (3.8029)	grad_norm 0.9437 (1.1795)	
[2022-01-19 22:30:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1020/1251]	eta 0:08:27 lr 0.000856	time 1.8602 (2.1970)	loss 3.9680 (3.8052)	grad_norm 1.1989 (1.1791)	
[2022-01-19 22:30:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1030/1251]	eta 0:08:05 lr 0.000856	time 1.9846 (2.1966)	loss 4.7130 (3.8026)	grad_norm 1.1166 (1.1789)	
[2022-01-19 22:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1040/1251]	eta 0:07:43 lr 0.000856	time 1.8917 (2.1975)	loss 4.2888 (3.8009)	grad_norm 1.1365 (1.1793)	
[2022-01-19 22:31:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1050/1251]	eta 0:07:21 lr 0.000856	time 2.1904 (2.1985)	loss 3.4344 (3.8016)	grad_norm 1.1435 (1.1791)	
[2022-01-19 22:31:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1060/1251]	eta 0:07:00 lr 0.000856	time 1.9386 (2.2000)	loss 3.2959 (3.8040)	grad_norm 1.1940 (1.1792)	
[2022-01-19 22:32:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1070/1251]	eta 0:06:38 lr 0.000856	time 2.1224 (2.2003)	loss 4.1435 (3.8050)	grad_norm 0.9938 (1.1789)	
[2022-01-19 22:32:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1080/1251]	eta 0:06:16 lr 0.000856	time 2.1810 (2.1994)	loss 3.3166 (3.8065)	grad_norm 1.4256 (1.1788)	
[2022-01-19 22:32:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1090/1251]	eta 0:05:53 lr 0.000855	time 1.7752 (2.1975)	loss 4.0983 (3.8068)	grad_norm 1.0909 (1.1799)	
[2022-01-19 22:33:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1100/1251]	eta 0:05:31 lr 0.000855	time 2.4905 (2.1975)	loss 3.9764 (3.8089)	grad_norm 1.1208 (1.1799)	
[2022-01-19 22:33:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1110/1251]	eta 0:05:09 lr 0.000855	time 2.0945 (2.1962)	loss 4.4687 (3.8098)	grad_norm 1.4427 (1.1801)	
[2022-01-19 22:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1120/1251]	eta 0:04:47 lr 0.000855	time 2.4789 (2.1971)	loss 4.5154 (3.8080)	grad_norm 1.2595 (1.1805)	
[2022-01-19 22:34:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1130/1251]	eta 0:04:25 lr 0.000855	time 2.1873 (2.1966)	loss 4.5053 (3.8091)	grad_norm 1.2345 (1.1809)	
[2022-01-19 22:34:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1140/1251]	eta 0:04:04 lr 0.000855	time 2.1452 (2.1989)	loss 3.8320 (3.8106)	grad_norm 1.0753 (1.1808)	
[2022-01-19 22:35:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1150/1251]	eta 0:03:42 lr 0.000855	time 1.9270 (2.1987)	loss 4.1944 (3.8100)	grad_norm 1.0541 (1.1798)	
[2022-01-19 22:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1160/1251]	eta 0:03:20 lr 0.000855	time 2.5019 (2.1980)	loss 3.5236 (3.8093)	grad_norm 1.0814 (1.1805)	
[2022-01-19 22:35:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1170/1251]	eta 0:02:57 lr 0.000855	time 1.8849 (2.1964)	loss 3.9352 (3.8103)	grad_norm 1.2693 (1.1806)	
[2022-01-19 22:36:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1180/1251]	eta 0:02:35 lr 0.000855	time 1.8796 (2.1970)	loss 2.7637 (3.8090)	grad_norm 1.0534 (1.1808)	
[2022-01-19 22:36:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1190/1251]	eta 0:02:14 lr 0.000855	time 2.3958 (2.1971)	loss 3.4973 (3.8072)	grad_norm 1.0893 (1.1810)	
[2022-01-19 22:36:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1200/1251]	eta 0:01:52 lr 0.000855	time 2.7830 (2.1976)	loss 2.9949 (3.8052)	grad_norm 1.0123 (1.1809)	
[2022-01-19 22:37:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1210/1251]	eta 0:01:30 lr 0.000855	time 2.8378 (2.1976)	loss 4.4391 (3.8067)	grad_norm 1.0842 (1.1805)	
[2022-01-19 22:37:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1220/1251]	eta 0:01:08 lr 0.000855	time 1.9267 (2.1972)	loss 3.6556 (3.8090)	grad_norm 1.1208 (1.1804)	
[2022-01-19 22:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1230/1251]	eta 0:00:46 lr 0.000855	time 2.2019 (2.1966)	loss 4.3486 (3.8097)	grad_norm 1.1504 (1.1803)	
[2022-01-19 22:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1240/1251]	eta 0:00:24 lr 0.000855	time 2.3278 (2.1951)	loss 4.1018 (3.8105)	grad_norm 1.4006 (1.1802)	
[2022-01-19 22:38:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [74/300][1250/1251]	eta 0:00:02 lr 0.000855	time 1.2041 (2.1889)	loss 3.8498 (3.8106)	grad_norm 1.1551 (1.1802)	
[2022-01-19 22:38:33 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 74 training takes 0:45:38
[2022-01-19 22:38:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.651 (18.651)	Loss 1.1708 (1.1708)	Acc@1 72.266 (72.266)	Acc@5 91.016 (91.016)	
[2022-01-19 22:39:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.613 (3.255)	Loss 1.2261 (1.1780)	Acc@1 72.168 (72.967)	Acc@5 91.602 (91.460)	
[2022-01-19 22:39:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.496 (2.474)	Loss 1.1570 (1.1970)	Acc@1 73.438 (72.252)	Acc@5 91.113 (91.178)	
[2022-01-19 22:39:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.605 (2.204)	Loss 1.2281 (1.2029)	Acc@1 72.363 (72.092)	Acc@5 90.430 (91.145)	
[2022-01-19 22:40:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.494 (2.126)	Loss 1.2079 (1.1990)	Acc@1 69.727 (72.263)	Acc@5 91.211 (91.182)	
[2022-01-19 22:40:08 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.336 Acc@5 91.230
[2022-01-19 22:40:08 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.3%
[2022-01-19 22:40:08 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.34%
[2022-01-19 22:40:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][0/1251]	eta 7:33:42 lr 0.000855	time 21.7609 (21.7609)	loss 4.0784 (4.0784)	grad_norm 1.1691 (1.1691)	
[2022-01-19 22:40:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][10/1251]	eta 1:23:16 lr 0.000855	time 1.5510 (4.0265)	loss 4.5222 (3.8766)	grad_norm 1.0108 (1.1515)	
[2022-01-19 22:41:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][20/1251]	eta 1:06:17 lr 0.000855	time 1.3545 (3.2312)	loss 3.7081 (3.7452)	grad_norm 1.1236 (1.1654)	
[2022-01-19 22:41:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][30/1251]	eta 0:58:19 lr 0.000855	time 1.5688 (2.8663)	loss 3.5987 (3.7724)	grad_norm 1.0567 (1.1582)	
[2022-01-19 22:41:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][40/1251]	eta 0:53:54 lr 0.000855	time 3.0236 (2.6706)	loss 4.1543 (3.8308)	grad_norm 1.0966 (1.1639)	
[2022-01-19 22:42:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][50/1251]	eta 0:52:21 lr 0.000855	time 2.4262 (2.6157)	loss 4.1020 (3.8370)	grad_norm 1.2668 (1.1703)	
[2022-01-19 22:42:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][60/1251]	eta 0:50:23 lr 0.000855	time 1.8548 (2.5387)	loss 3.9145 (3.8501)	grad_norm 1.1667 (1.1695)	
[2022-01-19 22:43:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][70/1251]	eta 0:49:06 lr 0.000855	time 1.6855 (2.4952)	loss 3.6486 (3.7894)	grad_norm 1.0766 (1.1733)	
[2022-01-19 22:43:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][80/1251]	eta 0:48:27 lr 0.000855	time 3.7924 (2.4827)	loss 4.0836 (3.7616)	grad_norm 1.5038 (1.1748)	
[2022-01-19 22:43:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][90/1251]	eta 0:47:29 lr 0.000855	time 1.6753 (2.4546)	loss 4.1913 (3.7762)	grad_norm 1.0482 (1.1803)	
[2022-01-19 22:44:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][100/1251]	eta 0:46:25 lr 0.000855	time 1.5993 (2.4202)	loss 3.8879 (3.7849)	grad_norm 1.0313 (1.1782)	
[2022-01-19 22:44:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][110/1251]	eta 0:45:21 lr 0.000855	time 1.6579 (2.3852)	loss 4.0242 (3.7864)	grad_norm 1.0822 (1.1770)	
[2022-01-19 22:44:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][120/1251]	eta 0:44:50 lr 0.000855	time 3.3582 (2.3787)	loss 4.3938 (3.7987)	grad_norm 1.3133 (1.1772)	
[2022-01-19 22:45:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][130/1251]	eta 0:44:08 lr 0.000855	time 1.5992 (2.3623)	loss 3.1328 (3.7908)	grad_norm 1.1618 (1.1844)	
[2022-01-19 22:45:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][140/1251]	eta 0:43:29 lr 0.000855	time 2.1576 (2.3484)	loss 4.3017 (3.8113)	grad_norm 1.3920 (1.1859)	
[2022-01-19 22:46:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][150/1251]	eta 0:42:54 lr 0.000855	time 1.8601 (2.3380)	loss 3.3327 (3.8160)	grad_norm 1.1340 (1.1837)	
[2022-01-19 22:46:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][160/1251]	eta 0:42:19 lr 0.000855	time 2.9880 (2.3279)	loss 4.1140 (3.8200)	grad_norm 1.2502 (1.1887)	
[2022-01-19 22:46:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][170/1251]	eta 0:41:39 lr 0.000855	time 1.5056 (2.3124)	loss 4.2126 (3.8281)	grad_norm 1.2530 (1.1878)	
[2022-01-19 22:47:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][180/1251]	eta 0:41:10 lr 0.000854	time 1.9222 (2.3066)	loss 3.0555 (3.8174)	grad_norm 1.1361 (1.1835)	
[2022-01-19 22:47:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][190/1251]	eta 0:40:39 lr 0.000854	time 1.8597 (2.2996)	loss 4.5734 (3.8182)	grad_norm 1.0113 (1.1814)	
[2022-01-19 22:47:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][200/1251]	eta 0:40:16 lr 0.000854	time 2.4456 (2.2996)	loss 4.2666 (3.8238)	grad_norm 1.3268 (1.1820)	
[2022-01-19 22:48:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][210/1251]	eta 0:39:46 lr 0.000854	time 1.9644 (2.2923)	loss 3.0749 (3.8210)	grad_norm 1.1409 (1.1851)	
[2022-01-19 22:48:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][220/1251]	eta 0:39:20 lr 0.000854	time 1.9352 (2.2898)	loss 2.7260 (3.8217)	grad_norm 1.4058 (1.1874)	
[2022-01-19 22:48:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][230/1251]	eta 0:38:58 lr 0.000854	time 1.9000 (2.2902)	loss 2.6211 (3.8157)	grad_norm 1.0756 (1.1856)	
[2022-01-19 22:49:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][240/1251]	eta 0:38:37 lr 0.000854	time 1.6123 (2.2924)	loss 4.4064 (3.8162)	grad_norm 1.0520 (1.1823)	
[2022-01-19 22:49:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][250/1251]	eta 0:38:01 lr 0.000854	time 1.8528 (2.2794)	loss 3.9913 (3.8161)	grad_norm 1.0361 (1.1802)	
[2022-01-19 22:49:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][260/1251]	eta 0:37:27 lr 0.000854	time 1.8667 (2.2675)	loss 3.0848 (3.8118)	grad_norm 1.2588 (1.1785)	
[2022-01-19 22:50:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][270/1251]	eta 0:36:56 lr 0.000854	time 1.9590 (2.2592)	loss 3.2320 (3.8048)	grad_norm 1.1062 (1.1815)	
[2022-01-19 22:50:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][280/1251]	eta 0:36:31 lr 0.000854	time 2.3169 (2.2565)	loss 4.2810 (3.8134)	grad_norm 1.2128 (1.1835)	
[2022-01-19 22:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][290/1251]	eta 0:36:07 lr 0.000854	time 1.5573 (2.2555)	loss 4.5946 (3.8276)	grad_norm 1.0787 (1.1843)	
[2022-01-19 22:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][300/1251]	eta 0:35:45 lr 0.000854	time 2.5123 (2.2562)	loss 3.9634 (3.8276)	grad_norm 1.1772 (1.1850)	
[2022-01-19 22:51:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][310/1251]	eta 0:35:17 lr 0.000854	time 2.1490 (2.2508)	loss 4.3302 (3.8186)	grad_norm 1.1086 (1.1836)	
[2022-01-19 22:52:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][320/1251]	eta 0:34:54 lr 0.000854	time 2.1679 (2.2496)	loss 4.7184 (3.8248)	grad_norm 1.4975 (1.1835)	
[2022-01-19 22:52:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][330/1251]	eta 0:34:30 lr 0.000854	time 1.6045 (2.2481)	loss 4.3880 (3.8195)	grad_norm 1.2159 (1.1833)	
[2022-01-19 22:52:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][340/1251]	eta 0:34:06 lr 0.000854	time 2.4140 (2.2469)	loss 4.2369 (3.8247)	grad_norm 0.9900 (1.1807)	
[2022-01-19 22:53:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][350/1251]	eta 0:33:41 lr 0.000854	time 1.8618 (2.2442)	loss 4.0042 (3.8278)	grad_norm 1.0682 (1.1783)	
[2022-01-19 22:53:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][360/1251]	eta 0:33:15 lr 0.000854	time 2.0549 (2.2400)	loss 3.3844 (3.8316)	grad_norm 1.2156 (1.1796)	
[2022-01-19 22:53:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][370/1251]	eta 0:32:51 lr 0.000854	time 1.8527 (2.2377)	loss 3.9500 (3.8286)	grad_norm 1.0013 (1.1789)	
[2022-01-19 22:54:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][380/1251]	eta 0:32:26 lr 0.000854	time 2.5003 (2.2353)	loss 4.5174 (3.8238)	grad_norm 1.0627 (1.1803)	
[2022-01-19 22:54:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][390/1251]	eta 0:32:02 lr 0.000854	time 1.6253 (2.2329)	loss 4.1699 (3.8261)	grad_norm 1.1814 (1.1800)	
[2022-01-19 22:55:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][400/1251]	eta 0:31:42 lr 0.000854	time 2.3025 (2.2360)	loss 4.3196 (3.8285)	grad_norm 0.9983 (1.1790)	
[2022-01-19 22:55:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][410/1251]	eta 0:31:21 lr 0.000854	time 2.7535 (2.2367)	loss 4.2693 (3.8308)	grad_norm 1.2743 (1.1804)	
[2022-01-19 22:55:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][420/1251]	eta 0:30:59 lr 0.000854	time 2.8070 (2.2381)	loss 4.1040 (3.8227)	grad_norm 1.0761 (1.1798)	
[2022-01-19 22:56:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][430/1251]	eta 0:30:33 lr 0.000854	time 1.8249 (2.2331)	loss 3.9437 (3.8276)	grad_norm 1.1790 (1.1800)	
[2022-01-19 22:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][440/1251]	eta 0:30:09 lr 0.000854	time 1.9279 (2.2315)	loss 3.9515 (3.8259)	grad_norm 1.1384 (1.1803)	
[2022-01-19 22:56:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][450/1251]	eta 0:29:46 lr 0.000854	time 2.5763 (2.2300)	loss 3.0193 (3.8244)	grad_norm 1.0779 (1.1794)	
[2022-01-19 22:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][460/1251]	eta 0:29:21 lr 0.000854	time 2.1734 (2.2275)	loss 2.6568 (3.8256)	grad_norm 1.1983 (1.1798)	
[2022-01-19 22:57:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][470/1251]	eta 0:28:57 lr 0.000854	time 2.0054 (2.2245)	loss 4.3373 (3.8271)	grad_norm 1.1091 (1.1806)	
[2022-01-19 22:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][480/1251]	eta 0:28:33 lr 0.000854	time 1.9099 (2.2224)	loss 3.1134 (3.8267)	grad_norm 1.1319 (1.1807)	
[2022-01-19 22:58:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][490/1251]	eta 0:28:13 lr 0.000854	time 2.2937 (2.2255)	loss 3.8731 (3.8246)	grad_norm 1.2267 (1.1811)	
[2022-01-19 22:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][500/1251]	eta 0:27:49 lr 0.000854	time 1.6028 (2.2235)	loss 3.4096 (3.8260)	grad_norm 1.1062 (1.1799)	
[2022-01-19 22:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][510/1251]	eta 0:27:27 lr 0.000854	time 2.1641 (2.2236)	loss 4.0926 (3.8228)	grad_norm 1.1197 (1.1795)	
[2022-01-19 22:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][520/1251]	eta 0:27:08 lr 0.000853	time 3.6985 (2.2278)	loss 3.4323 (3.8236)	grad_norm 1.1649 (1.1800)	
[2022-01-19 22:59:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][530/1251]	eta 0:26:44 lr 0.000853	time 1.6192 (2.2249)	loss 4.6959 (3.8283)	grad_norm 1.2736 (1.1798)	
[2022-01-19 23:00:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][540/1251]	eta 0:26:17 lr 0.000853	time 1.8588 (2.2184)	loss 3.4549 (3.8312)	grad_norm 1.2353 (1.1795)	
[2022-01-19 23:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][550/1251]	eta 0:25:53 lr 0.000853	time 1.8614 (2.2157)	loss 3.2045 (3.8286)	grad_norm 0.9624 (1.1795)	
[2022-01-19 23:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][560/1251]	eta 0:25:31 lr 0.000853	time 3.1290 (2.2170)	loss 4.0095 (3.8258)	grad_norm 1.2160 (1.1808)	
[2022-01-19 23:01:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][570/1251]	eta 0:25:09 lr 0.000853	time 1.7598 (2.2163)	loss 4.3136 (3.8292)	grad_norm 1.0363 (1.1812)	
[2022-01-19 23:01:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][580/1251]	eta 0:24:47 lr 0.000853	time 2.2598 (2.2172)	loss 3.9163 (3.8313)	grad_norm 1.1410 (1.1803)	
[2022-01-19 23:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][590/1251]	eta 0:24:27 lr 0.000853	time 2.2377 (2.2194)	loss 4.3587 (3.8348)	grad_norm 1.4047 (1.1809)	
[2022-01-19 23:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][600/1251]	eta 0:24:05 lr 0.000853	time 2.2049 (2.2203)	loss 3.6411 (3.8338)	grad_norm 1.2608 (1.1822)	
[2022-01-19 23:02:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][610/1251]	eta 0:23:43 lr 0.000853	time 1.7911 (2.2214)	loss 3.9666 (3.8374)	grad_norm 1.1166 (1.1823)	
[2022-01-19 23:03:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][620/1251]	eta 0:23:18 lr 0.000853	time 1.5882 (2.2164)	loss 3.8391 (3.8368)	grad_norm 0.9900 (1.1818)	
[2022-01-19 23:03:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][630/1251]	eta 0:22:54 lr 0.000853	time 1.7276 (2.2128)	loss 3.8227 (3.8380)	grad_norm 1.1226 (1.1814)	
[2022-01-19 23:03:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][640/1251]	eta 0:22:30 lr 0.000853	time 1.8950 (2.2104)	loss 4.0151 (3.8372)	grad_norm 1.1576 (1.1806)	
[2022-01-19 23:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][650/1251]	eta 0:22:06 lr 0.000853	time 1.5919 (2.2079)	loss 3.9068 (3.8391)	grad_norm 1.2180 (1.1795)	
[2022-01-19 23:04:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][660/1251]	eta 0:21:44 lr 0.000853	time 2.3490 (2.2067)	loss 4.1347 (3.8415)	grad_norm 1.1179 (1.1784)	
[2022-01-19 23:04:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][670/1251]	eta 0:21:21 lr 0.000853	time 1.9973 (2.2065)	loss 4.1509 (3.8423)	grad_norm 1.1806 (1.1779)	
[2022-01-19 23:05:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][680/1251]	eta 0:21:00 lr 0.000853	time 2.4907 (2.2077)	loss 3.5299 (3.8421)	grad_norm 1.0054 (1.1771)	
[2022-01-19 23:05:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][690/1251]	eta 0:20:38 lr 0.000853	time 2.1732 (2.2075)	loss 4.2479 (3.8425)	grad_norm 1.2426 (1.1780)	
[2022-01-19 23:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][700/1251]	eta 0:20:17 lr 0.000853	time 2.5286 (2.2102)	loss 3.5691 (3.8417)	grad_norm 1.3616 (1.1787)	
[2022-01-19 23:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][710/1251]	eta 0:19:55 lr 0.000853	time 1.8972 (2.2104)	loss 2.8604 (3.8387)	grad_norm 1.0135 (1.1786)	
[2022-01-19 23:06:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][720/1251]	eta 0:19:34 lr 0.000853	time 2.5870 (2.2114)	loss 3.8345 (3.8388)	grad_norm 1.4564 (1.1783)	
[2022-01-19 23:07:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][730/1251]	eta 0:19:11 lr 0.000853	time 1.4974 (2.2110)	loss 4.1539 (3.8386)	grad_norm 1.3451 (1.1785)	
[2022-01-19 23:07:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][740/1251]	eta 0:18:50 lr 0.000853	time 2.7927 (2.2114)	loss 2.9282 (3.8380)	grad_norm 1.2917 (1.1791)	
[2022-01-19 23:07:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][750/1251]	eta 0:18:26 lr 0.000853	time 1.9531 (2.2084)	loss 3.8929 (3.8336)	grad_norm 1.1635 (1.1788)	
[2022-01-19 23:08:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][760/1251]	eta 0:18:03 lr 0.000853	time 1.8872 (2.2063)	loss 4.1454 (3.8318)	grad_norm 1.3799 (1.1806)	
[2022-01-19 23:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][770/1251]	eta 0:17:40 lr 0.000853	time 2.1669 (2.2051)	loss 2.6377 (3.8340)	grad_norm 1.5515 (1.1807)	
[2022-01-19 23:08:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][780/1251]	eta 0:17:18 lr 0.000853	time 2.6225 (2.2039)	loss 3.8872 (3.8374)	grad_norm 1.1581 (1.1806)	
[2022-01-19 23:09:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][790/1251]	eta 0:16:55 lr 0.000853	time 1.8724 (2.2022)	loss 4.0915 (3.8404)	grad_norm 1.1759 (1.1815)	
[2022-01-19 23:09:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][800/1251]	eta 0:16:33 lr 0.000853	time 2.1119 (2.2019)	loss 3.0481 (3.8403)	grad_norm 0.9075 (1.1827)	
[2022-01-19 23:09:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][810/1251]	eta 0:16:10 lr 0.000853	time 2.1915 (2.2014)	loss 3.7467 (3.8395)	grad_norm 1.0854 (1.1834)	
[2022-01-19 23:10:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][820/1251]	eta 0:15:49 lr 0.000853	time 2.2993 (2.2022)	loss 3.7239 (3.8379)	grad_norm 1.2230 (1.1830)	
[2022-01-19 23:10:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][830/1251]	eta 0:15:27 lr 0.000853	time 2.4169 (2.2023)	loss 3.7394 (3.8390)	grad_norm 1.2751 (1.1827)	
[2022-01-19 23:11:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][840/1251]	eta 0:15:05 lr 0.000853	time 2.4332 (2.2024)	loss 3.5886 (3.8389)	grad_norm 1.6524 (1.1865)	
[2022-01-19 23:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][850/1251]	eta 0:14:43 lr 0.000853	time 2.2303 (2.2021)	loss 3.9949 (3.8377)	grad_norm 1.3072 (1.1868)	
[2022-01-19 23:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][860/1251]	eta 0:14:20 lr 0.000852	time 2.2462 (2.2020)	loss 3.8260 (3.8358)	grad_norm 0.9857 (1.1870)	
[2022-01-19 23:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][870/1251]	eta 0:13:58 lr 0.000852	time 1.5619 (2.1998)	loss 2.7132 (3.8359)	grad_norm 1.1563 (1.1873)	
[2022-01-19 23:12:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][880/1251]	eta 0:13:36 lr 0.000852	time 2.0676 (2.1996)	loss 3.9880 (3.8383)	grad_norm 1.0579 (1.1863)	
[2022-01-19 23:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][890/1251]	eta 0:13:14 lr 0.000852	time 2.2170 (2.2001)	loss 3.4786 (3.8413)	grad_norm 1.2735 (1.1858)	
[2022-01-19 23:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][900/1251]	eta 0:12:52 lr 0.000852	time 2.2141 (2.2001)	loss 4.1665 (3.8380)	grad_norm 1.0224 (1.1865)	
[2022-01-19 23:13:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][910/1251]	eta 0:12:29 lr 0.000852	time 1.8816 (2.1985)	loss 3.4869 (3.8342)	grad_norm 1.0075 (1.1855)	
[2022-01-19 23:13:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][920/1251]	eta 0:12:07 lr 0.000852	time 2.5651 (2.1980)	loss 4.4623 (3.8336)	grad_norm 1.1889 (1.1853)	
[2022-01-19 23:14:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][930/1251]	eta 0:11:45 lr 0.000852	time 1.9513 (2.1973)	loss 3.8923 (3.8338)	grad_norm 1.2429 (1.1854)	
[2022-01-19 23:14:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][940/1251]	eta 0:11:23 lr 0.000852	time 2.5185 (2.1979)	loss 4.3691 (3.8319)	grad_norm 1.3408 (1.1858)	
[2022-01-19 23:14:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][950/1251]	eta 0:11:02 lr 0.000852	time 2.1160 (2.1994)	loss 4.5147 (3.8363)	grad_norm 1.0468 (1.1861)	
[2022-01-19 23:15:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][960/1251]	eta 0:10:40 lr 0.000852	time 2.0932 (2.2001)	loss 4.8001 (3.8410)	grad_norm 0.9649 (1.1862)	
[2022-01-19 23:15:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][970/1251]	eta 0:10:18 lr 0.000852	time 2.0028 (2.1998)	loss 3.8353 (3.8417)	grad_norm 1.1030 (1.1856)	
[2022-01-19 23:16:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][980/1251]	eta 0:09:55 lr 0.000852	time 1.8051 (2.1989)	loss 3.6391 (3.8399)	grad_norm 1.0083 (1.1846)	
[2022-01-19 23:16:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][990/1251]	eta 0:09:33 lr 0.000852	time 1.8790 (2.1979)	loss 2.8713 (3.8389)	grad_norm 1.5388 (1.1848)	
[2022-01-19 23:16:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1000/1251]	eta 0:09:11 lr 0.000852	time 2.5606 (2.1980)	loss 4.3571 (3.8409)	grad_norm 1.2777 (1.1844)	
[2022-01-19 23:17:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1010/1251]	eta 0:08:50 lr 0.000852	time 1.8208 (2.1992)	loss 4.1238 (3.8403)	grad_norm 1.2609 (1.1847)	
[2022-01-19 23:17:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1020/1251]	eta 0:08:28 lr 0.000852	time 1.8903 (2.1998)	loss 3.7178 (3.8424)	grad_norm 1.2197 (1.1854)	
[2022-01-19 23:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1030/1251]	eta 0:08:05 lr 0.000852	time 1.6078 (2.1986)	loss 3.9563 (3.8437)	grad_norm 1.1207 (1.1848)	
[2022-01-19 23:18:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1040/1251]	eta 0:07:43 lr 0.000852	time 2.0863 (2.1978)	loss 3.2571 (3.8424)	grad_norm 1.1340 (1.1841)	
[2022-01-19 23:18:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1050/1251]	eta 0:07:21 lr 0.000852	time 1.6094 (2.1959)	loss 4.8504 (3.8455)	grad_norm 1.3016 (1.1839)	
[2022-01-19 23:18:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1060/1251]	eta 0:06:59 lr 0.000852	time 2.2844 (2.1956)	loss 4.2482 (3.8463)	grad_norm 1.0468 (1.1837)	
[2022-01-19 23:19:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1070/1251]	eta 0:06:37 lr 0.000852	time 2.2770 (2.1951)	loss 4.3860 (3.8472)	grad_norm 1.0940 (1.1833)	
[2022-01-19 23:19:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1080/1251]	eta 0:06:15 lr 0.000852	time 1.7926 (2.1944)	loss 3.8314 (3.8447)	grad_norm 1.2488 (1.1828)	
[2022-01-19 23:20:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1090/1251]	eta 0:05:53 lr 0.000852	time 1.9796 (2.1946)	loss 3.4543 (3.8416)	grad_norm 1.0211 (1.1824)	
[2022-01-19 23:20:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1100/1251]	eta 0:05:31 lr 0.000852	time 1.9099 (2.1947)	loss 3.6668 (3.8416)	grad_norm 1.3204 (1.1820)	
[2022-01-19 23:20:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1110/1251]	eta 0:05:09 lr 0.000852	time 3.0577 (2.1964)	loss 4.0162 (3.8415)	grad_norm 1.1652 (1.1816)	
[2022-01-19 23:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1120/1251]	eta 0:04:47 lr 0.000852	time 1.6787 (2.1956)	loss 3.6759 (3.8390)	grad_norm 1.0261 (1.1817)	
[2022-01-19 23:21:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1130/1251]	eta 0:04:25 lr 0.000852	time 1.7979 (2.1947)	loss 3.9679 (3.8413)	grad_norm 1.2313 (1.1816)	
[2022-01-19 23:21:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1140/1251]	eta 0:04:03 lr 0.000852	time 2.1367 (2.1941)	loss 3.1290 (3.8401)	grad_norm 1.0140 (1.1814)	
[2022-01-19 23:22:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1150/1251]	eta 0:03:41 lr 0.000852	time 2.6777 (2.1931)	loss 3.7191 (3.8389)	grad_norm 1.3508 (1.1812)	
[2022-01-19 23:22:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1160/1251]	eta 0:03:19 lr 0.000852	time 1.8505 (2.1928)	loss 3.8602 (3.8392)	grad_norm 1.1319 (1.1810)	
[2022-01-19 23:22:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1170/1251]	eta 0:02:57 lr 0.000852	time 1.8168 (2.1934)	loss 4.0595 (3.8377)	grad_norm 1.0759 (1.1809)	
[2022-01-19 23:23:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1180/1251]	eta 0:02:35 lr 0.000852	time 1.9184 (2.1932)	loss 3.5340 (3.8389)	grad_norm 1.2082 (1.1810)	
[2022-01-19 23:23:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1190/1251]	eta 0:02:13 lr 0.000852	time 2.4641 (2.1945)	loss 3.8040 (3.8389)	grad_norm 1.0525 (1.1811)	
[2022-01-19 23:24:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1200/1251]	eta 0:01:51 lr 0.000851	time 2.7333 (2.1948)	loss 4.4882 (3.8377)	grad_norm 1.2365 (1.1809)	
[2022-01-19 23:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1210/1251]	eta 0:01:29 lr 0.000851	time 1.6577 (2.1948)	loss 4.5986 (3.8357)	grad_norm 1.0379 (1.1805)	
[2022-01-19 23:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1220/1251]	eta 0:01:08 lr 0.000851	time 2.6225 (2.1945)	loss 4.4968 (3.8350)	grad_norm 1.1063 (1.1806)	
[2022-01-19 23:25:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1230/1251]	eta 0:00:46 lr 0.000851	time 1.6846 (2.1938)	loss 3.5968 (3.8358)	grad_norm 1.1246 (1.1804)	
[2022-01-19 23:25:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1240/1251]	eta 0:00:24 lr 0.000851	time 1.2969 (2.1919)	loss 4.2453 (3.8358)	grad_norm 1.0963 (1.1798)	
[2022-01-19 23:25:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [75/300][1250/1251]	eta 0:00:02 lr 0.000851	time 1.1694 (2.1868)	loss 4.7262 (3.8342)	grad_norm 1.2045 (1.1796)	
[2022-01-19 23:25:44 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 75 training takes 0:45:36
[2022-01-19 23:26:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.427 (18.427)	Loss 1.1381 (1.1381)	Acc@1 73.340 (73.340)	Acc@5 92.188 (92.188)	
[2022-01-19 23:26:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.007 (3.251)	Loss 1.2389 (1.2147)	Acc@1 70.703 (71.973)	Acc@5 90.039 (90.900)	
[2022-01-19 23:26:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.653 (2.551)	Loss 1.1764 (1.1956)	Acc@1 72.949 (72.424)	Acc@5 91.504 (91.309)	
[2022-01-19 23:26:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.281 (2.243)	Loss 1.2312 (1.1970)	Acc@1 71.680 (72.262)	Acc@5 91.211 (91.211)	
[2022-01-19 23:27:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.942 (2.168)	Loss 1.1682 (1.1955)	Acc@1 73.633 (72.192)	Acc@5 91.699 (91.273)	
[2022-01-19 23:27:20 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.180 Acc@5 91.272
[2022-01-19 23:27:20 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.2%
[2022-01-19 23:27:20 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.34%
[2022-01-19 23:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][0/1251]	eta 7:30:04 lr 0.000851	time 21.5863 (21.5863)	loss 4.0257 (4.0257)	grad_norm 1.1909 (1.1909)	
[2022-01-19 23:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][10/1251]	eta 1:25:05 lr 0.000851	time 2.4395 (4.1141)	loss 3.5432 (3.8318)	grad_norm 1.0300 (1.1595)	
[2022-01-19 23:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][20/1251]	eta 1:07:16 lr 0.000851	time 3.1252 (3.2789)	loss 3.2922 (3.7819)	grad_norm 1.3653 (1.1601)	
[2022-01-19 23:28:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][30/1251]	eta 0:59:32 lr 0.000851	time 1.4893 (2.9263)	loss 3.8295 (3.8658)	grad_norm 1.3228 (1.1722)	
[2022-01-19 23:29:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][40/1251]	eta 0:57:07 lr 0.000851	time 3.9116 (2.8307)	loss 3.7473 (3.8800)	grad_norm 1.2558 (1.1846)	
[2022-01-19 23:29:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][50/1251]	eta 0:54:26 lr 0.000851	time 2.1502 (2.7199)	loss 3.3465 (3.8694)	grad_norm 1.0602 (1.1761)	
[2022-01-19 23:30:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][60/1251]	eta 0:52:23 lr 0.000851	time 2.6279 (2.6394)	loss 4.5791 (3.8716)	grad_norm 1.0166 (1.1628)	
[2022-01-19 23:30:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][70/1251]	eta 0:50:20 lr 0.000851	time 1.8041 (2.5576)	loss 4.3738 (3.8556)	grad_norm 1.3291 (1.1711)	
[2022-01-19 23:30:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][80/1251]	eta 0:48:49 lr 0.000851	time 2.7977 (2.5021)	loss 2.6390 (3.8250)	grad_norm 1.2718 (1.1677)	
[2022-01-19 23:31:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][90/1251]	eta 0:47:17 lr 0.000851	time 1.7743 (2.4440)	loss 4.0594 (3.8596)	grad_norm 1.0648 (1.1687)	
[2022-01-19 23:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][100/1251]	eta 0:46:06 lr 0.000851	time 1.5972 (2.4035)	loss 3.7782 (3.8577)	grad_norm 1.0126 (1.1617)	
[2022-01-19 23:31:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][110/1251]	eta 0:45:20 lr 0.000851	time 2.0356 (2.3842)	loss 3.2202 (3.8711)	grad_norm 1.2217 (1.1592)	
[2022-01-19 23:32:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][120/1251]	eta 0:44:38 lr 0.000851	time 2.5395 (2.3679)	loss 3.6253 (3.8734)	grad_norm 1.3380 (1.1549)	
[2022-01-19 23:32:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][130/1251]	eta 0:43:57 lr 0.000851	time 2.2094 (2.3529)	loss 4.3512 (3.8857)	grad_norm 1.2107 (1.1507)	
[2022-01-19 23:32:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][140/1251]	eta 0:43:25 lr 0.000851	time 2.4660 (2.3449)	loss 3.5945 (3.8804)	grad_norm 1.0390 (1.1496)	
[2022-01-19 23:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][150/1251]	eta 0:43:04 lr 0.000851	time 2.2682 (2.3473)	loss 3.6786 (3.8624)	grad_norm 1.1017 (1.1501)	
[2022-01-19 23:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][160/1251]	eta 0:42:27 lr 0.000851	time 2.0365 (2.3350)	loss 4.3873 (3.8633)	grad_norm 1.2381 (1.1539)	
[2022-01-19 23:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][170/1251]	eta 0:41:54 lr 0.000851	time 1.9369 (2.3260)	loss 3.7030 (3.8518)	grad_norm 1.2588 (1.1583)	
[2022-01-19 23:34:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][180/1251]	eta 0:41:08 lr 0.000851	time 1.7461 (2.3049)	loss 3.7575 (3.8259)	grad_norm 1.1433 (1.1597)	
[2022-01-19 23:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][190/1251]	eta 0:40:34 lr 0.000851	time 2.0291 (2.2942)	loss 4.6260 (3.8375)	grad_norm 1.0169 (1.1637)	
[2022-01-19 23:34:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][200/1251]	eta 0:39:56 lr 0.000851	time 1.5744 (2.2805)	loss 2.8881 (3.8373)	grad_norm 1.1113 (1.1646)	
[2022-01-19 23:35:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][210/1251]	eta 0:39:36 lr 0.000851	time 2.2269 (2.2826)	loss 3.3727 (3.8307)	grad_norm 0.9847 (1.1634)	
[2022-01-19 23:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][220/1251]	eta 0:39:03 lr 0.000851	time 1.7881 (2.2734)	loss 4.3832 (3.8273)	grad_norm 1.0924 (1.1613)	
[2022-01-19 23:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][230/1251]	eta 0:38:38 lr 0.000851	time 2.2256 (2.2707)	loss 4.4088 (3.8240)	grad_norm 1.3621 (1.1605)	
[2022-01-19 23:36:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][240/1251]	eta 0:38:14 lr 0.000851	time 1.6301 (2.2698)	loss 4.0576 (3.8341)	grad_norm 1.1490 (1.1621)	
[2022-01-19 23:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][250/1251]	eta 0:37:57 lr 0.000851	time 1.8650 (2.2752)	loss 2.8388 (3.8094)	grad_norm 1.0771 (1.1641)	
[2022-01-19 23:37:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][260/1251]	eta 0:37:29 lr 0.000851	time 2.1675 (2.2696)	loss 4.2395 (3.8053)	grad_norm 1.0609 (1.1688)	
[2022-01-19 23:37:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][270/1251]	eta 0:37:01 lr 0.000851	time 3.0806 (2.2641)	loss 3.8214 (3.8089)	grad_norm 1.1515 (1.1675)	
[2022-01-19 23:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][280/1251]	eta 0:36:34 lr 0.000851	time 2.3184 (2.2599)	loss 3.9241 (3.8068)	grad_norm 1.1484 (1.1676)	
[2022-01-19 23:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][290/1251]	eta 0:36:08 lr 0.000850	time 2.3593 (2.2562)	loss 2.5386 (3.8042)	grad_norm 1.2360 (1.1673)	
[2022-01-19 23:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][300/1251]	eta 0:35:43 lr 0.000850	time 2.3408 (2.2542)	loss 3.3486 (3.8006)	grad_norm 1.2334 (1.1668)	
[2022-01-19 23:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][310/1251]	eta 0:35:21 lr 0.000850	time 2.4764 (2.2548)	loss 2.7181 (3.7966)	grad_norm 1.1175 (1.1657)	
[2022-01-19 23:39:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][320/1251]	eta 0:34:57 lr 0.000850	time 2.4242 (2.2530)	loss 3.1632 (3.8089)	grad_norm 0.9035 (1.1647)	
[2022-01-19 23:39:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][330/1251]	eta 0:34:31 lr 0.000850	time 1.8616 (2.2495)	loss 3.2767 (3.8060)	grad_norm 1.2818 (1.1663)	
[2022-01-19 23:40:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][340/1251]	eta 0:34:07 lr 0.000850	time 1.9239 (2.2472)	loss 4.0649 (3.8044)	grad_norm 1.1276 (1.1681)	
[2022-01-19 23:40:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][350/1251]	eta 0:33:41 lr 0.000850	time 1.8822 (2.2433)	loss 4.1178 (3.8073)	grad_norm 1.0399 (1.1666)	
[2022-01-19 23:40:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][360/1251]	eta 0:33:17 lr 0.000850	time 3.1132 (2.2420)	loss 4.0453 (3.8094)	grad_norm 1.3801 (1.1683)	
[2022-01-19 23:41:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][370/1251]	eta 0:32:51 lr 0.000850	time 2.1931 (2.2381)	loss 2.4264 (3.7991)	grad_norm 1.2575 (1.1696)	
[2022-01-19 23:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][380/1251]	eta 0:32:24 lr 0.000850	time 1.8491 (2.2327)	loss 3.7952 (3.7968)	grad_norm 1.1413 (1.1685)	
[2022-01-19 23:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][390/1251]	eta 0:32:02 lr 0.000850	time 2.2984 (2.2331)	loss 2.7439 (3.7864)	grad_norm 1.4965 (1.1693)	
[2022-01-19 23:42:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][400/1251]	eta 0:31:41 lr 0.000850	time 2.8064 (2.2340)	loss 3.2450 (3.7895)	grad_norm 1.2647 (1.1739)	
[2022-01-19 23:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][410/1251]	eta 0:31:17 lr 0.000850	time 2.4848 (2.2330)	loss 4.1363 (3.7930)	grad_norm 1.2092 (1.1754)	
[2022-01-19 23:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][420/1251]	eta 0:30:57 lr 0.000850	time 1.8638 (2.2349)	loss 3.7550 (3.7945)	grad_norm 1.0697 (1.1762)	
[2022-01-19 23:43:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][430/1251]	eta 0:30:32 lr 0.000850	time 1.7642 (2.2325)	loss 4.1690 (3.7998)	grad_norm 1.2169 (1.1766)	
[2022-01-19 23:43:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][440/1251]	eta 0:30:08 lr 0.000850	time 2.8124 (2.2297)	loss 4.0282 (3.8021)	grad_norm 1.2061 (1.1765)	
[2022-01-19 23:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][450/1251]	eta 0:29:40 lr 0.000850	time 1.8943 (2.2231)	loss 3.5553 (3.7975)	grad_norm 1.0040 (1.1754)	
[2022-01-19 23:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][460/1251]	eta 0:29:15 lr 0.000850	time 2.0526 (2.2196)	loss 3.4988 (3.7973)	grad_norm 1.2090 (1.1757)	
[2022-01-19 23:44:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][470/1251]	eta 0:28:50 lr 0.000850	time 2.0291 (2.2162)	loss 2.6841 (3.7969)	grad_norm 1.0203 (1.1740)	
[2022-01-19 23:45:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][480/1251]	eta 0:28:34 lr 0.000850	time 4.4497 (2.2234)	loss 3.1204 (3.7947)	grad_norm 1.3031 (1.1749)	
[2022-01-19 23:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][490/1251]	eta 0:28:11 lr 0.000850	time 1.7335 (2.2233)	loss 4.0749 (3.7960)	grad_norm 1.2334 (1.1759)	
[2022-01-19 23:45:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][500/1251]	eta 0:27:50 lr 0.000850	time 1.7273 (2.2238)	loss 2.9125 (3.7955)	grad_norm 1.0807 (1.1761)	
[2022-01-19 23:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][510/1251]	eta 0:27:30 lr 0.000850	time 2.2967 (2.2275)	loss 4.2811 (3.7946)	grad_norm 1.0583 (1.1771)	
[2022-01-19 23:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][520/1251]	eta 0:27:09 lr 0.000850	time 3.2243 (2.2291)	loss 3.9627 (3.7911)	grad_norm 1.4505 (1.1789)	
[2022-01-19 23:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][530/1251]	eta 0:26:45 lr 0.000850	time 1.8844 (2.2267)	loss 3.6829 (3.7921)	grad_norm 1.0459 (1.1782)	
[2022-01-19 23:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][540/1251]	eta 0:26:21 lr 0.000850	time 2.2607 (2.2240)	loss 3.6403 (3.7956)	grad_norm 1.2235 (1.1782)	
[2022-01-19 23:47:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][550/1251]	eta 0:25:55 lr 0.000850	time 1.5608 (2.2193)	loss 4.3481 (3.8017)	grad_norm 1.3299 (1.1781)	
[2022-01-19 23:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][560/1251]	eta 0:25:32 lr 0.000850	time 2.5029 (2.2179)	loss 3.4083 (3.8013)	grad_norm 1.3325 (1.1780)	
[2022-01-19 23:48:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][570/1251]	eta 0:25:11 lr 0.000850	time 1.9756 (2.2188)	loss 3.3174 (3.7966)	grad_norm 1.2623 (1.1791)	
[2022-01-19 23:48:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][580/1251]	eta 0:24:49 lr 0.000850	time 1.9277 (2.2203)	loss 3.9587 (3.7969)	grad_norm 1.1618 (1.1787)	
[2022-01-19 23:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][590/1251]	eta 0:24:27 lr 0.000850	time 2.1898 (2.2208)	loss 3.7378 (3.7977)	grad_norm 1.2958 (1.1804)	
[2022-01-19 23:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][600/1251]	eta 0:24:05 lr 0.000850	time 2.2226 (2.2204)	loss 4.0490 (3.7973)	grad_norm 0.9903 (1.1801)	
[2022-01-19 23:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][610/1251]	eta 0:23:42 lr 0.000850	time 2.5905 (2.2188)	loss 4.4933 (3.7954)	grad_norm 1.2259 (1.1804)	
[2022-01-19 23:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][620/1251]	eta 0:23:18 lr 0.000849	time 2.3655 (2.2157)	loss 4.3610 (3.7950)	grad_norm 1.1420 (1.1810)	
[2022-01-19 23:50:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][630/1251]	eta 0:22:54 lr 0.000849	time 2.5954 (2.2140)	loss 3.9931 (3.8019)	grad_norm 1.0883 (1.1812)	
[2022-01-19 23:50:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][640/1251]	eta 0:22:32 lr 0.000849	time 2.1301 (2.2128)	loss 3.2847 (3.7981)	grad_norm 1.2124 (1.1806)	
[2022-01-19 23:51:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][650/1251]	eta 0:22:09 lr 0.000849	time 1.8149 (2.2113)	loss 4.3266 (3.8027)	grad_norm 1.3014 (1.1801)	
[2022-01-19 23:51:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][660/1251]	eta 0:21:47 lr 0.000849	time 2.7604 (2.2117)	loss 4.5570 (3.8067)	grad_norm 1.0818 (1.1811)	
[2022-01-19 23:52:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][670/1251]	eta 0:21:23 lr 0.000849	time 2.3036 (2.2096)	loss 3.2982 (3.8059)	grad_norm 1.0855 (1.1815)	
[2022-01-19 23:52:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][680/1251]	eta 0:21:01 lr 0.000849	time 2.3076 (2.2089)	loss 4.5522 (3.8121)	grad_norm 1.1359 (1.1806)	
[2022-01-19 23:52:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][690/1251]	eta 0:20:38 lr 0.000849	time 1.5955 (2.2077)	loss 3.9922 (3.8075)	grad_norm 1.1351 (1.1795)	
[2022-01-19 23:53:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][700/1251]	eta 0:20:16 lr 0.000849	time 1.8562 (2.2086)	loss 4.6159 (3.8094)	grad_norm 1.1635 (1.1783)	
[2022-01-19 23:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][710/1251]	eta 0:19:56 lr 0.000849	time 2.5259 (2.2117)	loss 4.3225 (3.8115)	grad_norm 1.2542 (1.1782)	
[2022-01-19 23:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][720/1251]	eta 0:19:35 lr 0.000849	time 2.7299 (2.2129)	loss 2.9454 (3.8122)	grad_norm 1.4767 (1.1786)	
[2022-01-19 23:54:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][730/1251]	eta 0:19:11 lr 0.000849	time 1.7234 (2.2099)	loss 4.4259 (3.8139)	grad_norm 1.1145 (1.1787)	
[2022-01-19 23:54:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][740/1251]	eta 0:18:49 lr 0.000849	time 2.1802 (2.2096)	loss 4.1833 (3.8147)	grad_norm 1.1000 (1.1784)	
[2022-01-19 23:54:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][750/1251]	eta 0:18:26 lr 0.000849	time 2.2000 (2.2087)	loss 4.2334 (3.8155)	grad_norm 1.1001 (1.1799)	
[2022-01-19 23:55:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][760/1251]	eta 0:18:04 lr 0.000849	time 3.2074 (2.2094)	loss 3.6655 (3.8177)	grad_norm 1.1346 (1.1807)	
[2022-01-19 23:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][770/1251]	eta 0:17:43 lr 0.000849	time 1.9644 (2.2103)	loss 3.4010 (3.8185)	grad_norm 1.1241 (1.1811)	
[2022-01-19 23:56:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][780/1251]	eta 0:17:21 lr 0.000849	time 2.4471 (2.2106)	loss 3.3535 (3.8199)	grad_norm 1.4973 (1.1828)	
[2022-01-19 23:56:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][790/1251]	eta 0:16:57 lr 0.000849	time 1.8854 (2.2077)	loss 3.4203 (3.8168)	grad_norm 1.0898 (1.1834)	
[2022-01-19 23:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][800/1251]	eta 0:16:34 lr 0.000849	time 2.2209 (2.2060)	loss 4.1081 (3.8196)	grad_norm 0.9348 (1.1821)	
[2022-01-19 23:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][810/1251]	eta 0:16:13 lr 0.000849	time 2.3925 (2.2065)	loss 4.3835 (3.8223)	grad_norm 1.1943 (1.1818)	
[2022-01-19 23:57:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][820/1251]	eta 0:15:51 lr 0.000849	time 2.7634 (2.2085)	loss 3.2507 (3.8196)	grad_norm 1.2324 (1.1817)	
[2022-01-19 23:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][830/1251]	eta 0:15:29 lr 0.000849	time 2.4229 (2.2077)	loss 3.9671 (3.8218)	grad_norm 1.2649 (1.1810)	
[2022-01-19 23:58:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][840/1251]	eta 0:15:07 lr 0.000849	time 1.8805 (2.2074)	loss 4.7289 (3.8215)	grad_norm 1.2369 (1.1806)	
[2022-01-19 23:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][850/1251]	eta 0:14:45 lr 0.000849	time 2.8001 (2.2075)	loss 3.8878 (3.8213)	grad_norm 1.0964 (1.1809)	
[2022-01-19 23:58:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][860/1251]	eta 0:14:22 lr 0.000849	time 1.9642 (2.2064)	loss 3.0294 (3.8180)	grad_norm 1.3595 (1.1815)	
[2022-01-19 23:59:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][870/1251]	eta 0:14:00 lr 0.000849	time 2.5562 (2.2065)	loss 4.0808 (3.8176)	grad_norm 1.2841 (1.1817)	
[2022-01-19 23:59:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][880/1251]	eta 0:13:37 lr 0.000849	time 1.5016 (2.2045)	loss 4.3034 (3.8156)	grad_norm 1.3651 (1.1820)	
[2022-01-20 00:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][890/1251]	eta 0:13:15 lr 0.000849	time 2.4742 (2.2048)	loss 3.4001 (3.8163)	grad_norm 1.1267 (1.1813)	
[2022-01-20 00:00:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][900/1251]	eta 0:12:53 lr 0.000849	time 1.9054 (2.2037)	loss 4.0900 (3.8182)	grad_norm 1.0903 (1.1817)	
[2022-01-20 00:00:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][910/1251]	eta 0:12:32 lr 0.000849	time 3.5679 (2.2067)	loss 3.1610 (3.8134)	grad_norm 1.1500 (1.1806)	
[2022-01-20 00:01:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][920/1251]	eta 0:12:10 lr 0.000849	time 1.9922 (2.2070)	loss 4.4126 (3.8103)	grad_norm 1.3194 (1.1812)	
[2022-01-20 00:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][930/1251]	eta 0:11:47 lr 0.000849	time 2.1521 (2.2054)	loss 4.0893 (3.8093)	grad_norm 1.3803 (1.1817)	
[2022-01-20 00:01:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][940/1251]	eta 0:11:25 lr 0.000849	time 1.8485 (2.2026)	loss 4.7314 (3.8069)	grad_norm 1.3046 (1.1825)	
[2022-01-20 00:02:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][950/1251]	eta 0:11:02 lr 0.000849	time 2.0891 (2.2005)	loss 3.8706 (3.8061)	grad_norm 1.1774 (1.1820)	
[2022-01-20 00:02:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][960/1251]	eta 0:10:40 lr 0.000848	time 1.9477 (2.1995)	loss 4.4756 (3.8069)	grad_norm 1.1202 (1.1819)	
[2022-01-20 00:02:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][970/1251]	eta 0:10:17 lr 0.000848	time 2.2101 (2.1982)	loss 3.9835 (3.8073)	grad_norm 1.3390 (1.1822)	
[2022-01-20 00:03:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][980/1251]	eta 0:09:55 lr 0.000848	time 2.0969 (2.1978)	loss 3.7114 (3.8087)	grad_norm 1.1343 (1.1821)	
[2022-01-20 00:03:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][990/1251]	eta 0:09:34 lr 0.000848	time 2.5112 (2.1995)	loss 4.0329 (3.8083)	grad_norm 1.3251 (1.1819)	
[2022-01-20 00:04:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1000/1251]	eta 0:09:12 lr 0.000848	time 2.1432 (2.2009)	loss 4.3796 (3.8083)	grad_norm 1.1110 (1.1815)	
[2022-01-20 00:04:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1010/1251]	eta 0:08:50 lr 0.000848	time 2.0263 (2.2005)	loss 3.5017 (3.8070)	grad_norm 1.0503 (1.1818)	
[2022-01-20 00:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1020/1251]	eta 0:08:28 lr 0.000848	time 1.5698 (2.2014)	loss 3.2606 (3.8059)	grad_norm 1.1133 (1.1823)	
[2022-01-20 00:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1030/1251]	eta 0:08:06 lr 0.000848	time 3.0979 (2.2021)	loss 4.1187 (3.8042)	grad_norm 1.2947 (1.1824)	
[2022-01-20 00:05:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1040/1251]	eta 0:07:44 lr 0.000848	time 2.4993 (2.2007)	loss 3.8080 (3.8060)	grad_norm 1.3801 (1.1822)	
[2022-01-20 00:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1050/1251]	eta 0:07:22 lr 0.000848	time 1.9100 (2.1992)	loss 4.1869 (3.8088)	grad_norm 0.9867 (1.1815)	
[2022-01-20 00:06:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1060/1251]	eta 0:06:59 lr 0.000848	time 2.2222 (2.1982)	loss 4.1778 (3.8085)	grad_norm 1.1665 (1.1815)	
[2022-01-20 00:06:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1070/1251]	eta 0:06:38 lr 0.000848	time 2.7991 (2.1998)	loss 3.6574 (3.8082)	grad_norm 1.1279 (1.1812)	
[2022-01-20 00:06:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1080/1251]	eta 0:06:16 lr 0.000848	time 3.4102 (2.2014)	loss 3.7788 (3.8098)	grad_norm 1.0596 (1.1816)	
[2022-01-20 00:07:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1090/1251]	eta 0:05:54 lr 0.000848	time 1.6958 (2.2007)	loss 4.2314 (3.8102)	grad_norm 1.2335 (1.1817)	
[2022-01-20 00:07:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1100/1251]	eta 0:05:32 lr 0.000848	time 2.3487 (2.2001)	loss 3.6742 (3.8086)	grad_norm 1.0778 (1.1817)	
[2022-01-20 00:08:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1110/1251]	eta 0:05:09 lr 0.000848	time 2.1972 (2.1982)	loss 4.1910 (3.8086)	grad_norm 1.0798 (1.1816)	
[2022-01-20 00:08:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1120/1251]	eta 0:04:47 lr 0.000848	time 2.1725 (2.1962)	loss 2.9213 (3.8087)	grad_norm 1.2572 (1.1818)	
[2022-01-20 00:08:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1130/1251]	eta 0:04:25 lr 0.000848	time 1.8831 (2.1951)	loss 3.0242 (3.8053)	grad_norm 1.5287 (1.1827)	
[2022-01-20 00:09:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1140/1251]	eta 0:04:03 lr 0.000848	time 1.5132 (2.1946)	loss 3.2592 (3.8041)	grad_norm 1.2279 (1.1827)	
[2022-01-20 00:09:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1150/1251]	eta 0:03:41 lr 0.000848	time 2.4920 (2.1939)	loss 2.6294 (3.8020)	grad_norm 1.0741 (1.1828)	
[2022-01-20 00:09:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1160/1251]	eta 0:03:19 lr 0.000848	time 2.7065 (2.1944)	loss 3.4086 (3.8033)	grad_norm 1.1258 (1.1827)	
[2022-01-20 00:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1170/1251]	eta 0:02:57 lr 0.000848	time 2.8744 (2.1960)	loss 3.4756 (3.8026)	grad_norm 1.2136 (1.1827)	
[2022-01-20 00:10:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1180/1251]	eta 0:02:36 lr 0.000848	time 1.8103 (2.1974)	loss 3.1298 (3.8017)	grad_norm 1.0713 (1.1823)	
[2022-01-20 00:10:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1190/1251]	eta 0:02:14 lr 0.000848	time 1.9333 (2.1989)	loss 4.3038 (3.8016)	grad_norm 1.1280 (1.1821)	
[2022-01-20 00:11:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1200/1251]	eta 0:01:52 lr 0.000848	time 2.7817 (2.1983)	loss 4.5773 (3.8021)	grad_norm 1.0003 (1.1820)	
[2022-01-20 00:11:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1210/1251]	eta 0:01:30 lr 0.000848	time 1.6120 (2.1959)	loss 3.8812 (3.8023)	grad_norm 1.2755 (1.1818)	
[2022-01-20 00:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1220/1251]	eta 0:01:08 lr 0.000848	time 1.8544 (2.1947)	loss 3.7018 (3.7998)	grad_norm 1.0468 (1.1815)	
[2022-01-20 00:12:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1230/1251]	eta 0:00:46 lr 0.000848	time 2.5234 (2.1935)	loss 4.4838 (3.8015)	grad_norm 1.2634 (1.1815)	
[2022-01-20 00:12:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1240/1251]	eta 0:00:24 lr 0.000848	time 1.4660 (2.1924)	loss 3.1460 (3.7996)	grad_norm 1.2902 (1.1817)	
[2022-01-20 00:12:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [76/300][1250/1251]	eta 0:00:02 lr 0.000848	time 1.1601 (2.1874)	loss 3.3590 (3.7976)	grad_norm 1.3247 (1.1815)	
[2022-01-20 00:12:57 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 76 training takes 0:45:36
[2022-01-20 00:13:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.529 (18.529)	Loss 1.2341 (1.2341)	Acc@1 71.191 (71.191)	Acc@5 91.016 (91.016)	
[2022-01-20 00:13:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.961 (3.571)	Loss 1.0828 (1.1781)	Acc@1 73.633 (72.461)	Acc@5 93.457 (91.602)	
[2022-01-20 00:13:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.356 (2.611)	Loss 1.2203 (1.1838)	Acc@1 72.168 (72.480)	Acc@5 90.430 (91.430)	
[2022-01-20 00:14:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.646 (2.330)	Loss 1.1381 (1.1824)	Acc@1 72.656 (72.521)	Acc@5 92.285 (91.447)	
[2022-01-20 00:14:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.161 (2.220)	Loss 1.1560 (1.1775)	Acc@1 72.266 (72.604)	Acc@5 92.383 (91.552)	
[2022-01-20 00:14:35 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.532 Acc@5 91.490
[2022-01-20 00:14:35 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.5%
[2022-01-20 00:14:35 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.53%
[2022-01-20 00:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][0/1251]	eta 7:28:34 lr 0.000848	time 21.5143 (21.5143)	loss 2.8776 (2.8776)	grad_norm 1.2023 (1.2023)	
[2022-01-20 00:15:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][10/1251]	eta 1:22:27 lr 0.000848	time 2.4730 (3.9863)	loss 3.6330 (3.8203)	grad_norm 1.1059 (1.1689)	
[2022-01-20 00:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][20/1251]	eta 1:04:40 lr 0.000848	time 2.2427 (3.1526)	loss 2.6077 (3.7081)	grad_norm 1.0554 (1.1285)	
[2022-01-20 00:16:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][30/1251]	eta 0:57:42 lr 0.000848	time 1.7721 (2.8355)	loss 4.5171 (3.6524)	grad_norm 1.5484 (1.1796)	
[2022-01-20 00:16:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][40/1251]	eta 0:54:55 lr 0.000847	time 3.5544 (2.7212)	loss 4.2504 (3.7361)	grad_norm 1.2696 (1.1940)	
[2022-01-20 00:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][50/1251]	eta 0:53:28 lr 0.000847	time 3.5009 (2.6715)	loss 3.2440 (3.7330)	grad_norm 1.1824 (1.1859)	
[2022-01-20 00:17:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][60/1251]	eta 0:51:38 lr 0.000847	time 2.2743 (2.6017)	loss 2.7740 (3.7390)	grad_norm 1.1359 (1.1853)	
[2022-01-20 00:17:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][70/1251]	eta 0:49:40 lr 0.000847	time 1.9496 (2.5235)	loss 3.8292 (3.7918)	grad_norm 1.0817 (1.2142)	
[2022-01-20 00:17:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][80/1251]	eta 0:48:25 lr 0.000847	time 3.2105 (2.4813)	loss 3.3892 (3.8087)	grad_norm 1.1534 (1.2123)	
[2022-01-20 00:18:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][90/1251]	eta 0:47:19 lr 0.000847	time 2.3141 (2.4455)	loss 4.3034 (3.8441)	grad_norm 1.0543 (1.2003)	
[2022-01-20 00:18:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][100/1251]	eta 0:46:23 lr 0.000847	time 1.8133 (2.4186)	loss 3.5801 (3.8620)	grad_norm 1.1013 (1.1912)	
[2022-01-20 00:19:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][110/1251]	eta 0:45:38 lr 0.000847	time 1.8331 (2.4001)	loss 3.8429 (3.8546)	grad_norm 1.3070 (1.1947)	
[2022-01-20 00:19:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][120/1251]	eta 0:44:58 lr 0.000847	time 2.8031 (2.3862)	loss 3.9056 (3.8487)	grad_norm 1.4554 (1.1941)	
[2022-01-20 00:19:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][130/1251]	eta 0:44:24 lr 0.000847	time 2.9248 (2.3767)	loss 4.5565 (3.8521)	grad_norm 1.3652 (1.1988)	
[2022-01-20 00:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][140/1251]	eta 0:43:41 lr 0.000847	time 1.5577 (2.3593)	loss 4.6548 (3.8631)	grad_norm 1.1994 (1.2027)	
[2022-01-20 00:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][150/1251]	eta 0:42:59 lr 0.000847	time 1.7689 (2.3433)	loss 3.2665 (3.8572)	grad_norm 1.4335 (1.2067)	
[2022-01-20 00:20:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][160/1251]	eta 0:42:24 lr 0.000847	time 2.4474 (2.3321)	loss 4.7646 (3.8564)	grad_norm 1.2091 (1.2083)	
[2022-01-20 00:21:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][170/1251]	eta 0:41:43 lr 0.000847	time 1.6239 (2.3158)	loss 4.4517 (3.8629)	grad_norm 1.1071 (1.2059)	
[2022-01-20 00:21:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][180/1251]	eta 0:41:15 lr 0.000847	time 2.1292 (2.3110)	loss 2.7364 (3.8604)	grad_norm 1.1557 (1.2016)	
[2022-01-20 00:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][190/1251]	eta 0:40:42 lr 0.000847	time 2.0615 (2.3022)	loss 4.5040 (3.8653)	grad_norm 1.0860 (1.1960)	
[2022-01-20 00:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][200/1251]	eta 0:40:13 lr 0.000847	time 2.2054 (2.2964)	loss 2.8589 (3.8562)	grad_norm 1.2605 (1.1961)	
[2022-01-20 00:22:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][210/1251]	eta 0:39:41 lr 0.000847	time 2.1272 (2.2874)	loss 4.0677 (3.8628)	grad_norm 1.1996 (1.1982)	
[2022-01-20 00:22:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][220/1251]	eta 0:39:12 lr 0.000847	time 2.1928 (2.2821)	loss 3.7396 (3.8545)	grad_norm 1.0572 (1.1964)	
[2022-01-20 00:23:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][230/1251]	eta 0:38:47 lr 0.000847	time 2.1491 (2.2800)	loss 4.2623 (3.8550)	grad_norm 1.3814 (1.1954)	
[2022-01-20 00:23:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][240/1251]	eta 0:38:18 lr 0.000847	time 2.1499 (2.2739)	loss 4.0970 (3.8605)	grad_norm 1.3683 (1.1954)	
[2022-01-20 00:24:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][250/1251]	eta 0:37:53 lr 0.000847	time 1.5880 (2.2710)	loss 4.0368 (3.8553)	grad_norm 1.1826 (1.1930)	
[2022-01-20 00:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][260/1251]	eta 0:37:26 lr 0.000847	time 2.2253 (2.2673)	loss 4.1274 (3.8595)	grad_norm 1.1862 (1.1910)	
[2022-01-20 00:24:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][270/1251]	eta 0:37:02 lr 0.000847	time 2.1485 (2.2660)	loss 4.0940 (3.8601)	grad_norm 1.1042 (1.1909)	
[2022-01-20 00:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][280/1251]	eta 0:36:32 lr 0.000847	time 1.8602 (2.2580)	loss 3.8461 (3.8663)	grad_norm 1.2798 (1.1907)	
[2022-01-20 00:25:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][290/1251]	eta 0:36:01 lr 0.000847	time 2.4836 (2.2497)	loss 3.7801 (3.8565)	grad_norm 1.1304 (1.1905)	
[2022-01-20 00:25:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][300/1251]	eta 0:35:33 lr 0.000847	time 1.4675 (2.2433)	loss 3.9029 (3.8597)	grad_norm 1.0343 (1.1922)	
[2022-01-20 00:26:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][310/1251]	eta 0:35:10 lr 0.000847	time 2.2563 (2.2423)	loss 3.9901 (3.8595)	grad_norm 1.1748 (1.1916)	
[2022-01-20 00:26:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][320/1251]	eta 0:34:54 lr 0.000847	time 1.8556 (2.2495)	loss 3.2384 (3.8580)	grad_norm 1.1003 (1.1900)	
[2022-01-20 00:26:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][330/1251]	eta 0:34:31 lr 0.000847	time 2.1897 (2.2488)	loss 3.8776 (3.8506)	grad_norm 1.0905 (1.1921)	
[2022-01-20 00:27:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][340/1251]	eta 0:34:07 lr 0.000847	time 1.9452 (2.2474)	loss 4.5049 (3.8614)	grad_norm 1.0455 (1.1927)	
[2022-01-20 00:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][350/1251]	eta 0:33:45 lr 0.000847	time 1.9125 (2.2484)	loss 4.0813 (3.8556)	grad_norm 1.1352 (1.1927)	
[2022-01-20 00:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][360/1251]	eta 0:33:19 lr 0.000847	time 2.1978 (2.2439)	loss 3.5534 (3.8563)	grad_norm 1.2083 (1.1925)	
[2022-01-20 00:28:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][370/1251]	eta 0:32:53 lr 0.000847	time 1.5792 (2.2401)	loss 3.6441 (3.8544)	grad_norm 1.1583 (1.1916)	
[2022-01-20 00:28:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][380/1251]	eta 0:32:28 lr 0.000846	time 1.9479 (2.2368)	loss 4.0543 (3.8602)	grad_norm 1.1106 (1.1904)	
[2022-01-20 00:29:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][390/1251]	eta 0:32:07 lr 0.000846	time 1.9363 (2.2390)	loss 4.0431 (3.8557)	grad_norm 1.4262 (1.1905)	
[2022-01-20 00:29:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][400/1251]	eta 0:31:44 lr 0.000846	time 3.2797 (2.2378)	loss 3.7091 (3.8515)	grad_norm 1.3944 (1.1925)	
[2022-01-20 00:29:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][410/1251]	eta 0:31:19 lr 0.000846	time 1.9142 (2.2344)	loss 4.3796 (3.8547)	grad_norm 1.1583 (1.1918)	
[2022-01-20 00:30:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][420/1251]	eta 0:30:55 lr 0.000846	time 1.9990 (2.2329)	loss 3.9200 (3.8538)	grad_norm 1.3389 (1.1941)	
[2022-01-20 00:30:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][430/1251]	eta 0:30:35 lr 0.000846	time 2.2539 (2.2362)	loss 3.6709 (3.8584)	grad_norm 1.1763 (1.1951)	
[2022-01-20 00:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][440/1251]	eta 0:30:13 lr 0.000846	time 2.9551 (2.2361)	loss 3.8319 (3.8569)	grad_norm 1.1497 (1.1948)	
[2022-01-20 00:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][450/1251]	eta 0:29:48 lr 0.000846	time 1.9286 (2.2330)	loss 4.3040 (3.8552)	grad_norm 1.1594 (1.1949)	
[2022-01-20 00:31:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][460/1251]	eta 0:29:23 lr 0.000846	time 1.8598 (2.2294)	loss 4.2094 (3.8572)	grad_norm 1.1851 (1.1942)	
[2022-01-20 00:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][470/1251]	eta 0:28:58 lr 0.000846	time 2.3152 (2.2264)	loss 4.0526 (3.8553)	grad_norm 1.1662 (1.1922)	
[2022-01-20 00:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][480/1251]	eta 0:28:37 lr 0.000846	time 2.7347 (2.2271)	loss 3.4988 (3.8500)	grad_norm 1.3359 (1.1912)	
[2022-01-20 00:32:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][490/1251]	eta 0:28:14 lr 0.000846	time 1.6131 (2.2270)	loss 3.0226 (3.8504)	grad_norm 1.1971 (1.1921)	
[2022-01-20 00:33:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][500/1251]	eta 0:27:50 lr 0.000846	time 2.1104 (2.2244)	loss 2.6547 (3.8505)	grad_norm 1.2219 (1.1921)	
[2022-01-20 00:33:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][510/1251]	eta 0:27:25 lr 0.000846	time 1.6171 (2.2211)	loss 3.8818 (3.8516)	grad_norm 1.2703 (1.1917)	
[2022-01-20 00:33:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][520/1251]	eta 0:27:03 lr 0.000846	time 2.3981 (2.2208)	loss 3.0342 (3.8452)	grad_norm 1.1148 (1.1911)	
[2022-01-20 00:34:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][530/1251]	eta 0:26:42 lr 0.000846	time 2.7188 (2.2228)	loss 4.2901 (3.8407)	grad_norm 1.2031 (1.1905)	
[2022-01-20 00:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][540/1251]	eta 0:26:21 lr 0.000846	time 2.4825 (2.2244)	loss 4.6474 (3.8381)	grad_norm 1.1677 (1.1901)	
[2022-01-20 00:35:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][550/1251]	eta 0:25:58 lr 0.000846	time 2.0076 (2.2231)	loss 4.4980 (3.8408)	grad_norm 1.2701 (1.1899)	
[2022-01-20 00:35:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][560/1251]	eta 0:25:34 lr 0.000846	time 2.1955 (2.2208)	loss 4.0618 (3.8417)	grad_norm 1.4852 (1.1901)	
[2022-01-20 00:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][570/1251]	eta 0:25:09 lr 0.000846	time 1.9792 (2.2160)	loss 3.6222 (3.8375)	grad_norm 1.6316 (1.1904)	
[2022-01-20 00:36:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][580/1251]	eta 0:24:44 lr 0.000846	time 2.4766 (2.2120)	loss 4.1331 (3.8366)	grad_norm 1.0595 (1.1904)	
[2022-01-20 00:36:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][590/1251]	eta 0:24:21 lr 0.000846	time 2.1541 (2.2108)	loss 3.9042 (3.8345)	grad_norm 1.0313 (1.1896)	
[2022-01-20 00:36:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][600/1251]	eta 0:24:00 lr 0.000846	time 2.6265 (2.2124)	loss 3.9145 (3.8380)	grad_norm 1.2692 (1.1898)	
[2022-01-20 00:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][610/1251]	eta 0:23:40 lr 0.000846	time 2.8794 (2.2161)	loss 4.3355 (3.8372)	grad_norm 1.1220 (1.1900)	
[2022-01-20 00:37:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][620/1251]	eta 0:23:17 lr 0.000846	time 1.9321 (2.2154)	loss 3.8019 (3.8355)	grad_norm 1.1040 (1.1902)	
[2022-01-20 00:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][630/1251]	eta 0:22:56 lr 0.000846	time 2.4415 (2.2170)	loss 2.7754 (3.8359)	grad_norm 1.0308 (1.1892)	
[2022-01-20 00:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][640/1251]	eta 0:22:34 lr 0.000846	time 2.2429 (2.2172)	loss 3.4265 (3.8325)	grad_norm 1.1168 (1.1882)	
[2022-01-20 00:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][650/1251]	eta 0:22:11 lr 0.000846	time 2.0535 (2.2151)	loss 3.5898 (3.8295)	grad_norm 1.1706 (1.1872)	
[2022-01-20 00:38:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][660/1251]	eta 0:21:47 lr 0.000846	time 1.6150 (2.2122)	loss 3.9311 (3.8279)	grad_norm 1.0911 (1.1857)	
[2022-01-20 00:39:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][670/1251]	eta 0:21:26 lr 0.000846	time 2.5120 (2.2137)	loss 2.5699 (3.8264)	grad_norm 1.1475 (1.1855)	
[2022-01-20 00:39:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][680/1251]	eta 0:21:03 lr 0.000846	time 2.0665 (2.2129)	loss 4.3150 (3.8275)	grad_norm 1.2929 (1.1856)	
[2022-01-20 00:40:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][690/1251]	eta 0:20:41 lr 0.000846	time 1.8060 (2.2123)	loss 4.2809 (3.8292)	grad_norm 1.1978 (1.1851)	
[2022-01-20 00:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][700/1251]	eta 0:20:18 lr 0.000846	time 2.1143 (2.2112)	loss 4.4257 (3.8310)	grad_norm 1.0681 (1.1846)	
[2022-01-20 00:40:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][710/1251]	eta 0:19:56 lr 0.000845	time 1.9253 (2.2111)	loss 3.9373 (3.8328)	grad_norm 1.1627 (1.1853)	
[2022-01-20 00:41:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][720/1251]	eta 0:19:33 lr 0.000845	time 2.6674 (2.2093)	loss 4.0754 (3.8303)	grad_norm 1.0052 (1.1853)	
[2022-01-20 00:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][730/1251]	eta 0:19:11 lr 0.000845	time 2.2423 (2.2096)	loss 3.6140 (3.8292)	grad_norm 1.2299 (1.1844)	
[2022-01-20 00:41:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][740/1251]	eta 0:18:48 lr 0.000845	time 1.8958 (2.2085)	loss 4.2955 (3.8322)	grad_norm 1.0757 (1.1833)	
[2022-01-20 00:42:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][750/1251]	eta 0:18:25 lr 0.000845	time 1.7703 (2.2072)	loss 4.3428 (3.8316)	grad_norm 1.0945 (1.1837)	
[2022-01-20 00:42:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][760/1251]	eta 0:18:03 lr 0.000845	time 2.0749 (2.2066)	loss 3.8181 (3.8300)	grad_norm 1.1585 (1.1847)	
[2022-01-20 00:42:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][770/1251]	eta 0:17:41 lr 0.000845	time 2.2113 (2.2059)	loss 4.2060 (3.8325)	grad_norm 1.2492 (1.1853)	
[2022-01-20 00:43:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][780/1251]	eta 0:17:18 lr 0.000845	time 2.9179 (2.2058)	loss 4.3471 (3.8335)	grad_norm 1.1683 (1.1861)	
[2022-01-20 00:43:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][790/1251]	eta 0:16:56 lr 0.000845	time 1.8530 (2.2054)	loss 3.7972 (3.8349)	grad_norm 1.2051 (1.1861)	
[2022-01-20 00:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][800/1251]	eta 0:16:35 lr 0.000845	time 2.2140 (2.2065)	loss 2.8974 (3.8325)	grad_norm 1.0138 (1.1862)	
[2022-01-20 00:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][810/1251]	eta 0:16:13 lr 0.000845	time 2.5136 (2.2080)	loss 3.7119 (3.8332)	grad_norm 1.1922 (1.1872)	
[2022-01-20 00:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][820/1251]	eta 0:15:51 lr 0.000845	time 2.2362 (2.2087)	loss 3.9968 (3.8337)	grad_norm 1.1284 (1.1881)	
[2022-01-20 00:45:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][830/1251]	eta 0:15:29 lr 0.000845	time 1.9071 (2.2090)	loss 3.0968 (3.8328)	grad_norm 1.1541 (1.1879)	
[2022-01-20 00:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][840/1251]	eta 0:15:07 lr 0.000845	time 1.8448 (2.2072)	loss 4.3207 (3.8336)	grad_norm 1.1954 (1.1888)	
[2022-01-20 00:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][850/1251]	eta 0:14:43 lr 0.000845	time 1.5780 (2.2044)	loss 4.0261 (3.8325)	grad_norm 1.1274 (1.1881)	
[2022-01-20 00:46:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][860/1251]	eta 0:14:21 lr 0.000845	time 2.3682 (2.2040)	loss 3.0440 (3.8327)	grad_norm 1.1530 (1.1882)	
[2022-01-20 00:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][870/1251]	eta 0:13:59 lr 0.000845	time 1.8422 (2.2040)	loss 3.9953 (3.8306)	grad_norm 1.2116 (1.1879)	
[2022-01-20 00:46:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][880/1251]	eta 0:13:37 lr 0.000845	time 2.8604 (2.2041)	loss 3.8996 (3.8284)	grad_norm 1.1426 (1.1886)	
[2022-01-20 00:47:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][890/1251]	eta 0:13:16 lr 0.000845	time 2.0524 (2.2057)	loss 3.6555 (3.8287)	grad_norm 1.1855 (1.1885)	
[2022-01-20 00:47:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][900/1251]	eta 0:12:54 lr 0.000845	time 2.2245 (2.2068)	loss 2.9072 (3.8285)	grad_norm 1.1874 (1.1886)	
[2022-01-20 00:48:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][910/1251]	eta 0:12:32 lr 0.000845	time 1.8158 (2.2079)	loss 3.0492 (3.8297)	grad_norm 1.1982 (1.1888)	
[2022-01-20 00:48:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][920/1251]	eta 0:12:11 lr 0.000845	time 3.1431 (2.2087)	loss 2.9451 (3.8286)	grad_norm 1.1041 (1.1890)	
[2022-01-20 00:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][930/1251]	eta 0:11:48 lr 0.000845	time 2.2000 (2.2066)	loss 4.1699 (3.8285)	grad_norm 1.2761 (1.1891)	
[2022-01-20 00:49:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][940/1251]	eta 0:11:25 lr 0.000845	time 2.1651 (2.2049)	loss 4.1436 (3.8268)	grad_norm 1.3126 (1.1899)	
[2022-01-20 00:49:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][950/1251]	eta 0:11:03 lr 0.000845	time 1.8884 (2.2028)	loss 3.8673 (3.8284)	grad_norm 1.1648 (1.1907)	
[2022-01-20 00:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][960/1251]	eta 0:10:40 lr 0.000845	time 1.5414 (2.2005)	loss 3.8201 (3.8277)	grad_norm 1.1860 (1.1904)	
[2022-01-20 00:50:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][970/1251]	eta 0:10:18 lr 0.000845	time 2.0421 (2.2009)	loss 4.4147 (3.8300)	grad_norm 1.2761 (1.1913)	
[2022-01-20 00:50:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][980/1251]	eta 0:09:56 lr 0.000845	time 2.5291 (2.2009)	loss 4.0607 (3.8309)	grad_norm 1.0866 (1.1923)	
[2022-01-20 00:50:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][990/1251]	eta 0:09:34 lr 0.000845	time 2.2088 (2.2022)	loss 2.9253 (3.8300)	grad_norm 1.2481 (1.1926)	
[2022-01-20 00:51:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1000/1251]	eta 0:09:12 lr 0.000845	time 1.5466 (2.2029)	loss 3.0560 (3.8280)	grad_norm 1.1723 (1.1922)	
[2022-01-20 00:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1010/1251]	eta 0:08:51 lr 0.000845	time 2.1294 (2.2036)	loss 3.2386 (3.8292)	grad_norm 1.0996 (1.1915)	
[2022-01-20 00:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1020/1251]	eta 0:08:29 lr 0.000845	time 2.8777 (2.2047)	loss 4.0354 (3.8304)	grad_norm 0.9818 (1.1912)	
[2022-01-20 00:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1030/1251]	eta 0:08:07 lr 0.000845	time 1.8296 (2.2052)	loss 4.0708 (3.8339)	grad_norm 1.5666 (1.1915)	
[2022-01-20 00:52:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1040/1251]	eta 0:07:45 lr 0.000844	time 1.9645 (2.2060)	loss 2.9672 (3.8322)	grad_norm 1.6733 (1.1911)	
[2022-01-20 00:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1050/1251]	eta 0:07:22 lr 0.000844	time 1.6576 (2.2038)	loss 4.4383 (3.8318)	grad_norm 1.2226 (1.1904)	
[2022-01-20 00:53:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1060/1251]	eta 0:07:00 lr 0.000844	time 1.9525 (2.2005)	loss 4.1227 (3.8317)	grad_norm 1.3855 (1.1906)	
[2022-01-20 00:53:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1070/1251]	eta 0:06:37 lr 0.000844	time 1.9118 (2.1981)	loss 3.2483 (3.8345)	grad_norm 1.1812 (1.1908)	
[2022-01-20 00:54:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1080/1251]	eta 0:06:15 lr 0.000844	time 1.8227 (2.1970)	loss 2.7513 (3.8321)	grad_norm 1.3814 (1.1912)	
[2022-01-20 00:54:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1090/1251]	eta 0:05:53 lr 0.000844	time 2.5558 (2.1973)	loss 4.2347 (3.8309)	grad_norm 1.3829 (1.1917)	
[2022-01-20 00:54:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1100/1251]	eta 0:05:31 lr 0.000844	time 2.1313 (2.1977)	loss 4.4910 (3.8289)	grad_norm 1.1535 (1.1911)	
[2022-01-20 00:55:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1110/1251]	eta 0:05:09 lr 0.000844	time 2.9060 (2.1979)	loss 4.0709 (3.8294)	grad_norm 1.1994 (1.1906)	
[2022-01-20 00:55:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1120/1251]	eta 0:04:47 lr 0.000844	time 1.9129 (2.1976)	loss 4.2723 (3.8286)	grad_norm 1.1293 (1.1906)	
[2022-01-20 00:56:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1130/1251]	eta 0:04:25 lr 0.000844	time 1.8657 (2.1978)	loss 3.2826 (3.8277)	grad_norm 1.1274 (1.1902)	
[2022-01-20 00:56:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1140/1251]	eta 0:04:04 lr 0.000844	time 2.4043 (2.1988)	loss 3.8675 (3.8245)	grad_norm 1.1458 (1.1899)	
[2022-01-20 00:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1150/1251]	eta 0:03:42 lr 0.000844	time 2.7845 (2.1997)	loss 3.6614 (3.8240)	grad_norm 1.1802 (1.1901)	
[2022-01-20 00:57:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1160/1251]	eta 0:03:20 lr 0.000844	time 2.0710 (2.1994)	loss 4.0100 (3.8218)	grad_norm 1.1193 (1.1894)	
[2022-01-20 00:57:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1170/1251]	eta 0:02:58 lr 0.000844	time 1.5872 (2.1990)	loss 3.5483 (3.8180)	grad_norm 1.0759 (1.1892)	
[2022-01-20 00:57:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1180/1251]	eta 0:02:36 lr 0.000844	time 1.9033 (2.1995)	loss 2.9599 (3.8177)	grad_norm 1.1320 (1.1886)	
[2022-01-20 00:58:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1190/1251]	eta 0:02:14 lr 0.000844	time 2.1859 (2.1995)	loss 3.6650 (3.8166)	grad_norm 1.1127 (1.1886)	
[2022-01-20 00:58:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1200/1251]	eta 0:01:52 lr 0.000844	time 2.4105 (2.1992)	loss 3.9540 (3.8149)	grad_norm 1.0415 (1.1893)	
[2022-01-20 00:58:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1210/1251]	eta 0:01:30 lr 0.000844	time 2.1172 (2.1987)	loss 4.0322 (3.8156)	grad_norm 0.9747 (1.1894)	
[2022-01-20 00:59:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1220/1251]	eta 0:01:08 lr 0.000844	time 1.5667 (2.1984)	loss 3.9860 (3.8151)	grad_norm 1.0323 (1.1889)	
[2022-01-20 00:59:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1230/1251]	eta 0:00:46 lr 0.000844	time 2.0276 (2.1977)	loss 4.3011 (3.8172)	grad_norm 1.1726 (1.1891)	
[2022-01-20 01:00:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1240/1251]	eta 0:00:24 lr 0.000844	time 1.9812 (2.1967)	loss 4.3226 (3.8165)	grad_norm 1.3037 (1.1888)	
[2022-01-20 01:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [77/300][1250/1251]	eta 0:00:02 lr 0.000844	time 1.3109 (2.1910)	loss 3.7844 (3.8179)	grad_norm 1.0955 (1.1884)	
[2022-01-20 01:00:16 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 77 training takes 0:45:41
[2022-01-20 01:00:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.864 (17.864)	Loss 1.1873 (1.1873)	Acc@1 71.094 (71.094)	Acc@5 90.918 (90.918)	
[2022-01-20 01:00:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.989 (3.356)	Loss 1.2174 (1.1788)	Acc@1 71.777 (72.656)	Acc@5 90.820 (91.575)	
[2022-01-20 01:01:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.626 (2.551)	Loss 1.2052 (1.1976)	Acc@1 72.070 (72.015)	Acc@5 91.016 (91.434)	
[2022-01-20 01:01:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.323 (2.216)	Loss 1.1758 (1.1868)	Acc@1 72.461 (72.212)	Acc@5 91.602 (91.561)	
[2022-01-20 01:01:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.074 (2.122)	Loss 1.2236 (1.1889)	Acc@1 70.410 (72.099)	Acc@5 89.551 (91.502)	
[2022-01-20 01:01:51 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.188 Acc@5 91.452
[2022-01-20 01:01:51 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.2%
[2022-01-20 01:01:51 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.53%
[2022-01-20 01:02:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][0/1251]	eta 7:41:30 lr 0.000844	time 22.1345 (22.1345)	loss 4.1198 (4.1198)	grad_norm 1.1999 (1.1999)	
[2022-01-20 01:02:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][10/1251]	eta 1:22:58 lr 0.000844	time 1.8711 (4.0115)	loss 4.5209 (4.1783)	grad_norm 1.0196 (1.2087)	
[2022-01-20 01:02:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][20/1251]	eta 1:04:50 lr 0.000844	time 1.5415 (3.1607)	loss 3.6322 (4.1156)	grad_norm 1.1740 (1.1719)	
[2022-01-20 01:03:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][30/1251]	eta 0:56:45 lr 0.000844	time 1.8836 (2.7894)	loss 4.2494 (3.9927)	grad_norm 1.4268 (1.1908)	
[2022-01-20 01:03:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][40/1251]	eta 0:55:00 lr 0.000844	time 5.5366 (2.7256)	loss 3.9989 (3.9809)	grad_norm 1.0531 (1.1854)	
[2022-01-20 01:04:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][50/1251]	eta 0:53:01 lr 0.000844	time 2.6073 (2.6492)	loss 2.7857 (3.8815)	grad_norm 1.4197 (1.1899)	
[2022-01-20 01:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][60/1251]	eta 0:50:58 lr 0.000844	time 1.4113 (2.5681)	loss 3.3283 (3.7995)	grad_norm 1.1567 (1.2049)	
[2022-01-20 01:04:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][70/1251]	eta 0:49:19 lr 0.000844	time 1.7357 (2.5055)	loss 3.9093 (3.7637)	grad_norm 1.1380 (1.2131)	
[2022-01-20 01:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][80/1251]	eta 0:48:04 lr 0.000844	time 2.8764 (2.4633)	loss 4.1376 (3.7748)	grad_norm 1.2682 (1.2064)	
[2022-01-20 01:05:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][90/1251]	eta 0:47:07 lr 0.000844	time 1.8985 (2.4356)	loss 2.7564 (3.7861)	grad_norm 1.0858 (1.2016)	
[2022-01-20 01:05:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][100/1251]	eta 0:46:03 lr 0.000844	time 2.1668 (2.4007)	loss 3.9941 (3.8129)	grad_norm 1.1136 (1.1937)	
[2022-01-20 01:06:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][110/1251]	eta 0:45:12 lr 0.000844	time 1.8800 (2.3773)	loss 4.2487 (3.8010)	grad_norm 1.0487 (1.1856)	
[2022-01-20 01:06:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][120/1251]	eta 0:44:44 lr 0.000843	time 2.4816 (2.3732)	loss 2.3367 (3.7989)	grad_norm 1.2206 (1.1839)	
[2022-01-20 01:07:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][130/1251]	eta 0:44:14 lr 0.000843	time 1.7725 (2.3684)	loss 4.0289 (3.8042)	grad_norm 1.0845 (1.1830)	
[2022-01-20 01:07:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][140/1251]	eta 0:43:37 lr 0.000843	time 2.9950 (2.3560)	loss 3.2240 (3.7971)	grad_norm 1.0512 (1.1776)	
[2022-01-20 01:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][150/1251]	eta 0:42:55 lr 0.000843	time 1.8032 (2.3392)	loss 3.1056 (3.7978)	grad_norm 1.0088 (1.1753)	
[2022-01-20 01:08:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][160/1251]	eta 0:42:17 lr 0.000843	time 1.9017 (2.3259)	loss 4.1329 (3.8197)	grad_norm 1.1728 (1.1800)	
[2022-01-20 01:08:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][170/1251]	eta 0:41:45 lr 0.000843	time 1.7689 (2.3181)	loss 3.4734 (3.8005)	grad_norm 1.3034 (1.1805)	
[2022-01-20 01:08:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][180/1251]	eta 0:41:08 lr 0.000843	time 2.7280 (2.3047)	loss 4.0033 (3.7941)	grad_norm 1.3606 (1.1828)	
[2022-01-20 01:09:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][190/1251]	eta 0:40:34 lr 0.000843	time 2.3954 (2.2945)	loss 2.8377 (3.7587)	grad_norm 1.2078 (1.1907)	
[2022-01-20 01:09:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][200/1251]	eta 0:40:05 lr 0.000843	time 2.0895 (2.2890)	loss 4.3066 (3.7640)	grad_norm 1.1956 (1.1901)	
[2022-01-20 01:09:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][210/1251]	eta 0:39:42 lr 0.000843	time 2.0762 (2.2882)	loss 3.7295 (3.7623)	grad_norm 1.0648 (1.1908)	
[2022-01-20 01:10:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][220/1251]	eta 0:39:21 lr 0.000843	time 2.1615 (2.2908)	loss 2.8934 (3.7656)	grad_norm 1.2660 (1.1911)	
[2022-01-20 01:10:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][230/1251]	eta 0:38:56 lr 0.000843	time 2.8556 (2.2882)	loss 3.5845 (3.7681)	grad_norm 1.1175 (1.1913)	
[2022-01-20 01:10:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][240/1251]	eta 0:38:20 lr 0.000843	time 2.5022 (2.2752)	loss 4.1079 (3.7658)	grad_norm 1.3485 (1.1959)	
[2022-01-20 01:11:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][250/1251]	eta 0:37:47 lr 0.000843	time 1.8408 (2.2655)	loss 3.9497 (3.7595)	grad_norm 1.3074 (1.1982)	
[2022-01-20 01:11:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][260/1251]	eta 0:37:17 lr 0.000843	time 2.3632 (2.2582)	loss 3.9301 (3.7463)	grad_norm 1.0628 (1.1985)	
[2022-01-20 01:12:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][270/1251]	eta 0:36:52 lr 0.000843	time 2.0269 (2.2553)	loss 4.1466 (3.7568)	grad_norm 0.9875 (1.1987)	
[2022-01-20 01:12:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][280/1251]	eta 0:36:32 lr 0.000843	time 2.9134 (2.2578)	loss 4.2661 (3.7620)	grad_norm 1.0839 (1.1981)	
[2022-01-20 01:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][290/1251]	eta 0:36:10 lr 0.000843	time 2.0761 (2.2581)	loss 3.8815 (3.7610)	grad_norm 1.3043 (1.2009)	
[2022-01-20 01:13:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][300/1251]	eta 0:35:51 lr 0.000843	time 2.5812 (2.2626)	loss 2.7453 (3.7612)	grad_norm 1.3028 (1.2021)	
[2022-01-20 01:13:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][310/1251]	eta 0:35:24 lr 0.000843	time 1.8361 (2.2577)	loss 3.4921 (3.7595)	grad_norm 1.0677 (1.1998)	
[2022-01-20 01:13:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][320/1251]	eta 0:34:57 lr 0.000843	time 1.8382 (2.2532)	loss 4.8151 (3.7571)	grad_norm 1.1831 (1.1974)	
[2022-01-20 01:14:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][330/1251]	eta 0:34:28 lr 0.000843	time 1.9414 (2.2455)	loss 3.6590 (3.7477)	grad_norm 1.1703 (1.1959)	
[2022-01-20 01:14:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][340/1251]	eta 0:34:00 lr 0.000843	time 2.2260 (2.2403)	loss 4.1223 (3.7449)	grad_norm 1.0987 (1.1943)	
[2022-01-20 01:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][350/1251]	eta 0:33:35 lr 0.000843	time 2.1811 (2.2366)	loss 2.9512 (3.7498)	grad_norm 1.2226 (1.1941)	
[2022-01-20 01:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][360/1251]	eta 0:33:17 lr 0.000843	time 2.3313 (2.2421)	loss 3.2198 (3.7523)	grad_norm 1.1397 (1.1936)	
[2022-01-20 01:15:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][370/1251]	eta 0:32:54 lr 0.000843	time 2.0880 (2.2408)	loss 4.0516 (3.7614)	grad_norm 1.1000 (1.1942)	
[2022-01-20 01:16:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][380/1251]	eta 0:32:35 lr 0.000843	time 2.2380 (2.2447)	loss 3.7326 (3.7599)	grad_norm 1.1792 (1.1931)	
[2022-01-20 01:16:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][390/1251]	eta 0:32:11 lr 0.000843	time 1.9673 (2.2433)	loss 3.2865 (3.7589)	grad_norm 1.0575 (1.1941)	
[2022-01-20 01:16:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][400/1251]	eta 0:31:43 lr 0.000843	time 2.5109 (2.2369)	loss 4.5316 (3.7591)	grad_norm 1.1661 (1.1955)	
[2022-01-20 01:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][410/1251]	eta 0:31:18 lr 0.000843	time 2.2565 (2.2331)	loss 4.2883 (3.7625)	grad_norm 1.0422 (1.1938)	
[2022-01-20 01:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][420/1251]	eta 0:30:53 lr 0.000843	time 2.1548 (2.2310)	loss 3.8829 (3.7682)	grad_norm 1.0754 (1.1918)	
[2022-01-20 01:17:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][430/1251]	eta 0:30:27 lr 0.000843	time 2.2636 (2.2263)	loss 4.2747 (3.7653)	grad_norm 1.0984 (1.1900)	
[2022-01-20 01:18:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][440/1251]	eta 0:30:03 lr 0.000843	time 1.9383 (2.2236)	loss 3.9781 (3.7656)	grad_norm 1.1951 (1.1931)	
[2022-01-20 01:18:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][450/1251]	eta 0:29:41 lr 0.000842	time 2.1825 (2.2238)	loss 4.3642 (3.7630)	grad_norm 1.1260 (1.1914)	
[2022-01-20 01:18:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][460/1251]	eta 0:29:16 lr 0.000842	time 1.7122 (2.2200)	loss 3.3808 (3.7634)	grad_norm 1.0345 (1.1912)	
[2022-01-20 01:19:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][470/1251]	eta 0:28:52 lr 0.000842	time 2.2378 (2.2179)	loss 3.5231 (3.7605)	grad_norm 1.3639 (1.1907)	
[2022-01-20 01:19:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][480/1251]	eta 0:28:31 lr 0.000842	time 2.3162 (2.2203)	loss 4.4142 (3.7611)	grad_norm 1.4485 (1.1906)	
[2022-01-20 01:20:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][490/1251]	eta 0:28:10 lr 0.000842	time 1.9047 (2.2211)	loss 2.6816 (3.7638)	grad_norm 1.1466 (1.1911)	
[2022-01-20 01:20:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][500/1251]	eta 0:27:48 lr 0.000842	time 2.1819 (2.2220)	loss 4.4605 (3.7690)	grad_norm 1.2001 (1.1927)	
[2022-01-20 01:20:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][510/1251]	eta 0:27:27 lr 0.000842	time 2.4575 (2.2236)	loss 3.2719 (3.7706)	grad_norm 1.0808 (1.1907)	
[2022-01-20 01:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][520/1251]	eta 0:27:04 lr 0.000842	time 2.1547 (2.2228)	loss 4.7502 (3.7703)	grad_norm 1.0955 (1.1906)	
[2022-01-20 01:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][530/1251]	eta 0:26:40 lr 0.000842	time 2.2372 (2.2198)	loss 3.9869 (3.7675)	grad_norm 1.1781 (1.1898)	
[2022-01-20 01:21:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][540/1251]	eta 0:26:15 lr 0.000842	time 1.5658 (2.2159)	loss 4.2451 (3.7739)	grad_norm 1.3625 (1.1920)	
[2022-01-20 01:22:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][550/1251]	eta 0:25:52 lr 0.000842	time 2.2919 (2.2149)	loss 3.5658 (3.7658)	grad_norm 1.1923 (1.1920)	
[2022-01-20 01:22:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][560/1251]	eta 0:25:30 lr 0.000842	time 2.7955 (2.2146)	loss 3.0235 (3.7640)	grad_norm 1.2225 (1.1919)	
[2022-01-20 01:22:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][570/1251]	eta 0:25:10 lr 0.000842	time 2.7803 (2.2188)	loss 4.2787 (3.7639)	grad_norm 1.3281 (1.1921)	
[2022-01-20 01:23:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][580/1251]	eta 0:24:48 lr 0.000842	time 1.8866 (2.2185)	loss 3.0180 (3.7663)	grad_norm 1.0790 (1.1909)	
[2022-01-20 01:23:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][590/1251]	eta 0:24:25 lr 0.000842	time 1.8676 (2.2168)	loss 3.2870 (3.7673)	grad_norm 1.0863 (1.1910)	
[2022-01-20 01:24:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][600/1251]	eta 0:24:00 lr 0.000842	time 2.0553 (2.2124)	loss 2.8387 (3.7604)	grad_norm 1.3037 (1.1924)	
[2022-01-20 01:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][610/1251]	eta 0:23:37 lr 0.000842	time 1.8545 (2.2118)	loss 3.2242 (3.7570)	grad_norm 1.2495 (1.1914)	
[2022-01-20 01:24:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][620/1251]	eta 0:23:16 lr 0.000842	time 1.8393 (2.2132)	loss 4.5988 (3.7590)	grad_norm 1.2947 (1.1907)	
[2022-01-20 01:25:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][630/1251]	eta 0:22:54 lr 0.000842	time 1.9506 (2.2128)	loss 4.2635 (3.7558)	grad_norm 1.3834 (1.1907)	
[2022-01-20 01:25:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][640/1251]	eta 0:22:32 lr 0.000842	time 2.1845 (2.2141)	loss 3.3757 (3.7531)	grad_norm 1.0469 (1.1906)	
[2022-01-20 01:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][650/1251]	eta 0:22:10 lr 0.000842	time 1.8870 (2.2136)	loss 4.0556 (3.7571)	grad_norm 1.2442 (1.1905)	
[2022-01-20 01:26:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][660/1251]	eta 0:21:47 lr 0.000842	time 2.6696 (2.2120)	loss 2.6162 (3.7542)	grad_norm 1.2445 (1.1903)	
[2022-01-20 01:26:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][670/1251]	eta 0:21:22 lr 0.000842	time 1.8544 (2.2079)	loss 4.6710 (3.7584)	grad_norm 1.1280 (1.1902)	
[2022-01-20 01:26:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][680/1251]	eta 0:21:00 lr 0.000842	time 2.6715 (2.2076)	loss 3.6698 (3.7623)	grad_norm 1.0861 (1.1902)	
[2022-01-20 01:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][690/1251]	eta 0:20:38 lr 0.000842	time 1.5763 (2.2075)	loss 4.6454 (3.7627)	grad_norm 1.2277 (1.1896)	
[2022-01-20 01:27:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][700/1251]	eta 0:20:17 lr 0.000842	time 2.4656 (2.2102)	loss 4.1124 (3.7635)	grad_norm 1.2454 (1.1901)	
[2022-01-20 01:28:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][710/1251]	eta 0:19:54 lr 0.000842	time 2.0726 (2.2085)	loss 4.3941 (3.7666)	grad_norm 1.2698 (1.1910)	
[2022-01-20 01:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][720/1251]	eta 0:19:33 lr 0.000842	time 2.9190 (2.2094)	loss 3.5466 (3.7660)	grad_norm 1.1623 (1.1908)	
[2022-01-20 01:28:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][730/1251]	eta 0:19:10 lr 0.000842	time 1.9276 (2.2086)	loss 3.7221 (3.7671)	grad_norm 1.2779 (1.1901)	
[2022-01-20 01:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][740/1251]	eta 0:18:48 lr 0.000842	time 2.0393 (2.2085)	loss 4.4537 (3.7655)	grad_norm 1.2482 (1.1902)	
[2022-01-20 01:29:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][750/1251]	eta 0:18:26 lr 0.000842	time 2.0610 (2.2080)	loss 3.8665 (3.7688)	grad_norm 1.4019 (1.1910)	
[2022-01-20 01:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][760/1251]	eta 0:18:04 lr 0.000842	time 3.1155 (2.2090)	loss 3.4682 (3.7690)	grad_norm 1.2178 (1.1914)	
[2022-01-20 01:30:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][770/1251]	eta 0:17:41 lr 0.000842	time 1.8083 (2.2074)	loss 4.1876 (3.7698)	grad_norm 1.2720 (1.1909)	
[2022-01-20 01:30:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][780/1251]	eta 0:17:18 lr 0.000841	time 2.5414 (2.2054)	loss 4.2538 (3.7720)	grad_norm 1.1861 (1.1916)	
[2022-01-20 01:30:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][790/1251]	eta 0:16:56 lr 0.000841	time 1.9840 (2.2046)	loss 4.1378 (3.7736)	grad_norm 1.2326 (1.1911)	
[2022-01-20 01:31:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][800/1251]	eta 0:16:34 lr 0.000841	time 2.7793 (2.2047)	loss 2.7729 (3.7763)	grad_norm 1.0250 (1.1904)	
[2022-01-20 01:31:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][810/1251]	eta 0:16:11 lr 0.000841	time 1.6883 (2.2024)	loss 2.4494 (3.7755)	grad_norm 1.2068 (1.1904)	
[2022-01-20 01:31:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][820/1251]	eta 0:15:49 lr 0.000841	time 2.1817 (2.2025)	loss 3.0162 (3.7767)	grad_norm 1.2918 (1.1925)	
[2022-01-20 01:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][830/1251]	eta 0:15:26 lr 0.000841	time 2.1623 (2.2017)	loss 4.5769 (3.7782)	grad_norm 1.1599 (1.1924)	
[2022-01-20 01:32:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][840/1251]	eta 0:15:04 lr 0.000841	time 2.2992 (2.2017)	loss 3.1609 (3.7738)	grad_norm 1.1581 (1.1919)	
[2022-01-20 01:33:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][850/1251]	eta 0:14:42 lr 0.000841	time 1.7569 (2.2019)	loss 3.6894 (3.7736)	grad_norm 1.1325 (1.1929)	
[2022-01-20 01:33:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][860/1251]	eta 0:14:21 lr 0.000841	time 2.4272 (2.2035)	loss 4.0507 (3.7796)	grad_norm 1.1361 (1.1928)	
[2022-01-20 01:33:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][870/1251]	eta 0:13:58 lr 0.000841	time 1.8928 (2.2020)	loss 4.7087 (3.7806)	grad_norm 1.0731 (1.1925)	
[2022-01-20 01:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][880/1251]	eta 0:13:36 lr 0.000841	time 1.7177 (2.2011)	loss 3.4316 (3.7812)	grad_norm 1.2806 (1.1926)	
[2022-01-20 01:34:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][890/1251]	eta 0:13:15 lr 0.000841	time 1.9820 (2.2035)	loss 3.8307 (3.7841)	grad_norm 1.1494 (1.1926)	
[2022-01-20 01:34:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][900/1251]	eta 0:12:53 lr 0.000841	time 1.9589 (2.2037)	loss 3.6676 (3.7832)	grad_norm 1.0341 (1.1926)	
[2022-01-20 01:35:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][910/1251]	eta 0:12:30 lr 0.000841	time 1.5122 (2.2008)	loss 4.2365 (3.7851)	grad_norm 1.3970 (1.1922)	
[2022-01-20 01:35:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][920/1251]	eta 0:12:08 lr 0.000841	time 1.5026 (2.1994)	loss 3.9819 (3.7854)	grad_norm 1.1603 (1.1913)	
[2022-01-20 01:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][930/1251]	eta 0:11:46 lr 0.000841	time 2.0195 (2.1995)	loss 3.7355 (3.7868)	grad_norm 1.3355 (1.1920)	
[2022-01-20 01:36:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][940/1251]	eta 0:11:24 lr 0.000841	time 2.5820 (2.1999)	loss 4.3248 (3.7883)	grad_norm 1.1236 (1.1916)	
[2022-01-20 01:36:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][950/1251]	eta 0:11:02 lr 0.000841	time 1.9335 (2.2002)	loss 3.9299 (3.7877)	grad_norm 1.1403 (1.1914)	
[2022-01-20 01:37:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][960/1251]	eta 0:10:40 lr 0.000841	time 1.8731 (2.2006)	loss 3.3467 (3.7880)	grad_norm 0.9498 (1.1912)	
[2022-01-20 01:37:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][970/1251]	eta 0:10:18 lr 0.000841	time 2.1688 (2.2001)	loss 4.0596 (3.7908)	grad_norm 1.1089 (1.1908)	
[2022-01-20 01:37:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][980/1251]	eta 0:09:55 lr 0.000841	time 1.8778 (2.1986)	loss 3.2526 (3.7926)	grad_norm 1.0391 (1.1909)	
[2022-01-20 01:38:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][990/1251]	eta 0:09:33 lr 0.000841	time 1.9371 (2.1975)	loss 4.0809 (3.7958)	grad_norm 1.2259 (1.1905)	
[2022-01-20 01:38:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1000/1251]	eta 0:09:11 lr 0.000841	time 1.5369 (2.1963)	loss 2.4741 (3.7923)	grad_norm 1.0596 (1.1900)	
[2022-01-20 01:38:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1010/1251]	eta 0:08:49 lr 0.000841	time 2.3799 (2.1963)	loss 4.4440 (3.7912)	grad_norm 1.1391 (1.1898)	
[2022-01-20 01:39:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1020/1251]	eta 0:08:27 lr 0.000841	time 1.9226 (2.1963)	loss 2.6841 (3.7907)	grad_norm 1.1233 (1.1894)	
[2022-01-20 01:39:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1030/1251]	eta 0:08:05 lr 0.000841	time 2.5919 (2.1964)	loss 3.8341 (3.7926)	grad_norm 1.3069 (1.1888)	
[2022-01-20 01:39:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1040/1251]	eta 0:07:43 lr 0.000841	time 2.0490 (2.1969)	loss 3.5138 (3.7936)	grad_norm 1.1159 (1.1883)	
[2022-01-20 01:40:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1050/1251]	eta 0:07:21 lr 0.000841	time 2.1538 (2.1969)	loss 3.8820 (3.7962)	grad_norm 1.2657 (1.1879)	
[2022-01-20 01:40:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1060/1251]	eta 0:06:59 lr 0.000841	time 1.7031 (2.1964)	loss 3.5610 (3.7983)	grad_norm 1.3346 (1.1883)	
[2022-01-20 01:41:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1070/1251]	eta 0:06:37 lr 0.000841	time 3.1880 (2.1987)	loss 3.6571 (3.7986)	grad_norm 1.1850 (1.1882)	
[2022-01-20 01:41:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1080/1251]	eta 0:06:15 lr 0.000841	time 2.5721 (2.1988)	loss 3.7230 (3.7971)	grad_norm 1.1459 (1.1883)	
[2022-01-20 01:41:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1090/1251]	eta 0:05:53 lr 0.000841	time 2.0088 (2.1975)	loss 3.4876 (3.7963)	grad_norm 1.3341 (1.1885)	
[2022-01-20 01:42:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1100/1251]	eta 0:05:31 lr 0.000841	time 1.6021 (2.1962)	loss 2.8759 (3.7963)	grad_norm 1.1749 (1.1888)	
[2022-01-20 01:42:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1110/1251]	eta 0:05:09 lr 0.000840	time 1.8257 (2.1947)	loss 4.3231 (3.7994)	grad_norm 1.1141 (1.1880)	
[2022-01-20 01:42:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1120/1251]	eta 0:04:47 lr 0.000840	time 3.0379 (2.1953)	loss 4.4606 (3.8004)	grad_norm 1.1606 (1.1875)	
[2022-01-20 01:43:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1130/1251]	eta 0:04:25 lr 0.000840	time 1.8640 (2.1944)	loss 2.6157 (3.7996)	grad_norm 1.3217 (1.1877)	
[2022-01-20 01:43:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1140/1251]	eta 0:04:03 lr 0.000840	time 1.5317 (2.1945)	loss 3.9500 (3.7991)	grad_norm 1.1318 (1.1874)	
[2022-01-20 01:43:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1150/1251]	eta 0:03:41 lr 0.000840	time 1.8965 (2.1948)	loss 3.9012 (3.7995)	grad_norm 1.0698 (1.1870)	
[2022-01-20 01:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1160/1251]	eta 0:03:19 lr 0.000840	time 2.5385 (2.1963)	loss 4.1163 (3.7984)	grad_norm 1.1175 (1.1865)	
[2022-01-20 01:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1170/1251]	eta 0:02:57 lr 0.000840	time 1.8865 (2.1961)	loss 4.1587 (3.7997)	grad_norm 0.9611 (1.1857)	
[2022-01-20 01:45:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1180/1251]	eta 0:02:35 lr 0.000840	time 2.6154 (2.1955)	loss 3.1868 (3.8009)	grad_norm 1.1252 (1.1859)	
[2022-01-20 01:45:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1190/1251]	eta 0:02:13 lr 0.000840	time 1.8514 (2.1957)	loss 3.5193 (3.8008)	grad_norm 0.9563 (1.1860)	
[2022-01-20 01:45:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1200/1251]	eta 0:01:51 lr 0.000840	time 2.5900 (2.1958)	loss 4.9208 (3.8017)	grad_norm 1.1498 (1.1859)	
[2022-01-20 01:46:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1210/1251]	eta 0:01:30 lr 0.000840	time 1.9877 (2.1953)	loss 3.2226 (3.8013)	grad_norm 1.1183 (1.1859)	
[2022-01-20 01:46:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1220/1251]	eta 0:01:08 lr 0.000840	time 1.8735 (2.1946)	loss 4.1185 (3.8009)	grad_norm 1.1025 (1.1857)	
[2022-01-20 01:46:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1230/1251]	eta 0:00:46 lr 0.000840	time 2.1038 (2.1945)	loss 3.5060 (3.8016)	grad_norm 1.1524 (1.1855)	
[2022-01-20 01:47:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1240/1251]	eta 0:00:24 lr 0.000840	time 1.8994 (2.1933)	loss 4.0791 (3.8006)	grad_norm 1.0477 (1.1858)	
[2022-01-20 01:47:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [78/300][1250/1251]	eta 0:00:02 lr 0.000840	time 1.2082 (2.1876)	loss 4.1262 (3.7998)	grad_norm 1.4235 (1.1856)	
[2022-01-20 01:47:28 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 78 training takes 0:45:37
[2022-01-20 01:47:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.261 (18.261)	Loss 1.0615 (1.0615)	Acc@1 73.535 (73.535)	Acc@5 92.773 (92.773)	
[2022-01-20 01:48:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.572 (3.529)	Loss 1.1308 (1.1488)	Acc@1 73.535 (72.514)	Acc@5 92.871 (91.744)	
[2022-01-20 01:48:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.622 (2.581)	Loss 1.1160 (1.1607)	Acc@1 73.633 (72.638)	Acc@5 92.090 (91.336)	
[2022-01-20 01:48:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.921 (2.318)	Loss 1.0405 (1.1607)	Acc@1 75.879 (72.713)	Acc@5 92.480 (91.343)	
[2022-01-20 01:48:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.946 (2.159)	Loss 1.1459 (1.1638)	Acc@1 72.363 (72.559)	Acc@5 92.578 (91.316)	
[2022-01-20 01:49:03 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.590 Acc@5 91.364
[2022-01-20 01:49:03 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.6%
[2022-01-20 01:49:03 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.59%
[2022-01-20 01:49:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][0/1251]	eta 7:45:07 lr 0.000840	time 22.3079 (22.3079)	loss 3.0877 (3.0877)	grad_norm 1.4405 (1.4405)	
[2022-01-20 01:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][10/1251]	eta 1:25:05 lr 0.000840	time 2.1677 (4.1136)	loss 2.7692 (3.8081)	grad_norm 1.4923 (1.2000)	
[2022-01-20 01:50:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][20/1251]	eta 1:04:56 lr 0.000840	time 1.3089 (3.1653)	loss 3.8385 (3.7640)	grad_norm 1.1980 (1.1856)	
[2022-01-20 01:50:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][30/1251]	eta 0:57:54 lr 0.000840	time 1.9815 (2.8458)	loss 4.3920 (3.8690)	grad_norm 1.0568 (1.1867)	
[2022-01-20 01:50:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][40/1251]	eta 0:55:10 lr 0.000840	time 3.7795 (2.7339)	loss 4.2418 (3.8185)	grad_norm 1.1812 (1.1871)	
[2022-01-20 01:51:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][50/1251]	eta 0:53:54 lr 0.000840	time 2.6780 (2.6932)	loss 2.5503 (3.7576)	grad_norm 1.2689 (1.1797)	
[2022-01-20 01:51:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][60/1251]	eta 0:51:44 lr 0.000840	time 1.3084 (2.6068)	loss 3.9367 (3.7459)	grad_norm 1.2994 (1.1895)	
[2022-01-20 01:52:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][70/1251]	eta 0:49:59 lr 0.000840	time 1.7975 (2.5401)	loss 4.0973 (3.7201)	grad_norm 1.1156 (1.1906)	
[2022-01-20 01:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][80/1251]	eta 0:48:59 lr 0.000840	time 3.4131 (2.5104)	loss 3.8512 (3.7199)	grad_norm 1.2215 (1.1827)	
[2022-01-20 01:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][90/1251]	eta 0:47:44 lr 0.000840	time 1.5250 (2.4676)	loss 3.9044 (3.7117)	grad_norm 1.1744 (1.2016)	
[2022-01-20 01:53:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][100/1251]	eta 0:46:40 lr 0.000840	time 1.8058 (2.4333)	loss 3.5443 (3.7109)	grad_norm 1.1129 (1.2073)	
[2022-01-20 01:53:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][110/1251]	eta 0:45:54 lr 0.000840	time 2.4339 (2.4139)	loss 4.0991 (3.7169)	grad_norm 1.0828 (1.2031)	
[2022-01-20 01:53:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][120/1251]	eta 0:45:09 lr 0.000840	time 2.2078 (2.3959)	loss 3.7290 (3.7207)	grad_norm 1.2154 (1.1991)	
[2022-01-20 01:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][130/1251]	eta 0:44:19 lr 0.000840	time 1.6217 (2.3723)	loss 4.5033 (3.7426)	grad_norm 1.1626 (1.1934)	
[2022-01-20 01:54:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][140/1251]	eta 0:43:30 lr 0.000840	time 1.9070 (2.3493)	loss 2.7730 (3.7308)	grad_norm 1.5296 (1.1949)	
[2022-01-20 01:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][150/1251]	eta 0:43:00 lr 0.000840	time 2.2514 (2.3436)	loss 3.9705 (3.7381)	grad_norm 1.2603 (1.2017)	
[2022-01-20 01:55:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][160/1251]	eta 0:42:21 lr 0.000840	time 1.9586 (2.3293)	loss 3.7644 (3.7523)	grad_norm 1.0665 (1.1983)	
[2022-01-20 01:55:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][170/1251]	eta 0:41:46 lr 0.000840	time 2.2600 (2.3182)	loss 3.2224 (3.7519)	grad_norm 1.3999 (1.2013)	
[2022-01-20 01:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][180/1251]	eta 0:41:21 lr 0.000840	time 3.0670 (2.3166)	loss 4.1632 (3.7626)	grad_norm 1.2216 (1.1963)	
[2022-01-20 01:56:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][190/1251]	eta 0:40:52 lr 0.000839	time 2.5454 (2.3115)	loss 4.5072 (3.7621)	grad_norm 0.9972 (1.1953)	
[2022-01-20 01:56:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][200/1251]	eta 0:40:19 lr 0.000839	time 2.1776 (2.3023)	loss 3.7638 (3.7678)	grad_norm 1.0436 (1.1929)	
[2022-01-20 01:57:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][210/1251]	eta 0:39:48 lr 0.000839	time 2.1904 (2.2940)	loss 4.5183 (3.7701)	grad_norm 1.1287 (1.1928)	
[2022-01-20 01:57:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][220/1251]	eta 0:39:16 lr 0.000839	time 2.3255 (2.2859)	loss 2.7672 (3.7724)	grad_norm 1.3772 (1.1940)	
[2022-01-20 01:57:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][230/1251]	eta 0:38:55 lr 0.000839	time 2.6834 (2.2874)	loss 2.9449 (3.7674)	grad_norm 1.4721 (1.1953)	
[2022-01-20 01:58:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][240/1251]	eta 0:38:21 lr 0.000839	time 2.5433 (2.2768)	loss 3.9806 (3.7660)	grad_norm 1.1278 (1.1947)	
[2022-01-20 01:58:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][250/1251]	eta 0:37:53 lr 0.000839	time 2.7439 (2.2710)	loss 2.5765 (3.7591)	grad_norm 1.3502 (1.1955)	
[2022-01-20 01:58:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][260/1251]	eta 0:37:23 lr 0.000839	time 1.9768 (2.2638)	loss 4.2053 (3.7550)	grad_norm 1.1053 (1.1946)	
[2022-01-20 01:59:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][270/1251]	eta 0:37:01 lr 0.000839	time 2.1279 (2.2643)	loss 3.7272 (3.7654)	grad_norm 1.2500 (1.1924)	
[2022-01-20 01:59:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][280/1251]	eta 0:36:44 lr 0.000839	time 3.3445 (2.2698)	loss 3.5694 (3.7619)	grad_norm 1.0519 (1.1931)	
[2022-01-20 02:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][290/1251]	eta 0:36:23 lr 0.000839	time 3.0596 (2.2716)	loss 4.6475 (3.7636)	grad_norm 1.5271 (1.1953)	
[2022-01-20 02:00:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][300/1251]	eta 0:35:52 lr 0.000839	time 1.8812 (2.2637)	loss 3.7128 (3.7681)	grad_norm 1.0809 (1.1954)	
[2022-01-20 02:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][310/1251]	eta 0:35:21 lr 0.000839	time 1.7425 (2.2544)	loss 2.8182 (3.7734)	grad_norm 1.3082 (1.1940)	
[2022-01-20 02:01:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][320/1251]	eta 0:34:53 lr 0.000839	time 2.1343 (2.2483)	loss 4.3412 (3.7665)	grad_norm 1.1028 (1.1915)	
[2022-01-20 02:01:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][330/1251]	eta 0:34:30 lr 0.000839	time 3.0904 (2.2483)	loss 4.3565 (3.7714)	grad_norm 1.2217 (1.1898)	
[2022-01-20 02:01:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][340/1251]	eta 0:34:10 lr 0.000839	time 2.2978 (2.2505)	loss 3.3087 (3.7674)	grad_norm 1.0460 (1.1885)	
[2022-01-20 02:02:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][350/1251]	eta 0:33:45 lr 0.000839	time 2.1776 (2.2483)	loss 4.1686 (3.7668)	grad_norm 1.1572 (1.1885)	
[2022-01-20 02:02:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][360/1251]	eta 0:33:22 lr 0.000839	time 2.0875 (2.2475)	loss 4.6705 (3.7732)	grad_norm 1.0229 (1.1881)	
[2022-01-20 02:02:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][370/1251]	eta 0:33:00 lr 0.000839	time 3.2828 (2.2477)	loss 4.1006 (3.7739)	grad_norm 1.2002 (1.1893)	
[2022-01-20 02:03:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][380/1251]	eta 0:32:34 lr 0.000839	time 1.6173 (2.2438)	loss 4.1773 (3.7710)	grad_norm 1.0775 (1.1879)	
[2022-01-20 02:03:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][390/1251]	eta 0:32:09 lr 0.000839	time 1.9048 (2.2409)	loss 3.3880 (3.7748)	grad_norm 1.2266 (1.1863)	
[2022-01-20 02:04:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][400/1251]	eta 0:31:45 lr 0.000839	time 1.8217 (2.2396)	loss 3.0952 (3.7662)	grad_norm 1.2497 (1.1868)	
[2022-01-20 02:04:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][410/1251]	eta 0:31:20 lr 0.000839	time 2.6413 (2.2359)	loss 4.1331 (3.7751)	grad_norm 1.1022 (1.1872)	
[2022-01-20 02:04:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][420/1251]	eta 0:30:55 lr 0.000839	time 1.8969 (2.2327)	loss 4.5107 (3.7825)	grad_norm 1.1361 (1.1875)	
[2022-01-20 02:05:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][430/1251]	eta 0:30:29 lr 0.000839	time 1.6474 (2.2280)	loss 4.2198 (3.7888)	grad_norm 1.1975 (1.1866)	
[2022-01-20 02:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][440/1251]	eta 0:30:06 lr 0.000839	time 2.1742 (2.2279)	loss 3.4301 (3.7916)	grad_norm 1.1509 (1.1871)	
[2022-01-20 02:05:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][450/1251]	eta 0:29:44 lr 0.000839	time 2.8984 (2.2283)	loss 4.6047 (3.7906)	grad_norm 1.2352 (1.1874)	
[2022-01-20 02:06:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][460/1251]	eta 0:29:20 lr 0.000839	time 1.7790 (2.2263)	loss 3.7778 (3.7894)	grad_norm 1.4264 (1.1872)	
[2022-01-20 02:06:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][470/1251]	eta 0:28:57 lr 0.000839	time 2.0452 (2.2243)	loss 2.9312 (3.7879)	grad_norm 1.2861 (1.1867)	
[2022-01-20 02:06:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][480/1251]	eta 0:28:34 lr 0.000839	time 1.5859 (2.2239)	loss 2.5869 (3.7889)	grad_norm 1.2404 (1.1861)	
[2022-01-20 02:07:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][490/1251]	eta 0:28:13 lr 0.000839	time 3.0087 (2.2259)	loss 4.1607 (3.7910)	grad_norm 1.0715 (1.1859)	
[2022-01-20 02:07:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][500/1251]	eta 0:27:52 lr 0.000839	time 1.5170 (2.2272)	loss 3.3586 (3.7879)	grad_norm 1.0166 (1.1868)	
[2022-01-20 02:08:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][510/1251]	eta 0:27:30 lr 0.000838	time 1.7662 (2.2277)	loss 3.3875 (3.7854)	grad_norm 1.0126 (1.1859)	
[2022-01-20 02:08:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][520/1251]	eta 0:27:07 lr 0.000838	time 1.7993 (2.2267)	loss 3.8944 (3.7860)	grad_norm 1.0969 (1.1863)	
[2022-01-20 02:08:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][530/1251]	eta 0:26:43 lr 0.000838	time 1.9102 (2.2236)	loss 3.1742 (3.7877)	grad_norm 1.3167 (1.1861)	
[2022-01-20 02:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][540/1251]	eta 0:26:19 lr 0.000838	time 1.8302 (2.2217)	loss 4.5434 (3.7910)	grad_norm 1.0639 (1.1857)	
[2022-01-20 02:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][550/1251]	eta 0:25:56 lr 0.000838	time 1.9982 (2.2206)	loss 4.4956 (3.7970)	grad_norm 1.1210 (1.1838)	
[2022-01-20 02:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][560/1251]	eta 0:25:33 lr 0.000838	time 2.1081 (2.2195)	loss 3.9227 (3.7996)	grad_norm 1.3920 (1.1848)	
[2022-01-20 02:10:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][570/1251]	eta 0:25:10 lr 0.000838	time 1.9469 (2.2174)	loss 4.0509 (3.7975)	grad_norm 1.4093 (1.1868)	
[2022-01-20 02:10:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][580/1251]	eta 0:24:48 lr 0.000838	time 1.9435 (2.2177)	loss 4.0055 (3.7998)	grad_norm 1.0714 (1.1871)	
[2022-01-20 02:10:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][590/1251]	eta 0:24:26 lr 0.000838	time 1.9253 (2.2191)	loss 4.5198 (3.8029)	grad_norm 1.2529 (1.1878)	
[2022-01-20 02:11:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][600/1251]	eta 0:24:04 lr 0.000838	time 2.1708 (2.2187)	loss 3.3667 (3.8043)	grad_norm 1.1836 (1.1879)	
[2022-01-20 02:11:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][610/1251]	eta 0:23:42 lr 0.000838	time 1.8372 (2.2186)	loss 4.8213 (3.8066)	grad_norm 1.0995 (1.1884)	
[2022-01-20 02:12:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][620/1251]	eta 0:23:18 lr 0.000838	time 2.0559 (2.2164)	loss 4.4692 (3.8088)	grad_norm 1.3905 (1.1892)	
[2022-01-20 02:12:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][630/1251]	eta 0:22:54 lr 0.000838	time 2.1651 (2.2135)	loss 4.4836 (3.8144)	grad_norm 1.0053 (1.1878)	
[2022-01-20 02:12:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][640/1251]	eta 0:22:29 lr 0.000838	time 2.2094 (2.2094)	loss 3.6532 (3.8141)	grad_norm 1.1389 (1.1872)	
[2022-01-20 02:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][650/1251]	eta 0:22:05 lr 0.000838	time 1.8622 (2.2053)	loss 3.5168 (3.8095)	grad_norm 1.0469 (1.1853)	
[2022-01-20 02:13:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][660/1251]	eta 0:21:41 lr 0.000838	time 2.2297 (2.2027)	loss 3.2385 (3.8080)	grad_norm 0.9954 (1.1849)	
[2022-01-20 02:13:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][670/1251]	eta 0:21:18 lr 0.000838	time 2.1546 (2.2004)	loss 4.2736 (3.8106)	grad_norm 1.1548 (1.1846)	
[2022-01-20 02:14:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][680/1251]	eta 0:20:59 lr 0.000838	time 3.8589 (2.2059)	loss 3.9471 (3.8125)	grad_norm 1.0136 (1.1851)	
[2022-01-20 02:14:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][690/1251]	eta 0:20:38 lr 0.000838	time 2.3770 (2.2074)	loss 4.1593 (3.8156)	grad_norm 1.3388 (1.1859)	
[2022-01-20 02:14:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][700/1251]	eta 0:20:16 lr 0.000838	time 2.6881 (2.2084)	loss 4.3064 (3.8120)	grad_norm 1.3139 (1.1863)	
[2022-01-20 02:15:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][710/1251]	eta 0:19:54 lr 0.000838	time 1.9610 (2.2074)	loss 3.2915 (3.8103)	grad_norm 1.1297 (1.1863)	
[2022-01-20 02:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][720/1251]	eta 0:19:32 lr 0.000838	time 2.0780 (2.2084)	loss 2.8797 (3.8112)	grad_norm 1.2547 (1.1868)	
[2022-01-20 02:15:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][730/1251]	eta 0:19:10 lr 0.000838	time 1.6119 (2.2074)	loss 3.8102 (3.8092)	grad_norm 1.4971 (1.1874)	
[2022-01-20 02:16:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][740/1251]	eta 0:18:48 lr 0.000838	time 2.8214 (2.2081)	loss 4.2712 (3.8105)	grad_norm 1.2731 (1.1867)	
[2022-01-20 02:16:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][750/1251]	eta 0:18:25 lr 0.000838	time 1.9131 (2.2071)	loss 3.4109 (3.8084)	grad_norm 1.2085 (1.1866)	
[2022-01-20 02:17:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][760/1251]	eta 0:18:03 lr 0.000838	time 2.1605 (2.2075)	loss 3.8799 (3.8109)	grad_norm 1.1847 (1.1867)	
[2022-01-20 02:17:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][770/1251]	eta 0:17:42 lr 0.000838	time 2.7421 (2.2097)	loss 4.2729 (3.8064)	grad_norm 1.0997 (1.1863)	
[2022-01-20 02:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][780/1251]	eta 0:17:20 lr 0.000838	time 1.6535 (2.2097)	loss 3.9536 (3.8041)	grad_norm 1.2428 (1.1874)	
[2022-01-20 02:18:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][790/1251]	eta 0:16:57 lr 0.000838	time 1.6576 (2.2063)	loss 4.7239 (3.8053)	grad_norm 1.0831 (1.1872)	
[2022-01-20 02:18:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][800/1251]	eta 0:16:33 lr 0.000838	time 1.9478 (2.2032)	loss 3.8779 (3.8021)	grad_norm 1.2141 (1.1867)	
[2022-01-20 02:18:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][810/1251]	eta 0:16:11 lr 0.000838	time 1.9115 (2.2026)	loss 3.9705 (3.8022)	grad_norm 0.9539 (1.1859)	
[2022-01-20 02:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][820/1251]	eta 0:15:48 lr 0.000838	time 1.7157 (2.2016)	loss 4.0207 (3.8041)	grad_norm 1.1725 (1.1860)	
[2022-01-20 02:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][830/1251]	eta 0:15:26 lr 0.000838	time 1.8912 (2.2013)	loss 4.2292 (3.8035)	grad_norm 1.2133 (1.1852)	
[2022-01-20 02:19:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][840/1251]	eta 0:15:05 lr 0.000837	time 2.7045 (2.2024)	loss 4.0344 (3.8050)	grad_norm 0.9656 (1.1846)	
[2022-01-20 02:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][850/1251]	eta 0:14:43 lr 0.000837	time 2.5100 (2.2035)	loss 3.8182 (3.8036)	grad_norm 1.1028 (1.1845)	
[2022-01-20 02:20:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][860/1251]	eta 0:14:21 lr 0.000837	time 1.8608 (2.2040)	loss 4.5025 (3.8040)	grad_norm 1.0817 (1.1843)	
[2022-01-20 02:21:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][870/1251]	eta 0:13:59 lr 0.000837	time 1.8961 (2.2033)	loss 4.0629 (3.8027)	grad_norm 1.0168 (1.1837)	
[2022-01-20 02:21:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][880/1251]	eta 0:13:37 lr 0.000837	time 1.8417 (2.2031)	loss 3.4951 (3.8002)	grad_norm 1.1767 (1.1841)	
[2022-01-20 02:21:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][890/1251]	eta 0:13:15 lr 0.000837	time 1.8667 (2.2033)	loss 3.8244 (3.7987)	grad_norm 0.9542 (1.1832)	
[2022-01-20 02:22:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][900/1251]	eta 0:12:53 lr 0.000837	time 2.2149 (2.2030)	loss 3.4587 (3.7979)	grad_norm 1.0013 (1.1835)	
[2022-01-20 02:22:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][910/1251]	eta 0:12:30 lr 0.000837	time 1.9037 (2.2015)	loss 3.3750 (3.7986)	grad_norm 1.2696 (1.1853)	
[2022-01-20 02:22:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][920/1251]	eta 0:12:08 lr 0.000837	time 1.6513 (2.2005)	loss 3.5189 (3.7984)	grad_norm 1.2433 (1.1860)	
[2022-01-20 02:23:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][930/1251]	eta 0:11:46 lr 0.000837	time 2.6559 (2.2003)	loss 2.8804 (3.7965)	grad_norm 1.0681 (1.1862)	
[2022-01-20 02:23:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][940/1251]	eta 0:11:24 lr 0.000837	time 1.7541 (2.1996)	loss 2.7598 (3.7939)	grad_norm 1.3546 (1.1865)	
[2022-01-20 02:23:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][950/1251]	eta 0:11:01 lr 0.000837	time 2.2681 (2.1990)	loss 4.0613 (3.7941)	grad_norm 1.2629 (1.1875)	
[2022-01-20 02:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][960/1251]	eta 0:10:39 lr 0.000837	time 1.9032 (2.1993)	loss 3.2532 (3.7940)	grad_norm 1.1837 (1.1877)	
[2022-01-20 02:24:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][970/1251]	eta 0:10:18 lr 0.000837	time 2.4498 (2.2014)	loss 4.0893 (3.7938)	grad_norm 1.0775 (1.1880)	
[2022-01-20 02:25:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][980/1251]	eta 0:09:56 lr 0.000837	time 2.4945 (2.2028)	loss 3.7932 (3.7945)	grad_norm 1.0585 (1.1870)	
[2022-01-20 02:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][990/1251]	eta 0:09:34 lr 0.000837	time 2.2038 (2.2024)	loss 4.4327 (3.7962)	grad_norm 1.1597 (1.1862)	
[2022-01-20 02:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1000/1251]	eta 0:09:12 lr 0.000837	time 1.8252 (2.2022)	loss 3.3780 (3.7966)	grad_norm 1.1121 (1.1854)	
[2022-01-20 02:26:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1010/1251]	eta 0:08:50 lr 0.000837	time 1.9489 (2.2014)	loss 3.8362 (3.7991)	grad_norm 1.1519 (1.1852)	
[2022-01-20 02:26:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1020/1251]	eta 0:08:28 lr 0.000837	time 2.4501 (2.2004)	loss 3.8548 (3.7964)	grad_norm 1.1215 (1.1851)	
[2022-01-20 02:26:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1030/1251]	eta 0:08:05 lr 0.000837	time 2.2629 (2.1983)	loss 3.8374 (3.7970)	grad_norm 1.1685 (1.1849)	
[2022-01-20 02:27:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1040/1251]	eta 0:07:43 lr 0.000837	time 2.3833 (2.1976)	loss 2.9461 (3.7960)	grad_norm 1.1283 (1.1841)	
[2022-01-20 02:27:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1050/1251]	eta 0:07:21 lr 0.000837	time 2.2343 (2.1969)	loss 4.3934 (3.7982)	grad_norm 1.2084 (1.1838)	
[2022-01-20 02:27:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1060/1251]	eta 0:06:59 lr 0.000837	time 2.2733 (2.1984)	loss 4.2086 (3.8009)	grad_norm 1.1634 (1.1834)	
[2022-01-20 02:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1070/1251]	eta 0:06:38 lr 0.000837	time 2.1325 (2.2000)	loss 3.4928 (3.7994)	grad_norm 0.9957 (1.1827)	
[2022-01-20 02:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1080/1251]	eta 0:06:16 lr 0.000837	time 1.9546 (2.1998)	loss 4.2584 (3.8012)	grad_norm 1.2855 (1.1836)	
[2022-01-20 02:29:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1090/1251]	eta 0:05:54 lr 0.000837	time 1.8886 (2.1990)	loss 4.2024 (3.8007)	grad_norm 1.2191 (1.1833)	
[2022-01-20 02:29:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1100/1251]	eta 0:05:32 lr 0.000837	time 1.9165 (2.1988)	loss 4.2763 (3.7987)	grad_norm 1.1080 (1.1836)	
[2022-01-20 02:29:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1110/1251]	eta 0:05:10 lr 0.000837	time 1.8233 (2.1991)	loss 4.3475 (3.7967)	grad_norm 1.1135 (1.1833)	
[2022-01-20 02:30:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1120/1251]	eta 0:04:48 lr 0.000837	time 2.2086 (2.1993)	loss 4.4815 (3.7971)	grad_norm 1.0375 (1.1827)	
[2022-01-20 02:30:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1130/1251]	eta 0:04:26 lr 0.000837	time 2.1904 (2.1991)	loss 4.2399 (3.7989)	grad_norm 1.0785 (1.1821)	
[2022-01-20 02:30:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1140/1251]	eta 0:04:04 lr 0.000837	time 2.1674 (2.1993)	loss 4.1640 (3.7991)	grad_norm 1.2173 (1.1823)	
[2022-01-20 02:31:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1150/1251]	eta 0:03:42 lr 0.000837	time 2.1091 (2.1990)	loss 4.1891 (3.8010)	grad_norm 1.3018 (1.1821)	
[2022-01-20 02:31:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1160/1251]	eta 0:03:20 lr 0.000836	time 2.0215 (2.1984)	loss 4.1085 (3.8014)	grad_norm 1.1449 (1.1826)	
[2022-01-20 02:31:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1170/1251]	eta 0:02:57 lr 0.000836	time 1.9391 (2.1974)	loss 3.0511 (3.8024)	grad_norm 0.9502 (1.1824)	
[2022-01-20 02:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1180/1251]	eta 0:02:35 lr 0.000836	time 2.6213 (2.1969)	loss 2.8115 (3.8012)	grad_norm 1.0439 (1.1822)	
[2022-01-20 02:32:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1190/1251]	eta 0:02:14 lr 0.000836	time 2.2392 (2.1973)	loss 3.7261 (3.8007)	grad_norm 1.1040 (1.1819)	
[2022-01-20 02:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1200/1251]	eta 0:01:51 lr 0.000836	time 1.8914 (2.1960)	loss 3.3188 (3.7994)	grad_norm 1.0716 (1.1821)	
[2022-01-20 02:33:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1210/1251]	eta 0:01:30 lr 0.000836	time 1.5786 (2.1960)	loss 2.7025 (3.7971)	grad_norm 1.1028 (1.1819)	
[2022-01-20 02:33:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1220/1251]	eta 0:01:08 lr 0.000836	time 2.2841 (2.1949)	loss 4.4770 (3.7970)	grad_norm 1.1803 (1.1819)	
[2022-01-20 02:34:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1230/1251]	eta 0:00:46 lr 0.000836	time 1.5954 (2.1937)	loss 3.3050 (3.7949)	grad_norm 1.2185 (1.1814)	
[2022-01-20 02:34:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1240/1251]	eta 0:00:24 lr 0.000836	time 1.4030 (2.1934)	loss 4.3660 (3.7944)	grad_norm 1.0133 (1.1811)	
[2022-01-20 02:34:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [79/300][1250/1251]	eta 0:00:02 lr 0.000836	time 1.1738 (2.1882)	loss 4.5753 (3.7942)	grad_norm 1.1140 (1.1805)	
[2022-01-20 02:34:41 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 79 training takes 0:45:37
[2022-01-20 02:35:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.287 (18.287)	Loss 1.1729 (1.1729)	Acc@1 73.730 (73.730)	Acc@5 92.090 (92.090)	
[2022-01-20 02:35:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.382 (3.605)	Loss 1.2164 (1.2235)	Acc@1 71.582 (72.479)	Acc@5 90.820 (91.211)	
[2022-01-20 02:35:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.244 (2.666)	Loss 1.2223 (1.2084)	Acc@1 72.168 (72.656)	Acc@5 90.625 (91.504)	
[2022-01-20 02:35:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.890 (2.355)	Loss 1.2437 (1.2116)	Acc@1 72.852 (72.571)	Acc@5 90.723 (91.469)	
[2022-01-20 02:36:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.955 (2.185)	Loss 1.1774 (1.2167)	Acc@1 73.438 (72.432)	Acc@5 93.164 (91.380)	
[2022-01-20 02:36:18 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.516 Acc@5 91.458
[2022-01-20 02:36:18 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.5%
[2022-01-20 02:36:18 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.59%
[2022-01-20 02:36:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][0/1251]	eta 7:33:07 lr 0.000836	time 21.7328 (21.7328)	loss 3.1691 (3.1691)	grad_norm 1.0197 (1.0197)	
[2022-01-20 02:37:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][10/1251]	eta 1:22:37 lr 0.000836	time 2.9624 (3.9949)	loss 4.4038 (3.6233)	grad_norm 1.0780 (1.1164)	
[2022-01-20 02:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][20/1251]	eta 1:02:59 lr 0.000836	time 1.7717 (3.0700)	loss 3.3501 (3.5944)	grad_norm 1.1690 (1.1275)	
[2022-01-20 02:37:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][30/1251]	eta 0:55:41 lr 0.000836	time 1.5899 (2.7364)	loss 3.2478 (3.6337)	grad_norm 1.1533 (1.1482)	
[2022-01-20 02:38:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][40/1251]	eta 0:53:52 lr 0.000836	time 3.8612 (2.6697)	loss 4.2400 (3.6776)	grad_norm 1.2462 (1.1979)	
[2022-01-20 02:38:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][50/1251]	eta 0:52:29 lr 0.000836	time 3.9372 (2.6220)	loss 3.9439 (3.6392)	grad_norm 1.1822 (1.1856)	
[2022-01-20 02:38:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][60/1251]	eta 0:51:06 lr 0.000836	time 2.6468 (2.5749)	loss 2.6333 (3.6684)	grad_norm 0.9607 (1.1896)	
[2022-01-20 02:39:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][70/1251]	eta 0:49:34 lr 0.000836	time 1.6654 (2.5189)	loss 4.0152 (3.6446)	grad_norm 1.2474 (1.2027)	
[2022-01-20 02:39:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][80/1251]	eta 0:48:40 lr 0.000836	time 3.7228 (2.4942)	loss 3.9486 (3.6810)	grad_norm 1.2547 (1.1989)	
[2022-01-20 02:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][90/1251]	eta 0:48:07 lr 0.000836	time 3.2511 (2.4875)	loss 4.5280 (3.7360)	grad_norm 1.1238 (1.1969)	
[2022-01-20 02:40:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][100/1251]	eta 0:47:05 lr 0.000836	time 1.9119 (2.4553)	loss 4.0365 (3.7581)	grad_norm 1.2637 (1.1997)	
[2022-01-20 02:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][110/1251]	eta 0:45:54 lr 0.000836	time 1.6658 (2.4141)	loss 4.0357 (3.7433)	grad_norm 1.0999 (1.2086)	
[2022-01-20 02:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][120/1251]	eta 0:45:11 lr 0.000836	time 3.1633 (2.3973)	loss 3.8851 (3.7616)	grad_norm 1.3167 (1.2117)	
[2022-01-20 02:41:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][130/1251]	eta 0:44:33 lr 0.000836	time 3.1358 (2.3848)	loss 4.1936 (3.7729)	grad_norm 0.9859 (1.2061)	
[2022-01-20 02:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][140/1251]	eta 0:43:54 lr 0.000836	time 2.2943 (2.3709)	loss 4.0988 (3.7705)	grad_norm 1.2939 (1.2023)	
[2022-01-20 02:42:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][150/1251]	eta 0:43:18 lr 0.000836	time 1.9124 (2.3603)	loss 3.7761 (3.7655)	grad_norm 1.1505 (1.1994)	
[2022-01-20 02:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][160/1251]	eta 0:42:48 lr 0.000836	time 3.2643 (2.3541)	loss 3.6873 (3.7672)	grad_norm 1.2901 (1.1977)	
[2022-01-20 02:42:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][170/1251]	eta 0:42:14 lr 0.000836	time 1.8545 (2.3445)	loss 4.3426 (3.7910)	grad_norm 1.2132 (1.1990)	
[2022-01-20 02:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][180/1251]	eta 0:41:33 lr 0.000836	time 1.9798 (2.3281)	loss 4.4223 (3.7899)	grad_norm 1.1482 (1.1954)	
[2022-01-20 02:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][190/1251]	eta 0:40:54 lr 0.000836	time 2.0574 (2.3130)	loss 2.8512 (3.7805)	grad_norm 1.4607 (1.1947)	
[2022-01-20 02:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][200/1251]	eta 0:40:21 lr 0.000836	time 1.9094 (2.3043)	loss 4.2985 (3.7962)	grad_norm 1.1337 (1.1931)	
[2022-01-20 02:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][210/1251]	eta 0:40:01 lr 0.000836	time 2.1829 (2.3066)	loss 3.8268 (3.7964)	grad_norm 1.3937 (1.1951)	
[2022-01-20 02:44:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][220/1251]	eta 0:39:31 lr 0.000836	time 1.7959 (2.2998)	loss 3.2466 (3.7814)	grad_norm 1.2189 (1.1968)	
[2022-01-20 02:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][230/1251]	eta 0:38:59 lr 0.000836	time 2.0763 (2.2910)	loss 3.9802 (3.7864)	grad_norm 1.1423 (1.1979)	
[2022-01-20 02:45:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][240/1251]	eta 0:38:31 lr 0.000835	time 2.1983 (2.2867)	loss 4.1092 (3.8079)	grad_norm 1.1358 (1.1989)	
[2022-01-20 02:45:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][250/1251]	eta 0:38:13 lr 0.000835	time 3.0127 (2.2911)	loss 3.8687 (3.8083)	grad_norm 1.2312 (1.1978)	
[2022-01-20 02:46:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][260/1251]	eta 0:37:48 lr 0.000835	time 1.8028 (2.2887)	loss 2.9784 (3.8010)	grad_norm 1.2783 (1.1991)	
[2022-01-20 02:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][270/1251]	eta 0:37:23 lr 0.000835	time 1.8808 (2.2872)	loss 4.0651 (3.8022)	grad_norm 1.1321 (1.1971)	
[2022-01-20 02:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][280/1251]	eta 0:36:56 lr 0.000835	time 1.9282 (2.2829)	loss 4.2696 (3.8096)	grad_norm 1.0657 (1.1982)	
[2022-01-20 02:47:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][290/1251]	eta 0:36:27 lr 0.000835	time 2.8170 (2.2767)	loss 3.4969 (3.8089)	grad_norm 1.4270 (1.1996)	
[2022-01-20 02:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][300/1251]	eta 0:35:58 lr 0.000835	time 1.9478 (2.2692)	loss 3.3428 (3.8105)	grad_norm 1.1632 (1.1989)	
[2022-01-20 02:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][310/1251]	eta 0:35:32 lr 0.000835	time 2.2897 (2.2659)	loss 4.3167 (3.8033)	grad_norm 1.1318 (1.1969)	
[2022-01-20 02:48:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][320/1251]	eta 0:35:05 lr 0.000835	time 2.0067 (2.2616)	loss 4.4833 (3.8016)	grad_norm 1.2609 (1.2003)	
[2022-01-20 02:48:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][330/1251]	eta 0:34:40 lr 0.000835	time 2.8975 (2.2589)	loss 4.4043 (3.8092)	grad_norm 1.2247 (1.2011)	
[2022-01-20 02:49:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][340/1251]	eta 0:34:11 lr 0.000835	time 1.9928 (2.2515)	loss 3.8303 (3.8022)	grad_norm 1.0690 (1.1998)	
[2022-01-20 02:49:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][350/1251]	eta 0:33:45 lr 0.000835	time 1.9209 (2.2479)	loss 4.0365 (3.7971)	grad_norm 1.0992 (1.1979)	
[2022-01-20 02:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][360/1251]	eta 0:33:20 lr 0.000835	time 2.2721 (2.2458)	loss 4.4689 (3.8011)	grad_norm 1.2585 (1.1972)	
[2022-01-20 02:50:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][370/1251]	eta 0:32:59 lr 0.000835	time 3.0070 (2.2469)	loss 4.6645 (3.7927)	grad_norm 1.0437 (1.1988)	
[2022-01-20 02:50:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][380/1251]	eta 0:32:40 lr 0.000835	time 1.5065 (2.2506)	loss 3.8620 (3.7930)	grad_norm 1.1646 (1.1980)	
[2022-01-20 02:51:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][390/1251]	eta 0:32:21 lr 0.000835	time 2.7345 (2.2546)	loss 4.2113 (3.7880)	grad_norm 1.4231 (1.1988)	
[2022-01-20 02:51:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][400/1251]	eta 0:31:59 lr 0.000835	time 2.4021 (2.2554)	loss 3.8255 (3.7867)	grad_norm 1.0655 (1.1980)	
[2022-01-20 02:51:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][410/1251]	eta 0:31:37 lr 0.000835	time 3.4097 (2.2559)	loss 4.0581 (3.7834)	grad_norm 1.4502 (1.1982)	
[2022-01-20 02:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][420/1251]	eta 0:31:11 lr 0.000835	time 1.7140 (2.2516)	loss 4.6191 (3.7836)	grad_norm 1.3391 (1.1991)	
[2022-01-20 02:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][430/1251]	eta 0:30:45 lr 0.000835	time 1.9400 (2.2480)	loss 3.3513 (3.7822)	grad_norm 1.0805 (1.1983)	
[2022-01-20 02:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][440/1251]	eta 0:30:20 lr 0.000835	time 1.8234 (2.2446)	loss 3.9310 (3.7842)	grad_norm 1.1915 (1.1985)	
[2022-01-20 02:53:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][450/1251]	eta 0:30:01 lr 0.000835	time 3.5641 (2.2493)	loss 3.6591 (3.7863)	grad_norm 1.0929 (1.1981)	
[2022-01-20 02:53:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][460/1251]	eta 0:29:36 lr 0.000835	time 1.9228 (2.2456)	loss 3.5020 (3.7852)	grad_norm 1.1715 (1.1964)	
[2022-01-20 02:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][470/1251]	eta 0:29:11 lr 0.000835	time 1.9475 (2.2421)	loss 4.2405 (3.7794)	grad_norm 1.3088 (1.1966)	
[2022-01-20 02:54:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][480/1251]	eta 0:28:50 lr 0.000835	time 2.2877 (2.2439)	loss 4.4481 (3.7797)	grad_norm 1.2464 (1.1981)	
[2022-01-20 02:54:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][490/1251]	eta 0:28:27 lr 0.000835	time 3.4065 (2.2444)	loss 4.3523 (3.7757)	grad_norm 1.3130 (1.1983)	
[2022-01-20 02:55:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][500/1251]	eta 0:28:04 lr 0.000835	time 1.8639 (2.2424)	loss 4.1310 (3.7796)	grad_norm 1.2101 (1.1991)	
[2022-01-20 02:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][510/1251]	eta 0:27:39 lr 0.000835	time 1.6771 (2.2395)	loss 3.6260 (3.7803)	grad_norm 1.1611 (1.1984)	
[2022-01-20 02:55:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][520/1251]	eta 0:27:19 lr 0.000835	time 2.2879 (2.2430)	loss 2.8901 (3.7780)	grad_norm 1.0727 (1.1981)	
[2022-01-20 02:56:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][530/1251]	eta 0:26:56 lr 0.000835	time 3.0454 (2.2415)	loss 4.0210 (3.7795)	grad_norm 1.4168 (1.1986)	
[2022-01-20 02:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][540/1251]	eta 0:26:30 lr 0.000835	time 1.8993 (2.2375)	loss 4.2445 (3.7742)	grad_norm 1.1364 (1.2010)	
[2022-01-20 02:56:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][550/1251]	eta 0:26:05 lr 0.000835	time 1.9447 (2.2331)	loss 3.9431 (3.7745)	grad_norm 1.3002 (1.2017)	
[2022-01-20 02:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][560/1251]	eta 0:25:40 lr 0.000834	time 2.0394 (2.2297)	loss 4.1208 (3.7755)	grad_norm 1.4467 (1.2029)	
[2022-01-20 02:57:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][570/1251]	eta 0:25:17 lr 0.000834	time 2.1744 (2.2284)	loss 3.7959 (3.7810)	grad_norm 1.4400 (1.2039)	
[2022-01-20 02:57:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][580/1251]	eta 0:24:55 lr 0.000834	time 2.6775 (2.2288)	loss 2.7711 (3.7761)	grad_norm 1.2833 (1.2049)	
[2022-01-20 02:58:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][590/1251]	eta 0:24:32 lr 0.000834	time 1.4617 (2.2273)	loss 4.0106 (3.7811)	grad_norm 1.4563 (1.2052)	
[2022-01-20 02:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][600/1251]	eta 0:24:10 lr 0.000834	time 2.2154 (2.2282)	loss 3.1188 (3.7743)	grad_norm 1.0890 (1.2054)	
[2022-01-20 02:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][610/1251]	eta 0:23:49 lr 0.000834	time 2.7302 (2.2294)	loss 3.8755 (3.7742)	grad_norm 1.2622 (1.2048)	
[2022-01-20 02:59:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][620/1251]	eta 0:23:28 lr 0.000834	time 2.1310 (2.2325)	loss 3.2813 (3.7732)	grad_norm 1.2937 (1.2041)	
[2022-01-20 02:59:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][630/1251]	eta 0:23:07 lr 0.000834	time 1.9735 (2.2344)	loss 3.0454 (3.7717)	grad_norm 1.4322 (1.2042)	
[2022-01-20 03:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][640/1251]	eta 0:22:44 lr 0.000834	time 1.9944 (2.2329)	loss 2.8886 (3.7729)	grad_norm 1.2993 (1.2031)	
[2022-01-20 03:00:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][650/1251]	eta 0:22:20 lr 0.000834	time 2.2408 (2.2299)	loss 3.4895 (3.7761)	grad_norm 1.1865 (1.2026)	
[2022-01-20 03:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][660/1251]	eta 0:21:56 lr 0.000834	time 1.9475 (2.2274)	loss 3.7542 (3.7777)	grad_norm 1.0363 (1.2017)	
[2022-01-20 03:01:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][670/1251]	eta 0:21:33 lr 0.000834	time 2.2919 (2.2262)	loss 3.9323 (3.7768)	grad_norm 1.1369 (1.2015)	
[2022-01-20 03:01:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][680/1251]	eta 0:21:11 lr 0.000834	time 2.8035 (2.2268)	loss 3.9481 (3.7753)	grad_norm 1.0612 (1.2009)	
[2022-01-20 03:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][690/1251]	eta 0:20:51 lr 0.000834	time 2.9219 (2.2313)	loss 4.2433 (3.7753)	grad_norm 1.1378 (1.1992)	
[2022-01-20 03:02:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][700/1251]	eta 0:20:30 lr 0.000834	time 2.6410 (2.2331)	loss 3.2866 (3.7765)	grad_norm 1.0623 (1.1992)	
[2022-01-20 03:02:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][710/1251]	eta 0:20:06 lr 0.000834	time 1.9196 (2.2301)	loss 4.4205 (3.7804)	grad_norm 1.1887 (1.1982)	
[2022-01-20 03:03:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][720/1251]	eta 0:19:42 lr 0.000834	time 2.3291 (2.2267)	loss 2.6344 (3.7766)	grad_norm 1.1992 (1.1980)	
[2022-01-20 03:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][730/1251]	eta 0:19:19 lr 0.000834	time 2.2540 (2.2259)	loss 4.7078 (3.7777)	grad_norm 1.2340 (1.1976)	
[2022-01-20 03:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][740/1251]	eta 0:18:56 lr 0.000834	time 1.9966 (2.2236)	loss 4.4234 (3.7782)	grad_norm 1.0914 (1.1983)	
[2022-01-20 03:04:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][750/1251]	eta 0:18:32 lr 0.000834	time 1.8145 (2.2215)	loss 3.7265 (3.7784)	grad_norm 1.2670 (1.2000)	
[2022-01-20 03:04:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][760/1251]	eta 0:18:11 lr 0.000834	time 3.1675 (2.2231)	loss 4.4324 (3.7793)	grad_norm 1.2318 (1.2006)	
[2022-01-20 03:04:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][770/1251]	eta 0:17:50 lr 0.000834	time 1.7822 (2.2250)	loss 4.3298 (3.7803)	grad_norm 1.2800 (1.2009)	
[2022-01-20 03:05:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][780/1251]	eta 0:17:28 lr 0.000834	time 1.9051 (2.2254)	loss 4.0543 (3.7824)	grad_norm 1.3963 (1.2018)	
[2022-01-20 03:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][790/1251]	eta 0:17:06 lr 0.000834	time 2.2261 (2.2256)	loss 3.6474 (3.7807)	grad_norm 1.3769 (1.2032)	
[2022-01-20 03:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][800/1251]	eta 0:16:43 lr 0.000834	time 3.2170 (2.2251)	loss 4.0600 (3.7814)	grad_norm 1.1706 (1.2031)	
[2022-01-20 03:06:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][810/1251]	eta 0:16:19 lr 0.000834	time 1.8324 (2.2218)	loss 3.5552 (3.7796)	grad_norm 1.2874 (1.2037)	
[2022-01-20 03:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][820/1251]	eta 0:15:56 lr 0.000834	time 1.9711 (2.2194)	loss 3.1752 (3.7778)	grad_norm 1.0961 (1.2028)	
[2022-01-20 03:07:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][830/1251]	eta 0:15:34 lr 0.000834	time 2.2807 (2.2185)	loss 2.7506 (3.7757)	grad_norm 1.0777 (1.2020)	
[2022-01-20 03:07:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][840/1251]	eta 0:15:11 lr 0.000834	time 1.5045 (2.2167)	loss 2.6685 (3.7745)	grad_norm 0.9553 (1.2007)	
[2022-01-20 03:07:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][850/1251]	eta 0:14:47 lr 0.000834	time 1.5517 (2.2140)	loss 4.2991 (3.7747)	grad_norm 1.2184 (1.2005)	
[2022-01-20 03:08:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][860/1251]	eta 0:14:26 lr 0.000834	time 2.7980 (2.2150)	loss 3.8952 (3.7717)	grad_norm 1.0472 (1.1995)	
[2022-01-20 03:08:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][870/1251]	eta 0:14:03 lr 0.000834	time 2.1649 (2.2138)	loss 4.1746 (3.7694)	grad_norm 1.1547 (1.1986)	
[2022-01-20 03:08:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][880/1251]	eta 0:13:41 lr 0.000834	time 1.5910 (2.2134)	loss 3.1266 (3.7690)	grad_norm 1.1671 (1.1985)	
[2022-01-20 03:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][890/1251]	eta 0:13:19 lr 0.000833	time 1.6028 (2.2136)	loss 4.2916 (3.7715)	grad_norm 1.0693 (1.1973)	
[2022-01-20 03:09:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][900/1251]	eta 0:12:57 lr 0.000833	time 2.9165 (2.2149)	loss 3.9719 (3.7711)	grad_norm 1.0871 (1.1970)	
[2022-01-20 03:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][910/1251]	eta 0:12:34 lr 0.000833	time 1.8535 (2.2135)	loss 4.3187 (3.7717)	grad_norm 1.1397 (1.1964)	
[2022-01-20 03:10:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][920/1251]	eta 0:12:12 lr 0.000833	time 2.2580 (2.2121)	loss 3.3295 (3.7719)	grad_norm 1.2809 (1.1959)	
[2022-01-20 03:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][930/1251]	eta 0:11:49 lr 0.000833	time 1.8106 (2.2108)	loss 4.3099 (3.7740)	grad_norm 1.2371 (1.1960)	
[2022-01-20 03:11:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][940/1251]	eta 0:11:28 lr 0.000833	time 5.0835 (2.2148)	loss 3.5956 (3.7751)	grad_norm 1.3977 (1.1962)	
[2022-01-20 03:11:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][950/1251]	eta 0:11:06 lr 0.000833	time 1.8559 (2.2151)	loss 4.0709 (3.7730)	grad_norm 0.9286 (1.1958)	
[2022-01-20 03:11:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][960/1251]	eta 0:10:45 lr 0.000833	time 3.0188 (2.2172)	loss 4.4040 (3.7732)	grad_norm 1.2110 (1.1951)	
[2022-01-20 03:12:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][970/1251]	eta 0:10:22 lr 0.000833	time 2.0706 (2.2163)	loss 4.0439 (3.7721)	grad_norm 1.2168 (1.1946)	
[2022-01-20 03:12:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][980/1251]	eta 0:10:00 lr 0.000833	time 3.2301 (2.2157)	loss 3.9732 (3.7744)	grad_norm 1.0675 (1.1943)	
[2022-01-20 03:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][990/1251]	eta 0:09:37 lr 0.000833	time 1.9316 (2.2139)	loss 4.2117 (3.7769)	grad_norm 1.0593 (1.1938)	
[2022-01-20 03:13:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1000/1251]	eta 0:09:15 lr 0.000833	time 1.7039 (2.2130)	loss 2.9715 (3.7743)	grad_norm 1.0358 (1.1933)	
[2022-01-20 03:13:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1010/1251]	eta 0:08:53 lr 0.000833	time 2.3661 (2.2124)	loss 3.7351 (3.7724)	grad_norm 1.0479 (1.1932)	
[2022-01-20 03:13:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1020/1251]	eta 0:08:30 lr 0.000833	time 2.1028 (2.2111)	loss 3.6266 (3.7748)	grad_norm 1.1428 (1.1932)	
[2022-01-20 03:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1030/1251]	eta 0:08:08 lr 0.000833	time 1.9252 (2.2110)	loss 4.0947 (3.7752)	grad_norm 1.0736 (1.1928)	
[2022-01-20 03:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1040/1251]	eta 0:07:46 lr 0.000833	time 2.5144 (2.2110)	loss 2.9032 (3.7754)	grad_norm 2.2433 (1.1937)	
[2022-01-20 03:15:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1050/1251]	eta 0:07:24 lr 0.000833	time 2.4592 (2.2122)	loss 4.0344 (3.7720)	grad_norm 1.2025 (1.1940)	
[2022-01-20 03:15:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1060/1251]	eta 0:07:02 lr 0.000833	time 2.1612 (2.2122)	loss 4.0908 (3.7730)	grad_norm 1.2999 (1.1937)	
[2022-01-20 03:15:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1070/1251]	eta 0:06:40 lr 0.000833	time 1.6672 (2.2123)	loss 4.5186 (3.7739)	grad_norm 1.2100 (1.1939)	
[2022-01-20 03:16:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1080/1251]	eta 0:06:18 lr 0.000833	time 1.6357 (2.2110)	loss 3.9447 (3.7761)	grad_norm 1.1135 (1.1934)	
[2022-01-20 03:16:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1090/1251]	eta 0:05:55 lr 0.000833	time 2.5394 (2.2110)	loss 3.3638 (3.7778)	grad_norm 1.1380 (1.1936)	
[2022-01-20 03:16:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1100/1251]	eta 0:05:33 lr 0.000833	time 2.0339 (2.2103)	loss 2.8430 (3.7775)	grad_norm 1.2213 (1.1941)	
[2022-01-20 03:17:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1110/1251]	eta 0:05:11 lr 0.000833	time 1.9131 (2.2099)	loss 2.9711 (3.7736)	grad_norm 1.1975 (1.1957)	
[2022-01-20 03:17:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1120/1251]	eta 0:04:49 lr 0.000833	time 1.9320 (2.2084)	loss 3.7399 (3.7717)	grad_norm 1.1001 (1.1953)	
[2022-01-20 03:17:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1130/1251]	eta 0:04:27 lr 0.000833	time 2.5672 (2.2085)	loss 4.0772 (3.7714)	grad_norm 1.0581 (1.1945)	
[2022-01-20 03:18:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1140/1251]	eta 0:04:05 lr 0.000833	time 2.4078 (2.2095)	loss 4.1401 (3.7724)	grad_norm 1.3148 (1.1942)	
[2022-01-20 03:18:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1150/1251]	eta 0:03:43 lr 0.000833	time 2.7436 (2.2117)	loss 2.8035 (3.7703)	grad_norm 1.0887 (1.1937)	
[2022-01-20 03:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1160/1251]	eta 0:03:21 lr 0.000833	time 1.8899 (2.2121)	loss 3.7934 (3.7705)	grad_norm 1.5729 (1.1940)	
[2022-01-20 03:19:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1170/1251]	eta 0:02:59 lr 0.000833	time 2.2482 (2.2106)	loss 4.5089 (3.7731)	grad_norm 1.4775 (1.1944)	
[2022-01-20 03:19:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1180/1251]	eta 0:02:36 lr 0.000833	time 2.2558 (2.2086)	loss 4.3395 (3.7746)	grad_norm 1.5341 (1.1947)	
[2022-01-20 03:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1190/1251]	eta 0:02:14 lr 0.000833	time 1.9405 (2.2069)	loss 4.7273 (3.7757)	grad_norm 1.0458 (1.1950)	
[2022-01-20 03:20:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1200/1251]	eta 0:01:52 lr 0.000833	time 1.7895 (2.2047)	loss 4.4180 (3.7766)	grad_norm 1.1012 (1.1945)	
[2022-01-20 03:20:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1210/1251]	eta 0:01:30 lr 0.000832	time 1.8844 (2.2036)	loss 4.3101 (3.7774)	grad_norm 1.1209 (1.1940)	
[2022-01-20 03:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1220/1251]	eta 0:01:08 lr 0.000832	time 2.5161 (2.2027)	loss 4.5123 (3.7797)	grad_norm 1.1182 (1.1939)	
[2022-01-20 03:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1230/1251]	eta 0:00:46 lr 0.000832	time 1.9163 (2.2018)	loss 4.2242 (3.7814)	grad_norm 1.3379 (1.1943)	
[2022-01-20 03:21:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1240/1251]	eta 0:00:24 lr 0.000832	time 1.4101 (2.2029)	loss 4.2441 (3.7834)	grad_norm 1.2157 (1.1944)	
[2022-01-20 03:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [80/300][1250/1251]	eta 0:00:02 lr 0.000832	time 1.1519 (2.1983)	loss 3.6630 (3.7853)	grad_norm 1.3822 (1.1939)	
[2022-01-20 03:22:09 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 80 training takes 0:45:50
[2022-01-20 03:22:09 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_80 saving......
[2022-01-20 03:22:20 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_80 saved !!!
[2022-01-20 03:22:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.845 (16.845)	Loss 1.2917 (1.2917)	Acc@1 69.727 (69.727)	Acc@5 89.648 (89.648)	
[2022-01-20 03:22:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.916 (2.879)	Loss 1.1384 (1.2377)	Acc@1 74.121 (71.493)	Acc@5 91.602 (90.669)	
[2022-01-20 03:23:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.343 (2.149)	Loss 1.1860 (1.2112)	Acc@1 71.875 (72.028)	Acc@5 92.285 (91.090)	
[2022-01-20 03:23:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.613 (2.086)	Loss 1.1967 (1.2014)	Acc@1 72.266 (72.051)	Acc@5 90.820 (91.249)	
[2022-01-20 03:23:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.497 (2.024)	Loss 1.1917 (1.1991)	Acc@1 71.875 (72.180)	Acc@5 91.406 (91.332)	
[2022-01-20 03:23:51 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.358 Acc@5 91.332
[2022-01-20 03:23:51 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.4%
[2022-01-20 03:23:51 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.59%
[2022-01-20 03:24:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][0/1251]	eta 7:26:25 lr 0.000832	time 21.4112 (21.4112)	loss 3.1441 (3.1441)	grad_norm 1.1664 (1.1664)	
[2022-01-20 03:24:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][10/1251]	eta 1:24:39 lr 0.000832	time 2.4587 (4.0932)	loss 4.1283 (3.5694)	grad_norm 1.2875 (1.1487)	
[2022-01-20 03:24:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][20/1251]	eta 1:03:32 lr 0.000832	time 1.3887 (3.0969)	loss 3.9824 (3.6982)	grad_norm 1.1201 (1.1447)	
[2022-01-20 03:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][30/1251]	eta 0:57:52 lr 0.000832	time 1.9466 (2.8438)	loss 4.2747 (3.6749)	grad_norm 1.1500 (1.1479)	
[2022-01-20 03:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][40/1251]	eta 0:54:50 lr 0.000832	time 4.6944 (2.7171)	loss 3.6913 (3.6524)	grad_norm 0.9924 (1.1413)	
[2022-01-20 03:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][50/1251]	eta 0:52:06 lr 0.000832	time 2.0890 (2.6032)	loss 4.5905 (3.7009)	grad_norm 1.2556 (1.1428)	
[2022-01-20 03:26:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][60/1251]	eta 0:50:36 lr 0.000832	time 2.5247 (2.5494)	loss 3.0875 (3.7068)	grad_norm 1.1088 (1.1452)	
[2022-01-20 03:26:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][70/1251]	eta 0:49:34 lr 0.000832	time 1.5883 (2.5182)	loss 3.7688 (3.7304)	grad_norm 1.1882 (1.1592)	
[2022-01-20 03:27:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][80/1251]	eta 0:48:28 lr 0.000832	time 3.8151 (2.4834)	loss 3.8910 (3.7608)	grad_norm 1.5387 (1.1649)	
[2022-01-20 03:27:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][90/1251]	eta 0:47:43 lr 0.000832	time 2.3576 (2.4662)	loss 4.3040 (3.7712)	grad_norm 1.2291 (1.1758)	
[2022-01-20 03:27:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][100/1251]	eta 0:46:58 lr 0.000832	time 1.5918 (2.4485)	loss 3.9095 (3.7712)	grad_norm 1.1580 (1.1742)	
[2022-01-20 03:28:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][110/1251]	eta 0:46:00 lr 0.000832	time 1.7235 (2.4191)	loss 2.6875 (3.7272)	grad_norm 1.0075 (1.1704)	
[2022-01-20 03:28:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][120/1251]	eta 0:44:55 lr 0.000832	time 2.0607 (2.3830)	loss 3.1314 (3.7331)	grad_norm 1.9582 (1.1781)	
[2022-01-20 03:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][130/1251]	eta 0:43:53 lr 0.000832	time 1.8710 (2.3490)	loss 4.2023 (3.7439)	grad_norm 1.1862 (1.1780)	
[2022-01-20 03:29:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][140/1251]	eta 0:43:11 lr 0.000832	time 2.3194 (2.3324)	loss 4.9260 (3.7376)	grad_norm 1.5179 (1.1830)	
[2022-01-20 03:29:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][150/1251]	eta 0:42:34 lr 0.000832	time 2.1182 (2.3205)	loss 3.7941 (3.7561)	grad_norm 1.3130 (1.1850)	
[2022-01-20 03:30:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][160/1251]	eta 0:42:00 lr 0.000832	time 1.7075 (2.3105)	loss 4.1866 (3.7635)	grad_norm 1.3105 (1.1905)	
[2022-01-20 03:30:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][170/1251]	eta 0:41:41 lr 0.000832	time 2.3537 (2.3140)	loss 4.5866 (3.7828)	grad_norm 1.1194 (1.1936)	
[2022-01-20 03:30:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][180/1251]	eta 0:41:17 lr 0.000832	time 2.8266 (2.3128)	loss 4.1429 (3.7800)	grad_norm 1.1388 (1.1884)	
[2022-01-20 03:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][190/1251]	eta 0:40:51 lr 0.000832	time 1.6742 (2.3105)	loss 4.2392 (3.7773)	grad_norm 1.0907 (1.1847)	
[2022-01-20 03:31:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][200/1251]	eta 0:40:26 lr 0.000832	time 1.6781 (2.3087)	loss 3.4052 (3.7744)	grad_norm 1.1914 (1.1810)	
[2022-01-20 03:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][210/1251]	eta 0:40:02 lr 0.000832	time 1.7076 (2.3079)	loss 3.9268 (3.7781)	grad_norm 1.4162 (1.1805)	
[2022-01-20 03:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][220/1251]	eta 0:39:35 lr 0.000832	time 2.7043 (2.3038)	loss 4.4964 (3.7784)	grad_norm 1.2475 (1.1820)	
[2022-01-20 03:32:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][230/1251]	eta 0:39:00 lr 0.000832	time 1.6180 (2.2928)	loss 3.8583 (3.7684)	grad_norm 1.1501 (1.1811)	
[2022-01-20 03:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][240/1251]	eta 0:38:29 lr 0.000832	time 2.0205 (2.2845)	loss 3.3452 (3.7758)	grad_norm 1.1954 (1.1811)	
[2022-01-20 03:33:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][250/1251]	eta 0:38:01 lr 0.000832	time 1.8234 (2.2797)	loss 3.6703 (3.7697)	grad_norm 1.0296 (1.1777)	
[2022-01-20 03:33:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][260/1251]	eta 0:37:35 lr 0.000832	time 2.1701 (2.2763)	loss 3.6977 (3.7685)	grad_norm 1.0758 (1.1778)	
[2022-01-20 03:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][270/1251]	eta 0:37:07 lr 0.000832	time 1.9265 (2.2706)	loss 3.6999 (3.7722)	grad_norm 1.1697 (1.1778)	
[2022-01-20 03:34:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][280/1251]	eta 0:36:42 lr 0.000831	time 2.2171 (2.2686)	loss 4.5451 (3.7689)	grad_norm 1.1206 (1.1774)	
[2022-01-20 03:34:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][290/1251]	eta 0:36:16 lr 0.000831	time 1.8540 (2.2645)	loss 3.8298 (3.7681)	grad_norm 1.2092 (1.1782)	
[2022-01-20 03:35:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][300/1251]	eta 0:35:50 lr 0.000831	time 1.8176 (2.2615)	loss 4.0249 (3.7691)	grad_norm 1.0967 (1.1769)	
[2022-01-20 03:35:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][310/1251]	eta 0:35:27 lr 0.000831	time 2.2532 (2.2607)	loss 3.6864 (3.7703)	grad_norm 1.1712 (1.1748)	
[2022-01-20 03:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][320/1251]	eta 0:35:08 lr 0.000831	time 3.2969 (2.2646)	loss 4.3124 (3.7678)	grad_norm 1.1583 (1.1757)	
[2022-01-20 03:36:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][330/1251]	eta 0:34:48 lr 0.000831	time 1.8936 (2.2673)	loss 3.6703 (3.7652)	grad_norm 1.0408 (1.1746)	
[2022-01-20 03:36:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][340/1251]	eta 0:34:20 lr 0.000831	time 1.5508 (2.2622)	loss 3.4369 (3.7579)	grad_norm 1.3587 (1.1755)	
[2022-01-20 03:37:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][350/1251]	eta 0:33:51 lr 0.000831	time 2.2328 (2.2552)	loss 3.3597 (3.7605)	grad_norm 1.0527 (1.1770)	
[2022-01-20 03:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][360/1251]	eta 0:33:24 lr 0.000831	time 1.9241 (2.2498)	loss 4.1711 (3.7673)	grad_norm 1.1040 (1.1774)	
[2022-01-20 03:37:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][370/1251]	eta 0:33:02 lr 0.000831	time 1.9401 (2.2504)	loss 4.1600 (3.7691)	grad_norm 1.4146 (1.1777)	
[2022-01-20 03:38:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][380/1251]	eta 0:32:41 lr 0.000831	time 2.2034 (2.2518)	loss 2.4818 (3.7638)	grad_norm 0.9781 (1.1784)	
[2022-01-20 03:38:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][390/1251]	eta 0:32:15 lr 0.000831	time 2.8336 (2.2481)	loss 3.0034 (3.7670)	grad_norm 1.2602 (1.1781)	
[2022-01-20 03:38:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][400/1251]	eta 0:31:48 lr 0.000831	time 1.9811 (2.2426)	loss 4.5107 (3.7783)	grad_norm 1.3958 (1.1789)	
[2022-01-20 03:39:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][410/1251]	eta 0:31:22 lr 0.000831	time 1.7225 (2.2390)	loss 4.4941 (3.7752)	grad_norm 1.2622 (1.1789)	
[2022-01-20 03:39:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][420/1251]	eta 0:30:57 lr 0.000831	time 1.9007 (2.2351)	loss 4.5155 (3.7835)	grad_norm 1.1319 (1.1794)	
[2022-01-20 03:39:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][430/1251]	eta 0:30:34 lr 0.000831	time 2.4974 (2.2345)	loss 4.0138 (3.7824)	grad_norm 1.1860 (1.1805)	
[2022-01-20 03:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][440/1251]	eta 0:30:12 lr 0.000831	time 1.8202 (2.2344)	loss 3.8977 (3.7827)	grad_norm 1.3318 (1.1810)	
[2022-01-20 03:40:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][450/1251]	eta 0:29:51 lr 0.000831	time 2.6117 (2.2360)	loss 3.4098 (3.7837)	grad_norm 1.1539 (1.1817)	
[2022-01-20 03:41:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][460/1251]	eta 0:29:27 lr 0.000831	time 1.8152 (2.2342)	loss 4.0825 (3.7879)	grad_norm 1.2591 (1.1848)	
[2022-01-20 03:41:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][470/1251]	eta 0:29:05 lr 0.000831	time 3.3430 (2.2356)	loss 3.4049 (3.7895)	grad_norm 1.0949 (1.1864)	
[2022-01-20 03:41:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][480/1251]	eta 0:28:44 lr 0.000831	time 3.0595 (2.2368)	loss 4.2262 (3.7860)	grad_norm 1.2417 (1.1864)	
[2022-01-20 03:42:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][490/1251]	eta 0:28:20 lr 0.000831	time 2.2800 (2.2352)	loss 4.1474 (3.7875)	grad_norm 1.3718 (1.1866)	
[2022-01-20 03:42:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][500/1251]	eta 0:27:55 lr 0.000831	time 1.7103 (2.2313)	loss 4.0561 (3.7928)	grad_norm 0.9165 (1.1866)	
[2022-01-20 03:42:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][510/1251]	eta 0:27:30 lr 0.000831	time 1.8108 (2.2269)	loss 4.1349 (3.7875)	grad_norm 1.3926 (1.1873)	
[2022-01-20 03:43:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][520/1251]	eta 0:27:06 lr 0.000831	time 2.7622 (2.2256)	loss 3.1155 (3.7842)	grad_norm 1.3433 (1.1882)	
[2022-01-20 03:43:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][530/1251]	eta 0:26:43 lr 0.000831	time 3.1069 (2.2242)	loss 4.3230 (3.7830)	grad_norm 1.2518 (1.1881)	
[2022-01-20 03:43:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][540/1251]	eta 0:26:21 lr 0.000831	time 2.1551 (2.2240)	loss 4.6661 (3.7838)	grad_norm 1.0470 (1.1883)	
[2022-01-20 03:44:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][550/1251]	eta 0:25:59 lr 0.000831	time 2.5082 (2.2247)	loss 4.2273 (3.7862)	grad_norm 1.2512 (1.1885)	
[2022-01-20 03:44:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][560/1251]	eta 0:25:37 lr 0.000831	time 2.1290 (2.2245)	loss 3.1611 (3.7862)	grad_norm 1.1697 (1.1885)	
[2022-01-20 03:45:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][570/1251]	eta 0:25:16 lr 0.000831	time 2.9630 (2.2262)	loss 3.9105 (3.7888)	grad_norm 1.5176 (1.1885)	
[2022-01-20 03:45:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][580/1251]	eta 0:24:52 lr 0.000831	time 1.9455 (2.2250)	loss 3.8761 (3.7923)	grad_norm 1.0859 (1.1885)	
[2022-01-20 03:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][590/1251]	eta 0:24:31 lr 0.000831	time 2.8813 (2.2257)	loss 4.2340 (3.7900)	grad_norm 1.1858 (1.1884)	
[2022-01-20 03:46:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][600/1251]	eta 0:24:08 lr 0.000830	time 1.9007 (2.2249)	loss 4.0713 (3.7923)	grad_norm 1.0234 (1.1891)	
[2022-01-20 03:46:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][610/1251]	eta 0:23:45 lr 0.000830	time 2.7874 (2.2242)	loss 3.3162 (3.7935)	grad_norm 1.4137 (1.1897)	
[2022-01-20 03:46:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][620/1251]	eta 0:23:21 lr 0.000830	time 1.9019 (2.2207)	loss 2.3834 (3.7929)	grad_norm 1.1350 (1.1894)	
[2022-01-20 03:47:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][630/1251]	eta 0:22:56 lr 0.000830	time 2.1135 (2.2164)	loss 3.9853 (3.7955)	grad_norm 1.1066 (1.1907)	
[2022-01-20 03:47:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][640/1251]	eta 0:22:33 lr 0.000830	time 2.0222 (2.2148)	loss 3.9090 (3.7990)	grad_norm 1.2132 (1.1920)	
[2022-01-20 03:47:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][650/1251]	eta 0:22:11 lr 0.000830	time 3.0131 (2.2152)	loss 3.7119 (3.7993)	grad_norm 1.0690 (1.1914)	
[2022-01-20 03:48:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][660/1251]	eta 0:21:50 lr 0.000830	time 2.0946 (2.2174)	loss 4.3497 (3.8015)	grad_norm 1.2603 (1.1926)	
[2022-01-20 03:48:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][670/1251]	eta 0:21:29 lr 0.000830	time 2.6772 (2.2198)	loss 4.1386 (3.8002)	grad_norm 1.0738 (1.1918)	
[2022-01-20 03:49:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][680/1251]	eta 0:21:07 lr 0.000830	time 1.8376 (2.2198)	loss 3.8642 (3.8037)	grad_norm 1.0837 (1.1911)	
[2022-01-20 03:49:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][690/1251]	eta 0:20:45 lr 0.000830	time 2.5229 (2.2209)	loss 4.1922 (3.8000)	grad_norm 1.1015 (1.1912)	
[2022-01-20 03:49:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][700/1251]	eta 0:20:24 lr 0.000830	time 1.9145 (2.2222)	loss 4.1306 (3.7987)	grad_norm 1.1711 (1.1919)	
[2022-01-20 03:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][710/1251]	eta 0:20:00 lr 0.000830	time 2.1670 (2.2197)	loss 4.2427 (3.7968)	grad_norm 1.1651 (1.1931)	
[2022-01-20 03:50:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][720/1251]	eta 0:19:37 lr 0.000830	time 1.9116 (2.2167)	loss 3.8111 (3.7959)	grad_norm 1.3140 (1.1933)	
[2022-01-20 03:50:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][730/1251]	eta 0:19:13 lr 0.000830	time 2.2819 (2.2149)	loss 4.1352 (3.7976)	grad_norm 1.1091 (1.1929)	
[2022-01-20 03:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][740/1251]	eta 0:18:50 lr 0.000830	time 1.5886 (2.2131)	loss 3.8117 (3.7958)	grad_norm 1.3153 (1.1929)	
[2022-01-20 03:51:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][750/1251]	eta 0:18:28 lr 0.000830	time 3.0373 (2.2130)	loss 3.5108 (3.7951)	grad_norm 1.1204 (1.1931)	
[2022-01-20 03:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][760/1251]	eta 0:18:06 lr 0.000830	time 1.6635 (2.2128)	loss 4.3479 (3.7969)	grad_norm 1.3421 (1.1945)	
[2022-01-20 03:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][770/1251]	eta 0:17:44 lr 0.000830	time 1.9225 (2.2128)	loss 4.2876 (3.7939)	grad_norm 1.1261 (1.1952)	
[2022-01-20 03:52:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][780/1251]	eta 0:17:22 lr 0.000830	time 2.3688 (2.2137)	loss 3.3569 (3.7887)	grad_norm 1.4093 (1.1963)	
[2022-01-20 03:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][790/1251]	eta 0:17:00 lr 0.000830	time 3.0204 (2.2146)	loss 3.6999 (3.7895)	grad_norm 1.2856 (1.1957)	
[2022-01-20 03:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][800/1251]	eta 0:16:39 lr 0.000830	time 2.2304 (2.2152)	loss 4.5191 (3.7908)	grad_norm 1.0047 (1.1956)	
[2022-01-20 03:53:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][810/1251]	eta 0:16:16 lr 0.000830	time 2.2632 (2.2150)	loss 4.3193 (3.7951)	grad_norm 1.2097 (1.1963)	
[2022-01-20 03:54:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][820/1251]	eta 0:15:54 lr 0.000830	time 2.1281 (2.2135)	loss 3.7135 (3.7983)	grad_norm 1.0263 (1.1964)	
[2022-01-20 03:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][830/1251]	eta 0:15:31 lr 0.000830	time 1.8817 (2.2121)	loss 4.0096 (3.7975)	grad_norm 1.0948 (1.1960)	
[2022-01-20 03:54:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][840/1251]	eta 0:15:08 lr 0.000830	time 2.2284 (2.2108)	loss 4.0992 (3.7989)	grad_norm 1.2129 (1.1960)	
[2022-01-20 03:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][850/1251]	eta 0:14:46 lr 0.000830	time 2.5714 (2.2110)	loss 3.9353 (3.8006)	grad_norm 1.1820 (1.1957)	
[2022-01-20 03:55:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][860/1251]	eta 0:14:24 lr 0.000830	time 2.5962 (2.2107)	loss 4.5820 (3.7991)	grad_norm 1.2105 (1.1958)	
[2022-01-20 03:55:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][870/1251]	eta 0:14:01 lr 0.000830	time 1.4880 (2.2097)	loss 3.0497 (3.7987)	grad_norm 1.3112 (1.1959)	
[2022-01-20 03:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][880/1251]	eta 0:13:39 lr 0.000830	time 1.8447 (2.2089)	loss 4.0374 (3.7957)	grad_norm 1.1000 (1.1964)	
[2022-01-20 03:56:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][890/1251]	eta 0:13:16 lr 0.000830	time 1.8035 (2.2076)	loss 3.7569 (3.7961)	grad_norm 1.3892 (1.1968)	
[2022-01-20 03:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][900/1251]	eta 0:12:55 lr 0.000830	time 3.2865 (2.2086)	loss 4.2629 (3.7972)	grad_norm 0.9887 (1.1981)	
[2022-01-20 03:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][910/1251]	eta 0:12:33 lr 0.000830	time 1.7254 (2.2102)	loss 3.7903 (3.7946)	grad_norm 1.2405 (1.1975)	
[2022-01-20 03:57:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][920/1251]	eta 0:12:12 lr 0.000829	time 2.4935 (2.2141)	loss 3.3164 (3.7925)	grad_norm 1.3455 (1.1991)	
[2022-01-20 03:58:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][930/1251]	eta 0:11:50 lr 0.000829	time 2.2004 (2.2140)	loss 3.6858 (3.7940)	grad_norm 1.2797 (1.2002)	
[2022-01-20 03:58:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][940/1251]	eta 0:11:28 lr 0.000829	time 2.3946 (2.2137)	loss 3.9847 (3.7932)	grad_norm 1.3551 (1.2004)	
[2022-01-20 03:58:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][950/1251]	eta 0:11:05 lr 0.000829	time 1.8310 (2.2120)	loss 4.1036 (3.7937)	grad_norm 1.0311 (1.2006)	
[2022-01-20 03:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][960/1251]	eta 0:10:43 lr 0.000829	time 1.7218 (2.2099)	loss 3.8264 (3.7926)	grad_norm 1.1313 (1.2003)	
[2022-01-20 03:59:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][970/1251]	eta 0:10:20 lr 0.000829	time 1.9686 (2.2080)	loss 2.7902 (3.7941)	grad_norm 1.6787 (1.2002)	
[2022-01-20 03:59:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][980/1251]	eta 0:09:58 lr 0.000829	time 2.0692 (2.2069)	loss 3.5485 (3.7934)	grad_norm 1.0038 (1.1994)	
[2022-01-20 04:00:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][990/1251]	eta 0:09:35 lr 0.000829	time 2.5464 (2.2067)	loss 4.0497 (3.7937)	grad_norm 1.4506 (1.1990)	
[2022-01-20 04:00:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1000/1251]	eta 0:09:14 lr 0.000829	time 1.9619 (2.2095)	loss 3.9697 (3.7932)	grad_norm 1.1997 (1.1995)	
[2022-01-20 04:01:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1010/1251]	eta 0:08:53 lr 0.000829	time 2.4940 (2.2133)	loss 3.4390 (3.7941)	grad_norm 1.2016 (1.1994)	
[2022-01-20 04:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1020/1251]	eta 0:08:31 lr 0.000829	time 2.4496 (2.2155)	loss 2.7873 (3.7942)	grad_norm 1.4547 (1.2005)	
[2022-01-20 04:01:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1030/1251]	eta 0:08:09 lr 0.000829	time 2.2226 (2.2156)	loss 4.1374 (3.7944)	grad_norm 1.4247 (1.2003)	
[2022-01-20 04:02:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1040/1251]	eta 0:07:47 lr 0.000829	time 1.9199 (2.2154)	loss 2.9107 (3.7929)	grad_norm 1.2024 (1.2006)	
[2022-01-20 04:02:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1050/1251]	eta 0:07:24 lr 0.000829	time 1.9949 (2.2127)	loss 4.2959 (3.7959)	grad_norm 1.3688 (1.2000)	
[2022-01-20 04:02:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1060/1251]	eta 0:07:02 lr 0.000829	time 2.2195 (2.2106)	loss 3.9472 (3.7945)	grad_norm 1.1801 (1.1994)	
[2022-01-20 04:03:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1070/1251]	eta 0:06:39 lr 0.000829	time 1.8973 (2.2080)	loss 2.7539 (3.7893)	grad_norm 1.1138 (1.1983)	
[2022-01-20 04:03:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1080/1251]	eta 0:06:17 lr 0.000829	time 2.5704 (2.2086)	loss 3.9522 (3.7888)	grad_norm 1.3277 (1.1981)	
[2022-01-20 04:03:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1090/1251]	eta 0:05:55 lr 0.000829	time 1.8505 (2.2075)	loss 4.4610 (3.7885)	grad_norm 1.3859 (1.1982)	
[2022-01-20 04:04:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1100/1251]	eta 0:05:33 lr 0.000829	time 1.8038 (2.2066)	loss 3.2526 (3.7874)	grad_norm 1.1314 (1.1983)	
[2022-01-20 04:04:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1110/1251]	eta 0:05:11 lr 0.000829	time 2.5379 (2.2078)	loss 4.2762 (3.7857)	grad_norm 1.0675 (1.1976)	
[2022-01-20 04:05:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1120/1251]	eta 0:04:49 lr 0.000829	time 2.0930 (2.2092)	loss 3.0423 (3.7841)	grad_norm 1.1897 (1.1969)	
[2022-01-20 04:05:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1130/1251]	eta 0:04:27 lr 0.000829	time 1.8993 (2.2105)	loss 3.6438 (3.7840)	grad_norm 1.1782 (1.1970)	
[2022-01-20 04:05:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1140/1251]	eta 0:04:05 lr 0.000829	time 2.1860 (2.2111)	loss 4.0722 (3.7825)	grad_norm 1.1347 (1.1969)	
[2022-01-20 04:06:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1150/1251]	eta 0:03:43 lr 0.000829	time 2.1256 (2.2112)	loss 4.3448 (3.7829)	grad_norm 1.1470 (1.1970)	
[2022-01-20 04:06:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1160/1251]	eta 0:03:21 lr 0.000829	time 1.6663 (2.2109)	loss 3.0924 (3.7830)	grad_norm 1.0126 (1.1962)	
[2022-01-20 04:06:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1170/1251]	eta 0:02:59 lr 0.000829	time 1.9339 (2.2101)	loss 4.2219 (3.7832)	grad_norm 1.0696 (1.1956)	
[2022-01-20 04:07:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1180/1251]	eta 0:02:36 lr 0.000829	time 2.2614 (2.2099)	loss 3.8028 (3.7843)	grad_norm 1.2734 (1.1958)	
[2022-01-20 04:07:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1190/1251]	eta 0:02:14 lr 0.000829	time 2.2813 (2.2092)	loss 4.2572 (3.7843)	grad_norm 1.1274 (1.1963)	
[2022-01-20 04:08:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1200/1251]	eta 0:01:52 lr 0.000829	time 1.6722 (2.2089)	loss 3.3758 (3.7848)	grad_norm 1.1816 (1.1959)	
[2022-01-20 04:08:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1210/1251]	eta 0:01:30 lr 0.000829	time 1.8946 (2.2083)	loss 3.1100 (3.7836)	grad_norm 1.1013 (1.1960)	
[2022-01-20 04:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1220/1251]	eta 0:01:08 lr 0.000829	time 1.9458 (2.2080)	loss 3.5500 (3.7842)	grad_norm 1.0648 (1.1956)	
[2022-01-20 04:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1230/1251]	eta 0:00:46 lr 0.000829	time 2.4446 (2.2098)	loss 4.3935 (3.7852)	grad_norm 1.1747 (1.1957)	
[2022-01-20 04:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1240/1251]	eta 0:00:24 lr 0.000828	time 1.1855 (2.2094)	loss 3.4348 (3.7846)	grad_norm 1.2608 (1.1958)	
[2022-01-20 04:09:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [81/300][1250/1251]	eta 0:00:02 lr 0.000828	time 1.1709 (2.2034)	loss 3.9642 (3.7875)	grad_norm 1.2563 (1.1965)	
[2022-01-20 04:09:47 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 81 training takes 0:45:56
[2022-01-20 04:10:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.455 (18.455)	Loss 1.2080 (1.2080)	Acc@1 71.289 (71.289)	Acc@5 91.016 (91.016)	
[2022-01-20 04:10:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.988 (3.385)	Loss 1.1678 (1.1768)	Acc@1 71.973 (71.964)	Acc@5 91.602 (91.468)	
[2022-01-20 04:10:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.303 (2.483)	Loss 1.1568 (1.1770)	Acc@1 72.754 (72.270)	Acc@5 91.602 (91.448)	
[2022-01-20 04:10:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.958 (2.301)	Loss 1.2065 (1.1708)	Acc@1 71.582 (72.499)	Acc@5 91.113 (91.554)	
[2022-01-20 04:11:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.856 (2.145)	Loss 1.1031 (1.1652)	Acc@1 73.340 (72.649)	Acc@5 93.262 (91.592)	
[2022-01-20 04:11:24 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.686 Acc@5 91.536
[2022-01-20 04:11:24 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.7%
[2022-01-20 04:11:24 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.69%
[2022-01-20 04:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][0/1251]	eta 7:26:03 lr 0.000828	time 21.3936 (21.3936)	loss 2.8072 (2.8072)	grad_norm 1.3173 (1.3173)	
[2022-01-20 04:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][10/1251]	eta 1:24:02 lr 0.000828	time 2.5875 (4.0636)	loss 3.9719 (3.8596)	grad_norm 1.1013 (1.1682)	
[2022-01-20 04:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][20/1251]	eta 1:05:14 lr 0.000828	time 1.8873 (3.1796)	loss 3.9473 (3.7703)	grad_norm 1.0068 (1.1778)	
[2022-01-20 04:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][30/1251]	eta 0:58:09 lr 0.000828	time 1.8525 (2.8580)	loss 3.8479 (3.7242)	grad_norm 1.1911 (1.1598)	
[2022-01-20 04:13:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][40/1251]	eta 0:55:23 lr 0.000828	time 4.7228 (2.7446)	loss 4.0142 (3.8068)	grad_norm 1.1378 (1.1796)	
[2022-01-20 04:13:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][50/1251]	eta 0:52:35 lr 0.000828	time 2.1723 (2.6278)	loss 4.3508 (3.8156)	grad_norm 1.3873 (1.1964)	
[2022-01-20 04:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][60/1251]	eta 0:50:12 lr 0.000828	time 1.2227 (2.5295)	loss 4.2342 (3.7944)	grad_norm 1.1027 (1.2018)	
[2022-01-20 04:14:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][70/1251]	eta 0:48:33 lr 0.000828	time 1.8692 (2.4667)	loss 3.7488 (3.7913)	grad_norm 1.2437 (1.2095)	
[2022-01-20 04:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][80/1251]	eta 0:47:25 lr 0.000828	time 3.0506 (2.4298)	loss 2.7745 (3.7483)	grad_norm 1.1999 (1.2049)	
[2022-01-20 04:15:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][90/1251]	eta 0:46:40 lr 0.000828	time 2.9836 (2.4123)	loss 4.8239 (3.7726)	grad_norm 1.2289 (1.2046)	
[2022-01-20 04:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][100/1251]	eta 0:45:54 lr 0.000828	time 2.1830 (2.3933)	loss 4.1280 (3.7773)	grad_norm 1.2294 (1.2009)	
[2022-01-20 04:15:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][110/1251]	eta 0:45:10 lr 0.000828	time 1.5496 (2.3757)	loss 3.6813 (3.7848)	grad_norm 1.1217 (1.2017)	
[2022-01-20 04:16:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][120/1251]	eta 0:45:00 lr 0.000828	time 3.7814 (2.3877)	loss 4.2191 (3.7839)	grad_norm 1.4869 (1.2046)	
[2022-01-20 04:16:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][130/1251]	eta 0:44:27 lr 0.000828	time 2.5062 (2.3798)	loss 4.1826 (3.7770)	grad_norm 1.3004 (1.2042)	
[2022-01-20 04:16:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][140/1251]	eta 0:43:56 lr 0.000828	time 2.6292 (2.3729)	loss 3.5072 (3.7825)	grad_norm 1.2839 (1.2019)	
[2022-01-20 04:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][150/1251]	eta 0:43:10 lr 0.000828	time 1.6073 (2.3528)	loss 3.6590 (3.7929)	grad_norm 1.1136 (1.2017)	
[2022-01-20 04:17:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][160/1251]	eta 0:42:27 lr 0.000828	time 2.9157 (2.3350)	loss 4.1081 (3.8012)	grad_norm 1.0939 (1.1989)	
[2022-01-20 04:18:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][170/1251]	eta 0:41:48 lr 0.000828	time 2.8655 (2.3209)	loss 4.2359 (3.7865)	grad_norm 1.2327 (1.2005)	
[2022-01-20 04:18:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][180/1251]	eta 0:41:16 lr 0.000828	time 2.2889 (2.3125)	loss 3.4900 (3.7889)	grad_norm 1.2339 (1.1997)	
[2022-01-20 04:18:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][190/1251]	eta 0:40:42 lr 0.000828	time 1.8572 (2.3021)	loss 3.6395 (3.8000)	grad_norm 1.0230 (1.2002)	
[2022-01-20 04:19:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][200/1251]	eta 0:40:19 lr 0.000828	time 2.5873 (2.3025)	loss 2.9618 (3.7974)	grad_norm 1.2196 (1.2023)	
[2022-01-20 04:19:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][210/1251]	eta 0:39:47 lr 0.000828	time 1.5814 (2.2931)	loss 3.4630 (3.7969)	grad_norm 1.2967 (1.2033)	
[2022-01-20 04:19:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][220/1251]	eta 0:39:10 lr 0.000828	time 1.6703 (2.2798)	loss 3.2510 (3.7876)	grad_norm 1.6780 (1.2063)	
[2022-01-20 04:20:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][230/1251]	eta 0:38:45 lr 0.000828	time 2.1004 (2.2776)	loss 4.4306 (3.7892)	grad_norm 1.3565 (1.2072)	
[2022-01-20 04:20:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][240/1251]	eta 0:38:13 lr 0.000828	time 1.8597 (2.2689)	loss 3.0749 (3.7953)	grad_norm 1.1701 (1.2057)	
[2022-01-20 04:20:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][250/1251]	eta 0:37:51 lr 0.000828	time 1.5674 (2.2691)	loss 3.3381 (3.7917)	grad_norm 1.1220 (1.2026)	
[2022-01-20 04:21:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][260/1251]	eta 0:37:22 lr 0.000828	time 1.5583 (2.2629)	loss 4.2443 (3.7986)	grad_norm 1.2205 (1.2033)	
[2022-01-20 04:21:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][270/1251]	eta 0:37:01 lr 0.000828	time 2.5868 (2.2642)	loss 4.1352 (3.8021)	grad_norm 1.1845 (1.2009)	
[2022-01-20 04:21:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][280/1251]	eta 0:36:35 lr 0.000828	time 1.7283 (2.2615)	loss 3.8533 (3.8013)	grad_norm 1.1249 (1.2021)	
[2022-01-20 04:22:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][290/1251]	eta 0:36:16 lr 0.000828	time 2.1494 (2.2645)	loss 4.3634 (3.8098)	grad_norm 1.0579 (1.2009)	
[2022-01-20 04:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][300/1251]	eta 0:35:51 lr 0.000828	time 1.8950 (2.2620)	loss 4.2652 (3.8023)	grad_norm 1.1119 (1.2006)	
[2022-01-20 04:23:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][310/1251]	eta 0:35:28 lr 0.000827	time 2.6113 (2.2617)	loss 2.8506 (3.7982)	grad_norm 1.1128 (1.1990)	
[2022-01-20 04:23:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][320/1251]	eta 0:34:59 lr 0.000827	time 1.8284 (2.2555)	loss 3.0350 (3.7919)	grad_norm 1.3515 (1.1985)	
[2022-01-20 04:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][330/1251]	eta 0:34:35 lr 0.000827	time 2.5437 (2.2538)	loss 2.8175 (3.7950)	grad_norm 1.0610 (1.1965)	
[2022-01-20 04:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][340/1251]	eta 0:34:09 lr 0.000827	time 2.2444 (2.2498)	loss 4.3789 (3.7966)	grad_norm 1.1544 (1.1947)	
[2022-01-20 04:24:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][350/1251]	eta 0:33:40 lr 0.000827	time 1.6601 (2.2428)	loss 4.3198 (3.7963)	grad_norm 1.2402 (1.1935)	
[2022-01-20 04:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][360/1251]	eta 0:33:18 lr 0.000827	time 2.0841 (2.2425)	loss 3.5665 (3.8005)	grad_norm 1.1116 (1.1938)	
[2022-01-20 04:25:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][370/1251]	eta 0:33:00 lr 0.000827	time 2.6271 (2.2477)	loss 3.5930 (3.7969)	grad_norm 1.1158 (1.1919)	
[2022-01-20 04:25:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][380/1251]	eta 0:32:37 lr 0.000827	time 2.5101 (2.2470)	loss 4.3133 (3.7945)	grad_norm 1.2138 (1.1917)	
[2022-01-20 04:26:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][390/1251]	eta 0:32:11 lr 0.000827	time 1.7331 (2.2431)	loss 4.5556 (3.7954)	grad_norm 1.3160 (1.1944)	
[2022-01-20 04:26:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][400/1251]	eta 0:31:46 lr 0.000827	time 2.5015 (2.2400)	loss 3.0416 (3.7969)	grad_norm 1.2032 (1.1957)	
[2022-01-20 04:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][410/1251]	eta 0:31:22 lr 0.000827	time 2.2112 (2.2385)	loss 3.9589 (3.8004)	grad_norm 1.3180 (1.1955)	
[2022-01-20 04:27:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][420/1251]	eta 0:30:58 lr 0.000827	time 2.3375 (2.2366)	loss 4.3146 (3.7996)	grad_norm 1.0830 (1.1953)	
[2022-01-20 04:27:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][430/1251]	eta 0:30:36 lr 0.000827	time 2.0424 (2.2365)	loss 2.6297 (3.7919)	grad_norm 1.3131 (1.1939)	
[2022-01-20 04:27:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][440/1251]	eta 0:30:15 lr 0.000827	time 2.8863 (2.2386)	loss 4.2090 (3.7904)	grad_norm 1.2508 (1.1950)	
[2022-01-20 04:28:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][450/1251]	eta 0:29:51 lr 0.000827	time 2.1477 (2.2362)	loss 4.1235 (3.7906)	grad_norm 1.2003 (1.1946)	
[2022-01-20 04:28:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][460/1251]	eta 0:29:27 lr 0.000827	time 1.8595 (2.2341)	loss 3.9740 (3.7905)	grad_norm 1.2542 (1.1937)	
[2022-01-20 04:28:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][470/1251]	eta 0:29:02 lr 0.000827	time 2.2032 (2.2309)	loss 3.5293 (3.7867)	grad_norm 1.3651 (1.1928)	
[2022-01-20 04:29:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][480/1251]	eta 0:28:37 lr 0.000827	time 1.6812 (2.2274)	loss 3.8742 (3.7841)	grad_norm 1.1348 (1.1926)	
[2022-01-20 04:29:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][490/1251]	eta 0:28:15 lr 0.000827	time 2.3026 (2.2282)	loss 3.3358 (3.7878)	grad_norm 1.0831 (1.1912)	
[2022-01-20 04:29:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][500/1251]	eta 0:27:51 lr 0.000827	time 1.9434 (2.2259)	loss 3.8053 (3.7841)	grad_norm 1.1386 (1.1912)	
[2022-01-20 04:30:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][510/1251]	eta 0:27:28 lr 0.000827	time 1.7142 (2.2245)	loss 4.3739 (3.7822)	grad_norm 1.0458 (1.1916)	
[2022-01-20 04:30:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][520/1251]	eta 0:27:04 lr 0.000827	time 1.6627 (2.2222)	loss 4.4490 (3.7798)	grad_norm 1.2139 (1.1911)	
[2022-01-20 04:31:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][530/1251]	eta 0:26:41 lr 0.000827	time 1.7353 (2.2214)	loss 4.2079 (3.7818)	grad_norm 1.1593 (1.1906)	
[2022-01-20 04:31:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][540/1251]	eta 0:26:21 lr 0.000827	time 2.7244 (2.2239)	loss 4.2163 (3.7815)	grad_norm 1.0230 (1.1909)	
[2022-01-20 04:31:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][550/1251]	eta 0:26:01 lr 0.000827	time 2.9234 (2.2274)	loss 3.4336 (3.7837)	grad_norm 1.1489 (1.1913)	
[2022-01-20 04:32:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][560/1251]	eta 0:25:40 lr 0.000827	time 1.5684 (2.2293)	loss 3.6055 (3.7815)	grad_norm 1.0823 (1.1938)	
[2022-01-20 04:32:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][570/1251]	eta 0:25:17 lr 0.000827	time 1.6387 (2.2287)	loss 3.9540 (3.7795)	grad_norm 1.3863 (1.1960)	
[2022-01-20 04:32:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][580/1251]	eta 0:24:53 lr 0.000827	time 2.1273 (2.2265)	loss 4.1069 (3.7828)	grad_norm 0.9431 (1.1954)	
[2022-01-20 04:33:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][590/1251]	eta 0:24:27 lr 0.000827	time 1.8502 (2.2204)	loss 3.0804 (3.7794)	grad_norm 1.2201 (1.1952)	
[2022-01-20 04:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][600/1251]	eta 0:24:03 lr 0.000827	time 2.1002 (2.2175)	loss 4.4855 (3.7768)	grad_norm 1.0428 (1.1941)	
[2022-01-20 04:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][610/1251]	eta 0:23:40 lr 0.000827	time 2.1774 (2.2157)	loss 4.0547 (3.7807)	grad_norm 1.1104 (1.1954)	
[2022-01-20 04:34:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][620/1251]	eta 0:23:17 lr 0.000826	time 1.9586 (2.2154)	loss 3.2422 (3.7811)	grad_norm 1.3425 (1.1953)	
[2022-01-20 04:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][630/1251]	eta 0:22:54 lr 0.000826	time 2.1823 (2.2138)	loss 4.2059 (3.7838)	grad_norm 1.6272 (1.1962)	
[2022-01-20 04:35:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][640/1251]	eta 0:22:32 lr 0.000826	time 2.5012 (2.2143)	loss 3.8152 (3.7834)	grad_norm 1.0865 (1.1961)	
[2022-01-20 04:35:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][650/1251]	eta 0:22:11 lr 0.000826	time 2.5238 (2.2148)	loss 4.7039 (3.7865)	grad_norm 1.0495 (1.1953)	
[2022-01-20 04:35:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][660/1251]	eta 0:21:48 lr 0.000826	time 2.3517 (2.2133)	loss 3.1879 (3.7885)	grad_norm 1.2036 (1.1945)	
[2022-01-20 04:36:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][670/1251]	eta 0:21:25 lr 0.000826	time 2.0736 (2.2124)	loss 2.5435 (3.7833)	grad_norm 1.0343 (1.1932)	
[2022-01-20 04:36:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][680/1251]	eta 0:21:03 lr 0.000826	time 3.1442 (2.2122)	loss 3.0487 (3.7829)	grad_norm 1.0066 (1.1922)	
[2022-01-20 04:36:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][690/1251]	eta 0:20:40 lr 0.000826	time 1.9531 (2.2113)	loss 4.5261 (3.7865)	grad_norm 1.2040 (1.1923)	
[2022-01-20 04:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][700/1251]	eta 0:20:18 lr 0.000826	time 2.2406 (2.2120)	loss 4.3631 (3.7899)	grad_norm 1.2480 (1.1922)	
[2022-01-20 04:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][710/1251]	eta 0:19:56 lr 0.000826	time 1.9032 (2.2122)	loss 2.8994 (3.7897)	grad_norm 1.3404 (1.1945)	
[2022-01-20 04:38:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][720/1251]	eta 0:19:36 lr 0.000826	time 3.1101 (2.2155)	loss 4.0653 (3.7893)	grad_norm 1.2606 (1.1947)	
[2022-01-20 04:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][730/1251]	eta 0:19:15 lr 0.000826	time 2.2947 (2.2187)	loss 4.2773 (3.7880)	grad_norm 1.1349 (1.1954)	
[2022-01-20 04:38:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][740/1251]	eta 0:18:53 lr 0.000826	time 1.6265 (2.2178)	loss 4.3761 (3.7871)	grad_norm 1.0801 (1.1941)	
[2022-01-20 04:39:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][750/1251]	eta 0:18:29 lr 0.000826	time 1.9226 (2.2144)	loss 4.1160 (3.7881)	grad_norm 1.1939 (1.1940)	
[2022-01-20 04:39:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][760/1251]	eta 0:18:06 lr 0.000826	time 2.8208 (2.2124)	loss 3.8418 (3.7879)	grad_norm 1.3802 (1.1937)	
[2022-01-20 04:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][770/1251]	eta 0:17:43 lr 0.000826	time 2.2362 (2.2113)	loss 2.6961 (3.7846)	grad_norm 1.1769 (1.1945)	
[2022-01-20 04:40:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][780/1251]	eta 0:17:21 lr 0.000826	time 1.9384 (2.2108)	loss 3.8043 (3.7824)	grad_norm 1.4218 (1.1945)	
[2022-01-20 04:40:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][790/1251]	eta 0:16:59 lr 0.000826	time 2.3904 (2.2120)	loss 4.3959 (3.7872)	grad_norm 1.1542 (1.1949)	
[2022-01-20 04:40:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][800/1251]	eta 0:16:38 lr 0.000826	time 3.3457 (2.2143)	loss 3.0474 (3.7879)	grad_norm 0.9612 (1.1948)	
[2022-01-20 04:41:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][810/1251]	eta 0:16:16 lr 0.000826	time 2.3122 (2.2148)	loss 3.9787 (3.7894)	grad_norm 1.1592 (1.1951)	
[2022-01-20 04:41:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][820/1251]	eta 0:15:54 lr 0.000826	time 1.9513 (2.2150)	loss 4.2950 (3.7909)	grad_norm 1.5794 (1.1969)	
[2022-01-20 04:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][830/1251]	eta 0:15:32 lr 0.000826	time 1.5301 (2.2139)	loss 3.3530 (3.7917)	grad_norm 1.1516 (1.1967)	
[2022-01-20 04:42:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][840/1251]	eta 0:15:09 lr 0.000826	time 3.0059 (2.2134)	loss 3.4548 (3.7946)	grad_norm 1.1538 (1.1967)	
[2022-01-20 04:42:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][850/1251]	eta 0:14:46 lr 0.000826	time 2.1093 (2.2119)	loss 4.6550 (3.7977)	grad_norm 1.2239 (1.1963)	
[2022-01-20 04:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][860/1251]	eta 0:14:24 lr 0.000826	time 2.2745 (2.2114)	loss 4.7191 (3.7945)	grad_norm 1.1761 (1.1972)	
[2022-01-20 04:43:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][870/1251]	eta 0:14:02 lr 0.000826	time 1.8190 (2.2101)	loss 3.4003 (3.7897)	grad_norm 1.1975 (1.1972)	
[2022-01-20 04:43:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][880/1251]	eta 0:13:39 lr 0.000826	time 2.4005 (2.2093)	loss 3.8669 (3.7906)	grad_norm 1.1285 (1.1975)	
[2022-01-20 04:44:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][890/1251]	eta 0:13:16 lr 0.000826	time 2.3978 (2.2076)	loss 4.2210 (3.7915)	grad_norm 1.1616 (1.1973)	
[2022-01-20 04:44:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][900/1251]	eta 0:12:54 lr 0.000826	time 2.1661 (2.2072)	loss 3.9387 (3.7918)	grad_norm 1.1664 (1.1978)	
[2022-01-20 04:44:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][910/1251]	eta 0:12:32 lr 0.000826	time 2.0011 (2.2075)	loss 4.1540 (3.7907)	grad_norm 1.3508 (1.1982)	
[2022-01-20 04:45:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][920/1251]	eta 0:12:10 lr 0.000826	time 2.4429 (2.2081)	loss 3.9968 (3.7914)	grad_norm 1.1209 (1.1987)	
[2022-01-20 04:45:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][930/1251]	eta 0:11:49 lr 0.000826	time 2.5060 (2.2091)	loss 4.2459 (3.7920)	grad_norm 1.0536 (1.1989)	
[2022-01-20 04:46:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][940/1251]	eta 0:11:26 lr 0.000825	time 1.9334 (2.2090)	loss 3.5975 (3.7919)	grad_norm 1.6617 (1.2014)	
[2022-01-20 04:46:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][950/1251]	eta 0:11:04 lr 0.000825	time 2.2553 (2.2075)	loss 3.9366 (3.7915)	grad_norm 1.1100 (1.2016)	
[2022-01-20 04:46:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][960/1251]	eta 0:10:41 lr 0.000825	time 1.7486 (2.2051)	loss 3.5853 (3.7938)	grad_norm 1.2311 (1.2017)	
[2022-01-20 04:47:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][970/1251]	eta 0:10:19 lr 0.000825	time 2.2280 (2.2062)	loss 4.0160 (3.7894)	grad_norm 1.3454 (1.2012)	
[2022-01-20 04:47:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][980/1251]	eta 0:09:58 lr 0.000825	time 2.3112 (2.2079)	loss 3.3623 (3.7911)	grad_norm 1.1534 (1.2014)	
[2022-01-20 04:47:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][990/1251]	eta 0:09:36 lr 0.000825	time 2.2498 (2.2073)	loss 4.1103 (3.7930)	grad_norm 1.3759 (1.2021)	
[2022-01-20 04:48:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1000/1251]	eta 0:09:14 lr 0.000825	time 1.7803 (2.2072)	loss 3.1212 (3.7916)	grad_norm 1.1226 (1.2016)	
[2022-01-20 04:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1010/1251]	eta 0:08:51 lr 0.000825	time 2.3131 (2.2073)	loss 2.4630 (3.7908)	grad_norm 1.0909 (1.2007)	
[2022-01-20 04:48:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1020/1251]	eta 0:08:29 lr 0.000825	time 1.8016 (2.2063)	loss 3.9070 (3.7898)	grad_norm 1.1462 (1.2003)	
[2022-01-20 04:49:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1030/1251]	eta 0:08:07 lr 0.000825	time 2.1499 (2.2045)	loss 3.6512 (3.7876)	grad_norm 1.2477 (1.1998)	
[2022-01-20 04:49:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1040/1251]	eta 0:07:44 lr 0.000825	time 1.5980 (2.2035)	loss 2.8595 (3.7863)	grad_norm 1.2552 (1.2000)	
[2022-01-20 04:49:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1050/1251]	eta 0:07:22 lr 0.000825	time 2.5688 (2.2032)	loss 4.5099 (3.7852)	grad_norm 1.1854 (1.2000)	
[2022-01-20 04:50:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1060/1251]	eta 0:07:00 lr 0.000825	time 1.8756 (2.2029)	loss 3.6426 (3.7862)	grad_norm 1.1696 (1.2006)	
[2022-01-20 04:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1070/1251]	eta 0:06:38 lr 0.000825	time 2.2978 (2.2034)	loss 3.7177 (3.7865)	grad_norm 1.1170 (1.2001)	
[2022-01-20 04:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1080/1251]	eta 0:06:16 lr 0.000825	time 2.2112 (2.2019)	loss 4.0333 (3.7862)	grad_norm 1.1911 (1.1999)	
[2022-01-20 04:51:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1090/1251]	eta 0:05:54 lr 0.000825	time 2.4174 (2.2016)	loss 4.4880 (3.7874)	grad_norm 1.4929 (1.1998)	
[2022-01-20 04:51:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1100/1251]	eta 0:05:32 lr 0.000825	time 2.4613 (2.2026)	loss 4.0466 (3.7882)	grad_norm 1.3475 (1.1993)	
[2022-01-20 04:52:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1110/1251]	eta 0:05:10 lr 0.000825	time 3.0594 (2.2040)	loss 4.0409 (3.7883)	grad_norm 1.0675 (1.1988)	
[2022-01-20 04:52:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1120/1251]	eta 0:04:48 lr 0.000825	time 2.2396 (2.2040)	loss 4.1318 (3.7877)	grad_norm 1.0905 (1.1980)	
[2022-01-20 04:52:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1130/1251]	eta 0:04:26 lr 0.000825	time 2.2899 (2.2040)	loss 4.0127 (3.7876)	grad_norm 1.1899 (1.1979)	
[2022-01-20 04:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1140/1251]	eta 0:04:04 lr 0.000825	time 2.7377 (2.2042)	loss 3.2005 (3.7859)	grad_norm 1.0788 (1.1978)	
[2022-01-20 04:53:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1150/1251]	eta 0:03:42 lr 0.000825	time 1.6398 (2.2025)	loss 3.0094 (3.7855)	grad_norm 1.1257 (1.1972)	
[2022-01-20 04:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1160/1251]	eta 0:03:20 lr 0.000825	time 1.5300 (2.2008)	loss 3.8056 (3.7837)	grad_norm 1.0724 (1.1969)	
[2022-01-20 04:54:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1170/1251]	eta 0:02:58 lr 0.000825	time 1.8984 (2.1991)	loss 2.9375 (3.7824)	grad_norm 1.2177 (1.1967)	
[2022-01-20 04:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1180/1251]	eta 0:02:36 lr 0.000825	time 1.8919 (2.1977)	loss 2.8940 (3.7826)	grad_norm 1.2271 (1.1975)	
[2022-01-20 04:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1190/1251]	eta 0:02:14 lr 0.000825	time 2.1090 (2.1971)	loss 3.9085 (3.7800)	grad_norm 1.2776 (1.1979)	
[2022-01-20 04:55:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1200/1251]	eta 0:01:52 lr 0.000825	time 2.1819 (2.1984)	loss 4.4651 (3.7806)	grad_norm 1.0517 (1.1973)	
[2022-01-20 04:55:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1210/1251]	eta 0:01:30 lr 0.000825	time 2.5047 (2.2006)	loss 4.0352 (3.7811)	grad_norm 1.1042 (1.1967)	
[2022-01-20 04:56:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1220/1251]	eta 0:01:08 lr 0.000825	time 3.4767 (2.2024)	loss 3.4997 (3.7799)	grad_norm 1.2226 (1.1965)	
[2022-01-20 04:56:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1230/1251]	eta 0:00:46 lr 0.000825	time 2.2065 (2.2017)	loss 4.0661 (3.7804)	grad_norm 1.1683 (1.1966)	
[2022-01-20 04:56:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1240/1251]	eta 0:00:24 lr 0.000825	time 1.8003 (2.1997)	loss 2.7383 (3.7801)	grad_norm 1.0461 (1.1962)	
[2022-01-20 04:57:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [82/300][1250/1251]	eta 0:00:02 lr 0.000825	time 1.2125 (2.1937)	loss 3.9581 (3.7795)	grad_norm 0.9867 (1.1955)	
[2022-01-20 04:57:08 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 82 training takes 0:45:44
[2022-01-20 04:57:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.447 (18.447)	Loss 1.2359 (1.2359)	Acc@1 71.582 (71.582)	Acc@5 91.309 (91.309)	
[2022-01-20 04:57:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.659 (3.444)	Loss 1.2331 (1.1964)	Acc@1 71.582 (72.363)	Acc@5 90.430 (91.744)	
[2022-01-20 04:58:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.285 (2.479)	Loss 1.0665 (1.1812)	Acc@1 75.977 (72.917)	Acc@5 92.969 (91.713)	
[2022-01-20 04:58:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.634 (2.243)	Loss 1.2169 (1.1872)	Acc@1 73.145 (72.763)	Acc@5 91.504 (91.696)	
[2022-01-20 04:58:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.061 (2.145)	Loss 1.1712 (1.1890)	Acc@1 72.070 (72.694)	Acc@5 92.480 (91.647)	
[2022-01-20 04:58:44 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.656 Acc@5 91.582
[2022-01-20 04:58:44 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.7%
[2022-01-20 04:58:44 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.69%
[2022-01-20 04:59:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][0/1251]	eta 7:21:35 lr 0.000825	time 21.1794 (21.1794)	loss 3.4715 (3.4715)	grad_norm 1.2809 (1.2809)	
[2022-01-20 04:59:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][10/1251]	eta 1:24:37 lr 0.000824	time 1.8704 (4.0913)	loss 3.6579 (3.7615)	grad_norm 1.0710 (1.1443)	
[2022-01-20 04:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][20/1251]	eta 1:04:52 lr 0.000824	time 2.3047 (3.1619)	loss 4.6743 (3.7436)	grad_norm 1.1104 (1.1594)	
[2022-01-20 05:00:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][30/1251]	eta 0:57:11 lr 0.000824	time 1.8967 (2.8103)	loss 3.7312 (3.7341)	grad_norm 1.2691 (1.1890)	
[2022-01-20 05:00:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][40/1251]	eta 0:54:30 lr 0.000824	time 3.9039 (2.7007)	loss 3.2993 (3.7348)	grad_norm 1.1052 (1.1965)	
[2022-01-20 05:00:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][50/1251]	eta 0:52:52 lr 0.000824	time 1.8586 (2.6412)	loss 3.9060 (3.7760)	grad_norm 1.0027 (1.1934)	
[2022-01-20 05:01:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][60/1251]	eta 0:50:45 lr 0.000824	time 1.4619 (2.5573)	loss 4.1505 (3.8153)	grad_norm 1.0681 (1.1864)	
[2022-01-20 05:01:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][70/1251]	eta 0:49:39 lr 0.000824	time 1.7875 (2.5232)	loss 4.1542 (3.7958)	grad_norm 1.2716 (1.1893)	
[2022-01-20 05:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][80/1251]	eta 0:49:08 lr 0.000824	time 3.8411 (2.5181)	loss 4.5413 (3.8156)	grad_norm 1.5300 (1.1911)	
[2022-01-20 05:02:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][90/1251]	eta 0:48:05 lr 0.000824	time 1.8665 (2.4851)	loss 3.5554 (3.8246)	grad_norm 1.4369 (1.2118)	
[2022-01-20 05:02:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][100/1251]	eta 0:46:48 lr 0.000824	time 1.8854 (2.4401)	loss 3.4656 (3.8445)	grad_norm 1.4028 (1.2136)	
[2022-01-20 05:03:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][110/1251]	eta 0:45:35 lr 0.000824	time 1.8695 (2.3973)	loss 3.3871 (3.8288)	grad_norm 1.1523 (1.2069)	
[2022-01-20 05:03:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][120/1251]	eta 0:45:05 lr 0.000824	time 4.4323 (2.3921)	loss 4.2274 (3.8523)	grad_norm 1.3775 (1.2113)	
[2022-01-20 05:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][130/1251]	eta 0:44:28 lr 0.000824	time 1.7694 (2.3806)	loss 2.7494 (3.8210)	grad_norm 1.3457 (1.2127)	
[2022-01-20 05:04:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][140/1251]	eta 0:44:02 lr 0.000824	time 2.1706 (2.3781)	loss 4.2252 (3.8343)	grad_norm 1.1704 (1.2074)	
[2022-01-20 05:04:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][150/1251]	eta 0:43:23 lr 0.000824	time 2.1479 (2.3645)	loss 3.7576 (3.8244)	grad_norm 1.0582 (1.2069)	
[2022-01-20 05:05:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][160/1251]	eta 0:42:31 lr 0.000824	time 2.1290 (2.3389)	loss 4.1730 (3.8254)	grad_norm 1.1513 (1.2018)	
[2022-01-20 05:05:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][170/1251]	eta 0:41:52 lr 0.000824	time 2.4168 (2.3245)	loss 4.1203 (3.8196)	grad_norm 1.0151 (1.2000)	
[2022-01-20 05:05:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][180/1251]	eta 0:41:24 lr 0.000824	time 2.0023 (2.3198)	loss 4.1693 (3.8141)	grad_norm 1.2980 (1.2001)	
[2022-01-20 05:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][190/1251]	eta 0:40:56 lr 0.000824	time 2.2768 (2.3155)	loss 3.8869 (3.8095)	grad_norm 1.1102 (1.1975)	
[2022-01-20 05:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][200/1251]	eta 0:40:26 lr 0.000824	time 1.9697 (2.3089)	loss 3.3496 (3.8094)	grad_norm 1.2239 (1.1942)	
[2022-01-20 05:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][210/1251]	eta 0:39:58 lr 0.000824	time 2.2531 (2.3042)	loss 4.4077 (3.8048)	grad_norm 1.2613 (1.1950)	
[2022-01-20 05:07:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][220/1251]	eta 0:39:34 lr 0.000824	time 3.6350 (2.3026)	loss 4.3456 (3.8164)	grad_norm 1.1121 (1.1933)	
[2022-01-20 05:07:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][230/1251]	eta 0:39:01 lr 0.000824	time 2.1565 (2.2937)	loss 4.1145 (3.8166)	grad_norm 1.2916 (1.1955)	
[2022-01-20 05:07:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][240/1251]	eta 0:38:28 lr 0.000824	time 1.6203 (2.2834)	loss 3.1180 (3.8187)	grad_norm 1.1548 (1.1993)	
[2022-01-20 05:08:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][250/1251]	eta 0:38:00 lr 0.000824	time 2.3281 (2.2781)	loss 3.3480 (3.8123)	grad_norm 1.1644 (1.1980)	
[2022-01-20 05:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][260/1251]	eta 0:37:39 lr 0.000824	time 4.0139 (2.2799)	loss 2.5810 (3.8051)	grad_norm 1.1728 (1.2002)	
[2022-01-20 05:09:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][270/1251]	eta 0:37:12 lr 0.000824	time 1.6711 (2.2761)	loss 2.7046 (3.7972)	grad_norm 1.1391 (1.1990)	
[2022-01-20 05:09:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][280/1251]	eta 0:36:46 lr 0.000824	time 2.1334 (2.2728)	loss 2.7733 (3.7965)	grad_norm 1.1503 (1.1992)	
[2022-01-20 05:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][290/1251]	eta 0:36:21 lr 0.000824	time 1.8637 (2.2698)	loss 4.4280 (3.7911)	grad_norm 1.0975 (1.1996)	
[2022-01-20 05:10:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][300/1251]	eta 0:35:50 lr 0.000824	time 1.8684 (2.2615)	loss 4.1137 (3.7934)	grad_norm 1.0975 (1.1988)	
[2022-01-20 05:10:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][310/1251]	eta 0:35:19 lr 0.000824	time 2.1550 (2.2525)	loss 2.7721 (3.7767)	grad_norm 1.3704 (1.1959)	
[2022-01-20 05:10:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][320/1251]	eta 0:34:56 lr 0.000823	time 2.9808 (2.2516)	loss 3.3508 (3.7745)	grad_norm 0.9896 (1.1940)	
[2022-01-20 05:11:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][330/1251]	eta 0:34:34 lr 0.000823	time 2.0881 (2.2525)	loss 4.4965 (3.7721)	grad_norm 1.1327 (1.1976)	
[2022-01-20 05:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][340/1251]	eta 0:34:14 lr 0.000823	time 2.0053 (2.2549)	loss 3.9549 (3.7749)	grad_norm 1.2243 (1.1998)	
[2022-01-20 05:11:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][350/1251]	eta 0:33:53 lr 0.000823	time 1.9537 (2.2566)	loss 3.9270 (3.7779)	grad_norm 1.2382 (1.2009)	
[2022-01-20 05:12:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][360/1251]	eta 0:33:28 lr 0.000823	time 2.4734 (2.2542)	loss 4.0024 (3.7794)	grad_norm 1.1626 (1.2012)	
[2022-01-20 05:12:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][370/1251]	eta 0:33:03 lr 0.000823	time 2.2221 (2.2518)	loss 3.2587 (3.7786)	grad_norm 1.1863 (1.2009)	
[2022-01-20 05:13:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][380/1251]	eta 0:32:39 lr 0.000823	time 1.6521 (2.2500)	loss 4.3630 (3.7774)	grad_norm 1.1781 (1.2012)	
[2022-01-20 05:13:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][390/1251]	eta 0:32:14 lr 0.000823	time 1.9923 (2.2469)	loss 4.3185 (3.7801)	grad_norm 1.0847 (1.2010)	
[2022-01-20 05:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][400/1251]	eta 0:31:50 lr 0.000823	time 2.1175 (2.2449)	loss 3.5955 (3.7796)	grad_norm 1.0727 (1.1998)	
[2022-01-20 05:14:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][410/1251]	eta 0:31:31 lr 0.000823	time 1.7757 (2.2491)	loss 4.0101 (3.7879)	grad_norm 1.4426 (1.1988)	
[2022-01-20 05:14:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][420/1251]	eta 0:31:08 lr 0.000823	time 1.6937 (2.2485)	loss 3.4472 (3.7833)	grad_norm 1.1890 (1.1977)	
[2022-01-20 05:14:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][430/1251]	eta 0:30:42 lr 0.000823	time 1.6959 (2.2443)	loss 4.2982 (3.7814)	grad_norm 1.1883 (1.1968)	
[2022-01-20 05:15:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][440/1251]	eta 0:30:15 lr 0.000823	time 1.5355 (2.2389)	loss 3.6130 (3.7811)	grad_norm 1.1843 (1.1983)	
[2022-01-20 05:15:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][450/1251]	eta 0:29:52 lr 0.000823	time 2.1133 (2.2374)	loss 4.8122 (3.7747)	grad_norm 1.1504 (1.1971)	
[2022-01-20 05:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][460/1251]	eta 0:29:28 lr 0.000823	time 2.1560 (2.2363)	loss 3.5365 (3.7675)	grad_norm 1.5347 (1.1983)	
[2022-01-20 05:16:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][470/1251]	eta 0:29:03 lr 0.000823	time 1.9415 (2.2327)	loss 3.9301 (3.7679)	grad_norm 1.2678 (1.1980)	
[2022-01-20 05:16:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][480/1251]	eta 0:28:42 lr 0.000823	time 2.7298 (2.2336)	loss 3.5060 (3.7705)	grad_norm 1.0824 (1.1970)	
[2022-01-20 05:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][490/1251]	eta 0:28:18 lr 0.000823	time 1.8459 (2.2315)	loss 3.5799 (3.7717)	grad_norm 1.1373 (1.1959)	
[2022-01-20 05:17:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][500/1251]	eta 0:27:56 lr 0.000823	time 2.0159 (2.2324)	loss 3.2049 (3.7680)	grad_norm 1.0843 (1.1955)	
[2022-01-20 05:17:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][510/1251]	eta 0:27:31 lr 0.000823	time 2.2189 (2.2294)	loss 3.9258 (3.7702)	grad_norm 1.3517 (1.1961)	
[2022-01-20 05:18:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][520/1251]	eta 0:27:08 lr 0.000823	time 3.1686 (2.2279)	loss 4.7669 (3.7710)	grad_norm 1.4863 (1.1971)	
[2022-01-20 05:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][530/1251]	eta 0:26:45 lr 0.000823	time 2.0232 (2.2267)	loss 3.3671 (3.7642)	grad_norm 1.1230 (1.1983)	
[2022-01-20 05:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][540/1251]	eta 0:26:22 lr 0.000823	time 2.3328 (2.2259)	loss 4.3507 (3.7674)	grad_norm 1.2678 (1.1995)	
[2022-01-20 05:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][550/1251]	eta 0:25:59 lr 0.000823	time 1.7392 (2.2253)	loss 3.8980 (3.7693)	grad_norm 1.0464 (1.1989)	
[2022-01-20 05:19:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][560/1251]	eta 0:25:36 lr 0.000823	time 2.8465 (2.2239)	loss 3.8889 (3.7681)	grad_norm 1.4244 (1.1991)	
[2022-01-20 05:19:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][570/1251]	eta 0:25:13 lr 0.000823	time 2.5215 (2.2222)	loss 3.2530 (3.7730)	grad_norm 1.2144 (1.2001)	
[2022-01-20 05:20:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][580/1251]	eta 0:24:49 lr 0.000823	time 1.9239 (2.2199)	loss 2.5102 (3.7705)	grad_norm 1.0975 (1.1992)	
[2022-01-20 05:20:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][590/1251]	eta 0:24:26 lr 0.000823	time 2.5921 (2.2185)	loss 4.0522 (3.7669)	grad_norm 1.1863 (1.1985)	
[2022-01-20 05:20:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][600/1251]	eta 0:24:04 lr 0.000823	time 2.8177 (2.2182)	loss 2.8153 (3.7644)	grad_norm 1.1734 (1.1986)	
[2022-01-20 05:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][610/1251]	eta 0:23:41 lr 0.000823	time 1.8896 (2.2181)	loss 4.0491 (3.7691)	grad_norm 1.3682 (1.1987)	
[2022-01-20 05:21:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][620/1251]	eta 0:23:20 lr 0.000823	time 2.0684 (2.2191)	loss 4.3043 (3.7728)	grad_norm 1.0481 (1.1976)	
[2022-01-20 05:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][630/1251]	eta 0:22:59 lr 0.000823	time 2.7891 (2.2216)	loss 3.7386 (3.7706)	grad_norm 1.2609 (1.1967)	
[2022-01-20 05:22:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][640/1251]	eta 0:22:38 lr 0.000822	time 2.5017 (2.2226)	loss 4.0396 (3.7728)	grad_norm 1.0312 (1.1960)	
[2022-01-20 05:22:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][650/1251]	eta 0:22:14 lr 0.000822	time 1.9299 (2.2197)	loss 4.4978 (3.7751)	grad_norm 1.2090 (1.1946)	
[2022-01-20 05:23:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][660/1251]	eta 0:21:49 lr 0.000822	time 1.9359 (2.2155)	loss 4.4545 (3.7764)	grad_norm 1.0621 (1.1934)	
[2022-01-20 05:23:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][670/1251]	eta 0:21:26 lr 0.000822	time 2.8626 (2.2142)	loss 2.9605 (3.7755)	grad_norm 1.0602 (1.1923)	
[2022-01-20 05:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][680/1251]	eta 0:21:02 lr 0.000822	time 2.0294 (2.2118)	loss 2.6656 (3.7723)	grad_norm 1.4483 (1.1926)	
[2022-01-20 05:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][690/1251]	eta 0:20:39 lr 0.000822	time 1.5701 (2.2100)	loss 4.4312 (3.7708)	grad_norm 1.3579 (1.1929)	
[2022-01-20 05:24:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][700/1251]	eta 0:20:17 lr 0.000822	time 2.1784 (2.2102)	loss 2.9232 (3.7689)	grad_norm 1.3622 (1.1936)	
[2022-01-20 05:24:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][710/1251]	eta 0:19:56 lr 0.000822	time 3.0447 (2.2125)	loss 4.0474 (3.7711)	grad_norm 1.1566 (1.1940)	
[2022-01-20 05:25:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][720/1251]	eta 0:19:34 lr 0.000822	time 2.1796 (2.2119)	loss 4.0308 (3.7712)	grad_norm 1.1585 (1.1927)	
[2022-01-20 05:25:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][730/1251]	eta 0:19:11 lr 0.000822	time 1.6741 (2.2111)	loss 3.9896 (3.7692)	grad_norm 1.1887 (1.1935)	
[2022-01-20 05:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][740/1251]	eta 0:18:50 lr 0.000822	time 2.1878 (2.2126)	loss 3.5093 (3.7680)	grad_norm 1.2429 (1.1940)	
[2022-01-20 05:26:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][750/1251]	eta 0:18:30 lr 0.000822	time 3.8036 (2.2163)	loss 4.0609 (3.7701)	grad_norm 1.2462 (1.1945)	
[2022-01-20 05:26:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][760/1251]	eta 0:18:09 lr 0.000822	time 3.1082 (2.2185)	loss 4.4923 (3.7671)	grad_norm 1.3238 (1.1948)	
[2022-01-20 05:27:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][770/1251]	eta 0:17:46 lr 0.000822	time 1.9397 (2.2181)	loss 3.1123 (3.7640)	grad_norm 1.4062 (1.1949)	
[2022-01-20 05:27:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][780/1251]	eta 0:17:23 lr 0.000822	time 1.8237 (2.2161)	loss 4.4245 (3.7664)	grad_norm 1.1107 (1.1958)	
[2022-01-20 05:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][790/1251]	eta 0:17:00 lr 0.000822	time 1.9559 (2.2134)	loss 4.4320 (3.7661)	grad_norm 1.2579 (1.1964)	
[2022-01-20 05:28:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][800/1251]	eta 0:16:37 lr 0.000822	time 3.5899 (2.2128)	loss 3.3534 (3.7640)	grad_norm 1.1495 (1.1957)	
[2022-01-20 05:28:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][810/1251]	eta 0:16:14 lr 0.000822	time 2.1599 (2.2107)	loss 3.3997 (3.7597)	grad_norm 1.0661 (1.1950)	
[2022-01-20 05:28:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][820/1251]	eta 0:15:52 lr 0.000822	time 2.2080 (2.2107)	loss 3.5170 (3.7593)	grad_norm 1.2949 (1.1959)	
[2022-01-20 05:29:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][830/1251]	eta 0:15:31 lr 0.000822	time 2.1495 (2.2114)	loss 3.9470 (3.7581)	grad_norm 1.1235 (1.1960)	
[2022-01-20 05:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][840/1251]	eta 0:15:09 lr 0.000822	time 3.2648 (2.2123)	loss 3.8003 (3.7579)	grad_norm 1.2567 (1.1966)	
[2022-01-20 05:30:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][850/1251]	eta 0:14:46 lr 0.000822	time 2.3034 (2.2113)	loss 3.6990 (3.7581)	grad_norm 1.2250 (1.1957)	
[2022-01-20 05:30:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][860/1251]	eta 0:14:24 lr 0.000822	time 1.7980 (2.2113)	loss 4.5304 (3.7581)	grad_norm 1.1246 (1.1953)	
[2022-01-20 05:30:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][870/1251]	eta 0:14:02 lr 0.000822	time 1.9101 (2.2117)	loss 4.1047 (3.7603)	grad_norm 1.3574 (1.1949)	
[2022-01-20 05:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][880/1251]	eta 0:13:40 lr 0.000822	time 2.8495 (2.2117)	loss 3.3641 (3.7627)	grad_norm 1.2342 (1.1950)	
[2022-01-20 05:31:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][890/1251]	eta 0:13:17 lr 0.000822	time 2.5660 (2.2102)	loss 3.2614 (3.7648)	grad_norm 1.2206 (1.1954)	
[2022-01-20 05:31:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][900/1251]	eta 0:12:55 lr 0.000822	time 2.5677 (2.2087)	loss 3.4530 (3.7646)	grad_norm 1.1579 (1.1954)	
[2022-01-20 05:32:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][910/1251]	eta 0:12:32 lr 0.000822	time 1.5635 (2.2071)	loss 3.5422 (3.7658)	grad_norm 1.1251 (1.1958)	
[2022-01-20 05:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][920/1251]	eta 0:12:10 lr 0.000822	time 1.5534 (2.2059)	loss 4.5899 (3.7641)	grad_norm 1.2994 (1.1970)	
[2022-01-20 05:32:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][930/1251]	eta 0:11:48 lr 0.000822	time 2.5729 (2.2070)	loss 4.2881 (3.7630)	grad_norm 1.0743 (1.1970)	
[2022-01-20 05:33:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][940/1251]	eta 0:11:26 lr 0.000822	time 2.3625 (2.2078)	loss 4.1075 (3.7639)	grad_norm 1.0088 (1.1972)	
[2022-01-20 05:33:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][950/1251]	eta 0:11:04 lr 0.000821	time 1.8337 (2.2080)	loss 4.1785 (3.7650)	grad_norm 1.2087 (1.1975)	
[2022-01-20 05:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][960/1251]	eta 0:10:42 lr 0.000821	time 1.6333 (2.2086)	loss 4.3246 (3.7658)	grad_norm 1.1646 (1.1972)	
[2022-01-20 05:34:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][970/1251]	eta 0:10:20 lr 0.000821	time 2.7504 (2.2082)	loss 2.6032 (3.7671)	grad_norm 1.2049 (1.1975)	
[2022-01-20 05:34:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][980/1251]	eta 0:09:57 lr 0.000821	time 1.8252 (2.2050)	loss 3.8669 (3.7669)	grad_norm 1.1331 (1.1981)	
[2022-01-20 05:35:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][990/1251]	eta 0:09:35 lr 0.000821	time 1.9511 (2.2047)	loss 3.0363 (3.7669)	grad_norm 1.3477 (1.1976)	
[2022-01-20 05:35:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1000/1251]	eta 0:09:13 lr 0.000821	time 1.8878 (2.2046)	loss 4.4407 (3.7657)	grad_norm 1.2628 (1.1971)	
[2022-01-20 05:35:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1010/1251]	eta 0:08:51 lr 0.000821	time 2.5648 (2.2037)	loss 4.2796 (3.7637)	grad_norm 0.9940 (1.1967)	
[2022-01-20 05:36:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1020/1251]	eta 0:08:29 lr 0.000821	time 2.0055 (2.2038)	loss 4.1910 (3.7648)	grad_norm 1.1196 (1.1977)	
[2022-01-20 05:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1030/1251]	eta 0:08:07 lr 0.000821	time 2.1213 (2.2053)	loss 3.7948 (3.7608)	grad_norm 1.1718 (1.1975)	
[2022-01-20 05:36:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1040/1251]	eta 0:07:45 lr 0.000821	time 1.6638 (2.2047)	loss 3.4645 (3.7589)	grad_norm 1.4343 (1.1976)	
[2022-01-20 05:37:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1050/1251]	eta 0:07:22 lr 0.000821	time 1.7762 (2.2040)	loss 4.1834 (3.7584)	grad_norm 1.3132 (1.1978)	
[2022-01-20 05:37:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1060/1251]	eta 0:07:00 lr 0.000821	time 2.6585 (2.2035)	loss 3.5239 (3.7585)	grad_norm 1.2709 (1.1977)	
[2022-01-20 05:38:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1070/1251]	eta 0:06:38 lr 0.000821	time 2.7354 (2.2026)	loss 3.9546 (3.7598)	grad_norm 1.0422 (1.1971)	
[2022-01-20 05:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1080/1251]	eta 0:06:16 lr 0.000821	time 1.4659 (2.2025)	loss 4.2054 (3.7590)	grad_norm 1.1041 (1.1962)	
[2022-01-20 05:38:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1090/1251]	eta 0:05:54 lr 0.000821	time 1.5193 (2.2030)	loss 3.2572 (3.7582)	grad_norm 1.4565 (1.1955)	
[2022-01-20 05:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1100/1251]	eta 0:05:32 lr 0.000821	time 2.1754 (2.2039)	loss 3.4359 (3.7598)	grad_norm 1.3963 (1.1962)	
[2022-01-20 05:39:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1110/1251]	eta 0:05:11 lr 0.000821	time 4.0265 (2.2061)	loss 3.6018 (3.7598)	grad_norm 1.0048 (1.1954)	
[2022-01-20 05:39:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1120/1251]	eta 0:04:48 lr 0.000821	time 1.8359 (2.2055)	loss 4.3692 (3.7595)	grad_norm 1.1056 (1.1953)	
[2022-01-20 05:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1130/1251]	eta 0:04:26 lr 0.000821	time 1.7951 (2.2034)	loss 4.1374 (3.7605)	grad_norm 1.4629 (1.1960)	
[2022-01-20 05:40:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1140/1251]	eta 0:04:04 lr 0.000821	time 2.4740 (2.2025)	loss 4.4263 (3.7600)	grad_norm 1.0864 (1.1954)	
[2022-01-20 05:40:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1150/1251]	eta 0:03:42 lr 0.000821	time 2.5334 (2.2018)	loss 3.0355 (3.7619)	grad_norm 1.1461 (1.1950)	
[2022-01-20 05:41:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1160/1251]	eta 0:03:20 lr 0.000821	time 2.1685 (2.2011)	loss 4.5824 (3.7614)	grad_norm 1.0722 (1.1942)	
[2022-01-20 05:41:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1170/1251]	eta 0:02:58 lr 0.000821	time 1.9250 (2.2011)	loss 4.1884 (3.7642)	grad_norm 1.1813 (1.1942)	
[2022-01-20 05:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1180/1251]	eta 0:02:36 lr 0.000821	time 2.4066 (2.2008)	loss 3.0242 (3.7634)	grad_norm 1.0667 (1.1942)	
[2022-01-20 05:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1190/1251]	eta 0:02:14 lr 0.000821	time 2.2009 (2.2000)	loss 3.6917 (3.7642)	grad_norm 1.0727 (1.1946)	
[2022-01-20 05:42:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1200/1251]	eta 0:01:52 lr 0.000821	time 2.6267 (2.1999)	loss 3.4373 (3.7637)	grad_norm 1.1577 (1.1942)	
[2022-01-20 05:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1210/1251]	eta 0:01:30 lr 0.000821	time 2.5043 (2.2000)	loss 4.0742 (3.7632)	grad_norm 1.0408 (1.1941)	
[2022-01-20 05:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1220/1251]	eta 0:01:08 lr 0.000821	time 2.5381 (2.2010)	loss 4.2537 (3.7630)	grad_norm 1.0989 (1.1938)	
[2022-01-20 05:43:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1230/1251]	eta 0:00:46 lr 0.000821	time 2.5969 (2.2014)	loss 3.4100 (3.7627)	grad_norm 1.2578 (1.1936)	
[2022-01-20 05:44:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1240/1251]	eta 0:00:24 lr 0.000821	time 1.2034 (2.1996)	loss 3.7387 (3.7631)	grad_norm 1.1323 (1.1939)	
[2022-01-20 05:44:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [83/300][1250/1251]	eta 0:00:02 lr 0.000821	time 1.1961 (2.1943)	loss 4.0677 (3.7616)	grad_norm 1.5061 (1.1942)	
[2022-01-20 05:44:29 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 83 training takes 0:45:45
[2022-01-20 05:44:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.093 (18.093)	Loss 1.1823 (1.1823)	Acc@1 72.949 (72.949)	Acc@5 92.285 (92.285)	
[2022-01-20 05:45:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.306 (3.420)	Loss 1.1401 (1.1744)	Acc@1 74.219 (73.136)	Acc@5 91.113 (91.744)	
[2022-01-20 05:45:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.605 (2.575)	Loss 1.1563 (1.1740)	Acc@1 72.852 (73.042)	Acc@5 91.797 (91.825)	
[2022-01-20 05:45:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.006 (2.373)	Loss 1.1388 (1.1755)	Acc@1 72.266 (72.880)	Acc@5 92.480 (91.794)	
[2022-01-20 05:45:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.405 (2.175)	Loss 1.2063 (1.1780)	Acc@1 73.730 (72.842)	Acc@5 90.918 (91.740)	
[2022-01-20 05:46:05 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.936 Acc@5 91.666
[2022-01-20 05:46:05 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.9%
[2022-01-20 05:46:05 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.94%
[2022-01-20 05:46:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][0/1251]	eta 7:20:11 lr 0.000821	time 21.1119 (21.1119)	loss 3.5240 (3.5240)	grad_norm 1.4185 (1.4185)	
[2022-01-20 05:46:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][10/1251]	eta 1:21:20 lr 0.000820	time 1.8499 (3.9324)	loss 2.9182 (3.6047)	grad_norm 1.1942 (1.2492)	
[2022-01-20 05:47:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][20/1251]	eta 1:02:07 lr 0.000820	time 1.4995 (3.0278)	loss 3.9732 (3.7512)	grad_norm 1.1561 (1.2486)	
[2022-01-20 05:47:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][30/1251]	eta 0:56:07 lr 0.000820	time 1.4918 (2.7576)	loss 4.1474 (3.7385)	grad_norm 0.9991 (1.2189)	
[2022-01-20 05:47:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][40/1251]	eta 0:52:55 lr 0.000820	time 3.3344 (2.6225)	loss 4.2389 (3.7942)	grad_norm 1.1367 (1.1985)	
[2022-01-20 05:48:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][50/1251]	eta 0:51:42 lr 0.000820	time 2.2056 (2.5837)	loss 3.3841 (3.7796)	grad_norm 1.1620 (1.1971)	
[2022-01-20 05:48:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][60/1251]	eta 0:50:43 lr 0.000820	time 1.8481 (2.5555)	loss 3.9851 (3.8128)	grad_norm 1.0847 (1.1869)	
[2022-01-20 05:49:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][70/1251]	eta 0:49:00 lr 0.000820	time 1.6709 (2.4898)	loss 3.7934 (3.7939)	grad_norm 1.2024 (1.1874)	
[2022-01-20 05:49:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][80/1251]	eta 0:48:01 lr 0.000820	time 3.4475 (2.4609)	loss 2.5024 (3.7844)	grad_norm 1.3765 (1.1870)	
[2022-01-20 05:49:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][90/1251]	eta 0:47:10 lr 0.000820	time 2.1389 (2.4383)	loss 4.4472 (3.7902)	grad_norm 1.1445 (1.2004)	
[2022-01-20 05:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][100/1251]	eta 0:46:18 lr 0.000820	time 1.5128 (2.4143)	loss 2.8406 (3.7713)	grad_norm 1.0601 (1.2042)	
[2022-01-20 05:50:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][110/1251]	eta 0:45:32 lr 0.000820	time 1.7647 (2.3946)	loss 3.4205 (3.7564)	grad_norm 1.0019 (1.1983)	
[2022-01-20 05:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][120/1251]	eta 0:44:39 lr 0.000820	time 1.8841 (2.3694)	loss 4.2893 (3.7485)	grad_norm 1.9653 (1.2043)	
[2022-01-20 05:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][130/1251]	eta 0:44:06 lr 0.000820	time 1.6668 (2.3608)	loss 4.3351 (3.7726)	grad_norm 1.5065 (1.2093)	
[2022-01-20 05:51:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][140/1251]	eta 0:43:19 lr 0.000820	time 1.6854 (2.3400)	loss 3.8062 (3.7702)	grad_norm 1.1138 (1.2071)	
[2022-01-20 05:51:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][150/1251]	eta 0:42:56 lr 0.000820	time 2.1226 (2.3400)	loss 3.1039 (3.7769)	grad_norm 1.1622 (1.2080)	
[2022-01-20 05:52:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][160/1251]	eta 0:42:18 lr 0.000820	time 1.8839 (2.3271)	loss 4.0960 (3.7755)	grad_norm 1.0050 (1.2057)	
[2022-01-20 05:52:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][170/1251]	eta 0:41:51 lr 0.000820	time 1.7197 (2.3237)	loss 3.6966 (3.7616)	grad_norm 1.2363 (1.2069)	
[2022-01-20 05:53:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][180/1251]	eta 0:41:21 lr 0.000820	time 2.1847 (2.3166)	loss 3.9644 (3.7624)	grad_norm 1.2237 (1.2038)	
[2022-01-20 05:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][190/1251]	eta 0:40:43 lr 0.000820	time 1.7555 (2.3027)	loss 4.0761 (3.7598)	grad_norm 1.1208 (1.1986)	
[2022-01-20 05:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][200/1251]	eta 0:40:08 lr 0.000820	time 1.8804 (2.2915)	loss 4.2139 (3.7601)	grad_norm 1.0764 (1.1958)	
[2022-01-20 05:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][210/1251]	eta 0:39:43 lr 0.000820	time 1.9053 (2.2897)	loss 4.4672 (3.7453)	grad_norm 1.1538 (1.1970)	
[2022-01-20 05:54:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][220/1251]	eta 0:39:22 lr 0.000820	time 2.1302 (2.2919)	loss 4.1002 (3.7457)	grad_norm 1.0963 (1.1992)	
[2022-01-20 05:54:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][230/1251]	eta 0:38:52 lr 0.000820	time 1.8967 (2.2842)	loss 2.8088 (3.7312)	grad_norm 1.2479 (1.1988)	
[2022-01-20 05:55:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][240/1251]	eta 0:38:28 lr 0.000820	time 1.6773 (2.2830)	loss 3.7681 (3.7430)	grad_norm 1.2408 (1.1978)	
[2022-01-20 05:55:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][250/1251]	eta 0:38:02 lr 0.000820	time 2.1725 (2.2804)	loss 3.0543 (3.7342)	grad_norm 1.0858 (1.1977)	
[2022-01-20 05:55:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][260/1251]	eta 0:37:26 lr 0.000820	time 1.9769 (2.2671)	loss 4.3000 (3.7424)	grad_norm 1.1946 (1.1980)	
[2022-01-20 05:56:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][270/1251]	eta 0:36:57 lr 0.000820	time 1.7865 (2.2602)	loss 3.9027 (3.7459)	grad_norm 1.2399 (1.2022)	
[2022-01-20 05:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][280/1251]	eta 0:36:34 lr 0.000820	time 2.2376 (2.2602)	loss 2.5374 (3.7338)	grad_norm 1.1854 (1.2031)	
[2022-01-20 05:57:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][290/1251]	eta 0:36:08 lr 0.000820	time 1.8956 (2.2565)	loss 4.0874 (3.7370)	grad_norm 1.1568 (1.2032)	
[2022-01-20 05:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][300/1251]	eta 0:35:42 lr 0.000820	time 2.1111 (2.2532)	loss 2.7718 (3.7365)	grad_norm 1.0613 (1.2034)	
[2022-01-20 05:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][310/1251]	eta 0:35:20 lr 0.000820	time 1.8569 (2.2536)	loss 4.5347 (3.7459)	grad_norm 1.1967 (1.2031)	
[2022-01-20 05:58:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][320/1251]	eta 0:35:01 lr 0.000820	time 2.7433 (2.2570)	loss 2.8394 (3.7471)	grad_norm 1.1204 (1.2009)	
[2022-01-20 05:58:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][330/1251]	eta 0:34:39 lr 0.000819	time 2.1375 (2.2577)	loss 4.3153 (3.7540)	grad_norm 1.1300 (1.1992)	
[2022-01-20 05:58:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][340/1251]	eta 0:34:12 lr 0.000819	time 1.8859 (2.2532)	loss 3.7123 (3.7491)	grad_norm 1.1727 (1.1971)	
[2022-01-20 05:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][350/1251]	eta 0:33:44 lr 0.000819	time 1.8600 (2.2475)	loss 2.7811 (3.7495)	grad_norm 1.3840 (1.1971)	
[2022-01-20 05:59:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][360/1251]	eta 0:33:14 lr 0.000819	time 1.8528 (2.2383)	loss 4.6085 (3.7561)	grad_norm 1.3203 (1.1983)	
[2022-01-20 05:59:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][370/1251]	eta 0:32:48 lr 0.000819	time 1.9770 (2.2344)	loss 4.0253 (3.7572)	grad_norm 1.1916 (1.1992)	
[2022-01-20 06:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][380/1251]	eta 0:32:23 lr 0.000819	time 2.2204 (2.2314)	loss 4.2438 (3.7612)	grad_norm 1.3504 (1.1998)	
[2022-01-20 06:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][390/1251]	eta 0:32:03 lr 0.000819	time 2.4017 (2.2345)	loss 3.2248 (3.7608)	grad_norm 1.1235 (1.2016)	
[2022-01-20 06:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][400/1251]	eta 0:31:44 lr 0.000819	time 1.9300 (2.2374)	loss 2.6045 (3.7619)	grad_norm 1.2810 (1.2022)	
[2022-01-20 06:01:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][410/1251]	eta 0:31:21 lr 0.000819	time 2.8350 (2.2368)	loss 2.6842 (3.7557)	grad_norm 1.0777 (1.2017)	
[2022-01-20 06:01:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][420/1251]	eta 0:30:59 lr 0.000819	time 2.1812 (2.2372)	loss 3.7794 (3.7590)	grad_norm 1.1283 (1.2016)	
[2022-01-20 06:02:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][430/1251]	eta 0:30:39 lr 0.000819	time 2.1662 (2.2405)	loss 4.4691 (3.7616)	grad_norm 1.2131 (1.2031)	
[2022-01-20 06:02:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][440/1251]	eta 0:30:14 lr 0.000819	time 2.2750 (2.2377)	loss 4.3187 (3.7639)	grad_norm 1.0916 (1.2027)	
[2022-01-20 06:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][450/1251]	eta 0:29:48 lr 0.000819	time 2.3653 (2.2331)	loss 3.9312 (3.7669)	grad_norm 0.9486 (1.2020)	
[2022-01-20 06:03:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][460/1251]	eta 0:29:22 lr 0.000819	time 1.9009 (2.2288)	loss 4.1470 (3.7684)	grad_norm 1.1615 (1.2005)	
[2022-01-20 06:03:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][470/1251]	eta 0:29:01 lr 0.000819	time 1.8832 (2.2304)	loss 3.4683 (3.7769)	grad_norm 1.2414 (1.2006)	
[2022-01-20 06:03:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][480/1251]	eta 0:28:39 lr 0.000819	time 1.9250 (2.2307)	loss 4.1141 (3.7811)	grad_norm 1.0153 (1.1986)	
[2022-01-20 06:04:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][490/1251]	eta 0:28:15 lr 0.000819	time 2.3624 (2.2279)	loss 4.1108 (3.7770)	grad_norm 1.0892 (1.1979)	
[2022-01-20 06:04:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][500/1251]	eta 0:27:52 lr 0.000819	time 1.7897 (2.2265)	loss 3.8101 (3.7760)	grad_norm 1.0410 (1.1979)	
[2022-01-20 06:05:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][510/1251]	eta 0:27:32 lr 0.000819	time 2.6385 (2.2296)	loss 3.2469 (3.7739)	grad_norm 1.0677 (1.1973)	
[2022-01-20 06:05:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][520/1251]	eta 0:27:09 lr 0.000819	time 1.7258 (2.2286)	loss 3.6051 (3.7745)	grad_norm 1.2575 (1.1971)	
[2022-01-20 06:05:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][530/1251]	eta 0:26:45 lr 0.000819	time 2.1650 (2.2271)	loss 4.1597 (3.7747)	grad_norm 1.1196 (1.1971)	
[2022-01-20 06:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][540/1251]	eta 0:26:20 lr 0.000819	time 1.8507 (2.2224)	loss 2.6429 (3.7747)	grad_norm 1.0450 (1.1981)	
[2022-01-20 06:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][550/1251]	eta 0:25:56 lr 0.000819	time 2.6315 (2.2201)	loss 3.5938 (3.7736)	grad_norm 1.3675 (1.1991)	
[2022-01-20 06:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][560/1251]	eta 0:25:33 lr 0.000819	time 2.4024 (2.2197)	loss 4.1758 (3.7719)	grad_norm 1.2575 (1.1994)	
[2022-01-20 06:07:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][570/1251]	eta 0:25:11 lr 0.000819	time 2.2462 (2.2192)	loss 3.7118 (3.7657)	grad_norm 1.5300 (1.1995)	
[2022-01-20 06:07:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][580/1251]	eta 0:24:48 lr 0.000819	time 1.3340 (2.2189)	loss 2.9892 (3.7680)	grad_norm 1.1826 (1.1983)	
[2022-01-20 06:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][590/1251]	eta 0:24:25 lr 0.000819	time 1.9721 (2.2166)	loss 3.4148 (3.7657)	grad_norm 1.2800 (1.1991)	
[2022-01-20 06:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][600/1251]	eta 0:24:02 lr 0.000819	time 1.8885 (2.2158)	loss 3.8931 (3.7659)	grad_norm 1.1341 (1.1995)	
[2022-01-20 06:08:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][610/1251]	eta 0:23:40 lr 0.000819	time 2.7238 (2.2165)	loss 3.4498 (3.7652)	grad_norm 1.1246 (1.1989)	
[2022-01-20 06:09:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][620/1251]	eta 0:23:18 lr 0.000819	time 1.8909 (2.2170)	loss 4.3009 (3.7660)	grad_norm 1.1285 (1.1983)	
[2022-01-20 06:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][630/1251]	eta 0:22:57 lr 0.000819	time 1.5818 (2.2187)	loss 2.8417 (3.7662)	grad_norm 1.2794 (1.1983)	
[2022-01-20 06:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][640/1251]	eta 0:22:36 lr 0.000818	time 2.2537 (2.2209)	loss 3.4674 (3.7687)	grad_norm 1.0172 (1.1967)	
[2022-01-20 06:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][650/1251]	eta 0:22:14 lr 0.000818	time 2.8172 (2.2211)	loss 4.0994 (3.7649)	grad_norm 1.1986 (1.1960)	
[2022-01-20 06:10:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][660/1251]	eta 0:21:50 lr 0.000818	time 1.7046 (2.2176)	loss 4.0893 (3.7669)	grad_norm 1.0893 (1.1971)	
[2022-01-20 06:10:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][670/1251]	eta 0:21:26 lr 0.000818	time 1.7372 (2.2134)	loss 4.0380 (3.7719)	grad_norm 1.1344 (1.1961)	
[2022-01-20 06:11:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][680/1251]	eta 0:21:02 lr 0.000818	time 2.1832 (2.2106)	loss 4.5396 (3.7726)	grad_norm 1.1965 (1.1960)	
[2022-01-20 06:11:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][690/1251]	eta 0:20:38 lr 0.000818	time 1.9505 (2.2078)	loss 3.6155 (3.7737)	grad_norm 0.9718 (1.1956)	
[2022-01-20 06:11:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][700/1251]	eta 0:20:15 lr 0.000818	time 1.9899 (2.2063)	loss 3.0196 (3.7752)	grad_norm 1.0488 (1.1948)	
[2022-01-20 06:12:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][710/1251]	eta 0:19:52 lr 0.000818	time 1.7164 (2.2043)	loss 4.1145 (3.7753)	grad_norm 1.0221 (1.1939)	
[2022-01-20 06:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][720/1251]	eta 0:19:30 lr 0.000818	time 2.2195 (2.2041)	loss 3.9219 (3.7727)	grad_norm 1.1556 (1.1940)	
[2022-01-20 06:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][730/1251]	eta 0:19:08 lr 0.000818	time 2.1607 (2.2052)	loss 4.6056 (3.7770)	grad_norm 1.1278 (1.1936)	
[2022-01-20 06:13:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][740/1251]	eta 0:18:47 lr 0.000818	time 1.6069 (2.2063)	loss 4.1243 (3.7783)	grad_norm 1.0168 (1.1941)	
[2022-01-20 06:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][750/1251]	eta 0:18:26 lr 0.000818	time 1.9562 (2.2082)	loss 4.1276 (3.7790)	grad_norm 1.0751 (1.1956)	
[2022-01-20 06:14:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][760/1251]	eta 0:18:05 lr 0.000818	time 2.8761 (2.2112)	loss 3.4282 (3.7789)	grad_norm 1.3394 (1.1973)	
[2022-01-20 06:14:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][770/1251]	eta 0:17:43 lr 0.000818	time 1.9719 (2.2115)	loss 4.7281 (3.7748)	grad_norm 1.3265 (1.1982)	
[2022-01-20 06:14:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][780/1251]	eta 0:17:20 lr 0.000818	time 2.2692 (2.2100)	loss 2.7977 (3.7752)	grad_norm 1.2834 (1.2002)	
[2022-01-20 06:15:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][790/1251]	eta 0:16:57 lr 0.000818	time 1.8341 (2.2078)	loss 4.4177 (3.7768)	grad_norm 1.0750 (1.2006)	
[2022-01-20 06:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][800/1251]	eta 0:16:34 lr 0.000818	time 1.9806 (2.2053)	loss 4.0609 (3.7779)	grad_norm 1.0229 (1.2007)	
[2022-01-20 06:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][810/1251]	eta 0:16:12 lr 0.000818	time 2.1976 (2.2063)	loss 3.3900 (3.7789)	grad_norm 1.1795 (1.2006)	
[2022-01-20 06:16:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][820/1251]	eta 0:15:50 lr 0.000818	time 2.2413 (2.2063)	loss 4.3975 (3.7818)	grad_norm 1.3733 (1.2012)	
[2022-01-20 06:16:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][830/1251]	eta 0:15:28 lr 0.000818	time 1.8699 (2.2066)	loss 3.7508 (3.7825)	grad_norm 1.0961 (1.2011)	
[2022-01-20 06:17:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][840/1251]	eta 0:15:07 lr 0.000818	time 2.1915 (2.2070)	loss 3.9951 (3.7815)	grad_norm 1.1332 (1.2012)	
[2022-01-20 06:17:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][850/1251]	eta 0:14:45 lr 0.000818	time 1.9041 (2.2081)	loss 3.8802 (3.7821)	grad_norm 1.2503 (1.2017)	
[2022-01-20 06:17:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][860/1251]	eta 0:14:22 lr 0.000818	time 1.6828 (2.2058)	loss 4.2544 (3.7829)	grad_norm 1.2480 (1.2022)	
[2022-01-20 06:18:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][870/1251]	eta 0:13:59 lr 0.000818	time 1.7517 (2.2036)	loss 2.9260 (3.7825)	grad_norm 1.1943 (1.2017)	
[2022-01-20 06:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][880/1251]	eta 0:13:37 lr 0.000818	time 2.1641 (2.2031)	loss 3.7622 (3.7828)	grad_norm 1.0708 (1.2012)	
[2022-01-20 06:18:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][890/1251]	eta 0:13:16 lr 0.000818	time 2.4519 (2.2054)	loss 4.1561 (3.7829)	grad_norm 1.0908 (1.2010)	
[2022-01-20 06:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][900/1251]	eta 0:12:54 lr 0.000818	time 2.2598 (2.2052)	loss 4.3213 (3.7839)	grad_norm 1.2266 (1.2004)	
[2022-01-20 06:19:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][910/1251]	eta 0:12:31 lr 0.000818	time 1.9185 (2.2052)	loss 3.7710 (3.7837)	grad_norm 1.2647 (1.2002)	
[2022-01-20 06:19:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][920/1251]	eta 0:12:10 lr 0.000818	time 2.5572 (2.2058)	loss 3.9025 (3.7855)	grad_norm 1.2809 (1.2005)	
[2022-01-20 06:20:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][930/1251]	eta 0:11:47 lr 0.000818	time 1.5620 (2.2041)	loss 4.3899 (3.7858)	grad_norm 1.3476 (1.2011)	
[2022-01-20 06:20:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][940/1251]	eta 0:11:24 lr 0.000818	time 1.6279 (2.2019)	loss 3.6811 (3.7863)	grad_norm 1.3560 (1.2013)	
[2022-01-20 06:20:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][950/1251]	eta 0:11:02 lr 0.000817	time 2.6122 (2.2018)	loss 3.8215 (3.7841)	grad_norm 1.1888 (1.2018)	
[2022-01-20 06:21:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][960/1251]	eta 0:10:40 lr 0.000817	time 1.8545 (2.2027)	loss 4.6120 (3.7854)	grad_norm 1.0766 (1.2015)	
[2022-01-20 06:21:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][970/1251]	eta 0:10:19 lr 0.000817	time 2.3262 (2.2037)	loss 4.5938 (3.7838)	grad_norm 1.2086 (1.2027)	
[2022-01-20 06:22:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][980/1251]	eta 0:09:57 lr 0.000817	time 2.1329 (2.2038)	loss 4.2243 (3.7848)	grad_norm 1.0955 (1.2021)	
[2022-01-20 06:22:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][990/1251]	eta 0:09:34 lr 0.000817	time 1.8664 (2.2027)	loss 4.0653 (3.7853)	grad_norm 1.0909 (1.2023)	
[2022-01-20 06:22:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1000/1251]	eta 0:09:12 lr 0.000817	time 2.1078 (2.2012)	loss 2.8561 (3.7851)	grad_norm 1.0314 (1.2024)	
[2022-01-20 06:23:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1010/1251]	eta 0:08:50 lr 0.000817	time 2.8533 (2.2020)	loss 3.9716 (3.7829)	grad_norm 1.0920 (1.2029)	
[2022-01-20 06:23:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1020/1251]	eta 0:08:28 lr 0.000817	time 2.6838 (2.2017)	loss 4.3356 (3.7862)	grad_norm 1.2783 (1.2033)	
[2022-01-20 06:23:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1030/1251]	eta 0:08:06 lr 0.000817	time 2.7847 (2.2025)	loss 3.3062 (3.7870)	grad_norm 1.2517 (1.2036)	
[2022-01-20 06:24:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1040/1251]	eta 0:07:44 lr 0.000817	time 1.8703 (2.2037)	loss 4.5538 (3.7884)	grad_norm 1.1028 (1.2032)	
[2022-01-20 06:24:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1050/1251]	eta 0:07:23 lr 0.000817	time 2.1021 (2.2040)	loss 4.1940 (3.7861)	grad_norm 1.2473 (1.2031)	
[2022-01-20 06:25:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1060/1251]	eta 0:07:00 lr 0.000817	time 1.8826 (2.2021)	loss 3.7896 (3.7851)	grad_norm 1.2491 (1.2031)	
[2022-01-20 06:25:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1070/1251]	eta 0:06:38 lr 0.000817	time 2.6366 (2.2000)	loss 3.8031 (3.7852)	grad_norm 1.0423 (1.2022)	
[2022-01-20 06:25:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1080/1251]	eta 0:06:16 lr 0.000817	time 2.1829 (2.2002)	loss 2.9785 (3.7841)	grad_norm 1.4547 (1.2022)	
[2022-01-20 06:26:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1090/1251]	eta 0:05:54 lr 0.000817	time 1.9265 (2.2007)	loss 2.8058 (3.7832)	grad_norm 1.0910 (1.2021)	
[2022-01-20 06:26:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1100/1251]	eta 0:05:32 lr 0.000817	time 2.8698 (2.2021)	loss 2.8517 (3.7842)	grad_norm 1.1540 (1.2022)	
[2022-01-20 06:26:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1110/1251]	eta 0:05:10 lr 0.000817	time 3.1057 (2.2030)	loss 3.9621 (3.7836)	grad_norm 1.2629 (1.2022)	
[2022-01-20 06:27:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1120/1251]	eta 0:04:48 lr 0.000817	time 2.1083 (2.2028)	loss 2.5438 (3.7828)	grad_norm 1.3904 (1.2022)	
[2022-01-20 06:27:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1130/1251]	eta 0:04:26 lr 0.000817	time 2.0664 (2.2001)	loss 4.1012 (3.7824)	grad_norm 1.3589 (1.2022)	
[2022-01-20 06:27:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1140/1251]	eta 0:04:04 lr 0.000817	time 2.5118 (2.1991)	loss 4.1292 (3.7827)	grad_norm 1.0919 (1.2020)	
[2022-01-20 06:28:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1150/1251]	eta 0:03:42 lr 0.000817	time 2.2977 (2.1986)	loss 3.8221 (3.7819)	grad_norm 1.1116 (1.2016)	
[2022-01-20 06:28:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1160/1251]	eta 0:03:20 lr 0.000817	time 2.1276 (2.1989)	loss 3.9721 (3.7831)	grad_norm 1.1626 (1.2012)	
[2022-01-20 06:28:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1170/1251]	eta 0:02:58 lr 0.000817	time 1.8721 (2.1979)	loss 3.9571 (3.7859)	grad_norm 1.3325 (1.2017)	
[2022-01-20 06:29:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1180/1251]	eta 0:02:36 lr 0.000817	time 2.4339 (2.1983)	loss 4.0012 (3.7863)	grad_norm 1.2520 (1.2026)	
[2022-01-20 06:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1190/1251]	eta 0:02:14 lr 0.000817	time 2.5645 (2.1989)	loss 4.0787 (3.7839)	grad_norm 1.0527 (1.2022)	
[2022-01-20 06:30:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1200/1251]	eta 0:01:52 lr 0.000817	time 1.6828 (2.1989)	loss 4.4710 (3.7821)	grad_norm 1.2493 (1.2024)	
[2022-01-20 06:30:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1210/1251]	eta 0:01:30 lr 0.000817	time 2.1617 (2.1985)	loss 4.2149 (3.7816)	grad_norm 1.3878 (1.2029)	
[2022-01-20 06:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1220/1251]	eta 0:01:08 lr 0.000817	time 3.1495 (2.2005)	loss 4.0143 (3.7809)	grad_norm 1.0664 (1.2028)	
[2022-01-20 06:31:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1230/1251]	eta 0:00:46 lr 0.000817	time 1.8772 (2.2008)	loss 3.4074 (3.7805)	grad_norm 1.2498 (1.2026)	
[2022-01-20 06:31:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1240/1251]	eta 0:00:24 lr 0.000817	time 1.4454 (2.1986)	loss 3.9241 (3.7816)	grad_norm 1.3292 (1.2024)	
[2022-01-20 06:31:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [84/300][1250/1251]	eta 0:00:02 lr 0.000817	time 1.2227 (2.1925)	loss 4.0268 (3.7810)	grad_norm 1.1127 (1.2020)	
[2022-01-20 06:31:49 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 84 training takes 0:45:43
[2022-01-20 06:32:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.777 (18.777)	Loss 1.1787 (1.1787)	Acc@1 73.535 (73.535)	Acc@5 90.723 (90.723)	
[2022-01-20 06:32:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.501 (3.462)	Loss 1.2107 (1.2016)	Acc@1 71.680 (72.541)	Acc@5 91.406 (91.388)	
[2022-01-20 06:32:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.317 (2.547)	Loss 1.2408 (1.2037)	Acc@1 71.875 (72.698)	Acc@5 90.527 (91.420)	
[2022-01-20 06:32:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.179 (2.242)	Loss 1.1933 (1.2004)	Acc@1 73.828 (72.883)	Acc@5 91.992 (91.457)	
[2022-01-20 06:33:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.249 (2.205)	Loss 1.1138 (1.1971)	Acc@1 76.074 (72.942)	Acc@5 91.895 (91.556)	
[2022-01-20 06:33:26 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.882 Acc@5 91.498
[2022-01-20 06:33:26 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.9%
[2022-01-20 06:33:26 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 72.94%
[2022-01-20 06:33:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][0/1251]	eta 7:33:59 lr 0.000817	time 21.7742 (21.7742)	loss 2.7172 (2.7172)	grad_norm 1.4122 (1.4122)	
[2022-01-20 06:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][10/1251]	eta 1:23:38 lr 0.000816	time 2.8919 (4.0439)	loss 3.8288 (3.5676)	grad_norm 0.9456 (1.1699)	
[2022-01-20 06:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][20/1251]	eta 1:04:44 lr 0.000816	time 1.5437 (3.1558)	loss 3.4302 (3.7384)	grad_norm 1.0252 (1.1601)	
[2022-01-20 06:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][30/1251]	eta 0:57:42 lr 0.000816	time 1.8997 (2.8357)	loss 3.1745 (3.7713)	grad_norm 1.4341 (1.1582)	
[2022-01-20 06:35:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][40/1251]	eta 0:54:12 lr 0.000816	time 3.9991 (2.6861)	loss 4.1410 (3.7624)	grad_norm 1.1671 (1.1582)	
[2022-01-20 06:35:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][50/1251]	eta 0:51:53 lr 0.000816	time 2.0868 (2.5921)	loss 4.5318 (3.7857)	grad_norm 1.0941 (1.1538)	
[2022-01-20 06:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][60/1251]	eta 0:49:32 lr 0.000816	time 1.2867 (2.4959)	loss 4.6365 (3.7891)	grad_norm 1.3535 (1.1685)	
[2022-01-20 06:36:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][70/1251]	eta 0:48:11 lr 0.000816	time 1.5076 (2.4480)	loss 4.2864 (3.7789)	grad_norm 1.2522 (1.1823)	
[2022-01-20 06:36:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][80/1251]	eta 0:47:06 lr 0.000816	time 2.7969 (2.4140)	loss 4.1803 (3.7789)	grad_norm 1.3452 (1.1926)	
[2022-01-20 06:37:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][90/1251]	eta 0:46:19 lr 0.000816	time 2.2813 (2.3937)	loss 3.4674 (3.7665)	grad_norm 1.2440 (1.2071)	
[2022-01-20 06:37:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][100/1251]	eta 0:45:35 lr 0.000816	time 1.4552 (2.3766)	loss 2.6842 (3.7600)	grad_norm 1.0681 (1.2099)	
[2022-01-20 06:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][110/1251]	eta 0:44:58 lr 0.000816	time 1.8754 (2.3652)	loss 3.9579 (3.7747)	grad_norm 1.3132 (1.2108)	
[2022-01-20 06:38:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][120/1251]	eta 0:44:29 lr 0.000816	time 2.6038 (2.3600)	loss 4.1326 (3.7730)	grad_norm 1.2319 (1.2118)	
[2022-01-20 06:38:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][130/1251]	eta 0:44:15 lr 0.000816	time 2.9983 (2.3686)	loss 3.4976 (3.7775)	grad_norm 1.2746 (1.2084)	
[2022-01-20 06:38:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][140/1251]	eta 0:43:38 lr 0.000816	time 1.8005 (2.3573)	loss 2.3187 (3.7436)	grad_norm 1.4855 (1.2054)	
[2022-01-20 06:39:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][150/1251]	eta 0:42:57 lr 0.000816	time 2.1895 (2.3414)	loss 3.7950 (3.7479)	grad_norm 1.0960 (1.2025)	
[2022-01-20 06:39:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][160/1251]	eta 0:42:05 lr 0.000816	time 2.0354 (2.3145)	loss 4.3039 (3.7454)	grad_norm 1.1757 (1.2037)	
[2022-01-20 06:39:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][170/1251]	eta 0:41:20 lr 0.000816	time 1.8166 (2.2949)	loss 4.1107 (3.7559)	grad_norm 1.4185 (1.2035)	
[2022-01-20 06:40:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][180/1251]	eta 0:40:45 lr 0.000816	time 1.8792 (2.2835)	loss 4.1101 (3.7596)	grad_norm 1.1562 (1.2015)	
[2022-01-20 06:40:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][190/1251]	eta 0:40:08 lr 0.000816	time 2.0426 (2.2704)	loss 4.0263 (3.7525)	grad_norm 1.1703 (1.2012)	
[2022-01-20 06:41:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][200/1251]	eta 0:39:39 lr 0.000816	time 1.9515 (2.2642)	loss 4.0094 (3.7604)	grad_norm 1.2875 (1.2020)	
[2022-01-20 06:41:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][210/1251]	eta 0:39:14 lr 0.000816	time 1.9760 (2.2615)	loss 3.7797 (3.7495)	grad_norm 1.1282 (1.1999)	
[2022-01-20 06:41:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][220/1251]	eta 0:38:55 lr 0.000816	time 2.4673 (2.2649)	loss 2.7184 (3.7501)	grad_norm 1.2758 (1.2014)	
[2022-01-20 06:42:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][230/1251]	eta 0:38:44 lr 0.000816	time 2.9338 (2.2769)	loss 3.3722 (3.7457)	grad_norm 1.8667 (1.2079)	
[2022-01-20 06:42:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][240/1251]	eta 0:38:27 lr 0.000816	time 2.1263 (2.2823)	loss 4.0992 (3.7464)	grad_norm 1.1405 (1.2083)	
[2022-01-20 06:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][250/1251]	eta 0:38:12 lr 0.000816	time 2.0436 (2.2898)	loss 4.0099 (3.7435)	grad_norm 1.2265 (1.2094)	
[2022-01-20 06:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][260/1251]	eta 0:37:47 lr 0.000816	time 1.9068 (2.2877)	loss 3.5576 (3.7448)	grad_norm 1.2535 (1.2112)	
[2022-01-20 06:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][270/1251]	eta 0:37:09 lr 0.000816	time 1.9854 (2.2727)	loss 3.0918 (3.7460)	grad_norm 1.1055 (1.2119)	
[2022-01-20 06:44:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][280/1251]	eta 0:36:33 lr 0.000816	time 1.7701 (2.2594)	loss 3.5145 (3.7508)	grad_norm 1.1467 (1.2096)	
[2022-01-20 06:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][290/1251]	eta 0:36:03 lr 0.000816	time 1.7899 (2.2516)	loss 3.5694 (3.7530)	grad_norm 1.2591 (1.2106)	
[2022-01-20 06:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][300/1251]	eta 0:35:38 lr 0.000816	time 2.6090 (2.2482)	loss 4.6159 (3.7620)	grad_norm 1.0973 (1.2120)	
[2022-01-20 06:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][310/1251]	eta 0:35:14 lr 0.000816	time 2.2271 (2.2468)	loss 4.1874 (3.7561)	grad_norm 1.2294 (1.2096)	
[2022-01-20 06:45:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][320/1251]	eta 0:34:49 lr 0.000815	time 1.8429 (2.2447)	loss 4.0904 (3.7598)	grad_norm 0.9952 (1.2060)	
[2022-01-20 06:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][330/1251]	eta 0:34:32 lr 0.000815	time 1.4699 (2.2498)	loss 4.7602 (3.7664)	grad_norm 1.0539 (1.2036)	
[2022-01-20 06:46:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][340/1251]	eta 0:34:19 lr 0.000815	time 3.0807 (2.2610)	loss 3.2855 (3.7680)	grad_norm 1.2611 (1.2034)	
[2022-01-20 06:46:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][350/1251]	eta 0:33:56 lr 0.000815	time 1.6765 (2.2603)	loss 4.5020 (3.7658)	grad_norm 1.1924 (1.2015)	
[2022-01-20 06:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][360/1251]	eta 0:33:33 lr 0.000815	time 1.9881 (2.2595)	loss 2.8461 (3.7634)	grad_norm 1.0277 (1.2009)	
[2022-01-20 06:47:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][370/1251]	eta 0:33:03 lr 0.000815	time 2.0795 (2.2518)	loss 4.7590 (3.7644)	grad_norm 1.1686 (1.2028)	
[2022-01-20 06:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][380/1251]	eta 0:32:35 lr 0.000815	time 2.2559 (2.2453)	loss 4.2737 (3.7676)	grad_norm 1.0873 (1.2041)	
[2022-01-20 06:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][390/1251]	eta 0:32:10 lr 0.000815	time 2.3829 (2.2427)	loss 4.1918 (3.7688)	grad_norm 1.2706 (1.2056)	
[2022-01-20 06:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][400/1251]	eta 0:31:48 lr 0.000815	time 1.8360 (2.2426)	loss 4.0498 (3.7688)	grad_norm 1.2284 (1.2081)	
[2022-01-20 06:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][410/1251]	eta 0:31:23 lr 0.000815	time 1.8754 (2.2401)	loss 3.6575 (3.7695)	grad_norm 1.3488 (1.2091)	
[2022-01-20 06:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][420/1251]	eta 0:31:02 lr 0.000815	time 2.3067 (2.2407)	loss 3.0247 (3.7713)	grad_norm 1.1472 (1.2109)	
[2022-01-20 06:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][430/1251]	eta 0:30:39 lr 0.000815	time 2.0644 (2.2401)	loss 3.5581 (3.7675)	grad_norm 1.1642 (1.2118)	
[2022-01-20 06:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][440/1251]	eta 0:30:18 lr 0.000815	time 2.5802 (2.2424)	loss 3.7901 (3.7637)	grad_norm 1.4566 (1.2110)	
[2022-01-20 06:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][450/1251]	eta 0:29:57 lr 0.000815	time 1.9504 (2.2437)	loss 4.0597 (3.7654)	grad_norm 1.2718 (1.2113)	
[2022-01-20 06:50:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][460/1251]	eta 0:29:33 lr 0.000815	time 1.8721 (2.2417)	loss 2.9334 (3.7610)	grad_norm 1.3386 (1.2116)	
[2022-01-20 06:51:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][470/1251]	eta 0:29:07 lr 0.000815	time 1.7645 (2.2382)	loss 3.0220 (3.7599)	grad_norm 1.3702 (1.2125)	
[2022-01-20 06:51:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][480/1251]	eta 0:28:43 lr 0.000815	time 2.8030 (2.2349)	loss 3.6103 (3.7549)	grad_norm 1.2897 (1.2131)	
[2022-01-20 06:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][490/1251]	eta 0:28:17 lr 0.000815	time 1.9708 (2.2301)	loss 4.0208 (3.7555)	grad_norm 1.1080 (1.2123)	
[2022-01-20 06:52:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][500/1251]	eta 0:27:52 lr 0.000815	time 1.8077 (2.2268)	loss 3.3648 (3.7567)	grad_norm 1.1355 (1.2113)	
[2022-01-20 06:52:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][510/1251]	eta 0:27:27 lr 0.000815	time 1.9280 (2.2236)	loss 4.0690 (3.7566)	grad_norm 1.1989 (1.2112)	
[2022-01-20 06:52:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][520/1251]	eta 0:27:06 lr 0.000815	time 2.1609 (2.2255)	loss 4.1450 (3.7588)	grad_norm 1.3154 (1.2121)	
[2022-01-20 06:53:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][530/1251]	eta 0:26:45 lr 0.000815	time 1.5889 (2.2262)	loss 2.7617 (3.7569)	grad_norm 1.0560 (1.2121)	
[2022-01-20 06:53:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][540/1251]	eta 0:26:22 lr 0.000815	time 2.2054 (2.2251)	loss 2.7710 (3.7540)	grad_norm 1.1430 (1.2159)	
[2022-01-20 06:53:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][550/1251]	eta 0:25:59 lr 0.000815	time 1.7418 (2.2248)	loss 3.7428 (3.7536)	grad_norm 1.1259 (1.2157)	
[2022-01-20 06:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][560/1251]	eta 0:25:37 lr 0.000815	time 2.8465 (2.2253)	loss 3.9108 (3.7539)	grad_norm 1.0526 (1.2162)	
[2022-01-20 06:54:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][570/1251]	eta 0:25:15 lr 0.000815	time 1.8814 (2.2253)	loss 4.2231 (3.7571)	grad_norm 1.3162 (1.2152)	
[2022-01-20 06:54:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][580/1251]	eta 0:24:53 lr 0.000815	time 2.2494 (2.2263)	loss 4.0844 (3.7626)	grad_norm 1.1952 (1.2148)	
[2022-01-20 06:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][590/1251]	eta 0:24:33 lr 0.000815	time 1.5553 (2.2288)	loss 4.3130 (3.7643)	grad_norm 1.1613 (1.2144)	
[2022-01-20 06:55:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][600/1251]	eta 0:24:10 lr 0.000815	time 1.5852 (2.2282)	loss 3.2313 (3.7604)	grad_norm 1.0033 (1.2151)	
[2022-01-20 06:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][610/1251]	eta 0:23:47 lr 0.000815	time 1.9376 (2.2271)	loss 3.0472 (3.7595)	grad_norm 1.1163 (1.2166)	
[2022-01-20 06:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][620/1251]	eta 0:23:23 lr 0.000815	time 1.9126 (2.2242)	loss 4.3996 (3.7634)	grad_norm 1.0058 (1.2167)	
[2022-01-20 06:56:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][630/1251]	eta 0:23:00 lr 0.000814	time 1.6927 (2.2224)	loss 3.6034 (3.7627)	grad_norm 1.1521 (1.2157)	
[2022-01-20 06:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][640/1251]	eta 0:22:36 lr 0.000814	time 1.5194 (2.2198)	loss 3.6867 (3.7669)	grad_norm 1.1122 (1.2145)	
[2022-01-20 06:57:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][650/1251]	eta 0:22:14 lr 0.000814	time 1.9284 (2.2198)	loss 3.6124 (3.7647)	grad_norm 1.2230 (1.2146)	
[2022-01-20 06:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][660/1251]	eta 0:21:52 lr 0.000814	time 1.7754 (2.2207)	loss 4.1360 (3.7630)	grad_norm 1.2410 (1.2153)	
[2022-01-20 06:58:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][670/1251]	eta 0:21:30 lr 0.000814	time 2.9103 (2.2217)	loss 3.2138 (3.7609)	grad_norm 1.1735 (1.2151)	
[2022-01-20 06:58:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][680/1251]	eta 0:21:06 lr 0.000814	time 1.9113 (2.2189)	loss 3.9016 (3.7599)	grad_norm 1.3116 (1.2155)	
[2022-01-20 06:58:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][690/1251]	eta 0:20:43 lr 0.000814	time 1.8659 (2.2168)	loss 3.8411 (3.7641)	grad_norm 1.1759 (1.2160)	
[2022-01-20 06:59:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][700/1251]	eta 0:20:21 lr 0.000814	time 1.9541 (2.2166)	loss 4.5498 (3.7616)	grad_norm 1.0694 (1.2152)	
[2022-01-20 06:59:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][710/1251]	eta 0:19:59 lr 0.000814	time 2.7646 (2.2180)	loss 3.7435 (3.7617)	grad_norm 1.1294 (1.2145)	
[2022-01-20 07:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][720/1251]	eta 0:19:37 lr 0.000814	time 1.9260 (2.2171)	loss 4.1660 (3.7618)	grad_norm 1.0953 (1.2139)	
[2022-01-20 07:00:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][730/1251]	eta 0:19:15 lr 0.000814	time 2.2068 (2.2172)	loss 3.5705 (3.7601)	grad_norm 1.0535 (1.2143)	
[2022-01-20 07:00:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][740/1251]	eta 0:18:52 lr 0.000814	time 1.8436 (2.2164)	loss 3.9918 (3.7597)	grad_norm 1.2120 (1.2136)	
[2022-01-20 07:01:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][750/1251]	eta 0:18:30 lr 0.000814	time 2.3940 (2.2169)	loss 4.2560 (3.7619)	grad_norm 1.0830 (1.2139)	
[2022-01-20 07:01:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][760/1251]	eta 0:18:07 lr 0.000814	time 2.0112 (2.2146)	loss 4.2442 (3.7649)	grad_norm 1.1133 (1.2141)	
[2022-01-20 07:01:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][770/1251]	eta 0:17:44 lr 0.000814	time 2.2920 (2.2125)	loss 2.6936 (3.7617)	grad_norm 1.2561 (1.2141)	
[2022-01-20 07:02:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][780/1251]	eta 0:17:21 lr 0.000814	time 1.6812 (2.2107)	loss 2.9015 (3.7613)	grad_norm 1.2630 (1.2131)	
[2022-01-20 07:02:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][790/1251]	eta 0:16:59 lr 0.000814	time 2.1959 (2.2112)	loss 4.4596 (3.7599)	grad_norm 1.1653 (1.2133)	
[2022-01-20 07:02:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][800/1251]	eta 0:16:37 lr 0.000814	time 1.9373 (2.2124)	loss 3.7753 (3.7588)	grad_norm 1.0690 (1.2128)	
[2022-01-20 07:03:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][810/1251]	eta 0:16:16 lr 0.000814	time 2.2604 (2.2143)	loss 4.1311 (3.7569)	grad_norm 1.1136 (1.2129)	
[2022-01-20 07:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][820/1251]	eta 0:15:53 lr 0.000814	time 1.7186 (2.2133)	loss 3.2905 (3.7576)	grad_norm 1.1796 (1.2127)	
[2022-01-20 07:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][830/1251]	eta 0:15:31 lr 0.000814	time 2.6058 (2.2136)	loss 3.9529 (3.7600)	grad_norm 1.2711 (1.2124)	
[2022-01-20 07:04:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][840/1251]	eta 0:15:09 lr 0.000814	time 1.7634 (2.2122)	loss 3.3881 (3.7594)	grad_norm 1.0939 (1.2125)	
[2022-01-20 07:04:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][850/1251]	eta 0:14:47 lr 0.000814	time 1.7444 (2.2121)	loss 4.1021 (3.7560)	grad_norm 1.0720 (1.2114)	
[2022-01-20 07:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][860/1251]	eta 0:14:24 lr 0.000814	time 2.1187 (2.2115)	loss 4.2464 (3.7543)	grad_norm 1.1723 (1.2108)	
[2022-01-20 07:05:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][870/1251]	eta 0:14:02 lr 0.000814	time 2.5442 (2.2116)	loss 3.2939 (3.7522)	grad_norm 1.1093 (1.2096)	
[2022-01-20 07:05:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][880/1251]	eta 0:13:40 lr 0.000814	time 1.9341 (2.2116)	loss 3.3135 (3.7519)	grad_norm 1.2007 (1.2107)	
[2022-01-20 07:06:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][890/1251]	eta 0:13:17 lr 0.000814	time 2.0672 (2.2102)	loss 4.1133 (3.7524)	grad_norm 1.2531 (1.2106)	
[2022-01-20 07:06:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][900/1251]	eta 0:12:55 lr 0.000814	time 1.8949 (2.2089)	loss 4.2306 (3.7549)	grad_norm 1.1842 (1.2107)	
[2022-01-20 07:06:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][910/1251]	eta 0:12:32 lr 0.000814	time 2.3340 (2.2078)	loss 3.5054 (3.7558)	grad_norm 1.2651 (1.2101)	
[2022-01-20 07:07:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][920/1251]	eta 0:12:10 lr 0.000814	time 1.5589 (2.2055)	loss 4.3156 (3.7588)	grad_norm 1.1543 (1.2098)	
[2022-01-20 07:07:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][930/1251]	eta 0:11:47 lr 0.000814	time 1.8162 (2.2052)	loss 2.5968 (3.7584)	grad_norm 1.4359 (1.2092)	
[2022-01-20 07:08:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][940/1251]	eta 0:11:25 lr 0.000813	time 2.5056 (2.2048)	loss 3.7091 (3.7581)	grad_norm 1.2194 (1.2092)	
[2022-01-20 07:08:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][950/1251]	eta 0:11:03 lr 0.000813	time 2.0332 (2.2051)	loss 4.1647 (3.7580)	grad_norm 1.3763 (1.2096)	
[2022-01-20 07:08:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][960/1251]	eta 0:10:41 lr 0.000813	time 1.9230 (2.2053)	loss 2.6123 (3.7554)	grad_norm 1.2657 (1.2104)	
[2022-01-20 07:09:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][970/1251]	eta 0:10:20 lr 0.000813	time 1.8910 (2.2080)	loss 4.3728 (3.7571)	grad_norm 1.2901 (1.2107)	
[2022-01-20 07:09:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][980/1251]	eta 0:09:58 lr 0.000813	time 2.2261 (2.2100)	loss 2.4842 (3.7590)	grad_norm 1.5063 (1.2109)	
[2022-01-20 07:09:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][990/1251]	eta 0:09:36 lr 0.000813	time 2.3989 (2.2099)	loss 4.1136 (3.7609)	grad_norm 1.3812 (1.2117)	
[2022-01-20 07:10:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1000/1251]	eta 0:09:13 lr 0.000813	time 1.8857 (2.2071)	loss 3.1166 (3.7568)	grad_norm 1.1585 (1.2120)	
[2022-01-20 07:10:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1010/1251]	eta 0:08:51 lr 0.000813	time 1.8631 (2.2049)	loss 3.7920 (3.7562)	grad_norm 1.3826 (1.2118)	
[2022-01-20 07:10:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1020/1251]	eta 0:08:29 lr 0.000813	time 1.9877 (2.2037)	loss 3.7299 (3.7568)	grad_norm 1.4965 (1.2115)	
[2022-01-20 07:11:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1030/1251]	eta 0:08:06 lr 0.000813	time 2.0905 (2.2032)	loss 4.1760 (3.7567)	grad_norm 1.5764 (1.2116)	
[2022-01-20 07:11:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1040/1251]	eta 0:07:45 lr 0.000813	time 2.2567 (2.2039)	loss 4.0540 (3.7569)	grad_norm 1.4371 (1.2115)	
[2022-01-20 07:12:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1050/1251]	eta 0:07:22 lr 0.000813	time 2.4817 (2.2038)	loss 4.7197 (3.7580)	grad_norm 1.0661 (1.2107)	
[2022-01-20 07:12:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1060/1251]	eta 0:07:00 lr 0.000813	time 1.7757 (2.2036)	loss 3.4293 (3.7612)	grad_norm 1.0556 (1.2101)	
[2022-01-20 07:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1070/1251]	eta 0:06:39 lr 0.000813	time 2.0177 (2.2061)	loss 2.6786 (3.7598)	grad_norm 1.2457 (1.2093)	
[2022-01-20 07:13:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1080/1251]	eta 0:06:17 lr 0.000813	time 2.7978 (2.2073)	loss 4.0542 (3.7602)	grad_norm 1.1476 (1.2094)	
[2022-01-20 07:13:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1090/1251]	eta 0:05:55 lr 0.000813	time 1.5202 (2.2065)	loss 4.5729 (3.7594)	grad_norm 1.2397 (1.2096)	
[2022-01-20 07:13:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1100/1251]	eta 0:05:32 lr 0.000813	time 1.7825 (2.2051)	loss 4.3373 (3.7594)	grad_norm 1.5072 (1.2102)	
[2022-01-20 07:14:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1110/1251]	eta 0:05:10 lr 0.000813	time 2.0706 (2.2034)	loss 4.3029 (3.7602)	grad_norm 1.1448 (1.2105)	
[2022-01-20 07:14:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1120/1251]	eta 0:04:48 lr 0.000813	time 1.9144 (2.2026)	loss 4.3480 (3.7630)	grad_norm 1.3449 (1.2108)	
[2022-01-20 07:14:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1130/1251]	eta 0:04:26 lr 0.000813	time 2.4932 (2.2029)	loss 4.0059 (3.7647)	grad_norm 1.3364 (1.2101)	
[2022-01-20 07:15:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1140/1251]	eta 0:04:04 lr 0.000813	time 2.5449 (2.2027)	loss 3.4663 (3.7645)	grad_norm 1.2719 (1.2099)	
[2022-01-20 07:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1150/1251]	eta 0:03:42 lr 0.000813	time 2.4540 (2.2027)	loss 4.4414 (3.7667)	grad_norm 1.2660 (1.2102)	
[2022-01-20 07:16:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1160/1251]	eta 0:03:20 lr 0.000813	time 2.0792 (2.2028)	loss 4.0723 (3.7634)	grad_norm 1.2637 (1.2094)	
[2022-01-20 07:16:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1170/1251]	eta 0:02:58 lr 0.000813	time 2.2130 (2.2026)	loss 3.4169 (3.7629)	grad_norm 1.1340 (1.2091)	
[2022-01-20 07:16:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1180/1251]	eta 0:02:36 lr 0.000813	time 2.1534 (2.2032)	loss 2.7919 (3.7625)	grad_norm 1.1047 (1.2088)	
[2022-01-20 07:17:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1190/1251]	eta 0:02:14 lr 0.000813	time 2.4874 (2.2037)	loss 4.0823 (3.7635)	grad_norm 1.1186 (1.2092)	
[2022-01-20 07:17:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1200/1251]	eta 0:01:52 lr 0.000813	time 1.6696 (2.2028)	loss 4.1038 (3.7626)	grad_norm 1.1317 (1.2092)	
[2022-01-20 07:17:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1210/1251]	eta 0:01:30 lr 0.000813	time 1.9986 (2.2006)	loss 2.3981 (3.7617)	grad_norm 1.1231 (1.2101)	
[2022-01-20 07:18:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1220/1251]	eta 0:01:08 lr 0.000813	time 2.5696 (2.2013)	loss 4.1549 (3.7642)	grad_norm 1.0968 (1.2094)	
[2022-01-20 07:18:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1230/1251]	eta 0:00:46 lr 0.000813	time 1.6913 (2.2011)	loss 4.2625 (3.7620)	grad_norm 1.2329 (1.2092)	
[2022-01-20 07:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1240/1251]	eta 0:00:24 lr 0.000813	time 1.5427 (2.1998)	loss 4.0355 (3.7636)	grad_norm 1.2720 (1.2091)	
[2022-01-20 07:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [85/300][1250/1251]	eta 0:00:02 lr 0.000812	time 1.2175 (2.1941)	loss 4.0842 (3.7639)	grad_norm 0.9484 (1.2082)	
[2022-01-20 07:19:11 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 85 training takes 0:45:45
[2022-01-20 07:19:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.494 (18.494)	Loss 1.1592 (1.1592)	Acc@1 71.191 (71.191)	Acc@5 92.188 (92.188)	
[2022-01-20 07:19:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.556 (3.365)	Loss 1.1456 (1.1621)	Acc@1 74.219 (72.940)	Acc@5 91.895 (91.939)	
[2022-01-20 07:20:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.925 (2.574)	Loss 1.1347 (1.1661)	Acc@1 73.535 (72.959)	Acc@5 92.969 (91.783)	
[2022-01-20 07:20:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.486 (2.219)	Loss 1.1491 (1.1735)	Acc@1 73.926 (72.855)	Acc@5 91.602 (91.728)	
[2022-01-20 07:20:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.576 (2.146)	Loss 1.2041 (1.1704)	Acc@1 71.387 (73.023)	Acc@5 92.090 (91.730)	
[2022-01-20 07:20:48 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.018 Acc@5 91.758
[2022-01-20 07:20:48 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.0%
[2022-01-20 07:20:48 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.02%
[2022-01-20 07:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][0/1251]	eta 7:22:13 lr 0.000812	time 21.2100 (21.2100)	loss 4.1619 (4.1619)	grad_norm 1.2232 (1.2232)	
[2022-01-20 07:21:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][10/1251]	eta 1:26:13 lr 0.000812	time 2.1759 (4.1687)	loss 3.5965 (3.8532)	grad_norm 1.1028 (1.2434)	
[2022-01-20 07:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][20/1251]	eta 1:05:56 lr 0.000812	time 1.3382 (3.2144)	loss 3.2341 (3.8314)	grad_norm 1.0934 (1.2006)	
[2022-01-20 07:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][30/1251]	eta 0:57:56 lr 0.000812	time 1.4100 (2.8472)	loss 4.7365 (3.9318)	grad_norm 1.1537 (1.1961)	
[2022-01-20 07:22:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][40/1251]	eta 0:56:07 lr 0.000812	time 3.9355 (2.7810)	loss 4.3859 (3.8482)	grad_norm 1.4060 (1.1966)	
[2022-01-20 07:23:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][50/1251]	eta 0:53:48 lr 0.000812	time 2.7391 (2.6882)	loss 3.0840 (3.8463)	grad_norm 1.2198 (1.1896)	
[2022-01-20 07:23:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][60/1251]	eta 0:51:26 lr 0.000812	time 1.6191 (2.5913)	loss 3.6288 (3.7977)	grad_norm 1.1461 (1.1931)	
[2022-01-20 07:23:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][70/1251]	eta 0:49:39 lr 0.000812	time 1.9994 (2.5224)	loss 4.3015 (3.8153)	grad_norm 1.1174 (1.1984)	
[2022-01-20 07:24:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][80/1251]	eta 0:48:20 lr 0.000812	time 3.0703 (2.4765)	loss 4.0670 (3.8090)	grad_norm 1.4026 (1.1980)	
[2022-01-20 07:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][90/1251]	eta 0:47:17 lr 0.000812	time 2.5393 (2.4438)	loss 4.2878 (3.8325)	grad_norm 1.2195 (1.2099)	
[2022-01-20 07:24:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][100/1251]	eta 0:46:07 lr 0.000812	time 1.5889 (2.4048)	loss 4.2112 (3.8370)	grad_norm 1.2641 (1.2143)	
[2022-01-20 07:25:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][110/1251]	eta 0:45:07 lr 0.000812	time 2.2095 (2.3727)	loss 3.8588 (3.8370)	grad_norm 1.1693 (1.2193)	
[2022-01-20 07:25:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][120/1251]	eta 0:44:24 lr 0.000812	time 2.8192 (2.3561)	loss 3.8403 (3.8276)	grad_norm 1.2959 (1.2179)	
[2022-01-20 07:25:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][130/1251]	eta 0:43:39 lr 0.000812	time 1.9272 (2.3364)	loss 3.9706 (3.8261)	grad_norm 1.1308 (1.2155)	
[2022-01-20 07:26:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][140/1251]	eta 0:43:06 lr 0.000812	time 2.1858 (2.3279)	loss 3.7438 (3.8308)	grad_norm 1.1198 (1.2116)	
[2022-01-20 07:26:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][150/1251]	eta 0:42:34 lr 0.000812	time 2.5158 (2.3205)	loss 3.0680 (3.8080)	grad_norm 1.1202 (1.2092)	
[2022-01-20 07:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][160/1251]	eta 0:42:15 lr 0.000812	time 2.5889 (2.3240)	loss 3.8812 (3.8001)	grad_norm 1.1439 (1.2072)	
[2022-01-20 07:27:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][170/1251]	eta 0:42:01 lr 0.000812	time 2.7490 (2.3327)	loss 4.4839 (3.7940)	grad_norm 1.3192 (1.2090)	
[2022-01-20 07:27:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][180/1251]	eta 0:41:29 lr 0.000812	time 1.7151 (2.3242)	loss 3.7962 (3.8115)	grad_norm 1.4922 (1.2126)	
[2022-01-20 07:28:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][190/1251]	eta 0:40:58 lr 0.000812	time 2.5352 (2.3167)	loss 3.6352 (3.8054)	grad_norm 1.0927 (1.2070)	
[2022-01-20 07:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][200/1251]	eta 0:40:11 lr 0.000812	time 1.7379 (2.2940)	loss 4.3481 (3.8047)	grad_norm 1.2742 (1.2070)	
[2022-01-20 07:28:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][210/1251]	eta 0:39:32 lr 0.000812	time 1.8909 (2.2794)	loss 3.5840 (3.8114)	grad_norm 1.2263 (1.2058)	
[2022-01-20 07:29:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][220/1251]	eta 0:39:01 lr 0.000812	time 2.4510 (2.2715)	loss 3.3520 (3.8175)	grad_norm 1.3280 (1.2081)	
[2022-01-20 07:29:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][230/1251]	eta 0:38:31 lr 0.000812	time 2.4388 (2.2640)	loss 4.1462 (3.8221)	grad_norm 1.1256 (1.2084)	
[2022-01-20 07:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][240/1251]	eta 0:38:01 lr 0.000812	time 2.0575 (2.2563)	loss 4.3686 (3.8263)	grad_norm 1.2383 (1.2072)	
[2022-01-20 07:30:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][250/1251]	eta 0:37:37 lr 0.000812	time 1.8423 (2.2548)	loss 3.8934 (3.8288)	grad_norm 1.1769 (1.2062)	
[2022-01-20 07:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][260/1251]	eta 0:37:11 lr 0.000812	time 2.5734 (2.2516)	loss 4.3194 (3.8373)	grad_norm 1.4050 (1.2071)	
[2022-01-20 07:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][270/1251]	eta 0:36:50 lr 0.000812	time 2.3477 (2.2533)	loss 4.0756 (3.8387)	grad_norm 1.2266 (1.2076)	
[2022-01-20 07:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][280/1251]	eta 0:36:29 lr 0.000812	time 1.9549 (2.2544)	loss 3.4053 (3.8448)	grad_norm 1.0162 (1.2051)	
[2022-01-20 07:31:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][290/1251]	eta 0:36:09 lr 0.000812	time 3.0190 (2.2571)	loss 3.9891 (3.8462)	grad_norm 1.0906 (1.2041)	
[2022-01-20 07:32:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][300/1251]	eta 0:35:44 lr 0.000811	time 2.2733 (2.2552)	loss 4.1554 (3.8460)	grad_norm 1.1092 (1.2017)	
[2022-01-20 07:32:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][310/1251]	eta 0:35:19 lr 0.000811	time 1.9240 (2.2521)	loss 3.3388 (3.8420)	grad_norm 1.0648 (1.2012)	
[2022-01-20 07:32:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][320/1251]	eta 0:34:55 lr 0.000811	time 2.4979 (2.2508)	loss 3.2451 (3.8367)	grad_norm 1.0849 (1.1998)	
[2022-01-20 07:33:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][330/1251]	eta 0:34:30 lr 0.000811	time 1.5831 (2.2485)	loss 3.1635 (3.8303)	grad_norm 1.0908 (1.1994)	
[2022-01-20 07:33:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][340/1251]	eta 0:34:17 lr 0.000811	time 4.0505 (2.2581)	loss 4.0715 (3.8324)	grad_norm 1.1945 (1.1996)	
[2022-01-20 07:34:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][350/1251]	eta 0:33:56 lr 0.000811	time 1.7276 (2.2601)	loss 3.6955 (3.8315)	grad_norm 1.1205 (1.1982)	
[2022-01-20 07:34:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][360/1251]	eta 0:33:32 lr 0.000811	time 1.6947 (2.2590)	loss 3.7826 (3.8212)	grad_norm 1.2792 (1.1999)	
[2022-01-20 07:34:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][370/1251]	eta 0:33:05 lr 0.000811	time 2.2913 (2.2540)	loss 3.0960 (3.8239)	grad_norm 1.2707 (1.2026)	
[2022-01-20 07:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][380/1251]	eta 0:32:43 lr 0.000811	time 3.7563 (2.2541)	loss 3.6511 (3.8208)	grad_norm 1.1002 (1.2016)	
[2022-01-20 07:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][390/1251]	eta 0:32:12 lr 0.000811	time 1.6822 (2.2448)	loss 2.9450 (3.8214)	grad_norm 1.3626 (1.2046)	
[2022-01-20 07:35:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][400/1251]	eta 0:31:47 lr 0.000811	time 2.4963 (2.2417)	loss 4.0583 (3.8192)	grad_norm 1.2472 (1.2061)	
[2022-01-20 07:36:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][410/1251]	eta 0:31:20 lr 0.000811	time 1.8206 (2.2365)	loss 3.3695 (3.8213)	grad_norm 1.1068 (1.2065)	
[2022-01-20 07:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][420/1251]	eta 0:30:57 lr 0.000811	time 2.4896 (2.2350)	loss 2.9610 (3.8146)	grad_norm 1.0790 (1.2061)	
[2022-01-20 07:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][430/1251]	eta 0:30:34 lr 0.000811	time 1.9445 (2.2347)	loss 3.2052 (3.8123)	grad_norm 1.3669 (1.2067)	
[2022-01-20 07:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][440/1251]	eta 0:30:12 lr 0.000811	time 2.4304 (2.2345)	loss 4.1867 (3.8066)	grad_norm 1.3822 (1.2091)	
[2022-01-20 07:37:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][450/1251]	eta 0:29:47 lr 0.000811	time 1.6652 (2.2319)	loss 4.2258 (3.8075)	grad_norm 1.3479 (1.2089)	
[2022-01-20 07:37:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][460/1251]	eta 0:29:25 lr 0.000811	time 2.2080 (2.2325)	loss 3.5462 (3.8013)	grad_norm 1.1691 (1.2109)	
[2022-01-20 07:38:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][470/1251]	eta 0:29:02 lr 0.000811	time 2.4520 (2.2316)	loss 4.2931 (3.7987)	grad_norm 1.0827 (1.2097)	
[2022-01-20 07:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][480/1251]	eta 0:28:39 lr 0.000811	time 2.0976 (2.2308)	loss 3.7225 (3.7999)	grad_norm 1.1947 (1.2089)	
[2022-01-20 07:39:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][490/1251]	eta 0:28:17 lr 0.000811	time 2.2450 (2.2310)	loss 3.9237 (3.7964)	grad_norm 1.2030 (1.2102)	
[2022-01-20 07:39:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][500/1251]	eta 0:27:55 lr 0.000811	time 1.7508 (2.2304)	loss 4.0987 (3.7962)	grad_norm 1.0358 (1.2091)	
[2022-01-20 07:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][510/1251]	eta 0:27:32 lr 0.000811	time 2.0914 (2.2298)	loss 4.0968 (3.7991)	grad_norm 1.0724 (1.2095)	
[2022-01-20 07:40:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][520/1251]	eta 0:27:09 lr 0.000811	time 1.8467 (2.2298)	loss 3.1050 (3.7998)	grad_norm 1.1047 (1.2096)	
[2022-01-20 07:40:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][530/1251]	eta 0:26:46 lr 0.000811	time 1.8875 (2.2280)	loss 4.2554 (3.8011)	grad_norm 1.1781 (1.2094)	
[2022-01-20 07:40:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][540/1251]	eta 0:26:23 lr 0.000811	time 1.6187 (2.2269)	loss 4.1243 (3.7989)	grad_norm 1.0671 (1.2104)	
[2022-01-20 07:41:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][550/1251]	eta 0:26:00 lr 0.000811	time 1.8261 (2.2260)	loss 2.6981 (3.7964)	grad_norm 1.0930 (1.2090)	
[2022-01-20 07:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][560/1251]	eta 0:25:37 lr 0.000811	time 2.2004 (2.2257)	loss 3.7505 (3.7946)	grad_norm 1.2502 (1.2095)	
[2022-01-20 07:41:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][570/1251]	eta 0:25:13 lr 0.000811	time 2.0397 (2.2227)	loss 3.5355 (3.7973)	grad_norm 1.2896 (1.2104)	
[2022-01-20 07:42:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][580/1251]	eta 0:24:49 lr 0.000811	time 1.9472 (2.2200)	loss 3.8362 (3.7951)	grad_norm 1.1003 (1.2093)	
[2022-01-20 07:42:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][590/1251]	eta 0:24:26 lr 0.000811	time 1.8834 (2.2185)	loss 4.6536 (3.7917)	grad_norm 1.0873 (1.2102)	
[2022-01-20 07:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][600/1251]	eta 0:24:03 lr 0.000811	time 2.2809 (2.2172)	loss 4.3519 (3.7922)	grad_norm 1.1320 (1.2096)	
[2022-01-20 07:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][610/1251]	eta 0:23:41 lr 0.000810	time 1.8921 (2.2174)	loss 4.6586 (3.7964)	grad_norm 1.0152 (1.2097)	
[2022-01-20 07:43:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][620/1251]	eta 0:23:18 lr 0.000810	time 2.1747 (2.2170)	loss 4.2321 (3.7977)	grad_norm 1.2815 (1.2096)	
[2022-01-20 07:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][630/1251]	eta 0:22:57 lr 0.000810	time 2.1698 (2.2177)	loss 3.7902 (3.7970)	grad_norm 1.2465 (1.2097)	
[2022-01-20 07:44:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][640/1251]	eta 0:22:35 lr 0.000810	time 2.1588 (2.2189)	loss 3.5063 (3.8010)	grad_norm 1.2225 (1.2094)	
[2022-01-20 07:44:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][650/1251]	eta 0:22:13 lr 0.000810	time 1.9558 (2.2188)	loss 4.6028 (3.8028)	grad_norm 1.1186 (1.2095)	
[2022-01-20 07:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][660/1251]	eta 0:21:50 lr 0.000810	time 2.3675 (2.2182)	loss 4.1771 (3.7988)	grad_norm 1.1378 (1.2081)	
[2022-01-20 07:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][670/1251]	eta 0:21:27 lr 0.000810	time 1.9404 (2.2168)	loss 3.6886 (3.7990)	grad_norm 1.1593 (1.2076)	
[2022-01-20 07:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][680/1251]	eta 0:21:04 lr 0.000810	time 1.5835 (2.2152)	loss 3.3678 (3.7999)	grad_norm 1.1023 (1.2077)	
[2022-01-20 07:46:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][690/1251]	eta 0:20:42 lr 0.000810	time 2.5690 (2.2156)	loss 2.4154 (3.7990)	grad_norm 1.1990 (1.2072)	
[2022-01-20 07:46:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][700/1251]	eta 0:20:19 lr 0.000810	time 1.7799 (2.2125)	loss 3.0361 (3.7975)	grad_norm 1.2037 (1.2062)	
[2022-01-20 07:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][710/1251]	eta 0:19:56 lr 0.000810	time 2.2255 (2.2112)	loss 3.7236 (3.7939)	grad_norm 1.1185 (1.2054)	
[2022-01-20 07:47:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][720/1251]	eta 0:19:35 lr 0.000810	time 2.4235 (2.2133)	loss 4.3720 (3.7972)	grad_norm 1.2150 (1.2052)	
[2022-01-20 07:47:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][730/1251]	eta 0:19:14 lr 0.000810	time 2.1783 (2.2156)	loss 2.7179 (3.7970)	grad_norm 1.1876 (1.2049)	
[2022-01-20 07:48:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][740/1251]	eta 0:18:50 lr 0.000810	time 1.8378 (2.2133)	loss 4.1938 (3.7963)	grad_norm 1.0942 (1.2045)	
[2022-01-20 07:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][750/1251]	eta 0:18:27 lr 0.000810	time 1.9004 (2.2106)	loss 2.4113 (3.7940)	grad_norm 1.1985 (1.2040)	
[2022-01-20 07:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][760/1251]	eta 0:18:04 lr 0.000810	time 2.3588 (2.2085)	loss 3.8552 (3.7912)	grad_norm 1.5226 (1.2045)	
[2022-01-20 07:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][770/1251]	eta 0:17:42 lr 0.000810	time 1.8919 (2.2092)	loss 4.2509 (3.7923)	grad_norm 1.2227 (1.2042)	
[2022-01-20 07:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][780/1251]	eta 0:17:20 lr 0.000810	time 1.8842 (2.2100)	loss 2.8864 (3.7886)	grad_norm 0.9460 (1.2042)	
[2022-01-20 07:49:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][790/1251]	eta 0:16:58 lr 0.000810	time 2.1856 (2.2102)	loss 4.1736 (3.7876)	grad_norm 1.2212 (1.2039)	
[2022-01-20 07:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][800/1251]	eta 0:16:36 lr 0.000810	time 2.1768 (2.2099)	loss 4.1432 (3.7893)	grad_norm 1.1271 (1.2036)	
[2022-01-20 07:50:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][810/1251]	eta 0:16:15 lr 0.000810	time 2.8374 (2.2123)	loss 3.0989 (3.7909)	grad_norm 1.1941 (1.2040)	
[2022-01-20 07:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][820/1251]	eta 0:15:53 lr 0.000810	time 1.5271 (2.2115)	loss 4.5114 (3.7940)	grad_norm 1.2457 (1.2040)	
[2022-01-20 07:51:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][830/1251]	eta 0:15:30 lr 0.000810	time 1.7284 (2.2097)	loss 3.8142 (3.7935)	grad_norm 1.3744 (1.2041)	
[2022-01-20 07:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][840/1251]	eta 0:15:06 lr 0.000810	time 1.5907 (2.2067)	loss 4.2787 (3.7913)	grad_norm 1.0714 (1.2041)	
[2022-01-20 07:52:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][850/1251]	eta 0:14:44 lr 0.000810	time 1.9221 (2.2061)	loss 4.0008 (3.7916)	grad_norm 1.2668 (1.2041)	
[2022-01-20 07:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][860/1251]	eta 0:14:22 lr 0.000810	time 1.8311 (2.2061)	loss 3.0494 (3.7932)	grad_norm 1.0786 (1.2056)	
[2022-01-20 07:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][870/1251]	eta 0:14:00 lr 0.000810	time 2.4793 (2.2054)	loss 3.0369 (3.7921)	grad_norm 1.3752 (1.2053)	
[2022-01-20 07:53:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][880/1251]	eta 0:13:39 lr 0.000810	time 3.0413 (2.2086)	loss 3.3579 (3.7933)	grad_norm 1.1972 (1.2049)	
[2022-01-20 07:53:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][890/1251]	eta 0:13:17 lr 0.000810	time 2.5059 (2.2102)	loss 4.6325 (3.7903)	grad_norm 1.3053 (1.2044)	
[2022-01-20 07:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][900/1251]	eta 0:12:55 lr 0.000810	time 2.1711 (2.2098)	loss 4.5231 (3.7879)	grad_norm 1.2999 (1.2046)	
[2022-01-20 07:54:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][910/1251]	eta 0:12:33 lr 0.000810	time 2.5428 (2.2088)	loss 4.3942 (3.7891)	grad_norm 1.1152 (1.2038)	
[2022-01-20 07:54:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][920/1251]	eta 0:12:10 lr 0.000809	time 1.9613 (2.2078)	loss 4.1580 (3.7889)	grad_norm 1.0476 (1.2031)	
[2022-01-20 07:55:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][930/1251]	eta 0:11:48 lr 0.000809	time 1.5815 (2.2083)	loss 3.5151 (3.7900)	grad_norm 1.1918 (1.2032)	
[2022-01-20 07:55:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][940/1251]	eta 0:11:26 lr 0.000809	time 1.8647 (2.2088)	loss 3.2633 (3.7891)	grad_norm 1.0877 (1.2034)	
[2022-01-20 07:55:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][950/1251]	eta 0:11:04 lr 0.000809	time 2.4232 (2.2082)	loss 3.8261 (3.7876)	grad_norm 1.1670 (1.2035)	
[2022-01-20 07:56:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][960/1251]	eta 0:10:42 lr 0.000809	time 2.1285 (2.2084)	loss 3.9672 (3.7875)	grad_norm 1.2190 (1.2037)	
[2022-01-20 07:56:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][970/1251]	eta 0:10:20 lr 0.000809	time 1.9354 (2.2086)	loss 3.3151 (3.7876)	grad_norm 1.2187 (1.2038)	
[2022-01-20 07:56:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][980/1251]	eta 0:09:58 lr 0.000809	time 2.2390 (2.2093)	loss 3.8336 (3.7861)	grad_norm 1.3264 (1.2037)	
[2022-01-20 07:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][990/1251]	eta 0:09:35 lr 0.000809	time 2.1191 (2.2068)	loss 3.1858 (3.7823)	grad_norm 1.2162 (1.2035)	
[2022-01-20 07:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1000/1251]	eta 0:09:13 lr 0.000809	time 2.0779 (2.2035)	loss 3.8960 (3.7783)	grad_norm 1.1855 (1.2035)	
[2022-01-20 07:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1010/1251]	eta 0:08:50 lr 0.000809	time 1.7073 (2.2015)	loss 3.7299 (3.7772)	grad_norm 1.0166 (1.2023)	
[2022-01-20 07:58:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1020/1251]	eta 0:08:28 lr 0.000809	time 1.9078 (2.2009)	loss 2.9436 (3.7760)	grad_norm 0.9866 (1.2020)	
[2022-01-20 07:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1030/1251]	eta 0:08:06 lr 0.000809	time 2.3249 (2.2012)	loss 4.0581 (3.7755)	grad_norm 1.3044 (1.2023)	
[2022-01-20 07:58:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1040/1251]	eta 0:07:44 lr 0.000809	time 2.4159 (2.2010)	loss 3.6170 (3.7752)	grad_norm 1.6729 (1.2036)	
[2022-01-20 07:59:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1050/1251]	eta 0:07:22 lr 0.000809	time 2.1517 (2.2016)	loss 3.1010 (3.7746)	grad_norm 1.3465 (1.2039)	
[2022-01-20 07:59:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1060/1251]	eta 0:07:00 lr 0.000809	time 2.2415 (2.2034)	loss 4.5291 (3.7756)	grad_norm 1.1707 (1.2036)	
[2022-01-20 08:00:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1070/1251]	eta 0:06:38 lr 0.000809	time 2.2140 (2.2026)	loss 3.6890 (3.7749)	grad_norm 1.1651 (1.2030)	
[2022-01-20 08:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1080/1251]	eta 0:06:16 lr 0.000809	time 1.5848 (2.2029)	loss 4.4109 (3.7741)	grad_norm 1.3292 (1.2036)	
[2022-01-20 08:00:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1090/1251]	eta 0:05:54 lr 0.000809	time 3.1825 (2.2047)	loss 3.4497 (3.7719)	grad_norm 1.2091 (1.2037)	
[2022-01-20 08:01:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1100/1251]	eta 0:05:32 lr 0.000809	time 1.8305 (2.2041)	loss 3.8586 (3.7746)	grad_norm 1.1141 (1.2035)	
[2022-01-20 08:01:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1110/1251]	eta 0:05:10 lr 0.000809	time 2.1628 (2.2036)	loss 4.0127 (3.7739)	grad_norm 1.1544 (1.2035)	
[2022-01-20 08:01:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1120/1251]	eta 0:04:48 lr 0.000809	time 1.8712 (2.2026)	loss 3.9933 (3.7761)	grad_norm 1.1712 (1.2034)	
[2022-01-20 08:02:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1130/1251]	eta 0:04:26 lr 0.000809	time 1.7948 (2.2012)	loss 4.3668 (3.7757)	grad_norm 1.1218 (1.2036)	
[2022-01-20 08:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1140/1251]	eta 0:04:04 lr 0.000809	time 2.4684 (2.2009)	loss 3.1729 (3.7768)	grad_norm 1.0622 (1.2032)	
[2022-01-20 08:03:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1150/1251]	eta 0:03:42 lr 0.000809	time 2.1211 (2.2016)	loss 4.1808 (3.7791)	grad_norm 1.2041 (1.2031)	
[2022-01-20 08:03:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1160/1251]	eta 0:03:20 lr 0.000809	time 2.0557 (2.2024)	loss 4.0803 (3.7779)	grad_norm 1.2219 (1.2029)	
[2022-01-20 08:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1170/1251]	eta 0:02:58 lr 0.000809	time 2.4626 (2.2015)	loss 3.8743 (3.7756)	grad_norm 1.0813 (1.2027)	
[2022-01-20 08:04:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1180/1251]	eta 0:02:36 lr 0.000809	time 1.5642 (2.2005)	loss 3.8390 (3.7718)	grad_norm 1.2505 (1.2029)	
[2022-01-20 08:04:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1190/1251]	eta 0:02:14 lr 0.000809	time 1.5573 (2.1997)	loss 4.2378 (3.7727)	grad_norm 1.1711 (1.2027)	
[2022-01-20 08:04:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1200/1251]	eta 0:01:52 lr 0.000809	time 2.8794 (2.1992)	loss 4.2025 (3.7719)	grad_norm 1.3248 (1.2028)	
[2022-01-20 08:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1210/1251]	eta 0:01:30 lr 0.000809	time 2.1768 (2.1982)	loss 4.1554 (3.7703)	grad_norm 1.3612 (1.2030)	
[2022-01-20 08:05:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1220/1251]	eta 0:01:08 lr 0.000808	time 2.2510 (2.1989)	loss 3.4629 (3.7716)	grad_norm 1.0641 (1.2026)	
[2022-01-20 08:05:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1230/1251]	eta 0:00:46 lr 0.000808	time 1.7449 (2.1988)	loss 4.0398 (3.7725)	grad_norm 1.0278 (1.2022)	
[2022-01-20 08:06:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1240/1251]	eta 0:00:24 lr 0.000808	time 2.0028 (2.1981)	loss 4.0086 (3.7736)	grad_norm 1.0614 (1.2025)	
[2022-01-20 08:06:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [86/300][1250/1251]	eta 0:00:02 lr 0.000808	time 1.1231 (2.1929)	loss 3.8983 (3.7722)	grad_norm 1.4291 (1.2025)	
[2022-01-20 08:06:32 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 86 training takes 0:45:43
[2022-01-20 08:06:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.708 (18.708)	Loss 1.0918 (1.0918)	Acc@1 73.730 (73.730)	Acc@5 93.066 (93.066)	
[2022-01-20 08:07:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.378 (3.476)	Loss 1.1886 (1.1558)	Acc@1 72.266 (72.949)	Acc@5 91.113 (91.850)	
[2022-01-20 08:07:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.628 (2.715)	Loss 1.2145 (1.1652)	Acc@1 71.191 (72.670)	Acc@5 90.625 (91.648)	
[2022-01-20 08:07:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.286 (2.314)	Loss 1.1942 (1.1644)	Acc@1 70.996 (72.650)	Acc@5 91.895 (91.690)	
[2022-01-20 08:08:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.990 (2.228)	Loss 1.2018 (1.1654)	Acc@1 71.289 (72.725)	Acc@5 91.699 (91.661)	
[2022-01-20 08:08:10 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.786 Acc@5 91.664
[2022-01-20 08:08:10 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 72.8%
[2022-01-20 08:08:10 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.02%
[2022-01-20 08:08:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][0/1251]	eta 7:23:16 lr 0.000808	time 21.2605 (21.2605)	loss 3.9448 (3.9448)	grad_norm 1.1242 (1.1242)	
[2022-01-20 08:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][10/1251]	eta 1:27:15 lr 0.000808	time 2.7722 (4.2188)	loss 2.7397 (3.7382)	grad_norm 1.2473 (1.2075)	
[2022-01-20 08:09:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][20/1251]	eta 1:06:42 lr 0.000808	time 2.4812 (3.2515)	loss 3.5718 (3.7246)	grad_norm 1.1399 (1.2139)	
[2022-01-20 08:09:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][30/1251]	eta 0:58:34 lr 0.000808	time 1.3714 (2.8783)	loss 3.2014 (3.7266)	grad_norm 1.1878 (1.2159)	
[2022-01-20 08:10:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][40/1251]	eta 0:56:06 lr 0.000808	time 3.3724 (2.7796)	loss 3.9617 (3.7058)	grad_norm 1.0636 (1.2178)	
[2022-01-20 08:10:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][50/1251]	eta 0:53:53 lr 0.000808	time 2.3837 (2.6926)	loss 3.7507 (3.7235)	grad_norm 1.3823 (1.2010)	
[2022-01-20 08:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][60/1251]	eta 0:51:23 lr 0.000808	time 1.8160 (2.5889)	loss 4.5452 (3.7364)	grad_norm 1.0333 (1.1991)	
[2022-01-20 08:11:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][70/1251]	eta 0:49:28 lr 0.000808	time 1.6199 (2.5137)	loss 4.2141 (3.7770)	grad_norm 1.0880 (1.1949)	
[2022-01-20 08:11:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][80/1251]	eta 0:48:15 lr 0.000808	time 3.3311 (2.4728)	loss 4.0356 (3.7797)	grad_norm 1.4428 (1.1994)	
[2022-01-20 08:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][90/1251]	eta 0:47:27 lr 0.000808	time 2.1516 (2.4525)	loss 2.3706 (3.7483)	grad_norm 1.3107 (1.2178)	
[2022-01-20 08:12:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][100/1251]	eta 0:46:32 lr 0.000808	time 1.9447 (2.4261)	loss 4.0890 (3.7740)	grad_norm 1.1165 (1.2248)	
[2022-01-20 08:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][110/1251]	eta 0:45:38 lr 0.000808	time 1.6108 (2.4003)	loss 3.2789 (3.7606)	grad_norm 1.0421 (1.2186)	
[2022-01-20 08:13:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][120/1251]	eta 0:45:07 lr 0.000808	time 3.6101 (2.3941)	loss 3.1444 (3.7247)	grad_norm 1.4252 (1.2173)	
[2022-01-20 08:13:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][130/1251]	eta 0:44:34 lr 0.000808	time 1.8698 (2.3854)	loss 2.7835 (3.7095)	grad_norm 1.2651 (1.2107)	
[2022-01-20 08:13:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][140/1251]	eta 0:43:36 lr 0.000808	time 1.6429 (2.3549)	loss 3.7025 (3.7055)	grad_norm 1.1326 (1.2062)	
[2022-01-20 08:14:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][150/1251]	eta 0:42:43 lr 0.000808	time 1.6930 (2.3285)	loss 4.2383 (3.6952)	grad_norm 1.1536 (1.2085)	
[2022-01-20 08:14:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][160/1251]	eta 0:42:08 lr 0.000808	time 3.7495 (2.3176)	loss 3.5897 (3.7085)	grad_norm 1.1215 (1.2101)	
[2022-01-20 08:14:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][170/1251]	eta 0:41:48 lr 0.000808	time 2.2226 (2.3209)	loss 2.8014 (3.7064)	grad_norm 1.2280 (1.2041)	
[2022-01-20 08:15:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][180/1251]	eta 0:41:16 lr 0.000808	time 2.0960 (2.3124)	loss 3.2152 (3.6940)	grad_norm 1.1231 (1.1993)	
[2022-01-20 08:15:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][190/1251]	eta 0:40:44 lr 0.000808	time 1.8422 (2.3037)	loss 3.1461 (3.6882)	grad_norm 1.2934 (1.1974)	
[2022-01-20 08:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][200/1251]	eta 0:40:21 lr 0.000808	time 3.4316 (2.3044)	loss 3.4253 (3.6782)	grad_norm 1.1344 (1.1966)	
[2022-01-20 08:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][210/1251]	eta 0:39:54 lr 0.000808	time 2.2393 (2.2998)	loss 3.2295 (3.6778)	grad_norm 1.2323 (1.2011)	
[2022-01-20 08:16:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][220/1251]	eta 0:39:26 lr 0.000808	time 2.4366 (2.2958)	loss 4.5148 (3.6866)	grad_norm 1.3452 (1.2033)	
[2022-01-20 08:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][230/1251]	eta 0:38:54 lr 0.000808	time 2.3105 (2.2868)	loss 3.0604 (3.6938)	grad_norm 1.2302 (1.2035)	
[2022-01-20 08:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][240/1251]	eta 0:38:23 lr 0.000808	time 2.7361 (2.2784)	loss 4.2554 (3.6985)	grad_norm 1.1850 (1.2034)	
[2022-01-20 08:17:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][250/1251]	eta 0:37:51 lr 0.000808	time 1.9467 (2.2688)	loss 3.6895 (3.6982)	grad_norm 1.1146 (1.2037)	
[2022-01-20 08:18:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][260/1251]	eta 0:37:25 lr 0.000808	time 2.0436 (2.2664)	loss 3.8576 (3.6868)	grad_norm 1.2417 (1.2046)	
[2022-01-20 08:18:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][270/1251]	eta 0:36:59 lr 0.000808	time 2.2045 (2.2624)	loss 4.4473 (3.6879)	grad_norm 1.2226 (1.2083)	
[2022-01-20 08:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][280/1251]	eta 0:36:33 lr 0.000807	time 2.7335 (2.2594)	loss 4.3867 (3.6952)	grad_norm 1.2940 (1.2111)	
[2022-01-20 08:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][290/1251]	eta 0:36:09 lr 0.000807	time 1.8801 (2.2572)	loss 4.5162 (3.7044)	grad_norm 1.3686 (1.2127)	
[2022-01-20 08:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][300/1251]	eta 0:35:43 lr 0.000807	time 1.5729 (2.2540)	loss 3.4024 (3.7016)	grad_norm 1.1235 (1.2126)	
[2022-01-20 08:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][310/1251]	eta 0:35:18 lr 0.000807	time 2.4920 (2.2511)	loss 2.8055 (3.6962)	grad_norm 1.0105 (1.2108)	
[2022-01-20 08:20:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][320/1251]	eta 0:34:55 lr 0.000807	time 2.7495 (2.2504)	loss 4.2063 (3.6980)	grad_norm 1.5331 (1.2102)	
[2022-01-20 08:20:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][330/1251]	eta 0:34:32 lr 0.000807	time 2.7920 (2.2499)	loss 4.3213 (3.6967)	grad_norm 1.3353 (1.2126)	
[2022-01-20 08:20:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][340/1251]	eta 0:34:07 lr 0.000807	time 2.5243 (2.2471)	loss 4.0927 (3.6956)	grad_norm 1.2038 (1.2120)	
[2022-01-20 08:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][350/1251]	eta 0:33:44 lr 0.000807	time 2.0903 (2.2472)	loss 3.0344 (3.6928)	grad_norm 1.3029 (1.2128)	
[2022-01-20 08:21:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][360/1251]	eta 0:33:20 lr 0.000807	time 1.9807 (2.2456)	loss 3.7836 (3.6991)	grad_norm 1.1337 (1.2113)	
[2022-01-20 08:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][370/1251]	eta 0:32:55 lr 0.000807	time 2.2474 (2.2426)	loss 4.0580 (3.7035)	grad_norm 1.1581 (1.2112)	
[2022-01-20 08:22:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][380/1251]	eta 0:32:31 lr 0.000807	time 2.3974 (2.2407)	loss 4.4360 (3.7106)	grad_norm 1.1359 (1.2115)	
[2022-01-20 08:22:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][390/1251]	eta 0:32:07 lr 0.000807	time 1.6953 (2.2384)	loss 3.8932 (3.7169)	grad_norm 1.1852 (1.2122)	
[2022-01-20 08:23:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][400/1251]	eta 0:31:41 lr 0.000807	time 2.0354 (2.2341)	loss 2.6976 (3.7074)	grad_norm 1.3327 (1.2121)	
[2022-01-20 08:23:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][410/1251]	eta 0:31:22 lr 0.000807	time 3.3955 (2.2386)	loss 4.2850 (3.7036)	grad_norm 1.2556 (1.2116)	
[2022-01-20 08:23:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][420/1251]	eta 0:30:59 lr 0.000807	time 1.8786 (2.2378)	loss 3.6283 (3.7041)	grad_norm 1.2081 (1.2128)	
[2022-01-20 08:24:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][430/1251]	eta 0:30:36 lr 0.000807	time 1.6527 (2.2374)	loss 3.4352 (3.7029)	grad_norm 1.2839 (1.2134)	
[2022-01-20 08:24:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][440/1251]	eta 0:30:12 lr 0.000807	time 2.1984 (2.2343)	loss 3.9272 (3.6987)	grad_norm 1.2273 (1.2121)	
[2022-01-20 08:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][450/1251]	eta 0:29:43 lr 0.000807	time 2.0349 (2.2271)	loss 3.8803 (3.7033)	grad_norm 1.1487 (1.2118)	
[2022-01-20 08:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][460/1251]	eta 0:29:20 lr 0.000807	time 1.8693 (2.2258)	loss 3.8408 (3.6996)	grad_norm 1.3241 (1.2137)	
[2022-01-20 08:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][470/1251]	eta 0:28:56 lr 0.000807	time 1.8135 (2.2239)	loss 4.0153 (3.7040)	grad_norm 1.1643 (1.2141)	
[2022-01-20 08:26:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][480/1251]	eta 0:28:34 lr 0.000807	time 1.8831 (2.2235)	loss 3.9322 (3.7118)	grad_norm 1.3278 (1.2133)	
[2022-01-20 08:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][490/1251]	eta 0:28:12 lr 0.000807	time 2.0064 (2.2244)	loss 3.3945 (3.7129)	grad_norm 1.1812 (1.2121)	
[2022-01-20 08:26:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][500/1251]	eta 0:27:52 lr 0.000807	time 2.1642 (2.2276)	loss 3.9562 (3.7161)	grad_norm 1.1062 (1.2111)	
[2022-01-20 08:27:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][510/1251]	eta 0:27:30 lr 0.000807	time 1.9411 (2.2278)	loss 4.0835 (3.7199)	grad_norm 1.1060 (1.2113)	
[2022-01-20 08:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][520/1251]	eta 0:27:08 lr 0.000807	time 1.4892 (2.2273)	loss 4.6098 (3.7195)	grad_norm 1.2180 (1.2119)	
[2022-01-20 08:27:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][530/1251]	eta 0:26:43 lr 0.000807	time 2.2177 (2.2240)	loss 4.1611 (3.7212)	grad_norm 1.3131 (1.2117)	
[2022-01-20 08:28:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][540/1251]	eta 0:26:18 lr 0.000807	time 1.7973 (2.2195)	loss 4.0839 (3.7230)	grad_norm 1.0732 (1.2115)	
[2022-01-20 08:28:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][550/1251]	eta 0:25:53 lr 0.000807	time 1.8615 (2.2154)	loss 3.5613 (3.7211)	grad_norm 1.3916 (1.2125)	
[2022-01-20 08:28:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][560/1251]	eta 0:25:30 lr 0.000807	time 2.1662 (2.2154)	loss 3.7458 (3.7233)	grad_norm 1.1467 (1.2115)	
[2022-01-20 08:29:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][570/1251]	eta 0:25:06 lr 0.000807	time 2.2603 (2.2127)	loss 4.2149 (3.7254)	grad_norm 1.1931 (1.2113)	
[2022-01-20 08:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][580/1251]	eta 0:24:43 lr 0.000806	time 1.6908 (2.2112)	loss 3.6139 (3.7288)	grad_norm 1.0530 (1.2133)	
[2022-01-20 08:29:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][590/1251]	eta 0:24:23 lr 0.000806	time 2.8612 (2.2140)	loss 3.9398 (3.7309)	grad_norm 1.3924 (1.2133)	
[2022-01-20 08:30:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][600/1251]	eta 0:24:01 lr 0.000806	time 1.6061 (2.2139)	loss 3.4723 (3.7310)	grad_norm 1.2051 (1.2133)	
[2022-01-20 08:30:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][610/1251]	eta 0:23:40 lr 0.000806	time 2.8156 (2.2155)	loss 3.2817 (3.7307)	grad_norm 1.2755 (1.2126)	
[2022-01-20 08:31:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][620/1251]	eta 0:23:19 lr 0.000806	time 2.2362 (2.2176)	loss 2.9418 (3.7320)	grad_norm 1.1203 (1.2130)	
[2022-01-20 08:31:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][630/1251]	eta 0:22:57 lr 0.000806	time 2.1461 (2.2175)	loss 2.9607 (3.7321)	grad_norm 1.2616 (1.2151)	
[2022-01-20 08:31:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][640/1251]	eta 0:22:32 lr 0.000806	time 1.9114 (2.2141)	loss 4.1001 (3.7338)	grad_norm 1.0528 (1.2139)	
[2022-01-20 08:32:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][650/1251]	eta 0:22:09 lr 0.000806	time 2.3099 (2.2119)	loss 4.0595 (3.7385)	grad_norm 1.1071 (1.2132)	
[2022-01-20 08:32:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][660/1251]	eta 0:21:45 lr 0.000806	time 1.9633 (2.2096)	loss 2.7372 (3.7359)	grad_norm 1.2133 (1.2133)	
[2022-01-20 08:32:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][670/1251]	eta 0:21:23 lr 0.000806	time 2.4647 (2.2083)	loss 3.8827 (3.7354)	grad_norm 1.0058 (1.2144)	
[2022-01-20 08:33:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][680/1251]	eta 0:21:01 lr 0.000806	time 2.1960 (2.2089)	loss 4.5589 (3.7354)	grad_norm 1.1395 (1.2145)	
[2022-01-20 08:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][690/1251]	eta 0:20:38 lr 0.000806	time 1.8646 (2.2085)	loss 2.5982 (3.7332)	grad_norm 1.3845 (1.2152)	
[2022-01-20 08:33:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][700/1251]	eta 0:20:16 lr 0.000806	time 2.2138 (2.2081)	loss 3.1138 (3.7350)	grad_norm 1.2409 (1.2146)	
[2022-01-20 08:34:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][710/1251]	eta 0:19:55 lr 0.000806	time 2.1258 (2.2095)	loss 3.8975 (3.7369)	grad_norm 1.2271 (1.2137)	
[2022-01-20 08:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][720/1251]	eta 0:19:34 lr 0.000806	time 1.5725 (2.2115)	loss 3.7108 (3.7380)	grad_norm 1.1368 (1.2136)	
[2022-01-20 08:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][730/1251]	eta 0:19:12 lr 0.000806	time 1.8924 (2.2113)	loss 4.0285 (3.7389)	grad_norm 1.1388 (1.2127)	
[2022-01-20 08:35:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][740/1251]	eta 0:18:49 lr 0.000806	time 1.7165 (2.2105)	loss 2.9409 (3.7366)	grad_norm 1.1216 (1.2131)	
[2022-01-20 08:35:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][750/1251]	eta 0:18:26 lr 0.000806	time 2.3179 (2.2091)	loss 3.2236 (3.7360)	grad_norm 1.2281 (1.2133)	
[2022-01-20 08:36:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][760/1251]	eta 0:18:04 lr 0.000806	time 1.8746 (2.2086)	loss 3.9574 (3.7389)	grad_norm 1.3497 (1.2144)	
[2022-01-20 08:36:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][770/1251]	eta 0:17:42 lr 0.000806	time 2.1473 (2.2091)	loss 3.9352 (3.7383)	grad_norm 1.1299 (1.2149)	
[2022-01-20 08:36:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][780/1251]	eta 0:17:21 lr 0.000806	time 2.1490 (2.2106)	loss 3.2822 (3.7401)	grad_norm 1.4929 (1.2179)	
[2022-01-20 08:37:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][790/1251]	eta 0:16:59 lr 0.000806	time 2.2059 (2.2115)	loss 2.7005 (3.7353)	grad_norm 1.1250 (1.2175)	
[2022-01-20 08:37:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][800/1251]	eta 0:16:37 lr 0.000806	time 2.0958 (2.2108)	loss 3.5439 (3.7375)	grad_norm 1.1618 (1.2170)	
[2022-01-20 08:38:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][810/1251]	eta 0:16:13 lr 0.000806	time 1.6007 (2.2065)	loss 3.6545 (3.7338)	grad_norm 1.1215 (1.2162)	
[2022-01-20 08:38:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][820/1251]	eta 0:15:49 lr 0.000806	time 2.0474 (2.2040)	loss 2.6926 (3.7314)	grad_norm 1.1240 (1.2165)	
[2022-01-20 08:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][830/1251]	eta 0:15:27 lr 0.000806	time 2.5087 (2.2034)	loss 3.4012 (3.7297)	grad_norm 1.0386 (1.2155)	
[2022-01-20 08:39:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][840/1251]	eta 0:15:05 lr 0.000806	time 2.2612 (2.2033)	loss 4.2953 (3.7301)	grad_norm 1.0679 (1.2150)	
[2022-01-20 08:39:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][850/1251]	eta 0:14:43 lr 0.000806	time 1.9078 (2.2026)	loss 2.8901 (3.7290)	grad_norm 1.2080 (1.2148)	
[2022-01-20 08:39:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][860/1251]	eta 0:14:20 lr 0.000806	time 2.3163 (2.2017)	loss 4.1003 (3.7281)	grad_norm 0.9766 (1.2138)	
[2022-01-20 08:40:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][870/1251]	eta 0:13:58 lr 0.000806	time 2.1730 (2.2019)	loss 4.0681 (3.7307)	grad_norm 1.0922 (1.2133)	
[2022-01-20 08:40:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][880/1251]	eta 0:13:37 lr 0.000805	time 2.5710 (2.2044)	loss 2.7172 (3.7277)	grad_norm 1.2214 (1.2126)	
[2022-01-20 08:40:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][890/1251]	eta 0:13:16 lr 0.000805	time 2.9666 (2.2052)	loss 4.5446 (3.7269)	grad_norm 1.3080 (1.2129)	
[2022-01-20 08:41:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][900/1251]	eta 0:12:53 lr 0.000805	time 1.5395 (2.2045)	loss 3.7992 (3.7289)	grad_norm 1.2898 (1.2125)	
[2022-01-20 08:41:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][910/1251]	eta 0:12:32 lr 0.000805	time 2.1870 (2.2062)	loss 3.7714 (3.7305)	grad_norm 1.1999 (1.2123)	
[2022-01-20 08:42:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][920/1251]	eta 0:12:09 lr 0.000805	time 2.1822 (2.2050)	loss 2.8960 (3.7278)	grad_norm 1.5274 (1.2131)	
[2022-01-20 08:42:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][930/1251]	eta 0:11:47 lr 0.000805	time 3.4915 (2.2047)	loss 4.1754 (3.7268)	grad_norm 1.1612 (1.2130)	
[2022-01-20 08:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][940/1251]	eta 0:11:25 lr 0.000805	time 1.9806 (2.2032)	loss 4.2707 (3.7295)	grad_norm 1.2311 (1.2123)	
[2022-01-20 08:43:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][950/1251]	eta 0:11:02 lr 0.000805	time 1.5907 (2.2017)	loss 3.4795 (3.7307)	grad_norm 1.2316 (1.2127)	
[2022-01-20 08:43:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][960/1251]	eta 0:10:40 lr 0.000805	time 2.1408 (2.1997)	loss 2.7031 (3.7315)	grad_norm 1.1116 (1.2127)	
[2022-01-20 08:43:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][970/1251]	eta 0:10:18 lr 0.000805	time 2.9287 (2.2002)	loss 2.8673 (3.7286)	grad_norm 1.4049 (1.2123)	
[2022-01-20 08:44:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][980/1251]	eta 0:09:56 lr 0.000805	time 1.9396 (2.1999)	loss 3.5441 (3.7309)	grad_norm 1.2361 (1.2126)	
[2022-01-20 08:44:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][990/1251]	eta 0:09:35 lr 0.000805	time 3.4395 (2.2032)	loss 3.5344 (3.7305)	grad_norm 1.2064 (1.2125)	
[2022-01-20 08:44:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1000/1251]	eta 0:09:13 lr 0.000805	time 3.2840 (2.2050)	loss 2.6006 (3.7302)	grad_norm 1.1504 (1.2115)	
[2022-01-20 08:45:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1010/1251]	eta 0:08:51 lr 0.000805	time 3.1623 (2.2069)	loss 4.0351 (3.7317)	grad_norm 1.3110 (1.2125)	
[2022-01-20 08:45:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1020/1251]	eta 0:08:29 lr 0.000805	time 1.8653 (2.2061)	loss 3.1898 (3.7337)	grad_norm 1.0386 (1.2129)	
[2022-01-20 08:46:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1030/1251]	eta 0:08:07 lr 0.000805	time 2.1367 (2.2039)	loss 3.5267 (3.7333)	grad_norm 1.2668 (1.2127)	
[2022-01-20 08:46:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1040/1251]	eta 0:07:44 lr 0.000805	time 2.9133 (2.2018)	loss 4.5812 (3.7352)	grad_norm 1.3103 (1.2126)	
[2022-01-20 08:46:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1050/1251]	eta 0:07:22 lr 0.000805	time 1.9106 (2.2006)	loss 3.6835 (3.7357)	grad_norm 1.0860 (1.2121)	
[2022-01-20 08:47:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1060/1251]	eta 0:07:00 lr 0.000805	time 1.8561 (2.1998)	loss 4.3323 (3.7361)	grad_norm 1.3406 (1.2121)	
[2022-01-20 08:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1070/1251]	eta 0:06:38 lr 0.000805	time 2.4998 (2.1998)	loss 3.6573 (3.7341)	grad_norm 1.1404 (1.2123)	
[2022-01-20 08:47:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1080/1251]	eta 0:06:16 lr 0.000805	time 2.7564 (2.2022)	loss 3.4172 (3.7340)	grad_norm 0.9457 (1.2121)	
[2022-01-20 08:48:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1090/1251]	eta 0:05:54 lr 0.000805	time 2.3025 (2.2038)	loss 3.8256 (3.7345)	grad_norm 1.2626 (1.2124)	
[2022-01-20 08:48:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1100/1251]	eta 0:05:33 lr 0.000805	time 2.8089 (2.2053)	loss 4.3722 (3.7377)	grad_norm 1.1861 (1.2123)	
[2022-01-20 08:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1110/1251]	eta 0:05:10 lr 0.000805	time 2.0393 (2.2041)	loss 4.3125 (3.7379)	grad_norm 1.0597 (1.2119)	
[2022-01-20 08:49:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1120/1251]	eta 0:04:48 lr 0.000805	time 1.6402 (2.2015)	loss 4.2713 (3.7395)	grad_norm 1.1419 (1.2111)	
[2022-01-20 08:49:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1130/1251]	eta 0:04:26 lr 0.000805	time 1.9197 (2.1993)	loss 3.4391 (3.7408)	grad_norm 1.1488 (1.2103)	
[2022-01-20 08:49:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1140/1251]	eta 0:04:04 lr 0.000805	time 2.4809 (2.1985)	loss 3.9421 (3.7404)	grad_norm 1.0530 (1.2095)	
[2022-01-20 08:50:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1150/1251]	eta 0:03:42 lr 0.000805	time 3.2785 (2.1999)	loss 3.8689 (3.7407)	grad_norm 1.3205 (1.2098)	
[2022-01-20 08:50:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1160/1251]	eta 0:03:20 lr 0.000805	time 2.8228 (2.2003)	loss 4.4053 (3.7404)	grad_norm 1.0949 (1.2096)	
[2022-01-20 08:51:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1170/1251]	eta 0:02:58 lr 0.000805	time 1.8699 (2.2006)	loss 3.4790 (3.7431)	grad_norm 1.2080 (1.2100)	
[2022-01-20 08:51:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1180/1251]	eta 0:02:36 lr 0.000805	time 2.3001 (2.2005)	loss 3.9799 (3.7415)	grad_norm 1.1029 (1.2100)	
[2022-01-20 08:51:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1190/1251]	eta 0:02:14 lr 0.000804	time 2.8067 (2.2008)	loss 4.1035 (3.7410)	grad_norm 1.2644 (1.2097)	
[2022-01-20 08:52:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1200/1251]	eta 0:01:52 lr 0.000804	time 2.6924 (2.2015)	loss 3.8136 (3.7420)	grad_norm 1.1129 (1.2092)	
[2022-01-20 08:52:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1210/1251]	eta 0:01:30 lr 0.000804	time 1.9027 (2.2021)	loss 3.7281 (3.7410)	grad_norm 1.2979 (1.2092)	
[2022-01-20 08:52:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1220/1251]	eta 0:01:08 lr 0.000804	time 2.5817 (2.2018)	loss 3.5341 (3.7429)	grad_norm 1.1101 (1.2090)	
[2022-01-20 08:53:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1230/1251]	eta 0:00:46 lr 0.000804	time 2.7517 (2.2018)	loss 3.3679 (3.7422)	grad_norm 1.0730 (1.2084)	
[2022-01-20 08:53:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1240/1251]	eta 0:00:24 lr 0.000804	time 1.3003 (2.1997)	loss 2.8882 (3.7416)	grad_norm 1.2732 (1.2084)	
[2022-01-20 08:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [87/300][1250/1251]	eta 0:00:02 lr 0.000804	time 1.1942 (2.1943)	loss 2.9273 (3.7414)	grad_norm 1.1600 (1.2080)	
[2022-01-20 08:53:56 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 87 training takes 0:45:45
[2022-01-20 08:54:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.340 (18.340)	Loss 1.1011 (1.1011)	Acc@1 72.070 (72.070)	Acc@5 92.969 (92.969)	
[2022-01-20 08:54:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.777 (3.396)	Loss 1.1769 (1.1447)	Acc@1 71.973 (72.763)	Acc@5 91.797 (92.045)	
[2022-01-20 08:54:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.564 (2.564)	Loss 1.1579 (1.1453)	Acc@1 72.559 (73.191)	Acc@5 91.309 (91.978)	
[2022-01-20 08:55:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.562 (2.275)	Loss 1.1808 (1.1480)	Acc@1 72.070 (73.129)	Acc@5 91.406 (91.819)	
[2022-01-20 08:55:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.254 (2.176)	Loss 1.1270 (1.1462)	Acc@1 72.559 (73.168)	Acc@5 92.383 (91.883)	
[2022-01-20 08:55:31 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.192 Acc@5 91.858
[2022-01-20 08:55:31 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.2%
[2022-01-20 08:55:31 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.19%
[2022-01-20 08:55:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][0/1251]	eta 7:19:44 lr 0.000804	time 21.0903 (21.0903)	loss 4.4419 (4.4419)	grad_norm 1.8322 (1.8322)	
[2022-01-20 08:56:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][10/1251]	eta 1:27:33 lr 0.000804	time 2.8756 (4.2336)	loss 3.9983 (3.4016)	grad_norm 1.1597 (1.2889)	
[2022-01-20 08:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][20/1251]	eta 1:06:36 lr 0.000804	time 1.4810 (3.2466)	loss 4.2242 (3.5443)	grad_norm 1.1868 (1.2549)	
[2022-01-20 08:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][30/1251]	eta 0:59:06 lr 0.000804	time 1.2975 (2.9043)	loss 3.9846 (3.5372)	grad_norm 1.1713 (1.2516)	
[2022-01-20 08:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][40/1251]	eta 0:56:06 lr 0.000804	time 3.7391 (2.7802)	loss 3.9586 (3.6714)	grad_norm 1.0224 (1.2193)	
[2022-01-20 08:57:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][50/1251]	eta 0:54:36 lr 0.000804	time 2.5541 (2.7282)	loss 2.8312 (3.7281)	grad_norm 1.0025 (1.2076)	
[2022-01-20 08:58:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][60/1251]	eta 0:52:24 lr 0.000804	time 1.5791 (2.6401)	loss 4.4186 (3.7344)	grad_norm 1.1128 (1.2160)	
[2022-01-20 08:58:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][70/1251]	eta 0:50:21 lr 0.000804	time 1.9175 (2.5586)	loss 2.8439 (3.7007)	grad_norm 1.0957 (1.2116)	
[2022-01-20 08:58:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][80/1251]	eta 0:48:45 lr 0.000804	time 2.3213 (2.4982)	loss 4.3693 (3.6723)	grad_norm 1.1428 (1.2095)	
[2022-01-20 08:59:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][90/1251]	eta 0:47:41 lr 0.000804	time 2.0517 (2.4647)	loss 4.4497 (3.7089)	grad_norm 1.1585 (1.2097)	
[2022-01-20 08:59:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][100/1251]	eta 0:46:45 lr 0.000804	time 2.7298 (2.4377)	loss 4.2289 (3.7072)	grad_norm 1.4272 (1.2137)	
[2022-01-20 08:59:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][110/1251]	eta 0:45:49 lr 0.000804	time 1.5018 (2.4097)	loss 3.9432 (3.7150)	grad_norm 1.1322 (1.2073)	
[2022-01-20 09:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][120/1251]	eta 0:44:55 lr 0.000804	time 2.0521 (2.3834)	loss 3.1243 (3.7146)	grad_norm 1.1719 (1.2060)	
[2022-01-20 09:00:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][130/1251]	eta 0:44:17 lr 0.000804	time 1.9030 (2.3704)	loss 4.5990 (3.7008)	grad_norm 1.4124 (1.2024)	
[2022-01-20 09:01:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][140/1251]	eta 0:43:43 lr 0.000804	time 2.2731 (2.3614)	loss 3.6866 (3.7058)	grad_norm 1.2537 (1.2017)	
[2022-01-20 09:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][150/1251]	eta 0:43:04 lr 0.000804	time 2.1145 (2.3471)	loss 4.3715 (3.7169)	grad_norm 1.3788 (1.2045)	
[2022-01-20 09:01:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][160/1251]	eta 0:42:28 lr 0.000804	time 1.7641 (2.3359)	loss 3.4592 (3.7155)	grad_norm 1.2216 (1.2044)	
[2022-01-20 09:02:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][170/1251]	eta 0:41:56 lr 0.000804	time 1.9842 (2.3280)	loss 3.0219 (3.6960)	grad_norm 1.5368 (1.2039)	
[2022-01-20 09:02:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][180/1251]	eta 0:41:29 lr 0.000804	time 2.9905 (2.3246)	loss 4.1220 (3.7018)	grad_norm 1.5112 (1.2060)	
[2022-01-20 09:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][190/1251]	eta 0:40:51 lr 0.000804	time 1.8829 (2.3109)	loss 4.2522 (3.7094)	grad_norm 1.3292 (1.2091)	
[2022-01-20 09:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][200/1251]	eta 0:40:18 lr 0.000804	time 1.9428 (2.3014)	loss 4.5954 (3.7178)	grad_norm 1.1469 (1.2085)	
[2022-01-20 09:03:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][210/1251]	eta 0:39:56 lr 0.000804	time 2.3753 (2.3020)	loss 4.0106 (3.7200)	grad_norm 1.1812 (1.2076)	
[2022-01-20 09:04:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][220/1251]	eta 0:39:31 lr 0.000804	time 2.8291 (2.3004)	loss 3.6273 (3.7206)	grad_norm 1.3230 (1.2080)	
[2022-01-20 09:04:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][230/1251]	eta 0:39:05 lr 0.000804	time 1.9181 (2.2975)	loss 2.6328 (3.7193)	grad_norm 1.0579 (1.2045)	
[2022-01-20 09:04:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][240/1251]	eta 0:38:29 lr 0.000803	time 1.5904 (2.2846)	loss 2.6671 (3.7096)	grad_norm 1.0802 (1.2104)	
[2022-01-20 09:05:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][250/1251]	eta 0:37:58 lr 0.000803	time 2.5628 (2.2763)	loss 4.1674 (3.7134)	grad_norm 1.2219 (1.2129)	
[2022-01-20 09:05:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][260/1251]	eta 0:37:33 lr 0.000803	time 2.7704 (2.2744)	loss 3.0969 (3.7160)	grad_norm 1.1961 (1.2126)	
[2022-01-20 09:05:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][270/1251]	eta 0:37:05 lr 0.000803	time 1.9973 (2.2690)	loss 4.1979 (3.7165)	grad_norm 1.3060 (1.2116)	
[2022-01-20 09:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][280/1251]	eta 0:36:39 lr 0.000803	time 2.2027 (2.2657)	loss 3.1590 (3.7227)	grad_norm 1.3012 (1.2167)	
[2022-01-20 09:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][290/1251]	eta 0:36:08 lr 0.000803	time 1.8952 (2.2567)	loss 4.3897 (3.7182)	grad_norm 1.5595 (1.2201)	
[2022-01-20 09:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][300/1251]	eta 0:35:45 lr 0.000803	time 2.1629 (2.2560)	loss 4.0738 (3.7130)	grad_norm 1.2705 (1.2199)	
[2022-01-20 09:07:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][310/1251]	eta 0:35:23 lr 0.000803	time 2.5227 (2.2562)	loss 4.2450 (3.7094)	grad_norm 1.1075 (1.2195)	
[2022-01-20 09:07:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][320/1251]	eta 0:34:58 lr 0.000803	time 2.1983 (2.2541)	loss 4.0645 (3.6976)	grad_norm 1.2227 (1.2202)	
[2022-01-20 09:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][330/1251]	eta 0:34:32 lr 0.000803	time 2.0598 (2.2504)	loss 4.6443 (3.7021)	grad_norm 1.4024 (1.2232)	
[2022-01-20 09:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][340/1251]	eta 0:34:06 lr 0.000803	time 2.4578 (2.2462)	loss 3.8343 (3.7018)	grad_norm 0.9735 (1.2223)	
[2022-01-20 09:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][350/1251]	eta 0:33:42 lr 0.000803	time 1.4737 (2.2445)	loss 2.5685 (3.6996)	grad_norm 1.2676 (1.2212)	
[2022-01-20 09:09:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][360/1251]	eta 0:33:20 lr 0.000803	time 2.5713 (2.2455)	loss 4.6899 (3.7034)	grad_norm 1.2126 (1.2208)	
[2022-01-20 09:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][370/1251]	eta 0:32:57 lr 0.000803	time 2.0927 (2.2450)	loss 3.7569 (3.7122)	grad_norm 1.4159 (1.2221)	
[2022-01-20 09:09:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][380/1251]	eta 0:32:32 lr 0.000803	time 2.5098 (2.2413)	loss 4.1468 (3.7192)	grad_norm 1.3812 (1.2240)	
[2022-01-20 09:10:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][390/1251]	eta 0:32:05 lr 0.000803	time 2.2493 (2.2360)	loss 4.1259 (3.7142)	grad_norm 1.2035 (1.2241)	
[2022-01-20 09:10:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][400/1251]	eta 0:31:40 lr 0.000803	time 2.6370 (2.2336)	loss 3.5153 (3.7083)	grad_norm 1.3764 (1.2259)	
[2022-01-20 09:10:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][410/1251]	eta 0:31:17 lr 0.000803	time 2.6066 (2.2322)	loss 4.2989 (3.7117)	grad_norm 1.3707 (1.2269)	
[2022-01-20 09:11:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][420/1251]	eta 0:30:53 lr 0.000803	time 2.7987 (2.2306)	loss 4.0860 (3.7159)	grad_norm 1.0401 (1.2264)	
[2022-01-20 09:11:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][430/1251]	eta 0:30:30 lr 0.000803	time 1.7597 (2.2291)	loss 3.8058 (3.7176)	grad_norm 1.3682 (1.2263)	
[2022-01-20 09:11:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][440/1251]	eta 0:30:09 lr 0.000803	time 2.9630 (2.2311)	loss 4.1209 (3.7204)	grad_norm 1.4248 (1.2280)	
[2022-01-20 09:12:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][450/1251]	eta 0:29:49 lr 0.000803	time 3.0587 (2.2345)	loss 4.3185 (3.7279)	grad_norm 1.1122 (1.2275)	
[2022-01-20 09:12:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][460/1251]	eta 0:29:31 lr 0.000803	time 2.3690 (2.2392)	loss 3.3949 (3.7236)	grad_norm 1.2621 (1.2274)	
[2022-01-20 09:13:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][470/1251]	eta 0:29:09 lr 0.000803	time 2.1311 (2.2405)	loss 3.4025 (3.7259)	grad_norm 1.1269 (1.2270)	
[2022-01-20 09:13:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][480/1251]	eta 0:28:47 lr 0.000803	time 3.0931 (2.2406)	loss 3.7914 (3.7265)	grad_norm 1.1103 (1.2262)	
[2022-01-20 09:13:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][490/1251]	eta 0:28:21 lr 0.000803	time 1.9069 (2.2364)	loss 3.9714 (3.7288)	grad_norm 1.3649 (1.2267)	
[2022-01-20 09:14:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][500/1251]	eta 0:27:54 lr 0.000803	time 1.9704 (2.2296)	loss 2.9337 (3.7256)	grad_norm 1.1406 (1.2278)	
[2022-01-20 09:14:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][510/1251]	eta 0:27:31 lr 0.000803	time 2.0327 (2.2292)	loss 3.7695 (3.7229)	grad_norm 1.3274 (1.2279)	
[2022-01-20 09:14:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][520/1251]	eta 0:27:07 lr 0.000803	time 2.8722 (2.2267)	loss 3.5795 (3.7225)	grad_norm 1.1502 (1.2299)	
[2022-01-20 09:15:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][530/1251]	eta 0:26:46 lr 0.000803	time 1.7476 (2.2275)	loss 3.6219 (3.7240)	grad_norm 1.0912 (1.2291)	
[2022-01-20 09:15:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][540/1251]	eta 0:26:25 lr 0.000802	time 2.6989 (2.2299)	loss 3.7537 (3.7236)	grad_norm 1.1456 (1.2287)	
[2022-01-20 09:15:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][550/1251]	eta 0:26:00 lr 0.000802	time 1.5546 (2.2266)	loss 3.2464 (3.7243)	grad_norm 1.4478 (1.2307)	
[2022-01-20 09:16:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][560/1251]	eta 0:25:37 lr 0.000802	time 2.4666 (2.2249)	loss 3.7903 (3.7253)	grad_norm 1.2756 (1.2308)	
[2022-01-20 09:16:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][570/1251]	eta 0:25:13 lr 0.000802	time 1.5752 (2.2229)	loss 2.5295 (3.7229)	grad_norm 1.3617 (1.2308)	
[2022-01-20 09:17:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][580/1251]	eta 0:24:50 lr 0.000802	time 1.6497 (2.2216)	loss 3.6103 (3.7265)	grad_norm 1.0531 (1.2297)	
[2022-01-20 09:17:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][590/1251]	eta 0:24:28 lr 0.000802	time 2.4902 (2.2224)	loss 3.2915 (3.7303)	grad_norm 1.6850 (1.2308)	
[2022-01-20 09:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][600/1251]	eta 0:24:08 lr 0.000802	time 2.4859 (2.2256)	loss 4.1373 (3.7307)	grad_norm 1.0284 (1.2294)	
[2022-01-20 09:18:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][610/1251]	eta 0:23:46 lr 0.000802	time 2.1422 (2.2250)	loss 3.3068 (3.7295)	grad_norm 1.1809 (1.2280)	
[2022-01-20 09:18:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][620/1251]	eta 0:23:24 lr 0.000802	time 1.9864 (2.2258)	loss 3.7345 (3.7266)	grad_norm 1.3454 (1.2275)	
[2022-01-20 09:18:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][630/1251]	eta 0:23:01 lr 0.000802	time 2.6694 (2.2252)	loss 3.3712 (3.7257)	grad_norm 1.6407 (1.2283)	
[2022-01-20 09:19:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][640/1251]	eta 0:22:37 lr 0.000802	time 1.8631 (2.2226)	loss 3.7266 (3.7258)	grad_norm 1.1741 (1.2267)	
[2022-01-20 09:19:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][650/1251]	eta 0:22:15 lr 0.000802	time 1.5603 (2.2214)	loss 4.2565 (3.7254)	grad_norm 1.0229 (1.2258)	
[2022-01-20 09:19:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][660/1251]	eta 0:21:51 lr 0.000802	time 1.6458 (2.2193)	loss 3.7028 (3.7195)	grad_norm 1.0590 (1.2244)	
[2022-01-20 09:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][670/1251]	eta 0:21:27 lr 0.000802	time 1.6017 (2.2165)	loss 3.4448 (3.7213)	grad_norm 1.2794 (1.2256)	
[2022-01-20 09:20:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][680/1251]	eta 0:21:05 lr 0.000802	time 2.0806 (2.2168)	loss 3.9519 (3.7236)	grad_norm 1.0818 (1.2262)	
[2022-01-20 09:21:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][690/1251]	eta 0:20:44 lr 0.000802	time 1.8442 (2.2181)	loss 2.9054 (3.7246)	grad_norm 1.6063 (1.2266)	
[2022-01-20 09:21:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][700/1251]	eta 0:20:21 lr 0.000802	time 1.8922 (2.2174)	loss 4.4277 (3.7285)	grad_norm 1.1119 (1.2257)	
[2022-01-20 09:21:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][710/1251]	eta 0:19:58 lr 0.000802	time 1.9939 (2.2157)	loss 3.3019 (3.7284)	grad_norm 1.2113 (1.2251)	
[2022-01-20 09:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][720/1251]	eta 0:19:36 lr 0.000802	time 2.1407 (2.2154)	loss 3.5167 (3.7260)	grad_norm 1.1731 (1.2254)	
[2022-01-20 09:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][730/1251]	eta 0:19:14 lr 0.000802	time 1.9395 (2.2153)	loss 4.0788 (3.7273)	grad_norm 1.0997 (1.2263)	
[2022-01-20 09:22:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][740/1251]	eta 0:18:51 lr 0.000802	time 1.8053 (2.2143)	loss 3.2158 (3.7220)	grad_norm 1.0840 (1.2255)	
[2022-01-20 09:23:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][750/1251]	eta 0:18:29 lr 0.000802	time 1.6697 (2.2146)	loss 2.8654 (3.7207)	grad_norm 1.1344 (1.2248)	
[2022-01-20 09:23:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][760/1251]	eta 0:18:07 lr 0.000802	time 2.4487 (2.2142)	loss 2.7382 (3.7229)	grad_norm 1.2471 (1.2269)	
[2022-01-20 09:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][770/1251]	eta 0:17:44 lr 0.000802	time 2.4924 (2.2127)	loss 4.2464 (3.7239)	grad_norm 1.1391 (1.2265)	
[2022-01-20 09:24:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][780/1251]	eta 0:17:21 lr 0.000802	time 1.8899 (2.2108)	loss 3.6326 (3.7292)	grad_norm 1.1389 (1.2264)	
[2022-01-20 09:24:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][790/1251]	eta 0:16:59 lr 0.000802	time 1.9308 (2.2108)	loss 4.3643 (3.7293)	grad_norm 1.4252 (1.2267)	
[2022-01-20 09:25:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][800/1251]	eta 0:16:37 lr 0.000802	time 1.5469 (2.2110)	loss 2.8200 (3.7286)	grad_norm 1.2046 (1.2271)	
[2022-01-20 09:25:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][810/1251]	eta 0:16:14 lr 0.000802	time 2.5312 (2.2109)	loss 3.8312 (3.7311)	grad_norm 1.1916 (1.2272)	
[2022-01-20 09:25:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][820/1251]	eta 0:15:52 lr 0.000802	time 1.4833 (2.2095)	loss 4.0743 (3.7338)	grad_norm 1.1358 (1.2276)	
[2022-01-20 09:26:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][830/1251]	eta 0:15:30 lr 0.000802	time 2.2029 (2.2113)	loss 4.0053 (3.7342)	grad_norm 0.9648 (1.2270)	
[2022-01-20 09:26:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][840/1251]	eta 0:15:09 lr 0.000801	time 1.7896 (2.2119)	loss 3.0054 (3.7340)	grad_norm 1.0820 (1.2262)	
[2022-01-20 09:26:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][850/1251]	eta 0:14:46 lr 0.000801	time 2.1869 (2.2114)	loss 3.8190 (3.7340)	grad_norm 1.2108 (1.2265)	
[2022-01-20 09:27:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][860/1251]	eta 0:14:23 lr 0.000801	time 1.9605 (2.2091)	loss 4.5359 (3.7353)	grad_norm 1.2174 (1.2267)	
[2022-01-20 09:27:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][870/1251]	eta 0:14:01 lr 0.000801	time 1.9480 (2.2080)	loss 2.6635 (3.7355)	grad_norm 1.2449 (1.2260)	
[2022-01-20 09:27:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][880/1251]	eta 0:13:38 lr 0.000801	time 1.7771 (2.2070)	loss 2.6828 (3.7374)	grad_norm 1.0362 (1.2262)	
[2022-01-20 09:28:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][890/1251]	eta 0:13:16 lr 0.000801	time 1.9172 (2.2062)	loss 3.9566 (3.7375)	grad_norm 1.2281 (1.2258)	
[2022-01-20 09:28:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][900/1251]	eta 0:12:54 lr 0.000801	time 1.5363 (2.2064)	loss 3.0788 (3.7383)	grad_norm 1.2568 (1.2254)	
[2022-01-20 09:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][910/1251]	eta 0:12:32 lr 0.000801	time 2.2914 (2.2075)	loss 4.1393 (3.7420)	grad_norm 1.2602 (1.2260)	
[2022-01-20 09:29:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][920/1251]	eta 0:12:11 lr 0.000801	time 2.8449 (2.2104)	loss 4.2041 (3.7421)	grad_norm 1.0767 (1.2250)	
[2022-01-20 09:29:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][930/1251]	eta 0:11:48 lr 0.000801	time 1.9140 (2.2085)	loss 4.4169 (3.7434)	grad_norm 1.1242 (1.2246)	
[2022-01-20 09:30:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][940/1251]	eta 0:11:26 lr 0.000801	time 1.6518 (2.2075)	loss 4.2402 (3.7422)	grad_norm 1.1167 (1.2247)	
[2022-01-20 09:30:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][950/1251]	eta 0:11:03 lr 0.000801	time 2.2354 (2.2047)	loss 3.7305 (3.7428)	grad_norm 1.3769 (1.2253)	
[2022-01-20 09:30:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][960/1251]	eta 0:10:41 lr 0.000801	time 2.2298 (2.2037)	loss 4.1139 (3.7432)	grad_norm 1.1616 (1.2244)	
[2022-01-20 09:31:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][970/1251]	eta 0:10:19 lr 0.000801	time 2.1873 (2.2031)	loss 3.4545 (3.7445)	grad_norm 0.9988 (1.2233)	
[2022-01-20 09:31:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][980/1251]	eta 0:09:57 lr 0.000801	time 2.1657 (2.2048)	loss 4.2373 (3.7468)	grad_norm 1.1568 (1.2229)	
[2022-01-20 09:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][990/1251]	eta 0:09:35 lr 0.000801	time 2.7083 (2.2066)	loss 4.0660 (3.7490)	grad_norm 1.1229 (1.2223)	
[2022-01-20 09:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1000/1251]	eta 0:09:13 lr 0.000801	time 2.2406 (2.2067)	loss 4.1262 (3.7495)	grad_norm 1.3446 (1.2225)	
[2022-01-20 09:32:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1010/1251]	eta 0:08:51 lr 0.000801	time 2.0405 (2.2066)	loss 4.5084 (3.7506)	grad_norm 1.2049 (1.2234)	
[2022-01-20 09:33:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1020/1251]	eta 0:08:29 lr 0.000801	time 1.8519 (2.2077)	loss 2.8823 (3.7511)	grad_norm 1.1562 (1.2229)	
[2022-01-20 09:33:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1030/1251]	eta 0:08:07 lr 0.000801	time 2.3627 (2.2076)	loss 4.4949 (3.7528)	grad_norm 1.2233 (1.2230)	
[2022-01-20 09:33:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1040/1251]	eta 0:07:45 lr 0.000801	time 2.5460 (2.2078)	loss 3.7325 (3.7519)	grad_norm 1.2570 (1.2229)	
[2022-01-20 09:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1050/1251]	eta 0:07:23 lr 0.000801	time 1.6334 (2.2050)	loss 3.5235 (3.7517)	grad_norm 1.4031 (1.2223)	
[2022-01-20 09:34:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1060/1251]	eta 0:07:00 lr 0.000801	time 1.9060 (2.2035)	loss 3.9688 (3.7542)	grad_norm 1.2670 (1.2223)	
[2022-01-20 09:34:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1070/1251]	eta 0:06:38 lr 0.000801	time 1.9326 (2.2019)	loss 3.4715 (3.7531)	grad_norm 1.1189 (1.2217)	
[2022-01-20 09:35:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1080/1251]	eta 0:06:16 lr 0.000801	time 2.2102 (2.2015)	loss 3.7041 (3.7545)	grad_norm 1.4054 (1.2220)	
[2022-01-20 09:35:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1090/1251]	eta 0:05:54 lr 0.000801	time 1.9413 (2.2000)	loss 4.4821 (3.7565)	grad_norm 1.2236 (1.2220)	
[2022-01-20 09:35:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1100/1251]	eta 0:05:32 lr 0.000801	time 1.8226 (2.1990)	loss 3.2145 (3.7552)	grad_norm 1.3311 (1.2221)	
[2022-01-20 09:36:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1110/1251]	eta 0:05:10 lr 0.000801	time 2.9943 (2.1997)	loss 4.1910 (3.7545)	grad_norm 1.1563 (1.2220)	
[2022-01-20 09:36:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1120/1251]	eta 0:04:48 lr 0.000801	time 1.8721 (2.2001)	loss 2.8559 (3.7520)	grad_norm 1.4023 (1.2219)	
[2022-01-20 09:37:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1130/1251]	eta 0:04:26 lr 0.000801	time 2.5160 (2.2005)	loss 3.7654 (3.7524)	grad_norm 1.2948 (1.2214)	
[2022-01-20 09:37:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1140/1251]	eta 0:04:04 lr 0.000801	time 1.8156 (2.2023)	loss 4.3675 (3.7529)	grad_norm 1.1261 (1.2204)	
[2022-01-20 09:37:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1150/1251]	eta 0:03:42 lr 0.000800	time 3.1712 (2.2043)	loss 4.2113 (3.7551)	grad_norm 1.1534 (1.2196)	
[2022-01-20 09:38:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1160/1251]	eta 0:03:20 lr 0.000800	time 1.4431 (2.2053)	loss 4.5351 (3.7559)	grad_norm 1.3204 (1.2196)	
[2022-01-20 09:38:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1170/1251]	eta 0:02:58 lr 0.000800	time 2.5338 (2.2059)	loss 4.4337 (3.7563)	grad_norm 1.3640 (1.2202)	
[2022-01-20 09:38:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1180/1251]	eta 0:02:36 lr 0.000800	time 1.6866 (2.2029)	loss 3.8442 (3.7563)	grad_norm 1.2682 (1.2204)	
[2022-01-20 09:39:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1190/1251]	eta 0:02:14 lr 0.000800	time 1.8696 (2.1999)	loss 4.8202 (3.7563)	grad_norm 1.4258 (1.2207)	
[2022-01-20 09:39:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1200/1251]	eta 0:01:52 lr 0.000800	time 2.5767 (2.1987)	loss 3.9632 (3.7554)	grad_norm 1.3845 (1.2216)	
[2022-01-20 09:39:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1210/1251]	eta 0:01:30 lr 0.000800	time 1.9329 (2.1974)	loss 3.2850 (3.7540)	grad_norm 1.0886 (1.2213)	
[2022-01-20 09:40:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1220/1251]	eta 0:01:08 lr 0.000800	time 1.7905 (2.1977)	loss 3.5441 (3.7550)	grad_norm 1.2063 (1.2208)	
[2022-01-20 09:40:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1230/1251]	eta 0:00:46 lr 0.000800	time 2.3917 (2.1985)	loss 2.7516 (3.7540)	grad_norm 1.1451 (1.2209)	
[2022-01-20 09:41:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1240/1251]	eta 0:00:24 lr 0.000800	time 2.4582 (2.1986)	loss 3.6544 (3.7536)	grad_norm 1.2454 (1.2208)	
[2022-01-20 09:41:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [88/300][1250/1251]	eta 0:00:02 lr 0.000800	time 1.1372 (2.1935)	loss 4.0375 (3.7538)	grad_norm 1.2909 (1.2203)	
[2022-01-20 09:41:16 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 88 training takes 0:45:44
[2022-01-20 09:41:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.365 (18.365)	Loss 1.1451 (1.1451)	Acc@1 73.633 (73.633)	Acc@5 91.699 (91.699)	
[2022-01-20 09:41:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.672 (3.249)	Loss 1.1875 (1.1349)	Acc@1 72.852 (73.544)	Acc@5 91.309 (92.028)	
[2022-01-20 09:42:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 2.234 (2.600)	Loss 1.1245 (1.1590)	Acc@1 74.609 (73.228)	Acc@5 91.699 (91.853)	
[2022-01-20 09:42:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.922 (2.282)	Loss 1.1594 (1.1705)	Acc@1 74.023 (72.886)	Acc@5 91.797 (91.718)	
[2022-01-20 09:42:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.022 (2.196)	Loss 1.2423 (1.1703)	Acc@1 71.289 (72.942)	Acc@5 91.504 (91.733)	
[2022-01-20 09:42:53 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 72.964 Acc@5 91.712
[2022-01-20 09:42:53 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.0%
[2022-01-20 09:42:53 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.19%
[2022-01-20 09:43:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][0/1251]	eta 7:27:14 lr 0.000800	time 21.4505 (21.4505)	loss 3.8520 (3.8520)	grad_norm 1.2463 (1.2463)	
[2022-01-20 09:43:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][10/1251]	eta 1:24:08 lr 0.000800	time 1.6143 (4.0681)	loss 4.3168 (3.4488)	grad_norm 1.0514 (1.1849)	
[2022-01-20 09:44:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][20/1251]	eta 1:05:25 lr 0.000800	time 1.3856 (3.1891)	loss 3.3608 (3.5921)	grad_norm 1.1063 (1.1998)	
[2022-01-20 09:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][30/1251]	eta 0:58:58 lr 0.000800	time 1.8684 (2.8977)	loss 3.5151 (3.6274)	grad_norm 1.0919 (1.2326)	
[2022-01-20 09:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][40/1251]	eta 0:55:00 lr 0.000800	time 3.4887 (2.7251)	loss 2.9181 (3.6061)	grad_norm 1.2245 (1.2589)	
[2022-01-20 09:45:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][50/1251]	eta 0:52:28 lr 0.000800	time 2.2018 (2.6214)	loss 4.2391 (3.6524)	grad_norm 1.3444 (1.2598)	
[2022-01-20 09:45:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][60/1251]	eta 0:50:26 lr 0.000800	time 1.2248 (2.5407)	loss 4.0702 (3.6409)	grad_norm 0.9867 (1.2445)	
[2022-01-20 09:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][70/1251]	eta 0:49:14 lr 0.000800	time 1.9685 (2.5020)	loss 3.7716 (3.6265)	grad_norm 1.0755 (1.2272)	
[2022-01-20 09:46:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][80/1251]	eta 0:48:28 lr 0.000800	time 2.8783 (2.4834)	loss 3.1180 (3.6258)	grad_norm 1.2533 (1.2202)	
[2022-01-20 09:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][90/1251]	eta 0:47:45 lr 0.000800	time 1.9449 (2.4685)	loss 2.7692 (3.6314)	grad_norm 1.1144 (1.2250)	
[2022-01-20 09:46:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][100/1251]	eta 0:46:43 lr 0.000800	time 1.7484 (2.4353)	loss 3.5248 (3.6252)	grad_norm 1.2296 (1.2249)	
[2022-01-20 09:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][110/1251]	eta 0:45:30 lr 0.000800	time 1.5922 (2.3932)	loss 3.3299 (3.6401)	grad_norm 1.2565 (1.2231)	
[2022-01-20 09:47:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][120/1251]	eta 0:44:41 lr 0.000800	time 2.5674 (2.3711)	loss 3.2280 (3.6268)	grad_norm 1.5692 (1.2264)	
[2022-01-20 09:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][130/1251]	eta 0:44:18 lr 0.000800	time 2.7995 (2.3712)	loss 3.1405 (3.6532)	grad_norm 1.5161 (1.2310)	
[2022-01-20 09:48:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][140/1251]	eta 0:43:41 lr 0.000800	time 2.5142 (2.3599)	loss 2.9546 (3.6528)	grad_norm 1.1706 (1.2245)	
[2022-01-20 09:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][150/1251]	eta 0:42:59 lr 0.000800	time 1.8147 (2.3425)	loss 3.9364 (3.6652)	grad_norm 1.1629 (1.2261)	
[2022-01-20 09:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][160/1251]	eta 0:42:26 lr 0.000800	time 2.7828 (2.3343)	loss 3.9146 (3.6850)	grad_norm 1.1557 (1.2249)	
[2022-01-20 09:49:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][170/1251]	eta 0:41:49 lr 0.000800	time 2.2781 (2.3212)	loss 3.8411 (3.6772)	grad_norm 1.1732 (1.2216)	
[2022-01-20 09:49:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][180/1251]	eta 0:41:10 lr 0.000800	time 2.1267 (2.3063)	loss 3.9000 (3.6805)	grad_norm 1.2674 (1.2168)	
[2022-01-20 09:50:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][190/1251]	eta 0:40:42 lr 0.000799	time 2.9839 (2.3022)	loss 3.8014 (3.6963)	grad_norm 1.2916 (1.2159)	
[2022-01-20 09:50:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][200/1251]	eta 0:40:18 lr 0.000799	time 2.7866 (2.3010)	loss 4.0646 (3.6949)	grad_norm 1.1727 (1.2173)	
[2022-01-20 09:50:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][210/1251]	eta 0:39:45 lr 0.000799	time 2.2077 (2.2912)	loss 4.1184 (3.7055)	grad_norm 1.0079 (1.2127)	
[2022-01-20 09:51:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][220/1251]	eta 0:39:15 lr 0.000799	time 1.8642 (2.2848)	loss 3.8817 (3.7061)	grad_norm 1.1633 (1.2157)	
[2022-01-20 09:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][230/1251]	eta 0:38:51 lr 0.000799	time 3.2470 (2.2838)	loss 4.7378 (3.7142)	grad_norm 1.2140 (1.2172)	
[2022-01-20 09:52:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][240/1251]	eta 0:38:24 lr 0.000799	time 1.9530 (2.2794)	loss 4.2558 (3.7099)	grad_norm 1.1032 (1.2171)	
[2022-01-20 09:52:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][250/1251]	eta 0:37:58 lr 0.000799	time 2.0439 (2.2758)	loss 3.6376 (3.7150)	grad_norm 1.0993 (1.2148)	
[2022-01-20 09:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][260/1251]	eta 0:37:37 lr 0.000799	time 1.9171 (2.2779)	loss 3.9704 (3.7265)	grad_norm 1.2103 (1.2184)	
[2022-01-20 09:53:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][270/1251]	eta 0:37:07 lr 0.000799	time 2.5430 (2.2709)	loss 2.4650 (3.7151)	grad_norm 1.2353 (1.2199)	
[2022-01-20 09:53:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][280/1251]	eta 0:36:38 lr 0.000799	time 1.9928 (2.2645)	loss 4.0942 (3.7131)	grad_norm 1.1698 (1.2209)	
[2022-01-20 09:53:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][290/1251]	eta 0:36:13 lr 0.000799	time 2.1482 (2.2620)	loss 3.9822 (3.7180)	grad_norm 1.1211 (1.2199)	
[2022-01-20 09:54:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][300/1251]	eta 0:35:49 lr 0.000799	time 2.1285 (2.2598)	loss 4.4854 (3.7261)	grad_norm 1.1970 (1.2178)	
[2022-01-20 09:54:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][310/1251]	eta 0:35:23 lr 0.000799	time 2.5312 (2.2561)	loss 3.9766 (3.7301)	grad_norm 1.0041 (1.2133)	
[2022-01-20 09:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][320/1251]	eta 0:34:59 lr 0.000799	time 1.7803 (2.2549)	loss 3.8525 (3.7283)	grad_norm 1.2379 (1.2133)	
[2022-01-20 09:55:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][330/1251]	eta 0:34:33 lr 0.000799	time 1.8167 (2.2511)	loss 4.2330 (3.7285)	grad_norm 1.2565 (1.2145)	
[2022-01-20 09:55:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][340/1251]	eta 0:34:06 lr 0.000799	time 2.0735 (2.2467)	loss 3.1117 (3.7242)	grad_norm 1.2234 (1.2157)	
[2022-01-20 09:56:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][350/1251]	eta 0:33:42 lr 0.000799	time 2.0737 (2.2452)	loss 3.5758 (3.7347)	grad_norm 1.1588 (1.2145)	
[2022-01-20 09:56:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][360/1251]	eta 0:33:17 lr 0.000799	time 1.8955 (2.2419)	loss 4.5365 (3.7373)	grad_norm 1.2384 (1.2139)	
[2022-01-20 09:56:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][370/1251]	eta 0:32:53 lr 0.000799	time 2.2458 (2.2400)	loss 3.8103 (3.7331)	grad_norm 1.3113 (1.2162)	
[2022-01-20 09:57:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][380/1251]	eta 0:32:31 lr 0.000799	time 2.8593 (2.2406)	loss 3.1511 (3.7289)	grad_norm 1.2486 (1.2177)	
[2022-01-20 09:57:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][390/1251]	eta 0:32:08 lr 0.000799	time 2.2431 (2.2400)	loss 3.7047 (3.7211)	grad_norm 1.5939 (1.2223)	
[2022-01-20 09:57:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][400/1251]	eta 0:31:44 lr 0.000799	time 1.9378 (2.2378)	loss 4.2562 (3.7229)	grad_norm 1.3310 (1.2242)	
[2022-01-20 09:58:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][410/1251]	eta 0:31:24 lr 0.000799	time 2.5880 (2.2404)	loss 4.2747 (3.7217)	grad_norm 1.4650 (1.2238)	
[2022-01-20 09:58:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][420/1251]	eta 0:31:01 lr 0.000799	time 2.4775 (2.2398)	loss 4.1504 (3.7246)	grad_norm 1.1152 (1.2233)	
[2022-01-20 09:58:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][430/1251]	eta 0:30:36 lr 0.000799	time 2.0159 (2.2364)	loss 4.2972 (3.7237)	grad_norm 1.2667 (1.2226)	
[2022-01-20 09:59:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][440/1251]	eta 0:30:09 lr 0.000799	time 1.7274 (2.2317)	loss 3.3993 (3.7247)	grad_norm 1.1241 (1.2221)	
[2022-01-20 09:59:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][450/1251]	eta 0:29:46 lr 0.000799	time 2.4759 (2.2303)	loss 4.5269 (3.7232)	grad_norm 1.0847 (1.2224)	
[2022-01-20 10:00:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][460/1251]	eta 0:29:24 lr 0.000799	time 2.2002 (2.2303)	loss 4.7318 (3.7284)	grad_norm 1.0824 (1.2240)	
[2022-01-20 10:00:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][470/1251]	eta 0:28:59 lr 0.000799	time 2.7801 (2.2269)	loss 3.7782 (3.7322)	grad_norm 1.3827 (1.2243)	
[2022-01-20 10:00:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][480/1251]	eta 0:28:34 lr 0.000799	time 1.7366 (2.2235)	loss 3.5335 (3.7258)	grad_norm 1.0357 (1.2229)	
[2022-01-20 10:01:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][490/1251]	eta 0:28:10 lr 0.000798	time 1.9936 (2.2212)	loss 2.8198 (3.7273)	grad_norm 1.4781 (1.2236)	
[2022-01-20 10:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][500/1251]	eta 0:27:48 lr 0.000798	time 2.2105 (2.2215)	loss 3.9571 (3.7253)	grad_norm 1.2316 (1.2262)	
[2022-01-20 10:01:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][510/1251]	eta 0:27:29 lr 0.000798	time 2.5276 (2.2260)	loss 3.2206 (3.7214)	grad_norm 1.1502 (1.2267)	
[2022-01-20 10:02:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][520/1251]	eta 0:27:07 lr 0.000798	time 2.0511 (2.2265)	loss 2.6860 (3.7202)	grad_norm 1.0595 (1.2252)	
[2022-01-20 10:02:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][530/1251]	eta 0:26:44 lr 0.000798	time 1.9806 (2.2250)	loss 3.3306 (3.7229)	grad_norm 1.0519 (1.2243)	
[2022-01-20 10:02:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][540/1251]	eta 0:26:21 lr 0.000798	time 1.8755 (2.2244)	loss 3.9467 (3.7282)	grad_norm 1.1469 (1.2249)	
[2022-01-20 10:03:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][550/1251]	eta 0:25:59 lr 0.000798	time 3.6084 (2.2251)	loss 3.9845 (3.7219)	grad_norm 1.0629 (1.2238)	
[2022-01-20 10:03:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][560/1251]	eta 0:25:36 lr 0.000798	time 2.0822 (2.2239)	loss 4.2924 (3.7244)	grad_norm 1.5006 (1.2251)	
[2022-01-20 10:04:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][570/1251]	eta 0:25:12 lr 0.000798	time 2.0018 (2.2212)	loss 3.9959 (3.7248)	grad_norm 1.5055 (1.2273)	
[2022-01-20 10:04:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][580/1251]	eta 0:24:49 lr 0.000798	time 1.7218 (2.2197)	loss 3.2810 (3.7223)	grad_norm 1.2066 (1.2259)	
[2022-01-20 10:04:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][590/1251]	eta 0:24:24 lr 0.000798	time 2.1880 (2.2155)	loss 3.3391 (3.7223)	grad_norm 1.2323 (1.2252)	
[2022-01-20 10:05:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][600/1251]	eta 0:24:03 lr 0.000798	time 2.2822 (2.2168)	loss 4.4651 (3.7260)	grad_norm 1.0751 (1.2259)	
[2022-01-20 10:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][610/1251]	eta 0:23:42 lr 0.000798	time 3.1640 (2.2186)	loss 4.1024 (3.7278)	grad_norm 1.3098 (1.2256)	
[2022-01-20 10:05:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][620/1251]	eta 0:23:19 lr 0.000798	time 2.0590 (2.2180)	loss 3.6400 (3.7267)	grad_norm 1.3005 (1.2258)	
[2022-01-20 10:06:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][630/1251]	eta 0:22:57 lr 0.000798	time 1.5635 (2.2180)	loss 3.8099 (3.7253)	grad_norm 1.0623 (1.2269)	
[2022-01-20 10:06:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][640/1251]	eta 0:22:35 lr 0.000798	time 2.1131 (2.2184)	loss 3.1960 (3.7222)	grad_norm 1.1284 (1.2259)	
[2022-01-20 10:06:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][650/1251]	eta 0:22:12 lr 0.000798	time 2.1656 (2.2168)	loss 3.1473 (3.7243)	grad_norm 1.1851 (1.2259)	
[2022-01-20 10:07:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][660/1251]	eta 0:21:48 lr 0.000798	time 1.6021 (2.2143)	loss 4.3071 (3.7228)	grad_norm 1.0220 (1.2248)	
[2022-01-20 10:07:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][670/1251]	eta 0:21:26 lr 0.000798	time 1.6290 (2.2137)	loss 3.9116 (3.7282)	grad_norm 1.0464 (1.2237)	
[2022-01-20 10:08:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][680/1251]	eta 0:21:04 lr 0.000798	time 2.2401 (2.2144)	loss 3.7939 (3.7332)	grad_norm 1.4441 (1.2252)	
[2022-01-20 10:08:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][690/1251]	eta 0:20:42 lr 0.000798	time 1.9183 (2.2154)	loss 2.9870 (3.7354)	grad_norm 1.2321 (1.2261)	
[2022-01-20 10:08:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][700/1251]	eta 0:20:20 lr 0.000798	time 1.7212 (2.2147)	loss 4.2389 (3.7386)	grad_norm 1.2989 (1.2267)	
[2022-01-20 10:09:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][710/1251]	eta 0:19:56 lr 0.000798	time 2.0878 (2.2121)	loss 3.3643 (3.7408)	grad_norm 1.1860 (1.2265)	
[2022-01-20 10:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][720/1251]	eta 0:19:33 lr 0.000798	time 2.2132 (2.2091)	loss 4.5320 (3.7432)	grad_norm 1.3737 (1.2267)	
[2022-01-20 10:09:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][730/1251]	eta 0:19:11 lr 0.000798	time 2.8050 (2.2095)	loss 4.3523 (3.7448)	grad_norm 1.3320 (1.2267)	
[2022-01-20 10:10:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][740/1251]	eta 0:18:48 lr 0.000798	time 1.9297 (2.2078)	loss 4.2827 (3.7448)	grad_norm 1.1766 (1.2275)	
[2022-01-20 10:10:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][750/1251]	eta 0:18:25 lr 0.000798	time 2.3639 (2.2071)	loss 2.9623 (3.7391)	grad_norm 1.3255 (1.2282)	
[2022-01-20 10:10:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][760/1251]	eta 0:18:03 lr 0.000798	time 2.0006 (2.2068)	loss 3.9377 (3.7428)	grad_norm 1.2145 (1.2275)	
[2022-01-20 10:11:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][770/1251]	eta 0:17:41 lr 0.000798	time 2.2554 (2.2072)	loss 3.8297 (3.7460)	grad_norm 1.1192 (1.2270)	
[2022-01-20 10:11:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][780/1251]	eta 0:17:18 lr 0.000798	time 2.0077 (2.2058)	loss 4.1617 (3.7466)	grad_norm 1.2031 (1.2274)	
[2022-01-20 10:11:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][790/1251]	eta 0:16:56 lr 0.000797	time 2.5116 (2.2054)	loss 4.7056 (3.7469)	grad_norm 1.1260 (1.2272)	
[2022-01-20 10:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][800/1251]	eta 0:16:35 lr 0.000797	time 2.1671 (2.2067)	loss 3.8379 (3.7456)	grad_norm 0.9982 (1.2260)	
[2022-01-20 10:12:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][810/1251]	eta 0:16:13 lr 0.000797	time 2.5612 (2.2066)	loss 3.6384 (3.7484)	grad_norm 1.0887 (1.2256)	
[2022-01-20 10:13:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][820/1251]	eta 0:15:50 lr 0.000797	time 2.1243 (2.2050)	loss 3.9120 (3.7490)	grad_norm 1.3342 (1.2257)	
[2022-01-20 10:13:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][830/1251]	eta 0:15:28 lr 0.000797	time 3.4416 (2.2059)	loss 3.9389 (3.7513)	grad_norm 1.1440 (1.2254)	
[2022-01-20 10:13:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][840/1251]	eta 0:15:07 lr 0.000797	time 1.9230 (2.2073)	loss 2.5795 (3.7475)	grad_norm 1.0374 (1.2241)	
[2022-01-20 10:14:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][850/1251]	eta 0:14:45 lr 0.000797	time 2.7930 (2.2084)	loss 3.7887 (3.7499)	grad_norm 1.3693 (1.2239)	
[2022-01-20 10:14:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][860/1251]	eta 0:14:22 lr 0.000797	time 2.1523 (2.2063)	loss 2.7320 (3.7468)	grad_norm 0.9942 (1.2238)	
[2022-01-20 10:14:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][870/1251]	eta 0:13:59 lr 0.000797	time 2.1186 (2.2042)	loss 3.9163 (3.7493)	grad_norm 1.2254 (1.2229)	
[2022-01-20 10:15:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][880/1251]	eta 0:13:38 lr 0.000797	time 2.4261 (2.2052)	loss 3.3161 (3.7467)	grad_norm 1.1516 (1.2222)	
[2022-01-20 10:15:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][890/1251]	eta 0:13:16 lr 0.000797	time 2.9812 (2.2059)	loss 3.9462 (3.7476)	grad_norm 1.1017 (1.2212)	
[2022-01-20 10:16:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][900/1251]	eta 0:12:53 lr 0.000797	time 1.8320 (2.2051)	loss 3.6224 (3.7506)	grad_norm 1.1087 (1.2216)	
[2022-01-20 10:16:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][910/1251]	eta 0:12:31 lr 0.000797	time 1.9443 (2.2040)	loss 4.2402 (3.7521)	grad_norm 1.2876 (1.2211)	
[2022-01-20 10:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][920/1251]	eta 0:12:09 lr 0.000797	time 1.5433 (2.2027)	loss 4.5618 (3.7549)	grad_norm 1.1861 (1.2212)	
[2022-01-20 10:17:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][930/1251]	eta 0:11:46 lr 0.000797	time 2.8918 (2.2020)	loss 4.1151 (3.7559)	grad_norm 1.1489 (1.2208)	
[2022-01-20 10:17:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][940/1251]	eta 0:11:24 lr 0.000797	time 1.9149 (2.2015)	loss 4.1737 (3.7577)	grad_norm 1.3059 (1.2214)	
[2022-01-20 10:17:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][950/1251]	eta 0:11:02 lr 0.000797	time 2.1898 (2.2025)	loss 2.4359 (3.7566)	grad_norm 1.3269 (1.2209)	
[2022-01-20 10:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][960/1251]	eta 0:10:40 lr 0.000797	time 2.1030 (2.2026)	loss 3.8241 (3.7558)	grad_norm 1.0886 (1.2203)	
[2022-01-20 10:18:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][970/1251]	eta 0:10:18 lr 0.000797	time 1.8002 (2.2018)	loss 3.0339 (3.7550)	grad_norm 1.2254 (1.2200)	
[2022-01-20 10:18:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][980/1251]	eta 0:09:56 lr 0.000797	time 1.6791 (2.2006)	loss 3.5175 (3.7554)	grad_norm 1.1769 (1.2194)	
[2022-01-20 10:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][990/1251]	eta 0:09:33 lr 0.000797	time 2.2593 (2.1992)	loss 4.2401 (3.7557)	grad_norm 0.9497 (1.2190)	
[2022-01-20 10:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1000/1251]	eta 0:09:11 lr 0.000797	time 2.0197 (2.1982)	loss 3.3521 (3.7526)	grad_norm 1.1043 (1.2199)	
[2022-01-20 10:19:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1010/1251]	eta 0:08:49 lr 0.000797	time 1.7026 (2.1975)	loss 2.8699 (3.7543)	grad_norm 1.1762 (1.2200)	
[2022-01-20 10:20:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1020/1251]	eta 0:08:27 lr 0.000797	time 2.1495 (2.1988)	loss 4.7233 (3.7564)	grad_norm 1.1290 (1.2191)	
[2022-01-20 10:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1030/1251]	eta 0:08:06 lr 0.000797	time 3.0362 (2.2007)	loss 4.0588 (3.7556)	grad_norm 1.5323 (1.2193)	
[2022-01-20 10:21:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1040/1251]	eta 0:07:44 lr 0.000797	time 2.0952 (2.2003)	loss 3.3805 (3.7542)	grad_norm 1.2817 (1.2192)	
[2022-01-20 10:21:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1050/1251]	eta 0:07:21 lr 0.000797	time 2.0577 (2.1988)	loss 3.5900 (3.7545)	grad_norm 1.2453 (1.2188)	
[2022-01-20 10:21:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1060/1251]	eta 0:06:59 lr 0.000797	time 2.1990 (2.1985)	loss 3.3455 (3.7550)	grad_norm 1.3585 (1.2189)	
[2022-01-20 10:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1070/1251]	eta 0:06:38 lr 0.000797	time 3.2628 (2.1997)	loss 3.8814 (3.7561)	grad_norm 1.3006 (1.2199)	
[2022-01-20 10:22:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1080/1251]	eta 0:06:15 lr 0.000797	time 1.8724 (2.1984)	loss 4.2781 (3.7555)	grad_norm 1.2928 (1.2203)	
[2022-01-20 10:22:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1090/1251]	eta 0:05:53 lr 0.000796	time 1.9471 (2.1974)	loss 4.0342 (3.7559)	grad_norm 1.6806 (1.2210)	
[2022-01-20 10:23:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1100/1251]	eta 0:05:31 lr 0.000796	time 2.2575 (2.1981)	loss 4.1239 (3.7570)	grad_norm 1.0753 (1.2220)	
[2022-01-20 10:23:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1110/1251]	eta 0:05:09 lr 0.000796	time 2.2908 (2.1983)	loss 3.5157 (3.7568)	grad_norm 1.1261 (1.2213)	
[2022-01-20 10:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1120/1251]	eta 0:04:47 lr 0.000796	time 2.2097 (2.1978)	loss 2.9478 (3.7559)	grad_norm 1.4092 (1.2211)	
[2022-01-20 10:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1130/1251]	eta 0:04:25 lr 0.000796	time 1.6083 (2.1966)	loss 4.4777 (3.7553)	grad_norm 1.2314 (1.2208)	
[2022-01-20 10:24:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1140/1251]	eta 0:04:03 lr 0.000796	time 2.8571 (2.1974)	loss 3.1768 (3.7537)	grad_norm 1.0752 (1.2202)	
[2022-01-20 10:25:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1150/1251]	eta 0:03:41 lr 0.000796	time 1.7980 (2.1956)	loss 3.5923 (3.7504)	grad_norm 1.1642 (1.2201)	
[2022-01-20 10:25:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1160/1251]	eta 0:03:19 lr 0.000796	time 1.8387 (2.1951)	loss 4.3586 (3.7512)	grad_norm 1.2835 (1.2203)	
[2022-01-20 10:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1170/1251]	eta 0:02:57 lr 0.000796	time 1.5449 (2.1942)	loss 3.6442 (3.7511)	grad_norm 0.9902 (1.2199)	
[2022-01-20 10:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1180/1251]	eta 0:02:35 lr 0.000796	time 2.4582 (2.1932)	loss 3.8384 (3.7509)	grad_norm 1.1357 (1.2202)	
[2022-01-20 10:26:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1190/1251]	eta 0:02:13 lr 0.000796	time 2.2025 (2.1925)	loss 3.8605 (3.7491)	grad_norm 1.1938 (1.2201)	
[2022-01-20 10:26:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1200/1251]	eta 0:01:51 lr 0.000796	time 2.0329 (2.1918)	loss 4.0373 (3.7479)	grad_norm 1.2376 (1.2198)	
[2022-01-20 10:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1210/1251]	eta 0:01:29 lr 0.000796	time 1.5656 (2.1925)	loss 3.9570 (3.7483)	grad_norm 1.2187 (1.2194)	
[2022-01-20 10:27:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1220/1251]	eta 0:01:07 lr 0.000796	time 2.4770 (2.1927)	loss 3.9108 (3.7487)	grad_norm 1.2410 (1.2195)	
[2022-01-20 10:27:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1230/1251]	eta 0:00:46 lr 0.000796	time 1.6754 (2.1912)	loss 4.0872 (3.7466)	grad_norm 1.1626 (1.2193)	
[2022-01-20 10:28:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1240/1251]	eta 0:00:24 lr 0.000796	time 1.7054 (2.1900)	loss 3.9715 (3.7453)	grad_norm 1.1581 (1.2193)	
[2022-01-20 10:28:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [89/300][1250/1251]	eta 0:00:02 lr 0.000796	time 1.1859 (2.1844)	loss 3.7164 (3.7448)	grad_norm 1.1445 (1.2185)	
[2022-01-20 10:28:26 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 89 training takes 0:45:33
[2022-01-20 10:28:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.228 (18.228)	Loss 1.1066 (1.1066)	Acc@1 74.219 (74.219)	Acc@5 93.164 (93.164)	
[2022-01-20 10:29:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.284 (3.552)	Loss 1.1745 (1.1445)	Acc@1 72.949 (73.331)	Acc@5 91.699 (92.232)	
[2022-01-20 10:29:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.657 (2.635)	Loss 1.1516 (1.1529)	Acc@1 72.363 (73.093)	Acc@5 91.797 (91.983)	
[2022-01-20 10:29:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.990 (2.365)	Loss 1.2064 (1.1561)	Acc@1 71.777 (73.157)	Acc@5 90.625 (91.866)	
[2022-01-20 10:29:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.975 (2.173)	Loss 1.1906 (1.1584)	Acc@1 72.363 (73.090)	Acc@5 91.504 (91.830)	
[2022-01-20 10:30:02 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.040 Acc@5 91.902
[2022-01-20 10:30:02 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.0%
[2022-01-20 10:30:02 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.19%
[2022-01-20 10:30:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][0/1251]	eta 7:31:27 lr 0.000796	time 21.6525 (21.6525)	loss 3.9997 (3.9997)	grad_norm 1.8258 (1.8258)	
[2022-01-20 10:30:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][10/1251]	eta 1:23:25 lr 0.000796	time 2.2030 (4.0332)	loss 2.8382 (3.8304)	grad_norm 1.0503 (1.3113)	
[2022-01-20 10:31:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][20/1251]	eta 1:04:29 lr 0.000796	time 1.4152 (3.1432)	loss 4.3396 (3.8790)	grad_norm 1.2760 (1.3127)	
[2022-01-20 10:31:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][30/1251]	eta 0:57:37 lr 0.000796	time 1.8566 (2.8317)	loss 4.4523 (3.7895)	grad_norm 1.4118 (1.2886)	
[2022-01-20 10:31:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][40/1251]	eta 0:54:57 lr 0.000796	time 3.3689 (2.7230)	loss 3.9617 (3.7696)	grad_norm 1.3415 (1.2690)	
[2022-01-20 10:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][50/1251]	eta 0:53:14 lr 0.000796	time 2.4621 (2.6596)	loss 3.4849 (3.7567)	grad_norm 1.2386 (1.2548)	
[2022-01-20 10:32:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][60/1251]	eta 0:51:03 lr 0.000796	time 1.9749 (2.5718)	loss 2.6647 (3.7423)	grad_norm 1.2659 (1.2426)	
[2022-01-20 10:32:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][70/1251]	eta 0:49:04 lr 0.000796	time 1.8949 (2.4935)	loss 4.3048 (3.7733)	grad_norm 1.1164 (1.2396)	
[2022-01-20 10:33:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][80/1251]	eta 0:47:34 lr 0.000796	time 2.7564 (2.4378)	loss 3.8650 (3.7620)	grad_norm 1.1620 (1.2322)	
[2022-01-20 10:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][90/1251]	eta 0:46:17 lr 0.000796	time 1.9003 (2.3922)	loss 4.4884 (3.7565)	grad_norm 1.1512 (1.2310)	
[2022-01-20 10:34:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][100/1251]	eta 0:45:23 lr 0.000796	time 1.6462 (2.3662)	loss 4.2583 (3.7732)	grad_norm 1.2523 (1.2346)	
[2022-01-20 10:34:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][110/1251]	eta 0:45:02 lr 0.000796	time 1.8637 (2.3687)	loss 4.1829 (3.7446)	grad_norm 1.1474 (1.2292)	
[2022-01-20 10:34:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][120/1251]	eta 0:44:34 lr 0.000796	time 3.4503 (2.3645)	loss 2.5656 (3.7555)	grad_norm 1.3515 (1.2301)	
[2022-01-20 10:35:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][130/1251]	eta 0:43:54 lr 0.000796	time 1.9375 (2.3504)	loss 3.4928 (3.7401)	grad_norm 1.3111 (1.2268)	
[2022-01-20 10:35:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][140/1251]	eta 0:43:17 lr 0.000795	time 1.6414 (2.3379)	loss 3.9981 (3.7329)	grad_norm 1.1156 (1.2232)	
[2022-01-20 10:35:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][150/1251]	eta 0:42:40 lr 0.000795	time 2.5388 (2.3258)	loss 3.2290 (3.7104)	grad_norm 1.3457 (1.2197)	
[2022-01-20 10:36:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][160/1251]	eta 0:42:17 lr 0.000795	time 3.4403 (2.3256)	loss 3.5643 (3.7228)	grad_norm 1.0062 (1.2174)	
[2022-01-20 10:36:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][170/1251]	eta 0:41:38 lr 0.000795	time 1.9648 (2.3115)	loss 2.9417 (3.7329)	grad_norm 1.1977 (1.2161)	
[2022-01-20 10:36:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][180/1251]	eta 0:40:59 lr 0.000795	time 1.5996 (2.2963)	loss 3.2242 (3.7193)	grad_norm 1.1220 (1.2157)	
[2022-01-20 10:37:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][190/1251]	eta 0:40:27 lr 0.000795	time 2.3075 (2.2879)	loss 4.1177 (3.7004)	grad_norm 1.2795 (1.2138)	
[2022-01-20 10:37:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][200/1251]	eta 0:40:04 lr 0.000795	time 3.6483 (2.2874)	loss 4.1071 (3.7013)	grad_norm 1.0877 (1.2128)	
[2022-01-20 10:38:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][210/1251]	eta 0:39:30 lr 0.000795	time 2.1762 (2.2768)	loss 3.8951 (3.7026)	grad_norm 1.2604 (1.2144)	
[2022-01-20 10:38:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][220/1251]	eta 0:38:59 lr 0.000795	time 1.7968 (2.2687)	loss 4.0911 (3.7067)	grad_norm 1.0703 (1.2130)	
[2022-01-20 10:38:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][230/1251]	eta 0:38:35 lr 0.000795	time 2.4430 (2.2676)	loss 3.7881 (3.7037)	grad_norm 1.2213 (1.2151)	
[2022-01-20 10:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][240/1251]	eta 0:38:17 lr 0.000795	time 3.7020 (2.2724)	loss 4.3292 (3.7079)	grad_norm 1.4003 (1.2196)	
[2022-01-20 10:39:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][250/1251]	eta 0:37:55 lr 0.000795	time 2.2208 (2.2729)	loss 4.2224 (3.7061)	grad_norm 1.4629 (1.2238)	
[2022-01-20 10:39:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][260/1251]	eta 0:37:29 lr 0.000795	time 2.2154 (2.2704)	loss 3.9194 (3.7076)	grad_norm 1.1538 (1.2278)	
[2022-01-20 10:40:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][270/1251]	eta 0:36:57 lr 0.000795	time 1.9758 (2.2606)	loss 4.2431 (3.7089)	grad_norm 1.1685 (1.2270)	
[2022-01-20 10:40:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][280/1251]	eta 0:36:34 lr 0.000795	time 3.5196 (2.2598)	loss 3.3426 (3.7027)	grad_norm 1.1049 (1.2253)	
[2022-01-20 10:40:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][290/1251]	eta 0:36:07 lr 0.000795	time 1.9895 (2.2560)	loss 4.2306 (3.7154)	grad_norm 1.1816 (1.2251)	
[2022-01-20 10:41:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][300/1251]	eta 0:35:44 lr 0.000795	time 2.1292 (2.2547)	loss 4.4054 (3.7162)	grad_norm 1.2546 (1.2265)	
[2022-01-20 10:41:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][310/1251]	eta 0:35:16 lr 0.000795	time 1.6909 (2.2494)	loss 4.5146 (3.7251)	grad_norm 1.2234 (1.2291)	
[2022-01-20 10:42:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][320/1251]	eta 0:34:56 lr 0.000795	time 3.3543 (2.2520)	loss 4.0665 (3.7305)	grad_norm 1.1459 (1.2278)	
[2022-01-20 10:42:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][330/1251]	eta 0:34:26 lr 0.000795	time 1.7285 (2.2442)	loss 3.9054 (3.7349)	grad_norm 1.1594 (1.2286)	
[2022-01-20 10:42:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][340/1251]	eta 0:33:59 lr 0.000795	time 1.9211 (2.2389)	loss 3.2717 (3.7321)	grad_norm 1.1187 (1.2275)	
[2022-01-20 10:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][350/1251]	eta 0:33:36 lr 0.000795	time 2.8605 (2.2380)	loss 4.1464 (3.7267)	grad_norm 1.1099 (1.2266)	
[2022-01-20 10:43:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][360/1251]	eta 0:33:13 lr 0.000795	time 2.0928 (2.2378)	loss 4.2780 (3.7267)	grad_norm 1.0966 (1.2245)	
[2022-01-20 10:43:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][370/1251]	eta 0:32:53 lr 0.000795	time 2.4789 (2.2396)	loss 3.1379 (3.7240)	grad_norm 1.3615 (1.2247)	
[2022-01-20 10:44:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][380/1251]	eta 0:32:28 lr 0.000795	time 2.1952 (2.2369)	loss 3.3668 (3.7298)	grad_norm 1.1552 (1.2263)	
[2022-01-20 10:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][390/1251]	eta 0:32:06 lr 0.000795	time 2.4744 (2.2375)	loss 3.1688 (3.7311)	grad_norm 1.1929 (1.2253)	
[2022-01-20 10:44:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][400/1251]	eta 0:31:43 lr 0.000795	time 2.3202 (2.2363)	loss 2.8736 (3.7328)	grad_norm 1.3969 (1.2266)	
[2022-01-20 10:45:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][410/1251]	eta 0:31:19 lr 0.000795	time 2.3201 (2.2351)	loss 4.1137 (3.7342)	grad_norm 1.2306 (1.2267)	
[2022-01-20 10:45:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][420/1251]	eta 0:30:56 lr 0.000795	time 2.5334 (2.2343)	loss 3.7806 (3.7348)	grad_norm 1.2853 (1.2274)	
[2022-01-20 10:46:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][430/1251]	eta 0:30:33 lr 0.000795	time 1.8928 (2.2330)	loss 4.3116 (3.7327)	grad_norm 1.1452 (1.2260)	
[2022-01-20 10:46:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][440/1251]	eta 0:30:11 lr 0.000794	time 2.1280 (2.2340)	loss 3.5829 (3.7369)	grad_norm 1.3569 (1.2279)	
[2022-01-20 10:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][450/1251]	eta 0:29:51 lr 0.000794	time 2.9197 (2.2360)	loss 3.6654 (3.7428)	grad_norm 1.1872 (1.2280)	
[2022-01-20 10:47:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][460/1251]	eta 0:29:27 lr 0.000794	time 1.9043 (2.2339)	loss 4.2931 (3.7450)	grad_norm 1.2404 (1.2268)	
[2022-01-20 10:47:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][470/1251]	eta 0:29:01 lr 0.000794	time 2.1053 (2.2302)	loss 3.9434 (3.7459)	grad_norm 1.2749 (1.2251)	
[2022-01-20 10:47:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][480/1251]	eta 0:28:37 lr 0.000794	time 2.3673 (2.2277)	loss 2.6437 (3.7479)	grad_norm 1.3228 (1.2245)	
[2022-01-20 10:48:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][490/1251]	eta 0:28:13 lr 0.000794	time 1.8673 (2.2259)	loss 3.1624 (3.7459)	grad_norm 1.0475 (1.2230)	
[2022-01-20 10:48:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][500/1251]	eta 0:27:49 lr 0.000794	time 2.3030 (2.2235)	loss 3.6895 (3.7376)	grad_norm 1.0699 (1.2215)	
[2022-01-20 10:48:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][510/1251]	eta 0:27:26 lr 0.000794	time 1.8393 (2.2224)	loss 3.6248 (3.7414)	grad_norm 1.3886 (1.2222)	
[2022-01-20 10:49:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][520/1251]	eta 0:27:03 lr 0.000794	time 2.2821 (2.2204)	loss 4.2466 (3.7424)	grad_norm 1.0363 (1.2228)	
[2022-01-20 10:49:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][530/1251]	eta 0:26:41 lr 0.000794	time 2.5461 (2.2209)	loss 4.0420 (3.7425)	grad_norm 1.0842 (1.2209)	
[2022-01-20 10:50:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][540/1251]	eta 0:26:19 lr 0.000794	time 2.9630 (2.2208)	loss 3.7916 (3.7409)	grad_norm 1.0020 (1.2208)	
[2022-01-20 10:50:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][550/1251]	eta 0:25:56 lr 0.000794	time 1.8270 (2.2207)	loss 4.4869 (3.7351)	grad_norm 1.1110 (1.2209)	
[2022-01-20 10:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][560/1251]	eta 0:25:35 lr 0.000794	time 1.5948 (2.2225)	loss 4.1402 (3.7319)	grad_norm 1.3859 (1.2215)	
[2022-01-20 10:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][570/1251]	eta 0:25:12 lr 0.000794	time 2.3030 (2.2212)	loss 3.7855 (3.7294)	grad_norm 1.5363 (1.2241)	
[2022-01-20 10:51:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][580/1251]	eta 0:24:49 lr 0.000794	time 3.0185 (2.2201)	loss 3.0568 (3.7299)	grad_norm 1.3634 (1.2241)	
[2022-01-20 10:51:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][590/1251]	eta 0:24:25 lr 0.000794	time 1.6390 (2.2167)	loss 3.5443 (3.7306)	grad_norm 1.3245 (1.2239)	
[2022-01-20 10:52:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][600/1251]	eta 0:24:01 lr 0.000794	time 2.2213 (2.2150)	loss 3.6684 (3.7321)	grad_norm 1.0603 (1.2245)	
[2022-01-20 10:52:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][610/1251]	eta 0:23:40 lr 0.000794	time 2.8181 (2.2157)	loss 4.4762 (3.7346)	grad_norm 1.0502 (1.2239)	
[2022-01-20 10:52:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][620/1251]	eta 0:23:17 lr 0.000794	time 3.0198 (2.2154)	loss 4.5312 (3.7406)	grad_norm 1.3388 (1.2231)	
[2022-01-20 10:53:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][630/1251]	eta 0:22:55 lr 0.000794	time 2.2201 (2.2153)	loss 3.6207 (3.7390)	grad_norm 1.2503 (1.2231)	
[2022-01-20 10:53:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][640/1251]	eta 0:22:32 lr 0.000794	time 1.8709 (2.2141)	loss 2.4133 (3.7356)	grad_norm 1.1073 (1.2234)	
[2022-01-20 10:54:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][650/1251]	eta 0:22:10 lr 0.000794	time 2.8562 (2.2130)	loss 3.5639 (3.7382)	grad_norm 1.2283 (1.2234)	
[2022-01-20 10:54:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][660/1251]	eta 0:21:48 lr 0.000794	time 2.8139 (2.2140)	loss 4.2186 (3.7405)	grad_norm 1.2873 (1.2242)	
[2022-01-20 10:54:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][670/1251]	eta 0:21:27 lr 0.000794	time 2.2302 (2.2156)	loss 3.3723 (3.7403)	grad_norm 1.1932 (1.2243)	
[2022-01-20 10:55:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][680/1251]	eta 0:21:05 lr 0.000794	time 1.6172 (2.2156)	loss 2.5278 (3.7380)	grad_norm 1.1618 (1.2241)	
[2022-01-20 10:55:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][690/1251]	eta 0:20:42 lr 0.000794	time 2.9943 (2.2142)	loss 4.1058 (3.7368)	grad_norm 1.3306 (1.2235)	
[2022-01-20 10:55:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][700/1251]	eta 0:20:18 lr 0.000794	time 1.9860 (2.2121)	loss 4.2574 (3.7370)	grad_norm 1.2355 (1.2226)	
[2022-01-20 10:56:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][710/1251]	eta 0:19:55 lr 0.000794	time 2.1184 (2.2101)	loss 4.2920 (3.7399)	grad_norm 1.2644 (1.2218)	
[2022-01-20 10:56:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][720/1251]	eta 0:19:33 lr 0.000794	time 2.0670 (2.2092)	loss 3.9602 (3.7395)	grad_norm 1.2864 (1.2217)	
[2022-01-20 10:56:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][730/1251]	eta 0:19:11 lr 0.000794	time 2.6199 (2.2093)	loss 4.4236 (3.7389)	grad_norm 1.2454 (1.2227)	
[2022-01-20 10:57:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][740/1251]	eta 0:18:47 lr 0.000793	time 1.8952 (2.2067)	loss 4.2432 (3.7416)	grad_norm 1.0223 (1.2220)	
[2022-01-20 10:57:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][750/1251]	eta 0:18:25 lr 0.000793	time 2.2470 (2.2063)	loss 3.9869 (3.7417)	grad_norm 1.2525 (1.2223)	
[2022-01-20 10:58:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][760/1251]	eta 0:18:02 lr 0.000793	time 1.6193 (2.2047)	loss 3.7974 (3.7378)	grad_norm 1.4980 (1.2237)	
[2022-01-20 10:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][770/1251]	eta 0:17:40 lr 0.000793	time 2.4278 (2.2045)	loss 3.2877 (3.7382)	grad_norm 1.4081 (1.2234)	
[2022-01-20 10:58:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][780/1251]	eta 0:17:18 lr 0.000793	time 1.4911 (2.2039)	loss 4.1835 (3.7368)	grad_norm 1.1192 (1.2231)	
[2022-01-20 10:59:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][790/1251]	eta 0:16:56 lr 0.000793	time 1.8175 (2.2054)	loss 4.6390 (3.7352)	grad_norm 1.1000 (1.2226)	
[2022-01-20 10:59:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][800/1251]	eta 0:16:34 lr 0.000793	time 1.8698 (2.2054)	loss 4.3885 (3.7372)	grad_norm 1.1045 (1.2223)	
[2022-01-20 10:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][810/1251]	eta 0:16:13 lr 0.000793	time 2.1803 (2.2079)	loss 4.0322 (3.7376)	grad_norm 1.3341 (1.2222)	
[2022-01-20 11:00:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][820/1251]	eta 0:15:51 lr 0.000793	time 2.0272 (2.2084)	loss 2.9374 (3.7387)	grad_norm 1.4722 (1.2238)	
[2022-01-20 11:00:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][830/1251]	eta 0:15:29 lr 0.000793	time 1.9197 (2.2085)	loss 4.5296 (3.7401)	grad_norm 1.2351 (1.2242)	
[2022-01-20 11:01:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][840/1251]	eta 0:15:08 lr 0.000793	time 1.9614 (2.2094)	loss 3.8764 (3.7427)	grad_norm 1.2453 (1.2239)	
[2022-01-20 11:01:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][850/1251]	eta 0:14:45 lr 0.000793	time 2.2178 (2.2083)	loss 3.6654 (3.7426)	grad_norm 1.4888 (1.2242)	
[2022-01-20 11:01:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][860/1251]	eta 0:14:23 lr 0.000793	time 1.6701 (2.2080)	loss 3.1316 (3.7393)	grad_norm 1.0331 (1.2247)	
[2022-01-20 11:02:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][870/1251]	eta 0:14:01 lr 0.000793	time 3.0853 (2.2076)	loss 3.8363 (3.7383)	grad_norm 1.0990 (1.2239)	
[2022-01-20 11:02:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][880/1251]	eta 0:13:38 lr 0.000793	time 1.5876 (2.2071)	loss 4.2484 (3.7402)	grad_norm 1.4151 (1.2240)	
[2022-01-20 11:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][890/1251]	eta 0:13:15 lr 0.000793	time 1.9198 (2.2049)	loss 3.0938 (3.7396)	grad_norm 1.1361 (1.2231)	
[2022-01-20 11:03:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][900/1251]	eta 0:12:54 lr 0.000793	time 1.8794 (2.2056)	loss 3.7055 (3.7410)	grad_norm 1.1061 (1.2235)	
[2022-01-20 11:03:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][910/1251]	eta 0:12:31 lr 0.000793	time 2.0530 (2.2040)	loss 3.8093 (3.7404)	grad_norm 1.3628 (1.2257)	
[2022-01-20 11:03:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][920/1251]	eta 0:12:09 lr 0.000793	time 1.8654 (2.2029)	loss 4.1779 (3.7395)	grad_norm 1.2280 (1.2253)	
[2022-01-20 11:04:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][930/1251]	eta 0:11:46 lr 0.000793	time 2.1100 (2.2018)	loss 3.8666 (3.7401)	grad_norm 1.1019 (1.2255)	
[2022-01-20 11:04:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][940/1251]	eta 0:11:24 lr 0.000793	time 2.0894 (2.2015)	loss 4.4199 (3.7418)	grad_norm 1.2858 (1.2265)	
[2022-01-20 11:04:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][950/1251]	eta 0:11:02 lr 0.000793	time 2.3007 (2.2008)	loss 3.2521 (3.7429)	grad_norm 1.1837 (1.2263)	
[2022-01-20 11:05:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][960/1251]	eta 0:10:40 lr 0.000793	time 2.1469 (2.2013)	loss 2.6347 (3.7408)	grad_norm 1.1168 (1.2256)	
[2022-01-20 11:05:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][970/1251]	eta 0:10:18 lr 0.000793	time 1.6038 (2.2012)	loss 4.2959 (3.7423)	grad_norm 1.3582 (1.2252)	
[2022-01-20 11:06:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][980/1251]	eta 0:09:56 lr 0.000793	time 2.4808 (2.2028)	loss 2.7518 (3.7408)	grad_norm 1.3750 (1.2255)	
[2022-01-20 11:06:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][990/1251]	eta 0:09:36 lr 0.000793	time 5.1488 (2.2075)	loss 2.7612 (3.7416)	grad_norm 1.3794 (1.2250)	
[2022-01-20 11:06:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1000/1251]	eta 0:09:14 lr 0.000793	time 1.8660 (2.2082)	loss 3.4824 (3.7415)	grad_norm 1.2535 (1.2250)	
[2022-01-20 11:07:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1010/1251]	eta 0:08:52 lr 0.000793	time 1.5560 (2.2078)	loss 3.7590 (3.7397)	grad_norm 1.2494 (1.2255)	
[2022-01-20 11:07:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1020/1251]	eta 0:08:29 lr 0.000793	time 2.1024 (2.2064)	loss 4.4531 (3.7404)	grad_norm 1.1911 (1.2253)	
[2022-01-20 11:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1030/1251]	eta 0:08:07 lr 0.000792	time 3.1616 (2.2057)	loss 2.9070 (3.7373)	grad_norm 1.0471 (1.2244)	
[2022-01-20 11:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1040/1251]	eta 0:07:45 lr 0.000792	time 1.6185 (2.2044)	loss 4.0375 (3.7387)	grad_norm 1.2333 (1.2241)	
[2022-01-20 11:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1050/1251]	eta 0:07:23 lr 0.000792	time 1.8660 (2.2041)	loss 3.8967 (3.7386)	grad_norm 1.5442 (1.2245)	
[2022-01-20 11:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1060/1251]	eta 0:07:00 lr 0.000792	time 1.9011 (2.2039)	loss 2.7649 (3.7389)	grad_norm 1.3857 (1.2245)	
[2022-01-20 11:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1070/1251]	eta 0:06:39 lr 0.000792	time 3.5137 (2.2051)	loss 4.3100 (3.7401)	grad_norm 1.3074 (1.2248)	
[2022-01-20 11:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1080/1251]	eta 0:06:16 lr 0.000792	time 1.8785 (2.2037)	loss 2.5495 (3.7397)	grad_norm 1.2879 (1.2247)	
[2022-01-20 11:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1090/1251]	eta 0:05:54 lr 0.000792	time 1.9074 (2.2039)	loss 4.2791 (3.7426)	grad_norm 1.3025 (1.2254)	
[2022-01-20 11:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1100/1251]	eta 0:05:32 lr 0.000792	time 2.5597 (2.2039)	loss 3.8426 (3.7409)	grad_norm 1.2408 (1.2243)	
[2022-01-20 11:10:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1110/1251]	eta 0:05:10 lr 0.000792	time 3.3902 (2.2046)	loss 3.0932 (3.7419)	grad_norm 1.1570 (1.2236)	
[2022-01-20 11:11:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1120/1251]	eta 0:04:48 lr 0.000792	time 1.9625 (2.2037)	loss 3.1896 (3.7418)	grad_norm 1.2093 (1.2236)	
[2022-01-20 11:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1130/1251]	eta 0:04:26 lr 0.000792	time 2.4613 (2.2024)	loss 3.3450 (3.7378)	grad_norm 1.2047 (1.2232)	
[2022-01-20 11:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1140/1251]	eta 0:04:04 lr 0.000792	time 2.2328 (2.2010)	loss 3.6665 (3.7366)	grad_norm 1.0849 (1.2224)	
[2022-01-20 11:12:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1150/1251]	eta 0:03:42 lr 0.000792	time 1.9285 (2.2006)	loss 2.5906 (3.7368)	grad_norm 1.1321 (1.2217)	
[2022-01-20 11:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1160/1251]	eta 0:03:20 lr 0.000792	time 1.8498 (2.2004)	loss 3.9796 (3.7370)	grad_norm 1.3230 (1.2214)	
[2022-01-20 11:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1170/1251]	eta 0:02:58 lr 0.000792	time 2.5740 (2.2008)	loss 2.8482 (3.7367)	grad_norm 1.1553 (1.2213)	
[2022-01-20 11:13:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1180/1251]	eta 0:02:36 lr 0.000792	time 2.7302 (2.2031)	loss 4.1923 (3.7371)	grad_norm 1.4751 (1.2222)	
[2022-01-20 11:13:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1190/1251]	eta 0:02:14 lr 0.000792	time 2.1945 (2.2044)	loss 4.2990 (3.7366)	grad_norm 1.1158 (1.2229)	
[2022-01-20 11:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1200/1251]	eta 0:01:52 lr 0.000792	time 1.8585 (2.2045)	loss 3.0111 (3.7356)	grad_norm 1.3525 (1.2230)	
[2022-01-20 11:14:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1210/1251]	eta 0:01:30 lr 0.000792	time 2.5038 (2.2052)	loss 3.9252 (3.7374)	grad_norm 1.3273 (1.2232)	
[2022-01-20 11:14:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1220/1251]	eta 0:01:08 lr 0.000792	time 1.9450 (2.2037)	loss 4.2301 (3.7360)	grad_norm 1.2374 (1.2237)	
[2022-01-20 11:15:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1230/1251]	eta 0:00:46 lr 0.000792	time 2.0071 (2.2016)	loss 3.8037 (3.7348)	grad_norm 1.1824 (1.2239)	
[2022-01-20 11:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1240/1251]	eta 0:00:24 lr 0.000792	time 1.3128 (2.1993)	loss 4.0704 (3.7357)	grad_norm 1.0616 (1.2239)	
[2022-01-20 11:15:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [90/300][1250/1251]	eta 0:00:02 lr 0.000792	time 1.1769 (2.1937)	loss 3.6996 (3.7371)	grad_norm 1.3790 (1.2246)	
[2022-01-20 11:15:47 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 90 training takes 0:45:44
[2022-01-20 11:15:47 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_90 saving......
[2022-01-20 11:15:58 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_90 saved !!!
[2022-01-20 11:16:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.700 (16.700)	Loss 1.1173 (1.1173)	Acc@1 73.730 (73.730)	Acc@5 92.773 (92.773)	
[2022-01-20 11:16:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.611 (2.800)	Loss 1.1408 (1.1570)	Acc@1 73.926 (73.455)	Acc@5 91.992 (91.575)	
[2022-01-20 11:16:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.658 (2.298)	Loss 1.2252 (1.1595)	Acc@1 71.875 (73.293)	Acc@5 90.527 (91.643)	
[2022-01-20 11:17:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.301 (2.153)	Loss 1.1913 (1.1616)	Acc@1 72.363 (73.163)	Acc@5 91.992 (91.690)	
[2022-01-20 11:17:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.116 (2.063)	Loss 1.1457 (1.1613)	Acc@1 72.461 (73.087)	Acc@5 92.480 (91.866)	
[2022-01-20 11:17:30 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.022 Acc@5 91.768
[2022-01-20 11:17:30 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.0%
[2022-01-20 11:17:30 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.19%
[2022-01-20 11:17:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][0/1251]	eta 7:34:48 lr 0.000792	time 21.8135 (21.8135)	loss 3.5715 (3.5715)	grad_norm 1.2160 (1.2160)	
[2022-01-20 11:18:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][10/1251]	eta 1:23:16 lr 0.000792	time 1.5314 (4.0261)	loss 3.8375 (3.5886)	grad_norm 1.2148 (1.2077)	
[2022-01-20 11:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][20/1251]	eta 1:04:54 lr 0.000792	time 1.4840 (3.1635)	loss 3.0808 (3.6572)	grad_norm 1.1038 (1.2236)	
[2022-01-20 11:18:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][30/1251]	eta 0:56:54 lr 0.000792	time 1.5466 (2.7964)	loss 4.4278 (3.7717)	grad_norm 1.7749 (1.2320)	
[2022-01-20 11:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][40/1251]	eta 0:55:02 lr 0.000792	time 6.4872 (2.7273)	loss 3.3516 (3.7506)	grad_norm 1.0831 (1.2147)	
[2022-01-20 11:19:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][50/1251]	eta 0:52:33 lr 0.000792	time 2.7821 (2.6254)	loss 4.1858 (3.7782)	grad_norm 1.1458 (1.2051)	
[2022-01-20 11:20:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][60/1251]	eta 0:50:36 lr 0.000792	time 1.5154 (2.5499)	loss 3.8394 (3.8353)	grad_norm 1.2445 (1.1960)	
[2022-01-20 11:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][70/1251]	eta 0:48:54 lr 0.000792	time 2.0288 (2.4847)	loss 2.8268 (3.8183)	grad_norm 1.2365 (1.2216)	
[2022-01-20 11:20:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][80/1251]	eta 0:48:04 lr 0.000791	time 4.0983 (2.4637)	loss 3.8163 (3.8297)	grad_norm 1.0232 (1.2178)	
[2022-01-20 11:21:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][90/1251]	eta 0:47:24 lr 0.000791	time 2.1751 (2.4501)	loss 3.9450 (3.7875)	grad_norm 1.1902 (1.2299)	
[2022-01-20 11:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][100/1251]	eta 0:46:29 lr 0.000791	time 1.6059 (2.4237)	loss 4.1851 (3.7890)	grad_norm 1.1333 (1.2321)	
[2022-01-20 11:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][110/1251]	eta 0:45:40 lr 0.000791	time 1.7999 (2.4020)	loss 4.3444 (3.7903)	grad_norm 1.2437 (1.2315)	
[2022-01-20 11:22:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][120/1251]	eta 0:45:13 lr 0.000791	time 3.4553 (2.3988)	loss 3.3806 (3.7846)	grad_norm 1.1760 (1.2326)	
[2022-01-20 11:22:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][130/1251]	eta 0:44:37 lr 0.000791	time 1.5819 (2.3884)	loss 4.3232 (3.7745)	grad_norm 1.1600 (1.2343)	
[2022-01-20 11:23:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][140/1251]	eta 0:43:50 lr 0.000791	time 2.2530 (2.3679)	loss 3.9875 (3.7826)	grad_norm 1.2119 (1.2345)	
[2022-01-20 11:23:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][150/1251]	eta 0:43:02 lr 0.000791	time 1.6308 (2.3460)	loss 3.7954 (3.7663)	grad_norm 1.1773 (1.2359)	
[2022-01-20 11:23:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][160/1251]	eta 0:42:37 lr 0.000791	time 4.0982 (2.3442)	loss 3.0046 (3.7585)	grad_norm 1.2374 (1.2329)	
[2022-01-20 11:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][170/1251]	eta 0:42:06 lr 0.000791	time 1.9947 (2.3372)	loss 3.8583 (3.7684)	grad_norm 1.1449 (1.2253)	
[2022-01-20 11:24:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][180/1251]	eta 0:41:40 lr 0.000791	time 2.9043 (2.3344)	loss 4.1263 (3.7756)	grad_norm 1.3229 (1.2225)	
[2022-01-20 11:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][190/1251]	eta 0:41:07 lr 0.000791	time 2.0686 (2.3260)	loss 2.8733 (3.7568)	grad_norm 1.0784 (1.2174)	
[2022-01-20 11:25:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][200/1251]	eta 0:40:40 lr 0.000791	time 2.9791 (2.3218)	loss 4.3344 (3.7688)	grad_norm 1.1452 (1.2164)	
[2022-01-20 11:25:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][210/1251]	eta 0:39:58 lr 0.000791	time 1.5515 (2.3043)	loss 4.5622 (3.7759)	grad_norm 1.0727 (1.2148)	
[2022-01-20 11:25:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][220/1251]	eta 0:39:21 lr 0.000791	time 1.8447 (2.2905)	loss 3.0633 (3.7566)	grad_norm 1.3328 (1.2144)	
[2022-01-20 11:26:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][230/1251]	eta 0:38:46 lr 0.000791	time 1.8813 (2.2783)	loss 3.8114 (3.7475)	grad_norm 1.2006 (1.2151)	
[2022-01-20 11:26:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][240/1251]	eta 0:38:14 lr 0.000791	time 2.2240 (2.2696)	loss 4.6223 (3.7579)	grad_norm 1.1310 (1.2156)	
[2022-01-20 11:26:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][250/1251]	eta 0:37:49 lr 0.000791	time 1.7352 (2.2673)	loss 2.9756 (3.7553)	grad_norm 1.1292 (1.2153)	
[2022-01-20 11:27:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][260/1251]	eta 0:37:24 lr 0.000791	time 2.3939 (2.2645)	loss 4.4344 (3.7531)	grad_norm 1.2880 (1.2213)	
[2022-01-20 11:27:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][270/1251]	eta 0:36:58 lr 0.000791	time 1.9906 (2.2615)	loss 3.9804 (3.7563)	grad_norm 1.2272 (1.2234)	
[2022-01-20 11:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][280/1251]	eta 0:36:32 lr 0.000791	time 1.8267 (2.2576)	loss 4.3188 (3.7563)	grad_norm 1.0600 (1.2239)	
[2022-01-20 11:28:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][290/1251]	eta 0:36:07 lr 0.000791	time 1.8453 (2.2555)	loss 3.9336 (3.7557)	grad_norm 1.1123 (1.2205)	
[2022-01-20 11:28:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][300/1251]	eta 0:35:41 lr 0.000791	time 1.5983 (2.2519)	loss 3.8606 (3.7542)	grad_norm 1.2483 (1.2217)	
[2022-01-20 11:29:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][310/1251]	eta 0:35:15 lr 0.000791	time 1.8607 (2.2477)	loss 4.2955 (3.7622)	grad_norm 1.2926 (1.2200)	
[2022-01-20 11:29:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][320/1251]	eta 0:34:48 lr 0.000791	time 1.8734 (2.2438)	loss 4.1026 (3.7641)	grad_norm 1.2200 (1.2208)	
[2022-01-20 11:29:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][330/1251]	eta 0:34:25 lr 0.000791	time 1.8366 (2.2428)	loss 3.3188 (3.7614)	grad_norm 1.1778 (1.2211)	
[2022-01-20 11:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][340/1251]	eta 0:34:05 lr 0.000791	time 2.5589 (2.2458)	loss 2.7985 (3.7570)	grad_norm 1.3359 (1.2216)	
[2022-01-20 11:30:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][350/1251]	eta 0:33:47 lr 0.000791	time 2.8955 (2.2498)	loss 4.2930 (3.7593)	grad_norm 1.0523 (1.2219)	
[2022-01-20 11:31:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][360/1251]	eta 0:33:30 lr 0.000791	time 2.0806 (2.2563)	loss 3.1027 (3.7568)	grad_norm 1.3373 (1.2225)	
[2022-01-20 11:31:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][370/1251]	eta 0:33:06 lr 0.000790	time 1.8943 (2.2544)	loss 2.9355 (3.7571)	grad_norm 1.3748 (1.2228)	
[2022-01-20 11:31:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][380/1251]	eta 0:32:41 lr 0.000790	time 2.2087 (2.2514)	loss 4.5739 (3.7637)	grad_norm 1.1529 (1.2241)	
[2022-01-20 11:32:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][390/1251]	eta 0:32:10 lr 0.000790	time 1.8212 (2.2427)	loss 3.8660 (3.7642)	grad_norm 1.2913 (1.2251)	
[2022-01-20 11:32:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][400/1251]	eta 0:31:43 lr 0.000790	time 2.5072 (2.2373)	loss 2.9435 (3.7674)	grad_norm 1.2593 (1.2287)	
[2022-01-20 11:32:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][410/1251]	eta 0:31:17 lr 0.000790	time 1.2409 (2.2329)	loss 2.6748 (3.7622)	grad_norm 1.4415 (1.2310)	
[2022-01-20 11:33:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][420/1251]	eta 0:30:51 lr 0.000790	time 2.2389 (2.2282)	loss 3.9642 (3.7586)	grad_norm 1.1201 (1.2313)	
[2022-01-20 11:33:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][430/1251]	eta 0:30:28 lr 0.000790	time 2.2155 (2.2276)	loss 3.6716 (3.7563)	grad_norm 1.3369 (1.2295)	
[2022-01-20 11:33:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][440/1251]	eta 0:30:08 lr 0.000790	time 2.7380 (2.2302)	loss 3.4448 (3.7554)	grad_norm 1.1480 (1.2307)	
[2022-01-20 11:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][450/1251]	eta 0:29:46 lr 0.000790	time 1.7852 (2.2300)	loss 3.2012 (3.7507)	grad_norm 1.0924 (1.2306)	
[2022-01-20 11:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][460/1251]	eta 0:29:24 lr 0.000790	time 1.5632 (2.2313)	loss 4.4006 (3.7530)	grad_norm 1.4353 (1.2324)	
[2022-01-20 11:35:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][470/1251]	eta 0:29:02 lr 0.000790	time 2.3371 (2.2318)	loss 3.9329 (3.7545)	grad_norm 1.2796 (1.2313)	
[2022-01-20 11:35:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][480/1251]	eta 0:28:42 lr 0.000790	time 2.8791 (2.2346)	loss 3.7795 (3.7552)	grad_norm 1.8340 (1.2311)	
[2022-01-20 11:35:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][490/1251]	eta 0:28:19 lr 0.000790	time 1.5628 (2.2338)	loss 3.8281 (3.7526)	grad_norm 1.4067 (1.2323)	
[2022-01-20 11:36:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][500/1251]	eta 0:27:55 lr 0.000790	time 1.7315 (2.2306)	loss 3.5172 (3.7592)	grad_norm 1.0278 (1.2313)	
[2022-01-20 11:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][510/1251]	eta 0:27:31 lr 0.000790	time 1.8457 (2.2288)	loss 2.8211 (3.7601)	grad_norm 1.3381 (1.2319)	
[2022-01-20 11:36:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][520/1251]	eta 0:27:10 lr 0.000790	time 2.8450 (2.2308)	loss 3.7419 (3.7642)	grad_norm 1.2662 (1.2319)	
[2022-01-20 11:37:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][530/1251]	eta 0:26:49 lr 0.000790	time 1.9689 (2.2322)	loss 2.8771 (3.7612)	grad_norm 1.1895 (1.2324)	
[2022-01-20 11:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][540/1251]	eta 0:26:24 lr 0.000790	time 1.5017 (2.2283)	loss 2.8156 (3.7660)	grad_norm 1.0831 (1.2323)	
[2022-01-20 11:37:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][550/1251]	eta 0:25:59 lr 0.000790	time 1.9370 (2.2251)	loss 4.1570 (3.7669)	grad_norm 1.0853 (1.2314)	
[2022-01-20 11:38:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][560/1251]	eta 0:25:35 lr 0.000790	time 1.8644 (2.2221)	loss 3.8831 (3.7632)	grad_norm 1.2816 (1.2301)	
[2022-01-20 11:38:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][570/1251]	eta 0:25:13 lr 0.000790	time 2.2612 (2.2230)	loss 4.3613 (3.7596)	grad_norm 1.4273 (1.2301)	
[2022-01-20 11:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][580/1251]	eta 0:24:50 lr 0.000790	time 2.1164 (2.2214)	loss 4.4267 (3.7611)	grad_norm 1.1820 (1.2294)	
[2022-01-20 11:39:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][590/1251]	eta 0:24:28 lr 0.000790	time 1.9231 (2.2217)	loss 4.1948 (3.7627)	grad_norm 1.6063 (1.2310)	
[2022-01-20 11:39:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][600/1251]	eta 0:24:04 lr 0.000790	time 1.7413 (2.2192)	loss 3.9057 (3.7643)	grad_norm 1.2048 (1.2316)	
[2022-01-20 11:40:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][610/1251]	eta 0:23:43 lr 0.000790	time 2.4799 (2.2212)	loss 4.2383 (3.7657)	grad_norm 1.3785 (1.2334)	
[2022-01-20 11:40:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][620/1251]	eta 0:23:21 lr 0.000790	time 2.0312 (2.2206)	loss 3.9821 (3.7631)	grad_norm 1.3291 (1.2342)	
[2022-01-20 11:40:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][630/1251]	eta 0:22:58 lr 0.000790	time 2.4006 (2.2204)	loss 3.9210 (3.7631)	grad_norm 1.1902 (1.2333)	
[2022-01-20 11:41:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][640/1251]	eta 0:22:35 lr 0.000790	time 1.6898 (2.2177)	loss 3.8203 (3.7683)	grad_norm 1.1924 (1.2316)	
[2022-01-20 11:41:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][650/1251]	eta 0:22:11 lr 0.000790	time 1.5920 (2.2161)	loss 4.3108 (3.7695)	grad_norm 1.2964 (1.2309)	
[2022-01-20 11:41:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][660/1251]	eta 0:21:48 lr 0.000790	time 1.8897 (2.2146)	loss 3.9824 (3.7695)	grad_norm 1.2404 (1.2305)	
[2022-01-20 11:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][670/1251]	eta 0:21:27 lr 0.000789	time 2.4877 (2.2153)	loss 4.1846 (3.7720)	grad_norm 1.3350 (1.2303)	
[2022-01-20 11:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][680/1251]	eta 0:21:04 lr 0.000789	time 2.2426 (2.2137)	loss 3.0694 (3.7707)	grad_norm 1.1297 (1.2315)	
[2022-01-20 11:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][690/1251]	eta 0:20:42 lr 0.000789	time 1.9572 (2.2154)	loss 2.9173 (3.7724)	grad_norm 1.1971 (1.2309)	
[2022-01-20 11:43:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][700/1251]	eta 0:20:21 lr 0.000789	time 2.4998 (2.2167)	loss 4.2781 (3.7756)	grad_norm 1.1645 (1.2302)	
[2022-01-20 11:43:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][710/1251]	eta 0:19:59 lr 0.000789	time 2.4133 (2.2165)	loss 4.2178 (3.7762)	grad_norm 1.0966 (1.2307)	
[2022-01-20 11:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][720/1251]	eta 0:19:36 lr 0.000789	time 1.9579 (2.2148)	loss 4.2336 (3.7746)	grad_norm 1.0887 (1.2299)	
[2022-01-20 11:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][730/1251]	eta 0:19:12 lr 0.000789	time 1.8290 (2.2130)	loss 3.8623 (3.7719)	grad_norm 1.1337 (1.2299)	
[2022-01-20 11:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][740/1251]	eta 0:18:49 lr 0.000789	time 1.9666 (2.2097)	loss 4.0576 (3.7747)	grad_norm 1.1532 (1.2302)	
[2022-01-20 11:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][750/1251]	eta 0:18:25 lr 0.000789	time 1.9128 (2.2071)	loss 2.9334 (3.7721)	grad_norm 1.0896 (1.2300)	
[2022-01-20 11:45:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][760/1251]	eta 0:18:03 lr 0.000789	time 2.8994 (2.2074)	loss 4.0157 (3.7725)	grad_norm 1.4044 (1.2297)	
[2022-01-20 11:45:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][770/1251]	eta 0:17:42 lr 0.000789	time 1.8784 (2.2091)	loss 4.3080 (3.7781)	grad_norm 1.3887 (1.2300)	
[2022-01-20 11:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][780/1251]	eta 0:17:21 lr 0.000789	time 2.3582 (2.2120)	loss 3.9206 (3.7798)	grad_norm 1.3754 (1.2309)	
[2022-01-20 11:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][790/1251]	eta 0:17:00 lr 0.000789	time 2.8176 (2.2131)	loss 3.7857 (3.7771)	grad_norm 1.0660 (1.2310)	
[2022-01-20 11:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][800/1251]	eta 0:16:37 lr 0.000789	time 1.9061 (2.2129)	loss 4.0917 (3.7796)	grad_norm 1.1962 (1.2317)	
[2022-01-20 11:47:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][810/1251]	eta 0:16:15 lr 0.000789	time 1.8405 (2.2122)	loss 3.6426 (3.7803)	grad_norm 1.2134 (1.2323)	
[2022-01-20 11:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][820/1251]	eta 0:15:52 lr 0.000789	time 1.6470 (2.2098)	loss 3.1953 (3.7791)	grad_norm 1.1060 (1.2329)	
[2022-01-20 11:48:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][830/1251]	eta 0:15:29 lr 0.000789	time 1.8888 (2.2085)	loss 2.7802 (3.7806)	grad_norm 1.0534 (1.2316)	
[2022-01-20 11:48:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][840/1251]	eta 0:15:08 lr 0.000789	time 2.2093 (2.2107)	loss 4.0264 (3.7795)	grad_norm 1.1680 (1.2311)	
[2022-01-20 11:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][850/1251]	eta 0:14:47 lr 0.000789	time 2.2042 (2.2125)	loss 3.6704 (3.7815)	grad_norm 1.1738 (1.2308)	
[2022-01-20 11:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][860/1251]	eta 0:14:25 lr 0.000789	time 2.2846 (2.2143)	loss 3.8097 (3.7807)	grad_norm 1.2306 (1.2310)	
[2022-01-20 11:49:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][870/1251]	eta 0:14:03 lr 0.000789	time 1.8779 (2.2134)	loss 3.4803 (3.7806)	grad_norm 1.3133 (1.2304)	
[2022-01-20 11:49:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][880/1251]	eta 0:13:40 lr 0.000789	time 1.9154 (2.2105)	loss 3.7348 (3.7799)	grad_norm 1.4712 (1.2299)	
[2022-01-20 11:50:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][890/1251]	eta 0:13:17 lr 0.000789	time 1.8517 (2.2079)	loss 3.6569 (3.7820)	grad_norm 1.5624 (1.2299)	
[2022-01-20 11:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][900/1251]	eta 0:12:54 lr 0.000789	time 1.8648 (2.2063)	loss 4.0188 (3.7815)	grad_norm 1.1652 (1.2303)	
[2022-01-20 11:51:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][910/1251]	eta 0:12:32 lr 0.000789	time 2.0244 (2.2060)	loss 3.4613 (3.7804)	grad_norm 1.0720 (1.2294)	
[2022-01-20 11:51:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][920/1251]	eta 0:12:10 lr 0.000789	time 2.3757 (2.2072)	loss 4.2624 (3.7804)	grad_norm 1.3461 (1.2292)	
[2022-01-20 11:51:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][930/1251]	eta 0:11:48 lr 0.000789	time 1.6056 (2.2070)	loss 4.2764 (3.7797)	grad_norm 1.1518 (1.2286)	
[2022-01-20 11:52:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][940/1251]	eta 0:11:26 lr 0.000789	time 2.5365 (2.2071)	loss 3.9164 (3.7788)	grad_norm 1.1560 (1.2293)	
[2022-01-20 11:52:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][950/1251]	eta 0:11:04 lr 0.000789	time 1.6448 (2.2073)	loss 2.7514 (3.7802)	grad_norm 1.3277 (1.2296)	
[2022-01-20 11:52:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][960/1251]	eta 0:10:42 lr 0.000788	time 1.9949 (2.2065)	loss 4.1012 (3.7811)	grad_norm 1.2282 (1.2288)	
[2022-01-20 11:53:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][970/1251]	eta 0:10:20 lr 0.000788	time 2.1784 (2.2079)	loss 3.9044 (3.7823)	grad_norm 1.2937 (1.2293)	
[2022-01-20 11:53:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][980/1251]	eta 0:09:58 lr 0.000788	time 1.6666 (2.2072)	loss 2.8006 (3.7807)	grad_norm 1.2142 (1.2293)	
[2022-01-20 11:53:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][990/1251]	eta 0:09:36 lr 0.000788	time 1.7195 (2.2080)	loss 3.8667 (3.7831)	grad_norm 1.1747 (1.2292)	
[2022-01-20 11:54:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1000/1251]	eta 0:09:14 lr 0.000788	time 2.4186 (2.2079)	loss 4.1159 (3.7825)	grad_norm 1.1919 (1.2289)	
[2022-01-20 11:54:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1010/1251]	eta 0:08:52 lr 0.000788	time 1.7588 (2.2079)	loss 3.2347 (3.7833)	grad_norm 1.1227 (1.2285)	
[2022-01-20 11:55:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1020/1251]	eta 0:08:29 lr 0.000788	time 1.6640 (2.2054)	loss 4.4172 (3.7842)	grad_norm 1.1536 (1.2281)	
[2022-01-20 11:55:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1030/1251]	eta 0:08:06 lr 0.000788	time 1.9795 (2.2034)	loss 3.9349 (3.7852)	grad_norm 1.2982 (1.2280)	
[2022-01-20 11:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1040/1251]	eta 0:07:44 lr 0.000788	time 1.5332 (2.2021)	loss 3.5655 (3.7821)	grad_norm 1.2684 (1.2273)	
[2022-01-20 11:56:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1050/1251]	eta 0:07:22 lr 0.000788	time 1.9194 (2.2018)	loss 4.5801 (3.7811)	grad_norm 1.1019 (1.2270)	
[2022-01-20 11:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1060/1251]	eta 0:07:00 lr 0.000788	time 2.5681 (2.2021)	loss 4.4374 (3.7819)	grad_norm 1.5593 (1.2272)	
[2022-01-20 11:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1070/1251]	eta 0:06:38 lr 0.000788	time 1.6625 (2.2029)	loss 4.2301 (3.7833)	grad_norm 1.2400 (1.2276)	
[2022-01-20 11:57:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1080/1251]	eta 0:06:16 lr 0.000788	time 2.0671 (2.2037)	loss 3.9775 (3.7823)	grad_norm 1.3362 (1.2274)	
[2022-01-20 11:57:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1090/1251]	eta 0:05:55 lr 0.000788	time 2.8200 (2.2059)	loss 2.3167 (3.7802)	grad_norm 1.1904 (1.2275)	
[2022-01-20 11:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1100/1251]	eta 0:05:33 lr 0.000788	time 2.2206 (2.2064)	loss 3.3841 (3.7811)	grad_norm 1.2510 (1.2276)	
[2022-01-20 11:58:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1110/1251]	eta 0:05:11 lr 0.000788	time 2.2298 (2.2059)	loss 3.9961 (3.7813)	grad_norm 1.2676 (1.2283)	
[2022-01-20 11:58:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1120/1251]	eta 0:04:48 lr 0.000788	time 1.7392 (2.2043)	loss 4.3252 (3.7821)	grad_norm 1.3243 (1.2283)	
[2022-01-20 11:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1130/1251]	eta 0:04:26 lr 0.000788	time 2.2405 (2.2022)	loss 3.6761 (3.7819)	grad_norm 1.3502 (1.2288)	
[2022-01-20 11:59:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1140/1251]	eta 0:04:04 lr 0.000788	time 2.0990 (2.2002)	loss 3.7459 (3.7821)	grad_norm 1.1757 (1.2291)	
[2022-01-20 11:59:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1150/1251]	eta 0:03:42 lr 0.000788	time 2.4723 (2.2007)	loss 3.6740 (3.7803)	grad_norm 1.1480 (1.2289)	
[2022-01-20 12:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1160/1251]	eta 0:03:20 lr 0.000788	time 1.5193 (2.2004)	loss 3.9361 (3.7791)	grad_norm 1.1578 (1.2288)	
[2022-01-20 12:00:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1170/1251]	eta 0:02:58 lr 0.000788	time 1.8791 (2.2015)	loss 4.5185 (3.7807)	grad_norm 1.2348 (1.2287)	
[2022-01-20 12:00:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1180/1251]	eta 0:02:36 lr 0.000788	time 2.8512 (2.2031)	loss 3.6509 (3.7796)	grad_norm 1.3174 (1.2287)	
[2022-01-20 12:01:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1190/1251]	eta 0:02:14 lr 0.000788	time 2.7707 (2.2057)	loss 3.9968 (3.7784)	grad_norm 1.2305 (1.2286)	
[2022-01-20 12:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1200/1251]	eta 0:01:52 lr 0.000788	time 1.9018 (2.2046)	loss 2.8222 (3.7759)	grad_norm 1.5232 (1.2285)	
[2022-01-20 12:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1210/1251]	eta 0:01:30 lr 0.000788	time 1.9116 (2.2061)	loss 3.2849 (3.7749)	grad_norm 1.2300 (1.2284)	
[2022-01-20 12:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1220/1251]	eta 0:01:08 lr 0.000788	time 1.8058 (2.2044)	loss 3.9909 (3.7758)	grad_norm 1.0857 (1.2281)	
[2022-01-20 12:02:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1230/1251]	eta 0:00:46 lr 0.000788	time 1.9352 (2.2034)	loss 4.1247 (3.7779)	grad_norm 1.3316 (1.2281)	
[2022-01-20 12:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1240/1251]	eta 0:00:24 lr 0.000788	time 1.5168 (2.2023)	loss 3.8215 (3.7744)	grad_norm 1.4169 (1.2285)	
[2022-01-20 12:03:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [91/300][1250/1251]	eta 0:00:02 lr 0.000788	time 1.2029 (2.1969)	loss 4.1192 (3.7734)	grad_norm 1.5379 (1.2285)	
[2022-01-20 12:03:19 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 91 training takes 0:45:48
[2022-01-20 12:03:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 21.026 (21.026)	Loss 1.1828 (1.1828)	Acc@1 72.656 (72.656)	Acc@5 91.309 (91.309)	
[2022-01-20 12:03:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.926 (3.521)	Loss 1.2107 (1.1304)	Acc@1 71.680 (73.571)	Acc@5 90.723 (91.983)	
[2022-01-20 12:04:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.650 (2.794)	Loss 1.1526 (1.1309)	Acc@1 74.121 (73.679)	Acc@5 90.820 (91.895)	
[2022-01-20 12:04:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.650 (2.318)	Loss 1.0862 (1.1239)	Acc@1 74.023 (73.831)	Acc@5 92.285 (91.951)	
[2022-01-20 12:04:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.047 (2.193)	Loss 1.0635 (1.1227)	Acc@1 75.977 (73.857)	Acc@5 92.676 (91.992)	
[2022-01-20 12:04:56 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.718 Acc@5 91.930
[2022-01-20 12:04:56 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.7%
[2022-01-20 12:04:56 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.72%
[2022-01-20 12:05:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][0/1251]	eta 7:18:59 lr 0.000788	time 21.0547 (21.0547)	loss 3.7688 (3.7688)	grad_norm 1.1792 (1.1792)	
[2022-01-20 12:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][10/1251]	eta 1:21:36 lr 0.000787	time 1.6257 (3.9457)	loss 3.8560 (3.5799)	grad_norm 1.2304 (1.2252)	
[2022-01-20 12:06:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][20/1251]	eta 1:04:56 lr 0.000787	time 1.3280 (3.1656)	loss 4.3660 (3.6771)	grad_norm 1.0924 (1.2086)	
[2022-01-20 12:06:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][30/1251]	eta 0:57:10 lr 0.000787	time 1.8970 (2.8093)	loss 4.2598 (3.6629)	grad_norm 1.2919 (1.1949)	
[2022-01-20 12:06:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][40/1251]	eta 0:54:48 lr 0.000787	time 3.9026 (2.7156)	loss 4.5459 (3.7104)	grad_norm 1.0019 (1.1877)	
[2022-01-20 12:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][50/1251]	eta 0:52:35 lr 0.000787	time 2.5192 (2.6278)	loss 3.8704 (3.6774)	grad_norm 1.2665 (1.1928)	
[2022-01-20 12:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][60/1251]	eta 0:50:55 lr 0.000787	time 1.6168 (2.5651)	loss 3.9740 (3.6472)	grad_norm 1.1199 (1.1898)	
[2022-01-20 12:07:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][70/1251]	eta 0:49:31 lr 0.000787	time 1.6676 (2.5164)	loss 4.3896 (3.6564)	grad_norm 1.2356 (1.2000)	
[2022-01-20 12:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][80/1251]	eta 0:48:24 lr 0.000787	time 2.8585 (2.4803)	loss 4.1092 (3.6716)	grad_norm 1.1371 (1.1993)	
[2022-01-20 12:08:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][90/1251]	eta 0:47:33 lr 0.000787	time 2.4448 (2.4580)	loss 3.6697 (3.6717)	grad_norm 1.1055 (1.2065)	
[2022-01-20 12:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][100/1251]	eta 0:46:28 lr 0.000787	time 1.9548 (2.4230)	loss 3.8830 (3.6557)	grad_norm 1.1334 (1.2067)	
[2022-01-20 12:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][110/1251]	eta 0:45:25 lr 0.000787	time 2.1662 (2.3886)	loss 3.9876 (3.6702)	grad_norm 1.0606 (1.2076)	
[2022-01-20 12:09:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][120/1251]	eta 0:44:30 lr 0.000787	time 1.8805 (2.3616)	loss 4.3228 (3.6943)	grad_norm 1.4944 (1.2083)	
[2022-01-20 12:10:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][130/1251]	eta 0:43:50 lr 0.000787	time 2.8452 (2.3465)	loss 4.2064 (3.7137)	grad_norm 1.3334 (1.2087)	
[2022-01-20 12:10:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][140/1251]	eta 0:43:16 lr 0.000787	time 2.7821 (2.3373)	loss 4.1007 (3.7304)	grad_norm 1.2920 (1.2069)	
[2022-01-20 12:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][150/1251]	eta 0:42:46 lr 0.000787	time 2.0492 (2.3311)	loss 3.4829 (3.7291)	grad_norm 1.2488 (1.2114)	
[2022-01-20 12:11:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][160/1251]	eta 0:42:13 lr 0.000787	time 1.6083 (2.3225)	loss 4.0353 (3.7447)	grad_norm 1.0547 (1.2157)	
[2022-01-20 12:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][170/1251]	eta 0:41:50 lr 0.000787	time 2.2328 (2.3226)	loss 3.3299 (3.7509)	grad_norm 1.0609 (1.2127)	
[2022-01-20 12:11:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][180/1251]	eta 0:41:26 lr 0.000787	time 3.0675 (2.3219)	loss 3.3905 (3.7571)	grad_norm 1.1182 (1.2100)	
[2022-01-20 12:12:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][190/1251]	eta 0:40:43 lr 0.000787	time 2.1866 (2.3031)	loss 4.1865 (3.7577)	grad_norm 1.2976 (1.2090)	
[2022-01-20 12:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][200/1251]	eta 0:39:59 lr 0.000787	time 1.5443 (2.2828)	loss 3.4763 (3.7392)	grad_norm 1.4062 (1.2093)	
[2022-01-20 12:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][210/1251]	eta 0:39:33 lr 0.000787	time 2.2732 (2.2803)	loss 3.9833 (3.7474)	grad_norm 1.4038 (1.2122)	
[2022-01-20 12:13:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][220/1251]	eta 0:39:10 lr 0.000787	time 1.7959 (2.2795)	loss 3.8064 (3.7473)	grad_norm 1.3189 (1.2149)	
[2022-01-20 12:13:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][230/1251]	eta 0:38:40 lr 0.000787	time 2.4968 (2.2727)	loss 3.9201 (3.7541)	grad_norm 1.7852 (1.2186)	
[2022-01-20 12:14:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][240/1251]	eta 0:38:13 lr 0.000787	time 2.1369 (2.2685)	loss 3.5020 (3.7571)	grad_norm 1.2432 (1.2218)	
[2022-01-20 12:14:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][250/1251]	eta 0:37:52 lr 0.000787	time 1.8552 (2.2700)	loss 2.8816 (3.7589)	grad_norm 1.4060 (1.2244)	
[2022-01-20 12:14:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][260/1251]	eta 0:37:26 lr 0.000787	time 2.1290 (2.2669)	loss 2.9833 (3.7616)	grad_norm 1.1304 (1.2275)	
[2022-01-20 12:15:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][270/1251]	eta 0:37:02 lr 0.000787	time 3.5907 (2.2655)	loss 3.7390 (3.7606)	grad_norm 1.0273 (1.2270)	
[2022-01-20 12:15:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][280/1251]	eta 0:36:33 lr 0.000787	time 1.8414 (2.2592)	loss 4.3924 (3.7532)	grad_norm 1.1444 (1.2280)	
[2022-01-20 12:15:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][290/1251]	eta 0:36:02 lr 0.000787	time 1.6911 (2.2498)	loss 2.4186 (3.7483)	grad_norm 1.2117 (1.2289)	
[2022-01-20 12:16:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][300/1251]	eta 0:35:34 lr 0.000786	time 2.2967 (2.2448)	loss 3.6996 (3.7465)	grad_norm 1.2504 (1.2297)	
[2022-01-20 12:16:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][310/1251]	eta 0:35:14 lr 0.000786	time 3.4073 (2.2468)	loss 4.4113 (3.7510)	grad_norm 1.1196 (1.2294)	
[2022-01-20 12:16:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][320/1251]	eta 0:34:52 lr 0.000786	time 1.8610 (2.2475)	loss 3.2675 (3.7490)	grad_norm 1.2237 (1.2287)	
[2022-01-20 12:17:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][330/1251]	eta 0:34:30 lr 0.000786	time 2.2343 (2.2485)	loss 4.1372 (3.7525)	grad_norm 1.1917 (1.2295)	
[2022-01-20 12:17:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][340/1251]	eta 0:34:04 lr 0.000786	time 2.2928 (2.2447)	loss 4.0951 (3.7491)	grad_norm 1.3276 (1.2323)	
[2022-01-20 12:18:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][350/1251]	eta 0:33:45 lr 0.000786	time 3.8433 (2.2477)	loss 3.8588 (3.7541)	grad_norm 1.1693 (1.2312)	
[2022-01-20 12:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][360/1251]	eta 0:33:21 lr 0.000786	time 1.6500 (2.2465)	loss 4.0612 (3.7569)	grad_norm 1.2052 (1.2318)	
[2022-01-20 12:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][370/1251]	eta 0:32:56 lr 0.000786	time 1.8608 (2.2433)	loss 3.0574 (3.7618)	grad_norm 1.2796 (1.2327)	
[2022-01-20 12:19:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][380/1251]	eta 0:32:28 lr 0.000786	time 1.9154 (2.2368)	loss 3.3634 (3.7561)	grad_norm 1.3611 (1.2329)	
[2022-01-20 12:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][390/1251]	eta 0:32:10 lr 0.000786	time 4.1742 (2.2422)	loss 3.5157 (3.7565)	grad_norm 1.0580 (1.2344)	
[2022-01-20 12:19:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][400/1251]	eta 0:31:45 lr 0.000786	time 1.8890 (2.2388)	loss 3.8123 (3.7609)	grad_norm 1.2350 (1.2366)	
[2022-01-20 12:20:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][410/1251]	eta 0:31:17 lr 0.000786	time 1.8778 (2.2321)	loss 2.7140 (3.7559)	grad_norm 1.1654 (1.2365)	
[2022-01-20 12:20:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][420/1251]	eta 0:30:54 lr 0.000786	time 1.9267 (2.2319)	loss 2.2410 (3.7556)	grad_norm 1.2071 (1.2357)	
[2022-01-20 12:20:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][430/1251]	eta 0:30:34 lr 0.000786	time 2.9022 (2.2350)	loss 4.0600 (3.7587)	grad_norm 1.1150 (1.2339)	
[2022-01-20 12:21:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][440/1251]	eta 0:30:09 lr 0.000786	time 1.5632 (2.2314)	loss 3.8646 (3.7579)	grad_norm 1.4159 (1.2352)	
[2022-01-20 12:21:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][450/1251]	eta 0:29:45 lr 0.000786	time 1.9321 (2.2286)	loss 3.2714 (3.7602)	grad_norm 1.2551 (1.2360)	
[2022-01-20 12:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][460/1251]	eta 0:29:21 lr 0.000786	time 1.8397 (2.2264)	loss 4.2229 (3.7542)	grad_norm 1.3273 (1.2356)	
[2022-01-20 12:22:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][470/1251]	eta 0:29:03 lr 0.000786	time 3.6066 (2.2318)	loss 3.7292 (3.7621)	grad_norm 1.2179 (1.2355)	
[2022-01-20 12:22:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][480/1251]	eta 0:28:39 lr 0.000786	time 2.7225 (2.2302)	loss 4.0467 (3.7633)	grad_norm 1.2770 (1.2341)	
[2022-01-20 12:23:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][490/1251]	eta 0:28:12 lr 0.000786	time 1.6374 (2.2247)	loss 3.5636 (3.7686)	grad_norm 1.2896 (1.2341)	
[2022-01-20 12:23:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][500/1251]	eta 0:27:49 lr 0.000786	time 2.1271 (2.2232)	loss 2.7833 (3.7681)	grad_norm 1.0311 (1.2320)	
[2022-01-20 12:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][510/1251]	eta 0:27:25 lr 0.000786	time 2.1120 (2.2201)	loss 4.0792 (3.7650)	grad_norm 0.9947 (1.2317)	
[2022-01-20 12:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][520/1251]	eta 0:27:00 lr 0.000786	time 2.2837 (2.2173)	loss 4.1636 (3.7640)	grad_norm 1.3614 (1.2319)	
[2022-01-20 12:24:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][530/1251]	eta 0:26:37 lr 0.000786	time 1.9166 (2.2156)	loss 4.3723 (3.7666)	grad_norm 1.2079 (1.2304)	
[2022-01-20 12:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][540/1251]	eta 0:26:13 lr 0.000786	time 1.8425 (2.2128)	loss 3.3008 (3.7706)	grad_norm 1.0853 (1.2301)	
[2022-01-20 12:25:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][550/1251]	eta 0:25:50 lr 0.000786	time 2.1699 (2.2121)	loss 4.0702 (3.7700)	grad_norm 1.2332 (1.2299)	
[2022-01-20 12:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][560/1251]	eta 0:25:30 lr 0.000786	time 3.0321 (2.2143)	loss 4.3652 (3.7754)	grad_norm 1.1766 (1.2294)	
[2022-01-20 12:26:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][570/1251]	eta 0:25:07 lr 0.000786	time 1.8932 (2.2131)	loss 3.3487 (3.7681)	grad_norm 1.6243 (1.2297)	
[2022-01-20 12:26:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][580/1251]	eta 0:24:44 lr 0.000786	time 1.6142 (2.2117)	loss 4.0595 (3.7663)	grad_norm 1.0608 (1.2289)	
[2022-01-20 12:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][590/1251]	eta 0:24:22 lr 0.000785	time 1.8146 (2.2127)	loss 4.2901 (3.7652)	grad_norm 1.3734 (1.2294)	
[2022-01-20 12:27:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][600/1251]	eta 0:24:02 lr 0.000785	time 3.2033 (2.2155)	loss 4.3661 (3.7691)	grad_norm 1.2427 (1.2314)	
[2022-01-20 12:27:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][610/1251]	eta 0:23:40 lr 0.000785	time 2.7852 (2.2162)	loss 3.1469 (3.7714)	grad_norm 1.1776 (1.2317)	
[2022-01-20 12:27:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][620/1251]	eta 0:23:17 lr 0.000785	time 2.0013 (2.2150)	loss 4.1488 (3.7694)	grad_norm 1.1002 (1.2313)	
[2022-01-20 12:28:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][630/1251]	eta 0:22:54 lr 0.000785	time 2.0256 (2.2139)	loss 4.4726 (3.7668)	grad_norm 1.5742 (1.2321)	
[2022-01-20 12:28:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][640/1251]	eta 0:22:32 lr 0.000785	time 2.7414 (2.2139)	loss 3.6559 (3.7684)	grad_norm 1.3671 (1.2318)	
[2022-01-20 12:28:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][650/1251]	eta 0:22:09 lr 0.000785	time 2.4037 (2.2119)	loss 4.1371 (3.7702)	grad_norm 0.9608 (1.2301)	
[2022-01-20 12:29:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][660/1251]	eta 0:21:45 lr 0.000785	time 1.8798 (2.2085)	loss 3.9699 (3.7720)	grad_norm 1.0736 (1.2292)	
[2022-01-20 12:29:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][670/1251]	eta 0:21:22 lr 0.000785	time 1.9424 (2.2081)	loss 3.7885 (3.7732)	grad_norm 1.1213 (1.2291)	
[2022-01-20 12:29:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][680/1251]	eta 0:21:00 lr 0.000785	time 1.8421 (2.2078)	loss 3.8678 (3.7761)	grad_norm 1.2417 (1.2315)	
[2022-01-20 12:30:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][690/1251]	eta 0:20:40 lr 0.000785	time 3.5837 (2.2105)	loss 4.2734 (3.7740)	grad_norm 1.3251 (1.2323)	
[2022-01-20 12:30:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][700/1251]	eta 0:20:18 lr 0.000785	time 2.2158 (2.2116)	loss 3.8198 (3.7696)	grad_norm 1.3493 (1.2321)	
[2022-01-20 12:31:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][710/1251]	eta 0:19:55 lr 0.000785	time 2.2020 (2.2099)	loss 4.6107 (3.7736)	grad_norm 1.1677 (1.2328)	
[2022-01-20 12:31:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][720/1251]	eta 0:19:33 lr 0.000785	time 2.3072 (2.2093)	loss 3.5248 (3.7743)	grad_norm 1.3140 (1.2322)	
[2022-01-20 12:31:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][730/1251]	eta 0:19:09 lr 0.000785	time 2.2264 (2.2073)	loss 2.5935 (3.7701)	grad_norm 1.3935 (1.2336)	
[2022-01-20 12:32:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][740/1251]	eta 0:18:47 lr 0.000785	time 1.6805 (2.2057)	loss 4.5869 (3.7727)	grad_norm 1.1842 (1.2342)	
[2022-01-20 12:32:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][750/1251]	eta 0:18:25 lr 0.000785	time 2.8140 (2.2057)	loss 4.3855 (3.7747)	grad_norm 1.0906 (1.2332)	
[2022-01-20 12:32:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][760/1251]	eta 0:18:03 lr 0.000785	time 2.1867 (2.2075)	loss 4.2743 (3.7729)	grad_norm 1.1311 (1.2337)	
[2022-01-20 12:33:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][770/1251]	eta 0:17:41 lr 0.000785	time 2.3460 (2.2077)	loss 3.7641 (3.7718)	grad_norm 1.0969 (1.2331)	
[2022-01-20 12:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][780/1251]	eta 0:17:19 lr 0.000785	time 1.6614 (2.2070)	loss 3.4096 (3.7693)	grad_norm 1.1431 (1.2344)	
[2022-01-20 12:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][790/1251]	eta 0:16:56 lr 0.000785	time 2.0924 (2.2051)	loss 4.1152 (3.7707)	grad_norm 1.1039 (1.2338)	
[2022-01-20 12:34:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][800/1251]	eta 0:16:33 lr 0.000785	time 1.5881 (2.2027)	loss 3.9851 (3.7699)	grad_norm 1.2856 (1.2337)	
[2022-01-20 12:34:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][810/1251]	eta 0:16:10 lr 0.000785	time 1.8235 (2.2015)	loss 3.4447 (3.7689)	grad_norm 1.2889 (1.2341)	
[2022-01-20 12:35:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][820/1251]	eta 0:15:48 lr 0.000785	time 2.2834 (2.2014)	loss 3.7159 (3.7704)	grad_norm 1.1883 (1.2341)	
[2022-01-20 12:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][830/1251]	eta 0:15:26 lr 0.000785	time 2.8456 (2.2018)	loss 3.6863 (3.7682)	grad_norm 1.1781 (1.2332)	
[2022-01-20 12:35:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][840/1251]	eta 0:15:04 lr 0.000785	time 2.2360 (2.2016)	loss 4.3546 (3.7665)	grad_norm 1.2809 (1.2323)	
[2022-01-20 12:36:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][850/1251]	eta 0:14:43 lr 0.000785	time 2.0923 (2.2045)	loss 3.6278 (3.7659)	grad_norm 1.3658 (1.2324)	
[2022-01-20 12:36:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][860/1251]	eta 0:14:22 lr 0.000785	time 1.9532 (2.2056)	loss 2.1993 (3.7650)	grad_norm 1.2116 (1.2332)	
[2022-01-20 12:36:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][870/1251]	eta 0:14:00 lr 0.000785	time 2.7516 (2.2052)	loss 4.0498 (3.7646)	grad_norm 1.0789 (1.2332)	
[2022-01-20 12:37:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][880/1251]	eta 0:13:36 lr 0.000785	time 1.6475 (2.2020)	loss 3.8115 (3.7631)	grad_norm 1.1046 (1.2336)	
[2022-01-20 12:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][890/1251]	eta 0:13:14 lr 0.000784	time 1.6595 (2.1998)	loss 3.9192 (3.7655)	grad_norm 1.1348 (1.2332)	
[2022-01-20 12:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][900/1251]	eta 0:12:52 lr 0.000784	time 2.4009 (2.1996)	loss 4.2056 (3.7646)	grad_norm 1.2102 (1.2333)	
[2022-01-20 12:38:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][910/1251]	eta 0:12:30 lr 0.000784	time 2.8647 (2.1996)	loss 2.7113 (3.7636)	grad_norm 1.1865 (1.2329)	
[2022-01-20 12:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][920/1251]	eta 0:12:07 lr 0.000784	time 2.1057 (2.1988)	loss 3.5840 (3.7640)	grad_norm 1.3132 (1.2339)	
[2022-01-20 12:39:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][930/1251]	eta 0:11:45 lr 0.000784	time 1.9123 (2.1993)	loss 4.0827 (3.7631)	grad_norm 1.2289 (1.2331)	
[2022-01-20 12:39:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][940/1251]	eta 0:11:24 lr 0.000784	time 2.2375 (2.2010)	loss 3.6168 (3.7629)	grad_norm 1.2796 (1.2331)	
[2022-01-20 12:39:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][950/1251]	eta 0:11:03 lr 0.000784	time 3.1559 (2.2034)	loss 2.6216 (3.7620)	grad_norm 1.2453 (1.2346)	
[2022-01-20 12:40:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][960/1251]	eta 0:10:40 lr 0.000784	time 1.8907 (2.2027)	loss 3.7519 (3.7592)	grad_norm 1.1254 (1.2344)	
[2022-01-20 12:40:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][970/1251]	eta 0:10:18 lr 0.000784	time 1.6785 (2.2004)	loss 4.1488 (3.7586)	grad_norm 1.1677 (1.2348)	
[2022-01-20 12:40:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][980/1251]	eta 0:09:55 lr 0.000784	time 1.5683 (2.1984)	loss 4.1400 (3.7585)	grad_norm 1.1767 (1.2354)	
[2022-01-20 12:41:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][990/1251]	eta 0:09:33 lr 0.000784	time 1.8255 (2.1978)	loss 4.1302 (3.7591)	grad_norm 1.1764 (1.2358)	
[2022-01-20 12:41:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1000/1251]	eta 0:09:11 lr 0.000784	time 2.0976 (2.1983)	loss 4.3501 (3.7605)	grad_norm 1.1103 (1.2351)	
[2022-01-20 12:42:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1010/1251]	eta 0:08:50 lr 0.000784	time 1.8321 (2.1995)	loss 4.5406 (3.7596)	grad_norm 1.2055 (1.2349)	
[2022-01-20 12:42:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1020/1251]	eta 0:08:28 lr 0.000784	time 2.1771 (2.2003)	loss 3.8870 (3.7601)	grad_norm 1.1118 (1.2348)	
[2022-01-20 12:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1030/1251]	eta 0:08:06 lr 0.000784	time 2.1129 (2.1997)	loss 3.0345 (3.7594)	grad_norm 1.1081 (1.2353)	
[2022-01-20 12:43:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1040/1251]	eta 0:07:44 lr 0.000784	time 2.4999 (2.1992)	loss 4.1949 (3.7601)	grad_norm 1.5195 (1.2357)	
[2022-01-20 12:43:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1050/1251]	eta 0:07:21 lr 0.000784	time 1.8365 (2.1980)	loss 3.7900 (3.7606)	grad_norm 1.6233 (1.2358)	
[2022-01-20 12:43:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1060/1251]	eta 0:06:59 lr 0.000784	time 1.8957 (2.1972)	loss 3.5188 (3.7566)	grad_norm 1.1559 (1.2354)	
[2022-01-20 12:44:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1070/1251]	eta 0:06:38 lr 0.000784	time 2.8143 (2.2006)	loss 3.7598 (3.7590)	grad_norm 1.4332 (1.2358)	
[2022-01-20 12:44:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1080/1251]	eta 0:06:16 lr 0.000784	time 3.0501 (2.1991)	loss 3.3555 (3.7577)	grad_norm 1.2712 (1.2358)	
[2022-01-20 12:44:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1090/1251]	eta 0:05:53 lr 0.000784	time 1.9499 (2.1971)	loss 4.2060 (3.7586)	grad_norm 1.3614 (1.2355)	
[2022-01-20 12:45:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1100/1251]	eta 0:05:31 lr 0.000784	time 1.9523 (2.1946)	loss 4.0525 (3.7594)	grad_norm 1.2752 (1.2358)	
[2022-01-20 12:45:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1110/1251]	eta 0:05:09 lr 0.000784	time 2.1055 (2.1939)	loss 3.9564 (3.7607)	grad_norm 1.2460 (1.2357)	
[2022-01-20 12:45:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1120/1251]	eta 0:04:47 lr 0.000784	time 1.9603 (2.1939)	loss 4.3070 (3.7587)	grad_norm 1.2474 (1.2363)	
[2022-01-20 12:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1130/1251]	eta 0:04:25 lr 0.000784	time 2.5885 (2.1947)	loss 4.3046 (3.7609)	grad_norm 1.0615 (1.2367)	
[2022-01-20 12:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1140/1251]	eta 0:04:03 lr 0.000784	time 2.4269 (2.1953)	loss 4.2407 (3.7625)	grad_norm 1.2129 (1.2366)	
[2022-01-20 12:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1150/1251]	eta 0:03:41 lr 0.000784	time 2.4165 (2.1953)	loss 3.9353 (3.7611)	grad_norm 1.3144 (1.2371)	
[2022-01-20 12:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1160/1251]	eta 0:03:19 lr 0.000784	time 1.8282 (2.1967)	loss 3.9194 (3.7632)	grad_norm 1.0966 (1.2371)	
[2022-01-20 12:47:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1170/1251]	eta 0:02:57 lr 0.000784	time 1.9403 (2.1972)	loss 3.8485 (3.7630)	grad_norm 1.0673 (1.2365)	
[2022-01-20 12:48:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1180/1251]	eta 0:02:36 lr 0.000783	time 2.3745 (2.1984)	loss 3.6878 (3.7621)	grad_norm 1.4942 (1.2367)	
[2022-01-20 12:48:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1190/1251]	eta 0:02:14 lr 0.000783	time 2.6103 (2.1978)	loss 3.1529 (3.7603)	grad_norm 1.1944 (1.2364)	
[2022-01-20 12:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1200/1251]	eta 0:01:51 lr 0.000783	time 1.8039 (2.1958)	loss 3.4136 (3.7601)	grad_norm 1.0345 (1.2363)	
[2022-01-20 12:49:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1210/1251]	eta 0:01:29 lr 0.000783	time 1.8776 (2.1949)	loss 3.9194 (3.7619)	grad_norm 1.0675 (1.2360)	
[2022-01-20 12:49:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1220/1251]	eta 0:01:08 lr 0.000783	time 2.2318 (2.1944)	loss 4.3056 (3.7611)	grad_norm 1.1110 (1.2357)	
[2022-01-20 12:49:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1230/1251]	eta 0:00:46 lr 0.000783	time 1.9882 (2.1943)	loss 3.9209 (3.7610)	grad_norm 1.2388 (1.2351)	
[2022-01-20 12:50:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1240/1251]	eta 0:00:24 lr 0.000783	time 2.2646 (2.1941)	loss 3.4652 (3.7611)	grad_norm 1.3156 (1.2351)	
[2022-01-20 12:50:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [92/300][1250/1251]	eta 0:00:02 lr 0.000783	time 1.1609 (2.1887)	loss 3.7396 (3.7616)	grad_norm 1.1610 (1.2348)	
[2022-01-20 12:50:34 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 92 training takes 0:45:38
[2022-01-20 12:50:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.654 (18.654)	Loss 1.1378 (1.1378)	Acc@1 73.340 (73.340)	Acc@5 91.504 (91.504)	
[2022-01-20 12:51:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.210 (3.327)	Loss 1.0602 (1.1367)	Acc@1 75.977 (73.713)	Acc@5 94.141 (91.966)	
[2022-01-20 12:51:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.611 (2.691)	Loss 1.0733 (1.1382)	Acc@1 73.828 (73.419)	Acc@5 93.066 (91.969)	
[2022-01-20 12:51:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.582 (2.321)	Loss 1.0685 (1.1341)	Acc@1 75.195 (73.463)	Acc@5 92.773 (92.046)	
[2022-01-20 12:52:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.633 (2.136)	Loss 1.2764 (1.1477)	Acc@1 70.898 (73.237)	Acc@5 90.430 (91.916)	
[2022-01-20 12:52:11 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.284 Acc@5 91.972
[2022-01-20 12:52:11 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.3%
[2022-01-20 12:52:11 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.72%
[2022-01-20 12:52:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][0/1251]	eta 7:11:10 lr 0.000783	time 20.6802 (20.6802)	loss 4.2206 (4.2206)	grad_norm 1.2168 (1.2168)	
[2022-01-20 12:52:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][10/1251]	eta 1:21:55 lr 0.000783	time 2.5467 (3.9608)	loss 4.1512 (3.6941)	grad_norm 1.0660 (1.1843)	
[2022-01-20 12:53:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][20/1251]	eta 1:03:27 lr 0.000783	time 1.7107 (3.0929)	loss 3.5229 (3.8045)	grad_norm 1.1571 (1.1935)	
[2022-01-20 12:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][30/1251]	eta 0:57:01 lr 0.000783	time 1.5632 (2.8022)	loss 4.0183 (3.7670)	grad_norm 1.3163 (1.2036)	
[2022-01-20 12:54:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][40/1251]	eta 0:54:16 lr 0.000783	time 3.2022 (2.6891)	loss 3.8828 (3.7998)	grad_norm 1.1011 (1.2120)	
[2022-01-20 12:54:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][50/1251]	eta 0:52:35 lr 0.000783	time 2.7413 (2.6272)	loss 3.4409 (3.7407)	grad_norm 1.1616 (1.2063)	
[2022-01-20 12:54:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][60/1251]	eta 0:50:53 lr 0.000783	time 1.9527 (2.5637)	loss 4.5302 (3.7630)	grad_norm 1.0978 (1.2002)	
[2022-01-20 12:55:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][70/1251]	eta 0:49:11 lr 0.000783	time 2.2176 (2.4988)	loss 3.2378 (3.7781)	grad_norm 1.0908 (1.2108)	
[2022-01-20 12:55:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][80/1251]	eta 0:47:53 lr 0.000783	time 2.8631 (2.4542)	loss 4.4537 (3.7787)	grad_norm 1.4513 (1.2130)	
[2022-01-20 12:55:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][90/1251]	eta 0:47:07 lr 0.000783	time 3.2028 (2.4351)	loss 4.4822 (3.7945)	grad_norm 1.2895 (1.2175)	
[2022-01-20 12:56:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][100/1251]	eta 0:46:22 lr 0.000783	time 2.6723 (2.4173)	loss 4.2220 (3.8193)	grad_norm 1.1532 (1.2163)	
[2022-01-20 12:56:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][110/1251]	eta 0:45:49 lr 0.000783	time 2.7189 (2.4100)	loss 4.3044 (3.8205)	grad_norm 1.1809 (1.2116)	
[2022-01-20 12:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][120/1251]	eta 0:45:14 lr 0.000783	time 2.5242 (2.4004)	loss 3.4660 (3.8181)	grad_norm 1.5091 (1.2201)	
[2022-01-20 12:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][130/1251]	eta 0:44:36 lr 0.000783	time 2.5080 (2.3876)	loss 4.1956 (3.8067)	grad_norm 1.2416 (1.2228)	
[2022-01-20 12:57:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][140/1251]	eta 0:43:55 lr 0.000783	time 2.5130 (2.3718)	loss 3.8193 (3.7927)	grad_norm 1.2206 (1.2203)	
[2022-01-20 12:58:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][150/1251]	eta 0:43:08 lr 0.000783	time 2.2905 (2.3507)	loss 3.9147 (3.7956)	grad_norm 1.1862 (1.2213)	
[2022-01-20 12:58:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][160/1251]	eta 0:42:22 lr 0.000783	time 1.5366 (2.3301)	loss 4.0073 (3.8026)	grad_norm 1.0824 (1.2238)	
[2022-01-20 12:58:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][170/1251]	eta 0:41:55 lr 0.000783	time 3.1185 (2.3273)	loss 4.1383 (3.7934)	grad_norm 1.2317 (1.2231)	
[2022-01-20 12:59:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][180/1251]	eta 0:41:23 lr 0.000783	time 2.5290 (2.3193)	loss 4.2935 (3.8061)	grad_norm 1.3769 (1.2257)	
[2022-01-20 12:59:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][190/1251]	eta 0:40:55 lr 0.000783	time 2.4174 (2.3146)	loss 3.3446 (3.8005)	grad_norm 1.1033 (1.2279)	
[2022-01-20 12:59:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][200/1251]	eta 0:40:25 lr 0.000783	time 2.1308 (2.3078)	loss 4.1743 (3.7892)	grad_norm 1.2702 (1.2275)	
[2022-01-20 13:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][210/1251]	eta 0:39:54 lr 0.000783	time 2.2349 (2.3001)	loss 3.2733 (3.7900)	grad_norm 1.2410 (1.2287)	
[2022-01-20 13:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][220/1251]	eta 0:39:31 lr 0.000782	time 2.1389 (2.3002)	loss 2.7268 (3.7754)	grad_norm 1.3244 (1.2295)	
[2022-01-20 13:01:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][230/1251]	eta 0:39:02 lr 0.000782	time 2.3919 (2.2942)	loss 3.8185 (3.7838)	grad_norm 1.1430 (1.2304)	
[2022-01-20 13:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][240/1251]	eta 0:38:34 lr 0.000782	time 1.9296 (2.2893)	loss 2.9921 (3.7668)	grad_norm 1.3492 (1.2334)	
[2022-01-20 13:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][250/1251]	eta 0:38:13 lr 0.000782	time 2.5511 (2.2913)	loss 4.3564 (3.7730)	grad_norm 1.3200 (1.2332)	
[2022-01-20 13:02:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][260/1251]	eta 0:37:50 lr 0.000782	time 2.0361 (2.2911)	loss 3.9752 (3.7777)	grad_norm 1.3450 (1.2389)	
[2022-01-20 13:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][270/1251]	eta 0:37:18 lr 0.000782	time 2.0671 (2.2821)	loss 3.7334 (3.7807)	grad_norm 1.2554 (1.2432)	
[2022-01-20 13:02:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][280/1251]	eta 0:36:53 lr 0.000782	time 2.4102 (2.2796)	loss 3.4925 (3.7871)	grad_norm 1.2045 (1.2466)	
[2022-01-20 13:03:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][290/1251]	eta 0:36:24 lr 0.000782	time 1.9312 (2.2728)	loss 4.2548 (3.7865)	grad_norm 1.3078 (1.2451)	
[2022-01-20 13:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][300/1251]	eta 0:35:53 lr 0.000782	time 2.4843 (2.2645)	loss 2.4569 (3.7902)	grad_norm 1.2556 (1.2441)	
[2022-01-20 13:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][310/1251]	eta 0:35:24 lr 0.000782	time 2.5216 (2.2578)	loss 4.4935 (3.7980)	grad_norm 1.1410 (1.2422)	
[2022-01-20 13:04:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][320/1251]	eta 0:34:57 lr 0.000782	time 2.4422 (2.2528)	loss 4.0513 (3.7925)	grad_norm 1.1422 (1.2404)	
[2022-01-20 13:04:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][330/1251]	eta 0:34:33 lr 0.000782	time 1.8894 (2.2511)	loss 4.6678 (3.7846)	grad_norm 1.1921 (1.2393)	
[2022-01-20 13:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][340/1251]	eta 0:34:11 lr 0.000782	time 2.4509 (2.2523)	loss 3.8783 (3.7790)	grad_norm 1.1354 (1.2383)	
[2022-01-20 13:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][350/1251]	eta 0:33:50 lr 0.000782	time 1.9239 (2.2532)	loss 4.1507 (3.7831)	grad_norm 1.2634 (1.2378)	
[2022-01-20 13:05:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][360/1251]	eta 0:33:30 lr 0.000782	time 1.6409 (2.2570)	loss 3.9172 (3.7916)	grad_norm 1.3615 (1.2358)	
[2022-01-20 13:06:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][370/1251]	eta 0:33:10 lr 0.000782	time 2.0101 (2.2591)	loss 2.9184 (3.7861)	grad_norm 1.2589 (1.2360)	
[2022-01-20 13:06:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][380/1251]	eta 0:32:44 lr 0.000782	time 1.7712 (2.2552)	loss 3.3769 (3.7776)	grad_norm 1.1925 (1.2368)	
[2022-01-20 13:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][390/1251]	eta 0:32:17 lr 0.000782	time 1.9005 (2.2504)	loss 3.8024 (3.7741)	grad_norm 1.4080 (1.2377)	
[2022-01-20 13:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][400/1251]	eta 0:31:49 lr 0.000782	time 1.5822 (2.2436)	loss 3.0793 (3.7758)	grad_norm 1.2752 (1.2391)	
[2022-01-20 13:07:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][410/1251]	eta 0:31:23 lr 0.000782	time 1.9566 (2.2390)	loss 4.1642 (3.7808)	grad_norm 1.5416 (1.2395)	
[2022-01-20 13:07:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][420/1251]	eta 0:30:55 lr 0.000782	time 1.9005 (2.2331)	loss 2.9577 (3.7776)	grad_norm 1.2948 (1.2379)	
[2022-01-20 13:08:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][430/1251]	eta 0:30:33 lr 0.000782	time 2.5038 (2.2332)	loss 3.4610 (3.7772)	grad_norm 1.0921 (1.2368)	
[2022-01-20 13:08:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][440/1251]	eta 0:30:12 lr 0.000782	time 2.1731 (2.2353)	loss 3.3622 (3.7744)	grad_norm 1.2710 (1.2366)	
[2022-01-20 13:09:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][450/1251]	eta 0:29:51 lr 0.000782	time 2.1498 (2.2370)	loss 3.2171 (3.7756)	grad_norm 1.1024 (1.2357)	
[2022-01-20 13:09:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][460/1251]	eta 0:29:29 lr 0.000782	time 1.6625 (2.2368)	loss 3.9322 (3.7822)	grad_norm 1.2678 (1.2347)	
[2022-01-20 13:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][470/1251]	eta 0:29:06 lr 0.000782	time 1.9419 (2.2367)	loss 3.8355 (3.7783)	grad_norm 1.2301 (1.2366)	
[2022-01-20 13:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][480/1251]	eta 0:28:44 lr 0.000782	time 2.2713 (2.2367)	loss 4.4657 (3.7774)	grad_norm 1.3497 (1.2352)	
[2022-01-20 13:10:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][490/1251]	eta 0:28:19 lr 0.000782	time 1.5680 (2.2334)	loss 2.7288 (3.7773)	grad_norm 1.5858 (1.2352)	
[2022-01-20 13:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][500/1251]	eta 0:27:54 lr 0.000782	time 1.7469 (2.2291)	loss 4.1249 (3.7785)	grad_norm 1.0755 (1.2365)	
[2022-01-20 13:11:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][510/1251]	eta 0:27:32 lr 0.000781	time 1.8076 (2.2296)	loss 4.2934 (3.7769)	grad_norm 1.1092 (1.2355)	
[2022-01-20 13:11:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][520/1251]	eta 0:27:09 lr 0.000781	time 2.3708 (2.2296)	loss 4.5704 (3.7766)	grad_norm 1.4645 (1.2378)	
[2022-01-20 13:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][530/1251]	eta 0:26:46 lr 0.000781	time 2.5022 (2.2285)	loss 3.7229 (3.7698)	grad_norm 1.0365 (1.2376)	
[2022-01-20 13:12:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][540/1251]	eta 0:26:23 lr 0.000781	time 1.9288 (2.2267)	loss 4.1303 (3.7655)	grad_norm 1.2153 (1.2392)	
[2022-01-20 13:12:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][550/1251]	eta 0:26:02 lr 0.000781	time 2.2407 (2.2284)	loss 4.2005 (3.7638)	grad_norm 1.0397 (1.2386)	
[2022-01-20 13:13:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][560/1251]	eta 0:25:38 lr 0.000781	time 1.8774 (2.2263)	loss 3.5013 (3.7672)	grad_norm 1.3873 (1.2375)	
[2022-01-20 13:13:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][570/1251]	eta 0:25:14 lr 0.000781	time 1.9301 (2.2243)	loss 4.2291 (3.7673)	grad_norm 1.4964 (1.2389)	
[2022-01-20 13:13:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][580/1251]	eta 0:24:51 lr 0.000781	time 1.9665 (2.2225)	loss 4.6055 (3.7676)	grad_norm 1.3078 (1.2390)	
[2022-01-20 13:14:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][590/1251]	eta 0:24:30 lr 0.000781	time 1.8762 (2.2249)	loss 4.2579 (3.7667)	grad_norm 1.2181 (1.2387)	
[2022-01-20 13:14:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][600/1251]	eta 0:24:06 lr 0.000781	time 1.5514 (2.2222)	loss 3.6640 (3.7695)	grad_norm 1.1491 (1.2387)	
[2022-01-20 13:14:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][610/1251]	eta 0:23:43 lr 0.000781	time 2.2454 (2.2209)	loss 4.5100 (3.7692)	grad_norm 1.1397 (1.2377)	
[2022-01-20 13:15:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][620/1251]	eta 0:23:21 lr 0.000781	time 1.6616 (2.2217)	loss 4.0126 (3.7679)	grad_norm 1.4460 (1.2376)	
[2022-01-20 13:15:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][630/1251]	eta 0:23:00 lr 0.000781	time 2.2641 (2.2232)	loss 4.2522 (3.7705)	grad_norm 1.3219 (1.2379)	
[2022-01-20 13:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][640/1251]	eta 0:22:36 lr 0.000781	time 2.6349 (2.2198)	loss 4.0852 (3.7699)	grad_norm 1.0622 (1.2363)	
[2022-01-20 13:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][650/1251]	eta 0:22:13 lr 0.000781	time 2.3779 (2.2194)	loss 3.9629 (3.7705)	grad_norm 1.2300 (1.2359)	
[2022-01-20 13:16:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][660/1251]	eta 0:21:50 lr 0.000781	time 1.6556 (2.2169)	loss 3.7652 (3.7694)	grad_norm 1.1670 (1.2360)	
[2022-01-20 13:16:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][670/1251]	eta 0:21:27 lr 0.000781	time 2.5734 (2.2168)	loss 4.5506 (3.7709)	grad_norm 1.2223 (1.2366)	
[2022-01-20 13:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][680/1251]	eta 0:21:04 lr 0.000781	time 2.0353 (2.2147)	loss 3.8696 (3.7696)	grad_norm 1.4357 (1.2375)	
[2022-01-20 13:17:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][690/1251]	eta 0:20:42 lr 0.000781	time 2.8008 (2.2152)	loss 4.4866 (3.7716)	grad_norm 1.2871 (1.2364)	
[2022-01-20 13:18:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][700/1251]	eta 0:20:21 lr 0.000781	time 2.6621 (2.2170)	loss 4.4381 (3.7690)	grad_norm 1.2547 (1.2371)	
[2022-01-20 13:18:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][710/1251]	eta 0:20:00 lr 0.000781	time 2.6180 (2.2190)	loss 3.7610 (3.7690)	grad_norm 1.1112 (1.2379)	
[2022-01-20 13:18:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][720/1251]	eta 0:19:39 lr 0.000781	time 1.8080 (2.2211)	loss 3.7300 (3.7683)	grad_norm 1.1575 (1.2370)	
[2022-01-20 13:19:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][730/1251]	eta 0:19:16 lr 0.000781	time 1.5585 (2.2191)	loss 4.2965 (3.7730)	grad_norm 1.2248 (1.2367)	
[2022-01-20 13:19:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][740/1251]	eta 0:18:54 lr 0.000781	time 3.4937 (2.2196)	loss 4.1117 (3.7707)	grad_norm 1.1501 (1.2369)	
[2022-01-20 13:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][750/1251]	eta 0:18:33 lr 0.000781	time 3.7315 (2.2220)	loss 4.3039 (3.7731)	grad_norm 1.3443 (1.2370)	
[2022-01-20 13:20:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][760/1251]	eta 0:18:10 lr 0.000781	time 1.8618 (2.2209)	loss 3.6727 (3.7755)	grad_norm 1.1888 (1.2371)	
[2022-01-20 13:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][770/1251]	eta 0:17:47 lr 0.000781	time 1.8707 (2.2189)	loss 4.0291 (3.7771)	grad_norm 1.2901 (1.2374)	
[2022-01-20 13:21:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][780/1251]	eta 0:17:24 lr 0.000781	time 2.9276 (2.2182)	loss 2.7991 (3.7766)	grad_norm 1.1756 (1.2385)	
[2022-01-20 13:21:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][790/1251]	eta 0:17:02 lr 0.000781	time 3.0241 (2.2180)	loss 4.1607 (3.7769)	grad_norm 1.2425 (1.2379)	
[2022-01-20 13:21:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][800/1251]	eta 0:16:39 lr 0.000780	time 1.9431 (2.2159)	loss 3.0123 (3.7775)	grad_norm 1.0722 (1.2369)	
[2022-01-20 13:22:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][810/1251]	eta 0:16:16 lr 0.000780	time 2.6072 (2.2145)	loss 4.1315 (3.7755)	grad_norm 1.0982 (1.2368)	
[2022-01-20 13:22:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][820/1251]	eta 0:15:53 lr 0.000780	time 1.9589 (2.2130)	loss 4.5526 (3.7741)	grad_norm 1.3005 (1.2375)	
[2022-01-20 13:22:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][830/1251]	eta 0:15:31 lr 0.000780	time 2.7043 (2.2115)	loss 4.2811 (3.7731)	grad_norm 1.1638 (1.2368)	
[2022-01-20 13:23:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][840/1251]	eta 0:15:09 lr 0.000780	time 2.1641 (2.2119)	loss 3.0041 (3.7731)	grad_norm 1.0773 (1.2358)	
[2022-01-20 13:23:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][850/1251]	eta 0:14:47 lr 0.000780	time 2.8799 (2.2140)	loss 4.1097 (3.7721)	grad_norm 1.1858 (1.2352)	
[2022-01-20 13:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][860/1251]	eta 0:14:25 lr 0.000780	time 1.5588 (2.2135)	loss 3.9673 (3.7739)	grad_norm 1.1518 (1.2348)	
[2022-01-20 13:24:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][870/1251]	eta 0:14:03 lr 0.000780	time 1.8216 (2.2132)	loss 3.8213 (3.7767)	grad_norm 1.1608 (1.2338)	
[2022-01-20 13:24:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][880/1251]	eta 0:13:40 lr 0.000780	time 2.2438 (2.2123)	loss 3.3290 (3.7726)	grad_norm 1.2048 (1.2346)	
[2022-01-20 13:25:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][890/1251]	eta 0:13:17 lr 0.000780	time 2.1435 (2.2100)	loss 2.4168 (3.7728)	grad_norm 1.0882 (1.2345)	
[2022-01-20 13:25:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][900/1251]	eta 0:12:54 lr 0.000780	time 1.8885 (2.2080)	loss 2.7387 (3.7714)	grad_norm 1.2548 (1.2347)	
[2022-01-20 13:25:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][910/1251]	eta 0:12:32 lr 0.000780	time 1.5926 (2.2066)	loss 3.7189 (3.7700)	grad_norm 1.0492 (1.2346)	
[2022-01-20 13:26:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][920/1251]	eta 0:12:10 lr 0.000780	time 1.8283 (2.2072)	loss 3.9884 (3.7689)	grad_norm 1.3302 (1.2342)	
[2022-01-20 13:26:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][930/1251]	eta 0:11:48 lr 0.000780	time 1.8471 (2.2079)	loss 3.9605 (3.7701)	grad_norm 1.3951 (1.2343)	
[2022-01-20 13:26:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][940/1251]	eta 0:11:27 lr 0.000780	time 2.1286 (2.2102)	loss 4.3050 (3.7710)	grad_norm 1.3574 (1.2354)	
[2022-01-20 13:27:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][950/1251]	eta 0:11:05 lr 0.000780	time 1.6147 (2.2095)	loss 3.5526 (3.7696)	grad_norm 1.1938 (1.2363)	
[2022-01-20 13:27:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][960/1251]	eta 0:10:42 lr 0.000780	time 1.8671 (2.2090)	loss 3.1356 (3.7668)	grad_norm 1.1545 (1.2367)	
[2022-01-20 13:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][970/1251]	eta 0:10:20 lr 0.000780	time 1.8241 (2.2073)	loss 3.3406 (3.7669)	grad_norm 1.2684 (1.2365)	
[2022-01-20 13:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][980/1251]	eta 0:09:57 lr 0.000780	time 1.7992 (2.2065)	loss 3.5291 (3.7689)	grad_norm 1.0743 (1.2355)	
[2022-01-20 13:28:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][990/1251]	eta 0:09:35 lr 0.000780	time 1.9536 (2.2060)	loss 3.2655 (3.7689)	grad_norm 1.5587 (1.2354)	
[2022-01-20 13:29:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1000/1251]	eta 0:09:14 lr 0.000780	time 1.8406 (2.2074)	loss 4.4867 (3.7674)	grad_norm 1.1677 (1.2358)	
[2022-01-20 13:29:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1010/1251]	eta 0:08:51 lr 0.000780	time 2.5304 (2.2065)	loss 3.4162 (3.7653)	grad_norm 1.2840 (1.2372)	
[2022-01-20 13:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1020/1251]	eta 0:08:29 lr 0.000780	time 2.2489 (2.2064)	loss 4.1188 (3.7657)	grad_norm 1.1494 (1.2368)	
[2022-01-20 13:30:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1030/1251]	eta 0:08:07 lr 0.000780	time 1.8563 (2.2070)	loss 4.6870 (3.7639)	grad_norm 1.2526 (1.2361)	
[2022-01-20 13:30:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1040/1251]	eta 0:07:46 lr 0.000780	time 2.4250 (2.2091)	loss 4.8089 (3.7681)	grad_norm 1.4778 (1.2359)	
[2022-01-20 13:30:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1050/1251]	eta 0:07:24 lr 0.000780	time 2.6336 (2.2096)	loss 3.3513 (3.7663)	grad_norm 1.2356 (1.2365)	
[2022-01-20 13:31:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1060/1251]	eta 0:07:01 lr 0.000780	time 1.8314 (2.2087)	loss 4.0847 (3.7676)	grad_norm 1.3896 (1.2374)	
[2022-01-20 13:31:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1070/1251]	eta 0:06:39 lr 0.000780	time 1.5884 (2.2069)	loss 3.0832 (3.7661)	grad_norm 1.1384 (1.2377)	
[2022-01-20 13:31:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1080/1251]	eta 0:06:17 lr 0.000780	time 2.2556 (2.2073)	loss 4.0927 (3.7667)	grad_norm 1.2605 (1.2374)	
[2022-01-20 13:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1090/1251]	eta 0:05:55 lr 0.000779	time 1.5840 (2.2066)	loss 3.4131 (3.7657)	grad_norm 1.3620 (1.2371)	
[2022-01-20 13:32:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1100/1251]	eta 0:05:33 lr 0.000779	time 1.8886 (2.2060)	loss 3.5775 (3.7669)	grad_norm 1.1846 (1.2367)	
[2022-01-20 13:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1110/1251]	eta 0:05:10 lr 0.000779	time 1.9309 (2.2054)	loss 3.4165 (3.7662)	grad_norm 1.2776 (1.2364)	
[2022-01-20 13:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1120/1251]	eta 0:04:48 lr 0.000779	time 2.5995 (2.2058)	loss 4.0343 (3.7646)	grad_norm 1.2399 (1.2365)	
[2022-01-20 13:33:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1130/1251]	eta 0:04:26 lr 0.000779	time 1.9474 (2.2054)	loss 3.8422 (3.7648)	grad_norm 1.1600 (1.2373)	
[2022-01-20 13:34:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1140/1251]	eta 0:04:04 lr 0.000779	time 1.8571 (2.2056)	loss 3.5964 (3.7625)	grad_norm 1.3613 (1.2369)	
[2022-01-20 13:34:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1150/1251]	eta 0:03:42 lr 0.000779	time 2.0531 (2.2050)	loss 3.2547 (3.7623)	grad_norm 1.1722 (1.2376)	
[2022-01-20 13:34:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1160/1251]	eta 0:03:20 lr 0.000779	time 1.8989 (2.2064)	loss 4.2761 (3.7628)	grad_norm 1.1770 (1.2379)	
[2022-01-20 13:35:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1170/1251]	eta 0:02:58 lr 0.000779	time 1.9261 (2.2054)	loss 4.3688 (3.7665)	grad_norm 1.2366 (1.2382)	
[2022-01-20 13:35:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1180/1251]	eta 0:02:36 lr 0.000779	time 1.5784 (2.2043)	loss 3.5396 (3.7662)	grad_norm 1.1551 (1.2387)	
[2022-01-20 13:35:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1190/1251]	eta 0:02:14 lr 0.000779	time 2.0989 (2.2041)	loss 4.1848 (3.7656)	grad_norm 1.1940 (1.2383)	
[2022-01-20 13:36:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1200/1251]	eta 0:01:52 lr 0.000779	time 1.7841 (2.2024)	loss 3.4449 (3.7640)	grad_norm 1.3523 (1.2383)	
[2022-01-20 13:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1210/1251]	eta 0:01:30 lr 0.000779	time 2.5685 (2.2034)	loss 4.2988 (3.7644)	grad_norm 1.1424 (1.2377)	
[2022-01-20 13:37:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1220/1251]	eta 0:01:08 lr 0.000779	time 2.1984 (2.2058)	loss 4.0798 (3.7661)	grad_norm 1.2741 (1.2374)	
[2022-01-20 13:37:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1230/1251]	eta 0:00:46 lr 0.000779	time 2.4548 (2.2057)	loss 4.3482 (3.7656)	grad_norm 1.2187 (1.2368)	
[2022-01-20 13:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1240/1251]	eta 0:00:24 lr 0.000779	time 1.6618 (2.2052)	loss 3.4185 (3.7657)	grad_norm 1.3379 (1.2372)	
[2022-01-20 13:38:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [93/300][1250/1251]	eta 0:00:02 lr 0.000779	time 1.1659 (2.1989)	loss 4.1051 (3.7664)	grad_norm 1.2511 (1.2372)	
[2022-01-20 13:38:02 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 93 training takes 0:45:51
[2022-01-20 13:38:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.585 (18.585)	Loss 1.1304 (1.1304)	Acc@1 72.949 (72.949)	Acc@5 91.797 (91.797)	
[2022-01-20 13:38:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.904 (3.447)	Loss 1.1671 (1.1196)	Acc@1 74.219 (74.361)	Acc@5 91.602 (92.108)	
[2022-01-20 13:38:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.580 (2.727)	Loss 1.0658 (1.1350)	Acc@1 75.879 (73.796)	Acc@5 93.066 (92.067)	
[2022-01-20 13:39:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.937 (2.291)	Loss 1.1298 (1.1440)	Acc@1 73.730 (73.538)	Acc@5 92.383 (91.961)	
[2022-01-20 13:39:32 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.273 (2.202)	Loss 1.1361 (1.1440)	Acc@1 73.828 (73.438)	Acc@5 91.992 (91.964)	
[2022-01-20 13:39:40 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.402 Acc@5 91.970
[2022-01-20 13:39:40 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.4%
[2022-01-20 13:39:40 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.72%
[2022-01-20 13:40:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][0/1251]	eta 7:31:33 lr 0.000779	time 21.6572 (21.6572)	loss 3.6734 (3.6734)	grad_norm 1.1462 (1.1462)	
[2022-01-20 13:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][10/1251]	eta 1:25:40 lr 0.000779	time 2.7290 (4.1419)	loss 4.0455 (3.8429)	grad_norm 1.0280 (1.1414)	
[2022-01-20 13:40:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][20/1251]	eta 1:05:36 lr 0.000779	time 1.9269 (3.1975)	loss 4.2341 (3.6838)	grad_norm 1.1786 (1.2001)	
[2022-01-20 13:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][30/1251]	eta 0:58:46 lr 0.000779	time 1.9215 (2.8880)	loss 4.1867 (3.7084)	grad_norm 1.5053 (1.2341)	
[2022-01-20 13:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][40/1251]	eta 0:56:02 lr 0.000779	time 5.4699 (2.7763)	loss 3.2467 (3.6781)	grad_norm 1.1912 (1.2327)	
[2022-01-20 13:41:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][50/1251]	eta 0:52:56 lr 0.000779	time 2.8336 (2.6449)	loss 3.9833 (3.7088)	grad_norm 1.1664 (1.2267)	
[2022-01-20 13:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][60/1251]	eta 0:51:08 lr 0.000779	time 1.8181 (2.5762)	loss 4.0572 (3.6770)	grad_norm 1.1761 (1.2162)	
[2022-01-20 13:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][70/1251]	eta 0:49:14 lr 0.000779	time 1.6939 (2.5013)	loss 2.9436 (3.6866)	grad_norm 1.2880 (1.2218)	
[2022-01-20 13:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][80/1251]	eta 0:48:13 lr 0.000779	time 3.5464 (2.4712)	loss 3.7386 (3.6988)	grad_norm 1.4629 (1.2354)	
[2022-01-20 13:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][90/1251]	eta 0:46:58 lr 0.000779	time 2.1150 (2.4275)	loss 4.3693 (3.6965)	grad_norm 1.3747 (1.2490)	
[2022-01-20 13:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][100/1251]	eta 0:46:03 lr 0.000779	time 1.4879 (2.4013)	loss 4.6743 (3.7136)	grad_norm 1.3667 (1.2563)	
[2022-01-20 13:44:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][110/1251]	eta 0:45:09 lr 0.000779	time 1.5669 (2.3750)	loss 2.6254 (3.7070)	grad_norm 1.1875 (1.2538)	
[2022-01-20 13:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][120/1251]	eta 0:44:50 lr 0.000779	time 3.8367 (2.3793)	loss 4.3849 (3.6908)	grad_norm 1.5021 (1.2501)	
[2022-01-20 13:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][130/1251]	eta 0:44:08 lr 0.000778	time 2.1342 (2.3630)	loss 4.0364 (3.7123)	grad_norm 1.2321 (1.2438)	
[2022-01-20 13:45:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][140/1251]	eta 0:43:44 lr 0.000778	time 1.5317 (2.3627)	loss 3.8740 (3.7193)	grad_norm 1.2733 (1.2390)	
[2022-01-20 13:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][150/1251]	eta 0:43:13 lr 0.000778	time 1.9338 (2.3556)	loss 4.0036 (3.7338)	grad_norm 1.1791 (1.2360)	
[2022-01-20 13:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][160/1251]	eta 0:42:37 lr 0.000778	time 2.8230 (2.3443)	loss 3.4860 (3.7407)	grad_norm 1.1591 (1.2359)	
[2022-01-20 13:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][170/1251]	eta 0:41:55 lr 0.000778	time 1.9750 (2.3268)	loss 3.8010 (3.7432)	grad_norm 1.2002 (1.2421)	
[2022-01-20 13:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][180/1251]	eta 0:41:16 lr 0.000778	time 1.8730 (2.3123)	loss 4.1933 (3.7330)	grad_norm 1.3800 (1.2414)	
[2022-01-20 13:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][190/1251]	eta 0:40:45 lr 0.000778	time 2.0088 (2.3047)	loss 3.6465 (3.7396)	grad_norm 1.0844 (1.2403)	
[2022-01-20 13:47:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][200/1251]	eta 0:40:18 lr 0.000778	time 2.3556 (2.3010)	loss 2.9121 (3.7318)	grad_norm 1.3383 (1.2389)	
[2022-01-20 13:47:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][210/1251]	eta 0:39:40 lr 0.000778	time 1.8118 (2.2869)	loss 2.5258 (3.7395)	grad_norm 1.1205 (1.2391)	
[2022-01-20 13:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][220/1251]	eta 0:39:09 lr 0.000778	time 1.8021 (2.2786)	loss 4.4126 (3.7490)	grad_norm 1.1597 (1.2385)	
[2022-01-20 13:48:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][230/1251]	eta 0:38:43 lr 0.000778	time 2.4821 (2.2758)	loss 4.0727 (3.7319)	grad_norm 1.2222 (1.2399)	
[2022-01-20 13:48:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][240/1251]	eta 0:38:18 lr 0.000778	time 2.8928 (2.2740)	loss 4.4682 (3.7329)	grad_norm 1.1484 (1.2384)	
[2022-01-20 13:49:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][250/1251]	eta 0:37:47 lr 0.000778	time 1.6990 (2.2653)	loss 3.9186 (3.7355)	grad_norm 1.2781 (1.2398)	
[2022-01-20 13:49:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][260/1251]	eta 0:37:20 lr 0.000778	time 1.8171 (2.2606)	loss 3.4623 (3.7347)	grad_norm 1.2280 (1.2393)	
[2022-01-20 13:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][270/1251]	eta 0:37:00 lr 0.000778	time 1.8960 (2.2640)	loss 2.6761 (3.7196)	grad_norm 1.1288 (1.2387)	
[2022-01-20 13:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][280/1251]	eta 0:36:39 lr 0.000778	time 2.2139 (2.2648)	loss 4.1218 (3.7323)	grad_norm 1.0842 (1.2367)	
[2022-01-20 13:50:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][290/1251]	eta 0:36:08 lr 0.000778	time 1.6875 (2.2570)	loss 2.1869 (3.7266)	grad_norm 1.2949 (1.2370)	
[2022-01-20 13:50:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][300/1251]	eta 0:35:43 lr 0.000778	time 3.4604 (2.2543)	loss 3.5185 (3.7310)	grad_norm 1.4013 (1.2391)	
[2022-01-20 13:51:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][310/1251]	eta 0:35:18 lr 0.000778	time 1.8155 (2.2516)	loss 3.8927 (3.7359)	grad_norm 1.0753 (1.2384)	
[2022-01-20 13:51:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][320/1251]	eta 0:34:53 lr 0.000778	time 1.8811 (2.2488)	loss 4.0091 (3.7389)	grad_norm 1.1540 (1.2368)	
[2022-01-20 13:52:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][330/1251]	eta 0:34:27 lr 0.000778	time 2.0224 (2.2447)	loss 4.4472 (3.7496)	grad_norm 1.1976 (1.2378)	
[2022-01-20 13:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][340/1251]	eta 0:34:04 lr 0.000778	time 3.2320 (2.2443)	loss 4.3094 (3.7496)	grad_norm 1.1370 (1.2361)	
[2022-01-20 13:52:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][350/1251]	eta 0:33:40 lr 0.000778	time 1.9157 (2.2424)	loss 4.4247 (3.7485)	grad_norm 1.0479 (1.2347)	
[2022-01-20 13:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][360/1251]	eta 0:33:19 lr 0.000778	time 1.6492 (2.2444)	loss 3.6113 (3.7513)	grad_norm 1.1658 (1.2365)	
[2022-01-20 13:53:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][370/1251]	eta 0:32:58 lr 0.000778	time 2.5282 (2.2454)	loss 4.2250 (3.7535)	grad_norm 1.6001 (1.2390)	
[2022-01-20 13:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][380/1251]	eta 0:32:35 lr 0.000778	time 2.8514 (2.2455)	loss 4.1692 (3.7558)	grad_norm 1.3331 (1.2403)	
[2022-01-20 13:54:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][390/1251]	eta 0:32:13 lr 0.000778	time 1.8882 (2.2458)	loss 4.4779 (3.7558)	grad_norm 1.2790 (1.2411)	
[2022-01-20 13:54:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][400/1251]	eta 0:31:43 lr 0.000778	time 1.6922 (2.2370)	loss 3.8389 (3.7635)	grad_norm 1.2237 (1.2417)	
[2022-01-20 13:54:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][410/1251]	eta 0:31:18 lr 0.000778	time 2.1379 (2.2336)	loss 3.0202 (3.7560)	grad_norm 1.6307 (1.2450)	
[2022-01-20 13:55:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][420/1251]	eta 0:30:55 lr 0.000777	time 2.7267 (2.2331)	loss 3.7675 (3.7515)	grad_norm 1.2013 (1.2457)	
[2022-01-20 13:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][430/1251]	eta 0:30:34 lr 0.000777	time 1.8376 (2.2344)	loss 2.6110 (3.7516)	grad_norm 1.1167 (1.2444)	
[2022-01-20 13:56:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][440/1251]	eta 0:30:13 lr 0.000777	time 2.5616 (2.2356)	loss 4.2494 (3.7576)	grad_norm 1.2525 (1.2451)	
[2022-01-20 13:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][450/1251]	eta 0:29:48 lr 0.000777	time 1.9165 (2.2334)	loss 4.0803 (3.7586)	grad_norm 1.3232 (1.2460)	
[2022-01-20 13:56:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][460/1251]	eta 0:29:25 lr 0.000777	time 2.7719 (2.2326)	loss 3.8304 (3.7564)	grad_norm 1.4468 (1.2459)	
[2022-01-20 13:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][470/1251]	eta 0:29:02 lr 0.000777	time 1.8279 (2.2311)	loss 4.3622 (3.7512)	grad_norm 1.2197 (1.2452)	
[2022-01-20 13:57:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][480/1251]	eta 0:28:39 lr 0.000777	time 1.9048 (2.2296)	loss 2.7183 (3.7449)	grad_norm 1.3044 (1.2448)	
[2022-01-20 13:57:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][490/1251]	eta 0:28:16 lr 0.000777	time 1.8120 (2.2297)	loss 4.0476 (3.7403)	grad_norm 1.2433 (1.2441)	
[2022-01-20 13:58:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][500/1251]	eta 0:27:54 lr 0.000777	time 2.4012 (2.2302)	loss 4.2123 (3.7445)	grad_norm 1.1610 (1.2440)	
[2022-01-20 13:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][510/1251]	eta 0:27:30 lr 0.000777	time 1.6287 (2.2276)	loss 3.4392 (3.7492)	grad_norm 1.2018 (1.2424)	
[2022-01-20 13:59:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][520/1251]	eta 0:27:07 lr 0.000777	time 1.8438 (2.2268)	loss 4.5116 (3.7523)	grad_norm 1.1109 (1.2434)	
[2022-01-20 13:59:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][530/1251]	eta 0:26:43 lr 0.000777	time 1.6039 (2.2242)	loss 3.9241 (3.7494)	grad_norm 1.4118 (1.2440)	
[2022-01-20 13:59:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][540/1251]	eta 0:26:19 lr 0.000777	time 1.9838 (2.2209)	loss 4.0891 (3.7520)	grad_norm 1.0933 (1.2442)	
[2022-01-20 14:00:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][550/1251]	eta 0:25:56 lr 0.000777	time 2.5629 (2.2205)	loss 3.5419 (3.7474)	grad_norm 1.2119 (1.2443)	
[2022-01-20 14:00:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][560/1251]	eta 0:25:32 lr 0.000777	time 2.2089 (2.2184)	loss 2.5201 (3.7466)	grad_norm 1.4527 (1.2447)	
[2022-01-20 14:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][570/1251]	eta 0:25:09 lr 0.000777	time 1.8943 (2.2163)	loss 4.3347 (3.7430)	grad_norm 1.2406 (1.2463)	
[2022-01-20 14:01:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][580/1251]	eta 0:24:45 lr 0.000777	time 1.8973 (2.2144)	loss 3.7853 (3.7449)	grad_norm 1.1368 (1.2461)	
[2022-01-20 14:01:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][590/1251]	eta 0:24:26 lr 0.000777	time 2.8699 (2.2180)	loss 3.6888 (3.7393)	grad_norm 1.2639 (1.2468)	
[2022-01-20 14:01:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][600/1251]	eta 0:24:04 lr 0.000777	time 2.4948 (2.2191)	loss 2.7437 (3.7407)	grad_norm 1.0051 (1.2467)	
[2022-01-20 14:02:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][610/1251]	eta 0:23:43 lr 0.000777	time 2.5423 (2.2210)	loss 3.6943 (3.7432)	grad_norm 1.4097 (1.2479)	
[2022-01-20 14:02:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][620/1251]	eta 0:23:20 lr 0.000777	time 2.0040 (2.2198)	loss 4.0835 (3.7420)	grad_norm 1.1790 (1.2469)	
[2022-01-20 14:02:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][630/1251]	eta 0:22:56 lr 0.000777	time 1.9498 (2.2159)	loss 2.6459 (3.7393)	grad_norm 1.1068 (1.2469)	
[2022-01-20 14:03:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][640/1251]	eta 0:22:32 lr 0.000777	time 1.8714 (2.2132)	loss 2.8566 (3.7365)	grad_norm 1.2495 (1.2455)	
[2022-01-20 14:03:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][650/1251]	eta 0:22:08 lr 0.000777	time 2.1153 (2.2104)	loss 3.8927 (3.7382)	grad_norm 1.2491 (1.2457)	
[2022-01-20 14:04:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][660/1251]	eta 0:21:45 lr 0.000777	time 1.9296 (2.2098)	loss 3.8951 (3.7391)	grad_norm 1.1806 (1.2470)	
[2022-01-20 14:04:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][670/1251]	eta 0:21:23 lr 0.000777	time 2.2538 (2.2099)	loss 3.9114 (3.7439)	grad_norm 1.3277 (1.2471)	
[2022-01-20 14:04:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][680/1251]	eta 0:21:02 lr 0.000777	time 2.7876 (2.2118)	loss 4.3650 (3.7425)	grad_norm 1.0690 (1.2466)	
[2022-01-20 14:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][690/1251]	eta 0:20:41 lr 0.000777	time 2.1819 (2.2137)	loss 4.2115 (3.7486)	grad_norm 1.1036 (1.2464)	
[2022-01-20 14:05:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][700/1251]	eta 0:20:19 lr 0.000777	time 1.8446 (2.2137)	loss 3.7584 (3.7501)	grad_norm 1.4735 (1.2466)	
[2022-01-20 14:05:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][710/1251]	eta 0:19:57 lr 0.000776	time 1.8860 (2.2127)	loss 3.4580 (3.7517)	grad_norm 1.3120 (1.2470)	
[2022-01-20 14:06:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][720/1251]	eta 0:19:34 lr 0.000776	time 2.5160 (2.2114)	loss 3.6080 (3.7541)	grad_norm 1.3155 (1.2465)	
[2022-01-20 14:06:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][730/1251]	eta 0:19:11 lr 0.000776	time 2.5420 (2.2109)	loss 3.9522 (3.7558)	grad_norm 1.1252 (1.2468)	
[2022-01-20 14:06:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][740/1251]	eta 0:18:49 lr 0.000776	time 2.5169 (2.2096)	loss 3.8384 (3.7534)	grad_norm 1.2088 (1.2472)	
[2022-01-20 14:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][750/1251]	eta 0:18:27 lr 0.000776	time 2.6128 (2.2106)	loss 4.5022 (3.7554)	grad_norm 1.4480 (1.2489)	
[2022-01-20 14:07:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][760/1251]	eta 0:18:05 lr 0.000776	time 2.4459 (2.2108)	loss 2.6313 (3.7567)	grad_norm 1.2611 (1.2492)	
[2022-01-20 14:08:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][770/1251]	eta 0:17:43 lr 0.000776	time 2.1327 (2.2104)	loss 3.9080 (3.7579)	grad_norm 1.2785 (1.2490)	
[2022-01-20 14:08:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][780/1251]	eta 0:17:20 lr 0.000776	time 2.2157 (2.2102)	loss 2.8997 (3.7591)	grad_norm 1.2478 (1.2484)	
[2022-01-20 14:08:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][790/1251]	eta 0:16:58 lr 0.000776	time 2.2451 (2.2103)	loss 2.7418 (3.7592)	grad_norm 1.2888 (1.2472)	
[2022-01-20 14:09:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][800/1251]	eta 0:16:36 lr 0.000776	time 2.7852 (2.2087)	loss 3.7540 (3.7585)	grad_norm 1.0718 (1.2460)	
[2022-01-20 14:09:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][810/1251]	eta 0:16:12 lr 0.000776	time 1.8782 (2.2063)	loss 2.5881 (3.7571)	grad_norm 1.3942 (1.2460)	
[2022-01-20 14:09:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][820/1251]	eta 0:15:50 lr 0.000776	time 2.6906 (2.2051)	loss 4.2099 (3.7587)	grad_norm 1.2499 (1.2472)	
[2022-01-20 14:10:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][830/1251]	eta 0:15:28 lr 0.000776	time 1.9058 (2.2051)	loss 3.7718 (3.7568)	grad_norm 1.1331 (1.2474)	
[2022-01-20 14:10:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][840/1251]	eta 0:15:06 lr 0.000776	time 3.0260 (2.2061)	loss 4.2438 (3.7533)	grad_norm 1.2153 (1.2457)	
[2022-01-20 14:11:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][850/1251]	eta 0:14:45 lr 0.000776	time 2.1666 (2.2088)	loss 4.0732 (3.7502)	grad_norm 1.2481 (1.2453)	
[2022-01-20 14:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][860/1251]	eta 0:14:24 lr 0.000776	time 1.9538 (2.2103)	loss 3.4840 (3.7519)	grad_norm 1.3692 (1.2453)	
[2022-01-20 14:11:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][870/1251]	eta 0:14:01 lr 0.000776	time 1.9134 (2.2079)	loss 4.0623 (3.7505)	grad_norm 1.3185 (1.2445)	
[2022-01-20 14:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][880/1251]	eta 0:13:38 lr 0.000776	time 1.8820 (2.2068)	loss 4.1349 (3.7520)	grad_norm 1.2243 (1.2443)	
[2022-01-20 14:12:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][890/1251]	eta 0:13:16 lr 0.000776	time 2.2749 (2.2057)	loss 3.1175 (3.7486)	grad_norm 1.3066 (1.2445)	
[2022-01-20 14:12:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][900/1251]	eta 0:12:54 lr 0.000776	time 1.8642 (2.2057)	loss 4.1279 (3.7526)	grad_norm 1.2909 (1.2450)	
[2022-01-20 14:13:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][910/1251]	eta 0:12:32 lr 0.000776	time 1.8956 (2.2053)	loss 3.0889 (3.7519)	grad_norm 1.2053 (1.2446)	
[2022-01-20 14:13:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][920/1251]	eta 0:12:09 lr 0.000776	time 2.0086 (2.2043)	loss 3.8923 (3.7504)	grad_norm 1.1105 (1.2439)	
[2022-01-20 14:13:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][930/1251]	eta 0:11:47 lr 0.000776	time 1.8461 (2.2033)	loss 3.8056 (3.7470)	grad_norm 1.2362 (1.2428)	
[2022-01-20 14:14:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][940/1251]	eta 0:11:25 lr 0.000776	time 3.1713 (2.2051)	loss 3.1181 (3.7472)	grad_norm 1.3283 (1.2432)	
[2022-01-20 14:14:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][950/1251]	eta 0:11:03 lr 0.000776	time 1.7489 (2.2041)	loss 2.6101 (3.7452)	grad_norm 1.1956 (1.2434)	
[2022-01-20 14:14:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][960/1251]	eta 0:10:41 lr 0.000776	time 2.2915 (2.2036)	loss 4.3589 (3.7463)	grad_norm 1.1679 (1.2427)	
[2022-01-20 14:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][970/1251]	eta 0:10:19 lr 0.000776	time 1.2542 (2.2037)	loss 3.4590 (3.7447)	grad_norm 1.1663 (1.2422)	
[2022-01-20 14:15:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][980/1251]	eta 0:09:57 lr 0.000776	time 2.5008 (2.2060)	loss 4.1130 (3.7455)	grad_norm 1.2720 (1.2419)	
[2022-01-20 14:16:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][990/1251]	eta 0:09:35 lr 0.000776	time 1.8318 (2.2061)	loss 3.9003 (3.7459)	grad_norm 1.1017 (1.2415)	
[2022-01-20 14:16:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1000/1251]	eta 0:09:13 lr 0.000775	time 2.1774 (2.2063)	loss 4.2654 (3.7481)	grad_norm 1.2077 (1.2419)	
[2022-01-20 14:16:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1010/1251]	eta 0:08:51 lr 0.000775	time 1.8382 (2.2062)	loss 4.0771 (3.7477)	grad_norm 1.2313 (1.2426)	
[2022-01-20 14:17:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1020/1251]	eta 0:08:29 lr 0.000775	time 2.4773 (2.2075)	loss 4.5203 (3.7464)	grad_norm 1.2877 (1.2426)	
[2022-01-20 14:17:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1030/1251]	eta 0:08:07 lr 0.000775	time 1.8907 (2.2060)	loss 4.0184 (3.7446)	grad_norm 1.3152 (1.2427)	
[2022-01-20 14:17:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1040/1251]	eta 0:07:45 lr 0.000775	time 1.8664 (2.2045)	loss 3.7399 (3.7444)	grad_norm 1.4323 (1.2422)	
[2022-01-20 14:18:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1050/1251]	eta 0:07:22 lr 0.000775	time 2.2459 (2.2036)	loss 3.9266 (3.7467)	grad_norm 1.4140 (1.2421)	
[2022-01-20 14:18:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1060/1251]	eta 0:07:01 lr 0.000775	time 2.6979 (2.2048)	loss 4.5035 (3.7481)	grad_norm 1.1607 (1.2423)	
[2022-01-20 14:19:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1070/1251]	eta 0:06:39 lr 0.000775	time 2.0936 (2.2048)	loss 2.9770 (3.7478)	grad_norm 1.1132 (1.2419)	
[2022-01-20 14:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1080/1251]	eta 0:06:16 lr 0.000775	time 1.6853 (2.2037)	loss 2.8548 (3.7481)	grad_norm 1.1511 (1.2416)	
[2022-01-20 14:19:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1090/1251]	eta 0:05:54 lr 0.000775	time 2.6512 (2.2030)	loss 3.5113 (3.7457)	grad_norm 1.2440 (1.2412)	
[2022-01-20 14:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1100/1251]	eta 0:05:32 lr 0.000775	time 3.0983 (2.2043)	loss 3.6562 (3.7470)	grad_norm 1.2220 (1.2411)	
[2022-01-20 14:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1110/1251]	eta 0:05:10 lr 0.000775	time 1.8980 (2.2043)	loss 4.0281 (3.7473)	grad_norm 1.1011 (1.2411)	
[2022-01-20 14:20:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1120/1251]	eta 0:04:48 lr 0.000775	time 1.9674 (2.2026)	loss 2.5939 (3.7455)	grad_norm 1.0772 (1.2406)	
[2022-01-20 14:21:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1130/1251]	eta 0:04:26 lr 0.000775	time 2.5881 (2.2015)	loss 3.9354 (3.7460)	grad_norm 1.3361 (1.2415)	
[2022-01-20 14:21:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1140/1251]	eta 0:04:04 lr 0.000775	time 2.2259 (2.1997)	loss 4.0000 (3.7452)	grad_norm 1.1380 (1.2413)	
[2022-01-20 14:21:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1150/1251]	eta 0:03:42 lr 0.000775	time 1.7069 (2.1985)	loss 3.5534 (3.7445)	grad_norm 1.2085 (1.2410)	
[2022-01-20 14:22:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1160/1251]	eta 0:03:20 lr 0.000775	time 1.6888 (2.1985)	loss 3.1203 (3.7443)	grad_norm 1.0613 (1.2411)	
[2022-01-20 14:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1170/1251]	eta 0:02:58 lr 0.000775	time 2.5965 (2.1987)	loss 2.6694 (3.7415)	grad_norm 1.1838 (1.2407)	
[2022-01-20 14:22:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1180/1251]	eta 0:02:36 lr 0.000775	time 1.8655 (2.1980)	loss 4.3033 (3.7426)	grad_norm 1.0838 (1.2407)	
[2022-01-20 14:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1190/1251]	eta 0:02:14 lr 0.000775	time 1.9232 (2.1990)	loss 3.4776 (3.7401)	grad_norm 1.1431 (1.2402)	
[2022-01-20 14:23:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1200/1251]	eta 0:01:52 lr 0.000775	time 1.9895 (2.2001)	loss 3.1087 (3.7404)	grad_norm 1.0376 (1.2393)	
[2022-01-20 14:24:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1210/1251]	eta 0:01:30 lr 0.000775	time 2.1487 (2.2011)	loss 3.2456 (3.7403)	grad_norm 1.0653 (1.2387)	
[2022-01-20 14:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1220/1251]	eta 0:01:08 lr 0.000775	time 1.7144 (2.1998)	loss 4.2398 (3.7392)	grad_norm 1.2453 (1.2385)	
[2022-01-20 14:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1230/1251]	eta 0:00:46 lr 0.000775	time 2.1197 (2.1990)	loss 4.2528 (3.7379)	grad_norm 1.3715 (1.2389)	
[2022-01-20 14:25:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1240/1251]	eta 0:00:24 lr 0.000775	time 1.5562 (2.1976)	loss 4.0260 (3.7367)	grad_norm 1.2472 (1.2390)	
[2022-01-20 14:25:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [94/300][1250/1251]	eta 0:00:02 lr 0.000775	time 1.1787 (2.1916)	loss 4.1264 (3.7371)	grad_norm 1.5930 (1.2394)	
[2022-01-20 14:25:22 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 94 training takes 0:45:42
[2022-01-20 14:25:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.596 (18.596)	Loss 1.1059 (1.1059)	Acc@1 74.805 (74.805)	Acc@5 92.480 (92.480)	
[2022-01-20 14:25:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.607 (3.341)	Loss 1.0841 (1.1615)	Acc@1 76.270 (73.686)	Acc@5 92.578 (91.868)	
[2022-01-20 14:26:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.288 (2.564)	Loss 1.1591 (1.1565)	Acc@1 73.730 (73.624)	Acc@5 91.504 (92.006)	
[2022-01-20 14:26:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.946 (2.319)	Loss 1.1895 (1.1612)	Acc@1 73.438 (73.415)	Acc@5 91.406 (91.932)	
[2022-01-20 14:26:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.377 (2.150)	Loss 1.1428 (1.1626)	Acc@1 74.219 (73.383)	Acc@5 91.406 (91.928)	
[2022-01-20 14:26:57 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.494 Acc@5 91.908
[2022-01-20 14:26:57 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.5%
[2022-01-20 14:26:57 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.72%
[2022-01-20 14:27:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][0/1251]	eta 7:33:36 lr 0.000775	time 21.7555 (21.7555)	loss 3.9539 (3.9539)	grad_norm 1.2353 (1.2353)	
[2022-01-20 14:27:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][10/1251]	eta 1:23:46 lr 0.000775	time 2.3057 (4.0506)	loss 3.7433 (3.4003)	grad_norm 1.6619 (1.3464)	
[2022-01-20 14:28:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][20/1251]	eta 1:04:55 lr 0.000775	time 1.4750 (3.1642)	loss 3.8320 (3.5192)	grad_norm 1.0993 (1.2644)	
[2022-01-20 14:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][30/1251]	eta 0:56:57 lr 0.000774	time 1.9211 (2.7986)	loss 3.8235 (3.5036)	grad_norm 1.0196 (1.2256)	
[2022-01-20 14:28:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][40/1251]	eta 0:54:49 lr 0.000774	time 4.2734 (2.7161)	loss 4.1460 (3.5753)	grad_norm 1.3495 (1.2191)	
[2022-01-20 14:29:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][50/1251]	eta 0:52:18 lr 0.000774	time 2.4241 (2.6134)	loss 3.6416 (3.6315)	grad_norm 1.3167 (1.2256)	
[2022-01-20 14:29:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][60/1251]	eta 0:49:57 lr 0.000774	time 1.2561 (2.5170)	loss 4.2265 (3.6723)	grad_norm 1.1793 (1.2396)	
[2022-01-20 14:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][70/1251]	eta 0:48:25 lr 0.000774	time 1.5422 (2.4600)	loss 3.2668 (3.6969)	grad_norm 1.3102 (1.2526)	
[2022-01-20 14:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][80/1251]	eta 0:47:55 lr 0.000774	time 3.5408 (2.4552)	loss 4.7486 (3.7083)	grad_norm 1.1239 (1.2508)	
[2022-01-20 14:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][90/1251]	eta 0:46:57 lr 0.000774	time 2.1716 (2.4267)	loss 4.6378 (3.7526)	grad_norm 1.2952 (1.2513)	
[2022-01-20 14:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][100/1251]	eta 0:46:18 lr 0.000774	time 1.5057 (2.4142)	loss 2.9989 (3.7488)	grad_norm 1.0493 (1.2468)	
[2022-01-20 14:31:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][110/1251]	eta 0:45:29 lr 0.000774	time 1.9012 (2.3926)	loss 4.3482 (3.7553)	grad_norm 1.0623 (1.2474)	
[2022-01-20 14:31:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][120/1251]	eta 0:44:42 lr 0.000774	time 2.7491 (2.3715)	loss 4.0984 (3.7603)	grad_norm 1.6634 (1.2501)	
[2022-01-20 14:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][130/1251]	eta 0:43:50 lr 0.000774	time 1.8497 (2.3468)	loss 3.3744 (3.7410)	grad_norm 1.3507 (1.2477)	
[2022-01-20 14:32:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][140/1251]	eta 0:43:20 lr 0.000774	time 2.2923 (2.3409)	loss 4.0527 (3.7392)	grad_norm 1.3672 (1.2468)	
[2022-01-20 14:32:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][150/1251]	eta 0:42:39 lr 0.000774	time 1.9026 (2.3245)	loss 4.1631 (3.7482)	grad_norm 1.0331 (1.2419)	
[2022-01-20 14:33:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][160/1251]	eta 0:42:12 lr 0.000774	time 3.1750 (2.3212)	loss 3.8606 (3.7340)	grad_norm 1.2521 (1.2386)	
[2022-01-20 14:33:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][170/1251]	eta 0:41:31 lr 0.000774	time 2.1562 (2.3053)	loss 4.0727 (3.7294)	grad_norm 1.3981 (1.2362)	
[2022-01-20 14:33:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][180/1251]	eta 0:40:53 lr 0.000774	time 1.6165 (2.2909)	loss 3.2971 (3.7300)	grad_norm 1.1337 (1.2327)	
[2022-01-20 14:34:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][190/1251]	eta 0:40:24 lr 0.000774	time 1.6843 (2.2854)	loss 4.3581 (3.7256)	grad_norm 1.1012 (1.2332)	
[2022-01-20 14:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][200/1251]	eta 0:40:16 lr 0.000774	time 3.1545 (2.2993)	loss 3.1766 (3.7249)	grad_norm 1.2574 (1.2371)	
[2022-01-20 14:35:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][210/1251]	eta 0:39:54 lr 0.000774	time 1.7665 (2.3006)	loss 3.8063 (3.7262)	grad_norm 1.1253 (1.2414)	
[2022-01-20 14:35:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][220/1251]	eta 0:39:30 lr 0.000774	time 1.8655 (2.2992)	loss 4.0528 (3.7350)	grad_norm 1.3476 (1.2432)	
[2022-01-20 14:35:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][230/1251]	eta 0:38:52 lr 0.000774	time 1.8487 (2.2849)	loss 2.6379 (3.7309)	grad_norm 1.2563 (1.2459)	
[2022-01-20 14:36:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][240/1251]	eta 0:38:22 lr 0.000774	time 2.1177 (2.2779)	loss 3.8977 (3.7365)	grad_norm 1.2486 (1.2468)	
[2022-01-20 14:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][250/1251]	eta 0:37:56 lr 0.000774	time 2.1533 (2.2741)	loss 4.3540 (3.7411)	grad_norm 1.1658 (1.2461)	
[2022-01-20 14:36:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][260/1251]	eta 0:37:33 lr 0.000774	time 2.1378 (2.2736)	loss 3.6402 (3.7343)	grad_norm 1.0701 (1.2451)	
[2022-01-20 14:37:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][270/1251]	eta 0:37:07 lr 0.000774	time 2.0363 (2.2708)	loss 3.8997 (3.7409)	grad_norm 1.3354 (1.2476)	
[2022-01-20 14:37:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][280/1251]	eta 0:36:37 lr 0.000774	time 2.1991 (2.2628)	loss 4.1531 (3.7432)	grad_norm 1.1823 (1.2480)	
[2022-01-20 14:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][290/1251]	eta 0:36:08 lr 0.000774	time 1.8944 (2.2563)	loss 3.1383 (3.7448)	grad_norm 1.3913 (1.2487)	
[2022-01-20 14:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][300/1251]	eta 0:35:46 lr 0.000774	time 1.5283 (2.2573)	loss 4.4863 (3.7578)	grad_norm 1.1178 (1.2451)	
[2022-01-20 14:38:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][310/1251]	eta 0:35:24 lr 0.000774	time 1.8093 (2.2573)	loss 3.6626 (3.7568)	grad_norm 1.1183 (1.2430)	
[2022-01-20 14:39:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][320/1251]	eta 0:34:57 lr 0.000773	time 2.0777 (2.2530)	loss 2.8954 (3.7550)	grad_norm 1.2645 (1.2433)	
[2022-01-20 14:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][330/1251]	eta 0:34:30 lr 0.000773	time 2.0637 (2.2481)	loss 4.2479 (3.7566)	grad_norm 1.3061 (1.2437)	
[2022-01-20 14:39:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][340/1251]	eta 0:34:07 lr 0.000773	time 2.1354 (2.2472)	loss 4.5651 (3.7675)	grad_norm 1.1845 (1.2420)	
[2022-01-20 14:40:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][350/1251]	eta 0:33:44 lr 0.000773	time 2.5133 (2.2466)	loss 3.2157 (3.7634)	grad_norm 1.2610 (1.2419)	
[2022-01-20 14:40:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][360/1251]	eta 0:33:20 lr 0.000773	time 1.5654 (2.2451)	loss 2.8373 (3.7622)	grad_norm 1.1296 (1.2413)	
[2022-01-20 14:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][370/1251]	eta 0:32:58 lr 0.000773	time 2.1370 (2.2455)	loss 3.6931 (3.7653)	grad_norm 1.2801 (1.2410)	
[2022-01-20 14:41:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][380/1251]	eta 0:32:36 lr 0.000773	time 1.8746 (2.2464)	loss 2.8879 (3.7623)	grad_norm 1.1243 (1.2414)	
[2022-01-20 14:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][390/1251]	eta 0:32:12 lr 0.000773	time 2.1050 (2.2441)	loss 2.7867 (3.7644)	grad_norm 1.2852 (1.2421)	
[2022-01-20 14:41:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][400/1251]	eta 0:31:45 lr 0.000773	time 1.8062 (2.2396)	loss 4.2400 (3.7612)	grad_norm 1.0604 (1.2427)	
[2022-01-20 14:42:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][410/1251]	eta 0:31:20 lr 0.000773	time 1.8458 (2.2360)	loss 3.6690 (3.7616)	grad_norm 1.2760 (1.2408)	
[2022-01-20 14:42:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][420/1251]	eta 0:30:58 lr 0.000773	time 2.1354 (2.2369)	loss 3.3599 (3.7519)	grad_norm 1.1405 (1.2394)	
[2022-01-20 14:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][430/1251]	eta 0:30:33 lr 0.000773	time 1.7729 (2.2338)	loss 4.2475 (3.7513)	grad_norm 1.1568 (1.2385)	
[2022-01-20 14:43:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][440/1251]	eta 0:30:11 lr 0.000773	time 2.8687 (2.2341)	loss 4.0369 (3.7534)	grad_norm 1.2215 (1.2378)	
[2022-01-20 14:43:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][450/1251]	eta 0:29:48 lr 0.000773	time 1.5437 (2.2326)	loss 3.8429 (3.7464)	grad_norm 1.0897 (1.2372)	
[2022-01-20 14:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][460/1251]	eta 0:29:26 lr 0.000773	time 2.1871 (2.2330)	loss 4.5406 (3.7498)	grad_norm 1.3158 (1.2390)	
[2022-01-20 14:44:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][470/1251]	eta 0:29:03 lr 0.000773	time 2.0258 (2.2328)	loss 2.8214 (3.7481)	grad_norm 1.0964 (1.2382)	
[2022-01-20 14:44:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][480/1251]	eta 0:28:41 lr 0.000773	time 2.8584 (2.2328)	loss 3.7465 (3.7500)	grad_norm 1.1144 (1.2381)	
[2022-01-20 14:45:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][490/1251]	eta 0:28:17 lr 0.000773	time 1.7154 (2.2308)	loss 3.9839 (3.7483)	grad_norm 1.2229 (1.2381)	
[2022-01-20 14:45:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][500/1251]	eta 0:27:55 lr 0.000773	time 2.1189 (2.2311)	loss 2.4982 (3.7438)	grad_norm 1.0568 (1.2375)	
[2022-01-20 14:45:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][510/1251]	eta 0:27:31 lr 0.000773	time 1.8674 (2.2286)	loss 3.7486 (3.7447)	grad_norm 1.1812 (1.2375)	
[2022-01-20 14:46:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][520/1251]	eta 0:27:07 lr 0.000773	time 2.5418 (2.2268)	loss 4.1488 (3.7491)	grad_norm 1.5149 (1.2379)	
[2022-01-20 14:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][530/1251]	eta 0:26:43 lr 0.000773	time 1.8558 (2.2242)	loss 3.0346 (3.7459)	grad_norm 1.0013 (1.2370)	
[2022-01-20 14:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][540/1251]	eta 0:26:20 lr 0.000773	time 2.2672 (2.2233)	loss 4.7155 (3.7505)	grad_norm 1.2181 (1.2370)	
[2022-01-20 14:47:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][550/1251]	eta 0:26:00 lr 0.000773	time 3.4209 (2.2264)	loss 3.6374 (3.7541)	grad_norm 1.0970 (1.2386)	
[2022-01-20 14:47:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][560/1251]	eta 0:25:39 lr 0.000773	time 2.5421 (2.2274)	loss 4.4338 (3.7544)	grad_norm 1.2111 (1.2377)	
[2022-01-20 14:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][570/1251]	eta 0:25:17 lr 0.000773	time 1.5292 (2.2278)	loss 4.0795 (3.7569)	grad_norm 1.2852 (1.2396)	
[2022-01-20 14:48:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][580/1251]	eta 0:24:51 lr 0.000773	time 1.7541 (2.2235)	loss 3.2766 (3.7608)	grad_norm 1.1604 (1.2398)	
[2022-01-20 14:48:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][590/1251]	eta 0:24:29 lr 0.000773	time 2.1584 (2.2224)	loss 3.7880 (3.7594)	grad_norm 1.2640 (1.2398)	
[2022-01-20 14:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][600/1251]	eta 0:24:04 lr 0.000773	time 1.7543 (2.2191)	loss 2.5912 (3.7520)	grad_norm 1.1953 (1.2401)	
[2022-01-20 14:49:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][610/1251]	eta 0:23:42 lr 0.000772	time 2.1815 (2.2191)	loss 2.8010 (3.7514)	grad_norm 1.2152 (1.2401)	
[2022-01-20 14:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][620/1251]	eta 0:23:18 lr 0.000772	time 1.9182 (2.2171)	loss 4.1888 (3.7508)	grad_norm 1.1089 (1.2392)	
[2022-01-20 14:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][630/1251]	eta 0:22:56 lr 0.000772	time 2.2624 (2.2158)	loss 3.7220 (3.7504)	grad_norm 1.1534 (1.2387)	
[2022-01-20 14:50:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][640/1251]	eta 0:22:33 lr 0.000772	time 1.5016 (2.2153)	loss 3.9620 (3.7524)	grad_norm 1.1755 (1.2376)	
[2022-01-20 14:50:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][650/1251]	eta 0:22:10 lr 0.000772	time 1.9437 (2.2143)	loss 4.4942 (3.7485)	grad_norm 1.3281 (1.2378)	
[2022-01-20 14:51:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][660/1251]	eta 0:21:48 lr 0.000772	time 2.2792 (2.2146)	loss 3.5426 (3.7542)	grad_norm 1.1938 (1.2397)	
[2022-01-20 14:51:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][670/1251]	eta 0:21:28 lr 0.000772	time 2.5514 (2.2171)	loss 4.0822 (3.7528)	grad_norm 1.2637 (1.2396)	
[2022-01-20 14:52:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][680/1251]	eta 0:21:06 lr 0.000772	time 1.6624 (2.2174)	loss 2.7727 (3.7474)	grad_norm 1.3618 (1.2398)	
[2022-01-20 14:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][690/1251]	eta 0:20:42 lr 0.000772	time 1.8396 (2.2143)	loss 4.0851 (3.7427)	grad_norm 1.6156 (1.2402)	
[2022-01-20 14:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][700/1251]	eta 0:20:19 lr 0.000772	time 1.8560 (2.2130)	loss 3.3506 (3.7455)	grad_norm 1.3267 (1.2405)	
[2022-01-20 14:53:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][710/1251]	eta 0:19:58 lr 0.000772	time 2.4868 (2.2155)	loss 4.1558 (3.7449)	grad_norm 1.1961 (1.2417)	
[2022-01-20 14:53:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][720/1251]	eta 0:19:37 lr 0.000772	time 1.6551 (2.2170)	loss 4.4333 (3.7419)	grad_norm 1.2259 (1.2412)	
[2022-01-20 14:53:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][730/1251]	eta 0:19:14 lr 0.000772	time 1.6482 (2.2158)	loss 3.9996 (3.7401)	grad_norm 1.2239 (1.2411)	
[2022-01-20 14:54:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][740/1251]	eta 0:18:51 lr 0.000772	time 1.5912 (2.2140)	loss 3.8099 (3.7388)	grad_norm 1.1269 (1.2413)	
[2022-01-20 14:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][750/1251]	eta 0:18:28 lr 0.000772	time 3.0258 (2.2134)	loss 3.7400 (3.7371)	grad_norm 1.1825 (1.2414)	
[2022-01-20 14:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][760/1251]	eta 0:18:06 lr 0.000772	time 2.1470 (2.2122)	loss 4.0946 (3.7346)	grad_norm 1.3103 (1.2416)	
[2022-01-20 14:55:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][770/1251]	eta 0:17:43 lr 0.000772	time 2.2825 (2.2115)	loss 3.9560 (3.7362)	grad_norm 1.3059 (1.2417)	
[2022-01-20 14:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][780/1251]	eta 0:17:21 lr 0.000772	time 1.9549 (2.2106)	loss 4.2852 (3.7377)	grad_norm 1.4402 (1.2419)	
[2022-01-20 14:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][790/1251]	eta 0:16:59 lr 0.000772	time 2.4524 (2.2104)	loss 3.8072 (3.7369)	grad_norm 1.1499 (1.2419)	
[2022-01-20 14:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][800/1251]	eta 0:16:36 lr 0.000772	time 2.2577 (2.2106)	loss 3.6380 (3.7387)	grad_norm 1.0990 (1.2418)	
[2022-01-20 14:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][810/1251]	eta 0:16:14 lr 0.000772	time 1.9308 (2.2109)	loss 3.5493 (3.7378)	grad_norm 1.2203 (1.2410)	
[2022-01-20 14:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][820/1251]	eta 0:15:52 lr 0.000772	time 2.7017 (2.2101)	loss 3.4651 (3.7357)	grad_norm 1.0802 (1.2413)	
[2022-01-20 14:57:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][830/1251]	eta 0:15:29 lr 0.000772	time 1.7586 (2.2086)	loss 4.5869 (3.7379)	grad_norm 1.2011 (1.2412)	
[2022-01-20 14:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][840/1251]	eta 0:15:07 lr 0.000772	time 2.4988 (2.2086)	loss 4.3059 (3.7401)	grad_norm 1.1188 (1.2406)	
[2022-01-20 14:58:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][850/1251]	eta 0:14:44 lr 0.000772	time 1.8775 (2.2061)	loss 3.9590 (3.7398)	grad_norm 1.3899 (1.2403)	
[2022-01-20 14:58:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][860/1251]	eta 0:14:21 lr 0.000772	time 2.6123 (2.2044)	loss 3.5742 (3.7422)	grad_norm 1.1508 (1.2400)	
[2022-01-20 14:58:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][870/1251]	eta 0:13:59 lr 0.000772	time 2.2097 (2.2040)	loss 2.5509 (3.7389)	grad_norm 1.3087 (1.2397)	
[2022-01-20 14:59:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][880/1251]	eta 0:13:38 lr 0.000772	time 2.4935 (2.2055)	loss 4.7869 (3.7388)	grad_norm 1.2520 (1.2392)	
[2022-01-20 14:59:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][890/1251]	eta 0:13:16 lr 0.000771	time 1.7993 (2.2052)	loss 3.5434 (3.7351)	grad_norm 1.2354 (1.2403)	
[2022-01-20 15:00:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][900/1251]	eta 0:12:53 lr 0.000771	time 2.1967 (2.2046)	loss 4.0804 (3.7381)	grad_norm 1.1190 (1.2403)	
[2022-01-20 15:00:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][910/1251]	eta 0:12:32 lr 0.000771	time 2.0019 (2.2061)	loss 3.6401 (3.7396)	grad_norm 1.0540 (1.2397)	
[2022-01-20 15:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][920/1251]	eta 0:12:11 lr 0.000771	time 2.5469 (2.2089)	loss 3.3710 (3.7402)	grad_norm 1.1880 (1.2398)	
[2022-01-20 15:01:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][930/1251]	eta 0:11:48 lr 0.000771	time 2.2231 (2.2081)	loss 4.0281 (3.7418)	grad_norm 1.5042 (1.2406)	
[2022-01-20 15:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][940/1251]	eta 0:11:26 lr 0.000771	time 2.4966 (2.2065)	loss 4.1651 (3.7444)	grad_norm 1.4322 (1.2407)	
[2022-01-20 15:01:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][950/1251]	eta 0:11:03 lr 0.000771	time 2.0274 (2.2055)	loss 3.5853 (3.7438)	grad_norm 1.2674 (1.2412)	
[2022-01-20 15:02:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][960/1251]	eta 0:10:41 lr 0.000771	time 2.7094 (2.2059)	loss 4.0187 (3.7436)	grad_norm 1.0589 (1.2409)	
[2022-01-20 15:02:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][970/1251]	eta 0:10:19 lr 0.000771	time 1.6128 (2.2051)	loss 3.7465 (3.7426)	grad_norm 1.4358 (1.2408)	
[2022-01-20 15:03:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][980/1251]	eta 0:09:57 lr 0.000771	time 1.5711 (2.2055)	loss 2.8675 (3.7395)	grad_norm 1.2039 (1.2408)	
[2022-01-20 15:03:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][990/1251]	eta 0:09:35 lr 0.000771	time 1.8555 (2.2047)	loss 3.9802 (3.7388)	grad_norm 1.3429 (1.2408)	
[2022-01-20 15:03:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1000/1251]	eta 0:09:13 lr 0.000771	time 2.7816 (2.2054)	loss 3.1757 (3.7382)	grad_norm 1.1581 (1.2406)	
[2022-01-20 15:04:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1010/1251]	eta 0:08:51 lr 0.000771	time 2.1987 (2.2063)	loss 4.3382 (3.7400)	grad_norm 1.0705 (1.2399)	
[2022-01-20 15:04:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1020/1251]	eta 0:08:29 lr 0.000771	time 2.0966 (2.2071)	loss 3.7513 (3.7380)	grad_norm 1.1936 (1.2404)	
[2022-01-20 15:04:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1030/1251]	eta 0:08:07 lr 0.000771	time 1.9007 (2.2059)	loss 3.9476 (3.7369)	grad_norm 1.2943 (1.2398)	
[2022-01-20 15:05:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1040/1251]	eta 0:07:45 lr 0.000771	time 2.2174 (2.2046)	loss 4.4447 (3.7376)	grad_norm 1.2311 (1.2394)	
[2022-01-20 15:05:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1050/1251]	eta 0:07:22 lr 0.000771	time 1.6066 (2.2028)	loss 3.3448 (3.7368)	grad_norm 1.4304 (1.2400)	
[2022-01-20 15:05:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1060/1251]	eta 0:07:00 lr 0.000771	time 1.9515 (2.2017)	loss 4.5855 (3.7386)	grad_norm 1.5506 (1.2406)	
[2022-01-20 15:06:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1070/1251]	eta 0:06:38 lr 0.000771	time 1.8648 (2.2006)	loss 4.3949 (3.7384)	grad_norm 1.2777 (1.2405)	
[2022-01-20 15:06:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1080/1251]	eta 0:06:16 lr 0.000771	time 2.1488 (2.2005)	loss 3.4417 (3.7376)	grad_norm 1.5488 (1.2406)	
[2022-01-20 15:06:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1090/1251]	eta 0:05:54 lr 0.000771	time 2.4720 (2.2016)	loss 4.6741 (3.7392)	grad_norm 1.3088 (1.2408)	
[2022-01-20 15:07:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1100/1251]	eta 0:05:32 lr 0.000771	time 2.4922 (2.2027)	loss 4.5306 (3.7411)	grad_norm 1.3557 (1.2405)	
[2022-01-20 15:07:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1110/1251]	eta 0:05:10 lr 0.000771	time 1.8024 (2.2017)	loss 2.7481 (3.7392)	grad_norm 1.2278 (1.2402)	
[2022-01-20 15:08:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1120/1251]	eta 0:04:48 lr 0.000771	time 1.8998 (2.2010)	loss 4.2384 (3.7375)	grad_norm 1.1940 (1.2399)	
[2022-01-20 15:08:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1130/1251]	eta 0:04:26 lr 0.000771	time 1.9377 (2.2009)	loss 2.9689 (3.7387)	grad_norm 1.2058 (1.2399)	
[2022-01-20 15:08:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1140/1251]	eta 0:04:04 lr 0.000771	time 2.2134 (2.2008)	loss 4.6041 (3.7412)	grad_norm 1.1704 (1.2399)	
[2022-01-20 15:09:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1150/1251]	eta 0:03:42 lr 0.000771	time 2.2186 (2.2010)	loss 4.3207 (3.7393)	grad_norm 1.1497 (1.2401)	
[2022-01-20 15:09:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1160/1251]	eta 0:03:20 lr 0.000771	time 1.9909 (2.2006)	loss 4.2083 (3.7374)	grad_norm 0.9985 (1.2397)	
[2022-01-20 15:09:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1170/1251]	eta 0:02:58 lr 0.000771	time 2.0769 (2.2003)	loss 3.9533 (3.7382)	grad_norm 1.1656 (1.2389)	
[2022-01-20 15:10:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1180/1251]	eta 0:02:36 lr 0.000770	time 2.1791 (2.2004)	loss 2.9201 (3.7373)	grad_norm 1.3471 (1.2396)	
[2022-01-20 15:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1190/1251]	eta 0:02:14 lr 0.000770	time 2.7928 (2.1996)	loss 3.7690 (3.7361)	grad_norm 1.2254 (1.2400)	
[2022-01-20 15:10:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1200/1251]	eta 0:01:52 lr 0.000770	time 2.3211 (2.1986)	loss 3.8471 (3.7383)	grad_norm 1.2296 (1.2400)	
[2022-01-20 15:11:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1210/1251]	eta 0:01:30 lr 0.000770	time 1.6161 (2.1971)	loss 4.3072 (3.7388)	grad_norm 1.1958 (1.2399)	
[2022-01-20 15:11:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1220/1251]	eta 0:01:08 lr 0.000770	time 2.7884 (2.1979)	loss 3.6830 (3.7397)	grad_norm 1.1210 (1.2393)	
[2022-01-20 15:12:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1230/1251]	eta 0:00:46 lr 0.000770	time 1.8545 (2.1971)	loss 3.5765 (3.7409)	grad_norm 1.1686 (1.2396)	
[2022-01-20 15:12:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1240/1251]	eta 0:00:24 lr 0.000770	time 2.0057 (2.1974)	loss 4.3545 (3.7404)	grad_norm 1.1828 (1.2401)	
[2022-01-20 15:12:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [95/300][1250/1251]	eta 0:00:02 lr 0.000770	time 1.2865 (2.1930)	loss 4.2889 (3.7393)	grad_norm 1.2015 (1.2402)	
[2022-01-20 15:12:41 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 95 training takes 0:45:43
[2022-01-20 15:12:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.321 (18.321)	Loss 1.1285 (1.1285)	Acc@1 73.145 (73.145)	Acc@5 91.992 (91.992)	
[2022-01-20 15:13:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.614 (3.213)	Loss 1.1868 (1.1389)	Acc@1 72.168 (72.718)	Acc@5 91.113 (91.921)	
[2022-01-20 15:13:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.344 (2.590)	Loss 1.1480 (1.1419)	Acc@1 73.438 (72.949)	Acc@5 91.211 (91.913)	
[2022-01-20 15:13:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.300 (2.251)	Loss 1.1791 (1.1396)	Acc@1 72.852 (73.082)	Acc@5 91.797 (91.983)	
[2022-01-20 15:14:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.574 (2.180)	Loss 1.2010 (1.1411)	Acc@1 72.266 (73.068)	Acc@5 90.918 (91.937)	
[2022-01-20 15:14:17 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.290 Acc@5 92.034
[2022-01-20 15:14:17 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.3%
[2022-01-20 15:14:17 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.72%
[2022-01-20 15:14:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][0/1251]	eta 7:31:11 lr 0.000770	time 21.6403 (21.6403)	loss 4.6918 (4.6918)	grad_norm 1.2080 (1.2080)	
[2022-01-20 15:15:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][10/1251]	eta 1:21:31 lr 0.000770	time 3.2267 (3.9412)	loss 3.9488 (3.7988)	grad_norm 1.2248 (1.2708)	
[2022-01-20 15:15:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][20/1251]	eta 1:02:57 lr 0.000770	time 1.5305 (3.0686)	loss 3.3903 (3.6848)	grad_norm 1.2237 (1.2463)	
[2022-01-20 15:15:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][30/1251]	eta 0:59:24 lr 0.000770	time 1.6571 (2.9194)	loss 3.9973 (3.7728)	grad_norm 1.3799 (1.2511)	
[2022-01-20 15:16:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][40/1251]	eta 0:55:11 lr 0.000770	time 2.4059 (2.7342)	loss 3.2801 (3.6886)	grad_norm 1.2089 (1.2471)	
[2022-01-20 15:16:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][50/1251]	eta 0:54:22 lr 0.000770	time 2.7628 (2.7162)	loss 3.4498 (3.6155)	grad_norm 1.2591 (1.2412)	
[2022-01-20 15:16:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][60/1251]	eta 0:51:40 lr 0.000770	time 1.6801 (2.6036)	loss 3.0821 (3.6438)	grad_norm 1.3470 (1.2337)	
[2022-01-20 15:17:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][70/1251]	eta 0:49:50 lr 0.000770	time 1.9228 (2.5319)	loss 2.4880 (3.6432)	grad_norm 1.2445 (1.2361)	
[2022-01-20 15:17:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][80/1251]	eta 0:49:01 lr 0.000770	time 2.0097 (2.5116)	loss 3.9895 (3.6443)	grad_norm 1.5492 (1.2391)	
[2022-01-20 15:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][90/1251]	eta 0:48:00 lr 0.000770	time 1.8860 (2.4811)	loss 4.2631 (3.6669)	grad_norm 1.2423 (1.2407)	
[2022-01-20 15:18:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][100/1251]	eta 0:46:44 lr 0.000770	time 1.9255 (2.4368)	loss 4.4332 (3.6525)	grad_norm 1.4626 (1.2455)	
[2022-01-20 15:18:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][110/1251]	eta 0:45:43 lr 0.000770	time 2.2569 (2.4044)	loss 3.2653 (3.6612)	grad_norm 1.4552 (1.2466)	
[2022-01-20 15:19:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][120/1251]	eta 0:44:57 lr 0.000770	time 2.1383 (2.3850)	loss 4.3918 (3.6933)	grad_norm 1.4185 (1.2488)	
[2022-01-20 15:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][130/1251]	eta 0:44:27 lr 0.000770	time 1.8368 (2.3795)	loss 3.8660 (3.7049)	grad_norm 1.2470 (1.2463)	
[2022-01-20 15:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][140/1251]	eta 0:43:40 lr 0.000770	time 1.7067 (2.3590)	loss 4.1225 (3.7038)	grad_norm 1.1480 (1.2372)	
[2022-01-20 15:20:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][150/1251]	eta 0:42:59 lr 0.000770	time 1.9770 (2.3432)	loss 4.3696 (3.7118)	grad_norm 1.2189 (1.2380)	
[2022-01-20 15:20:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][160/1251]	eta 0:42:07 lr 0.000770	time 1.5837 (2.3168)	loss 3.9027 (3.7066)	grad_norm 1.1452 (1.2397)	
[2022-01-20 15:20:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][170/1251]	eta 0:41:28 lr 0.000770	time 2.1983 (2.3019)	loss 4.0326 (3.7247)	grad_norm 1.1354 (1.2428)	
[2022-01-20 15:21:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][180/1251]	eta 0:40:51 lr 0.000770	time 2.5566 (2.2889)	loss 3.9573 (3.7355)	grad_norm 1.2126 (1.2392)	
[2022-01-20 15:21:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][190/1251]	eta 0:40:24 lr 0.000770	time 2.5084 (2.2855)	loss 3.9446 (3.7241)	grad_norm 1.1735 (1.2387)	
[2022-01-20 15:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][200/1251]	eta 0:39:59 lr 0.000770	time 2.1034 (2.2829)	loss 2.6990 (3.7219)	grad_norm 1.2004 (1.2378)	
[2022-01-20 15:22:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][210/1251]	eta 0:39:41 lr 0.000769	time 2.0148 (2.2874)	loss 4.1584 (3.7429)	grad_norm 1.3515 (1.2413)	
[2022-01-20 15:22:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][220/1251]	eta 0:39:19 lr 0.000769	time 2.1011 (2.2885)	loss 2.7453 (3.7237)	grad_norm 1.5377 (1.2424)	
[2022-01-20 15:23:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][230/1251]	eta 0:38:51 lr 0.000769	time 2.2426 (2.2838)	loss 3.1673 (3.7205)	grad_norm 1.2174 (1.2418)	
[2022-01-20 15:23:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][240/1251]	eta 0:38:28 lr 0.000769	time 2.2432 (2.2830)	loss 3.9517 (3.7179)	grad_norm 1.0527 (1.2406)	
[2022-01-20 15:23:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][250/1251]	eta 0:37:57 lr 0.000769	time 1.9477 (2.2755)	loss 3.9983 (3.7076)	grad_norm 1.1733 (1.2434)	
[2022-01-20 15:24:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][260/1251]	eta 0:37:28 lr 0.000769	time 2.0314 (2.2687)	loss 4.1367 (3.7131)	grad_norm 1.3176 (1.2442)	
[2022-01-20 15:24:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][270/1251]	eta 0:37:11 lr 0.000769	time 5.3926 (2.2743)	loss 3.6843 (3.7166)	grad_norm 1.2327 (1.2460)	
[2022-01-20 15:24:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][280/1251]	eta 0:36:47 lr 0.000769	time 2.5604 (2.2735)	loss 3.7695 (3.7115)	grad_norm 1.1726 (1.2488)	
[2022-01-20 15:25:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][290/1251]	eta 0:36:22 lr 0.000769	time 1.9101 (2.2715)	loss 3.4608 (3.7150)	grad_norm 1.2583 (1.2500)	
[2022-01-20 15:25:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][300/1251]	eta 0:35:57 lr 0.000769	time 1.5275 (2.2686)	loss 2.5726 (3.7141)	grad_norm 1.3132 (1.2520)	
[2022-01-20 15:26:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][310/1251]	eta 0:35:30 lr 0.000769	time 3.3880 (2.2643)	loss 4.3877 (3.7115)	grad_norm 1.2189 (1.2515)	
[2022-01-20 15:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][320/1251]	eta 0:35:05 lr 0.000769	time 1.8633 (2.2619)	loss 2.7646 (3.7134)	grad_norm 1.2236 (1.2507)	
[2022-01-20 15:26:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][330/1251]	eta 0:34:45 lr 0.000769	time 2.5954 (2.2639)	loss 3.9373 (3.7161)	grad_norm 1.2622 (1.2505)	
[2022-01-20 15:27:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][340/1251]	eta 0:34:20 lr 0.000769	time 1.8047 (2.2623)	loss 3.4648 (3.7183)	grad_norm 1.1218 (1.2491)	
[2022-01-20 15:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][350/1251]	eta 0:33:58 lr 0.000769	time 2.5106 (2.2622)	loss 4.5657 (3.7192)	grad_norm 1.2861 (1.2475)	
[2022-01-20 15:27:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][360/1251]	eta 0:33:27 lr 0.000769	time 1.7351 (2.2530)	loss 3.8483 (3.7219)	grad_norm 1.1352 (1.2460)	
[2022-01-20 15:28:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][370/1251]	eta 0:32:58 lr 0.000769	time 2.3352 (2.2453)	loss 3.4196 (3.7303)	grad_norm 1.2103 (1.2435)	
[2022-01-20 15:28:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][380/1251]	eta 0:32:36 lr 0.000769	time 2.1902 (2.2463)	loss 4.1013 (3.7326)	grad_norm 1.0982 (1.2451)	
[2022-01-20 15:28:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][390/1251]	eta 0:32:13 lr 0.000769	time 2.9615 (2.2455)	loss 4.3120 (3.7326)	grad_norm 2.0164 (1.2485)	
[2022-01-20 15:29:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][400/1251]	eta 0:31:49 lr 0.000769	time 2.1953 (2.2438)	loss 2.6514 (3.7271)	grad_norm 1.3742 (1.2514)	
[2022-01-20 15:29:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][410/1251]	eta 0:31:25 lr 0.000769	time 2.8905 (2.2416)	loss 3.4940 (3.7299)	grad_norm 1.4074 (1.2532)	
[2022-01-20 15:29:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][420/1251]	eta 0:30:58 lr 0.000769	time 1.5790 (2.2369)	loss 3.3437 (3.7265)	grad_norm 1.1110 (1.2524)	
[2022-01-20 15:30:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][430/1251]	eta 0:30:37 lr 0.000769	time 2.2319 (2.2384)	loss 4.0998 (3.7298)	grad_norm 1.2515 (1.2529)	
[2022-01-20 15:30:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][440/1251]	eta 0:30:16 lr 0.000769	time 2.1513 (2.2400)	loss 3.9010 (3.7311)	grad_norm 1.1446 (1.2517)	
[2022-01-20 15:31:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][450/1251]	eta 0:29:54 lr 0.000769	time 2.2279 (2.2408)	loss 4.2711 (3.7352)	grad_norm 1.5117 (1.2539)	
[2022-01-20 15:31:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][460/1251]	eta 0:29:30 lr 0.000769	time 1.6230 (2.2389)	loss 3.5062 (3.7324)	grad_norm 1.2408 (1.2538)	
[2022-01-20 15:31:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][470/1251]	eta 0:29:06 lr 0.000769	time 2.2130 (2.2368)	loss 4.1951 (3.7274)	grad_norm 1.1805 (1.2524)	
[2022-01-20 15:32:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][480/1251]	eta 0:28:38 lr 0.000769	time 1.9744 (2.2287)	loss 3.8379 (3.7278)	grad_norm 1.3429 (1.2528)	
[2022-01-20 15:32:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][490/1251]	eta 0:28:12 lr 0.000769	time 1.7880 (2.2240)	loss 3.7977 (3.7233)	grad_norm 1.3573 (1.2529)	
[2022-01-20 15:32:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][500/1251]	eta 0:27:49 lr 0.000768	time 2.5278 (2.2227)	loss 3.1986 (3.7233)	grad_norm 1.0726 (1.2535)	
[2022-01-20 15:33:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][510/1251]	eta 0:27:25 lr 0.000768	time 2.0195 (2.2207)	loss 4.0464 (3.7276)	grad_norm 1.2972 (1.2536)	
[2022-01-20 15:33:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][520/1251]	eta 0:27:04 lr 0.000768	time 2.5378 (2.2223)	loss 3.4086 (3.7255)	grad_norm 1.0623 (1.2550)	
[2022-01-20 15:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][530/1251]	eta 0:26:42 lr 0.000768	time 2.4556 (2.2224)	loss 4.5947 (3.7279)	grad_norm 1.1815 (1.2543)	
[2022-01-20 15:34:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][540/1251]	eta 0:26:18 lr 0.000768	time 1.8544 (2.2205)	loss 4.0422 (3.7300)	grad_norm 1.2116 (1.2566)	
[2022-01-20 15:34:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][550/1251]	eta 0:25:56 lr 0.000768	time 1.9818 (2.2204)	loss 3.8862 (3.7368)	grad_norm 1.1158 (1.2566)	
[2022-01-20 15:35:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][560/1251]	eta 0:25:35 lr 0.000768	time 3.1752 (2.2224)	loss 3.9592 (3.7424)	grad_norm 1.2631 (1.2562)	
[2022-01-20 15:35:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][570/1251]	eta 0:25:17 lr 0.000768	time 2.1257 (2.2282)	loss 3.6966 (3.7440)	grad_norm 1.3339 (1.2572)	
[2022-01-20 15:35:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][580/1251]	eta 0:24:55 lr 0.000768	time 2.0473 (2.2291)	loss 3.7215 (3.7419)	grad_norm 1.1033 (1.2568)	
[2022-01-20 15:36:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][590/1251]	eta 0:24:33 lr 0.000768	time 1.9242 (2.2286)	loss 4.2075 (3.7451)	grad_norm 1.4187 (1.2571)	
[2022-01-20 15:36:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][600/1251]	eta 0:24:08 lr 0.000768	time 1.8367 (2.2248)	loss 3.9549 (3.7463)	grad_norm 1.0690 (1.2566)	
[2022-01-20 15:36:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][610/1251]	eta 0:23:42 lr 0.000768	time 1.8600 (2.2192)	loss 4.2887 (3.7475)	grad_norm 1.3135 (1.2556)	
[2022-01-20 15:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][620/1251]	eta 0:23:19 lr 0.000768	time 1.8232 (2.2175)	loss 4.2396 (3.7493)	grad_norm 1.1316 (1.2539)	
[2022-01-20 15:37:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][630/1251]	eta 0:22:58 lr 0.000768	time 2.4210 (2.2191)	loss 4.3846 (3.7502)	grad_norm 1.1802 (1.2526)	
[2022-01-20 15:37:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][640/1251]	eta 0:22:35 lr 0.000768	time 1.8205 (2.2183)	loss 3.7017 (3.7486)	grad_norm 0.9876 (1.2510)	
[2022-01-20 15:38:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][650/1251]	eta 0:22:13 lr 0.000768	time 2.0001 (2.2180)	loss 3.4825 (3.7540)	grad_norm 1.1574 (1.2499)	
[2022-01-20 15:38:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][660/1251]	eta 0:21:51 lr 0.000768	time 2.1293 (2.2190)	loss 3.2842 (3.7532)	grad_norm 1.1063 (1.2494)	
[2022-01-20 15:39:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][670/1251]	eta 0:21:27 lr 0.000768	time 2.1493 (2.2168)	loss 3.4984 (3.7541)	grad_norm 1.1931 (1.2490)	
[2022-01-20 15:39:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][680/1251]	eta 0:21:06 lr 0.000768	time 2.2451 (2.2172)	loss 2.9186 (3.7510)	grad_norm 1.5687 (1.2491)	
[2022-01-20 15:39:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][690/1251]	eta 0:20:45 lr 0.000768	time 2.1751 (2.2193)	loss 4.0357 (3.7485)	grad_norm 1.1126 (1.2494)	
[2022-01-20 15:40:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][700/1251]	eta 0:20:22 lr 0.000768	time 2.0719 (2.2179)	loss 4.3568 (3.7474)	grad_norm 1.4705 (1.2490)	
[2022-01-20 15:40:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][710/1251]	eta 0:20:00 lr 0.000768	time 2.3704 (2.2188)	loss 3.1619 (3.7483)	grad_norm 1.3256 (1.2504)	
[2022-01-20 15:40:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][720/1251]	eta 0:19:36 lr 0.000768	time 2.2146 (2.2165)	loss 3.3346 (3.7483)	grad_norm 1.1826 (1.2497)	
[2022-01-20 15:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][730/1251]	eta 0:19:14 lr 0.000768	time 1.9565 (2.2150)	loss 2.8230 (3.7464)	grad_norm 1.4799 (1.2509)	
[2022-01-20 15:41:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][740/1251]	eta 0:18:50 lr 0.000768	time 1.7720 (2.2123)	loss 4.3103 (3.7453)	grad_norm 1.1916 (1.2511)	
[2022-01-20 15:42:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][750/1251]	eta 0:18:29 lr 0.000768	time 2.7342 (2.2136)	loss 3.5455 (3.7462)	grad_norm 1.1150 (1.2514)	
[2022-01-20 15:42:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][760/1251]	eta 0:18:07 lr 0.000768	time 2.4514 (2.2150)	loss 4.5718 (3.7476)	grad_norm 1.1305 (1.2517)	
[2022-01-20 15:42:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][770/1251]	eta 0:17:46 lr 0.000768	time 2.0308 (2.2168)	loss 3.2487 (3.7488)	grad_norm 1.5288 (1.2523)	
[2022-01-20 15:43:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][780/1251]	eta 0:17:23 lr 0.000767	time 1.8226 (2.2155)	loss 3.5700 (3.7509)	grad_norm 1.2227 (1.2524)	
[2022-01-20 15:43:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][790/1251]	eta 0:17:00 lr 0.000767	time 1.9185 (2.2134)	loss 4.0139 (3.7526)	grad_norm 1.2895 (1.2530)	
[2022-01-20 15:43:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][800/1251]	eta 0:16:38 lr 0.000767	time 2.8109 (2.2147)	loss 4.4061 (3.7542)	grad_norm 1.1713 (1.2532)	
[2022-01-20 15:44:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][810/1251]	eta 0:16:16 lr 0.000767	time 1.8662 (2.2136)	loss 3.9073 (3.7536)	grad_norm 1.1388 (1.2527)	
[2022-01-20 15:44:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][820/1251]	eta 0:15:53 lr 0.000767	time 2.4147 (2.2119)	loss 2.7616 (3.7527)	grad_norm 1.5664 (1.2530)	
[2022-01-20 15:44:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][830/1251]	eta 0:15:30 lr 0.000767	time 1.7428 (2.2108)	loss 3.6535 (3.7530)	grad_norm 1.2877 (1.2541)	
[2022-01-20 15:45:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][840/1251]	eta 0:15:08 lr 0.000767	time 2.1665 (2.2097)	loss 2.7657 (3.7574)	grad_norm 1.2942 (1.2537)	
[2022-01-20 15:45:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][850/1251]	eta 0:14:45 lr 0.000767	time 1.8363 (2.2090)	loss 4.3961 (3.7562)	grad_norm 1.3032 (1.2537)	
[2022-01-20 15:45:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][860/1251]	eta 0:14:23 lr 0.000767	time 2.0830 (2.2079)	loss 4.0006 (3.7566)	grad_norm 1.3749 (1.2541)	
[2022-01-20 15:46:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][870/1251]	eta 0:14:00 lr 0.000767	time 1.8445 (2.2063)	loss 4.0810 (3.7540)	grad_norm 1.2921 (1.2532)	
[2022-01-20 15:46:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][880/1251]	eta 0:13:39 lr 0.000767	time 2.7017 (2.2085)	loss 3.4622 (3.7541)	grad_norm 1.0935 (1.2528)	
[2022-01-20 15:47:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][890/1251]	eta 0:13:17 lr 0.000767	time 1.6874 (2.2079)	loss 3.8725 (3.7534)	grad_norm 1.2093 (1.2529)	
[2022-01-20 15:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][900/1251]	eta 0:12:54 lr 0.000767	time 2.2559 (2.2076)	loss 4.3393 (3.7568)	grad_norm 1.0636 (1.2524)	
[2022-01-20 15:47:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][910/1251]	eta 0:12:32 lr 0.000767	time 1.9179 (2.2069)	loss 4.0378 (3.7537)	grad_norm 1.0678 (1.2524)	
[2022-01-20 15:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][920/1251]	eta 0:12:10 lr 0.000767	time 1.9078 (2.2060)	loss 2.8936 (3.7527)	grad_norm 1.2824 (1.2529)	
[2022-01-20 15:48:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][930/1251]	eta 0:11:48 lr 0.000767	time 1.8166 (2.2075)	loss 3.7891 (3.7500)	grad_norm 1.3925 (1.2523)	
[2022-01-20 15:48:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][940/1251]	eta 0:11:26 lr 0.000767	time 2.2542 (2.2069)	loss 3.2889 (3.7506)	grad_norm 1.3534 (1.2529)	
[2022-01-20 15:49:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][950/1251]	eta 0:11:04 lr 0.000767	time 2.2530 (2.2070)	loss 3.0703 (3.7491)	grad_norm 1.0952 (1.2529)	
[2022-01-20 15:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][960/1251]	eta 0:10:42 lr 0.000767	time 1.9149 (2.2075)	loss 2.8627 (3.7495)	grad_norm 1.2496 (1.2539)	
[2022-01-20 15:50:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][970/1251]	eta 0:10:20 lr 0.000767	time 1.9206 (2.2070)	loss 4.1607 (3.7500)	grad_norm 1.3365 (1.2545)	
[2022-01-20 15:50:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][980/1251]	eta 0:09:57 lr 0.000767	time 2.7518 (2.2066)	loss 4.3836 (3.7518)	grad_norm 1.1854 (1.2543)	
[2022-01-20 15:50:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][990/1251]	eta 0:09:35 lr 0.000767	time 1.6548 (2.2049)	loss 3.1363 (3.7513)	grad_norm 1.3323 (1.2546)	
[2022-01-20 15:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1000/1251]	eta 0:09:13 lr 0.000767	time 1.9229 (2.2046)	loss 3.5441 (3.7493)	grad_norm 1.2488 (1.2549)	
[2022-01-20 15:51:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1010/1251]	eta 0:08:51 lr 0.000767	time 2.5091 (2.2049)	loss 4.0034 (3.7492)	grad_norm 1.3327 (1.2544)	
[2022-01-20 15:51:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1020/1251]	eta 0:08:29 lr 0.000767	time 2.5293 (2.2044)	loss 3.1143 (3.7492)	grad_norm 1.0674 (1.2535)	
[2022-01-20 15:52:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1030/1251]	eta 0:08:07 lr 0.000767	time 1.7711 (2.2042)	loss 2.6270 (3.7491)	grad_norm 1.2960 (1.2527)	
[2022-01-20 15:52:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1040/1251]	eta 0:07:45 lr 0.000767	time 1.7337 (2.2040)	loss 3.7494 (3.7460)	grad_norm 1.7074 (1.2531)	
[2022-01-20 15:52:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1050/1251]	eta 0:07:22 lr 0.000767	time 2.1424 (2.2035)	loss 3.6146 (3.7432)	grad_norm 1.4372 (1.2532)	
[2022-01-20 15:53:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1060/1251]	eta 0:07:00 lr 0.000767	time 2.1812 (2.2025)	loss 4.4238 (3.7444)	grad_norm 1.2512 (1.2532)	
[2022-01-20 15:53:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1070/1251]	eta 0:06:38 lr 0.000766	time 1.9203 (2.2022)	loss 4.2223 (3.7462)	grad_norm 1.3195 (1.2526)	
[2022-01-20 15:53:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1080/1251]	eta 0:06:16 lr 0.000766	time 1.8568 (2.2029)	loss 4.6975 (3.7488)	grad_norm 1.2068 (1.2516)	
[2022-01-20 15:54:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1090/1251]	eta 0:05:54 lr 0.000766	time 2.4323 (2.2032)	loss 4.1693 (3.7484)	grad_norm 1.5516 (1.2512)	
[2022-01-20 15:54:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1100/1251]	eta 0:05:32 lr 0.000766	time 2.3816 (2.2033)	loss 3.1985 (3.7495)	grad_norm 1.3538 (1.2517)	
[2022-01-20 15:55:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1110/1251]	eta 0:05:10 lr 0.000766	time 1.7111 (2.2023)	loss 4.0801 (3.7507)	grad_norm 1.1553 (1.2512)	
[2022-01-20 15:55:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1120/1251]	eta 0:04:48 lr 0.000766	time 2.0971 (2.2027)	loss 4.1700 (3.7509)	grad_norm 1.2375 (1.2509)	
[2022-01-20 15:55:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1130/1251]	eta 0:04:26 lr 0.000766	time 1.8993 (2.2018)	loss 3.7909 (3.7506)	grad_norm 1.0897 (1.2508)	
[2022-01-20 15:56:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1140/1251]	eta 0:04:04 lr 0.000766	time 2.4823 (2.2017)	loss 4.0940 (3.7522)	grad_norm 1.0664 (1.2497)	
[2022-01-20 15:56:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1150/1251]	eta 0:03:42 lr 0.000766	time 2.3216 (2.2014)	loss 3.6184 (3.7508)	grad_norm 1.2157 (1.2493)	
[2022-01-20 15:56:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1160/1251]	eta 0:03:20 lr 0.000766	time 1.8076 (2.2019)	loss 3.4671 (3.7513)	grad_norm 1.1368 (1.2491)	
[2022-01-20 15:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1170/1251]	eta 0:02:58 lr 0.000766	time 1.5651 (2.2013)	loss 3.4224 (3.7479)	grad_norm 1.1114 (1.2485)	
[2022-01-20 15:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1180/1251]	eta 0:02:36 lr 0.000766	time 2.0200 (2.2002)	loss 4.1730 (3.7496)	grad_norm 1.0910 (1.2478)	
[2022-01-20 15:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1190/1251]	eta 0:02:14 lr 0.000766	time 2.0558 (2.1997)	loss 3.6568 (3.7498)	grad_norm 1.0659 (1.2477)	
[2022-01-20 15:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1200/1251]	eta 0:01:52 lr 0.000766	time 2.1155 (2.1996)	loss 3.9278 (3.7516)	grad_norm 1.0550 (1.2470)	
[2022-01-20 15:58:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1210/1251]	eta 0:01:30 lr 0.000766	time 1.9150 (2.1991)	loss 4.5219 (3.7527)	grad_norm 1.1905 (1.2472)	
[2022-01-20 15:59:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1220/1251]	eta 0:01:08 lr 0.000766	time 2.8111 (2.1990)	loss 3.5252 (3.7508)	grad_norm 1.2218 (1.2471)	
[2022-01-20 15:59:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1230/1251]	eta 0:00:46 lr 0.000766	time 2.1869 (2.2000)	loss 3.5660 (3.7512)	grad_norm 1.1455 (1.2466)	
[2022-01-20 15:59:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1240/1251]	eta 0:00:24 lr 0.000766	time 1.4557 (2.1987)	loss 2.7143 (3.7482)	grad_norm 1.6618 (1.2468)	
[2022-01-20 16:00:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [96/300][1250/1251]	eta 0:00:02 lr 0.000766	time 1.3142 (2.1927)	loss 4.1738 (3.7487)	grad_norm 1.1578 (1.2472)	
[2022-01-20 16:00:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 96 training takes 0:45:43
[2022-01-20 16:00:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.712 (17.712)	Loss 1.0944 (1.0944)	Acc@1 73.633 (73.633)	Acc@5 92.871 (92.871)	
[2022-01-20 16:00:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.612 (3.459)	Loss 1.1466 (1.1456)	Acc@1 74.023 (73.216)	Acc@5 92.285 (92.205)	
[2022-01-20 16:00:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.297 (2.653)	Loss 1.0630 (1.1455)	Acc@1 76.270 (73.484)	Acc@5 93.750 (92.197)	
[2022-01-20 16:01:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.619 (2.390)	Loss 1.1987 (1.1562)	Acc@1 72.461 (73.400)	Acc@5 91.504 (91.945)	
[2022-01-20 16:01:32 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.951 (2.236)	Loss 1.1825 (1.1549)	Acc@1 72.852 (73.449)	Acc@5 92.090 (91.942)	
[2022-01-20 16:01:39 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.416 Acc@5 91.974
[2022-01-20 16:01:39 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.4%
[2022-01-20 16:01:39 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.72%
[2022-01-20 16:02:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][0/1251]	eta 7:34:16 lr 0.000766	time 21.7880 (21.7880)	loss 3.6861 (3.6861)	grad_norm 1.2490 (1.2490)	
[2022-01-20 16:02:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][10/1251]	eta 1:24:40 lr 0.000766	time 1.6747 (4.0939)	loss 3.8660 (3.6875)	grad_norm 1.1635 (1.2834)	
[2022-01-20 16:02:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][20/1251]	eta 1:04:30 lr 0.000766	time 1.3350 (3.1438)	loss 3.9523 (3.8768)	grad_norm 1.1848 (1.2713)	
[2022-01-20 16:03:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][30/1251]	eta 0:57:23 lr 0.000766	time 1.5748 (2.8198)	loss 3.7364 (3.8403)	grad_norm 1.1942 (1.2474)	
[2022-01-20 16:03:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][40/1251]	eta 0:54:34 lr 0.000766	time 3.9813 (2.7041)	loss 3.2736 (3.7792)	grad_norm 1.3079 (1.2415)	
[2022-01-20 16:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][50/1251]	eta 0:52:35 lr 0.000766	time 2.4477 (2.6278)	loss 3.7948 (3.7730)	grad_norm 1.0732 (1.2363)	
[2022-01-20 16:04:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][60/1251]	eta 0:50:45 lr 0.000766	time 1.8538 (2.5570)	loss 2.7751 (3.7519)	grad_norm 1.2951 (1.2375)	
[2022-01-20 16:04:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][70/1251]	eta 0:49:07 lr 0.000766	time 2.3313 (2.4960)	loss 4.3892 (3.7251)	grad_norm 1.1935 (1.2377)	
[2022-01-20 16:05:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][80/1251]	eta 0:48:27 lr 0.000766	time 3.5239 (2.4829)	loss 3.4098 (3.7153)	grad_norm 1.5430 (1.2430)	
[2022-01-20 16:05:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][90/1251]	eta 0:47:41 lr 0.000766	time 2.5311 (2.4649)	loss 3.5963 (3.7055)	grad_norm 1.2353 (1.2565)	
[2022-01-20 16:05:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][100/1251]	eta 0:46:54 lr 0.000765	time 2.2434 (2.4456)	loss 4.0923 (3.6844)	grad_norm 1.1298 (1.2485)	
[2022-01-20 16:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][110/1251]	eta 0:45:45 lr 0.000765	time 1.9518 (2.4065)	loss 3.9784 (3.7041)	grad_norm 1.5161 (1.2517)	
[2022-01-20 16:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][120/1251]	eta 0:44:52 lr 0.000765	time 2.8573 (2.3807)	loss 3.4660 (3.7272)	grad_norm 1.2164 (1.2526)	
[2022-01-20 16:06:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][130/1251]	eta 0:44:05 lr 0.000765	time 2.1277 (2.3596)	loss 3.8901 (3.7493)	grad_norm 1.3333 (1.2502)	
[2022-01-20 16:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][140/1251]	eta 0:43:29 lr 0.000765	time 2.5116 (2.3487)	loss 2.6567 (3.7470)	grad_norm 1.3064 (1.2457)	
[2022-01-20 16:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][150/1251]	eta 0:42:57 lr 0.000765	time 2.0974 (2.3410)	loss 4.2856 (3.7590)	grad_norm 1.2670 (1.2474)	
[2022-01-20 16:07:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][160/1251]	eta 0:42:27 lr 0.000765	time 2.3485 (2.3351)	loss 4.2787 (3.7501)	grad_norm 1.0823 (1.2439)	
[2022-01-20 16:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][170/1251]	eta 0:41:53 lr 0.000765	time 2.5339 (2.3251)	loss 4.0598 (3.7453)	grad_norm 1.2172 (1.2410)	
[2022-01-20 16:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][180/1251]	eta 0:41:21 lr 0.000765	time 2.3898 (2.3167)	loss 2.9792 (3.7616)	grad_norm 1.2454 (1.2403)	
[2022-01-20 16:09:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][190/1251]	eta 0:40:50 lr 0.000765	time 1.8990 (2.3098)	loss 4.1179 (3.7597)	grad_norm 1.0919 (1.2394)	
[2022-01-20 16:09:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][200/1251]	eta 0:40:20 lr 0.000765	time 2.2318 (2.3028)	loss 3.4336 (3.7661)	grad_norm 1.2446 (1.2366)	
[2022-01-20 16:09:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][210/1251]	eta 0:39:54 lr 0.000765	time 2.6886 (2.3005)	loss 3.8692 (3.7682)	grad_norm 1.3855 (1.2387)	
[2022-01-20 16:10:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][220/1251]	eta 0:39:22 lr 0.000765	time 2.5084 (2.2919)	loss 2.7914 (3.7443)	grad_norm 1.3993 (1.2386)	
[2022-01-20 16:10:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][230/1251]	eta 0:38:52 lr 0.000765	time 2.1955 (2.2845)	loss 4.0055 (3.7467)	grad_norm 1.6245 (1.2386)	
[2022-01-20 16:10:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][240/1251]	eta 0:38:24 lr 0.000765	time 1.8681 (2.2795)	loss 2.8601 (3.7556)	grad_norm 1.3167 (1.2417)	
[2022-01-20 16:11:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][250/1251]	eta 0:37:54 lr 0.000765	time 2.6114 (2.2722)	loss 3.8036 (3.7625)	grad_norm 1.1198 (1.2394)	
[2022-01-20 16:11:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][260/1251]	eta 0:37:30 lr 0.000765	time 2.8645 (2.2705)	loss 3.1978 (3.7546)	grad_norm 1.2306 (1.2407)	
[2022-01-20 16:11:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][270/1251]	eta 0:36:59 lr 0.000765	time 1.9133 (2.2629)	loss 4.2319 (3.7566)	grad_norm 1.1964 (1.2400)	
[2022-01-20 16:12:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][280/1251]	eta 0:36:34 lr 0.000765	time 2.5621 (2.2599)	loss 4.4108 (3.7551)	grad_norm 1.1622 (1.2398)	
[2022-01-20 16:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][290/1251]	eta 0:36:11 lr 0.000765	time 2.3594 (2.2596)	loss 4.4142 (3.7539)	grad_norm 1.1698 (1.2397)	
[2022-01-20 16:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][300/1251]	eta 0:35:47 lr 0.000765	time 2.7750 (2.2578)	loss 4.3832 (3.7559)	grad_norm 1.1654 (1.2415)	
[2022-01-20 16:13:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][310/1251]	eta 0:35:21 lr 0.000765	time 2.5482 (2.2549)	loss 2.5863 (3.7598)	grad_norm 1.5575 (1.2407)	
[2022-01-20 16:13:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][320/1251]	eta 0:34:54 lr 0.000765	time 2.5906 (2.2496)	loss 4.1354 (3.7592)	grad_norm 1.0577 (1.2393)	
[2022-01-20 16:14:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][330/1251]	eta 0:34:25 lr 0.000765	time 1.9706 (2.2430)	loss 2.6138 (3.7581)	grad_norm 1.2097 (1.2373)	
[2022-01-20 16:14:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][340/1251]	eta 0:33:57 lr 0.000765	time 1.8781 (2.2368)	loss 4.5021 (3.7601)	grad_norm 1.3145 (1.2355)	
[2022-01-20 16:14:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][350/1251]	eta 0:33:32 lr 0.000765	time 1.8357 (2.2338)	loss 2.9106 (3.7529)	grad_norm 1.1582 (1.2355)	
[2022-01-20 16:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][360/1251]	eta 0:33:08 lr 0.000765	time 3.0988 (2.2316)	loss 4.0706 (3.7545)	grad_norm 1.0248 (1.2343)	
[2022-01-20 16:15:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][370/1251]	eta 0:32:49 lr 0.000765	time 1.8146 (2.2352)	loss 2.8280 (3.7490)	grad_norm 1.3071 (1.2334)	
[2022-01-20 16:15:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][380/1251]	eta 0:32:25 lr 0.000765	time 2.1166 (2.2342)	loss 3.6123 (3.7536)	grad_norm 1.3437 (1.2347)	
[2022-01-20 16:16:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][390/1251]	eta 0:32:02 lr 0.000764	time 2.1664 (2.2334)	loss 4.1370 (3.7555)	grad_norm 1.6639 (1.2351)	
[2022-01-20 16:16:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][400/1251]	eta 0:31:43 lr 0.000764	time 3.7237 (2.2366)	loss 4.1810 (3.7613)	grad_norm 1.3596 (1.2354)	
[2022-01-20 16:16:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][410/1251]	eta 0:31:18 lr 0.000764	time 2.2111 (2.2336)	loss 2.6604 (3.7599)	grad_norm 1.3721 (1.2347)	
[2022-01-20 16:17:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][420/1251]	eta 0:30:53 lr 0.000764	time 2.5025 (2.2300)	loss 4.0718 (3.7538)	grad_norm 1.1907 (1.2354)	
[2022-01-20 16:17:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][430/1251]	eta 0:30:30 lr 0.000764	time 2.1704 (2.2293)	loss 4.1060 (3.7490)	grad_norm 1.1291 (1.2351)	
[2022-01-20 16:18:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][440/1251]	eta 0:30:06 lr 0.000764	time 2.5449 (2.2277)	loss 4.3102 (3.7463)	grad_norm 1.6159 (1.2377)	
[2022-01-20 16:18:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][450/1251]	eta 0:29:42 lr 0.000764	time 2.1160 (2.2248)	loss 3.8523 (3.7461)	grad_norm 1.0124 (1.2367)	
[2022-01-20 16:18:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][460/1251]	eta 0:29:19 lr 0.000764	time 1.9696 (2.2239)	loss 4.5929 (3.7466)	grad_norm 1.2309 (1.2373)	
[2022-01-20 16:19:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][470/1251]	eta 0:28:55 lr 0.000764	time 1.7744 (2.2219)	loss 4.3761 (3.7470)	grad_norm 1.1919 (1.2367)	
[2022-01-20 16:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][480/1251]	eta 0:28:34 lr 0.000764	time 2.5633 (2.2241)	loss 3.3539 (3.7444)	grad_norm 1.4949 (1.2371)	
[2022-01-20 16:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][490/1251]	eta 0:28:11 lr 0.000764	time 1.9415 (2.2231)	loss 4.2088 (3.7469)	grad_norm 1.0224 (1.2366)	
[2022-01-20 16:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][500/1251]	eta 0:27:47 lr 0.000764	time 1.7375 (2.2207)	loss 4.2082 (3.7466)	grad_norm 1.1118 (1.2367)	
[2022-01-20 16:20:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][510/1251]	eta 0:27:26 lr 0.000764	time 2.1555 (2.2220)	loss 4.0256 (3.7418)	grad_norm 1.3948 (1.2368)	
[2022-01-20 16:20:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][520/1251]	eta 0:27:05 lr 0.000764	time 2.3271 (2.2231)	loss 3.8069 (3.7420)	grad_norm 1.2341 (1.2364)	
[2022-01-20 16:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][530/1251]	eta 0:26:41 lr 0.000764	time 2.2912 (2.2210)	loss 3.6924 (3.7452)	grad_norm 1.3026 (1.2360)	
[2022-01-20 16:21:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][540/1251]	eta 0:26:19 lr 0.000764	time 2.5109 (2.2214)	loss 3.6794 (3.7419)	grad_norm 1.2480 (1.2368)	
[2022-01-20 16:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][550/1251]	eta 0:25:55 lr 0.000764	time 1.8388 (2.2188)	loss 4.3174 (3.7409)	grad_norm 1.1586 (1.2367)	
[2022-01-20 16:22:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][560/1251]	eta 0:25:31 lr 0.000764	time 1.8543 (2.2159)	loss 4.3829 (3.7432)	grad_norm 1.2277 (1.2368)	
[2022-01-20 16:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][570/1251]	eta 0:25:08 lr 0.000764	time 2.4912 (2.2147)	loss 4.1733 (3.7387)	grad_norm 1.1892 (1.2367)	
[2022-01-20 16:23:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][580/1251]	eta 0:24:45 lr 0.000764	time 1.8344 (2.2145)	loss 2.5359 (3.7394)	grad_norm 1.0455 (1.2358)	
[2022-01-20 16:23:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][590/1251]	eta 0:24:22 lr 0.000764	time 1.8945 (2.2133)	loss 3.2612 (3.7341)	grad_norm 1.1849 (1.2372)	
[2022-01-20 16:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][600/1251]	eta 0:24:02 lr 0.000764	time 2.4833 (2.2158)	loss 4.4290 (3.7392)	grad_norm 1.1604 (1.2384)	
[2022-01-20 16:24:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][610/1251]	eta 0:23:40 lr 0.000764	time 2.7286 (2.2162)	loss 3.6854 (3.7423)	grad_norm 1.2776 (1.2390)	
[2022-01-20 16:24:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][620/1251]	eta 0:23:17 lr 0.000764	time 2.2258 (2.2146)	loss 4.4954 (3.7441)	grad_norm 1.3183 (1.2378)	
[2022-01-20 16:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][630/1251]	eta 0:22:53 lr 0.000764	time 1.8939 (2.2123)	loss 3.9722 (3.7450)	grad_norm 1.1865 (1.2374)	
[2022-01-20 16:25:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][640/1251]	eta 0:22:32 lr 0.000764	time 2.8383 (2.2140)	loss 4.1122 (3.7472)	grad_norm 1.3008 (1.2370)	
[2022-01-20 16:25:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][650/1251]	eta 0:22:11 lr 0.000764	time 1.9392 (2.2150)	loss 3.7033 (3.7436)	grad_norm 1.2570 (1.2378)	
[2022-01-20 16:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][660/1251]	eta 0:21:48 lr 0.000764	time 2.2628 (2.2141)	loss 3.8532 (3.7440)	grad_norm 1.2170 (1.2382)	
[2022-01-20 16:26:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][670/1251]	eta 0:21:25 lr 0.000763	time 1.8831 (2.2124)	loss 4.5372 (3.7476)	grad_norm 1.0681 (1.2394)	
[2022-01-20 16:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][680/1251]	eta 0:21:01 lr 0.000763	time 1.8843 (2.2094)	loss 3.4282 (3.7450)	grad_norm 1.1749 (1.2383)	
[2022-01-20 16:27:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][690/1251]	eta 0:20:39 lr 0.000763	time 2.2510 (2.2090)	loss 3.5386 (3.7444)	grad_norm 1.2171 (1.2372)	
[2022-01-20 16:27:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][700/1251]	eta 0:20:16 lr 0.000763	time 2.0426 (2.2079)	loss 3.7533 (3.7387)	grad_norm 1.5974 (1.2374)	
[2022-01-20 16:27:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][710/1251]	eta 0:19:53 lr 0.000763	time 1.6597 (2.2055)	loss 2.6438 (3.7320)	grad_norm 1.2007 (1.2378)	
[2022-01-20 16:28:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][720/1251]	eta 0:19:30 lr 0.000763	time 2.2117 (2.2042)	loss 3.7012 (3.7321)	grad_norm 1.2821 (1.2388)	
[2022-01-20 16:28:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][730/1251]	eta 0:19:07 lr 0.000763	time 1.7450 (2.2034)	loss 2.6575 (3.7311)	grad_norm 1.2696 (1.2396)	
[2022-01-20 16:28:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][740/1251]	eta 0:18:46 lr 0.000763	time 2.2984 (2.2036)	loss 4.2249 (3.7319)	grad_norm 1.0778 (1.2380)	
[2022-01-20 16:29:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][750/1251]	eta 0:18:23 lr 0.000763	time 2.1512 (2.2027)	loss 2.5219 (3.7285)	grad_norm 1.3787 (1.2395)	
[2022-01-20 16:29:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][760/1251]	eta 0:18:02 lr 0.000763	time 2.1575 (2.2050)	loss 2.7962 (3.7302)	grad_norm 1.2034 (1.2402)	
[2022-01-20 16:30:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][770/1251]	eta 0:17:40 lr 0.000763	time 1.9115 (2.2055)	loss 3.7722 (3.7309)	grad_norm 1.4966 (1.2400)	
[2022-01-20 16:30:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][780/1251]	eta 0:17:18 lr 0.000763	time 2.2355 (2.2056)	loss 3.8304 (3.7311)	grad_norm 1.3989 (1.2403)	
[2022-01-20 16:30:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][790/1251]	eta 0:16:56 lr 0.000763	time 2.6533 (2.2051)	loss 3.2049 (3.7300)	grad_norm 1.1673 (1.2396)	
[2022-01-20 16:31:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][800/1251]	eta 0:16:35 lr 0.000763	time 2.2611 (2.2072)	loss 4.7971 (3.7320)	grad_norm 1.1460 (1.2391)	
[2022-01-20 16:31:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][810/1251]	eta 0:16:13 lr 0.000763	time 1.8395 (2.2085)	loss 4.1486 (3.7334)	grad_norm 1.2301 (1.2392)	
[2022-01-20 16:31:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][820/1251]	eta 0:15:51 lr 0.000763	time 2.2417 (2.2086)	loss 3.0705 (3.7348)	grad_norm 1.3070 (1.2406)	
[2022-01-20 16:32:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][830/1251]	eta 0:15:29 lr 0.000763	time 1.6295 (2.2072)	loss 4.2004 (3.7341)	grad_norm 1.1273 (1.2407)	
[2022-01-20 16:32:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][840/1251]	eta 0:15:07 lr 0.000763	time 1.8478 (2.2073)	loss 4.2428 (3.7342)	grad_norm 1.2279 (1.2408)	
[2022-01-20 16:33:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][850/1251]	eta 0:14:46 lr 0.000763	time 1.8278 (2.2097)	loss 3.9481 (3.7351)	grad_norm 1.3323 (1.2415)	
[2022-01-20 16:33:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][860/1251]	eta 0:14:23 lr 0.000763	time 1.7043 (2.2085)	loss 3.1334 (3.7350)	grad_norm 1.2231 (1.2417)	
[2022-01-20 16:33:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][870/1251]	eta 0:14:01 lr 0.000763	time 1.7990 (2.2078)	loss 4.3293 (3.7384)	grad_norm 1.2116 (1.2411)	
[2022-01-20 16:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][880/1251]	eta 0:13:38 lr 0.000763	time 1.8756 (2.2061)	loss 3.9548 (3.7382)	grad_norm 1.1857 (1.2412)	
[2022-01-20 16:34:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][890/1251]	eta 0:13:16 lr 0.000763	time 2.0369 (2.2059)	loss 3.4520 (3.7368)	grad_norm 1.0913 (1.2412)	
[2022-01-20 16:34:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][900/1251]	eta 0:12:54 lr 0.000763	time 1.8556 (2.2067)	loss 4.3847 (3.7379)	grad_norm 1.2588 (1.2411)	
[2022-01-20 16:35:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][910/1251]	eta 0:12:32 lr 0.000763	time 1.6884 (2.2071)	loss 3.6495 (3.7396)	grad_norm 1.1212 (1.2405)	
[2022-01-20 16:35:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][920/1251]	eta 0:12:10 lr 0.000763	time 1.9981 (2.2068)	loss 2.7181 (3.7350)	grad_norm 1.2646 (1.2403)	
[2022-01-20 16:35:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][930/1251]	eta 0:11:48 lr 0.000763	time 2.3938 (2.2080)	loss 4.3149 (3.7343)	grad_norm 1.1302 (1.2402)	
[2022-01-20 16:36:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][940/1251]	eta 0:11:26 lr 0.000763	time 1.7397 (2.2071)	loss 4.5753 (3.7309)	grad_norm 1.1902 (1.2403)	
[2022-01-20 16:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][950/1251]	eta 0:11:03 lr 0.000762	time 1.7872 (2.2055)	loss 3.5145 (3.7282)	grad_norm 1.5326 (1.2415)	
[2022-01-20 16:36:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][960/1251]	eta 0:10:41 lr 0.000762	time 1.7119 (2.2041)	loss 3.4809 (3.7295)	grad_norm 1.1863 (1.2423)	
[2022-01-20 16:37:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][970/1251]	eta 0:10:19 lr 0.000762	time 1.8410 (2.2050)	loss 2.7687 (3.7273)	grad_norm 1.2233 (1.2427)	
[2022-01-20 16:37:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][980/1251]	eta 0:09:57 lr 0.000762	time 1.7509 (2.2044)	loss 4.0266 (3.7287)	grad_norm 1.0410 (1.2417)	
[2022-01-20 16:38:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][990/1251]	eta 0:09:35 lr 0.000762	time 1.9560 (2.2051)	loss 3.9127 (3.7265)	grad_norm 1.2146 (1.2411)	
[2022-01-20 16:38:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1000/1251]	eta 0:09:13 lr 0.000762	time 2.4718 (2.2062)	loss 2.8497 (3.7256)	grad_norm 1.0828 (1.2407)	
[2022-01-20 16:38:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1010/1251]	eta 0:08:51 lr 0.000762	time 2.3074 (2.2060)	loss 3.8415 (3.7246)	grad_norm 1.0404 (1.2407)	
[2022-01-20 16:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1020/1251]	eta 0:08:29 lr 0.000762	time 1.9380 (2.2039)	loss 4.0643 (3.7265)	grad_norm 1.3064 (1.2414)	
[2022-01-20 16:39:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1030/1251]	eta 0:08:06 lr 0.000762	time 1.9518 (2.2028)	loss 4.4924 (3.7264)	grad_norm 1.4720 (1.2418)	
[2022-01-20 16:39:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1040/1251]	eta 0:07:44 lr 0.000762	time 2.3956 (2.2027)	loss 3.0034 (3.7232)	grad_norm 1.5253 (1.2422)	
[2022-01-20 16:40:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1050/1251]	eta 0:07:22 lr 0.000762	time 2.6566 (2.2032)	loss 4.1911 (3.7248)	grad_norm 1.1373 (1.2421)	
[2022-01-20 16:40:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1060/1251]	eta 0:07:00 lr 0.000762	time 2.1597 (2.2028)	loss 3.4629 (3.7225)	grad_norm 1.2121 (1.2425)	
[2022-01-20 16:41:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1070/1251]	eta 0:06:38 lr 0.000762	time 2.0543 (2.2038)	loss 2.8955 (3.7212)	grad_norm 1.1768 (1.2419)	
[2022-01-20 16:41:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1080/1251]	eta 0:06:17 lr 0.000762	time 3.1098 (2.2048)	loss 3.3904 (3.7204)	grad_norm 1.4799 (1.2423)	
[2022-01-20 16:41:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1090/1251]	eta 0:05:55 lr 0.000762	time 2.9621 (2.2053)	loss 2.9233 (3.7192)	grad_norm 1.2271 (1.2417)	
[2022-01-20 16:42:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1100/1251]	eta 0:05:32 lr 0.000762	time 1.6915 (2.2033)	loss 3.9146 (3.7187)	grad_norm 1.2082 (1.2413)	
[2022-01-20 16:42:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1110/1251]	eta 0:05:10 lr 0.000762	time 1.9055 (2.2011)	loss 2.7450 (3.7167)	grad_norm 1.1873 (1.2409)	
[2022-01-20 16:42:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1120/1251]	eta 0:04:48 lr 0.000762	time 1.9602 (2.1998)	loss 4.4695 (3.7173)	grad_norm 1.2851 (1.2402)	
[2022-01-20 16:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1130/1251]	eta 0:04:26 lr 0.000762	time 2.8886 (2.2001)	loss 3.8303 (3.7199)	grad_norm 1.5058 (1.2415)	
[2022-01-20 16:43:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1140/1251]	eta 0:04:04 lr 0.000762	time 1.8955 (2.1999)	loss 3.9876 (3.7200)	grad_norm 1.1570 (1.2416)	
[2022-01-20 16:43:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1150/1251]	eta 0:03:42 lr 0.000762	time 2.1435 (2.2002)	loss 3.4042 (3.7188)	grad_norm 1.1222 (1.2412)	
[2022-01-20 16:44:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1160/1251]	eta 0:03:20 lr 0.000762	time 2.2365 (2.2001)	loss 3.2310 (3.7175)	grad_norm 1.1569 (1.2407)	
[2022-01-20 16:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1170/1251]	eta 0:02:58 lr 0.000762	time 2.4569 (2.2015)	loss 4.0519 (3.7183)	grad_norm 1.1036 (1.2410)	
[2022-01-20 16:45:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1180/1251]	eta 0:02:36 lr 0.000762	time 2.1566 (2.2028)	loss 4.1300 (3.7203)	grad_norm 1.1265 (1.2414)	
[2022-01-20 16:45:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1190/1251]	eta 0:02:14 lr 0.000762	time 2.2641 (2.2028)	loss 4.2185 (3.7233)	grad_norm 1.1793 (1.2412)	
[2022-01-20 16:45:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1200/1251]	eta 0:01:52 lr 0.000762	time 1.9360 (2.2007)	loss 3.3551 (3.7224)	grad_norm 1.1109 (1.2405)	
[2022-01-20 16:46:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1210/1251]	eta 0:01:30 lr 0.000762	time 3.0470 (2.2004)	loss 2.6914 (3.7210)	grad_norm 1.0607 (1.2404)	
[2022-01-20 16:46:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1220/1251]	eta 0:01:08 lr 0.000762	time 1.9424 (2.1999)	loss 3.1144 (3.7211)	grad_norm 1.3770 (1.2403)	
[2022-01-20 16:46:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1230/1251]	eta 0:00:46 lr 0.000761	time 2.2538 (2.2004)	loss 3.4476 (3.7218)	grad_norm 1.3626 (1.2411)	
[2022-01-20 16:47:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1240/1251]	eta 0:00:24 lr 0.000761	time 2.5590 (2.1998)	loss 4.2844 (3.7198)	grad_norm 1.1520 (1.2407)	
[2022-01-20 16:47:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [97/300][1250/1251]	eta 0:00:02 lr 0.000761	time 1.1723 (2.1944)	loss 4.2055 (3.7190)	grad_norm 1.2302 (1.2402)	
[2022-01-20 16:47:25 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 97 training takes 0:45:45
[2022-01-20 16:47:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.440 (18.440)	Loss 1.0585 (1.0585)	Acc@1 75.293 (75.293)	Acc@5 93.164 (93.164)	
[2022-01-20 16:48:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.889 (3.510)	Loss 1.1907 (1.1041)	Acc@1 71.582 (74.503)	Acc@5 92.188 (92.152)	
[2022-01-20 16:48:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.262 (2.702)	Loss 1.1307 (1.1093)	Acc@1 72.656 (74.228)	Acc@5 92.285 (92.118)	
[2022-01-20 16:48:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.956 (2.392)	Loss 1.1443 (1.1186)	Acc@1 73.633 (74.017)	Acc@5 91.602 (92.011)	
[2022-01-20 16:48:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.257 (2.304)	Loss 1.0817 (1.1163)	Acc@1 74.609 (73.919)	Acc@5 92.188 (92.047)	
[2022-01-20 16:49:07 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.884 Acc@5 92.060
[2022-01-20 16:49:07 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.9%
[2022-01-20 16:49:07 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.88%
[2022-01-20 16:49:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][0/1251]	eta 7:28:13 lr 0.000761	time 21.4976 (21.4976)	loss 4.4248 (4.4248)	grad_norm 1.3332 (1.3332)	
[2022-01-20 16:49:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][10/1251]	eta 1:22:20 lr 0.000761	time 2.1477 (3.9813)	loss 4.4051 (3.5519)	grad_norm 1.0998 (1.2097)	
[2022-01-20 16:50:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][20/1251]	eta 1:05:19 lr 0.000761	time 1.9195 (3.1839)	loss 4.0061 (3.6784)	grad_norm 1.2071 (1.1953)	
[2022-01-20 16:50:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][30/1251]	eta 0:58:27 lr 0.000761	time 1.2846 (2.8729)	loss 4.7085 (3.7441)	grad_norm 1.4420 (1.2101)	
[2022-01-20 16:51:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][40/1251]	eta 0:55:45 lr 0.000761	time 3.8609 (2.7622)	loss 3.5145 (3.7625)	grad_norm 1.2369 (1.2450)	
[2022-01-20 16:51:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][50/1251]	eta 0:53:46 lr 0.000761	time 1.6765 (2.6862)	loss 3.9114 (3.7475)	grad_norm 1.1980 (1.2330)	
[2022-01-20 16:51:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][60/1251]	eta 0:51:30 lr 0.000761	time 1.6493 (2.5953)	loss 2.5695 (3.7111)	grad_norm 1.2036 (1.2272)	
[2022-01-20 16:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][70/1251]	eta 0:49:35 lr 0.000761	time 1.8455 (2.5191)	loss 3.1525 (3.6811)	grad_norm 1.1505 (1.2313)	
[2022-01-20 16:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][80/1251]	eta 0:48:06 lr 0.000761	time 2.6918 (2.4652)	loss 3.5186 (3.6682)	grad_norm 1.2763 (1.2293)	
[2022-01-20 16:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][90/1251]	eta 0:47:13 lr 0.000761	time 1.5624 (2.4403)	loss 3.7420 (3.6978)	grad_norm 1.3978 (1.2426)	
[2022-01-20 16:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][100/1251]	eta 0:46:24 lr 0.000761	time 1.8734 (2.4190)	loss 4.2977 (3.6999)	grad_norm 1.4443 (1.2579)	
[2022-01-20 16:53:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][110/1251]	eta 0:45:35 lr 0.000761	time 1.7729 (2.3977)	loss 3.3045 (3.6902)	grad_norm 1.3379 (1.2566)	
[2022-01-20 16:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][120/1251]	eta 0:44:47 lr 0.000761	time 2.5693 (2.3766)	loss 3.2611 (3.6655)	grad_norm 1.1764 (1.2498)	
[2022-01-20 16:54:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][130/1251]	eta 0:44:10 lr 0.000761	time 2.2233 (2.3645)	loss 3.7080 (3.6854)	grad_norm 1.4346 (1.2428)	
[2022-01-20 16:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][140/1251]	eta 0:43:32 lr 0.000761	time 2.7000 (2.3515)	loss 4.0421 (3.6799)	grad_norm 1.0365 (1.2417)	
[2022-01-20 16:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][150/1251]	eta 0:42:57 lr 0.000761	time 1.6568 (2.3413)	loss 3.8670 (3.6773)	grad_norm 1.0993 (1.2429)	
[2022-01-20 16:55:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][160/1251]	eta 0:42:20 lr 0.000761	time 1.9039 (2.3285)	loss 3.7711 (3.6868)	grad_norm 1.0872 (1.2394)	
[2022-01-20 16:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][170/1251]	eta 0:41:38 lr 0.000761	time 1.8610 (2.3111)	loss 4.1961 (3.6802)	grad_norm 1.4541 (1.2395)	
[2022-01-20 16:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][180/1251]	eta 0:41:13 lr 0.000761	time 2.8339 (2.3091)	loss 4.4489 (3.6837)	grad_norm 1.4880 (1.2384)	
[2022-01-20 16:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][190/1251]	eta 0:40:43 lr 0.000761	time 2.2898 (2.3035)	loss 4.0935 (3.6947)	grad_norm 1.0942 (1.2398)	
[2022-01-20 16:56:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][200/1251]	eta 0:40:17 lr 0.000761	time 1.8013 (2.3001)	loss 4.4513 (3.6941)	grad_norm 1.2723 (1.2404)	
[2022-01-20 16:57:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][210/1251]	eta 0:39:42 lr 0.000761	time 1.9090 (2.2884)	loss 3.8822 (3.6955)	grad_norm 1.2110 (1.2424)	
[2022-01-20 16:57:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][220/1251]	eta 0:39:10 lr 0.000761	time 2.2257 (2.2795)	loss 3.7279 (3.7108)	grad_norm 1.2734 (1.2422)	
[2022-01-20 16:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][230/1251]	eta 0:38:49 lr 0.000761	time 3.0182 (2.2813)	loss 3.6094 (3.7187)	grad_norm 1.5183 (1.2450)	
[2022-01-20 16:58:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][240/1251]	eta 0:38:23 lr 0.000761	time 2.2550 (2.2781)	loss 4.0598 (3.7179)	grad_norm 1.0218 (1.2431)	
[2022-01-20 16:58:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][250/1251]	eta 0:38:00 lr 0.000761	time 2.7489 (2.2787)	loss 3.0642 (3.7186)	grad_norm 1.3725 (1.2444)	
[2022-01-20 16:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][260/1251]	eta 0:37:36 lr 0.000761	time 1.8951 (2.2765)	loss 3.9697 (3.7098)	grad_norm 1.2166 (1.2440)	
[2022-01-20 16:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][270/1251]	eta 0:37:09 lr 0.000760	time 2.8155 (2.2730)	loss 4.0787 (3.7074)	grad_norm 1.0816 (1.2435)	
[2022-01-20 16:59:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][280/1251]	eta 0:36:34 lr 0.000760	time 1.5716 (2.2600)	loss 4.1467 (3.7011)	grad_norm 1.2923 (1.2415)	
[2022-01-20 17:00:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][290/1251]	eta 0:36:04 lr 0.000760	time 2.2831 (2.2528)	loss 4.1186 (3.7046)	grad_norm 1.2627 (1.2409)	
[2022-01-20 17:00:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][300/1251]	eta 0:35:37 lr 0.000760	time 2.2186 (2.2480)	loss 3.8741 (3.7106)	grad_norm 1.1641 (1.2432)	
[2022-01-20 17:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][310/1251]	eta 0:35:11 lr 0.000760	time 2.2071 (2.2443)	loss 4.5928 (3.7049)	grad_norm 1.1633 (1.2423)	
[2022-01-20 17:01:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][320/1251]	eta 0:34:48 lr 0.000760	time 2.1383 (2.2433)	loss 2.8148 (3.7012)	grad_norm 1.3221 (1.2421)	
[2022-01-20 17:01:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][330/1251]	eta 0:34:29 lr 0.000760	time 2.0140 (2.2475)	loss 3.8664 (3.7029)	grad_norm 1.4798 (1.2444)	
[2022-01-20 17:01:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][340/1251]	eta 0:34:09 lr 0.000760	time 2.1125 (2.2502)	loss 4.3998 (3.7007)	grad_norm 1.1122 (1.2443)	
[2022-01-20 17:02:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][350/1251]	eta 0:33:43 lr 0.000760	time 2.2152 (2.2458)	loss 3.9776 (3.7091)	grad_norm 1.2482 (1.2441)	
[2022-01-20 17:02:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][360/1251]	eta 0:33:17 lr 0.000760	time 2.2344 (2.2419)	loss 3.5445 (3.7105)	grad_norm 1.2973 (1.2471)	
[2022-01-20 17:02:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][370/1251]	eta 0:32:54 lr 0.000760	time 1.9098 (2.2408)	loss 3.9887 (3.7054)	grad_norm 1.2796 (1.2483)	
[2022-01-20 17:03:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][380/1251]	eta 0:32:28 lr 0.000760	time 2.2009 (2.2372)	loss 3.9493 (3.7098)	grad_norm 1.4652 (1.2502)	
[2022-01-20 17:03:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][390/1251]	eta 0:32:04 lr 0.000760	time 2.0280 (2.2351)	loss 3.6089 (3.7091)	grad_norm 1.3449 (1.2508)	
[2022-01-20 17:04:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][400/1251]	eta 0:31:44 lr 0.000760	time 2.2486 (2.2381)	loss 3.2227 (3.7145)	grad_norm 1.0858 (1.2512)	
[2022-01-20 17:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][410/1251]	eta 0:31:21 lr 0.000760	time 1.5616 (2.2376)	loss 4.0371 (3.7194)	grad_norm 1.2273 (1.2503)	
[2022-01-20 17:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][420/1251]	eta 0:30:56 lr 0.000760	time 1.9521 (2.2335)	loss 3.6158 (3.7218)	grad_norm 1.1734 (1.2504)	
[2022-01-20 17:05:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][430/1251]	eta 0:30:30 lr 0.000760	time 2.6458 (2.2300)	loss 3.7915 (3.7183)	grad_norm 1.3635 (1.2509)	
[2022-01-20 17:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][440/1251]	eta 0:30:06 lr 0.000760	time 1.7890 (2.2279)	loss 4.2613 (3.7239)	grad_norm 1.4292 (1.2510)	
[2022-01-20 17:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][450/1251]	eta 0:29:43 lr 0.000760	time 1.8321 (2.2267)	loss 4.0697 (3.7248)	grad_norm 1.1483 (1.2516)	
[2022-01-20 17:06:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][460/1251]	eta 0:29:19 lr 0.000760	time 1.9433 (2.2243)	loss 3.2082 (3.7233)	grad_norm 1.3886 (1.2527)	
[2022-01-20 17:06:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][470/1251]	eta 0:28:58 lr 0.000760	time 3.0975 (2.2255)	loss 2.9905 (3.7166)	grad_norm 1.0792 (1.2508)	
[2022-01-20 17:06:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][480/1251]	eta 0:28:37 lr 0.000760	time 2.0658 (2.2270)	loss 2.8695 (3.7169)	grad_norm 1.2104 (1.2503)	
[2022-01-20 17:07:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][490/1251]	eta 0:28:15 lr 0.000760	time 2.7061 (2.2286)	loss 2.6237 (3.7089)	grad_norm 1.4030 (1.2507)	
[2022-01-20 17:07:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][500/1251]	eta 0:27:52 lr 0.000760	time 1.6767 (2.2266)	loss 3.7341 (3.7097)	grad_norm 1.2074 (1.2490)	
[2022-01-20 17:08:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][510/1251]	eta 0:27:25 lr 0.000760	time 2.0660 (2.2205)	loss 4.1360 (3.7090)	grad_norm 1.2236 (1.2492)	
[2022-01-20 17:08:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][520/1251]	eta 0:26:59 lr 0.000760	time 2.1442 (2.2161)	loss 4.2274 (3.7107)	grad_norm 1.2173 (1.2484)	
[2022-01-20 17:08:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][530/1251]	eta 0:26:35 lr 0.000760	time 2.5575 (2.2129)	loss 4.1619 (3.7119)	grad_norm 1.1529 (1.2455)	
[2022-01-20 17:09:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][540/1251]	eta 0:26:13 lr 0.000760	time 2.6384 (2.2124)	loss 3.3277 (3.7093)	grad_norm 1.1988 (1.2457)	
[2022-01-20 17:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][550/1251]	eta 0:25:50 lr 0.000759	time 1.8440 (2.2119)	loss 2.6798 (3.7037)	grad_norm 1.2374 (1.2457)	
[2022-01-20 17:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][560/1251]	eta 0:25:29 lr 0.000759	time 1.9485 (2.2136)	loss 4.3539 (3.7056)	grad_norm 1.1964 (1.2470)	
[2022-01-20 17:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][570/1251]	eta 0:25:07 lr 0.000759	time 1.8532 (2.2141)	loss 3.6569 (3.7092)	grad_norm 1.3828 (1.2459)	
[2022-01-20 17:10:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][580/1251]	eta 0:24:44 lr 0.000759	time 1.8824 (2.2131)	loss 3.2137 (3.7083)	grad_norm 1.1519 (1.2457)	
[2022-01-20 17:10:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][590/1251]	eta 0:24:22 lr 0.000759	time 2.0583 (2.2120)	loss 4.1008 (3.7076)	grad_norm 1.1606 (1.2452)	
[2022-01-20 17:11:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][600/1251]	eta 0:23:59 lr 0.000759	time 2.2396 (2.2114)	loss 3.9900 (3.7120)	grad_norm 1.2110 (1.2452)	
[2022-01-20 17:11:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][610/1251]	eta 0:23:39 lr 0.000759	time 2.0892 (2.2141)	loss 3.5629 (3.7071)	grad_norm 1.3806 (1.2454)	
[2022-01-20 17:12:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][620/1251]	eta 0:23:18 lr 0.000759	time 1.8981 (2.2159)	loss 3.0715 (3.7040)	grad_norm 1.2217 (1.2452)	
[2022-01-20 17:12:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][630/1251]	eta 0:22:56 lr 0.000759	time 2.1249 (2.2168)	loss 4.1324 (3.7052)	grad_norm 1.3640 (1.2466)	
[2022-01-20 17:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][640/1251]	eta 0:22:34 lr 0.000759	time 1.5312 (2.2170)	loss 2.7202 (3.7032)	grad_norm 1.1885 (1.2467)	
[2022-01-20 17:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][650/1251]	eta 0:22:12 lr 0.000759	time 3.6357 (2.2175)	loss 3.2829 (3.7012)	grad_norm 1.2947 (1.2468)	
[2022-01-20 17:13:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][660/1251]	eta 0:21:47 lr 0.000759	time 1.6441 (2.2130)	loss 2.9225 (3.7050)	grad_norm 1.2861 (1.2484)	
[2022-01-20 17:13:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][670/1251]	eta 0:21:24 lr 0.000759	time 1.8630 (2.2111)	loss 3.7603 (3.7043)	grad_norm 1.2024 (1.2476)	
[2022-01-20 17:14:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][680/1251]	eta 0:21:02 lr 0.000759	time 1.6501 (2.2106)	loss 4.4606 (3.7063)	grad_norm 1.1527 (1.2469)	
[2022-01-20 17:14:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][690/1251]	eta 0:20:39 lr 0.000759	time 2.7670 (2.2098)	loss 4.1112 (3.7083)	grad_norm 1.1140 (1.2459)	
[2022-01-20 17:14:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][700/1251]	eta 0:20:18 lr 0.000759	time 1.8656 (2.2110)	loss 2.9084 (3.7111)	grad_norm 1.0472 (1.2448)	
[2022-01-20 17:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][710/1251]	eta 0:19:57 lr 0.000759	time 1.8753 (2.2128)	loss 2.7618 (3.7098)	grad_norm 1.1353 (1.2446)	
[2022-01-20 17:15:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][720/1251]	eta 0:19:35 lr 0.000759	time 2.3437 (2.2144)	loss 3.5035 (3.7114)	grad_norm 1.3245 (1.2442)	
[2022-01-20 17:16:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][730/1251]	eta 0:19:14 lr 0.000759	time 3.3998 (2.2160)	loss 4.0738 (3.7122)	grad_norm 1.2384 (1.2440)	
[2022-01-20 17:16:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][740/1251]	eta 0:18:50 lr 0.000759	time 1.9842 (2.2131)	loss 3.3815 (3.7148)	grad_norm 1.1582 (1.2447)	
[2022-01-20 17:16:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][750/1251]	eta 0:18:27 lr 0.000759	time 2.1783 (2.2101)	loss 3.0363 (3.7131)	grad_norm 1.3042 (1.2443)	
[2022-01-20 17:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][760/1251]	eta 0:18:04 lr 0.000759	time 2.2358 (2.2087)	loss 3.1663 (3.7091)	grad_norm 1.5121 (1.2445)	
[2022-01-20 17:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][770/1251]	eta 0:17:42 lr 0.000759	time 2.1326 (2.2086)	loss 4.0054 (3.7093)	grad_norm 1.1576 (1.2446)	
[2022-01-20 17:17:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][780/1251]	eta 0:17:19 lr 0.000759	time 2.5164 (2.2081)	loss 4.0107 (3.7112)	grad_norm 1.3232 (1.2459)	
[2022-01-20 17:18:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][790/1251]	eta 0:16:57 lr 0.000759	time 2.5572 (2.2071)	loss 4.5441 (3.7153)	grad_norm 1.2192 (1.2476)	
[2022-01-20 17:18:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][800/1251]	eta 0:16:34 lr 0.000759	time 1.9251 (2.2060)	loss 3.1881 (3.7141)	grad_norm 1.1116 (1.2471)	
[2022-01-20 17:18:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][810/1251]	eta 0:16:13 lr 0.000759	time 1.9040 (2.2067)	loss 3.7884 (3.7089)	grad_norm 1.2648 (1.2481)	
[2022-01-20 17:19:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][820/1251]	eta 0:15:51 lr 0.000759	time 2.3507 (2.2076)	loss 3.2951 (3.7081)	grad_norm 1.2239 (1.2491)	
[2022-01-20 17:19:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][830/1251]	eta 0:15:29 lr 0.000758	time 2.5201 (2.2072)	loss 4.0599 (3.7048)	grad_norm 1.2175 (1.2490)	
[2022-01-20 17:20:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][840/1251]	eta 0:15:07 lr 0.000758	time 2.7525 (2.2075)	loss 2.6485 (3.7029)	grad_norm 1.1195 (1.2488)	
[2022-01-20 17:20:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][850/1251]	eta 0:14:45 lr 0.000758	time 1.6901 (2.2072)	loss 4.1175 (3.7026)	grad_norm 1.3158 (1.2490)	
[2022-01-20 17:20:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][860/1251]	eta 0:14:23 lr 0.000758	time 2.4984 (2.2076)	loss 4.3095 (3.7048)	grad_norm 1.2469 (1.2489)	
[2022-01-20 17:21:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][870/1251]	eta 0:14:01 lr 0.000758	time 2.0768 (2.2075)	loss 3.7467 (3.7032)	grad_norm 1.1168 (1.2475)	
[2022-01-20 17:21:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][880/1251]	eta 0:13:38 lr 0.000758	time 1.5923 (2.2068)	loss 4.0586 (3.7056)	grad_norm 1.3648 (1.2483)	
[2022-01-20 17:21:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][890/1251]	eta 0:13:16 lr 0.000758	time 1.9523 (2.2068)	loss 4.0063 (3.7074)	grad_norm 1.3006 (1.2479)	
[2022-01-20 17:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][900/1251]	eta 0:12:54 lr 0.000758	time 2.1198 (2.2051)	loss 3.3547 (3.7073)	grad_norm 1.0169 (1.2472)	
[2022-01-20 17:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][910/1251]	eta 0:12:31 lr 0.000758	time 2.6496 (2.2040)	loss 4.2038 (3.7078)	grad_norm 0.9805 (1.2462)	
[2022-01-20 17:22:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][920/1251]	eta 0:12:09 lr 0.000758	time 1.8740 (2.2025)	loss 4.6044 (3.7092)	grad_norm 1.0182 (1.2456)	
[2022-01-20 17:23:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][930/1251]	eta 0:11:46 lr 0.000758	time 1.6265 (2.2019)	loss 3.9735 (3.7106)	grad_norm 1.3504 (1.2446)	
[2022-01-20 17:23:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][940/1251]	eta 0:11:24 lr 0.000758	time 2.3112 (2.2022)	loss 2.8868 (3.7114)	grad_norm 1.3280 (1.2444)	
[2022-01-20 17:24:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][950/1251]	eta 0:11:03 lr 0.000758	time 3.6812 (2.2047)	loss 4.1410 (3.7149)	grad_norm 1.1526 (1.2436)	
[2022-01-20 17:24:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][960/1251]	eta 0:10:41 lr 0.000758	time 2.1921 (2.2044)	loss 3.8468 (3.7154)	grad_norm 1.2656 (1.2441)	
[2022-01-20 17:24:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][970/1251]	eta 0:10:19 lr 0.000758	time 1.9133 (2.2032)	loss 3.9571 (3.7144)	grad_norm 1.4004 (1.2440)	
[2022-01-20 17:25:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][980/1251]	eta 0:09:56 lr 0.000758	time 2.1566 (2.2016)	loss 3.1087 (3.7158)	grad_norm 1.1916 (1.2435)	
[2022-01-20 17:25:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][990/1251]	eta 0:09:34 lr 0.000758	time 2.5049 (2.2007)	loss 4.3292 (3.7144)	grad_norm 1.2717 (1.2436)	
[2022-01-20 17:25:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1000/1251]	eta 0:09:12 lr 0.000758	time 2.1916 (2.2000)	loss 4.0164 (3.7145)	grad_norm 1.1083 (1.2436)	
[2022-01-20 17:26:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1010/1251]	eta 0:08:50 lr 0.000758	time 1.4538 (2.2005)	loss 2.9003 (3.7142)	grad_norm 1.1547 (1.2439)	
[2022-01-20 17:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1020/1251]	eta 0:08:28 lr 0.000758	time 1.8865 (2.2012)	loss 4.4873 (3.7153)	grad_norm 1.1547 (1.2431)	
[2022-01-20 17:26:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1030/1251]	eta 0:08:06 lr 0.000758	time 1.9520 (2.2025)	loss 3.6869 (3.7148)	grad_norm 1.3162 (1.2429)	
[2022-01-20 17:27:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1040/1251]	eta 0:07:45 lr 0.000758	time 3.0666 (2.2046)	loss 3.9005 (3.7168)	grad_norm 1.3154 (1.2432)	
[2022-01-20 17:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1050/1251]	eta 0:07:23 lr 0.000758	time 1.4655 (2.2050)	loss 4.0510 (3.7179)	grad_norm 1.6459 (1.2436)	
[2022-01-20 17:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1060/1251]	eta 0:07:00 lr 0.000758	time 1.7411 (2.2036)	loss 4.1602 (3.7183)	grad_norm 1.1831 (1.2442)	
[2022-01-20 17:28:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1070/1251]	eta 0:06:38 lr 0.000758	time 2.2022 (2.2015)	loss 2.6453 (3.7172)	grad_norm 1.1584 (1.2443)	
[2022-01-20 17:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1080/1251]	eta 0:06:16 lr 0.000758	time 1.6302 (2.2006)	loss 4.2308 (3.7196)	grad_norm 1.2193 (1.2443)	
[2022-01-20 17:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1090/1251]	eta 0:05:54 lr 0.000758	time 1.7916 (2.2006)	loss 3.9071 (3.7189)	grad_norm 1.4408 (1.2446)	
[2022-01-20 17:29:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1100/1251]	eta 0:05:32 lr 0.000758	time 2.2445 (2.2022)	loss 3.8371 (3.7184)	grad_norm 1.3561 (1.2450)	
[2022-01-20 17:29:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1110/1251]	eta 0:05:10 lr 0.000757	time 2.1941 (2.2026)	loss 4.0538 (3.7174)	grad_norm 1.3189 (1.2452)	
[2022-01-20 17:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1120/1251]	eta 0:04:48 lr 0.000757	time 2.2080 (2.2047)	loss 3.7354 (3.7189)	grad_norm 1.2146 (1.2451)	
[2022-01-20 17:30:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1130/1251]	eta 0:04:26 lr 0.000757	time 1.6044 (2.2039)	loss 2.7514 (3.7181)	grad_norm 1.2078 (1.2447)	
[2022-01-20 17:31:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1140/1251]	eta 0:04:04 lr 0.000757	time 1.6000 (2.2021)	loss 3.7259 (3.7174)	grad_norm 1.1924 (1.2454)	
[2022-01-20 17:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1150/1251]	eta 0:03:42 lr 0.000757	time 1.6344 (2.1997)	loss 4.3087 (3.7181)	grad_norm 1.2862 (1.2451)	
[2022-01-20 17:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1160/1251]	eta 0:03:20 lr 0.000757	time 1.9705 (2.2002)	loss 4.1227 (3.7169)	grad_norm 1.1367 (1.2449)	
[2022-01-20 17:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1170/1251]	eta 0:02:58 lr 0.000757	time 2.4581 (2.1994)	loss 4.6168 (3.7188)	grad_norm 1.3244 (1.2447)	
[2022-01-20 17:32:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1180/1251]	eta 0:02:36 lr 0.000757	time 1.9382 (2.1989)	loss 2.5326 (3.7190)	grad_norm 1.2249 (1.2443)	
[2022-01-20 17:32:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1190/1251]	eta 0:02:14 lr 0.000757	time 1.8716 (2.1984)	loss 4.1011 (3.7177)	grad_norm 1.2732 (1.2444)	
[2022-01-20 17:33:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1200/1251]	eta 0:01:52 lr 0.000757	time 2.2404 (2.1991)	loss 2.7750 (3.7192)	grad_norm 1.3626 (1.2440)	
[2022-01-20 17:33:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1210/1251]	eta 0:01:30 lr 0.000757	time 2.4492 (2.1994)	loss 3.8853 (3.7168)	grad_norm 1.1158 (1.2440)	
[2022-01-20 17:33:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1220/1251]	eta 0:01:08 lr 0.000757	time 2.5151 (2.2016)	loss 3.5105 (3.7168)	grad_norm 1.0930 (1.2440)	
[2022-01-20 17:34:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1230/1251]	eta 0:00:46 lr 0.000757	time 2.5626 (2.2031)	loss 3.2546 (3.7162)	grad_norm 1.1067 (1.2435)	
[2022-01-20 17:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1240/1251]	eta 0:00:24 lr 0.000757	time 1.8063 (2.2018)	loss 4.3438 (3.7137)	grad_norm 1.1963 (1.2430)	
[2022-01-20 17:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [98/300][1250/1251]	eta 0:00:02 lr 0.000757	time 1.1909 (2.1957)	loss 4.0004 (3.7160)	grad_norm 1.1702 (1.2427)	
[2022-01-20 17:34:54 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 98 training takes 0:45:47
[2022-01-20 17:35:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.992 (17.992)	Loss 1.0703 (1.0703)	Acc@1 73.730 (73.730)	Acc@5 92.285 (92.285)	
[2022-01-20 17:35:32 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.325 (3.444)	Loss 1.1786 (1.1107)	Acc@1 73.438 (73.580)	Acc@5 91.211 (92.312)	
[2022-01-20 17:35:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.597 (2.692)	Loss 1.0629 (1.1004)	Acc@1 75.879 (73.893)	Acc@5 92.285 (92.229)	
[2022-01-20 17:36:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.295 (2.299)	Loss 1.0627 (1.1028)	Acc@1 73.730 (73.866)	Acc@5 92.969 (92.210)	
[2022-01-20 17:36:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.805 (2.137)	Loss 1.1058 (1.1116)	Acc@1 73.828 (73.690)	Acc@5 92.773 (92.126)	
[2022-01-20 17:36:29 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.618 Acc@5 92.116
[2022-01-20 17:36:29 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.6%
[2022-01-20 17:36:29 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.88%
[2022-01-20 17:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][0/1251]	eta 7:29:56 lr 0.000757	time 21.5798 (21.5798)	loss 2.9616 (2.9616)	grad_norm 1.2396 (1.2396)	
[2022-01-20 17:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][10/1251]	eta 1:23:34 lr 0.000757	time 1.8712 (4.0405)	loss 3.8724 (3.3987)	grad_norm 1.1150 (1.1627)	
[2022-01-20 17:37:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][20/1251]	eta 1:04:04 lr 0.000757	time 1.3985 (3.1230)	loss 4.0261 (3.6906)	grad_norm 1.2398 (1.1914)	
[2022-01-20 17:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][30/1251]	eta 0:56:07 lr 0.000757	time 1.9452 (2.7581)	loss 3.3058 (3.7341)	grad_norm 1.4269 (1.2144)	
[2022-01-20 17:38:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][40/1251]	eta 0:55:09 lr 0.000757	time 5.5570 (2.7330)	loss 3.8552 (3.7544)	grad_norm 1.2529 (1.2061)	
[2022-01-20 17:38:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][50/1251]	eta 0:52:40 lr 0.000757	time 1.4520 (2.6319)	loss 3.7721 (3.7528)	grad_norm 1.2952 (1.2157)	
[2022-01-20 17:39:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][60/1251]	eta 0:50:56 lr 0.000757	time 1.9325 (2.5664)	loss 3.7256 (3.6968)	grad_norm 1.1889 (1.2158)	
[2022-01-20 17:39:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][70/1251]	eta 0:49:56 lr 0.000757	time 2.1549 (2.5377)	loss 3.3690 (3.7065)	grad_norm 1.3920 (1.2314)	
[2022-01-20 17:39:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][80/1251]	eta 0:48:50 lr 0.000757	time 3.9740 (2.5025)	loss 3.0915 (3.7177)	grad_norm 1.1812 (1.2351)	
[2022-01-20 17:40:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][90/1251]	eta 0:47:23 lr 0.000757	time 1.6352 (2.4490)	loss 3.4081 (3.7213)	grad_norm 1.1979 (1.2385)	
[2022-01-20 17:40:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][100/1251]	eta 0:46:04 lr 0.000757	time 1.9096 (2.4017)	loss 2.6268 (3.6654)	grad_norm 1.4692 (1.2489)	
[2022-01-20 17:40:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][110/1251]	eta 0:45:23 lr 0.000757	time 2.2763 (2.3868)	loss 2.8430 (3.6637)	grad_norm 1.1671 (1.2486)	
[2022-01-20 17:41:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][120/1251]	eta 0:44:54 lr 0.000757	time 2.8030 (2.3821)	loss 2.9950 (3.6671)	grad_norm 1.6062 (1.2514)	
[2022-01-20 17:41:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][130/1251]	eta 0:44:16 lr 0.000757	time 2.1322 (2.3697)	loss 2.6396 (3.6357)	grad_norm 1.3159 (1.2526)	
[2022-01-20 17:42:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][140/1251]	eta 0:43:39 lr 0.000756	time 1.8981 (2.3576)	loss 3.1249 (3.6273)	grad_norm 1.2501 (1.2506)	
[2022-01-20 17:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][150/1251]	eta 0:43:03 lr 0.000756	time 1.9779 (2.3467)	loss 3.8801 (3.6263)	grad_norm 1.1481 (1.2503)	
[2022-01-20 17:42:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][160/1251]	eta 0:42:25 lr 0.000756	time 2.8948 (2.3336)	loss 4.2783 (3.6490)	grad_norm 1.3143 (1.2520)	
[2022-01-20 17:43:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][170/1251]	eta 0:41:43 lr 0.000756	time 1.6265 (2.3157)	loss 2.8434 (3.6561)	grad_norm 1.4003 (1.2555)	
[2022-01-20 17:43:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][180/1251]	eta 0:41:07 lr 0.000756	time 2.1593 (2.3043)	loss 4.1321 (3.6568)	grad_norm 1.2213 (1.2523)	
[2022-01-20 17:43:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][190/1251]	eta 0:40:37 lr 0.000756	time 2.0388 (2.2975)	loss 3.7266 (3.6720)	grad_norm 1.1009 (1.2502)	
[2022-01-20 17:44:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][200/1251]	eta 0:40:16 lr 0.000756	time 3.0700 (2.2996)	loss 3.2379 (3.6587)	grad_norm 1.1782 (1.2492)	
[2022-01-20 17:44:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][210/1251]	eta 0:39:56 lr 0.000756	time 2.1503 (2.3020)	loss 3.8449 (3.6631)	grad_norm 1.1120 (1.2450)	
[2022-01-20 17:44:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][220/1251]	eta 0:39:33 lr 0.000756	time 2.0507 (2.3021)	loss 3.3499 (3.6557)	grad_norm 1.3888 (1.2422)	
[2022-01-20 17:45:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][230/1251]	eta 0:38:59 lr 0.000756	time 1.9222 (2.2915)	loss 2.9153 (3.6546)	grad_norm 1.2082 (1.2401)	
[2022-01-20 17:45:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][240/1251]	eta 0:38:18 lr 0.000756	time 1.8530 (2.2737)	loss 4.5423 (3.6709)	grad_norm 1.1535 (1.2378)	
[2022-01-20 17:45:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][250/1251]	eta 0:37:40 lr 0.000756	time 1.6907 (2.2585)	loss 3.8655 (3.6731)	grad_norm 1.3652 (1.2380)	
[2022-01-20 17:46:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][260/1251]	eta 0:37:13 lr 0.000756	time 2.1829 (2.2537)	loss 3.5535 (3.6835)	grad_norm 1.0751 (1.2374)	
[2022-01-20 17:46:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][270/1251]	eta 0:36:46 lr 0.000756	time 2.6038 (2.2495)	loss 4.0701 (3.6817)	grad_norm 1.3541 (1.2373)	
[2022-01-20 17:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][280/1251]	eta 0:36:31 lr 0.000756	time 2.3418 (2.2566)	loss 3.4810 (3.6770)	grad_norm 1.1532 (1.2395)	
[2022-01-20 17:47:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][290/1251]	eta 0:36:19 lr 0.000756	time 2.1660 (2.2683)	loss 4.0438 (3.6758)	grad_norm 1.2615 (1.2417)	
[2022-01-20 17:47:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][300/1251]	eta 0:36:04 lr 0.000756	time 2.5309 (2.2756)	loss 2.6764 (3.6673)	grad_norm 1.0810 (1.2418)	
[2022-01-20 17:48:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][310/1251]	eta 0:35:40 lr 0.000756	time 2.0755 (2.2752)	loss 3.9076 (3.6722)	grad_norm 1.2844 (1.2426)	
[2022-01-20 17:48:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][320/1251]	eta 0:35:13 lr 0.000756	time 1.9726 (2.2698)	loss 3.7895 (3.6728)	grad_norm 1.1816 (1.2445)	
[2022-01-20 17:48:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][330/1251]	eta 0:34:41 lr 0.000756	time 2.0656 (2.2598)	loss 4.0143 (3.6747)	grad_norm 1.3978 (1.2440)	
[2022-01-20 17:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][340/1251]	eta 0:34:10 lr 0.000756	time 2.4336 (2.2513)	loss 3.7442 (3.6807)	grad_norm 1.1765 (1.2456)	
[2022-01-20 17:49:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][350/1251]	eta 0:33:43 lr 0.000756	time 2.3433 (2.2453)	loss 3.4196 (3.6849)	grad_norm 1.1796 (1.2462)	
[2022-01-20 17:49:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][360/1251]	eta 0:33:15 lr 0.000756	time 1.8742 (2.2402)	loss 3.9604 (3.6794)	grad_norm 1.1528 (1.2473)	
[2022-01-20 17:50:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][370/1251]	eta 0:32:52 lr 0.000756	time 1.5637 (2.2390)	loss 3.9607 (3.6880)	grad_norm 1.4162 (1.2497)	
[2022-01-20 17:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][380/1251]	eta 0:32:31 lr 0.000756	time 2.3289 (2.2402)	loss 3.9716 (3.6945)	grad_norm 1.7197 (1.2545)	
[2022-01-20 17:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][390/1251]	eta 0:32:07 lr 0.000756	time 1.6349 (2.2385)	loss 4.3425 (3.7006)	grad_norm 1.4130 (1.2565)	
[2022-01-20 17:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][400/1251]	eta 0:31:44 lr 0.000756	time 2.8552 (2.2379)	loss 3.4346 (3.7033)	grad_norm 1.3341 (1.2580)	
[2022-01-20 17:51:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][410/1251]	eta 0:31:23 lr 0.000756	time 2.0274 (2.2400)	loss 3.8775 (3.7050)	grad_norm 1.3215 (1.2590)	
[2022-01-20 17:52:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][420/1251]	eta 0:31:04 lr 0.000755	time 2.7756 (2.2442)	loss 3.4522 (3.7030)	grad_norm 1.1469 (1.2579)	
[2022-01-20 17:52:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][430/1251]	eta 0:30:42 lr 0.000755	time 1.8507 (2.2442)	loss 3.9578 (3.7072)	grad_norm 1.1790 (1.2566)	
[2022-01-20 17:52:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][440/1251]	eta 0:30:19 lr 0.000755	time 2.8356 (2.2441)	loss 4.1409 (3.7048)	grad_norm 1.0993 (1.2570)	
[2022-01-20 17:53:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][450/1251]	eta 0:29:56 lr 0.000755	time 1.6333 (2.2433)	loss 3.1046 (3.7095)	grad_norm 1.1833 (1.2566)	
[2022-01-20 17:53:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][460/1251]	eta 0:29:34 lr 0.000755	time 3.2518 (2.2434)	loss 4.4867 (3.7139)	grad_norm 1.4149 (1.2584)	
[2022-01-20 17:54:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][470/1251]	eta 0:29:07 lr 0.000755	time 1.5806 (2.2374)	loss 2.8342 (3.7096)	grad_norm 1.2900 (1.2583)	
[2022-01-20 17:54:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][480/1251]	eta 0:28:42 lr 0.000755	time 1.8113 (2.2341)	loss 3.9073 (3.7055)	grad_norm 1.2697 (1.2581)	
[2022-01-20 17:54:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][490/1251]	eta 0:28:20 lr 0.000755	time 2.2180 (2.2342)	loss 2.5618 (3.7066)	grad_norm 1.0586 (1.2579)	
[2022-01-20 17:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][500/1251]	eta 0:28:02 lr 0.000755	time 3.3981 (2.2406)	loss 2.8732 (3.7062)	grad_norm 1.2719 (1.2569)	
[2022-01-20 17:55:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][510/1251]	eta 0:27:39 lr 0.000755	time 1.7702 (2.2400)	loss 2.7279 (3.7009)	grad_norm 1.2581 (1.2567)	
[2022-01-20 17:55:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][520/1251]	eta 0:27:15 lr 0.000755	time 1.9180 (2.2370)	loss 2.4093 (3.7009)	grad_norm 1.2285 (1.2575)	
[2022-01-20 17:56:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][530/1251]	eta 0:26:50 lr 0.000755	time 1.9349 (2.2336)	loss 4.1471 (3.6940)	grad_norm 1.3369 (1.2582)	
[2022-01-20 17:56:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][540/1251]	eta 0:26:28 lr 0.000755	time 2.7404 (2.2335)	loss 4.0333 (3.6917)	grad_norm 1.2067 (1.2580)	
[2022-01-20 17:57:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][550/1251]	eta 0:26:06 lr 0.000755	time 2.2861 (2.2341)	loss 2.7716 (3.6935)	grad_norm 1.3887 (1.2578)	
[2022-01-20 17:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][560/1251]	eta 0:25:45 lr 0.000755	time 1.9999 (2.2363)	loss 3.9366 (3.6922)	grad_norm 1.2337 (1.2584)	
[2022-01-20 17:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][570/1251]	eta 0:25:22 lr 0.000755	time 1.8930 (2.2357)	loss 4.1119 (3.6937)	grad_norm 1.4377 (1.2606)	
[2022-01-20 17:58:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][580/1251]	eta 0:25:02 lr 0.000755	time 2.7830 (2.2387)	loss 2.9087 (3.6923)	grad_norm 1.2314 (1.2598)	
[2022-01-20 17:58:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][590/1251]	eta 0:24:37 lr 0.000755	time 1.8402 (2.2350)	loss 3.9406 (3.6916)	grad_norm 1.2476 (1.2584)	
[2022-01-20 17:58:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][600/1251]	eta 0:24:11 lr 0.000755	time 1.6061 (2.2291)	loss 4.2392 (3.6938)	grad_norm 1.2251 (1.2587)	
[2022-01-20 17:59:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][610/1251]	eta 0:23:46 lr 0.000755	time 2.0856 (2.2256)	loss 3.7794 (3.6949)	grad_norm 1.1410 (1.2589)	
[2022-01-20 17:59:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][620/1251]	eta 0:23:23 lr 0.000755	time 2.1988 (2.2242)	loss 4.0745 (3.6917)	grad_norm 1.5273 (1.2589)	
[2022-01-20 17:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][630/1251]	eta 0:23:01 lr 0.000755	time 2.0508 (2.2239)	loss 4.2021 (3.6894)	grad_norm 1.2599 (1.2596)	
[2022-01-20 18:00:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][640/1251]	eta 0:22:38 lr 0.000755	time 2.3022 (2.2235)	loss 4.4815 (3.6928)	grad_norm 1.0894 (1.2584)	
[2022-01-20 18:00:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][650/1251]	eta 0:22:17 lr 0.000755	time 1.9157 (2.2255)	loss 4.0447 (3.6962)	grad_norm 1.1783 (1.2571)	
[2022-01-20 18:01:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][660/1251]	eta 0:21:55 lr 0.000755	time 2.5635 (2.2261)	loss 4.0829 (3.6968)	grad_norm 1.1635 (1.2567)	
[2022-01-20 18:01:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][670/1251]	eta 0:21:32 lr 0.000755	time 1.9063 (2.2239)	loss 4.1775 (3.6948)	grad_norm 1.2375 (1.2561)	
[2022-01-20 18:01:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][680/1251]	eta 0:21:08 lr 0.000755	time 2.0233 (2.2222)	loss 4.1771 (3.6934)	grad_norm 1.1780 (1.2562)	
[2022-01-20 18:02:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][690/1251]	eta 0:20:45 lr 0.000755	time 1.9462 (2.2199)	loss 3.1112 (3.6906)	grad_norm 1.2229 (1.2547)	
[2022-01-20 18:02:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][700/1251]	eta 0:20:23 lr 0.000754	time 2.5724 (2.2200)	loss 3.5625 (3.6937)	grad_norm 1.4791 (1.2539)	
[2022-01-20 18:02:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][710/1251]	eta 0:20:01 lr 0.000754	time 2.3123 (2.2208)	loss 3.7413 (3.6900)	grad_norm 1.2370 (1.2540)	
[2022-01-20 18:03:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][720/1251]	eta 0:19:39 lr 0.000754	time 2.5042 (2.2204)	loss 3.6211 (3.6889)	grad_norm 1.2210 (1.2545)	
[2022-01-20 18:03:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][730/1251]	eta 0:19:17 lr 0.000754	time 1.8485 (2.2217)	loss 4.5272 (3.6881)	grad_norm 1.1942 (1.2556)	
[2022-01-20 18:03:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][740/1251]	eta 0:18:54 lr 0.000754	time 1.7468 (2.2201)	loss 3.5440 (3.6899)	grad_norm 1.3582 (1.2562)	
[2022-01-20 18:04:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][750/1251]	eta 0:18:31 lr 0.000754	time 1.8677 (2.2178)	loss 4.0050 (3.6942)	grad_norm 1.1939 (1.2572)	
[2022-01-20 18:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][760/1251]	eta 0:18:08 lr 0.000754	time 3.2684 (2.2174)	loss 4.2068 (3.6948)	grad_norm 1.1377 (1.2563)	
[2022-01-20 18:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][770/1251]	eta 0:17:46 lr 0.000754	time 1.8860 (2.2180)	loss 4.1882 (3.6923)	grad_norm 1.2048 (1.2563)	
[2022-01-20 18:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][780/1251]	eta 0:17:23 lr 0.000754	time 1.6761 (2.2160)	loss 4.4086 (3.6933)	grad_norm 1.6622 (1.2587)	
[2022-01-20 18:05:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][790/1251]	eta 0:17:01 lr 0.000754	time 1.7889 (2.2163)	loss 4.3989 (3.6971)	grad_norm 1.4457 (1.2594)	
[2022-01-20 18:06:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][800/1251]	eta 0:16:40 lr 0.000754	time 3.7673 (2.2175)	loss 4.1228 (3.6966)	grad_norm 1.0861 (1.2600)	
[2022-01-20 18:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][810/1251]	eta 0:16:17 lr 0.000754	time 2.2229 (2.2170)	loss 3.7927 (3.7019)	grad_norm 1.3848 (1.2605)	
[2022-01-20 18:06:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][820/1251]	eta 0:15:54 lr 0.000754	time 1.6377 (2.2141)	loss 4.4335 (3.7034)	grad_norm 1.2402 (1.2597)	
[2022-01-20 18:07:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][830/1251]	eta 0:15:31 lr 0.000754	time 1.8480 (2.2136)	loss 3.7143 (3.7054)	grad_norm 1.2672 (1.2589)	
[2022-01-20 18:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][840/1251]	eta 0:15:10 lr 0.000754	time 2.7010 (2.2153)	loss 3.1565 (3.7047)	grad_norm 1.2957 (1.2590)	
[2022-01-20 18:07:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][850/1251]	eta 0:14:47 lr 0.000754	time 1.5615 (2.2138)	loss 3.2401 (3.7045)	grad_norm 1.3149 (1.2582)	
[2022-01-20 18:08:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][860/1251]	eta 0:14:24 lr 0.000754	time 1.7504 (2.2117)	loss 3.9542 (3.7078)	grad_norm 1.1781 (1.2575)	
[2022-01-20 18:08:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][870/1251]	eta 0:14:02 lr 0.000754	time 1.6680 (2.2104)	loss 2.6443 (3.7062)	grad_norm 1.0559 (1.2560)	
[2022-01-20 18:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][880/1251]	eta 0:13:40 lr 0.000754	time 1.6936 (2.2110)	loss 4.5878 (3.7077)	grad_norm 1.2610 (1.2558)	
[2022-01-20 18:09:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][890/1251]	eta 0:13:17 lr 0.000754	time 1.8902 (2.2104)	loss 3.6526 (3.7075)	grad_norm 1.1808 (1.2553)	
[2022-01-20 18:09:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][900/1251]	eta 0:12:55 lr 0.000754	time 2.5174 (2.2104)	loss 3.1060 (3.7082)	grad_norm 1.1511 (1.2551)	
[2022-01-20 18:10:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][910/1251]	eta 0:12:33 lr 0.000754	time 1.9142 (2.2104)	loss 2.8219 (3.7049)	grad_norm 1.0361 (1.2540)	
[2022-01-20 18:10:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][920/1251]	eta 0:12:11 lr 0.000754	time 1.6518 (2.2107)	loss 4.0802 (3.7067)	grad_norm 1.1742 (1.2533)	
[2022-01-20 18:10:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][930/1251]	eta 0:11:49 lr 0.000754	time 1.8877 (2.2100)	loss 3.8866 (3.7041)	grad_norm 1.2063 (1.2530)	
[2022-01-20 18:11:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][940/1251]	eta 0:11:26 lr 0.000754	time 2.1537 (2.2090)	loss 4.1205 (3.7069)	grad_norm 1.3688 (1.2532)	
[2022-01-20 18:11:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][950/1251]	eta 0:11:04 lr 0.000754	time 2.4296 (2.2087)	loss 4.5621 (3.7106)	grad_norm 1.1493 (1.2533)	
[2022-01-20 18:11:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][960/1251]	eta 0:10:42 lr 0.000754	time 1.8540 (2.2092)	loss 2.7482 (3.7076)	grad_norm 1.1122 (1.2530)	
[2022-01-20 18:12:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][970/1251]	eta 0:10:20 lr 0.000754	time 2.0233 (2.2073)	loss 3.9519 (3.7102)	grad_norm 1.1621 (1.2524)	
[2022-01-20 18:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][980/1251]	eta 0:09:58 lr 0.000753	time 2.1023 (2.2071)	loss 4.5167 (3.7108)	grad_norm 1.2760 (1.2520)	
[2022-01-20 18:12:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][990/1251]	eta 0:09:35 lr 0.000753	time 1.8302 (2.2064)	loss 3.5506 (3.7113)	grad_norm 1.4897 (1.2526)	
[2022-01-20 18:13:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1000/1251]	eta 0:09:13 lr 0.000753	time 1.5221 (2.2067)	loss 3.2286 (3.7124)	grad_norm 1.0836 (1.2518)	
[2022-01-20 18:13:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1010/1251]	eta 0:08:51 lr 0.000753	time 2.9119 (2.2074)	loss 4.0046 (3.7132)	grad_norm 1.0267 (1.2512)	
[2022-01-20 18:14:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1020/1251]	eta 0:08:29 lr 0.000753	time 2.4512 (2.2077)	loss 4.1046 (3.7137)	grad_norm 1.2009 (1.2512)	
[2022-01-20 18:14:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1030/1251]	eta 0:08:08 lr 0.000753	time 1.7018 (2.2084)	loss 3.6896 (3.7143)	grad_norm 1.1620 (1.2511)	
[2022-01-20 18:14:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1040/1251]	eta 0:07:45 lr 0.000753	time 2.0611 (2.2083)	loss 3.1730 (3.7141)	grad_norm 1.4410 (1.2504)	
[2022-01-20 18:15:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1050/1251]	eta 0:07:23 lr 0.000753	time 3.4063 (2.2077)	loss 2.9229 (3.7126)	grad_norm 1.2145 (1.2501)	
[2022-01-20 18:15:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1060/1251]	eta 0:07:01 lr 0.000753	time 2.1687 (2.2068)	loss 4.0207 (3.7111)	grad_norm 1.3324 (1.2505)	
[2022-01-20 18:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1070/1251]	eta 0:06:39 lr 0.000753	time 1.7905 (2.2079)	loss 4.0505 (3.7100)	grad_norm 1.3693 (1.2499)	
[2022-01-20 18:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1080/1251]	eta 0:06:17 lr 0.000753	time 2.2729 (2.2077)	loss 4.3285 (3.7096)	grad_norm 1.1936 (1.2503)	
[2022-01-20 18:16:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1090/1251]	eta 0:05:55 lr 0.000753	time 2.5439 (2.2073)	loss 3.8458 (3.7120)	grad_norm 1.2863 (1.2499)	
[2022-01-20 18:16:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1100/1251]	eta 0:05:32 lr 0.000753	time 1.7108 (2.2049)	loss 2.8484 (3.7120)	grad_norm 1.2844 (1.2504)	
[2022-01-20 18:17:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1110/1251]	eta 0:05:10 lr 0.000753	time 1.9417 (2.2035)	loss 4.2066 (3.7098)	grad_norm 1.4830 (1.2518)	
[2022-01-20 18:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1120/1251]	eta 0:04:48 lr 0.000753	time 2.1496 (2.2036)	loss 2.5654 (3.7086)	grad_norm 1.2526 (1.2517)	
[2022-01-20 18:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1130/1251]	eta 0:04:26 lr 0.000753	time 2.5164 (2.2053)	loss 4.5395 (3.7109)	grad_norm 1.3669 (1.2517)	
[2022-01-20 18:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1140/1251]	eta 0:04:04 lr 0.000753	time 1.6587 (2.2067)	loss 3.9301 (3.7111)	grad_norm 1.0443 (1.2515)	
[2022-01-20 18:18:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1150/1251]	eta 0:03:42 lr 0.000753	time 2.4742 (2.2077)	loss 4.4049 (3.7116)	grad_norm 1.1521 (1.2515)	
[2022-01-20 18:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1160/1251]	eta 0:03:20 lr 0.000753	time 1.6585 (2.2054)	loss 4.1570 (3.7110)	grad_norm 1.2052 (1.2511)	
[2022-01-20 18:19:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1170/1251]	eta 0:02:58 lr 0.000753	time 1.9883 (2.2036)	loss 3.7152 (3.7112)	grad_norm 1.0781 (1.2497)	
[2022-01-20 18:19:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1180/1251]	eta 0:02:36 lr 0.000753	time 1.5804 (2.2012)	loss 4.3288 (3.7129)	grad_norm 1.3390 (1.2493)	
[2022-01-20 18:20:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1190/1251]	eta 0:02:14 lr 0.000753	time 1.5203 (2.2005)	loss 4.3774 (3.7145)	grad_norm 1.1976 (1.2494)	
[2022-01-20 18:20:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1200/1251]	eta 0:01:52 lr 0.000753	time 1.8575 (2.2000)	loss 3.8446 (3.7169)	grad_norm 1.4140 (1.2500)	
[2022-01-20 18:20:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1210/1251]	eta 0:01:30 lr 0.000753	time 1.8696 (2.2020)	loss 4.1137 (3.7184)	grad_norm 1.3026 (1.2502)	
[2022-01-20 18:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1220/1251]	eta 0:01:08 lr 0.000753	time 2.2580 (2.2028)	loss 3.7511 (3.7188)	grad_norm 1.4597 (1.2501)	
[2022-01-20 18:21:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1230/1251]	eta 0:00:46 lr 0.000753	time 2.1541 (2.2047)	loss 4.3333 (3.7226)	grad_norm 1.3400 (1.2502)	
[2022-01-20 18:22:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1240/1251]	eta 0:00:24 lr 0.000753	time 1.7183 (2.2044)	loss 3.6580 (3.7227)	grad_norm 1.1059 (1.2505)	
[2022-01-20 18:22:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [99/300][1250/1251]	eta 0:00:02 lr 0.000753	time 1.1833 (2.1981)	loss 4.4907 (3.7218)	grad_norm 1.2398 (1.2505)	
[2022-01-20 18:22:20 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 99 training takes 0:45:50
[2022-01-20 18:22:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.629 (18.629)	Loss 1.1411 (1.1411)	Acc@1 72.852 (72.852)	Acc@5 92.090 (92.090)	
[2022-01-20 18:22:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.869 (3.361)	Loss 1.1635 (1.1259)	Acc@1 71.094 (73.580)	Acc@5 92.676 (92.152)	
[2022-01-20 18:23:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 2.400 (2.602)	Loss 1.1868 (1.1269)	Acc@1 73.535 (73.744)	Acc@5 91.016 (92.192)	
[2022-01-20 18:23:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.904 (2.271)	Loss 1.1236 (1.1319)	Acc@1 75.293 (73.740)	Acc@5 91.797 (92.137)	
[2022-01-20 18:23:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.121 (2.174)	Loss 1.1933 (1.1411)	Acc@1 72.754 (73.540)	Acc@5 91.406 (92.026)	
[2022-01-20 18:23:56 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.598 Acc@5 92.086
[2022-01-20 18:23:56 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.6%
[2022-01-20 18:23:56 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.88%
[2022-01-20 18:24:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][0/1251]	eta 8:11:48 lr 0.000753	time 23.5883 (23.5883)	loss 2.8116 (2.8116)	grad_norm 1.4042 (1.4042)	
[2022-01-20 18:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][10/1251]	eta 1:28:43 lr 0.000752	time 1.9948 (4.2900)	loss 4.0054 (3.5784)	grad_norm 1.2456 (1.2877)	
[2022-01-20 18:25:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][20/1251]	eta 1:08:05 lr 0.000752	time 1.7565 (3.3189)	loss 3.7076 (3.7180)	grad_norm 1.3898 (1.2925)	
[2022-01-20 18:25:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][30/1251]	eta 0:59:50 lr 0.000752	time 1.5787 (2.9406)	loss 4.3817 (3.7886)	grad_norm 1.1864 (1.2719)	
[2022-01-20 18:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][40/1251]	eta 0:55:18 lr 0.000752	time 3.0059 (2.7400)	loss 4.3803 (3.7534)	grad_norm 1.2736 (1.2688)	
[2022-01-20 18:26:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][50/1251]	eta 0:52:45 lr 0.000752	time 2.2860 (2.6358)	loss 4.3755 (3.7783)	grad_norm 1.2472 (1.2674)	
[2022-01-20 18:26:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][60/1251]	eta 0:50:30 lr 0.000752	time 1.9182 (2.5449)	loss 3.9196 (3.7452)	grad_norm 1.1765 (1.2618)	
[2022-01-20 18:26:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][70/1251]	eta 0:48:36 lr 0.000752	time 1.7380 (2.4696)	loss 3.7464 (3.7353)	grad_norm 1.2794 (1.2709)	
[2022-01-20 18:27:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][80/1251]	eta 0:47:43 lr 0.000752	time 2.9323 (2.4449)	loss 2.6473 (3.7088)	grad_norm 1.3293 (1.2719)	
[2022-01-20 18:27:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][90/1251]	eta 0:46:47 lr 0.000752	time 2.1324 (2.4183)	loss 4.5059 (3.7460)	grad_norm 1.3069 (1.2697)	
[2022-01-20 18:27:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][100/1251]	eta 0:45:54 lr 0.000752	time 1.5031 (2.3932)	loss 3.0315 (3.7381)	grad_norm 1.2148 (1.2631)	
[2022-01-20 18:28:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][110/1251]	eta 0:45:06 lr 0.000752	time 1.9368 (2.3722)	loss 4.0689 (3.6967)	grad_norm 1.1689 (1.2579)	
[2022-01-20 18:28:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][120/1251]	eta 0:44:38 lr 0.000752	time 3.1195 (2.3683)	loss 3.7713 (3.6888)	grad_norm 1.1288 (1.2597)	
[2022-01-20 18:29:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][130/1251]	eta 0:43:58 lr 0.000752	time 1.5442 (2.3536)	loss 3.9310 (3.6772)	grad_norm 1.3348 (1.2582)	
[2022-01-20 18:29:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][140/1251]	eta 0:43:20 lr 0.000752	time 1.5112 (2.3404)	loss 4.0945 (3.6485)	grad_norm 1.3183 (1.2521)	
[2022-01-20 18:29:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][150/1251]	eta 0:42:46 lr 0.000752	time 1.8087 (2.3315)	loss 4.3747 (3.6740)	grad_norm 1.3367 (1.2486)	
[2022-01-20 18:30:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][160/1251]	eta 0:42:10 lr 0.000752	time 2.1487 (2.3197)	loss 2.6161 (3.6551)	grad_norm 1.1583 (1.2482)	
[2022-01-20 18:30:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][170/1251]	eta 0:41:28 lr 0.000752	time 1.9888 (2.3023)	loss 3.6178 (3.6507)	grad_norm 1.2509 (1.2489)	
[2022-01-20 18:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][180/1251]	eta 0:41:06 lr 0.000752	time 2.0642 (2.3029)	loss 4.1275 (3.6611)	grad_norm 1.1881 (1.2475)	
[2022-01-20 18:31:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][190/1251]	eta 0:40:40 lr 0.000752	time 1.8695 (2.3005)	loss 4.2989 (3.6710)	grad_norm 1.2477 (1.2520)	
[2022-01-20 18:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][200/1251]	eta 0:40:20 lr 0.000752	time 2.8516 (2.3033)	loss 3.3197 (3.6656)	grad_norm 1.3064 (1.2556)	
[2022-01-20 18:32:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][210/1251]	eta 0:39:48 lr 0.000752	time 1.9800 (2.2949)	loss 4.0357 (3.6718)	grad_norm 1.2943 (1.2578)	
[2022-01-20 18:32:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][220/1251]	eta 0:39:18 lr 0.000752	time 2.2326 (2.2872)	loss 3.6990 (3.6832)	grad_norm 1.8734 (1.2658)	
[2022-01-20 18:32:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][230/1251]	eta 0:38:43 lr 0.000752	time 1.9826 (2.2755)	loss 4.1525 (3.6790)	grad_norm 1.3218 (1.2677)	
[2022-01-20 18:33:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][240/1251]	eta 0:38:15 lr 0.000752	time 1.8999 (2.2709)	loss 3.7695 (3.6932)	grad_norm 1.1283 (1.2709)	
[2022-01-20 18:33:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][250/1251]	eta 0:37:43 lr 0.000752	time 1.8254 (2.2609)	loss 3.6213 (3.6830)	grad_norm 1.2334 (1.2711)	
[2022-01-20 18:33:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][260/1251]	eta 0:37:15 lr 0.000752	time 1.9015 (2.2557)	loss 4.5214 (3.6832)	grad_norm 1.3806 (1.2717)	
[2022-01-20 18:34:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][270/1251]	eta 0:36:55 lr 0.000752	time 3.4710 (2.2582)	loss 3.5616 (3.6787)	grad_norm 1.1186 (1.2741)	
[2022-01-20 18:34:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][280/1251]	eta 0:36:29 lr 0.000751	time 1.9452 (2.2554)	loss 4.2563 (3.6787)	grad_norm 1.1135 (1.2712)	
[2022-01-20 18:34:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][290/1251]	eta 0:36:01 lr 0.000751	time 1.8351 (2.2490)	loss 4.1844 (3.6833)	grad_norm 1.1559 (1.2687)	
[2022-01-20 18:35:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][300/1251]	eta 0:35:36 lr 0.000751	time 1.7890 (2.2467)	loss 3.5311 (3.6755)	grad_norm 1.2397 (1.2666)	
[2022-01-20 18:35:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][310/1251]	eta 0:35:16 lr 0.000751	time 2.6093 (2.2490)	loss 3.5687 (3.6808)	grad_norm 1.2691 (1.2664)	
[2022-01-20 18:35:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][320/1251]	eta 0:34:51 lr 0.000751	time 2.1441 (2.2464)	loss 4.2068 (3.6846)	grad_norm 1.1943 (1.2652)	
[2022-01-20 18:36:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][330/1251]	eta 0:34:28 lr 0.000751	time 2.1394 (2.2457)	loss 4.4994 (3.6877)	grad_norm 1.1752 (1.2648)	
[2022-01-20 18:36:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][340/1251]	eta 0:34:07 lr 0.000751	time 2.5436 (2.2471)	loss 4.3310 (3.6945)	grad_norm 1.1755 (1.2631)	
[2022-01-20 18:37:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][350/1251]	eta 0:33:41 lr 0.000751	time 2.9376 (2.2438)	loss 3.6543 (3.6950)	grad_norm 1.1219 (1.2615)	
[2022-01-20 18:37:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][360/1251]	eta 0:33:17 lr 0.000751	time 3.1026 (2.2422)	loss 3.6990 (3.6945)	grad_norm 1.1094 (1.2597)	
[2022-01-20 18:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][370/1251]	eta 0:32:56 lr 0.000751	time 3.1850 (2.2430)	loss 3.7179 (3.6937)	grad_norm 1.3089 (1.2606)	
[2022-01-20 18:38:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][380/1251]	eta 0:32:35 lr 0.000751	time 2.5450 (2.2452)	loss 4.3445 (3.6895)	grad_norm 1.2636 (1.2616)	
[2022-01-20 18:38:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][390/1251]	eta 0:32:11 lr 0.000751	time 1.9185 (2.2439)	loss 3.7345 (3.6869)	grad_norm 1.3854 (1.2622)	
[2022-01-20 18:38:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][400/1251]	eta 0:31:48 lr 0.000751	time 3.1012 (2.2429)	loss 3.5717 (3.6915)	grad_norm 1.2956 (1.2649)	
[2022-01-20 18:39:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][410/1251]	eta 0:31:24 lr 0.000751	time 2.9110 (2.2412)	loss 4.6021 (3.6922)	grad_norm 1.2738 (1.2649)	
[2022-01-20 18:39:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][420/1251]	eta 0:30:59 lr 0.000751	time 1.6418 (2.2377)	loss 4.2162 (3.6929)	grad_norm 1.1304 (1.2635)	
[2022-01-20 18:39:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][430/1251]	eta 0:30:34 lr 0.000751	time 1.8573 (2.2341)	loss 3.3254 (3.6929)	grad_norm 1.1823 (1.2622)	
[2022-01-20 18:40:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][440/1251]	eta 0:30:12 lr 0.000751	time 2.1169 (2.2348)	loss 4.0310 (3.6925)	grad_norm 1.1634 (1.2620)	
[2022-01-20 18:40:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][450/1251]	eta 0:29:48 lr 0.000751	time 2.7700 (2.2333)	loss 3.0979 (3.6889)	grad_norm 1.1665 (1.2618)	
[2022-01-20 18:41:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][460/1251]	eta 0:29:25 lr 0.000751	time 2.1265 (2.2326)	loss 3.8252 (3.6921)	grad_norm 1.2079 (1.2594)	
[2022-01-20 18:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][470/1251]	eta 0:29:00 lr 0.000751	time 1.8732 (2.2283)	loss 3.6904 (3.6980)	grad_norm 1.3395 (1.2595)	
[2022-01-20 18:41:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][480/1251]	eta 0:28:38 lr 0.000751	time 2.1642 (2.2287)	loss 4.1585 (3.6953)	grad_norm 1.1685 (1.2589)	
[2022-01-20 18:42:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][490/1251]	eta 0:28:14 lr 0.000751	time 2.7111 (2.2271)	loss 3.8358 (3.7036)	grad_norm 1.3175 (1.2591)	
[2022-01-20 18:42:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][500/1251]	eta 0:27:52 lr 0.000751	time 1.7565 (2.2272)	loss 3.7973 (3.7048)	grad_norm 1.1968 (1.2604)	
[2022-01-20 18:42:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][510/1251]	eta 0:27:29 lr 0.000751	time 1.6808 (2.2265)	loss 4.0259 (3.7039)	grad_norm 1.1513 (1.2595)	
[2022-01-20 18:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][520/1251]	eta 0:27:08 lr 0.000751	time 2.2436 (2.2281)	loss 4.5749 (3.7054)	grad_norm 1.2437 (1.2590)	
[2022-01-20 18:43:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][530/1251]	eta 0:26:46 lr 0.000751	time 2.9824 (2.2285)	loss 3.9242 (3.7081)	grad_norm 1.1757 (1.2576)	
[2022-01-20 18:43:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][540/1251]	eta 0:26:21 lr 0.000751	time 1.9268 (2.2240)	loss 2.9679 (3.7105)	grad_norm 1.3132 (1.2594)	
[2022-01-20 18:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][550/1251]	eta 0:25:59 lr 0.000751	time 2.4970 (2.2253)	loss 4.3764 (3.7123)	grad_norm 1.1349 (1.2583)	
[2022-01-20 18:44:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][560/1251]	eta 0:25:37 lr 0.000750	time 2.2956 (2.2244)	loss 3.5849 (3.7131)	grad_norm 1.2501 (1.2569)	
[2022-01-20 18:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][570/1251]	eta 0:25:14 lr 0.000750	time 2.7148 (2.2235)	loss 4.3463 (3.7147)	grad_norm 1.2926 (1.2599)	
[2022-01-20 18:45:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][580/1251]	eta 0:24:48 lr 0.000750	time 1.7024 (2.2189)	loss 2.8638 (3.7177)	grad_norm 1.2330 (1.2593)	
[2022-01-20 18:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][590/1251]	eta 0:24:25 lr 0.000750	time 2.0503 (2.2169)	loss 4.1671 (3.7194)	grad_norm 1.1765 (1.2610)	
[2022-01-20 18:46:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][600/1251]	eta 0:24:02 lr 0.000750	time 1.9916 (2.2156)	loss 3.4975 (3.7176)	grad_norm 1.2935 (1.2622)	
[2022-01-20 18:46:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][610/1251]	eta 0:23:40 lr 0.000750	time 3.2567 (2.2154)	loss 3.0437 (3.7125)	grad_norm 1.2757 (1.2614)	
[2022-01-20 18:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][620/1251]	eta 0:23:17 lr 0.000750	time 1.8798 (2.2152)	loss 3.9983 (3.7131)	grad_norm 1.2514 (1.2603)	
[2022-01-20 18:47:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][630/1251]	eta 0:22:54 lr 0.000750	time 1.5523 (2.2136)	loss 3.4779 (3.7114)	grad_norm 1.5993 (1.2603)	
[2022-01-20 18:47:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][640/1251]	eta 0:22:33 lr 0.000750	time 2.5756 (2.2151)	loss 4.1373 (3.7095)	grad_norm 1.2478 (1.2595)	
[2022-01-20 18:47:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][650/1251]	eta 0:22:11 lr 0.000750	time 2.9340 (2.2162)	loss 2.7076 (3.7102)	grad_norm 1.2493 (1.2598)	
[2022-01-20 18:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][660/1251]	eta 0:21:50 lr 0.000750	time 1.9210 (2.2169)	loss 4.3898 (3.7155)	grad_norm 1.2484 (1.2603)	
[2022-01-20 18:48:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][670/1251]	eta 0:21:29 lr 0.000750	time 2.0346 (2.2188)	loss 4.1460 (3.7197)	grad_norm 1.1115 (1.2592)	
[2022-01-20 18:49:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][680/1251]	eta 0:21:07 lr 0.000750	time 2.1147 (2.2194)	loss 4.2458 (3.7193)	grad_norm 1.2396 (1.2601)	
[2022-01-20 18:49:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][690/1251]	eta 0:20:42 lr 0.000750	time 1.8649 (2.2150)	loss 3.7950 (3.7201)	grad_norm 1.5890 (1.2601)	
[2022-01-20 18:49:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][700/1251]	eta 0:20:18 lr 0.000750	time 1.5912 (2.2121)	loss 4.1815 (3.7238)	grad_norm 1.2306 (1.2591)	
[2022-01-20 18:50:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][710/1251]	eta 0:19:55 lr 0.000750	time 2.5650 (2.2104)	loss 3.9250 (3.7234)	grad_norm 1.1828 (1.2588)	
[2022-01-20 18:50:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][720/1251]	eta 0:19:32 lr 0.000750	time 2.0008 (2.2090)	loss 4.2329 (3.7208)	grad_norm 1.3212 (1.2580)	
[2022-01-20 18:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][730/1251]	eta 0:19:09 lr 0.000750	time 1.9528 (2.2067)	loss 2.6747 (3.7212)	grad_norm 1.1106 (1.2593)	
[2022-01-20 18:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][740/1251]	eta 0:18:47 lr 0.000750	time 2.5197 (2.2066)	loss 3.2242 (3.7198)	grad_norm 1.1157 (1.2601)	
[2022-01-20 18:51:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][750/1251]	eta 0:18:25 lr 0.000750	time 1.8682 (2.2067)	loss 4.3114 (3.7184)	grad_norm 1.3828 (1.2610)	
[2022-01-20 18:51:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][760/1251]	eta 0:18:04 lr 0.000750	time 1.8504 (2.2087)	loss 2.9290 (3.7161)	grad_norm 1.4000 (1.2622)	
[2022-01-20 18:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][770/1251]	eta 0:17:42 lr 0.000750	time 2.3053 (2.2092)	loss 4.6048 (3.7173)	grad_norm 1.1612 (1.2617)	
[2022-01-20 18:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][780/1251]	eta 0:17:21 lr 0.000750	time 2.5356 (2.2107)	loss 3.9202 (3.7142)	grad_norm 1.1428 (1.2617)	
[2022-01-20 18:53:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][790/1251]	eta 0:16:58 lr 0.000750	time 1.9040 (2.2095)	loss 4.0561 (3.7149)	grad_norm 1.2135 (1.2613)	
[2022-01-20 18:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][800/1251]	eta 0:16:36 lr 0.000750	time 1.6075 (2.2088)	loss 3.8951 (3.7140)	grad_norm 1.2157 (1.2613)	
[2022-01-20 18:53:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][810/1251]	eta 0:16:13 lr 0.000750	time 2.2705 (2.2084)	loss 3.6435 (3.7120)	grad_norm 1.2280 (1.2621)	
[2022-01-20 18:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][820/1251]	eta 0:15:50 lr 0.000750	time 1.8762 (2.2063)	loss 2.7037 (3.7109)	grad_norm 1.3627 (1.2635)	
[2022-01-20 18:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][830/1251]	eta 0:15:28 lr 0.000750	time 2.5420 (2.2062)	loss 4.1609 (3.7065)	grad_norm 1.1129 (1.2622)	
[2022-01-20 18:54:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][840/1251]	eta 0:15:07 lr 0.000749	time 1.6085 (2.2072)	loss 4.4425 (3.7090)	grad_norm 1.1809 (1.2620)	
[2022-01-20 18:55:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][850/1251]	eta 0:14:45 lr 0.000749	time 2.2604 (2.2086)	loss 3.2701 (3.7080)	grad_norm 1.2142 (1.2625)	
[2022-01-20 18:55:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][860/1251]	eta 0:14:24 lr 0.000749	time 2.1837 (2.2097)	loss 3.5296 (3.7080)	grad_norm 1.1800 (1.2624)	
[2022-01-20 18:55:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][870/1251]	eta 0:14:01 lr 0.000749	time 1.9110 (2.2074)	loss 3.0125 (3.7056)	grad_norm 1.1351 (1.2622)	
[2022-01-20 18:56:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][880/1251]	eta 0:13:38 lr 0.000749	time 1.9638 (2.2050)	loss 3.6447 (3.7070)	grad_norm 1.2239 (1.2622)	
[2022-01-20 18:56:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][890/1251]	eta 0:13:15 lr 0.000749	time 2.1699 (2.2039)	loss 3.8475 (3.7071)	grad_norm 1.2221 (1.2618)	
[2022-01-20 18:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][900/1251]	eta 0:12:53 lr 0.000749	time 2.1879 (2.2040)	loss 4.0524 (3.7098)	grad_norm 1.1432 (1.2614)	
[2022-01-20 18:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][910/1251]	eta 0:12:31 lr 0.000749	time 1.6671 (2.2042)	loss 3.0600 (3.7085)	grad_norm 1.1732 (1.2604)	
[2022-01-20 18:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][920/1251]	eta 0:12:09 lr 0.000749	time 1.8966 (2.2041)	loss 2.8346 (3.7075)	grad_norm 1.0868 (1.2601)	
[2022-01-20 18:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][930/1251]	eta 0:11:47 lr 0.000749	time 2.3313 (2.2036)	loss 3.4682 (3.7084)	grad_norm 1.1589 (1.2604)	
[2022-01-20 18:58:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][940/1251]	eta 0:11:25 lr 0.000749	time 2.5904 (2.2040)	loss 4.0815 (3.7121)	grad_norm 1.3921 (1.2610)	
[2022-01-20 18:58:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][950/1251]	eta 0:11:02 lr 0.000749	time 1.9306 (2.2017)	loss 3.8108 (3.7124)	grad_norm 1.1397 (1.2619)	
[2022-01-20 18:59:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][960/1251]	eta 0:10:40 lr 0.000749	time 2.2197 (2.2003)	loss 3.1371 (3.7108)	grad_norm 1.1865 (1.2623)	
[2022-01-20 18:59:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][970/1251]	eta 0:10:18 lr 0.000749	time 2.5405 (2.1998)	loss 3.6359 (3.7122)	grad_norm 1.4062 (1.2630)	
[2022-01-20 18:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][980/1251]	eta 0:09:56 lr 0.000749	time 2.8537 (2.1996)	loss 2.6454 (3.7109)	grad_norm 1.2443 (1.2626)	
[2022-01-20 19:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][990/1251]	eta 0:09:34 lr 0.000749	time 2.6957 (2.2002)	loss 2.3565 (3.7085)	grad_norm 1.1908 (1.2623)	
[2022-01-20 19:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1000/1251]	eta 0:09:12 lr 0.000749	time 2.5755 (2.2011)	loss 3.4142 (3.7077)	grad_norm 1.1516 (1.2617)	
[2022-01-20 19:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1010/1251]	eta 0:08:50 lr 0.000749	time 2.0779 (2.2030)	loss 4.2004 (3.7062)	grad_norm 1.1694 (1.2618)	
[2022-01-20 19:01:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1020/1251]	eta 0:08:28 lr 0.000749	time 1.9214 (2.2028)	loss 3.1781 (3.7046)	grad_norm 1.2515 (1.2621)	
[2022-01-20 19:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1030/1251]	eta 0:08:06 lr 0.000749	time 2.4778 (2.2018)	loss 3.1303 (3.7025)	grad_norm 1.2109 (1.2619)	
[2022-01-20 19:02:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1040/1251]	eta 0:07:44 lr 0.000749	time 1.9156 (2.1999)	loss 4.3225 (3.7047)	grad_norm 1.3973 (1.2616)	
[2022-01-20 19:02:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1050/1251]	eta 0:07:21 lr 0.000749	time 1.8059 (2.1987)	loss 3.8210 (3.7025)	grad_norm 1.4962 (1.2620)	
[2022-01-20 19:02:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1060/1251]	eta 0:06:59 lr 0.000749	time 1.8856 (2.1982)	loss 3.8095 (3.7050)	grad_norm 1.1792 (1.2615)	
[2022-01-20 19:03:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1070/1251]	eta 0:06:37 lr 0.000749	time 1.8139 (2.1985)	loss 3.9678 (3.7072)	grad_norm 1.1103 (1.2611)	
[2022-01-20 19:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1080/1251]	eta 0:06:15 lr 0.000749	time 1.9054 (2.1985)	loss 3.9605 (3.7089)	grad_norm 1.1671 (1.2609)	
[2022-01-20 19:03:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1090/1251]	eta 0:05:54 lr 0.000749	time 2.3437 (2.2008)	loss 3.0368 (3.7128)	grad_norm 1.2295 (1.2601)	
[2022-01-20 19:04:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1100/1251]	eta 0:05:32 lr 0.000749	time 2.4158 (2.2018)	loss 3.2987 (3.7116)	grad_norm 1.2708 (1.2595)	
[2022-01-20 19:04:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1110/1251]	eta 0:05:10 lr 0.000749	time 2.3351 (2.2006)	loss 4.1296 (3.7112)	grad_norm 1.2286 (1.2588)	
[2022-01-20 19:05:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1120/1251]	eta 0:04:48 lr 0.000748	time 1.5903 (2.1988)	loss 2.5525 (3.7104)	grad_norm 1.4384 (1.2586)	
[2022-01-20 19:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1130/1251]	eta 0:04:26 lr 0.000748	time 3.1862 (2.1986)	loss 4.0650 (3.7125)	grad_norm 1.3301 (1.2590)	
[2022-01-20 19:05:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1140/1251]	eta 0:04:03 lr 0.000748	time 2.0158 (2.1974)	loss 3.6908 (3.7138)	grad_norm 1.6491 (1.2602)	
[2022-01-20 19:06:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1150/1251]	eta 0:03:41 lr 0.000748	time 1.9442 (2.1968)	loss 3.1736 (3.7112)	grad_norm 1.2002 (1.2599)	
[2022-01-20 19:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1160/1251]	eta 0:03:20 lr 0.000748	time 2.1044 (2.1978)	loss 3.0571 (3.7099)	grad_norm 1.1111 (1.2597)	
[2022-01-20 19:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1170/1251]	eta 0:02:58 lr 0.000748	time 2.4994 (2.1987)	loss 2.5295 (3.7097)	grad_norm 1.2199 (1.2589)	
[2022-01-20 19:07:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1180/1251]	eta 0:02:36 lr 0.000748	time 2.1471 (2.1990)	loss 4.0233 (3.7101)	grad_norm 1.3002 (1.2591)	
[2022-01-20 19:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1190/1251]	eta 0:02:14 lr 0.000748	time 1.9215 (2.1980)	loss 3.0091 (3.7085)	grad_norm 1.1227 (1.2593)	
[2022-01-20 19:07:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1200/1251]	eta 0:01:52 lr 0.000748	time 2.1285 (2.1977)	loss 3.0591 (3.7089)	grad_norm 1.2349 (1.2596)	
[2022-01-20 19:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1210/1251]	eta 0:01:30 lr 0.000748	time 2.2606 (2.1973)	loss 4.1530 (3.7109)	grad_norm 1.2967 (1.2593)	
[2022-01-20 19:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1220/1251]	eta 0:01:08 lr 0.000748	time 2.2061 (2.1977)	loss 2.8789 (3.7087)	grad_norm 1.4512 (1.2588)	
[2022-01-20 19:09:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1230/1251]	eta 0:00:46 lr 0.000748	time 1.8478 (2.1971)	loss 3.6302 (3.7078)	grad_norm 1.2944 (1.2581)	
[2022-01-20 19:09:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1240/1251]	eta 0:00:24 lr 0.000748	time 2.0834 (2.1971)	loss 3.6996 (3.7081)	grad_norm 1.7163 (1.2589)	
[2022-01-20 19:09:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [100/300][1250/1251]	eta 0:00:02 lr 0.000748	time 1.1874 (2.1911)	loss 3.6536 (3.7088)	grad_norm 1.1312 (1.2582)	
[2022-01-20 19:09:37 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 100 training takes 0:45:41
[2022-01-20 19:09:37 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_100 saving......
[2022-01-20 19:09:48 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_100 saved !!!
[2022-01-20 19:10:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 15.990 (15.990)	Loss 1.1089 (1.1089)	Acc@1 74.902 (74.902)	Acc@5 92.773 (92.773)	
[2022-01-20 19:10:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.951 (2.910)	Loss 1.1033 (1.1430)	Acc@1 73.340 (73.304)	Acc@5 93.457 (92.116)	
[2022-01-20 19:10:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.228 (2.432)	Loss 1.1867 (1.1334)	Acc@1 74.707 (73.670)	Acc@5 90.527 (92.225)	
[2022-01-20 19:10:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.930 (2.143)	Loss 1.0401 (1.1371)	Acc@1 76.270 (73.617)	Acc@5 93.066 (92.128)	
[2022-01-20 19:11:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 0.841 (2.025)	Loss 1.1538 (1.1335)	Acc@1 73.633 (73.695)	Acc@5 91.992 (92.157)	
[2022-01-20 19:11:20 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.638 Acc@5 92.150
[2022-01-20 19:11:20 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.6%
[2022-01-20 19:11:20 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.88%
[2022-01-20 19:11:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][0/1251]	eta 7:28:33 lr 0.000748	time 21.5133 (21.5133)	loss 3.1974 (3.1974)	grad_norm 1.1067 (1.1067)	
[2022-01-20 19:12:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][10/1251]	eta 1:25:58 lr 0.000748	time 2.8006 (4.1569)	loss 4.3138 (3.5698)	grad_norm 1.3169 (1.2148)	
[2022-01-20 19:12:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][20/1251]	eta 1:06:56 lr 0.000748	time 1.4429 (3.2632)	loss 3.7703 (3.4982)	grad_norm 1.2111 (1.2368)	
[2022-01-20 19:12:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][30/1251]	eta 0:59:41 lr 0.000748	time 1.8854 (2.9333)	loss 3.5078 (3.5049)	grad_norm 1.1829 (1.2767)	
[2022-01-20 19:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][40/1251]	eta 0:56:46 lr 0.000748	time 3.7266 (2.8129)	loss 2.9400 (3.6032)	grad_norm 1.1952 (1.3014)	
[2022-01-20 19:13:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][50/1251]	eta 0:55:03 lr 0.000748	time 2.7711 (2.7503)	loss 4.1055 (3.6170)	grad_norm 1.2897 (1.2803)	
[2022-01-20 19:14:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][60/1251]	eta 0:52:56 lr 0.000748	time 1.9281 (2.6669)	loss 3.8075 (3.6443)	grad_norm 1.2299 (1.2642)	
[2022-01-20 19:14:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][70/1251]	eta 0:50:59 lr 0.000748	time 1.9617 (2.5909)	loss 2.5425 (3.6754)	grad_norm 1.1892 (1.2669)	
[2022-01-20 19:14:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][80/1251]	eta 0:49:34 lr 0.000748	time 3.0278 (2.5401)	loss 3.4494 (3.6948)	grad_norm 1.2734 (1.2614)	
[2022-01-20 19:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][90/1251]	eta 0:47:55 lr 0.000748	time 1.8430 (2.4770)	loss 3.1110 (3.6959)	grad_norm 1.0861 (1.2632)	
[2022-01-20 19:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][100/1251]	eta 0:46:39 lr 0.000748	time 1.6864 (2.4318)	loss 4.0503 (3.7058)	grad_norm 1.1865 (1.2585)	
[2022-01-20 19:15:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][110/1251]	eta 0:45:40 lr 0.000748	time 1.7960 (2.4015)	loss 4.0379 (3.7093)	grad_norm 1.1159 (1.2578)	
[2022-01-20 19:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][120/1251]	eta 0:44:51 lr 0.000748	time 2.1413 (2.3799)	loss 2.6422 (3.7165)	grad_norm 1.1992 (1.2613)	
[2022-01-20 19:16:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][130/1251]	eta 0:44:17 lr 0.000748	time 1.8665 (2.3704)	loss 3.6609 (3.7160)	grad_norm 1.4359 (1.2611)	
[2022-01-20 19:16:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][140/1251]	eta 0:43:57 lr 0.000747	time 1.5947 (2.3736)	loss 3.2490 (3.7139)	grad_norm 1.1252 (1.2532)	
[2022-01-20 19:17:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][150/1251]	eta 0:43:32 lr 0.000747	time 2.4659 (2.3724)	loss 3.7801 (3.7171)	grad_norm 1.1614 (1.2512)	
[2022-01-20 19:17:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][160/1251]	eta 0:43:13 lr 0.000747	time 2.1688 (2.3767)	loss 3.8757 (3.7251)	grad_norm 1.2041 (1.2504)	
[2022-01-20 19:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][170/1251]	eta 0:42:31 lr 0.000747	time 1.7615 (2.3600)	loss 4.3791 (3.7195)	grad_norm 1.2539 (1.2454)	
[2022-01-20 19:18:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][180/1251]	eta 0:41:45 lr 0.000747	time 1.6541 (2.3397)	loss 3.5292 (3.7228)	grad_norm 1.6652 (1.2472)	
[2022-01-20 19:18:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][190/1251]	eta 0:41:03 lr 0.000747	time 1.9056 (2.3218)	loss 3.7504 (3.7161)	grad_norm 1.0863 (1.2461)	
[2022-01-20 19:19:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][200/1251]	eta 0:40:33 lr 0.000747	time 1.8973 (2.3158)	loss 3.6560 (3.7169)	grad_norm 1.2711 (1.2467)	
[2022-01-20 19:19:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][210/1251]	eta 0:40:10 lr 0.000747	time 1.8811 (2.3158)	loss 2.7130 (3.7093)	grad_norm 1.2187 (1.2478)	
[2022-01-20 19:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][220/1251]	eta 0:39:39 lr 0.000747	time 1.9489 (2.3080)	loss 3.2221 (3.7160)	grad_norm 1.3502 (1.2507)	
[2022-01-20 19:20:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][230/1251]	eta 0:39:07 lr 0.000747	time 2.1697 (2.2996)	loss 2.9553 (3.7220)	grad_norm 1.7472 (1.2587)	
[2022-01-20 19:20:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][240/1251]	eta 0:38:35 lr 0.000747	time 1.4883 (2.2899)	loss 3.6778 (3.7102)	grad_norm 1.2136 (1.2604)	
[2022-01-20 19:20:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][250/1251]	eta 0:38:06 lr 0.000747	time 3.0283 (2.2846)	loss 3.1447 (3.6971)	grad_norm 1.4289 (1.2606)	
[2022-01-20 19:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][260/1251]	eta 0:37:43 lr 0.000747	time 2.2608 (2.2837)	loss 4.3320 (3.6979)	grad_norm 1.5131 (1.2618)	
[2022-01-20 19:21:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][270/1251]	eta 0:37:17 lr 0.000747	time 1.8829 (2.2812)	loss 3.7107 (3.6973)	grad_norm 1.0275 (1.2632)	
[2022-01-20 19:22:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][280/1251]	eta 0:36:51 lr 0.000747	time 2.2841 (2.2775)	loss 3.6267 (3.7019)	grad_norm 1.1590 (1.2612)	
[2022-01-20 19:22:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][290/1251]	eta 0:36:26 lr 0.000747	time 3.3315 (2.2749)	loss 3.2214 (3.6973)	grad_norm 1.1963 (1.2604)	
[2022-01-20 19:22:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][300/1251]	eta 0:35:59 lr 0.000747	time 1.9532 (2.2709)	loss 3.9635 (3.6969)	grad_norm 1.2959 (1.2593)	
[2022-01-20 19:23:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][310/1251]	eta 0:35:38 lr 0.000747	time 2.3725 (2.2723)	loss 4.2429 (3.6967)	grad_norm 1.3362 (1.2603)	
[2022-01-20 19:23:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][320/1251]	eta 0:35:17 lr 0.000747	time 2.4794 (2.2748)	loss 3.5262 (3.6941)	grad_norm 1.2563 (1.2594)	
[2022-01-20 19:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][330/1251]	eta 0:34:50 lr 0.000747	time 2.4843 (2.2697)	loss 4.1858 (3.7015)	grad_norm 1.4385 (1.2596)	
[2022-01-20 19:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][340/1251]	eta 0:34:21 lr 0.000747	time 1.7147 (2.2624)	loss 3.9930 (3.7040)	grad_norm 1.1664 (1.2583)	
[2022-01-20 19:24:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][350/1251]	eta 0:33:53 lr 0.000747	time 2.5694 (2.2567)	loss 3.6743 (3.7005)	grad_norm 1.6084 (1.2581)	
[2022-01-20 19:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][360/1251]	eta 0:33:28 lr 0.000747	time 2.3048 (2.2538)	loss 3.2650 (3.6954)	grad_norm 1.1992 (1.2581)	
[2022-01-20 19:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][370/1251]	eta 0:33:06 lr 0.000747	time 2.7556 (2.2548)	loss 4.1359 (3.6969)	grad_norm 1.1759 (1.2588)	
[2022-01-20 19:25:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][380/1251]	eta 0:32:43 lr 0.000747	time 1.5635 (2.2541)	loss 4.1461 (3.6946)	grad_norm 1.4087 (1.2607)	
[2022-01-20 19:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][390/1251]	eta 0:32:24 lr 0.000747	time 2.9954 (2.2580)	loss 2.9884 (3.6902)	grad_norm 1.4332 (1.2633)	
[2022-01-20 19:26:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][400/1251]	eta 0:31:59 lr 0.000747	time 1.6537 (2.2552)	loss 3.1203 (3.6937)	grad_norm 1.0545 (1.2637)	
[2022-01-20 19:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][410/1251]	eta 0:31:38 lr 0.000747	time 2.5773 (2.2572)	loss 3.9272 (3.6963)	grad_norm 1.5655 (1.2630)	
[2022-01-20 19:27:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][420/1251]	eta 0:31:10 lr 0.000746	time 1.6254 (2.2507)	loss 3.9953 (3.6895)	grad_norm 1.3816 (1.2643)	
[2022-01-20 19:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][430/1251]	eta 0:30:49 lr 0.000746	time 2.6745 (2.2524)	loss 3.2214 (3.6918)	grad_norm 1.8863 (1.2657)	
[2022-01-20 19:27:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][440/1251]	eta 0:30:23 lr 0.000746	time 2.2551 (2.2480)	loss 4.3812 (3.6942)	grad_norm 1.5538 (1.2671)	
[2022-01-20 19:28:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][450/1251]	eta 0:29:59 lr 0.000746	time 2.8653 (2.2467)	loss 3.1943 (3.6914)	grad_norm 1.1236 (1.2659)	
[2022-01-20 19:28:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][460/1251]	eta 0:29:35 lr 0.000746	time 1.8854 (2.2444)	loss 3.8675 (3.6953)	grad_norm 1.4756 (1.2649)	
[2022-01-20 19:28:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][470/1251]	eta 0:29:11 lr 0.000746	time 2.5245 (2.2430)	loss 3.4720 (3.6916)	grad_norm 1.2097 (1.2650)	
[2022-01-20 19:29:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][480/1251]	eta 0:28:47 lr 0.000746	time 2.0041 (2.2407)	loss 4.1423 (3.6913)	grad_norm 1.1964 (1.2650)	
[2022-01-20 19:29:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][490/1251]	eta 0:28:22 lr 0.000746	time 2.1238 (2.2373)	loss 4.0169 (3.6898)	grad_norm 1.1705 (1.2651)	
[2022-01-20 19:29:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][500/1251]	eta 0:27:57 lr 0.000746	time 1.9875 (2.2342)	loss 2.8469 (3.6889)	grad_norm 1.0552 (1.2647)	
[2022-01-20 19:30:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][510/1251]	eta 0:27:36 lr 0.000746	time 2.5237 (2.2354)	loss 4.0555 (3.6921)	grad_norm 1.2592 (1.2649)	
[2022-01-20 19:30:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][520/1251]	eta 0:27:13 lr 0.000746	time 2.1069 (2.2344)	loss 2.7255 (3.6907)	grad_norm 1.7777 (1.2664)	
[2022-01-20 19:31:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][530/1251]	eta 0:26:51 lr 0.000746	time 2.5223 (2.2351)	loss 2.6099 (3.6911)	grad_norm 1.5311 (1.2663)	
[2022-01-20 19:31:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][540/1251]	eta 0:26:27 lr 0.000746	time 1.9145 (2.2326)	loss 4.3277 (3.6921)	grad_norm 1.2830 (1.2667)	
[2022-01-20 19:31:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][550/1251]	eta 0:26:06 lr 0.000746	time 3.2179 (2.2344)	loss 3.6803 (3.6950)	grad_norm 1.1182 (1.2655)	
[2022-01-20 19:32:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][560/1251]	eta 0:25:42 lr 0.000746	time 2.5614 (2.2321)	loss 3.4022 (3.6985)	grad_norm 1.1395 (1.2654)	
[2022-01-20 19:32:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][570/1251]	eta 0:25:16 lr 0.000746	time 2.5010 (2.2275)	loss 3.5276 (3.7025)	grad_norm 1.2477 (1.2650)	
[2022-01-20 19:32:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][580/1251]	eta 0:24:54 lr 0.000746	time 1.7762 (2.2274)	loss 4.2376 (3.6977)	grad_norm 1.3621 (1.2643)	
[2022-01-20 19:33:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][590/1251]	eta 0:24:34 lr 0.000746	time 2.6642 (2.2300)	loss 4.1982 (3.7015)	grad_norm 1.4120 (1.2641)	
[2022-01-20 19:33:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][600/1251]	eta 0:24:13 lr 0.000746	time 2.4703 (2.2331)	loss 3.5860 (3.7003)	grad_norm 1.0745 (1.2646)	
[2022-01-20 19:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][610/1251]	eta 0:23:49 lr 0.000746	time 1.9299 (2.2307)	loss 4.6079 (3.7011)	grad_norm 1.3963 (1.2639)	
[2022-01-20 19:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][620/1251]	eta 0:23:25 lr 0.000746	time 2.0330 (2.2267)	loss 4.1412 (3.7026)	grad_norm 1.3357 (1.2632)	
[2022-01-20 19:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][630/1251]	eta 0:23:03 lr 0.000746	time 2.6535 (2.2275)	loss 3.2930 (3.7016)	grad_norm 1.2083 (1.2646)	
[2022-01-20 19:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][640/1251]	eta 0:22:40 lr 0.000746	time 2.7537 (2.2271)	loss 4.1197 (3.7012)	grad_norm 1.3751 (1.2643)	
[2022-01-20 19:35:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][650/1251]	eta 0:22:17 lr 0.000746	time 2.1263 (2.2259)	loss 4.2387 (3.7011)	grad_norm 1.0449 (1.2637)	
[2022-01-20 19:35:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][660/1251]	eta 0:21:54 lr 0.000746	time 2.1795 (2.2236)	loss 3.2762 (3.6993)	grad_norm 1.3388 (1.2639)	
[2022-01-20 19:36:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][670/1251]	eta 0:21:30 lr 0.000746	time 2.8298 (2.2220)	loss 3.4134 (3.6942)	grad_norm 1.2397 (1.2648)	
[2022-01-20 19:36:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][680/1251]	eta 0:21:09 lr 0.000746	time 3.5144 (2.2233)	loss 3.4259 (3.6941)	grad_norm 1.3385 (1.2659)	
[2022-01-20 19:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][690/1251]	eta 0:20:47 lr 0.000746	time 2.5362 (2.2231)	loss 4.0054 (3.6956)	grad_norm 1.2742 (1.2648)	
[2022-01-20 19:37:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][700/1251]	eta 0:20:25 lr 0.000745	time 1.9492 (2.2239)	loss 4.1289 (3.6990)	grad_norm 1.3409 (1.2639)	
[2022-01-20 19:37:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][710/1251]	eta 0:20:02 lr 0.000745	time 2.7254 (2.2236)	loss 4.0135 (3.7021)	grad_norm 1.2190 (1.2637)	
[2022-01-20 19:38:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][720/1251]	eta 0:19:39 lr 0.000745	time 1.8094 (2.2222)	loss 4.0051 (3.7031)	grad_norm 1.1569 (1.2630)	
[2022-01-20 19:38:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][730/1251]	eta 0:19:16 lr 0.000745	time 2.4495 (2.2199)	loss 3.7055 (3.7031)	grad_norm 1.1443 (1.2619)	
[2022-01-20 19:38:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][740/1251]	eta 0:18:52 lr 0.000745	time 1.7760 (2.2166)	loss 2.4837 (3.7026)	grad_norm 1.1769 (1.2627)	
[2022-01-20 19:39:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][750/1251]	eta 0:18:29 lr 0.000745	time 2.2834 (2.2155)	loss 3.8445 (3.7028)	grad_norm 1.2476 (1.2637)	
[2022-01-20 19:39:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][760/1251]	eta 0:18:07 lr 0.000745	time 2.6990 (2.2152)	loss 3.7512 (3.7045)	grad_norm 1.3395 (1.2638)	
[2022-01-20 19:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][770/1251]	eta 0:17:45 lr 0.000745	time 2.5451 (2.2161)	loss 3.4561 (3.7070)	grad_norm 1.1975 (1.2629)	
[2022-01-20 19:40:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][780/1251]	eta 0:17:23 lr 0.000745	time 2.3399 (2.2157)	loss 4.1069 (3.7099)	grad_norm 1.0865 (1.2622)	
[2022-01-20 19:40:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][790/1251]	eta 0:17:01 lr 0.000745	time 1.8420 (2.2149)	loss 3.9438 (3.7125)	grad_norm 1.1496 (1.2621)	
[2022-01-20 19:40:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][800/1251]	eta 0:16:38 lr 0.000745	time 2.1860 (2.2135)	loss 3.9024 (3.7090)	grad_norm 1.1717 (1.2609)	
[2022-01-20 19:41:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][810/1251]	eta 0:16:15 lr 0.000745	time 2.3369 (2.2111)	loss 3.8586 (3.7073)	grad_norm 1.0917 (1.2599)	
[2022-01-20 19:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][820/1251]	eta 0:15:53 lr 0.000745	time 1.8182 (2.2130)	loss 3.2414 (3.7071)	grad_norm 1.4584 (1.2603)	
[2022-01-20 19:42:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][830/1251]	eta 0:15:32 lr 0.000745	time 2.2265 (2.2150)	loss 3.1611 (3.7070)	grad_norm 1.2095 (1.2605)	
[2022-01-20 19:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][840/1251]	eta 0:15:11 lr 0.000745	time 2.0735 (2.2171)	loss 2.7762 (3.7074)	grad_norm 1.3724 (1.2619)	
[2022-01-20 19:42:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][850/1251]	eta 0:14:49 lr 0.000745	time 2.2592 (2.2174)	loss 4.2154 (3.7085)	grad_norm 1.2706 (1.2625)	
[2022-01-20 19:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][860/1251]	eta 0:14:26 lr 0.000745	time 1.5396 (2.2164)	loss 3.6132 (3.7103)	grad_norm 1.0957 (1.2614)	
[2022-01-20 19:43:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][870/1251]	eta 0:14:03 lr 0.000745	time 1.5925 (2.2138)	loss 4.3193 (3.7095)	grad_norm 1.1868 (1.2606)	
[2022-01-20 19:43:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][880/1251]	eta 0:13:41 lr 0.000745	time 2.2893 (2.2134)	loss 4.3717 (3.7080)	grad_norm 1.1800 (1.2613)	
[2022-01-20 19:44:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][890/1251]	eta 0:13:18 lr 0.000745	time 2.0785 (2.2129)	loss 4.0668 (3.7085)	grad_norm 1.0999 (1.2614)	
[2022-01-20 19:44:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][900/1251]	eta 0:12:56 lr 0.000745	time 1.5135 (2.2122)	loss 3.6151 (3.7086)	grad_norm 1.1478 (1.2610)	
[2022-01-20 19:44:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][910/1251]	eta 0:12:34 lr 0.000745	time 2.4406 (2.2117)	loss 2.7160 (3.7075)	grad_norm 1.4646 (1.2614)	
[2022-01-20 19:45:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][920/1251]	eta 0:12:11 lr 0.000745	time 1.8961 (2.2109)	loss 3.4579 (3.7082)	grad_norm 1.2063 (1.2616)	
[2022-01-20 19:45:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][930/1251]	eta 0:11:49 lr 0.000745	time 2.2081 (2.2108)	loss 2.3162 (3.7049)	grad_norm 1.1814 (1.2608)	
[2022-01-20 19:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][940/1251]	eta 0:11:27 lr 0.000745	time 1.9222 (2.2103)	loss 3.5316 (3.7075)	grad_norm 1.2237 (1.2601)	
[2022-01-20 19:46:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][950/1251]	eta 0:11:05 lr 0.000745	time 2.5808 (2.2117)	loss 2.4833 (3.7078)	grad_norm 1.1681 (1.2604)	
[2022-01-20 19:46:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][960/1251]	eta 0:10:43 lr 0.000745	time 2.4726 (2.2114)	loss 3.3686 (3.7078)	grad_norm 1.1172 (1.2594)	
[2022-01-20 19:47:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][970/1251]	eta 0:10:21 lr 0.000744	time 1.8553 (2.2102)	loss 3.7989 (3.7090)	grad_norm 1.2194 (1.2589)	
[2022-01-20 19:47:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][980/1251]	eta 0:09:58 lr 0.000744	time 2.4703 (2.2103)	loss 3.9968 (3.7096)	grad_norm 1.1709 (1.2585)	
[2022-01-20 19:47:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][990/1251]	eta 0:09:37 lr 0.000744	time 3.0119 (2.2112)	loss 4.0221 (3.7072)	grad_norm 1.4477 (1.2590)	
[2022-01-20 19:48:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1000/1251]	eta 0:09:15 lr 0.000744	time 2.5149 (2.2114)	loss 3.1027 (3.7071)	grad_norm 1.5249 (1.2595)	
[2022-01-20 19:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1010/1251]	eta 0:08:52 lr 0.000744	time 1.9025 (2.2106)	loss 4.0121 (3.7080)	grad_norm 1.2209 (1.2594)	
[2022-01-20 19:48:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1020/1251]	eta 0:08:30 lr 0.000744	time 1.7223 (2.2100)	loss 4.2812 (3.7095)	grad_norm 1.2460 (1.2593)	
[2022-01-20 19:49:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1030/1251]	eta 0:08:07 lr 0.000744	time 1.5759 (2.2079)	loss 3.1620 (3.7076)	grad_norm 1.1696 (1.2590)	
[2022-01-20 19:49:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1040/1251]	eta 0:07:45 lr 0.000744	time 2.1132 (2.2059)	loss 2.5661 (3.7064)	grad_norm 1.3819 (1.2592)	
[2022-01-20 19:49:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1050/1251]	eta 0:07:23 lr 0.000744	time 1.8264 (2.2051)	loss 4.2430 (3.7097)	grad_norm 1.2426 (1.2582)	
[2022-01-20 19:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1060/1251]	eta 0:07:00 lr 0.000744	time 1.8487 (2.2040)	loss 4.2777 (3.7110)	grad_norm 1.3585 (1.2580)	
[2022-01-20 19:50:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1070/1251]	eta 0:06:39 lr 0.000744	time 2.1091 (2.2057)	loss 4.0785 (3.7084)	grad_norm 1.1177 (1.2578)	
[2022-01-20 19:51:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1080/1251]	eta 0:06:17 lr 0.000744	time 2.2889 (2.2070)	loss 3.7298 (3.7096)	grad_norm 1.4555 (1.2578)	
[2022-01-20 19:51:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1090/1251]	eta 0:05:55 lr 0.000744	time 2.8024 (2.2073)	loss 4.4360 (3.7081)	grad_norm 1.1924 (1.2586)	
[2022-01-20 19:51:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1100/1251]	eta 0:05:33 lr 0.000744	time 1.7873 (2.2071)	loss 3.4385 (3.7083)	grad_norm 1.3301 (1.2582)	
[2022-01-20 19:52:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1110/1251]	eta 0:05:11 lr 0.000744	time 2.7444 (2.2076)	loss 4.1833 (3.7073)	grad_norm 1.2918 (1.2577)	
[2022-01-20 19:52:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1120/1251]	eta 0:04:49 lr 0.000744	time 2.1146 (2.2074)	loss 3.8566 (3.7090)	grad_norm 1.2054 (1.2578)	
[2022-01-20 19:52:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1130/1251]	eta 0:04:26 lr 0.000744	time 1.7262 (2.2056)	loss 4.1937 (3.7114)	grad_norm 1.3110 (1.2592)	
[2022-01-20 19:53:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1140/1251]	eta 0:04:04 lr 0.000744	time 1.6250 (2.2054)	loss 4.0521 (3.7103)	grad_norm 1.3944 (1.2590)	
[2022-01-20 19:53:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1150/1251]	eta 0:03:42 lr 0.000744	time 1.8897 (2.2045)	loss 4.1661 (3.7090)	grad_norm 1.4690 (1.2591)	
[2022-01-20 19:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1160/1251]	eta 0:03:20 lr 0.000744	time 2.8440 (2.2047)	loss 3.4263 (3.7088)	grad_norm 1.2314 (1.2590)	
[2022-01-20 19:54:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1170/1251]	eta 0:02:58 lr 0.000744	time 1.9676 (2.2057)	loss 4.0197 (3.7100)	grad_norm 1.3776 (1.2599)	
[2022-01-20 19:54:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1180/1251]	eta 0:02:36 lr 0.000744	time 1.5831 (2.2050)	loss 2.4219 (3.7087)	grad_norm 1.2018 (1.2600)	
[2022-01-20 19:55:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1190/1251]	eta 0:02:14 lr 0.000744	time 1.9354 (2.2046)	loss 3.5360 (3.7104)	grad_norm 1.2269 (1.2602)	
[2022-01-20 19:55:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1200/1251]	eta 0:01:52 lr 0.000744	time 2.3095 (2.2032)	loss 3.9780 (3.7126)	grad_norm 1.2448 (1.2600)	
[2022-01-20 19:55:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1210/1251]	eta 0:01:30 lr 0.000744	time 2.4249 (2.2029)	loss 4.0479 (3.7145)	grad_norm 1.1539 (1.2595)	
[2022-01-20 19:56:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1220/1251]	eta 0:01:08 lr 0.000744	time 1.9510 (2.2024)	loss 3.7837 (3.7118)	grad_norm 1.1901 (1.2595)	
[2022-01-20 19:56:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1230/1251]	eta 0:00:46 lr 0.000744	time 2.5032 (2.2038)	loss 3.6725 (3.7130)	grad_norm 1.3242 (1.2592)	
[2022-01-20 19:56:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1240/1251]	eta 0:00:24 lr 0.000744	time 1.7341 (2.2029)	loss 2.7490 (3.7135)	grad_norm 1.3801 (1.2590)	
[2022-01-20 19:57:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [101/300][1250/1251]	eta 0:00:02 lr 0.000743	time 1.1948 (2.1971)	loss 4.2586 (3.7141)	grad_norm 1.3783 (1.2599)	
[2022-01-20 19:57:09 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 101 training takes 0:45:49
[2022-01-20 19:57:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.747 (17.747)	Loss 1.0720 (1.0720)	Acc@1 74.805 (74.805)	Acc@5 92.773 (92.773)	
[2022-01-20 19:57:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.218 (3.356)	Loss 1.0211 (1.0812)	Acc@1 74.121 (74.885)	Acc@5 92.773 (92.551)	
[2022-01-20 19:58:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.935 (2.680)	Loss 1.1281 (1.1048)	Acc@1 74.707 (74.461)	Acc@5 92.090 (92.267)	
[2022-01-20 19:58:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.989 (2.418)	Loss 1.1439 (1.1118)	Acc@1 73.633 (74.354)	Acc@5 91.895 (92.191)	
[2022-01-20 19:58:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.316 (2.208)	Loss 1.1017 (1.1216)	Acc@1 74.121 (74.040)	Acc@5 93.262 (92.085)	
[2022-01-20 19:58:47 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.982 Acc@5 92.090
[2022-01-20 19:58:47 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.0%
[2022-01-20 19:58:47 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.98%
[2022-01-20 19:59:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][0/1251]	eta 7:27:10 lr 0.000743	time 21.4476 (21.4476)	loss 4.0122 (4.0122)	grad_norm 1.2566 (1.2566)	
[2022-01-20 19:59:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][10/1251]	eta 1:23:24 lr 0.000743	time 2.1001 (4.0322)	loss 3.0531 (3.5591)	grad_norm 1.2568 (1.2848)	
[2022-01-20 19:59:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][20/1251]	eta 1:04:47 lr 0.000743	time 1.5351 (3.1581)	loss 3.9507 (3.5666)	grad_norm 1.0432 (1.2972)	
[2022-01-20 20:00:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][30/1251]	eta 0:58:35 lr 0.000743	time 1.5254 (2.8795)	loss 4.4682 (3.5982)	grad_norm 1.1170 (1.2671)	
[2022-01-20 20:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][40/1251]	eta 0:55:00 lr 0.000743	time 4.2030 (2.7254)	loss 3.8833 (3.6962)	grad_norm 1.2198 (1.2427)	
[2022-01-20 20:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][50/1251]	eta 0:52:42 lr 0.000743	time 2.3158 (2.6329)	loss 4.2893 (3.7164)	grad_norm 1.3771 (1.2441)	
[2022-01-20 20:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][60/1251]	eta 0:51:33 lr 0.000743	time 1.6342 (2.5972)	loss 3.6344 (3.7048)	grad_norm 1.2623 (1.2574)	
[2022-01-20 20:01:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][70/1251]	eta 0:49:55 lr 0.000743	time 1.9464 (2.5367)	loss 3.5569 (3.6064)	grad_norm 1.2129 (1.2599)	
[2022-01-20 20:02:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][80/1251]	eta 0:48:34 lr 0.000743	time 2.6616 (2.4888)	loss 4.4612 (3.6438)	grad_norm 1.4307 (1.2708)	
[2022-01-20 20:02:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][90/1251]	eta 0:47:19 lr 0.000743	time 2.2236 (2.4457)	loss 3.8802 (3.6456)	grad_norm 1.3364 (1.2869)	
[2022-01-20 20:02:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][100/1251]	eta 0:46:05 lr 0.000743	time 1.7418 (2.4031)	loss 4.5319 (3.6649)	grad_norm 1.3099 (1.2865)	
[2022-01-20 20:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][110/1251]	eta 0:45:12 lr 0.000743	time 2.0207 (2.3773)	loss 4.0673 (3.6615)	grad_norm 1.4147 (1.2805)	
[2022-01-20 20:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][120/1251]	eta 0:44:22 lr 0.000743	time 3.2503 (2.3545)	loss 4.3466 (3.6262)	grad_norm 1.4636 (1.2761)	
[2022-01-20 20:03:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][130/1251]	eta 0:43:44 lr 0.000743	time 2.7009 (2.3416)	loss 4.0161 (3.6335)	grad_norm 1.2212 (1.2715)	
[2022-01-20 20:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][140/1251]	eta 0:43:13 lr 0.000743	time 1.9554 (2.3348)	loss 3.9155 (3.6309)	grad_norm 1.2814 (1.2699)	
[2022-01-20 20:04:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][150/1251]	eta 0:42:46 lr 0.000743	time 1.9579 (2.3307)	loss 2.5802 (3.6298)	grad_norm 1.4351 (1.2732)	
[2022-01-20 20:05:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][160/1251]	eta 0:42:22 lr 0.000743	time 2.5859 (2.3304)	loss 4.4914 (3.6304)	grad_norm 1.1406 (1.2698)	
[2022-01-20 20:05:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][170/1251]	eta 0:41:50 lr 0.000743	time 2.4359 (2.3228)	loss 2.5427 (3.6326)	grad_norm 1.4383 (1.2748)	
[2022-01-20 20:05:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][180/1251]	eta 0:41:26 lr 0.000743	time 1.9108 (2.3218)	loss 3.9346 (3.6371)	grad_norm 1.5879 (1.2747)	
[2022-01-20 20:06:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][190/1251]	eta 0:40:55 lr 0.000743	time 1.9161 (2.3139)	loss 2.8206 (3.6274)	grad_norm 1.2942 (1.2824)	
[2022-01-20 20:06:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][200/1251]	eta 0:40:18 lr 0.000743	time 1.8684 (2.3011)	loss 4.3343 (3.6436)	grad_norm 1.2100 (1.2807)	
[2022-01-20 20:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][210/1251]	eta 0:39:47 lr 0.000743	time 1.9255 (2.2937)	loss 3.1920 (3.6431)	grad_norm 1.1702 (1.2772)	
[2022-01-20 20:07:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][220/1251]	eta 0:39:28 lr 0.000743	time 2.2127 (2.2976)	loss 4.4295 (3.6470)	grad_norm 1.2956 (1.2761)	
[2022-01-20 20:07:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][230/1251]	eta 0:38:57 lr 0.000743	time 1.4601 (2.2891)	loss 3.3721 (3.6575)	grad_norm 1.1998 (1.2729)	
[2022-01-20 20:07:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][240/1251]	eta 0:38:33 lr 0.000743	time 2.1963 (2.2884)	loss 3.4046 (3.6665)	grad_norm 1.1452 (1.2731)	
[2022-01-20 20:08:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][250/1251]	eta 0:38:01 lr 0.000743	time 1.6408 (2.2794)	loss 4.3055 (3.6669)	grad_norm 1.1830 (1.2708)	
[2022-01-20 20:08:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][260/1251]	eta 0:37:33 lr 0.000743	time 1.9629 (2.2744)	loss 4.3317 (3.6689)	grad_norm 1.1536 (1.2695)	
[2022-01-20 20:09:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][270/1251]	eta 0:37:05 lr 0.000742	time 1.8393 (2.2688)	loss 4.1540 (3.6731)	grad_norm 0.9556 (1.2656)	
[2022-01-20 20:09:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][280/1251]	eta 0:36:42 lr 0.000742	time 2.2204 (2.2679)	loss 4.1045 (3.6817)	grad_norm 1.2499 (1.2637)	
[2022-01-20 20:09:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][290/1251]	eta 0:36:16 lr 0.000742	time 2.4962 (2.2650)	loss 3.3143 (3.6901)	grad_norm 1.1819 (1.2626)	
[2022-01-20 20:10:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][300/1251]	eta 0:35:51 lr 0.000742	time 2.1356 (2.2624)	loss 3.8584 (3.6995)	grad_norm 1.1710 (1.2616)	
[2022-01-20 20:10:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][310/1251]	eta 0:35:26 lr 0.000742	time 2.1339 (2.2602)	loss 3.5459 (3.7072)	grad_norm 1.2853 (1.2595)	
[2022-01-20 20:10:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][320/1251]	eta 0:35:00 lr 0.000742	time 2.2384 (2.2562)	loss 4.2469 (3.7076)	grad_norm 1.5512 (1.2613)	
[2022-01-20 20:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][330/1251]	eta 0:34:37 lr 0.000742	time 2.1818 (2.2553)	loss 4.2735 (3.7177)	grad_norm 1.2017 (1.2604)	
[2022-01-20 20:11:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][340/1251]	eta 0:34:14 lr 0.000742	time 2.2981 (2.2555)	loss 3.9061 (3.7202)	grad_norm 1.1255 (1.2598)	
[2022-01-20 20:11:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][350/1251]	eta 0:33:49 lr 0.000742	time 1.6168 (2.2524)	loss 3.1413 (3.7178)	grad_norm 1.1128 (1.2595)	
[2022-01-20 20:12:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][360/1251]	eta 0:33:20 lr 0.000742	time 2.2958 (2.2457)	loss 4.0586 (3.7173)	grad_norm 1.1925 (1.2611)	
[2022-01-20 20:12:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][370/1251]	eta 0:32:54 lr 0.000742	time 1.7216 (2.2410)	loss 3.2087 (3.7086)	grad_norm 1.3017 (1.2619)	
[2022-01-20 20:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][380/1251]	eta 0:32:27 lr 0.000742	time 1.9048 (2.2355)	loss 3.8185 (3.7103)	grad_norm 1.2330 (1.2636)	
[2022-01-20 20:13:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][390/1251]	eta 0:32:02 lr 0.000742	time 2.3968 (2.2332)	loss 3.4529 (3.7079)	grad_norm 1.4863 (1.2657)	
[2022-01-20 20:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][400/1251]	eta 0:31:43 lr 0.000742	time 2.7449 (2.2367)	loss 4.0485 (3.7183)	grad_norm 1.2745 (1.2652)	
[2022-01-20 20:14:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][410/1251]	eta 0:31:20 lr 0.000742	time 2.6950 (2.2365)	loss 3.8751 (3.7136)	grad_norm 1.5066 (1.2671)	
[2022-01-20 20:14:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][420/1251]	eta 0:30:59 lr 0.000742	time 2.5283 (2.2373)	loss 3.0426 (3.7147)	grad_norm 1.3845 (1.2690)	
[2022-01-20 20:14:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][430/1251]	eta 0:30:37 lr 0.000742	time 2.2747 (2.2379)	loss 3.9452 (3.7190)	grad_norm 1.5362 (1.2694)	
[2022-01-20 20:15:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][440/1251]	eta 0:30:16 lr 0.000742	time 2.5176 (2.2394)	loss 3.4189 (3.7159)	grad_norm 1.6476 (1.2710)	
[2022-01-20 20:15:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][450/1251]	eta 0:29:53 lr 0.000742	time 2.1793 (2.2390)	loss 3.3721 (3.7173)	grad_norm 1.3204 (1.2719)	
[2022-01-20 20:15:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][460/1251]	eta 0:29:27 lr 0.000742	time 1.9436 (2.2350)	loss 3.9942 (3.7203)	grad_norm 1.3217 (1.2713)	
[2022-01-20 20:16:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][470/1251]	eta 0:29:00 lr 0.000742	time 1.9229 (2.2283)	loss 4.1681 (3.7156)	grad_norm 1.2717 (1.2704)	
[2022-01-20 20:16:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][480/1251]	eta 0:28:34 lr 0.000742	time 2.2437 (2.2244)	loss 2.9843 (3.7141)	grad_norm 1.1740 (1.2701)	
[2022-01-20 20:17:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][490/1251]	eta 0:28:13 lr 0.000742	time 2.4434 (2.2257)	loss 3.6071 (3.7097)	grad_norm 1.3192 (1.2689)	
[2022-01-20 20:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][500/1251]	eta 0:27:53 lr 0.000742	time 2.5822 (2.2283)	loss 3.3107 (3.7106)	grad_norm 1.2672 (1.2691)	
[2022-01-20 20:17:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][510/1251]	eta 0:27:30 lr 0.000742	time 1.9671 (2.2268)	loss 3.9542 (3.7041)	grad_norm 1.2879 (1.2680)	
[2022-01-20 20:18:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][520/1251]	eta 0:27:06 lr 0.000742	time 2.1587 (2.2256)	loss 3.7270 (3.7069)	grad_norm 1.2471 (1.2677)	
[2022-01-20 20:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][530/1251]	eta 0:26:42 lr 0.000742	time 2.1873 (2.2223)	loss 3.9603 (3.7030)	grad_norm 1.0709 (1.2664)	
[2022-01-20 20:18:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][540/1251]	eta 0:26:20 lr 0.000742	time 1.8161 (2.2227)	loss 4.0240 (3.7052)	grad_norm 1.2115 (1.2683)	
[2022-01-20 20:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][550/1251]	eta 0:25:57 lr 0.000741	time 1.9519 (2.2218)	loss 4.1132 (3.7051)	grad_norm 1.3386 (1.2680)	
[2022-01-20 20:19:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][560/1251]	eta 0:25:36 lr 0.000741	time 2.7402 (2.2238)	loss 2.6722 (3.7000)	grad_norm 1.2640 (1.2678)	
[2022-01-20 20:19:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][570/1251]	eta 0:25:13 lr 0.000741	time 2.2378 (2.2225)	loss 3.6881 (3.7026)	grad_norm 1.1049 (1.2682)	
[2022-01-20 20:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][580/1251]	eta 0:24:52 lr 0.000741	time 1.6360 (2.2240)	loss 3.3359 (3.7026)	grad_norm 1.4063 (1.2681)	
[2022-01-20 20:20:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][590/1251]	eta 0:24:31 lr 0.000741	time 2.1223 (2.2254)	loss 4.0398 (3.7022)	grad_norm 1.4236 (1.2682)	
[2022-01-20 20:21:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][600/1251]	eta 0:24:07 lr 0.000741	time 2.5882 (2.2230)	loss 3.6534 (3.7035)	grad_norm 1.0852 (1.2683)	
[2022-01-20 20:21:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][610/1251]	eta 0:23:43 lr 0.000741	time 2.3506 (2.2206)	loss 4.3576 (3.7065)	grad_norm 1.2923 (1.2678)	
[2022-01-20 20:21:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][620/1251]	eta 0:23:19 lr 0.000741	time 2.4246 (2.2176)	loss 3.7870 (3.7110)	grad_norm 1.3576 (1.2673)	
[2022-01-20 20:22:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][630/1251]	eta 0:22:55 lr 0.000741	time 1.6858 (2.2148)	loss 4.0339 (3.7094)	grad_norm 1.2576 (1.2682)	
[2022-01-20 20:22:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][640/1251]	eta 0:22:33 lr 0.000741	time 2.8190 (2.2152)	loss 3.2722 (3.7056)	grad_norm 1.0889 (1.2677)	
[2022-01-20 20:22:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][650/1251]	eta 0:22:09 lr 0.000741	time 2.1541 (2.2127)	loss 3.2312 (3.7029)	grad_norm 1.2337 (1.2679)	
[2022-01-20 20:23:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][660/1251]	eta 0:21:48 lr 0.000741	time 2.5077 (2.2138)	loss 3.3900 (3.7062)	grad_norm 1.1647 (1.2693)	
[2022-01-20 20:23:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][670/1251]	eta 0:21:27 lr 0.000741	time 1.5109 (2.2164)	loss 3.4332 (3.7063)	grad_norm 1.2056 (1.2709)	
[2022-01-20 20:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][680/1251]	eta 0:21:05 lr 0.000741	time 1.8250 (2.2166)	loss 4.6178 (3.7069)	grad_norm 1.1980 (1.2711)	
[2022-01-20 20:24:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][690/1251]	eta 0:20:42 lr 0.000741	time 2.2939 (2.2147)	loss 4.1742 (3.7034)	grad_norm 1.1341 (1.2706)	
[2022-01-20 20:24:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][700/1251]	eta 0:20:19 lr 0.000741	time 2.3383 (2.2134)	loss 4.3472 (3.7033)	grad_norm 1.2112 (1.2694)	
[2022-01-20 20:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][710/1251]	eta 0:19:57 lr 0.000741	time 1.9778 (2.2139)	loss 4.2883 (3.7014)	grad_norm 1.1867 (1.2696)	
[2022-01-20 20:25:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][720/1251]	eta 0:19:35 lr 0.000741	time 2.1659 (2.2134)	loss 2.7633 (3.6957)	grad_norm 1.3025 (1.2697)	
[2022-01-20 20:25:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][730/1251]	eta 0:19:13 lr 0.000741	time 2.2539 (2.2137)	loss 4.3079 (3.6977)	grad_norm 1.3227 (1.2692)	
[2022-01-20 20:26:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][740/1251]	eta 0:18:51 lr 0.000741	time 2.8198 (2.2149)	loss 4.2382 (3.6970)	grad_norm 1.2834 (1.2691)	
[2022-01-20 20:26:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][750/1251]	eta 0:18:29 lr 0.000741	time 1.6342 (2.2145)	loss 3.2554 (3.6987)	grad_norm 1.0984 (1.2689)	
[2022-01-20 20:26:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][760/1251]	eta 0:18:06 lr 0.000741	time 2.2636 (2.2127)	loss 4.4029 (3.6993)	grad_norm 1.2350 (1.2689)	
[2022-01-20 20:27:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][770/1251]	eta 0:17:43 lr 0.000741	time 1.5424 (2.2102)	loss 3.7736 (3.7018)	grad_norm 1.2372 (1.2683)	
[2022-01-20 20:27:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][780/1251]	eta 0:17:20 lr 0.000741	time 1.9409 (2.2096)	loss 3.9880 (3.7026)	grad_norm 1.5477 (1.2698)	
[2022-01-20 20:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][790/1251]	eta 0:16:58 lr 0.000741	time 2.5327 (2.2084)	loss 2.8142 (3.7054)	grad_norm 1.1465 (1.2691)	
[2022-01-20 20:28:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][800/1251]	eta 0:16:36 lr 0.000741	time 2.2370 (2.2103)	loss 3.9907 (3.7067)	grad_norm 1.2015 (1.2681)	
[2022-01-20 20:28:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][810/1251]	eta 0:16:14 lr 0.000741	time 1.9614 (2.2103)	loss 4.0167 (3.7051)	grad_norm 1.1048 (1.2677)	
[2022-01-20 20:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][820/1251]	eta 0:15:52 lr 0.000740	time 2.1339 (2.2099)	loss 4.4697 (3.7063)	grad_norm 1.3162 (1.2684)	
[2022-01-20 20:29:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][830/1251]	eta 0:15:30 lr 0.000740	time 2.1559 (2.2094)	loss 4.0865 (3.7050)	grad_norm 1.5625 (1.2681)	
[2022-01-20 20:29:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][840/1251]	eta 0:15:08 lr 0.000740	time 1.9004 (2.2095)	loss 4.2806 (3.7075)	grad_norm 1.1383 (1.2678)	
[2022-01-20 20:30:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][850/1251]	eta 0:14:45 lr 0.000740	time 2.1806 (2.2084)	loss 2.5851 (3.7076)	grad_norm 1.2272 (1.2675)	
[2022-01-20 20:30:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][860/1251]	eta 0:14:22 lr 0.000740	time 2.5599 (2.2071)	loss 3.0970 (3.7027)	grad_norm 1.1102 (1.2690)	
[2022-01-20 20:30:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][870/1251]	eta 0:14:00 lr 0.000740	time 1.8407 (2.2052)	loss 3.8658 (3.7016)	grad_norm 1.1327 (1.2684)	
[2022-01-20 20:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][880/1251]	eta 0:13:39 lr 0.000740	time 2.2505 (2.2077)	loss 3.7870 (3.7026)	grad_norm 1.3942 (1.2686)	
[2022-01-20 20:31:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][890/1251]	eta 0:13:16 lr 0.000740	time 2.2015 (2.2069)	loss 3.2932 (3.7040)	grad_norm 1.2607 (1.2681)	
[2022-01-20 20:31:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][900/1251]	eta 0:12:54 lr 0.000740	time 2.4824 (2.2076)	loss 4.3272 (3.7076)	grad_norm 1.1310 (1.2681)	
[2022-01-20 20:32:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][910/1251]	eta 0:12:32 lr 0.000740	time 2.1231 (2.2077)	loss 2.6665 (3.7085)	grad_norm 1.1870 (1.2672)	
[2022-01-20 20:32:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][920/1251]	eta 0:12:10 lr 0.000740	time 1.6075 (2.2065)	loss 4.2207 (3.7112)	grad_norm 1.2699 (1.2670)	
[2022-01-20 20:33:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][930/1251]	eta 0:11:47 lr 0.000740	time 1.8842 (2.2045)	loss 4.1613 (3.7099)	grad_norm 1.2021 (1.2658)	
[2022-01-20 20:33:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][940/1251]	eta 0:11:25 lr 0.000740	time 1.8747 (2.2036)	loss 4.0438 (3.7130)	grad_norm 1.2809 (1.2658)	
[2022-01-20 20:33:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][950/1251]	eta 0:11:02 lr 0.000740	time 2.2385 (2.2025)	loss 3.9380 (3.7146)	grad_norm 1.2159 (1.2667)	
[2022-01-20 20:34:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][960/1251]	eta 0:10:41 lr 0.000740	time 1.8903 (2.2031)	loss 3.8007 (3.7143)	grad_norm 1.0932 (1.2663)	
[2022-01-20 20:34:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][970/1251]	eta 0:10:19 lr 0.000740	time 2.5996 (2.2033)	loss 4.2663 (3.7142)	grad_norm 1.3138 (1.2657)	
[2022-01-20 20:34:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][980/1251]	eta 0:09:57 lr 0.000740	time 2.3763 (2.2039)	loss 3.9984 (3.7134)	grad_norm 1.2462 (1.2660)	
[2022-01-20 20:35:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][990/1251]	eta 0:09:35 lr 0.000740	time 1.6405 (2.2033)	loss 3.2689 (3.7112)	grad_norm 1.1954 (1.2656)	
[2022-01-20 20:35:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1000/1251]	eta 0:09:12 lr 0.000740	time 1.6163 (2.2031)	loss 4.1604 (3.7112)	grad_norm 1.1679 (1.2656)	
[2022-01-20 20:35:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1010/1251]	eta 0:08:50 lr 0.000740	time 2.2056 (2.2015)	loss 3.4077 (3.7112)	grad_norm 1.1550 (1.2648)	
[2022-01-20 20:36:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1020/1251]	eta 0:08:28 lr 0.000740	time 3.0113 (2.2011)	loss 3.2851 (3.7117)	grad_norm 1.1845 (1.2648)	
[2022-01-20 20:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1030/1251]	eta 0:08:06 lr 0.000740	time 2.1443 (2.2013)	loss 4.4094 (3.7125)	grad_norm 1.4572 (1.2651)	
[2022-01-20 20:36:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1040/1251]	eta 0:07:44 lr 0.000740	time 1.5703 (2.2012)	loss 3.9183 (3.7124)	grad_norm 1.5209 (1.2655)	
[2022-01-20 20:37:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1050/1251]	eta 0:07:22 lr 0.000740	time 1.6315 (2.2000)	loss 4.7448 (3.7120)	grad_norm 1.5840 (1.2655)	
[2022-01-20 20:37:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1060/1251]	eta 0:07:00 lr 0.000740	time 2.4372 (2.2007)	loss 4.0706 (3.7119)	grad_norm 1.2729 (1.2653)	
[2022-01-20 20:38:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1070/1251]	eta 0:06:38 lr 0.000740	time 1.5742 (2.2005)	loss 4.3847 (3.7128)	grad_norm 1.4053 (1.2652)	
[2022-01-20 20:38:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1080/1251]	eta 0:06:16 lr 0.000740	time 2.3686 (2.2020)	loss 4.0304 (3.7126)	grad_norm 1.2318 (1.2649)	
[2022-01-20 20:38:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1090/1251]	eta 0:05:54 lr 0.000740	time 1.9479 (2.2016)	loss 3.7038 (3.7112)	grad_norm 1.4160 (1.2649)	
[2022-01-20 20:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1100/1251]	eta 0:05:32 lr 0.000739	time 2.2171 (2.2005)	loss 4.3859 (3.7109)	grad_norm 1.3462 (1.2650)	
[2022-01-20 20:39:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1110/1251]	eta 0:05:10 lr 0.000739	time 1.5489 (2.1987)	loss 2.3354 (3.7116)	grad_norm 1.2039 (1.2653)	
[2022-01-20 20:39:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1120/1251]	eta 0:04:47 lr 0.000739	time 1.9573 (2.1975)	loss 3.9238 (3.7106)	grad_norm 1.1265 (1.2651)	
[2022-01-20 20:40:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1130/1251]	eta 0:04:25 lr 0.000739	time 1.9534 (2.1971)	loss 3.8723 (3.7107)	grad_norm 1.1655 (1.2643)	
[2022-01-20 20:40:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1140/1251]	eta 0:04:03 lr 0.000739	time 2.4169 (2.1979)	loss 2.8091 (3.7083)	grad_norm 1.1139 (1.2639)	
[2022-01-20 20:40:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1150/1251]	eta 0:03:42 lr 0.000739	time 2.2003 (2.1995)	loss 3.7381 (3.7061)	grad_norm 1.2791 (1.2636)	
[2022-01-20 20:41:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1160/1251]	eta 0:03:20 lr 0.000739	time 2.7526 (2.1997)	loss 3.3815 (3.7062)	grad_norm 1.0391 (1.2632)	
[2022-01-20 20:41:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1170/1251]	eta 0:02:58 lr 0.000739	time 2.1947 (2.1999)	loss 4.0691 (3.7086)	grad_norm 1.1471 (1.2630)	
[2022-01-20 20:42:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1180/1251]	eta 0:02:36 lr 0.000739	time 2.2048 (2.2002)	loss 3.2451 (3.7088)	grad_norm 1.2075 (1.2623)	
[2022-01-20 20:42:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1190/1251]	eta 0:02:14 lr 0.000739	time 1.6323 (2.1995)	loss 3.0957 (3.7077)	grad_norm 1.3551 (1.2631)	
[2022-01-20 20:42:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1200/1251]	eta 0:01:52 lr 0.000739	time 2.1485 (2.1995)	loss 3.2541 (3.7066)	grad_norm 1.1152 (1.2627)	
[2022-01-20 20:43:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1210/1251]	eta 0:01:30 lr 0.000739	time 1.6441 (2.1986)	loss 3.2025 (3.7042)	grad_norm 1.1851 (1.2625)	
[2022-01-20 20:43:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1220/1251]	eta 0:01:08 lr 0.000739	time 3.1325 (2.1990)	loss 3.7768 (3.7053)	grad_norm 1.1754 (1.2624)	
[2022-01-20 20:43:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1230/1251]	eta 0:00:46 lr 0.000739	time 2.4031 (2.2004)	loss 3.5154 (3.7043)	grad_norm 1.1677 (1.2621)	
[2022-01-20 20:44:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1240/1251]	eta 0:00:24 lr 0.000739	time 1.2564 (2.1975)	loss 4.2360 (3.7035)	grad_norm 1.2700 (1.2623)	
[2022-01-20 20:44:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [102/300][1250/1251]	eta 0:00:02 lr 0.000739	time 1.1896 (2.1916)	loss 4.1369 (3.7055)	grad_norm 1.2084 (1.2617)	
[2022-01-20 20:44:29 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 102 training takes 0:45:42
[2022-01-20 20:44:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.787 (18.787)	Loss 1.1350 (1.1350)	Acc@1 72.852 (72.852)	Acc@5 92.578 (92.578)	
[2022-01-20 20:45:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.693 (3.460)	Loss 1.0913 (1.1264)	Acc@1 73.438 (73.509)	Acc@5 93.164 (92.285)	
[2022-01-20 20:45:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.271 (2.482)	Loss 1.1779 (1.1374)	Acc@1 71.680 (73.498)	Acc@5 91.504 (92.090)	
[2022-01-20 20:45:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.636 (2.233)	Loss 1.1785 (1.1305)	Acc@1 72.949 (73.671)	Acc@5 90.918 (92.080)	
[2022-01-20 20:45:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.827 (2.162)	Loss 1.1580 (1.1335)	Acc@1 73.242 (73.552)	Acc@5 90.918 (92.054)	
[2022-01-20 20:46:05 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.596 Acc@5 92.040
[2022-01-20 20:46:05 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.6%
[2022-01-20 20:46:05 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.98%
[2022-01-20 20:46:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][0/1251]	eta 7:40:25 lr 0.000739	time 22.0824 (22.0824)	loss 3.7372 (3.7372)	grad_norm 1.1489 (1.1489)	
[2022-01-20 20:46:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][10/1251]	eta 1:23:27 lr 0.000739	time 2.5328 (4.0347)	loss 3.0550 (3.5069)	grad_norm 1.2587 (1.1680)	
[2022-01-20 20:47:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][20/1251]	eta 1:03:55 lr 0.000739	time 1.4664 (3.1154)	loss 3.2562 (3.6429)	grad_norm 1.2959 (1.2222)	
[2022-01-20 20:47:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][30/1251]	eta 0:57:29 lr 0.000739	time 1.9197 (2.8250)	loss 4.3172 (3.6639)	grad_norm 1.3547 (1.2611)	
[2022-01-20 20:47:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][40/1251]	eta 0:54:53 lr 0.000739	time 3.7461 (2.7196)	loss 3.0574 (3.6502)	grad_norm 1.2063 (1.2650)	
[2022-01-20 20:48:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][50/1251]	eta 0:52:36 lr 0.000739	time 2.2141 (2.6283)	loss 4.1299 (3.5744)	grad_norm 1.0609 (1.2456)	
[2022-01-20 20:48:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][60/1251]	eta 0:50:13 lr 0.000739	time 1.5377 (2.5305)	loss 4.3172 (3.6345)	grad_norm 1.2995 (1.2390)	
[2022-01-20 20:49:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][70/1251]	eta 0:48:44 lr 0.000739	time 1.8454 (2.4764)	loss 3.7278 (3.6555)	grad_norm 1.1082 (1.2458)	
[2022-01-20 20:49:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][80/1251]	eta 0:48:00 lr 0.000739	time 3.3560 (2.4594)	loss 4.1342 (3.6612)	grad_norm 1.3283 (1.2492)	
[2022-01-20 20:49:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][90/1251]	eta 0:47:00 lr 0.000739	time 2.3397 (2.4290)	loss 4.4713 (3.6805)	grad_norm 1.3437 (1.2571)	
[2022-01-20 20:50:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][100/1251]	eta 0:46:09 lr 0.000739	time 1.7500 (2.4062)	loss 3.8984 (3.6581)	grad_norm 1.3429 (1.2784)	
[2022-01-20 20:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][110/1251]	eta 0:45:23 lr 0.000739	time 1.9690 (2.3870)	loss 3.4662 (3.6328)	grad_norm 1.4909 (1.2791)	
[2022-01-20 20:50:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][120/1251]	eta 0:44:52 lr 0.000738	time 3.0818 (2.3805)	loss 3.9081 (3.6431)	grad_norm 1.4361 (1.2853)	
[2022-01-20 20:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][130/1251]	eta 0:44:09 lr 0.000738	time 2.1966 (2.3638)	loss 2.5915 (3.6390)	grad_norm 1.3169 (1.2800)	
[2022-01-20 20:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][140/1251]	eta 0:43:23 lr 0.000738	time 1.9267 (2.3433)	loss 4.6604 (3.6453)	grad_norm 1.2714 (1.2741)	
[2022-01-20 20:51:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][150/1251]	eta 0:42:43 lr 0.000738	time 1.9658 (2.3279)	loss 4.1587 (3.6519)	grad_norm 1.1500 (1.2700)	
[2022-01-20 20:52:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][160/1251]	eta 0:42:09 lr 0.000738	time 2.5557 (2.3183)	loss 3.3827 (3.6621)	grad_norm 1.1313 (1.2700)	
[2022-01-20 20:52:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][170/1251]	eta 0:41:37 lr 0.000738	time 1.8833 (2.3107)	loss 3.0973 (3.6631)	grad_norm 1.4495 (1.2718)	
[2022-01-20 20:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][180/1251]	eta 0:41:08 lr 0.000738	time 2.2320 (2.3051)	loss 3.6888 (3.6548)	grad_norm 1.1394 (1.2702)	
[2022-01-20 20:53:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][190/1251]	eta 0:40:39 lr 0.000738	time 2.1716 (2.2988)	loss 2.9548 (3.6463)	grad_norm 1.4253 (1.2666)	
[2022-01-20 20:53:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][200/1251]	eta 0:40:13 lr 0.000738	time 2.8607 (2.2961)	loss 3.7034 (3.6628)	grad_norm 1.1557 (1.2667)	
[2022-01-20 20:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][210/1251]	eta 0:39:44 lr 0.000738	time 2.1152 (2.2910)	loss 3.7848 (3.6676)	grad_norm 1.2182 (1.2667)	
[2022-01-20 20:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][220/1251]	eta 0:39:12 lr 0.000738	time 1.8572 (2.2815)	loss 3.8990 (3.6674)	grad_norm 1.3793 (1.2660)	
[2022-01-20 20:54:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][230/1251]	eta 0:38:43 lr 0.000738	time 2.2036 (2.2759)	loss 3.1349 (3.6648)	grad_norm 1.4120 (1.2667)	
[2022-01-20 20:55:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][240/1251]	eta 0:38:19 lr 0.000738	time 2.7948 (2.2741)	loss 4.3177 (3.6670)	grad_norm 1.2103 (1.2672)	
[2022-01-20 20:55:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][250/1251]	eta 0:37:51 lr 0.000738	time 1.7893 (2.2692)	loss 2.5820 (3.6703)	grad_norm 1.4548 (1.2654)	
[2022-01-20 20:55:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][260/1251]	eta 0:37:31 lr 0.000738	time 2.0818 (2.2715)	loss 3.8032 (3.6704)	grad_norm 1.3531 (1.2673)	
[2022-01-20 20:56:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][270/1251]	eta 0:37:06 lr 0.000738	time 2.2058 (2.2695)	loss 3.6686 (3.6663)	grad_norm 1.1049 (1.2661)	
[2022-01-20 20:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][280/1251]	eta 0:36:38 lr 0.000738	time 2.4786 (2.2640)	loss 4.0689 (3.6669)	grad_norm 1.3599 (1.2654)	
[2022-01-20 20:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][290/1251]	eta 0:36:04 lr 0.000738	time 1.5735 (2.2520)	loss 2.4580 (3.6606)	grad_norm 1.4036 (1.2646)	
[2022-01-20 20:57:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][300/1251]	eta 0:35:39 lr 0.000738	time 2.4132 (2.2492)	loss 3.0977 (3.6552)	grad_norm 1.1492 (1.2636)	
[2022-01-20 20:57:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][310/1251]	eta 0:35:16 lr 0.000738	time 3.1423 (2.2490)	loss 3.1757 (3.6535)	grad_norm 1.0991 (1.2618)	
[2022-01-20 20:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][320/1251]	eta 0:34:55 lr 0.000738	time 2.7276 (2.2512)	loss 4.0692 (3.6435)	grad_norm 1.3956 (1.2619)	
[2022-01-20 20:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][330/1251]	eta 0:34:28 lr 0.000738	time 1.9522 (2.2457)	loss 4.2085 (3.6475)	grad_norm 1.4633 (1.2686)	
[2022-01-20 20:58:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][340/1251]	eta 0:34:05 lr 0.000738	time 2.2041 (2.2459)	loss 2.6903 (3.6460)	grad_norm 1.1404 (1.2685)	
[2022-01-20 20:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][350/1251]	eta 0:33:45 lr 0.000738	time 3.1500 (2.2485)	loss 3.0064 (3.6496)	grad_norm 1.5071 (1.2698)	
[2022-01-20 20:59:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][360/1251]	eta 0:33:19 lr 0.000738	time 2.5563 (2.2445)	loss 3.9760 (3.6569)	grad_norm 1.5863 (1.2725)	
[2022-01-20 20:59:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][370/1251]	eta 0:32:50 lr 0.000738	time 1.9174 (2.2371)	loss 3.8611 (3.6547)	grad_norm 1.3004 (1.2721)	
[2022-01-20 21:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][380/1251]	eta 0:32:24 lr 0.000738	time 1.9431 (2.2322)	loss 4.4676 (3.6593)	grad_norm 1.1061 (1.2714)	
[2022-01-20 21:00:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][390/1251]	eta 0:32:00 lr 0.000737	time 1.8792 (2.2306)	loss 3.7700 (3.6639)	grad_norm 1.5799 (1.2727)	
[2022-01-20 21:01:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][400/1251]	eta 0:31:38 lr 0.000737	time 2.6738 (2.2307)	loss 4.3044 (3.6657)	grad_norm 1.2157 (1.2751)	
[2022-01-20 21:01:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][410/1251]	eta 0:31:16 lr 0.000737	time 2.7394 (2.2318)	loss 3.4030 (3.6741)	grad_norm 1.4617 (1.2763)	
[2022-01-20 21:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][420/1251]	eta 0:30:55 lr 0.000737	time 3.1036 (2.2324)	loss 3.5798 (3.6753)	grad_norm 1.1836 (1.2760)	
[2022-01-20 21:02:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][430/1251]	eta 0:30:30 lr 0.000737	time 2.0468 (2.2291)	loss 3.9490 (3.6753)	grad_norm 1.1943 (1.2748)	
[2022-01-20 21:02:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][440/1251]	eta 0:30:07 lr 0.000737	time 2.4470 (2.2291)	loss 4.5255 (3.6803)	grad_norm 1.2189 (1.2741)	
[2022-01-20 21:02:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][450/1251]	eta 0:29:47 lr 0.000737	time 2.5104 (2.2310)	loss 3.7327 (3.6712)	grad_norm 1.1240 (1.2739)	
[2022-01-20 21:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][460/1251]	eta 0:29:25 lr 0.000737	time 2.5618 (2.2321)	loss 2.9730 (3.6641)	grad_norm 1.2126 (1.2724)	
[2022-01-20 21:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][470/1251]	eta 0:29:00 lr 0.000737	time 1.9647 (2.2286)	loss 4.4757 (3.6667)	grad_norm 1.6471 (1.2721)	
[2022-01-20 21:03:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][480/1251]	eta 0:28:33 lr 0.000737	time 1.9312 (2.2231)	loss 4.2017 (3.6659)	grad_norm 1.3449 (1.2730)	
[2022-01-20 21:04:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][490/1251]	eta 0:28:08 lr 0.000737	time 2.0134 (2.2190)	loss 3.9629 (3.6646)	grad_norm 1.1332 (1.2722)	
[2022-01-20 21:04:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][500/1251]	eta 0:27:45 lr 0.000737	time 2.5684 (2.2178)	loss 3.8264 (3.6642)	grad_norm 1.2775 (1.2731)	
[2022-01-20 21:04:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][510/1251]	eta 0:27:22 lr 0.000737	time 2.1945 (2.2163)	loss 4.0792 (3.6689)	grad_norm 1.3590 (1.2728)	
[2022-01-20 21:05:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][520/1251]	eta 0:27:01 lr 0.000737	time 1.4591 (2.2181)	loss 4.1104 (3.6715)	grad_norm 1.2406 (1.2730)	
[2022-01-20 21:05:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][530/1251]	eta 0:26:40 lr 0.000737	time 2.2176 (2.2200)	loss 4.0891 (3.6681)	grad_norm 1.2222 (1.2738)	
[2022-01-20 21:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][540/1251]	eta 0:26:18 lr 0.000737	time 2.3646 (2.2201)	loss 2.7520 (3.6647)	grad_norm 1.2387 (1.2740)	
[2022-01-20 21:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][550/1251]	eta 0:25:55 lr 0.000737	time 2.1040 (2.2195)	loss 3.9114 (3.6620)	grad_norm 1.2752 (1.2749)	
[2022-01-20 21:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][560/1251]	eta 0:25:32 lr 0.000737	time 1.8407 (2.2183)	loss 3.0806 (3.6614)	grad_norm 1.0730 (1.2746)	
[2022-01-20 21:07:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][570/1251]	eta 0:25:11 lr 0.000737	time 2.1471 (2.2195)	loss 3.9881 (3.6670)	grad_norm 1.3040 (1.2751)	
[2022-01-20 21:07:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][580/1251]	eta 0:24:50 lr 0.000737	time 2.1574 (2.2207)	loss 4.6602 (3.6715)	grad_norm 1.2449 (1.2748)	
[2022-01-20 21:07:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][590/1251]	eta 0:24:29 lr 0.000737	time 2.6176 (2.2230)	loss 4.0407 (3.6720)	grad_norm 1.4439 (1.2749)	
[2022-01-20 21:08:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][600/1251]	eta 0:24:07 lr 0.000737	time 1.9347 (2.2228)	loss 2.9121 (3.6677)	grad_norm 1.3307 (1.2764)	
[2022-01-20 21:08:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][610/1251]	eta 0:23:42 lr 0.000737	time 2.2506 (2.2195)	loss 4.1069 (3.6716)	grad_norm 1.3766 (1.2765)	
[2022-01-20 21:09:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][620/1251]	eta 0:23:16 lr 0.000737	time 1.9129 (2.2138)	loss 3.7329 (3.6717)	grad_norm 1.2620 (1.2758)	
[2022-01-20 21:09:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][630/1251]	eta 0:22:52 lr 0.000737	time 1.8604 (2.2107)	loss 4.0685 (3.6730)	grad_norm 1.4392 (1.2757)	
[2022-01-20 21:09:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][640/1251]	eta 0:22:30 lr 0.000737	time 2.5864 (2.2099)	loss 4.0368 (3.6752)	grad_norm 1.2576 (1.2760)	
[2022-01-20 21:10:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][650/1251]	eta 0:22:08 lr 0.000737	time 2.4956 (2.2110)	loss 3.1563 (3.6801)	grad_norm 1.2501 (1.2752)	
[2022-01-20 21:10:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][660/1251]	eta 0:21:45 lr 0.000736	time 1.9130 (2.2090)	loss 3.4921 (3.6815)	grad_norm 1.3139 (1.2751)	
[2022-01-20 21:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][670/1251]	eta 0:21:24 lr 0.000736	time 2.5069 (2.2105)	loss 3.7273 (3.6819)	grad_norm 1.2350 (1.2760)	
[2022-01-20 21:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][680/1251]	eta 0:21:03 lr 0.000736	time 2.4968 (2.2122)	loss 4.6304 (3.6826)	grad_norm 1.3136 (1.2762)	
[2022-01-20 21:11:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][690/1251]	eta 0:20:41 lr 0.000736	time 2.7326 (2.2129)	loss 4.1411 (3.6848)	grad_norm 1.2320 (1.2751)	
[2022-01-20 21:11:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][700/1251]	eta 0:20:18 lr 0.000736	time 1.9741 (2.2116)	loss 2.4682 (3.6832)	grad_norm 1.6777 (1.2745)	
[2022-01-20 21:12:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][710/1251]	eta 0:19:55 lr 0.000736	time 1.9628 (2.2105)	loss 3.9000 (3.6823)	grad_norm 1.4556 (1.2754)	
[2022-01-20 21:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][720/1251]	eta 0:19:32 lr 0.000736	time 2.1820 (2.2080)	loss 3.6110 (3.6820)	grad_norm 1.1800 (1.2747)	
[2022-01-20 21:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][730/1251]	eta 0:19:09 lr 0.000736	time 2.8715 (2.2072)	loss 3.7498 (3.6821)	grad_norm 1.0880 (1.2744)	
[2022-01-20 21:13:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][740/1251]	eta 0:18:47 lr 0.000736	time 1.8933 (2.2070)	loss 4.4053 (3.6819)	grad_norm 1.3733 (1.2752)	
[2022-01-20 21:13:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][750/1251]	eta 0:18:25 lr 0.000736	time 2.1617 (2.2059)	loss 4.0206 (3.6849)	grad_norm 1.4016 (1.2760)	
[2022-01-20 21:14:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][760/1251]	eta 0:18:03 lr 0.000736	time 2.3979 (2.2077)	loss 4.3098 (3.6802)	grad_norm 1.2049 (1.2767)	
[2022-01-20 21:14:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][770/1251]	eta 0:17:42 lr 0.000736	time 2.9493 (2.2085)	loss 3.9341 (3.6813)	grad_norm 1.1393 (1.2756)	
[2022-01-20 21:14:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][780/1251]	eta 0:17:20 lr 0.000736	time 2.0155 (2.2092)	loss 3.4804 (3.6806)	grad_norm 1.1131 (1.2761)	
[2022-01-20 21:15:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][790/1251]	eta 0:16:58 lr 0.000736	time 2.2424 (2.2096)	loss 4.5421 (3.6801)	grad_norm 1.0817 (1.2764)	
[2022-01-20 21:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][800/1251]	eta 0:16:37 lr 0.000736	time 2.4080 (2.2106)	loss 4.2220 (3.6753)	grad_norm 1.1297 (1.2762)	
[2022-01-20 21:15:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][810/1251]	eta 0:16:14 lr 0.000736	time 2.2597 (2.2099)	loss 3.2919 (3.6738)	grad_norm 1.1321 (1.2750)	
[2022-01-20 21:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][820/1251]	eta 0:15:50 lr 0.000736	time 1.5901 (2.2062)	loss 4.0602 (3.6749)	grad_norm 1.2879 (1.2751)	
[2022-01-20 21:16:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][830/1251]	eta 0:15:27 lr 0.000736	time 1.9720 (2.2042)	loss 3.8528 (3.6763)	grad_norm 1.3756 (1.2750)	
[2022-01-20 21:16:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][840/1251]	eta 0:15:05 lr 0.000736	time 2.5554 (2.2025)	loss 3.9678 (3.6817)	grad_norm 1.1718 (1.2755)	
[2022-01-20 21:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][850/1251]	eta 0:14:42 lr 0.000736	time 1.8475 (2.2014)	loss 4.2149 (3.6814)	grad_norm 1.3972 (1.2746)	
[2022-01-20 21:17:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][860/1251]	eta 0:14:20 lr 0.000736	time 1.9104 (2.2020)	loss 4.2599 (3.6813)	grad_norm 1.2091 (1.2748)	
[2022-01-20 21:18:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][870/1251]	eta 0:13:59 lr 0.000736	time 2.2716 (2.2034)	loss 2.7614 (3.6807)	grad_norm 1.0626 (1.2750)	
[2022-01-20 21:18:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][880/1251]	eta 0:13:37 lr 0.000736	time 2.2498 (2.2047)	loss 3.5964 (3.6810)	grad_norm 1.3945 (1.2750)	
[2022-01-20 21:18:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][890/1251]	eta 0:13:16 lr 0.000736	time 2.1470 (2.2062)	loss 2.6905 (3.6796)	grad_norm 1.2288 (1.2747)	
[2022-01-20 21:19:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][900/1251]	eta 0:12:55 lr 0.000736	time 3.0415 (2.2087)	loss 3.7725 (3.6781)	grad_norm 1.0900 (1.2742)	
[2022-01-20 21:19:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][910/1251]	eta 0:12:33 lr 0.000736	time 2.1958 (2.2108)	loss 2.6170 (3.6788)	grad_norm 1.3127 (1.2737)	
[2022-01-20 21:20:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][920/1251]	eta 0:12:11 lr 0.000736	time 2.1635 (2.2102)	loss 3.8912 (3.6780)	grad_norm 1.3373 (1.2733)	
[2022-01-20 21:20:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][930/1251]	eta 0:11:49 lr 0.000736	time 2.0016 (2.2088)	loss 3.9882 (3.6803)	grad_norm 1.1950 (1.2727)	
[2022-01-20 21:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][940/1251]	eta 0:11:26 lr 0.000735	time 1.9340 (2.2074)	loss 4.1674 (3.6806)	grad_norm 1.4383 (1.2737)	
[2022-01-20 21:21:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][950/1251]	eta 0:11:04 lr 0.000735	time 2.2825 (2.2067)	loss 4.0298 (3.6850)	grad_norm 1.4602 (1.2737)	
[2022-01-20 21:21:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][960/1251]	eta 0:10:41 lr 0.000735	time 2.2192 (2.2059)	loss 3.6504 (3.6866)	grad_norm 1.0780 (1.2729)	
[2022-01-20 21:21:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][970/1251]	eta 0:10:19 lr 0.000735	time 1.8070 (2.2044)	loss 3.9882 (3.6886)	grad_norm 1.2881 (1.2727)	
[2022-01-20 21:22:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][980/1251]	eta 0:09:57 lr 0.000735	time 2.5153 (2.2041)	loss 3.4059 (3.6898)	grad_norm 1.1279 (1.2729)	
[2022-01-20 21:22:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][990/1251]	eta 0:09:35 lr 0.000735	time 2.1819 (2.2047)	loss 4.1110 (3.6927)	grad_norm 1.1477 (1.2730)	
[2022-01-20 21:22:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1000/1251]	eta 0:09:13 lr 0.000735	time 2.4582 (2.2059)	loss 3.8312 (3.6926)	grad_norm 1.3901 (1.2726)	
[2022-01-20 21:23:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1010/1251]	eta 0:08:51 lr 0.000735	time 1.7924 (2.2050)	loss 3.9345 (3.6933)	grad_norm 1.1882 (1.2722)	
[2022-01-20 21:23:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1020/1251]	eta 0:08:29 lr 0.000735	time 2.7516 (2.2053)	loss 3.5499 (3.6936)	grad_norm 1.3995 (1.2729)	
[2022-01-20 21:23:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1030/1251]	eta 0:08:07 lr 0.000735	time 2.6751 (2.2050)	loss 3.2167 (3.6926)	grad_norm 1.2063 (1.2721)	
[2022-01-20 21:24:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1040/1251]	eta 0:07:45 lr 0.000735	time 3.0985 (2.2054)	loss 2.9776 (3.6939)	grad_norm 1.3457 (1.2725)	
[2022-01-20 21:24:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1050/1251]	eta 0:07:22 lr 0.000735	time 1.5711 (2.2033)	loss 4.8188 (3.6951)	grad_norm 1.4669 (1.2728)	
[2022-01-20 21:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1060/1251]	eta 0:07:00 lr 0.000735	time 2.0377 (2.2013)	loss 3.5499 (3.6938)	grad_norm 1.2024 (1.2728)	
[2022-01-20 21:25:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1070/1251]	eta 0:06:38 lr 0.000735	time 2.6331 (2.2007)	loss 4.0241 (3.6920)	grad_norm 1.1032 (1.2719)	
[2022-01-20 21:25:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1080/1251]	eta 0:06:16 lr 0.000735	time 2.4373 (2.1997)	loss 3.5649 (3.6911)	grad_norm 1.3281 (1.2713)	
[2022-01-20 21:26:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1090/1251]	eta 0:05:53 lr 0.000735	time 1.9140 (2.1984)	loss 4.0080 (3.6916)	grad_norm 1.2522 (1.2710)	
[2022-01-20 21:26:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1100/1251]	eta 0:05:31 lr 0.000735	time 1.9428 (2.1980)	loss 4.1246 (3.6927)	grad_norm 1.2372 (1.2701)	
[2022-01-20 21:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1110/1251]	eta 0:05:09 lr 0.000735	time 2.1496 (2.1979)	loss 3.9096 (3.6930)	grad_norm 1.2105 (1.2699)	
[2022-01-20 21:27:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1120/1251]	eta 0:04:48 lr 0.000735	time 2.5781 (2.2011)	loss 3.1265 (3.6923)	grad_norm 1.2237 (1.2690)	
[2022-01-20 21:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1130/1251]	eta 0:04:26 lr 0.000735	time 2.4607 (2.2031)	loss 4.3512 (3.6947)	grad_norm 1.3920 (1.2692)	
[2022-01-20 21:28:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1140/1251]	eta 0:04:04 lr 0.000735	time 1.5300 (2.2041)	loss 4.4400 (3.6939)	grad_norm 1.0667 (1.2691)	
[2022-01-20 21:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1150/1251]	eta 0:03:42 lr 0.000735	time 1.9954 (2.2026)	loss 3.5164 (3.6949)	grad_norm 1.5148 (1.2694)	
[2022-01-20 21:28:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1160/1251]	eta 0:03:20 lr 0.000735	time 1.8840 (2.2003)	loss 2.8800 (3.6972)	grad_norm 1.1031 (1.2695)	
[2022-01-20 21:29:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1170/1251]	eta 0:02:58 lr 0.000735	time 1.9106 (2.1995)	loss 4.2032 (3.6987)	grad_norm 1.3434 (1.2697)	
[2022-01-20 21:29:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1180/1251]	eta 0:02:36 lr 0.000735	time 1.9980 (2.1986)	loss 3.5408 (3.6984)	grad_norm 1.2711 (1.2707)	
[2022-01-20 21:29:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1190/1251]	eta 0:02:14 lr 0.000735	time 2.2478 (2.2002)	loss 3.9974 (3.6983)	grad_norm 1.2893 (1.2713)	
[2022-01-20 21:30:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1200/1251]	eta 0:01:52 lr 0.000735	time 1.8988 (2.2016)	loss 4.2147 (3.6989)	grad_norm 1.4107 (1.2711)	
[2022-01-20 21:30:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1210/1251]	eta 0:01:30 lr 0.000734	time 1.8688 (2.2020)	loss 3.4879 (3.6992)	grad_norm 1.0701 (1.2709)	
[2022-01-20 21:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1220/1251]	eta 0:01:08 lr 0.000734	time 1.4784 (2.2007)	loss 3.4458 (3.6975)	grad_norm 1.0841 (1.2705)	
[2022-01-20 21:31:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1230/1251]	eta 0:00:46 lr 0.000734	time 3.0354 (2.2002)	loss 3.9134 (3.6982)	grad_norm 1.2470 (1.2704)	
[2022-01-20 21:31:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1240/1251]	eta 0:00:24 lr 0.000734	time 1.5715 (2.1984)	loss 4.2689 (3.6985)	grad_norm 1.1933 (1.2705)	
[2022-01-20 21:31:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [103/300][1250/1251]	eta 0:00:02 lr 0.000734	time 1.1970 (2.1924)	loss 3.6612 (3.6984)	grad_norm 1.1618 (1.2698)	
[2022-01-20 21:31:48 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 103 training takes 0:45:43
[2022-01-20 21:32:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.314 (18.314)	Loss 1.0247 (1.0247)	Acc@1 75.977 (75.977)	Acc@5 92.676 (92.676)	
[2022-01-20 21:32:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.264 (3.404)	Loss 1.0253 (1.0854)	Acc@1 75.684 (74.414)	Acc@5 92.285 (92.214)	
[2022-01-20 21:32:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.949 (2.581)	Loss 1.2002 (1.0979)	Acc@1 72.070 (74.172)	Acc@5 90.430 (92.225)	
[2022-01-20 21:33:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.317 (2.302)	Loss 1.1341 (1.0978)	Acc@1 70.898 (73.913)	Acc@5 91.602 (92.232)	
[2022-01-20 21:33:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.776 (2.163)	Loss 1.1227 (1.1002)	Acc@1 73.633 (73.983)	Acc@5 91.797 (92.221)	
[2022-01-20 21:33:24 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.922 Acc@5 92.216
[2022-01-20 21:33:24 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.9%
[2022-01-20 21:33:24 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.98%
[2022-01-20 21:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][0/1251]	eta 7:28:22 lr 0.000734	time 21.5049 (21.5049)	loss 3.6833 (3.6833)	grad_norm 1.2427 (1.2427)	
[2022-01-20 21:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][10/1251]	eta 1:24:00 lr 0.000734	time 2.4209 (4.0613)	loss 2.9496 (3.5552)	grad_norm 1.1218 (1.2691)	
[2022-01-20 21:34:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][20/1251]	eta 1:09:28 lr 0.000734	time 2.0798 (3.3862)	loss 3.2290 (3.4376)	grad_norm 1.1198 (1.2727)	
[2022-01-20 21:34:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][30/1251]	eta 1:01:08 lr 0.000734	time 1.8924 (3.0048)	loss 3.0295 (3.5298)	grad_norm 1.3051 (1.2742)	
[2022-01-20 21:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][40/1251]	eta 0:57:47 lr 0.000734	time 3.7496 (2.8635)	loss 3.1588 (3.5697)	grad_norm 1.3262 (1.2877)	
[2022-01-20 21:35:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][50/1251]	eta 0:55:03 lr 0.000734	time 1.8025 (2.7510)	loss 3.9115 (3.5195)	grad_norm 1.0917 (1.2768)	
[2022-01-20 21:36:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][60/1251]	eta 0:52:20 lr 0.000734	time 1.8075 (2.6372)	loss 3.5417 (3.5750)	grad_norm 1.0748 (1.2653)	
[2022-01-20 21:36:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][70/1251]	eta 0:50:11 lr 0.000734	time 1.9581 (2.5498)	loss 3.1055 (3.5757)	grad_norm 1.3371 (1.2760)	
[2022-01-20 21:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][80/1251]	eta 0:48:42 lr 0.000734	time 2.5024 (2.4954)	loss 4.2794 (3.6065)	grad_norm 1.6352 (1.2825)	
[2022-01-20 21:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][90/1251]	eta 0:47:40 lr 0.000734	time 2.2070 (2.4639)	loss 4.1668 (3.6111)	grad_norm 1.3519 (1.2926)	
[2022-01-20 21:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][100/1251]	eta 0:46:51 lr 0.000734	time 1.6134 (2.4430)	loss 3.9835 (3.6314)	grad_norm 1.2275 (1.2950)	
[2022-01-20 21:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][110/1251]	eta 0:46:00 lr 0.000734	time 2.0099 (2.4194)	loss 3.0155 (3.6372)	grad_norm 1.3331 (1.2943)	
[2022-01-20 21:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][120/1251]	eta 0:45:08 lr 0.000734	time 1.8877 (2.3948)	loss 2.9642 (3.6362)	grad_norm 1.4341 (1.2908)	
[2022-01-20 21:38:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][130/1251]	eta 0:44:28 lr 0.000734	time 1.9857 (2.3805)	loss 4.4388 (3.6606)	grad_norm 1.2310 (1.2859)	
[2022-01-20 21:38:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][140/1251]	eta 0:43:50 lr 0.000734	time 3.1224 (2.3679)	loss 2.3953 (3.6548)	grad_norm 1.1745 (1.2840)	
[2022-01-20 21:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][150/1251]	eta 0:43:19 lr 0.000734	time 2.2948 (2.3610)	loss 3.0749 (3.6602)	grad_norm 1.1460 (1.2837)	
[2022-01-20 21:39:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][160/1251]	eta 0:42:49 lr 0.000734	time 1.6257 (2.3555)	loss 3.8334 (3.6790)	grad_norm 1.0258 (1.2803)	
[2022-01-20 21:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][170/1251]	eta 0:42:11 lr 0.000734	time 1.5254 (2.3422)	loss 4.4195 (3.6891)	grad_norm 1.5452 (1.2783)	
[2022-01-20 21:40:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][180/1251]	eta 0:41:35 lr 0.000734	time 2.8812 (2.3298)	loss 3.7023 (3.6878)	grad_norm 1.3696 (1.2796)	
[2022-01-20 21:40:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][190/1251]	eta 0:40:58 lr 0.000734	time 1.6416 (2.3171)	loss 4.0566 (3.6861)	grad_norm 1.3555 (1.2776)	
[2022-01-20 21:41:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][200/1251]	eta 0:40:17 lr 0.000734	time 1.9573 (2.3005)	loss 3.2120 (3.6917)	grad_norm 1.2382 (1.2757)	
[2022-01-20 21:41:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][210/1251]	eta 0:39:44 lr 0.000734	time 2.1134 (2.2905)	loss 3.2956 (3.6872)	grad_norm 1.2012 (1.2757)	
[2022-01-20 21:41:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][220/1251]	eta 0:39:15 lr 0.000734	time 1.9712 (2.2848)	loss 4.5751 (3.6834)	grad_norm 1.4011 (1.2764)	
[2022-01-20 21:42:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][230/1251]	eta 0:38:53 lr 0.000733	time 1.5525 (2.2854)	loss 4.4352 (3.6932)	grad_norm 1.5276 (1.2771)	
[2022-01-20 21:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][240/1251]	eta 0:38:38 lr 0.000733	time 2.5609 (2.2935)	loss 3.2400 (3.6865)	grad_norm 1.3187 (1.2802)	
[2022-01-20 21:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][250/1251]	eta 0:38:19 lr 0.000733	time 2.4902 (2.2976)	loss 3.5929 (3.6920)	grad_norm 1.1014 (1.2792)	
[2022-01-20 21:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][260/1251]	eta 0:37:53 lr 0.000733	time 1.5631 (2.2938)	loss 2.7954 (3.6866)	grad_norm 1.3257 (1.2793)	
[2022-01-20 21:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][270/1251]	eta 0:37:17 lr 0.000733	time 1.7840 (2.2811)	loss 4.4094 (3.6913)	grad_norm 1.1832 (1.2778)	
[2022-01-20 21:44:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][280/1251]	eta 0:36:45 lr 0.000733	time 2.0595 (2.2713)	loss 3.2253 (3.6949)	grad_norm 1.1798 (1.2745)	
[2022-01-20 21:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][290/1251]	eta 0:36:22 lr 0.000733	time 1.6971 (2.2712)	loss 3.9756 (3.7022)	grad_norm 1.1786 (1.2769)	
[2022-01-20 21:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][300/1251]	eta 0:35:54 lr 0.000733	time 1.9514 (2.2651)	loss 4.0374 (3.7001)	grad_norm 1.2082 (1.2755)	
[2022-01-20 21:45:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][310/1251]	eta 0:35:27 lr 0.000733	time 2.1711 (2.2609)	loss 4.6194 (3.7001)	grad_norm 1.3656 (1.2770)	
[2022-01-20 21:45:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][320/1251]	eta 0:35:00 lr 0.000733	time 1.9141 (2.2559)	loss 3.6420 (3.6904)	grad_norm 1.3132 (1.2774)	
[2022-01-20 21:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][330/1251]	eta 0:34:38 lr 0.000733	time 1.9492 (2.2572)	loss 4.2596 (3.6910)	grad_norm 1.2475 (1.2761)	
[2022-01-20 21:46:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][340/1251]	eta 0:34:17 lr 0.000733	time 2.0503 (2.2586)	loss 3.9656 (3.6887)	grad_norm 1.0795 (1.2741)	
[2022-01-20 21:46:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][350/1251]	eta 0:33:59 lr 0.000733	time 2.4727 (2.2635)	loss 2.9736 (3.6806)	grad_norm 1.3058 (1.2749)	
[2022-01-20 21:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][360/1251]	eta 0:33:37 lr 0.000733	time 2.1174 (2.2640)	loss 4.2706 (3.6762)	grad_norm 1.1533 (1.2739)	
[2022-01-20 21:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][370/1251]	eta 0:33:10 lr 0.000733	time 1.9411 (2.2597)	loss 4.1086 (3.6871)	grad_norm 1.4847 (1.2758)	
[2022-01-20 21:47:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][380/1251]	eta 0:32:44 lr 0.000733	time 2.0749 (2.2556)	loss 3.1980 (3.6969)	grad_norm 1.3320 (1.2758)	
[2022-01-20 21:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][390/1251]	eta 0:32:16 lr 0.000733	time 1.9404 (2.2494)	loss 4.0648 (3.7002)	grad_norm 1.4584 (1.2748)	
[2022-01-20 21:48:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][400/1251]	eta 0:31:53 lr 0.000733	time 1.9030 (2.2481)	loss 3.7547 (3.6962)	grad_norm 1.4840 (1.2765)	
[2022-01-20 21:48:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][410/1251]	eta 0:31:31 lr 0.000733	time 2.1458 (2.2486)	loss 4.0079 (3.6923)	grad_norm 1.3941 (1.2792)	
[2022-01-20 21:49:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][420/1251]	eta 0:31:06 lr 0.000733	time 1.9082 (2.2463)	loss 3.8502 (3.6884)	grad_norm 1.2566 (1.2788)	
[2022-01-20 21:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][430/1251]	eta 0:30:43 lr 0.000733	time 1.5586 (2.2456)	loss 4.0070 (3.6846)	grad_norm 1.1459 (1.2766)	
[2022-01-20 21:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][440/1251]	eta 0:30:20 lr 0.000733	time 2.1882 (2.2445)	loss 2.6443 (3.6813)	grad_norm 1.5535 (1.2764)	
[2022-01-20 21:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][450/1251]	eta 0:29:56 lr 0.000733	time 2.6432 (2.2431)	loss 3.8695 (3.6790)	grad_norm 1.0552 (1.2772)	
[2022-01-20 21:50:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][460/1251]	eta 0:29:31 lr 0.000733	time 1.5315 (2.2390)	loss 3.1453 (3.6775)	grad_norm 1.5130 (1.2779)	
[2022-01-20 21:50:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][470/1251]	eta 0:29:06 lr 0.000733	time 1.7937 (2.2357)	loss 3.6225 (3.6728)	grad_norm 1.2179 (1.2771)	
[2022-01-20 21:51:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][480/1251]	eta 0:28:42 lr 0.000733	time 2.1564 (2.2343)	loss 4.3017 (3.6793)	grad_norm 1.1751 (1.2763)	
[2022-01-20 21:51:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][490/1251]	eta 0:28:18 lr 0.000733	time 1.9034 (2.2325)	loss 4.2520 (3.6856)	grad_norm 1.3366 (1.2769)	
[2022-01-20 21:52:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][500/1251]	eta 0:27:56 lr 0.000732	time 1.5935 (2.2325)	loss 3.8671 (3.6913)	grad_norm 1.1275 (1.2772)	
[2022-01-20 21:52:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][510/1251]	eta 0:27:32 lr 0.000732	time 2.1900 (2.2297)	loss 4.4872 (3.6972)	grad_norm 1.4569 (1.2771)	
[2022-01-20 21:52:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][520/1251]	eta 0:27:09 lr 0.000732	time 2.8288 (2.2290)	loss 4.3758 (3.6987)	grad_norm 1.3169 (1.2797)	
[2022-01-20 21:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][530/1251]	eta 0:26:49 lr 0.000732	time 2.2284 (2.2322)	loss 3.3531 (3.7020)	grad_norm 1.2630 (1.2808)	
[2022-01-20 21:53:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][540/1251]	eta 0:26:30 lr 0.000732	time 1.7505 (2.2367)	loss 4.1231 (3.6990)	grad_norm 1.0900 (1.2808)	
[2022-01-20 21:53:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][550/1251]	eta 0:26:09 lr 0.000732	time 2.1602 (2.2383)	loss 4.2210 (3.7036)	grad_norm 1.1528 (1.2795)	
[2022-01-20 21:54:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][560/1251]	eta 0:25:46 lr 0.000732	time 2.8873 (2.2379)	loss 2.7023 (3.7031)	grad_norm 1.2563 (1.2793)	
[2022-01-20 21:54:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][570/1251]	eta 0:25:20 lr 0.000732	time 1.8806 (2.2334)	loss 4.1440 (3.7028)	grad_norm 1.2863 (1.2797)	
[2022-01-20 21:54:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][580/1251]	eta 0:24:55 lr 0.000732	time 1.9401 (2.2287)	loss 3.7313 (3.7006)	grad_norm 1.1741 (1.2803)	
[2022-01-20 21:55:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][590/1251]	eta 0:24:31 lr 0.000732	time 2.5237 (2.2258)	loss 3.8878 (3.6973)	grad_norm 1.3366 (1.2795)	
[2022-01-20 21:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][600/1251]	eta 0:24:09 lr 0.000732	time 2.3580 (2.2262)	loss 3.5060 (3.6942)	grad_norm 1.2504 (1.2791)	
[2022-01-20 21:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][610/1251]	eta 0:23:47 lr 0.000732	time 2.1315 (2.2262)	loss 3.7395 (3.7010)	grad_norm 1.3468 (1.2804)	
[2022-01-20 21:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][620/1251]	eta 0:23:24 lr 0.000732	time 1.5928 (2.2259)	loss 3.8823 (3.7029)	grad_norm 1.3231 (1.2810)	
[2022-01-20 21:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][630/1251]	eta 0:23:04 lr 0.000732	time 3.1298 (2.2292)	loss 2.9061 (3.7029)	grad_norm 1.2058 (1.2798)	
[2022-01-20 21:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][640/1251]	eta 0:22:43 lr 0.000732	time 2.8403 (2.2323)	loss 3.4160 (3.6977)	grad_norm 1.2271 (1.2794)	
[2022-01-20 21:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][650/1251]	eta 0:22:19 lr 0.000732	time 1.6867 (2.2293)	loss 2.8193 (3.6926)	grad_norm 1.2408 (1.2788)	
[2022-01-20 21:57:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][660/1251]	eta 0:21:55 lr 0.000732	time 1.7095 (2.2255)	loss 4.4027 (3.6882)	grad_norm 1.1288 (1.2789)	
[2022-01-20 21:58:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][670/1251]	eta 0:21:31 lr 0.000732	time 2.2323 (2.2225)	loss 2.9641 (3.6894)	grad_norm 1.2580 (1.2794)	
[2022-01-20 21:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][680/1251]	eta 0:21:09 lr 0.000732	time 2.1768 (2.2224)	loss 3.8936 (3.6929)	grad_norm 1.1545 (1.2782)	
[2022-01-20 21:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][690/1251]	eta 0:20:47 lr 0.000732	time 1.4544 (2.2232)	loss 3.7204 (3.6934)	grad_norm 1.2210 (1.2773)	
[2022-01-20 21:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][700/1251]	eta 0:20:25 lr 0.000732	time 2.0180 (2.2235)	loss 3.8034 (3.6912)	grad_norm 1.3539 (1.2773)	
[2022-01-20 21:59:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][710/1251]	eta 0:20:04 lr 0.000732	time 2.3585 (2.2268)	loss 3.5086 (3.6912)	grad_norm 1.2113 (1.2768)	
[2022-01-20 22:00:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][720/1251]	eta 0:19:41 lr 0.000732	time 1.9510 (2.2252)	loss 3.9281 (3.6891)	grad_norm 1.2783 (1.2764)	
[2022-01-20 22:00:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][730/1251]	eta 0:19:17 lr 0.000732	time 1.8931 (2.2217)	loss 3.5209 (3.6913)	grad_norm 1.7599 (1.2766)	
[2022-01-20 22:00:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][740/1251]	eta 0:18:53 lr 0.000732	time 1.9071 (2.2186)	loss 2.6517 (3.6904)	grad_norm 1.2535 (1.2760)	
[2022-01-20 22:01:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][750/1251]	eta 0:18:32 lr 0.000732	time 2.8187 (2.2196)	loss 3.4222 (3.6936)	grad_norm 1.1737 (1.2757)	
[2022-01-20 22:01:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][760/1251]	eta 0:18:09 lr 0.000732	time 2.4183 (2.2180)	loss 2.7217 (3.6918)	grad_norm 1.2496 (1.2774)	
[2022-01-20 22:01:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][770/1251]	eta 0:17:45 lr 0.000731	time 2.1248 (2.2160)	loss 4.0061 (3.6918)	grad_norm 1.1261 (1.2770)	
[2022-01-20 22:02:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][780/1251]	eta 0:17:23 lr 0.000731	time 2.2392 (2.2146)	loss 4.2015 (3.6938)	grad_norm 1.2724 (1.2762)	
[2022-01-20 22:02:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][790/1251]	eta 0:17:00 lr 0.000731	time 1.8003 (2.2144)	loss 3.7057 (3.6937)	grad_norm 1.2953 (1.2757)	
[2022-01-20 22:02:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][800/1251]	eta 0:16:38 lr 0.000731	time 2.1456 (2.2137)	loss 4.2162 (3.6965)	grad_norm 1.1480 (1.2756)	
[2022-01-20 22:03:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][810/1251]	eta 0:16:16 lr 0.000731	time 2.7592 (2.2135)	loss 4.0766 (3.6959)	grad_norm 1.2891 (1.2758)	
[2022-01-20 22:03:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][820/1251]	eta 0:15:53 lr 0.000731	time 2.1975 (2.2121)	loss 3.7893 (3.6963)	grad_norm 1.2322 (1.2759)	
[2022-01-20 22:04:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][830/1251]	eta 0:15:31 lr 0.000731	time 1.7080 (2.2132)	loss 4.4461 (3.6968)	grad_norm 1.3492 (1.2758)	
[2022-01-20 22:04:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][840/1251]	eta 0:15:09 lr 0.000731	time 1.7336 (2.2138)	loss 4.1761 (3.6974)	grad_norm 1.2858 (1.2768)	
[2022-01-20 22:04:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][850/1251]	eta 0:14:48 lr 0.000731	time 2.8824 (2.2163)	loss 3.9562 (3.6969)	grad_norm 1.1940 (1.2771)	
[2022-01-20 22:05:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][860/1251]	eta 0:14:26 lr 0.000731	time 2.2142 (2.2161)	loss 3.3573 (3.6947)	grad_norm 1.1183 (1.2765)	
[2022-01-20 22:05:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][870/1251]	eta 0:14:04 lr 0.000731	time 1.8653 (2.2169)	loss 3.6064 (3.6928)	grad_norm 1.3627 (1.2756)	
[2022-01-20 22:05:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][880/1251]	eta 0:13:41 lr 0.000731	time 1.7318 (2.2146)	loss 4.3571 (3.6945)	grad_norm 1.2989 (1.2752)	
[2022-01-20 22:06:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][890/1251]	eta 0:13:19 lr 0.000731	time 2.3128 (2.2139)	loss 4.0054 (3.6939)	grad_norm 1.1473 (1.2739)	
[2022-01-20 22:06:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][900/1251]	eta 0:12:56 lr 0.000731	time 1.7847 (2.2126)	loss 4.0093 (3.6942)	grad_norm 1.0910 (1.2732)	
[2022-01-20 22:07:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][910/1251]	eta 0:12:34 lr 0.000731	time 2.4877 (2.2130)	loss 4.3475 (3.6955)	grad_norm 1.3647 (1.2732)	
[2022-01-20 22:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][920/1251]	eta 0:12:11 lr 0.000731	time 2.2014 (2.2102)	loss 2.4706 (3.6934)	grad_norm 1.1137 (1.2727)	
[2022-01-20 22:07:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][930/1251]	eta 0:11:49 lr 0.000731	time 2.3714 (2.2089)	loss 2.9736 (3.6900)	grad_norm 1.3540 (1.2723)	
[2022-01-20 22:08:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][940/1251]	eta 0:11:26 lr 0.000731	time 2.2322 (2.2085)	loss 3.3396 (3.6880)	grad_norm 1.3195 (1.2726)	
[2022-01-20 22:08:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][950/1251]	eta 0:11:04 lr 0.000731	time 2.5305 (2.2084)	loss 2.9798 (3.6880)	grad_norm 1.1642 (1.2725)	
[2022-01-20 22:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][960/1251]	eta 0:10:42 lr 0.000731	time 2.1197 (2.2090)	loss 3.6714 (3.6875)	grad_norm 1.1592 (1.2717)	
[2022-01-20 22:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][970/1251]	eta 0:10:21 lr 0.000731	time 2.8407 (2.2106)	loss 3.1750 (3.6856)	grad_norm 1.4844 (1.2722)	
[2022-01-20 22:09:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][980/1251]	eta 0:09:58 lr 0.000731	time 1.9845 (2.2097)	loss 3.5768 (3.6856)	grad_norm 1.0535 (1.2727)	
[2022-01-20 22:09:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][990/1251]	eta 0:09:36 lr 0.000731	time 2.8865 (2.2099)	loss 4.5033 (3.6870)	grad_norm 1.5075 (1.2730)	
[2022-01-20 22:10:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1000/1251]	eta 0:09:14 lr 0.000731	time 2.3255 (2.2096)	loss 3.6850 (3.6877)	grad_norm 1.2983 (1.2727)	
[2022-01-20 22:10:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1010/1251]	eta 0:08:52 lr 0.000731	time 2.7598 (2.2098)	loss 3.1017 (3.6869)	grad_norm 1.2386 (1.2725)	
[2022-01-20 22:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1020/1251]	eta 0:08:30 lr 0.000731	time 1.8081 (2.2100)	loss 4.2304 (3.6848)	grad_norm 1.1516 (1.2722)	
[2022-01-20 22:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1030/1251]	eta 0:08:08 lr 0.000731	time 2.7451 (2.2100)	loss 4.4275 (3.6868)	grad_norm 1.1391 (1.2719)	
[2022-01-20 22:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1040/1251]	eta 0:07:46 lr 0.000731	time 1.9077 (2.2097)	loss 3.8714 (3.6900)	grad_norm 1.6493 (1.2721)	
[2022-01-20 22:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1050/1251]	eta 0:07:23 lr 0.000730	time 1.9361 (2.2074)	loss 4.0039 (3.6891)	grad_norm 1.1331 (1.2718)	
[2022-01-20 22:12:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1060/1251]	eta 0:07:01 lr 0.000730	time 1.8181 (2.2076)	loss 3.6567 (3.6902)	grad_norm 1.2904 (1.2714)	
[2022-01-20 22:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1070/1251]	eta 0:06:39 lr 0.000730	time 2.5082 (2.2075)	loss 3.9044 (3.6907)	grad_norm 1.4563 (1.2713)	
[2022-01-20 22:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1080/1251]	eta 0:06:17 lr 0.000730	time 2.2368 (2.2079)	loss 3.8960 (3.6899)	grad_norm 1.3823 (1.2711)	
[2022-01-20 22:13:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1090/1251]	eta 0:05:55 lr 0.000730	time 1.8879 (2.2082)	loss 3.1210 (3.6894)	grad_norm 1.3114 (1.2711)	
[2022-01-20 22:13:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1100/1251]	eta 0:05:33 lr 0.000730	time 1.8662 (2.2090)	loss 4.1238 (3.6886)	grad_norm 1.2912 (1.2706)	
[2022-01-20 22:14:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1110/1251]	eta 0:05:11 lr 0.000730	time 1.7584 (2.2080)	loss 3.8928 (3.6856)	grad_norm 1.1516 (1.2702)	
[2022-01-20 22:14:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1120/1251]	eta 0:04:49 lr 0.000730	time 1.9125 (2.2072)	loss 3.5931 (3.6859)	grad_norm 1.1166 (1.2696)	
[2022-01-20 22:14:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1130/1251]	eta 0:04:26 lr 0.000730	time 1.8868 (2.2061)	loss 3.1440 (3.6857)	grad_norm 1.2316 (1.2695)	
[2022-01-20 22:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1140/1251]	eta 0:04:05 lr 0.000730	time 1.9777 (2.2072)	loss 3.6398 (3.6866)	grad_norm 1.4325 (1.2690)	
[2022-01-20 22:15:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1150/1251]	eta 0:03:42 lr 0.000730	time 1.9778 (2.2060)	loss 3.8409 (3.6884)	grad_norm 1.0874 (1.2687)	
[2022-01-20 22:16:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1160/1251]	eta 0:03:20 lr 0.000730	time 1.8410 (2.2057)	loss 4.4269 (3.6871)	grad_norm 1.2462 (1.2688)	
[2022-01-20 22:16:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1170/1251]	eta 0:02:58 lr 0.000730	time 2.0936 (2.2058)	loss 3.9005 (3.6886)	grad_norm 1.3393 (1.2692)	
[2022-01-20 22:16:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1180/1251]	eta 0:02:36 lr 0.000730	time 2.1941 (2.2049)	loss 3.0928 (3.6876)	grad_norm 1.0974 (1.2694)	
[2022-01-20 22:17:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1190/1251]	eta 0:02:14 lr 0.000730	time 2.1798 (2.2040)	loss 3.6355 (3.6891)	grad_norm 1.2921 (1.2697)	
[2022-01-20 22:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1200/1251]	eta 0:01:52 lr 0.000730	time 2.1554 (2.2027)	loss 2.5207 (3.6887)	grad_norm 1.4386 (1.2703)	
[2022-01-20 22:17:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1210/1251]	eta 0:01:30 lr 0.000730	time 1.8475 (2.2027)	loss 4.4276 (3.6906)	grad_norm 1.3698 (1.2703)	
[2022-01-20 22:18:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1220/1251]	eta 0:01:08 lr 0.000730	time 2.3590 (2.2029)	loss 4.2654 (3.6913)	grad_norm 1.1604 (1.2701)	
[2022-01-20 22:18:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1230/1251]	eta 0:00:46 lr 0.000730	time 2.2151 (2.2027)	loss 3.7258 (3.6904)	grad_norm 1.1995 (1.2700)	
[2022-01-20 22:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1240/1251]	eta 0:00:24 lr 0.000730	time 1.2820 (2.2008)	loss 4.2278 (3.6899)	grad_norm 1.5330 (1.2707)	
[2022-01-20 22:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [104/300][1250/1251]	eta 0:00:02 lr 0.000730	time 1.1931 (2.1953)	loss 3.9246 (3.6887)	grad_norm 1.0848 (1.2699)	
[2022-01-20 22:19:11 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 104 training takes 0:45:46
[2022-01-20 22:19:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.589 (18.589)	Loss 1.0873 (1.0873)	Acc@1 74.414 (74.414)	Acc@5 93.457 (93.457)	
[2022-01-20 22:19:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.231 (3.330)	Loss 1.1863 (1.1285)	Acc@1 72.949 (72.994)	Acc@5 91.797 (92.374)	
[2022-01-20 22:20:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.212 (2.683)	Loss 1.1436 (1.1240)	Acc@1 74.805 (73.479)	Acc@5 91.211 (92.267)	
[2022-01-20 22:20:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.614 (2.335)	Loss 1.0768 (1.1211)	Acc@1 73.828 (73.551)	Acc@5 93.457 (92.269)	
[2022-01-20 22:20:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.760 (2.185)	Loss 1.2278 (1.1182)	Acc@1 71.582 (73.676)	Acc@5 90.039 (92.235)	
[2022-01-20 22:20:48 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 73.682 Acc@5 92.208
[2022-01-20 22:20:48 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 73.7%
[2022-01-20 22:20:48 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 73.98%
[2022-01-20 22:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][0/1251]	eta 7:24:11 lr 0.000730	time 21.3042 (21.3042)	loss 3.7641 (3.7641)	grad_norm 1.3067 (1.3067)	
[2022-01-20 22:21:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][10/1251]	eta 1:20:24 lr 0.000730	time 1.9451 (3.8880)	loss 3.9858 (3.9229)	grad_norm 1.2011 (1.1682)	
[2022-01-20 22:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][20/1251]	eta 1:05:09 lr 0.000730	time 1.8656 (3.1758)	loss 3.1726 (3.8608)	grad_norm 1.3397 (1.2063)	
[2022-01-20 22:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][30/1251]	eta 0:56:55 lr 0.000730	time 1.9338 (2.7975)	loss 3.4127 (3.7948)	grad_norm 1.4725 (1.2587)	
[2022-01-20 22:22:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][40/1251]	eta 0:55:13 lr 0.000730	time 6.6171 (2.7366)	loss 4.1994 (3.8076)	grad_norm 1.1401 (1.2613)	
[2022-01-20 22:23:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][50/1251]	eta 0:52:39 lr 0.000730	time 1.7787 (2.6308)	loss 3.7016 (3.7094)	grad_norm 1.2531 (1.2799)	
[2022-01-20 22:23:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][60/1251]	eta 0:50:28 lr 0.000730	time 1.9378 (2.5430)	loss 4.1290 (3.6422)	grad_norm 1.2297 (1.2795)	
[2022-01-20 22:23:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][70/1251]	eta 0:49:03 lr 0.000729	time 1.9842 (2.4923)	loss 4.0860 (3.6567)	grad_norm 1.1632 (1.2806)	
[2022-01-20 22:24:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][80/1251]	eta 0:48:17 lr 0.000729	time 3.8461 (2.4747)	loss 3.8271 (3.6221)	grad_norm 1.2935 (1.2810)	
[2022-01-20 22:24:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][90/1251]	eta 0:47:49 lr 0.000729	time 2.4250 (2.4712)	loss 3.5692 (3.6028)	grad_norm 1.2282 (1.2954)	
[2022-01-20 22:24:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][100/1251]	eta 0:46:47 lr 0.000729	time 1.8769 (2.4393)	loss 4.1496 (3.6111)	grad_norm 1.3982 (1.2984)	
[2022-01-20 22:25:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][110/1251]	eta 0:45:45 lr 0.000729	time 1.7281 (2.4058)	loss 3.3344 (3.6117)	grad_norm 1.4863 (1.2970)	
[2022-01-20 22:25:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][120/1251]	eta 0:45:04 lr 0.000729	time 2.6694 (2.3911)	loss 4.1811 (3.6095)	grad_norm 1.3349 (1.2987)	
[2022-01-20 22:25:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][130/1251]	eta 0:44:27 lr 0.000729	time 1.6849 (2.3794)	loss 3.4031 (3.6225)	grad_norm 1.6070 (1.2924)	
[2022-01-20 22:26:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][140/1251]	eta 0:43:42 lr 0.000729	time 1.9142 (2.3601)	loss 4.5174 (3.6247)	grad_norm 1.4453 (1.2902)	
[2022-01-20 22:26:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][150/1251]	eta 0:43:00 lr 0.000729	time 1.9602 (2.3436)	loss 4.3215 (3.6364)	grad_norm 1.0922 (1.2861)	
[2022-01-20 22:27:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][160/1251]	eta 0:42:27 lr 0.000729	time 2.7517 (2.3351)	loss 3.3200 (3.6261)	grad_norm 1.1627 (1.2836)	
[2022-01-20 22:27:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][170/1251]	eta 0:41:57 lr 0.000729	time 1.9088 (2.3286)	loss 3.9238 (3.6403)	grad_norm 1.4238 (1.2834)	
[2022-01-20 22:27:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][180/1251]	eta 0:41:20 lr 0.000729	time 1.5122 (2.3157)	loss 4.4668 (3.6477)	grad_norm 1.6162 (1.2819)	
[2022-01-20 22:28:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][190/1251]	eta 0:40:50 lr 0.000729	time 2.2099 (2.3094)	loss 3.5501 (3.6407)	grad_norm 1.2343 (1.2795)	
[2022-01-20 22:28:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][200/1251]	eta 0:40:24 lr 0.000729	time 3.1285 (2.3073)	loss 4.2022 (3.6323)	grad_norm 1.2389 (1.2780)	
[2022-01-20 22:28:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][210/1251]	eta 0:39:54 lr 0.000729	time 1.9589 (2.2999)	loss 3.6604 (3.6496)	grad_norm 1.1079 (1.2793)	
[2022-01-20 22:29:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][220/1251]	eta 0:39:26 lr 0.000729	time 1.9516 (2.2954)	loss 3.6242 (3.6499)	grad_norm 1.1164 (1.2786)	
[2022-01-20 22:29:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][230/1251]	eta 0:39:00 lr 0.000729	time 1.9138 (2.2921)	loss 4.0594 (3.6433)	grad_norm 1.4460 (1.2781)	
[2022-01-20 22:29:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][240/1251]	eta 0:38:34 lr 0.000729	time 2.7675 (2.2892)	loss 4.0559 (3.6565)	grad_norm 1.2060 (1.2756)	
[2022-01-20 22:30:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][250/1251]	eta 0:38:09 lr 0.000729	time 1.8343 (2.2874)	loss 3.7656 (3.6483)	grad_norm 1.2918 (1.2782)	
[2022-01-20 22:30:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][260/1251]	eta 0:37:42 lr 0.000729	time 1.5915 (2.2832)	loss 3.5044 (3.6369)	grad_norm 1.2541 (1.2763)	
[2022-01-20 22:31:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][270/1251]	eta 0:37:13 lr 0.000729	time 1.8378 (2.2772)	loss 3.8493 (3.6447)	grad_norm 1.1509 (1.2747)	
[2022-01-20 22:31:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][280/1251]	eta 0:36:47 lr 0.000729	time 2.2138 (2.2732)	loss 3.1105 (3.6440)	grad_norm 1.1523 (1.2742)	
[2022-01-20 22:31:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][290/1251]	eta 0:36:13 lr 0.000729	time 1.8447 (2.2617)	loss 2.6366 (3.6493)	grad_norm 1.1803 (1.2749)	
[2022-01-20 22:32:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][300/1251]	eta 0:35:44 lr 0.000729	time 1.9351 (2.2549)	loss 4.1968 (3.6569)	grad_norm 1.2296 (1.2770)	
[2022-01-20 22:32:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][310/1251]	eta 0:35:19 lr 0.000729	time 1.8881 (2.2521)	loss 2.8409 (3.6547)	grad_norm 1.4995 (1.2773)	
[2022-01-20 22:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][320/1251]	eta 0:34:51 lr 0.000729	time 1.9252 (2.2467)	loss 4.0375 (3.6523)	grad_norm 1.2601 (1.2784)	
[2022-01-20 22:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][330/1251]	eta 0:34:26 lr 0.000729	time 1.9263 (2.2436)	loss 4.2591 (3.6520)	grad_norm 1.1462 (1.2801)	
[2022-01-20 22:33:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][340/1251]	eta 0:34:06 lr 0.000728	time 2.8031 (2.2465)	loss 2.9421 (3.6520)	grad_norm 1.2381 (1.2787)	
[2022-01-20 22:33:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][350/1251]	eta 0:33:47 lr 0.000728	time 1.8308 (2.2501)	loss 3.6407 (3.6444)	grad_norm 1.3760 (1.2778)	
[2022-01-20 22:34:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][360/1251]	eta 0:33:24 lr 0.000728	time 1.9210 (2.2495)	loss 4.4829 (3.6406)	grad_norm 1.2765 (1.2767)	
[2022-01-20 22:34:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][370/1251]	eta 0:33:01 lr 0.000728	time 1.8564 (2.2488)	loss 4.2304 (3.6425)	grad_norm 1.1093 (1.2757)	
[2022-01-20 22:35:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][380/1251]	eta 0:32:36 lr 0.000728	time 2.1488 (2.2466)	loss 3.8433 (3.6422)	grad_norm 1.1428 (1.2757)	
[2022-01-20 22:35:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][390/1251]	eta 0:32:09 lr 0.000728	time 1.8963 (2.2411)	loss 3.6683 (3.6547)	grad_norm 1.2863 (1.2762)	
[2022-01-20 22:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][400/1251]	eta 0:31:41 lr 0.000728	time 1.6496 (2.2349)	loss 3.6183 (3.6500)	grad_norm 1.4106 (1.2760)	
[2022-01-20 22:36:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][410/1251]	eta 0:31:20 lr 0.000728	time 2.2740 (2.2355)	loss 4.3200 (3.6564)	grad_norm 1.4128 (1.2751)	
[2022-01-20 22:36:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][420/1251]	eta 0:30:58 lr 0.000728	time 2.6297 (2.2370)	loss 3.2509 (3.6547)	grad_norm 1.0426 (1.2745)	
[2022-01-20 22:36:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][430/1251]	eta 0:30:36 lr 0.000728	time 2.1214 (2.2374)	loss 2.4525 (3.6535)	grad_norm 1.3424 (1.2741)	
[2022-01-20 22:37:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][440/1251]	eta 0:30:15 lr 0.000728	time 2.2617 (2.2387)	loss 4.6174 (3.6596)	grad_norm 1.6540 (1.2750)	
[2022-01-20 22:37:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][450/1251]	eta 0:29:51 lr 0.000728	time 2.0931 (2.2371)	loss 4.1061 (3.6541)	grad_norm 1.1550 (1.2760)	
[2022-01-20 22:37:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][460/1251]	eta 0:29:26 lr 0.000728	time 1.6330 (2.2334)	loss 3.7964 (3.6519)	grad_norm 1.1995 (1.2780)	
[2022-01-20 22:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][470/1251]	eta 0:29:01 lr 0.000728	time 1.8766 (2.2300)	loss 4.2652 (3.6530)	grad_norm 1.1946 (1.2773)	
[2022-01-20 22:38:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][480/1251]	eta 0:28:41 lr 0.000728	time 3.3588 (2.2324)	loss 3.6416 (3.6574)	grad_norm 1.1096 (1.2753)	
[2022-01-20 22:39:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][490/1251]	eta 0:28:18 lr 0.000728	time 1.9286 (2.2322)	loss 3.0978 (3.6563)	grad_norm 1.1514 (1.2735)	
[2022-01-20 22:39:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][500/1251]	eta 0:27:54 lr 0.000728	time 1.5995 (2.2293)	loss 3.0194 (3.6578)	grad_norm 1.2798 (1.2747)	
[2022-01-20 22:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][510/1251]	eta 0:27:29 lr 0.000728	time 1.8604 (2.2261)	loss 3.0365 (3.6545)	grad_norm 1.2070 (1.2741)	
[2022-01-20 22:40:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][520/1251]	eta 0:27:07 lr 0.000728	time 1.9753 (2.2263)	loss 4.2576 (3.6591)	grad_norm 1.4000 (1.2765)	
[2022-01-20 22:40:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][530/1251]	eta 0:26:43 lr 0.000728	time 2.1637 (2.2241)	loss 2.8531 (3.6601)	grad_norm 1.3298 (1.2753)	
[2022-01-20 22:40:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][540/1251]	eta 0:26:21 lr 0.000728	time 2.7383 (2.2239)	loss 2.8193 (3.6583)	grad_norm 1.4405 (1.2772)	
[2022-01-20 22:41:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][550/1251]	eta 0:25:59 lr 0.000728	time 2.8665 (2.2242)	loss 4.0643 (3.6596)	grad_norm 2.0701 (1.2785)	
[2022-01-20 22:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][560/1251]	eta 0:25:35 lr 0.000728	time 1.7169 (2.2215)	loss 4.3698 (3.6593)	grad_norm 1.1730 (1.2776)	
[2022-01-20 22:41:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][570/1251]	eta 0:25:11 lr 0.000728	time 2.1541 (2.2192)	loss 3.1613 (3.6614)	grad_norm 1.3185 (1.2767)	
[2022-01-20 22:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][580/1251]	eta 0:24:49 lr 0.000728	time 3.4866 (2.2197)	loss 3.8000 (3.6605)	grad_norm 1.0655 (1.2774)	
[2022-01-20 22:42:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][590/1251]	eta 0:24:26 lr 0.000728	time 2.3730 (2.2183)	loss 4.1116 (3.6572)	grad_norm 1.1619 (1.2777)	
[2022-01-20 22:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][600/1251]	eta 0:24:03 lr 0.000728	time 1.4740 (2.2175)	loss 3.6908 (3.6566)	grad_norm 1.3482 (1.2801)	
[2022-01-20 22:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][610/1251]	eta 0:23:41 lr 0.000727	time 2.5655 (2.2173)	loss 3.4964 (3.6578)	grad_norm 1.4393 (1.2819)	
[2022-01-20 22:43:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][620/1251]	eta 0:23:22 lr 0.000727	time 3.6435 (2.2231)	loss 3.7667 (3.6567)	grad_norm 1.4465 (1.2815)	
[2022-01-20 22:44:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][630/1251]	eta 0:23:00 lr 0.000727	time 2.2879 (2.2235)	loss 4.6523 (3.6594)	grad_norm 1.4893 (1.2826)	
[2022-01-20 22:44:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][640/1251]	eta 0:22:37 lr 0.000727	time 1.5504 (2.2211)	loss 3.1870 (3.6576)	grad_norm 1.0886 (1.2824)	
[2022-01-20 22:44:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][650/1251]	eta 0:22:12 lr 0.000727	time 1.8502 (2.2175)	loss 4.4008 (3.6588)	grad_norm 1.1209 (1.2825)	
[2022-01-20 22:45:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][660/1251]	eta 0:21:50 lr 0.000727	time 2.5131 (2.2167)	loss 4.0749 (3.6613)	grad_norm 1.1215 (1.2819)	
[2022-01-20 22:45:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][670/1251]	eta 0:21:26 lr 0.000727	time 1.9475 (2.2139)	loss 4.3251 (3.6613)	grad_norm 1.2965 (1.2821)	
[2022-01-20 22:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][680/1251]	eta 0:21:05 lr 0.000727	time 2.4805 (2.2159)	loss 3.5642 (3.6627)	grad_norm 1.1899 (1.2821)	
[2022-01-20 22:46:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][690/1251]	eta 0:20:42 lr 0.000727	time 1.5852 (2.2157)	loss 4.3176 (3.6640)	grad_norm 1.2235 (1.2812)	
[2022-01-20 22:46:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][700/1251]	eta 0:20:22 lr 0.000727	time 3.0575 (2.2184)	loss 4.2129 (3.6635)	grad_norm 1.4400 (1.2809)	
[2022-01-20 22:47:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][710/1251]	eta 0:19:59 lr 0.000727	time 2.0730 (2.2178)	loss 3.8711 (3.6624)	grad_norm 1.1527 (1.2813)	
[2022-01-20 22:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][720/1251]	eta 0:19:36 lr 0.000727	time 1.8378 (2.2163)	loss 4.2084 (3.6651)	grad_norm 1.6259 (1.2817)	
[2022-01-20 22:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][730/1251]	eta 0:19:12 lr 0.000727	time 1.8864 (2.2130)	loss 2.9925 (3.6699)	grad_norm 1.4149 (1.2822)	
[2022-01-20 22:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][740/1251]	eta 0:18:50 lr 0.000727	time 2.5405 (2.2119)	loss 3.8847 (3.6725)	grad_norm 1.3285 (1.2824)	
[2022-01-20 22:48:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][750/1251]	eta 0:18:28 lr 0.000727	time 1.8398 (2.2132)	loss 4.4251 (3.6756)	grad_norm 1.1402 (1.2828)	
[2022-01-20 22:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][760/1251]	eta 0:18:07 lr 0.000727	time 1.8673 (2.2144)	loss 3.9355 (3.6749)	grad_norm 1.4999 (1.2831)	
[2022-01-20 22:49:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][770/1251]	eta 0:17:45 lr 0.000727	time 1.8852 (2.2151)	loss 2.5528 (3.6735)	grad_norm 1.4589 (1.2836)	
[2022-01-20 22:49:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][780/1251]	eta 0:17:23 lr 0.000727	time 2.2327 (2.2158)	loss 3.7718 (3.6712)	grad_norm 1.3830 (1.2842)	
[2022-01-20 22:50:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][790/1251]	eta 0:17:01 lr 0.000727	time 1.5674 (2.2150)	loss 3.0761 (3.6677)	grad_norm 1.1779 (1.2838)	
[2022-01-20 22:50:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][800/1251]	eta 0:16:37 lr 0.000727	time 2.0869 (2.2127)	loss 4.1464 (3.6721)	grad_norm 1.2884 (1.2835)	
[2022-01-20 22:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][810/1251]	eta 0:16:14 lr 0.000727	time 1.9631 (2.2101)	loss 2.8081 (3.6732)	grad_norm 1.4402 (1.2840)	
[2022-01-20 22:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][820/1251]	eta 0:15:51 lr 0.000727	time 1.8756 (2.2084)	loss 3.8400 (3.6755)	grad_norm 1.1486 (1.2832)	
[2022-01-20 22:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][830/1251]	eta 0:15:29 lr 0.000727	time 1.7656 (2.2074)	loss 4.4774 (3.6770)	grad_norm 1.1401 (1.2821)	
[2022-01-20 22:51:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][840/1251]	eta 0:15:07 lr 0.000727	time 2.2658 (2.2079)	loss 3.6650 (3.6757)	grad_norm 1.3217 (1.2813)	
[2022-01-20 22:52:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][850/1251]	eta 0:14:45 lr 0.000727	time 2.5378 (2.2085)	loss 2.8443 (3.6745)	grad_norm 1.1297 (1.2812)	
[2022-01-20 22:52:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][860/1251]	eta 0:14:23 lr 0.000727	time 1.8098 (2.2079)	loss 4.1233 (3.6765)	grad_norm 1.2379 (1.2813)	
[2022-01-20 22:52:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][870/1251]	eta 0:14:00 lr 0.000727	time 1.4976 (2.2066)	loss 3.6488 (3.6750)	grad_norm 1.3406 (1.2810)	
[2022-01-20 22:53:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][880/1251]	eta 0:13:38 lr 0.000726	time 2.3709 (2.2070)	loss 3.7417 (3.6766)	grad_norm 1.2519 (1.2812)	
[2022-01-20 22:53:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][890/1251]	eta 0:13:16 lr 0.000726	time 2.5342 (2.2066)	loss 4.2668 (3.6808)	grad_norm 1.3944 (1.2811)	
[2022-01-20 22:53:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][900/1251]	eta 0:12:54 lr 0.000726	time 2.0843 (2.2062)	loss 3.4970 (3.6768)	grad_norm 1.3221 (1.2813)	
[2022-01-20 22:54:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][910/1251]	eta 0:12:33 lr 0.000726	time 1.9336 (2.2082)	loss 4.6476 (3.6789)	grad_norm 1.2716 (1.2803)	
[2022-01-20 22:54:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][920/1251]	eta 0:12:11 lr 0.000726	time 2.9905 (2.2089)	loss 3.2572 (3.6814)	grad_norm 1.2116 (1.2798)	
[2022-01-20 22:55:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][930/1251]	eta 0:11:48 lr 0.000726	time 1.9075 (2.2076)	loss 3.4349 (3.6801)	grad_norm 1.4827 (1.2804)	
[2022-01-20 22:55:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][940/1251]	eta 0:11:26 lr 0.000726	time 2.3333 (2.2068)	loss 4.2850 (3.6783)	grad_norm 1.4364 (1.2811)	
[2022-01-20 22:55:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][950/1251]	eta 0:11:03 lr 0.000726	time 1.7648 (2.2060)	loss 3.9731 (3.6816)	grad_norm 1.2942 (1.2808)	
[2022-01-20 22:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][960/1251]	eta 0:10:41 lr 0.000726	time 2.5700 (2.2054)	loss 4.1960 (3.6820)	grad_norm 1.1781 (1.2805)	
[2022-01-20 22:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][970/1251]	eta 0:10:19 lr 0.000726	time 1.8217 (2.2041)	loss 3.6464 (3.6780)	grad_norm 1.1683 (1.2795)	
[2022-01-20 22:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][980/1251]	eta 0:09:57 lr 0.000726	time 2.0384 (2.2036)	loss 3.7117 (3.6771)	grad_norm 1.1925 (1.2793)	
[2022-01-20 22:57:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][990/1251]	eta 0:09:35 lr 0.000726	time 2.1956 (2.2043)	loss 4.3834 (3.6778)	grad_norm 1.3017 (1.2790)	
[2022-01-20 22:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1000/1251]	eta 0:09:13 lr 0.000726	time 2.7252 (2.2038)	loss 3.8752 (3.6781)	grad_norm 1.0317 (1.2790)	
[2022-01-20 22:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1010/1251]	eta 0:08:50 lr 0.000726	time 2.0396 (2.2022)	loss 3.5997 (3.6774)	grad_norm 1.1639 (1.2785)	
[2022-01-20 22:58:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1020/1251]	eta 0:08:28 lr 0.000726	time 1.6392 (2.2014)	loss 4.1015 (3.6782)	grad_norm 1.1655 (1.2780)	
[2022-01-20 22:58:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1030/1251]	eta 0:08:06 lr 0.000726	time 2.6441 (2.2008)	loss 3.5453 (3.6784)	grad_norm 1.3637 (1.2777)	
[2022-01-20 22:58:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1040/1251]	eta 0:07:44 lr 0.000726	time 2.5659 (2.2008)	loss 3.9477 (3.6787)	grad_norm 1.2707 (1.2780)	
[2022-01-20 22:59:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1050/1251]	eta 0:07:22 lr 0.000726	time 1.5593 (2.1998)	loss 4.2171 (3.6811)	grad_norm 1.1407 (1.2775)	
[2022-01-20 22:59:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1060/1251]	eta 0:07:00 lr 0.000726	time 1.8985 (2.1996)	loss 4.1198 (3.6803)	grad_norm 1.3164 (1.2771)	
[2022-01-20 23:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1070/1251]	eta 0:06:38 lr 0.000726	time 2.3754 (2.2013)	loss 3.2549 (3.6822)	grad_norm 1.3877 (1.2761)	
[2022-01-20 23:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1080/1251]	eta 0:06:16 lr 0.000726	time 1.5126 (2.2004)	loss 4.1806 (3.6816)	grad_norm 1.3984 (1.2759)	
[2022-01-20 23:00:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1090/1251]	eta 0:05:54 lr 0.000726	time 1.7275 (2.1994)	loss 4.0943 (3.6832)	grad_norm 1.4824 (1.2760)	
[2022-01-20 23:01:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1100/1251]	eta 0:05:32 lr 0.000726	time 2.3899 (2.1998)	loss 3.0239 (3.6828)	grad_norm 1.5129 (1.2766)	
[2022-01-20 23:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1110/1251]	eta 0:05:10 lr 0.000726	time 2.7590 (2.2010)	loss 2.8441 (3.6845)	grad_norm 1.3996 (1.2772)	
[2022-01-20 23:01:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1120/1251]	eta 0:04:48 lr 0.000726	time 1.8603 (2.2025)	loss 4.4960 (3.6849)	grad_norm 1.3831 (1.2771)	
[2022-01-20 23:02:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1130/1251]	eta 0:04:26 lr 0.000726	time 1.8126 (2.2018)	loss 3.9699 (3.6839)	grad_norm 1.1282 (1.2770)	
[2022-01-20 23:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1140/1251]	eta 0:04:04 lr 0.000726	time 1.8781 (2.2012)	loss 3.9401 (3.6859)	grad_norm 1.2738 (1.2769)	
[2022-01-20 23:03:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1150/1251]	eta 0:03:42 lr 0.000725	time 2.0222 (2.2002)	loss 4.0793 (3.6885)	grad_norm 1.2816 (1.2769)	
[2022-01-20 23:03:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1160/1251]	eta 0:03:20 lr 0.000725	time 2.2724 (2.2003)	loss 3.9970 (3.6890)	grad_norm 1.5649 (1.2769)	
[2022-01-20 23:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1170/1251]	eta 0:02:58 lr 0.000725	time 1.9721 (2.1996)	loss 4.2047 (3.6914)	grad_norm 1.2889 (1.2771)	
[2022-01-20 23:04:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1180/1251]	eta 0:02:36 lr 0.000725	time 2.2488 (2.2009)	loss 4.2423 (3.6911)	grad_norm 1.4336 (1.2775)	
[2022-01-20 23:04:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1190/1251]	eta 0:02:14 lr 0.000725	time 2.2588 (2.2004)	loss 3.8112 (3.6910)	grad_norm 1.6838 (1.2781)	
[2022-01-20 23:04:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1200/1251]	eta 0:01:52 lr 0.000725	time 1.9311 (2.2000)	loss 4.1108 (3.6921)	grad_norm 1.2951 (1.2788)	
[2022-01-20 23:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1210/1251]	eta 0:01:30 lr 0.000725	time 2.1729 (2.1981)	loss 3.2077 (3.6951)	grad_norm 1.0486 (1.2785)	
[2022-01-20 23:05:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1220/1251]	eta 0:01:08 lr 0.000725	time 1.8997 (2.1966)	loss 4.4227 (3.6927)	grad_norm 1.0720 (1.2780)	
[2022-01-20 23:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1230/1251]	eta 0:00:46 lr 0.000725	time 2.1695 (2.1959)	loss 3.7611 (3.6939)	grad_norm 1.0984 (1.2777)	
[2022-01-20 23:06:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1240/1251]	eta 0:00:24 lr 0.000725	time 1.5357 (2.1961)	loss 3.6028 (3.6949)	grad_norm 1.3215 (1.2780)	
[2022-01-20 23:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [105/300][1250/1251]	eta 0:00:02 lr 0.000725	time 1.1615 (2.1905)	loss 3.1865 (3.6918)	grad_norm 1.3545 (1.2788)	
[2022-01-20 23:06:28 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 105 training takes 0:45:40
[2022-01-20 23:06:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.344 (18.344)	Loss 1.0316 (1.0316)	Acc@1 75.195 (75.195)	Acc@5 93.359 (93.359)	
[2022-01-20 23:07:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.967 (3.542)	Loss 1.1388 (1.1072)	Acc@1 72.754 (74.112)	Acc@5 91.504 (92.516)	
[2022-01-20 23:07:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.661 (2.724)	Loss 1.1105 (1.1099)	Acc@1 75.488 (74.126)	Acc@5 92.090 (92.332)	
[2022-01-20 23:07:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.298 (2.236)	Loss 1.0345 (1.1046)	Acc@1 75.586 (74.159)	Acc@5 92.188 (92.329)	
[2022-01-20 23:07:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.973 (2.195)	Loss 1.1810 (1.1070)	Acc@1 72.070 (74.166)	Acc@5 90.723 (92.288)	
[2022-01-20 23:08:07 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.228 Acc@5 92.234
[2022-01-20 23:08:07 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.2%
[2022-01-20 23:08:07 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.23%
[2022-01-20 23:08:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][0/1251]	eta 7:39:32 lr 0.000725	time 22.0405 (22.0405)	loss 3.8532 (3.8532)	grad_norm 1.3487 (1.3487)	
[2022-01-20 23:08:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][10/1251]	eta 1:23:38 lr 0.000725	time 1.9970 (4.0437)	loss 3.3312 (3.6121)	grad_norm 1.5003 (1.2738)	
[2022-01-20 23:09:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][20/1251]	eta 1:06:05 lr 0.000725	time 1.9157 (3.2214)	loss 3.9418 (3.6103)	grad_norm 1.1448 (1.2275)	
[2022-01-20 23:09:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][30/1251]	eta 0:58:12 lr 0.000725	time 1.6100 (2.8603)	loss 3.7019 (3.6432)	grad_norm 1.3352 (1.2198)	
[2022-01-20 23:09:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][40/1251]	eta 0:55:06 lr 0.000725	time 4.1768 (2.7306)	loss 4.6931 (3.6743)	grad_norm 1.1790 (1.2308)	
[2022-01-20 23:10:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][50/1251]	eta 0:52:44 lr 0.000725	time 1.7082 (2.6349)	loss 4.3336 (3.6598)	grad_norm 1.2618 (1.2425)	
[2022-01-20 23:10:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][60/1251]	eta 0:52:08 lr 0.000725	time 2.3057 (2.6268)	loss 3.7939 (3.6989)	grad_norm 1.2219 (1.2392)	
[2022-01-20 23:11:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][70/1251]	eta 0:50:47 lr 0.000725	time 1.8490 (2.5806)	loss 3.1954 (3.6845)	grad_norm 1.2233 (1.2514)	
[2022-01-20 23:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][80/1251]	eta 0:49:45 lr 0.000725	time 2.6288 (2.5496)	loss 3.8020 (3.6237)	grad_norm 1.2859 (1.2517)	
[2022-01-20 23:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][90/1251]	eta 0:48:19 lr 0.000725	time 1.9385 (2.4973)	loss 4.0527 (3.6186)	grad_norm 1.1450 (1.2570)	
[2022-01-20 23:12:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][100/1251]	eta 0:46:41 lr 0.000725	time 2.2930 (2.4340)	loss 3.5294 (3.6251)	grad_norm 1.6445 (1.2666)	
[2022-01-20 23:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][110/1251]	eta 0:45:50 lr 0.000725	time 2.2455 (2.4109)	loss 3.9111 (3.6126)	grad_norm 1.1349 (1.2601)	
[2022-01-20 23:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][120/1251]	eta 0:45:09 lr 0.000725	time 2.3697 (2.3958)	loss 3.0591 (3.6167)	grad_norm 1.6650 (1.2649)	
[2022-01-20 23:13:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][130/1251]	eta 0:44:26 lr 0.000725	time 2.1110 (2.3788)	loss 3.7947 (3.6138)	grad_norm 1.1692 (1.2638)	
[2022-01-20 23:13:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][140/1251]	eta 0:44:06 lr 0.000725	time 4.0493 (2.3819)	loss 3.8830 (3.6005)	grad_norm 1.6491 (1.2661)	
[2022-01-20 23:14:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][150/1251]	eta 0:43:43 lr 0.000725	time 1.6907 (2.3829)	loss 3.4675 (3.5786)	grad_norm 1.4679 (1.2666)	
[2022-01-20 23:14:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][160/1251]	eta 0:43:05 lr 0.000725	time 1.9188 (2.3696)	loss 4.1089 (3.5987)	grad_norm 1.5502 (1.2704)	
[2022-01-20 23:14:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][170/1251]	eta 0:42:27 lr 0.000724	time 1.9498 (2.3562)	loss 3.7656 (3.6132)	grad_norm 1.1712 (1.2677)	
[2022-01-20 23:15:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][180/1251]	eta 0:41:39 lr 0.000724	time 2.1046 (2.3339)	loss 4.1648 (3.6111)	grad_norm 1.4618 (1.2675)	
[2022-01-20 23:15:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][190/1251]	eta 0:41:07 lr 0.000724	time 1.9398 (2.3259)	loss 4.0356 (3.6259)	grad_norm 1.2256 (1.2678)	
[2022-01-20 23:15:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][200/1251]	eta 0:40:37 lr 0.000724	time 2.0585 (2.3193)	loss 3.9680 (3.6269)	grad_norm 1.2381 (1.2733)	
[2022-01-20 23:16:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][210/1251]	eta 0:40:05 lr 0.000724	time 2.2504 (2.3108)	loss 3.2755 (3.6365)	grad_norm 1.3977 (1.2770)	
[2022-01-20 23:16:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][220/1251]	eta 0:39:28 lr 0.000724	time 1.6774 (2.2970)	loss 2.9693 (3.6352)	grad_norm 1.1096 (1.2791)	
[2022-01-20 23:16:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][230/1251]	eta 0:39:03 lr 0.000724	time 2.2790 (2.2952)	loss 3.9261 (3.6416)	grad_norm 1.1242 (1.2763)	
[2022-01-20 23:17:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][240/1251]	eta 0:38:40 lr 0.000724	time 2.3513 (2.2950)	loss 3.7748 (3.6537)	grad_norm 1.1976 (1.2726)	
[2022-01-20 23:17:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][250/1251]	eta 0:38:17 lr 0.000724	time 2.6177 (2.2948)	loss 3.5256 (3.6582)	grad_norm 1.2730 (1.2727)	
[2022-01-20 23:18:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][260/1251]	eta 0:37:49 lr 0.000724	time 1.8868 (2.2904)	loss 3.8202 (3.6672)	grad_norm 1.2197 (1.2751)	
[2022-01-20 23:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][270/1251]	eta 0:37:24 lr 0.000724	time 2.5502 (2.2882)	loss 3.8849 (3.6657)	grad_norm 1.1389 (1.2732)	
[2022-01-20 23:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][280/1251]	eta 0:36:57 lr 0.000724	time 2.9260 (2.2838)	loss 4.3334 (3.6703)	grad_norm 1.4015 (1.2718)	
[2022-01-20 23:19:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][290/1251]	eta 0:36:22 lr 0.000724	time 2.1075 (2.2716)	loss 3.9867 (3.6687)	grad_norm 1.7712 (1.2758)	
[2022-01-20 23:19:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][300/1251]	eta 0:35:53 lr 0.000724	time 1.8564 (2.2649)	loss 3.7470 (3.6668)	grad_norm 1.1757 (1.2741)	
[2022-01-20 23:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][310/1251]	eta 0:35:28 lr 0.000724	time 2.1465 (2.2620)	loss 4.0713 (3.6684)	grad_norm 1.4011 (1.2723)	
[2022-01-20 23:20:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][320/1251]	eta 0:35:07 lr 0.000724	time 3.0589 (2.2639)	loss 3.7602 (3.6764)	grad_norm 1.1772 (1.2720)	
[2022-01-20 23:20:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][330/1251]	eta 0:34:42 lr 0.000724	time 1.9546 (2.2616)	loss 3.9137 (3.6782)	grad_norm 1.2818 (1.2702)	
[2022-01-20 23:20:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][340/1251]	eta 0:34:21 lr 0.000724	time 2.1650 (2.2634)	loss 3.8805 (3.6819)	grad_norm 1.2062 (1.2679)	
[2022-01-20 23:21:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][350/1251]	eta 0:34:01 lr 0.000724	time 2.1933 (2.2653)	loss 3.9067 (3.6807)	grad_norm 1.1482 (1.2671)	
[2022-01-20 23:21:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][360/1251]	eta 0:33:35 lr 0.000724	time 2.2541 (2.2619)	loss 4.0478 (3.6828)	grad_norm 1.0689 (1.2706)	
[2022-01-20 23:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][370/1251]	eta 0:33:03 lr 0.000724	time 1.6463 (2.2511)	loss 4.2623 (3.6850)	grad_norm 1.4451 (1.2725)	
[2022-01-20 23:22:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][380/1251]	eta 0:32:34 lr 0.000724	time 2.1793 (2.2440)	loss 2.8198 (3.6850)	grad_norm 1.3990 (1.2759)	
[2022-01-20 23:22:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][390/1251]	eta 0:32:09 lr 0.000724	time 2.1322 (2.2411)	loss 3.6433 (3.6823)	grad_norm 1.2096 (1.2750)	
[2022-01-20 23:23:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][400/1251]	eta 0:31:46 lr 0.000724	time 2.3244 (2.2399)	loss 3.5028 (3.6847)	grad_norm 1.2569 (1.2750)	
[2022-01-20 23:23:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][410/1251]	eta 0:31:21 lr 0.000724	time 1.7585 (2.2371)	loss 3.5059 (3.6777)	grad_norm 1.5097 (1.2758)	
[2022-01-20 23:23:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][420/1251]	eta 0:31:00 lr 0.000724	time 2.6201 (2.2391)	loss 3.8223 (3.6808)	grad_norm 1.1778 (1.2745)	
[2022-01-20 23:24:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][430/1251]	eta 0:30:37 lr 0.000723	time 2.1965 (2.2387)	loss 3.5325 (3.6790)	grad_norm 1.5427 (1.2751)	
[2022-01-20 23:24:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][440/1251]	eta 0:30:18 lr 0.000723	time 2.8091 (2.2417)	loss 4.0221 (3.6761)	grad_norm 1.4682 (1.2753)	
[2022-01-20 23:24:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][450/1251]	eta 0:29:57 lr 0.000723	time 2.4616 (2.2446)	loss 3.8392 (3.6841)	grad_norm 1.1728 (1.2757)	
[2022-01-20 23:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][460/1251]	eta 0:29:34 lr 0.000723	time 1.9579 (2.2434)	loss 4.1727 (3.6883)	grad_norm 1.3117 (1.2763)	
[2022-01-20 23:25:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][470/1251]	eta 0:29:08 lr 0.000723	time 1.9276 (2.2394)	loss 3.0976 (3.6824)	grad_norm 1.3269 (1.2768)	
[2022-01-20 23:26:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][480/1251]	eta 0:28:43 lr 0.000723	time 2.0016 (2.2348)	loss 3.8990 (3.6844)	grad_norm 1.2629 (1.2757)	
[2022-01-20 23:26:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][490/1251]	eta 0:28:21 lr 0.000723	time 2.0086 (2.2357)	loss 4.2499 (3.6876)	grad_norm 1.1936 (1.2759)	
[2022-01-20 23:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][500/1251]	eta 0:27:59 lr 0.000723	time 2.4578 (2.2369)	loss 4.1112 (3.6965)	grad_norm 1.2932 (1.2786)	
[2022-01-20 23:27:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][510/1251]	eta 0:27:36 lr 0.000723	time 1.9800 (2.2361)	loss 4.2436 (3.7037)	grad_norm 1.2588 (1.2781)	
[2022-01-20 23:27:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][520/1251]	eta 0:27:14 lr 0.000723	time 2.7672 (2.2364)	loss 3.3670 (3.7009)	grad_norm 1.3256 (1.2782)	
[2022-01-20 23:27:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][530/1251]	eta 0:26:50 lr 0.000723	time 1.6240 (2.2339)	loss 4.1766 (3.7024)	grad_norm 1.2493 (1.2773)	
[2022-01-20 23:28:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][540/1251]	eta 0:26:26 lr 0.000723	time 2.4783 (2.2318)	loss 4.2403 (3.7031)	grad_norm 1.1443 (1.2770)	
[2022-01-20 23:28:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][550/1251]	eta 0:26:03 lr 0.000723	time 1.5747 (2.2304)	loss 3.3304 (3.6983)	grad_norm 1.2645 (1.2764)	
[2022-01-20 23:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][560/1251]	eta 0:25:41 lr 0.000723	time 2.4677 (2.2307)	loss 4.1243 (3.6992)	grad_norm 1.2584 (1.2766)	
[2022-01-20 23:29:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][570/1251]	eta 0:25:18 lr 0.000723	time 1.9064 (2.2293)	loss 4.3949 (3.6938)	grad_norm 1.5077 (1.2781)	
[2022-01-20 23:29:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][580/1251]	eta 0:24:55 lr 0.000723	time 1.8935 (2.2295)	loss 4.2862 (3.6917)	grad_norm 1.2376 (1.2770)	
[2022-01-20 23:30:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][590/1251]	eta 0:24:33 lr 0.000723	time 2.1572 (2.2287)	loss 4.3277 (3.6918)	grad_norm 1.2546 (1.2777)	
[2022-01-20 23:30:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][600/1251]	eta 0:24:09 lr 0.000723	time 1.8760 (2.2269)	loss 3.5184 (3.6932)	grad_norm 1.3362 (1.2792)	
[2022-01-20 23:30:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][610/1251]	eta 0:23:46 lr 0.000723	time 1.8467 (2.2260)	loss 4.1357 (3.6944)	grad_norm 1.1750 (1.2788)	
[2022-01-20 23:31:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][620/1251]	eta 0:23:23 lr 0.000723	time 1.9450 (2.2238)	loss 3.8747 (3.6987)	grad_norm 1.3992 (1.2789)	
[2022-01-20 23:31:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][630/1251]	eta 0:22:59 lr 0.000723	time 2.3049 (2.2209)	loss 4.0418 (3.7010)	grad_norm 1.4620 (1.2793)	
[2022-01-20 23:31:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][640/1251]	eta 0:22:37 lr 0.000723	time 2.8074 (2.2211)	loss 3.9165 (3.7032)	grad_norm 1.1918 (1.2791)	
[2022-01-20 23:32:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][650/1251]	eta 0:22:16 lr 0.000723	time 1.9718 (2.2230)	loss 3.0863 (3.7028)	grad_norm 1.1687 (1.2784)	
[2022-01-20 23:32:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][660/1251]	eta 0:21:54 lr 0.000723	time 2.1091 (2.2246)	loss 3.3769 (3.7009)	grad_norm 1.4177 (1.2777)	
[2022-01-20 23:32:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][670/1251]	eta 0:21:30 lr 0.000723	time 1.8084 (2.2219)	loss 3.0158 (3.7019)	grad_norm 1.1112 (1.2777)	
[2022-01-20 23:33:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][680/1251]	eta 0:21:08 lr 0.000723	time 2.1551 (2.2210)	loss 3.9017 (3.7069)	grad_norm 1.4999 (1.2795)	
[2022-01-20 23:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][690/1251]	eta 0:20:44 lr 0.000723	time 1.6376 (2.2185)	loss 3.0922 (3.7084)	grad_norm 1.4095 (1.2797)	
[2022-01-20 23:34:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][700/1251]	eta 0:20:21 lr 0.000722	time 2.1124 (2.2176)	loss 2.6433 (3.7034)	grad_norm 1.4881 (1.2797)	
[2022-01-20 23:34:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][710/1251]	eta 0:20:00 lr 0.000722	time 1.6199 (2.2191)	loss 2.9877 (3.7023)	grad_norm 1.2588 (1.2784)	
[2022-01-20 23:34:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][720/1251]	eta 0:19:39 lr 0.000722	time 2.1053 (2.2215)	loss 2.9945 (3.6996)	grad_norm 1.1685 (1.2783)	
[2022-01-20 23:35:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][730/1251]	eta 0:19:16 lr 0.000722	time 1.5600 (2.2194)	loss 4.3775 (3.7029)	grad_norm 1.3707 (1.2784)	
[2022-01-20 23:35:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][740/1251]	eta 0:18:53 lr 0.000722	time 1.5872 (2.2182)	loss 3.9687 (3.7056)	grad_norm 1.0791 (1.2782)	
[2022-01-20 23:35:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][750/1251]	eta 0:18:31 lr 0.000722	time 1.8357 (2.2179)	loss 4.0661 (3.7081)	grad_norm 1.1083 (1.2780)	
[2022-01-20 23:36:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][760/1251]	eta 0:18:08 lr 0.000722	time 1.7783 (2.2165)	loss 2.9043 (3.7067)	grad_norm 1.3919 (1.2772)	
[2022-01-20 23:36:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][770/1251]	eta 0:17:45 lr 0.000722	time 2.1943 (2.2155)	loss 4.5178 (3.7059)	grad_norm 1.2212 (1.2765)	
[2022-01-20 23:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][780/1251]	eta 0:17:22 lr 0.000722	time 1.8626 (2.2141)	loss 4.1748 (3.7068)	grad_norm 1.2761 (1.2763)	
[2022-01-20 23:37:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][790/1251]	eta 0:17:00 lr 0.000722	time 2.5853 (2.2142)	loss 3.8261 (3.7058)	grad_norm 1.4338 (1.2763)	
[2022-01-20 23:37:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][800/1251]	eta 0:16:37 lr 0.000722	time 1.6479 (2.2127)	loss 3.9530 (3.7057)	grad_norm 1.2572 (1.2756)	
[2022-01-20 23:38:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][810/1251]	eta 0:16:15 lr 0.000722	time 1.9208 (2.2127)	loss 3.5760 (3.7071)	grad_norm 1.1656 (1.2748)	
[2022-01-20 23:38:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][820/1251]	eta 0:15:53 lr 0.000722	time 1.9883 (2.2125)	loss 3.8131 (3.7076)	grad_norm 1.1173 (1.2752)	
[2022-01-20 23:38:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][830/1251]	eta 0:15:32 lr 0.000722	time 2.4289 (2.2141)	loss 4.5728 (3.7091)	grad_norm 1.1423 (1.2741)	
[2022-01-20 23:39:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][840/1251]	eta 0:15:09 lr 0.000722	time 1.5369 (2.2127)	loss 4.1728 (3.7097)	grad_norm 1.1405 (1.2738)	
[2022-01-20 23:39:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][850/1251]	eta 0:14:46 lr 0.000722	time 1.8070 (2.2114)	loss 3.9052 (3.7063)	grad_norm 1.4918 (1.2733)	
[2022-01-20 23:39:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][860/1251]	eta 0:14:23 lr 0.000722	time 2.2588 (2.2094)	loss 4.3853 (3.7063)	grad_norm 1.2891 (1.2729)	
[2022-01-20 23:40:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][870/1251]	eta 0:14:01 lr 0.000722	time 1.7883 (2.2089)	loss 3.7510 (3.7084)	grad_norm 1.2307 (1.2730)	
[2022-01-20 23:40:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][880/1251]	eta 0:13:39 lr 0.000722	time 1.8277 (2.2093)	loss 3.6318 (3.7097)	grad_norm 1.2739 (1.2738)	
[2022-01-20 23:40:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][890/1251]	eta 0:13:17 lr 0.000722	time 1.4345 (2.2104)	loss 2.6279 (3.7117)	grad_norm 1.3121 (1.2745)	
[2022-01-20 23:41:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][900/1251]	eta 0:12:55 lr 0.000722	time 2.3950 (2.2107)	loss 3.6157 (3.7093)	grad_norm 1.0404 (1.2734)	
[2022-01-20 23:41:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][910/1251]	eta 0:12:33 lr 0.000722	time 1.8918 (2.2099)	loss 4.2508 (3.7129)	grad_norm 1.4173 (1.2731)	
[2022-01-20 23:42:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][920/1251]	eta 0:12:11 lr 0.000722	time 2.2319 (2.2088)	loss 3.7295 (3.7100)	grad_norm 1.3729 (1.2729)	
[2022-01-20 23:42:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][930/1251]	eta 0:11:48 lr 0.000722	time 1.8781 (2.2063)	loss 2.6813 (3.7088)	grad_norm 1.2007 (1.2727)	
[2022-01-20 23:42:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][940/1251]	eta 0:11:26 lr 0.000722	time 2.5038 (2.2059)	loss 3.5504 (3.7089)	grad_norm 1.2124 (1.2729)	
[2022-01-20 23:43:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][950/1251]	eta 0:11:04 lr 0.000722	time 1.9255 (2.2060)	loss 4.5247 (3.7069)	grad_norm 1.1657 (1.2734)	
[2022-01-20 23:43:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][960/1251]	eta 0:10:42 lr 0.000722	time 2.2499 (2.2069)	loss 4.3850 (3.7060)	grad_norm 1.2411 (1.2734)	
[2022-01-20 23:43:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][970/1251]	eta 0:10:19 lr 0.000721	time 1.7224 (2.2061)	loss 3.9154 (3.7054)	grad_norm 1.1987 (1.2735)	
[2022-01-20 23:44:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][980/1251]	eta 0:09:58 lr 0.000721	time 2.2266 (2.2071)	loss 4.6091 (3.7071)	grad_norm 1.1929 (1.2729)	
[2022-01-20 23:44:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][990/1251]	eta 0:09:36 lr 0.000721	time 1.7719 (2.2072)	loss 3.7541 (3.7090)	grad_norm 1.2306 (1.2721)	
[2022-01-20 23:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1000/1251]	eta 0:09:14 lr 0.000721	time 2.2850 (2.2077)	loss 3.9269 (3.7101)	grad_norm 1.1527 (1.2710)	
[2022-01-20 23:45:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1010/1251]	eta 0:08:51 lr 0.000721	time 1.5406 (2.2064)	loss 4.0634 (3.7094)	grad_norm 1.1240 (1.2708)	
[2022-01-20 23:45:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1020/1251]	eta 0:08:29 lr 0.000721	time 1.6334 (2.2051)	loss 3.6112 (3.7084)	grad_norm 1.0825 (1.2700)	
[2022-01-20 23:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1030/1251]	eta 0:08:07 lr 0.000721	time 2.1601 (2.2048)	loss 3.0285 (3.7093)	grad_norm 1.5939 (1.2698)	
[2022-01-20 23:46:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1040/1251]	eta 0:07:45 lr 0.000721	time 2.2565 (2.2065)	loss 4.1586 (3.7108)	grad_norm 1.4338 (1.2695)	
[2022-01-20 23:46:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1050/1251]	eta 0:07:23 lr 0.000721	time 2.0873 (2.2063)	loss 3.0362 (3.7093)	grad_norm 1.3491 (1.2692)	
[2022-01-20 23:47:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1060/1251]	eta 0:07:01 lr 0.000721	time 1.8486 (2.2054)	loss 3.9669 (3.7095)	grad_norm 1.2261 (1.2700)	
[2022-01-20 23:47:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1070/1251]	eta 0:06:39 lr 0.000721	time 1.8631 (2.2046)	loss 3.1297 (3.7095)	grad_norm 1.5645 (1.2701)	
[2022-01-20 23:47:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1080/1251]	eta 0:06:16 lr 0.000721	time 2.2716 (2.2041)	loss 3.9820 (3.7120)	grad_norm 1.4697 (1.2705)	
[2022-01-20 23:48:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1090/1251]	eta 0:05:54 lr 0.000721	time 1.9217 (2.2028)	loss 3.3913 (3.7114)	grad_norm 1.3776 (1.2702)	
[2022-01-20 23:48:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1100/1251]	eta 0:05:32 lr 0.000721	time 3.1245 (2.2037)	loss 3.9995 (3.7118)	grad_norm 1.3590 (1.2709)	
[2022-01-20 23:48:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1110/1251]	eta 0:05:10 lr 0.000721	time 1.8736 (2.2027)	loss 3.2995 (3.7110)	grad_norm 1.2492 (1.2720)	
[2022-01-20 23:49:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1120/1251]	eta 0:04:48 lr 0.000721	time 2.0076 (2.2018)	loss 2.8287 (3.7077)	grad_norm 1.3671 (1.2720)	
[2022-01-20 23:49:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1130/1251]	eta 0:04:26 lr 0.000721	time 2.3067 (2.2015)	loss 4.5878 (3.7101)	grad_norm 1.1715 (1.2719)	
[2022-01-20 23:49:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1140/1251]	eta 0:04:04 lr 0.000721	time 1.4703 (2.2016)	loss 2.9022 (3.7082)	grad_norm 1.4250 (1.2722)	
[2022-01-20 23:50:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1150/1251]	eta 0:03:42 lr 0.000721	time 2.6396 (2.2023)	loss 4.1838 (3.7086)	grad_norm 1.2667 (1.2721)	
[2022-01-20 23:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1160/1251]	eta 0:03:20 lr 0.000721	time 2.1538 (2.2018)	loss 3.4889 (3.7081)	grad_norm 1.3789 (1.2725)	
[2022-01-20 23:51:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1170/1251]	eta 0:02:58 lr 0.000721	time 2.3064 (2.2014)	loss 3.6278 (3.7074)	grad_norm 1.3980 (1.2727)	
[2022-01-20 23:51:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1180/1251]	eta 0:02:36 lr 0.000721	time 1.5081 (2.2009)	loss 4.0230 (3.7066)	grad_norm 1.2538 (1.2727)	
[2022-01-20 23:51:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1190/1251]	eta 0:02:14 lr 0.000721	time 2.5662 (2.2003)	loss 3.9544 (3.7058)	grad_norm 1.2087 (1.2729)	
[2022-01-20 23:52:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1200/1251]	eta 0:01:52 lr 0.000721	time 2.2899 (2.2004)	loss 2.6684 (3.7042)	grad_norm 1.2538 (1.2726)	
[2022-01-20 23:52:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1210/1251]	eta 0:01:30 lr 0.000721	time 1.7231 (2.2000)	loss 3.7791 (3.7048)	grad_norm 1.2857 (1.2729)	
[2022-01-20 23:52:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1220/1251]	eta 0:01:08 lr 0.000721	time 2.1302 (2.2011)	loss 3.7074 (3.7066)	grad_norm 1.2680 (1.2722)	
[2022-01-20 23:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1230/1251]	eta 0:00:46 lr 0.000721	time 2.5489 (2.2014)	loss 3.4305 (3.7059)	grad_norm 1.1500 (1.2719)	
[2022-01-20 23:53:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1240/1251]	eta 0:00:24 lr 0.000720	time 1.4007 (2.2004)	loss 4.1781 (3.7046)	grad_norm 1.2516 (1.2720)	
[2022-01-20 23:53:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [106/300][1250/1251]	eta 0:00:02 lr 0.000720	time 1.1910 (2.1950)	loss 3.6321 (3.7040)	grad_norm 1.2323 (1.2719)	
[2022-01-20 23:53:53 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 106 training takes 0:45:46
[2022-01-20 23:54:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.129 (18.129)	Loss 1.0796 (1.0796)	Acc@1 74.902 (74.902)	Acc@5 93.359 (93.359)	
[2022-01-20 23:54:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.885 (3.348)	Loss 1.2235 (1.1152)	Acc@1 72.168 (74.290)	Acc@5 90.527 (92.276)	
[2022-01-20 23:54:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.592 (2.468)	Loss 1.1081 (1.1141)	Acc@1 75.000 (74.358)	Acc@5 90.723 (92.160)	
[2022-01-20 23:55:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.040 (2.190)	Loss 1.1102 (1.1172)	Acc@1 74.805 (74.083)	Acc@5 92.383 (92.238)	
[2022-01-20 23:55:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.682 (2.134)	Loss 1.0852 (1.1086)	Acc@1 73.633 (74.204)	Acc@5 92.090 (92.297)	
[2022-01-20 23:55:28 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.166 Acc@5 92.188
[2022-01-20 23:55:28 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.2%
[2022-01-20 23:55:28 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.23%
[2022-01-20 23:55:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][0/1251]	eta 7:29:52 lr 0.000720	time 21.5764 (21.5764)	loss 2.5680 (2.5680)	grad_norm 1.4775 (1.4775)	
[2022-01-20 23:56:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][10/1251]	eta 1:30:30 lr 0.000720	time 2.6139 (4.3762)	loss 3.4718 (3.5144)	grad_norm 1.1910 (1.2890)	
[2022-01-20 23:56:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][20/1251]	eta 1:07:52 lr 0.000720	time 1.4292 (3.3082)	loss 4.5692 (3.5667)	grad_norm 1.1842 (1.2773)	
[2022-01-20 23:56:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][30/1251]	eta 1:00:06 lr 0.000720	time 1.5585 (2.9535)	loss 2.6323 (3.5467)	grad_norm 1.4231 (1.3173)	
[2022-01-20 23:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][40/1251]	eta 0:57:24 lr 0.000720	time 3.4062 (2.8443)	loss 3.9116 (3.5861)	grad_norm 1.4016 (1.3062)	
[2022-01-20 23:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][50/1251]	eta 0:55:08 lr 0.000720	time 2.2537 (2.7545)	loss 3.7589 (3.6091)	grad_norm 1.4417 (1.3115)	
[2022-01-20 23:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][60/1251]	eta 0:52:15 lr 0.000720	time 1.6326 (2.6325)	loss 4.4935 (3.6206)	grad_norm 1.2443 (1.3036)	
[2022-01-20 23:58:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][70/1251]	eta 0:49:41 lr 0.000720	time 2.0563 (2.5243)	loss 3.7207 (3.6204)	grad_norm 1.3940 (1.3057)	
[2022-01-20 23:58:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][80/1251]	eta 0:47:48 lr 0.000720	time 1.8728 (2.4497)	loss 4.2070 (3.6457)	grad_norm 1.1971 (1.3183)	
[2022-01-20 23:59:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][90/1251]	eta 0:46:43 lr 0.000720	time 1.7627 (2.4151)	loss 2.4378 (3.6259)	grad_norm 1.2091 (1.3183)	
[2022-01-20 23:59:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][100/1251]	eta 0:46:01 lr 0.000720	time 3.0408 (2.3989)	loss 3.9867 (3.6509)	grad_norm 1.2423 (1.3168)	
[2022-01-20 23:59:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][110/1251]	eta 0:45:19 lr 0.000720	time 2.0802 (2.3837)	loss 3.5925 (3.6371)	grad_norm 1.2360 (1.3065)	
[2022-01-21 00:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][120/1251]	eta 0:44:52 lr 0.000720	time 1.8416 (2.3803)	loss 3.4703 (3.6330)	grad_norm 1.1254 (1.3078)	
[2022-01-21 00:00:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][130/1251]	eta 0:44:42 lr 0.000720	time 3.1242 (2.3931)	loss 2.9335 (3.6320)	grad_norm 1.2520 (1.3075)	
[2022-01-21 00:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][140/1251]	eta 0:44:04 lr 0.000720	time 2.1873 (2.3801)	loss 3.3778 (3.6246)	grad_norm 1.3287 (1.2997)	
[2022-01-21 00:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][150/1251]	eta 0:43:17 lr 0.000720	time 1.9194 (2.3596)	loss 3.6398 (3.6269)	grad_norm 1.2401 (1.2982)	
[2022-01-21 00:01:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][160/1251]	eta 0:42:20 lr 0.000720	time 1.8817 (2.3290)	loss 2.7940 (3.6274)	grad_norm 1.1670 (1.2961)	
[2022-01-21 00:02:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][170/1251]	eta 0:41:41 lr 0.000720	time 1.8855 (2.3139)	loss 4.2365 (3.6272)	grad_norm 1.0269 (1.2902)	
[2022-01-21 00:02:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][180/1251]	eta 0:41:11 lr 0.000720	time 1.8667 (2.3075)	loss 4.1305 (3.6458)	grad_norm 1.2407 (1.2851)	
[2022-01-21 00:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][190/1251]	eta 0:40:40 lr 0.000720	time 2.0578 (2.3001)	loss 4.0190 (3.6358)	grad_norm 1.3845 (1.2874)	
[2022-01-21 00:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][200/1251]	eta 0:40:24 lr 0.000720	time 2.9655 (2.3070)	loss 3.0306 (3.6239)	grad_norm 1.3116 (1.2922)	
[2022-01-21 00:03:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][210/1251]	eta 0:39:57 lr 0.000720	time 2.0867 (2.3030)	loss 4.5611 (3.6431)	grad_norm 1.2061 (1.2896)	
[2022-01-21 00:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][220/1251]	eta 0:39:28 lr 0.000720	time 2.1567 (2.2974)	loss 4.0587 (3.6432)	grad_norm 1.8647 (1.2942)	
[2022-01-21 00:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][230/1251]	eta 0:38:59 lr 0.000720	time 1.9511 (2.2911)	loss 3.3816 (3.6336)	grad_norm 1.2346 (1.2945)	
[2022-01-21 00:04:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][240/1251]	eta 0:38:37 lr 0.000720	time 2.9332 (2.2925)	loss 4.0645 (3.6505)	grad_norm 1.1267 (1.2923)	
[2022-01-21 00:05:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][250/1251]	eta 0:38:04 lr 0.000720	time 2.1017 (2.2823)	loss 3.3970 (3.6543)	grad_norm 1.2782 (1.2912)	
[2022-01-21 00:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][260/1251]	eta 0:37:36 lr 0.000719	time 1.8369 (2.2774)	loss 3.2605 (3.6543)	grad_norm 1.3199 (1.2923)	
[2022-01-21 00:05:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][270/1251]	eta 0:37:10 lr 0.000719	time 1.8667 (2.2732)	loss 4.4319 (3.6575)	grad_norm 1.2745 (1.2932)	
[2022-01-21 00:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][280/1251]	eta 0:36:45 lr 0.000719	time 2.4147 (2.2714)	loss 3.5891 (3.6541)	grad_norm 1.0942 (1.2894)	
[2022-01-21 00:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][290/1251]	eta 0:36:20 lr 0.000719	time 1.8964 (2.2688)	loss 3.9439 (3.6665)	grad_norm 1.4151 (1.2884)	
[2022-01-21 00:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][300/1251]	eta 0:35:55 lr 0.000719	time 1.9605 (2.2668)	loss 3.8534 (3.6624)	grad_norm 1.2893 (1.2871)	
[2022-01-21 00:07:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][310/1251]	eta 0:35:36 lr 0.000719	time 1.8582 (2.2709)	loss 4.1803 (3.6714)	grad_norm 1.1534 (1.2869)	
[2022-01-21 00:07:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][320/1251]	eta 0:35:12 lr 0.000719	time 3.3962 (2.2691)	loss 4.0078 (3.6698)	grad_norm 1.2369 (1.2863)	
[2022-01-21 00:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][330/1251]	eta 0:34:41 lr 0.000719	time 1.7827 (2.2600)	loss 4.3675 (3.6813)	grad_norm 1.2559 (1.2861)	
[2022-01-21 00:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][340/1251]	eta 0:34:15 lr 0.000719	time 2.1939 (2.2567)	loss 3.8504 (3.6796)	grad_norm 1.5166 (1.2893)	
[2022-01-21 00:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][350/1251]	eta 0:33:51 lr 0.000719	time 1.5993 (2.2545)	loss 4.0702 (3.6804)	grad_norm 1.3819 (1.2898)	
[2022-01-21 00:09:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][360/1251]	eta 0:33:32 lr 0.000719	time 3.3066 (2.2590)	loss 3.8356 (3.6782)	grad_norm 1.1470 (1.2899)	
[2022-01-21 00:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][370/1251]	eta 0:33:09 lr 0.000719	time 2.0938 (2.2584)	loss 3.9835 (3.6779)	grad_norm 1.5848 (1.2907)	
[2022-01-21 00:09:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][380/1251]	eta 0:32:43 lr 0.000719	time 2.1599 (2.2541)	loss 4.1286 (3.6833)	grad_norm 1.1851 (1.2947)	
[2022-01-21 00:10:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][390/1251]	eta 0:32:13 lr 0.000719	time 1.9103 (2.2453)	loss 3.0229 (3.6803)	grad_norm 1.3766 (1.2968)	
[2022-01-21 00:10:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][400/1251]	eta 0:31:47 lr 0.000719	time 2.3159 (2.2410)	loss 4.4293 (3.6824)	grad_norm 1.2110 (1.2962)	
[2022-01-21 00:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][410/1251]	eta 0:31:22 lr 0.000719	time 2.1328 (2.2390)	loss 4.3980 (3.6757)	grad_norm 1.4105 (1.2961)	
[2022-01-21 00:11:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][420/1251]	eta 0:31:01 lr 0.000719	time 2.7965 (2.2395)	loss 4.0671 (3.6808)	grad_norm 1.3357 (1.2961)	
[2022-01-21 00:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][430/1251]	eta 0:30:39 lr 0.000719	time 2.1620 (2.2409)	loss 3.7798 (3.6798)	grad_norm 1.1694 (1.2945)	
[2022-01-21 00:11:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][440/1251]	eta 0:30:17 lr 0.000719	time 2.5057 (2.2408)	loss 2.2836 (3.6810)	grad_norm 1.0804 (1.2924)	
[2022-01-21 00:12:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][450/1251]	eta 0:29:56 lr 0.000719	time 2.1905 (2.2432)	loss 3.2837 (3.6801)	grad_norm 1.1582 (1.2903)	
[2022-01-21 00:12:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][460/1251]	eta 0:29:33 lr 0.000719	time 2.7732 (2.2423)	loss 3.2579 (3.6775)	grad_norm 1.4414 (1.2908)	
[2022-01-21 00:13:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][470/1251]	eta 0:29:07 lr 0.000719	time 1.6345 (2.2372)	loss 3.5963 (3.6754)	grad_norm 1.3132 (1.2917)	
[2022-01-21 00:13:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][480/1251]	eta 0:28:42 lr 0.000719	time 2.4326 (2.2345)	loss 3.6859 (3.6781)	grad_norm 1.3157 (1.2910)	
[2022-01-21 00:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][490/1251]	eta 0:28:19 lr 0.000719	time 1.8648 (2.2326)	loss 2.8092 (3.6787)	grad_norm 1.4411 (1.2907)	
[2022-01-21 00:14:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][500/1251]	eta 0:27:59 lr 0.000719	time 3.4182 (2.2361)	loss 2.6396 (3.6802)	grad_norm 1.2199 (1.2925)	
[2022-01-21 00:14:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][510/1251]	eta 0:27:38 lr 0.000719	time 2.1181 (2.2378)	loss 3.0714 (3.6832)	grad_norm 1.1964 (1.2919)	
[2022-01-21 00:14:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][520/1251]	eta 0:27:14 lr 0.000718	time 2.2177 (2.2358)	loss 2.9994 (3.6826)	grad_norm 1.4150 (1.2924)	
[2022-01-21 00:15:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][530/1251]	eta 0:26:48 lr 0.000718	time 1.7169 (2.2306)	loss 3.2121 (3.6791)	grad_norm 1.3180 (1.2918)	
[2022-01-21 00:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][540/1251]	eta 0:26:22 lr 0.000718	time 2.0586 (2.2256)	loss 3.0053 (3.6826)	grad_norm 1.1441 (1.2920)	
[2022-01-21 00:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][550/1251]	eta 0:26:00 lr 0.000718	time 2.4368 (2.2255)	loss 4.1807 (3.6808)	grad_norm 1.1321 (1.2907)	
[2022-01-21 00:16:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][560/1251]	eta 0:25:38 lr 0.000718	time 1.8550 (2.2265)	loss 4.0356 (3.6819)	grad_norm 1.2690 (1.2906)	
[2022-01-21 00:16:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][570/1251]	eta 0:25:17 lr 0.000718	time 2.5793 (2.2287)	loss 3.8465 (3.6839)	grad_norm 1.2956 (1.2895)	
[2022-01-21 00:17:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][580/1251]	eta 0:24:53 lr 0.000718	time 1.9858 (2.2262)	loss 2.5959 (3.6836)	grad_norm 1.3376 (1.2883)	
[2022-01-21 00:17:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][590/1251]	eta 0:24:30 lr 0.000718	time 2.9137 (2.2247)	loss 2.5468 (3.6839)	grad_norm 1.4629 (1.2878)	
[2022-01-21 00:17:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][600/1251]	eta 0:24:06 lr 0.000718	time 1.9566 (2.2218)	loss 3.1425 (3.6778)	grad_norm 1.1272 (1.2875)	
[2022-01-21 00:18:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][610/1251]	eta 0:23:43 lr 0.000718	time 2.3547 (2.2205)	loss 4.2165 (3.6748)	grad_norm 1.2813 (1.2865)	
[2022-01-21 00:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][620/1251]	eta 0:23:19 lr 0.000718	time 1.8973 (2.2174)	loss 4.0072 (3.6744)	grad_norm 1.1605 (1.2855)	
[2022-01-21 00:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][630/1251]	eta 0:22:57 lr 0.000718	time 2.9937 (2.2189)	loss 4.4204 (3.6789)	grad_norm 1.1514 (1.2845)	
[2022-01-21 00:19:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][640/1251]	eta 0:22:34 lr 0.000718	time 1.6976 (2.2169)	loss 3.6950 (3.6808)	grad_norm 1.1713 (1.2835)	
[2022-01-21 00:19:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][650/1251]	eta 0:22:13 lr 0.000718	time 2.2991 (2.2180)	loss 2.9448 (3.6855)	grad_norm 1.2650 (1.2849)	
[2022-01-21 00:19:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][660/1251]	eta 0:21:50 lr 0.000718	time 2.8015 (2.2168)	loss 3.6133 (3.6823)	grad_norm 1.2999 (1.2844)	
[2022-01-21 00:20:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][670/1251]	eta 0:21:27 lr 0.000718	time 2.2591 (2.2157)	loss 3.9982 (3.6813)	grad_norm 1.2633 (1.2833)	
[2022-01-21 00:20:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][680/1251]	eta 0:21:05 lr 0.000718	time 1.8437 (2.2155)	loss 3.9920 (3.6817)	grad_norm 1.5397 (1.2847)	
[2022-01-21 00:20:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][690/1251]	eta 0:20:43 lr 0.000718	time 2.0092 (2.2168)	loss 3.6783 (3.6764)	grad_norm 1.4449 (1.2852)	
[2022-01-21 00:21:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][700/1251]	eta 0:20:22 lr 0.000718	time 2.6168 (2.2182)	loss 4.2264 (3.6795)	grad_norm 1.0680 (1.2851)	
[2022-01-21 00:21:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][710/1251]	eta 0:20:00 lr 0.000718	time 3.0367 (2.2195)	loss 3.2452 (3.6786)	grad_norm 1.2752 (1.2843)	
[2022-01-21 00:22:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][720/1251]	eta 0:19:38 lr 0.000718	time 1.9079 (2.2189)	loss 3.9048 (3.6762)	grad_norm 1.1194 (1.2843)	
[2022-01-21 00:22:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][730/1251]	eta 0:19:15 lr 0.000718	time 1.9886 (2.2186)	loss 4.6781 (3.6743)	grad_norm 1.2226 (1.2851)	
[2022-01-21 00:22:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][740/1251]	eta 0:18:52 lr 0.000718	time 2.1562 (2.2166)	loss 4.0692 (3.6742)	grad_norm 1.2333 (1.2869)	
[2022-01-21 00:23:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][750/1251]	eta 0:18:29 lr 0.000718	time 2.5084 (2.2149)	loss 3.0391 (3.6727)	grad_norm 1.2078 (1.2871)	
[2022-01-21 00:23:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][760/1251]	eta 0:18:06 lr 0.000718	time 1.9259 (2.2122)	loss 2.7683 (3.6737)	grad_norm 1.2429 (1.2880)	
[2022-01-21 00:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][770/1251]	eta 0:17:42 lr 0.000718	time 1.5333 (2.2099)	loss 3.0245 (3.6721)	grad_norm 1.4953 (1.2879)	
[2022-01-21 00:24:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][780/1251]	eta 0:17:21 lr 0.000718	time 2.9541 (2.2106)	loss 3.8206 (3.6719)	grad_norm 1.4752 (1.2879)	
[2022-01-21 00:24:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][790/1251]	eta 0:16:58 lr 0.000717	time 1.7407 (2.2098)	loss 3.7282 (3.6769)	grad_norm 1.1549 (1.2874)	
[2022-01-21 00:24:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][800/1251]	eta 0:16:36 lr 0.000717	time 2.2363 (2.2103)	loss 3.8795 (3.6770)	grad_norm 1.0593 (1.2864)	
[2022-01-21 00:25:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][810/1251]	eta 0:16:14 lr 0.000717	time 1.9530 (2.2095)	loss 4.2244 (3.6768)	grad_norm 1.2801 (1.2869)	
[2022-01-21 00:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][820/1251]	eta 0:15:52 lr 0.000717	time 1.8717 (2.2099)	loss 3.4947 (3.6814)	grad_norm 1.3136 (1.2875)	
[2022-01-21 00:26:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][830/1251]	eta 0:15:30 lr 0.000717	time 2.2469 (2.2105)	loss 3.5112 (3.6829)	grad_norm 1.1500 (1.2865)	
[2022-01-21 00:26:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][840/1251]	eta 0:15:08 lr 0.000717	time 2.2946 (2.2114)	loss 4.0962 (3.6826)	grad_norm 1.1775 (1.2865)	
[2022-01-21 00:26:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][850/1251]	eta 0:14:46 lr 0.000717	time 1.6691 (2.2101)	loss 3.9842 (3.6825)	grad_norm 1.1274 (1.2864)	
[2022-01-21 00:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][860/1251]	eta 0:14:23 lr 0.000717	time 1.8128 (2.2091)	loss 4.2611 (3.6816)	grad_norm 1.2201 (1.2880)	
[2022-01-21 00:27:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][870/1251]	eta 0:14:01 lr 0.000717	time 1.9204 (2.2095)	loss 3.1472 (3.6806)	grad_norm 1.3713 (1.2875)	
[2022-01-21 00:27:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][880/1251]	eta 0:13:40 lr 0.000717	time 2.8024 (2.2109)	loss 4.2522 (3.6804)	grad_norm 1.4392 (1.2881)	
[2022-01-21 00:28:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][890/1251]	eta 0:13:18 lr 0.000717	time 1.9968 (2.2108)	loss 4.0329 (3.6813)	grad_norm 1.2360 (1.2877)	
[2022-01-21 00:28:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][900/1251]	eta 0:12:55 lr 0.000717	time 2.0423 (2.2094)	loss 3.2217 (3.6796)	grad_norm 1.1165 (1.2882)	
[2022-01-21 00:28:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][910/1251]	eta 0:12:32 lr 0.000717	time 1.8984 (2.2082)	loss 4.1238 (3.6822)	grad_norm 1.0520 (1.2876)	
[2022-01-21 00:29:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][920/1251]	eta 0:12:10 lr 0.000717	time 1.8530 (2.2068)	loss 4.1307 (3.6838)	grad_norm 1.2204 (1.2865)	
[2022-01-21 00:29:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][930/1251]	eta 0:11:47 lr 0.000717	time 2.1051 (2.2041)	loss 2.8602 (3.6859)	grad_norm 1.3013 (1.2865)	
[2022-01-21 00:30:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][940/1251]	eta 0:11:25 lr 0.000717	time 1.9222 (2.2037)	loss 3.1075 (3.6864)	grad_norm 1.7058 (1.2875)	
[2022-01-21 00:30:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][950/1251]	eta 0:11:03 lr 0.000717	time 1.9505 (2.2036)	loss 2.5983 (3.6855)	grad_norm 1.3896 (1.2876)	
[2022-01-21 00:30:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][960/1251]	eta 0:10:41 lr 0.000717	time 1.9477 (2.2036)	loss 2.6356 (3.6865)	grad_norm 1.2159 (1.2877)	
[2022-01-21 00:31:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][970/1251]	eta 0:10:19 lr 0.000717	time 2.7724 (2.2049)	loss 4.3463 (3.6882)	grad_norm 1.3114 (1.2874)	
[2022-01-21 00:31:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][980/1251]	eta 0:09:57 lr 0.000717	time 2.0636 (2.2053)	loss 3.9579 (3.6893)	grad_norm 1.3531 (1.2876)	
[2022-01-21 00:31:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][990/1251]	eta 0:09:35 lr 0.000717	time 2.1387 (2.2051)	loss 3.5803 (3.6867)	grad_norm 1.2997 (1.2881)	
[2022-01-21 00:32:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1000/1251]	eta 0:09:13 lr 0.000717	time 2.7566 (2.2046)	loss 3.9385 (3.6871)	grad_norm 1.5580 (1.2877)	
[2022-01-21 00:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1010/1251]	eta 0:08:51 lr 0.000717	time 2.7106 (2.2034)	loss 3.6505 (3.6891)	grad_norm 1.1441 (1.2886)	
[2022-01-21 00:32:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1020/1251]	eta 0:08:28 lr 0.000717	time 1.9529 (2.2018)	loss 4.0033 (3.6919)	grad_norm 1.2196 (1.2885)	
[2022-01-21 00:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1030/1251]	eta 0:08:06 lr 0.000717	time 1.8993 (2.2012)	loss 4.2114 (3.6929)	grad_norm 1.1234 (1.2875)	
[2022-01-21 00:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1040/1251]	eta 0:07:44 lr 0.000717	time 1.8903 (2.2016)	loss 3.7376 (3.6935)	grad_norm 1.3483 (1.2869)	
[2022-01-21 00:34:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1050/1251]	eta 0:07:22 lr 0.000717	time 2.7128 (2.2019)	loss 3.6186 (3.6925)	grad_norm 1.5130 (1.2866)	
[2022-01-21 00:34:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1060/1251]	eta 0:07:00 lr 0.000716	time 2.1611 (2.2007)	loss 4.1170 (3.6926)	grad_norm 1.4168 (1.2870)	
[2022-01-21 00:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1070/1251]	eta 0:06:38 lr 0.000716	time 2.0189 (2.2006)	loss 4.0792 (3.6930)	grad_norm 1.2104 (1.2874)	
[2022-01-21 00:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1080/1251]	eta 0:06:16 lr 0.000716	time 2.7386 (2.2015)	loss 3.3458 (3.6958)	grad_norm 1.2168 (1.2876)	
[2022-01-21 00:35:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1090/1251]	eta 0:05:54 lr 0.000716	time 1.9325 (2.2019)	loss 4.1492 (3.6960)	grad_norm 1.1753 (1.2870)	
[2022-01-21 00:35:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1100/1251]	eta 0:05:32 lr 0.000716	time 2.4720 (2.2013)	loss 4.2232 (3.6938)	grad_norm 1.4709 (1.2878)	
[2022-01-21 00:36:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1110/1251]	eta 0:05:10 lr 0.000716	time 1.4283 (2.1997)	loss 4.2579 (3.6936)	grad_norm 1.3941 (1.2880)	
[2022-01-21 00:36:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1120/1251]	eta 0:04:48 lr 0.000716	time 2.8871 (2.1999)	loss 3.5677 (3.6914)	grad_norm 1.2960 (1.2885)	
[2022-01-21 00:36:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1130/1251]	eta 0:04:26 lr 0.000716	time 2.1887 (2.1987)	loss 3.9532 (3.6904)	grad_norm 1.2018 (1.2891)	
[2022-01-21 00:37:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1140/1251]	eta 0:04:03 lr 0.000716	time 1.8473 (2.1981)	loss 4.4509 (3.6921)	grad_norm 1.3380 (1.2890)	
[2022-01-21 00:37:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1150/1251]	eta 0:03:41 lr 0.000716	time 1.7785 (2.1980)	loss 3.4285 (3.6913)	grad_norm 1.3218 (1.2894)	
[2022-01-21 00:38:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1160/1251]	eta 0:03:20 lr 0.000716	time 2.4011 (2.1982)	loss 4.1630 (3.6920)	grad_norm 1.1589 (1.2895)	
[2022-01-21 00:38:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1170/1251]	eta 0:02:58 lr 0.000716	time 2.7125 (2.1984)	loss 3.7258 (3.6919)	grad_norm 1.2472 (1.2896)	
[2022-01-21 00:38:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1180/1251]	eta 0:02:36 lr 0.000716	time 2.3950 (2.1993)	loss 3.8401 (3.6924)	grad_norm 1.2405 (1.2895)	
[2022-01-21 00:39:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1190/1251]	eta 0:02:14 lr 0.000716	time 2.1958 (2.1988)	loss 2.5887 (3.6910)	grad_norm 1.1133 (1.2890)	
[2022-01-21 00:39:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1200/1251]	eta 0:01:52 lr 0.000716	time 3.2697 (2.1992)	loss 3.9118 (3.6926)	grad_norm 1.2940 (1.2885)	
[2022-01-21 00:39:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1210/1251]	eta 0:01:30 lr 0.000716	time 1.5912 (2.1982)	loss 2.3864 (3.6898)	grad_norm 1.2350 (1.2885)	
[2022-01-21 00:40:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1220/1251]	eta 0:01:08 lr 0.000716	time 1.6199 (2.1983)	loss 4.1498 (3.6890)	grad_norm 1.2770 (1.2878)	
[2022-01-21 00:40:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1230/1251]	eta 0:00:46 lr 0.000716	time 1.8602 (2.1974)	loss 4.1868 (3.6884)	grad_norm 1.0552 (1.2874)	
[2022-01-21 00:40:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1240/1251]	eta 0:00:24 lr 0.000716	time 2.7089 (2.1982)	loss 4.3603 (3.6892)	grad_norm 1.2620 (1.2870)	
[2022-01-21 00:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [107/300][1250/1251]	eta 0:00:02 lr 0.000716	time 1.2138 (2.1916)	loss 2.8118 (3.6882)	grad_norm 1.2200 (1.2869)	
[2022-01-21 00:41:10 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 107 training takes 0:45:42
[2022-01-21 00:41:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.419 (18.419)	Loss 1.0641 (1.0641)	Acc@1 76.172 (76.172)	Acc@5 92.773 (92.773)	
[2022-01-21 00:41:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.017 (3.408)	Loss 1.1609 (1.0727)	Acc@1 72.070 (74.707)	Acc@5 91.113 (92.694)	
[2022-01-21 00:42:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.293 (2.763)	Loss 1.0478 (1.0827)	Acc@1 75.488 (74.456)	Acc@5 92.285 (92.480)	
[2022-01-21 00:42:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.305 (2.274)	Loss 1.1104 (1.0860)	Acc@1 74.219 (74.291)	Acc@5 91.504 (92.408)	
[2022-01-21 00:42:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.808 (2.169)	Loss 1.0935 (1.0865)	Acc@1 75.391 (74.219)	Acc@5 92.383 (92.445)	
[2022-01-21 00:42:47 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.062 Acc@5 92.408
[2022-01-21 00:42:47 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.1%
[2022-01-21 00:42:47 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.23%
[2022-01-21 00:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][0/1251]	eta 7:24:49 lr 0.000716	time 21.3346 (21.3346)	loss 4.1280 (4.1280)	grad_norm 1.1840 (1.1840)	
[2022-01-21 00:43:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][10/1251]	eta 1:20:51 lr 0.000716	time 1.8392 (3.9090)	loss 2.7842 (3.6450)	grad_norm 1.1590 (1.2363)	
[2022-01-21 00:43:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][20/1251]	eta 1:03:39 lr 0.000716	time 1.8744 (3.1026)	loss 2.9750 (3.7006)	grad_norm 1.1731 (1.2403)	
[2022-01-21 00:44:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][30/1251]	eta 0:56:56 lr 0.000716	time 1.7178 (2.7980)	loss 3.7207 (3.7508)	grad_norm 1.2847 (1.2456)	
[2022-01-21 00:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][40/1251]	eta 0:54:11 lr 0.000716	time 4.8357 (2.6851)	loss 3.7243 (3.7392)	grad_norm 1.1462 (1.2517)	
[2022-01-21 00:45:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][50/1251]	eta 0:52:21 lr 0.000716	time 2.1837 (2.6160)	loss 2.8805 (3.7495)	grad_norm 1.2681 (1.2553)	
[2022-01-21 00:45:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][60/1251]	eta 0:50:32 lr 0.000716	time 1.5006 (2.5466)	loss 3.7520 (3.7348)	grad_norm 1.1821 (1.2524)	
[2022-01-21 00:45:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][70/1251]	eta 0:49:12 lr 0.000715	time 2.7584 (2.5004)	loss 3.6047 (3.7161)	grad_norm 1.4306 (1.2642)	
[2022-01-21 00:46:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][80/1251]	eta 0:48:32 lr 0.000715	time 3.9392 (2.4870)	loss 4.0659 (3.7088)	grad_norm 1.2273 (1.2669)	
[2022-01-21 00:46:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][90/1251]	eta 0:47:38 lr 0.000715	time 2.4299 (2.4621)	loss 2.7221 (3.6848)	grad_norm 1.1645 (1.2796)	
[2022-01-21 00:46:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][100/1251]	eta 0:46:41 lr 0.000715	time 2.7279 (2.4341)	loss 4.1636 (3.6731)	grad_norm 1.1915 (1.2868)	
[2022-01-21 00:47:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][110/1251]	eta 0:45:42 lr 0.000715	time 1.6610 (2.4039)	loss 3.5135 (3.6812)	grad_norm 1.3514 (1.2867)	
[2022-01-21 00:47:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][120/1251]	eta 0:45:08 lr 0.000715	time 3.1565 (2.3951)	loss 2.9891 (3.6751)	grad_norm 1.3925 (1.2833)	
[2022-01-21 00:48:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][130/1251]	eta 0:44:42 lr 0.000715	time 3.0638 (2.3932)	loss 4.3741 (3.7035)	grad_norm 1.5996 (1.2808)	
[2022-01-21 00:48:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][140/1251]	eta 0:43:49 lr 0.000715	time 1.8907 (2.3671)	loss 2.9140 (3.6919)	grad_norm 1.2117 (1.2754)	
[2022-01-21 00:48:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][150/1251]	eta 0:43:03 lr 0.000715	time 1.7949 (2.3469)	loss 2.6537 (3.7000)	grad_norm 1.2395 (1.2729)	
[2022-01-21 00:49:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][160/1251]	eta 0:42:29 lr 0.000715	time 2.7714 (2.3365)	loss 2.6772 (3.6956)	grad_norm 1.2972 (1.2709)	
[2022-01-21 00:49:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][170/1251]	eta 0:41:53 lr 0.000715	time 2.1105 (2.3255)	loss 4.0113 (3.7001)	grad_norm 1.3444 (1.2684)	
[2022-01-21 00:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][180/1251]	eta 0:41:17 lr 0.000715	time 1.9211 (2.3129)	loss 3.9035 (3.7003)	grad_norm 1.3502 (1.2637)	
[2022-01-21 00:50:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][190/1251]	eta 0:40:47 lr 0.000715	time 1.6788 (2.3065)	loss 4.1358 (3.7051)	grad_norm 1.1233 (1.2597)	
[2022-01-21 00:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][200/1251]	eta 0:40:23 lr 0.000715	time 3.3890 (2.3061)	loss 4.3004 (3.7105)	grad_norm 1.1548 (1.2592)	
[2022-01-21 00:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][210/1251]	eta 0:39:53 lr 0.000715	time 1.8142 (2.2988)	loss 3.9754 (3.7087)	grad_norm 1.4622 (1.2612)	
[2022-01-21 00:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][220/1251]	eta 0:39:31 lr 0.000715	time 2.1902 (2.3006)	loss 3.5407 (3.7158)	grad_norm 1.3997 (1.2642)	
[2022-01-21 00:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][230/1251]	eta 0:39:00 lr 0.000715	time 1.6840 (2.2922)	loss 4.1929 (3.7111)	grad_norm 1.4345 (1.2699)	
[2022-01-21 00:51:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][240/1251]	eta 0:38:32 lr 0.000715	time 2.3420 (2.2875)	loss 3.9532 (3.7114)	grad_norm 1.0959 (1.2762)	
[2022-01-21 00:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][250/1251]	eta 0:38:01 lr 0.000715	time 1.8949 (2.2796)	loss 3.3101 (3.7146)	grad_norm 1.2168 (1.2785)	
[2022-01-21 00:52:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][260/1251]	eta 0:37:33 lr 0.000715	time 1.8775 (2.2736)	loss 3.6383 (3.7121)	grad_norm 1.1743 (1.2780)	
[2022-01-21 00:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][270/1251]	eta 0:37:08 lr 0.000715	time 2.4136 (2.2716)	loss 4.1493 (3.7164)	grad_norm 1.5637 (1.2826)	
[2022-01-21 00:53:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][280/1251]	eta 0:36:49 lr 0.000715	time 3.5604 (2.2758)	loss 4.1420 (3.7119)	grad_norm 1.2259 (1.2836)	
[2022-01-21 00:53:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][290/1251]	eta 0:36:23 lr 0.000715	time 1.8813 (2.2724)	loss 3.8703 (3.7175)	grad_norm 1.6046 (1.2836)	
[2022-01-21 00:54:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][300/1251]	eta 0:36:01 lr 0.000715	time 2.2487 (2.2727)	loss 3.9984 (3.7195)	grad_norm 1.2960 (1.2850)	
[2022-01-21 00:54:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][310/1251]	eta 0:35:28 lr 0.000715	time 1.8208 (2.2621)	loss 2.8878 (3.7186)	grad_norm 1.1984 (1.2839)	
[2022-01-21 00:54:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][320/1251]	eta 0:35:00 lr 0.000715	time 2.2042 (2.2564)	loss 4.1273 (3.7198)	grad_norm 1.2451 (1.2835)	
[2022-01-21 00:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][330/1251]	eta 0:34:34 lr 0.000715	time 2.1745 (2.2523)	loss 3.9472 (3.7258)	grad_norm 1.1711 (1.2833)	
[2022-01-21 00:55:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][340/1251]	eta 0:34:08 lr 0.000714	time 1.8371 (2.2482)	loss 4.0600 (3.7221)	grad_norm 1.1337 (1.2810)	
[2022-01-21 00:55:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][350/1251]	eta 0:33:45 lr 0.000714	time 1.9085 (2.2475)	loss 3.9372 (3.7244)	grad_norm 1.3350 (1.2814)	
[2022-01-21 00:56:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][360/1251]	eta 0:33:23 lr 0.000714	time 2.3094 (2.2487)	loss 3.7984 (3.7225)	grad_norm 1.1885 (1.2814)	
[2022-01-21 00:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][370/1251]	eta 0:32:59 lr 0.000714	time 1.9390 (2.2473)	loss 3.0435 (3.7051)	grad_norm 1.1293 (1.2827)	
[2022-01-21 00:57:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][380/1251]	eta 0:32:39 lr 0.000714	time 3.1221 (2.2492)	loss 3.4193 (3.7024)	grad_norm 1.1826 (1.2823)	
[2022-01-21 00:57:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][390/1251]	eta 0:32:19 lr 0.000714	time 1.8322 (2.2527)	loss 3.4918 (3.6939)	grad_norm 1.2771 (1.2847)	
[2022-01-21 00:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][400/1251]	eta 0:31:52 lr 0.000714	time 2.3121 (2.2473)	loss 4.1016 (3.6912)	grad_norm 1.2112 (1.2847)	
[2022-01-21 00:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][410/1251]	eta 0:31:24 lr 0.000714	time 1.8556 (2.2411)	loss 3.9867 (3.6989)	grad_norm 1.3027 (1.2873)	
[2022-01-21 00:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][420/1251]	eta 0:30:59 lr 0.000714	time 1.9107 (2.2381)	loss 3.6740 (3.6959)	grad_norm 1.1491 (1.2864)	
[2022-01-21 00:58:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][430/1251]	eta 0:30:35 lr 0.000714	time 2.4910 (2.2362)	loss 3.5089 (3.6966)	grad_norm 1.2835 (1.2845)	
[2022-01-21 00:59:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][440/1251]	eta 0:30:14 lr 0.000714	time 2.2410 (2.2371)	loss 3.7975 (3.7022)	grad_norm 1.5095 (1.2843)	
[2022-01-21 00:59:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][450/1251]	eta 0:29:51 lr 0.000714	time 1.5625 (2.2365)	loss 4.0251 (3.7057)	grad_norm 1.4265 (1.2841)	
[2022-01-21 00:59:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][460/1251]	eta 0:29:27 lr 0.000714	time 1.5907 (2.2347)	loss 2.8574 (3.7049)	grad_norm 1.3955 (1.2846)	
[2022-01-21 01:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][470/1251]	eta 0:29:06 lr 0.000714	time 3.5408 (2.2360)	loss 3.5250 (3.6997)	grad_norm 1.3058 (1.2851)	
[2022-01-21 01:00:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][480/1251]	eta 0:28:43 lr 0.000714	time 2.2992 (2.2348)	loss 3.4856 (3.6981)	grad_norm 1.2641 (1.2835)	
[2022-01-21 01:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][490/1251]	eta 0:28:19 lr 0.000714	time 1.5021 (2.2338)	loss 4.1664 (3.7016)	grad_norm 1.3551 (1.2846)	
[2022-01-21 01:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][500/1251]	eta 0:27:53 lr 0.000714	time 2.1383 (2.2288)	loss 2.5982 (3.7006)	grad_norm 1.2123 (1.2843)	
[2022-01-21 01:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][510/1251]	eta 0:27:31 lr 0.000714	time 3.1327 (2.2286)	loss 3.7992 (3.7005)	grad_norm 1.2020 (1.2842)	
[2022-01-21 01:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][520/1251]	eta 0:27:07 lr 0.000714	time 2.2649 (2.2271)	loss 4.1006 (3.7021)	grad_norm 1.1811 (1.2837)	
[2022-01-21 01:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][530/1251]	eta 0:26:45 lr 0.000714	time 1.5189 (2.2265)	loss 4.5887 (3.7054)	grad_norm 1.3393 (1.2838)	
[2022-01-21 01:02:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][540/1251]	eta 0:26:22 lr 0.000714	time 2.1058 (2.2259)	loss 3.9955 (3.7069)	grad_norm 1.1093 (1.2843)	
[2022-01-21 01:03:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][550/1251]	eta 0:26:00 lr 0.000714	time 2.6950 (2.2255)	loss 4.0700 (3.7057)	grad_norm 1.2223 (1.2833)	
[2022-01-21 01:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][560/1251]	eta 0:25:37 lr 0.000714	time 1.7709 (2.2257)	loss 3.5533 (3.7047)	grad_norm 1.2926 (1.2837)	
[2022-01-21 01:03:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][570/1251]	eta 0:25:15 lr 0.000714	time 2.1637 (2.2249)	loss 4.3815 (3.7102)	grad_norm 1.6642 (1.2839)	
[2022-01-21 01:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][580/1251]	eta 0:24:50 lr 0.000714	time 1.6481 (2.2215)	loss 3.1371 (3.7113)	grad_norm 1.1786 (1.2829)	
[2022-01-21 01:04:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][590/1251]	eta 0:24:28 lr 0.000714	time 3.6584 (2.2219)	loss 3.7847 (3.7073)	grad_norm 1.2825 (1.2831)	
[2022-01-21 01:05:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][600/1251]	eta 0:24:05 lr 0.000714	time 2.4809 (2.2203)	loss 3.0628 (3.7083)	grad_norm 1.2602 (1.2834)	
[2022-01-21 01:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][610/1251]	eta 0:23:41 lr 0.000713	time 1.5211 (2.2178)	loss 3.5716 (3.7119)	grad_norm 1.1563 (1.2830)	
[2022-01-21 01:05:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][620/1251]	eta 0:23:18 lr 0.000713	time 1.5969 (2.2165)	loss 3.8628 (3.7124)	grad_norm 1.2676 (1.2823)	
[2022-01-21 01:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][630/1251]	eta 0:22:56 lr 0.000713	time 3.1172 (2.2174)	loss 4.5401 (3.7090)	grad_norm 1.2293 (1.2817)	
[2022-01-21 01:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][640/1251]	eta 0:22:35 lr 0.000713	time 2.1380 (2.2182)	loss 3.7982 (3.7100)	grad_norm 1.3960 (1.2817)	
[2022-01-21 01:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][650/1251]	eta 0:22:12 lr 0.000713	time 1.7254 (2.2165)	loss 4.0446 (3.7130)	grad_norm 1.1094 (1.2810)	
[2022-01-21 01:07:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][660/1251]	eta 0:21:49 lr 0.000713	time 1.8367 (2.2158)	loss 4.0779 (3.7146)	grad_norm 1.5442 (1.2811)	
[2022-01-21 01:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][670/1251]	eta 0:21:26 lr 0.000713	time 2.2430 (2.2144)	loss 3.9653 (3.7154)	grad_norm 1.1870 (1.2808)	
[2022-01-21 01:07:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][680/1251]	eta 0:21:04 lr 0.000713	time 2.2377 (2.2142)	loss 3.9117 (3.7114)	grad_norm 1.1350 (1.2809)	
[2022-01-21 01:08:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][690/1251]	eta 0:20:41 lr 0.000713	time 2.2409 (2.2131)	loss 3.5175 (3.7066)	grad_norm 1.2140 (1.2803)	
[2022-01-21 01:08:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][700/1251]	eta 0:20:18 lr 0.000713	time 1.6448 (2.2119)	loss 3.0123 (3.7059)	grad_norm 1.1596 (1.2792)	
[2022-01-21 01:08:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][710/1251]	eta 0:19:55 lr 0.000713	time 1.8667 (2.2102)	loss 2.8016 (3.7060)	grad_norm 1.1037 (1.2785)	
[2022-01-21 01:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][720/1251]	eta 0:19:34 lr 0.000713	time 2.8501 (2.2112)	loss 4.2458 (3.7070)	grad_norm 1.1964 (1.2788)	
[2022-01-21 01:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][730/1251]	eta 0:19:12 lr 0.000713	time 1.9231 (2.2126)	loss 3.8945 (3.7080)	grad_norm 1.3418 (1.2788)	
[2022-01-21 01:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][740/1251]	eta 0:18:50 lr 0.000713	time 1.8641 (2.2131)	loss 3.5710 (3.7106)	grad_norm 1.3635 (1.2800)	
[2022-01-21 01:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][750/1251]	eta 0:18:28 lr 0.000713	time 1.9673 (2.2131)	loss 4.6081 (3.7091)	grad_norm 1.2690 (1.2800)	
[2022-01-21 01:10:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][760/1251]	eta 0:18:06 lr 0.000713	time 3.4143 (2.2130)	loss 4.3827 (3.7081)	grad_norm 1.3602 (1.2803)	
[2022-01-21 01:11:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][770/1251]	eta 0:17:44 lr 0.000713	time 1.9419 (2.2131)	loss 3.7507 (3.7061)	grad_norm 1.3026 (1.2803)	
[2022-01-21 01:11:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][780/1251]	eta 0:17:22 lr 0.000713	time 1.9632 (2.2125)	loss 3.7675 (3.7040)	grad_norm 1.3297 (1.2801)	
[2022-01-21 01:11:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][790/1251]	eta 0:16:59 lr 0.000713	time 2.2304 (2.2112)	loss 2.5555 (3.7036)	grad_norm 1.2568 (1.2801)	
[2022-01-21 01:12:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][800/1251]	eta 0:16:37 lr 0.000713	time 3.1574 (2.2107)	loss 4.1152 (3.7082)	grad_norm 1.1291 (1.2796)	
[2022-01-21 01:12:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][810/1251]	eta 0:16:14 lr 0.000713	time 2.3490 (2.2094)	loss 4.0090 (3.7091)	grad_norm 1.3031 (1.2791)	
[2022-01-21 01:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][820/1251]	eta 0:15:51 lr 0.000713	time 1.6029 (2.2073)	loss 3.3960 (3.7096)	grad_norm 1.3968 (1.2794)	
[2022-01-21 01:13:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][830/1251]	eta 0:15:28 lr 0.000713	time 2.6064 (2.2061)	loss 4.5149 (3.7096)	grad_norm 1.3349 (1.2789)	
[2022-01-21 01:13:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][840/1251]	eta 0:15:06 lr 0.000713	time 1.6367 (2.2052)	loss 3.6182 (3.7125)	grad_norm 1.4446 (1.2794)	
[2022-01-21 01:14:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][850/1251]	eta 0:14:44 lr 0.000713	time 2.6308 (2.2063)	loss 4.1702 (3.7143)	grad_norm 1.0869 (1.2790)	
[2022-01-21 01:14:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][860/1251]	eta 0:14:22 lr 0.000713	time 2.1017 (2.2068)	loss 4.1630 (3.7163)	grad_norm 1.1749 (1.2781)	
[2022-01-21 01:14:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][870/1251]	eta 0:14:01 lr 0.000712	time 2.0639 (2.2093)	loss 4.1946 (3.7155)	grad_norm 1.1830 (1.2775)	
[2022-01-21 01:15:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][880/1251]	eta 0:13:39 lr 0.000712	time 1.6781 (2.2096)	loss 3.4453 (3.7162)	grad_norm 1.2341 (1.2769)	
[2022-01-21 01:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][890/1251]	eta 0:13:17 lr 0.000712	time 2.0297 (2.2099)	loss 3.9992 (3.7164)	grad_norm 1.2169 (1.2770)	
[2022-01-21 01:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][900/1251]	eta 0:12:54 lr 0.000712	time 1.9186 (2.2071)	loss 3.0273 (3.7131)	grad_norm 1.1951 (1.2773)	
[2022-01-21 01:16:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][910/1251]	eta 0:12:31 lr 0.000712	time 1.8631 (2.2044)	loss 3.9941 (3.7132)	grad_norm 1.3315 (1.2776)	
[2022-01-21 01:16:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][920/1251]	eta 0:12:08 lr 0.000712	time 1.8152 (2.2023)	loss 3.0220 (3.7097)	grad_norm 1.2110 (1.2776)	
[2022-01-21 01:16:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][930/1251]	eta 0:11:46 lr 0.000712	time 1.9590 (2.2004)	loss 4.0544 (3.7085)	grad_norm 1.3384 (1.2785)	
[2022-01-21 01:17:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][940/1251]	eta 0:11:24 lr 0.000712	time 2.7077 (2.2007)	loss 3.9716 (3.7092)	grad_norm 1.2975 (1.2789)	
[2022-01-21 01:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][950/1251]	eta 0:11:02 lr 0.000712	time 1.9321 (2.2007)	loss 3.9663 (3.7108)	grad_norm 1.2256 (1.2790)	
[2022-01-21 01:18:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][960/1251]	eta 0:10:40 lr 0.000712	time 1.8998 (2.2012)	loss 4.2331 (3.7094)	grad_norm 1.1261 (1.2789)	
[2022-01-21 01:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][970/1251]	eta 0:10:19 lr 0.000712	time 1.9502 (2.2029)	loss 3.1710 (3.7097)	grad_norm 1.2883 (1.2798)	
[2022-01-21 01:18:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][980/1251]	eta 0:09:57 lr 0.000712	time 2.8407 (2.2062)	loss 3.4666 (3.7088)	grad_norm 1.4171 (1.2798)	
[2022-01-21 01:19:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][990/1251]	eta 0:09:35 lr 0.000712	time 1.8108 (2.2059)	loss 4.4742 (3.7120)	grad_norm 1.3829 (1.2791)	
[2022-01-21 01:19:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1000/1251]	eta 0:09:13 lr 0.000712	time 2.1795 (2.2055)	loss 3.9653 (3.7148)	grad_norm 1.1199 (1.2793)	
[2022-01-21 01:19:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1010/1251]	eta 0:08:51 lr 0.000712	time 1.5454 (2.2034)	loss 3.4335 (3.7130)	grad_norm 1.1394 (1.2795)	
[2022-01-21 01:20:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1020/1251]	eta 0:08:28 lr 0.000712	time 2.2515 (2.2023)	loss 4.4476 (3.7145)	grad_norm 1.3247 (1.2795)	
[2022-01-21 01:20:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1030/1251]	eta 0:08:06 lr 0.000712	time 2.5832 (2.2020)	loss 3.4657 (3.7129)	grad_norm 1.5935 (1.2792)	
[2022-01-21 01:20:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1040/1251]	eta 0:07:44 lr 0.000712	time 2.1239 (2.2018)	loss 4.0640 (3.7104)	grad_norm 1.4508 (1.2794)	
[2022-01-21 01:21:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1050/1251]	eta 0:07:22 lr 0.000712	time 2.1592 (2.2036)	loss 3.0650 (3.7110)	grad_norm 1.2431 (1.2789)	
[2022-01-21 01:21:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1060/1251]	eta 0:07:00 lr 0.000712	time 2.2457 (2.2033)	loss 2.8977 (3.7075)	grad_norm 1.2018 (1.2786)	
[2022-01-21 01:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1070/1251]	eta 0:06:38 lr 0.000712	time 2.2108 (2.2030)	loss 4.3996 (3.7082)	grad_norm 1.1678 (1.2782)	
[2022-01-21 01:22:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1080/1251]	eta 0:06:16 lr 0.000712	time 2.2576 (2.2031)	loss 4.1250 (3.7106)	grad_norm 1.2100 (1.2777)	
[2022-01-21 01:22:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1090/1251]	eta 0:05:54 lr 0.000712	time 2.0130 (2.2033)	loss 3.7930 (3.7126)	grad_norm 1.6434 (1.2774)	
[2022-01-21 01:23:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1100/1251]	eta 0:05:32 lr 0.000712	time 1.9363 (2.2020)	loss 3.2673 (3.7131)	grad_norm 1.2523 (1.2774)	
[2022-01-21 01:23:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1110/1251]	eta 0:05:10 lr 0.000712	time 2.3387 (2.2016)	loss 4.1356 (3.7131)	grad_norm 1.3084 (1.2782)	
[2022-01-21 01:23:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1120/1251]	eta 0:04:48 lr 0.000712	time 1.9586 (2.2002)	loss 4.0213 (3.7137)	grad_norm 1.2623 (1.2781)	
[2022-01-21 01:24:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1130/1251]	eta 0:04:26 lr 0.000712	time 2.0222 (2.1991)	loss 3.4685 (3.7107)	grad_norm 1.4555 (1.2781)	
[2022-01-21 01:24:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1140/1251]	eta 0:04:04 lr 0.000711	time 1.6178 (2.1985)	loss 3.9596 (3.7098)	grad_norm 1.1712 (1.2779)	
[2022-01-21 01:24:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1150/1251]	eta 0:03:42 lr 0.000711	time 2.6828 (2.1996)	loss 3.7172 (3.7114)	grad_norm 1.4746 (1.2784)	
[2022-01-21 01:25:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1160/1251]	eta 0:03:20 lr 0.000711	time 2.8903 (2.2007)	loss 4.4699 (3.7141)	grad_norm 1.4806 (1.2793)	
[2022-01-21 01:25:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1170/1251]	eta 0:02:58 lr 0.000711	time 1.6884 (2.2018)	loss 4.1850 (3.7163)	grad_norm 1.1925 (1.2792)	
[2022-01-21 01:26:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1180/1251]	eta 0:02:36 lr 0.000711	time 1.7916 (2.2025)	loss 4.2293 (3.7169)	grad_norm 1.2922 (1.2800)	
[2022-01-21 01:26:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1190/1251]	eta 0:02:14 lr 0.000711	time 1.8782 (2.2032)	loss 3.0148 (3.7176)	grad_norm 1.1499 (1.2805)	
[2022-01-21 01:26:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1200/1251]	eta 0:01:52 lr 0.000711	time 3.1314 (2.2027)	loss 3.0761 (3.7183)	grad_norm 1.2188 (1.2802)	
[2022-01-21 01:27:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1210/1251]	eta 0:01:30 lr 0.000711	time 2.1931 (2.2015)	loss 4.2538 (3.7167)	grad_norm 1.2213 (1.2798)	
[2022-01-21 01:27:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1220/1251]	eta 0:01:08 lr 0.000711	time 2.2114 (2.1998)	loss 3.5259 (3.7174)	grad_norm 1.1241 (1.2801)	
[2022-01-21 01:27:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1230/1251]	eta 0:00:46 lr 0.000711	time 2.2482 (2.1983)	loss 3.7163 (3.7190)	grad_norm 1.2731 (1.2804)	
[2022-01-21 01:28:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1240/1251]	eta 0:00:24 lr 0.000711	time 1.6730 (2.1990)	loss 3.4287 (3.7190)	grad_norm 1.2827 (1.2804)	
[2022-01-21 01:28:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [108/300][1250/1251]	eta 0:00:02 lr 0.000711	time 1.2880 (2.1934)	loss 3.9799 (3.7207)	grad_norm 1.2843 (1.2804)	
[2022-01-21 01:28:31 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 108 training takes 0:45:44
[2022-01-21 01:28:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.712 (18.712)	Loss 1.1144 (1.1144)	Acc@1 73.340 (73.340)	Acc@5 91.211 (91.211)	
[2022-01-21 01:29:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.319 (3.219)	Loss 1.0935 (1.0923)	Acc@1 72.168 (73.917)	Acc@5 93.262 (92.356)	
[2022-01-21 01:29:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.641 (2.547)	Loss 1.1945 (1.1028)	Acc@1 71.875 (73.772)	Acc@5 90.723 (92.188)	
[2022-01-21 01:29:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.572 (2.328)	Loss 1.0149 (1.0846)	Acc@1 76.172 (74.162)	Acc@5 94.531 (92.468)	
[2022-01-21 01:30:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 5.037 (2.186)	Loss 1.1054 (1.0898)	Acc@1 74.121 (74.021)	Acc@5 92.480 (92.452)	
[2022-01-21 01:30:07 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.076 Acc@5 92.410
[2022-01-21 01:30:07 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.1%
[2022-01-21 01:30:07 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.23%
[2022-01-21 01:30:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][0/1251]	eta 7:31:29 lr 0.000711	time 21.6540 (21.6540)	loss 3.4089 (3.4089)	grad_norm 1.1617 (1.1617)	
[2022-01-21 01:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][10/1251]	eta 1:23:33 lr 0.000711	time 1.5424 (4.0402)	loss 4.3264 (3.5265)	grad_norm 1.2256 (1.2304)	
[2022-01-21 01:31:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][20/1251]	eta 1:04:22 lr 0.000711	time 2.0895 (3.1375)	loss 3.2042 (3.5417)	grad_norm 1.1555 (1.2383)	
[2022-01-21 01:31:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][30/1251]	eta 0:56:36 lr 0.000711	time 1.5822 (2.7815)	loss 2.9705 (3.5423)	grad_norm 1.1456 (1.2423)	
[2022-01-21 01:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][40/1251]	eta 0:54:33 lr 0.000711	time 3.9737 (2.7033)	loss 3.9258 (3.6104)	grad_norm 1.1387 (1.2445)	
[2022-01-21 01:32:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][50/1251]	eta 0:51:29 lr 0.000711	time 1.3720 (2.5727)	loss 3.8328 (3.6286)	grad_norm 1.2881 (1.2459)	
[2022-01-21 01:32:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][60/1251]	eta 0:49:24 lr 0.000711	time 2.5967 (2.4890)	loss 3.8689 (3.6702)	grad_norm 1.2103 (1.2514)	
[2022-01-21 01:33:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][70/1251]	eta 0:47:43 lr 0.000711	time 2.2588 (2.4250)	loss 2.8862 (3.6492)	grad_norm 1.1840 (1.2625)	
[2022-01-21 01:33:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][80/1251]	eta 0:47:37 lr 0.000711	time 5.3752 (2.4399)	loss 3.8629 (3.6328)	grad_norm 1.3375 (1.2566)	
[2022-01-21 01:33:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][90/1251]	eta 0:46:35 lr 0.000711	time 1.4600 (2.4081)	loss 3.2457 (3.6081)	grad_norm 1.4128 (1.2608)	
[2022-01-21 01:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][100/1251]	eta 0:45:56 lr 0.000711	time 2.8202 (2.3952)	loss 3.3170 (3.6121)	grad_norm 1.1721 (1.2587)	
[2022-01-21 01:34:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][110/1251]	eta 0:44:56 lr 0.000711	time 1.7460 (2.3636)	loss 3.0216 (3.6066)	grad_norm 1.1869 (1.2557)	
[2022-01-21 01:34:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][120/1251]	eta 0:44:15 lr 0.000711	time 2.5298 (2.3478)	loss 2.8025 (3.6074)	grad_norm 1.3613 (1.2532)	
[2022-01-21 01:35:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][130/1251]	eta 0:43:46 lr 0.000711	time 2.0291 (2.3433)	loss 4.4148 (3.6070)	grad_norm 1.3731 (1.2517)	
[2022-01-21 01:35:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][140/1251]	eta 0:43:23 lr 0.000711	time 2.8052 (2.3434)	loss 2.4794 (3.5769)	grad_norm 1.4373 (1.2561)	
[2022-01-21 01:35:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][150/1251]	eta 0:42:43 lr 0.000710	time 1.8860 (2.3283)	loss 4.0396 (3.5855)	grad_norm 1.2282 (1.2606)	
[2022-01-21 01:36:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][160/1251]	eta 0:42:16 lr 0.000710	time 2.5913 (2.3246)	loss 4.0417 (3.5646)	grad_norm 1.3538 (1.2616)	
[2022-01-21 01:36:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][170/1251]	eta 0:41:49 lr 0.000710	time 2.8704 (2.3219)	loss 3.9544 (3.5748)	grad_norm 1.3922 (1.2645)	
[2022-01-21 01:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][180/1251]	eta 0:41:19 lr 0.000710	time 2.1724 (2.3149)	loss 3.3065 (3.5814)	grad_norm 1.2723 (1.2635)	
[2022-01-21 01:37:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][190/1251]	eta 0:40:47 lr 0.000710	time 2.1954 (2.3068)	loss 4.0967 (3.5803)	grad_norm 1.4032 (1.2650)	
[2022-01-21 01:37:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][200/1251]	eta 0:40:12 lr 0.000710	time 2.5171 (2.2952)	loss 3.4609 (3.5870)	grad_norm 1.2228 (1.2641)	
[2022-01-21 01:38:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][210/1251]	eta 0:39:40 lr 0.000710	time 2.1689 (2.2866)	loss 3.9119 (3.6104)	grad_norm 1.2064 (1.2675)	
[2022-01-21 01:38:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][220/1251]	eta 0:39:14 lr 0.000710	time 2.2280 (2.2837)	loss 3.7698 (3.6292)	grad_norm 1.6782 (1.2694)	
[2022-01-21 01:38:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][230/1251]	eta 0:38:46 lr 0.000710	time 1.7036 (2.2784)	loss 4.0135 (3.6317)	grad_norm 1.2126 (1.2702)	
[2022-01-21 01:39:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][240/1251]	eta 0:38:23 lr 0.000710	time 1.8434 (2.2789)	loss 4.2359 (3.6414)	grad_norm 1.0591 (1.2693)	
[2022-01-21 01:39:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][250/1251]	eta 0:37:53 lr 0.000710	time 2.4517 (2.2710)	loss 2.8274 (3.6373)	grad_norm 1.2650 (1.2679)	
[2022-01-21 01:39:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][260/1251]	eta 0:37:19 lr 0.000710	time 1.7865 (2.2594)	loss 3.6851 (3.6389)	grad_norm 1.3126 (1.2663)	
[2022-01-21 01:40:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][270/1251]	eta 0:36:52 lr 0.000710	time 1.6465 (2.2553)	loss 3.3211 (3.6316)	grad_norm 1.1026 (1.2687)	
[2022-01-21 01:40:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][280/1251]	eta 0:36:27 lr 0.000710	time 2.8612 (2.2525)	loss 3.9808 (3.6326)	grad_norm 1.2041 (1.2701)	
[2022-01-21 01:41:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][290/1251]	eta 0:35:59 lr 0.000710	time 2.1041 (2.2474)	loss 3.8105 (3.6381)	grad_norm 1.1116 (1.2696)	
[2022-01-21 01:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][300/1251]	eta 0:35:41 lr 0.000710	time 1.6632 (2.2519)	loss 3.9344 (3.6264)	grad_norm 1.1086 (1.2688)	
[2022-01-21 01:41:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][310/1251]	eta 0:35:19 lr 0.000710	time 1.9318 (2.2528)	loss 3.1304 (3.6251)	grad_norm 1.2330 (1.2673)	
[2022-01-21 01:42:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][320/1251]	eta 0:35:02 lr 0.000710	time 2.1483 (2.2584)	loss 2.5423 (3.6219)	grad_norm 1.2781 (1.2667)	
[2022-01-21 01:42:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][330/1251]	eta 0:34:36 lr 0.000710	time 2.0980 (2.2548)	loss 4.2196 (3.6219)	grad_norm 1.4052 (1.2698)	
[2022-01-21 01:42:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][340/1251]	eta 0:34:07 lr 0.000710	time 1.6545 (2.2472)	loss 4.1089 (3.6242)	grad_norm 1.2601 (1.2709)	
[2022-01-21 01:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][350/1251]	eta 0:33:43 lr 0.000710	time 1.6771 (2.2453)	loss 3.8686 (3.6164)	grad_norm 1.1889 (1.2696)	
[2022-01-21 01:43:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][360/1251]	eta 0:33:22 lr 0.000710	time 2.2175 (2.2475)	loss 4.2247 (3.6239)	grad_norm 1.1891 (1.2677)	
[2022-01-21 01:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][370/1251]	eta 0:33:00 lr 0.000710	time 1.7269 (2.2481)	loss 2.7602 (3.6286)	grad_norm 1.3479 (1.2684)	
[2022-01-21 01:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][380/1251]	eta 0:32:36 lr 0.000710	time 1.8175 (2.2458)	loss 3.7406 (3.6273)	grad_norm 1.1076 (1.2671)	
[2022-01-21 01:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][390/1251]	eta 0:32:07 lr 0.000710	time 1.9507 (2.2392)	loss 3.5014 (3.6275)	grad_norm 1.3867 (1.2682)	
[2022-01-21 01:45:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][400/1251]	eta 0:31:45 lr 0.000710	time 1.8796 (2.2396)	loss 2.6282 (3.6323)	grad_norm 1.2796 (1.2690)	
[2022-01-21 01:45:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][410/1251]	eta 0:31:23 lr 0.000710	time 1.6797 (2.2398)	loss 4.0160 (3.6400)	grad_norm 1.6320 (1.2711)	
[2022-01-21 01:45:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][420/1251]	eta 0:30:59 lr 0.000709	time 1.5399 (2.2376)	loss 3.5871 (3.6423)	grad_norm 1.1512 (1.2729)	
[2022-01-21 01:46:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][430/1251]	eta 0:30:34 lr 0.000709	time 1.9842 (2.2344)	loss 2.9073 (3.6397)	grad_norm 1.2257 (1.2726)	
[2022-01-21 01:46:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][440/1251]	eta 0:30:12 lr 0.000709	time 2.2059 (2.2355)	loss 2.4761 (3.6373)	grad_norm 1.2820 (1.2713)	
[2022-01-21 01:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][450/1251]	eta 0:29:49 lr 0.000709	time 1.8815 (2.2346)	loss 3.7854 (3.6383)	grad_norm 1.3269 (1.2713)	
[2022-01-21 01:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][460/1251]	eta 0:29:24 lr 0.000709	time 1.8738 (2.2308)	loss 4.5719 (3.6373)	grad_norm 1.2677 (1.2738)	
[2022-01-21 01:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][470/1251]	eta 0:29:02 lr 0.000709	time 1.9906 (2.2317)	loss 2.9893 (3.6390)	grad_norm 1.5493 (1.2760)	
[2022-01-21 01:48:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][480/1251]	eta 0:28:40 lr 0.000709	time 1.6152 (2.2321)	loss 4.2954 (3.6440)	grad_norm 1.5848 (1.2763)	
[2022-01-21 01:48:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][490/1251]	eta 0:28:16 lr 0.000709	time 1.6132 (2.2291)	loss 4.3545 (3.6448)	grad_norm 1.2241 (1.2751)	
[2022-01-21 01:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][500/1251]	eta 0:27:52 lr 0.000709	time 1.8241 (2.2267)	loss 4.3158 (3.6495)	grad_norm 1.2227 (1.2745)	
[2022-01-21 01:49:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][510/1251]	eta 0:27:28 lr 0.000709	time 1.8860 (2.2244)	loss 4.1621 (3.6536)	grad_norm 1.4545 (1.2741)	
[2022-01-21 01:49:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][520/1251]	eta 0:27:07 lr 0.000709	time 1.7901 (2.2259)	loss 3.4306 (3.6566)	grad_norm 1.3197 (1.2767)	
[2022-01-21 01:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][530/1251]	eta 0:26:44 lr 0.000709	time 1.5469 (2.2250)	loss 4.6223 (3.6538)	grad_norm 1.1836 (1.2764)	
[2022-01-21 01:50:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][540/1251]	eta 0:26:22 lr 0.000709	time 2.6985 (2.2259)	loss 3.5744 (3.6530)	grad_norm 1.2218 (1.2763)	
[2022-01-21 01:50:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][550/1251]	eta 0:25:59 lr 0.000709	time 1.7638 (2.2245)	loss 4.4011 (3.6545)	grad_norm 1.1873 (1.2750)	
[2022-01-21 01:50:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][560/1251]	eta 0:25:39 lr 0.000709	time 2.7516 (2.2273)	loss 4.2604 (3.6529)	grad_norm 1.1817 (1.2743)	
[2022-01-21 01:51:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][570/1251]	eta 0:25:17 lr 0.000709	time 1.8225 (2.2280)	loss 4.2169 (3.6510)	grad_norm 1.4767 (1.2745)	
[2022-01-21 01:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][580/1251]	eta 0:24:53 lr 0.000709	time 2.2206 (2.2263)	loss 3.1066 (3.6517)	grad_norm 1.1715 (1.2744)	
[2022-01-21 01:52:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][590/1251]	eta 0:24:29 lr 0.000709	time 1.8089 (2.2229)	loss 3.1072 (3.6551)	grad_norm 1.1288 (1.2753)	
[2022-01-21 01:52:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][600/1251]	eta 0:24:05 lr 0.000709	time 1.8365 (2.2207)	loss 3.7394 (3.6536)	grad_norm 1.1871 (1.2751)	
[2022-01-21 01:52:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][610/1251]	eta 0:23:42 lr 0.000709	time 1.8079 (2.2184)	loss 4.0624 (3.6577)	grad_norm 1.2087 (1.2756)	
[2022-01-21 01:53:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][620/1251]	eta 0:23:17 lr 0.000709	time 1.9649 (2.2154)	loss 4.7847 (3.6605)	grad_norm 1.3611 (1.2756)	
[2022-01-21 01:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][630/1251]	eta 0:22:55 lr 0.000709	time 2.2770 (2.2151)	loss 4.5072 (3.6610)	grad_norm 1.4091 (1.2766)	
[2022-01-21 01:53:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][640/1251]	eta 0:22:33 lr 0.000709	time 2.4797 (2.2153)	loss 3.3609 (3.6621)	grad_norm 1.2043 (1.2768)	
[2022-01-21 01:54:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][650/1251]	eta 0:22:11 lr 0.000709	time 1.9124 (2.2160)	loss 3.9748 (3.6640)	grad_norm 1.3352 (1.2768)	
[2022-01-21 01:54:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][660/1251]	eta 0:21:50 lr 0.000709	time 2.2520 (2.2175)	loss 3.7430 (3.6619)	grad_norm 1.2040 (1.2768)	
[2022-01-21 01:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][670/1251]	eta 0:21:29 lr 0.000709	time 1.8823 (2.2197)	loss 4.1913 (3.6683)	grad_norm 1.2632 (1.2769)	
[2022-01-21 01:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][680/1251]	eta 0:21:07 lr 0.000708	time 2.1893 (2.2200)	loss 3.0133 (3.6663)	grad_norm 1.3758 (1.2772)	
[2022-01-21 01:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][690/1251]	eta 0:20:45 lr 0.000708	time 1.8867 (2.2202)	loss 4.1440 (3.6698)	grad_norm 1.3718 (1.2778)	
[2022-01-21 01:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][700/1251]	eta 0:20:22 lr 0.000708	time 1.6946 (2.2193)	loss 3.8375 (3.6704)	grad_norm 1.4299 (1.2786)	
[2022-01-21 01:56:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][710/1251]	eta 0:20:01 lr 0.000708	time 1.7861 (2.2204)	loss 3.6423 (3.6705)	grad_norm 1.1608 (1.2806)	
[2022-01-21 01:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][720/1251]	eta 0:19:37 lr 0.000708	time 1.9067 (2.2184)	loss 3.8706 (3.6705)	grad_norm 1.4900 (1.2815)	
[2022-01-21 01:57:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][730/1251]	eta 0:19:14 lr 0.000708	time 1.8568 (2.2166)	loss 3.6475 (3.6700)	grad_norm 1.3096 (1.2821)	
[2022-01-21 01:57:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][740/1251]	eta 0:18:52 lr 0.000708	time 2.1281 (2.2154)	loss 4.2665 (3.6700)	grad_norm 1.1353 (1.2840)	
[2022-01-21 01:57:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][750/1251]	eta 0:18:29 lr 0.000708	time 1.8994 (2.2142)	loss 4.3130 (3.6749)	grad_norm 1.1692 (1.2851)	
[2022-01-21 01:58:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][760/1251]	eta 0:18:07 lr 0.000708	time 2.2487 (2.2153)	loss 3.8750 (3.6728)	grad_norm 1.2705 (1.2848)	
[2022-01-21 01:58:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][770/1251]	eta 0:17:45 lr 0.000708	time 2.6843 (2.2161)	loss 3.5892 (3.6738)	grad_norm 1.3239 (1.2851)	
[2022-01-21 01:58:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][780/1251]	eta 0:17:23 lr 0.000708	time 1.7396 (2.2166)	loss 4.0611 (3.6721)	grad_norm 1.1211 (1.2854)	
[2022-01-21 01:59:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][790/1251]	eta 0:17:01 lr 0.000708	time 2.1817 (2.2163)	loss 2.4279 (3.6689)	grad_norm 1.2732 (1.2855)	
[2022-01-21 01:59:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][800/1251]	eta 0:16:39 lr 0.000708	time 2.0387 (2.2163)	loss 4.6402 (3.6713)	grad_norm 1.1753 (1.2846)	
[2022-01-21 02:00:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][810/1251]	eta 0:16:18 lr 0.000708	time 2.9385 (2.2179)	loss 3.0089 (3.6743)	grad_norm 1.3769 (1.2853)	
[2022-01-21 02:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][820/1251]	eta 0:15:54 lr 0.000708	time 1.7151 (2.2152)	loss 4.1493 (3.6740)	grad_norm 1.3432 (1.2849)	
[2022-01-21 02:00:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][830/1251]	eta 0:15:31 lr 0.000708	time 1.9389 (2.2136)	loss 4.4766 (3.6734)	grad_norm 1.2782 (1.2849)	
[2022-01-21 02:01:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][840/1251]	eta 0:15:09 lr 0.000708	time 2.1420 (2.2137)	loss 3.9826 (3.6725)	grad_norm 1.1524 (1.2838)	
[2022-01-21 02:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][850/1251]	eta 0:14:48 lr 0.000708	time 3.1679 (2.2157)	loss 3.3423 (3.6681)	grad_norm 1.3005 (1.2828)	
[2022-01-21 02:01:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][860/1251]	eta 0:14:25 lr 0.000708	time 2.0657 (2.2141)	loss 4.2957 (3.6698)	grad_norm 1.2316 (1.2830)	
[2022-01-21 02:02:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][870/1251]	eta 0:14:03 lr 0.000708	time 1.5427 (2.2127)	loss 2.7513 (3.6707)	grad_norm 1.3989 (1.2833)	
[2022-01-21 02:02:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][880/1251]	eta 0:13:40 lr 0.000708	time 2.2011 (2.2113)	loss 4.4496 (3.6692)	grad_norm 1.2801 (1.2847)	
[2022-01-21 02:02:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][890/1251]	eta 0:13:18 lr 0.000708	time 2.5339 (2.2121)	loss 4.0030 (3.6724)	grad_norm 1.3397 (1.2841)	
[2022-01-21 02:03:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][900/1251]	eta 0:12:56 lr 0.000708	time 1.9163 (2.2118)	loss 3.2788 (3.6701)	grad_norm 1.2794 (1.2858)	
[2022-01-21 02:03:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][910/1251]	eta 0:12:34 lr 0.000708	time 1.8488 (2.2117)	loss 3.8894 (3.6717)	grad_norm 1.2537 (1.2858)	
[2022-01-21 02:04:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][920/1251]	eta 0:12:11 lr 0.000708	time 1.9092 (2.2112)	loss 3.3164 (3.6732)	grad_norm 1.4431 (1.2853)	
[2022-01-21 02:04:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][930/1251]	eta 0:11:49 lr 0.000708	time 1.8752 (2.2098)	loss 4.1026 (3.6765)	grad_norm 1.2374 (1.2856)	
[2022-01-21 02:04:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][940/1251]	eta 0:11:26 lr 0.000708	time 1.8365 (2.2080)	loss 3.8451 (3.6777)	grad_norm 1.2425 (1.2853)	
[2022-01-21 02:05:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][950/1251]	eta 0:11:04 lr 0.000707	time 1.6160 (2.2072)	loss 3.2631 (3.6731)	grad_norm 1.1074 (1.2853)	
[2022-01-21 02:05:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][960/1251]	eta 0:10:42 lr 0.000707	time 1.6143 (2.2064)	loss 3.9594 (3.6711)	grad_norm 1.3295 (1.2845)	
[2022-01-21 02:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][970/1251]	eta 0:10:20 lr 0.000707	time 2.8322 (2.2077)	loss 2.2044 (3.6708)	grad_norm 1.2195 (1.2844)	
[2022-01-21 02:06:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][980/1251]	eta 0:09:58 lr 0.000707	time 1.7815 (2.2079)	loss 2.6258 (3.6713)	grad_norm 1.2770 (1.2840)	
[2022-01-21 02:06:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][990/1251]	eta 0:09:36 lr 0.000707	time 1.5248 (2.2086)	loss 3.9323 (3.6736)	grad_norm 1.1862 (1.2842)	
[2022-01-21 02:06:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1000/1251]	eta 0:09:14 lr 0.000707	time 2.0662 (2.2087)	loss 2.8519 (3.6723)	grad_norm 1.2063 (1.2846)	
[2022-01-21 02:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1010/1251]	eta 0:08:52 lr 0.000707	time 2.4999 (2.2078)	loss 3.2408 (3.6692)	grad_norm 1.3384 (1.2842)	
[2022-01-21 02:07:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1020/1251]	eta 0:08:29 lr 0.000707	time 1.6272 (2.2054)	loss 4.1827 (3.6684)	grad_norm 1.2265 (1.2838)	
[2022-01-21 02:08:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1030/1251]	eta 0:08:07 lr 0.000707	time 2.0295 (2.2057)	loss 2.8929 (3.6652)	grad_norm 1.3645 (1.2834)	
[2022-01-21 02:08:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1040/1251]	eta 0:07:45 lr 0.000707	time 1.8705 (2.2048)	loss 3.6623 (3.6658)	grad_norm 1.6664 (1.2834)	
[2022-01-21 02:08:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1050/1251]	eta 0:07:23 lr 0.000707	time 2.3223 (2.2044)	loss 3.2004 (3.6644)	grad_norm 1.1976 (1.2825)	
[2022-01-21 02:09:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1060/1251]	eta 0:07:01 lr 0.000707	time 2.1962 (2.2048)	loss 3.4560 (3.6647)	grad_norm 1.1110 (1.2824)	
[2022-01-21 02:09:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1070/1251]	eta 0:06:39 lr 0.000707	time 2.1862 (2.2065)	loss 3.2513 (3.6663)	grad_norm 1.1893 (1.2826)	
[2022-01-21 02:09:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1080/1251]	eta 0:06:17 lr 0.000707	time 1.7684 (2.2063)	loss 3.2284 (3.6669)	grad_norm 1.1472 (1.2835)	
[2022-01-21 02:10:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1090/1251]	eta 0:05:55 lr 0.000707	time 2.5110 (2.2052)	loss 4.0229 (3.6699)	grad_norm 1.2654 (1.2834)	
[2022-01-21 02:10:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1100/1251]	eta 0:05:32 lr 0.000707	time 1.8245 (2.2030)	loss 3.7223 (3.6689)	grad_norm 1.0881 (1.2839)	
[2022-01-21 02:10:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1110/1251]	eta 0:05:10 lr 0.000707	time 1.9771 (2.2015)	loss 4.1640 (3.6703)	grad_norm 1.2756 (1.2848)	
[2022-01-21 02:11:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1120/1251]	eta 0:04:48 lr 0.000707	time 2.2770 (2.2007)	loss 4.0308 (3.6700)	grad_norm 1.3561 (1.2848)	
[2022-01-21 02:11:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1130/1251]	eta 0:04:26 lr 0.000707	time 2.9438 (2.2002)	loss 4.1698 (3.6706)	grad_norm 1.3142 (1.2859)	
[2022-01-21 02:11:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1140/1251]	eta 0:04:04 lr 0.000707	time 2.1699 (2.1990)	loss 3.5186 (3.6702)	grad_norm 1.0479 (1.2851)	
[2022-01-21 02:12:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1150/1251]	eta 0:03:42 lr 0.000707	time 2.0052 (2.1991)	loss 4.2808 (3.6695)	grad_norm 1.4757 (1.2850)	
[2022-01-21 02:12:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1160/1251]	eta 0:03:20 lr 0.000707	time 2.9336 (2.2007)	loss 4.0763 (3.6698)	grad_norm 1.6043 (1.2856)	
[2022-01-21 02:13:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1170/1251]	eta 0:02:58 lr 0.000707	time 1.8986 (2.2006)	loss 3.0074 (3.6685)	grad_norm 1.4965 (1.2857)	
[2022-01-21 02:13:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1180/1251]	eta 0:02:36 lr 0.000707	time 2.1566 (2.2009)	loss 2.7380 (3.6686)	grad_norm 1.4512 (1.2856)	
[2022-01-21 02:13:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1190/1251]	eta 0:02:14 lr 0.000707	time 1.6986 (2.2003)	loss 3.7294 (3.6679)	grad_norm 1.3487 (1.2861)	
[2022-01-21 02:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1200/1251]	eta 0:01:52 lr 0.000707	time 2.1458 (2.2004)	loss 3.0086 (3.6669)	grad_norm 1.0999 (1.2855)	
[2022-01-21 02:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1210/1251]	eta 0:01:30 lr 0.000706	time 2.1524 (2.2001)	loss 3.4177 (3.6672)	grad_norm 1.1079 (1.2849)	
[2022-01-21 02:14:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1220/1251]	eta 0:01:08 lr 0.000706	time 2.5489 (2.2005)	loss 3.1716 (3.6677)	grad_norm 1.3457 (1.2855)	
[2022-01-21 02:15:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1230/1251]	eta 0:00:46 lr 0.000706	time 2.2100 (2.2012)	loss 3.9488 (3.6667)	grad_norm 1.3955 (1.2856)	
[2022-01-21 02:15:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1240/1251]	eta 0:00:24 lr 0.000706	time 1.7498 (2.2008)	loss 4.2633 (3.6676)	grad_norm 1.1513 (1.2859)	
[2022-01-21 02:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [109/300][1250/1251]	eta 0:00:02 lr 0.000706	time 1.1839 (2.1957)	loss 3.0463 (3.6668)	grad_norm 1.2145 (1.2855)	
[2022-01-21 02:15:55 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 109 training takes 0:45:47
[2022-01-21 02:16:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.304 (18.304)	Loss 1.0103 (1.0103)	Acc@1 74.609 (74.609)	Acc@5 93.750 (93.750)	
[2022-01-21 02:16:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.274 (3.322)	Loss 0.9434 (1.0681)	Acc@1 78.906 (74.494)	Acc@5 93.750 (92.658)	
[2022-01-21 02:16:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.139 (2.488)	Loss 1.0972 (1.0890)	Acc@1 73.633 (73.982)	Acc@5 93.066 (92.304)	
[2022-01-21 02:17:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.602 (2.208)	Loss 1.0223 (1.0903)	Acc@1 76.074 (74.061)	Acc@5 93.066 (92.273)	
[2022-01-21 02:17:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.970 (2.113)	Loss 1.0353 (1.0838)	Acc@1 75.586 (74.307)	Acc@5 92.773 (92.369)	
[2022-01-21 02:17:28 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.252 Acc@5 92.412
[2022-01-21 02:17:28 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.3%
[2022-01-21 02:17:28 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.25%
[2022-01-21 02:17:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][0/1251]	eta 7:27:23 lr 0.000706	time 21.4576 (21.4576)	loss 4.0841 (4.0841)	grad_norm 1.2325 (1.2325)	
[2022-01-21 02:18:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][10/1251]	eta 1:23:15 lr 0.000706	time 1.4799 (4.0250)	loss 2.7721 (3.7263)	grad_norm 1.3950 (1.3028)	
[2022-01-21 02:18:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][20/1251]	eta 1:02:19 lr 0.000706	time 1.9657 (3.0376)	loss 2.6521 (3.6985)	grad_norm 1.3023 (1.3141)	
[2022-01-21 02:18:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][30/1251]	eta 0:54:39 lr 0.000706	time 1.8758 (2.6858)	loss 3.8519 (3.7290)	grad_norm 1.2630 (1.3100)	
[2022-01-21 02:19:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][40/1251]	eta 0:54:07 lr 0.000706	time 6.7793 (2.6814)	loss 2.7613 (3.6790)	grad_norm 1.2432 (1.3358)	
[2022-01-21 02:19:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][50/1251]	eta 0:52:22 lr 0.000706	time 1.7749 (2.6162)	loss 3.4673 (3.6824)	grad_norm 1.2687 (1.3212)	
[2022-01-21 02:20:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][60/1251]	eta 0:50:57 lr 0.000706	time 1.8604 (2.5669)	loss 2.6767 (3.6971)	grad_norm 1.2328 (1.3063)	
[2022-01-21 02:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][70/1251]	eta 0:49:30 lr 0.000706	time 1.4464 (2.5156)	loss 4.1419 (3.6914)	grad_norm 1.2653 (1.3007)	
[2022-01-21 02:20:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][80/1251]	eta 0:48:32 lr 0.000706	time 2.4863 (2.4870)	loss 3.8262 (3.6890)	grad_norm 1.4700 (1.3026)	
[2022-01-21 02:21:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][90/1251]	eta 0:47:42 lr 0.000706	time 2.7074 (2.4656)	loss 3.7832 (3.6690)	grad_norm 1.4856 (1.3168)	
[2022-01-21 02:21:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][100/1251]	eta 0:46:30 lr 0.000706	time 2.1645 (2.4244)	loss 3.3425 (3.6686)	grad_norm 1.2154 (1.3143)	
[2022-01-21 02:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][110/1251]	eta 0:45:25 lr 0.000706	time 2.0086 (2.3890)	loss 3.1485 (3.6675)	grad_norm 1.1285 (1.3096)	
[2022-01-21 02:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][120/1251]	eta 0:44:33 lr 0.000706	time 2.6426 (2.3642)	loss 4.4288 (3.6800)	grad_norm 1.3797 (1.3116)	
[2022-01-21 02:22:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][130/1251]	eta 0:43:56 lr 0.000706	time 1.7596 (2.3515)	loss 4.2595 (3.6951)	grad_norm 1.4855 (1.3049)	
[2022-01-21 02:22:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][140/1251]	eta 0:43:19 lr 0.000706	time 2.1298 (2.3395)	loss 4.1127 (3.7063)	grad_norm 1.4887 (1.2997)	
[2022-01-21 02:23:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][150/1251]	eta 0:42:53 lr 0.000706	time 3.6507 (2.3375)	loss 3.8465 (3.6850)	grad_norm 1.1193 (1.3061)	
[2022-01-21 02:23:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][160/1251]	eta 0:42:27 lr 0.000706	time 2.7669 (2.3348)	loss 3.2198 (3.6836)	grad_norm 1.1270 (1.3073)	
[2022-01-21 02:24:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][170/1251]	eta 0:42:03 lr 0.000706	time 2.2021 (2.3347)	loss 2.8082 (3.6785)	grad_norm 1.1049 (1.3061)	
[2022-01-21 02:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][180/1251]	eta 0:41:26 lr 0.000706	time 1.9416 (2.3215)	loss 3.8938 (3.6868)	grad_norm 1.2215 (1.3055)	
[2022-01-21 02:24:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][190/1251]	eta 0:40:41 lr 0.000706	time 2.1549 (2.3015)	loss 3.5993 (3.6780)	grad_norm 1.3453 (1.3047)	
[2022-01-21 02:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][200/1251]	eta 0:40:10 lr 0.000706	time 1.8904 (2.2937)	loss 3.8886 (3.6847)	grad_norm 1.2475 (1.3032)	
[2022-01-21 02:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][210/1251]	eta 0:39:39 lr 0.000706	time 2.4848 (2.2862)	loss 3.9319 (3.6892)	grad_norm 1.3596 (1.2993)	
[2022-01-21 02:25:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][220/1251]	eta 0:39:05 lr 0.000706	time 1.6409 (2.2751)	loss 4.0117 (3.6915)	grad_norm 1.3655 (1.2982)	
[2022-01-21 02:26:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][230/1251]	eta 0:38:33 lr 0.000705	time 2.2803 (2.2662)	loss 3.2655 (3.6830)	grad_norm 1.3719 (1.2966)	
[2022-01-21 02:26:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][240/1251]	eta 0:38:06 lr 0.000705	time 2.0347 (2.2614)	loss 3.2727 (3.6830)	grad_norm 1.1801 (1.2998)	
[2022-01-21 02:26:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][250/1251]	eta 0:37:46 lr 0.000705	time 2.3246 (2.2645)	loss 2.7576 (3.6745)	grad_norm 1.3694 (1.2994)	
[2022-01-21 02:27:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][260/1251]	eta 0:37:30 lr 0.000705	time 1.9160 (2.2714)	loss 2.5079 (3.6718)	grad_norm 1.2645 (1.2986)	
[2022-01-21 02:27:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][270/1251]	eta 0:37:12 lr 0.000705	time 2.4619 (2.2759)	loss 3.6467 (3.6728)	grad_norm 1.2101 (1.2995)	
[2022-01-21 02:28:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][280/1251]	eta 0:36:49 lr 0.000705	time 2.2610 (2.2755)	loss 3.9764 (3.6730)	grad_norm 1.1776 (1.2964)	
[2022-01-21 02:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][290/1251]	eta 0:36:20 lr 0.000705	time 2.4028 (2.2691)	loss 4.1271 (3.6712)	grad_norm 1.4214 (1.2950)	
[2022-01-21 02:28:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][300/1251]	eta 0:35:49 lr 0.000705	time 1.9337 (2.2605)	loss 2.6272 (3.6658)	grad_norm 1.1241 (1.2963)	
[2022-01-21 02:29:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][310/1251]	eta 0:35:19 lr 0.000705	time 2.3992 (2.2520)	loss 4.0855 (3.6684)	grad_norm 1.3912 (1.2956)	
[2022-01-21 02:29:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][320/1251]	eta 0:34:55 lr 0.000705	time 2.8728 (2.2508)	loss 3.5900 (3.6629)	grad_norm 1.1459 (1.2946)	
[2022-01-21 02:29:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][330/1251]	eta 0:34:34 lr 0.000705	time 2.4896 (2.2522)	loss 3.4224 (3.6656)	grad_norm 1.1920 (1.2944)	
[2022-01-21 02:30:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][340/1251]	eta 0:34:08 lr 0.000705	time 1.8737 (2.2487)	loss 4.4431 (3.6627)	grad_norm 1.2832 (1.2930)	
[2022-01-21 02:30:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][350/1251]	eta 0:33:49 lr 0.000705	time 3.7533 (2.2523)	loss 3.7381 (3.6570)	grad_norm 1.3574 (1.2932)	
[2022-01-21 02:31:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][360/1251]	eta 0:33:28 lr 0.000705	time 2.7500 (2.2539)	loss 3.9104 (3.6545)	grad_norm 1.4561 (1.2921)	
[2022-01-21 02:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][370/1251]	eta 0:32:59 lr 0.000705	time 1.6340 (2.2468)	loss 3.6816 (3.6535)	grad_norm 1.2575 (1.2924)	
[2022-01-21 02:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][380/1251]	eta 0:32:32 lr 0.000705	time 2.2050 (2.2418)	loss 3.4808 (3.6556)	grad_norm 1.0977 (1.2932)	
[2022-01-21 02:32:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][390/1251]	eta 0:32:10 lr 0.000705	time 3.0350 (2.2420)	loss 4.6194 (3.6667)	grad_norm 1.4679 (1.2929)	
[2022-01-21 02:32:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][400/1251]	eta 0:31:48 lr 0.000705	time 3.3330 (2.2430)	loss 3.2095 (3.6702)	grad_norm 1.2107 (1.2952)	
[2022-01-21 02:32:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][410/1251]	eta 0:31:27 lr 0.000705	time 1.7349 (2.2441)	loss 2.7759 (3.6724)	grad_norm 1.6525 (1.2957)	
[2022-01-21 02:33:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][420/1251]	eta 0:31:04 lr 0.000705	time 2.8367 (2.2433)	loss 2.9745 (3.6741)	grad_norm 1.2285 (1.2996)	
[2022-01-21 02:33:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][430/1251]	eta 0:30:38 lr 0.000705	time 2.5673 (2.2389)	loss 4.0819 (3.6807)	grad_norm 1.2228 (1.3001)	
[2022-01-21 02:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][440/1251]	eta 0:30:10 lr 0.000705	time 1.9556 (2.2323)	loss 2.8486 (3.6753)	grad_norm 1.2540 (1.3007)	
[2022-01-21 02:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][450/1251]	eta 0:29:46 lr 0.000705	time 1.9410 (2.2302)	loss 2.5269 (3.6700)	grad_norm 1.1440 (1.2992)	
[2022-01-21 02:34:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][460/1251]	eta 0:29:23 lr 0.000705	time 2.7289 (2.2300)	loss 3.9333 (3.6732)	grad_norm 1.2457 (1.2988)	
[2022-01-21 02:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][470/1251]	eta 0:29:02 lr 0.000705	time 2.5919 (2.2309)	loss 3.9383 (3.6728)	grad_norm 1.5125 (1.2989)	
[2022-01-21 02:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][480/1251]	eta 0:28:40 lr 0.000705	time 2.5047 (2.2321)	loss 3.3991 (3.6747)	grad_norm 1.1051 (1.2987)	
[2022-01-21 02:35:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][490/1251]	eta 0:28:21 lr 0.000704	time 2.2835 (2.2353)	loss 3.6603 (3.6740)	grad_norm 1.2594 (1.2977)	
[2022-01-21 02:36:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][500/1251]	eta 0:27:58 lr 0.000704	time 1.8335 (2.2353)	loss 3.8457 (3.6765)	grad_norm 1.1157 (1.2963)	
[2022-01-21 02:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][510/1251]	eta 0:27:33 lr 0.000704	time 1.5472 (2.2314)	loss 2.9347 (3.6783)	grad_norm 1.1831 (1.2973)	
[2022-01-21 02:36:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][520/1251]	eta 0:27:08 lr 0.000704	time 1.8230 (2.2277)	loss 2.6819 (3.6792)	grad_norm 1.4215 (1.2977)	
[2022-01-21 02:37:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][530/1251]	eta 0:26:43 lr 0.000704	time 1.7009 (2.2245)	loss 4.0723 (3.6825)	grad_norm 1.4663 (1.2981)	
[2022-01-21 02:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][540/1251]	eta 0:26:22 lr 0.000704	time 2.2796 (2.2252)	loss 3.5016 (3.6850)	grad_norm 1.3698 (1.3009)	
[2022-01-21 02:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][550/1251]	eta 0:25:59 lr 0.000704	time 1.6654 (2.2254)	loss 3.6068 (3.6868)	grad_norm 1.2377 (1.2998)	
[2022-01-21 02:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][560/1251]	eta 0:25:36 lr 0.000704	time 3.0306 (2.2240)	loss 4.1787 (3.6833)	grad_norm 1.2515 (1.3007)	
[2022-01-21 02:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][570/1251]	eta 0:25:13 lr 0.000704	time 1.9236 (2.2229)	loss 2.7054 (3.6800)	grad_norm 1.5214 (1.3024)	
[2022-01-21 02:38:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][580/1251]	eta 0:24:50 lr 0.000704	time 2.1784 (2.2217)	loss 4.5366 (3.6802)	grad_norm 1.3132 (1.3028)	
[2022-01-21 02:39:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][590/1251]	eta 0:24:28 lr 0.000704	time 2.0760 (2.2223)	loss 3.9694 (3.6774)	grad_norm 1.4987 (1.3037)	
[2022-01-21 02:39:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][600/1251]	eta 0:24:06 lr 0.000704	time 3.3543 (2.2223)	loss 4.4118 (3.6796)	grad_norm 1.3199 (1.3050)	
[2022-01-21 02:40:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][610/1251]	eta 0:23:45 lr 0.000704	time 2.7067 (2.2233)	loss 3.2229 (3.6793)	grad_norm 1.3261 (1.3039)	
[2022-01-21 02:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][620/1251]	eta 0:23:23 lr 0.000704	time 2.7788 (2.2244)	loss 4.4210 (3.6799)	grad_norm 1.2980 (1.3037)	
[2022-01-21 02:40:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][630/1251]	eta 0:22:59 lr 0.000704	time 1.8559 (2.2220)	loss 3.8434 (3.6829)	grad_norm 1.1789 (1.3017)	
[2022-01-21 02:41:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][640/1251]	eta 0:22:38 lr 0.000704	time 2.9518 (2.2241)	loss 3.7243 (3.6834)	grad_norm 1.4389 (1.3010)	
[2022-01-21 02:41:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][650/1251]	eta 0:22:16 lr 0.000704	time 2.3528 (2.2233)	loss 3.9901 (3.6835)	grad_norm 1.2380 (1.3003)	
[2022-01-21 02:41:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][660/1251]	eta 0:21:53 lr 0.000704	time 1.9235 (2.2223)	loss 3.4765 (3.6794)	grad_norm 1.2295 (1.2993)	
[2022-01-21 02:42:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][670/1251]	eta 0:21:29 lr 0.000704	time 1.8926 (2.2193)	loss 3.9453 (3.6788)	grad_norm 1.2697 (1.2983)	
[2022-01-21 02:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][680/1251]	eta 0:21:05 lr 0.000704	time 2.3004 (2.2161)	loss 3.2266 (3.6761)	grad_norm 1.3103 (1.2980)	
[2022-01-21 02:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][690/1251]	eta 0:20:41 lr 0.000704	time 2.1181 (2.2123)	loss 4.1989 (3.6769)	grad_norm 1.2248 (1.2975)	
[2022-01-21 02:43:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][700/1251]	eta 0:20:17 lr 0.000704	time 2.6162 (2.2102)	loss 4.0735 (3.6742)	grad_norm 1.2467 (1.2967)	
[2022-01-21 02:43:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][710/1251]	eta 0:19:54 lr 0.000704	time 2.2214 (2.2082)	loss 4.1731 (3.6765)	grad_norm 1.2175 (1.2956)	
[2022-01-21 02:44:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][720/1251]	eta 0:19:34 lr 0.000704	time 3.0096 (2.2114)	loss 3.7444 (3.6787)	grad_norm 1.3556 (1.2947)	
[2022-01-21 02:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][730/1251]	eta 0:19:12 lr 0.000704	time 1.7902 (2.2125)	loss 4.2862 (3.6772)	grad_norm 1.2301 (1.2948)	
[2022-01-21 02:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][740/1251]	eta 0:18:50 lr 0.000704	time 2.6967 (2.2126)	loss 2.7094 (3.6720)	grad_norm 1.4171 (1.2945)	
[2022-01-21 02:45:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][750/1251]	eta 0:18:29 lr 0.000703	time 2.0281 (2.2141)	loss 4.0907 (3.6725)	grad_norm 1.1637 (1.2961)	
[2022-01-21 02:45:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][760/1251]	eta 0:18:07 lr 0.000703	time 2.0988 (2.2156)	loss 3.1428 (3.6688)	grad_norm 1.2805 (1.2971)	
[2022-01-21 02:45:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][770/1251]	eta 0:17:46 lr 0.000703	time 1.9631 (2.2179)	loss 3.8281 (3.6693)	grad_norm 1.3858 (1.2972)	
[2022-01-21 02:46:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][780/1251]	eta 0:17:24 lr 0.000703	time 2.5802 (2.2175)	loss 3.0986 (3.6676)	grad_norm 1.2126 (1.2969)	
[2022-01-21 02:46:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][790/1251]	eta 0:17:00 lr 0.000703	time 1.5452 (2.2147)	loss 4.2565 (3.6707)	grad_norm 1.3262 (1.2972)	
[2022-01-21 02:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][800/1251]	eta 0:16:37 lr 0.000703	time 1.8314 (2.2123)	loss 3.1437 (3.6692)	grad_norm 1.2807 (1.2970)	
[2022-01-21 02:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][810/1251]	eta 0:16:15 lr 0.000703	time 2.3223 (2.2126)	loss 2.6784 (3.6679)	grad_norm 1.2446 (1.2967)	
[2022-01-21 02:47:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][820/1251]	eta 0:15:53 lr 0.000703	time 1.9934 (2.2112)	loss 4.3052 (3.6680)	grad_norm 1.6020 (1.2982)	
[2022-01-21 02:48:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][830/1251]	eta 0:15:30 lr 0.000703	time 1.7443 (2.2097)	loss 4.0480 (3.6689)	grad_norm 1.3538 (1.2982)	
[2022-01-21 02:48:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][840/1251]	eta 0:15:07 lr 0.000703	time 1.9087 (2.2088)	loss 4.0490 (3.6718)	grad_norm 1.1086 (1.2970)	
[2022-01-21 02:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][850/1251]	eta 0:14:46 lr 0.000703	time 2.3006 (2.2101)	loss 3.9413 (3.6723)	grad_norm 1.4403 (1.2972)	
[2022-01-21 02:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][860/1251]	eta 0:14:24 lr 0.000703	time 1.8968 (2.2112)	loss 2.7886 (3.6729)	grad_norm 1.0878 (1.2969)	
[2022-01-21 02:49:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][870/1251]	eta 0:14:02 lr 0.000703	time 1.8830 (2.2117)	loss 2.7655 (3.6725)	grad_norm 1.2523 (1.2963)	
[2022-01-21 02:49:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][880/1251]	eta 0:13:40 lr 0.000703	time 1.7340 (2.2108)	loss 2.6654 (3.6715)	grad_norm 1.4016 (1.2990)	
[2022-01-21 02:50:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][890/1251]	eta 0:13:18 lr 0.000703	time 1.8552 (2.2123)	loss 3.8649 (3.6693)	grad_norm 1.8858 (1.3011)	
[2022-01-21 02:50:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][900/1251]	eta 0:12:56 lr 0.000703	time 1.8526 (2.2115)	loss 4.1273 (3.6684)	grad_norm 1.2291 (1.3021)	
[2022-01-21 02:51:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][910/1251]	eta 0:12:33 lr 0.000703	time 1.7522 (2.2109)	loss 3.8608 (3.6672)	grad_norm 1.2242 (1.3018)	
[2022-01-21 02:51:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][920/1251]	eta 0:12:11 lr 0.000703	time 1.9679 (2.2101)	loss 4.2389 (3.6682)	grad_norm 1.0943 (1.3014)	
[2022-01-21 02:51:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][930/1251]	eta 0:11:49 lr 0.000703	time 2.3629 (2.2099)	loss 4.3410 (3.6691)	grad_norm 1.2770 (1.3004)	
[2022-01-21 02:52:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][940/1251]	eta 0:11:27 lr 0.000703	time 1.8670 (2.2096)	loss 4.1216 (3.6667)	grad_norm 1.3007 (1.3006)	
[2022-01-21 02:52:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][950/1251]	eta 0:11:04 lr 0.000703	time 1.9210 (2.2091)	loss 3.1165 (3.6670)	grad_norm 1.1758 (1.3007)	
[2022-01-21 02:52:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][960/1251]	eta 0:10:42 lr 0.000703	time 2.0866 (2.2074)	loss 4.3717 (3.6660)	grad_norm 1.2543 (1.3009)	
[2022-01-21 02:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][970/1251]	eta 0:10:20 lr 0.000703	time 2.3955 (2.2069)	loss 4.0255 (3.6698)	grad_norm 1.7742 (1.3009)	
[2022-01-21 02:53:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][980/1251]	eta 0:09:58 lr 0.000703	time 2.0349 (2.2075)	loss 3.6046 (3.6698)	grad_norm 1.3411 (1.3007)	
[2022-01-21 02:53:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][990/1251]	eta 0:09:36 lr 0.000703	time 1.7973 (2.2072)	loss 2.6415 (3.6668)	grad_norm 1.1890 (1.3002)	
[2022-01-21 02:54:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1000/1251]	eta 0:09:14 lr 0.000703	time 1.8769 (2.2079)	loss 4.1371 (3.6635)	grad_norm 1.2573 (1.3004)	
[2022-01-21 02:54:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1010/1251]	eta 0:08:52 lr 0.000703	time 3.2300 (2.2079)	loss 3.9783 (3.6621)	grad_norm 1.2288 (1.3008)	
[2022-01-21 02:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1020/1251]	eta 0:08:29 lr 0.000702	time 1.9217 (2.2061)	loss 2.8554 (3.6601)	grad_norm 1.1766 (1.3006)	
[2022-01-21 02:55:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1030/1251]	eta 0:08:07 lr 0.000702	time 1.9589 (2.2048)	loss 3.2508 (3.6601)	grad_norm 1.3508 (1.3002)	
[2022-01-21 02:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1040/1251]	eta 0:07:45 lr 0.000702	time 2.7699 (2.2051)	loss 3.3446 (3.6593)	grad_norm 1.7005 (1.3006)	
[2022-01-21 02:56:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1050/1251]	eta 0:07:23 lr 0.000702	time 2.3506 (2.2068)	loss 4.5135 (3.6593)	grad_norm 1.2062 (1.3005)	
[2022-01-21 02:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1060/1251]	eta 0:07:01 lr 0.000702	time 2.1610 (2.2065)	loss 4.3749 (3.6591)	grad_norm 1.4090 (1.3006)	
[2022-01-21 02:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1070/1251]	eta 0:06:39 lr 0.000702	time 2.0948 (2.2049)	loss 3.9311 (3.6603)	grad_norm 1.3662 (1.3000)	
[2022-01-21 02:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1080/1251]	eta 0:06:16 lr 0.000702	time 3.1215 (2.2045)	loss 3.5324 (3.6588)	grad_norm 1.4298 (1.2998)	
[2022-01-21 02:57:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1090/1251]	eta 0:05:54 lr 0.000702	time 2.4169 (2.2031)	loss 3.9979 (3.6610)	grad_norm 1.3347 (1.3000)	
[2022-01-21 02:57:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1100/1251]	eta 0:05:32 lr 0.000702	time 1.9159 (2.2013)	loss 4.2602 (3.6582)	grad_norm 1.2615 (1.2996)	
[2022-01-21 02:58:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1110/1251]	eta 0:05:10 lr 0.000702	time 1.5979 (2.2002)	loss 3.7886 (3.6583)	grad_norm 1.2030 (1.2992)	
[2022-01-21 02:58:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1120/1251]	eta 0:04:48 lr 0.000702	time 1.8188 (2.2008)	loss 4.0573 (3.6593)	grad_norm 1.3769 (1.2991)	
[2022-01-21 02:59:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1130/1251]	eta 0:04:26 lr 0.000702	time 2.2969 (2.2027)	loss 4.0549 (3.6601)	grad_norm 1.1168 (1.2992)	
[2022-01-21 02:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1140/1251]	eta 0:04:04 lr 0.000702	time 2.2151 (2.2039)	loss 3.9920 (3.6617)	grad_norm 1.2404 (1.2984)	
[2022-01-21 02:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1150/1251]	eta 0:03:42 lr 0.000702	time 1.5384 (2.2038)	loss 3.0815 (3.6604)	grad_norm 1.3494 (1.2982)	
[2022-01-21 03:00:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1160/1251]	eta 0:03:20 lr 0.000702	time 2.1918 (2.2033)	loss 3.8979 (3.6591)	grad_norm 1.2119 (1.2984)	
[2022-01-21 03:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1170/1251]	eta 0:02:58 lr 0.000702	time 2.0356 (2.2033)	loss 2.9104 (3.6574)	grad_norm 1.1410 (1.2979)	
[2022-01-21 03:00:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1180/1251]	eta 0:02:36 lr 0.000702	time 1.9620 (2.2029)	loss 3.7655 (3.6584)	grad_norm 1.4078 (1.2975)	
[2022-01-21 03:01:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1190/1251]	eta 0:02:14 lr 0.000702	time 2.9614 (2.2031)	loss 3.9416 (3.6581)	grad_norm 1.2234 (1.2972)	
[2022-01-21 03:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1200/1251]	eta 0:01:52 lr 0.000702	time 1.7934 (2.2022)	loss 3.8265 (3.6574)	grad_norm 1.5591 (1.2978)	
[2022-01-21 03:01:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1210/1251]	eta 0:01:30 lr 0.000702	time 1.9706 (2.2007)	loss 4.1157 (3.6601)	grad_norm 1.5731 (1.2983)	
[2022-01-21 03:02:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1220/1251]	eta 0:01:08 lr 0.000702	time 1.5538 (2.1997)	loss 2.5767 (3.6583)	grad_norm 1.3178 (1.2984)	
[2022-01-21 03:02:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1230/1251]	eta 0:00:46 lr 0.000702	time 3.4633 (2.2006)	loss 3.4540 (3.6602)	grad_norm 1.2644 (1.2978)	
[2022-01-21 03:02:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1240/1251]	eta 0:00:24 lr 0.000702	time 1.4631 (2.2004)	loss 4.5184 (3.6601)	grad_norm 1.1947 (1.2976)	
[2022-01-21 03:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [110/300][1250/1251]	eta 0:00:02 lr 0.000702	time 1.1879 (2.1948)	loss 3.8386 (3.6592)	grad_norm 1.0667 (1.2974)	
[2022-01-21 03:03:15 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 110 training takes 0:45:46
[2022-01-21 03:03:15 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_110 saving......
[2022-01-21 03:03:26 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_110 saved !!!
[2022-01-21 03:03:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.360 (16.360)	Loss 1.0318 (1.0318)	Acc@1 76.270 (76.270)	Acc@5 93.262 (93.262)	
[2022-01-21 03:03:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.564 (2.764)	Loss 1.1205 (1.0771)	Acc@1 73.438 (74.627)	Acc@5 91.992 (92.543)	
[2022-01-21 03:04:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.645 (2.318)	Loss 1.1025 (1.0888)	Acc@1 73.340 (74.186)	Acc@5 92.578 (92.401)	
[2022-01-21 03:04:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.034 (2.104)	Loss 1.0342 (1.0946)	Acc@1 75.488 (74.197)	Acc@5 92.773 (92.203)	
[2022-01-21 03:04:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.815 (2.018)	Loss 1.0836 (1.0922)	Acc@1 73.242 (74.162)	Acc@5 92.188 (92.342)	
[2022-01-21 03:04:55 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.214 Acc@5 92.336
[2022-01-21 03:04:55 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.2%
[2022-01-21 03:04:55 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.25%
[2022-01-21 03:05:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][0/1251]	eta 7:46:06 lr 0.000702	time 22.3554 (22.3554)	loss 3.4609 (3.4609)	grad_norm 1.3444 (1.3444)	
[2022-01-21 03:05:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][10/1251]	eta 1:26:49 lr 0.000702	time 2.5832 (4.1976)	loss 4.2617 (3.7078)	grad_norm 1.1330 (1.2514)	
[2022-01-21 03:06:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][20/1251]	eta 1:06:05 lr 0.000702	time 2.0466 (3.2216)	loss 3.9192 (3.6238)	grad_norm 1.2708 (1.2723)	
[2022-01-21 03:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][30/1251]	eta 0:58:28 lr 0.000701	time 1.5840 (2.8731)	loss 2.9162 (3.5905)	grad_norm 1.4461 (1.2999)	
[2022-01-21 03:06:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][40/1251]	eta 0:54:56 lr 0.000701	time 3.5650 (2.7222)	loss 4.4391 (3.5629)	grad_norm 1.2623 (1.3020)	
[2022-01-21 03:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][50/1251]	eta 0:52:56 lr 0.000701	time 2.0073 (2.6452)	loss 4.5177 (3.5971)	grad_norm 1.2930 (1.3025)	
[2022-01-21 03:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][60/1251]	eta 0:51:10 lr 0.000701	time 1.5979 (2.5780)	loss 4.1846 (3.6465)	grad_norm 1.2285 (1.3014)	
[2022-01-21 03:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][70/1251]	eta 0:49:57 lr 0.000701	time 1.9549 (2.5384)	loss 3.8820 (3.6574)	grad_norm 1.2490 (1.3194)	
[2022-01-21 03:08:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][80/1251]	eta 0:49:20 lr 0.000701	time 3.3232 (2.5284)	loss 4.0480 (3.6579)	grad_norm 1.2189 (1.3124)	
[2022-01-21 03:08:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][90/1251]	eta 0:47:59 lr 0.000701	time 1.8933 (2.4801)	loss 3.2619 (3.6525)	grad_norm 1.3346 (1.3066)	
[2022-01-21 03:09:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][100/1251]	eta 0:46:47 lr 0.000701	time 1.8803 (2.4388)	loss 3.5190 (3.6635)	grad_norm 1.1914 (1.3043)	
[2022-01-21 03:09:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][110/1251]	eta 0:45:36 lr 0.000701	time 1.7322 (2.3986)	loss 3.8534 (3.6559)	grad_norm 1.2381 (1.2998)	
[2022-01-21 03:09:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][120/1251]	eta 0:44:41 lr 0.000701	time 2.5134 (2.3705)	loss 3.4685 (3.6638)	grad_norm 1.3564 (1.3048)	
[2022-01-21 03:10:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][130/1251]	eta 0:43:52 lr 0.000701	time 1.6406 (2.3481)	loss 3.3502 (3.6390)	grad_norm 1.6221 (1.3045)	
[2022-01-21 03:10:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][140/1251]	eta 0:43:19 lr 0.000701	time 2.1953 (2.3400)	loss 4.0329 (3.6312)	grad_norm 1.4327 (1.3014)	
[2022-01-21 03:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][150/1251]	eta 0:42:54 lr 0.000701	time 2.8434 (2.3381)	loss 3.5504 (3.6279)	grad_norm 1.2185 (1.2995)	
[2022-01-21 03:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][160/1251]	eta 0:42:44 lr 0.000701	time 2.9991 (2.3505)	loss 4.0080 (3.6302)	grad_norm 1.2245 (1.2973)	
[2022-01-21 03:11:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][170/1251]	eta 0:42:18 lr 0.000701	time 1.9080 (2.3480)	loss 4.5364 (3.6367)	grad_norm 1.5364 (1.2987)	
[2022-01-21 03:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][180/1251]	eta 0:41:45 lr 0.000701	time 1.9393 (2.3394)	loss 4.1434 (3.6472)	grad_norm 1.5296 (1.3019)	
[2022-01-21 03:12:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][190/1251]	eta 0:41:01 lr 0.000701	time 1.9638 (2.3203)	loss 2.9964 (3.6450)	grad_norm 1.1691 (1.2992)	
[2022-01-21 03:12:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][200/1251]	eta 0:40:28 lr 0.000701	time 2.3113 (2.3103)	loss 3.8831 (3.6493)	grad_norm 1.3788 (1.2971)	
[2022-01-21 03:13:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][210/1251]	eta 0:39:57 lr 0.000701	time 1.7072 (2.3029)	loss 4.0668 (3.6566)	grad_norm 1.2498 (1.2954)	
[2022-01-21 03:13:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][220/1251]	eta 0:39:27 lr 0.000701	time 1.6783 (2.2961)	loss 2.6782 (3.6590)	grad_norm 1.2716 (1.2963)	
[2022-01-21 03:13:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][230/1251]	eta 0:39:00 lr 0.000701	time 1.7054 (2.2920)	loss 2.7739 (3.6550)	grad_norm 1.4922 (1.2959)	
[2022-01-21 03:14:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][240/1251]	eta 0:38:37 lr 0.000701	time 2.5060 (2.2926)	loss 4.5306 (3.6587)	grad_norm 1.3187 (1.2978)	
[2022-01-21 03:14:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][250/1251]	eta 0:38:13 lr 0.000701	time 1.7602 (2.2910)	loss 4.3133 (3.6699)	grad_norm 1.3202 (1.2967)	
[2022-01-21 03:14:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][260/1251]	eta 0:37:51 lr 0.000701	time 1.7844 (2.2916)	loss 3.4461 (3.6810)	grad_norm 1.3454 (1.2972)	
[2022-01-21 03:15:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][270/1251]	eta 0:37:24 lr 0.000701	time 1.8615 (2.2881)	loss 3.0980 (3.6729)	grad_norm 1.1193 (1.2964)	
[2022-01-21 03:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][280/1251]	eta 0:36:53 lr 0.000701	time 1.7950 (2.2798)	loss 4.2165 (3.6655)	grad_norm 1.2660 (1.2963)	
[2022-01-21 03:15:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][290/1251]	eta 0:36:25 lr 0.000700	time 1.8812 (2.2740)	loss 3.5511 (3.6666)	grad_norm 1.1393 (1.2953)	
[2022-01-21 03:16:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][300/1251]	eta 0:36:02 lr 0.000700	time 1.8957 (2.2736)	loss 2.5928 (3.6592)	grad_norm 1.4570 (1.2980)	
[2022-01-21 03:16:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][310/1251]	eta 0:35:33 lr 0.000700	time 2.2151 (2.2673)	loss 4.0210 (3.6599)	grad_norm 1.1936 (1.2984)	
[2022-01-21 03:17:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][320/1251]	eta 0:35:06 lr 0.000700	time 2.3567 (2.2629)	loss 4.1700 (3.6608)	grad_norm 1.1406 (1.2969)	
[2022-01-21 03:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][330/1251]	eta 0:34:42 lr 0.000700	time 1.9152 (2.2607)	loss 3.9304 (3.6646)	grad_norm 1.1290 (1.2959)	
[2022-01-21 03:17:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][340/1251]	eta 0:34:19 lr 0.000700	time 1.9400 (2.2609)	loss 3.6470 (3.6538)	grad_norm 1.1888 (1.2949)	
[2022-01-21 03:18:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][350/1251]	eta 0:33:55 lr 0.000700	time 2.2552 (2.2590)	loss 4.1805 (3.6489)	grad_norm 1.4802 (1.2921)	
[2022-01-21 03:18:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][360/1251]	eta 0:33:29 lr 0.000700	time 2.2463 (2.2552)	loss 4.0510 (3.6417)	grad_norm 1.3748 (1.2930)	
[2022-01-21 03:18:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][370/1251]	eta 0:33:02 lr 0.000700	time 1.9499 (2.2508)	loss 4.0723 (3.6409)	grad_norm 1.3236 (1.2921)	
[2022-01-21 03:19:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][380/1251]	eta 0:32:40 lr 0.000700	time 1.7846 (2.2511)	loss 3.5651 (3.6400)	grad_norm 1.2107 (1.2914)	
[2022-01-21 03:19:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][390/1251]	eta 0:32:16 lr 0.000700	time 1.7537 (2.2491)	loss 4.2246 (3.6486)	grad_norm 1.3286 (1.2914)	
[2022-01-21 03:19:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][400/1251]	eta 0:31:57 lr 0.000700	time 2.9756 (2.2527)	loss 2.8857 (3.6492)	grad_norm 1.3874 (1.2932)	
[2022-01-21 03:20:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][410/1251]	eta 0:31:34 lr 0.000700	time 1.9069 (2.2523)	loss 4.5439 (3.6618)	grad_norm 1.2170 (1.2913)	
[2022-01-21 03:20:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][420/1251]	eta 0:31:11 lr 0.000700	time 2.8623 (2.2524)	loss 3.6622 (3.6667)	grad_norm 1.3964 (1.2918)	
[2022-01-21 03:21:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][430/1251]	eta 0:30:44 lr 0.000700	time 1.9429 (2.2463)	loss 3.7571 (3.6612)	grad_norm 1.1750 (1.2929)	
[2022-01-21 03:21:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][440/1251]	eta 0:30:17 lr 0.000700	time 1.6590 (2.2414)	loss 4.1506 (3.6654)	grad_norm 1.0777 (1.2949)	
[2022-01-21 03:21:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][450/1251]	eta 0:29:53 lr 0.000700	time 1.9309 (2.2390)	loss 2.6652 (3.6637)	grad_norm 1.3114 (1.2936)	
[2022-01-21 03:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][460/1251]	eta 0:29:33 lr 0.000700	time 3.7885 (2.2419)	loss 3.9968 (3.6650)	grad_norm 1.3636 (1.2926)	
[2022-01-21 03:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][470/1251]	eta 0:29:10 lr 0.000700	time 2.8203 (2.2419)	loss 3.8771 (3.6653)	grad_norm 1.5977 (1.2931)	
[2022-01-21 03:22:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][480/1251]	eta 0:28:48 lr 0.000700	time 2.7001 (2.2418)	loss 4.3867 (3.6649)	grad_norm 1.1819 (1.2923)	
[2022-01-21 03:23:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][490/1251]	eta 0:28:23 lr 0.000700	time 1.8329 (2.2383)	loss 3.1129 (3.6676)	grad_norm 1.4685 (1.2920)	
[2022-01-21 03:23:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][500/1251]	eta 0:27:58 lr 0.000700	time 1.6078 (2.2353)	loss 3.7142 (3.6666)	grad_norm 1.3319 (1.2936)	
[2022-01-21 03:23:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][510/1251]	eta 0:27:34 lr 0.000700	time 2.3093 (2.2329)	loss 3.4146 (3.6656)	grad_norm 1.1603 (1.2938)	
[2022-01-21 03:24:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][520/1251]	eta 0:27:11 lr 0.000700	time 2.3834 (2.2324)	loss 3.9256 (3.6684)	grad_norm 1.2459 (1.2947)	
[2022-01-21 03:24:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][530/1251]	eta 0:26:49 lr 0.000700	time 2.1226 (2.2321)	loss 3.9779 (3.6662)	grad_norm 1.2299 (1.2944)	
[2022-01-21 03:25:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][540/1251]	eta 0:26:26 lr 0.000700	time 2.3614 (2.2315)	loss 3.5427 (3.6687)	grad_norm 1.2470 (1.2966)	
[2022-01-21 03:25:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][550/1251]	eta 0:26:03 lr 0.000699	time 2.5359 (2.2297)	loss 3.7286 (3.6686)	grad_norm 1.4451 (1.2971)	
[2022-01-21 03:25:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][560/1251]	eta 0:25:40 lr 0.000699	time 1.9426 (2.2287)	loss 3.7177 (3.6692)	grad_norm 1.4030 (1.2988)	
[2022-01-21 03:26:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][570/1251]	eta 0:25:18 lr 0.000699	time 2.8209 (2.2301)	loss 3.8329 (3.6709)	grad_norm 1.6126 (1.3026)	
[2022-01-21 03:26:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][580/1251]	eta 0:24:56 lr 0.000699	time 2.2786 (2.2297)	loss 4.0089 (3.6733)	grad_norm 1.2300 (1.3020)	
[2022-01-21 03:26:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][590/1251]	eta 0:24:32 lr 0.000699	time 2.4790 (2.2283)	loss 4.0010 (3.6741)	grad_norm 1.7223 (1.3021)	
[2022-01-21 03:27:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][600/1251]	eta 0:24:07 lr 0.000699	time 2.0879 (2.2240)	loss 4.0347 (3.6752)	grad_norm 1.1492 (1.3043)	
[2022-01-21 03:27:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][610/1251]	eta 0:23:44 lr 0.000699	time 2.1762 (2.2216)	loss 4.3360 (3.6767)	grad_norm 1.3722 (1.3055)	
[2022-01-21 03:27:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][620/1251]	eta 0:23:22 lr 0.000699	time 2.8690 (2.2224)	loss 3.8388 (3.6758)	grad_norm 1.1833 (1.3035)	
[2022-01-21 03:28:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][630/1251]	eta 0:23:00 lr 0.000699	time 1.8814 (2.2225)	loss 3.5039 (3.6708)	grad_norm 1.4265 (1.3030)	
[2022-01-21 03:28:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][640/1251]	eta 0:22:38 lr 0.000699	time 1.7939 (2.2227)	loss 2.9702 (3.6755)	grad_norm 1.4697 (1.3022)	
[2022-01-21 03:29:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][650/1251]	eta 0:22:16 lr 0.000699	time 1.9944 (2.2237)	loss 3.9713 (3.6744)	grad_norm 1.5352 (1.3033)	
[2022-01-21 03:29:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][660/1251]	eta 0:21:54 lr 0.000699	time 2.2873 (2.2238)	loss 4.0063 (3.6731)	grad_norm 1.1755 (1.3035)	
[2022-01-21 03:29:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][670/1251]	eta 0:21:31 lr 0.000699	time 1.8084 (2.2226)	loss 4.4730 (3.6779)	grad_norm 1.2868 (1.3032)	
[2022-01-21 03:30:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][680/1251]	eta 0:21:08 lr 0.000699	time 1.5454 (2.2207)	loss 3.6132 (3.6807)	grad_norm 1.1736 (1.3029)	
[2022-01-21 03:30:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][690/1251]	eta 0:20:45 lr 0.000699	time 2.2044 (2.2203)	loss 3.8375 (3.6794)	grad_norm 1.1409 (1.3028)	
[2022-01-21 03:30:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][700/1251]	eta 0:20:21 lr 0.000699	time 2.2903 (2.2177)	loss 4.0435 (3.6802)	grad_norm 1.1698 (1.3018)	
[2022-01-21 03:31:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][710/1251]	eta 0:19:59 lr 0.000699	time 1.9053 (2.2166)	loss 3.0050 (3.6786)	grad_norm 1.3391 (1.3018)	
[2022-01-21 03:31:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][720/1251]	eta 0:19:35 lr 0.000699	time 1.5517 (2.2140)	loss 3.1665 (3.6779)	grad_norm 1.2721 (1.3020)	
[2022-01-21 03:31:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][730/1251]	eta 0:19:12 lr 0.000699	time 2.2228 (2.2120)	loss 3.9393 (3.6744)	grad_norm 1.2380 (1.3027)	
[2022-01-21 03:32:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][740/1251]	eta 0:18:49 lr 0.000699	time 2.1811 (2.2110)	loss 3.7414 (3.6726)	grad_norm 1.2270 (1.3028)	
[2022-01-21 03:32:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][750/1251]	eta 0:18:28 lr 0.000699	time 3.1294 (2.2129)	loss 4.3800 (3.6759)	grad_norm 1.5301 (1.3057)	
[2022-01-21 03:32:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][760/1251]	eta 0:18:06 lr 0.000699	time 1.3009 (2.2129)	loss 4.1040 (3.6787)	grad_norm 1.1827 (1.3065)	
[2022-01-21 03:33:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][770/1251]	eta 0:17:44 lr 0.000699	time 2.5047 (2.2141)	loss 4.4238 (3.6788)	grad_norm 1.2733 (1.3069)	
[2022-01-21 03:33:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][780/1251]	eta 0:17:23 lr 0.000699	time 2.0603 (2.2152)	loss 3.1881 (3.6792)	grad_norm 1.6942 (1.3082)	
[2022-01-21 03:34:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][790/1251]	eta 0:17:01 lr 0.000699	time 2.5905 (2.2151)	loss 4.2896 (3.6776)	grad_norm 1.4385 (1.3080)	
[2022-01-21 03:34:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][800/1251]	eta 0:16:38 lr 0.000699	time 1.8435 (2.2134)	loss 3.1130 (3.6761)	grad_norm 1.2815 (1.3082)	
[2022-01-21 03:34:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][810/1251]	eta 0:16:16 lr 0.000699	time 2.4937 (2.2133)	loss 3.9359 (3.6768)	grad_norm 1.0666 (1.3092)	
[2022-01-21 03:35:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][820/1251]	eta 0:15:53 lr 0.000698	time 1.8108 (2.2112)	loss 2.6998 (3.6759)	grad_norm 1.2106 (1.3090)	
[2022-01-21 03:35:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][830/1251]	eta 0:15:30 lr 0.000698	time 1.8876 (2.2103)	loss 4.4955 (3.6798)	grad_norm 1.3102 (1.3093)	
[2022-01-21 03:35:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][840/1251]	eta 0:15:08 lr 0.000698	time 1.8616 (2.2097)	loss 4.4094 (3.6789)	grad_norm 1.3704 (1.3091)	
[2022-01-21 03:36:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][850/1251]	eta 0:14:45 lr 0.000698	time 1.9993 (2.2088)	loss 3.6805 (3.6788)	grad_norm 1.0985 (1.3086)	
[2022-01-21 03:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][860/1251]	eta 0:14:23 lr 0.000698	time 1.9531 (2.2083)	loss 4.0957 (3.6771)	grad_norm 1.1846 (1.3081)	
[2022-01-21 03:36:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][870/1251]	eta 0:14:01 lr 0.000698	time 2.4760 (2.2075)	loss 4.3321 (3.6771)	grad_norm 1.3067 (1.3085)	
[2022-01-21 03:37:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][880/1251]	eta 0:13:38 lr 0.000698	time 2.3757 (2.2064)	loss 3.6668 (3.6762)	grad_norm 1.4009 (1.3087)	
[2022-01-21 03:37:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][890/1251]	eta 0:13:16 lr 0.000698	time 1.5724 (2.2069)	loss 3.2289 (3.6757)	grad_norm 1.2483 (1.3090)	
[2022-01-21 03:38:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][900/1251]	eta 0:12:55 lr 0.000698	time 2.5915 (2.2080)	loss 4.2804 (3.6742)	grad_norm 1.3819 (1.3088)	
[2022-01-21 03:38:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][910/1251]	eta 0:12:32 lr 0.000698	time 2.2053 (2.2072)	loss 4.2707 (3.6762)	grad_norm 1.3713 (1.3090)	
[2022-01-21 03:38:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][920/1251]	eta 0:12:10 lr 0.000698	time 1.9182 (2.2067)	loss 4.4887 (3.6797)	grad_norm 1.5354 (1.3098)	
[2022-01-21 03:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][930/1251]	eta 0:11:48 lr 0.000698	time 2.2055 (2.2068)	loss 3.7447 (3.6788)	grad_norm 1.4233 (1.3105)	
[2022-01-21 03:39:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][940/1251]	eta 0:11:26 lr 0.000698	time 2.2545 (2.2067)	loss 3.9177 (3.6792)	grad_norm 1.5530 (1.3118)	
[2022-01-21 03:39:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][950/1251]	eta 0:11:03 lr 0.000698	time 1.9615 (2.2049)	loss 2.7979 (3.6789)	grad_norm 1.2868 (1.3125)	
[2022-01-21 03:40:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][960/1251]	eta 0:10:41 lr 0.000698	time 2.3845 (2.2038)	loss 4.4159 (3.6792)	grad_norm 1.2827 (1.3130)	
[2022-01-21 03:40:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][970/1251]	eta 0:10:19 lr 0.000698	time 2.6449 (2.2041)	loss 4.2480 (3.6815)	grad_norm 1.1785 (1.3128)	
[2022-01-21 03:40:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][980/1251]	eta 0:09:57 lr 0.000698	time 2.1796 (2.2048)	loss 4.3431 (3.6845)	grad_norm 1.3611 (1.3122)	
[2022-01-21 03:41:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][990/1251]	eta 0:09:35 lr 0.000698	time 1.5712 (2.2053)	loss 3.0898 (3.6833)	grad_norm 1.2358 (1.3115)	
[2022-01-21 03:41:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1000/1251]	eta 0:09:13 lr 0.000698	time 1.9693 (2.2051)	loss 3.3459 (3.6855)	grad_norm 1.3582 (1.3118)	
[2022-01-21 03:42:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1010/1251]	eta 0:08:51 lr 0.000698	time 2.4494 (2.2054)	loss 4.2347 (3.6864)	grad_norm 1.1843 (1.3114)	
[2022-01-21 03:42:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1020/1251]	eta 0:08:29 lr 0.000698	time 2.2653 (2.2044)	loss 3.8394 (3.6886)	grad_norm 1.3493 (1.3123)	
[2022-01-21 03:42:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1030/1251]	eta 0:08:06 lr 0.000698	time 2.3434 (2.2030)	loss 4.6375 (3.6883)	grad_norm 1.3373 (1.3120)	
[2022-01-21 03:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1040/1251]	eta 0:07:44 lr 0.000698	time 1.6666 (2.2020)	loss 4.0672 (3.6906)	grad_norm 1.1638 (1.3111)	
[2022-01-21 03:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1050/1251]	eta 0:07:22 lr 0.000698	time 2.4976 (2.2029)	loss 2.9809 (3.6915)	grad_norm 1.3369 (1.3110)	
[2022-01-21 03:43:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1060/1251]	eta 0:07:01 lr 0.000698	time 3.1035 (2.2050)	loss 4.0320 (3.6940)	grad_norm 1.2868 (1.3107)	
[2022-01-21 03:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1070/1251]	eta 0:06:39 lr 0.000698	time 2.9867 (2.2060)	loss 3.8238 (3.6895)	grad_norm 1.2846 (1.3100)	
[2022-01-21 03:44:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1080/1251]	eta 0:06:16 lr 0.000697	time 1.6090 (2.2043)	loss 2.9295 (3.6909)	grad_norm 1.4483 (1.3097)	
[2022-01-21 03:44:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1090/1251]	eta 0:05:54 lr 0.000697	time 1.8559 (2.2033)	loss 3.6635 (3.6915)	grad_norm 1.2805 (1.3096)	
[2022-01-21 03:45:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1100/1251]	eta 0:05:32 lr 0.000697	time 1.8887 (2.2011)	loss 2.6959 (3.6883)	grad_norm 1.4404 (1.3098)	
[2022-01-21 03:45:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1110/1251]	eta 0:05:10 lr 0.000697	time 1.8080 (2.2001)	loss 2.6773 (3.6846)	grad_norm 1.3040 (1.3106)	
[2022-01-21 03:46:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1120/1251]	eta 0:04:48 lr 0.000697	time 1.9298 (2.2002)	loss 3.8967 (3.6842)	grad_norm 1.1593 (1.3104)	
[2022-01-21 03:46:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1130/1251]	eta 0:04:26 lr 0.000697	time 2.1469 (2.1997)	loss 3.7077 (3.6860)	grad_norm 1.3143 (1.3101)	
[2022-01-21 03:46:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1140/1251]	eta 0:04:04 lr 0.000697	time 2.4490 (2.2013)	loss 3.5081 (3.6843)	grad_norm 1.1134 (1.3094)	
[2022-01-21 03:47:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1150/1251]	eta 0:03:42 lr 0.000697	time 1.9244 (2.2015)	loss 3.9369 (3.6834)	grad_norm 1.1987 (1.3098)	
[2022-01-21 03:47:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1160/1251]	eta 0:03:20 lr 0.000697	time 2.2925 (2.2016)	loss 2.4680 (3.6839)	grad_norm 1.4068 (1.3104)	
[2022-01-21 03:47:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1170/1251]	eta 0:02:58 lr 0.000697	time 1.5471 (2.2006)	loss 3.5329 (3.6842)	grad_norm 1.2054 (1.3096)	
[2022-01-21 03:48:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1180/1251]	eta 0:02:36 lr 0.000697	time 1.8924 (2.2011)	loss 4.0037 (3.6861)	grad_norm 1.2366 (1.3093)	
[2022-01-21 03:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1190/1251]	eta 0:02:14 lr 0.000697	time 2.2356 (2.1996)	loss 2.3388 (3.6864)	grad_norm 1.4068 (1.3099)	
[2022-01-21 03:48:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1200/1251]	eta 0:01:52 lr 0.000697	time 1.9938 (2.1984)	loss 4.5706 (3.6897)	grad_norm 1.1959 (1.3098)	
[2022-01-21 03:49:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1210/1251]	eta 0:01:30 lr 0.000697	time 2.2414 (2.1983)	loss 3.1701 (3.6894)	grad_norm 1.2699 (1.3096)	
[2022-01-21 03:49:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1220/1251]	eta 0:01:08 lr 0.000697	time 2.5186 (2.1997)	loss 4.0878 (3.6902)	grad_norm 1.1483 (1.3086)	
[2022-01-21 03:50:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1230/1251]	eta 0:00:46 lr 0.000697	time 2.5183 (2.2002)	loss 3.5610 (3.6909)	grad_norm 1.2845 (1.3088)	
[2022-01-21 03:50:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1240/1251]	eta 0:00:24 lr 0.000697	time 1.6346 (2.1995)	loss 2.6658 (3.6884)	grad_norm 1.2315 (1.3080)	
[2022-01-21 03:50:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [111/300][1250/1251]	eta 0:00:02 lr 0.000697	time 1.3031 (2.1945)	loss 2.9591 (3.6873)	grad_norm 1.2522 (1.3076)	
[2022-01-21 03:50:41 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 111 training takes 0:45:45
[2022-01-21 03:50:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.026 (18.026)	Loss 1.1370 (1.1370)	Acc@1 72.656 (72.656)	Acc@5 92.383 (92.383)	
[2022-01-21 03:51:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.941 (3.499)	Loss 1.0608 (1.0767)	Acc@1 75.781 (74.956)	Acc@5 93.066 (92.862)	
[2022-01-21 03:51:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.301 (2.528)	Loss 1.1185 (1.1051)	Acc@1 73.242 (74.233)	Acc@5 93.066 (92.527)	
[2022-01-21 03:51:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.635 (2.202)	Loss 1.1044 (1.1024)	Acc@1 72.168 (74.260)	Acc@5 92.480 (92.487)	
[2022-01-21 03:52:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.801 (2.158)	Loss 1.1236 (1.1075)	Acc@1 72.363 (74.019)	Acc@5 93.359 (92.476)	
[2022-01-21 03:52:17 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.096 Acc@5 92.452
[2022-01-21 03:52:17 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.1%
[2022-01-21 03:52:17 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.25%
[2022-01-21 03:52:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][0/1251]	eta 7:39:41 lr 0.000697	time 22.0473 (22.0473)	loss 4.3669 (4.3669)	grad_norm 1.2917 (1.2917)	
[2022-01-21 03:53:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][10/1251]	eta 1:26:13 lr 0.000697	time 2.5156 (4.1686)	loss 3.5350 (3.7665)	grad_norm 1.2701 (1.2595)	
[2022-01-21 03:53:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][20/1251]	eta 1:05:06 lr 0.000697	time 1.5791 (3.1734)	loss 4.1203 (3.6764)	grad_norm 1.1825 (1.2339)	
[2022-01-21 03:53:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][30/1251]	eta 0:57:53 lr 0.000697	time 1.5092 (2.8446)	loss 2.8272 (3.6240)	grad_norm 1.3804 (1.2593)	
[2022-01-21 03:54:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][40/1251]	eta 0:55:29 lr 0.000697	time 5.3761 (2.7491)	loss 3.8857 (3.6358)	grad_norm 1.3110 (1.2733)	
[2022-01-21 03:54:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][50/1251]	eta 0:53:28 lr 0.000697	time 2.8817 (2.6715)	loss 3.5450 (3.6151)	grad_norm 1.4744 (1.2697)	
[2022-01-21 03:54:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][60/1251]	eta 0:51:22 lr 0.000697	time 2.5187 (2.5882)	loss 4.0057 (3.6217)	grad_norm 1.1486 (1.2650)	
[2022-01-21 03:55:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][70/1251]	eta 0:49:24 lr 0.000697	time 1.6695 (2.5101)	loss 4.3497 (3.6449)	grad_norm 1.1854 (1.2671)	
[2022-01-21 03:55:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][80/1251]	eta 0:48:10 lr 0.000697	time 2.7021 (2.4686)	loss 4.1816 (3.6512)	grad_norm 1.3380 (1.2699)	
[2022-01-21 03:55:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][90/1251]	eta 0:47:13 lr 0.000696	time 2.1620 (2.4409)	loss 2.4511 (3.6439)	grad_norm 1.2310 (1.2750)	
[2022-01-21 03:56:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][100/1251]	eta 0:46:26 lr 0.000696	time 2.7953 (2.4211)	loss 3.9718 (3.6554)	grad_norm 1.3356 (1.2753)	
[2022-01-21 03:56:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][110/1251]	eta 0:45:39 lr 0.000696	time 2.0665 (2.4006)	loss 3.6919 (3.6498)	grad_norm 1.3315 (1.2778)	
[2022-01-21 03:57:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][120/1251]	eta 0:45:02 lr 0.000696	time 2.5809 (2.3896)	loss 2.9180 (3.6354)	grad_norm 1.9700 (1.2824)	
[2022-01-21 03:57:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][130/1251]	eta 0:44:18 lr 0.000696	time 3.0451 (2.3712)	loss 3.8170 (3.6298)	grad_norm 1.6354 (1.2818)	
[2022-01-21 03:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][140/1251]	eta 0:43:29 lr 0.000696	time 1.7228 (2.3483)	loss 4.2531 (3.6392)	grad_norm 1.2609 (1.2846)	
[2022-01-21 03:58:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][150/1251]	eta 0:42:56 lr 0.000696	time 2.4067 (2.3399)	loss 3.8198 (3.6610)	grad_norm 1.2132 (1.2872)	
[2022-01-21 03:58:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][160/1251]	eta 0:42:27 lr 0.000696	time 2.1412 (2.3346)	loss 2.7357 (3.6641)	grad_norm 1.1968 (1.2846)	
[2022-01-21 03:58:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][170/1251]	eta 0:41:59 lr 0.000696	time 2.5145 (2.3305)	loss 4.0177 (3.6690)	grad_norm 1.2494 (1.2835)	
[2022-01-21 03:59:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][180/1251]	eta 0:41:16 lr 0.000696	time 1.7733 (2.3124)	loss 2.6585 (3.6497)	grad_norm 1.4101 (1.2827)	
[2022-01-21 03:59:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][190/1251]	eta 0:40:37 lr 0.000696	time 2.0305 (2.2973)	loss 3.7083 (3.6530)	grad_norm 1.2451 (1.2846)	
[2022-01-21 03:59:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][200/1251]	eta 0:40:10 lr 0.000696	time 2.7565 (2.2933)	loss 4.2446 (3.6559)	grad_norm 1.1349 (1.2870)	
[2022-01-21 04:00:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][210/1251]	eta 0:39:36 lr 0.000696	time 1.9440 (2.2833)	loss 3.6660 (3.6520)	grad_norm 1.3885 (1.2870)	
[2022-01-21 04:00:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][220/1251]	eta 0:39:09 lr 0.000696	time 1.8184 (2.2787)	loss 3.7055 (3.6537)	grad_norm 1.2683 (1.2857)	
[2022-01-21 04:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][230/1251]	eta 0:38:42 lr 0.000696	time 1.9932 (2.2747)	loss 4.3268 (3.6446)	grad_norm 1.3636 (1.2853)	
[2022-01-21 04:01:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][240/1251]	eta 0:38:17 lr 0.000696	time 3.2784 (2.2727)	loss 4.0894 (3.6447)	grad_norm 1.2828 (1.2844)	
[2022-01-21 04:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][250/1251]	eta 0:37:47 lr 0.000696	time 1.7049 (2.2653)	loss 3.3686 (3.6434)	grad_norm 1.1320 (1.2830)	
[2022-01-21 04:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][260/1251]	eta 0:37:22 lr 0.000696	time 2.2393 (2.2628)	loss 4.1478 (3.6393)	grad_norm 1.2343 (1.2815)	
[2022-01-21 04:02:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][270/1251]	eta 0:37:00 lr 0.000696	time 2.6215 (2.2634)	loss 4.2609 (3.6490)	grad_norm 1.2143 (1.2834)	
[2022-01-21 04:02:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][280/1251]	eta 0:36:32 lr 0.000696	time 2.1655 (2.2575)	loss 2.8683 (3.6436)	grad_norm 1.3283 (1.2838)	
[2022-01-21 04:03:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][290/1251]	eta 0:36:03 lr 0.000696	time 1.6963 (2.2508)	loss 4.3050 (3.6515)	grad_norm 1.4432 (1.2861)	
[2022-01-21 04:03:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][300/1251]	eta 0:35:38 lr 0.000696	time 2.5894 (2.2489)	loss 4.1322 (3.6495)	grad_norm 1.1920 (1.2880)	
[2022-01-21 04:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][310/1251]	eta 0:35:12 lr 0.000696	time 2.4149 (2.2448)	loss 4.2684 (3.6583)	grad_norm 1.2141 (1.2874)	
[2022-01-21 04:04:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][320/1251]	eta 0:34:49 lr 0.000696	time 3.4080 (2.2449)	loss 3.5242 (3.6514)	grad_norm 1.2159 (1.2883)	
[2022-01-21 04:04:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][330/1251]	eta 0:34:23 lr 0.000696	time 1.8409 (2.2401)	loss 3.6065 (3.6529)	grad_norm 1.3181 (1.2876)	
[2022-01-21 04:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][340/1251]	eta 0:33:56 lr 0.000696	time 2.2324 (2.2352)	loss 4.3637 (3.6514)	grad_norm 1.4306 (1.2886)	
[2022-01-21 04:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][350/1251]	eta 0:33:35 lr 0.000695	time 1.7173 (2.2370)	loss 4.4272 (3.6538)	grad_norm 1.2949 (1.2880)	
[2022-01-21 04:05:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][360/1251]	eta 0:33:13 lr 0.000695	time 2.3174 (2.2369)	loss 3.8388 (3.6566)	grad_norm 1.0724 (1.2876)	
[2022-01-21 04:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][370/1251]	eta 0:32:51 lr 0.000695	time 2.6013 (2.2382)	loss 4.0024 (3.6590)	grad_norm 1.2717 (1.2889)	
[2022-01-21 04:06:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][380/1251]	eta 0:32:28 lr 0.000695	time 1.8212 (2.2370)	loss 4.3707 (3.6617)	grad_norm 1.2039 (1.2901)	
[2022-01-21 04:06:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][390/1251]	eta 0:32:06 lr 0.000695	time 2.3567 (2.2372)	loss 3.6820 (3.6669)	grad_norm 1.4036 (1.2903)	
[2022-01-21 04:07:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][400/1251]	eta 0:31:44 lr 0.000695	time 1.7774 (2.2381)	loss 3.5102 (3.6714)	grad_norm 1.4517 (1.2912)	
[2022-01-21 04:07:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][410/1251]	eta 0:31:22 lr 0.000695	time 2.0973 (2.2386)	loss 2.7685 (3.6661)	grad_norm 1.2718 (1.2908)	
[2022-01-21 04:08:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][420/1251]	eta 0:31:00 lr 0.000695	time 2.2242 (2.2391)	loss 3.4814 (3.6680)	grad_norm 1.1447 (1.2926)	
[2022-01-21 04:08:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][430/1251]	eta 0:30:35 lr 0.000695	time 2.2596 (2.2351)	loss 3.7958 (3.6721)	grad_norm 1.3092 (1.2923)	
[2022-01-21 04:08:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][440/1251]	eta 0:30:08 lr 0.000695	time 2.2374 (2.2299)	loss 4.0763 (3.6737)	grad_norm 1.4783 (1.2931)	
[2022-01-21 04:09:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][450/1251]	eta 0:29:44 lr 0.000695	time 1.8815 (2.2278)	loss 3.8337 (3.6730)	grad_norm 1.2868 (1.2945)	
[2022-01-21 04:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][460/1251]	eta 0:29:21 lr 0.000695	time 2.2786 (2.2265)	loss 3.0845 (3.6693)	grad_norm 1.2815 (1.2950)	
[2022-01-21 04:09:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][470/1251]	eta 0:28:59 lr 0.000695	time 2.5482 (2.2275)	loss 4.0255 (3.6726)	grad_norm 1.2977 (1.2937)	
[2022-01-21 04:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][480/1251]	eta 0:28:34 lr 0.000695	time 1.7370 (2.2237)	loss 2.6419 (3.6687)	grad_norm 1.2145 (1.2928)	
[2022-01-21 04:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][490/1251]	eta 0:28:11 lr 0.000695	time 1.9098 (2.2232)	loss 3.7131 (3.6725)	grad_norm 1.1634 (1.2923)	
[2022-01-21 04:10:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][500/1251]	eta 0:27:50 lr 0.000695	time 2.0987 (2.2239)	loss 3.5853 (3.6744)	grad_norm 1.1038 (1.2919)	
[2022-01-21 04:11:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][510/1251]	eta 0:27:27 lr 0.000695	time 2.8216 (2.2228)	loss 3.6739 (3.6800)	grad_norm 1.0917 (1.2906)	
[2022-01-21 04:11:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][520/1251]	eta 0:27:02 lr 0.000695	time 1.9039 (2.2199)	loss 2.6186 (3.6798)	grad_norm 1.3077 (1.2908)	
[2022-01-21 04:11:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][530/1251]	eta 0:26:42 lr 0.000695	time 2.1157 (2.2224)	loss 2.8675 (3.6831)	grad_norm 1.4355 (1.2909)	
[2022-01-21 04:12:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][540/1251]	eta 0:26:20 lr 0.000695	time 1.8887 (2.2229)	loss 4.1977 (3.6844)	grad_norm 1.2997 (1.2927)	
[2022-01-21 04:12:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][550/1251]	eta 0:25:57 lr 0.000695	time 2.4153 (2.2222)	loss 4.2910 (3.6840)	grad_norm 1.1513 (1.2923)	
[2022-01-21 04:13:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][560/1251]	eta 0:25:33 lr 0.000695	time 1.9620 (2.2196)	loss 3.7916 (3.6793)	grad_norm 1.4420 (1.2918)	
[2022-01-21 04:13:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][570/1251]	eta 0:25:09 lr 0.000695	time 1.8942 (2.2170)	loss 3.9596 (3.6813)	grad_norm 1.3182 (1.2913)	
[2022-01-21 04:13:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][580/1251]	eta 0:24:45 lr 0.000695	time 1.9629 (2.2133)	loss 3.5980 (3.6783)	grad_norm 1.2196 (1.2907)	
[2022-01-21 04:14:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][590/1251]	eta 0:24:22 lr 0.000695	time 2.5212 (2.2122)	loss 4.1441 (3.6768)	grad_norm 1.3125 (1.2915)	
[2022-01-21 04:14:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][600/1251]	eta 0:23:59 lr 0.000695	time 2.1640 (2.2107)	loss 3.8948 (3.6786)	grad_norm 1.1483 (1.2935)	
[2022-01-21 04:14:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][610/1251]	eta 0:23:36 lr 0.000694	time 2.8984 (2.2099)	loss 4.0503 (3.6824)	grad_norm 1.2264 (1.2943)	
[2022-01-21 04:15:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][620/1251]	eta 0:23:13 lr 0.000694	time 2.1320 (2.2077)	loss 3.2259 (3.6756)	grad_norm 1.2123 (1.2937)	
[2022-01-21 04:15:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][630/1251]	eta 0:22:50 lr 0.000694	time 1.8743 (2.2070)	loss 3.6618 (3.6736)	grad_norm 1.3897 (1.2925)	
[2022-01-21 04:15:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][640/1251]	eta 0:22:29 lr 0.000694	time 2.7343 (2.2080)	loss 4.4188 (3.6739)	grad_norm 1.2036 (1.2916)	
[2022-01-21 04:16:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][650/1251]	eta 0:22:07 lr 0.000694	time 2.4088 (2.2093)	loss 3.7917 (3.6725)	grad_norm 1.3638 (1.2917)	
[2022-01-21 04:16:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][660/1251]	eta 0:21:44 lr 0.000694	time 1.5470 (2.2076)	loss 4.0741 (3.6731)	grad_norm 1.1318 (1.2903)	
[2022-01-21 04:16:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][670/1251]	eta 0:21:22 lr 0.000694	time 1.8227 (2.2075)	loss 2.6971 (3.6703)	grad_norm 1.2491 (1.2912)	
[2022-01-21 04:17:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][680/1251]	eta 0:21:01 lr 0.000694	time 3.3756 (2.2088)	loss 2.7226 (3.6686)	grad_norm 1.4056 (1.2928)	
[2022-01-21 04:17:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][690/1251]	eta 0:20:39 lr 0.000694	time 2.8218 (2.2087)	loss 3.4823 (3.6699)	grad_norm 1.4477 (1.2935)	
[2022-01-21 04:18:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][700/1251]	eta 0:20:17 lr 0.000694	time 2.2828 (2.2101)	loss 3.5184 (3.6727)	grad_norm 1.3398 (1.2926)	
[2022-01-21 04:18:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][710/1251]	eta 0:19:56 lr 0.000694	time 1.7567 (2.2111)	loss 3.6659 (3.6723)	grad_norm 1.3829 (1.2933)	
[2022-01-21 04:18:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][720/1251]	eta 0:19:34 lr 0.000694	time 2.3245 (2.2118)	loss 3.6540 (3.6715)	grad_norm 1.1997 (1.2927)	
[2022-01-21 04:19:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][730/1251]	eta 0:19:14 lr 0.000694	time 6.0746 (2.2150)	loss 3.3646 (3.6711)	grad_norm 1.1818 (1.2931)	
[2022-01-21 04:19:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][740/1251]	eta 0:18:53 lr 0.000694	time 1.6490 (2.2185)	loss 3.4592 (3.6685)	grad_norm 1.3720 (1.2950)	
[2022-01-21 04:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][750/1251]	eta 0:18:29 lr 0.000694	time 1.8852 (2.2139)	loss 4.0870 (3.6666)	grad_norm 1.3243 (1.2948)	
[2022-01-21 04:20:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][760/1251]	eta 0:18:06 lr 0.000694	time 1.9053 (2.2132)	loss 4.3048 (3.6696)	grad_norm 1.2206 (1.2952)	
[2022-01-21 04:20:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][770/1251]	eta 0:17:45 lr 0.000694	time 3.8865 (2.2155)	loss 4.3810 (3.6709)	grad_norm 1.7313 (1.2968)	
[2022-01-21 04:21:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][780/1251]	eta 0:17:22 lr 0.000694	time 1.6769 (2.2124)	loss 3.8667 (3.6704)	grad_norm 1.3458 (1.2979)	
[2022-01-21 04:21:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][790/1251]	eta 0:16:58 lr 0.000694	time 1.6791 (2.2095)	loss 3.4278 (3.6690)	grad_norm 1.1295 (1.2972)	
[2022-01-21 04:21:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][800/1251]	eta 0:16:35 lr 0.000694	time 2.0663 (2.2084)	loss 3.1952 (3.6682)	grad_norm 1.1875 (1.2969)	
[2022-01-21 04:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][810/1251]	eta 0:16:14 lr 0.000694	time 3.2747 (2.2097)	loss 3.9126 (3.6698)	grad_norm 1.2003 (1.2962)	
[2022-01-21 04:22:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][820/1251]	eta 0:15:52 lr 0.000694	time 2.5061 (2.2100)	loss 2.8301 (3.6718)	grad_norm 1.4624 (1.2978)	
[2022-01-21 04:22:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][830/1251]	eta 0:15:30 lr 0.000694	time 1.9387 (2.2101)	loss 3.6973 (3.6714)	grad_norm 1.1660 (1.2972)	
[2022-01-21 04:23:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][840/1251]	eta 0:15:08 lr 0.000694	time 1.7268 (2.2114)	loss 3.9805 (3.6713)	grad_norm 1.2972 (1.2977)	
[2022-01-21 04:23:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][850/1251]	eta 0:14:48 lr 0.000694	time 2.8632 (2.2145)	loss 3.6800 (3.6710)	grad_norm 1.2999 (1.2968)	
[2022-01-21 04:24:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][860/1251]	eta 0:14:24 lr 0.000694	time 1.9119 (2.2117)	loss 3.5353 (3.6703)	grad_norm 1.1806 (1.2962)	
[2022-01-21 04:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][870/1251]	eta 0:14:01 lr 0.000693	time 2.0378 (2.2097)	loss 3.4323 (3.6692)	grad_norm 1.2068 (1.2958)	
[2022-01-21 04:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][880/1251]	eta 0:13:39 lr 0.000693	time 1.9250 (2.2090)	loss 3.2960 (3.6675)	grad_norm 1.0370 (1.2957)	
[2022-01-21 04:25:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][890/1251]	eta 0:13:17 lr 0.000693	time 2.3094 (2.2079)	loss 3.8885 (3.6671)	grad_norm 1.2040 (1.2949)	
[2022-01-21 04:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][900/1251]	eta 0:12:54 lr 0.000693	time 2.3273 (2.2076)	loss 3.0396 (3.6673)	grad_norm 1.2650 (1.2947)	
[2022-01-21 04:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][910/1251]	eta 0:12:32 lr 0.000693	time 2.2068 (2.2070)	loss 3.7974 (3.6673)	grad_norm 1.3085 (1.2942)	
[2022-01-21 04:26:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][920/1251]	eta 0:12:10 lr 0.000693	time 2.2325 (2.2070)	loss 3.6825 (3.6685)	grad_norm 1.4233 (1.2945)	
[2022-01-21 04:26:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][930/1251]	eta 0:11:48 lr 0.000693	time 2.1443 (2.2075)	loss 4.2401 (3.6691)	grad_norm 1.2334 (1.2946)	
[2022-01-21 04:26:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][940/1251]	eta 0:11:26 lr 0.000693	time 1.8462 (2.2069)	loss 3.2945 (3.6686)	grad_norm 2.0171 (1.2953)	
[2022-01-21 04:27:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][950/1251]	eta 0:11:03 lr 0.000693	time 1.7028 (2.2058)	loss 2.4365 (3.6670)	grad_norm 1.0940 (1.2948)	
[2022-01-21 04:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][960/1251]	eta 0:10:41 lr 0.000693	time 2.4929 (2.2060)	loss 3.6708 (3.6673)	grad_norm 1.1953 (1.2946)	
[2022-01-21 04:28:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][970/1251]	eta 0:10:20 lr 0.000693	time 2.1738 (2.2067)	loss 3.4154 (3.6685)	grad_norm 1.6516 (1.2946)	
[2022-01-21 04:28:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][980/1251]	eta 0:09:57 lr 0.000693	time 2.3976 (2.2066)	loss 3.7245 (3.6684)	grad_norm 1.1298 (1.2939)	
[2022-01-21 04:28:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][990/1251]	eta 0:09:35 lr 0.000693	time 1.9796 (2.2058)	loss 3.1985 (3.6712)	grad_norm 1.6311 (1.2942)	
[2022-01-21 04:29:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1000/1251]	eta 0:09:13 lr 0.000693	time 1.9169 (2.2043)	loss 4.3513 (3.6746)	grad_norm 1.3651 (1.2939)	
[2022-01-21 04:29:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1010/1251]	eta 0:08:51 lr 0.000693	time 1.8404 (2.2042)	loss 4.1441 (3.6714)	grad_norm 1.2098 (1.2934)	
[2022-01-21 04:29:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1020/1251]	eta 0:08:29 lr 0.000693	time 1.5851 (2.2038)	loss 4.0352 (3.6741)	grad_norm 1.4025 (1.2939)	
[2022-01-21 04:30:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1030/1251]	eta 0:08:06 lr 0.000693	time 1.8641 (2.2033)	loss 3.3511 (3.6727)	grad_norm 1.4552 (1.2942)	
[2022-01-21 04:30:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1040/1251]	eta 0:07:45 lr 0.000693	time 2.6387 (2.2038)	loss 3.0448 (3.6712)	grad_norm 1.2912 (1.2936)	
[2022-01-21 04:30:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1050/1251]	eta 0:07:23 lr 0.000693	time 2.1823 (2.2041)	loss 2.8704 (3.6680)	grad_norm 1.1769 (1.2933)	
[2022-01-21 04:31:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1060/1251]	eta 0:07:00 lr 0.000693	time 2.1527 (2.2031)	loss 3.9277 (3.6687)	grad_norm 1.1957 (1.2934)	
[2022-01-21 04:31:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1070/1251]	eta 0:06:38 lr 0.000693	time 1.6000 (2.2015)	loss 3.9955 (3.6690)	grad_norm 1.2830 (1.2929)	
[2022-01-21 04:31:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1080/1251]	eta 0:06:16 lr 0.000693	time 1.9090 (2.2005)	loss 2.9018 (3.6702)	grad_norm 1.2708 (1.2928)	
[2022-01-21 04:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1090/1251]	eta 0:05:54 lr 0.000693	time 2.2163 (2.2004)	loss 4.0531 (3.6674)	grad_norm 1.2121 (1.2931)	
[2022-01-21 04:32:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1100/1251]	eta 0:05:32 lr 0.000693	time 2.4727 (2.2011)	loss 3.4565 (3.6645)	grad_norm 1.3581 (1.2934)	
[2022-01-21 04:33:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1110/1251]	eta 0:05:10 lr 0.000693	time 2.5707 (2.2020)	loss 3.1670 (3.6605)	grad_norm 1.3379 (1.2933)	
[2022-01-21 04:33:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1120/1251]	eta 0:04:48 lr 0.000693	time 2.2091 (2.2018)	loss 2.8563 (3.6599)	grad_norm 1.4525 (1.2932)	
[2022-01-21 04:33:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1130/1251]	eta 0:04:26 lr 0.000692	time 1.8363 (2.2010)	loss 4.0357 (3.6613)	grad_norm 1.2310 (1.2933)	
[2022-01-21 04:34:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1140/1251]	eta 0:04:04 lr 0.000692	time 1.9823 (2.2001)	loss 2.8441 (3.6589)	grad_norm 1.3382 (1.2933)	
[2022-01-21 04:34:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1150/1251]	eta 0:03:42 lr 0.000692	time 2.2848 (2.1994)	loss 3.3276 (3.6562)	grad_norm 1.1512 (1.2934)	
[2022-01-21 04:34:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1160/1251]	eta 0:03:20 lr 0.000692	time 1.9252 (2.1989)	loss 3.5800 (3.6555)	grad_norm 1.3030 (1.2938)	
[2022-01-21 04:35:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1170/1251]	eta 0:02:58 lr 0.000692	time 1.8031 (2.1984)	loss 3.9892 (3.6553)	grad_norm 1.0754 (1.2943)	
[2022-01-21 04:35:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1180/1251]	eta 0:02:36 lr 0.000692	time 3.6653 (2.2000)	loss 3.9249 (3.6555)	grad_norm 1.3374 (1.2944)	
[2022-01-21 04:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1190/1251]	eta 0:02:14 lr 0.000692	time 1.9143 (2.2007)	loss 3.3645 (3.6540)	grad_norm 1.1909 (1.2941)	
[2022-01-21 04:36:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1200/1251]	eta 0:01:52 lr 0.000692	time 2.3992 (2.2019)	loss 3.7441 (3.6559)	grad_norm 1.1835 (1.2935)	
[2022-01-21 04:36:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1210/1251]	eta 0:01:30 lr 0.000692	time 1.5561 (2.2015)	loss 4.0053 (3.6568)	grad_norm 1.3076 (1.2933)	
[2022-01-21 04:37:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1220/1251]	eta 0:01:08 lr 0.000692	time 2.4149 (2.2011)	loss 2.9838 (3.6538)	grad_norm 1.2045 (1.2932)	
[2022-01-21 04:37:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1230/1251]	eta 0:00:46 lr 0.000692	time 1.5897 (2.1997)	loss 4.1556 (3.6562)	grad_norm 1.1256 (1.2925)	
[2022-01-21 04:37:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1240/1251]	eta 0:00:24 lr 0.000692	time 1.9570 (2.1981)	loss 3.8067 (3.6550)	grad_norm 1.2510 (1.2923)	
[2022-01-21 04:38:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [112/300][1250/1251]	eta 0:00:02 lr 0.000692	time 1.1691 (2.1925)	loss 3.6952 (3.6554)	grad_norm 1.3241 (1.2921)	
[2022-01-21 04:38:00 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 112 training takes 0:45:43
[2022-01-21 04:38:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.311 (18.311)	Loss 1.1475 (1.1475)	Acc@1 74.609 (74.609)	Acc@5 91.016 (91.016)	
[2022-01-21 04:38:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.894 (3.225)	Loss 1.1345 (1.0983)	Acc@1 72.266 (74.245)	Acc@5 91.602 (92.489)	
[2022-01-21 04:38:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.600 (2.453)	Loss 1.1052 (1.0964)	Acc@1 72.363 (74.298)	Acc@5 92.090 (92.494)	
[2022-01-21 04:39:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.557 (2.212)	Loss 1.1050 (1.0969)	Acc@1 74.512 (74.408)	Acc@5 91.602 (92.440)	
[2022-01-21 04:39:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.775 (2.149)	Loss 1.1909 (1.0963)	Acc@1 71.094 (74.243)	Acc@5 91.211 (92.519)	
[2022-01-21 04:39:35 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.242 Acc@5 92.550
[2022-01-21 04:39:35 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.2%
[2022-01-21 04:39:35 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.25%
[2022-01-21 04:39:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][0/1251]	eta 7:05:26 lr 0.000692	time 20.4052 (20.4052)	loss 2.6393 (2.6393)	grad_norm 1.1985 (1.1985)	
[2022-01-21 04:40:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][10/1251]	eta 1:19:18 lr 0.000692	time 2.1578 (3.8346)	loss 3.8375 (3.6697)	grad_norm 1.4295 (1.3106)	
[2022-01-21 04:40:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][20/1251]	eta 1:03:23 lr 0.000692	time 1.6558 (3.0894)	loss 4.0274 (3.4762)	grad_norm 1.2599 (1.3208)	
[2022-01-21 04:41:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][30/1251]	eta 0:56:09 lr 0.000692	time 1.6557 (2.7598)	loss 3.4952 (3.5203)	grad_norm 1.3097 (1.3049)	
[2022-01-21 04:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][40/1251]	eta 0:54:11 lr 0.000692	time 3.7804 (2.6846)	loss 4.1722 (3.5225)	grad_norm 1.3178 (1.2941)	
[2022-01-21 04:41:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][50/1251]	eta 0:52:49 lr 0.000692	time 2.1757 (2.6391)	loss 3.9821 (3.5236)	grad_norm 1.4881 (1.3065)	
[2022-01-21 04:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][60/1251]	eta 0:51:16 lr 0.000692	time 2.0758 (2.5829)	loss 3.4085 (3.5486)	grad_norm 1.3818 (1.3038)	
[2022-01-21 04:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][70/1251]	eta 0:49:42 lr 0.000692	time 2.0367 (2.5252)	loss 4.2169 (3.5822)	grad_norm 1.5488 (1.3250)	
[2022-01-21 04:42:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][80/1251]	eta 0:48:23 lr 0.000692	time 1.9650 (2.4799)	loss 3.8959 (3.5824)	grad_norm 1.3057 (1.3181)	
[2022-01-21 04:43:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][90/1251]	eta 0:47:18 lr 0.000692	time 2.1992 (2.4450)	loss 3.9982 (3.5951)	grad_norm 1.7931 (1.3314)	
[2022-01-21 04:43:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][100/1251]	eta 0:46:11 lr 0.000692	time 2.4938 (2.4079)	loss 3.7912 (3.5936)	grad_norm 1.5692 (1.3343)	
[2022-01-21 04:43:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][110/1251]	eta 0:45:13 lr 0.000692	time 1.8800 (2.3781)	loss 2.6928 (3.5911)	grad_norm 1.3792 (1.3388)	
[2022-01-21 04:44:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][120/1251]	eta 0:44:17 lr 0.000692	time 1.8084 (2.3496)	loss 4.0644 (3.6042)	grad_norm 1.4027 (1.3413)	
[2022-01-21 04:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][130/1251]	eta 0:43:45 lr 0.000692	time 2.3261 (2.3425)	loss 3.5691 (3.6378)	grad_norm 1.2982 (1.3351)	
[2022-01-21 04:45:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][140/1251]	eta 0:43:08 lr 0.000691	time 1.9084 (2.3296)	loss 4.3246 (3.6371)	grad_norm 1.4930 (1.3323)	
[2022-01-21 04:45:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][150/1251]	eta 0:42:45 lr 0.000691	time 2.9595 (2.3300)	loss 2.7463 (3.6471)	grad_norm 1.3589 (1.3344)	
[2022-01-21 04:45:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][160/1251]	eta 0:42:14 lr 0.000691	time 1.5129 (2.3229)	loss 3.4380 (3.6405)	grad_norm 1.2296 (1.3355)	
[2022-01-21 04:46:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][170/1251]	eta 0:41:51 lr 0.000691	time 2.4114 (2.3230)	loss 2.4585 (3.6407)	grad_norm 1.6137 (1.3377)	
[2022-01-21 04:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][180/1251]	eta 0:41:15 lr 0.000691	time 1.7854 (2.3117)	loss 3.3436 (3.6470)	grad_norm 1.1191 (1.3356)	
[2022-01-21 04:46:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][190/1251]	eta 0:40:35 lr 0.000691	time 1.8918 (2.2957)	loss 3.3964 (3.6412)	grad_norm 1.1942 (1.3343)	
[2022-01-21 04:47:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][200/1251]	eta 0:40:02 lr 0.000691	time 2.3237 (2.2860)	loss 4.4572 (3.6458)	grad_norm 1.3833 (1.3354)	
[2022-01-21 04:47:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][210/1251]	eta 0:39:37 lr 0.000691	time 2.4335 (2.2836)	loss 3.8918 (3.6493)	grad_norm 1.2526 (1.3337)	
[2022-01-21 04:48:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][220/1251]	eta 0:39:13 lr 0.000691	time 2.1683 (2.2827)	loss 4.2708 (3.6568)	grad_norm 1.3375 (1.3332)	
[2022-01-21 04:48:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][230/1251]	eta 0:38:46 lr 0.000691	time 2.1444 (2.2783)	loss 4.1205 (3.6590)	grad_norm 1.5662 (1.3334)	
[2022-01-21 04:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][240/1251]	eta 0:38:19 lr 0.000691	time 2.2208 (2.2740)	loss 3.6209 (3.6571)	grad_norm 1.0922 (1.3327)	
[2022-01-21 04:49:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][250/1251]	eta 0:37:56 lr 0.000691	time 2.7483 (2.2737)	loss 3.1505 (3.6518)	grad_norm 1.2392 (1.3311)	
[2022-01-21 04:49:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][260/1251]	eta 0:37:29 lr 0.000691	time 1.9066 (2.2702)	loss 3.7071 (3.6561)	grad_norm 1.2492 (1.3281)	
[2022-01-21 04:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][270/1251]	eta 0:37:01 lr 0.000691	time 1.9128 (2.2645)	loss 3.1217 (3.6470)	grad_norm 1.1046 (1.3267)	
[2022-01-21 04:50:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][280/1251]	eta 0:36:34 lr 0.000691	time 2.9218 (2.2603)	loss 3.6475 (3.6499)	grad_norm 1.3607 (1.3277)	
[2022-01-21 04:50:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][290/1251]	eta 0:36:09 lr 0.000691	time 2.6904 (2.2574)	loss 3.8862 (3.6539)	grad_norm 1.2155 (1.3267)	
[2022-01-21 04:50:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][300/1251]	eta 0:35:46 lr 0.000691	time 2.2385 (2.2575)	loss 4.0894 (3.6617)	grad_norm 1.1210 (1.3275)	
[2022-01-21 04:51:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][310/1251]	eta 0:35:24 lr 0.000691	time 2.3330 (2.2576)	loss 4.0801 (3.6576)	grad_norm 1.2435 (1.3251)	
[2022-01-21 04:51:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][320/1251]	eta 0:34:59 lr 0.000691	time 2.7690 (2.2551)	loss 4.0449 (3.6584)	grad_norm 1.3814 (1.3236)	
[2022-01-21 04:51:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][330/1251]	eta 0:34:29 lr 0.000691	time 1.6314 (2.2474)	loss 4.4164 (3.6645)	grad_norm 1.3083 (1.3239)	
[2022-01-21 04:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][340/1251]	eta 0:34:00 lr 0.000691	time 1.9984 (2.2398)	loss 3.9824 (3.6680)	grad_norm 1.1526 (1.3213)	
[2022-01-21 04:52:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][350/1251]	eta 0:33:36 lr 0.000691	time 2.1645 (2.2377)	loss 3.1188 (3.6728)	grad_norm 1.3816 (1.3225)	
[2022-01-21 04:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][360/1251]	eta 0:33:11 lr 0.000691	time 2.6038 (2.2348)	loss 3.9790 (3.6776)	grad_norm 1.2196 (1.3206)	
[2022-01-21 04:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][370/1251]	eta 0:32:49 lr 0.000691	time 3.1662 (2.2352)	loss 2.5313 (3.6785)	grad_norm 1.2030 (1.3196)	
[2022-01-21 04:53:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][380/1251]	eta 0:32:28 lr 0.000691	time 1.5039 (2.2373)	loss 3.5709 (3.6807)	grad_norm 1.5302 (1.3210)	
[2022-01-21 04:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][390/1251]	eta 0:32:10 lr 0.000691	time 2.6690 (2.2418)	loss 2.7469 (3.6867)	grad_norm 1.3958 (1.3193)	
[2022-01-21 04:54:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][400/1251]	eta 0:31:48 lr 0.000690	time 2.4684 (2.2426)	loss 3.9612 (3.6864)	grad_norm 1.2114 (1.3196)	
[2022-01-21 04:54:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][410/1251]	eta 0:31:22 lr 0.000690	time 2.5370 (2.2386)	loss 3.3192 (3.6836)	grad_norm 1.3910 (1.3205)	
[2022-01-21 04:55:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][420/1251]	eta 0:30:54 lr 0.000690	time 1.8581 (2.2315)	loss 3.5579 (3.6813)	grad_norm 1.1990 (1.3197)	
[2022-01-21 04:55:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][430/1251]	eta 0:30:28 lr 0.000690	time 2.5178 (2.2268)	loss 3.4373 (3.6809)	grad_norm 1.2479 (1.3176)	
[2022-01-21 04:55:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][440/1251]	eta 0:30:02 lr 0.000690	time 1.8866 (2.2223)	loss 2.8923 (3.6771)	grad_norm 1.1780 (1.3168)	
[2022-01-21 04:56:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][450/1251]	eta 0:29:37 lr 0.000690	time 1.8679 (2.2195)	loss 4.0883 (3.6785)	grad_norm 1.2588 (1.3174)	
[2022-01-21 04:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][460/1251]	eta 0:29:17 lr 0.000690	time 2.2211 (2.2220)	loss 4.0293 (3.6771)	grad_norm 1.3414 (1.3182)	
[2022-01-21 04:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][470/1251]	eta 0:28:56 lr 0.000690	time 2.5347 (2.2238)	loss 4.0914 (3.6792)	grad_norm 1.2081 (1.3170)	
[2022-01-21 04:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][480/1251]	eta 0:28:32 lr 0.000690	time 1.8685 (2.2215)	loss 3.9810 (3.6794)	grad_norm 1.4597 (1.3167)	
[2022-01-21 04:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][490/1251]	eta 0:28:10 lr 0.000690	time 2.0269 (2.2217)	loss 3.5410 (3.6809)	grad_norm 1.4128 (1.3184)	
[2022-01-21 04:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][500/1251]	eta 0:27:47 lr 0.000690	time 2.2702 (2.2210)	loss 3.8763 (3.6817)	grad_norm 1.1203 (1.3176)	
[2022-01-21 04:58:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][510/1251]	eta 0:27:26 lr 0.000690	time 3.0501 (2.2221)	loss 2.4993 (3.6735)	grad_norm 1.2268 (1.3161)	
[2022-01-21 04:58:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][520/1251]	eta 0:27:04 lr 0.000690	time 1.9193 (2.2217)	loss 3.9119 (3.6772)	grad_norm 1.4804 (1.3173)	
[2022-01-21 04:59:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][530/1251]	eta 0:26:38 lr 0.000690	time 1.8727 (2.2178)	loss 4.0672 (3.6776)	grad_norm 1.4490 (1.3182)	
[2022-01-21 04:59:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][540/1251]	eta 0:26:14 lr 0.000690	time 1.9909 (2.2142)	loss 3.2887 (3.6769)	grad_norm 1.2086 (1.3183)	
[2022-01-21 04:59:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][550/1251]	eta 0:25:54 lr 0.000690	time 3.3240 (2.2175)	loss 3.6038 (3.6796)	grad_norm 1.2763 (1.3170)	
[2022-01-21 05:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][560/1251]	eta 0:25:32 lr 0.000690	time 2.6082 (2.2184)	loss 3.9851 (3.6808)	grad_norm 1.3501 (1.3151)	
[2022-01-21 05:00:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][570/1251]	eta 0:25:10 lr 0.000690	time 1.8251 (2.2179)	loss 4.7131 (3.6772)	grad_norm 1.4535 (1.3154)	
[2022-01-21 05:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][580/1251]	eta 0:24:47 lr 0.000690	time 1.9507 (2.2163)	loss 2.8796 (3.6742)	grad_norm 1.1524 (1.3146)	
[2022-01-21 05:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][590/1251]	eta 0:24:25 lr 0.000690	time 3.0839 (2.2170)	loss 4.2712 (3.6760)	grad_norm 1.6648 (1.3159)	
[2022-01-21 05:01:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][600/1251]	eta 0:24:02 lr 0.000690	time 2.1212 (2.2163)	loss 3.7921 (3.6742)	grad_norm 1.3235 (1.3170)	
[2022-01-21 05:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][610/1251]	eta 0:23:38 lr 0.000690	time 2.0071 (2.2135)	loss 3.3553 (3.6692)	grad_norm 1.3747 (1.3172)	
[2022-01-21 05:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][620/1251]	eta 0:23:15 lr 0.000690	time 1.9392 (2.2121)	loss 4.3712 (3.6703)	grad_norm 1.4384 (1.3176)	
[2022-01-21 05:02:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][630/1251]	eta 0:22:53 lr 0.000690	time 3.0883 (2.2125)	loss 2.6178 (3.6678)	grad_norm 1.4398 (1.3180)	
[2022-01-21 05:03:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][640/1251]	eta 0:22:31 lr 0.000690	time 2.6086 (2.2115)	loss 4.0482 (3.6669)	grad_norm 1.3544 (1.3178)	
[2022-01-21 05:03:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][650/1251]	eta 0:22:07 lr 0.000690	time 1.5785 (2.2083)	loss 4.3530 (3.6668)	grad_norm 1.4150 (1.3171)	
[2022-01-21 05:03:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][660/1251]	eta 0:21:44 lr 0.000689	time 1.6500 (2.2073)	loss 4.0399 (3.6656)	grad_norm 1.2620 (1.3158)	
[2022-01-21 05:04:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][670/1251]	eta 0:21:23 lr 0.000689	time 3.0410 (2.2089)	loss 3.0466 (3.6670)	grad_norm 1.2169 (1.3151)	
[2022-01-21 05:04:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][680/1251]	eta 0:21:01 lr 0.000689	time 2.2877 (2.2102)	loss 2.8234 (3.6642)	grad_norm 1.5720 (1.3151)	
[2022-01-21 05:05:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][690/1251]	eta 0:20:40 lr 0.000689	time 2.1100 (2.2106)	loss 3.3007 (3.6647)	grad_norm 1.3281 (1.3157)	
[2022-01-21 05:05:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][700/1251]	eta 0:20:17 lr 0.000689	time 1.9078 (2.2102)	loss 4.2822 (3.6653)	grad_norm 1.4005 (1.3156)	
[2022-01-21 05:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][710/1251]	eta 0:19:56 lr 0.000689	time 3.0756 (2.2110)	loss 3.8592 (3.6639)	grad_norm 1.4184 (1.3155)	
[2022-01-21 05:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][720/1251]	eta 0:19:32 lr 0.000689	time 1.8657 (2.2074)	loss 4.2516 (3.6641)	grad_norm 1.3339 (1.3166)	
[2022-01-21 05:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][730/1251]	eta 0:19:08 lr 0.000689	time 1.8787 (2.2046)	loss 3.4015 (3.6650)	grad_norm 1.4711 (1.3171)	
[2022-01-21 05:06:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][740/1251]	eta 0:18:46 lr 0.000689	time 2.2624 (2.2041)	loss 3.9714 (3.6671)	grad_norm 1.2650 (1.3167)	
[2022-01-21 05:07:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][750/1251]	eta 0:18:24 lr 0.000689	time 3.0475 (2.2045)	loss 4.5000 (3.6675)	grad_norm 1.7391 (1.3188)	
[2022-01-21 05:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][760/1251]	eta 0:18:02 lr 0.000689	time 2.0917 (2.2048)	loss 3.1606 (3.6678)	grad_norm 1.3615 (1.3200)	
[2022-01-21 05:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][770/1251]	eta 0:17:41 lr 0.000689	time 2.4755 (2.2062)	loss 4.5291 (3.6731)	grad_norm 1.5059 (1.3196)	
[2022-01-21 05:08:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][780/1251]	eta 0:17:18 lr 0.000689	time 1.7187 (2.2059)	loss 2.6084 (3.6711)	grad_norm 1.3071 (1.3208)	
[2022-01-21 05:08:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][790/1251]	eta 0:16:57 lr 0.000689	time 2.8104 (2.2079)	loss 4.5261 (3.6712)	grad_norm 1.2656 (1.3205)	
[2022-01-21 05:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][800/1251]	eta 0:16:36 lr 0.000689	time 2.1766 (2.2091)	loss 3.5809 (3.6727)	grad_norm 1.3728 (1.3193)	
[2022-01-21 05:09:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][810/1251]	eta 0:16:13 lr 0.000689	time 2.1697 (2.2070)	loss 3.8707 (3.6724)	grad_norm 1.1887 (1.3194)	
[2022-01-21 05:09:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][820/1251]	eta 0:15:49 lr 0.000689	time 2.1260 (2.2040)	loss 3.0694 (3.6733)	grad_norm 1.5975 (1.3191)	
[2022-01-21 05:10:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][830/1251]	eta 0:15:27 lr 0.000689	time 2.1632 (2.2032)	loss 4.1232 (3.6740)	grad_norm 1.2505 (1.3187)	
[2022-01-21 05:10:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][840/1251]	eta 0:15:04 lr 0.000689	time 1.8312 (2.2012)	loss 4.2014 (3.6734)	grad_norm 1.2407 (1.3187)	
[2022-01-21 05:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][850/1251]	eta 0:14:42 lr 0.000689	time 2.1420 (2.2007)	loss 2.7044 (3.6698)	grad_norm 1.3682 (1.3184)	
[2022-01-21 05:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][860/1251]	eta 0:14:21 lr 0.000689	time 2.4861 (2.2026)	loss 3.2545 (3.6701)	grad_norm 1.4664 (1.3190)	
[2022-01-21 05:11:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][870/1251]	eta 0:13:59 lr 0.000689	time 1.9111 (2.2028)	loss 3.9330 (3.6714)	grad_norm 1.3694 (1.3183)	
[2022-01-21 05:11:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][880/1251]	eta 0:13:37 lr 0.000689	time 2.1793 (2.2039)	loss 3.5491 (3.6681)	grad_norm 1.7059 (1.3206)	
[2022-01-21 05:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][890/1251]	eta 0:13:16 lr 0.000689	time 3.1825 (2.2055)	loss 3.1564 (3.6658)	grad_norm 1.2870 (1.3202)	
[2022-01-21 05:12:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][900/1251]	eta 0:12:54 lr 0.000689	time 1.9623 (2.2053)	loss 4.1318 (3.6681)	grad_norm 1.3452 (1.3203)	
[2022-01-21 05:13:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][910/1251]	eta 0:12:31 lr 0.000689	time 1.8659 (2.2053)	loss 4.1654 (3.6668)	grad_norm 1.2597 (1.3201)	
[2022-01-21 05:13:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][920/1251]	eta 0:12:09 lr 0.000688	time 1.9055 (2.2035)	loss 3.1788 (3.6685)	grad_norm 1.2390 (1.3197)	
[2022-01-21 05:13:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][930/1251]	eta 0:11:46 lr 0.000688	time 1.9540 (2.2024)	loss 3.8704 (3.6704)	grad_norm 1.2212 (1.3192)	
[2022-01-21 05:14:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][940/1251]	eta 0:11:24 lr 0.000688	time 1.8833 (2.2008)	loss 4.0146 (3.6695)	grad_norm 1.1844 (1.3186)	
[2022-01-21 05:14:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][950/1251]	eta 0:11:02 lr 0.000688	time 1.5900 (2.2009)	loss 3.3396 (3.6704)	grad_norm 1.3580 (1.3182)	
[2022-01-21 05:14:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][960/1251]	eta 0:10:40 lr 0.000688	time 2.7253 (2.2022)	loss 3.9009 (3.6705)	grad_norm 1.1711 (1.3180)	
[2022-01-21 05:15:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][970/1251]	eta 0:10:18 lr 0.000688	time 2.2841 (2.2027)	loss 3.3389 (3.6693)	grad_norm 1.3401 (1.3181)	
[2022-01-21 05:15:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][980/1251]	eta 0:09:57 lr 0.000688	time 1.9572 (2.2030)	loss 3.1731 (3.6686)	grad_norm 1.4844 (1.3179)	
[2022-01-21 05:15:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][990/1251]	eta 0:09:35 lr 0.000688	time 1.9157 (2.2038)	loss 4.4916 (3.6710)	grad_norm 1.3710 (1.3165)	
[2022-01-21 05:16:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1000/1251]	eta 0:09:12 lr 0.000688	time 1.7354 (2.2025)	loss 3.7776 (3.6693)	grad_norm 1.3797 (1.3168)	
[2022-01-21 05:16:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1010/1251]	eta 0:08:50 lr 0.000688	time 1.9233 (2.1997)	loss 4.6662 (3.6701)	grad_norm 1.2217 (1.3172)	
[2022-01-21 05:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1020/1251]	eta 0:08:27 lr 0.000688	time 2.2520 (2.1978)	loss 4.2714 (3.6701)	grad_norm 1.2544 (1.3172)	
[2022-01-21 05:17:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1030/1251]	eta 0:08:05 lr 0.000688	time 1.9072 (2.1977)	loss 4.1534 (3.6709)	grad_norm 1.4405 (1.3167)	
[2022-01-21 05:17:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1040/1251]	eta 0:07:43 lr 0.000688	time 1.9691 (2.1979)	loss 4.0384 (3.6696)	grad_norm 1.5610 (1.3173)	
[2022-01-21 05:18:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1050/1251]	eta 0:07:22 lr 0.000688	time 2.7029 (2.1990)	loss 3.5374 (3.6684)	grad_norm 1.2329 (1.3171)	
[2022-01-21 05:18:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1060/1251]	eta 0:07:00 lr 0.000688	time 1.9162 (2.1996)	loss 4.0763 (3.6676)	grad_norm 1.5169 (1.3177)	
[2022-01-21 05:18:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1070/1251]	eta 0:06:38 lr 0.000688	time 2.0000 (2.1993)	loss 4.1441 (3.6666)	grad_norm 1.3683 (1.3191)	
[2022-01-21 05:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1080/1251]	eta 0:06:15 lr 0.000688	time 1.6365 (2.1982)	loss 4.0160 (3.6666)	grad_norm 1.6060 (1.3194)	
[2022-01-21 05:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1090/1251]	eta 0:05:53 lr 0.000688	time 2.4747 (2.1973)	loss 2.6325 (3.6684)	grad_norm 1.4800 (1.3188)	
[2022-01-21 05:19:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1100/1251]	eta 0:05:31 lr 0.000688	time 1.8403 (2.1971)	loss 4.4002 (3.6695)	grad_norm 1.2893 (1.3185)	
[2022-01-21 05:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1110/1251]	eta 0:05:10 lr 0.000688	time 1.8422 (2.1991)	loss 3.2290 (3.6673)	grad_norm 1.3363 (1.3189)	
[2022-01-21 05:20:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1120/1251]	eta 0:04:48 lr 0.000688	time 1.9356 (2.1995)	loss 2.9507 (3.6683)	grad_norm 1.2245 (1.3186)	
[2022-01-21 05:21:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1130/1251]	eta 0:04:26 lr 0.000688	time 2.1373 (2.1988)	loss 3.9393 (3.6675)	grad_norm 1.2987 (1.3190)	
[2022-01-21 05:21:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1140/1251]	eta 0:04:03 lr 0.000688	time 1.6226 (2.1980)	loss 4.2884 (3.6687)	grad_norm 1.4767 (1.3200)	
[2022-01-21 05:21:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1150/1251]	eta 0:03:41 lr 0.000688	time 1.8487 (2.1965)	loss 2.9762 (3.6680)	grad_norm 1.3019 (1.3195)	
[2022-01-21 05:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1160/1251]	eta 0:03:19 lr 0.000688	time 2.2527 (2.1968)	loss 3.8844 (3.6687)	grad_norm 1.1536 (1.3194)	
[2022-01-21 05:22:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1170/1251]	eta 0:02:57 lr 0.000688	time 2.5540 (2.1970)	loss 3.9139 (3.6682)	grad_norm 1.3327 (1.3201)	
[2022-01-21 05:22:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1180/1251]	eta 0:02:35 lr 0.000687	time 1.8964 (2.1970)	loss 3.9360 (3.6686)	grad_norm 1.3975 (1.3209)	
[2022-01-21 05:23:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1190/1251]	eta 0:02:13 lr 0.000687	time 1.6077 (2.1965)	loss 3.9412 (3.6693)	grad_norm 1.1873 (1.3207)	
[2022-01-21 05:23:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1200/1251]	eta 0:01:52 lr 0.000687	time 2.0240 (2.1964)	loss 3.7338 (3.6726)	grad_norm 1.4872 (1.3201)	
[2022-01-21 05:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1210/1251]	eta 0:01:30 lr 0.000687	time 2.0097 (2.1977)	loss 3.2390 (3.6725)	grad_norm 1.1755 (1.3195)	
[2022-01-21 05:24:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1220/1251]	eta 0:01:08 lr 0.000687	time 2.1729 (2.1978)	loss 4.1204 (3.6723)	grad_norm 1.3283 (1.3194)	
[2022-01-21 05:24:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1230/1251]	eta 0:00:46 lr 0.000687	time 2.5591 (2.1981)	loss 2.8801 (3.6714)	grad_norm 1.1786 (1.3189)	
[2022-01-21 05:25:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1240/1251]	eta 0:00:24 lr 0.000687	time 2.6610 (2.1973)	loss 3.8815 (3.6719)	grad_norm 1.2637 (1.3182)	
[2022-01-21 05:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [113/300][1250/1251]	eta 0:00:02 lr 0.000687	time 1.1791 (2.1911)	loss 3.8114 (3.6708)	grad_norm 1.2304 (1.3184)	
[2022-01-21 05:25:17 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 113 training takes 0:45:41
[2022-01-21 05:25:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.965 (18.965)	Loss 1.1364 (1.1364)	Acc@1 73.926 (73.926)	Acc@5 92.676 (92.676)	
[2022-01-21 05:25:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.531 (3.701)	Loss 1.0904 (1.1342)	Acc@1 74.902 (73.659)	Acc@5 91.699 (92.205)	
[2022-01-21 05:26:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.589 (2.684)	Loss 1.1089 (1.1281)	Acc@1 74.316 (73.889)	Acc@5 91.797 (92.299)	
[2022-01-21 05:26:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.956 (2.393)	Loss 1.0960 (1.1254)	Acc@1 73.438 (73.891)	Acc@5 92.676 (92.266)	
[2022-01-21 05:26:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.053 (2.211)	Loss 1.0234 (1.1200)	Acc@1 77.344 (74.126)	Acc@5 93.945 (92.302)	
[2022-01-21 05:26:55 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.130 Acc@5 92.338
[2022-01-21 05:26:55 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.1%
[2022-01-21 05:26:55 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.25%
[2022-01-21 05:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][0/1251]	eta 7:22:15 lr 0.000687	time 21.2117 (21.2117)	loss 3.8590 (3.8590)	grad_norm 1.4323 (1.4323)	
[2022-01-21 05:27:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][10/1251]	eta 1:22:04 lr 0.000687	time 1.9361 (3.9685)	loss 4.1762 (3.6982)	grad_norm 1.4278 (1.3779)	
[2022-01-21 05:28:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][20/1251]	eta 1:03:48 lr 0.000687	time 1.7380 (3.1102)	loss 4.1919 (3.7950)	grad_norm 1.3057 (1.3104)	
[2022-01-21 05:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][30/1251]	eta 0:56:01 lr 0.000687	time 1.9867 (2.7532)	loss 3.3838 (3.6704)	grad_norm 1.2176 (1.2965)	
[2022-01-21 05:28:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][40/1251]	eta 0:55:49 lr 0.000687	time 3.9225 (2.7662)	loss 3.4391 (3.6108)	grad_norm 1.0643 (1.3008)	
[2022-01-21 05:29:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][50/1251]	eta 0:53:35 lr 0.000687	time 2.5014 (2.6770)	loss 3.9149 (3.5934)	grad_norm 1.3350 (1.2911)	
[2022-01-21 05:29:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][60/1251]	eta 0:51:39 lr 0.000687	time 2.0927 (2.6024)	loss 4.1444 (3.6195)	grad_norm 1.3306 (1.2843)	
[2022-01-21 05:29:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][70/1251]	eta 0:49:50 lr 0.000687	time 1.9041 (2.5320)	loss 2.8611 (3.6165)	grad_norm 1.2203 (1.2864)	
[2022-01-21 05:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][80/1251]	eta 0:48:34 lr 0.000687	time 2.9076 (2.4887)	loss 2.9635 (3.5997)	grad_norm 1.3245 (1.2903)	
[2022-01-21 05:30:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][90/1251]	eta 0:47:11 lr 0.000687	time 1.9566 (2.4390)	loss 3.4176 (3.6022)	grad_norm 1.2984 (1.2949)	
[2022-01-21 05:30:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][100/1251]	eta 0:46:11 lr 0.000687	time 1.9159 (2.4078)	loss 4.3831 (3.6177)	grad_norm 1.6162 (1.2933)	
[2022-01-21 05:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][110/1251]	eta 0:45:18 lr 0.000687	time 2.0393 (2.3827)	loss 4.0171 (3.6116)	grad_norm 1.3044 (1.2978)	
[2022-01-21 05:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][120/1251]	eta 0:44:52 lr 0.000687	time 3.5600 (2.3808)	loss 4.0313 (3.6255)	grad_norm 1.1863 (1.2967)	
[2022-01-21 05:32:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][130/1251]	eta 0:44:21 lr 0.000687	time 1.4777 (2.3746)	loss 3.7448 (3.6422)	grad_norm 1.6462 (1.3021)	
[2022-01-21 05:32:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][140/1251]	eta 0:43:40 lr 0.000687	time 1.6964 (2.3586)	loss 4.0973 (3.6446)	grad_norm 1.4276 (1.3015)	
[2022-01-21 05:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][150/1251]	eta 0:43:00 lr 0.000687	time 2.2372 (2.3434)	loss 3.2369 (3.6524)	grad_norm 1.3232 (1.3008)	
[2022-01-21 05:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][160/1251]	eta 0:42:25 lr 0.000687	time 3.3886 (2.3335)	loss 3.8166 (3.6610)	grad_norm 1.3461 (1.3090)	
[2022-01-21 05:33:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][170/1251]	eta 0:41:52 lr 0.000687	time 1.8685 (2.3240)	loss 3.5631 (3.6576)	grad_norm 1.2917 (1.3094)	
[2022-01-21 05:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][180/1251]	eta 0:41:12 lr 0.000687	time 2.1343 (2.3089)	loss 3.6590 (3.6602)	grad_norm 1.1887 (1.3078)	
[2022-01-21 05:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][190/1251]	eta 0:40:40 lr 0.000686	time 1.6159 (2.2998)	loss 3.5113 (3.6672)	grad_norm 1.2314 (1.3064)	
[2022-01-21 05:34:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][200/1251]	eta 0:40:14 lr 0.000686	time 3.0876 (2.2976)	loss 4.4454 (3.6656)	grad_norm 1.2364 (1.3050)	
[2022-01-21 05:34:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][210/1251]	eta 0:39:44 lr 0.000686	time 2.2479 (2.2903)	loss 2.8463 (3.6543)	grad_norm 1.3029 (1.3079)	
[2022-01-21 05:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][220/1251]	eta 0:39:15 lr 0.000686	time 1.7359 (2.2848)	loss 3.9456 (3.6494)	grad_norm 1.2172 (1.3079)	
[2022-01-21 05:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][230/1251]	eta 0:38:48 lr 0.000686	time 2.1732 (2.2810)	loss 3.5798 (3.6507)	grad_norm 1.2578 (1.3068)	
[2022-01-21 05:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][240/1251]	eta 0:38:24 lr 0.000686	time 3.0968 (2.2797)	loss 2.8859 (3.6475)	grad_norm 1.2645 (1.3066)	
[2022-01-21 05:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][250/1251]	eta 0:38:06 lr 0.000686	time 3.1144 (2.2846)	loss 3.2369 (3.6485)	grad_norm 1.0911 (1.3045)	
[2022-01-21 05:36:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][260/1251]	eta 0:37:42 lr 0.000686	time 1.9300 (2.2826)	loss 4.0245 (3.6548)	grad_norm 1.3771 (1.3063)	
[2022-01-21 05:37:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][270/1251]	eta 0:37:18 lr 0.000686	time 2.4400 (2.2816)	loss 4.1367 (3.6644)	grad_norm 1.2379 (1.3075)	
[2022-01-21 05:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][280/1251]	eta 0:36:48 lr 0.000686	time 2.2169 (2.2748)	loss 4.0351 (3.6643)	grad_norm 1.2473 (1.3069)	
[2022-01-21 05:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][290/1251]	eta 0:36:14 lr 0.000686	time 2.1102 (2.2623)	loss 4.0939 (3.6655)	grad_norm 1.2777 (1.3067)	
[2022-01-21 05:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][300/1251]	eta 0:35:45 lr 0.000686	time 1.9674 (2.2561)	loss 3.7550 (3.6584)	grad_norm 1.3512 (1.3072)	
[2022-01-21 05:38:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][310/1251]	eta 0:35:23 lr 0.000686	time 2.7150 (2.2565)	loss 4.2147 (3.6543)	grad_norm 1.6050 (1.3100)	
[2022-01-21 05:38:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][320/1251]	eta 0:35:00 lr 0.000686	time 2.1003 (2.2561)	loss 3.3777 (3.6551)	grad_norm 1.2299 (1.3099)	
[2022-01-21 05:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][330/1251]	eta 0:34:35 lr 0.000686	time 2.1055 (2.2534)	loss 4.1672 (3.6547)	grad_norm 1.2359 (1.3084)	
[2022-01-21 05:39:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][340/1251]	eta 0:34:12 lr 0.000686	time 1.8927 (2.2529)	loss 3.0648 (3.6437)	grad_norm 1.4307 (1.3078)	
[2022-01-21 05:40:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][350/1251]	eta 0:33:49 lr 0.000686	time 2.3095 (2.2530)	loss 4.5322 (3.6483)	grad_norm 1.1757 (1.3054)	
[2022-01-21 05:40:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][360/1251]	eta 0:33:22 lr 0.000686	time 1.5589 (2.2471)	loss 4.2589 (3.6529)	grad_norm 1.2718 (1.3053)	
[2022-01-21 05:40:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][370/1251]	eta 0:33:00 lr 0.000686	time 3.1814 (2.2476)	loss 4.3549 (3.6522)	grad_norm 1.2758 (1.3067)	
[2022-01-21 05:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][380/1251]	eta 0:32:33 lr 0.000686	time 1.9107 (2.2429)	loss 3.4176 (3.6525)	grad_norm 1.2950 (1.3063)	
[2022-01-21 05:41:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][390/1251]	eta 0:32:04 lr 0.000686	time 2.1652 (2.2347)	loss 4.1551 (3.6516)	grad_norm 1.5339 (1.3087)	
[2022-01-21 05:41:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][400/1251]	eta 0:31:37 lr 0.000686	time 1.9887 (2.2293)	loss 3.9855 (3.6585)	grad_norm 1.3279 (1.3098)	
[2022-01-21 05:42:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][410/1251]	eta 0:31:12 lr 0.000686	time 2.2949 (2.2259)	loss 2.3723 (3.6531)	grad_norm 1.2702 (1.3090)	
[2022-01-21 05:42:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][420/1251]	eta 0:30:47 lr 0.000686	time 2.0068 (2.2235)	loss 2.8343 (3.6480)	grad_norm 1.3868 (1.3092)	
[2022-01-21 05:42:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][430/1251]	eta 0:30:25 lr 0.000686	time 2.2284 (2.2235)	loss 3.6039 (3.6514)	grad_norm 1.3298 (1.3094)	
[2022-01-21 05:43:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][440/1251]	eta 0:30:06 lr 0.000686	time 2.5483 (2.2271)	loss 4.1150 (3.6483)	grad_norm 1.7430 (1.3113)	
[2022-01-21 05:43:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][450/1251]	eta 0:29:46 lr 0.000685	time 1.8417 (2.2302)	loss 3.0962 (3.6479)	grad_norm 1.2542 (1.3114)	
[2022-01-21 05:44:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][460/1251]	eta 0:29:25 lr 0.000685	time 2.4447 (2.2322)	loss 4.0947 (3.6523)	grad_norm 1.4864 (1.3103)	
[2022-01-21 05:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][470/1251]	eta 0:29:03 lr 0.000685	time 1.7085 (2.2318)	loss 3.6779 (3.6574)	grad_norm 1.3659 (1.3108)	
[2022-01-21 05:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][480/1251]	eta 0:28:39 lr 0.000685	time 1.6777 (2.2307)	loss 3.6304 (3.6479)	grad_norm 1.4081 (1.3106)	
[2022-01-21 05:45:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][490/1251]	eta 0:28:16 lr 0.000685	time 2.0274 (2.2293)	loss 4.4312 (3.6478)	grad_norm 1.3642 (1.3109)	
[2022-01-21 05:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][500/1251]	eta 0:27:52 lr 0.000685	time 2.5992 (2.2273)	loss 2.7367 (3.6394)	grad_norm 1.2352 (1.3109)	
[2022-01-21 05:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][510/1251]	eta 0:27:27 lr 0.000685	time 2.0019 (2.2228)	loss 3.8177 (3.6393)	grad_norm 1.3822 (1.3101)	
[2022-01-21 05:46:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][520/1251]	eta 0:27:03 lr 0.000685	time 1.8053 (2.2208)	loss 4.5606 (3.6392)	grad_norm 1.3136 (1.3106)	
[2022-01-21 05:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][530/1251]	eta 0:26:40 lr 0.000685	time 2.0025 (2.2201)	loss 3.9951 (3.6397)	grad_norm 1.2758 (1.3105)	
[2022-01-21 05:46:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][540/1251]	eta 0:26:18 lr 0.000685	time 2.1443 (2.2200)	loss 3.4993 (3.6363)	grad_norm 1.1763 (1.3114)	
[2022-01-21 05:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][550/1251]	eta 0:25:54 lr 0.000685	time 1.6448 (2.2170)	loss 3.0613 (3.6320)	grad_norm 1.2853 (1.3120)	
[2022-01-21 05:47:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][560/1251]	eta 0:25:31 lr 0.000685	time 1.8490 (2.2159)	loss 4.2547 (3.6324)	grad_norm 1.2478 (1.3118)	
[2022-01-21 05:48:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][570/1251]	eta 0:25:10 lr 0.000685	time 2.3135 (2.2178)	loss 3.2879 (3.6265)	grad_norm 1.3833 (1.3115)	
[2022-01-21 05:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][580/1251]	eta 0:24:50 lr 0.000685	time 3.3800 (2.2212)	loss 2.5508 (3.6262)	grad_norm 1.2609 (1.3119)	
[2022-01-21 05:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][590/1251]	eta 0:24:27 lr 0.000685	time 1.9664 (2.2206)	loss 2.7031 (3.6213)	grad_norm 1.4317 (1.3121)	
[2022-01-21 05:49:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][600/1251]	eta 0:24:03 lr 0.000685	time 1.6010 (2.2176)	loss 4.2365 (3.6243)	grad_norm 1.2388 (1.3113)	
[2022-01-21 05:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][610/1251]	eta 0:23:42 lr 0.000685	time 1.8678 (2.2192)	loss 4.0462 (3.6241)	grad_norm 1.5614 (1.3123)	
[2022-01-21 05:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][620/1251]	eta 0:23:20 lr 0.000685	time 3.3736 (2.2191)	loss 4.1157 (3.6327)	grad_norm 1.2919 (1.3120)	
[2022-01-21 05:50:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][630/1251]	eta 0:22:55 lr 0.000685	time 1.9382 (2.2149)	loss 4.3015 (3.6351)	grad_norm 1.6947 (1.3119)	
[2022-01-21 05:50:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][640/1251]	eta 0:22:32 lr 0.000685	time 2.1864 (2.2132)	loss 4.3685 (3.6405)	grad_norm 1.2881 (1.3106)	
[2022-01-21 05:50:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][650/1251]	eta 0:22:10 lr 0.000685	time 2.3246 (2.2144)	loss 2.6020 (3.6383)	grad_norm 1.2197 (1.3099)	
[2022-01-21 05:51:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][660/1251]	eta 0:21:50 lr 0.000685	time 3.6361 (2.2177)	loss 3.9487 (3.6365)	grad_norm 1.2584 (1.3102)	
[2022-01-21 05:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][670/1251]	eta 0:21:27 lr 0.000685	time 1.6365 (2.2155)	loss 3.8740 (3.6378)	grad_norm 1.1711 (1.3097)	
[2022-01-21 05:52:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][680/1251]	eta 0:21:04 lr 0.000685	time 2.0221 (2.2138)	loss 3.6332 (3.6383)	grad_norm 1.2223 (1.3101)	
[2022-01-21 05:52:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][690/1251]	eta 0:20:41 lr 0.000685	time 2.1420 (2.2137)	loss 4.4076 (3.6394)	grad_norm 1.4274 (1.3092)	
[2022-01-21 05:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][700/1251]	eta 0:20:20 lr 0.000685	time 3.4056 (2.2157)	loss 2.9885 (3.6400)	grad_norm 1.4214 (1.3090)	
[2022-01-21 05:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][710/1251]	eta 0:19:59 lr 0.000684	time 2.2894 (2.2170)	loss 4.1780 (3.6416)	grad_norm 1.1051 (1.3094)	
[2022-01-21 05:53:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][720/1251]	eta 0:19:37 lr 0.000684	time 2.6634 (2.2173)	loss 4.2455 (3.6401)	grad_norm 1.2291 (1.3091)	
[2022-01-21 05:53:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][730/1251]	eta 0:19:14 lr 0.000684	time 1.7059 (2.2151)	loss 3.1201 (3.6414)	grad_norm 1.3141 (1.3100)	
[2022-01-21 05:54:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][740/1251]	eta 0:18:51 lr 0.000684	time 3.1438 (2.2151)	loss 2.5375 (3.6394)	grad_norm 1.2764 (1.3097)	
[2022-01-21 05:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][750/1251]	eta 0:18:28 lr 0.000684	time 1.9719 (2.2117)	loss 3.4021 (3.6440)	grad_norm 1.3208 (1.3103)	
[2022-01-21 05:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][760/1251]	eta 0:18:05 lr 0.000684	time 2.5451 (2.2106)	loss 4.0493 (3.6436)	grad_norm 1.6865 (1.3111)	
[2022-01-21 05:55:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][770/1251]	eta 0:17:42 lr 0.000684	time 2.0280 (2.2096)	loss 3.5930 (3.6464)	grad_norm 1.1937 (1.3111)	
[2022-01-21 05:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][780/1251]	eta 0:17:21 lr 0.000684	time 2.5310 (2.2111)	loss 3.7379 (3.6426)	grad_norm 1.1351 (1.3114)	
[2022-01-21 05:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][790/1251]	eta 0:16:58 lr 0.000684	time 1.9746 (2.2103)	loss 3.8710 (3.6446)	grad_norm 1.2674 (1.3109)	
[2022-01-21 05:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][800/1251]	eta 0:16:35 lr 0.000684	time 1.6081 (2.2080)	loss 4.3950 (3.6464)	grad_norm 1.1782 (1.3105)	
[2022-01-21 05:56:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][810/1251]	eta 0:16:13 lr 0.000684	time 2.1256 (2.2071)	loss 2.6809 (3.6451)	grad_norm 1.2030 (1.3112)	
[2022-01-21 05:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][820/1251]	eta 0:15:52 lr 0.000684	time 1.8605 (2.2097)	loss 3.0662 (3.6417)	grad_norm 1.7504 (1.3118)	
[2022-01-21 05:57:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][830/1251]	eta 0:15:29 lr 0.000684	time 1.5526 (2.2087)	loss 4.1676 (3.6434)	grad_norm 1.1674 (1.3110)	
[2022-01-21 05:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][840/1251]	eta 0:15:08 lr 0.000684	time 1.9660 (2.2103)	loss 4.1010 (3.6479)	grad_norm 1.3601 (1.3111)	
[2022-01-21 05:58:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][850/1251]	eta 0:14:46 lr 0.000684	time 2.7964 (2.2108)	loss 3.5836 (3.6476)	grad_norm 1.2518 (1.3110)	
[2022-01-21 05:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][860/1251]	eta 0:14:24 lr 0.000684	time 2.2141 (2.2102)	loss 3.6444 (3.6524)	grad_norm 1.2555 (1.3108)	
[2022-01-21 05:58:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][870/1251]	eta 0:14:01 lr 0.000684	time 1.5928 (2.2087)	loss 4.0466 (3.6518)	grad_norm 1.2176 (1.3098)	
[2022-01-21 05:59:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][880/1251]	eta 0:13:38 lr 0.000684	time 2.2316 (2.2072)	loss 3.7933 (3.6518)	grad_norm 1.2289 (1.3106)	
[2022-01-21 05:59:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][890/1251]	eta 0:13:16 lr 0.000684	time 1.5716 (2.2062)	loss 3.8481 (3.6527)	grad_norm 1.3307 (1.3108)	
[2022-01-21 06:00:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][900/1251]	eta 0:12:54 lr 0.000684	time 2.0123 (2.2063)	loss 3.6352 (3.6535)	grad_norm 1.2138 (1.3098)	
[2022-01-21 06:00:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][910/1251]	eta 0:12:32 lr 0.000684	time 1.9570 (2.2065)	loss 3.3560 (3.6516)	grad_norm 1.0753 (1.3094)	
[2022-01-21 06:00:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][920/1251]	eta 0:12:10 lr 0.000684	time 2.1996 (2.2064)	loss 4.0542 (3.6528)	grad_norm 1.1032 (1.3089)	
[2022-01-21 06:01:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][930/1251]	eta 0:11:48 lr 0.000684	time 2.1941 (2.2057)	loss 4.2146 (3.6558)	grad_norm 1.3715 (1.3089)	
[2022-01-21 06:01:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][940/1251]	eta 0:11:25 lr 0.000684	time 2.4402 (2.2054)	loss 3.5104 (3.6559)	grad_norm 1.2302 (1.3087)	
[2022-01-21 06:01:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][950/1251]	eta 0:11:03 lr 0.000684	time 2.1399 (2.2034)	loss 3.6264 (3.6560)	grad_norm 1.1964 (1.3083)	
[2022-01-21 06:02:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][960/1251]	eta 0:10:40 lr 0.000684	time 1.7881 (2.2020)	loss 4.0814 (3.6561)	grad_norm 1.2315 (1.3084)	
[2022-01-21 06:02:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][970/1251]	eta 0:10:18 lr 0.000683	time 2.0931 (2.2016)	loss 3.6228 (3.6546)	grad_norm 1.3907 (1.3091)	
[2022-01-21 06:02:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][980/1251]	eta 0:09:56 lr 0.000683	time 2.2600 (2.2013)	loss 3.9834 (3.6550)	grad_norm 1.1307 (1.3088)	
[2022-01-21 06:03:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][990/1251]	eta 0:09:34 lr 0.000683	time 2.2488 (2.2017)	loss 4.2408 (3.6538)	grad_norm 1.4407 (1.3087)	
[2022-01-21 06:03:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1000/1251]	eta 0:09:12 lr 0.000683	time 2.4478 (2.2028)	loss 3.5009 (3.6502)	grad_norm 1.1740 (1.3077)	
[2022-01-21 06:04:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1010/1251]	eta 0:08:51 lr 0.000683	time 2.2239 (2.2039)	loss 3.5878 (3.6487)	grad_norm 1.3313 (1.3075)	
[2022-01-21 06:04:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1020/1251]	eta 0:08:29 lr 0.000683	time 2.4254 (2.2052)	loss 3.6074 (3.6464)	grad_norm 1.2810 (1.3082)	
[2022-01-21 06:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1030/1251]	eta 0:08:07 lr 0.000683	time 2.2377 (2.2044)	loss 3.9652 (3.6466)	grad_norm 1.2824 (1.3090)	
[2022-01-21 06:05:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1040/1251]	eta 0:07:44 lr 0.000683	time 1.8616 (2.2011)	loss 4.3190 (3.6468)	grad_norm 1.4322 (1.3090)	
[2022-01-21 06:05:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1050/1251]	eta 0:07:21 lr 0.000683	time 1.8256 (2.1984)	loss 3.9975 (3.6480)	grad_norm 1.3678 (1.3096)	
[2022-01-21 06:05:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1060/1251]	eta 0:06:59 lr 0.000683	time 2.2027 (2.1972)	loss 3.8761 (3.6482)	grad_norm 1.2146 (1.3092)	
[2022-01-21 06:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1070/1251]	eta 0:06:37 lr 0.000683	time 2.7005 (2.1966)	loss 3.7790 (3.6474)	grad_norm 1.5657 (1.3093)	
[2022-01-21 06:06:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1080/1251]	eta 0:06:15 lr 0.000683	time 1.6777 (2.1972)	loss 3.4916 (3.6466)	grad_norm 1.4530 (1.3105)	
[2022-01-21 06:06:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1090/1251]	eta 0:05:53 lr 0.000683	time 2.0343 (2.1975)	loss 3.4842 (3.6437)	grad_norm 1.1612 (1.3103)	
[2022-01-21 06:07:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1100/1251]	eta 0:05:32 lr 0.000683	time 2.5443 (2.2000)	loss 3.8812 (3.6461)	grad_norm 1.5263 (1.3112)	
[2022-01-21 06:07:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1110/1251]	eta 0:05:10 lr 0.000683	time 2.6112 (2.2016)	loss 4.0133 (3.6480)	grad_norm 1.1618 (1.3109)	
[2022-01-21 06:08:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1120/1251]	eta 0:04:48 lr 0.000683	time 1.5618 (2.2026)	loss 4.0498 (3.6499)	grad_norm 1.3580 (1.3108)	
[2022-01-21 06:08:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1130/1251]	eta 0:04:26 lr 0.000683	time 1.8381 (2.2012)	loss 4.2231 (3.6498)	grad_norm 1.3181 (1.3109)	
[2022-01-21 06:08:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1140/1251]	eta 0:04:04 lr 0.000683	time 1.8518 (2.1997)	loss 3.7505 (3.6477)	grad_norm 1.5315 (1.3110)	
[2022-01-21 06:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1150/1251]	eta 0:03:41 lr 0.000683	time 2.1663 (2.1979)	loss 3.6049 (3.6507)	grad_norm 1.2410 (1.3110)	
[2022-01-21 06:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1160/1251]	eta 0:03:19 lr 0.000683	time 3.0750 (2.1976)	loss 3.9026 (3.6497)	grad_norm 1.3120 (1.3111)	
[2022-01-21 06:09:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1170/1251]	eta 0:02:57 lr 0.000683	time 1.9936 (2.1971)	loss 4.1041 (3.6496)	grad_norm 1.1429 (1.3116)	
[2022-01-21 06:10:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1180/1251]	eta 0:02:35 lr 0.000683	time 1.7414 (2.1960)	loss 3.8498 (3.6495)	grad_norm 1.1315 (1.3119)	
[2022-01-21 06:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1190/1251]	eta 0:02:13 lr 0.000683	time 2.0255 (2.1952)	loss 4.1568 (3.6472)	grad_norm 1.3282 (1.3127)	
[2022-01-21 06:10:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1200/1251]	eta 0:01:51 lr 0.000683	time 2.2196 (2.1942)	loss 3.8764 (3.6494)	grad_norm 1.3113 (1.3127)	
[2022-01-21 06:11:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1210/1251]	eta 0:01:29 lr 0.000683	time 1.8760 (2.1948)	loss 4.2726 (3.6457)	grad_norm 1.1907 (1.3126)	
[2022-01-21 06:11:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1220/1251]	eta 0:01:08 lr 0.000683	time 2.2408 (2.1964)	loss 3.9935 (3.6443)	grad_norm 1.4213 (1.3126)	
[2022-01-21 06:12:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1230/1251]	eta 0:00:46 lr 0.000682	time 2.7700 (2.1977)	loss 4.2326 (3.6447)	grad_norm 1.1198 (1.3123)	
[2022-01-21 06:12:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1240/1251]	eta 0:00:24 lr 0.000682	time 2.0964 (2.1975)	loss 4.1808 (3.6461)	grad_norm 1.3542 (1.3121)	
[2022-01-21 06:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [114/300][1250/1251]	eta 0:00:02 lr 0.000682	time 1.1857 (2.1920)	loss 4.1335 (3.6439)	grad_norm 1.3274 (1.3118)	
[2022-01-21 06:12:37 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 114 training takes 0:45:42
[2022-01-21 06:12:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.790 (18.790)	Loss 1.1055 (1.1055)	Acc@1 73.340 (73.340)	Acc@5 92.578 (92.578)	
[2022-01-21 06:13:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.286 (3.574)	Loss 1.1521 (1.0802)	Acc@1 72.754 (74.379)	Acc@5 91.797 (92.676)	
[2022-01-21 06:13:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.645 (2.724)	Loss 1.0459 (1.0879)	Acc@1 75.195 (74.414)	Acc@5 92.969 (92.666)	
[2022-01-21 06:13:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.241 (2.476)	Loss 1.1364 (1.0936)	Acc@1 73.926 (74.197)	Acc@5 91.602 (92.540)	
[2022-01-21 06:14:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.073 (2.274)	Loss 1.0885 (1.0989)	Acc@1 73.438 (74.131)	Acc@5 93.164 (92.483)	
[2022-01-21 06:14:18 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.178 Acc@5 92.454
[2022-01-21 06:14:18 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.2%
[2022-01-21 06:14:18 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.25%
[2022-01-21 06:14:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][0/1251]	eta 7:32:20 lr 0.000682	time 21.6950 (21.6950)	loss 4.3458 (4.3458)	grad_norm 1.1847 (1.1847)	
[2022-01-21 06:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][10/1251]	eta 1:24:01 lr 0.000682	time 1.9050 (4.0622)	loss 3.3009 (3.8459)	grad_norm 1.1080 (1.2128)	
[2022-01-21 06:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][20/1251]	eta 1:05:53 lr 0.000682	time 2.0984 (3.2114)	loss 4.1216 (3.7608)	grad_norm 1.2705 (1.2638)	
[2022-01-21 06:15:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][30/1251]	eta 0:57:40 lr 0.000682	time 1.2182 (2.8341)	loss 3.5616 (3.6323)	grad_norm 1.3018 (1.2908)	
[2022-01-21 06:16:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][40/1251]	eta 0:55:34 lr 0.000682	time 4.4326 (2.7532)	loss 4.3891 (3.6317)	grad_norm 1.3821 (1.3142)	
[2022-01-21 06:16:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][50/1251]	eta 0:52:48 lr 0.000682	time 1.2933 (2.6382)	loss 3.1167 (3.6019)	grad_norm 1.0617 (1.3154)	
[2022-01-21 06:16:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][60/1251]	eta 0:51:20 lr 0.000682	time 1.4191 (2.5863)	loss 3.8897 (3.6280)	grad_norm 1.2177 (1.3125)	
[2022-01-21 06:17:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][70/1251]	eta 0:49:40 lr 0.000682	time 1.6768 (2.5234)	loss 3.5437 (3.6685)	grad_norm 1.3006 (1.3095)	
[2022-01-21 06:17:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][80/1251]	eta 0:48:41 lr 0.000682	time 3.1542 (2.4950)	loss 2.7478 (3.6343)	grad_norm 1.4658 (1.3144)	
[2022-01-21 06:18:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][90/1251]	eta 0:47:18 lr 0.000682	time 1.6814 (2.4452)	loss 3.5982 (3.6105)	grad_norm 1.1885 (1.3209)	
[2022-01-21 06:18:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][100/1251]	eta 0:46:06 lr 0.000682	time 1.8897 (2.4032)	loss 2.7480 (3.6227)	grad_norm 1.2047 (1.3156)	
[2022-01-21 06:18:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][110/1251]	eta 0:45:05 lr 0.000682	time 1.7546 (2.3708)	loss 3.7921 (3.6436)	grad_norm 1.2123 (1.3114)	
[2022-01-21 06:19:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][120/1251]	eta 0:44:43 lr 0.000682	time 3.8726 (2.3723)	loss 3.9626 (3.6361)	grad_norm 1.3171 (1.3083)	
[2022-01-21 06:19:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][130/1251]	eta 0:44:03 lr 0.000682	time 1.8667 (2.3582)	loss 3.6448 (3.6439)	grad_norm 1.1497 (1.3041)	
[2022-01-21 06:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][140/1251]	eta 0:43:35 lr 0.000682	time 1.9637 (2.3540)	loss 3.8469 (3.6236)	grad_norm 1.2568 (1.2987)	
[2022-01-21 06:20:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][150/1251]	eta 0:42:55 lr 0.000682	time 2.0087 (2.3397)	loss 3.6344 (3.6246)	grad_norm 1.1341 (1.2978)	
[2022-01-21 06:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][160/1251]	eta 0:42:21 lr 0.000682	time 2.7912 (2.3292)	loss 4.2069 (3.6256)	grad_norm 1.1795 (1.2991)	
[2022-01-21 06:20:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][170/1251]	eta 0:41:52 lr 0.000682	time 2.2341 (2.3242)	loss 3.6647 (3.6275)	grad_norm 1.2504 (1.2979)	
[2022-01-21 06:21:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][180/1251]	eta 0:41:22 lr 0.000682	time 1.5666 (2.3179)	loss 4.0407 (3.6354)	grad_norm 1.0983 (1.2945)	
[2022-01-21 06:21:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][190/1251]	eta 0:40:54 lr 0.000682	time 2.1173 (2.3138)	loss 4.0974 (3.6203)	grad_norm 1.2663 (1.2993)	
[2022-01-21 06:22:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][200/1251]	eta 0:40:24 lr 0.000682	time 2.2586 (2.3073)	loss 4.0413 (3.6148)	grad_norm 1.3009 (1.3005)	
[2022-01-21 06:22:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][210/1251]	eta 0:39:47 lr 0.000682	time 2.1446 (2.2939)	loss 4.5162 (3.6341)	grad_norm 1.0983 (1.2958)	
[2022-01-21 06:22:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][220/1251]	eta 0:39:12 lr 0.000682	time 1.8212 (2.2822)	loss 3.2577 (3.6411)	grad_norm 1.2999 (1.2966)	
[2022-01-21 06:23:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][230/1251]	eta 0:38:42 lr 0.000682	time 1.8803 (2.2748)	loss 4.4585 (3.6537)	grad_norm 1.5652 (1.2962)	
[2022-01-21 06:23:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][240/1251]	eta 0:38:19 lr 0.000681	time 2.8097 (2.2747)	loss 3.8665 (3.6599)	grad_norm 1.1580 (1.2982)	
[2022-01-21 06:23:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][250/1251]	eta 0:37:56 lr 0.000681	time 2.2068 (2.2739)	loss 4.0619 (3.6491)	grad_norm 1.1969 (1.2968)	
[2022-01-21 06:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][260/1251]	eta 0:37:34 lr 0.000681	time 2.6559 (2.2753)	loss 4.0368 (3.6519)	grad_norm 1.1900 (1.2953)	
[2022-01-21 06:24:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][270/1251]	eta 0:37:10 lr 0.000681	time 2.7815 (2.2737)	loss 3.6750 (3.6574)	grad_norm 1.2007 (1.2945)	
[2022-01-21 06:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][280/1251]	eta 0:36:41 lr 0.000681	time 1.9630 (2.2674)	loss 3.0312 (3.6434)	grad_norm 1.2498 (1.2924)	
[2022-01-21 06:25:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][290/1251]	eta 0:36:10 lr 0.000681	time 1.9063 (2.2590)	loss 3.8078 (3.6466)	grad_norm 1.2075 (1.2932)	
[2022-01-21 06:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][300/1251]	eta 0:35:48 lr 0.000681	time 2.0617 (2.2589)	loss 4.4436 (3.6468)	grad_norm 1.3660 (1.2941)	
[2022-01-21 06:26:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][310/1251]	eta 0:35:27 lr 0.000681	time 3.0272 (2.2610)	loss 3.6076 (3.6414)	grad_norm 1.6890 (1.2975)	
[2022-01-21 06:26:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][320/1251]	eta 0:34:58 lr 0.000681	time 1.5612 (2.2542)	loss 3.3346 (3.6374)	grad_norm 1.3420 (1.2984)	
[2022-01-21 06:26:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][330/1251]	eta 0:34:32 lr 0.000681	time 1.9473 (2.2500)	loss 3.9598 (3.6481)	grad_norm 1.3006 (1.2986)	
[2022-01-21 06:27:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][340/1251]	eta 0:34:07 lr 0.000681	time 2.1778 (2.2473)	loss 3.5708 (3.6516)	grad_norm 1.3007 (1.2983)	
[2022-01-21 06:27:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][350/1251]	eta 0:33:43 lr 0.000681	time 2.2526 (2.2460)	loss 3.4979 (3.6501)	grad_norm 1.3204 (1.2987)	
[2022-01-21 06:27:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][360/1251]	eta 0:33:18 lr 0.000681	time 1.7292 (2.2435)	loss 4.2334 (3.6528)	grad_norm 1.1420 (1.2989)	
[2022-01-21 06:28:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][370/1251]	eta 0:32:54 lr 0.000681	time 2.0594 (2.2416)	loss 4.7405 (3.6523)	grad_norm 1.2833 (1.3003)	
[2022-01-21 06:28:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][380/1251]	eta 0:32:32 lr 0.000681	time 1.9225 (2.2419)	loss 3.3565 (3.6444)	grad_norm 1.2537 (1.3020)	
[2022-01-21 06:28:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][390/1251]	eta 0:32:08 lr 0.000681	time 2.2328 (2.2400)	loss 3.9160 (3.6423)	grad_norm 1.5259 (1.3035)	
[2022-01-21 06:29:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][400/1251]	eta 0:31:52 lr 0.000681	time 1.8164 (2.2478)	loss 2.8137 (3.6425)	grad_norm 1.2371 (1.3030)	
[2022-01-21 06:29:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][410/1251]	eta 0:31:27 lr 0.000681	time 1.5715 (2.2439)	loss 4.3807 (3.6409)	grad_norm 1.3490 (1.3033)	
[2022-01-21 06:29:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][420/1251]	eta 0:30:57 lr 0.000681	time 2.0691 (2.2358)	loss 4.0516 (3.6372)	grad_norm 1.1055 (1.3026)	
[2022-01-21 06:30:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][430/1251]	eta 0:30:32 lr 0.000681	time 2.9612 (2.2326)	loss 3.7354 (3.6376)	grad_norm 1.2380 (1.3026)	
[2022-01-21 06:30:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][440/1251]	eta 0:30:13 lr 0.000681	time 2.1444 (2.2367)	loss 4.0962 (3.6402)	grad_norm 1.3667 (1.3016)	
[2022-01-21 06:31:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][450/1251]	eta 0:29:53 lr 0.000681	time 1.5490 (2.2386)	loss 4.1181 (3.6421)	grad_norm 1.2949 (1.3025)	
[2022-01-21 06:31:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][460/1251]	eta 0:29:28 lr 0.000681	time 2.5721 (2.2358)	loss 2.8492 (3.6364)	grad_norm 1.4289 (1.3031)	
[2022-01-21 06:31:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][470/1251]	eta 0:29:08 lr 0.000681	time 3.4620 (2.2382)	loss 3.5779 (3.6333)	grad_norm 1.1518 (1.3026)	
[2022-01-21 06:32:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][480/1251]	eta 0:28:44 lr 0.000681	time 2.5303 (2.2365)	loss 2.8350 (3.6318)	grad_norm 1.2461 (1.3030)	
[2022-01-21 06:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][490/1251]	eta 0:28:20 lr 0.000680	time 1.6088 (2.2346)	loss 3.8333 (3.6288)	grad_norm 1.3189 (1.3023)	
[2022-01-21 06:32:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][500/1251]	eta 0:27:56 lr 0.000680	time 1.8638 (2.2329)	loss 2.5477 (3.6306)	grad_norm 1.2368 (1.3040)	
[2022-01-21 06:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][510/1251]	eta 0:27:31 lr 0.000680	time 1.9338 (2.2294)	loss 3.7397 (3.6305)	grad_norm 1.2670 (1.3044)	
[2022-01-21 06:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][520/1251]	eta 0:27:05 lr 0.000680	time 1.8274 (2.2240)	loss 3.8497 (3.6377)	grad_norm 1.7290 (1.3073)	
[2022-01-21 06:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][530/1251]	eta 0:26:40 lr 0.000680	time 1.9392 (2.2203)	loss 3.5107 (3.6346)	grad_norm 1.1619 (1.3060)	
[2022-01-21 06:34:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][540/1251]	eta 0:26:15 lr 0.000680	time 2.0640 (2.2165)	loss 3.9847 (3.6345)	grad_norm 1.2525 (1.3063)	
[2022-01-21 06:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][550/1251]	eta 0:25:53 lr 0.000680	time 2.2305 (2.2166)	loss 3.7872 (3.6342)	grad_norm 1.2483 (1.3078)	
[2022-01-21 06:35:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][560/1251]	eta 0:25:33 lr 0.000680	time 2.4318 (2.2187)	loss 3.5432 (3.6333)	grad_norm 1.4684 (1.3105)	
[2022-01-21 06:35:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][570/1251]	eta 0:25:11 lr 0.000680	time 2.3378 (2.2192)	loss 3.9469 (3.6331)	grad_norm 1.1883 (1.3120)	
[2022-01-21 06:35:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][580/1251]	eta 0:24:49 lr 0.000680	time 2.1018 (2.2198)	loss 2.9941 (3.6313)	grad_norm 1.1524 (1.3111)	
[2022-01-21 06:36:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][590/1251]	eta 0:24:28 lr 0.000680	time 2.0095 (2.2218)	loss 3.3891 (3.6316)	grad_norm 1.4984 (1.3122)	
[2022-01-21 06:36:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][600/1251]	eta 0:24:07 lr 0.000680	time 2.0862 (2.2236)	loss 3.9751 (3.6301)	grad_norm 1.4599 (1.3123)	
[2022-01-21 06:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][610/1251]	eta 0:23:45 lr 0.000680	time 1.5965 (2.2233)	loss 2.5082 (3.6267)	grad_norm 1.2574 (1.3121)	
[2022-01-21 06:37:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][620/1251]	eta 0:23:21 lr 0.000680	time 3.1587 (2.2217)	loss 3.4534 (3.6261)	grad_norm 1.3676 (1.3130)	
[2022-01-21 06:37:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][630/1251]	eta 0:22:57 lr 0.000680	time 1.9424 (2.2182)	loss 3.0492 (3.6246)	grad_norm 1.2887 (1.3127)	
[2022-01-21 06:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][640/1251]	eta 0:22:33 lr 0.000680	time 2.1020 (2.2154)	loss 3.4283 (3.6264)	grad_norm 1.3183 (1.3123)	
[2022-01-21 06:38:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][650/1251]	eta 0:22:11 lr 0.000680	time 1.8889 (2.2147)	loss 3.8040 (3.6234)	grad_norm 1.4269 (1.3109)	
[2022-01-21 06:38:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][660/1251]	eta 0:21:51 lr 0.000680	time 1.6814 (2.2197)	loss 3.2161 (3.6239)	grad_norm 1.2063 (1.3102)	
[2022-01-21 06:39:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][670/1251]	eta 0:21:29 lr 0.000680	time 1.8414 (2.2197)	loss 4.1297 (3.6236)	grad_norm 1.2064 (1.3091)	
[2022-01-21 06:39:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][680/1251]	eta 0:21:07 lr 0.000680	time 2.1828 (2.2203)	loss 4.4079 (3.6295)	grad_norm 1.2097 (1.3090)	
[2022-01-21 06:39:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][690/1251]	eta 0:20:44 lr 0.000680	time 1.9328 (2.2187)	loss 4.4243 (3.6314)	grad_norm 1.2705 (1.3086)	
[2022-01-21 06:40:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][700/1251]	eta 0:20:22 lr 0.000680	time 2.4695 (2.2179)	loss 3.6478 (3.6362)	grad_norm 1.2939 (1.3085)	
[2022-01-21 06:40:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][710/1251]	eta 0:19:58 lr 0.000680	time 2.0186 (2.2157)	loss 2.4974 (3.6373)	grad_norm 1.1754 (1.3089)	
[2022-01-21 06:40:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][720/1251]	eta 0:19:36 lr 0.000680	time 2.1504 (2.2155)	loss 4.2764 (3.6358)	grad_norm 1.2895 (1.3084)	
[2022-01-21 06:41:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][730/1251]	eta 0:19:14 lr 0.000680	time 1.6509 (2.2159)	loss 4.5854 (3.6365)	grad_norm 1.2812 (1.3083)	
[2022-01-21 06:41:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][740/1251]	eta 0:18:53 lr 0.000680	time 4.5641 (2.2175)	loss 3.4670 (3.6389)	grad_norm 1.1819 (1.3101)	
[2022-01-21 06:42:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][750/1251]	eta 0:18:31 lr 0.000679	time 2.1949 (2.2186)	loss 3.6608 (3.6410)	grad_norm 1.5157 (1.3124)	
[2022-01-21 06:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][760/1251]	eta 0:18:07 lr 0.000679	time 1.9101 (2.2155)	loss 3.8114 (3.6436)	grad_norm 1.2360 (1.3128)	
[2022-01-21 06:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][770/1251]	eta 0:17:44 lr 0.000679	time 1.7596 (2.2138)	loss 3.8985 (3.6455)	grad_norm 1.1642 (1.3122)	
[2022-01-21 06:43:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][780/1251]	eta 0:17:25 lr 0.000679	time 6.3836 (2.2188)	loss 3.3567 (3.6459)	grad_norm 1.1677 (1.3123)	
[2022-01-21 06:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][790/1251]	eta 0:17:01 lr 0.000679	time 1.9168 (2.2161)	loss 3.3624 (3.6454)	grad_norm 1.2325 (1.3130)	
[2022-01-21 06:43:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][800/1251]	eta 0:16:38 lr 0.000679	time 2.0436 (2.2132)	loss 4.1911 (3.6450)	grad_norm 1.2271 (1.3133)	
[2022-01-21 06:44:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][810/1251]	eta 0:16:16 lr 0.000679	time 2.0867 (2.2151)	loss 3.3118 (3.6428)	grad_norm 1.2041 (1.3123)	
[2022-01-21 06:44:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][820/1251]	eta 0:15:54 lr 0.000679	time 3.0558 (2.2140)	loss 3.0877 (3.6431)	grad_norm 1.4878 (1.3134)	
[2022-01-21 06:44:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][830/1251]	eta 0:15:31 lr 0.000679	time 1.9571 (2.2123)	loss 4.1216 (3.6441)	grad_norm 1.2787 (1.3136)	
[2022-01-21 06:45:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][840/1251]	eta 0:15:08 lr 0.000679	time 2.1351 (2.2104)	loss 3.3561 (3.6406)	grad_norm 1.4796 (1.3141)	
[2022-01-21 06:45:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][850/1251]	eta 0:14:45 lr 0.000679	time 1.5653 (2.2093)	loss 3.3077 (3.6391)	grad_norm 1.5717 (1.3142)	
[2022-01-21 06:46:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][860/1251]	eta 0:14:25 lr 0.000679	time 3.1162 (2.2127)	loss 3.6769 (3.6395)	grad_norm 1.3108 (1.3140)	
[2022-01-21 06:46:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][870/1251]	eta 0:14:03 lr 0.000679	time 2.2293 (2.2132)	loss 3.4387 (3.6374)	grad_norm 1.3616 (1.3134)	
[2022-01-21 06:46:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][880/1251]	eta 0:13:40 lr 0.000679	time 1.6013 (2.2117)	loss 3.6999 (3.6350)	grad_norm 1.2620 (1.3136)	
[2022-01-21 06:47:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][890/1251]	eta 0:13:17 lr 0.000679	time 2.1709 (2.2098)	loss 3.7210 (3.6351)	grad_norm 1.2070 (1.3134)	
[2022-01-21 06:47:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][900/1251]	eta 0:12:54 lr 0.000679	time 2.2659 (2.2079)	loss 4.1217 (3.6334)	grad_norm 1.2109 (1.3138)	
[2022-01-21 06:47:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][910/1251]	eta 0:12:32 lr 0.000679	time 1.9001 (2.2076)	loss 3.8016 (3.6349)	grad_norm 1.2940 (1.3140)	
[2022-01-21 06:48:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][920/1251]	eta 0:12:10 lr 0.000679	time 2.0828 (2.2078)	loss 3.4018 (3.6341)	grad_norm 1.2959 (1.3144)	
[2022-01-21 06:48:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][930/1251]	eta 0:11:48 lr 0.000679	time 2.6168 (2.2082)	loss 3.8422 (3.6321)	grad_norm 1.2769 (1.3139)	
[2022-01-21 06:48:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][940/1251]	eta 0:11:27 lr 0.000679	time 2.2822 (2.2092)	loss 4.0921 (3.6337)	grad_norm 1.4063 (1.3140)	
[2022-01-21 06:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][950/1251]	eta 0:11:04 lr 0.000679	time 1.8557 (2.2080)	loss 4.1852 (3.6352)	grad_norm 1.3457 (1.3142)	
[2022-01-21 06:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][960/1251]	eta 0:10:42 lr 0.000679	time 2.3758 (2.2076)	loss 3.9517 (3.6350)	grad_norm 1.2356 (1.3147)	
[2022-01-21 06:50:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][970/1251]	eta 0:10:20 lr 0.000679	time 2.5138 (2.2067)	loss 3.2036 (3.6361)	grad_norm 1.2021 (1.3151)	
[2022-01-21 06:50:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][980/1251]	eta 0:09:57 lr 0.000679	time 2.3102 (2.2063)	loss 3.8107 (3.6374)	grad_norm 1.4177 (1.3160)	
[2022-01-21 06:50:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][990/1251]	eta 0:09:35 lr 0.000679	time 2.2153 (2.2046)	loss 3.4513 (3.6360)	grad_norm 1.3775 (1.3172)	
[2022-01-21 06:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1000/1251]	eta 0:09:13 lr 0.000679	time 2.2268 (2.2040)	loss 3.5289 (3.6335)	grad_norm 1.4459 (1.3170)	
[2022-01-21 06:51:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1010/1251]	eta 0:08:50 lr 0.000678	time 2.6419 (2.2032)	loss 4.0150 (3.6349)	grad_norm 1.2514 (1.3170)	
[2022-01-21 06:51:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1020/1251]	eta 0:08:29 lr 0.000678	time 2.2262 (2.2047)	loss 3.5184 (3.6355)	grad_norm 1.3802 (1.3166)	
[2022-01-21 06:52:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1030/1251]	eta 0:08:07 lr 0.000678	time 3.0007 (2.2066)	loss 3.8814 (3.6344)	grad_norm 1.4861 (1.3166)	
[2022-01-21 06:52:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1040/1251]	eta 0:07:45 lr 0.000678	time 2.7299 (2.2080)	loss 4.0147 (3.6373)	grad_norm 1.4594 (1.3169)	
[2022-01-21 06:52:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1050/1251]	eta 0:07:23 lr 0.000678	time 2.4901 (2.2083)	loss 3.8093 (3.6357)	grad_norm 1.2677 (1.3165)	
[2022-01-21 06:53:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1060/1251]	eta 0:07:01 lr 0.000678	time 3.0856 (2.2081)	loss 3.3821 (3.6358)	grad_norm 1.4859 (1.3164)	
[2022-01-21 06:53:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1070/1251]	eta 0:06:39 lr 0.000678	time 2.1270 (2.2066)	loss 4.0505 (3.6350)	grad_norm 1.3703 (1.3167)	
[2022-01-21 06:54:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1080/1251]	eta 0:06:16 lr 0.000678	time 1.9082 (2.2041)	loss 3.1774 (3.6353)	grad_norm 1.4837 (1.3168)	
[2022-01-21 06:54:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1090/1251]	eta 0:05:54 lr 0.000678	time 1.6591 (2.2008)	loss 4.4376 (3.6347)	grad_norm 1.5427 (1.3172)	
[2022-01-21 06:54:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1100/1251]	eta 0:05:32 lr 0.000678	time 2.1361 (2.2013)	loss 3.2266 (3.6337)	grad_norm 1.3226 (1.3176)	
[2022-01-21 06:55:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1110/1251]	eta 0:05:10 lr 0.000678	time 2.2412 (2.2014)	loss 4.2407 (3.6316)	grad_norm 1.1783 (1.3173)	
[2022-01-21 06:55:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1120/1251]	eta 0:04:48 lr 0.000678	time 1.5161 (2.2014)	loss 3.6470 (3.6313)	grad_norm 1.4112 (1.3171)	
[2022-01-21 06:55:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1130/1251]	eta 0:04:26 lr 0.000678	time 2.1789 (2.2011)	loss 3.9886 (3.6354)	grad_norm 1.3415 (1.3175)	
[2022-01-21 06:56:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1140/1251]	eta 0:04:04 lr 0.000678	time 1.9606 (2.2004)	loss 3.9343 (3.6359)	grad_norm 1.5757 (1.3177)	
[2022-01-21 06:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1150/1251]	eta 0:03:42 lr 0.000678	time 2.4965 (2.2016)	loss 3.2010 (3.6340)	grad_norm 1.3055 (1.3177)	
[2022-01-21 06:56:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1160/1251]	eta 0:03:20 lr 0.000678	time 1.8626 (2.2029)	loss 3.9282 (3.6341)	grad_norm 1.2057 (1.3169)	
[2022-01-21 06:57:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1170/1251]	eta 0:02:58 lr 0.000678	time 2.0456 (2.2023)	loss 3.2319 (3.6338)	grad_norm 1.4702 (1.3167)	
[2022-01-21 06:57:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1180/1251]	eta 0:02:36 lr 0.000678	time 1.9688 (2.2016)	loss 3.4688 (3.6356)	grad_norm 2.5683 (1.3177)	
[2022-01-21 06:58:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1190/1251]	eta 0:02:14 lr 0.000678	time 2.7981 (2.2020)	loss 3.0527 (3.6342)	grad_norm 1.4366 (1.3187)	
[2022-01-21 06:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1200/1251]	eta 0:01:52 lr 0.000678	time 2.4273 (2.2020)	loss 3.5351 (3.6316)	grad_norm 1.3566 (1.3183)	
[2022-01-21 06:58:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1210/1251]	eta 0:01:30 lr 0.000678	time 1.8639 (2.2008)	loss 3.0405 (3.6301)	grad_norm 1.3812 (1.3180)	
[2022-01-21 06:59:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1220/1251]	eta 0:01:08 lr 0.000678	time 2.1375 (2.2011)	loss 4.0459 (3.6319)	grad_norm 1.3408 (1.3175)	
[2022-01-21 06:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1230/1251]	eta 0:00:46 lr 0.000678	time 2.2085 (2.2016)	loss 3.9016 (3.6324)	grad_norm 1.2223 (1.3171)	
[2022-01-21 06:59:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1240/1251]	eta 0:00:24 lr 0.000678	time 1.6115 (2.2003)	loss 3.1935 (3.6320)	grad_norm 1.4103 (1.3179)	
[2022-01-21 07:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [115/300][1250/1251]	eta 0:00:02 lr 0.000678	time 1.1536 (2.1954)	loss 3.8454 (3.6316)	grad_norm 1.2752 (1.3174)	
[2022-01-21 07:00:04 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 115 training takes 0:45:46
[2022-01-21 07:00:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.921 (17.921)	Loss 1.0901 (1.0901)	Acc@1 74.609 (74.609)	Acc@5 93.066 (93.066)	
[2022-01-21 07:00:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.312 (3.329)	Loss 1.1253 (1.0810)	Acc@1 73.438 (74.663)	Acc@5 93.066 (92.782)	
[2022-01-21 07:01:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.904 (2.685)	Loss 1.0945 (1.0868)	Acc@1 74.902 (74.656)	Acc@5 92.871 (92.592)	
[2022-01-21 07:01:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.314 (2.424)	Loss 1.0946 (1.0926)	Acc@1 75.391 (74.361)	Acc@5 92.480 (92.471)	
[2022-01-21 07:01:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.723 (2.179)	Loss 1.0888 (1.0863)	Acc@1 74.902 (74.481)	Acc@5 92.480 (92.616)	
[2022-01-21 07:01:42 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.404 Acc@5 92.554
[2022-01-21 07:01:42 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.4%
[2022-01-21 07:01:42 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.40%
[2022-01-21 07:02:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][0/1251]	eta 7:42:07 lr 0.000678	time 22.1643 (22.1643)	loss 3.8243 (3.8243)	grad_norm 1.2981 (1.2981)	
[2022-01-21 07:02:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][10/1251]	eta 1:23:20 lr 0.000678	time 2.1782 (4.0296)	loss 3.6794 (3.7207)	grad_norm 1.2387 (1.2602)	
[2022-01-21 07:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][20/1251]	eta 1:05:39 lr 0.000677	time 2.2140 (3.2000)	loss 3.8697 (3.6362)	grad_norm 1.2642 (1.2984)	
[2022-01-21 07:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][30/1251]	eta 0:58:10 lr 0.000677	time 1.5156 (2.8590)	loss 4.0445 (3.7065)	grad_norm 1.2850 (1.3155)	
[2022-01-21 07:03:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][40/1251]	eta 0:54:40 lr 0.000677	time 3.1717 (2.7093)	loss 3.8061 (3.6772)	grad_norm 1.2008 (1.3117)	
[2022-01-21 07:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][50/1251]	eta 0:52:36 lr 0.000677	time 1.5564 (2.6278)	loss 3.5609 (3.6840)	grad_norm 1.3030 (1.3125)	
[2022-01-21 07:04:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][60/1251]	eta 0:50:51 lr 0.000677	time 2.4387 (2.5619)	loss 3.8302 (3.6458)	grad_norm 1.3541 (1.3298)	
[2022-01-21 07:04:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][70/1251]	eta 0:49:22 lr 0.000677	time 1.5052 (2.5081)	loss 3.5999 (3.6843)	grad_norm 1.5377 (1.3493)	
[2022-01-21 07:05:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][80/1251]	eta 0:48:52 lr 0.000677	time 3.7125 (2.5046)	loss 2.7214 (3.6493)	grad_norm 1.2588 (1.3488)	
[2022-01-21 07:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][90/1251]	eta 0:48:17 lr 0.000677	time 1.9033 (2.4956)	loss 3.2864 (3.6495)	grad_norm 1.2331 (1.3513)	
[2022-01-21 07:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][100/1251]	eta 0:47:14 lr 0.000677	time 1.8663 (2.4625)	loss 4.3640 (3.6695)	grad_norm 1.4338 (1.3491)	
[2022-01-21 07:06:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][110/1251]	eta 0:46:03 lr 0.000677	time 1.6926 (2.4218)	loss 2.9814 (3.6291)	grad_norm 1.5899 (1.3484)	
[2022-01-21 07:06:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][120/1251]	eta 0:45:11 lr 0.000677	time 2.7471 (2.3975)	loss 4.5387 (3.6270)	grad_norm 1.3214 (1.3444)	
[2022-01-21 07:06:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][130/1251]	eta 0:44:16 lr 0.000677	time 1.6468 (2.3698)	loss 4.4201 (3.6426)	grad_norm 1.4764 (1.3374)	
[2022-01-21 07:07:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][140/1251]	eta 0:43:33 lr 0.000677	time 1.4996 (2.3522)	loss 4.0048 (3.6535)	grad_norm 1.3838 (1.3352)	
[2022-01-21 07:07:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][150/1251]	eta 0:43:00 lr 0.000677	time 2.1585 (2.3434)	loss 4.5102 (3.6390)	grad_norm 1.2619 (1.3354)	
[2022-01-21 07:07:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][160/1251]	eta 0:42:25 lr 0.000677	time 3.0952 (2.3335)	loss 4.6888 (3.6590)	grad_norm 1.2833 (1.3355)	
[2022-01-21 07:08:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][170/1251]	eta 0:42:05 lr 0.000677	time 2.5599 (2.3359)	loss 4.1697 (3.6618)	grad_norm 1.2532 (1.3336)	
[2022-01-21 07:08:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][180/1251]	eta 0:41:48 lr 0.000677	time 2.4611 (2.3425)	loss 3.7142 (3.6698)	grad_norm 1.3085 (1.3264)	
[2022-01-21 07:09:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][190/1251]	eta 0:41:24 lr 0.000677	time 1.5717 (2.3413)	loss 3.9676 (3.6678)	grad_norm 1.6172 (1.3331)	
[2022-01-21 07:09:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][200/1251]	eta 0:40:55 lr 0.000677	time 2.2853 (2.3360)	loss 3.5990 (3.6606)	grad_norm 1.1476 (1.3326)	
[2022-01-21 07:09:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][210/1251]	eta 0:40:15 lr 0.000677	time 2.1820 (2.3207)	loss 3.1600 (3.6515)	grad_norm 1.2354 (1.3330)	
[2022-01-21 07:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][220/1251]	eta 0:39:33 lr 0.000677	time 1.9372 (2.3026)	loss 3.9286 (3.6643)	grad_norm 1.2908 (1.3281)	
[2022-01-21 07:10:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][230/1251]	eta 0:38:55 lr 0.000677	time 1.9858 (2.2870)	loss 3.5602 (3.6486)	grad_norm 1.5888 (1.3272)	
[2022-01-21 07:10:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][240/1251]	eta 0:38:25 lr 0.000677	time 2.5512 (2.2805)	loss 4.4013 (3.6489)	grad_norm 1.3886 (1.3275)	
[2022-01-21 07:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][250/1251]	eta 0:38:02 lr 0.000677	time 2.1418 (2.2799)	loss 3.5278 (3.6458)	grad_norm 1.2701 (1.3238)	
[2022-01-21 07:11:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][260/1251]	eta 0:37:38 lr 0.000677	time 2.1719 (2.2792)	loss 3.5113 (3.6365)	grad_norm 1.2982 (1.3219)	
[2022-01-21 07:12:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][270/1251]	eta 0:37:17 lr 0.000676	time 1.8867 (2.2813)	loss 4.0914 (3.6408)	grad_norm 1.1755 (1.3244)	
[2022-01-21 07:12:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][280/1251]	eta 0:36:59 lr 0.000676	time 1.6970 (2.2858)	loss 3.9970 (3.6403)	grad_norm 1.4084 (1.3266)	
[2022-01-21 07:12:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][290/1251]	eta 0:36:32 lr 0.000676	time 2.9610 (2.2817)	loss 3.7505 (3.6413)	grad_norm 1.3759 (1.3292)	
[2022-01-21 07:13:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][300/1251]	eta 0:36:10 lr 0.000676	time 2.5438 (2.2819)	loss 3.7011 (3.6354)	grad_norm 1.3041 (1.3303)	
[2022-01-21 07:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][310/1251]	eta 0:35:46 lr 0.000676	time 2.6617 (2.2814)	loss 2.7042 (3.6338)	grad_norm 1.3915 (1.3289)	
[2022-01-21 07:13:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][320/1251]	eta 0:35:18 lr 0.000676	time 1.6621 (2.2757)	loss 3.7502 (3.6404)	grad_norm 1.3923 (1.3288)	
[2022-01-21 07:14:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][330/1251]	eta 0:34:47 lr 0.000676	time 2.2255 (2.2661)	loss 4.5442 (3.6537)	grad_norm 1.4145 (1.3301)	
[2022-01-21 07:14:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][340/1251]	eta 0:34:18 lr 0.000676	time 1.9250 (2.2599)	loss 4.4736 (3.6609)	grad_norm 1.3529 (1.3304)	
[2022-01-21 07:14:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][350/1251]	eta 0:33:54 lr 0.000676	time 3.0921 (2.2585)	loss 2.4293 (3.6537)	grad_norm 1.3201 (1.3302)	
[2022-01-21 07:15:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][360/1251]	eta 0:33:29 lr 0.000676	time 1.6950 (2.2551)	loss 3.9937 (3.6511)	grad_norm 1.0633 (1.3291)	
[2022-01-21 07:15:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][370/1251]	eta 0:33:06 lr 0.000676	time 2.9111 (2.2548)	loss 2.6328 (3.6567)	grad_norm 1.3500 (1.3288)	
[2022-01-21 07:16:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][380/1251]	eta 0:32:41 lr 0.000676	time 1.9497 (2.2520)	loss 3.4640 (3.6539)	grad_norm 1.3735 (1.3285)	
[2022-01-21 07:16:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][390/1251]	eta 0:32:17 lr 0.000676	time 1.9797 (2.2504)	loss 2.8046 (3.6556)	grad_norm 1.5678 (1.3311)	
[2022-01-21 07:16:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][400/1251]	eta 0:31:52 lr 0.000676	time 1.8612 (2.2476)	loss 2.8128 (3.6487)	grad_norm 1.3567 (1.3314)	
[2022-01-21 07:17:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][410/1251]	eta 0:31:31 lr 0.000676	time 3.1182 (2.2491)	loss 3.7754 (3.6449)	grad_norm 1.8644 (1.3328)	
[2022-01-21 07:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][420/1251]	eta 0:31:11 lr 0.000676	time 2.8622 (2.2521)	loss 4.1084 (3.6463)	grad_norm 1.3215 (1.3332)	
[2022-01-21 07:17:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][430/1251]	eta 0:30:47 lr 0.000676	time 2.6868 (2.2507)	loss 4.3960 (3.6465)	grad_norm 1.2500 (1.3320)	
[2022-01-21 07:18:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][440/1251]	eta 0:30:23 lr 0.000676	time 1.8198 (2.2483)	loss 2.8628 (3.6455)	grad_norm 1.9962 (1.3339)	
[2022-01-21 07:18:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][450/1251]	eta 0:29:58 lr 0.000676	time 2.5551 (2.2454)	loss 3.6072 (3.6420)	grad_norm 1.1394 (1.3321)	
[2022-01-21 07:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][460/1251]	eta 0:29:34 lr 0.000676	time 2.5131 (2.2429)	loss 3.9209 (3.6456)	grad_norm 1.2714 (1.3306)	
[2022-01-21 07:19:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][470/1251]	eta 0:29:09 lr 0.000676	time 2.1018 (2.2405)	loss 4.3428 (3.6477)	grad_norm 1.1887 (1.3297)	
[2022-01-21 07:19:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][480/1251]	eta 0:28:44 lr 0.000676	time 1.9004 (2.2370)	loss 4.0021 (3.6500)	grad_norm 1.5652 (1.3287)	
[2022-01-21 07:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][490/1251]	eta 0:28:21 lr 0.000676	time 2.2463 (2.2361)	loss 2.5733 (3.6478)	grad_norm 1.3241 (1.3290)	
[2022-01-21 07:20:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][500/1251]	eta 0:27:58 lr 0.000676	time 2.1982 (2.2353)	loss 3.4761 (3.6495)	grad_norm 1.1802 (1.3273)	
[2022-01-21 07:20:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][510/1251]	eta 0:27:37 lr 0.000676	time 2.5551 (2.2372)	loss 2.9901 (3.6460)	grad_norm 1.1233 (1.3259)	
[2022-01-21 07:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][520/1251]	eta 0:27:17 lr 0.000676	time 1.5916 (2.2394)	loss 3.4476 (3.6447)	grad_norm 1.2424 (1.3265)	
[2022-01-21 07:21:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][530/1251]	eta 0:26:56 lr 0.000675	time 2.6096 (2.2419)	loss 3.7507 (3.6406)	grad_norm 1.3729 (1.3258)	
[2022-01-21 07:21:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][540/1251]	eta 0:26:30 lr 0.000675	time 1.8788 (2.2367)	loss 2.4598 (3.6363)	grad_norm 1.2092 (1.3255)	
[2022-01-21 07:22:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][550/1251]	eta 0:26:03 lr 0.000675	time 2.2231 (2.2310)	loss 2.6476 (3.6365)	grad_norm 1.5157 (1.3266)	
[2022-01-21 07:22:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][560/1251]	eta 0:25:39 lr 0.000675	time 2.3081 (2.2276)	loss 3.1534 (3.6379)	grad_norm 1.0829 (1.3263)	
[2022-01-21 07:22:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][570/1251]	eta 0:25:16 lr 0.000675	time 2.5514 (2.2263)	loss 4.0949 (3.6400)	grad_norm 1.5775 (1.3263)	
[2022-01-21 07:23:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][580/1251]	eta 0:24:52 lr 0.000675	time 2.2425 (2.2249)	loss 3.1641 (3.6440)	grad_norm 1.2276 (1.3266)	
[2022-01-21 07:23:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][590/1251]	eta 0:24:28 lr 0.000675	time 2.2371 (2.2219)	loss 3.6124 (3.6441)	grad_norm 1.3665 (1.3259)	
[2022-01-21 07:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][600/1251]	eta 0:24:05 lr 0.000675	time 2.5586 (2.2208)	loss 3.9778 (3.6490)	grad_norm 1.3449 (1.3262)	
[2022-01-21 07:24:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][610/1251]	eta 0:23:43 lr 0.000675	time 2.6974 (2.2207)	loss 3.3395 (3.6491)	grad_norm 1.4671 (1.3295)	
[2022-01-21 07:24:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][620/1251]	eta 0:23:21 lr 0.000675	time 1.8471 (2.2217)	loss 2.6055 (3.6499)	grad_norm 1.4125 (1.3284)	
[2022-01-21 07:25:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][630/1251]	eta 0:23:00 lr 0.000675	time 2.0839 (2.2229)	loss 2.8620 (3.6464)	grad_norm 1.6538 (1.3281)	
[2022-01-21 07:25:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][640/1251]	eta 0:22:38 lr 0.000675	time 2.6472 (2.2231)	loss 3.6792 (3.6467)	grad_norm 1.2633 (1.3266)	
[2022-01-21 07:25:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][650/1251]	eta 0:22:15 lr 0.000675	time 2.8135 (2.2218)	loss 3.6958 (3.6462)	grad_norm 1.1711 (1.3252)	
[2022-01-21 07:26:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][660/1251]	eta 0:21:52 lr 0.000675	time 2.0867 (2.2212)	loss 3.7557 (3.6449)	grad_norm 1.2730 (1.3249)	
[2022-01-21 07:26:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][670/1251]	eta 0:21:30 lr 0.000675	time 1.9658 (2.2214)	loss 3.7219 (3.6437)	grad_norm 1.1742 (1.3242)	
[2022-01-21 07:26:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][680/1251]	eta 0:21:09 lr 0.000675	time 3.3752 (2.2235)	loss 3.7311 (3.6484)	grad_norm 1.4488 (1.3247)	
[2022-01-21 07:27:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][690/1251]	eta 0:20:46 lr 0.000675	time 2.6010 (2.2228)	loss 4.1549 (3.6451)	grad_norm 1.4569 (1.3251)	
[2022-01-21 07:27:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][700/1251]	eta 0:20:24 lr 0.000675	time 1.6521 (2.2214)	loss 3.1419 (3.6486)	grad_norm 1.3674 (1.3244)	
[2022-01-21 07:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][710/1251]	eta 0:20:00 lr 0.000675	time 1.9651 (2.2182)	loss 3.4985 (3.6513)	grad_norm 1.2378 (1.3243)	
[2022-01-21 07:28:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][720/1251]	eta 0:19:38 lr 0.000675	time 2.4836 (2.2191)	loss 3.8608 (3.6526)	grad_norm 1.2761 (1.3233)	
[2022-01-21 07:28:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][730/1251]	eta 0:19:15 lr 0.000675	time 2.7503 (2.2183)	loss 4.3755 (3.6544)	grad_norm 1.1270 (1.3227)	
[2022-01-21 07:29:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][740/1251]	eta 0:18:53 lr 0.000675	time 1.9898 (2.2186)	loss 4.1189 (3.6584)	grad_norm 1.1445 (1.3229)	
[2022-01-21 07:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][750/1251]	eta 0:18:31 lr 0.000675	time 2.3091 (2.2181)	loss 4.4557 (3.6549)	grad_norm 1.2751 (1.3234)	
[2022-01-21 07:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][760/1251]	eta 0:18:09 lr 0.000675	time 2.5405 (2.2180)	loss 2.8723 (3.6547)	grad_norm 1.6834 (1.3254)	
[2022-01-21 07:30:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][770/1251]	eta 0:17:46 lr 0.000675	time 1.8971 (2.2166)	loss 4.3930 (3.6537)	grad_norm 1.3808 (1.3264)	
[2022-01-21 07:30:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][780/1251]	eta 0:17:22 lr 0.000675	time 1.8948 (2.2137)	loss 3.7230 (3.6530)	grad_norm 1.3026 (1.3273)	
[2022-01-21 07:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][790/1251]	eta 0:17:00 lr 0.000674	time 1.9676 (2.2127)	loss 3.7340 (3.6550)	grad_norm 1.3786 (1.3270)	
[2022-01-21 07:31:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][800/1251]	eta 0:16:37 lr 0.000674	time 2.3181 (2.2127)	loss 3.9798 (3.6548)	grad_norm 1.1550 (1.3264)	
[2022-01-21 07:31:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][810/1251]	eta 0:16:16 lr 0.000674	time 2.6198 (2.2138)	loss 3.5160 (3.6576)	grad_norm 1.1709 (1.3254)	
[2022-01-21 07:31:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][820/1251]	eta 0:15:53 lr 0.000674	time 2.1027 (2.2134)	loss 2.5951 (3.6554)	grad_norm 1.6876 (1.3256)	
[2022-01-21 07:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][830/1251]	eta 0:15:31 lr 0.000674	time 1.9973 (2.2120)	loss 4.0335 (3.6558)	grad_norm 1.1188 (1.3247)	
[2022-01-21 07:32:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][840/1251]	eta 0:15:09 lr 0.000674	time 1.9166 (2.2135)	loss 4.1251 (3.6561)	grad_norm 1.1185 (1.3245)	
[2022-01-21 07:33:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][850/1251]	eta 0:14:47 lr 0.000674	time 1.9043 (2.2126)	loss 3.7199 (3.6573)	grad_norm 1.3628 (1.3235)	
[2022-01-21 07:33:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][860/1251]	eta 0:14:25 lr 0.000674	time 2.5107 (2.2127)	loss 4.2104 (3.6564)	grad_norm 1.1702 (1.3229)	
[2022-01-21 07:33:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][870/1251]	eta 0:14:02 lr 0.000674	time 2.4986 (2.2122)	loss 3.9091 (3.6545)	grad_norm 1.2018 (1.3224)	
[2022-01-21 07:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][880/1251]	eta 0:13:40 lr 0.000674	time 1.5515 (2.2112)	loss 4.0598 (3.6561)	grad_norm 1.3300 (1.3219)	
[2022-01-21 07:34:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][890/1251]	eta 0:13:18 lr 0.000674	time 2.4878 (2.2121)	loss 4.0846 (3.6596)	grad_norm 1.2412 (1.3219)	
[2022-01-21 07:34:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][900/1251]	eta 0:12:56 lr 0.000674	time 3.0936 (2.2120)	loss 3.9337 (3.6602)	grad_norm 1.1246 (1.3219)	
[2022-01-21 07:35:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][910/1251]	eta 0:12:33 lr 0.000674	time 2.1246 (2.2111)	loss 3.6987 (3.6600)	grad_norm 1.3860 (1.3210)	
[2022-01-21 07:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][920/1251]	eta 0:12:12 lr 0.000674	time 1.9144 (2.2123)	loss 3.2062 (3.6611)	grad_norm 1.2485 (1.3199)	
[2022-01-21 07:36:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][930/1251]	eta 0:11:50 lr 0.000674	time 2.7543 (2.2129)	loss 3.2232 (3.6613)	grad_norm 1.1464 (1.3198)	
[2022-01-21 07:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][940/1251]	eta 0:11:27 lr 0.000674	time 2.5109 (2.2110)	loss 4.2158 (3.6631)	grad_norm 1.4437 (1.3194)	
[2022-01-21 07:36:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][950/1251]	eta 0:11:05 lr 0.000674	time 1.7705 (2.2097)	loss 3.1103 (3.6606)	grad_norm 1.2632 (1.3201)	
[2022-01-21 07:37:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][960/1251]	eta 0:10:42 lr 0.000674	time 2.3400 (2.2091)	loss 4.4003 (3.6608)	grad_norm 1.2150 (1.3208)	
[2022-01-21 07:37:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][970/1251]	eta 0:10:20 lr 0.000674	time 2.3017 (2.2080)	loss 3.7541 (3.6616)	grad_norm 1.4343 (1.3211)	
[2022-01-21 07:37:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][980/1251]	eta 0:09:57 lr 0.000674	time 2.2531 (2.2066)	loss 3.4123 (3.6596)	grad_norm 1.2003 (1.3207)	
[2022-01-21 07:38:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][990/1251]	eta 0:09:35 lr 0.000674	time 2.2426 (2.2068)	loss 3.8797 (3.6611)	grad_norm 1.4102 (1.3207)	
[2022-01-21 07:38:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1000/1251]	eta 0:09:13 lr 0.000674	time 2.1760 (2.2056)	loss 3.5520 (3.6626)	grad_norm 1.1935 (1.3197)	
[2022-01-21 07:38:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1010/1251]	eta 0:08:51 lr 0.000674	time 1.9216 (2.2043)	loss 2.9320 (3.6624)	grad_norm 1.2075 (1.3194)	
[2022-01-21 07:39:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1020/1251]	eta 0:08:29 lr 0.000674	time 2.8197 (2.2046)	loss 3.2965 (3.6617)	grad_norm 1.2544 (1.3196)	
[2022-01-21 07:39:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1030/1251]	eta 0:08:07 lr 0.000674	time 2.5561 (2.2051)	loss 3.9992 (3.6613)	grad_norm 1.3159 (1.3190)	
[2022-01-21 07:39:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1040/1251]	eta 0:07:45 lr 0.000673	time 1.8780 (2.2046)	loss 2.6740 (3.6592)	grad_norm 1.2960 (1.3189)	
[2022-01-21 07:40:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1050/1251]	eta 0:07:23 lr 0.000673	time 1.7670 (2.2048)	loss 3.1829 (3.6611)	grad_norm 1.4949 (1.3192)	
[2022-01-21 07:40:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1060/1251]	eta 0:07:01 lr 0.000673	time 2.7132 (2.2056)	loss 3.9117 (3.6637)	grad_norm 1.1641 (1.3188)	
[2022-01-21 07:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1070/1251]	eta 0:06:39 lr 0.000673	time 2.1769 (2.2051)	loss 2.7812 (3.6618)	grad_norm 1.5998 (1.3186)	
[2022-01-21 07:41:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1080/1251]	eta 0:06:17 lr 0.000673	time 2.2104 (2.2056)	loss 3.8477 (3.6634)	grad_norm 1.8332 (1.3188)	
[2022-01-21 07:41:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1090/1251]	eta 0:05:55 lr 0.000673	time 2.3682 (2.2057)	loss 3.8064 (3.6636)	grad_norm 1.6176 (1.3188)	
[2022-01-21 07:42:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1100/1251]	eta 0:05:33 lr 0.000673	time 2.7383 (2.2061)	loss 4.0776 (3.6666)	grad_norm 1.4498 (1.3185)	
[2022-01-21 07:42:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1110/1251]	eta 0:05:10 lr 0.000673	time 2.2198 (2.2054)	loss 3.4972 (3.6670)	grad_norm 1.2351 (1.3183)	
[2022-01-21 07:42:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1120/1251]	eta 0:04:48 lr 0.000673	time 1.7820 (2.2036)	loss 3.5401 (3.6678)	grad_norm 1.4892 (1.3178)	
[2022-01-21 07:43:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1130/1251]	eta 0:04:26 lr 0.000673	time 1.7389 (2.2018)	loss 3.7980 (3.6663)	grad_norm 1.5312 (1.3184)	
[2022-01-21 07:43:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1140/1251]	eta 0:04:04 lr 0.000673	time 2.7200 (2.2052)	loss 3.4853 (3.6656)	grad_norm 1.3258 (1.3183)	
[2022-01-21 07:43:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1150/1251]	eta 0:03:42 lr 0.000673	time 1.8017 (2.2038)	loss 3.3899 (3.6643)	grad_norm 1.2245 (1.3176)	
[2022-01-21 07:44:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1160/1251]	eta 0:03:20 lr 0.000673	time 1.9392 (2.2026)	loss 3.2122 (3.6632)	grad_norm 1.0613 (1.3176)	
[2022-01-21 07:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1170/1251]	eta 0:02:58 lr 0.000673	time 2.4728 (2.2029)	loss 2.8810 (3.6618)	grad_norm 1.2580 (1.3171)	
[2022-01-21 07:45:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1180/1251]	eta 0:02:36 lr 0.000673	time 2.2393 (2.2029)	loss 3.8128 (3.6610)	grad_norm 1.1838 (1.3161)	
[2022-01-21 07:45:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1190/1251]	eta 0:02:14 lr 0.000673	time 2.3221 (2.2025)	loss 3.8690 (3.6603)	grad_norm 1.2874 (1.3156)	
[2022-01-21 07:45:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1200/1251]	eta 0:01:52 lr 0.000673	time 2.7374 (2.2035)	loss 3.6893 (3.6605)	grad_norm 1.2001 (1.3158)	
[2022-01-21 07:46:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1210/1251]	eta 0:01:30 lr 0.000673	time 2.5851 (2.2028)	loss 4.0179 (3.6592)	grad_norm 1.1069 (1.3151)	
[2022-01-21 07:46:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1220/1251]	eta 0:01:08 lr 0.000673	time 2.2474 (2.2016)	loss 3.6505 (3.6606)	grad_norm 1.1633 (1.3145)	
[2022-01-21 07:46:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1230/1251]	eta 0:00:46 lr 0.000673	time 3.1583 (2.2027)	loss 3.5945 (3.6602)	grad_norm 1.3295 (1.3140)	
[2022-01-21 07:47:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1240/1251]	eta 0:00:24 lr 0.000673	time 1.5027 (2.2018)	loss 2.7502 (3.6590)	grad_norm 1.4242 (1.3147)	
[2022-01-21 07:47:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [116/300][1250/1251]	eta 0:00:02 lr 0.000673	time 1.1911 (2.1968)	loss 2.5549 (3.6581)	grad_norm 1.3013 (1.3142)	
[2022-01-21 07:47:31 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 116 training takes 0:45:48
[2022-01-21 07:47:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.381 (18.381)	Loss 1.0418 (1.0418)	Acc@1 75.488 (75.488)	Acc@5 93.555 (93.555)	
[2022-01-21 07:48:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.968 (3.236)	Loss 1.0177 (1.0721)	Acc@1 75.098 (74.183)	Acc@5 93.359 (92.960)	
[2022-01-21 07:48:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.312 (2.570)	Loss 1.0640 (1.0690)	Acc@1 74.023 (74.400)	Acc@5 93.066 (93.080)	
[2022-01-21 07:48:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.304 (2.295)	Loss 1.1530 (1.0802)	Acc@1 73.926 (74.373)	Acc@5 91.309 (92.795)	
[2022-01-21 07:49:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.876 (2.245)	Loss 1.0560 (1.0849)	Acc@1 73.438 (74.247)	Acc@5 92.188 (92.731)	
[2022-01-21 07:49:10 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.320 Acc@5 92.684
[2022-01-21 07:49:10 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.3%
[2022-01-21 07:49:10 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.40%
[2022-01-21 07:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][0/1251]	eta 7:20:11 lr 0.000673	time 21.1120 (21.1120)	loss 3.9214 (3.9214)	grad_norm 1.7969 (1.7969)	
[2022-01-21 07:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][10/1251]	eta 1:24:16 lr 0.000673	time 1.5378 (4.0747)	loss 2.9477 (3.5819)	grad_norm 1.2452 (1.3521)	
[2022-01-21 07:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][20/1251]	eta 1:06:00 lr 0.000673	time 1.5083 (3.2171)	loss 3.2975 (3.6654)	grad_norm 1.3092 (1.3728)	
[2022-01-21 07:50:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][30/1251]	eta 0:58:14 lr 0.000673	time 1.2053 (2.8623)	loss 3.7505 (3.7690)	grad_norm 1.6798 (1.3980)	
[2022-01-21 07:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][40/1251]	eta 0:55:52 lr 0.000673	time 3.8691 (2.7683)	loss 2.4034 (3.7241)	grad_norm 1.1026 (1.3786)	
[2022-01-21 07:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][50/1251]	eta 0:53:52 lr 0.000672	time 3.2699 (2.6915)	loss 2.8087 (3.7493)	grad_norm 1.5821 (1.3674)	
[2022-01-21 07:51:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][60/1251]	eta 0:52:05 lr 0.000672	time 1.5955 (2.6245)	loss 2.7621 (3.7065)	grad_norm 1.1246 (1.3503)	
[2022-01-21 07:52:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][70/1251]	eta 0:50:15 lr 0.000672	time 1.6966 (2.5536)	loss 3.9982 (3.6904)	grad_norm 1.3117 (1.3533)	
[2022-01-21 07:52:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][80/1251]	eta 0:49:10 lr 0.000672	time 3.0193 (2.5197)	loss 4.2347 (3.6797)	grad_norm 1.4583 (1.3570)	
[2022-01-21 07:52:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][90/1251]	eta 0:47:45 lr 0.000672	time 2.1932 (2.4681)	loss 3.1759 (3.6847)	grad_norm 1.4390 (1.3651)	
[2022-01-21 07:53:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][100/1251]	eta 0:46:41 lr 0.000672	time 2.1946 (2.4338)	loss 4.1687 (3.6918)	grad_norm 1.3359 (1.3636)	
[2022-01-21 07:53:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][110/1251]	eta 0:45:38 lr 0.000672	time 1.5828 (2.3998)	loss 3.8260 (3.6854)	grad_norm 1.2066 (1.3556)	
[2022-01-21 07:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][120/1251]	eta 0:45:03 lr 0.000672	time 2.5112 (2.3908)	loss 3.2222 (3.6752)	grad_norm 1.6270 (1.3540)	
[2022-01-21 07:54:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][130/1251]	eta 0:44:24 lr 0.000672	time 2.7471 (2.3773)	loss 2.7510 (3.6715)	grad_norm 1.4457 (1.3560)	
[2022-01-21 07:54:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][140/1251]	eta 0:43:36 lr 0.000672	time 2.0461 (2.3550)	loss 3.8902 (3.6706)	grad_norm 1.3286 (1.3524)	
[2022-01-21 07:55:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][150/1251]	eta 0:42:53 lr 0.000672	time 1.5365 (2.3378)	loss 4.0516 (3.6806)	grad_norm 1.2464 (1.3527)	
[2022-01-21 07:55:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][160/1251]	eta 0:42:34 lr 0.000672	time 2.5594 (2.3411)	loss 3.0744 (3.6822)	grad_norm 1.2306 (1.3504)	
[2022-01-21 07:55:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][170/1251]	eta 0:42:06 lr 0.000672	time 2.3892 (2.3371)	loss 4.3137 (3.6902)	grad_norm 1.9941 (1.3517)	
[2022-01-21 07:56:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][180/1251]	eta 0:41:37 lr 0.000672	time 2.4586 (2.3316)	loss 4.4516 (3.6892)	grad_norm 1.2444 (1.3470)	
[2022-01-21 07:56:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][190/1251]	eta 0:41:09 lr 0.000672	time 1.8725 (2.3278)	loss 3.9253 (3.7002)	grad_norm 1.1751 (1.3428)	
[2022-01-21 07:56:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][200/1251]	eta 0:40:34 lr 0.000672	time 1.6434 (2.3166)	loss 3.2515 (3.6989)	grad_norm 1.1922 (1.3397)	
[2022-01-21 07:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][210/1251]	eta 0:39:50 lr 0.000672	time 1.9511 (2.2965)	loss 4.3580 (3.6905)	grad_norm 1.2656 (1.3390)	
[2022-01-21 07:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][220/1251]	eta 0:39:10 lr 0.000672	time 1.8489 (2.2800)	loss 2.8342 (3.6887)	grad_norm 1.7119 (1.3464)	
[2022-01-21 07:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][230/1251]	eta 0:38:34 lr 0.000672	time 1.8551 (2.2667)	loss 2.3583 (3.6865)	grad_norm 1.3770 (1.3477)	
[2022-01-21 07:58:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][240/1251]	eta 0:38:06 lr 0.000672	time 2.2595 (2.2616)	loss 2.9408 (3.6733)	grad_norm 1.4377 (1.3472)	
[2022-01-21 07:58:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][250/1251]	eta 0:37:37 lr 0.000672	time 2.4035 (2.2554)	loss 2.7379 (3.6789)	grad_norm 1.4352 (1.3457)	
[2022-01-21 07:58:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][260/1251]	eta 0:37:08 lr 0.000672	time 1.8860 (2.2487)	loss 3.6048 (3.6762)	grad_norm 1.3474 (1.3465)	
[2022-01-21 07:59:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][270/1251]	eta 0:36:46 lr 0.000672	time 2.4872 (2.2490)	loss 3.7749 (3.6703)	grad_norm 1.2381 (1.3477)	
[2022-01-21 07:59:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][280/1251]	eta 0:36:26 lr 0.000672	time 2.9225 (2.2517)	loss 4.4165 (3.6630)	grad_norm 1.7883 (1.3499)	
[2022-01-21 08:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][290/1251]	eta 0:36:02 lr 0.000672	time 2.2513 (2.2501)	loss 4.1723 (3.6642)	grad_norm 1.4048 (1.3512)	
[2022-01-21 08:00:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][300/1251]	eta 0:35:37 lr 0.000672	time 2.1959 (2.2477)	loss 2.4672 (3.6594)	grad_norm 1.2266 (1.3512)	
[2022-01-21 08:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][310/1251]	eta 0:35:21 lr 0.000671	time 3.2715 (2.2541)	loss 3.9686 (3.6651)	grad_norm 1.2045 (1.3500)	
[2022-01-21 08:01:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][320/1251]	eta 0:34:58 lr 0.000671	time 2.1238 (2.2544)	loss 3.9429 (3.6647)	grad_norm 1.3323 (1.3485)	
[2022-01-21 08:01:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][330/1251]	eta 0:34:36 lr 0.000671	time 2.4266 (2.2541)	loss 3.5534 (3.6689)	grad_norm 1.1753 (1.3453)	
[2022-01-21 08:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][340/1251]	eta 0:34:13 lr 0.000671	time 2.1974 (2.2540)	loss 3.9717 (3.6691)	grad_norm 1.3199 (1.3469)	
[2022-01-21 08:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][350/1251]	eta 0:33:48 lr 0.000671	time 1.5188 (2.2515)	loss 3.9824 (3.6617)	grad_norm 1.3674 (1.3463)	
[2022-01-21 08:02:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][360/1251]	eta 0:33:25 lr 0.000671	time 1.7262 (2.2505)	loss 2.8161 (3.6590)	grad_norm 1.2791 (1.3454)	
[2022-01-21 08:03:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][370/1251]	eta 0:33:01 lr 0.000671	time 2.0594 (2.2489)	loss 3.3617 (3.6631)	grad_norm 1.5095 (1.3511)	
[2022-01-21 08:03:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][380/1251]	eta 0:32:34 lr 0.000671	time 2.2390 (2.2443)	loss 3.4724 (3.6547)	grad_norm 1.3582 (1.3519)	
[2022-01-21 08:03:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][390/1251]	eta 0:32:10 lr 0.000671	time 1.7640 (2.2422)	loss 2.5005 (3.6494)	grad_norm 1.4250 (1.3518)	
[2022-01-21 08:04:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][400/1251]	eta 0:31:48 lr 0.000671	time 1.8013 (2.2426)	loss 2.6444 (3.6496)	grad_norm 1.5493 (1.3547)	
[2022-01-21 08:04:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][410/1251]	eta 0:31:26 lr 0.000671	time 2.8330 (2.2426)	loss 3.2680 (3.6513)	grad_norm 1.2991 (1.3527)	
[2022-01-21 08:04:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][420/1251]	eta 0:31:07 lr 0.000671	time 3.1159 (2.2472)	loss 3.6665 (3.6537)	grad_norm 1.2728 (1.3518)	
[2022-01-21 08:05:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][430/1251]	eta 0:30:46 lr 0.000671	time 2.1441 (2.2488)	loss 2.7653 (3.6544)	grad_norm 1.1802 (1.3519)	
[2022-01-21 08:05:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][440/1251]	eta 0:30:19 lr 0.000671	time 1.8683 (2.2440)	loss 3.8578 (3.6578)	grad_norm 1.2882 (1.3514)	
[2022-01-21 08:05:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][450/1251]	eta 0:29:52 lr 0.000671	time 1.8356 (2.2375)	loss 4.5658 (3.6619)	grad_norm 1.2227 (1.3496)	
[2022-01-21 08:06:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][460/1251]	eta 0:29:26 lr 0.000671	time 2.4928 (2.2329)	loss 3.7580 (3.6647)	grad_norm 1.1219 (1.3479)	
[2022-01-21 08:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][470/1251]	eta 0:29:01 lr 0.000671	time 2.5094 (2.2305)	loss 4.0544 (3.6715)	grad_norm 1.4714 (1.3484)	
[2022-01-21 08:07:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][480/1251]	eta 0:28:38 lr 0.000671	time 1.8136 (2.2291)	loss 3.7945 (3.6767)	grad_norm 1.1851 (1.3475)	
[2022-01-21 08:07:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][490/1251]	eta 0:28:15 lr 0.000671	time 2.2188 (2.2284)	loss 3.7034 (3.6758)	grad_norm 1.2992 (1.3462)	
[2022-01-21 08:07:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][500/1251]	eta 0:27:54 lr 0.000671	time 2.4272 (2.2293)	loss 3.3837 (3.6712)	grad_norm 1.0945 (1.3459)	
[2022-01-21 08:08:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][510/1251]	eta 0:27:30 lr 0.000671	time 2.1002 (2.2279)	loss 4.0124 (3.6657)	grad_norm 1.2182 (1.3434)	
[2022-01-21 08:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][520/1251]	eta 0:27:06 lr 0.000671	time 1.5274 (2.2257)	loss 2.7122 (3.6654)	grad_norm 1.2322 (1.3425)	
[2022-01-21 08:08:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][530/1251]	eta 0:26:44 lr 0.000671	time 2.6907 (2.2259)	loss 3.6178 (3.6694)	grad_norm 1.2468 (1.3407)	
[2022-01-21 08:09:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][540/1251]	eta 0:26:21 lr 0.000671	time 1.9964 (2.2246)	loss 3.8055 (3.6716)	grad_norm 1.1557 (1.3412)	
[2022-01-21 08:09:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][550/1251]	eta 0:25:58 lr 0.000671	time 2.4508 (2.2239)	loss 3.4810 (3.6677)	grad_norm 1.3626 (1.3421)	
[2022-01-21 08:10:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][560/1251]	eta 0:25:39 lr 0.000670	time 1.8116 (2.2282)	loss 4.0931 (3.6688)	grad_norm 1.1257 (1.3399)	
[2022-01-21 08:10:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][570/1251]	eta 0:25:17 lr 0.000670	time 2.5623 (2.2287)	loss 4.0568 (3.6683)	grad_norm 1.3966 (1.3413)	
[2022-01-21 08:10:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][580/1251]	eta 0:24:53 lr 0.000670	time 1.9270 (2.2256)	loss 3.4275 (3.6684)	grad_norm 1.4825 (1.3413)	
[2022-01-21 08:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][590/1251]	eta 0:24:29 lr 0.000670	time 1.9469 (2.2237)	loss 3.8377 (3.6687)	grad_norm 1.7080 (1.3412)	
[2022-01-21 08:11:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][600/1251]	eta 0:24:07 lr 0.000670	time 2.4890 (2.2240)	loss 3.5266 (3.6704)	grad_norm 1.5157 (1.3431)	
[2022-01-21 08:11:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][610/1251]	eta 0:23:45 lr 0.000670	time 1.8887 (2.2233)	loss 3.3158 (3.6667)	grad_norm 1.1669 (1.3425)	
[2022-01-21 08:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][620/1251]	eta 0:23:21 lr 0.000670	time 1.5350 (2.2204)	loss 3.9206 (3.6661)	grad_norm 1.4142 (1.3407)	
[2022-01-21 08:12:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][630/1251]	eta 0:22:58 lr 0.000670	time 2.7774 (2.2206)	loss 3.9720 (3.6683)	grad_norm 1.6196 (1.3411)	
[2022-01-21 08:12:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][640/1251]	eta 0:22:37 lr 0.000670	time 1.7796 (2.2216)	loss 3.8672 (3.6687)	grad_norm 1.3380 (1.3410)	
[2022-01-21 08:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][650/1251]	eta 0:22:14 lr 0.000670	time 2.0242 (2.2199)	loss 3.8478 (3.6695)	grad_norm 2.1576 (1.3411)	
[2022-01-21 08:13:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][660/1251]	eta 0:21:51 lr 0.000670	time 1.9144 (2.2184)	loss 4.2686 (3.6679)	grad_norm 1.2776 (1.3402)	
[2022-01-21 08:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][670/1251]	eta 0:21:28 lr 0.000670	time 1.8962 (2.2170)	loss 4.0562 (3.6674)	grad_norm 1.3958 (1.3403)	
[2022-01-21 08:14:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][680/1251]	eta 0:21:05 lr 0.000670	time 1.8320 (2.2154)	loss 4.0200 (3.6633)	grad_norm 1.1260 (1.3391)	
[2022-01-21 08:14:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][690/1251]	eta 0:20:45 lr 0.000670	time 1.8750 (2.2206)	loss 3.2051 (3.6617)	grad_norm 1.4197 (1.3389)	
[2022-01-21 08:15:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][700/1251]	eta 0:20:23 lr 0.000670	time 1.7227 (2.2198)	loss 3.7462 (3.6598)	grad_norm 1.5576 (1.3394)	
[2022-01-21 08:15:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][710/1251]	eta 0:20:02 lr 0.000670	time 1.5923 (2.2233)	loss 3.7019 (3.6609)	grad_norm 1.1654 (1.3408)	
[2022-01-21 08:15:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][720/1251]	eta 0:19:39 lr 0.000670	time 1.5878 (2.2208)	loss 4.0239 (3.6615)	grad_norm 1.2622 (1.3399)	
[2022-01-21 08:16:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][730/1251]	eta 0:19:14 lr 0.000670	time 1.6187 (2.2168)	loss 3.8952 (3.6569)	grad_norm 1.3036 (1.3395)	
[2022-01-21 08:16:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][740/1251]	eta 0:18:51 lr 0.000670	time 1.6053 (2.2140)	loss 3.6545 (3.6574)	grad_norm 1.3353 (1.3392)	
[2022-01-21 08:16:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][750/1251]	eta 0:18:31 lr 0.000670	time 2.4128 (2.2182)	loss 3.6437 (3.6558)	grad_norm 1.4768 (1.3391)	
[2022-01-21 08:17:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][760/1251]	eta 0:18:08 lr 0.000670	time 2.0372 (2.2170)	loss 3.9244 (3.6582)	grad_norm 1.3243 (1.3396)	
[2022-01-21 08:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][770/1251]	eta 0:17:46 lr 0.000670	time 1.8293 (2.2170)	loss 3.9693 (3.6605)	grad_norm 1.2661 (1.3393)	
[2022-01-21 08:18:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][780/1251]	eta 0:17:24 lr 0.000670	time 2.3205 (2.2174)	loss 3.9409 (3.6620)	grad_norm 1.3813 (1.3400)	
[2022-01-21 08:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][790/1251]	eta 0:17:03 lr 0.000670	time 2.9963 (2.2198)	loss 3.9819 (3.6624)	grad_norm 1.2282 (1.3391)	
[2022-01-21 08:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][800/1251]	eta 0:16:40 lr 0.000670	time 1.6068 (2.2191)	loss 4.0087 (3.6636)	grad_norm 1.1644 (1.3380)	
[2022-01-21 08:19:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][810/1251]	eta 0:16:18 lr 0.000670	time 1.8885 (2.2186)	loss 3.4719 (3.6610)	grad_norm 1.4309 (1.3378)	
[2022-01-21 08:19:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][820/1251]	eta 0:15:55 lr 0.000669	time 1.7522 (2.2161)	loss 4.1712 (3.6619)	grad_norm 1.2783 (1.3396)	
[2022-01-21 08:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][830/1251]	eta 0:15:32 lr 0.000669	time 3.0092 (2.2154)	loss 3.9147 (3.6610)	grad_norm 1.3587 (1.3405)	
[2022-01-21 08:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][840/1251]	eta 0:15:09 lr 0.000669	time 1.9022 (2.2135)	loss 3.1980 (3.6622)	grad_norm 1.2065 (1.3403)	
[2022-01-21 08:20:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][850/1251]	eta 0:14:48 lr 0.000669	time 2.0933 (2.2146)	loss 3.9913 (3.6629)	grad_norm 1.1291 (1.3400)	
[2022-01-21 08:20:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][860/1251]	eta 0:14:25 lr 0.000669	time 1.9666 (2.2135)	loss 2.8984 (3.6658)	grad_norm 1.3461 (1.3399)	
[2022-01-21 08:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][870/1251]	eta 0:14:03 lr 0.000669	time 2.9696 (2.2143)	loss 2.5601 (3.6663)	grad_norm 1.5077 (1.3392)	
[2022-01-21 08:21:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][880/1251]	eta 0:13:41 lr 0.000669	time 1.8159 (2.2132)	loss 2.7385 (3.6630)	grad_norm 1.3092 (1.3398)	
[2022-01-21 08:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][890/1251]	eta 0:13:18 lr 0.000669	time 2.3357 (2.2125)	loss 3.9508 (3.6601)	grad_norm 1.2547 (1.3401)	
[2022-01-21 08:22:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][900/1251]	eta 0:12:56 lr 0.000669	time 2.5180 (2.2115)	loss 4.0199 (3.6582)	grad_norm 1.6516 (1.3399)	
[2022-01-21 08:22:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][910/1251]	eta 0:12:34 lr 0.000669	time 2.4623 (2.2124)	loss 4.1614 (3.6572)	grad_norm 1.4860 (1.3399)	
[2022-01-21 08:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][920/1251]	eta 0:12:13 lr 0.000669	time 1.8117 (2.2149)	loss 4.4980 (3.6584)	grad_norm 1.4577 (1.3394)	
[2022-01-21 08:23:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][930/1251]	eta 0:11:51 lr 0.000669	time 1.6557 (2.2156)	loss 4.6575 (3.6574)	grad_norm 1.2576 (1.3394)	
[2022-01-21 08:23:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][940/1251]	eta 0:11:28 lr 0.000669	time 2.7536 (2.2147)	loss 2.2762 (3.6538)	grad_norm 1.5084 (1.3396)	
[2022-01-21 08:24:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][950/1251]	eta 0:11:05 lr 0.000669	time 1.9351 (2.2123)	loss 3.8296 (3.6559)	grad_norm 1.2192 (1.3399)	
[2022-01-21 08:24:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][960/1251]	eta 0:10:43 lr 0.000669	time 1.7727 (2.2102)	loss 4.5286 (3.6568)	grad_norm 1.1100 (1.3385)	
[2022-01-21 08:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][970/1251]	eta 0:10:20 lr 0.000669	time 2.2435 (2.2088)	loss 3.9378 (3.6587)	grad_norm 1.2949 (1.3383)	
[2022-01-21 08:25:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][980/1251]	eta 0:09:58 lr 0.000669	time 2.5659 (2.2093)	loss 3.1110 (3.6605)	grad_norm 1.2672 (1.3379)	
[2022-01-21 08:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][990/1251]	eta 0:09:37 lr 0.000669	time 4.0283 (2.2120)	loss 4.3537 (3.6618)	grad_norm 1.5929 (1.3386)	
[2022-01-21 08:26:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1000/1251]	eta 0:09:15 lr 0.000669	time 1.6844 (2.2118)	loss 3.0823 (3.6624)	grad_norm 1.2472 (1.3394)	
[2022-01-21 08:26:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1010/1251]	eta 0:08:53 lr 0.000669	time 1.9129 (2.2117)	loss 2.8025 (3.6621)	grad_norm 1.2096 (1.3392)	
[2022-01-21 08:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1020/1251]	eta 0:08:30 lr 0.000669	time 1.8877 (2.2102)	loss 2.8542 (3.6624)	grad_norm 1.1898 (1.3391)	
[2022-01-21 08:27:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1030/1251]	eta 0:08:08 lr 0.000669	time 3.7054 (2.2102)	loss 4.1553 (3.6625)	grad_norm 1.2676 (1.3384)	
[2022-01-21 08:27:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1040/1251]	eta 0:07:46 lr 0.000669	time 1.9417 (2.2096)	loss 3.6110 (3.6617)	grad_norm 1.4597 (1.3388)	
[2022-01-21 08:27:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1050/1251]	eta 0:07:23 lr 0.000669	time 1.7655 (2.2089)	loss 3.6750 (3.6607)	grad_norm 1.2267 (1.3381)	
[2022-01-21 08:28:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1060/1251]	eta 0:07:01 lr 0.000669	time 2.5588 (2.2080)	loss 2.8580 (3.6588)	grad_norm 1.2394 (1.3383)	
[2022-01-21 08:28:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1070/1251]	eta 0:06:39 lr 0.000668	time 3.0851 (2.2081)	loss 3.1728 (3.6577)	grad_norm 1.3900 (1.3379)	
[2022-01-21 08:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1080/1251]	eta 0:06:17 lr 0.000668	time 3.1507 (2.2090)	loss 2.9660 (3.6579)	grad_norm 1.2192 (1.3378)	
[2022-01-21 08:29:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1090/1251]	eta 0:05:55 lr 0.000668	time 1.6460 (2.2094)	loss 3.7629 (3.6604)	grad_norm 1.2339 (1.3382)	
[2022-01-21 08:29:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1100/1251]	eta 0:05:34 lr 0.000668	time 1.8432 (2.2133)	loss 4.1203 (3.6629)	grad_norm 1.3954 (1.3382)	
[2022-01-21 08:30:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1110/1251]	eta 0:05:11 lr 0.000668	time 2.2033 (2.2121)	loss 3.8623 (3.6639)	grad_norm 1.2355 (1.3378)	
[2022-01-21 08:30:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1120/1251]	eta 0:04:49 lr 0.000668	time 3.4840 (2.2122)	loss 4.4244 (3.6646)	grad_norm 1.3271 (1.3378)	
[2022-01-21 08:30:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1130/1251]	eta 0:04:27 lr 0.000668	time 1.9099 (2.2111)	loss 3.4987 (3.6630)	grad_norm 1.4403 (1.3384)	
[2022-01-21 08:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1140/1251]	eta 0:04:05 lr 0.000668	time 1.8199 (2.2101)	loss 3.9402 (3.6635)	grad_norm 1.3454 (1.3376)	
[2022-01-21 08:31:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1150/1251]	eta 0:03:43 lr 0.000668	time 2.1231 (2.2097)	loss 3.5081 (3.6631)	grad_norm 1.4915 (1.3377)	
[2022-01-21 08:31:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1160/1251]	eta 0:03:21 lr 0.000668	time 2.3769 (2.2096)	loss 4.1761 (3.6623)	grad_norm 1.2205 (1.3374)	
[2022-01-21 08:32:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1170/1251]	eta 0:02:58 lr 0.000668	time 2.2456 (2.2089)	loss 3.8157 (3.6628)	grad_norm 1.1072 (1.3370)	
[2022-01-21 08:32:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1180/1251]	eta 0:02:36 lr 0.000668	time 2.4068 (2.2087)	loss 3.3531 (3.6613)	grad_norm 1.2061 (1.3376)	
[2022-01-21 08:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1190/1251]	eta 0:02:14 lr 0.000668	time 2.2814 (2.2085)	loss 4.0116 (3.6613)	grad_norm 1.1776 (1.3380)	
[2022-01-21 08:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1200/1251]	eta 0:01:52 lr 0.000668	time 2.3164 (2.2099)	loss 3.9878 (3.6600)	grad_norm 1.1463 (1.3377)	
[2022-01-21 08:33:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1210/1251]	eta 0:01:30 lr 0.000668	time 2.4459 (2.2088)	loss 4.0854 (3.6622)	grad_norm 1.1112 (1.3371)	
[2022-01-21 08:34:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1220/1251]	eta 0:01:08 lr 0.000668	time 1.8375 (2.2070)	loss 4.3618 (3.6657)	grad_norm 1.3115 (1.3367)	
[2022-01-21 08:34:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1230/1251]	eta 0:00:46 lr 0.000668	time 1.6377 (2.2059)	loss 3.7754 (3.6665)	grad_norm 1.2031 (1.3367)	
[2022-01-21 08:34:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1240/1251]	eta 0:00:24 lr 0.000668	time 1.9151 (2.2049)	loss 3.2868 (3.6660)	grad_norm 1.2947 (1.3362)	
[2022-01-21 08:35:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [117/300][1250/1251]	eta 0:00:02 lr 0.000668	time 1.1566 (2.1992)	loss 4.0157 (3.6680)	grad_norm 1.1822 (1.3357)	
[2022-01-21 08:35:02 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 117 training takes 0:45:51
[2022-01-21 08:35:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.568 (18.568)	Loss 1.0669 (1.0669)	Acc@1 74.805 (74.805)	Acc@5 92.969 (92.969)	
[2022-01-21 08:35:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.458 (3.531)	Loss 1.0867 (1.0977)	Acc@1 74.707 (74.139)	Acc@5 91.895 (92.383)	
[2022-01-21 08:35:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.916 (2.727)	Loss 0.9662 (1.0733)	Acc@1 78.027 (74.865)	Acc@5 94.336 (92.713)	
[2022-01-21 08:36:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.621 (2.282)	Loss 1.0744 (1.0793)	Acc@1 77.148 (74.726)	Acc@5 92.480 (92.584)	
[2022-01-21 08:36:32 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.690 (2.210)	Loss 1.0352 (1.0781)	Acc@1 76.758 (74.721)	Acc@5 92.090 (92.590)	
[2022-01-21 08:36:39 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.552 Acc@5 92.506
[2022-01-21 08:36:39 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.6%
[2022-01-21 08:36:39 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.55%
[2022-01-21 08:37:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][0/1251]	eta 8:13:23 lr 0.000668	time 23.6636 (23.6636)	loss 2.3415 (2.3415)	grad_norm 1.3677 (1.3677)	
[2022-01-21 08:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][10/1251]	eta 1:22:21 lr 0.000668	time 1.5308 (3.9821)	loss 3.3639 (3.5571)	grad_norm 1.5687 (1.2749)	
[2022-01-21 08:37:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][20/1251]	eta 1:06:35 lr 0.000668	time 2.5401 (3.2453)	loss 4.4040 (3.5847)	grad_norm 1.4529 (1.3336)	
[2022-01-21 08:38:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][30/1251]	eta 0:57:48 lr 0.000668	time 1.2753 (2.8404)	loss 3.5838 (3.6633)	grad_norm 1.4206 (1.3546)	
[2022-01-21 08:38:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][40/1251]	eta 0:55:27 lr 0.000668	time 5.3635 (2.7475)	loss 4.3058 (3.6541)	grad_norm 1.2145 (1.3862)	
[2022-01-21 08:38:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][50/1251]	eta 0:52:47 lr 0.000668	time 2.0323 (2.6375)	loss 4.0710 (3.7151)	grad_norm 1.4563 (1.3765)	
[2022-01-21 08:39:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][60/1251]	eta 0:51:07 lr 0.000668	time 2.3239 (2.5755)	loss 3.9777 (3.7236)	grad_norm 1.3016 (1.3630)	
[2022-01-21 08:39:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][70/1251]	eta 0:49:36 lr 0.000668	time 1.5882 (2.5200)	loss 3.1422 (3.6588)	grad_norm 1.3571 (1.3506)	
[2022-01-21 08:40:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][80/1251]	eta 0:48:32 lr 0.000667	time 3.6126 (2.4871)	loss 4.0637 (3.6606)	grad_norm 1.3136 (1.3491)	
[2022-01-21 08:40:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][90/1251]	eta 0:47:00 lr 0.000667	time 1.5635 (2.4295)	loss 4.5623 (3.6530)	grad_norm 1.3480 (1.3438)	
[2022-01-21 08:40:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][100/1251]	eta 0:46:10 lr 0.000667	time 2.0235 (2.4069)	loss 3.6109 (3.6558)	grad_norm 1.7678 (1.3462)	
[2022-01-21 08:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][110/1251]	eta 0:45:24 lr 0.000667	time 2.1020 (2.3875)	loss 3.6279 (3.6805)	grad_norm 1.2435 (1.3430)	
[2022-01-21 08:41:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][120/1251]	eta 0:44:59 lr 0.000667	time 3.6439 (2.3869)	loss 4.1762 (3.6758)	grad_norm 1.4773 (1.3433)	
[2022-01-21 08:41:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][130/1251]	eta 0:44:22 lr 0.000667	time 2.1335 (2.3754)	loss 2.7898 (3.6529)	grad_norm 1.2190 (1.3383)	
[2022-01-21 08:42:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][140/1251]	eta 0:43:34 lr 0.000667	time 1.8923 (2.3534)	loss 4.0969 (3.6506)	grad_norm 1.2848 (1.3295)	
[2022-01-21 08:42:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][150/1251]	eta 0:42:43 lr 0.000667	time 1.9809 (2.3282)	loss 4.0620 (3.6659)	grad_norm 1.1975 (1.3253)	
[2022-01-21 08:42:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][160/1251]	eta 0:42:08 lr 0.000667	time 2.5808 (2.3180)	loss 3.8248 (3.6755)	grad_norm 1.2175 (1.3266)	
[2022-01-21 08:43:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][170/1251]	eta 0:41:35 lr 0.000667	time 2.9019 (2.3081)	loss 3.8769 (3.6904)	grad_norm 1.6780 (1.3243)	
[2022-01-21 08:43:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][180/1251]	eta 0:41:03 lr 0.000667	time 2.1341 (2.2997)	loss 3.3717 (3.7036)	grad_norm 1.4005 (1.3240)	
[2022-01-21 08:43:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][190/1251]	eta 0:40:38 lr 0.000667	time 2.2057 (2.2981)	loss 4.3628 (3.6980)	grad_norm 1.2149 (1.3198)	
[2022-01-21 08:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][200/1251]	eta 0:40:24 lr 0.000667	time 3.4182 (2.3065)	loss 3.0928 (3.6897)	grad_norm 1.2150 (1.3185)	
[2022-01-21 08:44:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][210/1251]	eta 0:39:52 lr 0.000667	time 1.5502 (2.2986)	loss 4.0364 (3.6817)	grad_norm 1.2402 (1.3189)	
[2022-01-21 08:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][220/1251]	eta 0:39:21 lr 0.000667	time 1.4834 (2.2902)	loss 3.7208 (3.6828)	grad_norm 1.6645 (1.3204)	
[2022-01-21 08:45:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][230/1251]	eta 0:38:51 lr 0.000667	time 2.1834 (2.2834)	loss 4.0249 (3.6820)	grad_norm 1.3248 (1.3281)	
[2022-01-21 08:45:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][240/1251]	eta 0:38:25 lr 0.000667	time 2.8550 (2.2801)	loss 2.6441 (3.6753)	grad_norm 1.3445 (1.3329)	
[2022-01-21 08:46:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][250/1251]	eta 0:37:54 lr 0.000667	time 1.6929 (2.2722)	loss 3.0894 (3.6711)	grad_norm 1.1625 (1.3337)	
[2022-01-21 08:46:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][260/1251]	eta 0:37:27 lr 0.000667	time 1.7616 (2.2677)	loss 4.3395 (3.6657)	grad_norm 1.3612 (1.3363)	
[2022-01-21 08:46:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][270/1251]	eta 0:36:56 lr 0.000667	time 1.5995 (2.2597)	loss 3.5141 (3.6546)	grad_norm 1.1624 (1.3361)	
[2022-01-21 08:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][280/1251]	eta 0:36:39 lr 0.000667	time 2.3622 (2.2650)	loss 2.9083 (3.6595)	grad_norm 1.3415 (1.3358)	
[2022-01-21 08:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][290/1251]	eta 0:36:18 lr 0.000667	time 2.1530 (2.2666)	loss 3.8586 (3.6507)	grad_norm 1.6125 (1.3378)	
[2022-01-21 08:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][300/1251]	eta 0:35:58 lr 0.000667	time 1.8953 (2.2692)	loss 3.7152 (3.6457)	grad_norm 1.1924 (1.3358)	
[2022-01-21 08:48:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][310/1251]	eta 0:35:30 lr 0.000667	time 1.9647 (2.2646)	loss 3.9587 (3.6379)	grad_norm 1.5002 (1.3357)	
[2022-01-21 08:48:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][320/1251]	eta 0:35:05 lr 0.000667	time 2.9000 (2.2615)	loss 3.7903 (3.6244)	grad_norm 1.5680 (1.3351)	
[2022-01-21 08:49:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][330/1251]	eta 0:34:36 lr 0.000666	time 1.8974 (2.2551)	loss 4.1657 (3.6350)	grad_norm 1.3844 (1.3344)	
[2022-01-21 08:49:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][340/1251]	eta 0:34:12 lr 0.000666	time 2.6057 (2.2535)	loss 2.7941 (3.6336)	grad_norm 1.2856 (1.3361)	
[2022-01-21 08:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][350/1251]	eta 0:33:48 lr 0.000666	time 2.1687 (2.2509)	loss 4.2047 (3.6401)	grad_norm 1.3531 (1.3359)	
[2022-01-21 08:50:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][360/1251]	eta 0:33:26 lr 0.000666	time 2.8914 (2.2515)	loss 3.2951 (3.6419)	grad_norm 1.2194 (1.3352)	
[2022-01-21 08:50:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][370/1251]	eta 0:32:59 lr 0.000666	time 2.1800 (2.2464)	loss 3.9839 (3.6475)	grad_norm 1.3049 (1.3376)	
[2022-01-21 08:50:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][380/1251]	eta 0:32:37 lr 0.000666	time 2.5341 (2.2470)	loss 4.1374 (3.6461)	grad_norm 1.2435 (1.3398)	
[2022-01-21 08:51:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][390/1251]	eta 0:32:11 lr 0.000666	time 1.8405 (2.2431)	loss 3.8880 (3.6474)	grad_norm 1.7935 (1.3426)	
[2022-01-21 08:51:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][400/1251]	eta 0:31:47 lr 0.000666	time 2.1870 (2.2419)	loss 3.0037 (3.6535)	grad_norm 1.4027 (1.3464)	
[2022-01-21 08:52:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][410/1251]	eta 0:31:24 lr 0.000666	time 2.5116 (2.2408)	loss 4.3375 (3.6442)	grad_norm 1.5682 (1.3458)	
[2022-01-21 08:52:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][420/1251]	eta 0:31:00 lr 0.000666	time 2.0172 (2.2392)	loss 3.6449 (3.6461)	grad_norm 1.1821 (1.3452)	
[2022-01-21 08:52:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][430/1251]	eta 0:30:37 lr 0.000666	time 1.8780 (2.2386)	loss 3.7455 (3.6476)	grad_norm 1.3724 (1.3437)	
[2022-01-21 08:53:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][440/1251]	eta 0:30:13 lr 0.000666	time 2.5310 (2.2358)	loss 3.9822 (3.6511)	grad_norm 2.1620 (1.3473)	
[2022-01-21 08:53:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][450/1251]	eta 0:29:50 lr 0.000666	time 1.8914 (2.2348)	loss 2.6405 (3.6477)	grad_norm 1.2318 (1.3473)	
[2022-01-21 08:53:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][460/1251]	eta 0:29:29 lr 0.000666	time 3.1237 (2.2366)	loss 4.4085 (3.6396)	grad_norm 1.6251 (1.3482)	
[2022-01-21 08:54:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][470/1251]	eta 0:29:04 lr 0.000666	time 1.8200 (2.2334)	loss 2.8115 (3.6390)	grad_norm 1.2776 (1.3472)	
[2022-01-21 08:54:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][480/1251]	eta 0:28:42 lr 0.000666	time 2.1627 (2.2339)	loss 3.9315 (3.6422)	grad_norm 1.2896 (1.3456)	
[2022-01-21 08:54:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][490/1251]	eta 0:28:18 lr 0.000666	time 1.5681 (2.2316)	loss 4.4451 (3.6477)	grad_norm 1.4151 (1.3453)	
[2022-01-21 08:55:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][500/1251]	eta 0:27:54 lr 0.000666	time 2.2433 (2.2300)	loss 3.5880 (3.6500)	grad_norm 1.1888 (1.3467)	
[2022-01-21 08:55:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][510/1251]	eta 0:27:28 lr 0.000666	time 2.1597 (2.2247)	loss 3.5500 (3.6462)	grad_norm 1.0781 (1.3468)	
[2022-01-21 08:55:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][520/1251]	eta 0:27:05 lr 0.000666	time 2.7510 (2.2234)	loss 3.5971 (3.6503)	grad_norm 1.4745 (1.3461)	
[2022-01-21 08:56:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][530/1251]	eta 0:26:41 lr 0.000666	time 2.6114 (2.2219)	loss 3.9036 (3.6522)	grad_norm 1.4681 (1.3452)	
[2022-01-21 08:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][540/1251]	eta 0:26:17 lr 0.000666	time 1.5477 (2.2188)	loss 3.9154 (3.6527)	grad_norm 1.2708 (1.3467)	
[2022-01-21 08:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][550/1251]	eta 0:25:56 lr 0.000666	time 2.1374 (2.2204)	loss 3.8829 (3.6496)	grad_norm 1.3300 (1.3468)	
[2022-01-21 08:57:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][560/1251]	eta 0:25:37 lr 0.000666	time 3.5651 (2.2250)	loss 4.3847 (3.6503)	grad_norm 1.4211 (1.3467)	
[2022-01-21 08:57:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][570/1251]	eta 0:25:16 lr 0.000666	time 3.1537 (2.2272)	loss 3.5884 (3.6551)	grad_norm 1.6592 (1.3468)	
[2022-01-21 08:58:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][580/1251]	eta 0:24:52 lr 0.000666	time 2.5075 (2.2250)	loss 3.2501 (3.6573)	grad_norm 1.4325 (1.3473)	
[2022-01-21 08:58:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][590/1251]	eta 0:24:28 lr 0.000665	time 2.0687 (2.2222)	loss 4.3045 (3.6588)	grad_norm 1.4194 (1.3469)	
[2022-01-21 08:58:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][600/1251]	eta 0:24:05 lr 0.000665	time 2.6514 (2.2203)	loss 4.3459 (3.6627)	grad_norm 1.2924 (1.3469)	
[2022-01-21 08:59:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][610/1251]	eta 0:23:43 lr 0.000665	time 2.5776 (2.2203)	loss 2.8326 (3.6574)	grad_norm 1.1809 (1.3458)	
[2022-01-21 08:59:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][620/1251]	eta 0:23:20 lr 0.000665	time 2.2124 (2.2198)	loss 3.5065 (3.6624)	grad_norm 1.1259 (1.3449)	
[2022-01-21 08:59:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][630/1251]	eta 0:22:57 lr 0.000665	time 3.1028 (2.2186)	loss 3.8952 (3.6617)	grad_norm 1.6254 (1.3449)	
[2022-01-21 09:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][640/1251]	eta 0:22:34 lr 0.000665	time 1.9734 (2.2166)	loss 4.2081 (3.6657)	grad_norm 1.2838 (1.3441)	
[2022-01-21 09:00:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][650/1251]	eta 0:22:11 lr 0.000665	time 1.9035 (2.2151)	loss 4.1151 (3.6651)	grad_norm 1.2777 (1.3439)	
[2022-01-21 09:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][660/1251]	eta 0:21:48 lr 0.000665	time 1.9220 (2.2141)	loss 3.5839 (3.6662)	grad_norm 1.1546 (1.3423)	
[2022-01-21 09:01:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][670/1251]	eta 0:21:26 lr 0.000665	time 2.4685 (2.2141)	loss 3.9510 (3.6640)	grad_norm 1.2562 (1.3423)	
[2022-01-21 09:01:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][680/1251]	eta 0:21:05 lr 0.000665	time 2.2244 (2.2155)	loss 3.8526 (3.6628)	grad_norm 1.3774 (1.3428)	
[2022-01-21 09:02:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][690/1251]	eta 0:20:43 lr 0.000665	time 2.5116 (2.2159)	loss 3.8795 (3.6618)	grad_norm 1.1844 (1.3422)	
[2022-01-21 09:02:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][700/1251]	eta 0:20:21 lr 0.000665	time 2.4698 (2.2161)	loss 3.5752 (3.6626)	grad_norm 1.5121 (1.3426)	
[2022-01-21 09:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][710/1251]	eta 0:19:57 lr 0.000665	time 1.9334 (2.2134)	loss 4.0744 (3.6622)	grad_norm 1.2711 (1.3427)	
[2022-01-21 09:03:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][720/1251]	eta 0:19:33 lr 0.000665	time 1.8018 (2.2107)	loss 3.6666 (3.6618)	grad_norm 1.3425 (1.3421)	
[2022-01-21 09:03:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][730/1251]	eta 0:19:11 lr 0.000665	time 1.9076 (2.2092)	loss 2.7395 (3.6627)	grad_norm 1.3879 (1.3411)	
[2022-01-21 09:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][740/1251]	eta 0:18:48 lr 0.000665	time 2.5182 (2.2092)	loss 4.1206 (3.6620)	grad_norm 1.1410 (1.3401)	
[2022-01-21 09:04:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][750/1251]	eta 0:18:27 lr 0.000665	time 2.0917 (2.2099)	loss 4.3541 (3.6575)	grad_norm 1.2058 (1.3400)	
[2022-01-21 09:04:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][760/1251]	eta 0:18:04 lr 0.000665	time 1.8712 (2.2092)	loss 3.9630 (3.6595)	grad_norm 1.4650 (1.3395)	
[2022-01-21 09:05:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][770/1251]	eta 0:17:43 lr 0.000665	time 2.8203 (2.2109)	loss 2.9020 (3.6604)	grad_norm 1.5505 (1.3400)	
[2022-01-21 09:05:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][780/1251]	eta 0:17:20 lr 0.000665	time 1.9572 (2.2090)	loss 3.8333 (3.6631)	grad_norm 1.3062 (1.3402)	
[2022-01-21 09:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][790/1251]	eta 0:16:58 lr 0.000665	time 2.1227 (2.2096)	loss 3.5627 (3.6670)	grad_norm 1.0937 (1.3413)	
[2022-01-21 09:06:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][800/1251]	eta 0:16:36 lr 0.000665	time 2.7275 (2.2096)	loss 3.9576 (3.6666)	grad_norm 1.2364 (1.3418)	
[2022-01-21 09:06:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][810/1251]	eta 0:16:14 lr 0.000665	time 2.3559 (2.2099)	loss 3.4917 (3.6658)	grad_norm 1.5373 (1.3430)	
[2022-01-21 09:06:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][820/1251]	eta 0:15:52 lr 0.000665	time 2.2218 (2.2092)	loss 3.5235 (3.6630)	grad_norm 1.6734 (1.3441)	
[2022-01-21 09:07:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][830/1251]	eta 0:15:30 lr 0.000665	time 2.1090 (2.2094)	loss 3.4898 (3.6616)	grad_norm 1.2787 (1.3439)	
[2022-01-21 09:07:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][840/1251]	eta 0:15:07 lr 0.000664	time 2.5309 (2.2075)	loss 3.5162 (3.6641)	grad_norm 1.1821 (1.3430)	
[2022-01-21 09:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][850/1251]	eta 0:14:44 lr 0.000664	time 1.9057 (2.2056)	loss 2.8212 (3.6646)	grad_norm 1.3159 (1.3428)	
[2022-01-21 09:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][860/1251]	eta 0:14:21 lr 0.000664	time 2.4234 (2.2044)	loss 3.3163 (3.6647)	grad_norm 1.3205 (1.3428)	
[2022-01-21 09:08:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][870/1251]	eta 0:13:59 lr 0.000664	time 2.0935 (2.2033)	loss 4.1837 (3.6644)	grad_norm 1.2538 (1.3422)	
[2022-01-21 09:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][880/1251]	eta 0:13:37 lr 0.000664	time 2.8555 (2.2042)	loss 2.9849 (3.6617)	grad_norm 1.3254 (1.3419)	
[2022-01-21 09:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][890/1251]	eta 0:13:16 lr 0.000664	time 2.9134 (2.2068)	loss 3.4970 (3.6594)	grad_norm 1.5253 (1.3425)	
[2022-01-21 09:09:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][900/1251]	eta 0:12:55 lr 0.000664	time 2.9450 (2.2089)	loss 4.0311 (3.6609)	grad_norm 1.3060 (1.3426)	
[2022-01-21 09:10:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][910/1251]	eta 0:12:32 lr 0.000664	time 1.6938 (2.2061)	loss 4.2505 (3.6648)	grad_norm 1.2036 (1.3422)	
[2022-01-21 09:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][920/1251]	eta 0:12:09 lr 0.000664	time 2.6557 (2.2042)	loss 2.6867 (3.6615)	grad_norm 1.3297 (1.3428)	
[2022-01-21 09:10:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][930/1251]	eta 0:11:47 lr 0.000664	time 1.9234 (2.2035)	loss 3.9959 (3.6615)	grad_norm 1.4234 (1.3420)	
[2022-01-21 09:11:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][940/1251]	eta 0:11:26 lr 0.000664	time 2.2172 (2.2070)	loss 3.9211 (3.6604)	grad_norm 1.2623 (1.3418)	
[2022-01-21 09:11:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][950/1251]	eta 0:11:04 lr 0.000664	time 1.5920 (2.2075)	loss 3.8300 (3.6602)	grad_norm 1.1106 (1.3409)	
[2022-01-21 09:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][960/1251]	eta 0:10:43 lr 0.000664	time 6.6802 (2.2110)	loss 4.1330 (3.6588)	grad_norm 1.1460 (1.3405)	
[2022-01-21 09:12:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][970/1251]	eta 0:10:20 lr 0.000664	time 1.6992 (2.2083)	loss 4.2942 (3.6605)	grad_norm 1.3440 (1.3396)	
[2022-01-21 09:12:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][980/1251]	eta 0:09:58 lr 0.000664	time 1.9733 (2.2079)	loss 4.2981 (3.6596)	grad_norm 1.2785 (1.3393)	
[2022-01-21 09:13:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][990/1251]	eta 0:09:35 lr 0.000664	time 1.6250 (2.2056)	loss 3.7434 (3.6599)	grad_norm 1.2896 (1.3389)	
[2022-01-21 09:13:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1000/1251]	eta 0:09:14 lr 0.000664	time 4.9885 (2.2090)	loss 4.1230 (3.6595)	grad_norm 1.2294 (1.3379)	
[2022-01-21 09:13:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1010/1251]	eta 0:08:52 lr 0.000664	time 1.8085 (2.2091)	loss 3.2907 (3.6590)	grad_norm 1.3004 (1.3386)	
[2022-01-21 09:14:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1020/1251]	eta 0:08:30 lr 0.000664	time 1.5762 (2.2083)	loss 2.5391 (3.6612)	grad_norm 1.3691 (1.3380)	
[2022-01-21 09:14:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1030/1251]	eta 0:08:07 lr 0.000664	time 1.8801 (2.2066)	loss 4.4939 (3.6632)	grad_norm 1.2573 (1.3376)	
[2022-01-21 09:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1040/1251]	eta 0:07:45 lr 0.000664	time 3.1740 (2.2059)	loss 3.7526 (3.6625)	grad_norm 1.3392 (1.3368)	
[2022-01-21 09:15:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1050/1251]	eta 0:07:23 lr 0.000664	time 1.9929 (2.2050)	loss 3.9125 (3.6626)	grad_norm 1.4585 (1.3368)	
[2022-01-21 09:15:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1060/1251]	eta 0:07:01 lr 0.000664	time 2.4822 (2.2053)	loss 4.3842 (3.6638)	grad_norm 1.2036 (1.3364)	
[2022-01-21 09:16:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1070/1251]	eta 0:06:38 lr 0.000664	time 1.9535 (2.2041)	loss 3.8170 (3.6627)	grad_norm 1.0873 (1.3352)	
[2022-01-21 09:16:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1080/1251]	eta 0:06:17 lr 0.000664	time 2.6275 (2.2056)	loss 3.3612 (3.6638)	grad_norm 1.6073 (1.3355)	
[2022-01-21 09:16:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1090/1251]	eta 0:05:55 lr 0.000664	time 2.2780 (2.2061)	loss 3.4909 (3.6609)	grad_norm 1.3492 (1.3357)	
[2022-01-21 09:17:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1100/1251]	eta 0:05:33 lr 0.000663	time 2.5401 (2.2067)	loss 3.4164 (3.6569)	grad_norm 1.2277 (1.3360)	
[2022-01-21 09:17:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1110/1251]	eta 0:05:11 lr 0.000663	time 2.3550 (2.2064)	loss 3.3616 (3.6592)	grad_norm 1.2237 (1.3363)	
[2022-01-21 09:17:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1120/1251]	eta 0:04:49 lr 0.000663	time 2.2560 (2.2066)	loss 3.7875 (3.6606)	grad_norm 1.3739 (1.3359)	
[2022-01-21 09:18:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1130/1251]	eta 0:04:26 lr 0.000663	time 2.0069 (2.2055)	loss 3.9839 (3.6623)	grad_norm 1.3546 (1.3357)	
[2022-01-21 09:18:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1140/1251]	eta 0:04:04 lr 0.000663	time 1.8304 (2.2048)	loss 4.1296 (3.6609)	grad_norm 1.4715 (1.3359)	
[2022-01-21 09:18:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1150/1251]	eta 0:03:42 lr 0.000663	time 1.8083 (2.2030)	loss 4.2909 (3.6633)	grad_norm 1.2562 (1.3359)	
[2022-01-21 09:19:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1160/1251]	eta 0:03:20 lr 0.000663	time 1.9027 (2.2039)	loss 3.6833 (3.6645)	grad_norm 1.1476 (1.3361)	
[2022-01-21 09:19:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1170/1251]	eta 0:02:58 lr 0.000663	time 2.2299 (2.2033)	loss 3.8733 (3.6625)	grad_norm 1.3017 (1.3357)	
[2022-01-21 09:20:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1180/1251]	eta 0:02:36 lr 0.000663	time 1.4992 (2.2027)	loss 4.0083 (3.6612)	grad_norm 1.2555 (1.3361)	
[2022-01-21 09:20:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1190/1251]	eta 0:02:14 lr 0.000663	time 1.9640 (2.2033)	loss 2.5709 (3.6591)	grad_norm 1.3071 (1.3360)	
[2022-01-21 09:20:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1200/1251]	eta 0:01:52 lr 0.000663	time 2.4504 (2.2053)	loss 4.0204 (3.6590)	grad_norm 1.5417 (1.3359)	
[2022-01-21 09:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1210/1251]	eta 0:01:30 lr 0.000663	time 1.9344 (2.2041)	loss 3.9411 (3.6609)	grad_norm 1.3972 (1.3361)	
[2022-01-21 09:21:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1220/1251]	eta 0:01:08 lr 0.000663	time 1.7956 (2.2021)	loss 3.3375 (3.6595)	grad_norm 1.5025 (1.3359)	
[2022-01-21 09:21:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1230/1251]	eta 0:00:46 lr 0.000663	time 2.0479 (2.2009)	loss 4.3104 (3.6572)	grad_norm 1.1515 (1.3352)	
[2022-01-21 09:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1240/1251]	eta 0:00:24 lr 0.000663	time 2.4053 (2.1995)	loss 4.5433 (3.6590)	grad_norm 1.2718 (1.3347)	
[2022-01-21 09:22:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [118/300][1250/1251]	eta 0:00:02 lr 0.000663	time 1.1571 (2.1943)	loss 3.8015 (3.6578)	grad_norm 1.3625 (1.3342)	
[2022-01-21 09:22:25 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 118 training takes 0:45:45
[2022-01-21 09:22:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 20.495 (20.495)	Loss 1.1206 (1.1206)	Acc@1 73.926 (73.926)	Acc@5 91.602 (91.602)	
[2022-01-21 09:23:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.338 (3.183)	Loss 1.0746 (1.1012)	Acc@1 74.902 (74.015)	Acc@5 92.383 (92.285)	
[2022-01-21 09:23:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.634 (2.532)	Loss 1.1734 (1.0982)	Acc@1 74.121 (74.423)	Acc@5 91.797 (92.401)	
[2022-01-21 09:23:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.962 (2.267)	Loss 1.0824 (1.1045)	Acc@1 72.949 (74.149)	Acc@5 92.969 (92.304)	
[2022-01-21 09:23:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.489 (2.177)	Loss 1.0761 (1.1007)	Acc@1 76.660 (74.340)	Acc@5 93.262 (92.452)	
[2022-01-21 09:24:01 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.462 Acc@5 92.502
[2022-01-21 09:24:01 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.5%
[2022-01-21 09:24:01 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.55%
[2022-01-21 09:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][0/1251]	eta 7:32:33 lr 0.000663	time 21.7051 (21.7051)	loss 4.0848 (4.0848)	grad_norm 1.2481 (1.2481)	
[2022-01-21 09:24:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][10/1251]	eta 1:20:08 lr 0.000663	time 1.6059 (3.8750)	loss 2.7303 (3.5836)	grad_norm 1.1847 (1.2617)	
[2022-01-21 09:25:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][20/1251]	eta 1:02:11 lr 0.000663	time 1.5845 (3.0312)	loss 3.8059 (3.5993)	grad_norm 1.4569 (1.2857)	
[2022-01-21 09:25:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][30/1251]	eta 0:56:16 lr 0.000663	time 1.6179 (2.7651)	loss 4.0082 (3.5810)	grad_norm 1.2235 (1.3021)	
[2022-01-21 09:25:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][40/1251]	eta 0:53:56 lr 0.000663	time 4.5789 (2.6722)	loss 3.6568 (3.6321)	grad_norm 1.3770 (1.3142)	
[2022-01-21 09:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][50/1251]	eta 0:52:02 lr 0.000663	time 1.4505 (2.6003)	loss 4.1128 (3.6439)	grad_norm 1.1455 (1.3094)	
[2022-01-21 09:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][60/1251]	eta 0:49:47 lr 0.000663	time 1.5909 (2.5081)	loss 3.1617 (3.5856)	grad_norm 1.2446 (1.3054)	
[2022-01-21 09:26:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][70/1251]	eta 0:48:07 lr 0.000663	time 2.0350 (2.4451)	loss 4.0084 (3.5591)	grad_norm 1.3700 (1.3240)	
[2022-01-21 09:27:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][80/1251]	eta 0:47:39 lr 0.000663	time 3.5088 (2.4420)	loss 3.6408 (3.5627)	grad_norm 1.4792 (1.3246)	
[2022-01-21 09:27:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][90/1251]	eta 0:47:03 lr 0.000663	time 1.2729 (2.4319)	loss 4.2590 (3.5764)	grad_norm 1.4991 (1.3234)	
[2022-01-21 09:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][100/1251]	eta 0:46:24 lr 0.000662	time 2.1153 (2.4188)	loss 3.6145 (3.5620)	grad_norm 1.2625 (1.3177)	
[2022-01-21 09:28:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][110/1251]	eta 0:45:47 lr 0.000662	time 1.8719 (2.4077)	loss 3.5000 (3.5755)	grad_norm 1.3418 (1.3140)	
[2022-01-21 09:28:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][120/1251]	eta 0:45:13 lr 0.000662	time 2.4790 (2.3990)	loss 3.9744 (3.5792)	grad_norm 1.4044 (1.3249)	
[2022-01-21 09:29:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][130/1251]	eta 0:44:23 lr 0.000662	time 2.2221 (2.3762)	loss 3.0197 (3.5607)	grad_norm 1.2986 (1.3227)	
[2022-01-21 09:29:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][140/1251]	eta 0:43:26 lr 0.000662	time 1.9536 (2.3462)	loss 4.3671 (3.5644)	grad_norm 1.3665 (1.3256)	
[2022-01-21 09:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][150/1251]	eta 0:42:41 lr 0.000662	time 2.5411 (2.3267)	loss 3.6189 (3.5698)	grad_norm 1.2334 (1.3246)	
[2022-01-21 09:30:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][160/1251]	eta 0:42:05 lr 0.000662	time 2.4566 (2.3147)	loss 3.4679 (3.5701)	grad_norm 1.2191 (1.3230)	
[2022-01-21 09:30:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][170/1251]	eta 0:41:44 lr 0.000662	time 2.4991 (2.3164)	loss 3.2153 (3.5771)	grad_norm 1.3709 (1.3244)	
[2022-01-21 09:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][180/1251]	eta 0:41:14 lr 0.000662	time 2.2011 (2.3104)	loss 4.0316 (3.5763)	grad_norm 1.1867 (1.3183)	
[2022-01-21 09:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][190/1251]	eta 0:40:42 lr 0.000662	time 2.0418 (2.3021)	loss 3.4339 (3.5728)	grad_norm 1.2907 (1.3162)	
[2022-01-21 09:31:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][200/1251]	eta 0:40:11 lr 0.000662	time 1.7833 (2.2942)	loss 4.1951 (3.5793)	grad_norm 1.3457 (1.3189)	
[2022-01-21 09:32:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][210/1251]	eta 0:39:47 lr 0.000662	time 2.1954 (2.2936)	loss 4.1532 (3.5922)	grad_norm 1.1784 (1.3173)	
[2022-01-21 09:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][220/1251]	eta 0:39:14 lr 0.000662	time 1.8916 (2.2837)	loss 4.1412 (3.6034)	grad_norm 1.8547 (1.3201)	
[2022-01-21 09:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][230/1251]	eta 0:38:54 lr 0.000662	time 2.6771 (2.2862)	loss 3.5470 (3.6094)	grad_norm 1.4492 (1.3227)	
[2022-01-21 09:33:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][240/1251]	eta 0:38:29 lr 0.000662	time 1.8978 (2.2841)	loss 4.0049 (3.6131)	grad_norm 1.2523 (1.3257)	
[2022-01-21 09:33:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][250/1251]	eta 0:38:05 lr 0.000662	time 1.7678 (2.2827)	loss 3.6345 (3.6117)	grad_norm 1.4747 (1.3235)	
[2022-01-21 09:33:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][260/1251]	eta 0:37:39 lr 0.000662	time 2.2356 (2.2801)	loss 3.2040 (3.6074)	grad_norm 1.1970 (1.3226)	
[2022-01-21 09:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][270/1251]	eta 0:37:07 lr 0.000662	time 1.6399 (2.2708)	loss 3.5248 (3.6065)	grad_norm 1.3841 (1.3258)	
[2022-01-21 09:34:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][280/1251]	eta 0:36:35 lr 0.000662	time 1.8540 (2.2610)	loss 4.6831 (3.5941)	grad_norm 1.2871 (1.3263)	
[2022-01-21 09:34:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][290/1251]	eta 0:36:08 lr 0.000662	time 1.9428 (2.2567)	loss 3.8065 (3.5926)	grad_norm 1.6374 (1.3331)	
[2022-01-21 09:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][300/1251]	eta 0:35:45 lr 0.000662	time 1.7611 (2.2562)	loss 3.4481 (3.5879)	grad_norm 1.2109 (1.3339)	
[2022-01-21 09:35:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][310/1251]	eta 0:35:23 lr 0.000662	time 2.1680 (2.2565)	loss 3.7074 (3.5951)	grad_norm 1.3770 (1.3327)	
[2022-01-21 09:36:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][320/1251]	eta 0:34:58 lr 0.000662	time 2.1181 (2.2543)	loss 3.5799 (3.5961)	grad_norm 1.5182 (1.3327)	
[2022-01-21 09:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][330/1251]	eta 0:34:37 lr 0.000662	time 1.9214 (2.2553)	loss 3.5206 (3.5925)	grad_norm 1.3643 (1.3305)	
[2022-01-21 09:36:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][340/1251]	eta 0:34:14 lr 0.000662	time 1.5314 (2.2550)	loss 3.4521 (3.5947)	grad_norm 1.2978 (1.3298)	
[2022-01-21 09:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][350/1251]	eta 0:33:47 lr 0.000662	time 2.2659 (2.2503)	loss 4.0054 (3.5919)	grad_norm 1.2697 (1.3286)	
[2022-01-21 09:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][360/1251]	eta 0:33:21 lr 0.000661	time 1.7532 (2.2465)	loss 2.7314 (3.5888)	grad_norm 1.1545 (1.3278)	
[2022-01-21 09:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][370/1251]	eta 0:32:57 lr 0.000661	time 1.8379 (2.2449)	loss 3.9937 (3.5937)	grad_norm 1.8879 (1.3293)	
[2022-01-21 09:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][380/1251]	eta 0:32:35 lr 0.000661	time 1.5146 (2.2451)	loss 3.4558 (3.5999)	grad_norm 1.3296 (1.3292)	
[2022-01-21 09:38:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][390/1251]	eta 0:32:12 lr 0.000661	time 1.5851 (2.2443)	loss 3.7632 (3.6034)	grad_norm 1.7341 (1.3323)	
[2022-01-21 09:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][400/1251]	eta 0:31:49 lr 0.000661	time 1.5677 (2.2442)	loss 3.1022 (3.5965)	grad_norm 1.1607 (1.3313)	
[2022-01-21 09:39:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][410/1251]	eta 0:31:25 lr 0.000661	time 1.7894 (2.2424)	loss 2.9957 (3.5963)	grad_norm 1.2542 (1.3302)	
[2022-01-21 09:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][420/1251]	eta 0:31:03 lr 0.000661	time 2.0611 (2.2429)	loss 4.1453 (3.5963)	grad_norm 1.3212 (1.3301)	
[2022-01-21 09:40:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][430/1251]	eta 0:30:41 lr 0.000661	time 1.6865 (2.2435)	loss 2.9193 (3.5879)	grad_norm 1.2090 (1.3303)	
[2022-01-21 09:40:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][440/1251]	eta 0:30:17 lr 0.000661	time 1.8507 (2.2404)	loss 2.5385 (3.5895)	grad_norm 1.3399 (1.3283)	
[2022-01-21 09:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][450/1251]	eta 0:29:51 lr 0.000661	time 1.6635 (2.2367)	loss 3.9475 (3.5911)	grad_norm 1.1547 (1.3281)	
[2022-01-21 09:41:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][460/1251]	eta 0:29:25 lr 0.000661	time 1.6254 (2.2324)	loss 3.9324 (3.5940)	grad_norm 1.2190 (1.3277)	
[2022-01-21 09:41:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][470/1251]	eta 0:29:01 lr 0.000661	time 2.3497 (2.2292)	loss 3.5277 (3.6004)	grad_norm 1.2061 (1.3259)	
[2022-01-21 09:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][480/1251]	eta 0:28:36 lr 0.000661	time 1.6915 (2.2268)	loss 3.4503 (3.6016)	grad_norm 1.4284 (1.3246)	
[2022-01-21 09:42:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][490/1251]	eta 0:28:16 lr 0.000661	time 2.5557 (2.2290)	loss 4.3506 (3.6025)	grad_norm 1.3712 (1.3243)	
[2022-01-21 09:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][500/1251]	eta 0:27:52 lr 0.000661	time 2.2617 (2.2266)	loss 3.3024 (3.6047)	grad_norm 1.2893 (1.3242)	
[2022-01-21 09:42:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][510/1251]	eta 0:27:30 lr 0.000661	time 2.3984 (2.2273)	loss 4.1243 (3.6017)	grad_norm 1.1928 (1.3249)	
[2022-01-21 09:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][520/1251]	eta 0:27:07 lr 0.000661	time 2.1875 (2.2263)	loss 3.4074 (3.6048)	grad_norm 1.2407 (1.3260)	
[2022-01-21 09:43:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][530/1251]	eta 0:26:47 lr 0.000661	time 2.4581 (2.2297)	loss 3.6967 (3.6042)	grad_norm 1.3363 (1.3264)	
[2022-01-21 09:44:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][540/1251]	eta 0:26:27 lr 0.000661	time 1.8751 (2.2334)	loss 3.9548 (3.6067)	grad_norm 1.2289 (1.3305)	
[2022-01-21 09:44:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][550/1251]	eta 0:26:06 lr 0.000661	time 2.1336 (2.2348)	loss 3.5277 (3.6126)	grad_norm 1.3781 (1.3303)	
[2022-01-21 09:44:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][560/1251]	eta 0:25:41 lr 0.000661	time 1.8799 (2.2310)	loss 4.0081 (3.6125)	grad_norm 1.2659 (1.3299)	
[2022-01-21 09:45:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][570/1251]	eta 0:25:16 lr 0.000661	time 1.8723 (2.2263)	loss 3.9176 (3.6175)	grad_norm 1.4092 (1.3290)	
[2022-01-21 09:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][580/1251]	eta 0:24:51 lr 0.000661	time 1.8380 (2.2226)	loss 4.1856 (3.6174)	grad_norm 1.3114 (1.3294)	
[2022-01-21 09:45:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][590/1251]	eta 0:24:27 lr 0.000661	time 1.9929 (2.2202)	loss 4.1309 (3.6194)	grad_norm 1.3083 (1.3287)	
[2022-01-21 09:46:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][600/1251]	eta 0:24:04 lr 0.000661	time 2.3688 (2.2194)	loss 3.1909 (3.6218)	grad_norm 1.5117 (1.3287)	
[2022-01-21 09:46:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][610/1251]	eta 0:23:40 lr 0.000660	time 2.1278 (2.2167)	loss 3.7775 (3.6241)	grad_norm 1.3653 (1.3284)	
[2022-01-21 09:46:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][620/1251]	eta 0:23:18 lr 0.000660	time 1.9660 (2.2166)	loss 3.7323 (3.6271)	grad_norm 1.4979 (1.3290)	
[2022-01-21 09:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][630/1251]	eta 0:22:55 lr 0.000660	time 2.5842 (2.2156)	loss 3.8396 (3.6289)	grad_norm 1.5001 (1.3294)	
[2022-01-21 09:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][640/1251]	eta 0:22:33 lr 0.000660	time 1.8919 (2.2159)	loss 3.7053 (3.6273)	grad_norm 1.2666 (1.3289)	
[2022-01-21 09:48:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][650/1251]	eta 0:22:12 lr 0.000660	time 2.4270 (2.2179)	loss 4.3109 (3.6288)	grad_norm 1.3433 (1.3292)	
[2022-01-21 09:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][660/1251]	eta 0:21:51 lr 0.000660	time 2.1641 (2.2188)	loss 3.9758 (3.6303)	grad_norm 1.2397 (1.3289)	
[2022-01-21 09:48:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][670/1251]	eta 0:21:30 lr 0.000660	time 2.2515 (2.2207)	loss 3.6343 (3.6332)	grad_norm 1.4004 (1.3285)	
[2022-01-21 09:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][680/1251]	eta 0:21:06 lr 0.000660	time 1.8954 (2.2187)	loss 4.3818 (3.6329)	grad_norm 1.1833 (1.3284)	
[2022-01-21 09:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][690/1251]	eta 0:20:43 lr 0.000660	time 1.5443 (2.2158)	loss 4.2067 (3.6344)	grad_norm 1.2823 (1.3275)	
[2022-01-21 09:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][700/1251]	eta 0:20:19 lr 0.000660	time 2.2499 (2.2138)	loss 2.5761 (3.6354)	grad_norm 1.7640 (1.3272)	
[2022-01-21 09:50:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][710/1251]	eta 0:19:57 lr 0.000660	time 1.9008 (2.2129)	loss 3.5798 (3.6338)	grad_norm 1.2440 (1.3281)	
[2022-01-21 09:50:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][720/1251]	eta 0:19:35 lr 0.000660	time 1.9588 (2.2137)	loss 3.7728 (3.6306)	grad_norm 1.1843 (1.3280)	
[2022-01-21 09:51:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][730/1251]	eta 0:19:13 lr 0.000660	time 2.1701 (2.2141)	loss 3.1087 (3.6283)	grad_norm 1.4591 (1.3283)	
[2022-01-21 09:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][740/1251]	eta 0:18:51 lr 0.000660	time 1.8824 (2.2142)	loss 3.2167 (3.6268)	grad_norm 1.1997 (1.3280)	
[2022-01-21 09:51:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][750/1251]	eta 0:18:30 lr 0.000660	time 2.1397 (2.2156)	loss 3.0027 (3.6244)	grad_norm 1.3533 (1.3284)	
[2022-01-21 09:52:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][760/1251]	eta 0:18:07 lr 0.000660	time 2.4746 (2.2155)	loss 4.0845 (3.6275)	grad_norm 1.2847 (1.3282)	
[2022-01-21 09:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][770/1251]	eta 0:17:44 lr 0.000660	time 2.4962 (2.2137)	loss 3.6096 (3.6255)	grad_norm 1.1705 (1.3281)	
[2022-01-21 09:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][780/1251]	eta 0:17:21 lr 0.000660	time 1.6109 (2.2119)	loss 4.1431 (3.6261)	grad_norm 1.4526 (1.3282)	
[2022-01-21 09:53:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][790/1251]	eta 0:17:01 lr 0.000660	time 2.1710 (2.2148)	loss 3.4835 (3.6281)	grad_norm 1.2987 (1.3294)	
[2022-01-21 09:53:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][800/1251]	eta 0:16:39 lr 0.000660	time 2.5143 (2.2158)	loss 3.8586 (3.6279)	grad_norm 1.2643 (1.3291)	
[2022-01-21 09:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][810/1251]	eta 0:16:17 lr 0.000660	time 2.3643 (2.2164)	loss 3.8811 (3.6310)	grad_norm 1.4107 (1.3294)	
[2022-01-21 09:54:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][820/1251]	eta 0:15:54 lr 0.000660	time 1.6546 (2.2156)	loss 3.4385 (3.6303)	grad_norm 1.2373 (1.3292)	
[2022-01-21 09:54:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][830/1251]	eta 0:15:32 lr 0.000660	time 2.1544 (2.2155)	loss 4.1379 (3.6300)	grad_norm 1.1379 (1.3286)	
[2022-01-21 09:55:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][840/1251]	eta 0:15:09 lr 0.000660	time 1.6653 (2.2130)	loss 3.6047 (3.6279)	grad_norm 1.3636 (1.3289)	
[2022-01-21 09:55:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][850/1251]	eta 0:14:47 lr 0.000660	time 2.1467 (2.2125)	loss 4.1306 (3.6269)	grad_norm 1.3786 (1.3299)	
[2022-01-21 09:55:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][860/1251]	eta 0:14:24 lr 0.000660	time 1.6809 (2.2116)	loss 4.0502 (3.6289)	grad_norm 1.2786 (1.3310)	
[2022-01-21 09:56:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][870/1251]	eta 0:14:04 lr 0.000659	time 2.7291 (2.2160)	loss 3.7129 (3.6312)	grad_norm 1.4795 (1.3315)	
[2022-01-21 09:56:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][880/1251]	eta 0:13:41 lr 0.000659	time 1.6649 (2.2153)	loss 3.3892 (3.6309)	grad_norm 1.5276 (1.3322)	
[2022-01-21 09:56:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][890/1251]	eta 0:13:19 lr 0.000659	time 2.1861 (2.2137)	loss 3.4885 (3.6344)	grad_norm 1.2373 (1.3318)	
[2022-01-21 09:57:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][900/1251]	eta 0:12:56 lr 0.000659	time 1.9741 (2.2120)	loss 2.7407 (3.6336)	grad_norm 1.4969 (1.3321)	
[2022-01-21 09:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][910/1251]	eta 0:12:34 lr 0.000659	time 2.2352 (2.2121)	loss 3.8699 (3.6318)	grad_norm 1.2185 (1.3317)	
[2022-01-21 09:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][920/1251]	eta 0:12:11 lr 0.000659	time 2.0431 (2.2105)	loss 3.7068 (3.6351)	grad_norm 1.1087 (1.3311)	
[2022-01-21 09:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][930/1251]	eta 0:11:49 lr 0.000659	time 1.8607 (2.2089)	loss 3.5627 (3.6362)	grad_norm 1.2877 (1.3310)	
[2022-01-21 09:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][940/1251]	eta 0:11:26 lr 0.000659	time 1.6278 (2.2074)	loss 3.2646 (3.6340)	grad_norm 1.5727 (1.3336)	
[2022-01-21 09:59:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][950/1251]	eta 0:11:04 lr 0.000659	time 2.6319 (2.2066)	loss 3.1706 (3.6319)	grad_norm 1.1664 (1.3344)	
[2022-01-21 09:59:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][960/1251]	eta 0:10:41 lr 0.000659	time 1.8172 (2.2048)	loss 4.1937 (3.6303)	grad_norm 1.2620 (1.3333)	
[2022-01-21 09:59:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][970/1251]	eta 0:10:19 lr 0.000659	time 1.5384 (2.2041)	loss 3.6327 (3.6291)	grad_norm 1.2018 (1.3325)	
[2022-01-21 10:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][980/1251]	eta 0:09:57 lr 0.000659	time 2.2531 (2.2045)	loss 3.8930 (3.6300)	grad_norm 1.1872 (1.3315)	
[2022-01-21 10:00:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][990/1251]	eta 0:09:36 lr 0.000659	time 2.7698 (2.2069)	loss 3.8934 (3.6311)	grad_norm 1.7134 (1.3323)	
[2022-01-21 10:00:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1000/1251]	eta 0:09:13 lr 0.000659	time 2.2010 (2.2066)	loss 3.7466 (3.6308)	grad_norm 1.3500 (1.3325)	
[2022-01-21 10:01:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1010/1251]	eta 0:08:52 lr 0.000659	time 1.6823 (2.2079)	loss 4.1224 (3.6324)	grad_norm 1.2021 (1.3323)	
[2022-01-21 10:01:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1020/1251]	eta 0:08:30 lr 0.000659	time 2.3805 (2.2089)	loss 3.4248 (3.6334)	grad_norm 1.2096 (1.3326)	
[2022-01-21 10:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1030/1251]	eta 0:08:08 lr 0.000659	time 3.2965 (2.2103)	loss 4.0492 (3.6334)	grad_norm 1.2174 (1.3320)	
[2022-01-21 10:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1040/1251]	eta 0:07:46 lr 0.000659	time 2.4565 (2.2106)	loss 4.0420 (3.6332)	grad_norm 1.4676 (1.3314)	
[2022-01-21 10:02:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1050/1251]	eta 0:07:24 lr 0.000659	time 1.8894 (2.2098)	loss 4.1352 (3.6361)	grad_norm 1.3767 (1.3319)	
[2022-01-21 10:03:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1060/1251]	eta 0:07:01 lr 0.000659	time 2.5971 (2.2087)	loss 4.2745 (3.6360)	grad_norm 1.4739 (1.3324)	
[2022-01-21 10:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1070/1251]	eta 0:06:39 lr 0.000659	time 2.8394 (2.2080)	loss 3.3348 (3.6337)	grad_norm 1.3337 (1.3325)	
[2022-01-21 10:03:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1080/1251]	eta 0:06:17 lr 0.000659	time 1.8950 (2.2081)	loss 3.6354 (3.6341)	grad_norm 1.6157 (1.3331)	
[2022-01-21 10:04:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1090/1251]	eta 0:05:55 lr 0.000659	time 2.5849 (2.2085)	loss 3.9734 (3.6368)	grad_norm 1.4826 (1.3331)	
[2022-01-21 10:04:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1100/1251]	eta 0:05:33 lr 0.000659	time 2.5372 (2.2080)	loss 3.9436 (3.6385)	grad_norm 1.2578 (1.3329)	
[2022-01-21 10:04:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1110/1251]	eta 0:05:11 lr 0.000659	time 2.7511 (2.2074)	loss 3.9534 (3.6391)	grad_norm 1.3700 (1.3323)	
[2022-01-21 10:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1120/1251]	eta 0:04:49 lr 0.000658	time 1.8977 (2.2068)	loss 4.6588 (3.6406)	grad_norm 1.2141 (1.3323)	
[2022-01-21 10:05:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1130/1251]	eta 0:04:26 lr 0.000658	time 1.9107 (2.2049)	loss 3.8876 (3.6418)	grad_norm 1.2500 (1.3320)	
[2022-01-21 10:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1140/1251]	eta 0:04:04 lr 0.000658	time 1.9596 (2.2048)	loss 3.8759 (3.6423)	grad_norm 1.3995 (1.3318)	
[2022-01-21 10:06:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1150/1251]	eta 0:03:42 lr 0.000658	time 2.8218 (2.2055)	loss 2.3835 (3.6423)	grad_norm 1.2773 (1.3311)	
[2022-01-21 10:06:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1160/1251]	eta 0:03:20 lr 0.000658	time 1.7942 (2.2055)	loss 3.8531 (3.6436)	grad_norm 1.2296 (1.3311)	
[2022-01-21 10:07:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1170/1251]	eta 0:02:58 lr 0.000658	time 2.0997 (2.2047)	loss 2.9366 (3.6444)	grad_norm 1.2011 (1.3313)	
[2022-01-21 10:07:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1180/1251]	eta 0:02:36 lr 0.000658	time 2.6329 (2.2054)	loss 4.0639 (3.6448)	grad_norm 1.1289 (1.3310)	
[2022-01-21 10:07:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1190/1251]	eta 0:02:14 lr 0.000658	time 2.6786 (2.2066)	loss 4.6634 (3.6450)	grad_norm 1.4376 (1.3312)	
[2022-01-21 10:08:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1200/1251]	eta 0:01:52 lr 0.000658	time 2.2501 (2.2060)	loss 4.2480 (3.6454)	grad_norm 1.4164 (1.3308)	
[2022-01-21 10:08:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1210/1251]	eta 0:01:30 lr 0.000658	time 1.9561 (2.2045)	loss 4.1423 (3.6483)	grad_norm 1.3879 (1.3307)	
[2022-01-21 10:08:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1220/1251]	eta 0:01:08 lr 0.000658	time 2.2403 (2.2035)	loss 2.9265 (3.6461)	grad_norm 1.3236 (1.3304)	
[2022-01-21 10:09:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1230/1251]	eta 0:00:46 lr 0.000658	time 1.7460 (2.2034)	loss 4.3236 (3.6450)	grad_norm 1.2665 (1.3300)	
[2022-01-21 10:09:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1240/1251]	eta 0:00:24 lr 0.000658	time 1.9823 (2.2029)	loss 3.8517 (3.6451)	grad_norm 1.3899 (1.3297)	
[2022-01-21 10:09:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [119/300][1250/1251]	eta 0:00:02 lr 0.000658	time 1.1969 (2.1974)	loss 3.2990 (3.6455)	grad_norm 1.3605 (1.3304)	
[2022-01-21 10:09:50 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 119 training takes 0:45:49
[2022-01-21 10:10:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.587 (18.587)	Loss 1.0913 (1.0913)	Acc@1 74.414 (74.414)	Acc@5 92.676 (92.676)	
[2022-01-21 10:10:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.921 (3.541)	Loss 1.1365 (1.0810)	Acc@1 72.461 (74.609)	Acc@5 92.090 (92.516)	
[2022-01-21 10:10:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.618 (2.586)	Loss 1.0825 (1.0873)	Acc@1 75.195 (74.577)	Acc@5 92.090 (92.420)	
[2022-01-21 10:11:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.891 (2.317)	Loss 1.1022 (1.0924)	Acc@1 74.414 (74.436)	Acc@5 92.578 (92.392)	
[2022-01-21 10:11:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.722 (2.237)	Loss 1.0333 (1.0861)	Acc@1 75.098 (74.464)	Acc@5 94.336 (92.540)	
[2022-01-21 10:11:29 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.502 Acc@5 92.466
[2022-01-21 10:11:29 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.5%
[2022-01-21 10:11:29 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.55%
[2022-01-21 10:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][0/1251]	eta 7:28:15 lr 0.000658	time 21.4995 (21.4995)	loss 3.0650 (3.0650)	grad_norm 1.2852 (1.2852)	
[2022-01-21 10:12:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][10/1251]	eta 1:23:51 lr 0.000658	time 1.5101 (4.0544)	loss 3.0806 (3.4787)	grad_norm 1.2243 (1.3707)	
[2022-01-21 10:12:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][20/1251]	eta 1:05:16 lr 0.000658	time 2.1386 (3.1816)	loss 3.8310 (3.6137)	grad_norm 1.6305 (1.3678)	
[2022-01-21 10:12:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][30/1251]	eta 0:56:46 lr 0.000658	time 1.4792 (2.7903)	loss 3.8554 (3.6732)	grad_norm 1.3331 (1.3516)	
[2022-01-21 10:13:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][40/1251]	eta 0:55:02 lr 0.000658	time 3.9319 (2.7269)	loss 3.0725 (3.6983)	grad_norm 1.3515 (1.3495)	
[2022-01-21 10:13:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][50/1251]	eta 0:52:29 lr 0.000658	time 1.8823 (2.6221)	loss 2.5843 (3.7034)	grad_norm 1.4340 (1.3411)	
[2022-01-21 10:14:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][60/1251]	eta 0:50:28 lr 0.000658	time 1.8258 (2.5427)	loss 4.3176 (3.6835)	grad_norm 1.2876 (1.3479)	
[2022-01-21 10:14:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][70/1251]	eta 0:49:07 lr 0.000658	time 1.8198 (2.4962)	loss 3.6891 (3.6570)	grad_norm 1.2795 (1.3536)	
[2022-01-21 10:14:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][80/1251]	eta 0:48:12 lr 0.000658	time 3.8165 (2.4697)	loss 3.9696 (3.6343)	grad_norm 1.6585 (1.3553)	
[2022-01-21 10:15:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][90/1251]	eta 0:47:18 lr 0.000658	time 2.5822 (2.4451)	loss 3.5207 (3.6377)	grad_norm 1.2750 (1.3533)	
[2022-01-21 10:15:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][100/1251]	eta 0:46:19 lr 0.000658	time 2.2783 (2.4146)	loss 3.9835 (3.6456)	grad_norm 1.2971 (1.3633)	
[2022-01-21 10:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][110/1251]	eta 0:45:24 lr 0.000658	time 1.6386 (2.3881)	loss 3.5693 (3.6629)	grad_norm 1.1955 (1.3714)	
[2022-01-21 10:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][120/1251]	eta 0:44:44 lr 0.000657	time 3.4649 (2.3733)	loss 4.0382 (3.6415)	grad_norm 1.4584 (1.3714)	
[2022-01-21 10:16:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][130/1251]	eta 0:44:14 lr 0.000657	time 3.1377 (2.3684)	loss 3.8232 (3.6431)	grad_norm 1.5224 (1.3689)	
[2022-01-21 10:17:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][140/1251]	eta 0:43:40 lr 0.000657	time 1.5375 (2.3585)	loss 3.2697 (3.6292)	grad_norm 1.5815 (1.3689)	
[2022-01-21 10:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][150/1251]	eta 0:43:07 lr 0.000657	time 1.8015 (2.3498)	loss 3.7350 (3.6249)	grad_norm 1.4163 (1.3752)	
[2022-01-21 10:17:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][160/1251]	eta 0:42:38 lr 0.000657	time 3.5209 (2.3449)	loss 3.7751 (3.6330)	grad_norm 1.1124 (1.3707)	
[2022-01-21 10:18:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][170/1251]	eta 0:41:59 lr 0.000657	time 2.1560 (2.3310)	loss 4.0332 (3.6309)	grad_norm 1.2055 (1.3677)	
[2022-01-21 10:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][180/1251]	eta 0:41:12 lr 0.000657	time 1.5548 (2.3082)	loss 4.4303 (3.6358)	grad_norm 1.3737 (1.3629)	
[2022-01-21 10:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][190/1251]	eta 0:40:38 lr 0.000657	time 2.1313 (2.2983)	loss 4.1696 (3.6315)	grad_norm 1.4767 (1.3632)	
[2022-01-21 10:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][200/1251]	eta 0:40:17 lr 0.000657	time 3.0234 (2.2999)	loss 4.1183 (3.6412)	grad_norm 1.2233 (1.3625)	
[2022-01-21 10:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][210/1251]	eta 0:39:45 lr 0.000657	time 1.8217 (2.2920)	loss 3.4320 (3.6382)	grad_norm 1.1737 (1.3580)	
[2022-01-21 10:19:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][220/1251]	eta 0:39:17 lr 0.000657	time 2.0309 (2.2865)	loss 4.2511 (3.6355)	grad_norm 1.1761 (1.3570)	
[2022-01-21 10:20:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][230/1251]	eta 0:38:47 lr 0.000657	time 1.6526 (2.2799)	loss 4.0083 (3.6435)	grad_norm 1.4785 (1.3555)	
[2022-01-21 10:20:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][240/1251]	eta 0:38:15 lr 0.000657	time 2.4959 (2.2710)	loss 4.1550 (3.6408)	grad_norm 1.3262 (1.3560)	
[2022-01-21 10:20:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][250/1251]	eta 0:37:47 lr 0.000657	time 2.4105 (2.2656)	loss 3.0759 (3.6443)	grad_norm 1.3522 (1.3555)	
[2022-01-21 10:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][260/1251]	eta 0:37:21 lr 0.000657	time 1.8920 (2.2615)	loss 3.2496 (3.6470)	grad_norm 1.2159 (1.3548)	
[2022-01-21 10:21:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][270/1251]	eta 0:36:56 lr 0.000657	time 2.0729 (2.2597)	loss 2.9563 (3.6545)	grad_norm 1.3311 (1.3548)	
[2022-01-21 10:22:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][280/1251]	eta 0:36:33 lr 0.000657	time 3.1048 (2.2590)	loss 2.8992 (3.6563)	grad_norm 1.2134 (1.3534)	
[2022-01-21 10:22:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][290/1251]	eta 0:36:07 lr 0.000657	time 1.7263 (2.2555)	loss 3.9203 (3.6572)	grad_norm 1.7367 (1.3533)	
[2022-01-21 10:22:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][300/1251]	eta 0:35:43 lr 0.000657	time 1.8447 (2.2539)	loss 2.9060 (3.6590)	grad_norm 1.3240 (1.3531)	
[2022-01-21 10:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][310/1251]	eta 0:35:18 lr 0.000657	time 2.2021 (2.2518)	loss 4.0146 (3.6625)	grad_norm 1.6640 (1.3539)	
[2022-01-21 10:23:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][320/1251]	eta 0:34:59 lr 0.000657	time 2.6592 (2.2550)	loss 4.0218 (3.6615)	grad_norm 1.7309 (1.3545)	
[2022-01-21 10:23:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][330/1251]	eta 0:34:35 lr 0.000657	time 2.8263 (2.2531)	loss 4.1097 (3.6649)	grad_norm 1.3003 (1.3563)	
[2022-01-21 10:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][340/1251]	eta 0:34:11 lr 0.000657	time 1.9272 (2.2524)	loss 2.7884 (3.6627)	grad_norm 1.2722 (1.3556)	
[2022-01-21 10:24:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][350/1251]	eta 0:33:48 lr 0.000657	time 1.7286 (2.2511)	loss 4.1939 (3.6638)	grad_norm 1.1865 (1.3551)	
[2022-01-21 10:25:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][360/1251]	eta 0:33:21 lr 0.000657	time 2.1587 (2.2468)	loss 4.1087 (3.6619)	grad_norm 1.4219 (1.3557)	
[2022-01-21 10:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][370/1251]	eta 0:32:54 lr 0.000657	time 2.2305 (2.2409)	loss 3.1246 (3.6608)	grad_norm 1.3559 (1.3568)	
[2022-01-21 10:25:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][380/1251]	eta 0:32:27 lr 0.000656	time 1.8254 (2.2358)	loss 4.0465 (3.6691)	grad_norm 1.1847 (1.3564)	
[2022-01-21 10:26:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][390/1251]	eta 0:32:02 lr 0.000656	time 2.6079 (2.2325)	loss 2.6327 (3.6654)	grad_norm 1.3351 (1.3547)	
[2022-01-21 10:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][400/1251]	eta 0:31:37 lr 0.000656	time 2.1091 (2.2295)	loss 2.3843 (3.6685)	grad_norm 1.4652 (1.3554)	
[2022-01-21 10:26:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][410/1251]	eta 0:31:15 lr 0.000656	time 2.6428 (2.2295)	loss 3.1625 (3.6642)	grad_norm 1.8143 (1.3571)	
[2022-01-21 10:27:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][420/1251]	eta 0:30:55 lr 0.000656	time 2.1541 (2.2331)	loss 4.4166 (3.6648)	grad_norm 1.1507 (1.3583)	
[2022-01-21 10:27:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][430/1251]	eta 0:30:36 lr 0.000656	time 2.5495 (2.2375)	loss 3.6897 (3.6658)	grad_norm 1.3581 (1.3576)	
[2022-01-21 10:27:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][440/1251]	eta 0:30:12 lr 0.000656	time 2.0245 (2.2354)	loss 3.9085 (3.6679)	grad_norm 1.4243 (1.3568)	
[2022-01-21 10:28:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][450/1251]	eta 0:29:49 lr 0.000656	time 1.6225 (2.2345)	loss 3.2879 (3.6703)	grad_norm 1.3837 (1.3542)	
[2022-01-21 10:28:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][460/1251]	eta 0:29:26 lr 0.000656	time 1.8993 (2.2336)	loss 3.3169 (3.6671)	grad_norm 1.4024 (1.3531)	
[2022-01-21 10:28:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][470/1251]	eta 0:29:01 lr 0.000656	time 1.7528 (2.2294)	loss 3.5400 (3.6661)	grad_norm 1.2321 (1.3524)	
[2022-01-21 10:29:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][480/1251]	eta 0:28:36 lr 0.000656	time 2.2965 (2.2259)	loss 4.5245 (3.6676)	grad_norm 1.3373 (1.3527)	
[2022-01-21 10:29:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][490/1251]	eta 0:28:12 lr 0.000656	time 1.8398 (2.2240)	loss 4.1142 (3.6661)	grad_norm 1.4537 (1.3518)	
[2022-01-21 10:30:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][500/1251]	eta 0:27:53 lr 0.000656	time 2.1496 (2.2280)	loss 3.2593 (3.6663)	grad_norm 1.0770 (1.3521)	
[2022-01-21 10:30:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][510/1251]	eta 0:27:29 lr 0.000656	time 1.5707 (2.2266)	loss 3.9388 (3.6669)	grad_norm 1.2214 (1.3517)	
[2022-01-21 10:30:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][520/1251]	eta 0:27:06 lr 0.000656	time 2.1997 (2.2254)	loss 3.8870 (3.6660)	grad_norm 1.2519 (1.3513)	
[2022-01-21 10:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][530/1251]	eta 0:26:45 lr 0.000656	time 2.4206 (2.2273)	loss 2.7927 (3.6634)	grad_norm 1.3571 (1.3519)	
[2022-01-21 10:31:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][540/1251]	eta 0:26:24 lr 0.000656	time 1.8776 (2.2285)	loss 4.1238 (3.6669)	grad_norm 1.4002 (1.3534)	
[2022-01-21 10:31:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][550/1251]	eta 0:25:58 lr 0.000656	time 2.1868 (2.2227)	loss 3.7255 (3.6693)	grad_norm 1.2925 (1.3526)	
[2022-01-21 10:32:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][560/1251]	eta 0:25:33 lr 0.000656	time 2.1299 (2.2192)	loss 2.9921 (3.6667)	grad_norm 1.3755 (1.3527)	
[2022-01-21 10:32:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][570/1251]	eta 0:25:13 lr 0.000656	time 2.5854 (2.2227)	loss 3.8241 (3.6693)	grad_norm 1.5395 (1.3522)	
[2022-01-21 10:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][580/1251]	eta 0:24:51 lr 0.000656	time 2.1098 (2.2230)	loss 3.4349 (3.6707)	grad_norm 1.2539 (1.3517)	
[2022-01-21 10:33:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][590/1251]	eta 0:24:27 lr 0.000656	time 2.1339 (2.2200)	loss 2.7839 (3.6661)	grad_norm 1.2079 (1.3506)	
[2022-01-21 10:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][600/1251]	eta 0:24:01 lr 0.000656	time 2.1481 (2.2145)	loss 3.7872 (3.6674)	grad_norm 1.2190 (1.3510)	
[2022-01-21 10:34:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][610/1251]	eta 0:23:38 lr 0.000656	time 2.0744 (2.2123)	loss 3.9665 (3.6680)	grad_norm 1.1925 (1.3523)	
[2022-01-21 10:34:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][620/1251]	eta 0:23:17 lr 0.000656	time 1.8285 (2.2143)	loss 3.6448 (3.6674)	grad_norm 1.4467 (1.3535)	
[2022-01-21 10:34:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][630/1251]	eta 0:22:54 lr 0.000655	time 2.1804 (2.2130)	loss 3.0244 (3.6684)	grad_norm 1.2250 (1.3541)	
[2022-01-21 10:35:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][640/1251]	eta 0:22:34 lr 0.000655	time 2.8329 (2.2162)	loss 3.6230 (3.6649)	grad_norm 1.1411 (1.3533)	
[2022-01-21 10:35:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][650/1251]	eta 0:22:13 lr 0.000655	time 3.3594 (2.2182)	loss 4.1825 (3.6613)	grad_norm 1.5674 (1.3533)	
[2022-01-21 10:35:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][660/1251]	eta 0:21:51 lr 0.000655	time 1.6691 (2.2197)	loss 4.0961 (3.6611)	grad_norm 1.2062 (1.3540)	
[2022-01-21 10:36:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][670/1251]	eta 0:21:28 lr 0.000655	time 1.8929 (2.2183)	loss 4.4877 (3.6606)	grad_norm 1.4790 (1.3533)	
[2022-01-21 10:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][680/1251]	eta 0:21:04 lr 0.000655	time 2.0135 (2.2148)	loss 3.7626 (3.6619)	grad_norm 1.2589 (1.3528)	
[2022-01-21 10:36:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][690/1251]	eta 0:20:40 lr 0.000655	time 1.7903 (2.2119)	loss 4.3685 (3.6630)	grad_norm 1.2914 (1.3516)	
[2022-01-21 10:37:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][700/1251]	eta 0:20:17 lr 0.000655	time 1.7704 (2.2102)	loss 2.7232 (3.6631)	grad_norm 1.3061 (1.3511)	
[2022-01-21 10:37:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][710/1251]	eta 0:19:55 lr 0.000655	time 2.0818 (2.2097)	loss 3.6555 (3.6638)	grad_norm 1.3691 (1.3501)	
[2022-01-21 10:38:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][720/1251]	eta 0:19:33 lr 0.000655	time 2.1575 (2.2094)	loss 3.3169 (3.6624)	grad_norm 1.4758 (1.3496)	
[2022-01-21 10:38:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][730/1251]	eta 0:19:11 lr 0.000655	time 1.9953 (2.2095)	loss 4.2296 (3.6649)	grad_norm 1.4394 (1.3490)	
[2022-01-21 10:38:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][740/1251]	eta 0:18:48 lr 0.000655	time 1.8635 (2.2087)	loss 3.8012 (3.6607)	grad_norm 1.2995 (1.3492)	
[2022-01-21 10:39:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][750/1251]	eta 0:18:25 lr 0.000655	time 2.2927 (2.2074)	loss 4.5236 (3.6630)	grad_norm 1.3843 (1.3496)	
[2022-01-21 10:39:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][760/1251]	eta 0:18:03 lr 0.000655	time 2.1368 (2.2067)	loss 3.0866 (3.6618)	grad_norm 1.2845 (1.3497)	
[2022-01-21 10:39:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][770/1251]	eta 0:17:41 lr 0.000655	time 1.9642 (2.2068)	loss 3.7161 (3.6636)	grad_norm 1.3647 (1.3500)	
[2022-01-21 10:40:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][780/1251]	eta 0:17:19 lr 0.000655	time 1.7333 (2.2063)	loss 3.8897 (3.6638)	grad_norm 1.4599 (1.3503)	
[2022-01-21 10:40:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][790/1251]	eta 0:16:57 lr 0.000655	time 1.9720 (2.2072)	loss 2.6364 (3.6619)	grad_norm 1.3914 (1.3513)	
[2022-01-21 10:40:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][800/1251]	eta 0:16:36 lr 0.000655	time 1.9816 (2.2097)	loss 3.0033 (3.6572)	grad_norm 1.2467 (1.3518)	
[2022-01-21 10:41:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][810/1251]	eta 0:16:13 lr 0.000655	time 1.6967 (2.2085)	loss 3.8731 (3.6562)	grad_norm 1.2160 (1.3529)	
[2022-01-21 10:41:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][820/1251]	eta 0:15:52 lr 0.000655	time 1.9521 (2.2092)	loss 4.0838 (3.6588)	grad_norm 1.3600 (1.3537)	
[2022-01-21 10:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][830/1251]	eta 0:15:29 lr 0.000655	time 1.5988 (2.2072)	loss 4.4233 (3.6646)	grad_norm 1.2879 (1.3531)	
[2022-01-21 10:42:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][840/1251]	eta 0:15:06 lr 0.000655	time 1.6350 (2.2060)	loss 2.9417 (3.6625)	grad_norm 1.1938 (1.3524)	
[2022-01-21 10:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][850/1251]	eta 0:14:43 lr 0.000655	time 2.2332 (2.2034)	loss 2.8965 (3.6623)	grad_norm 1.3524 (1.3523)	
[2022-01-21 10:43:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][860/1251]	eta 0:14:21 lr 0.000655	time 1.8809 (2.2038)	loss 4.1421 (3.6641)	grad_norm 1.3228 (1.3524)	
[2022-01-21 10:43:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][870/1251]	eta 0:13:59 lr 0.000655	time 1.5574 (2.2026)	loss 2.9455 (3.6640)	grad_norm 1.2945 (1.3521)	
[2022-01-21 10:43:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][880/1251]	eta 0:13:36 lr 0.000654	time 1.9636 (2.2016)	loss 3.5119 (3.6643)	grad_norm 1.2879 (1.3525)	
[2022-01-21 10:44:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][890/1251]	eta 0:13:15 lr 0.000654	time 2.0828 (2.2027)	loss 2.6579 (3.6644)	grad_norm 1.4209 (1.3523)	
[2022-01-21 10:44:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][900/1251]	eta 0:12:55 lr 0.000654	time 1.8115 (2.2085)	loss 3.5397 (3.6636)	grad_norm 1.2202 (1.3519)	
[2022-01-21 10:45:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][910/1251]	eta 0:12:33 lr 0.000654	time 1.9062 (2.2093)	loss 4.1573 (3.6647)	grad_norm 1.3886 (1.3517)	
[2022-01-21 10:45:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][920/1251]	eta 0:12:11 lr 0.000654	time 2.0031 (2.2086)	loss 2.7032 (3.6628)	grad_norm 1.3602 (1.3519)	
[2022-01-21 10:45:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][930/1251]	eta 0:11:48 lr 0.000654	time 1.5513 (2.2066)	loss 3.8974 (3.6612)	grad_norm 1.4697 (1.3515)	
[2022-01-21 10:46:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][940/1251]	eta 0:11:25 lr 0.000654	time 1.9830 (2.2045)	loss 3.8137 (3.6634)	grad_norm 1.2648 (1.3506)	
[2022-01-21 10:46:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][950/1251]	eta 0:11:03 lr 0.000654	time 2.2912 (2.2040)	loss 3.2885 (3.6649)	grad_norm 1.2727 (1.3515)	
[2022-01-21 10:46:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][960/1251]	eta 0:10:41 lr 0.000654	time 2.1877 (2.2042)	loss 2.5692 (3.6648)	grad_norm 1.2388 (1.3516)	
[2022-01-21 10:47:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][970/1251]	eta 0:10:19 lr 0.000654	time 1.8569 (2.2050)	loss 3.8485 (3.6648)	grad_norm 1.3364 (1.3521)	
[2022-01-21 10:47:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][980/1251]	eta 0:09:57 lr 0.000654	time 2.2103 (2.2047)	loss 3.7765 (3.6663)	grad_norm 1.1952 (1.3513)	
[2022-01-21 10:47:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][990/1251]	eta 0:09:35 lr 0.000654	time 2.1456 (2.2055)	loss 4.4855 (3.6671)	grad_norm 1.4854 (1.3524)	
[2022-01-21 10:48:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1000/1251]	eta 0:09:13 lr 0.000654	time 2.2494 (2.2059)	loss 3.1855 (3.6679)	grad_norm 1.6649 (1.3525)	
[2022-01-21 10:48:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1010/1251]	eta 0:08:51 lr 0.000654	time 1.5579 (2.2054)	loss 3.4836 (3.6661)	grad_norm 1.1420 (1.3526)	
[2022-01-21 10:49:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1020/1251]	eta 0:08:29 lr 0.000654	time 2.1804 (2.2043)	loss 3.9272 (3.6635)	grad_norm 1.3804 (1.3526)	
[2022-01-21 10:49:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1030/1251]	eta 0:08:06 lr 0.000654	time 1.9002 (2.2028)	loss 4.1479 (3.6653)	grad_norm 1.2937 (1.3519)	
[2022-01-21 10:49:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1040/1251]	eta 0:07:44 lr 0.000654	time 2.4230 (2.2024)	loss 3.7179 (3.6628)	grad_norm 1.4023 (1.3519)	
[2022-01-21 10:50:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1050/1251]	eta 0:07:22 lr 0.000654	time 1.8609 (2.2016)	loss 3.5960 (3.6641)	grad_norm 1.3041 (1.3517)	
[2022-01-21 10:50:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1060/1251]	eta 0:07:00 lr 0.000654	time 2.2795 (2.2016)	loss 2.9646 (3.6660)	grad_norm 1.6877 (1.3524)	
[2022-01-21 10:50:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1070/1251]	eta 0:06:38 lr 0.000654	time 1.5644 (2.2027)	loss 4.0529 (3.6667)	grad_norm 1.2402 (1.3520)	
[2022-01-21 10:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1080/1251]	eta 0:06:16 lr 0.000654	time 2.7892 (2.2033)	loss 3.5394 (3.6646)	grad_norm 1.2534 (1.3518)	
[2022-01-21 10:51:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1090/1251]	eta 0:05:54 lr 0.000654	time 1.9650 (2.2026)	loss 4.0875 (3.6652)	grad_norm 1.3653 (1.3513)	
[2022-01-21 10:51:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1100/1251]	eta 0:05:32 lr 0.000654	time 1.9780 (2.2023)	loss 3.9758 (3.6656)	grad_norm 1.2958 (1.3502)	
[2022-01-21 10:52:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1110/1251]	eta 0:05:10 lr 0.000654	time 1.7866 (2.2023)	loss 3.9959 (3.6644)	grad_norm 1.1985 (1.3496)	
[2022-01-21 10:52:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1120/1251]	eta 0:04:48 lr 0.000654	time 2.4757 (2.2019)	loss 3.2132 (3.6618)	grad_norm 1.1793 (1.3493)	
[2022-01-21 10:52:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1130/1251]	eta 0:04:26 lr 0.000654	time 2.2032 (2.2003)	loss 3.4295 (3.6624)	grad_norm 1.2700 (1.3491)	
[2022-01-21 10:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1140/1251]	eta 0:04:04 lr 0.000653	time 1.6658 (2.1993)	loss 3.5592 (3.6624)	grad_norm 1.2767 (1.3483)	
[2022-01-21 10:53:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1150/1251]	eta 0:03:42 lr 0.000653	time 1.9221 (2.2003)	loss 3.5846 (3.6623)	grad_norm 1.2278 (1.3478)	
[2022-01-21 10:54:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1160/1251]	eta 0:03:20 lr 0.000653	time 2.4210 (2.2021)	loss 3.0362 (3.6619)	grad_norm 1.4228 (1.3475)	
[2022-01-21 10:54:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1170/1251]	eta 0:02:58 lr 0.000653	time 3.1459 (2.2040)	loss 3.8438 (3.6618)	grad_norm 1.1438 (1.3469)	
[2022-01-21 10:54:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1180/1251]	eta 0:02:36 lr 0.000653	time 1.7979 (2.2039)	loss 2.5427 (3.6613)	grad_norm 1.3099 (1.3473)	
[2022-01-21 10:55:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1190/1251]	eta 0:02:14 lr 0.000653	time 1.7833 (2.2033)	loss 4.3048 (3.6583)	grad_norm 1.1762 (1.3474)	
[2022-01-21 10:55:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1200/1251]	eta 0:01:52 lr 0.000653	time 1.5745 (2.2014)	loss 4.3436 (3.6592)	grad_norm 1.2756 (1.3474)	
[2022-01-21 10:55:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1210/1251]	eta 0:01:30 lr 0.000653	time 1.6338 (2.1987)	loss 3.5671 (3.6612)	grad_norm 1.3803 (1.3477)	
[2022-01-21 10:56:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1220/1251]	eta 0:01:08 lr 0.000653	time 1.8598 (2.1971)	loss 4.0191 (3.6614)	grad_norm 1.2621 (1.3474)	
[2022-01-21 10:56:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1230/1251]	eta 0:00:46 lr 0.000653	time 2.3457 (2.1961)	loss 4.1682 (3.6632)	grad_norm 1.2068 (1.3477)	
[2022-01-21 10:56:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1240/1251]	eta 0:00:24 lr 0.000653	time 1.5427 (2.1977)	loss 4.3632 (3.6628)	grad_norm 1.4153 (1.3478)	
[2022-01-21 10:57:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [120/300][1250/1251]	eta 0:00:02 lr 0.000653	time 1.1840 (2.1922)	loss 2.3908 (3.6619)	grad_norm 1.2903 (1.3476)	
[2022-01-21 10:57:12 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 120 training takes 0:45:42
[2022-01-21 10:57:12 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_120 saving......
[2022-01-21 10:57:23 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_120 saved !!!
[2022-01-21 10:57:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.723 (16.723)	Loss 1.0924 (1.0924)	Acc@1 74.316 (74.316)	Acc@5 93.164 (93.164)	
[2022-01-21 10:57:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.400 (2.892)	Loss 1.0867 (1.0646)	Acc@1 74.512 (74.769)	Acc@5 92.383 (92.694)	
[2022-01-21 10:58:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.649 (2.397)	Loss 1.0385 (1.0747)	Acc@1 75.391 (74.595)	Acc@5 93.848 (92.680)	
[2022-01-21 10:58:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.925 (2.073)	Loss 1.0164 (1.0663)	Acc@1 75.977 (74.767)	Acc@5 93.164 (92.736)	
[2022-01-21 10:58:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.315 (1.932)	Loss 1.0824 (1.0658)	Acc@1 73.145 (74.869)	Acc@5 91.699 (92.635)	
[2022-01-21 10:58:50 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.952 Acc@5 92.696
[2022-01-21 10:58:50 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.0%
[2022-01-21 10:58:50 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.95%
[2022-01-21 10:59:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][0/1251]	eta 7:39:54 lr 0.000653	time 22.0581 (22.0581)	loss 3.1582 (3.1582)	grad_norm 1.2712 (1.2712)	
[2022-01-21 10:59:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][10/1251]	eta 1:22:33 lr 0.000653	time 2.1256 (3.9914)	loss 3.9637 (3.7630)	grad_norm 1.2706 (1.3200)	
[2022-01-21 10:59:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][20/1251]	eta 1:06:02 lr 0.000653	time 2.7280 (3.2193)	loss 3.9857 (3.7534)	grad_norm 1.1258 (1.3259)	
[2022-01-21 11:00:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][30/1251]	eta 0:59:42 lr 0.000653	time 1.8942 (2.9343)	loss 3.9605 (3.8079)	grad_norm 1.7471 (1.3605)	
[2022-01-21 11:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][40/1251]	eta 0:56:12 lr 0.000653	time 3.2709 (2.7848)	loss 3.8423 (3.7345)	grad_norm 1.3544 (1.3652)	
[2022-01-21 11:01:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][50/1251]	eta 0:53:37 lr 0.000653	time 1.9580 (2.6791)	loss 2.8108 (3.6865)	grad_norm 1.5400 (1.3565)	
[2022-01-21 11:01:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][60/1251]	eta 0:50:58 lr 0.000653	time 1.6884 (2.5679)	loss 3.3440 (3.6553)	grad_norm 1.2285 (1.3542)	
[2022-01-21 11:01:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][70/1251]	eta 0:49:17 lr 0.000653	time 2.0721 (2.5046)	loss 2.7684 (3.6542)	grad_norm 1.6829 (1.3596)	
[2022-01-21 11:02:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][80/1251]	eta 0:47:55 lr 0.000653	time 2.8399 (2.4554)	loss 2.7728 (3.6478)	grad_norm 1.3937 (1.3576)	
[2022-01-21 11:02:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][90/1251]	eta 0:46:49 lr 0.000653	time 1.9513 (2.4201)	loss 3.9256 (3.6333)	grad_norm 1.5137 (1.3620)	
[2022-01-21 11:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][100/1251]	eta 0:46:02 lr 0.000653	time 1.9388 (2.3998)	loss 3.1597 (3.6217)	grad_norm 1.2900 (1.3635)	
[2022-01-21 11:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][110/1251]	eta 0:45:13 lr 0.000653	time 1.8586 (2.3781)	loss 3.6976 (3.6011)	grad_norm 1.3930 (1.3670)	
[2022-01-21 11:03:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][120/1251]	eta 0:44:52 lr 0.000653	time 3.1171 (2.3808)	loss 4.2592 (3.6009)	grad_norm 1.5008 (1.3695)	
[2022-01-21 11:04:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][130/1251]	eta 0:44:12 lr 0.000653	time 2.4216 (2.3661)	loss 3.7849 (3.5952)	grad_norm 1.3888 (1.3664)	
[2022-01-21 11:04:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][140/1251]	eta 0:43:30 lr 0.000652	time 1.6882 (2.3500)	loss 3.6574 (3.5912)	grad_norm 1.1947 (1.3646)	
[2022-01-21 11:04:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][150/1251]	eta 0:42:55 lr 0.000652	time 1.9227 (2.3396)	loss 4.0500 (3.6060)	grad_norm 1.3610 (1.3586)	
[2022-01-21 11:05:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][160/1251]	eta 0:42:23 lr 0.000652	time 3.1196 (2.3310)	loss 2.7156 (3.5839)	grad_norm 1.3499 (1.3614)	
[2022-01-21 11:05:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][170/1251]	eta 0:41:51 lr 0.000652	time 2.3883 (2.3238)	loss 3.0411 (3.5863)	grad_norm 1.3156 (1.3604)	
[2022-01-21 11:05:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][180/1251]	eta 0:41:23 lr 0.000652	time 2.1407 (2.3188)	loss 3.4002 (3.5837)	grad_norm 1.3708 (1.3589)	
[2022-01-21 11:06:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][190/1251]	eta 0:40:57 lr 0.000652	time 2.1282 (2.3165)	loss 2.5486 (3.5860)	grad_norm 1.2105 (1.3616)	
[2022-01-21 11:06:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][200/1251]	eta 0:40:26 lr 0.000652	time 2.7419 (2.3084)	loss 3.5428 (3.5955)	grad_norm 1.2021 (1.3646)	
[2022-01-21 11:06:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][210/1251]	eta 0:39:52 lr 0.000652	time 1.8748 (2.2985)	loss 3.2193 (3.5832)	grad_norm 1.2156 (1.3586)	
[2022-01-21 11:07:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][220/1251]	eta 0:39:20 lr 0.000652	time 1.7995 (2.2898)	loss 4.3268 (3.5881)	grad_norm 1.4755 (1.3569)	
[2022-01-21 11:07:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][230/1251]	eta 0:38:47 lr 0.000652	time 1.6897 (2.2799)	loss 4.1406 (3.6020)	grad_norm 1.3664 (1.3572)	
[2022-01-21 11:07:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][240/1251]	eta 0:38:18 lr 0.000652	time 2.8400 (2.2739)	loss 3.9903 (3.6054)	grad_norm 1.0642 (1.3598)	
[2022-01-21 11:08:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][250/1251]	eta 0:37:48 lr 0.000652	time 2.3279 (2.2666)	loss 4.2847 (3.6046)	grad_norm 1.3669 (1.3591)	
[2022-01-21 11:08:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][260/1251]	eta 0:37:19 lr 0.000652	time 1.6229 (2.2595)	loss 4.3565 (3.6078)	grad_norm 1.3838 (1.3569)	
[2022-01-21 11:09:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][270/1251]	eta 0:36:55 lr 0.000652	time 2.2276 (2.2588)	loss 3.7586 (3.6124)	grad_norm 1.3884 (1.3535)	
[2022-01-21 11:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][280/1251]	eta 0:36:39 lr 0.000652	time 3.1579 (2.2650)	loss 4.1712 (3.6086)	grad_norm 1.2986 (1.3528)	
[2022-01-21 11:09:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][290/1251]	eta 0:36:17 lr 0.000652	time 2.3966 (2.2655)	loss 4.0540 (3.5968)	grad_norm 1.4571 (1.3536)	
[2022-01-21 11:10:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][300/1251]	eta 0:35:54 lr 0.000652	time 2.2767 (2.2653)	loss 3.4197 (3.5985)	grad_norm 1.2028 (1.3532)	
[2022-01-21 11:10:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][310/1251]	eta 0:35:29 lr 0.000652	time 1.9838 (2.2632)	loss 4.4353 (3.5978)	grad_norm 1.4498 (1.3511)	
[2022-01-21 11:10:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][320/1251]	eta 0:35:03 lr 0.000652	time 3.2519 (2.2590)	loss 3.5702 (3.5990)	grad_norm 1.3552 (1.3499)	
[2022-01-21 11:11:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][330/1251]	eta 0:34:32 lr 0.000652	time 1.8513 (2.2503)	loss 3.4768 (3.5949)	grad_norm 1.3604 (1.3507)	
[2022-01-21 11:11:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][340/1251]	eta 0:34:06 lr 0.000652	time 1.9203 (2.2460)	loss 2.9343 (3.5940)	grad_norm 1.1521 (1.3496)	
[2022-01-21 11:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][350/1251]	eta 0:33:43 lr 0.000652	time 2.5163 (2.2459)	loss 2.8041 (3.5947)	grad_norm 1.2505 (1.3492)	
[2022-01-21 11:12:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][360/1251]	eta 0:33:24 lr 0.000652	time 2.8147 (2.2496)	loss 3.9897 (3.5972)	grad_norm 1.1480 (1.3475)	
[2022-01-21 11:12:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][370/1251]	eta 0:33:05 lr 0.000652	time 3.0589 (2.2536)	loss 4.2509 (3.6005)	grad_norm 1.2463 (1.3481)	
[2022-01-21 11:13:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][380/1251]	eta 0:32:39 lr 0.000652	time 2.0431 (2.2494)	loss 3.8098 (3.6059)	grad_norm 1.1759 (1.3467)	
[2022-01-21 11:13:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][390/1251]	eta 0:32:15 lr 0.000651	time 3.0958 (2.2475)	loss 3.0284 (3.6094)	grad_norm 1.5005 (1.3485)	
[2022-01-21 11:13:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][400/1251]	eta 0:31:48 lr 0.000651	time 1.8608 (2.2431)	loss 3.5499 (3.6040)	grad_norm 1.1970 (1.3520)	
[2022-01-21 11:14:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][410/1251]	eta 0:31:23 lr 0.000651	time 2.2550 (2.2399)	loss 3.9436 (3.6103)	grad_norm 1.4867 (1.3508)	
[2022-01-21 11:14:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][420/1251]	eta 0:31:00 lr 0.000651	time 1.7107 (2.2389)	loss 3.4617 (3.6164)	grad_norm 1.2092 (1.3499)	
[2022-01-21 11:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][430/1251]	eta 0:30:39 lr 0.000651	time 2.6792 (2.2403)	loss 3.9282 (3.6192)	grad_norm 1.3918 (1.3479)	
[2022-01-21 11:15:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][440/1251]	eta 0:30:13 lr 0.000651	time 1.9029 (2.2359)	loss 3.3882 (3.6168)	grad_norm 1.2552 (1.3469)	
[2022-01-21 11:15:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][450/1251]	eta 0:29:48 lr 0.000651	time 2.5293 (2.2330)	loss 4.3048 (3.6202)	grad_norm 1.2596 (1.3471)	
[2022-01-21 11:15:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][460/1251]	eta 0:29:25 lr 0.000651	time 2.4957 (2.2317)	loss 3.5135 (3.6185)	grad_norm 1.5215 (1.3481)	
[2022-01-21 11:16:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][470/1251]	eta 0:29:01 lr 0.000651	time 2.1484 (2.2304)	loss 4.3043 (3.6223)	grad_norm 1.2211 (1.3469)	
[2022-01-21 11:16:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][480/1251]	eta 0:28:39 lr 0.000651	time 1.8830 (2.2299)	loss 4.0005 (3.6250)	grad_norm 1.3905 (1.3457)	
[2022-01-21 11:17:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][490/1251]	eta 0:28:17 lr 0.000651	time 2.5517 (2.2307)	loss 3.9922 (3.6274)	grad_norm 1.0470 (1.3450)	
[2022-01-21 11:17:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][500/1251]	eta 0:27:55 lr 0.000651	time 1.8415 (2.2305)	loss 4.0137 (3.6260)	grad_norm 1.2922 (1.3446)	
[2022-01-21 11:17:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][510/1251]	eta 0:27:33 lr 0.000651	time 1.8944 (2.2315)	loss 4.2499 (3.6249)	grad_norm 1.2929 (1.3431)	
[2022-01-21 11:18:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][520/1251]	eta 0:27:12 lr 0.000651	time 2.2529 (2.2328)	loss 3.6924 (3.6267)	grad_norm 1.2346 (1.3424)	
[2022-01-21 11:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][530/1251]	eta 0:26:50 lr 0.000651	time 3.1525 (2.2336)	loss 3.8724 (3.6245)	grad_norm 1.1668 (1.3420)	
[2022-01-21 11:18:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][540/1251]	eta 0:26:25 lr 0.000651	time 1.9029 (2.2298)	loss 3.9202 (3.6259)	grad_norm 1.1646 (1.3425)	
[2022-01-21 11:19:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][550/1251]	eta 0:26:00 lr 0.000651	time 2.1450 (2.2264)	loss 2.5694 (3.6285)	grad_norm 1.5223 (1.3420)	
[2022-01-21 11:19:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][560/1251]	eta 0:25:37 lr 0.000651	time 2.1312 (2.2247)	loss 3.9132 (3.6287)	grad_norm 1.3587 (1.3415)	
[2022-01-21 11:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][570/1251]	eta 0:25:13 lr 0.000651	time 2.5130 (2.2227)	loss 4.0020 (3.6281)	grad_norm 1.6248 (1.3417)	
[2022-01-21 11:20:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][580/1251]	eta 0:24:49 lr 0.000651	time 2.1476 (2.2195)	loss 3.7984 (3.6260)	grad_norm 1.4051 (1.3416)	
[2022-01-21 11:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][590/1251]	eta 0:24:26 lr 0.000651	time 2.6797 (2.2191)	loss 4.0429 (3.6253)	grad_norm 1.1365 (1.3435)	
[2022-01-21 11:21:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][600/1251]	eta 0:24:02 lr 0.000651	time 1.5962 (2.2163)	loss 3.4995 (3.6261)	grad_norm 1.2123 (1.3429)	
[2022-01-21 11:21:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][610/1251]	eta 0:23:40 lr 0.000651	time 2.1987 (2.2167)	loss 4.2213 (3.6303)	grad_norm 1.2425 (1.3420)	
[2022-01-21 11:21:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][620/1251]	eta 0:23:18 lr 0.000651	time 1.8874 (2.2159)	loss 3.1689 (3.6325)	grad_norm 1.3610 (1.3429)	
[2022-01-21 11:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][630/1251]	eta 0:22:56 lr 0.000651	time 2.3776 (2.2171)	loss 3.6279 (3.6303)	grad_norm 1.4368 (1.3435)	
[2022-01-21 11:22:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][640/1251]	eta 0:22:34 lr 0.000650	time 2.7908 (2.2176)	loss 3.1302 (3.6283)	grad_norm 1.3686 (1.3429)	
[2022-01-21 11:22:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][650/1251]	eta 0:22:12 lr 0.000650	time 2.1649 (2.2167)	loss 3.8723 (3.6325)	grad_norm 1.2999 (1.3416)	
[2022-01-21 11:23:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][660/1251]	eta 0:21:49 lr 0.000650	time 1.6562 (2.2160)	loss 4.0816 (3.6334)	grad_norm 1.3498 (1.3420)	
[2022-01-21 11:23:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][670/1251]	eta 0:21:28 lr 0.000650	time 2.2717 (2.2181)	loss 3.8168 (3.6313)	grad_norm 1.7827 (1.3428)	
[2022-01-21 11:24:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][680/1251]	eta 0:21:06 lr 0.000650	time 1.7481 (2.2174)	loss 3.0476 (3.6335)	grad_norm 1.3972 (1.3434)	
[2022-01-21 11:24:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][690/1251]	eta 0:20:42 lr 0.000650	time 1.5777 (2.2156)	loss 3.1053 (3.6320)	grad_norm 1.1735 (1.3442)	
[2022-01-21 11:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][700/1251]	eta 0:20:20 lr 0.000650	time 2.0350 (2.2152)	loss 3.9471 (3.6327)	grad_norm 1.3655 (1.3455)	
[2022-01-21 11:25:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][710/1251]	eta 0:19:58 lr 0.000650	time 1.8937 (2.2154)	loss 4.2266 (3.6346)	grad_norm 1.4776 (1.3467)	
[2022-01-21 11:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][720/1251]	eta 0:19:35 lr 0.000650	time 1.5631 (2.2134)	loss 2.7138 (3.6385)	grad_norm 1.3802 (1.3463)	
[2022-01-21 11:25:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][730/1251]	eta 0:19:11 lr 0.000650	time 1.9407 (2.2105)	loss 3.6999 (3.6370)	grad_norm 1.3183 (1.3467)	
[2022-01-21 11:26:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][740/1251]	eta 0:18:48 lr 0.000650	time 1.8921 (2.2089)	loss 2.5422 (3.6396)	grad_norm 1.2309 (1.3475)	
[2022-01-21 11:26:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][750/1251]	eta 0:18:27 lr 0.000650	time 2.1187 (2.2100)	loss 3.8557 (3.6409)	grad_norm 1.3880 (1.3489)	
[2022-01-21 11:26:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][760/1251]	eta 0:18:04 lr 0.000650	time 2.1477 (2.2093)	loss 3.4162 (3.6408)	grad_norm 1.3543 (1.3499)	
[2022-01-21 11:27:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][770/1251]	eta 0:17:42 lr 0.000650	time 2.2652 (2.2088)	loss 3.0608 (3.6407)	grad_norm 1.3498 (1.3501)	
[2022-01-21 11:27:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][780/1251]	eta 0:17:20 lr 0.000650	time 2.1849 (2.2099)	loss 4.2426 (3.6447)	grad_norm 1.3936 (1.3501)	
[2022-01-21 11:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][790/1251]	eta 0:16:59 lr 0.000650	time 1.9076 (2.2108)	loss 3.1891 (3.6414)	grad_norm 1.4557 (1.3513)	
[2022-01-21 11:28:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][800/1251]	eta 0:16:35 lr 0.000650	time 1.9330 (2.2083)	loss 3.1365 (3.6422)	grad_norm 1.3191 (1.3523)	
[2022-01-21 11:28:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][810/1251]	eta 0:16:14 lr 0.000650	time 1.7860 (2.2092)	loss 4.0014 (3.6416)	grad_norm 1.3733 (1.3524)	
[2022-01-21 11:29:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][820/1251]	eta 0:15:52 lr 0.000650	time 2.9347 (2.2098)	loss 2.5210 (3.6387)	grad_norm 1.4219 (1.3528)	
[2022-01-21 11:29:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][830/1251]	eta 0:15:29 lr 0.000650	time 1.5763 (2.2088)	loss 3.6640 (3.6388)	grad_norm 1.3717 (1.3522)	
[2022-01-21 11:29:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][840/1251]	eta 0:15:07 lr 0.000650	time 1.6846 (2.2075)	loss 4.1317 (3.6371)	grad_norm 1.3236 (1.3518)	
[2022-01-21 11:30:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][850/1251]	eta 0:14:44 lr 0.000650	time 1.5843 (2.2058)	loss 3.3178 (3.6382)	grad_norm 1.2397 (1.3512)	
[2022-01-21 11:30:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][860/1251]	eta 0:14:22 lr 0.000650	time 2.2753 (2.2050)	loss 4.1301 (3.6386)	grad_norm 1.2792 (1.3512)	
[2022-01-21 11:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][870/1251]	eta 0:14:00 lr 0.000650	time 2.3181 (2.2065)	loss 3.4177 (3.6377)	grad_norm 1.4402 (1.3514)	
[2022-01-21 11:31:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][880/1251]	eta 0:13:38 lr 0.000650	time 1.9782 (2.2061)	loss 3.5812 (3.6390)	grad_norm 1.7505 (1.3522)	
[2022-01-21 11:31:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][890/1251]	eta 0:13:16 lr 0.000650	time 1.5993 (2.2059)	loss 2.9837 (3.6406)	grad_norm 1.5026 (1.3548)	
[2022-01-21 11:31:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][900/1251]	eta 0:12:54 lr 0.000649	time 2.5917 (2.2067)	loss 4.1987 (3.6405)	grad_norm 1.1807 (1.3551)	
[2022-01-21 11:32:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][910/1251]	eta 0:12:32 lr 0.000649	time 2.2133 (2.2066)	loss 3.9393 (3.6408)	grad_norm 1.3642 (1.3545)	
[2022-01-21 11:32:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][920/1251]	eta 0:12:10 lr 0.000649	time 2.0512 (2.2072)	loss 3.8127 (3.6398)	grad_norm 1.3412 (1.3544)	
[2022-01-21 11:33:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][930/1251]	eta 0:11:48 lr 0.000649	time 2.1713 (2.2071)	loss 3.5037 (3.6401)	grad_norm 1.2513 (1.3539)	
[2022-01-21 11:33:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][940/1251]	eta 0:11:26 lr 0.000649	time 1.6170 (2.2073)	loss 4.0824 (3.6381)	grad_norm 1.3920 (1.3534)	
[2022-01-21 11:33:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][950/1251]	eta 0:11:03 lr 0.000649	time 1.9177 (2.2058)	loss 3.5668 (3.6369)	grad_norm 1.3332 (1.3530)	
[2022-01-21 11:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][960/1251]	eta 0:10:41 lr 0.000649	time 1.8722 (2.2054)	loss 2.8055 (3.6375)	grad_norm 1.2772 (1.3523)	
[2022-01-21 11:34:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][970/1251]	eta 0:10:19 lr 0.000649	time 1.9345 (2.2047)	loss 4.0045 (3.6387)	grad_norm 1.5627 (1.3526)	
[2022-01-21 11:34:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][980/1251]	eta 0:09:57 lr 0.000649	time 2.2823 (2.2034)	loss 3.7764 (3.6413)	grad_norm 1.1251 (1.3528)	
[2022-01-21 11:35:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][990/1251]	eta 0:09:34 lr 0.000649	time 2.4089 (2.2024)	loss 4.0326 (3.6415)	grad_norm 1.1890 (1.3537)	
[2022-01-21 11:35:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1000/1251]	eta 0:09:12 lr 0.000649	time 1.7779 (2.2008)	loss 3.4862 (3.6390)	grad_norm 1.3954 (1.3526)	
[2022-01-21 11:35:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1010/1251]	eta 0:08:49 lr 0.000649	time 2.0048 (2.1990)	loss 4.1699 (3.6380)	grad_norm 1.4365 (1.3519)	
[2022-01-21 11:36:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1020/1251]	eta 0:08:28 lr 0.000649	time 1.9935 (2.1995)	loss 3.3054 (3.6366)	grad_norm 1.3859 (1.3521)	
[2022-01-21 11:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1030/1251]	eta 0:08:06 lr 0.000649	time 2.8899 (2.2003)	loss 3.4653 (3.6399)	grad_norm 1.3018 (1.3522)	
[2022-01-21 11:37:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1040/1251]	eta 0:07:44 lr 0.000649	time 1.4816 (2.2021)	loss 4.0546 (3.6418)	grad_norm 1.2866 (1.3518)	
[2022-01-21 11:37:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1050/1251]	eta 0:07:23 lr 0.000649	time 1.7082 (2.2042)	loss 4.2784 (3.6413)	grad_norm 1.3246 (1.3517)	
[2022-01-21 11:37:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1060/1251]	eta 0:07:01 lr 0.000649	time 2.2822 (2.2053)	loss 3.5864 (3.6403)	grad_norm 1.3733 (1.3518)	
[2022-01-21 11:38:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1070/1251]	eta 0:06:39 lr 0.000649	time 2.4802 (2.2046)	loss 3.7125 (3.6409)	grad_norm 1.1589 (1.3511)	
[2022-01-21 11:38:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1080/1251]	eta 0:06:16 lr 0.000649	time 1.8724 (2.2025)	loss 3.1273 (3.6378)	grad_norm 1.2297 (1.3509)	
[2022-01-21 11:38:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1090/1251]	eta 0:05:54 lr 0.000649	time 1.9010 (2.2002)	loss 3.9996 (3.6371)	grad_norm 1.2662 (1.3508)	
[2022-01-21 11:39:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1100/1251]	eta 0:05:32 lr 0.000649	time 2.6297 (2.2007)	loss 3.3494 (3.6373)	grad_norm 1.4488 (1.3503)	
[2022-01-21 11:39:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1110/1251]	eta 0:05:10 lr 0.000649	time 3.4712 (2.2024)	loss 2.7254 (3.6342)	grad_norm 1.3129 (1.3502)	
[2022-01-21 11:40:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1120/1251]	eta 0:04:48 lr 0.000649	time 2.2152 (2.2033)	loss 2.5657 (3.6314)	grad_norm 1.3527 (1.3509)	
[2022-01-21 11:40:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1130/1251]	eta 0:04:26 lr 0.000649	time 2.5638 (2.2036)	loss 4.1265 (3.6325)	grad_norm 1.4070 (1.3510)	
[2022-01-21 11:40:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1140/1251]	eta 0:04:04 lr 0.000649	time 1.8554 (2.2016)	loss 3.9052 (3.6332)	grad_norm 1.4496 (1.3514)	
[2022-01-21 11:41:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1150/1251]	eta 0:03:42 lr 0.000648	time 2.2183 (2.1997)	loss 3.9407 (3.6313)	grad_norm 1.2847 (1.3513)	
[2022-01-21 11:41:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1160/1251]	eta 0:03:20 lr 0.000648	time 2.7414 (2.1984)	loss 3.9735 (3.6312)	grad_norm 1.3804 (1.3515)	
[2022-01-21 11:41:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1170/1251]	eta 0:02:58 lr 0.000648	time 2.4594 (2.1987)	loss 4.5380 (3.6295)	grad_norm 1.2500 (1.3509)	
[2022-01-21 11:42:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1180/1251]	eta 0:02:36 lr 0.000648	time 2.2425 (2.1981)	loss 4.0559 (3.6328)	grad_norm 1.3404 (1.3510)	
[2022-01-21 11:42:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1190/1251]	eta 0:02:14 lr 0.000648	time 1.8546 (2.1978)	loss 3.2280 (3.6319)	grad_norm 1.3848 (1.3509)	
[2022-01-21 11:42:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1200/1251]	eta 0:01:52 lr 0.000648	time 1.8809 (2.1973)	loss 2.9188 (3.6330)	grad_norm 1.6810 (1.3520)	
[2022-01-21 11:43:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1210/1251]	eta 0:01:30 lr 0.000648	time 2.8712 (2.1972)	loss 3.3985 (3.6328)	grad_norm 1.2255 (1.3520)	
[2022-01-21 11:43:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1220/1251]	eta 0:01:08 lr 0.000648	time 2.1459 (2.1975)	loss 4.2362 (3.6355)	grad_norm 1.3558 (1.3519)	
[2022-01-21 11:43:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1230/1251]	eta 0:00:46 lr 0.000648	time 1.5436 (2.1989)	loss 4.1756 (3.6386)	grad_norm 1.2009 (1.3514)	
[2022-01-21 11:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1240/1251]	eta 0:00:24 lr 0.000648	time 1.2178 (2.1976)	loss 2.5291 (3.6385)	grad_norm 1.5313 (1.3518)	
[2022-01-21 11:44:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [121/300][1250/1251]	eta 0:00:02 lr 0.000648	time 1.2968 (2.1930)	loss 3.0079 (3.6367)	grad_norm 1.1520 (1.3516)	
[2022-01-21 11:44:34 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 121 training takes 0:45:43
[2022-01-21 11:44:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.409 (18.409)	Loss 1.1320 (1.1320)	Acc@1 73.242 (73.242)	Acc@5 92.578 (92.578)	
[2022-01-21 11:45:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.159 (3.308)	Loss 1.1135 (1.0766)	Acc@1 72.852 (74.885)	Acc@5 92.871 (92.489)	
[2022-01-21 11:45:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.954 (2.604)	Loss 1.0083 (1.0750)	Acc@1 75.781 (74.879)	Acc@5 93.359 (92.639)	
[2022-01-21 11:45:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.615 (2.301)	Loss 1.0041 (1.0781)	Acc@1 76.367 (74.814)	Acc@5 92.871 (92.594)	
[2022-01-21 11:46:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.902 (2.206)	Loss 1.1103 (1.0763)	Acc@1 73.438 (74.829)	Acc@5 92.285 (92.652)	
[2022-01-21 11:46:12 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.844 Acc@5 92.696
[2022-01-21 11:46:12 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.8%
[2022-01-21 11:46:12 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.95%
[2022-01-21 11:46:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][0/1251]	eta 8:32:29 lr 0.000648	time 24.5803 (24.5803)	loss 3.5255 (3.5255)	grad_norm 1.3080 (1.3080)	
[2022-01-21 11:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][10/1251]	eta 1:33:04 lr 0.000648	time 3.3594 (4.4996)	loss 4.0601 (3.4600)	grad_norm 1.5652 (1.3676)	
[2022-01-21 11:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][20/1251]	eta 1:09:14 lr 0.000648	time 1.5000 (3.3752)	loss 3.7995 (3.6466)	grad_norm 1.3032 (1.3727)	
[2022-01-21 11:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][30/1251]	eta 1:01:06 lr 0.000648	time 1.8367 (3.0031)	loss 2.5439 (3.6671)	grad_norm 1.7548 (1.3850)	
[2022-01-21 11:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][40/1251]	eta 0:57:30 lr 0.000648	time 3.1742 (2.8494)	loss 3.1922 (3.6746)	grad_norm 1.3289 (1.4134)	
[2022-01-21 11:48:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][50/1251]	eta 0:54:38 lr 0.000648	time 2.4045 (2.7295)	loss 2.7125 (3.6598)	grad_norm 1.4493 (1.4129)	
[2022-01-21 11:48:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][60/1251]	eta 0:52:06 lr 0.000648	time 1.9065 (2.6247)	loss 3.6071 (3.6372)	grad_norm 1.1375 (1.3936)	
[2022-01-21 11:49:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][70/1251]	eta 0:50:16 lr 0.000648	time 2.2020 (2.5544)	loss 3.0625 (3.5790)	grad_norm 1.2975 (1.3915)	
[2022-01-21 11:49:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][80/1251]	eta 0:48:55 lr 0.000648	time 2.5836 (2.5069)	loss 4.4720 (3.5840)	grad_norm 1.5258 (1.3879)	
[2022-01-21 11:49:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][90/1251]	eta 0:47:59 lr 0.000648	time 2.3130 (2.4803)	loss 3.5817 (3.5821)	grad_norm 1.5185 (1.3855)	
[2022-01-21 11:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][100/1251]	eta 0:46:48 lr 0.000648	time 2.0572 (2.4399)	loss 2.7864 (3.5573)	grad_norm 1.3603 (1.3813)	
[2022-01-21 11:50:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][110/1251]	eta 0:45:43 lr 0.000648	time 1.9932 (2.4045)	loss 4.3009 (3.5518)	grad_norm 1.3797 (1.3843)	
[2022-01-21 11:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][120/1251]	eta 0:44:59 lr 0.000648	time 2.4987 (2.3865)	loss 3.2149 (3.5519)	grad_norm 1.4955 (1.3866)	
[2022-01-21 11:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][130/1251]	eta 0:44:11 lr 0.000648	time 2.2431 (2.3653)	loss 4.2109 (3.5648)	grad_norm 1.2063 (1.3834)	
[2022-01-21 11:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][140/1251]	eta 0:43:30 lr 0.000648	time 1.7480 (2.3499)	loss 3.2971 (3.5622)	grad_norm 1.4580 (1.3809)	
[2022-01-21 11:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][150/1251]	eta 0:42:58 lr 0.000647	time 2.0653 (2.3421)	loss 3.3083 (3.5671)	grad_norm 1.4855 (1.3823)	
[2022-01-21 11:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][160/1251]	eta 0:42:26 lr 0.000647	time 2.7610 (2.3345)	loss 3.8492 (3.5628)	grad_norm 1.1730 (1.3851)	
[2022-01-21 11:52:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][170/1251]	eta 0:42:10 lr 0.000647	time 2.9608 (2.3413)	loss 4.6766 (3.5600)	grad_norm 1.5461 (1.3828)	
[2022-01-21 11:53:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][180/1251]	eta 0:41:42 lr 0.000647	time 2.2608 (2.3362)	loss 3.6408 (3.5565)	grad_norm 1.2964 (1.3782)	
[2022-01-21 11:53:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][190/1251]	eta 0:41:11 lr 0.000647	time 1.8697 (2.3290)	loss 3.6487 (3.5561)	grad_norm 1.2484 (1.3723)	
[2022-01-21 11:53:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][200/1251]	eta 0:40:36 lr 0.000647	time 1.8351 (2.3181)	loss 3.4420 (3.5566)	grad_norm 1.0993 (1.3650)	
[2022-01-21 11:54:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][210/1251]	eta 0:40:02 lr 0.000647	time 2.3417 (2.3077)	loss 4.0320 (3.5607)	grad_norm 1.3232 (1.3626)	
[2022-01-21 11:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][220/1251]	eta 0:39:22 lr 0.000647	time 1.9196 (2.2912)	loss 3.1853 (3.5643)	grad_norm 1.2500 (1.3626)	
[2022-01-21 11:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][230/1251]	eta 0:38:52 lr 0.000647	time 2.3679 (2.2842)	loss 4.0546 (3.5701)	grad_norm 1.8530 (1.3650)	
[2022-01-21 11:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][240/1251]	eta 0:38:29 lr 0.000647	time 1.9517 (2.2841)	loss 4.3297 (3.5718)	grad_norm 1.2693 (1.3663)	
[2022-01-21 11:55:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][250/1251]	eta 0:38:06 lr 0.000647	time 2.1390 (2.2845)	loss 4.1633 (3.5662)	grad_norm 1.3125 (1.3634)	
[2022-01-21 11:56:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][260/1251]	eta 0:37:44 lr 0.000647	time 2.0367 (2.2855)	loss 2.7429 (3.5630)	grad_norm 1.2311 (1.3653)	
[2022-01-21 11:56:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][270/1251]	eta 0:37:39 lr 0.000647	time 3.1688 (2.3037)	loss 3.9313 (3.5685)	grad_norm 1.1776 (1.3648)	
[2022-01-21 11:57:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][280/1251]	eta 0:37:18 lr 0.000647	time 2.3064 (2.3052)	loss 3.7384 (3.5688)	grad_norm 1.2656 (1.3618)	
[2022-01-21 11:57:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][290/1251]	eta 0:36:46 lr 0.000647	time 1.9048 (2.2964)	loss 4.2160 (3.5812)	grad_norm 1.2647 (1.3626)	
[2022-01-21 11:57:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][300/1251]	eta 0:36:10 lr 0.000647	time 1.9702 (2.2820)	loss 3.3882 (3.5711)	grad_norm 1.2846 (1.3603)	
[2022-01-21 11:57:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][310/1251]	eta 0:35:37 lr 0.000647	time 2.1028 (2.2712)	loss 2.6232 (3.5621)	grad_norm 1.4651 (1.3580)	
[2022-01-21 11:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][320/1251]	eta 0:35:09 lr 0.000647	time 2.2091 (2.2656)	loss 4.4371 (3.5722)	grad_norm 1.3882 (1.3582)	
[2022-01-21 11:58:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][330/1251]	eta 0:34:48 lr 0.000647	time 3.1092 (2.2673)	loss 3.4088 (3.5672)	grad_norm 1.2708 (1.3566)	
[2022-01-21 11:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][340/1251]	eta 0:34:21 lr 0.000647	time 2.1880 (2.2629)	loss 3.7321 (3.5723)	grad_norm 1.2730 (1.3574)	
[2022-01-21 11:59:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][350/1251]	eta 0:33:55 lr 0.000647	time 2.2070 (2.2593)	loss 3.4181 (3.5739)	grad_norm 1.1662 (1.3563)	
[2022-01-21 11:59:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][360/1251]	eta 0:33:31 lr 0.000647	time 2.3810 (2.2580)	loss 3.9858 (3.5765)	grad_norm 1.3252 (1.3574)	
[2022-01-21 12:00:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][370/1251]	eta 0:33:11 lr 0.000647	time 2.4151 (2.2604)	loss 3.8108 (3.5735)	grad_norm 1.2835 (1.3557)	
[2022-01-21 12:00:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][380/1251]	eta 0:32:54 lr 0.000647	time 3.5537 (2.2666)	loss 4.0449 (3.5692)	grad_norm 1.3116 (1.3557)	
[2022-01-21 12:00:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][390/1251]	eta 0:32:32 lr 0.000647	time 2.7690 (2.2681)	loss 4.3854 (3.5719)	grad_norm 1.4782 (1.3554)	
[2022-01-21 12:01:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][400/1251]	eta 0:32:09 lr 0.000646	time 1.9391 (2.2677)	loss 3.9833 (3.5659)	grad_norm 1.2602 (1.3535)	
[2022-01-21 12:01:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][410/1251]	eta 0:31:42 lr 0.000646	time 1.8688 (2.2621)	loss 3.8063 (3.5688)	grad_norm 1.4362 (1.3530)	
[2022-01-21 12:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][420/1251]	eta 0:31:15 lr 0.000646	time 3.1333 (2.2575)	loss 4.1770 (3.5743)	grad_norm 1.1613 (1.3524)	
[2022-01-21 12:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][430/1251]	eta 0:30:47 lr 0.000646	time 2.0687 (2.2503)	loss 2.4127 (3.5759)	grad_norm 1.3449 (1.3527)	
[2022-01-21 12:02:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][440/1251]	eta 0:30:23 lr 0.000646	time 2.4445 (2.2490)	loss 3.0932 (3.5749)	grad_norm 1.2118 (1.3552)	
[2022-01-21 12:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][450/1251]	eta 0:29:59 lr 0.000646	time 1.9403 (2.2465)	loss 3.0288 (3.5756)	grad_norm 1.3703 (1.3555)	
[2022-01-21 12:03:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][460/1251]	eta 0:29:38 lr 0.000646	time 3.1535 (2.2481)	loss 3.9141 (3.5720)	grad_norm 1.5435 (1.3558)	
[2022-01-21 12:03:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][470/1251]	eta 0:29:16 lr 0.000646	time 1.9603 (2.2494)	loss 3.9701 (3.5723)	grad_norm 1.5480 (1.3554)	
[2022-01-21 12:04:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][480/1251]	eta 0:28:53 lr 0.000646	time 1.7974 (2.2482)	loss 3.8590 (3.5731)	grad_norm 1.4523 (1.3561)	
[2022-01-21 12:04:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][490/1251]	eta 0:28:28 lr 0.000646	time 1.8646 (2.2453)	loss 4.1091 (3.5734)	grad_norm 1.5083 (1.3556)	
[2022-01-21 12:04:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][500/1251]	eta 0:28:03 lr 0.000646	time 2.2805 (2.2423)	loss 4.1499 (3.5750)	grad_norm 1.2818 (1.3549)	
[2022-01-21 12:05:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][510/1251]	eta 0:27:38 lr 0.000646	time 1.8730 (2.2388)	loss 4.5742 (3.5784)	grad_norm 1.2426 (1.3547)	
[2022-01-21 12:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][520/1251]	eta 0:27:16 lr 0.000646	time 2.1782 (2.2392)	loss 4.1096 (3.5778)	grad_norm 1.1213 (1.3546)	
[2022-01-21 12:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][530/1251]	eta 0:26:55 lr 0.000646	time 1.8864 (2.2400)	loss 3.9429 (3.5791)	grad_norm 1.3174 (1.3547)	
[2022-01-21 12:06:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][540/1251]	eta 0:26:33 lr 0.000646	time 2.3825 (2.2416)	loss 3.2481 (3.5800)	grad_norm 1.3527 (1.3552)	
[2022-01-21 12:06:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][550/1251]	eta 0:26:09 lr 0.000646	time 1.9434 (2.2384)	loss 3.2867 (3.5814)	grad_norm 1.3916 (1.3553)	
[2022-01-21 12:07:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][560/1251]	eta 0:25:45 lr 0.000646	time 1.9037 (2.2366)	loss 3.4198 (3.5811)	grad_norm 1.4194 (1.3584)	
[2022-01-21 12:07:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][570/1251]	eta 0:25:21 lr 0.000646	time 2.0077 (2.2337)	loss 3.5494 (3.5799)	grad_norm 1.6927 (1.3615)	
[2022-01-21 12:07:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][580/1251]	eta 0:24:57 lr 0.000646	time 2.1720 (2.2323)	loss 2.5822 (3.5762)	grad_norm 1.3064 (1.3617)	
[2022-01-21 12:08:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][590/1251]	eta 0:24:33 lr 0.000646	time 1.8308 (2.2288)	loss 4.0006 (3.5738)	grad_norm 1.2340 (1.3603)	
[2022-01-21 12:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][600/1251]	eta 0:24:09 lr 0.000646	time 2.4662 (2.2264)	loss 2.8496 (3.5763)	grad_norm 1.1941 (1.3602)	
[2022-01-21 12:08:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][610/1251]	eta 0:23:45 lr 0.000646	time 2.5090 (2.2239)	loss 4.3497 (3.5739)	grad_norm 1.4171 (1.3605)	
[2022-01-21 12:09:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][620/1251]	eta 0:23:24 lr 0.000646	time 2.2150 (2.2262)	loss 3.7743 (3.5769)	grad_norm 1.3008 (1.3593)	
[2022-01-21 12:09:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][630/1251]	eta 0:23:03 lr 0.000646	time 1.5754 (2.2273)	loss 3.9723 (3.5782)	grad_norm 1.2202 (1.3581)	
[2022-01-21 12:10:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][640/1251]	eta 0:22:41 lr 0.000646	time 2.1358 (2.2282)	loss 4.1058 (3.5813)	grad_norm 1.2921 (1.3568)	
[2022-01-21 12:10:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][650/1251]	eta 0:22:19 lr 0.000645	time 1.9852 (2.2281)	loss 4.2727 (3.5877)	grad_norm 1.3239 (1.3571)	
[2022-01-21 12:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][660/1251]	eta 0:21:59 lr 0.000645	time 2.7894 (2.2322)	loss 3.5685 (3.5865)	grad_norm 1.2015 (1.3568)	
[2022-01-21 12:11:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][670/1251]	eta 0:21:35 lr 0.000645	time 1.6296 (2.2301)	loss 3.2745 (3.5893)	grad_norm 1.1630 (1.3560)	
[2022-01-21 12:11:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][680/1251]	eta 0:21:10 lr 0.000645	time 1.5380 (2.2259)	loss 4.0141 (3.5918)	grad_norm 1.4156 (1.3560)	
[2022-01-21 12:11:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][690/1251]	eta 0:20:47 lr 0.000645	time 2.0639 (2.2229)	loss 3.4279 (3.5949)	grad_norm 1.3601 (1.3563)	
[2022-01-21 12:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][700/1251]	eta 0:20:23 lr 0.000645	time 2.2052 (2.2212)	loss 3.9721 (3.5993)	grad_norm 1.2470 (1.3564)	
[2022-01-21 12:12:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][710/1251]	eta 0:20:02 lr 0.000645	time 1.6426 (2.2223)	loss 3.7206 (3.6014)	grad_norm 1.4516 (1.3554)	
[2022-01-21 12:12:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][720/1251]	eta 0:19:39 lr 0.000645	time 1.8689 (2.2216)	loss 3.9297 (3.6018)	grad_norm 1.3369 (1.3551)	
[2022-01-21 12:13:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][730/1251]	eta 0:19:17 lr 0.000645	time 2.5751 (2.2221)	loss 4.1368 (3.6057)	grad_norm 1.2899 (1.3551)	
[2022-01-21 12:13:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][740/1251]	eta 0:18:56 lr 0.000645	time 2.6137 (2.2239)	loss 4.1641 (3.6071)	grad_norm 1.4870 (1.3556)	
[2022-01-21 12:14:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][750/1251]	eta 0:18:34 lr 0.000645	time 1.5669 (2.2237)	loss 3.6684 (3.6057)	grad_norm 1.2413 (1.3555)	
[2022-01-21 12:14:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][760/1251]	eta 0:18:11 lr 0.000645	time 1.6967 (2.2224)	loss 3.9290 (3.6104)	grad_norm 1.3018 (1.3558)	
[2022-01-21 12:14:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][770/1251]	eta 0:17:48 lr 0.000645	time 1.9257 (2.2222)	loss 4.4600 (3.6137)	grad_norm 1.4680 (1.3554)	
[2022-01-21 12:15:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][780/1251]	eta 0:17:26 lr 0.000645	time 2.7165 (2.2217)	loss 3.7349 (3.6108)	grad_norm 1.3908 (1.3553)	
[2022-01-21 12:15:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][790/1251]	eta 0:17:03 lr 0.000645	time 1.9033 (2.2210)	loss 3.6585 (3.6104)	grad_norm 1.2373 (1.3557)	
[2022-01-21 12:15:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][800/1251]	eta 0:16:41 lr 0.000645	time 1.9175 (2.2200)	loss 3.6651 (3.6129)	grad_norm 1.2932 (1.3550)	
[2022-01-21 12:16:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][810/1251]	eta 0:16:18 lr 0.000645	time 1.8283 (2.2185)	loss 4.0823 (3.6171)	grad_norm 1.2717 (1.3550)	
[2022-01-21 12:16:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][820/1251]	eta 0:15:56 lr 0.000645	time 2.5105 (2.2198)	loss 3.9088 (3.6187)	grad_norm 1.9598 (1.3551)	
[2022-01-21 12:16:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][830/1251]	eta 0:15:34 lr 0.000645	time 2.4089 (2.2190)	loss 3.2146 (3.6195)	grad_norm 1.4958 (1.3552)	
[2022-01-21 12:17:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][840/1251]	eta 0:15:11 lr 0.000645	time 2.2826 (2.2182)	loss 4.0036 (3.6193)	grad_norm 1.2888 (1.3546)	
[2022-01-21 12:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][850/1251]	eta 0:14:48 lr 0.000645	time 2.0119 (2.2168)	loss 3.6002 (3.6174)	grad_norm 1.3528 (1.3547)	
[2022-01-21 12:18:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][860/1251]	eta 0:14:27 lr 0.000645	time 2.1434 (2.2174)	loss 3.3869 (3.6170)	grad_norm 1.2406 (1.3547)	
[2022-01-21 12:18:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][870/1251]	eta 0:14:04 lr 0.000645	time 2.0823 (2.2177)	loss 4.6234 (3.6146)	grad_norm 1.5382 (1.3544)	
[2022-01-21 12:18:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][880/1251]	eta 0:13:42 lr 0.000645	time 2.3702 (2.2174)	loss 4.2510 (3.6178)	grad_norm 1.3143 (1.3547)	
[2022-01-21 12:19:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][890/1251]	eta 0:13:20 lr 0.000645	time 2.2676 (2.2178)	loss 3.9948 (3.6205)	grad_norm 1.1656 (1.3543)	
[2022-01-21 12:19:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][900/1251]	eta 0:12:58 lr 0.000644	time 2.1700 (2.2172)	loss 3.9774 (3.6176)	grad_norm 1.2864 (1.3555)	
[2022-01-21 12:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][910/1251]	eta 0:12:35 lr 0.000644	time 2.4734 (2.2150)	loss 3.8829 (3.6212)	grad_norm 1.1858 (1.3547)	
[2022-01-21 12:20:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][920/1251]	eta 0:12:12 lr 0.000644	time 1.9862 (2.2124)	loss 3.8548 (3.6198)	grad_norm 1.1461 (1.3546)	
[2022-01-21 12:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][930/1251]	eta 0:11:49 lr 0.000644	time 1.8888 (2.2097)	loss 3.4922 (3.6186)	grad_norm 1.6004 (1.3544)	
[2022-01-21 12:20:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][940/1251]	eta 0:11:27 lr 0.000644	time 2.3220 (2.2104)	loss 4.1580 (3.6171)	grad_norm 1.4014 (1.3552)	
[2022-01-21 12:21:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][950/1251]	eta 0:11:05 lr 0.000644	time 2.8480 (2.2105)	loss 3.3752 (3.6163)	grad_norm 1.2581 (1.3546)	
[2022-01-21 12:21:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][960/1251]	eta 0:10:43 lr 0.000644	time 1.8947 (2.2110)	loss 4.2824 (3.6153)	grad_norm 1.4220 (1.3541)	
[2022-01-21 12:21:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][970/1251]	eta 0:10:21 lr 0.000644	time 2.1855 (2.2106)	loss 3.6517 (3.6187)	grad_norm 1.4101 (1.3546)	
[2022-01-21 12:22:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][980/1251]	eta 0:09:59 lr 0.000644	time 1.7179 (2.2118)	loss 4.1944 (3.6195)	grad_norm 1.2825 (1.3548)	
[2022-01-21 12:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][990/1251]	eta 0:09:37 lr 0.000644	time 2.8679 (2.2119)	loss 3.2145 (3.6159)	grad_norm 1.7112 (1.3552)	
[2022-01-21 12:23:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1000/1251]	eta 0:09:15 lr 0.000644	time 1.6491 (2.2112)	loss 3.8936 (3.6164)	grad_norm 1.3864 (1.3548)	
[2022-01-21 12:23:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1010/1251]	eta 0:08:53 lr 0.000644	time 2.0705 (2.2122)	loss 3.8481 (3.6164)	grad_norm 1.1708 (1.3546)	
[2022-01-21 12:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1020/1251]	eta 0:08:31 lr 0.000644	time 1.8995 (2.2122)	loss 3.4763 (3.6141)	grad_norm 1.5296 (1.3551)	
[2022-01-21 12:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1030/1251]	eta 0:08:08 lr 0.000644	time 2.0151 (2.2105)	loss 4.1309 (3.6151)	grad_norm 1.6356 (1.3554)	
[2022-01-21 12:24:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1040/1251]	eta 0:07:46 lr 0.000644	time 1.9484 (2.2104)	loss 4.0046 (3.6167)	grad_norm 1.5303 (1.3554)	
[2022-01-21 12:24:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1050/1251]	eta 0:07:24 lr 0.000644	time 2.5682 (2.2109)	loss 3.3931 (3.6165)	grad_norm 1.5471 (1.3561)	
[2022-01-21 12:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1060/1251]	eta 0:07:02 lr 0.000644	time 2.3437 (2.2120)	loss 3.8624 (3.6176)	grad_norm 1.2606 (1.3554)	
[2022-01-21 12:25:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1070/1251]	eta 0:06:39 lr 0.000644	time 1.7696 (2.2099)	loss 2.7350 (3.6181)	grad_norm 1.3381 (1.3550)	
[2022-01-21 12:26:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1080/1251]	eta 0:06:17 lr 0.000644	time 1.7798 (2.2090)	loss 3.0839 (3.6141)	grad_norm 1.5094 (1.3558)	
[2022-01-21 12:26:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1090/1251]	eta 0:05:55 lr 0.000644	time 1.8352 (2.2076)	loss 4.4054 (3.6142)	grad_norm 1.3216 (1.3561)	
[2022-01-21 12:26:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1100/1251]	eta 0:05:33 lr 0.000644	time 2.2663 (2.2076)	loss 3.8159 (3.6142)	grad_norm 1.1999 (1.3559)	
[2022-01-21 12:27:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1110/1251]	eta 0:05:11 lr 0.000644	time 1.8471 (2.2066)	loss 2.7203 (3.6133)	grad_norm 1.2049 (1.3557)	
[2022-01-21 12:27:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1120/1251]	eta 0:04:49 lr 0.000644	time 2.5648 (2.2072)	loss 3.9238 (3.6148)	grad_norm 1.3119 (1.3549)	
[2022-01-21 12:27:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1130/1251]	eta 0:04:27 lr 0.000644	time 1.9179 (2.2070)	loss 4.1466 (3.6163)	grad_norm 1.1770 (1.3541)	
[2022-01-21 12:28:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1140/1251]	eta 0:04:05 lr 0.000644	time 2.4773 (2.2075)	loss 3.5570 (3.6150)	grad_norm 1.5836 (1.3539)	
[2022-01-21 12:28:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1150/1251]	eta 0:03:42 lr 0.000644	time 2.5948 (2.2074)	loss 4.2159 (3.6153)	grad_norm 1.1828 (1.3535)	
[2022-01-21 12:28:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1160/1251]	eta 0:03:20 lr 0.000643	time 2.5594 (2.2087)	loss 3.7606 (3.6153)	grad_norm 1.1847 (1.3539)	
[2022-01-21 12:29:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1170/1251]	eta 0:02:58 lr 0.000643	time 1.7473 (2.2071)	loss 2.7133 (3.6147)	grad_norm 1.2170 (1.3532)	
[2022-01-21 12:29:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1180/1251]	eta 0:02:36 lr 0.000643	time 1.7296 (2.2051)	loss 3.3018 (3.6134)	grad_norm 1.4053 (1.3539)	
[2022-01-21 12:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1190/1251]	eta 0:02:14 lr 0.000643	time 2.0405 (2.2044)	loss 4.1121 (3.6150)	grad_norm 1.4697 (1.3541)	
[2022-01-21 12:30:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1200/1251]	eta 0:01:52 lr 0.000643	time 2.3530 (2.2060)	loss 3.8384 (3.6145)	grad_norm 1.3138 (1.3536)	
[2022-01-21 12:30:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1210/1251]	eta 0:01:30 lr 0.000643	time 2.0809 (2.2048)	loss 4.0221 (3.6162)	grad_norm 1.3501 (1.3532)	
[2022-01-21 12:31:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1220/1251]	eta 0:01:08 lr 0.000643	time 1.8291 (2.2044)	loss 2.7515 (3.6150)	grad_norm 1.1918 (1.3526)	
[2022-01-21 12:31:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1230/1251]	eta 0:00:46 lr 0.000643	time 1.7564 (2.2054)	loss 4.1425 (3.6154)	grad_norm 1.3492 (1.3526)	
[2022-01-21 12:31:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1240/1251]	eta 0:00:24 lr 0.000643	time 1.5307 (2.2045)	loss 3.7807 (3.6158)	grad_norm 1.0970 (1.3520)	
[2022-01-21 12:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [122/300][1250/1251]	eta 0:00:02 lr 0.000643	time 1.3275 (2.1995)	loss 3.5946 (3.6166)	grad_norm 1.1712 (1.3515)	
[2022-01-21 12:32:04 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 122 training takes 0:45:51
[2022-01-21 12:32:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.772 (18.772)	Loss 1.0526 (1.0526)	Acc@1 75.488 (75.488)	Acc@5 92.773 (92.773)	
[2022-01-21 12:32:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.550 (3.262)	Loss 1.1283 (1.0841)	Acc@1 73.047 (73.961)	Acc@5 92.383 (92.498)	
[2022-01-21 12:32:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.896 (2.612)	Loss 1.0748 (1.0743)	Acc@1 74.414 (74.419)	Acc@5 92.676 (92.690)	
[2022-01-21 12:33:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.899 (2.338)	Loss 1.0617 (1.0705)	Acc@1 74.512 (74.641)	Acc@5 93.164 (92.657)	
[2022-01-21 12:33:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.732 (2.200)	Loss 1.1380 (1.0784)	Acc@1 73.633 (74.533)	Acc@5 91.895 (92.554)	
[2022-01-21 12:33:41 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.618 Acc@5 92.560
[2022-01-21 12:33:41 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.6%
[2022-01-21 12:33:41 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.95%
[2022-01-21 12:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][0/1251]	eta 7:32:17 lr 0.000643	time 21.6925 (21.6925)	loss 4.1370 (4.1370)	grad_norm 1.6038 (1.6038)	
[2022-01-21 12:34:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][10/1251]	eta 1:22:42 lr 0.000643	time 2.2078 (3.9991)	loss 3.0796 (3.5957)	grad_norm 1.1625 (1.3572)	
[2022-01-21 12:34:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][20/1251]	eta 1:04:19 lr 0.000643	time 1.3763 (3.1354)	loss 3.5372 (3.6558)	grad_norm 1.1802 (1.3425)	
[2022-01-21 12:35:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][30/1251]	eta 0:57:36 lr 0.000643	time 2.2483 (2.8307)	loss 3.2836 (3.5797)	grad_norm 1.3682 (1.3458)	
[2022-01-21 12:35:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][40/1251]	eta 0:55:42 lr 0.000643	time 3.8884 (2.7605)	loss 3.1278 (3.5398)	grad_norm 1.2602 (1.3515)	
[2022-01-21 12:35:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][50/1251]	eta 0:53:53 lr 0.000643	time 3.0641 (2.6922)	loss 4.4054 (3.5601)	grad_norm 1.1926 (1.3400)	
[2022-01-21 12:36:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][60/1251]	eta 0:51:49 lr 0.000643	time 1.7665 (2.6107)	loss 2.4516 (3.5386)	grad_norm 1.3507 (1.3346)	
[2022-01-21 12:36:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][70/1251]	eta 0:50:04 lr 0.000643	time 2.2241 (2.5437)	loss 3.4089 (3.5387)	grad_norm 1.5757 (1.3528)	
[2022-01-21 12:37:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][80/1251]	eta 0:48:37 lr 0.000643	time 3.3480 (2.4912)	loss 3.7418 (3.5605)	grad_norm 1.6123 (1.3555)	
[2022-01-21 12:37:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][90/1251]	eta 0:47:46 lr 0.000643	time 3.1566 (2.4687)	loss 2.6453 (3.5754)	grad_norm 1.2491 (1.3544)	
[2022-01-21 12:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][100/1251]	eta 0:46:47 lr 0.000643	time 1.8692 (2.4394)	loss 3.6070 (3.5472)	grad_norm 1.2037 (1.3564)	
[2022-01-21 12:38:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][110/1251]	eta 0:46:01 lr 0.000643	time 2.2833 (2.4199)	loss 4.2680 (3.5736)	grad_norm 1.1286 (1.3500)	
[2022-01-21 12:38:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][120/1251]	eta 0:45:09 lr 0.000643	time 2.4427 (2.3958)	loss 3.9133 (3.5791)	grad_norm 1.6941 (1.3544)	
[2022-01-21 12:38:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][130/1251]	eta 0:44:28 lr 0.000643	time 3.1952 (2.3808)	loss 4.0293 (3.5844)	grad_norm 1.5102 (1.3533)	
[2022-01-21 12:39:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][140/1251]	eta 0:43:49 lr 0.000643	time 2.9133 (2.3670)	loss 4.1648 (3.5924)	grad_norm 1.4410 (1.3536)	
[2022-01-21 12:39:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][150/1251]	eta 0:43:11 lr 0.000643	time 1.7821 (2.3538)	loss 3.5227 (3.6050)	grad_norm 1.2826 (1.3613)	
[2022-01-21 12:39:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][160/1251]	eta 0:42:23 lr 0.000642	time 1.9826 (2.3312)	loss 3.4946 (3.6102)	grad_norm 1.2203 (1.3611)	
[2022-01-21 12:40:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][170/1251]	eta 0:41:47 lr 0.000642	time 2.5654 (2.3200)	loss 3.4679 (3.6294)	grad_norm 1.2036 (1.3578)	
[2022-01-21 12:40:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][180/1251]	eta 0:41:13 lr 0.000642	time 1.5321 (2.3091)	loss 2.9343 (3.6422)	grad_norm 1.7630 (1.3590)	
[2022-01-21 12:41:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][190/1251]	eta 0:40:41 lr 0.000642	time 2.0780 (2.3014)	loss 3.8385 (3.6489)	grad_norm 1.3776 (1.3573)	
[2022-01-21 12:41:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][200/1251]	eta 0:40:15 lr 0.000642	time 2.5600 (2.2980)	loss 3.7818 (3.6462)	grad_norm 1.3518 (1.3541)	
[2022-01-21 12:41:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][210/1251]	eta 0:39:42 lr 0.000642	time 1.9470 (2.2888)	loss 3.3823 (3.6422)	grad_norm 1.3912 (1.3523)	
[2022-01-21 12:42:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][220/1251]	eta 0:39:20 lr 0.000642	time 2.1166 (2.2895)	loss 3.5885 (3.6488)	grad_norm 1.4458 (1.3513)	
[2022-01-21 12:42:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][230/1251]	eta 0:38:56 lr 0.000642	time 2.4759 (2.2884)	loss 2.6706 (3.6396)	grad_norm 1.4763 (1.3515)	
[2022-01-21 12:42:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][240/1251]	eta 0:38:24 lr 0.000642	time 2.3194 (2.2789)	loss 2.8514 (3.6361)	grad_norm 1.2228 (1.3523)	
[2022-01-21 12:43:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][250/1251]	eta 0:38:02 lr 0.000642	time 2.3308 (2.2797)	loss 3.5244 (3.6228)	grad_norm 1.3628 (1.3532)	
[2022-01-21 12:43:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][260/1251]	eta 0:37:42 lr 0.000642	time 2.2065 (2.2831)	loss 3.7626 (3.6174)	grad_norm 1.2249 (1.3565)	
[2022-01-21 12:43:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][270/1251]	eta 0:37:12 lr 0.000642	time 2.9195 (2.2759)	loss 4.0670 (3.6157)	grad_norm 1.3262 (1.3568)	
[2022-01-21 12:44:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][280/1251]	eta 0:36:45 lr 0.000642	time 1.8920 (2.2709)	loss 3.9994 (3.6092)	grad_norm 1.2847 (1.3561)	
[2022-01-21 12:44:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][290/1251]	eta 0:36:16 lr 0.000642	time 2.2574 (2.2652)	loss 3.7466 (3.6072)	grad_norm 1.2803 (1.3547)	
[2022-01-21 12:45:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][300/1251]	eta 0:35:50 lr 0.000642	time 2.1800 (2.2609)	loss 3.8494 (3.5961)	grad_norm 1.3687 (1.3550)	
[2022-01-21 12:45:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][310/1251]	eta 0:35:23 lr 0.000642	time 2.5220 (2.2563)	loss 4.0253 (3.6079)	grad_norm 1.5247 (1.3561)	
[2022-01-21 12:45:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][320/1251]	eta 0:34:55 lr 0.000642	time 1.9529 (2.2503)	loss 3.0370 (3.6077)	grad_norm 1.2976 (1.3539)	
[2022-01-21 12:46:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][330/1251]	eta 0:34:29 lr 0.000642	time 2.3493 (2.2475)	loss 2.7809 (3.6146)	grad_norm 1.2801 (1.3540)	
[2022-01-21 12:46:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][340/1251]	eta 0:34:09 lr 0.000642	time 2.2050 (2.2495)	loss 4.1945 (3.6249)	grad_norm 1.4092 (1.3524)	
[2022-01-21 12:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][350/1251]	eta 0:33:47 lr 0.000642	time 3.0759 (2.2502)	loss 3.8630 (3.6251)	grad_norm 1.4866 (1.3531)	
[2022-01-21 12:47:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][360/1251]	eta 0:33:26 lr 0.000642	time 1.9259 (2.2514)	loss 3.5625 (3.6203)	grad_norm 1.3171 (1.3526)	
[2022-01-21 12:47:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][370/1251]	eta 0:33:03 lr 0.000642	time 1.9289 (2.2514)	loss 3.9339 (3.6252)	grad_norm 1.4343 (1.3529)	
[2022-01-21 12:48:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][380/1251]	eta 0:32:42 lr 0.000642	time 1.9369 (2.2531)	loss 3.9038 (3.6261)	grad_norm 1.4304 (1.3531)	
[2022-01-21 12:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][390/1251]	eta 0:32:18 lr 0.000642	time 2.7827 (2.2510)	loss 2.8858 (3.6167)	grad_norm 1.7409 (1.3557)	
[2022-01-21 12:48:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][400/1251]	eta 0:31:51 lr 0.000642	time 1.9237 (2.2460)	loss 4.0163 (3.6212)	grad_norm 1.1873 (1.3568)	
[2022-01-21 12:49:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][410/1251]	eta 0:31:23 lr 0.000641	time 1.6217 (2.2392)	loss 3.5353 (3.6223)	grad_norm 1.3253 (1.3558)	
[2022-01-21 12:49:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][420/1251]	eta 0:31:00 lr 0.000641	time 1.8825 (2.2384)	loss 2.9868 (3.6262)	grad_norm 1.3829 (1.3564)	
[2022-01-21 12:49:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][430/1251]	eta 0:30:37 lr 0.000641	time 3.1501 (2.2385)	loss 4.1250 (3.6240)	grad_norm 1.4301 (1.3560)	
[2022-01-21 12:50:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][440/1251]	eta 0:30:15 lr 0.000641	time 2.5504 (2.2380)	loss 4.1640 (3.6219)	grad_norm 1.5164 (1.3574)	
[2022-01-21 12:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][450/1251]	eta 0:29:51 lr 0.000641	time 2.0991 (2.2372)	loss 4.0402 (3.6233)	grad_norm 1.5418 (1.3581)	
[2022-01-21 12:50:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][460/1251]	eta 0:29:30 lr 0.000641	time 1.9197 (2.2379)	loss 2.7522 (3.6235)	grad_norm 1.4042 (1.3595)	
[2022-01-21 12:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][470/1251]	eta 0:29:08 lr 0.000641	time 3.0159 (2.2383)	loss 4.3685 (3.6254)	grad_norm 1.4926 (1.3603)	
[2022-01-21 12:51:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][480/1251]	eta 0:28:43 lr 0.000641	time 2.2530 (2.2357)	loss 2.6948 (3.6214)	grad_norm 1.2945 (1.3600)	
[2022-01-21 12:51:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][490/1251]	eta 0:28:18 lr 0.000641	time 1.8563 (2.2313)	loss 3.6082 (3.6186)	grad_norm 1.2903 (1.3601)	
[2022-01-21 12:52:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][500/1251]	eta 0:27:54 lr 0.000641	time 2.2127 (2.2291)	loss 3.9380 (3.6212)	grad_norm 1.2633 (1.3591)	
[2022-01-21 12:52:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][510/1251]	eta 0:27:27 lr 0.000641	time 1.9119 (2.2236)	loss 4.2825 (3.6248)	grad_norm 1.2139 (1.3575)	
[2022-01-21 12:52:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][520/1251]	eta 0:27:03 lr 0.000641	time 2.4659 (2.2214)	loss 3.6087 (3.6223)	grad_norm 1.6514 (1.3576)	
[2022-01-21 12:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][530/1251]	eta 0:26:38 lr 0.000641	time 1.4535 (2.2177)	loss 3.7084 (3.6247)	grad_norm 1.1981 (1.3564)	
[2022-01-21 12:53:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][540/1251]	eta 0:26:18 lr 0.000641	time 2.5073 (2.2194)	loss 3.4980 (3.6265)	grad_norm 1.2270 (1.3562)	
[2022-01-21 12:54:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][550/1251]	eta 0:25:56 lr 0.000641	time 2.2342 (2.2204)	loss 3.2644 (3.6311)	grad_norm 1.1844 (1.3564)	
[2022-01-21 12:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][560/1251]	eta 0:25:36 lr 0.000641	time 2.3217 (2.2238)	loss 3.7926 (3.6333)	grad_norm 1.2891 (1.3565)	
[2022-01-21 12:54:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][570/1251]	eta 0:25:15 lr 0.000641	time 2.0862 (2.2252)	loss 3.3758 (3.6366)	grad_norm 1.2327 (1.3563)	
[2022-01-21 12:55:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][580/1251]	eta 0:24:53 lr 0.000641	time 2.9200 (2.2258)	loss 3.5552 (3.6419)	grad_norm 1.2954 (1.3568)	
[2022-01-21 12:55:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][590/1251]	eta 0:24:29 lr 0.000641	time 1.6713 (2.2233)	loss 3.9397 (3.6393)	grad_norm 1.3216 (1.3568)	
[2022-01-21 12:55:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][600/1251]	eta 0:24:07 lr 0.000641	time 2.9441 (2.2239)	loss 4.1906 (3.6415)	grad_norm 1.1867 (1.3568)	
[2022-01-21 12:56:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][610/1251]	eta 0:23:45 lr 0.000641	time 1.5874 (2.2245)	loss 3.2695 (3.6387)	grad_norm 1.1423 (1.3556)	
[2022-01-21 12:56:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][620/1251]	eta 0:23:23 lr 0.000641	time 2.6511 (2.2241)	loss 4.2660 (3.6424)	grad_norm 1.2655 (1.3542)	
[2022-01-21 12:57:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][630/1251]	eta 0:23:00 lr 0.000641	time 1.8810 (2.2224)	loss 3.0829 (3.6421)	grad_norm 1.2650 (1.3544)	
[2022-01-21 12:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][640/1251]	eta 0:22:37 lr 0.000641	time 2.2919 (2.2214)	loss 4.0528 (3.6440)	grad_norm 1.2733 (1.3542)	
[2022-01-21 12:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][650/1251]	eta 0:22:15 lr 0.000641	time 2.0369 (2.2222)	loss 2.6138 (3.6465)	grad_norm 1.4194 (1.3533)	
[2022-01-21 12:58:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][660/1251]	eta 0:21:53 lr 0.000640	time 3.1142 (2.2226)	loss 4.1524 (3.6468)	grad_norm 1.2524 (1.3540)	
[2022-01-21 12:58:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][670/1251]	eta 0:21:30 lr 0.000640	time 2.2929 (2.2216)	loss 4.1223 (3.6455)	grad_norm 1.5257 (1.3547)	
[2022-01-21 12:58:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][680/1251]	eta 0:21:06 lr 0.000640	time 1.6187 (2.2188)	loss 3.6500 (3.6460)	grad_norm 1.5121 (1.3553)	
[2022-01-21 12:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][690/1251]	eta 0:20:44 lr 0.000640	time 2.4759 (2.2184)	loss 3.9889 (3.6432)	grad_norm 1.2081 (1.3551)	
[2022-01-21 12:59:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][700/1251]	eta 0:20:20 lr 0.000640	time 1.9287 (2.2154)	loss 3.3592 (3.6429)	grad_norm 1.3393 (1.3553)	
[2022-01-21 12:59:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][710/1251]	eta 0:19:57 lr 0.000640	time 2.6400 (2.2140)	loss 4.1321 (3.6427)	grad_norm 1.1671 (1.3552)	
[2022-01-21 13:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][720/1251]	eta 0:19:34 lr 0.000640	time 1.5881 (2.2124)	loss 3.5898 (3.6421)	grad_norm 1.6319 (1.3555)	
[2022-01-21 13:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][730/1251]	eta 0:19:13 lr 0.000640	time 2.7210 (2.2132)	loss 3.6510 (3.6438)	grad_norm 1.3228 (1.3562)	
[2022-01-21 13:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][740/1251]	eta 0:18:51 lr 0.000640	time 1.7444 (2.2145)	loss 4.0220 (3.6422)	grad_norm 1.2910 (1.3554)	
[2022-01-21 13:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][750/1251]	eta 0:18:30 lr 0.000640	time 1.9800 (2.2164)	loss 4.3631 (3.6453)	grad_norm 1.3560 (1.3549)	
[2022-01-21 13:01:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][760/1251]	eta 0:18:08 lr 0.000640	time 2.7044 (2.2177)	loss 3.4946 (3.6470)	grad_norm 1.2874 (1.3541)	
[2022-01-21 13:02:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][770/1251]	eta 0:17:46 lr 0.000640	time 2.6039 (2.2176)	loss 3.4121 (3.6466)	grad_norm 1.3468 (1.3535)	
[2022-01-21 13:02:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][780/1251]	eta 0:17:23 lr 0.000640	time 2.0767 (2.2160)	loss 3.3758 (3.6474)	grad_norm 1.6928 (1.3542)	
[2022-01-21 13:02:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][790/1251]	eta 0:17:00 lr 0.000640	time 1.9459 (2.2133)	loss 3.9457 (3.6474)	grad_norm 1.4277 (1.3544)	
[2022-01-21 13:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][800/1251]	eta 0:16:38 lr 0.000640	time 2.3284 (2.2129)	loss 3.7624 (3.6473)	grad_norm 1.2252 (1.3538)	
[2022-01-21 13:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][810/1251]	eta 0:16:15 lr 0.000640	time 2.3716 (2.2116)	loss 2.7705 (3.6467)	grad_norm 1.4275 (1.3548)	
[2022-01-21 13:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][820/1251]	eta 0:15:52 lr 0.000640	time 2.0215 (2.2101)	loss 3.8330 (3.6479)	grad_norm 1.4321 (1.3556)	
[2022-01-21 13:04:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][830/1251]	eta 0:15:30 lr 0.000640	time 2.8619 (2.2106)	loss 3.6735 (3.6476)	grad_norm 1.2462 (1.3546)	
[2022-01-21 13:04:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][840/1251]	eta 0:15:08 lr 0.000640	time 2.6460 (2.2107)	loss 3.9073 (3.6482)	grad_norm 1.2716 (1.3552)	
[2022-01-21 13:05:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][850/1251]	eta 0:14:46 lr 0.000640	time 1.8559 (2.2096)	loss 3.9109 (3.6492)	grad_norm 1.5756 (1.3563)	
[2022-01-21 13:05:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][860/1251]	eta 0:14:24 lr 0.000640	time 2.1542 (2.2103)	loss 2.7906 (3.6488)	grad_norm 1.3160 (1.3561)	
[2022-01-21 13:05:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][870/1251]	eta 0:14:01 lr 0.000640	time 2.2109 (2.2096)	loss 4.1518 (3.6490)	grad_norm 1.4755 (1.3552)	
[2022-01-21 13:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][880/1251]	eta 0:13:39 lr 0.000640	time 2.2737 (2.2081)	loss 3.6489 (3.6470)	grad_norm 1.3496 (1.3552)	
[2022-01-21 13:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][890/1251]	eta 0:13:17 lr 0.000640	time 2.4082 (2.2082)	loss 4.2547 (3.6460)	grad_norm 1.2172 (1.3547)	
[2022-01-21 13:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][900/1251]	eta 0:12:55 lr 0.000640	time 2.0527 (2.2088)	loss 3.9052 (3.6448)	grad_norm 1.1389 (1.3550)	
[2022-01-21 13:07:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][910/1251]	eta 0:12:33 lr 0.000639	time 2.9897 (2.2108)	loss 4.0459 (3.6452)	grad_norm 1.3337 (1.3542)	
[2022-01-21 13:07:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][920/1251]	eta 0:12:11 lr 0.000639	time 1.7105 (2.2098)	loss 4.0553 (3.6427)	grad_norm 1.5369 (1.3548)	
[2022-01-21 13:07:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][930/1251]	eta 0:11:48 lr 0.000639	time 2.1263 (2.2085)	loss 3.8747 (3.6417)	grad_norm 1.3322 (1.3555)	
[2022-01-21 13:08:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][940/1251]	eta 0:11:26 lr 0.000639	time 1.7415 (2.2066)	loss 4.1909 (3.6419)	grad_norm 1.2119 (1.3557)	
[2022-01-21 13:08:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][950/1251]	eta 0:11:03 lr 0.000639	time 2.4810 (2.2052)	loss 3.8087 (3.6440)	grad_norm 1.3328 (1.3567)	
[2022-01-21 13:09:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][960/1251]	eta 0:10:41 lr 0.000639	time 2.5970 (2.2044)	loss 4.0410 (3.6446)	grad_norm 1.1961 (1.3573)	
[2022-01-21 13:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][970/1251]	eta 0:10:19 lr 0.000639	time 1.8236 (2.2041)	loss 3.7905 (3.6463)	grad_norm 1.2252 (1.3569)	
[2022-01-21 13:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][980/1251]	eta 0:09:57 lr 0.000639	time 1.9593 (2.2046)	loss 4.4715 (3.6463)	grad_norm 1.3256 (1.3564)	
[2022-01-21 13:10:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][990/1251]	eta 0:09:36 lr 0.000639	time 3.0186 (2.2069)	loss 3.9648 (3.6448)	grad_norm 1.3874 (1.3567)	
[2022-01-21 13:10:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1000/1251]	eta 0:09:13 lr 0.000639	time 2.0199 (2.2071)	loss 3.3767 (3.6443)	grad_norm 1.5450 (1.3568)	
[2022-01-21 13:10:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1010/1251]	eta 0:08:51 lr 0.000639	time 2.3029 (2.2071)	loss 2.4402 (3.6426)	grad_norm 1.2969 (1.3568)	
[2022-01-21 13:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1020/1251]	eta 0:08:29 lr 0.000639	time 1.9335 (2.2063)	loss 3.9768 (3.6431)	grad_norm 1.3973 (1.3568)	
[2022-01-21 13:11:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1030/1251]	eta 0:08:07 lr 0.000639	time 2.1595 (2.2060)	loss 4.2544 (3.6432)	grad_norm 1.2161 (1.3562)	
[2022-01-21 13:11:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1040/1251]	eta 0:07:45 lr 0.000639	time 1.9726 (2.2058)	loss 3.6421 (3.6430)	grad_norm 1.5892 (1.3559)	
[2022-01-21 13:12:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1050/1251]	eta 0:07:23 lr 0.000639	time 2.5734 (2.2064)	loss 3.7754 (3.6433)	grad_norm 1.3432 (1.3552)	
[2022-01-21 13:12:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1060/1251]	eta 0:07:01 lr 0.000639	time 1.8592 (2.2057)	loss 4.2294 (3.6458)	grad_norm 1.2690 (1.3544)	
[2022-01-21 13:13:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1070/1251]	eta 0:06:39 lr 0.000639	time 2.2025 (2.2064)	loss 2.4514 (3.6446)	grad_norm 1.2150 (1.3535)	
[2022-01-21 13:13:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1080/1251]	eta 0:06:17 lr 0.000639	time 2.2002 (2.2057)	loss 2.8202 (3.6469)	grad_norm 1.4050 (1.3539)	
[2022-01-21 13:13:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1090/1251]	eta 0:05:55 lr 0.000639	time 1.8809 (2.2051)	loss 3.9924 (3.6446)	grad_norm 1.3208 (1.3535)	
[2022-01-21 13:14:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1100/1251]	eta 0:05:32 lr 0.000639	time 1.8970 (2.2035)	loss 4.0363 (3.6436)	grad_norm 1.4150 (1.3534)	
[2022-01-21 13:14:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1110/1251]	eta 0:05:10 lr 0.000639	time 2.4887 (2.2040)	loss 4.1373 (3.6405)	grad_norm 1.3355 (1.3534)	
[2022-01-21 13:14:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1120/1251]	eta 0:04:48 lr 0.000639	time 3.3922 (2.2060)	loss 3.8935 (3.6399)	grad_norm 1.2815 (1.3535)	
[2022-01-21 13:15:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1130/1251]	eta 0:04:26 lr 0.000639	time 1.7275 (2.2053)	loss 3.9018 (3.6406)	grad_norm 1.3271 (1.3536)	
[2022-01-21 13:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1140/1251]	eta 0:04:04 lr 0.000639	time 2.1844 (2.2039)	loss 3.9732 (3.6410)	grad_norm 1.1900 (1.3528)	
[2022-01-21 13:15:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1150/1251]	eta 0:03:42 lr 0.000639	time 2.2982 (2.2028)	loss 3.9234 (3.6414)	grad_norm 1.4359 (1.3524)	
[2022-01-21 13:16:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1160/1251]	eta 0:03:20 lr 0.000638	time 3.0634 (2.2039)	loss 3.9934 (3.6424)	grad_norm 1.2160 (1.3526)	
[2022-01-21 13:16:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1170/1251]	eta 0:02:58 lr 0.000638	time 1.9402 (2.2034)	loss 3.6350 (3.6421)	grad_norm 1.0687 (1.3521)	
[2022-01-21 13:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1180/1251]	eta 0:02:36 lr 0.000638	time 2.7119 (2.2035)	loss 2.8661 (3.6427)	grad_norm 1.3698 (1.3518)	
[2022-01-21 13:17:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1190/1251]	eta 0:02:14 lr 0.000638	time 1.6144 (2.2028)	loss 4.2811 (3.6435)	grad_norm 1.2271 (1.3509)	
[2022-01-21 13:17:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1200/1251]	eta 0:01:52 lr 0.000638	time 2.7705 (2.2025)	loss 4.1601 (3.6433)	grad_norm 1.1908 (1.3509)	
[2022-01-21 13:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1210/1251]	eta 0:01:30 lr 0.000638	time 1.9154 (2.2037)	loss 3.0104 (3.6402)	grad_norm 1.2235 (1.3508)	
[2022-01-21 13:18:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1220/1251]	eta 0:01:08 lr 0.000638	time 3.2277 (2.2044)	loss 2.5704 (3.6393)	grad_norm 1.2875 (1.3505)	
[2022-01-21 13:18:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1230/1251]	eta 0:00:46 lr 0.000638	time 1.5563 (2.2036)	loss 3.2915 (3.6381)	grad_norm 1.3771 (1.3506)	
[2022-01-21 13:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1240/1251]	eta 0:00:24 lr 0.000638	time 1.5277 (2.2008)	loss 4.2372 (3.6377)	grad_norm 1.3613 (1.3507)	
[2022-01-21 13:19:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [123/300][1250/1251]	eta 0:00:02 lr 0.000638	time 1.1771 (2.1941)	loss 4.1961 (3.6392)	grad_norm 1.4004 (1.3510)	
[2022-01-21 13:19:26 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 123 training takes 0:45:45
[2022-01-21 13:19:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.487 (18.487)	Loss 1.1270 (1.1270)	Acc@1 73.145 (73.145)	Acc@5 91.602 (91.602)	
[2022-01-21 13:20:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.866 (3.254)	Loss 1.0384 (1.0893)	Acc@1 76.562 (74.840)	Acc@5 92.871 (92.436)	
[2022-01-21 13:20:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.318 (2.446)	Loss 1.1157 (1.0871)	Acc@1 74.707 (74.642)	Acc@5 91.797 (92.518)	
[2022-01-21 13:20:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.656 (2.169)	Loss 1.0990 (1.0782)	Acc@1 74.707 (74.921)	Acc@5 92.480 (92.654)	
[2022-01-21 13:20:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.606 (2.171)	Loss 1.1601 (1.0776)	Acc@1 73.926 (74.898)	Acc@5 91.895 (92.712)	
[2022-01-21 13:21:03 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.774 Acc@5 92.658
[2022-01-21 13:21:03 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.8%
[2022-01-21 13:21:03 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.95%
[2022-01-21 13:21:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][0/1251]	eta 7:27:00 lr 0.000638	time 21.4391 (21.4391)	loss 3.7610 (3.7610)	grad_norm 1.4058 (1.4058)	
[2022-01-21 13:21:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][10/1251]	eta 1:25:19 lr 0.000638	time 2.0932 (4.1254)	loss 2.9035 (3.4939)	grad_norm 1.2937 (1.3029)	
[2022-01-21 13:22:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][20/1251]	eta 1:04:08 lr 0.000638	time 1.5138 (3.1262)	loss 3.2045 (3.4982)	grad_norm 1.2634 (1.3310)	
[2022-01-21 13:22:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][30/1251]	eta 0:56:43 lr 0.000638	time 1.3930 (2.7873)	loss 2.7639 (3.5630)	grad_norm 1.2240 (1.3391)	
[2022-01-21 13:22:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][40/1251]	eta 0:54:12 lr 0.000638	time 3.9259 (2.6860)	loss 4.1586 (3.5973)	grad_norm 1.1845 (1.3437)	
[2022-01-21 13:23:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][50/1251]	eta 0:52:28 lr 0.000638	time 2.7680 (2.6215)	loss 3.6597 (3.5902)	grad_norm 1.4001 (1.3633)	
[2022-01-21 13:23:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][60/1251]	eta 0:50:29 lr 0.000638	time 1.8800 (2.5433)	loss 4.0315 (3.6123)	grad_norm 1.3430 (1.3563)	
[2022-01-21 13:23:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][70/1251]	eta 0:48:45 lr 0.000638	time 1.8128 (2.4774)	loss 2.9380 (3.6194)	grad_norm 1.4345 (1.3667)	
[2022-01-21 13:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][80/1251]	eta 0:48:10 lr 0.000638	time 3.8316 (2.4681)	loss 3.0206 (3.5993)	grad_norm 1.3838 (1.3701)	
[2022-01-21 13:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][90/1251]	eta 0:47:37 lr 0.000638	time 3.4282 (2.4610)	loss 4.4442 (3.5601)	grad_norm 1.4459 (1.3725)	
[2022-01-21 13:25:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][100/1251]	eta 0:46:40 lr 0.000638	time 1.5172 (2.4327)	loss 4.2142 (3.5728)	grad_norm 1.2949 (1.3651)	
[2022-01-21 13:25:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][110/1251]	eta 0:45:52 lr 0.000638	time 1.7175 (2.4122)	loss 4.3674 (3.5867)	grad_norm 1.2989 (1.3653)	
[2022-01-21 13:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][120/1251]	eta 0:45:05 lr 0.000638	time 2.4013 (2.3918)	loss 2.8725 (3.6013)	grad_norm 1.7286 (1.3655)	
[2022-01-21 13:26:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][130/1251]	eta 0:44:11 lr 0.000638	time 1.9695 (2.3651)	loss 4.0424 (3.6092)	grad_norm 1.3179 (1.3610)	
[2022-01-21 13:26:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][140/1251]	eta 0:43:23 lr 0.000638	time 1.8849 (2.3437)	loss 4.1169 (3.5827)	grad_norm 1.5655 (1.3692)	
[2022-01-21 13:26:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][150/1251]	eta 0:42:53 lr 0.000638	time 1.9419 (2.3377)	loss 3.9885 (3.5832)	grad_norm 1.3165 (1.3724)	
[2022-01-21 13:27:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][160/1251]	eta 0:42:17 lr 0.000637	time 2.3027 (2.3255)	loss 3.7450 (3.5864)	grad_norm 1.2439 (1.3725)	
[2022-01-21 13:27:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][170/1251]	eta 0:41:46 lr 0.000637	time 2.5436 (2.3190)	loss 3.9121 (3.5846)	grad_norm 1.3028 (1.3725)	
[2022-01-21 13:28:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][180/1251]	eta 0:41:17 lr 0.000637	time 2.0409 (2.3135)	loss 3.2705 (3.5861)	grad_norm 1.5260 (1.3721)	
[2022-01-21 13:28:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][190/1251]	eta 0:40:46 lr 0.000637	time 1.9651 (2.3055)	loss 3.2827 (3.5910)	grad_norm 1.2714 (1.3747)	
[2022-01-21 13:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][200/1251]	eta 0:40:23 lr 0.000637	time 3.0195 (2.3060)	loss 4.3174 (3.5962)	grad_norm 1.7215 (1.3753)	
[2022-01-21 13:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][210/1251]	eta 0:39:53 lr 0.000637	time 2.2271 (2.2992)	loss 2.5708 (3.6038)	grad_norm 1.2566 (1.3742)	
[2022-01-21 13:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][220/1251]	eta 0:39:16 lr 0.000637	time 1.9344 (2.2860)	loss 3.2158 (3.6035)	grad_norm 1.4897 (1.3723)	
[2022-01-21 13:29:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][230/1251]	eta 0:38:42 lr 0.000637	time 1.8959 (2.2747)	loss 2.7253 (3.6051)	grad_norm 1.3953 (1.3738)	
[2022-01-21 13:30:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][240/1251]	eta 0:38:16 lr 0.000637	time 2.8629 (2.2715)	loss 3.3988 (3.6238)	grad_norm 1.1661 (1.3726)	
[2022-01-21 13:30:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][250/1251]	eta 0:37:47 lr 0.000637	time 2.0880 (2.2655)	loss 3.7517 (3.6226)	grad_norm 1.6422 (1.3760)	
[2022-01-21 13:30:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][260/1251]	eta 0:37:24 lr 0.000637	time 3.0974 (2.2650)	loss 3.1628 (3.6175)	grad_norm 1.4552 (1.3778)	
[2022-01-21 13:31:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][270/1251]	eta 0:37:00 lr 0.000637	time 1.4318 (2.2637)	loss 3.5000 (3.6232)	grad_norm 1.4144 (1.3756)	
[2022-01-21 13:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][280/1251]	eta 0:36:37 lr 0.000637	time 1.8479 (2.2635)	loss 3.0814 (3.6178)	grad_norm 1.3369 (1.3761)	
[2022-01-21 13:32:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][290/1251]	eta 0:36:13 lr 0.000637	time 2.0978 (2.2622)	loss 2.5034 (3.6136)	grad_norm 1.3304 (1.3766)	
[2022-01-21 13:32:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][300/1251]	eta 0:35:44 lr 0.000637	time 2.4084 (2.2552)	loss 3.3113 (3.6164)	grad_norm 1.2621 (1.3770)	
[2022-01-21 13:32:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][310/1251]	eta 0:35:19 lr 0.000637	time 2.8766 (2.2520)	loss 3.1986 (3.6136)	grad_norm 1.4085 (1.3755)	
[2022-01-21 13:33:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][320/1251]	eta 0:34:52 lr 0.000637	time 1.6945 (2.2481)	loss 3.6954 (3.6149)	grad_norm 1.1686 (1.3738)	
[2022-01-21 13:33:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][330/1251]	eta 0:34:33 lr 0.000637	time 2.3042 (2.2519)	loss 3.9946 (3.6181)	grad_norm 1.3118 (1.3738)	
[2022-01-21 13:33:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][340/1251]	eta 0:34:08 lr 0.000637	time 1.8864 (2.2489)	loss 4.1349 (3.6238)	grad_norm 1.4000 (1.3737)	
[2022-01-21 13:34:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][350/1251]	eta 0:33:44 lr 0.000637	time 2.4194 (2.2474)	loss 2.6848 (3.6307)	grad_norm 1.3383 (1.3747)	
[2022-01-21 13:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][360/1251]	eta 0:33:17 lr 0.000637	time 1.5493 (2.2422)	loss 3.7598 (3.6288)	grad_norm 1.4312 (1.3758)	
[2022-01-21 13:34:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][370/1251]	eta 0:32:52 lr 0.000637	time 2.3175 (2.2385)	loss 4.1321 (3.6323)	grad_norm 1.5148 (1.3773)	
[2022-01-21 13:35:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][380/1251]	eta 0:32:29 lr 0.000637	time 2.1530 (2.2384)	loss 4.4093 (3.6359)	grad_norm 1.2192 (1.3786)	
[2022-01-21 13:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][390/1251]	eta 0:32:12 lr 0.000637	time 3.7645 (2.2444)	loss 4.0826 (3.6415)	grad_norm 1.4036 (1.3837)	
[2022-01-21 13:36:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][400/1251]	eta 0:31:53 lr 0.000637	time 2.9408 (2.2491)	loss 3.7934 (3.6394)	grad_norm 1.2255 (1.3823)	
[2022-01-21 13:36:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][410/1251]	eta 0:31:32 lr 0.000636	time 2.1568 (2.2498)	loss 4.0350 (3.6384)	grad_norm 1.5737 (1.3838)	
[2022-01-21 13:36:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][420/1251]	eta 0:31:06 lr 0.000636	time 1.8855 (2.2464)	loss 3.0869 (3.6384)	grad_norm 1.5562 (1.3853)	
[2022-01-21 13:37:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][430/1251]	eta 0:30:38 lr 0.000636	time 1.8705 (2.2398)	loss 4.0439 (3.6407)	grad_norm 1.4579 (1.3862)	
[2022-01-21 13:37:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][440/1251]	eta 0:30:10 lr 0.000636	time 2.2063 (2.2329)	loss 3.5375 (3.6437)	grad_norm 1.2754 (1.3874)	
[2022-01-21 13:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][450/1251]	eta 0:29:45 lr 0.000636	time 1.9278 (2.2288)	loss 2.7238 (3.6412)	grad_norm 1.2084 (1.3882)	
[2022-01-21 13:38:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][460/1251]	eta 0:29:23 lr 0.000636	time 2.2457 (2.2292)	loss 3.2903 (3.6435)	grad_norm 1.5035 (1.3875)	
[2022-01-21 13:38:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][470/1251]	eta 0:28:59 lr 0.000636	time 2.2299 (2.2275)	loss 3.3807 (3.6454)	grad_norm 1.4193 (1.3855)	
[2022-01-21 13:38:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][480/1251]	eta 0:28:36 lr 0.000636	time 2.4990 (2.2258)	loss 3.1331 (3.6421)	grad_norm 1.5225 (1.3851)	
[2022-01-21 13:39:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][490/1251]	eta 0:28:16 lr 0.000636	time 1.5669 (2.2297)	loss 3.5845 (3.6454)	grad_norm 1.3203 (1.3844)	
[2022-01-21 13:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][500/1251]	eta 0:27:56 lr 0.000636	time 1.8660 (2.2326)	loss 3.4134 (3.6441)	grad_norm 1.3224 (1.3841)	
[2022-01-21 13:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][510/1251]	eta 0:27:36 lr 0.000636	time 3.2122 (2.2350)	loss 3.2771 (3.6441)	grad_norm 1.5350 (1.3829)	
[2022-01-21 13:40:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][520/1251]	eta 0:27:14 lr 0.000636	time 2.9094 (2.2360)	loss 4.4673 (3.6437)	grad_norm 1.3201 (1.3819)	
[2022-01-21 13:40:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][530/1251]	eta 0:26:51 lr 0.000636	time 1.8445 (2.2349)	loss 3.9041 (3.6430)	grad_norm 1.1934 (1.3803)	
[2022-01-21 13:41:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][540/1251]	eta 0:26:26 lr 0.000636	time 1.9142 (2.2320)	loss 3.6048 (3.6453)	grad_norm 1.2207 (1.3808)	
[2022-01-21 13:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][550/1251]	eta 0:26:01 lr 0.000636	time 2.5570 (2.2275)	loss 3.4473 (3.6399)	grad_norm 1.2670 (1.3799)	
[2022-01-21 13:41:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][560/1251]	eta 0:25:37 lr 0.000636	time 2.0159 (2.2255)	loss 3.1656 (3.6403)	grad_norm 1.6409 (1.3792)	
[2022-01-21 13:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][570/1251]	eta 0:25:15 lr 0.000636	time 1.8445 (2.2247)	loss 4.0210 (3.6444)	grad_norm 1.5042 (1.3792)	
[2022-01-21 13:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][580/1251]	eta 0:24:52 lr 0.000636	time 2.2541 (2.2236)	loss 3.1851 (3.6400)	grad_norm 1.4358 (1.3780)	
[2022-01-21 13:42:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][590/1251]	eta 0:24:31 lr 0.000636	time 3.2802 (2.2264)	loss 4.0378 (3.6376)	grad_norm 1.2091 (1.3767)	
[2022-01-21 13:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][600/1251]	eta 0:24:09 lr 0.000636	time 2.7164 (2.2264)	loss 4.0776 (3.6398)	grad_norm 1.2857 (1.3767)	
[2022-01-21 13:43:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][610/1251]	eta 0:23:46 lr 0.000636	time 1.8855 (2.2257)	loss 3.2878 (3.6415)	grad_norm 1.3610 (1.3770)	
[2022-01-21 13:44:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][620/1251]	eta 0:23:23 lr 0.000636	time 2.1851 (2.2248)	loss 3.9194 (3.6417)	grad_norm 1.2992 (1.3760)	
[2022-01-21 13:44:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][630/1251]	eta 0:23:02 lr 0.000636	time 3.1624 (2.2255)	loss 3.8853 (3.6411)	grad_norm 1.8536 (1.3757)	
[2022-01-21 13:44:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][640/1251]	eta 0:22:37 lr 0.000636	time 1.9606 (2.2214)	loss 3.5826 (3.6398)	grad_norm 1.2625 (1.3740)	
[2022-01-21 13:45:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][650/1251]	eta 0:22:13 lr 0.000636	time 1.9249 (2.2181)	loss 3.1496 (3.6400)	grad_norm 1.2515 (1.3723)	
[2022-01-21 13:45:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][660/1251]	eta 0:21:49 lr 0.000635	time 2.1717 (2.2150)	loss 2.8850 (3.6388)	grad_norm 1.5786 (1.3720)	
[2022-01-21 13:45:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][670/1251]	eta 0:21:26 lr 0.000635	time 2.6324 (2.2140)	loss 2.4957 (3.6370)	grad_norm 1.4849 (1.3720)	
[2022-01-21 13:46:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][680/1251]	eta 0:21:03 lr 0.000635	time 1.8959 (2.2129)	loss 4.0237 (3.6403)	grad_norm 1.3900 (1.3721)	
[2022-01-21 13:46:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][690/1251]	eta 0:20:39 lr 0.000635	time 1.8554 (2.2100)	loss 3.0108 (3.6368)	grad_norm 1.4291 (1.3705)	
[2022-01-21 13:46:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][700/1251]	eta 0:20:17 lr 0.000635	time 1.8257 (2.2100)	loss 3.7325 (3.6343)	grad_norm 1.3014 (1.3706)	
[2022-01-21 13:47:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][710/1251]	eta 0:19:55 lr 0.000635	time 2.8251 (2.2107)	loss 3.9760 (3.6397)	grad_norm 1.4804 (1.3707)	
[2022-01-21 13:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][720/1251]	eta 0:19:35 lr 0.000635	time 2.8067 (2.2144)	loss 4.4394 (3.6387)	grad_norm 1.4208 (1.3703)	
[2022-01-21 13:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][730/1251]	eta 0:19:14 lr 0.000635	time 2.0864 (2.2154)	loss 3.0039 (3.6376)	grad_norm 1.3789 (1.3700)	
[2022-01-21 13:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][740/1251]	eta 0:18:52 lr 0.000635	time 2.2592 (2.2169)	loss 4.3793 (3.6392)	grad_norm 1.2684 (1.3710)	
[2022-01-21 13:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][750/1251]	eta 0:18:30 lr 0.000635	time 2.3740 (2.2166)	loss 3.3960 (3.6437)	grad_norm 1.1561 (1.3721)	
[2022-01-21 13:49:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][760/1251]	eta 0:18:07 lr 0.000635	time 1.9533 (2.2149)	loss 2.9413 (3.6453)	grad_norm 1.3963 (1.3715)	
[2022-01-21 13:49:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][770/1251]	eta 0:17:44 lr 0.000635	time 2.2828 (2.2132)	loss 3.9917 (3.6433)	grad_norm 1.1912 (1.3713)	
[2022-01-21 13:49:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][780/1251]	eta 0:17:22 lr 0.000635	time 2.1257 (2.2128)	loss 4.2780 (3.6402)	grad_norm 1.2368 (1.3718)	
[2022-01-21 13:50:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][790/1251]	eta 0:16:59 lr 0.000635	time 2.3164 (2.2123)	loss 4.2618 (3.6395)	grad_norm 1.2187 (1.3702)	
[2022-01-21 13:50:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][800/1251]	eta 0:16:37 lr 0.000635	time 1.8033 (2.2110)	loss 4.2949 (3.6397)	grad_norm 1.2132 (1.3705)	
[2022-01-21 13:50:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][810/1251]	eta 0:16:14 lr 0.000635	time 1.8894 (2.2107)	loss 3.8461 (3.6413)	grad_norm 1.2365 (1.3706)	
[2022-01-21 13:51:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][820/1251]	eta 0:15:53 lr 0.000635	time 2.0978 (2.2120)	loss 3.1696 (3.6407)	grad_norm 1.2486 (1.3704)	
[2022-01-21 13:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][830/1251]	eta 0:15:32 lr 0.000635	time 3.3671 (2.2145)	loss 3.1968 (3.6403)	grad_norm 1.5256 (1.3698)	
[2022-01-21 13:52:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][840/1251]	eta 0:15:09 lr 0.000635	time 1.7834 (2.2136)	loss 4.1958 (3.6419)	grad_norm 1.2933 (1.3704)	
[2022-01-21 13:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][850/1251]	eta 0:14:47 lr 0.000635	time 1.5300 (2.2120)	loss 2.3395 (3.6360)	grad_norm 1.4354 (1.3706)	
[2022-01-21 13:52:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][860/1251]	eta 0:14:23 lr 0.000635	time 1.8784 (2.2093)	loss 3.6035 (3.6342)	grad_norm 1.4348 (1.3701)	
[2022-01-21 13:53:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][870/1251]	eta 0:14:01 lr 0.000635	time 2.4681 (2.2087)	loss 2.5704 (3.6314)	grad_norm 1.1186 (1.3686)	
[2022-01-21 13:53:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][880/1251]	eta 0:13:39 lr 0.000635	time 2.1047 (2.2076)	loss 3.9742 (3.6343)	grad_norm 1.5016 (1.3684)	
[2022-01-21 13:53:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][890/1251]	eta 0:13:16 lr 0.000635	time 2.3751 (2.2076)	loss 3.7905 (3.6355)	grad_norm 1.2334 (1.3683)	
[2022-01-21 13:54:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][900/1251]	eta 0:12:54 lr 0.000635	time 2.1706 (2.2063)	loss 4.0404 (3.6358)	grad_norm 1.2060 (1.3676)	
[2022-01-21 13:54:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][910/1251]	eta 0:12:32 lr 0.000634	time 1.8354 (2.2059)	loss 3.4822 (3.6384)	grad_norm 1.2804 (1.3676)	
[2022-01-21 13:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][920/1251]	eta 0:12:11 lr 0.000634	time 3.4509 (2.2089)	loss 3.2778 (3.6381)	grad_norm 1.3350 (1.3680)	
[2022-01-21 13:55:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][930/1251]	eta 0:11:49 lr 0.000634	time 2.4144 (2.2105)	loss 3.8782 (3.6373)	grad_norm 1.2125 (1.3681)	
[2022-01-21 13:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][940/1251]	eta 0:11:27 lr 0.000634	time 1.8627 (2.2104)	loss 4.0987 (3.6398)	grad_norm 1.5713 (1.3677)	
[2022-01-21 13:56:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][950/1251]	eta 0:11:04 lr 0.000634	time 1.8158 (2.2079)	loss 3.9281 (3.6407)	grad_norm 1.3224 (1.3675)	
[2022-01-21 13:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][960/1251]	eta 0:10:42 lr 0.000634	time 2.5174 (2.2067)	loss 2.7565 (3.6411)	grad_norm 1.3487 (1.3669)	
[2022-01-21 13:56:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][970/1251]	eta 0:10:19 lr 0.000634	time 2.2488 (2.2058)	loss 4.1635 (3.6411)	grad_norm 1.2447 (1.3659)	
[2022-01-21 13:57:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][980/1251]	eta 0:09:57 lr 0.000634	time 1.9370 (2.2052)	loss 3.0899 (3.6400)	grad_norm 1.3433 (1.3665)	
[2022-01-21 13:57:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][990/1251]	eta 0:09:35 lr 0.000634	time 2.1281 (2.2047)	loss 3.3226 (3.6403)	grad_norm 2.0166 (1.3668)	
[2022-01-21 13:57:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1000/1251]	eta 0:09:13 lr 0.000634	time 2.9304 (2.2050)	loss 3.9796 (3.6412)	grad_norm 1.5383 (1.3671)	
[2022-01-21 13:58:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1010/1251]	eta 0:08:51 lr 0.000634	time 3.5552 (2.2055)	loss 3.9129 (3.6405)	grad_norm 1.2591 (1.3676)	
[2022-01-21 13:58:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1020/1251]	eta 0:08:29 lr 0.000634	time 1.6368 (2.2053)	loss 4.3584 (3.6410)	grad_norm 1.5100 (1.3680)	
[2022-01-21 13:58:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1030/1251]	eta 0:08:07 lr 0.000634	time 2.8885 (2.2060)	loss 2.5552 (3.6405)	grad_norm 1.3249 (1.3684)	
[2022-01-21 13:59:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1040/1251]	eta 0:07:45 lr 0.000634	time 2.5514 (2.2057)	loss 3.5210 (3.6414)	grad_norm 1.3278 (1.3688)	
[2022-01-21 13:59:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1050/1251]	eta 0:07:23 lr 0.000634	time 2.8299 (2.2063)	loss 3.9908 (3.6399)	grad_norm 1.3898 (1.3688)	
[2022-01-21 14:00:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1060/1251]	eta 0:07:01 lr 0.000634	time 2.2111 (2.2052)	loss 3.0928 (3.6417)	grad_norm 1.3676 (1.3689)	
[2022-01-21 14:00:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1070/1251]	eta 0:06:39 lr 0.000634	time 1.9425 (2.2044)	loss 3.8503 (3.6420)	grad_norm 1.2349 (1.3682)	
[2022-01-21 14:00:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1080/1251]	eta 0:06:17 lr 0.000634	time 2.4252 (2.2051)	loss 4.0753 (3.6453)	grad_norm 1.2026 (1.3673)	
[2022-01-21 14:01:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1090/1251]	eta 0:05:55 lr 0.000634	time 2.8614 (2.2053)	loss 3.9142 (3.6458)	grad_norm 1.3696 (1.3673)	
[2022-01-21 14:01:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1100/1251]	eta 0:05:32 lr 0.000634	time 1.8815 (2.2035)	loss 3.6909 (3.6459)	grad_norm 1.4349 (1.3679)	
[2022-01-21 14:01:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1110/1251]	eta 0:05:10 lr 0.000634	time 2.2034 (2.2022)	loss 3.9804 (3.6451)	grad_norm 1.2601 (1.3678)	
[2022-01-21 14:02:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1120/1251]	eta 0:04:48 lr 0.000634	time 2.2527 (2.2012)	loss 4.2088 (3.6457)	grad_norm 1.2630 (1.3681)	
[2022-01-21 14:02:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1130/1251]	eta 0:04:26 lr 0.000634	time 1.7859 (2.2008)	loss 3.2570 (3.6454)	grad_norm 1.5715 (1.3687)	
[2022-01-21 14:02:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1140/1251]	eta 0:04:04 lr 0.000634	time 2.1908 (2.2013)	loss 4.3236 (3.6469)	grad_norm 1.3714 (1.3684)	
[2022-01-21 14:03:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1150/1251]	eta 0:03:42 lr 0.000634	time 2.7125 (2.2022)	loss 3.1886 (3.6490)	grad_norm 1.6199 (1.3684)	
[2022-01-21 14:03:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1160/1251]	eta 0:03:20 lr 0.000633	time 2.2878 (2.2022)	loss 4.0561 (3.6490)	grad_norm 1.1779 (1.3679)	
[2022-01-21 14:04:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1170/1251]	eta 0:02:58 lr 0.000633	time 2.1248 (2.2016)	loss 3.2924 (3.6507)	grad_norm 1.2553 (1.3678)	
[2022-01-21 14:04:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1180/1251]	eta 0:02:36 lr 0.000633	time 2.4079 (2.2017)	loss 4.2039 (3.6547)	grad_norm 1.3330 (1.3680)	
[2022-01-21 14:04:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1190/1251]	eta 0:02:14 lr 0.000633	time 2.5457 (2.2013)	loss 4.3032 (3.6533)	grad_norm 1.4946 (1.3687)	
[2022-01-21 14:05:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1200/1251]	eta 0:01:52 lr 0.000633	time 1.9372 (2.2007)	loss 2.7915 (3.6528)	grad_norm 1.5403 (1.3687)	
[2022-01-21 14:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1210/1251]	eta 0:01:30 lr 0.000633	time 1.8530 (2.2014)	loss 4.3928 (3.6553)	grad_norm 1.2660 (1.3686)	
[2022-01-21 14:05:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1220/1251]	eta 0:01:08 lr 0.000633	time 2.8605 (2.2011)	loss 3.5005 (3.6538)	grad_norm 1.2187 (1.3686)	
[2022-01-21 14:06:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1230/1251]	eta 0:00:46 lr 0.000633	time 2.2497 (2.2004)	loss 2.8668 (3.6532)	grad_norm 1.2822 (1.3687)	
[2022-01-21 14:06:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1240/1251]	eta 0:00:24 lr 0.000633	time 1.5248 (2.1989)	loss 3.9299 (3.6527)	grad_norm 1.4717 (1.3687)	
[2022-01-21 14:06:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [124/300][1250/1251]	eta 0:00:02 lr 0.000633	time 1.3146 (2.1932)	loss 2.8472 (3.6523)	grad_norm 1.4105 (1.3686)	
[2022-01-21 14:06:47 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 124 training takes 0:45:44
[2022-01-21 14:07:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.616 (18.616)	Loss 1.0201 (1.0201)	Acc@1 74.609 (74.609)	Acc@5 93.750 (93.750)	
[2022-01-21 14:07:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.562 (3.533)	Loss 1.0365 (1.0525)	Acc@1 76.074 (75.071)	Acc@5 92.871 (92.773)	
[2022-01-21 14:07:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.602 (2.571)	Loss 1.0615 (1.0659)	Acc@1 75.684 (74.893)	Acc@5 91.895 (92.690)	
[2022-01-21 14:07:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.302 (2.230)	Loss 1.0019 (1.0626)	Acc@1 76.465 (74.915)	Acc@5 93.555 (92.704)	
[2022-01-21 14:08:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.631 (2.151)	Loss 1.0858 (1.0695)	Acc@1 74.609 (74.721)	Acc@5 92.188 (92.595)	
[2022-01-21 14:08:22 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.818 Acc@5 92.600
[2022-01-21 14:08:22 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.8%
[2022-01-21 14:08:22 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.95%
[2022-01-21 14:08:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][0/1251]	eta 7:24:42 lr 0.000633	time 21.3286 (21.3286)	loss 3.3534 (3.3534)	grad_norm 1.4086 (1.4086)	
[2022-01-21 14:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][10/1251]	eta 1:21:14 lr 0.000633	time 1.5827 (3.9282)	loss 2.4392 (3.2766)	grad_norm 1.4138 (1.3314)	
[2022-01-21 14:09:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][20/1251]	eta 1:04:11 lr 0.000633	time 2.0673 (3.1291)	loss 4.3028 (3.5917)	grad_norm 1.3013 (1.3431)	
[2022-01-21 14:09:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][30/1251]	eta 0:56:29 lr 0.000633	time 1.8891 (2.7763)	loss 2.5952 (3.5197)	grad_norm 1.4078 (1.3413)	
[2022-01-21 14:10:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][40/1251]	eta 0:55:23 lr 0.000633	time 7.8021 (2.7447)	loss 3.6079 (3.4689)	grad_norm 1.2665 (1.3489)	
[2022-01-21 14:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][50/1251]	eta 0:52:42 lr 0.000633	time 1.2933 (2.6329)	loss 3.8386 (3.5077)	grad_norm 1.6919 (1.3531)	
[2022-01-21 14:10:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][60/1251]	eta 0:50:28 lr 0.000633	time 1.4638 (2.5431)	loss 3.9889 (3.5560)	grad_norm 1.3403 (1.3472)	
[2022-01-21 14:11:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][70/1251]	eta 0:48:51 lr 0.000633	time 1.8148 (2.4826)	loss 3.9040 (3.5624)	grad_norm 1.2722 (1.3546)	
[2022-01-21 14:11:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][80/1251]	eta 0:48:03 lr 0.000633	time 3.6565 (2.4627)	loss 3.5246 (3.5514)	grad_norm 1.6402 (1.3570)	
[2022-01-21 14:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][90/1251]	eta 0:47:12 lr 0.000633	time 1.6654 (2.4398)	loss 3.8719 (3.5693)	grad_norm 1.2399 (1.3600)	
[2022-01-21 14:12:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][100/1251]	eta 0:46:32 lr 0.000633	time 2.4564 (2.4263)	loss 3.7493 (3.5662)	grad_norm 1.4294 (1.3612)	
[2022-01-21 14:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][110/1251]	eta 0:45:38 lr 0.000633	time 1.7649 (2.3999)	loss 3.5002 (3.5786)	grad_norm 1.2853 (1.3602)	
[2022-01-21 14:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][120/1251]	eta 0:44:50 lr 0.000633	time 2.9047 (2.3786)	loss 3.7552 (3.6103)	grad_norm 1.6667 (1.3647)	
[2022-01-21 14:13:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][130/1251]	eta 0:44:04 lr 0.000633	time 1.8957 (2.3589)	loss 3.6426 (3.6117)	grad_norm 1.3869 (1.3632)	
[2022-01-21 14:13:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][140/1251]	eta 0:43:13 lr 0.000633	time 2.2510 (2.3346)	loss 4.0379 (3.6127)	grad_norm 1.2850 (1.3629)	
[2022-01-21 14:14:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][150/1251]	eta 0:42:30 lr 0.000633	time 1.8103 (2.3163)	loss 3.9280 (3.6234)	grad_norm 1.4621 (1.3620)	
[2022-01-21 14:14:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][160/1251]	eta 0:41:58 lr 0.000632	time 2.9368 (2.3088)	loss 4.1302 (3.6141)	grad_norm 1.3985 (1.3642)	
[2022-01-21 14:14:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][170/1251]	eta 0:41:35 lr 0.000632	time 2.3316 (2.3082)	loss 3.3224 (3.6195)	grad_norm 1.5269 (1.3632)	
[2022-01-21 14:15:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][180/1251]	eta 0:41:04 lr 0.000632	time 2.1640 (2.3008)	loss 3.9855 (3.6059)	grad_norm 1.4759 (1.3610)	
[2022-01-21 14:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][190/1251]	eta 0:40:38 lr 0.000632	time 2.3724 (2.2988)	loss 3.6208 (3.6091)	grad_norm 1.3244 (1.3649)	
[2022-01-21 14:16:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][200/1251]	eta 0:40:19 lr 0.000632	time 3.6006 (2.3024)	loss 4.0929 (3.6059)	grad_norm 1.2404 (1.3672)	
[2022-01-21 14:16:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][210/1251]	eta 0:39:54 lr 0.000632	time 1.8596 (2.3001)	loss 3.9152 (3.6194)	grad_norm 1.2442 (1.3634)	
[2022-01-21 14:16:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][220/1251]	eta 0:39:27 lr 0.000632	time 1.9887 (2.2962)	loss 3.4758 (3.6183)	grad_norm 1.5707 (1.3620)	
[2022-01-21 14:17:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][230/1251]	eta 0:38:50 lr 0.000632	time 1.8673 (2.2830)	loss 4.2086 (3.6195)	grad_norm 1.4934 (1.3617)	
[2022-01-21 14:17:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][240/1251]	eta 0:38:23 lr 0.000632	time 2.8395 (2.2782)	loss 3.4963 (3.6219)	grad_norm 1.3129 (1.3610)	
[2022-01-21 14:17:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][250/1251]	eta 0:37:58 lr 0.000632	time 2.4612 (2.2759)	loss 3.2005 (3.6200)	grad_norm 1.3824 (1.3604)	
[2022-01-21 14:18:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][260/1251]	eta 0:37:30 lr 0.000632	time 1.8465 (2.2711)	loss 4.1837 (3.6303)	grad_norm 1.3564 (1.3599)	
[2022-01-21 14:18:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][270/1251]	eta 0:37:08 lr 0.000632	time 2.8476 (2.2714)	loss 3.9766 (3.6426)	grad_norm 1.2032 (1.3584)	
[2022-01-21 14:19:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][280/1251]	eta 0:36:42 lr 0.000632	time 2.4883 (2.2688)	loss 3.8498 (3.6411)	grad_norm 1.2592 (1.3538)	
[2022-01-21 14:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][290/1251]	eta 0:36:20 lr 0.000632	time 2.3827 (2.2685)	loss 3.6286 (3.6433)	grad_norm 1.3780 (1.3529)	
[2022-01-21 14:19:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][300/1251]	eta 0:35:52 lr 0.000632	time 1.7832 (2.2639)	loss 3.2186 (3.6457)	grad_norm 1.5038 (1.3546)	
[2022-01-21 14:20:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][310/1251]	eta 0:35:24 lr 0.000632	time 2.2666 (2.2579)	loss 2.8248 (3.6370)	grad_norm 1.3985 (1.3571)	
[2022-01-21 14:20:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][320/1251]	eta 0:34:56 lr 0.000632	time 1.5767 (2.2520)	loss 2.9682 (3.6326)	grad_norm 1.2903 (1.3564)	
[2022-01-21 14:20:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][330/1251]	eta 0:34:29 lr 0.000632	time 2.1815 (2.2469)	loss 4.5973 (3.6327)	grad_norm 1.2349 (1.3566)	
[2022-01-21 14:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][340/1251]	eta 0:34:07 lr 0.000632	time 2.2607 (2.2471)	loss 3.9496 (3.6343)	grad_norm 1.3540 (1.3577)	
[2022-01-21 14:21:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][350/1251]	eta 0:33:44 lr 0.000632	time 2.1112 (2.2473)	loss 2.7253 (3.6331)	grad_norm 1.2952 (1.3562)	
[2022-01-21 14:21:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][360/1251]	eta 0:33:27 lr 0.000632	time 2.1571 (2.2530)	loss 4.1721 (3.6250)	grad_norm 1.3845 (1.3592)	
[2022-01-21 14:22:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][370/1251]	eta 0:33:02 lr 0.000632	time 1.7946 (2.2500)	loss 3.3800 (3.6189)	grad_norm 1.2226 (1.3610)	
[2022-01-21 14:22:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][380/1251]	eta 0:32:36 lr 0.000632	time 1.9364 (2.2466)	loss 3.8350 (3.6205)	grad_norm 1.2600 (1.3608)	
[2022-01-21 14:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][390/1251]	eta 0:32:12 lr 0.000632	time 1.9241 (2.2440)	loss 3.1024 (3.6242)	grad_norm 1.8855 (1.3638)	
[2022-01-21 14:23:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][400/1251]	eta 0:31:49 lr 0.000632	time 2.1839 (2.2435)	loss 4.1136 (3.6250)	grad_norm 1.2475 (1.3651)	
[2022-01-21 14:23:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][410/1251]	eta 0:31:25 lr 0.000631	time 2.3396 (2.2415)	loss 2.8483 (3.6270)	grad_norm 1.4884 (1.3662)	
[2022-01-21 14:24:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][420/1251]	eta 0:30:58 lr 0.000631	time 2.0766 (2.2370)	loss 2.7896 (3.6236)	grad_norm 1.2122 (1.3667)	
[2022-01-21 14:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][430/1251]	eta 0:30:35 lr 0.000631	time 1.6140 (2.2353)	loss 3.4989 (3.6240)	grad_norm 1.5537 (1.3672)	
[2022-01-21 14:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][440/1251]	eta 0:30:11 lr 0.000631	time 1.7341 (2.2342)	loss 3.3808 (3.6159)	grad_norm 1.5416 (1.3675)	
[2022-01-21 14:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][450/1251]	eta 0:29:47 lr 0.000631	time 2.5406 (2.2316)	loss 3.1901 (3.6192)	grad_norm 1.3364 (1.3696)	
[2022-01-21 14:25:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][460/1251]	eta 0:29:23 lr 0.000631	time 1.8407 (2.2300)	loss 2.4389 (3.6159)	grad_norm 1.3380 (1.3683)	
[2022-01-21 14:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][470/1251]	eta 0:29:00 lr 0.000631	time 2.3291 (2.2280)	loss 2.5164 (3.6113)	grad_norm 1.2873 (1.3689)	
[2022-01-21 14:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][480/1251]	eta 0:28:37 lr 0.000631	time 1.8774 (2.2274)	loss 3.5258 (3.6088)	grad_norm 1.2384 (1.3674)	
[2022-01-21 14:26:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][490/1251]	eta 0:28:16 lr 0.000631	time 2.8343 (2.2288)	loss 3.9336 (3.6076)	grad_norm 1.1879 (1.3664)	
[2022-01-21 14:26:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][500/1251]	eta 0:27:53 lr 0.000631	time 2.3346 (2.2289)	loss 4.2584 (3.6071)	grad_norm 1.3930 (1.3676)	
[2022-01-21 14:27:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][510/1251]	eta 0:27:30 lr 0.000631	time 2.2014 (2.2280)	loss 3.8578 (3.6063)	grad_norm 1.3933 (1.3669)	
[2022-01-21 14:27:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][520/1251]	eta 0:27:08 lr 0.000631	time 2.1453 (2.2277)	loss 4.0503 (3.6137)	grad_norm 1.3064 (1.3676)	
[2022-01-21 14:28:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][530/1251]	eta 0:26:44 lr 0.000631	time 2.2898 (2.2259)	loss 3.6873 (3.6136)	grad_norm 1.2656 (1.3663)	
[2022-01-21 14:28:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][540/1251]	eta 0:26:21 lr 0.000631	time 2.2389 (2.2238)	loss 2.6662 (3.6116)	grad_norm 1.3670 (1.3666)	
[2022-01-21 14:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][550/1251]	eta 0:25:56 lr 0.000631	time 2.0890 (2.2205)	loss 3.5397 (3.6128)	grad_norm 2.0561 (1.3697)	
[2022-01-21 14:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][560/1251]	eta 0:25:34 lr 0.000631	time 3.0688 (2.2203)	loss 4.5632 (3.6177)	grad_norm 1.4102 (1.3693)	
[2022-01-21 14:29:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][570/1251]	eta 0:25:13 lr 0.000631	time 1.9610 (2.2225)	loss 3.0572 (3.6195)	grad_norm 1.2775 (1.3697)	
[2022-01-21 14:29:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][580/1251]	eta 0:24:50 lr 0.000631	time 2.2281 (2.2217)	loss 2.6891 (3.6164)	grad_norm 1.2557 (1.3681)	
[2022-01-21 14:30:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][590/1251]	eta 0:24:27 lr 0.000631	time 2.4404 (2.2205)	loss 3.9419 (3.6182)	grad_norm 1.8576 (1.3680)	
[2022-01-21 14:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][600/1251]	eta 0:24:04 lr 0.000631	time 3.5676 (2.2190)	loss 3.1910 (3.6197)	grad_norm 1.6357 (1.3682)	
[2022-01-21 14:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][610/1251]	eta 0:23:42 lr 0.000631	time 2.0127 (2.2200)	loss 3.9598 (3.6168)	grad_norm 1.4422 (1.3677)	
[2022-01-21 14:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][620/1251]	eta 0:23:18 lr 0.000631	time 1.6151 (2.2167)	loss 4.4986 (3.6229)	grad_norm 1.3130 (1.3671)	
[2022-01-21 14:31:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][630/1251]	eta 0:22:55 lr 0.000631	time 2.4989 (2.2151)	loss 3.6027 (3.6186)	grad_norm 1.5696 (1.3668)	
[2022-01-21 14:32:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][640/1251]	eta 0:22:33 lr 0.000631	time 3.0783 (2.2152)	loss 3.3215 (3.6186)	grad_norm 1.3324 (1.3666)	
[2022-01-21 14:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][650/1251]	eta 0:22:10 lr 0.000631	time 1.7346 (2.2132)	loss 2.7897 (3.6145)	grad_norm 1.4472 (1.3668)	
[2022-01-21 14:32:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][660/1251]	eta 0:21:48 lr 0.000630	time 1.8879 (2.2136)	loss 3.8057 (3.6117)	grad_norm 1.2429 (1.3662)	
[2022-01-21 14:33:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][670/1251]	eta 0:21:27 lr 0.000630	time 2.1051 (2.2152)	loss 2.8887 (3.6097)	grad_norm 1.4756 (1.3657)	
[2022-01-21 14:33:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][680/1251]	eta 0:21:05 lr 0.000630	time 3.3085 (2.2163)	loss 3.9329 (3.6124)	grad_norm 1.2134 (1.3662)	
[2022-01-21 14:33:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][690/1251]	eta 0:20:41 lr 0.000630	time 1.9175 (2.2135)	loss 2.5974 (3.6115)	grad_norm 1.2388 (1.3660)	
[2022-01-21 14:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][700/1251]	eta 0:20:19 lr 0.000630	time 1.8678 (2.2132)	loss 3.7668 (3.6099)	grad_norm 1.4270 (1.3647)	
[2022-01-21 14:34:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][710/1251]	eta 0:19:56 lr 0.000630	time 2.0202 (2.2121)	loss 4.0778 (3.6114)	grad_norm 1.2249 (1.3644)	
[2022-01-21 14:34:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][720/1251]	eta 0:19:35 lr 0.000630	time 3.8392 (2.2139)	loss 3.0126 (3.6104)	grad_norm 1.5745 (1.3634)	
[2022-01-21 14:35:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][730/1251]	eta 0:19:11 lr 0.000630	time 1.8586 (2.2107)	loss 2.7249 (3.6121)	grad_norm 1.5321 (1.3639)	
[2022-01-21 14:35:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][740/1251]	eta 0:18:48 lr 0.000630	time 2.1823 (2.2090)	loss 4.0918 (3.6129)	grad_norm 1.4588 (1.3640)	
[2022-01-21 14:36:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][750/1251]	eta 0:18:26 lr 0.000630	time 1.9390 (2.2082)	loss 2.9566 (3.6107)	grad_norm 1.2539 (1.3641)	
[2022-01-21 14:36:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][760/1251]	eta 0:18:04 lr 0.000630	time 2.5427 (2.2081)	loss 3.9866 (3.6081)	grad_norm 1.4244 (1.3652)	
[2022-01-21 14:36:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][770/1251]	eta 0:17:42 lr 0.000630	time 2.6799 (2.2090)	loss 3.8701 (3.6102)	grad_norm 1.2744 (1.3654)	
[2022-01-21 14:37:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][780/1251]	eta 0:17:20 lr 0.000630	time 2.5351 (2.2101)	loss 4.2405 (3.6124)	grad_norm 1.3463 (1.3657)	
[2022-01-21 14:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][790/1251]	eta 0:16:59 lr 0.000630	time 2.2530 (2.2119)	loss 3.4344 (3.6100)	grad_norm 1.1639 (1.3647)	
[2022-01-21 14:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][800/1251]	eta 0:16:37 lr 0.000630	time 2.0263 (2.2114)	loss 3.5304 (3.6107)	grad_norm 1.2890 (1.3639)	
[2022-01-21 14:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][810/1251]	eta 0:16:15 lr 0.000630	time 3.1357 (2.2123)	loss 3.2599 (3.6078)	grad_norm 1.2869 (1.3645)	
[2022-01-21 14:38:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][820/1251]	eta 0:15:52 lr 0.000630	time 2.2604 (2.2096)	loss 3.3646 (3.6103)	grad_norm 1.4131 (1.3646)	
[2022-01-21 14:38:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][830/1251]	eta 0:15:29 lr 0.000630	time 2.2335 (2.2069)	loss 3.1636 (3.6080)	grad_norm 1.5200 (1.3648)	
[2022-01-21 14:39:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][840/1251]	eta 0:15:05 lr 0.000630	time 1.9491 (2.2038)	loss 4.0409 (3.6065)	grad_norm 1.2346 (1.3651)	
[2022-01-21 14:39:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][850/1251]	eta 0:14:43 lr 0.000630	time 2.8741 (2.2035)	loss 4.3714 (3.6093)	grad_norm 1.1508 (1.3645)	
[2022-01-21 14:39:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][860/1251]	eta 0:14:21 lr 0.000630	time 2.7314 (2.2028)	loss 3.8571 (3.6106)	grad_norm 1.2172 (1.3639)	
[2022-01-21 14:40:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][870/1251]	eta 0:14:00 lr 0.000630	time 2.7391 (2.2048)	loss 3.0339 (3.6095)	grad_norm 1.4033 (1.3633)	
[2022-01-21 14:40:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][880/1251]	eta 0:13:39 lr 0.000630	time 2.2029 (2.2080)	loss 4.2005 (3.6093)	grad_norm 1.3036 (1.3650)	
[2022-01-21 14:41:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][890/1251]	eta 0:13:17 lr 0.000630	time 2.5461 (2.2095)	loss 3.7803 (3.6104)	grad_norm 1.6150 (1.3652)	
[2022-01-21 14:41:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][900/1251]	eta 0:12:54 lr 0.000630	time 1.6359 (2.2076)	loss 3.9187 (3.6148)	grad_norm 1.2371 (1.3652)	
[2022-01-21 14:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][910/1251]	eta 0:12:32 lr 0.000629	time 2.9161 (2.2076)	loss 2.8190 (3.6139)	grad_norm 1.3574 (1.3651)	
[2022-01-21 14:42:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][920/1251]	eta 0:12:10 lr 0.000629	time 1.8484 (2.2063)	loss 2.4930 (3.6127)	grad_norm 1.2640 (1.3651)	
[2022-01-21 14:42:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][930/1251]	eta 0:11:48 lr 0.000629	time 1.8071 (2.2058)	loss 4.1803 (3.6117)	grad_norm 1.4996 (1.3647)	
[2022-01-21 14:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][940/1251]	eta 0:11:25 lr 0.000629	time 1.6764 (2.2052)	loss 4.1694 (3.6126)	grad_norm 1.4546 (1.3652)	
[2022-01-21 14:43:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][950/1251]	eta 0:11:04 lr 0.000629	time 3.2246 (2.2079)	loss 3.2014 (3.6124)	grad_norm 1.2688 (1.3647)	
[2022-01-21 14:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][960/1251]	eta 0:10:41 lr 0.000629	time 1.8349 (2.2061)	loss 4.0729 (3.6102)	grad_norm 1.2967 (1.3638)	
[2022-01-21 14:44:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][970/1251]	eta 0:10:19 lr 0.000629	time 1.8950 (2.2044)	loss 2.5871 (3.6104)	grad_norm 1.3446 (1.3631)	
[2022-01-21 14:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][980/1251]	eta 0:09:56 lr 0.000629	time 1.8285 (2.2028)	loss 3.5673 (3.6116)	grad_norm 1.2197 (1.3629)	
[2022-01-21 14:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][990/1251]	eta 0:09:35 lr 0.000629	time 1.9783 (2.2034)	loss 4.0963 (3.6117)	grad_norm 1.5940 (1.3630)	
[2022-01-21 14:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1000/1251]	eta 0:09:13 lr 0.000629	time 2.5278 (2.2035)	loss 3.4044 (3.6143)	grad_norm 1.1882 (1.3623)	
[2022-01-21 14:45:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1010/1251]	eta 0:08:50 lr 0.000629	time 1.6623 (2.2025)	loss 3.7481 (3.6167)	grad_norm 1.3825 (1.3629)	
[2022-01-21 14:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1020/1251]	eta 0:08:28 lr 0.000629	time 2.3636 (2.2025)	loss 3.9413 (3.6173)	grad_norm 1.2264 (1.3635)	
[2022-01-21 14:46:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1030/1251]	eta 0:08:07 lr 0.000629	time 1.6902 (2.2038)	loss 3.1357 (3.6148)	grad_norm 1.3938 (1.3641)	
[2022-01-21 14:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1040/1251]	eta 0:07:45 lr 0.000629	time 3.2023 (2.2051)	loss 3.6432 (3.6140)	grad_norm 1.5734 (1.3645)	
[2022-01-21 14:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1050/1251]	eta 0:07:23 lr 0.000629	time 1.6129 (2.2053)	loss 3.6848 (3.6121)	grad_norm 1.3118 (1.3646)	
[2022-01-21 14:47:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1060/1251]	eta 0:07:00 lr 0.000629	time 1.6338 (2.2041)	loss 2.9203 (3.6115)	grad_norm 1.2574 (1.3642)	
[2022-01-21 14:47:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1070/1251]	eta 0:06:39 lr 0.000629	time 2.0933 (2.2044)	loss 3.7325 (3.6116)	grad_norm 1.2959 (1.3646)	
[2022-01-21 14:48:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1080/1251]	eta 0:06:17 lr 0.000629	time 3.6972 (2.2054)	loss 2.6395 (3.6139)	grad_norm 1.6480 (1.3657)	
[2022-01-21 14:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1090/1251]	eta 0:05:55 lr 0.000629	time 1.5723 (2.2055)	loss 3.9231 (3.6119)	grad_norm 1.3969 (1.3658)	
[2022-01-21 14:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1100/1251]	eta 0:05:32 lr 0.000629	time 1.8348 (2.2040)	loss 4.1265 (3.6125)	grad_norm 1.3615 (1.3658)	
[2022-01-21 14:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1110/1251]	eta 0:05:10 lr 0.000629	time 2.3001 (2.2038)	loss 4.3687 (3.6131)	grad_norm 1.2370 (1.3653)	
[2022-01-21 14:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1120/1251]	eta 0:04:48 lr 0.000629	time 3.5363 (2.2049)	loss 3.7381 (3.6160)	grad_norm 1.7526 (1.3661)	
[2022-01-21 14:49:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1130/1251]	eta 0:04:26 lr 0.000629	time 1.6057 (2.2056)	loss 3.9197 (3.6175)	grad_norm 1.3312 (1.3666)	
[2022-01-21 14:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1140/1251]	eta 0:04:04 lr 0.000629	time 1.8961 (2.2049)	loss 2.9067 (3.6170)	grad_norm 1.2287 (1.3670)	
[2022-01-21 14:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1150/1251]	eta 0:03:42 lr 0.000629	time 1.6166 (2.2032)	loss 4.0974 (3.6161)	grad_norm 1.5766 (1.3667)	
[2022-01-21 14:50:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1160/1251]	eta 0:03:20 lr 0.000628	time 2.1052 (2.2019)	loss 3.2608 (3.6164)	grad_norm 1.3672 (1.3666)	
[2022-01-21 14:51:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1170/1251]	eta 0:02:58 lr 0.000628	time 1.6312 (2.2004)	loss 3.7317 (3.6191)	grad_norm 1.4393 (1.3663)	
[2022-01-21 14:51:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1180/1251]	eta 0:02:36 lr 0.000628	time 2.1281 (2.1995)	loss 3.8404 (3.6196)	grad_norm 1.2619 (1.3657)	
[2022-01-21 14:52:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1190/1251]	eta 0:02:14 lr 0.000628	time 1.6131 (2.1989)	loss 3.8359 (3.6200)	grad_norm 1.2941 (1.3655)	
[2022-01-21 14:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1200/1251]	eta 0:01:52 lr 0.000628	time 1.6952 (2.2008)	loss 3.3823 (3.6198)	grad_norm 1.3565 (1.3648)	
[2022-01-21 14:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1210/1251]	eta 0:01:30 lr 0.000628	time 1.8736 (2.2011)	loss 4.2648 (3.6200)	grad_norm 1.2141 (1.3643)	
[2022-01-21 14:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1220/1251]	eta 0:01:08 lr 0.000628	time 2.8261 (2.2019)	loss 4.1656 (3.6203)	grad_norm 1.3343 (1.3636)	
[2022-01-21 14:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1230/1251]	eta 0:00:46 lr 0.000628	time 1.5427 (2.2014)	loss 4.1477 (3.6220)	grad_norm 1.3649 (1.3640)	
[2022-01-21 14:53:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1240/1251]	eta 0:00:24 lr 0.000628	time 1.7134 (2.1996)	loss 2.5492 (3.6228)	grad_norm 1.2571 (1.3636)	
[2022-01-21 14:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [125/300][1250/1251]	eta 0:00:02 lr 0.000628	time 1.2739 (2.1942)	loss 3.7022 (3.6234)	grad_norm 1.4770 (1.3635)	
[2022-01-21 14:54:08 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 125 training takes 0:45:45
[2022-01-21 14:54:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.625 (18.625)	Loss 1.0342 (1.0342)	Acc@1 76.465 (76.465)	Acc@5 92.871 (92.871)	
[2022-01-21 14:54:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.951 (3.304)	Loss 1.1137 (1.0609)	Acc@1 73.730 (74.929)	Acc@5 91.992 (93.084)	
[2022-01-21 14:54:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.598 (2.445)	Loss 1.0388 (1.0681)	Acc@1 75.488 (74.856)	Acc@5 93.359 (92.871)	
[2022-01-21 14:55:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.627 (2.230)	Loss 1.0894 (1.0686)	Acc@1 74.414 (75.120)	Acc@5 91.602 (92.751)	
[2022-01-21 14:55:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.342 (2.172)	Loss 1.0739 (1.0704)	Acc@1 74.902 (74.955)	Acc@5 92.871 (92.714)	
[2022-01-21 14:55:44 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.982 Acc@5 92.726
[2022-01-21 14:55:44 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.0%
[2022-01-21 14:55:44 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 74.98%
[2022-01-21 14:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][0/1251]	eta 7:26:50 lr 0.000628	time 21.4310 (21.4310)	loss 3.9685 (3.9685)	grad_norm 1.5053 (1.5053)	
[2022-01-21 14:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][10/1251]	eta 1:25:41 lr 0.000628	time 1.4024 (4.1432)	loss 3.4631 (3.7172)	grad_norm 1.3460 (1.3484)	
[2022-01-21 14:56:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][20/1251]	eta 1:08:20 lr 0.000628	time 2.0883 (3.3313)	loss 4.4613 (3.7062)	grad_norm 1.5673 (1.3884)	
[2022-01-21 14:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][30/1251]	eta 0:59:46 lr 0.000628	time 1.5062 (2.9372)	loss 4.3585 (3.7059)	grad_norm 1.2746 (1.3821)	
[2022-01-21 14:57:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][40/1251]	eta 0:57:06 lr 0.000628	time 3.9067 (2.8291)	loss 4.1028 (3.7081)	grad_norm 1.2984 (1.3793)	
[2022-01-21 14:58:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][50/1251]	eta 0:54:16 lr 0.000628	time 1.4867 (2.7116)	loss 3.4439 (3.7057)	grad_norm 1.5685 (1.3733)	
[2022-01-21 14:58:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][60/1251]	eta 0:51:20 lr 0.000628	time 1.9715 (2.5866)	loss 2.9264 (3.6889)	grad_norm 1.3272 (1.3622)	
[2022-01-21 14:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][70/1251]	eta 0:49:19 lr 0.000628	time 1.9276 (2.5055)	loss 3.2627 (3.6963)	grad_norm 1.4163 (1.3677)	
[2022-01-21 14:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][80/1251]	eta 0:48:14 lr 0.000628	time 3.1238 (2.4716)	loss 3.7951 (3.6608)	grad_norm 1.2950 (1.3638)	
[2022-01-21 14:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][90/1251]	eta 0:47:42 lr 0.000628	time 2.8411 (2.4660)	loss 2.7618 (3.6541)	grad_norm 1.3583 (1.3685)	
[2022-01-21 14:59:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][100/1251]	eta 0:46:53 lr 0.000628	time 1.8504 (2.4445)	loss 4.1503 (3.6672)	grad_norm 1.3483 (1.3705)	
[2022-01-21 15:00:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][110/1251]	eta 0:46:08 lr 0.000628	time 2.6159 (2.4263)	loss 2.6260 (3.6600)	grad_norm 1.2640 (1.3587)	
[2022-01-21 15:00:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][120/1251]	eta 0:45:26 lr 0.000628	time 2.2779 (2.4103)	loss 3.6232 (3.6497)	grad_norm 1.4495 (1.3570)	
[2022-01-21 15:00:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][130/1251]	eta 0:44:16 lr 0.000628	time 1.9482 (2.3698)	loss 4.3850 (3.6474)	grad_norm 1.4423 (1.3569)	
[2022-01-21 15:01:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][140/1251]	eta 0:43:24 lr 0.000628	time 1.8838 (2.3446)	loss 3.0990 (3.6396)	grad_norm 1.5493 (1.3592)	
[2022-01-21 15:01:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][150/1251]	eta 0:43:14 lr 0.000627	time 3.6650 (2.3563)	loss 3.0774 (3.6338)	grad_norm 1.5287 (1.3578)	
[2022-01-21 15:02:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][160/1251]	eta 0:42:47 lr 0.000627	time 1.9646 (2.3534)	loss 4.0479 (3.6382)	grad_norm 1.2667 (1.3566)	
[2022-01-21 15:02:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][170/1251]	eta 0:42:19 lr 0.000627	time 2.4841 (2.3495)	loss 4.1330 (3.6420)	grad_norm 1.7307 (1.3558)	
[2022-01-21 15:02:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][180/1251]	eta 0:41:40 lr 0.000627	time 1.6193 (2.3351)	loss 3.8977 (3.6316)	grad_norm 1.3082 (1.3563)	
[2022-01-21 15:03:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][190/1251]	eta 0:40:58 lr 0.000627	time 2.5377 (2.3167)	loss 4.0703 (3.6314)	grad_norm 1.5239 (1.3621)	
[2022-01-21 15:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][200/1251]	eta 0:40:16 lr 0.000627	time 1.7595 (2.2993)	loss 4.6070 (3.6373)	grad_norm 1.2702 (1.3617)	
[2022-01-21 15:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][210/1251]	eta 0:39:39 lr 0.000627	time 2.2304 (2.2860)	loss 3.1219 (3.6348)	grad_norm 1.3435 (1.3612)	
[2022-01-21 15:04:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][220/1251]	eta 0:39:07 lr 0.000627	time 2.0806 (2.2766)	loss 3.7906 (3.6440)	grad_norm 1.2611 (1.3639)	
[2022-01-21 15:04:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][230/1251]	eta 0:38:44 lr 0.000627	time 1.8929 (2.2763)	loss 2.6890 (3.6335)	grad_norm 1.8220 (1.3647)	
[2022-01-21 15:04:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][240/1251]	eta 0:38:15 lr 0.000627	time 1.5894 (2.2706)	loss 4.1262 (3.6345)	grad_norm 1.2111 (1.3649)	
[2022-01-21 15:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][250/1251]	eta 0:37:56 lr 0.000627	time 2.1028 (2.2747)	loss 3.7617 (3.6394)	grad_norm 1.3252 (1.3664)	
[2022-01-21 15:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][260/1251]	eta 0:37:32 lr 0.000627	time 2.1579 (2.2733)	loss 3.9508 (3.6381)	grad_norm 1.4707 (1.3691)	
[2022-01-21 15:06:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][270/1251]	eta 0:37:11 lr 0.000627	time 1.8749 (2.2742)	loss 3.4786 (3.6430)	grad_norm 1.1957 (1.3702)	
[2022-01-21 15:06:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][280/1251]	eta 0:36:55 lr 0.000627	time 2.6403 (2.2812)	loss 4.1212 (3.6569)	grad_norm 1.3499 (1.3692)	
[2022-01-21 15:06:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][290/1251]	eta 0:36:31 lr 0.000627	time 1.9000 (2.2804)	loss 4.2070 (3.6634)	grad_norm 1.3837 (1.3728)	
[2022-01-21 15:07:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][300/1251]	eta 0:35:59 lr 0.000627	time 1.7152 (2.2711)	loss 2.8222 (3.6515)	grad_norm 1.2244 (1.3704)	
[2022-01-21 15:07:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][310/1251]	eta 0:35:26 lr 0.000627	time 1.9687 (2.2603)	loss 4.1619 (3.6484)	grad_norm 1.3844 (1.3687)	
[2022-01-21 15:07:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][320/1251]	eta 0:35:01 lr 0.000627	time 2.2248 (2.2567)	loss 3.8277 (3.6505)	grad_norm 1.5050 (1.3672)	
[2022-01-21 15:08:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][330/1251]	eta 0:34:37 lr 0.000627	time 2.5096 (2.2559)	loss 4.0759 (3.6383)	grad_norm 1.4387 (1.3652)	
[2022-01-21 15:08:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][340/1251]	eta 0:34:15 lr 0.000627	time 1.9135 (2.2560)	loss 3.3245 (3.6395)	grad_norm 1.2236 (1.3642)	
[2022-01-21 15:08:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][350/1251]	eta 0:33:53 lr 0.000627	time 2.0177 (2.2564)	loss 4.5437 (3.6411)	grad_norm 1.4471 (1.3637)	
[2022-01-21 15:09:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][360/1251]	eta 0:33:27 lr 0.000627	time 1.8948 (2.2532)	loss 4.4724 (3.6458)	grad_norm 1.3852 (1.3647)	
[2022-01-21 15:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][370/1251]	eta 0:33:03 lr 0.000627	time 2.1623 (2.2514)	loss 3.7530 (3.6450)	grad_norm 1.4448 (1.3686)	
[2022-01-21 15:10:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][380/1251]	eta 0:32:36 lr 0.000627	time 2.2664 (2.2468)	loss 3.1893 (3.6439)	grad_norm 1.3795 (1.3694)	
[2022-01-21 15:10:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][390/1251]	eta 0:32:13 lr 0.000627	time 2.2309 (2.2458)	loss 3.7727 (3.6486)	grad_norm 1.3285 (1.3708)	
[2022-01-21 15:10:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][400/1251]	eta 0:31:49 lr 0.000626	time 2.0958 (2.2434)	loss 3.6350 (3.6477)	grad_norm 1.1951 (1.3745)	
[2022-01-21 15:11:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][410/1251]	eta 0:31:25 lr 0.000626	time 1.9606 (2.2424)	loss 3.5578 (3.6476)	grad_norm 1.4290 (1.3752)	
[2022-01-21 15:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][420/1251]	eta 0:31:00 lr 0.000626	time 2.8163 (2.2388)	loss 4.1643 (3.6503)	grad_norm 1.2341 (1.3748)	
[2022-01-21 15:11:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][430/1251]	eta 0:30:37 lr 0.000626	time 1.9866 (2.2380)	loss 3.0685 (3.6482)	grad_norm 1.4792 (1.3739)	
[2022-01-21 15:12:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][440/1251]	eta 0:30:16 lr 0.000626	time 1.8370 (2.2396)	loss 3.9112 (3.6479)	grad_norm 1.3116 (1.3743)	
[2022-01-21 15:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][450/1251]	eta 0:29:54 lr 0.000626	time 2.4572 (2.2408)	loss 4.3191 (3.6460)	grad_norm 1.2997 (1.3737)	
[2022-01-21 15:12:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][460/1251]	eta 0:29:29 lr 0.000626	time 1.6140 (2.2370)	loss 4.2944 (3.6414)	grad_norm 1.4471 (1.3728)	
[2022-01-21 15:13:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][470/1251]	eta 0:29:04 lr 0.000626	time 1.6450 (2.2335)	loss 3.3018 (3.6481)	grad_norm 1.3586 (1.3724)	
[2022-01-21 15:13:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][480/1251]	eta 0:28:41 lr 0.000626	time 2.2787 (2.2324)	loss 4.3961 (3.6481)	grad_norm 1.6007 (1.3731)	
[2022-01-21 15:14:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][490/1251]	eta 0:28:21 lr 0.000626	time 3.0326 (2.2361)	loss 4.0156 (3.6479)	grad_norm 1.3591 (1.3737)	
[2022-01-21 15:14:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][500/1251]	eta 0:28:02 lr 0.000626	time 2.1155 (2.2408)	loss 3.0977 (3.6438)	grad_norm 1.2151 (1.3736)	
[2022-01-21 15:14:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][510/1251]	eta 0:27:41 lr 0.000626	time 2.0087 (2.2429)	loss 3.3336 (3.6388)	grad_norm 1.2804 (1.3728)	
[2022-01-21 15:15:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][520/1251]	eta 0:27:19 lr 0.000626	time 2.3885 (2.2432)	loss 4.0937 (3.6403)	grad_norm 1.3543 (1.3718)	
[2022-01-21 15:15:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][530/1251]	eta 0:26:55 lr 0.000626	time 2.2358 (2.2407)	loss 4.4039 (3.6366)	grad_norm 1.3893 (1.3714)	
[2022-01-21 15:15:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][540/1251]	eta 0:26:28 lr 0.000626	time 1.9771 (2.2341)	loss 3.9369 (3.6385)	grad_norm 1.1583 (1.3701)	
[2022-01-21 15:16:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][550/1251]	eta 0:26:03 lr 0.000626	time 2.6332 (2.2301)	loss 3.8939 (3.6379)	grad_norm 1.1595 (1.3691)	
[2022-01-21 15:16:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][560/1251]	eta 0:25:41 lr 0.000626	time 2.7802 (2.2302)	loss 2.6233 (3.6349)	grad_norm 1.3058 (1.3702)	
[2022-01-21 15:16:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][570/1251]	eta 0:25:18 lr 0.000626	time 2.7098 (2.2296)	loss 3.9210 (3.6321)	grad_norm 1.5984 (1.3712)	
[2022-01-21 15:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][580/1251]	eta 0:24:55 lr 0.000626	time 1.9179 (2.2294)	loss 4.2617 (3.6323)	grad_norm 1.4510 (1.3714)	
[2022-01-21 15:17:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][590/1251]	eta 0:24:34 lr 0.000626	time 2.8794 (2.2300)	loss 4.2612 (3.6375)	grad_norm 1.3616 (1.3713)	
[2022-01-21 15:18:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][600/1251]	eta 0:24:11 lr 0.000626	time 2.2711 (2.2296)	loss 3.2951 (3.6389)	grad_norm 1.1805 (1.3720)	
[2022-01-21 15:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][610/1251]	eta 0:23:48 lr 0.000626	time 2.2342 (2.2289)	loss 3.9279 (3.6400)	grad_norm 1.3190 (1.3721)	
[2022-01-21 15:18:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][620/1251]	eta 0:23:25 lr 0.000626	time 1.9320 (2.2282)	loss 2.9903 (3.6401)	grad_norm 1.5073 (1.3727)	
[2022-01-21 15:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][630/1251]	eta 0:23:03 lr 0.000626	time 2.6729 (2.2286)	loss 3.9273 (3.6404)	grad_norm 1.9370 (1.3725)	
[2022-01-21 15:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][640/1251]	eta 0:22:42 lr 0.000626	time 2.4329 (2.2292)	loss 3.9733 (3.6400)	grad_norm 1.3056 (1.3715)	
[2022-01-21 15:19:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][650/1251]	eta 0:22:17 lr 0.000625	time 1.6543 (2.2257)	loss 3.7948 (3.6408)	grad_norm 1.4327 (1.3719)	
[2022-01-21 15:20:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][660/1251]	eta 0:21:54 lr 0.000625	time 1.9539 (2.2236)	loss 3.6736 (3.6354)	grad_norm 1.3008 (1.3734)	
[2022-01-21 15:20:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][670/1251]	eta 0:21:31 lr 0.000625	time 2.8843 (2.2224)	loss 3.9459 (3.6310)	grad_norm 1.3189 (1.3746)	
[2022-01-21 15:20:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][680/1251]	eta 0:21:07 lr 0.000625	time 1.6233 (2.2200)	loss 3.8358 (3.6321)	grad_norm 1.4830 (1.3768)	
[2022-01-21 15:21:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][690/1251]	eta 0:20:44 lr 0.000625	time 2.1794 (2.2187)	loss 3.5222 (3.6357)	grad_norm 1.2372 (1.3759)	
[2022-01-21 15:21:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][700/1251]	eta 0:20:21 lr 0.000625	time 2.2167 (2.2174)	loss 3.5650 (3.6414)	grad_norm 1.3794 (1.3760)	
[2022-01-21 15:22:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][710/1251]	eta 0:19:59 lr 0.000625	time 2.3225 (2.2173)	loss 3.2764 (3.6396)	grad_norm 1.3412 (1.3768)	
[2022-01-21 15:22:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][720/1251]	eta 0:19:38 lr 0.000625	time 2.1450 (2.2195)	loss 3.6673 (3.6386)	grad_norm 1.2402 (1.3757)	
[2022-01-21 15:22:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][730/1251]	eta 0:19:16 lr 0.000625	time 1.5793 (2.2195)	loss 3.1217 (3.6369)	grad_norm 1.3223 (1.3775)	
[2022-01-21 15:23:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][740/1251]	eta 0:18:54 lr 0.000625	time 1.9681 (2.2198)	loss 4.0376 (3.6356)	grad_norm 1.5043 (1.3769)	
[2022-01-21 15:23:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][750/1251]	eta 0:18:31 lr 0.000625	time 2.4016 (2.2193)	loss 3.3365 (3.6356)	grad_norm 1.3594 (1.3772)	
[2022-01-21 15:23:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][760/1251]	eta 0:18:09 lr 0.000625	time 2.2235 (2.2179)	loss 2.4967 (3.6323)	grad_norm 1.2991 (1.3773)	
[2022-01-21 15:24:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][770/1251]	eta 0:17:46 lr 0.000625	time 2.4219 (2.2169)	loss 4.2839 (3.6359)	grad_norm 1.2305 (1.3763)	
[2022-01-21 15:24:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][780/1251]	eta 0:17:24 lr 0.000625	time 2.4500 (2.2167)	loss 2.8339 (3.6353)	grad_norm 1.3210 (1.3762)	
[2022-01-21 15:24:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][790/1251]	eta 0:17:01 lr 0.000625	time 2.2066 (2.2151)	loss 2.5462 (3.6350)	grad_norm 1.2856 (1.3753)	
[2022-01-21 15:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][800/1251]	eta 0:16:37 lr 0.000625	time 1.9736 (2.2127)	loss 3.8812 (3.6358)	grad_norm 1.2656 (1.3755)	
[2022-01-21 15:25:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][810/1251]	eta 0:16:16 lr 0.000625	time 2.9149 (2.2138)	loss 3.9765 (3.6377)	grad_norm 1.3984 (1.3759)	
[2022-01-21 15:26:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][820/1251]	eta 0:15:54 lr 0.000625	time 2.5092 (2.2138)	loss 3.2158 (3.6374)	grad_norm 1.7247 (1.3763)	
[2022-01-21 15:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][830/1251]	eta 0:15:32 lr 0.000625	time 1.7931 (2.2139)	loss 4.0213 (3.6389)	grad_norm 1.2378 (1.3762)	
[2022-01-21 15:26:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][840/1251]	eta 0:15:09 lr 0.000625	time 1.9032 (2.2133)	loss 3.7449 (3.6405)	grad_norm 1.1756 (1.3755)	
[2022-01-21 15:27:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][850/1251]	eta 0:14:46 lr 0.000625	time 2.2447 (2.2118)	loss 3.5279 (3.6432)	grad_norm 1.2105 (1.3747)	
[2022-01-21 15:27:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][860/1251]	eta 0:14:25 lr 0.000625	time 1.9218 (2.2130)	loss 4.3686 (3.6409)	grad_norm 1.2941 (1.3753)	
[2022-01-21 15:27:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][870/1251]	eta 0:14:03 lr 0.000625	time 1.7875 (2.2130)	loss 3.6426 (3.6428)	grad_norm 1.6085 (1.3761)	
[2022-01-21 15:28:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][880/1251]	eta 0:13:40 lr 0.000625	time 1.5637 (2.2126)	loss 3.4175 (3.6453)	grad_norm 1.3799 (1.3759)	
[2022-01-21 15:28:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][890/1251]	eta 0:13:18 lr 0.000625	time 1.5798 (2.2112)	loss 2.3763 (3.6448)	grad_norm 1.2122 (1.3747)	
[2022-01-21 15:28:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][900/1251]	eta 0:12:55 lr 0.000624	time 1.8717 (2.2106)	loss 3.8950 (3.6401)	grad_norm 1.1277 (1.3733)	
[2022-01-21 15:29:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][910/1251]	eta 0:12:33 lr 0.000624	time 1.9245 (2.2096)	loss 4.2404 (3.6371)	grad_norm 1.4389 (1.3720)	
[2022-01-21 15:29:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][920/1251]	eta 0:12:10 lr 0.000624	time 2.0408 (2.2083)	loss 3.2568 (3.6358)	grad_norm 1.3653 (1.3712)	
[2022-01-21 15:30:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][930/1251]	eta 0:11:48 lr 0.000624	time 2.0600 (2.2083)	loss 3.5112 (3.6351)	grad_norm 1.3261 (1.3702)	
[2022-01-21 15:30:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][940/1251]	eta 0:11:26 lr 0.000624	time 2.3173 (2.2080)	loss 3.7002 (3.6351)	grad_norm 1.3072 (1.3698)	
[2022-01-21 15:30:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][950/1251]	eta 0:11:05 lr 0.000624	time 2.4953 (2.2093)	loss 2.5277 (3.6328)	grad_norm 1.3787 (1.3703)	
[2022-01-21 15:31:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][960/1251]	eta 0:10:42 lr 0.000624	time 2.1553 (2.2087)	loss 3.6833 (3.6318)	grad_norm 1.2316 (1.3713)	
[2022-01-21 15:31:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][970/1251]	eta 0:10:20 lr 0.000624	time 2.1575 (2.2099)	loss 4.1528 (3.6330)	grad_norm 1.2705 (1.3711)	
[2022-01-21 15:31:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][980/1251]	eta 0:09:58 lr 0.000624	time 1.8862 (2.2096)	loss 3.0781 (3.6316)	grad_norm 1.3149 (1.3705)	
[2022-01-21 15:32:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][990/1251]	eta 0:09:37 lr 0.000624	time 2.1993 (2.2114)	loss 4.0175 (3.6335)	grad_norm 1.3946 (1.3701)	
[2022-01-21 15:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1000/1251]	eta 0:09:14 lr 0.000624	time 1.6065 (2.2091)	loss 3.7852 (3.6340)	grad_norm 1.3944 (1.3697)	
[2022-01-21 15:32:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1010/1251]	eta 0:08:52 lr 0.000624	time 2.2216 (2.2079)	loss 3.5365 (3.6349)	grad_norm 1.2748 (1.3703)	
[2022-01-21 15:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1020/1251]	eta 0:08:29 lr 0.000624	time 1.9865 (2.2072)	loss 3.9972 (3.6369)	grad_norm 1.2049 (1.3701)	
[2022-01-21 15:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1030/1251]	eta 0:08:07 lr 0.000624	time 2.2559 (2.2080)	loss 3.6376 (3.6381)	grad_norm 1.5149 (1.3721)	
[2022-01-21 15:34:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1040/1251]	eta 0:07:45 lr 0.000624	time 1.8189 (2.2076)	loss 3.6550 (3.6352)	grad_norm 1.4150 (1.3719)	
[2022-01-21 15:34:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1050/1251]	eta 0:07:23 lr 0.000624	time 2.2113 (2.2074)	loss 3.3461 (3.6347)	grad_norm 1.2791 (1.3713)	
[2022-01-21 15:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1060/1251]	eta 0:07:01 lr 0.000624	time 1.9142 (2.2064)	loss 3.8073 (3.6348)	grad_norm 1.4282 (1.3711)	
[2022-01-21 15:35:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1070/1251]	eta 0:06:39 lr 0.000624	time 1.6425 (2.2050)	loss 4.2500 (3.6347)	grad_norm 1.3973 (1.3702)	
[2022-01-21 15:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1080/1251]	eta 0:06:16 lr 0.000624	time 2.1882 (2.2040)	loss 3.2068 (3.6352)	grad_norm 1.6682 (1.3702)	
[2022-01-21 15:35:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1090/1251]	eta 0:05:54 lr 0.000624	time 1.7985 (2.2027)	loss 3.8439 (3.6337)	grad_norm 1.3389 (1.3695)	
[2022-01-21 15:36:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1100/1251]	eta 0:05:32 lr 0.000624	time 2.1745 (2.2013)	loss 3.1249 (3.6331)	grad_norm 1.5262 (1.3702)	
[2022-01-21 15:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1110/1251]	eta 0:05:10 lr 0.000624	time 1.4743 (2.2005)	loss 4.1870 (3.6337)	grad_norm 1.3320 (1.3712)	
[2022-01-21 15:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1120/1251]	eta 0:04:48 lr 0.000624	time 2.5339 (2.2006)	loss 4.1205 (3.6330)	grad_norm 1.2413 (1.3712)	
[2022-01-21 15:37:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1130/1251]	eta 0:04:26 lr 0.000624	time 1.5524 (2.2014)	loss 4.3333 (3.6344)	grad_norm 1.2472 (1.3712)	
[2022-01-21 15:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1140/1251]	eta 0:04:04 lr 0.000624	time 2.7645 (2.2020)	loss 3.5223 (3.6341)	grad_norm 1.1835 (1.3707)	
[2022-01-21 15:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1150/1251]	eta 0:03:42 lr 0.000623	time 1.6904 (2.2019)	loss 3.5655 (3.6341)	grad_norm 1.5654 (1.3706)	
[2022-01-21 15:38:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1160/1251]	eta 0:03:20 lr 0.000623	time 2.3619 (2.2030)	loss 3.7033 (3.6321)	grad_norm 1.2858 (1.3700)	
[2022-01-21 15:38:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1170/1251]	eta 0:02:58 lr 0.000623	time 2.4780 (2.2032)	loss 4.4980 (3.6317)	grad_norm 1.2889 (1.3692)	
[2022-01-21 15:39:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1180/1251]	eta 0:02:36 lr 0.000623	time 2.3593 (2.2031)	loss 3.6920 (3.6303)	grad_norm 1.3736 (1.3691)	
[2022-01-21 15:39:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1190/1251]	eta 0:02:14 lr 0.000623	time 1.7327 (2.2024)	loss 3.7818 (3.6301)	grad_norm 1.3278 (1.3687)	
[2022-01-21 15:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1200/1251]	eta 0:01:52 lr 0.000623	time 2.8475 (2.2018)	loss 4.0991 (3.6288)	grad_norm 1.2834 (1.3688)	
[2022-01-21 15:40:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1210/1251]	eta 0:01:30 lr 0.000623	time 2.1671 (2.2020)	loss 4.0039 (3.6308)	grad_norm 1.3792 (1.3687)	
[2022-01-21 15:40:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1220/1251]	eta 0:01:08 lr 0.000623	time 1.6042 (2.2008)	loss 4.1104 (3.6320)	grad_norm 1.3745 (1.3684)	
[2022-01-21 15:40:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1230/1251]	eta 0:00:46 lr 0.000623	time 1.8619 (2.2004)	loss 3.8842 (3.6330)	grad_norm 1.2899 (1.3677)	
[2022-01-21 15:41:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1240/1251]	eta 0:00:24 lr 0.000623	time 2.0128 (2.1997)	loss 3.1247 (3.6336)	grad_norm 1.7836 (1.3693)	
[2022-01-21 15:41:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [126/300][1250/1251]	eta 0:00:02 lr 0.000623	time 1.1569 (2.1940)	loss 4.2848 (3.6354)	grad_norm 1.3423 (1.3686)	
[2022-01-21 15:41:29 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 126 training takes 0:45:45
[2022-01-21 15:41:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.574 (18.574)	Loss 1.1716 (1.1716)	Acc@1 73.047 (73.047)	Acc@5 91.992 (91.992)	
[2022-01-21 15:42:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.581 (3.399)	Loss 1.0162 (1.0686)	Acc@1 74.512 (74.911)	Acc@5 94.238 (92.738)	
[2022-01-21 15:42:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.953 (2.532)	Loss 1.0942 (1.0634)	Acc@1 74.902 (74.926)	Acc@5 91.895 (92.787)	
[2022-01-21 15:42:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.580 (2.231)	Loss 1.0333 (1.0548)	Acc@1 76.367 (75.079)	Acc@5 93.457 (92.852)	
[2022-01-21 15:42:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.463 (2.154)	Loss 1.0363 (1.0555)	Acc@1 76.172 (75.143)	Acc@5 92.676 (92.838)	
[2022-01-21 15:43:04 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.068 Acc@5 92.816
[2022-01-21 15:43:04 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.1%
[2022-01-21 15:43:04 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.07%
[2022-01-21 15:43:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][0/1251]	eta 7:34:10 lr 0.000623	time 21.7829 (21.7829)	loss 4.3345 (4.3345)	grad_norm 1.3434 (1.3434)	
[2022-01-21 15:43:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][10/1251]	eta 1:24:02 lr 0.000623	time 1.4471 (4.0631)	loss 4.1204 (3.8208)	grad_norm 1.3903 (1.3388)	
[2022-01-21 15:44:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][20/1251]	eta 1:04:14 lr 0.000623	time 1.5443 (3.1311)	loss 3.9614 (3.6942)	grad_norm 1.3732 (1.3173)	
[2022-01-21 15:44:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][30/1251]	eta 0:59:14 lr 0.000623	time 1.6132 (2.9111)	loss 4.3887 (3.6418)	grad_norm 1.4152 (1.3270)	
[2022-01-21 15:44:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][40/1251]	eta 0:56:07 lr 0.000623	time 3.5598 (2.7804)	loss 3.1610 (3.6565)	grad_norm 1.3061 (1.3655)	
[2022-01-21 15:45:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][50/1251]	eta 0:53:34 lr 0.000623	time 2.4818 (2.6767)	loss 2.4234 (3.6115)	grad_norm 1.2942 (1.3558)	
[2022-01-21 15:45:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][60/1251]	eta 0:51:03 lr 0.000623	time 2.3948 (2.5719)	loss 3.3940 (3.6159)	grad_norm 1.2675 (1.3453)	
[2022-01-21 15:46:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][70/1251]	eta 0:49:42 lr 0.000623	time 2.5153 (2.5258)	loss 2.4368 (3.6011)	grad_norm 1.3707 (1.3394)	
[2022-01-21 15:46:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][80/1251]	eta 0:48:34 lr 0.000623	time 3.1786 (2.4888)	loss 4.0354 (3.5718)	grad_norm 1.3256 (1.3641)	
[2022-01-21 15:46:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][90/1251]	eta 0:47:16 lr 0.000623	time 2.1633 (2.4435)	loss 3.7830 (3.5679)	grad_norm 1.1310 (1.3760)	
[2022-01-21 15:47:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][100/1251]	eta 0:46:14 lr 0.000623	time 2.0337 (2.4101)	loss 3.5567 (3.5776)	grad_norm 1.4498 (1.3740)	
[2022-01-21 15:47:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][110/1251]	eta 0:45:27 lr 0.000623	time 2.3585 (2.3904)	loss 3.2579 (3.5824)	grad_norm 1.3518 (1.3751)	
[2022-01-21 15:47:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][120/1251]	eta 0:44:43 lr 0.000623	time 3.0184 (2.3731)	loss 4.0652 (3.5897)	grad_norm 1.4527 (1.3778)	
[2022-01-21 15:48:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][130/1251]	eta 0:44:07 lr 0.000623	time 2.5331 (2.3620)	loss 4.0587 (3.5748)	grad_norm 1.4506 (1.3778)	
[2022-01-21 15:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][140/1251]	eta 0:43:27 lr 0.000623	time 2.4632 (2.3471)	loss 4.2367 (3.5744)	grad_norm 1.3086 (1.3725)	
[2022-01-21 15:48:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][150/1251]	eta 0:42:39 lr 0.000622	time 1.8619 (2.3246)	loss 3.4257 (3.5851)	grad_norm 1.3785 (1.3723)	
[2022-01-21 15:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][160/1251]	eta 0:42:05 lr 0.000622	time 2.3680 (2.3153)	loss 2.3746 (3.5767)	grad_norm 1.1653 (1.3751)	
[2022-01-21 15:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][170/1251]	eta 0:41:37 lr 0.000622	time 2.0332 (2.3106)	loss 3.6560 (3.5906)	grad_norm 1.2953 (1.3727)	
[2022-01-21 15:50:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][180/1251]	eta 0:41:12 lr 0.000622	time 2.4177 (2.3083)	loss 3.5947 (3.6070)	grad_norm 1.4383 (1.3708)	
[2022-01-21 15:50:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][190/1251]	eta 0:40:47 lr 0.000622	time 1.8082 (2.3070)	loss 4.4698 (3.6277)	grad_norm 1.4310 (1.3683)	
[2022-01-21 15:50:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][200/1251]	eta 0:40:18 lr 0.000622	time 2.8205 (2.3010)	loss 3.9838 (3.6330)	grad_norm 1.2991 (1.3652)	
[2022-01-21 15:51:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][210/1251]	eta 0:39:41 lr 0.000622	time 1.9752 (2.2874)	loss 3.8433 (3.6159)	grad_norm 1.3075 (1.3617)	
[2022-01-21 15:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][220/1251]	eta 0:39:06 lr 0.000622	time 1.8618 (2.2756)	loss 3.8978 (3.6262)	grad_norm 1.1933 (1.3633)	
[2022-01-21 15:51:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][230/1251]	eta 0:38:38 lr 0.000622	time 1.8363 (2.2707)	loss 3.6581 (3.6225)	grad_norm 1.7803 (1.3677)	
[2022-01-21 15:52:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][240/1251]	eta 0:38:21 lr 0.000622	time 3.0973 (2.2767)	loss 3.8358 (3.6271)	grad_norm 1.2658 (1.3695)	
[2022-01-21 15:52:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][250/1251]	eta 0:37:57 lr 0.000622	time 2.5446 (2.2753)	loss 4.4450 (3.6347)	grad_norm 1.3960 (1.3681)	
[2022-01-21 15:52:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][260/1251]	eta 0:37:36 lr 0.000622	time 2.7295 (2.2768)	loss 3.3933 (3.6315)	grad_norm 1.3379 (1.3701)	
[2022-01-21 15:53:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][270/1251]	eta 0:37:13 lr 0.000622	time 1.8593 (2.2770)	loss 4.0851 (3.6295)	grad_norm 1.5023 (1.3700)	
[2022-01-21 15:53:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][280/1251]	eta 0:36:39 lr 0.000622	time 1.6754 (2.2657)	loss 3.8085 (3.6252)	grad_norm 1.2734 (1.3672)	
[2022-01-21 15:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][290/1251]	eta 0:36:03 lr 0.000622	time 1.9199 (2.2517)	loss 3.1570 (3.6237)	grad_norm 1.4707 (1.3672)	
[2022-01-21 15:54:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][300/1251]	eta 0:35:36 lr 0.000622	time 2.4417 (2.2465)	loss 3.8482 (3.6151)	grad_norm 1.3037 (1.3663)	
[2022-01-21 15:54:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][310/1251]	eta 0:35:08 lr 0.000622	time 2.7037 (2.2404)	loss 3.0351 (3.6112)	grad_norm 1.4333 (1.3667)	
[2022-01-21 15:55:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][320/1251]	eta 0:34:45 lr 0.000622	time 1.8234 (2.2402)	loss 3.6838 (3.6115)	grad_norm 1.3367 (1.3663)	
[2022-01-21 15:55:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][330/1251]	eta 0:34:24 lr 0.000622	time 2.3126 (2.2412)	loss 3.5070 (3.6190)	grad_norm 1.3341 (1.3657)	
[2022-01-21 15:55:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][340/1251]	eta 0:34:00 lr 0.000622	time 2.5728 (2.2396)	loss 2.9877 (3.6152)	grad_norm 1.4795 (1.3649)	
[2022-01-21 15:56:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][350/1251]	eta 0:33:37 lr 0.000622	time 2.2624 (2.2388)	loss 3.9366 (3.6145)	grad_norm 1.5771 (1.3667)	
[2022-01-21 15:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][360/1251]	eta 0:33:14 lr 0.000622	time 2.1807 (2.2387)	loss 3.9321 (3.6168)	grad_norm 1.3177 (1.3668)	
[2022-01-21 15:56:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][370/1251]	eta 0:32:50 lr 0.000622	time 2.1591 (2.2365)	loss 3.7603 (3.6192)	grad_norm 1.2854 (1.3668)	
[2022-01-21 15:57:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][380/1251]	eta 0:32:27 lr 0.000622	time 2.4290 (2.2362)	loss 4.3714 (3.6205)	grad_norm 1.5917 (1.3675)	
[2022-01-21 15:57:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][390/1251]	eta 0:32:05 lr 0.000622	time 2.9480 (2.2366)	loss 3.7266 (3.6265)	grad_norm 1.6148 (1.3706)	
[2022-01-21 15:58:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][400/1251]	eta 0:31:45 lr 0.000621	time 2.1453 (2.2390)	loss 3.5067 (3.6247)	grad_norm 1.3464 (1.3705)	
[2022-01-21 15:58:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][410/1251]	eta 0:31:19 lr 0.000621	time 2.2277 (2.2353)	loss 4.3128 (3.6220)	grad_norm 1.3902 (1.3711)	
[2022-01-21 15:58:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][420/1251]	eta 0:30:55 lr 0.000621	time 2.1773 (2.2334)	loss 3.8195 (3.6214)	grad_norm 1.4963 (1.3724)	
[2022-01-21 15:59:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][430/1251]	eta 0:30:32 lr 0.000621	time 2.1795 (2.2324)	loss 3.5008 (3.6192)	grad_norm 1.3832 (1.3719)	
[2022-01-21 15:59:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][440/1251]	eta 0:30:07 lr 0.000621	time 1.8518 (2.2289)	loss 3.5351 (3.6154)	grad_norm 1.2718 (1.3720)	
[2022-01-21 15:59:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][450/1251]	eta 0:29:41 lr 0.000621	time 1.8162 (2.2246)	loss 3.3439 (3.6186)	grad_norm 1.1827 (1.3740)	
[2022-01-21 16:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][460/1251]	eta 0:29:19 lr 0.000621	time 1.5747 (2.2250)	loss 2.5656 (3.6184)	grad_norm 1.4275 (1.3752)	
[2022-01-21 16:00:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][470/1251]	eta 0:28:57 lr 0.000621	time 1.9149 (2.2247)	loss 3.4543 (3.6195)	grad_norm 1.8318 (1.3788)	
[2022-01-21 16:00:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][480/1251]	eta 0:28:37 lr 0.000621	time 2.1249 (2.2281)	loss 4.0265 (3.6186)	grad_norm 1.5513 (1.3799)	
[2022-01-21 16:01:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][490/1251]	eta 0:28:16 lr 0.000621	time 2.0980 (2.2288)	loss 3.6424 (3.6175)	grad_norm 1.4839 (1.3793)	
[2022-01-21 16:01:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][500/1251]	eta 0:27:53 lr 0.000621	time 2.2782 (2.2277)	loss 3.4259 (3.6160)	grad_norm 1.1767 (1.3789)	
[2022-01-21 16:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][510/1251]	eta 0:27:29 lr 0.000621	time 2.5571 (2.2266)	loss 3.7164 (3.6104)	grad_norm 1.5393 (1.3795)	
[2022-01-21 16:02:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][520/1251]	eta 0:27:06 lr 0.000621	time 1.7365 (2.2249)	loss 3.9925 (3.6094)	grad_norm 1.5592 (1.3807)	
[2022-01-21 16:02:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][530/1251]	eta 0:26:44 lr 0.000621	time 2.5175 (2.2249)	loss 4.2372 (3.6119)	grad_norm 1.3519 (1.3799)	
[2022-01-21 16:03:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][540/1251]	eta 0:26:22 lr 0.000621	time 2.5491 (2.2262)	loss 2.6249 (3.6039)	grad_norm 1.2096 (1.3829)	
[2022-01-21 16:03:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][550/1251]	eta 0:26:01 lr 0.000621	time 2.3567 (2.2271)	loss 4.2594 (3.6085)	grad_norm 1.5462 (1.3844)	
[2022-01-21 16:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][560/1251]	eta 0:25:37 lr 0.000621	time 1.7963 (2.2257)	loss 3.9363 (3.6118)	grad_norm 1.4069 (1.3848)	
[2022-01-21 16:04:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][570/1251]	eta 0:25:11 lr 0.000621	time 1.9654 (2.2197)	loss 2.4764 (3.6107)	grad_norm 1.6943 (1.3870)	
[2022-01-21 16:04:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][580/1251]	eta 0:24:48 lr 0.000621	time 1.8595 (2.2176)	loss 3.1365 (3.6065)	grad_norm 1.4595 (1.3866)	
[2022-01-21 16:04:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][590/1251]	eta 0:24:23 lr 0.000621	time 2.1014 (2.2140)	loss 4.1451 (3.6092)	grad_norm 1.5302 (1.3860)	
[2022-01-21 16:05:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][600/1251]	eta 0:24:00 lr 0.000621	time 2.2556 (2.2134)	loss 3.8333 (3.6092)	grad_norm 1.3677 (1.3861)	
[2022-01-21 16:05:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][610/1251]	eta 0:23:38 lr 0.000621	time 2.7856 (2.2122)	loss 4.0512 (3.6072)	grad_norm 1.2850 (1.3868)	
[2022-01-21 16:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][620/1251]	eta 0:23:14 lr 0.000621	time 1.7264 (2.2105)	loss 4.2302 (3.6126)	grad_norm 1.6343 (1.3875)	
[2022-01-21 16:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][630/1251]	eta 0:22:52 lr 0.000621	time 1.8788 (2.2106)	loss 3.1819 (3.6099)	grad_norm 1.3711 (1.3872)	
[2022-01-21 16:06:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][640/1251]	eta 0:22:31 lr 0.000620	time 3.0179 (2.2116)	loss 3.9096 (3.6115)	grad_norm 1.2348 (1.3870)	
[2022-01-21 16:07:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][650/1251]	eta 0:22:09 lr 0.000620	time 2.0389 (2.2125)	loss 3.9130 (3.6141)	grad_norm 1.3673 (1.3862)	
[2022-01-21 16:07:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][660/1251]	eta 0:21:48 lr 0.000620	time 1.9003 (2.2146)	loss 3.4659 (3.6140)	grad_norm 1.3744 (1.3870)	
[2022-01-21 16:07:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][670/1251]	eta 0:21:28 lr 0.000620	time 3.1882 (2.2175)	loss 2.7718 (3.6138)	grad_norm 1.3928 (1.3865)	
[2022-01-21 16:08:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][680/1251]	eta 0:21:05 lr 0.000620	time 1.5893 (2.2164)	loss 3.8113 (3.6112)	grad_norm 1.5157 (1.3858)	
[2022-01-21 16:08:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][690/1251]	eta 0:20:42 lr 0.000620	time 1.9562 (2.2148)	loss 3.0260 (3.6113)	grad_norm 1.3219 (1.3853)	
[2022-01-21 16:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][700/1251]	eta 0:20:19 lr 0.000620	time 1.9197 (2.2125)	loss 4.2106 (3.6156)	grad_norm 1.5333 (1.3856)	
[2022-01-21 16:09:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][710/1251]	eta 0:19:57 lr 0.000620	time 2.1066 (2.2127)	loss 4.4617 (3.6133)	grad_norm 1.3458 (1.3857)	
[2022-01-21 16:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][720/1251]	eta 0:19:34 lr 0.000620	time 1.9781 (2.2119)	loss 4.2193 (3.6113)	grad_norm 1.2924 (1.3849)	
[2022-01-21 16:10:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][730/1251]	eta 0:19:11 lr 0.000620	time 1.7057 (2.2109)	loss 4.1034 (3.6129)	grad_norm 1.3190 (1.3852)	
[2022-01-21 16:10:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][740/1251]	eta 0:18:49 lr 0.000620	time 1.9312 (2.2095)	loss 3.3885 (3.6163)	grad_norm 1.2802 (1.3852)	
[2022-01-21 16:10:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][750/1251]	eta 0:18:27 lr 0.000620	time 2.0940 (2.2109)	loss 3.6227 (3.6180)	grad_norm 1.2269 (1.3842)	
[2022-01-21 16:11:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][760/1251]	eta 0:18:05 lr 0.000620	time 2.1122 (2.2108)	loss 3.4882 (3.6155)	grad_norm 1.3489 (1.3844)	
[2022-01-21 16:11:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][770/1251]	eta 0:17:42 lr 0.000620	time 1.8839 (2.2099)	loss 4.1550 (3.6184)	grad_norm 1.5316 (1.3851)	
[2022-01-21 16:11:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][780/1251]	eta 0:17:20 lr 0.000620	time 2.5357 (2.2099)	loss 3.2336 (3.6111)	grad_norm 1.2744 (1.3846)	
[2022-01-21 16:12:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][790/1251]	eta 0:16:58 lr 0.000620	time 2.1745 (2.2088)	loss 2.7898 (3.6096)	grad_norm 1.4310 (1.3842)	
[2022-01-21 16:12:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][800/1251]	eta 0:16:35 lr 0.000620	time 1.6138 (2.2083)	loss 2.8725 (3.6090)	grad_norm 1.3352 (1.3851)	
[2022-01-21 16:12:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][810/1251]	eta 0:16:13 lr 0.000620	time 1.9494 (2.2080)	loss 3.5566 (3.6097)	grad_norm 1.2434 (1.3844)	
[2022-01-21 16:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][820/1251]	eta 0:15:50 lr 0.000620	time 2.1503 (2.2061)	loss 3.5706 (3.6100)	grad_norm 1.3141 (1.3841)	
[2022-01-21 16:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][830/1251]	eta 0:15:28 lr 0.000620	time 2.2511 (2.2045)	loss 4.0221 (3.6091)	grad_norm 1.4580 (1.3833)	
[2022-01-21 16:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][840/1251]	eta 0:15:05 lr 0.000620	time 2.3983 (2.2040)	loss 4.3701 (3.6092)	grad_norm 1.4067 (1.3831)	
[2022-01-21 16:14:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][850/1251]	eta 0:14:43 lr 0.000620	time 1.9659 (2.2044)	loss 3.4241 (3.6101)	grad_norm 1.4224 (1.3843)	
[2022-01-21 16:14:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][860/1251]	eta 0:14:22 lr 0.000620	time 2.8803 (2.2071)	loss 2.8997 (3.6088)	grad_norm 1.5415 (1.3845)	
[2022-01-21 16:15:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][870/1251]	eta 0:14:01 lr 0.000620	time 2.2454 (2.2092)	loss 2.7692 (3.6067)	grad_norm 1.1564 (1.3834)	
[2022-01-21 16:15:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][880/1251]	eta 0:13:39 lr 0.000620	time 1.8548 (2.2086)	loss 2.9457 (3.6066)	grad_norm 1.3238 (1.3837)	
[2022-01-21 16:15:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][890/1251]	eta 0:13:16 lr 0.000619	time 1.9111 (2.2055)	loss 4.5005 (3.6037)	grad_norm 2.1146 (1.3846)	
[2022-01-21 16:16:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][900/1251]	eta 0:12:53 lr 0.000619	time 1.8191 (2.2036)	loss 3.6544 (3.6061)	grad_norm 1.3484 (1.3848)	
[2022-01-21 16:16:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][910/1251]	eta 0:12:30 lr 0.000619	time 2.1855 (2.2021)	loss 3.4676 (3.6078)	grad_norm 1.4538 (1.3851)	
[2022-01-21 16:16:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][920/1251]	eta 0:12:08 lr 0.000619	time 2.0995 (2.2016)	loss 4.1114 (3.6114)	grad_norm 1.3827 (1.3847)	
[2022-01-21 16:17:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][930/1251]	eta 0:11:46 lr 0.000619	time 2.1709 (2.2015)	loss 4.0813 (3.6101)	grad_norm 1.5107 (1.3836)	
[2022-01-21 16:17:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][940/1251]	eta 0:11:25 lr 0.000619	time 2.7697 (2.2041)	loss 4.2370 (3.6104)	grad_norm 1.5746 (1.3849)	
[2022-01-21 16:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][950/1251]	eta 0:11:04 lr 0.000619	time 3.4759 (2.2071)	loss 4.2786 (3.6112)	grad_norm 1.3179 (1.3841)	
[2022-01-21 16:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][960/1251]	eta 0:10:42 lr 0.000619	time 1.6597 (2.2070)	loss 4.2017 (3.6119)	grad_norm 1.3582 (1.3840)	
[2022-01-21 16:18:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][970/1251]	eta 0:10:19 lr 0.000619	time 1.6926 (2.2044)	loss 3.6213 (3.6121)	grad_norm 1.2836 (1.3839)	
[2022-01-21 16:19:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][980/1251]	eta 0:09:56 lr 0.000619	time 2.1748 (2.2028)	loss 3.7406 (3.6143)	grad_norm 1.0847 (1.3833)	
[2022-01-21 16:19:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][990/1251]	eta 0:09:34 lr 0.000619	time 2.2454 (2.2012)	loss 2.8520 (3.6137)	grad_norm 1.4868 (1.3826)	
[2022-01-21 16:19:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1000/1251]	eta 0:09:12 lr 0.000619	time 2.4912 (2.2005)	loss 3.6833 (3.6137)	grad_norm 1.1457 (1.3827)	
[2022-01-21 16:20:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1010/1251]	eta 0:08:50 lr 0.000619	time 2.7011 (2.2023)	loss 4.0036 (3.6139)	grad_norm 1.5360 (1.3823)	
[2022-01-21 16:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1020/1251]	eta 0:08:28 lr 0.000619	time 2.5565 (2.2031)	loss 2.3870 (3.6147)	grad_norm 1.2705 (1.3818)	
[2022-01-21 16:20:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1030/1251]	eta 0:08:06 lr 0.000619	time 1.8529 (2.2021)	loss 4.2431 (3.6131)	grad_norm 1.3201 (1.3822)	
[2022-01-21 16:21:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1040/1251]	eta 0:07:44 lr 0.000619	time 2.1959 (2.2008)	loss 2.7631 (3.6111)	grad_norm 1.8771 (1.3822)	
[2022-01-21 16:21:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1050/1251]	eta 0:07:22 lr 0.000619	time 2.2690 (2.2012)	loss 2.7388 (3.6121)	grad_norm 1.5416 (1.3827)	
[2022-01-21 16:21:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1060/1251]	eta 0:07:00 lr 0.000619	time 2.2307 (2.2012)	loss 3.7309 (3.6131)	grad_norm 1.4574 (1.3829)	
[2022-01-21 16:22:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1070/1251]	eta 0:06:38 lr 0.000619	time 2.1679 (2.2002)	loss 3.5840 (3.6122)	grad_norm 1.2908 (1.3827)	
[2022-01-21 16:22:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1080/1251]	eta 0:06:16 lr 0.000619	time 2.4431 (2.2002)	loss 3.3850 (3.6106)	grad_norm 1.5914 (1.3830)	
[2022-01-21 16:23:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1090/1251]	eta 0:05:54 lr 0.000619	time 1.7909 (2.2017)	loss 4.2504 (3.6107)	grad_norm 1.3485 (1.3828)	
[2022-01-21 16:23:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1100/1251]	eta 0:05:32 lr 0.000619	time 1.9348 (2.2021)	loss 3.9140 (3.6110)	grad_norm 1.2779 (1.3832)	
[2022-01-21 16:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1110/1251]	eta 0:05:10 lr 0.000619	time 2.1942 (2.2019)	loss 3.3018 (3.6103)	grad_norm 1.3142 (1.3827)	
[2022-01-21 16:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1120/1251]	eta 0:04:48 lr 0.000619	time 1.8930 (2.1996)	loss 4.0294 (3.6088)	grad_norm 1.3047 (1.3819)	
[2022-01-21 16:24:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1130/1251]	eta 0:04:26 lr 0.000619	time 2.7095 (2.1987)	loss 3.4502 (3.6081)	grad_norm 1.5272 (1.3815)	
[2022-01-21 16:24:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1140/1251]	eta 0:04:03 lr 0.000618	time 1.9457 (2.1978)	loss 3.8719 (3.6079)	grad_norm 1.3318 (1.3811)	
[2022-01-21 16:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1150/1251]	eta 0:03:42 lr 0.000618	time 2.2928 (2.1999)	loss 3.9374 (3.6063)	grad_norm 1.2923 (1.3800)	
[2022-01-21 16:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1160/1251]	eta 0:03:20 lr 0.000618	time 1.8790 (2.2003)	loss 4.1072 (3.6078)	grad_norm 1.2683 (1.3795)	
[2022-01-21 16:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1170/1251]	eta 0:02:58 lr 0.000618	time 2.4944 (2.2027)	loss 3.5619 (3.6077)	grad_norm 1.3455 (1.3788)	
[2022-01-21 16:26:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1180/1251]	eta 0:02:36 lr 0.000618	time 1.9827 (2.2021)	loss 4.1811 (3.6088)	grad_norm 1.5743 (1.3797)	
[2022-01-21 16:26:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1190/1251]	eta 0:02:14 lr 0.000618	time 1.9122 (2.2004)	loss 2.8141 (3.6077)	grad_norm 1.1316 (1.3805)	
[2022-01-21 16:27:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1200/1251]	eta 0:01:52 lr 0.000618	time 1.8422 (2.1996)	loss 3.0187 (3.6091)	grad_norm 1.4318 (1.3801)	
[2022-01-21 16:27:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1210/1251]	eta 0:01:30 lr 0.000618	time 2.1488 (2.1993)	loss 3.8784 (3.6093)	grad_norm 1.3200 (1.3793)	
[2022-01-21 16:27:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1220/1251]	eta 0:01:08 lr 0.000618	time 2.2570 (2.1986)	loss 3.8058 (3.6102)	grad_norm 1.3992 (1.3789)	
[2022-01-21 16:28:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1230/1251]	eta 0:00:46 lr 0.000618	time 2.5323 (2.1982)	loss 2.4253 (3.6105)	grad_norm 1.1792 (1.3790)	
[2022-01-21 16:28:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1240/1251]	eta 0:00:24 lr 0.000618	time 2.0216 (2.1972)	loss 3.9548 (3.6119)	grad_norm 1.3418 (1.3785)	
[2022-01-21 16:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [127/300][1250/1251]	eta 0:00:02 lr 0.000618	time 1.1984 (2.1919)	loss 4.0786 (3.6101)	grad_norm 1.3561 (1.3784)	
[2022-01-21 16:28:46 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 127 training takes 0:45:42
[2022-01-21 16:29:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.899 (17.899)	Loss 1.0080 (1.0080)	Acc@1 77.051 (77.051)	Acc@5 93.555 (93.555)	
[2022-01-21 16:29:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.619 (3.372)	Loss 1.0769 (1.0850)	Acc@1 75.195 (74.334)	Acc@5 93.555 (92.658)	
[2022-01-21 16:29:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.306 (2.432)	Loss 1.0470 (1.0773)	Acc@1 76.465 (74.619)	Acc@5 93.555 (92.773)	
[2022-01-21 16:29:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.920 (2.305)	Loss 1.1202 (1.0767)	Acc@1 73.438 (74.820)	Acc@5 93.066 (92.814)	
[2022-01-21 16:30:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.537 (2.170)	Loss 1.0615 (1.0765)	Acc@1 74.805 (74.786)	Acc@5 92.969 (92.778)	
[2022-01-21 16:30:23 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.874 Acc@5 92.806
[2022-01-21 16:30:23 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.9%
[2022-01-21 16:30:23 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.07%
[2022-01-21 16:30:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][0/1251]	eta 8:15:50 lr 0.000618	time 23.7811 (23.7811)	loss 3.8330 (3.8330)	grad_norm 1.2176 (1.2176)	
[2022-01-21 16:31:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][10/1251]	eta 1:26:02 lr 0.000618	time 2.4704 (4.1600)	loss 3.3607 (3.5037)	grad_norm 1.4205 (1.3561)	
[2022-01-21 16:31:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][20/1251]	eta 1:06:09 lr 0.000618	time 2.5011 (3.2244)	loss 3.9524 (3.6475)	grad_norm 1.2240 (1.3753)	
[2022-01-21 16:31:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][30/1251]	eta 0:58:38 lr 0.000618	time 1.9931 (2.8814)	loss 2.7981 (3.4895)	grad_norm 1.3787 (1.3625)	
[2022-01-21 16:32:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][40/1251]	eta 0:55:24 lr 0.000618	time 4.5883 (2.7451)	loss 3.3833 (3.5280)	grad_norm 1.4040 (1.3792)	
[2022-01-21 16:32:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][50/1251]	eta 0:53:29 lr 0.000618	time 2.4800 (2.6721)	loss 3.8244 (3.5674)	grad_norm 1.4696 (1.3814)	
[2022-01-21 16:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][60/1251]	eta 0:51:30 lr 0.000618	time 2.0852 (2.5952)	loss 3.6847 (3.5925)	grad_norm 1.4459 (1.3885)	
[2022-01-21 16:33:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][70/1251]	eta 0:49:55 lr 0.000618	time 1.8292 (2.5365)	loss 3.2533 (3.6167)	grad_norm 1.3882 (1.3954)	
[2022-01-21 16:33:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][80/1251]	eta 0:48:53 lr 0.000618	time 3.1976 (2.5047)	loss 2.7426 (3.6260)	grad_norm 1.4793 (1.3910)	
[2022-01-21 16:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][90/1251]	eta 0:48:09 lr 0.000618	time 2.0302 (2.4891)	loss 3.3337 (3.6472)	grad_norm 1.4241 (1.3885)	
[2022-01-21 16:34:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][100/1251]	eta 0:46:52 lr 0.000618	time 1.6981 (2.4432)	loss 4.4316 (3.6336)	grad_norm 1.5510 (1.3868)	
[2022-01-21 16:34:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][110/1251]	eta 0:45:49 lr 0.000618	time 1.9465 (2.4095)	loss 2.8420 (3.6357)	grad_norm 1.2034 (1.3801)	
[2022-01-21 16:35:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][120/1251]	eta 0:44:53 lr 0.000618	time 2.2361 (2.3812)	loss 4.3617 (3.6655)	grad_norm 1.5693 (1.3782)	
[2022-01-21 16:35:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][130/1251]	eta 0:44:34 lr 0.000618	time 2.3873 (2.3860)	loss 2.7463 (3.6292)	grad_norm 1.4970 (1.3783)	
[2022-01-21 16:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][140/1251]	eta 0:44:00 lr 0.000617	time 2.4180 (2.3766)	loss 3.0098 (3.6272)	grad_norm 1.3560 (1.3802)	
[2022-01-21 16:36:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][150/1251]	eta 0:43:20 lr 0.000617	time 2.0453 (2.3619)	loss 3.9960 (3.6280)	grad_norm 1.5601 (1.3787)	
[2022-01-21 16:36:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][160/1251]	eta 0:42:41 lr 0.000617	time 1.6212 (2.3480)	loss 3.5379 (3.6307)	grad_norm 1.1898 (1.3789)	
[2022-01-21 16:37:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][170/1251]	eta 0:42:00 lr 0.000617	time 2.2190 (2.3318)	loss 3.9441 (3.6327)	grad_norm 1.6973 (1.3787)	
[2022-01-21 16:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][180/1251]	eta 0:41:30 lr 0.000617	time 2.8344 (2.3255)	loss 3.1910 (3.6298)	grad_norm 1.7060 (1.3754)	
[2022-01-21 16:37:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][190/1251]	eta 0:40:53 lr 0.000617	time 1.9188 (2.3127)	loss 3.9181 (3.6382)	grad_norm 1.2906 (1.3776)	
[2022-01-21 16:38:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][200/1251]	eta 0:40:24 lr 0.000617	time 2.9101 (2.3072)	loss 4.5412 (3.6428)	grad_norm 1.5146 (1.3793)	
[2022-01-21 16:38:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][210/1251]	eta 0:39:58 lr 0.000617	time 2.2129 (2.3042)	loss 4.3692 (3.6410)	grad_norm 1.2972 (1.3808)	
[2022-01-21 16:38:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][220/1251]	eta 0:39:30 lr 0.000617	time 2.5291 (2.2994)	loss 3.3017 (3.6412)	grad_norm 1.2490 (1.3849)	
[2022-01-21 16:39:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][230/1251]	eta 0:39:08 lr 0.000617	time 2.0750 (2.3000)	loss 3.8120 (3.6407)	grad_norm 1.6889 (1.3862)	
[2022-01-21 16:39:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][240/1251]	eta 0:38:36 lr 0.000617	time 2.0724 (2.2909)	loss 3.6438 (3.6417)	grad_norm 1.3299 (1.3870)	
[2022-01-21 16:39:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][250/1251]	eta 0:38:02 lr 0.000617	time 1.8465 (2.2802)	loss 4.4792 (3.6352)	grad_norm 1.2505 (1.3900)	
[2022-01-21 16:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][260/1251]	eta 0:37:32 lr 0.000617	time 2.4392 (2.2727)	loss 3.2041 (3.6284)	grad_norm 1.4770 (1.3973)	
[2022-01-21 16:40:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][270/1251]	eta 0:37:02 lr 0.000617	time 2.2507 (2.2650)	loss 3.4747 (3.6296)	grad_norm 1.4398 (1.3986)	
[2022-01-21 16:40:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][280/1251]	eta 0:36:32 lr 0.000617	time 2.9998 (2.2584)	loss 3.7305 (3.6205)	grad_norm 1.2327 (1.4008)	
[2022-01-21 16:41:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][290/1251]	eta 0:36:05 lr 0.000617	time 2.5253 (2.2530)	loss 3.6165 (3.6213)	grad_norm 1.7491 (1.3994)	
[2022-01-21 16:41:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][300/1251]	eta 0:35:43 lr 0.000617	time 2.5197 (2.2537)	loss 3.5578 (3.6152)	grad_norm 1.4523 (1.4004)	
[2022-01-21 16:42:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][310/1251]	eta 0:35:21 lr 0.000617	time 2.1859 (2.2541)	loss 4.1092 (3.6106)	grad_norm 1.2971 (1.4013)	
[2022-01-21 16:42:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][320/1251]	eta 0:34:57 lr 0.000617	time 2.6872 (2.2532)	loss 3.5306 (3.6084)	grad_norm 1.1927 (1.3982)	
[2022-01-21 16:42:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][330/1251]	eta 0:34:33 lr 0.000617	time 2.1605 (2.2511)	loss 4.0347 (3.6107)	grad_norm 1.2718 (1.3970)	
[2022-01-21 16:43:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][340/1251]	eta 0:34:10 lr 0.000617	time 2.8193 (2.2509)	loss 3.7270 (3.6109)	grad_norm 1.2765 (1.3957)	
[2022-01-21 16:43:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][350/1251]	eta 0:33:48 lr 0.000617	time 2.1184 (2.2510)	loss 3.7522 (3.6044)	grad_norm 1.5490 (1.3953)	
[2022-01-21 16:43:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][360/1251]	eta 0:33:27 lr 0.000617	time 1.9038 (2.2529)	loss 3.8103 (3.6102)	grad_norm 1.2246 (1.3946)	
[2022-01-21 16:44:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][370/1251]	eta 0:33:02 lr 0.000617	time 2.3651 (2.2499)	loss 3.4467 (3.6132)	grad_norm 1.2780 (1.3956)	
[2022-01-21 16:44:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][380/1251]	eta 0:32:38 lr 0.000617	time 2.7996 (2.2484)	loss 4.0649 (3.6136)	grad_norm 1.5684 (1.3969)	
[2022-01-21 16:45:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][390/1251]	eta 0:32:12 lr 0.000616	time 2.2474 (2.2443)	loss 3.6436 (3.6114)	grad_norm 1.4987 (1.3991)	
[2022-01-21 16:45:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][400/1251]	eta 0:31:47 lr 0.000616	time 2.2706 (2.2417)	loss 3.8773 (3.6107)	grad_norm 1.4842 (1.3986)	
[2022-01-21 16:45:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][410/1251]	eta 0:31:24 lr 0.000616	time 1.9667 (2.2408)	loss 4.2975 (3.6071)	grad_norm 1.4664 (1.3974)	
[2022-01-21 16:46:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][420/1251]	eta 0:31:01 lr 0.000616	time 3.3774 (2.2406)	loss 2.2436 (3.6085)	grad_norm 1.1763 (1.3970)	
[2022-01-21 16:46:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][430/1251]	eta 0:30:38 lr 0.000616	time 2.4957 (2.2394)	loss 2.7421 (3.6065)	grad_norm 1.3640 (1.3949)	
[2022-01-21 16:46:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][440/1251]	eta 0:30:14 lr 0.000616	time 2.0924 (2.2375)	loss 4.3744 (3.6068)	grad_norm 1.5582 (1.3956)	
[2022-01-21 16:47:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][450/1251]	eta 0:29:54 lr 0.000616	time 1.7842 (2.2400)	loss 2.6826 (3.6012)	grad_norm 1.6105 (1.3951)	
[2022-01-21 16:47:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][460/1251]	eta 0:29:32 lr 0.000616	time 3.1006 (2.2405)	loss 3.3188 (3.6046)	grad_norm 1.4547 (1.3935)	
[2022-01-21 16:47:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][470/1251]	eta 0:29:06 lr 0.000616	time 2.0913 (2.2358)	loss 3.5210 (3.6075)	grad_norm 1.3394 (1.3919)	
[2022-01-21 16:48:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][480/1251]	eta 0:28:40 lr 0.000616	time 1.9210 (2.2310)	loss 3.6280 (3.6084)	grad_norm 1.3208 (1.3891)	
[2022-01-21 16:48:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][490/1251]	eta 0:28:19 lr 0.000616	time 2.4143 (2.2336)	loss 3.9339 (3.6042)	grad_norm 1.4304 (1.3879)	
[2022-01-21 16:49:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][500/1251]	eta 0:27:58 lr 0.000616	time 1.9473 (2.2345)	loss 3.9771 (3.6075)	grad_norm 1.3029 (1.3859)	
[2022-01-21 16:49:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][510/1251]	eta 0:27:33 lr 0.000616	time 1.5829 (2.2314)	loss 4.4610 (3.6020)	grad_norm 1.3983 (1.3859)	
[2022-01-21 16:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][520/1251]	eta 0:27:10 lr 0.000616	time 1.9966 (2.2305)	loss 2.9099 (3.6014)	grad_norm 1.4490 (1.3865)	
[2022-01-21 16:50:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][530/1251]	eta 0:26:49 lr 0.000616	time 3.1249 (2.2327)	loss 3.9528 (3.6013)	grad_norm 1.4383 (1.3879)	
[2022-01-21 16:50:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][540/1251]	eta 0:26:25 lr 0.000616	time 2.1075 (2.2304)	loss 4.5019 (3.6062)	grad_norm 1.2715 (1.3877)	
[2022-01-21 16:50:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][550/1251]	eta 0:26:01 lr 0.000616	time 2.1972 (2.2282)	loss 3.4903 (3.6093)	grad_norm 1.4287 (1.3865)	
[2022-01-21 16:51:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][560/1251]	eta 0:25:36 lr 0.000616	time 1.8497 (2.2237)	loss 4.0756 (3.6065)	grad_norm 1.4941 (1.3884)	
[2022-01-21 16:51:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][570/1251]	eta 0:25:13 lr 0.000616	time 2.5343 (2.2229)	loss 3.8116 (3.6073)	grad_norm 1.3572 (1.3880)	
[2022-01-21 16:51:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][580/1251]	eta 0:24:50 lr 0.000616	time 2.3004 (2.2215)	loss 4.2867 (3.6050)	grad_norm 1.3797 (1.3873)	
[2022-01-21 16:52:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][590/1251]	eta 0:24:27 lr 0.000616	time 2.2156 (2.2197)	loss 3.8658 (3.6052)	grad_norm 1.5508 (1.3871)	
[2022-01-21 16:52:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][600/1251]	eta 0:24:06 lr 0.000616	time 2.5054 (2.2214)	loss 3.3107 (3.6054)	grad_norm 1.3778 (1.3875)	
[2022-01-21 16:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][610/1251]	eta 0:23:46 lr 0.000616	time 2.9264 (2.2254)	loss 4.2564 (3.6075)	grad_norm 1.3628 (1.3887)	
[2022-01-21 16:53:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][620/1251]	eta 0:23:25 lr 0.000616	time 2.4771 (2.2279)	loss 2.8775 (3.6078)	grad_norm 1.2862 (1.3880)	
[2022-01-21 16:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][630/1251]	eta 0:23:00 lr 0.000615	time 1.7986 (2.2237)	loss 3.5283 (3.6053)	grad_norm 1.1876 (1.3862)	
[2022-01-21 16:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][640/1251]	eta 0:22:37 lr 0.000615	time 2.1288 (2.2215)	loss 3.7276 (3.6027)	grad_norm 1.3466 (1.3852)	
[2022-01-21 16:54:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][650/1251]	eta 0:22:12 lr 0.000615	time 1.9038 (2.2176)	loss 4.1182 (3.6020)	grad_norm 1.5511 (1.3856)	
[2022-01-21 16:54:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][660/1251]	eta 0:21:49 lr 0.000615	time 2.3167 (2.2150)	loss 4.1189 (3.6023)	grad_norm 1.4333 (1.3856)	
[2022-01-21 16:55:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][670/1251]	eta 0:21:26 lr 0.000615	time 2.0116 (2.2137)	loss 3.8204 (3.6002)	grad_norm 1.4483 (1.3849)	
[2022-01-21 16:55:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][680/1251]	eta 0:21:04 lr 0.000615	time 2.1357 (2.2137)	loss 3.3377 (3.5983)	grad_norm 1.4761 (1.3860)	
[2022-01-21 16:55:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][690/1251]	eta 0:20:42 lr 0.000615	time 2.8091 (2.2141)	loss 3.8940 (3.6009)	grad_norm 1.1632 (1.3856)	
[2022-01-21 16:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][700/1251]	eta 0:20:21 lr 0.000615	time 2.9082 (2.2174)	loss 3.7473 (3.6039)	grad_norm 1.6005 (1.3860)	
[2022-01-21 16:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][710/1251]	eta 0:20:00 lr 0.000615	time 1.6136 (2.2183)	loss 4.3882 (3.6026)	grad_norm 1.2865 (1.3856)	
[2022-01-21 16:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][720/1251]	eta 0:19:38 lr 0.000615	time 1.9422 (2.2195)	loss 4.3864 (3.6082)	grad_norm 1.3982 (1.3855)	
[2022-01-21 16:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][730/1251]	eta 0:19:16 lr 0.000615	time 1.6373 (2.2193)	loss 4.3631 (3.6082)	grad_norm 1.3830 (1.3852)	
[2022-01-21 16:57:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][740/1251]	eta 0:18:52 lr 0.000615	time 2.3418 (2.2172)	loss 3.5087 (3.6043)	grad_norm 1.2759 (1.3853)	
[2022-01-21 16:58:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][750/1251]	eta 0:18:29 lr 0.000615	time 1.8805 (2.2151)	loss 3.6048 (3.6064)	grad_norm 1.2695 (1.3843)	
[2022-01-21 16:58:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][760/1251]	eta 0:18:07 lr 0.000615	time 1.8171 (2.2153)	loss 3.6252 (3.6047)	grad_norm 1.3132 (1.3835)	
[2022-01-21 16:58:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][770/1251]	eta 0:17:44 lr 0.000615	time 2.5175 (2.2141)	loss 3.8859 (3.6042)	grad_norm 1.5376 (1.3842)	
[2022-01-21 16:59:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][780/1251]	eta 0:17:22 lr 0.000615	time 2.4437 (2.2132)	loss 2.7044 (3.5983)	grad_norm 1.2453 (1.3855)	
[2022-01-21 16:59:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][790/1251]	eta 0:16:59 lr 0.000615	time 1.6374 (2.2124)	loss 4.1877 (3.6016)	grad_norm 1.1798 (1.3851)	
[2022-01-21 16:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][800/1251]	eta 0:16:37 lr 0.000615	time 1.8451 (2.2107)	loss 3.1885 (3.6040)	grad_norm 1.2206 (1.3858)	
[2022-01-21 17:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][810/1251]	eta 0:16:15 lr 0.000615	time 2.4997 (2.2113)	loss 3.6634 (3.6050)	grad_norm 1.4234 (1.3858)	
[2022-01-21 17:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][820/1251]	eta 0:15:53 lr 0.000615	time 2.4044 (2.2120)	loss 4.2216 (3.6041)	grad_norm 1.4903 (1.3857)	
[2022-01-21 17:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][830/1251]	eta 0:15:32 lr 0.000615	time 2.2062 (2.2138)	loss 4.0384 (3.6067)	grad_norm 1.7592 (1.3854)	
[2022-01-21 17:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][840/1251]	eta 0:15:09 lr 0.000615	time 1.7527 (2.2134)	loss 4.2691 (3.6054)	grad_norm 1.3039 (1.3856)	
[2022-01-21 17:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][850/1251]	eta 0:14:47 lr 0.000615	time 2.1319 (2.2128)	loss 3.2596 (3.6057)	grad_norm 1.3790 (1.3850)	
[2022-01-21 17:02:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][860/1251]	eta 0:14:24 lr 0.000615	time 1.7830 (2.2111)	loss 3.9085 (3.6088)	grad_norm 1.2802 (1.3844)	
[2022-01-21 17:02:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][870/1251]	eta 0:14:01 lr 0.000615	time 1.6664 (2.2082)	loss 2.5775 (3.6074)	grad_norm 1.1902 (1.3828)	
[2022-01-21 17:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][880/1251]	eta 0:13:38 lr 0.000614	time 2.3356 (2.2071)	loss 3.7158 (3.6089)	grad_norm 1.3464 (1.3829)	
[2022-01-21 17:03:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][890/1251]	eta 0:13:16 lr 0.000614	time 1.9765 (2.2068)	loss 2.5260 (3.6063)	grad_norm 1.7987 (1.3834)	
[2022-01-21 17:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][900/1251]	eta 0:12:55 lr 0.000614	time 1.6142 (2.2084)	loss 3.7208 (3.6043)	grad_norm 1.4243 (1.3835)	
[2022-01-21 17:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][910/1251]	eta 0:12:33 lr 0.000614	time 1.8301 (2.2094)	loss 2.4417 (3.6068)	grad_norm 1.4533 (1.3832)	
[2022-01-21 17:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][920/1251]	eta 0:12:11 lr 0.000614	time 1.8431 (2.2093)	loss 2.8206 (3.6033)	grad_norm 1.4549 (1.3830)	
[2022-01-21 17:04:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][930/1251]	eta 0:11:49 lr 0.000614	time 2.0156 (2.2090)	loss 3.8980 (3.6058)	grad_norm 1.5743 (1.3835)	
[2022-01-21 17:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][940/1251]	eta 0:11:26 lr 0.000614	time 1.8442 (2.2067)	loss 3.6135 (3.6070)	grad_norm 1.4897 (1.3837)	
[2022-01-21 17:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][950/1251]	eta 0:11:03 lr 0.000614	time 2.5278 (2.2059)	loss 3.8812 (3.6052)	grad_norm 1.3415 (1.3841)	
[2022-01-21 17:05:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][960/1251]	eta 0:10:41 lr 0.000614	time 2.1877 (2.2062)	loss 3.1156 (3.6035)	grad_norm 1.3956 (1.3837)	
[2022-01-21 17:06:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][970/1251]	eta 0:10:20 lr 0.000614	time 2.4011 (2.2069)	loss 4.2227 (3.6051)	grad_norm 1.3739 (1.3830)	
[2022-01-21 17:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][980/1251]	eta 0:09:57 lr 0.000614	time 1.7559 (2.2064)	loss 3.5836 (3.6069)	grad_norm 1.4231 (1.3829)	
[2022-01-21 17:06:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][990/1251]	eta 0:09:35 lr 0.000614	time 2.1432 (2.2066)	loss 2.9072 (3.6063)	grad_norm 1.6781 (1.3836)	
[2022-01-21 17:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1000/1251]	eta 0:09:13 lr 0.000614	time 2.1997 (2.2053)	loss 4.0529 (3.6064)	grad_norm 1.5726 (1.3847)	
[2022-01-21 17:07:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1010/1251]	eta 0:08:51 lr 0.000614	time 1.8650 (2.2035)	loss 3.5577 (3.6077)	grad_norm 1.3547 (1.3857)	
[2022-01-21 17:07:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1020/1251]	eta 0:08:28 lr 0.000614	time 2.1808 (2.2017)	loss 3.1571 (3.6083)	grad_norm 1.2233 (1.3864)	
[2022-01-21 17:08:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1030/1251]	eta 0:08:06 lr 0.000614	time 1.9432 (2.2000)	loss 3.9541 (3.6077)	grad_norm 1.3352 (1.3858)	
[2022-01-21 17:08:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1040/1251]	eta 0:07:44 lr 0.000614	time 2.4892 (2.1992)	loss 3.4952 (3.6085)	grad_norm 1.4021 (1.3860)	
[2022-01-21 17:08:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1050/1251]	eta 0:07:21 lr 0.000614	time 1.5457 (2.1987)	loss 3.3557 (3.6083)	grad_norm 1.4306 (1.3863)	
[2022-01-21 17:09:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1060/1251]	eta 0:06:59 lr 0.000614	time 1.8877 (2.1969)	loss 4.0886 (3.6072)	grad_norm 1.1857 (1.3855)	
[2022-01-21 17:09:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1070/1251]	eta 0:06:37 lr 0.000614	time 1.8307 (2.1983)	loss 3.0011 (3.6089)	grad_norm 1.3694 (1.3851)	
[2022-01-21 17:10:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1080/1251]	eta 0:06:16 lr 0.000614	time 2.4780 (2.2005)	loss 2.5303 (3.6054)	grad_norm 1.4602 (1.3863)	
[2022-01-21 17:10:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1090/1251]	eta 0:05:54 lr 0.000614	time 1.6892 (2.2012)	loss 4.0022 (3.6057)	grad_norm 1.2530 (1.3862)	
[2022-01-21 17:10:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1100/1251]	eta 0:05:32 lr 0.000614	time 2.5043 (2.2017)	loss 3.7128 (3.6079)	grad_norm 1.2096 (1.3855)	
[2022-01-21 17:11:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1110/1251]	eta 0:05:10 lr 0.000614	time 1.4562 (2.2021)	loss 4.0140 (3.6086)	grad_norm 1.3536 (1.3852)	
[2022-01-21 17:11:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1120/1251]	eta 0:04:48 lr 0.000614	time 2.7392 (2.2025)	loss 3.1526 (3.6062)	grad_norm 1.2957 (1.3851)	
[2022-01-21 17:11:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1130/1251]	eta 0:04:26 lr 0.000613	time 1.5593 (2.2019)	loss 4.1802 (3.6065)	grad_norm 1.5276 (1.3849)	
[2022-01-21 17:12:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1140/1251]	eta 0:04:04 lr 0.000613	time 1.8514 (2.1999)	loss 4.0005 (3.6044)	grad_norm 1.3664 (1.3842)	
[2022-01-21 17:12:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1150/1251]	eta 0:03:42 lr 0.000613	time 1.5625 (2.1986)	loss 3.9853 (3.6060)	grad_norm 1.2882 (1.3837)	
[2022-01-21 17:12:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1160/1251]	eta 0:03:20 lr 0.000613	time 3.1182 (2.1984)	loss 3.8976 (3.6093)	grad_norm 1.1951 (1.3835)	
[2022-01-21 17:13:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1170/1251]	eta 0:02:58 lr 0.000613	time 1.7028 (2.1983)	loss 2.4566 (3.6091)	grad_norm 1.4430 (1.3831)	
[2022-01-21 17:13:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1180/1251]	eta 0:02:36 lr 0.000613	time 2.7708 (2.1975)	loss 3.8207 (3.6069)	grad_norm 1.1394 (1.3827)	
[2022-01-21 17:13:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1190/1251]	eta 0:02:13 lr 0.000613	time 1.8266 (2.1964)	loss 2.9163 (3.6058)	grad_norm 1.3070 (1.3823)	
[2022-01-21 17:14:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1200/1251]	eta 0:01:51 lr 0.000613	time 2.8332 (2.1960)	loss 3.4189 (3.6060)	grad_norm 1.2162 (1.3821)	
[2022-01-21 17:14:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1210/1251]	eta 0:01:30 lr 0.000613	time 2.1116 (2.1973)	loss 3.7180 (3.6059)	grad_norm 1.2190 (1.3821)	
[2022-01-21 17:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1220/1251]	eta 0:01:08 lr 0.000613	time 1.8582 (2.1972)	loss 4.2212 (3.6068)	grad_norm 1.2419 (1.3821)	
[2022-01-21 17:15:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1230/1251]	eta 0:00:46 lr 0.000613	time 1.7727 (2.1980)	loss 3.8222 (3.6061)	grad_norm 1.3434 (1.3822)	
[2022-01-21 17:15:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1240/1251]	eta 0:00:24 lr 0.000613	time 2.2976 (2.1982)	loss 3.5632 (3.6040)	grad_norm 1.4011 (1.3822)	
[2022-01-21 17:16:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [128/300][1250/1251]	eta 0:00:02 lr 0.000613	time 1.1414 (2.1927)	loss 2.6875 (3.6034)	grad_norm 1.2107 (1.3820)	
[2022-01-21 17:16:06 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 128 training takes 0:45:43
[2022-01-21 17:16:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.891 (18.891)	Loss 1.0375 (1.0375)	Acc@1 75.977 (75.977)	Acc@5 93.066 (93.066)	
[2022-01-21 17:16:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.962 (3.403)	Loss 1.0859 (1.0850)	Acc@1 75.098 (74.876)	Acc@5 92.285 (92.560)	
[2022-01-21 17:17:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.367 (2.671)	Loss 1.1211 (1.0782)	Acc@1 72.461 (74.688)	Acc@5 93.457 (92.690)	
[2022-01-21 17:17:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.594 (2.369)	Loss 1.0732 (1.0713)	Acc@1 74.023 (74.849)	Acc@5 92.285 (92.792)	
[2022-01-21 17:17:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.293 (2.248)	Loss 1.0977 (1.0735)	Acc@1 74.414 (74.871)	Acc@5 92.676 (92.785)	
[2022-01-21 17:17:45 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.812 Acc@5 92.760
[2022-01-21 17:17:45 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 74.8%
[2022-01-21 17:17:45 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.07%
[2022-01-21 17:18:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][0/1251]	eta 7:23:22 lr 0.000613	time 21.2649 (21.2649)	loss 3.9198 (3.9198)	grad_norm 1.3924 (1.3924)	
[2022-01-21 17:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][10/1251]	eta 1:18:59 lr 0.000613	time 1.7257 (3.8193)	loss 3.7813 (3.6290)	grad_norm 1.4327 (1.3628)	
[2022-01-21 17:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][20/1251]	eta 1:01:50 lr 0.000613	time 1.4767 (3.0142)	loss 3.8493 (3.7517)	grad_norm 1.2039 (1.3755)	
[2022-01-21 17:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][30/1251]	eta 0:55:43 lr 0.000613	time 1.3988 (2.7387)	loss 3.8511 (3.7416)	grad_norm 1.2150 (1.3617)	
[2022-01-21 17:19:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][40/1251]	eta 0:53:23 lr 0.000613	time 3.7117 (2.6450)	loss 3.7077 (3.6798)	grad_norm 1.1608 (1.3753)	
[2022-01-21 17:19:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][50/1251]	eta 0:51:52 lr 0.000613	time 3.0976 (2.5916)	loss 3.3183 (3.6283)	grad_norm 1.6311 (1.3715)	
[2022-01-21 17:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][60/1251]	eta 0:50:15 lr 0.000613	time 1.5236 (2.5318)	loss 4.2033 (3.5689)	grad_norm 1.4088 (1.3671)	
[2022-01-21 17:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][70/1251]	eta 0:49:05 lr 0.000613	time 1.5565 (2.4939)	loss 2.4762 (3.5582)	grad_norm 1.4956 (1.3839)	
[2022-01-21 17:21:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][80/1251]	eta 0:48:24 lr 0.000613	time 3.5249 (2.4807)	loss 3.2397 (3.5442)	grad_norm 1.5458 (1.3840)	
[2022-01-21 17:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][90/1251]	eta 0:47:31 lr 0.000613	time 1.4269 (2.4562)	loss 2.9655 (3.5484)	grad_norm 1.5947 (1.3815)	
[2022-01-21 17:21:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][100/1251]	eta 0:46:19 lr 0.000613	time 1.8305 (2.4144)	loss 3.8585 (3.5450)	grad_norm 1.8095 (1.3845)	
[2022-01-21 17:22:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][110/1251]	eta 0:45:25 lr 0.000613	time 1.8615 (2.3891)	loss 3.9762 (3.5568)	grad_norm 1.3139 (1.3799)	
[2022-01-21 17:22:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][120/1251]	eta 0:44:45 lr 0.000612	time 2.9931 (2.3748)	loss 4.2572 (3.5645)	grad_norm 1.3487 (1.3772)	
[2022-01-21 17:22:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][130/1251]	eta 0:44:14 lr 0.000612	time 2.4206 (2.3683)	loss 3.9521 (3.5628)	grad_norm 1.5227 (1.3697)	
[2022-01-21 17:23:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][140/1251]	eta 0:43:32 lr 0.000612	time 2.1138 (2.3516)	loss 4.4154 (3.5723)	grad_norm 1.2054 (1.3614)	
[2022-01-21 17:23:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][150/1251]	eta 0:42:58 lr 0.000612	time 1.9406 (2.3417)	loss 4.0828 (3.5763)	grad_norm 1.2687 (1.3617)	
[2022-01-21 17:24:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][160/1251]	eta 0:42:27 lr 0.000612	time 2.6752 (2.3346)	loss 2.6430 (3.5705)	grad_norm 1.4560 (1.3641)	
[2022-01-21 17:24:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][170/1251]	eta 0:41:43 lr 0.000612	time 1.8972 (2.3162)	loss 3.7613 (3.5713)	grad_norm 1.3370 (1.3654)	
[2022-01-21 17:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][180/1251]	eta 0:41:12 lr 0.000612	time 2.3051 (2.3087)	loss 3.8511 (3.5795)	grad_norm 1.5618 (1.3661)	
[2022-01-21 17:25:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][190/1251]	eta 0:40:42 lr 0.000612	time 2.1490 (2.3019)	loss 3.9928 (3.5886)	grad_norm 1.3941 (1.3666)	
[2022-01-21 17:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][200/1251]	eta 0:40:07 lr 0.000612	time 2.2213 (2.2908)	loss 3.9686 (3.5849)	grad_norm 1.4392 (1.3658)	
[2022-01-21 17:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][210/1251]	eta 0:39:44 lr 0.000612	time 2.1143 (2.2909)	loss 3.8083 (3.5925)	grad_norm 1.3591 (1.3680)	
[2022-01-21 17:26:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][220/1251]	eta 0:39:24 lr 0.000612	time 1.6331 (2.2933)	loss 3.8527 (3.6065)	grad_norm 1.4574 (1.3677)	
[2022-01-21 17:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][230/1251]	eta 0:38:59 lr 0.000612	time 1.9124 (2.2914)	loss 3.5964 (3.6075)	grad_norm 1.3889 (1.3722)	
[2022-01-21 17:26:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][240/1251]	eta 0:38:37 lr 0.000612	time 2.1503 (2.2920)	loss 3.9218 (3.6074)	grad_norm 1.3859 (1.3752)	
[2022-01-21 17:27:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][250/1251]	eta 0:38:03 lr 0.000612	time 1.9409 (2.2808)	loss 3.5220 (3.6009)	grad_norm 1.5811 (1.3749)	
[2022-01-21 17:27:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][260/1251]	eta 0:37:34 lr 0.000612	time 1.5902 (2.2748)	loss 3.9972 (3.6041)	grad_norm 1.2539 (1.3750)	
[2022-01-21 17:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][270/1251]	eta 0:37:02 lr 0.000612	time 1.9379 (2.2652)	loss 3.2509 (3.6093)	grad_norm 1.2414 (1.3758)	
[2022-01-21 17:28:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][280/1251]	eta 0:36:37 lr 0.000612	time 1.9243 (2.2628)	loss 3.4118 (3.6085)	grad_norm 1.3164 (1.3746)	
[2022-01-21 17:28:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][290/1251]	eta 0:36:15 lr 0.000612	time 2.8049 (2.2633)	loss 3.0522 (3.6021)	grad_norm 1.4298 (1.3777)	
[2022-01-21 17:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][300/1251]	eta 0:35:55 lr 0.000612	time 2.3067 (2.2663)	loss 3.5184 (3.6055)	grad_norm 1.4879 (1.3773)	
[2022-01-21 17:29:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][310/1251]	eta 0:35:30 lr 0.000612	time 1.9904 (2.2642)	loss 3.7615 (3.6009)	grad_norm 1.3952 (1.3784)	
[2022-01-21 17:29:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][320/1251]	eta 0:35:05 lr 0.000612	time 2.3568 (2.2611)	loss 3.3141 (3.6064)	grad_norm 1.6119 (1.3783)	
[2022-01-21 17:30:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][330/1251]	eta 0:34:32 lr 0.000612	time 2.1704 (2.2505)	loss 3.8497 (3.6149)	grad_norm 1.2967 (1.3784)	
[2022-01-21 17:30:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][340/1251]	eta 0:34:02 lr 0.000612	time 1.9413 (2.2424)	loss 3.2832 (3.6165)	grad_norm 1.3963 (1.3777)	
[2022-01-21 17:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][350/1251]	eta 0:33:40 lr 0.000612	time 2.2062 (2.2423)	loss 3.7447 (3.6165)	grad_norm 1.3460 (1.3794)	
[2022-01-21 17:31:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][360/1251]	eta 0:33:15 lr 0.000612	time 2.0265 (2.2401)	loss 3.8408 (3.6190)	grad_norm 1.2578 (1.3788)	
[2022-01-21 17:31:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][370/1251]	eta 0:32:52 lr 0.000611	time 2.1950 (2.2384)	loss 4.1000 (3.6200)	grad_norm 1.5598 (1.3794)	
[2022-01-21 17:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][380/1251]	eta 0:32:30 lr 0.000611	time 2.1951 (2.2390)	loss 3.0056 (3.6239)	grad_norm 1.4427 (1.3807)	
[2022-01-21 17:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][390/1251]	eta 0:32:06 lr 0.000611	time 1.7691 (2.2371)	loss 3.3861 (3.6256)	grad_norm 1.4457 (1.3825)	
[2022-01-21 17:32:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][400/1251]	eta 0:31:42 lr 0.000611	time 1.8406 (2.2360)	loss 3.3365 (3.6310)	grad_norm 1.2557 (1.3810)	
[2022-01-21 17:33:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][410/1251]	eta 0:31:17 lr 0.000611	time 2.0173 (2.2322)	loss 3.2439 (3.6289)	grad_norm 1.4188 (1.3791)	
[2022-01-21 17:33:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][420/1251]	eta 0:30:56 lr 0.000611	time 2.5290 (2.2339)	loss 2.5958 (3.6229)	grad_norm 1.1732 (1.3788)	
[2022-01-21 17:33:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][430/1251]	eta 0:30:35 lr 0.000611	time 2.3951 (2.2352)	loss 3.0193 (3.6219)	grad_norm 1.5073 (1.3780)	
[2022-01-21 17:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][440/1251]	eta 0:30:10 lr 0.000611	time 1.6589 (2.2328)	loss 3.6891 (3.6292)	grad_norm 1.5604 (1.3797)	
[2022-01-21 17:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][450/1251]	eta 0:29:47 lr 0.000611	time 2.3242 (2.2317)	loss 2.7623 (3.6192)	grad_norm 1.3765 (1.3792)	
[2022-01-21 17:34:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][460/1251]	eta 0:29:22 lr 0.000611	time 1.8637 (2.2278)	loss 3.9615 (3.6212)	grad_norm 1.4523 (1.3801)	
[2022-01-21 17:35:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][470/1251]	eta 0:28:58 lr 0.000611	time 2.1035 (2.2262)	loss 3.6894 (3.6237)	grad_norm 1.4371 (1.3800)	
[2022-01-21 17:35:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][480/1251]	eta 0:28:35 lr 0.000611	time 2.2211 (2.2254)	loss 3.3143 (3.6262)	grad_norm 1.2293 (1.3788)	
[2022-01-21 17:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][490/1251]	eta 0:28:13 lr 0.000611	time 2.4547 (2.2253)	loss 3.7469 (3.6239)	grad_norm 1.4734 (1.3781)	
[2022-01-21 17:36:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][500/1251]	eta 0:27:49 lr 0.000611	time 2.2885 (2.2232)	loss 4.0117 (3.6223)	grad_norm 1.2884 (1.3774)	
[2022-01-21 17:36:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][510/1251]	eta 0:27:26 lr 0.000611	time 2.2427 (2.2224)	loss 3.9807 (3.6179)	grad_norm 1.3506 (1.3779)	
[2022-01-21 17:37:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][520/1251]	eta 0:27:07 lr 0.000611	time 3.1014 (2.2258)	loss 3.0381 (3.6195)	grad_norm 1.3784 (1.3793)	
[2022-01-21 17:37:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][530/1251]	eta 0:26:44 lr 0.000611	time 2.1420 (2.2258)	loss 4.2248 (3.6195)	grad_norm 1.5008 (1.3788)	
[2022-01-21 17:37:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][540/1251]	eta 0:26:23 lr 0.000611	time 2.1806 (2.2267)	loss 3.1042 (3.6193)	grad_norm 1.1995 (1.3802)	
[2022-01-21 17:38:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][550/1251]	eta 0:25:58 lr 0.000611	time 1.7363 (2.2238)	loss 4.0845 (3.6192)	grad_norm 1.3201 (1.3800)	
[2022-01-21 17:38:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][560/1251]	eta 0:25:34 lr 0.000611	time 2.8328 (2.2211)	loss 4.2736 (3.6259)	grad_norm 1.3481 (1.3792)	
[2022-01-21 17:38:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][570/1251]	eta 0:25:10 lr 0.000611	time 1.8572 (2.2184)	loss 4.4579 (3.6292)	grad_norm 1.5059 (1.3799)	
[2022-01-21 17:39:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][580/1251]	eta 0:24:48 lr 0.000611	time 2.0695 (2.2184)	loss 3.3210 (3.6317)	grad_norm 1.2671 (1.3789)	
[2022-01-21 17:39:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][590/1251]	eta 0:24:23 lr 0.000611	time 1.7243 (2.2147)	loss 2.7900 (3.6306)	grad_norm 1.4129 (1.3787)	
[2022-01-21 17:39:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][600/1251]	eta 0:24:01 lr 0.000611	time 2.7366 (2.2141)	loss 3.2997 (3.6323)	grad_norm 1.2612 (1.3778)	
[2022-01-21 17:40:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][610/1251]	eta 0:23:38 lr 0.000611	time 2.0692 (2.2133)	loss 2.6587 (3.6310)	grad_norm 1.2911 (1.3771)	
[2022-01-21 17:40:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][620/1251]	eta 0:23:16 lr 0.000610	time 2.2659 (2.2128)	loss 3.3378 (3.6312)	grad_norm 1.4278 (1.3768)	
[2022-01-21 17:41:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][630/1251]	eta 0:22:53 lr 0.000610	time 2.1765 (2.2119)	loss 4.0065 (3.6307)	grad_norm 1.4365 (1.3762)	
[2022-01-21 17:41:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][640/1251]	eta 0:22:30 lr 0.000610	time 2.4755 (2.2107)	loss 3.8577 (3.6295)	grad_norm 1.3202 (1.3759)	
[2022-01-21 17:41:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][650/1251]	eta 0:22:09 lr 0.000610	time 2.3636 (2.2120)	loss 3.7948 (3.6306)	grad_norm 1.3083 (1.3752)	
[2022-01-21 17:42:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][660/1251]	eta 0:21:46 lr 0.000610	time 2.4038 (2.2114)	loss 4.3889 (3.6266)	grad_norm 1.2987 (1.3749)	
[2022-01-21 17:42:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][670/1251]	eta 0:21:24 lr 0.000610	time 2.0174 (2.2110)	loss 4.0413 (3.6275)	grad_norm 1.3861 (1.3737)	
[2022-01-21 17:42:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][680/1251]	eta 0:21:03 lr 0.000610	time 2.5263 (2.2122)	loss 2.7640 (3.6272)	grad_norm 1.2613 (1.3737)	
[2022-01-21 17:43:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][690/1251]	eta 0:20:41 lr 0.000610	time 2.7262 (2.2129)	loss 3.0408 (3.6264)	grad_norm 1.5591 (1.3738)	
[2022-01-21 17:43:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][700/1251]	eta 0:20:19 lr 0.000610	time 2.2113 (2.2132)	loss 3.9230 (3.6257)	grad_norm 1.3663 (1.3751)	
[2022-01-21 17:43:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][710/1251]	eta 0:19:57 lr 0.000610	time 2.5422 (2.2143)	loss 4.2549 (3.6235)	grad_norm 1.2219 (1.3758)	
[2022-01-21 17:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][720/1251]	eta 0:19:35 lr 0.000610	time 2.8724 (2.2138)	loss 3.3399 (3.6235)	grad_norm 1.3573 (1.3765)	
[2022-01-21 17:44:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][730/1251]	eta 0:19:11 lr 0.000610	time 1.8870 (2.2101)	loss 2.5980 (3.6229)	grad_norm 1.3920 (1.3766)	
[2022-01-21 17:45:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][740/1251]	eta 0:18:48 lr 0.000610	time 2.0336 (2.2089)	loss 3.8361 (3.6239)	grad_norm 1.2468 (1.3762)	
[2022-01-21 17:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][750/1251]	eta 0:18:26 lr 0.000610	time 2.5754 (2.2086)	loss 3.4171 (3.6224)	grad_norm 1.3122 (1.3758)	
[2022-01-21 17:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][760/1251]	eta 0:18:04 lr 0.000610	time 2.2018 (2.2092)	loss 3.9186 (3.6248)	grad_norm 1.4639 (1.3758)	
[2022-01-21 17:46:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][770/1251]	eta 0:17:42 lr 0.000610	time 2.7124 (2.2098)	loss 4.0398 (3.6273)	grad_norm 1.3163 (1.3761)	
[2022-01-21 17:46:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][780/1251]	eta 0:17:20 lr 0.000610	time 2.4885 (2.2102)	loss 3.5628 (3.6256)	grad_norm 1.2074 (1.3777)	
[2022-01-21 17:46:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][790/1251]	eta 0:16:58 lr 0.000610	time 1.7388 (2.2100)	loss 4.1585 (3.6279)	grad_norm 1.2077 (1.3772)	
[2022-01-21 17:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][800/1251]	eta 0:16:37 lr 0.000610	time 2.5775 (2.2110)	loss 4.3886 (3.6271)	grad_norm 1.2000 (1.3764)	
[2022-01-21 17:47:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][810/1251]	eta 0:16:15 lr 0.000610	time 2.8515 (2.2110)	loss 3.7562 (3.6257)	grad_norm 1.4218 (1.3774)	
[2022-01-21 17:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][820/1251]	eta 0:15:52 lr 0.000610	time 1.8907 (2.2093)	loss 4.0747 (3.6264)	grad_norm 1.5405 (1.3801)	
[2022-01-21 17:48:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][830/1251]	eta 0:15:29 lr 0.000610	time 1.7636 (2.2082)	loss 4.1941 (3.6281)	grad_norm 1.3935 (1.3799)	
[2022-01-21 17:48:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][840/1251]	eta 0:15:07 lr 0.000610	time 1.9382 (2.2085)	loss 3.3656 (3.6283)	grad_norm 1.2547 (1.3784)	
[2022-01-21 17:49:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][850/1251]	eta 0:14:45 lr 0.000610	time 2.8097 (2.2095)	loss 3.8058 (3.6267)	grad_norm 1.1716 (1.3778)	
[2022-01-21 17:49:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][860/1251]	eta 0:14:24 lr 0.000610	time 2.2809 (2.2098)	loss 4.0438 (3.6298)	grad_norm 1.3033 (1.3785)	
[2022-01-21 17:49:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][870/1251]	eta 0:14:01 lr 0.000609	time 1.8123 (2.2078)	loss 2.5102 (3.6281)	grad_norm 1.4288 (1.3790)	
[2022-01-21 17:50:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][880/1251]	eta 0:13:38 lr 0.000609	time 1.9458 (2.2058)	loss 2.8438 (3.6274)	grad_norm 1.2893 (1.3798)	
[2022-01-21 17:50:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][890/1251]	eta 0:13:16 lr 0.000609	time 2.6218 (2.2060)	loss 3.6357 (3.6292)	grad_norm 1.3548 (1.3794)	
[2022-01-21 17:50:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][900/1251]	eta 0:12:53 lr 0.000609	time 1.9579 (2.2036)	loss 3.5720 (3.6328)	grad_norm 1.2410 (1.3792)	
[2022-01-21 17:51:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][910/1251]	eta 0:12:31 lr 0.000609	time 2.1333 (2.2037)	loss 3.6042 (3.6341)	grad_norm 1.4358 (1.3788)	
[2022-01-21 17:51:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][920/1251]	eta 0:12:09 lr 0.000609	time 2.2123 (2.2040)	loss 3.6903 (3.6334)	grad_norm 1.5238 (1.3790)	
[2022-01-21 17:51:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][930/1251]	eta 0:11:47 lr 0.000609	time 1.8759 (2.2047)	loss 4.1644 (3.6356)	grad_norm 1.3655 (1.3786)	
[2022-01-21 17:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][940/1251]	eta 0:11:25 lr 0.000609	time 2.2598 (2.2043)	loss 3.2560 (3.6362)	grad_norm 1.3410 (1.3797)	
[2022-01-21 17:52:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][950/1251]	eta 0:11:03 lr 0.000609	time 2.4020 (2.2057)	loss 2.4459 (3.6342)	grad_norm 1.2832 (1.3801)	
[2022-01-21 17:53:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][960/1251]	eta 0:10:41 lr 0.000609	time 1.8712 (2.2059)	loss 3.9128 (3.6336)	grad_norm 1.1898 (1.3801)	
[2022-01-21 17:53:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][970/1251]	eta 0:10:19 lr 0.000609	time 1.9889 (2.2044)	loss 3.8958 (3.6338)	grad_norm 1.3603 (1.3802)	
[2022-01-21 17:53:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][980/1251]	eta 0:09:57 lr 0.000609	time 2.4067 (2.2043)	loss 3.4991 (3.6332)	grad_norm 1.4427 (1.3808)	
[2022-01-21 17:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][990/1251]	eta 0:09:35 lr 0.000609	time 1.7809 (2.2041)	loss 2.2918 (3.6339)	grad_norm 1.1667 (1.3805)	
[2022-01-21 17:54:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1000/1251]	eta 0:09:12 lr 0.000609	time 2.2591 (2.2030)	loss 3.6620 (3.6330)	grad_norm 1.5188 (1.3809)	
[2022-01-21 17:54:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1010/1251]	eta 0:08:50 lr 0.000609	time 1.6928 (2.2021)	loss 4.0564 (3.6346)	grad_norm 1.3131 (1.3817)	
[2022-01-21 17:55:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1020/1251]	eta 0:08:28 lr 0.000609	time 2.0993 (2.2014)	loss 4.4260 (3.6382)	grad_norm 1.2911 (1.3821)	
[2022-01-21 17:55:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1030/1251]	eta 0:08:06 lr 0.000609	time 2.1424 (2.2010)	loss 3.3479 (3.6404)	grad_norm 1.5586 (1.3823)	
[2022-01-21 17:55:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1040/1251]	eta 0:07:44 lr 0.000609	time 1.8672 (2.2001)	loss 3.1169 (3.6386)	grad_norm 1.4054 (1.3822)	
[2022-01-21 17:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1050/1251]	eta 0:07:22 lr 0.000609	time 2.1639 (2.1993)	loss 3.7222 (3.6393)	grad_norm 1.3410 (1.3820)	
[2022-01-21 17:56:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1060/1251]	eta 0:06:59 lr 0.000609	time 2.1509 (2.1989)	loss 3.9228 (3.6393)	grad_norm 1.2760 (1.3818)	
[2022-01-21 17:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1070/1251]	eta 0:06:38 lr 0.000609	time 1.9163 (2.1995)	loss 4.4499 (3.6426)	grad_norm 1.2536 (1.3812)	
[2022-01-21 17:57:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1080/1251]	eta 0:06:16 lr 0.000609	time 1.8464 (2.1989)	loss 3.9064 (3.6403)	grad_norm 1.3369 (1.3814)	
[2022-01-21 17:57:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1090/1251]	eta 0:05:53 lr 0.000609	time 2.2172 (2.1984)	loss 3.2326 (3.6382)	grad_norm 1.4237 (1.3812)	
[2022-01-21 17:58:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1100/1251]	eta 0:05:32 lr 0.000609	time 2.7724 (2.1991)	loss 4.0531 (3.6389)	grad_norm 1.6145 (1.3814)	
[2022-01-21 17:58:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1110/1251]	eta 0:05:10 lr 0.000608	time 1.7085 (2.1993)	loss 2.6842 (3.6388)	grad_norm 1.5453 (1.3815)	
[2022-01-21 17:58:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1120/1251]	eta 0:04:47 lr 0.000608	time 1.8367 (2.1983)	loss 3.8217 (3.6379)	grad_norm 1.2781 (1.3813)	
[2022-01-21 17:59:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1130/1251]	eta 0:04:25 lr 0.000608	time 1.9089 (2.1979)	loss 3.5722 (3.6368)	grad_norm 1.6128 (1.3810)	
[2022-01-21 17:59:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1140/1251]	eta 0:04:03 lr 0.000608	time 2.4786 (2.1972)	loss 2.6750 (3.6335)	grad_norm 1.4278 (1.3810)	
[2022-01-21 17:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1150/1251]	eta 0:03:41 lr 0.000608	time 1.9745 (2.1965)	loss 2.4242 (3.6317)	grad_norm 1.9364 (1.3819)	
[2022-01-21 18:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1160/1251]	eta 0:03:19 lr 0.000608	time 1.7570 (2.1976)	loss 4.0271 (3.6315)	grad_norm 1.4204 (1.3831)	
[2022-01-21 18:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1170/1251]	eta 0:02:58 lr 0.000608	time 1.8729 (2.1979)	loss 3.4284 (3.6319)	grad_norm 1.7418 (1.3837)	
[2022-01-21 18:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1180/1251]	eta 0:02:36 lr 0.000608	time 3.4915 (2.1995)	loss 3.9705 (3.6316)	grad_norm 1.5039 (1.3844)	
[2022-01-21 18:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1190/1251]	eta 0:02:14 lr 0.000608	time 1.7484 (2.2005)	loss 3.8616 (3.6343)	grad_norm 1.2553 (1.3837)	
[2022-01-21 18:01:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1200/1251]	eta 0:01:52 lr 0.000608	time 1.9212 (2.2009)	loss 3.7974 (3.6353)	grad_norm 1.3346 (1.3832)	
[2022-01-21 18:02:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1210/1251]	eta 0:01:30 lr 0.000608	time 1.6507 (2.2003)	loss 3.5809 (3.6341)	grad_norm 1.1297 (1.3830)	
[2022-01-21 18:02:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1220/1251]	eta 0:01:08 lr 0.000608	time 2.5038 (2.1989)	loss 3.8637 (3.6329)	grad_norm 1.2435 (1.3836)	
[2022-01-21 18:02:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1230/1251]	eta 0:00:46 lr 0.000608	time 1.8784 (2.1975)	loss 2.4830 (3.6331)	grad_norm 1.7089 (1.3840)	
[2022-01-21 18:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1240/1251]	eta 0:00:24 lr 0.000608	time 1.6021 (2.1962)	loss 3.7985 (3.6330)	grad_norm 1.2907 (1.3846)	
[2022-01-21 18:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [129/300][1250/1251]	eta 0:00:02 lr 0.000608	time 1.1568 (2.1912)	loss 3.5060 (3.6340)	grad_norm 1.3758 (1.3844)	
[2022-01-21 18:03:27 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 129 training takes 0:45:41
[2022-01-21 18:03:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.617 (18.617)	Loss 1.0534 (1.0534)	Acc@1 75.000 (75.000)	Acc@5 92.969 (92.969)	
[2022-01-21 18:04:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.048 (3.605)	Loss 1.1095 (1.0427)	Acc@1 74.414 (75.062)	Acc@5 92.383 (92.889)	
[2022-01-21 18:04:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.961 (2.657)	Loss 1.0368 (1.0404)	Acc@1 75.391 (75.051)	Acc@5 93.848 (92.992)	
[2022-01-21 18:04:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.599 (2.250)	Loss 0.9773 (1.0330)	Acc@1 76.953 (75.302)	Acc@5 93.359 (92.975)	
[2022-01-21 18:04:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.600 (2.130)	Loss 1.1184 (1.0386)	Acc@1 73.340 (75.176)	Acc@5 92.188 (92.933)	
[2022-01-21 18:05:02 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.162 Acc@5 92.884
[2022-01-21 18:05:02 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.2%
[2022-01-21 18:05:02 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.16%
[2022-01-21 18:05:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][0/1251]	eta 7:36:34 lr 0.000608	time 21.8984 (21.8984)	loss 3.7832 (3.7832)	grad_norm 1.3110 (1.3110)	
[2022-01-21 18:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][10/1251]	eta 1:25:39 lr 0.000608	time 2.4482 (4.1413)	loss 3.8099 (3.5681)	grad_norm 1.4619 (1.3442)	
[2022-01-21 18:06:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][20/1251]	eta 1:07:42 lr 0.000608	time 2.1682 (3.3001)	loss 3.9611 (3.6740)	grad_norm 1.4287 (1.3565)	
[2022-01-21 18:06:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][30/1251]	eta 0:59:56 lr 0.000608	time 1.8371 (2.9454)	loss 3.9759 (3.7611)	grad_norm 1.3407 (1.3727)	
[2022-01-21 18:06:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][40/1251]	eta 0:56:10 lr 0.000608	time 2.7720 (2.7832)	loss 4.2568 (3.7888)	grad_norm 1.2636 (1.4152)	
[2022-01-21 18:07:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][50/1251]	eta 0:53:48 lr 0.000608	time 2.4331 (2.6880)	loss 2.2982 (3.7771)	grad_norm 1.5283 (1.4273)	
[2022-01-21 18:07:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][60/1251]	eta 0:50:59 lr 0.000608	time 1.9363 (2.5691)	loss 3.3798 (3.7789)	grad_norm 1.3731 (1.4178)	
[2022-01-21 18:07:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][70/1251]	eta 0:49:09 lr 0.000608	time 1.9540 (2.4977)	loss 3.6409 (3.7472)	grad_norm 1.5102 (1.4335)	
[2022-01-21 18:08:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][80/1251]	eta 0:47:55 lr 0.000608	time 2.1458 (2.4554)	loss 3.9379 (3.7213)	grad_norm 1.6236 (1.4236)	
[2022-01-21 18:08:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][90/1251]	eta 0:47:13 lr 0.000608	time 3.3440 (2.4405)	loss 3.2887 (3.7290)	grad_norm 1.3472 (1.4143)	
[2022-01-21 18:09:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][100/1251]	eta 0:46:23 lr 0.000608	time 1.8703 (2.4184)	loss 3.0975 (3.6628)	grad_norm 1.3963 (1.4123)	
[2022-01-21 18:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][110/1251]	eta 0:45:26 lr 0.000607	time 1.8487 (2.3900)	loss 4.0242 (3.6626)	grad_norm 1.2528 (1.4092)	
[2022-01-21 18:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][120/1251]	eta 0:44:45 lr 0.000607	time 2.0242 (2.3744)	loss 3.9128 (3.6624)	grad_norm 1.3964 (1.4094)	
[2022-01-21 18:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][130/1251]	eta 0:44:09 lr 0.000607	time 2.8841 (2.3638)	loss 4.2233 (3.6648)	grad_norm 1.4276 (1.4120)	
[2022-01-21 18:10:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][140/1251]	eta 0:43:31 lr 0.000607	time 1.8883 (2.3507)	loss 3.0342 (3.6434)	grad_norm 1.4485 (1.4062)	
[2022-01-21 18:10:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][150/1251]	eta 0:42:48 lr 0.000607	time 2.1986 (2.3330)	loss 3.7956 (3.6622)	grad_norm 1.2190 (1.4039)	
[2022-01-21 18:11:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][160/1251]	eta 0:42:09 lr 0.000607	time 1.8016 (2.3186)	loss 4.0219 (3.6664)	grad_norm 1.7045 (1.4041)	
[2022-01-21 18:11:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][170/1251]	eta 0:41:26 lr 0.000607	time 1.8643 (2.2998)	loss 4.4026 (3.6752)	grad_norm 1.5110 (1.4048)	
[2022-01-21 18:11:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][180/1251]	eta 0:40:51 lr 0.000607	time 2.1248 (2.2890)	loss 2.8213 (3.6737)	grad_norm 1.3150 (1.4028)	
[2022-01-21 18:12:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][190/1251]	eta 0:40:19 lr 0.000607	time 2.4912 (2.2806)	loss 4.2695 (3.6834)	grad_norm 1.3015 (1.4019)	
[2022-01-21 18:12:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][200/1251]	eta 0:40:03 lr 0.000607	time 1.8108 (2.2867)	loss 4.0103 (3.6737)	grad_norm 1.3389 (1.3979)	
[2022-01-21 18:13:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][210/1251]	eta 0:39:36 lr 0.000607	time 2.2622 (2.2825)	loss 2.9143 (3.6691)	grad_norm 1.3622 (1.3965)	
[2022-01-21 18:13:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][220/1251]	eta 0:39:13 lr 0.000607	time 2.7701 (2.2827)	loss 3.8802 (3.6832)	grad_norm 1.4703 (1.3944)	
[2022-01-21 18:13:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][230/1251]	eta 0:38:38 lr 0.000607	time 1.9089 (2.2713)	loss 4.3796 (3.6842)	grad_norm 1.2533 (1.3984)	
[2022-01-21 18:14:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][240/1251]	eta 0:38:13 lr 0.000607	time 2.3040 (2.2686)	loss 4.0903 (3.6597)	grad_norm 1.7691 (1.3990)	
[2022-01-21 18:14:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][250/1251]	eta 0:37:48 lr 0.000607	time 1.6805 (2.2661)	loss 2.0902 (3.6446)	grad_norm 1.4881 (1.4000)	
[2022-01-21 18:14:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][260/1251]	eta 0:37:28 lr 0.000607	time 2.1494 (2.2690)	loss 2.9870 (3.6396)	grad_norm 1.3713 (1.4007)	
[2022-01-21 18:15:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][270/1251]	eta 0:37:04 lr 0.000607	time 1.8196 (2.2675)	loss 4.2608 (3.6469)	grad_norm 1.3145 (1.3980)	
[2022-01-21 18:15:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][280/1251]	eta 0:36:38 lr 0.000607	time 1.6797 (2.2639)	loss 4.2852 (3.6565)	grad_norm 1.3318 (1.3950)	
[2022-01-21 18:15:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][290/1251]	eta 0:36:08 lr 0.000607	time 1.9966 (2.2569)	loss 4.1332 (3.6650)	grad_norm 1.7579 (1.3940)	
[2022-01-21 18:16:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][300/1251]	eta 0:35:42 lr 0.000607	time 2.1749 (2.2526)	loss 4.5085 (3.6710)	grad_norm 1.2914 (1.3932)	
[2022-01-21 18:16:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][310/1251]	eta 0:35:12 lr 0.000607	time 1.8915 (2.2452)	loss 3.2468 (3.6765)	grad_norm 1.2578 (1.3902)	
[2022-01-21 18:17:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][320/1251]	eta 0:34:46 lr 0.000607	time 2.2703 (2.2407)	loss 3.7800 (3.6737)	grad_norm 1.1537 (1.3875)	
[2022-01-21 18:17:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][330/1251]	eta 0:34:19 lr 0.000607	time 1.9213 (2.2364)	loss 4.4612 (3.6713)	grad_norm 1.3080 (1.3845)	
[2022-01-21 18:17:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][340/1251]	eta 0:33:56 lr 0.000607	time 1.4292 (2.2350)	loss 2.8562 (3.6610)	grad_norm 1.3841 (1.3838)	
[2022-01-21 18:18:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][350/1251]	eta 0:33:34 lr 0.000606	time 1.9489 (2.2356)	loss 3.4290 (3.6539)	grad_norm 1.5060 (1.3845)	
[2022-01-21 18:18:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][360/1251]	eta 0:33:13 lr 0.000606	time 2.1481 (2.2369)	loss 3.6809 (3.6535)	grad_norm 1.3353 (1.3854)	
[2022-01-21 18:18:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][370/1251]	eta 0:32:53 lr 0.000606	time 1.7610 (2.2404)	loss 3.8716 (3.6582)	grad_norm 1.4161 (1.3860)	
[2022-01-21 18:19:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][380/1251]	eta 0:32:30 lr 0.000606	time 2.0588 (2.2397)	loss 4.2430 (3.6588)	grad_norm 1.4472 (1.3872)	
[2022-01-21 18:19:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][390/1251]	eta 0:32:04 lr 0.000606	time 1.8725 (2.2354)	loss 4.1128 (3.6574)	grad_norm 1.4128 (1.3904)	
[2022-01-21 18:19:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][400/1251]	eta 0:31:42 lr 0.000606	time 1.9129 (2.2352)	loss 3.5389 (3.6580)	grad_norm 1.2599 (1.3914)	
[2022-01-21 18:20:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][410/1251]	eta 0:31:21 lr 0.000606	time 2.1537 (2.2368)	loss 4.0578 (3.6549)	grad_norm 1.2957 (1.3903)	
[2022-01-21 18:20:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][420/1251]	eta 0:30:58 lr 0.000606	time 2.1060 (2.2363)	loss 3.7794 (3.6538)	grad_norm 1.3583 (1.3891)	
[2022-01-21 18:21:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][430/1251]	eta 0:30:33 lr 0.000606	time 1.5884 (2.2329)	loss 2.6002 (3.6589)	grad_norm 1.3178 (1.3889)	
[2022-01-21 18:21:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][440/1251]	eta 0:30:08 lr 0.000606	time 1.5049 (2.2297)	loss 4.3283 (3.6575)	grad_norm 1.7112 (1.3907)	
[2022-01-21 18:21:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][450/1251]	eta 0:29:46 lr 0.000606	time 1.9516 (2.2308)	loss 3.4318 (3.6594)	grad_norm 1.2733 (1.3900)	
[2022-01-21 18:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][460/1251]	eta 0:29:21 lr 0.000606	time 1.5921 (2.2273)	loss 2.7385 (3.6554)	grad_norm 1.4932 (1.3887)	
[2022-01-21 18:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][470/1251]	eta 0:28:59 lr 0.000606	time 2.3003 (2.2271)	loss 3.2641 (3.6577)	grad_norm 1.2004 (1.3878)	
[2022-01-21 18:22:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][480/1251]	eta 0:28:35 lr 0.000606	time 1.5389 (2.2256)	loss 3.3132 (3.6565)	grad_norm 1.9380 (1.3872)	
[2022-01-21 18:23:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][490/1251]	eta 0:28:15 lr 0.000606	time 2.1909 (2.2281)	loss 3.4552 (3.6582)	grad_norm 1.5915 (1.3877)	
[2022-01-21 18:23:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][500/1251]	eta 0:27:53 lr 0.000606	time 1.9190 (2.2278)	loss 4.1409 (3.6575)	grad_norm 1.1981 (1.3874)	
[2022-01-21 18:23:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][510/1251]	eta 0:27:28 lr 0.000606	time 2.5309 (2.2249)	loss 3.7155 (3.6581)	grad_norm 1.3368 (1.3863)	
[2022-01-21 18:24:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][520/1251]	eta 0:27:04 lr 0.000606	time 1.7315 (2.2218)	loss 4.0064 (3.6595)	grad_norm 1.4616 (1.3871)	
[2022-01-21 18:24:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][530/1251]	eta 0:26:42 lr 0.000606	time 1.8584 (2.2221)	loss 3.7689 (3.6600)	grad_norm 1.2832 (1.3866)	
[2022-01-21 18:25:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][540/1251]	eta 0:26:19 lr 0.000606	time 3.0259 (2.2213)	loss 4.2681 (3.6546)	grad_norm 1.4348 (1.3861)	
[2022-01-21 18:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][550/1251]	eta 0:25:57 lr 0.000606	time 2.4437 (2.2223)	loss 3.6637 (3.6574)	grad_norm 1.2963 (1.3846)	
[2022-01-21 18:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][560/1251]	eta 0:25:34 lr 0.000606	time 2.4208 (2.2211)	loss 3.7918 (3.6581)	grad_norm 1.3531 (1.3858)	
[2022-01-21 18:26:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][570/1251]	eta 0:25:11 lr 0.000606	time 2.2448 (2.2194)	loss 3.7544 (3.6596)	grad_norm 1.7994 (1.3870)	
[2022-01-21 18:26:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][580/1251]	eta 0:24:47 lr 0.000606	time 2.8765 (2.2164)	loss 2.4453 (3.6559)	grad_norm 1.4687 (1.3874)	
[2022-01-21 18:26:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][590/1251]	eta 0:24:24 lr 0.000606	time 2.2597 (2.2158)	loss 3.1520 (3.6599)	grad_norm 1.2435 (1.3877)	
[2022-01-21 18:27:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][600/1251]	eta 0:24:02 lr 0.000605	time 2.1707 (2.2155)	loss 3.5248 (3.6546)	grad_norm 1.2769 (1.3879)	
[2022-01-21 18:27:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][610/1251]	eta 0:23:40 lr 0.000605	time 2.1564 (2.2166)	loss 2.8528 (3.6535)	grad_norm 1.6320 (1.3877)	
[2022-01-21 18:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][620/1251]	eta 0:23:19 lr 0.000605	time 2.6668 (2.2173)	loss 3.0802 (3.6473)	grad_norm 1.3480 (1.3873)	
[2022-01-21 18:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][630/1251]	eta 0:22:55 lr 0.000605	time 1.7473 (2.2154)	loss 4.4091 (3.6484)	grad_norm 1.5611 (1.3874)	
[2022-01-21 18:28:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][640/1251]	eta 0:22:32 lr 0.000605	time 1.9693 (2.2130)	loss 4.0515 (3.6470)	grad_norm 1.1652 (1.3862)	
[2022-01-21 18:29:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][650/1251]	eta 0:22:08 lr 0.000605	time 1.8365 (2.2100)	loss 3.4926 (3.6449)	grad_norm 1.2398 (1.3853)	
[2022-01-21 18:29:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][660/1251]	eta 0:21:46 lr 0.000605	time 2.1849 (2.2106)	loss 2.5359 (3.6423)	grad_norm 1.2242 (1.3846)	
[2022-01-21 18:29:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][670/1251]	eta 0:21:23 lr 0.000605	time 1.8807 (2.2098)	loss 4.0096 (3.6386)	grad_norm 1.3404 (1.3844)	
[2022-01-21 18:30:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][680/1251]	eta 0:21:01 lr 0.000605	time 2.1165 (2.2096)	loss 4.1787 (3.6431)	grad_norm 1.5138 (1.3845)	
[2022-01-21 18:30:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][690/1251]	eta 0:20:40 lr 0.000605	time 1.9289 (2.2109)	loss 3.7102 (3.6420)	grad_norm 1.3627 (1.3837)	
[2022-01-21 18:30:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][700/1251]	eta 0:20:17 lr 0.000605	time 1.6677 (2.2104)	loss 3.9326 (3.6402)	grad_norm 1.2471 (1.3824)	
[2022-01-21 18:31:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][710/1251]	eta 0:19:56 lr 0.000605	time 1.7524 (2.2108)	loss 3.6495 (3.6411)	grad_norm 1.2902 (1.3826)	
[2022-01-21 18:31:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][720/1251]	eta 0:19:33 lr 0.000605	time 1.6450 (2.2099)	loss 3.7881 (3.6418)	grad_norm 1.7171 (1.3831)	
[2022-01-21 18:31:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][730/1251]	eta 0:19:11 lr 0.000605	time 2.0929 (2.2093)	loss 3.0531 (3.6436)	grad_norm 1.4117 (1.3835)	
[2022-01-21 18:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][740/1251]	eta 0:18:48 lr 0.000605	time 1.8791 (2.2077)	loss 4.1409 (3.6443)	grad_norm 1.1842 (1.3839)	
[2022-01-21 18:32:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][750/1251]	eta 0:18:26 lr 0.000605	time 3.1059 (2.2091)	loss 4.0114 (3.6450)	grad_norm 1.3119 (1.3840)	
[2022-01-21 18:33:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][760/1251]	eta 0:18:05 lr 0.000605	time 1.8413 (2.2100)	loss 3.4996 (3.6473)	grad_norm 1.7106 (1.3852)	
[2022-01-21 18:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][770/1251]	eta 0:17:42 lr 0.000605	time 1.6696 (2.2082)	loss 2.9656 (3.6423)	grad_norm 1.4439 (1.3848)	
[2022-01-21 18:33:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][780/1251]	eta 0:17:19 lr 0.000605	time 1.8611 (2.2061)	loss 3.0087 (3.6462)	grad_norm 1.4003 (1.3853)	
[2022-01-21 18:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][790/1251]	eta 0:16:58 lr 0.000605	time 2.5021 (2.2083)	loss 2.7942 (3.6426)	grad_norm 1.5184 (1.3866)	
[2022-01-21 18:34:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][800/1251]	eta 0:16:36 lr 0.000605	time 1.9439 (2.2085)	loss 4.2440 (3.6427)	grad_norm 1.4397 (1.3878)	
[2022-01-21 18:34:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][810/1251]	eta 0:16:13 lr 0.000605	time 1.6146 (2.2066)	loss 3.8969 (3.6401)	grad_norm 1.4869 (1.3877)	
[2022-01-21 18:35:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][820/1251]	eta 0:15:50 lr 0.000605	time 2.0516 (2.2043)	loss 3.7547 (3.6337)	grad_norm 1.4053 (1.3888)	
[2022-01-21 18:35:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][830/1251]	eta 0:15:27 lr 0.000605	time 1.9775 (2.2041)	loss 4.2185 (3.6326)	grad_norm 1.2984 (1.3884)	
[2022-01-21 18:35:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][840/1251]	eta 0:15:05 lr 0.000605	time 2.0341 (2.2042)	loss 3.9053 (3.6369)	grad_norm 1.2041 (1.3880)	
[2022-01-21 18:36:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][850/1251]	eta 0:14:43 lr 0.000604	time 1.8806 (2.2034)	loss 2.5866 (3.6365)	grad_norm 1.3768 (1.3871)	
[2022-01-21 18:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][860/1251]	eta 0:14:21 lr 0.000604	time 1.8051 (2.2034)	loss 4.2135 (3.6374)	grad_norm 1.3719 (1.3872)	
[2022-01-21 18:37:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][870/1251]	eta 0:13:59 lr 0.000604	time 2.5253 (2.2038)	loss 4.3794 (3.6406)	grad_norm 1.5525 (1.3868)	
[2022-01-21 18:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][880/1251]	eta 0:13:37 lr 0.000604	time 2.8422 (2.2039)	loss 3.6525 (3.6393)	grad_norm 1.4704 (1.3869)	
[2022-01-21 18:37:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][890/1251]	eta 0:13:15 lr 0.000604	time 1.8416 (2.2030)	loss 4.3990 (3.6411)	grad_norm 1.3891 (1.3867)	
[2022-01-21 18:38:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][900/1251]	eta 0:12:52 lr 0.000604	time 1.8667 (2.2021)	loss 3.4875 (3.6438)	grad_norm 1.3580 (1.3870)	
[2022-01-21 18:38:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][910/1251]	eta 0:12:30 lr 0.000604	time 1.9290 (2.2009)	loss 4.3924 (3.6477)	grad_norm 1.3170 (1.3867)	
[2022-01-21 18:38:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][920/1251]	eta 0:12:08 lr 0.000604	time 1.9413 (2.2001)	loss 4.2257 (3.6478)	grad_norm 1.3025 (1.3872)	
[2022-01-21 18:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][930/1251]	eta 0:11:45 lr 0.000604	time 1.6454 (2.1990)	loss 3.7969 (3.6472)	grad_norm 1.3316 (1.3873)	
[2022-01-21 18:39:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][940/1251]	eta 0:11:23 lr 0.000604	time 1.9507 (2.1962)	loss 2.4968 (3.6471)	grad_norm 1.6040 (1.3875)	
[2022-01-21 18:39:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][950/1251]	eta 0:11:01 lr 0.000604	time 1.9754 (2.1964)	loss 4.3566 (3.6489)	grad_norm 1.3455 (1.3882)	
[2022-01-21 18:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][960/1251]	eta 0:10:39 lr 0.000604	time 2.1436 (2.1976)	loss 3.4465 (3.6508)	grad_norm 1.3812 (1.3876)	
[2022-01-21 18:40:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][970/1251]	eta 0:10:18 lr 0.000604	time 2.5974 (2.1994)	loss 3.5016 (3.6520)	grad_norm 1.4452 (1.3879)	
[2022-01-21 18:40:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][980/1251]	eta 0:09:55 lr 0.000604	time 2.0772 (2.1990)	loss 3.8916 (3.6517)	grad_norm 1.3304 (1.3874)	
[2022-01-21 18:41:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][990/1251]	eta 0:09:34 lr 0.000604	time 2.2443 (2.2002)	loss 3.8896 (3.6513)	grad_norm 1.2713 (1.3866)	
[2022-01-21 18:41:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1000/1251]	eta 0:09:12 lr 0.000604	time 2.7966 (2.2025)	loss 3.8038 (3.6514)	grad_norm 1.2320 (1.3863)	
[2022-01-21 18:42:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1010/1251]	eta 0:08:50 lr 0.000604	time 1.8864 (2.2032)	loss 2.9243 (3.6522)	grad_norm 1.5281 (1.3870)	
[2022-01-21 18:42:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1020/1251]	eta 0:08:28 lr 0.000604	time 1.6109 (2.2029)	loss 2.5810 (3.6528)	grad_norm 1.3671 (1.3872)	
[2022-01-21 18:42:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1030/1251]	eta 0:08:06 lr 0.000604	time 1.9261 (2.2011)	loss 3.9186 (3.6499)	grad_norm 1.6077 (1.3879)	
[2022-01-21 18:43:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1040/1251]	eta 0:07:43 lr 0.000604	time 1.9711 (2.1984)	loss 2.7396 (3.6490)	grad_norm 1.3254 (1.3871)	
[2022-01-21 18:43:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1050/1251]	eta 0:07:21 lr 0.000604	time 1.9992 (2.1985)	loss 3.7544 (3.6491)	grad_norm 1.6723 (1.3873)	
[2022-01-21 18:43:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1060/1251]	eta 0:07:00 lr 0.000604	time 2.1019 (2.1991)	loss 3.8784 (3.6486)	grad_norm 1.8234 (1.3880)	
[2022-01-21 18:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1070/1251]	eta 0:06:38 lr 0.000604	time 2.0110 (2.2004)	loss 2.5848 (3.6459)	grad_norm 1.4192 (1.3880)	
[2022-01-21 18:44:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1080/1251]	eta 0:06:16 lr 0.000604	time 2.2291 (2.2006)	loss 3.7837 (3.6471)	grad_norm 1.3659 (1.3872)	
[2022-01-21 18:45:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1090/1251]	eta 0:05:54 lr 0.000603	time 2.3204 (2.2011)	loss 3.6230 (3.6461)	grad_norm 1.3488 (1.3864)	
[2022-01-21 18:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1100/1251]	eta 0:05:32 lr 0.000603	time 1.6682 (2.2001)	loss 3.7613 (3.6462)	grad_norm 1.5529 (1.3866)	
[2022-01-21 18:45:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1110/1251]	eta 0:05:10 lr 0.000603	time 2.3754 (2.2005)	loss 3.7581 (3.6470)	grad_norm 1.3801 (1.3862)	
[2022-01-21 18:46:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1120/1251]	eta 0:04:48 lr 0.000603	time 1.6934 (2.1995)	loss 3.9797 (3.6459)	grad_norm 1.4824 (1.3867)	
[2022-01-21 18:46:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1130/1251]	eta 0:04:26 lr 0.000603	time 2.5768 (2.1997)	loss 4.3438 (3.6473)	grad_norm 1.6483 (1.3866)	
[2022-01-21 18:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1140/1251]	eta 0:04:04 lr 0.000603	time 1.7834 (2.1992)	loss 3.9721 (3.6469)	grad_norm 1.5050 (1.3866)	
[2022-01-21 18:47:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1150/1251]	eta 0:03:42 lr 0.000603	time 2.4929 (2.1993)	loss 4.3512 (3.6458)	grad_norm 1.3159 (1.3873)	
[2022-01-21 18:47:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1160/1251]	eta 0:03:20 lr 0.000603	time 1.9004 (2.1995)	loss 4.2172 (3.6460)	grad_norm 1.3669 (1.3883)	
[2022-01-21 18:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1170/1251]	eta 0:02:58 lr 0.000603	time 2.7524 (2.2009)	loss 4.0313 (3.6468)	grad_norm 1.5366 (1.3882)	
[2022-01-21 18:48:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1180/1251]	eta 0:02:36 lr 0.000603	time 2.1885 (2.2003)	loss 3.0777 (3.6467)	grad_norm 1.4440 (1.3887)	
[2022-01-21 18:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1190/1251]	eta 0:02:14 lr 0.000603	time 2.5005 (2.2005)	loss 3.1199 (3.6458)	grad_norm 1.1494 (1.3890)	
[2022-01-21 18:49:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1200/1251]	eta 0:01:52 lr 0.000603	time 1.8624 (2.1985)	loss 4.5213 (3.6493)	grad_norm 1.4153 (1.3887)	
[2022-01-21 18:49:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1210/1251]	eta 0:01:30 lr 0.000603	time 1.8801 (2.1973)	loss 2.4912 (3.6499)	grad_norm 1.1373 (1.3886)	
[2022-01-21 18:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1220/1251]	eta 0:01:08 lr 0.000603	time 2.1885 (2.1972)	loss 3.3477 (3.6499)	grad_norm 1.2916 (1.3885)	
[2022-01-21 18:50:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1230/1251]	eta 0:00:46 lr 0.000603	time 2.1944 (2.1971)	loss 4.1939 (3.6498)	grad_norm 1.3226 (1.3883)	
[2022-01-21 18:50:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1240/1251]	eta 0:00:24 lr 0.000603	time 1.6375 (2.1971)	loss 2.9955 (3.6495)	grad_norm 1.4577 (1.3881)	
[2022-01-21 18:50:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [130/300][1250/1251]	eta 0:00:02 lr 0.000603	time 1.3117 (2.1927)	loss 3.2579 (3.6515)	grad_norm 1.6434 (1.3877)	
[2022-01-21 18:50:45 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 130 training takes 0:45:43
[2022-01-21 18:50:45 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_130 saving......
[2022-01-21 18:50:57 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_130 saved !!!
[2022-01-21 18:51:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 13.200 (13.200)	Loss 1.0646 (1.0646)	Acc@1 76.074 (76.074)	Acc@5 92.773 (92.773)	
[2022-01-21 18:51:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.625 (2.867)	Loss 1.1011 (1.0576)	Acc@1 74.121 (75.027)	Acc@5 92.383 (92.889)	
[2022-01-21 18:51:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.622 (2.164)	Loss 1.0794 (1.0550)	Acc@1 74.609 (74.949)	Acc@5 90.820 (92.885)	
[2022-01-21 18:52:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.995 (2.064)	Loss 1.0468 (1.0540)	Acc@1 74.902 (74.852)	Acc@5 92.871 (92.893)	
[2022-01-21 18:52:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.255 (1.930)	Loss 1.0173 (1.0566)	Acc@1 75.977 (74.793)	Acc@5 92.773 (92.871)	
[2022-01-21 18:52:24 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.964 Acc@5 92.858
[2022-01-21 18:52:24 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.0%
[2022-01-21 18:52:24 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.16%
[2022-01-21 18:52:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][0/1251]	eta 7:21:32 lr 0.000603	time 21.1773 (21.1773)	loss 3.5679 (3.5679)	grad_norm 1.4463 (1.4463)	
[2022-01-21 18:53:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][10/1251]	eta 1:24:44 lr 0.000603	time 2.1026 (4.0968)	loss 3.9503 (3.7554)	grad_norm 1.3785 (1.3749)	
[2022-01-21 18:53:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][20/1251]	eta 1:05:16 lr 0.000603	time 1.5730 (3.1817)	loss 2.8283 (3.5992)	grad_norm 1.3026 (1.3718)	
[2022-01-21 18:53:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][30/1251]	eta 0:57:42 lr 0.000603	time 1.4530 (2.8354)	loss 2.6060 (3.6044)	grad_norm 1.6553 (1.3894)	
[2022-01-21 18:54:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][40/1251]	eta 0:55:47 lr 0.000603	time 5.8746 (2.7645)	loss 4.5210 (3.6800)	grad_norm 1.2355 (1.3887)	
[2022-01-21 18:54:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][50/1251]	eta 0:54:10 lr 0.000603	time 2.4224 (2.7062)	loss 4.3613 (3.6780)	grad_norm 1.4781 (1.3969)	
[2022-01-21 18:55:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][60/1251]	eta 0:51:30 lr 0.000603	time 1.7274 (2.5949)	loss 4.3414 (3.6721)	grad_norm 1.3800 (1.3878)	
[2022-01-21 18:55:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][70/1251]	eta 0:49:56 lr 0.000603	time 1.7136 (2.5377)	loss 3.8459 (3.6075)	grad_norm 1.3851 (1.3870)	
[2022-01-21 18:55:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][80/1251]	eta 0:48:39 lr 0.000603	time 2.6171 (2.4933)	loss 3.8983 (3.6260)	grad_norm 1.2969 (1.3866)	
[2022-01-21 18:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][90/1251]	eta 0:47:19 lr 0.000602	time 1.7612 (2.4460)	loss 4.0609 (3.6336)	grad_norm 1.1969 (1.3895)	
[2022-01-21 18:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][100/1251]	eta 0:46:02 lr 0.000602	time 1.8295 (2.4004)	loss 3.8844 (3.6317)	grad_norm 1.6086 (1.3937)	
[2022-01-21 18:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][110/1251]	eta 0:45:05 lr 0.000602	time 2.1675 (2.3715)	loss 3.9184 (3.6483)	grad_norm 1.3429 (1.3870)	
[2022-01-21 18:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][120/1251]	eta 0:44:22 lr 0.000602	time 1.8706 (2.3540)	loss 3.6992 (3.6487)	grad_norm 1.5465 (1.3878)	
[2022-01-21 18:57:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][130/1251]	eta 0:43:59 lr 0.000602	time 2.4899 (2.3548)	loss 3.8158 (3.6220)	grad_norm 1.7635 (1.3888)	
[2022-01-21 18:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][140/1251]	eta 0:43:15 lr 0.000602	time 2.1661 (2.3366)	loss 4.4498 (3.6196)	grad_norm 1.4096 (1.3906)	
[2022-01-21 18:58:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][150/1251]	eta 0:42:54 lr 0.000602	time 2.4815 (2.3384)	loss 3.8057 (3.6086)	grad_norm 1.2483 (1.3901)	
[2022-01-21 18:58:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][160/1251]	eta 0:42:21 lr 0.000602	time 2.0652 (2.3297)	loss 2.9010 (3.6012)	grad_norm 1.2101 (1.3929)	
[2022-01-21 18:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][170/1251]	eta 0:41:46 lr 0.000602	time 1.6643 (2.3185)	loss 3.6193 (3.6046)	grad_norm 1.3924 (1.3919)	
[2022-01-21 18:59:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][180/1251]	eta 0:41:03 lr 0.000602	time 1.6120 (2.3002)	loss 4.6148 (3.5991)	grad_norm 1.4033 (1.3878)	
[2022-01-21 18:59:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][190/1251]	eta 0:40:33 lr 0.000602	time 2.2857 (2.2934)	loss 3.5109 (3.6070)	grad_norm 1.3378 (1.3870)	
[2022-01-21 19:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][200/1251]	eta 0:40:04 lr 0.000602	time 1.9638 (2.2882)	loss 2.9993 (3.6039)	grad_norm 1.2360 (1.3875)	
[2022-01-21 19:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][210/1251]	eta 0:39:38 lr 0.000602	time 1.9244 (2.2850)	loss 4.0947 (3.6058)	grad_norm 1.3820 (1.3868)	
[2022-01-21 19:00:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][220/1251]	eta 0:39:08 lr 0.000602	time 1.8687 (2.2774)	loss 3.7057 (3.5975)	grad_norm 1.4862 (1.3854)	
[2022-01-21 19:01:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][230/1251]	eta 0:38:41 lr 0.000602	time 2.3032 (2.2734)	loss 3.7879 (3.5907)	grad_norm 1.5064 (1.3859)	
[2022-01-21 19:01:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][240/1251]	eta 0:38:16 lr 0.000602	time 1.9509 (2.2712)	loss 4.2896 (3.6006)	grad_norm 1.2984 (1.3857)	
[2022-01-21 19:01:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][250/1251]	eta 0:37:53 lr 0.000602	time 2.0252 (2.2715)	loss 3.4114 (3.5949)	grad_norm 1.4765 (1.3899)	
[2022-01-21 19:02:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][260/1251]	eta 0:37:27 lr 0.000602	time 1.9474 (2.2678)	loss 4.0929 (3.6050)	grad_norm 1.1536 (1.3932)	
[2022-01-21 19:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][270/1251]	eta 0:37:05 lr 0.000602	time 2.2208 (2.2683)	loss 3.7274 (3.6032)	grad_norm 1.1972 (1.3936)	
[2022-01-21 19:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][280/1251]	eta 0:36:47 lr 0.000602	time 2.6701 (2.2735)	loss 4.0900 (3.6114)	grad_norm 1.4233 (1.3947)	
[2022-01-21 19:03:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][290/1251]	eta 0:36:21 lr 0.000602	time 2.6213 (2.2699)	loss 3.5289 (3.6179)	grad_norm 1.6118 (1.3955)	
[2022-01-21 19:03:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][300/1251]	eta 0:35:49 lr 0.000602	time 1.6504 (2.2606)	loss 3.5601 (3.6166)	grad_norm 1.4097 (1.3944)	
[2022-01-21 19:04:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][310/1251]	eta 0:35:18 lr 0.000602	time 1.8589 (2.2514)	loss 4.3746 (3.6215)	grad_norm 1.4499 (1.3950)	
[2022-01-21 19:04:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][320/1251]	eta 0:34:51 lr 0.000602	time 2.6420 (2.2468)	loss 3.4426 (3.6141)	grad_norm 1.3202 (1.3950)	
[2022-01-21 19:04:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][330/1251]	eta 0:34:25 lr 0.000601	time 1.5682 (2.2423)	loss 3.5357 (3.6146)	grad_norm 1.2729 (1.3946)	
[2022-01-21 19:05:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][340/1251]	eta 0:34:01 lr 0.000601	time 2.0394 (2.2410)	loss 3.5303 (3.6069)	grad_norm 1.3282 (1.3939)	
[2022-01-21 19:05:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][350/1251]	eta 0:33:39 lr 0.000601	time 1.5722 (2.2410)	loss 4.4660 (3.6092)	grad_norm 1.4760 (1.3929)	
[2022-01-21 19:05:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][360/1251]	eta 0:33:28 lr 0.000601	time 2.7586 (2.2539)	loss 3.6062 (3.6140)	grad_norm 1.3401 (1.3915)	
[2022-01-21 19:06:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][370/1251]	eta 0:33:05 lr 0.000601	time 2.1837 (2.2542)	loss 3.8607 (3.6145)	grad_norm 1.3638 (1.3912)	
[2022-01-21 19:06:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][380/1251]	eta 0:32:40 lr 0.000601	time 2.4626 (2.2508)	loss 3.4699 (3.6094)	grad_norm 1.3678 (1.3925)	
[2022-01-21 19:07:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][390/1251]	eta 0:32:11 lr 0.000601	time 1.5231 (2.2435)	loss 3.6577 (3.6114)	grad_norm 1.4592 (1.3957)	
[2022-01-21 19:07:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][400/1251]	eta 0:31:49 lr 0.000601	time 2.1702 (2.2442)	loss 3.2994 (3.6064)	grad_norm 1.3223 (1.3969)	
[2022-01-21 19:07:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][410/1251]	eta 0:31:23 lr 0.000601	time 1.5364 (2.2400)	loss 3.5997 (3.6064)	grad_norm 1.3800 (1.3969)	
[2022-01-21 19:08:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][420/1251]	eta 0:31:00 lr 0.000601	time 1.8983 (2.2391)	loss 3.9557 (3.6041)	grad_norm 1.2698 (1.3954)	
[2022-01-21 19:08:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][430/1251]	eta 0:30:37 lr 0.000601	time 1.9618 (2.2380)	loss 3.8178 (3.6049)	grad_norm 1.3206 (1.3943)	
[2022-01-21 19:08:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][440/1251]	eta 0:30:18 lr 0.000601	time 2.2271 (2.2419)	loss 3.8412 (3.6060)	grad_norm 1.5814 (1.3943)	
[2022-01-21 19:09:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][450/1251]	eta 0:29:54 lr 0.000601	time 1.6094 (2.2399)	loss 3.6927 (3.5995)	grad_norm 1.3985 (1.3961)	
[2022-01-21 19:09:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][460/1251]	eta 0:29:28 lr 0.000601	time 1.8843 (2.2353)	loss 3.4792 (3.5953)	grad_norm 1.6243 (1.3957)	
[2022-01-21 19:09:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][470/1251]	eta 0:29:04 lr 0.000601	time 2.1676 (2.2335)	loss 3.9814 (3.5955)	grad_norm 1.5206 (1.3970)	
[2022-01-21 19:10:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][480/1251]	eta 0:28:46 lr 0.000601	time 2.3956 (2.2393)	loss 3.7377 (3.5889)	grad_norm 1.2979 (1.3964)	
[2022-01-21 19:10:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][490/1251]	eta 0:28:22 lr 0.000601	time 2.1567 (2.2369)	loss 2.9570 (3.5850)	grad_norm 1.5354 (1.3974)	
[2022-01-21 19:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][500/1251]	eta 0:27:58 lr 0.000601	time 1.9501 (2.2349)	loss 4.3183 (3.5851)	grad_norm 1.2883 (1.3975)	
[2022-01-21 19:11:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][510/1251]	eta 0:27:33 lr 0.000601	time 1.8866 (2.2313)	loss 4.1783 (3.5858)	grad_norm 1.3978 (1.3977)	
[2022-01-21 19:11:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][520/1251]	eta 0:27:09 lr 0.000601	time 1.8133 (2.2294)	loss 3.9455 (3.5870)	grad_norm 1.4102 (1.3998)	
[2022-01-21 19:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][530/1251]	eta 0:26:45 lr 0.000601	time 1.9412 (2.2269)	loss 4.0040 (3.5841)	grad_norm 1.4905 (1.3999)	
[2022-01-21 19:12:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][540/1251]	eta 0:26:19 lr 0.000601	time 1.9622 (2.2215)	loss 4.0470 (3.5855)	grad_norm 1.3618 (1.4016)	
[2022-01-21 19:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][550/1251]	eta 0:25:56 lr 0.000601	time 1.9173 (2.2203)	loss 4.1669 (3.5888)	grad_norm 1.3838 (1.4001)	
[2022-01-21 19:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][560/1251]	eta 0:25:35 lr 0.000601	time 3.0791 (2.2219)	loss 2.5947 (3.5862)	grad_norm 1.1064 (1.4005)	
[2022-01-21 19:13:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][570/1251]	eta 0:25:14 lr 0.000601	time 2.3980 (2.2242)	loss 2.4964 (3.5865)	grad_norm 1.5720 (1.4013)	
[2022-01-21 19:13:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][580/1251]	eta 0:24:51 lr 0.000600	time 1.8968 (2.2235)	loss 4.2501 (3.5924)	grad_norm 1.3964 (1.4002)	
[2022-01-21 19:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][590/1251]	eta 0:24:29 lr 0.000600	time 2.0106 (2.2234)	loss 3.7558 (3.5908)	grad_norm 1.5338 (1.3994)	
[2022-01-21 19:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][600/1251]	eta 0:24:07 lr 0.000600	time 2.5624 (2.2240)	loss 4.0337 (3.5938)	grad_norm 1.4428 (1.4001)	
[2022-01-21 19:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][610/1251]	eta 0:23:44 lr 0.000600	time 2.1840 (2.2228)	loss 2.4685 (3.5946)	grad_norm 1.3621 (1.3998)	
[2022-01-21 19:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][620/1251]	eta 0:23:21 lr 0.000600	time 1.9321 (2.2207)	loss 4.2310 (3.5963)	grad_norm 1.3165 (1.4005)	
[2022-01-21 19:15:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][630/1251]	eta 0:22:57 lr 0.000600	time 1.9010 (2.2177)	loss 3.8299 (3.5943)	grad_norm 1.5016 (1.4013)	
[2022-01-21 19:16:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][640/1251]	eta 0:22:34 lr 0.000600	time 2.7873 (2.2161)	loss 3.1331 (3.5948)	grad_norm 1.1863 (1.3997)	
[2022-01-21 19:16:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][650/1251]	eta 0:22:11 lr 0.000600	time 2.1855 (2.2154)	loss 3.1834 (3.5929)	grad_norm 1.3556 (1.3982)	
[2022-01-21 19:16:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][660/1251]	eta 0:21:47 lr 0.000600	time 2.2337 (2.2128)	loss 3.9026 (3.5944)	grad_norm 1.2852 (1.3973)	
[2022-01-21 19:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][670/1251]	eta 0:21:24 lr 0.000600	time 1.8450 (2.2108)	loss 4.0153 (3.5938)	grad_norm 1.6619 (1.3973)	
[2022-01-21 19:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][680/1251]	eta 0:21:02 lr 0.000600	time 2.2207 (2.2105)	loss 3.6630 (3.5957)	grad_norm 1.3073 (1.3968)	
[2022-01-21 19:17:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][690/1251]	eta 0:20:41 lr 0.000600	time 2.7704 (2.2122)	loss 4.3891 (3.5956)	grad_norm 1.2183 (1.3969)	
[2022-01-21 19:18:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][700/1251]	eta 0:20:19 lr 0.000600	time 2.4403 (2.2124)	loss 3.5534 (3.5964)	grad_norm 1.4195 (1.3960)	
[2022-01-21 19:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][710/1251]	eta 0:19:57 lr 0.000600	time 1.6545 (2.2129)	loss 3.8108 (3.6007)	grad_norm 1.3779 (1.3955)	
[2022-01-21 19:19:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][720/1251]	eta 0:19:35 lr 0.000600	time 2.5145 (2.2131)	loss 4.7000 (3.6018)	grad_norm 1.4318 (1.3949)	
[2022-01-21 19:19:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][730/1251]	eta 0:19:12 lr 0.000600	time 2.1442 (2.2121)	loss 3.1878 (3.5968)	grad_norm 1.2066 (1.3945)	
[2022-01-21 19:19:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][740/1251]	eta 0:18:50 lr 0.000600	time 2.6190 (2.2121)	loss 3.3944 (3.5980)	grad_norm 1.5621 (1.3949)	
[2022-01-21 19:20:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][750/1251]	eta 0:18:28 lr 0.000600	time 2.1083 (2.2127)	loss 2.8731 (3.6007)	grad_norm 1.5272 (1.3965)	
[2022-01-21 19:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][760/1251]	eta 0:18:06 lr 0.000600	time 1.7157 (2.2134)	loss 3.5127 (3.5997)	grad_norm 2.0551 (1.3997)	
[2022-01-21 19:20:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][770/1251]	eta 0:17:44 lr 0.000600	time 1.9217 (2.2123)	loss 3.3373 (3.5949)	grad_norm 1.6010 (1.4003)	
[2022-01-21 19:21:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][780/1251]	eta 0:17:21 lr 0.000600	time 1.9463 (2.2111)	loss 4.3434 (3.5961)	grad_norm 1.3032 (1.4016)	
[2022-01-21 19:21:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][790/1251]	eta 0:16:58 lr 0.000600	time 2.0817 (2.2098)	loss 4.2614 (3.5954)	grad_norm 1.5627 (1.4024)	
[2022-01-21 19:21:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][800/1251]	eta 0:16:36 lr 0.000600	time 1.9658 (2.2103)	loss 3.7347 (3.5975)	grad_norm 1.1881 (1.4013)	
[2022-01-21 19:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][810/1251]	eta 0:16:14 lr 0.000600	time 2.1283 (2.2095)	loss 2.6174 (3.5973)	grad_norm 1.3929 (1.4011)	
[2022-01-21 19:22:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][820/1251]	eta 0:15:51 lr 0.000600	time 1.7498 (2.2088)	loss 3.4660 (3.5995)	grad_norm 1.1704 (1.4014)	
[2022-01-21 19:23:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][830/1251]	eta 0:15:30 lr 0.000599	time 1.8166 (2.2101)	loss 3.7739 (3.6012)	grad_norm 1.2749 (1.4009)	
[2022-01-21 19:23:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][840/1251]	eta 0:15:09 lr 0.000599	time 2.8773 (2.2139)	loss 3.4043 (3.6016)	grad_norm 1.2416 (1.4011)	
[2022-01-21 19:23:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][850/1251]	eta 0:14:47 lr 0.000599	time 1.8309 (2.2126)	loss 4.1310 (3.6029)	grad_norm 1.4756 (1.4011)	
[2022-01-21 19:24:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][860/1251]	eta 0:14:24 lr 0.000599	time 2.4636 (2.2121)	loss 4.0417 (3.6020)	grad_norm 1.3108 (1.4009)	
[2022-01-21 19:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][870/1251]	eta 0:14:01 lr 0.000599	time 1.6205 (2.2098)	loss 3.2678 (3.6023)	grad_norm 1.2942 (1.3996)	
[2022-01-21 19:24:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][880/1251]	eta 0:13:39 lr 0.000599	time 1.9580 (2.2077)	loss 4.6239 (3.6031)	grad_norm 1.4848 (1.3991)	
[2022-01-21 19:25:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][890/1251]	eta 0:13:16 lr 0.000599	time 1.9019 (2.2060)	loss 2.5559 (3.6021)	grad_norm 1.2095 (1.3988)	
[2022-01-21 19:25:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][900/1251]	eta 0:12:54 lr 0.000599	time 2.5443 (2.2059)	loss 4.2446 (3.6034)	grad_norm 1.2637 (1.3986)	
[2022-01-21 19:25:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][910/1251]	eta 0:12:32 lr 0.000599	time 2.7539 (2.2070)	loss 3.6686 (3.6036)	grad_norm 1.6173 (1.3997)	
[2022-01-21 19:26:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][920/1251]	eta 0:12:10 lr 0.000599	time 2.0496 (2.2066)	loss 4.2735 (3.6049)	grad_norm 1.3622 (1.4003)	
[2022-01-21 19:26:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][930/1251]	eta 0:11:47 lr 0.000599	time 1.4961 (2.2045)	loss 3.9871 (3.6033)	grad_norm 1.3084 (1.4003)	
[2022-01-21 19:26:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][940/1251]	eta 0:11:25 lr 0.000599	time 2.3543 (2.2045)	loss 3.2610 (3.6037)	grad_norm 1.4395 (1.4002)	
[2022-01-21 19:27:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][950/1251]	eta 0:11:03 lr 0.000599	time 2.5070 (2.2057)	loss 4.0087 (3.6005)	grad_norm 1.4258 (1.4003)	
[2022-01-21 19:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][960/1251]	eta 0:10:41 lr 0.000599	time 2.2999 (2.2057)	loss 4.4615 (3.6045)	grad_norm 1.3650 (1.4000)	
[2022-01-21 19:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][970/1251]	eta 0:10:20 lr 0.000599	time 1.7174 (2.2068)	loss 3.6778 (3.6017)	grad_norm 1.2785 (1.3992)	
[2022-01-21 19:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][980/1251]	eta 0:09:58 lr 0.000599	time 2.2266 (2.2068)	loss 2.7130 (3.6022)	grad_norm 1.4069 (1.3989)	
[2022-01-21 19:28:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][990/1251]	eta 0:09:35 lr 0.000599	time 1.8428 (2.2050)	loss 3.7323 (3.6004)	grad_norm 1.5605 (1.3986)	
[2022-01-21 19:29:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1000/1251]	eta 0:09:13 lr 0.000599	time 2.8307 (2.2035)	loss 3.1739 (3.5994)	grad_norm 1.3239 (1.3989)	
[2022-01-21 19:29:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1010/1251]	eta 0:08:50 lr 0.000599	time 1.9093 (2.2013)	loss 3.1782 (3.5990)	grad_norm 1.3541 (1.3995)	
[2022-01-21 19:29:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1020/1251]	eta 0:08:28 lr 0.000599	time 2.8668 (2.2008)	loss 3.8561 (3.6005)	grad_norm 1.9749 (1.4004)	
[2022-01-21 19:30:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1030/1251]	eta 0:08:06 lr 0.000599	time 2.0322 (2.2022)	loss 4.1036 (3.6021)	grad_norm 1.3004 (1.4006)	
[2022-01-21 19:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1040/1251]	eta 0:07:45 lr 0.000599	time 2.3242 (2.2038)	loss 3.6301 (3.6028)	grad_norm 1.3374 (1.4013)	
[2022-01-21 19:31:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1050/1251]	eta 0:07:22 lr 0.000599	time 1.7792 (2.2031)	loss 4.0626 (3.6047)	grad_norm 1.7570 (1.4011)	
[2022-01-21 19:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1060/1251]	eta 0:07:00 lr 0.000599	time 3.1747 (2.2035)	loss 4.1481 (3.6060)	grad_norm 1.2646 (1.4003)	
[2022-01-21 19:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1070/1251]	eta 0:06:38 lr 0.000598	time 2.2435 (2.2021)	loss 3.9743 (3.6062)	grad_norm 1.3411 (1.3998)	
[2022-01-21 19:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1080/1251]	eta 0:06:16 lr 0.000598	time 1.8992 (2.2003)	loss 3.6935 (3.6073)	grad_norm 1.4646 (1.4000)	
[2022-01-21 19:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1090/1251]	eta 0:05:53 lr 0.000598	time 1.7917 (2.1985)	loss 3.3335 (3.6061)	grad_norm 1.3619 (1.3993)	
[2022-01-21 19:32:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1100/1251]	eta 0:05:32 lr 0.000598	time 2.5611 (2.1990)	loss 3.9988 (3.6093)	grad_norm 1.3466 (1.3989)	
[2022-01-21 19:33:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1110/1251]	eta 0:05:10 lr 0.000598	time 2.5274 (2.1994)	loss 3.3117 (3.6110)	grad_norm 1.3309 (1.3984)	
[2022-01-21 19:33:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1120/1251]	eta 0:04:48 lr 0.000598	time 2.5728 (2.1987)	loss 3.8047 (3.6127)	grad_norm 1.2272 (1.3979)	
[2022-01-21 19:33:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1130/1251]	eta 0:04:25 lr 0.000598	time 1.5596 (2.1979)	loss 2.9409 (3.6098)	grad_norm 1.3623 (1.3979)	
[2022-01-21 19:34:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1140/1251]	eta 0:04:04 lr 0.000598	time 3.7666 (2.1983)	loss 3.8818 (3.6090)	grad_norm 1.3564 (1.3972)	
[2022-01-21 19:34:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1150/1251]	eta 0:03:42 lr 0.000598	time 2.8709 (2.1989)	loss 3.8145 (3.6088)	grad_norm 1.3411 (1.3970)	
[2022-01-21 19:34:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1160/1251]	eta 0:03:20 lr 0.000598	time 2.4509 (2.1998)	loss 3.9445 (3.6086)	grad_norm 1.3863 (1.3966)	
[2022-01-21 19:35:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1170/1251]	eta 0:02:58 lr 0.000598	time 1.9291 (2.2004)	loss 3.8691 (3.6105)	grad_norm 1.4668 (1.3968)	
[2022-01-21 19:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1180/1251]	eta 0:02:36 lr 0.000598	time 2.6995 (2.2000)	loss 4.0082 (3.6120)	grad_norm 1.7224 (1.3975)	
[2022-01-21 19:36:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1190/1251]	eta 0:02:14 lr 0.000598	time 2.7081 (2.2007)	loss 4.3987 (3.6135)	grad_norm 1.3101 (1.3978)	
[2022-01-21 19:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1200/1251]	eta 0:01:52 lr 0.000598	time 2.7402 (2.2013)	loss 2.8878 (3.6137)	grad_norm 1.2507 (1.3972)	
[2022-01-21 19:36:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1210/1251]	eta 0:01:30 lr 0.000598	time 1.8969 (2.2002)	loss 4.1295 (3.6140)	grad_norm 1.4724 (1.3970)	
[2022-01-21 19:37:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1220/1251]	eta 0:01:08 lr 0.000598	time 2.1258 (2.1997)	loss 4.1731 (3.6142)	grad_norm 1.3547 (1.3967)	
[2022-01-21 19:37:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1230/1251]	eta 0:00:46 lr 0.000598	time 2.0648 (2.1979)	loss 3.7602 (3.6139)	grad_norm 1.3260 (1.3969)	
[2022-01-21 19:37:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1240/1251]	eta 0:00:24 lr 0.000598	time 1.5090 (2.1964)	loss 3.8059 (3.6138)	grad_norm 1.4071 (1.3967)	
[2022-01-21 19:38:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [131/300][1250/1251]	eta 0:00:02 lr 0.000598	time 1.3229 (2.1906)	loss 2.3602 (3.6129)	grad_norm 1.2769 (1.3965)	
[2022-01-21 19:38:05 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 131 training takes 0:45:40
[2022-01-21 19:38:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.889 (18.889)	Loss 1.0969 (1.0969)	Acc@1 75.391 (75.391)	Acc@5 91.797 (91.797)	
[2022-01-21 19:38:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.574 (3.364)	Loss 1.0691 (1.0767)	Acc@1 74.512 (75.133)	Acc@5 92.578 (92.525)	
[2022-01-21 19:38:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.938 (2.524)	Loss 1.0159 (1.0735)	Acc@1 76.367 (75.195)	Acc@5 93.555 (92.569)	
[2022-01-21 19:39:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.677 (2.257)	Loss 1.1487 (1.0754)	Acc@1 74.219 (75.284)	Acc@5 91.504 (92.550)	
[2022-01-21 19:39:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.176 (2.171)	Loss 1.1413 (1.0746)	Acc@1 73.535 (75.162)	Acc@5 92.090 (92.573)	
[2022-01-21 19:39:41 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.150 Acc@5 92.704
[2022-01-21 19:39:41 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.1%
[2022-01-21 19:39:41 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.16%
[2022-01-21 19:40:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][0/1251]	eta 7:32:41 lr 0.000598	time 21.7121 (21.7121)	loss 4.2605 (4.2605)	grad_norm 1.4450 (1.4450)	
[2022-01-21 19:40:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][10/1251]	eta 1:24:08 lr 0.000598	time 2.5524 (4.0680)	loss 3.5729 (3.2561)	grad_norm 1.3653 (1.4173)	
[2022-01-21 19:40:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][20/1251]	eta 1:05:40 lr 0.000598	time 1.5308 (3.2015)	loss 3.1260 (3.4601)	grad_norm 1.3469 (1.4131)	
[2022-01-21 19:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][30/1251]	eta 0:57:57 lr 0.000598	time 1.5777 (2.8479)	loss 4.0777 (3.4855)	grad_norm 1.2612 (1.4031)	
[2022-01-21 19:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][40/1251]	eta 0:55:50 lr 0.000598	time 3.9169 (2.7668)	loss 3.7799 (3.5332)	grad_norm 1.2096 (1.3879)	
[2022-01-21 19:41:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][50/1251]	eta 0:53:32 lr 0.000598	time 3.0865 (2.6752)	loss 4.2410 (3.5400)	grad_norm 1.6623 (1.3869)	
[2022-01-21 19:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][60/1251]	eta 0:53:05 lr 0.000598	time 2.9079 (2.6748)	loss 3.9335 (3.5550)	grad_norm 1.3507 (1.3859)	
[2022-01-21 19:42:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][70/1251]	eta 0:51:51 lr 0.000597	time 1.5001 (2.6344)	loss 2.7378 (3.5498)	grad_norm 1.5160 (1.4028)	
[2022-01-21 19:43:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][80/1251]	eta 0:50:28 lr 0.000597	time 2.2800 (2.5860)	loss 4.2303 (3.5803)	grad_norm 1.4786 (1.4073)	
[2022-01-21 19:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][90/1251]	eta 0:49:00 lr 0.000597	time 2.2389 (2.5327)	loss 3.2167 (3.5583)	grad_norm 1.3573 (1.4054)	
[2022-01-21 19:43:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][100/1251]	eta 0:47:28 lr 0.000597	time 1.7892 (2.4745)	loss 2.6876 (3.5437)	grad_norm 1.7789 (1.4027)	
[2022-01-21 19:44:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][110/1251]	eta 0:46:12 lr 0.000597	time 2.2645 (2.4295)	loss 2.8930 (3.5375)	grad_norm 1.2986 (1.3967)	
[2022-01-21 19:44:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][120/1251]	eta 0:45:12 lr 0.000597	time 1.9433 (2.3979)	loss 3.1986 (3.5377)	grad_norm 1.4297 (1.3917)	
[2022-01-21 19:44:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][130/1251]	eta 0:44:19 lr 0.000597	time 1.9821 (2.3724)	loss 3.8752 (3.5555)	grad_norm 1.5542 (1.3938)	
[2022-01-21 19:45:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][140/1251]	eta 0:43:39 lr 0.000597	time 1.5558 (2.3580)	loss 3.9631 (3.5460)	grad_norm 1.4799 (1.3919)	
[2022-01-21 19:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][150/1251]	eta 0:43:06 lr 0.000597	time 1.9293 (2.3491)	loss 2.6163 (3.5537)	grad_norm 1.3872 (1.3980)	
[2022-01-21 19:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][160/1251]	eta 0:42:29 lr 0.000597	time 1.8199 (2.3372)	loss 3.5855 (3.5510)	grad_norm 1.3423 (1.3992)	
[2022-01-21 19:46:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][170/1251]	eta 0:42:15 lr 0.000597	time 3.2001 (2.3451)	loss 3.2083 (3.5562)	grad_norm 1.4874 (1.3982)	
[2022-01-21 19:46:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][180/1251]	eta 0:41:42 lr 0.000597	time 1.9186 (2.3365)	loss 3.8411 (3.5595)	grad_norm 1.4073 (1.3959)	
[2022-01-21 19:47:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][190/1251]	eta 0:41:11 lr 0.000597	time 2.3077 (2.3290)	loss 4.0679 (3.5733)	grad_norm 1.3573 (1.3961)	
[2022-01-21 19:47:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][200/1251]	eta 0:40:36 lr 0.000597	time 1.8918 (2.3181)	loss 2.7328 (3.5764)	grad_norm 1.4485 (1.3956)	
[2022-01-21 19:47:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][210/1251]	eta 0:40:09 lr 0.000597	time 2.5665 (2.3142)	loss 3.3951 (3.5661)	grad_norm 1.3892 (1.3963)	
[2022-01-21 19:48:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][220/1251]	eta 0:39:43 lr 0.000597	time 2.5454 (2.3116)	loss 4.1615 (3.5732)	grad_norm 1.3698 (1.3926)	
[2022-01-21 19:48:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][230/1251]	eta 0:39:28 lr 0.000597	time 3.2335 (2.3197)	loss 2.7471 (3.5759)	grad_norm 1.4546 (1.3937)	
[2022-01-21 19:48:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][240/1251]	eta 0:38:56 lr 0.000597	time 1.5556 (2.3109)	loss 3.9786 (3.5833)	grad_norm 1.2180 (1.3931)	
[2022-01-21 19:49:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][250/1251]	eta 0:38:26 lr 0.000597	time 1.8603 (2.3040)	loss 3.8340 (3.5813)	grad_norm 1.3936 (1.3946)	
[2022-01-21 19:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][260/1251]	eta 0:37:49 lr 0.000597	time 1.9389 (2.2901)	loss 3.4245 (3.5794)	grad_norm 1.4387 (1.3971)	
[2022-01-21 19:50:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][270/1251]	eta 0:37:33 lr 0.000597	time 2.4732 (2.2972)	loss 4.0453 (3.5849)	grad_norm 1.3098 (1.3960)	
[2022-01-21 19:50:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][280/1251]	eta 0:37:11 lr 0.000597	time 1.6686 (2.2979)	loss 4.1339 (3.5947)	grad_norm 1.2172 (1.3936)	
[2022-01-21 19:50:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][290/1251]	eta 0:36:42 lr 0.000597	time 1.7082 (2.2922)	loss 3.1748 (3.5915)	grad_norm 1.2204 (1.3908)	
[2022-01-21 19:51:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][300/1251]	eta 0:36:12 lr 0.000597	time 1.8638 (2.2843)	loss 3.2263 (3.5864)	grad_norm 1.2439 (1.3877)	
[2022-01-21 19:51:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][310/1251]	eta 0:35:44 lr 0.000596	time 1.9699 (2.2788)	loss 2.7239 (3.5801)	grad_norm 1.2746 (1.3852)	
[2022-01-21 19:51:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][320/1251]	eta 0:35:18 lr 0.000596	time 1.5726 (2.2753)	loss 4.2606 (3.5835)	grad_norm 1.2334 (1.3860)	
[2022-01-21 19:52:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][330/1251]	eta 0:34:56 lr 0.000596	time 1.9743 (2.2759)	loss 4.0991 (3.5893)	grad_norm 1.2990 (1.3850)	
[2022-01-21 19:52:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][340/1251]	eta 0:34:33 lr 0.000596	time 1.5398 (2.2759)	loss 3.6817 (3.5973)	grad_norm 1.2838 (1.3865)	
[2022-01-21 19:52:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][350/1251]	eta 0:34:07 lr 0.000596	time 1.6540 (2.2727)	loss 4.4187 (3.6007)	grad_norm 1.4580 (1.3866)	
[2022-01-21 19:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][360/1251]	eta 0:33:38 lr 0.000596	time 1.6172 (2.2654)	loss 3.3582 (3.5949)	grad_norm 1.4202 (1.3878)	
[2022-01-21 19:53:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][370/1251]	eta 0:33:20 lr 0.000596	time 1.5906 (2.2703)	loss 4.0646 (3.5990)	grad_norm 1.3452 (1.3872)	
[2022-01-21 19:54:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][380/1251]	eta 0:32:57 lr 0.000596	time 1.8652 (2.2709)	loss 3.0536 (3.5994)	grad_norm 1.4408 (1.3893)	
[2022-01-21 19:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][390/1251]	eta 0:32:34 lr 0.000596	time 1.8765 (2.2702)	loss 3.7642 (3.6096)	grad_norm 1.6383 (1.3921)	
[2022-01-21 19:54:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][400/1251]	eta 0:32:06 lr 0.000596	time 1.6849 (2.2632)	loss 4.5508 (3.6124)	grad_norm 1.3996 (1.3946)	
[2022-01-21 19:55:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][410/1251]	eta 0:31:42 lr 0.000596	time 2.2145 (2.2627)	loss 3.4216 (3.6071)	grad_norm 1.3041 (1.3954)	
[2022-01-21 19:55:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][420/1251]	eta 0:31:20 lr 0.000596	time 2.8337 (2.2628)	loss 3.6329 (3.6080)	grad_norm 1.5510 (1.3978)	
[2022-01-21 19:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][430/1251]	eta 0:30:57 lr 0.000596	time 1.8018 (2.2629)	loss 3.6694 (3.6049)	grad_norm 1.3750 (1.3984)	
[2022-01-21 19:56:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][440/1251]	eta 0:30:32 lr 0.000596	time 1.5848 (2.2601)	loss 3.4439 (3.6040)	grad_norm 1.7296 (1.4011)	
[2022-01-21 19:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][450/1251]	eta 0:30:09 lr 0.000596	time 1.5615 (2.2592)	loss 3.9156 (3.6070)	grad_norm 1.3611 (1.4021)	
[2022-01-21 19:57:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][460/1251]	eta 0:29:42 lr 0.000596	time 1.7386 (2.2540)	loss 3.5691 (3.6089)	grad_norm 1.3643 (1.4038)	
[2022-01-21 19:57:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][470/1251]	eta 0:29:19 lr 0.000596	time 2.0154 (2.2528)	loss 3.8886 (3.6099)	grad_norm 1.2636 (1.4025)	
[2022-01-21 19:57:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][480/1251]	eta 0:28:55 lr 0.000596	time 1.8818 (2.2508)	loss 4.0725 (3.6099)	grad_norm 1.2985 (1.4028)	
[2022-01-21 19:58:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][490/1251]	eta 0:28:37 lr 0.000596	time 1.9005 (2.2566)	loss 3.5330 (3.6082)	grad_norm 1.4886 (1.4029)	
[2022-01-21 19:58:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][500/1251]	eta 0:28:13 lr 0.000596	time 1.9912 (2.2554)	loss 3.7757 (3.6083)	grad_norm 1.1869 (1.4021)	
[2022-01-21 19:58:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][510/1251]	eta 0:27:46 lr 0.000596	time 1.9175 (2.2487)	loss 3.9075 (3.6091)	grad_norm 1.3682 (1.4019)	
[2022-01-21 19:59:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][520/1251]	eta 0:27:20 lr 0.000596	time 1.8398 (2.2437)	loss 3.5277 (3.6118)	grad_norm 1.4156 (1.4012)	
[2022-01-21 19:59:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][530/1251]	eta 0:27:01 lr 0.000596	time 2.6822 (2.2489)	loss 3.7902 (3.6188)	grad_norm 1.3139 (1.3994)	
[2022-01-21 19:59:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][540/1251]	eta 0:26:38 lr 0.000596	time 2.2290 (2.2489)	loss 4.3154 (3.6194)	grad_norm 1.2924 (1.3987)	
[2022-01-21 20:00:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][550/1251]	eta 0:26:15 lr 0.000596	time 2.1361 (2.2474)	loss 3.7091 (3.6212)	grad_norm 1.4630 (1.3999)	
[2022-01-21 20:00:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][560/1251]	eta 0:25:50 lr 0.000595	time 1.8978 (2.2441)	loss 3.6428 (3.6236)	grad_norm 1.2771 (1.3993)	
[2022-01-21 20:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][570/1251]	eta 0:25:29 lr 0.000595	time 1.7868 (2.2453)	loss 4.0569 (3.6266)	grad_norm 1.6241 (1.3990)	
[2022-01-21 20:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][580/1251]	eta 0:25:06 lr 0.000595	time 1.9567 (2.2455)	loss 2.3940 (3.6215)	grad_norm 1.4695 (1.3985)	
[2022-01-21 20:01:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][590/1251]	eta 0:24:43 lr 0.000595	time 2.2084 (2.2440)	loss 4.3246 (3.6228)	grad_norm 1.5348 (1.3993)	
[2022-01-21 20:02:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][600/1251]	eta 0:24:20 lr 0.000595	time 1.8105 (2.2428)	loss 3.8132 (3.6206)	grad_norm 1.1972 (1.3993)	
[2022-01-21 20:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][610/1251]	eta 0:23:54 lr 0.000595	time 1.5331 (2.2383)	loss 4.3044 (3.6209)	grad_norm 1.6163 (1.4012)	
[2022-01-21 20:02:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][620/1251]	eta 0:23:31 lr 0.000595	time 2.1744 (2.2369)	loss 2.9613 (3.6203)	grad_norm 1.6346 (1.4013)	
[2022-01-21 20:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][630/1251]	eta 0:23:07 lr 0.000595	time 2.2550 (2.2348)	loss 3.1294 (3.6171)	grad_norm 1.4989 (1.4028)	
[2022-01-21 20:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][640/1251]	eta 0:22:44 lr 0.000595	time 1.5837 (2.2329)	loss 3.7808 (3.6208)	grad_norm 1.4277 (1.4025)	
[2022-01-21 20:03:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][650/1251]	eta 0:22:21 lr 0.000595	time 1.6957 (2.2319)	loss 4.4320 (3.6194)	grad_norm 1.4910 (1.4036)	
[2022-01-21 20:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][660/1251]	eta 0:21:59 lr 0.000595	time 3.0780 (2.2323)	loss 3.6138 (3.6195)	grad_norm 1.5138 (1.4058)	
[2022-01-21 20:04:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][670/1251]	eta 0:21:37 lr 0.000595	time 3.4270 (2.2333)	loss 3.2733 (3.6107)	grad_norm 1.3668 (1.4052)	
[2022-01-21 20:05:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][680/1251]	eta 0:21:13 lr 0.000595	time 1.8792 (2.2309)	loss 4.2287 (3.6104)	grad_norm 1.4933 (1.4059)	
[2022-01-21 20:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][690/1251]	eta 0:20:50 lr 0.000595	time 1.8328 (2.2294)	loss 3.5291 (3.6086)	grad_norm 1.3748 (1.4054)	
[2022-01-21 20:05:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][700/1251]	eta 0:20:28 lr 0.000595	time 3.5850 (2.2297)	loss 3.6847 (3.6080)	grad_norm 1.3608 (1.4051)	
[2022-01-21 20:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][710/1251]	eta 0:20:07 lr 0.000595	time 2.7796 (2.2321)	loss 3.2366 (3.6083)	grad_norm 1.2383 (1.4043)	
[2022-01-21 20:06:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][720/1251]	eta 0:19:44 lr 0.000595	time 1.8047 (2.2312)	loss 4.0342 (3.6082)	grad_norm 1.1200 (1.4037)	
[2022-01-21 20:06:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][730/1251]	eta 0:19:22 lr 0.000595	time 1.9324 (2.2310)	loss 3.8592 (3.6097)	grad_norm 1.4828 (1.4043)	
[2022-01-21 20:07:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][740/1251]	eta 0:19:01 lr 0.000595	time 4.0027 (2.2329)	loss 4.3792 (3.6112)	grad_norm 1.5148 (1.4045)	
[2022-01-21 20:07:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][750/1251]	eta 0:18:38 lr 0.000595	time 1.9119 (2.2327)	loss 3.3433 (3.6080)	grad_norm 1.2103 (1.4039)	
[2022-01-21 20:07:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][760/1251]	eta 0:18:14 lr 0.000595	time 1.5788 (2.2295)	loss 3.2278 (3.6092)	grad_norm 1.5480 (1.4045)	
[2022-01-21 20:08:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][770/1251]	eta 0:17:51 lr 0.000595	time 2.2057 (2.2272)	loss 4.0661 (3.6069)	grad_norm 1.3678 (1.4045)	
[2022-01-21 20:08:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][780/1251]	eta 0:17:28 lr 0.000595	time 2.8536 (2.2262)	loss 4.2093 (3.6067)	grad_norm 1.5630 (1.4059)	
[2022-01-21 20:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][790/1251]	eta 0:17:05 lr 0.000595	time 2.7285 (2.2252)	loss 3.4967 (3.6067)	grad_norm 1.3103 (1.4066)	
[2022-01-21 20:09:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][800/1251]	eta 0:16:43 lr 0.000594	time 1.7301 (2.2242)	loss 2.5681 (3.6078)	grad_norm 1.3487 (1.4069)	
[2022-01-21 20:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][810/1251]	eta 0:16:20 lr 0.000594	time 2.1292 (2.2237)	loss 4.2163 (3.6107)	grad_norm 1.2537 (1.4071)	
[2022-01-21 20:10:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][820/1251]	eta 0:15:59 lr 0.000594	time 3.6134 (2.2270)	loss 3.1863 (3.6133)	grad_norm 1.3968 (1.4075)	
[2022-01-21 20:10:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][830/1251]	eta 0:15:38 lr 0.000594	time 2.8001 (2.2284)	loss 3.5592 (3.6104)	grad_norm 1.4985 (1.4084)	
[2022-01-21 20:10:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][840/1251]	eta 0:15:15 lr 0.000594	time 1.8530 (2.2275)	loss 4.1201 (3.6113)	grad_norm 1.3145 (1.4090)	
[2022-01-21 20:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][850/1251]	eta 0:14:51 lr 0.000594	time 1.7161 (2.2242)	loss 3.9541 (3.6098)	grad_norm 1.6467 (1.4091)	
[2022-01-21 20:11:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][860/1251]	eta 0:14:28 lr 0.000594	time 2.8106 (2.2219)	loss 3.7662 (3.6084)	grad_norm 1.3556 (1.4087)	
[2022-01-21 20:11:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][870/1251]	eta 0:14:05 lr 0.000594	time 2.0787 (2.2204)	loss 3.2338 (3.6059)	grad_norm 1.3036 (1.4080)	
[2022-01-21 20:12:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][880/1251]	eta 0:13:44 lr 0.000594	time 2.2610 (2.2212)	loss 4.2220 (3.6003)	grad_norm 1.3473 (1.4074)	
[2022-01-21 20:12:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][890/1251]	eta 0:13:21 lr 0.000594	time 2.2283 (2.2214)	loss 3.2857 (3.6037)	grad_norm 1.3239 (1.4068)	
[2022-01-21 20:13:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][900/1251]	eta 0:12:59 lr 0.000594	time 2.2484 (2.2210)	loss 3.6717 (3.6043)	grad_norm 1.2131 (1.4062)	
[2022-01-21 20:13:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][910/1251]	eta 0:12:37 lr 0.000594	time 1.7530 (2.2227)	loss 3.6240 (3.6051)	grad_norm 1.3424 (1.4054)	
[2022-01-21 20:13:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][920/1251]	eta 0:12:15 lr 0.000594	time 1.5804 (2.2224)	loss 3.6624 (3.6074)	grad_norm 1.7412 (1.4062)	
[2022-01-21 20:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][930/1251]	eta 0:11:53 lr 0.000594	time 1.8595 (2.2227)	loss 4.0740 (3.6065)	grad_norm 1.3203 (1.4054)	
[2022-01-21 20:14:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][940/1251]	eta 0:11:31 lr 0.000594	time 2.9307 (2.2231)	loss 4.3125 (3.6091)	grad_norm 1.5525 (1.4050)	
[2022-01-21 20:14:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][950/1251]	eta 0:11:08 lr 0.000594	time 1.8170 (2.2217)	loss 3.5013 (3.6108)	grad_norm 1.5222 (1.4045)	
[2022-01-21 20:15:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][960/1251]	eta 0:10:46 lr 0.000594	time 2.2637 (2.2211)	loss 2.8689 (3.6108)	grad_norm 1.1947 (1.4043)	
[2022-01-21 20:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][970/1251]	eta 0:10:23 lr 0.000594	time 1.6092 (2.2191)	loss 3.8666 (3.6113)	grad_norm 1.4818 (1.4036)	
[2022-01-21 20:15:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][980/1251]	eta 0:10:01 lr 0.000594	time 2.2761 (2.2193)	loss 2.5849 (3.6099)	grad_norm 1.2597 (1.4038)	
[2022-01-21 20:16:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][990/1251]	eta 0:09:39 lr 0.000594	time 1.7560 (2.2200)	loss 4.0177 (3.6106)	grad_norm 1.3512 (1.4041)	
[2022-01-21 20:16:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1000/1251]	eta 0:09:16 lr 0.000594	time 1.9230 (2.2183)	loss 3.6073 (3.6101)	grad_norm 1.1434 (1.4032)	
[2022-01-21 20:17:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1010/1251]	eta 0:08:54 lr 0.000594	time 2.5778 (2.2194)	loss 2.6616 (3.6090)	grad_norm 1.4877 (1.4025)	
[2022-01-21 20:17:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1020/1251]	eta 0:08:32 lr 0.000594	time 1.6503 (2.2196)	loss 3.1355 (3.6094)	grad_norm 1.4370 (1.4022)	
[2022-01-21 20:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1030/1251]	eta 0:08:10 lr 0.000594	time 2.1445 (2.2194)	loss 3.5113 (3.6105)	grad_norm 1.3965 (1.4029)	
[2022-01-21 20:18:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1040/1251]	eta 0:07:48 lr 0.000594	time 1.9791 (2.2195)	loss 4.3616 (3.6098)	grad_norm 1.6194 (1.4025)	
[2022-01-21 20:18:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1050/1251]	eta 0:07:25 lr 0.000593	time 1.9758 (2.2183)	loss 4.3867 (3.6108)	grad_norm 1.3236 (1.4025)	
[2022-01-21 20:18:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1060/1251]	eta 0:07:03 lr 0.000593	time 1.6977 (2.2162)	loss 3.7217 (3.6132)	grad_norm 1.4030 (1.4026)	
[2022-01-21 20:19:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1070/1251]	eta 0:06:40 lr 0.000593	time 1.8213 (2.2147)	loss 4.1521 (3.6146)	grad_norm 1.2648 (1.4027)	
[2022-01-21 20:19:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1080/1251]	eta 0:06:18 lr 0.000593	time 1.9287 (2.2136)	loss 3.1204 (3.6132)	grad_norm 1.7430 (1.4027)	
[2022-01-21 20:19:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1090/1251]	eta 0:05:56 lr 0.000593	time 2.8061 (2.2152)	loss 3.1248 (3.6120)	grad_norm 1.2716 (1.4022)	
[2022-01-21 20:20:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1100/1251]	eta 0:05:34 lr 0.000593	time 2.9044 (2.2156)	loss 2.7225 (3.6108)	grad_norm 1.1650 (1.4012)	
[2022-01-21 20:20:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1110/1251]	eta 0:05:12 lr 0.000593	time 1.6798 (2.2158)	loss 3.8531 (3.6104)	grad_norm 1.3472 (1.4013)	
[2022-01-21 20:21:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1120/1251]	eta 0:04:50 lr 0.000593	time 1.6140 (2.2151)	loss 2.8649 (3.6113)	grad_norm 1.6563 (1.4012)	
[2022-01-21 20:21:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1130/1251]	eta 0:04:28 lr 0.000593	time 2.2241 (2.2157)	loss 3.6838 (3.6107)	grad_norm 1.3712 (1.4019)	
[2022-01-21 20:21:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1140/1251]	eta 0:04:05 lr 0.000593	time 1.6596 (2.2140)	loss 3.5546 (3.6119)	grad_norm 1.3571 (1.4022)	
[2022-01-21 20:22:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1150/1251]	eta 0:03:43 lr 0.000593	time 2.5625 (2.2154)	loss 3.9997 (3.6130)	grad_norm 1.5141 (1.4021)	
[2022-01-21 20:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1160/1251]	eta 0:03:21 lr 0.000593	time 1.8987 (2.2134)	loss 3.1667 (3.6140)	grad_norm 1.3200 (1.4029)	
[2022-01-21 20:22:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1170/1251]	eta 0:02:59 lr 0.000593	time 2.1921 (2.2127)	loss 3.7429 (3.6172)	grad_norm 1.3897 (1.4024)	
[2022-01-21 20:23:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1180/1251]	eta 0:02:37 lr 0.000593	time 2.2350 (2.2132)	loss 3.7401 (3.6189)	grad_norm 1.3989 (1.4021)	
[2022-01-21 20:23:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1190/1251]	eta 0:02:14 lr 0.000593	time 2.5265 (2.2129)	loss 2.8816 (3.6172)	grad_norm 1.3586 (1.4023)	
[2022-01-21 20:23:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1200/1251]	eta 0:01:52 lr 0.000593	time 2.0950 (2.2132)	loss 3.2580 (3.6184)	grad_norm 1.2854 (1.4026)	
[2022-01-21 20:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1210/1251]	eta 0:01:30 lr 0.000593	time 2.4583 (2.2136)	loss 3.3793 (3.6184)	grad_norm 1.1956 (1.4026)	
[2022-01-21 20:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1220/1251]	eta 0:01:08 lr 0.000593	time 2.4067 (2.2134)	loss 3.9507 (3.6167)	grad_norm 1.5379 (1.4026)	
[2022-01-21 20:25:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1230/1251]	eta 0:00:46 lr 0.000593	time 1.9781 (2.2124)	loss 4.0953 (3.6158)	grad_norm 1.2987 (1.4022)	
[2022-01-21 20:25:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1240/1251]	eta 0:00:24 lr 0.000593	time 1.7301 (2.2112)	loss 3.6411 (3.6150)	grad_norm 1.3156 (1.4021)	
[2022-01-21 20:25:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [132/300][1250/1251]	eta 0:00:02 lr 0.000593	time 1.3276 (2.2063)	loss 3.9100 (3.6142)	grad_norm 1.5049 (1.4024)	
[2022-01-21 20:25:41 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 132 training takes 0:46:00
[2022-01-21 20:26:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.473 (18.473)	Loss 1.0796 (1.0796)	Acc@1 76.270 (76.270)	Acc@5 92.285 (92.285)	
[2022-01-21 20:26:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.316 (3.469)	Loss 1.0659 (1.0603)	Acc@1 75.098 (75.053)	Acc@5 93.457 (92.809)	
[2022-01-21 20:26:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.556 (2.652)	Loss 1.0276 (1.0474)	Acc@1 75.000 (74.991)	Acc@5 92.676 (93.043)	
[2022-01-21 20:26:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.277 (2.313)	Loss 0.9794 (1.0545)	Acc@1 77.637 (74.924)	Acc@5 94.043 (92.988)	
[2022-01-21 20:27:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.276 (2.231)	Loss 1.0809 (1.0513)	Acc@1 74.316 (75.062)	Acc@5 92.871 (93.040)	
[2022-01-21 20:27:20 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 74.988 Acc@5 93.020
[2022-01-21 20:27:20 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.0%
[2022-01-21 20:27:20 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.16%
[2022-01-21 20:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][0/1251]	eta 7:20:09 lr 0.000593	time 21.1107 (21.1107)	loss 4.0387 (4.0387)	grad_norm 1.5958 (1.5958)	
[2022-01-21 20:28:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][10/1251]	eta 1:25:30 lr 0.000593	time 1.8458 (4.1341)	loss 4.1758 (3.7219)	grad_norm 1.5215 (1.5284)	
[2022-01-21 20:28:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][20/1251]	eta 1:05:18 lr 0.000593	time 2.1813 (3.1829)	loss 3.1051 (3.5573)	grad_norm 1.5283 (1.4835)	
[2022-01-21 20:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][30/1251]	eta 0:56:38 lr 0.000593	time 1.5474 (2.7830)	loss 2.4935 (3.4992)	grad_norm 1.3982 (1.4585)	
[2022-01-21 20:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][40/1251]	eta 0:53:14 lr 0.000592	time 2.9841 (2.6382)	loss 3.8633 (3.5344)	grad_norm 1.3729 (1.4524)	
[2022-01-21 20:29:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][50/1251]	eta 0:51:24 lr 0.000592	time 1.5448 (2.5683)	loss 3.9954 (3.5435)	grad_norm 1.3007 (1.4306)	
[2022-01-21 20:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][60/1251]	eta 0:49:28 lr 0.000592	time 1.4763 (2.4921)	loss 3.6481 (3.5500)	grad_norm 1.3614 (1.4174)	
[2022-01-21 20:30:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][70/1251]	eta 0:48:01 lr 0.000592	time 1.9117 (2.4399)	loss 3.9759 (3.5391)	grad_norm 1.3075 (1.4105)	
[2022-01-21 20:30:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][80/1251]	eta 0:47:33 lr 0.000592	time 3.3961 (2.4368)	loss 3.9890 (3.5432)	grad_norm 1.8054 (1.4109)	
[2022-01-21 20:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][90/1251]	eta 0:46:54 lr 0.000592	time 1.5712 (2.4246)	loss 3.3382 (3.5595)	grad_norm 1.2797 (1.4145)	
[2022-01-21 20:31:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][100/1251]	eta 0:46:07 lr 0.000592	time 2.2058 (2.4046)	loss 4.5022 (3.5661)	grad_norm 1.6016 (1.4132)	
[2022-01-21 20:31:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][110/1251]	eta 0:45:17 lr 0.000592	time 1.7119 (2.3820)	loss 2.9084 (3.5709)	grad_norm 1.5076 (1.4158)	
[2022-01-21 20:32:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][120/1251]	eta 0:44:37 lr 0.000592	time 3.0421 (2.3671)	loss 3.8641 (3.5830)	grad_norm 1.3676 (1.4203)	
[2022-01-21 20:32:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][130/1251]	eta 0:43:55 lr 0.000592	time 1.8457 (2.3509)	loss 4.0114 (3.5822)	grad_norm 1.3506 (1.4192)	
[2022-01-21 20:32:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][140/1251]	eta 0:43:17 lr 0.000592	time 2.3894 (2.3384)	loss 3.8938 (3.5812)	grad_norm 1.2781 (1.4115)	
[2022-01-21 20:33:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][150/1251]	eta 0:42:45 lr 0.000592	time 2.1887 (2.3302)	loss 3.8456 (3.5903)	grad_norm 1.2777 (1.4088)	
[2022-01-21 20:33:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][160/1251]	eta 0:42:20 lr 0.000592	time 3.0585 (2.3290)	loss 3.7318 (3.5980)	grad_norm 1.3401 (1.4050)	
[2022-01-21 20:33:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][170/1251]	eta 0:41:45 lr 0.000592	time 2.2577 (2.3173)	loss 3.9713 (3.6052)	grad_norm 1.6719 (1.4065)	
[2022-01-21 20:34:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][180/1251]	eta 0:41:05 lr 0.000592	time 1.9851 (2.3017)	loss 3.4495 (3.6026)	grad_norm 1.3701 (1.4054)	
[2022-01-21 20:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][190/1251]	eta 0:40:30 lr 0.000592	time 1.7638 (2.2905)	loss 2.7577 (3.6066)	grad_norm 1.2728 (1.4034)	
[2022-01-21 20:35:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][200/1251]	eta 0:40:13 lr 0.000592	time 3.0216 (2.2968)	loss 3.7400 (3.6092)	grad_norm 1.3004 (1.4009)	
[2022-01-21 20:35:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][210/1251]	eta 0:39:44 lr 0.000592	time 1.8491 (2.2902)	loss 2.4954 (3.6107)	grad_norm 1.3372 (1.3962)	
[2022-01-21 20:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][220/1251]	eta 0:39:12 lr 0.000592	time 2.8035 (2.2821)	loss 3.3147 (3.6127)	grad_norm 1.4482 (1.3934)	
[2022-01-21 20:36:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][230/1251]	eta 0:38:51 lr 0.000592	time 1.8584 (2.2836)	loss 3.0666 (3.6124)	grad_norm 1.7377 (1.3958)	
[2022-01-21 20:36:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][240/1251]	eta 0:38:26 lr 0.000592	time 2.1848 (2.2813)	loss 3.6931 (3.6164)	grad_norm 1.3749 (1.3954)	
[2022-01-21 20:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][250/1251]	eta 0:37:58 lr 0.000592	time 1.9951 (2.2763)	loss 3.2260 (3.6081)	grad_norm 1.2121 (1.3925)	
[2022-01-21 20:37:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][260/1251]	eta 0:37:33 lr 0.000592	time 2.3929 (2.2735)	loss 4.4370 (3.6043)	grad_norm 1.4559 (1.3944)	
[2022-01-21 20:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][270/1251]	eta 0:37:09 lr 0.000592	time 1.9161 (2.2730)	loss 3.4916 (3.6011)	grad_norm 1.1791 (1.3970)	
[2022-01-21 20:37:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][280/1251]	eta 0:36:41 lr 0.000592	time 1.7491 (2.2673)	loss 3.4262 (3.5929)	grad_norm 1.2863 (1.3966)	
[2022-01-21 20:38:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][290/1251]	eta 0:36:14 lr 0.000591	time 1.6290 (2.2626)	loss 3.8242 (3.5936)	grad_norm 1.4436 (1.3963)	
[2022-01-21 20:38:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][300/1251]	eta 0:35:45 lr 0.000591	time 2.6525 (2.2558)	loss 2.6666 (3.5880)	grad_norm 1.2437 (1.3949)	
[2022-01-21 20:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][310/1251]	eta 0:35:20 lr 0.000591	time 2.1864 (2.2538)	loss 3.8729 (3.5920)	grad_norm 1.4304 (1.3932)	
[2022-01-21 20:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][320/1251]	eta 0:35:00 lr 0.000591	time 2.2757 (2.2560)	loss 4.1786 (3.5974)	grad_norm 1.4599 (1.3935)	
[2022-01-21 20:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][330/1251]	eta 0:34:39 lr 0.000591	time 1.6799 (2.2583)	loss 3.9344 (3.5976)	grad_norm 1.3564 (1.3918)	
[2022-01-21 20:40:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][340/1251]	eta 0:34:13 lr 0.000591	time 1.6536 (2.2544)	loss 3.3095 (3.5986)	grad_norm 1.6090 (1.3932)	
[2022-01-21 20:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][350/1251]	eta 0:33:48 lr 0.000591	time 2.5164 (2.2515)	loss 3.2124 (3.6022)	grad_norm 1.7184 (1.3943)	
[2022-01-21 20:40:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][360/1251]	eta 0:33:21 lr 0.000591	time 1.7491 (2.2461)	loss 3.6463 (3.6007)	grad_norm 1.3744 (1.3930)	
[2022-01-21 20:41:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][370/1251]	eta 0:32:54 lr 0.000591	time 1.9459 (2.2416)	loss 2.8761 (3.5983)	grad_norm 1.7936 (1.3966)	
[2022-01-21 20:41:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][380/1251]	eta 0:32:27 lr 0.000591	time 1.8592 (2.2354)	loss 4.5210 (3.5994)	grad_norm 1.3241 (1.3984)	
[2022-01-21 20:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][390/1251]	eta 0:32:03 lr 0.000591	time 1.9345 (2.2335)	loss 4.1152 (3.6083)	grad_norm 1.5237 (1.4009)	
[2022-01-21 20:42:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][400/1251]	eta 0:31:38 lr 0.000591	time 1.7256 (2.2315)	loss 2.7484 (3.6026)	grad_norm 1.4491 (1.4016)	
[2022-01-21 20:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][410/1251]	eta 0:31:17 lr 0.000591	time 2.2304 (2.2327)	loss 3.2207 (3.6055)	grad_norm 1.4121 (1.4017)	
[2022-01-21 20:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][420/1251]	eta 0:30:57 lr 0.000591	time 2.0712 (2.2357)	loss 2.8837 (3.5987)	grad_norm 1.2042 (1.4015)	
[2022-01-21 20:43:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][430/1251]	eta 0:30:37 lr 0.000591	time 2.0199 (2.2385)	loss 4.1590 (3.5959)	grad_norm 1.9006 (1.4040)	
[2022-01-21 20:43:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][440/1251]	eta 0:30:14 lr 0.000591	time 1.9855 (2.2375)	loss 4.0047 (3.5955)	grad_norm 1.5138 (1.4054)	
[2022-01-21 20:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][450/1251]	eta 0:29:48 lr 0.000591	time 2.4104 (2.2323)	loss 2.7160 (3.5994)	grad_norm 1.3669 (1.4059)	
[2022-01-21 20:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][460/1251]	eta 0:29:24 lr 0.000591	time 1.8646 (2.2306)	loss 4.0733 (3.6041)	grad_norm 1.7117 (1.4076)	
[2022-01-21 20:44:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][470/1251]	eta 0:29:03 lr 0.000591	time 2.4853 (2.2321)	loss 3.7422 (3.6080)	grad_norm 1.4062 (1.4066)	
[2022-01-21 20:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][480/1251]	eta 0:28:41 lr 0.000591	time 1.5207 (2.2325)	loss 2.4032 (3.6002)	grad_norm 1.4915 (1.4052)	
[2022-01-21 20:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][490/1251]	eta 0:28:18 lr 0.000591	time 2.1645 (2.2324)	loss 4.2329 (3.6033)	grad_norm 1.3496 (1.4037)	
[2022-01-21 20:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][500/1251]	eta 0:27:54 lr 0.000591	time 2.4874 (2.2291)	loss 3.2692 (3.6063)	grad_norm 1.4179 (1.4034)	
[2022-01-21 20:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][510/1251]	eta 0:27:29 lr 0.000591	time 1.9827 (2.2266)	loss 4.3568 (3.6082)	grad_norm 1.3865 (1.4031)	
[2022-01-21 20:46:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][520/1251]	eta 0:27:06 lr 0.000591	time 2.2027 (2.2249)	loss 3.8516 (3.6112)	grad_norm 1.2365 (1.4028)	
[2022-01-21 20:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][530/1251]	eta 0:26:45 lr 0.000590	time 2.2093 (2.2270)	loss 4.6519 (3.6143)	grad_norm 1.3567 (1.4016)	
[2022-01-21 20:47:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][540/1251]	eta 0:26:22 lr 0.000590	time 1.9751 (2.2262)	loss 4.6298 (3.6144)	grad_norm 1.6883 (1.4050)	
[2022-01-21 20:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][550/1251]	eta 0:25:59 lr 0.000590	time 2.0454 (2.2247)	loss 3.8889 (3.6157)	grad_norm 1.4355 (1.4059)	
[2022-01-21 20:48:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][560/1251]	eta 0:25:37 lr 0.000590	time 1.5883 (2.2250)	loss 3.9741 (3.6157)	grad_norm 1.5803 (1.4087)	
[2022-01-21 20:48:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][570/1251]	eta 0:25:14 lr 0.000590	time 1.9218 (2.2233)	loss 4.5223 (3.6220)	grad_norm 1.5324 (1.4112)	
[2022-01-21 20:48:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][580/1251]	eta 0:24:49 lr 0.000590	time 1.8445 (2.2203)	loss 3.6368 (3.6261)	grad_norm 1.3621 (1.4116)	
[2022-01-21 20:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][590/1251]	eta 0:24:25 lr 0.000590	time 1.8628 (2.2177)	loss 3.9371 (3.6191)	grad_norm 1.4175 (1.4110)	
[2022-01-21 20:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][600/1251]	eta 0:24:03 lr 0.000590	time 1.5696 (2.2167)	loss 4.2951 (3.6176)	grad_norm 1.5441 (1.4106)	
[2022-01-21 20:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][610/1251]	eta 0:23:40 lr 0.000590	time 2.4345 (2.2167)	loss 2.5070 (3.6128)	grad_norm 1.6326 (1.4101)	
[2022-01-21 20:50:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][620/1251]	eta 0:23:18 lr 0.000590	time 2.7218 (2.2169)	loss 4.1168 (3.6103)	grad_norm 1.4156 (1.4086)	
[2022-01-21 20:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][630/1251]	eta 0:22:57 lr 0.000590	time 2.1778 (2.2188)	loss 2.6065 (3.6079)	grad_norm 1.3615 (1.4082)	
[2022-01-21 20:51:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][640/1251]	eta 0:22:36 lr 0.000590	time 2.1114 (2.2200)	loss 3.3619 (3.6072)	grad_norm 1.4301 (1.4075)	
[2022-01-21 20:51:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][650/1251]	eta 0:22:14 lr 0.000590	time 2.1427 (2.2203)	loss 2.5760 (3.6053)	grad_norm 1.2541 (1.4063)	
[2022-01-21 20:51:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][660/1251]	eta 0:21:49 lr 0.000590	time 1.8505 (2.2162)	loss 2.6975 (3.6046)	grad_norm 1.6407 (1.4075)	
[2022-01-21 20:52:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][670/1251]	eta 0:21:25 lr 0.000590	time 1.8636 (2.2121)	loss 4.2957 (3.6058)	grad_norm 1.1655 (1.4074)	
[2022-01-21 20:52:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][680/1251]	eta 0:21:02 lr 0.000590	time 1.8309 (2.2111)	loss 3.6739 (3.6013)	grad_norm 1.4942 (1.4075)	
[2022-01-21 20:52:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][690/1251]	eta 0:20:39 lr 0.000590	time 1.9887 (2.2093)	loss 2.9891 (3.5976)	grad_norm 1.3530 (1.4069)	
[2022-01-21 20:53:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][700/1251]	eta 0:20:17 lr 0.000590	time 1.9570 (2.2096)	loss 4.0814 (3.5928)	grad_norm 1.3712 (1.4058)	
[2022-01-21 20:53:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][710/1251]	eta 0:19:54 lr 0.000590	time 1.6197 (2.2088)	loss 4.1605 (3.5938)	grad_norm 1.3340 (1.4060)	
[2022-01-21 20:53:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][720/1251]	eta 0:19:33 lr 0.000590	time 2.1995 (2.2091)	loss 3.7858 (3.5965)	grad_norm 1.3702 (1.4060)	
[2022-01-21 20:54:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][730/1251]	eta 0:19:10 lr 0.000590	time 2.5991 (2.2089)	loss 3.4570 (3.5980)	grad_norm 1.5153 (1.4072)	
[2022-01-21 20:54:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][740/1251]	eta 0:18:48 lr 0.000590	time 2.5628 (2.2093)	loss 3.2381 (3.5977)	grad_norm 1.4254 (1.4070)	
[2022-01-21 20:54:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][750/1251]	eta 0:18:26 lr 0.000590	time 1.5011 (2.2082)	loss 3.7908 (3.5990)	grad_norm 1.5200 (1.4072)	
[2022-01-21 20:55:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][760/1251]	eta 0:18:04 lr 0.000590	time 2.5893 (2.2092)	loss 4.0383 (3.6012)	grad_norm 1.6012 (1.4075)	
[2022-01-21 20:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][770/1251]	eta 0:17:42 lr 0.000590	time 2.2563 (2.2100)	loss 3.7012 (3.6001)	grad_norm 1.4408 (1.4074)	
[2022-01-21 20:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][780/1251]	eta 0:17:21 lr 0.000589	time 2.1810 (2.2114)	loss 4.2391 (3.5987)	grad_norm 1.3321 (1.4075)	
[2022-01-21 20:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][790/1251]	eta 0:16:58 lr 0.000589	time 1.7050 (2.2089)	loss 3.8099 (3.6000)	grad_norm 1.4823 (1.4081)	
[2022-01-21 20:56:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][800/1251]	eta 0:16:35 lr 0.000589	time 2.4675 (2.2077)	loss 4.1540 (3.5987)	grad_norm 1.3578 (1.4073)	
[2022-01-21 20:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][810/1251]	eta 0:16:13 lr 0.000589	time 2.1644 (2.2064)	loss 4.2082 (3.6003)	grad_norm 1.3352 (1.4094)	
[2022-01-21 20:57:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][820/1251]	eta 0:15:50 lr 0.000589	time 1.9318 (2.2061)	loss 4.1984 (3.6015)	grad_norm 1.6777 (1.4113)	
[2022-01-21 20:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][830/1251]	eta 0:15:29 lr 0.000589	time 2.1599 (2.2071)	loss 3.9708 (3.6013)	grad_norm 1.4766 (1.4115)	
[2022-01-21 20:58:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][840/1251]	eta 0:15:06 lr 0.000589	time 2.1686 (2.2061)	loss 3.7075 (3.6015)	grad_norm 1.2051 (1.4107)	
[2022-01-21 20:58:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][850/1251]	eta 0:14:44 lr 0.000589	time 1.8938 (2.2048)	loss 4.2183 (3.5998)	grad_norm 1.2788 (1.4097)	
[2022-01-21 20:58:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][860/1251]	eta 0:14:21 lr 0.000589	time 2.3617 (2.2027)	loss 3.8881 (3.5993)	grad_norm 1.5473 (1.4103)	
[2022-01-21 20:59:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][870/1251]	eta 0:13:59 lr 0.000589	time 2.3552 (2.2024)	loss 4.2038 (3.6000)	grad_norm 1.4156 (1.4099)	
[2022-01-21 20:59:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][880/1251]	eta 0:13:37 lr 0.000589	time 2.1229 (2.2034)	loss 2.8104 (3.5999)	grad_norm 1.3118 (1.4093)	
[2022-01-21 21:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][890/1251]	eta 0:13:15 lr 0.000589	time 2.4799 (2.2044)	loss 4.0093 (3.5986)	grad_norm 1.2516 (1.4087)	
[2022-01-21 21:00:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][900/1251]	eta 0:12:55 lr 0.000589	time 2.5038 (2.2081)	loss 4.0584 (3.5976)	grad_norm 1.3616 (1.4084)	
[2022-01-21 21:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][910/1251]	eta 0:12:32 lr 0.000589	time 2.2102 (2.2076)	loss 2.7358 (3.5970)	grad_norm 1.2577 (1.4083)	
[2022-01-21 21:01:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][920/1251]	eta 0:12:10 lr 0.000589	time 1.9685 (2.2060)	loss 3.9236 (3.5970)	grad_norm 1.3859 (1.4081)	
[2022-01-21 21:01:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][930/1251]	eta 0:11:47 lr 0.000589	time 1.9564 (2.2036)	loss 3.8799 (3.5988)	grad_norm 1.7145 (1.4085)	
[2022-01-21 21:01:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][940/1251]	eta 0:11:25 lr 0.000589	time 2.5519 (2.2041)	loss 4.4696 (3.5942)	grad_norm 1.4624 (1.4089)	
[2022-01-21 21:02:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][950/1251]	eta 0:11:03 lr 0.000589	time 1.6868 (2.2030)	loss 3.5212 (3.5970)	grad_norm 1.3119 (1.4089)	
[2022-01-21 21:02:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][960/1251]	eta 0:10:40 lr 0.000589	time 2.1669 (2.2022)	loss 2.8430 (3.5960)	grad_norm 1.1860 (1.4082)	
[2022-01-21 21:02:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][970/1251]	eta 0:10:18 lr 0.000589	time 1.9623 (2.2003)	loss 3.5885 (3.5951)	grad_norm 1.3412 (1.4081)	
[2022-01-21 21:03:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][980/1251]	eta 0:09:56 lr 0.000589	time 2.1444 (2.1998)	loss 4.2233 (3.5979)	grad_norm 1.3114 (1.4075)	
[2022-01-21 21:03:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][990/1251]	eta 0:09:34 lr 0.000589	time 1.9068 (2.1995)	loss 2.9589 (3.5977)	grad_norm 1.5041 (1.4076)	
[2022-01-21 21:04:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1000/1251]	eta 0:09:12 lr 0.000589	time 2.1568 (2.2001)	loss 3.8830 (3.5986)	grad_norm 1.2868 (1.4076)	
[2022-01-21 21:04:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1010/1251]	eta 0:08:50 lr 0.000589	time 1.9133 (2.2010)	loss 4.2089 (3.5970)	grad_norm 1.2997 (1.4079)	
[2022-01-21 21:04:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1020/1251]	eta 0:08:28 lr 0.000588	time 2.4373 (2.2018)	loss 3.6599 (3.5966)	grad_norm 1.3568 (1.4076)	
[2022-01-21 21:05:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1030/1251]	eta 0:08:06 lr 0.000588	time 1.9967 (2.2009)	loss 3.5980 (3.5975)	grad_norm 1.5689 (1.4076)	
[2022-01-21 21:05:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1040/1251]	eta 0:07:44 lr 0.000588	time 1.9634 (2.2014)	loss 3.5332 (3.5993)	grad_norm 1.6631 (1.4079)	
[2022-01-21 21:05:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1050/1251]	eta 0:07:22 lr 0.000588	time 2.2483 (2.2026)	loss 2.8685 (3.5980)	grad_norm 1.5218 (1.4077)	
[2022-01-21 21:06:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1060/1251]	eta 0:07:00 lr 0.000588	time 1.7582 (2.2023)	loss 3.1053 (3.5993)	grad_norm 1.4263 (1.4075)	
[2022-01-21 21:06:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1070/1251]	eta 0:06:38 lr 0.000588	time 2.2605 (2.2004)	loss 4.1927 (3.6002)	grad_norm 1.2989 (1.4073)	
[2022-01-21 21:06:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1080/1251]	eta 0:06:16 lr 0.000588	time 2.1950 (2.2002)	loss 3.9546 (3.5996)	grad_norm 1.6385 (1.4087)	
[2022-01-21 21:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1090/1251]	eta 0:05:54 lr 0.000588	time 1.8806 (2.1994)	loss 3.9516 (3.5987)	grad_norm 1.3563 (1.4087)	
[2022-01-21 21:07:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1100/1251]	eta 0:05:32 lr 0.000588	time 2.5231 (2.1996)	loss 4.0799 (3.6008)	grad_norm 1.2578 (1.4092)	
[2022-01-21 21:08:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1110/1251]	eta 0:05:10 lr 0.000588	time 1.8829 (2.2002)	loss 3.7433 (3.6014)	grad_norm 1.4224 (1.4084)	
[2022-01-21 21:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1120/1251]	eta 0:04:48 lr 0.000588	time 2.3462 (2.2018)	loss 4.5130 (3.6027)	grad_norm 1.4182 (1.4078)	
[2022-01-21 21:08:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1130/1251]	eta 0:04:26 lr 0.000588	time 3.1475 (2.2026)	loss 3.9889 (3.6029)	grad_norm 1.3036 (1.4070)	
[2022-01-21 21:09:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1140/1251]	eta 0:04:04 lr 0.000588	time 1.8829 (2.2015)	loss 3.4833 (3.6018)	grad_norm 1.3172 (1.4066)	
[2022-01-21 21:09:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1150/1251]	eta 0:03:42 lr 0.000588	time 1.8419 (2.2001)	loss 3.5345 (3.6029)	grad_norm 1.2521 (1.4057)	
[2022-01-21 21:09:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1160/1251]	eta 0:03:20 lr 0.000588	time 2.0119 (2.1994)	loss 4.0828 (3.6042)	grad_norm 1.2455 (1.4055)	
[2022-01-21 21:10:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1170/1251]	eta 0:02:58 lr 0.000588	time 2.4731 (2.1989)	loss 3.9208 (3.6062)	grad_norm 1.5199 (1.4057)	
[2022-01-21 21:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1180/1251]	eta 0:02:36 lr 0.000588	time 1.5196 (2.1977)	loss 2.4649 (3.6061)	grad_norm 1.3116 (1.4057)	
[2022-01-21 21:10:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1190/1251]	eta 0:02:14 lr 0.000588	time 1.8607 (2.1985)	loss 2.2548 (3.6043)	grad_norm 1.4118 (1.4054)	
[2022-01-21 21:11:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1200/1251]	eta 0:01:52 lr 0.000588	time 2.7381 (2.1990)	loss 3.3119 (3.6048)	grad_norm 1.3440 (1.4055)	
[2022-01-21 21:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1210/1251]	eta 0:01:30 lr 0.000588	time 1.9440 (2.1997)	loss 3.1545 (3.6054)	grad_norm 1.5780 (1.4049)	
[2022-01-21 21:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1220/1251]	eta 0:01:08 lr 0.000588	time 1.8259 (2.2004)	loss 2.8954 (3.6047)	grad_norm 1.4821 (1.4051)	
[2022-01-21 21:12:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1230/1251]	eta 0:00:46 lr 0.000588	time 1.6539 (2.1998)	loss 3.4013 (3.6039)	grad_norm 1.3128 (1.4051)	
[2022-01-21 21:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1240/1251]	eta 0:00:24 lr 0.000588	time 1.4971 (2.1981)	loss 2.8856 (3.6038)	grad_norm 1.4500 (1.4055)	
[2022-01-21 21:13:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [133/300][1250/1251]	eta 0:00:02 lr 0.000588	time 1.2328 (2.1919)	loss 2.9774 (3.6021)	grad_norm 1.5762 (1.4057)	
[2022-01-21 21:13:03 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 133 training takes 0:45:42
[2022-01-21 21:13:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.505 (18.505)	Loss 1.0326 (1.0326)	Acc@1 74.707 (74.707)	Acc@5 93.457 (93.457)	
[2022-01-21 21:13:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.970 (3.588)	Loss 1.0755 (1.0488)	Acc@1 74.414 (75.080)	Acc@5 92.676 (92.969)	
[2022-01-21 21:14:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.261 (2.763)	Loss 1.0352 (1.0416)	Acc@1 75.391 (75.339)	Acc@5 93.457 (93.006)	
[2022-01-21 21:14:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.269 (2.252)	Loss 1.0154 (1.0448)	Acc@1 76.074 (75.217)	Acc@5 92.871 (92.934)	
[2022-01-21 21:14:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.009 (2.137)	Loss 1.1024 (1.0473)	Acc@1 73.926 (75.138)	Acc@5 92.676 (92.966)	
[2022-01-21 21:14:38 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.164 Acc@5 92.884
[2022-01-21 21:14:38 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.2%
[2022-01-21 21:14:38 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.16%
[2022-01-21 21:14:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][0/1251]	eta 7:28:11 lr 0.000588	time 21.4957 (21.4957)	loss 3.4602 (3.4602)	grad_norm 1.4351 (1.4351)	
[2022-01-21 21:15:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][10/1251]	eta 1:26:58 lr 0.000588	time 2.5268 (4.2049)	loss 3.5177 (3.6851)	grad_norm 1.4507 (1.4633)	
[2022-01-21 21:15:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][20/1251]	eta 1:06:27 lr 0.000587	time 1.9080 (3.2391)	loss 2.7633 (3.6441)	grad_norm 1.2436 (1.4929)	
[2022-01-21 21:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][30/1251]	eta 0:59:03 lr 0.000587	time 1.5876 (2.9023)	loss 3.1971 (3.6229)	grad_norm 1.2748 (1.4418)	
[2022-01-21 21:16:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][40/1251]	eta 0:56:03 lr 0.000587	time 3.7675 (2.7778)	loss 3.1886 (3.6174)	grad_norm 1.3606 (1.4343)	
[2022-01-21 21:16:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][50/1251]	eta 0:53:33 lr 0.000587	time 1.8442 (2.6755)	loss 3.8291 (3.6180)	grad_norm 1.4942 (1.4419)	
[2022-01-21 21:17:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][60/1251]	eta 0:51:33 lr 0.000587	time 1.9555 (2.5976)	loss 2.3857 (3.5943)	grad_norm 1.4890 (1.4447)	
[2022-01-21 21:17:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][70/1251]	eta 0:49:22 lr 0.000587	time 1.8803 (2.5082)	loss 4.1263 (3.5907)	grad_norm 1.5245 (1.4513)	
[2022-01-21 21:17:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][80/1251]	eta 0:47:54 lr 0.000587	time 2.5986 (2.4548)	loss 3.8948 (3.5949)	grad_norm 1.2186 (1.4351)	
[2022-01-21 21:18:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][90/1251]	eta 0:46:33 lr 0.000587	time 2.2414 (2.4057)	loss 2.6191 (3.5832)	grad_norm 1.4389 (1.4232)	
[2022-01-21 21:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][100/1251]	eta 0:45:27 lr 0.000587	time 2.1622 (2.3696)	loss 2.8321 (3.5714)	grad_norm 1.4242 (1.4227)	
[2022-01-21 21:18:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][110/1251]	eta 0:44:29 lr 0.000587	time 1.5724 (2.3399)	loss 3.1865 (3.5761)	grad_norm 1.1909 (1.4221)	
[2022-01-21 21:19:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][120/1251]	eta 0:44:00 lr 0.000587	time 2.9661 (2.3349)	loss 3.9963 (3.5850)	grad_norm 1.7109 (1.4192)	
[2022-01-21 21:19:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][130/1251]	eta 0:43:23 lr 0.000587	time 2.4666 (2.3227)	loss 3.8813 (3.5768)	grad_norm 1.2979 (1.4120)	
[2022-01-21 21:20:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][140/1251]	eta 0:42:49 lr 0.000587	time 2.2528 (2.3131)	loss 2.9618 (3.5806)	grad_norm 1.3755 (1.4075)	
[2022-01-21 21:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][150/1251]	eta 0:42:25 lr 0.000587	time 2.3148 (2.3122)	loss 3.0636 (3.5692)	grad_norm 1.3455 (1.4075)	
[2022-01-21 21:20:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][160/1251]	eta 0:41:58 lr 0.000587	time 2.4196 (2.3081)	loss 3.7040 (3.5678)	grad_norm 1.4074 (1.4059)	
[2022-01-21 21:21:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][170/1251]	eta 0:41:38 lr 0.000587	time 2.7613 (2.3115)	loss 3.0813 (3.5439)	grad_norm 1.6153 (1.4078)	
[2022-01-21 21:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][180/1251]	eta 0:41:11 lr 0.000587	time 2.1350 (2.3072)	loss 2.9378 (3.5358)	grad_norm 1.5691 (1.4063)	
[2022-01-21 21:21:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][190/1251]	eta 0:40:44 lr 0.000587	time 1.8890 (2.3037)	loss 3.8660 (3.5453)	grad_norm 1.2594 (1.4074)	
[2022-01-21 21:22:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][200/1251]	eta 0:40:14 lr 0.000587	time 1.8324 (2.2978)	loss 3.7704 (3.5425)	grad_norm 1.6074 (1.4081)	
[2022-01-21 21:22:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][210/1251]	eta 0:39:52 lr 0.000587	time 3.4591 (2.2979)	loss 3.3005 (3.5544)	grad_norm 1.3023 (1.4075)	
[2022-01-21 21:23:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][220/1251]	eta 0:39:15 lr 0.000587	time 1.8634 (2.2844)	loss 3.7901 (3.5569)	grad_norm 1.4918 (1.4141)	
[2022-01-21 21:23:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][230/1251]	eta 0:38:40 lr 0.000587	time 1.9544 (2.2724)	loss 2.5032 (3.5565)	grad_norm 1.4689 (1.4162)	
[2022-01-21 21:23:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][240/1251]	eta 0:38:07 lr 0.000587	time 1.5968 (2.2629)	loss 3.0016 (3.5494)	grad_norm 1.3604 (1.4143)	
[2022-01-21 21:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][250/1251]	eta 0:37:45 lr 0.000587	time 2.8158 (2.2628)	loss 3.1074 (3.5528)	grad_norm 1.5490 (1.4130)	
[2022-01-21 21:24:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][260/1251]	eta 0:37:19 lr 0.000586	time 2.0426 (2.2597)	loss 4.3195 (3.5637)	grad_norm 1.4644 (1.4120)	
[2022-01-21 21:24:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][270/1251]	eta 0:36:56 lr 0.000586	time 2.1251 (2.2593)	loss 3.2953 (3.5647)	grad_norm 1.5396 (1.4125)	
[2022-01-21 21:25:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][280/1251]	eta 0:36:36 lr 0.000586	time 2.4354 (2.2621)	loss 4.3857 (3.5773)	grad_norm 1.4639 (1.4153)	
[2022-01-21 21:25:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][290/1251]	eta 0:36:15 lr 0.000586	time 2.1840 (2.2643)	loss 3.9208 (3.5900)	grad_norm 1.4281 (1.4149)	
[2022-01-21 21:25:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][300/1251]	eta 0:35:53 lr 0.000586	time 1.5557 (2.2643)	loss 3.9204 (3.5924)	grad_norm 1.3020 (1.4140)	
[2022-01-21 21:26:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][310/1251]	eta 0:35:26 lr 0.000586	time 2.4359 (2.2594)	loss 3.0950 (3.5850)	grad_norm 1.7281 (1.4134)	
[2022-01-21 21:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][320/1251]	eta 0:34:51 lr 0.000586	time 1.8856 (2.2463)	loss 4.1089 (3.5851)	grad_norm 1.6100 (1.4141)	
[2022-01-21 21:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][330/1251]	eta 0:34:26 lr 0.000586	time 2.5123 (2.2435)	loss 3.9049 (3.5739)	grad_norm 1.2329 (1.4132)	
[2022-01-21 21:27:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][340/1251]	eta 0:34:00 lr 0.000586	time 1.8272 (2.2400)	loss 3.7197 (3.5734)	grad_norm 1.3772 (1.4131)	
[2022-01-21 21:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][350/1251]	eta 0:33:39 lr 0.000586	time 2.4769 (2.2411)	loss 2.6494 (3.5715)	grad_norm 1.5659 (1.4124)	
[2022-01-21 21:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][360/1251]	eta 0:33:16 lr 0.000586	time 2.2772 (2.2407)	loss 3.6047 (3.5715)	grad_norm 1.5160 (1.4133)	
[2022-01-21 21:28:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][370/1251]	eta 0:32:50 lr 0.000586	time 2.4662 (2.2372)	loss 3.2813 (3.5775)	grad_norm 1.4373 (1.4142)	
[2022-01-21 21:28:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][380/1251]	eta 0:32:27 lr 0.000586	time 1.5939 (2.2354)	loss 4.4368 (3.5801)	grad_norm 1.3657 (1.4166)	
[2022-01-21 21:29:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][390/1251]	eta 0:32:06 lr 0.000586	time 2.6099 (2.2373)	loss 3.9629 (3.5851)	grad_norm 1.6596 (1.4184)	
[2022-01-21 21:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][400/1251]	eta 0:31:43 lr 0.000586	time 2.8133 (2.2372)	loss 4.1457 (3.5931)	grad_norm 1.4798 (1.4190)	
[2022-01-21 21:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][410/1251]	eta 0:31:20 lr 0.000586	time 2.5525 (2.2364)	loss 2.8053 (3.5940)	grad_norm 1.4665 (1.4187)	
[2022-01-21 21:30:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][420/1251]	eta 0:31:00 lr 0.000586	time 2.5279 (2.2387)	loss 2.8673 (3.5861)	grad_norm 1.2615 (1.4160)	
[2022-01-21 21:30:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][430/1251]	eta 0:30:38 lr 0.000586	time 3.1018 (2.2393)	loss 3.1385 (3.5855)	grad_norm 1.3607 (1.4157)	
[2022-01-21 21:31:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][440/1251]	eta 0:30:12 lr 0.000586	time 1.9957 (2.2355)	loss 3.1488 (3.5766)	grad_norm 1.3672 (1.4183)	
[2022-01-21 21:31:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][450/1251]	eta 0:29:46 lr 0.000586	time 2.5430 (2.2299)	loss 3.8334 (3.5687)	grad_norm 1.2713 (1.4187)	
[2022-01-21 21:31:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][460/1251]	eta 0:29:22 lr 0.000586	time 2.1872 (2.2277)	loss 3.2757 (3.5704)	grad_norm 1.5083 (1.4188)	
[2022-01-21 21:32:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][470/1251]	eta 0:29:02 lr 0.000586	time 3.1120 (2.2305)	loss 3.8561 (3.5749)	grad_norm 1.2333 (1.4183)	
[2022-01-21 21:32:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][480/1251]	eta 0:28:39 lr 0.000586	time 1.8465 (2.2308)	loss 2.9258 (3.5714)	grad_norm 1.5203 (1.4183)	
[2022-01-21 21:32:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][490/1251]	eta 0:28:16 lr 0.000586	time 2.2281 (2.2292)	loss 3.8717 (3.5720)	grad_norm 1.3628 (1.4170)	
[2022-01-21 21:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][500/1251]	eta 0:27:54 lr 0.000586	time 1.8377 (2.2292)	loss 3.9343 (3.5741)	grad_norm 1.2219 (1.4160)	
[2022-01-21 21:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][510/1251]	eta 0:27:30 lr 0.000585	time 2.2853 (2.2271)	loss 3.8024 (3.5771)	grad_norm 1.4418 (1.4150)	
[2022-01-21 21:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][520/1251]	eta 0:27:06 lr 0.000585	time 2.4975 (2.2245)	loss 3.2079 (3.5748)	grad_norm 1.3272 (1.4155)	
[2022-01-21 21:34:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][530/1251]	eta 0:26:42 lr 0.000585	time 1.8699 (2.2219)	loss 3.5638 (3.5756)	grad_norm 1.4328 (1.4152)	
[2022-01-21 21:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][540/1251]	eta 0:26:18 lr 0.000585	time 2.2075 (2.2204)	loss 3.8183 (3.5766)	grad_norm 1.6877 (1.4168)	
[2022-01-21 21:35:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][550/1251]	eta 0:25:57 lr 0.000585	time 2.6740 (2.2215)	loss 3.6980 (3.5803)	grad_norm 1.3534 (1.4170)	
[2022-01-21 21:35:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][560/1251]	eta 0:25:34 lr 0.000585	time 1.8042 (2.2203)	loss 4.0786 (3.5796)	grad_norm 1.4999 (1.4169)	
[2022-01-21 21:35:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][570/1251]	eta 0:25:12 lr 0.000585	time 2.7865 (2.2212)	loss 3.7459 (3.5838)	grad_norm 1.4864 (1.4176)	
[2022-01-21 21:36:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][580/1251]	eta 0:24:51 lr 0.000585	time 2.7639 (2.2225)	loss 3.4503 (3.5868)	grad_norm 1.4017 (1.4181)	
[2022-01-21 21:36:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][590/1251]	eta 0:24:28 lr 0.000585	time 1.5874 (2.2210)	loss 2.3590 (3.5884)	grad_norm 1.3378 (1.4181)	
[2022-01-21 21:36:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][600/1251]	eta 0:24:05 lr 0.000585	time 1.8280 (2.2200)	loss 3.1484 (3.5841)	grad_norm 1.4556 (1.4201)	
[2022-01-21 21:37:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][610/1251]	eta 0:23:41 lr 0.000585	time 2.3128 (2.2179)	loss 3.9060 (3.5840)	grad_norm 1.8234 (1.4227)	
[2022-01-21 21:37:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][620/1251]	eta 0:23:19 lr 0.000585	time 2.3470 (2.2178)	loss 4.2359 (3.5893)	grad_norm 1.4403 (1.4221)	
[2022-01-21 21:37:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][630/1251]	eta 0:22:57 lr 0.000585	time 1.9381 (2.2174)	loss 4.2794 (3.5904)	grad_norm 1.6384 (1.4222)	
[2022-01-21 21:38:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][640/1251]	eta 0:22:34 lr 0.000585	time 1.9348 (2.2168)	loss 3.9832 (3.5951)	grad_norm 1.3884 (1.4220)	
[2022-01-21 21:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][650/1251]	eta 0:22:12 lr 0.000585	time 2.5746 (2.2171)	loss 3.3381 (3.5994)	grad_norm 1.1980 (1.4212)	
[2022-01-21 21:39:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][660/1251]	eta 0:21:49 lr 0.000585	time 1.8342 (2.2165)	loss 3.5592 (3.5986)	grad_norm 1.5343 (1.4213)	
[2022-01-21 21:39:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][670/1251]	eta 0:21:28 lr 0.000585	time 3.1288 (2.2182)	loss 3.9197 (3.5982)	grad_norm 1.1785 (1.4214)	
[2022-01-21 21:39:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][680/1251]	eta 0:21:07 lr 0.000585	time 1.8541 (2.2189)	loss 3.6281 (3.5979)	grad_norm 1.4582 (1.4212)	
[2022-01-21 21:40:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][690/1251]	eta 0:20:44 lr 0.000585	time 1.8867 (2.2190)	loss 3.0855 (3.5966)	grad_norm 1.2543 (1.4208)	
[2022-01-21 21:40:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][700/1251]	eta 0:20:22 lr 0.000585	time 2.4972 (2.2190)	loss 3.0815 (3.5901)	grad_norm 1.4779 (1.4210)	
[2022-01-21 21:40:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][710/1251]	eta 0:19:59 lr 0.000585	time 1.9338 (2.2167)	loss 3.3397 (3.5890)	grad_norm 1.4126 (1.4210)	
[2022-01-21 21:41:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][720/1251]	eta 0:19:34 lr 0.000585	time 2.0298 (2.2128)	loss 4.2777 (3.5920)	grad_norm 1.4278 (1.4205)	
[2022-01-21 21:41:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][730/1251]	eta 0:19:11 lr 0.000585	time 2.1614 (2.2103)	loss 2.7404 (3.5931)	grad_norm 1.3423 (1.4199)	
[2022-01-21 21:41:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][740/1251]	eta 0:18:48 lr 0.000585	time 2.2456 (2.2091)	loss 3.7093 (3.5930)	grad_norm 1.3903 (1.4212)	
[2022-01-21 21:42:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][750/1251]	eta 0:18:26 lr 0.000584	time 2.0779 (2.2085)	loss 2.7552 (3.5951)	grad_norm 1.5624 (1.4219)	
[2022-01-21 21:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][760/1251]	eta 0:18:04 lr 0.000584	time 1.9650 (2.2087)	loss 3.9501 (3.5926)	grad_norm 1.4067 (1.4218)	
[2022-01-21 21:43:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][770/1251]	eta 0:17:43 lr 0.000584	time 1.5551 (2.2112)	loss 3.9826 (3.5951)	grad_norm 1.3443 (1.4219)	
[2022-01-21 21:43:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][780/1251]	eta 0:17:21 lr 0.000584	time 1.9978 (2.2111)	loss 3.8210 (3.5997)	grad_norm 1.4562 (1.4220)	
[2022-01-21 21:43:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][790/1251]	eta 0:16:59 lr 0.000584	time 2.0427 (2.2107)	loss 3.1625 (3.6002)	grad_norm 1.3677 (1.4218)	
[2022-01-21 21:44:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][800/1251]	eta 0:16:36 lr 0.000584	time 2.6380 (2.2103)	loss 2.5291 (3.5998)	grad_norm 1.2005 (1.4202)	
[2022-01-21 21:44:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][810/1251]	eta 0:16:15 lr 0.000584	time 1.8104 (2.2114)	loss 3.9327 (3.6028)	grad_norm 1.1650 (1.4199)	
[2022-01-21 21:44:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][820/1251]	eta 0:15:53 lr 0.000584	time 2.4942 (2.2124)	loss 3.4008 (3.6018)	grad_norm 1.1964 (1.4207)	
[2022-01-21 21:45:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][830/1251]	eta 0:15:31 lr 0.000584	time 1.9359 (2.2117)	loss 4.3072 (3.6036)	grad_norm 1.4871 (1.4203)	
[2022-01-21 21:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][840/1251]	eta 0:15:08 lr 0.000584	time 2.5544 (2.2096)	loss 3.7143 (3.6041)	grad_norm 1.3367 (1.4204)	
[2022-01-21 21:45:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][850/1251]	eta 0:14:44 lr 0.000584	time 1.9757 (2.2059)	loss 3.6273 (3.6034)	grad_norm 1.2266 (1.4194)	
[2022-01-21 21:46:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][860/1251]	eta 0:14:22 lr 0.000584	time 2.1823 (2.2052)	loss 4.0359 (3.6019)	grad_norm 1.3069 (1.4190)	
[2022-01-21 21:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][870/1251]	eta 0:14:00 lr 0.000584	time 1.6224 (2.2048)	loss 4.1509 (3.6020)	grad_norm 1.2643 (1.4188)	
[2022-01-21 21:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][880/1251]	eta 0:13:38 lr 0.000584	time 1.5562 (2.2050)	loss 4.3965 (3.6020)	grad_norm 1.6280 (1.4189)	
[2022-01-21 21:47:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][890/1251]	eta 0:13:15 lr 0.000584	time 1.7900 (2.2043)	loss 3.6665 (3.6031)	grad_norm 1.3311 (1.4191)	
[2022-01-21 21:47:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][900/1251]	eta 0:12:54 lr 0.000584	time 2.5064 (2.2079)	loss 4.0296 (3.6056)	grad_norm 1.1826 (1.4191)	
[2022-01-21 21:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][910/1251]	eta 0:12:32 lr 0.000584	time 1.5622 (2.2078)	loss 3.6221 (3.6055)	grad_norm 1.2139 (1.4181)	
[2022-01-21 21:48:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][920/1251]	eta 0:12:11 lr 0.000584	time 1.4705 (2.2089)	loss 3.4497 (3.6052)	grad_norm 1.6625 (1.4183)	
[2022-01-21 21:48:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][930/1251]	eta 0:11:49 lr 0.000584	time 1.5564 (2.2115)	loss 3.8050 (3.6032)	grad_norm 1.4381 (1.4180)	
[2022-01-21 21:49:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][940/1251]	eta 0:11:27 lr 0.000584	time 1.8810 (2.2118)	loss 3.1876 (3.6019)	grad_norm 1.4966 (1.4179)	
[2022-01-21 21:49:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][950/1251]	eta 0:11:05 lr 0.000584	time 1.9320 (2.2106)	loss 3.5652 (3.6002)	grad_norm 1.3662 (1.4181)	
[2022-01-21 21:50:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][960/1251]	eta 0:10:42 lr 0.000584	time 2.1996 (2.2096)	loss 3.2816 (3.5992)	grad_norm 1.3426 (1.4174)	
[2022-01-21 21:50:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][970/1251]	eta 0:10:20 lr 0.000584	time 1.6365 (2.2082)	loss 3.6991 (3.6026)	grad_norm 1.3204 (1.4170)	
[2022-01-21 21:50:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][980/1251]	eta 0:09:58 lr 0.000584	time 2.1653 (2.2090)	loss 3.4663 (3.6016)	grad_norm 1.5912 (1.4168)	
[2022-01-21 21:51:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][990/1251]	eta 0:09:36 lr 0.000584	time 2.1979 (2.2098)	loss 4.0084 (3.5977)	grad_norm 1.6466 (1.4180)	
[2022-01-21 21:51:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1000/1251]	eta 0:09:14 lr 0.000583	time 2.2555 (2.2086)	loss 4.2401 (3.5981)	grad_norm 1.5321 (1.4177)	
[2022-01-21 21:51:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1010/1251]	eta 0:08:51 lr 0.000583	time 1.7166 (2.2067)	loss 3.6850 (3.6008)	grad_norm 1.5671 (1.4173)	
[2022-01-21 21:52:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1020/1251]	eta 0:08:29 lr 0.000583	time 1.8570 (2.2071)	loss 3.7924 (3.6003)	grad_norm 1.3934 (1.4168)	
[2022-01-21 21:52:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1030/1251]	eta 0:08:07 lr 0.000583	time 2.2497 (2.2064)	loss 2.4318 (3.5994)	grad_norm 1.5389 (1.4166)	
[2022-01-21 21:52:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1040/1251]	eta 0:07:45 lr 0.000583	time 1.8782 (2.2048)	loss 3.8895 (3.6006)	grad_norm 1.3628 (1.4161)	
[2022-01-21 21:53:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1050/1251]	eta 0:07:23 lr 0.000583	time 1.7868 (2.2045)	loss 3.2948 (3.6010)	grad_norm 1.4578 (1.4170)	
[2022-01-21 21:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1060/1251]	eta 0:07:01 lr 0.000583	time 2.6839 (2.2054)	loss 2.6738 (3.6019)	grad_norm 1.4987 (1.4168)	
[2022-01-21 21:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1070/1251]	eta 0:06:39 lr 0.000583	time 2.0723 (2.2051)	loss 4.2713 (3.6021)	grad_norm 1.3823 (1.4171)	
[2022-01-21 21:54:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1080/1251]	eta 0:06:16 lr 0.000583	time 2.2204 (2.2045)	loss 3.5508 (3.6005)	grad_norm 1.4318 (1.4170)	
[2022-01-21 21:54:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1090/1251]	eta 0:05:54 lr 0.000583	time 1.6133 (2.2045)	loss 3.3498 (3.5998)	grad_norm 1.3216 (1.4170)	
[2022-01-21 21:55:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1100/1251]	eta 0:05:32 lr 0.000583	time 2.1223 (2.2051)	loss 3.7630 (3.6005)	grad_norm 1.4551 (1.4170)	
[2022-01-21 21:55:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1110/1251]	eta 0:05:11 lr 0.000583	time 2.7623 (2.2060)	loss 3.0322 (3.6012)	grad_norm 1.4213 (1.4170)	
[2022-01-21 21:55:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1120/1251]	eta 0:04:48 lr 0.000583	time 1.8838 (2.2041)	loss 3.5845 (3.6002)	grad_norm 1.6130 (1.4174)	
[2022-01-21 21:56:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1130/1251]	eta 0:04:26 lr 0.000583	time 2.1582 (2.2027)	loss 2.6300 (3.6007)	grad_norm 1.5093 (1.4172)	
[2022-01-21 21:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1140/1251]	eta 0:04:04 lr 0.000583	time 2.3811 (2.2036)	loss 4.2061 (3.6013)	grad_norm 1.3492 (1.4165)	
[2022-01-21 21:56:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1150/1251]	eta 0:03:42 lr 0.000583	time 2.2363 (2.2042)	loss 3.7662 (3.6038)	grad_norm 1.6289 (1.4171)	
[2022-01-21 21:57:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1160/1251]	eta 0:03:20 lr 0.000583	time 1.7072 (2.2038)	loss 3.5230 (3.6033)	grad_norm 1.2667 (1.4172)	
[2022-01-21 21:57:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1170/1251]	eta 0:02:58 lr 0.000583	time 2.1970 (2.2026)	loss 2.2949 (3.6027)	grad_norm 1.2937 (1.4170)	
[2022-01-21 21:57:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1180/1251]	eta 0:02:36 lr 0.000583	time 2.4722 (2.2015)	loss 4.0729 (3.6036)	grad_norm 1.3812 (1.4166)	
[2022-01-21 21:58:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1190/1251]	eta 0:02:14 lr 0.000583	time 2.1786 (2.2019)	loss 3.1713 (3.6006)	grad_norm 1.4404 (1.4162)	
[2022-01-21 21:58:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1200/1251]	eta 0:01:52 lr 0.000583	time 1.9140 (2.2022)	loss 3.2912 (3.6007)	grad_norm 1.1795 (1.4156)	
[2022-01-21 21:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1210/1251]	eta 0:01:30 lr 0.000583	time 2.2047 (2.2018)	loss 3.7788 (3.6014)	grad_norm 1.2379 (1.4145)	
[2022-01-21 21:59:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1220/1251]	eta 0:01:08 lr 0.000583	time 3.0860 (2.2022)	loss 3.4036 (3.6014)	grad_norm 1.3148 (1.4144)	
[2022-01-21 21:59:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1230/1251]	eta 0:00:46 lr 0.000583	time 1.9758 (2.2023)	loss 3.3451 (3.6025)	grad_norm 1.2158 (1.4139)	
[2022-01-21 22:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1240/1251]	eta 0:00:24 lr 0.000582	time 1.1964 (2.2015)	loss 3.2240 (3.6006)	grad_norm 1.3592 (1.4133)	
[2022-01-21 22:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [134/300][1250/1251]	eta 0:00:02 lr 0.000582	time 1.1934 (2.1969)	loss 3.6332 (3.6000)	grad_norm 1.4180 (1.4130)	
[2022-01-21 22:00:26 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 134 training takes 0:45:48
[2022-01-21 22:00:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 20.834 (20.834)	Loss 0.9621 (0.9621)	Acc@1 76.172 (76.172)	Acc@5 93.848 (93.848)	
[2022-01-21 22:01:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.630 (3.172)	Loss 1.0216 (1.0313)	Acc@1 76.270 (75.328)	Acc@5 92.480 (92.978)	
[2022-01-21 22:01:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 2.360 (2.555)	Loss 0.9491 (1.0201)	Acc@1 77.344 (75.535)	Acc@5 93.457 (93.127)	
[2022-01-21 22:01:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.625 (2.303)	Loss 1.0674 (1.0381)	Acc@1 73.730 (75.176)	Acc@5 92.578 (92.921)	
[2022-01-21 22:01:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.215 (2.201)	Loss 1.0455 (1.0370)	Acc@1 76.465 (75.243)	Acc@5 92.676 (92.976)	
[2022-01-21 22:02:04 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.248 Acc@5 93.006
[2022-01-21 22:02:04 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.2%
[2022-01-21 22:02:04 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.25%
[2022-01-21 22:02:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][0/1251]	eta 7:26:13 lr 0.000582	time 21.4014 (21.4014)	loss 4.2354 (4.2354)	grad_norm 1.3848 (1.3848)	
[2022-01-21 22:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][10/1251]	eta 1:24:36 lr 0.000582	time 2.0518 (4.0903)	loss 3.3111 (3.4470)	grad_norm 1.3100 (1.3541)	
[2022-01-21 22:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][20/1251]	eta 1:04:48 lr 0.000582	time 1.5133 (3.1584)	loss 4.0421 (3.5446)	grad_norm 1.4564 (1.4171)	
[2022-01-21 22:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][30/1251]	eta 0:57:43 lr 0.000582	time 1.5132 (2.8363)	loss 3.3703 (3.5069)	grad_norm 1.3873 (1.3940)	
[2022-01-21 22:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][40/1251]	eta 0:55:09 lr 0.000582	time 3.9799 (2.7326)	loss 3.2343 (3.5373)	grad_norm 1.2349 (1.4180)	
[2022-01-21 22:04:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][50/1251]	eta 0:52:45 lr 0.000582	time 2.1831 (2.6358)	loss 4.2719 (3.5470)	grad_norm 1.2742 (1.4323)	
[2022-01-21 22:04:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][60/1251]	eta 0:51:15 lr 0.000582	time 2.3793 (2.5823)	loss 3.9145 (3.5770)	grad_norm 1.3211 (1.4190)	
[2022-01-21 22:05:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][70/1251]	eta 0:49:52 lr 0.000582	time 1.8946 (2.5342)	loss 3.1509 (3.5381)	grad_norm 1.4319 (1.4251)	
[2022-01-21 22:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][80/1251]	eta 0:48:42 lr 0.000582	time 2.6083 (2.4956)	loss 3.7914 (3.5566)	grad_norm 1.5694 (1.4304)	
[2022-01-21 22:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][90/1251]	eta 0:47:17 lr 0.000582	time 2.8670 (2.4441)	loss 3.5176 (3.5981)	grad_norm 1.1926 (1.4305)	
[2022-01-21 22:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][100/1251]	eta 0:46:06 lr 0.000582	time 2.1480 (2.4035)	loss 3.9076 (3.5924)	grad_norm 1.4636 (1.4243)	
[2022-01-21 22:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][110/1251]	eta 0:45:02 lr 0.000582	time 1.9113 (2.3689)	loss 4.4067 (3.6058)	grad_norm 1.7003 (1.4256)	
[2022-01-21 22:06:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][120/1251]	eta 0:44:08 lr 0.000582	time 1.9885 (2.3420)	loss 2.9468 (3.6123)	grad_norm 1.5853 (1.4290)	
[2022-01-21 22:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][130/1251]	eta 0:43:35 lr 0.000582	time 1.9555 (2.3332)	loss 3.8177 (3.6206)	grad_norm 1.5253 (1.4236)	
[2022-01-21 22:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][140/1251]	eta 0:43:13 lr 0.000582	time 2.3975 (2.3346)	loss 3.0656 (3.6261)	grad_norm 1.5656 (1.4197)	
[2022-01-21 22:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][150/1251]	eta 0:42:44 lr 0.000582	time 1.8897 (2.3293)	loss 4.0116 (3.6355)	grad_norm 1.4630 (1.4204)	
[2022-01-21 22:08:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][160/1251]	eta 0:42:11 lr 0.000582	time 2.1968 (2.3200)	loss 3.3488 (3.6434)	grad_norm 1.2248 (1.4140)	
[2022-01-21 22:08:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][170/1251]	eta 0:41:50 lr 0.000582	time 3.4494 (2.3223)	loss 3.9726 (3.6340)	grad_norm 1.4119 (1.4157)	
[2022-01-21 22:09:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][180/1251]	eta 0:41:13 lr 0.000582	time 1.7430 (2.3092)	loss 3.8817 (3.6441)	grad_norm 1.5791 (1.4155)	
[2022-01-21 22:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][190/1251]	eta 0:40:52 lr 0.000582	time 1.8855 (2.3119)	loss 4.2446 (3.6530)	grad_norm 1.4605 (1.4159)	
[2022-01-21 22:09:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][200/1251]	eta 0:40:20 lr 0.000582	time 1.6384 (2.3029)	loss 4.1795 (3.6589)	grad_norm 1.5792 (1.4145)	
[2022-01-21 22:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][210/1251]	eta 0:40:03 lr 0.000582	time 3.2743 (2.3089)	loss 3.8016 (3.6519)	grad_norm 1.2426 (1.4146)	
[2022-01-21 22:10:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][220/1251]	eta 0:39:26 lr 0.000582	time 1.8981 (2.2949)	loss 3.1121 (3.6470)	grad_norm 1.2642 (1.4123)	
[2022-01-21 22:10:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][230/1251]	eta 0:38:54 lr 0.000581	time 1.9685 (2.2867)	loss 2.9767 (3.6404)	grad_norm 1.4563 (1.4109)	
[2022-01-21 22:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][240/1251]	eta 0:38:24 lr 0.000581	time 1.6339 (2.2799)	loss 3.5375 (3.6414)	grad_norm 1.3686 (1.4102)	
[2022-01-21 22:11:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][250/1251]	eta 0:38:07 lr 0.000581	time 3.0391 (2.2856)	loss 3.4007 (3.6407)	grad_norm 1.2414 (1.4080)	
[2022-01-21 22:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][260/1251]	eta 0:37:39 lr 0.000581	time 1.8907 (2.2797)	loss 2.5444 (3.6398)	grad_norm 1.2142 (1.4060)	
[2022-01-21 22:12:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][270/1251]	eta 0:37:05 lr 0.000581	time 1.6216 (2.2688)	loss 3.7025 (3.6290)	grad_norm 1.2944 (1.4060)	
[2022-01-21 22:12:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][280/1251]	eta 0:36:38 lr 0.000581	time 2.0260 (2.2638)	loss 4.2872 (3.6331)	grad_norm 1.2807 (1.4079)	
[2022-01-21 22:13:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][290/1251]	eta 0:36:13 lr 0.000581	time 2.2534 (2.2621)	loss 3.5424 (3.6320)	grad_norm 1.3671 (1.4070)	
[2022-01-21 22:13:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][300/1251]	eta 0:35:50 lr 0.000581	time 2.4758 (2.2611)	loss 3.4192 (3.6217)	grad_norm 1.3197 (1.4038)	
[2022-01-21 22:13:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][310/1251]	eta 0:35:27 lr 0.000581	time 1.9388 (2.2610)	loss 3.5869 (3.6288)	grad_norm 1.2686 (1.4018)	
[2022-01-21 22:14:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][320/1251]	eta 0:35:00 lr 0.000581	time 1.6343 (2.2564)	loss 4.0677 (3.6340)	grad_norm 1.5182 (1.4034)	
[2022-01-21 22:14:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][330/1251]	eta 0:34:31 lr 0.000581	time 1.8990 (2.2491)	loss 3.6206 (3.6375)	grad_norm 1.4166 (1.4049)	
[2022-01-21 22:14:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][340/1251]	eta 0:34:02 lr 0.000581	time 2.0645 (2.2419)	loss 3.2162 (3.6253)	grad_norm 1.2690 (1.4044)	
[2022-01-21 22:15:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][350/1251]	eta 0:33:38 lr 0.000581	time 2.5007 (2.2398)	loss 3.9158 (3.6254)	grad_norm 1.3948 (1.4041)	
[2022-01-21 22:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][360/1251]	eta 0:33:14 lr 0.000581	time 2.1242 (2.2381)	loss 4.3097 (3.6220)	grad_norm 1.2069 (1.4035)	
[2022-01-21 22:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][370/1251]	eta 0:32:52 lr 0.000581	time 1.8848 (2.2390)	loss 4.2390 (3.6253)	grad_norm 1.4009 (1.4043)	
[2022-01-21 22:16:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][380/1251]	eta 0:32:30 lr 0.000581	time 2.2364 (2.2388)	loss 3.3021 (3.6258)	grad_norm 1.3692 (1.4028)	
[2022-01-21 22:16:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][390/1251]	eta 0:32:09 lr 0.000581	time 3.1805 (2.2408)	loss 2.5329 (3.6264)	grad_norm 1.7546 (1.4028)	
[2022-01-21 22:17:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][400/1251]	eta 0:31:47 lr 0.000581	time 2.8381 (2.2418)	loss 3.5889 (3.6250)	grad_norm 1.3790 (1.4034)	
[2022-01-21 22:17:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][410/1251]	eta 0:31:26 lr 0.000581	time 1.9664 (2.2431)	loss 2.6817 (3.6245)	grad_norm 1.4623 (1.4041)	
[2022-01-21 22:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][420/1251]	eta 0:31:04 lr 0.000581	time 2.6483 (2.2431)	loss 2.5429 (3.6195)	grad_norm 1.3673 (1.4033)	
[2022-01-21 22:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][430/1251]	eta 0:30:40 lr 0.000581	time 1.7927 (2.2415)	loss 3.6755 (3.6189)	grad_norm 1.6128 (1.4025)	
[2022-01-21 22:18:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][440/1251]	eta 0:30:16 lr 0.000581	time 1.7864 (2.2400)	loss 3.8617 (3.6229)	grad_norm 1.3348 (1.4023)	
[2022-01-21 22:18:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][450/1251]	eta 0:29:47 lr 0.000581	time 1.8887 (2.2319)	loss 2.6835 (3.6248)	grad_norm 1.3682 (1.4020)	
[2022-01-21 22:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][460/1251]	eta 0:29:20 lr 0.000581	time 1.8246 (2.2263)	loss 3.9868 (3.6260)	grad_norm 1.4036 (1.4019)	
[2022-01-21 22:19:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][470/1251]	eta 0:28:57 lr 0.000581	time 2.5585 (2.2246)	loss 3.6165 (3.6283)	grad_norm 1.3824 (1.4021)	
[2022-01-21 22:19:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][480/1251]	eta 0:28:32 lr 0.000580	time 1.7145 (2.2218)	loss 3.2221 (3.6334)	grad_norm 1.4114 (1.4023)	
[2022-01-21 22:20:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][490/1251]	eta 0:28:09 lr 0.000580	time 2.8151 (2.2195)	loss 3.9783 (3.6365)	grad_norm 1.4849 (1.4020)	
[2022-01-21 22:20:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][500/1251]	eta 0:27:45 lr 0.000580	time 2.1835 (2.2176)	loss 3.5872 (3.6301)	grad_norm 1.2703 (1.4029)	
[2022-01-21 22:20:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][510/1251]	eta 0:27:25 lr 0.000580	time 2.7595 (2.2204)	loss 3.3969 (3.6309)	grad_norm 1.4690 (1.4035)	
[2022-01-21 22:21:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][520/1251]	eta 0:27:03 lr 0.000580	time 1.7390 (2.2211)	loss 3.0991 (3.6348)	grad_norm 1.6463 (1.4039)	
[2022-01-21 22:21:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][530/1251]	eta 0:26:42 lr 0.000580	time 1.9357 (2.2226)	loss 3.9168 (3.6307)	grad_norm 1.5149 (1.4048)	
[2022-01-21 22:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][540/1251]	eta 0:26:19 lr 0.000580	time 1.7845 (2.2215)	loss 4.5201 (3.6344)	grad_norm 1.3532 (1.4062)	
[2022-01-21 22:22:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][550/1251]	eta 0:25:55 lr 0.000580	time 2.2600 (2.2184)	loss 4.1229 (3.6367)	grad_norm 1.2036 (1.4049)	
[2022-01-21 22:22:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][560/1251]	eta 0:25:31 lr 0.000580	time 2.1051 (2.2160)	loss 2.6018 (3.6335)	grad_norm 1.1495 (1.4040)	
[2022-01-21 22:23:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][570/1251]	eta 0:25:08 lr 0.000580	time 2.6990 (2.2156)	loss 3.5479 (3.6323)	grad_norm 1.2553 (1.4041)	
[2022-01-21 22:23:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][580/1251]	eta 0:24:47 lr 0.000580	time 2.1613 (2.2164)	loss 3.9655 (3.6331)	grad_norm 1.1241 (1.4028)	
[2022-01-21 22:23:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][590/1251]	eta 0:24:23 lr 0.000580	time 2.2730 (2.2142)	loss 3.8066 (3.6333)	grad_norm 1.3306 (1.4035)	
[2022-01-21 22:24:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][600/1251]	eta 0:24:00 lr 0.000580	time 2.2829 (2.2133)	loss 4.0118 (3.6358)	grad_norm 1.3727 (1.4025)	
[2022-01-21 22:24:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][610/1251]	eta 0:23:38 lr 0.000580	time 2.7848 (2.2130)	loss 3.5577 (3.6389)	grad_norm 1.4187 (1.4033)	
[2022-01-21 22:24:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][620/1251]	eta 0:23:14 lr 0.000580	time 1.8798 (2.2096)	loss 4.4957 (3.6365)	grad_norm 1.5317 (1.4029)	
[2022-01-21 22:25:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][630/1251]	eta 0:22:51 lr 0.000580	time 2.5470 (2.2083)	loss 3.9462 (3.6312)	grad_norm 1.6401 (1.4040)	
[2022-01-21 22:25:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][640/1251]	eta 0:22:29 lr 0.000580	time 2.0391 (2.2087)	loss 3.9486 (3.6296)	grad_norm 1.6263 (1.4037)	
[2022-01-21 22:26:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][650/1251]	eta 0:22:08 lr 0.000580	time 2.8846 (2.2112)	loss 3.3531 (3.6290)	grad_norm 1.3933 (1.4033)	
[2022-01-21 22:26:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][660/1251]	eta 0:21:46 lr 0.000580	time 2.2169 (2.2105)	loss 3.6474 (3.6263)	grad_norm 1.2965 (1.4029)	
[2022-01-21 22:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][670/1251]	eta 0:21:23 lr 0.000580	time 2.8484 (2.2100)	loss 3.7931 (3.6275)	grad_norm 1.9214 (1.4036)	
[2022-01-21 22:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][680/1251]	eta 0:21:02 lr 0.000580	time 1.9544 (2.2105)	loss 3.2855 (3.6271)	grad_norm 1.8192 (1.4044)	
[2022-01-21 22:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][690/1251]	eta 0:20:39 lr 0.000580	time 2.5156 (2.2088)	loss 4.2956 (3.6281)	grad_norm 1.4892 (1.4047)	
[2022-01-21 22:27:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][700/1251]	eta 0:20:17 lr 0.000580	time 1.9051 (2.2088)	loss 4.3382 (3.6249)	grad_norm 1.3216 (1.4049)	
[2022-01-21 22:28:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][710/1251]	eta 0:19:54 lr 0.000580	time 1.9787 (2.2079)	loss 3.5759 (3.6236)	grad_norm 1.3780 (1.4050)	
[2022-01-21 22:28:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][720/1251]	eta 0:19:33 lr 0.000579	time 1.7432 (2.2104)	loss 4.4247 (3.6276)	grad_norm 1.4787 (1.4054)	
[2022-01-21 22:29:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][730/1251]	eta 0:19:12 lr 0.000579	time 1.8836 (2.2121)	loss 2.9390 (3.6253)	grad_norm 1.3648 (1.4065)	
[2022-01-21 22:29:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][740/1251]	eta 0:18:51 lr 0.000579	time 2.3032 (2.2137)	loss 3.5352 (3.6233)	grad_norm 1.2470 (1.4055)	
[2022-01-21 22:29:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][750/1251]	eta 0:18:28 lr 0.000579	time 1.9638 (2.2125)	loss 4.2877 (3.6273)	grad_norm 1.4182 (1.4065)	
[2022-01-21 22:30:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][760/1251]	eta 0:18:06 lr 0.000579	time 1.7655 (2.2124)	loss 2.9416 (3.6273)	grad_norm 1.5021 (1.4101)	
[2022-01-21 22:30:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][770/1251]	eta 0:17:43 lr 0.000579	time 1.8800 (2.2108)	loss 4.2094 (3.6281)	grad_norm 1.3353 (1.4102)	
[2022-01-21 22:30:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][780/1251]	eta 0:17:20 lr 0.000579	time 1.5134 (2.2085)	loss 2.8862 (3.6277)	grad_norm 1.3208 (1.4111)	
[2022-01-21 22:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][790/1251]	eta 0:16:58 lr 0.000579	time 1.8505 (2.2096)	loss 4.0329 (3.6257)	grad_norm 1.1700 (1.4113)	
[2022-01-21 22:31:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][800/1251]	eta 0:16:37 lr 0.000579	time 2.0118 (2.2108)	loss 3.9529 (3.6269)	grad_norm 1.2544 (1.4109)	
[2022-01-21 22:31:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][810/1251]	eta 0:16:14 lr 0.000579	time 1.6079 (2.2100)	loss 3.8413 (3.6297)	grad_norm 1.3589 (1.4100)	
[2022-01-21 22:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][820/1251]	eta 0:15:51 lr 0.000579	time 1.7844 (2.2087)	loss 2.9728 (3.6277)	grad_norm 1.2702 (1.4106)	
[2022-01-21 22:32:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][830/1251]	eta 0:15:28 lr 0.000579	time 2.2072 (2.2065)	loss 3.8859 (3.6257)	grad_norm 1.3400 (1.4110)	
[2022-01-21 22:32:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][840/1251]	eta 0:15:06 lr 0.000579	time 2.0526 (2.2051)	loss 2.6932 (3.6228)	grad_norm 1.3132 (1.4113)	
[2022-01-21 22:33:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][850/1251]	eta 0:14:44 lr 0.000579	time 2.1009 (2.2054)	loss 3.7107 (3.6249)	grad_norm 1.5202 (1.4130)	
[2022-01-21 22:33:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][860/1251]	eta 0:14:22 lr 0.000579	time 2.0860 (2.2049)	loss 3.1896 (3.6237)	grad_norm 1.3438 (1.4142)	
[2022-01-21 22:34:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][870/1251]	eta 0:14:01 lr 0.000579	time 2.1812 (2.2075)	loss 4.1293 (3.6233)	grad_norm 1.4001 (1.4149)	
[2022-01-21 22:34:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][880/1251]	eta 0:13:39 lr 0.000579	time 2.1087 (2.2079)	loss 4.0121 (3.6238)	grad_norm 1.2511 (1.4152)	
[2022-01-21 22:34:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][890/1251]	eta 0:13:17 lr 0.000579	time 1.8800 (2.2078)	loss 4.0402 (3.6247)	grad_norm 1.3181 (1.4147)	
[2022-01-21 22:35:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][900/1251]	eta 0:12:54 lr 0.000579	time 2.0393 (2.2069)	loss 3.0773 (3.6222)	grad_norm 1.3168 (1.4142)	
[2022-01-21 22:35:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][910/1251]	eta 0:12:32 lr 0.000579	time 2.6358 (2.2077)	loss 4.1016 (3.6230)	grad_norm 1.4149 (1.4136)	
[2022-01-21 22:35:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][920/1251]	eta 0:12:10 lr 0.000579	time 1.8883 (2.2057)	loss 4.0229 (3.6218)	grad_norm 1.3560 (1.4126)	
[2022-01-21 22:36:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][930/1251]	eta 0:11:47 lr 0.000579	time 1.8334 (2.2041)	loss 3.9870 (3.6186)	grad_norm 1.2354 (1.4121)	
[2022-01-21 22:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][940/1251]	eta 0:11:25 lr 0.000579	time 1.9445 (2.2029)	loss 3.7102 (3.6190)	grad_norm 1.5522 (1.4120)	
[2022-01-21 22:36:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][950/1251]	eta 0:11:02 lr 0.000579	time 2.4285 (2.2025)	loss 4.0165 (3.6192)	grad_norm 1.2944 (1.4121)	
[2022-01-21 22:37:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][960/1251]	eta 0:10:41 lr 0.000579	time 2.1940 (2.2038)	loss 4.0853 (3.6192)	grad_norm 1.1261 (1.4122)	
[2022-01-21 22:37:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][970/1251]	eta 0:10:19 lr 0.000578	time 2.4623 (2.2039)	loss 3.5720 (3.6153)	grad_norm 1.5360 (1.4135)	
[2022-01-21 22:38:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][980/1251]	eta 0:09:57 lr 0.000578	time 2.5447 (2.2051)	loss 4.2100 (3.6168)	grad_norm 1.3883 (1.4134)	
[2022-01-21 22:38:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][990/1251]	eta 0:09:35 lr 0.000578	time 1.9851 (2.2042)	loss 4.2890 (3.6179)	grad_norm 1.3441 (1.4133)	
[2022-01-21 22:38:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1000/1251]	eta 0:09:13 lr 0.000578	time 1.8683 (2.2050)	loss 2.8065 (3.6169)	grad_norm 1.3147 (1.4127)	
[2022-01-21 22:39:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1010/1251]	eta 0:08:51 lr 0.000578	time 1.9026 (2.2046)	loss 3.1171 (3.6149)	grad_norm 1.4837 (1.4129)	
[2022-01-21 22:39:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1020/1251]	eta 0:08:29 lr 0.000578	time 2.7391 (2.2036)	loss 3.8409 (3.6158)	grad_norm 1.2153 (1.4134)	
[2022-01-21 22:39:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1030/1251]	eta 0:08:06 lr 0.000578	time 1.5849 (2.2023)	loss 2.4363 (3.6119)	grad_norm 1.2945 (1.4128)	
[2022-01-21 22:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1040/1251]	eta 0:07:44 lr 0.000578	time 2.0795 (2.2018)	loss 4.1819 (3.6110)	grad_norm 2.0922 (1.4128)	
[2022-01-21 22:40:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1050/1251]	eta 0:07:22 lr 0.000578	time 1.7390 (2.2021)	loss 4.0906 (3.6120)	grad_norm 1.6189 (1.4133)	
[2022-01-21 22:41:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1060/1251]	eta 0:07:00 lr 0.000578	time 2.2911 (2.2022)	loss 3.5240 (3.6120)	grad_norm 1.6088 (1.4137)	
[2022-01-21 22:41:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1070/1251]	eta 0:06:38 lr 0.000578	time 2.4828 (2.2029)	loss 3.4877 (3.6131)	grad_norm 1.4098 (1.4143)	
[2022-01-21 22:41:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1080/1251]	eta 0:06:16 lr 0.000578	time 2.1908 (2.2018)	loss 2.7569 (3.6123)	grad_norm 1.8534 (1.4149)	
[2022-01-21 22:42:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1090/1251]	eta 0:05:54 lr 0.000578	time 1.6427 (2.2015)	loss 3.0451 (3.6104)	grad_norm 1.3627 (1.4154)	
[2022-01-21 22:42:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1100/1251]	eta 0:05:32 lr 0.000578	time 2.2740 (2.2000)	loss 3.8759 (3.6126)	grad_norm 1.5735 (1.4156)	
[2022-01-21 22:42:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1110/1251]	eta 0:05:10 lr 0.000578	time 2.2568 (2.1987)	loss 3.4129 (3.6105)	grad_norm 1.3956 (1.4157)	
[2022-01-21 22:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1120/1251]	eta 0:04:47 lr 0.000578	time 1.8217 (2.1978)	loss 3.9565 (3.6090)	grad_norm 1.3854 (1.4163)	
[2022-01-21 22:43:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1130/1251]	eta 0:04:25 lr 0.000578	time 1.7504 (2.1959)	loss 4.4012 (3.6087)	grad_norm 1.5254 (1.4161)	
[2022-01-21 22:43:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1140/1251]	eta 0:04:03 lr 0.000578	time 2.7186 (2.1955)	loss 3.9116 (3.6092)	grad_norm 1.4228 (1.4159)	
[2022-01-21 22:44:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1150/1251]	eta 0:03:41 lr 0.000578	time 2.1510 (2.1954)	loss 4.3847 (3.6103)	grad_norm 1.5325 (1.4156)	
[2022-01-21 22:44:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1160/1251]	eta 0:03:19 lr 0.000578	time 1.9366 (2.1977)	loss 4.0493 (3.6110)	grad_norm 1.1854 (1.4156)	
[2022-01-21 22:45:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1170/1251]	eta 0:02:58 lr 0.000578	time 2.1671 (2.2003)	loss 2.9618 (3.6102)	grad_norm 1.3046 (1.4148)	
[2022-01-21 22:45:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1180/1251]	eta 0:02:36 lr 0.000578	time 3.0737 (2.2024)	loss 3.4432 (3.6096)	grad_norm 1.3291 (1.4150)	
[2022-01-21 22:45:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1190/1251]	eta 0:02:14 lr 0.000578	time 2.4212 (2.2007)	loss 2.8028 (3.6100)	grad_norm 1.3133 (1.4146)	
[2022-01-21 22:46:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1200/1251]	eta 0:01:52 lr 0.000578	time 1.8270 (2.1988)	loss 2.9954 (3.6092)	grad_norm 1.3303 (1.4139)	
[2022-01-21 22:46:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1210/1251]	eta 0:01:30 lr 0.000577	time 1.6575 (2.1969)	loss 3.6517 (3.6066)	grad_norm 1.5811 (1.4137)	
[2022-01-21 22:46:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1220/1251]	eta 0:01:08 lr 0.000577	time 2.5627 (2.1963)	loss 3.8406 (3.6063)	grad_norm 1.4801 (1.4135)	
[2022-01-21 22:47:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1230/1251]	eta 0:00:46 lr 0.000577	time 2.1070 (2.1956)	loss 3.0812 (3.6079)	grad_norm 1.3777 (1.4129)	
[2022-01-21 22:47:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1240/1251]	eta 0:00:24 lr 0.000577	time 1.9725 (2.1963)	loss 3.7124 (3.6079)	grad_norm 1.6221 (1.4137)	
[2022-01-21 22:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [135/300][1250/1251]	eta 0:00:02 lr 0.000577	time 1.1786 (2.1912)	loss 2.8158 (3.6089)	grad_norm 1.4139 (1.4135)	
[2022-01-21 22:47:46 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 135 training takes 0:45:41
[2022-01-21 22:48:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.696 (18.696)	Loss 1.0181 (1.0181)	Acc@1 74.707 (74.707)	Acc@5 93.652 (93.652)	
[2022-01-21 22:48:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.957 (3.477)	Loss 1.0533 (1.0400)	Acc@1 74.609 (75.266)	Acc@5 93.359 (93.235)	
[2022-01-21 22:48:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.619 (2.480)	Loss 1.0675 (1.0461)	Acc@1 75.098 (75.191)	Acc@5 93.457 (93.006)	
[2022-01-21 22:48:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.880 (2.209)	Loss 1.1093 (1.0447)	Acc@1 74.316 (75.359)	Acc@5 92.383 (93.003)	
[2022-01-21 22:49:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.559 (2.144)	Loss 0.9409 (1.0492)	Acc@1 75.586 (75.248)	Acc@5 94.531 (92.926)	
[2022-01-21 22:49:21 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.232 Acc@5 92.938
[2022-01-21 22:49:21 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.2%
[2022-01-21 22:49:21 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.25%
[2022-01-21 22:49:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][0/1251]	eta 7:29:27 lr 0.000577	time 21.5564 (21.5564)	loss 3.3264 (3.3264)	grad_norm 1.3960 (1.3960)	
[2022-01-21 22:50:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][10/1251]	eta 1:23:04 lr 0.000577	time 1.7930 (4.0163)	loss 3.4800 (3.4534)	grad_norm 1.6349 (1.3589)	
[2022-01-21 22:50:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][20/1251]	eta 1:03:04 lr 0.000577	time 1.9164 (3.0744)	loss 2.6960 (3.4498)	grad_norm 1.4113 (1.3761)	
[2022-01-21 22:50:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][30/1251]	eta 0:56:40 lr 0.000577	time 1.8201 (2.7851)	loss 3.4598 (3.5445)	grad_norm 1.7104 (1.4214)	
[2022-01-21 22:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][40/1251]	eta 0:54:05 lr 0.000577	time 4.0461 (2.6800)	loss 3.7970 (3.5945)	grad_norm 1.1099 (1.4345)	
[2022-01-21 22:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][50/1251]	eta 0:53:07 lr 0.000577	time 2.1615 (2.6538)	loss 3.2240 (3.5479)	grad_norm 1.3060 (1.4277)	
[2022-01-21 22:51:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][60/1251]	eta 0:51:09 lr 0.000577	time 1.9539 (2.5776)	loss 3.2626 (3.5402)	grad_norm 1.5106 (1.4183)	
[2022-01-21 22:52:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][70/1251]	eta 0:49:45 lr 0.000577	time 1.8484 (2.5276)	loss 2.9636 (3.5127)	grad_norm 1.5573 (1.4166)	
[2022-01-21 22:52:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][80/1251]	eta 0:48:47 lr 0.000577	time 3.2632 (2.5002)	loss 4.3104 (3.5126)	grad_norm 1.6512 (1.4158)	
[2022-01-21 22:53:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][90/1251]	eta 0:47:27 lr 0.000577	time 2.3280 (2.4523)	loss 3.8358 (3.5145)	grad_norm 1.5023 (1.4236)	
[2022-01-21 22:53:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][100/1251]	eta 0:46:09 lr 0.000577	time 1.6041 (2.4060)	loss 4.0071 (3.5144)	grad_norm 1.4632 (1.4207)	
[2022-01-21 22:53:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][110/1251]	eta 0:45:05 lr 0.000577	time 1.7275 (2.3710)	loss 2.9925 (3.5202)	grad_norm 1.3489 (1.4245)	
[2022-01-21 22:54:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][120/1251]	eta 0:44:20 lr 0.000577	time 2.4782 (2.3523)	loss 3.6668 (3.5571)	grad_norm 1.3924 (1.4232)	
[2022-01-21 22:54:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][130/1251]	eta 0:43:51 lr 0.000577	time 2.3627 (2.3476)	loss 3.8710 (3.5611)	grad_norm 1.4585 (1.4155)	
[2022-01-21 22:54:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][140/1251]	eta 0:43:13 lr 0.000577	time 2.4058 (2.3340)	loss 3.7719 (3.5677)	grad_norm 1.9322 (1.4159)	
[2022-01-21 22:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][150/1251]	eta 0:42:39 lr 0.000577	time 2.0197 (2.3251)	loss 3.9858 (3.5953)	grad_norm 1.4619 (1.4199)	
[2022-01-21 22:55:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][160/1251]	eta 0:42:08 lr 0.000577	time 2.6263 (2.3176)	loss 3.7138 (3.6046)	grad_norm 1.2767 (1.4187)	
[2022-01-21 22:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][170/1251]	eta 0:41:37 lr 0.000577	time 2.5094 (2.3108)	loss 3.8759 (3.6284)	grad_norm 1.2144 (1.4127)	
[2022-01-21 22:56:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][180/1251]	eta 0:41:22 lr 0.000577	time 2.7258 (2.3176)	loss 3.7204 (3.6286)	grad_norm 1.4527 (1.4109)	
[2022-01-21 22:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][190/1251]	eta 0:40:42 lr 0.000577	time 1.5697 (2.3023)	loss 4.4399 (3.6308)	grad_norm 1.7413 (1.4128)	
[2022-01-21 22:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][200/1251]	eta 0:40:06 lr 0.000576	time 2.2334 (2.2897)	loss 4.1602 (3.6326)	grad_norm 1.4596 (1.4167)	
[2022-01-21 22:57:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][210/1251]	eta 0:39:40 lr 0.000576	time 2.3936 (2.2864)	loss 4.0852 (3.6371)	grad_norm 1.3029 (1.4156)	
[2022-01-21 22:57:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][220/1251]	eta 0:39:09 lr 0.000576	time 2.4159 (2.2792)	loss 3.7902 (3.6303)	grad_norm 1.3658 (1.4155)	
[2022-01-21 22:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][230/1251]	eta 0:38:43 lr 0.000576	time 2.4119 (2.2760)	loss 4.2557 (3.6324)	grad_norm 1.3749 (1.4140)	
[2022-01-21 22:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][240/1251]	eta 0:38:18 lr 0.000576	time 2.6801 (2.2738)	loss 2.9652 (3.6255)	grad_norm 1.1822 (1.4151)	
[2022-01-21 22:58:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][250/1251]	eta 0:37:53 lr 0.000576	time 2.1570 (2.2714)	loss 4.1278 (3.6248)	grad_norm 1.6244 (1.4162)	
[2022-01-21 22:59:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][260/1251]	eta 0:37:25 lr 0.000576	time 2.1142 (2.2661)	loss 3.5019 (3.6213)	grad_norm 1.4926 (1.4142)	
[2022-01-21 22:59:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][270/1251]	eta 0:37:04 lr 0.000576	time 2.4675 (2.2672)	loss 2.4910 (3.6259)	grad_norm 1.4118 (1.4118)	
[2022-01-21 22:59:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][280/1251]	eta 0:36:39 lr 0.000576	time 2.2972 (2.2652)	loss 3.2989 (3.6205)	grad_norm 1.1380 (1.4095)	
[2022-01-21 23:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][290/1251]	eta 0:36:17 lr 0.000576	time 2.4810 (2.2656)	loss 3.4413 (3.6249)	grad_norm 1.4690 (1.4089)	
[2022-01-21 23:00:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][300/1251]	eta 0:35:50 lr 0.000576	time 1.7144 (2.2610)	loss 3.7139 (3.6243)	grad_norm 1.3447 (1.4087)	
[2022-01-21 23:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][310/1251]	eta 0:35:21 lr 0.000576	time 2.6273 (2.2547)	loss 4.1630 (3.6297)	grad_norm 1.4551 (1.4121)	
[2022-01-21 23:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][320/1251]	eta 0:34:57 lr 0.000576	time 2.5351 (2.2533)	loss 4.0620 (3.6298)	grad_norm 1.3071 (1.4141)	
[2022-01-21 23:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][330/1251]	eta 0:34:33 lr 0.000576	time 2.1828 (2.2510)	loss 3.5701 (3.6234)	grad_norm 1.5985 (1.4141)	
[2022-01-21 23:02:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][340/1251]	eta 0:34:04 lr 0.000576	time 1.9118 (2.2437)	loss 3.5541 (3.6263)	grad_norm 1.5975 (1.4139)	
[2022-01-21 23:02:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][350/1251]	eta 0:33:38 lr 0.000576	time 2.1885 (2.2401)	loss 3.7993 (3.6242)	grad_norm 1.4040 (1.4147)	
[2022-01-21 23:02:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][360/1251]	eta 0:33:17 lr 0.000576	time 2.5185 (2.2420)	loss 4.1162 (3.6290)	grad_norm 1.3111 (1.4155)	
[2022-01-21 23:03:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][370/1251]	eta 0:32:54 lr 0.000576	time 2.1984 (2.2411)	loss 3.6994 (3.6265)	grad_norm 1.5404 (1.4158)	
[2022-01-21 23:03:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][380/1251]	eta 0:32:31 lr 0.000576	time 1.9109 (2.2400)	loss 3.5661 (3.6249)	grad_norm 1.5810 (1.4192)	
[2022-01-21 23:03:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][390/1251]	eta 0:32:08 lr 0.000576	time 2.2302 (2.2395)	loss 3.6495 (3.6248)	grad_norm 1.5664 (1.4202)	
[2022-01-21 23:04:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][400/1251]	eta 0:31:47 lr 0.000576	time 3.1552 (2.2409)	loss 2.5611 (3.6175)	grad_norm 1.6527 (1.4211)	
[2022-01-21 23:04:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][410/1251]	eta 0:31:22 lr 0.000576	time 1.8922 (2.2389)	loss 3.6366 (3.6134)	grad_norm 1.4978 (1.4208)	
[2022-01-21 23:05:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][420/1251]	eta 0:30:56 lr 0.000576	time 1.9421 (2.2344)	loss 4.2721 (3.6179)	grad_norm 1.3159 (1.4210)	
[2022-01-21 23:05:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][430/1251]	eta 0:30:28 lr 0.000576	time 1.5147 (2.2278)	loss 2.9257 (3.6178)	grad_norm 1.4812 (1.4208)	
[2022-01-21 23:05:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][440/1251]	eta 0:30:02 lr 0.000576	time 1.9061 (2.2222)	loss 4.6539 (3.6151)	grad_norm 1.4101 (1.4199)	
[2022-01-21 23:06:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][450/1251]	eta 0:29:38 lr 0.000575	time 2.1055 (2.2205)	loss 2.5275 (3.6132)	grad_norm 1.4912 (1.4203)	
[2022-01-21 23:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][460/1251]	eta 0:29:16 lr 0.000575	time 1.7908 (2.2201)	loss 4.5446 (3.6145)	grad_norm 1.4085 (1.4199)	
[2022-01-21 23:06:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][470/1251]	eta 0:28:53 lr 0.000575	time 1.4619 (2.2199)	loss 4.0924 (3.6197)	grad_norm 1.3426 (1.4180)	
[2022-01-21 23:07:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][480/1251]	eta 0:28:32 lr 0.000575	time 2.5062 (2.2210)	loss 2.4241 (3.6124)	grad_norm 1.1840 (1.4172)	
[2022-01-21 23:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][490/1251]	eta 0:28:11 lr 0.000575	time 3.0493 (2.2231)	loss 3.5357 (3.6097)	grad_norm 1.4914 (1.4173)	
[2022-01-21 23:07:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][500/1251]	eta 0:27:48 lr 0.000575	time 1.7952 (2.2222)	loss 4.2025 (3.6138)	grad_norm 1.4493 (1.4185)	
[2022-01-21 23:08:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][510/1251]	eta 0:27:28 lr 0.000575	time 1.6543 (2.2243)	loss 3.5884 (3.6130)	grad_norm 1.3527 (1.4195)	
[2022-01-21 23:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][520/1251]	eta 0:27:04 lr 0.000575	time 1.7972 (2.2218)	loss 2.6310 (3.6123)	grad_norm 1.5147 (1.4215)	
[2022-01-21 23:09:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][530/1251]	eta 0:26:41 lr 0.000575	time 2.1199 (2.2210)	loss 4.3247 (3.6140)	grad_norm 1.3413 (1.4215)	
[2022-01-21 23:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][540/1251]	eta 0:26:17 lr 0.000575	time 2.1182 (2.2188)	loss 4.3250 (3.6159)	grad_norm 1.3449 (1.4244)	
[2022-01-21 23:09:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][550/1251]	eta 0:25:53 lr 0.000575	time 1.8055 (2.2165)	loss 2.9990 (3.6204)	grad_norm 1.3255 (1.4239)	
[2022-01-21 23:10:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][560/1251]	eta 0:25:33 lr 0.000575	time 2.8419 (2.2186)	loss 2.7846 (3.6231)	grad_norm 1.4022 (1.4239)	
[2022-01-21 23:10:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][570/1251]	eta 0:25:11 lr 0.000575	time 1.8791 (2.2188)	loss 2.9716 (3.6223)	grad_norm 1.5446 (1.4247)	
[2022-01-21 23:10:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][580/1251]	eta 0:24:48 lr 0.000575	time 2.5763 (2.2188)	loss 3.3459 (3.6223)	grad_norm 1.2719 (1.4231)	
[2022-01-21 23:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][590/1251]	eta 0:24:26 lr 0.000575	time 2.8963 (2.2182)	loss 3.7563 (3.6224)	grad_norm 1.4403 (1.4232)	
[2022-01-21 23:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][600/1251]	eta 0:24:03 lr 0.000575	time 2.7307 (2.2166)	loss 3.8095 (3.6226)	grad_norm 1.3927 (1.4231)	
[2022-01-21 23:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][610/1251]	eta 0:23:39 lr 0.000575	time 1.8905 (2.2151)	loss 3.6178 (3.6208)	grad_norm 1.5614 (1.4231)	
[2022-01-21 23:12:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][620/1251]	eta 0:23:17 lr 0.000575	time 2.2813 (2.2140)	loss 2.3035 (3.6168)	grad_norm 1.5769 (1.4229)	
[2022-01-21 23:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][630/1251]	eta 0:22:53 lr 0.000575	time 2.8337 (2.2121)	loss 2.9951 (3.6204)	grad_norm 1.4471 (1.4220)	
[2022-01-21 23:13:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][640/1251]	eta 0:22:32 lr 0.000575	time 2.1849 (2.2134)	loss 3.9344 (3.6214)	grad_norm 1.5785 (1.4214)	
[2022-01-21 23:13:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][650/1251]	eta 0:22:10 lr 0.000575	time 1.9688 (2.2137)	loss 2.4187 (3.6220)	grad_norm 1.4760 (1.4208)	
[2022-01-21 23:13:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][660/1251]	eta 0:21:47 lr 0.000575	time 2.0018 (2.2119)	loss 4.0918 (3.6212)	grad_norm 1.3044 (1.4227)	
[2022-01-21 23:14:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][670/1251]	eta 0:21:24 lr 0.000575	time 2.5674 (2.2110)	loss 3.5743 (3.6188)	grad_norm 1.2984 (1.4231)	
[2022-01-21 23:14:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][680/1251]	eta 0:21:01 lr 0.000575	time 1.7067 (2.2090)	loss 4.2702 (3.6218)	grad_norm 1.6257 (1.4243)	
[2022-01-21 23:14:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][690/1251]	eta 0:20:39 lr 0.000574	time 2.2288 (2.2087)	loss 4.1522 (3.6226)	grad_norm 1.2279 (1.4230)	
[2022-01-21 23:15:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][700/1251]	eta 0:20:16 lr 0.000574	time 1.8030 (2.2078)	loss 4.3655 (3.6219)	grad_norm 1.4587 (1.4220)	
[2022-01-21 23:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][710/1251]	eta 0:19:55 lr 0.000574	time 3.6984 (2.2097)	loss 3.9765 (3.6204)	grad_norm 1.2157 (1.4226)	
[2022-01-21 23:15:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][720/1251]	eta 0:19:32 lr 0.000574	time 1.5740 (2.2082)	loss 3.8957 (3.6226)	grad_norm 1.5162 (1.4226)	
[2022-01-21 23:16:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][730/1251]	eta 0:19:09 lr 0.000574	time 2.3339 (2.2073)	loss 3.7883 (3.6209)	grad_norm 1.6294 (1.4242)	
[2022-01-21 23:16:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][740/1251]	eta 0:18:47 lr 0.000574	time 1.9234 (2.2057)	loss 3.5289 (3.6221)	grad_norm 1.5047 (1.4251)	
[2022-01-21 23:16:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][750/1251]	eta 0:18:25 lr 0.000574	time 3.3908 (2.2069)	loss 4.0226 (3.6215)	grad_norm 1.4794 (1.4256)	
[2022-01-21 23:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][760/1251]	eta 0:18:02 lr 0.000574	time 2.4615 (2.2049)	loss 3.9202 (3.6236)	grad_norm 1.2836 (1.4258)	
[2022-01-21 23:17:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][770/1251]	eta 0:17:40 lr 0.000574	time 2.4545 (2.2045)	loss 3.7729 (3.6227)	grad_norm 1.5691 (1.4267)	
[2022-01-21 23:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][780/1251]	eta 0:17:18 lr 0.000574	time 2.6551 (2.2054)	loss 3.8014 (3.6233)	grad_norm 1.5809 (1.4265)	
[2022-01-21 23:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][790/1251]	eta 0:16:57 lr 0.000574	time 2.9677 (2.2062)	loss 3.8850 (3.6220)	grad_norm 1.1906 (1.4259)	
[2022-01-21 23:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][800/1251]	eta 0:16:35 lr 0.000574	time 1.8773 (2.2064)	loss 4.0386 (3.6221)	grad_norm 1.5645 (1.4250)	
[2022-01-21 23:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][810/1251]	eta 0:16:13 lr 0.000574	time 2.7730 (2.2068)	loss 3.7537 (3.6186)	grad_norm 1.3219 (1.4250)	
[2022-01-21 23:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][820/1251]	eta 0:15:51 lr 0.000574	time 2.5232 (2.2067)	loss 4.4600 (3.6196)	grad_norm 1.6981 (1.4263)	
[2022-01-21 23:19:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][830/1251]	eta 0:15:28 lr 0.000574	time 2.6378 (2.2060)	loss 4.5379 (3.6227)	grad_norm 1.3767 (1.4266)	
[2022-01-21 23:20:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][840/1251]	eta 0:15:05 lr 0.000574	time 1.5702 (2.2043)	loss 4.3181 (3.6244)	grad_norm 1.3616 (1.4263)	
[2022-01-21 23:20:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][850/1251]	eta 0:14:44 lr 0.000574	time 3.4826 (2.2046)	loss 2.4488 (3.6228)	grad_norm 1.2436 (1.4258)	
[2022-01-21 23:20:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][860/1251]	eta 0:14:21 lr 0.000574	time 1.7357 (2.2032)	loss 4.1008 (3.6220)	grad_norm 1.0906 (1.4254)	
[2022-01-21 23:21:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][870/1251]	eta 0:13:59 lr 0.000574	time 2.0864 (2.2028)	loss 2.9786 (3.6197)	grad_norm 1.2845 (1.4244)	
[2022-01-21 23:21:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][880/1251]	eta 0:13:37 lr 0.000574	time 1.8537 (2.2035)	loss 3.9207 (3.6180)	grad_norm 1.4789 (1.4241)	
[2022-01-21 23:22:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][890/1251]	eta 0:13:15 lr 0.000574	time 3.3703 (2.2046)	loss 4.2312 (3.6196)	grad_norm 1.6052 (1.4245)	
[2022-01-21 23:22:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][900/1251]	eta 0:12:53 lr 0.000574	time 1.8120 (2.2034)	loss 3.8400 (3.6172)	grad_norm 1.3353 (1.4250)	
[2022-01-21 23:22:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][910/1251]	eta 0:12:31 lr 0.000574	time 2.8546 (2.2045)	loss 2.5143 (3.6150)	grad_norm 1.2585 (1.4240)	
[2022-01-21 23:23:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][920/1251]	eta 0:12:09 lr 0.000574	time 2.0087 (2.2025)	loss 3.7395 (3.6138)	grad_norm 1.9194 (1.4242)	
[2022-01-21 23:23:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][930/1251]	eta 0:11:46 lr 0.000573	time 2.8300 (2.2021)	loss 3.6330 (3.6134)	grad_norm 1.5552 (1.4249)	
[2022-01-21 23:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][940/1251]	eta 0:11:24 lr 0.000573	time 2.1524 (2.2001)	loss 3.6512 (3.6113)	grad_norm 1.4787 (1.4267)	
[2022-01-21 23:24:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][950/1251]	eta 0:11:02 lr 0.000573	time 2.4900 (2.2008)	loss 2.4426 (3.6096)	grad_norm 1.2614 (1.4267)	
[2022-01-21 23:24:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][960/1251]	eta 0:10:40 lr 0.000573	time 2.1326 (2.2018)	loss 2.7896 (3.6096)	grad_norm 1.2223 (1.4260)	
[2022-01-21 23:25:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][970/1251]	eta 0:10:19 lr 0.000573	time 2.9469 (2.2033)	loss 4.4469 (3.6117)	grad_norm 1.3349 (1.4252)	
[2022-01-21 23:25:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][980/1251]	eta 0:09:57 lr 0.000573	time 2.1776 (2.2036)	loss 3.4336 (3.6100)	grad_norm 1.2013 (1.4253)	
[2022-01-21 23:25:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][990/1251]	eta 0:09:35 lr 0.000573	time 2.7764 (2.2040)	loss 3.8017 (3.6085)	grad_norm 1.2939 (1.4248)	
[2022-01-21 23:26:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1000/1251]	eta 0:09:12 lr 0.000573	time 1.7782 (2.2026)	loss 3.8199 (3.6083)	grad_norm 1.5433 (1.4244)	
[2022-01-21 23:26:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1010/1251]	eta 0:08:50 lr 0.000573	time 2.5383 (2.2016)	loss 3.8530 (3.6072)	grad_norm 1.3005 (1.4246)	
[2022-01-21 23:26:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1020/1251]	eta 0:08:28 lr 0.000573	time 2.0241 (2.2015)	loss 3.0635 (3.6067)	grad_norm 1.4284 (1.4249)	
[2022-01-21 23:27:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1030/1251]	eta 0:08:06 lr 0.000573	time 2.4720 (2.2023)	loss 4.4522 (3.6080)	grad_norm 1.6484 (1.4242)	
[2022-01-21 23:27:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1040/1251]	eta 0:07:44 lr 0.000573	time 2.8887 (2.2020)	loss 3.3267 (3.6095)	grad_norm 2.0444 (1.4243)	
[2022-01-21 23:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1050/1251]	eta 0:07:22 lr 0.000573	time 2.0241 (2.2009)	loss 2.9246 (3.6069)	grad_norm 1.4637 (1.4244)	
[2022-01-21 23:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1060/1251]	eta 0:07:00 lr 0.000573	time 2.2838 (2.2001)	loss 4.4448 (3.6101)	grad_norm 1.5802 (1.4250)	
[2022-01-21 23:28:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1070/1251]	eta 0:06:38 lr 0.000573	time 1.8860 (2.1993)	loss 3.1760 (3.6066)	grad_norm 1.3618 (1.4245)	
[2022-01-21 23:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1080/1251]	eta 0:06:16 lr 0.000573	time 2.8006 (2.1990)	loss 3.1301 (3.6077)	grad_norm 1.6620 (1.4247)	
[2022-01-21 23:29:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1090/1251]	eta 0:05:54 lr 0.000573	time 2.4110 (2.1992)	loss 2.7284 (3.6069)	grad_norm 1.5627 (1.4246)	
[2022-01-21 23:29:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1100/1251]	eta 0:05:31 lr 0.000573	time 2.1681 (2.1984)	loss 3.6986 (3.6058)	grad_norm 1.3141 (1.4246)	
[2022-01-21 23:30:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1110/1251]	eta 0:05:10 lr 0.000573	time 1.9154 (2.1997)	loss 3.9516 (3.6048)	grad_norm 1.1876 (1.4241)	
[2022-01-21 23:30:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1120/1251]	eta 0:04:48 lr 0.000573	time 3.5739 (2.2018)	loss 3.8034 (3.6061)	grad_norm 1.6827 (1.4238)	
[2022-01-21 23:30:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1130/1251]	eta 0:04:26 lr 0.000573	time 1.6852 (2.2016)	loss 3.6982 (3.6071)	grad_norm 1.1818 (1.4241)	
[2022-01-21 23:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1140/1251]	eta 0:04:04 lr 0.000573	time 1.8755 (2.2010)	loss 3.7773 (3.6070)	grad_norm 1.3432 (1.4237)	
[2022-01-21 23:31:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1150/1251]	eta 0:03:42 lr 0.000573	time 1.7640 (2.1994)	loss 3.5904 (3.6088)	grad_norm 1.3775 (1.4236)	
[2022-01-21 23:31:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1160/1251]	eta 0:03:20 lr 0.000573	time 3.1492 (2.1982)	loss 3.7492 (3.6084)	grad_norm 1.4796 (1.4241)	
[2022-01-21 23:32:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1170/1251]	eta 0:02:58 lr 0.000573	time 1.8840 (2.1981)	loss 3.9354 (3.6094)	grad_norm 1.1552 (1.4236)	
[2022-01-21 23:32:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1180/1251]	eta 0:02:36 lr 0.000572	time 2.2249 (2.1986)	loss 3.8159 (3.6092)	grad_norm 1.2431 (1.4232)	
[2022-01-21 23:32:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1190/1251]	eta 0:02:14 lr 0.000572	time 2.2318 (2.1985)	loss 3.9712 (3.6080)	grad_norm 1.3529 (1.4229)	
[2022-01-21 23:33:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1200/1251]	eta 0:01:52 lr 0.000572	time 2.0444 (2.1970)	loss 3.7732 (3.6072)	grad_norm 1.3975 (1.4224)	
[2022-01-21 23:33:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1210/1251]	eta 0:01:30 lr 0.000572	time 1.9954 (2.1966)	loss 3.1919 (3.6062)	grad_norm 1.4014 (1.4220)	
[2022-01-21 23:34:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1220/1251]	eta 0:01:08 lr 0.000572	time 1.9168 (2.1959)	loss 3.4261 (3.6052)	grad_norm 1.2748 (1.4219)	
[2022-01-21 23:34:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1230/1251]	eta 0:00:46 lr 0.000572	time 2.2762 (2.1964)	loss 4.0619 (3.6074)	grad_norm 1.4103 (1.4217)	
[2022-01-21 23:34:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1240/1251]	eta 0:00:24 lr 0.000572	time 1.7504 (2.1958)	loss 4.0968 (3.6095)	grad_norm 1.7808 (1.4224)	
[2022-01-21 23:35:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [136/300][1250/1251]	eta 0:00:02 lr 0.000572	time 1.1292 (2.1905)	loss 4.1155 (3.6092)	grad_norm 1.6111 (1.4225)	
[2022-01-21 23:35:02 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 136 training takes 0:45:40
[2022-01-21 23:35:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.336 (18.336)	Loss 1.1019 (1.1019)	Acc@1 74.902 (74.902)	Acc@5 92.480 (92.480)	
[2022-01-21 23:35:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.646 (3.193)	Loss 1.1174 (1.0962)	Acc@1 75.391 (74.476)	Acc@5 91.504 (92.702)	
[2022-01-21 23:35:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.256 (2.429)	Loss 1.0695 (1.0820)	Acc@1 74.707 (75.056)	Acc@5 92.969 (92.829)	
[2022-01-21 23:36:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.355 (2.296)	Loss 1.0509 (1.0762)	Acc@1 77.246 (75.406)	Acc@5 93.652 (92.852)	
[2022-01-21 23:36:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.566 (2.168)	Loss 1.0818 (1.0761)	Acc@1 74.805 (75.310)	Acc@5 93.066 (92.878)	
[2022-01-21 23:36:37 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.432 Acc@5 92.958
[2022-01-21 23:36:37 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.4%
[2022-01-21 23:36:37 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.43%
[2022-01-21 23:36:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][0/1251]	eta 7:24:25 lr 0.000572	time 21.3151 (21.3151)	loss 3.3318 (3.3318)	grad_norm 1.4423 (1.4423)	
[2022-01-21 23:37:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][10/1251]	eta 1:24:19 lr 0.000572	time 3.0540 (4.0772)	loss 3.2084 (3.7473)	grad_norm 1.4305 (1.3864)	
[2022-01-21 23:37:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][20/1251]	eta 1:05:41 lr 0.000572	time 1.5437 (3.2019)	loss 4.3546 (3.6094)	grad_norm 1.3212 (1.4192)	
[2022-01-21 23:38:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][30/1251]	eta 0:58:26 lr 0.000572	time 1.5109 (2.8715)	loss 3.4531 (3.5610)	grad_norm 1.5014 (1.4200)	
[2022-01-21 23:38:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][40/1251]	eta 0:55:37 lr 0.000572	time 3.9455 (2.7562)	loss 3.9742 (3.5801)	grad_norm 1.4260 (1.4178)	
[2022-01-21 23:38:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][50/1251]	eta 0:53:30 lr 0.000572	time 2.0066 (2.6731)	loss 3.4929 (3.5766)	grad_norm 1.3190 (1.4121)	
[2022-01-21 23:39:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][60/1251]	eta 0:51:10 lr 0.000572	time 1.4289 (2.5782)	loss 2.6218 (3.5500)	grad_norm 1.3567 (1.4080)	
[2022-01-21 23:39:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][70/1251]	eta 0:49:28 lr 0.000572	time 1.6799 (2.5136)	loss 2.8879 (3.5475)	grad_norm 1.2382 (1.4109)	
[2022-01-21 23:39:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][80/1251]	eta 0:48:25 lr 0.000572	time 3.2553 (2.4814)	loss 3.8909 (3.5586)	grad_norm 1.3685 (1.4051)	
[2022-01-21 23:40:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][90/1251]	eta 0:47:25 lr 0.000572	time 2.2619 (2.4511)	loss 3.9443 (3.5790)	grad_norm 1.4098 (1.4148)	
[2022-01-21 23:40:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][100/1251]	eta 0:46:25 lr 0.000572	time 1.5575 (2.4201)	loss 2.5714 (3.5783)	grad_norm 1.6782 (1.4151)	
[2022-01-21 23:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][110/1251]	eta 0:45:37 lr 0.000572	time 1.9060 (2.3989)	loss 3.7661 (3.5711)	grad_norm 1.3951 (1.4214)	
[2022-01-21 23:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][120/1251]	eta 0:44:47 lr 0.000572	time 2.2767 (2.3760)	loss 3.9650 (3.5858)	grad_norm 1.8629 (1.4244)	
[2022-01-21 23:41:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][130/1251]	eta 0:44:33 lr 0.000572	time 3.5546 (2.3853)	loss 3.8473 (3.5780)	grad_norm 1.5219 (1.4191)	
[2022-01-21 23:42:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][140/1251]	eta 0:43:55 lr 0.000572	time 2.0428 (2.3718)	loss 4.2832 (3.5855)	grad_norm 1.5821 (1.4158)	
[2022-01-21 23:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][150/1251]	eta 0:43:23 lr 0.000572	time 2.3514 (2.3651)	loss 4.1885 (3.5785)	grad_norm 1.4923 (1.4218)	
[2022-01-21 23:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][160/1251]	eta 0:42:50 lr 0.000572	time 2.7310 (2.3563)	loss 3.3852 (3.5717)	grad_norm 1.4074 (1.4201)	
[2022-01-21 23:43:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][170/1251]	eta 0:42:07 lr 0.000571	time 1.8599 (2.3383)	loss 3.7682 (3.5725)	grad_norm 1.4111 (1.4139)	
[2022-01-21 23:43:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][180/1251]	eta 0:41:26 lr 0.000571	time 2.2107 (2.3217)	loss 3.5604 (3.5712)	grad_norm 1.2629 (1.4091)	
[2022-01-21 23:43:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][190/1251]	eta 0:40:51 lr 0.000571	time 1.8606 (2.3105)	loss 3.8294 (3.5843)	grad_norm 1.3192 (1.4130)	
[2022-01-21 23:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][200/1251]	eta 0:40:31 lr 0.000571	time 2.8121 (2.3135)	loss 4.2353 (3.5916)	grad_norm 1.5120 (1.4114)	
[2022-01-21 23:44:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][210/1251]	eta 0:40:00 lr 0.000571	time 1.6409 (2.3061)	loss 4.1250 (3.5926)	grad_norm 1.2476 (1.4080)	
[2022-01-21 23:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][220/1251]	eta 0:39:28 lr 0.000571	time 2.0934 (2.2970)	loss 4.3781 (3.5863)	grad_norm 1.8234 (1.4125)	
[2022-01-21 23:45:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][230/1251]	eta 0:38:58 lr 0.000571	time 1.9209 (2.2906)	loss 3.8952 (3.5815)	grad_norm 1.3492 (1.4127)	
[2022-01-21 23:45:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][240/1251]	eta 0:38:36 lr 0.000571	time 1.9948 (2.2909)	loss 4.0346 (3.5715)	grad_norm 1.3063 (1.4100)	
[2022-01-21 23:46:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][250/1251]	eta 0:38:12 lr 0.000571	time 2.0864 (2.2899)	loss 3.2095 (3.5691)	grad_norm 1.5021 (1.4094)	
[2022-01-21 23:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][260/1251]	eta 0:37:44 lr 0.000571	time 2.5811 (2.2848)	loss 4.3534 (3.5827)	grad_norm 1.3910 (1.4099)	
[2022-01-21 23:46:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][270/1251]	eta 0:37:12 lr 0.000571	time 1.6804 (2.2757)	loss 4.1971 (3.5807)	grad_norm 1.2535 (1.4119)	
[2022-01-21 23:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][280/1251]	eta 0:36:47 lr 0.000571	time 2.1501 (2.2739)	loss 4.1540 (3.5810)	grad_norm 1.3472 (1.4078)	
[2022-01-21 23:47:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][290/1251]	eta 0:36:19 lr 0.000571	time 2.5007 (2.2678)	loss 3.9012 (3.5881)	grad_norm 1.3403 (1.4093)	
[2022-01-21 23:48:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][300/1251]	eta 0:35:56 lr 0.000571	time 3.0289 (2.2672)	loss 3.1449 (3.5783)	grad_norm 1.2442 (1.4097)	
[2022-01-21 23:48:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][310/1251]	eta 0:35:26 lr 0.000571	time 1.9679 (2.2593)	loss 3.2485 (3.5755)	grad_norm 1.3986 (1.4100)	
[2022-01-21 23:48:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][320/1251]	eta 0:35:01 lr 0.000571	time 2.6511 (2.2570)	loss 3.6509 (3.5673)	grad_norm 1.5493 (1.4128)	
[2022-01-21 23:49:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][330/1251]	eta 0:34:39 lr 0.000571	time 2.2186 (2.2578)	loss 2.5675 (3.5646)	grad_norm 1.2817 (1.4139)	
[2022-01-21 23:49:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][340/1251]	eta 0:34:15 lr 0.000571	time 2.4546 (2.2559)	loss 3.5532 (3.5604)	grad_norm 1.3156 (1.4111)	
[2022-01-21 23:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][350/1251]	eta 0:33:50 lr 0.000571	time 1.8812 (2.2539)	loss 2.8443 (3.5644)	grad_norm 1.5768 (1.4102)	
[2022-01-21 23:50:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][360/1251]	eta 0:33:24 lr 0.000571	time 2.1179 (2.2494)	loss 3.3251 (3.5629)	grad_norm 1.3375 (1.4093)	
[2022-01-21 23:50:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][370/1251]	eta 0:32:59 lr 0.000571	time 1.7957 (2.2464)	loss 3.6586 (3.5629)	grad_norm 1.4825 (1.4102)	
[2022-01-21 23:50:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][380/1251]	eta 0:32:46 lr 0.000571	time 5.4474 (2.2580)	loss 4.2468 (3.5634)	grad_norm 1.3910 (1.4112)	
[2022-01-21 23:51:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][390/1251]	eta 0:32:22 lr 0.000571	time 2.1331 (2.2566)	loss 2.7680 (3.5592)	grad_norm 1.6384 (1.4138)	
[2022-01-21 23:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][400/1251]	eta 0:31:57 lr 0.000571	time 1.8536 (2.2529)	loss 4.1219 (3.5696)	grad_norm 1.4430 (1.4141)	
[2022-01-21 23:52:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][410/1251]	eta 0:31:31 lr 0.000570	time 1.7490 (2.2485)	loss 3.7560 (3.5666)	grad_norm 1.5347 (1.4130)	
[2022-01-21 23:52:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][420/1251]	eta 0:31:06 lr 0.000570	time 3.4003 (2.2463)	loss 3.4139 (3.5661)	grad_norm 1.4102 (1.4131)	
[2022-01-21 23:52:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][430/1251]	eta 0:30:41 lr 0.000570	time 2.0198 (2.2431)	loss 2.8834 (3.5642)	grad_norm 1.5005 (1.4132)	
[2022-01-21 23:53:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][440/1251]	eta 0:30:18 lr 0.000570	time 2.2024 (2.2420)	loss 2.7996 (3.5596)	grad_norm 1.3620 (1.4140)	
[2022-01-21 23:53:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][450/1251]	eta 0:29:56 lr 0.000570	time 2.2224 (2.2424)	loss 2.7900 (3.5592)	grad_norm 1.2463 (1.4138)	
[2022-01-21 23:53:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][460/1251]	eta 0:29:34 lr 0.000570	time 2.7571 (2.2429)	loss 3.0731 (3.5568)	grad_norm 1.4447 (1.4145)	
[2022-01-21 23:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][470/1251]	eta 0:29:08 lr 0.000570	time 1.9457 (2.2388)	loss 3.9132 (3.5578)	grad_norm 1.6709 (1.4153)	
[2022-01-21 23:54:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][480/1251]	eta 0:28:43 lr 0.000570	time 1.9175 (2.2358)	loss 3.5860 (3.5546)	grad_norm 1.3919 (1.4151)	
[2022-01-21 23:54:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][490/1251]	eta 0:28:19 lr 0.000570	time 2.0038 (2.2334)	loss 3.9289 (3.5614)	grad_norm 1.7867 (1.4156)	
[2022-01-21 23:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][500/1251]	eta 0:28:00 lr 0.000570	time 3.8144 (2.2378)	loss 2.8718 (3.5630)	grad_norm 1.2250 (1.4159)	
[2022-01-21 23:55:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][510/1251]	eta 0:27:37 lr 0.000570	time 1.8828 (2.2368)	loss 2.4119 (3.5629)	grad_norm 1.3161 (1.4152)	
[2022-01-21 23:56:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][520/1251]	eta 0:27:13 lr 0.000570	time 2.4274 (2.2344)	loss 3.5855 (3.5570)	grad_norm 1.4403 (1.4145)	
[2022-01-21 23:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][530/1251]	eta 0:26:50 lr 0.000570	time 1.5922 (2.2332)	loss 2.9066 (3.5571)	grad_norm 1.3246 (1.4129)	
[2022-01-21 23:56:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][540/1251]	eta 0:26:27 lr 0.000570	time 3.6476 (2.2328)	loss 2.5119 (3.5541)	grad_norm 1.3652 (1.4142)	
[2022-01-21 23:57:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][550/1251]	eta 0:26:03 lr 0.000570	time 2.4929 (2.2303)	loss 4.1026 (3.5527)	grad_norm 1.7730 (1.4183)	
[2022-01-21 23:57:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][560/1251]	eta 0:25:40 lr 0.000570	time 1.8883 (2.2299)	loss 4.1044 (3.5543)	grad_norm 1.6248 (1.4203)	
[2022-01-21 23:57:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][570/1251]	eta 0:25:18 lr 0.000570	time 2.2823 (2.2291)	loss 3.3955 (3.5485)	grad_norm 1.6851 (1.4212)	
[2022-01-21 23:58:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][580/1251]	eta 0:24:56 lr 0.000570	time 2.6096 (2.2302)	loss 3.2386 (3.5505)	grad_norm 1.3234 (1.4215)	
[2022-01-21 23:58:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][590/1251]	eta 0:24:33 lr 0.000570	time 2.4201 (2.2288)	loss 4.1045 (3.5513)	grad_norm 1.3297 (1.4214)	
[2022-01-21 23:58:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][600/1251]	eta 0:24:09 lr 0.000570	time 2.1187 (2.2272)	loss 3.8113 (3.5514)	grad_norm 1.2843 (1.4234)	
[2022-01-21 23:59:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][610/1251]	eta 0:23:46 lr 0.000570	time 2.2904 (2.2259)	loss 4.3350 (3.5580)	grad_norm 1.5147 (1.4240)	
[2022-01-21 23:59:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][620/1251]	eta 0:23:24 lr 0.000570	time 2.5590 (2.2252)	loss 3.9388 (3.5616)	grad_norm 1.4676 (1.4241)	
[2022-01-22 00:00:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][630/1251]	eta 0:23:02 lr 0.000570	time 2.7678 (2.2258)	loss 2.4261 (3.5605)	grad_norm 1.2980 (1.4227)	
[2022-01-22 00:00:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][640/1251]	eta 0:22:38 lr 0.000570	time 2.1628 (2.2236)	loss 3.3156 (3.5589)	grad_norm 1.5539 (1.4226)	
[2022-01-22 00:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][650/1251]	eta 0:22:16 lr 0.000570	time 2.4526 (2.2238)	loss 3.3924 (3.5606)	grad_norm 1.7067 (1.4231)	
[2022-01-22 00:01:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][660/1251]	eta 0:21:54 lr 0.000569	time 2.9362 (2.2247)	loss 3.6013 (3.5608)	grad_norm 1.2844 (1.4223)	
[2022-01-22 00:01:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][670/1251]	eta 0:21:32 lr 0.000569	time 2.7809 (2.2243)	loss 2.8023 (3.5623)	grad_norm 1.1437 (1.4223)	
[2022-01-22 00:01:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][680/1251]	eta 0:21:10 lr 0.000569	time 2.8413 (2.2249)	loss 3.9763 (3.5611)	grad_norm 1.5095 (1.4224)	
[2022-01-22 00:02:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][690/1251]	eta 0:20:47 lr 0.000569	time 1.7728 (2.2243)	loss 2.9482 (3.5605)	grad_norm 1.3257 (1.4220)	
[2022-01-22 00:02:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][700/1251]	eta 0:20:26 lr 0.000569	time 3.5160 (2.2260)	loss 2.8594 (3.5613)	grad_norm 1.4774 (1.4230)	
[2022-01-22 00:02:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][710/1251]	eta 0:20:02 lr 0.000569	time 1.8434 (2.2228)	loss 3.0186 (3.5564)	grad_norm 1.5066 (1.4243)	
[2022-01-22 00:03:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][720/1251]	eta 0:19:38 lr 0.000569	time 1.9347 (2.2186)	loss 3.8473 (3.5560)	grad_norm 1.5913 (1.4235)	
[2022-01-22 00:03:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][730/1251]	eta 0:19:14 lr 0.000569	time 1.8823 (2.2157)	loss 2.6471 (3.5561)	grad_norm 1.3980 (1.4237)	
[2022-01-22 00:03:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][740/1251]	eta 0:18:51 lr 0.000569	time 2.5809 (2.2142)	loss 3.1676 (3.5554)	grad_norm 1.3136 (1.4229)	
[2022-01-22 00:04:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][750/1251]	eta 0:18:28 lr 0.000569	time 1.7801 (2.2120)	loss 2.8513 (3.5545)	grad_norm 1.4564 (1.4250)	
[2022-01-22 00:04:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][760/1251]	eta 0:18:05 lr 0.000569	time 2.6075 (2.2108)	loss 2.8811 (3.5551)	grad_norm 1.3731 (1.4255)	
[2022-01-22 00:05:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][770/1251]	eta 0:17:43 lr 0.000569	time 2.3398 (2.2115)	loss 2.8563 (3.5539)	grad_norm 1.4315 (1.4250)	
[2022-01-22 00:05:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][780/1251]	eta 0:17:21 lr 0.000569	time 2.1606 (2.2115)	loss 3.9364 (3.5528)	grad_norm 1.4161 (1.4249)	
[2022-01-22 00:05:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][790/1251]	eta 0:17:00 lr 0.000569	time 2.5435 (2.2130)	loss 2.3961 (3.5531)	grad_norm 1.5229 (1.4254)	
[2022-01-22 00:06:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][800/1251]	eta 0:16:38 lr 0.000569	time 2.5233 (2.2150)	loss 3.4907 (3.5574)	grad_norm 1.3242 (1.4253)	
[2022-01-22 00:06:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][810/1251]	eta 0:16:17 lr 0.000569	time 2.9128 (2.2172)	loss 2.7046 (3.5576)	grad_norm 1.4462 (1.4261)	
[2022-01-22 00:06:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][820/1251]	eta 0:15:55 lr 0.000569	time 2.0460 (2.2168)	loss 4.0586 (3.5574)	grad_norm 1.3423 (1.4267)	
[2022-01-22 00:07:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][830/1251]	eta 0:15:32 lr 0.000569	time 1.9857 (2.2149)	loss 2.8679 (3.5528)	grad_norm 1.3774 (1.4268)	
[2022-01-22 00:07:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][840/1251]	eta 0:15:09 lr 0.000569	time 1.9272 (2.2120)	loss 4.1579 (3.5543)	grad_norm 1.3418 (1.4277)	
[2022-01-22 00:07:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][850/1251]	eta 0:14:45 lr 0.000569	time 1.8853 (2.2095)	loss 3.8852 (3.5553)	grad_norm 1.3320 (1.4280)	
[2022-01-22 00:08:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][860/1251]	eta 0:14:24 lr 0.000569	time 2.6077 (2.2101)	loss 2.3459 (3.5575)	grad_norm 1.5908 (1.4280)	
[2022-01-22 00:08:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][870/1251]	eta 0:14:02 lr 0.000569	time 1.8642 (2.2115)	loss 3.5899 (3.5569)	grad_norm 1.3809 (1.4265)	
[2022-01-22 00:09:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][880/1251]	eta 0:13:40 lr 0.000569	time 2.2214 (2.2116)	loss 3.9436 (3.5599)	grad_norm 1.3777 (1.4260)	
[2022-01-22 00:09:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][890/1251]	eta 0:13:18 lr 0.000569	time 1.8892 (2.2119)	loss 3.3307 (3.5610)	grad_norm 1.2335 (1.4251)	
[2022-01-22 00:09:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][900/1251]	eta 0:12:56 lr 0.000568	time 2.4654 (2.2124)	loss 3.6788 (3.5596)	grad_norm 1.2209 (1.4245)	
[2022-01-22 00:10:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][910/1251]	eta 0:12:33 lr 0.000568	time 2.2316 (2.2110)	loss 3.7753 (3.5635)	grad_norm 1.3034 (1.4240)	
[2022-01-22 00:10:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][920/1251]	eta 0:12:11 lr 0.000568	time 2.0539 (2.2113)	loss 4.3474 (3.5627)	grad_norm 1.3049 (1.4242)	
[2022-01-22 00:10:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][930/1251]	eta 0:11:49 lr 0.000568	time 1.9747 (2.2102)	loss 4.0812 (3.5636)	grad_norm 1.5464 (1.4235)	
[2022-01-22 00:11:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][940/1251]	eta 0:11:27 lr 0.000568	time 2.5660 (2.2091)	loss 3.6874 (3.5631)	grad_norm 1.4916 (1.4236)	
[2022-01-22 00:11:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][950/1251]	eta 0:11:04 lr 0.000568	time 1.9886 (2.2085)	loss 3.4331 (3.5641)	grad_norm 1.5086 (1.4235)	
[2022-01-22 00:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][960/1251]	eta 0:10:42 lr 0.000568	time 1.5523 (2.2077)	loss 4.0762 (3.5660)	grad_norm 1.2617 (1.4234)	
[2022-01-22 00:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][970/1251]	eta 0:10:20 lr 0.000568	time 2.4531 (2.2075)	loss 2.5985 (3.5648)	grad_norm 1.3838 (1.4231)	
[2022-01-22 00:12:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][980/1251]	eta 0:09:58 lr 0.000568	time 4.0363 (2.2081)	loss 4.0032 (3.5696)	grad_norm 1.2931 (1.4229)	
[2022-01-22 00:13:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][990/1251]	eta 0:09:36 lr 0.000568	time 2.2460 (2.2087)	loss 3.4695 (3.5706)	grad_norm 1.7205 (1.4230)	
[2022-01-22 00:13:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1000/1251]	eta 0:09:14 lr 0.000568	time 1.9469 (2.2085)	loss 3.2785 (3.5696)	grad_norm 1.2041 (1.4223)	
[2022-01-22 00:13:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1010/1251]	eta 0:08:52 lr 0.000568	time 2.3820 (2.2089)	loss 2.9507 (3.5673)	grad_norm 1.5598 (1.4223)	
[2022-01-22 00:14:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1020/1251]	eta 0:08:29 lr 0.000568	time 1.9696 (2.2077)	loss 4.0513 (3.5707)	grad_norm 1.3749 (1.4222)	
[2022-01-22 00:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1030/1251]	eta 0:08:07 lr 0.000568	time 2.2408 (2.2064)	loss 3.6677 (3.5724)	grad_norm 1.5411 (1.4216)	
[2022-01-22 00:14:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1040/1251]	eta 0:07:45 lr 0.000568	time 2.5111 (2.2052)	loss 3.5148 (3.5730)	grad_norm 1.4751 (1.4225)	
[2022-01-22 00:15:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1050/1251]	eta 0:07:23 lr 0.000568	time 2.5294 (2.2042)	loss 3.9673 (3.5733)	grad_norm 1.6518 (1.4239)	
[2022-01-22 00:15:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1060/1251]	eta 0:07:01 lr 0.000568	time 3.0731 (2.2048)	loss 4.1424 (3.5755)	grad_norm 1.4294 (1.4239)	
[2022-01-22 00:15:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1070/1251]	eta 0:06:39 lr 0.000568	time 1.9856 (2.2052)	loss 3.9927 (3.5766)	grad_norm 1.3148 (1.4236)	
[2022-01-22 00:16:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1080/1251]	eta 0:06:17 lr 0.000568	time 2.6762 (2.2061)	loss 2.7459 (3.5748)	grad_norm 1.8365 (1.4241)	
[2022-01-22 00:16:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1090/1251]	eta 0:05:55 lr 0.000568	time 1.7838 (2.2060)	loss 3.7418 (3.5783)	grad_norm 1.3598 (1.4251)	
[2022-01-22 00:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1100/1251]	eta 0:05:33 lr 0.000568	time 2.6639 (2.2074)	loss 3.2069 (3.5789)	grad_norm 1.4681 (1.4248)	
[2022-01-22 00:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1110/1251]	eta 0:05:11 lr 0.000568	time 2.5222 (2.2076)	loss 4.0279 (3.5804)	grad_norm 1.4157 (1.4252)	
[2022-01-22 00:17:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1120/1251]	eta 0:04:49 lr 0.000568	time 2.1016 (2.2077)	loss 4.0436 (3.5822)	grad_norm 1.6968 (1.4261)	
[2022-01-22 00:18:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1130/1251]	eta 0:04:26 lr 0.000568	time 1.9336 (2.2061)	loss 3.8544 (3.5819)	grad_norm 1.6305 (1.4264)	
[2022-01-22 00:18:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1140/1251]	eta 0:04:04 lr 0.000567	time 1.8922 (2.2031)	loss 4.0339 (3.5800)	grad_norm 1.2553 (1.4259)	
[2022-01-22 00:18:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1150/1251]	eta 0:03:42 lr 0.000567	time 1.9525 (2.2018)	loss 4.1395 (3.5797)	grad_norm 1.3463 (1.4261)	
[2022-01-22 00:19:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1160/1251]	eta 0:03:20 lr 0.000567	time 2.5251 (2.2017)	loss 3.9029 (3.5786)	grad_norm 1.3003 (1.4258)	
[2022-01-22 00:19:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1170/1251]	eta 0:02:58 lr 0.000567	time 1.8912 (2.2008)	loss 2.9525 (3.5793)	grad_norm 1.5380 (1.4255)	
[2022-01-22 00:19:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1180/1251]	eta 0:02:36 lr 0.000567	time 2.1750 (2.2007)	loss 2.4511 (3.5778)	grad_norm 1.4943 (1.4262)	
[2022-01-22 00:20:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1190/1251]	eta 0:02:14 lr 0.000567	time 3.1401 (2.2024)	loss 3.5592 (3.5761)	grad_norm 1.3357 (1.4269)	
[2022-01-22 00:20:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1200/1251]	eta 0:01:52 lr 0.000567	time 2.1072 (2.2035)	loss 4.3342 (3.5768)	grad_norm 1.3706 (1.4267)	
[2022-01-22 00:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1210/1251]	eta 0:01:30 lr 0.000567	time 2.1539 (2.2050)	loss 3.6075 (3.5758)	grad_norm 1.3925 (1.4264)	
[2022-01-22 00:21:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1220/1251]	eta 0:01:08 lr 0.000567	time 1.7439 (2.2062)	loss 4.1785 (3.5772)	grad_norm 1.3636 (1.4263)	
[2022-01-22 00:21:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1230/1251]	eta 0:00:46 lr 0.000567	time 2.6076 (2.2059)	loss 4.1064 (3.5787)	grad_norm 1.4925 (1.4268)	
[2022-01-22 00:22:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1240/1251]	eta 0:00:24 lr 0.000567	time 1.5426 (2.2028)	loss 3.8611 (3.5775)	grad_norm 1.5089 (1.4267)	
[2022-01-22 00:22:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [137/300][1250/1251]	eta 0:00:02 lr 0.000567	time 1.1997 (2.1970)	loss 3.1402 (3.5761)	grad_norm 1.8720 (1.4268)	
[2022-01-22 00:22:26 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 137 training takes 0:45:48
[2022-01-22 00:22:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.670 (18.670)	Loss 1.0270 (1.0270)	Acc@1 75.195 (75.195)	Acc@5 93.848 (93.848)	
[2022-01-22 00:23:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.975 (3.359)	Loss 1.0444 (1.0283)	Acc@1 75.879 (75.479)	Acc@5 92.188 (93.164)	
[2022-01-22 00:23:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.601 (2.541)	Loss 1.0604 (1.0282)	Acc@1 74.609 (75.632)	Acc@5 92.969 (93.206)	
[2022-01-22 00:23:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.849 (2.254)	Loss 1.0596 (1.0425)	Acc@1 75.391 (75.337)	Acc@5 91.602 (92.956)	
[2022-01-22 00:23:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.946 (2.184)	Loss 1.0013 (1.0393)	Acc@1 75.488 (75.403)	Acc@5 93.164 (92.993)	
[2022-01-22 00:24:03 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.318 Acc@5 93.048
[2022-01-22 00:24:03 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.3%
[2022-01-22 00:24:03 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.43%
[2022-01-22 00:24:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][0/1251]	eta 7:32:02 lr 0.000567	time 21.6808 (21.6808)	loss 3.8658 (3.8658)	grad_norm 1.5098 (1.5098)	
[2022-01-22 00:24:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][10/1251]	eta 1:29:10 lr 0.000567	time 1.7908 (4.3116)	loss 3.1264 (3.5643)	grad_norm 1.3959 (1.5015)	
[2022-01-22 00:25:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][20/1251]	eta 1:08:27 lr 0.000567	time 2.0767 (3.3370)	loss 4.1305 (3.6212)	grad_norm 1.5362 (1.4739)	
[2022-01-22 00:25:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][30/1251]	eta 0:59:53 lr 0.000567	time 1.6335 (2.9428)	loss 2.7547 (3.5089)	grad_norm 1.2943 (1.4424)	
[2022-01-22 00:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][40/1251]	eta 0:56:29 lr 0.000567	time 3.7836 (2.7988)	loss 4.0358 (3.5215)	grad_norm 1.3335 (1.4458)	
[2022-01-22 00:26:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][50/1251]	eta 0:53:58 lr 0.000567	time 1.8150 (2.6961)	loss 3.3894 (3.5172)	grad_norm 1.2893 (1.4282)	
[2022-01-22 00:26:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][60/1251]	eta 0:51:51 lr 0.000567	time 1.6523 (2.6126)	loss 3.0747 (3.5560)	grad_norm 1.3866 (1.4220)	
[2022-01-22 00:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][70/1251]	eta 0:49:39 lr 0.000567	time 1.5861 (2.5225)	loss 4.2493 (3.5797)	grad_norm 1.6909 (1.4323)	
[2022-01-22 00:27:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][80/1251]	eta 0:48:06 lr 0.000567	time 2.2177 (2.4649)	loss 3.8569 (3.5858)	grad_norm 1.4083 (1.4242)	
[2022-01-22 00:27:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][90/1251]	eta 0:47:11 lr 0.000567	time 2.4518 (2.4390)	loss 3.8352 (3.5740)	grad_norm 1.5840 (1.4375)	
[2022-01-22 00:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][100/1251]	eta 0:46:00 lr 0.000567	time 1.8574 (2.3981)	loss 2.4825 (3.5917)	grad_norm 1.3286 (1.4375)	
[2022-01-22 00:28:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][110/1251]	eta 0:45:22 lr 0.000567	time 1.8250 (2.3860)	loss 4.0619 (3.6153)	grad_norm 1.4395 (1.4340)	
[2022-01-22 00:28:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][120/1251]	eta 0:44:33 lr 0.000567	time 2.0049 (2.3635)	loss 2.8013 (3.6007)	grad_norm 1.4978 (1.4403)	
[2022-01-22 00:29:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][130/1251]	eta 0:43:59 lr 0.000567	time 2.4928 (2.3543)	loss 3.4396 (3.6105)	grad_norm 1.5415 (1.4387)	
[2022-01-22 00:29:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][140/1251]	eta 0:43:13 lr 0.000566	time 1.8715 (2.3340)	loss 4.1166 (3.6144)	grad_norm 1.8152 (1.4426)	
[2022-01-22 00:29:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][150/1251]	eta 0:42:42 lr 0.000566	time 1.8834 (2.3274)	loss 3.9046 (3.6197)	grad_norm 1.3827 (1.4479)	
[2022-01-22 00:30:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][160/1251]	eta 0:42:17 lr 0.000566	time 2.3132 (2.3256)	loss 3.8693 (3.6337)	grad_norm 1.4014 (1.4471)	
[2022-01-22 00:30:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][170/1251]	eta 0:41:49 lr 0.000566	time 2.2627 (2.3218)	loss 2.9953 (3.6279)	grad_norm 1.5766 (1.4455)	
[2022-01-22 00:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][180/1251]	eta 0:41:02 lr 0.000566	time 1.8815 (2.2996)	loss 4.4972 (3.6276)	grad_norm 1.7330 (1.4424)	
[2022-01-22 00:31:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][190/1251]	eta 0:40:17 lr 0.000566	time 1.9414 (2.2785)	loss 3.9048 (3.6261)	grad_norm 1.3872 (1.4424)	
[2022-01-22 00:31:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][200/1251]	eta 0:39:39 lr 0.000566	time 1.9034 (2.2644)	loss 3.7627 (3.6272)	grad_norm 1.3937 (1.4431)	
[2022-01-22 00:31:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][210/1251]	eta 0:39:11 lr 0.000566	time 2.0821 (2.2584)	loss 3.9103 (3.6337)	grad_norm 1.6221 (1.4404)	
[2022-01-22 00:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][220/1251]	eta 0:38:38 lr 0.000566	time 2.2449 (2.2491)	loss 2.3922 (3.6365)	grad_norm 1.5504 (1.4414)	
[2022-01-22 00:32:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][230/1251]	eta 0:38:15 lr 0.000566	time 1.9511 (2.2481)	loss 3.5565 (3.6279)	grad_norm 1.3662 (1.4451)	
[2022-01-22 00:33:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][240/1251]	eta 0:38:07 lr 0.000566	time 2.2178 (2.2628)	loss 3.3682 (3.6278)	grad_norm 1.3168 (1.4446)	
[2022-01-22 00:33:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][250/1251]	eta 0:37:48 lr 0.000566	time 1.8070 (2.2659)	loss 3.0596 (3.6139)	grad_norm 1.3755 (1.4428)	
[2022-01-22 00:33:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][260/1251]	eta 0:37:28 lr 0.000566	time 2.1583 (2.2687)	loss 3.9027 (3.6221)	grad_norm 1.2268 (1.4393)	
[2022-01-22 00:34:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][270/1251]	eta 0:37:04 lr 0.000566	time 2.1565 (2.2676)	loss 3.6935 (3.6291)	grad_norm 1.2283 (1.4348)	
[2022-01-22 00:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][280/1251]	eta 0:36:36 lr 0.000566	time 2.6743 (2.2626)	loss 4.1790 (3.6270)	grad_norm 1.3614 (1.4330)	
[2022-01-22 00:35:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][290/1251]	eta 0:36:10 lr 0.000566	time 1.6668 (2.2581)	loss 2.8679 (3.6277)	grad_norm 1.5282 (1.4374)	
[2022-01-22 00:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][300/1251]	eta 0:35:39 lr 0.000566	time 2.6168 (2.2496)	loss 2.8622 (3.6185)	grad_norm 1.3326 (1.4364)	
[2022-01-22 00:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][310/1251]	eta 0:35:15 lr 0.000566	time 2.5529 (2.2482)	loss 3.0003 (3.6153)	grad_norm 1.2995 (1.4385)	
[2022-01-22 00:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][320/1251]	eta 0:34:50 lr 0.000566	time 2.2168 (2.2457)	loss 3.1321 (3.6131)	grad_norm 1.6077 (1.4367)	
[2022-01-22 00:36:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][330/1251]	eta 0:34:29 lr 0.000566	time 2.1156 (2.2465)	loss 3.5613 (3.6012)	grad_norm 1.5770 (1.4394)	
[2022-01-22 00:36:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][340/1251]	eta 0:34:04 lr 0.000566	time 2.1998 (2.2447)	loss 2.5412 (3.5990)	grad_norm 1.3217 (1.4382)	
[2022-01-22 00:37:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][350/1251]	eta 0:33:39 lr 0.000566	time 1.9164 (2.2414)	loss 3.7388 (3.6009)	grad_norm 1.4357 (1.4371)	
[2022-01-22 00:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][360/1251]	eta 0:33:15 lr 0.000566	time 2.6879 (2.2391)	loss 2.7456 (3.6005)	grad_norm 1.3117 (1.4371)	
[2022-01-22 00:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][370/1251]	eta 0:32:53 lr 0.000566	time 1.9605 (2.2397)	loss 3.8940 (3.5989)	grad_norm 1.5170 (1.4360)	
[2022-01-22 00:38:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][380/1251]	eta 0:32:26 lr 0.000565	time 2.1619 (2.2353)	loss 2.8043 (3.5962)	grad_norm 1.2811 (1.4361)	
[2022-01-22 00:38:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][390/1251]	eta 0:32:02 lr 0.000565	time 2.6654 (2.2332)	loss 3.0456 (3.5906)	grad_norm 1.5006 (1.4398)	
[2022-01-22 00:38:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][400/1251]	eta 0:31:39 lr 0.000565	time 3.0591 (2.2324)	loss 2.6934 (3.5904)	grad_norm 1.4238 (1.4404)	
[2022-01-22 00:39:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][410/1251]	eta 0:31:15 lr 0.000565	time 2.1766 (2.2297)	loss 2.5929 (3.5841)	grad_norm 1.4662 (1.4420)	
[2022-01-22 00:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][420/1251]	eta 0:30:51 lr 0.000565	time 1.4833 (2.2276)	loss 3.4785 (3.5844)	grad_norm 1.2940 (1.4399)	
[2022-01-22 00:40:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][430/1251]	eta 0:30:28 lr 0.000565	time 2.2208 (2.2268)	loss 3.5749 (3.5865)	grad_norm 1.4722 (1.4386)	
[2022-01-22 00:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][440/1251]	eta 0:30:06 lr 0.000565	time 2.6474 (2.2278)	loss 4.0772 (3.5857)	grad_norm 1.4538 (1.4377)	
[2022-01-22 00:40:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][450/1251]	eta 0:29:44 lr 0.000565	time 1.9577 (2.2275)	loss 3.8850 (3.5814)	grad_norm 1.3269 (1.4366)	
[2022-01-22 00:41:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][460/1251]	eta 0:29:21 lr 0.000565	time 2.2060 (2.2269)	loss 3.1403 (3.5784)	grad_norm 1.3441 (1.4357)	
[2022-01-22 00:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][470/1251]	eta 0:28:56 lr 0.000565	time 2.1815 (2.2232)	loss 3.6210 (3.5770)	grad_norm 1.4415 (1.4341)	
[2022-01-22 00:41:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][480/1251]	eta 0:28:31 lr 0.000565	time 2.4467 (2.2204)	loss 3.7213 (3.5787)	grad_norm 1.4174 (1.4338)	
[2022-01-22 00:42:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][490/1251]	eta 0:28:10 lr 0.000565	time 2.1402 (2.2213)	loss 3.5764 (3.5783)	grad_norm 1.6997 (1.4335)	
[2022-01-22 00:42:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][500/1251]	eta 0:27:48 lr 0.000565	time 2.6081 (2.2215)	loss 3.9946 (3.5782)	grad_norm 1.4083 (1.4359)	
[2022-01-22 00:42:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][510/1251]	eta 0:27:27 lr 0.000565	time 2.2304 (2.2234)	loss 3.2463 (3.5821)	grad_norm 1.8698 (1.4368)	
[2022-01-22 00:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][520/1251]	eta 0:27:04 lr 0.000565	time 2.2033 (2.2221)	loss 3.2501 (3.5837)	grad_norm 1.5465 (1.4362)	
[2022-01-22 00:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][530/1251]	eta 0:26:41 lr 0.000565	time 1.9125 (2.2213)	loss 3.6132 (3.5854)	grad_norm 1.2206 (1.4355)	
[2022-01-22 00:44:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][540/1251]	eta 0:26:17 lr 0.000565	time 1.8834 (2.2181)	loss 3.4530 (3.5907)	grad_norm 1.4177 (1.4362)	
[2022-01-22 00:44:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][550/1251]	eta 0:25:52 lr 0.000565	time 2.2872 (2.2153)	loss 2.3370 (3.5832)	grad_norm 1.3800 (1.4364)	
[2022-01-22 00:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][560/1251]	eta 0:25:27 lr 0.000565	time 1.9223 (2.2110)	loss 2.9440 (3.5754)	grad_norm 1.3590 (1.4366)	
[2022-01-22 00:45:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][570/1251]	eta 0:25:04 lr 0.000565	time 1.9131 (2.2088)	loss 2.3042 (3.5743)	grad_norm 1.5618 (1.4374)	
[2022-01-22 00:45:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][580/1251]	eta 0:24:42 lr 0.000565	time 2.3008 (2.2087)	loss 2.4654 (3.5681)	grad_norm 1.4613 (1.4376)	
[2022-01-22 00:45:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][590/1251]	eta 0:24:20 lr 0.000565	time 2.6581 (2.2099)	loss 4.0466 (3.5603)	grad_norm 1.2944 (1.4361)	
[2022-01-22 00:46:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][600/1251]	eta 0:23:58 lr 0.000565	time 2.1188 (2.2092)	loss 4.0785 (3.5626)	grad_norm 1.4106 (1.4361)	
[2022-01-22 00:46:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][610/1251]	eta 0:23:35 lr 0.000565	time 2.0762 (2.2076)	loss 3.9857 (3.5637)	grad_norm 1.3847 (1.4375)	
[2022-01-22 00:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][620/1251]	eta 0:23:13 lr 0.000564	time 2.4118 (2.2089)	loss 4.2234 (3.5658)	grad_norm 1.4360 (1.4379)	
[2022-01-22 00:47:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][630/1251]	eta 0:22:53 lr 0.000564	time 2.9594 (2.2110)	loss 2.5639 (3.5609)	grad_norm 1.4248 (1.4373)	
[2022-01-22 00:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][640/1251]	eta 0:22:31 lr 0.000564	time 2.2390 (2.2119)	loss 3.8170 (3.5646)	grad_norm 1.4529 (1.4367)	
[2022-01-22 00:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][650/1251]	eta 0:22:09 lr 0.000564	time 1.8939 (2.2128)	loss 4.1411 (3.5605)	grad_norm 1.2993 (1.4378)	
[2022-01-22 00:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][660/1251]	eta 0:21:47 lr 0.000564	time 1.7594 (2.2119)	loss 3.8540 (3.5620)	grad_norm 1.4030 (1.4378)	
[2022-01-22 00:48:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][670/1251]	eta 0:21:25 lr 0.000564	time 2.6887 (2.2133)	loss 3.9032 (3.5625)	grad_norm 1.4432 (1.4373)	
[2022-01-22 00:49:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][680/1251]	eta 0:21:01 lr 0.000564	time 1.5297 (2.2086)	loss 3.1682 (3.5630)	grad_norm 1.3530 (1.4367)	
[2022-01-22 00:49:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][690/1251]	eta 0:20:36 lr 0.000564	time 1.8986 (2.2050)	loss 2.8060 (3.5656)	grad_norm 1.3011 (1.4358)	
[2022-01-22 00:49:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][700/1251]	eta 0:20:13 lr 0.000564	time 1.8768 (2.2029)	loss 3.3029 (3.5671)	grad_norm 1.4030 (1.4344)	
[2022-01-22 00:50:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][710/1251]	eta 0:19:52 lr 0.000564	time 2.5392 (2.2036)	loss 2.9451 (3.5668)	grad_norm 1.2181 (1.4331)	
[2022-01-22 00:50:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][720/1251]	eta 0:19:30 lr 0.000564	time 2.1304 (2.2044)	loss 3.8056 (3.5640)	grad_norm 1.5965 (1.4323)	
[2022-01-22 00:50:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][730/1251]	eta 0:19:09 lr 0.000564	time 2.2354 (2.2064)	loss 3.4793 (3.5649)	grad_norm 1.2974 (1.4335)	
[2022-01-22 00:51:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][740/1251]	eta 0:18:47 lr 0.000564	time 1.8465 (2.2073)	loss 3.7611 (3.5657)	grad_norm 1.4069 (1.4340)	
[2022-01-22 00:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][750/1251]	eta 0:18:26 lr 0.000564	time 1.8815 (2.2084)	loss 2.5801 (3.5659)	grad_norm 1.4912 (1.4342)	
[2022-01-22 00:52:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][760/1251]	eta 0:18:05 lr 0.000564	time 3.0479 (2.2101)	loss 3.2543 (3.5659)	grad_norm 1.2892 (1.4331)	
[2022-01-22 00:52:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][770/1251]	eta 0:17:42 lr 0.000564	time 2.0580 (2.2089)	loss 4.1208 (3.5650)	grad_norm 1.2685 (1.4320)	
[2022-01-22 00:52:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][780/1251]	eta 0:17:19 lr 0.000564	time 1.9038 (2.2066)	loss 3.5716 (3.5679)	grad_norm 1.4305 (1.4325)	
[2022-01-22 00:53:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][790/1251]	eta 0:16:56 lr 0.000564	time 1.9246 (2.2049)	loss 4.2823 (3.5683)	grad_norm 1.3192 (1.4332)	
[2022-01-22 00:53:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][800/1251]	eta 0:16:33 lr 0.000564	time 3.1744 (2.2038)	loss 2.8828 (3.5671)	grad_norm 1.3082 (1.4333)	
[2022-01-22 00:53:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][810/1251]	eta 0:16:11 lr 0.000564	time 2.2558 (2.2033)	loss 3.4586 (3.5697)	grad_norm 1.3766 (1.4339)	
[2022-01-22 00:54:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][820/1251]	eta 0:15:50 lr 0.000564	time 2.3279 (2.2043)	loss 3.1803 (3.5704)	grad_norm 1.5421 (1.4353)	
[2022-01-22 00:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][830/1251]	eta 0:15:28 lr 0.000564	time 2.4675 (2.2053)	loss 3.8374 (3.5704)	grad_norm 1.3263 (1.4356)	
[2022-01-22 00:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][840/1251]	eta 0:15:07 lr 0.000564	time 3.6788 (2.2078)	loss 3.6209 (3.5710)	grad_norm 1.4336 (1.4361)	
[2022-01-22 00:55:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][850/1251]	eta 0:14:45 lr 0.000564	time 1.9110 (2.2081)	loss 4.0924 (3.5733)	grad_norm 1.6266 (1.4383)	
[2022-01-22 00:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][860/1251]	eta 0:14:22 lr 0.000564	time 1.8448 (2.2063)	loss 4.1146 (3.5733)	grad_norm 1.4019 (1.4391)	
[2022-01-22 00:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][870/1251]	eta 0:13:59 lr 0.000563	time 2.1565 (2.2043)	loss 4.6094 (3.5735)	grad_norm 1.4269 (1.4387)	
[2022-01-22 00:56:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][880/1251]	eta 0:13:37 lr 0.000563	time 3.2152 (2.2046)	loss 4.0713 (3.5771)	grad_norm 1.7241 (1.4392)	
[2022-01-22 00:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][890/1251]	eta 0:13:15 lr 0.000563	time 2.2293 (2.2040)	loss 4.3038 (3.5810)	grad_norm 1.5899 (1.4402)	
[2022-01-22 00:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][900/1251]	eta 0:12:53 lr 0.000563	time 2.5130 (2.2045)	loss 2.7127 (3.5785)	grad_norm 1.3794 (1.4409)	
[2022-01-22 00:57:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][910/1251]	eta 0:12:31 lr 0.000563	time 2.1586 (2.2051)	loss 3.8553 (3.5781)	grad_norm 1.2335 (1.4404)	
[2022-01-22 00:57:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][920/1251]	eta 0:12:09 lr 0.000563	time 1.8634 (2.2043)	loss 4.1804 (3.5810)	grad_norm 1.3492 (1.4395)	
[2022-01-22 00:58:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][930/1251]	eta 0:11:46 lr 0.000563	time 1.6469 (2.2020)	loss 3.9228 (3.5789)	grad_norm 1.7920 (1.4395)	
[2022-01-22 00:58:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][940/1251]	eta 0:11:24 lr 0.000563	time 2.1646 (2.2006)	loss 3.8337 (3.5794)	grad_norm 1.3365 (1.4385)	
[2022-01-22 00:58:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][950/1251]	eta 0:11:01 lr 0.000563	time 1.9138 (2.1992)	loss 3.7396 (3.5814)	grad_norm 1.3343 (1.4376)	
[2022-01-22 00:59:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][960/1251]	eta 0:10:40 lr 0.000563	time 2.9078 (2.2011)	loss 3.5913 (3.5804)	grad_norm 1.2845 (1.4372)	
[2022-01-22 00:59:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][970/1251]	eta 0:10:18 lr 0.000563	time 1.9730 (2.2008)	loss 3.3002 (3.5813)	grad_norm 1.4176 (1.4376)	
[2022-01-22 01:00:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][980/1251]	eta 0:09:56 lr 0.000563	time 1.6406 (2.2005)	loss 4.1692 (3.5815)	grad_norm 1.2170 (1.4369)	
[2022-01-22 01:00:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][990/1251]	eta 0:09:34 lr 0.000563	time 2.2616 (2.2001)	loss 3.5101 (3.5809)	grad_norm 1.5428 (1.4370)	
[2022-01-22 01:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1000/1251]	eta 0:09:12 lr 0.000563	time 2.5862 (2.2001)	loss 4.0193 (3.5839)	grad_norm 1.5614 (1.4365)	
[2022-01-22 01:01:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1010/1251]	eta 0:08:49 lr 0.000563	time 1.8143 (2.1984)	loss 3.6295 (3.5857)	grad_norm 1.2186 (1.4361)	
[2022-01-22 01:01:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1020/1251]	eta 0:08:27 lr 0.000563	time 1.9321 (2.1982)	loss 3.2002 (3.5876)	grad_norm 1.3285 (1.4357)	
[2022-01-22 01:01:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1030/1251]	eta 0:08:06 lr 0.000563	time 2.1557 (2.1997)	loss 3.8962 (3.5869)	grad_norm 1.5824 (1.4356)	
[2022-01-22 01:02:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1040/1251]	eta 0:07:44 lr 0.000563	time 2.5469 (2.1993)	loss 3.9622 (3.5870)	grad_norm 1.6254 (1.4360)	
[2022-01-22 01:02:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1050/1251]	eta 0:07:21 lr 0.000563	time 2.2507 (2.1987)	loss 2.8412 (3.5853)	grad_norm 1.7712 (1.4366)	
[2022-01-22 01:02:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1060/1251]	eta 0:06:59 lr 0.000563	time 1.6336 (2.1974)	loss 2.9473 (3.5840)	grad_norm 1.3607 (1.4363)	
[2022-01-22 01:03:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1070/1251]	eta 0:06:37 lr 0.000563	time 1.9263 (2.1967)	loss 4.5736 (3.5845)	grad_norm 1.2715 (1.4355)	
[2022-01-22 01:03:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1080/1251]	eta 0:06:15 lr 0.000563	time 2.5284 (2.1967)	loss 3.5898 (3.5867)	grad_norm 1.5251 (1.4358)	
[2022-01-22 01:04:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1090/1251]	eta 0:05:53 lr 0.000563	time 2.8135 (2.1968)	loss 3.3218 (3.5872)	grad_norm 1.3326 (1.4348)	
[2022-01-22 01:04:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1100/1251]	eta 0:05:31 lr 0.000563	time 2.6205 (2.1968)	loss 3.8084 (3.5883)	grad_norm 1.3602 (1.4345)	
[2022-01-22 01:04:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1110/1251]	eta 0:05:09 lr 0.000562	time 2.0017 (2.1969)	loss 4.3763 (3.5896)	grad_norm 1.4504 (1.4340)	
[2022-01-22 01:05:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1120/1251]	eta 0:04:47 lr 0.000562	time 2.1747 (2.1975)	loss 3.4708 (3.5905)	grad_norm 1.5020 (1.4346)	
[2022-01-22 01:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1130/1251]	eta 0:04:26 lr 0.000562	time 2.6053 (2.1985)	loss 3.6131 (3.5900)	grad_norm 1.5072 (1.4342)	
[2022-01-22 01:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1140/1251]	eta 0:04:03 lr 0.000562	time 2.3288 (2.1978)	loss 3.7764 (3.5882)	grad_norm 1.3007 (1.4341)	
[2022-01-22 01:06:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1150/1251]	eta 0:03:41 lr 0.000562	time 1.8515 (2.1960)	loss 4.0651 (3.5896)	grad_norm 1.3839 (1.4349)	
[2022-01-22 01:06:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1160/1251]	eta 0:03:19 lr 0.000562	time 2.5780 (2.1948)	loss 3.4838 (3.5873)	grad_norm 1.4731 (1.4349)	
[2022-01-22 01:06:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1170/1251]	eta 0:02:57 lr 0.000562	time 2.1125 (2.1942)	loss 2.8768 (3.5878)	grad_norm 1.2962 (1.4349)	
[2022-01-22 01:07:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1180/1251]	eta 0:02:35 lr 0.000562	time 1.8535 (2.1935)	loss 3.4726 (3.5880)	grad_norm 1.3491 (1.4356)	
[2022-01-22 01:07:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1190/1251]	eta 0:02:13 lr 0.000562	time 2.2303 (2.1936)	loss 2.7796 (3.5875)	grad_norm 1.4197 (1.4357)	
[2022-01-22 01:08:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1200/1251]	eta 0:01:51 lr 0.000562	time 2.9048 (2.1955)	loss 3.8756 (3.5861)	grad_norm 1.4872 (1.4356)	
[2022-01-22 01:08:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1210/1251]	eta 0:01:30 lr 0.000562	time 1.5565 (2.1957)	loss 3.7369 (3.5871)	grad_norm 1.4376 (1.4353)	
[2022-01-22 01:08:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1220/1251]	eta 0:01:08 lr 0.000562	time 2.5373 (2.1969)	loss 3.9324 (3.5881)	grad_norm 1.3041 (1.4349)	
[2022-01-22 01:09:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1230/1251]	eta 0:00:46 lr 0.000562	time 2.1889 (2.1972)	loss 4.0534 (3.5887)	grad_norm 1.6780 (1.4350)	
[2022-01-22 01:09:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1240/1251]	eta 0:00:24 lr 0.000562	time 2.2809 (2.1954)	loss 2.8229 (3.5887)	grad_norm 1.6629 (1.4349)	
[2022-01-22 01:09:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [138/300][1250/1251]	eta 0:00:02 lr 0.000562	time 1.2330 (2.1886)	loss 3.5512 (3.5900)	grad_norm 1.4038 (1.4349)	
[2022-01-22 01:09:41 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 138 training takes 0:45:38
[2022-01-22 01:10:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.413 (19.413)	Loss 1.1198 (1.1198)	Acc@1 74.316 (74.316)	Acc@5 91.699 (91.699)	
[2022-01-22 01:10:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.879 (3.305)	Loss 1.0301 (1.0275)	Acc@1 76.855 (75.533)	Acc@5 92.871 (92.880)	
[2022-01-22 01:10:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.882 (2.671)	Loss 1.0679 (1.0136)	Acc@1 76.367 (76.046)	Acc@5 92.480 (93.048)	
[2022-01-22 01:10:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.298 (2.343)	Loss 1.0548 (1.0204)	Acc@1 74.121 (75.904)	Acc@5 92.871 (92.997)	
[2022-01-22 01:11:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.852 (2.168)	Loss 0.9623 (1.0244)	Acc@1 78.320 (75.715)	Acc@5 94.336 (92.983)	
[2022-01-22 01:11:17 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.630 Acc@5 92.980
[2022-01-22 01:11:17 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.6%
[2022-01-22 01:11:17 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.63%
[2022-01-22 01:11:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][0/1251]	eta 6:43:54 lr 0.000562	time 19.3723 (19.3723)	loss 2.8769 (2.8769)	grad_norm 1.5099 (1.5099)	
[2022-01-22 01:12:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][10/1251]	eta 1:21:20 lr 0.000562	time 2.5494 (3.9328)	loss 3.4981 (3.2680)	grad_norm 1.3137 (1.4792)	
[2022-01-22 01:12:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][20/1251]	eta 1:03:44 lr 0.000562	time 2.5766 (3.1066)	loss 4.0458 (3.4869)	grad_norm 1.4770 (1.4411)	
[2022-01-22 01:12:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][30/1251]	eta 0:57:09 lr 0.000562	time 1.8634 (2.8089)	loss 2.9395 (3.5280)	grad_norm 1.5296 (1.4531)	
[2022-01-22 01:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][40/1251]	eta 0:55:10 lr 0.000562	time 7.1322 (2.7334)	loss 3.9345 (3.5473)	grad_norm 1.5443 (1.4419)	
[2022-01-22 01:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][50/1251]	eta 0:52:59 lr 0.000562	time 2.3264 (2.6473)	loss 3.9714 (3.5221)	grad_norm 1.3595 (1.4291)	
[2022-01-22 01:13:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][60/1251]	eta 0:50:48 lr 0.000562	time 1.5612 (2.5598)	loss 4.0547 (3.5597)	grad_norm 1.3749 (1.4257)	
[2022-01-22 01:14:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][70/1251]	eta 0:49:27 lr 0.000562	time 1.9143 (2.5126)	loss 2.5628 (3.5115)	grad_norm 1.5526 (1.4300)	
[2022-01-22 01:14:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][80/1251]	eta 0:48:28 lr 0.000562	time 3.7143 (2.4836)	loss 2.4957 (3.5149)	grad_norm 1.5163 (1.4374)	
[2022-01-22 01:15:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][90/1251]	eta 0:47:30 lr 0.000562	time 1.8310 (2.4549)	loss 3.5955 (3.5169)	grad_norm 1.5853 (1.4337)	
[2022-01-22 01:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][100/1251]	eta 0:46:36 lr 0.000561	time 2.2108 (2.4295)	loss 3.6094 (3.5139)	grad_norm 1.4984 (1.4422)	
[2022-01-22 01:15:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][110/1251]	eta 0:45:52 lr 0.000561	time 1.8225 (2.4127)	loss 2.7883 (3.5210)	grad_norm 1.4105 (1.4441)	
[2022-01-22 01:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][120/1251]	eta 0:45:17 lr 0.000561	time 3.0321 (2.4023)	loss 4.2749 (3.5533)	grad_norm 2.0691 (1.4522)	
[2022-01-22 01:16:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][130/1251]	eta 0:44:41 lr 0.000561	time 1.8871 (2.3917)	loss 4.1598 (3.5623)	grad_norm 1.4148 (1.4476)	
[2022-01-22 01:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][140/1251]	eta 0:43:49 lr 0.000561	time 2.0456 (2.3670)	loss 3.4352 (3.5637)	grad_norm 1.7565 (1.4475)	
[2022-01-22 01:17:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][150/1251]	eta 0:42:59 lr 0.000561	time 1.7722 (2.3427)	loss 3.9945 (3.5817)	grad_norm 1.2568 (1.4442)	
[2022-01-22 01:17:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][160/1251]	eta 0:42:27 lr 0.000561	time 3.0364 (2.3348)	loss 4.3186 (3.5872)	grad_norm 1.3500 (1.4451)	
[2022-01-22 01:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][170/1251]	eta 0:41:47 lr 0.000561	time 1.9375 (2.3195)	loss 4.1541 (3.5920)	grad_norm 1.5955 (1.4442)	
[2022-01-22 01:18:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][180/1251]	eta 0:41:07 lr 0.000561	time 1.6087 (2.3035)	loss 4.0782 (3.5786)	grad_norm 1.6330 (1.4443)	
[2022-01-22 01:18:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][190/1251]	eta 0:40:35 lr 0.000561	time 2.5522 (2.2959)	loss 3.9876 (3.5818)	grad_norm 1.1940 (1.4393)	
[2022-01-22 01:18:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][200/1251]	eta 0:40:11 lr 0.000561	time 2.2738 (2.2944)	loss 2.8955 (3.5826)	grad_norm 1.3437 (1.4349)	
[2022-01-22 01:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][210/1251]	eta 0:39:52 lr 0.000561	time 2.2316 (2.2979)	loss 3.2953 (3.5920)	grad_norm 1.4792 (1.4339)	
[2022-01-22 01:19:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][220/1251]	eta 0:39:23 lr 0.000561	time 1.5225 (2.2924)	loss 3.6723 (3.5824)	grad_norm 1.7328 (1.4350)	
[2022-01-22 01:20:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][230/1251]	eta 0:38:56 lr 0.000561	time 2.6900 (2.2886)	loss 3.8203 (3.5845)	grad_norm 1.7418 (1.4358)	
[2022-01-22 01:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][240/1251]	eta 0:38:26 lr 0.000561	time 2.3051 (2.2813)	loss 3.6432 (3.5855)	grad_norm 1.2465 (1.4385)	
[2022-01-22 01:20:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][250/1251]	eta 0:37:57 lr 0.000561	time 2.1186 (2.2755)	loss 3.6925 (3.5893)	grad_norm 1.3836 (1.4367)	
[2022-01-22 01:21:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][260/1251]	eta 0:37:30 lr 0.000561	time 1.8461 (2.2710)	loss 3.0406 (3.5870)	grad_norm 1.3631 (1.4411)	
[2022-01-22 01:21:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][270/1251]	eta 0:37:05 lr 0.000561	time 2.5605 (2.2685)	loss 2.9944 (3.5867)	grad_norm 1.2980 (1.4415)	
[2022-01-22 01:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][280/1251]	eta 0:36:39 lr 0.000561	time 1.9087 (2.2648)	loss 4.0911 (3.5814)	grad_norm 1.4625 (1.4439)	
[2022-01-22 01:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][290/1251]	eta 0:36:22 lr 0.000561	time 2.9987 (2.2714)	loss 3.5834 (3.5778)	grad_norm 1.5270 (1.4465)	
[2022-01-22 01:22:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][300/1251]	eta 0:36:01 lr 0.000561	time 1.6698 (2.2734)	loss 4.3792 (3.5790)	grad_norm 1.5417 (1.4452)	
[2022-01-22 01:23:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][310/1251]	eta 0:35:32 lr 0.000561	time 2.2460 (2.2661)	loss 4.0582 (3.5803)	grad_norm 1.3904 (1.4430)	
[2022-01-22 01:23:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][320/1251]	eta 0:34:59 lr 0.000561	time 1.8560 (2.2553)	loss 3.9657 (3.5846)	grad_norm 1.3442 (1.4416)	
[2022-01-22 01:23:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][330/1251]	eta 0:34:36 lr 0.000561	time 2.4280 (2.2542)	loss 2.8663 (3.5791)	grad_norm 1.3025 (1.4426)	
[2022-01-22 01:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][340/1251]	eta 0:34:13 lr 0.000560	time 2.5366 (2.2541)	loss 2.8823 (3.5731)	grad_norm 1.5693 (1.4415)	
[2022-01-22 01:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][350/1251]	eta 0:33:51 lr 0.000560	time 2.1298 (2.2550)	loss 3.9949 (3.5641)	grad_norm 1.6141 (1.4408)	
[2022-01-22 01:24:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][360/1251]	eta 0:33:23 lr 0.000560	time 1.9321 (2.2491)	loss 4.1167 (3.5660)	grad_norm 1.3482 (1.4403)	
[2022-01-22 01:25:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][370/1251]	eta 0:33:00 lr 0.000560	time 2.5818 (2.2479)	loss 4.1323 (3.5727)	grad_norm 1.4284 (1.4406)	
[2022-01-22 01:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][380/1251]	eta 0:32:32 lr 0.000560	time 1.8746 (2.2415)	loss 3.8779 (3.5802)	grad_norm 1.4493 (1.4422)	
[2022-01-22 01:25:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][390/1251]	eta 0:32:10 lr 0.000560	time 2.3931 (2.2418)	loss 3.3905 (3.5776)	grad_norm 1.5364 (1.4432)	
[2022-01-22 01:26:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][400/1251]	eta 0:31:45 lr 0.000560	time 1.8887 (2.2395)	loss 3.4012 (3.5830)	grad_norm 1.5888 (1.4447)	
[2022-01-22 01:26:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][410/1251]	eta 0:31:24 lr 0.000560	time 3.5087 (2.2405)	loss 3.0068 (3.5852)	grad_norm 1.4490 (1.4459)	
[2022-01-22 01:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][420/1251]	eta 0:31:00 lr 0.000560	time 2.0222 (2.2389)	loss 3.5225 (3.5818)	grad_norm 1.4896 (1.4454)	
[2022-01-22 01:27:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][430/1251]	eta 0:30:36 lr 0.000560	time 2.2290 (2.2374)	loss 3.8394 (3.5870)	grad_norm 1.4798 (1.4455)	
[2022-01-22 01:27:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][440/1251]	eta 0:30:12 lr 0.000560	time 1.7090 (2.2353)	loss 2.9301 (3.5871)	grad_norm 1.3929 (1.4440)	
[2022-01-22 01:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][450/1251]	eta 0:29:48 lr 0.000560	time 2.7678 (2.2334)	loss 2.8097 (3.5838)	grad_norm 1.2495 (1.4453)	
[2022-01-22 01:28:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][460/1251]	eta 0:29:24 lr 0.000560	time 1.8627 (2.2307)	loss 3.5054 (3.5865)	grad_norm 1.6035 (1.4449)	
[2022-01-22 01:28:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][470/1251]	eta 0:29:01 lr 0.000560	time 2.2234 (2.2298)	loss 2.7297 (3.5855)	grad_norm 1.3863 (1.4438)	
[2022-01-22 01:29:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][480/1251]	eta 0:28:40 lr 0.000560	time 1.6409 (2.2315)	loss 4.1250 (3.5869)	grad_norm 1.6007 (1.4437)	
[2022-01-22 01:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][490/1251]	eta 0:28:20 lr 0.000560	time 3.4626 (2.2351)	loss 3.2856 (3.5852)	grad_norm 1.2828 (1.4427)	
[2022-01-22 01:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][500/1251]	eta 0:27:58 lr 0.000560	time 1.8035 (2.2347)	loss 3.3287 (3.5860)	grad_norm 1.5025 (1.4432)	
[2022-01-22 01:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][510/1251]	eta 0:27:33 lr 0.000560	time 1.9947 (2.2313)	loss 3.1337 (3.5773)	grad_norm 1.7083 (1.4431)	
[2022-01-22 01:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][520/1251]	eta 0:27:08 lr 0.000560	time 1.7626 (2.2274)	loss 4.1867 (3.5799)	grad_norm 1.3834 (1.4448)	
[2022-01-22 01:30:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][530/1251]	eta 0:26:42 lr 0.000560	time 1.9334 (2.2222)	loss 3.7985 (3.5809)	grad_norm 1.2659 (1.4432)	
[2022-01-22 01:31:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][540/1251]	eta 0:26:19 lr 0.000560	time 2.4302 (2.2222)	loss 3.2380 (3.5849)	grad_norm 1.3152 (1.4426)	
[2022-01-22 01:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][550/1251]	eta 0:25:56 lr 0.000560	time 2.5842 (2.2211)	loss 3.5477 (3.5837)	grad_norm 1.3581 (1.4410)	
[2022-01-22 01:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][560/1251]	eta 0:25:34 lr 0.000560	time 2.0539 (2.2210)	loss 3.6184 (3.5835)	grad_norm 1.4997 (1.4423)	
[2022-01-22 01:32:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][570/1251]	eta 0:25:11 lr 0.000560	time 2.0386 (2.2189)	loss 3.7474 (3.5824)	grad_norm 1.3235 (1.4428)	
[2022-01-22 01:32:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][580/1251]	eta 0:24:48 lr 0.000560	time 2.4635 (2.2179)	loss 3.8280 (3.5829)	grad_norm 1.4026 (1.4417)	
[2022-01-22 01:33:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][590/1251]	eta 0:24:25 lr 0.000559	time 2.2435 (2.2165)	loss 3.7115 (3.5813)	grad_norm 1.5239 (1.4408)	
[2022-01-22 01:33:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][600/1251]	eta 0:24:02 lr 0.000559	time 1.8293 (2.2158)	loss 4.0057 (3.5851)	grad_norm 1.2882 (1.4410)	
[2022-01-22 01:33:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][610/1251]	eta 0:23:40 lr 0.000559	time 2.4586 (2.2167)	loss 4.0800 (3.5865)	grad_norm 1.4098 (1.4430)	
[2022-01-22 01:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][620/1251]	eta 0:23:18 lr 0.000559	time 2.4548 (2.2170)	loss 3.6756 (3.5860)	grad_norm 2.0402 (1.4437)	
[2022-01-22 01:34:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][630/1251]	eta 0:22:57 lr 0.000559	time 2.6697 (2.2184)	loss 3.9700 (3.5810)	grad_norm 1.5545 (1.4458)	
[2022-01-22 01:34:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][640/1251]	eta 0:22:33 lr 0.000559	time 2.1771 (2.2160)	loss 4.0074 (3.5838)	grad_norm 1.3808 (1.4457)	
[2022-01-22 01:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][650/1251]	eta 0:22:11 lr 0.000559	time 2.4176 (2.2157)	loss 2.5985 (3.5852)	grad_norm 1.2810 (1.4454)	
[2022-01-22 01:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][660/1251]	eta 0:21:49 lr 0.000559	time 2.2060 (2.2150)	loss 2.3101 (3.5852)	grad_norm 1.3450 (1.4445)	
[2022-01-22 01:36:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][670/1251]	eta 0:21:27 lr 0.000559	time 2.9549 (2.2167)	loss 3.8339 (3.5844)	grad_norm 1.4979 (1.4440)	
[2022-01-22 01:36:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][680/1251]	eta 0:21:05 lr 0.000559	time 1.7972 (2.2170)	loss 2.8889 (3.5854)	grad_norm 1.4782 (1.4445)	
[2022-01-22 01:36:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][690/1251]	eta 0:20:43 lr 0.000559	time 1.5969 (2.2158)	loss 2.6406 (3.5838)	grad_norm 1.3542 (1.4440)	
[2022-01-22 01:37:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][700/1251]	eta 0:20:20 lr 0.000559	time 1.8968 (2.2143)	loss 4.1629 (3.5860)	grad_norm 1.3082 (1.4427)	
[2022-01-22 01:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][710/1251]	eta 0:19:57 lr 0.000559	time 2.8747 (2.2144)	loss 3.1988 (3.5842)	grad_norm 1.4599 (1.4420)	
[2022-01-22 01:37:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][720/1251]	eta 0:19:34 lr 0.000559	time 1.8647 (2.2122)	loss 3.3380 (3.5795)	grad_norm 1.3246 (1.4423)	
[2022-01-22 01:38:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][730/1251]	eta 0:19:11 lr 0.000559	time 2.0454 (2.2106)	loss 3.6358 (3.5809)	grad_norm 1.5186 (1.4436)	
[2022-01-22 01:38:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][740/1251]	eta 0:18:49 lr 0.000559	time 1.9186 (2.2104)	loss 2.3864 (3.5771)	grad_norm 1.3605 (1.4449)	
[2022-01-22 01:38:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][750/1251]	eta 0:18:27 lr 0.000559	time 2.1726 (2.2102)	loss 4.2874 (3.5795)	grad_norm 1.3272 (1.4457)	
[2022-01-22 01:39:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][760/1251]	eta 0:18:05 lr 0.000559	time 2.4034 (2.2116)	loss 4.0667 (3.5766)	grad_norm 1.3055 (1.4459)	
[2022-01-22 01:39:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][770/1251]	eta 0:17:43 lr 0.000559	time 1.9269 (2.2116)	loss 3.8878 (3.5774)	grad_norm 1.3781 (1.4456)	
[2022-01-22 01:40:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][780/1251]	eta 0:17:21 lr 0.000559	time 1.9702 (2.2105)	loss 4.0107 (3.5786)	grad_norm 1.4304 (1.4451)	
[2022-01-22 01:40:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][790/1251]	eta 0:16:59 lr 0.000559	time 2.1250 (2.2106)	loss 2.8326 (3.5737)	grad_norm 1.6024 (1.4449)	
[2022-01-22 01:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][800/1251]	eta 0:16:35 lr 0.000559	time 1.8225 (2.2083)	loss 3.3825 (3.5751)	grad_norm 1.2545 (1.4439)	
[2022-01-22 01:41:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][810/1251]	eta 0:16:13 lr 0.000559	time 1.4891 (2.2071)	loss 4.0085 (3.5773)	grad_norm 1.3756 (1.4448)	
[2022-01-22 01:41:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][820/1251]	eta 0:15:52 lr 0.000559	time 2.3425 (2.2109)	loss 2.3538 (3.5751)	grad_norm 1.2582 (1.4448)	
[2022-01-22 01:41:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][830/1251]	eta 0:15:31 lr 0.000558	time 2.2828 (2.2121)	loss 3.9430 (3.5730)	grad_norm 1.5657 (1.4451)	
[2022-01-22 01:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][840/1251]	eta 0:15:08 lr 0.000558	time 1.8629 (2.2110)	loss 3.3879 (3.5703)	grad_norm 1.2391 (1.4447)	
[2022-01-22 01:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][850/1251]	eta 0:14:45 lr 0.000558	time 2.2471 (2.2095)	loss 3.7826 (3.5687)	grad_norm 1.5400 (1.4448)	
[2022-01-22 01:42:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][860/1251]	eta 0:14:23 lr 0.000558	time 1.8492 (2.2077)	loss 3.3255 (3.5658)	grad_norm 1.5119 (1.4453)	
[2022-01-22 01:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][870/1251]	eta 0:14:00 lr 0.000558	time 2.3980 (2.2073)	loss 2.4895 (3.5681)	grad_norm 1.3997 (1.4448)	
[2022-01-22 01:43:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][880/1251]	eta 0:13:38 lr 0.000558	time 2.0902 (2.2062)	loss 3.9356 (3.5673)	grad_norm 1.5667 (1.4460)	
[2022-01-22 01:44:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][890/1251]	eta 0:13:16 lr 0.000558	time 1.9240 (2.2068)	loss 4.0349 (3.5684)	grad_norm 1.2855 (1.4453)	
[2022-01-22 01:44:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][900/1251]	eta 0:12:55 lr 0.000558	time 1.8471 (2.2084)	loss 4.3342 (3.5697)	grad_norm 1.5068 (1.4451)	
[2022-01-22 01:44:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][910/1251]	eta 0:12:33 lr 0.000558	time 3.1762 (2.2096)	loss 3.4979 (3.5711)	grad_norm 1.3751 (1.4450)	
[2022-01-22 01:45:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][920/1251]	eta 0:12:10 lr 0.000558	time 1.5695 (2.2084)	loss 2.6457 (3.5693)	grad_norm 1.2589 (1.4461)	
[2022-01-22 01:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][930/1251]	eta 0:11:47 lr 0.000558	time 2.0775 (2.2052)	loss 3.6912 (3.5685)	grad_norm 1.3480 (1.4464)	
[2022-01-22 01:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][940/1251]	eta 0:11:25 lr 0.000558	time 2.2349 (2.2034)	loss 3.6301 (3.5674)	grad_norm 1.5274 (1.4480)	
[2022-01-22 01:46:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][950/1251]	eta 0:11:03 lr 0.000558	time 1.8748 (2.2029)	loss 4.0192 (3.5703)	grad_norm 1.5380 (1.4483)	
[2022-01-22 01:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][960/1251]	eta 0:10:40 lr 0.000558	time 1.9959 (2.2023)	loss 2.8275 (3.5711)	grad_norm 1.3215 (1.4483)	
[2022-01-22 01:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][970/1251]	eta 0:10:18 lr 0.000558	time 1.6308 (2.2016)	loss 3.9889 (3.5677)	grad_norm 1.6591 (1.4479)	
[2022-01-22 01:47:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][980/1251]	eta 0:09:56 lr 0.000558	time 2.1934 (2.2011)	loss 4.1499 (3.5687)	grad_norm 1.4454 (1.4476)	
[2022-01-22 01:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][990/1251]	eta 0:09:34 lr 0.000558	time 2.0383 (2.2011)	loss 2.8077 (3.5656)	grad_norm 1.3408 (1.4469)	
[2022-01-22 01:48:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1000/1251]	eta 0:09:12 lr 0.000558	time 2.1266 (2.2009)	loss 3.6977 (3.5666)	grad_norm 1.6044 (1.4470)	
[2022-01-22 01:48:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1010/1251]	eta 0:08:50 lr 0.000558	time 1.9258 (2.2014)	loss 2.7601 (3.5650)	grad_norm 1.4362 (1.4460)	
[2022-01-22 01:48:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1020/1251]	eta 0:08:29 lr 0.000558	time 2.3085 (2.2040)	loss 3.0631 (3.5649)	grad_norm 1.5019 (1.4455)	
[2022-01-22 01:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1030/1251]	eta 0:08:07 lr 0.000558	time 2.0589 (2.2058)	loss 3.6054 (3.5666)	grad_norm 1.2434 (1.4442)	
[2022-01-22 01:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1040/1251]	eta 0:07:45 lr 0.000558	time 1.5429 (2.2059)	loss 3.8955 (3.5683)	grad_norm 1.7055 (1.4440)	
[2022-01-22 01:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1050/1251]	eta 0:07:23 lr 0.000558	time 2.3187 (2.2050)	loss 3.1050 (3.5649)	grad_norm 1.3477 (1.4455)	
[2022-01-22 01:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1060/1251]	eta 0:07:00 lr 0.000558	time 2.0670 (2.2027)	loss 3.1429 (3.5650)	grad_norm 1.3785 (1.4453)	
[2022-01-22 01:50:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1070/1251]	eta 0:06:38 lr 0.000557	time 1.9401 (2.2026)	loss 3.6674 (3.5641)	grad_norm 1.4257 (1.4449)	
[2022-01-22 01:50:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1080/1251]	eta 0:06:16 lr 0.000557	time 1.8899 (2.2033)	loss 4.0149 (3.5665)	grad_norm 1.2623 (1.4446)	
[2022-01-22 01:51:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1090/1251]	eta 0:05:54 lr 0.000557	time 1.5109 (2.2027)	loss 2.4239 (3.5652)	grad_norm 1.4551 (1.4436)	
[2022-01-22 01:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1100/1251]	eta 0:05:32 lr 0.000557	time 2.5985 (2.2030)	loss 3.6648 (3.5662)	grad_norm 1.3445 (1.4432)	
[2022-01-22 01:52:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1110/1251]	eta 0:05:11 lr 0.000557	time 2.7329 (2.2059)	loss 3.6003 (3.5665)	grad_norm 1.4351 (1.4442)	
[2022-01-22 01:52:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1120/1251]	eta 0:04:48 lr 0.000557	time 1.8728 (2.2059)	loss 2.4510 (3.5670)	grad_norm 1.4812 (1.4452)	
[2022-01-22 01:52:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1130/1251]	eta 0:04:26 lr 0.000557	time 1.7612 (2.2048)	loss 3.7308 (3.5667)	grad_norm 1.6024 (1.4464)	
[2022-01-22 01:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1140/1251]	eta 0:04:04 lr 0.000557	time 1.9651 (2.2026)	loss 4.1417 (3.5649)	grad_norm 1.4390 (1.4471)	
[2022-01-22 01:53:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1150/1251]	eta 0:03:42 lr 0.000557	time 1.9674 (2.2029)	loss 3.4871 (3.5679)	grad_norm 1.5392 (1.4469)	
[2022-01-22 01:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1160/1251]	eta 0:03:20 lr 0.000557	time 1.9875 (2.2027)	loss 3.7256 (3.5691)	grad_norm 1.4861 (1.4470)	
[2022-01-22 01:54:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1170/1251]	eta 0:02:58 lr 0.000557	time 1.9816 (2.2028)	loss 3.4500 (3.5684)	grad_norm 1.2619 (1.4465)	
[2022-01-22 01:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1180/1251]	eta 0:02:36 lr 0.000557	time 1.8291 (2.2032)	loss 3.6747 (3.5700)	grad_norm 1.2641 (1.4464)	
[2022-01-22 01:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1190/1251]	eta 0:02:14 lr 0.000557	time 1.6233 (2.2028)	loss 2.8882 (3.5680)	grad_norm 1.2310 (1.4466)	
[2022-01-22 01:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1200/1251]	eta 0:01:52 lr 0.000557	time 1.9450 (2.2026)	loss 4.1640 (3.5699)	grad_norm 1.2043 (1.4461)	
[2022-01-22 01:55:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1210/1251]	eta 0:01:30 lr 0.000557	time 4.1944 (2.2034)	loss 3.6819 (3.5713)	grad_norm 1.3216 (1.4449)	
[2022-01-22 01:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1220/1251]	eta 0:01:08 lr 0.000557	time 1.9350 (2.2026)	loss 4.0528 (3.5719)	grad_norm 1.4335 (1.4447)	
[2022-01-22 01:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1230/1251]	eta 0:00:46 lr 0.000557	time 1.9263 (2.2019)	loss 3.2502 (3.5731)	grad_norm 1.3548 (1.4447)	
[2022-01-22 01:56:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1240/1251]	eta 0:00:24 lr 0.000557	time 1.4960 (2.2007)	loss 3.0818 (3.5744)	grad_norm 1.4935 (1.4450)	
[2022-01-22 01:57:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [139/300][1250/1251]	eta 0:00:02 lr 0.000557	time 1.1728 (2.1957)	loss 4.4121 (3.5751)	grad_norm 1.4989 (1.4451)	
[2022-01-22 01:57:05 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 139 training takes 0:45:47
[2022-01-22 01:57:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.236 (18.236)	Loss 1.0305 (1.0305)	Acc@1 77.051 (77.051)	Acc@5 94.043 (94.043)	
[2022-01-22 01:57:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.188 (3.262)	Loss 1.0475 (1.0491)	Acc@1 75.000 (75.932)	Acc@5 92.188 (92.978)	
[2022-01-22 01:57:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.332 (2.577)	Loss 0.9347 (1.0423)	Acc@1 78.613 (76.014)	Acc@5 93.750 (92.950)	
[2022-01-22 01:58:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.307 (2.319)	Loss 0.9846 (1.0467)	Acc@1 78.809 (75.810)	Acc@5 93.750 (93.007)	
[2022-01-22 01:58:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.746 (2.183)	Loss 0.9965 (1.0517)	Acc@1 75.977 (75.631)	Acc@5 94.238 (92.943)	
[2022-01-22 01:58:41 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.616 Acc@5 92.942
[2022-01-22 01:58:41 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.6%
[2022-01-22 01:58:41 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.63%
[2022-01-22 01:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][0/1251]	eta 7:44:32 lr 0.000557	time 22.2803 (22.2803)	loss 4.1124 (4.1124)	grad_norm 1.3530 (1.3530)	
[2022-01-22 01:59:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][10/1251]	eta 1:24:14 lr 0.000557	time 2.7060 (4.0727)	loss 3.6442 (3.7141)	grad_norm 1.2962 (1.3475)	
[2022-01-22 01:59:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][20/1251]	eta 1:05:11 lr 0.000557	time 1.8180 (3.1773)	loss 3.3789 (3.5343)	grad_norm 1.3714 (1.3558)	
[2022-01-22 02:00:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][30/1251]	eta 0:58:49 lr 0.000557	time 1.5547 (2.8906)	loss 3.9685 (3.5877)	grad_norm 1.4003 (1.3677)	
[2022-01-22 02:00:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][40/1251]	eta 0:56:07 lr 0.000557	time 3.9999 (2.7806)	loss 4.0092 (3.5550)	grad_norm 1.3960 (1.4015)	
[2022-01-22 02:00:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][50/1251]	eta 0:53:09 lr 0.000557	time 1.9202 (2.6559)	loss 4.1712 (3.5529)	grad_norm 1.4172 (1.4121)	
[2022-01-22 02:01:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][60/1251]	eta 0:50:36 lr 0.000556	time 1.6740 (2.5499)	loss 3.8268 (3.5797)	grad_norm 1.4119 (1.4175)	
[2022-01-22 02:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][70/1251]	eta 0:49:03 lr 0.000556	time 2.0509 (2.4924)	loss 4.1448 (3.5577)	grad_norm 1.7372 (1.4217)	
[2022-01-22 02:02:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][80/1251]	eta 0:47:59 lr 0.000556	time 3.1891 (2.4586)	loss 4.3423 (3.5321)	grad_norm 1.3565 (1.4184)	
[2022-01-22 02:02:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][90/1251]	eta 0:47:07 lr 0.000556	time 2.8247 (2.4351)	loss 4.1650 (3.5440)	grad_norm 1.4039 (1.4277)	
[2022-01-22 02:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][100/1251]	eta 0:46:33 lr 0.000556	time 1.7432 (2.4274)	loss 2.7932 (3.5666)	grad_norm 1.4645 (1.4226)	
[2022-01-22 02:03:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][110/1251]	eta 0:45:35 lr 0.000556	time 2.2376 (2.3975)	loss 3.2967 (3.5823)	grad_norm 1.6132 (1.4280)	
[2022-01-22 02:03:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][120/1251]	eta 0:44:49 lr 0.000556	time 2.9755 (2.3778)	loss 2.4740 (3.5740)	grad_norm 1.5090 (1.4293)	
[2022-01-22 02:03:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][130/1251]	eta 0:44:03 lr 0.000556	time 2.6209 (2.3584)	loss 3.8666 (3.5521)	grad_norm 1.3863 (1.4360)	
[2022-01-22 02:04:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][140/1251]	eta 0:43:10 lr 0.000556	time 1.7973 (2.3320)	loss 3.1573 (3.5499)	grad_norm 1.6033 (1.4399)	
[2022-01-22 02:04:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][150/1251]	eta 0:42:30 lr 0.000556	time 1.9106 (2.3164)	loss 3.8319 (3.5409)	grad_norm 1.4830 (1.4394)	
[2022-01-22 02:04:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][160/1251]	eta 0:42:09 lr 0.000556	time 2.5470 (2.3184)	loss 4.0484 (3.5532)	grad_norm 1.4648 (1.4394)	
[2022-01-22 02:05:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][170/1251]	eta 0:41:50 lr 0.000556	time 2.0862 (2.3221)	loss 3.2555 (3.5598)	grad_norm 1.5273 (1.4379)	
[2022-01-22 02:05:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][180/1251]	eta 0:41:26 lr 0.000556	time 2.9031 (2.3216)	loss 3.5100 (3.5707)	grad_norm 1.6145 (1.4385)	
[2022-01-22 02:06:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][190/1251]	eta 0:41:01 lr 0.000556	time 1.8085 (2.3197)	loss 3.5674 (3.5619)	grad_norm 1.5944 (1.4414)	
[2022-01-22 02:06:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][200/1251]	eta 0:40:26 lr 0.000556	time 1.9701 (2.3092)	loss 3.8450 (3.5728)	grad_norm 1.5724 (1.4445)	
[2022-01-22 02:06:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][210/1251]	eta 0:39:45 lr 0.000556	time 1.8572 (2.2914)	loss 3.1265 (3.5713)	grad_norm 1.2790 (1.4431)	
[2022-01-22 02:07:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][220/1251]	eta 0:39:08 lr 0.000556	time 2.0182 (2.2778)	loss 3.7356 (3.5838)	grad_norm 1.3756 (1.4406)	
[2022-01-22 02:07:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][230/1251]	eta 0:38:36 lr 0.000556	time 2.4323 (2.2691)	loss 3.1508 (3.5789)	grad_norm 1.5857 (1.4433)	
[2022-01-22 02:07:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][240/1251]	eta 0:38:09 lr 0.000556	time 2.2122 (2.2650)	loss 2.3222 (3.5655)	grad_norm 1.4958 (1.4433)	
[2022-01-22 02:08:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][250/1251]	eta 0:37:46 lr 0.000556	time 2.4446 (2.2643)	loss 3.4750 (3.5642)	grad_norm 1.4187 (1.4428)	
[2022-01-22 02:08:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][260/1251]	eta 0:37:18 lr 0.000556	time 1.9548 (2.2585)	loss 3.8770 (3.5632)	grad_norm 1.3785 (1.4429)	
[2022-01-22 02:08:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][270/1251]	eta 0:36:54 lr 0.000556	time 2.7261 (2.2578)	loss 2.8664 (3.5662)	grad_norm 1.4374 (1.4445)	
[2022-01-22 02:09:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][280/1251]	eta 0:36:28 lr 0.000556	time 1.8892 (2.2542)	loss 4.1437 (3.5699)	grad_norm 1.8044 (1.4477)	
[2022-01-22 02:09:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][290/1251]	eta 0:36:09 lr 0.000556	time 2.3816 (2.2578)	loss 3.4907 (3.5645)	grad_norm 1.3602 (1.4489)	
[2022-01-22 02:10:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][300/1251]	eta 0:35:47 lr 0.000556	time 1.8088 (2.2578)	loss 3.8121 (3.5662)	grad_norm 1.3976 (1.4499)	
[2022-01-22 02:10:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][310/1251]	eta 0:35:30 lr 0.000555	time 2.7610 (2.2638)	loss 2.9727 (3.5620)	grad_norm 1.6350 (1.4481)	
[2022-01-22 02:10:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][320/1251]	eta 0:35:04 lr 0.000555	time 1.5643 (2.2602)	loss 4.2334 (3.5703)	grad_norm 1.2854 (1.4467)	
[2022-01-22 02:11:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][330/1251]	eta 0:34:38 lr 0.000555	time 1.5850 (2.2568)	loss 2.4115 (3.5670)	grad_norm 1.2410 (1.4425)	
[2022-01-22 02:11:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][340/1251]	eta 0:34:08 lr 0.000555	time 1.9980 (2.2482)	loss 3.8004 (3.5570)	grad_norm 1.4917 (1.4419)	
[2022-01-22 02:11:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][350/1251]	eta 0:33:40 lr 0.000555	time 2.1610 (2.2420)	loss 3.6291 (3.5626)	grad_norm 1.5755 (1.4423)	
[2022-01-22 02:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][360/1251]	eta 0:33:13 lr 0.000555	time 1.7177 (2.2374)	loss 3.4500 (3.5663)	grad_norm 1.6908 (1.4449)	
[2022-01-22 02:12:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][370/1251]	eta 0:32:45 lr 0.000555	time 1.8847 (2.2315)	loss 3.9082 (3.5693)	grad_norm 1.3016 (1.4494)	
[2022-01-22 02:12:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][380/1251]	eta 0:32:21 lr 0.000555	time 1.8012 (2.2293)	loss 4.0359 (3.5690)	grad_norm 1.2474 (1.4471)	
[2022-01-22 02:13:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][390/1251]	eta 0:31:58 lr 0.000555	time 2.4747 (2.2285)	loss 3.8073 (3.5732)	grad_norm 1.3989 (1.4467)	
[2022-01-22 02:13:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][400/1251]	eta 0:31:35 lr 0.000555	time 1.9575 (2.2275)	loss 3.6593 (3.5749)	grad_norm 1.2524 (1.4470)	
[2022-01-22 02:13:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][410/1251]	eta 0:31:11 lr 0.000555	time 1.8820 (2.2257)	loss 2.5456 (3.5751)	grad_norm 1.4469 (1.4454)	
[2022-01-22 02:14:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][420/1251]	eta 0:30:51 lr 0.000555	time 2.1986 (2.2277)	loss 3.3476 (3.5771)	grad_norm 1.3030 (1.4461)	
[2022-01-22 02:14:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][430/1251]	eta 0:30:28 lr 0.000555	time 2.6187 (2.2276)	loss 3.6789 (3.5772)	grad_norm 1.3316 (1.4451)	
[2022-01-22 02:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][440/1251]	eta 0:30:09 lr 0.000555	time 2.1129 (2.2307)	loss 3.3493 (3.5725)	grad_norm 1.4077 (1.4449)	
[2022-01-22 02:15:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][450/1251]	eta 0:29:44 lr 0.000555	time 2.0865 (2.2277)	loss 3.0265 (3.5731)	grad_norm 1.2946 (1.4441)	
[2022-01-22 02:15:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][460/1251]	eta 0:29:21 lr 0.000555	time 1.5811 (2.2271)	loss 4.2715 (3.5722)	grad_norm 1.3335 (1.4445)	
[2022-01-22 02:16:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][470/1251]	eta 0:28:59 lr 0.000555	time 1.9564 (2.2273)	loss 4.0394 (3.5742)	grad_norm 1.7236 (1.4436)	
[2022-01-22 02:16:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][480/1251]	eta 0:28:38 lr 0.000555	time 1.8671 (2.2291)	loss 4.3319 (3.5784)	grad_norm 1.8917 (1.4431)	
[2022-01-22 02:16:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][490/1251]	eta 0:28:14 lr 0.000555	time 1.5413 (2.2261)	loss 3.6994 (3.5795)	grad_norm 1.5674 (1.4462)	
[2022-01-22 02:17:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][500/1251]	eta 0:27:50 lr 0.000555	time 1.8156 (2.2249)	loss 3.5632 (3.5817)	grad_norm 1.1139 (1.4479)	
[2022-01-22 02:17:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][510/1251]	eta 0:27:28 lr 0.000555	time 2.8244 (2.2248)	loss 3.4654 (3.5830)	grad_norm 1.5622 (1.4488)	
[2022-01-22 02:18:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][520/1251]	eta 0:27:07 lr 0.000555	time 1.8651 (2.2268)	loss 3.0393 (3.5839)	grad_norm 1.2935 (1.4481)	
[2022-01-22 02:18:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][530/1251]	eta 0:26:43 lr 0.000555	time 1.6609 (2.2237)	loss 4.2626 (3.5859)	grad_norm 1.5562 (1.4472)	
[2022-01-22 02:18:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][540/1251]	eta 0:26:19 lr 0.000555	time 2.2554 (2.2214)	loss 2.5114 (3.5837)	grad_norm 1.2700 (1.4467)	
[2022-01-22 02:19:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][550/1251]	eta 0:25:56 lr 0.000554	time 1.8609 (2.2208)	loss 4.1718 (3.5860)	grad_norm 1.3612 (1.4451)	
[2022-01-22 02:19:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][560/1251]	eta 0:25:33 lr 0.000554	time 1.9089 (2.2198)	loss 3.2410 (3.5823)	grad_norm 1.5414 (1.4464)	
[2022-01-22 02:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][570/1251]	eta 0:25:12 lr 0.000554	time 2.0924 (2.2208)	loss 3.1417 (3.5816)	grad_norm 1.8235 (1.4468)	
[2022-01-22 02:20:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][580/1251]	eta 0:24:48 lr 0.000554	time 2.2473 (2.2190)	loss 3.6946 (3.5841)	grad_norm 1.2336 (1.4466)	
[2022-01-22 02:20:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][590/1251]	eta 0:24:26 lr 0.000554	time 2.3846 (2.2180)	loss 4.3384 (3.5875)	grad_norm 1.5593 (1.4468)	
[2022-01-22 02:20:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][600/1251]	eta 0:24:02 lr 0.000554	time 2.4513 (2.2163)	loss 2.4749 (3.5834)	grad_norm 1.5460 (1.4471)	
[2022-01-22 02:21:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][610/1251]	eta 0:23:38 lr 0.000554	time 2.5557 (2.2130)	loss 3.9968 (3.5851)	grad_norm 1.5654 (1.4499)	
[2022-01-22 02:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][620/1251]	eta 0:23:15 lr 0.000554	time 1.9429 (2.2113)	loss 3.9879 (3.5843)	grad_norm 1.5880 (1.4495)	
[2022-01-22 02:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][630/1251]	eta 0:22:53 lr 0.000554	time 2.6214 (2.2113)	loss 2.9502 (3.5845)	grad_norm 1.5332 (1.4495)	
[2022-01-22 02:22:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][640/1251]	eta 0:22:29 lr 0.000554	time 1.5999 (2.2090)	loss 4.0720 (3.5874)	grad_norm 1.3511 (1.4482)	
[2022-01-22 02:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][650/1251]	eta 0:22:07 lr 0.000554	time 2.4544 (2.2088)	loss 3.7171 (3.5914)	grad_norm 1.2302 (1.4474)	
[2022-01-22 02:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][660/1251]	eta 0:21:44 lr 0.000554	time 1.8158 (2.2072)	loss 4.0154 (3.5954)	grad_norm 1.3755 (1.4473)	
[2022-01-22 02:23:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][670/1251]	eta 0:21:26 lr 0.000554	time 2.2454 (2.2135)	loss 3.2906 (3.5955)	grad_norm 1.2754 (1.4472)	
[2022-01-22 02:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][680/1251]	eta 0:21:05 lr 0.000554	time 1.9163 (2.2165)	loss 4.3077 (3.5962)	grad_norm 1.4934 (1.4472)	
[2022-01-22 02:24:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][690/1251]	eta 0:20:43 lr 0.000554	time 2.2039 (2.2163)	loss 3.8408 (3.5928)	grad_norm 1.3660 (1.4462)	
[2022-01-22 02:24:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][700/1251]	eta 0:20:20 lr 0.000554	time 2.1297 (2.2154)	loss 3.4520 (3.5927)	grad_norm 1.4627 (1.4443)	
[2022-01-22 02:24:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][710/1251]	eta 0:19:59 lr 0.000554	time 2.4128 (2.2166)	loss 3.4320 (3.5939)	grad_norm 1.3617 (1.4436)	
[2022-01-22 02:25:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][720/1251]	eta 0:19:35 lr 0.000554	time 1.9468 (2.2137)	loss 3.5948 (3.5926)	grad_norm 1.6150 (1.4431)	
[2022-01-22 02:25:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][730/1251]	eta 0:19:12 lr 0.000554	time 2.4584 (2.2128)	loss 3.7690 (3.5939)	grad_norm 1.4514 (1.4432)	
[2022-01-22 02:26:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][740/1251]	eta 0:18:49 lr 0.000554	time 2.0899 (2.2108)	loss 3.1142 (3.5937)	grad_norm 1.3478 (1.4432)	
[2022-01-22 02:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][750/1251]	eta 0:18:28 lr 0.000554	time 1.8898 (2.2129)	loss 4.2372 (3.5903)	grad_norm 1.3813 (1.4427)	
[2022-01-22 02:26:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][760/1251]	eta 0:18:06 lr 0.000554	time 1.8454 (2.2128)	loss 4.0177 (3.5906)	grad_norm 1.5804 (1.4428)	
[2022-01-22 02:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][770/1251]	eta 0:17:44 lr 0.000554	time 2.1856 (2.2128)	loss 2.8357 (3.5886)	grad_norm 1.3518 (1.4423)	
[2022-01-22 02:27:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][780/1251]	eta 0:17:21 lr 0.000554	time 1.9216 (2.2112)	loss 2.8433 (3.5864)	grad_norm 1.2917 (1.4417)	
[2022-01-22 02:27:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][790/1251]	eta 0:17:01 lr 0.000553	time 2.4963 (2.2148)	loss 2.9875 (3.5821)	grad_norm 1.3940 (1.4409)	
[2022-01-22 02:28:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][800/1251]	eta 0:16:37 lr 0.000553	time 1.6731 (2.2123)	loss 4.2694 (3.5838)	grad_norm 1.4366 (1.4407)	
[2022-01-22 02:28:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][810/1251]	eta 0:16:14 lr 0.000553	time 1.8639 (2.2103)	loss 3.8933 (3.5865)	grad_norm 1.3928 (1.4405)	
[2022-01-22 02:28:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][820/1251]	eta 0:15:52 lr 0.000553	time 1.7618 (2.2092)	loss 4.0850 (3.5879)	grad_norm 1.5124 (1.4404)	
[2022-01-22 02:29:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][830/1251]	eta 0:15:30 lr 0.000553	time 2.4619 (2.2104)	loss 3.2346 (3.5907)	grad_norm 1.2541 (1.4400)	
[2022-01-22 02:29:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][840/1251]	eta 0:15:08 lr 0.000553	time 1.8117 (2.2102)	loss 2.8176 (3.5914)	grad_norm 1.4951 (1.4405)	
[2022-01-22 02:30:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][850/1251]	eta 0:14:46 lr 0.000553	time 1.9418 (2.2096)	loss 3.3702 (3.5902)	grad_norm 1.8829 (1.4412)	
[2022-01-22 02:30:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][860/1251]	eta 0:14:23 lr 0.000553	time 1.7208 (2.2090)	loss 3.9224 (3.5901)	grad_norm 1.2893 (1.4412)	
[2022-01-22 02:30:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][870/1251]	eta 0:14:01 lr 0.000553	time 2.0876 (2.2094)	loss 4.4237 (3.5886)	grad_norm 1.6382 (1.4405)	
[2022-01-22 02:31:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][880/1251]	eta 0:13:38 lr 0.000553	time 1.9015 (2.2069)	loss 3.6355 (3.5895)	grad_norm 1.3457 (1.4396)	
[2022-01-22 02:31:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][890/1251]	eta 0:13:16 lr 0.000553	time 1.9487 (2.2055)	loss 3.6452 (3.5915)	grad_norm 1.5496 (1.4389)	
[2022-01-22 02:31:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][900/1251]	eta 0:12:53 lr 0.000553	time 2.0792 (2.2047)	loss 2.9791 (3.5913)	grad_norm 1.5627 (1.4389)	
[2022-01-22 02:32:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][910/1251]	eta 0:12:32 lr 0.000553	time 2.1696 (2.2065)	loss 3.5513 (3.5912)	grad_norm 1.3440 (1.4388)	
[2022-01-22 02:32:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][920/1251]	eta 0:12:10 lr 0.000553	time 1.4738 (2.2071)	loss 2.5511 (3.5877)	grad_norm 1.5289 (1.4384)	
[2022-01-22 02:32:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][930/1251]	eta 0:11:48 lr 0.000553	time 1.4932 (2.2061)	loss 3.7070 (3.5848)	grad_norm 1.5926 (1.4378)	
[2022-01-22 02:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][940/1251]	eta 0:11:25 lr 0.000553	time 1.9596 (2.2053)	loss 2.6158 (3.5826)	grad_norm 1.8665 (1.4387)	
[2022-01-22 02:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][950/1251]	eta 0:11:04 lr 0.000553	time 2.1409 (2.2062)	loss 4.3952 (3.5845)	grad_norm 1.5786 (1.4392)	
[2022-01-22 02:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][960/1251]	eta 0:10:42 lr 0.000553	time 1.6579 (2.2074)	loss 4.4160 (3.5867)	grad_norm 1.3445 (1.4397)	
[2022-01-22 02:34:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][970/1251]	eta 0:10:19 lr 0.000553	time 1.8294 (2.2060)	loss 4.0480 (3.5836)	grad_norm 1.5664 (1.4400)	
[2022-01-22 02:34:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][980/1251]	eta 0:09:57 lr 0.000553	time 1.8901 (2.2048)	loss 2.7690 (3.5842)	grad_norm 1.4540 (1.4390)	
[2022-01-22 02:35:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][990/1251]	eta 0:09:34 lr 0.000553	time 1.6207 (2.2030)	loss 3.2159 (3.5844)	grad_norm 1.4802 (1.4392)	
[2022-01-22 02:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1000/1251]	eta 0:09:12 lr 0.000553	time 2.0133 (2.2021)	loss 3.4704 (3.5843)	grad_norm 1.4528 (1.4389)	
[2022-01-22 02:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1010/1251]	eta 0:08:50 lr 0.000553	time 1.9289 (2.2022)	loss 4.1575 (3.5861)	grad_norm 1.2704 (1.4393)	
[2022-01-22 02:36:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1020/1251]	eta 0:08:28 lr 0.000553	time 2.1810 (2.2017)	loss 3.7168 (3.5853)	grad_norm 1.4206 (1.4398)	
[2022-01-22 02:36:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1030/1251]	eta 0:08:07 lr 0.000552	time 2.2375 (2.2040)	loss 3.0007 (3.5847)	grad_norm 1.6255 (1.4396)	
[2022-01-22 02:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1040/1251]	eta 0:07:45 lr 0.000552	time 2.0049 (2.2044)	loss 3.9486 (3.5833)	grad_norm 2.0919 (1.4406)	
[2022-01-22 02:37:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1050/1251]	eta 0:07:23 lr 0.000552	time 2.1662 (2.2047)	loss 3.6698 (3.5837)	grad_norm 1.6947 (1.4412)	
[2022-01-22 02:37:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1060/1251]	eta 0:07:00 lr 0.000552	time 1.9694 (2.2032)	loss 3.2171 (3.5849)	grad_norm 1.4668 (1.4406)	
[2022-01-22 02:38:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1070/1251]	eta 0:06:38 lr 0.000552	time 2.5575 (2.2028)	loss 4.1487 (3.5877)	grad_norm 1.3050 (1.4398)	
[2022-01-22 02:38:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1080/1251]	eta 0:06:16 lr 0.000552	time 1.5630 (2.2016)	loss 3.8148 (3.5867)	grad_norm 1.4555 (1.4403)	
[2022-01-22 02:38:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1090/1251]	eta 0:05:54 lr 0.000552	time 1.8582 (2.2011)	loss 2.4675 (3.5851)	grad_norm 1.4715 (1.4406)	
[2022-01-22 02:39:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1100/1251]	eta 0:05:32 lr 0.000552	time 2.2404 (2.2017)	loss 3.8747 (3.5863)	grad_norm 1.3406 (1.4397)	
[2022-01-22 02:39:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1110/1251]	eta 0:05:10 lr 0.000552	time 2.1808 (2.2012)	loss 4.0064 (3.5866)	grad_norm 1.3038 (1.4392)	
[2022-01-22 02:39:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1120/1251]	eta 0:04:48 lr 0.000552	time 2.7813 (2.2025)	loss 3.0930 (3.5846)	grad_norm 1.7958 (1.4400)	
[2022-01-22 02:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1130/1251]	eta 0:04:26 lr 0.000552	time 2.4945 (2.2034)	loss 3.9487 (3.5873)	grad_norm 1.3148 (1.4402)	
[2022-01-22 02:40:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1140/1251]	eta 0:04:04 lr 0.000552	time 2.1065 (2.2039)	loss 3.9694 (3.5882)	grad_norm 1.4372 (1.4404)	
[2022-01-22 02:40:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1150/1251]	eta 0:03:42 lr 0.000552	time 1.8924 (2.2029)	loss 4.0104 (3.5894)	grad_norm 1.7326 (1.4407)	
[2022-01-22 02:41:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1160/1251]	eta 0:03:20 lr 0.000552	time 2.5085 (2.2016)	loss 3.9063 (3.5902)	grad_norm 1.3944 (1.4409)	
[2022-01-22 02:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1170/1251]	eta 0:02:58 lr 0.000552	time 1.9045 (2.1996)	loss 3.8777 (3.5881)	grad_norm 1.2959 (1.4405)	
[2022-01-22 02:41:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1180/1251]	eta 0:02:36 lr 0.000552	time 2.1619 (2.1986)	loss 4.0725 (3.5886)	grad_norm 1.5260 (1.4404)	
[2022-01-22 02:42:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1190/1251]	eta 0:02:14 lr 0.000552	time 2.0574 (2.1984)	loss 4.2398 (3.5902)	grad_norm 1.4430 (1.4408)	
[2022-01-22 02:42:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1200/1251]	eta 0:01:52 lr 0.000552	time 2.1519 (2.1984)	loss 3.8644 (3.5915)	grad_norm 1.5414 (1.4414)	
[2022-01-22 02:43:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1210/1251]	eta 0:01:30 lr 0.000552	time 1.9960 (2.1979)	loss 3.3396 (3.5934)	grad_norm 1.9549 (1.4428)	
[2022-01-22 02:43:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1220/1251]	eta 0:01:08 lr 0.000552	time 1.9173 (2.1967)	loss 2.7604 (3.5935)	grad_norm 1.3302 (1.4432)	
[2022-01-22 02:43:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1230/1251]	eta 0:00:46 lr 0.000552	time 2.1429 (2.1966)	loss 4.0964 (3.5959)	grad_norm 1.2297 (1.4430)	
[2022-01-22 02:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1240/1251]	eta 0:00:24 lr 0.000552	time 2.1203 (2.1959)	loss 4.1540 (3.5970)	grad_norm 1.1873 (1.4428)	
[2022-01-22 02:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [140/300][1250/1251]	eta 0:00:02 lr 0.000552	time 1.1904 (2.1908)	loss 3.5406 (3.5962)	grad_norm 1.5033 (1.4425)	
[2022-01-22 02:44:23 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 140 training takes 0:45:41
[2022-01-22 02:44:23 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_140 saving......
[2022-01-22 02:44:34 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_140 saved !!!
[2022-01-22 02:44:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 15.043 (15.043)	Loss 1.0058 (1.0058)	Acc@1 76.562 (76.562)	Acc@5 92.871 (92.871)	
[2022-01-22 02:45:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.600 (2.890)	Loss 1.1210 (1.0518)	Acc@1 73.730 (75.426)	Acc@5 91.602 (92.605)	
[2022-01-22 02:45:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.699 (2.386)	Loss 1.0345 (1.0467)	Acc@1 75.293 (75.437)	Acc@5 93.750 (92.811)	
[2022-01-22 02:45:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.028 (2.071)	Loss 0.9947 (1.0360)	Acc@1 76.465 (75.564)	Acc@5 93.359 (93.016)	
[2022-01-22 02:45:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.840 (1.955)	Loss 0.9948 (1.0345)	Acc@1 77.344 (75.679)	Acc@5 93.262 (93.062)	
[2022-01-22 02:46:01 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.632 Acc@5 93.040
[2022-01-22 02:46:01 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.6%
[2022-01-22 02:46:01 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.63%
[2022-01-22 02:46:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][0/1251]	eta 7:34:52 lr 0.000552	time 21.8162 (21.8162)	loss 2.9439 (2.9439)	grad_norm 1.4289 (1.4289)	
[2022-01-22 02:46:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][10/1251]	eta 1:24:30 lr 0.000552	time 2.0757 (4.0856)	loss 3.6359 (3.5176)	grad_norm 1.4123 (1.4190)	
[2022-01-22 02:47:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][20/1251]	eta 1:04:40 lr 0.000552	time 2.4170 (3.1524)	loss 4.0974 (3.6095)	grad_norm 1.3533 (1.4665)	
[2022-01-22 02:47:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][30/1251]	eta 0:57:50 lr 0.000551	time 1.3682 (2.8420)	loss 2.4714 (3.5609)	grad_norm 1.3546 (1.4796)	
[2022-01-22 02:47:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][40/1251]	eta 0:55:14 lr 0.000551	time 5.2599 (2.7368)	loss 3.6483 (3.5546)	grad_norm 1.2895 (1.4750)	
[2022-01-22 02:48:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][50/1251]	eta 0:53:26 lr 0.000551	time 3.7649 (2.6697)	loss 3.7475 (3.5831)	grad_norm 1.2044 (1.4635)	
[2022-01-22 02:48:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][60/1251]	eta 0:51:29 lr 0.000551	time 1.5350 (2.5938)	loss 2.7905 (3.5680)	grad_norm 1.4110 (1.4539)	
[2022-01-22 02:49:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][70/1251]	eta 0:49:32 lr 0.000551	time 1.9111 (2.5173)	loss 3.8842 (3.5685)	grad_norm 1.3909 (1.4684)	
[2022-01-22 02:49:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][80/1251]	eta 0:48:23 lr 0.000551	time 3.4654 (2.4798)	loss 4.1449 (3.5371)	grad_norm 1.4682 (1.4698)	
[2022-01-22 02:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][90/1251]	eta 0:47:29 lr 0.000551	time 2.7013 (2.4547)	loss 2.4644 (3.5507)	grad_norm 1.5055 (1.4729)	
[2022-01-22 02:50:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][100/1251]	eta 0:46:45 lr 0.000551	time 2.1116 (2.4377)	loss 3.0635 (3.5523)	grad_norm 1.3174 (1.4683)	
[2022-01-22 02:50:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][110/1251]	eta 0:45:55 lr 0.000551	time 2.3502 (2.4149)	loss 3.0402 (3.5206)	grad_norm 1.3103 (1.4583)	
[2022-01-22 02:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][120/1251]	eta 0:45:14 lr 0.000551	time 3.3905 (2.4002)	loss 3.5694 (3.5183)	grad_norm 1.5393 (1.4535)	
[2022-01-22 02:51:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][130/1251]	eta 0:44:16 lr 0.000551	time 1.8036 (2.3698)	loss 3.9516 (3.5222)	grad_norm 1.6162 (1.4491)	
[2022-01-22 02:51:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][140/1251]	eta 0:43:29 lr 0.000551	time 2.1524 (2.3487)	loss 3.5588 (3.5119)	grad_norm 1.4924 (1.4481)	
[2022-01-22 02:51:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][150/1251]	eta 0:42:51 lr 0.000551	time 2.2136 (2.3355)	loss 2.3846 (3.4985)	grad_norm 1.5844 (1.4492)	
[2022-01-22 02:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][160/1251]	eta 0:42:27 lr 0.000551	time 3.5379 (2.3353)	loss 3.5065 (3.4843)	grad_norm 1.5107 (1.4542)	
[2022-01-22 02:52:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][170/1251]	eta 0:41:56 lr 0.000551	time 2.5912 (2.3275)	loss 3.4987 (3.4693)	grad_norm 1.5075 (1.4528)	
[2022-01-22 02:52:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][180/1251]	eta 0:41:11 lr 0.000551	time 1.7782 (2.3078)	loss 3.6525 (3.4843)	grad_norm 1.5824 (1.4493)	
[2022-01-22 02:53:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][190/1251]	eta 0:40:43 lr 0.000551	time 2.5232 (2.3034)	loss 3.3933 (3.4708)	grad_norm 1.4288 (1.4489)	
[2022-01-22 02:53:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][200/1251]	eta 0:40:20 lr 0.000551	time 2.2998 (2.3027)	loss 3.7517 (3.4816)	grad_norm 1.4219 (1.4495)	
[2022-01-22 02:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][210/1251]	eta 0:39:57 lr 0.000551	time 2.1364 (2.3031)	loss 2.4752 (3.4893)	grad_norm 1.6670 (1.4515)	
[2022-01-22 02:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][220/1251]	eta 0:39:29 lr 0.000551	time 2.5271 (2.2980)	loss 4.0437 (3.4916)	grad_norm 1.4823 (1.4561)	
[2022-01-22 02:54:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][230/1251]	eta 0:38:54 lr 0.000551	time 1.9056 (2.2861)	loss 3.2416 (3.4880)	grad_norm 1.6281 (1.4572)	
[2022-01-22 02:55:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][240/1251]	eta 0:38:19 lr 0.000551	time 2.0110 (2.2747)	loss 3.6701 (3.4918)	grad_norm 1.5428 (1.4576)	
[2022-01-22 02:55:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][250/1251]	eta 0:37:53 lr 0.000551	time 2.4919 (2.2713)	loss 3.1732 (3.4956)	grad_norm 1.3758 (1.4572)	
[2022-01-22 02:55:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][260/1251]	eta 0:37:23 lr 0.000551	time 2.1615 (2.2642)	loss 3.9356 (3.4956)	grad_norm 1.5780 (1.4575)	
[2022-01-22 02:56:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][270/1251]	eta 0:37:01 lr 0.000550	time 2.8423 (2.2645)	loss 2.7730 (3.4890)	grad_norm 1.4966 (1.4598)	
[2022-01-22 02:56:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][280/1251]	eta 0:36:30 lr 0.000550	time 1.7606 (2.2557)	loss 3.0079 (3.4970)	grad_norm 1.2827 (1.4567)	
[2022-01-22 02:56:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][290/1251]	eta 0:36:06 lr 0.000550	time 2.6663 (2.2543)	loss 3.3996 (3.4972)	grad_norm 1.4931 (1.4560)	
[2022-01-22 02:57:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][300/1251]	eta 0:35:38 lr 0.000550	time 1.8500 (2.2489)	loss 3.0795 (3.5022)	grad_norm 1.2147 (1.4546)	
[2022-01-22 02:57:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][310/1251]	eta 0:35:15 lr 0.000550	time 2.2986 (2.2483)	loss 3.9654 (3.4960)	grad_norm 1.3631 (1.4530)	
[2022-01-22 02:58:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][320/1251]	eta 0:34:51 lr 0.000550	time 2.9358 (2.2467)	loss 2.8257 (3.4858)	grad_norm 1.2922 (1.4516)	
[2022-01-22 02:58:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][330/1251]	eta 0:34:30 lr 0.000550	time 2.8167 (2.2480)	loss 4.0766 (3.4854)	grad_norm 1.4713 (1.4510)	
[2022-01-22 02:58:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][340/1251]	eta 0:34:06 lr 0.000550	time 1.9275 (2.2469)	loss 4.1433 (3.4907)	grad_norm 1.3053 (1.4528)	
[2022-01-22 02:59:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][350/1251]	eta 0:33:44 lr 0.000550	time 2.8430 (2.2471)	loss 3.8418 (3.5005)	grad_norm 1.6345 (1.4508)	
[2022-01-22 02:59:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][360/1251]	eta 0:33:16 lr 0.000550	time 1.9833 (2.2409)	loss 3.5135 (3.5047)	grad_norm 1.4891 (1.4504)	
[2022-01-22 02:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][370/1251]	eta 0:32:55 lr 0.000550	time 2.6682 (2.2428)	loss 2.7756 (3.5040)	grad_norm 1.5472 (1.4482)	
[2022-01-22 03:00:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][380/1251]	eta 0:32:30 lr 0.000550	time 2.2240 (2.2399)	loss 4.1352 (3.5017)	grad_norm 1.5134 (1.4558)	
[2022-01-22 03:00:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][390/1251]	eta 0:32:09 lr 0.000550	time 2.2069 (2.2411)	loss 3.7366 (3.5072)	grad_norm 1.6818 (1.4562)	
[2022-01-22 03:01:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][400/1251]	eta 0:31:47 lr 0.000550	time 1.8767 (2.2410)	loss 4.1152 (3.5079)	grad_norm 1.3148 (1.4539)	
[2022-01-22 03:01:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][410/1251]	eta 0:31:24 lr 0.000550	time 3.3418 (2.2413)	loss 3.7005 (3.5100)	grad_norm 1.6609 (1.4547)	
[2022-01-22 03:01:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][420/1251]	eta 0:30:58 lr 0.000550	time 1.8902 (2.2364)	loss 3.4036 (3.5123)	grad_norm 1.2956 (1.4547)	
[2022-01-22 03:02:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][430/1251]	eta 0:30:31 lr 0.000550	time 2.1788 (2.2311)	loss 4.0725 (3.5099)	grad_norm 1.5825 (1.4554)	
[2022-01-22 03:02:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][440/1251]	eta 0:30:07 lr 0.000550	time 2.2520 (2.2287)	loss 3.3851 (3.5043)	grad_norm 1.4407 (1.4574)	
[2022-01-22 03:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][450/1251]	eta 0:29:45 lr 0.000550	time 2.4776 (2.2288)	loss 4.2303 (3.5062)	grad_norm 1.4156 (1.4584)	
[2022-01-22 03:03:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][460/1251]	eta 0:29:23 lr 0.000550	time 2.0949 (2.2300)	loss 2.8995 (3.5078)	grad_norm 1.5909 (1.4585)	
[2022-01-22 03:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][470/1251]	eta 0:29:02 lr 0.000550	time 1.8878 (2.2313)	loss 2.9170 (3.5099)	grad_norm 1.4441 (1.4578)	
[2022-01-22 03:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][480/1251]	eta 0:28:40 lr 0.000550	time 2.1591 (2.2317)	loss 3.6203 (3.5116)	grad_norm 1.5051 (1.4571)	
[2022-01-22 03:04:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][490/1251]	eta 0:28:16 lr 0.000550	time 2.2747 (2.2291)	loss 3.6348 (3.5137)	grad_norm 1.3377 (1.4564)	
[2022-01-22 03:04:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][500/1251]	eta 0:27:49 lr 0.000550	time 1.7835 (2.2234)	loss 3.0416 (3.5078)	grad_norm 1.4500 (1.4583)	
[2022-01-22 03:04:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][510/1251]	eta 0:27:25 lr 0.000549	time 1.7971 (2.2205)	loss 2.5851 (3.5121)	grad_norm 1.4985 (1.4587)	
[2022-01-22 03:05:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][520/1251]	eta 0:27:01 lr 0.000549	time 1.9684 (2.2188)	loss 2.9377 (3.5143)	grad_norm 1.3783 (1.4596)	
[2022-01-22 03:05:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][530/1251]	eta 0:26:40 lr 0.000549	time 3.0363 (2.2198)	loss 4.2135 (3.5132)	grad_norm 1.3181 (1.4587)	
[2022-01-22 03:06:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][540/1251]	eta 0:26:19 lr 0.000549	time 2.4220 (2.2213)	loss 3.2723 (3.5160)	grad_norm 1.4445 (1.4601)	
[2022-01-22 03:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][550/1251]	eta 0:25:55 lr 0.000549	time 1.9985 (2.2191)	loss 4.0355 (3.5156)	grad_norm 1.3952 (1.4599)	
[2022-01-22 03:06:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][560/1251]	eta 0:25:32 lr 0.000549	time 1.6985 (2.2184)	loss 4.0976 (3.5200)	grad_norm 1.2448 (1.4603)	
[2022-01-22 03:07:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][570/1251]	eta 0:25:11 lr 0.000549	time 3.0940 (2.2199)	loss 3.9320 (3.5198)	grad_norm 1.4528 (1.4599)	
[2022-01-22 03:07:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][580/1251]	eta 0:24:47 lr 0.000549	time 1.6522 (2.2169)	loss 2.9616 (3.5211)	grad_norm 1.3795 (1.4595)	
[2022-01-22 03:07:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][590/1251]	eta 0:24:25 lr 0.000549	time 2.3081 (2.2171)	loss 3.8372 (3.5242)	grad_norm 1.4329 (1.4597)	
[2022-01-22 03:08:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][600/1251]	eta 0:24:02 lr 0.000549	time 1.9797 (2.2159)	loss 4.1164 (3.5227)	grad_norm 1.3519 (1.4621)	
[2022-01-22 03:08:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][610/1251]	eta 0:23:40 lr 0.000549	time 2.8824 (2.2161)	loss 2.9448 (3.5254)	grad_norm 1.3862 (1.4644)	
[2022-01-22 03:08:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][620/1251]	eta 0:23:16 lr 0.000549	time 1.9553 (2.2136)	loss 3.0464 (3.5242)	grad_norm 1.5190 (1.4669)	
[2022-01-22 03:09:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][630/1251]	eta 0:22:53 lr 0.000549	time 1.9617 (2.2123)	loss 4.0207 (3.5302)	grad_norm 1.5953 (1.4661)	
[2022-01-22 03:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][640/1251]	eta 0:22:31 lr 0.000549	time 1.6471 (2.2114)	loss 3.8092 (3.5324)	grad_norm 1.4689 (1.4660)	
[2022-01-22 03:10:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][650/1251]	eta 0:22:10 lr 0.000549	time 3.6741 (2.2135)	loss 2.9592 (3.5349)	grad_norm 1.5143 (1.4658)	
[2022-01-22 03:10:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][660/1251]	eta 0:21:48 lr 0.000549	time 2.3110 (2.2144)	loss 3.7578 (3.5377)	grad_norm 1.3448 (1.4661)	
[2022-01-22 03:10:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][670/1251]	eta 0:21:27 lr 0.000549	time 1.8793 (2.2164)	loss 3.7921 (3.5395)	grad_norm 1.5642 (1.4654)	
[2022-01-22 03:11:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][680/1251]	eta 0:21:05 lr 0.000549	time 2.0023 (2.2165)	loss 2.8945 (3.5379)	grad_norm 1.3387 (1.4648)	
[2022-01-22 03:11:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][690/1251]	eta 0:20:44 lr 0.000549	time 3.6563 (2.2189)	loss 3.7239 (3.5402)	grad_norm 1.4323 (1.4634)	
[2022-01-22 03:11:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][700/1251]	eta 0:20:21 lr 0.000549	time 1.8930 (2.2165)	loss 4.1770 (3.5413)	grad_norm 1.3503 (1.4622)	
[2022-01-22 03:12:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][710/1251]	eta 0:19:57 lr 0.000549	time 1.8333 (2.2139)	loss 3.8087 (3.5403)	grad_norm 1.2814 (1.4623)	
[2022-01-22 03:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][720/1251]	eta 0:19:33 lr 0.000549	time 1.8926 (2.2101)	loss 4.1984 (3.5425)	grad_norm 1.6587 (1.4623)	
[2022-01-22 03:12:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][730/1251]	eta 0:19:10 lr 0.000549	time 2.2037 (2.2084)	loss 3.1280 (3.5419)	grad_norm 1.6301 (1.4626)	
[2022-01-22 03:13:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][740/1251]	eta 0:18:47 lr 0.000549	time 1.9130 (2.2062)	loss 3.7422 (3.5422)	grad_norm 1.2793 (1.4627)	
[2022-01-22 03:13:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][750/1251]	eta 0:18:25 lr 0.000548	time 1.9824 (2.2056)	loss 2.5358 (3.5433)	grad_norm 1.5090 (1.4625)	
[2022-01-22 03:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][760/1251]	eta 0:18:02 lr 0.000548	time 1.7720 (2.2038)	loss 4.3945 (3.5465)	grad_norm 1.4469 (1.4621)	
[2022-01-22 03:14:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][770/1251]	eta 0:17:40 lr 0.000548	time 2.7667 (2.2045)	loss 4.0517 (3.5484)	grad_norm 1.3041 (1.4611)	
[2022-01-22 03:14:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][780/1251]	eta 0:17:19 lr 0.000548	time 1.8329 (2.2063)	loss 3.8340 (3.5472)	grad_norm 1.4664 (1.4622)	
[2022-01-22 03:15:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][790/1251]	eta 0:16:57 lr 0.000548	time 1.9855 (2.2073)	loss 2.6992 (3.5448)	grad_norm 1.3286 (1.4628)	
[2022-01-22 03:15:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][800/1251]	eta 0:16:36 lr 0.000548	time 1.8682 (2.2098)	loss 3.2977 (3.5416)	grad_norm 1.4784 (1.4626)	
[2022-01-22 03:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][810/1251]	eta 0:16:15 lr 0.000548	time 2.2049 (2.2114)	loss 3.8479 (3.5451)	grad_norm 1.6612 (1.4650)	
[2022-01-22 03:16:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][820/1251]	eta 0:15:53 lr 0.000548	time 1.9774 (2.2113)	loss 3.6154 (3.5472)	grad_norm 1.4025 (1.4654)	
[2022-01-22 03:16:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][830/1251]	eta 0:15:29 lr 0.000548	time 1.9465 (2.2085)	loss 3.5573 (3.5473)	grad_norm 1.4593 (1.4651)	
[2022-01-22 03:16:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][840/1251]	eta 0:15:06 lr 0.000548	time 1.9360 (2.2059)	loss 4.1200 (3.5519)	grad_norm 1.3818 (1.4647)	
[2022-01-22 03:17:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][850/1251]	eta 0:14:45 lr 0.000548	time 2.8684 (2.2071)	loss 2.8293 (3.5549)	grad_norm 1.3037 (1.4634)	
[2022-01-22 03:17:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][860/1251]	eta 0:14:23 lr 0.000548	time 2.4216 (2.2081)	loss 2.8600 (3.5549)	grad_norm 1.3480 (1.4625)	
[2022-01-22 03:18:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][870/1251]	eta 0:14:01 lr 0.000548	time 1.8471 (2.2081)	loss 4.0517 (3.5540)	grad_norm 1.3759 (1.4611)	
[2022-01-22 03:18:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][880/1251]	eta 0:13:39 lr 0.000548	time 2.1941 (2.2097)	loss 2.6872 (3.5523)	grad_norm 1.2961 (1.4603)	
[2022-01-22 03:18:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][890/1251]	eta 0:13:18 lr 0.000548	time 1.5996 (2.2107)	loss 4.1646 (3.5565)	grad_norm 1.5559 (1.4599)	
[2022-01-22 03:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][900/1251]	eta 0:12:55 lr 0.000548	time 1.9878 (2.2080)	loss 3.1468 (3.5578)	grad_norm 1.3247 (1.4608)	
[2022-01-22 03:19:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][910/1251]	eta 0:12:32 lr 0.000548	time 2.0177 (2.2060)	loss 3.1077 (3.5558)	grad_norm 1.2999 (1.4607)	
[2022-01-22 03:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][920/1251]	eta 0:12:09 lr 0.000548	time 1.6447 (2.2039)	loss 4.2910 (3.5562)	grad_norm 1.3824 (1.4618)	
[2022-01-22 03:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][930/1251]	eta 0:11:47 lr 0.000548	time 1.8293 (2.2027)	loss 4.5163 (3.5594)	grad_norm 1.4214 (1.4619)	
[2022-01-22 03:20:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][940/1251]	eta 0:11:25 lr 0.000548	time 2.0881 (2.2028)	loss 4.0827 (3.5605)	grad_norm 1.4865 (1.4635)	
[2022-01-22 03:20:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][950/1251]	eta 0:11:03 lr 0.000548	time 2.5500 (2.2043)	loss 2.6402 (3.5611)	grad_norm 1.3460 (1.4633)	
[2022-01-22 03:21:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][960/1251]	eta 0:10:42 lr 0.000548	time 2.6984 (2.2064)	loss 3.4011 (3.5581)	grad_norm 1.3740 (1.4636)	
[2022-01-22 03:21:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][970/1251]	eta 0:10:20 lr 0.000548	time 2.4571 (2.2093)	loss 3.3961 (3.5614)	grad_norm 1.3502 (1.4629)	
[2022-01-22 03:22:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][980/1251]	eta 0:09:58 lr 0.000548	time 1.8469 (2.2090)	loss 3.9636 (3.5645)	grad_norm 1.3323 (1.4627)	
[2022-01-22 03:22:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][990/1251]	eta 0:09:36 lr 0.000547	time 1.9035 (2.2074)	loss 4.1621 (3.5674)	grad_norm 1.8120 (1.4639)	
[2022-01-22 03:22:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1000/1251]	eta 0:09:13 lr 0.000547	time 1.8427 (2.2045)	loss 3.8390 (3.5677)	grad_norm 1.5231 (1.4646)	
[2022-01-22 03:23:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1010/1251]	eta 0:08:50 lr 0.000547	time 1.7753 (2.2026)	loss 3.9826 (3.5702)	grad_norm 1.3074 (1.4651)	
[2022-01-22 03:23:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1020/1251]	eta 0:08:29 lr 0.000547	time 1.4838 (2.2052)	loss 4.3603 (3.5731)	grad_norm 1.3099 (1.4647)	
[2022-01-22 03:23:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1030/1251]	eta 0:08:07 lr 0.000547	time 1.8779 (2.2043)	loss 3.9659 (3.5748)	grad_norm 1.5266 (1.4648)	
[2022-01-22 03:24:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1040/1251]	eta 0:07:45 lr 0.000547	time 1.9202 (2.2040)	loss 2.8233 (3.5736)	grad_norm 1.4217 (1.4649)	
[2022-01-22 03:24:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1050/1251]	eta 0:07:23 lr 0.000547	time 1.8389 (2.2046)	loss 4.0819 (3.5772)	grad_norm 1.8410 (1.4650)	
[2022-01-22 03:25:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1060/1251]	eta 0:07:00 lr 0.000547	time 1.8303 (2.2039)	loss 3.6256 (3.5792)	grad_norm 1.3371 (1.4648)	
[2022-01-22 03:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1070/1251]	eta 0:06:38 lr 0.000547	time 1.7244 (2.2036)	loss 2.4053 (3.5800)	grad_norm 1.4011 (1.4640)	
[2022-01-22 03:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1080/1251]	eta 0:06:16 lr 0.000547	time 1.8011 (2.2021)	loss 2.9806 (3.5808)	grad_norm 1.4024 (1.4631)	
[2022-01-22 03:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1090/1251]	eta 0:05:54 lr 0.000547	time 2.9618 (2.2015)	loss 3.2902 (3.5796)	grad_norm 1.4501 (1.4626)	
[2022-01-22 03:26:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1100/1251]	eta 0:05:32 lr 0.000547	time 1.7747 (2.2006)	loss 3.0701 (3.5777)	grad_norm 1.4281 (1.4625)	
[2022-01-22 03:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1110/1251]	eta 0:05:10 lr 0.000547	time 2.4783 (2.2016)	loss 4.4640 (3.5796)	grad_norm 1.5078 (1.4625)	
[2022-01-22 03:27:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1120/1251]	eta 0:04:48 lr 0.000547	time 2.2049 (2.2015)	loss 3.6986 (3.5814)	grad_norm 1.3923 (1.4628)	
[2022-01-22 03:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1130/1251]	eta 0:04:26 lr 0.000547	time 2.1357 (2.2015)	loss 2.6309 (3.5814)	grad_norm 1.7149 (1.4630)	
[2022-01-22 03:27:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1140/1251]	eta 0:04:04 lr 0.000547	time 2.2023 (2.2003)	loss 4.0342 (3.5846)	grad_norm 1.3350 (1.4626)	
[2022-01-22 03:28:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1150/1251]	eta 0:03:42 lr 0.000547	time 1.8295 (2.2021)	loss 2.8861 (3.5864)	grad_norm 1.3991 (1.4622)	
[2022-01-22 03:28:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1160/1251]	eta 0:03:20 lr 0.000547	time 2.9054 (2.2021)	loss 2.8886 (3.5864)	grad_norm 1.3208 (1.4617)	
[2022-01-22 03:29:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1170/1251]	eta 0:02:58 lr 0.000547	time 2.0668 (2.2020)	loss 3.8703 (3.5866)	grad_norm 1.4802 (1.4617)	
[2022-01-22 03:29:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1180/1251]	eta 0:02:36 lr 0.000547	time 1.8765 (2.2001)	loss 4.1804 (3.5858)	grad_norm 1.8020 (1.4626)	
[2022-01-22 03:29:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1190/1251]	eta 0:02:14 lr 0.000547	time 1.8695 (2.1992)	loss 3.4538 (3.5856)	grad_norm 1.4772 (1.4625)	
[2022-01-22 03:30:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1200/1251]	eta 0:01:52 lr 0.000547	time 1.9874 (2.1983)	loss 3.4158 (3.5848)	grad_norm 1.4099 (1.4624)	
[2022-01-22 03:30:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1210/1251]	eta 0:01:30 lr 0.000547	time 1.8089 (2.1980)	loss 4.0328 (3.5838)	grad_norm 1.3746 (1.4621)	
[2022-01-22 03:30:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1220/1251]	eta 0:01:08 lr 0.000547	time 1.6753 (2.1975)	loss 3.6810 (3.5832)	grad_norm 1.2993 (1.4620)	
[2022-01-22 03:31:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1230/1251]	eta 0:00:46 lr 0.000547	time 1.7572 (2.1967)	loss 3.7962 (3.5861)	grad_norm 2.0059 (1.4625)	
[2022-01-22 03:31:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1240/1251]	eta 0:00:24 lr 0.000546	time 1.8161 (2.1976)	loss 2.8917 (3.5878)	grad_norm 1.5131 (1.4630)	
[2022-01-22 03:31:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [141/300][1250/1251]	eta 0:00:02 lr 0.000546	time 1.1540 (2.1926)	loss 3.5816 (3.5878)	grad_norm 1.3198 (1.4624)	
[2022-01-22 03:31:45 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 141 training takes 0:45:43
[2022-01-22 03:32:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.409 (19.409)	Loss 1.0407 (1.0407)	Acc@1 75.781 (75.781)	Acc@5 94.043 (94.043)	
[2022-01-22 03:32:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.461 (3.573)	Loss 1.0651 (1.0611)	Acc@1 76.074 (75.648)	Acc@5 92.773 (93.226)	
[2022-01-22 03:32:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.621 (2.638)	Loss 1.0216 (1.0558)	Acc@1 76.562 (75.581)	Acc@5 93.262 (93.299)	
[2022-01-22 03:32:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.954 (2.331)	Loss 1.0798 (1.0640)	Acc@1 74.316 (75.545)	Acc@5 92.090 (93.013)	
[2022-01-22 03:33:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.238 (2.202)	Loss 1.0319 (1.0650)	Acc@1 76.562 (75.550)	Acc@5 92.480 (92.945)	
[2022-01-22 03:33:23 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.550 Acc@5 92.968
[2022-01-22 03:33:23 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.6%
[2022-01-22 03:33:23 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.63%
[2022-01-22 03:33:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][0/1251]	eta 7:22:14 lr 0.000546	time 21.2104 (21.2104)	loss 2.8355 (2.8355)	grad_norm 1.5724 (1.5724)	
[2022-01-22 03:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][10/1251]	eta 1:26:35 lr 0.000546	time 2.9475 (4.1869)	loss 3.3418 (3.4564)	grad_norm 1.2028 (1.4404)	
[2022-01-22 03:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][20/1251]	eta 1:07:10 lr 0.000546	time 2.5170 (3.2739)	loss 3.9441 (3.4612)	grad_norm 1.2597 (1.4132)	
[2022-01-22 03:34:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][30/1251]	eta 0:58:02 lr 0.000546	time 1.4719 (2.8519)	loss 2.3949 (3.5043)	grad_norm 1.5624 (1.4051)	
[2022-01-22 03:35:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][40/1251]	eta 0:54:50 lr 0.000546	time 3.4985 (2.7174)	loss 3.9980 (3.4675)	grad_norm 1.4611 (1.4185)	
[2022-01-22 03:35:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][50/1251]	eta 0:53:02 lr 0.000546	time 2.8557 (2.6501)	loss 3.5281 (3.5596)	grad_norm 1.3102 (1.4184)	
[2022-01-22 03:36:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][60/1251]	eta 0:51:44 lr 0.000546	time 2.1896 (2.6065)	loss 3.5254 (3.5593)	grad_norm 1.6403 (1.4412)	
[2022-01-22 03:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][70/1251]	eta 0:49:52 lr 0.000546	time 1.9149 (2.5342)	loss 4.3283 (3.5637)	grad_norm 1.3694 (1.4395)	
[2022-01-22 03:36:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][80/1251]	eta 0:48:23 lr 0.000546	time 2.6243 (2.4794)	loss 4.2666 (3.5420)	grad_norm 1.3443 (1.4440)	
[2022-01-22 03:37:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][90/1251]	eta 0:46:44 lr 0.000546	time 1.6613 (2.4153)	loss 4.0439 (3.5374)	grad_norm 1.4683 (1.4532)	
[2022-01-22 03:37:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][100/1251]	eta 0:45:46 lr 0.000546	time 2.5558 (2.3861)	loss 3.6863 (3.5445)	grad_norm 1.9943 (1.4669)	
[2022-01-22 03:37:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][110/1251]	eta 0:44:53 lr 0.000546	time 2.1975 (2.3610)	loss 3.4327 (3.5513)	grad_norm 1.2818 (1.4658)	
[2022-01-22 03:38:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][120/1251]	eta 0:44:26 lr 0.000546	time 3.1846 (2.3576)	loss 4.4008 (3.5704)	grad_norm 1.8945 (1.4742)	
[2022-01-22 03:38:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][130/1251]	eta 0:43:46 lr 0.000546	time 1.4641 (2.3427)	loss 3.4336 (3.5422)	grad_norm 1.5187 (1.4765)	
[2022-01-22 03:38:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][140/1251]	eta 0:43:18 lr 0.000546	time 1.9807 (2.3388)	loss 3.8939 (3.5321)	grad_norm 1.5870 (1.4808)	
[2022-01-22 03:39:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][150/1251]	eta 0:42:43 lr 0.000546	time 1.5479 (2.3287)	loss 3.2157 (3.5307)	grad_norm 1.3356 (1.4800)	
[2022-01-22 03:39:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][160/1251]	eta 0:42:22 lr 0.000546	time 3.4821 (2.3304)	loss 4.1536 (3.5295)	grad_norm 1.5301 (1.4831)	
[2022-01-22 03:39:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][170/1251]	eta 0:41:42 lr 0.000546	time 2.1807 (2.3150)	loss 2.7485 (3.5365)	grad_norm 1.3487 (1.4814)	
[2022-01-22 03:40:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][180/1251]	eta 0:41:08 lr 0.000546	time 1.9707 (2.3048)	loss 3.3901 (3.5206)	grad_norm 1.4628 (1.4787)	
[2022-01-22 03:40:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][190/1251]	eta 0:40:32 lr 0.000546	time 1.5564 (2.2930)	loss 3.9399 (3.5106)	grad_norm 1.6817 (1.4807)	
[2022-01-22 03:41:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][200/1251]	eta 0:40:01 lr 0.000546	time 2.8802 (2.2849)	loss 4.0795 (3.5292)	grad_norm 1.2370 (1.4776)	
[2022-01-22 03:41:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][210/1251]	eta 0:39:31 lr 0.000546	time 2.4800 (2.2779)	loss 4.1855 (3.5370)	grad_norm 1.2107 (1.4752)	
[2022-01-22 03:41:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][220/1251]	eta 0:39:07 lr 0.000546	time 2.5732 (2.2770)	loss 3.8310 (3.5419)	grad_norm 1.6012 (1.4758)	
[2022-01-22 03:42:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][230/1251]	eta 0:38:41 lr 0.000545	time 1.8910 (2.2739)	loss 3.6890 (3.5393)	grad_norm 1.7445 (1.4746)	
[2022-01-22 03:42:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][240/1251]	eta 0:38:26 lr 0.000545	time 3.1925 (2.2812)	loss 3.0946 (3.5386)	grad_norm 1.2360 (1.4702)	
[2022-01-22 03:42:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][250/1251]	eta 0:37:56 lr 0.000545	time 1.8519 (2.2739)	loss 3.6442 (3.5436)	grad_norm 1.4847 (1.4668)	
[2022-01-22 03:43:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][260/1251]	eta 0:37:24 lr 0.000545	time 1.8943 (2.2649)	loss 3.7967 (3.5500)	grad_norm 1.5779 (1.4684)	
[2022-01-22 03:43:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][270/1251]	eta 0:36:50 lr 0.000545	time 1.9816 (2.2532)	loss 2.7662 (3.5493)	grad_norm 1.4571 (1.4715)	
[2022-01-22 03:43:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][280/1251]	eta 0:36:21 lr 0.000545	time 2.1293 (2.2466)	loss 2.9279 (3.5462)	grad_norm 1.3508 (1.4714)	
[2022-01-22 03:44:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][290/1251]	eta 0:35:56 lr 0.000545	time 1.8620 (2.2439)	loss 3.8549 (3.5510)	grad_norm 1.5873 (1.4728)	
[2022-01-22 03:44:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][300/1251]	eta 0:35:35 lr 0.000545	time 2.1738 (2.2457)	loss 3.6127 (3.5510)	grad_norm 1.3560 (1.4716)	
[2022-01-22 03:45:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][310/1251]	eta 0:35:16 lr 0.000545	time 3.2484 (2.2492)	loss 3.4827 (3.5421)	grad_norm 1.5193 (1.4693)	
[2022-01-22 03:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][320/1251]	eta 0:34:52 lr 0.000545	time 2.1376 (2.2472)	loss 3.2383 (3.5402)	grad_norm 1.4737 (1.4695)	
[2022-01-22 03:45:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][330/1251]	eta 0:34:30 lr 0.000545	time 1.5276 (2.2480)	loss 4.2201 (3.5361)	grad_norm 1.6438 (1.4713)	
[2022-01-22 03:46:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][340/1251]	eta 0:34:02 lr 0.000545	time 1.5171 (2.2417)	loss 3.6303 (3.5367)	grad_norm 1.3958 (1.4684)	
[2022-01-22 03:46:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][350/1251]	eta 0:33:41 lr 0.000545	time 3.2899 (2.2436)	loss 2.7812 (3.5369)	grad_norm 1.7206 (1.4704)	
[2022-01-22 03:46:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][360/1251]	eta 0:33:16 lr 0.000545	time 1.9032 (2.2411)	loss 3.6242 (3.5383)	grad_norm 1.2024 (1.4716)	
[2022-01-22 03:47:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][370/1251]	eta 0:32:50 lr 0.000545	time 2.1430 (2.2361)	loss 2.7276 (3.5380)	grad_norm 1.8268 (1.4763)	
[2022-01-22 03:47:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][380/1251]	eta 0:32:23 lr 0.000545	time 1.8708 (2.2312)	loss 3.7876 (3.5358)	grad_norm 1.4276 (1.4764)	
[2022-01-22 03:47:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][390/1251]	eta 0:32:00 lr 0.000545	time 3.4421 (2.2304)	loss 3.8186 (3.5384)	grad_norm 1.6040 (1.4768)	
[2022-01-22 03:48:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][400/1251]	eta 0:31:37 lr 0.000545	time 1.7833 (2.2296)	loss 3.9044 (3.5373)	grad_norm 1.5286 (1.4785)	
[2022-01-22 03:48:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][410/1251]	eta 0:31:14 lr 0.000545	time 2.4718 (2.2290)	loss 2.7323 (3.5407)	grad_norm 1.5114 (1.4777)	
[2022-01-22 03:49:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][420/1251]	eta 0:30:50 lr 0.000545	time 2.1689 (2.2274)	loss 4.2928 (3.5412)	grad_norm 1.3362 (1.4755)	
[2022-01-22 03:49:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][430/1251]	eta 0:30:33 lr 0.000545	time 3.6656 (2.2328)	loss 3.7104 (3.5395)	grad_norm 1.4578 (1.4738)	
[2022-01-22 03:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][440/1251]	eta 0:30:12 lr 0.000545	time 1.9504 (2.2352)	loss 3.2916 (3.5385)	grad_norm 1.3282 (1.4731)	
[2022-01-22 03:50:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][450/1251]	eta 0:29:49 lr 0.000545	time 2.3328 (2.2339)	loss 2.9536 (3.5311)	grad_norm 1.1671 (1.4725)	
[2022-01-22 03:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][460/1251]	eta 0:29:22 lr 0.000545	time 2.2641 (2.2287)	loss 3.6879 (3.5329)	grad_norm 1.4319 (1.4706)	
[2022-01-22 03:50:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][470/1251]	eta 0:28:57 lr 0.000544	time 3.0365 (2.2253)	loss 4.4666 (3.5381)	grad_norm 1.3638 (1.4711)	
[2022-01-22 03:51:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][480/1251]	eta 0:28:33 lr 0.000544	time 2.1337 (2.2221)	loss 3.5256 (3.5412)	grad_norm 1.4331 (1.4708)	
[2022-01-22 03:51:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][490/1251]	eta 0:28:09 lr 0.000544	time 1.7207 (2.2197)	loss 3.1381 (3.5413)	grad_norm 1.4973 (1.4705)	
[2022-01-22 03:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][500/1251]	eta 0:27:46 lr 0.000544	time 2.5142 (2.2196)	loss 3.3319 (3.5424)	grad_norm 1.3786 (1.4699)	
[2022-01-22 03:52:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][510/1251]	eta 0:27:26 lr 0.000544	time 2.4728 (2.2215)	loss 3.8132 (3.5389)	grad_norm 1.2882 (1.4684)	
[2022-01-22 03:52:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][520/1251]	eta 0:27:04 lr 0.000544	time 2.1450 (2.2219)	loss 3.6443 (3.5378)	grad_norm 1.2959 (1.4679)	
[2022-01-22 03:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][530/1251]	eta 0:26:40 lr 0.000544	time 1.8963 (2.2204)	loss 3.7698 (3.5357)	grad_norm 1.4465 (1.4682)	
[2022-01-22 03:53:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][540/1251]	eta 0:26:17 lr 0.000544	time 1.9617 (2.2182)	loss 3.4724 (3.5309)	grad_norm 1.4244 (1.4670)	
[2022-01-22 03:53:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][550/1251]	eta 0:25:52 lr 0.000544	time 1.9877 (2.2148)	loss 3.6902 (3.5356)	grad_norm 1.2528 (1.4663)	
[2022-01-22 03:54:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][560/1251]	eta 0:25:29 lr 0.000544	time 1.8576 (2.2132)	loss 4.1380 (3.5370)	grad_norm 1.4811 (1.4666)	
[2022-01-22 03:54:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][570/1251]	eta 0:25:06 lr 0.000544	time 1.8484 (2.2120)	loss 3.3508 (3.5376)	grad_norm 1.8457 (1.4684)	
[2022-01-22 03:54:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][580/1251]	eta 0:24:42 lr 0.000544	time 2.3469 (2.2101)	loss 3.9306 (3.5449)	grad_norm 1.3496 (1.4693)	
[2022-01-22 03:55:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][590/1251]	eta 0:24:21 lr 0.000544	time 2.0645 (2.2114)	loss 2.4884 (3.5420)	grad_norm 1.3573 (1.4692)	
[2022-01-22 03:55:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][600/1251]	eta 0:24:00 lr 0.000544	time 1.9788 (2.2128)	loss 4.1194 (3.5408)	grad_norm 1.4538 (1.4699)	
[2022-01-22 03:55:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][610/1251]	eta 0:23:39 lr 0.000544	time 2.3092 (2.2138)	loss 3.5160 (3.5436)	grad_norm 1.4886 (1.4698)	
[2022-01-22 03:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][620/1251]	eta 0:23:16 lr 0.000544	time 2.2146 (2.2136)	loss 3.5677 (3.5443)	grad_norm 1.4324 (1.4686)	
[2022-01-22 03:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][630/1251]	eta 0:22:55 lr 0.000544	time 2.7969 (2.2146)	loss 2.8600 (3.5436)	grad_norm 1.7217 (1.4684)	
[2022-01-22 03:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][640/1251]	eta 0:22:31 lr 0.000544	time 1.8909 (2.2120)	loss 2.6120 (3.5454)	grad_norm 1.3048 (1.4665)	
[2022-01-22 03:57:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][650/1251]	eta 0:22:08 lr 0.000544	time 1.6815 (2.2106)	loss 4.0740 (3.5424)	grad_norm 1.3279 (1.4663)	
[2022-01-22 03:57:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][660/1251]	eta 0:21:45 lr 0.000544	time 2.0356 (2.2094)	loss 3.7576 (3.5423)	grad_norm 1.4077 (1.4653)	
[2022-01-22 03:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][670/1251]	eta 0:21:25 lr 0.000544	time 3.6417 (2.2133)	loss 4.1888 (3.5451)	grad_norm 1.4195 (1.4640)	
[2022-01-22 03:58:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][680/1251]	eta 0:21:03 lr 0.000544	time 2.2040 (2.2136)	loss 2.2926 (3.5448)	grad_norm 1.2386 (1.4628)	
[2022-01-22 03:58:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][690/1251]	eta 0:20:41 lr 0.000544	time 1.6996 (2.2129)	loss 2.2671 (3.5401)	grad_norm 1.3509 (1.4636)	
[2022-01-22 03:59:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][700/1251]	eta 0:20:17 lr 0.000544	time 2.1813 (2.2104)	loss 3.3825 (3.5412)	grad_norm 1.2439 (1.4636)	
[2022-01-22 03:59:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][710/1251]	eta 0:19:56 lr 0.000543	time 2.5744 (2.2113)	loss 4.2277 (3.5419)	grad_norm 1.4460 (1.4640)	
[2022-01-22 03:59:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][720/1251]	eta 0:19:33 lr 0.000543	time 2.5546 (2.2101)	loss 4.0656 (3.5456)	grad_norm 1.3289 (1.4634)	
[2022-01-22 04:00:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][730/1251]	eta 0:19:11 lr 0.000543	time 2.1331 (2.2095)	loss 3.4986 (3.5436)	grad_norm 1.5193 (1.4624)	
[2022-01-22 04:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][740/1251]	eta 0:18:48 lr 0.000543	time 1.8043 (2.2085)	loss 2.4853 (3.5410)	grad_norm 1.6821 (1.4631)	
[2022-01-22 04:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][750/1251]	eta 0:18:27 lr 0.000543	time 3.0349 (2.2105)	loss 3.0196 (3.5432)	grad_norm 1.1784 (1.4630)	
[2022-01-22 04:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][760/1251]	eta 0:18:04 lr 0.000543	time 1.5753 (2.2094)	loss 3.6008 (3.5419)	grad_norm 1.2258 (1.4624)	
[2022-01-22 04:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][770/1251]	eta 0:17:42 lr 0.000543	time 2.4942 (2.2088)	loss 3.5571 (3.5424)	grad_norm 1.5829 (1.4629)	
[2022-01-22 04:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][780/1251]	eta 0:17:19 lr 0.000543	time 1.8219 (2.2071)	loss 4.3046 (3.5434)	grad_norm 1.3799 (1.4629)	
[2022-01-22 04:02:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][790/1251]	eta 0:16:56 lr 0.000543	time 2.1815 (2.2058)	loss 3.7421 (3.5456)	grad_norm 1.2027 (1.4627)	
[2022-01-22 04:02:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][800/1251]	eta 0:16:33 lr 0.000543	time 1.7626 (2.2039)	loss 3.7475 (3.5456)	grad_norm 1.3135 (1.4624)	
[2022-01-22 04:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][810/1251]	eta 0:16:12 lr 0.000543	time 2.4513 (2.2048)	loss 3.4938 (3.5428)	grad_norm 1.5309 (1.4624)	
[2022-01-22 04:03:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][820/1251]	eta 0:15:50 lr 0.000543	time 1.6740 (2.2053)	loss 3.8453 (3.5422)	grad_norm 1.4056 (1.4613)	
[2022-01-22 04:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][830/1251]	eta 0:15:28 lr 0.000543	time 2.5700 (2.2051)	loss 3.6003 (3.5423)	grad_norm 1.4823 (1.4608)	
[2022-01-22 04:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][840/1251]	eta 0:15:06 lr 0.000543	time 1.9586 (2.2047)	loss 3.8533 (3.5429)	grad_norm 1.3078 (1.4604)	
[2022-01-22 04:04:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][850/1251]	eta 0:14:44 lr 0.000543	time 1.9275 (2.2047)	loss 3.6956 (3.5449)	grad_norm 1.5402 (1.4617)	
[2022-01-22 04:05:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][860/1251]	eta 0:14:22 lr 0.000543	time 1.5662 (2.2058)	loss 3.9241 (3.5451)	grad_norm 1.3655 (1.4621)	
[2022-01-22 04:05:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][870/1251]	eta 0:14:00 lr 0.000543	time 2.2368 (2.2055)	loss 4.0423 (3.5497)	grad_norm 1.4045 (1.4617)	
[2022-01-22 04:05:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][880/1251]	eta 0:13:37 lr 0.000543	time 2.6728 (2.2042)	loss 4.1489 (3.5521)	grad_norm 1.3820 (1.4612)	
[2022-01-22 04:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][890/1251]	eta 0:13:15 lr 0.000543	time 2.1006 (2.2045)	loss 2.6043 (3.5537)	grad_norm 1.4151 (1.4611)	
[2022-01-22 04:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][900/1251]	eta 0:12:53 lr 0.000543	time 1.9114 (2.2044)	loss 3.7075 (3.5554)	grad_norm 1.4281 (1.4607)	
[2022-01-22 04:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][910/1251]	eta 0:12:31 lr 0.000543	time 1.8103 (2.2044)	loss 3.9859 (3.5570)	grad_norm 1.5076 (1.4602)	
[2022-01-22 04:07:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][920/1251]	eta 0:12:10 lr 0.000543	time 4.3612 (2.2066)	loss 3.4229 (3.5590)	grad_norm 1.4050 (1.4594)	
[2022-01-22 04:07:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][930/1251]	eta 0:11:48 lr 0.000543	time 2.3568 (2.2085)	loss 3.5990 (3.5607)	grad_norm 1.3926 (1.4580)	
[2022-01-22 04:08:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][940/1251]	eta 0:11:26 lr 0.000543	time 1.8173 (2.2076)	loss 2.9825 (3.5596)	grad_norm 1.6128 (1.4583)	
[2022-01-22 04:08:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][950/1251]	eta 0:11:03 lr 0.000542	time 1.6402 (2.2057)	loss 4.1451 (3.5623)	grad_norm 1.4064 (1.4578)	
[2022-01-22 04:08:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][960/1251]	eta 0:10:41 lr 0.000542	time 2.4866 (2.2035)	loss 3.4125 (3.5645)	grad_norm 1.3178 (1.4582)	
[2022-01-22 04:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][970/1251]	eta 0:10:18 lr 0.000542	time 1.8257 (2.2015)	loss 4.3674 (3.5656)	grad_norm 1.7683 (1.4595)	
[2022-01-22 04:09:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][980/1251]	eta 0:09:56 lr 0.000542	time 2.0818 (2.2008)	loss 3.5560 (3.5665)	grad_norm 1.4592 (1.4601)	
[2022-01-22 04:09:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][990/1251]	eta 0:09:34 lr 0.000542	time 2.2539 (2.2000)	loss 3.9073 (3.5653)	grad_norm 1.3777 (1.4592)	
[2022-01-22 04:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1000/1251]	eta 0:09:12 lr 0.000542	time 2.7603 (2.2021)	loss 3.5893 (3.5637)	grad_norm 1.4780 (1.4592)	
[2022-01-22 04:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1010/1251]	eta 0:08:50 lr 0.000542	time 1.6126 (2.2018)	loss 3.7030 (3.5658)	grad_norm 1.4666 (1.4587)	
[2022-01-22 04:10:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1020/1251]	eta 0:08:28 lr 0.000542	time 2.2060 (2.2017)	loss 3.8813 (3.5665)	grad_norm 1.3847 (1.4588)	
[2022-01-22 04:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1030/1251]	eta 0:08:06 lr 0.000542	time 1.9500 (2.2027)	loss 3.5547 (3.5645)	grad_norm 1.6439 (1.4595)	
[2022-01-22 04:11:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1040/1251]	eta 0:07:44 lr 0.000542	time 2.4874 (2.2019)	loss 2.9903 (3.5653)	grad_norm 1.3674 (1.4593)	
[2022-01-22 04:11:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1050/1251]	eta 0:07:22 lr 0.000542	time 2.0176 (2.2021)	loss 2.9866 (3.5645)	grad_norm 1.5318 (1.4591)	
[2022-01-22 04:12:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1060/1251]	eta 0:07:00 lr 0.000542	time 2.3900 (2.2013)	loss 4.0202 (3.5645)	grad_norm 1.6985 (1.4597)	
[2022-01-22 04:12:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1070/1251]	eta 0:06:38 lr 0.000542	time 2.0286 (2.2003)	loss 2.7548 (3.5650)	grad_norm 1.3814 (1.4594)	
[2022-01-22 04:13:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1080/1251]	eta 0:06:16 lr 0.000542	time 2.8174 (2.2001)	loss 2.3542 (3.5643)	grad_norm 1.3565 (1.4590)	
[2022-01-22 04:13:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1090/1251]	eta 0:05:54 lr 0.000542	time 2.8800 (2.2010)	loss 3.8364 (3.5635)	grad_norm 1.3358 (1.4588)	
[2022-01-22 04:13:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1100/1251]	eta 0:05:32 lr 0.000542	time 2.0966 (2.2016)	loss 3.9295 (3.5645)	grad_norm 1.4038 (1.4589)	
[2022-01-22 04:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1110/1251]	eta 0:05:10 lr 0.000542	time 2.2318 (2.2024)	loss 3.7200 (3.5633)	grad_norm 1.5233 (1.4589)	
[2022-01-22 04:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1120/1251]	eta 0:04:48 lr 0.000542	time 1.9329 (2.2027)	loss 3.6067 (3.5600)	grad_norm 1.5539 (1.4599)	
[2022-01-22 04:14:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1130/1251]	eta 0:04:26 lr 0.000542	time 2.7288 (2.2022)	loss 2.8787 (3.5592)	grad_norm 1.5942 (1.4611)	
[2022-01-22 04:15:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1140/1251]	eta 0:04:04 lr 0.000542	time 1.7634 (2.1999)	loss 3.7327 (3.5589)	grad_norm 1.4114 (1.4611)	
[2022-01-22 04:15:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1150/1251]	eta 0:03:42 lr 0.000542	time 2.5017 (2.1981)	loss 3.6384 (3.5594)	grad_norm 1.5564 (1.4615)	
[2022-01-22 04:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1160/1251]	eta 0:03:19 lr 0.000542	time 2.0139 (2.1976)	loss 3.4406 (3.5593)	grad_norm 1.2586 (1.4620)	
[2022-01-22 04:16:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1170/1251]	eta 0:02:58 lr 0.000542	time 2.2697 (2.1994)	loss 3.4285 (3.5607)	grad_norm 1.4661 (1.4620)	
[2022-01-22 04:16:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1180/1251]	eta 0:02:36 lr 0.000542	time 2.4973 (2.1994)	loss 3.1037 (3.5616)	grad_norm 1.5663 (1.4623)	
[2022-01-22 04:17:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1190/1251]	eta 0:02:14 lr 0.000542	time 1.8793 (2.1997)	loss 3.8165 (3.5644)	grad_norm 1.5626 (1.4625)	
[2022-01-22 04:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1200/1251]	eta 0:01:52 lr 0.000541	time 2.8206 (2.1994)	loss 2.2776 (3.5611)	grad_norm 1.5851 (1.4623)	
[2022-01-22 04:17:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1210/1251]	eta 0:01:30 lr 0.000541	time 2.4917 (2.1996)	loss 3.3774 (3.5613)	grad_norm 1.5246 (1.4629)	
[2022-01-22 04:18:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1220/1251]	eta 0:01:08 lr 0.000541	time 2.8290 (2.2003)	loss 3.3074 (3.5614)	grad_norm 1.6539 (1.4635)	
[2022-01-22 04:18:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1230/1251]	eta 0:00:46 lr 0.000541	time 1.7518 (2.1999)	loss 3.9519 (3.5611)	grad_norm 1.2809 (1.4633)	
[2022-01-22 04:18:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1240/1251]	eta 0:00:24 lr 0.000541	time 2.2441 (2.1985)	loss 3.7823 (3.5611)	grad_norm 1.6961 (1.4636)	
[2022-01-22 04:19:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [142/300][1250/1251]	eta 0:00:02 lr 0.000541	time 1.1782 (2.1926)	loss 3.9586 (3.5620)	grad_norm 1.2772 (1.4629)	
[2022-01-22 04:19:06 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 142 training takes 0:45:43
[2022-01-22 04:19:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.348 (18.348)	Loss 1.0572 (1.0572)	Acc@1 75.098 (75.098)	Acc@5 92.285 (92.285)	
[2022-01-22 04:19:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.319 (3.388)	Loss 1.0653 (1.0332)	Acc@1 74.219 (75.888)	Acc@5 92.578 (93.253)	
[2022-01-22 04:20:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 2.065 (2.610)	Loss 1.0221 (1.0379)	Acc@1 76.270 (75.702)	Acc@5 93.262 (93.150)	
[2022-01-22 04:20:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.989 (2.270)	Loss 1.0328 (1.0391)	Acc@1 75.391 (75.545)	Acc@5 93.164 (93.088)	
[2022-01-22 04:20:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.811 (2.136)	Loss 1.0452 (1.0374)	Acc@1 75.000 (75.593)	Acc@5 92.871 (93.054)	
[2022-01-22 04:20:41 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.616 Acc@5 93.090
[2022-01-22 04:20:41 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.6%
[2022-01-22 04:20:41 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.63%
[2022-01-22 04:21:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][0/1251]	eta 7:29:00 lr 0.000541	time 21.5349 (21.5349)	loss 2.9915 (2.9915)	grad_norm 1.3497 (1.3497)	
[2022-01-22 04:21:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][10/1251]	eta 1:25:14 lr 0.000541	time 2.5327 (4.1210)	loss 4.1917 (3.6324)	grad_norm 1.2954 (1.3757)	
[2022-01-22 04:21:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][20/1251]	eta 1:05:36 lr 0.000541	time 1.9102 (3.1976)	loss 2.9011 (3.6427)	grad_norm 1.2475 (1.3900)	
[2022-01-22 04:22:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][30/1251]	eta 0:58:56 lr 0.000541	time 1.8889 (2.8962)	loss 2.3852 (3.6023)	grad_norm 1.8333 (1.4036)	
[2022-01-22 04:22:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][40/1251]	eta 0:55:27 lr 0.000541	time 3.1255 (2.7473)	loss 3.7139 (3.5301)	grad_norm 1.4442 (1.4218)	
[2022-01-22 04:22:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][50/1251]	eta 0:52:44 lr 0.000541	time 1.5892 (2.6347)	loss 3.6162 (3.5691)	grad_norm 1.5659 (1.4234)	
[2022-01-22 04:23:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][60/1251]	eta 0:50:57 lr 0.000541	time 2.1848 (2.5668)	loss 3.8288 (3.5818)	grad_norm 1.5557 (1.4445)	
[2022-01-22 04:23:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][70/1251]	eta 0:49:35 lr 0.000541	time 1.5881 (2.5196)	loss 3.6656 (3.5811)	grad_norm 1.5398 (1.4581)	
[2022-01-22 04:24:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][80/1251]	eta 0:48:20 lr 0.000541	time 2.9991 (2.4772)	loss 3.3189 (3.5899)	grad_norm 1.3734 (1.4606)	
[2022-01-22 04:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][90/1251]	eta 0:47:09 lr 0.000541	time 1.9275 (2.4371)	loss 4.0428 (3.5823)	grad_norm 1.3249 (1.4590)	
[2022-01-22 04:24:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][100/1251]	eta 0:45:53 lr 0.000541	time 1.8654 (2.3926)	loss 3.7281 (3.5850)	grad_norm 1.4627 (1.4772)	
[2022-01-22 04:25:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][110/1251]	eta 0:45:04 lr 0.000541	time 2.1730 (2.3703)	loss 3.2534 (3.5666)	grad_norm 1.5942 (1.4797)	
[2022-01-22 04:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][120/1251]	eta 0:44:22 lr 0.000541	time 2.3254 (2.3545)	loss 3.6794 (3.5751)	grad_norm 1.2513 (1.4786)	
[2022-01-22 04:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][130/1251]	eta 0:43:51 lr 0.000541	time 1.5870 (2.3478)	loss 3.8879 (3.5644)	grad_norm 1.5160 (1.4734)	
[2022-01-22 04:26:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][140/1251]	eta 0:43:20 lr 0.000541	time 2.3717 (2.3409)	loss 2.8884 (3.5520)	grad_norm 1.6867 (1.4723)	
[2022-01-22 04:26:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][150/1251]	eta 0:42:48 lr 0.000541	time 2.8245 (2.3331)	loss 3.4495 (3.5547)	grad_norm 1.3152 (1.4730)	
[2022-01-22 04:26:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][160/1251]	eta 0:42:09 lr 0.000541	time 2.1628 (2.3183)	loss 4.1718 (3.5696)	grad_norm 1.2968 (1.4712)	
[2022-01-22 04:27:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][170/1251]	eta 0:41:33 lr 0.000541	time 1.8187 (2.3064)	loss 3.0893 (3.5656)	grad_norm 1.8523 (1.4705)	
[2022-01-22 04:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][180/1251]	eta 0:41:02 lr 0.000541	time 1.9021 (2.2992)	loss 3.0172 (3.5726)	grad_norm 1.8708 (1.4705)	
[2022-01-22 04:27:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][190/1251]	eta 0:40:29 lr 0.000540	time 2.2489 (2.2898)	loss 4.2393 (3.5845)	grad_norm 1.5037 (1.4730)	
[2022-01-22 04:28:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][200/1251]	eta 0:39:57 lr 0.000540	time 2.5741 (2.2812)	loss 2.7695 (3.5798)	grad_norm 1.3146 (1.4709)	
[2022-01-22 04:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][210/1251]	eta 0:39:29 lr 0.000540	time 2.0885 (2.2763)	loss 3.8114 (3.5767)	grad_norm 1.6322 (1.4701)	
[2022-01-22 04:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][220/1251]	eta 0:38:59 lr 0.000540	time 2.1241 (2.2688)	loss 4.2874 (3.5737)	grad_norm 2.3679 (1.4722)	
[2022-01-22 04:29:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][230/1251]	eta 0:38:30 lr 0.000540	time 2.2480 (2.2628)	loss 3.5937 (3.5751)	grad_norm 1.3937 (1.4724)	
[2022-01-22 04:29:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][240/1251]	eta 0:38:04 lr 0.000540	time 2.3860 (2.2595)	loss 2.8496 (3.5705)	grad_norm 1.2644 (1.4700)	
[2022-01-22 04:30:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][250/1251]	eta 0:37:33 lr 0.000540	time 2.0705 (2.2508)	loss 3.9996 (3.5784)	grad_norm 1.4926 (1.4689)	
[2022-01-22 04:30:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][260/1251]	eta 0:37:13 lr 0.000540	time 2.4117 (2.2534)	loss 2.7624 (3.5674)	grad_norm 1.3158 (1.4670)	
[2022-01-22 04:30:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][270/1251]	eta 0:36:46 lr 0.000540	time 3.0946 (2.2494)	loss 3.8619 (3.5614)	grad_norm 1.4284 (1.4658)	
[2022-01-22 04:31:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][280/1251]	eta 0:36:23 lr 0.000540	time 2.5947 (2.2491)	loss 2.8669 (3.5565)	grad_norm 1.5091 (1.4659)	
[2022-01-22 04:31:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][290/1251]	eta 0:36:08 lr 0.000540	time 2.1529 (2.2565)	loss 3.7529 (3.5558)	grad_norm 1.7699 (1.4704)	
[2022-01-22 04:31:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][300/1251]	eta 0:35:44 lr 0.000540	time 2.1677 (2.2546)	loss 3.7154 (3.5532)	grad_norm 1.5266 (1.4717)	
[2022-01-22 04:32:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][310/1251]	eta 0:35:20 lr 0.000540	time 3.1364 (2.2534)	loss 3.4867 (3.5569)	grad_norm 1.7970 (1.4691)	
[2022-01-22 04:32:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][320/1251]	eta 0:34:55 lr 0.000540	time 2.4176 (2.2504)	loss 4.3616 (3.5633)	grad_norm 1.3830 (1.4699)	
[2022-01-22 04:33:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][330/1251]	eta 0:34:30 lr 0.000540	time 2.5221 (2.2476)	loss 3.9165 (3.5617)	grad_norm 1.4325 (1.4727)	
[2022-01-22 04:33:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][340/1251]	eta 0:34:01 lr 0.000540	time 1.8811 (2.2414)	loss 3.5818 (3.5615)	grad_norm 1.3547 (1.4717)	
[2022-01-22 04:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][350/1251]	eta 0:33:35 lr 0.000540	time 2.7484 (2.2375)	loss 2.4650 (3.5491)	grad_norm 1.4434 (1.4720)	
[2022-01-22 04:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][360/1251]	eta 0:33:08 lr 0.000540	time 1.7980 (2.2312)	loss 4.1105 (3.5403)	grad_norm 1.4726 (1.4724)	
[2022-01-22 04:34:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][370/1251]	eta 0:32:44 lr 0.000540	time 1.7992 (2.2297)	loss 3.7033 (3.5414)	grad_norm 1.2967 (1.4715)	
[2022-01-22 04:34:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][380/1251]	eta 0:32:21 lr 0.000540	time 2.5644 (2.2293)	loss 3.5946 (3.5419)	grad_norm 1.7016 (1.4747)	
[2022-01-22 04:35:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][390/1251]	eta 0:32:00 lr 0.000540	time 2.3887 (2.2304)	loss 3.9520 (3.5409)	grad_norm 1.6472 (1.4757)	
[2022-01-22 04:35:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][400/1251]	eta 0:31:36 lr 0.000540	time 1.5857 (2.2291)	loss 4.2808 (3.5456)	grad_norm 1.3378 (1.4754)	
[2022-01-22 04:35:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][410/1251]	eta 0:31:14 lr 0.000540	time 2.5867 (2.2287)	loss 3.7948 (3.5465)	grad_norm 1.6298 (1.4759)	
[2022-01-22 04:36:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][420/1251]	eta 0:30:48 lr 0.000540	time 1.5984 (2.2247)	loss 4.0922 (3.5481)	grad_norm 1.4593 (1.4746)	
[2022-01-22 04:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][430/1251]	eta 0:30:24 lr 0.000539	time 2.0461 (2.2226)	loss 3.4983 (3.5417)	grad_norm 1.4455 (1.4724)	
[2022-01-22 04:37:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][440/1251]	eta 0:30:02 lr 0.000539	time 1.9265 (2.2230)	loss 2.7829 (3.5407)	grad_norm 1.5799 (1.4713)	
[2022-01-22 04:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][450/1251]	eta 0:29:40 lr 0.000539	time 2.4567 (2.2231)	loss 4.1106 (3.5399)	grad_norm 1.6112 (1.4711)	
[2022-01-22 04:37:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][460/1251]	eta 0:29:19 lr 0.000539	time 1.6131 (2.2240)	loss 4.3931 (3.5456)	grad_norm 1.5923 (1.4706)	
[2022-01-22 04:38:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][470/1251]	eta 0:28:56 lr 0.000539	time 2.1780 (2.2228)	loss 2.4073 (3.5413)	grad_norm 1.4433 (1.4713)	
[2022-01-22 04:38:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][480/1251]	eta 0:28:32 lr 0.000539	time 1.9763 (2.2217)	loss 3.0449 (3.5437)	grad_norm 1.6399 (1.4705)	
[2022-01-22 04:38:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][490/1251]	eta 0:28:09 lr 0.000539	time 2.2585 (2.2206)	loss 3.6685 (3.5377)	grad_norm 1.3507 (1.4697)	
[2022-01-22 04:39:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][500/1251]	eta 0:27:50 lr 0.000539	time 1.8915 (2.2246)	loss 3.8131 (3.5370)	grad_norm 1.5875 (1.4703)	
[2022-01-22 04:39:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][510/1251]	eta 0:27:28 lr 0.000539	time 2.5301 (2.2245)	loss 3.1365 (3.5373)	grad_norm 1.2975 (1.4699)	
[2022-01-22 04:39:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][520/1251]	eta 0:27:05 lr 0.000539	time 1.9326 (2.2231)	loss 3.4881 (3.5383)	grad_norm 1.4875 (1.4689)	
[2022-01-22 04:40:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][530/1251]	eta 0:26:41 lr 0.000539	time 1.9567 (2.2207)	loss 3.7267 (3.5406)	grad_norm 1.4514 (1.4697)	
[2022-01-22 04:40:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][540/1251]	eta 0:26:18 lr 0.000539	time 1.8826 (2.2205)	loss 3.7069 (3.5390)	grad_norm 1.3359 (1.4728)	
[2022-01-22 04:41:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][550/1251]	eta 0:25:54 lr 0.000539	time 2.7837 (2.2178)	loss 4.0364 (3.5448)	grad_norm 1.2375 (1.4716)	
[2022-01-22 04:41:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][560/1251]	eta 0:25:31 lr 0.000539	time 2.2488 (2.2164)	loss 4.2374 (3.5476)	grad_norm 1.7197 (1.4726)	
[2022-01-22 04:41:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][570/1251]	eta 0:25:08 lr 0.000539	time 1.8384 (2.2145)	loss 4.0630 (3.5544)	grad_norm 1.6449 (1.4731)	
[2022-01-22 04:42:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][580/1251]	eta 0:24:48 lr 0.000539	time 2.2180 (2.2179)	loss 3.9532 (3.5519)	grad_norm 1.2092 (1.4731)	
[2022-01-22 04:42:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][590/1251]	eta 0:24:27 lr 0.000539	time 3.0403 (2.2194)	loss 3.6899 (3.5525)	grad_norm 1.4593 (1.4737)	
[2022-01-22 04:42:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][600/1251]	eta 0:24:05 lr 0.000539	time 2.5521 (2.2210)	loss 3.8748 (3.5494)	grad_norm 1.3035 (1.4737)	
[2022-01-22 04:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][610/1251]	eta 0:23:41 lr 0.000539	time 1.9192 (2.2177)	loss 3.8542 (3.5494)	grad_norm 1.2872 (1.4726)	
[2022-01-22 04:43:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][620/1251]	eta 0:23:19 lr 0.000539	time 1.5233 (2.2171)	loss 2.9694 (3.5463)	grad_norm 1.3274 (1.4706)	
[2022-01-22 04:43:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][630/1251]	eta 0:22:56 lr 0.000539	time 2.8060 (2.2163)	loss 3.8450 (3.5433)	grad_norm 1.6835 (1.4701)	
[2022-01-22 04:44:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][640/1251]	eta 0:22:32 lr 0.000539	time 1.6558 (2.2139)	loss 2.6766 (3.5410)	grad_norm 1.3400 (1.4689)	
[2022-01-22 04:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][650/1251]	eta 0:22:10 lr 0.000539	time 2.1159 (2.2138)	loss 4.2041 (3.5386)	grad_norm 1.2882 (1.4677)	
[2022-01-22 04:45:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][660/1251]	eta 0:21:47 lr 0.000539	time 2.1785 (2.2124)	loss 4.1610 (3.5426)	grad_norm 1.3161 (1.4689)	
[2022-01-22 04:45:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][670/1251]	eta 0:21:25 lr 0.000538	time 3.3432 (2.2128)	loss 3.8654 (3.5414)	grad_norm 1.4889 (1.4688)	
[2022-01-22 04:45:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][680/1251]	eta 0:21:03 lr 0.000538	time 1.8350 (2.2127)	loss 3.6112 (3.5413)	grad_norm 1.3619 (1.4692)	
[2022-01-22 04:46:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][690/1251]	eta 0:20:42 lr 0.000538	time 2.1618 (2.2141)	loss 3.1916 (3.5389)	grad_norm 1.4338 (1.4688)	
[2022-01-22 04:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][700/1251]	eta 0:20:21 lr 0.000538	time 2.1971 (2.2161)	loss 4.0352 (3.5392)	grad_norm 1.5138 (1.4680)	
[2022-01-22 04:46:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][710/1251]	eta 0:19:58 lr 0.000538	time 3.1817 (2.2162)	loss 3.4617 (3.5363)	grad_norm 1.4512 (1.4681)	
[2022-01-22 04:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][720/1251]	eta 0:19:34 lr 0.000538	time 1.9453 (2.2124)	loss 3.0061 (3.5323)	grad_norm 1.3857 (1.4673)	
[2022-01-22 04:47:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][730/1251]	eta 0:19:10 lr 0.000538	time 1.8144 (2.2087)	loss 3.9244 (3.5331)	grad_norm 1.3549 (1.4675)	
[2022-01-22 04:47:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][740/1251]	eta 0:18:47 lr 0.000538	time 1.9333 (2.2057)	loss 3.6913 (3.5347)	grad_norm 1.4733 (1.4677)	
[2022-01-22 04:48:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][750/1251]	eta 0:18:23 lr 0.000538	time 2.4887 (2.2035)	loss 2.5369 (3.5324)	grad_norm 1.2616 (1.4684)	
[2022-01-22 04:48:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][760/1251]	eta 0:18:01 lr 0.000538	time 2.2192 (2.2019)	loss 4.2541 (3.5321)	grad_norm 1.7859 (1.4686)	
[2022-01-22 04:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][770/1251]	eta 0:17:39 lr 0.000538	time 2.4510 (2.2027)	loss 3.4908 (3.5343)	grad_norm 1.5116 (1.4684)	
[2022-01-22 04:49:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][780/1251]	eta 0:17:18 lr 0.000538	time 1.8485 (2.2044)	loss 2.6822 (3.5300)	grad_norm 1.3509 (1.4674)	
[2022-01-22 04:49:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][790/1251]	eta 0:16:55 lr 0.000538	time 2.0830 (2.2028)	loss 3.5788 (3.5286)	grad_norm 1.2855 (1.4673)	
[2022-01-22 04:50:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][800/1251]	eta 0:16:33 lr 0.000538	time 2.8798 (2.2022)	loss 4.0441 (3.5303)	grad_norm 1.2326 (1.4669)	
[2022-01-22 04:50:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][810/1251]	eta 0:16:10 lr 0.000538	time 1.7977 (2.2010)	loss 3.9702 (3.5321)	grad_norm 1.3521 (1.4685)	
[2022-01-22 04:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][820/1251]	eta 0:15:49 lr 0.000538	time 2.4972 (2.2022)	loss 4.1306 (3.5341)	grad_norm 1.4257 (1.4690)	
[2022-01-22 04:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][830/1251]	eta 0:15:27 lr 0.000538	time 1.9226 (2.2023)	loss 3.8554 (3.5368)	grad_norm 1.3941 (1.4686)	
[2022-01-22 04:51:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][840/1251]	eta 0:15:05 lr 0.000538	time 2.0057 (2.2026)	loss 3.2853 (3.5369)	grad_norm 1.3122 (1.4691)	
[2022-01-22 04:51:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][850/1251]	eta 0:14:44 lr 0.000538	time 2.4852 (2.2045)	loss 3.2056 (3.5376)	grad_norm 1.7632 (1.4699)	
[2022-01-22 04:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][860/1251]	eta 0:14:21 lr 0.000538	time 2.2694 (2.2041)	loss 3.7612 (3.5378)	grad_norm 1.2651 (1.4699)	
[2022-01-22 04:52:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][870/1251]	eta 0:13:59 lr 0.000538	time 2.1871 (2.2044)	loss 3.2436 (3.5369)	grad_norm 1.4192 (1.4698)	
[2022-01-22 04:53:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][880/1251]	eta 0:13:38 lr 0.000538	time 1.8648 (2.2053)	loss 4.2501 (3.5377)	grad_norm 1.4871 (1.4700)	
[2022-01-22 04:53:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][890/1251]	eta 0:13:16 lr 0.000538	time 2.7462 (2.2055)	loss 2.9633 (3.5385)	grad_norm 1.2826 (1.4697)	
[2022-01-22 04:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][900/1251]	eta 0:12:53 lr 0.000538	time 1.9117 (2.2038)	loss 4.1136 (3.5366)	grad_norm 1.5635 (1.4697)	
[2022-01-22 04:54:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][910/1251]	eta 0:12:31 lr 0.000537	time 2.6939 (2.2031)	loss 4.2872 (3.5375)	grad_norm 1.5268 (1.4693)	
[2022-01-22 04:54:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][920/1251]	eta 0:12:08 lr 0.000537	time 1.5610 (2.2012)	loss 3.3365 (3.5363)	grad_norm 1.4145 (1.4691)	
[2022-01-22 04:54:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][930/1251]	eta 0:11:46 lr 0.000537	time 1.9240 (2.1997)	loss 2.9443 (3.5390)	grad_norm 1.5136 (1.4685)	
[2022-01-22 04:55:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][940/1251]	eta 0:11:24 lr 0.000537	time 2.4896 (2.1999)	loss 3.7808 (3.5394)	grad_norm 1.3195 (1.4691)	
[2022-01-22 04:55:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][950/1251]	eta 0:11:02 lr 0.000537	time 2.8533 (2.2000)	loss 2.2839 (3.5392)	grad_norm 1.4518 (1.4697)	
[2022-01-22 04:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][960/1251]	eta 0:10:40 lr 0.000537	time 2.3433 (2.2008)	loss 4.1900 (3.5409)	grad_norm 1.5062 (1.4703)	
[2022-01-22 04:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][970/1251]	eta 0:10:18 lr 0.000537	time 1.8967 (2.2003)	loss 3.6122 (3.5377)	grad_norm 1.6256 (1.4712)	
[2022-01-22 04:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][980/1251]	eta 0:09:56 lr 0.000537	time 1.8710 (2.2005)	loss 2.8417 (3.5373)	grad_norm 1.3454 (1.4706)	
[2022-01-22 04:57:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][990/1251]	eta 0:09:34 lr 0.000537	time 2.4762 (2.2013)	loss 3.1785 (3.5364)	grad_norm 1.6429 (1.4712)	
[2022-01-22 04:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1000/1251]	eta 0:09:12 lr 0.000537	time 1.5186 (2.2016)	loss 2.2231 (3.5352)	grad_norm 1.3954 (1.4716)	
[2022-01-22 04:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1010/1251]	eta 0:08:50 lr 0.000537	time 1.8557 (2.2012)	loss 4.1229 (3.5350)	grad_norm 1.6316 (1.4718)	
[2022-01-22 04:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1020/1251]	eta 0:08:28 lr 0.000537	time 1.9016 (2.2013)	loss 3.6041 (3.5349)	grad_norm 1.3057 (1.4710)	
[2022-01-22 04:58:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1030/1251]	eta 0:08:06 lr 0.000537	time 2.5170 (2.2014)	loss 4.1746 (3.5362)	grad_norm 1.8754 (1.4715)	
[2022-01-22 04:58:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1040/1251]	eta 0:07:44 lr 0.000537	time 1.7352 (2.2014)	loss 3.5624 (3.5329)	grad_norm 1.6497 (1.4710)	
[2022-01-22 04:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1050/1251]	eta 0:07:22 lr 0.000537	time 1.5445 (2.2007)	loss 2.9238 (3.5306)	grad_norm 1.3970 (1.4706)	
[2022-01-22 04:59:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1060/1251]	eta 0:07:00 lr 0.000537	time 1.7702 (2.2013)	loss 3.4257 (3.5310)	grad_norm 1.6214 (1.4703)	
[2022-01-22 04:59:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1070/1251]	eta 0:06:38 lr 0.000537	time 1.9356 (2.2006)	loss 4.4178 (3.5326)	grad_norm 1.4034 (1.4693)	
[2022-01-22 05:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1080/1251]	eta 0:06:16 lr 0.000537	time 1.9051 (2.2011)	loss 3.0939 (3.5318)	grad_norm 1.4773 (1.4687)	
[2022-01-22 05:00:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1090/1251]	eta 0:05:54 lr 0.000537	time 1.6610 (2.2006)	loss 4.0667 (3.5337)	grad_norm 1.3758 (1.4678)	
[2022-01-22 05:01:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1100/1251]	eta 0:05:32 lr 0.000537	time 1.9336 (2.2007)	loss 3.9664 (3.5353)	grad_norm 1.7235 (1.4678)	
[2022-01-22 05:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1110/1251]	eta 0:05:10 lr 0.000537	time 1.6342 (2.1994)	loss 3.8991 (3.5372)	grad_norm 1.6682 (1.4684)	
[2022-01-22 05:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1120/1251]	eta 0:04:47 lr 0.000537	time 1.9338 (2.1984)	loss 2.8874 (3.5349)	grad_norm 1.3991 (1.4682)	
[2022-01-22 05:02:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1130/1251]	eta 0:04:25 lr 0.000537	time 1.7163 (2.1975)	loss 3.7676 (3.5365)	grad_norm 1.3339 (1.4683)	
[2022-01-22 05:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1140/1251]	eta 0:04:04 lr 0.000537	time 2.2372 (2.1985)	loss 3.5541 (3.5385)	grad_norm 1.6089 (1.4680)	
[2022-01-22 05:02:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1150/1251]	eta 0:03:42 lr 0.000536	time 2.2166 (2.1991)	loss 2.9373 (3.5381)	grad_norm 1.3781 (1.4682)	
[2022-01-22 05:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1160/1251]	eta 0:03:20 lr 0.000536	time 2.2421 (2.1990)	loss 2.8044 (3.5379)	grad_norm 1.4985 (1.4687)	
[2022-01-22 05:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1170/1251]	eta 0:02:58 lr 0.000536	time 1.9255 (2.1983)	loss 4.1306 (3.5395)	grad_norm 1.5138 (1.4686)	
[2022-01-22 05:03:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1180/1251]	eta 0:02:36 lr 0.000536	time 1.9241 (2.1985)	loss 3.9221 (3.5407)	grad_norm 1.3090 (1.4684)	
[2022-01-22 05:04:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1190/1251]	eta 0:02:14 lr 0.000536	time 1.8323 (2.1982)	loss 3.6169 (3.5419)	grad_norm 1.3950 (1.4678)	
[2022-01-22 05:04:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1200/1251]	eta 0:01:52 lr 0.000536	time 2.2532 (2.1979)	loss 4.0480 (3.5430)	grad_norm 1.5486 (1.4672)	
[2022-01-22 05:05:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1210/1251]	eta 0:01:30 lr 0.000536	time 1.6195 (2.1982)	loss 3.7281 (3.5424)	grad_norm 1.4918 (1.4666)	
[2022-01-22 05:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1220/1251]	eta 0:01:08 lr 0.000536	time 2.4260 (2.1993)	loss 3.7732 (3.5444)	grad_norm 1.3519 (1.4659)	
[2022-01-22 05:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1230/1251]	eta 0:00:46 lr 0.000536	time 1.8483 (2.1985)	loss 4.1010 (3.5440)	grad_norm 1.2575 (1.4662)	
[2022-01-22 05:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1240/1251]	eta 0:00:24 lr 0.000536	time 1.4224 (2.1966)	loss 3.4031 (3.5453)	grad_norm 1.8639 (1.4666)	
[2022-01-22 05:06:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [143/300][1250/1251]	eta 0:00:02 lr 0.000536	time 1.1829 (2.1908)	loss 3.2089 (3.5454)	grad_norm 1.5416 (1.4667)	
[2022-01-22 05:06:22 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 143 training takes 0:45:41
[2022-01-22 05:06:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.253 (18.253)	Loss 1.0716 (1.0716)	Acc@1 73.047 (73.047)	Acc@5 93.652 (93.652)	
[2022-01-22 05:07:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.674 (3.418)	Loss 1.0801 (1.0509)	Acc@1 73.828 (75.320)	Acc@5 93.750 (92.907)	
[2022-01-22 05:07:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.614 (2.466)	Loss 1.1317 (1.0426)	Acc@1 73.340 (75.335)	Acc@5 91.113 (92.927)	
[2022-01-22 05:07:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.623 (2.184)	Loss 1.0447 (1.0475)	Acc@1 75.000 (75.324)	Acc@5 93.457 (92.915)	
[2022-01-22 05:07:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.309 (2.133)	Loss 0.9858 (1.0437)	Acc@1 75.684 (75.291)	Acc@5 94.238 (93.069)	
[2022-01-22 05:07:56 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.360 Acc@5 93.076
[2022-01-22 05:07:56 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.4%
[2022-01-22 05:07:56 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.63%
[2022-01-22 05:08:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][0/1251]	eta 7:33:14 lr 0.000536	time 21.7383 (21.7383)	loss 3.8652 (3.8652)	grad_norm 1.5845 (1.5845)	
[2022-01-22 05:08:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][10/1251]	eta 1:22:51 lr 0.000536	time 2.7570 (4.0060)	loss 3.8432 (3.5964)	grad_norm 1.1972 (1.3719)	
[2022-01-22 05:09:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][20/1251]	eta 1:05:56 lr 0.000536	time 1.4088 (3.2137)	loss 3.8367 (3.5410)	grad_norm 1.2918 (1.3609)	
[2022-01-22 05:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][30/1251]	eta 0:57:40 lr 0.000536	time 1.4998 (2.8342)	loss 4.2453 (3.4978)	grad_norm 1.5481 (1.3931)	
[2022-01-22 05:09:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][40/1251]	eta 0:55:14 lr 0.000536	time 3.9413 (2.7369)	loss 2.8797 (3.4479)	grad_norm 1.3528 (1.4302)	
[2022-01-22 05:10:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][50/1251]	eta 0:53:13 lr 0.000536	time 2.2285 (2.6586)	loss 3.7392 (3.4411)	grad_norm 1.4113 (1.4578)	
[2022-01-22 05:10:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][60/1251]	eta 0:51:29 lr 0.000536	time 2.2225 (2.5936)	loss 3.3330 (3.5003)	grad_norm 1.3907 (1.4551)	
[2022-01-22 05:10:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][70/1251]	eta 0:49:57 lr 0.000536	time 1.5702 (2.5383)	loss 3.9258 (3.5363)	grad_norm 1.3022 (1.4533)	
[2022-01-22 05:11:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][80/1251]	eta 0:48:51 lr 0.000536	time 3.2810 (2.5037)	loss 2.9063 (3.5286)	grad_norm 1.3823 (1.4490)	
[2022-01-22 05:11:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][90/1251]	eta 0:47:50 lr 0.000536	time 1.6008 (2.4724)	loss 3.1442 (3.4863)	grad_norm 1.6017 (1.4597)	
[2022-01-22 05:12:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][100/1251]	eta 0:46:40 lr 0.000536	time 1.6739 (2.4330)	loss 4.1620 (3.5213)	grad_norm 1.3784 (1.4527)	
[2022-01-22 05:12:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][110/1251]	eta 0:45:38 lr 0.000536	time 1.9663 (2.4004)	loss 4.2377 (3.5233)	grad_norm 1.6818 (1.4582)	
[2022-01-22 05:12:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][120/1251]	eta 0:44:52 lr 0.000536	time 3.0965 (2.3808)	loss 3.7302 (3.5197)	grad_norm 1.4685 (1.4556)	
[2022-01-22 05:13:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][130/1251]	eta 0:44:29 lr 0.000536	time 2.0944 (2.3816)	loss 4.1061 (3.5359)	grad_norm 1.3781 (1.4544)	
[2022-01-22 05:13:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][140/1251]	eta 0:43:42 lr 0.000536	time 1.8878 (2.3605)	loss 3.7686 (3.5248)	grad_norm 1.5957 (1.4515)	
[2022-01-22 05:13:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][150/1251]	eta 0:43:03 lr 0.000535	time 1.9172 (2.3469)	loss 3.9271 (3.5120)	grad_norm 1.3436 (1.4588)	
[2022-01-22 05:14:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][160/1251]	eta 0:42:30 lr 0.000535	time 2.1917 (2.3381)	loss 3.0048 (3.5081)	grad_norm 1.6621 (1.4583)	
[2022-01-22 05:14:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][170/1251]	eta 0:41:58 lr 0.000535	time 2.1553 (2.3294)	loss 4.2169 (3.5049)	grad_norm 1.6240 (1.4579)	
[2022-01-22 05:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][180/1251]	eta 0:41:20 lr 0.000535	time 1.9918 (2.3165)	loss 2.7867 (3.4943)	grad_norm 1.4733 (1.4553)	
[2022-01-22 05:15:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][190/1251]	eta 0:40:43 lr 0.000535	time 2.2484 (2.3028)	loss 4.3590 (3.5018)	grad_norm 1.2824 (1.4519)	
[2022-01-22 05:15:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][200/1251]	eta 0:40:18 lr 0.000535	time 2.8311 (2.3012)	loss 3.2620 (3.4979)	grad_norm 1.4279 (1.4519)	
[2022-01-22 05:15:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][210/1251]	eta 0:39:42 lr 0.000535	time 2.1555 (2.2886)	loss 2.8996 (3.4871)	grad_norm 1.4199 (1.4567)	
[2022-01-22 05:16:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][220/1251]	eta 0:39:13 lr 0.000535	time 1.9907 (2.2827)	loss 4.2298 (3.4979)	grad_norm 1.5254 (1.4569)	
[2022-01-22 05:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][230/1251]	eta 0:38:44 lr 0.000535	time 2.5143 (2.2768)	loss 3.6002 (3.4941)	grad_norm 1.4448 (1.4568)	
[2022-01-22 05:17:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][240/1251]	eta 0:38:20 lr 0.000535	time 2.7494 (2.2751)	loss 3.1527 (3.4991)	grad_norm 1.6788 (1.4602)	
[2022-01-22 05:17:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][250/1251]	eta 0:37:54 lr 0.000535	time 2.3606 (2.2721)	loss 3.9212 (3.5085)	grad_norm 1.3614 (1.4587)	
[2022-01-22 05:17:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][260/1251]	eta 0:37:26 lr 0.000535	time 2.4022 (2.2667)	loss 3.7311 (3.5095)	grad_norm 1.2780 (1.4577)	
[2022-01-22 05:18:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][270/1251]	eta 0:37:08 lr 0.000535	time 1.5975 (2.2717)	loss 3.9700 (3.5113)	grad_norm 1.4569 (1.4571)	
[2022-01-22 05:18:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][280/1251]	eta 0:36:41 lr 0.000535	time 2.2776 (2.2668)	loss 4.2417 (3.5067)	grad_norm 1.4541 (1.4591)	
[2022-01-22 05:18:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][290/1251]	eta 0:36:13 lr 0.000535	time 3.0629 (2.2619)	loss 4.2013 (3.5045)	grad_norm 1.3663 (1.4575)	
[2022-01-22 05:19:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][300/1251]	eta 0:35:46 lr 0.000535	time 1.8547 (2.2575)	loss 3.7545 (3.5095)	grad_norm 1.3128 (1.4553)	
[2022-01-22 05:19:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][310/1251]	eta 0:35:20 lr 0.000535	time 1.8558 (2.2536)	loss 3.7360 (3.5120)	grad_norm 1.4299 (1.4537)	
[2022-01-22 05:20:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][320/1251]	eta 0:35:02 lr 0.000535	time 5.6024 (2.2579)	loss 3.6626 (3.5095)	grad_norm 1.4804 (1.4551)	
[2022-01-22 05:20:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][330/1251]	eta 0:34:39 lr 0.000535	time 1.9002 (2.2581)	loss 3.4643 (3.5093)	grad_norm 1.5707 (1.4548)	
[2022-01-22 05:20:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][340/1251]	eta 0:34:11 lr 0.000535	time 1.9996 (2.2522)	loss 3.6696 (3.5132)	grad_norm 1.2924 (1.4560)	
[2022-01-22 05:21:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][350/1251]	eta 0:33:42 lr 0.000535	time 2.0130 (2.2452)	loss 3.4596 (3.5190)	grad_norm 1.5252 (1.4573)	
[2022-01-22 05:21:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][360/1251]	eta 0:33:22 lr 0.000535	time 3.0934 (2.2475)	loss 3.5390 (3.5187)	grad_norm 1.4039 (1.4613)	
[2022-01-22 05:21:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][370/1251]	eta 0:32:58 lr 0.000535	time 2.2165 (2.2452)	loss 4.4243 (3.5164)	grad_norm 2.0113 (1.4626)	
[2022-01-22 05:22:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][380/1251]	eta 0:32:33 lr 0.000535	time 2.0306 (2.2429)	loss 3.4032 (3.5180)	grad_norm 1.5397 (1.4640)	
[2022-01-22 05:22:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][390/1251]	eta 0:32:10 lr 0.000534	time 2.1670 (2.2424)	loss 3.7033 (3.5224)	grad_norm 1.5757 (1.4686)	
[2022-01-22 05:22:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][400/1251]	eta 0:31:48 lr 0.000534	time 3.6185 (2.2422)	loss 3.9529 (3.5212)	grad_norm 1.4190 (1.4696)	
[2022-01-22 05:23:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][410/1251]	eta 0:31:24 lr 0.000534	time 2.2026 (2.2405)	loss 3.8418 (3.5290)	grad_norm 1.7376 (1.4710)	
[2022-01-22 05:23:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][420/1251]	eta 0:30:59 lr 0.000534	time 2.1701 (2.2376)	loss 3.8024 (3.5273)	grad_norm 1.5433 (1.4716)	
[2022-01-22 05:24:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][430/1251]	eta 0:30:34 lr 0.000534	time 1.7358 (2.2350)	loss 3.9478 (3.5282)	grad_norm 1.8100 (1.4729)	
[2022-01-22 05:24:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][440/1251]	eta 0:30:10 lr 0.000534	time 2.7675 (2.2319)	loss 3.8274 (3.5274)	grad_norm 1.5039 (1.4725)	
[2022-01-22 05:24:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][450/1251]	eta 0:29:43 lr 0.000534	time 1.6273 (2.2271)	loss 4.1029 (3.5287)	grad_norm 1.4597 (1.4696)	
[2022-01-22 05:25:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][460/1251]	eta 0:29:19 lr 0.000534	time 1.9554 (2.2244)	loss 4.1056 (3.5257)	grad_norm 1.4673 (1.4687)	
[2022-01-22 05:25:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][470/1251]	eta 0:28:55 lr 0.000534	time 2.0144 (2.2219)	loss 3.6941 (3.5214)	grad_norm 1.3815 (1.4674)	
[2022-01-22 05:25:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][480/1251]	eta 0:28:33 lr 0.000534	time 2.2232 (2.2228)	loss 3.8108 (3.5163)	grad_norm 1.5417 (1.4675)	
[2022-01-22 05:26:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][490/1251]	eta 0:28:08 lr 0.000534	time 1.8276 (2.2190)	loss 4.3069 (3.5237)	grad_norm 1.4103 (1.4687)	
[2022-01-22 05:26:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][500/1251]	eta 0:27:44 lr 0.000534	time 2.4310 (2.2166)	loss 2.8022 (3.5232)	grad_norm 1.4125 (1.4684)	
[2022-01-22 05:26:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][510/1251]	eta 0:27:22 lr 0.000534	time 1.5991 (2.2163)	loss 3.5348 (3.5262)	grad_norm 1.2606 (1.4691)	
[2022-01-22 05:27:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][520/1251]	eta 0:27:00 lr 0.000534	time 2.1854 (2.2163)	loss 3.7482 (3.5271)	grad_norm 1.4578 (1.4687)	
[2022-01-22 05:27:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][530/1251]	eta 0:26:37 lr 0.000534	time 2.2701 (2.2161)	loss 4.1135 (3.5303)	grad_norm 1.7012 (1.4693)	
[2022-01-22 05:27:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][540/1251]	eta 0:26:19 lr 0.000534	time 3.2044 (2.2212)	loss 3.5610 (3.5312)	grad_norm 1.3334 (1.4708)	
[2022-01-22 05:28:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][550/1251]	eta 0:25:58 lr 0.000534	time 2.5714 (2.2239)	loss 4.0212 (3.5299)	grad_norm 1.2255 (1.4686)	
[2022-01-22 05:28:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][560/1251]	eta 0:25:37 lr 0.000534	time 2.2307 (2.2256)	loss 3.4112 (3.5317)	grad_norm 1.6134 (1.4683)	
[2022-01-22 05:29:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][570/1251]	eta 0:25:14 lr 0.000534	time 1.5005 (2.2241)	loss 4.4500 (3.5355)	grad_norm 1.4795 (1.4684)	
[2022-01-22 05:29:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][580/1251]	eta 0:24:50 lr 0.000534	time 2.8263 (2.2218)	loss 4.0813 (3.5373)	grad_norm 1.3606 (1.4684)	
[2022-01-22 05:29:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][590/1251]	eta 0:24:25 lr 0.000534	time 1.9217 (2.2169)	loss 3.8418 (3.5378)	grad_norm 1.7325 (1.4685)	
[2022-01-22 05:30:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][600/1251]	eta 0:24:01 lr 0.000534	time 1.9416 (2.2150)	loss 3.1922 (3.5381)	grad_norm 1.3277 (1.4682)	
[2022-01-22 05:30:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][610/1251]	eta 0:23:41 lr 0.000534	time 2.0180 (2.2171)	loss 3.2766 (3.5323)	grad_norm 1.5027 (1.4686)	
[2022-01-22 05:30:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][620/1251]	eta 0:23:22 lr 0.000534	time 3.5490 (2.2228)	loss 2.6981 (3.5315)	grad_norm 1.5888 (1.4693)	
[2022-01-22 05:31:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][630/1251]	eta 0:22:59 lr 0.000533	time 1.9318 (2.2216)	loss 4.0374 (3.5366)	grad_norm 1.5428 (1.4690)	
[2022-01-22 05:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][640/1251]	eta 0:22:35 lr 0.000533	time 1.7676 (2.2191)	loss 3.0047 (3.5331)	grad_norm 1.2271 (1.4686)	
[2022-01-22 05:31:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][650/1251]	eta 0:22:12 lr 0.000533	time 2.5544 (2.2165)	loss 4.4255 (3.5345)	grad_norm 1.4588 (1.4681)	
[2022-01-22 05:32:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][660/1251]	eta 0:21:48 lr 0.000533	time 2.8747 (2.2135)	loss 4.0162 (3.5335)	grad_norm 1.5972 (1.4673)	
[2022-01-22 05:32:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][670/1251]	eta 0:21:24 lr 0.000533	time 1.8928 (2.2104)	loss 4.1406 (3.5340)	grad_norm 1.6481 (1.4677)	
[2022-01-22 05:33:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][680/1251]	eta 0:21:01 lr 0.000533	time 1.9138 (2.2085)	loss 3.0399 (3.5315)	grad_norm 1.4853 (1.4683)	
[2022-01-22 05:33:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][690/1251]	eta 0:20:39 lr 0.000533	time 2.5268 (2.2086)	loss 3.7680 (3.5318)	grad_norm 1.4501 (1.4691)	
[2022-01-22 05:33:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][700/1251]	eta 0:20:16 lr 0.000533	time 2.6894 (2.2075)	loss 4.1130 (3.5303)	grad_norm 1.5574 (1.4695)	
[2022-01-22 05:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][710/1251]	eta 0:19:54 lr 0.000533	time 2.4381 (2.2081)	loss 3.7842 (3.5301)	grad_norm 1.5760 (1.4700)	
[2022-01-22 05:34:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][720/1251]	eta 0:19:33 lr 0.000533	time 1.8877 (2.2106)	loss 2.3705 (3.5283)	grad_norm 1.5860 (1.4700)	
[2022-01-22 05:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][730/1251]	eta 0:19:13 lr 0.000533	time 2.8148 (2.2131)	loss 4.1885 (3.5277)	grad_norm 1.3724 (1.4691)	
[2022-01-22 05:35:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][740/1251]	eta 0:18:51 lr 0.000533	time 2.0979 (2.2144)	loss 3.8470 (3.5276)	grad_norm 1.4722 (1.4693)	
[2022-01-22 05:35:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][750/1251]	eta 0:18:29 lr 0.000533	time 1.8292 (2.2139)	loss 2.5111 (3.5275)	grad_norm 1.2820 (1.4715)	
[2022-01-22 05:35:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][760/1251]	eta 0:18:05 lr 0.000533	time 2.1552 (2.2115)	loss 3.7567 (3.5300)	grad_norm 1.6215 (1.4717)	
[2022-01-22 05:36:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][770/1251]	eta 0:17:41 lr 0.000533	time 1.9035 (2.2075)	loss 3.6531 (3.5313)	grad_norm 1.4865 (1.4719)	
[2022-01-22 05:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][780/1251]	eta 0:17:19 lr 0.000533	time 1.8889 (2.2061)	loss 2.4735 (3.5297)	grad_norm 1.5899 (1.4733)	
[2022-01-22 05:37:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][790/1251]	eta 0:16:56 lr 0.000533	time 1.8467 (2.2049)	loss 3.6396 (3.5306)	grad_norm 1.4107 (1.4738)	
[2022-01-22 05:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][800/1251]	eta 0:16:34 lr 0.000533	time 2.2217 (2.2059)	loss 4.0018 (3.5355)	grad_norm 1.4363 (1.4734)	
[2022-01-22 05:37:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][810/1251]	eta 0:16:12 lr 0.000533	time 1.8104 (2.2058)	loss 2.9115 (3.5341)	grad_norm 1.3417 (1.4741)	
[2022-01-22 05:38:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][820/1251]	eta 0:15:51 lr 0.000533	time 1.9272 (2.2079)	loss 3.7436 (3.5341)	grad_norm 1.4094 (1.4741)	
[2022-01-22 05:38:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][830/1251]	eta 0:15:30 lr 0.000533	time 1.7958 (2.2102)	loss 3.1315 (3.5336)	grad_norm 1.4017 (1.4736)	
[2022-01-22 05:38:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][840/1251]	eta 0:15:09 lr 0.000533	time 3.3894 (2.2127)	loss 3.0508 (3.5335)	grad_norm 1.2612 (1.4723)	
[2022-01-22 05:39:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][850/1251]	eta 0:14:47 lr 0.000533	time 1.8770 (2.2123)	loss 2.5618 (3.5320)	grad_norm 1.2925 (1.4718)	
[2022-01-22 05:39:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][860/1251]	eta 0:14:24 lr 0.000533	time 1.9069 (2.2110)	loss 3.1175 (3.5311)	grad_norm 1.2415 (1.4718)	
[2022-01-22 05:40:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][870/1251]	eta 0:14:01 lr 0.000532	time 1.8131 (2.2085)	loss 2.8774 (3.5318)	grad_norm 1.4989 (1.4713)	
[2022-01-22 05:40:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][880/1251]	eta 0:13:40 lr 0.000532	time 3.4732 (2.2108)	loss 2.6701 (3.5276)	grad_norm 1.4500 (1.4735)	
[2022-01-22 05:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][890/1251]	eta 0:13:18 lr 0.000532	time 1.5851 (2.2107)	loss 4.2061 (3.5302)	grad_norm 1.5721 (1.4733)	
[2022-01-22 05:41:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][900/1251]	eta 0:12:55 lr 0.000532	time 1.5479 (2.2105)	loss 4.1210 (3.5314)	grad_norm 1.3939 (1.4733)	
[2022-01-22 05:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][910/1251]	eta 0:12:33 lr 0.000532	time 2.2387 (2.2104)	loss 2.6567 (3.5314)	grad_norm 1.4847 (1.4728)	
[2022-01-22 05:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][920/1251]	eta 0:12:11 lr 0.000532	time 3.2028 (2.2109)	loss 3.8128 (3.5335)	grad_norm 1.4478 (1.4722)	
[2022-01-22 05:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][930/1251]	eta 0:11:49 lr 0.000532	time 1.6057 (2.2092)	loss 3.0723 (3.5339)	grad_norm 1.5554 (1.4724)	
[2022-01-22 05:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][940/1251]	eta 0:11:27 lr 0.000532	time 1.7676 (2.2092)	loss 3.5972 (3.5348)	grad_norm 1.9131 (1.4749)	
[2022-01-22 05:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][950/1251]	eta 0:11:04 lr 0.000532	time 1.8513 (2.2087)	loss 2.9387 (3.5375)	grad_norm 1.4067 (1.4752)	
[2022-01-22 05:43:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][960/1251]	eta 0:10:42 lr 0.000532	time 2.4811 (2.2082)	loss 3.1053 (3.5347)	grad_norm 1.1779 (1.4742)	
[2022-01-22 05:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][970/1251]	eta 0:10:20 lr 0.000532	time 1.8457 (2.2073)	loss 3.4140 (3.5335)	grad_norm 1.1829 (1.4735)	
[2022-01-22 05:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][980/1251]	eta 0:09:58 lr 0.000532	time 2.3071 (2.2075)	loss 2.8504 (3.5324)	grad_norm 1.2923 (1.4730)	
[2022-01-22 05:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][990/1251]	eta 0:09:35 lr 0.000532	time 2.2371 (2.2064)	loss 3.9979 (3.5320)	grad_norm 1.5454 (1.4733)	
[2022-01-22 05:44:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1000/1251]	eta 0:09:13 lr 0.000532	time 2.1844 (2.2055)	loss 3.6955 (3.5319)	grad_norm 1.2395 (1.4729)	
[2022-01-22 05:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1010/1251]	eta 0:08:51 lr 0.000532	time 1.7063 (2.2043)	loss 3.5540 (3.5317)	grad_norm 1.8087 (1.4724)	
[2022-01-22 05:45:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1020/1251]	eta 0:08:29 lr 0.000532	time 2.7578 (2.2062)	loss 3.0136 (3.5291)	grad_norm 1.4201 (1.4727)	
[2022-01-22 05:45:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1030/1251]	eta 0:08:07 lr 0.000532	time 2.8055 (2.2058)	loss 3.5375 (3.5308)	grad_norm 1.3713 (1.4725)	
[2022-01-22 05:46:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1040/1251]	eta 0:07:45 lr 0.000532	time 1.7099 (2.2047)	loss 4.0250 (3.5293)	grad_norm 2.0712 (1.4735)	
[2022-01-22 05:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1050/1251]	eta 0:07:23 lr 0.000532	time 1.6152 (2.2053)	loss 3.9220 (3.5318)	grad_norm 1.5516 (1.4730)	
[2022-01-22 05:46:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1060/1251]	eta 0:07:01 lr 0.000532	time 2.5244 (2.2068)	loss 4.5413 (3.5346)	grad_norm 1.6952 (1.4729)	
[2022-01-22 05:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1070/1251]	eta 0:06:39 lr 0.000532	time 2.4106 (2.2059)	loss 4.3940 (3.5366)	grad_norm 1.6315 (1.4736)	
[2022-01-22 05:47:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1080/1251]	eta 0:06:16 lr 0.000532	time 1.6161 (2.2036)	loss 2.8116 (3.5387)	grad_norm 1.6932 (1.4739)	
[2022-01-22 05:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1090/1251]	eta 0:05:54 lr 0.000532	time 2.0888 (2.2027)	loss 3.7373 (3.5393)	grad_norm 1.4647 (1.4730)	
[2022-01-22 05:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1100/1251]	eta 0:05:32 lr 0.000532	time 2.4424 (2.2024)	loss 3.3115 (3.5376)	grad_norm 1.3064 (1.4725)	
[2022-01-22 05:48:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1110/1251]	eta 0:05:10 lr 0.000531	time 1.8911 (2.2030)	loss 3.5614 (3.5376)	grad_norm 1.6150 (1.4725)	
[2022-01-22 05:49:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1120/1251]	eta 0:04:48 lr 0.000531	time 2.1910 (2.2038)	loss 3.9375 (3.5358)	grad_norm 1.3312 (1.4725)	
[2022-01-22 05:49:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1130/1251]	eta 0:04:26 lr 0.000531	time 1.9066 (2.2040)	loss 3.5497 (3.5359)	grad_norm 1.3182 (1.4719)	
[2022-01-22 05:49:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1140/1251]	eta 0:04:04 lr 0.000531	time 1.9030 (2.2043)	loss 2.6820 (3.5368)	grad_norm 1.2871 (1.4715)	
[2022-01-22 05:50:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1150/1251]	eta 0:03:42 lr 0.000531	time 1.6347 (2.2043)	loss 4.0633 (3.5353)	grad_norm 1.3547 (1.4706)	
[2022-01-22 05:50:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1160/1251]	eta 0:03:20 lr 0.000531	time 1.5061 (2.2038)	loss 3.7804 (3.5368)	grad_norm 1.4234 (1.4703)	
[2022-01-22 05:50:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1170/1251]	eta 0:02:58 lr 0.000531	time 1.7447 (2.2030)	loss 2.7818 (3.5369)	grad_norm 1.4131 (1.4702)	
[2022-01-22 05:51:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1180/1251]	eta 0:02:36 lr 0.000531	time 2.0205 (2.2025)	loss 3.4747 (3.5375)	grad_norm 1.5384 (1.4704)	
[2022-01-22 05:51:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1190/1251]	eta 0:02:14 lr 0.000531	time 2.1910 (2.2012)	loss 2.7413 (3.5399)	grad_norm 1.3876 (1.4701)	
[2022-01-22 05:51:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1200/1251]	eta 0:01:52 lr 0.000531	time 1.9465 (2.1995)	loss 4.1190 (3.5393)	grad_norm 1.5182 (1.4694)	
[2022-01-22 05:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1210/1251]	eta 0:01:30 lr 0.000531	time 1.8161 (2.1992)	loss 4.2299 (3.5398)	grad_norm 1.1956 (1.4683)	
[2022-01-22 05:52:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1220/1251]	eta 0:01:08 lr 0.000531	time 2.1621 (2.2010)	loss 4.0101 (3.5395)	grad_norm 1.5727 (1.4680)	
[2022-01-22 05:53:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1230/1251]	eta 0:00:46 lr 0.000531	time 1.7559 (2.2025)	loss 3.2421 (3.5384)	grad_norm 1.3489 (1.4675)	
[2022-01-22 05:53:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1240/1251]	eta 0:00:24 lr 0.000531	time 1.9086 (2.2020)	loss 3.4753 (3.5380)	grad_norm 1.5519 (1.4678)	
[2022-01-22 05:53:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [144/300][1250/1251]	eta 0:00:02 lr 0.000531	time 1.1628 (2.1965)	loss 2.8300 (3.5376)	grad_norm 1.6806 (1.4679)	
[2022-01-22 05:53:44 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 144 training takes 0:45:48
[2022-01-22 05:54:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.614 (18.614)	Loss 0.9720 (0.9720)	Acc@1 77.051 (77.051)	Acc@5 94.531 (94.531)	
[2022-01-22 05:54:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.965 (3.405)	Loss 0.9818 (1.0385)	Acc@1 75.586 (75.142)	Acc@5 93.945 (93.510)	
[2022-01-22 05:54:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.293 (2.543)	Loss 0.9838 (1.0392)	Acc@1 77.051 (75.242)	Acc@5 94.043 (93.411)	
[2022-01-22 05:54:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.282 (2.279)	Loss 1.0335 (1.0320)	Acc@1 75.781 (75.447)	Acc@5 93.164 (93.300)	
[2022-01-22 05:55:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.127 (2.225)	Loss 1.0184 (1.0327)	Acc@1 75.781 (75.460)	Acc@5 92.969 (93.155)	
[2022-01-22 05:55:23 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.458 Acc@5 93.202
[2022-01-22 05:55:23 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.5%
[2022-01-22 05:55:23 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.63%
[2022-01-22 05:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][0/1251]	eta 7:28:56 lr 0.000531	time 21.5319 (21.5319)	loss 2.6017 (2.6017)	grad_norm 1.4743 (1.4743)	
[2022-01-22 05:56:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][10/1251]	eta 1:21:57 lr 0.000531	time 1.8808 (3.9624)	loss 3.2876 (3.4396)	grad_norm 1.3315 (1.4380)	
[2022-01-22 05:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][20/1251]	eta 1:03:26 lr 0.000531	time 1.4774 (3.0926)	loss 4.0415 (3.4996)	grad_norm 1.4550 (1.4602)	
[2022-01-22 05:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][30/1251]	eta 0:57:54 lr 0.000531	time 1.6021 (2.8456)	loss 3.3850 (3.4284)	grad_norm 1.5743 (1.4735)	
[2022-01-22 05:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][40/1251]	eta 0:55:18 lr 0.000531	time 4.9029 (2.7399)	loss 3.8008 (3.4346)	grad_norm 1.3609 (1.4733)	
[2022-01-22 05:57:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][50/1251]	eta 0:51:46 lr 0.000531	time 1.6367 (2.5864)	loss 3.4247 (3.4383)	grad_norm 1.4929 (1.4739)	
[2022-01-22 05:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][60/1251]	eta 0:50:45 lr 0.000531	time 2.3770 (2.5569)	loss 4.5282 (3.4233)	grad_norm 1.9341 (1.4792)	
[2022-01-22 05:58:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][70/1251]	eta 0:49:00 lr 0.000531	time 1.6954 (2.4896)	loss 2.5592 (3.4689)	grad_norm 1.3946 (1.4837)	
[2022-01-22 05:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][80/1251]	eta 0:47:54 lr 0.000531	time 3.4323 (2.4551)	loss 2.3464 (3.4828)	grad_norm 1.6183 (1.4786)	
[2022-01-22 05:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][90/1251]	eta 0:46:55 lr 0.000531	time 2.0596 (2.4254)	loss 3.7220 (3.5028)	grad_norm 1.5994 (1.4795)	
[2022-01-22 05:59:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][100/1251]	eta 0:46:08 lr 0.000530	time 1.5754 (2.4053)	loss 2.7854 (3.5105)	grad_norm 1.3826 (1.4826)	
[2022-01-22 05:59:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][110/1251]	eta 0:45:17 lr 0.000530	time 1.9042 (2.3815)	loss 3.2273 (3.5135)	grad_norm 1.5133 (1.4786)	
[2022-01-22 06:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][120/1251]	eta 0:44:45 lr 0.000530	time 3.4335 (2.3747)	loss 4.3706 (3.5303)	grad_norm 1.5029 (1.4754)	
[2022-01-22 06:00:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][130/1251]	eta 0:44:16 lr 0.000530	time 2.5790 (2.3698)	loss 3.9852 (3.5403)	grad_norm 2.2719 (1.4792)	
[2022-01-22 06:00:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][140/1251]	eta 0:43:30 lr 0.000530	time 1.7864 (2.3499)	loss 3.9777 (3.5410)	grad_norm 1.6872 (1.4791)	
[2022-01-22 06:01:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][150/1251]	eta 0:42:54 lr 0.000530	time 2.1730 (2.3379)	loss 3.3143 (3.5683)	grad_norm 1.6560 (1.4828)	
[2022-01-22 06:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][160/1251]	eta 0:42:24 lr 0.000530	time 2.5296 (2.3318)	loss 3.9808 (3.5706)	grad_norm 1.4326 (1.4854)	
[2022-01-22 06:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][170/1251]	eta 0:41:51 lr 0.000530	time 2.5398 (2.3233)	loss 3.7751 (3.5770)	grad_norm 1.5700 (1.4784)	
[2022-01-22 06:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][180/1251]	eta 0:41:10 lr 0.000530	time 1.8375 (2.3067)	loss 2.4383 (3.5710)	grad_norm 1.5397 (1.4773)	
[2022-01-22 06:02:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][190/1251]	eta 0:40:49 lr 0.000530	time 2.4783 (2.3087)	loss 2.5090 (3.5531)	grad_norm 1.4000 (1.4738)	
[2022-01-22 06:03:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][200/1251]	eta 0:40:20 lr 0.000530	time 2.7532 (2.3033)	loss 3.0897 (3.5533)	grad_norm 1.3755 (1.4776)	
[2022-01-22 06:03:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][210/1251]	eta 0:39:47 lr 0.000530	time 2.3518 (2.2934)	loss 3.8319 (3.5675)	grad_norm 1.5647 (1.4778)	
[2022-01-22 06:03:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][220/1251]	eta 0:39:13 lr 0.000530	time 1.9368 (2.2831)	loss 3.2893 (3.5612)	grad_norm 1.4223 (1.4768)	
[2022-01-22 06:04:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][230/1251]	eta 0:38:43 lr 0.000530	time 2.1310 (2.2757)	loss 3.7297 (3.5714)	grad_norm 1.5070 (1.4764)	
[2022-01-22 06:04:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][240/1251]	eta 0:38:15 lr 0.000530	time 1.8098 (2.2702)	loss 2.5473 (3.5684)	grad_norm 1.2473 (1.4770)	
[2022-01-22 06:04:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][250/1251]	eta 0:37:49 lr 0.000530	time 2.8499 (2.2673)	loss 2.8026 (3.5607)	grad_norm 1.4391 (1.4742)	
[2022-01-22 06:05:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][260/1251]	eta 0:37:23 lr 0.000530	time 2.0546 (2.2639)	loss 4.1767 (3.5599)	grad_norm 1.5343 (1.4764)	
[2022-01-22 06:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][270/1251]	eta 0:37:04 lr 0.000530	time 3.6172 (2.2678)	loss 3.4506 (3.5624)	grad_norm 1.2635 (1.4767)	
[2022-01-22 06:06:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][280/1251]	eta 0:36:40 lr 0.000530	time 1.8109 (2.2661)	loss 3.4611 (3.5678)	grad_norm 1.6923 (1.4758)	
[2022-01-22 06:06:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][290/1251]	eta 0:36:17 lr 0.000530	time 2.8290 (2.2659)	loss 4.0037 (3.5668)	grad_norm 1.6062 (1.4767)	
[2022-01-22 06:06:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][300/1251]	eta 0:35:47 lr 0.000530	time 1.5767 (2.2582)	loss 4.3964 (3.5797)	grad_norm 1.2835 (1.4778)	
[2022-01-22 06:07:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][310/1251]	eta 0:35:22 lr 0.000530	time 2.9410 (2.2551)	loss 4.4057 (3.5730)	grad_norm 1.4433 (1.4763)	
[2022-01-22 06:07:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][320/1251]	eta 0:34:54 lr 0.000530	time 1.7109 (2.2499)	loss 3.0268 (3.5717)	grad_norm 1.6149 (1.4752)	
[2022-01-22 06:07:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][330/1251]	eta 0:34:29 lr 0.000530	time 2.2009 (2.2470)	loss 3.8135 (3.5734)	grad_norm 1.2731 (1.4763)	
[2022-01-22 06:08:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][340/1251]	eta 0:34:04 lr 0.000529	time 1.7834 (2.2442)	loss 2.6783 (3.5712)	grad_norm 1.3864 (1.4781)	
[2022-01-22 06:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][350/1251]	eta 0:33:41 lr 0.000529	time 3.0657 (2.2433)	loss 3.8150 (3.5719)	grad_norm 1.3751 (1.4779)	
[2022-01-22 06:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][360/1251]	eta 0:33:24 lr 0.000529	time 2.9884 (2.2498)	loss 3.1137 (3.5676)	grad_norm 1.2191 (1.4754)	
[2022-01-22 06:09:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][370/1251]	eta 0:33:01 lr 0.000529	time 1.9937 (2.2491)	loss 3.8253 (3.5724)	grad_norm 1.6679 (1.4747)	
[2022-01-22 06:09:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][380/1251]	eta 0:32:35 lr 0.000529	time 2.0083 (2.2452)	loss 3.3315 (3.5754)	grad_norm 1.3945 (1.4748)	
[2022-01-22 06:09:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][390/1251]	eta 0:32:07 lr 0.000529	time 1.8049 (2.2383)	loss 3.9947 (3.5804)	grad_norm 1.5233 (1.4757)	
[2022-01-22 06:10:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][400/1251]	eta 0:31:40 lr 0.000529	time 1.8723 (2.2334)	loss 3.9514 (3.5796)	grad_norm 1.4437 (1.4767)	
[2022-01-22 06:10:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][410/1251]	eta 0:31:15 lr 0.000529	time 2.0912 (2.2299)	loss 4.0891 (3.5769)	grad_norm 1.4043 (1.4764)	
[2022-01-22 06:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][420/1251]	eta 0:30:51 lr 0.000529	time 1.6407 (2.2278)	loss 3.8453 (3.5768)	grad_norm 1.3803 (1.4762)	
[2022-01-22 06:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][430/1251]	eta 0:30:29 lr 0.000529	time 2.3710 (2.2281)	loss 3.8518 (3.5764)	grad_norm 1.4682 (1.4769)	
[2022-01-22 06:11:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][440/1251]	eta 0:30:10 lr 0.000529	time 1.5366 (2.2319)	loss 2.7723 (3.5713)	grad_norm 1.7123 (1.4789)	
[2022-01-22 06:12:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][450/1251]	eta 0:29:49 lr 0.000529	time 2.3750 (2.2344)	loss 2.8461 (3.5687)	grad_norm 1.4622 (1.4777)	
[2022-01-22 06:12:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][460/1251]	eta 0:29:25 lr 0.000529	time 2.3692 (2.2316)	loss 2.6888 (3.5678)	grad_norm 1.4565 (1.4760)	
[2022-01-22 06:12:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][470/1251]	eta 0:29:00 lr 0.000529	time 2.2811 (2.2288)	loss 4.1117 (3.5685)	grad_norm 1.2126 (1.4749)	
[2022-01-22 06:13:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][480/1251]	eta 0:28:35 lr 0.000529	time 1.6513 (2.2249)	loss 3.1657 (3.5658)	grad_norm 1.9920 (1.4749)	
[2022-01-22 06:13:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][490/1251]	eta 0:28:11 lr 0.000529	time 2.3369 (2.2232)	loss 4.1007 (3.5636)	grad_norm 1.3934 (1.4742)	
[2022-01-22 06:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][500/1251]	eta 0:27:49 lr 0.000529	time 2.9165 (2.2236)	loss 2.9966 (3.5612)	grad_norm 1.4889 (1.4733)	
[2022-01-22 06:14:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][510/1251]	eta 0:27:27 lr 0.000529	time 2.7851 (2.2237)	loss 3.8737 (3.5605)	grad_norm 1.5186 (1.4730)	
[2022-01-22 06:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][520/1251]	eta 0:27:04 lr 0.000529	time 1.9250 (2.2229)	loss 3.7409 (3.5671)	grad_norm 1.3810 (1.4724)	
[2022-01-22 06:15:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][530/1251]	eta 0:26:43 lr 0.000529	time 3.1464 (2.2239)	loss 4.2310 (3.5757)	grad_norm 1.4140 (1.4720)	
[2022-01-22 06:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][540/1251]	eta 0:26:19 lr 0.000529	time 2.5690 (2.2220)	loss 3.6423 (3.5759)	grad_norm 1.3367 (1.4719)	
[2022-01-22 06:15:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][550/1251]	eta 0:25:58 lr 0.000529	time 3.3619 (2.2231)	loss 3.7701 (3.5756)	grad_norm 1.4145 (1.4713)	
[2022-01-22 06:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][560/1251]	eta 0:25:34 lr 0.000529	time 2.0061 (2.2201)	loss 2.7156 (3.5707)	grad_norm 1.4804 (1.4701)	
[2022-01-22 06:16:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][570/1251]	eta 0:25:09 lr 0.000529	time 2.1888 (2.2169)	loss 4.0036 (3.5718)	grad_norm 1.3599 (1.4687)	
[2022-01-22 06:16:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][580/1251]	eta 0:24:46 lr 0.000529	time 2.3281 (2.2158)	loss 3.5247 (3.5690)	grad_norm 1.3527 (1.4674)	
[2022-01-22 06:17:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][590/1251]	eta 0:24:25 lr 0.000528	time 2.5477 (2.2174)	loss 2.8318 (3.5681)	grad_norm 1.6876 (1.4688)	
[2022-01-22 06:17:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][600/1251]	eta 0:24:05 lr 0.000528	time 2.7711 (2.2206)	loss 4.1038 (3.5712)	grad_norm 1.4203 (1.4683)	
[2022-01-22 06:18:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][610/1251]	eta 0:23:43 lr 0.000528	time 2.1766 (2.2204)	loss 3.6741 (3.5714)	grad_norm 1.3327 (1.4690)	
[2022-01-22 06:18:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][620/1251]	eta 0:23:19 lr 0.000528	time 2.2672 (2.2186)	loss 2.4225 (3.5693)	grad_norm 1.4890 (1.4679)	
[2022-01-22 06:18:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][630/1251]	eta 0:22:55 lr 0.000528	time 1.9911 (2.2153)	loss 3.7308 (3.5698)	grad_norm 1.5849 (1.4677)	
[2022-01-22 06:19:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][640/1251]	eta 0:22:32 lr 0.000528	time 2.1814 (2.2129)	loss 4.4316 (3.5697)	grad_norm 1.5068 (1.4666)	
[2022-01-22 06:19:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][650/1251]	eta 0:22:10 lr 0.000528	time 2.2390 (2.2136)	loss 3.9204 (3.5697)	grad_norm 1.3285 (1.4651)	
[2022-01-22 06:19:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][660/1251]	eta 0:21:48 lr 0.000528	time 1.9495 (2.2138)	loss 4.1571 (3.5704)	grad_norm 1.6214 (1.4650)	
[2022-01-22 06:20:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][670/1251]	eta 0:21:26 lr 0.000528	time 2.5785 (2.2151)	loss 2.5213 (3.5672)	grad_norm 1.5044 (1.4652)	
[2022-01-22 06:20:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][680/1251]	eta 0:21:03 lr 0.000528	time 1.9330 (2.2136)	loss 3.7088 (3.5663)	grad_norm 1.8617 (1.4667)	
[2022-01-22 06:20:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][690/1251]	eta 0:20:40 lr 0.000528	time 1.7356 (2.2119)	loss 4.0067 (3.5685)	grad_norm 1.4784 (1.4658)	
[2022-01-22 06:21:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][700/1251]	eta 0:20:18 lr 0.000528	time 1.5125 (2.2114)	loss 3.6728 (3.5665)	grad_norm 1.4380 (1.4649)	
[2022-01-22 06:21:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][710/1251]	eta 0:19:55 lr 0.000528	time 1.7023 (2.2099)	loss 2.5632 (3.5646)	grad_norm 1.4194 (1.4649)	
[2022-01-22 06:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][720/1251]	eta 0:19:33 lr 0.000528	time 2.1515 (2.2101)	loss 2.5855 (3.5628)	grad_norm 1.5538 (1.4653)	
[2022-01-22 06:22:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][730/1251]	eta 0:19:12 lr 0.000528	time 2.7766 (2.2112)	loss 3.2267 (3.5630)	grad_norm 1.3347 (1.4659)	
[2022-01-22 06:22:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][740/1251]	eta 0:18:50 lr 0.000528	time 1.8806 (2.2119)	loss 3.7895 (3.5612)	grad_norm 1.3216 (1.4655)	
[2022-01-22 06:23:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][750/1251]	eta 0:18:27 lr 0.000528	time 1.8970 (2.2114)	loss 3.9767 (3.5646)	grad_norm 1.6613 (1.4654)	
[2022-01-22 06:23:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][760/1251]	eta 0:18:04 lr 0.000528	time 1.8125 (2.2092)	loss 3.1037 (3.5625)	grad_norm 1.4910 (1.4663)	
[2022-01-22 06:23:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][770/1251]	eta 0:17:41 lr 0.000528	time 1.5599 (2.2069)	loss 3.8323 (3.5628)	grad_norm 1.5511 (1.4655)	
[2022-01-22 06:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][780/1251]	eta 0:17:18 lr 0.000528	time 2.1380 (2.2058)	loss 4.1418 (3.5681)	grad_norm 1.7460 (1.4662)	
[2022-01-22 06:24:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][790/1251]	eta 0:16:56 lr 0.000528	time 2.1110 (2.2048)	loss 3.5857 (3.5658)	grad_norm 1.6235 (1.4680)	
[2022-01-22 06:24:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][800/1251]	eta 0:16:34 lr 0.000528	time 1.8737 (2.2051)	loss 3.0579 (3.5673)	grad_norm 1.2239 (1.4674)	
[2022-01-22 06:25:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][810/1251]	eta 0:16:12 lr 0.000528	time 2.5217 (2.2056)	loss 3.6248 (3.5675)	grad_norm 1.2702 (1.4682)	
[2022-01-22 06:25:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][820/1251]	eta 0:15:51 lr 0.000528	time 1.9162 (2.2075)	loss 2.4618 (3.5646)	grad_norm 1.6569 (1.4694)	
[2022-01-22 06:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][830/1251]	eta 0:15:29 lr 0.000527	time 2.3101 (2.2089)	loss 3.1889 (3.5641)	grad_norm 1.4465 (1.4693)	
[2022-01-22 06:26:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][840/1251]	eta 0:15:07 lr 0.000527	time 1.9222 (2.2071)	loss 2.4450 (3.5649)	grad_norm 1.4799 (1.4694)	
[2022-01-22 06:26:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][850/1251]	eta 0:14:44 lr 0.000527	time 1.9048 (2.2062)	loss 3.1627 (3.5637)	grad_norm 1.4326 (1.4703)	
[2022-01-22 06:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][860/1251]	eta 0:14:22 lr 0.000527	time 1.8640 (2.2062)	loss 3.3137 (3.5617)	grad_norm 1.5733 (1.4711)	
[2022-01-22 06:27:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][870/1251]	eta 0:14:00 lr 0.000527	time 1.8977 (2.2059)	loss 2.7400 (3.5579)	grad_norm 1.6804 (1.4716)	
[2022-01-22 06:27:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][880/1251]	eta 0:13:37 lr 0.000527	time 1.8309 (2.2047)	loss 3.2667 (3.5588)	grad_norm 1.4003 (1.4718)	
[2022-01-22 06:28:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][890/1251]	eta 0:13:15 lr 0.000527	time 2.1314 (2.2038)	loss 2.4550 (3.5587)	grad_norm 1.6494 (1.4719)	
[2022-01-22 06:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][900/1251]	eta 0:12:53 lr 0.000527	time 1.8765 (2.2041)	loss 3.8604 (3.5600)	grad_norm 1.2306 (1.4709)	
[2022-01-22 06:28:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][910/1251]	eta 0:12:31 lr 0.000527	time 1.9419 (2.2038)	loss 3.8822 (3.5602)	grad_norm 2.3213 (1.4722)	
[2022-01-22 06:29:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][920/1251]	eta 0:12:09 lr 0.000527	time 1.9249 (2.2036)	loss 3.7414 (3.5615)	grad_norm 1.2872 (1.4739)	
[2022-01-22 06:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][930/1251]	eta 0:11:47 lr 0.000527	time 2.2656 (2.2038)	loss 3.1277 (3.5615)	grad_norm 1.6204 (1.4748)	
[2022-01-22 06:29:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][940/1251]	eta 0:11:25 lr 0.000527	time 1.9259 (2.2032)	loss 4.2535 (3.5606)	grad_norm 1.4791 (1.4750)	
[2022-01-22 06:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][950/1251]	eta 0:11:03 lr 0.000527	time 1.8637 (2.2034)	loss 3.5523 (3.5585)	grad_norm 1.4931 (1.4756)	
[2022-01-22 06:30:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][960/1251]	eta 0:10:40 lr 0.000527	time 1.5395 (2.2021)	loss 3.3458 (3.5581)	grad_norm 1.4299 (1.4765)	
[2022-01-22 06:31:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][970/1251]	eta 0:10:19 lr 0.000527	time 3.4590 (2.2033)	loss 3.7713 (3.5568)	grad_norm 1.6803 (1.4761)	
[2022-01-22 06:31:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][980/1251]	eta 0:09:57 lr 0.000527	time 1.7155 (2.2035)	loss 2.8104 (3.5574)	grad_norm 1.4766 (1.4760)	
[2022-01-22 06:31:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][990/1251]	eta 0:09:35 lr 0.000527	time 1.8810 (2.2033)	loss 3.8684 (3.5567)	grad_norm 1.5339 (1.4771)	
[2022-01-22 06:32:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1000/1251]	eta 0:09:12 lr 0.000527	time 1.8930 (2.2027)	loss 2.6986 (3.5560)	grad_norm 1.3078 (1.4772)	
[2022-01-22 06:32:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1010/1251]	eta 0:08:50 lr 0.000527	time 3.2619 (2.2018)	loss 3.6646 (3.5554)	grad_norm 1.4945 (1.4763)	
[2022-01-22 06:32:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1020/1251]	eta 0:08:28 lr 0.000527	time 1.8704 (2.2008)	loss 2.8195 (3.5531)	grad_norm 1.5580 (1.4761)	
[2022-01-22 06:33:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1030/1251]	eta 0:08:06 lr 0.000527	time 2.0230 (2.2000)	loss 3.6594 (3.5522)	grad_norm 1.4736 (1.4748)	
[2022-01-22 06:33:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1040/1251]	eta 0:07:44 lr 0.000527	time 2.0706 (2.2009)	loss 3.6595 (3.5532)	grad_norm 1.3798 (1.4747)	
[2022-01-22 06:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1050/1251]	eta 0:07:22 lr 0.000527	time 2.8319 (2.2019)	loss 4.0611 (3.5507)	grad_norm 1.6571 (1.4746)	
[2022-01-22 06:34:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1060/1251]	eta 0:07:00 lr 0.000527	time 2.1188 (2.2006)	loss 3.9116 (3.5517)	grad_norm 1.2623 (1.4736)	
[2022-01-22 06:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1070/1251]	eta 0:06:38 lr 0.000526	time 1.8190 (2.2001)	loss 3.1455 (3.5520)	grad_norm 1.2551 (1.4730)	
[2022-01-22 06:35:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1080/1251]	eta 0:06:16 lr 0.000526	time 2.0484 (2.1993)	loss 3.7789 (3.5517)	grad_norm 1.4528 (1.4729)	
[2022-01-22 06:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1090/1251]	eta 0:05:54 lr 0.000526	time 2.8701 (2.1994)	loss 2.3171 (3.5513)	grad_norm 1.6038 (1.4734)	
[2022-01-22 06:35:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1100/1251]	eta 0:05:32 lr 0.000526	time 2.4918 (2.1995)	loss 3.7136 (3.5524)	grad_norm 1.4928 (1.4734)	
[2022-01-22 06:36:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1110/1251]	eta 0:05:10 lr 0.000526	time 2.1282 (2.2005)	loss 3.9302 (3.5543)	grad_norm 1.3123 (1.4733)	
[2022-01-22 06:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1120/1251]	eta 0:04:48 lr 0.000526	time 2.1905 (2.2003)	loss 2.8163 (3.5539)	grad_norm 1.6587 (1.4725)	
[2022-01-22 06:36:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1130/1251]	eta 0:04:26 lr 0.000526	time 3.1091 (2.2020)	loss 3.7906 (3.5540)	grad_norm 1.4034 (1.4722)	
[2022-01-22 06:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1140/1251]	eta 0:04:04 lr 0.000526	time 1.6623 (2.2007)	loss 2.4081 (3.5529)	grad_norm 1.3717 (1.4720)	
[2022-01-22 06:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1150/1251]	eta 0:03:42 lr 0.000526	time 1.6794 (2.1988)	loss 3.7649 (3.5508)	grad_norm 1.4535 (1.4718)	
[2022-01-22 06:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1160/1251]	eta 0:03:19 lr 0.000526	time 1.9280 (2.1978)	loss 3.6510 (3.5509)	grad_norm 1.4286 (1.4718)	
[2022-01-22 06:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1170/1251]	eta 0:02:58 lr 0.000526	time 2.5038 (2.1993)	loss 3.5317 (3.5519)	grad_norm 1.2893 (1.4719)	
[2022-01-22 06:38:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1180/1251]	eta 0:02:36 lr 0.000526	time 1.8676 (2.1993)	loss 4.0440 (3.5539)	grad_norm 1.3581 (1.4715)	
[2022-01-22 06:39:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1190/1251]	eta 0:02:14 lr 0.000526	time 1.9373 (2.1989)	loss 3.3588 (3.5540)	grad_norm 1.5066 (1.4713)	
[2022-01-22 06:39:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1200/1251]	eta 0:01:52 lr 0.000526	time 1.7353 (2.1978)	loss 3.7881 (3.5556)	grad_norm 1.4316 (1.4706)	
[2022-01-22 06:39:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1210/1251]	eta 0:01:30 lr 0.000526	time 1.8083 (2.1973)	loss 3.5996 (3.5555)	grad_norm 1.5745 (1.4702)	
[2022-01-22 06:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1220/1251]	eta 0:01:08 lr 0.000526	time 2.0717 (2.1969)	loss 4.2783 (3.5552)	grad_norm 1.3146 (1.4700)	
[2022-01-22 06:40:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1230/1251]	eta 0:00:46 lr 0.000526	time 2.7480 (2.1972)	loss 4.0952 (3.5567)	grad_norm 1.5796 (1.4705)	
[2022-01-22 06:40:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1240/1251]	eta 0:00:24 lr 0.000526	time 1.5346 (2.1959)	loss 3.5618 (3.5580)	grad_norm 1.3729 (1.4704)	
[2022-01-22 06:41:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [145/300][1250/1251]	eta 0:00:02 lr 0.000526	time 1.2877 (2.1907)	loss 3.6659 (3.5566)	grad_norm 1.3058 (1.4706)	
[2022-01-22 06:41:04 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 145 training takes 0:45:41
[2022-01-22 06:41:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.031 (19.031)	Loss 0.9948 (0.9948)	Acc@1 77.930 (77.930)	Acc@5 94.043 (94.043)	
[2022-01-22 06:41:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.951 (3.429)	Loss 1.0948 (1.0154)	Acc@1 73.926 (76.003)	Acc@5 93.555 (93.510)	
[2022-01-22 06:41:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.297 (2.473)	Loss 1.0425 (1.0250)	Acc@1 74.805 (75.944)	Acc@5 92.676 (93.331)	
[2022-01-22 06:42:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.654 (2.212)	Loss 0.9925 (1.0290)	Acc@1 77.344 (75.876)	Acc@5 94.336 (93.363)	
[2022-01-22 06:42:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.283 (2.137)	Loss 1.0362 (1.0334)	Acc@1 74.121 (75.653)	Acc@5 93.555 (93.297)	
[2022-01-22 06:42:39 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.706 Acc@5 93.252
[2022-01-22 06:42:39 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.7%
[2022-01-22 06:42:39 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.71%
[2022-01-22 06:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][0/1251]	eta 7:36:50 lr 0.000526	time 21.9106 (21.9106)	loss 4.1716 (4.1716)	grad_norm 1.5978 (1.5978)	
[2022-01-22 06:43:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][10/1251]	eta 1:25:05 lr 0.000526	time 2.5875 (4.1141)	loss 3.8748 (3.6219)	grad_norm 1.2156 (1.4401)	
[2022-01-22 06:43:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][20/1251]	eta 1:04:19 lr 0.000526	time 1.7921 (3.1350)	loss 2.6983 (3.5197)	grad_norm 1.4228 (1.5056)	
[2022-01-22 06:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][30/1251]	eta 0:57:18 lr 0.000526	time 1.6854 (2.8163)	loss 4.0033 (3.5454)	grad_norm 1.3814 (1.4921)	
[2022-01-22 06:44:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][40/1251]	eta 0:54:37 lr 0.000526	time 3.7529 (2.7065)	loss 3.4075 (3.5043)	grad_norm 1.4379 (1.4892)	
[2022-01-22 06:44:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][50/1251]	eta 0:53:20 lr 0.000526	time 3.3629 (2.6647)	loss 4.3507 (3.4937)	grad_norm 1.8470 (1.4760)	
[2022-01-22 06:45:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][60/1251]	eta 0:52:23 lr 0.000525	time 2.5617 (2.6395)	loss 2.7194 (3.4448)	grad_norm 1.4342 (1.4758)	
[2022-01-22 06:45:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][70/1251]	eta 0:50:31 lr 0.000525	time 1.6987 (2.5667)	loss 3.7964 (3.4513)	grad_norm 1.5139 (1.4809)	
[2022-01-22 06:46:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][80/1251]	eta 0:48:42 lr 0.000525	time 1.9118 (2.4954)	loss 3.8542 (3.4374)	grad_norm 1.5722 (1.4794)	
[2022-01-22 06:46:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][90/1251]	eta 0:46:48 lr 0.000525	time 1.6578 (2.4194)	loss 4.2321 (3.4417)	grad_norm 1.6077 (1.4966)	
[2022-01-22 06:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][100/1251]	eta 0:46:00 lr 0.000525	time 2.6072 (2.3981)	loss 2.3410 (3.4801)	grad_norm 1.4480 (1.5039)	
[2022-01-22 06:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][110/1251]	eta 0:45:09 lr 0.000525	time 1.8676 (2.3749)	loss 3.9605 (3.4762)	grad_norm 1.4966 (1.5029)	
[2022-01-22 06:47:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][120/1251]	eta 0:44:36 lr 0.000525	time 2.1136 (2.3661)	loss 3.0910 (3.4701)	grad_norm 1.9097 (1.5130)	
[2022-01-22 06:47:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][130/1251]	eta 0:44:02 lr 0.000525	time 1.5497 (2.3576)	loss 3.2443 (3.4631)	grad_norm 1.5257 (1.5085)	
[2022-01-22 06:48:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][140/1251]	eta 0:43:49 lr 0.000525	time 3.0828 (2.3667)	loss 4.0804 (3.4828)	grad_norm 1.5772 (1.5051)	
[2022-01-22 06:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][150/1251]	eta 0:43:19 lr 0.000525	time 2.6719 (2.3613)	loss 3.2699 (3.4860)	grad_norm 1.6870 (1.5068)	
[2022-01-22 06:48:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][160/1251]	eta 0:42:35 lr 0.000525	time 1.6310 (2.3421)	loss 3.2511 (3.4963)	grad_norm 1.3993 (1.5039)	
[2022-01-22 06:49:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][170/1251]	eta 0:41:49 lr 0.000525	time 1.7392 (2.3212)	loss 3.6742 (3.4924)	grad_norm 1.6695 (1.4981)	
[2022-01-22 06:49:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][180/1251]	eta 0:41:09 lr 0.000525	time 2.2697 (2.3061)	loss 3.7097 (3.5007)	grad_norm 1.3514 (1.4918)	
[2022-01-22 06:49:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][190/1251]	eta 0:40:38 lr 0.000525	time 2.5481 (2.2984)	loss 3.0928 (3.5021)	grad_norm 1.2474 (1.4869)	
[2022-01-22 06:50:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][200/1251]	eta 0:40:17 lr 0.000525	time 2.6047 (2.3003)	loss 2.6020 (3.4987)	grad_norm 1.5141 (1.4854)	
[2022-01-22 06:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][210/1251]	eta 0:39:51 lr 0.000525	time 1.8472 (2.2973)	loss 3.8803 (3.5077)	grad_norm 1.4394 (1.4842)	
[2022-01-22 06:51:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][220/1251]	eta 0:39:28 lr 0.000525	time 2.4276 (2.2972)	loss 3.9466 (3.4988)	grad_norm 1.7492 (1.4832)	
[2022-01-22 06:51:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][230/1251]	eta 0:38:58 lr 0.000525	time 2.4512 (2.2904)	loss 3.9745 (3.5094)	grad_norm 1.4234 (1.4817)	
[2022-01-22 06:51:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][240/1251]	eta 0:38:29 lr 0.000525	time 1.5532 (2.2847)	loss 3.7340 (3.5080)	grad_norm 1.3880 (1.4795)	
[2022-01-22 06:52:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][250/1251]	eta 0:37:56 lr 0.000525	time 1.8778 (2.2743)	loss 3.4311 (3.5082)	grad_norm 1.4778 (1.4770)	
[2022-01-22 06:52:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][260/1251]	eta 0:37:31 lr 0.000525	time 2.2803 (2.2723)	loss 2.7178 (3.5129)	grad_norm 1.3040 (1.4787)	
[2022-01-22 06:52:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][270/1251]	eta 0:37:01 lr 0.000525	time 2.7457 (2.2641)	loss 3.3128 (3.5142)	grad_norm 1.4020 (1.4822)	
[2022-01-22 06:53:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][280/1251]	eta 0:36:32 lr 0.000525	time 1.9795 (2.2577)	loss 2.8609 (3.5054)	grad_norm 1.5182 (1.4832)	
[2022-01-22 06:53:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][290/1251]	eta 0:36:09 lr 0.000525	time 2.2990 (2.2576)	loss 3.8928 (3.5065)	grad_norm 1.8767 (1.4875)	
[2022-01-22 06:53:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][300/1251]	eta 0:35:47 lr 0.000524	time 2.7429 (2.2579)	loss 3.0997 (3.5050)	grad_norm 1.6622 (1.4865)	
[2022-01-22 06:54:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][310/1251]	eta 0:35:32 lr 0.000524	time 3.1641 (2.2665)	loss 3.8270 (3.5083)	grad_norm 1.3894 (1.4859)	
[2022-01-22 06:54:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][320/1251]	eta 0:35:09 lr 0.000524	time 2.1096 (2.2656)	loss 4.1217 (3.5096)	grad_norm 1.4179 (1.4860)	
[2022-01-22 06:55:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][330/1251]	eta 0:34:41 lr 0.000524	time 1.6620 (2.2605)	loss 3.6795 (3.5123)	grad_norm 1.5073 (1.4857)	
[2022-01-22 06:55:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][340/1251]	eta 0:34:16 lr 0.000524	time 1.8363 (2.2574)	loss 2.3213 (3.5104)	grad_norm 1.3180 (1.4828)	
[2022-01-22 06:55:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][350/1251]	eta 0:33:49 lr 0.000524	time 2.2506 (2.2526)	loss 2.6322 (3.5126)	grad_norm 1.2709 (1.4798)	
[2022-01-22 06:56:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][360/1251]	eta 0:33:20 lr 0.000524	time 1.6955 (2.2452)	loss 3.3821 (3.5132)	grad_norm 1.5248 (1.4785)	
[2022-01-22 06:56:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][370/1251]	eta 0:32:55 lr 0.000524	time 2.2111 (2.2424)	loss 3.8323 (3.5191)	grad_norm 1.6105 (1.4802)	
[2022-01-22 06:56:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][380/1251]	eta 0:32:30 lr 0.000524	time 1.5903 (2.2396)	loss 3.7210 (3.5221)	grad_norm 1.6873 (1.4836)	
[2022-01-22 06:57:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][390/1251]	eta 0:32:06 lr 0.000524	time 2.4473 (2.2372)	loss 3.6351 (3.5156)	grad_norm 1.8879 (1.4888)	
[2022-01-22 06:57:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][400/1251]	eta 0:31:43 lr 0.000524	time 2.2446 (2.2368)	loss 4.2549 (3.5178)	grad_norm 1.3733 (1.4896)	
[2022-01-22 06:58:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][410/1251]	eta 0:31:24 lr 0.000524	time 2.5086 (2.2412)	loss 2.7384 (3.5072)	grad_norm 1.4512 (1.4888)	
[2022-01-22 06:58:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][420/1251]	eta 0:31:03 lr 0.000524	time 2.1195 (2.2430)	loss 4.0309 (3.5176)	grad_norm 1.4189 (1.4870)	
[2022-01-22 06:58:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][430/1251]	eta 0:30:41 lr 0.000524	time 2.5012 (2.2425)	loss 3.2311 (3.5131)	grad_norm 1.5058 (1.4860)	
[2022-01-22 06:59:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][440/1251]	eta 0:30:16 lr 0.000524	time 1.9013 (2.2400)	loss 3.9267 (3.5164)	grad_norm 1.7528 (1.4868)	
[2022-01-22 06:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][450/1251]	eta 0:29:53 lr 0.000524	time 2.5679 (2.2391)	loss 3.2470 (3.5205)	grad_norm 1.3470 (1.4863)	
[2022-01-22 06:59:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][460/1251]	eta 0:29:28 lr 0.000524	time 1.9323 (2.2352)	loss 3.8080 (3.5167)	grad_norm 1.6052 (1.4854)	
[2022-01-22 07:00:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][470/1251]	eta 0:29:02 lr 0.000524	time 2.0108 (2.2310)	loss 3.7606 (3.5205)	grad_norm 1.4771 (1.4854)	
[2022-01-22 07:00:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][480/1251]	eta 0:28:39 lr 0.000524	time 1.9037 (2.2300)	loss 3.3123 (3.5245)	grad_norm 1.4568 (1.4862)	
[2022-01-22 07:00:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][490/1251]	eta 0:28:16 lr 0.000524	time 2.7393 (2.2290)	loss 3.4750 (3.5273)	grad_norm 1.3545 (1.4842)	
[2022-01-22 07:01:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][500/1251]	eta 0:27:54 lr 0.000524	time 2.3680 (2.2302)	loss 2.4406 (3.5308)	grad_norm 1.2761 (1.4826)	
[2022-01-22 07:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][510/1251]	eta 0:27:32 lr 0.000524	time 2.1625 (2.2305)	loss 2.5578 (3.5312)	grad_norm 1.3395 (1.4829)	
[2022-01-22 07:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][520/1251]	eta 0:27:09 lr 0.000524	time 1.9516 (2.2293)	loss 3.3171 (3.5305)	grad_norm 1.3114 (1.4812)	
[2022-01-22 07:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][530/1251]	eta 0:26:44 lr 0.000524	time 1.6167 (2.2256)	loss 4.1123 (3.5311)	grad_norm 1.3894 (1.4799)	
[2022-01-22 07:02:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][540/1251]	eta 0:26:23 lr 0.000523	time 2.4523 (2.2268)	loss 3.5871 (3.5376)	grad_norm 1.3490 (1.4800)	
[2022-01-22 07:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][550/1251]	eta 0:25:58 lr 0.000523	time 1.8310 (2.2227)	loss 3.2745 (3.5375)	grad_norm 1.3903 (1.4778)	
[2022-01-22 07:03:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][560/1251]	eta 0:25:33 lr 0.000523	time 2.3756 (2.2199)	loss 3.4781 (3.5368)	grad_norm 1.4075 (1.4775)	
[2022-01-22 07:03:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][570/1251]	eta 0:25:09 lr 0.000523	time 2.0893 (2.2167)	loss 3.6965 (3.5358)	grad_norm 1.8630 (1.4793)	
[2022-01-22 07:04:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][580/1251]	eta 0:24:47 lr 0.000523	time 2.2406 (2.2163)	loss 2.4310 (3.5359)	grad_norm 1.3175 (1.4791)	
[2022-01-22 07:04:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][590/1251]	eta 0:24:25 lr 0.000523	time 2.4788 (2.2175)	loss 2.8521 (3.5362)	grad_norm 1.5863 (1.4792)	
[2022-01-22 07:04:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][600/1251]	eta 0:24:03 lr 0.000523	time 2.0659 (2.2169)	loss 4.1710 (3.5392)	grad_norm 1.5576 (1.4809)	
[2022-01-22 07:05:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][610/1251]	eta 0:23:40 lr 0.000523	time 2.4527 (2.2163)	loss 3.7466 (3.5347)	grad_norm 1.5014 (1.4803)	
[2022-01-22 07:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][620/1251]	eta 0:23:20 lr 0.000523	time 2.7957 (2.2201)	loss 3.5334 (3.5337)	grad_norm 1.4664 (1.4796)	
[2022-01-22 07:06:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][630/1251]	eta 0:23:01 lr 0.000523	time 3.6436 (2.2243)	loss 4.3444 (3.5335)	grad_norm 1.7279 (1.4783)	
[2022-01-22 07:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][640/1251]	eta 0:22:39 lr 0.000523	time 2.2004 (2.2245)	loss 3.6809 (3.5366)	grad_norm 1.3811 (1.4774)	
[2022-01-22 07:06:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][650/1251]	eta 0:22:16 lr 0.000523	time 2.2427 (2.2238)	loss 3.8223 (3.5414)	grad_norm 1.6788 (1.4786)	
[2022-01-22 07:07:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][660/1251]	eta 0:21:52 lr 0.000523	time 1.8977 (2.2203)	loss 3.6321 (3.5440)	grad_norm 1.3310 (1.4791)	
[2022-01-22 07:07:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][670/1251]	eta 0:21:29 lr 0.000523	time 1.8348 (2.2190)	loss 2.8109 (3.5445)	grad_norm 1.3733 (1.4794)	
[2022-01-22 07:07:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][680/1251]	eta 0:21:06 lr 0.000523	time 1.9825 (2.2176)	loss 3.8743 (3.5392)	grad_norm 1.3057 (1.4792)	
[2022-01-22 07:08:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][690/1251]	eta 0:20:43 lr 0.000523	time 1.9298 (2.2161)	loss 2.9813 (3.5367)	grad_norm 1.5505 (1.4793)	
[2022-01-22 07:08:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][700/1251]	eta 0:20:21 lr 0.000523	time 2.3593 (2.2163)	loss 2.4205 (3.5379)	grad_norm 1.7715 (1.4793)	
[2022-01-22 07:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][710/1251]	eta 0:20:01 lr 0.000523	time 2.6720 (2.2201)	loss 3.9086 (3.5366)	grad_norm 1.4485 (1.4798)	
[2022-01-22 07:09:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][720/1251]	eta 0:19:39 lr 0.000523	time 1.9005 (2.2205)	loss 3.4724 (3.5341)	grad_norm 1.4711 (1.4797)	
[2022-01-22 07:09:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][730/1251]	eta 0:19:16 lr 0.000523	time 1.9483 (2.2191)	loss 3.7368 (3.5342)	grad_norm 1.4432 (1.4803)	
[2022-01-22 07:10:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][740/1251]	eta 0:18:53 lr 0.000523	time 2.1805 (2.2176)	loss 4.3155 (3.5372)	grad_norm 1.3723 (1.4807)	
[2022-01-22 07:10:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][750/1251]	eta 0:18:31 lr 0.000523	time 3.1880 (2.2183)	loss 3.7478 (3.5366)	grad_norm 1.5096 (1.4812)	
[2022-01-22 07:10:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][760/1251]	eta 0:18:07 lr 0.000523	time 1.7108 (2.2151)	loss 3.8518 (3.5360)	grad_norm 1.7423 (1.4828)	
[2022-01-22 07:11:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][770/1251]	eta 0:17:45 lr 0.000523	time 2.1991 (2.2150)	loss 2.5939 (3.5382)	grad_norm 1.7165 (1.4824)	
[2022-01-22 07:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][780/1251]	eta 0:17:23 lr 0.000522	time 2.3497 (2.2161)	loss 3.2325 (3.5378)	grad_norm 1.4768 (1.4819)	
[2022-01-22 07:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][790/1251]	eta 0:17:01 lr 0.000522	time 2.1324 (2.2149)	loss 3.6277 (3.5366)	grad_norm 1.4242 (1.4816)	
[2022-01-22 07:12:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][800/1251]	eta 0:16:38 lr 0.000522	time 1.6538 (2.2139)	loss 3.5916 (3.5371)	grad_norm 1.5177 (1.4817)	
[2022-01-22 07:12:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][810/1251]	eta 0:16:15 lr 0.000522	time 1.6840 (2.2119)	loss 3.9407 (3.5356)	grad_norm 1.3691 (1.4837)	
[2022-01-22 07:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][820/1251]	eta 0:15:52 lr 0.000522	time 1.9381 (2.2092)	loss 3.4747 (3.5359)	grad_norm 1.6254 (1.4834)	
[2022-01-22 07:13:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][830/1251]	eta 0:15:29 lr 0.000522	time 1.7192 (2.2080)	loss 3.2965 (3.5347)	grad_norm 1.5148 (1.4834)	
[2022-01-22 07:13:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][840/1251]	eta 0:15:07 lr 0.000522	time 2.0890 (2.2072)	loss 3.6400 (3.5326)	grad_norm 1.5563 (1.4828)	
[2022-01-22 07:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][850/1251]	eta 0:14:45 lr 0.000522	time 2.5193 (2.2070)	loss 3.2400 (3.5329)	grad_norm 1.4853 (1.4822)	
[2022-01-22 07:14:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][860/1251]	eta 0:14:23 lr 0.000522	time 1.7818 (2.2088)	loss 4.0382 (3.5342)	grad_norm 1.5604 (1.4821)	
[2022-01-22 07:14:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][870/1251]	eta 0:14:02 lr 0.000522	time 2.2839 (2.2101)	loss 3.9219 (3.5362)	grad_norm 1.3423 (1.4819)	
[2022-01-22 07:15:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][880/1251]	eta 0:13:41 lr 0.000522	time 3.4489 (2.2130)	loss 3.5611 (3.5399)	grad_norm 1.5222 (1.4821)	
[2022-01-22 07:15:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][890/1251]	eta 0:13:18 lr 0.000522	time 2.0187 (2.2130)	loss 3.6219 (3.5402)	grad_norm 1.3576 (1.4815)	
[2022-01-22 07:15:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][900/1251]	eta 0:12:56 lr 0.000522	time 2.2425 (2.2127)	loss 3.0725 (3.5398)	grad_norm 1.5760 (1.4821)	
[2022-01-22 07:16:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][910/1251]	eta 0:12:33 lr 0.000522	time 2.7161 (2.2107)	loss 2.7178 (3.5426)	grad_norm 1.3886 (1.4821)	
[2022-01-22 07:16:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][920/1251]	eta 0:12:11 lr 0.000522	time 2.3307 (2.2099)	loss 3.8528 (3.5435)	grad_norm 1.4436 (1.4819)	
[2022-01-22 07:16:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][930/1251]	eta 0:11:49 lr 0.000522	time 1.8473 (2.2091)	loss 3.6384 (3.5420)	grad_norm 1.3546 (1.4814)	
[2022-01-22 07:17:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][940/1251]	eta 0:11:27 lr 0.000522	time 2.1827 (2.2099)	loss 3.3773 (3.5425)	grad_norm 1.8613 (1.4816)	
[2022-01-22 07:17:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][950/1251]	eta 0:11:05 lr 0.000522	time 3.2021 (2.2104)	loss 2.4498 (3.5420)	grad_norm 1.3067 (1.4809)	
[2022-01-22 07:18:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][960/1251]	eta 0:10:43 lr 0.000522	time 2.4292 (2.2115)	loss 2.7800 (3.5415)	grad_norm 1.3917 (1.4815)	
[2022-01-22 07:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][970/1251]	eta 0:10:21 lr 0.000522	time 1.8592 (2.2106)	loss 3.0890 (3.5416)	grad_norm 1.6114 (1.4814)	
[2022-01-22 07:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][980/1251]	eta 0:09:58 lr 0.000522	time 1.9579 (2.2086)	loss 4.2107 (3.5421)	grad_norm 1.6531 (1.4821)	
[2022-01-22 07:19:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][990/1251]	eta 0:09:35 lr 0.000522	time 2.1526 (2.2063)	loss 2.5469 (3.5423)	grad_norm 1.3800 (1.4817)	
[2022-01-22 07:19:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1000/1251]	eta 0:09:13 lr 0.000522	time 2.5603 (2.2064)	loss 3.9945 (3.5432)	grad_norm 1.4483 (1.4816)	
[2022-01-22 07:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1010/1251]	eta 0:08:51 lr 0.000522	time 2.5200 (2.2068)	loss 2.5093 (3.5424)	grad_norm 1.4855 (1.4815)	
[2022-01-22 07:20:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1020/1251]	eta 0:08:30 lr 0.000522	time 2.2365 (2.2078)	loss 4.1515 (3.5429)	grad_norm 1.4223 (1.4818)	
[2022-01-22 07:20:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1030/1251]	eta 0:08:08 lr 0.000521	time 1.8400 (2.2094)	loss 3.9353 (3.5431)	grad_norm 1.5389 (1.4812)	
[2022-01-22 07:20:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1040/1251]	eta 0:07:45 lr 0.000521	time 2.1472 (2.2076)	loss 2.6457 (3.5420)	grad_norm 1.8524 (1.4818)	
[2022-01-22 07:21:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1050/1251]	eta 0:07:23 lr 0.000521	time 1.8294 (2.2059)	loss 4.0047 (3.5433)	grad_norm 1.4888 (1.4818)	
[2022-01-22 07:21:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1060/1251]	eta 0:07:01 lr 0.000521	time 1.9910 (2.2043)	loss 4.0445 (3.5447)	grad_norm 1.5964 (1.4815)	
[2022-01-22 07:22:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1070/1251]	eta 0:06:39 lr 0.000521	time 2.4994 (2.2051)	loss 3.2997 (3.5411)	grad_norm 1.9248 (1.4815)	
[2022-01-22 07:22:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1080/1251]	eta 0:06:17 lr 0.000521	time 2.5264 (2.2054)	loss 4.0992 (3.5400)	grad_norm 1.5776 (1.4818)	
[2022-01-22 07:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1090/1251]	eta 0:05:54 lr 0.000521	time 2.5386 (2.2045)	loss 4.1396 (3.5431)	grad_norm 1.4270 (1.4816)	
[2022-01-22 07:23:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1100/1251]	eta 0:05:32 lr 0.000521	time 2.2787 (2.2047)	loss 2.3326 (3.5420)	grad_norm 1.3138 (1.4815)	
[2022-01-22 07:23:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1110/1251]	eta 0:05:11 lr 0.000521	time 3.0446 (2.2059)	loss 3.7664 (3.5433)	grad_norm 1.3212 (1.4805)	
[2022-01-22 07:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1120/1251]	eta 0:04:48 lr 0.000521	time 1.8862 (2.2055)	loss 2.8627 (3.5417)	grad_norm 1.5583 (1.4806)	
[2022-01-22 07:24:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1130/1251]	eta 0:04:26 lr 0.000521	time 2.5203 (2.2057)	loss 3.4040 (3.5425)	grad_norm 1.5344 (1.4803)	
[2022-01-22 07:24:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1140/1251]	eta 0:04:04 lr 0.000521	time 1.7580 (2.2045)	loss 4.2172 (3.5429)	grad_norm 1.5229 (1.4805)	
[2022-01-22 07:24:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1150/1251]	eta 0:03:42 lr 0.000521	time 1.9769 (2.2050)	loss 3.5260 (3.5425)	grad_norm 1.4145 (1.4799)	
[2022-01-22 07:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1160/1251]	eta 0:03:20 lr 0.000521	time 1.8305 (2.2050)	loss 3.2841 (3.5422)	grad_norm 1.5776 (1.4796)	
[2022-01-22 07:25:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1170/1251]	eta 0:02:58 lr 0.000521	time 1.8231 (2.2044)	loss 4.2703 (3.5439)	grad_norm 1.3997 (1.4794)	
[2022-01-22 07:26:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1180/1251]	eta 0:02:36 lr 0.000521	time 1.7103 (2.2029)	loss 3.6437 (3.5445)	grad_norm 1.4241 (1.4798)	
[2022-01-22 07:26:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1190/1251]	eta 0:02:14 lr 0.000521	time 1.8916 (2.2044)	loss 3.7892 (3.5448)	grad_norm 1.4413 (1.4810)	
[2022-01-22 07:26:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1200/1251]	eta 0:01:52 lr 0.000521	time 1.7839 (2.2034)	loss 4.3441 (3.5433)	grad_norm 1.7553 (1.4814)	
[2022-01-22 07:27:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1210/1251]	eta 0:01:30 lr 0.000521	time 1.9228 (2.2015)	loss 3.6518 (3.5432)	grad_norm 1.4746 (1.4819)	
[2022-01-22 07:27:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1220/1251]	eta 0:01:08 lr 0.000521	time 2.1143 (2.2006)	loss 4.1238 (3.5442)	grad_norm 1.3935 (1.4824)	
[2022-01-22 07:27:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1230/1251]	eta 0:00:46 lr 0.000521	time 2.3948 (2.1998)	loss 4.1461 (3.5443)	grad_norm 1.4017 (1.4823)	
[2022-01-22 07:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1240/1251]	eta 0:00:24 lr 0.000521	time 1.2991 (2.1986)	loss 2.5875 (3.5445)	grad_norm 1.6919 (1.4829)	
[2022-01-22 07:28:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [146/300][1250/1251]	eta 0:00:02 lr 0.000521	time 1.1934 (2.1930)	loss 3.6267 (3.5437)	grad_norm 1.3022 (1.4825)	
[2022-01-22 07:28:22 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 146 training takes 0:45:43
[2022-01-22 07:28:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.275 (18.275)	Loss 1.0373 (1.0373)	Acc@1 76.367 (76.367)	Acc@5 93.555 (93.555)	
[2022-01-22 07:29:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.975 (3.543)	Loss 0.9938 (1.0380)	Acc@1 77.539 (76.021)	Acc@5 94.141 (93.510)	
[2022-01-22 07:29:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.314 (2.673)	Loss 1.0863 (1.0593)	Acc@1 73.926 (75.521)	Acc@5 93.262 (93.206)	
[2022-01-22 07:29:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.961 (2.273)	Loss 1.1008 (1.0579)	Acc@1 74.902 (75.621)	Acc@5 93.164 (93.177)	
[2022-01-22 07:29:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.764 (2.127)	Loss 1.0840 (1.0615)	Acc@1 75.879 (75.603)	Acc@5 92.090 (93.074)	
[2022-01-22 07:29:57 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.706 Acc@5 93.098
[2022-01-22 07:29:57 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.7%
[2022-01-22 07:29:57 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 75.71%
[2022-01-22 07:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][0/1251]	eta 7:33:03 lr 0.000521	time 21.7298 (21.7298)	loss 3.5780 (3.5780)	grad_norm 1.4563 (1.4563)	
[2022-01-22 07:30:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][10/1251]	eta 1:27:19 lr 0.000521	time 2.8702 (4.2223)	loss 3.0455 (3.2807)	grad_norm 1.3920 (1.4099)	
[2022-01-22 07:31:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][20/1251]	eta 1:07:48 lr 0.000520	time 2.1782 (3.3047)	loss 3.4598 (3.4096)	grad_norm 1.4720 (1.4475)	
[2022-01-22 07:31:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][30/1251]	eta 1:00:41 lr 0.000520	time 1.8350 (2.9821)	loss 3.3781 (3.4690)	grad_norm 1.3694 (1.4488)	
[2022-01-22 07:31:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][40/1251]	eta 0:57:19 lr 0.000520	time 3.4979 (2.8405)	loss 3.9468 (3.4448)	grad_norm 1.3388 (1.4589)	
[2022-01-22 07:32:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][50/1251]	eta 0:54:08 lr 0.000520	time 1.9109 (2.7047)	loss 2.9368 (3.4407)	grad_norm 1.6441 (1.4462)	
[2022-01-22 07:32:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][60/1251]	eta 0:51:17 lr 0.000520	time 1.6390 (2.5842)	loss 2.6941 (3.3957)	grad_norm 1.3943 (1.4537)	
[2022-01-22 07:32:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][70/1251]	eta 0:49:18 lr 0.000520	time 1.8666 (2.5054)	loss 4.5168 (3.4644)	grad_norm 1.4740 (1.4762)	
[2022-01-22 07:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][80/1251]	eta 0:48:13 lr 0.000520	time 2.3237 (2.4710)	loss 3.8192 (3.4856)	grad_norm 1.5979 (1.4716)	
[2022-01-22 07:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][90/1251]	eta 0:47:24 lr 0.000520	time 2.3469 (2.4499)	loss 3.8239 (3.4774)	grad_norm 1.3568 (1.4870)	
[2022-01-22 07:34:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][100/1251]	eta 0:46:21 lr 0.000520	time 1.5151 (2.4168)	loss 3.8489 (3.5089)	grad_norm 1.6212 (1.4884)	
[2022-01-22 07:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][110/1251]	eta 0:45:28 lr 0.000520	time 1.7296 (2.3909)	loss 3.3235 (3.5021)	grad_norm 1.2884 (1.4876)	
[2022-01-22 07:34:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][120/1251]	eta 0:44:59 lr 0.000520	time 2.3053 (2.3870)	loss 2.9310 (3.4850)	grad_norm 1.4852 (1.4918)	
[2022-01-22 07:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][130/1251]	eta 0:44:16 lr 0.000520	time 2.9414 (2.3702)	loss 3.1527 (3.4950)	grad_norm 1.3749 (1.4839)	
[2022-01-22 07:35:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][140/1251]	eta 0:43:27 lr 0.000520	time 1.5660 (2.3474)	loss 3.8516 (3.4840)	grad_norm 1.4158 (1.4842)	
[2022-01-22 07:35:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][150/1251]	eta 0:42:56 lr 0.000520	time 2.0066 (2.3398)	loss 3.3722 (3.4749)	grad_norm 1.3999 (1.4866)	
[2022-01-22 07:36:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][160/1251]	eta 0:42:24 lr 0.000520	time 2.1841 (2.3327)	loss 2.9482 (3.4889)	grad_norm 1.4248 (1.4877)	
[2022-01-22 07:36:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][170/1251]	eta 0:41:59 lr 0.000520	time 3.7656 (2.3306)	loss 3.5292 (3.4920)	grad_norm 1.4483 (1.4885)	
[2022-01-22 07:36:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][180/1251]	eta 0:41:27 lr 0.000520	time 1.9587 (2.3222)	loss 4.1349 (3.5035)	grad_norm 1.3403 (1.4838)	
[2022-01-22 07:37:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][190/1251]	eta 0:40:57 lr 0.000520	time 1.8648 (2.3163)	loss 3.7060 (3.5001)	grad_norm 1.4667 (1.4869)	
[2022-01-22 07:37:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][200/1251]	eta 0:40:23 lr 0.000520	time 1.9619 (2.3057)	loss 3.1272 (3.4938)	grad_norm 1.6242 (1.4915)	
[2022-01-22 07:38:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][210/1251]	eta 0:39:51 lr 0.000520	time 2.9265 (2.2969)	loss 3.7806 (3.4909)	grad_norm 1.5697 (1.4929)	
[2022-01-22 07:38:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][220/1251]	eta 0:39:16 lr 0.000520	time 1.9451 (2.2860)	loss 3.3759 (3.4808)	grad_norm 1.5239 (1.4936)	
[2022-01-22 07:38:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][230/1251]	eta 0:38:47 lr 0.000520	time 2.1258 (2.2795)	loss 3.4272 (3.4895)	grad_norm 1.4887 (1.4939)	
[2022-01-22 07:39:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][240/1251]	eta 0:38:22 lr 0.000520	time 1.9524 (2.2773)	loss 3.2515 (3.4925)	grad_norm 1.5218 (1.4935)	
[2022-01-22 07:39:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][250/1251]	eta 0:37:54 lr 0.000520	time 2.5072 (2.2724)	loss 3.2358 (3.4946)	grad_norm 1.5812 (1.4978)	
[2022-01-22 07:39:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][260/1251]	eta 0:37:28 lr 0.000519	time 2.4683 (2.2689)	loss 3.5724 (3.4863)	grad_norm 1.5069 (1.5000)	
[2022-01-22 07:40:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][270/1251]	eta 0:37:06 lr 0.000519	time 2.7713 (2.2698)	loss 3.2940 (3.4893)	grad_norm 1.3765 (1.5027)	
[2022-01-22 07:40:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][280/1251]	eta 0:36:44 lr 0.000519	time 2.2449 (2.2704)	loss 3.1232 (3.4757)	grad_norm 1.6606 (1.5012)	
[2022-01-22 07:40:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][290/1251]	eta 0:36:21 lr 0.000519	time 2.9066 (2.2703)	loss 2.2715 (3.4772)	grad_norm 1.3468 (1.5007)	
[2022-01-22 07:41:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][300/1251]	eta 0:35:58 lr 0.000519	time 2.5942 (2.2695)	loss 3.4199 (3.4863)	grad_norm 1.3810 (1.4979)	
[2022-01-22 07:41:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][310/1251]	eta 0:35:32 lr 0.000519	time 2.0487 (2.2658)	loss 4.1420 (3.4923)	grad_norm 1.4631 (1.4959)	
[2022-01-22 07:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][320/1251]	eta 0:35:05 lr 0.000519	time 2.5195 (2.2618)	loss 4.0676 (3.4880)	grad_norm 1.4247 (1.4942)	
[2022-01-22 07:42:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][330/1251]	eta 0:34:43 lr 0.000519	time 2.6088 (2.2625)	loss 3.2901 (3.4833)	grad_norm 1.3776 (1.4916)	
[2022-01-22 07:42:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][340/1251]	eta 0:34:15 lr 0.000519	time 1.6126 (2.2559)	loss 2.6721 (3.4840)	grad_norm 1.4785 (1.4910)	
[2022-01-22 07:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][350/1251]	eta 0:33:50 lr 0.000519	time 1.7814 (2.2532)	loss 3.2190 (3.4837)	grad_norm 1.3109 (1.4884)	
[2022-01-22 07:43:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][360/1251]	eta 0:33:26 lr 0.000519	time 2.1692 (2.2521)	loss 4.0373 (3.4876)	grad_norm 1.4110 (1.4875)	
[2022-01-22 07:43:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][370/1251]	eta 0:33:03 lr 0.000519	time 2.2822 (2.2509)	loss 3.7855 (3.4804)	grad_norm 1.4009 (1.4867)	
[2022-01-22 07:44:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][380/1251]	eta 0:32:34 lr 0.000519	time 1.6250 (2.2445)	loss 3.7411 (3.4843)	grad_norm 1.4904 (1.4863)	
[2022-01-22 07:44:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][390/1251]	eta 0:32:10 lr 0.000519	time 2.1714 (2.2417)	loss 3.6966 (3.4797)	grad_norm 1.4957 (1.4876)	
[2022-01-22 07:44:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][400/1251]	eta 0:31:45 lr 0.000519	time 2.7751 (2.2387)	loss 2.5933 (3.4804)	grad_norm 1.7048 (1.4879)	
[2022-01-22 07:45:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][410/1251]	eta 0:31:22 lr 0.000519	time 2.5840 (2.2383)	loss 4.3918 (3.4859)	grad_norm 1.8082 (1.4874)	
[2022-01-22 07:45:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][420/1251]	eta 0:30:56 lr 0.000519	time 1.8932 (2.2341)	loss 3.7668 (3.4932)	grad_norm 1.4339 (1.4859)	
[2022-01-22 07:46:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][430/1251]	eta 0:30:38 lr 0.000519	time 2.2981 (2.2394)	loss 3.7630 (3.4996)	grad_norm 1.5049 (1.4864)	
[2022-01-22 07:46:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][440/1251]	eta 0:30:25 lr 0.000519	time 4.8734 (2.2505)	loss 3.8622 (3.5056)	grad_norm 1.5234 (1.4861)	
[2022-01-22 07:46:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][450/1251]	eta 0:30:00 lr 0.000519	time 2.1881 (2.2476)	loss 3.9980 (3.5067)	grad_norm 1.6297 (1.4859)	
[2022-01-22 07:47:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][460/1251]	eta 0:29:34 lr 0.000519	time 1.6366 (2.2433)	loss 3.6928 (3.5093)	grad_norm 1.5623 (1.4856)	
[2022-01-22 07:47:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][470/1251]	eta 0:29:08 lr 0.000519	time 1.9030 (2.2392)	loss 2.5781 (3.5054)	grad_norm 1.5351 (1.4855)	
[2022-01-22 07:47:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][480/1251]	eta 0:28:47 lr 0.000519	time 4.1354 (2.2406)	loss 2.6143 (3.5011)	grad_norm 1.5980 (1.4857)	
[2022-01-22 07:48:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][490/1251]	eta 0:28:28 lr 0.000519	time 2.4585 (2.2445)	loss 3.8111 (3.5022)	grad_norm 1.3998 (1.4883)	
[2022-01-22 07:48:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][500/1251]	eta 0:28:04 lr 0.000518	time 1.6255 (2.2436)	loss 3.7210 (3.4994)	grad_norm 1.3456 (1.4887)	
[2022-01-22 07:49:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][510/1251]	eta 0:27:40 lr 0.000518	time 2.2745 (2.2402)	loss 3.8644 (3.5037)	grad_norm 1.6441 (1.4894)	
[2022-01-22 07:49:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][520/1251]	eta 0:27:14 lr 0.000518	time 2.8389 (2.2357)	loss 4.2239 (3.5032)	grad_norm 1.4904 (1.4893)	
[2022-01-22 07:49:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][530/1251]	eta 0:26:50 lr 0.000518	time 1.9612 (2.2332)	loss 4.0479 (3.5021)	grad_norm 2.0196 (1.4909)	
[2022-01-22 07:50:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][540/1251]	eta 0:26:25 lr 0.000518	time 1.9303 (2.2293)	loss 3.9156 (3.5033)	grad_norm 1.2535 (1.4937)	
[2022-01-22 07:50:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][550/1251]	eta 0:26:02 lr 0.000518	time 3.0812 (2.2285)	loss 3.7977 (3.5072)	grad_norm 1.5564 (1.4932)	
[2022-01-22 07:50:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][560/1251]	eta 0:25:39 lr 0.000518	time 1.5488 (2.2284)	loss 3.9709 (3.5118)	grad_norm 1.3633 (1.4957)	
[2022-01-22 07:51:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][570/1251]	eta 0:25:16 lr 0.000518	time 2.2891 (2.2274)	loss 4.3641 (3.5130)	grad_norm 1.4187 (1.4954)	
[2022-01-22 07:51:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][580/1251]	eta 0:24:53 lr 0.000518	time 1.8776 (2.2260)	loss 3.7496 (3.5106)	grad_norm 1.3502 (1.4942)	
[2022-01-22 07:51:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][590/1251]	eta 0:24:32 lr 0.000518	time 3.5510 (2.2275)	loss 3.5999 (3.5129)	grad_norm 1.4300 (1.4944)	
[2022-01-22 07:52:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][600/1251]	eta 0:24:07 lr 0.000518	time 1.3467 (2.2239)	loss 2.8239 (3.5126)	grad_norm 1.2893 (1.4940)	
[2022-01-22 07:52:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][610/1251]	eta 0:23:46 lr 0.000518	time 3.9776 (2.2260)	loss 2.5758 (3.5143)	grad_norm 1.4111 (1.4957)	
[2022-01-22 07:53:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][620/1251]	eta 0:23:25 lr 0.000518	time 1.5562 (2.2267)	loss 3.2725 (3.5187)	grad_norm 1.5499 (1.4943)	
[2022-01-22 07:53:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][630/1251]	eta 0:23:04 lr 0.000518	time 3.1805 (2.2289)	loss 4.0437 (3.5211)	grad_norm 1.4789 (1.4942)	
[2022-01-22 07:53:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][640/1251]	eta 0:22:41 lr 0.000518	time 1.5135 (2.2281)	loss 3.5467 (3.5225)	grad_norm 1.3410 (1.4941)	
[2022-01-22 07:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][650/1251]	eta 0:22:20 lr 0.000518	time 3.3529 (2.2311)	loss 2.5265 (3.5181)	grad_norm 1.4378 (1.4939)	
[2022-01-22 07:54:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][660/1251]	eta 0:21:58 lr 0.000518	time 1.8573 (2.2309)	loss 3.5020 (3.5186)	grad_norm 1.5382 (1.4943)	
[2022-01-22 07:54:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][670/1251]	eta 0:21:35 lr 0.000518	time 2.8566 (2.2303)	loss 4.2115 (3.5198)	grad_norm 1.5935 (1.4948)	
[2022-01-22 07:55:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][680/1251]	eta 0:21:11 lr 0.000518	time 2.2771 (2.2262)	loss 2.8750 (3.5165)	grad_norm 1.9367 (1.4955)	
[2022-01-22 07:55:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][690/1251]	eta 0:20:46 lr 0.000518	time 1.7778 (2.2215)	loss 3.6843 (3.5126)	grad_norm 1.6914 (1.4959)	
[2022-01-22 07:55:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][700/1251]	eta 0:20:22 lr 0.000518	time 2.1697 (2.2184)	loss 4.1011 (3.5116)	grad_norm 1.7336 (1.4957)	
[2022-01-22 07:56:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][710/1251]	eta 0:19:59 lr 0.000518	time 1.9785 (2.2172)	loss 2.5212 (3.5140)	grad_norm 1.7832 (1.4953)	
[2022-01-22 07:56:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][720/1251]	eta 0:19:37 lr 0.000518	time 2.8666 (2.2170)	loss 3.6666 (3.5179)	grad_norm 1.6919 (1.4967)	
[2022-01-22 07:56:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][730/1251]	eta 0:19:16 lr 0.000518	time 1.8988 (2.2193)	loss 3.8102 (3.5194)	grad_norm 1.3246 (1.4966)	
[2022-01-22 07:57:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][740/1251]	eta 0:18:53 lr 0.000517	time 2.4883 (2.2183)	loss 4.3264 (3.5229)	grad_norm 1.6275 (1.4985)	
[2022-01-22 07:57:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][750/1251]	eta 0:18:31 lr 0.000517	time 2.2042 (2.2192)	loss 3.2867 (3.5282)	grad_norm 1.4420 (1.5001)	
[2022-01-22 07:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][760/1251]	eta 0:18:10 lr 0.000517	time 2.4938 (2.2219)	loss 3.9357 (3.5313)	grad_norm 1.4334 (1.5003)	
[2022-01-22 07:58:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][770/1251]	eta 0:17:49 lr 0.000517	time 2.2241 (2.2228)	loss 3.9373 (3.5317)	grad_norm 1.8070 (1.5008)	
[2022-01-22 07:58:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][780/1251]	eta 0:17:27 lr 0.000517	time 2.5250 (2.2235)	loss 2.3921 (3.5312)	grad_norm 1.3380 (1.5011)	
[2022-01-22 07:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][790/1251]	eta 0:17:04 lr 0.000517	time 1.9142 (2.2218)	loss 2.9142 (3.5322)	grad_norm 1.3632 (1.5014)	
[2022-01-22 07:59:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][800/1251]	eta 0:16:40 lr 0.000517	time 2.1912 (2.2187)	loss 3.9258 (3.5318)	grad_norm 1.4963 (1.5010)	
[2022-01-22 07:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][810/1251]	eta 0:16:17 lr 0.000517	time 1.9151 (2.2155)	loss 3.4182 (3.5330)	grad_norm 1.4282 (1.5020)	
[2022-01-22 08:00:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][820/1251]	eta 0:15:54 lr 0.000517	time 2.2725 (2.2145)	loss 4.6176 (3.5384)	grad_norm 1.7980 (1.5024)	
[2022-01-22 08:00:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][830/1251]	eta 0:15:32 lr 0.000517	time 2.8476 (2.2159)	loss 3.7794 (3.5360)	grad_norm 1.5476 (1.5032)	
[2022-01-22 08:01:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][840/1251]	eta 0:15:10 lr 0.000517	time 2.1668 (2.2152)	loss 4.0406 (3.5367)	grad_norm 1.4622 (1.5026)	
[2022-01-22 08:01:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][850/1251]	eta 0:14:49 lr 0.000517	time 2.8002 (2.2183)	loss 3.7503 (3.5376)	grad_norm 1.4874 (1.5020)	
[2022-01-22 08:01:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][860/1251]	eta 0:14:27 lr 0.000517	time 1.9787 (2.2194)	loss 3.4194 (3.5382)	grad_norm 1.3248 (1.5019)	
[2022-01-22 08:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][870/1251]	eta 0:14:04 lr 0.000517	time 1.9030 (2.2177)	loss 3.5628 (3.5378)	grad_norm 1.3150 (1.5005)	
[2022-01-22 08:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][880/1251]	eta 0:13:42 lr 0.000517	time 2.3159 (2.2156)	loss 4.2530 (3.5405)	grad_norm 1.5928 (1.5003)	
[2022-01-22 08:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][890/1251]	eta 0:13:18 lr 0.000517	time 1.9380 (2.2133)	loss 3.2471 (3.5404)	grad_norm 1.4107 (1.4997)	
[2022-01-22 08:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][900/1251]	eta 0:12:56 lr 0.000517	time 1.9525 (2.2131)	loss 3.7958 (3.5399)	grad_norm 1.6230 (1.4987)	
[2022-01-22 08:03:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][910/1251]	eta 0:12:34 lr 0.000517	time 2.2327 (2.2128)	loss 3.8450 (3.5396)	grad_norm 1.3957 (1.4972)	
[2022-01-22 08:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][920/1251]	eta 0:12:12 lr 0.000517	time 1.8582 (2.2140)	loss 3.6352 (3.5387)	grad_norm 1.3801 (1.4967)	
[2022-01-22 08:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][930/1251]	eta 0:11:50 lr 0.000517	time 1.7126 (2.2127)	loss 2.9930 (3.5373)	grad_norm 1.6528 (1.4959)	
[2022-01-22 08:04:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][940/1251]	eta 0:11:27 lr 0.000517	time 1.8180 (2.2122)	loss 3.8313 (3.5368)	grad_norm 1.5728 (1.4958)	
[2022-01-22 08:05:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][950/1251]	eta 0:11:06 lr 0.000517	time 3.4932 (2.2127)	loss 2.6650 (3.5361)	grad_norm 1.5252 (1.4959)	
[2022-01-22 08:05:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][960/1251]	eta 0:10:44 lr 0.000517	time 2.4663 (2.2135)	loss 3.5610 (3.5308)	grad_norm 1.4811 (1.4949)	
[2022-01-22 08:05:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][970/1251]	eta 0:10:21 lr 0.000517	time 1.8237 (2.2133)	loss 3.8057 (3.5300)	grad_norm 1.4440 (1.4945)	
[2022-01-22 08:06:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][980/1251]	eta 0:10:00 lr 0.000516	time 2.9555 (2.2146)	loss 3.8418 (3.5297)	grad_norm 1.5140 (1.4938)	
[2022-01-22 08:06:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][990/1251]	eta 0:09:38 lr 0.000516	time 3.2016 (2.2152)	loss 2.4634 (3.5316)	grad_norm 1.6031 (1.4934)	
[2022-01-22 08:06:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1000/1251]	eta 0:09:15 lr 0.000516	time 1.6707 (2.2139)	loss 3.1460 (3.5316)	grad_norm 1.3252 (1.4927)	
[2022-01-22 08:07:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1010/1251]	eta 0:08:53 lr 0.000516	time 1.9250 (2.2128)	loss 2.8459 (3.5330)	grad_norm 1.4363 (1.4937)	
[2022-01-22 08:07:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1020/1251]	eta 0:08:30 lr 0.000516	time 2.1009 (2.2111)	loss 4.2943 (3.5335)	grad_norm 1.4842 (1.4947)	
[2022-01-22 08:07:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1030/1251]	eta 0:08:08 lr 0.000516	time 3.7202 (2.2117)	loss 3.9774 (3.5334)	grad_norm 1.5253 (1.4947)	
[2022-01-22 08:08:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1040/1251]	eta 0:07:46 lr 0.000516	time 2.1852 (2.2126)	loss 4.2974 (3.5328)	grad_norm 1.3859 (1.4941)	
[2022-01-22 08:08:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1050/1251]	eta 0:07:25 lr 0.000516	time 2.0616 (2.2141)	loss 3.7841 (3.5339)	grad_norm 1.7234 (1.4942)	
[2022-01-22 08:09:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1060/1251]	eta 0:07:02 lr 0.000516	time 1.9955 (2.2126)	loss 3.3303 (3.5313)	grad_norm 1.6582 (1.4938)	
[2022-01-22 08:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1070/1251]	eta 0:06:40 lr 0.000516	time 3.6538 (2.2131)	loss 3.7710 (3.5303)	grad_norm 1.2787 (1.4930)	
[2022-01-22 08:09:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1080/1251]	eta 0:06:18 lr 0.000516	time 2.0134 (2.2121)	loss 3.2359 (3.5305)	grad_norm 1.3864 (1.4934)	
[2022-01-22 08:10:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1090/1251]	eta 0:05:56 lr 0.000516	time 2.5333 (2.2149)	loss 3.0159 (3.5307)	grad_norm 1.4597 (1.4929)	
[2022-01-22 08:10:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1100/1251]	eta 0:05:34 lr 0.000516	time 2.0012 (2.2146)	loss 3.6753 (3.5311)	grad_norm 1.2945 (1.4917)	
[2022-01-22 08:10:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1110/1251]	eta 0:05:12 lr 0.000516	time 2.2016 (2.2140)	loss 4.1464 (3.5312)	grad_norm 1.3978 (1.4908)	
[2022-01-22 08:11:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1120/1251]	eta 0:04:49 lr 0.000516	time 1.6383 (2.2126)	loss 2.9060 (3.5303)	grad_norm 1.4767 (1.4905)	
[2022-01-22 08:11:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1130/1251]	eta 0:04:27 lr 0.000516	time 2.5030 (2.2124)	loss 4.1459 (3.5298)	grad_norm 1.2690 (1.4899)	
[2022-01-22 08:12:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1140/1251]	eta 0:04:05 lr 0.000516	time 2.0995 (2.2110)	loss 4.0957 (3.5295)	grad_norm 1.4139 (1.4890)	
[2022-01-22 08:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1150/1251]	eta 0:03:43 lr 0.000516	time 2.5783 (2.2106)	loss 3.7413 (3.5309)	grad_norm 1.4766 (1.4891)	
[2022-01-22 08:12:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1160/1251]	eta 0:03:21 lr 0.000516	time 1.5644 (2.2088)	loss 3.6083 (3.5321)	grad_norm 1.5994 (1.4893)	
[2022-01-22 08:13:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1170/1251]	eta 0:02:58 lr 0.000516	time 1.9630 (2.2091)	loss 4.4895 (3.5343)	grad_norm 1.5809 (1.4892)	
[2022-01-22 08:13:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1180/1251]	eta 0:02:36 lr 0.000516	time 1.8872 (2.2099)	loss 4.1096 (3.5351)	grad_norm 1.4238 (1.4886)	
[2022-01-22 08:13:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1190/1251]	eta 0:02:14 lr 0.000516	time 2.8398 (2.2101)	loss 3.9588 (3.5345)	grad_norm 1.4699 (1.4888)	
[2022-01-22 08:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1200/1251]	eta 0:01:52 lr 0.000516	time 2.0520 (2.2089)	loss 3.4141 (3.5340)	grad_norm 1.5619 (1.4895)	
[2022-01-22 08:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1210/1251]	eta 0:01:30 lr 0.000516	time 1.9021 (2.2094)	loss 2.8216 (3.5344)	grad_norm 1.4194 (1.4893)	
[2022-01-22 08:14:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1220/1251]	eta 0:01:08 lr 0.000515	time 1.9020 (2.2086)	loss 3.3482 (3.5352)	grad_norm 1.5058 (1.4902)	
[2022-01-22 08:15:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1230/1251]	eta 0:00:46 lr 0.000515	time 2.2382 (2.2081)	loss 2.8273 (3.5334)	grad_norm 1.3632 (1.4900)	
[2022-01-22 08:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1240/1251]	eta 0:00:24 lr 0.000515	time 1.5406 (2.2071)	loss 3.0760 (3.5337)	grad_norm 1.4372 (1.4894)	
[2022-01-22 08:15:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [147/300][1250/1251]	eta 0:00:02 lr 0.000515	time 1.1880 (2.2010)	loss 3.9091 (3.5357)	grad_norm 1.3738 (1.4888)	
[2022-01-22 08:15:51 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 147 training takes 0:45:53
[2022-01-22 08:16:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.885 (18.885)	Loss 1.0742 (1.0742)	Acc@1 75.195 (75.195)	Acc@5 92.383 (92.383)	
[2022-01-22 08:16:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.976 (3.544)	Loss 1.0150 (1.0199)	Acc@1 76.758 (75.977)	Acc@5 93.262 (93.510)	
[2022-01-22 08:16:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.244 (2.602)	Loss 1.0977 (1.0269)	Acc@1 73.828 (75.902)	Acc@5 91.406 (93.308)	
[2022-01-22 08:17:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.203 (2.307)	Loss 1.0628 (1.0347)	Acc@1 77.246 (75.973)	Acc@5 92.383 (93.126)	
[2022-01-22 08:17:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.341 (2.141)	Loss 1.0619 (1.0387)	Acc@1 75.195 (75.912)	Acc@5 92.676 (93.107)	
[2022-01-22 08:17:26 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.996 Acc@5 93.148
[2022-01-22 08:17:26 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.0%
[2022-01-22 08:17:26 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.00%
[2022-01-22 08:17:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][0/1251]	eta 7:42:27 lr 0.000515	time 22.1804 (22.1804)	loss 3.3837 (3.3837)	grad_norm 1.5331 (1.5331)	
[2022-01-22 08:18:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][10/1251]	eta 1:24:41 lr 0.000515	time 1.8639 (4.0947)	loss 3.6210 (3.6955)	grad_norm 1.4473 (1.4957)	
[2022-01-22 08:18:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][20/1251]	eta 1:03:28 lr 0.000515	time 1.2651 (3.0934)	loss 4.1688 (3.7112)	grad_norm 1.5645 (1.5185)	
[2022-01-22 08:18:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][30/1251]	eta 0:57:07 lr 0.000515	time 1.8379 (2.8068)	loss 3.9763 (3.6666)	grad_norm 1.5796 (1.5134)	
[2022-01-22 08:19:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][40/1251]	eta 0:53:38 lr 0.000515	time 3.1026 (2.6580)	loss 4.0495 (3.6216)	grad_norm 1.3830 (1.5307)	
[2022-01-22 08:19:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][50/1251]	eta 0:51:59 lr 0.000515	time 1.9608 (2.5976)	loss 3.5271 (3.6142)	grad_norm 1.5323 (1.5079)	
[2022-01-22 08:19:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][60/1251]	eta 0:49:40 lr 0.000515	time 1.1514 (2.5021)	loss 3.0609 (3.5990)	grad_norm 1.5044 (1.5019)	
[2022-01-22 08:20:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][70/1251]	eta 0:48:44 lr 0.000515	time 1.8472 (2.4759)	loss 4.0884 (3.5833)	grad_norm 1.3950 (1.5079)	
[2022-01-22 08:20:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][80/1251]	eta 0:47:58 lr 0.000515	time 3.4580 (2.4585)	loss 4.0415 (3.5815)	grad_norm 1.5095 (1.5195)	
[2022-01-22 08:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][90/1251]	eta 0:47:15 lr 0.000515	time 2.1500 (2.4424)	loss 3.8182 (3.5974)	grad_norm 1.6614 (1.5144)	
[2022-01-22 08:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][100/1251]	eta 0:46:15 lr 0.000515	time 1.5110 (2.4118)	loss 2.4061 (3.5657)	grad_norm 1.6355 (1.5122)	
[2022-01-22 08:21:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][110/1251]	eta 0:45:33 lr 0.000515	time 1.8942 (2.3961)	loss 3.9251 (3.5549)	grad_norm 1.2940 (1.5055)	
[2022-01-22 08:22:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][120/1251]	eta 0:44:47 lr 0.000515	time 2.4451 (2.3759)	loss 3.4490 (3.5547)	grad_norm 1.6482 (1.5015)	
[2022-01-22 08:22:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][130/1251]	eta 0:44:21 lr 0.000515	time 3.0810 (2.3740)	loss 3.5801 (3.5653)	grad_norm 1.5919 (1.5013)	
[2022-01-22 08:22:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][140/1251]	eta 0:43:34 lr 0.000515	time 1.7526 (2.3537)	loss 3.3452 (3.5646)	grad_norm 1.6130 (1.4946)	
[2022-01-22 08:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][150/1251]	eta 0:42:56 lr 0.000515	time 1.8573 (2.3399)	loss 2.3510 (3.5466)	grad_norm 1.2340 (1.4878)	
[2022-01-22 08:23:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][160/1251]	eta 0:42:15 lr 0.000515	time 2.0789 (2.3242)	loss 2.7701 (3.5265)	grad_norm 1.4163 (1.4846)	
[2022-01-22 08:24:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][170/1251]	eta 0:41:39 lr 0.000515	time 2.1843 (2.3125)	loss 3.1778 (3.5210)	grad_norm 1.4382 (1.4840)	
[2022-01-22 08:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][180/1251]	eta 0:41:04 lr 0.000515	time 1.8968 (2.3015)	loss 3.7121 (3.5286)	grad_norm 1.5262 (1.4801)	
[2022-01-22 08:24:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][190/1251]	eta 0:40:34 lr 0.000515	time 2.3679 (2.2949)	loss 3.6281 (3.5280)	grad_norm 1.5188 (1.4806)	
[2022-01-22 08:25:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][200/1251]	eta 0:40:02 lr 0.000515	time 2.4252 (2.2858)	loss 3.9516 (3.5289)	grad_norm 1.5696 (1.4794)	
[2022-01-22 08:25:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][210/1251]	eta 0:39:40 lr 0.000514	time 1.6125 (2.2870)	loss 3.9745 (3.5277)	grad_norm 1.4504 (1.4821)	
[2022-01-22 08:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][220/1251]	eta 0:39:20 lr 0.000514	time 2.2323 (2.2898)	loss 3.7299 (3.5314)	grad_norm 1.3212 (1.4812)	
[2022-01-22 08:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][230/1251]	eta 0:38:56 lr 0.000514	time 1.5440 (2.2883)	loss 3.6741 (3.5262)	grad_norm 1.8405 (1.4845)	
[2022-01-22 08:26:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][240/1251]	eta 0:38:25 lr 0.000514	time 1.6202 (2.2804)	loss 3.6168 (3.5131)	grad_norm 1.3997 (1.4841)	
[2022-01-22 08:26:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][250/1251]	eta 0:37:54 lr 0.000514	time 1.9306 (2.2718)	loss 4.1508 (3.5108)	grad_norm 1.5494 (1.4860)	
[2022-01-22 08:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][260/1251]	eta 0:37:22 lr 0.000514	time 1.9453 (2.2631)	loss 3.9293 (3.5236)	grad_norm 1.8053 (1.4899)	
[2022-01-22 08:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][270/1251]	eta 0:36:54 lr 0.000514	time 1.9499 (2.2570)	loss 3.9329 (3.5251)	grad_norm 1.4471 (1.4912)	
[2022-01-22 08:27:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][280/1251]	eta 0:36:23 lr 0.000514	time 1.9037 (2.2486)	loss 3.8154 (3.5185)	grad_norm 1.3835 (1.4919)	
[2022-01-22 08:28:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][290/1251]	eta 0:35:58 lr 0.000514	time 2.4742 (2.2462)	loss 3.8021 (3.5212)	grad_norm 1.3116 (1.4907)	
[2022-01-22 08:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][300/1251]	eta 0:35:34 lr 0.000514	time 2.3980 (2.2445)	loss 4.0487 (3.5114)	grad_norm 1.5254 (1.4905)	
[2022-01-22 08:29:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][310/1251]	eta 0:35:12 lr 0.000514	time 1.6085 (2.2448)	loss 3.9587 (3.5158)	grad_norm 1.6046 (1.4917)	
[2022-01-22 08:29:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][320/1251]	eta 0:34:49 lr 0.000514	time 2.3309 (2.2439)	loss 4.1172 (3.5210)	grad_norm 1.5672 (1.4916)	
[2022-01-22 08:29:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][330/1251]	eta 0:34:27 lr 0.000514	time 2.4949 (2.2449)	loss 4.2061 (3.5294)	grad_norm 1.5554 (1.4929)	
[2022-01-22 08:30:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][340/1251]	eta 0:34:06 lr 0.000514	time 1.6620 (2.2467)	loss 3.8793 (3.5217)	grad_norm 1.7174 (1.4925)	
[2022-01-22 08:30:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][350/1251]	eta 0:33:45 lr 0.000514	time 2.2191 (2.2484)	loss 3.9730 (3.5308)	grad_norm 1.2954 (1.4900)	
[2022-01-22 08:30:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][360/1251]	eta 0:33:21 lr 0.000514	time 2.5241 (2.2464)	loss 4.0545 (3.5252)	grad_norm 1.3008 (1.4883)	
[2022-01-22 08:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][370/1251]	eta 0:32:58 lr 0.000514	time 3.3792 (2.2462)	loss 3.8336 (3.5188)	grad_norm 1.4609 (1.4901)	
[2022-01-22 08:31:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][380/1251]	eta 0:32:33 lr 0.000514	time 1.8546 (2.2426)	loss 3.5863 (3.5273)	grad_norm 1.4358 (1.4895)	
[2022-01-22 08:32:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][390/1251]	eta 0:32:09 lr 0.000514	time 2.0296 (2.2407)	loss 4.1386 (3.5281)	grad_norm 2.0329 (1.4907)	
[2022-01-22 08:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][400/1251]	eta 0:31:44 lr 0.000514	time 1.9796 (2.2379)	loss 4.3735 (3.5314)	grad_norm 1.7206 (1.4909)	
[2022-01-22 08:32:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][410/1251]	eta 0:31:20 lr 0.000514	time 2.1882 (2.2363)	loss 3.9675 (3.5269)	grad_norm 1.5757 (1.4910)	
[2022-01-22 08:33:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][420/1251]	eta 0:31:00 lr 0.000514	time 2.3311 (2.2390)	loss 2.8691 (3.5250)	grad_norm 1.5148 (1.4897)	
[2022-01-22 08:33:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][430/1251]	eta 0:30:36 lr 0.000514	time 1.4629 (2.2372)	loss 3.0739 (3.5241)	grad_norm 1.6958 (1.4897)	
[2022-01-22 08:33:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][440/1251]	eta 0:30:12 lr 0.000514	time 1.5582 (2.2347)	loss 3.4119 (3.5237)	grad_norm 1.8780 (1.4924)	
[2022-01-22 08:34:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][450/1251]	eta 0:29:45 lr 0.000514	time 2.0185 (2.2293)	loss 4.1447 (3.5191)	grad_norm 1.6762 (1.4954)	
[2022-01-22 08:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][460/1251]	eta 0:29:20 lr 0.000513	time 1.6659 (2.2259)	loss 4.0186 (3.5235)	grad_norm 1.4103 (1.4968)	
[2022-01-22 08:34:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][470/1251]	eta 0:28:57 lr 0.000513	time 1.6056 (2.2243)	loss 4.1411 (3.5274)	grad_norm 1.5638 (1.4956)	
[2022-01-22 08:35:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][480/1251]	eta 0:28:37 lr 0.000513	time 2.3192 (2.2276)	loss 3.9730 (3.5286)	grad_norm 1.3795 (1.4972)	
[2022-01-22 08:35:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][490/1251]	eta 0:28:13 lr 0.000513	time 2.1286 (2.2251)	loss 3.3877 (3.5286)	grad_norm 1.3462 (1.4946)	
[2022-01-22 08:36:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][500/1251]	eta 0:27:51 lr 0.000513	time 2.2378 (2.2252)	loss 3.5462 (3.5315)	grad_norm 1.3310 (1.4937)	
[2022-01-22 08:36:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][510/1251]	eta 0:27:26 lr 0.000513	time 1.5305 (2.2221)	loss 3.8850 (3.5329)	grad_norm 1.3184 (1.4940)	
[2022-01-22 08:36:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][520/1251]	eta 0:27:01 lr 0.000513	time 1.8495 (2.2177)	loss 4.2585 (3.5358)	grad_norm 1.3806 (1.4945)	
[2022-01-22 08:37:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][530/1251]	eta 0:26:38 lr 0.000513	time 2.1568 (2.2172)	loss 4.0248 (3.5348)	grad_norm 1.4433 (1.4926)	
[2022-01-22 08:37:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][540/1251]	eta 0:26:17 lr 0.000513	time 2.5647 (2.2185)	loss 3.5986 (3.5357)	grad_norm 1.5241 (1.4949)	
[2022-01-22 08:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][550/1251]	eta 0:25:54 lr 0.000513	time 2.0621 (2.2176)	loss 2.5033 (3.5326)	grad_norm 1.4426 (1.4943)	
[2022-01-22 08:38:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][560/1251]	eta 0:25:31 lr 0.000513	time 1.9403 (2.2160)	loss 3.5814 (3.5368)	grad_norm 1.6245 (1.4945)	
[2022-01-22 08:38:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][570/1251]	eta 0:25:08 lr 0.000513	time 1.9072 (2.2144)	loss 4.1246 (3.5397)	grad_norm 1.8157 (1.4960)	
[2022-01-22 08:38:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][580/1251]	eta 0:24:45 lr 0.000513	time 2.5779 (2.2137)	loss 3.3966 (3.5474)	grad_norm 1.2502 (1.4950)	
[2022-01-22 08:39:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][590/1251]	eta 0:24:23 lr 0.000513	time 1.6120 (2.2139)	loss 3.9072 (3.5449)	grad_norm 1.3862 (1.4947)	
[2022-01-22 08:39:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][600/1251]	eta 0:24:01 lr 0.000513	time 1.8795 (2.2137)	loss 4.3558 (3.5457)	grad_norm 1.5301 (1.4946)	
[2022-01-22 08:39:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][610/1251]	eta 0:23:39 lr 0.000513	time 2.4172 (2.2153)	loss 4.1404 (3.5460)	grad_norm 1.4324 (1.4944)	
[2022-01-22 08:40:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][620/1251]	eta 0:23:19 lr 0.000513	time 3.1507 (2.2179)	loss 3.8900 (3.5415)	grad_norm 1.6941 (1.4949)	
[2022-01-22 08:40:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][630/1251]	eta 0:22:56 lr 0.000513	time 2.2765 (2.2165)	loss 3.8822 (3.5386)	grad_norm 1.7524 (1.4956)	
[2022-01-22 08:41:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][640/1251]	eta 0:22:33 lr 0.000513	time 1.6202 (2.2151)	loss 3.9931 (3.5378)	grad_norm 1.3696 (1.4977)	
[2022-01-22 08:41:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][650/1251]	eta 0:22:10 lr 0.000513	time 1.9485 (2.2145)	loss 4.3853 (3.5450)	grad_norm 1.4255 (1.4983)	
[2022-01-22 08:41:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][660/1251]	eta 0:21:48 lr 0.000513	time 2.4600 (2.2140)	loss 2.9981 (3.5412)	grad_norm 1.3972 (1.4993)	
[2022-01-22 08:42:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][670/1251]	eta 0:21:26 lr 0.000513	time 2.1759 (2.2137)	loss 3.8564 (3.5393)	grad_norm 1.4239 (1.5003)	
[2022-01-22 08:42:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][680/1251]	eta 0:21:04 lr 0.000513	time 1.6122 (2.2139)	loss 3.1756 (3.5435)	grad_norm 1.5132 (1.5016)	
[2022-01-22 08:42:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][690/1251]	eta 0:20:40 lr 0.000513	time 2.2397 (2.2115)	loss 3.6792 (3.5413)	grad_norm 1.5269 (1.5016)	
[2022-01-22 08:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][700/1251]	eta 0:20:18 lr 0.000512	time 2.2160 (2.2113)	loss 3.6527 (3.5426)	grad_norm 1.5875 (1.5012)	
[2022-01-22 08:43:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][710/1251]	eta 0:19:56 lr 0.000512	time 2.4911 (2.2121)	loss 3.6738 (3.5433)	grad_norm 1.4351 (1.5014)	
[2022-01-22 08:44:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][720/1251]	eta 0:19:34 lr 0.000512	time 1.8772 (2.2124)	loss 3.8086 (3.5445)	grad_norm 1.3883 (1.5011)	
[2022-01-22 08:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][730/1251]	eta 0:19:11 lr 0.000512	time 2.8378 (2.2109)	loss 3.1469 (3.5440)	grad_norm 1.5143 (1.5011)	
[2022-01-22 08:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][740/1251]	eta 0:18:48 lr 0.000512	time 1.9628 (2.2094)	loss 2.6127 (3.5409)	grad_norm 1.5403 (1.5006)	
[2022-01-22 08:45:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][750/1251]	eta 0:18:25 lr 0.000512	time 1.8829 (2.2075)	loss 3.8723 (3.5403)	grad_norm 1.3726 (1.5002)	
[2022-01-22 08:45:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][760/1251]	eta 0:18:03 lr 0.000512	time 2.1531 (2.2073)	loss 4.1599 (3.5391)	grad_norm 1.5227 (1.4996)	
[2022-01-22 08:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][770/1251]	eta 0:17:40 lr 0.000512	time 1.5650 (2.2052)	loss 4.4022 (3.5388)	grad_norm 1.5262 (1.5002)	
[2022-01-22 08:46:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][780/1251]	eta 0:17:19 lr 0.000512	time 2.4617 (2.2063)	loss 3.3258 (3.5365)	grad_norm 1.6592 (1.5016)	
[2022-01-22 08:46:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][790/1251]	eta 0:16:56 lr 0.000512	time 1.4949 (2.2058)	loss 3.5715 (3.5390)	grad_norm 1.2745 (1.5009)	
[2022-01-22 08:46:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][800/1251]	eta 0:16:35 lr 0.000512	time 2.4244 (2.2068)	loss 3.9318 (3.5378)	grad_norm 1.5133 (1.5018)	
[2022-01-22 08:47:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][810/1251]	eta 0:16:12 lr 0.000512	time 1.9790 (2.2063)	loss 4.2265 (3.5392)	grad_norm 1.4681 (1.5017)	
[2022-01-22 08:47:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][820/1251]	eta 0:15:51 lr 0.000512	time 2.5954 (2.2079)	loss 4.0925 (3.5414)	grad_norm 1.6113 (1.5027)	
[2022-01-22 08:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][830/1251]	eta 0:15:28 lr 0.000512	time 1.5443 (2.2064)	loss 3.6546 (3.5435)	grad_norm 1.3770 (1.5017)	
[2022-01-22 08:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][840/1251]	eta 0:15:06 lr 0.000512	time 2.2558 (2.2057)	loss 3.0928 (3.5434)	grad_norm 1.2762 (1.5007)	
[2022-01-22 08:48:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][850/1251]	eta 0:14:43 lr 0.000512	time 2.1080 (2.2041)	loss 3.8578 (3.5437)	grad_norm 1.4176 (1.5001)	
[2022-01-22 08:49:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][860/1251]	eta 0:14:21 lr 0.000512	time 2.4799 (2.2030)	loss 3.0702 (3.5467)	grad_norm 1.4015 (1.4994)	
[2022-01-22 08:49:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][870/1251]	eta 0:13:59 lr 0.000512	time 1.6408 (2.2028)	loss 3.6301 (3.5453)	grad_norm 1.4277 (1.4991)	
[2022-01-22 08:49:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][880/1251]	eta 0:13:37 lr 0.000512	time 2.5967 (2.2041)	loss 3.5531 (3.5455)	grad_norm 1.5573 (1.4988)	
[2022-01-22 08:50:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][890/1251]	eta 0:13:15 lr 0.000512	time 1.9862 (2.2027)	loss 3.9872 (3.5468)	grad_norm 1.3578 (1.4987)	
[2022-01-22 08:50:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][900/1251]	eta 0:12:52 lr 0.000512	time 2.6261 (2.2016)	loss 3.1683 (3.5445)	grad_norm 1.4162 (1.4991)	
[2022-01-22 08:50:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][910/1251]	eta 0:12:30 lr 0.000512	time 1.8845 (2.2006)	loss 4.1233 (3.5457)	grad_norm 1.3244 (1.4990)	
[2022-01-22 08:51:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][920/1251]	eta 0:12:08 lr 0.000512	time 1.7162 (2.2006)	loss 3.7077 (3.5412)	grad_norm 1.4440 (1.4985)	
[2022-01-22 08:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][930/1251]	eta 0:11:46 lr 0.000512	time 2.5152 (2.2017)	loss 3.2962 (3.5422)	grad_norm 1.4868 (1.4987)	
[2022-01-22 08:51:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][940/1251]	eta 0:11:24 lr 0.000511	time 1.9007 (2.2010)	loss 4.2514 (3.5449)	grad_norm 1.5929 (1.4984)	
[2022-01-22 08:52:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][950/1251]	eta 0:11:03 lr 0.000511	time 2.4805 (2.2030)	loss 3.8293 (3.5433)	grad_norm 1.4102 (1.4977)	
[2022-01-22 08:52:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][960/1251]	eta 0:10:41 lr 0.000511	time 2.5188 (2.2045)	loss 4.1378 (3.5448)	grad_norm 1.5608 (1.4979)	
[2022-01-22 08:53:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][970/1251]	eta 0:10:19 lr 0.000511	time 1.8421 (2.2049)	loss 3.4392 (3.5469)	grad_norm 1.4312 (1.4979)	
[2022-01-22 08:53:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][980/1251]	eta 0:09:57 lr 0.000511	time 2.1446 (2.2039)	loss 3.9708 (3.5488)	grad_norm 1.5858 (1.4971)	
[2022-01-22 08:53:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][990/1251]	eta 0:09:35 lr 0.000511	time 2.2061 (2.2040)	loss 3.0033 (3.5490)	grad_norm 1.6703 (1.4973)	
[2022-01-22 08:54:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1000/1251]	eta 0:09:12 lr 0.000511	time 2.1949 (2.2019)	loss 2.1961 (3.5498)	grad_norm 1.3464 (1.4966)	
[2022-01-22 08:54:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1010/1251]	eta 0:08:50 lr 0.000511	time 2.2861 (2.2022)	loss 3.8241 (3.5501)	grad_norm 1.5572 (1.4967)	
[2022-01-22 08:54:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1020/1251]	eta 0:08:28 lr 0.000511	time 1.5290 (2.2016)	loss 3.7595 (3.5515)	grad_norm 1.8559 (1.4969)	
[2022-01-22 08:55:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1030/1251]	eta 0:08:07 lr 0.000511	time 2.4508 (2.2043)	loss 4.3672 (3.5537)	grad_norm 1.4779 (1.4964)	
[2022-01-22 08:55:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1040/1251]	eta 0:07:44 lr 0.000511	time 2.6140 (2.2027)	loss 3.0777 (3.5552)	grad_norm 1.4669 (1.4962)	
[2022-01-22 08:55:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1050/1251]	eta 0:07:22 lr 0.000511	time 2.2361 (2.2000)	loss 3.6256 (3.5541)	grad_norm 1.4955 (1.4965)	
[2022-01-22 08:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1060/1251]	eta 0:06:59 lr 0.000511	time 1.8584 (2.1976)	loss 3.1135 (3.5544)	grad_norm 1.6867 (1.4975)	
[2022-01-22 08:56:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1070/1251]	eta 0:06:37 lr 0.000511	time 1.5790 (2.1963)	loss 2.4505 (3.5531)	grad_norm 1.3477 (1.4965)	
[2022-01-22 08:56:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1080/1251]	eta 0:06:15 lr 0.000511	time 1.8502 (2.1952)	loss 4.2701 (3.5547)	grad_norm 1.6436 (1.4964)	
[2022-01-22 08:57:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1090/1251]	eta 0:05:53 lr 0.000511	time 2.7624 (2.1971)	loss 3.9726 (3.5554)	grad_norm 1.4179 (1.4957)	
[2022-01-22 08:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1100/1251]	eta 0:05:31 lr 0.000511	time 2.2267 (2.1982)	loss 3.8841 (3.5527)	grad_norm 1.5671 (1.4960)	
[2022-01-22 08:58:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1110/1251]	eta 0:05:10 lr 0.000511	time 1.8332 (2.2005)	loss 4.0449 (3.5541)	grad_norm 1.3709 (1.4965)	
[2022-01-22 08:58:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1120/1251]	eta 0:04:48 lr 0.000511	time 1.8899 (2.2012)	loss 3.5229 (3.5540)	grad_norm 1.5452 (1.4966)	
[2022-01-22 08:58:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1130/1251]	eta 0:04:26 lr 0.000511	time 2.1919 (2.2015)	loss 3.3908 (3.5545)	grad_norm 1.6421 (1.4962)	
[2022-01-22 08:59:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1140/1251]	eta 0:04:04 lr 0.000511	time 2.2962 (2.1996)	loss 3.4413 (3.5535)	grad_norm 1.3997 (1.4963)	
[2022-01-22 08:59:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1150/1251]	eta 0:03:42 lr 0.000511	time 1.4960 (2.1983)	loss 3.3481 (3.5497)	grad_norm 1.4026 (1.4961)	
[2022-01-22 08:59:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1160/1251]	eta 0:03:19 lr 0.000511	time 1.9263 (2.1969)	loss 3.8576 (3.5493)	grad_norm 1.2399 (1.4954)	
[2022-01-22 09:00:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1170/1251]	eta 0:02:57 lr 0.000511	time 1.8987 (2.1971)	loss 3.7725 (3.5490)	grad_norm 1.4112 (1.4952)	
[2022-01-22 09:00:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1180/1251]	eta 0:02:36 lr 0.000510	time 2.6190 (2.1973)	loss 3.2409 (3.5497)	grad_norm 1.4121 (1.4956)	
[2022-01-22 09:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1190/1251]	eta 0:02:13 lr 0.000510	time 1.5097 (2.1966)	loss 3.9138 (3.5508)	grad_norm 1.4425 (1.4951)	
[2022-01-22 09:01:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1200/1251]	eta 0:01:52 lr 0.000510	time 2.2482 (2.1974)	loss 3.3996 (3.5506)	grad_norm 1.3358 (1.4946)	
[2022-01-22 09:01:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1210/1251]	eta 0:01:30 lr 0.000510	time 2.2522 (2.1972)	loss 4.0948 (3.5504)	grad_norm 1.5684 (1.4944)	
[2022-01-22 09:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1220/1251]	eta 0:01:08 lr 0.000510	time 2.4636 (2.1968)	loss 3.5953 (3.5510)	grad_norm 1.4646 (1.4938)	
[2022-01-22 09:02:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1230/1251]	eta 0:00:46 lr 0.000510	time 2.4649 (2.1985)	loss 4.0744 (3.5524)	grad_norm 1.4450 (1.4945)	
[2022-01-22 09:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1240/1251]	eta 0:00:24 lr 0.000510	time 1.1740 (2.1974)	loss 3.2956 (3.5509)	grad_norm 1.6108 (1.4955)	
[2022-01-22 09:03:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [148/300][1250/1251]	eta 0:00:02 lr 0.000510	time 1.2005 (2.1925)	loss 3.9429 (3.5515)	grad_norm 2.0309 (1.4962)	
[2022-01-22 09:03:09 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 148 training takes 0:45:43
[2022-01-22 09:03:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.517 (18.517)	Loss 1.0111 (1.0111)	Acc@1 76.953 (76.953)	Acc@5 93.262 (93.262)	
[2022-01-22 09:03:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.233 (3.546)	Loss 1.0178 (1.0200)	Acc@1 76.465 (76.349)	Acc@5 94.043 (93.439)	
[2022-01-22 09:04:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.629 (2.504)	Loss 1.0634 (1.0269)	Acc@1 75.977 (76.121)	Acc@5 93.164 (93.359)	
[2022-01-22 09:04:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.484 (2.259)	Loss 1.0048 (1.0253)	Acc@1 75.781 (76.112)	Acc@5 93.457 (93.344)	
[2022-01-22 09:04:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.949 (2.178)	Loss 1.0463 (1.0246)	Acc@1 74.512 (76.093)	Acc@5 92.188 (93.274)	
[2022-01-22 09:04:45 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.908 Acc@5 93.174
[2022-01-22 09:04:45 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.9%
[2022-01-22 09:04:45 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.00%
[2022-01-22 09:05:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][0/1251]	eta 7:29:57 lr 0.000510	time 21.5810 (21.5810)	loss 3.6845 (3.6845)	grad_norm 1.6137 (1.6137)	
[2022-01-22 09:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][10/1251]	eta 1:21:22 lr 0.000510	time 1.5552 (3.9341)	loss 3.8808 (3.3887)	grad_norm 1.3402 (1.5054)	
[2022-01-22 09:05:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][20/1251]	eta 1:01:58 lr 0.000510	time 1.7959 (3.0209)	loss 2.7246 (3.4461)	grad_norm 1.5888 (1.4754)	
[2022-01-22 09:06:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][30/1251]	eta 0:54:56 lr 0.000510	time 1.6264 (2.6997)	loss 4.0956 (3.4774)	grad_norm 1.3661 (1.4589)	
[2022-01-22 09:06:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][40/1251]	eta 0:54:23 lr 0.000510	time 5.4630 (2.6949)	loss 3.8493 (3.4894)	grad_norm 1.4994 (1.4591)	
[2022-01-22 09:06:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][50/1251]	eta 0:52:23 lr 0.000510	time 2.5297 (2.6176)	loss 3.5906 (3.4842)	grad_norm 1.4085 (1.4711)	
[2022-01-22 09:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][60/1251]	eta 0:50:17 lr 0.000510	time 1.4739 (2.5340)	loss 3.5086 (3.5003)	grad_norm 1.4766 (1.4793)	
[2022-01-22 09:07:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][70/1251]	eta 0:49:09 lr 0.000510	time 2.8138 (2.4975)	loss 3.7419 (3.5089)	grad_norm 1.2526 (1.4827)	
[2022-01-22 09:08:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][80/1251]	eta 0:48:33 lr 0.000510	time 3.5453 (2.4880)	loss 4.0991 (3.5168)	grad_norm 1.5117 (1.4778)	
[2022-01-22 09:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][90/1251]	eta 0:47:46 lr 0.000510	time 2.9106 (2.4692)	loss 2.3970 (3.5253)	grad_norm 1.4373 (1.4861)	
[2022-01-22 09:08:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][100/1251]	eta 0:46:40 lr 0.000510	time 1.5686 (2.4335)	loss 3.6458 (3.5382)	grad_norm 1.6515 (1.4877)	
[2022-01-22 09:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][110/1251]	eta 0:45:27 lr 0.000510	time 1.7167 (2.3907)	loss 2.9478 (3.5425)	grad_norm 1.4702 (1.4912)	
[2022-01-22 09:09:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][120/1251]	eta 0:44:42 lr 0.000510	time 3.1890 (2.3720)	loss 4.3239 (3.5567)	grad_norm 1.5978 (1.4996)	
[2022-01-22 09:09:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][130/1251]	eta 0:43:57 lr 0.000510	time 1.9240 (2.3531)	loss 3.8644 (3.5289)	grad_norm 1.7122 (1.4964)	
[2022-01-22 09:10:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][140/1251]	eta 0:43:26 lr 0.000510	time 1.8716 (2.3459)	loss 3.9006 (3.5434)	grad_norm 1.3601 (1.4895)	
[2022-01-22 09:10:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][150/1251]	eta 0:43:06 lr 0.000510	time 2.1147 (2.3492)	loss 3.0760 (3.5297)	grad_norm 1.6234 (1.4998)	
[2022-01-22 09:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][160/1251]	eta 0:42:43 lr 0.000510	time 3.6717 (2.3493)	loss 3.8276 (3.5442)	grad_norm 1.5572 (1.5054)	
[2022-01-22 09:11:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][170/1251]	eta 0:42:01 lr 0.000509	time 1.8551 (2.3323)	loss 4.2051 (3.5494)	grad_norm 1.7068 (1.5069)	
[2022-01-22 09:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][180/1251]	eta 0:41:15 lr 0.000509	time 1.9025 (2.3112)	loss 2.7311 (3.5366)	grad_norm 1.5667 (1.5020)	
[2022-01-22 09:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][190/1251]	eta 0:40:37 lr 0.000509	time 1.6492 (2.2976)	loss 3.4119 (3.5442)	grad_norm 1.4886 (1.5009)	
[2022-01-22 09:12:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][200/1251]	eta 0:40:12 lr 0.000509	time 3.1303 (2.2956)	loss 3.4886 (3.5417)	grad_norm 1.4761 (1.5021)	
[2022-01-22 09:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][210/1251]	eta 0:39:47 lr 0.000509	time 2.2502 (2.2933)	loss 3.8220 (3.5359)	grad_norm 1.5054 (1.5019)	
[2022-01-22 09:13:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][220/1251]	eta 0:39:20 lr 0.000509	time 1.7081 (2.2897)	loss 3.5784 (3.5207)	grad_norm 1.7660 (1.5053)	
[2022-01-22 09:13:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][230/1251]	eta 0:38:52 lr 0.000509	time 2.1863 (2.2844)	loss 2.7742 (3.5208)	grad_norm 1.7923 (1.5064)	
[2022-01-22 09:13:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][240/1251]	eta 0:38:22 lr 0.000509	time 2.1983 (2.2776)	loss 3.7895 (3.5412)	grad_norm 1.6139 (1.5153)	
[2022-01-22 09:14:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][250/1251]	eta 0:37:55 lr 0.000509	time 1.8387 (2.2735)	loss 3.9459 (3.5555)	grad_norm 1.4280 (1.5159)	
[2022-01-22 09:14:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][260/1251]	eta 0:37:31 lr 0.000509	time 1.9597 (2.2717)	loss 2.5980 (3.5532)	grad_norm 1.6868 (1.5147)	
[2022-01-22 09:15:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][270/1251]	eta 0:37:02 lr 0.000509	time 2.1661 (2.2660)	loss 3.5436 (3.5594)	grad_norm 1.4675 (1.5137)	
[2022-01-22 09:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][280/1251]	eta 0:36:32 lr 0.000509	time 2.0042 (2.2585)	loss 2.5405 (3.5499)	grad_norm 1.4687 (1.5127)	
[2022-01-22 09:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][290/1251]	eta 0:36:03 lr 0.000509	time 1.8505 (2.2514)	loss 4.1061 (3.5523)	grad_norm 1.5020 (1.5122)	
[2022-01-22 09:16:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][300/1251]	eta 0:35:34 lr 0.000509	time 2.3527 (2.2440)	loss 3.1585 (3.5553)	grad_norm 1.2919 (1.5152)	
[2022-01-22 09:16:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][310/1251]	eta 0:35:05 lr 0.000509	time 2.0929 (2.2376)	loss 3.8166 (3.5511)	grad_norm 1.5770 (1.5161)	
[2022-01-22 09:16:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][320/1251]	eta 0:34:40 lr 0.000509	time 2.0588 (2.2344)	loss 2.5831 (3.5444)	grad_norm 1.3998 (1.5183)	
[2022-01-22 09:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][330/1251]	eta 0:34:14 lr 0.000509	time 2.2070 (2.2311)	loss 3.5418 (3.5458)	grad_norm 1.5265 (1.5157)	
[2022-01-22 09:17:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][340/1251]	eta 0:33:52 lr 0.000509	time 2.4120 (2.2311)	loss 3.5100 (3.5455)	grad_norm 1.3578 (1.5124)	
[2022-01-22 09:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][350/1251]	eta 0:33:31 lr 0.000509	time 2.3080 (2.2329)	loss 4.0344 (3.5471)	grad_norm 1.4323 (1.5126)	
[2022-01-22 09:18:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][360/1251]	eta 0:33:15 lr 0.000509	time 2.6712 (2.2396)	loss 3.7670 (3.5471)	grad_norm 1.5923 (1.5136)	
[2022-01-22 09:18:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][370/1251]	eta 0:32:57 lr 0.000509	time 2.5761 (2.2444)	loss 3.2903 (3.5536)	grad_norm 2.6407 (1.5152)	
[2022-01-22 09:19:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][380/1251]	eta 0:32:34 lr 0.000509	time 1.8821 (2.2435)	loss 3.5931 (3.5553)	grad_norm 1.6789 (1.5205)	
[2022-01-22 09:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][390/1251]	eta 0:32:09 lr 0.000509	time 1.7581 (2.2413)	loss 3.8149 (3.5548)	grad_norm 1.7278 (1.5230)	
[2022-01-22 09:19:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][400/1251]	eta 0:31:47 lr 0.000509	time 3.1694 (2.2421)	loss 4.2492 (3.5580)	grad_norm 1.6427 (1.5246)	
[2022-01-22 09:20:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][410/1251]	eta 0:31:22 lr 0.000508	time 1.9605 (2.2380)	loss 3.3426 (3.5600)	grad_norm 1.6441 (1.5231)	
[2022-01-22 09:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][420/1251]	eta 0:30:58 lr 0.000508	time 1.7171 (2.2362)	loss 2.6554 (3.5546)	grad_norm 1.2844 (1.5211)	
[2022-01-22 09:20:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][430/1251]	eta 0:30:34 lr 0.000508	time 1.7011 (2.2349)	loss 4.1110 (3.5599)	grad_norm 1.5951 (1.5207)	
[2022-01-22 09:21:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][440/1251]	eta 0:30:11 lr 0.000508	time 2.9348 (2.2342)	loss 3.6108 (3.5624)	grad_norm 1.4250 (1.5182)	
[2022-01-22 09:21:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][450/1251]	eta 0:29:49 lr 0.000508	time 2.5749 (2.2336)	loss 2.6314 (3.5586)	grad_norm 1.4352 (1.5162)	
[2022-01-22 09:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][460/1251]	eta 0:29:24 lr 0.000508	time 1.9735 (2.2313)	loss 2.8951 (3.5576)	grad_norm 1.3492 (1.5159)	
[2022-01-22 09:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][470/1251]	eta 0:28:59 lr 0.000508	time 1.9072 (2.2272)	loss 2.9002 (3.5577)	grad_norm 1.3600 (1.5141)	
[2022-01-22 09:22:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][480/1251]	eta 0:28:37 lr 0.000508	time 3.2167 (2.2273)	loss 3.5860 (3.5592)	grad_norm 1.5034 (1.5120)	
[2022-01-22 09:22:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][490/1251]	eta 0:28:12 lr 0.000508	time 2.1733 (2.2234)	loss 3.5721 (3.5556)	grad_norm 1.3989 (1.5120)	
[2022-01-22 09:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][500/1251]	eta 0:27:49 lr 0.000508	time 2.1743 (2.2233)	loss 4.1240 (3.5582)	grad_norm 1.3773 (1.5102)	
[2022-01-22 09:23:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][510/1251]	eta 0:27:26 lr 0.000508	time 3.1294 (2.2227)	loss 4.0997 (3.5565)	grad_norm 1.3484 (1.5095)	
[2022-01-22 09:24:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][520/1251]	eta 0:27:05 lr 0.000508	time 3.2093 (2.2235)	loss 3.8477 (3.5541)	grad_norm 1.6545 (1.5090)	
[2022-01-22 09:24:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][530/1251]	eta 0:26:41 lr 0.000508	time 1.8948 (2.2214)	loss 2.7330 (3.5498)	grad_norm 1.4285 (1.5083)	
[2022-01-22 09:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][540/1251]	eta 0:26:19 lr 0.000508	time 2.4687 (2.2218)	loss 4.3293 (3.5532)	grad_norm 1.4043 (1.5086)	
[2022-01-22 09:25:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][550/1251]	eta 0:25:57 lr 0.000508	time 2.4358 (2.2224)	loss 4.1614 (3.5537)	grad_norm 1.3855 (1.5090)	
[2022-01-22 09:25:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][560/1251]	eta 0:25:34 lr 0.000508	time 2.5837 (2.2211)	loss 2.9246 (3.5563)	grad_norm 1.4282 (1.5088)	
[2022-01-22 09:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][570/1251]	eta 0:25:10 lr 0.000508	time 1.8711 (2.2188)	loss 3.2746 (3.5550)	grad_norm 1.6048 (1.5080)	
[2022-01-22 09:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][580/1251]	eta 0:24:47 lr 0.000508	time 2.0301 (2.2175)	loss 3.4692 (3.5533)	grad_norm 1.4144 (1.5078)	
[2022-01-22 09:26:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][590/1251]	eta 0:24:25 lr 0.000508	time 2.2575 (2.2178)	loss 3.6706 (3.5535)	grad_norm 1.5639 (1.5079)	
[2022-01-22 09:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][600/1251]	eta 0:24:05 lr 0.000508	time 2.7694 (2.2202)	loss 3.6105 (3.5537)	grad_norm 1.4380 (1.5074)	
[2022-01-22 09:27:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][610/1251]	eta 0:23:43 lr 0.000508	time 1.5845 (2.2200)	loss 2.7835 (3.5506)	grad_norm 1.2944 (1.5066)	
[2022-01-22 09:27:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][620/1251]	eta 0:23:21 lr 0.000508	time 2.2234 (2.2212)	loss 3.7681 (3.5524)	grad_norm 1.9218 (1.5071)	
[2022-01-22 09:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][630/1251]	eta 0:22:57 lr 0.000508	time 1.7989 (2.2187)	loss 3.2048 (3.5534)	grad_norm 1.6276 (1.5071)	
[2022-01-22 09:28:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][640/1251]	eta 0:22:35 lr 0.000508	time 2.8779 (2.2186)	loss 4.0565 (3.5522)	grad_norm 1.3947 (1.5064)	
[2022-01-22 09:28:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][650/1251]	eta 0:22:11 lr 0.000507	time 1.9441 (2.2158)	loss 2.3680 (3.5492)	grad_norm 1.4287 (1.5059)	
[2022-01-22 09:29:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][660/1251]	eta 0:21:48 lr 0.000507	time 1.8802 (2.2135)	loss 3.8922 (3.5470)	grad_norm 1.5301 (1.5057)	
[2022-01-22 09:29:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][670/1251]	eta 0:21:25 lr 0.000507	time 2.2371 (2.2121)	loss 4.2292 (3.5485)	grad_norm 1.4334 (1.5062)	
[2022-01-22 09:29:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][680/1251]	eta 0:21:03 lr 0.000507	time 2.5222 (2.2136)	loss 3.7006 (3.5486)	grad_norm 1.6497 (1.5071)	
[2022-01-22 09:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][690/1251]	eta 0:20:42 lr 0.000507	time 2.2078 (2.2148)	loss 2.9800 (3.5466)	grad_norm 1.5573 (1.5079)	
[2022-01-22 09:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][700/1251]	eta 0:20:20 lr 0.000507	time 1.9416 (2.2152)	loss 2.7066 (3.5440)	grad_norm 1.5390 (1.5083)	
[2022-01-22 09:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][710/1251]	eta 0:19:58 lr 0.000507	time 2.4671 (2.2155)	loss 4.1885 (3.5414)	grad_norm 1.4392 (1.5087)	
[2022-01-22 09:31:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][720/1251]	eta 0:19:36 lr 0.000507	time 2.7412 (2.2152)	loss 3.2927 (3.5416)	grad_norm 1.8740 (1.5097)	
[2022-01-22 09:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][730/1251]	eta 0:19:12 lr 0.000507	time 1.9036 (2.2128)	loss 2.7324 (3.5427)	grad_norm 1.4054 (1.5094)	
[2022-01-22 09:32:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][740/1251]	eta 0:18:50 lr 0.000507	time 2.2059 (2.2128)	loss 3.2276 (3.5432)	grad_norm 1.3686 (1.5094)	
[2022-01-22 09:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][750/1251]	eta 0:18:27 lr 0.000507	time 1.7201 (2.2113)	loss 4.1548 (3.5410)	grad_norm 2.0188 (1.5097)	
[2022-01-22 09:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][760/1251]	eta 0:18:06 lr 0.000507	time 1.9261 (2.2125)	loss 3.0705 (3.5402)	grad_norm 1.5056 (1.5096)	
[2022-01-22 09:33:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][770/1251]	eta 0:17:43 lr 0.000507	time 1.8793 (2.2116)	loss 3.9283 (3.5375)	grad_norm 1.4137 (1.5089)	
[2022-01-22 09:33:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][780/1251]	eta 0:17:20 lr 0.000507	time 1.9571 (2.2100)	loss 2.8650 (3.5364)	grad_norm 1.5367 (1.5094)	
[2022-01-22 09:33:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][790/1251]	eta 0:16:57 lr 0.000507	time 1.8833 (2.2077)	loss 2.3636 (3.5357)	grad_norm 1.4267 (1.5097)	
[2022-01-22 09:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][800/1251]	eta 0:16:35 lr 0.000507	time 2.7537 (2.2081)	loss 3.4148 (3.5329)	grad_norm 1.4064 (1.5097)	
[2022-01-22 09:34:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][810/1251]	eta 0:16:13 lr 0.000507	time 2.3473 (2.2079)	loss 4.4395 (3.5324)	grad_norm 1.7728 (1.5099)	
[2022-01-22 09:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][820/1251]	eta 0:15:52 lr 0.000507	time 2.6512 (2.2094)	loss 4.0564 (3.5321)	grad_norm 1.6650 (1.5109)	
[2022-01-22 09:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][830/1251]	eta 0:15:30 lr 0.000507	time 2.3500 (2.2102)	loss 3.5539 (3.5317)	grad_norm 1.3753 (1.5107)	
[2022-01-22 09:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][840/1251]	eta 0:15:08 lr 0.000507	time 2.1461 (2.2097)	loss 3.9486 (3.5318)	grad_norm 1.5070 (1.5098)	
[2022-01-22 09:36:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][850/1251]	eta 0:14:44 lr 0.000507	time 1.9202 (2.2061)	loss 2.5270 (3.5307)	grad_norm 1.5269 (1.5094)	
[2022-01-22 09:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][860/1251]	eta 0:14:21 lr 0.000507	time 1.9255 (2.2040)	loss 2.5067 (3.5255)	grad_norm 1.3979 (1.5087)	
[2022-01-22 09:36:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][870/1251]	eta 0:13:59 lr 0.000507	time 2.6840 (2.2027)	loss 3.4933 (3.5235)	grad_norm 1.2614 (1.5083)	
[2022-01-22 09:37:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][880/1251]	eta 0:13:37 lr 0.000507	time 2.2782 (2.2029)	loss 2.6120 (3.5218)	grad_norm 1.3961 (1.5086)	
[2022-01-22 09:37:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][890/1251]	eta 0:13:14 lr 0.000506	time 1.9997 (2.2022)	loss 4.4976 (3.5253)	grad_norm 1.4484 (1.5084)	
[2022-01-22 09:37:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][900/1251]	eta 0:12:53 lr 0.000506	time 1.4848 (2.2028)	loss 4.1450 (3.5283)	grad_norm 1.6363 (1.5084)	
[2022-01-22 09:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][910/1251]	eta 0:12:31 lr 0.000506	time 2.7079 (2.2047)	loss 3.9774 (3.5318)	grad_norm 1.4027 (1.5084)	
[2022-01-22 09:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][920/1251]	eta 0:12:10 lr 0.000506	time 2.1408 (2.2055)	loss 3.9534 (3.5309)	grad_norm 1.5167 (1.5078)	
[2022-01-22 09:39:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][930/1251]	eta 0:11:48 lr 0.000506	time 2.4556 (2.2063)	loss 3.8512 (3.5289)	grad_norm 1.4599 (1.5077)	
[2022-01-22 09:39:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][940/1251]	eta 0:11:26 lr 0.000506	time 1.8189 (2.2064)	loss 4.3701 (3.5301)	grad_norm 1.5786 (1.5078)	
[2022-01-22 09:39:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][950/1251]	eta 0:11:03 lr 0.000506	time 1.8067 (2.2043)	loss 3.5683 (3.5319)	grad_norm 1.5548 (1.5082)	
[2022-01-22 09:40:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][960/1251]	eta 0:10:40 lr 0.000506	time 1.8349 (2.2021)	loss 3.3567 (3.5328)	grad_norm 1.3156 (1.5092)	
[2022-01-22 09:40:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][970/1251]	eta 0:10:18 lr 0.000506	time 1.8541 (2.2009)	loss 2.6239 (3.5320)	grad_norm 1.5225 (1.5101)	
[2022-01-22 09:40:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][980/1251]	eta 0:09:56 lr 0.000506	time 2.3633 (2.2002)	loss 3.0682 (3.5334)	grad_norm 1.3701 (1.5098)	
[2022-01-22 09:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][990/1251]	eta 0:09:33 lr 0.000506	time 2.5281 (2.1984)	loss 2.4417 (3.5339)	grad_norm 1.5795 (1.5098)	
[2022-01-22 09:41:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1000/1251]	eta 0:09:12 lr 0.000506	time 2.1191 (2.1992)	loss 2.9440 (3.5331)	grad_norm 1.3412 (1.5092)	
[2022-01-22 09:41:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1010/1251]	eta 0:08:50 lr 0.000506	time 2.1178 (2.2002)	loss 3.8217 (3.5324)	grad_norm 1.5563 (1.5093)	
[2022-01-22 09:42:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1020/1251]	eta 0:08:28 lr 0.000506	time 3.0444 (2.2028)	loss 3.7660 (3.5349)	grad_norm 1.5181 (1.5095)	
[2022-01-22 09:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1030/1251]	eta 0:08:07 lr 0.000506	time 2.9713 (2.2041)	loss 3.5979 (3.5365)	grad_norm 1.7663 (1.5092)	
[2022-01-22 09:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1040/1251]	eta 0:07:45 lr 0.000506	time 1.8999 (2.2049)	loss 4.2740 (3.5367)	grad_norm 1.4541 (1.5092)	
[2022-01-22 09:43:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1050/1251]	eta 0:07:23 lr 0.000506	time 1.6442 (2.2040)	loss 3.9675 (3.5340)	grad_norm 1.2653 (1.5084)	
[2022-01-22 09:43:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1060/1251]	eta 0:07:00 lr 0.000506	time 2.5324 (2.2035)	loss 3.9260 (3.5342)	grad_norm 1.5053 (1.5076)	
[2022-01-22 09:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1070/1251]	eta 0:06:38 lr 0.000506	time 1.9135 (2.2006)	loss 2.3167 (3.5326)	grad_norm 1.3835 (1.5068)	
[2022-01-22 09:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1080/1251]	eta 0:06:15 lr 0.000506	time 1.8447 (2.1982)	loss 3.3209 (3.5311)	grad_norm 1.7125 (1.5077)	
[2022-01-22 09:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1090/1251]	eta 0:05:53 lr 0.000506	time 2.1398 (2.1972)	loss 3.3543 (3.5325)	grad_norm 1.3244 (1.5079)	
[2022-01-22 09:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1100/1251]	eta 0:05:31 lr 0.000506	time 2.3081 (2.1976)	loss 3.6381 (3.5343)	grad_norm 1.5985 (1.5085)	
[2022-01-22 09:45:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1110/1251]	eta 0:05:09 lr 0.000506	time 2.4710 (2.1978)	loss 3.9298 (3.5331)	grad_norm 1.5241 (1.5084)	
[2022-01-22 09:45:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1120/1251]	eta 0:04:47 lr 0.000506	time 1.9379 (2.1971)	loss 4.2147 (3.5319)	grad_norm 1.6577 (1.5097)	
[2022-01-22 09:46:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1130/1251]	eta 0:04:25 lr 0.000506	time 2.5954 (2.1977)	loss 3.8180 (3.5326)	grad_norm 1.4222 (1.5091)	
[2022-01-22 09:46:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1140/1251]	eta 0:04:04 lr 0.000505	time 2.8139 (2.2003)	loss 3.6171 (3.5328)	grad_norm 1.5650 (1.5092)	
[2022-01-22 09:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1150/1251]	eta 0:03:42 lr 0.000505	time 1.7525 (2.2032)	loss 4.0573 (3.5349)	grad_norm 1.6681 (1.5092)	
[2022-01-22 09:47:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1160/1251]	eta 0:03:20 lr 0.000505	time 2.1789 (2.2042)	loss 4.0809 (3.5364)	grad_norm 1.4014 (1.5090)	
[2022-01-22 09:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1170/1251]	eta 0:02:58 lr 0.000505	time 1.9128 (2.2032)	loss 3.7373 (3.5370)	grad_norm 1.5055 (1.5090)	
[2022-01-22 09:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1180/1251]	eta 0:02:36 lr 0.000505	time 2.3011 (2.2005)	loss 3.9907 (3.5332)	grad_norm 1.5020 (1.5085)	
[2022-01-22 09:48:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1190/1251]	eta 0:02:14 lr 0.000505	time 1.8714 (2.1983)	loss 3.7938 (3.5330)	grad_norm 1.3286 (1.5083)	
[2022-01-22 09:48:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1200/1251]	eta 0:01:52 lr 0.000505	time 2.0999 (2.1965)	loss 3.5645 (3.5324)	grad_norm 1.5242 (1.5086)	
[2022-01-22 09:49:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1210/1251]	eta 0:01:30 lr 0.000505	time 2.8621 (2.1972)	loss 3.8790 (3.5325)	grad_norm 1.7826 (1.5086)	
[2022-01-22 09:49:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1220/1251]	eta 0:01:08 lr 0.000505	time 2.7669 (2.1970)	loss 3.4665 (3.5339)	grad_norm 1.4077 (1.5083)	
[2022-01-22 09:49:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1230/1251]	eta 0:00:46 lr 0.000505	time 2.4092 (2.1983)	loss 4.2997 (3.5340)	grad_norm 1.5569 (1.5079)	
[2022-01-22 09:50:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1240/1251]	eta 0:00:24 lr 0.000505	time 1.8907 (2.1968)	loss 2.0916 (3.5313)	grad_norm 1.4567 (1.5072)	
[2022-01-22 09:50:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [149/300][1250/1251]	eta 0:00:02 lr 0.000505	time 1.1804 (2.1913)	loss 3.6038 (3.5318)	grad_norm 1.4343 (1.5069)	
[2022-01-22 09:50:27 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 149 training takes 0:45:41
[2022-01-22 09:50:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.353 (18.353)	Loss 1.0754 (1.0754)	Acc@1 75.977 (75.977)	Acc@5 92.773 (92.773)	
[2022-01-22 09:51:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.565 (3.397)	Loss 0.9786 (1.0183)	Acc@1 76.758 (76.545)	Acc@5 93.750 (93.031)	
[2022-01-22 09:51:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.809 (2.689)	Loss 1.0336 (1.0336)	Acc@1 75.195 (75.893)	Acc@5 93.262 (92.866)	
[2022-01-22 09:51:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.261 (2.282)	Loss 1.0051 (1.0211)	Acc@1 76.074 (76.213)	Acc@5 95.117 (93.101)	
[2022-01-22 09:51:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.396 (2.169)	Loss 1.0025 (1.0172)	Acc@1 76.953 (76.243)	Acc@5 93.652 (93.200)	
[2022-01-22 09:52:04 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.300 Acc@5 93.212
[2022-01-22 09:52:04 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.3%
[2022-01-22 09:52:04 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.30%
[2022-01-22 09:52:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][0/1251]	eta 7:29:31 lr 0.000505	time 21.5599 (21.5599)	loss 4.0410 (4.0410)	grad_norm 1.3609 (1.3609)	
[2022-01-22 09:52:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][10/1251]	eta 1:25:51 lr 0.000505	time 1.7425 (4.1512)	loss 2.5807 (3.5343)	grad_norm 1.4347 (1.5160)	
[2022-01-22 09:53:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][20/1251]	eta 1:06:13 lr 0.000505	time 2.5557 (3.2281)	loss 3.9113 (3.5654)	grad_norm 1.4713 (1.5289)	
[2022-01-22 09:53:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][30/1251]	eta 0:58:45 lr 0.000505	time 1.5927 (2.8878)	loss 2.3415 (3.5231)	grad_norm 1.6767 (1.5002)	
[2022-01-22 09:53:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][40/1251]	eta 0:55:55 lr 0.000505	time 3.8272 (2.7710)	loss 4.1133 (3.5687)	grad_norm 1.5600 (1.4974)	
[2022-01-22 09:54:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][50/1251]	eta 0:53:21 lr 0.000505	time 2.3709 (2.6661)	loss 4.1202 (3.6107)	grad_norm 1.5455 (1.4947)	
[2022-01-22 09:54:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][60/1251]	eta 0:51:13 lr 0.000505	time 2.2345 (2.5809)	loss 4.2800 (3.6199)	grad_norm 1.4536 (1.5053)	
[2022-01-22 09:55:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][70/1251]	eta 0:49:25 lr 0.000505	time 1.6488 (2.5109)	loss 3.0505 (3.6172)	grad_norm 1.7754 (1.5140)	
[2022-01-22 09:55:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][80/1251]	eta 0:48:23 lr 0.000505	time 3.4320 (2.4794)	loss 3.8162 (3.5773)	grad_norm 1.5592 (1.5125)	
[2022-01-22 09:55:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][90/1251]	eta 0:47:17 lr 0.000505	time 2.5203 (2.4439)	loss 3.0534 (3.5884)	grad_norm 1.4120 (1.5105)	
[2022-01-22 09:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][100/1251]	eta 0:46:04 lr 0.000505	time 2.1869 (2.4021)	loss 2.8933 (3.5619)	grad_norm 1.5623 (1.5125)	
[2022-01-22 09:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][110/1251]	eta 0:45:12 lr 0.000505	time 1.8456 (2.3772)	loss 3.2270 (3.5553)	grad_norm 1.3566 (1.5054)	
[2022-01-22 09:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][120/1251]	eta 0:44:29 lr 0.000505	time 2.2281 (2.3604)	loss 3.2125 (3.5400)	grad_norm 1.5770 (1.5042)	
[2022-01-22 09:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][130/1251]	eta 0:44:22 lr 0.000504	time 3.2259 (2.3748)	loss 2.7127 (3.5068)	grad_norm 1.5725 (1.5093)	
[2022-01-22 09:57:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][140/1251]	eta 0:43:51 lr 0.000504	time 1.9689 (2.3689)	loss 4.2582 (3.5100)	grad_norm 1.5763 (1.5075)	
[2022-01-22 09:58:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][150/1251]	eta 0:43:13 lr 0.000504	time 2.2115 (2.3556)	loss 3.5678 (3.5089)	grad_norm 1.3338 (1.5096)	
[2022-01-22 09:58:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][160/1251]	eta 0:42:29 lr 0.000504	time 1.8399 (2.3370)	loss 2.3308 (3.5060)	grad_norm 1.5271 (1.5074)	
[2022-01-22 09:58:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][170/1251]	eta 0:42:03 lr 0.000504	time 3.1044 (2.3341)	loss 4.0937 (3.5126)	grad_norm 1.5264 (1.5063)	
[2022-01-22 09:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][180/1251]	eta 0:41:26 lr 0.000504	time 1.9790 (2.3221)	loss 2.8308 (3.5202)	grad_norm 1.5796 (1.5074)	
[2022-01-22 09:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][190/1251]	eta 0:40:45 lr 0.000504	time 1.6162 (2.3054)	loss 2.4347 (3.5185)	grad_norm 1.4322 (1.5091)	
[2022-01-22 09:59:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][200/1251]	eta 0:40:05 lr 0.000504	time 1.8159 (2.2887)	loss 3.3370 (3.5169)	grad_norm 1.4722 (1.5139)	
[2022-01-22 10:00:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][210/1251]	eta 0:39:36 lr 0.000504	time 1.8748 (2.2831)	loss 3.3876 (3.5248)	grad_norm 1.3564 (1.5143)	
[2022-01-22 10:00:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][220/1251]	eta 0:39:07 lr 0.000504	time 2.6978 (2.2769)	loss 3.6031 (3.5285)	grad_norm 1.5132 (1.5152)	
[2022-01-22 10:00:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][230/1251]	eta 0:38:46 lr 0.000504	time 2.8709 (2.2787)	loss 4.1187 (3.5257)	grad_norm 1.5060 (1.5181)	
[2022-01-22 10:01:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][240/1251]	eta 0:38:22 lr 0.000504	time 2.0832 (2.2776)	loss 3.1915 (3.5095)	grad_norm 1.2602 (1.5166)	
[2022-01-22 10:01:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][250/1251]	eta 0:38:00 lr 0.000504	time 2.7712 (2.2780)	loss 3.0738 (3.5053)	grad_norm 1.2276 (1.5135)	
[2022-01-22 10:01:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][260/1251]	eta 0:37:34 lr 0.000504	time 2.8352 (2.2754)	loss 4.1700 (3.5094)	grad_norm 1.5626 (1.5212)	
[2022-01-22 10:02:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][270/1251]	eta 0:37:05 lr 0.000504	time 2.1708 (2.2687)	loss 2.5932 (3.5135)	grad_norm 1.5192 (1.5215)	
[2022-01-22 10:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][280/1251]	eta 0:36:34 lr 0.000504	time 1.9176 (2.2601)	loss 3.9250 (3.5143)	grad_norm 1.4966 (1.5246)	
[2022-01-22 10:03:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][290/1251]	eta 0:36:06 lr 0.000504	time 2.2082 (2.2545)	loss 3.0141 (3.5102)	grad_norm 1.6690 (1.5253)	
[2022-01-22 10:03:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][300/1251]	eta 0:35:38 lr 0.000504	time 2.3006 (2.2488)	loss 3.9628 (3.5031)	grad_norm 1.3531 (1.5214)	
[2022-01-22 10:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][310/1251]	eta 0:35:15 lr 0.000504	time 2.9824 (2.2484)	loss 4.0574 (3.5030)	grad_norm 1.5825 (1.5211)	
[2022-01-22 10:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][320/1251]	eta 0:34:52 lr 0.000504	time 1.6132 (2.2473)	loss 2.4248 (3.5087)	grad_norm 1.5528 (1.5205)	
[2022-01-22 10:04:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][330/1251]	eta 0:34:25 lr 0.000504	time 2.0849 (2.2426)	loss 3.8429 (3.5146)	grad_norm 1.7210 (1.5216)	
[2022-01-22 10:04:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][340/1251]	eta 0:34:03 lr 0.000504	time 2.1875 (2.2427)	loss 4.2252 (3.5133)	grad_norm 1.3301 (1.5196)	
[2022-01-22 10:05:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][350/1251]	eta 0:33:41 lr 0.000504	time 2.6705 (2.2437)	loss 3.8888 (3.5181)	grad_norm 1.5348 (1.5199)	
[2022-01-22 10:05:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][360/1251]	eta 0:33:16 lr 0.000504	time 1.6857 (2.2410)	loss 2.3494 (3.5113)	grad_norm 1.3420 (1.5201)	
[2022-01-22 10:05:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][370/1251]	eta 0:32:53 lr 0.000503	time 1.6190 (2.2396)	loss 3.4699 (3.5105)	grad_norm 1.3471 (1.5217)	
[2022-01-22 10:06:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][380/1251]	eta 0:32:28 lr 0.000503	time 1.7692 (2.2368)	loss 3.4315 (3.4998)	grad_norm 1.5080 (1.5221)	
[2022-01-22 10:06:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][390/1251]	eta 0:32:01 lr 0.000503	time 2.4943 (2.2320)	loss 3.5562 (3.5025)	grad_norm 1.8437 (1.5233)	
[2022-01-22 10:06:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][400/1251]	eta 0:31:35 lr 0.000503	time 1.7030 (2.2272)	loss 2.7856 (3.5010)	grad_norm 1.5137 (1.5230)	
[2022-01-22 10:07:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][410/1251]	eta 0:31:11 lr 0.000503	time 2.2271 (2.2248)	loss 3.6495 (3.5042)	grad_norm 1.7192 (1.5244)	
[2022-01-22 10:07:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][420/1251]	eta 0:30:46 lr 0.000503	time 1.9985 (2.2217)	loss 2.8002 (3.4950)	grad_norm 1.6645 (1.5256)	
[2022-01-22 10:08:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][430/1251]	eta 0:30:23 lr 0.000503	time 2.6506 (2.2212)	loss 3.6646 (3.4946)	grad_norm 1.3973 (1.5264)	
[2022-01-22 10:08:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][440/1251]	eta 0:29:59 lr 0.000503	time 2.1280 (2.2194)	loss 2.7109 (3.4950)	grad_norm 1.4594 (1.5256)	
[2022-01-22 10:08:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][450/1251]	eta 0:29:38 lr 0.000503	time 3.1558 (2.2206)	loss 3.4355 (3.4955)	grad_norm 1.4666 (1.5265)	
[2022-01-22 10:09:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][460/1251]	eta 0:29:18 lr 0.000503	time 1.7667 (2.2236)	loss 2.3822 (3.4869)	grad_norm 1.4448 (1.5256)	
[2022-01-22 10:09:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][470/1251]	eta 0:28:58 lr 0.000503	time 2.3558 (2.2257)	loss 3.3715 (3.4832)	grad_norm 1.4546 (1.5261)	
[2022-01-22 10:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][480/1251]	eta 0:28:36 lr 0.000503	time 1.9003 (2.2257)	loss 3.8146 (3.4814)	grad_norm 1.6267 (1.5272)	
[2022-01-22 10:10:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][490/1251]	eta 0:28:13 lr 0.000503	time 2.4938 (2.2248)	loss 3.5131 (3.4806)	grad_norm 1.8259 (1.5283)	
[2022-01-22 10:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][500/1251]	eta 0:27:47 lr 0.000503	time 1.6479 (2.2206)	loss 4.2790 (3.4781)	grad_norm 1.3897 (1.5276)	
[2022-01-22 10:10:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][510/1251]	eta 0:27:23 lr 0.000503	time 2.1532 (2.2175)	loss 2.9677 (3.4777)	grad_norm 1.7346 (1.5276)	
[2022-01-22 10:11:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][520/1251]	eta 0:27:00 lr 0.000503	time 2.8452 (2.2162)	loss 3.7193 (3.4754)	grad_norm 1.7538 (1.5273)	
[2022-01-22 10:11:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][530/1251]	eta 0:26:41 lr 0.000503	time 2.1200 (2.2209)	loss 4.3724 (3.4760)	grad_norm 1.4302 (1.5263)	
[2022-01-22 10:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][540/1251]	eta 0:26:21 lr 0.000503	time 1.8033 (2.2246)	loss 4.0099 (3.4800)	grad_norm 1.5188 (1.5255)	
[2022-01-22 10:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][550/1251]	eta 0:25:59 lr 0.000503	time 2.2170 (2.2244)	loss 3.5208 (3.4811)	grad_norm 1.9328 (1.5248)	
[2022-01-22 10:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][560/1251]	eta 0:25:36 lr 0.000503	time 3.6462 (2.2241)	loss 3.8113 (3.4847)	grad_norm 1.5217 (1.5259)	
[2022-01-22 10:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][570/1251]	eta 0:25:11 lr 0.000503	time 1.8609 (2.2198)	loss 4.3257 (3.4881)	grad_norm 1.3362 (1.5251)	
[2022-01-22 10:13:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][580/1251]	eta 0:24:48 lr 0.000503	time 2.1241 (2.2181)	loss 3.3718 (3.4917)	grad_norm 1.5070 (1.5245)	
[2022-01-22 10:13:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][590/1251]	eta 0:24:25 lr 0.000503	time 2.2297 (2.2178)	loss 3.1475 (3.4850)	grad_norm 1.7883 (1.5238)	
[2022-01-22 10:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][600/1251]	eta 0:24:05 lr 0.000503	time 3.7631 (2.2199)	loss 2.8668 (3.4868)	grad_norm 1.5219 (1.5254)	
[2022-01-22 10:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][610/1251]	eta 0:23:42 lr 0.000502	time 2.0853 (2.2190)	loss 3.7721 (3.4884)	grad_norm 1.5223 (1.5258)	
[2022-01-22 10:15:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][620/1251]	eta 0:23:19 lr 0.000502	time 2.5308 (2.2179)	loss 3.4085 (3.4879)	grad_norm 1.3796 (1.5251)	
[2022-01-22 10:15:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][630/1251]	eta 0:22:56 lr 0.000502	time 1.8864 (2.2162)	loss 2.9474 (3.4889)	grad_norm 1.5699 (1.5243)	
[2022-01-22 10:15:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][640/1251]	eta 0:22:33 lr 0.000502	time 2.6132 (2.2156)	loss 3.5501 (3.4903)	grad_norm 1.4469 (1.5232)	
[2022-01-22 10:16:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][650/1251]	eta 0:22:10 lr 0.000502	time 1.8330 (2.2137)	loss 4.0118 (3.4934)	grad_norm 1.4582 (1.5213)	
[2022-01-22 10:16:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][660/1251]	eta 0:21:46 lr 0.000502	time 2.4494 (2.2112)	loss 3.9719 (3.4942)	grad_norm 1.5876 (1.5211)	
[2022-01-22 10:16:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][670/1251]	eta 0:21:24 lr 0.000502	time 2.0171 (2.2104)	loss 2.9007 (3.4969)	grad_norm 1.3953 (1.5202)	
[2022-01-22 10:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][680/1251]	eta 0:21:01 lr 0.000502	time 1.9251 (2.2088)	loss 3.2680 (3.5013)	grad_norm 1.4491 (1.5198)	
[2022-01-22 10:17:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][690/1251]	eta 0:20:38 lr 0.000502	time 1.5377 (2.2074)	loss 4.3050 (3.4992)	grad_norm 1.4591 (1.5187)	
[2022-01-22 10:17:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][700/1251]	eta 0:20:16 lr 0.000502	time 2.8162 (2.2073)	loss 2.8998 (3.4998)	grad_norm 1.7649 (1.5183)	
[2022-01-22 10:18:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][710/1251]	eta 0:19:53 lr 0.000502	time 2.2112 (2.2064)	loss 3.4411 (3.5034)	grad_norm 1.4384 (1.5188)	
[2022-01-22 10:18:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][720/1251]	eta 0:19:31 lr 0.000502	time 2.5272 (2.2069)	loss 3.8112 (3.5028)	grad_norm 1.9402 (1.5178)	
[2022-01-22 10:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][730/1251]	eta 0:19:09 lr 0.000502	time 1.9531 (2.2054)	loss 3.7689 (3.5028)	grad_norm 1.3512 (1.5169)	
[2022-01-22 10:19:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][740/1251]	eta 0:18:47 lr 0.000502	time 2.4379 (2.2070)	loss 3.7369 (3.5040)	grad_norm 1.3227 (1.5154)	
[2022-01-22 10:19:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][750/1251]	eta 0:18:26 lr 0.000502	time 2.4281 (2.2089)	loss 3.5560 (3.5042)	grad_norm 1.4076 (1.5155)	
[2022-01-22 10:20:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][760/1251]	eta 0:18:04 lr 0.000502	time 2.1234 (2.2085)	loss 2.7418 (3.5057)	grad_norm 1.3549 (1.5151)	
[2022-01-22 10:20:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][770/1251]	eta 0:17:41 lr 0.000502	time 1.5370 (2.2072)	loss 2.6739 (3.5044)	grad_norm 1.8169 (1.5142)	
[2022-01-22 10:20:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][780/1251]	eta 0:17:19 lr 0.000502	time 2.5391 (2.2066)	loss 4.2662 (3.5043)	grad_norm 1.5101 (1.5144)	
[2022-01-22 10:21:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][790/1251]	eta 0:16:55 lr 0.000502	time 1.7416 (2.2034)	loss 4.0939 (3.5031)	grad_norm 1.7014 (1.5154)	
[2022-01-22 10:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][800/1251]	eta 0:16:33 lr 0.000502	time 2.2487 (2.2032)	loss 3.2116 (3.5048)	grad_norm 1.3827 (1.5165)	
[2022-01-22 10:21:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][810/1251]	eta 0:16:11 lr 0.000502	time 2.2251 (2.2036)	loss 4.0034 (3.5072)	grad_norm 1.6832 (1.5168)	
[2022-01-22 10:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][820/1251]	eta 0:15:50 lr 0.000502	time 2.5343 (2.2043)	loss 3.9043 (3.5107)	grad_norm 1.9582 (1.5172)	
[2022-01-22 10:22:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][830/1251]	eta 0:15:28 lr 0.000502	time 2.1108 (2.2060)	loss 3.7811 (3.5068)	grad_norm 1.3628 (1.5161)	
[2022-01-22 10:23:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][840/1251]	eta 0:15:07 lr 0.000502	time 2.5508 (2.2080)	loss 3.6946 (3.5072)	grad_norm 1.4045 (1.5158)	
[2022-01-22 10:23:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][850/1251]	eta 0:14:45 lr 0.000501	time 2.1583 (2.2083)	loss 3.1337 (3.5074)	grad_norm 1.6302 (1.5157)	
[2022-01-22 10:23:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][860/1251]	eta 0:14:22 lr 0.000501	time 2.1691 (2.2059)	loss 4.1809 (3.5086)	grad_norm 1.3237 (1.5159)	
[2022-01-22 10:24:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][870/1251]	eta 0:13:59 lr 0.000501	time 1.8209 (2.2029)	loss 3.9745 (3.5078)	grad_norm 1.4088 (1.5150)	
[2022-01-22 10:24:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][880/1251]	eta 0:13:37 lr 0.000501	time 2.2535 (2.2031)	loss 3.9032 (3.5069)	grad_norm 1.3750 (1.5149)	
[2022-01-22 10:24:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][890/1251]	eta 0:13:15 lr 0.000501	time 2.3640 (2.2024)	loss 3.8202 (3.5088)	grad_norm 1.4445 (1.5152)	
[2022-01-22 10:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][900/1251]	eta 0:12:53 lr 0.000501	time 2.1263 (2.2031)	loss 3.5802 (3.5123)	grad_norm 1.4562 (1.5154)	
[2022-01-22 10:25:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][910/1251]	eta 0:12:31 lr 0.000501	time 2.1313 (2.2025)	loss 2.5997 (3.5096)	grad_norm 1.4682 (1.5141)	
[2022-01-22 10:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][920/1251]	eta 0:12:08 lr 0.000501	time 1.7909 (2.2016)	loss 3.0395 (3.5074)	grad_norm 1.6702 (1.5152)	
[2022-01-22 10:26:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][930/1251]	eta 0:11:46 lr 0.000501	time 2.3977 (2.2014)	loss 3.9373 (3.5083)	grad_norm 1.5658 (1.5149)	
[2022-01-22 10:26:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][940/1251]	eta 0:11:24 lr 0.000501	time 1.7601 (2.2008)	loss 4.0405 (3.5107)	grad_norm 1.3449 (1.5155)	
[2022-01-22 10:26:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][950/1251]	eta 0:11:02 lr 0.000501	time 2.4352 (2.2018)	loss 2.9346 (3.5102)	grad_norm 1.3843 (1.5150)	
[2022-01-22 10:27:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][960/1251]	eta 0:10:40 lr 0.000501	time 2.2368 (2.2016)	loss 3.7523 (3.5107)	grad_norm 1.4902 (1.5142)	
[2022-01-22 10:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][970/1251]	eta 0:10:18 lr 0.000501	time 2.1554 (2.2006)	loss 4.0886 (3.5106)	grad_norm 1.4463 (1.5151)	
[2022-01-22 10:28:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][980/1251]	eta 0:09:55 lr 0.000501	time 1.9157 (2.1991)	loss 4.2378 (3.5113)	grad_norm 1.5581 (1.5155)	
[2022-01-22 10:28:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][990/1251]	eta 0:09:33 lr 0.000501	time 2.6727 (2.1989)	loss 3.5430 (3.5103)	grad_norm 1.6229 (1.5161)	
[2022-01-22 10:28:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1000/1251]	eta 0:09:11 lr 0.000501	time 1.8732 (2.1986)	loss 3.8159 (3.5111)	grad_norm 1.5227 (1.5165)	
[2022-01-22 10:29:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1010/1251]	eta 0:08:50 lr 0.000501	time 2.8839 (2.2006)	loss 3.8258 (3.5118)	grad_norm 1.4788 (1.5165)	
[2022-01-22 10:29:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1020/1251]	eta 0:08:28 lr 0.000501	time 1.5309 (2.1996)	loss 3.1961 (3.5113)	grad_norm 1.5304 (1.5164)	
[2022-01-22 10:29:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1030/1251]	eta 0:08:06 lr 0.000501	time 2.7273 (2.2009)	loss 3.5954 (3.5136)	grad_norm 1.4044 (1.5162)	
[2022-01-22 10:30:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1040/1251]	eta 0:07:44 lr 0.000501	time 2.2868 (2.2000)	loss 3.2062 (3.5110)	grad_norm 1.8144 (1.5158)	
[2022-01-22 10:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1050/1251]	eta 0:07:22 lr 0.000501	time 2.1374 (2.1998)	loss 2.6591 (3.5119)	grad_norm 1.6631 (1.5155)	
[2022-01-22 10:30:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1060/1251]	eta 0:06:59 lr 0.000501	time 1.9116 (2.1987)	loss 3.8166 (3.5157)	grad_norm 1.6809 (1.5157)	
[2022-01-22 10:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1070/1251]	eta 0:06:38 lr 0.000501	time 2.2352 (2.1992)	loss 2.7720 (3.5158)	grad_norm 1.4264 (1.5161)	
[2022-01-22 10:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1080/1251]	eta 0:06:16 lr 0.000501	time 2.1974 (2.1992)	loss 2.7763 (3.5159)	grad_norm 1.3686 (1.5160)	
[2022-01-22 10:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1090/1251]	eta 0:05:53 lr 0.000500	time 1.9098 (2.1987)	loss 3.7850 (3.5160)	grad_norm 1.4934 (1.5156)	
[2022-01-22 10:32:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1100/1251]	eta 0:05:31 lr 0.000500	time 1.8031 (2.1976)	loss 3.7009 (3.5178)	grad_norm 1.3988 (1.5153)	
[2022-01-22 10:32:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1110/1251]	eta 0:05:10 lr 0.000500	time 1.8950 (2.1989)	loss 2.6942 (3.5126)	grad_norm 1.3373 (1.5151)	
[2022-01-22 10:33:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1120/1251]	eta 0:04:48 lr 0.000500	time 2.1233 (2.1994)	loss 2.7666 (3.5125)	grad_norm 1.2840 (1.5145)	
[2022-01-22 10:33:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1130/1251]	eta 0:04:26 lr 0.000500	time 1.9893 (2.1985)	loss 3.4970 (3.5116)	grad_norm 1.4763 (1.5144)	
[2022-01-22 10:33:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1140/1251]	eta 0:04:03 lr 0.000500	time 1.8709 (2.1971)	loss 3.5085 (3.5103)	grad_norm 1.5592 (1.5134)	
[2022-01-22 10:34:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1150/1251]	eta 0:03:41 lr 0.000500	time 1.9461 (2.1962)	loss 3.1166 (3.5104)	grad_norm 1.8768 (1.5135)	
[2022-01-22 10:34:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1160/1251]	eta 0:03:19 lr 0.000500	time 2.4596 (2.1970)	loss 3.8695 (3.5096)	grad_norm 1.4931 (1.5128)	
[2022-01-22 10:34:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1170/1251]	eta 0:02:57 lr 0.000500	time 1.8207 (2.1968)	loss 3.6370 (3.5099)	grad_norm 1.3321 (1.5123)	
[2022-01-22 10:35:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1180/1251]	eta 0:02:35 lr 0.000500	time 1.5404 (2.1962)	loss 2.5270 (3.5122)	grad_norm 1.2681 (1.5118)	
[2022-01-22 10:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1190/1251]	eta 0:02:13 lr 0.000500	time 2.1736 (2.1964)	loss 3.2469 (3.5131)	grad_norm 1.3080 (1.5111)	
[2022-01-22 10:36:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1200/1251]	eta 0:01:52 lr 0.000500	time 2.0393 (2.1970)	loss 3.7627 (3.5137)	grad_norm 1.5891 (1.5113)	
[2022-01-22 10:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1210/1251]	eta 0:01:30 lr 0.000500	time 1.6790 (2.1960)	loss 3.2299 (3.5136)	grad_norm 1.7789 (1.5116)	
[2022-01-22 10:36:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1220/1251]	eta 0:01:08 lr 0.000500	time 1.6271 (2.1955)	loss 3.3501 (3.5153)	grad_norm 1.4165 (1.5118)	
[2022-01-22 10:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1230/1251]	eta 0:00:46 lr 0.000500	time 1.8897 (2.1955)	loss 3.5399 (3.5144)	grad_norm 1.3475 (1.5110)	
[2022-01-22 10:37:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1240/1251]	eta 0:00:24 lr 0.000500	time 2.2178 (2.1964)	loss 4.1070 (3.5173)	grad_norm 1.6090 (1.5100)	
[2022-01-22 10:37:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [150/300][1250/1251]	eta 0:00:02 lr 0.000500	time 1.1670 (2.1902)	loss 3.8450 (3.5143)	grad_norm 1.4922 (1.5098)	
[2022-01-22 10:37:44 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 150 training takes 0:45:40
[2022-01-22 10:37:44 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_150 saving......
[2022-01-22 10:37:56 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_150 saved !!!
[2022-01-22 10:38:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 15.683 (15.683)	Loss 1.0901 (1.0901)	Acc@1 74.902 (74.902)	Acc@5 92.578 (92.578)	
[2022-01-22 10:38:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.966 (2.897)	Loss 0.9911 (1.0238)	Acc@1 75.293 (75.968)	Acc@5 94.238 (93.279)	
[2022-01-22 10:38:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.326 (2.378)	Loss 1.0493 (1.0254)	Acc@1 76.660 (76.018)	Acc@5 93.262 (93.257)	
[2022-01-22 10:38:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.919 (2.047)	Loss 1.1309 (1.0258)	Acc@1 73.926 (75.970)	Acc@5 90.723 (93.214)	
[2022-01-22 10:39:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.728 (2.008)	Loss 0.9769 (1.0275)	Acc@1 78.223 (75.972)	Acc@5 93.066 (93.216)	
[2022-01-22 10:39:26 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 75.890 Acc@5 93.238
[2022-01-22 10:39:26 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 75.9%
[2022-01-22 10:39:26 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.30%
[2022-01-22 10:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][0/1251]	eta 7:33:21 lr 0.000500	time 21.7439 (21.7439)	loss 3.8690 (3.8690)	grad_norm 1.6999 (1.6999)	
[2022-01-22 10:40:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][10/1251]	eta 1:25:12 lr 0.000500	time 2.3541 (4.1199)	loss 3.6261 (3.6631)	grad_norm 1.4919 (1.5682)	
[2022-01-22 10:40:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][20/1251]	eta 1:06:12 lr 0.000500	time 1.3533 (3.2271)	loss 3.7242 (3.5721)	grad_norm 1.5494 (1.5615)	
[2022-01-22 10:40:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][30/1251]	eta 0:58:02 lr 0.000500	time 1.4223 (2.8520)	loss 4.0085 (3.5784)	grad_norm 1.6250 (1.5727)	
[2022-01-22 10:41:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][40/1251]	eta 0:54:48 lr 0.000500	time 3.8406 (2.7152)	loss 3.7124 (3.5632)	grad_norm 1.5365 (1.5587)	
[2022-01-22 10:41:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][50/1251]	eta 0:52:31 lr 0.000500	time 2.7443 (2.6245)	loss 3.9043 (3.5416)	grad_norm 1.6147 (1.5269)	
[2022-01-22 10:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][60/1251]	eta 0:51:08 lr 0.000500	time 1.8842 (2.5767)	loss 4.2421 (3.5824)	grad_norm 1.6007 (1.5078)	
[2022-01-22 10:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][70/1251]	eta 0:49:25 lr 0.000500	time 1.8634 (2.5113)	loss 3.7071 (3.5525)	grad_norm 1.4085 (1.4975)	
[2022-01-22 10:42:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][80/1251]	eta 0:48:38 lr 0.000499	time 3.4409 (2.4921)	loss 3.8999 (3.5508)	grad_norm 1.8032 (1.5089)	
[2022-01-22 10:43:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][90/1251]	eta 0:47:33 lr 0.000499	time 2.5686 (2.4578)	loss 3.0813 (3.5605)	grad_norm 1.6417 (1.5023)	
[2022-01-22 10:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][100/1251]	eta 0:46:29 lr 0.000499	time 1.7898 (2.4235)	loss 3.0196 (3.5594)	grad_norm 1.5842 (1.5040)	
[2022-01-22 10:43:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][110/1251]	eta 0:45:42 lr 0.000499	time 1.8389 (2.4040)	loss 3.8570 (3.5565)	grad_norm 1.3346 (1.4986)	
[2022-01-22 10:44:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][120/1251]	eta 0:45:01 lr 0.000499	time 2.8707 (2.3886)	loss 3.8758 (3.5761)	grad_norm 1.5446 (1.5011)	
[2022-01-22 10:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][130/1251]	eta 0:44:19 lr 0.000499	time 2.5442 (2.3723)	loss 2.5032 (3.5917)	grad_norm 1.6093 (1.5006)	
[2022-01-22 10:44:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][140/1251]	eta 0:43:39 lr 0.000499	time 1.9768 (2.3574)	loss 3.8370 (3.6001)	grad_norm 1.3998 (1.4973)	
[2022-01-22 10:45:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][150/1251]	eta 0:43:24 lr 0.000499	time 3.1244 (2.3660)	loss 3.6623 (3.5857)	grad_norm 1.4511 (1.4979)	
[2022-01-22 10:45:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][160/1251]	eta 0:43:02 lr 0.000499	time 2.4027 (2.3674)	loss 3.7988 (3.5919)	grad_norm 1.4861 (1.4967)	
[2022-01-22 10:46:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][170/1251]	eta 0:42:27 lr 0.000499	time 1.9591 (2.3569)	loss 2.7940 (3.5869)	grad_norm 1.4431 (1.4944)	
[2022-01-22 10:46:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][180/1251]	eta 0:41:55 lr 0.000499	time 1.9125 (2.3483)	loss 3.8988 (3.5770)	grad_norm 1.3509 (1.4944)	
[2022-01-22 10:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][190/1251]	eta 0:41:11 lr 0.000499	time 2.1444 (2.3298)	loss 3.8304 (3.5638)	grad_norm 1.5851 (1.4921)	
[2022-01-22 10:47:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][200/1251]	eta 0:40:30 lr 0.000499	time 1.6420 (2.3126)	loss 3.1753 (3.5646)	grad_norm 1.3294 (1.4908)	
[2022-01-22 10:47:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][210/1251]	eta 0:39:58 lr 0.000499	time 2.4407 (2.3041)	loss 3.5746 (3.5723)	grad_norm 1.6738 (1.4911)	
[2022-01-22 10:47:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][220/1251]	eta 0:39:27 lr 0.000499	time 2.4982 (2.2961)	loss 3.9434 (3.5722)	grad_norm 1.5698 (1.4903)	
[2022-01-22 10:48:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][230/1251]	eta 0:39:04 lr 0.000499	time 2.7862 (2.2964)	loss 4.4810 (3.5781)	grad_norm 1.9170 (1.4942)	
[2022-01-22 10:48:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][240/1251]	eta 0:38:42 lr 0.000499	time 2.4595 (2.2968)	loss 3.7077 (3.5787)	grad_norm 1.6249 (1.4986)	
[2022-01-22 10:49:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][250/1251]	eta 0:38:18 lr 0.000499	time 2.4140 (2.2960)	loss 4.0032 (3.5809)	grad_norm 1.4939 (1.4990)	
[2022-01-22 10:49:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][260/1251]	eta 0:37:52 lr 0.000499	time 1.9656 (2.2932)	loss 3.3465 (3.5889)	grad_norm 1.4872 (1.4988)	
[2022-01-22 10:49:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][270/1251]	eta 0:37:28 lr 0.000499	time 2.8337 (2.2924)	loss 2.7346 (3.5803)	grad_norm 1.3281 (1.4973)	
[2022-01-22 10:50:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][280/1251]	eta 0:36:59 lr 0.000499	time 2.2601 (2.2860)	loss 3.0610 (3.5681)	grad_norm 1.3737 (1.4973)	
[2022-01-22 10:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][290/1251]	eta 0:36:32 lr 0.000499	time 1.9072 (2.2815)	loss 2.8286 (3.5626)	grad_norm 1.6558 (1.4968)	
[2022-01-22 10:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][300/1251]	eta 0:36:06 lr 0.000499	time 2.0263 (2.2779)	loss 3.8691 (3.5551)	grad_norm 1.4352 (1.4967)	
[2022-01-22 10:51:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][310/1251]	eta 0:35:39 lr 0.000499	time 2.5059 (2.2741)	loss 2.3859 (3.5502)	grad_norm 1.5724 (1.4964)	
[2022-01-22 10:51:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][320/1251]	eta 0:35:13 lr 0.000498	time 1.9845 (2.2698)	loss 3.3937 (3.5531)	grad_norm 1.5352 (1.4963)	
[2022-01-22 10:51:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][330/1251]	eta 0:34:51 lr 0.000498	time 2.1653 (2.2708)	loss 3.0647 (3.5509)	grad_norm 1.6706 (1.4987)	
[2022-01-22 10:52:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][340/1251]	eta 0:34:27 lr 0.000498	time 1.8094 (2.2692)	loss 3.6652 (3.5540)	grad_norm 1.5353 (1.4993)	
[2022-01-22 10:52:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][350/1251]	eta 0:34:07 lr 0.000498	time 3.2683 (2.2725)	loss 3.7003 (3.5526)	grad_norm 1.4753 (1.5007)	
[2022-01-22 10:53:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][360/1251]	eta 0:33:38 lr 0.000498	time 1.7759 (2.2651)	loss 3.8763 (3.5537)	grad_norm 1.5448 (1.5022)	
[2022-01-22 10:53:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][370/1251]	eta 0:33:10 lr 0.000498	time 2.6037 (2.2598)	loss 3.6859 (3.5520)	grad_norm 1.5730 (1.5049)	
[2022-01-22 10:53:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][380/1251]	eta 0:32:39 lr 0.000498	time 1.5366 (2.2493)	loss 4.1407 (3.5546)	grad_norm 1.6618 (1.5056)	
[2022-01-22 10:54:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][390/1251]	eta 0:32:13 lr 0.000498	time 1.9449 (2.2462)	loss 3.6882 (3.5568)	grad_norm 1.5661 (1.5053)	
[2022-01-22 10:54:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][400/1251]	eta 0:31:52 lr 0.000498	time 2.8365 (2.2476)	loss 2.4424 (3.5585)	grad_norm 1.2377 (1.5028)	
[2022-01-22 10:54:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][410/1251]	eta 0:31:32 lr 0.000498	time 1.6066 (2.2499)	loss 3.5332 (3.5615)	grad_norm 1.8173 (1.5037)	
[2022-01-22 10:55:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][420/1251]	eta 0:31:10 lr 0.000498	time 1.9391 (2.2514)	loss 3.8583 (3.5594)	grad_norm 1.3757 (1.5051)	
[2022-01-22 10:55:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][430/1251]	eta 0:30:49 lr 0.000498	time 1.9489 (2.2523)	loss 3.1023 (3.5569)	grad_norm 1.6994 (1.5068)	
[2022-01-22 10:55:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][440/1251]	eta 0:30:25 lr 0.000498	time 2.0055 (2.2513)	loss 3.5726 (3.5574)	grad_norm 1.6307 (1.5096)	
[2022-01-22 10:56:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][450/1251]	eta 0:30:01 lr 0.000498	time 1.7695 (2.2494)	loss 3.5863 (3.5519)	grad_norm 1.2758 (1.5090)	
[2022-01-22 10:56:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][460/1251]	eta 0:29:38 lr 0.000498	time 1.9706 (2.2487)	loss 3.2069 (3.5485)	grad_norm 1.6958 (1.5094)	
[2022-01-22 10:57:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][470/1251]	eta 0:29:13 lr 0.000498	time 1.9388 (2.2451)	loss 3.3806 (3.5505)	grad_norm 1.5058 (1.5081)	
[2022-01-22 10:57:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][480/1251]	eta 0:28:50 lr 0.000498	time 2.0044 (2.2442)	loss 3.8613 (3.5493)	grad_norm 1.8746 (1.5086)	
[2022-01-22 10:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][490/1251]	eta 0:28:27 lr 0.000498	time 1.9178 (2.2437)	loss 3.9570 (3.5451)	grad_norm 1.3069 (1.5068)	
[2022-01-22 10:58:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][500/1251]	eta 0:28:03 lr 0.000498	time 1.8394 (2.2420)	loss 3.9664 (3.5511)	grad_norm 1.2207 (1.5065)	
[2022-01-22 10:58:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][510/1251]	eta 0:27:39 lr 0.000498	time 1.7125 (2.2391)	loss 2.9483 (3.5529)	grad_norm 1.4664 (1.5075)	
[2022-01-22 10:58:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][520/1251]	eta 0:27:16 lr 0.000498	time 2.2882 (2.2388)	loss 3.9449 (3.5542)	grad_norm 1.5176 (1.5091)	
[2022-01-22 10:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][530/1251]	eta 0:26:53 lr 0.000498	time 1.6326 (2.2377)	loss 3.8221 (3.5535)	grad_norm 1.2822 (1.5095)	
[2022-01-22 10:59:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][540/1251]	eta 0:26:30 lr 0.000498	time 1.7628 (2.2376)	loss 4.2668 (3.5577)	grad_norm 1.6881 (1.5109)	
[2022-01-22 10:59:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][550/1251]	eta 0:26:07 lr 0.000498	time 1.8653 (2.2362)	loss 4.4128 (3.5589)	grad_norm 1.4787 (1.5103)	
[2022-01-22 11:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][560/1251]	eta 0:25:44 lr 0.000497	time 2.2124 (2.2349)	loss 3.4215 (3.5572)	grad_norm 1.4791 (1.5101)	
[2022-01-22 11:00:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][570/1251]	eta 0:25:20 lr 0.000497	time 1.7293 (2.2330)	loss 2.9669 (3.5590)	grad_norm 1.4409 (1.5104)	
[2022-01-22 11:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][580/1251]	eta 0:24:56 lr 0.000497	time 1.7820 (2.2307)	loss 4.0571 (3.5590)	grad_norm 1.7799 (1.5109)	
[2022-01-22 11:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][590/1251]	eta 0:24:32 lr 0.000497	time 2.1277 (2.2284)	loss 3.7723 (3.5592)	grad_norm 1.6555 (1.5117)	
[2022-01-22 11:01:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][600/1251]	eta 0:24:09 lr 0.000497	time 2.7822 (2.2267)	loss 3.0694 (3.5585)	grad_norm 1.4372 (1.5116)	
[2022-01-22 11:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][610/1251]	eta 0:23:48 lr 0.000497	time 1.7008 (2.2293)	loss 3.5923 (3.5603)	grad_norm 1.4501 (1.5133)	
[2022-01-22 11:02:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][620/1251]	eta 0:23:27 lr 0.000497	time 2.8977 (2.2300)	loss 3.4658 (3.5574)	grad_norm 1.4801 (1.5128)	
[2022-01-22 11:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][630/1251]	eta 0:23:04 lr 0.000497	time 2.1795 (2.2291)	loss 3.8596 (3.5571)	grad_norm 1.7749 (1.5136)	
[2022-01-22 11:03:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][640/1251]	eta 0:22:40 lr 0.000497	time 1.8850 (2.2261)	loss 3.7861 (3.5549)	grad_norm 1.3228 (1.5137)	
[2022-01-22 11:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][650/1251]	eta 0:22:17 lr 0.000497	time 2.2277 (2.2255)	loss 4.0789 (3.5575)	grad_norm 1.2744 (1.5119)	
[2022-01-22 11:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][660/1251]	eta 0:21:54 lr 0.000497	time 2.5766 (2.2243)	loss 3.9134 (3.5576)	grad_norm 1.4002 (1.5116)	
[2022-01-22 11:04:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][670/1251]	eta 0:21:31 lr 0.000497	time 2.2407 (2.2235)	loss 3.8547 (3.5577)	grad_norm 1.5601 (1.5113)	
[2022-01-22 11:04:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][680/1251]	eta 0:21:09 lr 0.000497	time 2.7481 (2.2235)	loss 4.2006 (3.5570)	grad_norm 1.5895 (1.5108)	
[2022-01-22 11:05:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][690/1251]	eta 0:20:48 lr 0.000497	time 2.3607 (2.2247)	loss 2.6308 (3.5571)	grad_norm 1.4456 (1.5104)	
[2022-01-22 11:05:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][700/1251]	eta 0:20:25 lr 0.000497	time 2.1541 (2.2244)	loss 2.9674 (3.5534)	grad_norm 1.3845 (1.5093)	
[2022-01-22 11:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][710/1251]	eta 0:20:02 lr 0.000497	time 1.9062 (2.2230)	loss 2.3935 (3.5520)	grad_norm 1.4712 (1.5078)	
[2022-01-22 11:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][720/1251]	eta 0:19:39 lr 0.000497	time 1.9086 (2.2215)	loss 4.0668 (3.5526)	grad_norm 1.7634 (1.5084)	
[2022-01-22 11:06:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][730/1251]	eta 0:19:17 lr 0.000497	time 1.7758 (2.2212)	loss 3.5278 (3.5539)	grad_norm 1.4115 (1.5078)	
[2022-01-22 11:06:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][740/1251]	eta 0:18:55 lr 0.000497	time 2.5112 (2.2211)	loss 3.0194 (3.5561)	grad_norm 1.3779 (1.5084)	
[2022-01-22 11:07:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][750/1251]	eta 0:18:33 lr 0.000497	time 2.0493 (2.2217)	loss 4.0546 (3.5556)	grad_norm 1.5739 (1.5089)	
[2022-01-22 11:07:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][760/1251]	eta 0:18:11 lr 0.000497	time 2.5377 (2.2229)	loss 3.8926 (3.5558)	grad_norm 1.4441 (1.5089)	
[2022-01-22 11:07:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][770/1251]	eta 0:17:48 lr 0.000497	time 1.9057 (2.2209)	loss 3.5238 (3.5592)	grad_norm 1.3919 (1.5078)	
[2022-01-22 11:08:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][780/1251]	eta 0:17:24 lr 0.000497	time 2.2421 (2.2180)	loss 3.6409 (3.5591)	grad_norm 1.3816 (1.5076)	
[2022-01-22 11:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][790/1251]	eta 0:17:01 lr 0.000497	time 1.6162 (2.2165)	loss 2.6190 (3.5569)	grad_norm 1.5047 (1.5081)	
[2022-01-22 11:09:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][800/1251]	eta 0:16:39 lr 0.000497	time 2.1968 (2.2166)	loss 3.8713 (3.5601)	grad_norm 1.4441 (1.5076)	
[2022-01-22 11:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][810/1251]	eta 0:16:17 lr 0.000496	time 2.5676 (2.2167)	loss 4.0374 (3.5629)	grad_norm 1.8042 (1.5082)	
[2022-01-22 11:09:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][820/1251]	eta 0:15:56 lr 0.000496	time 3.2934 (2.2183)	loss 3.7401 (3.5635)	grad_norm 1.7536 (1.5099)	
[2022-01-22 11:10:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][830/1251]	eta 0:15:34 lr 0.000496	time 2.1632 (2.2189)	loss 3.8766 (3.5640)	grad_norm 1.4167 (1.5102)	
[2022-01-22 11:10:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][840/1251]	eta 0:15:12 lr 0.000496	time 2.7019 (2.2210)	loss 2.8885 (3.5641)	grad_norm 1.3396 (1.5100)	
[2022-01-22 11:10:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][850/1251]	eta 0:14:50 lr 0.000496	time 2.4694 (2.2213)	loss 3.5411 (3.5609)	grad_norm 1.4915 (1.5094)	
[2022-01-22 11:11:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][860/1251]	eta 0:14:27 lr 0.000496	time 1.9432 (2.2195)	loss 3.4928 (3.5633)	grad_norm 1.5811 (1.5104)	
[2022-01-22 11:11:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][870/1251]	eta 0:14:04 lr 0.000496	time 1.8014 (2.2177)	loss 2.9923 (3.5633)	grad_norm 1.6964 (1.5105)	
[2022-01-22 11:12:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][880/1251]	eta 0:13:44 lr 0.000496	time 3.5735 (2.2213)	loss 2.8417 (3.5665)	grad_norm 1.4954 (1.5112)	
[2022-01-22 11:12:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][890/1251]	eta 0:13:22 lr 0.000496	time 2.2596 (2.2217)	loss 3.2268 (3.5663)	grad_norm 1.4625 (1.5112)	
[2022-01-22 11:12:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][900/1251]	eta 0:12:59 lr 0.000496	time 1.9034 (2.2201)	loss 4.1854 (3.5661)	grad_norm 1.4482 (1.5112)	
[2022-01-22 11:13:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][910/1251]	eta 0:12:36 lr 0.000496	time 2.0425 (2.2177)	loss 3.5455 (3.5654)	grad_norm 1.3892 (1.5108)	
[2022-01-22 11:13:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][920/1251]	eta 0:12:14 lr 0.000496	time 3.4790 (2.2189)	loss 3.9182 (3.5670)	grad_norm 1.5082 (1.5110)	
[2022-01-22 11:13:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][930/1251]	eta 0:11:51 lr 0.000496	time 2.3278 (2.2174)	loss 2.5805 (3.5653)	grad_norm 1.6436 (1.5113)	
[2022-01-22 11:14:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][940/1251]	eta 0:11:29 lr 0.000496	time 2.1344 (2.2183)	loss 3.5811 (3.5640)	grad_norm 1.5914 (1.5130)	
[2022-01-22 11:14:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][950/1251]	eta 0:11:07 lr 0.000496	time 1.7193 (2.2183)	loss 3.1621 (3.5624)	grad_norm 1.2429 (1.5129)	
[2022-01-22 11:14:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][960/1251]	eta 0:10:45 lr 0.000496	time 3.8343 (2.2183)	loss 3.2657 (3.5618)	grad_norm 1.5868 (1.5129)	
[2022-01-22 11:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][970/1251]	eta 0:10:23 lr 0.000496	time 1.8468 (2.2186)	loss 2.9439 (3.5613)	grad_norm 1.4129 (1.5119)	
[2022-01-22 11:15:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][980/1251]	eta 0:10:01 lr 0.000496	time 2.0324 (2.2199)	loss 2.5882 (3.5592)	grad_norm 1.4111 (1.5115)	
[2022-01-22 11:16:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][990/1251]	eta 0:09:38 lr 0.000496	time 1.6582 (2.2181)	loss 3.6326 (3.5594)	grad_norm 1.9435 (1.5117)	
[2022-01-22 11:16:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1000/1251]	eta 0:09:16 lr 0.000496	time 3.8677 (2.2190)	loss 3.5526 (3.5600)	grad_norm 1.2289 (1.5115)	
[2022-01-22 11:16:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1010/1251]	eta 0:08:54 lr 0.000496	time 2.2907 (2.2173)	loss 3.9304 (3.5645)	grad_norm 1.5741 (1.5107)	
[2022-01-22 11:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1020/1251]	eta 0:08:31 lr 0.000496	time 2.2146 (2.2155)	loss 3.8438 (3.5652)	grad_norm 1.4644 (1.5097)	
[2022-01-22 11:17:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1030/1251]	eta 0:08:09 lr 0.000496	time 2.2642 (2.2136)	loss 3.4437 (3.5668)	grad_norm 1.3164 (1.5103)	
[2022-01-22 11:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1040/1251]	eta 0:07:46 lr 0.000496	time 1.6427 (2.2123)	loss 3.6787 (3.5693)	grad_norm 1.5227 (1.5103)	
[2022-01-22 11:18:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1050/1251]	eta 0:07:24 lr 0.000495	time 2.9379 (2.2118)	loss 3.4681 (3.5685)	grad_norm 1.5072 (1.5098)	
[2022-01-22 11:18:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1060/1251]	eta 0:07:02 lr 0.000495	time 2.7004 (2.2121)	loss 2.6189 (3.5660)	grad_norm 1.4148 (1.5096)	
[2022-01-22 11:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1070/1251]	eta 0:06:40 lr 0.000495	time 3.3798 (2.2132)	loss 3.6040 (3.5676)	grad_norm 1.5055 (1.5087)	
[2022-01-22 11:19:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1080/1251]	eta 0:06:18 lr 0.000495	time 1.9960 (2.2136)	loss 2.6127 (3.5681)	grad_norm 1.4360 (1.5079)	
[2022-01-22 11:19:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1090/1251]	eta 0:05:56 lr 0.000495	time 2.5645 (2.2146)	loss 3.5916 (3.5684)	grad_norm 1.5498 (1.5069)	
[2022-01-22 11:20:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1100/1251]	eta 0:05:34 lr 0.000495	time 2.9227 (2.2155)	loss 3.4819 (3.5693)	grad_norm 1.2355 (1.5062)	
[2022-01-22 11:20:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1110/1251]	eta 0:05:12 lr 0.000495	time 2.5741 (2.2163)	loss 3.9681 (3.5699)	grad_norm 1.3653 (1.5056)	
[2022-01-22 11:20:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1120/1251]	eta 0:04:50 lr 0.000495	time 1.7172 (2.2142)	loss 3.9532 (3.5717)	grad_norm 1.5589 (1.5052)	
[2022-01-22 11:21:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1130/1251]	eta 0:04:27 lr 0.000495	time 1.9761 (2.2141)	loss 3.6727 (3.5682)	grad_norm 1.3523 (1.5049)	
[2022-01-22 11:21:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1140/1251]	eta 0:04:05 lr 0.000495	time 2.1056 (2.2125)	loss 3.1793 (3.5668)	grad_norm 1.6620 (1.5053)	
[2022-01-22 11:21:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1150/1251]	eta 0:03:43 lr 0.000495	time 2.2989 (2.2132)	loss 3.4509 (3.5656)	grad_norm 1.5048 (1.5046)	
[2022-01-22 11:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1160/1251]	eta 0:03:21 lr 0.000495	time 1.4531 (2.2132)	loss 3.7652 (3.5660)	grad_norm 1.4956 (1.5037)	
[2022-01-22 11:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1170/1251]	eta 0:02:59 lr 0.000495	time 2.8086 (2.2140)	loss 3.0273 (3.5668)	grad_norm 1.4198 (1.5042)	
[2022-01-22 11:23:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1180/1251]	eta 0:02:37 lr 0.000495	time 1.6002 (2.2137)	loss 3.2564 (3.5693)	grad_norm 1.4382 (1.5042)	
[2022-01-22 11:23:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1190/1251]	eta 0:02:15 lr 0.000495	time 2.3331 (2.2137)	loss 3.6075 (3.5706)	grad_norm 1.3761 (1.5049)	
[2022-01-22 11:23:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1200/1251]	eta 0:01:52 lr 0.000495	time 1.5044 (2.2150)	loss 2.4190 (3.5696)	grad_norm 1.5229 (1.5053)	
[2022-01-22 11:24:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1210/1251]	eta 0:01:30 lr 0.000495	time 1.9662 (2.2148)	loss 3.0152 (3.5690)	grad_norm 1.7768 (1.5062)	
[2022-01-22 11:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1220/1251]	eta 0:01:08 lr 0.000495	time 1.7112 (2.2135)	loss 2.9140 (3.5682)	grad_norm 1.5503 (1.5065)	
[2022-01-22 11:24:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1230/1251]	eta 0:00:46 lr 0.000495	time 2.7760 (2.2131)	loss 3.6055 (3.5685)	grad_norm 1.4280 (1.5071)	
[2022-01-22 11:25:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1240/1251]	eta 0:00:24 lr 0.000495	time 1.1892 (2.2133)	loss 4.2022 (3.5706)	grad_norm 1.5378 (1.5072)	
[2022-01-22 11:25:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [151/300][1250/1251]	eta 0:00:02 lr 0.000495	time 1.2155 (2.2072)	loss 3.7926 (3.5721)	grad_norm 1.6656 (1.5068)	
[2022-01-22 11:25:28 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 151 training takes 0:46:01
[2022-01-22 11:25:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.393 (18.393)	Loss 1.0198 (1.0198)	Acc@1 76.660 (76.660)	Acc@5 95.020 (95.020)	
[2022-01-22 11:26:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.981 (3.090)	Loss 1.0534 (1.0304)	Acc@1 76.172 (75.994)	Acc@5 93.457 (93.652)	
[2022-01-22 11:26:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 2.532 (2.506)	Loss 1.0710 (1.0350)	Acc@1 76.074 (75.972)	Acc@5 92.383 (93.466)	
[2022-01-22 11:26:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.418 (2.212)	Loss 0.9635 (1.0279)	Acc@1 77.930 (76.049)	Acc@5 93.555 (93.611)	
[2022-01-22 11:26:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.068 (2.141)	Loss 0.9889 (1.0318)	Acc@1 78.125 (76.053)	Acc@5 93.262 (93.509)	
[2022-01-22 11:27:04 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.040 Acc@5 93.436
[2022-01-22 11:27:04 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.0%
[2022-01-22 11:27:04 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.30%
[2022-01-22 11:27:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][0/1251]	eta 7:36:39 lr 0.000495	time 21.9023 (21.9023)	loss 4.3440 (4.3440)	grad_norm 1.6774 (1.6774)	
[2022-01-22 11:27:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][10/1251]	eta 1:24:21 lr 0.000495	time 2.1797 (4.0785)	loss 3.6726 (3.7272)	grad_norm 1.8703 (1.5849)	
[2022-01-22 11:28:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][20/1251]	eta 1:05:26 lr 0.000495	time 2.2594 (3.1894)	loss 2.9167 (3.5663)	grad_norm 1.4053 (1.5344)	
[2022-01-22 11:28:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][30/1251]	eta 0:57:58 lr 0.000495	time 1.5621 (2.8491)	loss 3.0309 (3.5263)	grad_norm 1.4531 (1.5676)	
[2022-01-22 11:28:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][40/1251]	eta 0:53:57 lr 0.000494	time 2.8432 (2.6731)	loss 2.7909 (3.5237)	grad_norm 1.2298 (1.5442)	
[2022-01-22 11:29:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][50/1251]	eta 0:52:16 lr 0.000494	time 1.8666 (2.6113)	loss 3.1652 (3.5549)	grad_norm 1.5042 (1.5212)	
[2022-01-22 11:29:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][60/1251]	eta 0:50:55 lr 0.000494	time 2.4917 (2.5654)	loss 2.6745 (3.5472)	grad_norm 1.5241 (1.5140)	
[2022-01-22 11:30:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][70/1251]	eta 0:49:30 lr 0.000494	time 1.8983 (2.5149)	loss 4.0100 (3.5610)	grad_norm 1.5281 (1.5152)	
[2022-01-22 11:30:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][80/1251]	eta 0:48:44 lr 0.000494	time 3.3360 (2.4973)	loss 3.6741 (3.5561)	grad_norm 1.3982 (1.5064)	
[2022-01-22 11:30:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][90/1251]	eta 0:47:45 lr 0.000494	time 2.5404 (2.4680)	loss 3.0276 (3.5382)	grad_norm 2.0775 (1.5226)	
[2022-01-22 11:31:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][100/1251]	eta 0:46:28 lr 0.000494	time 1.8407 (2.4230)	loss 4.0135 (3.5464)	grad_norm 1.4861 (1.5252)	
[2022-01-22 11:31:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][110/1251]	eta 0:45:20 lr 0.000494	time 1.9072 (2.3841)	loss 3.8611 (3.5366)	grad_norm 1.7021 (1.5224)	
[2022-01-22 11:31:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][120/1251]	eta 0:44:28 lr 0.000494	time 2.5634 (2.3593)	loss 3.9489 (3.5340)	grad_norm 2.2328 (1.5277)	
[2022-01-22 11:32:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][130/1251]	eta 0:43:48 lr 0.000494	time 2.1308 (2.3446)	loss 4.0674 (3.5488)	grad_norm 1.3622 (1.5285)	
[2022-01-22 11:32:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][140/1251]	eta 0:43:36 lr 0.000494	time 2.9956 (2.3550)	loss 4.0482 (3.5613)	grad_norm 1.6612 (1.5251)	
[2022-01-22 11:32:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][150/1251]	eta 0:42:53 lr 0.000494	time 1.8838 (2.3373)	loss 3.8031 (3.5603)	grad_norm 1.5801 (1.5285)	
[2022-01-22 11:33:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][160/1251]	eta 0:42:20 lr 0.000494	time 2.7387 (2.3290)	loss 2.9839 (3.5537)	grad_norm 1.4098 (1.5271)	
[2022-01-22 11:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][170/1251]	eta 0:41:43 lr 0.000494	time 1.9480 (2.3163)	loss 3.0035 (3.5517)	grad_norm 1.6535 (1.5225)	
[2022-01-22 11:34:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][180/1251]	eta 0:41:10 lr 0.000494	time 3.3197 (2.3069)	loss 3.4045 (3.5550)	grad_norm 1.4478 (1.5178)	
[2022-01-22 11:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][190/1251]	eta 0:40:36 lr 0.000494	time 2.2099 (2.2965)	loss 3.7644 (3.5695)	grad_norm 1.3975 (1.5150)	
[2022-01-22 11:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][200/1251]	eta 0:40:14 lr 0.000494	time 2.8521 (2.2970)	loss 2.4181 (3.5613)	grad_norm 1.6599 (1.5124)	
[2022-01-22 11:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][210/1251]	eta 0:39:45 lr 0.000494	time 2.6679 (2.2919)	loss 3.0331 (3.5550)	grad_norm 1.4857 (1.5123)	
[2022-01-22 11:35:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][220/1251]	eta 0:39:12 lr 0.000494	time 2.1698 (2.2821)	loss 2.3732 (3.5522)	grad_norm 1.7546 (1.5118)	
[2022-01-22 11:35:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][230/1251]	eta 0:38:49 lr 0.000494	time 3.0427 (2.2816)	loss 4.0962 (3.5451)	grad_norm 1.4020 (1.5111)	
[2022-01-22 11:36:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][240/1251]	eta 0:38:25 lr 0.000494	time 2.6981 (2.2804)	loss 2.8228 (3.5548)	grad_norm 1.6650 (1.5135)	
[2022-01-22 11:36:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][250/1251]	eta 0:38:01 lr 0.000494	time 1.5313 (2.2789)	loss 3.6376 (3.5511)	grad_norm 1.5670 (1.5152)	
[2022-01-22 11:36:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][260/1251]	eta 0:37:36 lr 0.000494	time 2.1713 (2.2773)	loss 3.0818 (3.5478)	grad_norm 1.4594 (1.5173)	
[2022-01-22 11:37:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][270/1251]	eta 0:37:16 lr 0.000494	time 3.0854 (2.2803)	loss 3.9536 (3.5537)	grad_norm 1.3785 (1.5145)	
[2022-01-22 11:37:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][280/1251]	eta 0:36:44 lr 0.000493	time 2.0468 (2.2707)	loss 3.8644 (3.5596)	grad_norm 1.5053 (1.5118)	
[2022-01-22 11:38:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][290/1251]	eta 0:36:09 lr 0.000493	time 1.5215 (2.2580)	loss 3.6583 (3.5614)	grad_norm 1.4305 (1.5105)	
[2022-01-22 11:38:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][300/1251]	eta 0:35:38 lr 0.000493	time 1.8836 (2.2491)	loss 2.4578 (3.5624)	grad_norm 1.5468 (1.5102)	
[2022-01-22 11:38:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][310/1251]	eta 0:35:08 lr 0.000493	time 2.1616 (2.2409)	loss 3.8751 (3.5646)	grad_norm 1.6103 (1.5115)	
[2022-01-22 11:39:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][320/1251]	eta 0:34:43 lr 0.000493	time 1.9499 (2.2378)	loss 2.7688 (3.5643)	grad_norm 1.5666 (1.5112)	
[2022-01-22 11:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][330/1251]	eta 0:34:19 lr 0.000493	time 2.1361 (2.2360)	loss 3.2545 (3.5603)	grad_norm 1.4901 (1.5142)	
[2022-01-22 11:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][340/1251]	eta 0:33:54 lr 0.000493	time 1.9413 (2.2330)	loss 3.6522 (3.5576)	grad_norm 1.5814 (1.5140)	
[2022-01-22 11:40:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][350/1251]	eta 0:33:35 lr 0.000493	time 2.7983 (2.2365)	loss 3.1376 (3.5589)	grad_norm 1.4923 (1.5132)	
[2022-01-22 11:40:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][360/1251]	eta 0:33:11 lr 0.000493	time 1.9549 (2.2354)	loss 3.8126 (3.5522)	grad_norm 1.5557 (1.5133)	
[2022-01-22 11:40:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][370/1251]	eta 0:32:49 lr 0.000493	time 2.4294 (2.2355)	loss 2.9554 (3.5500)	grad_norm 1.4361 (1.5135)	
[2022-01-22 11:41:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][380/1251]	eta 0:32:25 lr 0.000493	time 1.9474 (2.2337)	loss 3.6427 (3.5437)	grad_norm 1.6561 (1.5141)	
[2022-01-22 11:41:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][390/1251]	eta 0:32:06 lr 0.000493	time 3.4657 (2.2377)	loss 3.3448 (3.5413)	grad_norm 1.6105 (1.5135)	
[2022-01-22 11:42:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][400/1251]	eta 0:31:45 lr 0.000493	time 2.4853 (2.2397)	loss 3.5768 (3.5439)	grad_norm 1.6777 (1.5153)	
[2022-01-22 11:42:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][410/1251]	eta 0:31:21 lr 0.000493	time 2.5326 (2.2377)	loss 4.0630 (3.5445)	grad_norm 2.7175 (1.5209)	
[2022-01-22 11:42:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][420/1251]	eta 0:30:54 lr 0.000493	time 1.7772 (2.2317)	loss 3.4140 (3.5425)	grad_norm 1.6245 (1.5249)	
[2022-01-22 11:43:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][430/1251]	eta 0:30:29 lr 0.000493	time 3.5942 (2.2287)	loss 4.1426 (3.5383)	grad_norm 1.3085 (1.5224)	
[2022-01-22 11:43:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][440/1251]	eta 0:30:06 lr 0.000493	time 1.9710 (2.2274)	loss 3.2564 (3.5307)	grad_norm 2.1007 (1.5233)	
[2022-01-22 11:43:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][450/1251]	eta 0:29:45 lr 0.000493	time 1.8436 (2.2296)	loss 3.5859 (3.5288)	grad_norm 1.5380 (1.5219)	
[2022-01-22 11:44:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][460/1251]	eta 0:29:23 lr 0.000493	time 2.0045 (2.2288)	loss 2.8924 (3.5291)	grad_norm 1.7909 (1.5226)	
[2022-01-22 11:44:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][470/1251]	eta 0:29:00 lr 0.000493	time 3.0744 (2.2284)	loss 2.7717 (3.5310)	grad_norm 1.5441 (1.5233)	
[2022-01-22 11:44:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][480/1251]	eta 0:28:37 lr 0.000493	time 2.0425 (2.2271)	loss 3.3701 (3.5319)	grad_norm 1.3696 (1.5225)	
[2022-01-22 11:45:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][490/1251]	eta 0:28:11 lr 0.000493	time 1.8748 (2.2230)	loss 3.7787 (3.5339)	grad_norm 1.4787 (1.5222)	
[2022-01-22 11:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][500/1251]	eta 0:27:46 lr 0.000493	time 1.9939 (2.2196)	loss 3.6564 (3.5371)	grad_norm 1.3487 (1.5215)	
[2022-01-22 11:45:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][510/1251]	eta 0:27:26 lr 0.000493	time 2.5967 (2.2223)	loss 3.7587 (3.5347)	grad_norm 1.2859 (1.5217)	
[2022-01-22 11:46:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][520/1251]	eta 0:27:04 lr 0.000492	time 1.9908 (2.2228)	loss 3.3909 (3.5293)	grad_norm 1.6124 (1.5213)	
[2022-01-22 11:46:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][530/1251]	eta 0:26:42 lr 0.000492	time 2.1902 (2.2222)	loss 3.9025 (3.5308)	grad_norm 1.4128 (1.5205)	
[2022-01-22 11:47:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][540/1251]	eta 0:26:18 lr 0.000492	time 2.2751 (2.2205)	loss 3.9459 (3.5356)	grad_norm 1.4761 (1.5219)	
[2022-01-22 11:47:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][550/1251]	eta 0:25:54 lr 0.000492	time 1.8950 (2.2169)	loss 3.6928 (3.5349)	grad_norm 1.7499 (1.5220)	
[2022-01-22 11:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][560/1251]	eta 0:25:29 lr 0.000492	time 1.9875 (2.2134)	loss 3.2971 (3.5353)	grad_norm 1.4984 (1.5246)	
[2022-01-22 11:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][570/1251]	eta 0:25:06 lr 0.000492	time 2.3716 (2.2126)	loss 3.8485 (3.5330)	grad_norm 1.8964 (1.5258)	
[2022-01-22 11:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][580/1251]	eta 0:24:43 lr 0.000492	time 2.2364 (2.2109)	loss 4.0304 (3.5285)	grad_norm 1.7054 (1.5259)	
[2022-01-22 11:48:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][590/1251]	eta 0:24:21 lr 0.000492	time 2.4905 (2.2105)	loss 2.6431 (3.5229)	grad_norm 1.5713 (1.5266)	
[2022-01-22 11:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][600/1251]	eta 0:23:59 lr 0.000492	time 2.2185 (2.2107)	loss 3.7693 (3.5193)	grad_norm 1.5359 (1.5267)	
[2022-01-22 11:49:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][610/1251]	eta 0:23:39 lr 0.000492	time 1.6623 (2.2142)	loss 2.9022 (3.5204)	grad_norm 1.4045 (1.5265)	
[2022-01-22 11:49:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][620/1251]	eta 0:23:17 lr 0.000492	time 2.1074 (2.2148)	loss 3.8477 (3.5231)	grad_norm 1.5994 (1.5257)	
[2022-01-22 11:50:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][630/1251]	eta 0:22:56 lr 0.000492	time 2.1454 (2.2161)	loss 3.4526 (3.5213)	grad_norm 1.2981 (1.5257)	
[2022-01-22 11:50:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][640/1251]	eta 0:22:32 lr 0.000492	time 1.8593 (2.2133)	loss 3.6757 (3.5246)	grad_norm 1.5983 (1.5258)	
[2022-01-22 11:51:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][650/1251]	eta 0:22:08 lr 0.000492	time 1.5949 (2.2110)	loss 2.9816 (3.5239)	grad_norm 1.3011 (1.5242)	
[2022-01-22 11:51:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][660/1251]	eta 0:21:46 lr 0.000492	time 1.9227 (2.2102)	loss 3.4295 (3.5221)	grad_norm 1.3773 (1.5239)	
[2022-01-22 11:51:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][670/1251]	eta 0:21:25 lr 0.000492	time 2.4363 (2.2124)	loss 4.0509 (3.5240)	grad_norm 1.3502 (1.5226)	
[2022-01-22 11:52:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][680/1251]	eta 0:21:02 lr 0.000492	time 2.2769 (2.2109)	loss 2.4472 (3.5272)	grad_norm 1.7814 (1.5224)	
[2022-01-22 11:52:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][690/1251]	eta 0:20:39 lr 0.000492	time 1.8818 (2.2094)	loss 3.0260 (3.5265)	grad_norm 1.4729 (1.5216)	
[2022-01-22 11:52:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][700/1251]	eta 0:20:17 lr 0.000492	time 1.6468 (2.2092)	loss 2.9933 (3.5281)	grad_norm 1.5109 (1.5224)	
[2022-01-22 11:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][710/1251]	eta 0:19:57 lr 0.000492	time 3.6177 (2.2132)	loss 4.2490 (3.5281)	grad_norm 1.3600 (1.5214)	
[2022-01-22 11:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][720/1251]	eta 0:19:34 lr 0.000492	time 2.0297 (2.2115)	loss 4.1412 (3.5274)	grad_norm 1.8229 (1.5212)	
[2022-01-22 11:53:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][730/1251]	eta 0:19:10 lr 0.000492	time 2.0725 (2.2087)	loss 3.2849 (3.5279)	grad_norm 1.7860 (1.5227)	
[2022-01-22 11:54:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][740/1251]	eta 0:18:47 lr 0.000492	time 1.8310 (2.2061)	loss 2.9604 (3.5270)	grad_norm 1.8497 (1.5266)	
[2022-01-22 11:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][750/1251]	eta 0:18:24 lr 0.000492	time 2.3408 (2.2049)	loss 3.4368 (3.5243)	grad_norm 1.4844 (1.5273)	
[2022-01-22 11:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][760/1251]	eta 0:18:01 lr 0.000491	time 1.6109 (2.2029)	loss 3.4641 (3.5252)	grad_norm 1.3221 (1.5268)	
[2022-01-22 11:55:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][770/1251]	eta 0:17:39 lr 0.000491	time 1.9510 (2.2024)	loss 2.9669 (3.5267)	grad_norm 1.3399 (1.5265)	
[2022-01-22 11:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][780/1251]	eta 0:17:17 lr 0.000491	time 1.6822 (2.2032)	loss 2.3855 (3.5290)	grad_norm 1.5158 (1.5268)	
[2022-01-22 11:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][790/1251]	eta 0:16:56 lr 0.000491	time 3.1390 (2.2041)	loss 3.6870 (3.5247)	grad_norm 1.3310 (1.5270)	
[2022-01-22 11:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][800/1251]	eta 0:16:34 lr 0.000491	time 1.5590 (2.2047)	loss 3.6109 (3.5224)	grad_norm 1.5917 (1.5268)	
[2022-01-22 11:56:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][810/1251]	eta 0:16:12 lr 0.000491	time 1.7045 (2.2062)	loss 3.0348 (3.5234)	grad_norm 1.4686 (1.5274)	
[2022-01-22 11:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][820/1251]	eta 0:15:50 lr 0.000491	time 2.0859 (2.2062)	loss 3.8020 (3.5261)	grad_norm 1.4700 (1.5272)	
[2022-01-22 11:57:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][830/1251]	eta 0:15:29 lr 0.000491	time 3.3448 (2.2073)	loss 3.6695 (3.5252)	grad_norm 1.5176 (1.5264)	
[2022-01-22 11:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][840/1251]	eta 0:15:06 lr 0.000491	time 2.2421 (2.2060)	loss 3.9478 (3.5298)	grad_norm 1.3510 (1.5255)	
[2022-01-22 11:58:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][850/1251]	eta 0:14:44 lr 0.000491	time 1.5615 (2.2053)	loss 2.8928 (3.5299)	grad_norm 1.4528 (1.5248)	
[2022-01-22 11:58:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][860/1251]	eta 0:14:21 lr 0.000491	time 1.9259 (2.2043)	loss 3.5887 (3.5331)	grad_norm 1.5246 (1.5259)	
[2022-01-22 11:59:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][870/1251]	eta 0:14:00 lr 0.000491	time 3.6347 (2.2066)	loss 3.5640 (3.5336)	grad_norm 1.4325 (1.5252)	
[2022-01-22 11:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][880/1251]	eta 0:13:38 lr 0.000491	time 2.7451 (2.2069)	loss 4.2609 (3.5366)	grad_norm 1.6371 (1.5263)	
[2022-01-22 11:59:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][890/1251]	eta 0:13:16 lr 0.000491	time 1.5527 (2.2063)	loss 3.8293 (3.5389)	grad_norm 1.6884 (1.5278)	
[2022-01-22 12:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][900/1251]	eta 0:12:53 lr 0.000491	time 1.9032 (2.2049)	loss 3.6443 (3.5389)	grad_norm 1.2923 (1.5283)	
[2022-01-22 12:00:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][910/1251]	eta 0:12:31 lr 0.000491	time 3.1086 (2.2047)	loss 4.5296 (3.5378)	grad_norm 1.4279 (1.5284)	
[2022-01-22 12:00:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][920/1251]	eta 0:12:09 lr 0.000491	time 2.7517 (2.2045)	loss 4.0905 (3.5394)	grad_norm 1.7787 (1.5292)	
[2022-01-22 12:01:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][930/1251]	eta 0:11:47 lr 0.000491	time 2.3267 (2.2030)	loss 2.7158 (3.5414)	grad_norm 1.5731 (1.5286)	
[2022-01-22 12:01:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][940/1251]	eta 0:11:25 lr 0.000491	time 1.9469 (2.2028)	loss 3.9188 (3.5391)	grad_norm 1.6354 (1.5290)	
[2022-01-22 12:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][950/1251]	eta 0:11:03 lr 0.000491	time 2.4717 (2.2037)	loss 3.2479 (3.5397)	grad_norm 1.5239 (1.5289)	
[2022-01-22 12:02:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][960/1251]	eta 0:10:41 lr 0.000491	time 2.5135 (2.2052)	loss 4.0951 (3.5392)	grad_norm 1.3319 (1.5289)	
[2022-01-22 12:02:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][970/1251]	eta 0:10:19 lr 0.000491	time 1.7680 (2.2033)	loss 2.5296 (3.5386)	grad_norm 1.5604 (1.5293)	
[2022-01-22 12:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][980/1251]	eta 0:09:56 lr 0.000491	time 1.9674 (2.2015)	loss 3.4326 (3.5397)	grad_norm 1.3441 (1.5296)	
[2022-01-22 12:03:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][990/1251]	eta 0:09:34 lr 0.000491	time 3.0835 (2.2006)	loss 2.8813 (3.5398)	grad_norm 1.4876 (1.5301)	
[2022-01-22 12:03:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1000/1251]	eta 0:09:12 lr 0.000490	time 2.5294 (2.2013)	loss 3.5899 (3.5389)	grad_norm 1.4375 (1.5301)	
[2022-01-22 12:04:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1010/1251]	eta 0:08:50 lr 0.000490	time 2.2798 (2.2010)	loss 4.1969 (3.5384)	grad_norm 1.4506 (1.5300)	
[2022-01-22 12:04:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1020/1251]	eta 0:08:28 lr 0.000490	time 1.8314 (2.2015)	loss 3.0893 (3.5347)	grad_norm 1.5580 (1.5301)	
[2022-01-22 12:04:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1030/1251]	eta 0:08:07 lr 0.000490	time 3.0483 (2.2041)	loss 2.9734 (3.5329)	grad_norm 1.5184 (1.5298)	
[2022-01-22 12:05:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1040/1251]	eta 0:07:44 lr 0.000490	time 1.6899 (2.2018)	loss 3.9297 (3.5328)	grad_norm 1.8821 (1.5313)	
[2022-01-22 12:05:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1050/1251]	eta 0:07:22 lr 0.000490	time 1.6071 (2.1999)	loss 3.8627 (3.5306)	grad_norm 1.5363 (1.5322)	
[2022-01-22 12:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1060/1251]	eta 0:07:00 lr 0.000490	time 2.2233 (2.1993)	loss 3.1324 (3.5313)	grad_norm 1.6431 (1.5333)	
[2022-01-22 12:06:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1070/1251]	eta 0:06:38 lr 0.000490	time 2.5682 (2.1999)	loss 3.5184 (3.5326)	grad_norm 1.4680 (1.5330)	
[2022-01-22 12:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1080/1251]	eta 0:06:16 lr 0.000490	time 1.9453 (2.1989)	loss 3.9710 (3.5357)	grad_norm 1.5866 (1.5332)	
[2022-01-22 12:07:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1090/1251]	eta 0:05:54 lr 0.000490	time 3.1432 (2.1988)	loss 3.2556 (3.5351)	grad_norm 1.6208 (1.5331)	
[2022-01-22 12:07:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1100/1251]	eta 0:05:31 lr 0.000490	time 2.1369 (2.1981)	loss 4.0022 (3.5351)	grad_norm 1.3733 (1.5325)	
[2022-01-22 12:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1110/1251]	eta 0:05:09 lr 0.000490	time 2.1219 (2.1966)	loss 3.8486 (3.5367)	grad_norm 1.6628 (1.5319)	
[2022-01-22 12:08:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1120/1251]	eta 0:04:47 lr 0.000490	time 2.4644 (2.1971)	loss 3.3440 (3.5380)	grad_norm 1.6532 (1.5311)	
[2022-01-22 12:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1130/1251]	eta 0:04:26 lr 0.000490	time 2.4691 (2.1988)	loss 3.2091 (3.5389)	grad_norm 1.3141 (1.5312)	
[2022-01-22 12:08:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1140/1251]	eta 0:04:03 lr 0.000490	time 2.3980 (2.1981)	loss 3.0947 (3.5364)	grad_norm 1.4073 (1.5305)	
[2022-01-22 12:09:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1150/1251]	eta 0:03:42 lr 0.000490	time 2.2935 (2.1987)	loss 3.4673 (3.5367)	grad_norm 1.5891 (1.5302)	
[2022-01-22 12:09:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1160/1251]	eta 0:03:20 lr 0.000490	time 1.9360 (2.1987)	loss 4.2799 (3.5381)	grad_norm 2.1374 (1.5314)	
[2022-01-22 12:09:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1170/1251]	eta 0:02:58 lr 0.000490	time 1.6920 (2.1981)	loss 3.8121 (3.5399)	grad_norm 1.3818 (1.5321)	
[2022-01-22 12:10:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1180/1251]	eta 0:02:36 lr 0.000490	time 1.5755 (2.1974)	loss 3.7656 (3.5410)	grad_norm 1.4617 (1.5325)	
[2022-01-22 12:10:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1190/1251]	eta 0:02:13 lr 0.000490	time 1.9604 (2.1967)	loss 2.8568 (3.5398)	grad_norm 1.4500 (1.5331)	
[2022-01-22 12:11:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1200/1251]	eta 0:01:52 lr 0.000490	time 2.1243 (2.1976)	loss 4.2155 (3.5410)	grad_norm 1.6058 (1.5331)	
[2022-01-22 12:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1210/1251]	eta 0:01:30 lr 0.000490	time 2.2915 (2.1986)	loss 3.7112 (3.5420)	grad_norm 1.4881 (1.5326)	
[2022-01-22 12:11:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1220/1251]	eta 0:01:08 lr 0.000490	time 1.9756 (2.1992)	loss 4.2091 (3.5425)	grad_norm 1.4570 (1.5323)	
[2022-01-22 12:12:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1230/1251]	eta 0:00:46 lr 0.000490	time 1.8625 (2.1989)	loss 2.7227 (3.5419)	grad_norm 1.3504 (1.5316)	
[2022-01-22 12:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1240/1251]	eta 0:00:24 lr 0.000489	time 1.5708 (2.1966)	loss 3.1255 (3.5427)	grad_norm 1.5730 (1.5308)	
[2022-01-22 12:12:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [152/300][1250/1251]	eta 0:00:02 lr 0.000489	time 1.2111 (2.1899)	loss 3.1257 (3.5386)	grad_norm 1.3709 (1.5301)	
[2022-01-22 12:12:43 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 152 training takes 0:45:39
[2022-01-22 12:13:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.382 (18.382)	Loss 1.0430 (1.0430)	Acc@1 74.219 (74.219)	Acc@5 93.457 (93.457)	
[2022-01-22 12:13:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.107 (3.445)	Loss 1.0103 (1.0235)	Acc@1 76.855 (75.728)	Acc@5 92.676 (93.093)	
[2022-01-22 12:13:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.569 (2.638)	Loss 0.9303 (1.0217)	Acc@1 77.344 (75.698)	Acc@5 93.848 (93.197)	
[2022-01-22 12:13:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.603 (2.291)	Loss 0.9691 (1.0162)	Acc@1 77.051 (75.898)	Acc@5 93.945 (93.252)	
[2022-01-22 12:14:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.261 (2.153)	Loss 0.9611 (1.0111)	Acc@1 79.199 (76.129)	Acc@5 93.457 (93.317)	
[2022-01-22 12:14:19 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.178 Acc@5 93.272
[2022-01-22 12:14:19 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.2%
[2022-01-22 12:14:19 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.30%
[2022-01-22 12:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][0/1251]	eta 7:41:05 lr 0.000489	time 22.1145 (22.1145)	loss 3.3322 (3.3322)	grad_norm 1.4981 (1.4981)	
[2022-01-22 12:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][10/1251]	eta 1:26:30 lr 0.000489	time 2.0180 (4.1822)	loss 3.4864 (3.0185)	grad_norm 1.4389 (1.4853)	
[2022-01-22 12:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][20/1251]	eta 1:04:07 lr 0.000489	time 1.2247 (3.1253)	loss 3.1512 (3.1401)	grad_norm 1.4107 (1.5368)	
[2022-01-22 12:15:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][30/1251]	eta 0:56:57 lr 0.000489	time 1.9255 (2.7987)	loss 2.4099 (3.2206)	grad_norm 1.4210 (1.5446)	
[2022-01-22 12:16:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][40/1251]	eta 0:54:40 lr 0.000489	time 4.9678 (2.7090)	loss 2.7390 (3.3049)	grad_norm 1.2506 (1.5241)	
[2022-01-22 12:16:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][50/1251]	eta 0:52:57 lr 0.000489	time 2.6069 (2.6459)	loss 3.9116 (3.3189)	grad_norm 1.5276 (1.5244)	
[2022-01-22 12:16:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][60/1251]	eta 0:51:24 lr 0.000489	time 1.3910 (2.5899)	loss 3.7041 (3.3632)	grad_norm 1.4342 (1.5112)	
[2022-01-22 12:17:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][70/1251]	eta 0:50:23 lr 0.000489	time 3.0365 (2.5600)	loss 3.4781 (3.3863)	grad_norm 1.5324 (1.5233)	
[2022-01-22 12:17:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][80/1251]	eta 0:49:34 lr 0.000489	time 3.6612 (2.5402)	loss 3.3979 (3.4091)	grad_norm 1.3756 (1.5257)	
[2022-01-22 12:18:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][90/1251]	eta 0:48:19 lr 0.000489	time 1.9766 (2.4978)	loss 3.6701 (3.4167)	grad_norm 2.0622 (1.5412)	
[2022-01-22 12:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][100/1251]	eta 0:47:04 lr 0.000489	time 1.8872 (2.4542)	loss 3.1126 (3.4141)	grad_norm 1.5785 (1.5425)	
[2022-01-22 12:18:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][110/1251]	eta 0:46:13 lr 0.000489	time 3.3228 (2.4303)	loss 3.5277 (3.4343)	grad_norm 1.6426 (1.5498)	
[2022-01-22 12:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][120/1251]	eta 0:45:16 lr 0.000489	time 2.6231 (2.4018)	loss 3.9783 (3.4419)	grad_norm 1.7224 (1.5533)	
[2022-01-22 12:19:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][130/1251]	eta 0:44:17 lr 0.000489	time 1.8712 (2.3707)	loss 3.4930 (3.4290)	grad_norm 1.5336 (1.5459)	
[2022-01-22 12:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][140/1251]	eta 0:43:36 lr 0.000489	time 1.7923 (2.3554)	loss 3.7043 (3.4354)	grad_norm 1.5000 (1.5429)	
[2022-01-22 12:20:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][150/1251]	eta 0:43:09 lr 0.000489	time 3.3844 (2.3523)	loss 3.7778 (3.4620)	grad_norm 1.3914 (1.5391)	
[2022-01-22 12:20:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][160/1251]	eta 0:42:45 lr 0.000489	time 2.6050 (2.3519)	loss 4.1280 (3.4594)	grad_norm 1.4945 (1.5386)	
[2022-01-22 12:20:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][170/1251]	eta 0:42:07 lr 0.000489	time 1.7977 (2.3378)	loss 3.0238 (3.4554)	grad_norm 1.4832 (1.5346)	
[2022-01-22 12:21:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][180/1251]	eta 0:41:30 lr 0.000489	time 2.2617 (2.3258)	loss 4.1127 (3.4717)	grad_norm 1.3879 (1.5309)	
[2022-01-22 12:21:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][190/1251]	eta 0:40:58 lr 0.000489	time 2.7511 (2.3173)	loss 2.8011 (3.4769)	grad_norm 1.4598 (1.5263)	
[2022-01-22 12:22:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][200/1251]	eta 0:40:27 lr 0.000489	time 2.5566 (2.3094)	loss 3.1031 (3.4639)	grad_norm 1.7863 (1.5248)	
[2022-01-22 12:22:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][210/1251]	eta 0:39:59 lr 0.000489	time 2.1790 (2.3048)	loss 3.7468 (3.4562)	grad_norm 1.5192 (1.5289)	
[2022-01-22 12:22:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][220/1251]	eta 0:39:28 lr 0.000489	time 2.0335 (2.2976)	loss 3.8073 (3.4699)	grad_norm 1.7670 (1.5305)	
[2022-01-22 12:23:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][230/1251]	eta 0:39:00 lr 0.000488	time 2.5905 (2.2926)	loss 2.6135 (3.4741)	grad_norm 1.6122 (1.5271)	
[2022-01-22 12:23:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][240/1251]	eta 0:38:25 lr 0.000488	time 1.9345 (2.2803)	loss 3.0922 (3.4844)	grad_norm 1.4990 (1.5264)	
[2022-01-22 12:23:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][250/1251]	eta 0:37:50 lr 0.000488	time 1.4798 (2.2686)	loss 3.4389 (3.4880)	grad_norm 1.3326 (1.5268)	
[2022-01-22 12:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][260/1251]	eta 0:37:26 lr 0.000488	time 2.2424 (2.2668)	loss 3.6446 (3.4995)	grad_norm 1.5407 (1.5276)	
[2022-01-22 12:24:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][270/1251]	eta 0:37:05 lr 0.000488	time 2.7817 (2.2682)	loss 4.0787 (3.5008)	grad_norm 1.4038 (1.5274)	
[2022-01-22 12:24:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][280/1251]	eta 0:36:43 lr 0.000488	time 1.9436 (2.2694)	loss 3.2476 (3.5074)	grad_norm 1.4936 (1.5275)	
[2022-01-22 12:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][290/1251]	eta 0:36:18 lr 0.000488	time 2.1764 (2.2672)	loss 2.3867 (3.4949)	grad_norm 1.5304 (1.5286)	
[2022-01-22 12:25:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][300/1251]	eta 0:35:51 lr 0.000488	time 1.6860 (2.2620)	loss 3.7604 (3.5012)	grad_norm 1.3999 (1.5278)	
[2022-01-22 12:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][310/1251]	eta 0:35:29 lr 0.000488	time 4.0470 (2.2627)	loss 2.7580 (3.4997)	grad_norm 1.6697 (1.5268)	
[2022-01-22 12:26:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][320/1251]	eta 0:35:03 lr 0.000488	time 2.0195 (2.2599)	loss 3.9739 (3.4987)	grad_norm 1.6071 (1.5272)	
[2022-01-22 12:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][330/1251]	eta 0:34:40 lr 0.000488	time 2.1666 (2.2585)	loss 3.7922 (3.5016)	grad_norm 1.4860 (1.5293)	
[2022-01-22 12:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][340/1251]	eta 0:34:15 lr 0.000488	time 1.9008 (2.2558)	loss 4.6487 (3.5042)	grad_norm 1.4023 (1.5308)	
[2022-01-22 12:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][350/1251]	eta 0:33:52 lr 0.000488	time 3.8973 (2.2554)	loss 3.9179 (3.5006)	grad_norm 1.6131 (1.5312)	
[2022-01-22 12:27:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][360/1251]	eta 0:33:26 lr 0.000488	time 2.3984 (2.2519)	loss 3.6088 (3.4993)	grad_norm 1.4791 (1.5319)	
[2022-01-22 12:28:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][370/1251]	eta 0:33:02 lr 0.000488	time 2.1642 (2.2500)	loss 3.8640 (3.5002)	grad_norm 1.5760 (1.5320)	
[2022-01-22 12:28:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][380/1251]	eta 0:32:37 lr 0.000488	time 2.2163 (2.2473)	loss 3.4961 (3.4987)	grad_norm 1.3716 (1.5289)	
[2022-01-22 12:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][390/1251]	eta 0:32:15 lr 0.000488	time 2.7216 (2.2476)	loss 4.3142 (3.5018)	grad_norm 1.7118 (1.5305)	
[2022-01-22 12:29:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][400/1251]	eta 0:31:54 lr 0.000488	time 3.0152 (2.2496)	loss 3.4471 (3.5063)	grad_norm 1.4130 (1.5313)	
[2022-01-22 12:29:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][410/1251]	eta 0:31:28 lr 0.000488	time 1.6148 (2.2460)	loss 2.8736 (3.5090)	grad_norm 1.4907 (1.5295)	
[2022-01-22 12:30:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][420/1251]	eta 0:31:02 lr 0.000488	time 1.9411 (2.2416)	loss 4.0367 (3.5115)	grad_norm 1.5746 (1.5285)	
[2022-01-22 12:30:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][430/1251]	eta 0:30:35 lr 0.000488	time 1.8831 (2.2352)	loss 4.2606 (3.5081)	grad_norm 1.6223 (1.5304)	
[2022-01-22 12:30:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][440/1251]	eta 0:30:09 lr 0.000488	time 2.5542 (2.2309)	loss 3.2810 (3.5057)	grad_norm 1.5269 (1.5336)	
[2022-01-22 12:31:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][450/1251]	eta 0:29:43 lr 0.000488	time 1.9352 (2.2267)	loss 4.0353 (3.5101)	grad_norm 1.5306 (1.5336)	
[2022-01-22 12:31:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][460/1251]	eta 0:29:20 lr 0.000488	time 2.6693 (2.2259)	loss 3.5295 (3.5103)	grad_norm 1.5398 (1.5343)	
[2022-01-22 12:31:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][470/1251]	eta 0:28:58 lr 0.000488	time 2.4400 (2.2265)	loss 3.2136 (3.5113)	grad_norm 1.5440 (1.5326)	
[2022-01-22 12:32:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][480/1251]	eta 0:28:38 lr 0.000487	time 2.1080 (2.2285)	loss 3.9194 (3.5082)	grad_norm 1.6954 (1.5339)	
[2022-01-22 12:32:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][490/1251]	eta 0:28:15 lr 0.000487	time 2.4530 (2.2281)	loss 3.6385 (3.5089)	grad_norm 1.3117 (1.5332)	
[2022-01-22 12:32:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][500/1251]	eta 0:27:52 lr 0.000487	time 2.2266 (2.2274)	loss 3.5521 (3.5040)	grad_norm 1.2706 (1.5324)	
[2022-01-22 12:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][510/1251]	eta 0:27:29 lr 0.000487	time 1.7868 (2.2258)	loss 3.9126 (3.5038)	grad_norm 1.3641 (1.5318)	
[2022-01-22 12:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][520/1251]	eta 0:27:08 lr 0.000487	time 2.4363 (2.2282)	loss 3.9139 (3.5039)	grad_norm 1.3817 (1.5303)	
[2022-01-22 12:34:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][530/1251]	eta 0:26:46 lr 0.000487	time 2.7409 (2.2276)	loss 2.2972 (3.5023)	grad_norm 1.5717 (1.5307)	
[2022-01-22 12:34:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][540/1251]	eta 0:26:23 lr 0.000487	time 2.5033 (2.2274)	loss 2.6584 (3.5024)	grad_norm 1.4227 (1.5356)	
[2022-01-22 12:34:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][550/1251]	eta 0:26:02 lr 0.000487	time 1.6577 (2.2283)	loss 3.8109 (3.5036)	grad_norm 1.5020 (1.5356)	
[2022-01-22 12:35:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][560/1251]	eta 0:25:39 lr 0.000487	time 2.2351 (2.2277)	loss 4.3299 (3.5049)	grad_norm 1.6053 (1.5379)	
[2022-01-22 12:35:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][570/1251]	eta 0:25:15 lr 0.000487	time 2.2924 (2.2247)	loss 4.0485 (3.5111)	grad_norm 1.8392 (1.5396)	
[2022-01-22 12:35:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][580/1251]	eta 0:24:52 lr 0.000487	time 1.9033 (2.2245)	loss 2.1367 (3.5044)	grad_norm 1.3946 (1.5398)	
[2022-01-22 12:36:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][590/1251]	eta 0:24:28 lr 0.000487	time 1.7632 (2.2222)	loss 2.8841 (3.5046)	grad_norm 1.5428 (1.5384)	
[2022-01-22 12:36:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][600/1251]	eta 0:24:04 lr 0.000487	time 2.3660 (2.2191)	loss 3.0381 (3.5107)	grad_norm 1.4225 (1.5386)	
[2022-01-22 12:36:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][610/1251]	eta 0:23:40 lr 0.000487	time 2.2258 (2.2161)	loss 2.5678 (3.5107)	grad_norm 1.3811 (1.5370)	
[2022-01-22 12:37:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][620/1251]	eta 0:23:18 lr 0.000487	time 2.9574 (2.2161)	loss 3.5762 (3.5131)	grad_norm 1.4905 (1.5362)	
[2022-01-22 12:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][630/1251]	eta 0:22:54 lr 0.000487	time 2.1862 (2.2137)	loss 4.0341 (3.5137)	grad_norm 1.6174 (1.5340)	
[2022-01-22 12:38:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][640/1251]	eta 0:22:33 lr 0.000487	time 2.3354 (2.2160)	loss 2.9911 (3.5148)	grad_norm 1.4962 (1.5336)	
[2022-01-22 12:38:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][650/1251]	eta 0:22:12 lr 0.000487	time 2.6730 (2.2165)	loss 3.5706 (3.5131)	grad_norm 1.3158 (1.5312)	
[2022-01-22 12:38:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][660/1251]	eta 0:21:49 lr 0.000487	time 2.1594 (2.2165)	loss 3.1953 (3.5147)	grad_norm 1.6202 (1.5320)	
[2022-01-22 12:39:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][670/1251]	eta 0:21:28 lr 0.000487	time 2.8753 (2.2169)	loss 3.1066 (3.5066)	grad_norm 1.4786 (1.5317)	
[2022-01-22 12:39:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][680/1251]	eta 0:21:04 lr 0.000487	time 2.4738 (2.2145)	loss 3.5122 (3.5072)	grad_norm 1.6802 (1.5326)	
[2022-01-22 12:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][690/1251]	eta 0:20:41 lr 0.000487	time 2.2907 (2.2129)	loss 2.6411 (3.5050)	grad_norm 1.3931 (1.5325)	
[2022-01-22 12:40:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][700/1251]	eta 0:20:18 lr 0.000487	time 1.5055 (2.2122)	loss 3.6667 (3.5048)	grad_norm 1.6032 (1.5319)	
[2022-01-22 12:40:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][710/1251]	eta 0:19:56 lr 0.000487	time 2.3044 (2.2116)	loss 3.1494 (3.5019)	grad_norm 1.5144 (1.5337)	
[2022-01-22 12:40:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][720/1251]	eta 0:19:33 lr 0.000486	time 2.5153 (2.2108)	loss 3.2445 (3.5038)	grad_norm 1.6617 (1.5340)	
[2022-01-22 12:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][730/1251]	eta 0:19:12 lr 0.000486	time 2.7039 (2.2120)	loss 3.3491 (3.5064)	grad_norm 1.3638 (1.5338)	
[2022-01-22 12:41:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][740/1251]	eta 0:18:50 lr 0.000486	time 2.2034 (2.2118)	loss 3.5458 (3.5089)	grad_norm 1.5052 (1.5331)	
[2022-01-22 12:41:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][750/1251]	eta 0:18:27 lr 0.000486	time 1.7246 (2.2105)	loss 3.6221 (3.5097)	grad_norm 1.4036 (1.5332)	
[2022-01-22 12:42:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][760/1251]	eta 0:18:05 lr 0.000486	time 2.2142 (2.2103)	loss 3.9444 (3.5118)	grad_norm 1.5155 (1.5321)	
[2022-01-22 12:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][770/1251]	eta 0:17:43 lr 0.000486	time 2.1562 (2.2111)	loss 3.5331 (3.5114)	grad_norm 1.3197 (1.5317)	
[2022-01-22 12:43:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][780/1251]	eta 0:17:20 lr 0.000486	time 1.8504 (2.2099)	loss 3.7581 (3.5119)	grad_norm 1.5737 (1.5323)	
[2022-01-22 12:43:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][790/1251]	eta 0:16:57 lr 0.000486	time 1.7122 (2.2074)	loss 3.6236 (3.5094)	grad_norm 1.6076 (1.5329)	
[2022-01-22 12:43:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][800/1251]	eta 0:16:34 lr 0.000486	time 1.7890 (2.2048)	loss 3.7121 (3.5098)	grad_norm 1.4284 (1.5318)	
[2022-01-22 12:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][810/1251]	eta 0:16:12 lr 0.000486	time 1.8850 (2.2043)	loss 3.6249 (3.5094)	grad_norm 1.5143 (1.5329)	
[2022-01-22 12:44:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][820/1251]	eta 0:15:50 lr 0.000486	time 2.1704 (2.2051)	loss 3.6846 (3.5104)	grad_norm 1.6791 (1.5326)	
[2022-01-22 12:44:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][830/1251]	eta 0:15:28 lr 0.000486	time 1.8942 (2.2064)	loss 3.0044 (3.5098)	grad_norm 1.4242 (1.5318)	
[2022-01-22 12:45:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][840/1251]	eta 0:15:08 lr 0.000486	time 1.9269 (2.2097)	loss 3.5452 (3.5104)	grad_norm 1.4824 (1.5321)	
[2022-01-22 12:45:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][850/1251]	eta 0:14:46 lr 0.000486	time 2.7396 (2.2118)	loss 3.5282 (3.5115)	grad_norm 1.5158 (1.5323)	
[2022-01-22 12:46:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][860/1251]	eta 0:14:25 lr 0.000486	time 2.1511 (2.2129)	loss 3.7794 (3.5065)	grad_norm 1.5112 (1.5315)	
[2022-01-22 12:46:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][870/1251]	eta 0:14:02 lr 0.000486	time 1.9243 (2.2102)	loss 3.8686 (3.5091)	grad_norm 1.4986 (1.5310)	
[2022-01-22 12:46:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][880/1251]	eta 0:13:38 lr 0.000486	time 1.8791 (2.2070)	loss 2.9119 (3.5051)	grad_norm 1.5447 (1.5317)	
[2022-01-22 12:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][890/1251]	eta 0:13:15 lr 0.000486	time 1.9330 (2.2042)	loss 2.6275 (3.5020)	grad_norm 1.3221 (1.5314)	
[2022-01-22 12:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][900/1251]	eta 0:12:52 lr 0.000486	time 2.0943 (2.2016)	loss 3.7486 (3.5043)	grad_norm 1.4460 (1.5323)	
[2022-01-22 12:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][910/1251]	eta 0:12:30 lr 0.000486	time 1.8731 (2.2016)	loss 3.6209 (3.5045)	grad_norm 1.3196 (1.5323)	
[2022-01-22 12:48:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][920/1251]	eta 0:12:08 lr 0.000486	time 2.1881 (2.2008)	loss 4.2105 (3.5055)	grad_norm 1.4995 (1.5334)	
[2022-01-22 12:48:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][930/1251]	eta 0:11:46 lr 0.000486	time 2.5061 (2.2021)	loss 3.7476 (3.5061)	grad_norm 1.5351 (1.5340)	
[2022-01-22 12:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][940/1251]	eta 0:11:25 lr 0.000486	time 2.9014 (2.2035)	loss 3.5060 (3.5085)	grad_norm 1.5680 (1.5344)	
[2022-01-22 12:49:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][950/1251]	eta 0:11:03 lr 0.000486	time 2.1964 (2.2042)	loss 3.9232 (3.5097)	grad_norm 1.4699 (1.5348)	
[2022-01-22 12:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][960/1251]	eta 0:10:41 lr 0.000485	time 2.0841 (2.2058)	loss 3.1285 (3.5088)	grad_norm 1.6204 (1.5353)	
[2022-01-22 12:50:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][970/1251]	eta 0:10:19 lr 0.000485	time 2.2385 (2.2062)	loss 2.4628 (3.5093)	grad_norm 1.2980 (1.5362)	
[2022-01-22 12:50:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][980/1251]	eta 0:09:57 lr 0.000485	time 2.8411 (2.2055)	loss 3.3532 (3.5114)	grad_norm 1.8607 (1.5363)	
[2022-01-22 12:50:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][990/1251]	eta 0:09:35 lr 0.000485	time 1.8899 (2.2044)	loss 3.1810 (3.5108)	grad_norm 2.2251 (1.5377)	
[2022-01-22 12:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1000/1251]	eta 0:09:12 lr 0.000485	time 1.8825 (2.2023)	loss 3.4507 (3.5097)	grad_norm 1.4992 (1.5384)	
[2022-01-22 12:51:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1010/1251]	eta 0:08:50 lr 0.000485	time 1.7293 (2.2006)	loss 2.9841 (3.5090)	grad_norm 1.5931 (1.5384)	
[2022-01-22 12:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1020/1251]	eta 0:08:27 lr 0.000485	time 1.6860 (2.1985)	loss 3.2502 (3.5102)	grad_norm 1.4880 (1.5378)	
[2022-01-22 12:52:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1030/1251]	eta 0:08:06 lr 0.000485	time 2.2426 (2.1992)	loss 4.2418 (3.5121)	grad_norm 1.4302 (1.5366)	
[2022-01-22 12:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1040/1251]	eta 0:07:43 lr 0.000485	time 1.6592 (2.1988)	loss 2.9392 (3.5116)	grad_norm 1.5403 (1.5357)	
[2022-01-22 12:52:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1050/1251]	eta 0:07:22 lr 0.000485	time 1.8896 (2.1992)	loss 4.1550 (3.5139)	grad_norm 1.7170 (1.5355)	
[2022-01-22 12:53:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1060/1251]	eta 0:07:00 lr 0.000485	time 1.8168 (2.2002)	loss 3.5169 (3.5147)	grad_norm 1.5434 (1.5352)	
[2022-01-22 12:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1070/1251]	eta 0:06:38 lr 0.000485	time 2.1989 (2.2020)	loss 3.8567 (3.5155)	grad_norm 1.5352 (1.5346)	
[2022-01-22 12:54:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1080/1251]	eta 0:06:16 lr 0.000485	time 1.6589 (2.2025)	loss 2.5409 (3.5113)	grad_norm 1.3733 (1.5348)	
[2022-01-22 12:54:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1090/1251]	eta 0:05:54 lr 0.000485	time 2.4373 (2.2031)	loss 3.7914 (3.5103)	grad_norm 1.5713 (1.5346)	
[2022-01-22 12:54:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1100/1251]	eta 0:05:32 lr 0.000485	time 1.6349 (2.2026)	loss 3.8931 (3.5101)	grad_norm 1.3520 (1.5342)	
[2022-01-22 12:55:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1110/1251]	eta 0:05:10 lr 0.000485	time 1.9253 (2.2008)	loss 3.4760 (3.5094)	grad_norm 1.8064 (1.5338)	
[2022-01-22 12:55:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1120/1251]	eta 0:04:48 lr 0.000485	time 1.8864 (2.1986)	loss 2.5839 (3.5098)	grad_norm 1.4853 (1.5333)	
[2022-01-22 12:55:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1130/1251]	eta 0:04:25 lr 0.000485	time 2.3374 (2.1975)	loss 3.0553 (3.5099)	grad_norm 1.4872 (1.5338)	
[2022-01-22 12:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1140/1251]	eta 0:04:03 lr 0.000485	time 2.3763 (2.1963)	loss 3.4563 (3.5087)	grad_norm 1.3927 (1.5329)	
[2022-01-22 12:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1150/1251]	eta 0:03:41 lr 0.000485	time 2.3090 (2.1962)	loss 4.0641 (3.5085)	grad_norm 1.4760 (1.5324)	
[2022-01-22 12:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1160/1251]	eta 0:03:19 lr 0.000485	time 2.8142 (2.1976)	loss 3.3684 (3.5055)	grad_norm 1.2926 (1.5313)	
[2022-01-22 12:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1170/1251]	eta 0:02:58 lr 0.000485	time 2.7661 (2.1998)	loss 2.3905 (3.5042)	grad_norm 1.6150 (1.5314)	
[2022-01-22 12:57:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1180/1251]	eta 0:02:36 lr 0.000485	time 2.5182 (2.2025)	loss 3.2639 (3.5037)	grad_norm 1.3402 (1.5314)	
[2022-01-22 12:58:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1190/1251]	eta 0:02:14 lr 0.000485	time 2.0936 (2.2022)	loss 3.8509 (3.5024)	grad_norm 1.5384 (1.5314)	
[2022-01-22 12:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1200/1251]	eta 0:01:52 lr 0.000484	time 1.9673 (2.2008)	loss 3.1953 (3.5014)	grad_norm 1.4262 (1.5309)	
[2022-01-22 12:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1210/1251]	eta 0:01:30 lr 0.000484	time 1.6587 (2.1985)	loss 3.5861 (3.5017)	grad_norm 1.4602 (1.5308)	
[2022-01-22 12:59:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1220/1251]	eta 0:01:08 lr 0.000484	time 1.9136 (2.1973)	loss 3.4158 (3.5034)	grad_norm 1.6348 (1.5313)	
[2022-01-22 12:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1230/1251]	eta 0:00:46 lr 0.000484	time 2.6073 (2.1974)	loss 4.1845 (3.5028)	grad_norm 1.3972 (1.5313)	
[2022-01-22 12:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1240/1251]	eta 0:00:24 lr 0.000484	time 2.2370 (2.1965)	loss 4.1775 (3.5037)	grad_norm 1.5244 (1.5307)	
[2022-01-22 13:00:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [153/300][1250/1251]	eta 0:00:02 lr 0.000484	time 1.1334 (2.1914)	loss 3.4485 (3.5040)	grad_norm 1.4252 (1.5306)	
[2022-01-22 13:00:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 153 training takes 0:45:41
[2022-01-22 13:00:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.435 (18.435)	Loss 1.0815 (1.0815)	Acc@1 72.949 (72.949)	Acc@5 92.285 (92.285)	
[2022-01-22 13:00:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.292 (3.313)	Loss 0.9397 (1.0146)	Acc@1 77.734 (75.648)	Acc@5 93.262 (93.306)	
[2022-01-22 13:00:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.521 (2.537)	Loss 0.9484 (1.0040)	Acc@1 76.953 (76.190)	Acc@5 93.848 (93.406)	
[2022-01-22 13:01:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.615 (2.257)	Loss 1.0388 (0.9991)	Acc@1 75.586 (76.307)	Acc@5 92.480 (93.426)	
[2022-01-22 13:01:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 7.159 (2.149)	Loss 0.9575 (1.0025)	Acc@1 78.027 (76.279)	Acc@5 93.262 (93.333)	
[2022-01-22 13:01:36 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.292 Acc@5 93.390
[2022-01-22 13:01:36 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.3%
[2022-01-22 13:01:36 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.30%
[2022-01-22 13:01:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][0/1251]	eta 7:31:11 lr 0.000484	time 21.6398 (21.6398)	loss 3.1654 (3.1654)	grad_norm 1.6550 (1.6550)	
[2022-01-22 13:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][10/1251]	eta 1:26:51 lr 0.000484	time 2.7735 (4.1996)	loss 2.4444 (3.3810)	grad_norm 1.4539 (1.5282)	
[2022-01-22 13:02:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][20/1251]	eta 1:07:24 lr 0.000484	time 1.8311 (3.2857)	loss 4.1783 (3.3958)	grad_norm 1.4760 (1.5236)	
[2022-01-22 13:03:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][30/1251]	eta 0:58:57 lr 0.000484	time 1.6314 (2.8974)	loss 4.0698 (3.3453)	grad_norm 1.8520 (1.5652)	
[2022-01-22 13:03:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][40/1251]	eta 0:55:06 lr 0.000484	time 3.0336 (2.7300)	loss 3.2832 (3.3490)	grad_norm 1.2744 (1.5456)	
[2022-01-22 13:03:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][50/1251]	eta 0:52:23 lr 0.000484	time 1.5021 (2.6176)	loss 3.6680 (3.3553)	grad_norm 1.7485 (1.5480)	
[2022-01-22 13:04:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][60/1251]	eta 0:50:45 lr 0.000484	time 2.1759 (2.5568)	loss 3.9662 (3.3978)	grad_norm 1.3858 (1.5477)	
[2022-01-22 13:04:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][70/1251]	eta 0:49:35 lr 0.000484	time 1.9511 (2.5197)	loss 2.9336 (3.3990)	grad_norm 1.6138 (1.5585)	
[2022-01-22 13:04:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][80/1251]	eta 0:48:46 lr 0.000484	time 2.8433 (2.4991)	loss 3.9663 (3.4203)	grad_norm 1.8905 (1.5580)	
[2022-01-22 13:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][90/1251]	eta 0:48:06 lr 0.000484	time 2.7599 (2.4862)	loss 4.0035 (3.4585)	grad_norm 1.3630 (1.5518)	
[2022-01-22 13:05:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][100/1251]	eta 0:47:30 lr 0.000484	time 1.7614 (2.4767)	loss 4.0162 (3.4517)	grad_norm 1.6515 (1.5504)	
[2022-01-22 13:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][110/1251]	eta 0:46:20 lr 0.000484	time 1.8428 (2.4370)	loss 3.6278 (3.4510)	grad_norm 1.6213 (1.5538)	
[2022-01-22 13:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][120/1251]	eta 0:45:19 lr 0.000484	time 2.5419 (2.4049)	loss 3.1478 (3.4797)	grad_norm 1.7733 (1.5511)	
[2022-01-22 13:06:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][130/1251]	eta 0:44:25 lr 0.000484	time 1.8030 (2.3777)	loss 4.1240 (3.4816)	grad_norm 1.4029 (1.5464)	
[2022-01-22 13:07:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][140/1251]	eta 0:43:37 lr 0.000484	time 2.4817 (2.3558)	loss 3.8916 (3.4928)	grad_norm 1.6847 (1.5383)	
[2022-01-22 13:07:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][150/1251]	eta 0:42:56 lr 0.000484	time 2.1899 (2.3400)	loss 3.8684 (3.4967)	grad_norm 1.6093 (1.5392)	
[2022-01-22 13:07:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][160/1251]	eta 0:42:27 lr 0.000484	time 2.1820 (2.3354)	loss 4.4343 (3.5068)	grad_norm 2.0193 (1.5430)	
[2022-01-22 13:08:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][170/1251]	eta 0:42:02 lr 0.000484	time 1.8128 (2.3338)	loss 3.5502 (3.5120)	grad_norm 1.5370 (1.5443)	
[2022-01-22 13:08:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][180/1251]	eta 0:41:36 lr 0.000484	time 2.5425 (2.3312)	loss 4.1346 (3.5051)	grad_norm 1.4363 (1.5389)	
[2022-01-22 13:09:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][190/1251]	eta 0:41:07 lr 0.000483	time 2.3606 (2.3261)	loss 3.1426 (3.5049)	grad_norm 1.5565 (1.5344)	
[2022-01-22 13:09:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][200/1251]	eta 0:40:35 lr 0.000483	time 2.1777 (2.3173)	loss 3.8226 (3.5186)	grad_norm 1.4966 (1.5355)	
[2022-01-22 13:09:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][210/1251]	eta 0:40:01 lr 0.000483	time 1.8062 (2.3071)	loss 3.2337 (3.5144)	grad_norm 1.8319 (1.5342)	
[2022-01-22 13:10:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][220/1251]	eta 0:39:27 lr 0.000483	time 1.8792 (2.2962)	loss 3.7907 (3.5203)	grad_norm 1.4907 (1.5333)	
[2022-01-22 13:10:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][230/1251]	eta 0:38:52 lr 0.000483	time 2.1310 (2.2846)	loss 3.3120 (3.5159)	grad_norm 1.8146 (1.5351)	
[2022-01-22 13:10:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][240/1251]	eta 0:38:24 lr 0.000483	time 2.1541 (2.2796)	loss 2.8682 (3.5132)	grad_norm 1.6672 (1.5389)	
[2022-01-22 13:11:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][250/1251]	eta 0:37:58 lr 0.000483	time 2.2263 (2.2763)	loss 3.7975 (3.5140)	grad_norm 1.3663 (1.5358)	
[2022-01-22 13:11:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][260/1251]	eta 0:37:36 lr 0.000483	time 2.3790 (2.2769)	loss 2.7177 (3.5091)	grad_norm 1.9563 (1.5404)	
[2022-01-22 13:11:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][270/1251]	eta 0:37:09 lr 0.000483	time 1.9145 (2.2722)	loss 3.7398 (3.5107)	grad_norm 1.2519 (1.5415)	
[2022-01-22 13:12:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][280/1251]	eta 0:36:38 lr 0.000483	time 1.8315 (2.2638)	loss 2.7395 (3.4984)	grad_norm 1.7759 (1.5435)	
[2022-01-22 13:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][290/1251]	eta 0:36:11 lr 0.000483	time 1.9347 (2.2599)	loss 3.4161 (3.5006)	grad_norm 1.6483 (1.5459)	
[2022-01-22 13:12:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][300/1251]	eta 0:35:45 lr 0.000483	time 1.7654 (2.2561)	loss 3.9389 (3.5032)	grad_norm 1.5484 (1.5478)	
[2022-01-22 13:13:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][310/1251]	eta 0:35:25 lr 0.000483	time 2.6199 (2.2585)	loss 3.5973 (3.4968)	grad_norm 1.6202 (1.5473)	
[2022-01-22 13:13:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][320/1251]	eta 0:35:05 lr 0.000483	time 2.4360 (2.2616)	loss 3.4393 (3.4878)	grad_norm 1.6495 (1.5447)	
[2022-01-22 13:14:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][330/1251]	eta 0:34:45 lr 0.000483	time 2.1333 (2.2641)	loss 3.7187 (3.4903)	grad_norm 1.2618 (1.5420)	
[2022-01-22 13:14:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][340/1251]	eta 0:34:20 lr 0.000483	time 2.1476 (2.2621)	loss 3.7640 (3.4943)	grad_norm 1.3395 (1.5406)	
[2022-01-22 13:14:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][350/1251]	eta 0:33:55 lr 0.000483	time 1.9764 (2.2594)	loss 3.3959 (3.4888)	grad_norm 1.4541 (1.5377)	
[2022-01-22 13:15:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][360/1251]	eta 0:33:24 lr 0.000483	time 1.7919 (2.2497)	loss 3.9708 (3.4852)	grad_norm 1.3967 (1.5366)	
[2022-01-22 13:15:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][370/1251]	eta 0:32:56 lr 0.000483	time 2.0079 (2.2438)	loss 2.6529 (3.4864)	grad_norm 1.4434 (1.5362)	
[2022-01-22 13:15:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][380/1251]	eta 0:32:31 lr 0.000483	time 2.5180 (2.2402)	loss 3.8507 (3.4896)	grad_norm 1.5544 (1.5365)	
[2022-01-22 13:16:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][390/1251]	eta 0:32:11 lr 0.000483	time 2.4387 (2.2436)	loss 3.7186 (3.4947)	grad_norm 1.7525 (1.5398)	
[2022-01-22 13:16:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][400/1251]	eta 0:31:48 lr 0.000483	time 2.2008 (2.2428)	loss 3.9183 (3.4955)	grad_norm 1.7623 (1.5421)	
[2022-01-22 13:16:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][410/1251]	eta 0:31:23 lr 0.000483	time 2.4005 (2.2401)	loss 3.7271 (3.4939)	grad_norm 2.3421 (1.5442)	
[2022-01-22 13:17:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][420/1251]	eta 0:31:02 lr 0.000483	time 2.1497 (2.2412)	loss 2.7662 (3.4934)	grad_norm 1.3320 (1.5428)	
[2022-01-22 13:17:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][430/1251]	eta 0:30:41 lr 0.000482	time 1.8865 (2.2425)	loss 2.8130 (3.4974)	grad_norm 1.6818 (1.5420)	
[2022-01-22 13:18:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][440/1251]	eta 0:30:17 lr 0.000482	time 2.2131 (2.2410)	loss 3.5797 (3.4973)	grad_norm 1.7022 (1.5422)	
[2022-01-22 13:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][450/1251]	eta 0:29:53 lr 0.000482	time 2.1229 (2.2391)	loss 3.8097 (3.5024)	grad_norm 1.6202 (1.5396)	
[2022-01-22 13:18:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][460/1251]	eta 0:29:27 lr 0.000482	time 2.3019 (2.2345)	loss 3.6089 (3.4951)	grad_norm 1.4147 (1.5400)	
[2022-01-22 13:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][470/1251]	eta 0:29:02 lr 0.000482	time 2.1261 (2.2310)	loss 3.7298 (3.4992)	grad_norm 1.4407 (1.5371)	
[2022-01-22 13:19:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][480/1251]	eta 0:28:37 lr 0.000482	time 2.2937 (2.2271)	loss 2.5038 (3.4922)	grad_norm 1.5313 (1.5360)	
[2022-01-22 13:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][490/1251]	eta 0:28:15 lr 0.000482	time 2.1886 (2.2276)	loss 3.0020 (3.4916)	grad_norm 1.5303 (1.5359)	
[2022-01-22 13:20:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][500/1251]	eta 0:27:50 lr 0.000482	time 1.9049 (2.2240)	loss 3.4741 (3.4891)	grad_norm 1.3502 (1.5346)	
[2022-01-22 13:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][510/1251]	eta 0:27:28 lr 0.000482	time 2.1235 (2.2243)	loss 3.5301 (3.4877)	grad_norm 1.6971 (1.5379)	
[2022-01-22 13:20:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][520/1251]	eta 0:27:07 lr 0.000482	time 3.1773 (2.2260)	loss 3.6943 (3.4920)	grad_norm 1.4786 (1.5375)	
[2022-01-22 13:21:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][530/1251]	eta 0:26:45 lr 0.000482	time 2.0326 (2.2262)	loss 4.3353 (3.4942)	grad_norm 1.2938 (1.5357)	
[2022-01-22 13:21:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][540/1251]	eta 0:26:22 lr 0.000482	time 2.1717 (2.2256)	loss 3.5942 (3.4927)	grad_norm 1.5164 (1.5365)	
[2022-01-22 13:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][550/1251]	eta 0:25:59 lr 0.000482	time 1.8690 (2.2249)	loss 3.5366 (3.4943)	grad_norm 1.6260 (1.5369)	
[2022-01-22 13:22:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][560/1251]	eta 0:25:37 lr 0.000482	time 2.5014 (2.2254)	loss 4.1449 (3.4973)	grad_norm 1.5863 (1.5370)	
[2022-01-22 13:22:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][570/1251]	eta 0:25:15 lr 0.000482	time 1.6390 (2.2252)	loss 3.6195 (3.4917)	grad_norm 1.8477 (1.5384)	
[2022-01-22 13:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][580/1251]	eta 0:24:54 lr 0.000482	time 1.5260 (2.2268)	loss 2.3435 (3.4949)	grad_norm 1.4753 (1.5381)	
[2022-01-22 13:23:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][590/1251]	eta 0:24:32 lr 0.000482	time 1.6645 (2.2280)	loss 3.0133 (3.4975)	grad_norm 1.3875 (1.5380)	
[2022-01-22 13:23:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][600/1251]	eta 0:24:10 lr 0.000482	time 3.5672 (2.2287)	loss 2.7675 (3.4943)	grad_norm 1.3423 (1.5408)	
[2022-01-22 13:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][610/1251]	eta 0:23:47 lr 0.000482	time 1.8301 (2.2268)	loss 3.6445 (3.4914)	grad_norm 1.4535 (1.5418)	
[2022-01-22 13:24:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][620/1251]	eta 0:23:23 lr 0.000482	time 1.8421 (2.2239)	loss 3.4572 (3.4961)	grad_norm 1.8747 (1.5419)	
[2022-01-22 13:24:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][630/1251]	eta 0:23:00 lr 0.000482	time 1.9852 (2.2223)	loss 2.4110 (3.4976)	grad_norm 1.6271 (1.5424)	
[2022-01-22 13:25:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][640/1251]	eta 0:22:37 lr 0.000482	time 2.9032 (2.2220)	loss 3.5817 (3.4995)	grad_norm 1.5340 (1.5418)	
[2022-01-22 13:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][650/1251]	eta 0:22:15 lr 0.000482	time 2.5122 (2.2218)	loss 3.1908 (3.5031)	grad_norm 1.3955 (1.5419)	
[2022-01-22 13:26:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][660/1251]	eta 0:21:52 lr 0.000482	time 1.9415 (2.2204)	loss 3.8743 (3.5001)	grad_norm 1.6196 (1.5421)	
[2022-01-22 13:26:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][670/1251]	eta 0:21:29 lr 0.000481	time 2.1595 (2.2203)	loss 2.6590 (3.4968)	grad_norm 1.3001 (1.5405)	
[2022-01-22 13:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][680/1251]	eta 0:21:06 lr 0.000481	time 2.7822 (2.2182)	loss 3.3604 (3.4982)	grad_norm 1.5336 (1.5404)	
[2022-01-22 13:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][690/1251]	eta 0:20:45 lr 0.000481	time 2.8176 (2.2199)	loss 4.2709 (3.5047)	grad_norm 1.9779 (1.5411)	
[2022-01-22 13:27:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][700/1251]	eta 0:20:22 lr 0.000481	time 2.2071 (2.2194)	loss 3.7568 (3.5047)	grad_norm 1.7279 (1.5419)	
[2022-01-22 13:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][710/1251]	eta 0:20:00 lr 0.000481	time 2.4039 (2.2198)	loss 3.9608 (3.5082)	grad_norm 1.5057 (1.5442)	
[2022-01-22 13:28:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][720/1251]	eta 0:19:38 lr 0.000481	time 2.2271 (2.2188)	loss 3.7631 (3.5094)	grad_norm 1.4701 (1.5443)	
[2022-01-22 13:28:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][730/1251]	eta 0:19:14 lr 0.000481	time 2.3350 (2.2160)	loss 3.6319 (3.5097)	grad_norm 1.5301 (1.5455)	
[2022-01-22 13:28:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][740/1251]	eta 0:18:51 lr 0.000481	time 1.8365 (2.2145)	loss 3.0104 (3.5049)	grad_norm 1.3095 (1.5453)	
[2022-01-22 13:29:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][750/1251]	eta 0:18:28 lr 0.000481	time 1.8898 (2.2134)	loss 3.9218 (3.5059)	grad_norm 1.4334 (1.5451)	
[2022-01-22 13:29:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][760/1251]	eta 0:18:06 lr 0.000481	time 1.9144 (2.2118)	loss 3.4788 (3.5022)	grad_norm 1.6127 (1.5453)	
[2022-01-22 13:30:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][770/1251]	eta 0:17:44 lr 0.000481	time 2.4100 (2.2134)	loss 4.1361 (3.5037)	grad_norm 1.5401 (1.5449)	
[2022-01-22 13:30:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][780/1251]	eta 0:17:22 lr 0.000481	time 1.8524 (2.2137)	loss 3.4893 (3.5029)	grad_norm 1.5476 (1.5445)	
[2022-01-22 13:30:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][790/1251]	eta 0:17:01 lr 0.000481	time 2.0582 (2.2149)	loss 3.1483 (3.5010)	grad_norm 1.6733 (1.5460)	
[2022-01-22 13:31:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][800/1251]	eta 0:16:38 lr 0.000481	time 2.0763 (2.2149)	loss 3.9595 (3.5039)	grad_norm 1.4469 (1.5457)	
[2022-01-22 13:31:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][810/1251]	eta 0:16:15 lr 0.000481	time 2.0946 (2.2121)	loss 3.9034 (3.5041)	grad_norm 1.7658 (1.5465)	
[2022-01-22 13:31:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][820/1251]	eta 0:15:51 lr 0.000481	time 1.9709 (2.2087)	loss 4.2647 (3.5026)	grad_norm 1.4836 (1.5484)	
[2022-01-22 13:32:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][830/1251]	eta 0:15:28 lr 0.000481	time 1.9095 (2.2060)	loss 2.9114 (3.5020)	grad_norm 1.5341 (1.5481)	
[2022-01-22 13:32:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][840/1251]	eta 0:15:06 lr 0.000481	time 1.8779 (2.2048)	loss 3.0254 (3.4977)	grad_norm 1.3332 (1.5464)	
[2022-01-22 13:32:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][850/1251]	eta 0:14:44 lr 0.000481	time 2.4807 (2.2053)	loss 3.7834 (3.5001)	grad_norm 1.6726 (1.5472)	
[2022-01-22 13:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][860/1251]	eta 0:14:21 lr 0.000481	time 1.8418 (2.2046)	loss 3.3591 (3.4964)	grad_norm 1.4572 (1.5469)	
[2022-01-22 13:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][870/1251]	eta 0:13:59 lr 0.000481	time 2.3359 (2.2044)	loss 3.5663 (3.4947)	grad_norm 1.5510 (1.5459)	
[2022-01-22 13:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][880/1251]	eta 0:13:38 lr 0.000481	time 3.1034 (2.2055)	loss 3.5739 (3.4969)	grad_norm 1.4964 (1.5466)	
[2022-01-22 13:34:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][890/1251]	eta 0:13:17 lr 0.000481	time 3.5158 (2.2102)	loss 2.8890 (3.4963)	grad_norm 1.4676 (1.5466)	
[2022-01-22 13:34:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][900/1251]	eta 0:12:56 lr 0.000481	time 2.4982 (2.2111)	loss 3.0637 (3.4935)	grad_norm 1.3761 (1.5458)	
[2022-01-22 13:35:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][910/1251]	eta 0:12:33 lr 0.000481	time 2.9343 (2.2107)	loss 3.8119 (3.4908)	grad_norm 1.3577 (1.5451)	
[2022-01-22 13:35:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][920/1251]	eta 0:12:11 lr 0.000480	time 1.5606 (2.2103)	loss 3.5022 (3.4912)	grad_norm 1.5433 (1.5450)	
[2022-01-22 13:35:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][930/1251]	eta 0:11:49 lr 0.000480	time 2.6180 (2.2094)	loss 3.6322 (3.4897)	grad_norm 1.4039 (1.5438)	
[2022-01-22 13:36:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][940/1251]	eta 0:11:26 lr 0.000480	time 1.9925 (2.2068)	loss 4.2779 (3.4936)	grad_norm 1.4325 (1.5435)	
[2022-01-22 13:36:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][950/1251]	eta 0:11:03 lr 0.000480	time 1.9028 (2.2045)	loss 4.2340 (3.4918)	grad_norm 1.6893 (1.5456)	
[2022-01-22 13:36:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][960/1251]	eta 0:10:40 lr 0.000480	time 1.6015 (2.2027)	loss 3.8493 (3.4920)	grad_norm 1.3720 (1.5469)	
[2022-01-22 13:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][970/1251]	eta 0:10:18 lr 0.000480	time 1.7573 (2.2023)	loss 4.0033 (3.4906)	grad_norm 1.6665 (1.5462)	
[2022-01-22 13:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][980/1251]	eta 0:09:56 lr 0.000480	time 2.4089 (2.2023)	loss 3.1322 (3.4915)	grad_norm 1.5492 (1.5458)	
[2022-01-22 13:37:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][990/1251]	eta 0:09:34 lr 0.000480	time 2.5492 (2.2027)	loss 3.9165 (3.4882)	grad_norm 1.4182 (1.5459)	
[2022-01-22 13:38:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1000/1251]	eta 0:09:12 lr 0.000480	time 2.5082 (2.2024)	loss 4.3400 (3.4888)	grad_norm 1.6609 (1.5463)	
[2022-01-22 13:38:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1010/1251]	eta 0:08:51 lr 0.000480	time 2.2720 (2.2042)	loss 3.8551 (3.4879)	grad_norm 1.4961 (1.5464)	
[2022-01-22 13:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1020/1251]	eta 0:08:29 lr 0.000480	time 2.1011 (2.2063)	loss 2.7130 (3.4901)	grad_norm 1.6112 (1.5464)	
[2022-01-22 13:39:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1030/1251]	eta 0:08:08 lr 0.000480	time 2.8103 (2.2083)	loss 2.5663 (3.4906)	grad_norm 1.8051 (1.5466)	
[2022-01-22 13:39:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1040/1251]	eta 0:07:46 lr 0.000480	time 2.4767 (2.2085)	loss 3.6072 (3.4926)	grad_norm 1.5902 (1.5459)	
[2022-01-22 13:40:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1050/1251]	eta 0:07:23 lr 0.000480	time 2.4415 (2.2084)	loss 3.8596 (3.4928)	grad_norm 1.3895 (1.5448)	
[2022-01-22 13:40:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1060/1251]	eta 0:07:01 lr 0.000480	time 1.8261 (2.2058)	loss 4.5446 (3.4952)	grad_norm 1.4962 (1.5447)	
[2022-01-22 13:40:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1070/1251]	eta 0:06:38 lr 0.000480	time 1.6171 (2.2039)	loss 3.9708 (3.4959)	grad_norm 1.8755 (1.5451)	
[2022-01-22 13:41:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1080/1251]	eta 0:06:16 lr 0.000480	time 2.2262 (2.2043)	loss 3.7102 (3.4948)	grad_norm 1.4885 (1.5452)	
[2022-01-22 13:41:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1090/1251]	eta 0:05:54 lr 0.000480	time 2.2864 (2.2048)	loss 4.0536 (3.4966)	grad_norm 1.8584 (1.5463)	
[2022-01-22 13:42:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1100/1251]	eta 0:05:33 lr 0.000480	time 2.3879 (2.2064)	loss 4.1218 (3.4962)	grad_norm 1.6156 (1.5466)	
[2022-01-22 13:42:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1110/1251]	eta 0:05:11 lr 0.000480	time 1.7937 (2.2063)	loss 3.7419 (3.4966)	grad_norm 1.4196 (1.5465)	
[2022-01-22 13:42:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1120/1251]	eta 0:04:48 lr 0.000480	time 2.1738 (2.2061)	loss 3.5266 (3.4963)	grad_norm 1.3322 (1.5469)	
[2022-01-22 13:43:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1130/1251]	eta 0:04:26 lr 0.000480	time 1.6427 (2.2049)	loss 2.8746 (3.4960)	grad_norm 1.5382 (1.5471)	
[2022-01-22 13:43:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1140/1251]	eta 0:04:04 lr 0.000480	time 2.2036 (2.2056)	loss 3.9981 (3.4980)	grad_norm 1.4844 (1.5461)	
[2022-01-22 13:43:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1150/1251]	eta 0:03:42 lr 0.000480	time 2.9452 (2.2063)	loss 3.0408 (3.5001)	grad_norm 1.6397 (1.5473)	
[2022-01-22 13:44:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1160/1251]	eta 0:03:20 lr 0.000479	time 1.8484 (2.2050)	loss 3.3143 (3.5005)	grad_norm 1.5905 (1.5471)	
[2022-01-22 13:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1170/1251]	eta 0:02:58 lr 0.000479	time 2.4663 (2.2038)	loss 3.2119 (3.5028)	grad_norm 1.4883 (1.5471)	
[2022-01-22 13:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1180/1251]	eta 0:02:36 lr 0.000479	time 2.0889 (2.2023)	loss 2.7343 (3.5031)	grad_norm 1.7068 (1.5476)	
[2022-01-22 13:45:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1190/1251]	eta 0:02:14 lr 0.000479	time 2.8700 (2.2021)	loss 3.9806 (3.5030)	grad_norm 1.3668 (1.5476)	
[2022-01-22 13:45:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1200/1251]	eta 0:01:52 lr 0.000479	time 2.8522 (2.2033)	loss 3.0453 (3.5027)	grad_norm 1.4683 (1.5470)	
[2022-01-22 13:46:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1210/1251]	eta 0:01:30 lr 0.000479	time 2.2524 (2.2046)	loss 3.1503 (3.5008)	grad_norm 1.6085 (1.5470)	
[2022-01-22 13:46:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1220/1251]	eta 0:01:08 lr 0.000479	time 1.4649 (2.2051)	loss 3.9122 (3.5001)	grad_norm 1.5091 (1.5465)	
[2022-01-22 13:46:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1230/1251]	eta 0:00:46 lr 0.000479	time 3.7614 (2.2059)	loss 3.9961 (3.5017)	grad_norm 1.6166 (1.5463)	
[2022-01-22 13:47:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1240/1251]	eta 0:00:24 lr 0.000479	time 1.2124 (2.2033)	loss 4.2808 (3.5034)	grad_norm 1.5757 (1.5458)	
[2022-01-22 13:47:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [154/300][1250/1251]	eta 0:00:02 lr 0.000479	time 1.2041 (2.1973)	loss 2.6050 (3.5053)	grad_norm 1.4222 (1.5454)	
[2022-01-22 13:47:25 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 154 training takes 0:45:49
[2022-01-22 13:47:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.140 (18.140)	Loss 0.9670 (0.9670)	Acc@1 78.418 (78.418)	Acc@5 93.750 (93.750)	
[2022-01-22 13:48:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.262 (3.355)	Loss 0.9696 (1.0348)	Acc@1 79.785 (76.225)	Acc@5 93.945 (93.208)	
[2022-01-22 13:48:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.891 (2.684)	Loss 1.0392 (1.0392)	Acc@1 75.488 (76.004)	Acc@5 93.848 (93.192)	
[2022-01-22 13:48:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.593 (2.224)	Loss 1.0680 (1.0325)	Acc@1 75.098 (76.112)	Acc@5 92.383 (93.230)	
[2022-01-22 13:48:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.134 (2.179)	Loss 1.0032 (1.0294)	Acc@1 77.441 (76.143)	Acc@5 93.848 (93.250)	
[2022-01-22 13:49:02 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.156 Acc@5 93.294
[2022-01-22 13:49:02 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.2%
[2022-01-22 13:49:02 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.30%
[2022-01-22 13:49:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][0/1251]	eta 7:07:12 lr 0.000479	time 20.4892 (20.4892)	loss 3.4387 (3.4387)	grad_norm 1.3399 (1.3399)	
[2022-01-22 13:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][10/1251]	eta 1:21:08 lr 0.000479	time 2.9071 (3.9231)	loss 3.9518 (3.4837)	grad_norm 1.4195 (1.4638)	
[2022-01-22 13:50:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][20/1251]	eta 1:03:06 lr 0.000479	time 1.5413 (3.0760)	loss 3.7387 (3.5320)	grad_norm 1.5865 (1.5059)	
[2022-01-22 13:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][30/1251]	eta 0:57:34 lr 0.000479	time 1.8325 (2.8292)	loss 3.8308 (3.5359)	grad_norm 1.6060 (1.5346)	
[2022-01-22 13:50:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][40/1251]	eta 0:55:18 lr 0.000479	time 3.8446 (2.7403)	loss 3.3036 (3.5610)	grad_norm 1.4033 (1.5229)	
[2022-01-22 13:51:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][50/1251]	eta 0:53:10 lr 0.000479	time 2.6464 (2.6563)	loss 3.9128 (3.5511)	grad_norm 1.3659 (1.5140)	
[2022-01-22 13:51:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][60/1251]	eta 0:51:10 lr 0.000479	time 1.7561 (2.5782)	loss 4.2899 (3.5635)	grad_norm 1.6937 (1.5172)	
[2022-01-22 13:52:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][70/1251]	eta 0:49:39 lr 0.000479	time 1.9305 (2.5230)	loss 3.1118 (3.5265)	grad_norm 1.4224 (1.5291)	
[2022-01-22 13:52:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][80/1251]	eta 0:48:46 lr 0.000479	time 4.2527 (2.4992)	loss 3.0963 (3.4975)	grad_norm 1.3844 (1.5275)	
[2022-01-22 13:52:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][90/1251]	eta 0:47:35 lr 0.000479	time 2.0450 (2.4595)	loss 3.6958 (3.4932)	grad_norm 1.6565 (1.5240)	
[2022-01-22 13:53:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][100/1251]	eta 0:46:34 lr 0.000479	time 1.7834 (2.4280)	loss 3.7355 (3.4674)	grad_norm 1.4451 (1.5170)	
[2022-01-22 13:53:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][110/1251]	eta 0:45:44 lr 0.000479	time 2.2226 (2.4055)	loss 3.4795 (3.4755)	grad_norm 1.5143 (1.5188)	
[2022-01-22 13:53:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][120/1251]	eta 0:45:00 lr 0.000479	time 2.8511 (2.3873)	loss 3.5651 (3.4640)	grad_norm 1.4233 (1.5194)	
[2022-01-22 13:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][130/1251]	eta 0:44:10 lr 0.000479	time 1.9912 (2.3643)	loss 2.5891 (3.4730)	grad_norm 1.8572 (1.5207)	
[2022-01-22 13:54:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][140/1251]	eta 0:43:28 lr 0.000479	time 2.0219 (2.3482)	loss 2.9936 (3.4718)	grad_norm 1.6286 (1.5203)	
[2022-01-22 13:54:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][150/1251]	eta 0:43:01 lr 0.000478	time 2.3341 (2.3443)	loss 3.6675 (3.4893)	grad_norm 1.6279 (1.5212)	
[2022-01-22 13:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][160/1251]	eta 0:42:34 lr 0.000478	time 3.4206 (2.3415)	loss 4.0139 (3.5005)	grad_norm 1.4506 (1.5227)	
[2022-01-22 13:55:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][170/1251]	eta 0:42:02 lr 0.000478	time 1.6968 (2.3331)	loss 3.5899 (3.5099)	grad_norm 1.5660 (1.5248)	
[2022-01-22 13:56:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][180/1251]	eta 0:41:18 lr 0.000478	time 1.8408 (2.3143)	loss 2.6209 (3.4955)	grad_norm 1.4152 (1.5250)	
[2022-01-22 13:56:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][190/1251]	eta 0:40:39 lr 0.000478	time 2.2192 (2.2994)	loss 3.7941 (3.5042)	grad_norm 1.6050 (1.5219)	
[2022-01-22 13:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][200/1251]	eta 0:39:59 lr 0.000478	time 2.2336 (2.2831)	loss 3.3870 (3.4941)	grad_norm 1.4471 (1.5213)	
[2022-01-22 13:57:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][210/1251]	eta 0:39:29 lr 0.000478	time 1.9924 (2.2765)	loss 2.4570 (3.4849)	grad_norm 1.6342 (1.5189)	
[2022-01-22 13:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][220/1251]	eta 0:39:08 lr 0.000478	time 2.5547 (2.2775)	loss 3.7024 (3.4841)	grad_norm 1.2868 (1.5175)	
[2022-01-22 13:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][230/1251]	eta 0:38:46 lr 0.000478	time 2.1701 (2.2786)	loss 3.4480 (3.4843)	grad_norm 1.5012 (1.5174)	
[2022-01-22 13:58:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][240/1251]	eta 0:38:25 lr 0.000478	time 2.7687 (2.2803)	loss 3.2893 (3.4784)	grad_norm 1.3126 (1.5170)	
[2022-01-22 13:58:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][250/1251]	eta 0:38:02 lr 0.000478	time 1.9119 (2.2802)	loss 3.2052 (3.4859)	grad_norm 1.7184 (1.5185)	
[2022-01-22 13:58:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][260/1251]	eta 0:37:34 lr 0.000478	time 2.2212 (2.2753)	loss 3.9744 (3.4848)	grad_norm 1.3227 (1.5225)	
[2022-01-22 13:59:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][270/1251]	eta 0:37:07 lr 0.000478	time 2.1516 (2.2701)	loss 3.1731 (3.4899)	grad_norm 1.3467 (1.5213)	
[2022-01-22 13:59:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][280/1251]	eta 0:36:41 lr 0.000478	time 2.2482 (2.2668)	loss 3.6753 (3.4934)	grad_norm 1.2269 (1.5192)	
[2022-01-22 14:00:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][290/1251]	eta 0:36:15 lr 0.000478	time 2.2096 (2.2639)	loss 3.4084 (3.4999)	grad_norm 1.4633 (1.5184)	
[2022-01-22 14:00:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][300/1251]	eta 0:35:48 lr 0.000478	time 2.4753 (2.2596)	loss 3.3554 (3.5005)	grad_norm 1.4001 (1.5182)	
[2022-01-22 14:00:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][310/1251]	eta 0:35:25 lr 0.000478	time 3.4361 (2.2586)	loss 4.0857 (3.5044)	grad_norm 1.4169 (1.5166)	
[2022-01-22 14:01:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][320/1251]	eta 0:35:04 lr 0.000478	time 1.8950 (2.2605)	loss 3.8680 (3.5057)	grad_norm 1.5297 (1.5162)	
[2022-01-22 14:01:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][330/1251]	eta 0:34:40 lr 0.000478	time 1.5481 (2.2593)	loss 3.9149 (3.5053)	grad_norm 1.4283 (1.5151)	
[2022-01-22 14:01:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][340/1251]	eta 0:34:15 lr 0.000478	time 1.5955 (2.2564)	loss 4.1223 (3.5067)	grad_norm 1.3894 (1.5138)	
[2022-01-22 14:02:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][350/1251]	eta 0:33:50 lr 0.000478	time 2.5648 (2.2541)	loss 3.5970 (3.5126)	grad_norm 1.3986 (1.5136)	
[2022-01-22 14:02:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][360/1251]	eta 0:33:22 lr 0.000478	time 2.1621 (2.2471)	loss 2.6152 (3.5043)	grad_norm 1.3889 (1.5158)	
[2022-01-22 14:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][370/1251]	eta 0:32:53 lr 0.000478	time 1.9267 (2.2403)	loss 3.6772 (3.5066)	grad_norm 1.5695 (1.5160)	
[2022-01-22 14:03:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][380/1251]	eta 0:32:32 lr 0.000478	time 1.5449 (2.2421)	loss 3.7126 (3.5064)	grad_norm 1.7882 (1.5194)	
[2022-01-22 14:03:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][390/1251]	eta 0:32:07 lr 0.000477	time 1.9644 (2.2390)	loss 3.9821 (3.5080)	grad_norm 1.6578 (1.5223)	
[2022-01-22 14:04:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][400/1251]	eta 0:31:46 lr 0.000477	time 2.3178 (2.2408)	loss 3.7920 (3.5033)	grad_norm 1.3226 (1.5230)	
[2022-01-22 14:04:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][410/1251]	eta 0:31:26 lr 0.000477	time 2.5806 (2.2428)	loss 3.3642 (3.5058)	grad_norm 1.5795 (1.5257)	
[2022-01-22 14:04:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][420/1251]	eta 0:31:01 lr 0.000477	time 1.6029 (2.2405)	loss 3.9932 (3.5048)	grad_norm 1.7793 (1.5306)	
[2022-01-22 14:05:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][430/1251]	eta 0:30:43 lr 0.000477	time 3.1996 (2.2448)	loss 3.1192 (3.5047)	grad_norm 1.5585 (1.5298)	
[2022-01-22 14:05:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][440/1251]	eta 0:30:21 lr 0.000477	time 2.0918 (2.2456)	loss 4.3012 (3.5059)	grad_norm 1.5713 (1.5300)	
[2022-01-22 14:05:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][450/1251]	eta 0:29:54 lr 0.000477	time 1.8782 (2.2408)	loss 4.1163 (3.5023)	grad_norm 1.5249 (1.5307)	
[2022-01-22 14:06:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][460/1251]	eta 0:29:26 lr 0.000477	time 1.8628 (2.2338)	loss 3.5719 (3.5006)	grad_norm 1.6074 (1.5326)	
[2022-01-22 14:06:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][470/1251]	eta 0:28:59 lr 0.000477	time 2.2683 (2.2277)	loss 3.3949 (3.5053)	grad_norm 1.4410 (1.5309)	
[2022-01-22 14:06:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][480/1251]	eta 0:28:37 lr 0.000477	time 2.7306 (2.2270)	loss 3.5983 (3.4995)	grad_norm 1.4657 (1.5301)	
[2022-01-22 14:07:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][490/1251]	eta 0:28:16 lr 0.000477	time 2.5533 (2.2296)	loss 3.6270 (3.5063)	grad_norm 1.5625 (1.5299)	
[2022-01-22 14:07:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][500/1251]	eta 0:27:55 lr 0.000477	time 1.2154 (2.2307)	loss 2.7936 (3.5068)	grad_norm 1.3124 (1.5296)	
[2022-01-22 14:08:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][510/1251]	eta 0:27:31 lr 0.000477	time 1.8512 (2.2288)	loss 3.3328 (3.5059)	grad_norm 1.6011 (1.5308)	
[2022-01-22 14:08:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][520/1251]	eta 0:27:11 lr 0.000477	time 3.0841 (2.2315)	loss 3.8324 (3.5035)	grad_norm 1.6505 (1.5330)	
[2022-01-22 14:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][530/1251]	eta 0:26:49 lr 0.000477	time 2.2729 (2.2325)	loss 3.0618 (3.4972)	grad_norm 1.4796 (1.5319)	
[2022-01-22 14:09:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][540/1251]	eta 0:26:26 lr 0.000477	time 1.5819 (2.2314)	loss 4.1683 (3.5021)	grad_norm 1.5457 (1.5306)	
[2022-01-22 14:09:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][550/1251]	eta 0:26:02 lr 0.000477	time 2.2717 (2.2295)	loss 3.1876 (3.4991)	grad_norm 1.4162 (1.5299)	
[2022-01-22 14:09:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][560/1251]	eta 0:25:38 lr 0.000477	time 1.8649 (2.2267)	loss 2.8889 (3.4988)	grad_norm 1.8836 (1.5310)	
[2022-01-22 14:10:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][570/1251]	eta 0:25:15 lr 0.000477	time 2.0724 (2.2251)	loss 2.6460 (3.4951)	grad_norm 1.6796 (1.5305)	
[2022-01-22 14:10:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][580/1251]	eta 0:24:51 lr 0.000477	time 2.1034 (2.2235)	loss 3.9476 (3.4974)	grad_norm 1.3837 (1.5314)	
[2022-01-22 14:10:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][590/1251]	eta 0:24:28 lr 0.000477	time 2.1484 (2.2223)	loss 2.6363 (3.5006)	grad_norm 1.5824 (1.5321)	
[2022-01-22 14:11:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][600/1251]	eta 0:24:06 lr 0.000477	time 2.3784 (2.2227)	loss 3.9826 (3.5045)	grad_norm 1.6286 (1.5325)	
[2022-01-22 14:11:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][610/1251]	eta 0:23:43 lr 0.000477	time 1.9210 (2.2207)	loss 3.4584 (3.5072)	grad_norm 1.5307 (1.5312)	
[2022-01-22 14:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][620/1251]	eta 0:23:19 lr 0.000477	time 2.0586 (2.2174)	loss 4.2105 (3.5054)	grad_norm 1.5315 (1.5309)	
[2022-01-22 14:12:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][630/1251]	eta 0:22:56 lr 0.000476	time 2.2000 (2.2162)	loss 2.3887 (3.5029)	grad_norm 1.6447 (1.5334)	
[2022-01-22 14:12:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][640/1251]	eta 0:22:33 lr 0.000476	time 1.5907 (2.2147)	loss 3.9021 (3.5047)	grad_norm 1.3965 (1.5331)	
[2022-01-22 14:13:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][650/1251]	eta 0:22:10 lr 0.000476	time 1.5434 (2.2140)	loss 2.9356 (3.5024)	grad_norm 1.5002 (1.5336)	
[2022-01-22 14:13:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][660/1251]	eta 0:21:48 lr 0.000476	time 1.9695 (2.2139)	loss 3.5563 (3.4983)	grad_norm 1.4205 (1.5351)	
[2022-01-22 14:13:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][670/1251]	eta 0:21:25 lr 0.000476	time 2.2841 (2.2132)	loss 2.7388 (3.5004)	grad_norm 1.3806 (1.5348)	
[2022-01-22 14:14:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][680/1251]	eta 0:21:05 lr 0.000476	time 2.9667 (2.2167)	loss 3.8533 (3.5030)	grad_norm 1.6182 (1.5355)	
[2022-01-22 14:14:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][690/1251]	eta 0:20:45 lr 0.000476	time 1.8572 (2.2203)	loss 4.2779 (3.5035)	grad_norm 1.5346 (1.5355)	
[2022-01-22 14:14:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][700/1251]	eta 0:20:23 lr 0.000476	time 1.9599 (2.2211)	loss 2.8826 (3.5054)	grad_norm 1.6069 (1.5348)	
[2022-01-22 14:15:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][710/1251]	eta 0:20:01 lr 0.000476	time 2.5259 (2.2204)	loss 2.9995 (3.5067)	grad_norm 1.6428 (1.5354)	
[2022-01-22 14:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][720/1251]	eta 0:19:37 lr 0.000476	time 2.1942 (2.2179)	loss 3.8306 (3.5101)	grad_norm 1.7042 (1.5346)	
[2022-01-22 14:16:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][730/1251]	eta 0:19:13 lr 0.000476	time 1.6162 (2.2132)	loss 3.9355 (3.5122)	grad_norm 1.3603 (1.5335)	
[2022-01-22 14:16:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][740/1251]	eta 0:18:49 lr 0.000476	time 2.2575 (2.2099)	loss 4.1477 (3.5130)	grad_norm 1.4013 (1.5331)	
[2022-01-22 14:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][750/1251]	eta 0:18:27 lr 0.000476	time 1.9451 (2.2102)	loss 2.3053 (3.5111)	grad_norm 1.2913 (1.5326)	
[2022-01-22 14:17:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][760/1251]	eta 0:18:05 lr 0.000476	time 2.2408 (2.2111)	loss 3.8909 (3.5109)	grad_norm 1.6111 (1.5330)	
[2022-01-22 14:17:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][770/1251]	eta 0:17:44 lr 0.000476	time 2.4407 (2.2128)	loss 4.1775 (3.5080)	grad_norm 1.5788 (1.5328)	
[2022-01-22 14:17:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][780/1251]	eta 0:17:22 lr 0.000476	time 2.5220 (2.2131)	loss 3.9276 (3.5068)	grad_norm 1.2677 (1.5332)	
[2022-01-22 14:18:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][790/1251]	eta 0:17:00 lr 0.000476	time 2.0978 (2.2128)	loss 3.8308 (3.5072)	grad_norm 1.5872 (1.5333)	
[2022-01-22 14:18:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][800/1251]	eta 0:16:37 lr 0.000476	time 2.5116 (2.2121)	loss 3.2328 (3.5103)	grad_norm 1.4020 (1.5339)	
[2022-01-22 14:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][810/1251]	eta 0:16:15 lr 0.000476	time 2.1879 (2.2118)	loss 3.5229 (3.5095)	grad_norm 1.4309 (1.5339)	
[2022-01-22 14:19:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][820/1251]	eta 0:15:53 lr 0.000476	time 2.0964 (2.2111)	loss 3.5857 (3.5100)	grad_norm 1.4469 (1.5355)	
[2022-01-22 14:19:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][830/1251]	eta 0:15:30 lr 0.000476	time 1.8465 (2.2098)	loss 3.3759 (3.5134)	grad_norm 1.5202 (1.5346)	
[2022-01-22 14:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][840/1251]	eta 0:15:08 lr 0.000476	time 1.9633 (2.2093)	loss 3.5472 (3.5137)	grad_norm 1.2519 (1.5347)	
[2022-01-22 14:20:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][850/1251]	eta 0:14:45 lr 0.000476	time 1.9461 (2.2094)	loss 3.3364 (3.5144)	grad_norm 1.7953 (1.5350)	
[2022-01-22 14:20:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][860/1251]	eta 0:14:24 lr 0.000476	time 3.4780 (2.2100)	loss 3.7891 (3.5122)	grad_norm 1.4706 (1.5358)	
[2022-01-22 14:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][870/1251]	eta 0:14:02 lr 0.000475	time 2.3568 (2.2109)	loss 4.1964 (3.5129)	grad_norm 1.7764 (1.5362)	
[2022-01-22 14:21:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][880/1251]	eta 0:13:40 lr 0.000475	time 1.7850 (2.2109)	loss 4.0101 (3.5146)	grad_norm 1.6019 (1.5363)	
[2022-01-22 14:21:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][890/1251]	eta 0:13:18 lr 0.000475	time 1.9186 (2.2121)	loss 4.0576 (3.5179)	grad_norm 1.5790 (1.5373)	
[2022-01-22 14:22:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][900/1251]	eta 0:12:57 lr 0.000475	time 3.6043 (2.2138)	loss 2.5123 (3.5185)	grad_norm 1.3955 (1.5378)	
[2022-01-22 14:22:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][910/1251]	eta 0:12:34 lr 0.000475	time 2.1871 (2.2124)	loss 2.8066 (3.5165)	grad_norm 1.6268 (1.5381)	
[2022-01-22 14:22:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][920/1251]	eta 0:12:11 lr 0.000475	time 1.8489 (2.2102)	loss 3.6142 (3.5148)	grad_norm 1.4124 (1.5383)	
[2022-01-22 14:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][930/1251]	eta 0:11:49 lr 0.000475	time 1.8927 (2.2090)	loss 4.0462 (3.5157)	grad_norm 1.5074 (1.5384)	
[2022-01-22 14:23:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][940/1251]	eta 0:11:27 lr 0.000475	time 3.8815 (2.2107)	loss 3.6278 (3.5171)	grad_norm 1.5099 (1.5389)	
[2022-01-22 14:24:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][950/1251]	eta 0:11:05 lr 0.000475	time 2.1172 (2.2112)	loss 3.6861 (3.5161)	grad_norm 1.3880 (1.5387)	
[2022-01-22 14:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][960/1251]	eta 0:10:43 lr 0.000475	time 1.6987 (2.2103)	loss 4.0817 (3.5174)	grad_norm 1.5669 (1.5385)	
[2022-01-22 14:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][970/1251]	eta 0:10:20 lr 0.000475	time 1.6606 (2.2091)	loss 4.0843 (3.5149)	grad_norm 1.5952 (1.5395)	
[2022-01-22 14:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][980/1251]	eta 0:09:58 lr 0.000475	time 3.7460 (2.2094)	loss 3.2330 (3.5163)	grad_norm 1.5946 (1.5402)	
[2022-01-22 14:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][990/1251]	eta 0:09:36 lr 0.000475	time 1.9287 (2.2088)	loss 4.1133 (3.5163)	grad_norm 1.5781 (1.5399)	
[2022-01-22 14:25:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1000/1251]	eta 0:09:14 lr 0.000475	time 2.1538 (2.2101)	loss 3.7963 (3.5187)	grad_norm 1.4378 (1.5394)	
[2022-01-22 14:26:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1010/1251]	eta 0:08:52 lr 0.000475	time 2.1121 (2.2087)	loss 2.5592 (3.5171)	grad_norm 1.4626 (1.5392)	
[2022-01-22 14:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1020/1251]	eta 0:08:30 lr 0.000475	time 3.7197 (2.2104)	loss 2.9659 (3.5179)	grad_norm 1.7033 (1.5404)	
[2022-01-22 14:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1030/1251]	eta 0:08:08 lr 0.000475	time 1.7076 (2.2091)	loss 4.0461 (3.5207)	grad_norm 2.0635 (1.5410)	
[2022-01-22 14:27:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1040/1251]	eta 0:07:45 lr 0.000475	time 1.9927 (2.2081)	loss 3.7605 (3.5224)	grad_norm 1.9307 (1.5418)	
[2022-01-22 14:27:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1050/1251]	eta 0:07:23 lr 0.000475	time 1.6979 (2.2071)	loss 4.4402 (3.5233)	grad_norm 1.8662 (1.5415)	
[2022-01-22 14:28:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1060/1251]	eta 0:07:01 lr 0.000475	time 3.0542 (2.2069)	loss 3.8761 (3.5223)	grad_norm 1.4507 (1.5415)	
[2022-01-22 14:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1070/1251]	eta 0:06:39 lr 0.000475	time 1.9014 (2.2054)	loss 3.3434 (3.5225)	grad_norm 1.5447 (1.5424)	
[2022-01-22 14:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1080/1251]	eta 0:06:17 lr 0.000475	time 2.2027 (2.2053)	loss 2.7237 (3.5208)	grad_norm 1.5041 (1.5426)	
[2022-01-22 14:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1090/1251]	eta 0:05:55 lr 0.000475	time 2.2425 (2.2057)	loss 2.5165 (3.5208)	grad_norm 1.4631 (1.5427)	
[2022-01-22 14:29:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1100/1251]	eta 0:05:32 lr 0.000475	time 2.0297 (2.2046)	loss 3.0418 (3.5197)	grad_norm 1.5049 (1.5434)	
[2022-01-22 14:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1110/1251]	eta 0:05:10 lr 0.000475	time 1.9906 (2.2035)	loss 3.0062 (3.5201)	grad_norm 1.5821 (1.5440)	
[2022-01-22 14:30:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1120/1251]	eta 0:04:48 lr 0.000474	time 2.1795 (2.2028)	loss 3.8218 (3.5190)	grad_norm 1.3543 (1.5431)	
[2022-01-22 14:30:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1130/1251]	eta 0:04:26 lr 0.000474	time 1.6170 (2.2023)	loss 3.2970 (3.5186)	grad_norm 1.6173 (1.5426)	
[2022-01-22 14:30:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1140/1251]	eta 0:04:04 lr 0.000474	time 2.8366 (2.2031)	loss 3.5763 (3.5198)	grad_norm 1.4249 (1.5426)	
[2022-01-22 14:31:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1150/1251]	eta 0:03:42 lr 0.000474	time 2.5454 (2.2034)	loss 3.9286 (3.5191)	grad_norm 1.6508 (1.5431)	
[2022-01-22 14:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1160/1251]	eta 0:03:20 lr 0.000474	time 1.8219 (2.2043)	loss 3.5302 (3.5196)	grad_norm 1.4171 (1.5423)	
[2022-01-22 14:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1170/1251]	eta 0:02:58 lr 0.000474	time 1.8481 (2.2037)	loss 3.7262 (3.5190)	grad_norm 1.3530 (1.5416)	
[2022-01-22 14:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1180/1251]	eta 0:02:36 lr 0.000474	time 2.1682 (2.2024)	loss 2.8944 (3.5190)	grad_norm 1.4402 (1.5414)	
[2022-01-22 14:32:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1190/1251]	eta 0:02:14 lr 0.000474	time 1.9848 (2.2013)	loss 3.8709 (3.5211)	grad_norm 1.6610 (1.5417)	
[2022-01-22 14:33:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1200/1251]	eta 0:01:52 lr 0.000474	time 2.6563 (2.2010)	loss 3.0984 (3.5197)	grad_norm 1.8480 (1.5425)	
[2022-01-22 14:33:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1210/1251]	eta 0:01:30 lr 0.000474	time 2.2404 (2.2009)	loss 3.7092 (3.5178)	grad_norm 1.6183 (1.5427)	
[2022-01-22 14:33:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1220/1251]	eta 0:01:08 lr 0.000474	time 2.0572 (2.2002)	loss 2.7963 (3.5154)	grad_norm 1.3258 (1.5423)	
[2022-01-22 14:34:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1230/1251]	eta 0:00:46 lr 0.000474	time 2.2743 (2.2008)	loss 3.4278 (3.5143)	grad_norm 1.3439 (1.5420)	
[2022-01-22 14:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1240/1251]	eta 0:00:24 lr 0.000474	time 2.2662 (2.1996)	loss 3.8482 (3.5141)	grad_norm 1.4011 (1.5419)	
[2022-01-22 14:34:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [155/300][1250/1251]	eta 0:00:02 lr 0.000474	time 1.1730 (2.1942)	loss 4.0729 (3.5148)	grad_norm 1.4609 (1.5421)	
[2022-01-22 14:34:47 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 155 training takes 0:45:45
[2022-01-22 14:35:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 20.712 (20.712)	Loss 0.9550 (0.9550)	Acc@1 77.441 (77.441)	Acc@5 93.457 (93.457)	
[2022-01-22 14:35:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.637 (3.428)	Loss 1.0063 (0.9823)	Acc@1 77.344 (76.403)	Acc@5 93.066 (93.679)	
[2022-01-22 14:35:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.608 (2.443)	Loss 0.9776 (1.0000)	Acc@1 77.441 (76.204)	Acc@5 93.555 (93.494)	
[2022-01-22 14:35:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.976 (2.228)	Loss 0.9286 (0.9991)	Acc@1 77.051 (76.162)	Acc@5 94.336 (93.514)	
[2022-01-22 14:36:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.647 (2.177)	Loss 1.0202 (0.9957)	Acc@1 76.465 (76.348)	Acc@5 92.285 (93.498)	
[2022-01-22 14:36:23 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.278 Acc@5 93.430
[2022-01-22 14:36:23 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.3%
[2022-01-22 14:36:23 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.30%
[2022-01-22 14:36:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][0/1251]	eta 7:24:35 lr 0.000474	time 21.3236 (21.3236)	loss 4.0382 (4.0382)	grad_norm 1.6244 (1.6244)	
[2022-01-22 14:37:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][10/1251]	eta 1:24:10 lr 0.000474	time 2.1647 (4.0700)	loss 3.1890 (3.6292)	grad_norm 1.3700 (1.5452)	
[2022-01-22 14:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][20/1251]	eta 1:05:32 lr 0.000474	time 1.8439 (3.1944)	loss 3.4251 (3.6155)	grad_norm 1.5774 (1.5496)	
[2022-01-22 14:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][30/1251]	eta 0:58:52 lr 0.000474	time 1.4658 (2.8931)	loss 2.6423 (3.6301)	grad_norm 1.5167 (1.5528)	
[2022-01-22 14:38:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][40/1251]	eta 0:55:50 lr 0.000474	time 3.8447 (2.7669)	loss 3.6806 (3.6150)	grad_norm 1.4918 (1.5572)	
[2022-01-22 14:38:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][50/1251]	eta 0:53:41 lr 0.000474	time 1.4702 (2.6823)	loss 3.7945 (3.6011)	grad_norm 1.3918 (1.5559)	
[2022-01-22 14:39:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][60/1251]	eta 0:51:46 lr 0.000474	time 1.5442 (2.6085)	loss 3.8929 (3.5524)	grad_norm 1.5415 (1.5535)	
[2022-01-22 14:39:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][70/1251]	eta 0:50:31 lr 0.000474	time 1.7675 (2.5668)	loss 3.2182 (3.5512)	grad_norm 1.3840 (1.5529)	
[2022-01-22 14:39:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][80/1251]	eta 0:48:58 lr 0.000474	time 2.0277 (2.5097)	loss 2.4362 (3.5065)	grad_norm 1.3676 (1.5432)	
[2022-01-22 14:40:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][90/1251]	eta 0:47:32 lr 0.000474	time 1.6402 (2.4566)	loss 3.9837 (3.5372)	grad_norm 1.4326 (1.5397)	
[2022-01-22 14:40:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][100/1251]	eta 0:46:35 lr 0.000474	time 1.7466 (2.4287)	loss 4.1407 (3.5558)	grad_norm 2.1871 (1.5495)	
[2022-01-22 14:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][110/1251]	eta 0:45:41 lr 0.000473	time 2.0244 (2.4031)	loss 2.6920 (3.5772)	grad_norm 1.3986 (1.5411)	
[2022-01-22 14:41:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][120/1251]	eta 0:45:00 lr 0.000473	time 2.6458 (2.3876)	loss 3.9087 (3.5574)	grad_norm 1.6735 (1.5363)	
[2022-01-22 14:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][130/1251]	eta 0:44:18 lr 0.000473	time 1.9994 (2.3718)	loss 3.5773 (3.5440)	grad_norm 1.6801 (1.5361)	
[2022-01-22 14:41:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][140/1251]	eta 0:43:43 lr 0.000473	time 1.9005 (2.3610)	loss 2.6282 (3.5399)	grad_norm 1.4994 (1.5323)	
[2022-01-22 14:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][150/1251]	eta 0:42:56 lr 0.000473	time 2.3241 (2.3404)	loss 3.2674 (3.5411)	grad_norm 1.4041 (1.5334)	
[2022-01-22 14:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][160/1251]	eta 0:42:14 lr 0.000473	time 2.2195 (2.3227)	loss 3.0808 (3.5394)	grad_norm 1.6195 (1.5424)	
[2022-01-22 14:42:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][170/1251]	eta 0:41:36 lr 0.000473	time 2.0217 (2.3096)	loss 4.2209 (3.5297)	grad_norm 1.6470 (1.5483)	
[2022-01-22 14:43:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][180/1251]	eta 0:41:17 lr 0.000473	time 2.8208 (2.3135)	loss 3.9136 (3.5389)	grad_norm 1.6651 (1.5495)	
[2022-01-22 14:43:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][190/1251]	eta 0:40:54 lr 0.000473	time 2.2466 (2.3132)	loss 3.2883 (3.5311)	grad_norm 1.3713 (1.5520)	
[2022-01-22 14:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][200/1251]	eta 0:40:23 lr 0.000473	time 1.2365 (2.3057)	loss 3.7567 (3.5275)	grad_norm 1.5305 (1.5526)	
[2022-01-22 14:44:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][210/1251]	eta 0:39:56 lr 0.000473	time 1.5665 (2.3025)	loss 3.8246 (3.5258)	grad_norm 1.6547 (1.5528)	
[2022-01-22 14:44:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][220/1251]	eta 0:39:33 lr 0.000473	time 2.7543 (2.3024)	loss 3.6022 (3.5261)	grad_norm 1.4643 (1.5545)	
[2022-01-22 14:45:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][230/1251]	eta 0:38:58 lr 0.000473	time 2.2880 (2.2902)	loss 2.4180 (3.5119)	grad_norm 1.5932 (1.5542)	
[2022-01-22 14:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][240/1251]	eta 0:38:18 lr 0.000473	time 1.8350 (2.2737)	loss 3.6444 (3.5122)	grad_norm 1.3668 (1.5501)	
[2022-01-22 14:45:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][250/1251]	eta 0:37:46 lr 0.000473	time 2.1995 (2.2646)	loss 3.5427 (3.5047)	grad_norm 1.4954 (1.5453)	
[2022-01-22 14:46:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][260/1251]	eta 0:37:21 lr 0.000473	time 2.3005 (2.2621)	loss 3.8356 (3.4992)	grad_norm 1.3158 (1.5452)	
[2022-01-22 14:46:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][270/1251]	eta 0:36:54 lr 0.000473	time 1.6207 (2.2578)	loss 2.8919 (3.5042)	grad_norm 1.4329 (1.5456)	
[2022-01-22 14:46:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][280/1251]	eta 0:36:33 lr 0.000473	time 2.4661 (2.2591)	loss 4.3452 (3.5010)	grad_norm 1.4694 (1.5486)	
[2022-01-22 14:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][290/1251]	eta 0:36:16 lr 0.000473	time 2.4001 (2.2650)	loss 3.5168 (3.4945)	grad_norm 1.5561 (1.5481)	
[2022-01-22 14:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][300/1251]	eta 0:35:52 lr 0.000473	time 1.8726 (2.2638)	loss 3.7498 (3.5028)	grad_norm 1.3276 (1.5452)	
[2022-01-22 14:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][310/1251]	eta 0:35:28 lr 0.000473	time 1.5972 (2.2618)	loss 3.9922 (3.5018)	grad_norm 1.6522 (1.5463)	
[2022-01-22 14:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][320/1251]	eta 0:35:02 lr 0.000473	time 1.9971 (2.2585)	loss 3.6813 (3.5074)	grad_norm 1.3853 (1.5468)	
[2022-01-22 14:48:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][330/1251]	eta 0:34:32 lr 0.000473	time 2.3135 (2.2503)	loss 4.1018 (3.5085)	grad_norm 1.5633 (1.5463)	
[2022-01-22 14:49:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][340/1251]	eta 0:34:07 lr 0.000473	time 1.9227 (2.2471)	loss 3.8682 (3.5068)	grad_norm 1.4704 (1.5438)	
[2022-01-22 14:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][350/1251]	eta 0:33:42 lr 0.000472	time 2.2119 (2.2447)	loss 3.4704 (3.4933)	grad_norm 1.5033 (1.5441)	
[2022-01-22 14:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][360/1251]	eta 0:33:20 lr 0.000472	time 1.5963 (2.2450)	loss 3.5525 (3.4911)	grad_norm 1.4652 (1.5462)	
[2022-01-22 14:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][370/1251]	eta 0:32:56 lr 0.000472	time 2.2031 (2.2434)	loss 3.8574 (3.4920)	grad_norm 1.4248 (1.5500)	
[2022-01-22 14:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][380/1251]	eta 0:32:33 lr 0.000472	time 2.2457 (2.2424)	loss 3.2353 (3.4921)	grad_norm 1.5087 (1.5491)	
[2022-01-22 14:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][390/1251]	eta 0:32:11 lr 0.000472	time 2.1272 (2.2439)	loss 2.6888 (3.4856)	grad_norm 1.7333 (1.5492)	
[2022-01-22 14:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][400/1251]	eta 0:31:47 lr 0.000472	time 1.5530 (2.2417)	loss 3.9048 (3.4879)	grad_norm 1.6612 (1.5493)	
[2022-01-22 14:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][410/1251]	eta 0:31:23 lr 0.000472	time 1.9074 (2.2394)	loss 4.2042 (3.4959)	grad_norm 1.5648 (1.5515)	
[2022-01-22 14:52:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][420/1251]	eta 0:30:58 lr 0.000472	time 1.6634 (2.2362)	loss 2.9925 (3.4996)	grad_norm 1.2986 (1.5522)	
[2022-01-22 14:52:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][430/1251]	eta 0:30:38 lr 0.000472	time 2.1284 (2.2397)	loss 3.5537 (3.5051)	grad_norm 1.5493 (1.5522)	
[2022-01-22 14:52:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][440/1251]	eta 0:30:14 lr 0.000472	time 1.8785 (2.2369)	loss 3.8435 (3.5114)	grad_norm 1.5793 (1.5515)	
[2022-01-22 14:53:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][450/1251]	eta 0:29:50 lr 0.000472	time 1.5937 (2.2358)	loss 3.8713 (3.5185)	grad_norm 1.4722 (1.5541)	
[2022-01-22 14:53:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][460/1251]	eta 0:29:29 lr 0.000472	time 1.7924 (2.2365)	loss 2.4063 (3.5190)	grad_norm 1.7779 (1.5544)	
[2022-01-22 14:53:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][470/1251]	eta 0:29:04 lr 0.000472	time 1.6480 (2.2339)	loss 3.8352 (3.5169)	grad_norm 1.6145 (1.5555)	
[2022-01-22 14:54:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][480/1251]	eta 0:28:39 lr 0.000472	time 2.0339 (2.2302)	loss 4.3024 (3.5139)	grad_norm 1.5214 (1.5569)	
[2022-01-22 14:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][490/1251]	eta 0:28:17 lr 0.000472	time 2.5899 (2.2300)	loss 2.4441 (3.5113)	grad_norm 1.5921 (1.5569)	
[2022-01-22 14:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][500/1251]	eta 0:27:55 lr 0.000472	time 2.2575 (2.2313)	loss 3.5851 (3.5075)	grad_norm 1.3155 (1.5584)	
[2022-01-22 14:55:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][510/1251]	eta 0:27:36 lr 0.000472	time 1.8329 (2.2349)	loss 3.5467 (3.5044)	grad_norm 1.3643 (1.5580)	
[2022-01-22 14:55:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][520/1251]	eta 0:27:12 lr 0.000472	time 1.8696 (2.2331)	loss 3.5665 (3.5063)	grad_norm 1.6034 (1.5580)	
[2022-01-22 14:56:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][530/1251]	eta 0:26:47 lr 0.000472	time 1.6029 (2.2300)	loss 3.8327 (3.5051)	grad_norm 1.7848 (1.5582)	
[2022-01-22 14:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][540/1251]	eta 0:26:23 lr 0.000472	time 2.3144 (2.2265)	loss 3.4983 (3.5032)	grad_norm 1.5712 (1.5584)	
[2022-01-22 14:56:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][550/1251]	eta 0:25:58 lr 0.000472	time 1.8130 (2.2232)	loss 4.2244 (3.5074)	grad_norm 1.4293 (1.5577)	
[2022-01-22 14:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][560/1251]	eta 0:25:36 lr 0.000472	time 2.9497 (2.2230)	loss 2.3685 (3.5052)	grad_norm 1.6067 (1.5577)	
[2022-01-22 14:57:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][570/1251]	eta 0:25:13 lr 0.000472	time 1.9927 (2.2232)	loss 3.8313 (3.5060)	grad_norm 1.9266 (1.5579)	
[2022-01-22 14:57:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][580/1251]	eta 0:24:51 lr 0.000472	time 2.9466 (2.2228)	loss 4.2537 (3.5093)	grad_norm 1.6905 (1.5574)	
[2022-01-22 14:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][590/1251]	eta 0:24:30 lr 0.000471	time 2.1718 (2.2247)	loss 2.7582 (3.5104)	grad_norm 1.5436 (1.5582)	
[2022-01-22 14:58:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][600/1251]	eta 0:24:06 lr 0.000471	time 1.7826 (2.2227)	loss 3.8049 (3.5117)	grad_norm 1.4548 (1.5585)	
[2022-01-22 14:59:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][610/1251]	eta 0:23:43 lr 0.000471	time 2.3090 (2.2202)	loss 3.8375 (3.5110)	grad_norm 1.5312 (1.5582)	
[2022-01-22 14:59:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][620/1251]	eta 0:23:19 lr 0.000471	time 1.9594 (2.2178)	loss 3.3575 (3.5114)	grad_norm 1.6088 (1.5575)	
[2022-01-22 14:59:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][630/1251]	eta 0:22:56 lr 0.000471	time 2.1137 (2.2160)	loss 3.9267 (3.5120)	grad_norm 1.7670 (1.5574)	
[2022-01-22 15:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][640/1251]	eta 0:22:33 lr 0.000471	time 2.3514 (2.2154)	loss 3.7682 (3.5055)	grad_norm 1.4673 (1.5579)	
[2022-01-22 15:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][650/1251]	eta 0:22:12 lr 0.000471	time 2.6840 (2.2166)	loss 4.3977 (3.5096)	grad_norm 1.6171 (1.5575)	
[2022-01-22 15:00:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][660/1251]	eta 0:21:49 lr 0.000471	time 1.9880 (2.2149)	loss 3.8284 (3.5092)	grad_norm 1.3959 (1.5569)	
[2022-01-22 15:01:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][670/1251]	eta 0:21:27 lr 0.000471	time 2.3205 (2.2154)	loss 3.8093 (3.5106)	grad_norm 1.3333 (1.5574)	
[2022-01-22 15:01:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][680/1251]	eta 0:21:05 lr 0.000471	time 2.4331 (2.2157)	loss 2.7211 (3.5110)	grad_norm 1.5023 (1.5566)	
[2022-01-22 15:01:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][690/1251]	eta 0:20:43 lr 0.000471	time 2.4105 (2.2159)	loss 4.1080 (3.5164)	grad_norm 1.4134 (1.5555)	
[2022-01-22 15:02:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][700/1251]	eta 0:20:21 lr 0.000471	time 1.9299 (2.2161)	loss 3.9292 (3.5169)	grad_norm 1.5094 (1.5548)	
[2022-01-22 15:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][710/1251]	eta 0:19:59 lr 0.000471	time 2.7380 (2.2164)	loss 3.7136 (3.5176)	grad_norm 1.6102 (1.5546)	
[2022-01-22 15:03:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][720/1251]	eta 0:19:35 lr 0.000471	time 1.6281 (2.2143)	loss 3.4178 (3.5172)	grad_norm 1.6706 (1.5552)	
[2022-01-22 15:03:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][730/1251]	eta 0:19:12 lr 0.000471	time 1.8380 (2.2119)	loss 3.9175 (3.5170)	grad_norm 1.7251 (1.5563)	
[2022-01-22 15:03:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][740/1251]	eta 0:18:48 lr 0.000471	time 1.8589 (2.2089)	loss 3.8905 (3.5182)	grad_norm 1.4742 (1.5544)	
[2022-01-22 15:04:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][750/1251]	eta 0:18:26 lr 0.000471	time 2.7313 (2.2088)	loss 3.0639 (3.5200)	grad_norm 1.4008 (1.5539)	
[2022-01-22 15:04:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][760/1251]	eta 0:18:04 lr 0.000471	time 1.7388 (2.2090)	loss 3.4516 (3.5208)	grad_norm 1.3295 (1.5532)	
[2022-01-22 15:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][770/1251]	eta 0:17:42 lr 0.000471	time 1.8454 (2.2093)	loss 2.8538 (3.5153)	grad_norm 1.4530 (1.5533)	
[2022-01-22 15:05:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][780/1251]	eta 0:17:20 lr 0.000471	time 1.5504 (2.2082)	loss 4.1469 (3.5150)	grad_norm 1.6065 (1.5540)	
[2022-01-22 15:05:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][790/1251]	eta 0:16:59 lr 0.000471	time 2.6301 (2.2113)	loss 3.9869 (3.5162)	grad_norm 1.5764 (1.5548)	
[2022-01-22 15:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][800/1251]	eta 0:16:38 lr 0.000471	time 1.9461 (2.2135)	loss 3.7706 (3.5167)	grad_norm 1.3603 (1.5546)	
[2022-01-22 15:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][810/1251]	eta 0:16:16 lr 0.000471	time 1.8893 (2.2139)	loss 3.0954 (3.5166)	grad_norm 1.4851 (1.5538)	
[2022-01-22 15:06:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][820/1251]	eta 0:15:53 lr 0.000471	time 2.1833 (2.2123)	loss 4.1610 (3.5159)	grad_norm 1.7297 (1.5546)	
[2022-01-22 15:06:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][830/1251]	eta 0:15:30 lr 0.000470	time 1.6143 (2.2092)	loss 3.3548 (3.5179)	grad_norm 1.5536 (1.5573)	
[2022-01-22 15:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][840/1251]	eta 0:15:07 lr 0.000470	time 2.1647 (2.2076)	loss 3.4445 (3.5207)	grad_norm 1.4261 (1.5576)	
[2022-01-22 15:07:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][850/1251]	eta 0:14:45 lr 0.000470	time 1.9610 (2.2081)	loss 4.3730 (3.5233)	grad_norm 1.4836 (1.5571)	
[2022-01-22 15:08:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][860/1251]	eta 0:14:23 lr 0.000470	time 2.2713 (2.2083)	loss 2.7908 (3.5244)	grad_norm 1.5472 (1.5566)	
[2022-01-22 15:08:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][870/1251]	eta 0:14:01 lr 0.000470	time 2.1798 (2.2084)	loss 2.8829 (3.5248)	grad_norm 1.5656 (1.5565)	
[2022-01-22 15:08:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][880/1251]	eta 0:13:39 lr 0.000470	time 2.4925 (2.2080)	loss 4.1064 (3.5253)	grad_norm 1.4807 (1.5567)	
[2022-01-22 15:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][890/1251]	eta 0:13:17 lr 0.000470	time 1.8739 (2.2080)	loss 3.7315 (3.5262)	grad_norm 1.8157 (1.5567)	
[2022-01-22 15:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][900/1251]	eta 0:12:54 lr 0.000470	time 1.9154 (2.2080)	loss 3.8890 (3.5271)	grad_norm 1.3473 (1.5558)	
[2022-01-22 15:09:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][910/1251]	eta 0:12:32 lr 0.000470	time 1.8212 (2.2069)	loss 3.9441 (3.5287)	grad_norm 1.5235 (1.5554)	
[2022-01-22 15:10:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][920/1251]	eta 0:12:09 lr 0.000470	time 2.5569 (2.2053)	loss 3.3460 (3.5311)	grad_norm 1.5263 (1.5548)	
[2022-01-22 15:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][930/1251]	eta 0:11:47 lr 0.000470	time 1.9050 (2.2047)	loss 3.9008 (3.5336)	grad_norm 1.5333 (1.5548)	
[2022-01-22 15:10:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][940/1251]	eta 0:11:25 lr 0.000470	time 2.0600 (2.2036)	loss 2.3541 (3.5325)	grad_norm 1.5783 (1.5553)	
[2022-01-22 15:11:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][950/1251]	eta 0:11:03 lr 0.000470	time 1.9682 (2.2047)	loss 3.1599 (3.5313)	grad_norm 1.5265 (1.5551)	
[2022-01-22 15:11:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][960/1251]	eta 0:10:41 lr 0.000470	time 2.5772 (2.2056)	loss 2.7037 (3.5298)	grad_norm 1.3925 (1.5546)	
[2022-01-22 15:12:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][970/1251]	eta 0:10:19 lr 0.000470	time 2.3028 (2.2053)	loss 3.8947 (3.5286)	grad_norm 1.6796 (1.5548)	
[2022-01-22 15:12:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][980/1251]	eta 0:09:57 lr 0.000470	time 1.9646 (2.2057)	loss 3.8383 (3.5261)	grad_norm 1.4337 (1.5546)	
[2022-01-22 15:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][990/1251]	eta 0:09:35 lr 0.000470	time 1.9795 (2.2040)	loss 3.8696 (3.5273)	grad_norm 1.5391 (1.5550)	
[2022-01-22 15:13:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1000/1251]	eta 0:09:12 lr 0.000470	time 2.2287 (2.2029)	loss 4.1495 (3.5273)	grad_norm 1.6358 (1.5545)	
[2022-01-22 15:13:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1010/1251]	eta 0:08:50 lr 0.000470	time 2.7010 (2.2018)	loss 2.7430 (3.5275)	grad_norm 1.3536 (1.5549)	
[2022-01-22 15:13:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1020/1251]	eta 0:08:28 lr 0.000470	time 2.8091 (2.2014)	loss 3.2452 (3.5275)	grad_norm 1.6029 (1.5549)	
[2022-01-22 15:14:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1030/1251]	eta 0:08:06 lr 0.000470	time 1.8970 (2.2010)	loss 3.9546 (3.5275)	grad_norm 1.6571 (1.5544)	
[2022-01-22 15:14:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1040/1251]	eta 0:07:44 lr 0.000470	time 1.5538 (2.2015)	loss 3.6685 (3.5296)	grad_norm 1.4801 (1.5547)	
[2022-01-22 15:14:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1050/1251]	eta 0:07:22 lr 0.000470	time 2.8293 (2.2028)	loss 4.0712 (3.5305)	grad_norm 1.6020 (1.5547)	
[2022-01-22 15:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1060/1251]	eta 0:07:00 lr 0.000470	time 1.8312 (2.2020)	loss 2.7009 (3.5306)	grad_norm 1.5469 (1.5540)	
[2022-01-22 15:15:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1070/1251]	eta 0:06:38 lr 0.000469	time 2.0740 (2.2005)	loss 4.0451 (3.5315)	grad_norm 1.5811 (1.5536)	
[2022-01-22 15:16:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1080/1251]	eta 0:06:16 lr 0.000469	time 2.5308 (2.2013)	loss 4.1795 (3.5292)	grad_norm 1.7287 (1.5528)	
[2022-01-22 15:16:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1090/1251]	eta 0:05:54 lr 0.000469	time 2.6259 (2.2004)	loss 2.7513 (3.5278)	grad_norm 1.5186 (1.5521)	
[2022-01-22 15:16:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1100/1251]	eta 0:05:32 lr 0.000469	time 1.8679 (2.2001)	loss 3.1583 (3.5292)	grad_norm 1.5175 (1.5528)	
[2022-01-22 15:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1110/1251]	eta 0:05:10 lr 0.000469	time 2.4816 (2.1999)	loss 4.1323 (3.5276)	grad_norm 1.5884 (1.5535)	
[2022-01-22 15:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1120/1251]	eta 0:04:48 lr 0.000469	time 1.7956 (2.2004)	loss 3.0034 (3.5228)	grad_norm 1.8954 (1.5533)	
[2022-01-22 15:17:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1130/1251]	eta 0:04:26 lr 0.000469	time 2.8731 (2.2009)	loss 4.4714 (3.5225)	grad_norm 1.6100 (1.5540)	
[2022-01-22 15:18:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1140/1251]	eta 0:04:04 lr 0.000469	time 2.3841 (2.2020)	loss 3.7565 (3.5229)	grad_norm 1.5853 (1.5539)	
[2022-01-22 15:18:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1150/1251]	eta 0:03:42 lr 0.000469	time 1.7723 (2.2018)	loss 2.5800 (3.5240)	grad_norm 1.5418 (1.5539)	
[2022-01-22 15:18:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1160/1251]	eta 0:03:20 lr 0.000469	time 1.8743 (2.2011)	loss 4.3565 (3.5247)	grad_norm 1.5513 (1.5540)	
[2022-01-22 15:19:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1170/1251]	eta 0:02:58 lr 0.000469	time 2.4230 (2.1998)	loss 3.5090 (3.5254)	grad_norm 1.5030 (1.5536)	
[2022-01-22 15:19:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1180/1251]	eta 0:02:36 lr 0.000469	time 1.7917 (2.1988)	loss 3.3345 (3.5254)	grad_norm 1.4450 (1.5535)	
[2022-01-22 15:20:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1190/1251]	eta 0:02:14 lr 0.000469	time 2.1718 (2.1982)	loss 3.8005 (3.5259)	grad_norm 1.5231 (1.5542)	
[2022-01-22 15:20:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1200/1251]	eta 0:01:52 lr 0.000469	time 2.2518 (2.1972)	loss 2.5867 (3.5259)	grad_norm 1.4789 (1.5536)	
[2022-01-22 15:20:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1210/1251]	eta 0:01:30 lr 0.000469	time 2.2968 (2.1959)	loss 3.8352 (3.5257)	grad_norm 1.5168 (1.5541)	
[2022-01-22 15:21:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1220/1251]	eta 0:01:08 lr 0.000469	time 1.8336 (2.1964)	loss 3.9806 (3.5278)	grad_norm 1.6220 (1.5548)	
[2022-01-22 15:21:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1230/1251]	eta 0:00:46 lr 0.000469	time 1.8093 (2.1974)	loss 4.0522 (3.5298)	grad_norm 1.5283 (1.5545)	
[2022-01-22 15:21:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1240/1251]	eta 0:00:24 lr 0.000469	time 1.4278 (2.1971)	loss 3.3619 (3.5301)	grad_norm 1.4179 (1.5542)	
[2022-01-22 15:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [156/300][1250/1251]	eta 0:00:02 lr 0.000469	time 1.3892 (2.1926)	loss 3.1820 (3.5299)	grad_norm 1.5039 (1.5539)	
[2022-01-22 15:22:07 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 156 training takes 0:45:43
[2022-01-22 15:22:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.727 (18.727)	Loss 0.9997 (0.9997)	Acc@1 76.367 (76.367)	Acc@5 94.336 (94.336)	
[2022-01-22 15:22:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.577 (3.505)	Loss 1.0016 (0.9867)	Acc@1 75.977 (76.465)	Acc@5 93.359 (93.688)	
[2022-01-22 15:23:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.273 (2.594)	Loss 0.9397 (0.9910)	Acc@1 77.637 (76.609)	Acc@5 93.750 (93.578)	
[2022-01-22 15:23:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.630 (2.365)	Loss 0.9961 (0.9865)	Acc@1 77.344 (76.742)	Acc@5 93.750 (93.621)	
[2022-01-22 15:23:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.778 (2.175)	Loss 0.9070 (0.9860)	Acc@1 78.125 (76.648)	Acc@5 94.434 (93.571)	
[2022-01-22 15:23:44 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.516 Acc@5 93.514
[2022-01-22 15:23:44 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.5%
[2022-01-22 15:23:44 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.52%
[2022-01-22 15:24:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][0/1251]	eta 8:07:47 lr 0.000469	time 23.3954 (23.3954)	loss 2.3488 (2.3488)	grad_norm 1.5571 (1.5571)	
[2022-01-22 15:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][10/1251]	eta 1:25:04 lr 0.000469	time 1.3494 (4.1131)	loss 3.8283 (3.4575)	grad_norm 1.3287 (1.6275)	
[2022-01-22 15:24:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][20/1251]	eta 1:05:10 lr 0.000469	time 2.3598 (3.1770)	loss 3.9159 (3.5585)	grad_norm 1.5965 (1.5916)	
[2022-01-22 15:25:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][30/1251]	eta 0:58:35 lr 0.000469	time 1.5129 (2.8792)	loss 2.6446 (3.5457)	grad_norm 1.5213 (1.5881)	
[2022-01-22 15:25:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][40/1251]	eta 0:55:29 lr 0.000469	time 3.5271 (2.7497)	loss 3.3343 (3.5595)	grad_norm 1.6181 (1.5829)	
[2022-01-22 15:26:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][50/1251]	eta 0:53:16 lr 0.000469	time 2.8748 (2.6618)	loss 3.6859 (3.5607)	grad_norm 1.4792 (1.5659)	
[2022-01-22 15:26:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][60/1251]	eta 0:51:19 lr 0.000468	time 2.7617 (2.5860)	loss 3.6630 (3.5668)	grad_norm 1.5553 (1.5452)	
[2022-01-22 15:26:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][70/1251]	eta 0:49:42 lr 0.000468	time 1.6311 (2.5251)	loss 2.2930 (3.5478)	grad_norm 1.5598 (1.5556)	
[2022-01-22 15:27:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][80/1251]	eta 0:48:15 lr 0.000468	time 2.2533 (2.4728)	loss 3.8063 (3.5468)	grad_norm 1.6022 (1.5628)	
[2022-01-22 15:27:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][90/1251]	eta 0:46:58 lr 0.000468	time 2.2425 (2.4274)	loss 3.6952 (3.5391)	grad_norm 1.6922 (1.5643)	
[2022-01-22 15:27:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][100/1251]	eta 0:46:04 lr 0.000468	time 2.2830 (2.4016)	loss 3.5568 (3.5018)	grad_norm 1.5786 (1.5739)	
[2022-01-22 15:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][110/1251]	eta 0:45:06 lr 0.000468	time 1.9028 (2.3719)	loss 2.3825 (3.4899)	grad_norm 1.4868 (1.5740)	
[2022-01-22 15:28:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][120/1251]	eta 0:44:30 lr 0.000468	time 2.8759 (2.3613)	loss 2.4463 (3.4843)	grad_norm 2.1178 (1.5786)	
[2022-01-22 15:28:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][130/1251]	eta 0:43:57 lr 0.000468	time 2.9494 (2.3526)	loss 4.0067 (3.4861)	grad_norm 1.4924 (1.5787)	
[2022-01-22 15:29:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][140/1251]	eta 0:43:22 lr 0.000468	time 2.2937 (2.3423)	loss 3.3282 (3.4770)	grad_norm 1.7077 (1.5702)	
[2022-01-22 15:29:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][150/1251]	eta 0:42:50 lr 0.000468	time 1.9208 (2.3344)	loss 2.9999 (3.4806)	grad_norm 1.3859 (1.5692)	
[2022-01-22 15:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][160/1251]	eta 0:42:09 lr 0.000468	time 1.8305 (2.3188)	loss 2.4747 (3.4793)	grad_norm 1.5043 (1.5723)	
[2022-01-22 15:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][170/1251]	eta 0:41:29 lr 0.000468	time 1.8440 (2.3033)	loss 3.5927 (3.4825)	grad_norm 1.5645 (1.5673)	
[2022-01-22 15:30:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][180/1251]	eta 0:41:03 lr 0.000468	time 2.5515 (2.2999)	loss 3.6369 (3.4797)	grad_norm 1.6924 (1.5616)	
[2022-01-22 15:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][190/1251]	eta 0:40:29 lr 0.000468	time 1.8742 (2.2902)	loss 3.2471 (3.4758)	grad_norm 1.4796 (1.5586)	
[2022-01-22 15:31:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][200/1251]	eta 0:40:07 lr 0.000468	time 1.8577 (2.2906)	loss 4.0475 (3.4913)	grad_norm 1.5123 (1.5604)	
[2022-01-22 15:31:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][210/1251]	eta 0:39:45 lr 0.000468	time 2.0499 (2.2917)	loss 3.7496 (3.4974)	grad_norm 1.6861 (1.5618)	
[2022-01-22 15:32:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][220/1251]	eta 0:39:37 lr 0.000468	time 2.0996 (2.3065)	loss 3.6596 (3.5143)	grad_norm 1.4305 (1.5597)	
[2022-01-22 15:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][230/1251]	eta 0:39:06 lr 0.000468	time 2.2129 (2.2985)	loss 4.0891 (3.5090)	grad_norm 1.5216 (1.5612)	
[2022-01-22 15:32:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][240/1251]	eta 0:38:30 lr 0.000468	time 1.7431 (2.2858)	loss 4.1985 (3.5167)	grad_norm 1.5208 (1.5621)	
[2022-01-22 15:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][250/1251]	eta 0:37:54 lr 0.000468	time 1.6650 (2.2722)	loss 4.1713 (3.5230)	grad_norm 1.4196 (1.5601)	
[2022-01-22 15:33:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][260/1251]	eta 0:37:34 lr 0.000468	time 1.9477 (2.2746)	loss 4.2060 (3.5191)	grad_norm 1.5200 (1.5602)	
[2022-01-22 15:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][270/1251]	eta 0:37:11 lr 0.000468	time 1.8969 (2.2748)	loss 2.7928 (3.5166)	grad_norm 1.4863 (1.5642)	
[2022-01-22 15:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][280/1251]	eta 0:36:46 lr 0.000468	time 1.9244 (2.2723)	loss 3.5766 (3.5185)	grad_norm 1.8069 (1.5680)	
[2022-01-22 15:34:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][290/1251]	eta 0:36:16 lr 0.000468	time 1.8181 (2.2652)	loss 4.0290 (3.5193)	grad_norm 1.6021 (1.5677)	
[2022-01-22 15:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][300/1251]	eta 0:35:59 lr 0.000468	time 1.9082 (2.2709)	loss 2.3099 (3.5091)	grad_norm 1.6620 (1.5685)	
[2022-01-22 15:35:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][310/1251]	eta 0:35:28 lr 0.000467	time 1.9511 (2.2620)	loss 3.2395 (3.5114)	grad_norm 1.6385 (1.5680)	
[2022-01-22 15:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][320/1251]	eta 0:35:00 lr 0.000467	time 2.1403 (2.2561)	loss 3.7130 (3.5089)	grad_norm 1.4589 (1.5679)	
[2022-01-22 15:36:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][330/1251]	eta 0:34:35 lr 0.000467	time 2.4673 (2.2536)	loss 3.7243 (3.5079)	grad_norm 1.6393 (1.5684)	
[2022-01-22 15:36:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][340/1251]	eta 0:34:09 lr 0.000467	time 2.1150 (2.2495)	loss 2.4759 (3.5067)	grad_norm 1.6223 (1.5672)	
[2022-01-22 15:36:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][350/1251]	eta 0:33:44 lr 0.000467	time 1.8489 (2.2468)	loss 3.9541 (3.5104)	grad_norm 1.5143 (1.5657)	
[2022-01-22 15:37:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][360/1251]	eta 0:33:24 lr 0.000467	time 2.3006 (2.2502)	loss 2.9613 (3.5123)	grad_norm 1.4146 (1.5654)	
[2022-01-22 15:37:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][370/1251]	eta 0:32:59 lr 0.000467	time 2.3217 (2.2472)	loss 2.9518 (3.5045)	grad_norm 1.7493 (1.5670)	
[2022-01-22 15:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][380/1251]	eta 0:32:33 lr 0.000467	time 2.0328 (2.2429)	loss 3.5956 (3.5059)	grad_norm 1.4196 (1.5648)	
[2022-01-22 15:38:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][390/1251]	eta 0:32:11 lr 0.000467	time 1.9804 (2.2430)	loss 3.0347 (3.5114)	grad_norm 1.5079 (1.5627)	
[2022-01-22 15:38:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][400/1251]	eta 0:31:47 lr 0.000467	time 1.9145 (2.2414)	loss 3.6350 (3.5139)	grad_norm 1.7784 (1.5631)	
[2022-01-22 15:39:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][410/1251]	eta 0:31:23 lr 0.000467	time 2.3554 (2.2399)	loss 3.6098 (3.5088)	grad_norm 1.5416 (1.5599)	
[2022-01-22 15:39:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][420/1251]	eta 0:30:58 lr 0.000467	time 2.1959 (2.2361)	loss 3.7429 (3.5155)	grad_norm 1.4180 (1.5595)	
[2022-01-22 15:39:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][430/1251]	eta 0:30:33 lr 0.000467	time 2.2639 (2.2326)	loss 3.6787 (3.5131)	grad_norm 1.6182 (1.5594)	
[2022-01-22 15:40:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][440/1251]	eta 0:30:08 lr 0.000467	time 1.8142 (2.2294)	loss 2.3151 (3.5053)	grad_norm 1.4850 (1.5580)	
[2022-01-22 15:40:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][450/1251]	eta 0:29:45 lr 0.000467	time 2.4886 (2.2296)	loss 2.8302 (3.4985)	grad_norm 1.4132 (1.5566)	
[2022-01-22 15:40:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][460/1251]	eta 0:29:22 lr 0.000467	time 1.8140 (2.2288)	loss 3.6660 (3.5041)	grad_norm 1.7632 (1.5572)	
[2022-01-22 15:41:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][470/1251]	eta 0:29:01 lr 0.000467	time 2.3485 (2.2298)	loss 3.6340 (3.5061)	grad_norm 1.4091 (1.5568)	
[2022-01-22 15:41:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][480/1251]	eta 0:28:39 lr 0.000467	time 1.9268 (2.2298)	loss 3.9448 (3.5051)	grad_norm 1.4629 (1.5556)	
[2022-01-22 15:41:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][490/1251]	eta 0:28:17 lr 0.000467	time 2.8883 (2.2309)	loss 4.2670 (3.5063)	grad_norm 1.5482 (1.5537)	
[2022-01-22 15:42:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][500/1251]	eta 0:27:54 lr 0.000467	time 1.6534 (2.2294)	loss 3.7209 (3.5062)	grad_norm 1.4904 (1.5538)	
[2022-01-22 15:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][510/1251]	eta 0:27:33 lr 0.000467	time 3.6540 (2.2314)	loss 3.7601 (3.5031)	grad_norm 1.6332 (1.5537)	
[2022-01-22 15:43:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][520/1251]	eta 0:27:07 lr 0.000467	time 1.8153 (2.2263)	loss 3.5722 (3.5040)	grad_norm 1.5517 (1.5533)	
[2022-01-22 15:43:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][530/1251]	eta 0:26:44 lr 0.000467	time 2.5563 (2.2257)	loss 3.8004 (3.5002)	grad_norm 1.4615 (1.5532)	
[2022-01-22 15:43:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][540/1251]	eta 0:26:20 lr 0.000467	time 2.2136 (2.2227)	loss 3.2780 (3.4984)	grad_norm 1.4541 (1.5545)	
[2022-01-22 15:44:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][550/1251]	eta 0:25:57 lr 0.000466	time 2.4500 (2.2223)	loss 3.5725 (3.5008)	grad_norm 1.4204 (1.5548)	
[2022-01-22 15:44:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][560/1251]	eta 0:25:35 lr 0.000466	time 2.1911 (2.2215)	loss 4.5096 (3.5024)	grad_norm 1.4701 (1.5561)	
[2022-01-22 15:44:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][570/1251]	eta 0:25:13 lr 0.000466	time 2.9050 (2.2226)	loss 3.8544 (3.5040)	grad_norm 1.5490 (1.5561)	
[2022-01-22 15:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][580/1251]	eta 0:24:49 lr 0.000466	time 2.4689 (2.2202)	loss 3.2647 (3.5024)	grad_norm 1.6910 (1.5566)	
[2022-01-22 15:45:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][590/1251]	eta 0:24:29 lr 0.000466	time 2.5054 (2.2225)	loss 3.4538 (3.5025)	grad_norm 1.4933 (1.5580)	
[2022-01-22 15:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][600/1251]	eta 0:24:07 lr 0.000466	time 2.1845 (2.2240)	loss 3.7925 (3.5037)	grad_norm 1.3761 (1.5581)	
[2022-01-22 15:46:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][610/1251]	eta 0:23:47 lr 0.000466	time 2.3475 (2.2276)	loss 4.1846 (3.5049)	grad_norm 1.4644 (1.5576)	
[2022-01-22 15:46:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][620/1251]	eta 0:23:25 lr 0.000466	time 2.9489 (2.2278)	loss 4.1499 (3.5043)	grad_norm 1.5010 (1.5577)	
[2022-01-22 15:47:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][630/1251]	eta 0:23:01 lr 0.000466	time 1.8565 (2.2240)	loss 3.2447 (3.5086)	grad_norm 2.0593 (1.5574)	
[2022-01-22 15:47:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][640/1251]	eta 0:22:36 lr 0.000466	time 2.0310 (2.2196)	loss 3.6815 (3.5061)	grad_norm 1.3629 (1.5573)	
[2022-01-22 15:47:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][650/1251]	eta 0:22:12 lr 0.000466	time 1.9131 (2.2172)	loss 4.0650 (3.5052)	grad_norm 1.8100 (1.5574)	
[2022-01-22 15:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][660/1251]	eta 0:21:47 lr 0.000466	time 1.6010 (2.2131)	loss 3.3966 (3.5074)	grad_norm 1.4311 (1.5587)	
[2022-01-22 15:48:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][670/1251]	eta 0:21:25 lr 0.000466	time 2.4307 (2.2130)	loss 2.7935 (3.5071)	grad_norm 1.5388 (1.5587)	
[2022-01-22 15:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][680/1251]	eta 0:21:05 lr 0.000466	time 2.2466 (2.2162)	loss 3.5796 (3.5079)	grad_norm 1.4082 (1.5609)	
[2022-01-22 15:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][690/1251]	eta 0:20:44 lr 0.000466	time 2.4772 (2.2183)	loss 4.3077 (3.5125)	grad_norm 1.5830 (1.5604)	
[2022-01-22 15:49:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][700/1251]	eta 0:20:21 lr 0.000466	time 1.8983 (2.2160)	loss 3.5918 (3.5120)	grad_norm 1.5064 (1.5593)	
[2022-01-22 15:49:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][710/1251]	eta 0:19:58 lr 0.000466	time 1.9124 (2.2156)	loss 4.3912 (3.5077)	grad_norm 1.5095 (1.5587)	
[2022-01-22 15:50:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][720/1251]	eta 0:19:36 lr 0.000466	time 2.4075 (2.2151)	loss 4.0512 (3.5109)	grad_norm 1.4880 (1.5578)	
[2022-01-22 15:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][730/1251]	eta 0:19:13 lr 0.000466	time 1.8986 (2.2149)	loss 2.7413 (3.5095)	grad_norm 1.5177 (1.5589)	
[2022-01-22 15:51:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][740/1251]	eta 0:18:51 lr 0.000466	time 2.0690 (2.2147)	loss 3.4078 (3.5098)	grad_norm 1.5237 (1.5586)	
[2022-01-22 15:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][750/1251]	eta 0:18:29 lr 0.000466	time 1.8528 (2.2144)	loss 3.8974 (3.5102)	grad_norm 1.5900 (1.5595)	
[2022-01-22 15:51:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][760/1251]	eta 0:18:07 lr 0.000466	time 2.2222 (2.2146)	loss 2.8132 (3.5105)	grad_norm 1.7577 (1.5602)	
[2022-01-22 15:52:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][770/1251]	eta 0:17:45 lr 0.000466	time 2.1913 (2.2155)	loss 4.1221 (3.5126)	grad_norm 1.6310 (1.5611)	
[2022-01-22 15:52:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][780/1251]	eta 0:17:22 lr 0.000466	time 1.6095 (2.2134)	loss 3.1760 (3.5140)	grad_norm 1.4116 (1.5622)	
[2022-01-22 15:52:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][790/1251]	eta 0:17:00 lr 0.000465	time 2.0829 (2.2142)	loss 2.3707 (3.5067)	grad_norm 1.7096 (1.5630)	
[2022-01-22 15:53:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][800/1251]	eta 0:16:38 lr 0.000465	time 2.1832 (2.2129)	loss 2.4851 (3.5044)	grad_norm 1.3273 (1.5630)	
[2022-01-22 15:53:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][810/1251]	eta 0:16:15 lr 0.000465	time 2.1129 (2.2111)	loss 3.7956 (3.5052)	grad_norm 1.6139 (1.5636)	
[2022-01-22 15:53:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][820/1251]	eta 0:15:51 lr 0.000465	time 1.6831 (2.2085)	loss 3.9945 (3.5080)	grad_norm 1.7483 (1.5640)	
[2022-01-22 15:54:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][830/1251]	eta 0:15:29 lr 0.000465	time 2.5405 (2.2074)	loss 3.3651 (3.5071)	grad_norm 1.5641 (1.5639)	
[2022-01-22 15:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][840/1251]	eta 0:15:06 lr 0.000465	time 2.2206 (2.2064)	loss 2.6710 (3.5060)	grad_norm 1.5381 (1.5647)	
[2022-01-22 15:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][850/1251]	eta 0:14:44 lr 0.000465	time 2.4966 (2.2064)	loss 3.8643 (3.5095)	grad_norm 1.3896 (1.5654)	
[2022-01-22 15:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][860/1251]	eta 0:14:22 lr 0.000465	time 1.9390 (2.2056)	loss 3.1513 (3.5099)	grad_norm 1.5631 (1.5652)	
[2022-01-22 15:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][870/1251]	eta 0:14:00 lr 0.000465	time 2.3458 (2.2048)	loss 3.7270 (3.5099)	grad_norm 1.3941 (1.5649)	
[2022-01-22 15:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][880/1251]	eta 0:13:38 lr 0.000465	time 2.3821 (2.2052)	loss 3.6430 (3.5124)	grad_norm 1.4219 (1.5648)	
[2022-01-22 15:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][890/1251]	eta 0:13:16 lr 0.000465	time 2.2183 (2.2057)	loss 4.1806 (3.5122)	grad_norm 1.5264 (1.5646)	
[2022-01-22 15:56:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][900/1251]	eta 0:12:55 lr 0.000465	time 1.5398 (2.2093)	loss 3.8185 (3.5144)	grad_norm 1.4018 (1.5651)	
[2022-01-22 15:57:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][910/1251]	eta 0:12:34 lr 0.000465	time 3.6572 (2.2120)	loss 3.2171 (3.5151)	grad_norm 1.4531 (1.5636)	
[2022-01-22 15:57:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][920/1251]	eta 0:12:12 lr 0.000465	time 1.8880 (2.2122)	loss 3.1562 (3.5150)	grad_norm 1.2337 (1.5632)	
[2022-01-22 15:58:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][930/1251]	eta 0:11:49 lr 0.000465	time 1.8662 (2.2105)	loss 2.6309 (3.5119)	grad_norm 1.3833 (1.5623)	
[2022-01-22 15:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][940/1251]	eta 0:11:26 lr 0.000465	time 1.8281 (2.2087)	loss 3.7361 (3.5116)	grad_norm 1.6701 (1.5620)	
[2022-01-22 15:58:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][950/1251]	eta 0:11:04 lr 0.000465	time 3.1305 (2.2079)	loss 3.7190 (3.5113)	grad_norm 1.4958 (1.5623)	
[2022-01-22 15:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][960/1251]	eta 0:10:41 lr 0.000465	time 1.6559 (2.2060)	loss 2.9128 (3.5113)	grad_norm 1.3503 (1.5621)	
[2022-01-22 15:59:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][970/1251]	eta 0:10:19 lr 0.000465	time 2.0200 (2.2061)	loss 2.7127 (3.5076)	grad_norm 1.3345 (1.5613)	
[2022-01-22 15:59:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][980/1251]	eta 0:09:57 lr 0.000465	time 2.0271 (2.2062)	loss 4.2909 (3.5076)	grad_norm 1.3704 (1.5607)	
[2022-01-22 16:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][990/1251]	eta 0:09:35 lr 0.000465	time 2.2172 (2.2056)	loss 3.2807 (3.5055)	grad_norm 1.4949 (1.5609)	
[2022-01-22 16:00:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1000/1251]	eta 0:09:13 lr 0.000465	time 2.2080 (2.2042)	loss 3.9091 (3.5076)	grad_norm 1.3958 (1.5607)	
[2022-01-22 16:00:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1010/1251]	eta 0:08:51 lr 0.000465	time 2.1186 (2.2038)	loss 3.7057 (3.5070)	grad_norm 1.4097 (1.5609)	
[2022-01-22 16:01:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1020/1251]	eta 0:08:28 lr 0.000465	time 1.8576 (2.2020)	loss 4.4485 (3.5082)	grad_norm 1.4296 (1.5603)	
[2022-01-22 16:01:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1030/1251]	eta 0:08:06 lr 0.000464	time 2.2112 (2.2015)	loss 3.7617 (3.5059)	grad_norm 1.6516 (1.5605)	
[2022-01-22 16:01:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1040/1251]	eta 0:07:44 lr 0.000464	time 3.2464 (2.2028)	loss 4.1823 (3.5057)	grad_norm 1.5136 (1.5602)	
[2022-01-22 16:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1050/1251]	eta 0:07:22 lr 0.000464	time 2.3323 (2.2035)	loss 3.5881 (3.5068)	grad_norm 1.6845 (1.5601)	
[2022-01-22 16:02:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1060/1251]	eta 0:07:01 lr 0.000464	time 2.0106 (2.2042)	loss 3.7987 (3.5057)	grad_norm 1.5070 (1.5597)	
[2022-01-22 16:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1070/1251]	eta 0:06:39 lr 0.000464	time 2.5377 (2.2046)	loss 3.9872 (3.5058)	grad_norm 1.4744 (1.5596)	
[2022-01-22 16:03:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1080/1251]	eta 0:06:16 lr 0.000464	time 2.5999 (2.2046)	loss 3.2747 (3.5038)	grad_norm 1.4842 (1.5594)	
[2022-01-22 16:03:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1090/1251]	eta 0:05:54 lr 0.000464	time 1.8680 (2.2040)	loss 3.7317 (3.5031)	grad_norm 1.6299 (1.5596)	
[2022-01-22 16:04:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1100/1251]	eta 0:05:32 lr 0.000464	time 1.7710 (2.2027)	loss 4.1049 (3.5031)	grad_norm 1.6938 (1.5599)	
[2022-01-22 16:04:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1110/1251]	eta 0:05:10 lr 0.000464	time 2.2969 (2.2020)	loss 3.9456 (3.5003)	grad_norm 1.6029 (1.5595)	
[2022-01-22 16:04:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1120/1251]	eta 0:04:48 lr 0.000464	time 3.1931 (2.2020)	loss 3.5111 (3.5000)	grad_norm 1.4363 (1.5592)	
[2022-01-22 16:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1130/1251]	eta 0:04:26 lr 0.000464	time 1.9006 (2.2024)	loss 3.9579 (3.5013)	grad_norm 1.4481 (1.5586)	
[2022-01-22 16:05:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1140/1251]	eta 0:04:04 lr 0.000464	time 1.9231 (2.2033)	loss 3.3086 (3.5039)	grad_norm 1.3765 (1.5588)	
[2022-01-22 16:05:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1150/1251]	eta 0:03:42 lr 0.000464	time 1.7659 (2.2026)	loss 2.8956 (3.5040)	grad_norm 1.3605 (1.5587)	
[2022-01-22 16:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1160/1251]	eta 0:03:20 lr 0.000464	time 2.8450 (2.2012)	loss 3.8895 (3.5036)	grad_norm 1.5734 (1.5587)	
[2022-01-22 16:06:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1170/1251]	eta 0:02:58 lr 0.000464	time 2.1554 (2.1992)	loss 3.7133 (3.5029)	grad_norm 1.3844 (1.5585)	
[2022-01-22 16:06:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1180/1251]	eta 0:02:36 lr 0.000464	time 2.3939 (2.1976)	loss 3.2271 (3.5033)	grad_norm 1.4471 (1.5580)	
[2022-01-22 16:07:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1190/1251]	eta 0:02:14 lr 0.000464	time 2.0965 (2.1972)	loss 3.6895 (3.5023)	grad_norm 1.4726 (1.5577)	
[2022-01-22 16:07:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1200/1251]	eta 0:01:52 lr 0.000464	time 2.7581 (2.1971)	loss 3.4323 (3.5017)	grad_norm 1.3885 (1.5574)	
[2022-01-22 16:08:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1210/1251]	eta 0:01:30 lr 0.000464	time 1.8854 (2.1978)	loss 4.1112 (3.5033)	grad_norm 1.6561 (1.5567)	
[2022-01-22 16:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1220/1251]	eta 0:01:08 lr 0.000464	time 2.2145 (2.1983)	loss 3.9045 (3.5043)	grad_norm 1.5097 (1.5560)	
[2022-01-22 16:08:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1230/1251]	eta 0:00:46 lr 0.000464	time 2.3771 (2.1979)	loss 3.6732 (3.5029)	grad_norm 1.6064 (1.5557)	
[2022-01-22 16:09:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1240/1251]	eta 0:00:24 lr 0.000464	time 1.4784 (2.1968)	loss 2.9311 (3.5016)	grad_norm 1.5669 (1.5556)	
[2022-01-22 16:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [157/300][1250/1251]	eta 0:00:02 lr 0.000464	time 1.1798 (2.1918)	loss 3.1203 (3.5009)	grad_norm 1.4110 (1.5554)	
[2022-01-22 16:09:26 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 157 training takes 0:45:42
[2022-01-22 16:09:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.579 (18.579)	Loss 1.0036 (1.0036)	Acc@1 75.293 (75.293)	Acc@5 93.457 (93.457)	
[2022-01-22 16:10:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.642 (3.487)	Loss 0.9187 (0.9846)	Acc@1 78.711 (76.820)	Acc@5 94.141 (93.652)	
[2022-01-22 16:10:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.622 (2.591)	Loss 0.9403 (0.9916)	Acc@1 77.832 (76.823)	Acc@5 93.652 (93.411)	
[2022-01-22 16:10:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.602 (2.285)	Loss 0.9345 (0.9994)	Acc@1 76.758 (76.459)	Acc@5 94.434 (93.400)	
[2022-01-22 16:10:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.096 (2.162)	Loss 1.0205 (0.9964)	Acc@1 75.586 (76.348)	Acc@5 93.555 (93.481)	
[2022-01-22 16:11:02 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.392 Acc@5 93.510
[2022-01-22 16:11:02 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.4%
[2022-01-22 16:11:02 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.52%
[2022-01-22 16:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][0/1251]	eta 7:20:07 lr 0.000464	time 21.1091 (21.1091)	loss 2.6215 (2.6215)	grad_norm 1.4429 (1.4429)	
[2022-01-22 16:11:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][10/1251]	eta 1:23:12 lr 0.000464	time 1.8262 (4.0226)	loss 3.6053 (3.4581)	grad_norm 1.3819 (1.5263)	
[2022-01-22 16:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][20/1251]	eta 1:04:56 lr 0.000463	time 1.4635 (3.1655)	loss 2.6477 (3.3797)	grad_norm 1.4445 (1.5696)	
[2022-01-22 16:12:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][30/1251]	eta 0:58:11 lr 0.000463	time 1.4733 (2.8596)	loss 3.4976 (3.4533)	grad_norm 1.5420 (1.5684)	
[2022-01-22 16:12:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][40/1251]	eta 0:55:44 lr 0.000463	time 4.7301 (2.7614)	loss 3.7480 (3.4783)	grad_norm 1.5699 (1.5751)	
[2022-01-22 16:13:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][50/1251]	eta 0:52:56 lr 0.000463	time 1.5924 (2.6451)	loss 3.7330 (3.4753)	grad_norm 1.6257 (1.5871)	
[2022-01-22 16:13:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][60/1251]	eta 0:51:03 lr 0.000463	time 1.5792 (2.5718)	loss 3.6339 (3.5027)	grad_norm 1.5550 (1.5799)	
[2022-01-22 16:14:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][70/1251]	eta 0:49:24 lr 0.000463	time 1.8945 (2.5098)	loss 3.7116 (3.5228)	grad_norm 1.7071 (1.5772)	
[2022-01-22 16:14:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][80/1251]	eta 0:48:33 lr 0.000463	time 3.5605 (2.4876)	loss 4.2316 (3.5391)	grad_norm 1.7049 (1.5755)	
[2022-01-22 16:14:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][90/1251]	eta 0:47:23 lr 0.000463	time 1.7295 (2.4490)	loss 3.0003 (3.5328)	grad_norm 1.5817 (1.5831)	
[2022-01-22 16:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][100/1251]	eta 0:46:10 lr 0.000463	time 1.9280 (2.4072)	loss 4.0760 (3.5576)	grad_norm 1.5647 (1.5814)	
[2022-01-22 16:15:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][110/1251]	eta 0:45:34 lr 0.000463	time 2.6498 (2.3964)	loss 3.8031 (3.5565)	grad_norm 1.5255 (1.5709)	
[2022-01-22 16:15:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][120/1251]	eta 0:45:18 lr 0.000463	time 3.4186 (2.4035)	loss 2.7319 (3.5405)	grad_norm 1.8851 (1.5712)	
[2022-01-22 16:16:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][130/1251]	eta 0:44:34 lr 0.000463	time 1.9116 (2.3858)	loss 2.6715 (3.5322)	grad_norm 1.6541 (1.5709)	
[2022-01-22 16:16:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][140/1251]	eta 0:43:51 lr 0.000463	time 1.8318 (2.3689)	loss 3.4345 (3.5334)	grad_norm 1.7312 (1.5693)	
[2022-01-22 16:16:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][150/1251]	eta 0:42:59 lr 0.000463	time 1.7807 (2.3431)	loss 4.1632 (3.5412)	grad_norm 1.4525 (1.5629)	
[2022-01-22 16:17:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][160/1251]	eta 0:42:12 lr 0.000463	time 2.2368 (2.3214)	loss 3.8620 (3.5518)	grad_norm 1.4606 (1.5651)	
[2022-01-22 16:17:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][170/1251]	eta 0:41:37 lr 0.000463	time 2.0644 (2.3106)	loss 4.1370 (3.5497)	grad_norm 1.7863 (1.5658)	
[2022-01-22 16:18:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][180/1251]	eta 0:41:11 lr 0.000463	time 2.2541 (2.3079)	loss 3.8454 (3.5323)	grad_norm 1.4327 (1.5650)	
[2022-01-22 16:18:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][190/1251]	eta 0:40:45 lr 0.000463	time 2.4201 (2.3047)	loss 3.9891 (3.5448)	grad_norm 1.6140 (1.5690)	
[2022-01-22 16:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][200/1251]	eta 0:40:21 lr 0.000463	time 2.7680 (2.3042)	loss 3.3856 (3.5331)	grad_norm 1.5703 (1.5651)	
[2022-01-22 16:19:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][210/1251]	eta 0:39:50 lr 0.000463	time 1.6797 (2.2965)	loss 4.1743 (3.5444)	grad_norm 1.4959 (1.5670)	
[2022-01-22 16:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][220/1251]	eta 0:39:25 lr 0.000463	time 2.1835 (2.2944)	loss 2.7617 (3.5337)	grad_norm 1.6149 (1.5694)	
[2022-01-22 16:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][230/1251]	eta 0:38:54 lr 0.000463	time 1.6367 (2.2861)	loss 4.2494 (3.5249)	grad_norm 1.7607 (1.5742)	
[2022-01-22 16:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][240/1251]	eta 0:38:27 lr 0.000463	time 2.4566 (2.2825)	loss 4.1750 (3.5179)	grad_norm 1.7877 (1.5737)	
[2022-01-22 16:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][250/1251]	eta 0:37:57 lr 0.000463	time 1.5662 (2.2756)	loss 3.1334 (3.5197)	grad_norm 1.3293 (1.5702)	
[2022-01-22 16:20:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][260/1251]	eta 0:37:30 lr 0.000463	time 1.7306 (2.2710)	loss 3.4439 (3.5177)	grad_norm 1.5775 (1.5744)	
[2022-01-22 16:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][270/1251]	eta 0:37:03 lr 0.000462	time 2.1037 (2.2663)	loss 3.8684 (3.5140)	grad_norm 1.4687 (1.5731)	
[2022-01-22 16:21:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][280/1251]	eta 0:36:39 lr 0.000462	time 2.4737 (2.2653)	loss 2.9085 (3.5079)	grad_norm 1.4356 (1.5733)	
[2022-01-22 16:22:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][290/1251]	eta 0:36:18 lr 0.000462	time 2.4294 (2.2666)	loss 3.7106 (3.5024)	grad_norm 1.6908 (1.5751)	
[2022-01-22 16:22:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][300/1251]	eta 0:35:51 lr 0.000462	time 1.6736 (2.2626)	loss 3.9603 (3.4931)	grad_norm 1.3147 (1.5743)	
[2022-01-22 16:22:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][310/1251]	eta 0:35:27 lr 0.000462	time 1.7603 (2.2604)	loss 3.1728 (3.4937)	grad_norm 1.3369 (1.5710)	
[2022-01-22 16:23:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][320/1251]	eta 0:35:04 lr 0.000462	time 2.7272 (2.2604)	loss 3.4067 (3.4883)	grad_norm 1.4265 (1.5708)	
[2022-01-22 16:23:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][330/1251]	eta 0:34:42 lr 0.000462	time 2.5287 (2.2606)	loss 4.0862 (3.4928)	grad_norm 1.5732 (1.5686)	
[2022-01-22 16:23:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][340/1251]	eta 0:34:16 lr 0.000462	time 2.4987 (2.2572)	loss 3.2780 (3.4962)	grad_norm 1.4316 (1.5669)	
[2022-01-22 16:24:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][350/1251]	eta 0:33:48 lr 0.000462	time 1.6770 (2.2517)	loss 4.1433 (3.5017)	grad_norm 1.5704 (1.5665)	
[2022-01-22 16:24:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][360/1251]	eta 0:33:21 lr 0.000462	time 1.8587 (2.2468)	loss 3.2201 (3.5031)	grad_norm 1.3964 (1.5658)	
[2022-01-22 16:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][370/1251]	eta 0:32:57 lr 0.000462	time 1.9404 (2.2446)	loss 3.9226 (3.5009)	grad_norm 1.6400 (1.5674)	
[2022-01-22 16:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][380/1251]	eta 0:32:32 lr 0.000462	time 2.1936 (2.2420)	loss 2.6109 (3.4909)	grad_norm 1.3387 (1.5669)	
[2022-01-22 16:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][390/1251]	eta 0:32:08 lr 0.000462	time 2.1925 (2.2399)	loss 3.1936 (3.4960)	grad_norm 1.4498 (1.5682)	
[2022-01-22 16:26:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][400/1251]	eta 0:31:46 lr 0.000462	time 2.2596 (2.2409)	loss 3.2609 (3.4978)	grad_norm 1.6294 (1.5672)	
[2022-01-22 16:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][410/1251]	eta 0:31:24 lr 0.000462	time 2.2611 (2.2403)	loss 3.7730 (3.4942)	grad_norm 1.5987 (1.5655)	
[2022-01-22 16:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][420/1251]	eta 0:30:59 lr 0.000462	time 2.3200 (2.2381)	loss 2.9668 (3.4899)	grad_norm 1.2771 (1.5627)	
[2022-01-22 16:27:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][430/1251]	eta 0:30:32 lr 0.000462	time 1.7622 (2.2322)	loss 3.5802 (3.4883)	grad_norm 1.5131 (1.5614)	
[2022-01-22 16:27:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][440/1251]	eta 0:30:08 lr 0.000462	time 2.3644 (2.2298)	loss 2.9792 (3.4880)	grad_norm 1.9055 (1.5625)	
[2022-01-22 16:27:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][450/1251]	eta 0:29:44 lr 0.000462	time 2.2496 (2.2274)	loss 4.1404 (3.4847)	grad_norm 1.3895 (1.5616)	
[2022-01-22 16:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][460/1251]	eta 0:29:19 lr 0.000462	time 1.9274 (2.2243)	loss 3.6570 (3.4885)	grad_norm 1.6416 (1.5615)	
[2022-01-22 16:28:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][470/1251]	eta 0:28:58 lr 0.000462	time 2.4488 (2.2263)	loss 3.8894 (3.4894)	grad_norm 1.6811 (1.5625)	
[2022-01-22 16:28:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][480/1251]	eta 0:28:38 lr 0.000462	time 2.8327 (2.2287)	loss 3.5423 (3.4964)	grad_norm 1.4722 (1.5605)	
[2022-01-22 16:29:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][490/1251]	eta 0:28:16 lr 0.000462	time 2.3589 (2.2290)	loss 3.6124 (3.4987)	grad_norm 1.5176 (1.5591)	
[2022-01-22 16:29:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][500/1251]	eta 0:27:54 lr 0.000462	time 2.3315 (2.2296)	loss 3.4718 (3.5005)	grad_norm 1.3444 (1.5589)	
[2022-01-22 16:30:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][510/1251]	eta 0:27:31 lr 0.000461	time 2.2126 (2.2292)	loss 3.3070 (3.4999)	grad_norm 1.5400 (1.5588)	
[2022-01-22 16:30:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][520/1251]	eta 0:27:08 lr 0.000461	time 2.2393 (2.2278)	loss 2.4303 (3.4977)	grad_norm 1.4172 (1.5585)	
[2022-01-22 16:30:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][530/1251]	eta 0:26:46 lr 0.000461	time 2.1296 (2.2275)	loss 3.3463 (3.5000)	grad_norm 1.3716 (1.5591)	
[2022-01-22 16:31:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][540/1251]	eta 0:26:23 lr 0.000461	time 1.6177 (2.2265)	loss 3.0652 (3.4994)	grad_norm 1.3917 (1.5592)	
[2022-01-22 16:31:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][550/1251]	eta 0:25:58 lr 0.000461	time 1.8881 (2.2232)	loss 3.8433 (3.5041)	grad_norm 1.4386 (1.5572)	
[2022-01-22 16:31:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][560/1251]	eta 0:25:34 lr 0.000461	time 1.9259 (2.2210)	loss 2.6929 (3.5033)	grad_norm 1.5991 (1.5567)	
[2022-01-22 16:32:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][570/1251]	eta 0:25:11 lr 0.000461	time 1.8614 (2.2200)	loss 3.3441 (3.5044)	grad_norm 1.4712 (1.5564)	
[2022-01-22 16:32:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][580/1251]	eta 0:24:51 lr 0.000461	time 2.1828 (2.2226)	loss 3.1799 (3.5073)	grad_norm 1.4206 (1.5568)	
[2022-01-22 16:32:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][590/1251]	eta 0:24:29 lr 0.000461	time 2.7844 (2.2234)	loss 3.8518 (3.5114)	grad_norm 1.5137 (1.5568)	
[2022-01-22 16:33:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][600/1251]	eta 0:24:07 lr 0.000461	time 2.3930 (2.2233)	loss 3.9825 (3.5154)	grad_norm 1.3567 (1.5577)	
[2022-01-22 16:33:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][610/1251]	eta 0:23:43 lr 0.000461	time 1.6094 (2.2200)	loss 3.2406 (3.5175)	grad_norm 1.4719 (1.5588)	
[2022-01-22 16:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][620/1251]	eta 0:23:19 lr 0.000461	time 1.8952 (2.2172)	loss 3.3230 (3.5181)	grad_norm 1.6069 (1.5591)	
[2022-01-22 16:34:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][630/1251]	eta 0:22:54 lr 0.000461	time 1.9788 (2.2139)	loss 3.5240 (3.5195)	grad_norm 1.6712 (1.5589)	
[2022-01-22 16:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][640/1251]	eta 0:22:31 lr 0.000461	time 2.1399 (2.2126)	loss 3.4227 (3.5232)	grad_norm 1.4036 (1.5578)	
[2022-01-22 16:35:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][650/1251]	eta 0:22:09 lr 0.000461	time 1.8781 (2.2118)	loss 4.0195 (3.5277)	grad_norm 1.4368 (1.5570)	
[2022-01-22 16:35:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][660/1251]	eta 0:21:47 lr 0.000461	time 2.8481 (2.2122)	loss 2.4992 (3.5277)	grad_norm 1.5431 (1.5570)	
[2022-01-22 16:35:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][670/1251]	eta 0:21:26 lr 0.000461	time 2.9241 (2.2136)	loss 4.0358 (3.5277)	grad_norm 1.4191 (1.5574)	
[2022-01-22 16:36:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][680/1251]	eta 0:21:04 lr 0.000461	time 2.7552 (2.2149)	loss 3.0613 (3.5252)	grad_norm 1.5517 (1.5573)	
[2022-01-22 16:36:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][690/1251]	eta 0:20:41 lr 0.000461	time 2.1883 (2.2126)	loss 3.3604 (3.5265)	grad_norm 1.5968 (1.5573)	
[2022-01-22 16:36:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][700/1251]	eta 0:20:19 lr 0.000461	time 2.2727 (2.2138)	loss 2.9951 (3.5261)	grad_norm 1.6394 (1.5572)	
[2022-01-22 16:37:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][710/1251]	eta 0:19:59 lr 0.000461	time 2.0295 (2.2171)	loss 2.7797 (3.5245)	grad_norm 1.6284 (1.5570)	
[2022-01-22 16:37:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][720/1251]	eta 0:19:37 lr 0.000461	time 1.8724 (2.2169)	loss 3.6621 (3.5227)	grad_norm 2.2757 (1.5590)	
[2022-01-22 16:38:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][730/1251]	eta 0:19:14 lr 0.000461	time 2.5790 (2.2158)	loss 2.9938 (3.5222)	grad_norm 1.7040 (1.5597)	
[2022-01-22 16:38:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][740/1251]	eta 0:18:50 lr 0.000461	time 1.8651 (2.2126)	loss 2.9643 (3.5208)	grad_norm 1.3687 (1.5591)	
[2022-01-22 16:38:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][750/1251]	eta 0:18:27 lr 0.000460	time 2.5409 (2.2116)	loss 3.0198 (3.5167)	grad_norm 1.4846 (1.5599)	
[2022-01-22 16:39:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][760/1251]	eta 0:18:04 lr 0.000460	time 2.1757 (2.2091)	loss 3.2375 (3.5173)	grad_norm 1.5688 (1.5602)	
[2022-01-22 16:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][770/1251]	eta 0:17:41 lr 0.000460	time 2.0857 (2.2072)	loss 3.4357 (3.5174)	grad_norm 1.4577 (1.5614)	
[2022-01-22 16:39:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][780/1251]	eta 0:17:19 lr 0.000460	time 2.1692 (2.2071)	loss 4.2435 (3.5203)	grad_norm 1.6878 (1.5629)	
[2022-01-22 16:40:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][790/1251]	eta 0:16:56 lr 0.000460	time 2.2061 (2.2060)	loss 3.4944 (3.5218)	grad_norm 1.3867 (1.5637)	
[2022-01-22 16:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][800/1251]	eta 0:16:35 lr 0.000460	time 2.5158 (2.2075)	loss 2.3218 (3.5207)	grad_norm 1.5102 (1.5644)	
[2022-01-22 16:40:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][810/1251]	eta 0:16:13 lr 0.000460	time 2.5019 (2.2081)	loss 3.1726 (3.5165)	grad_norm 1.5400 (1.5631)	
[2022-01-22 16:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][820/1251]	eta 0:15:52 lr 0.000460	time 2.5317 (2.2094)	loss 4.2631 (3.5202)	grad_norm 1.5795 (1.5640)	
[2022-01-22 16:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][830/1251]	eta 0:15:29 lr 0.000460	time 1.8848 (2.2083)	loss 3.7990 (3.5215)	grad_norm 1.2943 (1.5638)	
[2022-01-22 16:41:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][840/1251]	eta 0:15:06 lr 0.000460	time 1.8856 (2.2066)	loss 3.5864 (3.5232)	grad_norm 1.3802 (1.5636)	
[2022-01-22 16:42:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][850/1251]	eta 0:14:43 lr 0.000460	time 1.8645 (2.2040)	loss 4.2228 (3.5226)	grad_norm 1.4661 (1.5637)	
[2022-01-22 16:42:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][860/1251]	eta 0:14:21 lr 0.000460	time 1.8222 (2.2041)	loss 3.6103 (3.5218)	grad_norm 1.4296 (1.5639)	
[2022-01-22 16:43:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][870/1251]	eta 0:13:59 lr 0.000460	time 1.7268 (2.2044)	loss 3.9670 (3.5241)	grad_norm 1.5238 (1.5626)	
[2022-01-22 16:43:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][880/1251]	eta 0:13:38 lr 0.000460	time 2.1481 (2.2063)	loss 3.7695 (3.5236)	grad_norm 1.3442 (1.5624)	
[2022-01-22 16:43:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][890/1251]	eta 0:13:16 lr 0.000460	time 2.4678 (2.2066)	loss 2.5608 (3.5231)	grad_norm 1.5937 (1.5634)	
[2022-01-22 16:44:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][900/1251]	eta 0:12:54 lr 0.000460	time 2.1489 (2.2060)	loss 4.2043 (3.5255)	grad_norm 1.5616 (1.5634)	
[2022-01-22 16:44:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][910/1251]	eta 0:12:32 lr 0.000460	time 2.2202 (2.2054)	loss 3.2515 (3.5234)	grad_norm 1.5418 (1.5640)	
[2022-01-22 16:44:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][920/1251]	eta 0:12:09 lr 0.000460	time 1.8580 (2.2050)	loss 2.3856 (3.5223)	grad_norm 1.5368 (1.5640)	
[2022-01-22 16:45:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][930/1251]	eta 0:11:47 lr 0.000460	time 2.4723 (2.2051)	loss 3.7986 (3.5219)	grad_norm 1.4227 (1.5641)	
[2022-01-22 16:45:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][940/1251]	eta 0:11:25 lr 0.000460	time 1.6452 (2.2026)	loss 3.6589 (3.5234)	grad_norm 1.6110 (1.5649)	
[2022-01-22 16:45:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][950/1251]	eta 0:11:02 lr 0.000460	time 1.7915 (2.2020)	loss 3.6978 (3.5228)	grad_norm 1.6669 (1.5645)	
[2022-01-22 16:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][960/1251]	eta 0:10:40 lr 0.000460	time 2.4115 (2.2016)	loss 3.5439 (3.5239)	grad_norm 1.4987 (1.5644)	
[2022-01-22 16:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][970/1251]	eta 0:10:19 lr 0.000460	time 2.2311 (2.2034)	loss 2.5178 (3.5235)	grad_norm 1.6465 (1.5644)	
[2022-01-22 16:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][980/1251]	eta 0:09:56 lr 0.000460	time 1.8221 (2.2028)	loss 4.1857 (3.5227)	grad_norm 1.6703 (1.5645)	
[2022-01-22 16:47:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][990/1251]	eta 0:09:34 lr 0.000459	time 1.9676 (2.2024)	loss 3.3232 (3.5249)	grad_norm 1.5100 (1.5642)	
[2022-01-22 16:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1000/1251]	eta 0:09:12 lr 0.000459	time 1.8346 (2.2020)	loss 3.7506 (3.5283)	grad_norm 1.5141 (1.5637)	
[2022-01-22 16:48:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1010/1251]	eta 0:08:50 lr 0.000459	time 2.5749 (2.2022)	loss 3.7390 (3.5299)	grad_norm 1.4088 (1.5635)	
[2022-01-22 16:48:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1020/1251]	eta 0:08:28 lr 0.000459	time 1.7092 (2.2015)	loss 2.9369 (3.5278)	grad_norm 1.4129 (1.5627)	
[2022-01-22 16:48:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1030/1251]	eta 0:08:06 lr 0.000459	time 2.3199 (2.2036)	loss 4.1692 (3.5303)	grad_norm 1.8897 (1.5628)	
[2022-01-22 16:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1040/1251]	eta 0:07:45 lr 0.000459	time 2.6056 (2.2048)	loss 2.7703 (3.5308)	grad_norm 1.4654 (1.5634)	
[2022-01-22 16:49:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1050/1251]	eta 0:07:23 lr 0.000459	time 3.2647 (2.2057)	loss 2.8142 (3.5278)	grad_norm 1.4585 (1.5621)	
[2022-01-22 16:50:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1060/1251]	eta 0:07:01 lr 0.000459	time 1.8203 (2.2054)	loss 3.2272 (3.5289)	grad_norm 1.5850 (1.5615)	
[2022-01-22 16:50:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1070/1251]	eta 0:06:39 lr 0.000459	time 1.6362 (2.2049)	loss 2.6233 (3.5292)	grad_norm 1.4380 (1.5607)	
[2022-01-22 16:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1080/1251]	eta 0:06:16 lr 0.000459	time 2.3135 (2.2026)	loss 2.9065 (3.5293)	grad_norm 1.5162 (1.5605)	
[2022-01-22 16:51:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1090/1251]	eta 0:05:54 lr 0.000459	time 2.8155 (2.2024)	loss 3.0581 (3.5298)	grad_norm 1.6992 (1.5605)	
[2022-01-22 16:51:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1100/1251]	eta 0:05:32 lr 0.000459	time 2.1587 (2.2018)	loss 4.2430 (3.5322)	grad_norm 1.6758 (1.5600)	
[2022-01-22 16:51:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1110/1251]	eta 0:05:10 lr 0.000459	time 2.1633 (2.2016)	loss 4.2789 (3.5342)	grad_norm 1.5157 (1.5600)	
[2022-01-22 16:52:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1120/1251]	eta 0:04:48 lr 0.000459	time 3.1821 (2.2013)	loss 3.6829 (3.5339)	grad_norm 1.4753 (1.5597)	
[2022-01-22 16:52:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1130/1251]	eta 0:04:26 lr 0.000459	time 1.8142 (2.2003)	loss 3.7766 (3.5338)	grad_norm 1.5879 (1.5597)	
[2022-01-22 16:52:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1140/1251]	eta 0:04:04 lr 0.000459	time 2.1922 (2.2000)	loss 3.1994 (3.5297)	grad_norm 1.7014 (1.5598)	
[2022-01-22 16:53:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1150/1251]	eta 0:03:42 lr 0.000459	time 2.4417 (2.2004)	loss 2.7966 (3.5300)	grad_norm 1.5780 (1.5589)	
[2022-01-22 16:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1160/1251]	eta 0:03:20 lr 0.000459	time 2.8804 (2.2013)	loss 4.1626 (3.5306)	grad_norm 1.5916 (1.5591)	
[2022-01-22 16:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1170/1251]	eta 0:02:58 lr 0.000459	time 1.5432 (2.2009)	loss 3.1499 (3.5306)	grad_norm 1.5589 (1.5588)	
[2022-01-22 16:54:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1180/1251]	eta 0:02:36 lr 0.000459	time 2.5395 (2.2004)	loss 3.4161 (3.5308)	grad_norm 1.3256 (1.5587)	
[2022-01-22 16:54:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1190/1251]	eta 0:02:14 lr 0.000459	time 2.1120 (2.1997)	loss 3.8980 (3.5296)	grad_norm 1.4771 (1.5593)	
[2022-01-22 16:55:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1200/1251]	eta 0:01:52 lr 0.000459	time 2.2428 (2.2006)	loss 3.9742 (3.5310)	grad_norm 1.3450 (1.5586)	
[2022-01-22 16:55:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1210/1251]	eta 0:01:30 lr 0.000459	time 2.1170 (2.2005)	loss 3.7010 (3.5300)	grad_norm 1.6110 (1.5579)	
[2022-01-22 16:55:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1220/1251]	eta 0:01:08 lr 0.000459	time 2.2004 (2.1994)	loss 3.5322 (3.5285)	grad_norm 1.5044 (1.5573)	
[2022-01-22 16:56:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1230/1251]	eta 0:00:46 lr 0.000459	time 3.5853 (2.2001)	loss 3.7171 (3.5273)	grad_norm 1.3122 (1.5568)	
[2022-01-22 16:56:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1240/1251]	eta 0:00:24 lr 0.000458	time 1.6602 (2.1989)	loss 3.5230 (3.5260)	grad_norm 1.5385 (1.5571)	
[2022-01-22 16:56:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [158/300][1250/1251]	eta 0:00:02 lr 0.000458	time 1.1322 (2.1937)	loss 3.7553 (3.5264)	grad_norm 1.5456 (1.5571)	
[2022-01-22 16:56:47 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 158 training takes 0:45:44
[2022-01-22 16:57:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.243 (18.243)	Loss 1.0705 (1.0705)	Acc@1 74.316 (74.316)	Acc@5 92.383 (92.383)	
[2022-01-22 16:57:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.857 (3.528)	Loss 0.9509 (1.0188)	Acc@1 77.734 (75.914)	Acc@5 93.066 (93.288)	
[2022-01-22 16:57:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.893 (2.659)	Loss 1.0667 (1.0194)	Acc@1 74.902 (75.967)	Acc@5 92.773 (93.252)	
[2022-01-22 16:57:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.603 (2.332)	Loss 0.9839 (1.0122)	Acc@1 77.441 (76.247)	Acc@5 93.750 (93.366)	
[2022-01-22 16:58:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.807 (2.199)	Loss 1.0072 (1.0101)	Acc@1 78.027 (76.331)	Acc@5 93.652 (93.431)	
[2022-01-22 16:58:25 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.444 Acc@5 93.474
[2022-01-22 16:58:25 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.4%
[2022-01-22 16:58:25 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.52%
[2022-01-22 16:58:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][0/1251]	eta 7:24:07 lr 0.000458	time 21.3009 (21.3009)	loss 3.7544 (3.7544)	grad_norm 1.5750 (1.5750)	
[2022-01-22 16:59:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][10/1251]	eta 1:21:00 lr 0.000458	time 2.4466 (3.9169)	loss 3.5647 (3.5384)	grad_norm 1.3565 (1.5221)	
[2022-01-22 16:59:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][20/1251]	eta 1:04:28 lr 0.000458	time 1.9926 (3.1426)	loss 3.4535 (3.6154)	grad_norm 1.5274 (1.5624)	
[2022-01-22 16:59:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][30/1251]	eta 0:57:06 lr 0.000458	time 1.2554 (2.8064)	loss 2.3206 (3.4999)	grad_norm 1.7363 (1.5727)	
[2022-01-22 17:00:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][40/1251]	eta 0:53:45 lr 0.000458	time 3.2566 (2.6631)	loss 3.8171 (3.4932)	grad_norm 1.6985 (1.5801)	
[2022-01-22 17:00:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][50/1251]	eta 0:51:16 lr 0.000458	time 2.5769 (2.5613)	loss 3.4501 (3.5372)	grad_norm 1.4003 (1.5600)	
[2022-01-22 17:00:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][60/1251]	eta 0:49:33 lr 0.000458	time 2.2421 (2.4970)	loss 3.5881 (3.5345)	grad_norm 1.6608 (1.5543)	
[2022-01-22 17:01:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][70/1251]	eta 0:48:30 lr 0.000458	time 1.8300 (2.4648)	loss 3.7960 (3.5198)	grad_norm 1.5493 (1.5515)	
[2022-01-22 17:01:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][80/1251]	eta 0:47:57 lr 0.000458	time 3.3017 (2.4570)	loss 2.7022 (3.4998)	grad_norm 1.4190 (1.5453)	
[2022-01-22 17:02:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][90/1251]	eta 0:46:59 lr 0.000458	time 1.8177 (2.4282)	loss 4.2385 (3.5028)	grad_norm 1.6072 (1.5572)	
[2022-01-22 17:02:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][100/1251]	eta 0:46:18 lr 0.000458	time 3.2230 (2.4139)	loss 4.2720 (3.5021)	grad_norm 1.4121 (1.5603)	
[2022-01-22 17:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][110/1251]	eta 0:45:19 lr 0.000458	time 1.5966 (2.3833)	loss 3.8138 (3.5047)	grad_norm 2.6092 (1.5698)	
[2022-01-22 17:03:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][120/1251]	eta 0:44:57 lr 0.000458	time 3.4498 (2.3853)	loss 3.5821 (3.4906)	grad_norm 1.5178 (1.5703)	
[2022-01-22 17:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][130/1251]	eta 0:44:15 lr 0.000458	time 1.7323 (2.3692)	loss 4.0937 (3.4816)	grad_norm 1.8673 (1.5748)	
[2022-01-22 17:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][140/1251]	eta 0:43:32 lr 0.000458	time 2.2850 (2.3518)	loss 2.8392 (3.4787)	grad_norm 1.5244 (1.5758)	
[2022-01-22 17:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][150/1251]	eta 0:42:50 lr 0.000458	time 1.6336 (2.3347)	loss 3.6310 (3.4740)	grad_norm 1.6630 (1.5721)	
[2022-01-22 17:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][160/1251]	eta 0:42:07 lr 0.000458	time 2.1599 (2.3164)	loss 4.2234 (3.4907)	grad_norm 1.4456 (1.5751)	
[2022-01-22 17:05:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][170/1251]	eta 0:41:37 lr 0.000458	time 1.8922 (2.3106)	loss 3.6016 (3.4810)	grad_norm 1.5298 (1.5722)	
[2022-01-22 17:05:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][180/1251]	eta 0:41:18 lr 0.000458	time 1.8597 (2.3142)	loss 3.4258 (3.4726)	grad_norm 1.9941 (1.5673)	
[2022-01-22 17:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][190/1251]	eta 0:40:56 lr 0.000458	time 1.9882 (2.3155)	loss 4.0071 (3.4783)	grad_norm 1.4475 (1.5658)	
[2022-01-22 17:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][200/1251]	eta 0:40:23 lr 0.000458	time 1.9445 (2.3057)	loss 3.5065 (3.4854)	grad_norm 1.6437 (1.5656)	
[2022-01-22 17:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][210/1251]	eta 0:39:45 lr 0.000458	time 1.7236 (2.2915)	loss 2.3709 (3.4753)	grad_norm 1.5348 (1.5657)	
[2022-01-22 17:06:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][220/1251]	eta 0:39:05 lr 0.000458	time 2.1172 (2.2753)	loss 3.9047 (3.4842)	grad_norm 1.4240 (1.5649)	
[2022-01-22 17:07:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][230/1251]	eta 0:38:38 lr 0.000457	time 1.8414 (2.2707)	loss 3.8981 (3.4941)	grad_norm 1.9700 (1.5656)	
[2022-01-22 17:07:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][240/1251]	eta 0:38:11 lr 0.000457	time 2.4245 (2.2664)	loss 2.8013 (3.4977)	grad_norm 1.4754 (1.5627)	
[2022-01-22 17:07:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][250/1251]	eta 0:37:47 lr 0.000457	time 2.3175 (2.2656)	loss 3.3576 (3.4946)	grad_norm 1.6653 (1.5613)	
[2022-01-22 17:08:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][260/1251]	eta 0:37:25 lr 0.000457	time 2.6259 (2.2663)	loss 3.8615 (3.4787)	grad_norm 1.2601 (1.5591)	
[2022-01-22 17:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][270/1251]	eta 0:37:02 lr 0.000457	time 1.5257 (2.2657)	loss 3.8899 (3.4844)	grad_norm 1.3595 (1.5579)	
[2022-01-22 17:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][280/1251]	eta 0:36:40 lr 0.000457	time 1.5536 (2.2658)	loss 3.5211 (3.4860)	grad_norm 1.4048 (1.5587)	
[2022-01-22 17:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][290/1251]	eta 0:36:16 lr 0.000457	time 2.0576 (2.2645)	loss 3.7130 (3.4970)	grad_norm 1.6440 (1.5582)	
[2022-01-22 17:09:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][300/1251]	eta 0:35:49 lr 0.000457	time 2.7325 (2.2606)	loss 4.0441 (3.5079)	grad_norm 1.5551 (1.5577)	
[2022-01-22 17:10:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][310/1251]	eta 0:35:17 lr 0.000457	time 1.8388 (2.2508)	loss 3.7363 (3.5100)	grad_norm 1.4764 (1.5578)	
[2022-01-22 17:10:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][320/1251]	eta 0:34:53 lr 0.000457	time 1.8899 (2.2483)	loss 3.4640 (3.5130)	grad_norm 1.3947 (1.5568)	
[2022-01-22 17:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][330/1251]	eta 0:34:29 lr 0.000457	time 2.1931 (2.2469)	loss 4.0684 (3.5204)	grad_norm 1.3228 (1.5555)	
[2022-01-22 17:11:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][340/1251]	eta 0:34:12 lr 0.000457	time 3.1047 (2.2526)	loss 3.6584 (3.5129)	grad_norm 1.4294 (1.5566)	
[2022-01-22 17:11:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][350/1251]	eta 0:33:52 lr 0.000457	time 1.9989 (2.2563)	loss 3.9990 (3.5147)	grad_norm 1.5061 (1.5551)	
[2022-01-22 17:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][360/1251]	eta 0:33:29 lr 0.000457	time 1.8332 (2.2557)	loss 2.2291 (3.5103)	grad_norm 1.3596 (1.5585)	
[2022-01-22 17:12:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][370/1251]	eta 0:32:58 lr 0.000457	time 1.6144 (2.2462)	loss 3.6103 (3.4971)	grad_norm 1.8632 (1.5621)	
[2022-01-22 17:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][380/1251]	eta 0:32:29 lr 0.000457	time 2.2054 (2.2385)	loss 2.7790 (3.4949)	grad_norm 1.5351 (1.5632)	
[2022-01-22 17:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][390/1251]	eta 0:32:02 lr 0.000457	time 1.8621 (2.2325)	loss 4.1397 (3.4972)	grad_norm 1.7128 (1.5633)	
[2022-01-22 17:13:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][400/1251]	eta 0:31:36 lr 0.000457	time 1.8495 (2.2288)	loss 2.9626 (3.4987)	grad_norm 1.4882 (1.5646)	
[2022-01-22 17:13:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][410/1251]	eta 0:31:10 lr 0.000457	time 2.5900 (2.2241)	loss 3.0571 (3.4963)	grad_norm 1.5550 (1.5640)	
[2022-01-22 17:14:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][420/1251]	eta 0:30:47 lr 0.000457	time 2.4456 (2.2235)	loss 3.6851 (3.5005)	grad_norm 1.3795 (1.5621)	
[2022-01-22 17:14:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][430/1251]	eta 0:30:27 lr 0.000457	time 2.4965 (2.2265)	loss 3.1839 (3.4934)	grad_norm 1.5691 (1.5617)	
[2022-01-22 17:14:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][440/1251]	eta 0:30:06 lr 0.000457	time 2.5905 (2.2279)	loss 2.2242 (3.4912)	grad_norm 1.4955 (1.5626)	
[2022-01-22 17:15:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][450/1251]	eta 0:29:45 lr 0.000457	time 2.7391 (2.2289)	loss 3.5904 (3.4925)	grad_norm 1.6918 (1.5625)	
[2022-01-22 17:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][460/1251]	eta 0:29:23 lr 0.000457	time 2.2630 (2.2293)	loss 3.2039 (3.4943)	grad_norm 1.7401 (1.5656)	
[2022-01-22 17:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][470/1251]	eta 0:29:00 lr 0.000456	time 1.7948 (2.2282)	loss 3.8779 (3.4923)	grad_norm 1.4277 (1.5648)	
[2022-01-22 17:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][480/1251]	eta 0:28:37 lr 0.000456	time 2.3187 (2.2280)	loss 4.3703 (3.4890)	grad_norm 1.6986 (1.5634)	
[2022-01-22 17:16:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][490/1251]	eta 0:28:14 lr 0.000456	time 1.8774 (2.2269)	loss 3.4669 (3.4908)	grad_norm 1.3838 (1.5650)	
[2022-01-22 17:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][500/1251]	eta 0:27:49 lr 0.000456	time 1.8403 (2.2237)	loss 2.5265 (3.4832)	grad_norm 1.4473 (1.5641)	
[2022-01-22 17:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][510/1251]	eta 0:27:25 lr 0.000456	time 1.9266 (2.2205)	loss 2.9918 (3.4785)	grad_norm 1.4287 (1.5655)	
[2022-01-22 17:17:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][520/1251]	eta 0:27:02 lr 0.000456	time 2.1300 (2.2192)	loss 3.1214 (3.4722)	grad_norm 1.5343 (1.5669)	
[2022-01-22 17:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][530/1251]	eta 0:26:39 lr 0.000456	time 1.8915 (2.2185)	loss 3.8174 (3.4753)	grad_norm 1.3838 (1.5677)	
[2022-01-22 17:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][540/1251]	eta 0:26:17 lr 0.000456	time 2.1087 (2.2184)	loss 3.7409 (3.4798)	grad_norm 1.3908 (1.5677)	
[2022-01-22 17:18:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][550/1251]	eta 0:25:55 lr 0.000456	time 2.1914 (2.2195)	loss 3.2567 (3.4803)	grad_norm 1.2454 (1.5657)	
[2022-01-22 17:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][560/1251]	eta 0:25:35 lr 0.000456	time 3.4502 (2.2225)	loss 3.2325 (3.4762)	grad_norm 1.4101 (1.5658)	
[2022-01-22 17:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][570/1251]	eta 0:25:13 lr 0.000456	time 1.8322 (2.2219)	loss 2.5909 (3.4773)	grad_norm 1.7388 (1.5675)	
[2022-01-22 17:19:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][580/1251]	eta 0:24:48 lr 0.000456	time 1.8653 (2.2186)	loss 3.7177 (3.4759)	grad_norm 1.3831 (1.5669)	
[2022-01-22 17:20:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][590/1251]	eta 0:24:24 lr 0.000456	time 1.7195 (2.2156)	loss 3.6859 (3.4776)	grad_norm 1.7023 (1.5676)	
[2022-01-22 17:20:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][600/1251]	eta 0:24:02 lr 0.000456	time 3.0539 (2.2153)	loss 3.0993 (3.4774)	grad_norm 1.7714 (1.5693)	
[2022-01-22 17:20:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][610/1251]	eta 0:23:39 lr 0.000456	time 2.4083 (2.2151)	loss 3.1823 (3.4762)	grad_norm 1.4941 (1.5693)	
[2022-01-22 17:21:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][620/1251]	eta 0:23:18 lr 0.000456	time 1.8678 (2.2169)	loss 3.0193 (3.4736)	grad_norm 1.6111 (1.5674)	
[2022-01-22 17:21:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][630/1251]	eta 0:22:57 lr 0.000456	time 1.6781 (2.2182)	loss 3.5870 (3.4732)	grad_norm 1.4253 (1.5673)	
[2022-01-22 17:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][640/1251]	eta 0:22:34 lr 0.000456	time 2.1569 (2.2177)	loss 3.9381 (3.4752)	grad_norm 1.5940 (1.5663)	
[2022-01-22 17:22:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][650/1251]	eta 0:22:11 lr 0.000456	time 2.7645 (2.2157)	loss 3.2228 (3.4792)	grad_norm 1.3749 (1.5646)	
[2022-01-22 17:22:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][660/1251]	eta 0:21:47 lr 0.000456	time 2.2405 (2.2131)	loss 3.3101 (3.4739)	grad_norm 1.6297 (1.5647)	
[2022-01-22 17:23:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][670/1251]	eta 0:21:24 lr 0.000456	time 1.8678 (2.2109)	loss 4.0170 (3.4779)	grad_norm 1.4689 (1.5641)	
[2022-01-22 17:23:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][680/1251]	eta 0:21:02 lr 0.000456	time 1.5986 (2.2116)	loss 4.0702 (3.4798)	grad_norm 1.4561 (1.5640)	
[2022-01-22 17:23:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][690/1251]	eta 0:20:40 lr 0.000456	time 2.3822 (2.2118)	loss 3.0603 (3.4798)	grad_norm 1.6082 (1.5645)	
[2022-01-22 17:24:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][700/1251]	eta 0:20:17 lr 0.000456	time 2.1525 (2.2101)	loss 3.3674 (3.4833)	grad_norm 1.5146 (1.5635)	
[2022-01-22 17:24:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][710/1251]	eta 0:19:56 lr 0.000455	time 2.7687 (2.2121)	loss 4.4174 (3.4863)	grad_norm 1.4011 (1.5630)	
[2022-01-22 17:24:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][720/1251]	eta 0:19:34 lr 0.000455	time 1.8926 (2.2120)	loss 3.9250 (3.4838)	grad_norm 1.4102 (1.5615)	
[2022-01-22 17:25:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][730/1251]	eta 0:19:13 lr 0.000455	time 2.6650 (2.2131)	loss 3.4700 (3.4836)	grad_norm 1.7851 (1.5617)	
[2022-01-22 17:25:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][740/1251]	eta 0:18:49 lr 0.000455	time 1.9064 (2.2105)	loss 4.1031 (3.4867)	grad_norm 1.6131 (1.5631)	
[2022-01-22 17:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][750/1251]	eta 0:18:26 lr 0.000455	time 1.9633 (2.2084)	loss 3.6819 (3.4898)	grad_norm 1.4499 (1.5633)	
[2022-01-22 17:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][760/1251]	eta 0:18:03 lr 0.000455	time 1.6391 (2.2060)	loss 4.0607 (3.4902)	grad_norm 1.5283 (1.5631)	
[2022-01-22 17:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][770/1251]	eta 0:17:41 lr 0.000455	time 2.8124 (2.2075)	loss 2.2754 (3.4877)	grad_norm 1.6057 (1.5632)	
[2022-01-22 17:27:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][780/1251]	eta 0:17:19 lr 0.000455	time 1.8286 (2.2077)	loss 3.5368 (3.4907)	grad_norm 1.7842 (1.5639)	
[2022-01-22 17:27:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][790/1251]	eta 0:16:58 lr 0.000455	time 2.1383 (2.2095)	loss 3.8597 (3.4897)	grad_norm 1.7645 (1.5651)	
[2022-01-22 17:27:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][800/1251]	eta 0:16:37 lr 0.000455	time 2.3768 (2.2109)	loss 3.6649 (3.4906)	grad_norm 1.4691 (1.5654)	
[2022-01-22 17:28:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][810/1251]	eta 0:16:15 lr 0.000455	time 2.1979 (2.2121)	loss 3.2370 (3.4906)	grad_norm 1.4159 (1.5648)	
[2022-01-22 17:28:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][820/1251]	eta 0:15:53 lr 0.000455	time 2.1886 (2.2113)	loss 3.4183 (3.4877)	grad_norm 1.4058 (1.5642)	
[2022-01-22 17:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][830/1251]	eta 0:15:30 lr 0.000455	time 1.7896 (2.2107)	loss 3.9413 (3.4879)	grad_norm 1.6232 (1.5640)	
[2022-01-22 17:29:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][840/1251]	eta 0:15:07 lr 0.000455	time 2.1590 (2.2088)	loss 3.5402 (3.4895)	grad_norm 1.4014 (1.5631)	
[2022-01-22 17:29:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][850/1251]	eta 0:14:45 lr 0.000455	time 1.8611 (2.2075)	loss 3.2850 (3.4871)	grad_norm 1.4202 (1.5626)	
[2022-01-22 17:30:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][860/1251]	eta 0:14:23 lr 0.000455	time 2.7565 (2.2073)	loss 3.4493 (3.4881)	grad_norm 1.4998 (1.5627)	
[2022-01-22 17:30:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][870/1251]	eta 0:14:00 lr 0.000455	time 1.7708 (2.2068)	loss 3.5911 (3.4879)	grad_norm 1.3171 (1.5612)	
[2022-01-22 17:30:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][880/1251]	eta 0:13:38 lr 0.000455	time 1.7978 (2.2059)	loss 2.3781 (3.4878)	grad_norm 1.4175 (1.5617)	
[2022-01-22 17:31:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][890/1251]	eta 0:13:16 lr 0.000455	time 1.8928 (2.2056)	loss 3.5142 (3.4915)	grad_norm 1.7633 (1.5624)	
[2022-01-22 17:31:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][900/1251]	eta 0:12:54 lr 0.000455	time 2.2265 (2.2053)	loss 4.1732 (3.4936)	grad_norm 1.4486 (1.5625)	
[2022-01-22 17:31:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][910/1251]	eta 0:12:32 lr 0.000455	time 2.8053 (2.2063)	loss 3.4865 (3.4936)	grad_norm 1.5237 (1.5619)	
[2022-01-22 17:32:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][920/1251]	eta 0:12:10 lr 0.000455	time 1.9306 (2.2058)	loss 3.8407 (3.4921)	grad_norm 1.5943 (1.5609)	
[2022-01-22 17:32:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][930/1251]	eta 0:11:47 lr 0.000455	time 1.5674 (2.2039)	loss 3.8195 (3.4934)	grad_norm 1.6479 (1.5607)	
[2022-01-22 17:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][940/1251]	eta 0:11:26 lr 0.000455	time 3.4570 (2.2063)	loss 3.5863 (3.4921)	grad_norm 1.6108 (1.5609)	
[2022-01-22 17:33:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][950/1251]	eta 0:11:04 lr 0.000454	time 2.8582 (2.2085)	loss 4.0650 (3.4897)	grad_norm 1.6723 (1.5610)	
[2022-01-22 17:33:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][960/1251]	eta 0:10:42 lr 0.000454	time 2.2994 (2.2082)	loss 3.9918 (3.4904)	grad_norm 1.4326 (1.5609)	
[2022-01-22 17:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][970/1251]	eta 0:10:19 lr 0.000454	time 1.7578 (2.2051)	loss 3.2409 (3.4914)	grad_norm 1.3398 (1.5613)	
[2022-01-22 17:34:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][980/1251]	eta 0:09:57 lr 0.000454	time 1.9613 (2.2034)	loss 4.1995 (3.4925)	grad_norm 1.6807 (1.5622)	
[2022-01-22 17:34:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][990/1251]	eta 0:09:35 lr 0.000454	time 2.2050 (2.2042)	loss 3.5398 (3.4930)	grad_norm 1.4335 (1.5619)	
[2022-01-22 17:35:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1000/1251]	eta 0:09:13 lr 0.000454	time 3.1099 (2.2057)	loss 4.1334 (3.4941)	grad_norm 1.7365 (1.5618)	
[2022-01-22 17:35:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1010/1251]	eta 0:08:51 lr 0.000454	time 1.8328 (2.2042)	loss 3.6006 (3.4927)	grad_norm 1.4536 (1.5620)	
[2022-01-22 17:35:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1020/1251]	eta 0:08:29 lr 0.000454	time 1.5929 (2.2038)	loss 3.4275 (3.4922)	grad_norm 1.6119 (1.5629)	
[2022-01-22 17:36:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1030/1251]	eta 0:08:07 lr 0.000454	time 1.8748 (2.2038)	loss 3.5400 (3.4921)	grad_norm 1.7041 (1.5638)	
[2022-01-22 17:36:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1040/1251]	eta 0:07:45 lr 0.000454	time 2.7184 (2.2050)	loss 3.8262 (3.4922)	grad_norm 1.7140 (1.5637)	
[2022-01-22 17:37:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1050/1251]	eta 0:07:22 lr 0.000454	time 1.7869 (2.2033)	loss 2.6293 (3.4906)	grad_norm 1.9628 (1.5632)	
[2022-01-22 17:37:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1060/1251]	eta 0:07:00 lr 0.000454	time 2.2374 (2.2021)	loss 3.0887 (3.4909)	grad_norm 1.5101 (1.5629)	
[2022-01-22 17:37:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1070/1251]	eta 0:06:38 lr 0.000454	time 1.8780 (2.2011)	loss 3.8348 (3.4921)	grad_norm 1.5487 (1.5618)	
[2022-01-22 17:38:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1080/1251]	eta 0:06:16 lr 0.000454	time 2.5641 (2.2007)	loss 4.2216 (3.4949)	grad_norm 1.4516 (1.5614)	
[2022-01-22 17:38:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1090/1251]	eta 0:05:54 lr 0.000454	time 2.2503 (2.1996)	loss 4.2164 (3.4965)	grad_norm 1.6607 (1.5609)	
[2022-01-22 17:38:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1100/1251]	eta 0:05:31 lr 0.000454	time 3.0231 (2.1985)	loss 3.8228 (3.4965)	grad_norm 1.5478 (1.5607)	
[2022-01-22 17:39:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1110/1251]	eta 0:05:09 lr 0.000454	time 1.6089 (2.1974)	loss 3.8888 (3.4957)	grad_norm 1.4971 (1.5608)	
[2022-01-22 17:39:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1120/1251]	eta 0:04:47 lr 0.000454	time 1.8842 (2.1962)	loss 3.3757 (3.4955)	grad_norm 1.5812 (1.5609)	
[2022-01-22 17:39:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1130/1251]	eta 0:04:25 lr 0.000454	time 2.1066 (2.1968)	loss 4.4838 (3.4976)	grad_norm 1.6337 (1.5617)	
[2022-01-22 17:40:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1140/1251]	eta 0:04:03 lr 0.000454	time 2.5494 (2.1979)	loss 3.3744 (3.4972)	grad_norm 1.4427 (1.5614)	
[2022-01-22 17:40:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1150/1251]	eta 0:03:41 lr 0.000454	time 2.2354 (2.1971)	loss 2.3348 (3.4966)	grad_norm 1.4612 (1.5612)	
[2022-01-22 17:40:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1160/1251]	eta 0:03:19 lr 0.000454	time 2.1205 (2.1973)	loss 2.5777 (3.4971)	grad_norm 1.6342 (1.5614)	
[2022-01-22 17:41:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1170/1251]	eta 0:02:57 lr 0.000454	time 1.7306 (2.1973)	loss 3.7261 (3.4964)	grad_norm 1.4869 (1.5626)	
[2022-01-22 17:41:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1180/1251]	eta 0:02:36 lr 0.000454	time 2.8064 (2.1988)	loss 2.2628 (3.4964)	grad_norm 1.4520 (1.5622)	
[2022-01-22 17:42:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1190/1251]	eta 0:02:14 lr 0.000454	time 2.3394 (2.2006)	loss 2.5934 (3.4959)	grad_norm 1.5337 (1.5627)	
[2022-01-22 17:42:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1200/1251]	eta 0:01:52 lr 0.000453	time 1.8646 (2.1998)	loss 3.0355 (3.4948)	grad_norm 1.4676 (1.5622)	
[2022-01-22 17:42:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1210/1251]	eta 0:01:30 lr 0.000453	time 2.1525 (2.1993)	loss 2.7842 (3.4936)	grad_norm 1.7390 (1.5624)	
[2022-01-22 17:43:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1220/1251]	eta 0:01:08 lr 0.000453	time 1.6430 (2.1984)	loss 2.4894 (3.4950)	grad_norm 1.4956 (1.5624)	
[2022-01-22 17:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1230/1251]	eta 0:00:46 lr 0.000453	time 1.8047 (2.1987)	loss 2.5427 (3.4945)	grad_norm 2.3922 (1.5638)	
[2022-01-22 17:43:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1240/1251]	eta 0:00:24 lr 0.000453	time 1.4024 (2.1973)	loss 3.7817 (3.4945)	grad_norm 1.3251 (1.5637)	
[2022-01-22 17:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [159/300][1250/1251]	eta 0:00:02 lr 0.000453	time 1.1923 (2.1919)	loss 2.6675 (3.4936)	grad_norm 1.4074 (1.5634)	
[2022-01-22 17:44:07 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 159 training takes 0:45:42
[2022-01-22 17:44:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.473 (18.473)	Loss 0.9845 (0.9845)	Acc@1 78.027 (78.027)	Acc@5 93.262 (93.262)	
[2022-01-22 17:44:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.575 (3.457)	Loss 1.0708 (1.0087)	Acc@1 75.586 (76.527)	Acc@5 92.969 (93.457)	
[2022-01-22 17:45:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.576 (2.559)	Loss 1.0186 (0.9949)	Acc@1 75.879 (76.814)	Acc@5 93.262 (93.676)	
[2022-01-22 17:45:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.963 (2.360)	Loss 0.8966 (0.9994)	Acc@1 78.906 (76.663)	Acc@5 94.922 (93.693)	
[2022-01-22 17:45:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.748 (2.237)	Loss 0.9770 (1.0016)	Acc@1 77.930 (76.651)	Acc@5 94.043 (93.676)	
[2022-01-22 17:45:46 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.550 Acc@5 93.530
[2022-01-22 17:45:46 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.5%
[2022-01-22 17:45:46 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.55%
[2022-01-22 17:46:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][0/1251]	eta 8:29:52 lr 0.000453	time 24.4544 (24.4544)	loss 4.2291 (4.2291)	grad_norm 1.8724 (1.8724)	
[2022-01-22 17:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][10/1251]	eta 1:37:14 lr 0.000453	time 2.8426 (4.7011)	loss 3.8267 (3.3976)	grad_norm 1.4842 (1.5757)	
[2022-01-22 17:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][20/1251]	eta 1:12:51 lr 0.000453	time 1.4159 (3.5512)	loss 4.0757 (3.6373)	grad_norm 1.4305 (1.5816)	
[2022-01-22 17:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][30/1251]	eta 1:03:21 lr 0.000453	time 2.0385 (3.1131)	loss 3.2739 (3.6212)	grad_norm 1.6829 (1.5712)	
[2022-01-22 17:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][40/1251]	eta 0:58:36 lr 0.000453	time 3.8085 (2.9041)	loss 4.1835 (3.6249)	grad_norm 1.4326 (1.5597)	
[2022-01-22 17:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][50/1251]	eta 0:55:13 lr 0.000453	time 1.5535 (2.7586)	loss 3.2712 (3.5890)	grad_norm 1.5288 (1.5577)	
[2022-01-22 17:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][60/1251]	eta 0:52:39 lr 0.000453	time 2.0289 (2.6527)	loss 4.1920 (3.6281)	grad_norm 1.5323 (1.5503)	
[2022-01-22 17:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][70/1251]	eta 0:50:45 lr 0.000453	time 1.9403 (2.5790)	loss 2.3824 (3.5583)	grad_norm 1.4373 (1.5480)	
[2022-01-22 17:49:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][80/1251]	eta 0:49:45 lr 0.000453	time 3.6096 (2.5494)	loss 3.6679 (3.5296)	grad_norm 1.5928 (1.5413)	
[2022-01-22 17:49:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][90/1251]	eta 0:48:13 lr 0.000453	time 1.9093 (2.4920)	loss 2.7579 (3.5031)	grad_norm 1.5675 (1.5477)	
[2022-01-22 17:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][100/1251]	eta 0:46:52 lr 0.000453	time 1.6763 (2.4435)	loss 3.9803 (3.5206)	grad_norm 1.6110 (1.5506)	
[2022-01-22 17:50:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][110/1251]	eta 0:45:50 lr 0.000453	time 2.2363 (2.4107)	loss 3.7022 (3.5090)	grad_norm 1.4634 (1.5553)	
[2022-01-22 17:50:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][120/1251]	eta 0:45:03 lr 0.000453	time 2.5400 (2.3906)	loss 3.5313 (3.4936)	grad_norm 2.2937 (1.5648)	
[2022-01-22 17:50:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][130/1251]	eta 0:44:28 lr 0.000453	time 2.3469 (2.3801)	loss 3.6164 (3.4911)	grad_norm 1.7546 (1.5631)	
[2022-01-22 17:51:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][140/1251]	eta 0:43:51 lr 0.000453	time 1.8913 (2.3685)	loss 2.9522 (3.4762)	grad_norm 1.8677 (1.5717)	
[2022-01-22 17:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][150/1251]	eta 0:43:20 lr 0.000453	time 2.3968 (2.3622)	loss 3.9748 (3.4862)	grad_norm 1.8053 (1.5744)	
[2022-01-22 17:52:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][160/1251]	eta 0:42:58 lr 0.000453	time 2.1401 (2.3634)	loss 2.9391 (3.4835)	grad_norm 1.6451 (1.5767)	
[2022-01-22 17:52:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][170/1251]	eta 0:42:26 lr 0.000453	time 1.8151 (2.3561)	loss 4.2070 (3.5093)	grad_norm 1.5308 (1.5816)	
[2022-01-22 17:52:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][180/1251]	eta 0:41:49 lr 0.000453	time 1.9082 (2.3427)	loss 3.8283 (3.5100)	grad_norm 1.9380 (1.5784)	
[2022-01-22 17:53:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][190/1251]	eta 0:41:01 lr 0.000452	time 1.6552 (2.3201)	loss 4.0845 (3.5230)	grad_norm 1.6741 (1.5750)	
[2022-01-22 17:53:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][200/1251]	eta 0:40:20 lr 0.000452	time 1.8866 (2.3028)	loss 3.9174 (3.5128)	grad_norm 1.5289 (1.5780)	
[2022-01-22 17:53:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][210/1251]	eta 0:39:50 lr 0.000452	time 2.0090 (2.2967)	loss 4.0792 (3.5243)	grad_norm 1.8316 (1.5768)	
[2022-01-22 17:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][220/1251]	eta 0:39:20 lr 0.000452	time 2.7239 (2.2900)	loss 3.9260 (3.5344)	grad_norm 1.4822 (1.5783)	
[2022-01-22 17:54:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][230/1251]	eta 0:38:55 lr 0.000452	time 2.6465 (2.2879)	loss 4.0161 (3.5369)	grad_norm 1.5668 (1.5817)	
[2022-01-22 17:54:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][240/1251]	eta 0:38:25 lr 0.000452	time 1.6085 (2.2807)	loss 2.4703 (3.5332)	grad_norm 1.3523 (1.5830)	
[2022-01-22 17:55:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][250/1251]	eta 0:37:58 lr 0.000452	time 1.6390 (2.2763)	loss 3.0167 (3.5249)	grad_norm 1.5706 (1.5814)	
[2022-01-22 17:55:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][260/1251]	eta 0:37:39 lr 0.000452	time 2.6108 (2.2802)	loss 2.2346 (3.5125)	grad_norm 1.4613 (1.5782)	
[2022-01-22 17:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][270/1251]	eta 0:37:13 lr 0.000452	time 2.3519 (2.2764)	loss 3.3624 (3.4975)	grad_norm 1.3302 (1.5770)	
[2022-01-22 17:56:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][280/1251]	eta 0:36:47 lr 0.000452	time 1.8419 (2.2731)	loss 3.8381 (3.5066)	grad_norm 1.5963 (1.5762)	
[2022-01-22 17:56:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][290/1251]	eta 0:36:24 lr 0.000452	time 1.8406 (2.2730)	loss 3.8308 (3.5068)	grad_norm 1.7745 (1.5803)	
[2022-01-22 17:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][300/1251]	eta 0:36:04 lr 0.000452	time 2.8857 (2.2760)	loss 2.5897 (3.5025)	grad_norm 1.4008 (1.5798)	
[2022-01-22 17:57:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][310/1251]	eta 0:35:33 lr 0.000452	time 1.5967 (2.2668)	loss 2.4694 (3.4988)	grad_norm 1.5571 (1.5779)	
[2022-01-22 17:57:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][320/1251]	eta 0:35:05 lr 0.000452	time 1.8485 (2.2620)	loss 3.8144 (3.5081)	grad_norm 1.4920 (1.5751)	
[2022-01-22 17:58:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][330/1251]	eta 0:34:38 lr 0.000452	time 1.8275 (2.2565)	loss 3.7482 (3.5068)	grad_norm 1.5117 (1.5764)	
[2022-01-22 17:58:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][340/1251]	eta 0:34:14 lr 0.000452	time 2.7908 (2.2549)	loss 2.8243 (3.5020)	grad_norm 1.4659 (1.5764)	
[2022-01-22 17:58:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][350/1251]	eta 0:33:52 lr 0.000452	time 2.2588 (2.2553)	loss 3.3848 (3.5018)	grad_norm 1.4905 (1.5751)	
[2022-01-22 17:59:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][360/1251]	eta 0:33:25 lr 0.000452	time 1.5881 (2.2510)	loss 3.9416 (3.5010)	grad_norm 1.4375 (1.5734)	
[2022-01-22 17:59:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][370/1251]	eta 0:33:03 lr 0.000452	time 2.5431 (2.2515)	loss 3.2109 (3.4990)	grad_norm 1.4711 (1.5742)	
[2022-01-22 18:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][380/1251]	eta 0:32:41 lr 0.000452	time 2.8114 (2.2519)	loss 2.4557 (3.4980)	grad_norm 1.2827 (1.5734)	
[2022-01-22 18:00:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][390/1251]	eta 0:32:20 lr 0.000452	time 2.4809 (2.2537)	loss 2.4861 (3.4998)	grad_norm 1.6852 (1.5735)	
[2022-01-22 18:00:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][400/1251]	eta 0:31:57 lr 0.000452	time 2.1795 (2.2536)	loss 4.1215 (3.4994)	grad_norm 1.5959 (1.5734)	
[2022-01-22 18:01:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][410/1251]	eta 0:31:31 lr 0.000452	time 1.6079 (2.2492)	loss 3.1850 (3.5018)	grad_norm 1.6315 (1.5725)	
[2022-01-22 18:01:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][420/1251]	eta 0:31:07 lr 0.000452	time 2.1656 (2.2471)	loss 3.7867 (3.5027)	grad_norm 1.8198 (1.5752)	
[2022-01-22 18:01:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][430/1251]	eta 0:30:49 lr 0.000451	time 2.5851 (2.2525)	loss 4.0689 (3.5069)	grad_norm 1.4823 (1.5752)	
[2022-01-22 18:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][440/1251]	eta 0:30:27 lr 0.000451	time 2.2049 (2.2535)	loss 3.3536 (3.5078)	grad_norm 1.6326 (1.5764)	
[2022-01-22 18:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][450/1251]	eta 0:29:59 lr 0.000451	time 1.6787 (2.2461)	loss 2.7151 (3.4981)	grad_norm 1.5446 (1.5764)	
[2022-01-22 18:03:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][460/1251]	eta 0:29:35 lr 0.000451	time 2.0075 (2.2449)	loss 3.3235 (3.4939)	grad_norm 1.6310 (1.5773)	
[2022-01-22 18:03:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][470/1251]	eta 0:29:16 lr 0.000451	time 1.6007 (2.2487)	loss 3.7862 (3.4903)	grad_norm 1.6515 (1.5783)	
[2022-01-22 18:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][480/1251]	eta 0:28:50 lr 0.000451	time 1.8741 (2.2439)	loss 2.3796 (3.4892)	grad_norm 2.3139 (1.5789)	
[2022-01-22 18:04:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][490/1251]	eta 0:28:24 lr 0.000451	time 1.9088 (2.2404)	loss 4.1014 (3.4872)	grad_norm 2.0259 (1.5805)	
[2022-01-22 18:04:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][500/1251]	eta 0:28:01 lr 0.000451	time 1.9036 (2.2388)	loss 2.8070 (3.4829)	grad_norm 1.4316 (1.5795)	
[2022-01-22 18:04:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][510/1251]	eta 0:27:42 lr 0.000451	time 1.8040 (2.2430)	loss 2.8820 (3.4841)	grad_norm 1.4845 (1.5781)	
[2022-01-22 18:05:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][520/1251]	eta 0:27:21 lr 0.000451	time 2.9376 (2.2452)	loss 3.8284 (3.4823)	grad_norm 1.4852 (1.5784)	
[2022-01-22 18:05:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][530/1251]	eta 0:26:57 lr 0.000451	time 1.8636 (2.2438)	loss 3.3676 (3.4822)	grad_norm 1.9408 (1.5796)	
[2022-01-22 18:05:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][540/1251]	eta 0:26:32 lr 0.000451	time 1.7653 (2.2398)	loss 2.4219 (3.4812)	grad_norm 1.3905 (1.5810)	
[2022-01-22 18:06:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][550/1251]	eta 0:26:09 lr 0.000451	time 2.0444 (2.2395)	loss 3.2667 (3.4758)	grad_norm 1.6586 (1.5806)	
[2022-01-22 18:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][560/1251]	eta 0:25:45 lr 0.000451	time 1.9454 (2.2371)	loss 4.1288 (3.4775)	grad_norm 1.5887 (1.5810)	
[2022-01-22 18:07:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][570/1251]	eta 0:25:22 lr 0.000451	time 1.9668 (2.2350)	loss 2.4549 (3.4704)	grad_norm 1.3162 (1.5799)	
[2022-01-22 18:07:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][580/1251]	eta 0:24:58 lr 0.000451	time 2.1352 (2.2337)	loss 3.5781 (3.4738)	grad_norm 1.4827 (1.5786)	
[2022-01-22 18:07:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][590/1251]	eta 0:24:35 lr 0.000451	time 1.8774 (2.2324)	loss 2.9436 (3.4749)	grad_norm 2.0841 (1.5793)	
[2022-01-22 18:08:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][600/1251]	eta 0:24:12 lr 0.000451	time 2.2355 (2.2314)	loss 4.2289 (3.4778)	grad_norm 1.7560 (1.5803)	
[2022-01-22 18:08:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][610/1251]	eta 0:23:49 lr 0.000451	time 1.8682 (2.2303)	loss 3.9714 (3.4770)	grad_norm 1.5520 (1.5808)	
[2022-01-22 18:08:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][620/1251]	eta 0:23:28 lr 0.000451	time 2.8346 (2.2319)	loss 3.3391 (3.4782)	grad_norm 1.6428 (1.5800)	
[2022-01-22 18:09:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][630/1251]	eta 0:23:04 lr 0.000451	time 1.8568 (2.2302)	loss 4.0715 (3.4747)	grad_norm 1.6993 (1.5795)	
[2022-01-22 18:09:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][640/1251]	eta 0:22:41 lr 0.000451	time 2.4433 (2.2279)	loss 4.1089 (3.4749)	grad_norm 1.7176 (1.5804)	
[2022-01-22 18:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][650/1251]	eta 0:22:17 lr 0.000451	time 1.7851 (2.2263)	loss 2.7085 (3.4774)	grad_norm 1.4646 (1.5805)	
[2022-01-22 18:10:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][660/1251]	eta 0:21:56 lr 0.000451	time 3.0733 (2.2280)	loss 3.7697 (3.4716)	grad_norm 1.6813 (1.5824)	
[2022-01-22 18:10:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][670/1251]	eta 0:21:34 lr 0.000450	time 2.0710 (2.2276)	loss 3.6458 (3.4754)	grad_norm 1.4077 (1.5829)	
[2022-01-22 18:11:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][680/1251]	eta 0:21:11 lr 0.000450	time 2.9099 (2.2269)	loss 3.3285 (3.4771)	grad_norm 1.5014 (1.5827)	
[2022-01-22 18:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][690/1251]	eta 0:20:49 lr 0.000450	time 3.2740 (2.2280)	loss 3.1020 (3.4734)	grad_norm 1.4354 (1.5814)	
[2022-01-22 18:11:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][700/1251]	eta 0:20:26 lr 0.000450	time 2.2935 (2.2265)	loss 2.3403 (3.4744)	grad_norm 1.6524 (1.5819)	
[2022-01-22 18:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][710/1251]	eta 0:20:04 lr 0.000450	time 1.7985 (2.2255)	loss 2.8241 (3.4708)	grad_norm 1.3587 (1.5829)	
[2022-01-22 18:12:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][720/1251]	eta 0:19:42 lr 0.000450	time 3.0956 (2.2261)	loss 2.4549 (3.4728)	grad_norm 1.5590 (1.5830)	
[2022-01-22 18:12:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][730/1251]	eta 0:19:20 lr 0.000450	time 2.2541 (2.2266)	loss 3.6132 (3.4712)	grad_norm 1.3373 (1.5833)	
[2022-01-22 18:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][740/1251]	eta 0:18:57 lr 0.000450	time 1.8340 (2.2254)	loss 4.1381 (3.4700)	grad_norm 1.6498 (1.5838)	
[2022-01-22 18:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][750/1251]	eta 0:18:34 lr 0.000450	time 2.1561 (2.2238)	loss 3.3033 (3.4681)	grad_norm 1.6175 (1.5851)	
[2022-01-22 18:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][760/1251]	eta 0:18:10 lr 0.000450	time 2.7163 (2.2219)	loss 3.9186 (3.4710)	grad_norm 1.5432 (1.5853)	
[2022-01-22 18:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][770/1251]	eta 0:17:48 lr 0.000450	time 1.8948 (2.2204)	loss 3.6751 (3.4726)	grad_norm 1.6654 (1.5851)	
[2022-01-22 18:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][780/1251]	eta 0:17:25 lr 0.000450	time 1.9056 (2.2195)	loss 3.1749 (3.4726)	grad_norm 1.4874 (1.5852)	
[2022-01-22 18:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][790/1251]	eta 0:17:03 lr 0.000450	time 1.7302 (2.2203)	loss 2.9451 (3.4692)	grad_norm 1.4306 (1.5858)	
[2022-01-22 18:15:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][800/1251]	eta 0:16:42 lr 0.000450	time 3.1097 (2.2224)	loss 3.5294 (3.4680)	grad_norm 1.5034 (1.5858)	
[2022-01-22 18:15:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][810/1251]	eta 0:16:19 lr 0.000450	time 1.5528 (2.2215)	loss 3.0434 (3.4649)	grad_norm 1.3356 (1.5846)	
[2022-01-22 18:16:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][820/1251]	eta 0:15:56 lr 0.000450	time 1.9138 (2.2197)	loss 3.9274 (3.4685)	grad_norm 1.3953 (1.5841)	
[2022-01-22 18:16:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][830/1251]	eta 0:15:34 lr 0.000450	time 1.9323 (2.2188)	loss 2.9663 (3.4650)	grad_norm 1.4037 (1.5835)	
[2022-01-22 18:16:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][840/1251]	eta 0:15:10 lr 0.000450	time 1.6367 (2.2164)	loss 4.1284 (3.4662)	grad_norm 1.6971 (1.5843)	
[2022-01-22 18:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][850/1251]	eta 0:14:48 lr 0.000450	time 1.8399 (2.2160)	loss 3.4938 (3.4628)	grad_norm 1.4930 (1.5836)	
[2022-01-22 18:17:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][860/1251]	eta 0:14:26 lr 0.000450	time 1.9030 (2.2164)	loss 2.8292 (3.4651)	grad_norm 1.6242 (1.5836)	
[2022-01-22 18:17:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][870/1251]	eta 0:14:04 lr 0.000450	time 2.7511 (2.2172)	loss 3.9786 (3.4650)	grad_norm 1.6116 (1.5829)	
[2022-01-22 18:18:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][880/1251]	eta 0:13:42 lr 0.000450	time 1.9040 (2.2175)	loss 2.4025 (3.4653)	grad_norm 1.5358 (1.5818)	
[2022-01-22 18:18:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][890/1251]	eta 0:13:20 lr 0.000450	time 1.7920 (2.2168)	loss 3.1913 (3.4667)	grad_norm 1.5224 (1.5818)	
[2022-01-22 18:19:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][900/1251]	eta 0:12:57 lr 0.000450	time 2.2098 (2.2157)	loss 3.9136 (3.4685)	grad_norm 1.4285 (1.5816)	
[2022-01-22 18:19:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][910/1251]	eta 0:12:35 lr 0.000450	time 2.4778 (2.2158)	loss 2.5645 (3.4682)	grad_norm 1.4135 (1.5806)	
[2022-01-22 18:19:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][920/1251]	eta 0:12:13 lr 0.000449	time 1.7731 (2.2149)	loss 2.8739 (3.4660)	grad_norm 1.3728 (1.5797)	
[2022-01-22 18:20:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][930/1251]	eta 0:11:50 lr 0.000449	time 1.8643 (2.2128)	loss 4.0749 (3.4638)	grad_norm 2.1221 (1.5803)	
[2022-01-22 18:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][940/1251]	eta 0:11:27 lr 0.000449	time 1.9320 (2.2114)	loss 4.2402 (3.4661)	grad_norm 1.8404 (1.5809)	
[2022-01-22 18:20:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][950/1251]	eta 0:11:05 lr 0.000449	time 2.7264 (2.2110)	loss 4.1941 (3.4665)	grad_norm 1.5118 (1.5815)	
[2022-01-22 18:21:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][960/1251]	eta 0:10:43 lr 0.000449	time 2.4029 (2.2129)	loss 3.9695 (3.4651)	grad_norm 1.5996 (1.5807)	
[2022-01-22 18:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][970/1251]	eta 0:10:21 lr 0.000449	time 1.5781 (2.2129)	loss 3.7726 (3.4671)	grad_norm 1.8241 (1.5798)	
[2022-01-22 18:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][980/1251]	eta 0:09:59 lr 0.000449	time 2.5277 (2.2124)	loss 3.8751 (3.4683)	grad_norm 1.4002 (1.5795)	
[2022-01-22 18:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][990/1251]	eta 0:09:36 lr 0.000449	time 1.7296 (2.2100)	loss 3.0237 (3.4680)	grad_norm 1.5864 (1.5796)	
[2022-01-22 18:22:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1000/1251]	eta 0:09:15 lr 0.000449	time 2.4360 (2.2112)	loss 4.1729 (3.4700)	grad_norm 1.6484 (1.5796)	
[2022-01-22 18:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1010/1251]	eta 0:08:52 lr 0.000449	time 1.5726 (2.2097)	loss 2.8965 (3.4690)	grad_norm 1.4707 (1.5795)	
[2022-01-22 18:23:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1020/1251]	eta 0:08:30 lr 0.000449	time 2.3625 (2.2091)	loss 2.4357 (3.4668)	grad_norm 1.3270 (1.5810)	
[2022-01-22 18:23:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1030/1251]	eta 0:08:07 lr 0.000449	time 1.9212 (2.2075)	loss 3.5765 (3.4646)	grad_norm 1.4006 (1.5802)	
[2022-01-22 18:24:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1040/1251]	eta 0:07:45 lr 0.000449	time 2.9070 (2.2071)	loss 3.5502 (3.4643)	grad_norm 1.7314 (1.5804)	
[2022-01-22 18:24:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1050/1251]	eta 0:07:23 lr 0.000449	time 2.1850 (2.2060)	loss 3.7726 (3.4640)	grad_norm 1.5314 (1.5801)	
[2022-01-22 18:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1060/1251]	eta 0:07:01 lr 0.000449	time 1.5534 (2.2060)	loss 4.1217 (3.4626)	grad_norm 1.6714 (1.5806)	
[2022-01-22 18:25:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1070/1251]	eta 0:06:39 lr 0.000449	time 2.2908 (2.2068)	loss 2.4398 (3.4609)	grad_norm 1.4937 (1.5799)	
[2022-01-22 18:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1080/1251]	eta 0:06:17 lr 0.000449	time 2.1974 (2.2065)	loss 4.0087 (3.4624)	grad_norm 1.7640 (1.5800)	
[2022-01-22 18:25:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1090/1251]	eta 0:05:55 lr 0.000449	time 2.1939 (2.2064)	loss 3.9555 (3.4615)	grad_norm 1.9006 (1.5812)	
[2022-01-22 18:26:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1100/1251]	eta 0:05:33 lr 0.000449	time 2.1991 (2.2065)	loss 4.1356 (3.4620)	grad_norm 1.5660 (1.5810)	
[2022-01-22 18:26:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1110/1251]	eta 0:05:11 lr 0.000449	time 3.1833 (2.2073)	loss 3.5279 (3.4625)	grad_norm 1.5168 (1.5803)	
[2022-01-22 18:27:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1120/1251]	eta 0:04:49 lr 0.000449	time 1.6166 (2.2074)	loss 3.5992 (3.4632)	grad_norm 1.6886 (1.5800)	
[2022-01-22 18:27:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1130/1251]	eta 0:04:27 lr 0.000449	time 2.2563 (2.2066)	loss 2.8329 (3.4654)	grad_norm 1.5754 (1.5798)	
[2022-01-22 18:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1140/1251]	eta 0:04:04 lr 0.000449	time 1.8987 (2.2064)	loss 2.3670 (3.4667)	grad_norm 1.4427 (1.5795)	
[2022-01-22 18:28:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1150/1251]	eta 0:03:42 lr 0.000449	time 1.9698 (2.2050)	loss 2.6590 (3.4658)	grad_norm 2.5198 (1.5807)	
[2022-01-22 18:28:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1160/1251]	eta 0:03:20 lr 0.000448	time 2.1164 (2.2039)	loss 3.2388 (3.4635)	grad_norm 1.4126 (1.5810)	
[2022-01-22 18:28:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1170/1251]	eta 0:02:58 lr 0.000448	time 1.4547 (2.2038)	loss 4.3560 (3.4643)	grad_norm 1.4797 (1.5810)	
[2022-01-22 18:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1180/1251]	eta 0:02:36 lr 0.000448	time 2.1869 (2.2035)	loss 2.9133 (3.4646)	grad_norm 1.5197 (1.5812)	
[2022-01-22 18:29:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1190/1251]	eta 0:02:14 lr 0.000448	time 2.2015 (2.2036)	loss 3.9177 (3.4667)	grad_norm 1.3869 (1.5814)	
[2022-01-22 18:29:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1200/1251]	eta 0:01:52 lr 0.000448	time 1.6663 (2.2039)	loss 4.0037 (3.4683)	grad_norm 1.6338 (1.5813)	
[2022-01-22 18:30:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1210/1251]	eta 0:01:30 lr 0.000448	time 2.0531 (2.2019)	loss 4.1141 (3.4676)	grad_norm 1.6679 (1.5812)	
[2022-01-22 18:30:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1220/1251]	eta 0:01:08 lr 0.000448	time 1.9738 (2.2015)	loss 4.4528 (3.4675)	grad_norm 1.4062 (1.5810)	
[2022-01-22 18:30:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1230/1251]	eta 0:00:46 lr 0.000448	time 1.8868 (2.2016)	loss 2.7351 (3.4651)	grad_norm 1.5950 (1.5809)	
[2022-01-22 18:31:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1240/1251]	eta 0:00:24 lr 0.000448	time 2.0128 (2.2003)	loss 2.9778 (3.4614)	grad_norm 1.4141 (1.5801)	
[2022-01-22 18:31:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [160/300][1250/1251]	eta 0:00:02 lr 0.000448	time 1.1850 (2.1950)	loss 3.5581 (3.4595)	grad_norm 1.6583 (1.5798)	
[2022-01-22 18:31:33 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 160 training takes 0:45:46
[2022-01-22 18:31:33 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_160 saving......
[2022-01-22 18:31:44 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_160 saved !!!
[2022-01-22 18:32:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 15.884 (15.884)	Loss 1.0632 (1.0632)	Acc@1 74.902 (74.902)	Acc@5 93.945 (93.945)	
[2022-01-22 18:32:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.988 (2.670)	Loss 0.9686 (1.0154)	Acc@1 77.539 (76.323)	Acc@5 93.945 (93.422)	
[2022-01-22 18:32:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.893 (2.122)	Loss 0.9508 (1.0102)	Acc@1 77.246 (76.414)	Acc@5 93.652 (93.541)	
[2022-01-22 18:32:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.243 (2.072)	Loss 1.0584 (1.0156)	Acc@1 75.684 (76.421)	Acc@5 92.871 (93.381)	
[2022-01-22 18:33:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.305 (2.016)	Loss 0.9237 (1.0171)	Acc@1 79.102 (76.420)	Acc@5 94.043 (93.400)	
[2022-01-22 18:33:14 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.556 Acc@5 93.406
[2022-01-22 18:33:14 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.6%
[2022-01-22 18:33:14 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.56%
[2022-01-22 18:33:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][0/1251]	eta 7:24:36 lr 0.000448	time 21.3242 (21.3242)	loss 3.6099 (3.6099)	grad_norm 1.4698 (1.4698)	
[2022-01-22 18:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][10/1251]	eta 1:24:26 lr 0.000448	time 2.2603 (4.0827)	loss 3.7870 (3.2597)	grad_norm 1.4812 (1.5005)	
[2022-01-22 18:34:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][20/1251]	eta 1:04:51 lr 0.000448	time 2.4572 (3.1612)	loss 3.7224 (3.4603)	grad_norm 1.7454 (1.5250)	
[2022-01-22 18:34:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][30/1251]	eta 0:57:26 lr 0.000448	time 1.5759 (2.8229)	loss 2.2965 (3.4341)	grad_norm 1.4931 (1.5214)	
[2022-01-22 18:35:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][40/1251]	eta 0:54:42 lr 0.000448	time 3.5224 (2.7102)	loss 3.7961 (3.4158)	grad_norm 1.4267 (1.5372)	
[2022-01-22 18:35:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][50/1251]	eta 0:53:26 lr 0.000448	time 3.0876 (2.6700)	loss 3.7207 (3.4122)	grad_norm 1.8267 (1.5450)	
[2022-01-22 18:35:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][60/1251]	eta 0:52:03 lr 0.000448	time 2.5350 (2.6224)	loss 3.9790 (3.4169)	grad_norm 1.4392 (1.5538)	
[2022-01-22 18:36:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][70/1251]	eta 0:50:21 lr 0.000448	time 1.5898 (2.5588)	loss 3.8551 (3.4217)	grad_norm 2.4692 (1.5704)	
[2022-01-22 18:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][80/1251]	eta 0:48:54 lr 0.000448	time 2.8346 (2.5057)	loss 3.2393 (3.4037)	grad_norm 1.5948 (1.5602)	
[2022-01-22 18:36:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][90/1251]	eta 0:47:22 lr 0.000448	time 2.2927 (2.4483)	loss 4.0809 (3.3935)	grad_norm 1.4415 (1.5621)	
[2022-01-22 18:37:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][100/1251]	eta 0:46:14 lr 0.000448	time 1.9245 (2.4107)	loss 3.2202 (3.3917)	grad_norm 1.3980 (1.5589)	
[2022-01-22 18:37:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][110/1251]	eta 0:45:14 lr 0.000448	time 1.9373 (2.3794)	loss 3.5252 (3.4047)	grad_norm 1.3508 (1.5616)	
[2022-01-22 18:38:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][120/1251]	eta 0:44:47 lr 0.000448	time 3.2988 (2.3765)	loss 3.3153 (3.3920)	grad_norm 1.5557 (1.5636)	
[2022-01-22 18:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][130/1251]	eta 0:44:20 lr 0.000448	time 1.6460 (2.3735)	loss 3.4859 (3.3953)	grad_norm 1.9943 (1.5669)	
[2022-01-22 18:38:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][140/1251]	eta 0:43:49 lr 0.000448	time 1.3829 (2.3668)	loss 3.3380 (3.3781)	grad_norm 1.5441 (1.5682)	
[2022-01-22 18:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][150/1251]	eta 0:43:17 lr 0.000447	time 1.8556 (2.3596)	loss 3.5003 (3.3994)	grad_norm 1.4126 (1.5646)	
[2022-01-22 18:39:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][160/1251]	eta 0:42:45 lr 0.000447	time 2.5947 (2.3514)	loss 3.0184 (3.4057)	grad_norm 1.5356 (1.5603)	
[2022-01-22 18:39:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][170/1251]	eta 0:42:04 lr 0.000447	time 2.6652 (2.3354)	loss 3.6048 (3.4160)	grad_norm 1.7471 (1.5569)	
[2022-01-22 18:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][180/1251]	eta 0:41:26 lr 0.000447	time 1.8530 (2.3217)	loss 2.6770 (3.4181)	grad_norm 1.5237 (1.5581)	
[2022-01-22 18:40:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][190/1251]	eta 0:40:52 lr 0.000447	time 1.8967 (2.3113)	loss 2.6500 (3.4083)	grad_norm 1.6746 (1.5578)	
[2022-01-22 18:40:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][200/1251]	eta 0:40:23 lr 0.000447	time 1.8950 (2.3064)	loss 3.5957 (3.4137)	grad_norm 1.5071 (1.5592)	
[2022-01-22 18:41:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][210/1251]	eta 0:39:53 lr 0.000447	time 2.1782 (2.2994)	loss 3.9711 (3.4210)	grad_norm 1.5294 (1.5553)	
[2022-01-22 18:41:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][220/1251]	eta 0:39:28 lr 0.000447	time 2.7910 (2.2976)	loss 3.0145 (3.4267)	grad_norm 1.5354 (1.5565)	
[2022-01-22 18:42:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][230/1251]	eta 0:38:55 lr 0.000447	time 1.9507 (2.2875)	loss 3.0823 (3.4302)	grad_norm 1.8711 (1.5622)	
[2022-01-22 18:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][240/1251]	eta 0:38:27 lr 0.000447	time 1.9595 (2.2821)	loss 3.4462 (3.4397)	grad_norm 1.3431 (1.5603)	
[2022-01-22 18:42:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][250/1251]	eta 0:38:00 lr 0.000447	time 2.8266 (2.2784)	loss 2.9809 (3.4418)	grad_norm 1.6091 (1.5642)	
[2022-01-22 18:43:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][260/1251]	eta 0:37:30 lr 0.000447	time 1.6461 (2.2706)	loss 2.9588 (3.4475)	grad_norm 1.8122 (1.5684)	
[2022-01-22 18:43:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][270/1251]	eta 0:37:01 lr 0.000447	time 1.9279 (2.2650)	loss 3.6681 (3.4559)	grad_norm 1.3302 (1.5684)	
[2022-01-22 18:43:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][280/1251]	eta 0:36:38 lr 0.000447	time 2.2305 (2.2638)	loss 3.2883 (3.4492)	grad_norm 1.3647 (1.5680)	
[2022-01-22 18:44:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][290/1251]	eta 0:36:16 lr 0.000447	time 2.9385 (2.2648)	loss 3.4975 (3.4431)	grad_norm 2.5863 (1.5733)	
[2022-01-22 18:44:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][300/1251]	eta 0:35:48 lr 0.000447	time 1.8611 (2.2592)	loss 4.0026 (3.4419)	grad_norm 1.4104 (1.5723)	
[2022-01-22 18:44:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][310/1251]	eta 0:35:22 lr 0.000447	time 2.5390 (2.2557)	loss 4.0219 (3.4484)	grad_norm 1.8112 (1.5734)	
[2022-01-22 18:45:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][320/1251]	eta 0:34:58 lr 0.000447	time 1.5767 (2.2540)	loss 3.8359 (3.4437)	grad_norm 1.4385 (1.5721)	
[2022-01-22 18:45:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][330/1251]	eta 0:34:34 lr 0.000447	time 2.5932 (2.2528)	loss 3.9161 (3.4465)	grad_norm 1.5666 (1.5712)	
[2022-01-22 18:46:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][340/1251]	eta 0:34:08 lr 0.000447	time 1.9111 (2.2488)	loss 3.5669 (3.4480)	grad_norm 1.3674 (1.5704)	
[2022-01-22 18:46:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][350/1251]	eta 0:33:47 lr 0.000447	time 2.2604 (2.2507)	loss 3.8910 (3.4499)	grad_norm 1.6016 (1.5689)	
[2022-01-22 18:46:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][360/1251]	eta 0:33:24 lr 0.000447	time 1.9821 (2.2498)	loss 2.8143 (3.4481)	grad_norm 1.3541 (1.5734)	
[2022-01-22 18:47:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][370/1251]	eta 0:33:04 lr 0.000447	time 2.5265 (2.2531)	loss 3.0701 (3.4509)	grad_norm 1.4465 (1.5769)	
[2022-01-22 18:47:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][380/1251]	eta 0:32:40 lr 0.000447	time 1.8785 (2.2505)	loss 3.0078 (3.4528)	grad_norm 1.5290 (1.5748)	
[2022-01-22 18:47:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][390/1251]	eta 0:32:12 lr 0.000447	time 2.6072 (2.2445)	loss 3.9857 (3.4577)	grad_norm 1.4602 (1.5746)	
[2022-01-22 18:48:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][400/1251]	eta 0:31:46 lr 0.000446	time 1.9132 (2.2406)	loss 4.3555 (3.4661)	grad_norm 1.3784 (1.5748)	
[2022-01-22 18:48:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][410/1251]	eta 0:31:19 lr 0.000446	time 1.6205 (2.2343)	loss 4.3890 (3.4734)	grad_norm 1.6030 (1.5730)	
[2022-01-22 18:48:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][420/1251]	eta 0:30:52 lr 0.000446	time 2.1715 (2.2294)	loss 2.7250 (3.4756)	grad_norm 1.4111 (1.5719)	
[2022-01-22 18:49:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][430/1251]	eta 0:30:28 lr 0.000446	time 2.5206 (2.2276)	loss 3.5922 (3.4705)	grad_norm 2.0201 (1.5733)	
[2022-01-22 18:49:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][440/1251]	eta 0:30:07 lr 0.000446	time 2.1844 (2.2292)	loss 2.8159 (3.4706)	grad_norm 1.6446 (1.5748)	
[2022-01-22 18:49:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][450/1251]	eta 0:29:43 lr 0.000446	time 1.6513 (2.2264)	loss 3.9177 (3.4779)	grad_norm 1.5231 (1.5741)	
[2022-01-22 18:50:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][460/1251]	eta 0:29:21 lr 0.000446	time 2.2975 (2.2272)	loss 3.5653 (3.4751)	grad_norm 1.5843 (1.5733)	
[2022-01-22 18:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][470/1251]	eta 0:28:58 lr 0.000446	time 2.2600 (2.2265)	loss 3.1599 (3.4782)	grad_norm 1.5896 (1.5723)	
[2022-01-22 18:51:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][480/1251]	eta 0:28:39 lr 0.000446	time 2.4327 (2.2297)	loss 2.4699 (3.4715)	grad_norm 1.5770 (1.5753)	
[2022-01-22 18:51:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][490/1251]	eta 0:28:17 lr 0.000446	time 1.8549 (2.2307)	loss 3.4290 (3.4728)	grad_norm 1.8477 (1.5789)	
[2022-01-22 18:51:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][500/1251]	eta 0:27:55 lr 0.000446	time 2.6610 (2.2312)	loss 3.1114 (3.4730)	grad_norm 1.4396 (1.5826)	
[2022-01-22 18:52:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][510/1251]	eta 0:27:29 lr 0.000446	time 1.6463 (2.2265)	loss 2.6155 (3.4750)	grad_norm 2.0999 (1.5841)	
[2022-01-22 18:52:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][520/1251]	eta 0:27:08 lr 0.000446	time 2.8378 (2.2279)	loss 3.4218 (3.4718)	grad_norm 1.4984 (1.5835)	
[2022-01-22 18:52:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][530/1251]	eta 0:26:44 lr 0.000446	time 1.9491 (2.2254)	loss 4.3351 (3.4741)	grad_norm 1.4041 (1.5814)	
[2022-01-22 18:53:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][540/1251]	eta 0:26:22 lr 0.000446	time 2.8038 (2.2258)	loss 4.0104 (3.4741)	grad_norm 1.4296 (1.5800)	
[2022-01-22 18:53:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][550/1251]	eta 0:25:59 lr 0.000446	time 1.6175 (2.2247)	loss 3.3852 (3.4760)	grad_norm 1.5225 (1.5803)	
[2022-01-22 18:54:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][560/1251]	eta 0:25:37 lr 0.000446	time 2.3645 (2.2253)	loss 2.6489 (3.4761)	grad_norm 1.6575 (1.5805)	
[2022-01-22 18:54:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][570/1251]	eta 0:25:14 lr 0.000446	time 1.9076 (2.2234)	loss 2.6349 (3.4742)	grad_norm 1.7185 (1.5806)	
[2022-01-22 18:54:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][580/1251]	eta 0:24:50 lr 0.000446	time 2.6037 (2.2210)	loss 3.6624 (3.4739)	grad_norm 1.4999 (1.5807)	
[2022-01-22 18:55:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][590/1251]	eta 0:24:27 lr 0.000446	time 2.0352 (2.2198)	loss 3.0898 (3.4793)	grad_norm 1.4790 (1.5803)	
[2022-01-22 18:55:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][600/1251]	eta 0:24:03 lr 0.000446	time 2.2057 (2.2178)	loss 4.1844 (3.4757)	grad_norm 1.5721 (1.5808)	
[2022-01-22 18:55:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][610/1251]	eta 0:23:40 lr 0.000446	time 2.2125 (2.2155)	loss 2.8449 (3.4745)	grad_norm 1.4951 (1.5795)	
[2022-01-22 18:56:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][620/1251]	eta 0:23:17 lr 0.000446	time 2.6030 (2.2154)	loss 4.4531 (3.4803)	grad_norm 1.6027 (1.5788)	
[2022-01-22 18:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][630/1251]	eta 0:22:55 lr 0.000446	time 2.2474 (2.2154)	loss 3.7610 (3.4821)	grad_norm 1.6746 (1.5780)	
[2022-01-22 18:56:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][640/1251]	eta 0:22:34 lr 0.000445	time 2.1626 (2.2174)	loss 2.7068 (3.4796)	grad_norm 1.6039 (1.5773)	
[2022-01-22 18:57:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][650/1251]	eta 0:22:12 lr 0.000445	time 1.8288 (2.2175)	loss 3.8875 (3.4834)	grad_norm 1.4426 (1.5783)	
[2022-01-22 18:57:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][660/1251]	eta 0:21:52 lr 0.000445	time 3.3940 (2.2208)	loss 3.4762 (3.4823)	grad_norm 1.3541 (1.5772)	
[2022-01-22 18:58:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][670/1251]	eta 0:21:30 lr 0.000445	time 1.6461 (2.2204)	loss 3.6855 (3.4823)	grad_norm 1.3491 (1.5765)	
[2022-01-22 18:58:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][680/1251]	eta 0:21:07 lr 0.000445	time 1.5028 (2.2193)	loss 4.3018 (3.4797)	grad_norm 2.2222 (1.5791)	
[2022-01-22 18:58:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][690/1251]	eta 0:20:43 lr 0.000445	time 2.6069 (2.2174)	loss 4.3612 (3.4801)	grad_norm 1.5501 (1.5810)	
[2022-01-22 18:59:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][700/1251]	eta 0:20:20 lr 0.000445	time 2.1343 (2.2157)	loss 4.3526 (3.4808)	grad_norm 1.7657 (1.5806)	
[2022-01-22 18:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][710/1251]	eta 0:19:57 lr 0.000445	time 1.7797 (2.2140)	loss 3.1792 (3.4808)	grad_norm 1.6296 (1.5817)	
[2022-01-22 18:59:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][720/1251]	eta 0:19:36 lr 0.000445	time 2.4605 (2.2148)	loss 3.8259 (3.4830)	grad_norm 1.6137 (1.5812)	
[2022-01-22 19:00:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][730/1251]	eta 0:19:14 lr 0.000445	time 2.7381 (2.2153)	loss 3.5784 (3.4841)	grad_norm 1.4779 (1.5813)	
[2022-01-22 19:00:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][740/1251]	eta 0:18:51 lr 0.000445	time 2.3181 (2.2140)	loss 3.5468 (3.4858)	grad_norm 1.5971 (1.5817)	
[2022-01-22 19:00:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][750/1251]	eta 0:18:29 lr 0.000445	time 2.0420 (2.2137)	loss 3.0799 (3.4862)	grad_norm 1.5017 (1.5829)	
[2022-01-22 19:01:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][760/1251]	eta 0:18:07 lr 0.000445	time 2.2020 (2.2142)	loss 3.9584 (3.4865)	grad_norm 1.6816 (1.5832)	
[2022-01-22 19:01:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][770/1251]	eta 0:17:45 lr 0.000445	time 2.7880 (2.2143)	loss 4.2829 (3.4863)	grad_norm 1.4374 (1.5839)	
[2022-01-22 19:02:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][780/1251]	eta 0:17:21 lr 0.000445	time 2.1006 (2.2118)	loss 3.8614 (3.4884)	grad_norm 1.7009 (1.5839)	
[2022-01-22 19:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][790/1251]	eta 0:16:58 lr 0.000445	time 1.8234 (2.2095)	loss 2.5877 (3.4906)	grad_norm 1.6120 (1.5835)	
[2022-01-22 19:02:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][800/1251]	eta 0:16:35 lr 0.000445	time 2.2660 (2.2078)	loss 3.8214 (3.4900)	grad_norm 1.8522 (1.5841)	
[2022-01-22 19:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][810/1251]	eta 0:16:13 lr 0.000445	time 1.6450 (2.2080)	loss 3.7910 (3.4903)	grad_norm 1.3993 (1.5855)	
[2022-01-22 19:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][820/1251]	eta 0:15:51 lr 0.000445	time 1.7898 (2.2076)	loss 3.4567 (3.4902)	grad_norm 1.6504 (1.5873)	
[2022-01-22 19:03:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][830/1251]	eta 0:15:29 lr 0.000445	time 2.1950 (2.2089)	loss 2.6794 (3.4873)	grad_norm 1.9866 (1.5882)	
[2022-01-22 19:04:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][840/1251]	eta 0:15:08 lr 0.000445	time 2.7750 (2.2111)	loss 3.1414 (3.4850)	grad_norm 1.7550 (1.5886)	
[2022-01-22 19:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][850/1251]	eta 0:14:47 lr 0.000445	time 2.2050 (2.2131)	loss 3.9562 (3.4899)	grad_norm 1.6379 (1.5884)	
[2022-01-22 19:04:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][860/1251]	eta 0:14:24 lr 0.000445	time 1.6534 (2.2119)	loss 2.1876 (3.4926)	grad_norm 1.6794 (1.5886)	
[2022-01-22 19:05:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][870/1251]	eta 0:14:02 lr 0.000445	time 1.8119 (2.2107)	loss 2.5068 (3.4948)	grad_norm 1.7443 (1.5883)	
[2022-01-22 19:05:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][880/1251]	eta 0:13:39 lr 0.000444	time 2.4735 (2.2091)	loss 3.9541 (3.4907)	grad_norm 1.5279 (1.5892)	
[2022-01-22 19:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][890/1251]	eta 0:13:16 lr 0.000444	time 1.8241 (2.2072)	loss 4.2125 (3.4916)	grad_norm 1.5980 (1.5895)	
[2022-01-22 19:06:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][900/1251]	eta 0:12:54 lr 0.000444	time 2.4214 (2.2070)	loss 3.7735 (3.4946)	grad_norm 1.5363 (1.5893)	
[2022-01-22 19:06:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][910/1251]	eta 0:12:32 lr 0.000444	time 2.1184 (2.2066)	loss 4.3881 (3.4955)	grad_norm 1.4906 (1.5892)	
[2022-01-22 19:07:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][920/1251]	eta 0:12:10 lr 0.000444	time 2.2536 (2.2064)	loss 4.1375 (3.4957)	grad_norm 1.3476 (1.5886)	
[2022-01-22 19:07:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][930/1251]	eta 0:11:48 lr 0.000444	time 2.2562 (2.2071)	loss 3.0583 (3.4940)	grad_norm 1.4791 (1.5872)	
[2022-01-22 19:07:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][940/1251]	eta 0:11:26 lr 0.000444	time 2.8454 (2.2076)	loss 3.2261 (3.4926)	grad_norm 1.7062 (1.5881)	
[2022-01-22 19:08:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][950/1251]	eta 0:11:05 lr 0.000444	time 2.7281 (2.2095)	loss 3.3627 (3.4932)	grad_norm 1.5415 (1.5889)	
[2022-01-22 19:08:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][960/1251]	eta 0:10:42 lr 0.000444	time 2.2039 (2.2087)	loss 3.4428 (3.4931)	grad_norm 1.5684 (1.5887)	
[2022-01-22 19:08:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][970/1251]	eta 0:10:20 lr 0.000444	time 2.2404 (2.2089)	loss 3.6758 (3.4960)	grad_norm 1.5723 (1.5887)	
[2022-01-22 19:09:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][980/1251]	eta 0:09:58 lr 0.000444	time 1.8606 (2.2078)	loss 3.5844 (3.4980)	grad_norm 1.3152 (1.5879)	
[2022-01-22 19:09:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][990/1251]	eta 0:09:35 lr 0.000444	time 1.6997 (2.2063)	loss 3.7542 (3.4971)	grad_norm 1.4986 (1.5870)	
[2022-01-22 19:10:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1000/1251]	eta 0:09:13 lr 0.000444	time 1.8980 (2.2048)	loss 3.7998 (3.4976)	grad_norm 1.3839 (1.5869)	
[2022-01-22 19:10:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1010/1251]	eta 0:08:51 lr 0.000444	time 2.1981 (2.2041)	loss 4.1699 (3.4980)	grad_norm 1.5120 (1.5864)	
[2022-01-22 19:10:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1020/1251]	eta 0:08:29 lr 0.000444	time 2.1534 (2.2048)	loss 2.7189 (3.4976)	grad_norm 1.5409 (1.5862)	
[2022-01-22 19:11:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1030/1251]	eta 0:08:07 lr 0.000444	time 1.9303 (2.2040)	loss 3.8902 (3.4989)	grad_norm 1.4871 (1.5853)	
[2022-01-22 19:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1040/1251]	eta 0:07:45 lr 0.000444	time 2.1562 (2.2046)	loss 2.6377 (3.4986)	grad_norm 1.7921 (1.5851)	
[2022-01-22 19:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1050/1251]	eta 0:07:23 lr 0.000444	time 2.1543 (2.2049)	loss 3.9183 (3.4988)	grad_norm 1.9502 (1.5848)	
[2022-01-22 19:12:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1060/1251]	eta 0:07:01 lr 0.000444	time 1.6078 (2.2050)	loss 3.5047 (3.4957)	grad_norm 1.4986 (1.5845)	
[2022-01-22 19:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1070/1251]	eta 0:06:39 lr 0.000444	time 1.8482 (2.2049)	loss 2.5436 (3.4932)	grad_norm 1.6692 (1.5850)	
[2022-01-22 19:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1080/1251]	eta 0:06:16 lr 0.000444	time 1.6037 (2.2042)	loss 3.4720 (3.4930)	grad_norm 1.6349 (1.5844)	
[2022-01-22 19:13:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1090/1251]	eta 0:05:54 lr 0.000444	time 2.1369 (2.2045)	loss 3.6840 (3.4948)	grad_norm 1.5475 (1.5838)	
[2022-01-22 19:13:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1100/1251]	eta 0:05:32 lr 0.000444	time 1.8288 (2.2029)	loss 4.0140 (3.4963)	grad_norm 1.5535 (1.5829)	
[2022-01-22 19:14:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1110/1251]	eta 0:05:10 lr 0.000444	time 2.0219 (2.2026)	loss 2.6293 (3.4944)	grad_norm 1.4827 (1.5818)	
[2022-01-22 19:14:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1120/1251]	eta 0:04:48 lr 0.000443	time 2.1298 (2.2023)	loss 3.9329 (3.4968)	grad_norm 1.6219 (1.5808)	
[2022-01-22 19:14:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1130/1251]	eta 0:04:26 lr 0.000443	time 1.9067 (2.2020)	loss 3.4729 (3.4971)	grad_norm 1.6550 (1.5812)	
[2022-01-22 19:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1140/1251]	eta 0:04:04 lr 0.000443	time 1.8575 (2.2011)	loss 3.9331 (3.4986)	grad_norm 1.6693 (1.5813)	
[2022-01-22 19:15:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1150/1251]	eta 0:03:42 lr 0.000443	time 2.2249 (2.2009)	loss 3.8411 (3.4991)	grad_norm 1.4785 (1.5811)	
[2022-01-22 19:15:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1160/1251]	eta 0:03:20 lr 0.000443	time 2.4640 (2.2010)	loss 2.2207 (3.4979)	grad_norm 1.5047 (1.5812)	
[2022-01-22 19:16:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1170/1251]	eta 0:02:58 lr 0.000443	time 2.8372 (2.2022)	loss 3.0825 (3.4958)	grad_norm 1.4938 (1.5805)	
[2022-01-22 19:16:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1180/1251]	eta 0:02:36 lr 0.000443	time 2.2125 (2.2011)	loss 2.9490 (3.4948)	grad_norm 1.4634 (1.5801)	
[2022-01-22 19:16:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1190/1251]	eta 0:02:14 lr 0.000443	time 2.2388 (2.2010)	loss 2.6333 (3.4950)	grad_norm 1.4863 (1.5801)	
[2022-01-22 19:17:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1200/1251]	eta 0:01:52 lr 0.000443	time 2.9964 (2.2013)	loss 3.5917 (3.4966)	grad_norm 1.5438 (1.5795)	
[2022-01-22 19:17:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1210/1251]	eta 0:01:30 lr 0.000443	time 2.5205 (2.2023)	loss 3.6424 (3.4949)	grad_norm 1.4242 (1.5786)	
[2022-01-22 19:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1220/1251]	eta 0:01:08 lr 0.000443	time 2.2386 (2.2022)	loss 3.6395 (3.4935)	grad_norm 1.4559 (1.5782)	
[2022-01-22 19:18:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1230/1251]	eta 0:00:46 lr 0.000443	time 2.2417 (2.2019)	loss 4.0373 (3.4952)	grad_norm 1.3145 (1.5786)	
[2022-01-22 19:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1240/1251]	eta 0:00:24 lr 0.000443	time 1.6570 (2.2009)	loss 4.2297 (3.4979)	grad_norm 1.7784 (1.5786)	
[2022-01-22 19:19:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [161/300][1250/1251]	eta 0:00:02 lr 0.000443	time 1.1695 (2.1957)	loss 3.3583 (3.4983)	grad_norm 1.5259 (1.5781)	
[2022-01-22 19:19:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 161 training takes 0:45:47
[2022-01-22 19:19:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.916 (18.916)	Loss 0.9207 (0.9207)	Acc@1 78.223 (78.223)	Acc@5 94.043 (94.043)	
[2022-01-22 19:19:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.944 (3.501)	Loss 0.9997 (0.9780)	Acc@1 75.098 (76.926)	Acc@5 93.359 (93.581)	
[2022-01-22 19:19:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.351 (2.612)	Loss 1.0061 (0.9860)	Acc@1 74.902 (76.767)	Acc@5 93.359 (93.508)	
[2022-01-22 19:20:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.251 (2.369)	Loss 0.8647 (0.9840)	Acc@1 78.516 (76.714)	Acc@5 95.508 (93.586)	
[2022-01-22 19:20:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.713 (2.201)	Loss 1.0588 (0.9857)	Acc@1 74.805 (76.655)	Acc@5 92.578 (93.526)	
[2022-01-22 19:20:39 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.650 Acc@5 93.540
[2022-01-22 19:20:39 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.7%
[2022-01-22 19:20:39 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.65%
[2022-01-22 19:21:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][0/1251]	eta 7:38:35 lr 0.000443	time 21.9950 (21.9950)	loss 2.8408 (2.8408)	grad_norm 1.7174 (1.7174)	
[2022-01-22 19:21:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][10/1251]	eta 1:25:56 lr 0.000443	time 2.1645 (4.1555)	loss 3.8664 (3.4385)	grad_norm 1.5473 (1.5272)	
[2022-01-22 19:21:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][20/1251]	eta 1:05:35 lr 0.000443	time 1.4371 (3.1967)	loss 3.4504 (3.5149)	grad_norm 1.5643 (1.5599)	
[2022-01-22 19:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][30/1251]	eta 0:58:53 lr 0.000443	time 1.8897 (2.8940)	loss 3.8089 (3.4523)	grad_norm 1.6051 (1.6000)	
[2022-01-22 19:22:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][40/1251]	eta 0:56:11 lr 0.000443	time 3.9151 (2.7842)	loss 4.0170 (3.4603)	grad_norm 1.6236 (1.6156)	
[2022-01-22 19:22:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][50/1251]	eta 0:54:07 lr 0.000443	time 2.9681 (2.7040)	loss 3.0663 (3.4574)	grad_norm 2.0544 (1.6158)	
[2022-01-22 19:23:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][60/1251]	eta 0:51:25 lr 0.000443	time 1.5540 (2.5910)	loss 3.3223 (3.4332)	grad_norm 1.4941 (1.6066)	
[2022-01-22 19:23:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][70/1251]	eta 0:49:28 lr 0.000443	time 1.6815 (2.5138)	loss 2.3527 (3.4149)	grad_norm 1.6722 (1.6196)	
[2022-01-22 19:24:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][80/1251]	eta 0:48:29 lr 0.000443	time 4.1120 (2.4845)	loss 3.7623 (3.3766)	grad_norm 1.4948 (1.6049)	
[2022-01-22 19:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][90/1251]	eta 0:47:34 lr 0.000443	time 1.7510 (2.4585)	loss 4.1147 (3.3999)	grad_norm 1.7758 (1.6009)	
[2022-01-22 19:24:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][100/1251]	eta 0:46:39 lr 0.000443	time 1.9328 (2.4325)	loss 3.4292 (3.4158)	grad_norm 1.5156 (1.5936)	
[2022-01-22 19:25:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][110/1251]	eta 0:45:37 lr 0.000443	time 1.8920 (2.3996)	loss 2.5217 (3.4290)	grad_norm 1.8987 (1.5942)	
[2022-01-22 19:25:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][120/1251]	eta 0:44:46 lr 0.000442	time 2.0744 (2.3749)	loss 2.8141 (3.4162)	grad_norm 1.4969 (1.5920)	
[2022-01-22 19:25:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][130/1251]	eta 0:43:51 lr 0.000442	time 2.1233 (2.3473)	loss 3.7883 (3.4336)	grad_norm 1.9348 (1.5923)	
[2022-01-22 19:26:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][140/1251]	eta 0:43:22 lr 0.000442	time 2.0374 (2.3427)	loss 4.0297 (3.4418)	grad_norm 1.5813 (1.5936)	
[2022-01-22 19:26:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][150/1251]	eta 0:42:47 lr 0.000442	time 2.7296 (2.3323)	loss 3.0996 (3.4336)	grad_norm 1.4621 (1.5954)	
[2022-01-22 19:26:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][160/1251]	eta 0:42:17 lr 0.000442	time 2.3624 (2.3255)	loss 3.7421 (3.4298)	grad_norm 1.4519 (1.5959)	
[2022-01-22 19:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][170/1251]	eta 0:41:45 lr 0.000442	time 2.5699 (2.3175)	loss 3.3523 (3.4307)	grad_norm 1.6572 (1.5928)	
[2022-01-22 19:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][180/1251]	eta 0:41:12 lr 0.000442	time 2.3911 (2.3082)	loss 2.9938 (3.4276)	grad_norm 1.7932 (1.5943)	
[2022-01-22 19:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][190/1251]	eta 0:40:43 lr 0.000442	time 1.9357 (2.3033)	loss 2.9086 (3.4307)	grad_norm 1.7134 (1.5947)	
[2022-01-22 19:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][200/1251]	eta 0:40:09 lr 0.000442	time 1.5773 (2.2929)	loss 3.5541 (3.4310)	grad_norm 1.4514 (1.5903)	
[2022-01-22 19:28:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][210/1251]	eta 0:39:38 lr 0.000442	time 2.2054 (2.2848)	loss 3.9102 (3.4204)	grad_norm 1.4388 (1.5862)	
[2022-01-22 19:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][220/1251]	eta 0:39:06 lr 0.000442	time 1.9677 (2.2755)	loss 3.3295 (3.4189)	grad_norm 1.6689 (1.5819)	
[2022-01-22 19:29:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][230/1251]	eta 0:38:32 lr 0.000442	time 1.8732 (2.2650)	loss 2.9945 (3.4237)	grad_norm 1.4948 (1.5801)	
[2022-01-22 19:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][240/1251]	eta 0:38:05 lr 0.000442	time 1.5874 (2.2604)	loss 3.9828 (3.4205)	grad_norm 1.4799 (1.5811)	
[2022-01-22 19:30:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][250/1251]	eta 0:37:43 lr 0.000442	time 3.1495 (2.2611)	loss 3.2633 (3.4235)	grad_norm 1.5707 (1.5804)	
[2022-01-22 19:30:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][260/1251]	eta 0:37:23 lr 0.000442	time 2.0704 (2.2640)	loss 2.8026 (3.4145)	grad_norm 1.6617 (1.5805)	
[2022-01-22 19:30:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][270/1251]	eta 0:37:01 lr 0.000442	time 1.9556 (2.2643)	loss 2.8347 (3.4140)	grad_norm 1.4567 (1.5801)	
[2022-01-22 19:31:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][280/1251]	eta 0:36:41 lr 0.000442	time 1.8522 (2.2676)	loss 3.6392 (3.4132)	grad_norm 1.5028 (1.5775)	
[2022-01-22 19:31:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][290/1251]	eta 0:36:22 lr 0.000442	time 3.0467 (2.2709)	loss 3.8616 (3.4194)	grad_norm 1.5020 (1.5786)	
[2022-01-22 19:32:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][300/1251]	eta 0:35:49 lr 0.000442	time 1.8340 (2.2604)	loss 3.7436 (3.4292)	grad_norm 1.3916 (1.5785)	
[2022-01-22 19:32:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][310/1251]	eta 0:35:15 lr 0.000442	time 1.9613 (2.2485)	loss 3.5763 (3.4371)	grad_norm 1.5453 (1.5796)	
[2022-01-22 19:32:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][320/1251]	eta 0:34:45 lr 0.000442	time 1.9070 (2.2401)	loss 2.9048 (3.4354)	grad_norm 1.4263 (1.5813)	
[2022-01-22 19:32:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][330/1251]	eta 0:34:18 lr 0.000442	time 2.2928 (2.2348)	loss 4.0840 (3.4378)	grad_norm 1.6331 (1.5805)	
[2022-01-22 19:33:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][340/1251]	eta 0:33:55 lr 0.000442	time 2.7937 (2.2339)	loss 4.0292 (3.4337)	grad_norm 1.5136 (1.5790)	
[2022-01-22 19:33:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][350/1251]	eta 0:33:27 lr 0.000442	time 1.8487 (2.2284)	loss 3.3812 (3.4374)	grad_norm 1.9367 (1.5811)	
[2022-01-22 19:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][360/1251]	eta 0:33:04 lr 0.000441	time 2.1558 (2.2270)	loss 2.8532 (3.4367)	grad_norm 1.6043 (1.5854)	
[2022-01-22 19:34:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][370/1251]	eta 0:32:41 lr 0.000441	time 2.6133 (2.2262)	loss 3.5821 (3.4404)	grad_norm 1.5664 (1.5892)	
[2022-01-22 19:34:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][380/1251]	eta 0:32:17 lr 0.000441	time 1.6867 (2.2242)	loss 3.5826 (3.4482)	grad_norm 1.4479 (1.5884)	
[2022-01-22 19:35:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][390/1251]	eta 0:31:57 lr 0.000441	time 2.1966 (2.2265)	loss 3.5648 (3.4445)	grad_norm 1.6857 (1.5912)	
[2022-01-22 19:35:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][400/1251]	eta 0:31:35 lr 0.000441	time 2.7185 (2.2273)	loss 3.3794 (3.4480)	grad_norm 1.4512 (1.5890)	
[2022-01-22 19:35:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][410/1251]	eta 0:31:11 lr 0.000441	time 2.0957 (2.2251)	loss 4.1136 (3.4440)	grad_norm 1.4641 (1.5883)	
[2022-01-22 19:36:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][420/1251]	eta 0:30:56 lr 0.000441	time 3.0082 (2.2345)	loss 3.2260 (3.4462)	grad_norm 1.3831 (1.5867)	
[2022-01-22 19:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][430/1251]	eta 0:30:40 lr 0.000441	time 2.0975 (2.2418)	loss 2.9202 (3.4484)	grad_norm 1.5908 (1.5840)	
[2022-01-22 19:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][440/1251]	eta 0:30:19 lr 0.000441	time 2.4160 (2.2439)	loss 3.5879 (3.4507)	grad_norm 1.5608 (1.5845)	
[2022-01-22 19:37:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][450/1251]	eta 0:29:54 lr 0.000441	time 1.8562 (2.2399)	loss 3.9521 (3.4532)	grad_norm 1.5969 (1.5858)	
[2022-01-22 19:37:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][460/1251]	eta 0:29:25 lr 0.000441	time 1.8006 (2.2324)	loss 4.0065 (3.4480)	grad_norm 1.9104 (1.5878)	
[2022-01-22 19:38:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][470/1251]	eta 0:28:58 lr 0.000441	time 2.1874 (2.2265)	loss 3.5236 (3.4514)	grad_norm 1.5958 (1.5879)	
[2022-01-22 19:38:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][480/1251]	eta 0:28:33 lr 0.000441	time 1.9082 (2.2227)	loss 4.0523 (3.4511)	grad_norm 2.0683 (1.5912)	
[2022-01-22 19:38:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][490/1251]	eta 0:28:09 lr 0.000441	time 2.2061 (2.2206)	loss 2.5903 (3.4540)	grad_norm 1.4230 (1.5903)	
[2022-01-22 19:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][500/1251]	eta 0:27:44 lr 0.000441	time 1.5020 (2.2165)	loss 3.6451 (3.4573)	grad_norm 1.4995 (1.5913)	
[2022-01-22 19:39:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][510/1251]	eta 0:27:24 lr 0.000441	time 3.2012 (2.2193)	loss 3.5176 (3.4612)	grad_norm 1.8684 (1.5913)	
[2022-01-22 19:39:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][520/1251]	eta 0:27:05 lr 0.000441	time 2.6184 (2.2232)	loss 3.7414 (3.4684)	grad_norm 1.3921 (1.5918)	
[2022-01-22 19:40:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][530/1251]	eta 0:26:44 lr 0.000441	time 2.2706 (2.2260)	loss 3.5488 (3.4720)	grad_norm 1.3919 (1.5899)	
[2022-01-22 19:40:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][540/1251]	eta 0:26:22 lr 0.000441	time 2.2475 (2.2260)	loss 3.9519 (3.4763)	grad_norm 1.4350 (1.5909)	
[2022-01-22 19:41:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][550/1251]	eta 0:26:01 lr 0.000441	time 2.9382 (2.2274)	loss 4.2354 (3.4766)	grad_norm 1.4719 (1.5899)	
[2022-01-22 19:41:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][560/1251]	eta 0:25:37 lr 0.000441	time 1.9252 (2.2252)	loss 4.0488 (3.4727)	grad_norm 1.7409 (1.5905)	
[2022-01-22 19:41:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][570/1251]	eta 0:25:13 lr 0.000441	time 1.8165 (2.2222)	loss 2.7199 (3.4727)	grad_norm 1.7984 (1.5915)	
[2022-01-22 19:42:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][580/1251]	eta 0:24:49 lr 0.000441	time 2.1931 (2.2204)	loss 3.6388 (3.4711)	grad_norm 1.4679 (1.5906)	
[2022-01-22 19:42:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][590/1251]	eta 0:24:28 lr 0.000441	time 3.4798 (2.2214)	loss 4.0070 (3.4735)	grad_norm 1.5180 (1.5898)	
[2022-01-22 19:42:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][600/1251]	eta 0:24:05 lr 0.000440	time 1.8192 (2.2203)	loss 3.0213 (3.4716)	grad_norm 1.5628 (1.5905)	
[2022-01-22 19:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][610/1251]	eta 0:23:42 lr 0.000440	time 2.2407 (2.2196)	loss 2.5695 (3.4730)	grad_norm 1.6589 (1.5916)	
[2022-01-22 19:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][620/1251]	eta 0:23:22 lr 0.000440	time 2.5095 (2.2222)	loss 3.8738 (3.4747)	grad_norm 1.4762 (1.5910)	
[2022-01-22 19:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][630/1251]	eta 0:22:59 lr 0.000440	time 2.5579 (2.2221)	loss 3.2942 (3.4726)	grad_norm 1.6321 (1.5915)	
[2022-01-22 19:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][640/1251]	eta 0:22:37 lr 0.000440	time 1.5496 (2.2213)	loss 3.7627 (3.4738)	grad_norm 1.3306 (1.5909)	
[2022-01-22 19:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][650/1251]	eta 0:22:14 lr 0.000440	time 1.8871 (2.2201)	loss 4.1908 (3.4744)	grad_norm 1.5807 (1.5912)	
[2022-01-22 19:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][660/1251]	eta 0:21:50 lr 0.000440	time 1.8473 (2.2167)	loss 4.1897 (3.4735)	grad_norm 1.7504 (1.5907)	
[2022-01-22 19:45:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][670/1251]	eta 0:21:27 lr 0.000440	time 2.5213 (2.2160)	loss 4.5442 (3.4765)	grad_norm 1.5276 (1.5923)	
[2022-01-22 19:45:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][680/1251]	eta 0:21:04 lr 0.000440	time 2.1492 (2.2144)	loss 3.9341 (3.4766)	grad_norm 1.6929 (1.5936)	
[2022-01-22 19:46:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][690/1251]	eta 0:20:41 lr 0.000440	time 2.5312 (2.2137)	loss 3.1302 (3.4784)	grad_norm 1.3993 (1.5929)	
[2022-01-22 19:46:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][700/1251]	eta 0:20:19 lr 0.000440	time 2.3615 (2.2127)	loss 3.6905 (3.4811)	grad_norm 1.7442 (1.5929)	
[2022-01-22 19:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][710/1251]	eta 0:19:58 lr 0.000440	time 3.1827 (2.2159)	loss 3.6859 (3.4830)	grad_norm 1.8584 (1.5940)	
[2022-01-22 19:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][720/1251]	eta 0:19:35 lr 0.000440	time 1.8655 (2.2147)	loss 3.6429 (3.4871)	grad_norm 2.1128 (1.5945)	
[2022-01-22 19:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][730/1251]	eta 0:19:14 lr 0.000440	time 2.5310 (2.2154)	loss 3.2452 (3.4836)	grad_norm 1.6062 (1.5930)	
[2022-01-22 19:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][740/1251]	eta 0:18:50 lr 0.000440	time 1.9197 (2.2123)	loss 3.0460 (3.4844)	grad_norm 1.4219 (1.5918)	
[2022-01-22 19:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][750/1251]	eta 0:18:28 lr 0.000440	time 1.8047 (2.2120)	loss 3.1255 (3.4817)	grad_norm 1.5368 (1.5916)	
[2022-01-22 19:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][760/1251]	eta 0:18:05 lr 0.000440	time 1.5802 (2.2117)	loss 4.1891 (3.4854)	grad_norm 1.5589 (1.5910)	
[2022-01-22 19:49:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][770/1251]	eta 0:17:44 lr 0.000440	time 2.7630 (2.2124)	loss 4.1789 (3.4874)	grad_norm 1.6987 (1.5894)	
[2022-01-22 19:49:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][780/1251]	eta 0:17:21 lr 0.000440	time 1.7698 (2.2108)	loss 3.3895 (3.4884)	grad_norm 1.4220 (1.5896)	
[2022-01-22 19:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][790/1251]	eta 0:16:59 lr 0.000440	time 2.1674 (2.2119)	loss 3.8952 (3.4874)	grad_norm 1.3924 (1.5891)	
[2022-01-22 19:50:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][800/1251]	eta 0:16:37 lr 0.000440	time 1.8681 (2.2112)	loss 3.6020 (3.4869)	grad_norm 1.4449 (1.5877)	
[2022-01-22 19:50:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][810/1251]	eta 0:16:15 lr 0.000440	time 2.5808 (2.2115)	loss 3.8359 (3.4903)	grad_norm 1.4872 (1.5870)	
[2022-01-22 19:50:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][820/1251]	eta 0:15:52 lr 0.000440	time 1.9445 (2.2097)	loss 3.5060 (3.4916)	grad_norm 1.7001 (1.5875)	
[2022-01-22 19:51:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][830/1251]	eta 0:15:29 lr 0.000440	time 2.6219 (2.2080)	loss 3.7164 (3.4895)	grad_norm 1.4643 (1.5868)	
[2022-01-22 19:51:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][840/1251]	eta 0:15:06 lr 0.000440	time 1.9004 (2.2062)	loss 3.9986 (3.4883)	grad_norm 1.4423 (1.5860)	
[2022-01-22 19:51:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][850/1251]	eta 0:14:44 lr 0.000439	time 2.0827 (2.2069)	loss 4.1112 (3.4870)	grad_norm 1.3584 (1.5867)	
[2022-01-22 19:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][860/1251]	eta 0:14:22 lr 0.000439	time 2.5466 (2.2066)	loss 3.1753 (3.4903)	grad_norm 1.6510 (1.5870)	
[2022-01-22 19:52:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][870/1251]	eta 0:13:59 lr 0.000439	time 2.4563 (2.2046)	loss 4.2182 (3.4915)	grad_norm 1.4939 (1.5860)	
[2022-01-22 19:53:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][880/1251]	eta 0:13:37 lr 0.000439	time 1.9145 (2.2035)	loss 3.0245 (3.4904)	grad_norm 1.5141 (1.5859)	
[2022-01-22 19:53:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][890/1251]	eta 0:13:15 lr 0.000439	time 2.1537 (2.2028)	loss 3.1776 (3.4905)	grad_norm 1.5658 (1.5852)	
[2022-01-22 19:53:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][900/1251]	eta 0:12:52 lr 0.000439	time 1.5865 (2.2020)	loss 3.4804 (3.4892)	grad_norm 1.3670 (1.5856)	
[2022-01-22 19:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][910/1251]	eta 0:12:31 lr 0.000439	time 3.3192 (2.2041)	loss 3.8028 (3.4906)	grad_norm 1.6037 (1.5854)	
[2022-01-22 19:54:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][920/1251]	eta 0:12:10 lr 0.000439	time 1.4586 (2.2055)	loss 3.8846 (3.4898)	grad_norm 1.8615 (1.5846)	
[2022-01-22 19:54:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][930/1251]	eta 0:11:47 lr 0.000439	time 2.3932 (2.2054)	loss 3.8544 (3.4920)	grad_norm 1.4747 (1.5837)	
[2022-01-22 19:55:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][940/1251]	eta 0:11:25 lr 0.000439	time 1.7571 (2.2048)	loss 3.1210 (3.4932)	grad_norm 1.7913 (1.5839)	
[2022-01-22 19:55:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][950/1251]	eta 0:11:03 lr 0.000439	time 1.9243 (2.2033)	loss 3.2013 (3.4917)	grad_norm 1.4718 (1.5840)	
[2022-01-22 19:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][960/1251]	eta 0:10:40 lr 0.000439	time 1.9072 (2.2020)	loss 3.7768 (3.4908)	grad_norm 1.3049 (1.5838)	
[2022-01-22 19:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][970/1251]	eta 0:10:18 lr 0.000439	time 1.6129 (2.2010)	loss 3.1619 (3.4912)	grad_norm 1.5587 (1.5835)	
[2022-01-22 19:56:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][980/1251]	eta 0:09:56 lr 0.000439	time 2.2199 (2.2010)	loss 4.1236 (3.4872)	grad_norm 2.0756 (1.5834)	
[2022-01-22 19:56:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][990/1251]	eta 0:09:34 lr 0.000439	time 2.1649 (2.1996)	loss 2.6573 (3.4875)	grad_norm 1.5195 (1.5831)	
[2022-01-22 19:57:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1000/1251]	eta 0:09:12 lr 0.000439	time 2.6931 (2.1996)	loss 2.3684 (3.4864)	grad_norm 1.6477 (1.5832)	
[2022-01-22 19:57:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1010/1251]	eta 0:08:50 lr 0.000439	time 1.8844 (2.2004)	loss 3.8031 (3.4887)	grad_norm 1.4794 (1.5826)	
[2022-01-22 19:58:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1020/1251]	eta 0:08:28 lr 0.000439	time 2.1293 (2.2003)	loss 3.7994 (3.4907)	grad_norm 1.2989 (1.5828)	
[2022-01-22 19:58:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1030/1251]	eta 0:08:06 lr 0.000439	time 2.2622 (2.2005)	loss 3.7371 (3.4916)	grad_norm 1.5611 (1.5826)	
[2022-01-22 19:58:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1040/1251]	eta 0:07:44 lr 0.000439	time 2.7836 (2.2010)	loss 3.7392 (3.4924)	grad_norm 1.4634 (1.5826)	
[2022-01-22 19:59:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1050/1251]	eta 0:07:22 lr 0.000439	time 1.5836 (2.2012)	loss 2.6520 (3.4916)	grad_norm 1.6988 (1.5823)	
[2022-01-22 19:59:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1060/1251]	eta 0:07:00 lr 0.000439	time 3.0201 (2.2024)	loss 3.9064 (3.4913)	grad_norm 1.4792 (1.5819)	
[2022-01-22 19:59:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1070/1251]	eta 0:06:38 lr 0.000439	time 2.0774 (2.2018)	loss 3.4729 (3.4922)	grad_norm 1.7126 (1.5818)	
[2022-01-22 20:00:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1080/1251]	eta 0:06:16 lr 0.000439	time 2.3820 (2.2014)	loss 3.2751 (3.4921)	grad_norm 1.7839 (1.5814)	
[2022-01-22 20:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1090/1251]	eta 0:05:54 lr 0.000438	time 1.9255 (2.1995)	loss 2.5441 (3.4914)	grad_norm 1.6004 (1.5811)	
[2022-01-22 20:01:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1100/1251]	eta 0:05:32 lr 0.000438	time 2.2526 (2.1991)	loss 4.1741 (3.4908)	grad_norm 1.5076 (1.5810)	
[2022-01-22 20:01:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1110/1251]	eta 0:05:09 lr 0.000438	time 2.6055 (2.1983)	loss 3.2903 (3.4874)	grad_norm 1.8340 (1.5818)	
[2022-01-22 20:01:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1120/1251]	eta 0:04:47 lr 0.000438	time 2.5190 (2.1982)	loss 3.8498 (3.4889)	grad_norm 1.5174 (1.5819)	
[2022-01-22 20:02:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1130/1251]	eta 0:04:25 lr 0.000438	time 1.6884 (2.1975)	loss 3.0751 (3.4878)	grad_norm 1.4295 (1.5816)	
[2022-01-22 20:02:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1140/1251]	eta 0:04:03 lr 0.000438	time 2.5102 (2.1976)	loss 4.1632 (3.4906)	grad_norm 1.4149 (1.5814)	
[2022-01-22 20:02:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1150/1251]	eta 0:03:42 lr 0.000438	time 2.8475 (2.1986)	loss 3.9571 (3.4917)	grad_norm 1.4434 (1.5810)	
[2022-01-22 20:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1160/1251]	eta 0:03:20 lr 0.000438	time 2.7284 (2.2003)	loss 3.7907 (3.4939)	grad_norm 1.4874 (1.5805)	
[2022-01-22 20:03:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1170/1251]	eta 0:02:58 lr 0.000438	time 1.6868 (2.1999)	loss 3.9017 (3.4965)	grad_norm 1.3895 (1.5810)	
[2022-01-22 20:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1180/1251]	eta 0:02:36 lr 0.000438	time 2.0007 (2.1987)	loss 3.4836 (3.4979)	grad_norm 1.5710 (1.5808)	
[2022-01-22 20:04:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1190/1251]	eta 0:02:14 lr 0.000438	time 1.9038 (2.1971)	loss 3.1028 (3.4999)	grad_norm 1.4056 (1.5802)	
[2022-01-22 20:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1200/1251]	eta 0:01:51 lr 0.000438	time 2.2408 (2.1957)	loss 4.2082 (3.5007)	grad_norm 1.5013 (1.5801)	
[2022-01-22 20:04:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1210/1251]	eta 0:01:29 lr 0.000438	time 2.3002 (2.1948)	loss 3.1629 (3.4995)	grad_norm 1.4865 (1.5810)	
[2022-01-22 20:05:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1220/1251]	eta 0:01:08 lr 0.000438	time 2.1492 (2.1948)	loss 3.8234 (3.4972)	grad_norm 1.6903 (1.5829)	
[2022-01-22 20:05:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1230/1251]	eta 0:00:46 lr 0.000438	time 2.4277 (2.1956)	loss 3.5003 (3.4957)	grad_norm 1.7018 (1.5832)	
[2022-01-22 20:06:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1240/1251]	eta 0:00:24 lr 0.000438	time 1.7128 (2.1956)	loss 3.8124 (3.4960)	grad_norm 1.4609 (1.5829)	
[2022-01-22 20:06:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [162/300][1250/1251]	eta 0:00:02 lr 0.000438	time 1.1733 (2.1913)	loss 3.3769 (3.4991)	grad_norm 1.3210 (1.5826)	
[2022-01-22 20:06:21 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 162 training takes 0:45:41
[2022-01-22 20:06:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.031 (16.031)	Loss 0.9319 (0.9319)	Acc@1 78.027 (78.027)	Acc@5 94.922 (94.922)	
[2022-01-22 20:06:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.278 (3.296)	Loss 1.0291 (0.9643)	Acc@1 75.098 (76.634)	Acc@5 92.480 (93.910)	
[2022-01-22 20:07:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.632 (2.567)	Loss 1.0100 (0.9864)	Acc@1 78.320 (76.469)	Acc@5 92.773 (93.708)	
[2022-01-22 20:07:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.326 (2.234)	Loss 0.9690 (0.9897)	Acc@1 77.051 (76.418)	Acc@5 94.141 (93.709)	
[2022-01-22 20:07:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.442 (2.140)	Loss 0.9764 (0.9930)	Acc@1 76.660 (76.398)	Acc@5 94.238 (93.707)	
[2022-01-22 20:07:57 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.468 Acc@5 93.676
[2022-01-22 20:07:57 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.5%
[2022-01-22 20:07:57 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.65%
[2022-01-22 20:08:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][0/1251]	eta 7:30:20 lr 0.000438	time 21.5995 (21.5995)	loss 3.8873 (3.8873)	grad_norm 1.3607 (1.3607)	
[2022-01-22 20:08:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][10/1251]	eta 1:26:30 lr 0.000438	time 1.5704 (4.1825)	loss 3.7828 (3.4536)	grad_norm 1.6039 (1.5654)	
[2022-01-22 20:09:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][20/1251]	eta 1:07:38 lr 0.000438	time 1.8309 (3.2970)	loss 3.8017 (3.5242)	grad_norm 1.6543 (1.5616)	
[2022-01-22 20:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][30/1251]	eta 0:59:04 lr 0.000438	time 1.5463 (2.9027)	loss 4.2577 (3.5110)	grad_norm 1.5866 (1.5796)	
[2022-01-22 20:09:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][40/1251]	eta 0:56:25 lr 0.000438	time 3.8762 (2.7953)	loss 3.4650 (3.5113)	grad_norm 1.4792 (1.5809)	
[2022-01-22 20:10:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][50/1251]	eta 0:53:41 lr 0.000438	time 1.4944 (2.6821)	loss 4.2141 (3.5392)	grad_norm 1.6358 (1.5848)	
[2022-01-22 20:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][60/1251]	eta 0:52:04 lr 0.000438	time 1.7520 (2.6237)	loss 3.3839 (3.5255)	grad_norm 1.5008 (1.5768)	
[2022-01-22 20:10:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][70/1251]	eta 0:50:00 lr 0.000438	time 1.6736 (2.5408)	loss 3.3871 (3.5406)	grad_norm 1.4245 (1.5821)	
[2022-01-22 20:11:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][80/1251]	eta 0:49:00 lr 0.000437	time 3.7353 (2.5108)	loss 4.1145 (3.5160)	grad_norm 1.5014 (1.5842)	
[2022-01-22 20:11:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][90/1251]	eta 0:47:49 lr 0.000437	time 1.7687 (2.4715)	loss 3.5036 (3.5013)	grad_norm 1.4489 (1.5775)	
[2022-01-22 20:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][100/1251]	eta 0:46:59 lr 0.000437	time 2.0301 (2.4498)	loss 2.3134 (3.4943)	grad_norm 1.9179 (1.5780)	
[2022-01-22 20:12:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][110/1251]	eta 0:46:11 lr 0.000437	time 2.8783 (2.4291)	loss 3.8468 (3.4990)	grad_norm 1.6251 (1.5760)	
[2022-01-22 20:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][120/1251]	eta 0:45:27 lr 0.000437	time 3.3752 (2.4116)	loss 3.7813 (3.4930)	grad_norm 2.0014 (1.5809)	
[2022-01-22 20:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][130/1251]	eta 0:44:39 lr 0.000437	time 1.6004 (2.3905)	loss 3.7545 (3.4987)	grad_norm 1.5379 (1.5805)	
[2022-01-22 20:13:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][140/1251]	eta 0:44:22 lr 0.000437	time 2.4430 (2.3966)	loss 3.6973 (3.4981)	grad_norm 1.6245 (1.5811)	
[2022-01-22 20:13:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][150/1251]	eta 0:43:37 lr 0.000437	time 1.6536 (2.3776)	loss 3.7326 (3.4988)	grad_norm 1.5614 (1.5843)	
[2022-01-22 20:14:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][160/1251]	eta 0:42:57 lr 0.000437	time 1.7964 (2.3628)	loss 2.8604 (3.4826)	grad_norm 1.3878 (1.5772)	
[2022-01-22 20:14:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][170/1251]	eta 0:42:10 lr 0.000437	time 1.8557 (2.3407)	loss 3.0173 (3.4679)	grad_norm 1.6303 (1.5716)	
[2022-01-22 20:14:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][180/1251]	eta 0:41:39 lr 0.000437	time 2.2771 (2.3336)	loss 3.5699 (3.4709)	grad_norm 1.6344 (1.5707)	
[2022-01-22 20:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][190/1251]	eta 0:41:03 lr 0.000437	time 1.5883 (2.3218)	loss 4.1961 (3.4651)	grad_norm 1.4539 (1.5694)	
[2022-01-22 20:15:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][200/1251]	eta 0:40:36 lr 0.000437	time 2.5772 (2.3184)	loss 3.9479 (3.4816)	grad_norm 1.4839 (1.5684)	
[2022-01-22 20:16:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][210/1251]	eta 0:39:58 lr 0.000437	time 1.9079 (2.3045)	loss 3.2708 (3.4875)	grad_norm 1.3692 (1.5714)	
[2022-01-22 20:16:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][220/1251]	eta 0:39:24 lr 0.000437	time 1.9228 (2.2935)	loss 4.2497 (3.4856)	grad_norm 1.5420 (1.5690)	
[2022-01-22 20:16:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][230/1251]	eta 0:38:56 lr 0.000437	time 1.5538 (2.2886)	loss 3.3368 (3.4836)	grad_norm 1.6987 (1.5691)	
[2022-01-22 20:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][240/1251]	eta 0:38:30 lr 0.000437	time 2.3728 (2.2856)	loss 3.1099 (3.4888)	grad_norm 1.5454 (1.5717)	
[2022-01-22 20:17:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][250/1251]	eta 0:38:11 lr 0.000437	time 2.3237 (2.2893)	loss 3.8681 (3.4960)	grad_norm 1.7669 (1.5718)	
[2022-01-22 20:17:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][260/1251]	eta 0:37:49 lr 0.000437	time 1.6630 (2.2903)	loss 3.3544 (3.4907)	grad_norm 1.7607 (1.5718)	
[2022-01-22 20:18:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][270/1251]	eta 0:37:27 lr 0.000437	time 1.7079 (2.2907)	loss 3.2395 (3.4915)	grad_norm 1.4513 (1.5754)	
[2022-01-22 20:18:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][280/1251]	eta 0:36:56 lr 0.000437	time 2.4288 (2.2826)	loss 3.5281 (3.4876)	grad_norm 1.4782 (1.5770)	
[2022-01-22 20:18:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][290/1251]	eta 0:36:23 lr 0.000437	time 1.8885 (2.2721)	loss 3.6356 (3.4726)	grad_norm 1.8966 (1.5766)	
[2022-01-22 20:19:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][300/1251]	eta 0:35:52 lr 0.000437	time 1.9373 (2.2639)	loss 2.2581 (3.4665)	grad_norm 1.4800 (1.5777)	
[2022-01-22 20:19:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][310/1251]	eta 0:35:24 lr 0.000437	time 1.9063 (2.2580)	loss 4.0654 (3.4762)	grad_norm 1.6006 (1.5779)	
[2022-01-22 20:20:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][320/1251]	eta 0:35:00 lr 0.000437	time 2.6922 (2.2559)	loss 3.8389 (3.4861)	grad_norm 1.9465 (1.5796)	
[2022-01-22 20:20:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][330/1251]	eta 0:34:39 lr 0.000436	time 2.3634 (2.2575)	loss 3.7245 (3.4905)	grad_norm 1.5592 (1.5814)	
[2022-01-22 20:20:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][340/1251]	eta 0:34:16 lr 0.000436	time 1.8111 (2.2574)	loss 4.0361 (3.4845)	grad_norm 1.5078 (1.5800)	
[2022-01-22 20:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][350/1251]	eta 0:33:53 lr 0.000436	time 1.6507 (2.2567)	loss 3.8493 (3.4816)	grad_norm 1.4983 (1.5789)	
[2022-01-22 20:21:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][360/1251]	eta 0:33:33 lr 0.000436	time 3.4095 (2.2599)	loss 3.0872 (3.4850)	grad_norm 1.6248 (1.5832)	
[2022-01-22 20:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][370/1251]	eta 0:33:14 lr 0.000436	time 1.6235 (2.2642)	loss 3.1586 (3.4871)	grad_norm 1.7424 (1.5899)	
[2022-01-22 20:22:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][380/1251]	eta 0:32:46 lr 0.000436	time 1.5682 (2.2581)	loss 2.6631 (3.4889)	grad_norm 1.6407 (1.5900)	
[2022-01-22 20:22:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][390/1251]	eta 0:32:19 lr 0.000436	time 1.6919 (2.2529)	loss 2.6023 (3.4860)	grad_norm 1.3390 (1.5931)	
[2022-01-22 20:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][400/1251]	eta 0:31:57 lr 0.000436	time 3.7068 (2.2533)	loss 3.4689 (3.4890)	grad_norm 1.4810 (1.5948)	
[2022-01-22 20:23:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][410/1251]	eta 0:31:33 lr 0.000436	time 2.1825 (2.2517)	loss 2.9098 (3.4853)	grad_norm 1.8198 (1.5964)	
[2022-01-22 20:23:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][420/1251]	eta 0:31:09 lr 0.000436	time 1.8933 (2.2502)	loss 3.8911 (3.4837)	grad_norm 1.4854 (1.5966)	
[2022-01-22 20:24:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][430/1251]	eta 0:30:48 lr 0.000436	time 2.1717 (2.2510)	loss 4.2501 (3.4828)	grad_norm 1.5632 (1.5959)	
[2022-01-22 20:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][440/1251]	eta 0:30:25 lr 0.000436	time 3.1565 (2.2512)	loss 3.8589 (3.4789)	grad_norm 1.9356 (1.5969)	
[2022-01-22 20:24:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][450/1251]	eta 0:30:00 lr 0.000436	time 2.7576 (2.2482)	loss 3.1021 (3.4825)	grad_norm 1.3822 (1.5960)	
[2022-01-22 20:25:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][460/1251]	eta 0:29:37 lr 0.000436	time 1.5277 (2.2475)	loss 3.7615 (3.4869)	grad_norm 1.7693 (1.5990)	
[2022-01-22 20:25:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][470/1251]	eta 0:29:13 lr 0.000436	time 1.9172 (2.2457)	loss 2.6395 (3.4769)	grad_norm 1.6207 (1.5984)	
[2022-01-22 20:25:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][480/1251]	eta 0:28:47 lr 0.000436	time 2.0976 (2.2405)	loss 3.4719 (3.4787)	grad_norm 1.4542 (1.5968)	
[2022-01-22 20:26:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][490/1251]	eta 0:28:22 lr 0.000436	time 3.2242 (2.2374)	loss 3.8307 (3.4767)	grad_norm 1.4095 (1.5946)	
[2022-01-22 20:26:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][500/1251]	eta 0:27:57 lr 0.000436	time 2.0002 (2.2343)	loss 2.1364 (3.4756)	grad_norm 1.3998 (1.5950)	
[2022-01-22 20:26:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][510/1251]	eta 0:27:34 lr 0.000436	time 2.5970 (2.2328)	loss 3.5052 (3.4767)	grad_norm 1.9636 (1.5960)	
[2022-01-22 20:27:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][520/1251]	eta 0:27:11 lr 0.000436	time 2.1977 (2.2315)	loss 3.1028 (3.4742)	grad_norm 1.6612 (1.5947)	
[2022-01-22 20:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][530/1251]	eta 0:26:48 lr 0.000436	time 2.0138 (2.2308)	loss 3.7828 (3.4808)	grad_norm 1.4032 (1.5936)	
[2022-01-22 20:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][540/1251]	eta 0:26:27 lr 0.000436	time 2.9707 (2.2330)	loss 3.9477 (3.4840)	grad_norm 1.3873 (1.5933)	
[2022-01-22 20:28:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][550/1251]	eta 0:26:04 lr 0.000436	time 2.4848 (2.2315)	loss 3.4295 (3.4857)	grad_norm 1.4129 (1.5920)	
[2022-01-22 20:28:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][560/1251]	eta 0:25:41 lr 0.000436	time 2.2876 (2.2312)	loss 3.4620 (3.4858)	grad_norm 1.4384 (1.5909)	
[2022-01-22 20:29:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][570/1251]	eta 0:25:21 lr 0.000435	time 2.2605 (2.2344)	loss 2.4709 (3.4859)	grad_norm 1.7520 (1.5953)	
[2022-01-22 20:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][580/1251]	eta 0:24:59 lr 0.000435	time 2.2531 (2.2345)	loss 2.8469 (3.4847)	grad_norm 1.4720 (1.5954)	
[2022-01-22 20:29:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][590/1251]	eta 0:24:35 lr 0.000435	time 2.1849 (2.2328)	loss 2.9548 (3.4821)	grad_norm 1.4206 (1.5945)	
[2022-01-22 20:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][600/1251]	eta 0:24:10 lr 0.000435	time 1.9089 (2.2282)	loss 3.3475 (3.4851)	grad_norm 1.3665 (1.5937)	
[2022-01-22 20:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][610/1251]	eta 0:23:47 lr 0.000435	time 2.8648 (2.2271)	loss 3.9806 (3.4864)	grad_norm 1.4809 (1.5938)	
[2022-01-22 20:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][620/1251]	eta 0:23:26 lr 0.000435	time 2.7938 (2.2283)	loss 3.3881 (3.4817)	grad_norm 1.7027 (1.5935)	
[2022-01-22 20:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][630/1251]	eta 0:23:02 lr 0.000435	time 1.8326 (2.2264)	loss 4.2210 (3.4833)	grad_norm 1.8467 (1.5930)	
[2022-01-22 20:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][640/1251]	eta 0:22:39 lr 0.000435	time 2.7447 (2.2254)	loss 3.3232 (3.4871)	grad_norm 1.4759 (1.5916)	
[2022-01-22 20:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][650/1251]	eta 0:22:15 lr 0.000435	time 2.2954 (2.2224)	loss 3.2288 (3.4865)	grad_norm 1.4752 (1.5910)	
[2022-01-22 20:32:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][660/1251]	eta 0:21:53 lr 0.000435	time 2.2831 (2.2218)	loss 3.9348 (3.4874)	grad_norm 1.3994 (1.5919)	
[2022-01-22 20:32:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][670/1251]	eta 0:21:30 lr 0.000435	time 1.9106 (2.2205)	loss 2.5401 (3.4875)	grad_norm 1.4797 (1.5917)	
[2022-01-22 20:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][680/1251]	eta 0:21:08 lr 0.000435	time 3.2083 (2.2216)	loss 3.4843 (3.4883)	grad_norm 1.6157 (1.5914)	
[2022-01-22 20:33:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][690/1251]	eta 0:20:46 lr 0.000435	time 2.5589 (2.2211)	loss 3.2747 (3.4853)	grad_norm 1.7908 (1.5913)	
[2022-01-22 20:33:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][700/1251]	eta 0:20:22 lr 0.000435	time 2.6295 (2.2191)	loss 4.1479 (3.4859)	grad_norm 1.7234 (1.5923)	
[2022-01-22 20:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][710/1251]	eta 0:20:00 lr 0.000435	time 2.8486 (2.2188)	loss 3.5039 (3.4805)	grad_norm 1.5718 (1.5914)	
[2022-01-22 20:34:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][720/1251]	eta 0:19:38 lr 0.000435	time 2.5442 (2.2186)	loss 3.2338 (3.4816)	grad_norm 1.6199 (1.5918)	
[2022-01-22 20:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][730/1251]	eta 0:19:16 lr 0.000435	time 2.3575 (2.2193)	loss 4.2423 (3.4827)	grad_norm 1.6414 (1.5912)	
[2022-01-22 20:35:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][740/1251]	eta 0:18:53 lr 0.000435	time 2.2643 (2.2189)	loss 3.1520 (3.4819)	grad_norm 1.5926 (1.5911)	
[2022-01-22 20:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][750/1251]	eta 0:18:30 lr 0.000435	time 1.9941 (2.2168)	loss 3.4835 (3.4831)	grad_norm 1.7126 (1.5902)	
[2022-01-22 20:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][760/1251]	eta 0:18:08 lr 0.000435	time 2.6760 (2.2167)	loss 3.8907 (3.4858)	grad_norm 1.6504 (1.5903)	
[2022-01-22 20:36:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][770/1251]	eta 0:17:45 lr 0.000435	time 2.1940 (2.2154)	loss 3.8579 (3.4857)	grad_norm 1.6047 (1.5906)	
[2022-01-22 20:36:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][780/1251]	eta 0:17:23 lr 0.000435	time 2.2482 (2.2148)	loss 3.6197 (3.4861)	grad_norm 1.6408 (1.5914)	
[2022-01-22 20:37:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][790/1251]	eta 0:17:00 lr 0.000435	time 2.2427 (2.2136)	loss 3.4733 (3.4828)	grad_norm 1.6616 (1.5912)	
[2022-01-22 20:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][800/1251]	eta 0:16:41 lr 0.000435	time 4.0181 (2.2207)	loss 3.6023 (3.4809)	grad_norm 1.5195 (1.5914)	
[2022-01-22 20:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][810/1251]	eta 0:16:19 lr 0.000434	time 2.2497 (2.2204)	loss 3.6935 (3.4807)	grad_norm 1.4878 (1.5911)	
[2022-01-22 20:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][820/1251]	eta 0:15:56 lr 0.000434	time 1.9947 (2.2185)	loss 3.5551 (3.4832)	grad_norm 1.5448 (1.5921)	
[2022-01-22 20:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][830/1251]	eta 0:15:32 lr 0.000434	time 1.6106 (2.2149)	loss 4.2666 (3.4858)	grad_norm 1.5128 (1.5919)	
[2022-01-22 20:38:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][840/1251]	eta 0:15:10 lr 0.000434	time 2.8206 (2.2147)	loss 4.2251 (3.4865)	grad_norm 1.4148 (1.5924)	
[2022-01-22 20:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][850/1251]	eta 0:14:47 lr 0.000434	time 2.3131 (2.2135)	loss 3.7376 (3.4890)	grad_norm 2.1505 (1.5929)	
[2022-01-22 20:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][860/1251]	eta 0:14:24 lr 0.000434	time 1.8439 (2.2118)	loss 3.7707 (3.4925)	grad_norm 1.4698 (1.5934)	
[2022-01-22 20:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][870/1251]	eta 0:14:03 lr 0.000434	time 1.9415 (2.2137)	loss 4.0768 (3.4941)	grad_norm 1.5214 (1.5931)	
[2022-01-22 20:40:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][880/1251]	eta 0:13:41 lr 0.000434	time 2.1572 (2.2156)	loss 2.5992 (3.4924)	grad_norm 1.8530 (1.5948)	
[2022-01-22 20:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][890/1251]	eta 0:13:19 lr 0.000434	time 2.4597 (2.2147)	loss 3.9060 (3.4917)	grad_norm 1.3252 (1.5958)	
[2022-01-22 20:41:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][900/1251]	eta 0:12:57 lr 0.000434	time 2.0153 (2.2137)	loss 4.1176 (3.4893)	grad_norm 1.4586 (1.5952)	
[2022-01-22 20:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][910/1251]	eta 0:12:34 lr 0.000434	time 2.2596 (2.2136)	loss 2.8503 (3.4888)	grad_norm 1.5540 (1.5939)	
[2022-01-22 20:41:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][920/1251]	eta 0:12:12 lr 0.000434	time 2.4888 (2.2136)	loss 4.0952 (3.4903)	grad_norm 1.5846 (1.5940)	
[2022-01-22 20:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][930/1251]	eta 0:11:50 lr 0.000434	time 2.5711 (2.2129)	loss 3.9662 (3.4898)	grad_norm 1.9215 (1.5938)	
[2022-01-22 20:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][940/1251]	eta 0:11:27 lr 0.000434	time 1.6286 (2.2111)	loss 3.7885 (3.4893)	grad_norm 1.3630 (1.5943)	
[2022-01-22 20:42:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][950/1251]	eta 0:11:05 lr 0.000434	time 2.1177 (2.2104)	loss 3.8517 (3.4894)	grad_norm 1.4869 (1.5928)	
[2022-01-22 20:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][960/1251]	eta 0:10:42 lr 0.000434	time 1.9054 (2.2096)	loss 3.5979 (3.4894)	grad_norm 1.4998 (1.5935)	
[2022-01-22 20:43:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][970/1251]	eta 0:10:20 lr 0.000434	time 2.4543 (2.2097)	loss 3.5729 (3.4904)	grad_norm 1.4134 (1.5937)	
[2022-01-22 20:44:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][980/1251]	eta 0:09:58 lr 0.000434	time 3.0606 (2.2085)	loss 3.6549 (3.4928)	grad_norm 1.5662 (1.5939)	
[2022-01-22 20:44:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][990/1251]	eta 0:09:36 lr 0.000434	time 2.0110 (2.2069)	loss 3.1495 (3.4925)	grad_norm 2.0899 (1.5946)	
[2022-01-22 20:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1000/1251]	eta 0:09:13 lr 0.000434	time 2.1377 (2.2057)	loss 2.3236 (3.4903)	grad_norm 1.9648 (1.5960)	
[2022-01-22 20:45:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1010/1251]	eta 0:08:51 lr 0.000434	time 2.2325 (2.2061)	loss 3.8891 (3.4876)	grad_norm 1.4133 (1.5956)	
[2022-01-22 20:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1020/1251]	eta 0:08:30 lr 0.000434	time 2.4763 (2.2085)	loss 3.5050 (3.4866)	grad_norm 1.4247 (1.5952)	
[2022-01-22 20:45:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1030/1251]	eta 0:08:08 lr 0.000434	time 1.9787 (2.2097)	loss 3.5136 (3.4873)	grad_norm 1.8962 (1.5954)	
[2022-01-22 20:46:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1040/1251]	eta 0:07:46 lr 0.000434	time 1.5804 (2.2097)	loss 4.3791 (3.4887)	grad_norm 1.5821 (1.5952)	
[2022-01-22 20:46:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1050/1251]	eta 0:07:24 lr 0.000434	time 3.0304 (2.2096)	loss 3.8448 (3.4885)	grad_norm 1.5106 (1.5942)	
[2022-01-22 20:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1060/1251]	eta 0:07:01 lr 0.000433	time 2.1548 (2.2090)	loss 3.4284 (3.4893)	grad_norm 1.4351 (1.5937)	
[2022-01-22 20:47:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1070/1251]	eta 0:06:39 lr 0.000433	time 1.6362 (2.2076)	loss 3.8504 (3.4877)	grad_norm 1.3790 (1.5930)	
[2022-01-22 20:47:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1080/1251]	eta 0:06:17 lr 0.000433	time 2.2310 (2.2071)	loss 3.5247 (3.4861)	grad_norm 1.5891 (1.5926)	
[2022-01-22 20:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1090/1251]	eta 0:05:55 lr 0.000433	time 3.0326 (2.2066)	loss 3.1774 (3.4843)	grad_norm 1.5652 (1.5916)	
[2022-01-22 20:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1100/1251]	eta 0:05:33 lr 0.000433	time 1.9454 (2.2057)	loss 4.2022 (3.4880)	grad_norm 1.5336 (1.5909)	
[2022-01-22 20:48:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1110/1251]	eta 0:05:11 lr 0.000433	time 2.8066 (2.2058)	loss 3.4729 (3.4902)	grad_norm 1.4532 (1.5905)	
[2022-01-22 20:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1120/1251]	eta 0:04:48 lr 0.000433	time 2.0816 (2.2052)	loss 3.2453 (3.4895)	grad_norm 1.7769 (1.5902)	
[2022-01-22 20:49:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1130/1251]	eta 0:04:26 lr 0.000433	time 1.9213 (2.2039)	loss 3.3775 (3.4899)	grad_norm 1.8204 (1.5900)	
[2022-01-22 20:49:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1140/1251]	eta 0:04:04 lr 0.000433	time 2.0058 (2.2043)	loss 2.7087 (3.4888)	grad_norm 1.7436 (1.5900)	
[2022-01-22 20:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1150/1251]	eta 0:03:42 lr 0.000433	time 2.4746 (2.2058)	loss 3.9533 (3.4884)	grad_norm 1.6617 (1.5913)	
[2022-01-22 20:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1160/1251]	eta 0:03:20 lr 0.000433	time 1.8456 (2.2061)	loss 3.2012 (3.4868)	grad_norm 1.4782 (1.5916)	
[2022-01-22 20:51:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1170/1251]	eta 0:02:58 lr 0.000433	time 2.6484 (2.2075)	loss 3.9782 (3.4885)	grad_norm 1.7319 (1.5917)	
[2022-01-22 20:51:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1180/1251]	eta 0:02:36 lr 0.000433	time 2.2581 (2.2075)	loss 3.4897 (3.4869)	grad_norm 1.6160 (1.5920)	
[2022-01-22 20:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1190/1251]	eta 0:02:14 lr 0.000433	time 1.5892 (2.2060)	loss 3.4313 (3.4863)	grad_norm 1.6631 (1.5919)	
[2022-01-22 20:52:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1200/1251]	eta 0:01:52 lr 0.000433	time 1.8530 (2.2043)	loss 3.5540 (3.4866)	grad_norm 1.5144 (1.5914)	
[2022-01-22 20:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1210/1251]	eta 0:01:30 lr 0.000433	time 2.0017 (2.2034)	loss 4.1640 (3.4872)	grad_norm 1.4358 (1.5912)	
[2022-01-22 20:52:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1220/1251]	eta 0:01:08 lr 0.000433	time 1.9792 (2.2030)	loss 3.7976 (3.4880)	grad_norm 1.6956 (1.5921)	
[2022-01-22 20:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1230/1251]	eta 0:00:46 lr 0.000433	time 2.2461 (2.2043)	loss 3.9100 (3.4868)	grad_norm 1.7799 (1.5926)	
[2022-01-22 20:53:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1240/1251]	eta 0:00:24 lr 0.000433	time 1.1981 (2.2026)	loss 3.2138 (3.4855)	grad_norm 1.7019 (1.5927)	
[2022-01-22 20:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [163/300][1250/1251]	eta 0:00:02 lr 0.000433	time 1.1813 (2.1975)	loss 2.8267 (3.4863)	grad_norm 1.3745 (1.5922)	
[2022-01-22 20:53:46 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 163 training takes 0:45:49
[2022-01-22 20:54:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.257 (18.257)	Loss 0.9939 (0.9939)	Acc@1 76.074 (76.074)	Acc@5 93.848 (93.848)	
[2022-01-22 20:54:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.246 (3.197)	Loss 0.9357 (0.9752)	Acc@1 76.465 (76.740)	Acc@5 94.824 (94.087)	
[2022-01-22 20:54:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.284 (2.486)	Loss 1.0160 (0.9874)	Acc@1 74.805 (76.483)	Acc@5 93.652 (93.829)	
[2022-01-22 20:54:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.608 (2.268)	Loss 1.0332 (0.9900)	Acc@1 76.465 (76.537)	Acc@5 93.359 (93.637)	
[2022-01-22 20:55:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.775 (2.163)	Loss 1.0039 (0.9852)	Acc@1 77.051 (76.686)	Acc@5 93.457 (93.633)	
[2022-01-22 20:55:22 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.650 Acc@5 93.552
[2022-01-22 20:55:22 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.6%
[2022-01-22 20:55:22 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.65%
[2022-01-22 20:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][0/1251]	eta 6:47:56 lr 0.000433	time 19.5656 (19.5656)	loss 3.9414 (3.9414)	grad_norm 1.4998 (1.4998)	
[2022-01-22 20:56:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][10/1251]	eta 1:22:07 lr 0.000433	time 1.8413 (3.9707)	loss 2.9159 (3.6456)	grad_norm 1.4646 (1.5723)	
[2022-01-22 20:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][20/1251]	eta 1:03:11 lr 0.000433	time 1.5649 (3.0800)	loss 3.3758 (3.7073)	grad_norm 1.4088 (1.6169)	
[2022-01-22 20:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][30/1251]	eta 0:57:37 lr 0.000433	time 1.5617 (2.8315)	loss 3.7629 (3.6615)	grad_norm 1.7265 (1.6019)	
[2022-01-22 20:57:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][40/1251]	eta 0:54:46 lr 0.000433	time 3.7700 (2.7140)	loss 2.8103 (3.5743)	grad_norm 1.4532 (1.6050)	
[2022-01-22 20:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][50/1251]	eta 0:52:39 lr 0.000432	time 1.7975 (2.6307)	loss 3.9251 (3.5810)	grad_norm 1.5410 (1.5932)	
[2022-01-22 20:57:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][60/1251]	eta 0:50:50 lr 0.000432	time 1.5802 (2.5616)	loss 3.6413 (3.5445)	grad_norm 1.4332 (1.5867)	
[2022-01-22 20:58:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][70/1251]	eta 0:49:23 lr 0.000432	time 1.3055 (2.5096)	loss 4.0971 (3.5621)	grad_norm 1.6811 (1.5848)	
[2022-01-22 20:58:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][80/1251]	eta 0:48:35 lr 0.000432	time 3.2171 (2.4897)	loss 2.3709 (3.5638)	grad_norm 1.5197 (1.5748)	
[2022-01-22 20:59:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][90/1251]	eta 0:47:57 lr 0.000432	time 1.6850 (2.4781)	loss 3.2640 (3.5707)	grad_norm 1.3686 (1.5609)	
[2022-01-22 20:59:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][100/1251]	eta 0:46:50 lr 0.000432	time 1.9466 (2.4418)	loss 2.7477 (3.5735)	grad_norm 1.4111 (1.5601)	
[2022-01-22 20:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][110/1251]	eta 0:45:50 lr 0.000432	time 1.5963 (2.4107)	loss 3.7912 (3.5644)	grad_norm 1.8671 (1.5573)	
[2022-01-22 21:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][120/1251]	eta 0:44:53 lr 0.000432	time 2.5790 (2.3813)	loss 2.4926 (3.5534)	grad_norm 1.6780 (1.5593)	
[2022-01-22 21:00:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][130/1251]	eta 0:44:17 lr 0.000432	time 1.6454 (2.3711)	loss 2.8210 (3.5450)	grad_norm 1.5335 (1.5588)	
[2022-01-22 21:00:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][140/1251]	eta 0:43:47 lr 0.000432	time 2.3027 (2.3649)	loss 3.1645 (3.5483)	grad_norm 1.6646 (1.5587)	
[2022-01-22 21:01:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][150/1251]	eta 0:43:03 lr 0.000432	time 1.8940 (2.3467)	loss 4.3106 (3.5535)	grad_norm 1.4082 (1.5605)	
[2022-01-22 21:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][160/1251]	eta 0:42:24 lr 0.000432	time 2.2498 (2.3321)	loss 2.6827 (3.5609)	grad_norm 1.4583 (1.5602)	
[2022-01-22 21:02:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][170/1251]	eta 0:41:58 lr 0.000432	time 2.1556 (2.3301)	loss 3.5214 (3.5561)	grad_norm 1.7045 (1.5644)	
[2022-01-22 21:02:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][180/1251]	eta 0:41:28 lr 0.000432	time 1.5197 (2.3234)	loss 4.0456 (3.5576)	grad_norm 1.9132 (1.5701)	
[2022-01-22 21:02:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][190/1251]	eta 0:40:59 lr 0.000432	time 2.2794 (2.3177)	loss 3.8620 (3.5565)	grad_norm 1.4932 (1.5707)	
[2022-01-22 21:03:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][200/1251]	eta 0:40:23 lr 0.000432	time 2.1242 (2.3062)	loss 3.5377 (3.5528)	grad_norm 1.4940 (1.5755)	
[2022-01-22 21:03:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][210/1251]	eta 0:39:49 lr 0.000432	time 2.5843 (2.2954)	loss 4.0383 (3.5650)	grad_norm 1.5822 (1.5792)	
[2022-01-22 21:03:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][220/1251]	eta 0:39:21 lr 0.000432	time 1.9424 (2.2909)	loss 2.7315 (3.5600)	grad_norm 1.5601 (1.5811)	
[2022-01-22 21:04:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][230/1251]	eta 0:38:56 lr 0.000432	time 2.0411 (2.2888)	loss 3.9234 (3.5597)	grad_norm 1.4944 (1.5789)	
[2022-01-22 21:04:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][240/1251]	eta 0:38:30 lr 0.000432	time 2.8760 (2.2853)	loss 3.9394 (3.5507)	grad_norm 1.6260 (1.5807)	
[2022-01-22 21:04:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][250/1251]	eta 0:38:02 lr 0.000432	time 2.7850 (2.2807)	loss 3.8875 (3.5472)	grad_norm 1.5814 (1.5825)	
[2022-01-22 21:05:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][260/1251]	eta 0:37:33 lr 0.000432	time 1.5745 (2.2739)	loss 3.4495 (3.5416)	grad_norm 1.8855 (1.5847)	
[2022-01-22 21:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][270/1251]	eta 0:37:11 lr 0.000432	time 2.2831 (2.2751)	loss 2.8822 (3.5291)	grad_norm 1.4455 (1.5821)	
[2022-01-22 21:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][280/1251]	eta 0:36:47 lr 0.000432	time 1.9347 (2.2733)	loss 2.7465 (3.5280)	grad_norm 1.5601 (1.5812)	
[2022-01-22 21:06:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][290/1251]	eta 0:36:22 lr 0.000432	time 3.0871 (2.2714)	loss 3.3794 (3.5209)	grad_norm 1.7394 (1.5838)	
[2022-01-22 21:06:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][300/1251]	eta 0:35:51 lr 0.000431	time 1.7747 (2.2624)	loss 2.9708 (3.5182)	grad_norm 1.6247 (1.5868)	
[2022-01-22 21:07:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][310/1251]	eta 0:35:29 lr 0.000431	time 1.6718 (2.2634)	loss 3.3978 (3.5158)	grad_norm 1.5302 (1.5857)	
[2022-01-22 21:07:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][320/1251]	eta 0:35:07 lr 0.000431	time 1.7885 (2.2636)	loss 3.5104 (3.5082)	grad_norm 1.6180 (1.5857)	
[2022-01-22 21:07:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][330/1251]	eta 0:34:43 lr 0.000431	time 2.8335 (2.2618)	loss 3.7672 (3.5149)	grad_norm 1.7861 (1.5882)	
[2022-01-22 21:08:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][340/1251]	eta 0:34:14 lr 0.000431	time 1.8614 (2.2547)	loss 2.9058 (3.5055)	grad_norm 1.4530 (1.5860)	
[2022-01-22 21:08:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][350/1251]	eta 0:33:47 lr 0.000431	time 1.9025 (2.2506)	loss 4.0296 (3.5129)	grad_norm 1.3988 (1.5856)	
[2022-01-22 21:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][360/1251]	eta 0:33:26 lr 0.000431	time 2.1206 (2.2521)	loss 3.0386 (3.5043)	grad_norm 1.4313 (1.5865)	
[2022-01-22 21:09:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][370/1251]	eta 0:33:00 lr 0.000431	time 1.9791 (2.2477)	loss 4.1560 (3.5037)	grad_norm 1.5253 (1.5858)	
[2022-01-22 21:09:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][380/1251]	eta 0:32:30 lr 0.000431	time 1.6237 (2.2393)	loss 2.4973 (3.5039)	grad_norm 1.6603 (1.5861)	
[2022-01-22 21:09:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][390/1251]	eta 0:32:05 lr 0.000431	time 1.7821 (2.2360)	loss 2.4888 (3.5016)	grad_norm 1.8372 (1.5900)	
[2022-01-22 21:10:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][400/1251]	eta 0:31:40 lr 0.000431	time 1.5663 (2.2335)	loss 3.8879 (3.5076)	grad_norm 1.6883 (1.5901)	
[2022-01-22 21:10:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][410/1251]	eta 0:31:18 lr 0.000431	time 2.2343 (2.2333)	loss 3.7873 (3.5087)	grad_norm 1.5813 (1.5907)	
[2022-01-22 21:11:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][420/1251]	eta 0:30:54 lr 0.000431	time 2.2520 (2.2319)	loss 2.7413 (3.5111)	grad_norm 1.5507 (1.5921)	
[2022-01-22 21:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][430/1251]	eta 0:30:35 lr 0.000431	time 3.1521 (2.2359)	loss 4.0285 (3.5111)	grad_norm 1.3141 (1.5899)	
[2022-01-22 21:11:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][440/1251]	eta 0:30:14 lr 0.000431	time 2.2322 (2.2374)	loss 3.9433 (3.5120)	grad_norm 1.6160 (1.5909)	
[2022-01-22 21:12:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][450/1251]	eta 0:29:51 lr 0.000431	time 2.3930 (2.2368)	loss 2.6294 (3.5131)	grad_norm 1.5336 (1.5886)	
[2022-01-22 21:12:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][460/1251]	eta 0:29:26 lr 0.000431	time 2.2624 (2.2336)	loss 3.4416 (3.5193)	grad_norm 1.5464 (1.5874)	
[2022-01-22 21:12:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][470/1251]	eta 0:29:02 lr 0.000431	time 2.6240 (2.2312)	loss 2.3064 (3.5161)	grad_norm 1.5639 (1.5865)	
[2022-01-22 21:13:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][480/1251]	eta 0:28:38 lr 0.000431	time 2.4747 (2.2285)	loss 3.6327 (3.5133)	grad_norm 1.5263 (1.5850)	
[2022-01-22 21:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][490/1251]	eta 0:28:15 lr 0.000431	time 2.1187 (2.2276)	loss 2.3081 (3.5080)	grad_norm 1.4369 (1.5839)	
[2022-01-22 21:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][500/1251]	eta 0:27:50 lr 0.000431	time 2.3471 (2.2245)	loss 3.0609 (3.5075)	grad_norm 1.4332 (1.5829)	
[2022-01-22 21:14:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][510/1251]	eta 0:27:29 lr 0.000431	time 2.3695 (2.2259)	loss 3.7501 (3.5032)	grad_norm 1.4708 (1.5846)	
[2022-01-22 21:14:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][520/1251]	eta 0:27:07 lr 0.000431	time 2.3732 (2.2265)	loss 3.7308 (3.5024)	grad_norm 1.5596 (1.5857)	
[2022-01-22 21:15:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][530/1251]	eta 0:26:44 lr 0.000431	time 1.8642 (2.2261)	loss 2.6389 (3.4994)	grad_norm 1.5419 (1.5849)	
[2022-01-22 21:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][540/1251]	eta 0:26:20 lr 0.000430	time 2.1316 (2.2235)	loss 3.3406 (3.5000)	grad_norm 1.6163 (1.5854)	
[2022-01-22 21:15:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][550/1251]	eta 0:25:57 lr 0.000430	time 1.9161 (2.2220)	loss 4.1218 (3.5037)	grad_norm 1.5457 (1.5860)	
[2022-01-22 21:16:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][560/1251]	eta 0:25:36 lr 0.000430	time 2.5187 (2.2242)	loss 3.3412 (3.5033)	grad_norm 1.5735 (1.5845)	
[2022-01-22 21:16:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][570/1251]	eta 0:25:14 lr 0.000430	time 2.0039 (2.2235)	loss 2.7120 (3.5003)	grad_norm 1.8724 (1.5849)	
[2022-01-22 21:16:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][580/1251]	eta 0:24:49 lr 0.000430	time 2.0984 (2.2194)	loss 4.1057 (3.5013)	grad_norm 1.5286 (1.5849)	
[2022-01-22 21:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][590/1251]	eta 0:24:25 lr 0.000430	time 1.9957 (2.2169)	loss 3.5485 (3.5011)	grad_norm 1.5931 (1.5853)	
[2022-01-22 21:17:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][600/1251]	eta 0:24:01 lr 0.000430	time 1.5867 (2.2136)	loss 4.3631 (3.5040)	grad_norm 1.6634 (1.5846)	
[2022-01-22 21:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][610/1251]	eta 0:23:38 lr 0.000430	time 2.5059 (2.2126)	loss 2.8340 (3.5002)	grad_norm 1.6847 (1.5845)	
[2022-01-22 21:18:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][620/1251]	eta 0:23:16 lr 0.000430	time 1.8768 (2.2124)	loss 3.7054 (3.5015)	grad_norm 1.5126 (1.5837)	
[2022-01-22 21:18:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][630/1251]	eta 0:22:55 lr 0.000430	time 2.4717 (2.2154)	loss 3.0203 (3.5002)	grad_norm 1.7442 (1.5846)	
[2022-01-22 21:19:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][640/1251]	eta 0:22:35 lr 0.000430	time 2.3794 (2.2180)	loss 4.0245 (3.5026)	grad_norm 1.9149 (1.5845)	
[2022-01-22 21:19:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][650/1251]	eta 0:22:15 lr 0.000430	time 2.8117 (2.2214)	loss 3.6852 (3.5058)	grad_norm 1.4865 (1.5846)	
[2022-01-22 21:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][660/1251]	eta 0:21:52 lr 0.000430	time 1.8212 (2.2212)	loss 4.0507 (3.5031)	grad_norm 1.4785 (1.5851)	
[2022-01-22 21:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][670/1251]	eta 0:21:30 lr 0.000430	time 2.1701 (2.2207)	loss 3.7353 (3.5056)	grad_norm 1.7144 (1.5860)	
[2022-01-22 21:20:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][680/1251]	eta 0:21:05 lr 0.000430	time 1.9517 (2.2161)	loss 3.1863 (3.5013)	grad_norm 1.4501 (1.5857)	
[2022-01-22 21:20:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][690/1251]	eta 0:20:42 lr 0.000430	time 2.2073 (2.2140)	loss 2.2481 (3.5023)	grad_norm 1.5006 (1.5849)	
[2022-01-22 21:21:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][700/1251]	eta 0:20:20 lr 0.000430	time 1.9398 (2.2145)	loss 3.8444 (3.5020)	grad_norm 1.5463 (1.5846)	
[2022-01-22 21:21:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][710/1251]	eta 0:19:59 lr 0.000430	time 2.5089 (2.2177)	loss 3.3853 (3.5036)	grad_norm 1.7610 (1.5844)	
[2022-01-22 21:22:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][720/1251]	eta 0:19:37 lr 0.000430	time 1.8974 (2.2178)	loss 3.7054 (3.5029)	grad_norm 1.4509 (1.5843)	
[2022-01-22 21:22:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][730/1251]	eta 0:19:14 lr 0.000430	time 2.2307 (2.2163)	loss 4.3474 (3.5068)	grad_norm 1.5000 (1.5837)	
[2022-01-22 21:22:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][740/1251]	eta 0:18:50 lr 0.000430	time 2.0081 (2.2125)	loss 3.6869 (3.5080)	grad_norm 1.7097 (1.5840)	
[2022-01-22 21:23:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][750/1251]	eta 0:18:28 lr 0.000430	time 2.2226 (2.2126)	loss 3.3761 (3.5124)	grad_norm 1.4980 (1.5849)	
[2022-01-22 21:23:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][760/1251]	eta 0:18:07 lr 0.000430	time 2.4825 (2.2139)	loss 4.0072 (3.5107)	grad_norm 1.7610 (1.5854)	
[2022-01-22 21:23:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][770/1251]	eta 0:17:44 lr 0.000430	time 1.9033 (2.2141)	loss 3.2192 (3.5105)	grad_norm 1.6071 (1.5849)	
[2022-01-22 21:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][780/1251]	eta 0:17:22 lr 0.000429	time 1.6363 (2.2123)	loss 2.1704 (3.5097)	grad_norm 1.4653 (1.5847)	
[2022-01-22 21:24:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][790/1251]	eta 0:16:59 lr 0.000429	time 3.0498 (2.2124)	loss 3.7830 (3.5077)	grad_norm 1.6182 (1.5846)	
[2022-01-22 21:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][800/1251]	eta 0:16:36 lr 0.000429	time 1.9161 (2.2104)	loss 3.1746 (3.5083)	grad_norm 1.3801 (1.5854)	
[2022-01-22 21:25:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][810/1251]	eta 0:16:14 lr 0.000429	time 2.1483 (2.2101)	loss 3.1649 (3.5076)	grad_norm 1.4056 (1.5859)	
[2022-01-22 21:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][820/1251]	eta 0:15:53 lr 0.000429	time 1.7456 (2.2114)	loss 3.9692 (3.5035)	grad_norm 1.6151 (1.5864)	
[2022-01-22 21:26:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][830/1251]	eta 0:15:31 lr 0.000429	time 3.1854 (2.2131)	loss 2.3467 (3.5033)	grad_norm 1.6867 (1.5870)	
[2022-01-22 21:26:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][840/1251]	eta 0:15:09 lr 0.000429	time 2.3662 (2.2137)	loss 3.8864 (3.5050)	grad_norm 1.3762 (1.5881)	
[2022-01-22 21:26:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][850/1251]	eta 0:14:47 lr 0.000429	time 1.9004 (2.2129)	loss 3.5774 (3.5046)	grad_norm 1.4901 (1.5879)	
[2022-01-22 21:27:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][860/1251]	eta 0:14:24 lr 0.000429	time 2.1797 (2.2116)	loss 3.0377 (3.5051)	grad_norm 1.4052 (1.5876)	
[2022-01-22 21:27:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][870/1251]	eta 0:14:01 lr 0.000429	time 1.9747 (2.2083)	loss 3.8195 (3.5054)	grad_norm 1.4688 (1.5872)	
[2022-01-22 21:27:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][880/1251]	eta 0:13:38 lr 0.000429	time 2.3037 (2.2066)	loss 3.4839 (3.5070)	grad_norm 1.8332 (1.5877)	
[2022-01-22 21:28:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][890/1251]	eta 0:13:15 lr 0.000429	time 1.8995 (2.2046)	loss 3.0809 (3.5088)	grad_norm 1.6817 (1.5876)	
[2022-01-22 21:28:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][900/1251]	eta 0:12:53 lr 0.000429	time 2.2384 (2.2030)	loss 3.9638 (3.5117)	grad_norm 1.3184 (1.5870)	
[2022-01-22 21:28:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][910/1251]	eta 0:12:31 lr 0.000429	time 2.3122 (2.2030)	loss 3.4419 (3.5094)	grad_norm 1.5945 (1.5865)	
[2022-01-22 21:29:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][920/1251]	eta 0:12:09 lr 0.000429	time 2.5779 (2.2038)	loss 3.9458 (3.5097)	grad_norm 1.7062 (1.5864)	
[2022-01-22 21:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][930/1251]	eta 0:11:47 lr 0.000429	time 2.1910 (2.2048)	loss 2.9180 (3.5105)	grad_norm 1.5866 (1.5873)	
[2022-01-22 21:29:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][940/1251]	eta 0:11:26 lr 0.000429	time 2.4335 (2.2069)	loss 2.5954 (3.5122)	grad_norm 1.7992 (1.5878)	
[2022-01-22 21:30:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][950/1251]	eta 0:11:04 lr 0.000429	time 2.2991 (2.2074)	loss 2.3807 (3.5113)	grad_norm 1.5082 (1.5884)	
[2022-01-22 21:30:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][960/1251]	eta 0:10:42 lr 0.000429	time 2.5523 (2.2088)	loss 3.9215 (3.5089)	grad_norm 1.6020 (1.5879)	
[2022-01-22 21:31:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][970/1251]	eta 0:10:20 lr 0.000429	time 2.1157 (2.2082)	loss 3.5570 (3.5108)	grad_norm 1.8392 (1.5886)	
[2022-01-22 21:31:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][980/1251]	eta 0:09:58 lr 0.000429	time 1.6235 (2.2082)	loss 3.4003 (3.5086)	grad_norm 1.8102 (1.5900)	
[2022-01-22 21:31:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][990/1251]	eta 0:09:36 lr 0.000429	time 1.8218 (2.2076)	loss 3.1765 (3.5073)	grad_norm 1.7666 (1.5900)	
[2022-01-22 21:32:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1000/1251]	eta 0:09:14 lr 0.000429	time 1.9581 (2.2079)	loss 2.3508 (3.5034)	grad_norm 1.7062 (1.5909)	
[2022-01-22 21:32:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1010/1251]	eta 0:08:51 lr 0.000429	time 1.8922 (2.2057)	loss 2.2489 (3.5006)	grad_norm 1.4176 (1.5916)	
[2022-01-22 21:32:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1020/1251]	eta 0:08:29 lr 0.000429	time 1.9753 (2.2051)	loss 3.6637 (3.5034)	grad_norm 1.4710 (1.5915)	
[2022-01-22 21:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1030/1251]	eta 0:08:07 lr 0.000428	time 1.5622 (2.2037)	loss 3.7854 (3.5029)	grad_norm 1.6380 (1.5914)	
[2022-01-22 21:33:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1040/1251]	eta 0:07:45 lr 0.000428	time 2.1565 (2.2045)	loss 4.0242 (3.5032)	grad_norm 1.8558 (1.5913)	
[2022-01-22 21:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1050/1251]	eta 0:07:23 lr 0.000428	time 2.0135 (2.2053)	loss 2.5437 (3.5028)	grad_norm 1.4834 (1.5911)	
[2022-01-22 21:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1060/1251]	eta 0:07:01 lr 0.000428	time 2.4371 (2.2053)	loss 3.7667 (3.5042)	grad_norm 1.7456 (1.5913)	
[2022-01-22 21:34:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1070/1251]	eta 0:06:38 lr 0.000428	time 1.6009 (2.2039)	loss 3.0455 (3.5043)	grad_norm 1.6403 (1.5908)	
[2022-01-22 21:35:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1080/1251]	eta 0:06:17 lr 0.000428	time 1.9708 (2.2049)	loss 3.8740 (3.5023)	grad_norm 1.4449 (1.5906)	
[2022-01-22 21:35:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1090/1251]	eta 0:05:54 lr 0.000428	time 2.2033 (2.2040)	loss 2.4400 (3.4997)	grad_norm 1.6055 (1.5906)	
[2022-01-22 21:35:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1100/1251]	eta 0:05:32 lr 0.000428	time 2.2826 (2.2044)	loss 4.0490 (3.4994)	grad_norm 1.5854 (1.5908)	
[2022-01-22 21:36:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1110/1251]	eta 0:05:10 lr 0.000428	time 1.8977 (2.2034)	loss 3.5371 (3.5005)	grad_norm 1.6399 (1.5904)	
[2022-01-22 21:36:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1120/1251]	eta 0:04:48 lr 0.000428	time 1.9915 (2.2033)	loss 3.6141 (3.5020)	grad_norm 1.5846 (1.5905)	
[2022-01-22 21:36:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1130/1251]	eta 0:04:26 lr 0.000428	time 2.3189 (2.2020)	loss 3.7417 (3.5047)	grad_norm 1.8417 (1.5915)	
[2022-01-22 21:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1140/1251]	eta 0:04:04 lr 0.000428	time 1.9482 (2.2015)	loss 2.9441 (3.5033)	grad_norm 1.7040 (1.5915)	
[2022-01-22 21:37:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1150/1251]	eta 0:03:42 lr 0.000428	time 1.7995 (2.2009)	loss 3.0471 (3.5051)	grad_norm 1.5972 (1.5913)	
[2022-01-22 21:37:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1160/1251]	eta 0:03:20 lr 0.000428	time 2.2856 (2.2003)	loss 3.0416 (3.5035)	grad_norm 1.6989 (1.5919)	
[2022-01-22 21:38:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1170/1251]	eta 0:02:58 lr 0.000428	time 1.9016 (2.2005)	loss 2.8764 (3.5028)	grad_norm 1.6369 (1.5919)	
[2022-01-22 21:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1180/1251]	eta 0:02:36 lr 0.000428	time 2.0136 (2.2005)	loss 3.6396 (3.5033)	grad_norm 1.6875 (1.5919)	
[2022-01-22 21:39:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1190/1251]	eta 0:02:14 lr 0.000428	time 1.9097 (2.2016)	loss 3.5123 (3.5021)	grad_norm 1.3918 (1.5914)	
[2022-01-22 21:39:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1200/1251]	eta 0:01:52 lr 0.000428	time 1.9910 (2.2020)	loss 3.2605 (3.5013)	grad_norm 1.5757 (1.5908)	
[2022-01-22 21:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1210/1251]	eta 0:01:30 lr 0.000428	time 2.1931 (2.2017)	loss 3.5906 (3.5035)	grad_norm 1.4494 (1.5915)	
[2022-01-22 21:40:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1220/1251]	eta 0:01:08 lr 0.000428	time 1.8764 (2.2006)	loss 3.2474 (3.5038)	grad_norm 1.4866 (1.5922)	
[2022-01-22 21:40:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1230/1251]	eta 0:00:46 lr 0.000428	time 1.9376 (2.1992)	loss 4.1510 (3.5073)	grad_norm 1.5397 (1.5926)	
[2022-01-22 21:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1240/1251]	eta 0:00:24 lr 0.000428	time 1.7984 (2.1985)	loss 4.0654 (3.5077)	grad_norm 1.5442 (1.5926)	
[2022-01-22 21:41:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [164/300][1250/1251]	eta 0:00:02 lr 0.000428	time 1.2945 (2.1931)	loss 2.6523 (3.5075)	grad_norm 1.4129 (1.5925)	
[2022-01-22 21:41:06 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 164 training takes 0:45:44
[2022-01-22 21:41:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.099 (18.099)	Loss 0.9847 (0.9847)	Acc@1 76.367 (76.367)	Acc@5 93.262 (93.262)	
[2022-01-22 21:41:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.018 (3.178)	Loss 1.0550 (0.9989)	Acc@1 76.465 (76.420)	Acc@5 91.797 (93.164)	
[2022-01-22 21:42:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.594 (2.641)	Loss 1.0388 (0.9913)	Acc@1 75.488 (76.567)	Acc@5 92.676 (93.355)	
[2022-01-22 21:42:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.305 (2.363)	Loss 0.9714 (0.9934)	Acc@1 76.465 (76.654)	Acc@5 94.043 (93.466)	
[2022-01-22 21:42:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.756 (2.185)	Loss 0.9198 (0.9927)	Acc@1 77.930 (76.620)	Acc@5 94.238 (93.526)	
[2022-01-22 21:42:43 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.644 Acc@5 93.596
[2022-01-22 21:42:43 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.6%
[2022-01-22 21:42:43 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.65%
[2022-01-22 21:43:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][0/1251]	eta 7:37:55 lr 0.000428	time 21.9625 (21.9625)	loss 3.2232 (3.2232)	grad_norm 1.6375 (1.6375)	
[2022-01-22 21:43:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][10/1251]	eta 1:22:53 lr 0.000428	time 2.8980 (4.0075)	loss 3.9464 (3.4119)	grad_norm 1.4874 (1.5617)	
[2022-01-22 21:43:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][20/1251]	eta 1:03:35 lr 0.000427	time 2.1838 (3.0997)	loss 2.9105 (3.3778)	grad_norm 1.5503 (1.5340)	
[2022-01-22 21:44:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][30/1251]	eta 0:56:24 lr 0.000427	time 1.6565 (2.7722)	loss 3.7441 (3.4682)	grad_norm 1.7703 (1.5407)	
[2022-01-22 21:44:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][40/1251]	eta 0:56:35 lr 0.000427	time 7.1801 (2.8036)	loss 3.6211 (3.4480)	grad_norm 1.7532 (1.5884)	
[2022-01-22 21:45:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][50/1251]	eta 0:54:16 lr 0.000427	time 1.9961 (2.7112)	loss 3.0820 (3.4542)	grad_norm 1.8952 (1.6335)	
[2022-01-22 21:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][60/1251]	eta 0:52:16 lr 0.000427	time 2.1747 (2.6338)	loss 3.1007 (3.4737)	grad_norm 1.5862 (1.6310)	
[2022-01-22 21:45:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][70/1251]	eta 0:50:04 lr 0.000427	time 1.8060 (2.5442)	loss 3.2743 (3.4950)	grad_norm 1.5903 (1.6350)	
[2022-01-22 21:46:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][80/1251]	eta 0:48:13 lr 0.000427	time 2.2339 (2.4707)	loss 3.1681 (3.5138)	grad_norm 1.7607 (1.6314)	
[2022-01-22 21:46:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][90/1251]	eta 0:47:07 lr 0.000427	time 1.6170 (2.4350)	loss 3.5925 (3.5092)	grad_norm 1.5669 (1.6299)	
[2022-01-22 21:46:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][100/1251]	eta 0:46:22 lr 0.000427	time 1.6135 (2.4171)	loss 3.4751 (3.5225)	grad_norm 1.8708 (1.6346)	
[2022-01-22 21:47:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][110/1251]	eta 0:45:28 lr 0.000427	time 2.2025 (2.3914)	loss 4.0200 (3.4973)	grad_norm 1.5494 (1.6288)	
[2022-01-22 21:47:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][120/1251]	eta 0:44:47 lr 0.000427	time 1.9725 (2.3759)	loss 3.4093 (3.4826)	grad_norm 1.4407 (1.6227)	
[2022-01-22 21:47:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][130/1251]	eta 0:43:50 lr 0.000427	time 1.9042 (2.3468)	loss 3.7442 (3.4704)	grad_norm 1.8369 (1.6275)	
[2022-01-22 21:48:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][140/1251]	eta 0:43:24 lr 0.000427	time 3.0258 (2.3442)	loss 3.7559 (3.4637)	grad_norm 1.9075 (1.6242)	
[2022-01-22 21:48:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][150/1251]	eta 0:42:56 lr 0.000427	time 2.1484 (2.3400)	loss 3.0708 (3.4620)	grad_norm 1.4554 (1.6190)	
[2022-01-22 21:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][160/1251]	eta 0:42:24 lr 0.000427	time 1.5268 (2.3322)	loss 4.0883 (3.4691)	grad_norm 1.5048 (1.6183)	
[2022-01-22 21:49:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][170/1251]	eta 0:41:56 lr 0.000427	time 2.1559 (2.3280)	loss 3.3585 (3.4804)	grad_norm 1.4228 (1.6161)	
[2022-01-22 21:49:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][180/1251]	eta 0:41:30 lr 0.000427	time 2.9927 (2.3258)	loss 3.5608 (3.4813)	grad_norm 2.9488 (1.6186)	
[2022-01-22 21:50:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][190/1251]	eta 0:40:54 lr 0.000427	time 1.8807 (2.3136)	loss 4.0357 (3.4808)	grad_norm 1.5718 (1.6195)	
[2022-01-22 21:50:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][200/1251]	eta 0:40:21 lr 0.000427	time 1.8479 (2.3042)	loss 3.3133 (3.4910)	grad_norm 1.7646 (1.6197)	
[2022-01-22 21:50:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][210/1251]	eta 0:39:45 lr 0.000427	time 1.8413 (2.2913)	loss 3.5317 (3.4985)	grad_norm 1.8349 (1.6215)	
[2022-01-22 21:51:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][220/1251]	eta 0:39:25 lr 0.000427	time 4.2432 (2.2941)	loss 3.5558 (3.4902)	grad_norm 1.5217 (1.6174)	
[2022-01-22 21:51:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][230/1251]	eta 0:39:05 lr 0.000427	time 2.8938 (2.2975)	loss 3.6322 (3.5013)	grad_norm 1.8192 (1.6167)	
[2022-01-22 21:51:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][240/1251]	eta 0:38:39 lr 0.000427	time 2.1080 (2.2944)	loss 3.8055 (3.4935)	grad_norm 1.3870 (1.6154)	
[2022-01-22 21:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][250/1251]	eta 0:38:09 lr 0.000427	time 1.9730 (2.2872)	loss 3.7426 (3.4963)	grad_norm 2.0224 (1.6131)	
[2022-01-22 21:52:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][260/1251]	eta 0:37:46 lr 0.000427	time 3.1630 (2.2874)	loss 3.1649 (3.5067)	grad_norm 1.4953 (1.6106)	
[2022-01-22 21:53:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][270/1251]	eta 0:37:12 lr 0.000426	time 1.7752 (2.2758)	loss 2.1497 (3.5022)	grad_norm 1.3861 (1.6124)	
[2022-01-22 21:53:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][280/1251]	eta 0:36:43 lr 0.000426	time 2.1140 (2.2689)	loss 3.0335 (3.4996)	grad_norm 1.4101 (1.6092)	
[2022-01-22 21:53:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][290/1251]	eta 0:36:14 lr 0.000426	time 1.8523 (2.2629)	loss 3.7608 (3.5020)	grad_norm 1.6468 (1.6080)	
[2022-01-22 21:54:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][300/1251]	eta 0:35:51 lr 0.000426	time 2.5201 (2.2623)	loss 2.5891 (3.4937)	grad_norm 1.4692 (1.6062)	
[2022-01-22 21:54:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][310/1251]	eta 0:35:24 lr 0.000426	time 2.0906 (2.2579)	loss 3.9004 (3.4979)	grad_norm 1.8997 (1.6061)	
[2022-01-22 21:54:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][320/1251]	eta 0:35:01 lr 0.000426	time 2.7155 (2.2571)	loss 3.8925 (3.4990)	grad_norm 1.5367 (1.6084)	
[2022-01-22 21:55:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][330/1251]	eta 0:34:36 lr 0.000426	time 2.5402 (2.2549)	loss 3.8428 (3.4930)	grad_norm 1.8179 (1.6121)	
[2022-01-22 21:55:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][340/1251]	eta 0:34:12 lr 0.000426	time 2.1572 (2.2526)	loss 3.4681 (3.4977)	grad_norm 1.5929 (1.6114)	
[2022-01-22 21:55:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][350/1251]	eta 0:33:44 lr 0.000426	time 1.4968 (2.2472)	loss 3.6074 (3.4946)	grad_norm 1.7420 (1.6117)	
[2022-01-22 21:56:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][360/1251]	eta 0:33:20 lr 0.000426	time 2.2965 (2.2452)	loss 3.8568 (3.4921)	grad_norm 1.5317 (1.6128)	
[2022-01-22 21:56:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][370/1251]	eta 0:32:55 lr 0.000426	time 2.2497 (2.2419)	loss 2.5457 (3.4841)	grad_norm 1.9673 (1.6147)	
[2022-01-22 21:56:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][380/1251]	eta 0:32:31 lr 0.000426	time 2.5265 (2.2408)	loss 3.6118 (3.4851)	grad_norm 1.4736 (1.6136)	
[2022-01-22 21:57:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][390/1251]	eta 0:32:08 lr 0.000426	time 1.5778 (2.2397)	loss 4.2114 (3.4964)	grad_norm 1.9355 (1.6140)	
[2022-01-22 21:57:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][400/1251]	eta 0:31:48 lr 0.000426	time 2.8704 (2.2425)	loss 2.8277 (3.4924)	grad_norm 1.6189 (1.6145)	
[2022-01-22 21:58:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][410/1251]	eta 0:31:26 lr 0.000426	time 3.6968 (2.2437)	loss 3.7009 (3.4938)	grad_norm 1.9770 (1.6163)	
[2022-01-22 21:58:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][420/1251]	eta 0:31:04 lr 0.000426	time 2.5753 (2.2436)	loss 3.8100 (3.4960)	grad_norm 1.7554 (1.6166)	
[2022-01-22 21:58:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][430/1251]	eta 0:30:39 lr 0.000426	time 1.5666 (2.2406)	loss 4.2635 (3.4985)	grad_norm 1.5581 (1.6141)	
[2022-01-22 21:59:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][440/1251]	eta 0:30:13 lr 0.000426	time 1.6845 (2.2361)	loss 3.4159 (3.4928)	grad_norm 1.5057 (1.6132)	
[2022-01-22 21:59:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][450/1251]	eta 0:29:47 lr 0.000426	time 2.8526 (2.2321)	loss 2.6322 (3.4958)	grad_norm 1.5005 (1.6130)	
[2022-01-22 21:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][460/1251]	eta 0:29:21 lr 0.000426	time 2.0076 (2.2265)	loss 3.4965 (3.4971)	grad_norm 1.5309 (1.6136)	
[2022-01-22 22:00:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][470/1251]	eta 0:29:00 lr 0.000426	time 2.4996 (2.2280)	loss 2.9937 (3.4979)	grad_norm 1.6511 (1.6132)	
[2022-01-22 22:00:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][480/1251]	eta 0:28:39 lr 0.000426	time 1.9146 (2.2296)	loss 2.7958 (3.4967)	grad_norm 1.9221 (1.6135)	
[2022-01-22 22:01:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][490/1251]	eta 0:28:19 lr 0.000426	time 2.6095 (2.2330)	loss 3.2093 (3.5011)	grad_norm 1.5613 (1.6122)	
[2022-01-22 22:01:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][500/1251]	eta 0:28:00 lr 0.000426	time 2.2153 (2.2383)	loss 3.9931 (3.5008)	grad_norm 1.5910 (1.6117)	
[2022-01-22 22:01:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][510/1251]	eta 0:27:38 lr 0.000425	time 2.0117 (2.2382)	loss 3.5667 (3.4981)	grad_norm 1.3869 (1.6105)	
[2022-01-22 22:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][520/1251]	eta 0:27:12 lr 0.000425	time 1.7217 (2.2331)	loss 3.9614 (3.5015)	grad_norm 1.5483 (1.6086)	
[2022-01-22 22:02:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][530/1251]	eta 0:26:45 lr 0.000425	time 1.7783 (2.2270)	loss 2.3391 (3.4975)	grad_norm 1.5827 (1.6079)	
[2022-01-22 22:02:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][540/1251]	eta 0:26:20 lr 0.000425	time 2.0521 (2.2231)	loss 3.5851 (3.4982)	grad_norm 1.4718 (1.6075)	
[2022-01-22 22:03:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][550/1251]	eta 0:25:55 lr 0.000425	time 1.7774 (2.2191)	loss 4.0501 (3.4968)	grad_norm 1.6389 (1.6065)	
[2022-01-22 22:03:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][560/1251]	eta 0:25:33 lr 0.000425	time 2.4741 (2.2190)	loss 4.1970 (3.4944)	grad_norm 1.7943 (1.6063)	
[2022-01-22 22:03:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][570/1251]	eta 0:25:10 lr 0.000425	time 2.0661 (2.2179)	loss 3.5057 (3.4982)	grad_norm 1.8219 (1.6076)	
[2022-01-22 22:04:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][580/1251]	eta 0:24:49 lr 0.000425	time 2.1689 (2.2199)	loss 2.6657 (3.4953)	grad_norm 1.5150 (1.6064)	
[2022-01-22 22:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][590/1251]	eta 0:24:29 lr 0.000425	time 3.1660 (2.2228)	loss 3.7069 (3.4971)	grad_norm 1.6779 (1.6075)	
[2022-01-22 22:05:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][600/1251]	eta 0:24:08 lr 0.000425	time 3.0025 (2.2251)	loss 3.6879 (3.4988)	grad_norm 1.3811 (1.6065)	
[2022-01-22 22:05:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][610/1251]	eta 0:23:47 lr 0.000425	time 2.5806 (2.2273)	loss 3.1557 (3.4980)	grad_norm 1.7183 (1.6064)	
[2022-01-22 22:05:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][620/1251]	eta 0:23:23 lr 0.000425	time 1.6462 (2.2242)	loss 2.3194 (3.4943)	grad_norm 1.8358 (1.6070)	
[2022-01-22 22:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][630/1251]	eta 0:23:00 lr 0.000425	time 1.8200 (2.2227)	loss 4.2771 (3.4961)	grad_norm 1.7079 (1.6074)	
[2022-01-22 22:06:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][640/1251]	eta 0:22:36 lr 0.000425	time 1.6378 (2.2195)	loss 4.0647 (3.4964)	grad_norm 1.5575 (1.6076)	
[2022-01-22 22:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][650/1251]	eta 0:22:15 lr 0.000425	time 3.3090 (2.2217)	loss 2.5133 (3.4972)	grad_norm 1.4421 (1.6064)	
[2022-01-22 22:07:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][660/1251]	eta 0:21:53 lr 0.000425	time 1.8461 (2.2223)	loss 3.4364 (3.4998)	grad_norm 1.4588 (1.6060)	
[2022-01-22 22:07:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][670/1251]	eta 0:21:31 lr 0.000425	time 2.3437 (2.2223)	loss 3.9474 (3.5034)	grad_norm 1.7567 (1.6073)	
[2022-01-22 22:07:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][680/1251]	eta 0:21:07 lr 0.000425	time 2.2143 (2.2199)	loss 3.1113 (3.5052)	grad_norm 1.7078 (1.6081)	
[2022-01-22 22:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][690/1251]	eta 0:20:45 lr 0.000425	time 2.8615 (2.2200)	loss 4.0089 (3.5037)	grad_norm 1.5179 (1.6079)	
[2022-01-22 22:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][700/1251]	eta 0:20:23 lr 0.000425	time 1.9341 (2.2199)	loss 3.8565 (3.5065)	grad_norm 1.6061 (1.6083)	
[2022-01-22 22:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][710/1251]	eta 0:20:00 lr 0.000425	time 2.1764 (2.2193)	loss 4.0472 (3.5078)	grad_norm 1.6073 (1.6099)	
[2022-01-22 22:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][720/1251]	eta 0:19:38 lr 0.000425	time 2.1297 (2.2196)	loss 3.9370 (3.5057)	grad_norm 1.5723 (1.6096)	
[2022-01-22 22:09:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][730/1251]	eta 0:19:17 lr 0.000425	time 1.8543 (2.2213)	loss 2.9825 (3.5056)	grad_norm 1.5957 (1.6098)	
[2022-01-22 22:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][740/1251]	eta 0:18:53 lr 0.000425	time 1.6197 (2.2178)	loss 3.7267 (3.5047)	grad_norm 1.5527 (1.6093)	
[2022-01-22 22:10:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][750/1251]	eta 0:18:29 lr 0.000424	time 1.7946 (2.2150)	loss 3.2821 (3.5058)	grad_norm 1.5212 (1.6105)	
[2022-01-22 22:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][760/1251]	eta 0:18:07 lr 0.000424	time 2.1382 (2.2144)	loss 3.5097 (3.5045)	grad_norm 1.4558 (1.6104)	
[2022-01-22 22:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][770/1251]	eta 0:17:46 lr 0.000424	time 2.6273 (2.2166)	loss 3.7739 (3.5048)	grad_norm 1.5559 (1.6107)	
[2022-01-22 22:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][780/1251]	eta 0:17:23 lr 0.000424	time 2.1862 (2.2148)	loss 4.4693 (3.5054)	grad_norm 1.7976 (1.6116)	
[2022-01-22 22:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][790/1251]	eta 0:17:00 lr 0.000424	time 1.8652 (2.2139)	loss 3.5090 (3.5065)	grad_norm 1.8980 (1.6129)	
[2022-01-22 22:12:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][800/1251]	eta 0:16:38 lr 0.000424	time 1.6670 (2.2130)	loss 3.2771 (3.5061)	grad_norm 1.5838 (1.6128)	
[2022-01-22 22:12:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][810/1251]	eta 0:16:16 lr 0.000424	time 2.7760 (2.2139)	loss 3.5509 (3.5063)	grad_norm 1.5308 (1.6138)	
[2022-01-22 22:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][820/1251]	eta 0:15:53 lr 0.000424	time 1.6300 (2.2117)	loss 2.6795 (3.5069)	grad_norm 1.6386 (1.6139)	
[2022-01-22 22:13:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][830/1251]	eta 0:15:31 lr 0.000424	time 1.9845 (2.2117)	loss 3.4117 (3.5061)	grad_norm 1.4655 (1.6130)	
[2022-01-22 22:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][840/1251]	eta 0:15:09 lr 0.000424	time 1.5524 (2.2122)	loss 2.6677 (3.5029)	grad_norm 1.4864 (1.6120)	
[2022-01-22 22:14:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][850/1251]	eta 0:14:47 lr 0.000424	time 2.8340 (2.2137)	loss 3.3745 (3.5027)	grad_norm 1.7956 (1.6119)	
[2022-01-22 22:14:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][860/1251]	eta 0:14:25 lr 0.000424	time 2.2480 (2.2145)	loss 2.3178 (3.5014)	grad_norm 1.4122 (1.6123)	
[2022-01-22 22:14:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][870/1251]	eta 0:14:02 lr 0.000424	time 1.8873 (2.2123)	loss 4.4696 (3.5007)	grad_norm 1.7948 (1.6122)	
[2022-01-22 22:15:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][880/1251]	eta 0:13:40 lr 0.000424	time 1.6884 (2.2110)	loss 4.0634 (3.5026)	grad_norm 1.6374 (1.6125)	
[2022-01-22 22:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][890/1251]	eta 0:13:17 lr 0.000424	time 1.5880 (2.2100)	loss 2.4407 (3.4989)	grad_norm 1.4010 (1.6130)	
[2022-01-22 22:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][900/1251]	eta 0:12:55 lr 0.000424	time 2.8467 (2.2093)	loss 3.1547 (3.4986)	grad_norm 1.5502 (1.6137)	
[2022-01-22 22:16:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][910/1251]	eta 0:12:33 lr 0.000424	time 2.1790 (2.2104)	loss 2.6545 (3.4959)	grad_norm 1.4672 (1.6127)	
[2022-01-22 22:16:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][920/1251]	eta 0:12:13 lr 0.000424	time 1.8633 (2.2148)	loss 3.6854 (3.4964)	grad_norm 1.5749 (1.6117)	
[2022-01-22 22:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][930/1251]	eta 0:11:51 lr 0.000424	time 3.1723 (2.2173)	loss 3.6537 (3.4963)	grad_norm 1.5539 (1.6116)	
[2022-01-22 22:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][940/1251]	eta 0:11:29 lr 0.000424	time 2.2292 (2.2175)	loss 3.3869 (3.4923)	grad_norm 1.7015 (1.6122)	
[2022-01-22 22:17:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][950/1251]	eta 0:11:06 lr 0.000424	time 1.9103 (2.2156)	loss 3.5954 (3.4925)	grad_norm 1.5448 (1.6119)	
[2022-01-22 22:18:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][960/1251]	eta 0:10:44 lr 0.000424	time 1.9171 (2.2136)	loss 3.3083 (3.4924)	grad_norm 1.4937 (1.6117)	
[2022-01-22 22:18:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][970/1251]	eta 0:10:21 lr 0.000424	time 1.9672 (2.2107)	loss 3.8165 (3.4917)	grad_norm 1.4746 (1.6119)	
[2022-01-22 22:18:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][980/1251]	eta 0:09:58 lr 0.000424	time 1.8281 (2.2096)	loss 3.7825 (3.4884)	grad_norm 1.4954 (1.6115)	
[2022-01-22 22:19:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][990/1251]	eta 0:09:37 lr 0.000424	time 2.4636 (2.2108)	loss 3.6547 (3.4887)	grad_norm 1.5155 (1.6111)	
[2022-01-22 22:19:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1000/1251]	eta 0:09:15 lr 0.000423	time 2.5714 (2.2115)	loss 3.7403 (3.4889)	grad_norm 1.4910 (1.6105)	
[2022-01-22 22:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1010/1251]	eta 0:08:53 lr 0.000423	time 2.1808 (2.2122)	loss 3.7376 (3.4907)	grad_norm 1.4595 (1.6103)	
[2022-01-22 22:20:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1020/1251]	eta 0:08:31 lr 0.000423	time 1.9987 (2.2124)	loss 3.4386 (3.4932)	grad_norm 1.5381 (1.6097)	
[2022-01-22 22:20:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1030/1251]	eta 0:08:09 lr 0.000423	time 1.6930 (2.2128)	loss 3.4540 (3.4924)	grad_norm 1.5343 (1.6093)	
[2022-01-22 22:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1040/1251]	eta 0:07:47 lr 0.000423	time 2.2206 (2.2147)	loss 2.8580 (3.4896)	grad_norm 1.6608 (1.6098)	
[2022-01-22 22:21:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1050/1251]	eta 0:07:25 lr 0.000423	time 2.2378 (2.2144)	loss 3.5718 (3.4907)	grad_norm 1.6742 (1.6095)	
[2022-01-22 22:21:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1060/1251]	eta 0:07:02 lr 0.000423	time 2.0121 (2.2127)	loss 3.9144 (3.4869)	grad_norm 1.7706 (1.6094)	
[2022-01-22 22:22:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1070/1251]	eta 0:06:39 lr 0.000423	time 1.7434 (2.2097)	loss 2.1374 (3.4854)	grad_norm 1.7355 (1.6101)	
[2022-01-22 22:22:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1080/1251]	eta 0:06:17 lr 0.000423	time 2.2303 (2.2093)	loss 3.8059 (3.4836)	grad_norm 1.9325 (1.6108)	
[2022-01-22 22:22:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1090/1251]	eta 0:05:55 lr 0.000423	time 1.8750 (2.2083)	loss 3.6875 (3.4824)	grad_norm 1.6903 (1.6115)	
[2022-01-22 22:23:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1100/1251]	eta 0:05:33 lr 0.000423	time 2.3019 (2.2082)	loss 3.6761 (3.4832)	grad_norm 1.4193 (1.6111)	
[2022-01-22 22:23:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1110/1251]	eta 0:05:11 lr 0.000423	time 2.4934 (2.2084)	loss 2.6713 (3.4836)	grad_norm 1.6250 (1.6116)	
[2022-01-22 22:24:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1120/1251]	eta 0:04:49 lr 0.000423	time 2.1494 (2.2110)	loss 3.9496 (3.4857)	grad_norm 1.7401 (1.6122)	
[2022-01-22 22:24:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1130/1251]	eta 0:04:27 lr 0.000423	time 1.7786 (2.2110)	loss 3.7691 (3.4844)	grad_norm 1.9443 (1.6126)	
[2022-01-22 22:24:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1140/1251]	eta 0:04:05 lr 0.000423	time 2.1180 (2.2107)	loss 3.1367 (3.4852)	grad_norm 1.6503 (1.6129)	
[2022-01-22 22:25:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1150/1251]	eta 0:03:43 lr 0.000423	time 1.8725 (2.2102)	loss 3.8198 (3.4855)	grad_norm 1.5396 (1.6130)	
[2022-01-22 22:25:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1160/1251]	eta 0:03:20 lr 0.000423	time 1.9569 (2.2082)	loss 3.5381 (3.4847)	grad_norm 1.3368 (1.6127)	
[2022-01-22 22:25:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1170/1251]	eta 0:02:58 lr 0.000423	time 1.7209 (2.2081)	loss 2.8839 (3.4842)	grad_norm 1.4116 (1.6129)	
[2022-01-22 22:26:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1180/1251]	eta 0:02:36 lr 0.000423	time 2.0856 (2.2081)	loss 3.6455 (3.4853)	grad_norm 1.4740 (1.6122)	
[2022-01-22 22:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1190/1251]	eta 0:02:14 lr 0.000423	time 2.3502 (2.2085)	loss 4.1416 (3.4874)	grad_norm 1.7985 (1.6118)	
[2022-01-22 22:26:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1200/1251]	eta 0:01:52 lr 0.000423	time 2.9784 (2.2077)	loss 3.9733 (3.4904)	grad_norm 1.5460 (1.6123)	
[2022-01-22 22:27:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1210/1251]	eta 0:01:30 lr 0.000423	time 1.8199 (2.2081)	loss 3.9831 (3.4904)	grad_norm 1.5214 (1.6119)	
[2022-01-22 22:27:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1220/1251]	eta 0:01:08 lr 0.000423	time 1.9445 (2.2069)	loss 3.3203 (3.4892)	grad_norm 1.5310 (1.6118)	
[2022-01-22 22:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1230/1251]	eta 0:00:46 lr 0.000423	time 2.5440 (2.2064)	loss 3.8161 (3.4863)	grad_norm 1.6040 (1.6117)	
[2022-01-22 22:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1240/1251]	eta 0:00:24 lr 0.000422	time 2.0451 (2.2051)	loss 3.5194 (3.4823)	grad_norm 1.4677 (1.6119)	
[2022-01-22 22:28:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [165/300][1250/1251]	eta 0:00:02 lr 0.000422	time 1.1663 (2.1996)	loss 4.0310 (3.4826)	grad_norm 1.4571 (1.6122)	
[2022-01-22 22:28:35 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 165 training takes 0:45:52
[2022-01-22 22:28:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.150 (18.150)	Loss 1.0073 (1.0073)	Acc@1 75.293 (75.293)	Acc@5 94.141 (94.141)	
[2022-01-22 22:29:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.691 (3.374)	Loss 1.0108 (1.0001)	Acc@1 75.098 (76.474)	Acc@5 93.555 (93.466)	
[2022-01-22 22:29:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.229 (2.660)	Loss 0.9316 (0.9911)	Acc@1 77.832 (76.758)	Acc@5 94.434 (93.690)	
[2022-01-22 22:29:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.270 (2.355)	Loss 0.8833 (0.9788)	Acc@1 79.688 (77.007)	Acc@5 95.312 (93.782)	
[2022-01-22 22:30:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.206 (2.211)	Loss 1.0590 (0.9870)	Acc@1 75.098 (76.829)	Acc@5 92.773 (93.581)	
[2022-01-22 22:30:14 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.816 Acc@5 93.570
[2022-01-22 22:30:14 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.8%
[2022-01-22 22:30:14 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.82%
[2022-01-22 22:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][0/1251]	eta 7:37:39 lr 0.000422	time 21.9504 (21.9504)	loss 3.9292 (3.9292)	grad_norm 1.9007 (1.9007)	
[2022-01-22 22:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][10/1251]	eta 1:24:16 lr 0.000422	time 1.9639 (4.0747)	loss 3.0035 (3.3708)	grad_norm 1.5633 (1.6475)	
[2022-01-22 22:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][20/1251]	eta 1:05:34 lr 0.000422	time 1.5062 (3.1959)	loss 3.3466 (3.3749)	grad_norm 1.7248 (1.6225)	
[2022-01-22 22:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][30/1251]	eta 0:58:44 lr 0.000422	time 2.2093 (2.8866)	loss 3.3506 (3.3214)	grad_norm 1.8187 (1.6103)	
[2022-01-22 22:32:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][40/1251]	eta 0:55:57 lr 0.000422	time 3.8851 (2.7728)	loss 3.0263 (3.3909)	grad_norm 1.6390 (1.6139)	
[2022-01-22 22:32:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][50/1251]	eta 0:53:43 lr 0.000422	time 3.5146 (2.6841)	loss 3.6734 (3.3945)	grad_norm 1.4708 (1.5983)	
[2022-01-22 22:32:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][60/1251]	eta 0:51:18 lr 0.000422	time 2.0269 (2.5846)	loss 2.7253 (3.4122)	grad_norm 1.3873 (1.5786)	
[2022-01-22 22:33:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][70/1251]	eta 0:49:35 lr 0.000422	time 1.9872 (2.5192)	loss 3.4548 (3.4445)	grad_norm 1.9123 (1.5894)	
[2022-01-22 22:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][80/1251]	eta 0:48:38 lr 0.000422	time 3.1099 (2.4921)	loss 3.6035 (3.4797)	grad_norm 1.8264 (1.5930)	
[2022-01-22 22:33:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][90/1251]	eta 0:47:35 lr 0.000422	time 3.0156 (2.4595)	loss 3.8177 (3.4955)	grad_norm 1.8195 (1.6002)	
[2022-01-22 22:34:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][100/1251]	eta 0:46:23 lr 0.000422	time 2.0526 (2.4184)	loss 3.9651 (3.4942)	grad_norm 1.4497 (1.6067)	
[2022-01-22 22:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][110/1251]	eta 0:45:15 lr 0.000422	time 1.5831 (2.3799)	loss 3.5941 (3.4719)	grad_norm 1.7772 (1.6164)	
[2022-01-22 22:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][120/1251]	eta 0:44:22 lr 0.000422	time 2.3061 (2.3538)	loss 4.1571 (3.4761)	grad_norm 2.0347 (1.6176)	
[2022-01-22 22:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][130/1251]	eta 0:43:40 lr 0.000422	time 2.6081 (2.3378)	loss 3.2777 (3.4536)	grad_norm 1.9746 (1.6175)	
[2022-01-22 22:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][140/1251]	eta 0:43:04 lr 0.000422	time 1.8401 (2.3262)	loss 3.8726 (3.4671)	grad_norm 1.6844 (1.6141)	
[2022-01-22 22:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][150/1251]	eta 0:42:32 lr 0.000422	time 2.1984 (2.3185)	loss 2.8953 (3.4607)	grad_norm 1.5166 (1.6143)	
[2022-01-22 22:36:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][160/1251]	eta 0:41:56 lr 0.000422	time 2.2006 (2.3069)	loss 3.8382 (3.4483)	grad_norm 1.5984 (1.6208)	
[2022-01-22 22:36:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][170/1251]	eta 0:41:39 lr 0.000422	time 3.4342 (2.3119)	loss 2.4014 (3.4546)	grad_norm 1.5954 (1.6154)	
[2022-01-22 22:37:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][180/1251]	eta 0:41:16 lr 0.000422	time 2.4079 (2.3122)	loss 3.4535 (3.4312)	grad_norm 1.5451 (1.6115)	
[2022-01-22 22:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][190/1251]	eta 0:40:43 lr 0.000422	time 1.7564 (2.3028)	loss 3.7920 (3.4299)	grad_norm 1.6025 (1.6096)	
[2022-01-22 22:37:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][200/1251]	eta 0:40:16 lr 0.000422	time 1.9863 (2.2995)	loss 3.7322 (3.4421)	grad_norm 1.4664 (1.6082)	
[2022-01-22 22:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][210/1251]	eta 0:39:49 lr 0.000422	time 2.4922 (2.2957)	loss 3.5182 (3.4311)	grad_norm 1.5888 (1.6079)	
[2022-01-22 22:38:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][220/1251]	eta 0:39:18 lr 0.000422	time 2.2741 (2.2881)	loss 3.2131 (3.4234)	grad_norm 1.5397 (1.6116)	
[2022-01-22 22:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][230/1251]	eta 0:38:49 lr 0.000422	time 1.8805 (2.2816)	loss 3.7909 (3.4225)	grad_norm 1.7846 (1.6154)	
[2022-01-22 22:39:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][240/1251]	eta 0:38:20 lr 0.000421	time 2.1934 (2.2758)	loss 3.9626 (3.4229)	grad_norm 1.4715 (1.6190)	
[2022-01-22 22:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][250/1251]	eta 0:37:58 lr 0.000421	time 3.1317 (2.2762)	loss 4.1395 (3.4198)	grad_norm 1.8441 (1.6192)	
[2022-01-22 22:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][260/1251]	eta 0:37:25 lr 0.000421	time 2.0235 (2.2660)	loss 3.9309 (3.4305)	grad_norm 1.5274 (1.6187)	
[2022-01-22 22:40:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][270/1251]	eta 0:36:55 lr 0.000421	time 1.9398 (2.2588)	loss 2.5294 (3.4348)	grad_norm 1.3312 (1.6157)	
[2022-01-22 22:40:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][280/1251]	eta 0:36:31 lr 0.000421	time 2.2060 (2.2566)	loss 3.8375 (3.4412)	grad_norm 1.7570 (1.6152)	
[2022-01-22 22:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][290/1251]	eta 0:36:02 lr 0.000421	time 1.6297 (2.2503)	loss 3.3442 (3.4409)	grad_norm 1.9816 (1.6150)	
[2022-01-22 22:41:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][300/1251]	eta 0:35:43 lr 0.000421	time 1.7770 (2.2535)	loss 3.8823 (3.4471)	grad_norm 1.4091 (1.6114)	
[2022-01-22 22:41:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][310/1251]	eta 0:35:21 lr 0.000421	time 2.4055 (2.2540)	loss 3.9818 (3.4537)	grad_norm 1.3764 (1.6103)	
[2022-01-22 22:42:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][320/1251]	eta 0:34:59 lr 0.000421	time 2.1822 (2.2546)	loss 2.5115 (3.4459)	grad_norm 1.6709 (1.6090)	
[2022-01-22 22:42:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][330/1251]	eta 0:34:38 lr 0.000421	time 2.1993 (2.2570)	loss 3.5797 (3.4548)	grad_norm 1.5155 (1.6134)	
[2022-01-22 22:43:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][340/1251]	eta 0:34:16 lr 0.000421	time 1.9192 (2.2570)	loss 3.9949 (3.4555)	grad_norm 1.6609 (1.6140)	
[2022-01-22 22:43:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][350/1251]	eta 0:33:53 lr 0.000421	time 2.8605 (2.2571)	loss 3.8436 (3.4604)	grad_norm 1.4143 (1.6129)	
[2022-01-22 22:43:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][360/1251]	eta 0:33:24 lr 0.000421	time 1.6948 (2.2502)	loss 3.8490 (3.4566)	grad_norm 1.6942 (1.6136)	
[2022-01-22 22:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][370/1251]	eta 0:32:57 lr 0.000421	time 1.9203 (2.2444)	loss 3.7117 (3.4622)	grad_norm 1.6844 (1.6192)	
[2022-01-22 22:44:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][380/1251]	eta 0:32:35 lr 0.000421	time 2.3662 (2.2450)	loss 3.5413 (3.4603)	grad_norm 1.6174 (1.6219)	
[2022-01-22 22:44:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][390/1251]	eta 0:32:12 lr 0.000421	time 2.5374 (2.2446)	loss 4.1771 (3.4613)	grad_norm 1.7907 (1.6238)	
[2022-01-22 22:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][400/1251]	eta 0:31:50 lr 0.000421	time 2.1754 (2.2448)	loss 3.1796 (3.4578)	grad_norm 1.6510 (1.6237)	
[2022-01-22 22:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][410/1251]	eta 0:31:25 lr 0.000421	time 1.8669 (2.2423)	loss 3.0863 (3.4542)	grad_norm 1.3804 (1.6232)	
[2022-01-22 22:45:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][420/1251]	eta 0:31:03 lr 0.000421	time 1.8751 (2.2427)	loss 2.7883 (3.4571)	grad_norm 1.5179 (1.6227)	
[2022-01-22 22:46:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][430/1251]	eta 0:30:39 lr 0.000421	time 1.8956 (2.2400)	loss 3.7304 (3.4571)	grad_norm 1.6755 (1.6233)	
[2022-01-22 22:46:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][440/1251]	eta 0:30:12 lr 0.000421	time 2.0510 (2.2343)	loss 4.1243 (3.4570)	grad_norm 1.5690 (1.6233)	
[2022-01-22 22:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][450/1251]	eta 0:29:47 lr 0.000421	time 2.1243 (2.2314)	loss 4.0075 (3.4522)	grad_norm 1.6455 (1.6226)	
[2022-01-22 22:47:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][460/1251]	eta 0:29:22 lr 0.000421	time 2.1930 (2.2285)	loss 3.9399 (3.4563)	grad_norm 1.5283 (1.6225)	
[2022-01-22 22:47:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][470/1251]	eta 0:28:58 lr 0.000421	time 2.1799 (2.2264)	loss 2.9986 (3.4575)	grad_norm 1.5563 (1.6232)	
[2022-01-22 22:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][480/1251]	eta 0:28:32 lr 0.000420	time 1.9448 (2.2217)	loss 3.7774 (3.4554)	grad_norm 1.5834 (1.6225)	
[2022-01-22 22:48:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][490/1251]	eta 0:28:06 lr 0.000420	time 2.2896 (2.2166)	loss 3.6716 (3.4586)	grad_norm 1.3678 (1.6222)	
[2022-01-22 22:48:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][500/1251]	eta 0:27:44 lr 0.000420	time 2.2559 (2.2163)	loss 4.0634 (3.4575)	grad_norm 1.5492 (1.6233)	
[2022-01-22 22:49:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][510/1251]	eta 0:27:21 lr 0.000420	time 1.8571 (2.2154)	loss 2.3937 (3.4602)	grad_norm 1.5831 (1.6229)	
[2022-01-22 22:49:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][520/1251]	eta 0:27:00 lr 0.000420	time 2.1229 (2.2165)	loss 3.9368 (3.4579)	grad_norm 1.7346 (1.6218)	
[2022-01-22 22:49:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][530/1251]	eta 0:26:38 lr 0.000420	time 2.4961 (2.2177)	loss 3.7208 (3.4614)	grad_norm 1.7512 (1.6214)	
[2022-01-22 22:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][540/1251]	eta 0:26:17 lr 0.000420	time 2.4319 (2.2193)	loss 3.2882 (3.4580)	grad_norm 1.6294 (1.6210)	
[2022-01-22 22:50:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][550/1251]	eta 0:25:56 lr 0.000420	time 1.9124 (2.2201)	loss 2.7249 (3.4543)	grad_norm 1.5476 (1.6215)	
[2022-01-22 22:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][560/1251]	eta 0:25:36 lr 0.000420	time 3.0536 (2.2230)	loss 3.7637 (3.4573)	grad_norm 1.8963 (1.6202)	
[2022-01-22 22:51:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][570/1251]	eta 0:25:13 lr 0.000420	time 2.4895 (2.2229)	loss 2.9538 (3.4586)	grad_norm 1.7276 (1.6219)	
[2022-01-22 22:51:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][580/1251]	eta 0:24:52 lr 0.000420	time 2.2883 (2.2241)	loss 3.4172 (3.4581)	grad_norm 1.7265 (1.6215)	
[2022-01-22 22:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][590/1251]	eta 0:24:27 lr 0.000420	time 1.6255 (2.2198)	loss 3.6763 (3.4591)	grad_norm 1.5578 (1.6206)	
[2022-01-22 22:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][600/1251]	eta 0:24:05 lr 0.000420	time 2.2492 (2.2197)	loss 3.6558 (3.4604)	grad_norm 1.4299 (1.6203)	
[2022-01-22 22:52:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][610/1251]	eta 0:23:42 lr 0.000420	time 2.5945 (2.2188)	loss 3.5174 (3.4602)	grad_norm 1.6068 (1.6206)	
[2022-01-22 22:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][620/1251]	eta 0:23:18 lr 0.000420	time 2.1599 (2.2168)	loss 3.1985 (3.4626)	grad_norm 1.7117 (1.6216)	
[2022-01-22 22:53:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][630/1251]	eta 0:22:56 lr 0.000420	time 2.4659 (2.2166)	loss 3.7669 (3.4632)	grad_norm 1.6171 (1.6225)	
[2022-01-22 22:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][640/1251]	eta 0:22:34 lr 0.000420	time 2.0910 (2.2175)	loss 3.4708 (3.4637)	grad_norm 1.7314 (1.6243)	
[2022-01-22 22:54:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][650/1251]	eta 0:22:13 lr 0.000420	time 3.0137 (2.2193)	loss 4.3939 (3.4642)	grad_norm 1.4349 (1.6222)	
[2022-01-22 22:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][660/1251]	eta 0:21:49 lr 0.000420	time 1.6612 (2.2163)	loss 4.0402 (3.4631)	grad_norm 1.7026 (1.6239)	
[2022-01-22 22:54:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][670/1251]	eta 0:21:26 lr 0.000420	time 1.8507 (2.2135)	loss 3.5652 (3.4643)	grad_norm 1.3378 (1.6229)	
[2022-01-22 22:55:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][680/1251]	eta 0:21:02 lr 0.000420	time 2.2829 (2.2111)	loss 3.7044 (3.4633)	grad_norm 1.8531 (1.6241)	
[2022-01-22 22:55:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][690/1251]	eta 0:20:38 lr 0.000420	time 1.9281 (2.2077)	loss 3.8222 (3.4656)	grad_norm 1.4532 (1.6229)	
[2022-01-22 22:56:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][700/1251]	eta 0:20:16 lr 0.000420	time 1.9412 (2.2071)	loss 3.8323 (3.4679)	grad_norm 1.7797 (1.6235)	
[2022-01-22 22:56:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][710/1251]	eta 0:19:54 lr 0.000420	time 2.2077 (2.2081)	loss 4.0179 (3.4642)	grad_norm 1.7404 (1.6246)	
[2022-01-22 22:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][720/1251]	eta 0:19:33 lr 0.000420	time 2.5375 (2.2096)	loss 3.7787 (3.4679)	grad_norm 1.5385 (1.6258)	
[2022-01-22 22:57:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][730/1251]	eta 0:19:12 lr 0.000419	time 2.6400 (2.2113)	loss 2.6358 (3.4674)	grad_norm 1.7061 (1.6263)	
[2022-01-22 22:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][740/1251]	eta 0:18:51 lr 0.000419	time 2.3973 (2.2134)	loss 3.0684 (3.4690)	grad_norm 1.4516 (1.6267)	
[2022-01-22 22:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][750/1251]	eta 0:18:30 lr 0.000419	time 2.6680 (2.2169)	loss 3.7698 (3.4684)	grad_norm 1.5216 (1.6265)	
[2022-01-22 22:58:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][760/1251]	eta 0:18:07 lr 0.000419	time 1.9440 (2.2152)	loss 3.7719 (3.4700)	grad_norm 1.4776 (1.6257)	
[2022-01-22 22:58:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][770/1251]	eta 0:17:44 lr 0.000419	time 1.9129 (2.2121)	loss 3.4914 (3.4664)	grad_norm 1.7067 (1.6248)	
[2022-01-22 22:58:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][780/1251]	eta 0:17:20 lr 0.000419	time 1.8084 (2.2089)	loss 3.7338 (3.4669)	grad_norm 1.9064 (1.6255)	
[2022-01-22 22:59:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][790/1251]	eta 0:16:58 lr 0.000419	time 2.3889 (2.2092)	loss 3.2743 (3.4648)	grad_norm 1.5880 (1.6257)	
[2022-01-22 22:59:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][800/1251]	eta 0:16:36 lr 0.000419	time 2.5159 (2.2086)	loss 2.5348 (3.4635)	grad_norm 1.4999 (1.6255)	
[2022-01-22 23:00:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][810/1251]	eta 0:16:13 lr 0.000419	time 2.0598 (2.2064)	loss 3.6435 (3.4609)	grad_norm 1.3445 (1.6246)	
[2022-01-22 23:00:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][820/1251]	eta 0:15:50 lr 0.000419	time 1.6728 (2.2053)	loss 2.8063 (3.4579)	grad_norm 1.7829 (1.6249)	
[2022-01-22 23:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][830/1251]	eta 0:15:27 lr 0.000419	time 2.1702 (2.2035)	loss 3.8574 (3.4608)	grad_norm 1.7651 (1.6245)	
[2022-01-22 23:01:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][840/1251]	eta 0:15:05 lr 0.000419	time 1.8355 (2.2033)	loss 3.3940 (3.4608)	grad_norm 1.4589 (1.6238)	
[2022-01-22 23:01:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][850/1251]	eta 0:14:43 lr 0.000419	time 2.8669 (2.2039)	loss 4.2561 (3.4608)	grad_norm 1.5908 (1.6237)	
[2022-01-22 23:01:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][860/1251]	eta 0:14:22 lr 0.000419	time 2.4625 (2.2056)	loss 3.7811 (3.4628)	grad_norm 1.5419 (1.6242)	
[2022-01-22 23:02:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][870/1251]	eta 0:14:00 lr 0.000419	time 1.9222 (2.2059)	loss 3.6787 (3.4624)	grad_norm 1.5275 (1.6232)	
[2022-01-22 23:02:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][880/1251]	eta 0:13:38 lr 0.000419	time 1.7971 (2.2058)	loss 3.7743 (3.4624)	grad_norm 1.6750 (1.6243)	
[2022-01-22 23:02:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][890/1251]	eta 0:13:16 lr 0.000419	time 2.2449 (2.2052)	loss 3.1517 (3.4612)	grad_norm 1.4797 (1.6231)	
[2022-01-22 23:03:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][900/1251]	eta 0:12:53 lr 0.000419	time 1.5895 (2.2043)	loss 3.7246 (3.4607)	grad_norm 1.6921 (1.6216)	
[2022-01-22 23:03:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][910/1251]	eta 0:12:31 lr 0.000419	time 1.8507 (2.2038)	loss 3.6242 (3.4617)	grad_norm 1.7351 (1.6220)	
[2022-01-22 23:04:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][920/1251]	eta 0:12:09 lr 0.000419	time 2.7893 (2.2047)	loss 2.4859 (3.4600)	grad_norm 1.4317 (1.6229)	
[2022-01-22 23:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][930/1251]	eta 0:11:47 lr 0.000419	time 2.1943 (2.2056)	loss 3.6890 (3.4628)	grad_norm 1.6525 (1.6222)	
[2022-01-22 23:04:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][940/1251]	eta 0:11:26 lr 0.000419	time 2.2142 (2.2071)	loss 3.8295 (3.4637)	grad_norm 1.6906 (1.6225)	
[2022-01-22 23:05:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][950/1251]	eta 0:11:03 lr 0.000419	time 1.9415 (2.2059)	loss 3.8658 (3.4671)	grad_norm 1.7657 (1.6231)	
[2022-01-22 23:05:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][960/1251]	eta 0:10:41 lr 0.000419	time 3.1740 (2.2052)	loss 3.1583 (3.4672)	grad_norm 1.4138 (1.6234)	
[2022-01-22 23:05:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][970/1251]	eta 0:10:19 lr 0.000418	time 1.9708 (2.2039)	loss 3.9521 (3.4665)	grad_norm 1.5642 (1.6228)	
[2022-01-22 23:06:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][980/1251]	eta 0:09:56 lr 0.000418	time 1.9327 (2.2029)	loss 2.2745 (3.4655)	grad_norm 1.7998 (1.6227)	
[2022-01-22 23:06:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][990/1251]	eta 0:09:34 lr 0.000418	time 1.5636 (2.2021)	loss 2.9267 (3.4639)	grad_norm 1.6605 (1.6228)	
[2022-01-22 23:06:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1000/1251]	eta 0:09:12 lr 0.000418	time 3.4913 (2.2032)	loss 3.8463 (3.4675)	grad_norm 1.6017 (1.6221)	
[2022-01-22 23:07:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1010/1251]	eta 0:08:51 lr 0.000418	time 1.2835 (2.2048)	loss 3.1150 (3.4664)	grad_norm 1.5484 (1.6214)	
[2022-01-22 23:07:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1020/1251]	eta 0:08:29 lr 0.000418	time 1.5901 (2.2052)	loss 3.5167 (3.4642)	grad_norm 1.4868 (1.6222)	
[2022-01-22 23:08:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1030/1251]	eta 0:08:07 lr 0.000418	time 1.7144 (2.2052)	loss 3.5508 (3.4646)	grad_norm 1.5739 (1.6220)	
[2022-01-22 23:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1040/1251]	eta 0:07:45 lr 0.000418	time 2.5000 (2.2056)	loss 3.1363 (3.4641)	grad_norm 1.7101 (1.6215)	
[2022-01-22 23:08:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1050/1251]	eta 0:07:23 lr 0.000418	time 1.6134 (2.2055)	loss 3.7266 (3.4622)	grad_norm 1.5809 (1.6216)	
[2022-01-22 23:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1060/1251]	eta 0:07:00 lr 0.000418	time 1.5830 (2.2029)	loss 3.3450 (3.4649)	grad_norm 2.3049 (1.6225)	
[2022-01-22 23:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1070/1251]	eta 0:06:38 lr 0.000418	time 2.5255 (2.2024)	loss 4.2808 (3.4661)	grad_norm 1.6710 (1.6224)	
[2022-01-22 23:09:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1080/1251]	eta 0:06:16 lr 0.000418	time 1.7814 (2.2019)	loss 3.8703 (3.4668)	grad_norm 1.6645 (1.6231)	
[2022-01-22 23:10:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1090/1251]	eta 0:05:54 lr 0.000418	time 2.1841 (2.2029)	loss 4.0245 (3.4657)	grad_norm 1.4830 (1.6241)	
[2022-01-22 23:10:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1100/1251]	eta 0:05:32 lr 0.000418	time 1.5617 (2.2015)	loss 3.7612 (3.4666)	grad_norm 1.4605 (1.6235)	
[2022-01-22 23:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1110/1251]	eta 0:05:10 lr 0.000418	time 2.5604 (2.2023)	loss 2.9799 (3.4677)	grad_norm 1.4280 (1.6236)	
[2022-01-22 23:11:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1120/1251]	eta 0:04:48 lr 0.000418	time 2.1851 (2.2007)	loss 3.4643 (3.4668)	grad_norm 1.5136 (1.6245)	
[2022-01-22 23:11:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1130/1251]	eta 0:04:26 lr 0.000418	time 1.8802 (2.2011)	loss 3.6917 (3.4678)	grad_norm 1.4104 (1.6254)	
[2022-01-22 23:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1140/1251]	eta 0:04:04 lr 0.000418	time 1.7260 (2.2023)	loss 2.7446 (3.4688)	grad_norm 1.7074 (1.6257)	
[2022-01-22 23:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1150/1251]	eta 0:03:42 lr 0.000418	time 3.0975 (2.2036)	loss 3.3269 (3.4685)	grad_norm 1.8318 (1.6259)	
[2022-01-22 23:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1160/1251]	eta 0:03:20 lr 0.000418	time 1.5726 (2.2035)	loss 3.6919 (3.4692)	grad_norm 1.4106 (1.6262)	
[2022-01-22 23:13:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1170/1251]	eta 0:02:58 lr 0.000418	time 1.5483 (2.2029)	loss 3.7305 (3.4708)	grad_norm 1.8007 (1.6260)	
[2022-01-22 23:13:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1180/1251]	eta 0:02:36 lr 0.000418	time 1.7061 (2.2021)	loss 4.2882 (3.4738)	grad_norm 1.6293 (1.6261)	
[2022-01-22 23:13:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1190/1251]	eta 0:02:14 lr 0.000418	time 2.8655 (2.2017)	loss 4.1602 (3.4740)	grad_norm 1.5241 (1.6263)	
[2022-01-22 23:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1200/1251]	eta 0:01:52 lr 0.000418	time 1.8155 (2.2011)	loss 3.7275 (3.4746)	grad_norm 1.5489 (1.6263)	
[2022-01-22 23:14:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1210/1251]	eta 0:01:30 lr 0.000418	time 1.5096 (2.2007)	loss 3.9117 (3.4754)	grad_norm 1.8008 (1.6267)	
[2022-01-22 23:15:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1220/1251]	eta 0:01:08 lr 0.000417	time 2.9717 (2.2026)	loss 2.7125 (3.4756)	grad_norm 1.3508 (1.6266)	
[2022-01-22 23:15:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1230/1251]	eta 0:00:46 lr 0.000417	time 2.4849 (2.2033)	loss 3.6705 (3.4789)	grad_norm 1.9338 (1.6274)	
[2022-01-22 23:15:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1240/1251]	eta 0:00:24 lr 0.000417	time 1.4075 (2.2018)	loss 3.2955 (3.4787)	grad_norm 1.4604 (1.6275)	
[2022-01-22 23:16:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [166/300][1250/1251]	eta 0:00:02 lr 0.000417	time 1.1895 (2.1957)	loss 3.9323 (3.4770)	grad_norm 1.4766 (1.6276)	
[2022-01-22 23:16:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 166 training takes 0:45:47
[2022-01-22 23:16:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.968 (17.968)	Loss 0.9161 (0.9161)	Acc@1 78.516 (78.516)	Acc@5 93.555 (93.555)	
[2022-01-22 23:16:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.566 (3.462)	Loss 0.9657 (0.9866)	Acc@1 77.148 (76.607)	Acc@5 95.117 (93.697)	
[2022-01-22 23:16:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.888 (2.643)	Loss 0.9313 (0.9748)	Acc@1 77.539 (77.018)	Acc@5 94.238 (93.806)	
[2022-01-22 23:17:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.648 (2.367)	Loss 0.9851 (0.9819)	Acc@1 76.172 (76.868)	Acc@5 94.434 (93.655)	
[2022-01-22 23:17:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.844 (2.196)	Loss 0.9148 (0.9793)	Acc@1 79.199 (76.839)	Acc@5 93.750 (93.698)	
[2022-01-22 23:17:39 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.722 Acc@5 93.706
[2022-01-22 23:17:39 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.7%
[2022-01-22 23:17:39 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.82%
[2022-01-22 23:18:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][0/1251]	eta 7:38:15 lr 0.000417	time 21.9787 (21.9787)	loss 3.7360 (3.7360)	grad_norm 2.1806 (2.1806)	
[2022-01-22 23:18:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][10/1251]	eta 1:22:02 lr 0.000417	time 2.0352 (3.9667)	loss 2.8183 (3.4397)	grad_norm 1.4875 (1.6955)	
[2022-01-22 23:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][20/1251]	eta 1:03:35 lr 0.000417	time 1.8927 (3.0997)	loss 3.5132 (3.3759)	grad_norm 1.3387 (1.6372)	
[2022-01-22 23:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][30/1251]	eta 0:57:16 lr 0.000417	time 1.8037 (2.8144)	loss 2.7864 (3.3815)	grad_norm 1.8678 (1.6451)	
[2022-01-22 23:19:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][40/1251]	eta 0:54:20 lr 0.000417	time 3.6187 (2.6921)	loss 3.7936 (3.4191)	grad_norm 1.6263 (1.6581)	
[2022-01-22 23:19:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][50/1251]	eta 0:52:36 lr 0.000417	time 1.7630 (2.6282)	loss 3.7363 (3.4719)	grad_norm 1.6398 (1.6522)	
[2022-01-22 23:20:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][60/1251]	eta 0:51:18 lr 0.000417	time 2.4023 (2.5852)	loss 3.3322 (3.4816)	grad_norm 1.8692 (1.6582)	
[2022-01-22 23:20:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][70/1251]	eta 0:49:20 lr 0.000417	time 1.8738 (2.5067)	loss 3.9245 (3.4688)	grad_norm 1.3630 (1.6654)	
[2022-01-22 23:20:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][80/1251]	eta 0:47:55 lr 0.000417	time 2.6923 (2.4555)	loss 3.0676 (3.4589)	grad_norm 1.5162 (1.6595)	
[2022-01-22 23:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][90/1251]	eta 0:46:42 lr 0.000417	time 1.8131 (2.4141)	loss 3.6730 (3.4631)	grad_norm 1.5586 (1.6487)	
[2022-01-22 23:21:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][100/1251]	eta 0:45:54 lr 0.000417	time 2.1870 (2.3935)	loss 3.7332 (3.4842)	grad_norm 1.5711 (1.6451)	
[2022-01-22 23:22:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][110/1251]	eta 0:45:19 lr 0.000417	time 1.5908 (2.3830)	loss 3.8927 (3.4758)	grad_norm 1.6530 (1.6385)	
[2022-01-22 23:22:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][120/1251]	eta 0:44:47 lr 0.000417	time 2.8533 (2.3761)	loss 3.1527 (3.4935)	grad_norm 1.5628 (1.6369)	
[2022-01-22 23:22:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][130/1251]	eta 0:44:02 lr 0.000417	time 2.1447 (2.3572)	loss 3.7504 (3.4915)	grad_norm 1.6032 (1.6289)	
[2022-01-22 23:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][140/1251]	eta 0:43:21 lr 0.000417	time 2.0761 (2.3420)	loss 3.2108 (3.4976)	grad_norm 1.4222 (1.6241)	
[2022-01-22 23:23:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][150/1251]	eta 0:42:39 lr 0.000417	time 2.2625 (2.3251)	loss 2.4734 (3.4965)	grad_norm 1.5422 (1.6232)	
[2022-01-22 23:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][160/1251]	eta 0:41:58 lr 0.000417	time 1.8913 (2.3089)	loss 3.4098 (3.5093)	grad_norm 1.4834 (1.6172)	
[2022-01-22 23:24:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][170/1251]	eta 0:41:26 lr 0.000417	time 2.0346 (2.3003)	loss 3.8453 (3.5219)	grad_norm 1.7497 (1.6210)	
[2022-01-22 23:24:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][180/1251]	eta 0:41:07 lr 0.000417	time 2.5527 (2.3038)	loss 3.0843 (3.5180)	grad_norm 1.6832 (1.6191)	
[2022-01-22 23:24:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][190/1251]	eta 0:40:29 lr 0.000417	time 1.8266 (2.2896)	loss 2.4330 (3.5284)	grad_norm 1.4751 (1.6203)	
[2022-01-22 23:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][200/1251]	eta 0:40:02 lr 0.000417	time 2.8582 (2.2856)	loss 3.9131 (3.5344)	grad_norm 1.5139 (1.6188)	
[2022-01-22 23:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][210/1251]	eta 0:39:38 lr 0.000416	time 1.8802 (2.2850)	loss 2.7861 (3.5361)	grad_norm 1.6564 (1.6216)	
[2022-01-22 23:26:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][220/1251]	eta 0:39:20 lr 0.000416	time 2.5951 (2.2900)	loss 3.7229 (3.5408)	grad_norm 1.8762 (1.6269)	
[2022-01-22 23:26:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][230/1251]	eta 0:38:53 lr 0.000416	time 1.6658 (2.2852)	loss 3.8517 (3.5456)	grad_norm 1.6937 (1.6285)	
[2022-01-22 23:26:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][240/1251]	eta 0:38:30 lr 0.000416	time 2.7883 (2.2850)	loss 3.8017 (3.5491)	grad_norm 1.5222 (1.6278)	
[2022-01-22 23:27:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][250/1251]	eta 0:37:51 lr 0.000416	time 1.6345 (2.2696)	loss 2.7193 (3.5355)	grad_norm 1.6681 (1.6259)	
[2022-01-22 23:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][260/1251]	eta 0:37:25 lr 0.000416	time 1.8922 (2.2655)	loss 3.7876 (3.5340)	grad_norm 1.3809 (1.6249)	
[2022-01-22 23:27:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][270/1251]	eta 0:36:59 lr 0.000416	time 2.0328 (2.2626)	loss 2.6793 (3.5419)	grad_norm 1.4763 (1.6243)	
[2022-01-22 23:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][280/1251]	eta 0:36:36 lr 0.000416	time 1.8429 (2.2618)	loss 3.6733 (3.5404)	grad_norm 1.6019 (1.6260)	
[2022-01-22 23:28:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][290/1251]	eta 0:36:10 lr 0.000416	time 1.9228 (2.2581)	loss 4.1444 (3.5378)	grad_norm 1.6619 (1.6266)	
[2022-01-22 23:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][300/1251]	eta 0:35:45 lr 0.000416	time 1.9322 (2.2556)	loss 4.0444 (3.5360)	grad_norm 1.7531 (1.6282)	
[2022-01-22 23:29:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][310/1251]	eta 0:35:20 lr 0.000416	time 1.8519 (2.2535)	loss 2.3782 (3.5251)	grad_norm 1.6687 (1.6285)	
[2022-01-22 23:29:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][320/1251]	eta 0:34:55 lr 0.000416	time 1.9313 (2.2505)	loss 3.2835 (3.5101)	grad_norm 1.6725 (1.6286)	
[2022-01-22 23:30:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][330/1251]	eta 0:34:32 lr 0.000416	time 1.9197 (2.2508)	loss 3.6152 (3.5061)	grad_norm 1.5927 (1.6289)	
[2022-01-22 23:30:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][340/1251]	eta 0:34:09 lr 0.000416	time 2.1160 (2.2493)	loss 3.3060 (3.5075)	grad_norm 1.4213 (1.6295)	
[2022-01-22 23:30:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][350/1251]	eta 0:33:43 lr 0.000416	time 2.4182 (2.2464)	loss 3.3361 (3.5098)	grad_norm 1.4311 (1.6272)	
[2022-01-22 23:31:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][360/1251]	eta 0:33:18 lr 0.000416	time 2.3128 (2.2433)	loss 2.7453 (3.5111)	grad_norm 1.6649 (1.6279)	
[2022-01-22 23:31:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][370/1251]	eta 0:32:54 lr 0.000416	time 2.1454 (2.2408)	loss 2.4692 (3.5070)	grad_norm 1.5899 (1.6282)	
[2022-01-22 23:31:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][380/1251]	eta 0:32:29 lr 0.000416	time 2.2497 (2.2380)	loss 3.4296 (3.5052)	grad_norm 1.6071 (1.6285)	
[2022-01-22 23:32:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][390/1251]	eta 0:32:10 lr 0.000416	time 2.2160 (2.2425)	loss 2.6326 (3.4999)	grad_norm 1.6930 (1.6301)	
[2022-01-22 23:32:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][400/1251]	eta 0:31:46 lr 0.000416	time 1.9130 (2.2404)	loss 4.0097 (3.5006)	grad_norm 1.9705 (1.6321)	
[2022-01-22 23:32:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][410/1251]	eta 0:31:21 lr 0.000416	time 1.9366 (2.2375)	loss 3.7857 (3.5025)	grad_norm 1.7755 (1.6330)	
[2022-01-22 23:33:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][420/1251]	eta 0:30:55 lr 0.000416	time 2.0492 (2.2327)	loss 3.5137 (3.4999)	grad_norm 1.5645 (1.6336)	
[2022-01-22 23:33:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][430/1251]	eta 0:30:27 lr 0.000416	time 2.1566 (2.2265)	loss 2.4572 (3.4907)	grad_norm 1.4303 (1.6327)	
[2022-01-22 23:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][440/1251]	eta 0:30:02 lr 0.000416	time 2.0328 (2.2230)	loss 3.5494 (3.4934)	grad_norm 1.4705 (1.6328)	
[2022-01-22 23:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][450/1251]	eta 0:29:40 lr 0.000416	time 2.1684 (2.2230)	loss 3.6816 (3.4988)	grad_norm 1.6291 (1.6346)	
[2022-01-22 23:34:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][460/1251]	eta 0:29:15 lr 0.000415	time 2.1656 (2.2191)	loss 3.4543 (3.5018)	grad_norm 1.7288 (1.6360)	
[2022-01-22 23:35:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][470/1251]	eta 0:28:55 lr 0.000415	time 2.8083 (2.2226)	loss 3.7195 (3.4970)	grad_norm 1.5181 (1.6360)	
[2022-01-22 23:35:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][480/1251]	eta 0:28:38 lr 0.000415	time 2.9193 (2.2289)	loss 3.5824 (3.5008)	grad_norm 1.4866 (1.6354)	
[2022-01-22 23:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][490/1251]	eta 0:28:22 lr 0.000415	time 2.5321 (2.2378)	loss 3.9001 (3.5001)	grad_norm 1.7741 (1.6346)	
[2022-01-22 23:36:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][500/1251]	eta 0:28:00 lr 0.000415	time 1.8149 (2.2374)	loss 4.1651 (3.4998)	grad_norm 1.5766 (1.6341)	
[2022-01-22 23:36:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][510/1251]	eta 0:27:36 lr 0.000415	time 2.1866 (2.2354)	loss 3.0172 (3.5007)	grad_norm 1.4590 (1.6331)	
[2022-01-22 23:37:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][520/1251]	eta 0:27:10 lr 0.000415	time 1.9717 (2.2303)	loss 3.5940 (3.5045)	grad_norm 1.6916 (1.6346)	
[2022-01-22 23:37:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][530/1251]	eta 0:26:42 lr 0.000415	time 1.7560 (2.2230)	loss 3.1995 (3.5020)	grad_norm 1.9404 (1.6355)	
[2022-01-22 23:37:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][540/1251]	eta 0:26:16 lr 0.000415	time 2.2015 (2.2172)	loss 3.7279 (3.4998)	grad_norm 1.4562 (1.6359)	
[2022-01-22 23:38:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][550/1251]	eta 0:25:53 lr 0.000415	time 2.4197 (2.2159)	loss 3.9334 (3.4996)	grad_norm 1.7980 (1.6370)	
[2022-01-22 23:38:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][560/1251]	eta 0:25:29 lr 0.000415	time 1.9409 (2.2140)	loss 3.0635 (3.4988)	grad_norm 1.5824 (1.6378)	
[2022-01-22 23:38:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][570/1251]	eta 0:25:11 lr 0.000415	time 2.8643 (2.2190)	loss 3.7072 (3.4964)	grad_norm 1.7795 (1.6386)	
[2022-01-22 23:39:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][580/1251]	eta 0:24:55 lr 0.000415	time 2.8032 (2.2283)	loss 2.4893 (3.4984)	grad_norm 1.5858 (1.6371)	
[2022-01-22 23:39:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][590/1251]	eta 0:24:34 lr 0.000415	time 2.1561 (2.2314)	loss 4.2270 (3.4983)	grad_norm 1.8264 (1.6377)	
[2022-01-22 23:39:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][600/1251]	eta 0:24:11 lr 0.000415	time 1.5683 (2.2297)	loss 4.0526 (3.4976)	grad_norm 1.5258 (1.6389)	
[2022-01-22 23:40:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][610/1251]	eta 0:23:46 lr 0.000415	time 2.1842 (2.2262)	loss 3.9978 (3.5001)	grad_norm 1.5923 (1.6404)	
[2022-01-22 23:40:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][620/1251]	eta 0:23:21 lr 0.000415	time 2.2843 (2.2210)	loss 3.6299 (3.4991)	grad_norm 1.6645 (1.6392)	
[2022-01-22 23:40:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][630/1251]	eta 0:22:57 lr 0.000415	time 2.5656 (2.2177)	loss 3.3931 (3.5007)	grad_norm 2.0169 (1.6388)	
[2022-01-22 23:41:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][640/1251]	eta 0:22:34 lr 0.000415	time 1.8831 (2.2171)	loss 4.0098 (3.4995)	grad_norm 1.5871 (1.6388)	
[2022-01-22 23:41:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][650/1251]	eta 0:22:12 lr 0.000415	time 2.9785 (2.2168)	loss 3.8016 (3.5029)	grad_norm 1.5726 (1.6385)	
[2022-01-22 23:42:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][660/1251]	eta 0:21:50 lr 0.000415	time 2.4722 (2.2178)	loss 3.5947 (3.4998)	grad_norm 1.6843 (1.6373)	
[2022-01-22 23:42:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][670/1251]	eta 0:21:28 lr 0.000415	time 2.7797 (2.2183)	loss 2.9569 (3.5012)	grad_norm 1.6111 (1.6368)	
[2022-01-22 23:42:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][680/1251]	eta 0:21:08 lr 0.000415	time 1.9916 (2.2217)	loss 3.0522 (3.5009)	grad_norm 1.4551 (1.6361)	
[2022-01-22 23:43:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][690/1251]	eta 0:20:49 lr 0.000415	time 3.4815 (2.2270)	loss 3.7871 (3.5051)	grad_norm 1.5518 (1.6349)	
[2022-01-22 23:43:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][700/1251]	eta 0:20:26 lr 0.000414	time 1.8869 (2.2251)	loss 4.5414 (3.5041)	grad_norm 1.7653 (1.6354)	
[2022-01-22 23:43:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][710/1251]	eta 0:20:01 lr 0.000414	time 1.6333 (2.2203)	loss 3.6974 (3.4983)	grad_norm 1.6396 (1.6349)	
[2022-01-22 23:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][720/1251]	eta 0:19:37 lr 0.000414	time 2.2621 (2.2176)	loss 4.0349 (3.4974)	grad_norm 2.1412 (1.6350)	
[2022-01-22 23:44:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][730/1251]	eta 0:19:14 lr 0.000414	time 2.2997 (2.2156)	loss 3.4776 (3.4937)	grad_norm 1.8898 (1.6347)	
[2022-01-22 23:45:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][740/1251]	eta 0:18:51 lr 0.000414	time 2.0457 (2.2146)	loss 3.7589 (3.4922)	grad_norm 1.6254 (1.6341)	
[2022-01-22 23:45:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][750/1251]	eta 0:18:29 lr 0.000414	time 2.0967 (2.2155)	loss 3.3611 (3.4937)	grad_norm 1.6103 (1.6333)	
[2022-01-22 23:45:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][760/1251]	eta 0:18:07 lr 0.000414	time 2.2179 (2.2150)	loss 3.4231 (3.4952)	grad_norm 1.6008 (1.6335)	
[2022-01-22 23:46:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][770/1251]	eta 0:17:45 lr 0.000414	time 1.8325 (2.2146)	loss 3.9027 (3.4982)	grad_norm 1.6918 (1.6340)	
[2022-01-22 23:46:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][780/1251]	eta 0:17:23 lr 0.000414	time 2.4355 (2.2148)	loss 4.1516 (3.5000)	grad_norm 1.7539 (1.6350)	
[2022-01-22 23:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][790/1251]	eta 0:17:01 lr 0.000414	time 1.6667 (2.2148)	loss 2.9682 (3.4996)	grad_norm 1.4784 (1.6355)	
[2022-01-22 23:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][800/1251]	eta 0:16:40 lr 0.000414	time 2.8585 (2.2176)	loss 3.3491 (3.5009)	grad_norm 1.4708 (1.6352)	
[2022-01-22 23:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][810/1251]	eta 0:16:18 lr 0.000414	time 2.1673 (2.2190)	loss 3.2747 (3.5004)	grad_norm 1.7297 (1.6344)	
[2022-01-22 23:48:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][820/1251]	eta 0:15:56 lr 0.000414	time 2.5171 (2.2184)	loss 3.4173 (3.5015)	grad_norm 1.5453 (1.6355)	
[2022-01-22 23:48:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][830/1251]	eta 0:15:32 lr 0.000414	time 2.2393 (2.2149)	loss 3.3179 (3.4981)	grad_norm 1.7362 (1.6354)	
[2022-01-22 23:48:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][840/1251]	eta 0:15:09 lr 0.000414	time 2.5157 (2.2123)	loss 3.5327 (3.4983)	grad_norm 1.3289 (1.6346)	
[2022-01-22 23:49:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][850/1251]	eta 0:14:46 lr 0.000414	time 1.9804 (2.2103)	loss 3.4911 (3.4993)	grad_norm 1.4768 (1.6341)	
[2022-01-22 23:49:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][860/1251]	eta 0:14:23 lr 0.000414	time 1.8631 (2.2096)	loss 3.5145 (3.4998)	grad_norm 1.6664 (1.6345)	
[2022-01-22 23:49:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][870/1251]	eta 0:14:02 lr 0.000414	time 1.8729 (2.2100)	loss 4.1421 (3.5000)	grad_norm 1.6025 (1.6358)	
[2022-01-22 23:50:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][880/1251]	eta 0:13:40 lr 0.000414	time 2.5964 (2.2112)	loss 3.5108 (3.4990)	grad_norm 1.8474 (1.6374)	
[2022-01-22 23:50:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][890/1251]	eta 0:13:19 lr 0.000414	time 2.9878 (2.2144)	loss 2.3672 (3.4966)	grad_norm 1.7382 (1.6379)	
[2022-01-22 23:50:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][900/1251]	eta 0:12:57 lr 0.000414	time 2.1611 (2.2164)	loss 2.4716 (3.4946)	grad_norm 1.5749 (1.6385)	
[2022-01-22 23:51:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][910/1251]	eta 0:12:35 lr 0.000414	time 1.8923 (2.2154)	loss 2.2618 (3.4971)	grad_norm 1.5639 (1.6400)	
[2022-01-22 23:51:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][920/1251]	eta 0:12:12 lr 0.000414	time 1.9814 (2.2127)	loss 3.8354 (3.4971)	grad_norm 1.4811 (1.6398)	
[2022-01-22 23:51:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][930/1251]	eta 0:11:49 lr 0.000414	time 1.8200 (2.2102)	loss 3.4984 (3.4953)	grad_norm 1.3975 (1.6401)	
[2022-01-22 23:52:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][940/1251]	eta 0:11:27 lr 0.000414	time 2.4110 (2.2093)	loss 3.3163 (3.4951)	grad_norm 1.5933 (1.6399)	
[2022-01-22 23:52:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][950/1251]	eta 0:11:04 lr 0.000413	time 2.1991 (2.2083)	loss 2.3560 (3.4929)	grad_norm 1.3862 (1.6405)	
[2022-01-22 23:53:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][960/1251]	eta 0:10:43 lr 0.000413	time 3.3427 (2.2103)	loss 3.8691 (3.4919)	grad_norm 1.8226 (1.6405)	
[2022-01-22 23:53:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][970/1251]	eta 0:10:21 lr 0.000413	time 1.6225 (2.2109)	loss 4.0391 (3.4946)	grad_norm 1.8933 (1.6408)	
[2022-01-22 23:53:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][980/1251]	eta 0:09:59 lr 0.000413	time 2.8637 (2.2134)	loss 2.6060 (3.4935)	grad_norm 1.6340 (1.6402)	
[2022-01-22 23:54:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][990/1251]	eta 0:09:38 lr 0.000413	time 1.7499 (2.2150)	loss 3.6168 (3.4937)	grad_norm 1.5938 (1.6403)	
[2022-01-22 23:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1000/1251]	eta 0:09:15 lr 0.000413	time 2.4767 (2.2145)	loss 2.2528 (3.4921)	grad_norm 1.4580 (1.6395)	
[2022-01-22 23:54:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1010/1251]	eta 0:08:53 lr 0.000413	time 1.6327 (2.2123)	loss 3.3215 (3.4914)	grad_norm 1.3819 (1.6391)	
[2022-01-22 23:55:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1020/1251]	eta 0:08:30 lr 0.000413	time 2.0076 (2.2095)	loss 3.3942 (3.4887)	grad_norm 1.7394 (1.6388)	
[2022-01-22 23:55:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1030/1251]	eta 0:08:07 lr 0.000413	time 2.2230 (2.2078)	loss 2.4754 (3.4885)	grad_norm 1.7876 (1.6383)	
[2022-01-22 23:55:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1040/1251]	eta 0:07:45 lr 0.000413	time 2.8709 (2.2070)	loss 4.1436 (3.4897)	grad_norm 1.7310 (1.6380)	
[2022-01-22 23:56:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1050/1251]	eta 0:07:23 lr 0.000413	time 1.9007 (2.2066)	loss 3.0706 (3.4892)	grad_norm 1.8163 (1.6386)	
[2022-01-22 23:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1060/1251]	eta 0:07:01 lr 0.000413	time 2.1906 (2.2072)	loss 2.5253 (3.4876)	grad_norm 2.0112 (1.6391)	
[2022-01-22 23:57:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1070/1251]	eta 0:06:39 lr 0.000413	time 2.4746 (2.2083)	loss 2.5344 (3.4882)	grad_norm 1.6219 (1.6387)	
[2022-01-22 23:57:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1080/1251]	eta 0:06:17 lr 0.000413	time 2.5100 (2.2084)	loss 4.0787 (3.4901)	grad_norm 2.0043 (1.6392)	
[2022-01-22 23:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1090/1251]	eta 0:05:55 lr 0.000413	time 1.7866 (2.2080)	loss 3.4720 (3.4885)	grad_norm 1.6467 (1.6387)	
[2022-01-22 23:58:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1100/1251]	eta 0:05:33 lr 0.000413	time 1.9778 (2.2076)	loss 3.5874 (3.4891)	grad_norm 1.3802 (1.6382)	
[2022-01-22 23:58:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1110/1251]	eta 0:05:11 lr 0.000413	time 1.9199 (2.2067)	loss 2.7258 (3.4892)	grad_norm 1.5770 (1.6377)	
[2022-01-22 23:58:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1120/1251]	eta 0:04:49 lr 0.000413	time 3.1338 (2.2082)	loss 3.9518 (3.4884)	grad_norm 1.4515 (1.6370)	
[2022-01-22 23:59:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1130/1251]	eta 0:04:27 lr 0.000413	time 2.1300 (2.2089)	loss 4.2423 (3.4883)	grad_norm 1.5878 (1.6368)	
[2022-01-22 23:59:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1140/1251]	eta 0:04:05 lr 0.000413	time 1.6262 (2.2090)	loss 3.7280 (3.4908)	grad_norm 1.5149 (1.6369)	
[2022-01-23 00:00:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1150/1251]	eta 0:03:43 lr 0.000413	time 1.6988 (2.2080)	loss 2.7252 (3.4900)	grad_norm 1.6332 (1.6372)	
[2022-01-23 00:00:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1160/1251]	eta 0:03:20 lr 0.000413	time 2.2595 (2.2068)	loss 2.3146 (3.4886)	grad_norm 1.5270 (1.6368)	
[2022-01-23 00:00:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1170/1251]	eta 0:02:58 lr 0.000413	time 1.8218 (2.2053)	loss 3.3412 (3.4865)	grad_norm 1.6083 (1.6367)	
[2022-01-23 00:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1180/1251]	eta 0:02:36 lr 0.000413	time 1.8395 (2.2049)	loss 3.8541 (3.4869)	grad_norm 1.4668 (1.6362)	
[2022-01-23 00:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1190/1251]	eta 0:02:14 lr 0.000412	time 3.1797 (2.2055)	loss 4.0389 (3.4851)	grad_norm 1.7569 (1.6362)	
[2022-01-23 00:01:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1200/1251]	eta 0:01:52 lr 0.000412	time 1.4921 (2.2062)	loss 4.3045 (3.4856)	grad_norm 1.8135 (1.6367)	
[2022-01-23 00:02:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1210/1251]	eta 0:01:30 lr 0.000412	time 1.5526 (2.2064)	loss 2.9501 (3.4826)	grad_norm 1.5640 (1.6369)	
[2022-01-23 00:02:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1220/1251]	eta 0:01:08 lr 0.000412	time 2.2057 (2.2072)	loss 3.6388 (3.4829)	grad_norm 1.5417 (1.6361)	
[2022-01-23 00:02:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1230/1251]	eta 0:00:46 lr 0.000412	time 3.1180 (2.2076)	loss 4.3766 (3.4830)	grad_norm 1.8909 (1.6360)	
[2022-01-23 00:03:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1240/1251]	eta 0:00:24 lr 0.000412	time 1.5080 (2.2047)	loss 3.8379 (3.4842)	grad_norm 1.6302 (1.6364)	
[2022-01-23 00:03:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [167/300][1250/1251]	eta 0:00:02 lr 0.000412	time 1.1916 (2.1988)	loss 2.9706 (3.4811)	grad_norm 1.7987 (1.6372)	
[2022-01-23 00:03:31 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 167 training takes 0:45:51
[2022-01-23 00:03:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 21.030 (21.030)	Loss 1.1271 (1.1271)	Acc@1 75.000 (75.000)	Acc@5 91.211 (91.211)	
[2022-01-23 00:04:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.264 (3.395)	Loss 0.9979 (1.0282)	Acc@1 75.391 (76.385)	Acc@5 94.434 (93.333)	
[2022-01-23 00:04:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.608 (2.745)	Loss 1.0318 (1.0046)	Acc@1 76.172 (76.618)	Acc@5 93.555 (93.620)	
[2022-01-23 00:04:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.294 (2.300)	Loss 0.9273 (0.9915)	Acc@1 78.418 (76.830)	Acc@5 94.434 (93.775)	
[2022-01-23 00:05:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.786 (2.250)	Loss 0.9440 (0.9928)	Acc@1 76.855 (76.836)	Acc@5 94.629 (93.724)	
[2022-01-23 00:05:11 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.770 Acc@5 93.672
[2022-01-23 00:05:11 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.8%
[2022-01-23 00:05:11 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.82%
[2022-01-23 00:05:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][0/1251]	eta 7:26:40 lr 0.000412	time 21.4237 (21.4237)	loss 3.8565 (3.8565)	grad_norm 1.7680 (1.7680)	
[2022-01-23 00:05:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][10/1251]	eta 1:22:12 lr 0.000412	time 2.2137 (3.9745)	loss 3.7844 (3.4879)	grad_norm 1.8817 (1.6538)	
[2022-01-23 00:06:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][20/1251]	eta 1:04:56 lr 0.000412	time 2.1761 (3.1653)	loss 3.5050 (3.4315)	grad_norm 1.7188 (1.6597)	
[2022-01-23 00:06:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][30/1251]	eta 0:58:07 lr 0.000412	time 2.1698 (2.8564)	loss 3.7308 (3.4620)	grad_norm 1.6619 (1.6233)	
[2022-01-23 00:07:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][40/1251]	eta 0:54:33 lr 0.000412	time 2.7864 (2.7034)	loss 3.5755 (3.4822)	grad_norm 1.4763 (1.6381)	
[2022-01-23 00:07:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][50/1251]	eta 0:53:08 lr 0.000412	time 3.3146 (2.6547)	loss 3.9015 (3.5015)	grad_norm 1.7223 (1.6434)	
[2022-01-23 00:07:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][60/1251]	eta 0:51:30 lr 0.000412	time 1.8175 (2.5951)	loss 3.8317 (3.4879)	grad_norm 1.5712 (1.6245)	
[2022-01-23 00:08:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][70/1251]	eta 0:50:20 lr 0.000412	time 2.3315 (2.5572)	loss 4.0382 (3.5025)	grad_norm 1.9739 (1.6448)	
[2022-01-23 00:08:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][80/1251]	eta 0:49:07 lr 0.000412	time 2.4686 (2.5172)	loss 3.3984 (3.4923)	grad_norm 1.4959 (1.6341)	
[2022-01-23 00:08:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][90/1251]	eta 0:47:30 lr 0.000412	time 1.8203 (2.4549)	loss 3.9972 (3.4942)	grad_norm 1.6059 (1.6273)	
[2022-01-23 00:09:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][100/1251]	eta 0:45:59 lr 0.000412	time 1.9159 (2.3974)	loss 3.8907 (3.5195)	grad_norm 1.5274 (1.6298)	
[2022-01-23 00:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][110/1251]	eta 0:44:55 lr 0.000412	time 2.5940 (2.3625)	loss 3.5740 (3.5019)	grad_norm 1.7222 (1.6251)	
[2022-01-23 00:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][120/1251]	eta 0:44:16 lr 0.000412	time 2.1357 (2.3486)	loss 2.7983 (3.4836)	grad_norm 2.2917 (1.6339)	
[2022-01-23 00:10:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][130/1251]	eta 0:43:40 lr 0.000412	time 1.6699 (2.3377)	loss 3.8115 (3.4802)	grad_norm 1.7887 (1.6317)	
[2022-01-23 00:10:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][140/1251]	eta 0:43:13 lr 0.000412	time 1.9707 (2.3340)	loss 2.9562 (3.4872)	grad_norm 1.4762 (1.6276)	
[2022-01-23 00:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][150/1251]	eta 0:42:56 lr 0.000412	time 3.2604 (2.3401)	loss 3.4064 (3.4668)	grad_norm 1.5541 (1.6291)	
[2022-01-23 00:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][160/1251]	eta 0:42:25 lr 0.000412	time 1.9632 (2.3335)	loss 2.8209 (3.4606)	grad_norm 1.7293 (1.6290)	
[2022-01-23 00:11:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][170/1251]	eta 0:41:59 lr 0.000412	time 1.6339 (2.3303)	loss 3.2646 (3.4640)	grad_norm 1.7028 (1.6343)	
[2022-01-23 00:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][180/1251]	eta 0:41:14 lr 0.000412	time 1.6333 (2.3107)	loss 3.6234 (3.4759)	grad_norm 1.7927 (1.6359)	
[2022-01-23 00:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][190/1251]	eta 0:40:39 lr 0.000411	time 1.9625 (2.2997)	loss 3.2349 (3.4451)	grad_norm 1.5904 (1.6342)	
[2022-01-23 00:12:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][200/1251]	eta 0:40:07 lr 0.000411	time 1.7920 (2.2903)	loss 3.1190 (3.4483)	grad_norm 1.5746 (1.6327)	
[2022-01-23 00:13:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][210/1251]	eta 0:39:46 lr 0.000411	time 2.3142 (2.2921)	loss 3.3653 (3.4431)	grad_norm 1.8911 (1.6326)	
[2022-01-23 00:13:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][220/1251]	eta 0:39:23 lr 0.000411	time 1.5514 (2.2922)	loss 2.7594 (3.4411)	grad_norm 1.5834 (1.6331)	
[2022-01-23 00:13:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][230/1251]	eta 0:38:55 lr 0.000411	time 1.7885 (2.2876)	loss 3.4174 (3.4416)	grad_norm 1.9162 (1.6322)	
[2022-01-23 00:14:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][240/1251]	eta 0:38:23 lr 0.000411	time 1.9103 (2.2788)	loss 2.7272 (3.4513)	grad_norm 1.4240 (1.6344)	
[2022-01-23 00:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][250/1251]	eta 0:37:54 lr 0.000411	time 1.9311 (2.2724)	loss 3.4447 (3.4491)	grad_norm 1.7113 (1.6349)	
[2022-01-23 00:15:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][260/1251]	eta 0:37:22 lr 0.000411	time 2.1673 (2.2632)	loss 2.5807 (3.4497)	grad_norm 1.5945 (1.6350)	
[2022-01-23 00:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][270/1251]	eta 0:36:58 lr 0.000411	time 2.4844 (2.2611)	loss 3.8486 (3.4410)	grad_norm 1.7861 (1.6338)	
[2022-01-23 00:15:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][280/1251]	eta 0:36:42 lr 0.000411	time 1.6020 (2.2682)	loss 3.7426 (3.4398)	grad_norm 1.7967 (1.6343)	
[2022-01-23 00:16:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][290/1251]	eta 0:36:19 lr 0.000411	time 1.6917 (2.2683)	loss 3.8245 (3.4428)	grad_norm 1.9276 (1.6377)	
[2022-01-23 00:16:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][300/1251]	eta 0:35:57 lr 0.000411	time 2.0226 (2.2689)	loss 3.1180 (3.4349)	grad_norm 1.3751 (1.6383)	
[2022-01-23 00:16:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][310/1251]	eta 0:35:35 lr 0.000411	time 2.2120 (2.2698)	loss 3.5845 (3.4461)	grad_norm 1.4408 (1.6399)	
[2022-01-23 00:17:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][320/1251]	eta 0:35:10 lr 0.000411	time 1.9776 (2.2665)	loss 3.8637 (3.4426)	grad_norm 2.0068 (1.6386)	
[2022-01-23 00:17:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][330/1251]	eta 0:34:38 lr 0.000411	time 1.8682 (2.2568)	loss 4.0951 (3.4487)	grad_norm 1.6778 (1.6377)	
[2022-01-23 00:17:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][340/1251]	eta 0:34:11 lr 0.000411	time 1.9100 (2.2523)	loss 3.8149 (3.4508)	grad_norm 1.4855 (1.6343)	
[2022-01-23 00:18:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][350/1251]	eta 0:33:46 lr 0.000411	time 1.9334 (2.2494)	loss 3.1129 (3.4527)	grad_norm 1.5164 (1.6336)	
[2022-01-23 00:18:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][360/1251]	eta 0:33:20 lr 0.000411	time 2.0957 (2.2457)	loss 3.1204 (3.4443)	grad_norm 1.5358 (1.6313)	
[2022-01-23 00:19:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][370/1251]	eta 0:32:57 lr 0.000411	time 1.9324 (2.2451)	loss 3.6041 (3.4443)	grad_norm 1.7176 (1.6305)	
[2022-01-23 00:19:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][380/1251]	eta 0:32:36 lr 0.000411	time 2.5451 (2.2466)	loss 3.9798 (3.4465)	grad_norm 1.6455 (1.6308)	
[2022-01-23 00:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][390/1251]	eta 0:32:19 lr 0.000411	time 1.8531 (2.2521)	loss 3.3590 (3.4495)	grad_norm 1.7402 (1.6330)	
[2022-01-23 00:20:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][400/1251]	eta 0:31:54 lr 0.000411	time 2.3405 (2.2502)	loss 3.5102 (3.4535)	grad_norm 1.5534 (1.6357)	
[2022-01-23 00:20:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][410/1251]	eta 0:31:29 lr 0.000411	time 1.6095 (2.2472)	loss 4.1181 (3.4594)	grad_norm 1.5569 (1.6369)	
[2022-01-23 00:20:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][420/1251]	eta 0:31:03 lr 0.000411	time 1.6076 (2.2424)	loss 3.3748 (3.4548)	grad_norm 1.5271 (1.6360)	
[2022-01-23 00:21:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][430/1251]	eta 0:30:36 lr 0.000410	time 1.9823 (2.2370)	loss 2.5325 (3.4495)	grad_norm 1.5070 (1.6357)	
[2022-01-23 00:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][440/1251]	eta 0:30:10 lr 0.000410	time 2.2073 (2.2328)	loss 2.4497 (3.4455)	grad_norm 1.9794 (1.6374)	
[2022-01-23 00:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][450/1251]	eta 0:29:46 lr 0.000410	time 1.8330 (2.2304)	loss 3.8044 (3.4469)	grad_norm 1.8536 (1.6393)	
[2022-01-23 00:22:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][460/1251]	eta 0:29:24 lr 0.000410	time 2.5983 (2.2312)	loss 3.9622 (3.4492)	grad_norm 1.6624 (1.6422)	
[2022-01-23 00:22:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][470/1251]	eta 0:29:03 lr 0.000410	time 1.9512 (2.2329)	loss 3.6572 (3.4521)	grad_norm 1.4728 (1.6414)	
[2022-01-23 00:23:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][480/1251]	eta 0:28:43 lr 0.000410	time 2.8178 (2.2354)	loss 3.0474 (3.4495)	grad_norm 1.5834 (1.6420)	
[2022-01-23 00:23:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][490/1251]	eta 0:28:21 lr 0.000410	time 1.6397 (2.2355)	loss 2.6839 (3.4478)	grad_norm 1.5346 (1.6405)	
[2022-01-23 00:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][500/1251]	eta 0:27:59 lr 0.000410	time 1.8192 (2.2365)	loss 3.1906 (3.4458)	grad_norm 1.6148 (1.6404)	
[2022-01-23 00:24:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][510/1251]	eta 0:27:38 lr 0.000410	time 1.9175 (2.2383)	loss 3.9834 (3.4465)	grad_norm 1.7464 (1.6411)	
[2022-01-23 00:24:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][520/1251]	eta 0:27:12 lr 0.000410	time 2.2725 (2.2328)	loss 3.6888 (3.4379)	grad_norm 1.9217 (1.6447)	
[2022-01-23 00:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][530/1251]	eta 0:26:46 lr 0.000410	time 2.0092 (2.2276)	loss 4.2276 (3.4349)	grad_norm 1.6345 (1.6440)	
[2022-01-23 00:25:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][540/1251]	eta 0:26:21 lr 0.000410	time 2.1254 (2.2238)	loss 3.4097 (3.4287)	grad_norm 1.3402 (1.6447)	
[2022-01-23 00:25:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][550/1251]	eta 0:25:57 lr 0.000410	time 1.8373 (2.2215)	loss 4.3600 (3.4326)	grad_norm 1.5813 (1.6437)	
[2022-01-23 00:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][560/1251]	eta 0:25:36 lr 0.000410	time 2.6176 (2.2229)	loss 3.3198 (3.4373)	grad_norm 1.7091 (1.6441)	
[2022-01-23 00:26:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][570/1251]	eta 0:25:13 lr 0.000410	time 2.1645 (2.2230)	loss 3.6298 (3.4366)	grad_norm 2.0023 (1.6465)	
[2022-01-23 00:26:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][580/1251]	eta 0:24:52 lr 0.000410	time 2.8076 (2.2244)	loss 3.7253 (3.4403)	grad_norm 1.5436 (1.6451)	
[2022-01-23 00:27:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][590/1251]	eta 0:24:29 lr 0.000410	time 1.6802 (2.2227)	loss 3.5355 (3.4408)	grad_norm 1.6335 (1.6459)	
[2022-01-23 00:27:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][600/1251]	eta 0:24:07 lr 0.000410	time 2.0625 (2.2237)	loss 3.6791 (3.4412)	grad_norm 1.6455 (1.6455)	
[2022-01-23 00:27:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][610/1251]	eta 0:23:45 lr 0.000410	time 2.2674 (2.2239)	loss 3.6354 (3.4407)	grad_norm 1.5650 (1.6460)	
[2022-01-23 00:28:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][620/1251]	eta 0:23:23 lr 0.000410	time 2.7235 (2.2242)	loss 3.9571 (3.4406)	grad_norm 1.4785 (1.6460)	
[2022-01-23 00:28:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][630/1251]	eta 0:23:01 lr 0.000410	time 1.5464 (2.2239)	loss 4.1336 (3.4390)	grad_norm 1.5633 (1.6462)	
[2022-01-23 00:28:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][640/1251]	eta 0:22:39 lr 0.000410	time 2.1663 (2.2245)	loss 2.8119 (3.4391)	grad_norm 1.4668 (1.6444)	
[2022-01-23 00:29:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][650/1251]	eta 0:22:16 lr 0.000410	time 1.8915 (2.2242)	loss 3.9345 (3.4377)	grad_norm 1.7755 (1.6520)	
[2022-01-23 00:29:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][660/1251]	eta 0:21:55 lr 0.000410	time 1.8857 (2.2257)	loss 3.7713 (3.4412)	grad_norm 1.4773 (1.6544)	
[2022-01-23 00:30:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][670/1251]	eta 0:21:31 lr 0.000410	time 1.9346 (2.2236)	loss 3.5452 (3.4405)	grad_norm 1.6555 (1.6556)	
[2022-01-23 00:30:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][680/1251]	eta 0:21:08 lr 0.000409	time 1.9528 (2.2216)	loss 3.7265 (3.4410)	grad_norm 1.8640 (1.6552)	
[2022-01-23 00:30:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][690/1251]	eta 0:20:45 lr 0.000409	time 1.8578 (2.2199)	loss 4.1191 (3.4410)	grad_norm 1.7060 (1.6550)	
[2022-01-23 00:31:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][700/1251]	eta 0:20:23 lr 0.000409	time 2.4314 (2.2214)	loss 2.8927 (3.4370)	grad_norm 1.6833 (1.6558)	
[2022-01-23 00:31:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][710/1251]	eta 0:20:01 lr 0.000409	time 2.2684 (2.2209)	loss 3.8297 (3.4375)	grad_norm 1.5622 (1.6540)	
[2022-01-23 00:31:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][720/1251]	eta 0:19:38 lr 0.000409	time 1.5789 (2.2202)	loss 3.4122 (3.4403)	grad_norm 1.8216 (1.6541)	
[2022-01-23 00:32:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][730/1251]	eta 0:19:16 lr 0.000409	time 1.7200 (2.2189)	loss 3.9870 (3.4439)	grad_norm 1.4691 (1.6545)	
[2022-01-23 00:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][740/1251]	eta 0:18:54 lr 0.000409	time 1.6636 (2.2193)	loss 3.3693 (3.4446)	grad_norm 1.7097 (1.6544)	
[2022-01-23 00:32:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][750/1251]	eta 0:18:30 lr 0.000409	time 1.7494 (2.2167)	loss 3.0402 (3.4425)	grad_norm 1.6359 (1.6557)	
[2022-01-23 00:33:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][760/1251]	eta 0:18:06 lr 0.000409	time 1.8399 (2.2138)	loss 3.1534 (3.4389)	grad_norm 1.5498 (1.6559)	
[2022-01-23 00:33:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][770/1251]	eta 0:17:44 lr 0.000409	time 2.1836 (2.2126)	loss 2.7239 (3.4410)	grad_norm 1.6945 (1.6561)	
[2022-01-23 00:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][780/1251]	eta 0:17:22 lr 0.000409	time 2.3233 (2.2130)	loss 4.0564 (3.4432)	grad_norm 1.4646 (1.6570)	
[2022-01-23 00:34:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][790/1251]	eta 0:16:59 lr 0.000409	time 1.7896 (2.2116)	loss 4.0058 (3.4432)	grad_norm 1.5655 (1.6583)	
[2022-01-23 00:34:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][800/1251]	eta 0:16:37 lr 0.000409	time 2.5574 (2.2118)	loss 2.4530 (3.4442)	grad_norm 1.2767 (1.6566)	
[2022-01-23 00:35:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][810/1251]	eta 0:16:15 lr 0.000409	time 1.7801 (2.2111)	loss 3.3982 (3.4480)	grad_norm 1.4744 (1.6562)	
[2022-01-23 00:35:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][820/1251]	eta 0:15:53 lr 0.000409	time 1.9303 (2.2121)	loss 3.1691 (3.4510)	grad_norm 1.5072 (1.6559)	
[2022-01-23 00:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][830/1251]	eta 0:15:31 lr 0.000409	time 2.2464 (2.2116)	loss 3.7598 (3.4553)	grad_norm 1.7783 (1.6555)	
[2022-01-23 00:36:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][840/1251]	eta 0:15:09 lr 0.000409	time 1.9495 (2.2117)	loss 3.0976 (3.4576)	grad_norm 1.4955 (1.6554)	
[2022-01-23 00:36:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][850/1251]	eta 0:14:47 lr 0.000409	time 2.0287 (2.2123)	loss 3.6929 (3.4574)	grad_norm 1.5255 (1.6544)	
[2022-01-23 00:36:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][860/1251]	eta 0:14:25 lr 0.000409	time 2.5258 (2.2138)	loss 3.7125 (3.4586)	grad_norm 1.7004 (1.6532)	
[2022-01-23 00:37:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][870/1251]	eta 0:14:02 lr 0.000409	time 1.9839 (2.2123)	loss 3.6464 (3.4588)	grad_norm 1.6242 (1.6516)	
[2022-01-23 00:37:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][880/1251]	eta 0:13:39 lr 0.000409	time 1.8731 (2.2099)	loss 3.1637 (3.4608)	grad_norm 1.6259 (1.6515)	
[2022-01-23 00:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][890/1251]	eta 0:13:17 lr 0.000409	time 1.8873 (2.2084)	loss 3.4853 (3.4612)	grad_norm 1.5631 (1.6523)	
[2022-01-23 00:38:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][900/1251]	eta 0:12:56 lr 0.000409	time 3.4413 (2.2120)	loss 3.6727 (3.4615)	grad_norm 1.5623 (1.6522)	
[2022-01-23 00:38:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][910/1251]	eta 0:12:35 lr 0.000409	time 2.1647 (2.2141)	loss 3.4903 (3.4626)	grad_norm 1.5960 (1.6520)	
[2022-01-23 00:39:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][920/1251]	eta 0:12:12 lr 0.000409	time 2.2593 (2.2125)	loss 4.0131 (3.4625)	grad_norm 1.7349 (1.6519)	
[2022-01-23 00:39:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][930/1251]	eta 0:11:49 lr 0.000408	time 1.9691 (2.2096)	loss 3.7002 (3.4604)	grad_norm 1.5330 (1.6508)	
[2022-01-23 00:39:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][940/1251]	eta 0:11:26 lr 0.000408	time 1.9287 (2.2065)	loss 3.7240 (3.4572)	grad_norm 1.6195 (1.6500)	
[2022-01-23 00:40:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][950/1251]	eta 0:11:03 lr 0.000408	time 2.4222 (2.2054)	loss 3.7505 (3.4580)	grad_norm 1.4273 (1.6493)	
[2022-01-23 00:40:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][960/1251]	eta 0:10:41 lr 0.000408	time 1.9523 (2.2045)	loss 3.9953 (3.4603)	grad_norm 1.5110 (1.6488)	
[2022-01-23 00:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][970/1251]	eta 0:10:19 lr 0.000408	time 1.8205 (2.2035)	loss 3.2534 (3.4595)	grad_norm 1.5778 (1.6505)	
[2022-01-23 00:41:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][980/1251]	eta 0:09:57 lr 0.000408	time 2.0364 (2.2035)	loss 4.0242 (3.4624)	grad_norm 1.7664 (1.6500)	
[2022-01-23 00:41:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][990/1251]	eta 0:09:35 lr 0.000408	time 2.4784 (2.2037)	loss 3.4085 (3.4624)	grad_norm 1.7032 (1.6504)	
[2022-01-23 00:41:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1000/1251]	eta 0:09:13 lr 0.000408	time 2.4799 (2.2051)	loss 2.5123 (3.4620)	grad_norm 1.6995 (1.6507)	
[2022-01-23 00:42:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1010/1251]	eta 0:08:51 lr 0.000408	time 2.4319 (2.2074)	loss 2.5134 (3.4592)	grad_norm 1.5071 (1.6505)	
[2022-01-23 00:42:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1020/1251]	eta 0:08:30 lr 0.000408	time 2.6933 (2.2095)	loss 2.9198 (3.4605)	grad_norm 1.7341 (1.6512)	
[2022-01-23 00:43:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1030/1251]	eta 0:08:07 lr 0.000408	time 1.8969 (2.2081)	loss 4.0415 (3.4604)	grad_norm 1.5638 (1.6510)	
[2022-01-23 00:43:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1040/1251]	eta 0:07:45 lr 0.000408	time 1.7251 (2.2083)	loss 3.7158 (3.4610)	grad_norm 1.6372 (1.6510)	
[2022-01-23 00:43:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1050/1251]	eta 0:07:23 lr 0.000408	time 1.8512 (2.2055)	loss 3.4347 (3.4647)	grad_norm 1.4954 (1.6504)	
[2022-01-23 00:44:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1060/1251]	eta 0:07:00 lr 0.000408	time 1.9061 (2.2028)	loss 4.0108 (3.4683)	grad_norm 1.8173 (1.6509)	
[2022-01-23 00:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1070/1251]	eta 0:06:38 lr 0.000408	time 2.1899 (2.2012)	loss 3.9201 (3.4688)	grad_norm 1.6089 (1.6502)	
[2022-01-23 00:44:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1080/1251]	eta 0:06:16 lr 0.000408	time 2.2059 (2.2011)	loss 2.5840 (3.4702)	grad_norm 2.0184 (1.6500)	
[2022-01-23 00:45:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1090/1251]	eta 0:05:54 lr 0.000408	time 1.8852 (2.2009)	loss 3.2110 (3.4690)	grad_norm 1.7221 (1.6500)	
[2022-01-23 00:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1100/1251]	eta 0:05:32 lr 0.000408	time 2.5291 (2.2024)	loss 3.3222 (3.4635)	grad_norm 1.5705 (1.6502)	
[2022-01-23 00:45:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1110/1251]	eta 0:05:10 lr 0.000408	time 2.2585 (2.2039)	loss 2.6824 (3.4587)	grad_norm 1.6959 (1.6504)	
[2022-01-23 00:46:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1120/1251]	eta 0:04:48 lr 0.000408	time 2.1683 (2.2049)	loss 3.5392 (3.4584)	grad_norm 1.6616 (1.6499)	
[2022-01-23 00:46:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1130/1251]	eta 0:04:26 lr 0.000408	time 2.8224 (2.2048)	loss 3.7529 (3.4589)	grad_norm 1.6472 (1.6496)	
[2022-01-23 00:47:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1140/1251]	eta 0:04:04 lr 0.000408	time 2.2147 (2.2031)	loss 3.3830 (3.4580)	grad_norm 1.6865 (1.6491)	
[2022-01-23 00:47:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1150/1251]	eta 0:03:42 lr 0.000408	time 2.1710 (2.2016)	loss 3.1285 (3.4569)	grad_norm 1.2937 (1.6486)	
[2022-01-23 00:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1160/1251]	eta 0:03:20 lr 0.000408	time 2.8394 (2.2013)	loss 3.5822 (3.4541)	grad_norm 1.3791 (1.6480)	
[2022-01-23 00:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1170/1251]	eta 0:02:58 lr 0.000407	time 1.9053 (2.2003)	loss 2.4113 (3.4529)	grad_norm 1.6087 (1.6475)	
[2022-01-23 00:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1180/1251]	eta 0:02:36 lr 0.000407	time 2.3658 (2.1992)	loss 2.7774 (3.4509)	grad_norm 1.5951 (1.6480)	
[2022-01-23 00:48:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1190/1251]	eta 0:02:14 lr 0.000407	time 2.2776 (2.1992)	loss 3.7517 (3.4508)	grad_norm 1.5280 (1.6489)	
[2022-01-23 00:49:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1200/1251]	eta 0:01:52 lr 0.000407	time 2.9311 (2.2016)	loss 3.3355 (3.4503)	grad_norm 1.4692 (1.6485)	
[2022-01-23 00:49:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1210/1251]	eta 0:01:30 lr 0.000407	time 2.1817 (2.2018)	loss 3.5613 (3.4493)	grad_norm 1.5741 (1.6484)	
[2022-01-23 00:49:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1220/1251]	eta 0:01:08 lr 0.000407	time 2.5586 (2.2018)	loss 3.6651 (3.4503)	grad_norm 1.5263 (1.6480)	
[2022-01-23 00:50:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1230/1251]	eta 0:00:46 lr 0.000407	time 1.7238 (2.2010)	loss 3.7236 (3.4523)	grad_norm 1.5916 (1.6478)	
[2022-01-23 00:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1240/1251]	eta 0:00:24 lr 0.000407	time 1.2877 (2.1992)	loss 3.2931 (3.4535)	grad_norm 1.7453 (1.6478)	
[2022-01-23 00:50:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [168/300][1250/1251]	eta 0:00:02 lr 0.000407	time 1.3184 (2.1934)	loss 4.0180 (3.4531)	grad_norm 2.0515 (1.6476)	
[2022-01-23 00:50:55 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 168 training takes 0:45:44
[2022-01-23 00:51:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.954 (18.954)	Loss 0.9862 (0.9862)	Acc@1 77.832 (77.832)	Acc@5 93.652 (93.652)	
[2022-01-23 00:51:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.939 (3.422)	Loss 0.8987 (0.9942)	Acc@1 79.492 (77.033)	Acc@5 94.531 (93.377)	
[2022-01-23 00:51:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.945 (2.608)	Loss 1.0069 (0.9898)	Acc@1 75.488 (76.930)	Acc@5 93.555 (93.555)	
[2022-01-23 00:52:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.211 (2.279)	Loss 0.9938 (0.9947)	Acc@1 76.367 (76.764)	Acc@5 93.652 (93.536)	
[2022-01-23 00:52:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.171 (2.200)	Loss 0.9371 (0.9883)	Acc@1 76.270 (76.798)	Acc@5 94.727 (93.707)	
[2022-01-23 00:52:32 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.770 Acc@5 93.684
[2022-01-23 00:52:32 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.8%
[2022-01-23 00:52:32 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.82%
[2022-01-23 00:52:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][0/1251]	eta 7:18:39 lr 0.000407	time 21.0390 (21.0390)	loss 3.8790 (3.8790)	grad_norm 1.6041 (1.6041)	
[2022-01-23 00:53:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][10/1251]	eta 1:25:14 lr 0.000407	time 2.7289 (4.1209)	loss 3.5494 (3.1078)	grad_norm 1.5822 (1.5884)	
[2022-01-23 00:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][20/1251]	eta 1:04:21 lr 0.000407	time 1.5447 (3.1369)	loss 3.3560 (3.2049)	grad_norm 1.5670 (1.5979)	
[2022-01-23 00:54:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][30/1251]	eta 0:57:59 lr 0.000407	time 1.8435 (2.8500)	loss 2.2442 (3.2467)	grad_norm 1.6579 (1.5823)	
[2022-01-23 00:54:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][40/1251]	eta 0:54:49 lr 0.000407	time 3.9959 (2.7159)	loss 3.0375 (3.2195)	grad_norm 1.4389 (1.6080)	
[2022-01-23 00:54:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][50/1251]	eta 0:52:36 lr 0.000407	time 1.5441 (2.6279)	loss 3.5522 (3.2939)	grad_norm 1.5670 (1.5993)	
[2022-01-23 00:55:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][60/1251]	eta 0:50:40 lr 0.000407	time 2.1861 (2.5530)	loss 3.8511 (3.2798)	grad_norm 1.5877 (1.6132)	
[2022-01-23 00:55:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][70/1251]	eta 0:49:22 lr 0.000407	time 1.9124 (2.5087)	loss 4.1700 (3.3198)	grad_norm 1.6757 (1.6264)	
[2022-01-23 00:55:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][80/1251]	eta 0:48:14 lr 0.000407	time 2.8561 (2.4721)	loss 3.4924 (3.3281)	grad_norm 1.7073 (1.6245)	
[2022-01-23 00:56:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][90/1251]	eta 0:47:31 lr 0.000407	time 1.9244 (2.4558)	loss 4.2369 (3.3662)	grad_norm 1.5567 (1.6151)	
[2022-01-23 00:56:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][100/1251]	eta 0:46:27 lr 0.000407	time 2.4489 (2.4214)	loss 3.8139 (3.3890)	grad_norm 1.8898 (1.6201)	
[2022-01-23 00:56:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][110/1251]	eta 0:45:30 lr 0.000407	time 1.9178 (2.3935)	loss 3.8900 (3.3949)	grad_norm 1.6009 (1.6299)	
[2022-01-23 00:57:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][120/1251]	eta 0:44:47 lr 0.000407	time 2.8708 (2.3764)	loss 3.4555 (3.3955)	grad_norm 1.9751 (1.6358)	
[2022-01-23 00:57:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][130/1251]	eta 0:44:14 lr 0.000407	time 2.6457 (2.3679)	loss 3.3607 (3.3947)	grad_norm 1.7174 (1.6349)	
[2022-01-23 00:58:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][140/1251]	eta 0:43:45 lr 0.000407	time 2.7832 (2.3633)	loss 4.2286 (3.4080)	grad_norm 1.8186 (1.6300)	
[2022-01-23 00:58:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][150/1251]	eta 0:43:10 lr 0.000407	time 1.8933 (2.3532)	loss 3.0441 (3.4056)	grad_norm 1.4226 (1.6299)	
[2022-01-23 00:58:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][160/1251]	eta 0:42:38 lr 0.000407	time 2.5711 (2.3452)	loss 3.0191 (3.4040)	grad_norm 1.5170 (1.6336)	
[2022-01-23 00:59:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][170/1251]	eta 0:41:53 lr 0.000406	time 1.7850 (2.3254)	loss 3.6356 (3.4000)	grad_norm 1.7601 (1.6368)	
[2022-01-23 00:59:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][180/1251]	eta 0:41:10 lr 0.000406	time 2.1676 (2.3063)	loss 3.5178 (3.4002)	grad_norm 1.7678 (1.6375)	
[2022-01-23 00:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][190/1251]	eta 0:40:30 lr 0.000406	time 2.0645 (2.2912)	loss 2.8653 (3.4002)	grad_norm 1.4202 (1.6316)	
[2022-01-23 01:00:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][200/1251]	eta 0:40:00 lr 0.000406	time 2.6033 (2.2839)	loss 3.9458 (3.3920)	grad_norm 1.5966 (1.6325)	
[2022-01-23 01:00:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][210/1251]	eta 0:39:32 lr 0.000406	time 2.1966 (2.2795)	loss 3.4932 (3.3996)	grad_norm 1.4153 (1.6283)	
[2022-01-23 01:00:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][220/1251]	eta 0:39:09 lr 0.000406	time 2.5751 (2.2784)	loss 3.6283 (3.4149)	grad_norm 2.0687 (1.6347)	
[2022-01-23 01:01:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][230/1251]	eta 0:38:39 lr 0.000406	time 1.4256 (2.2721)	loss 3.2310 (3.4247)	grad_norm 1.7215 (1.6328)	
[2022-01-23 01:01:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][240/1251]	eta 0:38:23 lr 0.000406	time 2.6017 (2.2783)	loss 3.0130 (3.4218)	grad_norm 1.4109 (1.6294)	
[2022-01-23 01:02:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][250/1251]	eta 0:38:01 lr 0.000406	time 2.4346 (2.2792)	loss 3.3092 (3.4250)	grad_norm 1.6463 (1.6267)	
[2022-01-23 01:02:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][260/1251]	eta 0:37:33 lr 0.000406	time 2.0073 (2.2741)	loss 3.6045 (3.4141)	grad_norm 1.5053 (1.6259)	
[2022-01-23 01:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][270/1251]	eta 0:37:06 lr 0.000406	time 1.5959 (2.2693)	loss 3.0639 (3.4144)	grad_norm 1.5074 (1.6259)	
[2022-01-23 01:03:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][280/1251]	eta 0:36:37 lr 0.000406	time 1.8818 (2.2636)	loss 3.4627 (3.4170)	grad_norm 1.4523 (1.6234)	
[2022-01-23 01:03:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][290/1251]	eta 0:36:16 lr 0.000406	time 2.5962 (2.2644)	loss 3.8141 (3.4187)	grad_norm 1.7704 (1.6234)	
[2022-01-23 01:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][300/1251]	eta 0:35:49 lr 0.000406	time 2.2335 (2.2601)	loss 3.5445 (3.4272)	grad_norm 1.4387 (1.6244)	
[2022-01-23 01:04:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][310/1251]	eta 0:35:25 lr 0.000406	time 1.9473 (2.2592)	loss 3.3108 (3.4243)	grad_norm 1.6800 (1.6218)	
[2022-01-23 01:04:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][320/1251]	eta 0:35:00 lr 0.000406	time 2.2148 (2.2557)	loss 3.3311 (3.4261)	grad_norm 1.5959 (1.6208)	
[2022-01-23 01:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][330/1251]	eta 0:34:37 lr 0.000406	time 2.2491 (2.2557)	loss 4.1058 (3.4328)	grad_norm 1.6109 (1.6194)	
[2022-01-23 01:05:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][340/1251]	eta 0:34:08 lr 0.000406	time 2.1729 (2.2489)	loss 3.7639 (3.4332)	grad_norm 1.5410 (1.6238)	
[2022-01-23 01:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][350/1251]	eta 0:33:39 lr 0.000406	time 1.5698 (2.2416)	loss 3.1329 (3.4285)	grad_norm 1.7868 (1.6283)	
[2022-01-23 01:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][360/1251]	eta 0:33:15 lr 0.000406	time 2.2092 (2.2391)	loss 3.8780 (3.4346)	grad_norm 1.5552 (1.6286)	
[2022-01-23 01:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][370/1251]	eta 0:32:54 lr 0.000406	time 2.4535 (2.2415)	loss 3.3250 (3.4408)	grad_norm 2.5197 (1.6311)	
[2022-01-23 01:06:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][380/1251]	eta 0:32:29 lr 0.000406	time 2.1135 (2.2377)	loss 3.5056 (3.4418)	grad_norm 1.7916 (1.6320)	
[2022-01-23 01:07:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][390/1251]	eta 0:32:08 lr 0.000406	time 2.4357 (2.2393)	loss 4.0341 (3.4479)	grad_norm 1.7032 (1.6361)	
[2022-01-23 01:07:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][400/1251]	eta 0:31:47 lr 0.000406	time 2.0019 (2.2411)	loss 3.4838 (3.4340)	grad_norm 1.7682 (1.6395)	
[2022-01-23 01:07:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][410/1251]	eta 0:31:21 lr 0.000405	time 1.9358 (2.2371)	loss 3.6176 (3.4382)	grad_norm 1.8197 (1.6400)	
[2022-01-23 01:08:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][420/1251]	eta 0:30:54 lr 0.000405	time 2.2295 (2.2315)	loss 3.6394 (3.4360)	grad_norm 1.5275 (1.6393)	
[2022-01-23 01:08:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][430/1251]	eta 0:30:26 lr 0.000405	time 1.7086 (2.2253)	loss 3.7447 (3.4401)	grad_norm 1.7290 (1.6401)	
[2022-01-23 01:08:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][440/1251]	eta 0:30:01 lr 0.000405	time 2.4531 (2.2217)	loss 4.0642 (3.4476)	grad_norm 1.6932 (1.6408)	
[2022-01-23 01:09:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][450/1251]	eta 0:29:34 lr 0.000405	time 1.7891 (2.2155)	loss 2.6633 (3.4470)	grad_norm 1.5942 (1.6398)	
[2022-01-23 01:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][460/1251]	eta 0:29:10 lr 0.000405	time 2.4584 (2.2131)	loss 3.6660 (3.4427)	grad_norm 1.8296 (1.6400)	
[2022-01-23 01:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][470/1251]	eta 0:28:48 lr 0.000405	time 2.0462 (2.2132)	loss 3.8634 (3.4482)	grad_norm 1.5312 (1.6394)	
[2022-01-23 01:10:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][480/1251]	eta 0:28:27 lr 0.000405	time 1.8992 (2.2150)	loss 3.9848 (3.4516)	grad_norm 1.6931 (1.6394)	
[2022-01-23 01:10:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][490/1251]	eta 0:28:07 lr 0.000405	time 2.2320 (2.2178)	loss 3.5082 (3.4480)	grad_norm 1.6735 (1.6383)	
[2022-01-23 01:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][500/1251]	eta 0:27:46 lr 0.000405	time 1.9350 (2.2186)	loss 3.6554 (3.4504)	grad_norm 1.4086 (1.6375)	
[2022-01-23 01:11:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][510/1251]	eta 0:27:25 lr 0.000405	time 2.4631 (2.2205)	loss 2.8785 (3.4516)	grad_norm 1.7554 (1.6368)	
[2022-01-23 01:11:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][520/1251]	eta 0:27:04 lr 0.000405	time 1.7212 (2.2223)	loss 3.7991 (3.4519)	grad_norm 1.7954 (1.6371)	
[2022-01-23 01:12:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][530/1251]	eta 0:26:42 lr 0.000405	time 1.9040 (2.2228)	loss 3.7344 (3.4528)	grad_norm 1.7847 (1.6412)	
[2022-01-23 01:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][540/1251]	eta 0:26:20 lr 0.000405	time 1.8265 (2.2231)	loss 4.0050 (3.4576)	grad_norm 1.6809 (1.6437)	
[2022-01-23 01:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][550/1251]	eta 0:25:58 lr 0.000405	time 2.1978 (2.2229)	loss 3.5640 (3.4574)	grad_norm 1.5360 (1.6433)	
[2022-01-23 01:13:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][560/1251]	eta 0:25:34 lr 0.000405	time 1.9172 (2.2205)	loss 3.9209 (3.4541)	grad_norm 1.5104 (1.6465)	
[2022-01-23 01:13:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][570/1251]	eta 0:25:11 lr 0.000405	time 3.4310 (2.2193)	loss 3.8256 (3.4625)	grad_norm 1.5187 (1.6466)	
[2022-01-23 01:14:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][580/1251]	eta 0:24:48 lr 0.000405	time 2.0039 (2.2182)	loss 3.8347 (3.4656)	grad_norm 1.7689 (1.6471)	
[2022-01-23 01:14:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][590/1251]	eta 0:24:25 lr 0.000405	time 2.8268 (2.2169)	loss 2.5785 (3.4672)	grad_norm 1.7725 (1.6485)	
[2022-01-23 01:14:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][600/1251]	eta 0:24:02 lr 0.000405	time 2.0881 (2.2154)	loss 2.8344 (3.4676)	grad_norm 1.4696 (1.6479)	
[2022-01-23 01:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][610/1251]	eta 0:23:38 lr 0.000405	time 1.8918 (2.2137)	loss 3.4799 (3.4703)	grad_norm 1.8266 (1.6496)	
[2022-01-23 01:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][620/1251]	eta 0:23:14 lr 0.000405	time 1.9468 (2.2101)	loss 2.5070 (3.4684)	grad_norm 1.5165 (1.6473)	
[2022-01-23 01:15:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][630/1251]	eta 0:22:52 lr 0.000405	time 2.2091 (2.2098)	loss 3.2818 (3.4632)	grad_norm 1.5223 (1.6457)	
[2022-01-23 01:16:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][640/1251]	eta 0:22:30 lr 0.000405	time 2.5155 (2.2098)	loss 3.8415 (3.4642)	grad_norm 1.7812 (1.6445)	
[2022-01-23 01:16:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][650/1251]	eta 0:22:08 lr 0.000405	time 1.5647 (2.2105)	loss 3.8687 (3.4661)	grad_norm 1.4194 (1.6438)	
[2022-01-23 01:16:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][660/1251]	eta 0:21:47 lr 0.000404	time 2.3897 (2.2121)	loss 3.6785 (3.4627)	grad_norm 1.5197 (1.6418)	
[2022-01-23 01:17:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][670/1251]	eta 0:21:24 lr 0.000404	time 1.9706 (2.2116)	loss 3.8637 (3.4635)	grad_norm 1.4907 (1.6416)	
[2022-01-23 01:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][680/1251]	eta 0:21:03 lr 0.000404	time 2.8539 (2.2129)	loss 3.0913 (3.4639)	grad_norm 1.4714 (1.6407)	
[2022-01-23 01:18:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][690/1251]	eta 0:20:41 lr 0.000404	time 1.6338 (2.2125)	loss 2.8507 (3.4631)	grad_norm 2.0027 (1.6402)	
[2022-01-23 01:18:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][700/1251]	eta 0:20:18 lr 0.000404	time 1.9306 (2.2113)	loss 4.0166 (3.4655)	grad_norm 1.5381 (1.6397)	
[2022-01-23 01:18:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][710/1251]	eta 0:19:55 lr 0.000404	time 1.9411 (2.2096)	loss 3.7194 (3.4665)	grad_norm 1.7163 (1.6398)	
[2022-01-23 01:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][720/1251]	eta 0:19:34 lr 0.000404	time 3.1006 (2.2112)	loss 2.9273 (3.4659)	grad_norm 1.5845 (1.6394)	
[2022-01-23 01:19:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][730/1251]	eta 0:19:10 lr 0.000404	time 1.6122 (2.2075)	loss 3.7110 (3.4670)	grad_norm 1.7131 (1.6392)	
[2022-01-23 01:19:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][740/1251]	eta 0:18:47 lr 0.000404	time 2.3559 (2.2056)	loss 4.0287 (3.4684)	grad_norm 1.8399 (1.6403)	
[2022-01-23 01:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][750/1251]	eta 0:18:23 lr 0.000404	time 1.8491 (2.2033)	loss 4.2418 (3.4687)	grad_norm 1.5542 (1.6402)	
[2022-01-23 01:20:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][760/1251]	eta 0:18:02 lr 0.000404	time 2.1075 (2.2042)	loss 3.7850 (3.4690)	grad_norm 1.7529 (1.6408)	
[2022-01-23 01:20:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][770/1251]	eta 0:17:39 lr 0.000404	time 1.5638 (2.2025)	loss 4.0211 (3.4696)	grad_norm 1.5452 (1.6401)	
[2022-01-23 01:21:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][780/1251]	eta 0:17:17 lr 0.000404	time 3.3479 (2.2038)	loss 2.5266 (3.4694)	grad_norm 1.6155 (1.6411)	
[2022-01-23 01:21:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][790/1251]	eta 0:16:56 lr 0.000404	time 2.2210 (2.2040)	loss 3.7841 (3.4674)	grad_norm 1.6336 (1.6415)	
[2022-01-23 01:21:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][800/1251]	eta 0:16:34 lr 0.000404	time 2.2039 (2.2045)	loss 4.2256 (3.4686)	grad_norm 1.7113 (1.6418)	
[2022-01-23 01:22:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][810/1251]	eta 0:16:12 lr 0.000404	time 1.8632 (2.2045)	loss 3.9422 (3.4664)	grad_norm 1.5612 (1.6421)	
[2022-01-23 01:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][820/1251]	eta 0:15:51 lr 0.000404	time 2.6733 (2.2068)	loss 3.7401 (3.4660)	grad_norm 1.7919 (1.6442)	
[2022-01-23 01:23:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][830/1251]	eta 0:15:28 lr 0.000404	time 1.7936 (2.2051)	loss 3.7007 (3.4644)	grad_norm 1.5697 (1.6429)	
[2022-01-23 01:23:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][840/1251]	eta 0:15:05 lr 0.000404	time 1.6523 (2.2040)	loss 3.5760 (3.4644)	grad_norm 1.7669 (1.6445)	
[2022-01-23 01:23:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][850/1251]	eta 0:14:42 lr 0.000404	time 1.9209 (2.2016)	loss 3.5064 (3.4644)	grad_norm 1.7295 (1.6450)	
[2022-01-23 01:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][860/1251]	eta 0:14:21 lr 0.000404	time 3.3761 (2.2037)	loss 3.6499 (3.4652)	grad_norm 1.5797 (1.6454)	
[2022-01-23 01:24:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][870/1251]	eta 0:14:00 lr 0.000404	time 2.3843 (2.2049)	loss 3.1223 (3.4639)	grad_norm 1.5342 (1.6442)	
[2022-01-23 01:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][880/1251]	eta 0:13:38 lr 0.000404	time 1.6293 (2.2049)	loss 2.5687 (3.4618)	grad_norm 1.8602 (1.6462)	
[2022-01-23 01:25:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][890/1251]	eta 0:13:16 lr 0.000404	time 2.1706 (2.2054)	loss 2.7369 (3.4622)	grad_norm 1.5953 (1.6468)	
[2022-01-23 01:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][900/1251]	eta 0:12:53 lr 0.000404	time 2.1904 (2.2038)	loss 4.0542 (3.4619)	grad_norm 1.6107 (1.6469)	
[2022-01-23 01:25:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][910/1251]	eta 0:12:31 lr 0.000403	time 2.6685 (2.2025)	loss 2.4476 (3.4596)	grad_norm 1.5849 (1.6470)	
[2022-01-23 01:26:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][920/1251]	eta 0:12:08 lr 0.000403	time 2.4868 (2.2020)	loss 3.7667 (3.4599)	grad_norm 1.7987 (1.6485)	
[2022-01-23 01:26:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][930/1251]	eta 0:11:46 lr 0.000403	time 1.8917 (2.2000)	loss 3.4522 (3.4609)	grad_norm 1.8884 (1.6492)	
[2022-01-23 01:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][940/1251]	eta 0:11:24 lr 0.000403	time 2.6766 (2.1998)	loss 4.2313 (3.4595)	grad_norm 1.6552 (1.6492)	
[2022-01-23 01:27:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][950/1251]	eta 0:11:01 lr 0.000403	time 2.2672 (2.1993)	loss 3.6519 (3.4593)	grad_norm 1.5375 (1.6484)	
[2022-01-23 01:27:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][960/1251]	eta 0:10:40 lr 0.000403	time 2.3957 (2.2000)	loss 3.6306 (3.4602)	grad_norm 1.4629 (1.6471)	
[2022-01-23 01:28:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][970/1251]	eta 0:10:18 lr 0.000403	time 1.9540 (2.2005)	loss 3.8318 (3.4609)	grad_norm 1.6819 (1.6472)	
[2022-01-23 01:28:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][980/1251]	eta 0:09:56 lr 0.000403	time 2.6120 (2.2007)	loss 2.8748 (3.4628)	grad_norm 1.7659 (1.6475)	
[2022-01-23 01:28:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][990/1251]	eta 0:09:34 lr 0.000403	time 1.8469 (2.2014)	loss 4.0128 (3.4654)	grad_norm 1.8227 (1.6478)	
[2022-01-23 01:29:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1000/1251]	eta 0:09:12 lr 0.000403	time 2.8346 (2.2027)	loss 4.0619 (3.4670)	grad_norm 1.5720 (1.6468)	
[2022-01-23 01:29:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1010/1251]	eta 0:08:50 lr 0.000403	time 1.7611 (2.2029)	loss 3.0635 (3.4661)	grad_norm 1.6868 (1.6477)	
[2022-01-23 01:30:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1020/1251]	eta 0:08:28 lr 0.000403	time 1.9763 (2.2015)	loss 4.1828 (3.4693)	grad_norm 1.7179 (1.6480)	
[2022-01-23 01:30:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1030/1251]	eta 0:08:06 lr 0.000403	time 1.9446 (2.2002)	loss 2.9015 (3.4686)	grad_norm 1.6934 (1.6474)	
[2022-01-23 01:30:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1040/1251]	eta 0:07:44 lr 0.000403	time 2.5841 (2.2002)	loss 3.5512 (3.4690)	grad_norm 1.7708 (1.6476)	
[2022-01-23 01:31:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1050/1251]	eta 0:07:22 lr 0.000403	time 1.5295 (2.2004)	loss 3.4077 (3.4704)	grad_norm 1.4149 (1.6461)	
[2022-01-23 01:31:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1060/1251]	eta 0:07:00 lr 0.000403	time 2.0663 (2.1997)	loss 2.5224 (3.4678)	grad_norm 1.6942 (1.6455)	
[2022-01-23 01:31:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1070/1251]	eta 0:06:38 lr 0.000403	time 1.6095 (2.1992)	loss 3.6606 (3.4693)	grad_norm 1.5809 (1.6446)	
[2022-01-23 01:32:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1080/1251]	eta 0:06:16 lr 0.000403	time 2.7790 (2.1996)	loss 4.0209 (3.4703)	grad_norm 2.0531 (1.6447)	
[2022-01-23 01:32:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1090/1251]	eta 0:05:54 lr 0.000403	time 1.5070 (2.2008)	loss 2.9405 (3.4695)	grad_norm 1.6236 (1.6436)	
[2022-01-23 01:32:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1100/1251]	eta 0:05:32 lr 0.000403	time 1.5969 (2.2006)	loss 3.6002 (3.4676)	grad_norm 1.7408 (1.6440)	
[2022-01-23 01:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1110/1251]	eta 0:05:10 lr 0.000403	time 1.8881 (2.2005)	loss 3.4197 (3.4668)	grad_norm 1.6936 (1.6446)	
[2022-01-23 01:33:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1120/1251]	eta 0:04:48 lr 0.000403	time 2.2451 (2.1997)	loss 4.2278 (3.4669)	grad_norm 1.7597 (1.6447)	
[2022-01-23 01:34:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1130/1251]	eta 0:04:26 lr 0.000403	time 1.5493 (2.2000)	loss 3.0402 (3.4679)	grad_norm 1.4898 (1.6447)	
[2022-01-23 01:34:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1140/1251]	eta 0:04:04 lr 0.000403	time 1.7680 (2.1984)	loss 3.6074 (3.4703)	grad_norm 1.6802 (1.6440)	
[2022-01-23 01:34:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1150/1251]	eta 0:03:42 lr 0.000402	time 2.1137 (2.1981)	loss 4.1251 (3.4710)	grad_norm 1.4832 (1.6434)	
[2022-01-23 01:35:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1160/1251]	eta 0:03:20 lr 0.000402	time 3.1060 (2.1984)	loss 3.7150 (3.4720)	grad_norm 1.5302 (1.6424)	
[2022-01-23 01:35:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1170/1251]	eta 0:02:58 lr 0.000402	time 3.1399 (2.1992)	loss 2.3976 (3.4703)	grad_norm 1.5360 (1.6422)	
[2022-01-23 01:35:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1180/1251]	eta 0:02:36 lr 0.000402	time 2.1242 (2.1994)	loss 2.6632 (3.4706)	grad_norm 1.9157 (1.6420)	
[2022-01-23 01:36:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1190/1251]	eta 0:02:14 lr 0.000402	time 2.2010 (2.1998)	loss 3.3214 (3.4696)	grad_norm 1.4941 (1.6418)	
[2022-01-23 01:36:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1200/1251]	eta 0:01:52 lr 0.000402	time 2.5340 (2.1999)	loss 2.2893 (3.4673)	grad_norm 1.5100 (1.6417)	
[2022-01-23 01:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1210/1251]	eta 0:01:30 lr 0.000402	time 1.9530 (2.1993)	loss 2.4239 (3.4637)	grad_norm 1.5058 (1.6414)	
[2022-01-23 01:37:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1220/1251]	eta 0:01:08 lr 0.000402	time 2.0614 (2.1986)	loss 4.3608 (3.4648)	grad_norm 1.5091 (1.6409)	
[2022-01-23 01:37:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1230/1251]	eta 0:00:46 lr 0.000402	time 1.9352 (2.1985)	loss 3.9314 (3.4666)	grad_norm 1.4785 (1.6400)	
[2022-01-23 01:38:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1240/1251]	eta 0:00:24 lr 0.000402	time 1.4478 (2.1979)	loss 3.1306 (3.4654)	grad_norm 1.6982 (1.6397)	
[2022-01-23 01:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [169/300][1250/1251]	eta 0:00:02 lr 0.000402	time 1.1680 (2.1932)	loss 3.0005 (3.4666)	grad_norm 1.4773 (1.6390)	
[2022-01-23 01:38:16 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 169 training takes 0:45:44
[2022-01-23 01:38:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.769 (17.769)	Loss 1.0747 (1.0747)	Acc@1 74.805 (74.805)	Acc@5 91.699 (91.699)	
[2022-01-23 01:38:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.241 (3.364)	Loss 1.0556 (1.0091)	Acc@1 74.023 (76.465)	Acc@5 92.383 (93.457)	
[2022-01-23 01:39:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.313 (2.601)	Loss 0.9111 (1.0006)	Acc@1 78.223 (76.660)	Acc@5 94.531 (93.652)	
[2022-01-23 01:39:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.926 (2.367)	Loss 1.0549 (1.0034)	Acc@1 76.465 (76.588)	Acc@5 93.457 (93.655)	
[2022-01-23 01:39:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.142 (2.221)	Loss 1.0334 (1.0004)	Acc@1 75.781 (76.705)	Acc@5 93.457 (93.681)	
[2022-01-23 01:39:55 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.788 Acc@5 93.638
[2022-01-23 01:39:55 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.8%
[2022-01-23 01:39:55 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.82%
[2022-01-23 01:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][0/1251]	eta 7:11:06 lr 0.000402	time 20.6766 (20.6766)	loss 2.6924 (2.6924)	grad_norm 1.9016 (1.9016)	
[2022-01-23 01:40:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][10/1251]	eta 1:26:21 lr 0.000402	time 2.8956 (4.1754)	loss 3.4584 (3.0901)	grad_norm 1.4476 (1.6243)	
[2022-01-23 01:41:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][20/1251]	eta 1:06:26 lr 0.000402	time 2.2670 (3.2384)	loss 2.9825 (3.2157)	grad_norm 1.4809 (1.6206)	
[2022-01-23 01:41:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][30/1251]	eta 0:58:07 lr 0.000402	time 1.5956 (2.8564)	loss 3.5302 (3.2948)	grad_norm 2.0070 (1.6144)	
[2022-01-23 01:41:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][40/1251]	eta 0:54:58 lr 0.000402	time 3.6213 (2.7235)	loss 2.7223 (3.4001)	grad_norm 1.6639 (1.6076)	
[2022-01-23 01:42:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][50/1251]	eta 0:52:29 lr 0.000402	time 1.9398 (2.6221)	loss 3.7080 (3.4013)	grad_norm 1.7187 (1.6023)	
[2022-01-23 01:42:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][60/1251]	eta 0:51:06 lr 0.000402	time 1.8607 (2.5743)	loss 3.8372 (3.3956)	grad_norm 1.4205 (1.5915)	
[2022-01-23 01:42:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][70/1251]	eta 0:49:36 lr 0.000402	time 1.6518 (2.5204)	loss 3.8551 (3.4310)	grad_norm 1.8437 (1.6038)	
[2022-01-23 01:43:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][80/1251]	eta 0:48:52 lr 0.000402	time 3.6249 (2.5044)	loss 3.6316 (3.4432)	grad_norm 1.6099 (1.6120)	
[2022-01-23 01:43:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][90/1251]	eta 0:48:00 lr 0.000402	time 1.8869 (2.4808)	loss 2.3879 (3.4413)	grad_norm 1.7487 (1.6243)	
[2022-01-23 01:44:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][100/1251]	eta 0:46:40 lr 0.000402	time 1.7240 (2.4327)	loss 3.8378 (3.4493)	grad_norm 1.6525 (1.6256)	
[2022-01-23 01:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][110/1251]	eta 0:45:45 lr 0.000402	time 2.2712 (2.4060)	loss 3.5641 (3.4708)	grad_norm 1.7587 (1.6257)	
[2022-01-23 01:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][120/1251]	eta 0:45:13 lr 0.000402	time 2.4967 (2.3994)	loss 3.7948 (3.4766)	grad_norm 1.8708 (1.6229)	
[2022-01-23 01:45:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][130/1251]	eta 0:44:30 lr 0.000402	time 2.3899 (2.3822)	loss 2.9890 (3.4678)	grad_norm 1.7418 (1.6250)	
[2022-01-23 01:45:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][140/1251]	eta 0:43:43 lr 0.000402	time 1.5876 (2.3612)	loss 3.5165 (3.4617)	grad_norm 1.6428 (1.6249)	
[2022-01-23 01:45:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][150/1251]	eta 0:42:58 lr 0.000401	time 2.1948 (2.3415)	loss 3.5488 (3.4838)	grad_norm 1.7148 (1.6344)	
[2022-01-23 01:46:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][160/1251]	eta 0:42:21 lr 0.000401	time 2.2017 (2.3293)	loss 2.8890 (3.4749)	grad_norm 1.9036 (1.6549)	
[2022-01-23 01:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][170/1251]	eta 0:41:57 lr 0.000401	time 3.0142 (2.3287)	loss 3.3632 (3.4685)	grad_norm 1.5061 (1.6560)	
[2022-01-23 01:46:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][180/1251]	eta 0:41:19 lr 0.000401	time 2.2521 (2.3147)	loss 4.2011 (3.4799)	grad_norm 1.8361 (1.6532)	
[2022-01-23 01:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][190/1251]	eta 0:40:46 lr 0.000401	time 2.1986 (2.3055)	loss 3.4235 (3.4814)	grad_norm 1.3447 (1.6503)	
[2022-01-23 01:47:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][200/1251]	eta 0:40:13 lr 0.000401	time 2.0450 (2.2968)	loss 2.8119 (3.4671)	grad_norm 1.6722 (1.6483)	
[2022-01-23 01:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][210/1251]	eta 0:39:44 lr 0.000401	time 2.1780 (2.2903)	loss 2.9711 (3.4626)	grad_norm 1.8040 (1.6505)	
[2022-01-23 01:48:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][220/1251]	eta 0:39:10 lr 0.000401	time 2.5888 (2.2798)	loss 4.1344 (3.4565)	grad_norm 1.5243 (1.6514)	
[2022-01-23 01:48:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][230/1251]	eta 0:38:46 lr 0.000401	time 2.6165 (2.2785)	loss 3.5526 (3.4622)	grad_norm 1.5327 (1.6493)	
[2022-01-23 01:49:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][240/1251]	eta 0:38:19 lr 0.000401	time 2.2310 (2.2744)	loss 3.5585 (3.4505)	grad_norm 1.5920 (1.6516)	
[2022-01-23 01:49:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][250/1251]	eta 0:37:57 lr 0.000401	time 2.2930 (2.2752)	loss 4.1246 (3.4480)	grad_norm 1.5571 (1.6480)	
[2022-01-23 01:49:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][260/1251]	eta 0:37:25 lr 0.000401	time 1.7745 (2.2664)	loss 2.6454 (3.4512)	grad_norm 1.4935 (1.6483)	
[2022-01-23 01:50:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][270/1251]	eta 0:36:57 lr 0.000401	time 1.8877 (2.2608)	loss 2.5356 (3.4424)	grad_norm 1.5459 (1.6462)	
[2022-01-23 01:50:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][280/1251]	eta 0:36:29 lr 0.000401	time 2.2445 (2.2547)	loss 3.8858 (3.4524)	grad_norm 1.3507 (1.6433)	
[2022-01-23 01:50:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][290/1251]	eta 0:36:02 lr 0.000401	time 2.1137 (2.2502)	loss 3.2891 (3.4518)	grad_norm 1.5232 (1.6442)	
[2022-01-23 01:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][300/1251]	eta 0:35:35 lr 0.000401	time 1.8913 (2.2454)	loss 3.2857 (3.4574)	grad_norm 1.7912 (1.6445)	
[2022-01-23 01:51:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][310/1251]	eta 0:35:10 lr 0.000401	time 1.8668 (2.2424)	loss 3.2596 (3.4545)	grad_norm 1.6567 (1.6431)	
[2022-01-23 01:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][320/1251]	eta 0:34:48 lr 0.000401	time 2.7473 (2.2430)	loss 3.9167 (3.4570)	grad_norm 1.6160 (1.6412)	
[2022-01-23 01:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][330/1251]	eta 0:34:28 lr 0.000401	time 2.3198 (2.2462)	loss 2.5571 (3.4552)	grad_norm 1.5833 (1.6397)	
[2022-01-23 01:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][340/1251]	eta 0:34:07 lr 0.000401	time 2.5767 (2.2473)	loss 3.7884 (3.4548)	grad_norm 1.6686 (1.6387)	
[2022-01-23 01:53:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][350/1251]	eta 0:33:42 lr 0.000401	time 1.9681 (2.2445)	loss 3.2327 (3.4592)	grad_norm 1.7173 (1.6385)	
[2022-01-23 01:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][360/1251]	eta 0:33:18 lr 0.000401	time 1.8343 (2.2427)	loss 3.9705 (3.4581)	grad_norm 1.8093 (1.6426)	
[2022-01-23 01:53:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][370/1251]	eta 0:32:56 lr 0.000401	time 2.6827 (2.2440)	loss 3.4791 (3.4566)	grad_norm 1.8631 (1.6430)	
[2022-01-23 01:54:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][380/1251]	eta 0:32:33 lr 0.000401	time 2.3506 (2.2434)	loss 4.0871 (3.4559)	grad_norm 1.6522 (1.6440)	
[2022-01-23 01:54:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][390/1251]	eta 0:32:08 lr 0.000401	time 1.9700 (2.2403)	loss 2.9564 (3.4560)	grad_norm 1.8436 (1.6451)	
[2022-01-23 01:54:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][400/1251]	eta 0:31:41 lr 0.000400	time 1.7268 (2.2348)	loss 4.1816 (3.4562)	grad_norm 1.8086 (1.6456)	
[2022-01-23 01:55:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][410/1251]	eta 0:31:20 lr 0.000400	time 2.4364 (2.2356)	loss 3.7650 (3.4620)	grad_norm 1.7664 (1.6464)	
[2022-01-23 01:55:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][420/1251]	eta 0:30:54 lr 0.000400	time 1.6949 (2.2311)	loss 2.9711 (3.4639)	grad_norm 1.7708 (1.6453)	
[2022-01-23 01:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][430/1251]	eta 0:30:28 lr 0.000400	time 1.9635 (2.2276)	loss 2.9752 (3.4628)	grad_norm 1.7961 (1.6466)	
[2022-01-23 01:56:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][440/1251]	eta 0:30:06 lr 0.000400	time 1.6022 (2.2278)	loss 3.5970 (3.4590)	grad_norm 1.7225 (1.6452)	
[2022-01-23 01:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][450/1251]	eta 0:29:46 lr 0.000400	time 3.3720 (2.2306)	loss 2.8742 (3.4498)	grad_norm 1.5373 (1.6444)	
[2022-01-23 01:57:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][460/1251]	eta 0:29:24 lr 0.000400	time 1.8089 (2.2311)	loss 3.7459 (3.4505)	grad_norm 1.6829 (1.6443)	
[2022-01-23 01:57:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][470/1251]	eta 0:29:02 lr 0.000400	time 2.0730 (2.2308)	loss 3.8854 (3.4517)	grad_norm 1.6695 (1.6444)	
[2022-01-23 01:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][480/1251]	eta 0:28:38 lr 0.000400	time 2.0093 (2.2289)	loss 3.1554 (3.4524)	grad_norm 1.4467 (1.6438)	
[2022-01-23 01:58:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][490/1251]	eta 0:28:15 lr 0.000400	time 2.7265 (2.2275)	loss 3.0980 (3.4486)	grad_norm 1.8587 (1.6447)	
[2022-01-23 01:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][500/1251]	eta 0:27:49 lr 0.000400	time 2.2424 (2.2234)	loss 3.6957 (3.4553)	grad_norm 1.4215 (1.6471)	
[2022-01-23 01:58:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][510/1251]	eta 0:27:23 lr 0.000400	time 1.5634 (2.2176)	loss 3.1740 (3.4512)	grad_norm 2.0473 (1.6476)	
[2022-01-23 01:59:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][520/1251]	eta 0:26:59 lr 0.000400	time 1.7856 (2.2148)	loss 3.5517 (3.4519)	grad_norm 1.7546 (1.6481)	
[2022-01-23 01:59:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][530/1251]	eta 0:26:37 lr 0.000400	time 2.7539 (2.2159)	loss 2.8560 (3.4540)	grad_norm 1.6085 (1.6491)	
[2022-01-23 01:59:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][540/1251]	eta 0:26:15 lr 0.000400	time 1.8047 (2.2158)	loss 3.1199 (3.4518)	grad_norm 1.6642 (1.6523)	
[2022-01-23 02:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][550/1251]	eta 0:25:53 lr 0.000400	time 2.2059 (2.2160)	loss 3.0974 (3.4565)	grad_norm 1.4701 (1.6535)	
[2022-01-23 02:00:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][560/1251]	eta 0:25:32 lr 0.000400	time 2.6303 (2.2177)	loss 3.3432 (3.4564)	grad_norm 1.7472 (1.6543)	
[2022-01-23 02:01:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][570/1251]	eta 0:25:11 lr 0.000400	time 1.4792 (2.2201)	loss 4.5789 (3.4561)	grad_norm 2.0840 (1.6542)	
[2022-01-23 02:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][580/1251]	eta 0:24:48 lr 0.000400	time 1.8931 (2.2186)	loss 3.0758 (3.4603)	grad_norm 1.6772 (1.6536)	
[2022-01-23 02:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][590/1251]	eta 0:24:25 lr 0.000400	time 1.7582 (2.2173)	loss 3.5692 (3.4581)	grad_norm 1.9158 (1.6538)	
[2022-01-23 02:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][600/1251]	eta 0:24:03 lr 0.000400	time 2.2013 (2.2179)	loss 3.6324 (3.4569)	grad_norm 1.6798 (1.6547)	
[2022-01-23 02:02:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][610/1251]	eta 0:23:40 lr 0.000400	time 1.8588 (2.2164)	loss 3.1490 (3.4551)	grad_norm 1.6022 (1.6555)	
[2022-01-23 02:02:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][620/1251]	eta 0:23:17 lr 0.000400	time 2.1633 (2.2142)	loss 4.2093 (3.4551)	grad_norm 1.7801 (1.6550)	
[2022-01-23 02:03:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][630/1251]	eta 0:22:54 lr 0.000400	time 1.9361 (2.2140)	loss 3.4980 (3.4524)	grad_norm 1.6793 (1.6559)	
[2022-01-23 02:03:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][640/1251]	eta 0:22:32 lr 0.000399	time 1.8996 (2.2133)	loss 3.3986 (3.4536)	grad_norm 1.8139 (1.6570)	
[2022-01-23 02:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][650/1251]	eta 0:22:08 lr 0.000399	time 1.9728 (2.2112)	loss 4.0367 (3.4538)	grad_norm 1.5282 (1.6556)	
[2022-01-23 02:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][660/1251]	eta 0:21:46 lr 0.000399	time 1.8441 (2.2113)	loss 3.3338 (3.4535)	grad_norm 1.6824 (1.6550)	
[2022-01-23 02:04:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][670/1251]	eta 0:21:26 lr 0.000399	time 3.0985 (2.2147)	loss 3.2336 (3.4520)	grad_norm 1.7188 (1.6555)	
[2022-01-23 02:05:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][680/1251]	eta 0:21:06 lr 0.000399	time 1.9192 (2.2172)	loss 3.5008 (3.4552)	grad_norm 2.0147 (1.6536)	
[2022-01-23 02:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][690/1251]	eta 0:20:44 lr 0.000399	time 2.7944 (2.2187)	loss 3.5130 (3.4571)	grad_norm 1.6805 (1.6528)	
[2022-01-23 02:05:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][700/1251]	eta 0:20:21 lr 0.000399	time 1.8053 (2.2167)	loss 3.8734 (3.4566)	grad_norm 2.0249 (1.6542)	
[2022-01-23 02:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][710/1251]	eta 0:19:56 lr 0.000399	time 1.7008 (2.2124)	loss 3.5493 (3.4557)	grad_norm 1.4888 (1.6562)	
[2022-01-23 02:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][720/1251]	eta 0:19:32 lr 0.000399	time 1.6898 (2.2089)	loss 3.4217 (3.4535)	grad_norm 1.7447 (1.6551)	
[2022-01-23 02:06:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][730/1251]	eta 0:19:09 lr 0.000399	time 2.5060 (2.2060)	loss 2.5314 (3.4552)	grad_norm 1.6089 (1.6557)	
[2022-01-23 02:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][740/1251]	eta 0:18:47 lr 0.000399	time 2.5440 (2.2061)	loss 4.0238 (3.4586)	grad_norm 1.4679 (1.6540)	
[2022-01-23 02:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][750/1251]	eta 0:18:25 lr 0.000399	time 2.7754 (2.2065)	loss 2.1903 (3.4607)	grad_norm 1.6522 (1.6559)	
[2022-01-23 02:07:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][760/1251]	eta 0:18:03 lr 0.000399	time 1.9469 (2.2069)	loss 4.3682 (3.4643)	grad_norm 1.6931 (1.6560)	
[2022-01-23 02:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][770/1251]	eta 0:17:41 lr 0.000399	time 2.2942 (2.2070)	loss 2.5605 (3.4617)	grad_norm 1.7157 (1.6557)	
[2022-01-23 02:08:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][780/1251]	eta 0:17:20 lr 0.000399	time 1.9542 (2.2097)	loss 3.1513 (3.4613)	grad_norm 1.4153 (1.6559)	
[2022-01-23 02:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][790/1251]	eta 0:16:59 lr 0.000399	time 2.2237 (2.2115)	loss 4.1208 (3.4582)	grad_norm 1.6021 (1.6552)	
[2022-01-23 02:09:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][800/1251]	eta 0:16:38 lr 0.000399	time 1.8411 (2.2141)	loss 3.7136 (3.4609)	grad_norm 1.6400 (1.6556)	
[2022-01-23 02:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][810/1251]	eta 0:16:15 lr 0.000399	time 1.6894 (2.2121)	loss 4.1986 (3.4645)	grad_norm 1.7293 (1.6566)	
[2022-01-23 02:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][820/1251]	eta 0:15:53 lr 0.000399	time 1.9981 (2.2119)	loss 4.2899 (3.4687)	grad_norm 1.9920 (1.6588)	
[2022-01-23 02:10:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][830/1251]	eta 0:15:30 lr 0.000399	time 1.8713 (2.2094)	loss 3.5516 (3.4700)	grad_norm 1.6005 (1.6587)	
[2022-01-23 02:10:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][840/1251]	eta 0:15:07 lr 0.000399	time 2.1817 (2.2084)	loss 3.6297 (3.4719)	grad_norm 1.5495 (1.6576)	
[2022-01-23 02:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][850/1251]	eta 0:14:45 lr 0.000399	time 1.9873 (2.2077)	loss 3.5542 (3.4724)	grad_norm 1.6308 (1.6574)	
[2022-01-23 02:11:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][860/1251]	eta 0:14:22 lr 0.000399	time 2.2277 (2.2061)	loss 3.3767 (3.4726)	grad_norm 1.4816 (1.6575)	
[2022-01-23 02:11:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][870/1251]	eta 0:13:59 lr 0.000399	time 1.9427 (2.2040)	loss 3.9370 (3.4742)	grad_norm 1.4919 (1.6566)	
[2022-01-23 02:12:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][880/1251]	eta 0:13:37 lr 0.000399	time 1.9601 (2.2029)	loss 4.0865 (3.4714)	grad_norm 1.5556 (1.6566)	
[2022-01-23 02:12:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][890/1251]	eta 0:13:15 lr 0.000398	time 2.1870 (2.2037)	loss 4.2937 (3.4710)	grad_norm 1.7553 (1.6561)	
[2022-01-23 02:13:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][900/1251]	eta 0:12:53 lr 0.000398	time 2.4467 (2.2045)	loss 2.7704 (3.4723)	grad_norm 1.7972 (1.6564)	
[2022-01-23 02:13:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][910/1251]	eta 0:12:32 lr 0.000398	time 2.4022 (2.2069)	loss 2.9655 (3.4733)	grad_norm 1.6507 (1.6564)	
[2022-01-23 02:13:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][920/1251]	eta 0:12:10 lr 0.000398	time 1.8870 (2.2067)	loss 4.0846 (3.4732)	grad_norm 1.4440 (1.6561)	
[2022-01-23 02:14:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][930/1251]	eta 0:11:48 lr 0.000398	time 2.3975 (2.2076)	loss 3.4479 (3.4721)	grad_norm 1.6044 (1.6555)	
[2022-01-23 02:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][940/1251]	eta 0:11:26 lr 0.000398	time 1.7904 (2.2066)	loss 4.0102 (3.4723)	grad_norm 1.5786 (1.6554)	
[2022-01-23 02:14:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][950/1251]	eta 0:11:03 lr 0.000398	time 2.2141 (2.2050)	loss 3.8488 (3.4728)	grad_norm 1.5524 (1.6556)	
[2022-01-23 02:15:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][960/1251]	eta 0:10:41 lr 0.000398	time 2.1112 (2.2038)	loss 3.9889 (3.4733)	grad_norm 1.6516 (1.6566)	
[2022-01-23 02:15:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][970/1251]	eta 0:10:19 lr 0.000398	time 1.9816 (2.2030)	loss 2.4425 (3.4732)	grad_norm 1.6718 (1.6567)	
[2022-01-23 02:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][980/1251]	eta 0:09:56 lr 0.000398	time 1.9823 (2.2017)	loss 3.5031 (3.4743)	grad_norm 1.7528 (1.6566)	
[2022-01-23 02:16:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][990/1251]	eta 0:09:34 lr 0.000398	time 2.5667 (2.2015)	loss 2.7256 (3.4709)	grad_norm 1.9588 (1.6573)	
[2022-01-23 02:16:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1000/1251]	eta 0:09:12 lr 0.000398	time 2.2808 (2.2018)	loss 3.8164 (3.4694)	grad_norm 1.5332 (1.6572)	
[2022-01-23 02:17:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1010/1251]	eta 0:08:51 lr 0.000398	time 2.8327 (2.2035)	loss 3.5079 (3.4696)	grad_norm 1.3717 (1.6562)	
[2022-01-23 02:17:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1020/1251]	eta 0:08:28 lr 0.000398	time 1.9084 (2.2034)	loss 3.7192 (3.4702)	grad_norm 1.6563 (1.6563)	
[2022-01-23 02:17:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1030/1251]	eta 0:08:06 lr 0.000398	time 1.9726 (2.2035)	loss 3.6018 (3.4681)	grad_norm 1.5736 (1.6569)	
[2022-01-23 02:18:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1040/1251]	eta 0:07:44 lr 0.000398	time 1.9439 (2.2035)	loss 4.1014 (3.4683)	grad_norm 1.7864 (1.6572)	
[2022-01-23 02:18:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1050/1251]	eta 0:07:22 lr 0.000398	time 2.3755 (2.2036)	loss 2.4357 (3.4662)	grad_norm 1.5783 (1.6568)	
[2022-01-23 02:18:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1060/1251]	eta 0:07:00 lr 0.000398	time 2.2108 (2.2032)	loss 3.7950 (3.4647)	grad_norm 1.6088 (1.6569)	
[2022-01-23 02:19:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1070/1251]	eta 0:06:38 lr 0.000398	time 1.6639 (2.2030)	loss 2.5471 (3.4627)	grad_norm 1.5884 (1.6575)	
[2022-01-23 02:19:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1080/1251]	eta 0:06:16 lr 0.000398	time 2.5330 (2.2045)	loss 2.6838 (3.4613)	grad_norm 1.5079 (1.6576)	
[2022-01-23 02:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1090/1251]	eta 0:05:54 lr 0.000398	time 1.7967 (2.2042)	loss 3.9848 (3.4605)	grad_norm 1.6332 (1.6579)	
[2022-01-23 02:20:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1100/1251]	eta 0:05:32 lr 0.000398	time 1.7300 (2.2019)	loss 3.9160 (3.4605)	grad_norm 1.6313 (1.6579)	
[2022-01-23 02:20:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1110/1251]	eta 0:05:10 lr 0.000398	time 1.7044 (2.1998)	loss 3.1228 (3.4605)	grad_norm 1.7869 (1.6576)	
[2022-01-23 02:21:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1120/1251]	eta 0:04:48 lr 0.000398	time 2.2206 (2.1999)	loss 3.3561 (3.4615)	grad_norm 1.6456 (1.6572)	
[2022-01-23 02:21:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1130/1251]	eta 0:04:26 lr 0.000398	time 2.7464 (2.2000)	loss 3.6420 (3.4615)	grad_norm 1.5552 (1.6567)	
[2022-01-23 02:21:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1140/1251]	eta 0:04:04 lr 0.000397	time 1.8628 (2.2001)	loss 3.5184 (3.4599)	grad_norm 1.5372 (1.6565)	
[2022-01-23 02:22:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1150/1251]	eta 0:03:42 lr 0.000397	time 1.8986 (2.2006)	loss 3.8624 (3.4595)	grad_norm 1.6640 (1.6564)	
[2022-01-23 02:22:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1160/1251]	eta 0:03:20 lr 0.000397	time 2.4813 (2.2021)	loss 3.4310 (3.4606)	grad_norm 1.6223 (1.6562)	
[2022-01-23 02:22:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1170/1251]	eta 0:02:58 lr 0.000397	time 2.1958 (2.2032)	loss 3.7316 (3.4613)	grad_norm 1.6791 (1.6569)	
[2022-01-23 02:23:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1180/1251]	eta 0:02:36 lr 0.000397	time 2.3924 (2.2039)	loss 3.2980 (3.4618)	grad_norm 1.4484 (1.6564)	
[2022-01-23 02:23:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1190/1251]	eta 0:02:14 lr 0.000397	time 1.6194 (2.2035)	loss 3.8921 (3.4620)	grad_norm 1.6484 (1.6564)	
[2022-01-23 02:23:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1200/1251]	eta 0:01:52 lr 0.000397	time 2.2130 (2.2013)	loss 3.8672 (3.4634)	grad_norm 1.5919 (1.6561)	
[2022-01-23 02:24:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1210/1251]	eta 0:01:30 lr 0.000397	time 1.6402 (2.1993)	loss 2.9517 (3.4625)	grad_norm 1.6070 (1.6561)	
[2022-01-23 02:24:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1220/1251]	eta 0:01:08 lr 0.000397	time 2.4353 (2.1989)	loss 3.4249 (3.4616)	grad_norm 1.7355 (1.6555)	
[2022-01-23 02:25:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1230/1251]	eta 0:00:46 lr 0.000397	time 2.3366 (2.1992)	loss 2.5489 (3.4608)	grad_norm 1.5942 (1.6552)	
[2022-01-23 02:25:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1240/1251]	eta 0:00:24 lr 0.000397	time 2.3877 (2.1990)	loss 3.9452 (3.4614)	grad_norm 1.5677 (1.6549)	
[2022-01-23 02:25:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [170/300][1250/1251]	eta 0:00:02 lr 0.000397	time 1.1535 (2.1938)	loss 3.3544 (3.4613)	grad_norm 1.5343 (1.6545)	
[2022-01-23 02:25:40 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 170 training takes 0:45:44
[2022-01-23 02:25:40 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_170 saving......
[2022-01-23 02:25:51 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_170 saved !!!
[2022-01-23 02:26:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 13.797 (13.797)	Loss 1.0238 (1.0238)	Acc@1 76.660 (76.660)	Acc@5 92.285 (92.285)	
[2022-01-23 02:26:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.702 (2.693)	Loss 0.9360 (0.9709)	Acc@1 77.734 (76.971)	Acc@5 93.262 (93.288)	
[2022-01-23 02:26:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.017 (2.178)	Loss 1.0112 (0.9623)	Acc@1 76.465 (77.214)	Acc@5 93.848 (93.569)	
[2022-01-23 02:26:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.327 (2.133)	Loss 0.9291 (0.9597)	Acc@1 76.758 (77.205)	Acc@5 94.336 (93.621)	
[2022-01-23 02:27:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 0.809 (1.981)	Loss 0.9691 (0.9669)	Acc@1 75.781 (76.925)	Acc@5 93.262 (93.593)	
[2022-01-23 02:27:21 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.842 Acc@5 93.642
[2022-01-23 02:27:21 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.8%
[2022-01-23 02:27:21 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.84%
[2022-01-23 02:27:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][0/1251]	eta 7:38:10 lr 0.000397	time 21.9750 (21.9750)	loss 4.4041 (4.4041)	grad_norm 2.0500 (2.0500)	
[2022-01-23 02:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][10/1251]	eta 1:24:20 lr 0.000397	time 2.1080 (4.0774)	loss 2.2593 (3.2920)	grad_norm 1.5752 (1.6375)	
[2022-01-23 02:28:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][20/1251]	eta 1:03:10 lr 0.000397	time 2.1989 (3.0795)	loss 3.7557 (3.3668)	grad_norm 1.6852 (1.6219)	
[2022-01-23 02:28:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][30/1251]	eta 0:56:28 lr 0.000397	time 1.5101 (2.7753)	loss 3.5393 (3.3819)	grad_norm 1.7638 (1.6074)	
[2022-01-23 02:29:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][40/1251]	eta 0:53:24 lr 0.000397	time 3.2581 (2.6466)	loss 3.2047 (3.3073)	grad_norm 1.3662 (1.6420)	
[2022-01-23 02:29:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][50/1251]	eta 0:52:22 lr 0.000397	time 2.8570 (2.6164)	loss 2.5644 (3.3587)	grad_norm 1.7695 (1.6586)	
[2022-01-23 02:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][60/1251]	eta 0:50:46 lr 0.000397	time 2.4108 (2.5579)	loss 3.1533 (3.3418)	grad_norm 1.5959 (1.6463)	
[2022-01-23 02:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][70/1251]	eta 0:49:07 lr 0.000397	time 1.7754 (2.4962)	loss 3.0414 (3.3344)	grad_norm 1.6654 (1.6543)	
[2022-01-23 02:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][80/1251]	eta 0:47:37 lr 0.000397	time 2.7811 (2.4403)	loss 3.2972 (3.3394)	grad_norm 1.8627 (1.6505)	
[2022-01-23 02:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][90/1251]	eta 0:46:27 lr 0.000397	time 2.3602 (2.4011)	loss 3.8553 (3.3565)	grad_norm 1.8440 (1.6495)	
[2022-01-23 02:31:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][100/1251]	eta 0:45:34 lr 0.000397	time 2.2527 (2.3754)	loss 2.5557 (3.3782)	grad_norm 1.8934 (1.6519)	
[2022-01-23 02:31:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][110/1251]	eta 0:44:45 lr 0.000397	time 1.6728 (2.3539)	loss 4.3756 (3.3840)	grad_norm 1.7906 (1.6540)	
[2022-01-23 02:32:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][120/1251]	eta 0:44:27 lr 0.000397	time 2.5974 (2.3585)	loss 3.7932 (3.4008)	grad_norm 1.8346 (1.6597)	
[2022-01-23 02:32:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][130/1251]	eta 0:44:10 lr 0.000396	time 2.7222 (2.3647)	loss 3.8340 (3.3987)	grad_norm 1.7012 (1.6587)	
[2022-01-23 02:32:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][140/1251]	eta 0:43:44 lr 0.000396	time 2.8851 (2.3623)	loss 3.5355 (3.4192)	grad_norm 1.6517 (1.6582)	
[2022-01-23 02:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][150/1251]	eta 0:42:59 lr 0.000396	time 1.6404 (2.3432)	loss 3.4931 (3.4262)	grad_norm 1.7803 (1.6603)	
[2022-01-23 02:33:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][160/1251]	eta 0:42:05 lr 0.000396	time 1.8278 (2.3151)	loss 2.2494 (3.4240)	grad_norm 1.3693 (1.6570)	
[2022-01-23 02:33:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][170/1251]	eta 0:41:29 lr 0.000396	time 2.1293 (2.3030)	loss 3.7580 (3.4115)	grad_norm 1.5120 (1.6514)	
[2022-01-23 02:34:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][180/1251]	eta 0:40:52 lr 0.000396	time 2.4638 (2.2899)	loss 2.9029 (3.4070)	grad_norm 1.6895 (1.6556)	
[2022-01-23 02:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][190/1251]	eta 0:40:33 lr 0.000396	time 2.8444 (2.2931)	loss 3.5945 (3.4162)	grad_norm 1.5710 (1.6505)	
[2022-01-23 02:35:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][200/1251]	eta 0:40:05 lr 0.000396	time 2.1869 (2.2885)	loss 3.2359 (3.4166)	grad_norm 1.5149 (1.6478)	
[2022-01-23 02:35:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][210/1251]	eta 0:39:43 lr 0.000396	time 2.2314 (2.2896)	loss 3.7842 (3.4105)	grad_norm 2.0229 (1.6554)	
[2022-01-23 02:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][220/1251]	eta 0:39:26 lr 0.000396	time 2.9116 (2.2958)	loss 3.3275 (3.4231)	grad_norm 1.5330 (1.6568)	
[2022-01-23 02:36:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][230/1251]	eta 0:38:57 lr 0.000396	time 2.1754 (2.2896)	loss 3.3955 (3.4180)	grad_norm 1.8356 (1.6544)	
[2022-01-23 02:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][240/1251]	eta 0:38:22 lr 0.000396	time 1.8814 (2.2777)	loss 3.9978 (3.4219)	grad_norm 1.7212 (1.6548)	
[2022-01-23 02:36:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][250/1251]	eta 0:37:50 lr 0.000396	time 2.2614 (2.2678)	loss 3.9692 (3.4250)	grad_norm 1.4458 (1.6545)	
[2022-01-23 02:37:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][260/1251]	eta 0:37:19 lr 0.000396	time 2.4801 (2.2598)	loss 3.6692 (3.4268)	grad_norm 1.5853 (1.6540)	
[2022-01-23 02:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][270/1251]	eta 0:36:50 lr 0.000396	time 1.9028 (2.2533)	loss 3.7397 (3.4290)	grad_norm 1.6759 (1.6567)	
[2022-01-23 02:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][280/1251]	eta 0:36:31 lr 0.000396	time 2.5360 (2.2571)	loss 3.4815 (3.4211)	grad_norm 1.4071 (1.6555)	
[2022-01-23 02:38:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][290/1251]	eta 0:36:06 lr 0.000396	time 2.1760 (2.2546)	loss 3.6295 (3.4140)	grad_norm 1.8214 (1.6605)	
[2022-01-23 02:38:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][300/1251]	eta 0:35:43 lr 0.000396	time 2.7414 (2.2540)	loss 3.7523 (3.4055)	grad_norm 1.4891 (1.6577)	
[2022-01-23 02:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][310/1251]	eta 0:35:19 lr 0.000396	time 2.2148 (2.2525)	loss 3.8007 (3.4083)	grad_norm 1.6059 (1.6538)	
[2022-01-23 02:39:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][320/1251]	eta 0:34:52 lr 0.000396	time 2.4995 (2.2481)	loss 3.6102 (3.4050)	grad_norm 1.6494 (1.6541)	
[2022-01-23 02:39:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][330/1251]	eta 0:34:28 lr 0.000396	time 3.0064 (2.2458)	loss 4.0583 (3.4160)	grad_norm 1.5938 (1.6547)	
[2022-01-23 02:40:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][340/1251]	eta 0:34:00 lr 0.000396	time 1.7792 (2.2394)	loss 4.0186 (3.4121)	grad_norm 1.6369 (1.6527)	
[2022-01-23 02:40:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][350/1251]	eta 0:33:36 lr 0.000396	time 2.3685 (2.2376)	loss 3.5423 (3.4147)	grad_norm 1.5636 (1.6502)	
[2022-01-23 02:40:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][360/1251]	eta 0:33:10 lr 0.000396	time 2.2726 (2.2338)	loss 3.8857 (3.4148)	grad_norm 1.5515 (1.6491)	
[2022-01-23 02:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][370/1251]	eta 0:32:47 lr 0.000396	time 2.5154 (2.2336)	loss 3.8058 (3.4152)	grad_norm 1.7951 (1.6514)	
[2022-01-23 02:41:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][380/1251]	eta 0:32:25 lr 0.000395	time 2.4369 (2.2339)	loss 4.0297 (3.4215)	grad_norm 1.6308 (1.6536)	
[2022-01-23 02:41:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][390/1251]	eta 0:32:02 lr 0.000395	time 1.8615 (2.2329)	loss 3.2494 (3.4250)	grad_norm 1.7891 (1.6548)	
[2022-01-23 02:42:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][400/1251]	eta 0:31:38 lr 0.000395	time 2.7159 (2.2314)	loss 3.8403 (3.4283)	grad_norm 1.6829 (1.6605)	
[2022-01-23 02:42:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][410/1251]	eta 0:31:20 lr 0.000395	time 3.7334 (2.2358)	loss 3.9936 (3.4263)	grad_norm 1.9468 (1.6603)	
[2022-01-23 02:43:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][420/1251]	eta 0:31:01 lr 0.000395	time 2.4979 (2.2396)	loss 3.2560 (3.4283)	grad_norm 1.4592 (1.6583)	
[2022-01-23 02:43:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][430/1251]	eta 0:30:37 lr 0.000395	time 1.8181 (2.2381)	loss 3.5599 (3.4232)	grad_norm 1.4659 (1.6568)	
[2022-01-23 02:43:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][440/1251]	eta 0:30:11 lr 0.000395	time 1.7987 (2.2331)	loss 3.7936 (3.4179)	grad_norm 2.0110 (1.6557)	
[2022-01-23 02:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][450/1251]	eta 0:29:45 lr 0.000395	time 2.9634 (2.2291)	loss 3.6070 (3.4207)	grad_norm 1.6627 (1.6575)	
[2022-01-23 02:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][460/1251]	eta 0:29:19 lr 0.000395	time 1.9012 (2.2250)	loss 4.1035 (3.4219)	grad_norm 1.7820 (1.6582)	
[2022-01-23 02:44:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][470/1251]	eta 0:28:55 lr 0.000395	time 1.5400 (2.2216)	loss 3.0647 (3.4198)	grad_norm 1.6559 (1.6593)	
[2022-01-23 02:45:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][480/1251]	eta 0:28:33 lr 0.000395	time 2.2739 (2.2221)	loss 3.7586 (3.4256)	grad_norm 1.7859 (1.6589)	
[2022-01-23 02:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][490/1251]	eta 0:28:11 lr 0.000395	time 2.7813 (2.2224)	loss 3.5513 (3.4314)	grad_norm 1.5391 (1.6589)	
[2022-01-23 02:45:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][500/1251]	eta 0:27:48 lr 0.000395	time 2.5854 (2.2222)	loss 3.6865 (3.4269)	grad_norm 1.8827 (1.6596)	
[2022-01-23 02:46:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][510/1251]	eta 0:27:27 lr 0.000395	time 2.4809 (2.2235)	loss 3.4782 (3.4272)	grad_norm 1.6872 (1.6586)	
[2022-01-23 02:46:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][520/1251]	eta 0:27:05 lr 0.000395	time 2.6837 (2.2241)	loss 3.4806 (3.4328)	grad_norm 1.4850 (1.6565)	
[2022-01-23 02:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][530/1251]	eta 0:26:42 lr 0.000395	time 2.4858 (2.2223)	loss 3.0609 (3.4393)	grad_norm 1.8250 (1.6569)	
[2022-01-23 02:47:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][540/1251]	eta 0:26:18 lr 0.000395	time 1.9134 (2.2204)	loss 2.7646 (3.4352)	grad_norm 1.7690 (1.6602)	
[2022-01-23 02:47:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][550/1251]	eta 0:25:55 lr 0.000395	time 2.0909 (2.2184)	loss 3.1956 (3.4385)	grad_norm 1.7744 (1.6603)	
[2022-01-23 02:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][560/1251]	eta 0:25:31 lr 0.000395	time 2.5679 (2.2158)	loss 3.7522 (3.4387)	grad_norm 1.5771 (1.6603)	
[2022-01-23 02:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][570/1251]	eta 0:25:08 lr 0.000395	time 3.3897 (2.2153)	loss 3.9768 (3.4380)	grad_norm 2.1279 (1.6606)	
[2022-01-23 02:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][580/1251]	eta 0:24:46 lr 0.000395	time 2.5618 (2.2146)	loss 2.5409 (3.4384)	grad_norm 1.5016 (1.6587)	
[2022-01-23 02:49:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][590/1251]	eta 0:24:22 lr 0.000395	time 2.2559 (2.2124)	loss 3.5002 (3.4434)	grad_norm 1.7342 (1.6582)	
[2022-01-23 02:49:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][600/1251]	eta 0:23:59 lr 0.000395	time 2.4423 (2.2109)	loss 2.2989 (3.4428)	grad_norm 1.5307 (1.6586)	
[2022-01-23 02:49:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][610/1251]	eta 0:23:38 lr 0.000395	time 3.1801 (2.2125)	loss 3.6492 (3.4405)	grad_norm 1.6541 (1.6598)	
[2022-01-23 02:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][620/1251]	eta 0:23:19 lr 0.000395	time 2.9491 (2.2176)	loss 3.4750 (3.4403)	grad_norm 1.7951 (1.6606)	
[2022-01-23 02:50:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][630/1251]	eta 0:22:58 lr 0.000394	time 2.4853 (2.2197)	loss 3.6319 (3.4421)	grad_norm 1.5620 (1.6600)	
[2022-01-23 02:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][640/1251]	eta 0:22:36 lr 0.000394	time 2.3163 (2.2202)	loss 3.2051 (3.4392)	grad_norm 1.6875 (1.6584)	
[2022-01-23 02:51:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][650/1251]	eta 0:22:12 lr 0.000394	time 1.9043 (2.2176)	loss 3.8930 (3.4417)	grad_norm 1.4742 (1.6567)	
[2022-01-23 02:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][660/1251]	eta 0:21:48 lr 0.000394	time 1.7823 (2.2140)	loss 3.6008 (3.4440)	grad_norm 1.8136 (1.6579)	
[2022-01-23 02:52:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][670/1251]	eta 0:21:24 lr 0.000394	time 1.9777 (2.2101)	loss 3.9631 (3.4474)	grad_norm 1.7629 (1.6598)	
[2022-01-23 02:52:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][680/1251]	eta 0:21:00 lr 0.000394	time 1.9001 (2.2076)	loss 3.7038 (3.4520)	grad_norm 1.6556 (1.6609)	
[2022-01-23 02:52:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][690/1251]	eta 0:20:38 lr 0.000394	time 2.6523 (2.2076)	loss 3.7125 (3.4533)	grad_norm 1.7572 (1.6598)	
[2022-01-23 02:53:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][700/1251]	eta 0:20:16 lr 0.000394	time 2.3898 (2.2084)	loss 3.7770 (3.4530)	grad_norm 1.7272 (1.6597)	
[2022-01-23 02:53:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][710/1251]	eta 0:19:56 lr 0.000394	time 2.1136 (2.2124)	loss 3.0500 (3.4527)	grad_norm 1.7330 (1.6600)	
[2022-01-23 02:53:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][720/1251]	eta 0:19:34 lr 0.000394	time 1.9130 (2.2121)	loss 4.3181 (3.4543)	grad_norm 1.7892 (1.6601)	
[2022-01-23 02:54:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][730/1251]	eta 0:19:11 lr 0.000394	time 2.0855 (2.2105)	loss 3.0972 (3.4520)	grad_norm 1.8061 (1.6597)	
[2022-01-23 02:54:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][740/1251]	eta 0:18:50 lr 0.000394	time 1.8870 (2.2129)	loss 3.5766 (3.4530)	grad_norm 1.5840 (1.6618)	
[2022-01-23 02:55:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][750/1251]	eta 0:18:29 lr 0.000394	time 1.8242 (2.2149)	loss 3.1381 (3.4545)	grad_norm 1.7850 (1.6622)	
[2022-01-23 02:55:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][760/1251]	eta 0:18:08 lr 0.000394	time 2.1859 (2.2167)	loss 3.1231 (3.4530)	grad_norm 2.0432 (1.6623)	
[2022-01-23 02:55:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][770/1251]	eta 0:17:45 lr 0.000394	time 2.2652 (2.2161)	loss 3.9444 (3.4541)	grad_norm 1.4544 (1.6621)	
[2022-01-23 02:56:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][780/1251]	eta 0:17:22 lr 0.000394	time 1.8859 (2.2137)	loss 3.3309 (3.4527)	grad_norm 1.4413 (1.6645)	
[2022-01-23 02:56:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][790/1251]	eta 0:16:59 lr 0.000394	time 1.9997 (2.2113)	loss 4.2523 (3.4523)	grad_norm 1.5860 (1.6643)	
[2022-01-23 02:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][800/1251]	eta 0:16:36 lr 0.000394	time 2.6369 (2.2102)	loss 3.8378 (3.4538)	grad_norm 1.9107 (1.6638)	
[2022-01-23 02:57:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][810/1251]	eta 0:16:14 lr 0.000394	time 1.9629 (2.2098)	loss 2.5253 (3.4513)	grad_norm 1.4322 (1.6626)	
[2022-01-23 02:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][820/1251]	eta 0:15:53 lr 0.000394	time 2.4653 (2.2113)	loss 3.5653 (3.4532)	grad_norm 1.5210 (1.6626)	
[2022-01-23 02:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][830/1251]	eta 0:15:31 lr 0.000394	time 2.4569 (2.2123)	loss 3.6632 (3.4546)	grad_norm 1.6307 (1.6623)	
[2022-01-23 02:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][840/1251]	eta 0:15:09 lr 0.000394	time 2.5699 (2.2129)	loss 3.6376 (3.4553)	grad_norm 1.4020 (1.6634)	
[2022-01-23 02:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][850/1251]	eta 0:14:46 lr 0.000394	time 1.5567 (2.2106)	loss 2.7477 (3.4571)	grad_norm 1.8905 (1.6638)	
[2022-01-23 02:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][860/1251]	eta 0:14:24 lr 0.000394	time 2.8023 (2.2106)	loss 2.3927 (3.4546)	grad_norm 1.6182 (1.6641)	
[2022-01-23 02:59:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][870/1251]	eta 0:14:01 lr 0.000394	time 2.2126 (2.2096)	loss 3.5337 (3.4510)	grad_norm 1.7088 (1.6643)	
[2022-01-23 02:59:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][880/1251]	eta 0:13:39 lr 0.000393	time 1.6828 (2.2085)	loss 2.9948 (3.4516)	grad_norm 1.6382 (1.6640)	
[2022-01-23 03:00:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][890/1251]	eta 0:13:17 lr 0.000393	time 1.9781 (2.2090)	loss 3.4358 (3.4537)	grad_norm 1.5803 (1.6639)	
[2022-01-23 03:00:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][900/1251]	eta 0:12:55 lr 0.000393	time 3.4241 (2.2095)	loss 3.8563 (3.4559)	grad_norm 1.4709 (1.6636)	
[2022-01-23 03:00:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][910/1251]	eta 0:12:33 lr 0.000393	time 2.4267 (2.2083)	loss 2.5228 (3.4522)	grad_norm 1.8008 (1.6636)	
[2022-01-23 03:01:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][920/1251]	eta 0:12:10 lr 0.000393	time 1.5636 (2.2070)	loss 3.4839 (3.4528)	grad_norm 1.5350 (1.6624)	
[2022-01-23 03:01:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][930/1251]	eta 0:11:47 lr 0.000393	time 1.8989 (2.2056)	loss 2.7982 (3.4489)	grad_norm 1.7143 (1.6630)	
[2022-01-23 03:01:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][940/1251]	eta 0:11:26 lr 0.000393	time 3.7354 (2.2068)	loss 3.9708 (3.4524)	grad_norm 2.0604 (1.6645)	
[2022-01-23 03:02:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][950/1251]	eta 0:11:03 lr 0.000393	time 1.5645 (2.2049)	loss 3.9349 (3.4546)	grad_norm 1.7091 (1.6654)	
[2022-01-23 03:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][960/1251]	eta 0:10:41 lr 0.000393	time 1.8651 (2.2043)	loss 3.8724 (3.4539)	grad_norm 1.7469 (1.6661)	
[2022-01-23 03:03:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][970/1251]	eta 0:10:20 lr 0.000393	time 1.9721 (2.2075)	loss 3.5138 (3.4526)	grad_norm 1.8436 (1.6654)	
[2022-01-23 03:03:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][980/1251]	eta 0:09:58 lr 0.000393	time 3.4160 (2.2092)	loss 3.3644 (3.4519)	grad_norm 1.8133 (1.6655)	
[2022-01-23 03:03:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][990/1251]	eta 0:09:36 lr 0.000393	time 2.8006 (2.2097)	loss 3.2947 (3.4527)	grad_norm 1.8155 (1.6653)	
[2022-01-23 03:04:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1000/1251]	eta 0:09:14 lr 0.000393	time 1.8725 (2.2097)	loss 3.1200 (3.4496)	grad_norm 1.6506 (1.6649)	
[2022-01-23 03:04:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1010/1251]	eta 0:08:52 lr 0.000393	time 1.9636 (2.2087)	loss 3.5090 (3.4506)	grad_norm 1.5641 (1.6651)	
[2022-01-23 03:04:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1020/1251]	eta 0:08:29 lr 0.000393	time 1.9814 (2.2062)	loss 4.1351 (3.4522)	grad_norm 1.9395 (1.6652)	
[2022-01-23 03:05:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1030/1251]	eta 0:08:07 lr 0.000393	time 2.5775 (2.2049)	loss 2.1473 (3.4485)	grad_norm 1.6132 (1.6641)	
[2022-01-23 03:05:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1040/1251]	eta 0:07:45 lr 0.000393	time 2.2832 (2.2039)	loss 4.0471 (3.4506)	grad_norm 1.7361 (1.6639)	
[2022-01-23 03:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1050/1251]	eta 0:07:22 lr 0.000393	time 1.9360 (2.2027)	loss 3.5871 (3.4505)	grad_norm 1.8211 (1.6641)	
[2022-01-23 03:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1060/1251]	eta 0:07:01 lr 0.000393	time 2.4175 (2.2042)	loss 3.8303 (3.4518)	grad_norm 1.4424 (1.6638)	
[2022-01-23 03:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1070/1251]	eta 0:06:38 lr 0.000393	time 2.0290 (2.2042)	loss 2.3731 (3.4486)	grad_norm 1.5395 (1.6642)	
[2022-01-23 03:07:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1080/1251]	eta 0:06:17 lr 0.000393	time 2.5074 (2.2059)	loss 3.7454 (3.4482)	grad_norm 1.5421 (1.6637)	
[2022-01-23 03:07:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1090/1251]	eta 0:05:55 lr 0.000393	time 1.9414 (2.2055)	loss 3.5246 (3.4507)	grad_norm 1.5022 (1.6629)	
[2022-01-23 03:07:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1100/1251]	eta 0:05:32 lr 0.000393	time 1.9089 (2.2051)	loss 2.9483 (3.4495)	grad_norm 1.7061 (1.6629)	
[2022-01-23 03:08:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1110/1251]	eta 0:05:10 lr 0.000393	time 1.8919 (2.2034)	loss 4.3796 (3.4509)	grad_norm 1.7300 (1.6624)	
[2022-01-23 03:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1120/1251]	eta 0:04:48 lr 0.000392	time 2.7458 (2.2026)	loss 3.6142 (3.4513)	grad_norm 1.4992 (1.6629)	
[2022-01-23 03:08:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1130/1251]	eta 0:04:26 lr 0.000392	time 2.1426 (2.2018)	loss 2.9805 (3.4504)	grad_norm 1.9142 (1.6639)	
[2022-01-23 03:09:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1140/1251]	eta 0:04:04 lr 0.000392	time 2.2108 (2.2018)	loss 3.9645 (3.4516)	grad_norm 1.5368 (1.6646)	
[2022-01-23 03:09:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1150/1251]	eta 0:03:42 lr 0.000392	time 2.5308 (2.2015)	loss 4.0837 (3.4552)	grad_norm 1.6111 (1.6644)	
[2022-01-23 03:09:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1160/1251]	eta 0:03:20 lr 0.000392	time 2.2291 (2.2022)	loss 3.8389 (3.4570)	grad_norm 1.5601 (1.6642)	
[2022-01-23 03:10:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1170/1251]	eta 0:02:58 lr 0.000392	time 1.7105 (2.2025)	loss 3.7889 (3.4554)	grad_norm 1.8409 (1.6641)	
[2022-01-23 03:10:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1180/1251]	eta 0:02:36 lr 0.000392	time 1.9636 (2.2033)	loss 2.4824 (3.4535)	grad_norm 1.9411 (1.6657)	
[2022-01-23 03:11:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1190/1251]	eta 0:02:14 lr 0.000392	time 3.1704 (2.2038)	loss 3.9380 (3.4536)	grad_norm 1.7988 (1.6659)	
[2022-01-23 03:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1200/1251]	eta 0:01:52 lr 0.000392	time 1.9933 (2.2026)	loss 4.3369 (3.4540)	grad_norm 1.5136 (1.6662)	
[2022-01-23 03:11:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1210/1251]	eta 0:01:30 lr 0.000392	time 2.2104 (2.2016)	loss 3.1333 (3.4539)	grad_norm 1.5587 (1.6659)	
[2022-01-23 03:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1220/1251]	eta 0:01:08 lr 0.000392	time 2.2383 (2.2005)	loss 2.2388 (3.4548)	grad_norm 1.4851 (1.6655)	
[2022-01-23 03:12:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1230/1251]	eta 0:00:46 lr 0.000392	time 1.6086 (2.1996)	loss 2.8972 (3.4555)	grad_norm 1.4422 (1.6661)	
[2022-01-23 03:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1240/1251]	eta 0:00:24 lr 0.000392	time 1.6510 (2.1981)	loss 3.9535 (3.4559)	grad_norm 1.9332 (1.6661)	
[2022-01-23 03:13:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [171/300][1250/1251]	eta 0:00:02 lr 0.000392	time 1.1834 (2.1934)	loss 3.6602 (3.4554)	grad_norm 1.7493 (1.6666)	
[2022-01-23 03:13:05 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 171 training takes 0:45:44
[2022-01-23 03:13:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.524 (18.524)	Loss 0.9536 (0.9536)	Acc@1 76.465 (76.465)	Acc@5 94.434 (94.434)	
[2022-01-23 03:13:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.589 (3.323)	Loss 0.9519 (0.9634)	Acc@1 76.465 (76.456)	Acc@5 94.043 (93.928)	
[2022-01-23 03:13:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.614 (2.592)	Loss 1.0109 (0.9631)	Acc@1 76.562 (76.683)	Acc@5 93.066 (93.880)	
[2022-01-23 03:14:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.306 (2.308)	Loss 0.9541 (0.9627)	Acc@1 77.051 (76.896)	Acc@5 94.336 (93.832)	
[2022-01-23 03:14:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.882 (2.142)	Loss 0.9674 (0.9666)	Acc@1 76.953 (76.832)	Acc@5 93.848 (93.748)	
[2022-01-23 03:14:40 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.876 Acc@5 93.720
[2022-01-23 03:14:40 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.9%
[2022-01-23 03:14:40 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 76.88%
[2022-01-23 03:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][0/1251]	eta 7:34:59 lr 0.000392	time 21.8221 (21.8221)	loss 2.5257 (2.5257)	grad_norm 1.7780 (1.7780)	
[2022-01-23 03:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][10/1251]	eta 1:25:11 lr 0.000392	time 2.9521 (4.1189)	loss 3.5892 (3.6593)	grad_norm 1.4641 (1.6731)	
[2022-01-23 03:15:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][20/1251]	eta 1:04:50 lr 0.000392	time 2.1469 (3.1600)	loss 3.8870 (3.5605)	grad_norm 1.8740 (1.6852)	
[2022-01-23 03:16:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][30/1251]	eta 0:58:14 lr 0.000392	time 1.8668 (2.8624)	loss 2.2058 (3.4238)	grad_norm 1.5121 (1.6810)	
[2022-01-23 03:16:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][40/1251]	eta 0:54:53 lr 0.000392	time 2.8752 (2.7198)	loss 3.2859 (3.3967)	grad_norm 1.5770 (1.6854)	
[2022-01-23 03:16:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][50/1251]	eta 0:52:39 lr 0.000392	time 2.2032 (2.6310)	loss 2.2829 (3.3977)	grad_norm 1.6636 (1.6766)	
[2022-01-23 03:17:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][60/1251]	eta 0:50:31 lr 0.000392	time 2.2421 (2.5450)	loss 4.1084 (3.3873)	grad_norm 1.7508 (1.6642)	
[2022-01-23 03:17:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][70/1251]	eta 0:48:50 lr 0.000392	time 1.8421 (2.4810)	loss 3.8655 (3.4178)	grad_norm 1.6598 (1.6649)	
[2022-01-23 03:17:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][80/1251]	eta 0:47:57 lr 0.000392	time 3.3955 (2.4572)	loss 3.4797 (3.4060)	grad_norm 1.8779 (1.6703)	
[2022-01-23 03:18:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][90/1251]	eta 0:47:14 lr 0.000392	time 3.2078 (2.4416)	loss 2.9334 (3.3968)	grad_norm 2.0162 (1.6889)	
[2022-01-23 03:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][100/1251]	eta 0:46:31 lr 0.000392	time 2.9173 (2.4256)	loss 3.5273 (3.3773)	grad_norm 1.5014 (1.7037)	
[2022-01-23 03:19:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][110/1251]	eta 0:45:37 lr 0.000392	time 1.9254 (2.3992)	loss 2.5213 (3.3752)	grad_norm 1.6754 (1.7068)	
[2022-01-23 03:19:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][120/1251]	eta 0:44:47 lr 0.000391	time 2.7339 (2.3763)	loss 3.7741 (3.3898)	grad_norm 1.8195 (1.7030)	
[2022-01-23 03:19:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][130/1251]	eta 0:44:05 lr 0.000391	time 1.9603 (2.3598)	loss 3.0128 (3.3985)	grad_norm 2.4247 (1.7037)	
[2022-01-23 03:20:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][140/1251]	eta 0:43:42 lr 0.000391	time 3.7149 (2.3601)	loss 4.2267 (3.4006)	grad_norm 1.7221 (1.6989)	
[2022-01-23 03:20:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][150/1251]	eta 0:43:06 lr 0.000391	time 2.0065 (2.3495)	loss 3.2855 (3.3843)	grad_norm 1.4657 (1.6943)	
[2022-01-23 03:20:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][160/1251]	eta 0:42:27 lr 0.000391	time 1.8722 (2.3349)	loss 2.8224 (3.3875)	grad_norm 1.5729 (1.6909)	
[2022-01-23 03:21:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][170/1251]	eta 0:41:53 lr 0.000391	time 2.1205 (2.3249)	loss 3.9631 (3.3919)	grad_norm 1.5553 (1.6875)	
[2022-01-23 03:21:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][180/1251]	eta 0:41:18 lr 0.000391	time 2.8421 (2.3144)	loss 2.9454 (3.3804)	grad_norm 1.6636 (1.6814)	
[2022-01-23 03:21:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][190/1251]	eta 0:40:39 lr 0.000391	time 1.5851 (2.2994)	loss 3.0637 (3.3771)	grad_norm 1.6276 (1.6783)	
[2022-01-23 03:22:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][200/1251]	eta 0:40:07 lr 0.000391	time 1.8567 (2.2907)	loss 3.1040 (3.3716)	grad_norm 1.7513 (1.6741)	
[2022-01-23 03:22:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][210/1251]	eta 0:39:35 lr 0.000391	time 2.1039 (2.2817)	loss 2.5760 (3.3761)	grad_norm 1.6935 (1.6864)	
[2022-01-23 03:23:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][220/1251]	eta 0:39:08 lr 0.000391	time 2.7733 (2.2777)	loss 3.6081 (3.3710)	grad_norm 2.1345 (1.6900)	
[2022-01-23 03:23:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][230/1251]	eta 0:38:40 lr 0.000391	time 1.8238 (2.2726)	loss 2.6028 (3.3751)	grad_norm 1.5498 (1.6882)	
[2022-01-23 03:23:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][240/1251]	eta 0:38:19 lr 0.000391	time 2.3039 (2.2741)	loss 3.4756 (3.3807)	grad_norm 1.6326 (1.6901)	
[2022-01-23 03:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][250/1251]	eta 0:37:52 lr 0.000391	time 1.8688 (2.2703)	loss 2.3457 (3.3732)	grad_norm 1.6349 (1.6900)	
[2022-01-23 03:24:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][260/1251]	eta 0:37:26 lr 0.000391	time 2.5789 (2.2672)	loss 2.8781 (3.3792)	grad_norm 1.4968 (1.6877)	
[2022-01-23 03:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][270/1251]	eta 0:36:59 lr 0.000391	time 2.7862 (2.2620)	loss 3.6293 (3.3844)	grad_norm 1.6795 (1.6859)	
[2022-01-23 03:25:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][280/1251]	eta 0:36:33 lr 0.000391	time 2.1193 (2.2590)	loss 3.0086 (3.3745)	grad_norm 1.6588 (1.6838)	
[2022-01-23 03:25:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][290/1251]	eta 0:36:05 lr 0.000391	time 1.8628 (2.2529)	loss 3.8029 (3.3790)	grad_norm 1.6690 (1.6828)	
[2022-01-23 03:25:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][300/1251]	eta 0:35:36 lr 0.000391	time 1.8076 (2.2463)	loss 4.0501 (3.3853)	grad_norm 1.5483 (1.6805)	
[2022-01-23 03:26:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][310/1251]	eta 0:35:12 lr 0.000391	time 2.2212 (2.2452)	loss 3.8811 (3.3931)	grad_norm 1.5236 (1.6788)	
[2022-01-23 03:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][320/1251]	eta 0:34:46 lr 0.000391	time 1.8575 (2.2412)	loss 3.8134 (3.3966)	grad_norm 1.5952 (1.6779)	
[2022-01-23 03:27:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][330/1251]	eta 0:34:20 lr 0.000391	time 1.9049 (2.2376)	loss 3.7124 (3.3961)	grad_norm 2.1611 (1.6757)	
[2022-01-23 03:27:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][340/1251]	eta 0:34:03 lr 0.000391	time 3.2108 (2.2431)	loss 3.6335 (3.3927)	grad_norm 1.8069 (1.6751)	
[2022-01-23 03:27:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][350/1251]	eta 0:33:40 lr 0.000391	time 2.2855 (2.2430)	loss 3.8572 (3.3887)	grad_norm 1.7982 (1.6769)	
[2022-01-23 03:28:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][360/1251]	eta 0:33:14 lr 0.000391	time 1.7540 (2.2390)	loss 3.8195 (3.3915)	grad_norm 1.6879 (1.6800)	
[2022-01-23 03:28:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][370/1251]	eta 0:32:50 lr 0.000390	time 1.9436 (2.2366)	loss 3.9001 (3.3906)	grad_norm 1.8507 (1.6806)	
[2022-01-23 03:28:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][380/1251]	eta 0:32:27 lr 0.000390	time 3.3627 (2.2362)	loss 2.8159 (3.3822)	grad_norm 1.5949 (1.6817)	
[2022-01-23 03:29:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][390/1251]	eta 0:32:03 lr 0.000390	time 1.6737 (2.2344)	loss 2.7833 (3.3807)	grad_norm 2.2265 (1.6843)	
[2022-01-23 03:29:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][400/1251]	eta 0:31:37 lr 0.000390	time 2.1130 (2.2300)	loss 3.8270 (3.3851)	grad_norm 1.4411 (1.6839)	
[2022-01-23 03:29:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][410/1251]	eta 0:31:12 lr 0.000390	time 1.7974 (2.2269)	loss 3.7105 (3.3929)	grad_norm 1.7828 (1.6844)	
[2022-01-23 03:30:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][420/1251]	eta 0:30:49 lr 0.000390	time 3.0743 (2.2262)	loss 3.3608 (3.3971)	grad_norm 1.6071 (1.6841)	
[2022-01-23 03:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][430/1251]	eta 0:30:25 lr 0.000390	time 1.5806 (2.2239)	loss 3.0112 (3.3954)	grad_norm 1.7402 (1.6833)	
[2022-01-23 03:31:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][440/1251]	eta 0:30:02 lr 0.000390	time 1.9002 (2.2226)	loss 4.1017 (3.3936)	grad_norm 1.5078 (1.6834)	
[2022-01-23 03:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][450/1251]	eta 0:29:40 lr 0.000390	time 1.8846 (2.2227)	loss 2.4395 (3.3951)	grad_norm 1.4409 (1.6847)	
[2022-01-23 03:31:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][460/1251]	eta 0:29:20 lr 0.000390	time 2.2477 (2.2262)	loss 2.8591 (3.3900)	grad_norm 1.8597 (1.6852)	
[2022-01-23 03:32:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][470/1251]	eta 0:28:58 lr 0.000390	time 1.7544 (2.2257)	loss 3.7026 (3.3882)	grad_norm 1.7746 (1.6851)	
[2022-01-23 03:32:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][480/1251]	eta 0:28:35 lr 0.000390	time 1.9892 (2.2244)	loss 3.7305 (3.3922)	grad_norm 1.7901 (1.6859)	
[2022-01-23 03:32:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][490/1251]	eta 0:28:12 lr 0.000390	time 1.9756 (2.2237)	loss 2.4373 (3.3945)	grad_norm 1.5384 (1.6868)	
[2022-01-23 03:33:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][500/1251]	eta 0:27:47 lr 0.000390	time 1.9543 (2.2202)	loss 3.4690 (3.3984)	grad_norm 1.4221 (1.6853)	
[2022-01-23 03:33:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][510/1251]	eta 0:27:23 lr 0.000390	time 2.0362 (2.2184)	loss 2.9360 (3.4025)	grad_norm 1.7959 (1.6837)	
[2022-01-23 03:33:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][520/1251]	eta 0:27:01 lr 0.000390	time 1.9718 (2.2176)	loss 3.7124 (3.3996)	grad_norm 1.7443 (1.6837)	
[2022-01-23 03:34:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][530/1251]	eta 0:26:40 lr 0.000390	time 1.9017 (2.2193)	loss 3.6504 (3.3988)	grad_norm 1.5659 (1.6826)	
[2022-01-23 03:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][540/1251]	eta 0:26:16 lr 0.000390	time 2.1543 (2.2178)	loss 2.5090 (3.4000)	grad_norm 1.5127 (1.6834)	
[2022-01-23 03:35:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][550/1251]	eta 0:25:53 lr 0.000390	time 1.5632 (2.2164)	loss 4.1505 (3.4042)	grad_norm 1.4275 (1.6813)	
[2022-01-23 03:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][560/1251]	eta 0:25:29 lr 0.000390	time 1.5217 (2.2140)	loss 3.9619 (3.4016)	grad_norm 1.7115 (1.6813)	
[2022-01-23 03:35:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][570/1251]	eta 0:25:10 lr 0.000390	time 2.2925 (2.2180)	loss 4.1491 (3.4059)	grad_norm 1.9649 (1.6821)	
[2022-01-23 03:36:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][580/1251]	eta 0:24:48 lr 0.000390	time 1.8466 (2.2180)	loss 4.1842 (3.4099)	grad_norm 1.7746 (1.6815)	
[2022-01-23 03:36:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][590/1251]	eta 0:24:27 lr 0.000390	time 2.2804 (2.2199)	loss 3.1860 (3.4102)	grad_norm 1.7033 (1.6833)	
[2022-01-23 03:36:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][600/1251]	eta 0:24:02 lr 0.000390	time 1.5434 (2.2165)	loss 3.5984 (3.4125)	grad_norm 1.7992 (1.6847)	
[2022-01-23 03:37:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][610/1251]	eta 0:23:39 lr 0.000390	time 2.7133 (2.2149)	loss 3.8765 (3.4128)	grad_norm 1.5668 (1.6842)	
[2022-01-23 03:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][620/1251]	eta 0:23:16 lr 0.000389	time 2.2675 (2.2128)	loss 3.1809 (3.4131)	grad_norm 1.5407 (1.6829)	
[2022-01-23 03:37:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][630/1251]	eta 0:22:53 lr 0.000389	time 1.7614 (2.2123)	loss 4.4659 (3.4158)	grad_norm 1.5461 (1.6817)	
[2022-01-23 03:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][640/1251]	eta 0:22:30 lr 0.000389	time 2.1769 (2.2098)	loss 2.5707 (3.4152)	grad_norm 1.4924 (1.6800)	
[2022-01-23 03:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][650/1251]	eta 0:22:07 lr 0.000389	time 2.6051 (2.2086)	loss 3.4166 (3.4185)	grad_norm 1.4013 (1.6783)	
[2022-01-23 03:39:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][660/1251]	eta 0:21:45 lr 0.000389	time 1.4962 (2.2088)	loss 2.3717 (3.4164)	grad_norm 1.6377 (1.6773)	
[2022-01-23 03:39:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][670/1251]	eta 0:21:23 lr 0.000389	time 2.2979 (2.2096)	loss 3.8127 (3.4186)	grad_norm 1.5924 (1.6761)	
[2022-01-23 03:39:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][680/1251]	eta 0:21:00 lr 0.000389	time 1.6073 (2.2083)	loss 4.0421 (3.4151)	grad_norm 1.9752 (1.6761)	
[2022-01-23 03:40:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][690/1251]	eta 0:20:39 lr 0.000389	time 2.1639 (2.2088)	loss 2.9123 (3.4160)	grad_norm 1.4715 (1.6751)	
[2022-01-23 03:40:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][700/1251]	eta 0:20:16 lr 0.000389	time 1.8390 (2.2084)	loss 4.1066 (3.4160)	grad_norm 1.8294 (1.6749)	
[2022-01-23 03:40:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][710/1251]	eta 0:19:55 lr 0.000389	time 1.9266 (2.2100)	loss 2.4219 (3.4140)	grad_norm 1.6182 (1.6746)	
[2022-01-23 03:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][720/1251]	eta 0:19:35 lr 0.000389	time 1.8641 (2.2130)	loss 4.1352 (3.4167)	grad_norm 1.6283 (1.6738)	
[2022-01-23 03:41:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][730/1251]	eta 0:19:14 lr 0.000389	time 2.1435 (2.2153)	loss 3.5764 (3.4183)	grad_norm 1.6323 (1.6733)	
[2022-01-23 03:42:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][740/1251]	eta 0:18:51 lr 0.000389	time 1.9324 (2.2137)	loss 3.1762 (3.4176)	grad_norm 1.6585 (1.6737)	
[2022-01-23 03:42:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][750/1251]	eta 0:18:27 lr 0.000389	time 1.8293 (2.2101)	loss 3.8720 (3.4221)	grad_norm 1.6767 (1.6733)	
[2022-01-23 03:42:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][760/1251]	eta 0:18:04 lr 0.000389	time 1.8719 (2.2094)	loss 4.1487 (3.4208)	grad_norm 1.7470 (1.6731)	
[2022-01-23 03:43:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][770/1251]	eta 0:17:41 lr 0.000389	time 1.8475 (2.2075)	loss 3.7725 (3.4251)	grad_norm 1.5326 (1.6737)	
[2022-01-23 03:43:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][780/1251]	eta 0:17:20 lr 0.000389	time 2.0006 (2.2088)	loss 4.1701 (3.4270)	grad_norm 1.8095 (1.6747)	
[2022-01-23 03:43:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][790/1251]	eta 0:16:58 lr 0.000389	time 1.9420 (2.2097)	loss 3.8120 (3.4234)	grad_norm 1.5760 (1.6742)	
[2022-01-23 03:44:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][800/1251]	eta 0:16:36 lr 0.000389	time 2.5919 (2.2105)	loss 3.8817 (3.4227)	grad_norm 1.4880 (1.6743)	
[2022-01-23 03:44:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][810/1251]	eta 0:16:14 lr 0.000389	time 2.1048 (2.2088)	loss 3.7691 (3.4224)	grad_norm 1.6332 (1.6731)	
[2022-01-23 03:44:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][820/1251]	eta 0:15:51 lr 0.000389	time 1.9921 (2.2082)	loss 3.0630 (3.4218)	grad_norm 1.6849 (1.6748)	
[2022-01-23 03:45:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][830/1251]	eta 0:15:28 lr 0.000389	time 1.9106 (2.2057)	loss 3.0445 (3.4213)	grad_norm 1.6045 (1.6759)	
[2022-01-23 03:45:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][840/1251]	eta 0:15:05 lr 0.000389	time 2.1758 (2.2044)	loss 3.3902 (3.4194)	grad_norm 1.5316 (1.6746)	
[2022-01-23 03:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][850/1251]	eta 0:14:44 lr 0.000389	time 2.8607 (2.2055)	loss 4.1464 (3.4197)	grad_norm 1.8406 (1.6734)	
[2022-01-23 03:46:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][860/1251]	eta 0:14:22 lr 0.000388	time 3.0876 (2.2071)	loss 3.6762 (3.4209)	grad_norm 1.4683 (1.6744)	
[2022-01-23 03:46:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][870/1251]	eta 0:14:00 lr 0.000388	time 1.5673 (2.2062)	loss 3.4172 (3.4221)	grad_norm 1.5085 (1.6747)	
[2022-01-23 03:47:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][880/1251]	eta 0:13:39 lr 0.000388	time 2.3346 (2.2076)	loss 3.8595 (3.4254)	grad_norm 1.8833 (1.6747)	
[2022-01-23 03:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][890/1251]	eta 0:13:16 lr 0.000388	time 1.8849 (2.2064)	loss 3.4284 (3.4224)	grad_norm 1.6230 (1.6751)	
[2022-01-23 03:47:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][900/1251]	eta 0:12:54 lr 0.000388	time 3.5854 (2.2074)	loss 3.7973 (3.4244)	grad_norm 1.7225 (1.6756)	
[2022-01-23 03:48:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][910/1251]	eta 0:12:32 lr 0.000388	time 2.2379 (2.2062)	loss 3.6693 (3.4253)	grad_norm 1.5217 (1.6742)	
[2022-01-23 03:48:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][920/1251]	eta 0:12:09 lr 0.000388	time 1.9995 (2.2045)	loss 2.1174 (3.4217)	grad_norm 1.6167 (1.6743)	
[2022-01-23 03:48:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][930/1251]	eta 0:11:47 lr 0.000388	time 2.2322 (2.2036)	loss 3.3583 (3.4231)	grad_norm 1.8307 (1.6747)	
[2022-01-23 03:49:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][940/1251]	eta 0:11:25 lr 0.000388	time 3.1157 (2.2055)	loss 3.4933 (3.4233)	grad_norm 1.7013 (1.6745)	
[2022-01-23 03:49:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][950/1251]	eta 0:11:03 lr 0.000388	time 1.8360 (2.2040)	loss 2.6389 (3.4230)	grad_norm 1.5028 (1.6751)	
[2022-01-23 03:49:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][960/1251]	eta 0:10:40 lr 0.000388	time 1.9446 (2.2027)	loss 3.5780 (3.4227)	grad_norm 1.5979 (1.6746)	
[2022-01-23 03:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][970/1251]	eta 0:10:18 lr 0.000388	time 1.8666 (2.2023)	loss 4.2497 (3.4251)	grad_norm 1.6124 (1.6750)	
[2022-01-23 03:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][980/1251]	eta 0:09:56 lr 0.000388	time 2.7704 (2.2020)	loss 3.4118 (3.4272)	grad_norm 1.6430 (1.6743)	
[2022-01-23 03:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][990/1251]	eta 0:09:34 lr 0.000388	time 2.2952 (2.2009)	loss 3.8659 (3.4291)	grad_norm 1.6354 (1.6748)	
[2022-01-23 03:51:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1000/1251]	eta 0:09:12 lr 0.000388	time 2.8813 (2.2005)	loss 3.6416 (3.4285)	grad_norm 1.7565 (1.6743)	
[2022-01-23 03:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1010/1251]	eta 0:08:50 lr 0.000388	time 2.5106 (2.2003)	loss 4.1495 (3.4305)	grad_norm 1.6325 (1.6746)	
[2022-01-23 03:52:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1020/1251]	eta 0:08:28 lr 0.000388	time 3.3900 (2.2013)	loss 3.0476 (3.4285)	grad_norm 1.8295 (1.6756)	
[2022-01-23 03:52:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1030/1251]	eta 0:08:06 lr 0.000388	time 2.5210 (2.2009)	loss 3.6246 (3.4299)	grad_norm 1.6528 (1.6761)	
[2022-01-23 03:52:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1040/1251]	eta 0:07:44 lr 0.000388	time 2.0943 (2.2012)	loss 3.6857 (3.4296)	grad_norm 1.6512 (1.6764)	
[2022-01-23 03:53:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1050/1251]	eta 0:07:22 lr 0.000388	time 2.1883 (2.2022)	loss 3.7677 (3.4312)	grad_norm 1.8154 (1.6759)	
[2022-01-23 03:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1060/1251]	eta 0:07:00 lr 0.000388	time 3.3772 (2.2038)	loss 3.2230 (3.4306)	grad_norm 1.6265 (1.6760)	
[2022-01-23 03:54:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1070/1251]	eta 0:06:38 lr 0.000388	time 1.9446 (2.2041)	loss 3.2280 (3.4301)	grad_norm 1.4491 (1.6753)	
[2022-01-23 03:54:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1080/1251]	eta 0:06:16 lr 0.000388	time 1.8325 (2.2025)	loss 3.5985 (3.4302)	grad_norm 1.8003 (1.6753)	
[2022-01-23 03:54:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1090/1251]	eta 0:05:54 lr 0.000388	time 2.0060 (2.2006)	loss 3.4268 (3.4301)	grad_norm 1.7115 (1.6749)	
[2022-01-23 03:55:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1100/1251]	eta 0:05:32 lr 0.000388	time 1.8287 (2.2000)	loss 3.8059 (3.4311)	grad_norm 1.6340 (1.6743)	
[2022-01-23 03:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1110/1251]	eta 0:05:10 lr 0.000387	time 2.6657 (2.1989)	loss 3.9962 (3.4305)	grad_norm 1.9502 (1.6738)	
[2022-01-23 03:55:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1120/1251]	eta 0:04:48 lr 0.000387	time 2.7898 (2.1988)	loss 3.9295 (3.4290)	grad_norm 1.8262 (1.6761)	
[2022-01-23 03:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1130/1251]	eta 0:04:26 lr 0.000387	time 1.9043 (2.1987)	loss 4.2150 (3.4281)	grad_norm 1.7289 (1.6761)	
[2022-01-23 03:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1140/1251]	eta 0:04:04 lr 0.000387	time 1.9534 (2.1984)	loss 3.7659 (3.4284)	grad_norm 1.4727 (1.6758)	
[2022-01-23 03:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1150/1251]	eta 0:03:42 lr 0.000387	time 1.8729 (2.1987)	loss 2.9576 (3.4275)	grad_norm 1.6413 (1.6762)	
[2022-01-23 03:57:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1160/1251]	eta 0:03:20 lr 0.000387	time 2.5553 (2.1993)	loss 3.7292 (3.4295)	grad_norm 1.5773 (1.6758)	
[2022-01-23 03:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1170/1251]	eta 0:02:58 lr 0.000387	time 1.9690 (2.1985)	loss 2.5133 (3.4296)	grad_norm 1.5876 (1.6754)	
[2022-01-23 03:57:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1180/1251]	eta 0:02:35 lr 0.000387	time 2.1795 (2.1970)	loss 3.3674 (3.4274)	grad_norm 1.4799 (1.6758)	
[2022-01-23 03:58:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1190/1251]	eta 0:02:14 lr 0.000387	time 2.4528 (2.1971)	loss 2.9418 (3.4278)	grad_norm 1.6177 (1.6752)	
[2022-01-23 03:58:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1200/1251]	eta 0:01:52 lr 0.000387	time 2.0203 (2.1977)	loss 4.1836 (3.4286)	grad_norm 1.6045 (1.6758)	
[2022-01-23 03:59:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1210/1251]	eta 0:01:30 lr 0.000387	time 2.5124 (2.1979)	loss 2.7821 (3.4274)	grad_norm 1.9333 (1.6753)	
[2022-01-23 03:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1220/1251]	eta 0:01:08 lr 0.000387	time 1.9839 (2.1975)	loss 3.5983 (3.4285)	grad_norm 1.6507 (1.6750)	
[2022-01-23 03:59:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1230/1251]	eta 0:00:46 lr 0.000387	time 3.2223 (2.1980)	loss 3.9504 (3.4285)	grad_norm 1.6825 (1.6745)	
[2022-01-23 04:00:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1240/1251]	eta 0:00:24 lr 0.000387	time 2.0971 (2.1986)	loss 3.2784 (3.4272)	grad_norm 1.6040 (1.6742)	
[2022-01-23 04:00:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [172/300][1250/1251]	eta 0:00:02 lr 0.000387	time 1.1953 (2.1932)	loss 3.1964 (3.4253)	grad_norm 1.6749 (1.6745)	
[2022-01-23 04:00:24 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 172 training takes 0:45:44
[2022-01-23 04:00:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 12.223 (12.223)	Loss 0.9118 (0.9118)	Acc@1 77.344 (77.344)	Acc@5 94.629 (94.629)	
[2022-01-23 04:01:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.854 (3.327)	Loss 0.9055 (0.9476)	Acc@1 78.418 (77.069)	Acc@5 93.555 (93.857)	
[2022-01-23 04:01:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.323 (2.460)	Loss 0.9795 (0.9495)	Acc@1 76.660 (77.083)	Acc@5 93.359 (93.866)	
[2022-01-23 04:01:32 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.315 (2.189)	Loss 0.9349 (0.9499)	Acc@1 78.223 (77.152)	Acc@5 94.434 (93.813)	
[2022-01-23 04:01:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.840 (2.112)	Loss 0.9675 (0.9534)	Acc@1 75.977 (77.065)	Acc@5 94.434 (93.855)	
[2022-01-23 04:01:59 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.014 Acc@5 93.790
[2022-01-23 04:01:59 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.0%
[2022-01-23 04:01:59 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.01%
[2022-01-23 04:02:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][0/1251]	eta 7:36:05 lr 0.000387	time 21.8748 (21.8748)	loss 3.8356 (3.8356)	grad_norm 1.8094 (1.8094)	
[2022-01-23 04:02:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][10/1251]	eta 1:22:18 lr 0.000387	time 1.3460 (3.9797)	loss 3.1840 (3.4761)	grad_norm 1.5807 (1.5886)	
[2022-01-23 04:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][20/1251]	eta 1:04:55 lr 0.000387	time 2.1521 (3.1647)	loss 2.9472 (3.4111)	grad_norm 1.7679 (1.6014)	
[2022-01-23 04:03:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][30/1251]	eta 0:57:42 lr 0.000387	time 1.8571 (2.8356)	loss 4.1239 (3.4634)	grad_norm 1.7852 (1.6216)	
[2022-01-23 04:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][40/1251]	eta 0:56:08 lr 0.000387	time 3.8943 (2.7818)	loss 3.5768 (3.4252)	grad_norm 1.5720 (1.6539)	
[2022-01-23 04:04:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][50/1251]	eta 0:53:42 lr 0.000387	time 1.6607 (2.6828)	loss 2.8432 (3.4082)	grad_norm 1.6447 (1.6666)	
[2022-01-23 04:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][60/1251]	eta 0:51:30 lr 0.000387	time 1.8170 (2.5949)	loss 3.6716 (3.3962)	grad_norm 2.0164 (1.7033)	
[2022-01-23 04:04:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][70/1251]	eta 0:49:27 lr 0.000387	time 1.8856 (2.5124)	loss 3.7007 (3.4301)	grad_norm 1.8426 (1.7190)	
[2022-01-23 04:05:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][80/1251]	eta 0:47:51 lr 0.000387	time 2.5354 (2.4519)	loss 3.6755 (3.4458)	grad_norm 1.6495 (1.7082)	
[2022-01-23 04:05:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][90/1251]	eta 0:46:41 lr 0.000387	time 1.8565 (2.4127)	loss 3.8195 (3.4625)	grad_norm 1.9361 (1.7048)	
[2022-01-23 04:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][100/1251]	eta 0:45:58 lr 0.000387	time 2.2331 (2.3962)	loss 3.1457 (3.4143)	grad_norm 1.7104 (1.7035)	
[2022-01-23 04:06:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][110/1251]	eta 0:45:20 lr 0.000386	time 2.4598 (2.3844)	loss 4.0621 (3.4274)	grad_norm 1.6053 (1.6903)	
[2022-01-23 04:06:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][120/1251]	eta 0:44:46 lr 0.000386	time 2.8803 (2.3756)	loss 3.8973 (3.4163)	grad_norm 1.7218 (1.6895)	
[2022-01-23 04:07:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][130/1251]	eta 0:44:04 lr 0.000386	time 1.7955 (2.3594)	loss 3.3578 (3.4345)	grad_norm 1.7187 (1.6826)	
[2022-01-23 04:07:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][140/1251]	eta 0:43:26 lr 0.000386	time 1.6879 (2.3460)	loss 3.8915 (3.4423)	grad_norm 1.5284 (1.6731)	
[2022-01-23 04:07:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][150/1251]	eta 0:42:56 lr 0.000386	time 1.9359 (2.3399)	loss 3.8412 (3.4383)	grad_norm 1.7448 (1.6745)	
[2022-01-23 04:08:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][160/1251]	eta 0:42:29 lr 0.000386	time 2.8194 (2.3368)	loss 2.5854 (3.4373)	grad_norm 1.6800 (1.6737)	
[2022-01-23 04:08:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][170/1251]	eta 0:42:01 lr 0.000386	time 1.7589 (2.3323)	loss 3.9577 (3.4354)	grad_norm 1.7591 (1.6723)	
[2022-01-23 04:08:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][180/1251]	eta 0:41:25 lr 0.000386	time 1.5415 (2.3205)	loss 3.5496 (3.4456)	grad_norm 1.7985 (1.6717)	
[2022-01-23 04:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][190/1251]	eta 0:40:54 lr 0.000386	time 1.8012 (2.3135)	loss 3.5774 (3.4504)	grad_norm 1.7070 (1.6697)	
[2022-01-23 04:09:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][200/1251]	eta 0:40:27 lr 0.000386	time 2.1672 (2.3097)	loss 2.8799 (3.4565)	grad_norm 1.6244 (1.6683)	
[2022-01-23 04:10:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][210/1251]	eta 0:39:52 lr 0.000386	time 1.7028 (2.2986)	loss 3.6926 (3.4713)	grad_norm 1.6816 (1.6678)	
[2022-01-23 04:10:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][220/1251]	eta 0:39:21 lr 0.000386	time 1.9297 (2.2906)	loss 3.1614 (3.4657)	grad_norm 1.7392 (1.6707)	
[2022-01-23 04:10:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][230/1251]	eta 0:38:52 lr 0.000386	time 1.7099 (2.2844)	loss 3.8604 (3.4728)	grad_norm 1.5723 (1.6707)	
[2022-01-23 04:11:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][240/1251]	eta 0:38:26 lr 0.000386	time 2.4271 (2.2813)	loss 3.7796 (3.4658)	grad_norm 1.9795 (1.6697)	
[2022-01-23 04:11:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][250/1251]	eta 0:38:00 lr 0.000386	time 2.0030 (2.2784)	loss 3.7533 (3.4785)	grad_norm 1.8122 (1.6708)	
[2022-01-23 04:11:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][260/1251]	eta 0:37:38 lr 0.000386	time 2.5787 (2.2785)	loss 2.4920 (3.4754)	grad_norm 1.3977 (1.6698)	
[2022-01-23 04:12:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][270/1251]	eta 0:37:11 lr 0.000386	time 2.1628 (2.2750)	loss 3.7859 (3.4788)	grad_norm 1.5086 (1.6701)	
[2022-01-23 04:12:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][280/1251]	eta 0:36:42 lr 0.000386	time 1.8432 (2.2688)	loss 3.5453 (3.4716)	grad_norm 1.6142 (1.6705)	
[2022-01-23 04:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][290/1251]	eta 0:36:15 lr 0.000386	time 2.0002 (2.2634)	loss 2.6191 (3.4591)	grad_norm 1.7321 (1.6695)	
[2022-01-23 04:13:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][300/1251]	eta 0:35:50 lr 0.000386	time 2.2336 (2.2615)	loss 3.4682 (3.4630)	grad_norm 1.5084 (1.6681)	
[2022-01-23 04:13:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][310/1251]	eta 0:35:24 lr 0.000386	time 2.2447 (2.2576)	loss 2.7914 (3.4649)	grad_norm 1.7532 (1.6665)	
[2022-01-23 04:14:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][320/1251]	eta 0:34:57 lr 0.000386	time 2.3547 (2.2531)	loss 2.6999 (3.4696)	grad_norm 1.6757 (1.6669)	
[2022-01-23 04:14:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][330/1251]	eta 0:34:30 lr 0.000386	time 1.9325 (2.2480)	loss 2.7979 (3.4678)	grad_norm 1.9564 (1.6674)	
[2022-01-23 04:14:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][340/1251]	eta 0:34:07 lr 0.000386	time 2.5149 (2.2476)	loss 4.4452 (3.4683)	grad_norm 1.7450 (1.6681)	
[2022-01-23 04:15:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][350/1251]	eta 0:33:48 lr 0.000386	time 2.2450 (2.2515)	loss 3.1618 (3.4666)	grad_norm 1.5704 (1.6665)	
[2022-01-23 04:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][360/1251]	eta 0:33:26 lr 0.000385	time 2.7013 (2.2516)	loss 2.8858 (3.4549)	grad_norm 1.4923 (1.6644)	
[2022-01-23 04:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][370/1251]	eta 0:33:02 lr 0.000385	time 2.2012 (2.2506)	loss 3.6658 (3.4532)	grad_norm 2.0312 (1.6639)	
[2022-01-23 04:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][380/1251]	eta 0:32:40 lr 0.000385	time 1.8385 (2.2504)	loss 3.9412 (3.4454)	grad_norm 1.6872 (1.6653)	
[2022-01-23 04:16:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][390/1251]	eta 0:32:15 lr 0.000385	time 2.5371 (2.2485)	loss 3.0898 (3.4458)	grad_norm 1.8252 (1.6701)	
[2022-01-23 04:16:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][400/1251]	eta 0:31:49 lr 0.000385	time 1.8566 (2.2437)	loss 3.7541 (3.4468)	grad_norm 1.7793 (1.6744)	
[2022-01-23 04:17:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][410/1251]	eta 0:31:24 lr 0.000385	time 1.9434 (2.2409)	loss 2.8709 (3.4501)	grad_norm 2.2465 (1.6771)	
[2022-01-23 04:17:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][420/1251]	eta 0:30:59 lr 0.000385	time 2.0338 (2.2378)	loss 2.5843 (3.4519)	grad_norm 1.5633 (1.6770)	
[2022-01-23 04:18:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][430/1251]	eta 0:30:35 lr 0.000385	time 2.5709 (2.2352)	loss 3.0408 (3.4516)	grad_norm 1.6431 (1.6770)	
[2022-01-23 04:18:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][440/1251]	eta 0:30:11 lr 0.000385	time 1.8873 (2.2336)	loss 3.9568 (3.4498)	grad_norm 1.5625 (1.6787)	
[2022-01-23 04:18:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][450/1251]	eta 0:29:49 lr 0.000385	time 2.9272 (2.2341)	loss 3.2008 (3.4513)	grad_norm 1.6038 (1.6791)	
[2022-01-23 04:19:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][460/1251]	eta 0:29:25 lr 0.000385	time 1.8330 (2.2321)	loss 3.0103 (3.4474)	grad_norm 1.5011 (1.6808)	
[2022-01-23 04:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][470/1251]	eta 0:29:01 lr 0.000385	time 2.7986 (2.2304)	loss 3.7578 (3.4463)	grad_norm 1.5333 (1.6814)	
[2022-01-23 04:19:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][480/1251]	eta 0:28:42 lr 0.000385	time 2.3850 (2.2343)	loss 3.4952 (3.4421)	grad_norm 1.5677 (1.6803)	
[2022-01-23 04:20:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][490/1251]	eta 0:28:21 lr 0.000385	time 2.5682 (2.2362)	loss 3.2679 (3.4432)	grad_norm 1.6770 (1.6799)	
[2022-01-23 04:20:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][500/1251]	eta 0:27:59 lr 0.000385	time 1.8982 (2.2362)	loss 3.7601 (3.4469)	grad_norm 1.5085 (1.6807)	
[2022-01-23 04:20:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][510/1251]	eta 0:27:33 lr 0.000385	time 1.8666 (2.2320)	loss 4.2995 (3.4483)	grad_norm 1.7669 (1.6814)	
[2022-01-23 04:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][520/1251]	eta 0:27:08 lr 0.000385	time 1.9207 (2.2274)	loss 2.6988 (3.4483)	grad_norm 1.6059 (1.6816)	
[2022-01-23 04:21:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][530/1251]	eta 0:26:43 lr 0.000385	time 1.6045 (2.2247)	loss 3.9079 (3.4467)	grad_norm 1.4039 (1.6816)	
[2022-01-23 04:22:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][540/1251]	eta 0:26:20 lr 0.000385	time 1.8050 (2.2231)	loss 3.5828 (3.4449)	grad_norm 1.5547 (1.6813)	
[2022-01-23 04:22:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][550/1251]	eta 0:25:59 lr 0.000385	time 2.0082 (2.2247)	loss 3.5709 (3.4476)	grad_norm 1.5037 (1.6798)	
[2022-01-23 04:22:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][560/1251]	eta 0:25:35 lr 0.000385	time 1.6811 (2.2227)	loss 3.2628 (3.4477)	grad_norm 1.7374 (1.6820)	
[2022-01-23 04:23:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][570/1251]	eta 0:25:13 lr 0.000385	time 3.0177 (2.2231)	loss 3.9044 (3.4500)	grad_norm 1.5746 (1.6846)	
[2022-01-23 04:23:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][580/1251]	eta 0:24:53 lr 0.000385	time 2.1208 (2.2255)	loss 4.0641 (3.4543)	grad_norm 1.7179 (1.6851)	
[2022-01-23 04:23:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][590/1251]	eta 0:24:31 lr 0.000385	time 2.5056 (2.2262)	loss 3.7166 (3.4562)	grad_norm 1.8383 (1.6858)	
[2022-01-23 04:24:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][600/1251]	eta 0:24:08 lr 0.000385	time 2.1403 (2.2253)	loss 3.3340 (3.4541)	grad_norm 1.4625 (1.6846)	
[2022-01-23 04:24:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][610/1251]	eta 0:23:47 lr 0.000384	time 3.1361 (2.2264)	loss 3.6883 (3.4561)	grad_norm 1.5198 (1.6840)	
[2022-01-23 04:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][620/1251]	eta 0:23:24 lr 0.000384	time 1.8804 (2.2264)	loss 3.7270 (3.4585)	grad_norm 1.5458 (1.6843)	
[2022-01-23 04:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][630/1251]	eta 0:22:59 lr 0.000384	time 1.8077 (2.2222)	loss 2.4767 (3.4603)	grad_norm 1.6951 (1.6848)	
[2022-01-23 04:25:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][640/1251]	eta 0:22:38 lr 0.000384	time 1.9253 (2.2229)	loss 3.7439 (3.4622)	grad_norm 1.5705 (1.6841)	
[2022-01-23 04:26:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][650/1251]	eta 0:22:15 lr 0.000384	time 2.2088 (2.2221)	loss 3.6005 (3.4623)	grad_norm 1.7016 (1.6835)	
[2022-01-23 04:26:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][660/1251]	eta 0:21:52 lr 0.000384	time 1.8182 (2.2212)	loss 3.6414 (3.4607)	grad_norm 1.9230 (1.6845)	
[2022-01-23 04:26:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][670/1251]	eta 0:21:29 lr 0.000384	time 1.9618 (2.2190)	loss 4.1914 (3.4639)	grad_norm 1.6844 (1.6836)	
[2022-01-23 04:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][680/1251]	eta 0:21:05 lr 0.000384	time 1.8924 (2.2162)	loss 3.7517 (3.4634)	grad_norm 1.4144 (1.6830)	
[2022-01-23 04:27:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][690/1251]	eta 0:20:42 lr 0.000384	time 2.5468 (2.2150)	loss 3.1693 (3.4642)	grad_norm 1.4626 (1.6817)	
[2022-01-23 04:27:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][700/1251]	eta 0:20:20 lr 0.000384	time 2.4061 (2.2154)	loss 2.7523 (3.4657)	grad_norm 1.6906 (1.6816)	
[2022-01-23 04:28:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][710/1251]	eta 0:20:00 lr 0.000384	time 1.7566 (2.2192)	loss 2.7219 (3.4626)	grad_norm 1.4500 (1.6807)	
[2022-01-23 04:28:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][720/1251]	eta 0:19:38 lr 0.000384	time 2.9153 (2.2199)	loss 3.4122 (3.4630)	grad_norm 1.5142 (1.6811)	
[2022-01-23 04:29:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][730/1251]	eta 0:19:16 lr 0.000384	time 1.8896 (2.2195)	loss 3.0670 (3.4581)	grad_norm 1.4469 (1.6810)	
[2022-01-23 04:29:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][740/1251]	eta 0:18:52 lr 0.000384	time 2.2603 (2.2160)	loss 3.5497 (3.4583)	grad_norm 1.5632 (1.6808)	
[2022-01-23 04:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][750/1251]	eta 0:18:30 lr 0.000384	time 2.2448 (2.2168)	loss 2.7764 (3.4592)	grad_norm 1.5642 (1.6806)	
[2022-01-23 04:30:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][760/1251]	eta 0:18:08 lr 0.000384	time 2.3659 (2.2159)	loss 3.4142 (3.4560)	grad_norm 1.7683 (1.6810)	
[2022-01-23 04:30:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][770/1251]	eta 0:17:45 lr 0.000384	time 2.2340 (2.2147)	loss 2.4687 (3.4569)	grad_norm 1.5221 (1.6797)	
[2022-01-23 04:30:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][780/1251]	eta 0:17:22 lr 0.000384	time 1.9277 (2.2129)	loss 4.1666 (3.4597)	grad_norm 2.3002 (1.6815)	
[2022-01-23 04:31:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][790/1251]	eta 0:16:59 lr 0.000384	time 2.0851 (2.2112)	loss 3.8067 (3.4570)	grad_norm 1.5061 (1.6828)	
[2022-01-23 04:31:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][800/1251]	eta 0:16:37 lr 0.000384	time 1.8461 (2.2120)	loss 3.7660 (3.4578)	grad_norm 1.3777 (1.6824)	
[2022-01-23 04:31:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][810/1251]	eta 0:16:16 lr 0.000384	time 1.9136 (2.2145)	loss 3.6818 (3.4566)	grad_norm 1.7495 (1.6823)	
[2022-01-23 04:32:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][820/1251]	eta 0:15:54 lr 0.000384	time 2.8259 (2.2151)	loss 3.5728 (3.4587)	grad_norm 1.7862 (1.6824)	
[2022-01-23 04:32:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][830/1251]	eta 0:15:31 lr 0.000384	time 1.5905 (2.2129)	loss 3.6411 (3.4610)	grad_norm 1.9005 (1.6822)	
[2022-01-23 04:32:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][840/1251]	eta 0:15:08 lr 0.000384	time 1.9311 (2.2105)	loss 3.8488 (3.4629)	grad_norm 1.6336 (1.6818)	
[2022-01-23 04:33:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][850/1251]	eta 0:14:46 lr 0.000384	time 2.4967 (2.2100)	loss 4.3020 (3.4659)	grad_norm 1.6378 (1.6814)	
[2022-01-23 04:33:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][860/1251]	eta 0:14:24 lr 0.000383	time 1.8761 (2.2103)	loss 3.9309 (3.4638)	grad_norm 1.4743 (1.6818)	
[2022-01-23 04:34:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][870/1251]	eta 0:14:02 lr 0.000383	time 2.4392 (2.2111)	loss 3.4674 (3.4625)	grad_norm 1.7979 (1.6811)	
[2022-01-23 04:34:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][880/1251]	eta 0:13:40 lr 0.000383	time 2.2771 (2.2128)	loss 3.3084 (3.4613)	grad_norm 1.7258 (1.6814)	
[2022-01-23 04:34:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][890/1251]	eta 0:13:18 lr 0.000383	time 2.2251 (2.2111)	loss 3.4618 (3.4625)	grad_norm 1.5189 (1.6811)	
[2022-01-23 04:35:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][900/1251]	eta 0:12:55 lr 0.000383	time 1.7973 (2.2096)	loss 2.4311 (3.4633)	grad_norm 1.8178 (1.6807)	
[2022-01-23 04:35:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][910/1251]	eta 0:12:32 lr 0.000383	time 2.4805 (2.2081)	loss 3.9249 (3.4633)	grad_norm 1.5383 (1.6807)	
[2022-01-23 04:35:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][920/1251]	eta 0:12:10 lr 0.000383	time 2.2471 (2.2070)	loss 3.3838 (3.4625)	grad_norm 1.6236 (1.6797)	
[2022-01-23 04:36:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][930/1251]	eta 0:11:48 lr 0.000383	time 2.1517 (2.2069)	loss 3.9180 (3.4641)	grad_norm 1.7318 (1.6796)	
[2022-01-23 04:36:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][940/1251]	eta 0:11:26 lr 0.000383	time 1.5273 (2.2065)	loss 3.5789 (3.4679)	grad_norm 1.9219 (1.6796)	
[2022-01-23 04:36:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][950/1251]	eta 0:11:04 lr 0.000383	time 2.4916 (2.2068)	loss 3.7213 (3.4693)	grad_norm 1.7295 (1.6809)	
[2022-01-23 04:37:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][960/1251]	eta 0:10:42 lr 0.000383	time 2.5126 (2.2066)	loss 4.0397 (3.4680)	grad_norm 1.7220 (1.6832)	
[2022-01-23 04:37:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][970/1251]	eta 0:10:19 lr 0.000383	time 2.2314 (2.2059)	loss 3.9879 (3.4678)	grad_norm 2.1046 (1.6839)	
[2022-01-23 04:38:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][980/1251]	eta 0:09:57 lr 0.000383	time 1.9438 (2.2059)	loss 3.9437 (3.4673)	grad_norm 1.5547 (1.6832)	
[2022-01-23 04:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][990/1251]	eta 0:09:35 lr 0.000383	time 2.2927 (2.2057)	loss 3.2680 (3.4672)	grad_norm 1.9649 (1.6831)	
[2022-01-23 04:38:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1000/1251]	eta 0:09:13 lr 0.000383	time 2.5622 (2.2062)	loss 3.9676 (3.4700)	grad_norm 1.4422 (1.6825)	
[2022-01-23 04:39:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1010/1251]	eta 0:08:52 lr 0.000383	time 2.2386 (2.2079)	loss 2.5067 (3.4701)	grad_norm 1.5795 (1.6822)	
[2022-01-23 04:39:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1020/1251]	eta 0:08:30 lr 0.000383	time 2.5633 (2.2085)	loss 2.4900 (3.4716)	grad_norm 1.6022 (1.6818)	
[2022-01-23 04:39:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1030/1251]	eta 0:08:07 lr 0.000383	time 2.0413 (2.2074)	loss 3.3321 (3.4713)	grad_norm 1.6772 (1.6810)	
[2022-01-23 04:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1040/1251]	eta 0:07:45 lr 0.000383	time 2.0144 (2.2046)	loss 3.1932 (3.4712)	grad_norm 2.4131 (1.6826)	
[2022-01-23 04:40:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1050/1251]	eta 0:07:22 lr 0.000383	time 2.2818 (2.2032)	loss 3.9025 (3.4716)	grad_norm 1.5028 (1.6825)	
[2022-01-23 04:40:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1060/1251]	eta 0:07:00 lr 0.000383	time 1.8787 (2.2022)	loss 2.5433 (3.4704)	grad_norm 1.8211 (1.6831)	
[2022-01-23 04:41:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1070/1251]	eta 0:06:38 lr 0.000383	time 2.8468 (2.2018)	loss 2.8736 (3.4706)	grad_norm 1.7573 (1.6831)	
[2022-01-23 04:41:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1080/1251]	eta 0:06:16 lr 0.000383	time 1.9180 (2.2019)	loss 3.8219 (3.4701)	grad_norm 1.5896 (1.6835)	
[2022-01-23 04:42:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1090/1251]	eta 0:05:54 lr 0.000383	time 1.9151 (2.2025)	loss 4.0343 (3.4706)	grad_norm 1.9534 (1.6834)	
[2022-01-23 04:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1100/1251]	eta 0:05:32 lr 0.000383	time 2.2928 (2.2027)	loss 2.8538 (3.4685)	grad_norm 1.7355 (1.6841)	
[2022-01-23 04:42:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1110/1251]	eta 0:05:10 lr 0.000382	time 2.5812 (2.2023)	loss 3.6745 (3.4677)	grad_norm 1.6530 (1.6838)	
[2022-01-23 04:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1120/1251]	eta 0:04:48 lr 0.000382	time 2.2241 (2.2026)	loss 3.1967 (3.4649)	grad_norm 1.6827 (1.6833)	
[2022-01-23 04:43:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1130/1251]	eta 0:04:26 lr 0.000382	time 1.5755 (2.2021)	loss 3.6709 (3.4630)	grad_norm 1.6323 (1.6835)	
[2022-01-23 04:43:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1140/1251]	eta 0:04:04 lr 0.000382	time 1.8953 (2.2012)	loss 3.2066 (3.4637)	grad_norm 1.7218 (1.6840)	
[2022-01-23 04:44:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1150/1251]	eta 0:03:42 lr 0.000382	time 2.1611 (2.2024)	loss 3.7486 (3.4646)	grad_norm 1.5425 (1.6831)	
[2022-01-23 04:44:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1160/1251]	eta 0:03:20 lr 0.000382	time 1.5940 (2.2025)	loss 3.2447 (3.4621)	grad_norm 1.6139 (1.6839)	
[2022-01-23 04:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1170/1251]	eta 0:02:58 lr 0.000382	time 2.2781 (2.2019)	loss 3.7862 (3.4626)	grad_norm 1.5697 (1.6838)	
[2022-01-23 04:45:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1180/1251]	eta 0:02:36 lr 0.000382	time 2.2173 (2.2015)	loss 3.5311 (3.4615)	grad_norm 1.4899 (1.6840)	
[2022-01-23 04:45:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1190/1251]	eta 0:02:14 lr 0.000382	time 2.2470 (2.2024)	loss 3.9797 (3.4650)	grad_norm 1.7765 (1.6844)	
[2022-01-23 04:46:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1200/1251]	eta 0:01:52 lr 0.000382	time 1.6389 (2.2020)	loss 3.5636 (3.4652)	grad_norm 1.5216 (1.6842)	
[2022-01-23 04:46:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1210/1251]	eta 0:01:30 lr 0.000382	time 1.8875 (2.2008)	loss 2.7534 (3.4643)	grad_norm 1.4864 (1.6838)	
[2022-01-23 04:46:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1220/1251]	eta 0:01:08 lr 0.000382	time 3.1590 (2.2008)	loss 2.6312 (3.4652)	grad_norm 1.6885 (1.6837)	
[2022-01-23 04:47:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1230/1251]	eta 0:00:46 lr 0.000382	time 2.1232 (2.2012)	loss 3.4551 (3.4663)	grad_norm 1.6070 (1.6835)	
[2022-01-23 04:47:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1240/1251]	eta 0:00:24 lr 0.000382	time 1.2233 (2.1995)	loss 3.8302 (3.4670)	grad_norm 1.4020 (1.6838)	
[2022-01-23 04:47:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [173/300][1250/1251]	eta 0:00:02 lr 0.000382	time 1.1893 (2.1941)	loss 3.8783 (3.4682)	grad_norm 1.5371 (1.6833)	
[2022-01-23 04:47:44 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 173 training takes 0:45:45
[2022-01-23 04:48:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.728 (19.728)	Loss 0.9694 (0.9694)	Acc@1 78.516 (78.516)	Acc@5 94.434 (94.434)	
[2022-01-23 04:48:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.738 (3.429)	Loss 0.9110 (0.9613)	Acc@1 79.492 (77.282)	Acc@5 94.141 (94.087)	
[2022-01-23 04:48:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.364 (2.605)	Loss 1.0542 (0.9731)	Acc@1 74.609 (77.065)	Acc@5 92.773 (93.955)	
[2022-01-23 04:48:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.206 (2.286)	Loss 0.9575 (0.9862)	Acc@1 78.320 (76.972)	Acc@5 94.434 (93.725)	
[2022-01-23 04:49:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.890 (2.170)	Loss 1.0123 (0.9858)	Acc@1 76.660 (76.944)	Acc@5 93.848 (93.736)	
[2022-01-23 04:49:20 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 76.910 Acc@5 93.786
[2022-01-23 04:49:20 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 76.9%
[2022-01-23 04:49:20 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.01%
[2022-01-23 04:49:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][0/1251]	eta 7:28:55 lr 0.000382	time 21.5309 (21.5309)	loss 2.9704 (2.9704)	grad_norm 1.5682 (1.5682)	
[2022-01-23 04:50:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][10/1251]	eta 1:20:46 lr 0.000382	time 1.5624 (3.9056)	loss 2.9898 (3.4771)	grad_norm 1.5506 (1.6656)	
[2022-01-23 04:50:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][20/1251]	eta 1:02:31 lr 0.000382	time 1.5512 (3.0473)	loss 2.5172 (3.3075)	grad_norm 1.4729 (1.6478)	
[2022-01-23 04:50:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][30/1251]	eta 0:55:52 lr 0.000382	time 1.4013 (2.7461)	loss 3.1554 (3.3695)	grad_norm 1.7703 (1.6524)	
[2022-01-23 04:51:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][40/1251]	eta 0:54:17 lr 0.000382	time 3.8125 (2.6898)	loss 3.5889 (3.4361)	grad_norm 1.4887 (1.6506)	
[2022-01-23 04:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][50/1251]	eta 0:53:23 lr 0.000382	time 2.6125 (2.6671)	loss 3.1503 (3.4637)	grad_norm 1.8061 (1.6476)	
[2022-01-23 04:51:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][60/1251]	eta 0:51:15 lr 0.000382	time 1.5519 (2.5823)	loss 2.9755 (3.3943)	grad_norm 1.5071 (1.6411)	
[2022-01-23 04:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][70/1251]	eta 0:49:42 lr 0.000382	time 1.5609 (2.5252)	loss 3.4142 (3.3686)	grad_norm 1.6423 (1.6341)	
[2022-01-23 04:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][80/1251]	eta 0:48:39 lr 0.000382	time 3.2433 (2.4932)	loss 3.7466 (3.3923)	grad_norm 1.5643 (1.6426)	
[2022-01-23 04:53:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][90/1251]	eta 0:47:57 lr 0.000382	time 3.0884 (2.4783)	loss 3.6353 (3.4098)	grad_norm 1.4104 (1.6263)	
[2022-01-23 04:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][100/1251]	eta 0:46:30 lr 0.000381	time 1.6732 (2.4244)	loss 3.1061 (3.4250)	grad_norm 1.6404 (1.6257)	
[2022-01-23 04:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][110/1251]	eta 0:45:30 lr 0.000381	time 2.2583 (2.3927)	loss 3.7782 (3.4286)	grad_norm 1.5806 (1.6303)	
[2022-01-23 04:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][120/1251]	eta 0:44:40 lr 0.000381	time 2.2799 (2.3700)	loss 2.1670 (3.4192)	grad_norm 1.6715 (1.6306)	
[2022-01-23 04:54:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][130/1251]	eta 0:43:50 lr 0.000381	time 2.4489 (2.3463)	loss 3.3559 (3.4177)	grad_norm 1.7555 (1.6289)	
[2022-01-23 04:54:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][140/1251]	eta 0:43:02 lr 0.000381	time 2.2985 (2.3248)	loss 3.3840 (3.4200)	grad_norm 1.8606 (1.6308)	
[2022-01-23 04:55:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][150/1251]	eta 0:42:28 lr 0.000381	time 2.0559 (2.3145)	loss 4.1225 (3.4219)	grad_norm 1.6509 (1.6356)	
[2022-01-23 04:55:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][160/1251]	eta 0:41:59 lr 0.000381	time 1.8720 (2.3090)	loss 3.4206 (3.4405)	grad_norm 2.0039 (1.6404)	
[2022-01-23 04:55:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][170/1251]	eta 0:41:25 lr 0.000381	time 1.5458 (2.2990)	loss 3.5826 (3.4538)	grad_norm 1.9164 (1.6527)	
[2022-01-23 04:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][180/1251]	eta 0:41:09 lr 0.000381	time 3.1310 (2.3057)	loss 3.4777 (3.4508)	grad_norm 3.2199 (1.7307)	
[2022-01-23 04:56:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][190/1251]	eta 0:40:53 lr 0.000381	time 2.6255 (2.3128)	loss 2.9175 (3.4433)	grad_norm 1.7423 (1.7296)	
[2022-01-23 04:57:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][200/1251]	eta 0:40:33 lr 0.000381	time 2.1745 (2.3158)	loss 4.1459 (3.4521)	grad_norm 1.6472 (1.7264)	
[2022-01-23 04:57:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][210/1251]	eta 0:40:09 lr 0.000381	time 1.8630 (2.3150)	loss 3.3582 (3.4649)	grad_norm 1.8248 (1.7249)	
[2022-01-23 04:57:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][220/1251]	eta 0:39:41 lr 0.000381	time 2.4000 (2.3103)	loss 3.8075 (3.4658)	grad_norm 1.9128 (1.7223)	
[2022-01-23 04:58:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][230/1251]	eta 0:39:06 lr 0.000381	time 1.8681 (2.2985)	loss 2.1892 (3.4444)	grad_norm 1.8006 (1.7184)	
[2022-01-23 04:58:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][240/1251]	eta 0:38:25 lr 0.000381	time 1.8864 (2.2801)	loss 3.8179 (3.4510)	grad_norm 1.3964 (1.7127)	
[2022-01-23 04:58:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][250/1251]	eta 0:37:51 lr 0.000381	time 1.9474 (2.2694)	loss 3.6068 (3.4550)	grad_norm 1.8754 (1.7088)	
[2022-01-23 04:59:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][260/1251]	eta 0:37:21 lr 0.000381	time 2.3643 (2.2622)	loss 3.6781 (3.4503)	grad_norm 1.6931 (1.7059)	
[2022-01-23 04:59:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][270/1251]	eta 0:37:01 lr 0.000381	time 2.5246 (2.2645)	loss 3.7990 (3.4481)	grad_norm 1.6162 (1.7040)	
[2022-01-23 04:59:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][280/1251]	eta 0:36:40 lr 0.000381	time 2.2349 (2.2667)	loss 3.8670 (3.4469)	grad_norm 1.7224 (1.7063)	
[2022-01-23 05:00:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][290/1251]	eta 0:36:17 lr 0.000381	time 2.7867 (2.2658)	loss 2.9358 (3.4440)	grad_norm 1.6798 (1.7063)	
[2022-01-23 05:00:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][300/1251]	eta 0:35:56 lr 0.000381	time 1.9149 (2.2672)	loss 2.5734 (3.4405)	grad_norm 1.4707 (1.7060)	
[2022-01-23 05:01:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][310/1251]	eta 0:35:32 lr 0.000381	time 2.1389 (2.2659)	loss 2.9028 (3.4406)	grad_norm 1.8276 (1.7087)	
[2022-01-23 05:01:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][320/1251]	eta 0:35:08 lr 0.000381	time 2.1763 (2.2647)	loss 3.5930 (3.4375)	grad_norm 2.0408 (1.7097)	
[2022-01-23 05:01:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][330/1251]	eta 0:34:44 lr 0.000381	time 1.8327 (2.2628)	loss 3.8552 (3.4449)	grad_norm 1.8187 (1.7094)	
[2022-01-23 05:02:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][340/1251]	eta 0:34:19 lr 0.000381	time 2.1761 (2.2610)	loss 3.7614 (3.4439)	grad_norm 1.4847 (1.7087)	
[2022-01-23 05:02:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][350/1251]	eta 0:33:52 lr 0.000380	time 1.8060 (2.2556)	loss 3.5578 (3.4423)	grad_norm 1.6737 (1.7066)	
[2022-01-23 05:02:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][360/1251]	eta 0:33:24 lr 0.000380	time 1.8327 (2.2498)	loss 3.9686 (3.4464)	grad_norm 2.0657 (1.7063)	
[2022-01-23 05:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][370/1251]	eta 0:32:59 lr 0.000380	time 1.7772 (2.2466)	loss 4.1975 (3.4465)	grad_norm 1.6905 (1.7077)	
[2022-01-23 05:03:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][380/1251]	eta 0:32:32 lr 0.000380	time 1.8235 (2.2416)	loss 3.5628 (3.4474)	grad_norm 1.7961 (1.7083)	
[2022-01-23 05:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][390/1251]	eta 0:32:06 lr 0.000380	time 2.2630 (2.2374)	loss 4.2495 (3.4518)	grad_norm 1.6113 (1.7056)	
[2022-01-23 05:04:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][400/1251]	eta 0:31:41 lr 0.000380	time 2.1706 (2.2341)	loss 3.8314 (3.4550)	grad_norm 1.5141 (1.7027)	
[2022-01-23 05:04:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][410/1251]	eta 0:31:17 lr 0.000380	time 1.8808 (2.2322)	loss 2.1646 (3.4566)	grad_norm 1.8402 (1.7021)	
[2022-01-23 05:05:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][420/1251]	eta 0:30:57 lr 0.000380	time 2.6242 (2.2352)	loss 3.2452 (3.4526)	grad_norm 1.6775 (1.7013)	
[2022-01-23 05:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][430/1251]	eta 0:30:32 lr 0.000380	time 1.8500 (2.2321)	loss 3.9744 (3.4568)	grad_norm 1.7421 (1.7000)	
[2022-01-23 05:05:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][440/1251]	eta 0:30:06 lr 0.000380	time 1.7447 (2.2281)	loss 2.6190 (3.4585)	grad_norm 1.7851 (1.7011)	
[2022-01-23 05:06:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][450/1251]	eta 0:29:43 lr 0.000380	time 1.9995 (2.2271)	loss 3.8012 (3.4602)	grad_norm 1.6036 (1.7007)	
[2022-01-23 05:06:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][460/1251]	eta 0:29:20 lr 0.000380	time 1.6362 (2.2252)	loss 3.6453 (3.4658)	grad_norm 1.5261 (1.7017)	
[2022-01-23 05:06:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][470/1251]	eta 0:28:57 lr 0.000380	time 1.8767 (2.2250)	loss 3.7433 (3.4675)	grad_norm 1.6025 (1.7010)	
[2022-01-23 05:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][480/1251]	eta 0:28:35 lr 0.000380	time 1.4198 (2.2248)	loss 3.3038 (3.4704)	grad_norm 1.8325 (1.7006)	
[2022-01-23 05:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][490/1251]	eta 0:28:12 lr 0.000380	time 1.8852 (2.2236)	loss 3.1070 (3.4688)	grad_norm 1.6662 (1.6993)	
[2022-01-23 05:07:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][500/1251]	eta 0:27:49 lr 0.000380	time 2.2124 (2.2231)	loss 3.4236 (3.4663)	grad_norm 1.5467 (1.6985)	
[2022-01-23 05:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][510/1251]	eta 0:27:28 lr 0.000380	time 2.2454 (2.2242)	loss 2.5898 (3.4642)	grad_norm 1.7056 (1.6956)	
[2022-01-23 05:08:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][520/1251]	eta 0:27:04 lr 0.000380	time 1.6693 (2.2219)	loss 2.6374 (3.4621)	grad_norm 1.7514 (1.6946)	
[2022-01-23 05:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][530/1251]	eta 0:26:44 lr 0.000380	time 1.9329 (2.2249)	loss 2.4368 (3.4574)	grad_norm 1.9478 (1.6941)	
[2022-01-23 05:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][540/1251]	eta 0:26:24 lr 0.000380	time 2.4149 (2.2288)	loss 3.7801 (3.4599)	grad_norm 1.6396 (1.6961)	
[2022-01-23 05:09:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][550/1251]	eta 0:26:01 lr 0.000380	time 1.8266 (2.2271)	loss 3.1945 (3.4579)	grad_norm 1.4913 (1.6963)	
[2022-01-23 05:10:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][560/1251]	eta 0:25:36 lr 0.000380	time 1.8678 (2.2241)	loss 2.6228 (3.4580)	grad_norm 1.7768 (1.6984)	
[2022-01-23 05:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][570/1251]	eta 0:25:13 lr 0.000380	time 1.9588 (2.2222)	loss 3.9511 (3.4619)	grad_norm 1.9742 (1.6972)	
[2022-01-23 05:10:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][580/1251]	eta 0:24:49 lr 0.000380	time 1.8980 (2.2194)	loss 2.5360 (3.4604)	grad_norm 1.5214 (1.6965)	
[2022-01-23 05:11:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][590/1251]	eta 0:24:25 lr 0.000380	time 1.9337 (2.2172)	loss 3.8531 (3.4615)	grad_norm 1.7338 (1.6970)	
[2022-01-23 05:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][600/1251]	eta 0:24:03 lr 0.000379	time 2.7748 (2.2173)	loss 3.9517 (3.4619)	grad_norm 1.5553 (1.6968)	
[2022-01-23 05:11:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][610/1251]	eta 0:23:41 lr 0.000379	time 1.6614 (2.2181)	loss 4.0706 (3.4557)	grad_norm 1.8008 (1.6965)	
[2022-01-23 05:12:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][620/1251]	eta 0:23:19 lr 0.000379	time 1.9124 (2.2180)	loss 3.2079 (3.4563)	grad_norm 1.6271 (1.6949)	
[2022-01-23 05:12:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][630/1251]	eta 0:22:58 lr 0.000379	time 2.0498 (2.2206)	loss 2.7984 (3.4567)	grad_norm 1.6322 (1.6956)	
[2022-01-23 05:13:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][640/1251]	eta 0:22:37 lr 0.000379	time 2.8685 (2.2215)	loss 3.3327 (3.4532)	grad_norm 1.5317 (1.6945)	
[2022-01-23 05:13:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][650/1251]	eta 0:22:13 lr 0.000379	time 1.8654 (2.2181)	loss 3.4346 (3.4504)	grad_norm 1.5931 (1.6944)	
[2022-01-23 05:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][660/1251]	eta 0:21:48 lr 0.000379	time 1.9503 (2.2143)	loss 3.9137 (3.4492)	grad_norm 1.8102 (1.6920)	
[2022-01-23 05:14:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][670/1251]	eta 0:21:25 lr 0.000379	time 2.2570 (2.2121)	loss 3.9668 (3.4515)	grad_norm 1.7394 (1.6910)	
[2022-01-23 05:14:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][680/1251]	eta 0:21:03 lr 0.000379	time 2.2611 (2.2126)	loss 3.1971 (3.4517)	grad_norm 1.8090 (1.6918)	
[2022-01-23 05:14:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][690/1251]	eta 0:20:40 lr 0.000379	time 1.5637 (2.2114)	loss 3.6740 (3.4513)	grad_norm 1.4802 (1.6912)	
[2022-01-23 05:15:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][700/1251]	eta 0:20:19 lr 0.000379	time 2.0350 (2.2125)	loss 2.4531 (3.4473)	grad_norm 1.7280 (1.6911)	
[2022-01-23 05:15:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][710/1251]	eta 0:19:56 lr 0.000379	time 1.8801 (2.2123)	loss 3.5146 (3.4465)	grad_norm 1.7272 (1.6898)	
[2022-01-23 05:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][720/1251]	eta 0:19:33 lr 0.000379	time 1.3258 (2.2106)	loss 3.9341 (3.4431)	grad_norm 1.5550 (1.6891)	
[2022-01-23 05:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][730/1251]	eta 0:19:11 lr 0.000379	time 1.7899 (2.2107)	loss 4.1045 (3.4427)	grad_norm 1.7562 (1.6891)	
[2022-01-23 05:16:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][740/1251]	eta 0:18:49 lr 0.000379	time 2.0782 (2.2106)	loss 3.4087 (3.4420)	grad_norm 1.5238 (1.6899)	
[2022-01-23 05:17:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][750/1251]	eta 0:18:27 lr 0.000379	time 1.8000 (2.2109)	loss 4.1519 (3.4450)	grad_norm 1.5779 (1.6907)	
[2022-01-23 05:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][760/1251]	eta 0:18:06 lr 0.000379	time 1.9161 (2.2132)	loss 3.6490 (3.4448)	grad_norm 1.8548 (1.6910)	
[2022-01-23 05:17:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][770/1251]	eta 0:17:44 lr 0.000379	time 1.5360 (2.2129)	loss 2.1722 (3.4462)	grad_norm 1.5086 (1.6898)	
[2022-01-23 05:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][780/1251]	eta 0:17:23 lr 0.000379	time 3.0248 (2.2150)	loss 3.9907 (3.4450)	grad_norm 1.4293 (1.6905)	
[2022-01-23 05:18:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][790/1251]	eta 0:17:00 lr 0.000379	time 1.8485 (2.2145)	loss 3.9561 (3.4472)	grad_norm 1.4294 (1.6900)	
[2022-01-23 05:18:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][800/1251]	eta 0:16:38 lr 0.000379	time 1.8382 (2.2133)	loss 2.8114 (3.4469)	grad_norm 1.3679 (1.6915)	
[2022-01-23 05:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][810/1251]	eta 0:16:14 lr 0.000379	time 1.9488 (2.2101)	loss 3.5492 (3.4482)	grad_norm 1.6567 (1.6933)	
[2022-01-23 05:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][820/1251]	eta 0:15:51 lr 0.000379	time 2.5121 (2.2087)	loss 3.7401 (3.4493)	grad_norm 1.6435 (1.6936)	
[2022-01-23 05:19:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][830/1251]	eta 0:15:29 lr 0.000379	time 1.8746 (2.2067)	loss 3.9237 (3.4502)	grad_norm 1.5255 (1.6946)	
[2022-01-23 05:20:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][840/1251]	eta 0:15:06 lr 0.000379	time 1.8819 (2.2063)	loss 2.8900 (3.4502)	grad_norm 1.8026 (1.6938)	
[2022-01-23 05:20:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][850/1251]	eta 0:14:44 lr 0.000378	time 2.1413 (2.2066)	loss 2.2469 (3.4481)	grad_norm 1.7263 (1.6937)	
[2022-01-23 05:21:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][860/1251]	eta 0:14:22 lr 0.000378	time 2.3294 (2.2064)	loss 3.7148 (3.4480)	grad_norm 1.5587 (1.6935)	
[2022-01-23 05:21:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][870/1251]	eta 0:14:00 lr 0.000378	time 2.1029 (2.2069)	loss 2.8924 (3.4448)	grad_norm 1.6278 (1.6932)	
[2022-01-23 05:21:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][880/1251]	eta 0:13:39 lr 0.000378	time 1.8976 (2.2086)	loss 3.9461 (3.4476)	grad_norm 1.9697 (1.6926)	
[2022-01-23 05:22:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][890/1251]	eta 0:13:18 lr 0.000378	time 2.1898 (2.2109)	loss 3.6947 (3.4502)	grad_norm 1.5935 (1.6922)	
[2022-01-23 05:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][900/1251]	eta 0:12:55 lr 0.000378	time 2.0135 (2.2097)	loss 3.8879 (3.4502)	grad_norm 1.4831 (1.6913)	
[2022-01-23 05:22:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][910/1251]	eta 0:12:32 lr 0.000378	time 1.7964 (2.2071)	loss 3.7655 (3.4498)	grad_norm 1.5359 (1.6903)	
[2022-01-23 05:23:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][920/1251]	eta 0:12:10 lr 0.000378	time 1.9910 (2.2056)	loss 3.9422 (3.4524)	grad_norm 1.5879 (1.6900)	
[2022-01-23 05:23:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][930/1251]	eta 0:11:48 lr 0.000378	time 1.9103 (2.2065)	loss 3.7590 (3.4505)	grad_norm 1.4757 (1.6885)	
[2022-01-23 05:23:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][940/1251]	eta 0:11:26 lr 0.000378	time 2.5644 (2.2064)	loss 2.9812 (3.4501)	grad_norm 1.5475 (1.6889)	
[2022-01-23 05:24:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][950/1251]	eta 0:11:04 lr 0.000378	time 1.4542 (2.2064)	loss 3.6814 (3.4513)	grad_norm 1.3513 (1.6892)	
[2022-01-23 05:24:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][960/1251]	eta 0:10:41 lr 0.000378	time 1.6956 (2.2045)	loss 3.6650 (3.4540)	grad_norm 1.5665 (1.6890)	
[2022-01-23 05:24:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][970/1251]	eta 0:10:19 lr 0.000378	time 1.8532 (2.2029)	loss 3.2933 (3.4530)	grad_norm 1.5979 (1.6893)	
[2022-01-23 05:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][980/1251]	eta 0:09:57 lr 0.000378	time 1.8916 (2.2030)	loss 3.6329 (3.4518)	grad_norm 1.7193 (1.6889)	
[2022-01-23 05:25:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][990/1251]	eta 0:09:34 lr 0.000378	time 1.7721 (2.2030)	loss 4.1696 (3.4524)	grad_norm 1.6540 (1.6887)	
[2022-01-23 05:26:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1000/1251]	eta 0:09:13 lr 0.000378	time 1.6212 (2.2032)	loss 3.2957 (3.4472)	grad_norm 1.9031 (1.6889)	
[2022-01-23 05:26:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1010/1251]	eta 0:08:51 lr 0.000378	time 1.6684 (2.2036)	loss 4.0365 (3.4491)	grad_norm 1.6240 (1.6899)	
[2022-01-23 05:26:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1020/1251]	eta 0:08:29 lr 0.000378	time 1.6799 (2.2041)	loss 3.4039 (3.4471)	grad_norm 2.0764 (1.6903)	
[2022-01-23 05:27:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1030/1251]	eta 0:08:06 lr 0.000378	time 1.8533 (2.2033)	loss 3.7922 (3.4485)	grad_norm 1.5461 (1.6901)	
[2022-01-23 05:27:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1040/1251]	eta 0:07:45 lr 0.000378	time 2.4317 (2.2041)	loss 3.7145 (3.4481)	grad_norm 2.0442 (1.6902)	
[2022-01-23 05:27:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1050/1251]	eta 0:07:23 lr 0.000378	time 1.9528 (2.2042)	loss 3.0840 (3.4480)	grad_norm 1.4800 (1.6909)	
[2022-01-23 05:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1060/1251]	eta 0:07:01 lr 0.000378	time 1.9065 (2.2053)	loss 3.5967 (3.4497)	grad_norm 2.1472 (1.6917)	
[2022-01-23 05:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1070/1251]	eta 0:06:38 lr 0.000378	time 1.8898 (2.2043)	loss 4.0426 (3.4491)	grad_norm 1.6436 (1.6917)	
[2022-01-23 05:29:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1080/1251]	eta 0:06:16 lr 0.000378	time 1.9915 (2.2028)	loss 2.5132 (3.4495)	grad_norm 1.8605 (1.6915)	
[2022-01-23 05:29:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1090/1251]	eta 0:05:54 lr 0.000378	time 2.0612 (2.2023)	loss 3.3326 (3.4503)	grad_norm 1.6924 (1.6914)	
[2022-01-23 05:29:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1100/1251]	eta 0:05:33 lr 0.000377	time 2.5164 (2.2061)	loss 2.7218 (3.4491)	grad_norm 1.6451 (1.6916)	
[2022-01-23 05:30:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1110/1251]	eta 0:05:10 lr 0.000377	time 1.9442 (2.2053)	loss 3.4186 (3.4492)	grad_norm 1.8273 (1.6912)	
[2022-01-23 05:30:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1120/1251]	eta 0:04:48 lr 0.000377	time 1.7150 (2.2032)	loss 4.3813 (3.4517)	grad_norm 1.5684 (1.6905)	
[2022-01-23 05:30:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1130/1251]	eta 0:04:26 lr 0.000377	time 2.1475 (2.2023)	loss 3.3726 (3.4527)	grad_norm 1.6719 (1.6899)	
[2022-01-23 05:31:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1140/1251]	eta 0:04:04 lr 0.000377	time 2.2208 (2.2026)	loss 3.6445 (3.4525)	grad_norm 1.5316 (1.6906)	
[2022-01-23 05:31:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1150/1251]	eta 0:03:42 lr 0.000377	time 1.9620 (2.2016)	loss 3.3434 (3.4529)	grad_norm 1.4934 (1.6906)	
[2022-01-23 05:31:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1160/1251]	eta 0:03:20 lr 0.000377	time 2.3389 (2.2025)	loss 3.6593 (3.4547)	grad_norm 1.8797 (1.6910)	
[2022-01-23 05:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1170/1251]	eta 0:02:58 lr 0.000377	time 1.4864 (2.2019)	loss 3.9643 (3.4539)	grad_norm 1.6850 (1.6909)	
[2022-01-23 05:32:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1180/1251]	eta 0:02:36 lr 0.000377	time 1.7106 (2.2035)	loss 2.1500 (3.4520)	grad_norm 1.7588 (1.6905)	
[2022-01-23 05:33:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1190/1251]	eta 0:02:14 lr 0.000377	time 2.3928 (2.2037)	loss 2.7226 (3.4510)	grad_norm 1.5559 (1.6903)	
[2022-01-23 05:33:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1200/1251]	eta 0:01:52 lr 0.000377	time 2.4627 (2.2044)	loss 3.2501 (3.4506)	grad_norm 1.7139 (1.6894)	
[2022-01-23 05:33:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1210/1251]	eta 0:01:30 lr 0.000377	time 1.7080 (2.2044)	loss 1.9800 (3.4511)	grad_norm 1.5134 (1.6891)	
[2022-01-23 05:34:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1220/1251]	eta 0:01:08 lr 0.000377	time 1.7813 (2.2049)	loss 3.8494 (3.4513)	grad_norm 1.6211 (1.6887)	
[2022-01-23 05:34:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1230/1251]	eta 0:00:46 lr 0.000377	time 3.3662 (2.2051)	loss 3.6295 (3.4521)	grad_norm 1.6202 (1.6885)	
[2022-01-23 05:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1240/1251]	eta 0:00:24 lr 0.000377	time 1.4845 (2.2032)	loss 4.0699 (3.4504)	grad_norm 1.5975 (1.6879)	
[2022-01-23 05:35:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [174/300][1250/1251]	eta 0:00:02 lr 0.000377	time 1.1852 (2.1972)	loss 3.3342 (3.4513)	grad_norm 1.5302 (1.6882)	
[2022-01-23 05:35:09 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 174 training takes 0:45:49
[2022-01-23 05:35:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.889 (19.889)	Loss 0.9903 (0.9903)	Acc@1 77.344 (77.344)	Acc@5 92.383 (92.383)	
[2022-01-23 05:35:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.985 (3.689)	Loss 0.9520 (0.9462)	Acc@1 77.930 (77.628)	Acc@5 94.141 (94.070)	
[2022-01-23 05:36:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.949 (2.704)	Loss 0.9065 (0.9527)	Acc@1 78.809 (77.344)	Acc@5 94.434 (94.043)	
[2022-01-23 05:36:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.957 (2.285)	Loss 0.9695 (0.9661)	Acc@1 77.930 (77.278)	Acc@5 92.871 (93.775)	
[2022-01-23 05:36:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.594 (2.184)	Loss 0.9792 (0.9700)	Acc@1 76.855 (77.153)	Acc@5 93.945 (93.738)	
[2022-01-23 05:36:46 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.154 Acc@5 93.768
[2022-01-23 05:36:46 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.2%
[2022-01-23 05:36:46 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.15%
[2022-01-23 05:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][0/1251]	eta 7:13:51 lr 0.000377	time 20.8086 (20.8086)	loss 4.0396 (4.0396)	grad_norm 1.4355 (1.4355)	
[2022-01-23 05:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][10/1251]	eta 1:23:50 lr 0.000377	time 2.5642 (4.0537)	loss 3.5395 (3.5558)	grad_norm 1.5863 (1.5502)	
[2022-01-23 05:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][20/1251]	eta 1:05:01 lr 0.000377	time 2.1646 (3.1693)	loss 3.2992 (3.4505)	grad_norm 1.5323 (1.6056)	
[2022-01-23 05:38:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][30/1251]	eta 0:57:17 lr 0.000377	time 1.7425 (2.8156)	loss 2.5764 (3.4662)	grad_norm 1.7542 (1.6475)	
[2022-01-23 05:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][40/1251]	eta 0:55:00 lr 0.000377	time 5.3205 (2.7258)	loss 2.6060 (3.4667)	grad_norm 1.5299 (1.6428)	
[2022-01-23 05:39:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][50/1251]	eta 0:52:31 lr 0.000377	time 1.5929 (2.6240)	loss 3.4946 (3.4686)	grad_norm 2.0163 (1.6500)	
[2022-01-23 05:39:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][60/1251]	eta 0:51:01 lr 0.000377	time 1.7495 (2.5708)	loss 3.0064 (3.4859)	grad_norm 1.7417 (1.6497)	
[2022-01-23 05:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][70/1251]	eta 0:49:41 lr 0.000377	time 1.7785 (2.5244)	loss 4.1694 (3.4969)	grad_norm 1.7752 (1.6602)	
[2022-01-23 05:40:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][80/1251]	eta 0:48:52 lr 0.000377	time 4.6190 (2.5039)	loss 3.5541 (3.4500)	grad_norm 2.0146 (1.6713)	
[2022-01-23 05:40:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][90/1251]	eta 0:48:06 lr 0.000377	time 1.5823 (2.4864)	loss 3.7361 (3.4887)	grad_norm 1.5480 (1.6761)	
[2022-01-23 05:40:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][100/1251]	eta 0:47:12 lr 0.000376	time 1.8244 (2.4611)	loss 3.8073 (3.4932)	grad_norm 1.9155 (1.6892)	
[2022-01-23 05:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][110/1251]	eta 0:46:12 lr 0.000376	time 1.8546 (2.4301)	loss 4.1612 (3.4796)	grad_norm 1.5650 (1.6934)	
[2022-01-23 05:41:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][120/1251]	eta 0:45:28 lr 0.000376	time 2.9594 (2.4128)	loss 3.6922 (3.4736)	grad_norm 2.1339 (1.6991)	
[2022-01-23 05:41:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][130/1251]	eta 0:44:24 lr 0.000376	time 2.2602 (2.3770)	loss 2.8422 (3.4677)	grad_norm 1.7112 (1.7039)	
[2022-01-23 05:42:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][140/1251]	eta 0:43:33 lr 0.000376	time 2.0128 (2.3525)	loss 2.9737 (3.4499)	grad_norm 1.6853 (1.6978)	
[2022-01-23 05:42:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][150/1251]	eta 0:42:52 lr 0.000376	time 2.2558 (2.3363)	loss 3.4397 (3.4541)	grad_norm 1.4827 (1.6910)	
[2022-01-23 05:43:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][160/1251]	eta 0:42:24 lr 0.000376	time 3.3689 (2.3325)	loss 3.8155 (3.4634)	grad_norm 1.6663 (1.6930)	
[2022-01-23 05:43:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][170/1251]	eta 0:42:05 lr 0.000376	time 2.2436 (2.3364)	loss 3.5998 (3.4566)	grad_norm 1.9962 (1.6968)	
[2022-01-23 05:43:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][180/1251]	eta 0:41:34 lr 0.000376	time 2.0664 (2.3296)	loss 3.8201 (3.4629)	grad_norm 1.9141 (1.7002)	
[2022-01-23 05:44:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][190/1251]	eta 0:41:07 lr 0.000376	time 2.2590 (2.3259)	loss 2.8755 (3.4441)	grad_norm 1.8667 (1.7011)	
[2022-01-23 05:44:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][200/1251]	eta 0:40:42 lr 0.000376	time 2.6210 (2.3237)	loss 3.9510 (3.4494)	grad_norm 1.5978 (1.7004)	
[2022-01-23 05:44:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][210/1251]	eta 0:40:03 lr 0.000376	time 1.6260 (2.3093)	loss 3.6914 (3.4524)	grad_norm 2.1788 (1.7037)	
[2022-01-23 05:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][220/1251]	eta 0:39:30 lr 0.000376	time 2.0392 (2.2991)	loss 3.5746 (3.4438)	grad_norm 1.5391 (1.6996)	
[2022-01-23 05:45:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][230/1251]	eta 0:39:03 lr 0.000376	time 2.3175 (2.2957)	loss 3.1858 (3.4336)	grad_norm 2.0038 (1.6991)	
[2022-01-23 05:46:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][240/1251]	eta 0:38:47 lr 0.000376	time 3.0029 (2.3026)	loss 3.4066 (3.4307)	grad_norm 1.9525 (1.7016)	
[2022-01-23 05:46:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][250/1251]	eta 0:38:22 lr 0.000376	time 2.4836 (2.3004)	loss 2.6594 (3.4293)	grad_norm 1.7536 (1.6998)	
[2022-01-23 05:46:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][260/1251]	eta 0:37:49 lr 0.000376	time 1.8371 (2.2900)	loss 4.0082 (3.4241)	grad_norm 1.6502 (1.7011)	
[2022-01-23 05:47:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][270/1251]	eta 0:37:17 lr 0.000376	time 1.9372 (2.2809)	loss 3.5907 (3.4281)	grad_norm 1.5940 (1.6998)	
[2022-01-23 05:47:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][280/1251]	eta 0:36:46 lr 0.000376	time 1.9669 (2.2726)	loss 3.7052 (3.4390)	grad_norm 1.8006 (1.6966)	
[2022-01-23 05:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][290/1251]	eta 0:36:20 lr 0.000376	time 2.1608 (2.2689)	loss 2.9661 (3.4284)	grad_norm 1.6906 (1.6987)	
[2022-01-23 05:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][300/1251]	eta 0:35:51 lr 0.000376	time 1.8672 (2.2628)	loss 3.3985 (3.4356)	grad_norm 1.6633 (1.6966)	
[2022-01-23 05:48:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][310/1251]	eta 0:35:26 lr 0.000376	time 1.8886 (2.2603)	loss 3.9193 (3.4393)	grad_norm 1.6924 (1.6946)	
[2022-01-23 05:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][320/1251]	eta 0:34:57 lr 0.000376	time 1.9844 (2.2525)	loss 3.3037 (3.4406)	grad_norm 1.4553 (1.6932)	
[2022-01-23 05:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][330/1251]	eta 0:34:32 lr 0.000376	time 2.4218 (2.2508)	loss 2.4821 (3.4412)	grad_norm 1.5474 (1.6937)	
[2022-01-23 05:49:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][340/1251]	eta 0:34:09 lr 0.000376	time 2.7536 (2.2498)	loss 4.0356 (3.4379)	grad_norm 1.4458 (1.6936)	
[2022-01-23 05:49:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][350/1251]	eta 0:33:48 lr 0.000375	time 2.5907 (2.2512)	loss 3.8014 (3.4409)	grad_norm 1.5749 (1.6916)	
[2022-01-23 05:50:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][360/1251]	eta 0:33:25 lr 0.000375	time 2.1255 (2.2504)	loss 2.7397 (3.4334)	grad_norm 1.5967 (1.6918)	
[2022-01-23 05:50:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][370/1251]	eta 0:33:03 lr 0.000375	time 2.5397 (2.2518)	loss 3.2616 (3.4309)	grad_norm 1.7142 (1.6913)	
[2022-01-23 05:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][380/1251]	eta 0:32:41 lr 0.000375	time 2.1958 (2.2519)	loss 2.7283 (3.4252)	grad_norm 1.4581 (1.6887)	
[2022-01-23 05:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][390/1251]	eta 0:32:19 lr 0.000375	time 2.5566 (2.2527)	loss 3.0566 (3.4304)	grad_norm 1.6753 (1.6894)	
[2022-01-23 05:51:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][400/1251]	eta 0:31:53 lr 0.000375	time 1.8956 (2.2487)	loss 2.5783 (3.4290)	grad_norm 1.8316 (1.6917)	
[2022-01-23 05:52:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][410/1251]	eta 0:31:33 lr 0.000375	time 2.1603 (2.2518)	loss 4.0234 (3.4263)	grad_norm 2.1218 (1.6945)	
[2022-01-23 05:52:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][420/1251]	eta 0:31:07 lr 0.000375	time 1.6307 (2.2474)	loss 4.0647 (3.4329)	grad_norm 1.7000 (1.6976)	
[2022-01-23 05:52:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][430/1251]	eta 0:30:47 lr 0.000375	time 2.3324 (2.2497)	loss 4.0758 (3.4352)	grad_norm 1.7913 (1.6972)	
[2022-01-23 05:53:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][440/1251]	eta 0:30:20 lr 0.000375	time 1.5431 (2.2448)	loss 3.0754 (3.4292)	grad_norm 2.6964 (1.7000)	
[2022-01-23 05:53:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][450/1251]	eta 0:29:57 lr 0.000375	time 2.2440 (2.2445)	loss 2.8341 (3.4320)	grad_norm 1.6961 (1.6998)	
[2022-01-23 05:54:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][460/1251]	eta 0:29:34 lr 0.000375	time 1.5124 (2.2430)	loss 3.5997 (3.4367)	grad_norm 1.6149 (1.7030)	
[2022-01-23 05:54:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][470/1251]	eta 0:29:12 lr 0.000375	time 2.2679 (2.2444)	loss 4.0366 (3.4405)	grad_norm 1.4993 (1.7021)	
[2022-01-23 05:54:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][480/1251]	eta 0:28:46 lr 0.000375	time 2.1839 (2.2394)	loss 2.8508 (3.4449)	grad_norm 1.6506 (1.7017)	
[2022-01-23 05:55:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][490/1251]	eta 0:28:20 lr 0.000375	time 1.7034 (2.2350)	loss 3.7943 (3.4332)	grad_norm 1.6392 (1.7008)	
[2022-01-23 05:55:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][500/1251]	eta 0:27:58 lr 0.000375	time 2.2521 (2.2350)	loss 3.6298 (3.4381)	grad_norm 1.6221 (1.7011)	
[2022-01-23 05:55:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][510/1251]	eta 0:27:37 lr 0.000375	time 2.7360 (2.2371)	loss 2.4098 (3.4314)	grad_norm 1.7005 (1.6991)	
[2022-01-23 05:56:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][520/1251]	eta 0:27:16 lr 0.000375	time 2.7454 (2.2388)	loss 2.4846 (3.4317)	grad_norm 1.6754 (1.6984)	
[2022-01-23 05:56:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][530/1251]	eta 0:26:53 lr 0.000375	time 1.5445 (2.2380)	loss 3.1608 (3.4348)	grad_norm 1.7717 (1.6977)	
[2022-01-23 05:56:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][540/1251]	eta 0:26:28 lr 0.000375	time 1.5927 (2.2345)	loss 2.9365 (3.4394)	grad_norm 1.4699 (1.6984)	
[2022-01-23 05:57:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][550/1251]	eta 0:26:05 lr 0.000375	time 1.6633 (2.2333)	loss 3.6570 (3.4433)	grad_norm 1.5042 (1.6966)	
[2022-01-23 05:57:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][560/1251]	eta 0:25:40 lr 0.000375	time 2.2655 (2.2290)	loss 4.2439 (3.4417)	grad_norm 1.6480 (1.6959)	
[2022-01-23 05:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][570/1251]	eta 0:25:15 lr 0.000375	time 1.8543 (2.2261)	loss 2.5505 (3.4422)	grad_norm 1.5427 (1.6950)	
[2022-01-23 05:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][580/1251]	eta 0:24:53 lr 0.000375	time 2.1356 (2.2257)	loss 3.7049 (3.4458)	grad_norm 1.5314 (1.6951)	
[2022-01-23 05:58:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][590/1251]	eta 0:24:33 lr 0.000375	time 2.3540 (2.2292)	loss 3.5922 (3.4516)	grad_norm 1.5018 (1.6944)	
[2022-01-23 05:59:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][600/1251]	eta 0:24:11 lr 0.000374	time 1.9898 (2.2299)	loss 3.0941 (3.4509)	grad_norm 1.4473 (1.6935)	
[2022-01-23 05:59:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][610/1251]	eta 0:23:50 lr 0.000374	time 2.1282 (2.2310)	loss 3.3083 (3.4502)	grad_norm 1.7901 (1.6935)	
[2022-01-23 05:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][620/1251]	eta 0:23:25 lr 0.000374	time 1.7205 (2.2279)	loss 3.4472 (3.4525)	grad_norm 1.6601 (1.6933)	
[2022-01-23 06:00:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][630/1251]	eta 0:23:04 lr 0.000374	time 2.2578 (2.2297)	loss 2.4213 (3.4454)	grad_norm 1.5299 (1.6924)	
[2022-01-23 06:00:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][640/1251]	eta 0:22:40 lr 0.000374	time 1.5167 (2.2271)	loss 3.6347 (3.4455)	grad_norm 1.5329 (1.6919)	
[2022-01-23 06:00:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][650/1251]	eta 0:22:18 lr 0.000374	time 1.8727 (2.2264)	loss 3.6789 (3.4432)	grad_norm 1.4334 (1.6912)	
[2022-01-23 06:01:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][660/1251]	eta 0:21:55 lr 0.000374	time 2.0652 (2.2261)	loss 3.3460 (3.4425)	grad_norm 1.6981 (1.6903)	
[2022-01-23 06:01:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][670/1251]	eta 0:21:33 lr 0.000374	time 2.7653 (2.2259)	loss 3.6622 (3.4407)	grad_norm 1.6009 (1.6909)	
[2022-01-23 06:02:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][680/1251]	eta 0:21:10 lr 0.000374	time 1.9934 (2.2243)	loss 3.6943 (3.4418)	grad_norm 1.8572 (1.6900)	
[2022-01-23 06:02:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][690/1251]	eta 0:20:47 lr 0.000374	time 2.0653 (2.2236)	loss 3.3628 (3.4420)	grad_norm 2.0545 (1.6901)	
[2022-01-23 06:02:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][700/1251]	eta 0:20:24 lr 0.000374	time 1.9561 (2.2227)	loss 3.5265 (3.4400)	grad_norm 2.0177 (1.6906)	
[2022-01-23 06:03:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][710/1251]	eta 0:20:02 lr 0.000374	time 2.2501 (2.2228)	loss 3.4670 (3.4360)	grad_norm 1.5481 (1.6893)	
[2022-01-23 06:03:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][720/1251]	eta 0:19:39 lr 0.000374	time 2.4741 (2.2208)	loss 2.4951 (3.4360)	grad_norm 1.6066 (1.6890)	
[2022-01-23 06:03:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][730/1251]	eta 0:19:16 lr 0.000374	time 2.1992 (2.2199)	loss 2.4917 (3.4340)	grad_norm 1.5403 (1.6894)	
[2022-01-23 06:04:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][740/1251]	eta 0:18:53 lr 0.000374	time 2.0333 (2.2186)	loss 2.9997 (3.4342)	grad_norm 1.7593 (1.6901)	
[2022-01-23 06:04:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][750/1251]	eta 0:18:31 lr 0.000374	time 2.4672 (2.2195)	loss 3.6446 (3.4361)	grad_norm 1.6772 (1.6902)	
[2022-01-23 06:04:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][760/1251]	eta 0:18:09 lr 0.000374	time 1.4958 (2.2192)	loss 3.3176 (3.4361)	grad_norm 2.0769 (1.6918)	
[2022-01-23 06:05:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][770/1251]	eta 0:17:47 lr 0.000374	time 1.8434 (2.2194)	loss 3.2614 (3.4328)	grad_norm 1.5246 (1.6928)	
[2022-01-23 06:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][780/1251]	eta 0:17:25 lr 0.000374	time 2.2888 (2.2190)	loss 3.5172 (3.4332)	grad_norm 1.7300 (1.6944)	
[2022-01-23 06:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][790/1251]	eta 0:17:02 lr 0.000374	time 2.2196 (2.2181)	loss 3.3148 (3.4327)	grad_norm 1.6172 (1.6959)	
[2022-01-23 06:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][800/1251]	eta 0:16:41 lr 0.000374	time 3.0505 (2.2196)	loss 3.7604 (3.4338)	grad_norm 1.6177 (1.6948)	
[2022-01-23 06:06:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][810/1251]	eta 0:16:17 lr 0.000374	time 1.4921 (2.2173)	loss 3.7899 (3.4318)	grad_norm 1.6707 (1.6946)	
[2022-01-23 06:07:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][820/1251]	eta 0:15:56 lr 0.000374	time 2.4653 (2.2182)	loss 3.6590 (3.4329)	grad_norm 1.4150 (1.6955)	
[2022-01-23 06:07:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][830/1251]	eta 0:15:33 lr 0.000374	time 1.8376 (2.2172)	loss 4.2358 (3.4358)	grad_norm 2.1359 (1.6954)	
[2022-01-23 06:07:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][840/1251]	eta 0:15:11 lr 0.000374	time 2.7585 (2.2180)	loss 2.5869 (3.4310)	grad_norm 1.8489 (1.6958)	
[2022-01-23 06:08:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][850/1251]	eta 0:14:48 lr 0.000373	time 1.8672 (2.2161)	loss 3.7973 (3.4312)	grad_norm 1.5442 (1.6953)	
[2022-01-23 06:08:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][860/1251]	eta 0:14:26 lr 0.000373	time 2.7872 (2.2163)	loss 4.2242 (3.4351)	grad_norm 1.8639 (1.6961)	
[2022-01-23 06:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][870/1251]	eta 0:14:03 lr 0.000373	time 1.6158 (2.2147)	loss 3.9445 (3.4352)	grad_norm 1.8542 (1.6962)	
[2022-01-23 06:09:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][880/1251]	eta 0:13:41 lr 0.000373	time 1.8308 (2.2143)	loss 3.8800 (3.4364)	grad_norm 1.9913 (1.6971)	
[2022-01-23 06:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][890/1251]	eta 0:13:19 lr 0.000373	time 1.7134 (2.2136)	loss 3.4550 (3.4351)	grad_norm 1.7316 (1.6971)	
[2022-01-23 06:10:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][900/1251]	eta 0:12:57 lr 0.000373	time 2.6447 (2.2144)	loss 3.9594 (3.4339)	grad_norm 1.6373 (1.6970)	
[2022-01-23 06:10:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][910/1251]	eta 0:12:35 lr 0.000373	time 2.6616 (2.2141)	loss 3.3159 (3.4328)	grad_norm 1.4995 (1.6969)	
[2022-01-23 06:10:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][920/1251]	eta 0:12:13 lr 0.000373	time 1.8587 (2.2146)	loss 3.4678 (3.4329)	grad_norm 1.6763 (1.6968)	
[2022-01-23 06:11:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][930/1251]	eta 0:11:50 lr 0.000373	time 1.9003 (2.2136)	loss 4.0912 (3.4333)	grad_norm 1.6766 (1.6971)	
[2022-01-23 06:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][940/1251]	eta 0:11:28 lr 0.000373	time 1.7362 (2.2131)	loss 3.3457 (3.4328)	grad_norm 1.8496 (1.6986)	
[2022-01-23 06:11:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][950/1251]	eta 0:11:05 lr 0.000373	time 1.8052 (2.2120)	loss 3.5540 (3.4312)	grad_norm 1.4613 (1.6990)	
[2022-01-23 06:12:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][960/1251]	eta 0:10:43 lr 0.000373	time 1.8579 (2.2105)	loss 3.0253 (3.4291)	grad_norm 1.4932 (1.6992)	
[2022-01-23 06:12:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][970/1251]	eta 0:10:20 lr 0.000373	time 2.1125 (2.2086)	loss 2.9259 (3.4290)	grad_norm 1.6741 (1.6996)	
[2022-01-23 06:12:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][980/1251]	eta 0:09:58 lr 0.000373	time 1.5941 (2.2094)	loss 3.1454 (3.4292)	grad_norm 1.5978 (1.6994)	
[2022-01-23 06:13:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][990/1251]	eta 0:09:36 lr 0.000373	time 1.5800 (2.2079)	loss 2.4734 (3.4275)	grad_norm 2.2299 (1.6999)	
[2022-01-23 06:13:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1000/1251]	eta 0:09:14 lr 0.000373	time 2.5020 (2.2095)	loss 3.7648 (3.4266)	grad_norm 1.5615 (1.6999)	
[2022-01-23 06:14:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1010/1251]	eta 0:08:52 lr 0.000373	time 2.4617 (2.2105)	loss 4.1517 (3.4275)	grad_norm 1.4086 (1.6994)	
[2022-01-23 06:14:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1020/1251]	eta 0:08:30 lr 0.000373	time 1.8036 (2.2102)	loss 4.0904 (3.4307)	grad_norm 1.7249 (1.6990)	
[2022-01-23 06:14:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1030/1251]	eta 0:08:08 lr 0.000373	time 2.2297 (2.2102)	loss 2.8263 (3.4306)	grad_norm 1.5163 (1.6983)	
[2022-01-23 06:15:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1040/1251]	eta 0:07:46 lr 0.000373	time 2.3845 (2.2099)	loss 2.5336 (3.4285)	grad_norm 1.6241 (1.6981)	
[2022-01-23 06:15:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1050/1251]	eta 0:07:23 lr 0.000373	time 2.2398 (2.2085)	loss 2.3099 (3.4278)	grad_norm 1.8465 (1.6979)	
[2022-01-23 06:15:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1060/1251]	eta 0:07:01 lr 0.000373	time 1.8525 (2.2084)	loss 4.1088 (3.4277)	grad_norm 1.7264 (1.6977)	
[2022-01-23 06:16:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1070/1251]	eta 0:06:40 lr 0.000373	time 3.3267 (2.2103)	loss 3.8399 (3.4282)	grad_norm 1.4474 (1.6967)	
[2022-01-23 06:16:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1080/1251]	eta 0:06:17 lr 0.000373	time 1.8931 (2.2093)	loss 3.0178 (3.4279)	grad_norm 1.6313 (1.6957)	
[2022-01-23 06:16:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1090/1251]	eta 0:05:55 lr 0.000373	time 2.0002 (2.2078)	loss 3.6515 (3.4298)	grad_norm 1.7630 (1.6966)	
[2022-01-23 06:17:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1100/1251]	eta 0:05:33 lr 0.000372	time 1.7706 (2.2070)	loss 3.7274 (3.4311)	grad_norm 1.4942 (1.6966)	
[2022-01-23 06:17:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1110/1251]	eta 0:05:11 lr 0.000372	time 3.0313 (2.2090)	loss 3.9198 (3.4318)	grad_norm 1.6045 (1.6960)	
[2022-01-23 06:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1120/1251]	eta 0:04:49 lr 0.000372	time 2.0885 (2.2093)	loss 3.7353 (3.4318)	grad_norm 1.7192 (1.6960)	
[2022-01-23 06:18:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1130/1251]	eta 0:04:27 lr 0.000372	time 1.7631 (2.2087)	loss 3.9363 (3.4336)	grad_norm 1.7074 (1.6952)	
[2022-01-23 06:18:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1140/1251]	eta 0:04:05 lr 0.000372	time 1.8465 (2.2082)	loss 3.9483 (3.4328)	grad_norm 1.7622 (1.6946)	
[2022-01-23 06:19:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1150/1251]	eta 0:03:43 lr 0.000372	time 3.5190 (2.2094)	loss 4.1001 (3.4323)	grad_norm 1.8032 (1.6938)	
[2022-01-23 06:19:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1160/1251]	eta 0:03:21 lr 0.000372	time 1.8280 (2.2091)	loss 2.8687 (3.4312)	grad_norm 1.5572 (1.6935)	
[2022-01-23 06:19:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1170/1251]	eta 0:02:58 lr 0.000372	time 1.8582 (2.2082)	loss 3.9217 (3.4297)	grad_norm 1.4643 (1.6926)	
[2022-01-23 06:20:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1180/1251]	eta 0:02:36 lr 0.000372	time 1.5485 (2.2076)	loss 3.9976 (3.4295)	grad_norm 1.6795 (1.6918)	
[2022-01-23 06:20:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1190/1251]	eta 0:02:14 lr 0.000372	time 3.2279 (2.2084)	loss 2.8508 (3.4281)	grad_norm 1.5560 (1.6921)	
[2022-01-23 06:20:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1200/1251]	eta 0:01:52 lr 0.000372	time 1.9290 (2.2070)	loss 3.7462 (3.4282)	grad_norm 1.8142 (1.6921)	
[2022-01-23 06:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1210/1251]	eta 0:01:30 lr 0.000372	time 2.4712 (2.2073)	loss 3.6579 (3.4256)	grad_norm 1.7305 (1.6922)	
[2022-01-23 06:21:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1220/1251]	eta 0:01:08 lr 0.000372	time 1.6426 (2.2068)	loss 2.3069 (3.4254)	grad_norm 1.5709 (1.6919)	
[2022-01-23 06:22:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1230/1251]	eta 0:00:46 lr 0.000372	time 2.8152 (2.2074)	loss 3.9739 (3.4267)	grad_norm 1.7021 (1.6918)	
[2022-01-23 06:22:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1240/1251]	eta 0:00:24 lr 0.000372	time 1.7406 (2.2055)	loss 3.8946 (3.4258)	grad_norm 1.5015 (1.6914)	
[2022-01-23 06:22:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [175/300][1250/1251]	eta 0:00:02 lr 0.000372	time 1.2525 (2.1998)	loss 2.9574 (3.4269)	grad_norm 2.0807 (1.6923)	
[2022-01-23 06:22:39 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 175 training takes 0:45:52
[2022-01-23 06:22:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.991 (18.991)	Loss 0.9883 (0.9883)	Acc@1 78.320 (78.320)	Acc@5 92.969 (92.969)	
[2022-01-23 06:23:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.922 (3.278)	Loss 0.9238 (0.9842)	Acc@1 77.539 (77.317)	Acc@5 93.848 (93.333)	
[2022-01-23 06:23:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.570 (2.460)	Loss 1.0506 (0.9894)	Acc@1 74.902 (76.939)	Acc@5 92.676 (93.592)	
[2022-01-23 06:23:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.477 (2.221)	Loss 1.0203 (0.9756)	Acc@1 75.098 (77.142)	Acc@5 94.531 (93.800)	
[2022-01-23 06:24:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.052 (2.138)	Loss 0.9514 (0.9812)	Acc@1 76.953 (76.967)	Acc@5 93.848 (93.721)	
[2022-01-23 06:24:14 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.028 Acc@5 93.800
[2022-01-23 06:24:14 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.0%
[2022-01-23 06:24:14 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.15%
[2022-01-23 06:24:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][0/1251]	eta 7:31:24 lr 0.000372	time 21.6501 (21.6501)	loss 3.4045 (3.4045)	grad_norm 1.6495 (1.6495)	
[2022-01-23 06:24:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][10/1251]	eta 1:22:33 lr 0.000372	time 1.5781 (3.9918)	loss 2.8869 (3.3661)	grad_norm 1.5310 (1.6524)	
[2022-01-23 06:25:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][20/1251]	eta 1:04:43 lr 0.000372	time 1.3120 (3.1549)	loss 2.9993 (3.4521)	grad_norm 1.6903 (1.6548)	
[2022-01-23 06:25:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][30/1251]	eta 0:57:26 lr 0.000372	time 1.4730 (2.8227)	loss 3.5737 (3.3949)	grad_norm 1.5353 (1.6540)	
[2022-01-23 06:26:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][40/1251]	eta 0:53:56 lr 0.000372	time 3.5683 (2.6729)	loss 3.6430 (3.4073)	grad_norm 1.7453 (1.6661)	
[2022-01-23 06:26:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][50/1251]	eta 0:52:22 lr 0.000372	time 1.6005 (2.6164)	loss 3.3074 (3.4141)	grad_norm 1.5081 (1.6637)	
[2022-01-23 06:26:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][60/1251]	eta 0:50:44 lr 0.000372	time 1.5714 (2.5560)	loss 3.3382 (3.4218)	grad_norm 1.5186 (1.6582)	
[2022-01-23 06:27:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][70/1251]	eta 0:49:08 lr 0.000372	time 1.8119 (2.4970)	loss 3.2072 (3.4394)	grad_norm 1.5374 (1.6538)	
[2022-01-23 06:27:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][80/1251]	eta 0:48:01 lr 0.000372	time 2.8391 (2.4609)	loss 3.2898 (3.4402)	grad_norm 1.9096 (1.6671)	
[2022-01-23 06:27:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][90/1251]	eta 0:47:32 lr 0.000372	time 2.3920 (2.4572)	loss 3.3807 (3.4368)	grad_norm 1.7321 (1.6733)	
[2022-01-23 06:28:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][100/1251]	eta 0:46:35 lr 0.000371	time 1.6461 (2.4288)	loss 3.8518 (3.4576)	grad_norm 1.7414 (1.6829)	
[2022-01-23 06:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][110/1251]	eta 0:45:43 lr 0.000371	time 1.5119 (2.4046)	loss 2.4845 (3.4425)	grad_norm 1.8577 (1.6935)	
[2022-01-23 06:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][120/1251]	eta 0:44:52 lr 0.000371	time 2.2712 (2.3807)	loss 2.9629 (3.4303)	grad_norm 1.7233 (1.6947)	
[2022-01-23 06:29:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][130/1251]	eta 0:44:18 lr 0.000371	time 2.1923 (2.3717)	loss 4.1748 (3.4410)	grad_norm 1.8866 (1.6891)	
[2022-01-23 06:29:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][140/1251]	eta 0:43:33 lr 0.000371	time 2.1957 (2.3528)	loss 3.8763 (3.4432)	grad_norm 1.9526 (1.6917)	
[2022-01-23 06:30:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][150/1251]	eta 0:42:55 lr 0.000371	time 1.8992 (2.3389)	loss 3.2979 (3.4291)	grad_norm 1.9933 (1.7028)	
[2022-01-23 06:30:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][160/1251]	eta 0:42:22 lr 0.000371	time 1.7669 (2.3304)	loss 4.0353 (3.4228)	grad_norm 1.3726 (1.7057)	
[2022-01-23 06:30:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][170/1251]	eta 0:42:00 lr 0.000371	time 2.5416 (2.3319)	loss 3.9635 (3.4204)	grad_norm 1.6621 (1.7040)	
[2022-01-23 06:31:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][180/1251]	eta 0:41:39 lr 0.000371	time 2.9855 (2.3335)	loss 3.6492 (3.4277)	grad_norm 1.4479 (1.6962)	
[2022-01-23 06:31:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][190/1251]	eta 0:40:58 lr 0.000371	time 1.6136 (2.3172)	loss 3.1910 (3.4134)	grad_norm 1.6164 (1.6974)	
[2022-01-23 06:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][200/1251]	eta 0:40:23 lr 0.000371	time 1.8984 (2.3064)	loss 3.8297 (3.4098)	grad_norm 1.5801 (1.6989)	
[2022-01-23 06:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][210/1251]	eta 0:39:58 lr 0.000371	time 1.8330 (2.3036)	loss 3.9521 (3.4097)	grad_norm 1.7375 (1.7003)	
[2022-01-23 06:32:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][220/1251]	eta 0:39:25 lr 0.000371	time 1.9854 (2.2940)	loss 2.9558 (3.4047)	grad_norm 1.7538 (1.7065)	
[2022-01-23 06:33:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][230/1251]	eta 0:38:54 lr 0.000371	time 2.3000 (2.2867)	loss 2.8995 (3.4144)	grad_norm 1.5622 (1.7074)	
[2022-01-23 06:33:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][240/1251]	eta 0:38:20 lr 0.000371	time 1.9856 (2.2757)	loss 3.2999 (3.4075)	grad_norm 1.4698 (1.7116)	
[2022-01-23 06:33:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][250/1251]	eta 0:37:56 lr 0.000371	time 1.9510 (2.2738)	loss 3.2692 (3.4045)	grad_norm 2.8173 (1.7123)	
[2022-01-23 06:34:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][260/1251]	eta 0:37:32 lr 0.000371	time 2.6558 (2.2731)	loss 4.1274 (3.4165)	grad_norm 1.6397 (1.7167)	
[2022-01-23 06:34:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][270/1251]	eta 0:37:01 lr 0.000371	time 2.0753 (2.2649)	loss 4.0466 (3.4286)	grad_norm 1.6871 (1.7214)	
[2022-01-23 06:34:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][280/1251]	eta 0:36:32 lr 0.000371	time 2.2992 (2.2582)	loss 3.7181 (3.4312)	grad_norm 1.6611 (1.7180)	
[2022-01-23 06:35:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][290/1251]	eta 0:36:03 lr 0.000371	time 1.9265 (2.2508)	loss 3.5228 (3.4290)	grad_norm 2.3922 (1.7201)	
[2022-01-23 06:35:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][300/1251]	eta 0:35:39 lr 0.000371	time 2.8718 (2.2492)	loss 3.5015 (3.4199)	grad_norm 1.5466 (1.7207)	
[2022-01-23 06:35:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][310/1251]	eta 0:35:14 lr 0.000371	time 1.6020 (2.2467)	loss 3.4066 (3.4195)	grad_norm 1.5242 (1.7205)	
[2022-01-23 06:36:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][320/1251]	eta 0:34:55 lr 0.000371	time 2.4824 (2.2505)	loss 3.9904 (3.4303)	grad_norm 1.6940 (1.7197)	
[2022-01-23 06:36:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][330/1251]	eta 0:34:31 lr 0.000371	time 1.8589 (2.2491)	loss 4.0657 (3.4313)	grad_norm 1.6574 (1.7217)	
[2022-01-23 06:37:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][340/1251]	eta 0:34:05 lr 0.000371	time 2.7224 (2.2458)	loss 4.2698 (3.4414)	grad_norm 1.5769 (1.7226)	
[2022-01-23 06:37:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][350/1251]	eta 0:33:40 lr 0.000370	time 1.6142 (2.2429)	loss 3.7886 (3.4452)	grad_norm 1.5916 (1.7236)	
[2022-01-23 06:37:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][360/1251]	eta 0:33:19 lr 0.000370	time 2.4179 (2.2446)	loss 3.6875 (3.4481)	grad_norm 1.6397 (1.7225)	
[2022-01-23 06:38:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][370/1251]	eta 0:32:55 lr 0.000370	time 1.5856 (2.2423)	loss 3.9558 (3.4534)	grad_norm 1.9353 (1.7239)	
[2022-01-23 06:38:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][380/1251]	eta 0:32:32 lr 0.000370	time 2.9830 (2.2421)	loss 3.8102 (3.4491)	grad_norm 1.8534 (1.7237)	
[2022-01-23 06:38:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][390/1251]	eta 0:32:07 lr 0.000370	time 2.0230 (2.2392)	loss 2.7224 (3.4531)	grad_norm 1.9190 (1.7252)	
[2022-01-23 06:39:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][400/1251]	eta 0:31:45 lr 0.000370	time 2.7320 (2.2394)	loss 2.9651 (3.4523)	grad_norm 1.7071 (1.7239)	
[2022-01-23 06:39:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][410/1251]	eta 0:31:20 lr 0.000370	time 1.8425 (2.2362)	loss 2.9554 (3.4519)	grad_norm 1.6481 (1.7215)	
[2022-01-23 06:39:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][420/1251]	eta 0:30:54 lr 0.000370	time 2.3942 (2.2319)	loss 3.7189 (3.4539)	grad_norm 1.7276 (1.7224)	
[2022-01-23 06:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][430/1251]	eta 0:30:28 lr 0.000370	time 2.3686 (2.2267)	loss 2.8344 (3.4532)	grad_norm 1.8810 (1.7228)	
[2022-01-23 06:40:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][440/1251]	eta 0:30:05 lr 0.000370	time 2.5121 (2.2265)	loss 3.8032 (3.4556)	grad_norm 1.8109 (1.7219)	
[2022-01-23 06:40:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][450/1251]	eta 0:29:44 lr 0.000370	time 2.5037 (2.2277)	loss 3.8086 (3.4627)	grad_norm 1.5191 (1.7220)	
[2022-01-23 06:41:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][460/1251]	eta 0:29:20 lr 0.000370	time 1.8206 (2.2261)	loss 3.1284 (3.4601)	grad_norm 1.7728 (1.7212)	
[2022-01-23 06:41:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][470/1251]	eta 0:29:00 lr 0.000370	time 2.8704 (2.2286)	loss 3.8056 (3.4637)	grad_norm 1.8095 (1.7192)	
[2022-01-23 06:42:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][480/1251]	eta 0:28:38 lr 0.000370	time 2.4549 (2.2286)	loss 2.8589 (3.4623)	grad_norm 1.7426 (1.7179)	
[2022-01-23 06:42:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][490/1251]	eta 0:28:12 lr 0.000370	time 1.9053 (2.2245)	loss 2.5664 (3.4668)	grad_norm 1.7554 (1.7185)	
[2022-01-23 06:42:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][500/1251]	eta 0:27:47 lr 0.000370	time 2.2197 (2.2209)	loss 3.1185 (3.4676)	grad_norm 1.7217 (1.7176)	
[2022-01-23 06:43:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][510/1251]	eta 0:27:22 lr 0.000370	time 2.2770 (2.2173)	loss 2.5128 (3.4579)	grad_norm 1.4561 (1.7165)	
[2022-01-23 06:43:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][520/1251]	eta 0:27:02 lr 0.000370	time 2.1858 (2.2193)	loss 2.2411 (3.4539)	grad_norm 1.6651 (1.7184)	
[2022-01-23 06:43:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][530/1251]	eta 0:26:41 lr 0.000370	time 2.4644 (2.2210)	loss 3.6045 (3.4551)	grad_norm 1.7997 (1.7203)	
[2022-01-23 06:44:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][540/1251]	eta 0:26:18 lr 0.000370	time 2.4290 (2.2204)	loss 3.7994 (3.4620)	grad_norm 1.5460 (1.7202)	
[2022-01-23 06:44:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][550/1251]	eta 0:25:55 lr 0.000370	time 1.5837 (2.2185)	loss 3.9488 (3.4652)	grad_norm 1.6426 (1.7197)	
[2022-01-23 06:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][560/1251]	eta 0:25:31 lr 0.000370	time 2.3115 (2.2165)	loss 2.1424 (3.4591)	grad_norm 1.7932 (1.7176)	
[2022-01-23 06:45:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][570/1251]	eta 0:25:10 lr 0.000370	time 1.9409 (2.2174)	loss 3.6477 (3.4594)	grad_norm 2.0167 (1.7174)	
[2022-01-23 06:45:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][580/1251]	eta 0:24:47 lr 0.000370	time 2.1092 (2.2165)	loss 2.6906 (3.4580)	grad_norm 1.7140 (1.7158)	
[2022-01-23 06:46:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][590/1251]	eta 0:24:23 lr 0.000370	time 1.5780 (2.2145)	loss 2.9708 (3.4582)	grad_norm 1.8964 (1.7164)	
[2022-01-23 06:46:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][600/1251]	eta 0:24:00 lr 0.000369	time 2.1140 (2.2129)	loss 3.2069 (3.4591)	grad_norm 1.7304 (1.7148)	
[2022-01-23 06:46:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][610/1251]	eta 0:23:37 lr 0.000369	time 2.4580 (2.2119)	loss 3.7325 (3.4557)	grad_norm 1.8308 (1.7135)	
[2022-01-23 06:47:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][620/1251]	eta 0:23:15 lr 0.000369	time 2.2893 (2.2112)	loss 3.4704 (3.4523)	grad_norm 1.7937 (1.7121)	
[2022-01-23 06:47:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][630/1251]	eta 0:22:52 lr 0.000369	time 2.1941 (2.2104)	loss 3.3939 (3.4506)	grad_norm 1.5655 (1.7112)	
[2022-01-23 06:47:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][640/1251]	eta 0:22:28 lr 0.000369	time 2.1003 (2.2077)	loss 2.1879 (3.4480)	grad_norm 1.8823 (1.7099)	
[2022-01-23 06:48:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][650/1251]	eta 0:22:07 lr 0.000369	time 1.8407 (2.2094)	loss 2.7706 (3.4522)	grad_norm 1.5360 (1.7083)	
[2022-01-23 06:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][660/1251]	eta 0:21:46 lr 0.000369	time 2.4959 (2.2099)	loss 3.9790 (3.4527)	grad_norm 1.8953 (1.7096)	
[2022-01-23 06:48:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][670/1251]	eta 0:21:24 lr 0.000369	time 2.0917 (2.2103)	loss 2.3947 (3.4513)	grad_norm 1.6066 (1.7094)	
[2022-01-23 06:49:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][680/1251]	eta 0:21:03 lr 0.000369	time 2.7258 (2.2119)	loss 2.8663 (3.4505)	grad_norm 1.7184 (1.7106)	
[2022-01-23 06:49:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][690/1251]	eta 0:20:40 lr 0.000369	time 1.5214 (2.2106)	loss 4.2640 (3.4523)	grad_norm 1.5803 (1.7116)	
[2022-01-23 06:50:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][700/1251]	eta 0:20:17 lr 0.000369	time 2.2327 (2.2089)	loss 2.4843 (3.4496)	grad_norm 1.7560 (1.7116)	
[2022-01-23 06:50:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][710/1251]	eta 0:19:54 lr 0.000369	time 2.2642 (2.2081)	loss 2.4225 (3.4490)	grad_norm 1.6303 (1.7112)	
[2022-01-23 06:50:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][720/1251]	eta 0:19:33 lr 0.000369	time 2.8369 (2.2092)	loss 3.9321 (3.4502)	grad_norm 2.1965 (1.7119)	
[2022-01-23 06:51:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][730/1251]	eta 0:19:11 lr 0.000369	time 2.1274 (2.2104)	loss 2.7633 (3.4489)	grad_norm 1.7117 (1.7117)	
[2022-01-23 06:51:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][740/1251]	eta 0:18:49 lr 0.000369	time 2.8733 (2.2099)	loss 3.9215 (3.4483)	grad_norm 1.5660 (1.7108)	
[2022-01-23 06:51:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][750/1251]	eta 0:18:25 lr 0.000369	time 1.8887 (2.2070)	loss 3.6929 (3.4482)	grad_norm 1.6667 (1.7103)	
[2022-01-23 06:52:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][760/1251]	eta 0:18:02 lr 0.000369	time 2.2181 (2.2056)	loss 3.5220 (3.4485)	grad_norm 1.9087 (1.7096)	
[2022-01-23 06:52:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][770/1251]	eta 0:17:40 lr 0.000369	time 1.7743 (2.2053)	loss 2.9695 (3.4460)	grad_norm 1.5604 (1.7081)	
[2022-01-23 06:52:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][780/1251]	eta 0:17:19 lr 0.000369	time 2.7246 (2.2063)	loss 3.3106 (3.4449)	grad_norm 1.6441 (1.7086)	
[2022-01-23 06:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][790/1251]	eta 0:16:57 lr 0.000369	time 1.9156 (2.2064)	loss 2.1886 (3.4425)	grad_norm 1.8228 (1.7086)	
[2022-01-23 06:53:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][800/1251]	eta 0:16:35 lr 0.000369	time 1.5220 (2.2064)	loss 2.3501 (3.4452)	grad_norm 1.7397 (1.7093)	
[2022-01-23 06:54:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][810/1251]	eta 0:16:14 lr 0.000369	time 1.9492 (2.2090)	loss 3.3843 (3.4418)	grad_norm 1.6440 (1.7083)	
[2022-01-23 06:54:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][820/1251]	eta 0:15:52 lr 0.000369	time 2.1505 (2.2091)	loss 2.5683 (3.4420)	grad_norm 1.9285 (1.7080)	
[2022-01-23 06:54:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][830/1251]	eta 0:15:29 lr 0.000369	time 1.9373 (2.2090)	loss 3.3461 (3.4439)	grad_norm 1.6889 (1.7084)	
[2022-01-23 06:55:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][840/1251]	eta 0:15:06 lr 0.000369	time 1.7157 (2.2064)	loss 2.3651 (3.4406)	grad_norm 1.8393 (1.7084)	
[2022-01-23 06:55:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][850/1251]	eta 0:14:44 lr 0.000368	time 2.0525 (2.2059)	loss 3.7886 (3.4362)	grad_norm 1.7212 (1.7070)	
[2022-01-23 06:55:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][860/1251]	eta 0:14:22 lr 0.000368	time 2.3033 (2.2047)	loss 3.6973 (3.4396)	grad_norm 1.8832 (1.7085)	
[2022-01-23 06:56:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][870/1251]	eta 0:13:59 lr 0.000368	time 1.8635 (2.2040)	loss 3.4918 (3.4377)	grad_norm 1.5754 (1.7077)	
[2022-01-23 06:56:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][880/1251]	eta 0:13:37 lr 0.000368	time 2.0889 (2.2035)	loss 2.8499 (3.4388)	grad_norm 2.0130 (1.7083)	
[2022-01-23 06:56:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][890/1251]	eta 0:13:15 lr 0.000368	time 2.1464 (2.2043)	loss 2.5454 (3.4388)	grad_norm 2.5137 (1.7116)	
[2022-01-23 06:57:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][900/1251]	eta 0:12:53 lr 0.000368	time 2.2766 (2.2035)	loss 3.2038 (3.4358)	grad_norm 1.5740 (1.7113)	
[2022-01-23 06:57:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][910/1251]	eta 0:12:31 lr 0.000368	time 2.1734 (2.2035)	loss 2.2682 (3.4344)	grad_norm 1.5984 (1.7099)	
[2022-01-23 06:58:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][920/1251]	eta 0:12:08 lr 0.000368	time 1.8540 (2.2023)	loss 3.5029 (3.4369)	grad_norm 1.4817 (1.7085)	
[2022-01-23 06:58:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][930/1251]	eta 0:11:46 lr 0.000368	time 1.7188 (2.2015)	loss 3.5960 (3.4360)	grad_norm 1.7812 (1.7091)	
[2022-01-23 06:58:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][940/1251]	eta 0:11:25 lr 0.000368	time 2.5614 (2.2027)	loss 3.8873 (3.4380)	grad_norm 1.7955 (1.7096)	
[2022-01-23 06:59:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][950/1251]	eta 0:11:02 lr 0.000368	time 1.6966 (2.2017)	loss 3.3945 (3.4388)	grad_norm 1.8035 (1.7106)	
[2022-01-23 06:59:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][960/1251]	eta 0:10:40 lr 0.000368	time 2.4912 (2.2016)	loss 3.6999 (3.4377)	grad_norm 1.5672 (1.7121)	
[2022-01-23 06:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][970/1251]	eta 0:10:18 lr 0.000368	time 1.7416 (2.2002)	loss 3.8199 (3.4390)	grad_norm 1.9689 (1.7124)	
[2022-01-23 07:00:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][980/1251]	eta 0:09:56 lr 0.000368	time 2.2350 (2.1994)	loss 2.5256 (3.4375)	grad_norm 1.5893 (1.7121)	
[2022-01-23 07:00:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][990/1251]	eta 0:09:33 lr 0.000368	time 1.9021 (2.1972)	loss 2.5954 (3.4375)	grad_norm 1.6863 (1.7125)	
[2022-01-23 07:00:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1000/1251]	eta 0:09:11 lr 0.000368	time 2.1982 (2.1970)	loss 3.7899 (3.4378)	grad_norm 1.8721 (1.7123)	
[2022-01-23 07:01:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1010/1251]	eta 0:08:49 lr 0.000368	time 1.8693 (2.1967)	loss 3.8948 (3.4384)	grad_norm 1.6587 (1.7120)	
[2022-01-23 07:01:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1020/1251]	eta 0:08:27 lr 0.000368	time 1.6999 (2.1970)	loss 3.0707 (3.4381)	grad_norm 1.7157 (1.7121)	
[2022-01-23 07:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1030/1251]	eta 0:08:05 lr 0.000368	time 2.0926 (2.1979)	loss 3.8218 (3.4391)	grad_norm 1.9733 (1.7119)	
[2022-01-23 07:02:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1040/1251]	eta 0:07:44 lr 0.000368	time 2.7334 (2.1997)	loss 3.8167 (3.4384)	grad_norm 2.0807 (1.7125)	
[2022-01-23 07:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1050/1251]	eta 0:07:22 lr 0.000368	time 1.5996 (2.2003)	loss 4.0993 (3.4392)	grad_norm 1.7870 (1.7131)	
[2022-01-23 07:03:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1060/1251]	eta 0:07:00 lr 0.000368	time 1.5597 (2.2014)	loss 3.7649 (3.4402)	grad_norm 1.4855 (1.7134)	
[2022-01-23 07:03:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1070/1251]	eta 0:06:38 lr 0.000368	time 1.9283 (2.2007)	loss 3.5156 (3.4391)	grad_norm 1.9106 (1.7132)	
[2022-01-23 07:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1080/1251]	eta 0:06:16 lr 0.000368	time 2.7988 (2.2005)	loss 3.7346 (3.4399)	grad_norm 1.7873 (1.7131)	
[2022-01-23 07:04:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1090/1251]	eta 0:05:54 lr 0.000368	time 1.8506 (2.1998)	loss 3.7383 (3.4397)	grad_norm 1.5436 (1.7128)	
[2022-01-23 07:04:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1100/1251]	eta 0:05:32 lr 0.000368	time 2.2196 (2.2001)	loss 3.2164 (3.4379)	grad_norm 1.7830 (1.7129)	
[2022-01-23 07:04:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1110/1251]	eta 0:05:10 lr 0.000367	time 1.8099 (2.2000)	loss 3.9619 (3.4388)	grad_norm 1.6708 (1.7130)	
[2022-01-23 07:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1120/1251]	eta 0:04:48 lr 0.000367	time 2.1814 (2.1999)	loss 4.2662 (3.4370)	grad_norm 1.9479 (1.7129)	
[2022-01-23 07:05:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1130/1251]	eta 0:04:26 lr 0.000367	time 2.2195 (2.1983)	loss 3.7033 (3.4386)	grad_norm 1.7159 (1.7129)	
[2022-01-23 07:06:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1140/1251]	eta 0:04:04 lr 0.000367	time 1.8888 (2.1983)	loss 3.6600 (3.4397)	grad_norm 2.1659 (1.7130)	
[2022-01-23 07:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1150/1251]	eta 0:03:42 lr 0.000367	time 2.0301 (2.1980)	loss 3.0496 (3.4381)	grad_norm 1.6961 (1.7123)	
[2022-01-23 07:06:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1160/1251]	eta 0:03:20 lr 0.000367	time 2.1403 (2.1984)	loss 2.6243 (3.4361)	grad_norm 1.6349 (1.7121)	
[2022-01-23 07:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1170/1251]	eta 0:02:58 lr 0.000367	time 2.0769 (2.1994)	loss 3.5127 (3.4380)	grad_norm 1.8873 (1.7121)	
[2022-01-23 07:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1180/1251]	eta 0:02:36 lr 0.000367	time 1.9053 (2.2008)	loss 3.1817 (3.4378)	grad_norm 1.5956 (1.7127)	
[2022-01-23 07:07:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1190/1251]	eta 0:02:14 lr 0.000367	time 1.9648 (2.1992)	loss 3.6113 (3.4351)	grad_norm 1.9026 (1.7133)	
[2022-01-23 07:08:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1200/1251]	eta 0:01:52 lr 0.000367	time 2.4946 (2.1987)	loss 2.5985 (3.4343)	grad_norm 1.5497 (1.7128)	
[2022-01-23 07:08:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1210/1251]	eta 0:01:30 lr 0.000367	time 2.2432 (2.1977)	loss 2.9561 (3.4334)	grad_norm 1.4768 (1.7121)	
[2022-01-23 07:08:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1220/1251]	eta 0:01:08 lr 0.000367	time 2.0809 (2.1979)	loss 3.9374 (3.4339)	grad_norm 1.6123 (1.7117)	
[2022-01-23 07:09:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1230/1251]	eta 0:00:46 lr 0.000367	time 1.6916 (2.1985)	loss 2.7253 (3.4348)	grad_norm 1.4801 (1.7118)	
[2022-01-23 07:09:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1240/1251]	eta 0:00:24 lr 0.000367	time 1.4595 (2.1968)	loss 3.7357 (3.4337)	grad_norm 1.8397 (1.7123)	
[2022-01-23 07:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [176/300][1250/1251]	eta 0:00:02 lr 0.000367	time 1.3171 (2.1911)	loss 2.5178 (3.4337)	grad_norm 1.5529 (1.7133)	
[2022-01-23 07:09:55 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 176 training takes 0:45:41
[2022-01-23 07:10:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.401 (18.401)	Loss 0.9359 (0.9359)	Acc@1 77.539 (77.539)	Acc@5 93.945 (93.945)	
[2022-01-23 07:10:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.217 (3.372)	Loss 0.9308 (0.9478)	Acc@1 77.930 (77.583)	Acc@5 93.945 (94.114)	
[2022-01-23 07:10:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.959 (2.625)	Loss 0.9905 (0.9575)	Acc@1 76.270 (77.534)	Acc@5 92.285 (93.936)	
[2022-01-23 07:11:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.629 (2.236)	Loss 0.9919 (0.9696)	Acc@1 76.172 (77.293)	Acc@5 94.336 (93.791)	
[2022-01-23 07:11:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.760 (2.198)	Loss 0.9321 (0.9703)	Acc@1 78.320 (77.272)	Acc@5 94.531 (93.848)	
[2022-01-23 07:11:33 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.234 Acc@5 93.844
[2022-01-23 07:11:33 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.2%
[2022-01-23 07:11:33 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.23%
[2022-01-23 07:11:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][0/1251]	eta 8:29:47 lr 0.000367	time 24.4504 (24.4504)	loss 4.1515 (4.1515)	grad_norm 2.0056 (2.0056)	
[2022-01-23 07:12:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][10/1251]	eta 1:28:17 lr 0.000367	time 2.1887 (4.2688)	loss 2.9427 (3.4564)	grad_norm 1.4442 (1.7108)	
[2022-01-23 07:12:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][20/1251]	eta 1:08:25 lr 0.000367	time 1.8854 (3.3349)	loss 3.8548 (3.4855)	grad_norm 1.6971 (1.6813)	
[2022-01-23 07:13:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][30/1251]	eta 0:59:48 lr 0.000367	time 1.5845 (2.9392)	loss 2.4987 (3.3978)	grad_norm 1.7357 (1.6769)	
[2022-01-23 07:13:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][40/1251]	eta 0:56:26 lr 0.000367	time 3.8707 (2.7967)	loss 3.1863 (3.4092)	grad_norm 1.8119 (1.7290)	
[2022-01-23 07:13:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][50/1251]	eta 0:53:45 lr 0.000367	time 2.1889 (2.6854)	loss 2.2134 (3.3752)	grad_norm 1.9295 (1.7142)	
[2022-01-23 07:14:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][60/1251]	eta 0:51:32 lr 0.000367	time 2.5416 (2.5962)	loss 2.6185 (3.4135)	grad_norm 1.5763 (1.7070)	
[2022-01-23 07:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][70/1251]	eta 0:49:45 lr 0.000367	time 1.8973 (2.5282)	loss 3.7171 (3.4121)	grad_norm 1.9330 (1.7216)	
[2022-01-23 07:14:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][80/1251]	eta 0:48:17 lr 0.000367	time 1.8221 (2.4742)	loss 3.0137 (3.4310)	grad_norm 1.6628 (1.7148)	
[2022-01-23 07:15:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][90/1251]	eta 0:47:30 lr 0.000367	time 2.2021 (2.4550)	loss 4.0711 (3.4510)	grad_norm 1.6920 (1.7144)	
[2022-01-23 07:15:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][100/1251]	eta 0:46:39 lr 0.000367	time 2.4826 (2.4321)	loss 2.9462 (3.4087)	grad_norm 1.8777 (1.7149)	
[2022-01-23 07:16:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][110/1251]	eta 0:45:50 lr 0.000366	time 1.9056 (2.4107)	loss 4.1492 (3.4062)	grad_norm 1.6320 (1.7079)	
[2022-01-23 07:16:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][120/1251]	eta 0:45:02 lr 0.000366	time 1.9000 (2.3890)	loss 2.2806 (3.4037)	grad_norm 1.6999 (1.7052)	
[2022-01-23 07:16:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][130/1251]	eta 0:44:26 lr 0.000366	time 2.0721 (2.3787)	loss 3.3408 (3.4100)	grad_norm 1.9084 (1.7090)	
[2022-01-23 07:17:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][140/1251]	eta 0:43:53 lr 0.000366	time 3.0407 (2.3699)	loss 4.2182 (3.4011)	grad_norm 1.7846 (1.7166)	
[2022-01-23 07:17:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][150/1251]	eta 0:43:20 lr 0.000366	time 1.9340 (2.3623)	loss 4.0825 (3.4034)	grad_norm 1.8065 (1.7165)	
[2022-01-23 07:17:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][160/1251]	eta 0:42:39 lr 0.000366	time 1.5547 (2.3463)	loss 2.6195 (3.4041)	grad_norm 1.7496 (1.7266)	
[2022-01-23 07:18:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][170/1251]	eta 0:41:58 lr 0.000366	time 1.8077 (2.3302)	loss 3.9927 (3.4127)	grad_norm 1.5473 (1.7236)	
[2022-01-23 07:18:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][180/1251]	eta 0:41:23 lr 0.000366	time 2.7183 (2.3193)	loss 3.8364 (3.4237)	grad_norm 2.0024 (1.7249)	
[2022-01-23 07:18:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][190/1251]	eta 0:40:57 lr 0.000366	time 1.9152 (2.3167)	loss 3.1856 (3.4241)	grad_norm 1.5124 (1.7228)	
[2022-01-23 07:19:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][200/1251]	eta 0:40:24 lr 0.000366	time 1.8835 (2.3069)	loss 3.5774 (3.4261)	grad_norm 1.6273 (1.7226)	
[2022-01-23 07:19:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][210/1251]	eta 0:39:55 lr 0.000366	time 2.2729 (2.3014)	loss 3.3074 (3.4366)	grad_norm 1.5400 (1.7216)	
[2022-01-23 07:19:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][220/1251]	eta 0:39:22 lr 0.000366	time 2.3153 (2.2918)	loss 4.4247 (3.4515)	grad_norm 1.8654 (1.7184)	
[2022-01-23 07:20:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][230/1251]	eta 0:38:51 lr 0.000366	time 2.0601 (2.2839)	loss 3.9355 (3.4571)	grad_norm 1.7519 (1.7174)	
[2022-01-23 07:20:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][240/1251]	eta 0:38:21 lr 0.000366	time 1.5078 (2.2769)	loss 3.5130 (3.4625)	grad_norm 1.7453 (1.7194)	
[2022-01-23 07:21:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][250/1251]	eta 0:37:53 lr 0.000366	time 1.9226 (2.2709)	loss 2.6381 (3.4526)	grad_norm 1.6958 (1.7213)	
[2022-01-23 07:21:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][260/1251]	eta 0:37:24 lr 0.000366	time 2.1311 (2.2647)	loss 3.9428 (3.4555)	grad_norm 1.7800 (1.7198)	
[2022-01-23 07:21:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][270/1251]	eta 0:36:58 lr 0.000366	time 2.2463 (2.2618)	loss 3.5148 (3.4606)	grad_norm 1.5362 (1.7184)	
[2022-01-23 07:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][280/1251]	eta 0:36:38 lr 0.000366	time 1.8598 (2.2644)	loss 3.5739 (3.4508)	grad_norm 1.5224 (1.7153)	
[2022-01-23 07:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][290/1251]	eta 0:36:14 lr 0.000366	time 1.8432 (2.2629)	loss 3.7779 (3.4521)	grad_norm 1.6534 (1.7116)	
[2022-01-23 07:22:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][300/1251]	eta 0:35:50 lr 0.000366	time 1.5578 (2.2614)	loss 3.9307 (3.4557)	grad_norm 1.4593 (1.7096)	
[2022-01-23 07:23:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][310/1251]	eta 0:35:28 lr 0.000366	time 2.6040 (2.2617)	loss 2.5430 (3.4375)	grad_norm 1.7031 (1.7059)	
[2022-01-23 07:23:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][320/1251]	eta 0:35:08 lr 0.000366	time 1.8315 (2.2652)	loss 2.8362 (3.4342)	grad_norm 1.6472 (1.7031)	
[2022-01-23 07:24:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][330/1251]	eta 0:34:45 lr 0.000366	time 2.3653 (2.2641)	loss 3.8703 (3.4254)	grad_norm 1.6356 (1.7033)	
[2022-01-23 07:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][340/1251]	eta 0:34:18 lr 0.000366	time 1.6610 (2.2596)	loss 2.7996 (3.4244)	grad_norm 1.5527 (1.7034)	
[2022-01-23 07:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][350/1251]	eta 0:33:49 lr 0.000366	time 1.9278 (2.2527)	loss 3.9208 (3.4157)	grad_norm 1.8000 (1.7011)	
[2022-01-23 07:25:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][360/1251]	eta 0:33:27 lr 0.000365	time 2.1604 (2.2533)	loss 3.5321 (3.4114)	grad_norm 1.7248 (1.7046)	
[2022-01-23 07:25:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][370/1251]	eta 0:33:04 lr 0.000365	time 2.3677 (2.2520)	loss 4.0150 (3.4114)	grad_norm 2.0426 (1.7073)	
[2022-01-23 07:25:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][380/1251]	eta 0:32:42 lr 0.000365	time 2.1818 (2.2532)	loss 3.6254 (3.4076)	grad_norm 1.8041 (1.7051)	
[2022-01-23 07:26:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][390/1251]	eta 0:32:18 lr 0.000365	time 2.2071 (2.2512)	loss 3.6088 (3.4117)	grad_norm 1.6521 (1.7044)	
[2022-01-23 07:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][400/1251]	eta 0:31:53 lr 0.000365	time 2.6862 (2.2482)	loss 3.7737 (3.4091)	grad_norm 2.2353 (1.7082)	
[2022-01-23 07:26:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][410/1251]	eta 0:31:24 lr 0.000365	time 1.7398 (2.2413)	loss 3.8536 (3.4101)	grad_norm 1.8839 (1.7100)	
[2022-01-23 07:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][420/1251]	eta 0:31:02 lr 0.000365	time 2.5604 (2.2414)	loss 2.9995 (3.4106)	grad_norm 1.7127 (1.7126)	
[2022-01-23 07:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][430/1251]	eta 0:30:36 lr 0.000365	time 2.2759 (2.2371)	loss 3.6390 (3.4139)	grad_norm 1.5630 (1.7121)	
[2022-01-23 07:27:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][440/1251]	eta 0:30:10 lr 0.000365	time 2.2253 (2.2323)	loss 3.4872 (3.4161)	grad_norm 1.6783 (1.7100)	
[2022-01-23 07:28:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][450/1251]	eta 0:29:46 lr 0.000365	time 2.5774 (2.2306)	loss 3.4195 (3.4166)	grad_norm 1.7287 (1.7114)	
[2022-01-23 07:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][460/1251]	eta 0:29:24 lr 0.000365	time 2.6253 (2.2307)	loss 3.6812 (3.4112)	grad_norm 1.6587 (1.7096)	
[2022-01-23 07:29:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][470/1251]	eta 0:29:03 lr 0.000365	time 2.5487 (2.2330)	loss 3.1272 (3.4097)	grad_norm 1.8492 (1.7081)	
[2022-01-23 07:29:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][480/1251]	eta 0:28:40 lr 0.000365	time 2.1160 (2.2322)	loss 2.2419 (3.4078)	grad_norm 1.7435 (1.7079)	
[2022-01-23 07:29:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][490/1251]	eta 0:28:19 lr 0.000365	time 2.1159 (2.2326)	loss 3.1667 (3.4059)	grad_norm 1.7807 (1.7088)	
[2022-01-23 07:30:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][500/1251]	eta 0:27:56 lr 0.000365	time 2.5240 (2.2319)	loss 3.7274 (3.4071)	grad_norm 1.4898 (1.7086)	
[2022-01-23 07:30:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][510/1251]	eta 0:27:32 lr 0.000365	time 2.3412 (2.2305)	loss 3.7942 (3.4099)	grad_norm 1.7329 (1.7085)	
[2022-01-23 07:30:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][520/1251]	eta 0:27:09 lr 0.000365	time 2.0665 (2.2287)	loss 4.0356 (3.4166)	grad_norm 1.9756 (1.7116)	
[2022-01-23 07:31:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][530/1251]	eta 0:26:44 lr 0.000365	time 2.6304 (2.2250)	loss 3.5082 (3.4163)	grad_norm 1.6998 (1.7120)	
[2022-01-23 07:31:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][540/1251]	eta 0:26:20 lr 0.000365	time 2.9570 (2.2228)	loss 2.7828 (3.4172)	grad_norm 1.5380 (1.7123)	
[2022-01-23 07:31:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][550/1251]	eta 0:25:56 lr 0.000365	time 2.7099 (2.2210)	loss 2.7382 (3.4217)	grad_norm 1.8767 (1.7127)	
[2022-01-23 07:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][560/1251]	eta 0:25:34 lr 0.000365	time 1.5484 (2.2202)	loss 3.3894 (3.4248)	grad_norm 1.8881 (1.7119)	
[2022-01-23 07:32:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][570/1251]	eta 0:25:13 lr 0.000365	time 2.4795 (2.2230)	loss 3.9188 (3.4276)	grad_norm 1.7389 (1.7114)	
[2022-01-23 07:33:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][580/1251]	eta 0:24:53 lr 0.000365	time 2.8161 (2.2251)	loss 3.4836 (3.4329)	grad_norm 1.6891 (1.7106)	
[2022-01-23 07:33:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][590/1251]	eta 0:24:30 lr 0.000365	time 2.5832 (2.2241)	loss 3.3273 (3.4330)	grad_norm 1.7122 (1.7106)	
[2022-01-23 07:33:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][600/1251]	eta 0:24:07 lr 0.000365	time 2.1646 (2.2231)	loss 4.0226 (3.4343)	grad_norm 1.4393 (1.7102)	
[2022-01-23 07:34:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][610/1251]	eta 0:23:42 lr 0.000364	time 1.9616 (2.2188)	loss 3.4119 (3.4303)	grad_norm 1.7938 (1.7115)	
[2022-01-23 07:34:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][620/1251]	eta 0:23:18 lr 0.000364	time 2.7586 (2.2161)	loss 3.7910 (3.4328)	grad_norm 1.7940 (1.7126)	
[2022-01-23 07:34:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][630/1251]	eta 0:22:55 lr 0.000364	time 2.4073 (2.2153)	loss 4.1325 (3.4347)	grad_norm 1.7021 (1.7142)	
[2022-01-23 07:35:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][640/1251]	eta 0:22:33 lr 0.000364	time 2.5853 (2.2159)	loss 3.7300 (3.4404)	grad_norm 1.5281 (1.7136)	
[2022-01-23 07:35:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][650/1251]	eta 0:22:12 lr 0.000364	time 2.4784 (2.2172)	loss 4.0695 (3.4432)	grad_norm 1.5731 (1.7148)	
[2022-01-23 07:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][660/1251]	eta 0:21:49 lr 0.000364	time 2.2738 (2.2163)	loss 3.1850 (3.4413)	grad_norm 1.6461 (1.7146)	
[2022-01-23 07:36:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][670/1251]	eta 0:21:26 lr 0.000364	time 1.8374 (2.2149)	loss 3.5413 (3.4414)	grad_norm 1.5738 (1.7137)	
[2022-01-23 07:36:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][680/1251]	eta 0:21:05 lr 0.000364	time 2.7962 (2.2171)	loss 2.7181 (3.4393)	grad_norm 2.0763 (1.7176)	
[2022-01-23 07:37:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][690/1251]	eta 0:20:44 lr 0.000364	time 1.8750 (2.2186)	loss 3.3633 (3.4389)	grad_norm 1.8398 (1.7172)	
[2022-01-23 07:37:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][700/1251]	eta 0:20:22 lr 0.000364	time 1.9937 (2.2188)	loss 2.3749 (3.4391)	grad_norm 1.6588 (1.7183)	
[2022-01-23 07:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][710/1251]	eta 0:19:59 lr 0.000364	time 1.7857 (2.2164)	loss 3.8165 (3.4425)	grad_norm 1.7605 (1.7170)	
[2022-01-23 07:38:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][720/1251]	eta 0:19:35 lr 0.000364	time 1.9092 (2.2135)	loss 3.6570 (3.4434)	grad_norm 1.6808 (1.7170)	
[2022-01-23 07:38:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][730/1251]	eta 0:19:12 lr 0.000364	time 2.1546 (2.2120)	loss 2.6233 (3.4408)	grad_norm 1.7443 (1.7176)	
[2022-01-23 07:38:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][740/1251]	eta 0:18:50 lr 0.000364	time 1.5999 (2.2117)	loss 3.5983 (3.4418)	grad_norm 1.3793 (1.7164)	
[2022-01-23 07:39:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][750/1251]	eta 0:18:29 lr 0.000364	time 1.5629 (2.2143)	loss 3.7706 (3.4395)	grad_norm 1.6283 (1.7160)	
[2022-01-23 07:39:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][760/1251]	eta 0:18:07 lr 0.000364	time 2.2472 (2.2153)	loss 3.7856 (3.4379)	grad_norm 1.8220 (1.7164)	
[2022-01-23 07:40:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][770/1251]	eta 0:17:45 lr 0.000364	time 2.7813 (2.2159)	loss 3.4322 (3.4375)	grad_norm 1.6850 (1.7160)	
[2022-01-23 07:40:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][780/1251]	eta 0:17:23 lr 0.000364	time 1.7872 (2.2158)	loss 2.8584 (3.4355)	grad_norm 1.7857 (1.7169)	
[2022-01-23 07:40:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][790/1251]	eta 0:17:00 lr 0.000364	time 1.5982 (2.2138)	loss 2.6266 (3.4375)	grad_norm 1.5669 (1.7171)	
[2022-01-23 07:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][800/1251]	eta 0:16:37 lr 0.000364	time 1.8964 (2.2121)	loss 3.6584 (3.4388)	grad_norm 1.5971 (1.7163)	
[2022-01-23 07:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][810/1251]	eta 0:16:14 lr 0.000364	time 2.4763 (2.2103)	loss 2.3630 (3.4398)	grad_norm 1.5230 (1.7171)	
[2022-01-23 07:41:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][820/1251]	eta 0:15:51 lr 0.000364	time 1.5785 (2.2083)	loss 2.7823 (3.4388)	grad_norm 1.7941 (1.7164)	
[2022-01-23 07:42:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][830/1251]	eta 0:15:29 lr 0.000364	time 2.1866 (2.2078)	loss 3.5045 (3.4373)	grad_norm 1.5516 (1.7159)	
[2022-01-23 07:42:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][840/1251]	eta 0:15:07 lr 0.000364	time 1.9071 (2.2077)	loss 3.8971 (3.4339)	grad_norm 1.6148 (1.7147)	
[2022-01-23 07:42:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][850/1251]	eta 0:14:45 lr 0.000364	time 2.4702 (2.2073)	loss 3.3401 (3.4337)	grad_norm 1.7623 (1.7142)	
[2022-01-23 07:43:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][860/1251]	eta 0:14:22 lr 0.000363	time 2.1503 (2.2071)	loss 2.8919 (3.4320)	grad_norm 1.9428 (1.7139)	
[2022-01-23 07:43:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][870/1251]	eta 0:14:00 lr 0.000363	time 2.1772 (2.2073)	loss 3.9356 (3.4323)	grad_norm 1.8418 (1.7136)	
[2022-01-23 07:43:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][880/1251]	eta 0:13:38 lr 0.000363	time 2.5526 (2.2067)	loss 4.1956 (3.4342)	grad_norm 1.6142 (1.7146)	
[2022-01-23 07:44:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][890/1251]	eta 0:13:16 lr 0.000363	time 2.4893 (2.2073)	loss 3.7721 (3.4355)	grad_norm 1.6877 (1.7145)	
[2022-01-23 07:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][900/1251]	eta 0:12:55 lr 0.000363	time 2.1110 (2.2088)	loss 3.8653 (3.4317)	grad_norm 1.6947 (1.7154)	
[2022-01-23 07:45:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][910/1251]	eta 0:12:32 lr 0.000363	time 2.0006 (2.2079)	loss 4.0134 (3.4352)	grad_norm 1.6403 (1.7150)	
[2022-01-23 07:45:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][920/1251]	eta 0:12:11 lr 0.000363	time 2.8185 (2.2087)	loss 3.6250 (3.4351)	grad_norm 1.4373 (1.7142)	
[2022-01-23 07:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][930/1251]	eta 0:11:49 lr 0.000363	time 2.5896 (2.2106)	loss 3.6847 (3.4368)	grad_norm 1.6014 (1.7135)	
[2022-01-23 07:46:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][940/1251]	eta 0:11:27 lr 0.000363	time 1.5733 (2.2095)	loss 2.7321 (3.4372)	grad_norm 1.7695 (1.7142)	
[2022-01-23 07:46:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][950/1251]	eta 0:11:04 lr 0.000363	time 1.7807 (2.2085)	loss 2.8044 (3.4347)	grad_norm 1.6635 (1.7139)	
[2022-01-23 07:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][960/1251]	eta 0:10:42 lr 0.000363	time 3.6649 (2.2090)	loss 2.7083 (3.4340)	grad_norm 1.5279 (1.7139)	
[2022-01-23 07:47:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][970/1251]	eta 0:10:20 lr 0.000363	time 1.9552 (2.2086)	loss 3.3876 (3.4339)	grad_norm 1.7203 (1.7136)	
[2022-01-23 07:47:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][980/1251]	eta 0:09:58 lr 0.000363	time 1.7049 (2.2068)	loss 3.0917 (3.4337)	grad_norm 1.6960 (1.7135)	
[2022-01-23 07:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][990/1251]	eta 0:09:35 lr 0.000363	time 2.1645 (2.2059)	loss 3.9072 (3.4350)	grad_norm 1.7081 (1.7139)	
[2022-01-23 07:48:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1000/1251]	eta 0:09:13 lr 0.000363	time 3.3968 (2.2069)	loss 4.0984 (3.4335)	grad_norm 1.6283 (1.7132)	
[2022-01-23 07:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1010/1251]	eta 0:08:51 lr 0.000363	time 1.6637 (2.2059)	loss 3.9565 (3.4330)	grad_norm 1.6262 (1.7135)	
[2022-01-23 07:49:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1020/1251]	eta 0:08:29 lr 0.000363	time 2.0819 (2.2051)	loss 2.5187 (3.4316)	grad_norm 1.6573 (1.7134)	
[2022-01-23 07:49:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1030/1251]	eta 0:08:07 lr 0.000363	time 1.8714 (2.2041)	loss 4.0809 (3.4307)	grad_norm 1.9605 (1.7143)	
[2022-01-23 07:49:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1040/1251]	eta 0:07:45 lr 0.000363	time 2.3756 (2.2045)	loss 3.7038 (3.4316)	grad_norm 2.0366 (1.7144)	
[2022-01-23 07:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1050/1251]	eta 0:07:22 lr 0.000363	time 1.6994 (2.2037)	loss 3.1657 (3.4327)	grad_norm 1.7923 (1.7146)	
[2022-01-23 07:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1060/1251]	eta 0:07:00 lr 0.000363	time 1.8276 (2.2026)	loss 3.7923 (3.4344)	grad_norm 1.9935 (1.7155)	
[2022-01-23 07:50:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1070/1251]	eta 0:06:38 lr 0.000363	time 1.8530 (2.2012)	loss 3.5795 (3.4356)	grad_norm 1.9802 (1.7162)	
[2022-01-23 07:51:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1080/1251]	eta 0:06:16 lr 0.000363	time 2.2051 (2.2011)	loss 3.6280 (3.4346)	grad_norm 1.7736 (1.7166)	
[2022-01-23 07:51:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1090/1251]	eta 0:05:54 lr 0.000363	time 3.3831 (2.2020)	loss 3.6458 (3.4345)	grad_norm 1.6513 (1.7170)	
[2022-01-23 07:52:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1100/1251]	eta 0:05:33 lr 0.000363	time 1.9426 (2.2059)	loss 2.6271 (3.4338)	grad_norm 1.8409 (1.7174)	
[2022-01-23 07:52:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1110/1251]	eta 0:05:10 lr 0.000362	time 2.0949 (2.2052)	loss 3.7715 (3.4350)	grad_norm 1.4511 (1.7177)	
[2022-01-23 07:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1120/1251]	eta 0:04:48 lr 0.000362	time 1.8624 (2.2029)	loss 2.2724 (3.4341)	grad_norm 1.5924 (1.7172)	
[2022-01-23 07:53:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1130/1251]	eta 0:04:26 lr 0.000362	time 1.9845 (2.2029)	loss 4.2880 (3.4335)	grad_norm 2.0698 (1.7180)	
[2022-01-23 07:53:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1140/1251]	eta 0:04:04 lr 0.000362	time 1.8099 (2.2027)	loss 3.6601 (3.4336)	grad_norm 1.7164 (1.7168)	
[2022-01-23 07:53:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1150/1251]	eta 0:03:42 lr 0.000362	time 2.1713 (2.2030)	loss 3.4172 (3.4322)	grad_norm 1.9697 (1.7168)	
[2022-01-23 07:54:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1160/1251]	eta 0:03:20 lr 0.000362	time 1.9069 (2.2035)	loss 3.9904 (3.4321)	grad_norm 1.8076 (1.7165)	
[2022-01-23 07:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1170/1251]	eta 0:02:58 lr 0.000362	time 4.3218 (2.2063)	loss 2.8216 (3.4312)	grad_norm 1.6057 (1.7159)	
[2022-01-23 07:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1180/1251]	eta 0:02:36 lr 0.000362	time 2.1123 (2.2053)	loss 3.5179 (3.4310)	grad_norm 1.6249 (1.7149)	
[2022-01-23 07:55:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1190/1251]	eta 0:02:14 lr 0.000362	time 1.7840 (2.2045)	loss 3.2009 (3.4302)	grad_norm 1.8997 (1.7150)	
[2022-01-23 07:55:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1200/1251]	eta 0:01:52 lr 0.000362	time 1.9032 (2.2035)	loss 3.3235 (3.4297)	grad_norm 1.5536 (1.7145)	
[2022-01-23 07:56:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1210/1251]	eta 0:01:30 lr 0.000362	time 2.3720 (2.2029)	loss 3.2329 (3.4274)	grad_norm 1.5031 (1.7141)	
[2022-01-23 07:56:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1220/1251]	eta 0:01:08 lr 0.000362	time 1.9427 (2.2009)	loss 3.2522 (3.4295)	grad_norm 1.6003 (1.7136)	
[2022-01-23 07:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1230/1251]	eta 0:00:46 lr 0.000362	time 2.2404 (2.2006)	loss 3.6603 (3.4287)	grad_norm 1.9884 (1.7137)	
[2022-01-23 07:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1240/1251]	eta 0:00:24 lr 0.000362	time 2.2279 (2.2000)	loss 3.2180 (3.4288)	grad_norm 1.8892 (1.7150)	
[2022-01-23 07:57:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [177/300][1250/1251]	eta 0:00:02 lr 0.000362	time 1.1923 (2.1949)	loss 2.9246 (3.4280)	grad_norm 1.9256 (1.7150)	
[2022-01-23 07:57:19 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 177 training takes 0:45:46
[2022-01-23 07:57:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.676 (18.676)	Loss 0.9426 (0.9426)	Acc@1 79.199 (79.199)	Acc@5 93.945 (93.945)	
[2022-01-23 07:57:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.274 (3.292)	Loss 1.0278 (0.9627)	Acc@1 75.195 (77.228)	Acc@5 93.262 (94.034)	
[2022-01-23 07:58:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.191 (2.493)	Loss 0.9216 (0.9516)	Acc@1 77.344 (77.562)	Acc@5 94.629 (93.964)	
[2022-01-23 07:58:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.586 (2.308)	Loss 0.9952 (0.9586)	Acc@1 76.660 (77.341)	Acc@5 93.945 (93.936)	
[2022-01-23 07:58:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.881 (2.112)	Loss 0.9367 (0.9578)	Acc@1 78.711 (77.458)	Acc@5 94.727 (93.914)	
[2022-01-23 07:58:53 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.444 Acc@5 93.966
[2022-01-23 07:58:53 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.4%
[2022-01-23 07:58:53 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.44%
[2022-01-23 07:59:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][0/1251]	eta 7:32:02 lr 0.000362	time 21.6807 (21.6807)	loss 2.4149 (2.4149)	grad_norm 1.8394 (1.8394)	
[2022-01-23 07:59:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][10/1251]	eta 1:22:47 lr 0.000362	time 1.8708 (4.0025)	loss 3.6357 (3.3666)	grad_norm 1.5689 (1.7511)	
[2022-01-23 07:59:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][20/1251]	eta 1:04:31 lr 0.000362	time 1.3492 (3.1448)	loss 3.6555 (3.4421)	grad_norm 1.6739 (1.7254)	
[2022-01-23 08:00:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][30/1251]	eta 0:55:11 lr 0.000362	time 1.6957 (2.7124)	loss 3.4785 (3.4235)	grad_norm 1.6811 (1.7264)	
[2022-01-23 08:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][40/1251]	eta 0:55:05 lr 0.000362	time 4.4494 (2.7297)	loss 3.5156 (3.4036)	grad_norm 1.7025 (1.7655)	
[2022-01-23 08:01:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][50/1251]	eta 0:52:43 lr 0.000362	time 2.5527 (2.6340)	loss 3.7844 (3.4213)	grad_norm 1.6558 (1.7861)	
[2022-01-23 08:01:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][60/1251]	eta 0:50:01 lr 0.000362	time 1.5690 (2.5200)	loss 3.9229 (3.4107)	grad_norm 1.7842 (1.7644)	
[2022-01-23 08:01:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][70/1251]	eta 0:48:51 lr 0.000362	time 1.9573 (2.4820)	loss 4.1149 (3.4439)	grad_norm 1.6290 (1.7629)	
[2022-01-23 08:02:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][80/1251]	eta 0:48:54 lr 0.000362	time 6.5294 (2.5060)	loss 3.3831 (3.4391)	grad_norm 1.6812 (1.7493)	
[2022-01-23 08:02:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][90/1251]	eta 0:47:21 lr 0.000362	time 1.9060 (2.4472)	loss 3.3015 (3.4445)	grad_norm 1.9337 (1.7469)	
[2022-01-23 08:02:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][100/1251]	eta 0:46:06 lr 0.000362	time 1.9040 (2.4036)	loss 4.3323 (3.4399)	grad_norm 1.7842 (1.7437)	
[2022-01-23 08:03:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][110/1251]	eta 0:45:06 lr 0.000361	time 1.6278 (2.3720)	loss 2.9165 (3.4275)	grad_norm 1.7315 (1.7362)	
[2022-01-23 08:03:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][120/1251]	eta 0:44:33 lr 0.000361	time 3.6411 (2.3639)	loss 3.8705 (3.4394)	grad_norm 1.8455 (1.7306)	
[2022-01-23 08:04:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][130/1251]	eta 0:43:49 lr 0.000361	time 2.4004 (2.3457)	loss 3.9300 (3.4553)	grad_norm 1.9664 (1.7374)	
[2022-01-23 08:04:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][140/1251]	eta 0:43:23 lr 0.000361	time 2.2278 (2.3437)	loss 4.4587 (3.4581)	grad_norm 1.7658 (1.7305)	
[2022-01-23 08:04:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][150/1251]	eta 0:42:45 lr 0.000361	time 1.5888 (2.3305)	loss 3.6814 (3.4591)	grad_norm 1.9004 (1.7326)	
[2022-01-23 08:05:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][160/1251]	eta 0:42:14 lr 0.000361	time 2.9341 (2.3231)	loss 3.0676 (3.4564)	grad_norm 1.5196 (1.7311)	
[2022-01-23 08:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][170/1251]	eta 0:41:40 lr 0.000361	time 2.4658 (2.3129)	loss 2.5218 (3.4573)	grad_norm 1.9591 (1.7281)	
[2022-01-23 08:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][180/1251]	eta 0:41:12 lr 0.000361	time 1.8496 (2.3085)	loss 4.1755 (3.4669)	grad_norm 2.0025 (1.7251)	
[2022-01-23 08:06:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][190/1251]	eta 0:40:44 lr 0.000361	time 2.2428 (2.3043)	loss 3.9827 (3.4601)	grad_norm 1.7005 (1.7252)	
[2022-01-23 08:06:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][200/1251]	eta 0:40:16 lr 0.000361	time 2.7437 (2.2988)	loss 3.8530 (3.4641)	grad_norm 1.6665 (1.7261)	
[2022-01-23 08:06:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][210/1251]	eta 0:39:44 lr 0.000361	time 2.1753 (2.2908)	loss 3.5517 (3.4595)	grad_norm 1.6595 (1.7250)	
[2022-01-23 08:07:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][220/1251]	eta 0:39:18 lr 0.000361	time 1.9654 (2.2875)	loss 3.8109 (3.4482)	grad_norm 1.9763 (1.7251)	
[2022-01-23 08:07:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][230/1251]	eta 0:38:48 lr 0.000361	time 1.9586 (2.2801)	loss 3.9644 (3.4402)	grad_norm 1.7226 (1.7236)	
[2022-01-23 08:08:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][240/1251]	eta 0:38:23 lr 0.000361	time 2.8081 (2.2782)	loss 3.7015 (3.4330)	grad_norm 1.7477 (1.7219)	
[2022-01-23 08:08:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][250/1251]	eta 0:37:55 lr 0.000361	time 1.7489 (2.2736)	loss 2.3942 (3.4228)	grad_norm 1.6081 (1.7200)	
[2022-01-23 08:08:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][260/1251]	eta 0:37:30 lr 0.000361	time 1.9589 (2.2708)	loss 3.7639 (3.4257)	grad_norm 1.7600 (1.7206)	
[2022-01-23 08:09:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][270/1251]	eta 0:36:58 lr 0.000361	time 1.8694 (2.2616)	loss 3.7648 (3.4338)	grad_norm 1.5104 (1.7210)	
[2022-01-23 08:09:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][280/1251]	eta 0:36:38 lr 0.000361	time 3.7037 (2.2637)	loss 2.3291 (3.4311)	grad_norm 1.7895 (1.7181)	
[2022-01-23 08:09:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][290/1251]	eta 0:36:08 lr 0.000361	time 2.0618 (2.2566)	loss 3.8699 (3.4319)	grad_norm 1.9622 (1.7192)	
[2022-01-23 08:10:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][300/1251]	eta 0:35:45 lr 0.000361	time 2.7181 (2.2557)	loss 3.7566 (3.4362)	grad_norm 1.4580 (1.7177)	
[2022-01-23 08:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][310/1251]	eta 0:35:26 lr 0.000361	time 2.8734 (2.2600)	loss 3.9389 (3.4398)	grad_norm 1.7151 (1.7170)	
[2022-01-23 08:10:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][320/1251]	eta 0:35:00 lr 0.000361	time 1.6038 (2.2566)	loss 4.1375 (3.4438)	grad_norm 1.6854 (1.7158)	
[2022-01-23 08:11:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][330/1251]	eta 0:34:33 lr 0.000361	time 1.8889 (2.2509)	loss 4.0795 (3.4491)	grad_norm 1.5096 (1.7149)	
[2022-01-23 08:11:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][340/1251]	eta 0:34:08 lr 0.000361	time 2.0938 (2.2483)	loss 3.9427 (3.4535)	grad_norm 1.6865 (1.7156)	
[2022-01-23 08:12:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][350/1251]	eta 0:33:39 lr 0.000361	time 1.5872 (2.2416)	loss 3.5274 (3.4481)	grad_norm 1.8029 (1.7164)	
[2022-01-23 08:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][360/1251]	eta 0:33:13 lr 0.000361	time 2.3102 (2.2379)	loss 3.0580 (3.4473)	grad_norm 1.7241 (1.7170)	
[2022-01-23 08:12:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][370/1251]	eta 0:32:54 lr 0.000360	time 2.4668 (2.2414)	loss 3.6992 (3.4399)	grad_norm 2.0927 (1.7184)	
[2022-01-23 08:13:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][380/1251]	eta 0:32:32 lr 0.000360	time 2.3091 (2.2411)	loss 4.4418 (3.4419)	grad_norm 1.5317 (1.7174)	
[2022-01-23 08:13:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][390/1251]	eta 0:32:06 lr 0.000360	time 2.1572 (2.2377)	loss 2.2936 (3.4318)	grad_norm 2.3135 (1.7206)	
[2022-01-23 08:13:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][400/1251]	eta 0:31:43 lr 0.000360	time 2.6314 (2.2367)	loss 3.2594 (3.4299)	grad_norm 1.5457 (1.7194)	
[2022-01-23 08:14:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][410/1251]	eta 0:31:21 lr 0.000360	time 2.6964 (2.2372)	loss 3.4481 (3.4373)	grad_norm 1.7855 (1.7189)	
[2022-01-23 08:14:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][420/1251]	eta 0:30:57 lr 0.000360	time 2.5094 (2.2350)	loss 3.7516 (3.4411)	grad_norm 1.7283 (1.7189)	
[2022-01-23 08:14:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][430/1251]	eta 0:30:38 lr 0.000360	time 2.1262 (2.2395)	loss 2.2481 (3.4326)	grad_norm 2.1852 (1.7218)	
[2022-01-23 08:15:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][440/1251]	eta 0:30:13 lr 0.000360	time 1.6319 (2.2357)	loss 2.6783 (3.4317)	grad_norm 1.7499 (1.7266)	
[2022-01-23 08:15:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][450/1251]	eta 0:29:51 lr 0.000360	time 1.8121 (2.2364)	loss 3.2800 (3.4344)	grad_norm 1.6364 (1.7274)	
[2022-01-23 08:16:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][460/1251]	eta 0:29:25 lr 0.000360	time 1.7384 (2.2321)	loss 3.5568 (3.4399)	grad_norm 1.9377 (1.7272)	
[2022-01-23 08:16:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][470/1251]	eta 0:29:03 lr 0.000360	time 1.9347 (2.2322)	loss 3.4703 (3.4388)	grad_norm 1.6646 (1.7263)	
[2022-01-23 08:16:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][480/1251]	eta 0:28:38 lr 0.000360	time 2.2010 (2.2288)	loss 2.4220 (3.4330)	grad_norm 2.1228 (1.7268)	
[2022-01-23 08:17:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][490/1251]	eta 0:28:14 lr 0.000360	time 2.0026 (2.2270)	loss 2.4492 (3.4275)	grad_norm 2.0289 (1.7268)	
[2022-01-23 08:17:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][500/1251]	eta 0:27:51 lr 0.000360	time 2.6805 (2.2258)	loss 2.4869 (3.4286)	grad_norm 1.4373 (1.7281)	
[2022-01-23 08:17:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][510/1251]	eta 0:27:28 lr 0.000360	time 2.6693 (2.2241)	loss 3.5837 (3.4287)	grad_norm 1.7710 (1.7271)	
[2022-01-23 08:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][520/1251]	eta 0:27:03 lr 0.000360	time 1.8504 (2.2203)	loss 3.8699 (3.4256)	grad_norm 1.7866 (1.7281)	
[2022-01-23 08:18:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][530/1251]	eta 0:26:40 lr 0.000360	time 2.1447 (2.2197)	loss 3.7256 (3.4276)	grad_norm 1.6852 (1.7284)	
[2022-01-23 08:18:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][540/1251]	eta 0:26:19 lr 0.000360	time 2.4238 (2.2215)	loss 3.1991 (3.4262)	grad_norm 1.4108 (1.7314)	
[2022-01-23 08:19:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][550/1251]	eta 0:25:55 lr 0.000360	time 1.9539 (2.2190)	loss 2.4892 (3.4263)	grad_norm 1.7008 (1.7322)	
[2022-01-23 08:19:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][560/1251]	eta 0:25:32 lr 0.000360	time 1.8562 (2.2177)	loss 4.1300 (3.4239)	grad_norm 1.5434 (1.7309)	
[2022-01-23 08:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][570/1251]	eta 0:25:10 lr 0.000360	time 1.8116 (2.2177)	loss 3.6134 (3.4229)	grad_norm 1.7094 (1.7321)	
[2022-01-23 08:20:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][580/1251]	eta 0:24:47 lr 0.000360	time 2.8603 (2.2165)	loss 2.9313 (3.4231)	grad_norm 1.6596 (1.7305)	
[2022-01-23 08:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][590/1251]	eta 0:24:23 lr 0.000360	time 1.9711 (2.2136)	loss 2.4223 (3.4245)	grad_norm 1.8902 (1.7307)	
[2022-01-23 08:21:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][600/1251]	eta 0:24:00 lr 0.000360	time 1.7985 (2.2120)	loss 3.7744 (3.4227)	grad_norm 1.5725 (1.7312)	
[2022-01-23 08:21:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][610/1251]	eta 0:23:38 lr 0.000360	time 2.0489 (2.2136)	loss 3.3788 (3.4261)	grad_norm 1.6352 (1.7318)	
[2022-01-23 08:21:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][620/1251]	eta 0:23:16 lr 0.000359	time 2.1496 (2.2137)	loss 3.4939 (3.4253)	grad_norm 1.7317 (1.7298)	
[2022-01-23 08:22:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][630/1251]	eta 0:22:54 lr 0.000359	time 1.9684 (2.2127)	loss 2.9958 (3.4254)	grad_norm 1.6341 (1.7282)	
[2022-01-23 08:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][640/1251]	eta 0:22:31 lr 0.000359	time 1.5780 (2.2115)	loss 3.2337 (3.4268)	grad_norm 1.4085 (1.7284)	
[2022-01-23 08:22:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][650/1251]	eta 0:22:08 lr 0.000359	time 2.4263 (2.2103)	loss 3.5688 (3.4268)	grad_norm 1.6463 (1.7279)	
[2022-01-23 08:23:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][660/1251]	eta 0:21:45 lr 0.000359	time 2.6094 (2.2095)	loss 3.2335 (3.4248)	grad_norm 1.7584 (1.7269)	
[2022-01-23 08:23:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][670/1251]	eta 0:21:24 lr 0.000359	time 3.0434 (2.2113)	loss 3.7370 (3.4269)	grad_norm 1.7181 (1.7290)	
[2022-01-23 08:24:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][680/1251]	eta 0:21:02 lr 0.000359	time 2.3022 (2.2119)	loss 3.8589 (3.4295)	grad_norm 2.1106 (1.7303)	
[2022-01-23 08:24:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][690/1251]	eta 0:20:40 lr 0.000359	time 1.9587 (2.2113)	loss 3.1988 (3.4285)	grad_norm 1.7680 (1.7298)	
[2022-01-23 08:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][700/1251]	eta 0:20:18 lr 0.000359	time 1.9125 (2.2109)	loss 3.0798 (3.4286)	grad_norm 2.1181 (1.7302)	
[2022-01-23 08:25:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][710/1251]	eta 0:19:56 lr 0.000359	time 2.6238 (2.2117)	loss 3.7418 (3.4315)	grad_norm 1.8018 (1.7301)	
[2022-01-23 08:25:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][720/1251]	eta 0:19:34 lr 0.000359	time 2.7970 (2.2123)	loss 3.1217 (3.4325)	grad_norm 1.7378 (1.7302)	
[2022-01-23 08:25:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][730/1251]	eta 0:19:12 lr 0.000359	time 1.9319 (2.2120)	loss 3.3392 (3.4328)	grad_norm 1.6865 (1.7293)	
[2022-01-23 08:26:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][740/1251]	eta 0:18:49 lr 0.000359	time 2.1804 (2.2102)	loss 3.6657 (3.4334)	grad_norm 1.5759 (1.7284)	
[2022-01-23 08:26:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][750/1251]	eta 0:18:27 lr 0.000359	time 2.5107 (2.2099)	loss 3.9657 (3.4332)	grad_norm 1.6188 (1.7284)	
[2022-01-23 08:26:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][760/1251]	eta 0:18:04 lr 0.000359	time 2.8723 (2.2086)	loss 3.6661 (3.4341)	grad_norm 1.6209 (1.7304)	
[2022-01-23 08:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][770/1251]	eta 0:17:41 lr 0.000359	time 2.0695 (2.2076)	loss 4.0791 (3.4354)	grad_norm 1.5689 (1.7296)	
[2022-01-23 08:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][780/1251]	eta 0:17:19 lr 0.000359	time 2.5920 (2.2069)	loss 3.1104 (3.4370)	grad_norm 1.6483 (1.7303)	
[2022-01-23 08:27:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][790/1251]	eta 0:16:56 lr 0.000359	time 2.2401 (2.2058)	loss 4.2748 (3.4376)	grad_norm 1.7310 (1.7322)	
[2022-01-23 08:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][800/1251]	eta 0:16:34 lr 0.000359	time 1.8055 (2.2057)	loss 3.1201 (3.4404)	grad_norm 1.7149 (1.7320)	
[2022-01-23 08:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][810/1251]	eta 0:16:12 lr 0.000359	time 1.6892 (2.2042)	loss 2.5567 (3.4366)	grad_norm 1.8325 (1.7326)	
[2022-01-23 08:29:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][820/1251]	eta 0:15:49 lr 0.000359	time 1.5791 (2.2020)	loss 4.1242 (3.4378)	grad_norm 1.6689 (1.7321)	
[2022-01-23 08:29:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][830/1251]	eta 0:15:27 lr 0.000359	time 1.8061 (2.2023)	loss 3.3733 (3.4397)	grad_norm 1.7806 (1.7322)	
[2022-01-23 08:29:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][840/1251]	eta 0:15:05 lr 0.000359	time 2.4338 (2.2030)	loss 3.8574 (3.4412)	grad_norm 1.5746 (1.7316)	
[2022-01-23 08:30:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][850/1251]	eta 0:14:43 lr 0.000359	time 1.6442 (2.2021)	loss 3.7182 (3.4413)	grad_norm 1.6616 (1.7323)	
[2022-01-23 08:30:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][860/1251]	eta 0:14:20 lr 0.000359	time 1.9423 (2.2007)	loss 4.1078 (3.4420)	grad_norm 1.8777 (1.7324)	
[2022-01-23 08:30:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][870/1251]	eta 0:13:58 lr 0.000358	time 2.0851 (2.2001)	loss 2.9569 (3.4408)	grad_norm 1.9899 (1.7331)	
[2022-01-23 08:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][880/1251]	eta 0:13:36 lr 0.000358	time 2.2112 (2.2007)	loss 3.5231 (3.4445)	grad_norm 1.8436 (1.7353)	
[2022-01-23 08:31:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][890/1251]	eta 0:13:14 lr 0.000358	time 1.5892 (2.2018)	loss 3.7833 (3.4451)	grad_norm 1.5652 (1.7345)	
[2022-01-23 08:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][900/1251]	eta 0:12:52 lr 0.000358	time 1.8325 (2.2021)	loss 3.4598 (3.4454)	grad_norm 1.7400 (1.7336)	
[2022-01-23 08:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][910/1251]	eta 0:12:31 lr 0.000358	time 2.4629 (2.2029)	loss 3.2625 (3.4426)	grad_norm 1.6743 (1.7327)	
[2022-01-23 08:32:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][920/1251]	eta 0:12:09 lr 0.000358	time 2.8613 (2.2029)	loss 3.0257 (3.4388)	grad_norm 1.9177 (1.7332)	
[2022-01-23 08:33:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][930/1251]	eta 0:11:47 lr 0.000358	time 1.8242 (2.2035)	loss 2.6664 (3.4354)	grad_norm 1.7099 (1.7337)	
[2022-01-23 08:33:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][940/1251]	eta 0:11:25 lr 0.000358	time 1.5360 (2.2028)	loss 3.2586 (3.4370)	grad_norm 1.7793 (1.7353)	
[2022-01-23 08:33:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][950/1251]	eta 0:11:02 lr 0.000358	time 2.2060 (2.2018)	loss 3.7297 (3.4390)	grad_norm 1.8087 (1.7358)	
[2022-01-23 08:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][960/1251]	eta 0:10:40 lr 0.000358	time 2.5808 (2.2017)	loss 3.7560 (3.4412)	grad_norm 1.7252 (1.7357)	
[2022-01-23 08:34:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][970/1251]	eta 0:10:18 lr 0.000358	time 2.7491 (2.2010)	loss 4.1906 (3.4392)	grad_norm 1.8591 (1.7357)	
[2022-01-23 08:34:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][980/1251]	eta 0:09:56 lr 0.000358	time 2.0348 (2.2018)	loss 2.3399 (3.4368)	grad_norm 1.6474 (1.7373)	
[2022-01-23 08:35:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][990/1251]	eta 0:09:34 lr 0.000358	time 2.2121 (2.2017)	loss 3.7120 (3.4344)	grad_norm 1.8940 (1.7372)	
[2022-01-23 08:35:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1000/1251]	eta 0:09:12 lr 0.000358	time 1.6203 (2.2002)	loss 2.8559 (3.4352)	grad_norm 2.1829 (1.7375)	
[2022-01-23 08:35:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1010/1251]	eta 0:08:49 lr 0.000358	time 2.1035 (2.1987)	loss 3.4800 (3.4356)	grad_norm 1.5059 (1.7380)	
[2022-01-23 08:36:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1020/1251]	eta 0:08:27 lr 0.000358	time 2.3069 (2.1987)	loss 3.0074 (3.4339)	grad_norm 1.6917 (1.7378)	
[2022-01-23 08:36:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1030/1251]	eta 0:08:06 lr 0.000358	time 2.0997 (2.2000)	loss 3.6275 (3.4353)	grad_norm 1.7024 (1.7368)	
[2022-01-23 08:37:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1040/1251]	eta 0:07:44 lr 0.000358	time 1.8249 (2.2007)	loss 3.9947 (3.4374)	grad_norm 2.0272 (1.7369)	
[2022-01-23 08:37:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1050/1251]	eta 0:07:22 lr 0.000358	time 1.8855 (2.1995)	loss 3.6558 (3.4388)	grad_norm 1.6871 (1.7361)	
[2022-01-23 08:37:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1060/1251]	eta 0:06:59 lr 0.000358	time 1.7176 (2.1975)	loss 3.5701 (3.4388)	grad_norm 1.6600 (1.7355)	
[2022-01-23 08:38:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1070/1251]	eta 0:06:37 lr 0.000358	time 2.6969 (2.1972)	loss 3.4822 (3.4376)	grad_norm 1.7285 (1.7350)	
[2022-01-23 08:38:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1080/1251]	eta 0:06:15 lr 0.000358	time 2.4386 (2.1976)	loss 3.5997 (3.4392)	grad_norm 1.6512 (1.7352)	
[2022-01-23 08:38:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1090/1251]	eta 0:05:53 lr 0.000358	time 2.3745 (2.1975)	loss 3.7659 (3.4389)	grad_norm 1.7013 (1.7343)	
[2022-01-23 08:39:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1100/1251]	eta 0:05:31 lr 0.000358	time 1.9051 (2.1986)	loss 3.7877 (3.4407)	grad_norm 1.6685 (1.7341)	
[2022-01-23 08:39:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1110/1251]	eta 0:05:10 lr 0.000358	time 3.0793 (2.2000)	loss 3.4867 (3.4401)	grad_norm 1.5635 (1.7333)	
[2022-01-23 08:40:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1120/1251]	eta 0:04:48 lr 0.000357	time 2.7551 (2.2000)	loss 3.3919 (3.4375)	grad_norm 1.7393 (1.7333)	
[2022-01-23 08:40:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1130/1251]	eta 0:04:25 lr 0.000357	time 1.7850 (2.1981)	loss 2.7818 (3.4378)	grad_norm 1.8775 (1.7343)	
[2022-01-23 08:40:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1140/1251]	eta 0:04:03 lr 0.000357	time 1.9238 (2.1965)	loss 2.7380 (3.4386)	grad_norm 1.5698 (1.7348)	
[2022-01-23 08:40:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1150/1251]	eta 0:03:41 lr 0.000357	time 1.9127 (2.1945)	loss 3.6324 (3.4394)	grad_norm 1.5871 (1.7340)	
[2022-01-23 08:41:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1160/1251]	eta 0:03:19 lr 0.000357	time 2.0428 (2.1938)	loss 2.3147 (3.4398)	grad_norm 1.7856 (1.7337)	
[2022-01-23 08:41:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1170/1251]	eta 0:02:58 lr 0.000357	time 2.3425 (2.1987)	loss 2.1006 (3.4380)	grad_norm 1.6486 (1.7332)	
[2022-01-23 08:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1180/1251]	eta 0:02:36 lr 0.000357	time 2.1308 (2.2014)	loss 3.6979 (3.4382)	grad_norm 1.6552 (1.7337)	
[2022-01-23 08:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1190/1251]	eta 0:02:14 lr 0.000357	time 1.9109 (2.2012)	loss 4.0287 (3.4388)	grad_norm 1.7143 (1.7342)	
[2022-01-23 08:42:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1200/1251]	eta 0:01:52 lr 0.000357	time 1.9485 (2.1993)	loss 3.9768 (3.4393)	grad_norm 1.7318 (1.7346)	
[2022-01-23 08:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1210/1251]	eta 0:01:30 lr 0.000357	time 1.9591 (2.1984)	loss 2.2237 (3.4379)	grad_norm 1.5548 (1.7340)	
[2022-01-23 08:43:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1220/1251]	eta 0:01:08 lr 0.000357	time 1.5877 (2.1973)	loss 3.2846 (3.4391)	grad_norm 1.5198 (1.7333)	
[2022-01-23 08:43:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1230/1251]	eta 0:00:46 lr 0.000357	time 1.8318 (2.1969)	loss 2.2966 (3.4376)	grad_norm 1.5065 (1.7334)	
[2022-01-23 08:44:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1240/1251]	eta 0:00:24 lr 0.000357	time 1.8082 (2.1959)	loss 3.7710 (3.4383)	grad_norm 1.7131 (1.7326)	
[2022-01-23 08:44:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [178/300][1250/1251]	eta 0:00:02 lr 0.000357	time 1.1811 (2.1912)	loss 3.1934 (3.4373)	grad_norm 1.6923 (1.7327)	
[2022-01-23 08:44:35 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 178 training takes 0:45:41
[2022-01-23 08:44:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.151 (18.151)	Loss 0.9777 (0.9777)	Acc@1 77.637 (77.637)	Acc@5 93.164 (93.164)	
[2022-01-23 08:45:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.671 (3.316)	Loss 0.9855 (0.9598)	Acc@1 76.465 (77.495)	Acc@5 93.750 (93.768)	
[2022-01-23 08:45:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.230 (2.579)	Loss 0.9861 (0.9591)	Acc@1 77.051 (77.483)	Acc@5 93.652 (93.810)	
[2022-01-23 08:45:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.616 (2.221)	Loss 0.9710 (0.9546)	Acc@1 75.879 (77.526)	Acc@5 94.043 (93.889)	
[2022-01-23 08:46:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.933 (2.162)	Loss 0.9199 (0.9606)	Acc@1 77.930 (77.289)	Acc@5 94.043 (93.838)	
[2022-01-23 08:46:11 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.236 Acc@5 93.854
[2022-01-23 08:46:11 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.2%
[2022-01-23 08:46:11 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.44%
[2022-01-23 08:46:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][0/1251]	eta 7:31:44 lr 0.000357	time 21.6665 (21.6665)	loss 3.7030 (3.7030)	grad_norm 1.9334 (1.9334)	
[2022-01-23 08:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][10/1251]	eta 1:23:23 lr 0.000357	time 1.3738 (4.0315)	loss 3.4684 (3.6100)	grad_norm 1.5123 (1.7532)	
[2022-01-23 08:47:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][20/1251]	eta 1:04:22 lr 0.000357	time 1.4260 (3.1379)	loss 3.4677 (3.5034)	grad_norm 1.7990 (1.7552)	
[2022-01-23 08:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][30/1251]	eta 0:57:50 lr 0.000357	time 1.4743 (2.8427)	loss 3.5871 (3.5441)	grad_norm 1.7278 (1.7438)	
[2022-01-23 08:48:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][40/1251]	eta 0:54:09 lr 0.000357	time 3.9441 (2.6834)	loss 4.2377 (3.5630)	grad_norm 1.7190 (1.7421)	
[2022-01-23 08:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][50/1251]	eta 0:52:30 lr 0.000357	time 1.6873 (2.6235)	loss 2.4058 (3.4993)	grad_norm 1.8477 (1.7617)	
[2022-01-23 08:48:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][60/1251]	eta 0:50:25 lr 0.000357	time 1.4152 (2.5405)	loss 3.6380 (3.4836)	grad_norm 1.9122 (1.7591)	
[2022-01-23 08:49:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][70/1251]	eta 0:48:49 lr 0.000357	time 1.7003 (2.4802)	loss 4.0943 (3.4941)	grad_norm 1.7565 (1.7903)	
[2022-01-23 08:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][80/1251]	eta 0:48:12 lr 0.000357	time 3.7234 (2.4701)	loss 2.6078 (3.4697)	grad_norm 1.7610 (1.7819)	
[2022-01-23 08:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][90/1251]	eta 0:47:22 lr 0.000357	time 1.5792 (2.4480)	loss 3.7103 (3.4620)	grad_norm 1.6804 (1.7883)	
[2022-01-23 08:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][100/1251]	eta 0:46:26 lr 0.000357	time 1.6842 (2.4209)	loss 2.8578 (3.4243)	grad_norm 1.5073 (1.7823)	
[2022-01-23 08:50:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][110/1251]	eta 0:45:23 lr 0.000357	time 1.6443 (2.3866)	loss 3.8361 (3.4276)	grad_norm 1.7535 (1.7718)	
[2022-01-23 08:50:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][120/1251]	eta 0:44:52 lr 0.000357	time 3.5698 (2.3810)	loss 3.8133 (3.4265)	grad_norm 1.8144 (1.7693)	
[2022-01-23 08:51:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][130/1251]	eta 0:44:11 lr 0.000356	time 1.5496 (2.3656)	loss 3.7373 (3.4181)	grad_norm 1.5520 (1.7571)	
[2022-01-23 08:51:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][140/1251]	eta 0:43:29 lr 0.000356	time 1.7361 (2.3484)	loss 3.0073 (3.4298)	grad_norm 2.0268 (1.7511)	
[2022-01-23 08:52:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][150/1251]	eta 0:42:41 lr 0.000356	time 1.9034 (2.3267)	loss 3.7617 (3.4452)	grad_norm 1.5798 (1.7490)	
[2022-01-23 08:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][160/1251]	eta 0:42:15 lr 0.000356	time 3.6691 (2.3244)	loss 3.8212 (3.4545)	grad_norm 1.5606 (1.7497)	
[2022-01-23 08:52:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][170/1251]	eta 0:41:40 lr 0.000356	time 1.7462 (2.3135)	loss 3.4625 (3.4525)	grad_norm 1.6787 (1.7467)	
[2022-01-23 08:53:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][180/1251]	eta 0:41:11 lr 0.000356	time 2.1390 (2.3078)	loss 3.2539 (3.4477)	grad_norm 1.9078 (1.7368)	
[2022-01-23 08:53:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][190/1251]	eta 0:40:45 lr 0.000356	time 1.9647 (2.3052)	loss 3.7685 (3.4309)	grad_norm 1.6905 (1.7340)	
[2022-01-23 08:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][200/1251]	eta 0:40:28 lr 0.000356	time 3.3768 (2.3104)	loss 2.7268 (3.4348)	grad_norm 1.9598 (1.7353)	
[2022-01-23 08:54:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][210/1251]	eta 0:39:56 lr 0.000356	time 1.5320 (2.3022)	loss 3.6846 (3.4375)	grad_norm 1.7174 (1.7401)	
[2022-01-23 08:54:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][220/1251]	eta 0:39:22 lr 0.000356	time 1.6371 (2.2912)	loss 3.1536 (3.4465)	grad_norm 1.9863 (1.7416)	
[2022-01-23 08:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][230/1251]	eta 0:38:47 lr 0.000356	time 1.9302 (2.2799)	loss 3.5190 (3.4466)	grad_norm 2.1578 (1.7411)	
[2022-01-23 08:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][240/1251]	eta 0:38:18 lr 0.000356	time 2.1905 (2.2735)	loss 2.1717 (3.4367)	grad_norm 1.8663 (1.7408)	
[2022-01-23 08:55:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][250/1251]	eta 0:37:49 lr 0.000356	time 1.8389 (2.2669)	loss 3.6441 (3.4362)	grad_norm 1.7949 (1.7401)	
[2022-01-23 08:56:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][260/1251]	eta 0:37:26 lr 0.000356	time 2.8773 (2.2667)	loss 3.3372 (3.4364)	grad_norm 2.0723 (1.7484)	
[2022-01-23 08:56:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][270/1251]	eta 0:37:01 lr 0.000356	time 2.1092 (2.2645)	loss 3.2014 (3.4355)	grad_norm 1.7078 (1.7478)	
[2022-01-23 08:56:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][280/1251]	eta 0:36:41 lr 0.000356	time 1.5550 (2.2674)	loss 4.0865 (3.4230)	grad_norm 1.5850 (1.7474)	
[2022-01-23 08:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][290/1251]	eta 0:36:18 lr 0.000356	time 2.2451 (2.2673)	loss 3.8278 (3.4317)	grad_norm 1.8537 (1.7524)	
[2022-01-23 08:57:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][300/1251]	eta 0:35:50 lr 0.000356	time 2.2705 (2.2616)	loss 2.7521 (3.4250)	grad_norm 1.5700 (1.7519)	
[2022-01-23 08:57:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][310/1251]	eta 0:35:22 lr 0.000356	time 1.6869 (2.2554)	loss 2.8472 (3.4225)	grad_norm 1.6705 (1.7519)	
[2022-01-23 08:58:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][320/1251]	eta 0:34:55 lr 0.000356	time 1.8899 (2.2508)	loss 3.6379 (3.4238)	grad_norm 1.8843 (1.7506)	
[2022-01-23 08:58:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][330/1251]	eta 0:34:32 lr 0.000356	time 2.5475 (2.2501)	loss 3.6653 (3.4237)	grad_norm 1.7204 (1.7525)	
[2022-01-23 08:58:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][340/1251]	eta 0:34:09 lr 0.000356	time 2.4714 (2.2495)	loss 4.1304 (3.4281)	grad_norm 1.5937 (1.7509)	
[2022-01-23 08:59:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][350/1251]	eta 0:33:45 lr 0.000356	time 2.2797 (2.2479)	loss 3.8789 (3.4232)	grad_norm 1.9256 (1.7506)	
[2022-01-23 08:59:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][360/1251]	eta 0:33:26 lr 0.000356	time 2.2655 (2.2515)	loss 2.5700 (3.4256)	grad_norm 1.5654 (1.7480)	
[2022-01-23 09:00:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][370/1251]	eta 0:33:08 lr 0.000356	time 3.0174 (2.2567)	loss 2.7881 (3.4241)	grad_norm 2.1294 (1.7549)	
[2022-01-23 09:00:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][380/1251]	eta 0:32:43 lr 0.000355	time 2.9284 (2.2549)	loss 3.1182 (3.4167)	grad_norm 1.6380 (1.7536)	
[2022-01-23 09:00:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][390/1251]	eta 0:32:14 lr 0.000355	time 1.7441 (2.2473)	loss 3.3202 (3.4192)	grad_norm 2.1048 (1.7543)	
[2022-01-23 09:01:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][400/1251]	eta 0:31:46 lr 0.000355	time 1.8648 (2.2400)	loss 2.8439 (3.4151)	grad_norm 1.7633 (1.7546)	
[2022-01-23 09:01:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][410/1251]	eta 0:31:21 lr 0.000355	time 1.9051 (2.2378)	loss 2.9020 (3.4147)	grad_norm 1.5413 (1.7549)	
[2022-01-23 09:01:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][420/1251]	eta 0:31:05 lr 0.000355	time 3.3361 (2.2444)	loss 3.7778 (3.4137)	grad_norm 1.7944 (1.7545)	
[2022-01-23 09:02:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][430/1251]	eta 0:30:43 lr 0.000355	time 2.4890 (2.2460)	loss 3.5267 (3.4124)	grad_norm 1.7828 (1.7545)	
[2022-01-23 09:02:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][440/1251]	eta 0:30:21 lr 0.000355	time 1.9073 (2.2459)	loss 3.6023 (3.4118)	grad_norm 1.5837 (1.7526)	
[2022-01-23 09:03:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][450/1251]	eta 0:29:53 lr 0.000355	time 1.8665 (2.2388)	loss 3.6868 (3.4111)	grad_norm 1.7657 (1.7513)	
[2022-01-23 09:03:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][460/1251]	eta 0:29:26 lr 0.000355	time 2.3028 (2.2331)	loss 3.8500 (3.4122)	grad_norm 2.0429 (1.7526)	
[2022-01-23 09:03:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][470/1251]	eta 0:29:01 lr 0.000355	time 1.4893 (2.2300)	loss 3.9079 (3.4113)	grad_norm 1.7299 (1.7529)	
[2022-01-23 09:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][480/1251]	eta 0:28:41 lr 0.000355	time 1.5463 (2.2324)	loss 2.3311 (3.4084)	grad_norm 1.8432 (1.7517)	
[2022-01-23 09:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][490/1251]	eta 0:28:19 lr 0.000355	time 2.4391 (2.2337)	loss 3.7225 (3.4087)	grad_norm 1.8917 (1.7528)	
[2022-01-23 09:04:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][500/1251]	eta 0:27:55 lr 0.000355	time 2.5752 (2.2311)	loss 3.6098 (3.4087)	grad_norm 1.5623 (1.7515)	
[2022-01-23 09:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][510/1251]	eta 0:27:31 lr 0.000355	time 2.0044 (2.2285)	loss 3.8345 (3.4108)	grad_norm 1.8574 (1.7497)	
[2022-01-23 09:05:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][520/1251]	eta 0:27:06 lr 0.000355	time 1.5479 (2.2251)	loss 3.7336 (3.4120)	grad_norm 1.9808 (1.7488)	
[2022-01-23 09:05:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][530/1251]	eta 0:26:43 lr 0.000355	time 1.2578 (2.2237)	loss 2.2941 (3.4098)	grad_norm 1.6212 (1.7484)	
[2022-01-23 09:06:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][540/1251]	eta 0:26:19 lr 0.000355	time 1.8215 (2.2211)	loss 4.0770 (3.4112)	grad_norm 1.9949 (1.7504)	
[2022-01-23 09:06:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][550/1251]	eta 0:25:57 lr 0.000355	time 1.9167 (2.2221)	loss 3.3282 (3.4162)	grad_norm 1.6949 (1.7508)	
[2022-01-23 09:06:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][560/1251]	eta 0:25:37 lr 0.000355	time 2.5070 (2.2250)	loss 3.7449 (3.4156)	grad_norm 1.7568 (1.7528)	
[2022-01-23 09:07:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][570/1251]	eta 0:25:15 lr 0.000355	time 1.8939 (2.2253)	loss 3.7256 (3.4169)	grad_norm 2.1844 (1.7542)	
[2022-01-23 09:07:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][580/1251]	eta 0:24:54 lr 0.000355	time 2.2374 (2.2279)	loss 3.6441 (3.4184)	grad_norm 1.6232 (1.7529)	
[2022-01-23 09:08:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][590/1251]	eta 0:24:31 lr 0.000355	time 1.8586 (2.2259)	loss 2.9646 (3.4181)	grad_norm 1.6964 (1.7519)	
[2022-01-23 09:08:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][600/1251]	eta 0:24:07 lr 0.000355	time 1.8781 (2.2240)	loss 3.5892 (3.4174)	grad_norm 1.5060 (1.7516)	
[2022-01-23 09:08:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][610/1251]	eta 0:23:44 lr 0.000355	time 1.9964 (2.2229)	loss 3.5297 (3.4218)	grad_norm 1.9549 (1.7511)	
[2022-01-23 09:09:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][620/1251]	eta 0:23:20 lr 0.000355	time 2.2777 (2.2199)	loss 3.0023 (3.4204)	grad_norm 2.0071 (1.7516)	
[2022-01-23 09:09:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][630/1251]	eta 0:22:58 lr 0.000354	time 1.9889 (2.2192)	loss 3.3078 (3.4199)	grad_norm 2.2578 (1.7540)	
[2022-01-23 09:09:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][640/1251]	eta 0:22:35 lr 0.000354	time 2.3371 (2.2185)	loss 2.8910 (3.4184)	grad_norm 1.9302 (1.7536)	
[2022-01-23 09:10:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][650/1251]	eta 0:22:13 lr 0.000354	time 1.5910 (2.2181)	loss 4.2649 (3.4210)	grad_norm 1.5961 (1.7527)	
[2022-01-23 09:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][660/1251]	eta 0:21:49 lr 0.000354	time 1.6685 (2.2161)	loss 2.1750 (3.4194)	grad_norm 2.0242 (1.7527)	
[2022-01-23 09:10:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][670/1251]	eta 0:21:27 lr 0.000354	time 1.9791 (2.2167)	loss 4.1744 (3.4207)	grad_norm 1.7117 (1.7525)	
[2022-01-23 09:11:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][680/1251]	eta 0:21:05 lr 0.000354	time 2.3378 (2.2160)	loss 3.0389 (3.4218)	grad_norm 1.8409 (1.7522)	
[2022-01-23 09:11:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][690/1251]	eta 0:20:44 lr 0.000354	time 2.3569 (2.2181)	loss 2.7637 (3.4207)	grad_norm 1.5802 (1.7517)	
[2022-01-23 09:12:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][700/1251]	eta 0:20:22 lr 0.000354	time 1.8968 (2.2183)	loss 3.3152 (3.4197)	grad_norm 1.7459 (1.7504)	
[2022-01-23 09:12:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][710/1251]	eta 0:20:00 lr 0.000354	time 2.1979 (2.2187)	loss 2.4880 (3.4172)	grad_norm 1.6526 (1.7489)	
[2022-01-23 09:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][720/1251]	eta 0:19:37 lr 0.000354	time 1.9721 (2.2170)	loss 3.8710 (3.4161)	grad_norm 1.6306 (1.7466)	
[2022-01-23 09:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][730/1251]	eta 0:19:14 lr 0.000354	time 1.8467 (2.2156)	loss 3.6719 (3.4184)	grad_norm 1.6353 (1.7446)	
[2022-01-23 09:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][740/1251]	eta 0:18:51 lr 0.000354	time 2.4691 (2.2149)	loss 2.8582 (3.4167)	grad_norm 1.4932 (1.7436)	
[2022-01-23 09:13:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][750/1251]	eta 0:18:30 lr 0.000354	time 2.2667 (2.2160)	loss 4.0880 (3.4181)	grad_norm 1.8400 (1.7438)	
[2022-01-23 09:14:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][760/1251]	eta 0:18:06 lr 0.000354	time 1.9488 (2.2131)	loss 3.2531 (3.4201)	grad_norm 1.8212 (1.7448)	
[2022-01-23 09:14:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][770/1251]	eta 0:17:42 lr 0.000354	time 2.1772 (2.2096)	loss 2.4146 (3.4183)	grad_norm 1.5655 (1.7436)	
[2022-01-23 09:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][780/1251]	eta 0:17:20 lr 0.000354	time 2.1105 (2.2086)	loss 2.3812 (3.4194)	grad_norm 1.5898 (1.7446)	
[2022-01-23 09:15:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][790/1251]	eta 0:16:58 lr 0.000354	time 2.4351 (2.2095)	loss 2.4014 (3.4137)	grad_norm 1.6182 (1.7456)	
[2022-01-23 09:15:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][800/1251]	eta 0:16:37 lr 0.000354	time 1.9769 (2.2111)	loss 3.7889 (3.4156)	grad_norm 1.5618 (1.7455)	
[2022-01-23 09:16:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][810/1251]	eta 0:16:15 lr 0.000354	time 2.2973 (2.2110)	loss 3.3328 (3.4136)	grad_norm 2.0483 (1.7447)	
[2022-01-23 09:16:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][820/1251]	eta 0:15:53 lr 0.000354	time 2.5343 (2.2115)	loss 3.5660 (3.4132)	grad_norm 1.6513 (1.7441)	
[2022-01-23 09:16:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][830/1251]	eta 0:15:31 lr 0.000354	time 2.2320 (2.2133)	loss 3.0706 (3.4149)	grad_norm 1.7428 (1.7433)	
[2022-01-23 09:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][840/1251]	eta 0:15:09 lr 0.000354	time 1.7315 (2.2126)	loss 3.5881 (3.4144)	grad_norm 1.5680 (1.7441)	
[2022-01-23 09:17:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][850/1251]	eta 0:14:46 lr 0.000354	time 1.5396 (2.2114)	loss 2.9408 (3.4119)	grad_norm 1.6491 (1.7438)	
[2022-01-23 09:17:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][860/1251]	eta 0:14:23 lr 0.000354	time 1.7420 (2.2084)	loss 2.9191 (3.4110)	grad_norm 1.8118 (1.7428)	
[2022-01-23 09:18:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][870/1251]	eta 0:14:01 lr 0.000354	time 1.9441 (2.2079)	loss 2.3469 (3.4076)	grad_norm 1.6729 (1.7420)	
[2022-01-23 09:18:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][880/1251]	eta 0:13:39 lr 0.000353	time 1.9249 (2.2077)	loss 4.2842 (3.4091)	grad_norm 1.8284 (1.7425)	
[2022-01-23 09:18:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][890/1251]	eta 0:13:17 lr 0.000353	time 1.9736 (2.2079)	loss 3.0266 (3.4095)	grad_norm 1.8415 (1.7421)	
[2022-01-23 09:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][900/1251]	eta 0:12:55 lr 0.000353	time 1.9970 (2.2095)	loss 3.7584 (3.4072)	grad_norm 1.7169 (1.7419)	
[2022-01-23 09:19:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][910/1251]	eta 0:12:33 lr 0.000353	time 2.1888 (2.2097)	loss 2.7593 (3.4068)	grad_norm 1.6860 (1.7410)	
[2022-01-23 09:20:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][920/1251]	eta 0:12:10 lr 0.000353	time 2.2034 (2.2083)	loss 2.4896 (3.4049)	grad_norm 1.8490 (1.7402)	
[2022-01-23 09:20:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][930/1251]	eta 0:11:48 lr 0.000353	time 1.8714 (2.2068)	loss 3.6596 (3.4046)	grad_norm 1.5890 (1.7399)	
[2022-01-23 09:20:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][940/1251]	eta 0:11:25 lr 0.000353	time 1.9140 (2.2057)	loss 3.3244 (3.4020)	grad_norm 1.9858 (1.7403)	
[2022-01-23 09:21:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][950/1251]	eta 0:11:03 lr 0.000353	time 2.1308 (2.2046)	loss 3.2841 (3.4022)	grad_norm 1.8265 (1.7411)	
[2022-01-23 09:21:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][960/1251]	eta 0:10:42 lr 0.000353	time 2.9505 (2.2068)	loss 2.7422 (3.4028)	grad_norm 1.5109 (1.7406)	
[2022-01-23 09:21:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][970/1251]	eta 0:10:19 lr 0.000353	time 1.9251 (2.2063)	loss 3.0319 (3.4032)	grad_norm 1.7475 (1.7406)	
[2022-01-23 09:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][980/1251]	eta 0:09:58 lr 0.000353	time 2.7504 (2.2076)	loss 3.7074 (3.4068)	grad_norm 1.6789 (1.7399)	
[2022-01-23 09:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][990/1251]	eta 0:09:36 lr 0.000353	time 2.0267 (2.2076)	loss 3.6557 (3.4096)	grad_norm 1.6925 (1.7388)	
[2022-01-23 09:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1000/1251]	eta 0:09:13 lr 0.000353	time 2.1856 (2.2069)	loss 3.6596 (3.4085)	grad_norm 1.5517 (1.7383)	
[2022-01-23 09:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1010/1251]	eta 0:08:51 lr 0.000353	time 1.8310 (2.2042)	loss 2.6220 (3.4052)	grad_norm 1.5385 (1.7374)	
[2022-01-23 09:23:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1020/1251]	eta 0:08:28 lr 0.000353	time 1.9363 (2.2023)	loss 1.9905 (3.4041)	grad_norm 1.7006 (1.7379)	
[2022-01-23 09:23:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1030/1251]	eta 0:08:06 lr 0.000353	time 1.9314 (2.2004)	loss 2.4591 (3.4051)	grad_norm 2.1751 (1.7381)	
[2022-01-23 09:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1040/1251]	eta 0:07:44 lr 0.000353	time 2.8392 (2.2009)	loss 2.8635 (3.4008)	grad_norm 1.7144 (1.7383)	
[2022-01-23 09:24:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1050/1251]	eta 0:07:22 lr 0.000353	time 1.5663 (2.2015)	loss 3.9373 (3.4026)	grad_norm 1.5648 (1.7376)	
[2022-01-23 09:25:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1060/1251]	eta 0:07:00 lr 0.000353	time 2.3788 (2.2026)	loss 3.7144 (3.4033)	grad_norm 1.5836 (1.7372)	
[2022-01-23 09:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1070/1251]	eta 0:06:38 lr 0.000353	time 1.9211 (2.2042)	loss 3.4642 (3.4039)	grad_norm 1.5165 (1.7369)	
[2022-01-23 09:25:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1080/1251]	eta 0:06:17 lr 0.000353	time 2.6090 (2.2075)	loss 2.6389 (3.4040)	grad_norm 1.6226 (1.7361)	
[2022-01-23 09:26:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1090/1251]	eta 0:05:55 lr 0.000353	time 2.0956 (2.2074)	loss 3.3080 (3.4041)	grad_norm 1.8432 (1.7370)	
[2022-01-23 09:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1100/1251]	eta 0:05:33 lr 0.000353	time 1.8736 (2.2059)	loss 4.1272 (3.4056)	grad_norm 1.7385 (1.7367)	
[2022-01-23 09:26:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1110/1251]	eta 0:05:10 lr 0.000353	time 1.9330 (2.2037)	loss 4.0480 (3.4072)	grad_norm 1.8250 (1.7372)	
[2022-01-23 09:27:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1120/1251]	eta 0:04:48 lr 0.000353	time 1.9136 (2.2021)	loss 4.1420 (3.4068)	grad_norm 1.8222 (1.7372)	
[2022-01-23 09:27:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1130/1251]	eta 0:04:26 lr 0.000353	time 1.8342 (2.2005)	loss 3.6375 (3.4056)	grad_norm 1.7422 (1.7365)	
[2022-01-23 09:28:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1140/1251]	eta 0:04:04 lr 0.000352	time 2.2753 (2.1992)	loss 3.8807 (3.4057)	grad_norm 1.5881 (1.7358)	
[2022-01-23 09:28:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1150/1251]	eta 0:03:42 lr 0.000352	time 2.1466 (2.1986)	loss 3.7086 (3.4066)	grad_norm 1.4858 (1.7357)	
[2022-01-23 09:28:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1160/1251]	eta 0:03:20 lr 0.000352	time 5.2908 (2.2028)	loss 3.3762 (3.4058)	grad_norm 1.6397 (1.7352)	
[2022-01-23 09:29:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1170/1251]	eta 0:02:58 lr 0.000352	time 4.1055 (2.2074)	loss 3.8337 (3.4042)	grad_norm 1.9408 (1.7352)	
[2022-01-23 09:29:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1180/1251]	eta 0:02:36 lr 0.000352	time 1.9569 (2.2067)	loss 2.9872 (3.4042)	grad_norm 1.5363 (1.7350)	
[2022-01-23 09:29:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1190/1251]	eta 0:02:14 lr 0.000352	time 1.8437 (2.2057)	loss 3.4741 (3.4039)	grad_norm 1.5235 (1.7348)	
[2022-01-23 09:30:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1200/1251]	eta 0:01:52 lr 0.000352	time 2.1869 (2.2048)	loss 3.5000 (3.4053)	grad_norm 1.4603 (1.7342)	
[2022-01-23 09:30:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1210/1251]	eta 0:01:30 lr 0.000352	time 2.8307 (2.2032)	loss 2.8239 (3.4039)	grad_norm 1.5221 (1.7337)	
[2022-01-23 09:31:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1220/1251]	eta 0:01:08 lr 0.000352	time 1.8809 (2.2027)	loss 3.8029 (3.4060)	grad_norm 1.5932 (1.7334)	
[2022-01-23 09:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1230/1251]	eta 0:00:46 lr 0.000352	time 2.2347 (2.2027)	loss 2.5902 (3.4032)	grad_norm 1.5426 (1.7329)	
[2022-01-23 09:31:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1240/1251]	eta 0:00:24 lr 0.000352	time 1.6770 (2.2032)	loss 2.3716 (3.4031)	grad_norm 1.6804 (1.7330)	
[2022-01-23 09:32:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [179/300][1250/1251]	eta 0:00:02 lr 0.000352	time 1.1565 (2.1979)	loss 3.4294 (3.4040)	grad_norm 1.7610 (1.7337)	
[2022-01-23 09:32:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 179 training takes 0:45:50
[2022-01-23 09:32:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.510 (18.510)	Loss 1.0461 (1.0461)	Acc@1 75.391 (75.391)	Acc@5 92.773 (92.773)	
[2022-01-23 09:32:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.041 (3.596)	Loss 0.9965 (0.9772)	Acc@1 76.660 (77.069)	Acc@5 92.969 (93.608)	
[2022-01-23 09:32:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.593 (2.565)	Loss 0.9610 (0.9725)	Acc@1 76.465 (77.162)	Acc@5 94.434 (93.871)	
[2022-01-23 09:33:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.918 (2.303)	Loss 0.9397 (0.9602)	Acc@1 78.320 (77.482)	Acc@5 94.531 (93.989)	
[2022-01-23 09:33:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.321 (2.200)	Loss 1.0851 (0.9678)	Acc@1 73.340 (77.203)	Acc@5 92.383 (93.936)	
[2022-01-23 09:33:38 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.260 Acc@5 93.968
[2022-01-23 09:33:38 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.3%
[2022-01-23 09:33:38 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.44%
[2022-01-23 09:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][0/1251]	eta 7:29:42 lr 0.000352	time 21.5687 (21.5687)	loss 3.4673 (3.4673)	grad_norm 1.7734 (1.7734)	
[2022-01-23 09:34:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][10/1251]	eta 1:27:19 lr 0.000352	time 2.8226 (4.2219)	loss 3.7473 (3.3331)	grad_norm 1.7377 (1.8143)	
[2022-01-23 09:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][20/1251]	eta 1:05:47 lr 0.000352	time 1.3064 (3.2071)	loss 2.4458 (3.3474)	grad_norm 1.9886 (1.8293)	
[2022-01-23 09:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][30/1251]	eta 0:58:36 lr 0.000352	time 1.5082 (2.8801)	loss 3.3241 (3.4317)	grad_norm 1.9506 (1.7971)	
[2022-01-23 09:35:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][40/1251]	eta 0:55:11 lr 0.000352	time 3.7520 (2.7347)	loss 3.5394 (3.4629)	grad_norm 1.4454 (1.7773)	
[2022-01-23 09:35:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][50/1251]	eta 0:52:31 lr 0.000352	time 1.5260 (2.6242)	loss 2.7637 (3.4166)	grad_norm 1.6016 (1.7656)	
[2022-01-23 09:36:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][60/1251]	eta 0:51:04 lr 0.000352	time 1.8587 (2.5732)	loss 4.1014 (3.3868)	grad_norm 1.5369 (1.7498)	
[2022-01-23 09:36:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][70/1251]	eta 0:49:54 lr 0.000352	time 1.5206 (2.5359)	loss 3.6688 (3.4126)	grad_norm 2.0350 (1.7489)	
[2022-01-23 09:37:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][80/1251]	eta 0:49:00 lr 0.000352	time 3.1018 (2.5108)	loss 3.8034 (3.4131)	grad_norm 1.8195 (1.7399)	
[2022-01-23 09:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][90/1251]	eta 0:47:45 lr 0.000352	time 1.8701 (2.4680)	loss 3.1762 (3.3925)	grad_norm 2.0285 (1.7378)	
[2022-01-23 09:37:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][100/1251]	eta 0:46:38 lr 0.000352	time 1.9223 (2.4314)	loss 2.8741 (3.4004)	grad_norm 1.5466 (1.7368)	
[2022-01-23 09:38:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][110/1251]	eta 0:45:39 lr 0.000352	time 1.9612 (2.4007)	loss 3.9843 (3.3952)	grad_norm 1.8982 (1.7413)	
[2022-01-23 09:38:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][120/1251]	eta 0:44:47 lr 0.000352	time 2.7939 (2.3760)	loss 2.9960 (3.3745)	grad_norm 1.9316 (1.7434)	
[2022-01-23 09:38:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][130/1251]	eta 0:43:51 lr 0.000352	time 1.8879 (2.3477)	loss 2.9981 (3.3689)	grad_norm 1.9462 (1.7455)	
[2022-01-23 09:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][140/1251]	eta 0:43:30 lr 0.000351	time 3.0646 (2.3498)	loss 4.1375 (3.3692)	grad_norm 1.4700 (1.7403)	
[2022-01-23 09:39:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][150/1251]	eta 0:42:52 lr 0.000351	time 2.2541 (2.3365)	loss 2.7197 (3.3707)	grad_norm 1.5907 (1.7399)	
[2022-01-23 09:39:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][160/1251]	eta 0:42:27 lr 0.000351	time 1.5447 (2.3354)	loss 3.5158 (3.3632)	grad_norm 1.8553 (1.7386)	
[2022-01-23 09:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][170/1251]	eta 0:41:54 lr 0.000351	time 1.5842 (2.3258)	loss 3.6517 (3.3634)	grad_norm 1.6597 (1.7397)	
[2022-01-23 09:40:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][180/1251]	eta 0:41:26 lr 0.000351	time 2.4888 (2.3218)	loss 3.8451 (3.3716)	grad_norm 2.2677 (1.7431)	
[2022-01-23 09:41:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][190/1251]	eta 0:40:53 lr 0.000351	time 2.2206 (2.3128)	loss 3.5014 (3.3732)	grad_norm 1.9933 (1.7495)	
[2022-01-23 09:41:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][200/1251]	eta 0:40:25 lr 0.000351	time 1.5144 (2.3080)	loss 3.4083 (3.3897)	grad_norm 2.0461 (1.7513)	
[2022-01-23 09:41:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][210/1251]	eta 0:39:58 lr 0.000351	time 1.8149 (2.3039)	loss 3.7317 (3.3896)	grad_norm 1.5143 (1.7516)	
[2022-01-23 09:42:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][220/1251]	eta 0:39:35 lr 0.000351	time 2.9899 (2.3038)	loss 4.0556 (3.3972)	grad_norm 1.9039 (1.7511)	
[2022-01-23 09:42:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][230/1251]	eta 0:38:58 lr 0.000351	time 1.9374 (2.2901)	loss 3.7182 (3.3933)	grad_norm 2.0998 (1.7501)	
[2022-01-23 09:42:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][240/1251]	eta 0:38:19 lr 0.000351	time 1.9457 (2.2749)	loss 2.3734 (3.3786)	grad_norm 1.6034 (1.7489)	
[2022-01-23 09:43:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][250/1251]	eta 0:37:47 lr 0.000351	time 2.3240 (2.2655)	loss 4.2074 (3.3832)	grad_norm 1.6191 (1.7472)	
[2022-01-23 09:43:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][260/1251]	eta 0:37:19 lr 0.000351	time 2.5217 (2.2599)	loss 2.9013 (3.3818)	grad_norm 1.5764 (1.7521)	
[2022-01-23 09:43:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][270/1251]	eta 0:36:50 lr 0.000351	time 2.1467 (2.2534)	loss 3.6546 (3.3805)	grad_norm 1.8102 (1.7519)	
[2022-01-23 09:44:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][280/1251]	eta 0:36:31 lr 0.000351	time 2.3348 (2.2564)	loss 4.0740 (3.3816)	grad_norm 1.6164 (1.7523)	
[2022-01-23 09:44:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][290/1251]	eta 0:36:08 lr 0.000351	time 1.9858 (2.2560)	loss 4.1143 (3.3749)	grad_norm 1.9213 (1.7567)	
[2022-01-23 09:44:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][300/1251]	eta 0:35:50 lr 0.000351	time 3.4188 (2.2617)	loss 3.5858 (3.3796)	grad_norm 1.5060 (1.7594)	
[2022-01-23 09:45:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][310/1251]	eta 0:35:28 lr 0.000351	time 2.2226 (2.2616)	loss 3.8372 (3.3766)	grad_norm 1.7911 (1.7600)	
[2022-01-23 09:45:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][320/1251]	eta 0:35:00 lr 0.000351	time 1.8743 (2.2562)	loss 2.4790 (3.3642)	grad_norm 1.8440 (1.7596)	
[2022-01-23 09:46:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][330/1251]	eta 0:34:34 lr 0.000351	time 2.2981 (2.2527)	loss 3.0048 (3.3774)	grad_norm 1.5439 (1.7604)	
[2022-01-23 09:46:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][340/1251]	eta 0:34:09 lr 0.000351	time 2.9288 (2.2493)	loss 3.7591 (3.3784)	grad_norm 1.7559 (1.7592)	
[2022-01-23 09:46:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][350/1251]	eta 0:33:45 lr 0.000351	time 2.2479 (2.2486)	loss 3.0985 (3.3828)	grad_norm 1.8219 (1.7601)	
[2022-01-23 09:47:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][360/1251]	eta 0:33:24 lr 0.000351	time 2.4321 (2.2499)	loss 3.4256 (3.3910)	grad_norm 1.6767 (1.7587)	
[2022-01-23 09:47:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][370/1251]	eta 0:33:00 lr 0.000351	time 2.5312 (2.2485)	loss 3.6960 (3.3913)	grad_norm 1.7621 (1.7596)	
[2022-01-23 09:47:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][380/1251]	eta 0:32:36 lr 0.000351	time 3.4055 (2.2463)	loss 3.5995 (3.3893)	grad_norm 1.7189 (1.7645)	
[2022-01-23 09:48:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][390/1251]	eta 0:32:10 lr 0.000351	time 2.4636 (2.2420)	loss 3.9660 (3.3941)	grad_norm 1.9208 (1.7661)	
[2022-01-23 09:48:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][400/1251]	eta 0:31:45 lr 0.000350	time 1.6954 (2.2397)	loss 3.6168 (3.3977)	grad_norm 1.5786 (1.7662)	
[2022-01-23 09:48:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][410/1251]	eta 0:31:21 lr 0.000350	time 1.5800 (2.2369)	loss 3.5545 (3.3954)	grad_norm 1.8255 (1.7639)	
[2022-01-23 09:49:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][420/1251]	eta 0:31:03 lr 0.000350	time 4.9781 (2.2426)	loss 3.9392 (3.3978)	grad_norm 1.5171 (1.7623)	
[2022-01-23 09:49:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][430/1251]	eta 0:30:42 lr 0.000350	time 2.6903 (2.2446)	loss 3.9369 (3.4029)	grad_norm 2.1497 (1.7630)	
[2022-01-23 09:50:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][440/1251]	eta 0:30:16 lr 0.000350	time 1.6156 (2.2394)	loss 3.8097 (3.4003)	grad_norm 1.9431 (1.7626)	
[2022-01-23 09:50:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][450/1251]	eta 0:29:51 lr 0.000350	time 1.8393 (2.2362)	loss 2.9949 (3.4052)	grad_norm 1.7430 (1.7612)	
[2022-01-23 09:50:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][460/1251]	eta 0:29:27 lr 0.000350	time 2.6576 (2.2340)	loss 3.8797 (3.4015)	grad_norm 1.7572 (1.7609)	
[2022-01-23 09:51:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][470/1251]	eta 0:29:01 lr 0.000350	time 2.2627 (2.2295)	loss 3.6413 (3.3973)	grad_norm 1.6784 (1.7604)	
[2022-01-23 09:51:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][480/1251]	eta 0:28:39 lr 0.000350	time 2.1890 (2.2302)	loss 2.4593 (3.3996)	grad_norm 1.6864 (1.7604)	
[2022-01-23 09:51:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][490/1251]	eta 0:28:16 lr 0.000350	time 1.8520 (2.2292)	loss 2.7970 (3.3989)	grad_norm 1.5890 (1.7598)	
[2022-01-23 09:52:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][500/1251]	eta 0:27:54 lr 0.000350	time 2.4492 (2.2294)	loss 2.1975 (3.3960)	grad_norm 1.6192 (1.7604)	
[2022-01-23 09:52:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][510/1251]	eta 0:27:30 lr 0.000350	time 2.2039 (2.2278)	loss 3.5544 (3.3984)	grad_norm 1.9667 (1.7619)	
[2022-01-23 09:52:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][520/1251]	eta 0:27:09 lr 0.000350	time 2.7837 (2.2285)	loss 2.7923 (3.3976)	grad_norm 1.6255 (1.7623)	
[2022-01-23 09:53:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][530/1251]	eta 0:26:47 lr 0.000350	time 2.5126 (2.2300)	loss 3.4108 (3.3980)	grad_norm 1.5443 (1.7593)	
[2022-01-23 09:53:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][540/1251]	eta 0:26:24 lr 0.000350	time 2.7949 (2.2285)	loss 3.5769 (3.3962)	grad_norm 1.7958 (1.7601)	
[2022-01-23 09:54:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][550/1251]	eta 0:26:01 lr 0.000350	time 2.1528 (2.2275)	loss 3.5777 (3.4004)	grad_norm 1.5222 (1.7576)	
[2022-01-23 09:54:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][560/1251]	eta 0:25:37 lr 0.000350	time 1.9666 (2.2258)	loss 3.6607 (3.3992)	grad_norm 1.8856 (1.7588)	
[2022-01-23 09:54:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][570/1251]	eta 0:25:16 lr 0.000350	time 2.8631 (2.2276)	loss 3.5375 (3.4014)	grad_norm 1.7907 (1.7589)	
[2022-01-23 09:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][580/1251]	eta 0:24:54 lr 0.000350	time 2.2144 (2.2269)	loss 2.7036 (3.4027)	grad_norm 1.7773 (1.7604)	
[2022-01-23 09:55:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][590/1251]	eta 0:24:29 lr 0.000350	time 1.9736 (2.2227)	loss 2.6730 (3.4036)	grad_norm 1.9728 (1.7630)	
[2022-01-23 09:55:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][600/1251]	eta 0:24:04 lr 0.000350	time 2.1972 (2.2194)	loss 3.1601 (3.4055)	grad_norm 1.6697 (1.7646)	
[2022-01-23 09:56:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][610/1251]	eta 0:23:40 lr 0.000350	time 1.6185 (2.2157)	loss 4.2405 (3.4051)	grad_norm 1.8332 (1.7672)	
[2022-01-23 09:56:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][620/1251]	eta 0:23:18 lr 0.000350	time 2.7585 (2.2155)	loss 2.8320 (3.4031)	grad_norm 1.6028 (1.7663)	
[2022-01-23 09:56:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][630/1251]	eta 0:22:57 lr 0.000350	time 1.6125 (2.2185)	loss 2.2704 (3.4028)	grad_norm 1.6576 (1.7663)	
[2022-01-23 09:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][640/1251]	eta 0:22:39 lr 0.000350	time 2.4136 (2.2253)	loss 2.5906 (3.4014)	grad_norm 1.5734 (1.7649)	
[2022-01-23 09:57:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][650/1251]	eta 0:22:17 lr 0.000349	time 1.8869 (2.2260)	loss 3.2511 (3.4043)	grad_norm 1.4865 (1.7643)	
[2022-01-23 09:58:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][660/1251]	eta 0:21:56 lr 0.000349	time 3.6477 (2.2273)	loss 2.8443 (3.4045)	grad_norm 1.5205 (1.7630)	
[2022-01-23 09:58:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][670/1251]	eta 0:21:31 lr 0.000349	time 1.8878 (2.2236)	loss 3.2828 (3.4052)	grad_norm 1.5331 (1.7611)	
[2022-01-23 09:58:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][680/1251]	eta 0:21:07 lr 0.000349	time 2.0423 (2.2190)	loss 3.6125 (3.4075)	grad_norm 1.8255 (1.7611)	
[2022-01-23 09:59:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][690/1251]	eta 0:20:43 lr 0.000349	time 1.4595 (2.2159)	loss 3.2571 (3.4095)	grad_norm 1.6401 (1.7616)	
[2022-01-23 09:59:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][700/1251]	eta 0:20:20 lr 0.000349	time 2.5968 (2.2154)	loss 3.9006 (3.4108)	grad_norm 1.7651 (1.7607)	
[2022-01-23 09:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][710/1251]	eta 0:19:57 lr 0.000349	time 1.5715 (2.2143)	loss 3.8936 (3.4101)	grad_norm 1.6806 (1.7605)	
[2022-01-23 10:00:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][720/1251]	eta 0:19:35 lr 0.000349	time 2.8437 (2.2145)	loss 4.3448 (3.4137)	grad_norm 1.8371 (1.7595)	
[2022-01-23 10:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][730/1251]	eta 0:19:15 lr 0.000349	time 1.6228 (2.2173)	loss 3.8933 (3.4130)	grad_norm 1.5676 (1.7597)	
[2022-01-23 10:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][740/1251]	eta 0:18:53 lr 0.000349	time 2.7929 (2.2178)	loss 4.1004 (3.4134)	grad_norm 1.5912 (1.7600)	
[2022-01-23 10:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][750/1251]	eta 0:18:30 lr 0.000349	time 1.8587 (2.2164)	loss 3.2847 (3.4135)	grad_norm 1.6124 (1.7601)	
[2022-01-23 10:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][760/1251]	eta 0:18:08 lr 0.000349	time 1.6887 (2.2171)	loss 3.8239 (3.4124)	grad_norm 1.6909 (1.7600)	
[2022-01-23 10:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][770/1251]	eta 0:17:46 lr 0.000349	time 1.5324 (2.2162)	loss 4.0624 (3.4178)	grad_norm 1.7022 (1.7590)	
[2022-01-23 10:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][780/1251]	eta 0:17:23 lr 0.000349	time 2.1068 (2.2163)	loss 3.9685 (3.4204)	grad_norm 2.0209 (1.7591)	
[2022-01-23 10:02:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][790/1251]	eta 0:17:01 lr 0.000349	time 2.6177 (2.2161)	loss 3.0482 (3.4194)	grad_norm 1.6420 (1.7599)	
[2022-01-23 10:03:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][800/1251]	eta 0:16:38 lr 0.000349	time 2.2904 (2.2140)	loss 3.2022 (3.4168)	grad_norm 1.6127 (1.7597)	
[2022-01-23 10:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][810/1251]	eta 0:16:15 lr 0.000349	time 1.8868 (2.2122)	loss 3.8341 (3.4170)	grad_norm 1.7755 (1.7596)	
[2022-01-23 10:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][820/1251]	eta 0:15:53 lr 0.000349	time 2.3604 (2.2128)	loss 3.5694 (3.4181)	grad_norm 1.9024 (1.7589)	
[2022-01-23 10:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][830/1251]	eta 0:15:31 lr 0.000349	time 2.4611 (2.2125)	loss 2.6660 (3.4184)	grad_norm 1.8396 (1.7575)	
[2022-01-23 10:04:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][840/1251]	eta 0:15:08 lr 0.000349	time 1.8526 (2.2113)	loss 3.4987 (3.4159)	grad_norm 1.7366 (1.7570)	
[2022-01-23 10:05:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][850/1251]	eta 0:14:47 lr 0.000349	time 2.2942 (2.2125)	loss 3.1530 (3.4187)	grad_norm 1.9262 (1.7574)	
[2022-01-23 10:05:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][860/1251]	eta 0:14:25 lr 0.000349	time 3.1370 (2.2135)	loss 2.7718 (3.4142)	grad_norm 1.5679 (1.7573)	
[2022-01-23 10:05:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][870/1251]	eta 0:14:03 lr 0.000349	time 2.4575 (2.2131)	loss 3.5739 (3.4137)	grad_norm 1.7720 (1.7573)	
[2022-01-23 10:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][880/1251]	eta 0:13:40 lr 0.000349	time 1.6327 (2.2117)	loss 3.7280 (3.4180)	grad_norm 2.4147 (1.7581)	
[2022-01-23 10:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][890/1251]	eta 0:13:18 lr 0.000349	time 1.9581 (2.2110)	loss 2.6599 (3.4194)	grad_norm 1.5890 (1.7575)	
[2022-01-23 10:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][900/1251]	eta 0:12:56 lr 0.000348	time 2.8203 (2.2118)	loss 4.0868 (3.4202)	grad_norm 1.7642 (1.7576)	
[2022-01-23 10:07:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][910/1251]	eta 0:12:34 lr 0.000348	time 2.2783 (2.2122)	loss 3.5060 (3.4210)	grad_norm 1.7556 (1.7592)	
[2022-01-23 10:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][920/1251]	eta 0:12:11 lr 0.000348	time 2.0575 (2.2099)	loss 3.9970 (3.4211)	grad_norm 1.6034 (1.7589)	
[2022-01-23 10:07:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][930/1251]	eta 0:11:48 lr 0.000348	time 1.9575 (2.2078)	loss 2.3684 (3.4206)	grad_norm 1.5780 (1.7582)	
[2022-01-23 10:08:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][940/1251]	eta 0:11:26 lr 0.000348	time 2.2071 (2.2064)	loss 2.9381 (3.4213)	grad_norm 1.7016 (1.7590)	
[2022-01-23 10:08:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][950/1251]	eta 0:11:04 lr 0.000348	time 2.1994 (2.2066)	loss 3.2616 (3.4159)	grad_norm 1.4908 (1.7593)	
[2022-01-23 10:08:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][960/1251]	eta 0:10:42 lr 0.000348	time 2.1433 (2.2063)	loss 2.5333 (3.4169)	grad_norm 1.6573 (1.7600)	
[2022-01-23 10:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][970/1251]	eta 0:10:20 lr 0.000348	time 2.8032 (2.2068)	loss 2.4865 (3.4149)	grad_norm 1.8126 (1.7612)	
[2022-01-23 10:09:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][980/1251]	eta 0:09:58 lr 0.000348	time 2.7820 (2.2072)	loss 3.3941 (3.4172)	grad_norm 1.6838 (1.7607)	
[2022-01-23 10:10:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][990/1251]	eta 0:09:35 lr 0.000348	time 2.5979 (2.2068)	loss 3.7358 (3.4170)	grad_norm 1.8371 (1.7607)	
[2022-01-23 10:10:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1000/1251]	eta 0:09:14 lr 0.000348	time 1.6878 (2.2081)	loss 3.4910 (3.4146)	grad_norm 1.6058 (1.7604)	
[2022-01-23 10:10:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1010/1251]	eta 0:08:52 lr 0.000348	time 2.3565 (2.2086)	loss 3.2337 (3.4160)	grad_norm 1.6581 (1.7617)	
[2022-01-23 10:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1020/1251]	eta 0:08:30 lr 0.000348	time 3.7184 (2.2094)	loss 3.2428 (3.4154)	grad_norm 1.8261 (1.7622)	
[2022-01-23 10:11:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1030/1251]	eta 0:08:08 lr 0.000348	time 2.1980 (2.2088)	loss 3.4394 (3.4148)	grad_norm 1.8434 (1.7622)	
[2022-01-23 10:11:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1040/1251]	eta 0:07:45 lr 0.000348	time 2.0332 (2.2070)	loss 3.7085 (3.4147)	grad_norm 1.9234 (1.7618)	
[2022-01-23 10:12:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1050/1251]	eta 0:07:23 lr 0.000348	time 2.2059 (2.2051)	loss 4.1460 (3.4151)	grad_norm 1.6544 (1.7618)	
[2022-01-23 10:12:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1060/1251]	eta 0:07:01 lr 0.000348	time 2.7340 (2.2050)	loss 3.1672 (3.4159)	grad_norm 1.6135 (1.7610)	
[2022-01-23 10:13:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1070/1251]	eta 0:06:39 lr 0.000348	time 2.0971 (2.2050)	loss 3.4807 (3.4159)	grad_norm 1.9755 (1.7614)	
[2022-01-23 10:13:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1080/1251]	eta 0:06:16 lr 0.000348	time 1.6613 (2.2037)	loss 2.8107 (3.4157)	grad_norm 1.7002 (1.7613)	
[2022-01-23 10:13:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1090/1251]	eta 0:05:54 lr 0.000348	time 1.5312 (2.2040)	loss 3.6695 (3.4167)	grad_norm 1.8349 (1.7608)	
[2022-01-23 10:14:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1100/1251]	eta 0:05:32 lr 0.000348	time 2.3817 (2.2041)	loss 3.8845 (3.4177)	grad_norm 1.6724 (1.7607)	
[2022-01-23 10:14:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1110/1251]	eta 0:05:10 lr 0.000348	time 2.4822 (2.2050)	loss 3.5481 (3.4184)	grad_norm 1.7518 (1.7600)	
[2022-01-23 10:14:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1120/1251]	eta 0:04:48 lr 0.000348	time 1.8025 (2.2054)	loss 2.6900 (3.4171)	grad_norm 1.8001 (1.7605)	
[2022-01-23 10:15:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1130/1251]	eta 0:04:26 lr 0.000348	time 1.7409 (2.2046)	loss 3.7839 (3.4190)	grad_norm 1.4429 (1.7601)	
[2022-01-23 10:15:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1140/1251]	eta 0:04:04 lr 0.000348	time 2.1509 (2.2054)	loss 2.8478 (3.4195)	grad_norm 1.9298 (1.7598)	
[2022-01-23 10:15:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1150/1251]	eta 0:03:42 lr 0.000348	time 2.0940 (2.2074)	loss 3.5417 (3.4190)	grad_norm 1.8435 (1.7603)	
[2022-01-23 10:16:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1160/1251]	eta 0:03:20 lr 0.000347	time 2.1659 (2.2065)	loss 3.2932 (3.4178)	grad_norm 1.7923 (1.7596)	
[2022-01-23 10:16:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1170/1251]	eta 0:02:58 lr 0.000347	time 1.9012 (2.2050)	loss 3.5404 (3.4179)	grad_norm 1.7089 (1.7594)	
[2022-01-23 10:17:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1180/1251]	eta 0:02:36 lr 0.000347	time 1.9015 (2.2042)	loss 3.8465 (3.4185)	grad_norm 1.6721 (1.7594)	
[2022-01-23 10:17:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1190/1251]	eta 0:02:14 lr 0.000347	time 1.9831 (2.2032)	loss 3.7754 (3.4176)	grad_norm 1.8464 (1.7605)	
[2022-01-23 10:17:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1200/1251]	eta 0:01:52 lr 0.000347	time 2.2185 (2.2014)	loss 4.1573 (3.4191)	grad_norm 1.8855 (1.7604)	
[2022-01-23 10:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1210/1251]	eta 0:01:30 lr 0.000347	time 1.8511 (2.2001)	loss 4.0422 (3.4192)	grad_norm 1.5182 (1.7600)	
[2022-01-23 10:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1220/1251]	eta 0:01:08 lr 0.000347	time 2.4923 (2.2004)	loss 3.9322 (3.4216)	grad_norm 1.6229 (1.7593)	
[2022-01-23 10:18:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1230/1251]	eta 0:00:46 lr 0.000347	time 1.9214 (2.2002)	loss 4.0858 (3.4232)	grad_norm 1.6944 (1.7590)	
[2022-01-23 10:19:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1240/1251]	eta 0:00:24 lr 0.000347	time 2.0296 (2.2001)	loss 3.7419 (3.4242)	grad_norm 1.8062 (1.7591)	
[2022-01-23 10:19:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [180/300][1250/1251]	eta 0:00:02 lr 0.000347	time 1.1361 (2.1948)	loss 3.4826 (3.4257)	grad_norm 1.5118 (1.7588)	
[2022-01-23 10:19:24 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 180 training takes 0:45:46
[2022-01-23 10:19:24 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_180 saving......
[2022-01-23 10:19:36 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_180 saved !!!
[2022-01-23 10:19:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 11.712 (11.712)	Loss 0.9382 (0.9382)	Acc@1 78.809 (78.809)	Acc@5 94.336 (94.336)	
[2022-01-23 10:20:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.311 (2.888)	Loss 0.9914 (0.9723)	Acc@1 76.270 (77.486)	Acc@5 93.457 (93.830)	
[2022-01-23 10:20:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.294 (2.144)	Loss 1.0055 (0.9740)	Acc@1 77.148 (77.125)	Acc@5 93.555 (93.750)	
[2022-01-23 10:20:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 5.273 (2.037)	Loss 0.9319 (0.9675)	Acc@1 77.832 (77.315)	Acc@5 95.117 (93.841)	
[2022-01-23 10:20:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.192 (1.908)	Loss 0.9668 (0.9621)	Acc@1 78.320 (77.525)	Acc@5 93.945 (93.891)	
[2022-01-23 10:21:02 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.510 Acc@5 93.960
[2022-01-23 10:21:02 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.5%
[2022-01-23 10:21:02 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.51%
[2022-01-23 10:21:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][0/1251]	eta 7:31:40 lr 0.000347	time 21.6634 (21.6634)	loss 3.7377 (3.7377)	grad_norm 1.8894 (1.8894)	
[2022-01-23 10:21:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][10/1251]	eta 1:23:13 lr 0.000347	time 1.7662 (4.0237)	loss 3.4957 (3.5600)	grad_norm 1.5371 (1.7804)	
[2022-01-23 10:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][20/1251]	eta 1:02:36 lr 0.000347	time 1.5367 (3.0519)	loss 3.7261 (3.6071)	grad_norm 1.9850 (1.8702)	
[2022-01-23 10:22:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][30/1251]	eta 0:55:19 lr 0.000347	time 1.7839 (2.7189)	loss 3.9238 (3.6155)	grad_norm 1.7460 (1.8838)	
[2022-01-23 10:22:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][40/1251]	eta 0:54:39 lr 0.000347	time 6.8835 (2.7082)	loss 2.0187 (3.5521)	grad_norm 1.5398 (1.8918)	
[2022-01-23 10:23:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][50/1251]	eta 0:52:12 lr 0.000347	time 1.8670 (2.6078)	loss 3.6244 (3.5747)	grad_norm 1.5871 (1.8565)	
[2022-01-23 10:23:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][60/1251]	eta 0:50:09 lr 0.000347	time 1.6251 (2.5271)	loss 4.1327 (3.5672)	grad_norm 1.7109 (1.8276)	
[2022-01-23 10:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][70/1251]	eta 0:48:46 lr 0.000347	time 1.5544 (2.4780)	loss 2.8920 (3.5677)	grad_norm 1.6606 (1.8381)	
[2022-01-23 10:24:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][80/1251]	eta 0:48:06 lr 0.000347	time 3.5596 (2.4653)	loss 4.4239 (3.5173)	grad_norm 1.5961 (1.8285)	
[2022-01-23 10:24:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][90/1251]	eta 0:47:22 lr 0.000347	time 2.0736 (2.4486)	loss 3.7337 (3.5271)	grad_norm 1.5812 (1.8083)	
[2022-01-23 10:25:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][100/1251]	eta 0:46:17 lr 0.000347	time 1.9056 (2.4130)	loss 2.5317 (3.5213)	grad_norm 1.7483 (1.8018)	
[2022-01-23 10:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][110/1251]	eta 0:45:18 lr 0.000347	time 1.5231 (2.3822)	loss 3.8525 (3.5016)	grad_norm 1.5609 (1.7911)	
[2022-01-23 10:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][120/1251]	eta 0:44:41 lr 0.000347	time 2.8179 (2.3706)	loss 3.5106 (3.4971)	grad_norm 1.6119 (1.7813)	
[2022-01-23 10:26:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][130/1251]	eta 0:44:01 lr 0.000347	time 2.0404 (2.3563)	loss 3.8676 (3.4792)	grad_norm 2.0205 (1.7797)	
[2022-01-23 10:26:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][140/1251]	eta 0:43:16 lr 0.000347	time 2.1225 (2.3374)	loss 3.7990 (3.4816)	grad_norm 1.7944 (1.7842)	
[2022-01-23 10:26:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][150/1251]	eta 0:42:54 lr 0.000347	time 1.8582 (2.3383)	loss 2.9779 (3.4843)	grad_norm 1.6638 (1.7805)	
[2022-01-23 10:27:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][160/1251]	eta 0:42:29 lr 0.000346	time 3.0694 (2.3365)	loss 3.7911 (3.4912)	grad_norm 1.4617 (1.7724)	
[2022-01-23 10:27:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][170/1251]	eta 0:41:53 lr 0.000346	time 1.8856 (2.3251)	loss 3.4604 (3.4923)	grad_norm 1.6158 (1.7705)	
[2022-01-23 10:28:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][180/1251]	eta 0:41:15 lr 0.000346	time 1.8606 (2.3110)	loss 3.4092 (3.4942)	grad_norm 1.8796 (1.7722)	
[2022-01-23 10:28:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][190/1251]	eta 0:40:39 lr 0.000346	time 2.2617 (2.2992)	loss 3.6752 (3.4827)	grad_norm 1.7319 (1.7717)	
[2022-01-23 10:28:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][200/1251]	eta 0:40:05 lr 0.000346	time 1.9769 (2.2884)	loss 4.0838 (3.4913)	grad_norm 1.8751 (1.7750)	
[2022-01-23 10:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][210/1251]	eta 0:39:29 lr 0.000346	time 1.8129 (2.2757)	loss 3.0691 (3.4936)	grad_norm 1.4443 (1.7704)	
[2022-01-23 10:29:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][220/1251]	eta 0:39:02 lr 0.000346	time 2.1344 (2.2719)	loss 2.3650 (3.4950)	grad_norm 1.8854 (1.7691)	
[2022-01-23 10:29:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][230/1251]	eta 0:38:37 lr 0.000346	time 2.1930 (2.2696)	loss 4.0855 (3.4753)	grad_norm 1.9612 (1.7679)	
[2022-01-23 10:30:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][240/1251]	eta 0:38:15 lr 0.000346	time 2.3717 (2.2709)	loss 2.5162 (3.4770)	grad_norm 1.7611 (1.7672)	
[2022-01-23 10:30:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][250/1251]	eta 0:37:53 lr 0.000346	time 2.1314 (2.2709)	loss 2.2578 (3.4754)	grad_norm 1.8024 (1.7638)	
[2022-01-23 10:30:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][260/1251]	eta 0:37:30 lr 0.000346	time 2.0101 (2.2712)	loss 3.7503 (3.4655)	grad_norm 1.5792 (1.7695)	
[2022-01-23 10:31:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][270/1251]	eta 0:37:02 lr 0.000346	time 1.9350 (2.2657)	loss 3.3601 (3.4601)	grad_norm 1.5270 (1.7717)	
[2022-01-23 10:31:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][280/1251]	eta 0:36:37 lr 0.000346	time 2.3196 (2.2634)	loss 3.7587 (3.4587)	grad_norm 1.8944 (1.7692)	
[2022-01-23 10:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][290/1251]	eta 0:36:09 lr 0.000346	time 1.5299 (2.2571)	loss 3.7296 (3.4632)	grad_norm 1.9420 (1.7718)	
[2022-01-23 10:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][300/1251]	eta 0:35:42 lr 0.000346	time 1.9378 (2.2532)	loss 2.4105 (3.4589)	grad_norm 1.7923 (1.7756)	
[2022-01-23 10:32:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][310/1251]	eta 0:35:20 lr 0.000346	time 1.9195 (2.2532)	loss 3.6463 (3.4546)	grad_norm 1.7246 (1.7746)	
[2022-01-23 10:33:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][320/1251]	eta 0:34:58 lr 0.000346	time 1.7619 (2.2535)	loss 3.7119 (3.4500)	grad_norm 1.7165 (1.7720)	
[2022-01-23 10:33:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][330/1251]	eta 0:34:33 lr 0.000346	time 1.5772 (2.2514)	loss 3.5816 (3.4476)	grad_norm 1.8481 (1.7699)	
[2022-01-23 10:33:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][340/1251]	eta 0:34:11 lr 0.000346	time 2.4274 (2.2517)	loss 3.2706 (3.4422)	grad_norm 1.5129 (1.7664)	
[2022-01-23 10:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][350/1251]	eta 0:33:43 lr 0.000346	time 1.9197 (2.2461)	loss 2.7162 (3.4404)	grad_norm 1.7991 (1.7657)	
[2022-01-23 10:34:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][360/1251]	eta 0:33:16 lr 0.000346	time 1.5959 (2.2411)	loss 3.7690 (3.4320)	grad_norm 1.6502 (1.7662)	
[2022-01-23 10:34:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][370/1251]	eta 0:32:51 lr 0.000346	time 1.7377 (2.2379)	loss 3.9911 (3.4333)	grad_norm 1.6517 (1.7673)	
[2022-01-23 10:35:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][380/1251]	eta 0:32:30 lr 0.000346	time 2.5827 (2.2390)	loss 2.9454 (3.4323)	grad_norm 1.7835 (1.7669)	
[2022-01-23 10:35:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][390/1251]	eta 0:32:04 lr 0.000346	time 1.6009 (2.2351)	loss 3.7236 (3.4296)	grad_norm 2.6411 (1.7715)	
[2022-01-23 10:35:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][400/1251]	eta 0:31:38 lr 0.000346	time 1.8697 (2.2311)	loss 3.1175 (3.4276)	grad_norm 1.7256 (1.7731)	
[2022-01-23 10:36:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][410/1251]	eta 0:31:18 lr 0.000346	time 1.8894 (2.2337)	loss 2.6352 (3.4318)	grad_norm 1.9821 (1.7726)	
[2022-01-23 10:36:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][420/1251]	eta 0:30:57 lr 0.000345	time 2.1421 (2.2357)	loss 3.8937 (3.4309)	grad_norm 1.7834 (1.7701)	
[2022-01-23 10:37:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][430/1251]	eta 0:30:34 lr 0.000345	time 1.8947 (2.2340)	loss 3.4872 (3.4281)	grad_norm 1.6724 (1.7672)	
[2022-01-23 10:37:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][440/1251]	eta 0:30:10 lr 0.000345	time 1.9026 (2.2322)	loss 3.7372 (3.4314)	grad_norm 1.7231 (1.7641)	
[2022-01-23 10:37:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][450/1251]	eta 0:29:46 lr 0.000345	time 2.0224 (2.2302)	loss 2.7826 (3.4333)	grad_norm 1.6310 (1.7628)	
[2022-01-23 10:38:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][460/1251]	eta 0:29:19 lr 0.000345	time 1.7115 (2.2246)	loss 4.2214 (3.4354)	grad_norm 1.9245 (1.7627)	
[2022-01-23 10:38:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][470/1251]	eta 0:28:55 lr 0.000345	time 1.9929 (2.2223)	loss 3.6478 (3.4378)	grad_norm 1.7679 (1.7627)	
[2022-01-23 10:38:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][480/1251]	eta 0:28:34 lr 0.000345	time 2.6516 (2.2234)	loss 4.3277 (3.4410)	grad_norm 1.6128 (1.7626)	
[2022-01-23 10:39:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][490/1251]	eta 0:28:11 lr 0.000345	time 1.7920 (2.2231)	loss 3.9224 (3.4449)	grad_norm 1.7987 (1.7623)	
[2022-01-23 10:39:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][500/1251]	eta 0:27:47 lr 0.000345	time 1.7357 (2.2202)	loss 3.6054 (3.4466)	grad_norm 1.6077 (1.7630)	
[2022-01-23 10:39:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][510/1251]	eta 0:27:23 lr 0.000345	time 2.5542 (2.2183)	loss 3.7993 (3.4450)	grad_norm 1.7576 (1.7634)	
[2022-01-23 10:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][520/1251]	eta 0:27:00 lr 0.000345	time 1.8561 (2.2168)	loss 3.9246 (3.4440)	grad_norm 2.0307 (1.7656)	
[2022-01-23 10:40:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][530/1251]	eta 0:26:38 lr 0.000345	time 1.6184 (2.2165)	loss 3.9834 (3.4496)	grad_norm 1.5892 (1.7654)	
[2022-01-23 10:41:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][540/1251]	eta 0:26:16 lr 0.000345	time 2.5248 (2.2166)	loss 3.6431 (3.4535)	grad_norm 1.5592 (1.7680)	
[2022-01-23 10:41:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][550/1251]	eta 0:25:54 lr 0.000345	time 1.8017 (2.2178)	loss 2.6392 (3.4496)	grad_norm 1.6253 (1.7661)	
[2022-01-23 10:41:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][560/1251]	eta 0:25:35 lr 0.000345	time 2.7140 (2.2215)	loss 3.5406 (3.4481)	grad_norm 1.8812 (1.7672)	
[2022-01-23 10:42:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][570/1251]	eta 0:25:10 lr 0.000345	time 1.8407 (2.2183)	loss 2.5645 (3.4478)	grad_norm 1.6110 (1.7709)	
[2022-01-23 10:42:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][580/1251]	eta 0:24:47 lr 0.000345	time 1.5915 (2.2164)	loss 2.6357 (3.4446)	grad_norm 1.5772 (1.7710)	
[2022-01-23 10:42:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][590/1251]	eta 0:24:22 lr 0.000345	time 1.9206 (2.2133)	loss 3.1982 (3.4438)	grad_norm 1.7189 (1.7718)	
[2022-01-23 10:43:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][600/1251]	eta 0:24:01 lr 0.000345	time 2.9961 (2.2147)	loss 3.8875 (3.4454)	grad_norm 1.6378 (1.7740)	
[2022-01-23 10:43:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][610/1251]	eta 0:23:38 lr 0.000345	time 1.5005 (2.2136)	loss 2.8358 (3.4450)	grad_norm 1.9389 (1.7738)	
[2022-01-23 10:43:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][620/1251]	eta 0:23:16 lr 0.000345	time 2.5042 (2.2129)	loss 3.4350 (3.4465)	grad_norm 1.9327 (1.7733)	
[2022-01-23 10:44:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][630/1251]	eta 0:22:53 lr 0.000345	time 2.2337 (2.2113)	loss 3.7440 (3.4478)	grad_norm 2.3119 (1.7737)	
[2022-01-23 10:44:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][640/1251]	eta 0:22:30 lr 0.000345	time 1.9802 (2.2101)	loss 3.3913 (3.4444)	grad_norm 1.7207 (1.7723)	
[2022-01-23 10:44:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][650/1251]	eta 0:22:06 lr 0.000345	time 1.6036 (2.2077)	loss 3.5353 (3.4427)	grad_norm 1.6600 (1.7721)	
[2022-01-23 10:45:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][660/1251]	eta 0:21:43 lr 0.000345	time 2.2186 (2.2062)	loss 2.9680 (3.4446)	grad_norm 1.8773 (1.7734)	
[2022-01-23 10:45:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][670/1251]	eta 0:21:21 lr 0.000344	time 2.3056 (2.2055)	loss 3.1404 (3.4462)	grad_norm 1.7725 (1.7740)	
[2022-01-23 10:46:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][680/1251]	eta 0:20:58 lr 0.000344	time 2.1873 (2.2049)	loss 2.8522 (3.4491)	grad_norm 1.8873 (1.7747)	
[2022-01-23 10:46:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][690/1251]	eta 0:20:37 lr 0.000344	time 1.8954 (2.2064)	loss 3.5572 (3.4467)	grad_norm 1.6634 (1.7731)	
[2022-01-23 10:46:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][700/1251]	eta 0:20:15 lr 0.000344	time 2.4161 (2.2066)	loss 3.7696 (3.4447)	grad_norm 2.0116 (1.7716)	
[2022-01-23 10:47:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][710/1251]	eta 0:19:53 lr 0.000344	time 3.3112 (2.2068)	loss 4.1201 (3.4453)	grad_norm 1.6307 (1.7709)	
[2022-01-23 10:47:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][720/1251]	eta 0:19:31 lr 0.000344	time 2.1509 (2.2063)	loss 3.1922 (3.4410)	grad_norm 1.6913 (1.7710)	
[2022-01-23 10:47:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][730/1251]	eta 0:19:09 lr 0.000344	time 1.9763 (2.2070)	loss 2.6127 (3.4402)	grad_norm 1.4733 (1.7715)	
[2022-01-23 10:48:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][740/1251]	eta 0:18:49 lr 0.000344	time 2.5140 (2.2100)	loss 3.6026 (3.4384)	grad_norm 1.7417 (1.7717)	
[2022-01-23 10:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][750/1251]	eta 0:18:28 lr 0.000344	time 2.8691 (2.2122)	loss 3.7005 (3.4366)	grad_norm 1.8195 (1.7727)	
[2022-01-23 10:49:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][760/1251]	eta 0:18:05 lr 0.000344	time 1.6314 (2.2116)	loss 2.4331 (3.4339)	grad_norm 1.8327 (1.7742)	
[2022-01-23 10:49:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][770/1251]	eta 0:17:42 lr 0.000344	time 1.8069 (2.2095)	loss 4.0379 (3.4351)	grad_norm 1.6618 (1.7749)	
[2022-01-23 10:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][780/1251]	eta 0:17:19 lr 0.000344	time 1.7016 (2.2070)	loss 3.8394 (3.4352)	grad_norm 1.7714 (1.7756)	
[2022-01-23 10:50:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][790/1251]	eta 0:16:57 lr 0.000344	time 3.1731 (2.2066)	loss 3.7942 (3.4353)	grad_norm 1.4297 (1.7770)	
[2022-01-23 10:50:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][800/1251]	eta 0:16:34 lr 0.000344	time 1.6729 (2.2042)	loss 3.6364 (3.4352)	grad_norm 1.7267 (1.7764)	
[2022-01-23 10:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][810/1251]	eta 0:16:12 lr 0.000344	time 1.9046 (2.2044)	loss 3.5442 (3.4344)	grad_norm 1.5622 (1.7769)	
[2022-01-23 10:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][820/1251]	eta 0:15:50 lr 0.000344	time 2.6182 (2.2042)	loss 3.8171 (3.4339)	grad_norm 1.6586 (1.7769)	
[2022-01-23 10:51:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][830/1251]	eta 0:15:28 lr 0.000344	time 2.5587 (2.2046)	loss 3.4360 (3.4322)	grad_norm 1.6829 (1.7754)	
[2022-01-23 10:51:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][840/1251]	eta 0:15:06 lr 0.000344	time 1.8686 (2.2054)	loss 3.6648 (3.4328)	grad_norm 1.6235 (1.7743)	
[2022-01-23 10:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][850/1251]	eta 0:14:44 lr 0.000344	time 2.8480 (2.2063)	loss 4.0681 (3.4329)	grad_norm 1.5817 (1.7731)	
[2022-01-23 10:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][860/1251]	eta 0:14:22 lr 0.000344	time 2.8129 (2.2069)	loss 3.2886 (3.4319)	grad_norm 1.7674 (1.7732)	
[2022-01-23 10:53:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][870/1251]	eta 0:14:00 lr 0.000344	time 1.8622 (2.2058)	loss 3.8142 (3.4339)	grad_norm 1.7657 (1.7725)	
[2022-01-23 10:53:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][880/1251]	eta 0:13:37 lr 0.000344	time 1.8608 (2.2041)	loss 3.4152 (3.4337)	grad_norm 1.8582 (1.7726)	
[2022-01-23 10:53:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][890/1251]	eta 0:13:15 lr 0.000344	time 3.0689 (2.2039)	loss 3.1194 (3.4320)	grad_norm 1.8375 (1.7716)	
[2022-01-23 10:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][900/1251]	eta 0:12:53 lr 0.000344	time 3.0081 (2.2031)	loss 3.7938 (3.4289)	grad_norm 1.7503 (1.7711)	
[2022-01-23 10:54:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][910/1251]	eta 0:12:31 lr 0.000344	time 1.9170 (2.2028)	loss 3.2615 (3.4267)	grad_norm 1.5284 (1.7693)	
[2022-01-23 10:54:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][920/1251]	eta 0:12:08 lr 0.000344	time 1.7077 (2.2013)	loss 3.5303 (3.4276)	grad_norm 1.4117 (1.7682)	
[2022-01-23 10:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][930/1251]	eta 0:11:46 lr 0.000343	time 3.3167 (2.2022)	loss 2.9007 (3.4247)	grad_norm 1.8626 (1.7682)	
[2022-01-23 10:55:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][940/1251]	eta 0:11:25 lr 0.000343	time 2.6265 (2.2027)	loss 3.6262 (3.4243)	grad_norm 1.7677 (1.7684)	
[2022-01-23 10:55:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][950/1251]	eta 0:11:03 lr 0.000343	time 1.7814 (2.2031)	loss 3.8644 (3.4266)	grad_norm 1.8516 (1.7679)	
[2022-01-23 10:56:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][960/1251]	eta 0:10:41 lr 0.000343	time 1.7575 (2.2032)	loss 3.6172 (3.4272)	grad_norm 1.6499 (1.7679)	
[2022-01-23 10:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][970/1251]	eta 0:10:18 lr 0.000343	time 3.3291 (2.2028)	loss 3.3074 (3.4283)	grad_norm 1.6857 (1.7666)	
[2022-01-23 10:57:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][980/1251]	eta 0:09:56 lr 0.000343	time 2.3353 (2.2018)	loss 3.6060 (3.4267)	grad_norm 1.8675 (1.7666)	
[2022-01-23 10:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][990/1251]	eta 0:09:35 lr 0.000343	time 2.2702 (2.2032)	loss 3.7674 (3.4264)	grad_norm 1.7084 (1.7665)	
[2022-01-23 10:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1000/1251]	eta 0:09:12 lr 0.000343	time 1.9997 (2.2025)	loss 2.9561 (3.4241)	grad_norm 2.0377 (1.7662)	
[2022-01-23 10:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1010/1251]	eta 0:08:50 lr 0.000343	time 2.7622 (2.2016)	loss 2.7534 (3.4219)	grad_norm 1.5919 (1.7648)	
[2022-01-23 10:58:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1020/1251]	eta 0:08:28 lr 0.000343	time 1.8060 (2.2021)	loss 3.3930 (3.4224)	grad_norm 1.9289 (1.7641)	
[2022-01-23 10:58:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1030/1251]	eta 0:08:06 lr 0.000343	time 1.9088 (2.2007)	loss 3.3302 (3.4219)	grad_norm 1.8337 (1.7631)	
[2022-01-23 10:59:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1040/1251]	eta 0:07:43 lr 0.000343	time 2.0122 (2.1983)	loss 3.9495 (3.4234)	grad_norm 1.8689 (1.7626)	
[2022-01-23 10:59:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1050/1251]	eta 0:07:21 lr 0.000343	time 2.2124 (2.1986)	loss 3.9659 (3.4252)	grad_norm 1.6635 (1.7632)	
[2022-01-23 10:59:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1060/1251]	eta 0:07:00 lr 0.000343	time 2.1568 (2.1990)	loss 3.7224 (3.4271)	grad_norm 1.7198 (1.7637)	
[2022-01-23 11:00:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1070/1251]	eta 0:06:38 lr 0.000343	time 2.4505 (2.1991)	loss 3.7118 (3.4260)	grad_norm 1.5155 (1.7624)	
[2022-01-23 11:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1080/1251]	eta 0:06:16 lr 0.000343	time 2.3265 (2.1992)	loss 2.3531 (3.4256)	grad_norm 1.8845 (1.7616)	
[2022-01-23 11:01:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1090/1251]	eta 0:05:54 lr 0.000343	time 2.2217 (2.1988)	loss 3.8401 (3.4255)	grad_norm 1.5002 (1.7614)	
[2022-01-23 11:01:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1100/1251]	eta 0:05:32 lr 0.000343	time 1.5778 (2.1989)	loss 2.8386 (3.4271)	grad_norm 1.6048 (1.7609)	
[2022-01-23 11:01:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1110/1251]	eta 0:05:10 lr 0.000343	time 2.3627 (2.1989)	loss 4.0689 (3.4261)	grad_norm 1.8620 (1.7605)	
[2022-01-23 11:02:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1120/1251]	eta 0:04:47 lr 0.000343	time 1.9823 (2.1975)	loss 3.1926 (3.4280)	grad_norm 1.5652 (1.7604)	
[2022-01-23 11:02:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1130/1251]	eta 0:04:25 lr 0.000343	time 1.6869 (2.1967)	loss 2.7755 (3.4259)	grad_norm 1.7096 (1.7596)	
[2022-01-23 11:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1140/1251]	eta 0:04:03 lr 0.000343	time 2.1420 (2.1976)	loss 3.8762 (3.4264)	grad_norm 1.6533 (1.7587)	
[2022-01-23 11:03:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1150/1251]	eta 0:03:42 lr 0.000343	time 1.9363 (2.1982)	loss 3.5663 (3.4256)	grad_norm 1.7477 (1.7585)	
[2022-01-23 11:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1160/1251]	eta 0:03:20 lr 0.000343	time 2.1381 (2.1991)	loss 3.4793 (3.4256)	grad_norm 1.6224 (1.7582)	
[2022-01-23 11:03:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1170/1251]	eta 0:02:58 lr 0.000343	time 1.5824 (2.1987)	loss 2.6566 (3.4267)	grad_norm 1.6878 (1.7576)	
[2022-01-23 11:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1180/1251]	eta 0:02:36 lr 0.000342	time 1.7151 (2.1973)	loss 3.5469 (3.4270)	grad_norm 1.7751 (1.7591)	
[2022-01-23 11:04:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1190/1251]	eta 0:02:13 lr 0.000342	time 2.2453 (2.1966)	loss 3.5887 (3.4264)	grad_norm 1.8003 (1.7604)	
[2022-01-23 11:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1200/1251]	eta 0:01:52 lr 0.000342	time 2.2236 (2.1962)	loss 2.6467 (3.4259)	grad_norm 2.0327 (1.7612)	
[2022-01-23 11:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1210/1251]	eta 0:01:30 lr 0.000342	time 1.6294 (2.1955)	loss 2.3796 (3.4229)	grad_norm 1.7981 (1.7616)	
[2022-01-23 11:05:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1220/1251]	eta 0:01:08 lr 0.000342	time 1.9626 (2.1957)	loss 2.6269 (3.4239)	grad_norm 1.7779 (1.7612)	
[2022-01-23 11:06:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1230/1251]	eta 0:00:46 lr 0.000342	time 1.7415 (2.1958)	loss 3.4445 (3.4236)	grad_norm 2.6147 (1.7614)	
[2022-01-23 11:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1240/1251]	eta 0:00:24 lr 0.000342	time 1.8583 (2.1962)	loss 4.0528 (3.4243)	grad_norm 1.7865 (1.7623)	
[2022-01-23 11:06:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [181/300][1250/1251]	eta 0:00:02 lr 0.000342	time 1.3580 (2.1913)	loss 3.4475 (3.4242)	grad_norm 2.1420 (1.7623)	
[2022-01-23 11:06:43 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 181 training takes 0:45:41
[2022-01-23 11:07:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.310 (19.310)	Loss 0.9862 (0.9862)	Acc@1 76.270 (76.270)	Acc@5 93.164 (93.164)	
[2022-01-23 11:07:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.246 (3.534)	Loss 0.9373 (0.9518)	Acc@1 78.516 (77.646)	Acc@5 94.434 (93.857)	
[2022-01-23 11:07:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.900 (2.767)	Loss 0.9177 (0.9621)	Acc@1 77.637 (77.251)	Acc@5 95.703 (93.983)	
[2022-01-23 11:07:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.276 (2.262)	Loss 1.0735 (0.9688)	Acc@1 76.074 (77.268)	Acc@5 92.578 (93.898)	
[2022-01-23 11:08:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.480 (2.197)	Loss 0.9384 (0.9682)	Acc@1 77.539 (77.303)	Acc@5 94.238 (93.862)	
[2022-01-23 11:08:20 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.326 Acc@5 93.876
[2022-01-23 11:08:20 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.3%
[2022-01-23 11:08:20 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.51%
[2022-01-23 11:08:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][0/1251]	eta 7:25:11 lr 0.000342	time 21.3519 (21.3519)	loss 2.3975 (2.3975)	grad_norm 1.8036 (1.8036)	
[2022-01-23 11:09:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][10/1251]	eta 1:25:50 lr 0.000342	time 2.7696 (4.1500)	loss 2.4092 (2.9888)	grad_norm 1.6279 (1.7147)	
[2022-01-23 11:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][20/1251]	eta 1:04:34 lr 0.000342	time 1.2047 (3.1475)	loss 3.6178 (3.3087)	grad_norm 1.5906 (1.7055)	
[2022-01-23 11:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][30/1251]	eta 0:58:06 lr 0.000342	time 1.8537 (2.8551)	loss 3.6531 (3.2930)	grad_norm 1.6950 (1.7262)	
[2022-01-23 11:10:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][40/1251]	eta 0:54:59 lr 0.000342	time 3.7400 (2.7246)	loss 3.3237 (3.3049)	grad_norm 1.6035 (1.7387)	
[2022-01-23 11:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][50/1251]	eta 0:53:28 lr 0.000342	time 2.7479 (2.6712)	loss 3.7628 (3.3408)	grad_norm 1.5720 (1.7490)	
[2022-01-23 11:11:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][60/1251]	eta 0:52:00 lr 0.000342	time 2.3507 (2.6201)	loss 3.4402 (3.3413)	grad_norm 1.7433 (1.7376)	
[2022-01-23 11:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][70/1251]	eta 0:50:13 lr 0.000342	time 1.5766 (2.5513)	loss 3.6270 (3.3317)	grad_norm 1.6061 (1.7553)	
[2022-01-23 11:11:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][80/1251]	eta 0:48:54 lr 0.000342	time 2.5827 (2.5057)	loss 3.7029 (3.3520)	grad_norm 1.8632 (1.7612)	
[2022-01-23 11:12:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][90/1251]	eta 0:47:42 lr 0.000342	time 1.8727 (2.4659)	loss 3.8704 (3.3488)	grad_norm 1.9099 (1.7623)	
[2022-01-23 11:12:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][100/1251]	eta 0:46:38 lr 0.000342	time 3.0914 (2.4312)	loss 3.6791 (3.3702)	grad_norm 1.8027 (1.7859)	
[2022-01-23 11:12:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][110/1251]	eta 0:45:31 lr 0.000342	time 1.6382 (2.3937)	loss 3.8878 (3.3741)	grad_norm 1.5100 (1.7851)	
[2022-01-23 11:13:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][120/1251]	eta 0:44:33 lr 0.000342	time 1.9855 (2.3642)	loss 2.2872 (3.3754)	grad_norm 2.1627 (1.7822)	
[2022-01-23 11:13:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][130/1251]	eta 0:43:41 lr 0.000342	time 1.9117 (2.3388)	loss 4.1176 (3.3742)	grad_norm 2.6539 (1.7954)	
[2022-01-23 11:13:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][140/1251]	eta 0:43:10 lr 0.000342	time 2.3251 (2.3313)	loss 3.6922 (3.3772)	grad_norm 1.9176 (1.7941)	
[2022-01-23 11:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][150/1251]	eta 0:42:29 lr 0.000342	time 2.2113 (2.3153)	loss 2.7019 (3.3937)	grad_norm 1.6268 (1.7945)	
[2022-01-23 11:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][160/1251]	eta 0:42:01 lr 0.000342	time 2.1005 (2.3109)	loss 3.5060 (3.3803)	grad_norm 1.5442 (1.7896)	
[2022-01-23 11:14:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][170/1251]	eta 0:41:35 lr 0.000342	time 2.2143 (2.3086)	loss 3.8982 (3.3776)	grad_norm 1.7314 (1.7893)	
[2022-01-23 11:15:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][180/1251]	eta 0:41:07 lr 0.000342	time 2.1803 (2.3036)	loss 2.9959 (3.3725)	grad_norm 1.6393 (1.7855)	
[2022-01-23 11:15:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][190/1251]	eta 0:40:42 lr 0.000341	time 2.4553 (2.3023)	loss 4.0271 (3.3905)	grad_norm 1.9400 (1.7817)	
[2022-01-23 11:16:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][200/1251]	eta 0:40:19 lr 0.000341	time 1.8296 (2.3021)	loss 3.6093 (3.3829)	grad_norm 1.5517 (1.7765)	
[2022-01-23 11:16:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][210/1251]	eta 0:39:52 lr 0.000341	time 1.8788 (2.2982)	loss 2.5276 (3.3791)	grad_norm 1.5963 (1.7756)	
[2022-01-23 11:16:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][220/1251]	eta 0:39:19 lr 0.000341	time 1.8522 (2.2882)	loss 3.5781 (3.3934)	grad_norm 1.5081 (1.7748)	
[2022-01-23 11:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][230/1251]	eta 0:38:52 lr 0.000341	time 2.6109 (2.2848)	loss 3.6366 (3.3990)	grad_norm 1.8746 (1.7786)	
[2022-01-23 11:17:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][240/1251]	eta 0:38:22 lr 0.000341	time 2.4816 (2.2773)	loss 3.8949 (3.3895)	grad_norm 1.9061 (1.7856)	
[2022-01-23 11:17:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][250/1251]	eta 0:37:50 lr 0.000341	time 2.4452 (2.2678)	loss 3.6269 (3.3992)	grad_norm 1.6870 (1.7876)	
[2022-01-23 11:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][260/1251]	eta 0:37:19 lr 0.000341	time 2.1116 (2.2600)	loss 3.3101 (3.4073)	grad_norm 1.8589 (1.7888)	
[2022-01-23 11:18:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][270/1251]	eta 0:37:01 lr 0.000341	time 3.0966 (2.2643)	loss 2.9177 (3.4002)	grad_norm 1.6237 (1.7880)	
[2022-01-23 11:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][280/1251]	eta 0:36:35 lr 0.000341	time 2.5302 (2.2606)	loss 3.3661 (3.3895)	grad_norm 1.6988 (1.7903)	
[2022-01-23 11:19:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][290/1251]	eta 0:36:09 lr 0.000341	time 1.8007 (2.2576)	loss 2.9856 (3.3968)	grad_norm 1.7738 (1.7913)	
[2022-01-23 11:19:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][300/1251]	eta 0:35:48 lr 0.000341	time 2.6516 (2.2591)	loss 4.1107 (3.4016)	grad_norm 1.7474 (1.7941)	
[2022-01-23 11:20:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][310/1251]	eta 0:35:25 lr 0.000341	time 2.4936 (2.2589)	loss 2.9549 (3.4084)	grad_norm 1.9186 (1.7920)	
[2022-01-23 11:20:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][320/1251]	eta 0:35:02 lr 0.000341	time 2.3132 (2.2586)	loss 3.7164 (3.4119)	grad_norm 1.5392 (1.7902)	
[2022-01-23 11:20:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][330/1251]	eta 0:34:37 lr 0.000341	time 1.8809 (2.2555)	loss 3.5487 (3.4200)	grad_norm 1.7804 (1.7873)	
[2022-01-23 11:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][340/1251]	eta 0:34:11 lr 0.000341	time 2.5035 (2.2520)	loss 3.8934 (3.4264)	grad_norm 2.1207 (1.7899)	
[2022-01-23 11:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][350/1251]	eta 0:33:43 lr 0.000341	time 1.6176 (2.2460)	loss 4.2934 (3.4368)	grad_norm 2.0996 (1.7905)	
[2022-01-23 11:21:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][360/1251]	eta 0:33:23 lr 0.000341	time 2.5204 (2.2483)	loss 3.3108 (3.4393)	grad_norm 1.9020 (1.7898)	
[2022-01-23 11:22:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][370/1251]	eta 0:32:56 lr 0.000341	time 2.0907 (2.2430)	loss 3.3684 (3.4402)	grad_norm 1.5318 (1.7878)	
[2022-01-23 11:22:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][380/1251]	eta 0:32:31 lr 0.000341	time 1.8550 (2.2407)	loss 3.8846 (3.4445)	grad_norm 1.8887 (1.7886)	
[2022-01-23 11:22:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][390/1251]	eta 0:32:07 lr 0.000341	time 1.8926 (2.2390)	loss 3.5934 (3.4448)	grad_norm 1.7768 (1.7875)	
[2022-01-23 11:23:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][400/1251]	eta 0:31:41 lr 0.000341	time 1.9163 (2.2348)	loss 3.9276 (3.4427)	grad_norm 1.8749 (1.7893)	
[2022-01-23 11:23:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][410/1251]	eta 0:31:20 lr 0.000341	time 2.7499 (2.2360)	loss 3.8852 (3.4448)	grad_norm 1.8507 (1.7872)	
[2022-01-23 11:24:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][420/1251]	eta 0:30:59 lr 0.000341	time 2.7577 (2.2375)	loss 3.4561 (3.4495)	grad_norm 1.6330 (1.7848)	
[2022-01-23 11:24:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][430/1251]	eta 0:30:35 lr 0.000341	time 1.5217 (2.2353)	loss 2.6517 (3.4352)	grad_norm 1.7387 (1.7831)	
[2022-01-23 11:24:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][440/1251]	eta 0:30:13 lr 0.000340	time 1.9203 (2.2356)	loss 3.4149 (3.4359)	grad_norm 1.8551 (1.7822)	
[2022-01-23 11:25:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][450/1251]	eta 0:29:50 lr 0.000340	time 2.4930 (2.2349)	loss 3.9406 (3.4337)	grad_norm 1.9648 (1.7828)	
[2022-01-23 11:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][460/1251]	eta 0:29:27 lr 0.000340	time 2.3217 (2.2348)	loss 3.5223 (3.4305)	grad_norm 1.9075 (1.7805)	
[2022-01-23 11:25:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][470/1251]	eta 0:29:00 lr 0.000340	time 1.6617 (2.2290)	loss 3.5183 (3.4353)	grad_norm 1.7814 (1.7810)	
[2022-01-23 11:26:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][480/1251]	eta 0:28:35 lr 0.000340	time 1.9158 (2.2253)	loss 2.5642 (3.4315)	grad_norm 1.8071 (1.7797)	
[2022-01-23 11:26:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][490/1251]	eta 0:28:13 lr 0.000340	time 2.1449 (2.2257)	loss 3.7103 (3.4282)	grad_norm 1.7781 (1.7785)	
[2022-01-23 11:26:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][500/1251]	eta 0:27:51 lr 0.000340	time 2.2100 (2.2252)	loss 3.6140 (3.4328)	grad_norm 2.1854 (1.7825)	
[2022-01-23 11:27:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][510/1251]	eta 0:27:29 lr 0.000340	time 2.1947 (2.2264)	loss 4.0371 (3.4360)	grad_norm 2.0314 (1.7834)	
[2022-01-23 11:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][520/1251]	eta 0:27:12 lr 0.000340	time 2.3943 (2.2333)	loss 2.5408 (3.4343)	grad_norm 1.6440 (1.7830)	
[2022-01-23 11:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][530/1251]	eta 0:26:47 lr 0.000340	time 1.9261 (2.2299)	loss 3.7111 (3.4382)	grad_norm 1.7362 (1.7806)	
[2022-01-23 11:28:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][540/1251]	eta 0:26:23 lr 0.000340	time 1.9141 (2.2268)	loss 2.8128 (3.4362)	grad_norm 1.6095 (1.7803)	
[2022-01-23 11:28:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][550/1251]	eta 0:25:56 lr 0.000340	time 1.7777 (2.2204)	loss 3.1505 (3.4366)	grad_norm 1.6630 (1.7783)	
[2022-01-23 11:29:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][560/1251]	eta 0:25:30 lr 0.000340	time 1.5898 (2.2152)	loss 4.0489 (3.4393)	grad_norm 1.5864 (1.7778)	
[2022-01-23 11:29:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][570/1251]	eta 0:25:06 lr 0.000340	time 1.8133 (2.2123)	loss 4.0655 (3.4412)	grad_norm 1.9350 (1.7787)	
[2022-01-23 11:29:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][580/1251]	eta 0:24:45 lr 0.000340	time 1.9490 (2.2135)	loss 2.7193 (3.4417)	grad_norm 1.4242 (1.7768)	
[2022-01-23 11:30:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][590/1251]	eta 0:24:25 lr 0.000340	time 2.1639 (2.2164)	loss 3.5026 (3.4386)	grad_norm 2.0662 (1.7760)	
[2022-01-23 11:30:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][600/1251]	eta 0:24:03 lr 0.000340	time 2.0170 (2.2174)	loss 3.8062 (3.4360)	grad_norm 1.8060 (1.7767)	
[2022-01-23 11:30:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][610/1251]	eta 0:23:40 lr 0.000340	time 1.9893 (2.2159)	loss 3.7014 (3.4388)	grad_norm 1.7062 (1.7764)	
[2022-01-23 11:31:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][620/1251]	eta 0:23:18 lr 0.000340	time 2.1752 (2.2156)	loss 2.7121 (3.4361)	grad_norm 2.9273 (1.7791)	
[2022-01-23 11:31:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][630/1251]	eta 0:22:57 lr 0.000340	time 2.4499 (2.2174)	loss 2.4465 (3.4342)	grad_norm 1.9467 (1.7801)	
[2022-01-23 11:32:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][640/1251]	eta 0:22:33 lr 0.000340	time 1.5568 (2.2159)	loss 3.6832 (3.4346)	grad_norm 1.5673 (1.7800)	
[2022-01-23 11:32:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][650/1251]	eta 0:22:10 lr 0.000340	time 1.9152 (2.2140)	loss 3.2073 (3.4342)	grad_norm 1.5727 (1.7792)	
[2022-01-23 11:32:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][660/1251]	eta 0:21:48 lr 0.000340	time 1.8516 (2.2142)	loss 3.7604 (3.4356)	grad_norm 1.8550 (1.7788)	
[2022-01-23 11:33:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][670/1251]	eta 0:21:26 lr 0.000340	time 2.5724 (2.2148)	loss 3.9215 (3.4384)	grad_norm 1.4653 (1.7785)	
[2022-01-23 11:33:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][680/1251]	eta 0:21:05 lr 0.000340	time 2.4771 (2.2171)	loss 3.1360 (3.4365)	grad_norm 1.7225 (1.7770)	
[2022-01-23 11:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][690/1251]	eta 0:20:44 lr 0.000340	time 1.8769 (2.2178)	loss 3.4235 (3.4326)	grad_norm 1.9500 (1.7780)	
[2022-01-23 11:34:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][700/1251]	eta 0:20:20 lr 0.000339	time 1.7723 (2.2151)	loss 3.5797 (3.4337)	grad_norm 1.9146 (1.7795)	
[2022-01-23 11:34:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][710/1251]	eta 0:19:57 lr 0.000339	time 1.9643 (2.2127)	loss 2.7382 (3.4321)	grad_norm 1.5606 (1.7783)	
[2022-01-23 11:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][720/1251]	eta 0:19:33 lr 0.000339	time 2.3725 (2.2101)	loss 4.1716 (3.4319)	grad_norm 1.9464 (1.7780)	
[2022-01-23 11:35:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][730/1251]	eta 0:19:11 lr 0.000339	time 2.1176 (2.2108)	loss 2.4067 (3.4297)	grad_norm 1.8464 (1.7789)	
[2022-01-23 11:35:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][740/1251]	eta 0:18:51 lr 0.000339	time 2.4746 (2.2136)	loss 4.0755 (3.4277)	grad_norm 1.6781 (1.7794)	
[2022-01-23 11:36:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][750/1251]	eta 0:18:29 lr 0.000339	time 1.9287 (2.2141)	loss 2.6367 (3.4278)	grad_norm 2.1203 (1.7799)	
[2022-01-23 11:36:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][760/1251]	eta 0:18:07 lr 0.000339	time 2.6003 (2.2158)	loss 3.0390 (3.4257)	grad_norm 1.6806 (1.7780)	
[2022-01-23 11:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][770/1251]	eta 0:17:44 lr 0.000339	time 1.6889 (2.2128)	loss 2.5644 (3.4224)	grad_norm 1.6086 (1.7772)	
[2022-01-23 11:37:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][780/1251]	eta 0:17:20 lr 0.000339	time 1.6944 (2.2100)	loss 3.8444 (3.4213)	grad_norm 1.8070 (1.7775)	
[2022-01-23 11:37:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][790/1251]	eta 0:16:57 lr 0.000339	time 2.2506 (2.2071)	loss 3.7214 (3.4175)	grad_norm 1.6494 (1.7766)	
[2022-01-23 11:37:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][800/1251]	eta 0:16:35 lr 0.000339	time 2.0374 (2.2081)	loss 2.4304 (3.4163)	grad_norm 1.6301 (1.7764)	
[2022-01-23 11:38:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][810/1251]	eta 0:16:14 lr 0.000339	time 1.9291 (2.2089)	loss 3.4344 (3.4160)	grad_norm 1.8267 (1.7771)	
[2022-01-23 11:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][820/1251]	eta 0:15:53 lr 0.000339	time 1.9882 (2.2124)	loss 3.8136 (3.4163)	grad_norm 1.7602 (1.7776)	
[2022-01-23 11:38:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][830/1251]	eta 0:15:31 lr 0.000339	time 1.5896 (2.2121)	loss 3.3683 (3.4162)	grad_norm 1.8540 (1.7783)	
[2022-01-23 11:39:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][840/1251]	eta 0:15:09 lr 0.000339	time 1.9363 (2.2134)	loss 4.0792 (3.4196)	grad_norm 1.7830 (1.7780)	
[2022-01-23 11:39:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][850/1251]	eta 0:14:46 lr 0.000339	time 1.8968 (2.2111)	loss 3.8830 (3.4154)	grad_norm 2.0508 (1.7775)	
[2022-01-23 11:40:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][860/1251]	eta 0:14:24 lr 0.000339	time 2.2249 (2.2101)	loss 2.7735 (3.4154)	grad_norm 1.8867 (1.7788)	
[2022-01-23 11:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][870/1251]	eta 0:14:01 lr 0.000339	time 1.9480 (2.2094)	loss 3.7740 (3.4156)	grad_norm 1.7617 (1.7783)	
[2022-01-23 11:40:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][880/1251]	eta 0:13:40 lr 0.000339	time 2.2772 (2.2123)	loss 3.4732 (3.4148)	grad_norm 2.0650 (1.7797)	
[2022-01-23 11:41:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][890/1251]	eta 0:13:18 lr 0.000339	time 1.5503 (2.2113)	loss 4.0818 (3.4167)	grad_norm 1.6058 (1.7795)	
[2022-01-23 11:41:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][900/1251]	eta 0:12:55 lr 0.000339	time 2.1762 (2.2098)	loss 3.3423 (3.4151)	grad_norm 1.7497 (1.7792)	
[2022-01-23 11:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][910/1251]	eta 0:12:32 lr 0.000339	time 1.9443 (2.2077)	loss 3.9868 (3.4183)	grad_norm 1.6031 (1.7788)	
[2022-01-23 11:42:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][920/1251]	eta 0:12:10 lr 0.000339	time 1.9171 (2.2082)	loss 3.3309 (3.4162)	grad_norm 1.9045 (1.7786)	
[2022-01-23 11:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][930/1251]	eta 0:11:48 lr 0.000339	time 2.1176 (2.2070)	loss 3.0501 (3.4188)	grad_norm 1.9419 (1.7783)	
[2022-01-23 11:42:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][940/1251]	eta 0:11:27 lr 0.000339	time 1.8314 (2.2092)	loss 3.5687 (3.4206)	grad_norm 1.9052 (1.7779)	
[2022-01-23 11:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][950/1251]	eta 0:11:04 lr 0.000338	time 2.5229 (2.2086)	loss 2.7889 (3.4184)	grad_norm 1.4634 (1.7769)	
[2022-01-23 11:43:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][960/1251]	eta 0:10:42 lr 0.000338	time 1.6437 (2.2087)	loss 3.4068 (3.4176)	grad_norm 1.6854 (1.7765)	
[2022-01-23 11:44:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][970/1251]	eta 0:10:20 lr 0.000338	time 2.5292 (2.2084)	loss 3.5817 (3.4186)	grad_norm 1.8569 (1.7776)	
[2022-01-23 11:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][980/1251]	eta 0:09:58 lr 0.000338	time 1.7124 (2.2073)	loss 3.5110 (3.4191)	grad_norm 1.5843 (1.7767)	
[2022-01-23 11:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][990/1251]	eta 0:09:35 lr 0.000338	time 1.9236 (2.2059)	loss 3.9700 (3.4184)	grad_norm 1.6976 (1.7767)	
[2022-01-23 11:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1000/1251]	eta 0:09:13 lr 0.000338	time 1.9345 (2.2058)	loss 3.5646 (3.4191)	grad_norm 1.4579 (1.7760)	
[2022-01-23 11:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1010/1251]	eta 0:08:51 lr 0.000338	time 2.1803 (2.2070)	loss 3.7883 (3.4200)	grad_norm 1.8298 (1.7758)	
[2022-01-23 11:45:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1020/1251]	eta 0:08:29 lr 0.000338	time 1.5627 (2.2072)	loss 3.0520 (3.4181)	grad_norm 2.0393 (1.7752)	
[2022-01-23 11:46:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1030/1251]	eta 0:08:07 lr 0.000338	time 1.8338 (2.2069)	loss 4.1673 (3.4179)	grad_norm 2.2514 (1.7761)	
[2022-01-23 11:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1040/1251]	eta 0:07:45 lr 0.000338	time 2.2478 (2.2072)	loss 3.8332 (3.4176)	grad_norm 1.9296 (1.7761)	
[2022-01-23 11:46:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1050/1251]	eta 0:07:23 lr 0.000338	time 1.9189 (2.2052)	loss 3.8749 (3.4195)	grad_norm 1.8245 (1.7764)	
[2022-01-23 11:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1060/1251]	eta 0:07:00 lr 0.000338	time 1.9407 (2.2037)	loss 3.0720 (3.4207)	grad_norm 1.8251 (1.7772)	
[2022-01-23 11:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1070/1251]	eta 0:06:38 lr 0.000338	time 1.7782 (2.2038)	loss 4.0251 (3.4227)	grad_norm 1.7378 (1.7769)	
[2022-01-23 11:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1080/1251]	eta 0:06:17 lr 0.000338	time 2.2369 (2.2053)	loss 3.4722 (3.4238)	grad_norm 1.8473 (1.7766)	
[2022-01-23 11:48:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1090/1251]	eta 0:05:55 lr 0.000338	time 2.0654 (2.2057)	loss 3.7910 (3.4236)	grad_norm 1.9708 (1.7776)	
[2022-01-23 11:48:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1100/1251]	eta 0:05:33 lr 0.000338	time 2.0535 (2.2072)	loss 3.7023 (3.4254)	grad_norm 1.7970 (1.7772)	
[2022-01-23 11:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1110/1251]	eta 0:05:11 lr 0.000338	time 1.6904 (2.2060)	loss 2.7054 (3.4233)	grad_norm 1.8025 (1.7771)	
[2022-01-23 11:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1120/1251]	eta 0:04:49 lr 0.000338	time 1.7886 (2.2064)	loss 3.0900 (3.4245)	grad_norm 1.7125 (1.7771)	
[2022-01-23 11:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1130/1251]	eta 0:04:26 lr 0.000338	time 1.8735 (2.2050)	loss 3.2000 (3.4235)	grad_norm 1.6514 (1.7773)	
[2022-01-23 11:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1140/1251]	eta 0:04:04 lr 0.000338	time 1.9632 (2.2051)	loss 2.8176 (3.4227)	grad_norm 1.7648 (1.7784)	
[2022-01-23 11:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1150/1251]	eta 0:03:42 lr 0.000338	time 1.8505 (2.2046)	loss 3.9290 (3.4237)	grad_norm 1.7783 (1.7775)	
[2022-01-23 11:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1160/1251]	eta 0:03:20 lr 0.000338	time 1.9365 (2.2058)	loss 2.6735 (3.4226)	grad_norm 1.6756 (1.7763)	
[2022-01-23 11:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1170/1251]	eta 0:02:58 lr 0.000338	time 2.1346 (2.2046)	loss 3.5847 (3.4240)	grad_norm 1.5653 (1.7747)	
[2022-01-23 11:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1180/1251]	eta 0:02:36 lr 0.000338	time 2.2096 (2.2037)	loss 2.7863 (3.4242)	grad_norm 1.7992 (1.7749)	
[2022-01-23 11:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1190/1251]	eta 0:02:14 lr 0.000338	time 2.5215 (2.2043)	loss 3.7699 (3.4233)	grad_norm 1.8188 (1.7753)	
[2022-01-23 11:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1200/1251]	eta 0:01:52 lr 0.000338	time 1.8971 (2.2045)	loss 3.5444 (3.4212)	grad_norm 1.9080 (1.7752)	
[2022-01-23 11:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1210/1251]	eta 0:01:30 lr 0.000337	time 1.7062 (2.2033)	loss 3.6043 (3.4191)	grad_norm 1.7600 (1.7747)	
[2022-01-23 11:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1220/1251]	eta 0:01:08 lr 0.000337	time 2.0242 (2.2030)	loss 2.8053 (3.4192)	grad_norm 1.7204 (1.7742)	
[2022-01-23 11:53:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1230/1251]	eta 0:00:46 lr 0.000337	time 2.0487 (2.2034)	loss 4.0198 (3.4201)	grad_norm 1.7734 (1.7736)	
[2022-01-23 11:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1240/1251]	eta 0:00:24 lr 0.000337	time 1.4422 (2.2038)	loss 3.0422 (3.4200)	grad_norm 1.7023 (1.7737)	
[2022-01-23 11:54:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [182/300][1250/1251]	eta 0:00:02 lr 0.000337	time 1.1953 (2.1989)	loss 2.3009 (3.4183)	grad_norm 1.9093 (1.7735)	
[2022-01-23 11:54:12 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 182 training takes 0:45:51
[2022-01-23 11:54:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.455 (18.455)	Loss 0.9626 (0.9626)	Acc@1 78.320 (78.320)	Acc@5 93.262 (93.262)	
[2022-01-23 11:54:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.229 (3.504)	Loss 0.9355 (0.9712)	Acc@1 78.125 (77.512)	Acc@5 95.508 (93.590)	
[2022-01-23 11:55:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.915 (2.726)	Loss 0.8868 (0.9655)	Acc@1 78.906 (77.307)	Acc@5 94.727 (93.862)	
[2022-01-23 11:55:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.591 (2.339)	Loss 1.0185 (0.9601)	Acc@1 76.562 (77.416)	Acc@5 92.773 (93.819)	
[2022-01-23 11:55:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.885 (2.200)	Loss 0.9607 (0.9615)	Acc@1 78.711 (77.375)	Acc@5 93.359 (93.814)	
[2022-01-23 11:55:49 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.428 Acc@5 93.872
[2022-01-23 11:55:49 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.4%
[2022-01-23 11:55:49 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.51%
[2022-01-23 11:56:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][0/1251]	eta 7:40:20 lr 0.000337	time 22.0791 (22.0791)	loss 3.0205 (3.0205)	grad_norm 1.7365 (1.7365)	
[2022-01-23 11:56:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][10/1251]	eta 1:25:04 lr 0.000337	time 1.8730 (4.1135)	loss 3.5030 (3.1462)	grad_norm 1.7571 (1.7439)	
[2022-01-23 11:56:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][20/1251]	eta 1:07:21 lr 0.000337	time 1.4990 (3.2832)	loss 4.0316 (3.3016)	grad_norm 1.6978 (1.7727)	
[2022-01-23 11:57:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][30/1251]	eta 0:59:31 lr 0.000337	time 1.5025 (2.9250)	loss 3.6228 (3.3320)	grad_norm 1.7599 (1.7514)	
[2022-01-23 11:57:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][40/1251]	eta 0:56:09 lr 0.000337	time 3.2265 (2.7825)	loss 3.8084 (3.3544)	grad_norm 1.5553 (1.7360)	
[2022-01-23 11:58:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][50/1251]	eta 0:53:22 lr 0.000337	time 1.9178 (2.6662)	loss 3.4885 (3.3554)	grad_norm 1.7324 (1.7153)	
[2022-01-23 11:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][60/1251]	eta 0:52:00 lr 0.000337	time 2.1816 (2.6204)	loss 3.6768 (3.3448)	grad_norm 1.7331 (1.7196)	
[2022-01-23 11:58:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][70/1251]	eta 0:50:11 lr 0.000337	time 1.7365 (2.5498)	loss 3.5355 (3.3482)	grad_norm 1.7059 (1.7331)	
[2022-01-23 11:59:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][80/1251]	eta 0:48:49 lr 0.000337	time 2.1732 (2.5020)	loss 2.3966 (3.3343)	grad_norm 1.8336 (1.7484)	
[2022-01-23 11:59:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][90/1251]	eta 0:47:26 lr 0.000337	time 1.8975 (2.4521)	loss 3.2054 (3.3417)	grad_norm 1.7498 (1.7528)	
[2022-01-23 11:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][100/1251]	eta 0:46:22 lr 0.000337	time 1.8780 (2.4172)	loss 2.9813 (3.3418)	grad_norm 1.9415 (1.7553)	
[2022-01-23 12:00:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][110/1251]	eta 0:45:21 lr 0.000337	time 1.8848 (2.3855)	loss 3.5128 (3.3558)	grad_norm 1.6243 (1.7586)	
[2022-01-23 12:00:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][120/1251]	eta 0:44:28 lr 0.000337	time 2.5937 (2.3591)	loss 3.7254 (3.3859)	grad_norm 1.5612 (1.7600)	
[2022-01-23 12:00:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][130/1251]	eta 0:43:43 lr 0.000337	time 2.1045 (2.3401)	loss 3.2080 (3.3923)	grad_norm 1.7378 (1.7541)	
[2022-01-23 12:01:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][140/1251]	eta 0:43:05 lr 0.000337	time 1.7706 (2.3269)	loss 3.6934 (3.4095)	grad_norm 1.7053 (1.7505)	
[2022-01-23 12:01:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][150/1251]	eta 0:42:34 lr 0.000337	time 2.0635 (2.3204)	loss 3.7648 (3.4303)	grad_norm 1.6349 (1.7496)	
[2022-01-23 12:02:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][160/1251]	eta 0:42:11 lr 0.000337	time 3.2066 (2.3201)	loss 3.8474 (3.4393)	grad_norm 1.6421 (1.7506)	
[2022-01-23 12:02:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][170/1251]	eta 0:41:47 lr 0.000337	time 2.1309 (2.3200)	loss 3.7088 (3.4443)	grad_norm 1.9712 (1.7512)	
[2022-01-23 12:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][180/1251]	eta 0:41:22 lr 0.000337	time 1.9090 (2.3181)	loss 3.5161 (3.4357)	grad_norm 1.8518 (1.7483)	
[2022-01-23 12:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][190/1251]	eta 0:40:55 lr 0.000337	time 1.7893 (2.3146)	loss 3.8803 (3.4427)	grad_norm 1.9103 (1.7527)	
[2022-01-23 12:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][200/1251]	eta 0:40:20 lr 0.000337	time 2.0869 (2.3033)	loss 3.7260 (3.4433)	grad_norm 1.7633 (1.7535)	
[2022-01-23 12:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][210/1251]	eta 0:39:48 lr 0.000337	time 1.9120 (2.2942)	loss 3.0970 (3.4394)	grad_norm 1.5513 (1.7532)	
[2022-01-23 12:04:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][220/1251]	eta 0:39:14 lr 0.000336	time 2.3863 (2.2838)	loss 3.1981 (3.4365)	grad_norm 1.8812 (1.7578)	
[2022-01-23 12:04:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][230/1251]	eta 0:38:39 lr 0.000336	time 1.6478 (2.2720)	loss 3.6545 (3.4485)	grad_norm 1.8663 (1.7575)	
[2022-01-23 12:04:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][240/1251]	eta 0:38:09 lr 0.000336	time 2.5298 (2.2647)	loss 3.4442 (3.4543)	grad_norm 1.6146 (1.7553)	
[2022-01-23 12:05:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][250/1251]	eta 0:37:33 lr 0.000336	time 1.9307 (2.2516)	loss 3.9419 (3.4547)	grad_norm 1.5667 (1.7553)	
[2022-01-23 12:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][260/1251]	eta 0:37:17 lr 0.000336	time 5.3299 (2.2581)	loss 3.4755 (3.4533)	grad_norm 2.2293 (1.7592)	
[2022-01-23 12:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][270/1251]	eta 0:36:55 lr 0.000336	time 2.2898 (2.2579)	loss 3.6521 (3.4522)	grad_norm 1.7433 (1.7636)	
[2022-01-23 12:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][280/1251]	eta 0:36:32 lr 0.000336	time 1.6046 (2.2575)	loss 2.8289 (3.4467)	grad_norm 1.7054 (1.7612)	
[2022-01-23 12:06:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][290/1251]	eta 0:36:11 lr 0.000336	time 2.4068 (2.2599)	loss 2.7808 (3.4430)	grad_norm 1.8248 (1.7610)	
[2022-01-23 12:07:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][300/1251]	eta 0:35:56 lr 0.000336	time 3.9449 (2.2675)	loss 3.2007 (3.4412)	grad_norm 1.4837 (1.7596)	
[2022-01-23 12:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][310/1251]	eta 0:35:28 lr 0.000336	time 1.8351 (2.2617)	loss 3.4057 (3.4387)	grad_norm 1.5724 (1.7575)	
[2022-01-23 12:07:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][320/1251]	eta 0:35:00 lr 0.000336	time 1.6675 (2.2567)	loss 2.5520 (3.4367)	grad_norm 1.6155 (1.7554)	
[2022-01-23 12:08:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][330/1251]	eta 0:34:37 lr 0.000336	time 2.2842 (2.2554)	loss 3.4218 (3.4361)	grad_norm 1.6662 (1.7560)	
[2022-01-23 12:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][340/1251]	eta 0:34:15 lr 0.000336	time 4.1728 (2.2563)	loss 3.8793 (3.4360)	grad_norm 1.6993 (1.7564)	
[2022-01-23 12:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][350/1251]	eta 0:33:51 lr 0.000336	time 2.1567 (2.2545)	loss 2.6854 (3.4268)	grad_norm 1.6938 (1.7585)	
[2022-01-23 12:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][360/1251]	eta 0:33:22 lr 0.000336	time 1.5638 (2.2478)	loss 3.5501 (3.4306)	grad_norm 1.8727 (1.7581)	
[2022-01-23 12:09:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][370/1251]	eta 0:33:00 lr 0.000336	time 1.9148 (2.2482)	loss 3.3775 (3.4289)	grad_norm 1.7125 (1.7593)	
[2022-01-23 12:10:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][380/1251]	eta 0:32:39 lr 0.000336	time 3.2099 (2.2495)	loss 3.1224 (3.4355)	grad_norm 1.6316 (1.7594)	
[2022-01-23 12:10:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][390/1251]	eta 0:32:14 lr 0.000336	time 1.9934 (2.2465)	loss 4.3222 (3.4308)	grad_norm 2.0026 (1.7596)	
[2022-01-23 12:10:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][400/1251]	eta 0:31:48 lr 0.000336	time 1.9437 (2.2431)	loss 3.9177 (3.4284)	grad_norm 1.9837 (1.7617)	
[2022-01-23 12:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][410/1251]	eta 0:31:27 lr 0.000336	time 1.8444 (2.2443)	loss 3.8191 (3.4248)	grad_norm 1.6281 (1.7624)	
[2022-01-23 12:11:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][420/1251]	eta 0:31:04 lr 0.000336	time 2.4839 (2.2442)	loss 3.5699 (3.4217)	grad_norm 1.4987 (1.7610)	
[2022-01-23 12:11:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][430/1251]	eta 0:30:41 lr 0.000336	time 2.9507 (2.2429)	loss 2.9338 (3.4157)	grad_norm 1.6978 (1.7609)	
[2022-01-23 12:12:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][440/1251]	eta 0:30:15 lr 0.000336	time 2.0100 (2.2387)	loss 3.8490 (3.4113)	grad_norm 2.4774 (1.7650)	
[2022-01-23 12:12:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][450/1251]	eta 0:29:52 lr 0.000336	time 2.6449 (2.2376)	loss 2.9007 (3.4093)	grad_norm 1.7391 (1.7653)	
[2022-01-23 12:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][460/1251]	eta 0:29:26 lr 0.000336	time 2.0284 (2.2335)	loss 3.7450 (3.4069)	grad_norm 1.8458 (1.7659)	
[2022-01-23 12:13:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][470/1251]	eta 0:29:06 lr 0.000335	time 4.0312 (2.2358)	loss 3.6272 (3.4091)	grad_norm 1.5875 (1.7665)	
[2022-01-23 12:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][480/1251]	eta 0:28:43 lr 0.000335	time 2.1704 (2.2351)	loss 2.4974 (3.4057)	grad_norm 1.7859 (1.7666)	
[2022-01-23 12:14:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][490/1251]	eta 0:28:21 lr 0.000335	time 2.5530 (2.2365)	loss 3.1190 (3.4069)	grad_norm 1.9944 (1.7695)	
[2022-01-23 12:14:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][500/1251]	eta 0:27:57 lr 0.000335	time 1.8536 (2.2341)	loss 3.8864 (3.4100)	grad_norm 1.6149 (1.7715)	
[2022-01-23 12:14:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][510/1251]	eta 0:27:35 lr 0.000335	time 3.6671 (2.2344)	loss 4.0657 (3.4142)	grad_norm 1.6803 (1.7723)	
[2022-01-23 12:15:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][520/1251]	eta 0:27:12 lr 0.000335	time 1.8837 (2.2337)	loss 3.7617 (3.4162)	grad_norm 2.2073 (1.7748)	
[2022-01-23 12:15:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][530/1251]	eta 0:26:49 lr 0.000335	time 2.0657 (2.2316)	loss 2.7498 (3.4109)	grad_norm 1.7616 (1.7764)	
[2022-01-23 12:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][540/1251]	eta 0:26:24 lr 0.000335	time 1.8478 (2.2279)	loss 3.5771 (3.4131)	grad_norm 1.8486 (1.7781)	
[2022-01-23 12:16:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][550/1251]	eta 0:26:01 lr 0.000335	time 3.1724 (2.2280)	loss 3.2868 (3.4167)	grad_norm 2.1411 (1.7784)	
[2022-01-23 12:16:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][560/1251]	eta 0:25:38 lr 0.000335	time 2.2011 (2.2262)	loss 3.8527 (3.4137)	grad_norm 1.9485 (1.7802)	
[2022-01-23 12:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][570/1251]	eta 0:25:14 lr 0.000335	time 1.6020 (2.2243)	loss 3.9027 (3.4187)	grad_norm 1.7989 (1.7797)	
[2022-01-23 12:17:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][580/1251]	eta 0:24:53 lr 0.000335	time 2.4697 (2.2262)	loss 3.3743 (3.4176)	grad_norm 1.7991 (1.7794)	
[2022-01-23 12:17:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][590/1251]	eta 0:24:35 lr 0.000335	time 3.3742 (2.2318)	loss 2.3628 (3.4175)	grad_norm 2.0544 (1.7798)	
[2022-01-23 12:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][600/1251]	eta 0:24:12 lr 0.000335	time 1.9597 (2.2315)	loss 3.7418 (3.4151)	grad_norm 1.6942 (1.7822)	
[2022-01-23 12:18:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][610/1251]	eta 0:23:47 lr 0.000335	time 1.9620 (2.2274)	loss 3.6496 (3.4171)	grad_norm 2.0487 (1.7845)	
[2022-01-23 12:18:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][620/1251]	eta 0:23:21 lr 0.000335	time 1.7542 (2.2212)	loss 2.3965 (3.4158)	grad_norm 1.8857 (1.7835)	
[2022-01-23 12:19:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][630/1251]	eta 0:22:57 lr 0.000335	time 1.9767 (2.2188)	loss 4.1401 (3.4173)	grad_norm 2.0028 (1.7830)	
[2022-01-23 12:19:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][640/1251]	eta 0:22:34 lr 0.000335	time 2.2446 (2.2167)	loss 3.1350 (3.4148)	grad_norm 1.6686 (1.7822)	
[2022-01-23 12:19:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][650/1251]	eta 0:22:12 lr 0.000335	time 2.2061 (2.2175)	loss 3.0324 (3.4131)	grad_norm 1.6671 (1.7819)	
[2022-01-23 12:20:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][660/1251]	eta 0:21:49 lr 0.000335	time 1.9791 (2.2153)	loss 3.5548 (3.4159)	grad_norm 1.6840 (1.7812)	
[2022-01-23 12:20:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][670/1251]	eta 0:21:27 lr 0.000335	time 3.1967 (2.2158)	loss 4.0213 (3.4171)	grad_norm 1.6560 (1.7804)	
[2022-01-23 12:20:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][680/1251]	eta 0:21:06 lr 0.000335	time 2.8069 (2.2175)	loss 3.4313 (3.4188)	grad_norm 1.6455 (1.7809)	
[2022-01-23 12:21:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][690/1251]	eta 0:20:45 lr 0.000335	time 2.7786 (2.2194)	loss 4.1707 (3.4197)	grad_norm 1.6900 (1.7799)	
[2022-01-23 12:21:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][700/1251]	eta 0:20:21 lr 0.000335	time 1.8108 (2.2169)	loss 3.7225 (3.4228)	grad_norm 1.8032 (1.7789)	
[2022-01-23 12:22:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][710/1251]	eta 0:19:58 lr 0.000335	time 2.2329 (2.2156)	loss 3.6336 (3.4217)	grad_norm 1.8693 (1.7788)	
[2022-01-23 12:22:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][720/1251]	eta 0:19:36 lr 0.000335	time 2.1234 (2.2160)	loss 2.4459 (3.4206)	grad_norm 1.8015 (1.7799)	
[2022-01-23 12:22:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][730/1251]	eta 0:19:15 lr 0.000334	time 2.4429 (2.2183)	loss 3.7758 (3.4199)	grad_norm 1.7485 (1.7789)	
[2022-01-23 12:23:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][740/1251]	eta 0:18:52 lr 0.000334	time 1.6389 (2.2168)	loss 3.5535 (3.4254)	grad_norm 1.6397 (1.7787)	
[2022-01-23 12:23:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][750/1251]	eta 0:18:29 lr 0.000334	time 1.9046 (2.2151)	loss 3.6418 (3.4232)	grad_norm 1.7757 (1.7777)	
[2022-01-23 12:23:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][760/1251]	eta 0:18:06 lr 0.000334	time 2.6422 (2.2137)	loss 3.6405 (3.4227)	grad_norm 1.8383 (1.7774)	
[2022-01-23 12:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][770/1251]	eta 0:17:45 lr 0.000334	time 2.4837 (2.2147)	loss 4.0453 (3.4205)	grad_norm 1.7206 (1.7773)	
[2022-01-23 12:24:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][780/1251]	eta 0:17:23 lr 0.000334	time 2.2080 (2.2151)	loss 3.4203 (3.4168)	grad_norm 1.6865 (1.7774)	
[2022-01-23 12:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][790/1251]	eta 0:17:00 lr 0.000334	time 1.9253 (2.2147)	loss 2.7635 (3.4191)	grad_norm 1.7838 (1.7784)	
[2022-01-23 12:25:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][800/1251]	eta 0:16:38 lr 0.000334	time 2.6282 (2.2130)	loss 3.8454 (3.4180)	grad_norm 1.7521 (1.7789)	
[2022-01-23 12:25:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][810/1251]	eta 0:16:16 lr 0.000334	time 1.9074 (2.2140)	loss 3.0714 (3.4203)	grad_norm 1.8630 (1.7799)	
[2022-01-23 12:26:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][820/1251]	eta 0:15:53 lr 0.000334	time 1.9138 (2.2121)	loss 4.1105 (3.4202)	grad_norm 1.8704 (1.7791)	
[2022-01-23 12:26:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][830/1251]	eta 0:15:30 lr 0.000334	time 2.1511 (2.2102)	loss 3.6652 (3.4219)	grad_norm 1.8037 (1.7792)	
[2022-01-23 12:26:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][840/1251]	eta 0:15:08 lr 0.000334	time 1.9268 (2.2105)	loss 3.9983 (3.4221)	grad_norm 1.9280 (1.7795)	
[2022-01-23 12:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][850/1251]	eta 0:14:46 lr 0.000334	time 2.2865 (2.2098)	loss 3.0048 (3.4213)	grad_norm 2.5195 (1.7809)	
[2022-01-23 12:27:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][860/1251]	eta 0:14:23 lr 0.000334	time 2.2140 (2.2073)	loss 3.4390 (3.4186)	grad_norm 1.3967 (1.7817)	
[2022-01-23 12:27:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][870/1251]	eta 0:14:01 lr 0.000334	time 2.4829 (2.2075)	loss 3.8361 (3.4164)	grad_norm 1.6255 (1.7805)	
[2022-01-23 12:28:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][880/1251]	eta 0:13:38 lr 0.000334	time 1.9890 (2.2062)	loss 3.6715 (3.4153)	grad_norm 1.6922 (1.7807)	
[2022-01-23 12:28:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][890/1251]	eta 0:13:16 lr 0.000334	time 2.3677 (2.2051)	loss 3.9820 (3.4143)	grad_norm 1.6902 (1.7800)	
[2022-01-23 12:28:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][900/1251]	eta 0:12:53 lr 0.000334	time 1.8969 (2.2039)	loss 3.1711 (3.4151)	grad_norm 1.5585 (1.7793)	
[2022-01-23 12:29:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][910/1251]	eta 0:12:32 lr 0.000334	time 2.5401 (2.2056)	loss 3.4196 (3.4120)	grad_norm 1.7989 (1.7779)	
[2022-01-23 12:29:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][920/1251]	eta 0:12:10 lr 0.000334	time 1.8918 (2.2060)	loss 3.6173 (3.4128)	grad_norm 2.1957 (1.7774)	
[2022-01-23 12:30:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][930/1251]	eta 0:11:48 lr 0.000334	time 1.8794 (2.2069)	loss 3.4021 (3.4136)	grad_norm 1.7169 (1.7772)	
[2022-01-23 12:30:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][940/1251]	eta 0:11:26 lr 0.000334	time 2.1646 (2.2074)	loss 3.4786 (3.4136)	grad_norm 1.8717 (1.7776)	
[2022-01-23 12:30:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][950/1251]	eta 0:11:04 lr 0.000334	time 2.6156 (2.2092)	loss 4.0253 (3.4128)	grad_norm 1.6265 (1.7796)	
[2022-01-23 12:31:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][960/1251]	eta 0:10:43 lr 0.000334	time 3.1854 (2.2101)	loss 3.9544 (3.4135)	grad_norm 1.8572 (1.7808)	
[2022-01-23 12:31:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][970/1251]	eta 0:10:20 lr 0.000334	time 2.2053 (2.2087)	loss 3.5818 (3.4149)	grad_norm 1.9181 (1.7815)	
[2022-01-23 12:31:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][980/1251]	eta 0:09:58 lr 0.000334	time 1.6212 (2.2072)	loss 3.7891 (3.4155)	grad_norm 1.5636 (1.7807)	
[2022-01-23 12:32:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][990/1251]	eta 0:09:35 lr 0.000333	time 1.6053 (2.2054)	loss 3.6559 (3.4180)	grad_norm 1.6875 (1.7806)	
[2022-01-23 12:32:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1000/1251]	eta 0:09:13 lr 0.000333	time 2.7042 (2.2046)	loss 2.4372 (3.4168)	grad_norm 1.9980 (1.7815)	
[2022-01-23 12:32:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1010/1251]	eta 0:08:51 lr 0.000333	time 2.4879 (2.2037)	loss 2.6332 (3.4167)	grad_norm 1.8134 (1.7811)	
[2022-01-23 12:33:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1020/1251]	eta 0:08:29 lr 0.000333	time 2.5336 (2.2046)	loss 3.6233 (3.4155)	grad_norm 1.8229 (1.7811)	
[2022-01-23 12:33:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1030/1251]	eta 0:08:07 lr 0.000333	time 2.1366 (2.2056)	loss 3.8038 (3.4151)	grad_norm 1.7946 (1.7803)	
[2022-01-23 12:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1040/1251]	eta 0:07:45 lr 0.000333	time 2.5606 (2.2059)	loss 3.6603 (3.4160)	grad_norm 2.5022 (1.7812)	
[2022-01-23 12:34:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1050/1251]	eta 0:07:23 lr 0.000333	time 1.7808 (2.2040)	loss 3.7419 (3.4184)	grad_norm 1.7888 (1.7808)	
[2022-01-23 12:34:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1060/1251]	eta 0:07:00 lr 0.000333	time 2.1793 (2.2022)	loss 3.5806 (3.4173)	grad_norm 1.9526 (1.7814)	
[2022-01-23 12:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1070/1251]	eta 0:06:38 lr 0.000333	time 2.2556 (2.2012)	loss 3.0354 (3.4157)	grad_norm 2.0407 (1.7809)	
[2022-01-23 12:35:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1080/1251]	eta 0:06:16 lr 0.000333	time 2.8494 (2.2004)	loss 3.5811 (3.4168)	grad_norm 2.0318 (1.7812)	
[2022-01-23 12:35:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1090/1251]	eta 0:05:54 lr 0.000333	time 2.1757 (2.2011)	loss 3.5324 (3.4163)	grad_norm 1.5649 (1.7810)	
[2022-01-23 12:36:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1100/1251]	eta 0:05:32 lr 0.000333	time 2.2610 (2.2023)	loss 3.3261 (3.4166)	grad_norm 2.0219 (1.7813)	
[2022-01-23 12:36:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1110/1251]	eta 0:05:10 lr 0.000333	time 1.8344 (2.2015)	loss 3.1508 (3.4137)	grad_norm 1.7721 (1.7806)	
[2022-01-23 12:36:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1120/1251]	eta 0:04:48 lr 0.000333	time 2.4206 (2.2019)	loss 3.5401 (3.4120)	grad_norm 1.5113 (1.7802)	
[2022-01-23 12:37:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1130/1251]	eta 0:04:26 lr 0.000333	time 2.1640 (2.2020)	loss 3.7630 (3.4122)	grad_norm 1.4461 (1.7801)	
[2022-01-23 12:37:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1140/1251]	eta 0:04:04 lr 0.000333	time 1.7794 (2.2022)	loss 2.5370 (3.4106)	grad_norm 1.7544 (1.7796)	
[2022-01-23 12:38:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1150/1251]	eta 0:03:42 lr 0.000333	time 1.9131 (2.2012)	loss 3.6581 (3.4071)	grad_norm 1.5580 (1.7791)	
[2022-01-23 12:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1160/1251]	eta 0:03:20 lr 0.000333	time 1.8645 (2.2018)	loss 3.1512 (3.4064)	grad_norm 1.6927 (1.7785)	
[2022-01-23 12:38:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1170/1251]	eta 0:02:58 lr 0.000333	time 1.9030 (2.2007)	loss 3.6156 (3.4070)	grad_norm 1.6480 (1.7786)	
[2022-01-23 12:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1180/1251]	eta 0:02:36 lr 0.000333	time 1.5711 (2.2014)	loss 3.5899 (3.4057)	grad_norm 1.8615 (1.7781)	
[2022-01-23 12:39:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1190/1251]	eta 0:02:14 lr 0.000333	time 1.9017 (2.2014)	loss 3.8898 (3.4069)	grad_norm 1.7024 (1.7776)	
[2022-01-23 12:39:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1200/1251]	eta 0:01:52 lr 0.000333	time 2.3700 (2.2022)	loss 3.5251 (3.4050)	grad_norm 2.2108 (1.7776)	
[2022-01-23 12:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1210/1251]	eta 0:01:30 lr 0.000333	time 1.9087 (2.2018)	loss 3.1580 (3.4037)	grad_norm 1.6408 (1.7777)	
[2022-01-23 12:40:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1220/1251]	eta 0:01:08 lr 0.000333	time 1.9416 (2.2018)	loss 3.7739 (3.4033)	grad_norm 1.4871 (1.7764)	
[2022-01-23 12:40:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1230/1251]	eta 0:00:46 lr 0.000333	time 1.7064 (2.2010)	loss 2.8960 (3.4054)	grad_norm 1.5796 (1.7758)	
[2022-01-23 12:41:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1240/1251]	eta 0:00:24 lr 0.000332	time 1.3126 (2.2001)	loss 3.1149 (3.4059)	grad_norm 1.7732 (1.7755)	
[2022-01-23 12:41:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [183/300][1250/1251]	eta 0:00:02 lr 0.000332	time 1.1783 (2.1949)	loss 2.2680 (3.4060)	grad_norm 1.7777 (1.7754)	
[2022-01-23 12:41:35 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 183 training takes 0:45:46
[2022-01-23 12:41:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.759 (18.759)	Loss 1.0226 (1.0226)	Acc@1 74.805 (74.805)	Acc@5 93.555 (93.555)	
[2022-01-23 12:42:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.594 (3.271)	Loss 0.9339 (0.9570)	Acc@1 78.516 (77.264)	Acc@5 93.164 (93.839)	
[2022-01-23 12:42:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.452 (2.640)	Loss 0.9759 (0.9558)	Acc@1 78.223 (77.144)	Acc@5 93.457 (93.871)	
[2022-01-23 12:42:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.951 (2.241)	Loss 0.9505 (0.9616)	Acc@1 76.855 (77.010)	Acc@5 94.336 (93.750)	
[2022-01-23 12:43:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.870 (2.159)	Loss 0.9103 (0.9553)	Acc@1 78.516 (77.244)	Acc@5 94.238 (93.874)	
[2022-01-23 12:43:11 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.402 Acc@5 93.976
[2022-01-23 12:43:11 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.4%
[2022-01-23 12:43:11 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.51%
[2022-01-23 12:43:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][0/1251]	eta 7:37:44 lr 0.000332	time 21.9539 (21.9539)	loss 2.2831 (2.2831)	grad_norm 1.6299 (1.6299)	
[2022-01-23 12:43:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][10/1251]	eta 1:26:58 lr 0.000332	time 2.4164 (4.2047)	loss 3.5328 (3.5076)	grad_norm 1.6182 (1.7067)	
[2022-01-23 12:44:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][20/1251]	eta 1:06:10 lr 0.000332	time 1.5829 (3.2258)	loss 3.7156 (3.4034)	grad_norm 1.7416 (1.7464)	
[2022-01-23 12:44:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][30/1251]	eta 0:59:12 lr 0.000332	time 2.2213 (2.9092)	loss 3.5036 (3.3707)	grad_norm 2.1230 (1.8124)	
[2022-01-23 12:45:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][40/1251]	eta 0:55:06 lr 0.000332	time 2.9269 (2.7303)	loss 3.6260 (3.3531)	grad_norm 1.7629 (1.8248)	
[2022-01-23 12:45:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][50/1251]	eta 0:52:58 lr 0.000332	time 1.8931 (2.6463)	loss 2.9928 (3.3567)	grad_norm 1.9706 (1.8085)	
[2022-01-23 12:45:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][60/1251]	eta 0:50:51 lr 0.000332	time 1.6123 (2.5621)	loss 4.1412 (3.3828)	grad_norm 1.6201 (1.7963)	
[2022-01-23 12:46:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][70/1251]	eta 0:49:22 lr 0.000332	time 1.6068 (2.5088)	loss 3.3342 (3.3544)	grad_norm 1.6964 (1.7970)	
[2022-01-23 12:46:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][80/1251]	eta 0:48:16 lr 0.000332	time 2.9343 (2.4739)	loss 3.9935 (3.3726)	grad_norm 1.9512 (1.7919)	
[2022-01-23 12:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][90/1251]	eta 0:47:42 lr 0.000332	time 2.2284 (2.4659)	loss 3.8984 (3.3700)	grad_norm 1.8423 (1.7885)	
[2022-01-23 12:47:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][100/1251]	eta 0:46:47 lr 0.000332	time 1.5299 (2.4393)	loss 2.1773 (3.3566)	grad_norm 2.0585 (1.7873)	
[2022-01-23 12:47:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][110/1251]	eta 0:45:44 lr 0.000332	time 1.7829 (2.4051)	loss 3.7697 (3.3571)	grad_norm 1.8136 (1.7790)	
[2022-01-23 12:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][120/1251]	eta 0:44:55 lr 0.000332	time 2.9155 (2.3837)	loss 3.4790 (3.3605)	grad_norm 1.9981 (1.7787)	
[2022-01-23 12:48:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][130/1251]	eta 0:44:18 lr 0.000332	time 2.1894 (2.3714)	loss 3.0508 (3.3562)	grad_norm 1.7404 (1.7778)	
[2022-01-23 12:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][140/1251]	eta 0:43:38 lr 0.000332	time 2.1335 (2.3565)	loss 3.8153 (3.3496)	grad_norm 1.7252 (1.7715)	
[2022-01-23 12:49:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][150/1251]	eta 0:43:03 lr 0.000332	time 2.6064 (2.3465)	loss 3.3454 (3.3529)	grad_norm 1.8037 (1.7745)	
[2022-01-23 12:49:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][160/1251]	eta 0:42:35 lr 0.000332	time 2.2271 (2.3425)	loss 2.7263 (3.3525)	grad_norm 1.6696 (1.7759)	
[2022-01-23 12:49:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][170/1251]	eta 0:42:07 lr 0.000332	time 1.8892 (2.3378)	loss 3.3432 (3.3571)	grad_norm 1.6113 (1.7740)	
[2022-01-23 12:50:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][180/1251]	eta 0:41:34 lr 0.000332	time 1.7766 (2.3294)	loss 3.5546 (3.3688)	grad_norm 1.6896 (1.7716)	
[2022-01-23 12:50:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][190/1251]	eta 0:40:53 lr 0.000332	time 1.7837 (2.3122)	loss 3.4984 (3.3649)	grad_norm 1.7671 (1.7720)	
[2022-01-23 12:50:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][200/1251]	eta 0:40:16 lr 0.000332	time 2.1819 (2.2996)	loss 3.1669 (3.3626)	grad_norm 1.7925 (1.7679)	
[2022-01-23 12:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][210/1251]	eta 0:39:47 lr 0.000332	time 2.7920 (2.2932)	loss 3.3184 (3.3810)	grad_norm 1.7621 (1.7664)	
[2022-01-23 12:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][220/1251]	eta 0:39:17 lr 0.000332	time 1.9018 (2.2865)	loss 3.6290 (3.3943)	grad_norm 1.8252 (1.7739)	
[2022-01-23 12:52:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][230/1251]	eta 0:38:57 lr 0.000332	time 2.5182 (2.2893)	loss 2.8165 (3.3970)	grad_norm 1.9331 (1.7750)	
[2022-01-23 12:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][240/1251]	eta 0:38:42 lr 0.000332	time 2.4594 (2.2968)	loss 2.8341 (3.4021)	grad_norm 1.6565 (1.7776)	
[2022-01-23 12:52:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][250/1251]	eta 0:38:12 lr 0.000331	time 2.1796 (2.2900)	loss 4.1330 (3.4121)	grad_norm 1.8065 (1.7816)	
[2022-01-23 12:53:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][260/1251]	eta 0:37:40 lr 0.000331	time 1.8905 (2.2807)	loss 3.7675 (3.4170)	grad_norm 2.0971 (1.7839)	
[2022-01-23 12:53:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][270/1251]	eta 0:37:08 lr 0.000331	time 1.7363 (2.2715)	loss 3.7037 (3.4195)	grad_norm 1.6810 (1.7823)	
[2022-01-23 12:53:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][280/1251]	eta 0:36:37 lr 0.000331	time 1.8809 (2.2636)	loss 3.9030 (3.4125)	grad_norm 1.8373 (1.7802)	
[2022-01-23 12:54:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][290/1251]	eta 0:36:08 lr 0.000331	time 1.8978 (2.2568)	loss 3.3520 (3.4107)	grad_norm 1.8525 (1.7853)	
[2022-01-23 12:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][300/1251]	eta 0:35:42 lr 0.000331	time 1.8112 (2.2530)	loss 3.2166 (3.4117)	grad_norm 1.6335 (1.7862)	
[2022-01-23 12:54:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][310/1251]	eta 0:35:17 lr 0.000331	time 1.5105 (2.2501)	loss 3.9510 (3.4077)	grad_norm 1.7449 (1.7845)	
[2022-01-23 12:55:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][320/1251]	eta 0:34:55 lr 0.000331	time 1.8928 (2.2507)	loss 3.7449 (3.4045)	grad_norm 1.7178 (1.7836)	
[2022-01-23 12:55:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][330/1251]	eta 0:34:33 lr 0.000331	time 2.8626 (2.2516)	loss 3.2364 (3.4056)	grad_norm 1.4515 (1.7822)	
[2022-01-23 12:55:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][340/1251]	eta 0:34:09 lr 0.000331	time 2.8483 (2.2499)	loss 3.7958 (3.4071)	grad_norm 1.8207 (1.7794)	
[2022-01-23 12:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][350/1251]	eta 0:33:52 lr 0.000331	time 2.5185 (2.2554)	loss 3.2707 (3.4054)	grad_norm 1.8378 (1.7777)	
[2022-01-23 12:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][360/1251]	eta 0:33:34 lr 0.000331	time 1.8961 (2.2608)	loss 3.8012 (3.4049)	grad_norm 1.5655 (1.7754)	
[2022-01-23 12:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][370/1251]	eta 0:33:09 lr 0.000331	time 1.7321 (2.2581)	loss 3.2712 (3.4080)	grad_norm 1.9392 (1.7752)	
[2022-01-23 12:57:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][380/1251]	eta 0:32:38 lr 0.000331	time 1.6840 (2.2490)	loss 3.3031 (3.4124)	grad_norm 1.9275 (1.7779)	
[2022-01-23 12:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][390/1251]	eta 0:32:10 lr 0.000331	time 2.1141 (2.2421)	loss 3.9642 (3.4181)	grad_norm 1.9923 (1.7878)	
[2022-01-23 12:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][400/1251]	eta 0:31:41 lr 0.000331	time 1.8402 (2.2348)	loss 3.6251 (3.4204)	grad_norm 1.9539 (1.7912)	
[2022-01-23 12:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][410/1251]	eta 0:31:18 lr 0.000331	time 2.1605 (2.2336)	loss 3.9286 (3.4221)	grad_norm 1.8467 (1.7931)	
[2022-01-23 12:58:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][420/1251]	eta 0:30:54 lr 0.000331	time 1.8124 (2.2320)	loss 4.1568 (3.4214)	grad_norm 1.8586 (1.7928)	
[2022-01-23 12:59:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][430/1251]	eta 0:30:32 lr 0.000331	time 2.6970 (2.2322)	loss 2.9389 (3.4154)	grad_norm 1.8851 (1.7927)	
[2022-01-23 12:59:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][440/1251]	eta 0:30:10 lr 0.000331	time 2.3645 (2.2325)	loss 4.0495 (3.4184)	grad_norm 2.0237 (1.7918)	
[2022-01-23 12:59:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][450/1251]	eta 0:29:50 lr 0.000331	time 1.6547 (2.2350)	loss 3.8247 (3.4205)	grad_norm 1.6826 (1.7923)	
[2022-01-23 13:00:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][460/1251]	eta 0:29:28 lr 0.000331	time 1.8714 (2.2352)	loss 3.0997 (3.4204)	grad_norm 1.9140 (1.7918)	
[2022-01-23 13:00:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][470/1251]	eta 0:29:08 lr 0.000331	time 2.3315 (2.2391)	loss 2.4790 (3.4192)	grad_norm 1.8832 (1.7920)	
[2022-01-23 13:01:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][480/1251]	eta 0:28:54 lr 0.000331	time 3.0773 (2.2496)	loss 3.8108 (3.4247)	grad_norm 1.6500 (1.7920)	
[2022-01-23 13:01:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][490/1251]	eta 0:28:33 lr 0.000331	time 2.6210 (2.2514)	loss 3.4122 (3.4243)	grad_norm 1.6511 (1.7920)	
[2022-01-23 13:01:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][500/1251]	eta 0:28:08 lr 0.000331	time 1.8574 (2.2490)	loss 3.2644 (3.4249)	grad_norm 1.5822 (1.7903)	
[2022-01-23 13:02:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][510/1251]	eta 0:27:41 lr 0.000330	time 1.8630 (2.2422)	loss 2.6675 (3.4299)	grad_norm 2.0860 (1.7895)	
[2022-01-23 13:02:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][520/1251]	eta 0:27:13 lr 0.000330	time 1.9074 (2.2341)	loss 3.9078 (3.4299)	grad_norm 1.8141 (1.7900)	
[2022-01-23 13:02:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][530/1251]	eta 0:26:49 lr 0.000330	time 1.8654 (2.2318)	loss 2.9584 (3.4301)	grad_norm 1.5923 (1.7887)	
[2022-01-23 13:03:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][540/1251]	eta 0:26:25 lr 0.000330	time 2.1776 (2.2298)	loss 3.0665 (3.4321)	grad_norm 1.4496 (1.7875)	
[2022-01-23 13:03:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][550/1251]	eta 0:26:02 lr 0.000330	time 1.9879 (2.2291)	loss 3.0102 (3.4338)	grad_norm 1.9241 (1.7880)	
[2022-01-23 13:04:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][560/1251]	eta 0:25:43 lr 0.000330	time 2.8592 (2.2341)	loss 3.6207 (3.4342)	grad_norm 1.7970 (1.7893)	
[2022-01-23 13:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][570/1251]	eta 0:25:21 lr 0.000330	time 2.4878 (2.2349)	loss 3.9351 (3.4361)	grad_norm 1.7471 (1.7877)	
[2022-01-23 13:04:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][580/1251]	eta 0:25:01 lr 0.000330	time 2.5876 (2.2371)	loss 3.9982 (3.4346)	grad_norm 1.7885 (1.7870)	
[2022-01-23 13:05:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][590/1251]	eta 0:24:39 lr 0.000330	time 2.2893 (2.2376)	loss 3.8057 (3.4364)	grad_norm 1.8116 (1.7863)	
[2022-01-23 13:05:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][600/1251]	eta 0:24:15 lr 0.000330	time 1.8978 (2.2360)	loss 3.5602 (3.4383)	grad_norm 1.4258 (1.7855)	
[2022-01-23 13:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][610/1251]	eta 0:23:52 lr 0.000330	time 2.6929 (2.2343)	loss 4.0912 (3.4391)	grad_norm 1.7340 (1.7855)	
[2022-01-23 13:06:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][620/1251]	eta 0:23:28 lr 0.000330	time 2.3261 (2.2324)	loss 2.5839 (3.4350)	grad_norm 1.8319 (1.7853)	
[2022-01-23 13:06:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][630/1251]	eta 0:23:05 lr 0.000330	time 2.0227 (2.2308)	loss 3.7261 (3.4378)	grad_norm 1.7562 (1.7876)	
[2022-01-23 13:07:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][640/1251]	eta 0:22:43 lr 0.000330	time 2.1855 (2.2312)	loss 3.9325 (3.4376)	grad_norm 1.7621 (1.7873)	
[2022-01-23 13:07:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][650/1251]	eta 0:22:21 lr 0.000330	time 1.9703 (2.2323)	loss 3.7070 (3.4337)	grad_norm 1.6868 (1.7855)	
[2022-01-23 13:07:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][660/1251]	eta 0:21:58 lr 0.000330	time 2.2646 (2.2317)	loss 3.5860 (3.4312)	grad_norm 2.5219 (1.7860)	
[2022-01-23 13:08:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][670/1251]	eta 0:21:35 lr 0.000330	time 1.9205 (2.2295)	loss 4.0747 (3.4335)	grad_norm 1.6443 (1.7851)	
[2022-01-23 13:08:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][680/1251]	eta 0:21:12 lr 0.000330	time 3.2037 (2.2288)	loss 4.0339 (3.4323)	grad_norm 1.7620 (1.7859)	
[2022-01-23 13:08:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][690/1251]	eta 0:20:48 lr 0.000330	time 2.2039 (2.2264)	loss 2.9115 (3.4353)	grad_norm 1.6912 (1.7856)	
[2022-01-23 13:09:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][700/1251]	eta 0:20:25 lr 0.000330	time 1.8816 (2.2240)	loss 4.0566 (3.4361)	grad_norm 1.6513 (1.7858)	
[2022-01-23 13:09:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][710/1251]	eta 0:20:02 lr 0.000330	time 2.5837 (2.2228)	loss 3.7852 (3.4344)	grad_norm 1.8445 (1.7852)	
[2022-01-23 13:09:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][720/1251]	eta 0:19:40 lr 0.000330	time 1.9125 (2.2232)	loss 2.6371 (3.4296)	grad_norm 1.6017 (1.7836)	
[2022-01-23 13:10:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][730/1251]	eta 0:19:17 lr 0.000330	time 2.6025 (2.2221)	loss 2.8523 (3.4306)	grad_norm 1.8679 (1.7839)	
[2022-01-23 13:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][740/1251]	eta 0:18:54 lr 0.000330	time 2.1780 (2.2209)	loss 4.1632 (3.4322)	grad_norm 1.7469 (1.7854)	
[2022-01-23 13:10:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][750/1251]	eta 0:18:32 lr 0.000330	time 2.4891 (2.2203)	loss 4.0551 (3.4321)	grad_norm 1.5313 (1.7858)	
[2022-01-23 13:11:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][760/1251]	eta 0:18:10 lr 0.000330	time 1.9167 (2.2210)	loss 3.9924 (3.4345)	grad_norm 1.9371 (1.7856)	
[2022-01-23 13:11:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][770/1251]	eta 0:17:48 lr 0.000329	time 1.8151 (2.2205)	loss 3.3075 (3.4334)	grad_norm 1.7424 (1.7852)	
[2022-01-23 13:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][780/1251]	eta 0:17:26 lr 0.000329	time 2.6381 (2.2229)	loss 3.3599 (3.4320)	grad_norm 1.8759 (1.7860)	
[2022-01-23 13:12:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][790/1251]	eta 0:17:04 lr 0.000329	time 2.7972 (2.2227)	loss 3.5229 (3.4303)	grad_norm 1.7639 (1.7850)	
[2022-01-23 13:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][800/1251]	eta 0:16:41 lr 0.000329	time 1.6468 (2.2200)	loss 3.7169 (3.4335)	grad_norm 1.4803 (1.7847)	
[2022-01-23 13:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][810/1251]	eta 0:16:18 lr 0.000329	time 2.1524 (2.2179)	loss 4.1001 (3.4314)	grad_norm 1.6609 (1.7847)	
[2022-01-23 13:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][820/1251]	eta 0:15:55 lr 0.000329	time 1.9141 (2.2175)	loss 2.4988 (3.4266)	grad_norm 1.6894 (1.7846)	
[2022-01-23 13:13:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][830/1251]	eta 0:15:32 lr 0.000329	time 2.3507 (2.2161)	loss 3.5862 (3.4268)	grad_norm 1.8959 (1.7840)	
[2022-01-23 13:14:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][840/1251]	eta 0:15:10 lr 0.000329	time 2.1543 (2.2157)	loss 3.7495 (3.4274)	grad_norm 1.6112 (1.7832)	
[2022-01-23 13:14:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][850/1251]	eta 0:14:48 lr 0.000329	time 2.5654 (2.2154)	loss 2.8896 (3.4277)	grad_norm 1.4434 (1.7829)	
[2022-01-23 13:14:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][860/1251]	eta 0:14:25 lr 0.000329	time 1.9016 (2.2140)	loss 4.1747 (3.4254)	grad_norm 1.5753 (1.7847)	
[2022-01-23 13:15:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][870/1251]	eta 0:14:03 lr 0.000329	time 2.8503 (2.2132)	loss 3.3947 (3.4255)	grad_norm 1.8492 (1.7863)	
[2022-01-23 13:15:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][880/1251]	eta 0:13:41 lr 0.000329	time 3.0448 (2.2141)	loss 3.7786 (3.4276)	grad_norm 1.9460 (1.7857)	
[2022-01-23 13:16:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][890/1251]	eta 0:13:19 lr 0.000329	time 2.1960 (2.2148)	loss 3.8344 (3.4309)	grad_norm 1.9709 (1.7890)	
[2022-01-23 13:16:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][900/1251]	eta 0:12:58 lr 0.000329	time 2.7510 (2.2169)	loss 3.6707 (3.4310)	grad_norm 1.4659 (1.7894)	
[2022-01-23 13:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][910/1251]	eta 0:12:36 lr 0.000329	time 1.9202 (2.2177)	loss 3.2939 (3.4314)	grad_norm 1.7007 (1.7892)	
[2022-01-23 13:17:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][920/1251]	eta 0:12:14 lr 0.000329	time 2.5087 (2.2186)	loss 3.0466 (3.4274)	grad_norm 1.6502 (1.7887)	
[2022-01-23 13:17:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][930/1251]	eta 0:11:51 lr 0.000329	time 1.9735 (2.2156)	loss 2.1229 (3.4250)	grad_norm 1.7620 (1.7884)	
[2022-01-23 13:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][940/1251]	eta 0:11:28 lr 0.000329	time 2.9280 (2.2136)	loss 3.5417 (3.4245)	grad_norm 2.2127 (1.7889)	
[2022-01-23 13:18:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][950/1251]	eta 0:11:05 lr 0.000329	time 2.1845 (2.2116)	loss 3.1935 (3.4247)	grad_norm 1.8125 (1.7894)	
[2022-01-23 13:18:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][960/1251]	eta 0:10:43 lr 0.000329	time 2.4542 (2.2111)	loss 3.8269 (3.4224)	grad_norm 1.5998 (1.7900)	
[2022-01-23 13:18:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][970/1251]	eta 0:10:20 lr 0.000329	time 2.2493 (2.2098)	loss 3.6733 (3.4219)	grad_norm 1.7730 (1.7903)	
[2022-01-23 13:19:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][980/1251]	eta 0:09:58 lr 0.000329	time 2.0075 (2.2099)	loss 3.2297 (3.4206)	grad_norm 1.5264 (1.7907)	
[2022-01-23 13:19:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][990/1251]	eta 0:09:36 lr 0.000329	time 2.1505 (2.2104)	loss 3.5274 (3.4222)	grad_norm 1.5754 (1.7908)	
[2022-01-23 13:20:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1000/1251]	eta 0:09:15 lr 0.000329	time 1.8381 (2.2119)	loss 2.4893 (3.4198)	grad_norm 1.6637 (1.7899)	
[2022-01-23 13:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1010/1251]	eta 0:08:53 lr 0.000329	time 2.1636 (2.2134)	loss 3.4178 (3.4185)	grad_norm 1.5341 (1.7890)	
[2022-01-23 13:20:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1020/1251]	eta 0:08:31 lr 0.000329	time 2.0908 (2.2123)	loss 3.2494 (3.4171)	grad_norm 1.7093 (1.7886)	
[2022-01-23 13:21:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1030/1251]	eta 0:08:08 lr 0.000328	time 2.2555 (2.2109)	loss 3.2682 (3.4177)	grad_norm 1.6632 (1.7885)	
[2022-01-23 13:21:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1040/1251]	eta 0:07:46 lr 0.000328	time 1.9375 (2.2091)	loss 2.6853 (3.4178)	grad_norm 1.8825 (1.7879)	
[2022-01-23 13:21:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1050/1251]	eta 0:07:23 lr 0.000328	time 2.2202 (2.2087)	loss 3.4776 (3.4176)	grad_norm 1.9514 (1.7878)	
[2022-01-23 13:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1060/1251]	eta 0:07:01 lr 0.000328	time 1.8521 (2.2081)	loss 3.5184 (3.4197)	grad_norm 1.9230 (1.7879)	
[2022-01-23 13:22:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1070/1251]	eta 0:06:39 lr 0.000328	time 2.3274 (2.2084)	loss 3.6767 (3.4182)	grad_norm 1.7669 (1.7877)	
[2022-01-23 13:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1080/1251]	eta 0:06:17 lr 0.000328	time 2.5970 (2.2099)	loss 3.4971 (3.4191)	grad_norm 1.7313 (1.7874)	
[2022-01-23 13:23:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1090/1251]	eta 0:05:55 lr 0.000328	time 2.1522 (2.2107)	loss 2.4603 (3.4192)	grad_norm 1.7766 (1.7869)	
[2022-01-23 13:23:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1100/1251]	eta 0:05:33 lr 0.000328	time 1.7235 (2.2093)	loss 3.1532 (3.4186)	grad_norm 1.6134 (1.7865)	
[2022-01-23 13:24:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1110/1251]	eta 0:05:11 lr 0.000328	time 1.9460 (2.2082)	loss 2.9959 (3.4168)	grad_norm 1.6373 (1.7874)	
[2022-01-23 13:24:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1120/1251]	eta 0:04:49 lr 0.000328	time 2.5199 (2.2070)	loss 3.6978 (3.4167)	grad_norm 1.6269 (1.7872)	
[2022-01-23 13:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1130/1251]	eta 0:04:27 lr 0.000328	time 2.5627 (2.2068)	loss 3.8245 (3.4167)	grad_norm 1.5804 (1.7874)	
[2022-01-23 13:25:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1140/1251]	eta 0:04:04 lr 0.000328	time 2.2275 (2.2063)	loss 3.5815 (3.4180)	grad_norm 1.5543 (1.7876)	
[2022-01-23 13:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1150/1251]	eta 0:03:42 lr 0.000328	time 1.8541 (2.2064)	loss 4.1230 (3.4172)	grad_norm 2.0003 (1.7870)	
[2022-01-23 13:25:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1160/1251]	eta 0:03:20 lr 0.000328	time 2.0205 (2.2068)	loss 3.7707 (3.4189)	grad_norm 1.6257 (1.7869)	
[2022-01-23 13:26:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1170/1251]	eta 0:02:58 lr 0.000328	time 2.1975 (2.2062)	loss 3.9702 (3.4195)	grad_norm 1.8694 (1.7867)	
[2022-01-23 13:26:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1180/1251]	eta 0:02:36 lr 0.000328	time 3.0414 (2.2072)	loss 2.6126 (3.4214)	grad_norm 1.6907 (1.7858)	
[2022-01-23 13:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1190/1251]	eta 0:02:14 lr 0.000328	time 2.4005 (2.2078)	loss 3.2675 (3.4227)	grad_norm 1.6266 (1.7853)	
[2022-01-23 13:27:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1200/1251]	eta 0:01:52 lr 0.000328	time 2.5148 (2.2089)	loss 3.3400 (3.4244)	grad_norm 1.6801 (1.7844)	
[2022-01-23 13:27:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1210/1251]	eta 0:01:30 lr 0.000328	time 2.2155 (2.2085)	loss 3.7317 (3.4249)	grad_norm 1.6535 (1.7838)	
[2022-01-23 13:28:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1220/1251]	eta 0:01:08 lr 0.000328	time 3.3731 (2.2089)	loss 3.9513 (3.4253)	grad_norm 1.5744 (1.7836)	
[2022-01-23 13:28:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1230/1251]	eta 0:00:46 lr 0.000328	time 1.6214 (2.2072)	loss 2.6348 (3.4240)	grad_norm 1.6003 (1.7829)	
[2022-01-23 13:28:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1240/1251]	eta 0:00:24 lr 0.000328	time 1.2519 (2.2064)	loss 2.7469 (3.4235)	grad_norm 1.6768 (1.7832)	
[2022-01-23 13:29:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [184/300][1250/1251]	eta 0:00:02 lr 0.000328	time 1.1781 (2.2015)	loss 3.6657 (3.4255)	grad_norm 1.6277 (1.7829)	
[2022-01-23 13:29:06 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 184 training takes 0:45:54
[2022-01-23 13:29:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.887 (18.887)	Loss 0.9228 (0.9228)	Acc@1 79.395 (79.395)	Acc@5 94.434 (94.434)	
[2022-01-23 13:29:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.893 (3.331)	Loss 0.9974 (0.9507)	Acc@1 76.660 (77.894)	Acc@5 94.141 (94.025)	
[2022-01-23 13:29:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.532 (2.481)	Loss 1.0183 (0.9555)	Acc@1 76.074 (77.832)	Acc@5 94.336 (93.996)	
[2022-01-23 13:30:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.642 (2.259)	Loss 0.9438 (0.9602)	Acc@1 78.711 (77.646)	Acc@5 94.043 (93.986)	
[2022-01-23 13:30:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.535 (2.156)	Loss 0.9110 (0.9573)	Acc@1 76.953 (77.620)	Acc@5 95.508 (94.014)	
[2022-01-23 13:30:41 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.562 Acc@5 93.998
[2022-01-23 13:30:41 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.6%
[2022-01-23 13:30:41 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.56%
[2022-01-23 13:31:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][0/1251]	eta 7:17:49 lr 0.000328	time 20.9988 (20.9988)	loss 3.3484 (3.3484)	grad_norm 1.6913 (1.6913)	
[2022-01-23 13:31:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][10/1251]	eta 1:25:08 lr 0.000328	time 2.2601 (4.1168)	loss 3.1224 (3.3656)	grad_norm 1.6351 (1.7762)	
[2022-01-23 13:31:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][20/1251]	eta 1:07:08 lr 0.000328	time 1.9309 (3.2726)	loss 4.2264 (3.3070)	grad_norm 1.7625 (1.7560)	
[2022-01-23 13:32:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][30/1251]	eta 0:59:30 lr 0.000327	time 1.6791 (2.9239)	loss 3.8545 (3.3324)	grad_norm 1.7595 (1.7638)	
[2022-01-23 13:32:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][40/1251]	eta 0:55:32 lr 0.000327	time 2.8381 (2.7523)	loss 2.6540 (3.3438)	grad_norm 1.6332 (1.7943)	
[2022-01-23 13:32:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][50/1251]	eta 0:52:48 lr 0.000327	time 1.5884 (2.6380)	loss 2.7342 (3.3060)	grad_norm 1.9312 (1.8035)	
[2022-01-23 13:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][60/1251]	eta 0:50:52 lr 0.000327	time 1.8978 (2.5629)	loss 3.8436 (3.3040)	grad_norm 1.6942 (1.7956)	
[2022-01-23 13:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][70/1251]	eta 0:49:32 lr 0.000327	time 1.8473 (2.5168)	loss 2.6960 (3.3273)	grad_norm 1.7166 (1.7977)	
[2022-01-23 13:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][80/1251]	eta 0:48:35 lr 0.000327	time 2.6842 (2.4894)	loss 3.5279 (3.3536)	grad_norm 1.8056 (1.7933)	
[2022-01-23 13:34:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][90/1251]	eta 0:47:22 lr 0.000327	time 1.9129 (2.4484)	loss 4.0900 (3.3419)	grad_norm 1.5924 (1.7868)	
[2022-01-23 13:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][100/1251]	eta 0:46:22 lr 0.000327	time 1.8989 (2.4178)	loss 2.3900 (3.3542)	grad_norm 1.7857 (1.7821)	
[2022-01-23 13:35:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][110/1251]	eta 0:45:19 lr 0.000327	time 1.9890 (2.3835)	loss 3.9746 (3.3692)	grad_norm 1.7675 (1.7825)	
[2022-01-23 13:35:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][120/1251]	eta 0:44:39 lr 0.000327	time 1.8668 (2.3689)	loss 2.9633 (3.3733)	grad_norm 1.9797 (1.7934)	
[2022-01-23 13:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][130/1251]	eta 0:43:50 lr 0.000327	time 1.7744 (2.3466)	loss 3.2324 (3.3880)	grad_norm 1.8589 (1.7947)	
[2022-01-23 13:36:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][140/1251]	eta 0:43:22 lr 0.000327	time 2.4388 (2.3420)	loss 2.5450 (3.3723)	grad_norm 1.7451 (1.7890)	
[2022-01-23 13:36:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][150/1251]	eta 0:42:44 lr 0.000327	time 1.8505 (2.3296)	loss 3.6369 (3.3875)	grad_norm 1.6875 (1.7929)	
[2022-01-23 13:36:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][160/1251]	eta 0:42:10 lr 0.000327	time 1.8273 (2.3199)	loss 3.6777 (3.3747)	grad_norm 1.5218 (1.7944)	
[2022-01-23 13:37:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][170/1251]	eta 0:41:50 lr 0.000327	time 2.4465 (2.3223)	loss 3.7759 (3.3835)	grad_norm 1.6380 (1.7977)	
[2022-01-23 13:37:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][180/1251]	eta 0:41:22 lr 0.000327	time 1.9749 (2.3182)	loss 2.4635 (3.3904)	grad_norm 2.0516 (1.7931)	
[2022-01-23 13:38:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][190/1251]	eta 0:40:42 lr 0.000327	time 1.6653 (2.3023)	loss 3.0093 (3.3816)	grad_norm 1.6213 (1.7911)	
[2022-01-23 13:38:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][200/1251]	eta 0:40:10 lr 0.000327	time 2.1673 (2.2932)	loss 3.3200 (3.3616)	grad_norm 1.8019 (1.7892)	
[2022-01-23 13:38:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][210/1251]	eta 0:39:40 lr 0.000327	time 2.0560 (2.2871)	loss 3.1663 (3.3713)	grad_norm 1.6057 (1.7845)	
[2022-01-23 13:39:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][220/1251]	eta 0:39:11 lr 0.000327	time 1.5852 (2.2806)	loss 2.5845 (3.3676)	grad_norm 1.8836 (1.7831)	
[2022-01-23 13:39:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][230/1251]	eta 0:38:40 lr 0.000327	time 1.8506 (2.2731)	loss 3.5205 (3.3744)	grad_norm 2.3845 (1.7838)	
[2022-01-23 13:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][240/1251]	eta 0:38:15 lr 0.000327	time 1.9761 (2.2703)	loss 2.8441 (3.3772)	grad_norm 2.1447 (1.7917)	
[2022-01-23 13:40:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][250/1251]	eta 0:37:51 lr 0.000327	time 3.0730 (2.2694)	loss 4.0665 (3.3895)	grad_norm 1.7437 (1.7873)	
[2022-01-23 13:40:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][260/1251]	eta 0:37:24 lr 0.000327	time 1.5972 (2.2653)	loss 2.5155 (3.3872)	grad_norm 1.5425 (1.7893)	
[2022-01-23 13:40:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][270/1251]	eta 0:37:04 lr 0.000327	time 1.4918 (2.2676)	loss 3.4260 (3.3844)	grad_norm 1.7693 (1.7905)	
[2022-01-23 13:41:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][280/1251]	eta 0:36:45 lr 0.000327	time 1.8823 (2.2718)	loss 3.3391 (3.3787)	grad_norm 1.7504 (1.7900)	
[2022-01-23 13:41:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][290/1251]	eta 0:36:26 lr 0.000326	time 3.0963 (2.2757)	loss 3.4362 (3.3817)	grad_norm 1.6588 (1.7886)	
[2022-01-23 13:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][300/1251]	eta 0:35:55 lr 0.000326	time 1.6179 (2.2661)	loss 3.2535 (3.3805)	grad_norm 1.8431 (1.7886)	
[2022-01-23 13:42:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][310/1251]	eta 0:35:24 lr 0.000326	time 1.9958 (2.2581)	loss 3.0568 (3.3793)	grad_norm 1.9973 (1.7912)	
[2022-01-23 13:42:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][320/1251]	eta 0:34:53 lr 0.000326	time 1.8869 (2.2490)	loss 4.1616 (3.3785)	grad_norm 1.8088 (1.7915)	
[2022-01-23 13:43:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][330/1251]	eta 0:34:29 lr 0.000326	time 2.5766 (2.2471)	loss 4.0611 (3.3789)	grad_norm 1.9914 (1.7929)	
[2022-01-23 13:43:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][340/1251]	eta 0:34:05 lr 0.000326	time 1.8565 (2.2450)	loss 3.3134 (3.3821)	grad_norm 1.8105 (1.7894)	
[2022-01-23 13:43:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][350/1251]	eta 0:33:43 lr 0.000326	time 2.5457 (2.2463)	loss 3.6201 (3.3770)	grad_norm 1.8743 (1.7883)	
[2022-01-23 13:44:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][360/1251]	eta 0:33:25 lr 0.000326	time 1.7783 (2.2506)	loss 3.3773 (3.3745)	grad_norm 1.8605 (1.7889)	
[2022-01-23 13:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][370/1251]	eta 0:33:04 lr 0.000326	time 1.9085 (2.2520)	loss 3.1181 (3.3773)	grad_norm 1.9410 (1.7896)	
[2022-01-23 13:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][380/1251]	eta 0:32:37 lr 0.000326	time 1.8561 (2.2475)	loss 4.0611 (3.3825)	grad_norm 1.6528 (1.7882)	
[2022-01-23 13:45:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][390/1251]	eta 0:32:09 lr 0.000326	time 1.8338 (2.2415)	loss 3.5520 (3.3801)	grad_norm 1.6645 (1.7878)	
[2022-01-23 13:45:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][400/1251]	eta 0:31:43 lr 0.000326	time 2.3039 (2.2369)	loss 3.6143 (3.3856)	grad_norm 1.9499 (1.7899)	
[2022-01-23 13:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][410/1251]	eta 0:31:15 lr 0.000326	time 1.6400 (2.2296)	loss 2.6479 (3.3843)	grad_norm 1.9513 (1.7883)	
[2022-01-23 13:46:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][420/1251]	eta 0:30:51 lr 0.000326	time 1.9355 (2.2275)	loss 2.6873 (3.3795)	grad_norm 1.8927 (1.7867)	
[2022-01-23 13:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][430/1251]	eta 0:30:27 lr 0.000326	time 1.8875 (2.2265)	loss 3.9039 (3.3751)	grad_norm 1.9238 (1.7883)	
[2022-01-23 13:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][440/1251]	eta 0:30:06 lr 0.000326	time 2.7450 (2.2274)	loss 3.7412 (3.3763)	grad_norm 1.7728 (1.7904)	
[2022-01-23 13:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][450/1251]	eta 0:29:45 lr 0.000326	time 3.1064 (2.2287)	loss 3.2824 (3.3810)	grad_norm 1.7128 (1.7882)	
[2022-01-23 13:47:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][460/1251]	eta 0:29:20 lr 0.000326	time 1.4629 (2.2253)	loss 3.9763 (3.3799)	grad_norm 1.6620 (1.7866)	
[2022-01-23 13:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][470/1251]	eta 0:28:58 lr 0.000326	time 2.1775 (2.2254)	loss 3.5929 (3.3847)	grad_norm 2.1134 (1.7848)	
[2022-01-23 13:48:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][480/1251]	eta 0:28:34 lr 0.000326	time 2.8499 (2.2233)	loss 3.9606 (3.3847)	grad_norm 1.6865 (1.7845)	
[2022-01-23 13:48:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][490/1251]	eta 0:28:13 lr 0.000326	time 2.1424 (2.2255)	loss 3.6676 (3.3833)	grad_norm 1.8393 (1.7826)	
[2022-01-23 13:49:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][500/1251]	eta 0:27:51 lr 0.000326	time 1.8958 (2.2259)	loss 3.3374 (3.3832)	grad_norm 1.4998 (1.7817)	
[2022-01-23 13:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][510/1251]	eta 0:27:30 lr 0.000326	time 1.7874 (2.2271)	loss 4.0985 (3.3833)	grad_norm 1.7644 (1.7808)	
[2022-01-23 13:50:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][520/1251]	eta 0:27:07 lr 0.000326	time 2.8118 (2.2259)	loss 3.6243 (3.3790)	grad_norm 1.7448 (1.7813)	
[2022-01-23 13:50:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][530/1251]	eta 0:26:44 lr 0.000326	time 1.5702 (2.2252)	loss 4.1722 (3.3811)	grad_norm 1.7655 (1.7809)	
[2022-01-23 13:50:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][540/1251]	eta 0:26:21 lr 0.000326	time 1.7044 (2.2236)	loss 3.7138 (3.3829)	grad_norm 1.5246 (1.7801)	
[2022-01-23 13:51:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][550/1251]	eta 0:25:57 lr 0.000325	time 1.9603 (2.2221)	loss 2.8745 (3.3838)	grad_norm 1.7362 (1.7802)	
[2022-01-23 13:51:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][560/1251]	eta 0:25:35 lr 0.000325	time 2.9677 (2.2227)	loss 3.5592 (3.3847)	grad_norm 1.5531 (1.7823)	
[2022-01-23 13:51:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][570/1251]	eta 0:25:13 lr 0.000325	time 1.8942 (2.2232)	loss 3.0678 (3.3856)	grad_norm 1.8500 (1.7824)	
[2022-01-23 13:52:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][580/1251]	eta 0:24:50 lr 0.000325	time 1.8842 (2.2210)	loss 3.3053 (3.3852)	grad_norm 1.7889 (1.7827)	
[2022-01-23 13:52:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][590/1251]	eta 0:24:27 lr 0.000325	time 1.8137 (2.2205)	loss 2.3455 (3.3867)	grad_norm 2.2330 (1.7839)	
[2022-01-23 13:52:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][600/1251]	eta 0:24:05 lr 0.000325	time 2.4225 (2.2197)	loss 3.5784 (3.3919)	grad_norm 2.1442 (1.7867)	
[2022-01-23 13:53:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][610/1251]	eta 0:23:41 lr 0.000325	time 1.9143 (2.2179)	loss 3.6328 (3.3908)	grad_norm 1.6407 (1.7891)	
[2022-01-23 13:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][620/1251]	eta 0:23:18 lr 0.000325	time 2.2100 (2.2166)	loss 3.1238 (3.3886)	grad_norm 1.8820 (1.7894)	
[2022-01-23 13:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][630/1251]	eta 0:22:55 lr 0.000325	time 1.9466 (2.2151)	loss 3.2157 (3.3875)	grad_norm 1.8953 (1.7892)	
[2022-01-23 13:54:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][640/1251]	eta 0:22:33 lr 0.000325	time 2.6063 (2.2155)	loss 3.6360 (3.3892)	grad_norm 1.6671 (1.7903)	
[2022-01-23 13:54:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][650/1251]	eta 0:22:10 lr 0.000325	time 1.8438 (2.2139)	loss 3.6370 (3.3920)	grad_norm 1.6371 (1.7895)	
[2022-01-23 13:55:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][660/1251]	eta 0:21:48 lr 0.000325	time 2.2687 (2.2137)	loss 3.6324 (3.3931)	grad_norm 1.6887 (1.7905)	
[2022-01-23 13:55:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][670/1251]	eta 0:21:25 lr 0.000325	time 1.8438 (2.2123)	loss 3.7605 (3.3951)	grad_norm 1.5802 (1.7916)	
[2022-01-23 13:55:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][680/1251]	eta 0:21:03 lr 0.000325	time 1.7951 (2.2128)	loss 3.7401 (3.3968)	grad_norm 1.5283 (1.7917)	
[2022-01-23 13:56:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][690/1251]	eta 0:20:41 lr 0.000325	time 1.8493 (2.2123)	loss 2.7873 (3.3993)	grad_norm 1.7719 (1.7907)	
[2022-01-23 13:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][700/1251]	eta 0:20:19 lr 0.000325	time 2.2527 (2.2124)	loss 3.5082 (3.4027)	grad_norm 1.5822 (1.7898)	
[2022-01-23 13:56:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][710/1251]	eta 0:19:56 lr 0.000325	time 2.2718 (2.2116)	loss 4.2545 (3.4050)	grad_norm 1.6560 (1.7897)	
[2022-01-23 13:57:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][720/1251]	eta 0:19:33 lr 0.000325	time 2.0704 (2.2099)	loss 2.6782 (3.4028)	grad_norm 1.7653 (1.7897)	
[2022-01-23 13:57:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][730/1251]	eta 0:19:12 lr 0.000325	time 2.2037 (2.2114)	loss 3.7287 (3.4030)	grad_norm 1.6316 (1.7874)	
[2022-01-23 13:58:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][740/1251]	eta 0:18:50 lr 0.000325	time 2.1741 (2.2120)	loss 3.3217 (3.4026)	grad_norm 1.6887 (1.7888)	
[2022-01-23 13:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][750/1251]	eta 0:18:28 lr 0.000325	time 2.4640 (2.2118)	loss 4.2489 (3.4014)	grad_norm 2.0542 (1.7911)	
[2022-01-23 13:58:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][760/1251]	eta 0:18:06 lr 0.000325	time 2.1541 (2.2122)	loss 3.3328 (3.4024)	grad_norm 2.0852 (1.7921)	
[2022-01-23 13:59:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][770/1251]	eta 0:17:44 lr 0.000325	time 1.7189 (2.2126)	loss 3.6176 (3.4042)	grad_norm 1.7392 (1.7926)	
[2022-01-23 13:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][780/1251]	eta 0:17:21 lr 0.000325	time 1.9970 (2.2112)	loss 2.8616 (3.4052)	grad_norm 1.7627 (1.7924)	
[2022-01-23 13:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][790/1251]	eta 0:16:59 lr 0.000325	time 2.3690 (2.2110)	loss 3.7733 (3.4062)	grad_norm 1.8978 (1.7933)	
[2022-01-23 14:00:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][800/1251]	eta 0:16:36 lr 0.000325	time 2.5830 (2.2106)	loss 3.4443 (3.4080)	grad_norm 1.5448 (1.7930)	
[2022-01-23 14:00:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][810/1251]	eta 0:16:14 lr 0.000324	time 1.6062 (2.2088)	loss 3.6607 (3.4055)	grad_norm 1.8554 (1.7936)	
[2022-01-23 14:00:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][820/1251]	eta 0:15:50 lr 0.000324	time 2.1789 (2.2064)	loss 3.9805 (3.4081)	grad_norm 1.9664 (1.7941)	
[2022-01-23 14:01:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][830/1251]	eta 0:15:28 lr 0.000324	time 2.0644 (2.2049)	loss 2.6788 (3.4076)	grad_norm 1.8872 (1.7944)	
[2022-01-23 14:01:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][840/1251]	eta 0:15:06 lr 0.000324	time 2.1004 (2.2046)	loss 3.9009 (3.4092)	grad_norm 1.6874 (1.7941)	
[2022-01-23 14:01:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][850/1251]	eta 0:14:43 lr 0.000324	time 2.2342 (2.2041)	loss 3.5608 (3.4106)	grad_norm 1.5490 (1.7929)	
[2022-01-23 14:02:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][860/1251]	eta 0:14:21 lr 0.000324	time 3.3297 (2.2031)	loss 3.3132 (3.4095)	grad_norm 1.7787 (1.7928)	
[2022-01-23 14:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][870/1251]	eta 0:13:58 lr 0.000324	time 1.4251 (2.2016)	loss 3.0793 (3.4103)	grad_norm 1.5428 (1.7926)	
[2022-01-23 14:03:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][880/1251]	eta 0:13:36 lr 0.000324	time 1.8916 (2.2015)	loss 3.7430 (3.4070)	grad_norm 1.7801 (1.7924)	
[2022-01-23 14:03:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][890/1251]	eta 0:13:14 lr 0.000324	time 1.6281 (2.2009)	loss 4.1882 (3.4059)	grad_norm 1.5712 (1.7914)	
[2022-01-23 14:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][900/1251]	eta 0:12:53 lr 0.000324	time 2.5994 (2.2031)	loss 3.1697 (3.4053)	grad_norm 1.6814 (1.7909)	
[2022-01-23 14:04:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][910/1251]	eta 0:12:31 lr 0.000324	time 1.6484 (2.2027)	loss 3.7575 (3.4065)	grad_norm 1.7737 (1.7897)	
[2022-01-23 14:04:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][920/1251]	eta 0:12:08 lr 0.000324	time 1.8333 (2.2023)	loss 2.6389 (3.4031)	grad_norm 1.6160 (1.7891)	
[2022-01-23 14:04:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][930/1251]	eta 0:11:46 lr 0.000324	time 1.8484 (2.2016)	loss 3.7802 (3.4061)	grad_norm 1.7670 (1.7881)	
[2022-01-23 14:05:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][940/1251]	eta 0:11:25 lr 0.000324	time 2.8793 (2.2028)	loss 3.4261 (3.4054)	grad_norm 2.1517 (1.7897)	
[2022-01-23 14:05:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][950/1251]	eta 0:11:02 lr 0.000324	time 2.1869 (2.2026)	loss 3.2748 (3.4046)	grad_norm 1.8037 (1.7898)	
[2022-01-23 14:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][960/1251]	eta 0:10:40 lr 0.000324	time 1.6747 (2.2011)	loss 3.9063 (3.4050)	grad_norm 1.7224 (1.7896)	
[2022-01-23 14:06:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][970/1251]	eta 0:10:18 lr 0.000324	time 1.8769 (2.2005)	loss 3.9463 (3.4041)	grad_norm 1.7150 (1.7890)	
[2022-01-23 14:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][980/1251]	eta 0:09:56 lr 0.000324	time 2.7978 (2.2014)	loss 3.9510 (3.4063)	grad_norm 1.5908 (1.7893)	
[2022-01-23 14:07:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][990/1251]	eta 0:09:35 lr 0.000324	time 2.1943 (2.2035)	loss 3.7162 (3.4094)	grad_norm 1.7190 (1.7894)	
[2022-01-23 14:07:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1000/1251]	eta 0:09:13 lr 0.000324	time 2.3557 (2.2048)	loss 3.4163 (3.4087)	grad_norm 1.7569 (1.7897)	
[2022-01-23 14:07:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1010/1251]	eta 0:08:51 lr 0.000324	time 2.1211 (2.2050)	loss 4.0436 (3.4104)	grad_norm 1.7486 (1.7896)	
[2022-01-23 14:08:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1020/1251]	eta 0:08:28 lr 0.000324	time 2.2962 (2.2032)	loss 3.2704 (3.4091)	grad_norm 1.8213 (1.7888)	
[2022-01-23 14:08:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1030/1251]	eta 0:08:06 lr 0.000324	time 1.6380 (2.1998)	loss 3.7732 (3.4054)	grad_norm 2.1268 (1.7883)	
[2022-01-23 14:08:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1040/1251]	eta 0:07:43 lr 0.000324	time 2.3048 (2.1982)	loss 3.0589 (3.4067)	grad_norm 2.1489 (1.7887)	
[2022-01-23 14:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1050/1251]	eta 0:07:21 lr 0.000324	time 1.8341 (2.1977)	loss 3.6988 (3.4093)	grad_norm 2.1786 (1.7891)	
[2022-01-23 14:09:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1060/1251]	eta 0:06:59 lr 0.000324	time 2.3439 (2.1990)	loss 4.0762 (3.4104)	grad_norm 1.7109 (1.7884)	
[2022-01-23 14:09:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1070/1251]	eta 0:06:38 lr 0.000323	time 1.8990 (2.1997)	loss 3.6128 (3.4095)	grad_norm 1.9125 (1.7880)	
[2022-01-23 14:10:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1080/1251]	eta 0:06:16 lr 0.000323	time 2.5424 (2.2013)	loss 2.8845 (3.4103)	grad_norm 2.1912 (1.7883)	
[2022-01-23 14:10:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1090/1251]	eta 0:05:54 lr 0.000323	time 1.9866 (2.2014)	loss 4.1019 (3.4090)	grad_norm 1.6973 (1.7878)	
[2022-01-23 14:11:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1100/1251]	eta 0:05:32 lr 0.000323	time 1.9024 (2.2018)	loss 2.3036 (3.4078)	grad_norm 1.6144 (1.7878)	
[2022-01-23 14:11:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1110/1251]	eta 0:05:10 lr 0.000323	time 3.1823 (2.2022)	loss 4.2723 (3.4070)	grad_norm 2.1778 (1.7884)	
[2022-01-23 14:11:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1120/1251]	eta 0:04:48 lr 0.000323	time 1.8629 (2.2015)	loss 3.8387 (3.4094)	grad_norm 1.7165 (1.7884)	
[2022-01-23 14:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1130/1251]	eta 0:04:26 lr 0.000323	time 1.8722 (2.1997)	loss 3.9838 (3.4099)	grad_norm 1.7103 (1.7886)	
[2022-01-23 14:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1140/1251]	eta 0:04:04 lr 0.000323	time 2.2390 (2.1987)	loss 3.8121 (3.4087)	grad_norm 1.9679 (1.7885)	
[2022-01-23 14:12:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1150/1251]	eta 0:03:41 lr 0.000323	time 2.1868 (2.1978)	loss 2.8096 (3.4062)	grad_norm 1.6494 (1.7878)	
[2022-01-23 14:13:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1160/1251]	eta 0:03:19 lr 0.000323	time 2.5358 (2.1967)	loss 4.0140 (3.4074)	grad_norm 1.6850 (1.7875)	
[2022-01-23 14:13:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1170/1251]	eta 0:02:57 lr 0.000323	time 2.6285 (2.1974)	loss 3.6772 (3.4094)	grad_norm 1.7197 (1.7875)	
[2022-01-23 14:13:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1180/1251]	eta 0:02:35 lr 0.000323	time 1.8927 (2.1971)	loss 3.3961 (3.4104)	grad_norm 1.5995 (1.7870)	
[2022-01-23 14:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1190/1251]	eta 0:02:14 lr 0.000323	time 2.2501 (2.1973)	loss 2.8611 (3.4094)	grad_norm 1.6184 (1.7868)	
[2022-01-23 14:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1200/1251]	eta 0:01:52 lr 0.000323	time 2.7665 (2.1980)	loss 3.7019 (3.4090)	grad_norm 1.5110 (1.7858)	
[2022-01-23 14:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1210/1251]	eta 0:01:30 lr 0.000323	time 2.6454 (2.1997)	loss 3.8509 (3.4121)	grad_norm 1.7958 (1.7850)	
[2022-01-23 14:15:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1220/1251]	eta 0:01:08 lr 0.000323	time 2.7986 (2.2001)	loss 2.9823 (3.4131)	grad_norm 1.6784 (1.7849)	
[2022-01-23 14:15:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1230/1251]	eta 0:00:46 lr 0.000323	time 2.3277 (2.2001)	loss 3.5078 (3.4138)	grad_norm 1.5254 (1.7853)	
[2022-01-23 14:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1240/1251]	eta 0:00:24 lr 0.000323	time 1.2430 (2.1976)	loss 3.2180 (3.4127)	grad_norm 1.6532 (1.7854)	
[2022-01-23 14:16:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [185/300][1250/1251]	eta 0:00:02 lr 0.000323	time 1.2336 (2.1913)	loss 3.4395 (3.4115)	grad_norm 1.7094 (1.7852)	
[2022-01-23 14:16:23 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 185 training takes 0:45:41
[2022-01-23 14:16:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.027 (19.027)	Loss 0.9558 (0.9558)	Acc@1 76.465 (76.465)	Acc@5 93.555 (93.555)	
[2022-01-23 14:17:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.884 (3.566)	Loss 0.9275 (0.9609)	Acc@1 78.125 (77.024)	Acc@5 94.336 (93.661)	
[2022-01-23 14:17:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.951 (2.717)	Loss 0.9120 (0.9465)	Acc@1 78.711 (77.348)	Acc@5 94.727 (93.848)	
[2022-01-23 14:17:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.645 (2.340)	Loss 0.8797 (0.9354)	Acc@1 80.176 (77.520)	Acc@5 95.020 (93.993)	
[2022-01-23 14:17:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.943 (2.214)	Loss 0.9533 (0.9392)	Acc@1 76.270 (77.496)	Acc@5 94.727 (93.995)	
[2022-01-23 14:18:01 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.504 Acc@5 94.028
[2022-01-23 14:18:01 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.5%
[2022-01-23 14:18:01 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.56%
[2022-01-23 14:18:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][0/1251]	eta 7:21:23 lr 0.000323	time 21.1701 (21.1701)	loss 2.5238 (2.5238)	grad_norm 1.5406 (1.5406)	
[2022-01-23 14:18:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][10/1251]	eta 1:21:54 lr 0.000323	time 1.8690 (3.9600)	loss 4.0860 (3.4880)	grad_norm 1.5569 (1.8077)	
[2022-01-23 14:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][20/1251]	eta 1:04:42 lr 0.000323	time 2.1515 (3.1535)	loss 3.9596 (3.4621)	grad_norm 1.8184 (1.7715)	
[2022-01-23 14:19:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][30/1251]	eta 0:57:11 lr 0.000323	time 1.8425 (2.8101)	loss 3.6670 (3.3609)	grad_norm 2.0103 (1.7729)	
[2022-01-23 14:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][40/1251]	eta 0:54:14 lr 0.000323	time 3.6398 (2.6873)	loss 2.8658 (3.3385)	grad_norm 1.6090 (1.7675)	
[2022-01-23 14:20:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][50/1251]	eta 0:52:50 lr 0.000323	time 3.0173 (2.6402)	loss 2.4219 (3.3103)	grad_norm 1.4853 (1.7621)	
[2022-01-23 14:20:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][60/1251]	eta 0:51:12 lr 0.000323	time 2.1785 (2.5796)	loss 3.5420 (3.3520)	grad_norm 2.1175 (1.7570)	
[2022-01-23 14:21:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][70/1251]	eta 0:49:47 lr 0.000323	time 1.8109 (2.5299)	loss 3.9510 (3.4022)	grad_norm 1.8129 (1.7891)	
[2022-01-23 14:21:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][80/1251]	eta 0:48:45 lr 0.000322	time 2.3419 (2.4987)	loss 2.4266 (3.3876)	grad_norm 1.7720 (1.7973)	
[2022-01-23 14:21:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][90/1251]	eta 0:47:39 lr 0.000322	time 1.8834 (2.4629)	loss 4.0756 (3.3958)	grad_norm 1.9165 (1.7935)	
[2022-01-23 14:22:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][100/1251]	eta 0:46:21 lr 0.000322	time 1.8717 (2.4163)	loss 2.3371 (3.4008)	grad_norm 1.7049 (1.7895)	
[2022-01-23 14:22:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][110/1251]	eta 0:45:23 lr 0.000322	time 2.0405 (2.3873)	loss 2.7816 (3.4129)	grad_norm 1.7146 (1.8021)	
[2022-01-23 14:22:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][120/1251]	eta 0:44:59 lr 0.000322	time 2.5200 (2.3865)	loss 4.1608 (3.4189)	grad_norm 2.7496 (1.8144)	
[2022-01-23 14:23:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][130/1251]	eta 0:44:25 lr 0.000322	time 1.5542 (2.3780)	loss 3.3584 (3.4193)	grad_norm 1.6251 (1.8122)	
[2022-01-23 14:23:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][140/1251]	eta 0:43:46 lr 0.000322	time 1.8685 (2.3641)	loss 2.5464 (3.4075)	grad_norm 1.8375 (1.8159)	
[2022-01-23 14:23:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][150/1251]	eta 0:43:07 lr 0.000322	time 2.1364 (2.3503)	loss 4.0018 (3.4148)	grad_norm 1.8776 (1.8221)	
[2022-01-23 14:24:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][160/1251]	eta 0:42:24 lr 0.000322	time 1.7406 (2.3327)	loss 3.4156 (3.4136)	grad_norm 1.8449 (1.8230)	
[2022-01-23 14:24:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][170/1251]	eta 0:41:50 lr 0.000322	time 1.7323 (2.3228)	loss 3.7230 (3.4031)	grad_norm 1.6408 (1.8186)	
[2022-01-23 14:25:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][180/1251]	eta 0:41:19 lr 0.000322	time 1.9684 (2.3154)	loss 3.0416 (3.4084)	grad_norm 1.7415 (1.8125)	
[2022-01-23 14:25:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][190/1251]	eta 0:40:50 lr 0.000322	time 1.6111 (2.3098)	loss 3.9639 (3.3988)	grad_norm 1.7656 (1.8141)	
[2022-01-23 14:25:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][200/1251]	eta 0:40:17 lr 0.000322	time 1.7458 (2.3006)	loss 3.1135 (3.3873)	grad_norm 1.6723 (1.8143)	
[2022-01-23 14:26:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][210/1251]	eta 0:39:42 lr 0.000322	time 1.5653 (2.2890)	loss 3.5146 (3.3856)	grad_norm 1.7205 (1.8174)	
[2022-01-23 14:26:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][220/1251]	eta 0:39:16 lr 0.000322	time 2.5182 (2.2860)	loss 2.6397 (3.3806)	grad_norm 1.9900 (1.8195)	
[2022-01-23 14:26:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][230/1251]	eta 0:38:59 lr 0.000322	time 2.5590 (2.2910)	loss 3.3223 (3.3870)	grad_norm 1.8508 (1.8210)	
[2022-01-23 14:27:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][240/1251]	eta 0:38:34 lr 0.000322	time 2.2067 (2.2896)	loss 3.3992 (3.3788)	grad_norm 1.5266 (1.8219)	
[2022-01-23 14:27:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][250/1251]	eta 0:37:59 lr 0.000322	time 1.5918 (2.2777)	loss 3.8521 (3.3925)	grad_norm 1.9682 (1.8231)	
[2022-01-23 14:27:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][260/1251]	eta 0:37:27 lr 0.000322	time 1.7669 (2.2675)	loss 3.6259 (3.3979)	grad_norm 1.7715 (1.8215)	
[2022-01-23 14:28:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][270/1251]	eta 0:36:54 lr 0.000322	time 1.9397 (2.2576)	loss 3.0650 (3.3844)	grad_norm 1.6833 (1.8191)	
[2022-01-23 14:28:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][280/1251]	eta 0:36:29 lr 0.000322	time 2.6449 (2.2551)	loss 3.9610 (3.3875)	grad_norm 1.6613 (1.8157)	
[2022-01-23 14:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][290/1251]	eta 0:36:11 lr 0.000322	time 2.6868 (2.2593)	loss 3.5969 (3.3861)	grad_norm 1.9880 (1.8164)	
[2022-01-23 14:29:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][300/1251]	eta 0:35:43 lr 0.000322	time 1.9745 (2.2539)	loss 3.6549 (3.3854)	grad_norm 1.5374 (1.8163)	
[2022-01-23 14:29:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][310/1251]	eta 0:35:18 lr 0.000322	time 2.3696 (2.2513)	loss 3.7216 (3.3901)	grad_norm 1.7909 (1.8147)	
[2022-01-23 14:30:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][320/1251]	eta 0:34:58 lr 0.000322	time 2.9260 (2.2543)	loss 3.6344 (3.3977)	grad_norm 1.6097 (1.8114)	
[2022-01-23 14:30:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][330/1251]	eta 0:34:37 lr 0.000322	time 2.4424 (2.2559)	loss 4.0438 (3.4018)	grad_norm 1.6374 (1.8097)	
[2022-01-23 14:30:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][340/1251]	eta 0:34:13 lr 0.000321	time 2.3084 (2.2540)	loss 3.4997 (3.3977)	grad_norm 1.8066 (1.8090)	
[2022-01-23 14:31:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][350/1251]	eta 0:33:48 lr 0.000321	time 2.2034 (2.2511)	loss 3.4167 (3.4005)	grad_norm 1.6757 (1.8077)	
[2022-01-23 14:31:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][360/1251]	eta 0:33:17 lr 0.000321	time 1.9371 (2.2421)	loss 3.2069 (3.4020)	grad_norm 1.7202 (1.8038)	
[2022-01-23 14:31:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][370/1251]	eta 0:32:52 lr 0.000321	time 2.5489 (2.2392)	loss 3.4520 (3.4024)	grad_norm 1.9174 (1.8041)	
[2022-01-23 14:32:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][380/1251]	eta 0:32:27 lr 0.000321	time 1.9850 (2.2360)	loss 3.4470 (3.4073)	grad_norm 1.6539 (1.8049)	
[2022-01-23 14:32:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][390/1251]	eta 0:32:06 lr 0.000321	time 2.1301 (2.2371)	loss 3.5498 (3.4069)	grad_norm 3.6472 (1.8180)	
[2022-01-23 14:32:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][400/1251]	eta 0:31:43 lr 0.000321	time 2.4405 (2.2363)	loss 3.6896 (3.4002)	grad_norm 1.8699 (1.8226)	
[2022-01-23 14:33:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][410/1251]	eta 0:31:18 lr 0.000321	time 1.9892 (2.2337)	loss 3.3029 (3.3967)	grad_norm 1.8325 (1.8234)	
[2022-01-23 14:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][420/1251]	eta 0:30:54 lr 0.000321	time 1.9182 (2.2311)	loss 3.6635 (3.3969)	grad_norm 1.8297 (1.8231)	
[2022-01-23 14:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][430/1251]	eta 0:30:27 lr 0.000321	time 1.6635 (2.2254)	loss 4.0492 (3.3961)	grad_norm 2.0402 (1.8221)	
[2022-01-23 14:34:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][440/1251]	eta 0:30:02 lr 0.000321	time 1.6297 (2.2222)	loss 3.0189 (3.3967)	grad_norm 1.7912 (1.8219)	
[2022-01-23 14:34:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][450/1251]	eta 0:29:41 lr 0.000321	time 2.6134 (2.2244)	loss 3.8758 (3.3993)	grad_norm 1.9420 (1.8192)	
[2022-01-23 14:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][460/1251]	eta 0:29:19 lr 0.000321	time 2.0231 (2.2249)	loss 3.5337 (3.3971)	grad_norm 1.8206 (1.8186)	
[2022-01-23 14:35:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][470/1251]	eta 0:28:56 lr 0.000321	time 2.2933 (2.2240)	loss 3.4830 (3.3933)	grad_norm 1.6713 (1.8171)	
[2022-01-23 14:35:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][480/1251]	eta 0:28:35 lr 0.000321	time 1.5762 (2.2255)	loss 3.8822 (3.3935)	grad_norm 1.6709 (1.8153)	
[2022-01-23 14:36:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][490/1251]	eta 0:28:14 lr 0.000321	time 2.9041 (2.2272)	loss 3.5866 (3.3897)	grad_norm 1.7636 (1.8167)	
[2022-01-23 14:36:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][500/1251]	eta 0:27:50 lr 0.000321	time 1.8561 (2.2240)	loss 2.8375 (3.3860)	grad_norm 1.5768 (1.8149)	
[2022-01-23 14:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][510/1251]	eta 0:27:26 lr 0.000321	time 2.6873 (2.2222)	loss 3.2772 (3.3889)	grad_norm 1.9691 (1.8127)	
[2022-01-23 14:37:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][520/1251]	eta 0:27:03 lr 0.000321	time 1.8501 (2.2214)	loss 2.8148 (3.3821)	grad_norm 1.6915 (1.8115)	
[2022-01-23 14:37:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][530/1251]	eta 0:26:40 lr 0.000321	time 1.9099 (2.2192)	loss 3.8283 (3.3881)	grad_norm 1.8875 (1.8144)	
[2022-01-23 14:38:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][540/1251]	eta 0:26:15 lr 0.000321	time 2.4792 (2.2165)	loss 2.8280 (3.3861)	grad_norm 1.5403 (1.8140)	
[2022-01-23 14:38:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][550/1251]	eta 0:25:53 lr 0.000321	time 1.9255 (2.2157)	loss 2.8270 (3.3881)	grad_norm 1.6466 (1.8121)	
[2022-01-23 14:38:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][560/1251]	eta 0:25:34 lr 0.000321	time 2.3166 (2.2211)	loss 3.6643 (3.3801)	grad_norm 1.7955 (1.8115)	
[2022-01-23 14:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][570/1251]	eta 0:25:12 lr 0.000321	time 2.1911 (2.2216)	loss 3.8492 (3.3820)	grad_norm 2.0166 (1.8132)	
[2022-01-23 14:39:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][580/1251]	eta 0:24:51 lr 0.000321	time 2.6890 (2.2225)	loss 3.5901 (3.3844)	grad_norm 1.9789 (1.8136)	
[2022-01-23 14:39:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][590/1251]	eta 0:24:28 lr 0.000321	time 2.2046 (2.2216)	loss 3.7544 (3.3822)	grad_norm 1.8263 (1.8138)	
[2022-01-23 14:40:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][600/1251]	eta 0:24:05 lr 0.000320	time 2.2043 (2.2203)	loss 3.7622 (3.3855)	grad_norm 1.4357 (1.8118)	
[2022-01-23 14:40:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][610/1251]	eta 0:23:41 lr 0.000320	time 1.6818 (2.2174)	loss 3.7280 (3.3804)	grad_norm 1.9298 (1.8110)	
[2022-01-23 14:40:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][620/1251]	eta 0:23:18 lr 0.000320	time 2.3577 (2.2165)	loss 3.8526 (3.3790)	grad_norm 1.7533 (1.8108)	
[2022-01-23 14:41:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][630/1251]	eta 0:22:55 lr 0.000320	time 1.8904 (2.2143)	loss 3.5206 (3.3777)	grad_norm 1.6894 (1.8109)	
[2022-01-23 14:41:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][640/1251]	eta 0:22:33 lr 0.000320	time 2.8038 (2.2159)	loss 3.8882 (3.3767)	grad_norm 1.7405 (1.8099)	
[2022-01-23 14:42:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][650/1251]	eta 0:22:10 lr 0.000320	time 1.7620 (2.2135)	loss 2.3236 (3.3740)	grad_norm 1.7625 (1.8092)	
[2022-01-23 14:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][660/1251]	eta 0:21:47 lr 0.000320	time 2.2089 (2.2130)	loss 3.5687 (3.3743)	grad_norm 1.6896 (1.8085)	
[2022-01-23 14:42:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][670/1251]	eta 0:21:26 lr 0.000320	time 2.4031 (2.2137)	loss 3.7611 (3.3762)	grad_norm 1.8329 (1.8071)	
[2022-01-23 14:43:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][680/1251]	eta 0:21:04 lr 0.000320	time 3.0462 (2.2152)	loss 3.9917 (3.3794)	grad_norm 1.7001 (1.8062)	
[2022-01-23 14:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][690/1251]	eta 0:20:42 lr 0.000320	time 1.4936 (2.2148)	loss 3.3735 (3.3829)	grad_norm 1.9760 (1.8057)	
[2022-01-23 14:43:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][700/1251]	eta 0:20:18 lr 0.000320	time 1.8869 (2.2115)	loss 3.8443 (3.3844)	grad_norm 2.1784 (1.8075)	
[2022-01-23 14:44:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][710/1251]	eta 0:19:57 lr 0.000320	time 2.4806 (2.2136)	loss 3.8402 (3.3862)	grad_norm 2.0177 (1.8090)	
[2022-01-23 14:44:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][720/1251]	eta 0:19:35 lr 0.000320	time 2.1832 (2.2129)	loss 3.4267 (3.3853)	grad_norm 1.7949 (1.8080)	
[2022-01-23 14:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][730/1251]	eta 0:19:12 lr 0.000320	time 1.8614 (2.2114)	loss 3.8296 (3.3887)	grad_norm 1.8055 (1.8071)	
[2022-01-23 14:45:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][740/1251]	eta 0:18:49 lr 0.000320	time 2.5650 (2.2106)	loss 4.0545 (3.3901)	grad_norm 1.6463 (1.8063)	
[2022-01-23 14:45:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][750/1251]	eta 0:18:27 lr 0.000320	time 2.1662 (2.2096)	loss 3.6135 (3.3889)	grad_norm 1.6157 (1.8061)	
[2022-01-23 14:46:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][760/1251]	eta 0:18:05 lr 0.000320	time 3.0905 (2.2112)	loss 3.2681 (3.3906)	grad_norm 1.8941 (1.8051)	
[2022-01-23 14:46:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][770/1251]	eta 0:17:43 lr 0.000320	time 1.5924 (2.2100)	loss 2.6846 (3.3895)	grad_norm 1.8453 (1.8046)	
[2022-01-23 14:46:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][780/1251]	eta 0:17:20 lr 0.000320	time 2.9340 (2.2098)	loss 2.7750 (3.3891)	grad_norm 1.6748 (1.8049)	
[2022-01-23 14:47:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][790/1251]	eta 0:16:58 lr 0.000320	time 2.4929 (2.2089)	loss 3.9700 (3.3903)	grad_norm 1.6644 (1.8049)	
[2022-01-23 14:47:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][800/1251]	eta 0:16:36 lr 0.000320	time 2.2060 (2.2088)	loss 3.9899 (3.3912)	grad_norm 1.6064 (1.8045)	
[2022-01-23 14:47:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][810/1251]	eta 0:16:13 lr 0.000320	time 2.7476 (2.2081)	loss 2.6105 (3.3889)	grad_norm 2.0190 (1.8054)	
[2022-01-23 14:48:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][820/1251]	eta 0:15:51 lr 0.000320	time 2.1777 (2.2074)	loss 3.9301 (3.3912)	grad_norm 1.7018 (1.8056)	
[2022-01-23 14:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][830/1251]	eta 0:15:29 lr 0.000320	time 1.8610 (2.2073)	loss 3.7717 (3.3918)	grad_norm 1.8088 (1.8046)	
[2022-01-23 14:48:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][840/1251]	eta 0:15:07 lr 0.000320	time 1.8542 (2.2071)	loss 4.0500 (3.3915)	grad_norm 1.9392 (1.8039)	
[2022-01-23 14:49:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][850/1251]	eta 0:14:44 lr 0.000320	time 2.8017 (2.2055)	loss 2.7831 (3.3911)	grad_norm 1.9747 (1.8041)	
[2022-01-23 14:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][860/1251]	eta 0:14:21 lr 0.000319	time 2.9665 (2.2045)	loss 2.9408 (3.3894)	grad_norm 1.6050 (1.8044)	
[2022-01-23 14:49:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][870/1251]	eta 0:13:59 lr 0.000319	time 1.9083 (2.2025)	loss 2.7318 (3.3879)	grad_norm 1.8337 (1.8040)	
[2022-01-23 14:50:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][880/1251]	eta 0:13:37 lr 0.000319	time 2.3256 (2.2026)	loss 3.7982 (3.3888)	grad_norm 1.5991 (1.8046)	
[2022-01-23 14:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][890/1251]	eta 0:13:15 lr 0.000319	time 2.1313 (2.2026)	loss 2.5491 (3.3920)	grad_norm 1.9725 (1.8044)	
[2022-01-23 14:51:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][900/1251]	eta 0:12:53 lr 0.000319	time 2.5886 (2.2043)	loss 3.5227 (3.3923)	grad_norm 2.0882 (1.8049)	
[2022-01-23 14:51:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][910/1251]	eta 0:12:32 lr 0.000319	time 2.4008 (2.2053)	loss 3.1321 (3.3893)	grad_norm 1.6401 (1.8047)	
[2022-01-23 14:51:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][920/1251]	eta 0:12:09 lr 0.000319	time 2.1759 (2.2050)	loss 3.5626 (3.3880)	grad_norm 1.7548 (1.8040)	
[2022-01-23 14:52:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][930/1251]	eta 0:11:48 lr 0.000319	time 2.4919 (2.2058)	loss 2.4300 (3.3862)	grad_norm 1.7373 (1.8039)	
[2022-01-23 14:52:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][940/1251]	eta 0:11:25 lr 0.000319	time 2.4087 (2.2037)	loss 3.2874 (3.3869)	grad_norm 2.0877 (1.8036)	
[2022-01-23 14:52:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][950/1251]	eta 0:11:02 lr 0.000319	time 1.9817 (2.2015)	loss 2.6157 (3.3845)	grad_norm 1.6403 (1.8034)	
[2022-01-23 14:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][960/1251]	eta 0:10:40 lr 0.000319	time 2.8228 (2.2024)	loss 2.9562 (3.3822)	grad_norm 1.8689 (1.8030)	
[2022-01-23 14:53:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][970/1251]	eta 0:10:19 lr 0.000319	time 2.4753 (2.2033)	loss 3.2299 (3.3804)	grad_norm 1.8577 (1.8036)	
[2022-01-23 14:54:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][980/1251]	eta 0:09:56 lr 0.000319	time 1.8860 (2.2026)	loss 4.0517 (3.3834)	grad_norm 1.9286 (1.8043)	
[2022-01-23 14:54:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][990/1251]	eta 0:09:34 lr 0.000319	time 2.2751 (2.2020)	loss 4.2976 (3.3859)	grad_norm 1.7011 (1.8045)	
[2022-01-23 14:54:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1000/1251]	eta 0:09:12 lr 0.000319	time 2.4868 (2.2017)	loss 2.4760 (3.3847)	grad_norm 2.0891 (1.8037)	
[2022-01-23 14:55:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1010/1251]	eta 0:08:50 lr 0.000319	time 2.6779 (2.2013)	loss 2.9474 (3.3831)	grad_norm 1.4866 (1.8032)	
[2022-01-23 14:55:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1020/1251]	eta 0:08:28 lr 0.000319	time 2.1737 (2.2004)	loss 3.3563 (3.3817)	grad_norm 1.8752 (1.8045)	
[2022-01-23 14:55:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1030/1251]	eta 0:08:06 lr 0.000319	time 1.8276 (2.2016)	loss 3.0884 (3.3810)	grad_norm 2.3620 (1.8046)	
[2022-01-23 14:56:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1040/1251]	eta 0:07:44 lr 0.000319	time 1.9758 (2.2025)	loss 3.8506 (3.3806)	grad_norm 1.6436 (1.8031)	
[2022-01-23 14:56:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1050/1251]	eta 0:07:22 lr 0.000319	time 1.9583 (2.2030)	loss 3.5510 (3.3829)	grad_norm 1.7632 (1.8021)	
[2022-01-23 14:56:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1060/1251]	eta 0:07:00 lr 0.000319	time 2.4032 (2.2015)	loss 2.6103 (3.3809)	grad_norm 2.3362 (1.8031)	
[2022-01-23 14:57:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1070/1251]	eta 0:06:38 lr 0.000319	time 1.9071 (2.1992)	loss 3.2419 (3.3811)	grad_norm 1.8968 (1.8020)	
[2022-01-23 14:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1080/1251]	eta 0:06:15 lr 0.000319	time 1.5860 (2.1975)	loss 2.5474 (3.3781)	grad_norm 1.8786 (1.8015)	
[2022-01-23 14:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1090/1251]	eta 0:05:53 lr 0.000319	time 1.9368 (2.1965)	loss 3.4388 (3.3773)	grad_norm 1.6781 (1.8003)	
[2022-01-23 14:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1100/1251]	eta 0:05:31 lr 0.000319	time 2.2045 (2.1966)	loss 3.8396 (3.3785)	grad_norm 1.5465 (1.7991)	
[2022-01-23 14:58:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1110/1251]	eta 0:05:09 lr 0.000319	time 2.5026 (2.1959)	loss 3.2479 (3.3756)	grad_norm 1.7680 (1.7982)	
[2022-01-23 14:59:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1120/1251]	eta 0:04:47 lr 0.000318	time 2.1979 (2.1965)	loss 3.0693 (3.3750)	grad_norm 2.0005 (1.7977)	
[2022-01-23 14:59:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1130/1251]	eta 0:04:25 lr 0.000318	time 2.5400 (2.1975)	loss 2.9948 (3.3749)	grad_norm 1.8039 (1.7973)	
[2022-01-23 14:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1140/1251]	eta 0:04:04 lr 0.000318	time 2.2637 (2.1988)	loss 3.9432 (3.3742)	grad_norm 2.0365 (1.7979)	
[2022-01-23 15:00:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1150/1251]	eta 0:03:42 lr 0.000318	time 2.0690 (2.2011)	loss 3.4593 (3.3755)	grad_norm 1.9998 (1.7986)	
[2022-01-23 15:00:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1160/1251]	eta 0:03:20 lr 0.000318	time 2.7657 (2.2028)	loss 4.1654 (3.3747)	grad_norm 1.7833 (1.8002)	
[2022-01-23 15:01:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1170/1251]	eta 0:02:58 lr 0.000318	time 1.6084 (2.2026)	loss 3.6632 (3.3749)	grad_norm 1.9298 (1.8016)	
[2022-01-23 15:01:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1180/1251]	eta 0:02:36 lr 0.000318	time 1.8985 (2.2003)	loss 3.5788 (3.3767)	grad_norm 2.0182 (1.8029)	
[2022-01-23 15:01:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1190/1251]	eta 0:02:14 lr 0.000318	time 1.8315 (2.1994)	loss 2.6045 (3.3740)	grad_norm 1.7366 (1.8034)	
[2022-01-23 15:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1200/1251]	eta 0:01:52 lr 0.000318	time 2.3851 (2.1987)	loss 3.7057 (3.3744)	grad_norm 1.8193 (1.8037)	
[2022-01-23 15:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1210/1251]	eta 0:01:30 lr 0.000318	time 2.0093 (2.1977)	loss 2.9835 (3.3755)	grad_norm 1.8234 (1.8042)	
[2022-01-23 15:02:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1220/1251]	eta 0:01:08 lr 0.000318	time 2.0901 (2.1975)	loss 2.8752 (3.3756)	grad_norm 1.7394 (1.8035)	
[2022-01-23 15:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1230/1251]	eta 0:00:46 lr 0.000318	time 1.9856 (2.1966)	loss 3.8059 (3.3766)	grad_norm 1.6703 (1.8030)	
[2022-01-23 15:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1240/1251]	eta 0:00:24 lr 0.000318	time 2.1658 (2.1961)	loss 3.5533 (3.3783)	grad_norm 1.6632 (1.8026)	
[2022-01-23 15:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [186/300][1250/1251]	eta 0:00:02 lr 0.000318	time 1.1083 (2.1915)	loss 3.2485 (3.3786)	grad_norm 1.7595 (1.8025)	
[2022-01-23 15:03:43 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 186 training takes 0:45:42
[2022-01-23 15:04:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.090 (18.090)	Loss 0.9099 (0.9099)	Acc@1 78.906 (78.906)	Acc@5 93.262 (93.262)	
[2022-01-23 15:04:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.600 (3.289)	Loss 0.9554 (0.9420)	Acc@1 77.930 (78.072)	Acc@5 94.824 (94.283)	
[2022-01-23 15:04:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.010 (2.497)	Loss 0.9787 (0.9554)	Acc@1 76.855 (77.758)	Acc@5 93.945 (94.113)	
[2022-01-23 15:04:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.577 (2.243)	Loss 0.9929 (0.9656)	Acc@1 75.781 (77.589)	Acc@5 93.750 (93.980)	
[2022-01-23 15:05:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.280 (2.178)	Loss 0.9487 (0.9607)	Acc@1 78.320 (77.653)	Acc@5 93.652 (94.012)	
[2022-01-23 15:05:19 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.760 Acc@5 94.052
[2022-01-23 15:05:19 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.8%
[2022-01-23 15:05:19 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.76%
[2022-01-23 15:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][0/1251]	eta 7:04:36 lr 0.000318	time 20.3646 (20.3646)	loss 3.2221 (3.2221)	grad_norm 2.0229 (2.0229)	
[2022-01-23 15:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][10/1251]	eta 1:19:36 lr 0.000318	time 1.6178 (3.8488)	loss 2.3597 (3.2434)	grad_norm 1.8219 (1.8304)	
[2022-01-23 15:06:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][20/1251]	eta 1:02:09 lr 0.000318	time 1.4879 (3.0298)	loss 3.3838 (3.3864)	grad_norm 1.6653 (1.7939)	
[2022-01-23 15:06:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][30/1251]	eta 0:56:40 lr 0.000318	time 1.7724 (2.7854)	loss 3.6104 (3.4055)	grad_norm 1.8211 (1.7746)	
[2022-01-23 15:07:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][40/1251]	eta 0:53:45 lr 0.000318	time 3.8919 (2.6638)	loss 3.8047 (3.4774)	grad_norm 1.6272 (1.7708)	
[2022-01-23 15:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][50/1251]	eta 0:52:30 lr 0.000318	time 1.5047 (2.6229)	loss 4.0336 (3.4839)	grad_norm 1.7535 (1.7696)	
[2022-01-23 15:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][60/1251]	eta 0:51:12 lr 0.000318	time 1.5739 (2.5798)	loss 3.3324 (3.4547)	grad_norm 1.9610 (1.7842)	
[2022-01-23 15:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][70/1251]	eta 0:49:33 lr 0.000318	time 1.5031 (2.5175)	loss 3.7993 (3.4605)	grad_norm 2.0415 (1.7903)	
[2022-01-23 15:08:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][80/1251]	eta 0:48:24 lr 0.000318	time 2.5238 (2.4806)	loss 3.6122 (3.4294)	grad_norm 3.4070 (1.8145)	
[2022-01-23 15:09:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][90/1251]	eta 0:47:35 lr 0.000318	time 2.2038 (2.4598)	loss 2.3514 (3.4280)	grad_norm 1.9870 (1.8267)	
[2022-01-23 15:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][100/1251]	eta 0:46:38 lr 0.000318	time 1.7342 (2.4316)	loss 3.8258 (3.4110)	grad_norm 1.9722 (1.8302)	
[2022-01-23 15:09:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][110/1251]	eta 0:45:33 lr 0.000318	time 1.8069 (2.3955)	loss 2.4974 (3.3921)	grad_norm 1.8054 (1.8235)	
[2022-01-23 15:10:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][120/1251]	eta 0:44:44 lr 0.000318	time 2.1219 (2.3738)	loss 2.5030 (3.3907)	grad_norm 2.0039 (1.8274)	
[2022-01-23 15:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][130/1251]	eta 0:44:12 lr 0.000317	time 2.4033 (2.3666)	loss 2.8168 (3.4003)	grad_norm 2.0389 (1.8332)	
[2022-01-23 15:10:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][140/1251]	eta 0:43:36 lr 0.000317	time 1.8535 (2.3553)	loss 3.3898 (3.4028)	grad_norm 1.6965 (1.8291)	
[2022-01-23 15:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][150/1251]	eta 0:42:57 lr 0.000317	time 1.8963 (2.3414)	loss 3.6929 (3.3997)	grad_norm 1.6888 (1.8231)	
[2022-01-23 15:11:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][160/1251]	eta 0:42:22 lr 0.000317	time 2.4878 (2.3308)	loss 3.8358 (3.4062)	grad_norm 1.6553 (1.8188)	
[2022-01-23 15:11:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][170/1251]	eta 0:41:47 lr 0.000317	time 2.5126 (2.3197)	loss 3.9717 (3.4207)	grad_norm 1.7556 (1.8145)	
[2022-01-23 15:12:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][180/1251]	eta 0:41:17 lr 0.000317	time 2.1774 (2.3131)	loss 3.2355 (3.4164)	grad_norm 1.6406 (1.8076)	
[2022-01-23 15:12:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][190/1251]	eta 0:41:06 lr 0.000317	time 3.5728 (2.3251)	loss 3.3497 (3.3950)	grad_norm 1.5668 (1.8044)	
[2022-01-23 15:13:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][200/1251]	eta 0:40:43 lr 0.000317	time 1.9092 (2.3245)	loss 4.0045 (3.4058)	grad_norm 1.7943 (1.8033)	
[2022-01-23 15:13:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][210/1251]	eta 0:40:12 lr 0.000317	time 1.8924 (2.3170)	loss 3.1068 (3.4065)	grad_norm 1.7791 (1.8000)	
[2022-01-23 15:13:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][220/1251]	eta 0:39:31 lr 0.000317	time 1.7092 (2.3000)	loss 3.4083 (3.4066)	grad_norm 1.8351 (1.7997)	
[2022-01-23 15:14:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][230/1251]	eta 0:38:57 lr 0.000317	time 2.4725 (2.2891)	loss 3.9540 (3.4119)	grad_norm 1.9236 (1.7991)	
[2022-01-23 15:14:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][240/1251]	eta 0:38:30 lr 0.000317	time 1.8264 (2.2855)	loss 2.7794 (3.4065)	grad_norm 1.8807 (1.8003)	
[2022-01-23 15:14:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][250/1251]	eta 0:38:04 lr 0.000317	time 2.3194 (2.2821)	loss 3.5790 (3.4195)	grad_norm 1.8237 (1.8041)	
[2022-01-23 15:15:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][260/1251]	eta 0:37:38 lr 0.000317	time 2.2134 (2.2791)	loss 3.5119 (3.4180)	grad_norm 1.7873 (1.8056)	
[2022-01-23 15:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][270/1251]	eta 0:37:13 lr 0.000317	time 2.6961 (2.2764)	loss 2.7982 (3.4177)	grad_norm 1.9677 (1.8105)	
[2022-01-23 15:15:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][280/1251]	eta 0:36:47 lr 0.000317	time 1.8671 (2.2732)	loss 3.7574 (3.4106)	grad_norm 1.4671 (1.8092)	
[2022-01-23 15:16:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][290/1251]	eta 0:36:20 lr 0.000317	time 2.3535 (2.2690)	loss 3.7052 (3.4139)	grad_norm 1.6489 (1.8068)	
[2022-01-23 15:16:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][300/1251]	eta 0:35:55 lr 0.000317	time 2.2880 (2.2671)	loss 3.7704 (3.4126)	grad_norm 1.8002 (1.8070)	
[2022-01-23 15:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][310/1251]	eta 0:35:33 lr 0.000317	time 3.6286 (2.2668)	loss 3.9521 (3.4147)	grad_norm 1.8729 (1.8075)	
[2022-01-23 15:17:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][320/1251]	eta 0:35:05 lr 0.000317	time 1.8902 (2.2613)	loss 2.7383 (3.4086)	grad_norm 1.6574 (1.8051)	
[2022-01-23 15:17:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][330/1251]	eta 0:34:39 lr 0.000317	time 2.0104 (2.2584)	loss 3.7757 (3.4127)	grad_norm 1.8998 (1.8040)	
[2022-01-23 15:18:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][340/1251]	eta 0:34:18 lr 0.000317	time 2.0703 (2.2594)	loss 2.7688 (3.4038)	grad_norm 1.8585 (1.8054)	
[2022-01-23 15:18:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][350/1251]	eta 0:33:55 lr 0.000317	time 3.0372 (2.2593)	loss 2.2782 (3.3943)	grad_norm 1.9493 (1.8064)	
[2022-01-23 15:18:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][360/1251]	eta 0:33:26 lr 0.000317	time 1.6308 (2.2516)	loss 3.4741 (3.3919)	grad_norm 2.0789 (1.8092)	
[2022-01-23 15:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][370/1251]	eta 0:32:56 lr 0.000317	time 1.7101 (2.2439)	loss 3.5539 (3.3838)	grad_norm 2.0151 (1.8103)	
[2022-01-23 15:19:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][380/1251]	eta 0:32:28 lr 0.000317	time 2.0468 (2.2374)	loss 3.9952 (3.3842)	grad_norm 1.8926 (1.8114)	
[2022-01-23 15:19:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][390/1251]	eta 0:32:04 lr 0.000316	time 2.1043 (2.2349)	loss 4.0519 (3.3867)	grad_norm 1.9210 (1.8097)	
[2022-01-23 15:20:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][400/1251]	eta 0:31:42 lr 0.000316	time 2.1545 (2.2351)	loss 4.2984 (3.3903)	grad_norm 1.8060 (1.8124)	
[2022-01-23 15:20:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][410/1251]	eta 0:31:21 lr 0.000316	time 1.5766 (2.2375)	loss 3.5990 (3.3854)	grad_norm 1.5133 (1.8126)	
[2022-01-23 15:21:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][420/1251]	eta 0:31:01 lr 0.000316	time 1.7824 (2.2396)	loss 3.5505 (3.3902)	grad_norm 1.6613 (1.8119)	
[2022-01-23 15:21:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][430/1251]	eta 0:30:45 lr 0.000316	time 3.3326 (2.2474)	loss 4.0241 (3.3923)	grad_norm 2.0688 (1.8115)	
[2022-01-23 15:21:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][440/1251]	eta 0:30:25 lr 0.000316	time 1.8781 (2.2506)	loss 2.7870 (3.4006)	grad_norm 1.5191 (1.8110)	
[2022-01-23 15:22:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][450/1251]	eta 0:29:58 lr 0.000316	time 1.5854 (2.2454)	loss 4.1311 (3.4080)	grad_norm 1.7686 (1.8108)	
[2022-01-23 15:22:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][460/1251]	eta 0:29:29 lr 0.000316	time 1.5510 (2.2377)	loss 3.6990 (3.4053)	grad_norm 1.9236 (1.8110)	
[2022-01-23 15:22:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][470/1251]	eta 0:29:05 lr 0.000316	time 2.7030 (2.2353)	loss 3.0317 (3.4084)	grad_norm 1.5143 (1.8110)	
[2022-01-23 15:23:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][480/1251]	eta 0:28:40 lr 0.000316	time 1.9880 (2.2319)	loss 3.6438 (3.4088)	grad_norm 1.8739 (1.8096)	
[2022-01-23 15:23:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][490/1251]	eta 0:28:16 lr 0.000316	time 2.2992 (2.2288)	loss 2.7669 (3.3958)	grad_norm 1.7893 (1.8091)	
[2022-01-23 15:23:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][500/1251]	eta 0:27:53 lr 0.000316	time 2.3645 (2.2277)	loss 2.5117 (3.3923)	grad_norm 1.5466 (1.8099)	
[2022-01-23 15:24:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][510/1251]	eta 0:27:32 lr 0.000316	time 2.6950 (2.2298)	loss 3.0415 (3.3915)	grad_norm 1.7249 (1.8101)	
[2022-01-23 15:24:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][520/1251]	eta 0:27:15 lr 0.000316	time 4.9626 (2.2380)	loss 3.6155 (3.3906)	grad_norm 1.6830 (1.8087)	
[2022-01-23 15:25:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][530/1251]	eta 0:26:54 lr 0.000316	time 2.3932 (2.2389)	loss 3.8374 (3.3951)	grad_norm 1.8458 (1.8084)	
[2022-01-23 15:25:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][540/1251]	eta 0:26:32 lr 0.000316	time 2.7137 (2.2398)	loss 3.7241 (3.3953)	grad_norm 1.7115 (1.8097)	
[2022-01-23 15:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][550/1251]	eta 0:26:08 lr 0.000316	time 1.9514 (2.2379)	loss 2.3490 (3.3983)	grad_norm 1.6147 (1.8094)	
[2022-01-23 15:26:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][560/1251]	eta 0:25:43 lr 0.000316	time 2.2463 (2.2344)	loss 3.8778 (3.4037)	grad_norm 1.9148 (1.8098)	
[2022-01-23 15:26:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][570/1251]	eta 0:25:18 lr 0.000316	time 2.1727 (2.2303)	loss 3.9269 (3.4054)	grad_norm 2.0817 (1.8111)	
[2022-01-23 15:26:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][580/1251]	eta 0:24:53 lr 0.000316	time 2.2976 (2.2261)	loss 3.8112 (3.4055)	grad_norm 1.9472 (1.8122)	
[2022-01-23 15:27:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][590/1251]	eta 0:24:29 lr 0.000316	time 2.6158 (2.2238)	loss 3.8356 (3.4064)	grad_norm 1.9061 (1.8123)	
[2022-01-23 15:27:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][600/1251]	eta 0:24:07 lr 0.000316	time 2.2017 (2.2231)	loss 4.1482 (3.4105)	grad_norm 1.9172 (1.8135)	
[2022-01-23 15:27:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][610/1251]	eta 0:23:44 lr 0.000316	time 2.2792 (2.2221)	loss 3.7906 (3.4108)	grad_norm 1.7942 (1.8147)	
[2022-01-23 15:28:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][620/1251]	eta 0:23:22 lr 0.000316	time 1.8262 (2.2231)	loss 3.5025 (3.4065)	grad_norm 2.0129 (1.8148)	
[2022-01-23 15:28:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][630/1251]	eta 0:23:02 lr 0.000316	time 3.2977 (2.2269)	loss 2.8927 (3.3995)	grad_norm 2.3338 (1.8158)	
[2022-01-23 15:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][640/1251]	eta 0:22:41 lr 0.000316	time 1.6545 (2.2277)	loss 2.9177 (3.3972)	grad_norm 1.6369 (1.8154)	
[2022-01-23 15:29:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][650/1251]	eta 0:22:18 lr 0.000315	time 2.0826 (2.2273)	loss 3.9686 (3.3981)	grad_norm 1.5550 (1.8148)	
[2022-01-23 15:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][660/1251]	eta 0:21:55 lr 0.000315	time 2.0331 (2.2256)	loss 2.6072 (3.3996)	grad_norm 1.9664 (1.8148)	
[2022-01-23 15:30:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][670/1251]	eta 0:21:32 lr 0.000315	time 2.8658 (2.2250)	loss 2.5463 (3.3977)	grad_norm 1.6914 (1.8133)	
[2022-01-23 15:30:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][680/1251]	eta 0:21:10 lr 0.000315	time 2.4988 (2.2246)	loss 3.4558 (3.3967)	grad_norm 1.6102 (1.8136)	
[2022-01-23 15:30:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][690/1251]	eta 0:20:47 lr 0.000315	time 2.1294 (2.2237)	loss 3.7504 (3.3965)	grad_norm 1.7725 (1.8131)	
[2022-01-23 15:31:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][700/1251]	eta 0:20:24 lr 0.000315	time 2.1684 (2.2223)	loss 2.9426 (3.3934)	grad_norm 1.8371 (1.8125)	
[2022-01-23 15:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][710/1251]	eta 0:20:02 lr 0.000315	time 2.6353 (2.2226)	loss 3.7202 (3.3908)	grad_norm 1.7557 (1.8124)	
[2022-01-23 15:31:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][720/1251]	eta 0:19:38 lr 0.000315	time 1.8474 (2.2190)	loss 3.1332 (3.3901)	grad_norm 1.7341 (1.8113)	
[2022-01-23 15:32:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][730/1251]	eta 0:19:14 lr 0.000315	time 2.2653 (2.2166)	loss 3.5686 (3.3895)	grad_norm 1.6016 (1.8109)	
[2022-01-23 15:32:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][740/1251]	eta 0:18:51 lr 0.000315	time 1.9581 (2.2149)	loss 3.6480 (3.3914)	grad_norm 1.7377 (1.8124)	
[2022-01-23 15:33:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][750/1251]	eta 0:18:30 lr 0.000315	time 2.5090 (2.2175)	loss 3.5659 (3.3914)	grad_norm 1.5723 (1.8131)	
[2022-01-23 15:33:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][760/1251]	eta 0:18:09 lr 0.000315	time 2.1867 (2.2189)	loss 3.5741 (3.3891)	grad_norm 1.4427 (1.8131)	
[2022-01-23 15:33:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][770/1251]	eta 0:17:46 lr 0.000315	time 2.1460 (2.2169)	loss 2.1212 (3.3896)	grad_norm 1.6257 (1.8116)	
[2022-01-23 15:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][780/1251]	eta 0:17:23 lr 0.000315	time 2.1365 (2.2157)	loss 3.6708 (3.3881)	grad_norm 1.5984 (1.8095)	
[2022-01-23 15:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][790/1251]	eta 0:17:01 lr 0.000315	time 3.1702 (2.2169)	loss 2.5810 (3.3853)	grad_norm 1.8013 (1.8089)	
[2022-01-23 15:34:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][800/1251]	eta 0:16:40 lr 0.000315	time 2.3957 (2.2173)	loss 2.6311 (3.3850)	grad_norm 1.5809 (1.8078)	
[2022-01-23 15:35:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][810/1251]	eta 0:16:17 lr 0.000315	time 1.5154 (2.2167)	loss 2.8461 (3.3822)	grad_norm 1.8896 (1.8078)	
[2022-01-23 15:35:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][820/1251]	eta 0:15:55 lr 0.000315	time 2.3505 (2.2166)	loss 3.6214 (3.3820)	grad_norm 1.6070 (1.8094)	
[2022-01-23 15:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][830/1251]	eta 0:15:31 lr 0.000315	time 1.6360 (2.2138)	loss 3.0523 (3.3824)	grad_norm 1.8654 (1.8090)	
[2022-01-23 15:36:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][840/1251]	eta 0:15:09 lr 0.000315	time 2.2528 (2.2135)	loss 2.7745 (3.3824)	grad_norm 1.7444 (1.8086)	
[2022-01-23 15:36:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][850/1251]	eta 0:14:48 lr 0.000315	time 1.5390 (2.2152)	loss 2.7744 (3.3814)	grad_norm 1.6582 (1.8086)	
[2022-01-23 15:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][860/1251]	eta 0:14:27 lr 0.000315	time 3.0024 (2.2181)	loss 3.7798 (3.3818)	grad_norm 1.6269 (1.8086)	
[2022-01-23 15:37:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][870/1251]	eta 0:14:04 lr 0.000315	time 1.9344 (2.2178)	loss 3.5030 (3.3782)	grad_norm 1.6215 (1.8073)	
[2022-01-23 15:37:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][880/1251]	eta 0:13:41 lr 0.000315	time 1.6226 (2.2138)	loss 3.1031 (3.3791)	grad_norm 1.6988 (1.8073)	
[2022-01-23 15:38:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][890/1251]	eta 0:13:18 lr 0.000315	time 2.3625 (2.2113)	loss 2.4204 (3.3746)	grad_norm 1.7629 (1.8084)	
[2022-01-23 15:38:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][900/1251]	eta 0:12:56 lr 0.000315	time 1.8838 (2.2126)	loss 2.3255 (3.3718)	grad_norm 1.9796 (1.8086)	
[2022-01-23 15:38:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][910/1251]	eta 0:12:34 lr 0.000314	time 2.1642 (2.2119)	loss 4.2121 (3.3708)	grad_norm 1.6934 (1.8087)	
[2022-01-23 15:39:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][920/1251]	eta 0:12:12 lr 0.000314	time 2.4486 (2.2117)	loss 3.0296 (3.3719)	grad_norm 1.7784 (1.8080)	
[2022-01-23 15:39:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][930/1251]	eta 0:11:49 lr 0.000314	time 1.9132 (2.2109)	loss 3.6793 (3.3743)	grad_norm 2.0214 (1.8080)	
[2022-01-23 15:40:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][940/1251]	eta 0:11:27 lr 0.000314	time 1.9008 (2.2116)	loss 2.5861 (3.3736)	grad_norm 1.7378 (1.8090)	
[2022-01-23 15:40:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][950/1251]	eta 0:11:05 lr 0.000314	time 2.5724 (2.2122)	loss 3.5138 (3.3714)	grad_norm 1.7425 (1.8105)	
[2022-01-23 15:40:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][960/1251]	eta 0:10:43 lr 0.000314	time 2.2098 (2.2115)	loss 4.2729 (3.3742)	grad_norm 1.7001 (1.8112)	
[2022-01-23 15:41:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][970/1251]	eta 0:10:21 lr 0.000314	time 2.2645 (2.2114)	loss 2.2880 (3.3751)	grad_norm 1.7396 (1.8119)	
[2022-01-23 15:41:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][980/1251]	eta 0:09:59 lr 0.000314	time 2.2139 (2.2112)	loss 3.6689 (3.3770)	grad_norm 1.7697 (1.8124)	
[2022-01-23 15:41:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][990/1251]	eta 0:09:37 lr 0.000314	time 2.7016 (2.2117)	loss 3.0812 (3.3786)	grad_norm 1.9066 (1.8119)	
[2022-01-23 15:42:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1000/1251]	eta 0:09:14 lr 0.000314	time 1.9147 (2.2096)	loss 3.5345 (3.3812)	grad_norm 1.7543 (1.8114)	
[2022-01-23 15:42:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1010/1251]	eta 0:08:52 lr 0.000314	time 1.5750 (2.2093)	loss 3.2774 (3.3808)	grad_norm 1.7185 (1.8109)	
[2022-01-23 15:42:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1020/1251]	eta 0:08:30 lr 0.000314	time 2.0614 (2.2087)	loss 3.6370 (3.3815)	grad_norm 1.5792 (1.8114)	
[2022-01-23 15:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1030/1251]	eta 0:08:08 lr 0.000314	time 1.8781 (2.2088)	loss 3.2228 (3.3830)	grad_norm 2.6412 (1.8111)	
[2022-01-23 15:43:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1040/1251]	eta 0:07:45 lr 0.000314	time 1.8670 (2.2085)	loss 2.1697 (3.3811)	grad_norm 1.9972 (1.8109)	
[2022-01-23 15:43:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1050/1251]	eta 0:07:23 lr 0.000314	time 2.2715 (2.2078)	loss 3.8862 (3.3813)	grad_norm 1.7994 (1.8099)	
[2022-01-23 15:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1060/1251]	eta 0:07:01 lr 0.000314	time 1.9114 (2.2081)	loss 3.0265 (3.3820)	grad_norm 1.6616 (1.8100)	
[2022-01-23 15:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1070/1251]	eta 0:06:39 lr 0.000314	time 1.7771 (2.2070)	loss 3.4190 (3.3805)	grad_norm 1.7314 (1.8091)	
[2022-01-23 15:45:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1080/1251]	eta 0:06:17 lr 0.000314	time 2.2172 (2.2083)	loss 3.4852 (3.3814)	grad_norm 1.7664 (1.8090)	
[2022-01-23 15:45:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1090/1251]	eta 0:05:55 lr 0.000314	time 2.3814 (2.2082)	loss 2.3916 (3.3821)	grad_norm 1.8914 (1.8095)	
[2022-01-23 15:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1100/1251]	eta 0:05:33 lr 0.000314	time 2.2417 (2.2090)	loss 3.6823 (3.3819)	grad_norm 1.8087 (1.8107)	
[2022-01-23 15:46:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1110/1251]	eta 0:05:11 lr 0.000314	time 1.8560 (2.2083)	loss 3.6204 (3.3819)	grad_norm 2.1357 (1.8115)	
[2022-01-23 15:46:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1120/1251]	eta 0:04:49 lr 0.000314	time 1.6760 (2.2070)	loss 2.8791 (3.3827)	grad_norm 1.8474 (1.8119)	
[2022-01-23 15:46:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1130/1251]	eta 0:04:26 lr 0.000314	time 3.1825 (2.2061)	loss 2.9362 (3.3828)	grad_norm 1.8047 (1.8120)	
[2022-01-23 15:47:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1140/1251]	eta 0:04:04 lr 0.000314	time 1.8503 (2.2047)	loss 3.4064 (3.3833)	grad_norm 1.7283 (1.8111)	
[2022-01-23 15:47:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1150/1251]	eta 0:03:42 lr 0.000314	time 2.3694 (2.2045)	loss 2.9943 (3.3816)	grad_norm 1.7277 (1.8109)	
[2022-01-23 15:47:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1160/1251]	eta 0:03:20 lr 0.000314	time 1.9865 (2.2044)	loss 3.8383 (3.3829)	grad_norm 1.7573 (1.8100)	
[2022-01-23 15:48:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1170/1251]	eta 0:02:58 lr 0.000313	time 2.1729 (2.2044)	loss 3.4351 (3.3825)	grad_norm 1.7189 (1.8108)	
[2022-01-23 15:48:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1180/1251]	eta 0:02:36 lr 0.000313	time 1.8821 (2.2044)	loss 3.7112 (3.3828)	grad_norm 1.8168 (1.8113)	
[2022-01-23 15:49:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1190/1251]	eta 0:02:14 lr 0.000313	time 2.1766 (2.2041)	loss 3.6802 (3.3834)	grad_norm 1.7713 (1.8130)	
[2022-01-23 15:49:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1200/1251]	eta 0:01:52 lr 0.000313	time 1.8061 (2.2052)	loss 3.7567 (3.3864)	grad_norm 1.6831 (1.8130)	
[2022-01-23 15:49:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1210/1251]	eta 0:01:30 lr 0.000313	time 1.8820 (2.2046)	loss 3.7229 (3.3881)	grad_norm 1.7004 (1.8133)	
[2022-01-23 15:50:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1220/1251]	eta 0:01:08 lr 0.000313	time 2.1975 (2.2055)	loss 2.3321 (3.3878)	grad_norm 1.4319 (1.8125)	
[2022-01-23 15:50:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1230/1251]	eta 0:00:46 lr 0.000313	time 1.6701 (2.2043)	loss 3.4291 (3.3863)	grad_norm 1.6750 (1.8123)	
[2022-01-23 15:50:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1240/1251]	eta 0:00:24 lr 0.000313	time 1.6895 (2.2034)	loss 3.2920 (3.3834)	grad_norm 1.7605 (1.8125)	
[2022-01-23 15:51:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [187/300][1250/1251]	eta 0:00:02 lr 0.000313	time 1.2109 (2.1975)	loss 3.6921 (3.3826)	grad_norm 1.7577 (1.8121)	
[2022-01-23 15:51:08 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 187 training takes 0:45:49
[2022-01-23 15:51:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.717 (18.717)	Loss 0.9238 (0.9238)	Acc@1 78.027 (78.027)	Acc@5 93.848 (93.848)	
[2022-01-23 15:51:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.953 (3.313)	Loss 1.0136 (0.9654)	Acc@1 77.051 (77.051)	Acc@5 92.480 (93.626)	
[2022-01-23 15:52:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.933 (2.599)	Loss 0.9572 (0.9432)	Acc@1 75.488 (77.469)	Acc@5 94.531 (93.964)	
[2022-01-23 15:52:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.560 (2.261)	Loss 0.9340 (0.9403)	Acc@1 78.223 (77.778)	Acc@5 95.508 (94.040)	
[2022-01-23 15:52:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.030 (2.209)	Loss 0.8376 (0.9344)	Acc@1 80.273 (77.742)	Acc@5 95.020 (94.086)	
[2022-01-23 15:52:46 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.870 Acc@5 94.134
[2022-01-23 15:52:46 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.9%
[2022-01-23 15:52:46 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.87%
[2022-01-23 15:53:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][0/1251]	eta 7:33:14 lr 0.000313	time 21.7378 (21.7378)	loss 2.7614 (2.7614)	grad_norm 1.6973 (1.6973)	
[2022-01-23 15:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][10/1251]	eta 1:26:51 lr 0.000313	time 2.1049 (4.1995)	loss 3.5284 (3.5170)	grad_norm 1.6867 (1.7752)	
[2022-01-23 15:53:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][20/1251]	eta 1:05:36 lr 0.000313	time 1.2505 (3.1978)	loss 3.4051 (3.3890)	grad_norm 1.6404 (1.7482)	
[2022-01-23 15:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][30/1251]	eta 0:57:38 lr 0.000313	time 1.5269 (2.8329)	loss 3.0468 (3.3934)	grad_norm 1.7476 (1.7524)	
[2022-01-23 15:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][40/1251]	eta 0:54:06 lr 0.000313	time 3.3035 (2.6807)	loss 2.0542 (3.3751)	grad_norm 1.7741 (1.7623)	
[2022-01-23 15:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][50/1251]	eta 0:51:40 lr 0.000313	time 1.7611 (2.5818)	loss 3.9238 (3.3896)	grad_norm 1.8727 (1.7865)	
[2022-01-23 15:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][60/1251]	eta 0:49:47 lr 0.000313	time 1.3374 (2.5086)	loss 2.6723 (3.3907)	grad_norm 2.0885 (1.7951)	
[2022-01-23 15:55:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][70/1251]	eta 0:48:19 lr 0.000313	time 2.0721 (2.4555)	loss 3.2275 (3.3835)	grad_norm 1.8789 (1.8068)	
[2022-01-23 15:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][80/1251]	eta 0:47:30 lr 0.000313	time 3.2968 (2.4346)	loss 4.0683 (3.3639)	grad_norm 1.8913 (1.8232)	
[2022-01-23 15:56:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][90/1251]	eta 0:46:32 lr 0.000313	time 1.3485 (2.4051)	loss 2.9099 (3.3535)	grad_norm 1.9078 (1.8259)	
[2022-01-23 15:56:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][100/1251]	eta 0:45:36 lr 0.000313	time 1.5162 (2.3774)	loss 3.4832 (3.3639)	grad_norm 1.7670 (1.8231)	
[2022-01-23 15:57:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][110/1251]	eta 0:44:51 lr 0.000313	time 1.7328 (2.3590)	loss 3.8827 (3.3839)	grad_norm 1.6541 (1.8282)	
[2022-01-23 15:57:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][120/1251]	eta 0:44:20 lr 0.000313	time 3.2151 (2.3520)	loss 2.6678 (3.3729)	grad_norm 2.0288 (1.8330)	
[2022-01-23 15:57:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][130/1251]	eta 0:43:46 lr 0.000313	time 2.1610 (2.3427)	loss 3.8081 (3.3812)	grad_norm 1.9848 (1.8340)	
[2022-01-23 15:58:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][140/1251]	eta 0:43:15 lr 0.000313	time 1.5154 (2.3365)	loss 3.3761 (3.3858)	grad_norm 1.7939 (1.8397)	
[2022-01-23 15:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][150/1251]	eta 0:42:44 lr 0.000313	time 1.8687 (2.3293)	loss 3.5209 (3.4058)	grad_norm 1.6983 (1.8416)	
[2022-01-23 15:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][160/1251]	eta 0:42:22 lr 0.000313	time 3.5539 (2.3302)	loss 2.7517 (3.3956)	grad_norm 1.7013 (1.8344)	
[2022-01-23 15:59:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][170/1251]	eta 0:41:46 lr 0.000313	time 1.8304 (2.3182)	loss 4.1679 (3.4206)	grad_norm 1.8062 (1.8332)	
[2022-01-23 15:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][180/1251]	eta 0:41:18 lr 0.000312	time 1.6437 (2.3141)	loss 4.0599 (3.4124)	grad_norm 2.5519 (1.8356)	
[2022-01-23 16:00:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][190/1251]	eta 0:40:45 lr 0.000312	time 2.0336 (2.3047)	loss 3.0224 (3.4081)	grad_norm 1.8298 (1.8415)	
[2022-01-23 16:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][200/1251]	eta 0:40:22 lr 0.000312	time 2.7056 (2.3047)	loss 3.3824 (3.4063)	grad_norm 1.8798 (1.8435)	
[2022-01-23 16:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][210/1251]	eta 0:39:53 lr 0.000312	time 1.5754 (2.2997)	loss 3.6964 (3.4064)	grad_norm 1.7708 (1.8424)	
[2022-01-23 16:01:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][220/1251]	eta 0:39:25 lr 0.000312	time 1.5959 (2.2945)	loss 2.6179 (3.4091)	grad_norm 1.6909 (1.8394)	
[2022-01-23 16:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][230/1251]	eta 0:38:50 lr 0.000312	time 2.0283 (2.2822)	loss 3.8489 (3.4030)	grad_norm 2.2052 (1.8383)	
[2022-01-23 16:01:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][240/1251]	eta 0:38:24 lr 0.000312	time 2.1318 (2.2796)	loss 3.9280 (3.4097)	grad_norm 1.7885 (1.8409)	
[2022-01-23 16:02:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][250/1251]	eta 0:38:03 lr 0.000312	time 1.9197 (2.2817)	loss 3.5369 (3.4107)	grad_norm 1.7666 (1.8419)	
[2022-01-23 16:02:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][260/1251]	eta 0:37:39 lr 0.000312	time 1.6909 (2.2801)	loss 2.5778 (3.4062)	grad_norm 2.0532 (1.8491)	
[2022-01-23 16:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][270/1251]	eta 0:37:14 lr 0.000312	time 1.8751 (2.2775)	loss 3.1275 (3.3952)	grad_norm 1.8646 (1.8506)	
[2022-01-23 16:03:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][280/1251]	eta 0:36:47 lr 0.000312	time 1.9116 (2.2736)	loss 3.8993 (3.3923)	grad_norm 1.8777 (1.8534)	
[2022-01-23 16:03:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][290/1251]	eta 0:36:22 lr 0.000312	time 1.8672 (2.2707)	loss 2.7133 (3.3925)	grad_norm 1.7611 (1.8554)	
[2022-01-23 16:04:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][300/1251]	eta 0:35:53 lr 0.000312	time 2.2209 (2.2647)	loss 3.3030 (3.4023)	grad_norm 1.9945 (1.8565)	
[2022-01-23 16:04:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][310/1251]	eta 0:35:27 lr 0.000312	time 2.2795 (2.2609)	loss 3.6558 (3.3983)	grad_norm 2.0742 (1.8564)	
[2022-01-23 16:04:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][320/1251]	eta 0:35:00 lr 0.000312	time 2.2121 (2.2565)	loss 3.3701 (3.3916)	grad_norm 1.7311 (1.8559)	
[2022-01-23 16:05:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][330/1251]	eta 0:34:37 lr 0.000312	time 1.8571 (2.2562)	loss 2.7879 (3.3958)	grad_norm 1.9232 (1.8552)	
[2022-01-23 16:05:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][340/1251]	eta 0:34:13 lr 0.000312	time 1.8926 (2.2537)	loss 3.2364 (3.3940)	grad_norm 1.7601 (1.8528)	
[2022-01-23 16:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][350/1251]	eta 0:33:48 lr 0.000312	time 1.5171 (2.2511)	loss 2.5061 (3.3933)	grad_norm 1.6514 (1.8512)	
[2022-01-23 16:06:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][360/1251]	eta 0:33:22 lr 0.000312	time 2.6469 (2.2480)	loss 3.2513 (3.3954)	grad_norm 1.8449 (1.8498)	
[2022-01-23 16:06:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][370/1251]	eta 0:32:57 lr 0.000312	time 2.1621 (2.2442)	loss 3.7201 (3.4015)	grad_norm 2.4941 (1.8511)	
[2022-01-23 16:06:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][380/1251]	eta 0:32:29 lr 0.000312	time 1.5872 (2.2387)	loss 3.6939 (3.4065)	grad_norm 1.6105 (1.8521)	
[2022-01-23 16:07:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][390/1251]	eta 0:32:08 lr 0.000312	time 1.9132 (2.2396)	loss 3.7287 (3.4074)	grad_norm 1.6649 (1.8547)	
[2022-01-23 16:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][400/1251]	eta 0:31:46 lr 0.000312	time 2.5649 (2.2404)	loss 4.1538 (3.4163)	grad_norm 2.0156 (1.8543)	
[2022-01-23 16:08:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][410/1251]	eta 0:31:22 lr 0.000312	time 1.9819 (2.2389)	loss 4.1593 (3.4197)	grad_norm 1.9549 (1.8561)	
[2022-01-23 16:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][420/1251]	eta 0:30:59 lr 0.000312	time 1.5337 (2.2377)	loss 3.2791 (3.4180)	grad_norm 1.6065 (1.8533)	
[2022-01-23 16:08:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][430/1251]	eta 0:30:36 lr 0.000312	time 2.5979 (2.2370)	loss 3.6791 (3.4173)	grad_norm 2.1717 (1.8568)	
[2022-01-23 16:09:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][440/1251]	eta 0:30:14 lr 0.000312	time 3.8637 (2.2373)	loss 2.4611 (3.4188)	grad_norm 1.7911 (1.8580)	
[2022-01-23 16:09:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][450/1251]	eta 0:29:50 lr 0.000311	time 1.5817 (2.2358)	loss 3.9926 (3.4205)	grad_norm 1.6711 (1.8553)	
[2022-01-23 16:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][460/1251]	eta 0:29:25 lr 0.000311	time 1.6371 (2.2321)	loss 2.5525 (3.4199)	grad_norm 2.1957 (1.8559)	
[2022-01-23 16:10:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][470/1251]	eta 0:29:02 lr 0.000311	time 2.4970 (2.2311)	loss 2.5572 (3.4180)	grad_norm 2.1088 (1.8572)	
[2022-01-23 16:10:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][480/1251]	eta 0:28:42 lr 0.000311	time 3.6471 (2.2347)	loss 2.8134 (3.4128)	grad_norm 1.6922 (1.8554)	
[2022-01-23 16:11:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][490/1251]	eta 0:28:18 lr 0.000311	time 1.9573 (2.2324)	loss 3.5445 (3.4171)	grad_norm 1.7816 (1.8542)	
[2022-01-23 16:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][500/1251]	eta 0:27:54 lr 0.000311	time 1.9964 (2.2293)	loss 2.9467 (3.4149)	grad_norm 1.6500 (1.8532)	
[2022-01-23 16:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][510/1251]	eta 0:27:30 lr 0.000311	time 2.1954 (2.2267)	loss 2.5076 (3.4094)	grad_norm 1.7159 (1.8509)	
[2022-01-23 16:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][520/1251]	eta 0:27:08 lr 0.000311	time 3.7191 (2.2284)	loss 3.4598 (3.4081)	grad_norm 1.8338 (1.8532)	
[2022-01-23 16:12:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][530/1251]	eta 0:26:45 lr 0.000311	time 1.6464 (2.2272)	loss 2.5372 (3.4078)	grad_norm 1.7680 (1.8523)	
[2022-01-23 16:12:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][540/1251]	eta 0:26:22 lr 0.000311	time 1.6477 (2.2256)	loss 3.3304 (3.4051)	grad_norm 1.8520 (1.8518)	
[2022-01-23 16:13:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][550/1251]	eta 0:26:00 lr 0.000311	time 1.8414 (2.2257)	loss 3.4087 (3.4013)	grad_norm 1.9646 (1.8532)	
[2022-01-23 16:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][560/1251]	eta 0:25:39 lr 0.000311	time 3.6569 (2.2280)	loss 3.4746 (3.4019)	grad_norm 1.6818 (1.8514)	
[2022-01-23 16:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][570/1251]	eta 0:25:16 lr 0.000311	time 2.1976 (2.2273)	loss 2.4543 (3.3966)	grad_norm 1.8229 (1.8492)	
[2022-01-23 16:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][580/1251]	eta 0:24:52 lr 0.000311	time 1.6352 (2.2247)	loss 3.3984 (3.3981)	grad_norm 1.5754 (1.8494)	
[2022-01-23 16:14:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][590/1251]	eta 0:24:27 lr 0.000311	time 1.5930 (2.2205)	loss 3.2909 (3.3987)	grad_norm 2.2834 (1.8504)	
[2022-01-23 16:14:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][600/1251]	eta 0:24:03 lr 0.000311	time 2.8798 (2.2180)	loss 3.4608 (3.3951)	grad_norm 1.6122 (1.8497)	
[2022-01-23 16:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][610/1251]	eta 0:23:40 lr 0.000311	time 1.9874 (2.2158)	loss 4.0767 (3.3919)	grad_norm 1.9664 (1.8490)	
[2022-01-23 16:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][620/1251]	eta 0:23:17 lr 0.000311	time 2.2357 (2.2152)	loss 3.8868 (3.3916)	grad_norm 2.1507 (1.8488)	
[2022-01-23 16:16:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][630/1251]	eta 0:22:55 lr 0.000311	time 1.9634 (2.2142)	loss 2.2996 (3.3898)	grad_norm 2.0579 (1.8478)	
[2022-01-23 16:16:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][640/1251]	eta 0:22:34 lr 0.000311	time 3.4637 (2.2168)	loss 3.6628 (3.3923)	grad_norm 1.7322 (1.8475)	
[2022-01-23 16:16:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][650/1251]	eta 0:22:12 lr 0.000311	time 1.8916 (2.2164)	loss 3.5150 (3.3945)	grad_norm 1.6136 (1.8475)	
[2022-01-23 16:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][660/1251]	eta 0:21:50 lr 0.000311	time 1.7406 (2.2181)	loss 3.2835 (3.3975)	grad_norm 1.8271 (1.8475)	
[2022-01-23 16:17:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][670/1251]	eta 0:21:29 lr 0.000311	time 2.2360 (2.2188)	loss 3.0916 (3.3960)	grad_norm 2.0107 (1.8483)	
[2022-01-23 16:17:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][680/1251]	eta 0:21:08 lr 0.000311	time 3.1703 (2.2207)	loss 2.4980 (3.3947)	grad_norm 1.7571 (1.8471)	
[2022-01-23 16:18:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][690/1251]	eta 0:20:45 lr 0.000311	time 1.6988 (2.2195)	loss 3.4879 (3.3992)	grad_norm 1.7466 (1.8455)	
[2022-01-23 16:18:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][700/1251]	eta 0:20:21 lr 0.000311	time 1.5868 (2.2162)	loss 2.7675 (3.3991)	grad_norm 1.7550 (1.8439)	
[2022-01-23 16:19:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][710/1251]	eta 0:19:57 lr 0.000310	time 1.8225 (2.2138)	loss 3.4003 (3.4013)	grad_norm 2.0259 (1.8434)	
[2022-01-23 16:19:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][720/1251]	eta 0:19:34 lr 0.000310	time 1.9287 (2.2118)	loss 3.4353 (3.3999)	grad_norm 1.7102 (1.8433)	
[2022-01-23 16:19:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][730/1251]	eta 0:19:11 lr 0.000310	time 1.8464 (2.2105)	loss 4.0735 (3.3988)	grad_norm 1.9232 (1.8438)	
[2022-01-23 16:20:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][740/1251]	eta 0:18:49 lr 0.000310	time 2.4176 (2.2098)	loss 3.4904 (3.3986)	grad_norm 1.5685 (1.8451)	
[2022-01-23 16:20:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][750/1251]	eta 0:18:26 lr 0.000310	time 2.2153 (2.2085)	loss 2.9386 (3.4006)	grad_norm 1.8087 (1.8458)	
[2022-01-23 16:20:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][760/1251]	eta 0:18:04 lr 0.000310	time 2.3427 (2.2085)	loss 4.0724 (3.3997)	grad_norm 1.6573 (1.8471)	
[2022-01-23 16:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][770/1251]	eta 0:17:42 lr 0.000310	time 2.2445 (2.2093)	loss 3.5519 (3.4009)	grad_norm 1.8442 (1.8470)	
[2022-01-23 16:21:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][780/1251]	eta 0:17:20 lr 0.000310	time 2.2846 (2.2086)	loss 3.3274 (3.4020)	grad_norm 1.5051 (1.8460)	
[2022-01-23 16:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][790/1251]	eta 0:16:58 lr 0.000310	time 1.7802 (2.2099)	loss 2.9658 (3.4037)	grad_norm 1.6973 (1.8461)	
[2022-01-23 16:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][800/1251]	eta 0:16:37 lr 0.000310	time 2.1753 (2.2119)	loss 3.9014 (3.4037)	grad_norm 1.6654 (1.8464)	
[2022-01-23 16:22:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][810/1251]	eta 0:16:15 lr 0.000310	time 2.2362 (2.2128)	loss 3.6199 (3.4046)	grad_norm 1.9253 (1.8456)	
[2022-01-23 16:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][820/1251]	eta 0:15:52 lr 0.000310	time 1.7033 (2.2099)	loss 2.4436 (3.4034)	grad_norm 1.8427 (1.8456)	
[2022-01-23 16:23:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][830/1251]	eta 0:15:30 lr 0.000310	time 2.5546 (2.2109)	loss 3.6450 (3.4011)	grad_norm 1.7259 (1.8456)	
[2022-01-23 16:23:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][840/1251]	eta 0:15:08 lr 0.000310	time 2.2594 (2.2100)	loss 3.1623 (3.4034)	grad_norm 1.6752 (1.8449)	
[2022-01-23 16:24:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][850/1251]	eta 0:14:45 lr 0.000310	time 1.8978 (2.2070)	loss 3.9976 (3.4021)	grad_norm 1.9592 (1.8446)	
[2022-01-23 16:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][860/1251]	eta 0:14:21 lr 0.000310	time 1.9458 (2.2040)	loss 3.9849 (3.4019)	grad_norm 1.8687 (1.8451)	
[2022-01-23 16:24:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][870/1251]	eta 0:13:59 lr 0.000310	time 2.4020 (2.2039)	loss 3.2096 (3.4036)	grad_norm 1.9269 (1.8448)	
[2022-01-23 16:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][880/1251]	eta 0:13:38 lr 0.000310	time 2.5869 (2.2053)	loss 3.6446 (3.4028)	grad_norm 1.6490 (1.8459)	
[2022-01-23 16:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][890/1251]	eta 0:13:16 lr 0.000310	time 2.0506 (2.2056)	loss 2.9048 (3.4015)	grad_norm 2.0065 (1.8464)	
[2022-01-23 16:25:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][900/1251]	eta 0:12:54 lr 0.000310	time 1.9522 (2.2054)	loss 3.9605 (3.4033)	grad_norm 1.8674 (1.8456)	
[2022-01-23 16:26:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][910/1251]	eta 0:12:32 lr 0.000310	time 2.0152 (2.2076)	loss 3.7308 (3.4044)	grad_norm 2.0719 (1.8454)	
[2022-01-23 16:26:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][920/1251]	eta 0:12:11 lr 0.000310	time 2.5461 (2.2088)	loss 3.9384 (3.4026)	grad_norm 1.7178 (1.8444)	
[2022-01-23 16:27:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][930/1251]	eta 0:11:49 lr 0.000310	time 2.1557 (2.2099)	loss 3.9565 (3.4012)	grad_norm 1.7455 (1.8430)	
[2022-01-23 16:27:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][940/1251]	eta 0:11:26 lr 0.000310	time 2.2161 (2.2089)	loss 3.7552 (3.4023)	grad_norm 1.8327 (1.8425)	
[2022-01-23 16:27:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][950/1251]	eta 0:11:04 lr 0.000310	time 1.8147 (2.2082)	loss 3.5507 (3.3994)	grad_norm 1.5754 (1.8416)	
[2022-01-23 16:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][960/1251]	eta 0:10:42 lr 0.000310	time 1.5940 (2.2071)	loss 3.6999 (3.3987)	grad_norm 1.7305 (1.8416)	
[2022-01-23 16:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][970/1251]	eta 0:10:20 lr 0.000309	time 1.5420 (2.2074)	loss 2.8782 (3.3966)	grad_norm 1.7809 (1.8399)	
[2022-01-23 16:28:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][980/1251]	eta 0:09:57 lr 0.000309	time 2.1490 (2.2062)	loss 3.9002 (3.3935)	grad_norm 2.3426 (1.8405)	
[2022-01-23 16:29:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][990/1251]	eta 0:09:36 lr 0.000309	time 2.2321 (2.2070)	loss 2.9488 (3.3924)	grad_norm 1.7798 (1.8402)	
[2022-01-23 16:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1000/1251]	eta 0:09:13 lr 0.000309	time 2.1831 (2.2065)	loss 2.6993 (3.3937)	grad_norm 1.5538 (1.8403)	
[2022-01-23 16:29:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1010/1251]	eta 0:08:52 lr 0.000309	time 2.1101 (2.2079)	loss 3.5726 (3.3931)	grad_norm 1.4450 (1.8394)	
[2022-01-23 16:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1020/1251]	eta 0:08:29 lr 0.000309	time 1.8210 (2.2057)	loss 3.4988 (3.3905)	grad_norm 1.7618 (1.8387)	
[2022-01-23 16:30:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1030/1251]	eta 0:08:07 lr 0.000309	time 1.6259 (2.2046)	loss 2.4089 (3.3899)	grad_norm 2.1039 (1.8381)	
[2022-01-23 16:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1040/1251]	eta 0:07:44 lr 0.000309	time 1.6348 (2.2028)	loss 3.5257 (3.3883)	grad_norm 1.9014 (1.8379)	
[2022-01-23 16:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1050/1251]	eta 0:07:22 lr 0.000309	time 1.9598 (2.2027)	loss 3.4843 (3.3876)	grad_norm 1.8853 (1.8367)	
[2022-01-23 16:31:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1060/1251]	eta 0:07:00 lr 0.000309	time 2.1239 (2.2021)	loss 3.2686 (3.3862)	grad_norm 1.8268 (1.8365)	
[2022-01-23 16:32:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1070/1251]	eta 0:06:39 lr 0.000309	time 2.8575 (2.2044)	loss 3.7620 (3.3869)	grad_norm 1.7060 (1.8362)	
[2022-01-23 16:32:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1080/1251]	eta 0:06:17 lr 0.000309	time 1.9112 (2.2061)	loss 3.7324 (3.3876)	grad_norm 2.3503 (1.8388)	
[2022-01-23 16:32:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1090/1251]	eta 0:05:55 lr 0.000309	time 1.5615 (2.2066)	loss 3.0114 (3.3872)	grad_norm 2.0965 (1.8398)	
[2022-01-23 16:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1100/1251]	eta 0:05:33 lr 0.000309	time 1.8651 (2.2054)	loss 2.6317 (3.3876)	grad_norm 1.8531 (1.8398)	
[2022-01-23 16:33:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1110/1251]	eta 0:05:10 lr 0.000309	time 1.9596 (2.2031)	loss 2.6013 (3.3855)	grad_norm 1.5652 (1.8396)	
[2022-01-23 16:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1120/1251]	eta 0:04:48 lr 0.000309	time 1.8882 (2.2009)	loss 3.9978 (3.3883)	grad_norm 1.7698 (1.8384)	
[2022-01-23 16:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1130/1251]	eta 0:04:26 lr 0.000309	time 1.9233 (2.1997)	loss 3.6715 (3.3880)	grad_norm 1.7782 (1.8380)	
[2022-01-23 16:34:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1140/1251]	eta 0:04:04 lr 0.000309	time 2.1855 (2.1999)	loss 2.9631 (3.3871)	grad_norm 1.7708 (1.8372)	
[2022-01-23 16:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1150/1251]	eta 0:03:42 lr 0.000309	time 2.4906 (2.2005)	loss 3.6141 (3.3871)	grad_norm 1.9779 (1.8367)	
[2022-01-23 16:35:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1160/1251]	eta 0:03:20 lr 0.000309	time 2.8373 (2.2022)	loss 3.9254 (3.3879)	grad_norm 1.6449 (1.8361)	
[2022-01-23 16:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1170/1251]	eta 0:02:58 lr 0.000309	time 2.8566 (2.2048)	loss 2.3029 (3.3873)	grad_norm 1.6927 (1.8358)	
[2022-01-23 16:36:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1180/1251]	eta 0:02:36 lr 0.000309	time 3.1045 (2.2061)	loss 2.8465 (3.3886)	grad_norm 1.7960 (1.8355)	
[2022-01-23 16:36:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1190/1251]	eta 0:02:14 lr 0.000309	time 2.0164 (2.2039)	loss 2.5293 (3.3878)	grad_norm 1.5718 (1.8351)	
[2022-01-23 16:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1200/1251]	eta 0:01:52 lr 0.000309	time 2.5232 (2.2023)	loss 3.7193 (3.3887)	grad_norm 1.7291 (1.8343)	
[2022-01-23 16:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1210/1251]	eta 0:01:30 lr 0.000309	time 3.0559 (2.2032)	loss 3.9670 (3.3899)	grad_norm 2.2194 (1.8346)	
[2022-01-23 16:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1220/1251]	eta 0:01:08 lr 0.000309	time 2.2691 (2.2030)	loss 4.0753 (3.3918)	grad_norm 1.9065 (1.8345)	
[2022-01-23 16:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1230/1251]	eta 0:00:46 lr 0.000308	time 2.2257 (2.2033)	loss 2.7717 (3.3903)	grad_norm 2.0049 (1.8339)	
[2022-01-23 16:38:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1240/1251]	eta 0:00:24 lr 0.000308	time 1.6631 (2.2023)	loss 3.4646 (3.3905)	grad_norm 1.8457 (1.8345)	
[2022-01-23 16:38:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [188/300][1250/1251]	eta 0:00:02 lr 0.000308	time 1.1533 (2.1967)	loss 3.3982 (3.3912)	grad_norm 2.2809 (1.8342)	
[2022-01-23 16:38:34 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 188 training takes 0:45:48
[2022-01-23 16:38:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.532 (18.532)	Loss 0.9680 (0.9680)	Acc@1 77.246 (77.246)	Acc@5 94.336 (94.336)	
[2022-01-23 16:39:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.259 (3.231)	Loss 0.9871 (0.9580)	Acc@1 77.344 (77.539)	Acc@5 94.727 (94.070)	
[2022-01-23 16:39:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.610 (2.577)	Loss 0.9246 (0.9524)	Acc@1 76.270 (77.441)	Acc@5 94.922 (94.043)	
[2022-01-23 16:39:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.942 (2.363)	Loss 1.0375 (0.9473)	Acc@1 75.000 (77.589)	Acc@5 93.164 (94.040)	
[2022-01-23 16:40:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.289 (2.189)	Loss 0.8460 (0.9391)	Acc@1 80.176 (77.811)	Acc@5 95.605 (94.153)	
[2022-01-23 16:40:11 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.818 Acc@5 94.102
[2022-01-23 16:40:11 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.8%
[2022-01-23 16:40:11 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.87%
[2022-01-23 16:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][0/1251]	eta 6:44:45 lr 0.000308	time 19.4133 (19.4133)	loss 3.2774 (3.2774)	grad_norm 2.1148 (2.1148)	
[2022-01-23 16:40:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][10/1251]	eta 1:23:01 lr 0.000308	time 2.6533 (4.0141)	loss 3.8573 (3.4814)	grad_norm 1.6988 (1.7564)	
[2022-01-23 16:41:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][20/1251]	eta 1:05:25 lr 0.000308	time 2.1926 (3.1892)	loss 2.3956 (3.4954)	grad_norm 1.8835 (1.7790)	
[2022-01-23 16:41:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][30/1251]	eta 0:57:55 lr 0.000308	time 1.6089 (2.8462)	loss 4.0056 (3.3479)	grad_norm 1.9661 (1.8253)	
[2022-01-23 16:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][40/1251]	eta 0:55:13 lr 0.000308	time 3.6509 (2.7366)	loss 3.7303 (3.2938)	grad_norm 1.8895 (1.8270)	
[2022-01-23 16:42:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][50/1251]	eta 0:52:47 lr 0.000308	time 2.3827 (2.6373)	loss 3.4123 (3.2837)	grad_norm 1.6917 (1.8154)	
[2022-01-23 16:42:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][60/1251]	eta 0:51:11 lr 0.000308	time 2.5557 (2.5789)	loss 2.2912 (3.3070)	grad_norm 1.8259 (1.7983)	
[2022-01-23 16:43:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][70/1251]	eta 0:49:21 lr 0.000308	time 2.1851 (2.5076)	loss 3.0232 (3.3064)	grad_norm 1.7716 (1.8083)	
[2022-01-23 16:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][80/1251]	eta 0:48:11 lr 0.000308	time 3.3070 (2.4694)	loss 3.3455 (3.3123)	grad_norm 1.6183 (1.8187)	
[2022-01-23 16:43:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][90/1251]	eta 0:46:55 lr 0.000308	time 1.6126 (2.4251)	loss 2.7393 (3.3360)	grad_norm 1.8398 (1.8228)	
[2022-01-23 16:44:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][100/1251]	eta 0:47:12 lr 0.000308	time 1.8233 (2.4610)	loss 3.5132 (3.3572)	grad_norm 1.9532 (1.8247)	
[2022-01-23 16:44:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][110/1251]	eta 0:46:06 lr 0.000308	time 2.2394 (2.4244)	loss 2.3539 (3.3420)	grad_norm 1.7208 (1.8287)	
[2022-01-23 16:44:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][120/1251]	eta 0:44:47 lr 0.000308	time 2.2837 (2.3761)	loss 3.4434 (3.3457)	grad_norm 1.8272 (1.8350)	
[2022-01-23 16:45:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][130/1251]	eta 0:43:49 lr 0.000308	time 1.9427 (2.3455)	loss 3.6366 (3.3452)	grad_norm 1.8076 (1.8338)	
[2022-01-23 16:45:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][140/1251]	eta 0:43:06 lr 0.000308	time 1.8653 (2.3279)	loss 3.7661 (3.3660)	grad_norm 1.9597 (1.8333)	
[2022-01-23 16:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][150/1251]	eta 0:42:27 lr 0.000308	time 2.2233 (2.3135)	loss 3.5285 (3.3888)	grad_norm 1.8635 (1.8462)	
[2022-01-23 16:46:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][160/1251]	eta 0:42:00 lr 0.000308	time 2.4555 (2.3102)	loss 3.2565 (3.3927)	grad_norm 1.5546 (1.8512)	
[2022-01-23 16:46:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][170/1251]	eta 0:41:31 lr 0.000308	time 1.7418 (2.3047)	loss 2.1448 (3.3917)	grad_norm 1.9261 (1.8500)	
[2022-01-23 16:47:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][180/1251]	eta 0:41:06 lr 0.000308	time 2.7409 (2.3026)	loss 3.0551 (3.3838)	grad_norm 2.0078 (1.8466)	
[2022-01-23 16:47:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][190/1251]	eta 0:40:38 lr 0.000308	time 2.6070 (2.2981)	loss 3.6925 (3.3914)	grad_norm 1.6255 (1.8460)	
[2022-01-23 16:47:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][200/1251]	eta 0:40:31 lr 0.000308	time 3.2077 (2.3137)	loss 2.8530 (3.4007)	grad_norm 1.9792 (1.8479)	
[2022-01-23 16:48:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][210/1251]	eta 0:40:07 lr 0.000308	time 2.0910 (2.3123)	loss 3.5688 (3.4027)	grad_norm 1.6752 (1.8473)	
[2022-01-23 16:48:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][220/1251]	eta 0:39:33 lr 0.000308	time 2.2162 (2.3022)	loss 3.6433 (3.4085)	grad_norm 2.1727 (1.8470)	
[2022-01-23 16:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][230/1251]	eta 0:38:52 lr 0.000308	time 1.6453 (2.2845)	loss 3.2200 (3.4087)	grad_norm 2.4303 (1.8485)	
[2022-01-23 16:49:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][240/1251]	eta 0:38:18 lr 0.000307	time 1.6240 (2.2734)	loss 3.6617 (3.4081)	grad_norm 1.7618 (1.8506)	
[2022-01-23 16:49:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][250/1251]	eta 0:37:50 lr 0.000307	time 1.8737 (2.2681)	loss 4.0083 (3.4112)	grad_norm 2.0947 (1.8509)	
[2022-01-23 16:50:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][260/1251]	eta 0:37:31 lr 0.000307	time 2.2425 (2.2723)	loss 3.7139 (3.4194)	grad_norm 1.7386 (1.8495)	
[2022-01-23 16:50:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][270/1251]	eta 0:37:05 lr 0.000307	time 2.4909 (2.2691)	loss 2.6785 (3.4132)	grad_norm 1.6276 (1.8472)	
[2022-01-23 16:50:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][280/1251]	eta 0:36:40 lr 0.000307	time 1.6174 (2.2658)	loss 3.4007 (3.4040)	grad_norm 2.0033 (1.8491)	
[2022-01-23 16:51:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][290/1251]	eta 0:36:17 lr 0.000307	time 2.2841 (2.2661)	loss 2.3973 (3.3987)	grad_norm 1.9556 (1.8480)	
[2022-01-23 16:51:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][300/1251]	eta 0:35:54 lr 0.000307	time 2.5518 (2.2653)	loss 3.8055 (3.3919)	grad_norm 1.8638 (1.8458)	
[2022-01-23 16:51:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][310/1251]	eta 0:35:32 lr 0.000307	time 1.8289 (2.2657)	loss 3.9521 (3.3862)	grad_norm 1.6861 (1.8434)	
[2022-01-23 16:52:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][320/1251]	eta 0:35:09 lr 0.000307	time 1.8539 (2.2657)	loss 3.3708 (3.3828)	grad_norm 1.6707 (1.8425)	
[2022-01-23 16:52:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][330/1251]	eta 0:35:29 lr 0.000307	time 2.1507 (2.3122)	loss 3.7205 (3.3854)	grad_norm 1.7344 (1.8426)	
[2022-01-23 16:53:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][340/1251]	eta 0:34:57 lr 0.000307	time 1.7627 (2.3023)	loss 3.9105 (3.3827)	grad_norm 1.5863 (1.8405)	
[2022-01-23 16:54:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][350/1251]	eta 0:35:34 lr 0.000307	time 1.8090 (2.3686)	loss 3.0536 (3.3804)	grad_norm 1.8334 (1.8394)	
[2022-01-23 16:54:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][360/1251]	eta 0:34:55 lr 0.000307	time 1.8876 (2.3516)	loss 3.6400 (3.3823)	grad_norm 1.6115 (1.8389)	
[2022-01-23 16:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][370/1251]	eta 0:34:21 lr 0.000307	time 1.8663 (2.3401)	loss 3.6708 (3.3820)	grad_norm 2.0158 (1.8416)	
[2022-01-23 16:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][380/1251]	eta 0:33:52 lr 0.000307	time 2.2406 (2.3337)	loss 3.8519 (3.3750)	grad_norm 1.9640 (1.8379)	
[2022-01-23 16:55:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][390/1251]	eta 0:33:26 lr 0.000307	time 2.3171 (2.3301)	loss 3.5450 (3.3823)	grad_norm 1.9563 (1.8408)	
[2022-01-23 16:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][400/1251]	eta 0:32:58 lr 0.000307	time 2.5317 (2.3248)	loss 3.9985 (3.3787)	grad_norm 1.9455 (1.8382)	
[2022-01-23 16:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][410/1251]	eta 0:32:32 lr 0.000307	time 1.8557 (2.3217)	loss 3.5203 (3.3737)	grad_norm 1.9338 (1.8391)	
[2022-01-23 16:56:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][420/1251]	eta 0:32:11 lr 0.000307	time 2.9464 (2.3248)	loss 3.0613 (3.3782)	grad_norm 2.1159 (1.8374)	
[2022-01-23 16:57:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][430/1251]	eta 0:32:02 lr 0.000307	time 2.5690 (2.3413)	loss 3.1470 (3.3731)	grad_norm 1.7513 (1.8361)	
[2022-01-23 16:57:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][440/1251]	eta 0:31:33 lr 0.000307	time 2.5312 (2.3343)	loss 3.1036 (3.3698)	grad_norm 2.0127 (1.8348)	
[2022-01-23 16:57:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][450/1251]	eta 0:31:03 lr 0.000307	time 1.9394 (2.3260)	loss 2.5294 (3.3657)	grad_norm 1.7846 (1.8331)	
[2022-01-23 16:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][460/1251]	eta 0:30:32 lr 0.000307	time 1.8504 (2.3163)	loss 4.2096 (3.3641)	grad_norm 1.9959 (1.8330)	
[2022-01-23 16:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][470/1251]	eta 0:30:04 lr 0.000307	time 1.8630 (2.3109)	loss 4.0414 (3.3658)	grad_norm 1.8908 (1.8340)	
[2022-01-23 16:58:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][480/1251]	eta 0:29:37 lr 0.000307	time 2.0288 (2.3058)	loss 2.6787 (3.3647)	grad_norm 1.9322 (1.8338)	
[2022-01-23 16:59:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][490/1251]	eta 0:29:12 lr 0.000307	time 2.1777 (2.3025)	loss 3.5339 (3.3666)	grad_norm 1.7210 (1.8338)	
[2022-01-23 16:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][500/1251]	eta 0:28:47 lr 0.000307	time 1.5425 (2.3009)	loss 3.5180 (3.3623)	grad_norm 1.5949 (1.8329)	
[2022-01-23 16:59:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][510/1251]	eta 0:28:26 lr 0.000306	time 2.8195 (2.3030)	loss 3.0069 (3.3635)	grad_norm 1.5879 (1.8306)	
[2022-01-23 17:00:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][520/1251]	eta 0:28:01 lr 0.000306	time 1.9685 (2.2998)	loss 2.4013 (3.3624)	grad_norm 1.6783 (1.8297)	
[2022-01-23 17:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][530/1251]	eta 0:27:34 lr 0.000306	time 2.1866 (2.2943)	loss 3.3966 (3.3619)	grad_norm 1.8375 (1.8280)	
[2022-01-23 17:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][540/1251]	eta 0:27:09 lr 0.000306	time 1.5069 (2.2917)	loss 3.0307 (3.3635)	grad_norm 1.7168 (1.8272)	
[2022-01-23 17:01:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][550/1251]	eta 0:26:45 lr 0.000306	time 2.6027 (2.2900)	loss 3.5823 (3.3619)	grad_norm 1.6909 (1.8261)	
[2022-01-23 17:01:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][560/1251]	eta 0:26:21 lr 0.000306	time 2.0148 (2.2884)	loss 2.8554 (3.3576)	grad_norm 2.0390 (1.8261)	
[2022-01-23 17:01:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][570/1251]	eta 0:25:57 lr 0.000306	time 2.3068 (2.2873)	loss 2.8932 (3.3515)	grad_norm 1.9872 (1.8253)	
[2022-01-23 17:02:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][580/1251]	eta 0:25:32 lr 0.000306	time 2.1863 (2.2843)	loss 3.1723 (3.3481)	grad_norm 1.7773 (1.8256)	
[2022-01-23 17:02:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][590/1251]	eta 0:25:06 lr 0.000306	time 1.8870 (2.2794)	loss 3.3151 (3.3467)	grad_norm 1.8605 (1.8254)	
[2022-01-23 17:03:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][600/1251]	eta 0:24:42 lr 0.000306	time 2.1798 (2.2772)	loss 3.9295 (3.3521)	grad_norm 1.7515 (1.8252)	
[2022-01-23 17:03:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][610/1251]	eta 0:24:17 lr 0.000306	time 2.0579 (2.2732)	loss 3.6794 (3.3485)	grad_norm 1.6929 (1.8256)	
[2022-01-23 17:03:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][620/1251]	eta 0:23:53 lr 0.000306	time 2.2049 (2.2719)	loss 2.6780 (3.3491)	grad_norm 1.7949 (1.8267)	
[2022-01-23 17:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][630/1251]	eta 0:23:30 lr 0.000306	time 2.1824 (2.2719)	loss 3.6554 (3.3467)	grad_norm 2.1880 (1.8268)	
[2022-01-23 17:04:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][640/1251]	eta 0:23:08 lr 0.000306	time 1.8800 (2.2724)	loss 3.6878 (3.3435)	grad_norm 1.6949 (1.8259)	
[2022-01-23 17:04:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][650/1251]	eta 0:22:46 lr 0.000306	time 2.3575 (2.2730)	loss 3.0988 (3.3467)	grad_norm 1.9426 (1.8262)	
[2022-01-23 17:05:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][660/1251]	eta 0:22:23 lr 0.000306	time 1.8414 (2.2727)	loss 2.8389 (3.3444)	grad_norm 1.9096 (1.8265)	
[2022-01-23 17:05:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][670/1251]	eta 0:22:01 lr 0.000306	time 1.8649 (2.2751)	loss 2.6705 (3.3424)	grad_norm 1.7891 (1.8280)	
[2022-01-23 17:05:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][680/1251]	eta 0:21:37 lr 0.000306	time 1.6216 (2.2728)	loss 4.0584 (3.3413)	grad_norm 1.9025 (1.8295)	
[2022-01-23 17:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][690/1251]	eta 0:21:13 lr 0.000306	time 1.9361 (2.2693)	loss 4.2683 (3.3424)	grad_norm 2.1057 (1.8321)	
[2022-01-23 17:06:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][700/1251]	eta 0:20:51 lr 0.000306	time 1.9197 (2.2717)	loss 3.7226 (3.3465)	grad_norm 1.7543 (1.8323)	
[2022-01-23 17:07:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][710/1251]	eta 0:20:28 lr 0.000306	time 1.8500 (2.2701)	loss 2.5194 (3.3469)	grad_norm 1.7292 (1.8317)	
[2022-01-23 17:07:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][720/1251]	eta 0:20:03 lr 0.000306	time 1.8658 (2.2668)	loss 3.1651 (3.3489)	grad_norm 1.8188 (1.8314)	
[2022-01-23 17:07:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][730/1251]	eta 0:19:40 lr 0.000306	time 2.6309 (2.2654)	loss 3.5027 (3.3470)	grad_norm 1.8205 (1.8317)	
[2022-01-23 17:08:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][740/1251]	eta 0:19:17 lr 0.000306	time 2.1899 (2.2659)	loss 2.4118 (3.3444)	grad_norm 1.7063 (1.8313)	
[2022-01-23 17:08:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][750/1251]	eta 0:18:55 lr 0.000306	time 2.3033 (2.2663)	loss 3.5562 (3.3448)	grad_norm 1.7399 (1.8304)	
[2022-01-23 17:08:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][760/1251]	eta 0:18:31 lr 0.000306	time 2.2756 (2.2643)	loss 3.2866 (3.3466)	grad_norm 1.6936 (1.8313)	
[2022-01-23 17:09:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][770/1251]	eta 0:18:07 lr 0.000305	time 2.3004 (2.2619)	loss 3.4831 (3.3480)	grad_norm 1.6577 (1.8313)	
[2022-01-23 17:09:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][780/1251]	eta 0:17:44 lr 0.000305	time 1.8457 (2.2593)	loss 3.3071 (3.3507)	grad_norm 1.5493 (1.8308)	
[2022-01-23 17:09:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][790/1251]	eta 0:17:21 lr 0.000305	time 2.0381 (2.2600)	loss 3.6253 (3.3544)	grad_norm 1.6082 (1.8305)	
[2022-01-23 17:10:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][800/1251]	eta 0:16:59 lr 0.000305	time 1.9512 (2.2603)	loss 3.7390 (3.3577)	grad_norm 1.6317 (1.8299)	
[2022-01-23 17:10:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][810/1251]	eta 0:16:36 lr 0.000305	time 1.8713 (2.2593)	loss 3.8328 (3.3544)	grad_norm 1.7057 (1.8299)	
[2022-01-23 17:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][820/1251]	eta 0:16:12 lr 0.000305	time 1.9457 (2.2573)	loss 2.7313 (3.3545)	grad_norm 1.8439 (1.8302)	
[2022-01-23 17:11:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][830/1251]	eta 0:15:51 lr 0.000305	time 1.6783 (2.2590)	loss 3.6973 (3.3557)	grad_norm 1.6739 (1.8295)	
[2022-01-23 17:11:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][840/1251]	eta 0:15:27 lr 0.000305	time 1.9123 (2.2562)	loss 3.7375 (3.3560)	grad_norm 1.5187 (1.8290)	
[2022-01-23 17:12:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][850/1251]	eta 0:15:07 lr 0.000305	time 1.6644 (2.2622)	loss 2.5591 (3.3554)	grad_norm 1.9845 (1.8299)	
[2022-01-23 17:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][860/1251]	eta 0:14:43 lr 0.000305	time 1.8556 (2.2583)	loss 3.9170 (3.3550)	grad_norm 1.5829 (1.8308)	
[2022-01-23 17:13:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][870/1251]	eta 0:14:23 lr 0.000305	time 2.2169 (2.2651)	loss 3.2341 (3.3562)	grad_norm 1.9586 (1.8311)	
[2022-01-23 17:13:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][880/1251]	eta 0:13:58 lr 0.000305	time 1.5819 (2.2601)	loss 3.1085 (3.3566)	grad_norm 1.8970 (1.8312)	
[2022-01-23 17:13:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][890/1251]	eta 0:13:34 lr 0.000305	time 2.2324 (2.2566)	loss 3.6518 (3.3564)	grad_norm 1.7032 (1.8321)	
[2022-01-23 17:14:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][900/1251]	eta 0:13:11 lr 0.000305	time 1.8858 (2.2549)	loss 3.5632 (3.3564)	grad_norm 1.7168 (1.8312)	
[2022-01-23 17:14:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][910/1251]	eta 0:12:48 lr 0.000305	time 2.5157 (2.2542)	loss 2.1413 (3.3564)	grad_norm 1.8500 (1.8303)	
[2022-01-23 17:14:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][920/1251]	eta 0:12:26 lr 0.000305	time 1.8596 (2.2549)	loss 3.7645 (3.3581)	grad_norm 1.9369 (1.8304)	
[2022-01-23 17:15:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][930/1251]	eta 0:12:04 lr 0.000305	time 2.5930 (2.2564)	loss 3.5856 (3.3612)	grad_norm 1.6090 (1.8297)	
[2022-01-23 17:15:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][940/1251]	eta 0:11:41 lr 0.000305	time 2.1865 (2.2559)	loss 3.7050 (3.3645)	grad_norm 1.7008 (1.8297)	
[2022-01-23 17:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][950/1251]	eta 0:11:18 lr 0.000305	time 2.5122 (2.2550)	loss 2.4148 (3.3621)	grad_norm 1.6629 (1.8299)	
[2022-01-23 17:16:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][960/1251]	eta 0:10:59 lr 0.000305	time 2.4359 (2.2652)	loss 3.5454 (3.3610)	grad_norm 1.6882 (1.8286)	
[2022-01-23 17:16:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][970/1251]	eta 0:10:36 lr 0.000305	time 2.1807 (2.2634)	loss 3.5167 (3.3607)	grad_norm 1.8064 (1.8280)	
[2022-01-23 17:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][980/1251]	eta 0:10:12 lr 0.000305	time 1.8363 (2.2599)	loss 3.9939 (3.3604)	grad_norm 2.5635 (1.8284)	
[2022-01-23 17:17:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][990/1251]	eta 0:09:49 lr 0.000305	time 2.5725 (2.2578)	loss 3.8189 (3.3620)	grad_norm 2.2090 (1.8284)	
[2022-01-23 17:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1000/1251]	eta 0:09:26 lr 0.000305	time 2.2452 (2.2559)	loss 3.1702 (3.3601)	grad_norm 1.6577 (1.8272)	
[2022-01-23 17:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1010/1251]	eta 0:09:03 lr 0.000305	time 1.9569 (2.2544)	loss 2.6518 (3.3601)	grad_norm 1.5773 (1.8270)	
[2022-01-23 17:18:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1020/1251]	eta 0:08:40 lr 0.000305	time 2.2416 (2.2532)	loss 3.3935 (3.3597)	grad_norm 1.7924 (1.8260)	
[2022-01-23 17:18:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1030/1251]	eta 0:08:18 lr 0.000305	time 2.4635 (2.2543)	loss 3.7518 (3.3600)	grad_norm 1.5847 (1.8258)	
[2022-01-23 17:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1040/1251]	eta 0:08:08 lr 0.000304	time 2.4936 (2.3136)	loss 4.2148 (3.3566)	grad_norm 1.8802 (1.8250)	
[2022-01-23 17:20:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1050/1251]	eta 0:07:44 lr 0.000304	time 1.8386 (2.3098)	loss 3.0073 (3.3573)	grad_norm 2.0950 (1.8255)	
[2022-01-23 17:20:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1060/1251]	eta 0:07:20 lr 0.000304	time 1.9277 (2.3061)	loss 3.3888 (3.3558)	grad_norm 1.8299 (1.8263)	
[2022-01-23 17:21:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1070/1251]	eta 0:06:56 lr 0.000304	time 1.8575 (2.3024)	loss 2.5680 (3.3570)	grad_norm 1.8555 (1.8265)	
[2022-01-23 17:21:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1080/1251]	eta 0:06:33 lr 0.000304	time 1.9362 (2.2996)	loss 3.4123 (3.3566)	grad_norm 1.9246 (1.8268)	
[2022-01-23 17:21:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1090/1251]	eta 0:06:10 lr 0.000304	time 2.1753 (2.2987)	loss 2.3814 (3.3545)	grad_norm 1.9788 (1.8260)	
[2022-01-23 17:22:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1100/1251]	eta 0:05:46 lr 0.000304	time 2.3522 (2.2976)	loss 3.5415 (3.3563)	grad_norm 1.7020 (1.8252)	
[2022-01-23 17:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1110/1251]	eta 0:05:24 lr 0.000304	time 2.5103 (2.2980)	loss 3.8892 (3.3553)	grad_norm 1.7255 (1.8248)	
[2022-01-23 17:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1120/1251]	eta 0:05:02 lr 0.000304	time 1.7654 (2.3083)	loss 2.1162 (3.3556)	grad_norm 2.0250 (1.8250)	
[2022-01-23 17:23:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1130/1251]	eta 0:04:39 lr 0.000304	time 2.4059 (2.3072)	loss 2.8696 (3.3568)	grad_norm 1.6844 (1.8250)	
[2022-01-23 17:24:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1140/1251]	eta 0:04:15 lr 0.000304	time 1.9405 (2.3039)	loss 2.4369 (3.3588)	grad_norm 1.6167 (1.8255)	
[2022-01-23 17:24:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1150/1251]	eta 0:03:52 lr 0.000304	time 1.8558 (2.3005)	loss 2.6102 (3.3596)	grad_norm 1.9357 (1.8257)	
[2022-01-23 17:24:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1160/1251]	eta 0:03:29 lr 0.000304	time 1.8923 (2.2975)	loss 3.6004 (3.3606)	grad_norm 1.7101 (1.8256)	
[2022-01-23 17:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1170/1251]	eta 0:03:06 lr 0.000304	time 2.2563 (2.2969)	loss 3.0201 (3.3599)	grad_norm 1.5833 (1.8257)	
[2022-01-23 17:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1180/1251]	eta 0:02:42 lr 0.000304	time 2.3476 (2.2950)	loss 3.0917 (3.3622)	grad_norm 1.7322 (1.8254)	
[2022-01-23 17:25:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1190/1251]	eta 0:02:19 lr 0.000304	time 1.8686 (2.2941)	loss 3.8783 (3.3634)	grad_norm 1.8919 (1.8255)	
[2022-01-23 17:26:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1200/1251]	eta 0:01:57 lr 0.000304	time 1.5195 (2.2941)	loss 3.5716 (3.3631)	grad_norm 2.4288 (1.8255)	
[2022-01-23 17:26:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1210/1251]	eta 0:01:34 lr 0.000304	time 2.7552 (2.2950)	loss 3.6000 (3.3634)	grad_norm 1.6985 (1.8251)	
[2022-01-23 17:26:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1220/1251]	eta 0:01:11 lr 0.000304	time 2.4256 (2.2951)	loss 3.9923 (3.3662)	grad_norm 1.7035 (1.8244)	
[2022-01-23 17:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1230/1251]	eta 0:00:48 lr 0.000304	time 1.9963 (2.2946)	loss 3.1824 (3.3633)	grad_norm 1.5773 (1.8235)	
[2022-01-23 17:27:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1240/1251]	eta 0:00:25 lr 0.000304	time 1.4220 (2.2926)	loss 3.5095 (3.3655)	grad_norm 1.7957 (1.8232)	
[2022-01-23 17:27:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [189/300][1250/1251]	eta 0:00:02 lr 0.000304	time 1.2084 (2.2864)	loss 2.6782 (3.3668)	grad_norm 2.0107 (1.8226)	
[2022-01-23 17:27:52 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 189 training takes 0:47:40
[2022-01-23 17:28:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.826 (18.826)	Loss 0.9549 (0.9549)	Acc@1 78.516 (78.516)	Acc@5 93.164 (93.164)	
[2022-01-23 17:28:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.824 (3.566)	Loss 0.9837 (0.9644)	Acc@1 79.199 (77.601)	Acc@5 93.066 (93.865)	
[2022-01-23 17:28:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.960 (2.473)	Loss 0.9903 (0.9653)	Acc@1 75.879 (77.479)	Acc@5 94.336 (94.001)	
[2022-01-23 17:29:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.304 (2.259)	Loss 0.9809 (0.9653)	Acc@1 76.855 (77.441)	Acc@5 94.336 (94.081)	
[2022-01-23 17:29:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.049 (2.183)	Loss 1.0495 (0.9609)	Acc@1 76.270 (77.596)	Acc@5 92.480 (94.069)	
[2022-01-23 17:29:28 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.680 Acc@5 94.194
[2022-01-23 17:29:28 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.7%
[2022-01-23 17:29:28 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 77.87%
[2022-01-23 17:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][0/1251]	eta 7:37:33 lr 0.000304	time 21.9454 (21.9454)	loss 3.1383 (3.1383)	grad_norm 2.1254 (2.1254)	
[2022-01-23 17:30:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][10/1251]	eta 1:25:18 lr 0.000304	time 1.2990 (4.1248)	loss 2.9926 (3.3624)	grad_norm 1.5118 (1.8465)	
[2022-01-23 17:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][20/1251]	eta 1:06:33 lr 0.000304	time 1.5150 (3.2444)	loss 3.5171 (3.3407)	grad_norm 1.7333 (1.8081)	
[2022-01-23 17:30:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][30/1251]	eta 0:58:27 lr 0.000304	time 1.5988 (2.8723)	loss 2.2127 (3.3251)	grad_norm 2.1721 (1.8201)	
[2022-01-23 17:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][40/1251]	eta 0:54:43 lr 0.000304	time 3.2918 (2.7111)	loss 3.0940 (3.3131)	grad_norm 1.6118 (1.7933)	
[2022-01-23 17:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][50/1251]	eta 0:52:54 lr 0.000303	time 1.5079 (2.6432)	loss 3.3769 (3.3525)	grad_norm 1.9347 (1.7962)	
[2022-01-23 17:32:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][60/1251]	eta 0:51:20 lr 0.000303	time 2.3555 (2.5864)	loss 3.1927 (3.3427)	grad_norm 1.6062 (1.8108)	
[2022-01-23 17:32:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][70/1251]	eta 0:49:54 lr 0.000303	time 1.5925 (2.5354)	loss 2.4436 (3.3187)	grad_norm 1.8199 (1.8320)	
[2022-01-23 17:32:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][80/1251]	eta 0:48:59 lr 0.000303	time 2.8655 (2.5105)	loss 4.0031 (3.3260)	grad_norm 2.0446 (1.8287)	
[2022-01-23 17:33:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][90/1251]	eta 0:47:47 lr 0.000303	time 1.9398 (2.4701)	loss 3.8857 (3.3449)	grad_norm 2.2071 (1.8460)	
[2022-01-23 17:33:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][100/1251]	eta 0:46:22 lr 0.000303	time 1.9422 (2.4173)	loss 3.9257 (3.3468)	grad_norm 2.0096 (1.8622)	
[2022-01-23 17:33:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][110/1251]	eta 0:45:30 lr 0.000303	time 2.2722 (2.3931)	loss 3.5387 (3.3582)	grad_norm 1.7470 (1.8577)	
[2022-01-23 17:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][120/1251]	eta 0:44:47 lr 0.000303	time 3.1501 (2.3760)	loss 2.2341 (3.3570)	grad_norm 2.2139 (1.8647)	
[2022-01-23 17:34:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][130/1251]	eta 0:44:04 lr 0.000303	time 1.9655 (2.3589)	loss 3.7387 (3.3753)	grad_norm 1.7805 (1.8571)	
[2022-01-23 17:35:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][140/1251]	eta 0:43:32 lr 0.000303	time 1.4339 (2.3514)	loss 3.8897 (3.3842)	grad_norm 2.1940 (1.8562)	
[2022-01-23 17:35:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][150/1251]	eta 0:43:06 lr 0.000303	time 2.1292 (2.3494)	loss 2.3453 (3.3795)	grad_norm 1.6125 (1.8617)	
[2022-01-23 17:35:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][160/1251]	eta 0:42:38 lr 0.000303	time 2.3848 (2.3450)	loss 3.2749 (3.3737)	grad_norm 1.7966 (1.8597)	
[2022-01-23 17:36:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][170/1251]	eta 0:41:59 lr 0.000303	time 1.5867 (2.3305)	loss 3.8674 (3.3802)	grad_norm 1.9578 (1.8595)	
[2022-01-23 17:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][180/1251]	eta 0:41:21 lr 0.000303	time 1.6198 (2.3174)	loss 3.9506 (3.3749)	grad_norm 2.0370 (1.8562)	
[2022-01-23 17:36:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][190/1251]	eta 0:40:56 lr 0.000303	time 1.9094 (2.3152)	loss 3.4522 (3.3854)	grad_norm 1.7473 (1.8531)	
[2022-01-23 17:37:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][200/1251]	eta 0:40:38 lr 0.000303	time 2.2442 (2.3202)	loss 2.6623 (3.3957)	grad_norm 2.0676 (1.8561)	
[2022-01-23 17:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][210/1251]	eta 0:40:05 lr 0.000303	time 1.8407 (2.3110)	loss 3.4303 (3.3939)	grad_norm 1.6236 (1.8673)	
[2022-01-23 17:37:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][220/1251]	eta 0:39:28 lr 0.000303	time 1.6698 (2.2977)	loss 3.6858 (3.3916)	grad_norm 1.7901 (1.8715)	
[2022-01-23 17:38:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][230/1251]	eta 0:39:05 lr 0.000303	time 1.6879 (2.2972)	loss 3.8169 (3.3854)	grad_norm 1.9974 (1.8715)	
[2022-01-23 17:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][240/1251]	eta 0:38:36 lr 0.000303	time 2.0474 (2.2917)	loss 3.6349 (3.3780)	grad_norm 1.8946 (1.8676)	
[2022-01-23 17:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][250/1251]	eta 0:38:04 lr 0.000303	time 1.9128 (2.2819)	loss 3.4306 (3.3773)	grad_norm 1.7931 (1.8653)	
[2022-01-23 17:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][260/1251]	eta 0:37:29 lr 0.000303	time 2.2378 (2.2702)	loss 3.3213 (3.3703)	grad_norm 1.8720 (1.8641)	
[2022-01-23 17:39:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][270/1251]	eta 0:37:04 lr 0.000303	time 1.6641 (2.2676)	loss 3.3552 (3.3686)	grad_norm 1.5816 (1.8611)	
[2022-01-23 17:40:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][280/1251]	eta 0:36:47 lr 0.000303	time 1.5694 (2.2731)	loss 3.7996 (3.3687)	grad_norm 1.5909 (1.8566)	
[2022-01-23 17:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][290/1251]	eta 0:36:24 lr 0.000303	time 1.9020 (2.2727)	loss 4.0575 (3.3620)	grad_norm 1.9056 (1.8582)	
[2022-01-23 17:40:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][300/1251]	eta 0:35:56 lr 0.000303	time 1.7918 (2.2679)	loss 3.2885 (3.3669)	grad_norm 1.6091 (1.8525)	
[2022-01-23 17:41:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][310/1251]	eta 0:35:30 lr 0.000302	time 1.8051 (2.2642)	loss 3.9237 (3.3656)	grad_norm 1.7845 (1.8483)	
[2022-01-23 17:41:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][320/1251]	eta 0:35:00 lr 0.000302	time 1.8548 (2.2566)	loss 3.3167 (3.3657)	grad_norm 1.5825 (1.8467)	
[2022-01-23 17:41:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][330/1251]	eta 0:34:35 lr 0.000302	time 1.9313 (2.2531)	loss 3.6655 (3.3647)	grad_norm 1.6366 (1.8434)	
[2022-01-23 17:42:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][340/1251]	eta 0:34:16 lr 0.000302	time 2.6590 (2.2572)	loss 3.8517 (3.3685)	grad_norm 1.6933 (1.8430)	
[2022-01-23 17:42:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][350/1251]	eta 0:33:53 lr 0.000302	time 2.2435 (2.2567)	loss 2.7124 (3.3641)	grad_norm 1.7732 (1.8413)	
[2022-01-23 17:43:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][360/1251]	eta 0:33:27 lr 0.000302	time 2.4731 (2.2528)	loss 4.0159 (3.3662)	grad_norm 2.0721 (1.8438)	
[2022-01-23 17:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][370/1251]	eta 0:33:01 lr 0.000302	time 1.9267 (2.2496)	loss 3.5418 (3.3570)	grad_norm 1.8131 (1.8492)	
[2022-01-23 17:43:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][380/1251]	eta 0:32:36 lr 0.000302	time 2.2210 (2.2468)	loss 3.3758 (3.3633)	grad_norm 1.8752 (1.8514)	
[2022-01-23 17:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][390/1251]	eta 0:32:12 lr 0.000302	time 2.3039 (2.2443)	loss 3.4862 (3.3682)	grad_norm 1.7510 (1.8505)	
[2022-01-23 17:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][400/1251]	eta 0:31:44 lr 0.000302	time 1.8582 (2.2382)	loss 3.2023 (3.3658)	grad_norm 1.6934 (1.8480)	
[2022-01-23 17:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][410/1251]	eta 0:31:17 lr 0.000302	time 1.9745 (2.2327)	loss 3.0918 (3.3625)	grad_norm 1.7392 (1.8482)	
[2022-01-23 17:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][420/1251]	eta 0:30:55 lr 0.000302	time 2.9573 (2.2330)	loss 2.7438 (3.3604)	grad_norm 1.6526 (1.8475)	
[2022-01-23 17:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][430/1251]	eta 0:30:33 lr 0.000302	time 2.4348 (2.2327)	loss 3.4672 (3.3598)	grad_norm 1.6609 (1.8476)	
[2022-01-23 17:45:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][440/1251]	eta 0:30:14 lr 0.000302	time 1.9801 (2.2371)	loss 2.7560 (3.3653)	grad_norm 1.7985 (1.8484)	
[2022-01-23 17:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][450/1251]	eta 0:29:54 lr 0.000302	time 2.2645 (2.2398)	loss 3.0090 (3.3677)	grad_norm 1.7815 (1.8472)	
[2022-01-23 17:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][460/1251]	eta 0:29:31 lr 0.000302	time 2.5600 (2.2394)	loss 3.2041 (3.3631)	grad_norm 1.8937 (1.8459)	
[2022-01-23 17:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][470/1251]	eta 0:29:05 lr 0.000302	time 1.5265 (2.2346)	loss 3.8446 (3.3650)	grad_norm 1.9919 (1.8460)	
[2022-01-23 17:47:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][480/1251]	eta 0:28:38 lr 0.000302	time 1.9882 (2.2290)	loss 3.0058 (3.3666)	grad_norm 1.7793 (1.8446)	
[2022-01-23 17:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][490/1251]	eta 0:28:13 lr 0.000302	time 1.6419 (2.2259)	loss 4.1284 (3.3673)	grad_norm 1.9559 (1.8436)	
[2022-01-23 17:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][500/1251]	eta 0:27:49 lr 0.000302	time 2.5496 (2.2227)	loss 3.9966 (3.3747)	grad_norm 2.0490 (1.8444)	
[2022-01-23 17:48:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][510/1251]	eta 0:27:25 lr 0.000302	time 1.8827 (2.2212)	loss 2.3455 (3.3703)	grad_norm 1.8410 (1.8436)	
[2022-01-23 17:48:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][520/1251]	eta 0:27:04 lr 0.000302	time 2.5789 (2.2221)	loss 3.5403 (3.3741)	grad_norm 1.8931 (1.8439)	
[2022-01-23 17:49:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][530/1251]	eta 0:26:42 lr 0.000302	time 2.2264 (2.2224)	loss 2.8000 (3.3748)	grad_norm 1.8366 (1.8437)	
[2022-01-23 17:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][540/1251]	eta 0:26:21 lr 0.000302	time 2.5824 (2.2241)	loss 3.2079 (3.3719)	grad_norm 2.0696 (1.8466)	
[2022-01-23 17:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][550/1251]	eta 0:25:58 lr 0.000302	time 2.3316 (2.2230)	loss 3.0421 (3.3719)	grad_norm 1.9079 (1.8452)	
[2022-01-23 17:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][560/1251]	eta 0:25:35 lr 0.000302	time 1.8156 (2.2226)	loss 3.1374 (3.3682)	grad_norm 1.8182 (1.8448)	
[2022-01-23 17:50:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][570/1251]	eta 0:25:13 lr 0.000302	time 2.3043 (2.2224)	loss 3.7433 (3.3726)	grad_norm 2.4512 (1.8479)	
[2022-01-23 17:50:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][580/1251]	eta 0:24:51 lr 0.000301	time 2.6999 (2.2222)	loss 2.4279 (3.3698)	grad_norm 1.7691 (1.8478)	
[2022-01-23 17:51:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][590/1251]	eta 0:24:30 lr 0.000301	time 2.2687 (2.2241)	loss 2.9258 (3.3678)	grad_norm 2.3056 (1.8475)	
[2022-01-23 17:51:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][600/1251]	eta 0:24:04 lr 0.000301	time 1.5629 (2.2194)	loss 3.3635 (3.3679)	grad_norm 1.6731 (1.8510)	
[2022-01-23 17:52:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][610/1251]	eta 0:23:41 lr 0.000301	time 2.4614 (2.2175)	loss 3.7981 (3.3707)	grad_norm 1.7874 (1.8505)	
[2022-01-23 17:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][620/1251]	eta 0:23:18 lr 0.000301	time 1.9628 (2.2169)	loss 2.6597 (3.3681)	grad_norm 1.8757 (1.8506)	
[2022-01-23 17:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][630/1251]	eta 0:22:57 lr 0.000301	time 1.7185 (2.2175)	loss 3.6714 (3.3725)	grad_norm 2.3903 (1.8517)	
[2022-01-23 17:53:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][640/1251]	eta 0:22:34 lr 0.000301	time 2.1693 (2.2170)	loss 3.0582 (3.3722)	grad_norm 1.8538 (1.8512)	
[2022-01-23 17:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][650/1251]	eta 0:22:12 lr 0.000301	time 2.1581 (2.2178)	loss 4.0153 (3.3745)	grad_norm 2.0230 (1.8506)	
[2022-01-23 17:53:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][660/1251]	eta 0:21:49 lr 0.000301	time 1.9218 (2.2164)	loss 3.4913 (3.3747)	grad_norm 1.8249 (1.8508)	
[2022-01-23 17:54:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][670/1251]	eta 0:21:27 lr 0.000301	time 1.9348 (2.2163)	loss 2.9740 (3.3738)	grad_norm 1.6718 (1.8522)	
[2022-01-23 17:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][680/1251]	eta 0:21:05 lr 0.000301	time 1.9832 (2.2162)	loss 3.9669 (3.3766)	grad_norm 1.6790 (1.8516)	
[2022-01-23 17:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][690/1251]	eta 0:20:43 lr 0.000301	time 2.3866 (2.2160)	loss 3.6188 (3.3759)	grad_norm 1.7517 (1.8506)	
[2022-01-23 17:55:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][700/1251]	eta 0:20:20 lr 0.000301	time 2.1828 (2.2143)	loss 3.9405 (3.3786)	grad_norm 1.7015 (1.8492)	
[2022-01-23 17:55:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][710/1251]	eta 0:19:56 lr 0.000301	time 1.5621 (2.2117)	loss 2.9795 (3.3794)	grad_norm 1.7846 (1.8476)	
[2022-01-23 17:56:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][720/1251]	eta 0:19:33 lr 0.000301	time 1.9173 (2.2101)	loss 3.3351 (3.3749)	grad_norm 1.6720 (1.8471)	
[2022-01-23 17:56:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][730/1251]	eta 0:19:11 lr 0.000301	time 2.5898 (2.2111)	loss 3.5495 (3.3733)	grad_norm 1.6110 (1.8452)	
[2022-01-23 17:56:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][740/1251]	eta 0:18:49 lr 0.000301	time 1.8695 (2.2099)	loss 2.8434 (3.3720)	grad_norm 2.0961 (1.8443)	
[2022-01-23 17:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][750/1251]	eta 0:18:27 lr 0.000301	time 1.7021 (2.2110)	loss 3.7478 (3.3725)	grad_norm 1.7857 (1.8435)	
[2022-01-23 17:57:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][760/1251]	eta 0:18:07 lr 0.000301	time 1.9445 (2.2139)	loss 2.6289 (3.3730)	grad_norm 1.6775 (1.8438)	
[2022-01-23 17:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][770/1251]	eta 0:17:45 lr 0.000301	time 2.5421 (2.2162)	loss 4.0977 (3.3739)	grad_norm 1.6671 (1.8439)	
[2022-01-23 17:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][780/1251]	eta 0:17:23 lr 0.000301	time 1.8521 (2.2149)	loss 3.5333 (3.3738)	grad_norm 1.7587 (1.8436)	
[2022-01-23 17:58:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][790/1251]	eta 0:16:59 lr 0.000301	time 1.9140 (2.2113)	loss 3.7099 (3.3740)	grad_norm 1.6076 (1.8424)	
[2022-01-23 17:58:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][800/1251]	eta 0:16:35 lr 0.000301	time 2.2206 (2.2081)	loss 3.2652 (3.3747)	grad_norm 1.8383 (1.8425)	
[2022-01-23 17:59:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][810/1251]	eta 0:16:12 lr 0.000301	time 2.3940 (2.2060)	loss 4.2467 (3.3738)	grad_norm 1.7042 (1.8412)	
[2022-01-23 17:59:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][820/1251]	eta 0:15:50 lr 0.000301	time 2.7413 (2.2059)	loss 3.7448 (3.3761)	grad_norm 1.8182 (1.8411)	
[2022-01-23 18:00:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][830/1251]	eta 0:15:28 lr 0.000301	time 1.6183 (2.2051)	loss 3.9117 (3.3768)	grad_norm 1.8460 (1.8402)	
[2022-01-23 18:00:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][840/1251]	eta 0:15:06 lr 0.000300	time 1.6186 (2.2046)	loss 3.5544 (3.3757)	grad_norm 1.8914 (1.8397)	
[2022-01-23 18:00:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][850/1251]	eta 0:14:44 lr 0.000300	time 2.7869 (2.2062)	loss 3.5020 (3.3746)	grad_norm 1.6702 (1.8387)	
[2022-01-23 18:01:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][860/1251]	eta 0:14:23 lr 0.000300	time 2.8704 (2.2089)	loss 3.7380 (3.3735)	grad_norm 1.6063 (1.8369)	
[2022-01-23 18:01:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][870/1251]	eta 0:14:01 lr 0.000300	time 1.8905 (2.2087)	loss 3.4155 (3.3753)	grad_norm 2.0178 (1.8358)	
[2022-01-23 18:01:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][880/1251]	eta 0:13:39 lr 0.000300	time 2.2075 (2.2085)	loss 4.0730 (3.3735)	grad_norm 1.8866 (1.8349)	
[2022-01-23 18:02:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][890/1251]	eta 0:13:17 lr 0.000300	time 3.2807 (2.2089)	loss 3.4151 (3.3729)	grad_norm 2.3383 (1.8354)	
[2022-01-23 18:02:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][900/1251]	eta 0:12:54 lr 0.000300	time 1.8186 (2.2069)	loss 2.3468 (3.3744)	grad_norm 1.7401 (1.8347)	
[2022-01-23 18:02:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][910/1251]	eta 0:12:32 lr 0.000300	time 1.6610 (2.2064)	loss 3.2489 (3.3743)	grad_norm 1.9308 (1.8345)	
[2022-01-23 18:03:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][920/1251]	eta 0:12:10 lr 0.000300	time 2.4554 (2.2062)	loss 3.2366 (3.3733)	grad_norm 1.7891 (1.8349)	
[2022-01-23 18:03:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][930/1251]	eta 0:11:48 lr 0.000300	time 2.1501 (2.2058)	loss 3.4858 (3.3731)	grad_norm 1.7034 (1.8354)	
[2022-01-23 18:04:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][940/1251]	eta 0:11:25 lr 0.000300	time 2.3414 (2.2052)	loss 3.5399 (3.3734)	grad_norm 1.6646 (1.8349)	
[2022-01-23 18:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][950/1251]	eta 0:11:04 lr 0.000300	time 3.1741 (2.2066)	loss 2.7668 (3.3710)	grad_norm 1.8461 (1.8356)	
[2022-01-23 18:04:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][960/1251]	eta 0:10:42 lr 0.000300	time 2.7235 (2.2075)	loss 3.6432 (3.3718)	grad_norm 2.0325 (1.8360)	
[2022-01-23 18:05:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][970/1251]	eta 0:10:20 lr 0.000300	time 2.4361 (2.2070)	loss 2.4492 (3.3725)	grad_norm 1.7171 (1.8365)	
[2022-01-23 18:05:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][980/1251]	eta 0:09:58 lr 0.000300	time 2.2183 (2.2069)	loss 3.1374 (3.3727)	grad_norm 1.6288 (1.8363)	
[2022-01-23 18:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][990/1251]	eta 0:09:36 lr 0.000300	time 3.0229 (2.2076)	loss 3.7245 (3.3754)	grad_norm 2.0784 (1.8373)	
[2022-01-23 18:06:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1000/1251]	eta 0:09:14 lr 0.000300	time 2.0329 (2.2072)	loss 3.7223 (3.3736)	grad_norm 1.9223 (1.8378)	
[2022-01-23 18:06:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1010/1251]	eta 0:08:51 lr 0.000300	time 2.1553 (2.2059)	loss 2.3889 (3.3723)	grad_norm 1.8186 (1.8378)	
[2022-01-23 18:07:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1020/1251]	eta 0:08:29 lr 0.000300	time 1.9880 (2.2058)	loss 2.2412 (3.3705)	grad_norm 1.5972 (1.8373)	
[2022-01-23 18:07:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1030/1251]	eta 0:08:07 lr 0.000300	time 2.6196 (2.2062)	loss 3.7927 (3.3704)	grad_norm 2.0953 (1.8366)	
[2022-01-23 18:07:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1040/1251]	eta 0:07:45 lr 0.000300	time 2.2662 (2.2068)	loss 2.8182 (3.3711)	grad_norm 2.0310 (1.8371)	
[2022-01-23 18:08:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1050/1251]	eta 0:07:23 lr 0.000300	time 1.8532 (2.2068)	loss 4.2689 (3.3735)	grad_norm 1.8010 (1.8368)	
[2022-01-23 18:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1060/1251]	eta 0:07:01 lr 0.000300	time 1.8318 (2.2069)	loss 3.2977 (3.3758)	grad_norm 1.8473 (1.8364)	
[2022-01-23 18:08:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1070/1251]	eta 0:06:39 lr 0.000300	time 1.6804 (2.2059)	loss 3.3132 (3.3759)	grad_norm 1.8014 (1.8365)	
[2022-01-23 18:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1080/1251]	eta 0:06:16 lr 0.000300	time 1.6195 (2.2045)	loss 3.7189 (3.3757)	grad_norm 1.7033 (1.8362)	
[2022-01-23 18:09:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1090/1251]	eta 0:05:54 lr 0.000300	time 1.8554 (2.2046)	loss 2.4892 (3.3770)	grad_norm 1.6664 (1.8350)	
[2022-01-23 18:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1100/1251]	eta 0:05:32 lr 0.000300	time 1.9580 (2.2044)	loss 3.9329 (3.3786)	grad_norm 1.8703 (1.8346)	
[2022-01-23 18:10:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1110/1251]	eta 0:05:10 lr 0.000299	time 2.2397 (2.2029)	loss 3.5164 (3.3801)	grad_norm 1.7731 (1.8343)	
[2022-01-23 18:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1120/1251]	eta 0:04:48 lr 0.000299	time 2.4807 (2.2024)	loss 3.8269 (3.3792)	grad_norm 2.1421 (1.8341)	
[2022-01-23 18:10:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1130/1251]	eta 0:04:26 lr 0.000299	time 2.4756 (2.2026)	loss 4.1917 (3.3765)	grad_norm 1.5199 (1.8339)	
[2022-01-23 18:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1140/1251]	eta 0:04:04 lr 0.000299	time 3.8403 (2.2064)	loss 3.6590 (3.3754)	grad_norm 1.7023 (1.8332)	
[2022-01-23 18:11:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1150/1251]	eta 0:03:43 lr 0.000299	time 2.2061 (2.2080)	loss 3.6325 (3.3746)	grad_norm 1.6112 (1.8330)	
[2022-01-23 18:12:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1160/1251]	eta 0:03:20 lr 0.000299	time 2.8492 (2.2076)	loss 2.3595 (3.3761)	grad_norm 1.6636 (1.8321)	
[2022-01-23 18:12:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1170/1251]	eta 0:02:58 lr 0.000299	time 1.9263 (2.2069)	loss 3.8280 (3.3763)	grad_norm 1.6980 (1.8317)	
[2022-01-23 18:12:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1180/1251]	eta 0:02:36 lr 0.000299	time 2.1983 (2.2056)	loss 2.4491 (3.3764)	grad_norm 1.8279 (1.8308)	
[2022-01-23 18:13:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1190/1251]	eta 0:02:14 lr 0.000299	time 2.2181 (2.2039)	loss 3.2428 (3.3772)	grad_norm 1.5479 (1.8313)	
[2022-01-23 18:13:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1200/1251]	eta 0:01:52 lr 0.000299	time 2.2213 (2.2031)	loss 2.2845 (3.3739)	grad_norm 1.7633 (1.8317)	
[2022-01-23 18:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1210/1251]	eta 0:01:30 lr 0.000299	time 2.2768 (2.2037)	loss 3.3964 (3.3705)	grad_norm 1.7321 (1.8326)	
[2022-01-23 18:14:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1220/1251]	eta 0:01:08 lr 0.000299	time 1.8830 (2.2036)	loss 3.8331 (3.3727)	grad_norm 1.9688 (1.8321)	
[2022-01-23 18:14:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1230/1251]	eta 0:00:46 lr 0.000299	time 2.5299 (2.2043)	loss 2.2160 (3.3724)	grad_norm 1.7140 (1.8310)	
[2022-01-23 18:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1240/1251]	eta 0:00:24 lr 0.000299	time 2.2699 (2.2053)	loss 2.8925 (3.3738)	grad_norm 1.7368 (1.8306)	
[2022-01-23 18:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [190/300][1250/1251]	eta 0:00:02 lr 0.000299	time 1.2057 (2.1997)	loss 2.1907 (3.3722)	grad_norm 1.9260 (1.8304)	
[2022-01-23 18:15:21 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 190 training takes 0:45:52
[2022-01-23 18:15:21 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_190 saving......
[2022-01-23 18:15:33 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_190 saved !!!
[2022-01-23 18:15:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.534 (16.534)	Loss 0.9682 (0.9682)	Acc@1 78.516 (78.516)	Acc@5 93.652 (93.652)	
[2022-01-23 18:16:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.313 (2.799)	Loss 0.9405 (0.9425)	Acc@1 78.027 (78.205)	Acc@5 94.434 (94.363)	
[2022-01-23 18:16:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.030 (2.255)	Loss 0.9343 (0.9412)	Acc@1 76.270 (78.125)	Acc@5 93.945 (94.262)	
[2022-01-23 18:16:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.412 (2.086)	Loss 0.9553 (0.9470)	Acc@1 79.395 (78.046)	Acc@5 94.141 (94.150)	
[2022-01-23 18:16:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.086 (2.054)	Loss 0.9349 (0.9450)	Acc@1 77.734 (78.011)	Acc@5 94.629 (94.210)	
[2022-01-23 18:17:04 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.020 Acc@5 94.248
[2022-01-23 18:17:04 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.0%
[2022-01-23 18:17:04 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.02%
[2022-01-23 18:17:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][0/1251]	eta 7:32:12 lr 0.000299	time 21.6889 (21.6889)	loss 3.6249 (3.6249)	grad_norm 1.8185 (1.8185)	
[2022-01-23 18:17:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][10/1251]	eta 1:22:19 lr 0.000299	time 1.7117 (3.9805)	loss 3.4358 (3.2552)	grad_norm 1.8209 (1.8331)	
[2022-01-23 18:18:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][20/1251]	eta 1:03:12 lr 0.000299	time 1.4741 (3.0808)	loss 2.4294 (3.1984)	grad_norm 1.5543 (1.7824)	
[2022-01-23 18:18:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][30/1251]	eta 0:58:16 lr 0.000299	time 1.9582 (2.8638)	loss 3.0219 (3.1885)	grad_norm 1.8393 (1.7599)	
[2022-01-23 18:18:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][40/1251]	eta 0:54:37 lr 0.000299	time 3.6029 (2.7065)	loss 3.0138 (3.2045)	grad_norm 1.7280 (1.7629)	
[2022-01-23 18:19:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][50/1251]	eta 0:52:10 lr 0.000299	time 1.8355 (2.6068)	loss 3.4303 (3.2880)	grad_norm 1.4803 (1.7587)	
[2022-01-23 18:19:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][60/1251]	eta 0:49:47 lr 0.000299	time 1.5893 (2.5083)	loss 3.5533 (3.3340)	grad_norm 1.8147 (1.7886)	
[2022-01-23 18:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][70/1251]	eta 0:48:50 lr 0.000299	time 2.2943 (2.4812)	loss 3.3774 (3.3437)	grad_norm 1.6929 (1.7844)	
[2022-01-23 18:20:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][80/1251]	eta 0:48:11 lr 0.000299	time 3.5694 (2.4692)	loss 3.5880 (3.3373)	grad_norm 2.1785 (1.7997)	
[2022-01-23 18:20:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][90/1251]	eta 0:47:06 lr 0.000299	time 1.5557 (2.4347)	loss 3.2518 (3.3218)	grad_norm 1.8852 (1.8048)	
[2022-01-23 18:21:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][100/1251]	eta 0:46:09 lr 0.000299	time 2.2861 (2.4066)	loss 3.6018 (3.3381)	grad_norm 1.7558 (1.8069)	
[2022-01-23 18:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][110/1251]	eta 0:45:23 lr 0.000299	time 1.9733 (2.3872)	loss 3.9036 (3.3506)	grad_norm 1.7253 (1.7997)	
[2022-01-23 18:21:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][120/1251]	eta 0:44:51 lr 0.000298	time 4.0806 (2.3800)	loss 3.7137 (3.3439)	grad_norm 1.7518 (1.7928)	
[2022-01-23 18:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][130/1251]	eta 0:44:10 lr 0.000298	time 1.5605 (2.3642)	loss 3.4294 (3.3437)	grad_norm 1.7979 (1.7933)	
[2022-01-23 18:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][140/1251]	eta 0:43:24 lr 0.000298	time 1.8703 (2.3440)	loss 3.8730 (3.3435)	grad_norm 1.7596 (1.7948)	
[2022-01-23 18:22:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][150/1251]	eta 0:42:45 lr 0.000298	time 1.8690 (2.3298)	loss 3.9265 (3.3568)	grad_norm 1.8100 (1.7988)	
[2022-01-23 18:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][160/1251]	eta 0:42:17 lr 0.000298	time 3.0882 (2.3258)	loss 4.0176 (3.3719)	grad_norm 1.6393 (1.8006)	
[2022-01-23 18:23:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][170/1251]	eta 0:41:48 lr 0.000298	time 1.7862 (2.3207)	loss 3.8527 (3.3749)	grad_norm 2.0639 (1.8059)	
[2022-01-23 18:24:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][180/1251]	eta 0:41:15 lr 0.000298	time 1.5485 (2.3113)	loss 3.0341 (3.3702)	grad_norm 1.5785 (1.8038)	
[2022-01-23 18:24:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][190/1251]	eta 0:40:47 lr 0.000298	time 1.8840 (2.3067)	loss 3.7983 (3.3648)	grad_norm 1.9311 (1.8048)	
[2022-01-23 18:24:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][200/1251]	eta 0:40:13 lr 0.000298	time 2.7882 (2.2963)	loss 3.5414 (3.3691)	grad_norm 1.7089 (1.8128)	
[2022-01-23 18:25:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][210/1251]	eta 0:39:46 lr 0.000298	time 1.8976 (2.2924)	loss 3.1502 (3.3780)	grad_norm 1.8895 (1.8146)	
[2022-01-23 18:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][220/1251]	eta 0:39:23 lr 0.000298	time 1.8345 (2.2921)	loss 3.4158 (3.3733)	grad_norm 2.0892 (1.8158)	
[2022-01-23 18:25:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][230/1251]	eta 0:38:57 lr 0.000298	time 1.9095 (2.2895)	loss 3.0577 (3.3770)	grad_norm 1.8273 (1.8115)	
[2022-01-23 18:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][240/1251]	eta 0:38:25 lr 0.000298	time 1.9177 (2.2801)	loss 2.9435 (3.3693)	grad_norm 2.0087 (1.8136)	
[2022-01-23 18:26:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][250/1251]	eta 0:37:58 lr 0.000298	time 3.2461 (2.2761)	loss 3.9794 (3.3624)	grad_norm 1.9182 (1.8254)	
[2022-01-23 18:26:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][260/1251]	eta 0:37:22 lr 0.000298	time 1.9700 (2.2628)	loss 3.3030 (3.3649)	grad_norm 1.7463 (1.8244)	
[2022-01-23 18:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][270/1251]	eta 0:36:55 lr 0.000298	time 2.1281 (2.2582)	loss 3.0191 (3.3633)	grad_norm 1.7014 (1.8264)	
[2022-01-23 18:27:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][280/1251]	eta 0:36:31 lr 0.000298	time 1.9168 (2.2570)	loss 3.9318 (3.3725)	grad_norm 1.9593 (1.8321)	
[2022-01-23 18:28:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][290/1251]	eta 0:36:18 lr 0.000298	time 3.6370 (2.2670)	loss 3.7658 (3.3801)	grad_norm 2.0059 (1.8302)	
[2022-01-23 18:28:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][300/1251]	eta 0:35:55 lr 0.000298	time 1.8238 (2.2668)	loss 3.1738 (3.3784)	grad_norm 1.5817 (1.8285)	
[2022-01-23 18:28:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][310/1251]	eta 0:35:26 lr 0.000298	time 1.7997 (2.2601)	loss 3.1470 (3.3818)	grad_norm 1.9456 (1.8308)	
[2022-01-23 18:29:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][320/1251]	eta 0:34:54 lr 0.000298	time 1.9124 (2.2497)	loss 4.0368 (3.3907)	grad_norm 1.7303 (1.8315)	
[2022-01-23 18:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][330/1251]	eta 0:34:29 lr 0.000298	time 2.5355 (2.2465)	loss 4.0358 (3.3965)	grad_norm 1.6508 (1.8318)	
[2022-01-23 18:29:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][340/1251]	eta 0:34:02 lr 0.000298	time 1.6779 (2.2417)	loss 4.1486 (3.3969)	grad_norm 1.7781 (1.8324)	
[2022-01-23 18:30:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][350/1251]	eta 0:33:37 lr 0.000298	time 1.6142 (2.2395)	loss 4.0676 (3.3974)	grad_norm 2.1885 (1.8321)	
[2022-01-23 18:30:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][360/1251]	eta 0:33:14 lr 0.000298	time 2.1773 (2.2389)	loss 2.8157 (3.4022)	grad_norm 1.7615 (1.8357)	
[2022-01-23 18:30:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][370/1251]	eta 0:32:55 lr 0.000298	time 3.2261 (2.2423)	loss 2.8142 (3.4023)	grad_norm 1.8095 (1.8400)	
[2022-01-23 18:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][380/1251]	eta 0:32:34 lr 0.000298	time 2.7060 (2.2440)	loss 3.8335 (3.4116)	grad_norm 1.8750 (1.8426)	
[2022-01-23 18:31:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][390/1251]	eta 0:32:09 lr 0.000297	time 1.8572 (2.2410)	loss 3.8366 (3.4036)	grad_norm 1.7365 (1.8423)	
[2022-01-23 18:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][400/1251]	eta 0:31:46 lr 0.000297	time 2.2211 (2.2403)	loss 3.9953 (3.4024)	grad_norm 1.7883 (1.8433)	
[2022-01-23 18:32:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][410/1251]	eta 0:31:22 lr 0.000297	time 2.4786 (2.2384)	loss 3.1940 (3.4039)	grad_norm 1.7929 (1.8425)	
[2022-01-23 18:32:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][420/1251]	eta 0:30:58 lr 0.000297	time 3.0235 (2.2362)	loss 2.7151 (3.4018)	grad_norm 1.7383 (1.8425)	
[2022-01-23 18:33:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][430/1251]	eta 0:30:31 lr 0.000297	time 1.9220 (2.2311)	loss 3.6993 (3.4037)	grad_norm 1.7149 (1.8421)	
[2022-01-23 18:33:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][440/1251]	eta 0:30:08 lr 0.000297	time 1.9446 (2.2297)	loss 3.3442 (3.3992)	grad_norm 1.6925 (1.8382)	
[2022-01-23 18:33:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][450/1251]	eta 0:29:43 lr 0.000297	time 2.4858 (2.2272)	loss 3.7359 (3.3927)	grad_norm 1.7120 (1.8365)	
[2022-01-23 18:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][460/1251]	eta 0:29:19 lr 0.000297	time 1.9934 (2.2250)	loss 3.4824 (3.3899)	grad_norm 1.8453 (1.8373)	
[2022-01-23 18:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][470/1251]	eta 0:28:56 lr 0.000297	time 1.9066 (2.2240)	loss 3.0104 (3.3934)	grad_norm 1.7574 (1.8357)	
[2022-01-23 18:34:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][480/1251]	eta 0:28:36 lr 0.000297	time 2.8029 (2.2267)	loss 3.5068 (3.3888)	grad_norm 1.6455 (1.8338)	
[2022-01-23 18:35:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][490/1251]	eta 0:28:14 lr 0.000297	time 2.7406 (2.2268)	loss 3.6135 (3.3907)	grad_norm 1.8712 (1.8355)	
[2022-01-23 18:35:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][500/1251]	eta 0:27:51 lr 0.000297	time 1.9059 (2.2257)	loss 3.8278 (3.3925)	grad_norm 1.8431 (1.8362)	
[2022-01-23 18:36:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][510/1251]	eta 0:27:27 lr 0.000297	time 1.8019 (2.2237)	loss 3.9739 (3.3953)	grad_norm 1.5828 (1.8357)	
[2022-01-23 18:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][520/1251]	eta 0:27:05 lr 0.000297	time 2.6510 (2.2241)	loss 4.2123 (3.3957)	grad_norm 1.8174 (1.8354)	
[2022-01-23 18:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][530/1251]	eta 0:26:44 lr 0.000297	time 2.2246 (2.2252)	loss 3.9560 (3.3962)	grad_norm 1.5293 (1.8353)	
[2022-01-23 18:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][540/1251]	eta 0:26:23 lr 0.000297	time 1.8442 (2.2275)	loss 3.3012 (3.3977)	grad_norm 1.6825 (1.8356)	
[2022-01-23 18:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][550/1251]	eta 0:26:00 lr 0.000297	time 1.7714 (2.2261)	loss 3.7772 (3.4017)	grad_norm 1.8608 (1.8361)	
[2022-01-23 18:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][560/1251]	eta 0:25:37 lr 0.000297	time 1.8466 (2.2254)	loss 2.2796 (3.3982)	grad_norm 1.8727 (1.8358)	
[2022-01-23 18:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][570/1251]	eta 0:25:14 lr 0.000297	time 2.3885 (2.2237)	loss 4.1794 (3.3990)	grad_norm 2.1894 (1.8348)	
[2022-01-23 18:38:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][580/1251]	eta 0:24:50 lr 0.000297	time 1.6227 (2.2218)	loss 3.6550 (3.3981)	grad_norm 1.8694 (1.8340)	
[2022-01-23 18:38:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][590/1251]	eta 0:24:27 lr 0.000297	time 2.2399 (2.2199)	loss 4.0065 (3.4006)	grad_norm 1.8744 (1.8341)	
[2022-01-23 18:39:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][600/1251]	eta 0:24:04 lr 0.000297	time 2.2440 (2.2195)	loss 3.7626 (3.4039)	grad_norm 2.0778 (1.8370)	
[2022-01-23 18:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][610/1251]	eta 0:23:43 lr 0.000297	time 2.6713 (2.2207)	loss 3.6821 (3.4022)	grad_norm 2.0981 (1.8369)	
[2022-01-23 18:40:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][620/1251]	eta 0:23:20 lr 0.000297	time 2.1658 (2.2190)	loss 3.7443 (3.3995)	grad_norm 1.7395 (1.8381)	
[2022-01-23 18:40:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][630/1251]	eta 0:22:56 lr 0.000297	time 1.6421 (2.2164)	loss 2.7701 (3.4035)	grad_norm 1.6794 (1.8372)	
[2022-01-23 18:40:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][640/1251]	eta 0:22:36 lr 0.000297	time 3.2662 (2.2204)	loss 3.5545 (3.3993)	grad_norm 1.8178 (1.8370)	
[2022-01-23 18:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][650/1251]	eta 0:22:14 lr 0.000296	time 1.4604 (2.2199)	loss 3.7429 (3.3971)	grad_norm 1.6363 (1.8360)	
[2022-01-23 18:41:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][660/1251]	eta 0:21:53 lr 0.000296	time 1.6345 (2.2224)	loss 2.5662 (3.3964)	grad_norm 2.0497 (1.8351)	
[2022-01-23 18:41:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][670/1251]	eta 0:21:30 lr 0.000296	time 1.6541 (2.2206)	loss 3.5257 (3.3955)	grad_norm 1.9555 (1.8348)	
[2022-01-23 18:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][680/1251]	eta 0:21:08 lr 0.000296	time 2.9916 (2.2208)	loss 3.2892 (3.3953)	grad_norm 1.8217 (1.8349)	
[2022-01-23 18:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][690/1251]	eta 0:20:44 lr 0.000296	time 1.9349 (2.2179)	loss 3.6803 (3.3945)	grad_norm 1.7357 (1.8334)	
[2022-01-23 18:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][700/1251]	eta 0:20:20 lr 0.000296	time 1.7247 (2.2154)	loss 2.5223 (3.3955)	grad_norm 1.8829 (1.8326)	
[2022-01-23 18:43:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][710/1251]	eta 0:19:58 lr 0.000296	time 1.8234 (2.2151)	loss 2.3900 (3.3938)	grad_norm 1.7697 (1.8336)	
[2022-01-23 18:43:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][720/1251]	eta 0:19:37 lr 0.000296	time 2.7427 (2.2173)	loss 2.9697 (3.3931)	grad_norm 1.6298 (1.8325)	
[2022-01-23 18:44:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][730/1251]	eta 0:19:14 lr 0.000296	time 1.8141 (2.2159)	loss 3.2450 (3.3941)	grad_norm 1.9571 (1.8318)	
[2022-01-23 18:44:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][740/1251]	eta 0:18:52 lr 0.000296	time 2.6550 (2.2170)	loss 3.4016 (3.3933)	grad_norm 1.8479 (1.8324)	
[2022-01-23 18:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][750/1251]	eta 0:18:30 lr 0.000296	time 1.5067 (2.2161)	loss 3.5890 (3.3964)	grad_norm 1.7029 (1.8328)	
[2022-01-23 18:45:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][760/1251]	eta 0:18:09 lr 0.000296	time 2.9997 (2.2180)	loss 3.4256 (3.3961)	grad_norm 1.7634 (1.8324)	
[2022-01-23 18:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][770/1251]	eta 0:17:45 lr 0.000296	time 1.8129 (2.2153)	loss 3.6645 (3.3982)	grad_norm 1.6305 (1.8325)	
[2022-01-23 18:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][780/1251]	eta 0:17:21 lr 0.000296	time 1.8190 (2.2115)	loss 3.6932 (3.3978)	grad_norm 1.8236 (1.8325)	
[2022-01-23 18:46:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][790/1251]	eta 0:16:59 lr 0.000296	time 1.8360 (2.2112)	loss 3.3848 (3.3976)	grad_norm 1.7497 (1.8319)	
[2022-01-23 18:46:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][800/1251]	eta 0:16:36 lr 0.000296	time 2.3411 (2.2104)	loss 3.3797 (3.3983)	grad_norm 1.5286 (1.8321)	
[2022-01-23 18:46:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][810/1251]	eta 0:16:15 lr 0.000296	time 2.0842 (2.2114)	loss 3.5967 (3.3957)	grad_norm 1.6717 (1.8323)	
[2022-01-23 18:47:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][820/1251]	eta 0:15:53 lr 0.000296	time 2.5305 (2.2115)	loss 3.8116 (3.3947)	grad_norm 1.7501 (1.8332)	
[2022-01-23 18:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][830/1251]	eta 0:15:30 lr 0.000296	time 2.2218 (2.2102)	loss 3.8657 (3.3941)	grad_norm 1.8075 (1.8327)	
[2022-01-23 18:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][840/1251]	eta 0:15:08 lr 0.000296	time 2.4930 (2.2109)	loss 3.6744 (3.3944)	grad_norm 1.7249 (1.8331)	
[2022-01-23 18:48:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][850/1251]	eta 0:14:46 lr 0.000296	time 1.9247 (2.2107)	loss 3.5240 (3.3970)	grad_norm 1.5987 (1.8330)	
[2022-01-23 18:48:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][860/1251]	eta 0:14:24 lr 0.000296	time 1.9310 (2.2109)	loss 3.0729 (3.3958)	grad_norm 1.5878 (1.8327)	
[2022-01-23 18:49:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][870/1251]	eta 0:14:02 lr 0.000296	time 2.1823 (2.2109)	loss 3.6570 (3.3934)	grad_norm 1.8647 (1.8339)	
[2022-01-23 18:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][880/1251]	eta 0:13:39 lr 0.000296	time 2.7583 (2.2101)	loss 3.6422 (3.3953)	grad_norm 1.7323 (1.8346)	
[2022-01-23 18:49:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][890/1251]	eta 0:13:16 lr 0.000296	time 1.9124 (2.2071)	loss 2.4235 (3.3947)	grad_norm 1.8898 (1.8342)	
[2022-01-23 18:50:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][900/1251]	eta 0:12:53 lr 0.000296	time 1.9633 (2.2049)	loss 3.4646 (3.3921)	grad_norm 1.6277 (1.8339)	
[2022-01-23 18:50:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][910/1251]	eta 0:12:31 lr 0.000296	time 1.9217 (2.2040)	loss 2.8046 (3.3872)	grad_norm 1.8425 (1.8336)	
[2022-01-23 18:50:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][920/1251]	eta 0:12:09 lr 0.000295	time 2.8114 (2.2042)	loss 3.3867 (3.3828)	grad_norm 2.0207 (1.8334)	
[2022-01-23 18:51:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][930/1251]	eta 0:11:48 lr 0.000295	time 2.0966 (2.2059)	loss 3.0783 (3.3830)	grad_norm 1.7454 (1.8325)	
[2022-01-23 18:51:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][940/1251]	eta 0:11:26 lr 0.000295	time 1.5588 (2.2061)	loss 3.4201 (3.3821)	grad_norm 1.8795 (1.8330)	
[2022-01-23 18:52:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][950/1251]	eta 0:11:04 lr 0.000295	time 2.2065 (2.2079)	loss 3.1351 (3.3817)	grad_norm 1.7287 (1.8344)	
[2022-01-23 18:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][960/1251]	eta 0:10:42 lr 0.000295	time 2.0169 (2.2070)	loss 3.1357 (3.3808)	grad_norm 1.7420 (1.8347)	
[2022-01-23 18:52:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][970/1251]	eta 0:10:19 lr 0.000295	time 2.2614 (2.2060)	loss 3.7594 (3.3800)	grad_norm 1.9581 (1.8342)	
[2022-01-23 18:53:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][980/1251]	eta 0:09:57 lr 0.000295	time 2.0295 (2.2060)	loss 3.5655 (3.3805)	grad_norm 1.6728 (1.8344)	
[2022-01-23 18:53:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][990/1251]	eta 0:09:35 lr 0.000295	time 1.6066 (2.2043)	loss 3.4323 (3.3786)	grad_norm 1.8785 (1.8338)	
[2022-01-23 18:53:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1000/1251]	eta 0:09:13 lr 0.000295	time 1.7616 (2.2035)	loss 3.6649 (3.3755)	grad_norm 2.1458 (1.8329)	
[2022-01-23 18:54:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1010/1251]	eta 0:08:51 lr 0.000295	time 1.8739 (2.2048)	loss 4.2212 (3.3772)	grad_norm 1.8824 (1.8339)	
[2022-01-23 18:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1020/1251]	eta 0:08:29 lr 0.000295	time 1.6723 (2.2051)	loss 1.8628 (3.3761)	grad_norm 1.5812 (1.8338)	
[2022-01-23 18:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1030/1251]	eta 0:08:07 lr 0.000295	time 1.4817 (2.2046)	loss 3.0688 (3.3744)	grad_norm 2.0948 (1.8342)	
[2022-01-23 18:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1040/1251]	eta 0:07:45 lr 0.000295	time 1.5655 (2.2048)	loss 2.7463 (3.3753)	grad_norm 2.1567 (1.8351)	
[2022-01-23 18:55:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1050/1251]	eta 0:07:23 lr 0.000295	time 1.6685 (2.2044)	loss 3.7452 (3.3746)	grad_norm 1.8836 (1.8360)	
[2022-01-23 18:56:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1060/1251]	eta 0:07:00 lr 0.000295	time 1.9257 (2.2032)	loss 3.0628 (3.3748)	grad_norm 1.8119 (1.8352)	
[2022-01-23 18:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1070/1251]	eta 0:06:38 lr 0.000295	time 1.7159 (2.2023)	loss 2.8482 (3.3748)	grad_norm 1.6560 (1.8345)	
[2022-01-23 18:56:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1080/1251]	eta 0:06:16 lr 0.000295	time 2.2028 (2.2022)	loss 4.1331 (3.3769)	grad_norm 2.0105 (1.8348)	
[2022-01-23 18:57:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1090/1251]	eta 0:05:54 lr 0.000295	time 2.7872 (2.2028)	loss 3.4832 (3.3763)	grad_norm 2.0901 (1.8342)	
[2022-01-23 18:57:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1100/1251]	eta 0:05:32 lr 0.000295	time 1.6346 (2.2024)	loss 2.8945 (3.3779)	grad_norm 1.6518 (1.8337)	
[2022-01-23 18:57:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1110/1251]	eta 0:05:10 lr 0.000295	time 2.1835 (2.2025)	loss 3.5659 (3.3753)	grad_norm 2.0034 (1.8335)	
[2022-01-23 18:58:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1120/1251]	eta 0:04:48 lr 0.000295	time 1.9320 (2.2031)	loss 3.8095 (3.3776)	grad_norm 1.9635 (1.8337)	
[2022-01-23 18:58:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1130/1251]	eta 0:04:26 lr 0.000295	time 2.2421 (2.2037)	loss 3.4142 (3.3787)	grad_norm 1.9918 (1.8347)	
[2022-01-23 18:58:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1140/1251]	eta 0:04:04 lr 0.000295	time 1.8276 (2.2032)	loss 3.6847 (3.3800)	grad_norm 2.1217 (1.8347)	
[2022-01-23 18:59:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1150/1251]	eta 0:03:42 lr 0.000295	time 2.2689 (2.2021)	loss 3.3204 (3.3791)	grad_norm 1.8846 (1.8353)	
[2022-01-23 18:59:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1160/1251]	eta 0:03:20 lr 0.000295	time 2.5280 (2.2008)	loss 2.8887 (3.3793)	grad_norm 1.7237 (1.8345)	
[2022-01-23 19:00:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1170/1251]	eta 0:02:58 lr 0.000295	time 2.0958 (2.2000)	loss 3.3215 (3.3787)	grad_norm 2.0159 (1.8354)	
[2022-01-23 19:00:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1180/1251]	eta 0:02:36 lr 0.000295	time 2.4488 (2.2002)	loss 3.6126 (3.3799)	grad_norm 1.8685 (1.8362)	
[2022-01-23 19:00:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1190/1251]	eta 0:02:14 lr 0.000294	time 2.4120 (2.2010)	loss 2.1349 (3.3796)	grad_norm 1.8441 (1.8360)	
[2022-01-23 19:01:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1200/1251]	eta 0:01:52 lr 0.000294	time 2.2653 (2.2012)	loss 1.9975 (3.3785)	grad_norm 1.5530 (1.8352)	
[2022-01-23 19:01:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1210/1251]	eta 0:01:30 lr 0.000294	time 3.3623 (2.2032)	loss 2.7064 (3.3773)	grad_norm 1.8936 (1.8357)	
[2022-01-23 19:01:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1220/1251]	eta 0:01:08 lr 0.000294	time 2.8908 (2.2037)	loss 2.9271 (3.3753)	grad_norm 1.8086 (1.8356)	
[2022-01-23 19:02:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1230/1251]	eta 0:00:46 lr 0.000294	time 1.6481 (2.2029)	loss 3.2060 (3.3756)	grad_norm 1.6637 (1.8365)	
[2022-01-23 19:02:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1240/1251]	eta 0:00:24 lr 0.000294	time 1.4797 (2.2007)	loss 3.4943 (3.3749)	grad_norm 2.0888 (1.8368)	
[2022-01-23 19:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [191/300][1250/1251]	eta 0:00:02 lr 0.000294	time 1.2345 (2.1941)	loss 3.7519 (3.3763)	grad_norm 1.7069 (1.8364)	
[2022-01-23 19:02:49 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 191 training takes 0:45:45
[2022-01-23 19:03:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.744 (18.744)	Loss 0.9147 (0.9147)	Acc@1 78.027 (78.027)	Acc@5 94.141 (94.141)	
[2022-01-23 19:03:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.866 (3.290)	Loss 0.9481 (0.9343)	Acc@1 77.441 (77.868)	Acc@5 94.922 (94.371)	
[2022-01-23 19:03:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.506 (2.579)	Loss 0.9388 (0.9366)	Acc@1 77.637 (77.860)	Acc@5 93.750 (94.266)	
[2022-01-23 19:04:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.277 (2.276)	Loss 0.9425 (0.9394)	Acc@1 76.855 (77.816)	Acc@5 94.043 (94.172)	
[2022-01-23 19:04:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.195 (2.181)	Loss 0.9793 (0.9380)	Acc@1 76.953 (77.911)	Acc@5 93.848 (94.167)	
[2022-01-23 19:04:25 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 77.904 Acc@5 94.210
[2022-01-23 19:04:25 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 77.9%
[2022-01-23 19:04:25 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.02%
[2022-01-23 19:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][0/1251]	eta 7:32:34 lr 0.000294	time 21.7066 (21.7066)	loss 2.1244 (2.1244)	grad_norm 2.2493 (2.2493)	
[2022-01-23 19:05:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][10/1251]	eta 1:22:59 lr 0.000294	time 1.9739 (4.0123)	loss 3.2323 (3.3059)	grad_norm 1.9857 (1.8966)	
[2022-01-23 19:05:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][20/1251]	eta 1:06:37 lr 0.000294	time 2.5196 (3.2470)	loss 3.4869 (3.4845)	grad_norm 1.5572 (1.8727)	
[2022-01-23 19:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][30/1251]	eta 0:59:39 lr 0.000294	time 1.7798 (2.9319)	loss 3.6903 (3.4102)	grad_norm 1.7833 (1.8847)	
[2022-01-23 19:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][40/1251]	eta 0:56:06 lr 0.000294	time 3.8113 (2.7797)	loss 2.7183 (3.3611)	grad_norm 1.6797 (1.8769)	
[2022-01-23 19:06:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][50/1251]	eta 0:53:48 lr 0.000294	time 2.3124 (2.6884)	loss 3.2996 (3.3151)	grad_norm 2.0039 (1.8915)	
[2022-01-23 19:07:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][60/1251]	eta 0:51:29 lr 0.000294	time 2.4923 (2.5943)	loss 3.6149 (3.3628)	grad_norm 1.7155 (1.8818)	
[2022-01-23 19:07:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][70/1251]	eta 0:48:56 lr 0.000294	time 1.9261 (2.4864)	loss 3.4950 (3.3639)	grad_norm 1.7129 (1.8757)	
[2022-01-23 19:07:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][80/1251]	eta 0:47:33 lr 0.000294	time 2.6251 (2.4364)	loss 3.7967 (3.3729)	grad_norm 1.7667 (1.8748)	
[2022-01-23 19:08:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][90/1251]	eta 0:46:40 lr 0.000294	time 1.8413 (2.4124)	loss 3.7013 (3.3757)	grad_norm 2.1551 (1.8710)	
[2022-01-23 19:08:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][100/1251]	eta 0:45:47 lr 0.000294	time 1.9239 (2.3871)	loss 3.9462 (3.3921)	grad_norm 1.9749 (1.8775)	
[2022-01-23 19:08:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][110/1251]	eta 0:45:09 lr 0.000294	time 2.9468 (2.3745)	loss 2.5795 (3.3838)	grad_norm 1.9776 (1.8896)	
[2022-01-23 19:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][120/1251]	eta 0:44:32 lr 0.000294	time 2.1766 (2.3629)	loss 2.6883 (3.3572)	grad_norm 2.0904 (1.8845)	
[2022-01-23 19:09:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][130/1251]	eta 0:44:08 lr 0.000294	time 3.1261 (2.3626)	loss 3.4427 (3.3681)	grad_norm 2.0230 (1.9010)	
[2022-01-23 19:09:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][140/1251]	eta 0:43:37 lr 0.000294	time 2.1331 (2.3563)	loss 2.7257 (3.3633)	grad_norm 2.1850 (1.8975)	
[2022-01-23 19:10:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][150/1251]	eta 0:43:15 lr 0.000294	time 2.8283 (2.3578)	loss 2.2102 (3.3485)	grad_norm 1.5468 (1.8954)	
[2022-01-23 19:10:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][160/1251]	eta 0:42:32 lr 0.000294	time 1.6330 (2.3398)	loss 3.7145 (3.3542)	grad_norm 1.6584 (1.8926)	
[2022-01-23 19:11:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][170/1251]	eta 0:41:47 lr 0.000294	time 1.7066 (2.3196)	loss 3.6954 (3.3581)	grad_norm 1.7443 (1.8993)	
[2022-01-23 19:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][180/1251]	eta 0:41:08 lr 0.000294	time 2.0880 (2.3048)	loss 3.1249 (3.3584)	grad_norm 1.7507 (1.8907)	
[2022-01-23 19:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][190/1251]	eta 0:40:35 lr 0.000294	time 2.2465 (2.2958)	loss 2.5435 (3.3533)	grad_norm 1.7248 (1.8873)	
[2022-01-23 19:12:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][200/1251]	eta 0:40:03 lr 0.000293	time 1.5536 (2.2873)	loss 3.7467 (3.3538)	grad_norm 1.6117 (1.8809)	
[2022-01-23 19:12:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][210/1251]	eta 0:39:44 lr 0.000293	time 2.4260 (2.2907)	loss 3.8735 (3.3491)	grad_norm 1.7203 (1.8784)	
[2022-01-23 19:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][220/1251]	eta 0:39:24 lr 0.000293	time 2.2879 (2.2935)	loss 3.1629 (3.3504)	grad_norm 1.8086 (1.8758)	
[2022-01-23 19:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][230/1251]	eta 0:39:00 lr 0.000293	time 2.2584 (2.2927)	loss 4.0144 (3.3601)	grad_norm 1.8486 (1.8745)	
[2022-01-23 19:13:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][240/1251]	eta 0:38:35 lr 0.000293	time 1.9224 (2.2907)	loss 3.3852 (3.3627)	grad_norm 2.0180 (1.8762)	
[2022-01-23 19:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][250/1251]	eta 0:38:04 lr 0.000293	time 1.6786 (2.2822)	loss 3.6071 (3.3686)	grad_norm 1.8446 (1.8733)	
[2022-01-23 19:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][260/1251]	eta 0:37:29 lr 0.000293	time 1.9522 (2.2696)	loss 4.1580 (3.3633)	grad_norm 1.7637 (1.8753)	
[2022-01-23 19:14:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][270/1251]	eta 0:36:58 lr 0.000293	time 2.1878 (2.2610)	loss 2.3943 (3.3592)	grad_norm 1.6049 (1.8759)	
[2022-01-23 19:15:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][280/1251]	eta 0:36:33 lr 0.000293	time 2.3279 (2.2589)	loss 2.7100 (3.3476)	grad_norm 1.6333 (1.8736)	
[2022-01-23 19:15:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][290/1251]	eta 0:36:07 lr 0.000293	time 1.8312 (2.2556)	loss 3.1988 (3.3498)	grad_norm 1.9073 (1.8746)	
[2022-01-23 19:15:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][300/1251]	eta 0:35:44 lr 0.000293	time 2.1170 (2.2553)	loss 2.6596 (3.3513)	grad_norm 1.7479 (1.8756)	
[2022-01-23 19:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][310/1251]	eta 0:35:24 lr 0.000293	time 1.8590 (2.2581)	loss 3.2820 (3.3471)	grad_norm 1.7619 (1.8742)	
[2022-01-23 19:16:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][320/1251]	eta 0:35:00 lr 0.000293	time 2.5142 (2.2567)	loss 4.1016 (3.3474)	grad_norm 1.9785 (1.8740)	
[2022-01-23 19:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][330/1251]	eta 0:34:35 lr 0.000293	time 1.8358 (2.2537)	loss 3.6523 (3.3516)	grad_norm 2.2640 (1.8757)	
[2022-01-23 19:17:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][340/1251]	eta 0:34:04 lr 0.000293	time 1.6558 (2.2445)	loss 3.6164 (3.3537)	grad_norm 1.8390 (1.8758)	
[2022-01-23 19:17:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][350/1251]	eta 0:33:40 lr 0.000293	time 2.4513 (2.2422)	loss 3.4995 (3.3466)	grad_norm 1.6989 (1.8721)	
[2022-01-23 19:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][360/1251]	eta 0:33:16 lr 0.000293	time 2.7287 (2.2413)	loss 2.0974 (3.3469)	grad_norm 1.7908 (1.8709)	
[2022-01-23 19:18:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][370/1251]	eta 0:32:53 lr 0.000293	time 2.2093 (2.2397)	loss 4.2504 (3.3474)	grad_norm 1.9503 (1.8699)	
[2022-01-23 19:18:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][380/1251]	eta 0:32:31 lr 0.000293	time 1.8826 (2.2406)	loss 3.2945 (3.3515)	grad_norm 2.1772 (1.8751)	
[2022-01-23 19:19:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][390/1251]	eta 0:32:08 lr 0.000293	time 1.9404 (2.2394)	loss 3.7116 (3.3516)	grad_norm 2.1973 (1.8769)	
[2022-01-23 19:19:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][400/1251]	eta 0:31:47 lr 0.000293	time 2.6303 (2.2413)	loss 3.8373 (3.3558)	grad_norm 1.6559 (1.8772)	
[2022-01-23 19:19:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][410/1251]	eta 0:31:22 lr 0.000293	time 1.7444 (2.2390)	loss 3.6742 (3.3522)	grad_norm 1.6942 (1.8779)	
[2022-01-23 19:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][420/1251]	eta 0:30:58 lr 0.000293	time 2.1633 (2.2361)	loss 2.5106 (3.3557)	grad_norm 1.6415 (1.8787)	
[2022-01-23 19:20:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][430/1251]	eta 0:30:33 lr 0.000293	time 2.0351 (2.2333)	loss 2.8656 (3.3552)	grad_norm 1.7564 (1.8781)	
[2022-01-23 19:20:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][440/1251]	eta 0:30:06 lr 0.000293	time 1.9012 (2.2274)	loss 3.3838 (3.3616)	grad_norm 1.9715 (1.8788)	
[2022-01-23 19:21:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][450/1251]	eta 0:29:44 lr 0.000293	time 2.2857 (2.2276)	loss 4.0317 (3.3550)	grad_norm 1.8298 (1.8800)	
[2022-01-23 19:21:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][460/1251]	eta 0:29:22 lr 0.000293	time 1.8645 (2.2276)	loss 3.7135 (3.3553)	grad_norm 2.3238 (1.8808)	
[2022-01-23 19:21:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][470/1251]	eta 0:29:00 lr 0.000292	time 2.4787 (2.2281)	loss 2.3918 (3.3568)	grad_norm 2.0823 (1.8810)	
[2022-01-23 19:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][480/1251]	eta 0:28:36 lr 0.000292	time 1.9818 (2.2261)	loss 3.5618 (3.3595)	grad_norm 1.7879 (1.8824)	
[2022-01-23 19:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][490/1251]	eta 0:28:14 lr 0.000292	time 2.2067 (2.2265)	loss 3.9298 (3.3560)	grad_norm 2.0049 (1.8832)	
[2022-01-23 19:23:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][500/1251]	eta 0:27:52 lr 0.000292	time 2.5369 (2.2270)	loss 3.7621 (3.3568)	grad_norm 1.9409 (1.8839)	
[2022-01-23 19:23:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][510/1251]	eta 0:27:30 lr 0.000292	time 2.9016 (2.2277)	loss 3.4890 (3.3551)	grad_norm 1.7821 (1.8850)	
[2022-01-23 19:23:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][520/1251]	eta 0:27:07 lr 0.000292	time 2.0620 (2.2258)	loss 3.6595 (3.3594)	grad_norm 1.7639 (1.8838)	
[2022-01-23 19:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][530/1251]	eta 0:26:42 lr 0.000292	time 1.6320 (2.2231)	loss 3.0063 (3.3582)	grad_norm 1.8375 (1.8848)	
[2022-01-23 19:24:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][540/1251]	eta 0:26:18 lr 0.000292	time 2.1221 (2.2204)	loss 4.0252 (3.3630)	grad_norm 1.6722 (1.8842)	
[2022-01-23 19:24:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][550/1251]	eta 0:25:55 lr 0.000292	time 1.9555 (2.2185)	loss 3.7144 (3.3606)	grad_norm 1.7908 (1.8849)	
[2022-01-23 19:25:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][560/1251]	eta 0:25:32 lr 0.000292	time 2.2385 (2.2180)	loss 2.3165 (3.3598)	grad_norm 1.9159 (1.8844)	
[2022-01-23 19:25:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][570/1251]	eta 0:25:11 lr 0.000292	time 1.8732 (2.2192)	loss 2.5902 (3.3566)	grad_norm 2.3087 (1.8840)	
[2022-01-23 19:25:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][580/1251]	eta 0:24:49 lr 0.000292	time 2.5278 (2.2198)	loss 2.8764 (3.3562)	grad_norm 1.6635 (1.8873)	
[2022-01-23 19:26:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][590/1251]	eta 0:24:27 lr 0.000292	time 2.1567 (2.2196)	loss 3.4247 (3.3560)	grad_norm 1.8078 (1.8904)	
[2022-01-23 19:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][600/1251]	eta 0:24:04 lr 0.000292	time 2.2757 (2.2186)	loss 4.0333 (3.3595)	grad_norm 1.7154 (1.8941)	
[2022-01-23 19:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][610/1251]	eta 0:23:43 lr 0.000292	time 1.8799 (2.2205)	loss 3.7321 (3.3601)	grad_norm 2.0051 (1.8937)	
[2022-01-23 19:27:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][620/1251]	eta 0:23:20 lr 0.000292	time 2.2919 (2.2190)	loss 3.2662 (3.3570)	grad_norm 1.9418 (1.8934)	
[2022-01-23 19:27:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][630/1251]	eta 0:22:55 lr 0.000292	time 1.7852 (2.2155)	loss 3.3759 (3.3568)	grad_norm 1.9708 (1.8917)	
[2022-01-23 19:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][640/1251]	eta 0:22:33 lr 0.000292	time 2.1686 (2.2150)	loss 3.8824 (3.3587)	grad_norm 1.7319 (1.8896)	
[2022-01-23 19:28:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][650/1251]	eta 0:22:12 lr 0.000292	time 1.9850 (2.2164)	loss 2.3524 (3.3563)	grad_norm 1.8132 (1.8879)	
[2022-01-23 19:28:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][660/1251]	eta 0:21:49 lr 0.000292	time 2.2495 (2.2154)	loss 3.2249 (3.3575)	grad_norm 1.7203 (1.8854)	
[2022-01-23 19:29:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][670/1251]	eta 0:21:27 lr 0.000292	time 1.6070 (2.2153)	loss 3.1845 (3.3596)	grad_norm 1.7268 (1.8847)	
[2022-01-23 19:29:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][680/1251]	eta 0:21:04 lr 0.000292	time 1.8790 (2.2148)	loss 2.7361 (3.3603)	grad_norm 1.8782 (1.8841)	
[2022-01-23 19:29:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][690/1251]	eta 0:20:43 lr 0.000292	time 2.4683 (2.2174)	loss 3.3554 (3.3587)	grad_norm 1.7060 (1.8820)	
[2022-01-23 19:30:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][700/1251]	eta 0:20:21 lr 0.000292	time 1.9283 (2.2165)	loss 2.8035 (3.3583)	grad_norm 2.0417 (1.8815)	
[2022-01-23 19:30:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][710/1251]	eta 0:19:58 lr 0.000292	time 1.6579 (2.2146)	loss 3.2976 (3.3609)	grad_norm 1.6826 (1.8828)	
[2022-01-23 19:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][720/1251]	eta 0:19:35 lr 0.000292	time 2.1671 (2.2137)	loss 2.7922 (3.3580)	grad_norm 1.8352 (1.8822)	
[2022-01-23 19:31:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][730/1251]	eta 0:19:13 lr 0.000292	time 1.9264 (2.2143)	loss 2.9778 (3.3586)	grad_norm 1.9125 (1.8831)	
[2022-01-23 19:31:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][740/1251]	eta 0:18:51 lr 0.000291	time 2.2873 (2.2139)	loss 4.0021 (3.3579)	grad_norm 1.7602 (1.8838)	
[2022-01-23 19:32:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][750/1251]	eta 0:18:28 lr 0.000291	time 1.8134 (2.2124)	loss 3.3680 (3.3593)	grad_norm 1.5891 (1.8829)	
[2022-01-23 19:32:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][760/1251]	eta 0:18:05 lr 0.000291	time 2.0938 (2.2110)	loss 3.6464 (3.3598)	grad_norm 2.0363 (1.8811)	
[2022-01-23 19:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][770/1251]	eta 0:17:43 lr 0.000291	time 2.2347 (2.2100)	loss 3.7747 (3.3599)	grad_norm 1.6813 (1.8799)	
[2022-01-23 19:33:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][780/1251]	eta 0:17:19 lr 0.000291	time 2.0760 (2.2073)	loss 3.9686 (3.3611)	grad_norm 1.7268 (1.8796)	
[2022-01-23 19:33:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][790/1251]	eta 0:16:56 lr 0.000291	time 2.0081 (2.2055)	loss 3.6625 (3.3636)	grad_norm 1.5583 (1.8788)	
[2022-01-23 19:33:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][800/1251]	eta 0:16:34 lr 0.000291	time 2.5596 (2.2052)	loss 2.9714 (3.3642)	grad_norm 1.8211 (1.8778)	
[2022-01-23 19:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][810/1251]	eta 0:16:12 lr 0.000291	time 2.4941 (2.2059)	loss 3.6934 (3.3669)	grad_norm 1.8720 (1.8766)	
[2022-01-23 19:34:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][820/1251]	eta 0:15:50 lr 0.000291	time 2.1675 (2.2061)	loss 3.7860 (3.3676)	grad_norm 2.3988 (1.8774)	
[2022-01-23 19:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][830/1251]	eta 0:15:28 lr 0.000291	time 2.1965 (2.2061)	loss 4.0155 (3.3731)	grad_norm 1.9468 (1.8758)	
[2022-01-23 19:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][840/1251]	eta 0:15:06 lr 0.000291	time 2.2502 (2.2053)	loss 3.4203 (3.3757)	grad_norm 1.7049 (1.8740)	
[2022-01-23 19:35:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][850/1251]	eta 0:14:44 lr 0.000291	time 2.7515 (2.2058)	loss 3.6723 (3.3768)	grad_norm 1.6985 (1.8723)	
[2022-01-23 19:36:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][860/1251]	eta 0:14:22 lr 0.000291	time 2.0777 (2.2059)	loss 3.0221 (3.3765)	grad_norm 1.9278 (1.8715)	
[2022-01-23 19:36:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][870/1251]	eta 0:14:00 lr 0.000291	time 1.9262 (2.2062)	loss 3.0568 (3.3777)	grad_norm 1.7029 (1.8728)	
[2022-01-23 19:36:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][880/1251]	eta 0:13:38 lr 0.000291	time 2.1234 (2.2072)	loss 4.0166 (3.3767)	grad_norm 1.9167 (1.8748)	
[2022-01-23 19:37:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][890/1251]	eta 0:13:17 lr 0.000291	time 2.8485 (2.2087)	loss 2.1810 (3.3775)	grad_norm 1.7196 (1.8748)	
[2022-01-23 19:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][900/1251]	eta 0:12:54 lr 0.000291	time 1.6714 (2.2074)	loss 3.8410 (3.3796)	grad_norm 1.6947 (1.8763)	
[2022-01-23 19:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][910/1251]	eta 0:12:32 lr 0.000291	time 1.9205 (2.2063)	loss 2.7692 (3.3815)	grad_norm 1.7510 (1.8756)	
[2022-01-23 19:38:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][920/1251]	eta 0:12:10 lr 0.000291	time 1.6491 (2.2062)	loss 4.1021 (3.3827)	grad_norm 1.6300 (1.8750)	
[2022-01-23 19:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][930/1251]	eta 0:11:48 lr 0.000291	time 3.3544 (2.2076)	loss 3.5513 (3.3840)	grad_norm 1.6232 (1.8738)	
[2022-01-23 19:39:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][940/1251]	eta 0:11:26 lr 0.000291	time 1.7007 (2.2070)	loss 3.3770 (3.3825)	grad_norm 2.0517 (1.8736)	
[2022-01-23 19:39:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][950/1251]	eta 0:11:03 lr 0.000291	time 1.8121 (2.2054)	loss 3.1174 (3.3816)	grad_norm 1.8917 (1.8745)	
[2022-01-23 19:39:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][960/1251]	eta 0:10:40 lr 0.000291	time 2.1998 (2.2023)	loss 3.1096 (3.3804)	grad_norm 1.9036 (1.8754)	
[2022-01-23 19:40:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][970/1251]	eta 0:10:18 lr 0.000291	time 3.1092 (2.2019)	loss 3.8210 (3.3787)	grad_norm 1.7241 (1.8750)	
[2022-01-23 19:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][980/1251]	eta 0:09:56 lr 0.000291	time 2.1029 (2.2015)	loss 3.7812 (3.3797)	grad_norm 1.7694 (1.8740)	
[2022-01-23 19:40:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][990/1251]	eta 0:09:34 lr 0.000291	time 2.6219 (2.2025)	loss 3.5691 (3.3784)	grad_norm 1.9731 (1.8748)	
[2022-01-23 19:41:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1000/1251]	eta 0:09:13 lr 0.000290	time 2.0983 (2.2037)	loss 3.3879 (3.3772)	grad_norm 1.5346 (1.8743)	
[2022-01-23 19:41:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1010/1251]	eta 0:08:51 lr 0.000290	time 3.4147 (2.2057)	loss 3.9638 (3.3780)	grad_norm 1.9768 (1.8738)	
[2022-01-23 19:41:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1020/1251]	eta 0:08:29 lr 0.000290	time 2.1035 (2.2053)	loss 2.3421 (3.3785)	grad_norm 1.7478 (1.8738)	
[2022-01-23 19:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1030/1251]	eta 0:08:07 lr 0.000290	time 1.7531 (2.2038)	loss 2.4414 (3.3787)	grad_norm 1.9567 (1.8734)	
[2022-01-23 19:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1040/1251]	eta 0:07:44 lr 0.000290	time 1.5303 (2.2016)	loss 3.7985 (3.3803)	grad_norm 2.3757 (1.8737)	
[2022-01-23 19:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1050/1251]	eta 0:07:22 lr 0.000290	time 3.1612 (2.2021)	loss 3.5555 (3.3780)	grad_norm 1.6507 (1.8730)	
[2022-01-23 19:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1060/1251]	eta 0:07:00 lr 0.000290	time 1.9530 (2.2018)	loss 3.1624 (3.3735)	grad_norm 2.1848 (1.8737)	
[2022-01-23 19:43:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1070/1251]	eta 0:06:38 lr 0.000290	time 2.5760 (2.2025)	loss 3.2523 (3.3756)	grad_norm 2.0318 (1.8738)	
[2022-01-23 19:44:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1080/1251]	eta 0:06:16 lr 0.000290	time 2.0795 (2.2014)	loss 3.4864 (3.3755)	grad_norm 2.1400 (1.8735)	
[2022-01-23 19:44:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1090/1251]	eta 0:05:54 lr 0.000290	time 2.3186 (2.2009)	loss 3.8093 (3.3757)	grad_norm 1.8952 (1.8730)	
[2022-01-23 19:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1100/1251]	eta 0:05:32 lr 0.000290	time 2.4664 (2.2005)	loss 3.5715 (3.3757)	grad_norm 1.7336 (1.8724)	
[2022-01-23 19:45:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1110/1251]	eta 0:05:10 lr 0.000290	time 2.2080 (2.2004)	loss 3.5410 (3.3769)	grad_norm 1.8387 (1.8706)	
[2022-01-23 19:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1120/1251]	eta 0:04:48 lr 0.000290	time 1.5274 (2.2001)	loss 2.9346 (3.3776)	grad_norm 1.8624 (1.8697)	
[2022-01-23 19:45:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1130/1251]	eta 0:04:26 lr 0.000290	time 2.2462 (2.2002)	loss 3.7413 (3.3758)	grad_norm 1.8013 (1.8699)	
[2022-01-23 19:46:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1140/1251]	eta 0:04:04 lr 0.000290	time 2.7918 (2.2011)	loss 3.4204 (3.3781)	grad_norm 1.6432 (1.8694)	
[2022-01-23 19:46:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1150/1251]	eta 0:03:42 lr 0.000290	time 2.6976 (2.2022)	loss 4.2174 (3.3773)	grad_norm 1.9478 (1.8701)	
[2022-01-23 19:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1160/1251]	eta 0:03:20 lr 0.000290	time 1.8210 (2.2031)	loss 2.7917 (3.3777)	grad_norm 2.0153 (1.8700)	
[2022-01-23 19:47:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1170/1251]	eta 0:02:58 lr 0.000290	time 2.1666 (2.2018)	loss 2.9557 (3.3784)	grad_norm 1.7722 (1.8707)	
[2022-01-23 19:47:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1180/1251]	eta 0:02:36 lr 0.000290	time 1.9645 (2.1993)	loss 3.6132 (3.3798)	grad_norm 1.5924 (1.8703)	
[2022-01-23 19:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1190/1251]	eta 0:02:14 lr 0.000290	time 1.9402 (2.1972)	loss 3.2959 (3.3788)	grad_norm 1.8404 (1.8697)	
[2022-01-23 19:48:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1200/1251]	eta 0:01:51 lr 0.000290	time 2.2139 (2.1960)	loss 2.3750 (3.3771)	grad_norm 1.7937 (1.8697)	
[2022-01-23 19:48:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1210/1251]	eta 0:01:30 lr 0.000290	time 2.6194 (2.1964)	loss 3.7694 (3.3776)	grad_norm 2.2341 (1.8700)	
[2022-01-23 19:49:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1220/1251]	eta 0:01:08 lr 0.000290	time 2.4267 (2.1972)	loss 3.8258 (3.3784)	grad_norm 2.1820 (1.8703)	
[2022-01-23 19:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1230/1251]	eta 0:00:46 lr 0.000290	time 1.8620 (2.1978)	loss 3.2658 (3.3780)	grad_norm 1.8123 (1.8704)	
[2022-01-23 19:49:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1240/1251]	eta 0:00:24 lr 0.000290	time 1.7500 (2.1974)	loss 3.3584 (3.3786)	grad_norm 2.0705 (1.8703)	
[2022-01-23 19:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [192/300][1250/1251]	eta 0:00:02 lr 0.000290	time 1.1953 (2.1928)	loss 3.2575 (3.3778)	grad_norm 1.9375 (1.8700)	
[2022-01-23 19:50:09 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 192 training takes 0:45:43
[2022-01-23 19:50:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.236 (18.236)	Loss 0.9165 (0.9165)	Acc@1 80.273 (80.273)	Acc@5 93.848 (93.848)	
[2022-01-23 19:50:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.223 (3.441)	Loss 0.8985 (0.9165)	Acc@1 78.906 (78.587)	Acc@5 94.727 (94.478)	
[2022-01-23 19:51:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.975 (2.503)	Loss 0.9402 (0.9258)	Acc@1 77.246 (78.199)	Acc@5 93.457 (94.303)	
[2022-01-23 19:51:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.312 (2.227)	Loss 0.9180 (0.9218)	Acc@1 77.637 (78.317)	Acc@5 94.727 (94.330)	
[2022-01-23 19:51:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.221 (2.163)	Loss 0.9344 (0.9231)	Acc@1 78.711 (78.332)	Acc@5 93.457 (94.281)	
[2022-01-23 19:51:45 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.214 Acc@5 94.300
[2022-01-23 19:51:45 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.2%
[2022-01-23 19:51:45 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.21%
[2022-01-23 19:52:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][0/1251]	eta 6:58:03 lr 0.000290	time 20.0511 (20.0511)	loss 3.8971 (3.8971)	grad_norm 2.0842 (2.0842)	
[2022-01-23 19:52:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][10/1251]	eta 1:22:02 lr 0.000290	time 2.3017 (3.9669)	loss 3.6525 (3.3419)	grad_norm 1.5482 (1.9188)	
[2022-01-23 19:52:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][20/1251]	eta 1:04:19 lr 0.000289	time 1.5114 (3.1355)	loss 3.3322 (3.3222)	grad_norm 1.9105 (1.8818)	
[2022-01-23 19:53:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][30/1251]	eta 0:59:14 lr 0.000289	time 1.5847 (2.9108)	loss 4.1578 (3.3426)	grad_norm 2.1350 (1.8779)	
[2022-01-23 19:53:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][40/1251]	eta 0:54:25 lr 0.000289	time 2.6475 (2.6963)	loss 4.0792 (3.4078)	grad_norm 1.8222 (1.8634)	
[2022-01-23 19:54:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][50/1251]	eta 0:53:15 lr 0.000289	time 3.4587 (2.6607)	loss 3.7039 (3.4238)	grad_norm 1.8194 (1.8611)	
[2022-01-23 19:54:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][60/1251]	eta 0:51:27 lr 0.000289	time 1.3425 (2.5924)	loss 3.2181 (3.4184)	grad_norm 1.7235 (1.8463)	
[2022-01-23 19:54:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][70/1251]	eta 0:49:52 lr 0.000289	time 1.6928 (2.5341)	loss 3.2714 (3.3662)	grad_norm 1.7589 (1.8556)	
[2022-01-23 19:55:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][80/1251]	eta 0:48:38 lr 0.000289	time 2.4816 (2.4925)	loss 4.1967 (3.3870)	grad_norm 1.9461 (1.8585)	
[2022-01-23 19:55:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][90/1251]	eta 0:47:36 lr 0.000289	time 2.8772 (2.4600)	loss 3.2036 (3.3861)	grad_norm 1.7693 (1.8633)	
[2022-01-23 19:55:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][100/1251]	eta 0:46:31 lr 0.000289	time 1.5915 (2.4257)	loss 3.1096 (3.3835)	grad_norm 1.9559 (1.8578)	
[2022-01-23 19:56:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][110/1251]	eta 0:45:29 lr 0.000289	time 1.8702 (2.3918)	loss 3.2860 (3.3915)	grad_norm 1.6905 (1.8574)	
[2022-01-23 19:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][120/1251]	eta 0:44:44 lr 0.000289	time 1.8282 (2.3736)	loss 4.1626 (3.4000)	grad_norm 1.8611 (1.8607)	
[2022-01-23 19:56:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][130/1251]	eta 0:44:10 lr 0.000289	time 2.3946 (2.3643)	loss 3.4098 (3.3624)	grad_norm 1.8622 (1.8588)	
[2022-01-23 19:57:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][140/1251]	eta 0:43:24 lr 0.000289	time 2.2898 (2.3445)	loss 3.5274 (3.3653)	grad_norm 1.8058 (1.8638)	
[2022-01-23 19:57:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][150/1251]	eta 0:42:32 lr 0.000289	time 2.2441 (2.3180)	loss 3.7959 (3.3875)	grad_norm 1.7223 (1.8652)	
[2022-01-23 19:57:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][160/1251]	eta 0:41:51 lr 0.000289	time 2.3500 (2.3017)	loss 3.4977 (3.3836)	grad_norm 1.6973 (1.8620)	
[2022-01-23 19:58:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][170/1251]	eta 0:41:19 lr 0.000289	time 2.9228 (2.2938)	loss 3.7146 (3.3834)	grad_norm 2.3453 (1.8614)	
[2022-01-23 19:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][180/1251]	eta 0:40:44 lr 0.000289	time 1.8680 (2.2822)	loss 3.4349 (3.3968)	grad_norm 1.6834 (1.8569)	
[2022-01-23 19:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][190/1251]	eta 0:40:21 lr 0.000289	time 2.1318 (2.2821)	loss 3.7847 (3.3910)	grad_norm 1.8663 (1.8618)	
[2022-01-23 19:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][200/1251]	eta 0:40:00 lr 0.000289	time 2.3561 (2.2841)	loss 2.6144 (3.3759)	grad_norm 1.8120 (1.8599)	
[2022-01-23 19:59:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][210/1251]	eta 0:40:03 lr 0.000289	time 3.3408 (2.3085)	loss 2.5052 (3.3733)	grad_norm 1.6875 (1.8586)	
[2022-01-23 20:00:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][220/1251]	eta 0:39:37 lr 0.000289	time 1.8943 (2.3056)	loss 3.3889 (3.3729)	grad_norm 1.8882 (1.8644)	
[2022-01-23 20:00:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][230/1251]	eta 0:39:02 lr 0.000289	time 1.9139 (2.2947)	loss 3.7098 (3.3716)	grad_norm 1.6824 (1.8651)	
[2022-01-23 20:00:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][240/1251]	eta 0:38:20 lr 0.000289	time 1.5646 (2.2760)	loss 2.4493 (3.3735)	grad_norm 1.5182 (1.8642)	
[2022-01-23 20:01:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][250/1251]	eta 0:37:50 lr 0.000289	time 2.4328 (2.2677)	loss 2.7587 (3.3653)	grad_norm 2.1884 (1.8647)	
[2022-01-23 20:01:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][260/1251]	eta 0:37:17 lr 0.000289	time 1.9072 (2.2580)	loss 2.8250 (3.3577)	grad_norm 2.0305 (1.8660)	
[2022-01-23 20:01:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][270/1251]	eta 0:36:53 lr 0.000289	time 3.1781 (2.2563)	loss 2.3840 (3.3572)	grad_norm 1.7989 (1.8636)	
[2022-01-23 20:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][280/1251]	eta 0:36:33 lr 0.000289	time 2.4167 (2.2586)	loss 3.6110 (3.3632)	grad_norm 2.1674 (1.8635)	
[2022-01-23 20:02:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][290/1251]	eta 0:36:11 lr 0.000288	time 1.9441 (2.2593)	loss 3.7888 (3.3600)	grad_norm 1.7364 (1.8626)	
[2022-01-23 20:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][300/1251]	eta 0:35:47 lr 0.000288	time 1.6227 (2.2581)	loss 2.2724 (3.3581)	grad_norm 1.5500 (1.8655)	
[2022-01-23 20:03:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][310/1251]	eta 0:35:30 lr 0.000288	time 3.2434 (2.2636)	loss 3.5511 (3.3622)	grad_norm 1.7765 (1.8640)	
[2022-01-23 20:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][320/1251]	eta 0:35:10 lr 0.000288	time 2.9241 (2.2673)	loss 2.8808 (3.3485)	grad_norm 1.8472 (1.8639)	
[2022-01-23 20:04:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][330/1251]	eta 0:34:44 lr 0.000288	time 1.6007 (2.2636)	loss 4.2145 (3.3516)	grad_norm 2.0375 (1.8648)	
[2022-01-23 20:04:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][340/1251]	eta 0:34:16 lr 0.000288	time 1.9858 (2.2574)	loss 2.6474 (3.3470)	grad_norm 2.0744 (1.8670)	
[2022-01-23 20:04:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][350/1251]	eta 0:33:49 lr 0.000288	time 2.9033 (2.2522)	loss 3.4791 (3.3390)	grad_norm 1.9187 (1.8653)	
[2022-01-23 20:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][360/1251]	eta 0:33:20 lr 0.000288	time 2.1654 (2.2448)	loss 2.5573 (3.3419)	grad_norm 1.9099 (1.8660)	
[2022-01-23 20:05:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][370/1251]	eta 0:32:56 lr 0.000288	time 2.5528 (2.2437)	loss 3.4139 (3.3373)	grad_norm 2.1723 (1.8672)	
[2022-01-23 20:05:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][380/1251]	eta 0:32:30 lr 0.000288	time 1.8613 (2.2393)	loss 3.3594 (3.3373)	grad_norm 1.9804 (1.8692)	
[2022-01-23 20:06:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][390/1251]	eta 0:32:09 lr 0.000288	time 3.1409 (2.2415)	loss 2.1727 (3.3323)	grad_norm 1.7827 (1.8702)	
[2022-01-23 20:06:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][400/1251]	eta 0:31:48 lr 0.000288	time 2.8134 (2.2425)	loss 3.6247 (3.3334)	grad_norm 1.8391 (1.8725)	
[2022-01-23 20:07:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][410/1251]	eta 0:31:25 lr 0.000288	time 2.1301 (2.2422)	loss 2.9616 (3.3345)	grad_norm 2.1276 (1.8709)	
[2022-01-23 20:07:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][420/1251]	eta 0:31:01 lr 0.000288	time 2.1460 (2.2402)	loss 2.9207 (3.3339)	grad_norm 1.7376 (1.8704)	
[2022-01-23 20:07:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][430/1251]	eta 0:30:37 lr 0.000288	time 2.6205 (2.2382)	loss 4.1363 (3.3304)	grad_norm 1.9085 (1.8693)	
[2022-01-23 20:08:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][440/1251]	eta 0:30:13 lr 0.000288	time 2.2744 (2.2355)	loss 2.1322 (3.3327)	grad_norm 1.8836 (1.8706)	
[2022-01-23 20:08:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][450/1251]	eta 0:29:49 lr 0.000288	time 2.8617 (2.2338)	loss 3.3009 (3.3299)	grad_norm 1.6593 (1.8698)	
[2022-01-23 20:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][460/1251]	eta 0:29:26 lr 0.000288	time 2.8787 (2.2336)	loss 3.2473 (3.3322)	grad_norm 1.7513 (1.8681)	
[2022-01-23 20:09:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][470/1251]	eta 0:29:03 lr 0.000288	time 2.2868 (2.2321)	loss 3.6917 (3.3318)	grad_norm 1.9449 (1.8670)	
[2022-01-23 20:09:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][480/1251]	eta 0:28:37 lr 0.000288	time 1.7469 (2.2272)	loss 2.6551 (3.3246)	grad_norm 1.7752 (1.8655)	
[2022-01-23 20:09:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][490/1251]	eta 0:28:12 lr 0.000288	time 1.9557 (2.2238)	loss 2.9192 (3.3236)	grad_norm 2.0838 (1.8650)	
[2022-01-23 20:10:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][500/1251]	eta 0:27:47 lr 0.000288	time 2.1017 (2.2198)	loss 3.1226 (3.3291)	grad_norm 1.6768 (1.8635)	
[2022-01-23 20:10:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][510/1251]	eta 0:27:24 lr 0.000288	time 1.8836 (2.2199)	loss 3.6936 (3.3289)	grad_norm 1.7070 (1.8613)	
[2022-01-23 20:11:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][520/1251]	eta 0:27:03 lr 0.000288	time 2.3069 (2.2209)	loss 4.2416 (3.3279)	grad_norm 1.7951 (1.8607)	
[2022-01-23 20:11:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][530/1251]	eta 0:26:44 lr 0.000288	time 2.7295 (2.2251)	loss 3.7731 (3.3344)	grad_norm 1.8454 (1.8599)	
[2022-01-23 20:11:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][540/1251]	eta 0:26:21 lr 0.000288	time 1.5152 (2.2239)	loss 3.7797 (3.3371)	grad_norm 1.6329 (1.8605)	
[2022-01-23 20:12:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][550/1251]	eta 0:25:57 lr 0.000288	time 1.5388 (2.2224)	loss 3.4149 (3.3362)	grad_norm 1.7748 (1.8595)	
[2022-01-23 20:12:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][560/1251]	eta 0:25:36 lr 0.000287	time 2.5278 (2.2235)	loss 2.7325 (3.3370)	grad_norm 1.5912 (1.8594)	
[2022-01-23 20:12:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][570/1251]	eta 0:25:16 lr 0.000287	time 2.2932 (2.2261)	loss 3.6940 (3.3379)	grad_norm 1.8720 (1.8599)	
[2022-01-23 20:13:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][580/1251]	eta 0:24:52 lr 0.000287	time 1.5320 (2.2242)	loss 3.9140 (3.3378)	grad_norm 1.7681 (1.8594)	
[2022-01-23 20:13:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][590/1251]	eta 0:24:29 lr 0.000287	time 1.6813 (2.2226)	loss 2.9110 (3.3363)	grad_norm 2.1596 (1.8583)	
[2022-01-23 20:14:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][600/1251]	eta 0:24:05 lr 0.000287	time 1.6621 (2.2205)	loss 4.0259 (3.3384)	grad_norm 1.6957 (1.8595)	
[2022-01-23 20:14:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][610/1251]	eta 0:23:41 lr 0.000287	time 2.2331 (2.2181)	loss 2.1359 (3.3408)	grad_norm 1.8270 (1.8618)	
[2022-01-23 20:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][620/1251]	eta 0:23:18 lr 0.000287	time 1.9675 (2.2164)	loss 3.3053 (3.3385)	grad_norm 1.8883 (1.8624)	
[2022-01-23 20:15:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][630/1251]	eta 0:22:55 lr 0.000287	time 1.8631 (2.2150)	loss 3.7678 (3.3356)	grad_norm 2.1551 (1.8624)	
[2022-01-23 20:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][640/1251]	eta 0:22:33 lr 0.000287	time 2.2456 (2.2154)	loss 3.5474 (3.3334)	grad_norm 1.8228 (1.8610)	
[2022-01-23 20:15:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][650/1251]	eta 0:22:12 lr 0.000287	time 2.9664 (2.2167)	loss 2.4342 (3.3336)	grad_norm 1.6375 (1.8600)	
[2022-01-23 20:16:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][660/1251]	eta 0:21:51 lr 0.000287	time 1.8765 (2.2190)	loss 3.3411 (3.3355)	grad_norm 1.7971 (1.8577)	
[2022-01-23 20:16:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][670/1251]	eta 0:21:29 lr 0.000287	time 2.5839 (2.2202)	loss 3.4812 (3.3391)	grad_norm 1.8999 (1.8571)	
[2022-01-23 20:16:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][680/1251]	eta 0:21:06 lr 0.000287	time 1.6426 (2.2179)	loss 3.6405 (3.3397)	grad_norm 1.5773 (1.8558)	
[2022-01-23 20:17:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][690/1251]	eta 0:20:42 lr 0.000287	time 2.0996 (2.2150)	loss 3.7747 (3.3379)	grad_norm 1.9166 (1.8552)	
[2022-01-23 20:17:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][700/1251]	eta 0:20:18 lr 0.000287	time 2.6305 (2.2119)	loss 3.9277 (3.3424)	grad_norm 1.7336 (1.8544)	
[2022-01-23 20:17:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][710/1251]	eta 0:19:55 lr 0.000287	time 2.5257 (2.2104)	loss 2.5354 (3.3426)	grad_norm 1.8902 (1.8588)	
[2022-01-23 20:18:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][720/1251]	eta 0:19:32 lr 0.000287	time 1.9439 (2.2090)	loss 2.8014 (3.3390)	grad_norm 1.7417 (1.8577)	
[2022-01-23 20:18:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][730/1251]	eta 0:19:11 lr 0.000287	time 2.5438 (2.2093)	loss 2.3780 (3.3389)	grad_norm 1.9072 (1.8581)	
[2022-01-23 20:19:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][740/1251]	eta 0:18:49 lr 0.000287	time 2.0987 (2.2098)	loss 3.6292 (3.3429)	grad_norm 1.9139 (1.8599)	
[2022-01-23 20:19:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][750/1251]	eta 0:18:27 lr 0.000287	time 1.8388 (2.2098)	loss 3.9151 (3.3448)	grad_norm 2.0739 (1.8603)	
[2022-01-23 20:19:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][760/1251]	eta 0:18:05 lr 0.000287	time 2.4824 (2.2110)	loss 3.6553 (3.3463)	grad_norm 1.6975 (1.8608)	
[2022-01-23 20:20:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][770/1251]	eta 0:17:44 lr 0.000287	time 2.5601 (2.2124)	loss 2.5716 (3.3446)	grad_norm 1.8868 (1.8598)	
[2022-01-23 20:20:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][780/1251]	eta 0:17:22 lr 0.000287	time 2.1318 (2.2140)	loss 3.1041 (3.3452)	grad_norm 1.8925 (1.8593)	
[2022-01-23 20:20:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][790/1251]	eta 0:17:00 lr 0.000287	time 1.9700 (2.2138)	loss 3.3567 (3.3462)	grad_norm 1.9980 (1.8591)	
[2022-01-23 20:21:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][800/1251]	eta 0:16:37 lr 0.000287	time 2.0037 (2.2115)	loss 3.5544 (3.3453)	grad_norm 1.6164 (1.8590)	
[2022-01-23 20:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][810/1251]	eta 0:16:13 lr 0.000287	time 1.9409 (2.2074)	loss 3.7787 (3.3474)	grad_norm 1.8332 (1.8598)	
[2022-01-23 20:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][820/1251]	eta 0:15:50 lr 0.000287	time 1.8666 (2.2057)	loss 3.9314 (3.3442)	grad_norm 1.9287 (1.8605)	
[2022-01-23 20:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][830/1251]	eta 0:15:28 lr 0.000286	time 1.8984 (2.2054)	loss 2.0826 (3.3423)	grad_norm 1.8227 (1.8607)	
[2022-01-23 20:22:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][840/1251]	eta 0:15:08 lr 0.000286	time 5.6446 (2.2114)	loss 2.2967 (3.3429)	grad_norm 1.9039 (1.8608)	
[2022-01-23 20:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][850/1251]	eta 0:14:47 lr 0.000286	time 2.2243 (2.2144)	loss 3.4181 (3.3429)	grad_norm 1.9602 (1.8616)	
[2022-01-23 20:23:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][860/1251]	eta 0:14:25 lr 0.000286	time 1.9344 (2.2144)	loss 3.7685 (3.3441)	grad_norm 1.8080 (1.8629)	
[2022-01-23 20:23:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][870/1251]	eta 0:14:02 lr 0.000286	time 1.5878 (2.2122)	loss 2.9246 (3.3411)	grad_norm 1.9025 (1.8631)	
[2022-01-23 20:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][880/1251]	eta 0:13:39 lr 0.000286	time 2.0640 (2.2091)	loss 3.4942 (3.3422)	grad_norm 1.9391 (1.8647)	
[2022-01-23 20:24:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][890/1251]	eta 0:13:16 lr 0.000286	time 2.2545 (2.2073)	loss 4.1909 (3.3414)	grad_norm 2.0508 (1.8642)	
[2022-01-23 20:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][900/1251]	eta 0:12:54 lr 0.000286	time 2.5849 (2.2061)	loss 3.7877 (3.3426)	grad_norm 1.9927 (1.8641)	
[2022-01-23 20:25:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][910/1251]	eta 0:12:31 lr 0.000286	time 2.2683 (2.2052)	loss 2.4283 (3.3429)	grad_norm 1.7126 (1.8630)	
[2022-01-23 20:25:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][920/1251]	eta 0:12:09 lr 0.000286	time 1.8685 (2.2052)	loss 2.6798 (3.3415)	grad_norm 1.4941 (1.8620)	
[2022-01-23 20:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][930/1251]	eta 0:11:47 lr 0.000286	time 2.6626 (2.2055)	loss 3.8417 (3.3438)	grad_norm 1.9560 (1.8619)	
[2022-01-23 20:26:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][940/1251]	eta 0:11:26 lr 0.000286	time 1.6676 (2.2060)	loss 3.6343 (3.3448)	grad_norm 2.2059 (1.8613)	
[2022-01-23 20:26:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][950/1251]	eta 0:11:04 lr 0.000286	time 1.9701 (2.2064)	loss 3.6541 (3.3458)	grad_norm 1.8710 (1.8617)	
[2022-01-23 20:27:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][960/1251]	eta 0:10:42 lr 0.000286	time 2.4041 (2.2083)	loss 3.4353 (3.3470)	grad_norm 1.8980 (1.8614)	
[2022-01-23 20:27:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][970/1251]	eta 0:10:20 lr 0.000286	time 2.8573 (2.2086)	loss 3.9745 (3.3494)	grad_norm 1.9609 (1.8623)	
[2022-01-23 20:27:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][980/1251]	eta 0:09:58 lr 0.000286	time 2.4329 (2.2082)	loss 2.9938 (3.3463)	grad_norm 1.4382 (1.8612)	
[2022-01-23 20:28:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][990/1251]	eta 0:09:35 lr 0.000286	time 2.2451 (2.2067)	loss 2.9368 (3.3450)	grad_norm 1.9057 (1.8607)	
[2022-01-23 20:28:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1000/1251]	eta 0:09:13 lr 0.000286	time 2.3876 (2.2052)	loss 3.5411 (3.3449)	grad_norm 1.5432 (1.8589)	
[2022-01-23 20:28:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1010/1251]	eta 0:08:51 lr 0.000286	time 2.6139 (2.2047)	loss 2.3613 (3.3452)	grad_norm 1.7594 (1.8592)	
[2022-01-23 20:29:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1020/1251]	eta 0:08:29 lr 0.000286	time 2.1422 (2.2041)	loss 3.8285 (3.3470)	grad_norm 1.9900 (1.8592)	
[2022-01-23 20:29:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1030/1251]	eta 0:08:07 lr 0.000286	time 2.1702 (2.2041)	loss 3.6478 (3.3485)	grad_norm 2.0979 (1.8596)	
[2022-01-23 20:29:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1040/1251]	eta 0:07:44 lr 0.000286	time 2.2862 (2.2036)	loss 3.6537 (3.3478)	grad_norm 2.0399 (1.8594)	
[2022-01-23 20:30:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1050/1251]	eta 0:07:22 lr 0.000286	time 1.5022 (2.2035)	loss 2.9928 (3.3489)	grad_norm 2.1028 (1.8601)	
[2022-01-23 20:30:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1060/1251]	eta 0:07:00 lr 0.000286	time 2.4655 (2.2033)	loss 4.0241 (3.3491)	grad_norm 2.4260 (1.8604)	
[2022-01-23 20:31:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1070/1251]	eta 0:06:38 lr 0.000286	time 1.9320 (2.2023)	loss 2.4963 (3.3495)	grad_norm 1.8992 (1.8606)	
[2022-01-23 20:31:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1080/1251]	eta 0:06:16 lr 0.000286	time 2.5377 (2.2012)	loss 3.3827 (3.3462)	grad_norm 2.2917 (1.8618)	
[2022-01-23 20:31:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1090/1251]	eta 0:05:54 lr 0.000286	time 1.8059 (2.2002)	loss 3.9402 (3.3461)	grad_norm 2.3323 (1.8631)	
[2022-01-23 20:32:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1100/1251]	eta 0:05:32 lr 0.000285	time 2.9828 (2.2015)	loss 2.9071 (3.3425)	grad_norm 1.8405 (1.8645)	
[2022-01-23 20:32:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1110/1251]	eta 0:05:10 lr 0.000285	time 2.4994 (2.2024)	loss 3.1927 (3.3439)	grad_norm 1.8133 (1.8644)	
[2022-01-23 20:32:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1120/1251]	eta 0:04:48 lr 0.000285	time 2.1829 (2.2028)	loss 3.4577 (3.3428)	grad_norm 2.0452 (1.8650)	
[2022-01-23 20:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1130/1251]	eta 0:04:26 lr 0.000285	time 1.6076 (2.2031)	loss 3.8101 (3.3414)	grad_norm 1.8240 (1.8648)	
[2022-01-23 20:33:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1140/1251]	eta 0:04:04 lr 0.000285	time 2.8275 (2.2026)	loss 2.9784 (3.3433)	grad_norm 1.9548 (1.8640)	
[2022-01-23 20:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1150/1251]	eta 0:03:42 lr 0.000285	time 1.7561 (2.1999)	loss 3.3129 (3.3409)	grad_norm 2.1195 (1.8638)	
[2022-01-23 20:34:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1160/1251]	eta 0:03:20 lr 0.000285	time 2.4323 (2.1980)	loss 3.1600 (3.3413)	grad_norm 1.8244 (1.8640)	
[2022-01-23 20:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1170/1251]	eta 0:02:57 lr 0.000285	time 2.4248 (2.1972)	loss 2.8891 (3.3402)	grad_norm 1.7005 (1.8629)	
[2022-01-23 20:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1180/1251]	eta 0:02:35 lr 0.000285	time 1.5120 (2.1962)	loss 2.5101 (3.3398)	grad_norm 1.6860 (1.8632)	
[2022-01-23 20:35:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1190/1251]	eta 0:02:13 lr 0.000285	time 2.3875 (2.1966)	loss 4.0494 (3.3395)	grad_norm 1.7655 (1.8637)	
[2022-01-23 20:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1200/1251]	eta 0:01:52 lr 0.000285	time 3.1649 (2.1970)	loss 3.1150 (3.3362)	grad_norm 1.7791 (1.8637)	
[2022-01-23 20:36:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1210/1251]	eta 0:01:30 lr 0.000285	time 2.8964 (2.1976)	loss 3.8679 (3.3366)	grad_norm 1.8738 (1.8639)	
[2022-01-23 20:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1220/1251]	eta 0:01:08 lr 0.000285	time 2.4902 (2.1973)	loss 3.5057 (3.3384)	grad_norm 1.7210 (1.8635)	
[2022-01-23 20:36:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1230/1251]	eta 0:00:46 lr 0.000285	time 3.2063 (2.2002)	loss 3.5826 (3.3395)	grad_norm 1.7988 (1.8635)	
[2022-01-23 20:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1240/1251]	eta 0:00:24 lr 0.000285	time 2.0936 (2.1992)	loss 3.6886 (3.3427)	grad_norm 1.7037 (1.8642)	
[2022-01-23 20:37:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [193/300][1250/1251]	eta 0:00:02 lr 0.000285	time 1.2077 (2.1932)	loss 3.3216 (3.3448)	grad_norm 1.7649 (1.8641)	
[2022-01-23 20:37:29 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 193 training takes 0:45:44
[2022-01-23 20:37:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.912 (17.912)	Loss 1.0044 (1.0044)	Acc@1 75.293 (75.293)	Acc@5 93.359 (93.359)	
[2022-01-23 20:38:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.288 (3.217)	Loss 1.0179 (0.9429)	Acc@1 75.977 (78.125)	Acc@5 93.262 (94.292)	
[2022-01-23 20:38:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.941 (2.458)	Loss 0.9090 (0.9340)	Acc@1 79.004 (78.246)	Acc@5 94.336 (94.434)	
[2022-01-23 20:38:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.616 (2.305)	Loss 0.9306 (0.9456)	Acc@1 78.027 (77.949)	Acc@5 94.238 (94.311)	
[2022-01-23 20:38:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.853 (2.176)	Loss 0.9891 (0.9435)	Acc@1 78.223 (78.092)	Acc@5 93.164 (94.331)	
[2022-01-23 20:39:06 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.138 Acc@5 94.310
[2022-01-23 20:39:06 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.1%
[2022-01-23 20:39:06 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.21%
[2022-01-23 20:39:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][0/1251]	eta 7:38:56 lr 0.000285	time 22.0118 (22.0118)	loss 3.0033 (3.0033)	grad_norm 2.1691 (2.1691)	
[2022-01-23 20:39:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][10/1251]	eta 1:23:29 lr 0.000285	time 1.9770 (4.0367)	loss 3.6431 (3.3169)	grad_norm 1.9433 (1.9166)	
[2022-01-23 20:40:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][20/1251]	eta 1:03:53 lr 0.000285	time 1.6710 (3.1141)	loss 3.9088 (3.3581)	grad_norm 1.7333 (1.9362)	
[2022-01-23 20:40:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][30/1251]	eta 0:57:17 lr 0.000285	time 1.6286 (2.8156)	loss 3.3963 (3.3674)	grad_norm 2.3122 (2.0088)	
[2022-01-23 20:40:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][40/1251]	eta 0:55:32 lr 0.000285	time 6.6662 (2.7520)	loss 3.6885 (3.4073)	grad_norm 1.5770 (1.9818)	
[2022-01-23 20:41:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][50/1251]	eta 0:52:25 lr 0.000285	time 1.3106 (2.6188)	loss 3.3324 (3.4135)	grad_norm 1.6616 (1.9493)	
[2022-01-23 20:41:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][60/1251]	eta 0:50:37 lr 0.000285	time 2.2602 (2.5505)	loss 3.1545 (3.3838)	grad_norm 1.8134 (1.9124)	
[2022-01-23 20:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][70/1251]	eta 0:49:02 lr 0.000285	time 1.7094 (2.4916)	loss 4.1572 (3.4139)	grad_norm 1.8449 (1.9096)	
[2022-01-23 20:42:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][80/1251]	eta 0:48:22 lr 0.000285	time 3.1677 (2.4788)	loss 3.7248 (3.4295)	grad_norm 1.9201 (1.9013)	
[2022-01-23 20:42:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][90/1251]	eta 0:47:27 lr 0.000285	time 1.6425 (2.4525)	loss 3.5129 (3.4221)	grad_norm 1.7609 (1.8999)	
[2022-01-23 20:43:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][100/1251]	eta 0:46:38 lr 0.000285	time 2.2243 (2.4318)	loss 3.7688 (3.4448)	grad_norm 1.9469 (1.9025)	
[2022-01-23 20:43:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][110/1251]	eta 0:45:34 lr 0.000284	time 1.7223 (2.3969)	loss 2.6508 (3.4469)	grad_norm 2.0277 (1.9055)	
[2022-01-23 20:43:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][120/1251]	eta 0:44:44 lr 0.000284	time 2.3744 (2.3733)	loss 2.9165 (3.4508)	grad_norm 2.0751 (1.9088)	
[2022-01-23 20:44:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][130/1251]	eta 0:43:46 lr 0.000284	time 1.5546 (2.3429)	loss 2.4970 (3.4271)	grad_norm 2.2797 (1.9092)	
[2022-01-23 20:44:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][140/1251]	eta 0:43:18 lr 0.000284	time 2.3442 (2.3385)	loss 2.8010 (3.4043)	grad_norm 2.2288 (1.9121)	
[2022-01-23 20:44:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][150/1251]	eta 0:42:40 lr 0.000284	time 1.8715 (2.3258)	loss 3.8230 (3.4077)	grad_norm 2.2181 (1.9189)	
[2022-01-23 20:45:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][160/1251]	eta 0:42:20 lr 0.000284	time 3.0792 (2.3290)	loss 3.2784 (3.4014)	grad_norm 1.5670 (1.9166)	
[2022-01-23 20:45:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][170/1251]	eta 0:41:52 lr 0.000284	time 1.8039 (2.3244)	loss 3.4955 (3.4028)	grad_norm 1.9930 (1.9139)	
[2022-01-23 20:46:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][180/1251]	eta 0:41:21 lr 0.000284	time 2.4919 (2.3171)	loss 3.4128 (3.4051)	grad_norm 1.7303 (1.9135)	
[2022-01-23 20:46:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][190/1251]	eta 0:40:49 lr 0.000284	time 1.5955 (2.3090)	loss 3.3562 (3.3954)	grad_norm 1.8743 (1.9047)	
[2022-01-23 20:46:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][200/1251]	eta 0:40:16 lr 0.000284	time 2.8179 (2.2990)	loss 3.5852 (3.3838)	grad_norm 2.0807 (1.9115)	
[2022-01-23 20:47:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][210/1251]	eta 0:39:43 lr 0.000284	time 1.9079 (2.2899)	loss 4.0581 (3.3767)	grad_norm 1.7752 (1.9092)	
[2022-01-23 20:47:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][220/1251]	eta 0:39:14 lr 0.000284	time 3.3189 (2.2841)	loss 3.7109 (3.3789)	grad_norm 1.7734 (1.9064)	
[2022-01-23 20:47:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][230/1251]	eta 0:38:45 lr 0.000284	time 1.9357 (2.2781)	loss 3.0829 (3.3778)	grad_norm 1.9452 (1.9058)	
[2022-01-23 20:48:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][240/1251]	eta 0:38:24 lr 0.000284	time 3.1680 (2.2795)	loss 2.3622 (3.3671)	grad_norm 1.7647 (1.9031)	
[2022-01-23 20:48:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][250/1251]	eta 0:37:54 lr 0.000284	time 2.2344 (2.2719)	loss 4.0946 (3.3615)	grad_norm 1.8107 (1.9026)	
[2022-01-23 20:48:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][260/1251]	eta 0:37:27 lr 0.000284	time 2.8487 (2.2680)	loss 3.6657 (3.3520)	grad_norm 1.9367 (1.9032)	
[2022-01-23 20:49:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][270/1251]	eta 0:37:03 lr 0.000284	time 1.9097 (2.2669)	loss 3.5691 (3.3497)	grad_norm 1.9540 (1.9024)	
[2022-01-23 20:49:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][280/1251]	eta 0:36:38 lr 0.000284	time 2.3883 (2.2640)	loss 3.7401 (3.3548)	grad_norm 1.5333 (1.8987)	
[2022-01-23 20:50:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][290/1251]	eta 0:36:10 lr 0.000284	time 1.8435 (2.2583)	loss 3.5491 (3.3558)	grad_norm 1.7942 (1.8961)	
[2022-01-23 20:50:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][300/1251]	eta 0:35:43 lr 0.000284	time 2.4345 (2.2536)	loss 3.3432 (3.3612)	grad_norm 1.8417 (1.8932)	
[2022-01-23 20:50:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][310/1251]	eta 0:35:14 lr 0.000284	time 2.2001 (2.2473)	loss 3.7617 (3.3595)	grad_norm 1.9123 (1.8897)	
[2022-01-23 20:51:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][320/1251]	eta 0:34:50 lr 0.000284	time 2.3032 (2.2452)	loss 4.1497 (3.3609)	grad_norm 1.6246 (1.8845)	
[2022-01-23 20:51:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][330/1251]	eta 0:34:24 lr 0.000284	time 1.8122 (2.2413)	loss 3.2528 (3.3648)	grad_norm 1.8261 (1.8815)	
[2022-01-23 20:51:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][340/1251]	eta 0:34:03 lr 0.000284	time 2.3927 (2.2428)	loss 3.4715 (3.3643)	grad_norm 1.6524 (1.8779)	
[2022-01-23 20:52:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][350/1251]	eta 0:33:37 lr 0.000284	time 2.2584 (2.2388)	loss 3.3147 (3.3642)	grad_norm 1.7694 (1.8750)	
[2022-01-23 20:52:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][360/1251]	eta 0:33:14 lr 0.000284	time 2.3674 (2.2385)	loss 3.1344 (3.3575)	grad_norm 1.5248 (1.8716)	
[2022-01-23 20:52:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][370/1251]	eta 0:32:50 lr 0.000284	time 1.8812 (2.2368)	loss 4.0315 (3.3651)	grad_norm 1.9691 (1.8723)	
[2022-01-23 20:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][380/1251]	eta 0:32:29 lr 0.000283	time 2.1799 (2.2380)	loss 3.0872 (3.3625)	grad_norm 1.7091 (1.8730)	
[2022-01-23 20:53:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][390/1251]	eta 0:32:06 lr 0.000283	time 1.8987 (2.2376)	loss 3.4957 (3.3587)	grad_norm 1.6760 (1.8743)	
[2022-01-23 20:54:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][400/1251]	eta 0:31:46 lr 0.000283	time 1.8724 (2.2406)	loss 3.5989 (3.3580)	grad_norm 1.7468 (1.8739)	
[2022-01-23 20:54:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][410/1251]	eta 0:31:24 lr 0.000283	time 1.8648 (2.2410)	loss 2.3708 (3.3540)	grad_norm 2.0092 (1.8741)	
[2022-01-23 20:54:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][420/1251]	eta 0:31:01 lr 0.000283	time 2.4375 (2.2403)	loss 2.7572 (3.3537)	grad_norm 1.7746 (1.8727)	
[2022-01-23 20:55:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][430/1251]	eta 0:30:32 lr 0.000283	time 1.8646 (2.2325)	loss 3.6557 (3.3520)	grad_norm 1.9099 (1.8737)	
[2022-01-23 20:55:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][440/1251]	eta 0:30:07 lr 0.000283	time 1.6038 (2.2290)	loss 3.5906 (3.3552)	grad_norm 2.7943 (1.8772)	
[2022-01-23 20:55:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][450/1251]	eta 0:29:42 lr 0.000283	time 1.8823 (2.2252)	loss 3.0517 (3.3576)	grad_norm 1.9546 (1.8806)	
[2022-01-23 20:56:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][460/1251]	eta 0:29:20 lr 0.000283	time 1.8358 (2.2256)	loss 4.0147 (3.3555)	grad_norm 1.9088 (1.8810)	
[2022-01-23 20:56:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][470/1251]	eta 0:28:57 lr 0.000283	time 1.8488 (2.2252)	loss 3.7663 (3.3514)	grad_norm 1.7456 (1.8809)	
[2022-01-23 20:56:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][480/1251]	eta 0:28:35 lr 0.000283	time 2.2531 (2.2245)	loss 3.3262 (3.3539)	grad_norm 1.9894 (1.8797)	
[2022-01-23 20:57:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][490/1251]	eta 0:28:10 lr 0.000283	time 1.5815 (2.2221)	loss 3.9119 (3.3615)	grad_norm 1.6034 (1.8789)	
[2022-01-23 20:57:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][500/1251]	eta 0:27:49 lr 0.000283	time 2.7610 (2.2226)	loss 3.1615 (3.3549)	grad_norm 1.5720 (1.8793)	
[2022-01-23 20:58:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][510/1251]	eta 0:27:27 lr 0.000283	time 2.1692 (2.2233)	loss 2.1188 (3.3549)	grad_norm 1.9149 (1.8789)	
[2022-01-23 20:58:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][520/1251]	eta 0:27:06 lr 0.000283	time 2.1895 (2.2245)	loss 2.4134 (3.3511)	grad_norm 1.8348 (1.8774)	
[2022-01-23 20:58:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][530/1251]	eta 0:26:41 lr 0.000283	time 1.7443 (2.2209)	loss 3.1634 (3.3517)	grad_norm 1.6203 (1.8748)	
[2022-01-23 20:59:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][540/1251]	eta 0:26:19 lr 0.000283	time 2.9948 (2.2210)	loss 4.0860 (3.3555)	grad_norm 1.7515 (1.8758)	
[2022-01-23 20:59:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][550/1251]	eta 0:25:56 lr 0.000283	time 1.8804 (2.2203)	loss 3.5820 (3.3566)	grad_norm 1.7073 (1.8746)	
[2022-01-23 20:59:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][560/1251]	eta 0:25:34 lr 0.000283	time 1.8261 (2.2204)	loss 3.4566 (3.3640)	grad_norm 1.8560 (1.8748)	
[2022-01-23 21:00:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][570/1251]	eta 0:25:10 lr 0.000283	time 2.0014 (2.2174)	loss 3.3880 (3.3647)	grad_norm 1.8089 (1.8734)	
[2022-01-23 21:00:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][580/1251]	eta 0:24:47 lr 0.000283	time 2.4675 (2.2164)	loss 3.3551 (3.3654)	grad_norm 1.7974 (1.8731)	
[2022-01-23 21:00:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][590/1251]	eta 0:24:24 lr 0.000283	time 1.6096 (2.2150)	loss 3.7243 (3.3690)	grad_norm 1.6829 (1.8724)	
[2022-01-23 21:01:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][600/1251]	eta 0:24:00 lr 0.000283	time 2.1857 (2.2130)	loss 3.6393 (3.3669)	grad_norm 1.7364 (1.8734)	
[2022-01-23 21:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][610/1251]	eta 0:23:37 lr 0.000283	time 2.1444 (2.2118)	loss 2.2735 (3.3604)	grad_norm 1.9634 (1.8725)	
[2022-01-23 21:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][620/1251]	eta 0:23:15 lr 0.000283	time 2.1714 (2.2113)	loss 3.7021 (3.3571)	grad_norm 2.4990 (1.8730)	
[2022-01-23 21:02:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][630/1251]	eta 0:22:52 lr 0.000283	time 1.8603 (2.2100)	loss 3.4085 (3.3557)	grad_norm 2.0552 (1.8734)	
[2022-01-23 21:02:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][640/1251]	eta 0:22:31 lr 0.000283	time 3.0187 (2.2121)	loss 2.0661 (3.3503)	grad_norm 2.1638 (1.8735)	
[2022-01-23 21:03:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][650/1251]	eta 0:22:10 lr 0.000282	time 2.2085 (2.2139)	loss 3.8582 (3.3557)	grad_norm 1.5709 (1.8716)	
[2022-01-23 21:03:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][660/1251]	eta 0:21:47 lr 0.000282	time 2.2855 (2.2128)	loss 3.8586 (3.3542)	grad_norm 2.1916 (1.8708)	
[2022-01-23 21:03:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][670/1251]	eta 0:21:24 lr 0.000282	time 1.6839 (2.2110)	loss 2.5364 (3.3514)	grad_norm 1.6682 (1.8698)	
[2022-01-23 21:04:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][680/1251]	eta 0:21:02 lr 0.000282	time 3.0576 (2.2115)	loss 2.4901 (3.3478)	grad_norm 1.9536 (1.8724)	
[2022-01-23 21:04:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][690/1251]	eta 0:20:40 lr 0.000282	time 2.1999 (2.2118)	loss 3.4151 (3.3480)	grad_norm 1.8060 (1.8710)	
[2022-01-23 21:04:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][700/1251]	eta 0:20:18 lr 0.000282	time 2.4866 (2.2118)	loss 3.4560 (3.3475)	grad_norm 1.9896 (1.8702)	
[2022-01-23 21:05:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][710/1251]	eta 0:19:56 lr 0.000282	time 2.0777 (2.2124)	loss 3.3843 (3.3493)	grad_norm 1.7288 (1.8703)	
[2022-01-23 21:05:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][720/1251]	eta 0:19:36 lr 0.000282	time 3.2729 (2.2150)	loss 3.4822 (3.3489)	grad_norm 1.8022 (1.8695)	
[2022-01-23 21:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][730/1251]	eta 0:19:14 lr 0.000282	time 1.8485 (2.2164)	loss 3.4466 (3.3496)	grad_norm 1.9111 (1.8705)	
[2022-01-23 21:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][740/1251]	eta 0:18:52 lr 0.000282	time 1.7340 (2.2153)	loss 3.7984 (3.3521)	grad_norm 1.9505 (1.8713)	
[2022-01-23 21:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][750/1251]	eta 0:18:29 lr 0.000282	time 2.9205 (2.2145)	loss 3.9079 (3.3542)	grad_norm 2.1114 (1.8720)	
[2022-01-23 21:07:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][760/1251]	eta 0:18:06 lr 0.000282	time 3.0811 (2.2129)	loss 4.0214 (3.3541)	grad_norm 1.9336 (1.8726)	
[2022-01-23 21:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][770/1251]	eta 0:17:44 lr 0.000282	time 1.7922 (2.2122)	loss 3.4459 (3.3510)	grad_norm 1.9706 (1.8742)	
[2022-01-23 21:07:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][780/1251]	eta 0:17:21 lr 0.000282	time 1.6110 (2.2119)	loss 3.8233 (3.3526)	grad_norm 1.9976 (1.8738)	
[2022-01-23 21:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][790/1251]	eta 0:17:00 lr 0.000282	time 2.9241 (2.2126)	loss 3.5726 (3.3551)	grad_norm 1.7599 (1.8743)	
[2022-01-23 21:08:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][800/1251]	eta 0:16:37 lr 0.000282	time 3.1839 (2.2115)	loss 3.6550 (3.3551)	grad_norm 1.9441 (1.8743)	
[2022-01-23 21:08:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][810/1251]	eta 0:16:14 lr 0.000282	time 2.0242 (2.2087)	loss 4.3443 (3.3551)	grad_norm 1.9002 (1.8757)	
[2022-01-23 21:09:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][820/1251]	eta 0:15:52 lr 0.000282	time 1.9711 (2.2090)	loss 3.9741 (3.3551)	grad_norm 1.9261 (1.8757)	
[2022-01-23 21:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][830/1251]	eta 0:15:30 lr 0.000282	time 3.0503 (2.2107)	loss 3.8027 (3.3527)	grad_norm 1.7249 (1.8751)	
[2022-01-23 21:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][840/1251]	eta 0:15:09 lr 0.000282	time 2.9944 (2.2118)	loss 4.0845 (3.3545)	grad_norm 1.6663 (1.8751)	
[2022-01-23 21:10:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][850/1251]	eta 0:14:46 lr 0.000282	time 1.5259 (2.2102)	loss 2.8163 (3.3525)	grad_norm 2.0955 (1.8752)	
[2022-01-23 21:10:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][860/1251]	eta 0:14:23 lr 0.000282	time 1.9331 (2.2091)	loss 2.1369 (3.3503)	grad_norm 2.2230 (1.8769)	
[2022-01-23 21:11:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][870/1251]	eta 0:14:01 lr 0.000282	time 2.2864 (2.2078)	loss 2.8943 (3.3432)	grad_norm 2.3142 (1.8768)	
[2022-01-23 21:11:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][880/1251]	eta 0:13:39 lr 0.000282	time 3.4482 (2.2086)	loss 3.7277 (3.3447)	grad_norm 1.9428 (1.8784)	
[2022-01-23 21:11:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][890/1251]	eta 0:13:16 lr 0.000282	time 2.2163 (2.2073)	loss 2.4069 (3.3401)	grad_norm 1.6911 (1.8789)	
[2022-01-23 21:12:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][900/1251]	eta 0:12:54 lr 0.000282	time 1.7068 (2.2071)	loss 3.6887 (3.3430)	grad_norm 1.9147 (1.8791)	
[2022-01-23 21:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][910/1251]	eta 0:12:32 lr 0.000282	time 1.9105 (2.2068)	loss 3.5568 (3.3406)	grad_norm 1.8100 (1.8793)	
[2022-01-23 21:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][920/1251]	eta 0:12:10 lr 0.000281	time 2.1523 (2.2065)	loss 3.4725 (3.3415)	grad_norm 1.5926 (1.8783)	
[2022-01-23 21:13:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][930/1251]	eta 0:11:48 lr 0.000281	time 2.2160 (2.2076)	loss 4.1113 (3.3463)	grad_norm 1.7765 (1.8782)	
[2022-01-23 21:13:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][940/1251]	eta 0:11:25 lr 0.000281	time 1.6858 (2.2057)	loss 3.9513 (3.3471)	grad_norm 1.6048 (1.8778)	
[2022-01-23 21:14:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][950/1251]	eta 0:11:03 lr 0.000281	time 1.6090 (2.2052)	loss 2.3284 (3.3466)	grad_norm 1.7960 (1.8781)	
[2022-01-23 21:14:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][960/1251]	eta 0:10:41 lr 0.000281	time 2.8163 (2.2054)	loss 3.1676 (3.3460)	grad_norm 1.7719 (1.8776)	
[2022-01-23 21:14:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][970/1251]	eta 0:10:19 lr 0.000281	time 2.4802 (2.2061)	loss 3.6222 (3.3499)	grad_norm 1.9799 (1.8780)	
[2022-01-23 21:15:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][980/1251]	eta 0:09:57 lr 0.000281	time 1.8377 (2.2060)	loss 3.0725 (3.3508)	grad_norm 2.0602 (1.8782)	
[2022-01-23 21:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][990/1251]	eta 0:09:35 lr 0.000281	time 2.6420 (2.2055)	loss 3.7898 (3.3500)	grad_norm 1.8690 (1.8787)	
[2022-01-23 21:15:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1000/1251]	eta 0:09:13 lr 0.000281	time 2.2855 (2.2041)	loss 2.1395 (3.3490)	grad_norm 1.9525 (1.8783)	
[2022-01-23 21:16:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1010/1251]	eta 0:08:50 lr 0.000281	time 1.4918 (2.2026)	loss 3.1258 (3.3489)	grad_norm 1.4681 (1.8774)	
[2022-01-23 21:16:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1020/1251]	eta 0:08:28 lr 0.000281	time 2.1306 (2.2016)	loss 3.9202 (3.3479)	grad_norm 2.1062 (1.8781)	
[2022-01-23 21:16:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1030/1251]	eta 0:08:06 lr 0.000281	time 2.5830 (2.2016)	loss 4.0468 (3.3492)	grad_norm 1.9421 (1.8775)	
[2022-01-23 21:17:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1040/1251]	eta 0:07:44 lr 0.000281	time 2.5310 (2.2008)	loss 3.5462 (3.3494)	grad_norm 2.1631 (1.8779)	
[2022-01-23 21:17:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1050/1251]	eta 0:07:22 lr 0.000281	time 2.4299 (2.2019)	loss 3.4951 (3.3510)	grad_norm 1.9219 (1.8778)	
[2022-01-23 21:18:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1060/1251]	eta 0:07:00 lr 0.000281	time 1.8981 (2.2013)	loss 2.4734 (3.3513)	grad_norm 1.8587 (1.8775)	
[2022-01-23 21:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1070/1251]	eta 0:06:38 lr 0.000281	time 2.8898 (2.2021)	loss 2.7065 (3.3524)	grad_norm 2.1224 (1.8773)	
[2022-01-23 21:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1080/1251]	eta 0:06:16 lr 0.000281	time 2.6150 (2.2027)	loss 2.2783 (3.3498)	grad_norm 2.0682 (1.8779)	
[2022-01-23 21:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1090/1251]	eta 0:05:54 lr 0.000281	time 2.0855 (2.2030)	loss 2.5292 (3.3466)	grad_norm 1.7785 (1.8775)	
[2022-01-23 21:19:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1100/1251]	eta 0:05:32 lr 0.000281	time 1.5936 (2.2022)	loss 3.7272 (3.3450)	grad_norm 2.0074 (1.8785)	
[2022-01-23 21:19:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1110/1251]	eta 0:05:10 lr 0.000281	time 2.4128 (2.2011)	loss 3.4207 (3.3438)	grad_norm 1.7704 (1.8781)	
[2022-01-23 21:20:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1120/1251]	eta 0:04:48 lr 0.000281	time 2.4898 (2.2002)	loss 3.6142 (3.3460)	grad_norm 2.0192 (1.8775)	
[2022-01-23 21:20:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1130/1251]	eta 0:04:26 lr 0.000281	time 2.2125 (2.2007)	loss 2.7383 (3.3468)	grad_norm 2.0881 (1.8774)	
[2022-01-23 21:20:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1140/1251]	eta 0:04:04 lr 0.000281	time 1.8262 (2.2013)	loss 3.9822 (3.3465)	grad_norm 1.6839 (1.8769)	
[2022-01-23 21:21:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1150/1251]	eta 0:03:42 lr 0.000281	time 1.6780 (2.2022)	loss 2.3736 (3.3443)	grad_norm 1.6387 (1.8763)	
[2022-01-23 21:21:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1160/1251]	eta 0:03:20 lr 0.000281	time 2.0540 (2.2014)	loss 3.2480 (3.3459)	grad_norm 1.6825 (1.8751)	
[2022-01-23 21:22:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1170/1251]	eta 0:02:58 lr 0.000281	time 2.5251 (2.2011)	loss 3.4409 (3.3450)	grad_norm 1.9381 (1.8759)	
[2022-01-23 21:22:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1180/1251]	eta 0:02:36 lr 0.000281	time 1.6284 (2.2002)	loss 2.9445 (3.3461)	grad_norm 1.8747 (1.8759)	
[2022-01-23 21:22:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1190/1251]	eta 0:02:14 lr 0.000280	time 2.2786 (2.1994)	loss 2.6471 (3.3454)	grad_norm 1.9010 (1.8755)	
[2022-01-23 21:23:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1200/1251]	eta 0:01:52 lr 0.000280	time 2.6012 (2.1989)	loss 2.1093 (3.3452)	grad_norm 1.8164 (1.8760)	
[2022-01-23 21:23:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1210/1251]	eta 0:01:30 lr 0.000280	time 2.2544 (2.1984)	loss 2.7937 (3.3408)	grad_norm 1.7145 (1.8754)	
[2022-01-23 21:23:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1220/1251]	eta 0:01:08 lr 0.000280	time 1.8057 (2.1974)	loss 3.7310 (3.3405)	grad_norm 1.8164 (1.8760)	
[2022-01-23 21:24:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1230/1251]	eta 0:00:46 lr 0.000280	time 2.4656 (2.1976)	loss 2.6558 (3.3384)	grad_norm 1.8058 (1.8760)	
[2022-01-23 21:24:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1240/1251]	eta 0:00:24 lr 0.000280	time 2.6986 (2.1983)	loss 3.3839 (3.3383)	grad_norm 2.3339 (1.8778)	
[2022-01-23 21:24:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [194/300][1250/1251]	eta 0:00:02 lr 0.000280	time 1.1750 (2.1933)	loss 3.8494 (3.3405)	grad_norm 1.8315 (1.8775)	
[2022-01-23 21:24:51 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 194 training takes 0:45:44
[2022-01-23 21:25:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.523 (18.523)	Loss 0.7964 (0.7964)	Acc@1 81.055 (81.055)	Acc@5 95.410 (95.410)	
[2022-01-23 21:25:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.572 (3.186)	Loss 0.8543 (0.9043)	Acc@1 79.199 (78.232)	Acc@5 95.508 (94.744)	
[2022-01-23 21:25:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.600 (2.484)	Loss 0.9161 (0.9080)	Acc@1 76.855 (78.227)	Acc@5 95.312 (94.643)	
[2022-01-23 21:26:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.615 (2.241)	Loss 0.9392 (0.9152)	Acc@1 77.637 (78.197)	Acc@5 94.141 (94.446)	
[2022-01-23 21:26:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.410 (2.140)	Loss 0.9670 (0.9171)	Acc@1 77.539 (78.218)	Acc@5 93.750 (94.403)	
[2022-01-23 21:26:26 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.232 Acc@5 94.338
[2022-01-23 21:26:26 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.2%
[2022-01-23 21:26:26 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.23%
[2022-01-23 21:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][0/1251]	eta 7:29:06 lr 0.000280	time 21.5402 (21.5402)	loss 3.6333 (3.6333)	grad_norm 2.0853 (2.0853)	
[2022-01-23 21:27:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][10/1251]	eta 1:21:14 lr 0.000280	time 2.1698 (3.9281)	loss 3.3996 (3.3210)	grad_norm 1.6571 (1.8316)	
[2022-01-23 21:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][20/1251]	eta 1:03:40 lr 0.000280	time 1.8196 (3.1033)	loss 2.8085 (3.2344)	grad_norm 1.7951 (1.7992)	
[2022-01-23 21:27:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][30/1251]	eta 0:57:08 lr 0.000280	time 1.5358 (2.8080)	loss 3.0199 (3.2256)	grad_norm 2.0590 (1.9016)	
[2022-01-23 21:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][40/1251]	eta 0:53:57 lr 0.000280	time 3.5419 (2.6732)	loss 4.0692 (3.3233)	grad_norm 1.9209 (1.9190)	
[2022-01-23 21:28:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][50/1251]	eta 0:52:18 lr 0.000280	time 2.4303 (2.6136)	loss 2.4592 (3.3174)	grad_norm 2.0241 (1.9067)	
[2022-01-23 21:29:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][60/1251]	eta 0:50:24 lr 0.000280	time 1.5553 (2.5396)	loss 3.8047 (3.3666)	grad_norm 1.8075 (1.8783)	
[2022-01-23 21:29:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][70/1251]	eta 0:49:23 lr 0.000280	time 1.8665 (2.5092)	loss 2.6537 (3.3675)	grad_norm 1.7944 (1.8842)	
[2022-01-23 21:29:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][80/1251]	eta 0:48:20 lr 0.000280	time 3.1666 (2.4773)	loss 3.4482 (3.3095)	grad_norm 1.5626 (1.8719)	
[2022-01-23 21:30:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][90/1251]	eta 0:47:14 lr 0.000280	time 2.1044 (2.4415)	loss 3.1971 (3.2991)	grad_norm 1.8981 (1.8676)	
[2022-01-23 21:30:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][100/1251]	eta 0:46:29 lr 0.000280	time 2.1291 (2.4239)	loss 4.0637 (3.3059)	grad_norm 1.9414 (1.8682)	
[2022-01-23 21:30:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][110/1251]	eta 0:45:27 lr 0.000280	time 1.9130 (2.3901)	loss 3.4272 (3.3216)	grad_norm 1.7989 (1.8691)	
[2022-01-23 21:31:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][120/1251]	eta 0:44:48 lr 0.000280	time 3.4601 (2.3771)	loss 3.8308 (3.3275)	grad_norm 2.1795 (1.8745)	
[2022-01-23 21:31:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][130/1251]	eta 0:44:07 lr 0.000280	time 1.6264 (2.3617)	loss 3.5390 (3.3350)	grad_norm 2.1729 (1.8773)	
[2022-01-23 21:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][140/1251]	eta 0:43:37 lr 0.000280	time 1.9549 (2.3562)	loss 3.2150 (3.3414)	grad_norm 1.8033 (1.8839)	
[2022-01-23 21:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][150/1251]	eta 0:43:02 lr 0.000280	time 1.7948 (2.3453)	loss 3.7762 (3.3511)	grad_norm 2.0636 (1.8803)	
[2022-01-23 21:32:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][160/1251]	eta 0:42:34 lr 0.000280	time 3.1167 (2.3412)	loss 3.4177 (3.3413)	grad_norm 1.9050 (1.8747)	
[2022-01-23 21:33:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][170/1251]	eta 0:41:58 lr 0.000280	time 1.5715 (2.3300)	loss 3.2626 (3.3265)	grad_norm 1.8758 (1.8701)	
[2022-01-23 21:33:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][180/1251]	eta 0:41:22 lr 0.000280	time 2.1471 (2.3182)	loss 3.7679 (3.3375)	grad_norm 2.3284 (1.8721)	
[2022-01-23 21:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][190/1251]	eta 0:40:48 lr 0.000280	time 1.8972 (2.3076)	loss 3.6117 (3.3337)	grad_norm 1.7377 (1.8723)	
[2022-01-23 21:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][200/1251]	eta 0:40:22 lr 0.000280	time 3.6365 (2.3052)	loss 3.5897 (3.3415)	grad_norm 1.9403 (1.8743)	
[2022-01-23 21:34:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][210/1251]	eta 0:39:51 lr 0.000279	time 2.1692 (2.2969)	loss 2.4832 (3.3487)	grad_norm 2.5541 (1.8799)	
[2022-01-23 21:34:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][220/1251]	eta 0:39:26 lr 0.000279	time 1.7620 (2.2952)	loss 3.2116 (3.3547)	grad_norm 1.7083 (1.8766)	
[2022-01-23 21:35:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][230/1251]	eta 0:39:02 lr 0.000279	time 1.7501 (2.2942)	loss 3.4163 (3.3556)	grad_norm 2.5882 (1.8783)	
[2022-01-23 21:35:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][240/1251]	eta 0:38:39 lr 0.000279	time 4.6597 (2.2945)	loss 3.0874 (3.3524)	grad_norm 1.7567 (1.8776)	
[2022-01-23 21:35:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][250/1251]	eta 0:38:07 lr 0.000279	time 1.8465 (2.2850)	loss 4.0974 (3.3538)	grad_norm 1.9594 (1.8736)	
[2022-01-23 21:36:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][260/1251]	eta 0:37:31 lr 0.000279	time 1.8672 (2.2720)	loss 3.3916 (3.3518)	grad_norm 2.1876 (1.8704)	
[2022-01-23 21:36:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][270/1251]	eta 0:37:03 lr 0.000279	time 1.9006 (2.2667)	loss 3.2456 (3.3556)	grad_norm 1.7951 (1.8705)	
[2022-01-23 21:37:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][280/1251]	eta 0:36:48 lr 0.000279	time 3.5851 (2.2747)	loss 4.0013 (3.3637)	grad_norm 1.9111 (1.8688)	
[2022-01-23 21:37:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][290/1251]	eta 0:36:25 lr 0.000279	time 2.0927 (2.2740)	loss 3.6490 (3.3615)	grad_norm 2.0070 (1.8672)	
[2022-01-23 21:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][300/1251]	eta 0:35:55 lr 0.000279	time 1.8856 (2.2665)	loss 2.4208 (3.3576)	grad_norm 1.6989 (1.8643)	
[2022-01-23 21:38:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][310/1251]	eta 0:35:31 lr 0.000279	time 1.8296 (2.2648)	loss 3.6581 (3.3585)	grad_norm 1.7466 (1.8621)	
[2022-01-23 21:38:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][320/1251]	eta 0:35:04 lr 0.000279	time 2.5872 (2.2607)	loss 3.7961 (3.3603)	grad_norm 1.7935 (1.8625)	
[2022-01-23 21:38:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][330/1251]	eta 0:34:38 lr 0.000279	time 1.9725 (2.2572)	loss 3.7715 (3.3579)	grad_norm 1.6566 (1.8598)	
[2022-01-23 21:39:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][340/1251]	eta 0:34:17 lr 0.000279	time 1.9680 (2.2581)	loss 3.6196 (3.3587)	grad_norm 1.9200 (1.8590)	
[2022-01-23 21:39:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][350/1251]	eta 0:33:48 lr 0.000279	time 1.6695 (2.2515)	loss 2.2337 (3.3571)	grad_norm 1.8924 (1.8574)	
[2022-01-23 21:39:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][360/1251]	eta 0:33:24 lr 0.000279	time 2.7426 (2.2496)	loss 2.7175 (3.3478)	grad_norm 2.0612 (1.8614)	
[2022-01-23 21:40:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][370/1251]	eta 0:32:59 lr 0.000279	time 2.3035 (2.2469)	loss 3.9580 (3.3491)	grad_norm 1.9518 (1.8627)	
[2022-01-23 21:40:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][380/1251]	eta 0:32:38 lr 0.000279	time 1.9441 (2.2482)	loss 3.0162 (3.3602)	grad_norm 1.7758 (1.8648)	
[2022-01-23 21:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][390/1251]	eta 0:32:14 lr 0.000279	time 2.6053 (2.2470)	loss 2.4233 (3.3584)	grad_norm 2.0212 (1.8667)	
[2022-01-23 21:41:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][400/1251]	eta 0:31:49 lr 0.000279	time 1.6822 (2.2444)	loss 3.3463 (3.3597)	grad_norm 1.8130 (1.8662)	
[2022-01-23 21:41:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][410/1251]	eta 0:31:25 lr 0.000279	time 2.4441 (2.2418)	loss 3.5690 (3.3618)	grad_norm 1.9295 (1.8659)	
[2022-01-23 21:42:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][420/1251]	eta 0:30:58 lr 0.000279	time 1.8075 (2.2368)	loss 3.1594 (3.3589)	grad_norm 1.6455 (1.8668)	
[2022-01-23 21:42:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][430/1251]	eta 0:30:39 lr 0.000279	time 3.6193 (2.2409)	loss 3.2689 (3.3615)	grad_norm 2.3032 (1.8668)	
[2022-01-23 21:42:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][440/1251]	eta 0:30:17 lr 0.000279	time 1.5658 (2.2405)	loss 3.7475 (3.3558)	grad_norm 1.7284 (1.8655)	
[2022-01-23 21:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][450/1251]	eta 0:29:54 lr 0.000279	time 3.0132 (2.2405)	loss 3.5505 (3.3481)	grad_norm 1.7069 (1.8644)	
[2022-01-23 21:43:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][460/1251]	eta 0:29:27 lr 0.000279	time 2.1964 (2.2351)	loss 3.0142 (3.3482)	grad_norm 1.8489 (1.8648)	
[2022-01-23 21:43:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][470/1251]	eta 0:29:02 lr 0.000279	time 1.5107 (2.2312)	loss 3.7321 (3.3481)	grad_norm 1.7222 (1.8636)	
[2022-01-23 21:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][480/1251]	eta 0:28:39 lr 0.000279	time 1.8800 (2.2303)	loss 2.4895 (3.3530)	grad_norm 2.5087 (1.8655)	
[2022-01-23 21:44:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][490/1251]	eta 0:28:16 lr 0.000278	time 3.1015 (2.2297)	loss 2.5644 (3.3509)	grad_norm 2.0158 (1.8666)	
[2022-01-23 21:45:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][500/1251]	eta 0:27:52 lr 0.000278	time 2.1808 (2.2268)	loss 3.5001 (3.3536)	grad_norm 1.4597 (1.8693)	
[2022-01-23 21:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][510/1251]	eta 0:27:31 lr 0.000278	time 2.1732 (2.2288)	loss 3.8791 (3.3553)	grad_norm 1.9134 (1.8700)	
[2022-01-23 21:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][520/1251]	eta 0:27:07 lr 0.000278	time 2.3020 (2.2267)	loss 3.3268 (3.3592)	grad_norm 2.0294 (1.8701)	
[2022-01-23 21:46:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][530/1251]	eta 0:26:46 lr 0.000278	time 3.6843 (2.2276)	loss 3.6363 (3.3595)	grad_norm 1.9108 (1.8720)	
[2022-01-23 21:46:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][540/1251]	eta 0:26:22 lr 0.000278	time 2.5377 (2.2261)	loss 3.5901 (3.3566)	grad_norm 2.2019 (1.8741)	
[2022-01-23 21:46:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][550/1251]	eta 0:26:00 lr 0.000278	time 1.9228 (2.2255)	loss 2.5950 (3.3560)	grad_norm 1.8155 (1.8750)	
[2022-01-23 21:47:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][560/1251]	eta 0:25:35 lr 0.000278	time 1.9684 (2.2215)	loss 3.8312 (3.3568)	grad_norm 2.0077 (1.8773)	
[2022-01-23 21:47:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][570/1251]	eta 0:25:13 lr 0.000278	time 3.4212 (2.2225)	loss 3.3627 (3.3542)	grad_norm 2.1846 (1.8767)	
[2022-01-23 21:47:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][580/1251]	eta 0:24:51 lr 0.000278	time 1.8881 (2.2232)	loss 3.3343 (3.3498)	grad_norm 1.7612 (1.8762)	
[2022-01-23 21:48:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][590/1251]	eta 0:24:28 lr 0.000278	time 1.9264 (2.2214)	loss 3.8913 (3.3563)	grad_norm 2.2383 (1.8784)	
[2022-01-23 21:48:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][600/1251]	eta 0:24:03 lr 0.000278	time 1.8203 (2.2174)	loss 3.8392 (3.3525)	grad_norm 1.5625 (1.8811)	
[2022-01-23 21:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][610/1251]	eta 0:23:39 lr 0.000278	time 2.8461 (2.2148)	loss 3.7001 (3.3501)	grad_norm 1.8730 (1.8819)	
[2022-01-23 21:49:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][620/1251]	eta 0:23:15 lr 0.000278	time 2.2246 (2.2121)	loss 3.9735 (3.3523)	grad_norm 1.7223 (1.8813)	
[2022-01-23 21:49:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][630/1251]	eta 0:22:54 lr 0.000278	time 1.9453 (2.2135)	loss 3.1032 (3.3532)	grad_norm 2.1622 (1.8818)	
[2022-01-23 21:50:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][640/1251]	eta 0:22:32 lr 0.000278	time 1.9197 (2.2137)	loss 4.0233 (3.3557)	grad_norm 2.1764 (1.8808)	
[2022-01-23 21:50:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][650/1251]	eta 0:22:10 lr 0.000278	time 3.2371 (2.2134)	loss 3.7034 (3.3564)	grad_norm 1.6994 (1.8797)	
[2022-01-23 21:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][660/1251]	eta 0:21:48 lr 0.000278	time 2.3855 (2.2145)	loss 3.4188 (3.3547)	grad_norm 1.9393 (1.8811)	
[2022-01-23 21:51:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][670/1251]	eta 0:21:27 lr 0.000278	time 2.1279 (2.2158)	loss 3.8006 (3.3572)	grad_norm 1.9523 (1.8815)	
[2022-01-23 21:51:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][680/1251]	eta 0:21:05 lr 0.000278	time 2.3508 (2.2168)	loss 3.1076 (3.3586)	grad_norm 1.7670 (1.8828)	
[2022-01-23 21:51:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][690/1251]	eta 0:20:44 lr 0.000278	time 3.4647 (2.2187)	loss 3.2230 (3.3605)	grad_norm 1.9064 (1.8837)	
[2022-01-23 21:52:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][700/1251]	eta 0:20:23 lr 0.000278	time 2.9116 (2.2196)	loss 2.5913 (3.3566)	grad_norm 1.9025 (1.8846)	
[2022-01-23 21:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][710/1251]	eta 0:19:59 lr 0.000278	time 1.9845 (2.2165)	loss 3.6763 (3.3562)	grad_norm 1.6302 (1.8847)	
[2022-01-23 21:53:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][720/1251]	eta 0:19:35 lr 0.000278	time 1.7297 (2.2132)	loss 3.6427 (3.3547)	grad_norm 1.9894 (1.8845)	
[2022-01-23 21:53:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][730/1251]	eta 0:19:11 lr 0.000278	time 1.8899 (2.2100)	loss 3.7574 (3.3570)	grad_norm 1.5576 (1.8855)	
[2022-01-23 21:53:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][740/1251]	eta 0:18:48 lr 0.000278	time 1.9033 (2.2077)	loss 3.7095 (3.3578)	grad_norm 1.7644 (1.8860)	
[2022-01-23 21:54:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][750/1251]	eta 0:18:25 lr 0.000278	time 2.3179 (2.2069)	loss 3.7803 (3.3619)	grad_norm 1.7012 (1.8866)	
[2022-01-23 21:54:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][760/1251]	eta 0:18:03 lr 0.000277	time 2.1631 (2.2066)	loss 3.4527 (3.3619)	grad_norm 1.6259 (1.8864)	
[2022-01-23 21:54:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][770/1251]	eta 0:17:41 lr 0.000277	time 2.1388 (2.2065)	loss 3.6565 (3.3604)	grad_norm 1.6523 (1.8854)	
[2022-01-23 21:55:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][780/1251]	eta 0:17:19 lr 0.000277	time 2.7864 (2.2078)	loss 3.7465 (3.3610)	grad_norm 1.6545 (1.8858)	
[2022-01-23 21:55:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][790/1251]	eta 0:16:58 lr 0.000277	time 2.8519 (2.2089)	loss 3.2269 (3.3621)	grad_norm 2.0531 (1.8856)	
[2022-01-23 21:55:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][800/1251]	eta 0:16:36 lr 0.000277	time 2.2038 (2.2087)	loss 3.0255 (3.3590)	grad_norm 2.1720 (1.8850)	
[2022-01-23 21:56:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][810/1251]	eta 0:16:13 lr 0.000277	time 1.9110 (2.2071)	loss 3.1289 (3.3579)	grad_norm 1.8520 (1.8851)	
[2022-01-23 21:56:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][820/1251]	eta 0:15:50 lr 0.000277	time 2.2060 (2.2062)	loss 3.1951 (3.3594)	grad_norm 1.8823 (1.8849)	
[2022-01-23 21:57:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][830/1251]	eta 0:15:29 lr 0.000277	time 2.8412 (2.2078)	loss 3.0620 (3.3577)	grad_norm 1.7029 (1.8844)	
[2022-01-23 21:57:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][840/1251]	eta 0:15:07 lr 0.000277	time 2.4677 (2.2081)	loss 3.5008 (3.3583)	grad_norm 1.6899 (1.8830)	
[2022-01-23 21:57:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][850/1251]	eta 0:14:44 lr 0.000277	time 1.9242 (2.2064)	loss 2.3660 (3.3550)	grad_norm 2.1163 (1.8849)	
[2022-01-23 21:58:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][860/1251]	eta 0:14:22 lr 0.000277	time 2.1851 (2.2047)	loss 3.2710 (3.3527)	grad_norm 1.9205 (1.8857)	
[2022-01-23 21:58:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][870/1251]	eta 0:13:59 lr 0.000277	time 2.0937 (2.2038)	loss 3.7522 (3.3514)	grad_norm 1.7969 (1.8853)	
[2022-01-23 21:58:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][880/1251]	eta 0:13:37 lr 0.000277	time 2.5902 (2.2027)	loss 3.7532 (3.3510)	grad_norm 1.6918 (1.8871)	
[2022-01-23 21:59:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][890/1251]	eta 0:13:15 lr 0.000277	time 1.8278 (2.2025)	loss 3.1661 (3.3503)	grad_norm 1.6531 (1.8869)	
[2022-01-23 21:59:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][900/1251]	eta 0:12:52 lr 0.000277	time 2.1971 (2.2021)	loss 2.9107 (3.3497)	grad_norm 1.7282 (1.8861)	
[2022-01-23 21:59:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][910/1251]	eta 0:12:30 lr 0.000277	time 2.2871 (2.2009)	loss 2.9215 (3.3501)	grad_norm 1.7163 (1.8843)	
[2022-01-23 22:00:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][920/1251]	eta 0:12:08 lr 0.000277	time 3.0346 (2.2017)	loss 3.5570 (3.3491)	grad_norm 1.9372 (1.8833)	
[2022-01-23 22:00:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][930/1251]	eta 0:11:46 lr 0.000277	time 2.3658 (2.2013)	loss 3.4500 (3.3527)	grad_norm 2.0645 (1.8840)	
[2022-01-23 22:00:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][940/1251]	eta 0:11:25 lr 0.000277	time 2.3912 (2.2037)	loss 3.4685 (3.3539)	grad_norm 2.1950 (1.8856)	
[2022-01-23 22:01:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][950/1251]	eta 0:11:03 lr 0.000277	time 2.1298 (2.2040)	loss 3.5141 (3.3556)	grad_norm 1.6802 (1.8856)	
[2022-01-23 22:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][960/1251]	eta 0:10:41 lr 0.000277	time 3.2105 (2.2054)	loss 3.3845 (3.3546)	grad_norm 1.7504 (1.8848)	
[2022-01-23 22:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][970/1251]	eta 0:10:19 lr 0.000277	time 3.1071 (2.2061)	loss 3.7646 (3.3572)	grad_norm 1.9769 (1.8841)	
[2022-01-23 22:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][980/1251]	eta 0:09:57 lr 0.000277	time 2.1647 (2.2056)	loss 3.6198 (3.3594)	grad_norm 1.7717 (1.8845)	
[2022-01-23 22:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][990/1251]	eta 0:09:35 lr 0.000277	time 1.9328 (2.2032)	loss 3.5306 (3.3603)	grad_norm 2.3558 (1.8860)	
[2022-01-23 22:03:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1000/1251]	eta 0:09:12 lr 0.000277	time 1.8737 (2.2012)	loss 3.8364 (3.3605)	grad_norm 2.1658 (1.8870)	
[2022-01-23 22:03:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1010/1251]	eta 0:08:50 lr 0.000277	time 2.4451 (2.1996)	loss 3.6375 (3.3624)	grad_norm 1.9030 (1.8875)	
[2022-01-23 22:03:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1020/1251]	eta 0:08:28 lr 0.000277	time 1.8366 (2.1994)	loss 3.6621 (3.3638)	grad_norm 1.5906 (1.8881)	
[2022-01-23 22:04:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1030/1251]	eta 0:08:06 lr 0.000276	time 1.8437 (2.2003)	loss 3.7556 (3.3640)	grad_norm 1.5671 (1.8871)	
[2022-01-23 22:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1040/1251]	eta 0:07:44 lr 0.000276	time 2.5729 (2.2015)	loss 3.0907 (3.3644)	grad_norm 1.8666 (1.8863)	
[2022-01-23 22:05:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1050/1251]	eta 0:07:22 lr 0.000276	time 2.5580 (2.2016)	loss 2.9071 (3.3645)	grad_norm 2.3201 (1.8866)	
[2022-01-23 22:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1060/1251]	eta 0:07:00 lr 0.000276	time 1.9523 (2.2018)	loss 3.6700 (3.3620)	grad_norm 1.7363 (1.8868)	
[2022-01-23 22:05:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1070/1251]	eta 0:06:38 lr 0.000276	time 1.6119 (2.2012)	loss 3.9889 (3.3618)	grad_norm 2.0020 (1.8867)	
[2022-01-23 22:06:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1080/1251]	eta 0:06:16 lr 0.000276	time 2.0831 (2.2004)	loss 2.8879 (3.3600)	grad_norm 1.8712 (1.8864)	
[2022-01-23 22:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1090/1251]	eta 0:05:54 lr 0.000276	time 2.5046 (2.2007)	loss 3.7654 (3.3606)	grad_norm 1.7228 (1.8856)	
[2022-01-23 22:06:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1100/1251]	eta 0:05:32 lr 0.000276	time 2.2890 (2.2006)	loss 2.5231 (3.3612)	grad_norm 2.1748 (1.8857)	
[2022-01-23 22:07:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1110/1251]	eta 0:05:10 lr 0.000276	time 1.8196 (2.1996)	loss 3.2970 (3.3607)	grad_norm 1.8657 (1.8853)	
[2022-01-23 22:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1120/1251]	eta 0:04:48 lr 0.000276	time 2.2661 (2.2003)	loss 2.2979 (3.3582)	grad_norm 1.7658 (1.8858)	
[2022-01-23 22:07:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1130/1251]	eta 0:04:26 lr 0.000276	time 3.1351 (2.2009)	loss 2.4568 (3.3553)	grad_norm 1.9516 (1.8869)	
[2022-01-23 22:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1140/1251]	eta 0:04:04 lr 0.000276	time 2.0128 (2.2010)	loss 2.9712 (3.3543)	grad_norm 1.5548 (1.8865)	
[2022-01-23 22:08:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1150/1251]	eta 0:03:42 lr 0.000276	time 1.7524 (2.1992)	loss 3.8232 (3.3562)	grad_norm 1.8326 (1.8863)	
[2022-01-23 22:08:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1160/1251]	eta 0:03:20 lr 0.000276	time 1.9346 (2.1989)	loss 2.9875 (3.3552)	grad_norm 1.7923 (1.8855)	
[2022-01-23 22:09:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1170/1251]	eta 0:02:58 lr 0.000276	time 2.4236 (2.1985)	loss 3.1899 (3.3541)	grad_norm 1.8944 (1.8844)	
[2022-01-23 22:09:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1180/1251]	eta 0:02:36 lr 0.000276	time 2.2473 (2.1976)	loss 3.1663 (3.3534)	grad_norm 1.7133 (1.8841)	
[2022-01-23 22:10:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1190/1251]	eta 0:02:13 lr 0.000276	time 2.2718 (2.1967)	loss 3.4449 (3.3549)	grad_norm 1.6039 (1.8840)	
[2022-01-23 22:10:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1200/1251]	eta 0:01:51 lr 0.000276	time 1.8791 (2.1955)	loss 3.0744 (3.3546)	grad_norm 1.7699 (1.8839)	
[2022-01-23 22:10:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1210/1251]	eta 0:01:30 lr 0.000276	time 2.6942 (2.1958)	loss 3.9070 (3.3558)	grad_norm 1.6819 (1.8832)	
[2022-01-23 22:11:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1220/1251]	eta 0:01:08 lr 0.000276	time 2.4417 (2.1960)	loss 3.4176 (3.3562)	grad_norm 2.1807 (1.8836)	
[2022-01-23 22:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1230/1251]	eta 0:00:46 lr 0.000276	time 1.9108 (2.1964)	loss 2.7932 (3.3559)	grad_norm 2.3148 (1.8844)	
[2022-01-23 22:11:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1240/1251]	eta 0:00:24 lr 0.000276	time 1.4863 (2.1976)	loss 2.6457 (3.3557)	grad_norm 2.1136 (1.8838)	
[2022-01-23 22:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [195/300][1250/1251]	eta 0:00:02 lr 0.000276	time 1.1838 (2.1923)	loss 3.8539 (3.3564)	grad_norm 2.1407 (1.8841)	
[2022-01-23 22:12:09 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 195 training takes 0:45:43
[2022-01-23 22:12:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.296 (18.296)	Loss 0.9208 (0.9208)	Acc@1 78.320 (78.320)	Acc@5 94.043 (94.043)	
[2022-01-23 22:12:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.238 (3.243)	Loss 0.7929 (0.9205)	Acc@1 80.762 (78.125)	Acc@5 96.094 (94.309)	
[2022-01-23 22:13:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.994 (2.444)	Loss 0.9028 (0.9165)	Acc@1 78.027 (78.288)	Acc@5 94.238 (94.387)	
[2022-01-23 22:13:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.571 (2.281)	Loss 0.8768 (0.9179)	Acc@1 79.395 (78.270)	Acc@5 94.434 (94.371)	
[2022-01-23 22:13:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.827 (2.130)	Loss 0.9007 (0.9192)	Acc@1 77.246 (78.161)	Acc@5 94.922 (94.329)	
[2022-01-23 22:13:43 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.174 Acc@5 94.302
[2022-01-23 22:13:43 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.2%
[2022-01-23 22:13:43 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.23%
[2022-01-23 22:14:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][0/1251]	eta 7:29:54 lr 0.000276	time 21.5784 (21.5784)	loss 3.5666 (3.5666)	grad_norm 2.3138 (2.3138)	
[2022-01-23 22:14:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][10/1251]	eta 1:24:37 lr 0.000276	time 1.7049 (4.0914)	loss 2.6127 (3.3904)	grad_norm 1.5256 (1.8483)	
[2022-01-23 22:14:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][20/1251]	eta 1:03:36 lr 0.000276	time 1.9523 (3.1001)	loss 3.2638 (3.1598)	grad_norm 1.9856 (1.8600)	
[2022-01-23 22:15:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][30/1251]	eta 0:56:09 lr 0.000276	time 1.3559 (2.7598)	loss 3.3199 (3.3285)	grad_norm 2.0414 (1.8364)	
[2022-01-23 22:15:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][40/1251]	eta 0:54:04 lr 0.000276	time 5.6742 (2.6796)	loss 3.3009 (3.3333)	grad_norm 1.7897 (1.8498)	
[2022-01-23 22:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][50/1251]	eta 0:51:50 lr 0.000275	time 2.0396 (2.5901)	loss 3.0441 (3.2919)	grad_norm 1.7939 (1.8733)	
[2022-01-23 22:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][60/1251]	eta 0:49:51 lr 0.000275	time 1.9623 (2.5113)	loss 2.7935 (3.2995)	grad_norm 2.2084 (1.8781)	
[2022-01-23 22:16:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][70/1251]	eta 0:48:11 lr 0.000275	time 1.4922 (2.4484)	loss 3.7819 (3.3077)	grad_norm 1.9670 (1.8958)	
[2022-01-23 22:17:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][80/1251]	eta 0:47:36 lr 0.000275	time 3.3655 (2.4391)	loss 3.3761 (3.3304)	grad_norm 1.9248 (1.9032)	
[2022-01-23 22:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][90/1251]	eta 0:46:54 lr 0.000275	time 2.3573 (2.4240)	loss 2.9924 (3.3229)	grad_norm 1.9062 (1.9119)	
[2022-01-23 22:17:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][100/1251]	eta 0:46:13 lr 0.000275	time 2.5336 (2.4100)	loss 2.7448 (3.3195)	grad_norm 2.2567 (1.9167)	
[2022-01-23 22:18:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][110/1251]	eta 0:45:34 lr 0.000275	time 1.9589 (2.3969)	loss 2.6079 (3.3124)	grad_norm 1.8393 (1.9136)	
[2022-01-23 22:18:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][120/1251]	eta 0:44:55 lr 0.000275	time 2.8699 (2.3830)	loss 3.5398 (3.2941)	grad_norm 1.8385 (1.9191)	
[2022-01-23 22:18:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][130/1251]	eta 0:44:22 lr 0.000275	time 2.4426 (2.3754)	loss 3.6666 (3.2982)	grad_norm 2.0239 (1.9237)	
[2022-01-23 22:19:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][140/1251]	eta 0:43:50 lr 0.000275	time 1.7935 (2.3674)	loss 3.3476 (3.3024)	grad_norm 2.2813 (1.9256)	
[2022-01-23 22:19:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][150/1251]	eta 0:43:01 lr 0.000275	time 1.9698 (2.3450)	loss 3.6353 (3.3150)	grad_norm 1.6646 (1.9237)	
[2022-01-23 22:19:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][160/1251]	eta 0:42:12 lr 0.000275	time 2.2635 (2.3210)	loss 2.8703 (3.2883)	grad_norm 1.8407 (1.9182)	
[2022-01-23 22:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][170/1251]	eta 0:41:41 lr 0.000275	time 1.9786 (2.3143)	loss 3.1118 (3.2788)	grad_norm 1.7519 (1.9155)	
[2022-01-23 22:20:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][180/1251]	eta 0:41:11 lr 0.000275	time 2.2567 (2.3072)	loss 4.1433 (3.2985)	grad_norm 1.9577 (1.9164)	
[2022-01-23 22:21:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][190/1251]	eta 0:40:44 lr 0.000275	time 2.2800 (2.3042)	loss 3.3960 (3.3049)	grad_norm 1.9881 (1.9162)	
[2022-01-23 22:21:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][200/1251]	eta 0:40:21 lr 0.000275	time 2.7748 (2.3037)	loss 2.3198 (3.2973)	grad_norm 1.7712 (1.9127)	
[2022-01-23 22:21:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][210/1251]	eta 0:39:48 lr 0.000275	time 2.2606 (2.2947)	loss 2.9051 (3.2864)	grad_norm 1.7712 (1.9130)	
[2022-01-23 22:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][220/1251]	eta 0:39:19 lr 0.000275	time 1.7650 (2.2888)	loss 2.4637 (3.2907)	grad_norm 1.7001 (1.9069)	
[2022-01-23 22:22:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][230/1251]	eta 0:38:49 lr 0.000275	time 1.8904 (2.2817)	loss 2.8745 (3.2873)	grad_norm 2.1918 (1.9059)	
[2022-01-23 22:22:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][240/1251]	eta 0:38:26 lr 0.000275	time 3.1728 (2.2819)	loss 3.2116 (3.2886)	grad_norm 1.6846 (1.9047)	
[2022-01-23 22:23:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][250/1251]	eta 0:38:05 lr 0.000275	time 2.5745 (2.2828)	loss 3.6054 (3.2786)	grad_norm 1.7903 (1.9051)	
[2022-01-23 22:23:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][260/1251]	eta 0:37:30 lr 0.000275	time 1.6654 (2.2712)	loss 2.3013 (3.2699)	grad_norm 1.8892 (1.9029)	
[2022-01-23 22:23:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][270/1251]	eta 0:37:00 lr 0.000275	time 2.2373 (2.2634)	loss 3.1092 (3.2686)	grad_norm 1.7948 (1.9004)	
[2022-01-23 22:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][280/1251]	eta 0:36:32 lr 0.000275	time 2.1847 (2.2577)	loss 3.4597 (3.2779)	grad_norm 2.3069 (1.9005)	
[2022-01-23 22:24:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][290/1251]	eta 0:36:09 lr 0.000275	time 2.7406 (2.2579)	loss 2.1651 (3.2633)	grad_norm 1.8378 (1.8988)	
[2022-01-23 22:25:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][300/1251]	eta 0:35:44 lr 0.000275	time 2.6073 (2.2553)	loss 3.7450 (3.2637)	grad_norm 1.9187 (1.8983)	
[2022-01-23 22:25:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][310/1251]	eta 0:35:24 lr 0.000275	time 2.1398 (2.2576)	loss 3.5670 (3.2741)	grad_norm 2.0314 (1.8999)	
[2022-01-23 22:25:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][320/1251]	eta 0:34:57 lr 0.000274	time 2.5244 (2.2528)	loss 3.4117 (3.2684)	grad_norm 2.2125 (1.8991)	
[2022-01-23 22:26:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][330/1251]	eta 0:34:31 lr 0.000274	time 2.0860 (2.2490)	loss 3.8411 (3.2729)	grad_norm 2.0787 (1.8999)	
[2022-01-23 22:26:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][340/1251]	eta 0:34:07 lr 0.000274	time 2.4979 (2.2472)	loss 3.1936 (3.2668)	grad_norm 1.8792 (1.9000)	
[2022-01-23 22:26:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][350/1251]	eta 0:33:43 lr 0.000274	time 1.8619 (2.2463)	loss 3.3947 (3.2702)	grad_norm 1.8370 (1.8998)	
[2022-01-23 22:27:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][360/1251]	eta 0:33:18 lr 0.000274	time 1.9233 (2.2429)	loss 2.9003 (3.2718)	grad_norm 1.7335 (1.8994)	
[2022-01-23 22:27:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][370/1251]	eta 0:32:51 lr 0.000274	time 2.3931 (2.2372)	loss 3.2219 (3.2699)	grad_norm 1.9849 (1.8978)	
[2022-01-23 22:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][380/1251]	eta 0:32:25 lr 0.000274	time 2.8701 (2.2333)	loss 4.0939 (3.2770)	grad_norm 1.7902 (1.8989)	
[2022-01-23 22:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][390/1251]	eta 0:31:59 lr 0.000274	time 2.5690 (2.2293)	loss 3.4863 (3.2748)	grad_norm 1.7132 (1.8995)	
[2022-01-23 22:28:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][400/1251]	eta 0:31:34 lr 0.000274	time 1.7567 (2.2265)	loss 3.6550 (3.2795)	grad_norm 1.8950 (1.8991)	
[2022-01-23 22:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][410/1251]	eta 0:31:12 lr 0.000274	time 1.8484 (2.2261)	loss 3.5335 (3.2779)	grad_norm 1.9538 (1.8968)	
[2022-01-23 22:29:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][420/1251]	eta 0:30:54 lr 0.000274	time 3.5069 (2.2313)	loss 4.2758 (3.2801)	grad_norm 2.4368 (1.8997)	
[2022-01-23 22:29:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][430/1251]	eta 0:30:36 lr 0.000274	time 3.2070 (2.2364)	loss 3.4663 (3.2857)	grad_norm 1.8054 (1.9015)	
[2022-01-23 22:30:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][440/1251]	eta 0:30:09 lr 0.000274	time 1.5500 (2.2310)	loss 3.4940 (3.2874)	grad_norm 2.8795 (1.9031)	
[2022-01-23 22:30:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][450/1251]	eta 0:29:43 lr 0.000274	time 2.2195 (2.2271)	loss 3.8213 (3.2889)	grad_norm 1.8647 (1.9041)	
[2022-01-23 22:30:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][460/1251]	eta 0:29:21 lr 0.000274	time 3.3881 (2.2267)	loss 3.5635 (3.2875)	grad_norm 2.2471 (1.9061)	
[2022-01-23 22:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][470/1251]	eta 0:28:59 lr 0.000274	time 2.8329 (2.2272)	loss 2.6772 (3.2936)	grad_norm 1.8075 (1.9046)	
[2022-01-23 22:31:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][480/1251]	eta 0:28:37 lr 0.000274	time 2.2629 (2.2281)	loss 2.7584 (3.2908)	grad_norm 1.8619 (1.9034)	
[2022-01-23 22:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][490/1251]	eta 0:28:16 lr 0.000274	time 2.0265 (2.2298)	loss 3.4447 (3.2968)	grad_norm 1.9516 (1.9028)	
[2022-01-23 22:32:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][500/1251]	eta 0:27:55 lr 0.000274	time 3.2454 (2.2307)	loss 3.7794 (3.3022)	grad_norm 2.0297 (1.9044)	
[2022-01-23 22:32:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][510/1251]	eta 0:27:31 lr 0.000274	time 2.1796 (2.2294)	loss 2.6796 (3.3021)	grad_norm 2.0482 (1.9058)	
[2022-01-23 22:33:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][520/1251]	eta 0:27:06 lr 0.000274	time 1.6494 (2.2244)	loss 3.5950 (3.3057)	grad_norm 1.9341 (1.9057)	
[2022-01-23 22:33:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][530/1251]	eta 0:26:41 lr 0.000274	time 2.1273 (2.2218)	loss 3.8196 (3.3102)	grad_norm 1.8141 (1.9040)	
[2022-01-23 22:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][540/1251]	eta 0:26:20 lr 0.000274	time 3.4539 (2.2232)	loss 2.6818 (3.3100)	grad_norm 1.8032 (1.9032)	
[2022-01-23 22:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][550/1251]	eta 0:25:55 lr 0.000274	time 1.5871 (2.2195)	loss 2.4068 (3.3105)	grad_norm 1.7151 (1.9011)	
[2022-01-23 22:34:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][560/1251]	eta 0:25:32 lr 0.000274	time 1.5427 (2.2175)	loss 3.0561 (3.3090)	grad_norm 1.9018 (1.9013)	
[2022-01-23 22:34:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][570/1251]	eta 0:25:07 lr 0.000274	time 1.5956 (2.2144)	loss 3.7968 (3.3136)	grad_norm 2.1523 (1.9000)	
[2022-01-23 22:35:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][580/1251]	eta 0:24:44 lr 0.000274	time 2.2113 (2.2130)	loss 3.2520 (3.3121)	grad_norm 1.8263 (1.8997)	
[2022-01-23 22:35:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][590/1251]	eta 0:24:22 lr 0.000274	time 2.1765 (2.2123)	loss 3.5473 (3.3130)	grad_norm 1.6505 (1.8986)	
[2022-01-23 22:35:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][600/1251]	eta 0:24:01 lr 0.000273	time 2.0348 (2.2146)	loss 3.7710 (3.3155)	grad_norm 1.8556 (1.9002)	
[2022-01-23 22:36:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][610/1251]	eta 0:23:39 lr 0.000273	time 2.1914 (2.2147)	loss 3.6388 (3.3183)	grad_norm 2.0376 (1.9021)	
[2022-01-23 22:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][620/1251]	eta 0:23:16 lr 0.000273	time 2.2783 (2.2127)	loss 2.5389 (3.3203)	grad_norm 2.0379 (1.9012)	
[2022-01-23 22:36:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][630/1251]	eta 0:22:53 lr 0.000273	time 1.7287 (2.2118)	loss 3.7722 (3.3222)	grad_norm 2.4624 (1.9037)	
[2022-01-23 22:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][640/1251]	eta 0:22:33 lr 0.000273	time 2.2983 (2.2147)	loss 3.4478 (3.3266)	grad_norm 1.7235 (1.9046)	
[2022-01-23 22:37:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][650/1251]	eta 0:22:12 lr 0.000273	time 2.6401 (2.2164)	loss 2.4480 (3.3278)	grad_norm 2.0463 (1.9051)	
[2022-01-23 22:38:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][660/1251]	eta 0:21:49 lr 0.000273	time 1.7392 (2.2157)	loss 3.6528 (3.3324)	grad_norm 1.8321 (1.9052)	
[2022-01-23 22:38:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][670/1251]	eta 0:21:26 lr 0.000273	time 2.2340 (2.2144)	loss 3.8966 (3.3360)	grad_norm 1.7679 (1.9038)	
[2022-01-23 22:38:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][680/1251]	eta 0:21:04 lr 0.000273	time 3.1048 (2.2138)	loss 3.5787 (3.3369)	grad_norm 1.9592 (1.9049)	
[2022-01-23 22:39:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][690/1251]	eta 0:20:41 lr 0.000273	time 2.0714 (2.2130)	loss 2.5499 (3.3357)	grad_norm 2.0065 (1.9045)	
[2022-01-23 22:39:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][700/1251]	eta 0:20:19 lr 0.000273	time 2.2362 (2.2124)	loss 3.7781 (3.3376)	grad_norm 1.9140 (1.9036)	
[2022-01-23 22:39:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][710/1251]	eta 0:19:57 lr 0.000273	time 1.8142 (2.2129)	loss 2.4639 (3.3323)	grad_norm 1.7199 (1.9038)	
[2022-01-23 22:40:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][720/1251]	eta 0:19:35 lr 0.000273	time 2.7958 (2.2145)	loss 3.3146 (3.3331)	grad_norm 1.7079 (1.9020)	
[2022-01-23 22:40:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][730/1251]	eta 0:19:13 lr 0.000273	time 2.2424 (2.2143)	loss 3.1728 (3.3309)	grad_norm 1.5862 (1.9012)	
[2022-01-23 22:41:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][740/1251]	eta 0:18:52 lr 0.000273	time 2.0537 (2.2156)	loss 3.3746 (3.3340)	grad_norm 1.9073 (1.9027)	
[2022-01-23 22:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][750/1251]	eta 0:18:28 lr 0.000273	time 1.6169 (2.2128)	loss 3.6239 (3.3338)	grad_norm 1.6264 (1.9033)	
[2022-01-23 22:41:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][760/1251]	eta 0:18:05 lr 0.000273	time 2.7505 (2.2118)	loss 3.7496 (3.3334)	grad_norm 1.9730 (1.9027)	
[2022-01-23 22:42:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][770/1251]	eta 0:17:43 lr 0.000273	time 1.8960 (2.2101)	loss 4.1944 (3.3370)	grad_norm 2.2252 (1.9029)	
[2022-01-23 22:42:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][780/1251]	eta 0:17:20 lr 0.000273	time 1.8700 (2.2087)	loss 2.9558 (3.3355)	grad_norm 1.8532 (1.9022)	
[2022-01-23 22:42:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][790/1251]	eta 0:16:58 lr 0.000273	time 2.0505 (2.2100)	loss 3.2423 (3.3370)	grad_norm 2.2673 (1.9021)	
[2022-01-23 22:43:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][800/1251]	eta 0:16:36 lr 0.000273	time 2.5261 (2.2098)	loss 3.8513 (3.3376)	grad_norm 1.7699 (1.9058)	
[2022-01-23 22:43:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][810/1251]	eta 0:16:13 lr 0.000273	time 2.0720 (2.2081)	loss 3.5780 (3.3384)	grad_norm 1.7701 (1.9060)	
[2022-01-23 22:43:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][820/1251]	eta 0:15:52 lr 0.000273	time 1.8668 (2.2097)	loss 2.7854 (3.3363)	grad_norm 1.6937 (1.9072)	
[2022-01-23 22:44:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][830/1251]	eta 0:15:30 lr 0.000273	time 2.1385 (2.2107)	loss 2.6618 (3.3341)	grad_norm 2.0155 (1.9070)	
[2022-01-23 22:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][840/1251]	eta 0:15:08 lr 0.000273	time 1.8089 (2.2102)	loss 3.3636 (3.3335)	grad_norm 1.8185 (1.9063)	
[2022-01-23 22:45:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][850/1251]	eta 0:14:46 lr 0.000273	time 2.8762 (2.2100)	loss 3.4217 (3.3316)	grad_norm 1.6878 (1.9063)	
[2022-01-23 22:45:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][860/1251]	eta 0:14:23 lr 0.000273	time 2.1528 (2.2096)	loss 3.0321 (3.3317)	grad_norm 1.7461 (1.9061)	
[2022-01-23 22:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][870/1251]	eta 0:14:01 lr 0.000272	time 2.2631 (2.2079)	loss 3.0126 (3.3294)	grad_norm 2.2735 (1.9063)	
[2022-01-23 22:46:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][880/1251]	eta 0:13:39 lr 0.000272	time 1.9822 (2.2078)	loss 3.1826 (3.3293)	grad_norm 1.7184 (1.9077)	
[2022-01-23 22:46:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][890/1251]	eta 0:13:17 lr 0.000272	time 3.4734 (2.2097)	loss 2.5704 (3.3285)	grad_norm 1.6016 (1.9074)	
[2022-01-23 22:46:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][900/1251]	eta 0:12:55 lr 0.000272	time 2.4874 (2.2094)	loss 2.7334 (3.3281)	grad_norm 1.6406 (1.9063)	
[2022-01-23 22:47:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][910/1251]	eta 0:12:33 lr 0.000272	time 2.4764 (2.2087)	loss 3.2990 (3.3287)	grad_norm 1.8753 (1.9053)	
[2022-01-23 22:47:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][920/1251]	eta 0:12:10 lr 0.000272	time 2.8136 (2.2074)	loss 3.6183 (3.3318)	grad_norm 1.9169 (1.9053)	
[2022-01-23 22:47:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][930/1251]	eta 0:11:47 lr 0.000272	time 1.6518 (2.2050)	loss 2.7331 (3.3298)	grad_norm 1.8893 (1.9060)	
[2022-01-23 22:48:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][940/1251]	eta 0:11:25 lr 0.000272	time 2.0758 (2.2035)	loss 3.1991 (3.3293)	grad_norm 1.9267 (1.9060)	
[2022-01-23 22:48:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][950/1251]	eta 0:11:03 lr 0.000272	time 2.4394 (2.2033)	loss 4.0966 (3.3293)	grad_norm 1.7322 (1.9056)	
[2022-01-23 22:49:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][960/1251]	eta 0:10:41 lr 0.000272	time 3.0433 (2.2031)	loss 3.5849 (3.3312)	grad_norm 1.7521 (1.9046)	
[2022-01-23 22:49:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][970/1251]	eta 0:10:19 lr 0.000272	time 2.1643 (2.2048)	loss 2.7933 (3.3311)	grad_norm 2.0581 (1.9059)	
[2022-01-23 22:49:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][980/1251]	eta 0:09:57 lr 0.000272	time 1.8758 (2.2050)	loss 3.9538 (3.3310)	grad_norm 1.7182 (1.9056)	
[2022-01-23 22:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][990/1251]	eta 0:09:35 lr 0.000272	time 2.2333 (2.2058)	loss 3.7996 (3.3329)	grad_norm 2.3577 (1.9059)	
[2022-01-23 22:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1000/1251]	eta 0:09:13 lr 0.000272	time 2.7415 (2.2049)	loss 2.9411 (3.3351)	grad_norm 1.8124 (1.9072)	
[2022-01-23 22:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1010/1251]	eta 0:08:51 lr 0.000272	time 2.9057 (2.2052)	loss 3.4414 (3.3335)	grad_norm 1.7174 (1.9075)	
[2022-01-23 22:51:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1020/1251]	eta 0:08:29 lr 0.000272	time 1.9479 (2.2043)	loss 3.9115 (3.3359)	grad_norm 1.8606 (1.9078)	
[2022-01-23 22:51:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1030/1251]	eta 0:08:06 lr 0.000272	time 1.6607 (2.2024)	loss 4.0379 (3.3368)	grad_norm 1.8681 (1.9067)	
[2022-01-23 22:51:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1040/1251]	eta 0:07:44 lr 0.000272	time 2.6965 (2.2029)	loss 3.6609 (3.3391)	grad_norm 2.2932 (1.9074)	
[2022-01-23 22:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1050/1251]	eta 0:07:22 lr 0.000272	time 2.7817 (2.2039)	loss 3.7390 (3.3405)	grad_norm 1.8363 (1.9081)	
[2022-01-23 22:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1060/1251]	eta 0:07:01 lr 0.000272	time 2.0813 (2.2043)	loss 3.9726 (3.3412)	grad_norm 2.3285 (1.9085)	
[2022-01-23 22:53:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1070/1251]	eta 0:06:38 lr 0.000272	time 1.6917 (2.2032)	loss 2.6299 (3.3398)	grad_norm 1.8928 (1.9078)	
[2022-01-23 22:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1080/1251]	eta 0:06:16 lr 0.000272	time 1.6615 (2.2035)	loss 2.4916 (3.3401)	grad_norm 1.7712 (1.9071)	
[2022-01-23 22:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1090/1251]	eta 0:05:54 lr 0.000272	time 2.4240 (2.2028)	loss 3.4076 (3.3409)	grad_norm 1.7417 (1.9067)	
[2022-01-23 22:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1100/1251]	eta 0:05:32 lr 0.000272	time 1.9442 (2.2014)	loss 2.6218 (3.3411)	grad_norm 1.5633 (1.9056)	
[2022-01-23 22:54:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1110/1251]	eta 0:05:10 lr 0.000272	time 1.6002 (2.2008)	loss 2.2061 (3.3387)	grad_norm 1.9597 (1.9056)	
[2022-01-23 22:54:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1120/1251]	eta 0:04:48 lr 0.000272	time 1.6925 (2.1999)	loss 3.1491 (3.3406)	grad_norm 1.8302 (1.9053)	
[2022-01-23 22:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1130/1251]	eta 0:04:26 lr 0.000272	time 2.4684 (2.2003)	loss 3.8631 (3.3422)	grad_norm 2.0240 (1.9066)	
[2022-01-23 22:55:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1140/1251]	eta 0:04:04 lr 0.000271	time 1.8041 (2.1994)	loss 3.3532 (3.3442)	grad_norm 1.6417 (1.9065)	
[2022-01-23 22:55:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1150/1251]	eta 0:03:42 lr 0.000271	time 2.5135 (2.1992)	loss 2.5701 (3.3439)	grad_norm 1.8597 (1.9069)	
[2022-01-23 22:56:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1160/1251]	eta 0:03:20 lr 0.000271	time 1.9653 (2.2015)	loss 3.3464 (3.3449)	grad_norm 1.7171 (1.9067)	
[2022-01-23 22:56:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1170/1251]	eta 0:02:58 lr 0.000271	time 2.5213 (2.2026)	loss 2.5312 (3.3435)	grad_norm 1.8718 (1.9066)	
[2022-01-23 22:57:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1180/1251]	eta 0:02:36 lr 0.000271	time 1.7391 (2.2025)	loss 3.3573 (3.3432)	grad_norm 1.6749 (1.9060)	
[2022-01-23 22:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1190/1251]	eta 0:02:14 lr 0.000271	time 1.9888 (2.2013)	loss 3.6955 (3.3451)	grad_norm 1.8321 (1.9053)	
[2022-01-23 22:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1200/1251]	eta 0:01:52 lr 0.000271	time 1.8427 (2.2003)	loss 3.5445 (3.3472)	grad_norm 1.8934 (1.9047)	
[2022-01-23 22:58:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1210/1251]	eta 0:01:30 lr 0.000271	time 1.7267 (2.1983)	loss 3.3259 (3.3472)	grad_norm 2.0254 (1.9051)	
[2022-01-23 22:58:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1220/1251]	eta 0:01:08 lr 0.000271	time 2.0180 (2.1974)	loss 3.9536 (3.3455)	grad_norm 2.3121 (1.9053)	
[2022-01-23 22:58:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1230/1251]	eta 0:00:46 lr 0.000271	time 2.2304 (2.1987)	loss 3.8564 (3.3455)	grad_norm 1.9180 (1.9058)	
[2022-01-23 22:59:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1240/1251]	eta 0:00:24 lr 0.000271	time 1.7055 (2.1995)	loss 2.9227 (3.3455)	grad_norm 1.8473 (1.9055)	
[2022-01-23 22:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [196/300][1250/1251]	eta 0:00:02 lr 0.000271	time 1.1883 (2.1942)	loss 2.4368 (3.3448)	grad_norm 2.7521 (1.9053)	
[2022-01-23 22:59:28 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 196 training takes 0:45:45
[2022-01-23 22:59:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.615 (18.615)	Loss 0.8878 (0.8878)	Acc@1 79.688 (79.688)	Acc@5 94.043 (94.043)	
[2022-01-23 23:00:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.592 (3.187)	Loss 0.8784 (0.9241)	Acc@1 79.395 (78.489)	Acc@5 94.238 (94.300)	
[2022-01-23 23:00:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.941 (2.445)	Loss 0.9541 (0.9284)	Acc@1 77.930 (78.344)	Acc@5 94.336 (94.303)	
[2022-01-23 23:00:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.277 (2.290)	Loss 0.8920 (0.9303)	Acc@1 79.395 (78.188)	Acc@5 94.824 (94.386)	
[2022-01-23 23:00:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.563 (2.170)	Loss 0.9602 (0.9336)	Acc@1 79.004 (78.142)	Acc@5 93.848 (94.334)	
[2022-01-23 23:01:04 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.090 Acc@5 94.274
[2022-01-23 23:01:04 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.1%
[2022-01-23 23:01:04 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.23%
[2022-01-23 23:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][0/1251]	eta 7:39:19 lr 0.000271	time 22.0298 (22.0298)	loss 3.6029 (3.6029)	grad_norm 2.0025 (2.0025)	
[2022-01-23 23:01:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][10/1251]	eta 1:24:58 lr 0.000271	time 2.4635 (4.1083)	loss 2.5746 (3.3504)	grad_norm 1.9031 (2.0820)	
[2022-01-23 23:02:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][20/1251]	eta 1:05:42 lr 0.000271	time 1.5417 (3.2026)	loss 3.7556 (3.2677)	grad_norm 1.8287 (2.0088)	
[2022-01-23 23:02:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][30/1251]	eta 0:59:43 lr 0.000271	time 1.8093 (2.9348)	loss 4.2138 (3.3456)	grad_norm 2.2054 (1.9490)	
[2022-01-23 23:02:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][40/1251]	eta 0:55:27 lr 0.000271	time 2.9533 (2.7477)	loss 3.8393 (3.3076)	grad_norm 1.8892 (1.9473)	
[2022-01-23 23:03:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][50/1251]	eta 0:53:18 lr 0.000271	time 3.2229 (2.6635)	loss 3.5836 (3.2644)	grad_norm 1.8041 (1.9389)	
[2022-01-23 23:03:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][60/1251]	eta 0:51:17 lr 0.000271	time 2.4247 (2.5841)	loss 2.5702 (3.2984)	grad_norm 1.7811 (1.9269)	
[2022-01-23 23:04:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][70/1251]	eta 0:49:41 lr 0.000271	time 1.8797 (2.5249)	loss 3.7208 (3.3312)	grad_norm 1.9662 (1.9135)	
[2022-01-23 23:04:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][80/1251]	eta 0:48:27 lr 0.000271	time 2.5609 (2.4832)	loss 3.3218 (3.3278)	grad_norm 2.1360 (1.9160)	
[2022-01-23 23:04:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][90/1251]	eta 0:47:42 lr 0.000271	time 2.8718 (2.4655)	loss 4.2756 (3.3148)	grad_norm 1.7664 (1.9205)	
[2022-01-23 23:05:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][100/1251]	eta 0:46:53 lr 0.000271	time 3.0683 (2.4442)	loss 3.5124 (3.3347)	grad_norm 2.0051 (1.9234)	
[2022-01-23 23:05:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][110/1251]	eta 0:45:55 lr 0.000271	time 1.7723 (2.4150)	loss 3.2585 (3.3200)	grad_norm 1.8126 (1.9252)	
[2022-01-23 23:05:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][120/1251]	eta 0:45:13 lr 0.000271	time 2.3272 (2.3989)	loss 4.0493 (3.3248)	grad_norm 2.7813 (1.9330)	
[2022-01-23 23:06:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][130/1251]	eta 0:44:20 lr 0.000271	time 1.6421 (2.3738)	loss 3.5900 (3.3142)	grad_norm 1.9263 (1.9357)	
[2022-01-23 23:06:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][140/1251]	eta 0:43:41 lr 0.000271	time 2.6266 (2.3593)	loss 3.1327 (3.3187)	grad_norm 2.1234 (1.9378)	
[2022-01-23 23:06:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][150/1251]	eta 0:42:55 lr 0.000271	time 2.1969 (2.3393)	loss 3.2932 (3.3320)	grad_norm 1.7509 (1.9414)	
[2022-01-23 23:07:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][160/1251]	eta 0:42:11 lr 0.000271	time 1.8759 (2.3202)	loss 3.3592 (3.3373)	grad_norm 2.0054 (1.9370)	
[2022-01-23 23:07:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][170/1251]	eta 0:41:28 lr 0.000270	time 1.6331 (2.3024)	loss 3.4586 (3.3380)	grad_norm 2.2700 (1.9376)	
[2022-01-23 23:08:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][180/1251]	eta 0:40:59 lr 0.000270	time 1.6577 (2.2962)	loss 2.1461 (3.3350)	grad_norm 1.7833 (1.9329)	
[2022-01-23 23:08:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][190/1251]	eta 0:40:33 lr 0.000270	time 2.1299 (2.2938)	loss 3.2740 (3.3423)	grad_norm 1.7053 (1.9284)	
[2022-01-23 23:08:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][200/1251]	eta 0:40:10 lr 0.000270	time 1.7967 (2.2934)	loss 3.4446 (3.3472)	grad_norm 1.9586 (1.9241)	
[2022-01-23 23:09:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][210/1251]	eta 0:39:41 lr 0.000270	time 1.8850 (2.2882)	loss 3.5873 (3.3556)	grad_norm 1.9048 (1.9207)	
[2022-01-23 23:09:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][220/1251]	eta 0:39:17 lr 0.000270	time 2.2072 (2.2864)	loss 3.5466 (3.3588)	grad_norm 1.8498 (1.9197)	
[2022-01-23 23:09:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][230/1251]	eta 0:38:50 lr 0.000270	time 2.4187 (2.2828)	loss 2.7947 (3.3524)	grad_norm 1.9481 (1.9168)	
[2022-01-23 23:10:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][240/1251]	eta 0:38:29 lr 0.000270	time 2.2312 (2.2843)	loss 3.4834 (3.3605)	grad_norm 1.8124 (1.9128)	
[2022-01-23 23:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][250/1251]	eta 0:38:01 lr 0.000270	time 1.8826 (2.2794)	loss 4.1802 (3.3499)	grad_norm 1.6164 (1.9118)	
[2022-01-23 23:10:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][260/1251]	eta 0:37:30 lr 0.000270	time 2.0044 (2.2707)	loss 2.4868 (3.3459)	grad_norm 1.7186 (1.9156)	
[2022-01-23 23:11:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][270/1251]	eta 0:37:06 lr 0.000270	time 2.2044 (2.2699)	loss 3.6124 (3.3495)	grad_norm 1.9041 (1.9125)	
[2022-01-23 23:11:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][280/1251]	eta 0:36:39 lr 0.000270	time 2.1627 (2.2649)	loss 3.2431 (3.3434)	grad_norm 1.6489 (1.9076)	
[2022-01-23 23:12:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][290/1251]	eta 0:36:08 lr 0.000270	time 1.8751 (2.2565)	loss 3.9788 (3.3499)	grad_norm 1.8716 (1.9081)	
[2022-01-23 23:12:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][300/1251]	eta 0:35:41 lr 0.000270	time 2.2523 (2.2522)	loss 3.5827 (3.3561)	grad_norm 1.9956 (1.9085)	
[2022-01-23 23:12:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][310/1251]	eta 0:35:15 lr 0.000270	time 1.8713 (2.2479)	loss 3.6345 (3.3562)	grad_norm 2.2509 (1.9102)	
[2022-01-23 23:13:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][320/1251]	eta 0:34:50 lr 0.000270	time 2.0976 (2.2455)	loss 2.2738 (3.3504)	grad_norm 1.6759 (1.9069)	
[2022-01-23 23:13:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][330/1251]	eta 0:34:24 lr 0.000270	time 1.7930 (2.2413)	loss 3.1801 (3.3485)	grad_norm 1.8424 (1.9061)	
[2022-01-23 23:13:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][340/1251]	eta 0:33:58 lr 0.000270	time 2.6148 (2.2375)	loss 3.5075 (3.3488)	grad_norm 1.6688 (1.9050)	
[2022-01-23 23:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][350/1251]	eta 0:33:37 lr 0.000270	time 2.5619 (2.2394)	loss 3.0519 (3.3489)	grad_norm 1.6431 (1.9041)	
[2022-01-23 23:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][360/1251]	eta 0:33:12 lr 0.000270	time 1.8118 (2.2367)	loss 3.7850 (3.3512)	grad_norm 1.8995 (1.9025)	
[2022-01-23 23:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][370/1251]	eta 0:32:54 lr 0.000270	time 2.3622 (2.2410)	loss 3.3006 (3.3429)	grad_norm 1.7518 (1.9054)	
[2022-01-23 23:15:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][380/1251]	eta 0:32:33 lr 0.000270	time 1.5758 (2.2425)	loss 3.6016 (3.3382)	grad_norm 1.7978 (1.9067)	
[2022-01-23 23:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][390/1251]	eta 0:32:09 lr 0.000270	time 2.2869 (2.2412)	loss 3.1948 (3.3351)	grad_norm 2.2663 (1.9096)	
[2022-01-23 23:16:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][400/1251]	eta 0:31:43 lr 0.000270	time 2.3163 (2.2373)	loss 2.8304 (3.3379)	grad_norm 1.7995 (1.9091)	
[2022-01-23 23:16:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][410/1251]	eta 0:31:18 lr 0.000270	time 1.7192 (2.2332)	loss 3.4759 (3.3384)	grad_norm 1.7864 (1.9115)	
[2022-01-23 23:16:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][420/1251]	eta 0:30:51 lr 0.000270	time 1.7947 (2.2284)	loss 3.8926 (3.3397)	grad_norm 1.7544 (1.9114)	
[2022-01-23 23:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][430/1251]	eta 0:30:28 lr 0.000270	time 2.1090 (2.2269)	loss 3.0248 (3.3371)	grad_norm 2.0770 (1.9117)	
[2022-01-23 23:17:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][440/1251]	eta 0:30:05 lr 0.000269	time 1.8349 (2.2260)	loss 3.0838 (3.3363)	grad_norm 2.1363 (1.9122)	
[2022-01-23 23:17:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][450/1251]	eta 0:29:43 lr 0.000269	time 1.8529 (2.2260)	loss 2.4837 (3.3300)	grad_norm 1.9881 (1.9130)	
[2022-01-23 23:18:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][460/1251]	eta 0:29:22 lr 0.000269	time 2.4528 (2.2282)	loss 3.2053 (3.3298)	grad_norm 1.8121 (1.9121)	
[2022-01-23 23:18:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][470/1251]	eta 0:28:59 lr 0.000269	time 2.4517 (2.2277)	loss 3.1418 (3.3291)	grad_norm 1.6234 (1.9139)	
[2022-01-23 23:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][480/1251]	eta 0:28:37 lr 0.000269	time 1.8022 (2.2275)	loss 3.7881 (3.3337)	grad_norm 2.1228 (1.9160)	
[2022-01-23 23:19:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][490/1251]	eta 0:28:12 lr 0.000269	time 2.0275 (2.2245)	loss 3.7434 (3.3325)	grad_norm 1.8874 (1.9150)	
[2022-01-23 23:19:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][500/1251]	eta 0:27:47 lr 0.000269	time 2.2324 (2.2209)	loss 3.3985 (3.3330)	grad_norm 1.7009 (1.9148)	
[2022-01-23 23:19:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][510/1251]	eta 0:27:23 lr 0.000269	time 1.6865 (2.2183)	loss 3.5680 (3.3370)	grad_norm 2.1066 (1.9160)	
[2022-01-23 23:20:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][520/1251]	eta 0:27:02 lr 0.000269	time 1.8270 (2.2192)	loss 3.2759 (3.3332)	grad_norm 2.1576 (1.9153)	
[2022-01-23 23:20:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][530/1251]	eta 0:26:41 lr 0.000269	time 1.9163 (2.2217)	loss 3.7183 (3.3355)	grad_norm 1.8391 (1.9142)	
[2022-01-23 23:21:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][540/1251]	eta 0:26:20 lr 0.000269	time 2.5876 (2.2227)	loss 2.9549 (3.3328)	grad_norm 1.9913 (1.9163)	
[2022-01-23 23:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][550/1251]	eta 0:25:57 lr 0.000269	time 2.7134 (2.2221)	loss 2.7132 (3.3294)	grad_norm 2.1611 (1.9152)	
[2022-01-23 23:21:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][560/1251]	eta 0:25:34 lr 0.000269	time 1.7866 (2.2210)	loss 2.2912 (3.3302)	grad_norm 1.9220 (1.9158)	
[2022-01-23 23:22:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][570/1251]	eta 0:25:12 lr 0.000269	time 1.8293 (2.2212)	loss 3.6396 (3.3295)	grad_norm 2.2775 (1.9168)	
[2022-01-23 23:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][580/1251]	eta 0:24:50 lr 0.000269	time 1.8011 (2.2207)	loss 2.3510 (3.3290)	grad_norm 1.7604 (1.9168)	
[2022-01-23 23:22:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][590/1251]	eta 0:24:27 lr 0.000269	time 2.4327 (2.2200)	loss 3.7799 (3.3294)	grad_norm 1.7682 (1.9154)	
[2022-01-23 23:23:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][600/1251]	eta 0:24:03 lr 0.000269	time 1.9084 (2.2167)	loss 3.8000 (3.3301)	grad_norm 1.7289 (1.9185)	
[2022-01-23 23:23:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][610/1251]	eta 0:23:39 lr 0.000269	time 2.1816 (2.2152)	loss 2.5457 (3.3301)	grad_norm 1.8296 (1.9190)	
[2022-01-23 23:23:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][620/1251]	eta 0:23:17 lr 0.000269	time 1.9042 (2.2140)	loss 2.6097 (3.3284)	grad_norm 1.7798 (1.9195)	
[2022-01-23 23:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][630/1251]	eta 0:22:55 lr 0.000269	time 1.7495 (2.2144)	loss 3.5694 (3.3321)	grad_norm 1.8203 (1.9189)	
[2022-01-23 23:24:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][640/1251]	eta 0:22:33 lr 0.000269	time 1.7321 (2.2144)	loss 3.8573 (3.3357)	grad_norm 1.6689 (1.9165)	
[2022-01-23 23:25:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][650/1251]	eta 0:22:11 lr 0.000269	time 2.5038 (2.2148)	loss 3.4387 (3.3354)	grad_norm 1.7672 (1.9149)	
[2022-01-23 23:25:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][660/1251]	eta 0:21:49 lr 0.000269	time 2.2052 (2.2157)	loss 3.1862 (3.3356)	grad_norm 1.7077 (1.9152)	
[2022-01-23 23:25:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][670/1251]	eta 0:21:26 lr 0.000269	time 2.2317 (2.2149)	loss 3.7780 (3.3346)	grad_norm 1.9480 (1.9149)	
[2022-01-23 23:26:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][680/1251]	eta 0:21:04 lr 0.000269	time 1.9941 (2.2140)	loss 3.0784 (3.3369)	grad_norm 2.0848 (1.9155)	
[2022-01-23 23:26:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][690/1251]	eta 0:20:42 lr 0.000269	time 3.1360 (2.2148)	loss 3.4592 (3.3337)	grad_norm 1.8587 (1.9141)	
[2022-01-23 23:26:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][700/1251]	eta 0:20:18 lr 0.000269	time 1.8459 (2.2123)	loss 3.8074 (3.3375)	grad_norm 1.9224 (1.9131)	
[2022-01-23 23:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][710/1251]	eta 0:19:55 lr 0.000268	time 2.5230 (2.2105)	loss 3.0768 (3.3395)	grad_norm 1.8493 (1.9142)	
[2022-01-23 23:27:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][720/1251]	eta 0:19:32 lr 0.000268	time 1.9137 (2.2074)	loss 4.1083 (3.3406)	grad_norm 1.8178 (1.9139)	
[2022-01-23 23:27:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][730/1251]	eta 0:19:09 lr 0.000268	time 2.2193 (2.2062)	loss 3.7499 (3.3441)	grad_norm 1.8517 (1.9139)	
[2022-01-23 23:28:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][740/1251]	eta 0:18:46 lr 0.000268	time 1.7760 (2.2037)	loss 3.0729 (3.3449)	grad_norm 2.0475 (1.9161)	
[2022-01-23 23:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][750/1251]	eta 0:18:24 lr 0.000268	time 2.9896 (2.2052)	loss 3.6198 (3.3444)	grad_norm 1.8080 (1.9183)	
[2022-01-23 23:29:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][760/1251]	eta 0:18:03 lr 0.000268	time 2.4905 (2.2074)	loss 4.0190 (3.3456)	grad_norm 2.1057 (1.9198)	
[2022-01-23 23:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][770/1251]	eta 0:17:42 lr 0.000268	time 2.3959 (2.2098)	loss 3.5434 (3.3444)	grad_norm 1.8098 (1.9197)	
[2022-01-23 23:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][780/1251]	eta 0:17:20 lr 0.000268	time 2.2683 (2.2099)	loss 3.8388 (3.3450)	grad_norm 1.6265 (1.9203)	
[2022-01-23 23:30:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][790/1251]	eta 0:16:59 lr 0.000268	time 3.3519 (2.2107)	loss 3.3690 (3.3453)	grad_norm 2.0753 (1.9210)	
[2022-01-23 23:30:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][800/1251]	eta 0:16:35 lr 0.000268	time 1.9853 (2.2070)	loss 3.2417 (3.3449)	grad_norm 1.7772 (1.9197)	
[2022-01-23 23:30:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][810/1251]	eta 0:16:12 lr 0.000268	time 1.6526 (2.2048)	loss 3.5209 (3.3493)	grad_norm 1.8504 (1.9203)	
[2022-01-23 23:31:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][820/1251]	eta 0:15:50 lr 0.000268	time 2.3316 (2.2045)	loss 3.9775 (3.3475)	grad_norm 2.1700 (1.9203)	
[2022-01-23 23:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][830/1251]	eta 0:15:29 lr 0.000268	time 3.5723 (2.2078)	loss 3.6467 (3.3493)	grad_norm 2.1773 (1.9207)	
[2022-01-23 23:32:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][840/1251]	eta 0:15:07 lr 0.000268	time 1.9258 (2.2076)	loss 3.9800 (3.3485)	grad_norm 1.7764 (1.9200)	
[2022-01-23 23:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][850/1251]	eta 0:14:45 lr 0.000268	time 2.1732 (2.2073)	loss 2.2819 (3.3413)	grad_norm 1.7691 (1.9195)	
[2022-01-23 23:32:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][860/1251]	eta 0:14:23 lr 0.000268	time 2.1890 (2.2078)	loss 3.9013 (3.3441)	grad_norm 1.7541 (1.9191)	
[2022-01-23 23:33:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][870/1251]	eta 0:14:01 lr 0.000268	time 3.3445 (2.2091)	loss 2.3198 (3.3390)	grad_norm 1.8610 (1.9184)	
[2022-01-23 23:33:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][880/1251]	eta 0:13:38 lr 0.000268	time 1.6086 (2.2068)	loss 3.7296 (3.3376)	grad_norm 1.7166 (1.9185)	
[2022-01-23 23:33:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][890/1251]	eta 0:13:16 lr 0.000268	time 1.9116 (2.2062)	loss 3.7342 (3.3343)	grad_norm 1.6538 (1.9183)	
[2022-01-23 23:34:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][900/1251]	eta 0:12:54 lr 0.000268	time 2.2989 (2.2053)	loss 3.4030 (3.3365)	grad_norm 1.8612 (1.9180)	
[2022-01-23 23:34:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][910/1251]	eta 0:12:32 lr 0.000268	time 3.6738 (2.2066)	loss 3.3198 (3.3365)	grad_norm 2.0502 (1.9179)	
[2022-01-23 23:34:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][920/1251]	eta 0:12:10 lr 0.000268	time 2.2220 (2.2066)	loss 3.4462 (3.3370)	grad_norm 2.2747 (1.9189)	
[2022-01-23 23:35:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][930/1251]	eta 0:11:48 lr 0.000268	time 1.7197 (2.2061)	loss 3.6477 (3.3348)	grad_norm 2.1334 (1.9192)	
[2022-01-23 23:35:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][940/1251]	eta 0:11:25 lr 0.000268	time 1.8439 (2.2044)	loss 3.7554 (3.3337)	grad_norm 1.8675 (1.9205)	
[2022-01-23 23:36:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][950/1251]	eta 0:11:03 lr 0.000268	time 3.0073 (2.2052)	loss 2.3675 (3.3323)	grad_norm 1.9705 (1.9218)	
[2022-01-23 23:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][960/1251]	eta 0:10:41 lr 0.000268	time 2.1585 (2.2042)	loss 2.7388 (3.3304)	grad_norm 1.9081 (1.9238)	
[2022-01-23 23:36:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][970/1251]	eta 0:10:19 lr 0.000268	time 1.7291 (2.2030)	loss 2.7419 (3.3321)	grad_norm 1.9434 (1.9234)	
[2022-01-23 23:37:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][980/1251]	eta 0:09:56 lr 0.000268	time 2.2408 (2.2022)	loss 3.5825 (3.3341)	grad_norm 1.7284 (1.9236)	
[2022-01-23 23:37:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][990/1251]	eta 0:09:34 lr 0.000267	time 3.4078 (2.2025)	loss 2.8194 (3.3372)	grad_norm 1.8380 (1.9236)	
[2022-01-23 23:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1000/1251]	eta 0:09:12 lr 0.000267	time 1.6947 (2.2017)	loss 3.5215 (3.3407)	grad_norm 1.7692 (1.9230)	
[2022-01-23 23:38:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1010/1251]	eta 0:08:50 lr 0.000267	time 1.9054 (2.2033)	loss 3.3276 (3.3395)	grad_norm 1.8811 (1.9233)	
[2022-01-23 23:38:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1020/1251]	eta 0:08:28 lr 0.000267	time 2.8108 (2.2029)	loss 2.5158 (3.3403)	grad_norm 1.7932 (1.9236)	
[2022-01-23 23:38:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1030/1251]	eta 0:08:06 lr 0.000267	time 2.9805 (2.2029)	loss 2.9822 (3.3399)	grad_norm 2.4230 (1.9247)	
[2022-01-23 23:39:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1040/1251]	eta 0:07:44 lr 0.000267	time 1.9388 (2.2022)	loss 3.6573 (3.3388)	grad_norm 1.8925 (1.9246)	
[2022-01-23 23:39:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1050/1251]	eta 0:07:22 lr 0.000267	time 2.6699 (2.2023)	loss 3.7670 (3.3417)	grad_norm 2.0690 (1.9241)	
[2022-01-23 23:40:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1060/1251]	eta 0:07:00 lr 0.000267	time 2.0669 (2.2023)	loss 3.9893 (3.3415)	grad_norm 2.1004 (1.9241)	
[2022-01-23 23:40:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1070/1251]	eta 0:06:38 lr 0.000267	time 2.0183 (2.2012)	loss 3.7936 (3.3431)	grad_norm 2.0896 (1.9239)	
[2022-01-23 23:40:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1080/1251]	eta 0:06:16 lr 0.000267	time 1.8744 (2.1999)	loss 2.3178 (3.3427)	grad_norm 1.9675 (1.9230)	
[2022-01-23 23:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1090/1251]	eta 0:05:54 lr 0.000267	time 2.6561 (2.1997)	loss 2.9887 (3.3437)	grad_norm 2.1897 (1.9231)	
[2022-01-23 23:41:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1100/1251]	eta 0:05:32 lr 0.000267	time 3.3194 (2.2009)	loss 3.4851 (3.3436)	grad_norm 1.9725 (1.9230)	
[2022-01-23 23:41:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1110/1251]	eta 0:05:10 lr 0.000267	time 1.5497 (2.2008)	loss 3.4026 (3.3431)	grad_norm 1.9108 (1.9223)	
[2022-01-23 23:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1120/1251]	eta 0:04:48 lr 0.000267	time 2.1190 (2.2022)	loss 3.6706 (3.3454)	grad_norm 2.3267 (1.9221)	
[2022-01-23 23:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1130/1251]	eta 0:04:26 lr 0.000267	time 2.2788 (2.2023)	loss 3.6279 (3.3452)	grad_norm 2.1085 (1.9225)	
[2022-01-23 23:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1140/1251]	eta 0:04:04 lr 0.000267	time 3.4402 (2.2023)	loss 2.6850 (3.3440)	grad_norm 1.7432 (1.9219)	
[2022-01-23 23:43:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1150/1251]	eta 0:03:42 lr 0.000267	time 1.9801 (2.2010)	loss 3.6429 (3.3460)	grad_norm 2.5246 (1.9215)	
[2022-01-23 23:43:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1160/1251]	eta 0:03:20 lr 0.000267	time 2.2422 (2.2006)	loss 2.1552 (3.3463)	grad_norm 1.6995 (1.9210)	
[2022-01-23 23:44:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1170/1251]	eta 0:02:58 lr 0.000267	time 1.8140 (2.1992)	loss 3.6284 (3.3464)	grad_norm 1.8786 (1.9203)	
[2022-01-23 23:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1180/1251]	eta 0:02:36 lr 0.000267	time 1.9001 (2.1987)	loss 3.5163 (3.3469)	grad_norm 1.8503 (1.9204)	
[2022-01-23 23:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1190/1251]	eta 0:02:14 lr 0.000267	time 2.3024 (2.1983)	loss 3.6145 (3.3489)	grad_norm 1.7189 (1.9206)	
[2022-01-23 23:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1200/1251]	eta 0:01:52 lr 0.000267	time 2.1595 (2.1984)	loss 3.5058 (3.3487)	grad_norm 1.9444 (1.9203)	
[2022-01-23 23:45:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1210/1251]	eta 0:01:30 lr 0.000267	time 2.3560 (2.1983)	loss 4.0377 (3.3477)	grad_norm 1.6849 (1.9200)	
[2022-01-23 23:45:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1220/1251]	eta 0:01:08 lr 0.000267	time 2.0347 (2.1983)	loss 3.9274 (3.3477)	grad_norm 1.7801 (1.9194)	
[2022-01-23 23:46:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1230/1251]	eta 0:00:46 lr 0.000267	time 1.4982 (2.1988)	loss 3.6456 (3.3479)	grad_norm 2.1494 (1.9191)	
[2022-01-23 23:46:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1240/1251]	eta 0:00:24 lr 0.000267	time 1.4326 (2.1990)	loss 2.5157 (3.3465)	grad_norm 1.8991 (1.9188)	
[2022-01-23 23:46:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [197/300][1250/1251]	eta 0:00:02 lr 0.000267	time 1.1977 (2.1930)	loss 3.2563 (3.3468)	grad_norm 2.1397 (1.9186)	
[2022-01-23 23:46:48 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 197 training takes 0:45:43
[2022-01-23 23:47:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.473 (18.473)	Loss 0.9335 (0.9335)	Acc@1 76.758 (76.758)	Acc@5 94.531 (94.531)	
[2022-01-23 23:47:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.833 (3.377)	Loss 0.8902 (0.9397)	Acc@1 78.320 (77.468)	Acc@5 94.531 (94.300)	
[2022-01-23 23:47:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.288 (2.536)	Loss 0.9198 (0.9325)	Acc@1 78.320 (77.911)	Acc@5 95.410 (94.443)	
[2022-01-23 23:47:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.911 (2.195)	Loss 0.9967 (0.9305)	Acc@1 76.562 (77.990)	Acc@5 93.652 (94.377)	
[2022-01-23 23:48:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.810 (2.179)	Loss 0.9037 (0.9321)	Acc@1 78.906 (77.968)	Acc@5 94.531 (94.355)	
[2022-01-23 23:48:25 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.094 Acc@5 94.394
[2022-01-23 23:48:25 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.1%
[2022-01-23 23:48:25 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.23%
[2022-01-23 23:48:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][0/1251]	eta 7:30:40 lr 0.000267	time 21.6154 (21.6154)	loss 3.3291 (3.3291)	grad_norm 1.7549 (1.7549)	
[2022-01-23 23:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][10/1251]	eta 1:23:53 lr 0.000266	time 1.9949 (4.0561)	loss 3.5467 (3.4670)	grad_norm 1.7567 (1.7674)	
[2022-01-23 23:49:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][20/1251]	eta 1:03:21 lr 0.000266	time 1.9579 (3.0882)	loss 3.6122 (3.5586)	grad_norm 1.8907 (1.8338)	
[2022-01-23 23:49:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][30/1251]	eta 0:56:46 lr 0.000266	time 1.4750 (2.7901)	loss 4.3628 (3.5901)	grad_norm 1.9389 (1.8297)	
[2022-01-23 23:50:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][40/1251]	eta 0:55:14 lr 0.000266	time 3.9478 (2.7366)	loss 3.2011 (3.5486)	grad_norm 1.7569 (1.8936)	
[2022-01-23 23:50:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][50/1251]	eta 0:52:36 lr 0.000266	time 1.4320 (2.6278)	loss 3.4911 (3.4785)	grad_norm 1.9916 (1.9001)	
[2022-01-23 23:51:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][60/1251]	eta 0:51:16 lr 0.000266	time 2.8701 (2.5835)	loss 2.4870 (3.4603)	grad_norm 1.6869 (1.8772)	
[2022-01-23 23:51:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][70/1251]	eta 0:49:29 lr 0.000266	time 1.6844 (2.5140)	loss 2.6986 (3.4315)	grad_norm 2.1443 (1.8782)	
[2022-01-23 23:51:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][80/1251]	eta 0:48:24 lr 0.000266	time 3.4139 (2.4806)	loss 3.5637 (3.4141)	grad_norm 1.9676 (1.8653)	
[2022-01-23 23:52:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][90/1251]	eta 0:47:15 lr 0.000266	time 1.8317 (2.4419)	loss 2.1867 (3.4062)	grad_norm 1.7691 (1.8669)	
[2022-01-23 23:52:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][100/1251]	eta 0:46:24 lr 0.000266	time 2.4870 (2.4196)	loss 3.4153 (3.3868)	grad_norm 1.7228 (1.8699)	
[2022-01-23 23:52:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][110/1251]	eta 0:45:33 lr 0.000266	time 1.9691 (2.3955)	loss 3.1604 (3.4009)	grad_norm 1.7753 (1.8706)	
[2022-01-23 23:53:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][120/1251]	eta 0:44:44 lr 0.000266	time 2.8919 (2.3738)	loss 3.1689 (3.3779)	grad_norm 1.6450 (1.8728)	
[2022-01-23 23:53:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][130/1251]	eta 0:44:03 lr 0.000266	time 2.1449 (2.3583)	loss 3.6778 (3.3706)	grad_norm 2.3209 (1.8695)	
[2022-01-23 23:53:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][140/1251]	eta 0:43:29 lr 0.000266	time 1.9331 (2.3487)	loss 3.6322 (3.3612)	grad_norm 1.9685 (1.8694)	
[2022-01-23 23:54:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][150/1251]	eta 0:42:44 lr 0.000266	time 1.8877 (2.3291)	loss 3.5004 (3.3656)	grad_norm 1.9757 (1.8867)	
[2022-01-23 23:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][160/1251]	eta 0:42:06 lr 0.000266	time 2.8947 (2.3158)	loss 2.4378 (3.3546)	grad_norm 1.7660 (1.8867)	
[2022-01-23 23:54:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][170/1251]	eta 0:41:31 lr 0.000266	time 2.0016 (2.3048)	loss 3.3770 (3.3590)	grad_norm 2.1593 (1.8939)	
[2022-01-23 23:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][180/1251]	eta 0:40:53 lr 0.000266	time 1.7412 (2.2905)	loss 3.4177 (3.3470)	grad_norm 1.8721 (1.8977)	
[2022-01-23 23:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][190/1251]	eta 0:40:26 lr 0.000266	time 2.1536 (2.2871)	loss 2.5441 (3.3387)	grad_norm 2.1301 (1.8981)	
[2022-01-23 23:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][200/1251]	eta 0:40:04 lr 0.000266	time 3.3579 (2.2878)	loss 4.0357 (3.3457)	grad_norm 1.9063 (1.8994)	
[2022-01-23 23:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][210/1251]	eta 0:39:36 lr 0.000266	time 1.9210 (2.2832)	loss 3.6362 (3.3477)	grad_norm 1.8307 (1.8986)	
[2022-01-23 23:56:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][220/1251]	eta 0:39:07 lr 0.000266	time 2.1335 (2.2768)	loss 2.4435 (3.3462)	grad_norm 1.7765 (1.8975)	
[2022-01-23 23:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][230/1251]	eta 0:38:43 lr 0.000266	time 1.7645 (2.2761)	loss 3.5283 (3.3481)	grad_norm 1.9037 (1.8956)	
[2022-01-23 23:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][240/1251]	eta 0:38:22 lr 0.000266	time 3.4159 (2.2771)	loss 3.4726 (3.3445)	grad_norm 1.9926 (1.9003)	
[2022-01-23 23:57:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][250/1251]	eta 0:37:52 lr 0.000266	time 1.6299 (2.2706)	loss 3.7842 (3.3445)	grad_norm 1.9099 (1.8975)	
[2022-01-23 23:58:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][260/1251]	eta 0:37:23 lr 0.000266	time 2.1663 (2.2636)	loss 3.9776 (3.3554)	grad_norm 1.7142 (1.8980)	
[2022-01-23 23:58:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][270/1251]	eta 0:36:56 lr 0.000266	time 2.5114 (2.2593)	loss 3.6406 (3.3526)	grad_norm 1.8188 (1.8968)	
[2022-01-23 23:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][280/1251]	eta 0:36:36 lr 0.000266	time 2.4093 (2.2626)	loss 3.6486 (3.3443)	grad_norm 1.9291 (1.8960)	
[2022-01-23 23:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][290/1251]	eta 0:36:13 lr 0.000265	time 2.1875 (2.2620)	loss 3.8438 (3.3424)	grad_norm 1.7452 (1.8951)	
[2022-01-23 23:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][300/1251]	eta 0:35:50 lr 0.000265	time 2.4563 (2.2608)	loss 3.0275 (3.3301)	grad_norm 2.1177 (1.8942)	
[2022-01-24 00:00:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][310/1251]	eta 0:35:21 lr 0.000265	time 1.9593 (2.2550)	loss 3.6362 (3.3242)	grad_norm 2.1080 (1.8943)	
[2022-01-24 00:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][320/1251]	eta 0:34:50 lr 0.000265	time 2.5306 (2.2454)	loss 3.6502 (3.3207)	grad_norm 2.1871 (1.8986)	
[2022-01-24 00:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][330/1251]	eta 0:34:20 lr 0.000265	time 1.9871 (2.2376)	loss 4.0744 (3.3186)	grad_norm 2.0031 (1.8984)	
[2022-01-24 00:01:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][340/1251]	eta 0:33:55 lr 0.000265	time 2.2298 (2.2338)	loss 3.1873 (3.3204)	grad_norm 1.5919 (1.8964)	
[2022-01-24 00:01:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][350/1251]	eta 0:33:34 lr 0.000265	time 2.6527 (2.2358)	loss 3.8036 (3.3237)	grad_norm 1.7206 (1.8952)	
[2022-01-24 00:01:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][360/1251]	eta 0:33:12 lr 0.000265	time 2.5014 (2.2360)	loss 2.6290 (3.3155)	grad_norm 1.6078 (1.8933)	
[2022-01-24 00:02:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][370/1251]	eta 0:32:52 lr 0.000265	time 2.1566 (2.2387)	loss 3.5842 (3.3209)	grad_norm 2.6613 (1.8966)	
[2022-01-24 00:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][380/1251]	eta 0:32:32 lr 0.000265	time 2.0646 (2.2411)	loss 3.0836 (3.3257)	grad_norm 2.0799 (1.8986)	
[2022-01-24 00:03:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][390/1251]	eta 0:32:12 lr 0.000265	time 2.8570 (2.2445)	loss 3.8028 (3.3330)	grad_norm 2.2673 (1.9008)	
[2022-01-24 00:03:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][400/1251]	eta 0:31:45 lr 0.000265	time 1.9180 (2.2386)	loss 3.2926 (3.3396)	grad_norm 1.8620 (1.9016)	
[2022-01-24 00:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][410/1251]	eta 0:31:18 lr 0.000265	time 1.8494 (2.2333)	loss 3.4509 (3.3454)	grad_norm 2.4883 (1.9022)	
[2022-01-24 00:04:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][420/1251]	eta 0:30:49 lr 0.000265	time 1.5755 (2.2262)	loss 4.1128 (3.3466)	grad_norm 1.7268 (1.9043)	
[2022-01-24 00:04:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][430/1251]	eta 0:30:24 lr 0.000265	time 2.2504 (2.2220)	loss 2.9397 (3.3429)	grad_norm 2.2501 (1.9046)	
[2022-01-24 00:04:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][440/1251]	eta 0:29:59 lr 0.000265	time 1.7728 (2.2192)	loss 3.6600 (3.3369)	grad_norm 1.8055 (1.9060)	
[2022-01-24 00:05:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][450/1251]	eta 0:29:36 lr 0.000265	time 2.0572 (2.2183)	loss 3.6223 (3.3342)	grad_norm 1.8460 (1.9067)	
[2022-01-24 00:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][460/1251]	eta 0:29:17 lr 0.000265	time 2.2492 (2.2224)	loss 3.7957 (3.3345)	grad_norm 1.9133 (1.9060)	
[2022-01-24 00:05:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][470/1251]	eta 0:28:57 lr 0.000265	time 3.4756 (2.2253)	loss 3.6099 (3.3385)	grad_norm 1.9384 (1.9045)	
[2022-01-24 00:06:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][480/1251]	eta 0:28:38 lr 0.000265	time 1.7832 (2.2288)	loss 4.0064 (3.3361)	grad_norm 1.8928 (1.9044)	
[2022-01-24 00:06:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][490/1251]	eta 0:28:18 lr 0.000265	time 2.5699 (2.2315)	loss 3.0291 (3.3308)	grad_norm 1.6443 (1.9021)	
[2022-01-24 00:07:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][500/1251]	eta 0:27:55 lr 0.000265	time 1.6408 (2.2308)	loss 3.0994 (3.3312)	grad_norm 1.6889 (1.9037)	
[2022-01-24 00:07:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][510/1251]	eta 0:27:31 lr 0.000265	time 1.9275 (2.2284)	loss 3.8100 (3.3374)	grad_norm 1.9173 (1.9036)	
[2022-01-24 00:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][520/1251]	eta 0:27:05 lr 0.000265	time 1.8047 (2.2242)	loss 3.4184 (3.3399)	grad_norm 1.8264 (1.9019)	
[2022-01-24 00:08:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][530/1251]	eta 0:26:41 lr 0.000265	time 1.5879 (2.2207)	loss 3.6909 (3.3452)	grad_norm 2.1365 (1.9030)	
[2022-01-24 00:08:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][540/1251]	eta 0:26:16 lr 0.000265	time 2.2007 (2.2172)	loss 3.4825 (3.3470)	grad_norm 2.0858 (1.9052)	
[2022-01-24 00:08:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][550/1251]	eta 0:25:52 lr 0.000265	time 2.1671 (2.2144)	loss 2.4186 (3.3449)	grad_norm 2.1157 (1.9047)	
[2022-01-24 00:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][560/1251]	eta 0:25:28 lr 0.000265	time 1.9191 (2.2115)	loss 4.1294 (3.3472)	grad_norm 2.1042 (1.9065)	
[2022-01-24 00:09:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][570/1251]	eta 0:25:07 lr 0.000264	time 2.8133 (2.2129)	loss 3.8887 (3.3465)	grad_norm 2.4682 (1.9101)	
[2022-01-24 00:09:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][580/1251]	eta 0:24:44 lr 0.000264	time 1.8244 (2.2129)	loss 3.9329 (3.3484)	grad_norm 1.9324 (1.9104)	
[2022-01-24 00:10:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][590/1251]	eta 0:24:22 lr 0.000264	time 2.2259 (2.2127)	loss 3.3283 (3.3501)	grad_norm 2.3421 (1.9125)	
[2022-01-24 00:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][600/1251]	eta 0:24:02 lr 0.000264	time 2.4500 (2.2154)	loss 3.0879 (3.3480)	grad_norm 1.6327 (1.9129)	
[2022-01-24 00:10:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][610/1251]	eta 0:23:41 lr 0.000264	time 2.8840 (2.2169)	loss 3.4257 (3.3449)	grad_norm 2.0805 (1.9138)	
[2022-01-24 00:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][620/1251]	eta 0:23:20 lr 0.000264	time 1.7219 (2.2187)	loss 2.3044 (3.3447)	grad_norm 1.6473 (1.9126)	
[2022-01-24 00:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][630/1251]	eta 0:22:57 lr 0.000264	time 2.0964 (2.2176)	loss 3.9229 (3.3435)	grad_norm 1.6204 (1.9109)	
[2022-01-24 00:12:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][640/1251]	eta 0:22:34 lr 0.000264	time 2.3187 (2.2166)	loss 3.6922 (3.3429)	grad_norm 1.7917 (1.9093)	
[2022-01-24 00:12:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][650/1251]	eta 0:22:10 lr 0.000264	time 2.5613 (2.2143)	loss 3.5064 (3.3422)	grad_norm 1.6425 (1.9075)	
[2022-01-24 00:12:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][660/1251]	eta 0:21:47 lr 0.000264	time 1.6175 (2.2127)	loss 3.3009 (3.3411)	grad_norm 1.7612 (1.9062)	
[2022-01-24 00:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][670/1251]	eta 0:21:25 lr 0.000264	time 2.1931 (2.2130)	loss 3.7186 (3.3421)	grad_norm 1.8463 (1.9051)	
[2022-01-24 00:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][680/1251]	eta 0:21:03 lr 0.000264	time 1.9526 (2.2126)	loss 3.5451 (3.3415)	grad_norm 1.7745 (1.9032)	
[2022-01-24 00:13:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][690/1251]	eta 0:20:41 lr 0.000264	time 2.2633 (2.2131)	loss 3.2039 (3.3397)	grad_norm 1.8160 (1.9021)	
[2022-01-24 00:14:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][700/1251]	eta 0:20:19 lr 0.000264	time 1.8848 (2.2130)	loss 3.0484 (3.3398)	grad_norm 1.9937 (1.9022)	
[2022-01-24 00:14:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][710/1251]	eta 0:19:56 lr 0.000264	time 1.9658 (2.2108)	loss 3.9349 (3.3435)	grad_norm 1.5831 (1.9014)	
[2022-01-24 00:14:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][720/1251]	eta 0:19:33 lr 0.000264	time 2.5936 (2.2100)	loss 3.9383 (3.3437)	grad_norm 1.7496 (1.9001)	
[2022-01-24 00:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][730/1251]	eta 0:19:11 lr 0.000264	time 1.5846 (2.2093)	loss 2.6870 (3.3461)	grad_norm 1.8833 (1.9002)	
[2022-01-24 00:15:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][740/1251]	eta 0:18:49 lr 0.000264	time 2.8235 (2.2107)	loss 3.0428 (3.3483)	grad_norm 2.3054 (1.9015)	
[2022-01-24 00:16:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][750/1251]	eta 0:18:26 lr 0.000264	time 2.2084 (2.2096)	loss 3.0391 (3.3437)	grad_norm 1.9367 (1.9007)	
[2022-01-24 00:16:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][760/1251]	eta 0:18:04 lr 0.000264	time 1.8944 (2.2079)	loss 3.2729 (3.3415)	grad_norm 1.8780 (1.8997)	
[2022-01-24 00:16:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][770/1251]	eta 0:17:41 lr 0.000264	time 1.9010 (2.2073)	loss 3.7358 (3.3421)	grad_norm 1.9954 (1.9001)	
[2022-01-24 00:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][780/1251]	eta 0:17:19 lr 0.000264	time 1.8174 (2.2069)	loss 3.6942 (3.3422)	grad_norm 2.1536 (1.9021)	
[2022-01-24 00:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][790/1251]	eta 0:16:57 lr 0.000264	time 3.3814 (2.2062)	loss 3.4780 (3.3415)	grad_norm 1.6765 (1.9026)	
[2022-01-24 00:17:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][800/1251]	eta 0:16:34 lr 0.000264	time 2.4895 (2.2060)	loss 2.5146 (3.3398)	grad_norm 1.8982 (1.9020)	
[2022-01-24 00:18:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][810/1251]	eta 0:16:12 lr 0.000264	time 2.0262 (2.2043)	loss 3.1871 (3.3423)	grad_norm 2.0630 (1.9017)	
[2022-01-24 00:18:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][820/1251]	eta 0:15:50 lr 0.000264	time 2.7152 (2.2055)	loss 2.9317 (3.3406)	grad_norm 1.8744 (1.9017)	
[2022-01-24 00:18:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][830/1251]	eta 0:15:28 lr 0.000264	time 1.5213 (2.2049)	loss 3.7911 (3.3413)	grad_norm 1.8411 (1.9021)	
[2022-01-24 00:19:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][840/1251]	eta 0:15:05 lr 0.000263	time 2.9002 (2.2039)	loss 3.3680 (3.3380)	grad_norm 1.9285 (1.9038)	
[2022-01-24 00:19:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][850/1251]	eta 0:14:43 lr 0.000263	time 1.9026 (2.2038)	loss 2.9985 (3.3387)	grad_norm 2.0587 (1.9032)	
[2022-01-24 00:20:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][860/1251]	eta 0:14:22 lr 0.000263	time 2.6365 (2.2056)	loss 3.0387 (3.3398)	grad_norm 1.8336 (1.9032)	
[2022-01-24 00:20:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][870/1251]	eta 0:13:59 lr 0.000263	time 1.5853 (2.2045)	loss 2.3417 (3.3385)	grad_norm 1.8277 (1.9036)	
[2022-01-24 00:20:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][880/1251]	eta 0:13:37 lr 0.000263	time 2.2977 (2.2033)	loss 2.7560 (3.3364)	grad_norm 2.0273 (1.9050)	
[2022-01-24 00:21:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][890/1251]	eta 0:13:14 lr 0.000263	time 1.6963 (2.2005)	loss 2.7798 (3.3369)	grad_norm 1.7490 (1.9046)	
[2022-01-24 00:21:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][900/1251]	eta 0:12:52 lr 0.000263	time 3.0929 (2.2001)	loss 2.8678 (3.3333)	grad_norm 1.7640 (1.9034)	
[2022-01-24 00:21:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][910/1251]	eta 0:12:30 lr 0.000263	time 1.9565 (2.2008)	loss 2.5724 (3.3329)	grad_norm 1.7192 (1.9037)	
[2022-01-24 00:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][920/1251]	eta 0:12:09 lr 0.000263	time 2.8254 (2.2032)	loss 3.4763 (3.3331)	grad_norm 1.7995 (1.9030)	
[2022-01-24 00:22:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][930/1251]	eta 0:11:47 lr 0.000263	time 2.1067 (2.2034)	loss 3.7254 (3.3332)	grad_norm 1.8433 (1.9018)	
[2022-01-24 00:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][940/1251]	eta 0:11:25 lr 0.000263	time 3.3159 (2.2050)	loss 3.3122 (3.3320)	grad_norm 1.9210 (1.9046)	
[2022-01-24 00:23:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][950/1251]	eta 0:11:03 lr 0.000263	time 2.4415 (2.2048)	loss 2.6281 (3.3309)	grad_norm 1.7270 (1.9060)	
[2022-01-24 00:23:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][960/1251]	eta 0:10:41 lr 0.000263	time 1.6609 (2.2044)	loss 3.3817 (3.3313)	grad_norm 1.9309 (1.9057)	
[2022-01-24 00:24:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][970/1251]	eta 0:10:19 lr 0.000263	time 2.2648 (2.2035)	loss 3.6901 (3.3321)	grad_norm 1.8520 (1.9060)	
[2022-01-24 00:24:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][980/1251]	eta 0:09:56 lr 0.000263	time 1.9735 (2.2018)	loss 3.1929 (3.3301)	grad_norm 2.5268 (1.9062)	
[2022-01-24 00:24:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][990/1251]	eta 0:09:34 lr 0.000263	time 2.6047 (2.2009)	loss 3.4486 (3.3298)	grad_norm 2.0713 (1.9064)	
[2022-01-24 00:25:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1000/1251]	eta 0:09:12 lr 0.000263	time 2.4429 (2.1996)	loss 3.1324 (3.3293)	grad_norm 2.0023 (1.9077)	
[2022-01-24 00:25:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1010/1251]	eta 0:08:49 lr 0.000263	time 2.0161 (2.1988)	loss 3.6116 (3.3286)	grad_norm 1.6450 (1.9071)	
[2022-01-24 00:25:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1020/1251]	eta 0:08:27 lr 0.000263	time 1.8864 (2.1984)	loss 2.2748 (3.3262)	grad_norm 1.8504 (1.9077)	
[2022-01-24 00:26:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1030/1251]	eta 0:08:05 lr 0.000263	time 2.8928 (2.1983)	loss 3.5593 (3.3277)	grad_norm 2.0071 (1.9083)	
[2022-01-24 00:26:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1040/1251]	eta 0:07:44 lr 0.000263	time 2.5213 (2.1996)	loss 3.7104 (3.3275)	grad_norm 1.6623 (1.9090)	
[2022-01-24 00:26:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1050/1251]	eta 0:07:22 lr 0.000263	time 2.3538 (2.2018)	loss 3.6003 (3.3268)	grad_norm 2.0081 (1.9092)	
[2022-01-24 00:27:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1060/1251]	eta 0:07:00 lr 0.000263	time 2.2070 (2.2013)	loss 3.0101 (3.3260)	grad_norm 1.9445 (1.9087)	
[2022-01-24 00:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1070/1251]	eta 0:06:38 lr 0.000263	time 1.8721 (2.1997)	loss 3.7348 (3.3269)	grad_norm 1.9098 (1.9082)	
[2022-01-24 00:28:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1080/1251]	eta 0:06:15 lr 0.000263	time 1.8256 (2.1977)	loss 3.8984 (3.3279)	grad_norm 2.1061 (1.9082)	
[2022-01-24 00:28:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1090/1251]	eta 0:05:53 lr 0.000263	time 2.2872 (2.1966)	loss 4.0531 (3.3285)	grad_norm 2.1607 (1.9078)	
[2022-01-24 00:28:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1100/1251]	eta 0:05:31 lr 0.000263	time 1.8437 (2.1951)	loss 3.5704 (3.3285)	grad_norm 1.7572 (1.9074)	
[2022-01-24 00:29:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1110/1251]	eta 0:05:09 lr 0.000263	time 1.8994 (2.1946)	loss 3.5107 (3.3305)	grad_norm 1.9419 (1.9064)	
[2022-01-24 00:29:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1120/1251]	eta 0:04:47 lr 0.000262	time 1.9746 (2.1946)	loss 3.0754 (3.3321)	grad_norm 1.9877 (1.9066)	
[2022-01-24 00:29:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1130/1251]	eta 0:04:25 lr 0.000262	time 2.2596 (2.1938)	loss 3.8106 (3.3317)	grad_norm 1.7269 (1.9073)	
[2022-01-24 00:30:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1140/1251]	eta 0:04:03 lr 0.000262	time 2.1399 (2.1934)	loss 3.1116 (3.3325)	grad_norm 1.9267 (1.9078)	
[2022-01-24 00:30:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1150/1251]	eta 0:03:41 lr 0.000262	time 2.5972 (2.1935)	loss 2.9701 (3.3318)	grad_norm 1.9305 (1.9090)	
[2022-01-24 00:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1160/1251]	eta 0:03:19 lr 0.000262	time 2.2194 (2.1942)	loss 2.5001 (3.3292)	grad_norm 1.6551 (1.9089)	
[2022-01-24 00:31:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1170/1251]	eta 0:02:57 lr 0.000262	time 2.7450 (2.1952)	loss 3.5316 (3.3304)	grad_norm 1.6642 (1.9087)	
[2022-01-24 00:31:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1180/1251]	eta 0:02:36 lr 0.000262	time 2.7656 (2.1978)	loss 2.8706 (3.3307)	grad_norm 2.2749 (1.9095)	
[2022-01-24 00:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1190/1251]	eta 0:02:14 lr 0.000262	time 1.8953 (2.1988)	loss 3.4238 (3.3314)	grad_norm 1.9890 (1.9093)	
[2022-01-24 00:32:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1200/1251]	eta 0:01:52 lr 0.000262	time 2.4541 (2.2003)	loss 3.3209 (3.3329)	grad_norm 1.6685 (1.9088)	
[2022-01-24 00:32:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1210/1251]	eta 0:01:30 lr 0.000262	time 1.9289 (2.2005)	loss 3.7655 (3.3326)	grad_norm 1.7102 (1.9080)	
[2022-01-24 00:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1220/1251]	eta 0:01:08 lr 0.000262	time 1.9171 (2.1989)	loss 3.6631 (3.3325)	grad_norm 1.8390 (1.9076)	
[2022-01-24 00:33:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1230/1251]	eta 0:00:46 lr 0.000262	time 1.6353 (2.1972)	loss 3.5247 (3.3332)	grad_norm 1.7245 (1.9087)	
[2022-01-24 00:33:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1240/1251]	eta 0:00:24 lr 0.000262	time 1.6465 (2.1952)	loss 3.7908 (3.3338)	grad_norm 1.9287 (1.9083)	
[2022-01-24 00:34:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [198/300][1250/1251]	eta 0:00:02 lr 0.000262	time 1.1914 (2.1897)	loss 3.1692 (3.3336)	grad_norm 1.7074 (1.9075)	
[2022-01-24 00:34:05 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 198 training takes 0:45:39
[2022-01-24 00:34:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.435 (18.435)	Loss 0.8896 (0.8896)	Acc@1 78.320 (78.320)	Acc@5 95.312 (95.312)	
[2022-01-24 00:34:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.830 (3.234)	Loss 0.9571 (0.9157)	Acc@1 76.855 (78.622)	Acc@5 94.629 (94.735)	
[2022-01-24 00:34:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.258 (2.469)	Loss 0.9842 (0.9305)	Acc@1 77.051 (78.306)	Acc@5 93.457 (94.517)	
[2022-01-24 00:35:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.942 (2.212)	Loss 0.9727 (0.9392)	Acc@1 78.320 (78.254)	Acc@5 93.359 (94.349)	
[2022-01-24 00:35:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.589 (2.178)	Loss 0.9697 (0.9343)	Acc@1 77.734 (78.320)	Acc@5 93.750 (94.424)	
[2022-01-24 00:35:41 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.336 Acc@5 94.420
[2022-01-24 00:35:41 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.3%
[2022-01-24 00:35:41 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.34%
[2022-01-24 00:36:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][0/1251]	eta 7:33:21 lr 0.000262	time 21.7438 (21.7438)	loss 2.6113 (2.6113)	grad_norm 1.8464 (1.8464)	
[2022-01-24 00:36:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][10/1251]	eta 1:22:23 lr 0.000262	time 1.8083 (3.9834)	loss 2.0909 (3.2045)	grad_norm 1.6548 (1.7322)	
[2022-01-24 00:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][20/1251]	eta 1:03:23 lr 0.000262	time 1.4200 (3.0896)	loss 3.3233 (3.3254)	grad_norm 1.6805 (1.7626)	
[2022-01-24 00:37:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][30/1251]	eta 0:56:08 lr 0.000262	time 1.4782 (2.7591)	loss 2.8923 (3.3179)	grad_norm 1.9336 (1.7994)	
[2022-01-24 00:37:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][40/1251]	eta 0:53:27 lr 0.000262	time 3.3032 (2.6486)	loss 3.8371 (3.3258)	grad_norm 2.0906 (1.8157)	
[2022-01-24 00:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][50/1251]	eta 0:52:26 lr 0.000262	time 2.7963 (2.6198)	loss 2.6758 (3.3339)	grad_norm 1.8580 (1.8195)	
[2022-01-24 00:38:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][60/1251]	eta 0:50:11 lr 0.000262	time 1.3874 (2.5282)	loss 3.9422 (3.3104)	grad_norm 1.6985 (1.8130)	
[2022-01-24 00:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][70/1251]	eta 0:48:57 lr 0.000262	time 1.5564 (2.4871)	loss 2.8393 (3.2879)	grad_norm 2.0028 (1.8327)	
[2022-01-24 00:39:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][80/1251]	eta 0:48:03 lr 0.000262	time 2.7074 (2.4628)	loss 3.6840 (3.3044)	grad_norm 1.8448 (1.8359)	
[2022-01-24 00:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][90/1251]	eta 0:47:31 lr 0.000262	time 2.5890 (2.4562)	loss 3.7790 (3.2991)	grad_norm 1.8354 (1.8373)	
[2022-01-24 00:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][100/1251]	eta 0:46:54 lr 0.000262	time 1.5155 (2.4455)	loss 3.8845 (3.2949)	grad_norm 1.8299 (1.8514)	
[2022-01-24 00:40:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][110/1251]	eta 0:46:01 lr 0.000262	time 2.2134 (2.4206)	loss 3.6085 (3.3117)	grad_norm 2.0058 (1.8558)	
[2022-01-24 00:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][120/1251]	eta 0:45:03 lr 0.000262	time 2.6229 (2.3901)	loss 4.3176 (3.3297)	grad_norm 1.9869 (1.8558)	
[2022-01-24 00:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][130/1251]	eta 0:44:02 lr 0.000262	time 1.9784 (2.3576)	loss 2.9100 (3.3343)	grad_norm 1.8593 (1.8545)	
[2022-01-24 00:41:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][140/1251]	eta 0:43:15 lr 0.000261	time 2.4744 (2.3366)	loss 3.6951 (3.3466)	grad_norm 1.8715 (1.8543)	
[2022-01-24 00:41:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][150/1251]	eta 0:42:35 lr 0.000261	time 2.3031 (2.3209)	loss 3.2505 (3.3356)	grad_norm 1.5983 (1.8570)	
[2022-01-24 00:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][160/1251]	eta 0:42:00 lr 0.000261	time 2.6953 (2.3099)	loss 3.6753 (3.3306)	grad_norm 1.8264 (1.8597)	
[2022-01-24 00:42:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][170/1251]	eta 0:41:28 lr 0.000261	time 1.8590 (2.3018)	loss 2.7698 (3.3296)	grad_norm 1.9042 (1.8668)	
[2022-01-24 00:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][180/1251]	eta 0:41:02 lr 0.000261	time 2.5322 (2.2990)	loss 3.1277 (3.3330)	grad_norm 1.8576 (1.8691)	
[2022-01-24 00:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][190/1251]	eta 0:40:45 lr 0.000261	time 2.4931 (2.3052)	loss 3.3778 (3.3302)	grad_norm 2.2143 (1.8731)	
[2022-01-24 00:43:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][200/1251]	eta 0:40:35 lr 0.000261	time 3.0577 (2.3172)	loss 2.3198 (3.3208)	grad_norm 1.9093 (1.8750)	
[2022-01-24 00:43:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][210/1251]	eta 0:40:06 lr 0.000261	time 2.4873 (2.3115)	loss 2.6971 (3.3250)	grad_norm 1.6316 (1.8753)	
[2022-01-24 00:44:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][220/1251]	eta 0:39:28 lr 0.000261	time 2.0405 (2.2977)	loss 3.7811 (3.3277)	grad_norm 1.8402 (1.8818)	
[2022-01-24 00:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][230/1251]	eta 0:38:50 lr 0.000261	time 1.8598 (2.2830)	loss 3.6254 (3.3274)	grad_norm 2.1862 (1.8816)	
[2022-01-24 00:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][240/1251]	eta 0:38:16 lr 0.000261	time 2.4991 (2.2711)	loss 2.5688 (3.3355)	grad_norm 1.7668 (1.8835)	
[2022-01-24 00:45:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][250/1251]	eta 0:37:49 lr 0.000261	time 2.1189 (2.2668)	loss 3.5812 (3.3336)	grad_norm 1.8756 (1.8836)	
[2022-01-24 00:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][260/1251]	eta 0:37:22 lr 0.000261	time 2.2167 (2.2627)	loss 3.4390 (3.3324)	grad_norm 1.9575 (1.8790)	
[2022-01-24 00:45:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][270/1251]	eta 0:36:59 lr 0.000261	time 2.3023 (2.2621)	loss 3.7725 (3.3362)	grad_norm 1.8333 (1.8800)	
[2022-01-24 00:46:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][280/1251]	eta 0:36:39 lr 0.000261	time 2.8700 (2.2652)	loss 2.4520 (3.3289)	grad_norm 1.8254 (1.8781)	
[2022-01-24 00:46:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][290/1251]	eta 0:36:17 lr 0.000261	time 2.2865 (2.2661)	loss 2.7810 (3.3342)	grad_norm 1.5899 (1.8775)	
[2022-01-24 00:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][300/1251]	eta 0:35:49 lr 0.000261	time 1.9258 (2.2603)	loss 2.8425 (3.3257)	grad_norm 1.6585 (1.8816)	
[2022-01-24 00:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][310/1251]	eta 0:35:23 lr 0.000261	time 2.2380 (2.2568)	loss 3.8137 (3.3148)	grad_norm 1.8082 (1.8811)	
[2022-01-24 00:47:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][320/1251]	eta 0:34:57 lr 0.000261	time 2.5377 (2.2527)	loss 3.8715 (3.3185)	grad_norm 2.0545 (1.8823)	
[2022-01-24 00:48:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][330/1251]	eta 0:34:33 lr 0.000261	time 2.2046 (2.2514)	loss 3.1673 (3.3197)	grad_norm 1.7332 (1.8803)	
[2022-01-24 00:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][340/1251]	eta 0:34:08 lr 0.000261	time 1.8378 (2.2489)	loss 2.6054 (3.3182)	grad_norm 1.8038 (1.8809)	
[2022-01-24 00:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][350/1251]	eta 0:33:43 lr 0.000261	time 1.8880 (2.2459)	loss 2.6191 (3.3165)	grad_norm 1.9647 (1.8839)	
[2022-01-24 00:49:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][360/1251]	eta 0:33:18 lr 0.000261	time 1.6327 (2.2427)	loss 3.3675 (3.3198)	grad_norm 1.8897 (1.8837)	
[2022-01-24 00:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][370/1251]	eta 0:32:52 lr 0.000261	time 1.9118 (2.2387)	loss 3.5533 (3.3240)	grad_norm 1.9838 (1.8833)	
[2022-01-24 00:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][380/1251]	eta 0:32:27 lr 0.000261	time 1.9835 (2.2364)	loss 2.7384 (3.3221)	grad_norm 1.7619 (1.8865)	
[2022-01-24 00:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][390/1251]	eta 0:32:05 lr 0.000261	time 2.5454 (2.2358)	loss 3.3773 (3.3181)	grad_norm 2.3264 (1.8892)	
[2022-01-24 00:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][400/1251]	eta 0:31:45 lr 0.000261	time 2.2963 (2.2387)	loss 3.1705 (3.3196)	grad_norm 1.6521 (1.8908)	
[2022-01-24 00:50:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][410/1251]	eta 0:31:19 lr 0.000261	time 1.8431 (2.2352)	loss 3.3737 (3.3170)	grad_norm 1.8496 (1.8928)	
[2022-01-24 00:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][420/1251]	eta 0:30:58 lr 0.000260	time 2.3189 (2.2359)	loss 2.6826 (3.3206)	grad_norm 1.6787 (1.8933)	
[2022-01-24 00:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][430/1251]	eta 0:30:35 lr 0.000260	time 2.3838 (2.2359)	loss 3.3190 (3.3205)	grad_norm 2.0568 (1.8940)	
[2022-01-24 00:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][440/1251]	eta 0:30:12 lr 0.000260	time 1.8356 (2.2349)	loss 3.3344 (3.3267)	grad_norm 1.9790 (1.8972)	
[2022-01-24 00:52:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][450/1251]	eta 0:29:50 lr 0.000260	time 2.1461 (2.2358)	loss 3.5082 (3.3276)	grad_norm 1.6515 (1.8976)	
[2022-01-24 00:52:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][460/1251]	eta 0:29:25 lr 0.000260	time 1.7975 (2.2316)	loss 3.5237 (3.3307)	grad_norm 2.3805 (1.8975)	
[2022-01-24 00:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][470/1251]	eta 0:29:00 lr 0.000260	time 2.0464 (2.2280)	loss 2.5453 (3.3234)	grad_norm 1.7367 (1.8984)	
[2022-01-24 00:53:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][480/1251]	eta 0:28:34 lr 0.000260	time 1.9338 (2.2237)	loss 2.2815 (3.3169)	grad_norm 1.9394 (1.8986)	
[2022-01-24 00:53:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][490/1251]	eta 0:28:10 lr 0.000260	time 2.0615 (2.2219)	loss 2.3601 (3.3171)	grad_norm 1.6795 (1.9011)	
[2022-01-24 00:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][500/1251]	eta 0:27:48 lr 0.000260	time 2.1668 (2.2219)	loss 2.5902 (3.3099)	grad_norm 1.9372 (1.9027)	
[2022-01-24 00:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][510/1251]	eta 0:27:26 lr 0.000260	time 2.4699 (2.2221)	loss 2.6950 (3.3110)	grad_norm 2.1166 (1.9021)	
[2022-01-24 00:54:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][520/1251]	eta 0:27:03 lr 0.000260	time 1.5882 (2.2213)	loss 2.9904 (3.3117)	grad_norm 2.0204 (1.9034)	
[2022-01-24 00:55:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][530/1251]	eta 0:26:43 lr 0.000260	time 2.5767 (2.2237)	loss 3.1199 (3.3051)	grad_norm 1.9319 (1.9041)	
[2022-01-24 00:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][540/1251]	eta 0:26:19 lr 0.000260	time 2.0038 (2.2213)	loss 2.8782 (3.3086)	grad_norm 1.8836 (1.9041)	
[2022-01-24 00:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][550/1251]	eta 0:25:55 lr 0.000260	time 1.8915 (2.2190)	loss 2.3613 (3.3081)	grad_norm 1.8655 (1.9049)	
[2022-01-24 00:56:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][560/1251]	eta 0:25:32 lr 0.000260	time 2.0011 (2.2180)	loss 3.4541 (3.3091)	grad_norm 1.9174 (1.9041)	
[2022-01-24 00:56:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][570/1251]	eta 0:25:09 lr 0.000260	time 2.5509 (2.2173)	loss 2.5479 (3.3071)	grad_norm 1.8541 (1.9028)	
[2022-01-24 00:57:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][580/1251]	eta 0:24:47 lr 0.000260	time 2.4533 (2.2169)	loss 3.8310 (3.3095)	grad_norm 1.7392 (1.9024)	
[2022-01-24 00:57:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][590/1251]	eta 0:24:26 lr 0.000260	time 1.8569 (2.2182)	loss 2.2587 (3.3076)	grad_norm 2.1304 (1.9021)	
[2022-01-24 00:57:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][600/1251]	eta 0:24:05 lr 0.000260	time 2.2856 (2.2197)	loss 3.6698 (3.3076)	grad_norm 1.9188 (1.9026)	
[2022-01-24 00:58:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][610/1251]	eta 0:23:42 lr 0.000260	time 2.5181 (2.2198)	loss 3.5408 (3.3047)	grad_norm 2.0929 (1.9038)	
[2022-01-24 00:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][620/1251]	eta 0:23:19 lr 0.000260	time 2.2322 (2.2177)	loss 4.0230 (3.3105)	grad_norm 1.8814 (1.9040)	
[2022-01-24 00:58:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][630/1251]	eta 0:22:55 lr 0.000260	time 1.6600 (2.2147)	loss 3.0114 (3.3057)	grad_norm 1.8798 (1.9046)	
[2022-01-24 00:59:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][640/1251]	eta 0:22:31 lr 0.000260	time 1.9448 (2.2113)	loss 3.8232 (3.3080)	grad_norm 1.9165 (1.9042)	
[2022-01-24 00:59:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][650/1251]	eta 0:22:08 lr 0.000260	time 2.0518 (2.2107)	loss 3.5485 (3.3114)	grad_norm 1.8974 (1.9049)	
[2022-01-24 01:00:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][660/1251]	eta 0:21:45 lr 0.000260	time 2.2692 (2.2092)	loss 3.7449 (3.3144)	grad_norm 1.8135 (1.9050)	
[2022-01-24 01:00:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][670/1251]	eta 0:21:23 lr 0.000260	time 1.7246 (2.2085)	loss 2.3614 (3.3109)	grad_norm 1.7996 (1.9033)	
[2022-01-24 01:00:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][680/1251]	eta 0:21:01 lr 0.000260	time 1.7982 (2.2097)	loss 3.4371 (3.3123)	grad_norm 1.9199 (1.9045)	
[2022-01-24 01:01:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][690/1251]	eta 0:20:41 lr 0.000260	time 2.7648 (2.2125)	loss 3.3127 (3.3131)	grad_norm 1.9930 (1.9044)	
[2022-01-24 01:01:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][700/1251]	eta 0:20:18 lr 0.000259	time 1.8554 (2.2119)	loss 3.1268 (3.3114)	grad_norm 2.7793 (1.9058)	
[2022-01-24 01:01:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][710/1251]	eta 0:19:55 lr 0.000259	time 1.5648 (2.2090)	loss 2.4347 (3.3144)	grad_norm 1.6603 (1.9059)	
[2022-01-24 01:02:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][720/1251]	eta 0:19:32 lr 0.000259	time 2.4257 (2.2088)	loss 2.4258 (3.3164)	grad_norm 1.9274 (1.9055)	
[2022-01-24 01:02:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][730/1251]	eta 0:19:09 lr 0.000259	time 1.9800 (2.2065)	loss 3.2127 (3.3166)	grad_norm 1.6900 (1.9053)	
[2022-01-24 01:02:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][740/1251]	eta 0:18:47 lr 0.000259	time 2.3041 (2.2060)	loss 3.6577 (3.3179)	grad_norm 1.9150 (1.9058)	
[2022-01-24 01:03:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][750/1251]	eta 0:18:25 lr 0.000259	time 1.8306 (2.2062)	loss 3.5034 (3.3186)	grad_norm 1.5728 (1.9065)	
[2022-01-24 01:03:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][760/1251]	eta 0:18:04 lr 0.000259	time 1.8498 (2.2084)	loss 3.1429 (3.3222)	grad_norm 1.9130 (1.9055)	
[2022-01-24 01:04:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][770/1251]	eta 0:17:41 lr 0.000259	time 1.5898 (2.2074)	loss 3.4977 (3.3204)	grad_norm 2.1622 (1.9070)	
[2022-01-24 01:04:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][780/1251]	eta 0:17:19 lr 0.000259	time 2.5719 (2.2073)	loss 3.5413 (3.3194)	grad_norm 1.6900 (1.9085)	
[2022-01-24 01:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][790/1251]	eta 0:16:57 lr 0.000259	time 2.0833 (2.2070)	loss 3.4886 (3.3197)	grad_norm 1.8941 (1.9089)	
[2022-01-24 01:05:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][800/1251]	eta 0:16:35 lr 0.000259	time 2.4922 (2.2068)	loss 4.1419 (3.3185)	grad_norm 1.8892 (1.9086)	
[2022-01-24 01:05:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][810/1251]	eta 0:16:13 lr 0.000259	time 1.6351 (2.2066)	loss 2.3937 (3.3219)	grad_norm 1.7728 (1.9102)	
[2022-01-24 01:05:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][820/1251]	eta 0:15:51 lr 0.000259	time 2.4976 (2.2079)	loss 3.7753 (3.3229)	grad_norm 2.0730 (1.9102)	
[2022-01-24 01:06:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][830/1251]	eta 0:15:29 lr 0.000259	time 1.9245 (2.2069)	loss 2.3076 (3.3231)	grad_norm 1.9841 (1.9113)	
[2022-01-24 01:06:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][840/1251]	eta 0:15:06 lr 0.000259	time 2.9881 (2.2060)	loss 3.0248 (3.3237)	grad_norm 1.8974 (1.9115)	
[2022-01-24 01:06:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][850/1251]	eta 0:14:43 lr 0.000259	time 1.6658 (2.2035)	loss 3.5429 (3.3250)	grad_norm 1.7090 (1.9120)	
[2022-01-24 01:07:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][860/1251]	eta 0:14:21 lr 0.000259	time 2.4491 (2.2030)	loss 3.0801 (3.3262)	grad_norm 1.6420 (1.9124)	
[2022-01-24 01:07:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][870/1251]	eta 0:13:59 lr 0.000259	time 2.1307 (2.2036)	loss 3.6523 (3.3282)	grad_norm 1.6731 (1.9121)	
[2022-01-24 01:08:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][880/1251]	eta 0:13:38 lr 0.000259	time 3.5652 (2.2062)	loss 3.7948 (3.3289)	grad_norm 1.7988 (1.9117)	
[2022-01-24 01:08:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][890/1251]	eta 0:13:16 lr 0.000259	time 1.7237 (2.2052)	loss 2.3047 (3.3282)	grad_norm 1.5603 (1.9103)	
[2022-01-24 01:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][900/1251]	eta 0:12:53 lr 0.000259	time 2.1783 (2.2049)	loss 2.6289 (3.3285)	grad_norm 1.6564 (1.9092)	
[2022-01-24 01:09:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][910/1251]	eta 0:12:31 lr 0.000259	time 2.2164 (2.2048)	loss 3.5575 (3.3269)	grad_norm 1.6621 (1.9085)	
[2022-01-24 01:09:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][920/1251]	eta 0:12:09 lr 0.000259	time 2.2403 (2.2035)	loss 3.3356 (3.3259)	grad_norm 1.7660 (1.9082)	
[2022-01-24 01:09:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][930/1251]	eta 0:11:46 lr 0.000259	time 2.2713 (2.2018)	loss 2.9601 (3.3248)	grad_norm 1.8027 (1.9091)	
[2022-01-24 01:10:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][940/1251]	eta 0:11:25 lr 0.000259	time 2.7710 (2.2027)	loss 3.6951 (3.3254)	grad_norm 2.0805 (1.9110)	
[2022-01-24 01:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][950/1251]	eta 0:11:03 lr 0.000259	time 2.5531 (2.2037)	loss 3.1306 (3.3281)	grad_norm 2.3960 (1.9127)	
[2022-01-24 01:10:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][960/1251]	eta 0:10:41 lr 0.000259	time 2.0951 (2.2042)	loss 3.6823 (3.3285)	grad_norm 1.9060 (1.9124)	
[2022-01-24 01:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][970/1251]	eta 0:10:19 lr 0.000259	time 1.8857 (2.2050)	loss 3.5145 (3.3303)	grad_norm 1.9289 (1.9122)	
[2022-01-24 01:11:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][980/1251]	eta 0:09:57 lr 0.000258	time 1.9312 (2.2040)	loss 3.4044 (3.3279)	grad_norm 1.9298 (1.9123)	
[2022-01-24 01:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][990/1251]	eta 0:09:35 lr 0.000258	time 2.5573 (2.2035)	loss 2.1924 (3.3262)	grad_norm 2.1610 (1.9123)	
[2022-01-24 01:12:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1000/1251]	eta 0:09:12 lr 0.000258	time 1.9126 (2.2011)	loss 3.7984 (3.3256)	grad_norm 1.8129 (1.9111)	
[2022-01-24 01:12:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1010/1251]	eta 0:08:49 lr 0.000258	time 1.8219 (2.1990)	loss 2.6581 (3.3230)	grad_norm 1.7740 (1.9119)	
[2022-01-24 01:13:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1020/1251]	eta 0:08:28 lr 0.000258	time 2.2707 (2.1995)	loss 4.0520 (3.3222)	grad_norm 1.8903 (1.9137)	
[2022-01-24 01:13:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1030/1251]	eta 0:08:06 lr 0.000258	time 2.0332 (2.2000)	loss 2.6687 (3.3202)	grad_norm 2.3510 (1.9137)	
[2022-01-24 01:13:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1040/1251]	eta 0:07:44 lr 0.000258	time 2.0625 (2.2018)	loss 3.3328 (3.3180)	grad_norm 2.3715 (1.9138)	
[2022-01-24 01:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1050/1251]	eta 0:07:23 lr 0.000258	time 3.0771 (2.2045)	loss 3.6990 (3.3183)	grad_norm 1.9976 (1.9138)	
[2022-01-24 01:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1060/1251]	eta 0:07:01 lr 0.000258	time 1.9018 (2.2044)	loss 3.7772 (3.3192)	grad_norm 2.1992 (1.9144)	
[2022-01-24 01:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1070/1251]	eta 0:06:39 lr 0.000258	time 1.8909 (2.2050)	loss 3.7763 (3.3182)	grad_norm 1.9030 (1.9150)	
[2022-01-24 01:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1080/1251]	eta 0:06:16 lr 0.000258	time 1.9056 (2.2034)	loss 3.9188 (3.3191)	grad_norm 2.1320 (1.9148)	
[2022-01-24 01:15:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1090/1251]	eta 0:05:54 lr 0.000258	time 1.8079 (2.2020)	loss 3.4894 (3.3198)	grad_norm 1.9126 (1.9146)	
[2022-01-24 01:16:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1100/1251]	eta 0:05:32 lr 0.000258	time 1.8084 (2.2008)	loss 3.4712 (3.3174)	grad_norm 1.8252 (1.9140)	
[2022-01-24 01:16:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1110/1251]	eta 0:05:10 lr 0.000258	time 2.1783 (2.2011)	loss 2.3753 (3.3156)	grad_norm 1.7150 (1.9135)	
[2022-01-24 01:16:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1120/1251]	eta 0:04:48 lr 0.000258	time 2.1923 (2.2011)	loss 3.2028 (3.3139)	grad_norm 2.1607 (1.9140)	
[2022-01-24 01:17:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1130/1251]	eta 0:04:26 lr 0.000258	time 2.4185 (2.2020)	loss 3.4157 (3.3143)	grad_norm 1.7903 (1.9143)	
[2022-01-24 01:17:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1140/1251]	eta 0:04:04 lr 0.000258	time 1.8730 (2.2016)	loss 2.6942 (3.3128)	grad_norm 1.7423 (1.9144)	
[2022-01-24 01:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1150/1251]	eta 0:03:42 lr 0.000258	time 1.5716 (2.2012)	loss 2.4549 (3.3098)	grad_norm 1.9701 (1.9145)	
[2022-01-24 01:18:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1160/1251]	eta 0:03:20 lr 0.000258	time 2.1371 (2.2009)	loss 3.1966 (3.3079)	grad_norm 2.0792 (1.9139)	
[2022-01-24 01:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1170/1251]	eta 0:02:58 lr 0.000258	time 1.9174 (2.2000)	loss 2.8064 (3.3080)	grad_norm 1.8289 (1.9140)	
[2022-01-24 01:18:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1180/1251]	eta 0:02:36 lr 0.000258	time 1.4137 (2.1989)	loss 2.3981 (3.3082)	grad_norm 2.0268 (1.9138)	
[2022-01-24 01:19:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1190/1251]	eta 0:02:14 lr 0.000258	time 2.2168 (2.2000)	loss 2.3776 (3.3060)	grad_norm 1.8022 (1.9144)	
[2022-01-24 01:19:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1200/1251]	eta 0:01:52 lr 0.000258	time 1.6607 (2.2005)	loss 3.4951 (3.3076)	grad_norm 2.1488 (1.9154)	
[2022-01-24 01:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1210/1251]	eta 0:01:30 lr 0.000258	time 2.5434 (2.2017)	loss 3.7509 (3.3100)	grad_norm 1.8127 (1.9152)	
[2022-01-24 01:20:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1220/1251]	eta 0:01:08 lr 0.000258	time 1.4816 (2.2022)	loss 3.6619 (3.3098)	grad_norm 1.8115 (1.9150)	
[2022-01-24 01:20:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1230/1251]	eta 0:00:46 lr 0.000258	time 2.4127 (2.2022)	loss 3.8552 (3.3093)	grad_norm 2.1138 (1.9163)	
[2022-01-24 01:21:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1240/1251]	eta 0:00:24 lr 0.000258	time 1.2828 (2.2000)	loss 3.8419 (3.3094)	grad_norm 2.0031 (1.9175)	
[2022-01-24 01:21:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [199/300][1250/1251]	eta 0:00:02 lr 0.000258	time 1.2044 (2.1936)	loss 3.4539 (3.3086)	grad_norm 1.6506 (1.9177)	
[2022-01-24 01:21:25 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 199 training takes 0:45:44
[2022-01-24 01:21:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.497 (18.497)	Loss 0.8443 (0.8443)	Acc@1 79.785 (79.785)	Acc@5 94.531 (94.531)	
[2022-01-24 01:22:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.940 (3.385)	Loss 0.8718 (0.9088)	Acc@1 79.199 (77.805)	Acc@5 94.141 (94.229)	
[2022-01-24 01:22:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.219 (2.554)	Loss 0.9518 (0.9088)	Acc@1 77.441 (78.097)	Acc@5 93.848 (94.308)	
[2022-01-24 01:22:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.596 (2.215)	Loss 0.8961 (0.9012)	Acc@1 79.199 (78.462)	Acc@5 94.824 (94.421)	
[2022-01-24 01:22:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.870 (2.132)	Loss 0.8119 (0.9015)	Acc@1 79.297 (78.408)	Acc@5 95.703 (94.431)	
[2022-01-24 01:23:00 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.396 Acc@5 94.418
[2022-01-24 01:23:00 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.4%
[2022-01-24 01:23:00 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.40%
[2022-01-24 01:23:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][0/1251]	eta 6:50:39 lr 0.000258	time 19.6962 (19.6962)	loss 3.2415 (3.2415)	grad_norm 1.9278 (1.9278)	
[2022-01-24 01:23:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][10/1251]	eta 1:24:00 lr 0.000257	time 3.0438 (4.0618)	loss 2.4177 (3.2070)	grad_norm 1.9742 (1.9851)	
[2022-01-24 01:24:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][20/1251]	eta 1:05:52 lr 0.000257	time 1.9570 (3.2107)	loss 2.5977 (3.2205)	grad_norm 1.8678 (1.9907)	
[2022-01-24 01:24:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][30/1251]	eta 0:59:39 lr 0.000257	time 1.5372 (2.9314)	loss 3.9714 (3.2794)	grad_norm 1.8811 (1.9549)	
[2022-01-24 01:24:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][40/1251]	eta 0:57:39 lr 0.000257	time 3.5491 (2.8566)	loss 3.4939 (3.3233)	grad_norm 1.9435 (1.9776)	
[2022-01-24 01:25:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][50/1251]	eta 0:54:52 lr 0.000257	time 2.1153 (2.7415)	loss 2.3271 (3.2905)	grad_norm 2.1875 (1.9747)	
[2022-01-24 01:25:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][60/1251]	eta 0:51:57 lr 0.000257	time 1.9317 (2.6177)	loss 3.4374 (3.3235)	grad_norm 1.9121 (1.9681)	
[2022-01-24 01:26:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][70/1251]	eta 0:49:59 lr 0.000257	time 1.6294 (2.5397)	loss 3.4605 (3.3212)	grad_norm 2.0182 (1.9688)	
[2022-01-24 01:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][80/1251]	eta 0:48:55 lr 0.000257	time 3.0834 (2.5064)	loss 3.7362 (3.3203)	grad_norm 2.4474 (1.9663)	
[2022-01-24 01:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][90/1251]	eta 0:47:38 lr 0.000257	time 1.8889 (2.4620)	loss 3.4824 (3.3005)	grad_norm 1.7288 (1.9671)	
[2022-01-24 01:27:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][100/1251]	eta 0:46:20 lr 0.000257	time 1.8866 (2.4154)	loss 3.5642 (3.3034)	grad_norm 1.8144 (1.9617)	
[2022-01-24 01:27:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][110/1251]	eta 0:45:26 lr 0.000257	time 1.9274 (2.3892)	loss 3.1634 (3.2861)	grad_norm 1.9452 (1.9557)	
[2022-01-24 01:27:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][120/1251]	eta 0:44:42 lr 0.000257	time 2.8940 (2.3717)	loss 2.3237 (3.2599)	grad_norm 2.0888 (1.9595)	
[2022-01-24 01:28:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][130/1251]	eta 0:43:57 lr 0.000257	time 1.8732 (2.3527)	loss 3.6785 (3.2728)	grad_norm 2.8188 (1.9610)	
[2022-01-24 01:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][140/1251]	eta 0:43:16 lr 0.000257	time 1.9422 (2.3371)	loss 2.9348 (3.2886)	grad_norm 2.1074 (1.9581)	
[2022-01-24 01:28:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][150/1251]	eta 0:42:37 lr 0.000257	time 2.1816 (2.3226)	loss 2.5476 (3.2877)	grad_norm 1.5681 (1.9582)	
[2022-01-24 01:29:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][160/1251]	eta 0:42:08 lr 0.000257	time 2.9731 (2.3176)	loss 4.0353 (3.2844)	grad_norm 1.9644 (1.9581)	
[2022-01-24 01:29:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][170/1251]	eta 0:42:03 lr 0.000257	time 1.5852 (2.3345)	loss 2.8716 (3.2933)	grad_norm 1.8720 (1.9557)	
[2022-01-24 01:30:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][180/1251]	eta 0:41:34 lr 0.000257	time 2.4828 (2.3287)	loss 3.6175 (3.2980)	grad_norm 1.9259 (1.9481)	
[2022-01-24 01:30:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][190/1251]	eta 0:40:51 lr 0.000257	time 2.0101 (2.3106)	loss 3.6845 (3.3067)	grad_norm 1.9414 (1.9458)	
[2022-01-24 01:30:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][200/1251]	eta 0:40:13 lr 0.000257	time 1.9146 (2.2968)	loss 3.2081 (3.2953)	grad_norm 2.2919 (1.9481)	
[2022-01-24 01:31:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][210/1251]	eta 0:39:39 lr 0.000257	time 2.1529 (2.2860)	loss 2.5666 (3.2939)	grad_norm 2.0947 (1.9448)	
[2022-01-24 01:31:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][220/1251]	eta 0:39:08 lr 0.000257	time 1.9729 (2.2783)	loss 3.2945 (3.3003)	grad_norm 2.1804 (1.9436)	
[2022-01-24 01:31:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][230/1251]	eta 0:38:41 lr 0.000257	time 2.2232 (2.2735)	loss 2.6352 (3.2967)	grad_norm 2.1228 (1.9414)	
[2022-01-24 01:32:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][240/1251]	eta 0:38:18 lr 0.000257	time 1.5855 (2.2738)	loss 2.3409 (3.2800)	grad_norm 1.8096 (1.9405)	
[2022-01-24 01:32:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][250/1251]	eta 0:37:59 lr 0.000257	time 1.5719 (2.2775)	loss 3.3807 (3.2758)	grad_norm 1.8663 (1.9403)	
[2022-01-24 01:32:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][260/1251]	eta 0:37:29 lr 0.000257	time 1.6572 (2.2701)	loss 3.4585 (3.2795)	grad_norm 1.8789 (1.9410)	
[2022-01-24 01:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][270/1251]	eta 0:37:04 lr 0.000257	time 2.1471 (2.2680)	loss 3.6144 (3.2848)	grad_norm 2.0696 (1.9400)	
[2022-01-24 01:33:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][280/1251]	eta 0:36:34 lr 0.000256	time 1.5376 (2.2599)	loss 2.9234 (3.2834)	grad_norm 1.9068 (1.9403)	
[2022-01-24 01:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][290/1251]	eta 0:36:08 lr 0.000256	time 2.2005 (2.2568)	loss 2.5358 (3.2915)	grad_norm 1.9035 (1.9428)	
[2022-01-24 01:34:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][300/1251]	eta 0:35:47 lr 0.000256	time 2.6887 (2.2583)	loss 3.2387 (3.2974)	grad_norm 1.8579 (1.9502)	
[2022-01-24 01:34:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][310/1251]	eta 0:35:21 lr 0.000256	time 1.6040 (2.2547)	loss 3.3357 (3.2993)	grad_norm 1.7594 (1.9497)	
[2022-01-24 01:35:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][320/1251]	eta 0:34:53 lr 0.000256	time 1.8303 (2.2486)	loss 3.5927 (3.2874)	grad_norm 1.8155 (1.9464)	
[2022-01-24 01:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][330/1251]	eta 0:34:24 lr 0.000256	time 1.9123 (2.2416)	loss 2.5863 (3.2807)	grad_norm 1.8470 (1.9447)	
[2022-01-24 01:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][340/1251]	eta 0:34:00 lr 0.000256	time 2.2005 (2.2402)	loss 4.0081 (3.2815)	grad_norm 2.1046 (1.9453)	
[2022-01-24 01:36:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][350/1251]	eta 0:33:35 lr 0.000256	time 2.4396 (2.2374)	loss 3.2607 (3.2798)	grad_norm 1.7589 (1.9448)	
[2022-01-24 01:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][360/1251]	eta 0:33:15 lr 0.000256	time 1.5826 (2.2391)	loss 4.1319 (3.2812)	grad_norm 2.2863 (1.9461)	
[2022-01-24 01:36:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][370/1251]	eta 0:32:52 lr 0.000256	time 1.6812 (2.2388)	loss 3.2041 (3.2870)	grad_norm 1.9827 (1.9456)	
[2022-01-24 01:37:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][380/1251]	eta 0:32:28 lr 0.000256	time 1.8831 (2.2375)	loss 3.8360 (3.2930)	grad_norm 1.7488 (1.9449)	
[2022-01-24 01:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][390/1251]	eta 0:32:05 lr 0.000256	time 2.0255 (2.2363)	loss 3.4199 (3.2912)	grad_norm 2.3049 (1.9457)	
[2022-01-24 01:37:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][400/1251]	eta 0:31:40 lr 0.000256	time 1.7369 (2.2337)	loss 3.2392 (3.2962)	grad_norm 1.8148 (1.9436)	
[2022-01-24 01:38:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][410/1251]	eta 0:31:17 lr 0.000256	time 1.9556 (2.2328)	loss 3.3736 (3.3004)	grad_norm 1.8456 (1.9411)	
[2022-01-24 01:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][420/1251]	eta 0:30:50 lr 0.000256	time 1.8787 (2.2273)	loss 2.2346 (3.2970)	grad_norm 1.8215 (1.9394)	
[2022-01-24 01:38:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][430/1251]	eta 0:30:27 lr 0.000256	time 2.2174 (2.2265)	loss 3.5316 (3.2983)	grad_norm 1.9033 (1.9369)	
[2022-01-24 01:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][440/1251]	eta 0:30:03 lr 0.000256	time 1.5225 (2.2238)	loss 4.0743 (3.2942)	grad_norm 2.2133 (1.9376)	
[2022-01-24 01:39:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][450/1251]	eta 0:29:41 lr 0.000256	time 1.7913 (2.2237)	loss 3.6798 (3.2965)	grad_norm 2.1443 (1.9407)	
[2022-01-24 01:40:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][460/1251]	eta 0:29:22 lr 0.000256	time 2.1989 (2.2280)	loss 3.5651 (3.2983)	grad_norm 2.2909 (1.9443)	
[2022-01-24 01:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][470/1251]	eta 0:29:01 lr 0.000256	time 1.6639 (2.2297)	loss 3.5096 (3.2952)	grad_norm 2.1325 (1.9449)	
[2022-01-24 01:40:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][480/1251]	eta 0:28:38 lr 0.000256	time 1.9024 (2.2291)	loss 2.8947 (3.2981)	grad_norm 2.0436 (1.9436)	
[2022-01-24 01:41:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][490/1251]	eta 0:28:13 lr 0.000256	time 1.5340 (2.2249)	loss 2.3630 (3.2956)	grad_norm 1.8774 (1.9434)	
[2022-01-24 01:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][500/1251]	eta 0:27:49 lr 0.000256	time 1.9573 (2.2236)	loss 3.5684 (3.2926)	grad_norm 1.7889 (1.9441)	
[2022-01-24 01:41:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][510/1251]	eta 0:27:25 lr 0.000256	time 2.3529 (2.2209)	loss 3.2734 (3.2896)	grad_norm 1.8363 (1.9427)	
[2022-01-24 01:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][520/1251]	eta 0:27:03 lr 0.000256	time 1.9606 (2.2215)	loss 2.2949 (3.2861)	grad_norm 1.8720 (1.9443)	
[2022-01-24 01:42:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][530/1251]	eta 0:26:42 lr 0.000256	time 1.8886 (2.2222)	loss 3.9251 (3.2922)	grad_norm 1.9810 (1.9445)	
[2022-01-24 01:43:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][540/1251]	eta 0:26:19 lr 0.000256	time 2.2499 (2.2214)	loss 3.5917 (3.2942)	grad_norm 1.9967 (1.9444)	
[2022-01-24 01:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][550/1251]	eta 0:25:56 lr 0.000256	time 2.1975 (2.2199)	loss 2.6264 (3.2933)	grad_norm 1.7362 (1.9451)	
[2022-01-24 01:43:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][560/1251]	eta 0:25:33 lr 0.000255	time 2.1783 (2.2190)	loss 3.5753 (3.2955)	grad_norm 2.1447 (1.9462)	
[2022-01-24 01:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][570/1251]	eta 0:25:09 lr 0.000255	time 2.2220 (2.2168)	loss 3.0368 (3.2949)	grad_norm 1.9295 (1.9462)	
[2022-01-24 01:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][580/1251]	eta 0:24:48 lr 0.000255	time 2.6995 (2.2180)	loss 3.6694 (3.2974)	grad_norm 1.8403 (1.9449)	
[2022-01-24 01:44:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][590/1251]	eta 0:24:27 lr 0.000255	time 1.4878 (2.2197)	loss 2.5912 (3.2956)	grad_norm 2.2615 (1.9449)	
[2022-01-24 01:45:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][600/1251]	eta 0:24:04 lr 0.000255	time 2.3074 (2.2189)	loss 3.4038 (3.2997)	grad_norm 1.7953 (1.9464)	
[2022-01-24 01:45:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][610/1251]	eta 0:23:41 lr 0.000255	time 2.5685 (2.2173)	loss 3.8020 (3.3006)	grad_norm 1.7307 (1.9458)	
[2022-01-24 01:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][620/1251]	eta 0:23:18 lr 0.000255	time 2.2967 (2.2171)	loss 3.5180 (3.3052)	grad_norm 1.8391 (1.9440)	
[2022-01-24 01:46:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][630/1251]	eta 0:22:56 lr 0.000255	time 1.8225 (2.2171)	loss 2.4035 (3.3045)	grad_norm 1.7682 (1.9431)	
[2022-01-24 01:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][640/1251]	eta 0:22:34 lr 0.000255	time 1.8863 (2.2174)	loss 3.3928 (3.3060)	grad_norm 1.7218 (1.9420)	
[2022-01-24 01:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][650/1251]	eta 0:22:12 lr 0.000255	time 1.8751 (2.2168)	loss 2.5810 (3.3042)	grad_norm 1.9656 (1.9408)	
[2022-01-24 01:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][660/1251]	eta 0:21:48 lr 0.000255	time 2.4717 (2.2141)	loss 3.5040 (3.3026)	grad_norm 2.2520 (1.9401)	
[2022-01-24 01:47:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][670/1251]	eta 0:21:24 lr 0.000255	time 1.9918 (2.2102)	loss 3.5110 (3.3042)	grad_norm 1.6954 (1.9380)	
[2022-01-24 01:48:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][680/1251]	eta 0:21:01 lr 0.000255	time 2.8693 (2.2098)	loss 2.9694 (3.3057)	grad_norm 1.9420 (1.9367)	
[2022-01-24 01:48:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][690/1251]	eta 0:20:39 lr 0.000255	time 2.1644 (2.2087)	loss 3.2775 (3.3048)	grad_norm 1.9254 (1.9366)	
[2022-01-24 01:48:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][700/1251]	eta 0:20:16 lr 0.000255	time 1.9701 (2.2082)	loss 3.1299 (3.3054)	grad_norm 1.8317 (1.9377)	
[2022-01-24 01:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][710/1251]	eta 0:19:55 lr 0.000255	time 2.2985 (2.2096)	loss 3.1851 (3.3031)	grad_norm 1.6867 (1.9371)	
[2022-01-24 01:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][720/1251]	eta 0:19:33 lr 0.000255	time 2.7944 (2.2108)	loss 3.5575 (3.3018)	grad_norm 1.8598 (1.9378)	
[2022-01-24 01:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][730/1251]	eta 0:19:11 lr 0.000255	time 1.9952 (2.2101)	loss 2.7654 (3.3052)	grad_norm 1.8569 (1.9377)	
[2022-01-24 01:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][740/1251]	eta 0:18:49 lr 0.000255	time 2.5592 (2.2109)	loss 4.0689 (3.3089)	grad_norm 1.8896 (1.9388)	
[2022-01-24 01:50:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][750/1251]	eta 0:18:28 lr 0.000255	time 2.4454 (2.2123)	loss 3.8013 (3.3114)	grad_norm 1.9509 (1.9385)	
[2022-01-24 01:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][760/1251]	eta 0:18:04 lr 0.000255	time 1.8838 (2.2096)	loss 3.6113 (3.3141)	grad_norm 1.7159 (1.9382)	
[2022-01-24 01:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][770/1251]	eta 0:17:41 lr 0.000255	time 1.7394 (2.2073)	loss 3.3258 (3.3114)	grad_norm 1.7330 (1.9375)	
[2022-01-24 01:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][780/1251]	eta 0:17:19 lr 0.000255	time 1.9907 (2.2062)	loss 2.5965 (3.3101)	grad_norm 1.8910 (1.9375)	
[2022-01-24 01:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][790/1251]	eta 0:16:57 lr 0.000255	time 2.5635 (2.2070)	loss 3.2836 (3.3134)	grad_norm 1.9813 (1.9376)	
[2022-01-24 01:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][800/1251]	eta 0:16:35 lr 0.000255	time 2.1006 (2.2066)	loss 3.5037 (3.3151)	grad_norm 1.8567 (1.9362)	
[2022-01-24 01:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][810/1251]	eta 0:16:13 lr 0.000255	time 1.9502 (2.2064)	loss 3.7567 (3.3184)	grad_norm 1.9707 (1.9372)	
[2022-01-24 01:53:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][820/1251]	eta 0:15:51 lr 0.000255	time 2.1330 (2.2067)	loss 2.5584 (3.3164)	grad_norm 1.9748 (1.9375)	
[2022-01-24 01:53:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][830/1251]	eta 0:15:28 lr 0.000255	time 2.3798 (2.2066)	loss 4.1848 (3.3201)	grad_norm 2.0306 (1.9365)	
[2022-01-24 01:53:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][840/1251]	eta 0:15:07 lr 0.000254	time 2.4692 (2.2089)	loss 3.7020 (3.3217)	grad_norm 1.9634 (1.9363)	
[2022-01-24 01:54:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][850/1251]	eta 0:14:45 lr 0.000254	time 1.9610 (2.2093)	loss 2.6987 (3.3184)	grad_norm 2.1714 (1.9357)	
[2022-01-24 01:54:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][860/1251]	eta 0:14:23 lr 0.000254	time 3.3631 (2.2088)	loss 3.4144 (3.3163)	grad_norm 1.6814 (1.9351)	
[2022-01-24 01:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][870/1251]	eta 0:14:00 lr 0.000254	time 1.9475 (2.2062)	loss 2.9714 (3.3163)	grad_norm 2.0933 (1.9362)	
[2022-01-24 01:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][880/1251]	eta 0:13:38 lr 0.000254	time 2.2399 (2.2057)	loss 3.6208 (3.3153)	grad_norm 1.8027 (1.9376)	
[2022-01-24 01:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][890/1251]	eta 0:13:15 lr 0.000254	time 1.9506 (2.2046)	loss 3.0267 (3.3159)	grad_norm 1.9760 (1.9378)	
[2022-01-24 01:56:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][900/1251]	eta 0:12:53 lr 0.000254	time 2.4087 (2.2049)	loss 3.4270 (3.3168)	grad_norm 1.7959 (1.9395)	
[2022-01-24 01:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][910/1251]	eta 0:12:31 lr 0.000254	time 2.1947 (2.2049)	loss 3.4212 (3.3168)	grad_norm 2.0918 (1.9416)	
[2022-01-24 01:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][920/1251]	eta 0:12:09 lr 0.000254	time 2.0681 (2.2049)	loss 2.3932 (3.3152)	grad_norm 1.9301 (1.9416)	
[2022-01-24 01:57:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][930/1251]	eta 0:11:47 lr 0.000254	time 1.9715 (2.2055)	loss 3.5590 (3.3156)	grad_norm 2.1393 (1.9414)	
[2022-01-24 01:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][940/1251]	eta 0:11:25 lr 0.000254	time 1.8932 (2.2046)	loss 3.7682 (3.3175)	grad_norm 1.8815 (1.9434)	
[2022-01-24 01:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][950/1251]	eta 0:11:03 lr 0.000254	time 3.0751 (2.2055)	loss 3.3353 (3.3155)	grad_norm 1.5431 (1.9438)	
[2022-01-24 01:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][960/1251]	eta 0:10:41 lr 0.000254	time 1.8770 (2.2049)	loss 2.6200 (3.3151)	grad_norm 1.9472 (1.9434)	
[2022-01-24 01:58:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][970/1251]	eta 0:10:19 lr 0.000254	time 2.5664 (2.2047)	loss 3.6267 (3.3154)	grad_norm 2.3479 (1.9448)	
[2022-01-24 01:59:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][980/1251]	eta 0:09:57 lr 0.000254	time 1.8785 (2.2035)	loss 3.5309 (3.3177)	grad_norm 1.5779 (1.9446)	
[2022-01-24 01:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][990/1251]	eta 0:09:35 lr 0.000254	time 3.2696 (2.2040)	loss 3.6013 (3.3179)	grad_norm 2.1574 (1.9458)	
[2022-01-24 01:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1000/1251]	eta 0:09:12 lr 0.000254	time 1.8138 (2.2027)	loss 2.4970 (3.3165)	grad_norm 2.0754 (1.9483)	
[2022-01-24 02:00:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1010/1251]	eta 0:08:50 lr 0.000254	time 2.0341 (2.2021)	loss 3.9962 (3.3174)	grad_norm 1.7512 (1.9481)	
[2022-01-24 02:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1020/1251]	eta 0:08:28 lr 0.000254	time 2.0817 (2.2001)	loss 3.7850 (3.3173)	grad_norm 2.3217 (1.9486)	
[2022-01-24 02:00:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1030/1251]	eta 0:08:06 lr 0.000254	time 2.8719 (2.2001)	loss 4.0194 (3.3179)	grad_norm 1.8095 (1.9481)	
[2022-01-24 02:01:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1040/1251]	eta 0:07:44 lr 0.000254	time 2.1604 (2.1995)	loss 3.4572 (3.3170)	grad_norm 2.4772 (1.9489)	
[2022-01-24 02:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1050/1251]	eta 0:07:22 lr 0.000254	time 2.4578 (2.2005)	loss 3.6806 (3.3166)	grad_norm 1.8942 (1.9483)	
[2022-01-24 02:01:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1060/1251]	eta 0:07:00 lr 0.000254	time 1.9365 (2.2015)	loss 3.2168 (3.3139)	grad_norm 1.9111 (1.9485)	
[2022-01-24 02:02:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1070/1251]	eta 0:06:38 lr 0.000254	time 2.8486 (2.2024)	loss 3.1802 (3.3151)	grad_norm 1.8885 (1.9485)	
[2022-01-24 02:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1080/1251]	eta 0:06:16 lr 0.000254	time 1.8860 (2.2010)	loss 3.3227 (3.3163)	grad_norm 2.1465 (1.9478)	
[2022-01-24 02:02:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1090/1251]	eta 0:05:53 lr 0.000254	time 1.9334 (2.1984)	loss 3.7355 (3.3178)	grad_norm 1.5995 (1.9468)	
[2022-01-24 02:03:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1100/1251]	eta 0:05:31 lr 0.000254	time 2.2812 (2.1977)	loss 3.7768 (3.3167)	grad_norm 1.7638 (1.9463)	
[2022-01-24 02:03:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1110/1251]	eta 0:05:09 lr 0.000254	time 2.1578 (2.1974)	loss 3.2915 (3.3170)	grad_norm 1.8368 (1.9459)	
[2022-01-24 02:04:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1120/1251]	eta 0:04:47 lr 0.000253	time 2.0284 (2.1964)	loss 3.5708 (3.3199)	grad_norm 2.2752 (1.9463)	
[2022-01-24 02:04:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1130/1251]	eta 0:04:25 lr 0.000253	time 2.7939 (2.1973)	loss 3.8616 (3.3186)	grad_norm 2.3313 (1.9474)	
[2022-01-24 02:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1140/1251]	eta 0:04:03 lr 0.000253	time 2.4831 (2.1974)	loss 3.4499 (3.3196)	grad_norm 1.7943 (1.9478)	
[2022-01-24 02:05:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1150/1251]	eta 0:03:41 lr 0.000253	time 2.3396 (2.1968)	loss 2.5303 (3.3176)	grad_norm 1.9643 (1.9481)	
[2022-01-24 02:05:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1160/1251]	eta 0:03:19 lr 0.000253	time 2.4963 (2.1962)	loss 3.9610 (3.3196)	grad_norm 1.9113 (1.9482)	
[2022-01-24 02:05:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1170/1251]	eta 0:02:58 lr 0.000253	time 2.7888 (2.1984)	loss 3.5050 (3.3210)	grad_norm 2.0020 (1.9478)	
[2022-01-24 02:06:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1180/1251]	eta 0:02:36 lr 0.000253	time 2.5654 (2.1986)	loss 2.2763 (3.3222)	grad_norm 1.8328 (1.9479)	
[2022-01-24 02:06:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1190/1251]	eta 0:02:14 lr 0.000253	time 1.7023 (2.1974)	loss 2.8304 (3.3235)	grad_norm 1.9037 (1.9485)	
[2022-01-24 02:06:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1200/1251]	eta 0:01:52 lr 0.000253	time 1.8601 (2.1965)	loss 3.7676 (3.3246)	grad_norm 2.0415 (1.9487)	
[2022-01-24 02:07:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1210/1251]	eta 0:01:30 lr 0.000253	time 1.5871 (2.1959)	loss 3.3172 (3.3259)	grad_norm 1.8978 (1.9504)	
[2022-01-24 02:07:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1220/1251]	eta 0:01:08 lr 0.000253	time 2.2583 (2.1953)	loss 2.8599 (3.3259)	grad_norm 1.9273 (1.9502)	
[2022-01-24 02:08:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1230/1251]	eta 0:00:46 lr 0.000253	time 1.9059 (2.1956)	loss 3.2827 (3.3265)	grad_norm 2.0821 (1.9514)	
[2022-01-24 02:08:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1240/1251]	eta 0:00:24 lr 0.000253	time 1.2729 (2.1944)	loss 3.5071 (3.3260)	grad_norm 2.0350 (1.9551)	
[2022-01-24 02:08:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [200/300][1250/1251]	eta 0:00:02 lr 0.000253	time 1.1757 (2.1891)	loss 3.8951 (3.3291)	grad_norm 2.0201 (1.9550)	
[2022-01-24 02:08:39 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 200 training takes 0:45:38
[2022-01-24 02:08:39 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_200 saving......
[2022-01-24 02:08:50 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_200 saved !!!
[2022-01-24 02:09:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 15.207 (15.207)	Loss 0.9469 (0.9469)	Acc@1 78.320 (78.320)	Acc@5 93.164 (93.164)	
[2022-01-24 02:09:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.968 (2.661)	Loss 0.9927 (0.9120)	Acc@1 76.855 (78.427)	Acc@5 93.457 (94.425)	
[2022-01-24 02:09:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.721 (2.233)	Loss 0.8864 (0.9114)	Acc@1 79.492 (78.371)	Acc@5 94.922 (94.420)	
[2022-01-24 02:09:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.969 (1.957)	Loss 0.9581 (0.9189)	Acc@1 78.320 (78.364)	Acc@5 93.848 (94.317)	
[2022-01-24 02:10:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.493 (1.947)	Loss 0.8496 (0.9180)	Acc@1 80.078 (78.399)	Acc@5 94.922 (94.310)	
[2022-01-24 02:10:18 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.300 Acc@5 94.328
[2022-01-24 02:10:18 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.3%
[2022-01-24 02:10:18 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.40%
[2022-01-24 02:10:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][0/1251]	eta 7:15:18 lr 0.000253	time 20.8783 (20.8783)	loss 2.6863 (2.6863)	grad_norm 2.1116 (2.1116)	
[2022-01-24 02:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][10/1251]	eta 1:21:07 lr 0.000253	time 1.5115 (3.9225)	loss 3.5487 (3.3144)	grad_norm 1.6138 (1.9444)	
[2022-01-24 02:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][20/1251]	eta 1:02:47 lr 0.000253	time 1.4475 (3.0605)	loss 3.6222 (3.4419)	grad_norm 1.8705 (1.9180)	
[2022-01-24 02:11:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][30/1251]	eta 0:57:38 lr 0.000253	time 1.8027 (2.8323)	loss 3.8460 (3.4422)	grad_norm 2.5386 (1.9402)	
[2022-01-24 02:12:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][40/1251]	eta 0:54:53 lr 0.000253	time 3.8418 (2.7200)	loss 2.7741 (3.3685)	grad_norm 1.9569 (1.9430)	
[2022-01-24 02:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][50/1251]	eta 0:53:41 lr 0.000253	time 3.1095 (2.6825)	loss 3.6686 (3.3347)	grad_norm 2.3370 (1.9706)	
[2022-01-24 02:12:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][60/1251]	eta 0:51:24 lr 0.000253	time 1.5507 (2.5898)	loss 3.3975 (3.3255)	grad_norm 1.8046 (1.9737)	
[2022-01-24 02:13:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][70/1251]	eta 0:49:57 lr 0.000253	time 1.9036 (2.5381)	loss 3.2019 (3.3273)	grad_norm 1.7959 (1.9867)	
[2022-01-24 02:13:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][80/1251]	eta 0:49:11 lr 0.000253	time 3.8860 (2.5204)	loss 4.1091 (3.3269)	grad_norm 1.9971 (1.9854)	
[2022-01-24 02:14:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][90/1251]	eta 0:48:21 lr 0.000253	time 1.8765 (2.4992)	loss 3.7570 (3.3118)	grad_norm 1.9491 (1.9887)	
[2022-01-24 02:14:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][100/1251]	eta 0:47:15 lr 0.000253	time 1.6691 (2.4635)	loss 3.3608 (3.3327)	grad_norm 1.9394 (1.9861)	
[2022-01-24 02:14:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][110/1251]	eta 0:46:09 lr 0.000253	time 1.7723 (2.4273)	loss 3.6809 (3.3508)	grad_norm 1.9914 (1.9772)	
[2022-01-24 02:15:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][120/1251]	eta 0:45:40 lr 0.000253	time 3.6632 (2.4230)	loss 3.5480 (3.3554)	grad_norm 2.3952 (1.9796)	
[2022-01-24 02:15:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][130/1251]	eta 0:44:50 lr 0.000253	time 1.7546 (2.3996)	loss 4.0220 (3.3497)	grad_norm 2.1135 (1.9686)	
[2022-01-24 02:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][140/1251]	eta 0:44:02 lr 0.000253	time 2.1644 (2.3789)	loss 3.8191 (3.3626)	grad_norm 1.9737 (1.9657)	
[2022-01-24 02:16:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][150/1251]	eta 0:43:12 lr 0.000252	time 1.5806 (2.3545)	loss 3.9410 (3.3898)	grad_norm 1.8485 (1.9675)	
[2022-01-24 02:16:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][160/1251]	eta 0:42:36 lr 0.000252	time 2.6005 (2.3436)	loss 3.7049 (3.4072)	grad_norm 1.8684 (1.9703)	
[2022-01-24 02:16:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][170/1251]	eta 0:42:09 lr 0.000252	time 2.1531 (2.3396)	loss 3.2036 (3.4067)	grad_norm 2.3485 (1.9790)	
[2022-01-24 02:17:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][180/1251]	eta 0:41:41 lr 0.000252	time 1.9165 (2.3356)	loss 3.4436 (3.4059)	grad_norm 2.5174 (1.9796)	
[2022-01-24 02:17:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][190/1251]	eta 0:41:14 lr 0.000252	time 2.1016 (2.3320)	loss 3.3205 (3.3967)	grad_norm 2.2780 (1.9938)	
[2022-01-24 02:18:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][200/1251]	eta 0:40:37 lr 0.000252	time 1.9312 (2.3190)	loss 4.0465 (3.3946)	grad_norm 2.4037 (2.0015)	
[2022-01-24 02:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][210/1251]	eta 0:40:04 lr 0.000252	time 1.9743 (2.3100)	loss 3.6987 (3.4016)	grad_norm 1.8261 (1.9931)	
[2022-01-24 02:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][220/1251]	eta 0:39:37 lr 0.000252	time 2.2771 (2.3063)	loss 3.7655 (3.4021)	grad_norm 1.9317 (1.9885)	
[2022-01-24 02:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][230/1251]	eta 0:39:13 lr 0.000252	time 1.9125 (2.3051)	loss 3.3225 (3.4030)	grad_norm 2.3566 (1.9884)	
[2022-01-24 02:19:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][240/1251]	eta 0:38:43 lr 0.000252	time 1.8581 (2.2986)	loss 2.4911 (3.3979)	grad_norm 1.8387 (1.9877)	
[2022-01-24 02:19:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][250/1251]	eta 0:38:14 lr 0.000252	time 1.8717 (2.2924)	loss 3.7212 (3.3872)	grad_norm 2.1756 (1.9902)	
[2022-01-24 02:20:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][260/1251]	eta 0:37:44 lr 0.000252	time 1.8910 (2.2854)	loss 2.2209 (3.3648)	grad_norm 1.5733 (1.9868)	
[2022-01-24 02:20:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][270/1251]	eta 0:37:19 lr 0.000252	time 2.7255 (2.2830)	loss 3.4019 (3.3618)	grad_norm 1.8523 (1.9881)	
[2022-01-24 02:21:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][280/1251]	eta 0:36:55 lr 0.000252	time 1.7563 (2.2819)	loss 3.4310 (3.3511)	grad_norm 1.8601 (1.9825)	
[2022-01-24 02:21:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][290/1251]	eta 0:36:29 lr 0.000252	time 2.0875 (2.2787)	loss 3.5795 (3.3439)	grad_norm 2.0151 (1.9803)	
[2022-01-24 02:21:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][300/1251]	eta 0:36:04 lr 0.000252	time 2.2550 (2.2765)	loss 3.5524 (3.3413)	grad_norm 1.7458 (1.9738)	
[2022-01-24 02:22:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][310/1251]	eta 0:35:37 lr 0.000252	time 2.5495 (2.2719)	loss 3.1028 (3.3431)	grad_norm 2.0690 (1.9708)	
[2022-01-24 02:22:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][320/1251]	eta 0:35:06 lr 0.000252	time 1.6374 (2.2626)	loss 2.6404 (3.3353)	grad_norm 1.8796 (1.9687)	
[2022-01-24 02:22:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][330/1251]	eta 0:34:38 lr 0.000252	time 2.4438 (2.2565)	loss 3.8446 (3.3404)	grad_norm 1.9428 (1.9676)	
[2022-01-24 02:23:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][340/1251]	eta 0:34:17 lr 0.000252	time 2.9764 (2.2590)	loss 3.7126 (3.3423)	grad_norm 1.7951 (1.9663)	
[2022-01-24 02:23:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][350/1251]	eta 0:33:54 lr 0.000252	time 2.5123 (2.2580)	loss 3.7268 (3.3390)	grad_norm 1.9192 (1.9632)	
[2022-01-24 02:23:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][360/1251]	eta 0:33:31 lr 0.000252	time 2.2810 (2.2574)	loss 2.7347 (3.3433)	grad_norm 1.4797 (1.9617)	
[2022-01-24 02:24:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][370/1251]	eta 0:33:07 lr 0.000252	time 2.2410 (2.2561)	loss 3.1707 (3.3446)	grad_norm 1.8604 (1.9621)	
[2022-01-24 02:24:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][380/1251]	eta 0:32:45 lr 0.000252	time 2.9371 (2.2562)	loss 4.0022 (3.3449)	grad_norm 2.4494 (1.9642)	
[2022-01-24 02:25:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][390/1251]	eta 0:32:21 lr 0.000252	time 2.4856 (2.2550)	loss 3.0089 (3.3395)	grad_norm 1.9714 (1.9656)	
[2022-01-24 02:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][400/1251]	eta 0:31:56 lr 0.000252	time 1.7192 (2.2516)	loss 3.5474 (3.3438)	grad_norm 2.2139 (1.9651)	
[2022-01-24 02:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][410/1251]	eta 0:31:30 lr 0.000252	time 1.8032 (2.2476)	loss 3.5249 (3.3434)	grad_norm 1.9806 (1.9673)	
[2022-01-24 02:26:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][420/1251]	eta 0:31:03 lr 0.000252	time 1.9450 (2.2424)	loss 2.6243 (3.3452)	grad_norm 1.7516 (1.9644)	
[2022-01-24 02:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][430/1251]	eta 0:30:37 lr 0.000251	time 2.2046 (2.2384)	loss 2.5333 (3.3483)	grad_norm 2.0326 (1.9632)	
[2022-01-24 02:26:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][440/1251]	eta 0:30:14 lr 0.000251	time 2.4728 (2.2371)	loss 3.0096 (3.3530)	grad_norm 1.8983 (1.9617)	
[2022-01-24 02:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][450/1251]	eta 0:29:53 lr 0.000251	time 2.8604 (2.2392)	loss 4.1193 (3.3572)	grad_norm 1.8705 (1.9603)	
[2022-01-24 02:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][460/1251]	eta 0:29:31 lr 0.000251	time 2.0091 (2.2400)	loss 3.1065 (3.3553)	grad_norm 2.1296 (1.9614)	
[2022-01-24 02:27:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][470/1251]	eta 0:29:09 lr 0.000251	time 2.1917 (2.2398)	loss 3.4901 (3.3565)	grad_norm 1.8509 (1.9606)	
[2022-01-24 02:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][480/1251]	eta 0:28:46 lr 0.000251	time 2.4812 (2.2391)	loss 3.8848 (3.3554)	grad_norm 1.8732 (1.9596)	
[2022-01-24 02:28:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][490/1251]	eta 0:28:23 lr 0.000251	time 2.5331 (2.2383)	loss 3.8625 (3.3573)	grad_norm 2.0639 (1.9588)	
[2022-01-24 02:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][500/1251]	eta 0:27:58 lr 0.000251	time 1.6798 (2.2346)	loss 3.5864 (3.3571)	grad_norm 1.6315 (1.9645)	
[2022-01-24 02:29:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][510/1251]	eta 0:27:35 lr 0.000251	time 2.7418 (2.2338)	loss 3.4577 (3.3561)	grad_norm 2.0985 (1.9643)	
[2022-01-24 02:29:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][520/1251]	eta 0:27:09 lr 0.000251	time 1.9683 (2.2291)	loss 2.5162 (3.3543)	grad_norm 2.1551 (1.9646)	
[2022-01-24 02:30:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][530/1251]	eta 0:26:46 lr 0.000251	time 2.5227 (2.2285)	loss 3.2106 (3.3546)	grad_norm 1.7611 (1.9620)	
[2022-01-24 02:30:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][540/1251]	eta 0:26:24 lr 0.000251	time 2.2311 (2.2281)	loss 3.6719 (3.3544)	grad_norm 1.6397 (1.9633)	
[2022-01-24 02:30:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][550/1251]	eta 0:26:04 lr 0.000251	time 2.6942 (2.2314)	loss 3.1270 (3.3550)	grad_norm 1.9867 (1.9641)	
[2022-01-24 02:31:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][560/1251]	eta 0:25:40 lr 0.000251	time 1.5615 (2.2297)	loss 3.4602 (3.3558)	grad_norm 2.2243 (1.9648)	
[2022-01-24 02:31:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][570/1251]	eta 0:25:18 lr 0.000251	time 2.4840 (2.2297)	loss 3.5713 (3.3552)	grad_norm 2.2638 (1.9631)	
[2022-01-24 02:31:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][580/1251]	eta 0:24:53 lr 0.000251	time 1.9482 (2.2261)	loss 2.5690 (3.3510)	grad_norm 1.7643 (1.9627)	
[2022-01-24 02:32:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][590/1251]	eta 0:24:30 lr 0.000251	time 2.5899 (2.2244)	loss 3.3008 (3.3457)	grad_norm 1.7690 (1.9623)	
[2022-01-24 02:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][600/1251]	eta 0:24:08 lr 0.000251	time 2.1770 (2.2246)	loss 3.7532 (3.3482)	grad_norm 1.7925 (1.9616)	
[2022-01-24 02:32:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][610/1251]	eta 0:23:46 lr 0.000251	time 2.2551 (2.2257)	loss 3.6625 (3.3509)	grad_norm 1.8841 (1.9595)	
[2022-01-24 02:33:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][620/1251]	eta 0:23:25 lr 0.000251	time 1.8344 (2.2270)	loss 4.0302 (3.3496)	grad_norm 2.0347 (1.9591)	
[2022-01-24 02:33:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][630/1251]	eta 0:23:02 lr 0.000251	time 2.2848 (2.2263)	loss 2.8196 (3.3482)	grad_norm 2.2697 (1.9571)	
[2022-01-24 02:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][640/1251]	eta 0:22:40 lr 0.000251	time 3.1935 (2.2266)	loss 3.3718 (3.3454)	grad_norm 1.8749 (1.9559)	
[2022-01-24 02:34:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][650/1251]	eta 0:22:16 lr 0.000251	time 1.9477 (2.2245)	loss 3.9914 (3.3448)	grad_norm 1.9055 (1.9545)	
[2022-01-24 02:34:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][660/1251]	eta 0:21:53 lr 0.000251	time 2.2689 (2.2222)	loss 3.1080 (3.3481)	grad_norm 1.7308 (1.9542)	
[2022-01-24 02:35:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][670/1251]	eta 0:21:29 lr 0.000251	time 1.8388 (2.2203)	loss 3.1835 (3.3451)	grad_norm 1.7643 (1.9539)	
[2022-01-24 02:35:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][680/1251]	eta 0:21:08 lr 0.000251	time 3.2156 (2.2216)	loss 3.6916 (3.3478)	grad_norm 1.8858 (1.9536)	
[2022-01-24 02:35:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][690/1251]	eta 0:20:46 lr 0.000251	time 2.2440 (2.2217)	loss 2.5884 (3.3429)	grad_norm 1.8551 (1.9528)	
[2022-01-24 02:36:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][700/1251]	eta 0:20:24 lr 0.000251	time 2.2019 (2.2223)	loss 3.5709 (3.3420)	grad_norm 2.0231 (1.9520)	
[2022-01-24 02:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][710/1251]	eta 0:20:01 lr 0.000250	time 2.0690 (2.2211)	loss 3.1912 (3.3440)	grad_norm 1.9138 (1.9512)	
[2022-01-24 02:36:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][720/1251]	eta 0:19:38 lr 0.000250	time 2.7443 (2.2192)	loss 2.4890 (3.3422)	grad_norm 1.9739 (1.9509)	
[2022-01-24 02:37:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][730/1251]	eta 0:19:15 lr 0.000250	time 1.9632 (2.2171)	loss 3.6102 (3.3412)	grad_norm 1.6442 (1.9509)	
[2022-01-24 02:37:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][740/1251]	eta 0:18:52 lr 0.000250	time 2.7773 (2.2167)	loss 2.2636 (3.3373)	grad_norm 1.9174 (1.9495)	
[2022-01-24 02:38:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][750/1251]	eta 0:18:30 lr 0.000250	time 2.2004 (2.2174)	loss 3.5813 (3.3395)	grad_norm 1.7932 (1.9505)	
[2022-01-24 02:38:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][760/1251]	eta 0:18:08 lr 0.000250	time 2.4959 (2.2175)	loss 3.8459 (3.3439)	grad_norm 1.8269 (1.9494)	
[2022-01-24 02:38:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][770/1251]	eta 0:17:46 lr 0.000250	time 2.1536 (2.2176)	loss 2.4023 (3.3453)	grad_norm 1.8049 (1.9489)	
[2022-01-24 02:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][780/1251]	eta 0:17:24 lr 0.000250	time 2.7806 (2.2178)	loss 3.9740 (3.3474)	grad_norm 2.1332 (1.9514)	
[2022-01-24 02:39:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][790/1251]	eta 0:17:02 lr 0.000250	time 1.6196 (2.2174)	loss 3.2621 (3.3467)	grad_norm 2.0378 (1.9535)	
[2022-01-24 02:39:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][800/1251]	eta 0:16:40 lr 0.000250	time 2.4747 (2.2183)	loss 3.8978 (3.3452)	grad_norm 1.8975 (1.9532)	
[2022-01-24 02:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][810/1251]	eta 0:16:17 lr 0.000250	time 2.1616 (2.2168)	loss 3.9246 (3.3438)	grad_norm 2.3126 (1.9546)	
[2022-01-24 02:40:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][820/1251]	eta 0:15:54 lr 0.000250	time 1.8497 (2.2139)	loss 3.1859 (3.3433)	grad_norm 2.2011 (1.9547)	
[2022-01-24 02:40:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][830/1251]	eta 0:15:31 lr 0.000250	time 2.4967 (2.2131)	loss 3.8698 (3.3438)	grad_norm 1.8913 (1.9534)	
[2022-01-24 02:41:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][840/1251]	eta 0:15:08 lr 0.000250	time 1.9822 (2.2103)	loss 3.7098 (3.3439)	grad_norm 1.9275 (1.9527)	
[2022-01-24 02:41:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][850/1251]	eta 0:14:46 lr 0.000250	time 2.4284 (2.2100)	loss 3.0373 (3.3438)	grad_norm 1.9636 (1.9525)	
[2022-01-24 02:42:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][860/1251]	eta 0:14:24 lr 0.000250	time 2.0013 (2.2101)	loss 3.6046 (3.3466)	grad_norm 1.7917 (1.9515)	
[2022-01-24 02:42:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][870/1251]	eta 0:14:02 lr 0.000250	time 2.4397 (2.2116)	loss 2.7829 (3.3477)	grad_norm 2.0126 (1.9522)	
[2022-01-24 02:42:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][880/1251]	eta 0:13:40 lr 0.000250	time 2.9658 (2.2117)	loss 3.5161 (3.3431)	grad_norm 1.8868 (1.9529)	
[2022-01-24 02:43:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][890/1251]	eta 0:13:18 lr 0.000250	time 1.9309 (2.2117)	loss 3.4022 (3.3462)	grad_norm 2.0237 (1.9522)	
[2022-01-24 02:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][900/1251]	eta 0:12:56 lr 0.000250	time 1.8238 (2.2115)	loss 3.5688 (3.3447)	grad_norm 2.0194 (1.9533)	
[2022-01-24 02:43:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][910/1251]	eta 0:12:33 lr 0.000250	time 2.1692 (2.2110)	loss 3.2452 (3.3446)	grad_norm 2.2269 (1.9541)	
[2022-01-24 02:44:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][920/1251]	eta 0:12:11 lr 0.000250	time 2.7210 (2.2109)	loss 3.6394 (3.3447)	grad_norm 1.8749 (1.9549)	
[2022-01-24 02:44:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][930/1251]	eta 0:11:49 lr 0.000250	time 2.6046 (2.2101)	loss 3.6748 (3.3474)	grad_norm 2.1250 (1.9561)	
[2022-01-24 02:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][940/1251]	eta 0:11:27 lr 0.000250	time 1.8844 (2.2095)	loss 3.5910 (3.3472)	grad_norm 1.8448 (1.9557)	
[2022-01-24 02:45:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][950/1251]	eta 0:11:04 lr 0.000250	time 1.4719 (2.2093)	loss 3.2708 (3.3485)	grad_norm 1.5983 (1.9558)	
[2022-01-24 02:45:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][960/1251]	eta 0:10:43 lr 0.000250	time 3.3038 (2.2102)	loss 3.4340 (3.3466)	grad_norm 1.8378 (1.9563)	
[2022-01-24 02:46:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][970/1251]	eta 0:10:21 lr 0.000250	time 2.7565 (2.2107)	loss 4.1942 (3.3454)	grad_norm 2.1613 (1.9565)	
[2022-01-24 02:46:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][980/1251]	eta 0:09:58 lr 0.000250	time 2.2104 (2.2099)	loss 4.2507 (3.3464)	grad_norm 1.9755 (1.9572)	
[2022-01-24 02:46:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][990/1251]	eta 0:09:36 lr 0.000250	time 1.8541 (2.2098)	loss 3.4304 (3.3453)	grad_norm 1.9036 (1.9580)	
[2022-01-24 02:47:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1000/1251]	eta 0:09:14 lr 0.000249	time 2.1389 (2.2087)	loss 2.9140 (3.3449)	grad_norm 1.8386 (1.9578)	
[2022-01-24 02:47:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1010/1251]	eta 0:08:52 lr 0.000249	time 2.1898 (2.2081)	loss 2.3545 (3.3439)	grad_norm 1.6334 (1.9568)	
[2022-01-24 02:47:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1020/1251]	eta 0:08:30 lr 0.000249	time 2.1474 (2.2084)	loss 3.5366 (3.3422)	grad_norm 1.9248 (1.9578)	
[2022-01-24 02:48:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1030/1251]	eta 0:08:08 lr 0.000249	time 1.6986 (2.2096)	loss 2.8056 (3.3418)	grad_norm 1.8361 (1.9576)	
[2022-01-24 02:48:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1040/1251]	eta 0:07:46 lr 0.000249	time 2.5072 (2.2102)	loss 3.3353 (3.3413)	grad_norm 1.7732 (1.9580)	
[2022-01-24 02:49:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1050/1251]	eta 0:07:24 lr 0.000249	time 2.6142 (2.2096)	loss 3.3405 (3.3407)	grad_norm 2.0474 (1.9575)	
[2022-01-24 02:49:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1060/1251]	eta 0:07:01 lr 0.000249	time 1.7490 (2.2080)	loss 2.2476 (3.3394)	grad_norm 2.3072 (1.9584)	
[2022-01-24 02:49:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1070/1251]	eta 0:06:39 lr 0.000249	time 1.8883 (2.2069)	loss 3.4826 (3.3415)	grad_norm 1.9056 (1.9578)	
[2022-01-24 02:50:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1080/1251]	eta 0:06:17 lr 0.000249	time 2.2050 (2.2053)	loss 3.7995 (3.3415)	grad_norm 3.2131 (1.9592)	
[2022-01-24 02:50:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1090/1251]	eta 0:05:54 lr 0.000249	time 1.5645 (2.2043)	loss 2.1572 (3.3394)	grad_norm 2.1608 (1.9599)	
[2022-01-24 02:50:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1100/1251]	eta 0:05:32 lr 0.000249	time 2.2360 (2.2043)	loss 3.9543 (3.3396)	grad_norm 1.8371 (1.9590)	
[2022-01-24 02:51:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1110/1251]	eta 0:05:10 lr 0.000249	time 1.8912 (2.2047)	loss 2.0553 (3.3387)	grad_norm 1.7402 (1.9587)	
[2022-01-24 02:51:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1120/1251]	eta 0:04:49 lr 0.000249	time 3.4100 (2.2069)	loss 3.6306 (3.3370)	grad_norm 2.2381 (1.9591)	
[2022-01-24 02:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1130/1251]	eta 0:04:27 lr 0.000249	time 1.6616 (2.2075)	loss 3.8575 (3.3377)	grad_norm 1.9988 (1.9590)	
[2022-01-24 02:52:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1140/1251]	eta 0:04:05 lr 0.000249	time 2.9036 (2.2098)	loss 3.6407 (3.3396)	grad_norm 2.2087 (1.9583)	
[2022-01-24 02:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1150/1251]	eta 0:03:43 lr 0.000249	time 2.2475 (2.2098)	loss 2.7069 (3.3378)	grad_norm 1.7139 (1.9586)	
[2022-01-24 02:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1160/1251]	eta 0:03:20 lr 0.000249	time 2.2357 (2.2084)	loss 2.2430 (3.3351)	grad_norm 1.9190 (1.9580)	
[2022-01-24 02:53:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1170/1251]	eta 0:02:58 lr 0.000249	time 1.9735 (2.2058)	loss 3.1584 (3.3356)	grad_norm 1.8827 (1.9578)	
[2022-01-24 02:53:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1180/1251]	eta 0:02:36 lr 0.000249	time 1.8476 (2.2039)	loss 3.8615 (3.3369)	grad_norm 1.8842 (1.9589)	
[2022-01-24 02:54:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1190/1251]	eta 0:02:14 lr 0.000249	time 2.1992 (2.2037)	loss 2.7614 (3.3353)	grad_norm 2.0964 (1.9592)	
[2022-01-24 02:54:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1200/1251]	eta 0:01:52 lr 0.000249	time 2.0579 (2.2032)	loss 3.3587 (3.3371)	grad_norm 2.0816 (1.9600)	
[2022-01-24 02:54:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1210/1251]	eta 0:01:30 lr 0.000249	time 2.9319 (2.2036)	loss 3.3989 (3.3376)	grad_norm 1.8504 (1.9605)	
[2022-01-24 02:55:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1220/1251]	eta 0:01:08 lr 0.000249	time 2.1063 (2.2047)	loss 3.0238 (3.3377)	grad_norm 1.9586 (1.9609)	
[2022-01-24 02:55:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1230/1251]	eta 0:00:46 lr 0.000249	time 2.7879 (2.2050)	loss 3.5933 (3.3373)	grad_norm 1.9402 (1.9623)	
[2022-01-24 02:55:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1240/1251]	eta 0:00:24 lr 0.000249	time 1.4775 (2.2046)	loss 3.6554 (3.3373)	grad_norm 1.8403 (1.9626)	
[2022-01-24 02:56:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [201/300][1250/1251]	eta 0:00:02 lr 0.000249	time 1.3072 (2.2000)	loss 3.3968 (3.3373)	grad_norm 2.0220 (1.9622)	
[2022-01-24 02:56:11 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 201 training takes 0:45:52
[2022-01-24 02:56:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.554 (18.554)	Loss 1.0418 (1.0418)	Acc@1 76.660 (76.660)	Acc@5 93.262 (93.262)	
[2022-01-24 02:56:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.111 (3.293)	Loss 0.8872 (0.9133)	Acc@1 80.273 (78.516)	Acc@5 94.824 (94.460)	
[2022-01-24 02:57:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.189 (2.679)	Loss 0.8688 (0.9116)	Acc@1 79.102 (78.367)	Acc@5 94.727 (94.438)	
[2022-01-24 02:57:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.314 (2.265)	Loss 0.9614 (0.9157)	Acc@1 77.637 (78.292)	Acc@5 93.750 (94.352)	
[2022-01-24 02:57:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.686 (2.130)	Loss 0.9210 (0.9091)	Acc@1 78.418 (78.361)	Acc@5 95.312 (94.484)	
[2022-01-24 02:57:45 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.336 Acc@5 94.490
[2022-01-24 02:57:45 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.3%
[2022-01-24 02:57:45 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.40%
[2022-01-24 02:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][0/1251]	eta 7:27:21 lr 0.000249	time 21.4559 (21.4559)	loss 3.4813 (3.4813)	grad_norm 1.8247 (1.8247)	
[2022-01-24 02:58:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][10/1251]	eta 1:25:42 lr 0.000249	time 2.5925 (4.1436)	loss 3.4062 (3.0395)	grad_norm 1.8915 (1.8853)	
[2022-01-24 02:58:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][20/1251]	eta 1:05:34 lr 0.000249	time 1.4322 (3.1958)	loss 3.4024 (3.1855)	grad_norm 1.8547 (1.9768)	
[2022-01-24 02:59:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][30/1251]	eta 0:58:39 lr 0.000248	time 2.0344 (2.8824)	loss 4.0566 (3.3056)	grad_norm 1.9063 (1.9874)	
[2022-01-24 02:59:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][40/1251]	eta 0:55:33 lr 0.000248	time 2.8413 (2.7527)	loss 3.2687 (3.3545)	grad_norm 1.9028 (1.9762)	
[2022-01-24 03:00:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][50/1251]	eta 0:53:47 lr 0.000248	time 2.0375 (2.6870)	loss 3.6930 (3.3893)	grad_norm 1.9837 (1.9721)	
[2022-01-24 03:00:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][60/1251]	eta 0:52:02 lr 0.000248	time 1.6028 (2.6215)	loss 3.9079 (3.4075)	grad_norm 1.8912 (1.9899)	
[2022-01-24 03:00:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][70/1251]	eta 0:50:22 lr 0.000248	time 2.3164 (2.5591)	loss 3.2627 (3.4247)	grad_norm 1.9460 (1.9798)	
[2022-01-24 03:01:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][80/1251]	eta 0:48:54 lr 0.000248	time 2.2431 (2.5057)	loss 3.6435 (3.4249)	grad_norm 2.1115 (1.9802)	
[2022-01-24 03:01:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][90/1251]	eta 0:47:28 lr 0.000248	time 1.9323 (2.4532)	loss 2.4842 (3.4221)	grad_norm 1.8630 (2.0143)	
[2022-01-24 03:01:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][100/1251]	eta 0:46:13 lr 0.000248	time 1.8511 (2.4096)	loss 3.8004 (3.4243)	grad_norm 1.8337 (2.0123)	
[2022-01-24 03:02:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][110/1251]	eta 0:45:18 lr 0.000248	time 2.1655 (2.3824)	loss 3.2944 (3.4137)	grad_norm 1.7820 (2.0044)	
[2022-01-24 03:02:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][120/1251]	eta 0:44:25 lr 0.000248	time 2.4218 (2.3571)	loss 3.5798 (3.3943)	grad_norm 1.8955 (2.0046)	
[2022-01-24 03:02:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][130/1251]	eta 0:44:00 lr 0.000248	time 2.9985 (2.3558)	loss 2.2373 (3.3838)	grad_norm 1.8849 (1.9958)	
[2022-01-24 03:03:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][140/1251]	eta 0:43:47 lr 0.000248	time 2.6093 (2.3649)	loss 3.0669 (3.3711)	grad_norm 2.1211 (1.9936)	
[2022-01-24 03:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][150/1251]	eta 0:43:27 lr 0.000248	time 2.0422 (2.3681)	loss 3.4932 (3.3416)	grad_norm 2.0339 (1.9920)	
[2022-01-24 03:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][160/1251]	eta 0:42:54 lr 0.000248	time 2.1991 (2.3600)	loss 3.1565 (3.3439)	grad_norm 1.8763 (1.9856)	
[2022-01-24 03:04:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][170/1251]	eta 0:42:17 lr 0.000248	time 2.5630 (2.3470)	loss 3.4241 (3.3344)	grad_norm 2.1058 (1.9823)	
[2022-01-24 03:04:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][180/1251]	eta 0:41:28 lr 0.000248	time 2.1778 (2.3233)	loss 3.9039 (3.3477)	grad_norm 2.2636 (1.9845)	
[2022-01-24 03:05:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][190/1251]	eta 0:40:51 lr 0.000248	time 2.2987 (2.3108)	loss 3.8445 (3.3605)	grad_norm 1.8338 (1.9867)	
[2022-01-24 03:05:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][200/1251]	eta 0:40:18 lr 0.000248	time 2.4810 (2.3007)	loss 3.6532 (3.3561)	grad_norm 1.7374 (1.9888)	
[2022-01-24 03:05:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][210/1251]	eta 0:39:46 lr 0.000248	time 2.1723 (2.2930)	loss 3.5594 (3.3590)	grad_norm 1.6999 (1.9946)	
[2022-01-24 03:06:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][220/1251]	eta 0:39:14 lr 0.000248	time 2.4483 (2.2834)	loss 2.5575 (3.3494)	grad_norm 2.1123 (1.9990)	
[2022-01-24 03:06:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][230/1251]	eta 0:38:42 lr 0.000248	time 2.2153 (2.2748)	loss 3.1358 (3.3412)	grad_norm 2.2151 (2.0064)	
[2022-01-24 03:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][240/1251]	eta 0:38:11 lr 0.000248	time 2.0085 (2.2669)	loss 3.4430 (3.3525)	grad_norm 1.8728 (2.0040)	
[2022-01-24 03:07:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][250/1251]	eta 0:37:47 lr 0.000248	time 2.3633 (2.2656)	loss 2.9986 (3.3458)	grad_norm 1.8999 (1.9998)	
[2022-01-24 03:07:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][260/1251]	eta 0:37:23 lr 0.000248	time 2.5392 (2.2636)	loss 3.5584 (3.3461)	grad_norm 1.8005 (1.9988)	
[2022-01-24 03:07:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][270/1251]	eta 0:36:57 lr 0.000248	time 2.4380 (2.2603)	loss 2.8823 (3.3411)	grad_norm 1.9860 (2.0035)	
[2022-01-24 03:08:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][280/1251]	eta 0:36:34 lr 0.000248	time 1.8907 (2.2602)	loss 3.5255 (3.3356)	grad_norm 1.6662 (2.0046)	
[2022-01-24 03:08:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][290/1251]	eta 0:36:23 lr 0.000248	time 3.1245 (2.2719)	loss 3.3051 (3.3341)	grad_norm 2.0191 (2.0094)	
[2022-01-24 03:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][300/1251]	eta 0:36:07 lr 0.000248	time 3.2584 (2.2790)	loss 3.5969 (3.3316)	grad_norm 1.7509 (2.0039)	
[2022-01-24 03:09:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][310/1251]	eta 0:35:46 lr 0.000247	time 2.8707 (2.2812)	loss 2.9015 (3.3246)	grad_norm 2.0279 (1.9970)	
[2022-01-24 03:09:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][320/1251]	eta 0:35:19 lr 0.000247	time 1.7669 (2.2768)	loss 3.6537 (3.3246)	grad_norm 2.0579 (1.9976)	
[2022-01-24 03:10:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][330/1251]	eta 0:34:53 lr 0.000247	time 1.8360 (2.2725)	loss 3.2075 (3.3232)	grad_norm 2.0485 (1.9962)	
[2022-01-24 03:10:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][340/1251]	eta 0:34:24 lr 0.000247	time 1.8493 (2.2658)	loss 2.3592 (3.3181)	grad_norm 1.8115 (1.9918)	
[2022-01-24 03:11:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][350/1251]	eta 0:33:59 lr 0.000247	time 2.3979 (2.2634)	loss 2.8674 (3.3148)	grad_norm 2.2285 (1.9902)	
[2022-01-24 03:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][360/1251]	eta 0:33:36 lr 0.000247	time 2.1515 (2.2637)	loss 3.4187 (3.3168)	grad_norm 2.0588 (1.9923)	
[2022-01-24 03:11:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][370/1251]	eta 0:33:10 lr 0.000247	time 1.8033 (2.2596)	loss 3.1131 (3.3132)	grad_norm 1.9869 (1.9905)	
[2022-01-24 03:12:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][380/1251]	eta 0:32:46 lr 0.000247	time 2.1845 (2.2575)	loss 3.6811 (3.3155)	grad_norm 2.2801 (1.9892)	
[2022-01-24 03:12:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][390/1251]	eta 0:32:21 lr 0.000247	time 1.9111 (2.2549)	loss 3.4354 (3.3112)	grad_norm 2.1508 (1.9909)	
[2022-01-24 03:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][400/1251]	eta 0:31:58 lr 0.000247	time 2.0835 (2.2539)	loss 3.8897 (3.3167)	grad_norm 1.9778 (1.9905)	
[2022-01-24 03:13:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][410/1251]	eta 0:31:31 lr 0.000247	time 2.2480 (2.2486)	loss 3.4692 (3.3162)	grad_norm 2.3809 (1.9918)	
[2022-01-24 03:13:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][420/1251]	eta 0:31:04 lr 0.000247	time 1.8741 (2.2434)	loss 2.9127 (3.3190)	grad_norm 1.9953 (1.9914)	
[2022-01-24 03:13:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][430/1251]	eta 0:30:36 lr 0.000247	time 1.9316 (2.2370)	loss 3.3505 (3.3203)	grad_norm 1.7296 (1.9926)	
[2022-01-24 03:14:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][440/1251]	eta 0:30:12 lr 0.000247	time 2.2829 (2.2355)	loss 3.5701 (3.3240)	grad_norm 2.1523 (1.9926)	
[2022-01-24 03:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][450/1251]	eta 0:29:48 lr 0.000247	time 2.7698 (2.2334)	loss 3.1935 (3.3281)	grad_norm 1.7908 (1.9901)	
[2022-01-24 03:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][460/1251]	eta 0:29:28 lr 0.000247	time 2.1507 (2.2359)	loss 3.7403 (3.3256)	grad_norm 2.0370 (1.9892)	
[2022-01-24 03:15:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][470/1251]	eta 0:29:12 lr 0.000247	time 2.9958 (2.2436)	loss 3.7167 (3.3247)	grad_norm 1.8971 (1.9866)	
[2022-01-24 03:15:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][480/1251]	eta 0:28:52 lr 0.000247	time 2.8040 (2.2467)	loss 4.2115 (3.3281)	grad_norm 2.1318 (1.9863)	
[2022-01-24 03:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][490/1251]	eta 0:28:29 lr 0.000247	time 2.1809 (2.2469)	loss 3.6131 (3.3307)	grad_norm 1.7496 (1.9875)	
[2022-01-24 03:16:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][500/1251]	eta 0:28:05 lr 0.000247	time 1.9012 (2.2442)	loss 3.6654 (3.3302)	grad_norm 1.8390 (1.9890)	
[2022-01-24 03:16:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][510/1251]	eta 0:27:38 lr 0.000247	time 2.2117 (2.2388)	loss 3.2717 (3.3319)	grad_norm 1.6836 (1.9886)	
[2022-01-24 03:17:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][520/1251]	eta 0:27:13 lr 0.000247	time 2.7191 (2.2344)	loss 2.7419 (3.3311)	grad_norm 2.0384 (1.9924)	
[2022-01-24 03:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][530/1251]	eta 0:26:48 lr 0.000247	time 2.1590 (2.2310)	loss 3.5219 (3.3276)	grad_norm 2.2340 (1.9931)	
[2022-01-24 03:17:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][540/1251]	eta 0:26:24 lr 0.000247	time 1.9655 (2.2292)	loss 3.6742 (3.3273)	grad_norm 1.8284 (1.9922)	
[2022-01-24 03:18:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][550/1251]	eta 0:26:02 lr 0.000247	time 1.6674 (2.2283)	loss 3.7329 (3.3325)	grad_norm 2.0189 (1.9922)	
[2022-01-24 03:18:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][560/1251]	eta 0:25:40 lr 0.000247	time 2.8835 (2.2294)	loss 3.4341 (3.3304)	grad_norm 2.0188 (1.9930)	
[2022-01-24 03:18:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][570/1251]	eta 0:25:19 lr 0.000247	time 3.1283 (2.2314)	loss 3.5952 (3.3309)	grad_norm 2.0383 (1.9912)	
[2022-01-24 03:19:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][580/1251]	eta 0:24:57 lr 0.000247	time 2.0340 (2.2311)	loss 3.2528 (3.3333)	grad_norm 1.7989 (1.9903)	
[2022-01-24 03:19:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][590/1251]	eta 0:24:34 lr 0.000246	time 1.6491 (2.2307)	loss 3.7813 (3.3364)	grad_norm 1.7791 (1.9889)	
[2022-01-24 03:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][600/1251]	eta 0:24:13 lr 0.000246	time 3.3755 (2.2321)	loss 3.9449 (3.3389)	grad_norm 2.1187 (1.9889)	
[2022-01-24 03:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][610/1251]	eta 0:23:50 lr 0.000246	time 2.0546 (2.2314)	loss 3.3947 (3.3390)	grad_norm 1.8127 (1.9891)	
[2022-01-24 03:20:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][620/1251]	eta 0:23:26 lr 0.000246	time 1.9234 (2.2284)	loss 3.8375 (3.3401)	grad_norm 2.0064 (1.9885)	
[2022-01-24 03:21:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][630/1251]	eta 0:23:03 lr 0.000246	time 2.2556 (2.2273)	loss 2.5809 (3.3361)	grad_norm 2.0895 (1.9897)	
[2022-01-24 03:21:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][640/1251]	eta 0:22:40 lr 0.000246	time 2.2502 (2.2274)	loss 3.7180 (3.3393)	grad_norm 1.7543 (1.9903)	
[2022-01-24 03:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][650/1251]	eta 0:22:17 lr 0.000246	time 2.4434 (2.2259)	loss 2.2448 (3.3318)	grad_norm 1.7993 (1.9889)	
[2022-01-24 03:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][660/1251]	eta 0:21:55 lr 0.000246	time 1.5767 (2.2253)	loss 3.8456 (3.3294)	grad_norm 1.9257 (1.9881)	
[2022-01-24 03:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][670/1251]	eta 0:21:33 lr 0.000246	time 1.8301 (2.2261)	loss 3.4342 (3.3348)	grad_norm 1.6058 (1.9876)	
[2022-01-24 03:23:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][680/1251]	eta 0:21:11 lr 0.000246	time 2.4083 (2.2265)	loss 2.3783 (3.3342)	grad_norm 1.7402 (1.9889)	
[2022-01-24 03:23:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][690/1251]	eta 0:20:49 lr 0.000246	time 3.7183 (2.2280)	loss 3.3363 (3.3374)	grad_norm 1.6298 (1.9869)	
[2022-01-24 03:23:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][700/1251]	eta 0:20:26 lr 0.000246	time 1.9781 (2.2256)	loss 3.6996 (3.3361)	grad_norm 2.3877 (1.9859)	
[2022-01-24 03:24:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][710/1251]	eta 0:20:01 lr 0.000246	time 1.8854 (2.2218)	loss 2.3650 (3.3334)	grad_norm 1.5838 (1.9858)	
[2022-01-24 03:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][720/1251]	eta 0:19:38 lr 0.000246	time 1.9382 (2.2199)	loss 3.2063 (3.3296)	grad_norm 1.8144 (1.9855)	
[2022-01-24 03:24:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][730/1251]	eta 0:19:16 lr 0.000246	time 3.0117 (2.2202)	loss 3.4017 (3.3297)	grad_norm 1.8722 (1.9841)	
[2022-01-24 03:25:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][740/1251]	eta 0:18:54 lr 0.000246	time 2.2753 (2.2202)	loss 2.8932 (3.3273)	grad_norm 2.0743 (1.9854)	
[2022-01-24 03:25:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][750/1251]	eta 0:18:33 lr 0.000246	time 2.1087 (2.2221)	loss 3.8701 (3.3303)	grad_norm 2.2930 (1.9868)	
[2022-01-24 03:25:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][760/1251]	eta 0:18:11 lr 0.000246	time 2.3172 (2.2226)	loss 2.9453 (3.3298)	grad_norm 1.9078 (1.9860)	
[2022-01-24 03:26:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][770/1251]	eta 0:17:47 lr 0.000246	time 1.7408 (2.2200)	loss 3.0515 (3.3275)	grad_norm 1.8064 (1.9865)	
[2022-01-24 03:26:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][780/1251]	eta 0:17:23 lr 0.000246	time 1.8700 (2.2164)	loss 2.9948 (3.3267)	grad_norm 1.8148 (1.9879)	
[2022-01-24 03:26:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][790/1251]	eta 0:17:00 lr 0.000246	time 2.0548 (2.2141)	loss 2.3783 (3.3269)	grad_norm 1.7908 (1.9871)	
[2022-01-24 03:27:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][800/1251]	eta 0:16:38 lr 0.000246	time 2.2484 (2.2137)	loss 3.9758 (3.3278)	grad_norm 2.1057 (1.9872)	
[2022-01-24 03:27:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][810/1251]	eta 0:16:15 lr 0.000246	time 1.5194 (2.2131)	loss 3.5816 (3.3286)	grad_norm 1.7638 (1.9875)	
[2022-01-24 03:28:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][820/1251]	eta 0:15:54 lr 0.000246	time 2.7623 (2.2150)	loss 3.9723 (3.3294)	grad_norm 2.7210 (1.9919)	
[2022-01-24 03:28:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][830/1251]	eta 0:15:32 lr 0.000246	time 1.7985 (2.2145)	loss 2.9899 (3.3271)	grad_norm 2.0549 (1.9916)	
[2022-01-24 03:28:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][840/1251]	eta 0:15:10 lr 0.000246	time 2.6228 (2.2162)	loss 3.1036 (3.3263)	grad_norm 1.8903 (1.9923)	
[2022-01-24 03:29:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][850/1251]	eta 0:14:49 lr 0.000246	time 1.5029 (2.2175)	loss 3.3540 (3.3250)	grad_norm 1.7756 (1.9920)	
[2022-01-24 03:29:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][860/1251]	eta 0:14:26 lr 0.000246	time 1.6279 (2.2165)	loss 3.6887 (3.3227)	grad_norm 1.8400 (1.9919)	
[2022-01-24 03:29:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][870/1251]	eta 0:14:04 lr 0.000245	time 1.5863 (2.2156)	loss 3.4286 (3.3214)	grad_norm 1.8305 (1.9900)	
[2022-01-24 03:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][880/1251]	eta 0:13:41 lr 0.000245	time 2.1735 (2.2146)	loss 3.8029 (3.3200)	grad_norm 2.0434 (1.9917)	
[2022-01-24 03:30:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][890/1251]	eta 0:13:19 lr 0.000245	time 2.2564 (2.2155)	loss 3.6774 (3.3184)	grad_norm 1.8750 (1.9908)	
[2022-01-24 03:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][900/1251]	eta 0:12:57 lr 0.000245	time 1.8643 (2.2146)	loss 3.0314 (3.3174)	grad_norm 1.8992 (1.9919)	
[2022-01-24 03:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][910/1251]	eta 0:12:34 lr 0.000245	time 1.7480 (2.2135)	loss 2.8832 (3.3150)	grad_norm 1.7459 (1.9919)	
[2022-01-24 03:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][920/1251]	eta 0:12:12 lr 0.000245	time 2.2567 (2.2131)	loss 3.6408 (3.3151)	grad_norm 2.1422 (1.9918)	
[2022-01-24 03:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][930/1251]	eta 0:11:49 lr 0.000245	time 2.1493 (2.2115)	loss 2.9023 (3.3126)	grad_norm 1.9331 (1.9919)	
[2022-01-24 03:32:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][940/1251]	eta 0:11:27 lr 0.000245	time 1.8324 (2.2101)	loss 3.2535 (3.3135)	grad_norm 1.9577 (1.9912)	
[2022-01-24 03:32:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][950/1251]	eta 0:11:05 lr 0.000245	time 2.1448 (2.2107)	loss 3.5071 (3.3140)	grad_norm 2.0501 (1.9912)	
[2022-01-24 03:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][960/1251]	eta 0:10:43 lr 0.000245	time 2.3198 (2.2115)	loss 4.0189 (3.3147)	grad_norm 1.9435 (1.9915)	
[2022-01-24 03:33:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][970/1251]	eta 0:10:21 lr 0.000245	time 1.9113 (2.2117)	loss 2.7252 (3.3146)	grad_norm 1.8525 (1.9918)	
[2022-01-24 03:33:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][980/1251]	eta 0:09:59 lr 0.000245	time 1.6095 (2.2130)	loss 3.4419 (3.3140)	grad_norm 1.8120 (1.9910)	
[2022-01-24 03:34:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][990/1251]	eta 0:09:37 lr 0.000245	time 1.8482 (2.2139)	loss 3.3729 (3.3138)	grad_norm 2.1357 (1.9907)	
[2022-01-24 03:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1000/1251]	eta 0:09:15 lr 0.000245	time 1.5706 (2.2125)	loss 3.5960 (3.3132)	grad_norm 1.8619 (1.9897)	
[2022-01-24 03:35:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1010/1251]	eta 0:08:53 lr 0.000245	time 1.8240 (2.2128)	loss 2.8644 (3.3160)	grad_norm 1.9261 (1.9897)	
[2022-01-24 03:35:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1020/1251]	eta 0:08:30 lr 0.000245	time 2.1478 (2.2118)	loss 1.9287 (3.3131)	grad_norm 1.8492 (1.9895)	
[2022-01-24 03:35:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1030/1251]	eta 0:08:08 lr 0.000245	time 1.9908 (2.2114)	loss 3.5553 (3.3141)	grad_norm 2.1146 (1.9893)	
[2022-01-24 03:36:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1040/1251]	eta 0:07:46 lr 0.000245	time 1.9174 (2.2102)	loss 2.4231 (3.3112)	grad_norm 2.3228 (1.9910)	
[2022-01-24 03:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1050/1251]	eta 0:07:24 lr 0.000245	time 2.0388 (2.2109)	loss 3.6478 (3.3124)	grad_norm 1.8416 (1.9908)	
[2022-01-24 03:36:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1060/1251]	eta 0:07:02 lr 0.000245	time 2.0467 (2.2097)	loss 3.6511 (3.3126)	grad_norm 2.3312 (1.9913)	
[2022-01-24 03:37:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1070/1251]	eta 0:06:39 lr 0.000245	time 2.2221 (2.2096)	loss 3.0358 (3.3127)	grad_norm 2.0891 (1.9920)	
[2022-01-24 03:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1080/1251]	eta 0:06:17 lr 0.000245	time 1.8083 (2.2101)	loss 3.3055 (3.3145)	grad_norm 1.9515 (1.9913)	
[2022-01-24 03:37:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1090/1251]	eta 0:05:55 lr 0.000245	time 2.2382 (2.2100)	loss 3.7270 (3.3166)	grad_norm 2.0695 (1.9916)	
[2022-01-24 03:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1100/1251]	eta 0:05:33 lr 0.000245	time 2.2917 (2.2098)	loss 3.3022 (3.3152)	grad_norm 1.9920 (1.9927)	
[2022-01-24 03:38:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1110/1251]	eta 0:05:11 lr 0.000245	time 2.4026 (2.2084)	loss 3.8371 (3.3126)	grad_norm 2.1816 (1.9929)	
[2022-01-24 03:38:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1120/1251]	eta 0:04:49 lr 0.000245	time 2.3182 (2.2070)	loss 3.7550 (3.3131)	grad_norm 1.9212 (1.9930)	
[2022-01-24 03:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1130/1251]	eta 0:04:26 lr 0.000245	time 2.2512 (2.2063)	loss 3.5590 (3.3144)	grad_norm 2.0410 (1.9916)	
[2022-01-24 03:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1140/1251]	eta 0:04:04 lr 0.000245	time 1.9246 (2.2051)	loss 4.0780 (3.3130)	grad_norm 1.7384 (1.9901)	
[2022-01-24 03:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1150/1251]	eta 0:03:42 lr 0.000245	time 3.3547 (2.2066)	loss 2.3861 (3.3133)	grad_norm 1.9188 (1.9906)	
[2022-01-24 03:40:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1160/1251]	eta 0:03:20 lr 0.000244	time 1.9006 (2.2081)	loss 2.2987 (3.3136)	grad_norm 1.8188 (1.9916)	
[2022-01-24 03:40:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1170/1251]	eta 0:02:58 lr 0.000244	time 2.6316 (2.2088)	loss 3.7762 (3.3150)	grad_norm 2.0050 (1.9909)	
[2022-01-24 03:41:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1180/1251]	eta 0:02:36 lr 0.000244	time 1.7315 (2.2080)	loss 3.2411 (3.3164)	grad_norm 1.8340 (1.9905)	
[2022-01-24 03:41:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1190/1251]	eta 0:02:14 lr 0.000244	time 2.5719 (2.2081)	loss 3.6248 (3.3157)	grad_norm 1.7962 (1.9898)	
[2022-01-24 03:41:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1200/1251]	eta 0:01:52 lr 0.000244	time 1.6304 (2.2068)	loss 3.4094 (3.3150)	grad_norm 2.2142 (1.9896)	
[2022-01-24 03:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1210/1251]	eta 0:01:30 lr 0.000244	time 2.2852 (2.2063)	loss 3.5900 (3.3144)	grad_norm 1.8319 (1.9897)	
[2022-01-24 03:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1220/1251]	eta 0:01:08 lr 0.000244	time 1.7632 (2.2057)	loss 3.8597 (3.3154)	grad_norm 1.8507 (1.9892)	
[2022-01-24 03:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1230/1251]	eta 0:00:46 lr 0.000244	time 2.7570 (2.2059)	loss 3.8484 (3.3184)	grad_norm 1.9245 (1.9888)	
[2022-01-24 03:43:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1240/1251]	eta 0:00:24 lr 0.000244	time 1.4343 (2.2052)	loss 2.5338 (3.3169)	grad_norm 1.8294 (1.9885)	
[2022-01-24 03:43:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [202/300][1250/1251]	eta 0:00:02 lr 0.000244	time 1.1611 (2.1998)	loss 3.4526 (3.3151)	grad_norm 1.7524 (1.9873)	
[2022-01-24 03:43:38 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 202 training takes 0:45:52
[2022-01-24 03:43:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.799 (18.799)	Loss 0.8968 (0.8968)	Acc@1 78.711 (78.711)	Acc@5 94.531 (94.531)	
[2022-01-24 03:44:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.943 (3.389)	Loss 0.8112 (0.9340)	Acc@1 80.078 (78.178)	Acc@5 95.801 (94.309)	
[2022-01-24 03:44:32 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.268 (2.589)	Loss 0.8592 (0.9180)	Acc@1 79.395 (78.339)	Acc@5 94.531 (94.294)	
[2022-01-24 03:44:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.620 (2.264)	Loss 0.8658 (0.9141)	Acc@1 80.078 (78.380)	Acc@5 94.727 (94.358)	
[2022-01-24 03:45:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.787 (2.177)	Loss 0.9064 (0.9095)	Acc@1 78.711 (78.442)	Acc@5 93.848 (94.424)	
[2022-01-24 03:45:14 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.466 Acc@5 94.446
[2022-01-24 03:45:14 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.5%
[2022-01-24 03:45:14 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.47%
[2022-01-24 03:45:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][0/1251]	eta 7:24:20 lr 0.000244	time 21.3116 (21.3116)	loss 2.8047 (2.8047)	grad_norm 1.8881 (1.8881)	
[2022-01-24 03:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][10/1251]	eta 1:21:34 lr 0.000244	time 1.8370 (3.9436)	loss 3.4103 (3.3696)	grad_norm 1.9110 (1.9181)	
[2022-01-24 03:46:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][20/1251]	eta 1:03:45 lr 0.000244	time 1.4167 (3.1075)	loss 3.3636 (3.4094)	grad_norm 1.9330 (1.9350)	
[2022-01-24 03:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][30/1251]	eta 0:57:23 lr 0.000244	time 2.2202 (2.8206)	loss 2.8135 (3.4208)	grad_norm 2.1761 (1.9479)	
[2022-01-24 03:47:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][40/1251]	eta 0:54:23 lr 0.000244	time 3.8325 (2.6952)	loss 3.6493 (3.3939)	grad_norm 1.9549 (1.9456)	
[2022-01-24 03:47:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][50/1251]	eta 0:52:10 lr 0.000244	time 1.9360 (2.6062)	loss 3.5785 (3.3403)	grad_norm 2.4237 (1.9570)	
[2022-01-24 03:47:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][60/1251]	eta 0:50:01 lr 0.000244	time 1.7396 (2.5200)	loss 3.6655 (3.3555)	grad_norm 1.7788 (1.9593)	
[2022-01-24 03:48:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][70/1251]	eta 0:49:06 lr 0.000244	time 2.2601 (2.4952)	loss 3.1800 (3.3262)	grad_norm 2.0605 (1.9796)	
[2022-01-24 03:48:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][80/1251]	eta 0:48:10 lr 0.000244	time 3.5688 (2.4687)	loss 3.7576 (3.3400)	grad_norm 2.3004 (1.9864)	
[2022-01-24 03:48:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][90/1251]	eta 0:47:10 lr 0.000244	time 1.8932 (2.4380)	loss 3.7567 (3.3287)	grad_norm 1.7735 (1.9757)	
[2022-01-24 03:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][100/1251]	eta 0:46:09 lr 0.000244	time 1.6405 (2.4058)	loss 3.6439 (3.3324)	grad_norm 2.0430 (1.9729)	
[2022-01-24 03:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][110/1251]	eta 0:45:29 lr 0.000244	time 1.8739 (2.3924)	loss 2.8219 (3.3442)	grad_norm 1.8104 (1.9783)	
[2022-01-24 03:50:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][120/1251]	eta 0:44:57 lr 0.000244	time 3.5245 (2.3852)	loss 3.7959 (3.3401)	grad_norm 2.1653 (1.9809)	
[2022-01-24 03:50:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][130/1251]	eta 0:44:13 lr 0.000244	time 1.6067 (2.3670)	loss 3.8046 (3.3362)	grad_norm 2.1709 (1.9790)	
[2022-01-24 03:50:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][140/1251]	eta 0:43:26 lr 0.000244	time 1.9943 (2.3458)	loss 3.8902 (3.3429)	grad_norm 2.0290 (1.9785)	
[2022-01-24 03:51:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][150/1251]	eta 0:42:50 lr 0.000244	time 1.7960 (2.3351)	loss 3.8967 (3.3508)	grad_norm 1.8395 (1.9752)	
[2022-01-24 03:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][160/1251]	eta 0:42:10 lr 0.000244	time 2.8892 (2.3196)	loss 3.4102 (3.3521)	grad_norm 1.6587 (1.9788)	
[2022-01-24 03:51:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][170/1251]	eta 0:41:41 lr 0.000244	time 2.5160 (2.3145)	loss 3.7296 (3.3625)	grad_norm 2.1563 (1.9736)	
[2022-01-24 03:52:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][180/1251]	eta 0:41:11 lr 0.000244	time 2.2380 (2.3073)	loss 3.3183 (3.3572)	grad_norm 2.1080 (1.9740)	
[2022-01-24 03:52:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][190/1251]	eta 0:40:37 lr 0.000243	time 1.9229 (2.2969)	loss 3.5022 (3.3720)	grad_norm 1.9359 (1.9698)	
[2022-01-24 03:52:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][200/1251]	eta 0:40:09 lr 0.000243	time 2.5684 (2.2928)	loss 4.2461 (3.3739)	grad_norm 2.0285 (1.9697)	
[2022-01-24 03:53:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][210/1251]	eta 0:39:33 lr 0.000243	time 2.6537 (2.2801)	loss 2.9654 (3.3706)	grad_norm 2.0681 (1.9740)	
[2022-01-24 03:53:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][220/1251]	eta 0:39:03 lr 0.000243	time 2.0136 (2.2733)	loss 3.0147 (3.3837)	grad_norm 1.8392 (1.9688)	
[2022-01-24 03:53:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][230/1251]	eta 0:38:36 lr 0.000243	time 2.2716 (2.2687)	loss 2.5418 (3.3750)	grad_norm 2.6751 (1.9733)	
[2022-01-24 03:54:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][240/1251]	eta 0:38:08 lr 0.000243	time 2.5231 (2.2636)	loss 3.0843 (3.3797)	grad_norm 2.3116 (1.9767)	
[2022-01-24 03:54:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][250/1251]	eta 0:37:41 lr 0.000243	time 1.6110 (2.2596)	loss 2.2113 (3.3616)	grad_norm 1.8340 (1.9720)	
[2022-01-24 03:55:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][260/1251]	eta 0:37:24 lr 0.000243	time 3.0283 (2.2644)	loss 3.2576 (3.3582)	grad_norm 1.7602 (1.9737)	
[2022-01-24 03:55:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][270/1251]	eta 0:36:56 lr 0.000243	time 2.2868 (2.2590)	loss 3.5631 (3.3471)	grad_norm 1.9035 (1.9725)	
[2022-01-24 03:55:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][280/1251]	eta 0:36:26 lr 0.000243	time 1.8468 (2.2522)	loss 3.7553 (3.3437)	grad_norm 2.1861 (1.9725)	
[2022-01-24 03:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][290/1251]	eta 0:35:57 lr 0.000243	time 1.9230 (2.2446)	loss 3.3630 (3.3509)	grad_norm 1.9051 (1.9738)	
[2022-01-24 03:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][300/1251]	eta 0:35:34 lr 0.000243	time 2.0167 (2.2440)	loss 3.3608 (3.3364)	grad_norm 1.8122 (1.9748)	
[2022-01-24 03:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][310/1251]	eta 0:35:08 lr 0.000243	time 2.4526 (2.2406)	loss 3.1306 (3.3274)	grad_norm 1.9831 (1.9705)	
[2022-01-24 03:57:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][320/1251]	eta 0:34:49 lr 0.000243	time 2.1298 (2.2443)	loss 3.3130 (3.3263)	grad_norm 1.9285 (1.9712)	
[2022-01-24 03:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][330/1251]	eta 0:34:25 lr 0.000243	time 1.6988 (2.2428)	loss 3.4367 (3.3261)	grad_norm 1.8532 (1.9681)	
[2022-01-24 03:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][340/1251]	eta 0:34:04 lr 0.000243	time 2.1348 (2.2447)	loss 2.8922 (3.3262)	grad_norm 1.8894 (1.9677)	
[2022-01-24 03:58:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][350/1251]	eta 0:33:39 lr 0.000243	time 2.1910 (2.2413)	loss 3.2562 (3.3184)	grad_norm 1.9227 (1.9687)	
[2022-01-24 03:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][360/1251]	eta 0:33:13 lr 0.000243	time 2.1241 (2.2378)	loss 2.4171 (3.3149)	grad_norm 2.0757 (1.9713)	
[2022-01-24 03:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][370/1251]	eta 0:32:45 lr 0.000243	time 1.5210 (2.2308)	loss 3.5663 (3.3166)	grad_norm 2.1151 (1.9714)	
[2022-01-24 03:59:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][380/1251]	eta 0:32:19 lr 0.000243	time 1.8392 (2.2264)	loss 3.5166 (3.3140)	grad_norm 1.8092 (1.9711)	
[2022-01-24 03:59:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][390/1251]	eta 0:31:55 lr 0.000243	time 2.1915 (2.2250)	loss 3.0834 (3.3157)	grad_norm 1.7733 (1.9705)	
[2022-01-24 04:00:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][400/1251]	eta 0:31:36 lr 0.000243	time 2.8131 (2.2284)	loss 3.0998 (3.3173)	grad_norm 1.7096 (1.9715)	
[2022-01-24 04:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][410/1251]	eta 0:31:12 lr 0.000243	time 1.6380 (2.2271)	loss 3.2303 (3.3145)	grad_norm 2.3727 (1.9752)	
[2022-01-24 04:00:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][420/1251]	eta 0:30:53 lr 0.000243	time 1.7109 (2.2309)	loss 3.5802 (3.3213)	grad_norm 2.0518 (1.9767)	
[2022-01-24 04:01:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][430/1251]	eta 0:30:29 lr 0.000243	time 1.9535 (2.2288)	loss 3.8622 (3.3205)	grad_norm 1.7517 (1.9758)	
[2022-01-24 04:01:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][440/1251]	eta 0:30:07 lr 0.000243	time 2.7626 (2.2282)	loss 3.6935 (3.3233)	grad_norm 1.7599 (1.9747)	
[2022-01-24 04:01:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][450/1251]	eta 0:29:43 lr 0.000243	time 2.2404 (2.2269)	loss 3.8962 (3.3209)	grad_norm 1.9853 (1.9744)	
[2022-01-24 04:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][460/1251]	eta 0:29:21 lr 0.000243	time 1.5985 (2.2267)	loss 2.3244 (3.3202)	grad_norm 2.0617 (1.9735)	
[2022-01-24 04:02:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][470/1251]	eta 0:28:58 lr 0.000243	time 2.4999 (2.2256)	loss 3.3982 (3.3201)	grad_norm 2.7387 (1.9800)	
[2022-01-24 04:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][480/1251]	eta 0:28:33 lr 0.000242	time 1.8639 (2.2220)	loss 3.9224 (3.3229)	grad_norm 1.7353 (1.9785)	
[2022-01-24 04:03:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][490/1251]	eta 0:28:07 lr 0.000242	time 1.6035 (2.2177)	loss 2.6622 (3.3177)	grad_norm 1.9944 (1.9773)	
[2022-01-24 04:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][500/1251]	eta 0:27:47 lr 0.000242	time 1.8871 (2.2198)	loss 1.9228 (3.3098)	grad_norm 1.8954 (1.9796)	
[2022-01-24 04:04:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][510/1251]	eta 0:27:26 lr 0.000242	time 3.0594 (2.2221)	loss 3.6320 (3.3104)	grad_norm 1.8462 (1.9805)	
[2022-01-24 04:04:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][520/1251]	eta 0:27:04 lr 0.000242	time 1.5221 (2.2227)	loss 3.7271 (3.3106)	grad_norm 1.9086 (1.9800)	
[2022-01-24 04:04:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][530/1251]	eta 0:26:40 lr 0.000242	time 1.4841 (2.2201)	loss 2.8341 (3.3135)	grad_norm 1.8541 (1.9808)	
[2022-01-24 04:05:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][540/1251]	eta 0:26:15 lr 0.000242	time 1.8420 (2.2163)	loss 3.4514 (3.3117)	grad_norm 1.9482 (1.9808)	
[2022-01-24 04:05:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][550/1251]	eta 0:25:50 lr 0.000242	time 1.9096 (2.2124)	loss 3.4665 (3.3110)	grad_norm 2.0031 (1.9795)	
[2022-01-24 04:05:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][560/1251]	eta 0:25:28 lr 0.000242	time 2.3421 (2.2114)	loss 3.9936 (3.3107)	grad_norm 1.9137 (1.9788)	
[2022-01-24 04:06:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][570/1251]	eta 0:25:07 lr 0.000242	time 1.4793 (2.2130)	loss 3.7954 (3.3158)	grad_norm 2.1411 (1.9781)	
[2022-01-24 04:06:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][580/1251]	eta 0:24:45 lr 0.000242	time 2.4535 (2.2134)	loss 2.9645 (3.3151)	grad_norm 2.4806 (1.9788)	
[2022-01-24 04:07:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][590/1251]	eta 0:24:22 lr 0.000242	time 1.9517 (2.2132)	loss 3.6786 (3.3187)	grad_norm 2.1060 (1.9849)	
[2022-01-24 04:07:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][600/1251]	eta 0:24:01 lr 0.000242	time 2.9557 (2.2144)	loss 4.0408 (3.3213)	grad_norm 1.9153 (1.9864)	
[2022-01-24 04:07:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][610/1251]	eta 0:23:39 lr 0.000242	time 1.8771 (2.2152)	loss 3.5650 (3.3235)	grad_norm 2.0905 (1.9865)	
[2022-01-24 04:08:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][620/1251]	eta 0:23:17 lr 0.000242	time 1.6379 (2.2150)	loss 2.3332 (3.3212)	grad_norm 1.9738 (1.9881)	
[2022-01-24 04:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][630/1251]	eta 0:22:54 lr 0.000242	time 1.9862 (2.2129)	loss 2.3133 (3.3213)	grad_norm 2.1885 (1.9885)	
[2022-01-24 04:08:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][640/1251]	eta 0:22:30 lr 0.000242	time 2.2380 (2.2109)	loss 3.6150 (3.3215)	grad_norm 1.7054 (1.9872)	
[2022-01-24 04:09:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][650/1251]	eta 0:22:08 lr 0.000242	time 2.1258 (2.2097)	loss 3.7106 (3.3231)	grad_norm 2.0371 (1.9860)	
[2022-01-24 04:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][660/1251]	eta 0:21:44 lr 0.000242	time 2.0455 (2.2080)	loss 3.0089 (3.3222)	grad_norm 1.7449 (1.9850)	
[2022-01-24 04:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][670/1251]	eta 0:21:22 lr 0.000242	time 2.1336 (2.2073)	loss 3.8669 (3.3208)	grad_norm 2.2785 (1.9858)	
[2022-01-24 04:10:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][680/1251]	eta 0:21:00 lr 0.000242	time 2.1842 (2.2080)	loss 2.5153 (3.3205)	grad_norm 1.8914 (1.9850)	
[2022-01-24 04:10:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][690/1251]	eta 0:20:38 lr 0.000242	time 2.4449 (2.2085)	loss 3.5671 (3.3206)	grad_norm 2.0233 (1.9847)	
[2022-01-24 04:11:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][700/1251]	eta 0:20:17 lr 0.000242	time 2.2556 (2.2091)	loss 3.0408 (3.3233)	grad_norm 2.0611 (1.9842)	
[2022-01-24 04:11:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][710/1251]	eta 0:19:57 lr 0.000242	time 3.3709 (2.2132)	loss 3.1066 (3.3263)	grad_norm 2.1021 (1.9839)	
[2022-01-24 04:11:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][720/1251]	eta 0:19:35 lr 0.000242	time 3.1976 (2.2133)	loss 3.4851 (3.3262)	grad_norm 1.8182 (1.9832)	
[2022-01-24 04:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][730/1251]	eta 0:19:11 lr 0.000242	time 1.7480 (2.2092)	loss 3.4906 (3.3273)	grad_norm 1.9500 (1.9837)	
[2022-01-24 04:12:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][740/1251]	eta 0:18:46 lr 0.000242	time 1.9872 (2.2049)	loss 3.5969 (3.3296)	grad_norm 1.8386 (1.9834)	
[2022-01-24 04:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][750/1251]	eta 0:18:23 lr 0.000242	time 2.1352 (2.2019)	loss 2.6945 (3.3291)	grad_norm 1.9600 (1.9837)	
[2022-01-24 04:13:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][760/1251]	eta 0:17:59 lr 0.000241	time 1.9049 (2.1992)	loss 4.0396 (3.3299)	grad_norm 2.1289 (1.9840)	
[2022-01-24 04:13:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][770/1251]	eta 0:17:37 lr 0.000241	time 2.7546 (2.1993)	loss 2.8713 (3.3323)	grad_norm 1.9380 (1.9830)	
[2022-01-24 04:13:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][780/1251]	eta 0:17:15 lr 0.000241	time 1.5320 (2.1986)	loss 4.0975 (3.3333)	grad_norm 2.0017 (1.9833)	
[2022-01-24 04:14:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][790/1251]	eta 0:16:53 lr 0.000241	time 1.8122 (2.1986)	loss 3.7423 (3.3343)	grad_norm 2.0468 (1.9847)	
[2022-01-24 04:14:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][800/1251]	eta 0:16:32 lr 0.000241	time 2.1724 (2.1998)	loss 3.1034 (3.3363)	grad_norm 1.7501 (1.9841)	
[2022-01-24 04:14:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][810/1251]	eta 0:16:10 lr 0.000241	time 2.3717 (2.1998)	loss 3.3324 (3.3352)	grad_norm 2.0206 (1.9837)	
[2022-01-24 04:15:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][820/1251]	eta 0:15:47 lr 0.000241	time 1.9016 (2.1984)	loss 3.7261 (3.3312)	grad_norm 2.5251 (1.9837)	
[2022-01-24 04:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][830/1251]	eta 0:15:25 lr 0.000241	time 2.0009 (2.1986)	loss 2.6492 (3.3302)	grad_norm 1.9929 (1.9837)	
[2022-01-24 04:16:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][840/1251]	eta 0:15:04 lr 0.000241	time 2.6951 (2.2012)	loss 3.6747 (3.3302)	grad_norm 1.7792 (1.9835)	
[2022-01-24 04:16:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][850/1251]	eta 0:14:43 lr 0.000241	time 2.9291 (2.2037)	loss 3.1469 (3.3281)	grad_norm 1.9607 (1.9831)	
[2022-01-24 04:16:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][860/1251]	eta 0:14:21 lr 0.000241	time 1.7859 (2.2041)	loss 3.2344 (3.3289)	grad_norm 1.9620 (1.9825)	
[2022-01-24 04:17:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][870/1251]	eta 0:14:00 lr 0.000241	time 1.8682 (2.2051)	loss 3.0259 (3.3297)	grad_norm 1.8591 (1.9820)	
[2022-01-24 04:17:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][880/1251]	eta 0:13:38 lr 0.000241	time 1.6198 (2.2054)	loss 3.9050 (3.3310)	grad_norm 2.1537 (1.9837)	
[2022-01-24 04:17:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][890/1251]	eta 0:13:15 lr 0.000241	time 1.8282 (2.2029)	loss 3.8951 (3.3337)	grad_norm 2.0145 (1.9844)	
[2022-01-24 04:18:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][900/1251]	eta 0:12:52 lr 0.000241	time 2.3003 (2.2003)	loss 2.9770 (3.3343)	grad_norm 1.7242 (1.9845)	
[2022-01-24 04:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][910/1251]	eta 0:12:29 lr 0.000241	time 2.3372 (2.1991)	loss 3.7887 (3.3356)	grad_norm 2.1280 (1.9850)	
[2022-01-24 04:18:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][920/1251]	eta 0:12:07 lr 0.000241	time 2.5131 (2.1986)	loss 3.3536 (3.3383)	grad_norm 2.0211 (1.9874)	
[2022-01-24 04:19:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][930/1251]	eta 0:11:45 lr 0.000241	time 2.3793 (2.1986)	loss 3.4311 (3.3391)	grad_norm 2.3737 (1.9887)	
[2022-01-24 04:19:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][940/1251]	eta 0:11:24 lr 0.000241	time 2.6753 (2.2000)	loss 3.3605 (3.3402)	grad_norm 1.7345 (1.9888)	
[2022-01-24 04:20:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][950/1251]	eta 0:11:02 lr 0.000241	time 2.1141 (2.2000)	loss 2.6336 (3.3382)	grad_norm 2.3771 (1.9888)	
[2022-01-24 04:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][960/1251]	eta 0:10:39 lr 0.000241	time 2.3257 (2.1989)	loss 3.2666 (3.3381)	grad_norm 1.9335 (1.9894)	
[2022-01-24 04:20:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][970/1251]	eta 0:10:18 lr 0.000241	time 2.5054 (2.1995)	loss 3.7091 (3.3406)	grad_norm 2.5818 (1.9912)	
[2022-01-24 04:21:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][980/1251]	eta 0:09:56 lr 0.000241	time 2.7583 (2.2012)	loss 2.8516 (3.3389)	grad_norm 1.8391 (1.9917)	
[2022-01-24 04:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][990/1251]	eta 0:09:34 lr 0.000241	time 2.1192 (2.2010)	loss 3.8178 (3.3413)	grad_norm 1.9992 (1.9925)	
[2022-01-24 04:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1000/1251]	eta 0:09:12 lr 0.000241	time 1.8944 (2.2001)	loss 2.5992 (3.3400)	grad_norm 1.7276 (1.9921)	
[2022-01-24 04:22:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1010/1251]	eta 0:08:49 lr 0.000241	time 1.8826 (2.1989)	loss 3.5073 (3.3402)	grad_norm 1.8141 (1.9915)	
[2022-01-24 04:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1020/1251]	eta 0:08:27 lr 0.000241	time 2.4395 (2.1988)	loss 3.3408 (3.3390)	grad_norm 1.9910 (1.9919)	
[2022-01-24 04:23:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1030/1251]	eta 0:08:06 lr 0.000241	time 2.9301 (2.1996)	loss 3.6512 (3.3371)	grad_norm 1.9385 (1.9912)	
[2022-01-24 04:23:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1040/1251]	eta 0:07:44 lr 0.000241	time 1.8403 (2.2002)	loss 2.5106 (3.3343)	grad_norm 1.9156 (1.9910)	
[2022-01-24 04:23:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1050/1251]	eta 0:07:22 lr 0.000240	time 3.3656 (2.2001)	loss 3.6678 (3.3336)	grad_norm 1.8377 (1.9899)	
[2022-01-24 04:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1060/1251]	eta 0:06:59 lr 0.000240	time 1.6679 (2.1984)	loss 3.7834 (3.3353)	grad_norm 2.0930 (1.9890)	
[2022-01-24 04:24:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1070/1251]	eta 0:06:37 lr 0.000240	time 1.8631 (2.1968)	loss 3.5631 (3.3354)	grad_norm 1.8258 (1.9883)	
[2022-01-24 04:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1080/1251]	eta 0:06:15 lr 0.000240	time 1.8752 (2.1949)	loss 3.3650 (3.3337)	grad_norm 2.0417 (1.9873)	
[2022-01-24 04:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1090/1251]	eta 0:05:53 lr 0.000240	time 2.9251 (2.1952)	loss 3.2217 (3.3353)	grad_norm 2.1567 (1.9877)	
[2022-01-24 04:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1100/1251]	eta 0:05:31 lr 0.000240	time 2.0715 (2.1955)	loss 2.5836 (3.3370)	grad_norm 1.8685 (1.9871)	
[2022-01-24 04:25:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1110/1251]	eta 0:05:09 lr 0.000240	time 3.0619 (2.1961)	loss 3.2926 (3.3343)	grad_norm 2.0477 (1.9868)	
[2022-01-24 04:26:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1120/1251]	eta 0:04:47 lr 0.000240	time 2.8222 (2.1976)	loss 3.8250 (3.3344)	grad_norm 1.9400 (1.9866)	
[2022-01-24 04:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1130/1251]	eta 0:04:25 lr 0.000240	time 2.2272 (2.1975)	loss 3.7294 (3.3372)	grad_norm 1.9801 (1.9865)	
[2022-01-24 04:26:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1140/1251]	eta 0:04:03 lr 0.000240	time 1.6224 (2.1957)	loss 2.9824 (3.3372)	grad_norm 1.8994 (1.9865)	
[2022-01-24 04:27:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1150/1251]	eta 0:03:41 lr 0.000240	time 2.0146 (2.1942)	loss 2.5389 (3.3358)	grad_norm 1.9342 (1.9863)	
[2022-01-24 04:27:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1160/1251]	eta 0:03:19 lr 0.000240	time 2.2074 (2.1929)	loss 3.8865 (3.3351)	grad_norm 2.0141 (1.9879)	
[2022-01-24 04:28:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1170/1251]	eta 0:02:57 lr 0.000240	time 2.2316 (2.1935)	loss 3.0714 (3.3359)	grad_norm 1.7315 (1.9876)	
[2022-01-24 04:28:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1180/1251]	eta 0:02:35 lr 0.000240	time 1.5113 (2.1926)	loss 2.1928 (3.3370)	grad_norm 1.6765 (1.9884)	
[2022-01-24 04:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1190/1251]	eta 0:02:13 lr 0.000240	time 1.9565 (2.1929)	loss 3.2347 (3.3377)	grad_norm 2.1235 (1.9882)	
[2022-01-24 04:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1200/1251]	eta 0:01:51 lr 0.000240	time 2.4018 (2.1936)	loss 3.7975 (3.3397)	grad_norm 1.7385 (1.9881)	
[2022-01-24 04:29:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1210/1251]	eta 0:01:30 lr 0.000240	time 2.7334 (2.1953)	loss 3.6970 (3.3404)	grad_norm 1.8583 (1.9873)	
[2022-01-24 04:29:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1220/1251]	eta 0:01:08 lr 0.000240	time 1.7212 (2.1947)	loss 3.9677 (3.3406)	grad_norm 2.1497 (1.9868)	
[2022-01-24 04:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1230/1251]	eta 0:00:46 lr 0.000240	time 2.2110 (2.1951)	loss 2.5406 (3.3390)	grad_norm 1.9754 (1.9860)	
[2022-01-24 04:30:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1240/1251]	eta 0:00:24 lr 0.000240	time 2.1641 (2.1946)	loss 3.9016 (3.3392)	grad_norm 2.0770 (1.9856)	
[2022-01-24 04:30:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [203/300][1250/1251]	eta 0:00:02 lr 0.000240	time 1.2056 (2.1893)	loss 2.6058 (3.3380)	grad_norm 1.7979 (1.9851)	
[2022-01-24 04:30:53 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 203 training takes 0:45:39
[2022-01-24 04:31:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.817 (18.817)	Loss 0.9722 (0.9722)	Acc@1 76.465 (76.465)	Acc@5 94.434 (94.434)	
[2022-01-24 04:31:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.313 (3.327)	Loss 0.8584 (0.9154)	Acc@1 79.590 (78.436)	Acc@5 95.215 (94.744)	
[2022-01-24 04:31:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.166 (2.534)	Loss 0.9024 (0.9161)	Acc@1 79.297 (78.585)	Acc@5 94.922 (94.689)	
[2022-01-24 04:32:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.678 (2.204)	Loss 0.8325 (0.9200)	Acc@1 79.492 (78.572)	Acc@5 95.996 (94.497)	
[2022-01-24 04:32:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.843 (2.179)	Loss 0.9038 (0.9269)	Acc@1 78.906 (78.361)	Acc@5 95.410 (94.426)	
[2022-01-24 04:32:30 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.428 Acc@5 94.408
[2022-01-24 04:32:30 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.4%
[2022-01-24 04:32:30 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.47%
[2022-01-24 04:32:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][0/1251]	eta 8:28:07 lr 0.000240	time 24.3708 (24.3708)	loss 2.3917 (2.3917)	grad_norm 1.8991 (1.8991)	
[2022-01-24 04:33:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][10/1251]	eta 1:25:45 lr 0.000240	time 1.5104 (4.1460)	loss 3.5460 (3.3587)	grad_norm 1.9722 (1.8778)	
[2022-01-24 04:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][20/1251]	eta 1:05:19 lr 0.000240	time 1.5038 (3.1840)	loss 3.3273 (3.2576)	grad_norm 1.7319 (1.9661)	
[2022-01-24 04:33:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][30/1251]	eta 0:58:10 lr 0.000240	time 1.9741 (2.8583)	loss 3.1981 (3.2978)	grad_norm 1.9987 (2.0210)	
[2022-01-24 04:34:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][40/1251]	eta 0:55:42 lr 0.000240	time 6.3633 (2.7601)	loss 3.6107 (3.3116)	grad_norm 1.9989 (2.0325)	
[2022-01-24 04:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][50/1251]	eta 0:53:07 lr 0.000240	time 1.6876 (2.6541)	loss 3.8288 (3.3560)	grad_norm 1.8724 (2.0203)	
[2022-01-24 04:35:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][60/1251]	eta 0:50:53 lr 0.000240	time 1.9681 (2.5640)	loss 3.2463 (3.3534)	grad_norm 2.1645 (2.0128)	
[2022-01-24 04:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][70/1251]	eta 0:48:56 lr 0.000240	time 1.6628 (2.4867)	loss 3.2362 (3.3634)	grad_norm 1.9182 (2.0139)	
[2022-01-24 04:35:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][80/1251]	eta 0:48:18 lr 0.000239	time 3.5180 (2.4753)	loss 2.4921 (3.3471)	grad_norm 2.0516 (2.0127)	
[2022-01-24 04:36:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][90/1251]	eta 0:47:17 lr 0.000239	time 1.9959 (2.4436)	loss 3.6731 (3.3688)	grad_norm 1.7924 (2.0119)	
[2022-01-24 04:36:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][100/1251]	eta 0:46:04 lr 0.000239	time 1.8916 (2.4015)	loss 3.4685 (3.3807)	grad_norm 2.2431 (2.0211)	
[2022-01-24 04:36:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][110/1251]	eta 0:45:18 lr 0.000239	time 1.9164 (2.3823)	loss 3.6850 (3.3796)	grad_norm 1.7711 (2.0140)	
[2022-01-24 04:37:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][120/1251]	eta 0:44:35 lr 0.000239	time 2.9093 (2.3659)	loss 2.8850 (3.3586)	grad_norm 2.0236 (2.0124)	
[2022-01-24 04:37:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][130/1251]	eta 0:44:01 lr 0.000239	time 2.4741 (2.3560)	loss 3.5622 (3.3459)	grad_norm 1.9035 (2.0022)	
[2022-01-24 04:38:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][140/1251]	eta 0:43:24 lr 0.000239	time 1.6768 (2.3445)	loss 3.0549 (3.3359)	grad_norm 1.8940 (1.9936)	
[2022-01-24 04:38:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][150/1251]	eta 0:42:46 lr 0.000239	time 1.8948 (2.3313)	loss 3.1624 (3.3355)	grad_norm 2.4250 (2.0041)	
[2022-01-24 04:38:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][160/1251]	eta 0:42:20 lr 0.000239	time 2.4155 (2.3287)	loss 3.5376 (3.3214)	grad_norm 1.7667 (2.0028)	
[2022-01-24 04:39:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][170/1251]	eta 0:41:51 lr 0.000239	time 2.1416 (2.3230)	loss 3.6597 (3.3255)	grad_norm 1.7795 (1.9977)	
[2022-01-24 04:39:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][180/1251]	eta 0:41:14 lr 0.000239	time 1.8966 (2.3107)	loss 3.5678 (3.3083)	grad_norm 2.2059 (1.9941)	
[2022-01-24 04:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][190/1251]	eta 0:40:33 lr 0.000239	time 1.7906 (2.2936)	loss 3.5915 (3.2977)	grad_norm 1.8268 (1.9908)	
[2022-01-24 04:40:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][200/1251]	eta 0:40:00 lr 0.000239	time 2.6421 (2.2836)	loss 3.7067 (3.3180)	grad_norm 1.8083 (1.9919)	
[2022-01-24 04:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][210/1251]	eta 0:39:29 lr 0.000239	time 2.7547 (2.2759)	loss 3.3644 (3.3256)	grad_norm 1.7902 (1.9902)	
[2022-01-24 04:40:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][220/1251]	eta 0:39:06 lr 0.000239	time 2.2267 (2.2764)	loss 2.2434 (3.3252)	grad_norm 2.2616 (1.9893)	
[2022-01-24 04:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][230/1251]	eta 0:38:45 lr 0.000239	time 2.1879 (2.2777)	loss 2.7750 (3.3272)	grad_norm 2.0047 (1.9939)	
[2022-01-24 04:41:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][240/1251]	eta 0:38:18 lr 0.000239	time 2.1861 (2.2736)	loss 3.4278 (3.3312)	grad_norm 2.2381 (2.0030)	
[2022-01-24 04:42:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][250/1251]	eta 0:37:56 lr 0.000239	time 2.9763 (2.2743)	loss 3.7468 (3.3409)	grad_norm 1.9147 (1.9986)	
[2022-01-24 04:42:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][260/1251]	eta 0:37:32 lr 0.000239	time 1.9213 (2.2733)	loss 3.9852 (3.3426)	grad_norm 2.0746 (1.9993)	
[2022-01-24 04:42:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][270/1251]	eta 0:37:00 lr 0.000239	time 1.8555 (2.2633)	loss 3.7199 (3.3545)	grad_norm 1.8839 (2.0001)	
[2022-01-24 04:43:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][280/1251]	eta 0:36:28 lr 0.000239	time 2.1395 (2.2535)	loss 3.6663 (3.3477)	grad_norm 1.9634 (1.9987)	
[2022-01-24 04:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][290/1251]	eta 0:35:58 lr 0.000239	time 1.8252 (2.2456)	loss 3.0313 (3.3391)	grad_norm 1.9391 (1.9952)	
[2022-01-24 04:43:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][300/1251]	eta 0:35:35 lr 0.000239	time 2.3487 (2.2454)	loss 2.1351 (3.3328)	grad_norm 1.8823 (1.9931)	
[2022-01-24 04:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][310/1251]	eta 0:35:11 lr 0.000239	time 1.5185 (2.2440)	loss 3.7873 (3.3278)	grad_norm 1.8256 (1.9910)	
[2022-01-24 04:44:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][320/1251]	eta 0:34:49 lr 0.000239	time 2.3868 (2.2447)	loss 3.4607 (3.3329)	grad_norm 2.0082 (1.9899)	
[2022-01-24 04:44:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][330/1251]	eta 0:34:32 lr 0.000239	time 2.2713 (2.2507)	loss 2.6615 (3.3292)	grad_norm 2.2452 (1.9883)	
[2022-01-24 04:45:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][340/1251]	eta 0:34:13 lr 0.000239	time 2.3736 (2.2545)	loss 3.7546 (3.3360)	grad_norm 2.7079 (1.9944)	
[2022-01-24 04:45:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][350/1251]	eta 0:33:47 lr 0.000239	time 2.1900 (2.2504)	loss 2.8984 (3.3377)	grad_norm 1.9159 (1.9926)	
[2022-01-24 04:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][360/1251]	eta 0:33:19 lr 0.000239	time 2.2779 (2.2441)	loss 4.1022 (3.3416)	grad_norm 2.0786 (1.9931)	
[2022-01-24 04:46:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][370/1251]	eta 0:32:51 lr 0.000238	time 1.9167 (2.2380)	loss 3.5866 (3.3469)	grad_norm 1.9374 (1.9942)	
[2022-01-24 04:46:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][380/1251]	eta 0:32:27 lr 0.000238	time 2.1328 (2.2363)	loss 3.6054 (3.3484)	grad_norm 1.9247 (1.9915)	
[2022-01-24 04:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][390/1251]	eta 0:32:01 lr 0.000238	time 1.8662 (2.2320)	loss 3.5163 (3.3496)	grad_norm 1.9141 (1.9935)	
[2022-01-24 04:47:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][400/1251]	eta 0:31:39 lr 0.000238	time 2.5313 (2.2315)	loss 3.0122 (3.3455)	grad_norm 1.8876 (1.9935)	
[2022-01-24 04:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][410/1251]	eta 0:31:15 lr 0.000238	time 2.1137 (2.2299)	loss 3.6762 (3.3404)	grad_norm 1.7540 (1.9920)	
[2022-01-24 04:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][420/1251]	eta 0:30:53 lr 0.000238	time 1.9474 (2.2306)	loss 3.4244 (3.3353)	grad_norm 1.6822 (1.9915)	
[2022-01-24 04:48:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][430/1251]	eta 0:30:31 lr 0.000238	time 1.6751 (2.2313)	loss 3.9290 (3.3339)	grad_norm 1.8731 (1.9880)	
[2022-01-24 04:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][440/1251]	eta 0:30:09 lr 0.000238	time 2.2355 (2.2310)	loss 3.5248 (3.3326)	grad_norm 1.7265 (1.9861)	
[2022-01-24 04:49:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][450/1251]	eta 0:29:47 lr 0.000238	time 2.6941 (2.2316)	loss 3.7615 (3.3304)	grad_norm 1.7467 (1.9848)	
[2022-01-24 04:49:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][460/1251]	eta 0:29:25 lr 0.000238	time 1.7872 (2.2314)	loss 3.4807 (3.3320)	grad_norm 1.9926 (1.9825)	
[2022-01-24 04:50:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][470/1251]	eta 0:29:03 lr 0.000238	time 2.0784 (2.2322)	loss 3.9821 (3.3340)	grad_norm 2.0678 (1.9844)	
[2022-01-24 04:50:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][480/1251]	eta 0:28:36 lr 0.000238	time 1.8746 (2.2269)	loss 3.4806 (3.3360)	grad_norm 2.4727 (1.9847)	
[2022-01-24 04:50:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][490/1251]	eta 0:28:12 lr 0.000238	time 2.0841 (2.2238)	loss 3.1296 (3.3342)	grad_norm 1.8571 (1.9842)	
[2022-01-24 04:51:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][500/1251]	eta 0:27:48 lr 0.000238	time 1.8750 (2.2213)	loss 3.4092 (3.3319)	grad_norm 2.1543 (1.9834)	
[2022-01-24 04:51:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][510/1251]	eta 0:27:24 lr 0.000238	time 2.2461 (2.2195)	loss 3.6485 (3.3299)	grad_norm 1.9955 (1.9819)	
[2022-01-24 04:51:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][520/1251]	eta 0:27:02 lr 0.000238	time 1.9486 (2.2194)	loss 3.8450 (3.3344)	grad_norm 2.2892 (1.9817)	
[2022-01-24 04:52:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][530/1251]	eta 0:26:41 lr 0.000238	time 2.7330 (2.2206)	loss 3.0440 (3.3351)	grad_norm 1.9675 (1.9809)	
[2022-01-24 04:52:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][540/1251]	eta 0:26:19 lr 0.000238	time 2.1835 (2.2222)	loss 2.5609 (3.3346)	grad_norm 1.9044 (1.9806)	
[2022-01-24 04:52:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][550/1251]	eta 0:25:57 lr 0.000238	time 1.8273 (2.2220)	loss 4.0588 (3.3384)	grad_norm 1.8787 (1.9795)	
[2022-01-24 04:53:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][560/1251]	eta 0:25:35 lr 0.000238	time 1.8840 (2.2225)	loss 3.4794 (3.3441)	grad_norm 1.9202 (1.9793)	
[2022-01-24 04:53:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][570/1251]	eta 0:25:10 lr 0.000238	time 1.6165 (2.2173)	loss 3.2106 (3.3443)	grad_norm 2.0985 (1.9817)	
[2022-01-24 04:53:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][580/1251]	eta 0:24:47 lr 0.000238	time 2.0883 (2.2164)	loss 3.4237 (3.3436)	grad_norm 1.7570 (1.9827)	
[2022-01-24 04:54:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][590/1251]	eta 0:24:25 lr 0.000238	time 2.4437 (2.2164)	loss 3.0911 (3.3421)	grad_norm 2.6779 (1.9854)	
[2022-01-24 04:54:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][600/1251]	eta 0:24:04 lr 0.000238	time 2.0698 (2.2185)	loss 2.7338 (3.3456)	grad_norm 2.2028 (1.9851)	
[2022-01-24 04:55:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][610/1251]	eta 0:23:41 lr 0.000238	time 1.9173 (2.2173)	loss 3.1958 (3.3407)	grad_norm 2.1066 (1.9862)	
[2022-01-24 04:55:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][620/1251]	eta 0:23:17 lr 0.000238	time 1.6910 (2.2145)	loss 3.8123 (3.3394)	grad_norm 2.0753 (1.9853)	
[2022-01-24 04:55:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][630/1251]	eta 0:22:53 lr 0.000238	time 2.1422 (2.2120)	loss 4.0221 (3.3390)	grad_norm 2.5634 (1.9848)	
[2022-01-24 04:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][640/1251]	eta 0:22:30 lr 0.000238	time 1.8300 (2.2109)	loss 3.4531 (3.3417)	grad_norm 1.8662 (1.9844)	
[2022-01-24 04:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][650/1251]	eta 0:22:09 lr 0.000237	time 1.8843 (2.2114)	loss 3.5696 (3.3351)	grad_norm 1.9960 (1.9850)	
[2022-01-24 04:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][660/1251]	eta 0:21:46 lr 0.000237	time 2.2604 (2.2102)	loss 3.3769 (3.3364)	grad_norm 1.9934 (1.9864)	
[2022-01-24 04:57:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][670/1251]	eta 0:21:22 lr 0.000237	time 1.9434 (2.2070)	loss 2.7396 (3.3357)	grad_norm 1.8456 (1.9867)	
[2022-01-24 04:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][680/1251]	eta 0:21:01 lr 0.000237	time 1.7720 (2.2090)	loss 3.2747 (3.3393)	grad_norm 2.2029 (1.9871)	
[2022-01-24 04:57:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][690/1251]	eta 0:20:39 lr 0.000237	time 2.6229 (2.2096)	loss 3.4437 (3.3409)	grad_norm 2.1305 (1.9865)	
[2022-01-24 04:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][700/1251]	eta 0:20:17 lr 0.000237	time 2.2519 (2.2100)	loss 3.8533 (3.3429)	grad_norm 2.1495 (1.9888)	
[2022-01-24 04:58:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][710/1251]	eta 0:19:55 lr 0.000237	time 2.1327 (2.2097)	loss 3.7644 (3.3454)	grad_norm 1.8469 (1.9900)	
[2022-01-24 04:59:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][720/1251]	eta 0:19:33 lr 0.000237	time 1.6763 (2.2101)	loss 3.3930 (3.3426)	grad_norm 2.0455 (1.9893)	
[2022-01-24 04:59:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][730/1251]	eta 0:19:12 lr 0.000237	time 2.8102 (2.2115)	loss 3.3968 (3.3421)	grad_norm 2.0017 (1.9896)	
[2022-01-24 04:59:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][740/1251]	eta 0:18:49 lr 0.000237	time 1.8535 (2.2106)	loss 3.1738 (3.3435)	grad_norm 2.0891 (1.9901)	
[2022-01-24 05:00:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][750/1251]	eta 0:18:27 lr 0.000237	time 2.6765 (2.2098)	loss 3.0609 (3.3449)	grad_norm 2.0360 (1.9915)	
[2022-01-24 05:00:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][760/1251]	eta 0:18:03 lr 0.000237	time 1.5925 (2.2075)	loss 3.7706 (3.3471)	grad_norm 2.1165 (1.9920)	
[2022-01-24 05:00:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][770/1251]	eta 0:17:41 lr 0.000237	time 2.6998 (2.2060)	loss 3.6572 (3.3457)	grad_norm 1.9994 (1.9920)	
[2022-01-24 05:01:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][780/1251]	eta 0:17:18 lr 0.000237	time 1.9132 (2.2046)	loss 3.5798 (3.3462)	grad_norm 1.9041 (1.9924)	
[2022-01-24 05:01:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][790/1251]	eta 0:16:56 lr 0.000237	time 2.0445 (2.2049)	loss 3.2997 (3.3462)	grad_norm 2.0710 (1.9933)	
[2022-01-24 05:01:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][800/1251]	eta 0:16:34 lr 0.000237	time 2.2130 (2.2050)	loss 3.1706 (3.3451)	grad_norm 1.6743 (1.9928)	
[2022-01-24 05:02:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][810/1251]	eta 0:16:12 lr 0.000237	time 2.7738 (2.2061)	loss 3.6650 (3.3445)	grad_norm 1.8528 (1.9922)	
[2022-01-24 05:02:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][820/1251]	eta 0:15:51 lr 0.000237	time 2.1431 (2.2069)	loss 2.8990 (3.3452)	grad_norm 2.1318 (1.9934)	
[2022-01-24 05:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][830/1251]	eta 0:15:28 lr 0.000237	time 1.9114 (2.2063)	loss 3.5715 (3.3491)	grad_norm 1.8940 (1.9934)	
[2022-01-24 05:03:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][840/1251]	eta 0:15:05 lr 0.000237	time 2.0557 (2.2038)	loss 3.7788 (3.3492)	grad_norm 2.0583 (1.9948)	
[2022-01-24 05:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][850/1251]	eta 0:14:43 lr 0.000237	time 2.2313 (2.2020)	loss 2.8757 (3.3469)	grad_norm 2.2341 (1.9957)	
[2022-01-24 05:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][860/1251]	eta 0:14:20 lr 0.000237	time 1.9448 (2.2013)	loss 3.7387 (3.3468)	grad_norm 1.8075 (1.9967)	
[2022-01-24 05:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][870/1251]	eta 0:13:58 lr 0.000237	time 2.2636 (2.2013)	loss 3.1275 (3.3435)	grad_norm 1.6669 (1.9948)	
[2022-01-24 05:04:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][880/1251]	eta 0:13:36 lr 0.000237	time 2.4762 (2.2019)	loss 2.3506 (3.3409)	grad_norm 2.0080 (1.9945)	
[2022-01-24 05:05:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][890/1251]	eta 0:13:14 lr 0.000237	time 1.9653 (2.2011)	loss 3.3967 (3.3423)	grad_norm 2.0979 (1.9941)	
[2022-01-24 05:05:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][900/1251]	eta 0:12:52 lr 0.000237	time 2.8729 (2.2013)	loss 2.6799 (3.3381)	grad_norm 1.8964 (1.9938)	
[2022-01-24 05:05:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][910/1251]	eta 0:12:30 lr 0.000237	time 1.8593 (2.2007)	loss 2.6428 (3.3362)	grad_norm 1.8827 (1.9954)	
[2022-01-24 05:06:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][920/1251]	eta 0:12:07 lr 0.000237	time 2.0665 (2.1988)	loss 3.9620 (3.3366)	grad_norm 1.8198 (1.9951)	
[2022-01-24 05:06:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][930/1251]	eta 0:11:45 lr 0.000237	time 2.5625 (2.1972)	loss 3.2740 (3.3364)	grad_norm 2.0071 (1.9958)	
[2022-01-24 05:06:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][940/1251]	eta 0:11:22 lr 0.000236	time 2.2230 (2.1954)	loss 3.6994 (3.3374)	grad_norm 2.3350 (1.9978)	
[2022-01-24 05:07:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][950/1251]	eta 0:11:00 lr 0.000236	time 2.3340 (2.1946)	loss 3.2078 (3.3366)	grad_norm 2.4250 (1.9990)	
[2022-01-24 05:07:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][960/1251]	eta 0:10:39 lr 0.000236	time 2.3463 (2.1984)	loss 3.6377 (3.3347)	grad_norm 2.0594 (1.9998)	
[2022-01-24 05:08:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][970/1251]	eta 0:10:18 lr 0.000236	time 2.2300 (2.1995)	loss 2.3355 (3.3334)	grad_norm 1.7821 (1.9995)	
[2022-01-24 05:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][980/1251]	eta 0:09:56 lr 0.000236	time 2.3234 (2.2006)	loss 2.6294 (3.3329)	grad_norm 1.9095 (2.0000)	
[2022-01-24 05:08:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][990/1251]	eta 0:09:34 lr 0.000236	time 1.9150 (2.1998)	loss 2.7727 (3.3314)	grad_norm 2.0164 (1.9998)	
[2022-01-24 05:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1000/1251]	eta 0:09:11 lr 0.000236	time 2.3969 (2.1988)	loss 2.9444 (3.3313)	grad_norm 2.0744 (1.9989)	
[2022-01-24 05:09:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1010/1251]	eta 0:08:49 lr 0.000236	time 2.1480 (2.1972)	loss 3.7269 (3.3342)	grad_norm 1.8652 (1.9986)	
[2022-01-24 05:09:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1020/1251]	eta 0:08:27 lr 0.000236	time 2.2734 (2.1964)	loss 2.0362 (3.3334)	grad_norm 2.0744 (1.9988)	
[2022-01-24 05:10:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1030/1251]	eta 0:08:05 lr 0.000236	time 1.4925 (2.1952)	loss 3.5394 (3.3352)	grad_norm 1.8105 (1.9985)	
[2022-01-24 05:10:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1040/1251]	eta 0:07:43 lr 0.000236	time 2.0938 (2.1946)	loss 3.9436 (3.3359)	grad_norm 2.2511 (1.9979)	
[2022-01-24 05:10:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1050/1251]	eta 0:07:21 lr 0.000236	time 2.7126 (2.1970)	loss 3.5796 (3.3360)	grad_norm 2.0046 (1.9986)	
[2022-01-24 05:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1060/1251]	eta 0:06:59 lr 0.000236	time 2.3939 (2.1979)	loss 3.4785 (3.3350)	grad_norm 2.3702 (1.9989)	
[2022-01-24 05:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1070/1251]	eta 0:06:37 lr 0.000236	time 1.9875 (2.1983)	loss 3.6435 (3.3358)	grad_norm 2.0657 (1.9989)	
[2022-01-24 05:12:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1080/1251]	eta 0:06:15 lr 0.000236	time 2.1829 (2.1978)	loss 3.0961 (3.3377)	grad_norm 2.1166 (1.9988)	
[2022-01-24 05:12:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1090/1251]	eta 0:05:53 lr 0.000236	time 1.5646 (2.1974)	loss 3.0370 (3.3384)	grad_norm 1.8680 (1.9983)	
[2022-01-24 05:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1100/1251]	eta 0:05:31 lr 0.000236	time 1.9953 (2.1965)	loss 2.8272 (3.3389)	grad_norm 1.8946 (1.9976)	
[2022-01-24 05:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1110/1251]	eta 0:05:09 lr 0.000236	time 2.2716 (2.1971)	loss 3.3255 (3.3392)	grad_norm 1.9381 (2.0027)	
[2022-01-24 05:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1120/1251]	eta 0:04:47 lr 0.000236	time 1.8205 (2.1966)	loss 2.6555 (3.3376)	grad_norm 2.1010 (2.0034)	
[2022-01-24 05:13:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1130/1251]	eta 0:04:25 lr 0.000236	time 2.0689 (2.1965)	loss 2.4384 (3.3380)	grad_norm 1.9543 (2.0042)	
[2022-01-24 05:14:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1140/1251]	eta 0:04:03 lr 0.000236	time 2.5125 (2.1970)	loss 3.1133 (3.3365)	grad_norm 1.6302 (2.0043)	
[2022-01-24 05:14:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1150/1251]	eta 0:03:41 lr 0.000236	time 1.5231 (2.1976)	loss 3.8491 (3.3379)	grad_norm 2.2495 (2.0054)	
[2022-01-24 05:15:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1160/1251]	eta 0:03:19 lr 0.000236	time 1.6529 (2.1964)	loss 3.6453 (3.3370)	grad_norm 2.1783 (2.0062)	
[2022-01-24 05:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1170/1251]	eta 0:02:57 lr 0.000236	time 1.8620 (2.1949)	loss 3.5366 (3.3365)	grad_norm 2.0367 (2.0069)	
[2022-01-24 05:15:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1180/1251]	eta 0:02:36 lr 0.000236	time 2.9468 (2.1972)	loss 3.3403 (3.3371)	grad_norm 1.8224 (2.0064)	
[2022-01-24 05:16:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1190/1251]	eta 0:02:14 lr 0.000236	time 2.2124 (2.1989)	loss 3.2705 (3.3364)	grad_norm 1.7053 (2.0065)	
[2022-01-24 05:16:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1200/1251]	eta 0:01:52 lr 0.000236	time 1.5671 (2.1978)	loss 3.0614 (3.3376)	grad_norm 2.2012 (2.0070)	
[2022-01-24 05:16:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1210/1251]	eta 0:01:30 lr 0.000236	time 1.5969 (2.1961)	loss 3.0415 (3.3378)	grad_norm 2.1244 (2.0074)	
[2022-01-24 05:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1220/1251]	eta 0:01:08 lr 0.000236	time 3.1814 (2.1967)	loss 3.7261 (3.3396)	grad_norm 1.9593 (2.0071)	
[2022-01-24 05:17:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1230/1251]	eta 0:00:46 lr 0.000235	time 2.2576 (2.1962)	loss 2.9486 (3.3386)	grad_norm 1.9193 (2.0065)	
[2022-01-24 05:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1240/1251]	eta 0:00:24 lr 0.000235	time 1.4267 (2.1952)	loss 2.8843 (3.3366)	grad_norm 2.3665 (2.0063)	
[2022-01-24 05:18:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [204/300][1250/1251]	eta 0:00:02 lr 0.000235	time 1.1708 (2.1900)	loss 2.8573 (3.3367)	grad_norm 2.0744 (2.0054)	
[2022-01-24 05:18:10 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 204 training takes 0:45:40
[2022-01-24 05:18:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.575 (18.575)	Loss 0.9054 (0.9054)	Acc@1 77.441 (77.441)	Acc@5 95.215 (95.215)	
[2022-01-24 05:18:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.937 (3.413)	Loss 0.8935 (0.9080)	Acc@1 79.590 (78.746)	Acc@5 95.215 (94.478)	
[2022-01-24 05:19:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.595 (2.493)	Loss 0.9193 (0.9080)	Acc@1 78.027 (78.492)	Acc@5 94.336 (94.508)	
[2022-01-24 05:19:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.854 (2.327)	Loss 0.9142 (0.9084)	Acc@1 79.395 (78.528)	Acc@5 93.848 (94.553)	
[2022-01-24 05:19:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.408 (2.163)	Loss 0.8895 (0.9139)	Acc@1 78.125 (78.442)	Acc@5 94.727 (94.457)	
[2022-01-24 05:19:46 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.496 Acc@5 94.538
[2022-01-24 05:19:46 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.5%
[2022-01-24 05:19:46 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.50%
[2022-01-24 05:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][0/1251]	eta 7:28:59 lr 0.000235	time 21.5348 (21.5348)	loss 3.5117 (3.5117)	grad_norm 2.1309 (2.1309)	
[2022-01-24 05:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][10/1251]	eta 1:21:32 lr 0.000235	time 2.9061 (3.9424)	loss 3.2877 (3.3948)	grad_norm 1.8341 (1.9743)	
[2022-01-24 05:20:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][20/1251]	eta 1:03:07 lr 0.000235	time 1.6895 (3.0765)	loss 3.2592 (3.3122)	grad_norm 1.7756 (1.9702)	
[2022-01-24 05:21:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][30/1251]	eta 0:56:14 lr 0.000235	time 1.5912 (2.7639)	loss 4.0885 (3.3975)	grad_norm 2.2744 (1.9715)	
[2022-01-24 05:21:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][40/1251]	eta 0:53:13 lr 0.000235	time 3.0645 (2.6368)	loss 2.6888 (3.3817)	grad_norm 1.8819 (1.9754)	
[2022-01-24 05:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][50/1251]	eta 0:51:22 lr 0.000235	time 2.9659 (2.5663)	loss 3.6149 (3.3338)	grad_norm 2.4056 (1.9910)	
[2022-01-24 05:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][60/1251]	eta 0:49:40 lr 0.000235	time 1.6400 (2.5025)	loss 3.8975 (3.3446)	grad_norm 2.0166 (1.9905)	
[2022-01-24 05:22:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][70/1251]	eta 0:48:18 lr 0.000235	time 1.5172 (2.4545)	loss 3.7286 (3.3705)	grad_norm 1.9594 (1.9983)	
[2022-01-24 05:23:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][80/1251]	eta 0:48:01 lr 0.000235	time 3.5662 (2.4605)	loss 3.3657 (3.3971)	grad_norm 1.9543 (1.9853)	
[2022-01-24 05:23:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][90/1251]	eta 0:47:27 lr 0.000235	time 3.2570 (2.4525)	loss 3.6830 (3.4215)	grad_norm 1.9324 (1.9956)	
[2022-01-24 05:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][100/1251]	eta 0:46:20 lr 0.000235	time 1.5279 (2.4161)	loss 3.2498 (3.4232)	grad_norm 2.0349 (2.0081)	
[2022-01-24 05:24:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][110/1251]	eta 0:45:10 lr 0.000235	time 1.7655 (2.3752)	loss 3.9810 (3.4054)	grad_norm 2.2794 (2.0186)	
[2022-01-24 05:24:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][120/1251]	eta 0:44:24 lr 0.000235	time 2.6581 (2.3558)	loss 2.7690 (3.4011)	grad_norm 2.2189 (2.0277)	
[2022-01-24 05:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][130/1251]	eta 0:44:06 lr 0.000235	time 2.8120 (2.3612)	loss 2.9254 (3.3778)	grad_norm 1.9938 (2.0232)	
[2022-01-24 05:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][140/1251]	eta 0:43:47 lr 0.000235	time 1.7842 (2.3649)	loss 3.5785 (3.3728)	grad_norm 2.2251 (2.0276)	
[2022-01-24 05:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][150/1251]	eta 0:43:17 lr 0.000235	time 1.6124 (2.3589)	loss 3.4803 (3.3560)	grad_norm 1.9510 (2.0285)	
[2022-01-24 05:26:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][160/1251]	eta 0:42:33 lr 0.000235	time 1.9183 (2.3407)	loss 3.0028 (3.3546)	grad_norm 2.3431 (2.0301)	
[2022-01-24 05:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][170/1251]	eta 0:41:50 lr 0.000235	time 1.9322 (2.3220)	loss 3.6988 (3.3637)	grad_norm 1.7919 (2.0279)	
[2022-01-24 05:26:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][180/1251]	eta 0:41:11 lr 0.000235	time 2.0004 (2.3079)	loss 3.2407 (3.3546)	grad_norm 2.3002 (2.0285)	
[2022-01-24 05:27:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][190/1251]	eta 0:40:34 lr 0.000235	time 2.4143 (2.2941)	loss 3.3605 (3.3479)	grad_norm 2.0317 (2.0225)	
[2022-01-24 05:27:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][200/1251]	eta 0:40:02 lr 0.000235	time 2.1770 (2.2857)	loss 3.9837 (3.3500)	grad_norm 2.0723 (2.0210)	
[2022-01-24 05:27:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][210/1251]	eta 0:39:30 lr 0.000235	time 2.4807 (2.2767)	loss 3.4897 (3.3402)	grad_norm 2.0817 (2.0213)	
[2022-01-24 05:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][220/1251]	eta 0:38:59 lr 0.000235	time 1.8887 (2.2689)	loss 3.4740 (3.3324)	grad_norm 2.1770 (2.0186)	
[2022-01-24 05:28:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][230/1251]	eta 0:38:36 lr 0.000235	time 2.1590 (2.2691)	loss 2.3635 (3.3189)	grad_norm 1.8989 (2.0181)	
[2022-01-24 05:28:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][240/1251]	eta 0:38:15 lr 0.000235	time 2.3724 (2.2704)	loss 3.1427 (3.3156)	grad_norm 2.0906 (2.0196)	
[2022-01-24 05:29:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][250/1251]	eta 0:37:52 lr 0.000235	time 2.4866 (2.2705)	loss 3.6848 (3.3015)	grad_norm 1.9967 (2.0205)	
[2022-01-24 05:29:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][260/1251]	eta 0:37:29 lr 0.000235	time 2.1621 (2.2699)	loss 2.5301 (3.2980)	grad_norm 1.8495 (2.0193)	
[2022-01-24 05:30:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][270/1251]	eta 0:37:03 lr 0.000234	time 2.1527 (2.2665)	loss 3.7782 (3.3035)	grad_norm 1.7158 (2.0161)	
[2022-01-24 05:30:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][280/1251]	eta 0:36:44 lr 0.000234	time 2.9180 (2.2707)	loss 3.5925 (3.3032)	grad_norm 1.8172 (2.0098)	
[2022-01-24 05:30:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][290/1251]	eta 0:36:19 lr 0.000234	time 1.9510 (2.2675)	loss 3.2245 (3.3073)	grad_norm 1.9690 (2.0101)	
[2022-01-24 05:31:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][300/1251]	eta 0:35:54 lr 0.000234	time 2.8300 (2.2654)	loss 3.5551 (3.3071)	grad_norm 2.0083 (2.0103)	
[2022-01-24 05:31:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][310/1251]	eta 0:35:28 lr 0.000234	time 2.4341 (2.2624)	loss 3.9621 (3.3132)	grad_norm 2.0269 (2.0119)	
[2022-01-24 05:31:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][320/1251]	eta 0:35:00 lr 0.000234	time 2.6984 (2.2562)	loss 3.4671 (3.3166)	grad_norm 1.9086 (2.0097)	
[2022-01-24 05:32:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][330/1251]	eta 0:34:30 lr 0.000234	time 1.5891 (2.2486)	loss 3.2566 (3.3139)	grad_norm 1.9393 (2.0098)	
[2022-01-24 05:32:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][340/1251]	eta 0:34:04 lr 0.000234	time 1.8993 (2.2438)	loss 2.4607 (3.3046)	grad_norm 1.9774 (2.0091)	
[2022-01-24 05:32:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][350/1251]	eta 0:33:40 lr 0.000234	time 2.7370 (2.2428)	loss 3.3394 (3.2998)	grad_norm 1.8568 (2.0073)	
[2022-01-24 05:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][360/1251]	eta 0:33:22 lr 0.000234	time 2.4563 (2.2472)	loss 2.9666 (3.2994)	grad_norm 2.2269 (2.0083)	
[2022-01-24 05:33:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][370/1251]	eta 0:33:02 lr 0.000234	time 2.2091 (2.2505)	loss 3.1417 (3.3024)	grad_norm 2.1486 (2.0090)	
[2022-01-24 05:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][380/1251]	eta 0:32:34 lr 0.000234	time 1.9034 (2.2438)	loss 3.1345 (3.2941)	grad_norm 2.2532 (2.0108)	
[2022-01-24 05:34:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][390/1251]	eta 0:32:06 lr 0.000234	time 2.6923 (2.2376)	loss 3.7913 (3.2980)	grad_norm 2.1690 (2.0193)	
[2022-01-24 05:34:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][400/1251]	eta 0:31:39 lr 0.000234	time 2.1188 (2.2325)	loss 3.5744 (3.2994)	grad_norm 1.8784 (2.0200)	
[2022-01-24 05:35:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][410/1251]	eta 0:31:18 lr 0.000234	time 2.5996 (2.2337)	loss 3.6565 (3.3061)	grad_norm 1.8938 (2.0202)	
[2022-01-24 05:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][420/1251]	eta 0:30:57 lr 0.000234	time 3.0450 (2.2348)	loss 3.5535 (3.3114)	grad_norm 2.1355 (2.0203)	
[2022-01-24 05:35:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][430/1251]	eta 0:30:37 lr 0.000234	time 3.1311 (2.2382)	loss 3.5659 (3.3167)	grad_norm 1.9320 (2.0225)	
[2022-01-24 05:36:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][440/1251]	eta 0:30:14 lr 0.000234	time 2.2735 (2.2379)	loss 3.5056 (3.3115)	grad_norm 2.4038 (2.0226)	
[2022-01-24 05:36:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][450/1251]	eta 0:29:52 lr 0.000234	time 2.9197 (2.2374)	loss 3.5223 (3.3181)	grad_norm 2.1917 (2.0215)	
[2022-01-24 05:36:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][460/1251]	eta 0:29:25 lr 0.000234	time 1.6020 (2.2321)	loss 3.2578 (3.3177)	grad_norm 1.7789 (2.0205)	
[2022-01-24 05:37:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][470/1251]	eta 0:29:01 lr 0.000234	time 2.5999 (2.2296)	loss 3.6476 (3.3127)	grad_norm 1.8072 (2.0203)	
[2022-01-24 05:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][480/1251]	eta 0:28:35 lr 0.000234	time 2.1569 (2.2253)	loss 2.9956 (3.3165)	grad_norm 2.0453 (2.0221)	
[2022-01-24 05:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][490/1251]	eta 0:28:12 lr 0.000234	time 2.4960 (2.2247)	loss 3.5786 (3.3161)	grad_norm 2.3200 (2.0216)	
[2022-01-24 05:38:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][500/1251]	eta 0:27:49 lr 0.000234	time 1.5572 (2.2234)	loss 3.7120 (3.3171)	grad_norm 1.7781 (2.0201)	
[2022-01-24 05:38:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][510/1251]	eta 0:27:25 lr 0.000234	time 2.1950 (2.2204)	loss 3.9201 (3.3199)	grad_norm 1.7593 (2.0170)	
[2022-01-24 05:39:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][520/1251]	eta 0:27:01 lr 0.000234	time 2.0254 (2.2186)	loss 2.5232 (3.3192)	grad_norm 2.1553 (2.0180)	
[2022-01-24 05:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][530/1251]	eta 0:26:40 lr 0.000234	time 2.6101 (2.2197)	loss 3.8244 (3.3185)	grad_norm 2.3125 (2.0186)	
[2022-01-24 05:39:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][540/1251]	eta 0:26:17 lr 0.000234	time 2.2187 (2.2190)	loss 3.6836 (3.3171)	grad_norm 1.9368 (2.0216)	
[2022-01-24 05:40:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][550/1251]	eta 0:25:57 lr 0.000233	time 2.7797 (2.2217)	loss 3.1736 (3.3167)	grad_norm 1.6704 (2.0205)	
[2022-01-24 05:40:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][560/1251]	eta 0:25:35 lr 0.000233	time 2.4462 (2.2229)	loss 3.3709 (3.3200)	grad_norm 1.8311 (2.0212)	
[2022-01-24 05:40:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][570/1251]	eta 0:25:13 lr 0.000233	time 2.1656 (2.2225)	loss 3.3527 (3.3197)	grad_norm 1.9230 (2.0220)	
[2022-01-24 05:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][580/1251]	eta 0:24:50 lr 0.000233	time 2.0191 (2.2208)	loss 2.1167 (3.3183)	grad_norm 2.2252 (2.0210)	
[2022-01-24 05:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][590/1251]	eta 0:24:26 lr 0.000233	time 2.4608 (2.2182)	loss 3.7337 (3.3174)	grad_norm 2.1423 (2.0206)	
[2022-01-24 05:41:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][600/1251]	eta 0:24:04 lr 0.000233	time 1.6597 (2.2186)	loss 3.5499 (3.3210)	grad_norm 1.6954 (2.0196)	
[2022-01-24 05:42:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][610/1251]	eta 0:23:41 lr 0.000233	time 2.5091 (2.2180)	loss 3.2765 (3.3224)	grad_norm 2.0543 (2.0199)	
[2022-01-24 05:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][620/1251]	eta 0:23:20 lr 0.000233	time 2.5787 (2.2200)	loss 3.9280 (3.3240)	grad_norm 2.1870 (2.0174)	
[2022-01-24 05:43:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][630/1251]	eta 0:22:57 lr 0.000233	time 2.0669 (2.2186)	loss 3.6138 (3.3220)	grad_norm 2.3062 (2.0169)	
[2022-01-24 05:43:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][640/1251]	eta 0:22:34 lr 0.000233	time 2.2603 (2.2163)	loss 2.3410 (3.3217)	grad_norm 2.0596 (2.0162)	
[2022-01-24 05:43:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][650/1251]	eta 0:22:10 lr 0.000233	time 1.9686 (2.2132)	loss 3.7054 (3.3174)	grad_norm 2.1084 (2.0154)	
[2022-01-24 05:44:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][660/1251]	eta 0:21:47 lr 0.000233	time 2.1215 (2.2132)	loss 3.1910 (3.3145)	grad_norm 2.4677 (2.0159)	
[2022-01-24 05:44:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][670/1251]	eta 0:21:26 lr 0.000233	time 2.2765 (2.2139)	loss 3.1682 (3.3123)	grad_norm 1.8228 (2.0163)	
[2022-01-24 05:44:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][680/1251]	eta 0:21:04 lr 0.000233	time 2.5175 (2.2152)	loss 3.3334 (3.3133)	grad_norm 1.8994 (2.0154)	
[2022-01-24 05:45:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][690/1251]	eta 0:20:42 lr 0.000233	time 2.2721 (2.2147)	loss 2.5901 (3.3089)	grad_norm 1.8788 (2.0166)	
[2022-01-24 05:45:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][700/1251]	eta 0:20:19 lr 0.000233	time 1.6303 (2.2140)	loss 3.3043 (3.3094)	grad_norm 2.0570 (2.0165)	
[2022-01-24 05:46:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][710/1251]	eta 0:19:58 lr 0.000233	time 2.5562 (2.2152)	loss 3.8496 (3.3074)	grad_norm 2.1785 (2.0169)	
[2022-01-24 05:46:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][720/1251]	eta 0:19:35 lr 0.000233	time 1.6412 (2.2132)	loss 4.0937 (3.3069)	grad_norm 2.1056 (2.0177)	
[2022-01-24 05:46:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][730/1251]	eta 0:19:12 lr 0.000233	time 2.4415 (2.2123)	loss 3.9359 (3.3093)	grad_norm 1.8455 (2.0165)	
[2022-01-24 05:47:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][740/1251]	eta 0:18:49 lr 0.000233	time 1.7072 (2.2113)	loss 3.0289 (3.3108)	grad_norm 1.9096 (2.0174)	
[2022-01-24 05:47:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][750/1251]	eta 0:18:28 lr 0.000233	time 2.2640 (2.2121)	loss 3.7254 (3.3108)	grad_norm 1.9244 (2.0187)	
[2022-01-24 05:47:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][760/1251]	eta 0:18:06 lr 0.000233	time 1.5794 (2.2128)	loss 3.6255 (3.3118)	grad_norm 1.7488 (2.0197)	
[2022-01-24 05:48:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][770/1251]	eta 0:17:44 lr 0.000233	time 1.9463 (2.2138)	loss 3.5167 (3.3113)	grad_norm 1.9232 (2.0182)	
[2022-01-24 05:48:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][780/1251]	eta 0:17:24 lr 0.000233	time 2.2836 (2.2166)	loss 3.1463 (3.3122)	grad_norm 2.3032 (2.0185)	
[2022-01-24 05:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][790/1251]	eta 0:17:01 lr 0.000233	time 2.0307 (2.2167)	loss 3.5547 (3.3129)	grad_norm 1.7764 (2.0199)	
[2022-01-24 05:49:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][800/1251]	eta 0:16:38 lr 0.000233	time 1.6503 (2.2143)	loss 3.3784 (3.3096)	grad_norm 1.9427 (2.0203)	
[2022-01-24 05:49:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][810/1251]	eta 0:16:14 lr 0.000233	time 1.9180 (2.2099)	loss 3.4810 (3.3120)	grad_norm 2.2904 (2.0205)	
[2022-01-24 05:49:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][820/1251]	eta 0:15:51 lr 0.000233	time 2.1915 (2.2073)	loss 3.5110 (3.3130)	grad_norm 1.9975 (2.0210)	
[2022-01-24 05:50:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][830/1251]	eta 0:15:29 lr 0.000233	time 2.4554 (2.2076)	loss 3.0265 (3.3131)	grad_norm 1.8385 (2.0195)	
[2022-01-24 05:50:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][840/1251]	eta 0:15:06 lr 0.000232	time 2.6276 (2.2064)	loss 2.4981 (3.3132)	grad_norm 1.8636 (2.0193)	
[2022-01-24 05:51:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][850/1251]	eta 0:14:44 lr 0.000232	time 2.0347 (2.2053)	loss 2.8182 (3.3128)	grad_norm 1.9195 (2.0185)	
[2022-01-24 05:51:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][860/1251]	eta 0:14:22 lr 0.000232	time 2.2730 (2.2059)	loss 3.0884 (3.3123)	grad_norm 2.4870 (2.0186)	
[2022-01-24 05:51:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][870/1251]	eta 0:14:01 lr 0.000232	time 2.4802 (2.2086)	loss 3.5132 (3.3109)	grad_norm 2.2004 (2.0173)	
[2022-01-24 05:52:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][880/1251]	eta 0:13:41 lr 0.000232	time 2.8177 (2.2131)	loss 3.5504 (3.3100)	grad_norm 2.4045 (2.0188)	
[2022-01-24 05:52:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][890/1251]	eta 0:13:19 lr 0.000232	time 1.9346 (2.2146)	loss 3.1075 (3.3082)	grad_norm 1.8772 (2.0185)	
[2022-01-24 05:52:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][900/1251]	eta 0:12:56 lr 0.000232	time 2.0452 (2.2129)	loss 3.6415 (3.3066)	grad_norm 1.6380 (2.0179)	
[2022-01-24 05:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][910/1251]	eta 0:12:33 lr 0.000232	time 2.1050 (2.2100)	loss 3.4856 (3.3069)	grad_norm 1.9349 (2.0185)	
[2022-01-24 05:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][920/1251]	eta 0:12:10 lr 0.000232	time 1.9405 (2.2070)	loss 3.6505 (3.3065)	grad_norm 2.1526 (2.0180)	
[2022-01-24 05:54:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][930/1251]	eta 0:11:48 lr 0.000232	time 2.2332 (2.2062)	loss 3.2516 (3.3063)	grad_norm 2.3556 (2.0180)	
[2022-01-24 05:54:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][940/1251]	eta 0:11:26 lr 0.000232	time 2.6733 (2.2064)	loss 3.3195 (3.3072)	grad_norm 2.1561 (2.0193)	
[2022-01-24 05:54:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][950/1251]	eta 0:11:04 lr 0.000232	time 2.2689 (2.2068)	loss 3.8327 (3.3064)	grad_norm 1.8893 (2.0192)	
[2022-01-24 05:55:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][960/1251]	eta 0:10:42 lr 0.000232	time 1.9962 (2.2080)	loss 3.3397 (3.3086)	grad_norm 2.0032 (2.0197)	
[2022-01-24 05:55:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][970/1251]	eta 0:10:20 lr 0.000232	time 2.6395 (2.2096)	loss 3.8235 (3.3098)	grad_norm 2.0341 (2.0198)	
[2022-01-24 05:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][980/1251]	eta 0:09:59 lr 0.000232	time 3.5488 (2.2121)	loss 3.3008 (3.3101)	grad_norm 2.2132 (2.0204)	
[2022-01-24 05:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][990/1251]	eta 0:09:37 lr 0.000232	time 1.8431 (2.2113)	loss 3.9599 (3.3078)	grad_norm 2.0838 (2.0199)	
[2022-01-24 05:56:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1000/1251]	eta 0:09:14 lr 0.000232	time 1.8244 (2.2087)	loss 2.4643 (3.3063)	grad_norm 1.7994 (2.0193)	
[2022-01-24 05:56:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1010/1251]	eta 0:08:51 lr 0.000232	time 2.6012 (2.2070)	loss 3.2386 (3.3048)	grad_norm 1.6959 (2.0191)	
[2022-01-24 05:57:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1020/1251]	eta 0:08:29 lr 0.000232	time 2.3162 (2.2058)	loss 3.3644 (3.3056)	grad_norm 2.0573 (2.0189)	
[2022-01-24 05:57:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1030/1251]	eta 0:08:07 lr 0.000232	time 1.8391 (2.2050)	loss 3.6932 (3.3049)	grad_norm 2.2317 (2.0192)	
[2022-01-24 05:58:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1040/1251]	eta 0:07:45 lr 0.000232	time 2.8306 (2.2054)	loss 3.6260 (3.3047)	grad_norm 2.2600 (2.0193)	
[2022-01-24 05:58:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1050/1251]	eta 0:07:23 lr 0.000232	time 3.1262 (2.2060)	loss 3.5191 (3.3057)	grad_norm 1.9856 (2.0194)	
[2022-01-24 05:58:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1060/1251]	eta 0:07:01 lr 0.000232	time 2.4900 (2.2078)	loss 4.1284 (3.3085)	grad_norm 2.1369 (2.0201)	
[2022-01-24 05:59:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1070/1251]	eta 0:06:39 lr 0.000232	time 2.0274 (2.2090)	loss 3.8184 (3.3111)	grad_norm 2.1688 (2.0198)	
[2022-01-24 05:59:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1080/1251]	eta 0:06:17 lr 0.000232	time 1.8439 (2.2088)	loss 2.1037 (3.3100)	grad_norm 1.9952 (2.0194)	
[2022-01-24 05:59:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1090/1251]	eta 0:05:55 lr 0.000232	time 1.9352 (2.2073)	loss 2.7542 (3.3101)	grad_norm 1.9746 (2.0186)	
[2022-01-24 06:00:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1100/1251]	eta 0:05:33 lr 0.000232	time 2.6717 (2.2057)	loss 2.1827 (3.3074)	grad_norm 2.0893 (2.0183)	
[2022-01-24 06:00:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1110/1251]	eta 0:05:10 lr 0.000232	time 3.1260 (2.2056)	loss 2.4710 (3.3067)	grad_norm 1.9449 (2.0185)	
[2022-01-24 06:00:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1120/1251]	eta 0:04:48 lr 0.000232	time 2.5661 (2.2052)	loss 3.2530 (3.3088)	grad_norm 2.0724 (2.0187)	
[2022-01-24 06:01:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1130/1251]	eta 0:04:27 lr 0.000231	time 2.1860 (2.2072)	loss 3.7668 (3.3081)	grad_norm 1.9906 (2.0188)	
[2022-01-24 06:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1140/1251]	eta 0:04:05 lr 0.000231	time 2.4554 (2.2082)	loss 3.7370 (3.3077)	grad_norm 2.7267 (2.0195)	
[2022-01-24 06:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1150/1251]	eta 0:03:43 lr 0.000231	time 2.2223 (2.2080)	loss 3.6162 (3.3070)	grad_norm 2.1715 (2.0191)	
[2022-01-24 06:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1160/1251]	eta 0:03:20 lr 0.000231	time 2.9551 (2.2083)	loss 3.6187 (3.3078)	grad_norm 1.9666 (2.0189)	
[2022-01-24 06:02:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1170/1251]	eta 0:02:58 lr 0.000231	time 1.5121 (2.2086)	loss 3.3724 (3.3075)	grad_norm 2.0678 (2.0194)	
[2022-01-24 06:03:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1180/1251]	eta 0:02:36 lr 0.000231	time 2.1403 (2.2070)	loss 2.3265 (3.3083)	grad_norm 1.9504 (2.0201)	
[2022-01-24 06:03:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1190/1251]	eta 0:02:14 lr 0.000231	time 1.8881 (2.2060)	loss 3.3016 (3.3077)	grad_norm 2.0091 (2.0201)	
[2022-01-24 06:03:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1200/1251]	eta 0:01:52 lr 0.000231	time 2.7823 (2.2055)	loss 3.6828 (3.3073)	grad_norm 1.9132 (2.0197)	
[2022-01-24 06:04:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1210/1251]	eta 0:01:30 lr 0.000231	time 2.5671 (2.2055)	loss 3.5013 (3.3073)	grad_norm 3.1317 (2.0217)	
[2022-01-24 06:04:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1220/1251]	eta 0:01:08 lr 0.000231	time 2.5789 (2.2057)	loss 4.0003 (3.3089)	grad_norm 2.1356 (2.0218)	
[2022-01-24 06:05:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1230/1251]	eta 0:00:46 lr 0.000231	time 1.6066 (2.2060)	loss 3.2924 (3.3091)	grad_norm 2.2546 (2.0225)	
[2022-01-24 06:05:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1240/1251]	eta 0:00:24 lr 0.000231	time 2.0936 (2.2054)	loss 3.2991 (3.3096)	grad_norm 2.1365 (2.0234)	
[2022-01-24 06:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [205/300][1250/1251]	eta 0:00:02 lr 0.000231	time 1.1840 (2.1997)	loss 2.2349 (3.3065)	grad_norm 5.2297 (2.0259)	
[2022-01-24 06:05:38 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 205 training takes 0:45:52
[2022-01-24 06:05:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.819 (18.819)	Loss 0.9508 (0.9508)	Acc@1 77.148 (77.148)	Acc@5 94.434 (94.434)	
[2022-01-24 06:06:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.267 (3.559)	Loss 0.9169 (0.9264)	Acc@1 76.367 (77.947)	Acc@5 95.020 (94.371)	
[2022-01-24 06:06:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.302 (2.657)	Loss 0.8980 (0.9167)	Acc@1 80.078 (78.255)	Acc@5 94.336 (94.396)	
[2022-01-24 06:06:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.935 (2.298)	Loss 0.9172 (0.9044)	Acc@1 78.516 (78.434)	Acc@5 93.555 (94.427)	
[2022-01-24 06:07:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.781 (2.206)	Loss 0.9684 (0.9064)	Acc@1 77.930 (78.387)	Acc@5 93.359 (94.391)	
[2022-01-24 06:07:15 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.336 Acc@5 94.390
[2022-01-24 06:07:15 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.3%
[2022-01-24 06:07:15 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.50%
[2022-01-24 06:07:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][0/1251]	eta 7:35:19 lr 0.000231	time 21.8378 (21.8378)	loss 3.6264 (3.6264)	grad_norm 2.0276 (2.0276)	
[2022-01-24 06:08:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][10/1251]	eta 1:24:37 lr 0.000231	time 2.8021 (4.0914)	loss 3.0778 (3.4037)	grad_norm 1.7699 (1.9417)	
[2022-01-24 06:08:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][20/1251]	eta 1:05:40 lr 0.000231	time 1.7094 (3.2010)	loss 2.1911 (3.3133)	grad_norm 2.0610 (1.9558)	
[2022-01-24 06:08:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][30/1251]	eta 0:58:52 lr 0.000231	time 1.5420 (2.8929)	loss 3.5712 (3.3124)	grad_norm 1.7623 (1.9527)	
[2022-01-24 06:09:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][40/1251]	eta 0:56:36 lr 0.000231	time 3.5024 (2.8043)	loss 3.7864 (3.3327)	grad_norm 2.2111 (2.0089)	
[2022-01-24 06:09:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][50/1251]	eta 0:55:36 lr 0.000231	time 3.2170 (2.7782)	loss 3.7913 (3.2924)	grad_norm 1.9317 (1.9900)	
[2022-01-24 06:09:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][60/1251]	eta 0:53:07 lr 0.000231	time 2.6556 (2.6760)	loss 3.3001 (3.2849)	grad_norm 1.9872 (1.9876)	
[2022-01-24 06:10:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][70/1251]	eta 0:50:21 lr 0.000231	time 2.0173 (2.5587)	loss 2.2271 (3.2776)	grad_norm 2.1047 (1.9982)	
[2022-01-24 06:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][80/1251]	eta 0:48:22 lr 0.000231	time 2.1458 (2.4785)	loss 3.4722 (3.2974)	grad_norm 2.1425 (2.0067)	
[2022-01-24 06:10:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][90/1251]	eta 0:46:54 lr 0.000231	time 1.9815 (2.4244)	loss 2.3781 (3.2790)	grad_norm 2.0085 (1.9931)	
[2022-01-24 06:11:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][100/1251]	eta 0:46:02 lr 0.000231	time 2.5422 (2.4004)	loss 2.6745 (3.2892)	grad_norm 1.9227 (1.9934)	
[2022-01-24 06:11:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][110/1251]	eta 0:46:20 lr 0.000231	time 6.2091 (2.4367)	loss 2.6401 (3.2729)	grad_norm 1.8592 (2.0003)	
[2022-01-24 06:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][120/1251]	eta 0:45:38 lr 0.000231	time 2.0852 (2.4211)	loss 3.7490 (3.2655)	grad_norm 2.5862 (2.0087)	
[2022-01-24 06:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][130/1251]	eta 0:44:50 lr 0.000231	time 1.9506 (2.4003)	loss 2.6914 (3.2461)	grad_norm 2.2533 (2.0051)	
[2022-01-24 06:12:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][140/1251]	eta 0:44:03 lr 0.000231	time 2.1286 (2.3797)	loss 3.5661 (3.2625)	grad_norm 1.9104 (1.9957)	
[2022-01-24 06:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][150/1251]	eta 0:43:41 lr 0.000231	time 4.5638 (2.3806)	loss 3.6452 (3.2835)	grad_norm 1.7688 (1.9923)	
[2022-01-24 06:13:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][160/1251]	eta 0:42:50 lr 0.000231	time 1.7614 (2.3565)	loss 3.3755 (3.3043)	grad_norm 1.6090 (1.9946)	
[2022-01-24 06:13:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][170/1251]	eta 0:42:11 lr 0.000230	time 2.0240 (2.3417)	loss 3.7927 (3.3052)	grad_norm 2.1758 (1.9901)	
[2022-01-24 06:14:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][180/1251]	eta 0:41:32 lr 0.000230	time 1.8867 (2.3274)	loss 3.7308 (3.3106)	grad_norm 1.9002 (1.9894)	
[2022-01-24 06:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][190/1251]	eta 0:41:14 lr 0.000230	time 3.6150 (2.3318)	loss 3.0245 (3.3063)	grad_norm 1.8941 (1.9915)	
[2022-01-24 06:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][200/1251]	eta 0:40:53 lr 0.000230	time 1.9745 (2.3347)	loss 4.3117 (3.3173)	grad_norm 2.1308 (1.9948)	
[2022-01-24 06:15:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][210/1251]	eta 0:40:22 lr 0.000230	time 1.7105 (2.3266)	loss 3.5985 (3.3260)	grad_norm 2.1980 (1.9949)	
[2022-01-24 06:15:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][220/1251]	eta 0:39:52 lr 0.000230	time 1.7408 (2.3209)	loss 3.8213 (3.3297)	grad_norm 2.2579 (2.0001)	
[2022-01-24 06:16:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][230/1251]	eta 0:39:28 lr 0.000230	time 3.9998 (2.3202)	loss 3.6540 (3.3382)	grad_norm 2.0733 (2.0015)	
[2022-01-24 06:16:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][240/1251]	eta 0:38:55 lr 0.000230	time 1.7048 (2.3104)	loss 3.5298 (3.3349)	grad_norm 2.0054 (2.0058)	
[2022-01-24 06:16:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][250/1251]	eta 0:38:22 lr 0.000230	time 1.6061 (2.3003)	loss 3.6562 (3.3282)	grad_norm 1.8823 (2.0037)	
[2022-01-24 06:17:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][260/1251]	eta 0:37:57 lr 0.000230	time 2.2287 (2.2986)	loss 3.7986 (3.3306)	grad_norm 2.0148 (2.0073)	
[2022-01-24 06:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][270/1251]	eta 0:37:36 lr 0.000230	time 3.6813 (2.3000)	loss 2.9452 (3.3371)	grad_norm 1.8817 (2.0044)	
[2022-01-24 06:18:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][280/1251]	eta 0:37:14 lr 0.000230	time 1.8778 (2.3016)	loss 2.6369 (3.3368)	grad_norm 1.8433 (2.0047)	
[2022-01-24 06:18:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][290/1251]	eta 0:36:42 lr 0.000230	time 1.7056 (2.2917)	loss 3.7691 (3.3275)	grad_norm 1.8834 (2.0059)	
[2022-01-24 06:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][300/1251]	eta 0:36:18 lr 0.000230	time 1.8656 (2.2904)	loss 2.3821 (3.3251)	grad_norm 2.3341 (2.0102)	
[2022-01-24 06:19:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][310/1251]	eta 0:35:58 lr 0.000230	time 5.5589 (2.2936)	loss 3.6329 (3.3246)	grad_norm 1.7237 (2.0101)	
[2022-01-24 06:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][320/1251]	eta 0:35:28 lr 0.000230	time 1.8681 (2.2859)	loss 3.0344 (3.3246)	grad_norm 1.8624 (2.0095)	
[2022-01-24 06:19:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][330/1251]	eta 0:34:57 lr 0.000230	time 1.8642 (2.2774)	loss 3.8591 (3.3192)	grad_norm 2.1074 (2.0077)	
[2022-01-24 06:20:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][340/1251]	eta 0:34:26 lr 0.000230	time 1.8959 (2.2682)	loss 3.8342 (3.3231)	grad_norm 1.9386 (2.0067)	
[2022-01-24 06:20:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][350/1251]	eta 0:33:59 lr 0.000230	time 2.4262 (2.2639)	loss 3.6000 (3.3113)	grad_norm 2.2084 (2.0063)	
[2022-01-24 06:20:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][360/1251]	eta 0:33:35 lr 0.000230	time 2.2467 (2.2625)	loss 3.5046 (3.3094)	grad_norm 1.8911 (2.0059)	
[2022-01-24 06:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][370/1251]	eta 0:33:17 lr 0.000230	time 4.4610 (2.2673)	loss 3.3591 (3.3116)	grad_norm 2.3147 (2.0085)	
[2022-01-24 06:21:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][380/1251]	eta 0:32:53 lr 0.000230	time 2.5531 (2.2661)	loss 2.6831 (3.3007)	grad_norm 2.0913 (2.0111)	
[2022-01-24 06:22:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][390/1251]	eta 0:32:28 lr 0.000230	time 1.6783 (2.2631)	loss 3.7094 (3.3048)	grad_norm 2.5407 (2.0154)	
[2022-01-24 06:22:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][400/1251]	eta 0:32:00 lr 0.000230	time 1.9197 (2.2566)	loss 3.6701 (3.3078)	grad_norm 2.1217 (2.0196)	
[2022-01-24 06:22:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][410/1251]	eta 0:31:34 lr 0.000230	time 2.4653 (2.2528)	loss 3.7206 (3.3057)	grad_norm 1.8300 (2.0194)	
[2022-01-24 06:23:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][420/1251]	eta 0:31:10 lr 0.000230	time 2.5108 (2.2509)	loss 2.7908 (3.3020)	grad_norm 1.7636 (2.0186)	
[2022-01-24 06:23:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][430/1251]	eta 0:30:45 lr 0.000230	time 1.8462 (2.2476)	loss 2.1563 (3.2929)	grad_norm 1.9460 (2.0159)	
[2022-01-24 06:23:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][440/1251]	eta 0:30:24 lr 0.000230	time 2.3098 (2.2491)	loss 3.6304 (3.2888)	grad_norm 1.9977 (2.0137)	
[2022-01-24 06:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][450/1251]	eta 0:30:04 lr 0.000230	time 3.3590 (2.2528)	loss 3.3937 (3.2908)	grad_norm 1.8556 (2.0109)	
[2022-01-24 06:24:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][460/1251]	eta 0:29:45 lr 0.000229	time 1.4234 (2.2573)	loss 3.5312 (3.2983)	grad_norm 2.0489 (2.0096)	
[2022-01-24 06:25:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][470/1251]	eta 0:29:25 lr 0.000229	time 1.5191 (2.2606)	loss 2.8607 (3.2952)	grad_norm 1.8790 (2.0062)	
[2022-01-24 06:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][480/1251]	eta 0:29:00 lr 0.000229	time 2.2540 (2.2578)	loss 2.3257 (3.2918)	grad_norm 1.8290 (2.0062)	
[2022-01-24 06:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][490/1251]	eta 0:28:34 lr 0.000229	time 1.8604 (2.2531)	loss 2.9075 (3.2866)	grad_norm 2.0083 (2.0063)	
[2022-01-24 06:26:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][500/1251]	eta 0:28:08 lr 0.000229	time 1.6379 (2.2482)	loss 2.1387 (3.2844)	grad_norm 1.9998 (2.0059)	
[2022-01-24 06:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][510/1251]	eta 0:27:44 lr 0.000229	time 2.2259 (2.2467)	loss 3.7821 (3.2826)	grad_norm 1.9787 (2.0040)	
[2022-01-24 06:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][520/1251]	eta 0:27:19 lr 0.000229	time 2.2282 (2.2430)	loss 4.0950 (3.2872)	grad_norm 2.0339 (2.0058)	
[2022-01-24 06:27:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][530/1251]	eta 0:26:58 lr 0.000229	time 2.5409 (2.2448)	loss 2.5872 (3.2840)	grad_norm 2.1927 (2.0083)	
[2022-01-24 06:27:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][540/1251]	eta 0:26:34 lr 0.000229	time 1.8753 (2.2432)	loss 2.9751 (3.2840)	grad_norm 1.9584 (2.0105)	
[2022-01-24 06:27:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][550/1251]	eta 0:26:10 lr 0.000229	time 2.4916 (2.2408)	loss 3.6035 (3.2882)	grad_norm 1.8410 (2.0092)	
[2022-01-24 06:28:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][560/1251]	eta 0:25:45 lr 0.000229	time 1.8847 (2.2369)	loss 3.4557 (3.2901)	grad_norm 1.9107 (2.0092)	
[2022-01-24 06:28:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][570/1251]	eta 0:25:22 lr 0.000229	time 2.1401 (2.2356)	loss 2.3810 (3.2868)	grad_norm 2.0406 (2.0081)	
[2022-01-24 06:28:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][580/1251]	eta 0:25:01 lr 0.000229	time 2.4742 (2.2384)	loss 2.4228 (3.2832)	grad_norm 1.8975 (2.0074)	
[2022-01-24 06:29:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][590/1251]	eta 0:24:40 lr 0.000229	time 2.3153 (2.2401)	loss 3.5842 (3.2841)	grad_norm 1.9574 (2.0085)	
[2022-01-24 06:29:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][600/1251]	eta 0:24:19 lr 0.000229	time 2.5217 (2.2424)	loss 3.5931 (3.2858)	grad_norm 2.1541 (2.0097)	
[2022-01-24 06:30:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][610/1251]	eta 0:23:58 lr 0.000229	time 2.1981 (2.2441)	loss 3.1909 (3.2865)	grad_norm 2.0352 (2.0085)	
[2022-01-24 06:30:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][620/1251]	eta 0:23:33 lr 0.000229	time 2.2482 (2.2406)	loss 3.2652 (3.2916)	grad_norm 1.8523 (2.0083)	
[2022-01-24 06:30:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][630/1251]	eta 0:23:09 lr 0.000229	time 2.5836 (2.2372)	loss 3.4403 (3.2856)	grad_norm 1.8985 (2.0070)	
[2022-01-24 06:31:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][640/1251]	eta 0:22:44 lr 0.000229	time 2.2331 (2.2337)	loss 3.2521 (3.2872)	grad_norm 1.9301 (2.0063)	
[2022-01-24 06:31:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][650/1251]	eta 0:22:21 lr 0.000229	time 1.9085 (2.2320)	loss 2.1617 (3.2876)	grad_norm 1.8763 (2.0060)	
[2022-01-24 06:31:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][660/1251]	eta 0:21:58 lr 0.000229	time 2.2459 (2.2317)	loss 2.7011 (3.2851)	grad_norm 1.8420 (2.0041)	
[2022-01-24 06:32:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][670/1251]	eta 0:21:36 lr 0.000229	time 2.1863 (2.2313)	loss 3.2990 (3.2878)	grad_norm 1.7121 (2.0030)	
[2022-01-24 06:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][680/1251]	eta 0:21:14 lr 0.000229	time 2.5651 (2.2321)	loss 2.0904 (3.2887)	grad_norm 1.7392 (2.0022)	
[2022-01-24 06:32:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][690/1251]	eta 0:20:52 lr 0.000229	time 2.0902 (2.2329)	loss 3.9071 (3.2903)	grad_norm 2.0410 (2.0024)	
[2022-01-24 06:33:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][700/1251]	eta 0:20:29 lr 0.000229	time 1.5689 (2.2316)	loss 3.3559 (3.2921)	grad_norm 1.9836 (2.0015)	
[2022-01-24 06:33:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][710/1251]	eta 0:20:07 lr 0.000229	time 2.4720 (2.2319)	loss 2.9550 (3.2934)	grad_norm 1.8181 (2.0023)	
[2022-01-24 06:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][720/1251]	eta 0:19:43 lr 0.000229	time 2.4504 (2.2294)	loss 2.7679 (3.2887)	grad_norm 1.8710 (2.0015)	
[2022-01-24 06:34:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][730/1251]	eta 0:19:19 lr 0.000229	time 2.5399 (2.2261)	loss 2.8189 (3.2884)	grad_norm 2.4274 (2.0087)	
[2022-01-24 06:34:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][740/1251]	eta 0:18:56 lr 0.000229	time 1.9377 (2.2246)	loss 2.1240 (3.2851)	grad_norm 2.2010 (2.0110)	
[2022-01-24 06:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][750/1251]	eta 0:18:34 lr 0.000228	time 2.6514 (2.2254)	loss 2.9557 (3.2813)	grad_norm 2.0908 (2.0123)	
[2022-01-24 06:35:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][760/1251]	eta 0:18:11 lr 0.000228	time 1.5528 (2.2234)	loss 3.6097 (3.2836)	grad_norm 2.1418 (2.0133)	
[2022-01-24 06:35:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][770/1251]	eta 0:17:49 lr 0.000228	time 1.8796 (2.2238)	loss 2.3033 (3.2819)	grad_norm 1.9516 (2.0141)	
[2022-01-24 06:36:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][780/1251]	eta 0:17:27 lr 0.000228	time 2.3169 (2.2250)	loss 3.7500 (3.2817)	grad_norm 2.0448 (2.0150)	
[2022-01-24 06:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][790/1251]	eta 0:17:06 lr 0.000228	time 2.9966 (2.2271)	loss 3.4141 (3.2817)	grad_norm 1.8750 (2.0143)	
[2022-01-24 06:36:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][800/1251]	eta 0:16:44 lr 0.000228	time 1.5441 (2.2275)	loss 3.2917 (3.2836)	grad_norm 1.7417 (2.0149)	
[2022-01-24 06:37:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][810/1251]	eta 0:16:22 lr 0.000228	time 2.4265 (2.2270)	loss 3.4966 (3.2816)	grad_norm 1.8621 (2.0152)	
[2022-01-24 06:37:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][820/1251]	eta 0:15:59 lr 0.000228	time 1.9211 (2.2267)	loss 3.8180 (3.2848)	grad_norm 1.9392 (2.0141)	
[2022-01-24 06:38:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][830/1251]	eta 0:15:36 lr 0.000228	time 2.4799 (2.2251)	loss 3.2250 (3.2851)	grad_norm 2.0791 (2.0148)	
[2022-01-24 06:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][840/1251]	eta 0:15:13 lr 0.000228	time 1.7611 (2.2233)	loss 3.9421 (3.2875)	grad_norm 2.0873 (2.0142)	
[2022-01-24 06:38:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][850/1251]	eta 0:14:50 lr 0.000228	time 2.0741 (2.2212)	loss 3.7485 (3.2880)	grad_norm 2.0014 (2.0141)	
[2022-01-24 06:39:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][860/1251]	eta 0:14:28 lr 0.000228	time 2.1079 (2.2210)	loss 2.6286 (3.2899)	grad_norm 2.1435 (2.0143)	
[2022-01-24 06:39:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][870/1251]	eta 0:14:06 lr 0.000228	time 2.7468 (2.2212)	loss 3.8856 (3.2894)	grad_norm 2.5103 (2.0145)	
[2022-01-24 06:39:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][880/1251]	eta 0:13:44 lr 0.000228	time 1.8326 (2.2229)	loss 2.4782 (3.2905)	grad_norm 2.1202 (2.0146)	
[2022-01-24 06:40:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][890/1251]	eta 0:13:22 lr 0.000228	time 2.0128 (2.2225)	loss 3.0364 (3.2926)	grad_norm 1.7905 (2.0139)	
[2022-01-24 06:40:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][900/1251]	eta 0:13:00 lr 0.000228	time 1.8633 (2.2226)	loss 3.2128 (3.2934)	grad_norm 2.5658 (2.0143)	
[2022-01-24 06:41:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][910/1251]	eta 0:12:37 lr 0.000228	time 1.6396 (2.2222)	loss 2.3651 (3.2935)	grad_norm 1.9149 (2.0143)	
[2022-01-24 06:41:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][920/1251]	eta 0:12:15 lr 0.000228	time 1.9176 (2.2214)	loss 2.9578 (3.2935)	grad_norm 2.0217 (2.0135)	
[2022-01-24 06:41:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][930/1251]	eta 0:11:52 lr 0.000228	time 2.1574 (2.2200)	loss 2.8063 (3.2942)	grad_norm 2.0841 (2.0131)	
[2022-01-24 06:42:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][940/1251]	eta 0:11:29 lr 0.000228	time 2.2822 (2.2172)	loss 2.5415 (3.2941)	grad_norm 1.6845 (2.0127)	
[2022-01-24 06:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][950/1251]	eta 0:11:07 lr 0.000228	time 2.1204 (2.2171)	loss 3.3615 (3.2945)	grad_norm 1.8173 (2.0126)	
[2022-01-24 06:42:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][960/1251]	eta 0:10:44 lr 0.000228	time 1.9145 (2.2159)	loss 2.4570 (3.2951)	grad_norm 1.9332 (2.0124)	
[2022-01-24 06:43:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][970/1251]	eta 0:10:22 lr 0.000228	time 1.8046 (2.2155)	loss 3.8933 (3.2955)	grad_norm 1.7892 (2.0112)	
[2022-01-24 06:43:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][980/1251]	eta 0:10:00 lr 0.000228	time 1.9101 (2.2155)	loss 3.5225 (3.2949)	grad_norm 1.8724 (2.0109)	
[2022-01-24 06:43:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][990/1251]	eta 0:09:38 lr 0.000228	time 2.7391 (2.2168)	loss 2.8406 (3.2929)	grad_norm 1.8830 (2.0102)	
[2022-01-24 06:44:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1000/1251]	eta 0:09:16 lr 0.000228	time 2.3808 (2.2164)	loss 3.4915 (3.2946)	grad_norm 1.7961 (2.0094)	
[2022-01-24 06:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1010/1251]	eta 0:08:54 lr 0.000228	time 1.9896 (2.2173)	loss 3.2319 (3.2968)	grad_norm 1.6095 (2.0081)	
[2022-01-24 06:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1020/1251]	eta 0:08:31 lr 0.000228	time 1.8629 (2.2156)	loss 3.8591 (3.2978)	grad_norm 1.8965 (2.0086)	
[2022-01-24 06:45:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1030/1251]	eta 0:08:09 lr 0.000228	time 2.5564 (2.2160)	loss 3.6486 (3.3003)	grad_norm 1.7666 (2.0068)	
[2022-01-24 06:45:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1040/1251]	eta 0:07:47 lr 0.000227	time 2.2062 (2.2151)	loss 3.4071 (3.3005)	grad_norm 1.9003 (2.0066)	
[2022-01-24 06:46:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1050/1251]	eta 0:07:24 lr 0.000227	time 1.6487 (2.2139)	loss 3.4768 (3.3006)	grad_norm 2.3757 (2.0065)	
[2022-01-24 06:46:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1060/1251]	eta 0:07:02 lr 0.000227	time 2.2300 (2.2140)	loss 3.8958 (3.3032)	grad_norm 1.9866 (2.0062)	
[2022-01-24 06:46:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1070/1251]	eta 0:06:40 lr 0.000227	time 2.4387 (2.2151)	loss 2.4634 (3.3028)	grad_norm 2.2862 (2.0060)	
[2022-01-24 06:47:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1080/1251]	eta 0:06:18 lr 0.000227	time 2.2691 (2.2134)	loss 2.3861 (3.3033)	grad_norm 1.8828 (2.0052)	
[2022-01-24 06:47:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1090/1251]	eta 0:05:56 lr 0.000227	time 1.8439 (2.2123)	loss 3.3495 (3.3053)	grad_norm 1.9422 (2.0057)	
[2022-01-24 06:47:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1100/1251]	eta 0:05:34 lr 0.000227	time 1.9958 (2.2122)	loss 3.1668 (3.3065)	grad_norm 1.7778 (2.0049)	
[2022-01-24 06:48:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1110/1251]	eta 0:05:12 lr 0.000227	time 2.8523 (2.2131)	loss 2.0228 (3.3046)	grad_norm 1.9228 (2.0047)	
[2022-01-24 06:48:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1120/1251]	eta 0:04:50 lr 0.000227	time 2.6891 (2.2144)	loss 2.2749 (3.3037)	grad_norm 2.3128 (2.0052)	
[2022-01-24 06:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1130/1251]	eta 0:04:27 lr 0.000227	time 1.5304 (2.2141)	loss 3.4284 (3.3039)	grad_norm 1.9938 (2.0062)	
[2022-01-24 06:49:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1140/1251]	eta 0:04:05 lr 0.000227	time 1.9801 (2.2135)	loss 2.2882 (3.3010)	grad_norm 1.8547 (2.0067)	
[2022-01-24 06:49:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1150/1251]	eta 0:03:43 lr 0.000227	time 2.0727 (2.2130)	loss 3.5524 (3.3004)	grad_norm 1.7052 (2.0059)	
[2022-01-24 06:50:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1160/1251]	eta 0:03:21 lr 0.000227	time 2.2204 (2.2121)	loss 3.2743 (3.3025)	grad_norm 2.1983 (2.0061)	
[2022-01-24 06:50:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1170/1251]	eta 0:02:59 lr 0.000227	time 2.1309 (2.2109)	loss 3.8186 (3.3040)	grad_norm 1.8653 (2.0060)	
[2022-01-24 06:50:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1180/1251]	eta 0:02:36 lr 0.000227	time 1.6912 (2.2109)	loss 2.8555 (3.3040)	grad_norm 1.8379 (2.0069)	
[2022-01-24 06:51:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1190/1251]	eta 0:02:14 lr 0.000227	time 1.5504 (2.2108)	loss 3.7992 (3.3051)	grad_norm 2.0937 (2.0078)	
[2022-01-24 06:51:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1200/1251]	eta 0:01:52 lr 0.000227	time 2.8274 (2.2126)	loss 3.8072 (3.3067)	grad_norm 2.1178 (2.0078)	
[2022-01-24 06:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1210/1251]	eta 0:01:30 lr 0.000227	time 2.5231 (2.2132)	loss 3.7400 (3.3088)	grad_norm 1.9483 (2.0073)	
[2022-01-24 06:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1220/1251]	eta 0:01:08 lr 0.000227	time 1.8161 (2.2124)	loss 2.5551 (3.3078)	grad_norm 1.8747 (2.0065)	
[2022-01-24 06:52:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1230/1251]	eta 0:00:46 lr 0.000227	time 1.8107 (2.2098)	loss 3.5839 (3.3097)	grad_norm 2.0570 (2.0062)	
[2022-01-24 06:52:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1240/1251]	eta 0:00:24 lr 0.000227	time 1.8287 (2.2083)	loss 3.5634 (3.3099)	grad_norm 1.9679 (2.0062)	
[2022-01-24 06:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [206/300][1250/1251]	eta 0:00:02 lr 0.000227	time 1.1742 (2.2026)	loss 2.7568 (3.3083)	grad_norm 2.1284 (2.0060)	
[2022-01-24 06:53:11 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 206 training takes 0:45:55
[2022-01-24 06:53:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.341 (18.341)	Loss 1.0157 (1.0157)	Acc@1 77.539 (77.539)	Acc@5 93.457 (93.457)	
[2022-01-24 06:53:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.996 (3.543)	Loss 1.0265 (0.9592)	Acc@1 76.172 (77.681)	Acc@5 93.066 (94.221)	
[2022-01-24 06:54:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.314 (2.673)	Loss 0.8773 (0.9369)	Acc@1 78.906 (78.111)	Acc@5 94.629 (94.424)	
[2022-01-24 06:54:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.992 (2.286)	Loss 0.9049 (0.9247)	Acc@1 78.809 (78.409)	Acc@5 94.238 (94.544)	
[2022-01-24 06:54:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.449 (2.210)	Loss 0.9593 (0.9202)	Acc@1 78.223 (78.520)	Acc@5 93.750 (94.484)	
[2022-01-24 06:54:49 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.614 Acc@5 94.518
[2022-01-24 06:54:49 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.6%
[2022-01-24 06:54:49 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.61%
[2022-01-24 06:55:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][0/1251]	eta 7:34:44 lr 0.000227	time 21.8105 (21.8105)	loss 3.3460 (3.3460)	grad_norm 2.2938 (2.2938)	
[2022-01-24 06:55:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][10/1251]	eta 1:20:59 lr 0.000227	time 1.4944 (3.9159)	loss 2.8422 (3.4777)	grad_norm 1.7365 (1.9594)	
[2022-01-24 06:55:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][20/1251]	eta 1:02:21 lr 0.000227	time 2.2200 (3.0394)	loss 4.0095 (3.4235)	grad_norm 2.0052 (1.9627)	
[2022-01-24 06:56:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][30/1251]	eta 0:55:37 lr 0.000227	time 1.8797 (2.7337)	loss 3.5499 (3.3267)	grad_norm 2.2313 (1.9556)	
[2022-01-24 06:56:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][40/1251]	eta 0:52:52 lr 0.000227	time 3.3960 (2.6197)	loss 3.7319 (3.3739)	grad_norm 1.8911 (1.9700)	
[2022-01-24 06:56:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][50/1251]	eta 0:50:48 lr 0.000227	time 2.3026 (2.5384)	loss 2.4736 (3.3031)	grad_norm 2.0245 (1.9846)	
[2022-01-24 06:57:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][60/1251]	eta 0:49:44 lr 0.000227	time 3.0910 (2.5060)	loss 3.6127 (3.3091)	grad_norm 1.8839 (1.9956)	
[2022-01-24 06:57:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][70/1251]	eta 0:48:19 lr 0.000227	time 1.8671 (2.4554)	loss 2.3901 (3.2698)	grad_norm 1.8324 (1.9842)	
[2022-01-24 06:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][80/1251]	eta 0:47:41 lr 0.000226	time 3.7967 (2.4438)	loss 3.9224 (3.2459)	grad_norm 1.8328 (1.9796)	
[2022-01-24 06:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][90/1251]	eta 0:46:52 lr 0.000226	time 1.6168 (2.4224)	loss 3.3808 (3.2671)	grad_norm 1.9551 (1.9895)	
[2022-01-24 06:58:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][100/1251]	eta 0:46:08 lr 0.000226	time 1.7316 (2.4051)	loss 3.3580 (3.2273)	grad_norm 2.1524 (1.9975)	
[2022-01-24 06:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][110/1251]	eta 0:45:24 lr 0.000226	time 1.8147 (2.3877)	loss 4.1089 (3.2417)	grad_norm 2.1921 (2.0078)	
[2022-01-24 06:59:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][120/1251]	eta 0:45:07 lr 0.000226	time 3.4434 (2.3939)	loss 3.3201 (3.2495)	grad_norm 2.8958 (2.0180)	
[2022-01-24 07:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][130/1251]	eta 0:44:52 lr 0.000226	time 2.7826 (2.4023)	loss 3.3552 (3.2608)	grad_norm 1.8190 (2.0145)	
[2022-01-24 07:00:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][140/1251]	eta 0:44:01 lr 0.000226	time 1.8457 (2.3776)	loss 4.2022 (3.2556)	grad_norm 1.8850 (2.0148)	
[2022-01-24 07:00:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][150/1251]	eta 0:43:12 lr 0.000226	time 1.9279 (2.3548)	loss 2.9508 (3.2536)	grad_norm 2.2352 (2.0193)	
[2022-01-24 07:01:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][160/1251]	eta 0:42:26 lr 0.000226	time 1.9774 (2.3344)	loss 3.2237 (3.2637)	grad_norm 2.1126 (2.0193)	
[2022-01-24 07:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][170/1251]	eta 0:41:50 lr 0.000226	time 2.0093 (2.3224)	loss 3.3185 (3.2721)	grad_norm 2.0363 (2.0173)	
[2022-01-24 07:01:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][180/1251]	eta 0:41:17 lr 0.000226	time 1.9476 (2.3134)	loss 3.1470 (3.2664)	grad_norm 1.9451 (2.0116)	
[2022-01-24 07:02:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][190/1251]	eta 0:40:46 lr 0.000226	time 2.2219 (2.3055)	loss 3.7248 (3.2700)	grad_norm 1.9462 (2.0064)	
[2022-01-24 07:02:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][200/1251]	eta 0:40:17 lr 0.000226	time 2.6652 (2.3006)	loss 3.5587 (3.2862)	grad_norm 1.7524 (2.0030)	
[2022-01-24 07:02:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][210/1251]	eta 0:39:53 lr 0.000226	time 2.4565 (2.2992)	loss 3.8345 (3.2916)	grad_norm 1.7896 (2.0026)	
[2022-01-24 07:03:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][220/1251]	eta 0:39:28 lr 0.000226	time 1.8344 (2.2972)	loss 2.7180 (3.2974)	grad_norm 1.8726 (2.0076)	
[2022-01-24 07:03:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][230/1251]	eta 0:39:13 lr 0.000226	time 3.0786 (2.3054)	loss 2.8040 (3.2968)	grad_norm 2.1104 (2.0098)	
[2022-01-24 07:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][240/1251]	eta 0:38:51 lr 0.000226	time 2.4974 (2.3061)	loss 3.7399 (3.2991)	grad_norm 1.9780 (2.0152)	
[2022-01-24 07:04:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][250/1251]	eta 0:38:18 lr 0.000226	time 1.8684 (2.2965)	loss 2.8113 (3.2905)	grad_norm 1.9271 (2.0156)	
[2022-01-24 07:04:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][260/1251]	eta 0:37:46 lr 0.000226	time 1.9115 (2.2872)	loss 4.1835 (3.2888)	grad_norm 2.2576 (2.0159)	
[2022-01-24 07:05:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][270/1251]	eta 0:37:15 lr 0.000226	time 2.9330 (2.2793)	loss 3.4378 (3.2871)	grad_norm 2.1459 (2.0198)	
[2022-01-24 07:05:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][280/1251]	eta 0:36:46 lr 0.000226	time 2.1757 (2.2723)	loss 3.6888 (3.2826)	grad_norm 2.1149 (2.0171)	
[2022-01-24 07:05:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][290/1251]	eta 0:36:17 lr 0.000226	time 2.1792 (2.2659)	loss 3.4391 (3.2878)	grad_norm 2.0536 (2.0205)	
[2022-01-24 07:06:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][300/1251]	eta 0:35:51 lr 0.000226	time 1.8264 (2.2622)	loss 3.6696 (3.2982)	grad_norm 2.1754 (2.0199)	
[2022-01-24 07:06:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][310/1251]	eta 0:35:26 lr 0.000226	time 2.7890 (2.2594)	loss 3.8435 (3.2973)	grad_norm 1.8913 (2.0165)	
[2022-01-24 07:06:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][320/1251]	eta 0:35:03 lr 0.000226	time 2.2264 (2.2590)	loss 3.0265 (3.2978)	grad_norm 2.0461 (2.0143)	
[2022-01-24 07:07:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][330/1251]	eta 0:34:39 lr 0.000226	time 2.1711 (2.2578)	loss 2.4610 (3.2938)	grad_norm 1.9496 (2.0150)	
[2022-01-24 07:07:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][340/1251]	eta 0:34:18 lr 0.000226	time 2.5039 (2.2600)	loss 3.8561 (3.2940)	grad_norm 1.9487 (2.0165)	
[2022-01-24 07:08:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][350/1251]	eta 0:33:58 lr 0.000226	time 2.7910 (2.2627)	loss 3.1039 (3.2850)	grad_norm 2.0692 (2.0167)	
[2022-01-24 07:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][360/1251]	eta 0:33:40 lr 0.000226	time 2.8009 (2.2681)	loss 3.9755 (3.2864)	grad_norm 1.8795 (2.0176)	
[2022-01-24 07:08:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][370/1251]	eta 0:33:15 lr 0.000226	time 1.9641 (2.2649)	loss 3.6994 (3.2933)	grad_norm 1.8988 (2.0161)	
[2022-01-24 07:09:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][380/1251]	eta 0:32:47 lr 0.000225	time 1.9002 (2.2591)	loss 3.0516 (3.2943)	grad_norm 2.1409 (2.0182)	
[2022-01-24 07:09:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][390/1251]	eta 0:32:15 lr 0.000225	time 1.8085 (2.2476)	loss 3.4645 (3.2976)	grad_norm 2.2398 (2.0195)	
[2022-01-24 07:09:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][400/1251]	eta 0:31:44 lr 0.000225	time 1.9562 (2.2376)	loss 2.8501 (3.2990)	grad_norm 1.8045 (2.0210)	
[2022-01-24 07:10:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][410/1251]	eta 0:31:20 lr 0.000225	time 1.8132 (2.2366)	loss 2.9795 (3.2982)	grad_norm 2.3673 (2.0247)	
[2022-01-24 07:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][420/1251]	eta 0:30:55 lr 0.000225	time 2.0205 (2.2331)	loss 3.0794 (3.3037)	grad_norm 1.7603 (2.0248)	
[2022-01-24 07:10:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][430/1251]	eta 0:30:33 lr 0.000225	time 2.5775 (2.2328)	loss 3.8118 (3.3106)	grad_norm 1.8923 (2.0242)	
[2022-01-24 07:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][440/1251]	eta 0:30:11 lr 0.000225	time 2.1039 (2.2334)	loss 4.0729 (3.3092)	grad_norm 2.0692 (2.0229)	
[2022-01-24 07:11:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][450/1251]	eta 0:29:51 lr 0.000225	time 1.9245 (2.2360)	loss 3.5406 (3.3067)	grad_norm 2.2709 (2.0231)	
[2022-01-24 07:12:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][460/1251]	eta 0:29:28 lr 0.000225	time 1.9034 (2.2361)	loss 2.4011 (3.3040)	grad_norm 1.9137 (2.0209)	
[2022-01-24 07:12:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][470/1251]	eta 0:29:05 lr 0.000225	time 2.0624 (2.2353)	loss 3.5377 (3.3014)	grad_norm 2.2067 (2.0204)	
[2022-01-24 07:12:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][480/1251]	eta 0:28:45 lr 0.000225	time 3.0503 (2.2382)	loss 4.1012 (3.3035)	grad_norm 2.1184 (2.0205)	
[2022-01-24 07:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][490/1251]	eta 0:28:25 lr 0.000225	time 1.7093 (2.2416)	loss 3.5300 (3.3016)	grad_norm 1.7256 (2.0204)	
[2022-01-24 07:13:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][500/1251]	eta 0:28:02 lr 0.000225	time 2.1298 (2.2406)	loss 3.4697 (3.3029)	grad_norm 1.8171 (2.0201)	
[2022-01-24 07:13:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][510/1251]	eta 0:27:37 lr 0.000225	time 2.2802 (2.2366)	loss 3.9583 (3.3037)	grad_norm 1.8786 (2.0187)	
[2022-01-24 07:14:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][520/1251]	eta 0:27:12 lr 0.000225	time 2.2205 (2.2333)	loss 2.8283 (3.3031)	grad_norm 1.9804 (2.0184)	
[2022-01-24 07:14:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][530/1251]	eta 0:26:48 lr 0.000225	time 2.1936 (2.2310)	loss 3.6951 (3.2995)	grad_norm 1.9521 (2.0198)	
[2022-01-24 07:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][540/1251]	eta 0:26:26 lr 0.000225	time 2.3951 (2.2308)	loss 2.7336 (3.2960)	grad_norm 1.9161 (2.0233)	
[2022-01-24 07:15:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][550/1251]	eta 0:26:03 lr 0.000225	time 2.1858 (2.2307)	loss 3.9257 (3.2960)	grad_norm 2.0107 (2.0240)	
[2022-01-24 07:15:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][560/1251]	eta 0:25:41 lr 0.000225	time 2.2206 (2.2307)	loss 2.3756 (3.2938)	grad_norm 2.0447 (2.0244)	
[2022-01-24 07:16:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][570/1251]	eta 0:25:18 lr 0.000225	time 2.4063 (2.2302)	loss 2.8051 (3.2913)	grad_norm 2.3335 (2.0266)	
[2022-01-24 07:16:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][580/1251]	eta 0:24:56 lr 0.000225	time 2.3947 (2.2295)	loss 3.4245 (3.2921)	grad_norm 1.7816 (2.0252)	
[2022-01-24 07:16:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][590/1251]	eta 0:24:32 lr 0.000225	time 1.9484 (2.2269)	loss 2.3318 (3.2906)	grad_norm 1.9548 (2.0255)	
[2022-01-24 07:17:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][600/1251]	eta 0:24:07 lr 0.000225	time 1.9075 (2.2241)	loss 3.7045 (3.2904)	grad_norm 2.0943 (2.0262)	
[2022-01-24 07:17:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][610/1251]	eta 0:23:44 lr 0.000225	time 2.1485 (2.2225)	loss 2.6664 (3.2946)	grad_norm 1.8666 (2.0257)	
[2022-01-24 07:17:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][620/1251]	eta 0:23:23 lr 0.000225	time 2.8496 (2.2235)	loss 2.9285 (3.2935)	grad_norm 1.8745 (2.0266)	
[2022-01-24 07:18:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][630/1251]	eta 0:22:59 lr 0.000225	time 1.9720 (2.2216)	loss 2.9889 (3.2931)	grad_norm 2.0634 (2.0261)	
[2022-01-24 07:18:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][640/1251]	eta 0:22:37 lr 0.000225	time 2.1675 (2.2212)	loss 3.3250 (3.2922)	grad_norm 1.8413 (2.0260)	
[2022-01-24 07:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][650/1251]	eta 0:22:15 lr 0.000225	time 1.5934 (2.2222)	loss 3.2782 (3.2889)	grad_norm 2.1279 (2.0265)	
[2022-01-24 07:19:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][660/1251]	eta 0:21:54 lr 0.000225	time 3.0500 (2.2235)	loss 2.3576 (3.2822)	grad_norm 1.9890 (2.0257)	
[2022-01-24 07:19:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][670/1251]	eta 0:21:30 lr 0.000224	time 1.5398 (2.2212)	loss 3.4070 (3.2813)	grad_norm 2.1566 (2.0269)	
[2022-01-24 07:20:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][680/1251]	eta 0:21:07 lr 0.000224	time 2.3295 (2.2205)	loss 2.6939 (3.2789)	grad_norm 1.7514 (2.0274)	
[2022-01-24 07:20:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][690/1251]	eta 0:20:44 lr 0.000224	time 1.7206 (2.2183)	loss 3.4403 (3.2776)	grad_norm 2.1208 (2.0274)	
[2022-01-24 07:20:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][700/1251]	eta 0:20:22 lr 0.000224	time 2.1811 (2.2188)	loss 4.0187 (3.2796)	grad_norm 2.9185 (2.0273)	
[2022-01-24 07:21:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][710/1251]	eta 0:19:59 lr 0.000224	time 1.7024 (2.2174)	loss 3.4087 (3.2813)	grad_norm 1.8838 (2.0285)	
[2022-01-24 07:21:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][720/1251]	eta 0:19:36 lr 0.000224	time 2.2004 (2.2165)	loss 4.0172 (3.2807)	grad_norm 2.2790 (2.0279)	
[2022-01-24 07:21:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][730/1251]	eta 0:19:14 lr 0.000224	time 1.8615 (2.2150)	loss 4.0861 (3.2790)	grad_norm 2.1571 (2.0278)	
[2022-01-24 07:22:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][740/1251]	eta 0:18:52 lr 0.000224	time 2.1635 (2.2165)	loss 3.7065 (3.2791)	grad_norm 1.7007 (2.0264)	
[2022-01-24 07:22:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][750/1251]	eta 0:18:29 lr 0.000224	time 1.8061 (2.2139)	loss 3.5609 (3.2752)	grad_norm 2.2106 (2.0270)	
[2022-01-24 07:22:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][760/1251]	eta 0:18:06 lr 0.000224	time 1.8098 (2.2128)	loss 2.8140 (3.2773)	grad_norm 1.8431 (2.0268)	
[2022-01-24 07:23:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][770/1251]	eta 0:17:43 lr 0.000224	time 2.6366 (2.2118)	loss 2.5778 (3.2782)	grad_norm 2.1381 (2.0267)	
[2022-01-24 07:23:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][780/1251]	eta 0:17:21 lr 0.000224	time 1.7549 (2.2103)	loss 3.4795 (3.2809)	grad_norm 1.9584 (2.0273)	
[2022-01-24 07:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][790/1251]	eta 0:16:58 lr 0.000224	time 1.9131 (2.2103)	loss 3.6341 (3.2791)	grad_norm 1.8900 (2.0285)	
[2022-01-24 07:24:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][800/1251]	eta 0:16:37 lr 0.000224	time 2.9042 (2.2124)	loss 3.7471 (3.2787)	grad_norm 1.9665 (2.0279)	
[2022-01-24 07:24:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][810/1251]	eta 0:16:15 lr 0.000224	time 2.5867 (2.2113)	loss 3.8850 (3.2797)	grad_norm 2.0993 (2.0271)	
[2022-01-24 07:25:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][820/1251]	eta 0:15:53 lr 0.000224	time 1.8062 (2.2117)	loss 4.1694 (3.2847)	grad_norm 2.1292 (2.0265)	
[2022-01-24 07:25:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][830/1251]	eta 0:15:31 lr 0.000224	time 2.4839 (2.2117)	loss 3.6150 (3.2830)	grad_norm 1.8569 (2.0250)	
[2022-01-24 07:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][840/1251]	eta 0:15:08 lr 0.000224	time 1.8525 (2.2107)	loss 3.0289 (3.2817)	grad_norm 2.1476 (2.0250)	
[2022-01-24 07:26:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][850/1251]	eta 0:14:45 lr 0.000224	time 1.7013 (2.2088)	loss 3.2737 (3.2804)	grad_norm 1.8805 (2.0244)	
[2022-01-24 07:26:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][860/1251]	eta 0:14:22 lr 0.000224	time 2.1763 (2.2071)	loss 3.7031 (3.2811)	grad_norm 1.7829 (2.0231)	
[2022-01-24 07:26:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][870/1251]	eta 0:14:00 lr 0.000224	time 1.5287 (2.2062)	loss 2.9183 (3.2772)	grad_norm 1.8758 (2.0221)	
[2022-01-24 07:27:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][880/1251]	eta 0:13:39 lr 0.000224	time 2.3994 (2.2093)	loss 3.5619 (3.2800)	grad_norm 1.8381 (2.0214)	
[2022-01-24 07:27:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][890/1251]	eta 0:13:17 lr 0.000224	time 1.6570 (2.2095)	loss 3.3458 (3.2792)	grad_norm 2.1830 (2.0208)	
[2022-01-24 07:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][900/1251]	eta 0:12:55 lr 0.000224	time 1.8354 (2.2092)	loss 3.2219 (3.2766)	grad_norm 1.6886 (2.0204)	
[2022-01-24 07:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][910/1251]	eta 0:12:32 lr 0.000224	time 1.8907 (2.2077)	loss 3.7232 (3.2792)	grad_norm 2.5190 (2.0196)	
[2022-01-24 07:28:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][920/1251]	eta 0:12:10 lr 0.000224	time 1.7993 (2.2075)	loss 3.3781 (3.2813)	grad_norm 1.8306 (2.0194)	
[2022-01-24 07:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][930/1251]	eta 0:11:47 lr 0.000224	time 1.9357 (2.2049)	loss 2.7779 (3.2816)	grad_norm 2.0410 (2.0190)	
[2022-01-24 07:29:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][940/1251]	eta 0:11:25 lr 0.000224	time 1.9359 (2.2038)	loss 2.7855 (3.2808)	grad_norm 2.0668 (2.0198)	
[2022-01-24 07:29:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][950/1251]	eta 0:11:03 lr 0.000224	time 2.7565 (2.2038)	loss 3.8007 (3.2793)	grad_norm 1.8433 (2.0228)	
[2022-01-24 07:30:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][960/1251]	eta 0:10:41 lr 0.000223	time 2.2143 (2.2049)	loss 3.4470 (3.2812)	grad_norm 2.0227 (2.0225)	
[2022-01-24 07:30:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][970/1251]	eta 0:10:19 lr 0.000223	time 1.8602 (2.2048)	loss 3.4775 (3.2805)	grad_norm 2.0392 (2.0227)	
[2022-01-24 07:30:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][980/1251]	eta 0:09:57 lr 0.000223	time 2.4541 (2.2058)	loss 3.7468 (3.2801)	grad_norm 1.7248 (2.0230)	
[2022-01-24 07:31:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][990/1251]	eta 0:09:35 lr 0.000223	time 2.3897 (2.2058)	loss 3.6832 (3.2829)	grad_norm 2.1660 (2.0234)	
[2022-01-24 07:31:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1000/1251]	eta 0:09:13 lr 0.000223	time 1.8648 (2.2045)	loss 3.5819 (3.2834)	grad_norm 1.8079 (2.0233)	
[2022-01-24 07:31:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1010/1251]	eta 0:08:51 lr 0.000223	time 1.9783 (2.2035)	loss 3.4563 (3.2856)	grad_norm 1.6402 (2.0236)	
[2022-01-24 07:32:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1020/1251]	eta 0:08:29 lr 0.000223	time 2.8097 (2.2041)	loss 2.5400 (3.2857)	grad_norm 2.0154 (2.0241)	
[2022-01-24 07:32:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1030/1251]	eta 0:08:07 lr 0.000223	time 2.2282 (2.2041)	loss 3.1824 (3.2856)	grad_norm 1.9023 (2.0241)	
[2022-01-24 07:33:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1040/1251]	eta 0:07:45 lr 0.000223	time 2.5319 (2.2052)	loss 3.0971 (3.2843)	grad_norm 1.9550 (2.0236)	
[2022-01-24 07:33:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1050/1251]	eta 0:07:23 lr 0.000223	time 1.6382 (2.2050)	loss 3.6361 (3.2846)	grad_norm 2.0744 (2.0233)	
[2022-01-24 07:33:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1060/1251]	eta 0:07:01 lr 0.000223	time 3.1240 (2.2052)	loss 3.2377 (3.2834)	grad_norm 1.9385 (2.0226)	
[2022-01-24 07:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1070/1251]	eta 0:06:38 lr 0.000223	time 1.6156 (2.2043)	loss 3.2888 (3.2856)	grad_norm 1.9412 (2.0223)	
[2022-01-24 07:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1080/1251]	eta 0:06:17 lr 0.000223	time 2.7679 (2.2050)	loss 3.9100 (3.2900)	grad_norm 1.8880 (2.0215)	
[2022-01-24 07:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1090/1251]	eta 0:05:54 lr 0.000223	time 2.1992 (2.2041)	loss 3.4948 (3.2902)	grad_norm 1.8468 (2.0206)	
[2022-01-24 07:35:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1100/1251]	eta 0:05:32 lr 0.000223	time 1.9277 (2.2028)	loss 4.0045 (3.2915)	grad_norm 1.9738 (2.0196)	
[2022-01-24 07:35:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1110/1251]	eta 0:05:10 lr 0.000223	time 1.8933 (2.2011)	loss 3.1353 (3.2915)	grad_norm 1.9392 (2.0192)	
[2022-01-24 07:35:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1120/1251]	eta 0:04:48 lr 0.000223	time 1.8635 (2.2002)	loss 2.8652 (3.2906)	grad_norm 1.7607 (2.0176)	
[2022-01-24 07:36:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1130/1251]	eta 0:04:26 lr 0.000223	time 2.5200 (2.1999)	loss 2.0085 (3.2901)	grad_norm 1.8424 (2.0172)	
[2022-01-24 07:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1140/1251]	eta 0:04:04 lr 0.000223	time 1.4562 (2.2002)	loss 2.5217 (3.2876)	grad_norm 1.6897 (2.0167)	
[2022-01-24 07:37:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1150/1251]	eta 0:03:42 lr 0.000223	time 1.7918 (2.2001)	loss 3.4703 (3.2860)	grad_norm 2.1020 (2.0172)	
[2022-01-24 07:37:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1160/1251]	eta 0:03:20 lr 0.000223	time 2.1760 (2.2009)	loss 2.8375 (3.2852)	grad_norm 1.8396 (2.0174)	
[2022-01-24 07:37:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1170/1251]	eta 0:02:58 lr 0.000223	time 2.7881 (2.2017)	loss 3.1254 (3.2856)	grad_norm 1.8375 (2.0179)	
[2022-01-24 07:38:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1180/1251]	eta 0:02:36 lr 0.000223	time 1.8519 (2.2016)	loss 3.3491 (3.2855)	grad_norm 1.8957 (2.0185)	
[2022-01-24 07:38:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1190/1251]	eta 0:02:14 lr 0.000223	time 1.5734 (2.2010)	loss 3.2465 (3.2863)	grad_norm 1.9410 (2.0187)	
[2022-01-24 07:38:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1200/1251]	eta 0:01:52 lr 0.000223	time 1.8091 (2.2000)	loss 2.6923 (3.2847)	grad_norm 2.2934 (2.0183)	
[2022-01-24 07:39:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1210/1251]	eta 0:01:30 lr 0.000223	time 2.9624 (2.1998)	loss 3.1139 (3.2864)	grad_norm 1.7419 (2.0181)	
[2022-01-24 07:39:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1220/1251]	eta 0:01:08 lr 0.000223	time 2.1541 (2.2001)	loss 3.5810 (3.2848)	grad_norm 2.3277 (2.0184)	
[2022-01-24 07:39:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1230/1251]	eta 0:00:46 lr 0.000223	time 1.6810 (2.2000)	loss 3.7585 (3.2838)	grad_norm 1.8337 (2.0189)	
[2022-01-24 07:40:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1240/1251]	eta 0:00:24 lr 0.000223	time 1.2384 (2.1987)	loss 3.3424 (3.2847)	grad_norm 1.9074 (2.0192)	
[2022-01-24 07:40:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [207/300][1250/1251]	eta 0:00:02 lr 0.000223	time 1.1967 (2.1938)	loss 3.3251 (3.2846)	grad_norm 1.8231 (2.0192)	
[2022-01-24 07:40:34 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 207 training takes 0:45:44
[2022-01-24 07:40:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 20.534 (20.534)	Loss 0.8590 (0.8590)	Acc@1 80.176 (80.176)	Acc@5 95.703 (95.703)	
[2022-01-24 07:41:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.670 (3.210)	Loss 0.9491 (0.9200)	Acc@1 77.734 (78.382)	Acc@5 94.531 (94.434)	
[2022-01-24 07:41:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.661 (2.529)	Loss 0.8747 (0.8923)	Acc@1 78.906 (78.818)	Acc@5 94.824 (94.717)	
[2022-01-24 07:41:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.917 (2.298)	Loss 0.7907 (0.8913)	Acc@1 80.273 (78.897)	Acc@5 95.996 (94.686)	
[2022-01-24 07:42:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.014 (2.232)	Loss 0.8829 (0.8988)	Acc@1 79.004 (78.792)	Acc@5 94.629 (94.536)	
[2022-01-24 07:42:13 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.808 Acc@5 94.604
[2022-01-24 07:42:13 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.8%
[2022-01-24 07:42:13 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.81%
[2022-01-24 07:42:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][0/1251]	eta 7:17:56 lr 0.000222	time 21.0041 (21.0041)	loss 3.9569 (3.9569)	grad_norm 2.1016 (2.1016)	
[2022-01-24 07:42:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][10/1251]	eta 1:24:16 lr 0.000222	time 1.8692 (4.0745)	loss 2.9819 (3.4589)	grad_norm 2.0838 (2.0716)	
[2022-01-24 07:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][20/1251]	eta 1:05:51 lr 0.000222	time 2.2744 (3.2104)	loss 3.8610 (3.2581)	grad_norm 1.6508 (2.0421)	
[2022-01-24 07:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][30/1251]	eta 0:58:32 lr 0.000222	time 1.7387 (2.8764)	loss 3.7835 (3.2777)	grad_norm 2.2736 (2.0722)	
[2022-01-24 07:44:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][40/1251]	eta 0:55:15 lr 0.000222	time 3.6652 (2.7381)	loss 2.2496 (3.2487)	grad_norm 2.0946 (2.1132)	
[2022-01-24 07:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][50/1251]	eta 0:53:08 lr 0.000222	time 2.0855 (2.6548)	loss 3.6491 (3.2624)	grad_norm 2.0170 (2.1030)	
[2022-01-24 07:44:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][60/1251]	eta 0:51:00 lr 0.000222	time 1.8880 (2.5699)	loss 3.4680 (3.2522)	grad_norm 1.8681 (2.0866)	
[2022-01-24 07:45:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][70/1251]	eta 0:49:42 lr 0.000222	time 1.8643 (2.5252)	loss 3.6221 (3.2884)	grad_norm 2.1301 (2.0931)	
[2022-01-24 07:45:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][80/1251]	eta 0:48:44 lr 0.000222	time 3.3725 (2.4971)	loss 3.1874 (3.2959)	grad_norm 2.3725 (2.1016)	
[2022-01-24 07:45:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][90/1251]	eta 0:47:49 lr 0.000222	time 3.3937 (2.4713)	loss 3.5924 (3.2643)	grad_norm 1.7361 (2.0869)	
[2022-01-24 07:46:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][100/1251]	eta 0:46:51 lr 0.000222	time 1.9264 (2.4431)	loss 3.0121 (3.2697)	grad_norm 2.0156 (2.0915)	
[2022-01-24 07:46:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][110/1251]	eta 0:45:47 lr 0.000222	time 2.1719 (2.4079)	loss 2.8707 (3.2688)	grad_norm 1.8206 (2.0808)	
[2022-01-24 07:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][120/1251]	eta 0:45:01 lr 0.000222	time 2.3446 (2.3882)	loss 3.7580 (3.2650)	grad_norm 2.3515 (2.0776)	
[2022-01-24 07:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][130/1251]	eta 0:44:18 lr 0.000222	time 2.4258 (2.3716)	loss 3.2230 (3.2640)	grad_norm 2.2808 (2.0682)	
[2022-01-24 07:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][140/1251]	eta 0:43:42 lr 0.000222	time 2.1252 (2.3602)	loss 2.7687 (3.2713)	grad_norm 2.0780 (2.0618)	
[2022-01-24 07:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][150/1251]	eta 0:43:01 lr 0.000222	time 1.5850 (2.3446)	loss 3.4138 (3.2611)	grad_norm 1.9050 (2.0581)	
[2022-01-24 07:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][160/1251]	eta 0:42:25 lr 0.000222	time 2.9428 (2.3335)	loss 3.6288 (3.2725)	grad_norm 1.8448 (2.0589)	
[2022-01-24 07:48:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][170/1251]	eta 0:41:52 lr 0.000222	time 2.1490 (2.3240)	loss 2.7290 (3.2785)	grad_norm 1.9318 (2.0551)	
[2022-01-24 07:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][180/1251]	eta 0:41:19 lr 0.000222	time 1.9650 (2.3147)	loss 3.7747 (3.2852)	grad_norm 2.1615 (2.0545)	
[2022-01-24 07:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][190/1251]	eta 0:40:49 lr 0.000222	time 1.6580 (2.3086)	loss 3.5839 (3.2781)	grad_norm 1.8626 (2.0592)	
[2022-01-24 07:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][200/1251]	eta 0:40:15 lr 0.000222	time 1.8882 (2.2980)	loss 2.3115 (3.2736)	grad_norm 2.0091 (2.0543)	
[2022-01-24 07:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][210/1251]	eta 0:39:54 lr 0.000222	time 2.4085 (2.2998)	loss 3.5719 (3.2644)	grad_norm 1.9113 (2.0515)	
[2022-01-24 07:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][220/1251]	eta 0:39:27 lr 0.000222	time 1.9140 (2.2962)	loss 2.8671 (3.2649)	grad_norm 1.9277 (2.0471)	
[2022-01-24 07:51:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][230/1251]	eta 0:39:02 lr 0.000222	time 2.5264 (2.2947)	loss 3.3558 (3.2646)	grad_norm 2.1097 (2.0492)	
[2022-01-24 07:51:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][240/1251]	eta 0:38:32 lr 0.000222	time 2.0155 (2.2870)	loss 3.3237 (3.2639)	grad_norm 2.0892 (2.0504)	
[2022-01-24 07:51:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][250/1251]	eta 0:38:07 lr 0.000222	time 1.8583 (2.2854)	loss 3.0305 (3.2427)	grad_norm 2.1921 (2.0462)	
[2022-01-24 07:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][260/1251]	eta 0:37:30 lr 0.000222	time 1.9774 (2.2712)	loss 2.9364 (3.2411)	grad_norm 1.8937 (2.0521)	
[2022-01-24 07:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][270/1251]	eta 0:37:03 lr 0.000222	time 1.7739 (2.2667)	loss 3.2466 (3.2464)	grad_norm 1.9791 (2.0539)	
[2022-01-24 07:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][280/1251]	eta 0:36:34 lr 0.000222	time 1.9428 (2.2606)	loss 3.6466 (3.2520)	grad_norm 1.8515 (2.0502)	
[2022-01-24 07:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][290/1251]	eta 0:36:13 lr 0.000222	time 1.9326 (2.2614)	loss 2.4692 (3.2557)	grad_norm 2.4836 (2.0500)	
[2022-01-24 07:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][300/1251]	eta 0:35:47 lr 0.000221	time 2.7919 (2.2582)	loss 2.4328 (3.2578)	grad_norm 1.8864 (2.0473)	
[2022-01-24 07:53:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][310/1251]	eta 0:35:26 lr 0.000221	time 2.4228 (2.2603)	loss 3.8731 (3.2593)	grad_norm 2.0520 (2.0468)	
[2022-01-24 07:54:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][320/1251]	eta 0:35:03 lr 0.000221	time 1.9851 (2.2597)	loss 3.8344 (3.2629)	grad_norm 2.3206 (2.0514)	
[2022-01-24 07:54:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][330/1251]	eta 0:34:39 lr 0.000221	time 2.5127 (2.2581)	loss 3.1445 (3.2644)	grad_norm 2.2181 (2.0510)	
[2022-01-24 07:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][340/1251]	eta 0:34:10 lr 0.000221	time 2.1695 (2.2512)	loss 2.1826 (3.2626)	grad_norm 1.7258 (2.0509)	
[2022-01-24 07:55:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][350/1251]	eta 0:33:43 lr 0.000221	time 2.8086 (2.2459)	loss 3.6027 (3.2677)	grad_norm 1.9772 (2.0555)	
[2022-01-24 07:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][360/1251]	eta 0:33:16 lr 0.000221	time 1.7859 (2.2406)	loss 3.7518 (3.2625)	grad_norm 1.7727 (2.0565)	
[2022-01-24 07:56:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][370/1251]	eta 0:32:54 lr 0.000221	time 2.6475 (2.2413)	loss 2.2669 (3.2599)	grad_norm 2.5369 (2.0618)	
[2022-01-24 07:56:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][380/1251]	eta 0:32:29 lr 0.000221	time 2.1111 (2.2378)	loss 3.4220 (3.2682)	grad_norm 1.9560 (2.0637)	
[2022-01-24 07:56:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][390/1251]	eta 0:32:10 lr 0.000221	time 3.2200 (2.2423)	loss 2.8733 (3.2627)	grad_norm 1.9756 (2.0634)	
[2022-01-24 07:57:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][400/1251]	eta 0:31:51 lr 0.000221	time 2.9120 (2.2465)	loss 2.9979 (3.2606)	grad_norm 1.9559 (2.0613)	
[2022-01-24 07:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][410/1251]	eta 0:31:30 lr 0.000221	time 2.1189 (2.2474)	loss 3.5435 (3.2612)	grad_norm 2.4299 (2.0611)	
[2022-01-24 07:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][420/1251]	eta 0:31:03 lr 0.000221	time 2.0478 (2.2430)	loss 3.7285 (3.2616)	grad_norm 2.2129 (2.0599)	
[2022-01-24 07:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][430/1251]	eta 0:30:39 lr 0.000221	time 3.5080 (2.2410)	loss 3.4284 (3.2581)	grad_norm 2.1935 (2.0596)	
[2022-01-24 07:58:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][440/1251]	eta 0:30:12 lr 0.000221	time 2.2339 (2.2354)	loss 3.1688 (3.2584)	grad_norm 1.9010 (2.0585)	
[2022-01-24 07:58:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][450/1251]	eta 0:29:46 lr 0.000221	time 1.9279 (2.2303)	loss 4.0626 (3.2615)	grad_norm 2.1887 (2.0576)	
[2022-01-24 07:59:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][460/1251]	eta 0:29:23 lr 0.000221	time 2.5312 (2.2300)	loss 3.1959 (3.2645)	grad_norm 1.8842 (2.0586)	
[2022-01-24 07:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][470/1251]	eta 0:29:04 lr 0.000221	time 3.0035 (2.2332)	loss 3.5810 (3.2640)	grad_norm 1.8943 (2.0591)	
[2022-01-24 08:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][480/1251]	eta 0:28:39 lr 0.000221	time 1.5762 (2.2300)	loss 3.3834 (3.2633)	grad_norm 2.2346 (2.0589)	
[2022-01-24 08:00:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][490/1251]	eta 0:28:13 lr 0.000221	time 1.6746 (2.2252)	loss 3.4710 (3.2672)	grad_norm 1.8504 (2.0599)	
[2022-01-24 08:00:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][500/1251]	eta 0:27:51 lr 0.000221	time 2.0997 (2.2255)	loss 3.5982 (3.2663)	grad_norm 1.8401 (2.0608)	
[2022-01-24 08:01:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][510/1251]	eta 0:27:26 lr 0.000221	time 2.0709 (2.2225)	loss 3.1363 (3.2690)	grad_norm 2.0717 (2.0585)	
[2022-01-24 08:01:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][520/1251]	eta 0:27:03 lr 0.000221	time 1.8413 (2.2209)	loss 3.5698 (3.2712)	grad_norm 2.1528 (2.0594)	
[2022-01-24 08:01:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][530/1251]	eta 0:26:41 lr 0.000221	time 1.8022 (2.2206)	loss 2.1915 (3.2673)	grad_norm 1.7825 (2.0608)	
[2022-01-24 08:02:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][540/1251]	eta 0:26:19 lr 0.000221	time 1.7934 (2.2215)	loss 3.2156 (3.2707)	grad_norm 1.9326 (2.0628)	
[2022-01-24 08:02:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][550/1251]	eta 0:25:56 lr 0.000221	time 1.9047 (2.2209)	loss 3.7765 (3.2660)	grad_norm 2.0044 (2.0629)	
[2022-01-24 08:02:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][560/1251]	eta 0:25:35 lr 0.000221	time 2.0561 (2.2223)	loss 3.1854 (3.2674)	grad_norm 2.0115 (2.0641)	
[2022-01-24 08:03:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][570/1251]	eta 0:25:14 lr 0.000221	time 1.4792 (2.2237)	loss 3.6646 (3.2667)	grad_norm 2.0804 (2.0651)	
[2022-01-24 08:03:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][580/1251]	eta 0:24:52 lr 0.000221	time 1.5493 (2.2240)	loss 3.5747 (3.2667)	grad_norm 1.9864 (2.0638)	
[2022-01-24 08:04:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][590/1251]	eta 0:24:28 lr 0.000220	time 2.2038 (2.2221)	loss 3.3621 (3.2648)	grad_norm 2.0078 (2.0619)	
[2022-01-24 08:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][600/1251]	eta 0:24:05 lr 0.000220	time 1.7945 (2.2205)	loss 3.6203 (3.2679)	grad_norm 1.8378 (2.0614)	
[2022-01-24 08:04:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][610/1251]	eta 0:23:42 lr 0.000220	time 2.4978 (2.2197)	loss 3.4673 (3.2665)	grad_norm 1.8705 (2.0603)	
[2022-01-24 08:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][620/1251]	eta 0:23:19 lr 0.000220	time 2.2220 (2.2186)	loss 3.6948 (3.2695)	grad_norm 1.8677 (2.0629)	
[2022-01-24 08:05:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][630/1251]	eta 0:22:56 lr 0.000220	time 1.9123 (2.2161)	loss 3.1113 (3.2659)	grad_norm 2.3824 (2.0622)	
[2022-01-24 08:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][640/1251]	eta 0:22:32 lr 0.000220	time 1.8566 (2.2128)	loss 2.8349 (3.2677)	grad_norm 1.7157 (2.0599)	
[2022-01-24 08:06:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][650/1251]	eta 0:22:09 lr 0.000220	time 3.0639 (2.2130)	loss 3.6067 (3.2668)	grad_norm 1.7821 (2.0578)	
[2022-01-24 08:06:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][660/1251]	eta 0:21:47 lr 0.000220	time 2.2266 (2.2123)	loss 3.3846 (3.2644)	grad_norm 1.7819 (2.0561)	
[2022-01-24 08:06:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][670/1251]	eta 0:21:25 lr 0.000220	time 2.0370 (2.2132)	loss 3.4261 (3.2690)	grad_norm 1.9493 (2.0558)	
[2022-01-24 08:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][680/1251]	eta 0:21:03 lr 0.000220	time 1.5617 (2.2128)	loss 3.6297 (3.2680)	grad_norm 2.0339 (2.0554)	
[2022-01-24 08:07:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][690/1251]	eta 0:20:41 lr 0.000220	time 2.4894 (2.2136)	loss 3.5529 (3.2667)	grad_norm 2.0847 (2.0540)	
[2022-01-24 08:08:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][700/1251]	eta 0:20:19 lr 0.000220	time 2.3715 (2.2136)	loss 3.9014 (3.2708)	grad_norm 2.0777 (2.0532)	
[2022-01-24 08:08:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][710/1251]	eta 0:19:56 lr 0.000220	time 2.0267 (2.2119)	loss 3.2838 (3.2703)	grad_norm 1.9865 (2.0524)	
[2022-01-24 08:08:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][720/1251]	eta 0:19:33 lr 0.000220	time 1.9572 (2.2104)	loss 2.6549 (3.2678)	grad_norm 2.1130 (2.0524)	
[2022-01-24 08:09:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][730/1251]	eta 0:19:11 lr 0.000220	time 2.1882 (2.2096)	loss 3.7061 (3.2635)	grad_norm 2.1248 (2.0532)	
[2022-01-24 08:09:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][740/1251]	eta 0:18:49 lr 0.000220	time 2.1673 (2.2099)	loss 3.9038 (3.2626)	grad_norm 2.0973 (2.0532)	
[2022-01-24 08:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][750/1251]	eta 0:18:28 lr 0.000220	time 2.1651 (2.2130)	loss 3.8960 (3.2619)	grad_norm 1.9275 (2.0531)	
[2022-01-24 08:10:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][760/1251]	eta 0:18:06 lr 0.000220	time 1.8414 (2.2134)	loss 3.7292 (3.2643)	grad_norm 2.0093 (2.0546)	
[2022-01-24 08:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][770/1251]	eta 0:17:43 lr 0.000220	time 1.9565 (2.2103)	loss 3.0593 (3.2652)	grad_norm 1.9598 (2.0551)	
[2022-01-24 08:10:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][780/1251]	eta 0:17:19 lr 0.000220	time 1.6790 (2.2074)	loss 3.9026 (3.2650)	grad_norm 2.4492 (2.0570)	
[2022-01-24 08:11:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][790/1251]	eta 0:16:56 lr 0.000220	time 1.9316 (2.2051)	loss 3.4958 (3.2635)	grad_norm 1.9241 (2.0577)	
[2022-01-24 08:11:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][800/1251]	eta 0:16:33 lr 0.000220	time 1.7885 (2.2026)	loss 2.7070 (3.2652)	grad_norm 1.9688 (2.0587)	
[2022-01-24 08:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][810/1251]	eta 0:16:11 lr 0.000220	time 2.2302 (2.2023)	loss 3.1066 (3.2647)	grad_norm 2.4594 (2.0613)	
[2022-01-24 08:12:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][820/1251]	eta 0:15:48 lr 0.000220	time 1.9312 (2.2016)	loss 3.7392 (3.2637)	grad_norm 1.9136 (2.0602)	
[2022-01-24 08:12:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][830/1251]	eta 0:15:26 lr 0.000220	time 2.2109 (2.2019)	loss 2.2173 (3.2640)	grad_norm 2.0337 (2.0593)	
[2022-01-24 08:13:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][840/1251]	eta 0:15:05 lr 0.000220	time 2.5265 (2.2034)	loss 3.2508 (3.2638)	grad_norm 1.7262 (2.0585)	
[2022-01-24 08:13:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][850/1251]	eta 0:14:44 lr 0.000220	time 2.4685 (2.2061)	loss 3.5488 (3.2651)	grad_norm 2.3371 (2.0590)	
[2022-01-24 08:13:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][860/1251]	eta 0:14:23 lr 0.000220	time 2.5731 (2.2080)	loss 3.6753 (3.2629)	grad_norm 1.9473 (2.0581)	
[2022-01-24 08:14:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][870/1251]	eta 0:14:01 lr 0.000220	time 1.8233 (2.2074)	loss 2.7528 (3.2593)	grad_norm 1.7843 (2.0557)	
[2022-01-24 08:14:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][880/1251]	eta 0:13:38 lr 0.000220	time 2.1024 (2.2053)	loss 2.5842 (3.2605)	grad_norm 1.7810 (2.0548)	
[2022-01-24 08:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][890/1251]	eta 0:13:15 lr 0.000219	time 1.9133 (2.2031)	loss 3.6026 (3.2616)	grad_norm 1.7571 (2.0533)	
[2022-01-24 08:15:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][900/1251]	eta 0:12:52 lr 0.000219	time 2.0714 (2.2011)	loss 3.7869 (3.2627)	grad_norm 2.1300 (2.0545)	
[2022-01-24 08:15:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][910/1251]	eta 0:12:30 lr 0.000219	time 2.1806 (2.1999)	loss 3.8330 (3.2617)	grad_norm 2.2721 (2.0551)	
[2022-01-24 08:16:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][920/1251]	eta 0:12:08 lr 0.000219	time 2.7479 (2.2006)	loss 3.5016 (3.2655)	grad_norm 2.1960 (2.0553)	
[2022-01-24 08:16:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][930/1251]	eta 0:11:46 lr 0.000219	time 2.0147 (2.2012)	loss 3.6006 (3.2662)	grad_norm 1.8767 (2.0554)	
[2022-01-24 08:16:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][940/1251]	eta 0:11:24 lr 0.000219	time 1.9481 (2.2022)	loss 3.6996 (3.2653)	grad_norm 1.9541 (2.0555)	
[2022-01-24 08:17:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][950/1251]	eta 0:11:02 lr 0.000219	time 2.1872 (2.2020)	loss 3.2384 (3.2650)	grad_norm 1.9080 (2.0547)	
[2022-01-24 08:17:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][960/1251]	eta 0:10:40 lr 0.000219	time 2.4337 (2.2017)	loss 3.2467 (3.2655)	grad_norm 2.3945 (2.0555)	
[2022-01-24 08:17:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][970/1251]	eta 0:10:18 lr 0.000219	time 1.9605 (2.2014)	loss 3.8205 (3.2674)	grad_norm 2.2876 (2.0554)	
[2022-01-24 08:18:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][980/1251]	eta 0:09:56 lr 0.000219	time 2.1740 (2.2014)	loss 2.4984 (3.2642)	grad_norm 1.8542 (2.0554)	
[2022-01-24 08:18:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][990/1251]	eta 0:09:34 lr 0.000219	time 2.4057 (2.2010)	loss 3.2927 (3.2642)	grad_norm 2.0177 (2.0563)	
[2022-01-24 08:18:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1000/1251]	eta 0:09:12 lr 0.000219	time 2.3974 (2.1998)	loss 3.9061 (3.2659)	grad_norm 2.0772 (2.0560)	
[2022-01-24 08:19:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1010/1251]	eta 0:08:49 lr 0.000219	time 2.6317 (2.1988)	loss 4.0423 (3.2669)	grad_norm 2.0270 (2.0558)	
[2022-01-24 08:19:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1020/1251]	eta 0:08:27 lr 0.000219	time 1.9424 (2.1988)	loss 3.2413 (3.2670)	grad_norm 2.4416 (2.0553)	
[2022-01-24 08:20:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1030/1251]	eta 0:08:06 lr 0.000219	time 2.4817 (2.2000)	loss 3.3607 (3.2672)	grad_norm 2.1500 (2.0566)	
[2022-01-24 08:20:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1040/1251]	eta 0:07:44 lr 0.000219	time 3.0869 (2.2026)	loss 3.7118 (3.2690)	grad_norm 2.0964 (2.0559)	
[2022-01-24 08:20:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1050/1251]	eta 0:07:22 lr 0.000219	time 1.9394 (2.2023)	loss 3.6581 (3.2683)	grad_norm 2.2498 (2.0553)	
[2022-01-24 08:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1060/1251]	eta 0:07:00 lr 0.000219	time 2.1202 (2.2005)	loss 3.7246 (3.2695)	grad_norm 1.7720 (2.0546)	
[2022-01-24 08:21:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1070/1251]	eta 0:06:37 lr 0.000219	time 2.5127 (2.1987)	loss 3.2211 (3.2689)	grad_norm 1.7854 (2.0530)	
[2022-01-24 08:21:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1080/1251]	eta 0:06:15 lr 0.000219	time 2.2324 (2.1969)	loss 3.0548 (3.2672)	grad_norm 2.0027 (2.0522)	
[2022-01-24 08:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1090/1251]	eta 0:05:53 lr 0.000219	time 2.2507 (2.1962)	loss 2.3207 (3.2680)	grad_norm 2.0877 (2.0518)	
[2022-01-24 08:22:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1100/1251]	eta 0:05:31 lr 0.000219	time 2.5715 (2.1972)	loss 2.2261 (3.2684)	grad_norm 2.2022 (2.0506)	
[2022-01-24 08:22:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1110/1251]	eta 0:05:09 lr 0.000219	time 2.5579 (2.1978)	loss 2.6870 (3.2669)	grad_norm 2.1863 (2.0505)	
[2022-01-24 08:23:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1120/1251]	eta 0:04:48 lr 0.000219	time 2.7379 (2.1992)	loss 3.3929 (3.2692)	grad_norm 2.0109 (2.0500)	
[2022-01-24 08:23:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1130/1251]	eta 0:04:26 lr 0.000219	time 2.2393 (2.1998)	loss 3.5425 (3.2707)	grad_norm 2.0457 (2.0498)	
[2022-01-24 08:24:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1140/1251]	eta 0:04:04 lr 0.000219	time 2.6950 (2.2001)	loss 3.6691 (3.2713)	grad_norm 2.2389 (2.0505)	
[2022-01-24 08:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1150/1251]	eta 0:03:42 lr 0.000219	time 2.8239 (2.2013)	loss 2.8723 (3.2691)	grad_norm 2.1486 (2.0523)	
[2022-01-24 08:24:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1160/1251]	eta 0:03:20 lr 0.000219	time 1.6993 (2.1986)	loss 3.5428 (3.2693)	grad_norm 2.2053 (2.0530)	
[2022-01-24 08:25:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1170/1251]	eta 0:02:57 lr 0.000219	time 1.8668 (2.1975)	loss 3.1658 (3.2684)	grad_norm 1.7036 (2.0527)	
[2022-01-24 08:25:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1180/1251]	eta 0:02:36 lr 0.000218	time 2.1613 (2.1973)	loss 2.8639 (3.2680)	grad_norm 2.0393 (2.0525)	
[2022-01-24 08:25:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1190/1251]	eta 0:02:14 lr 0.000218	time 3.0433 (2.1972)	loss 3.3417 (3.2695)	grad_norm 2.4693 (2.0545)	
[2022-01-24 08:26:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1200/1251]	eta 0:01:52 lr 0.000218	time 2.4433 (2.1969)	loss 3.0707 (3.2703)	grad_norm 1.8125 (2.0544)	
[2022-01-24 08:26:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1210/1251]	eta 0:01:30 lr 0.000218	time 2.0446 (2.1965)	loss 3.4916 (3.2718)	grad_norm 2.1800 (2.0536)	
[2022-01-24 08:26:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1220/1251]	eta 0:01:08 lr 0.000218	time 1.9818 (2.1960)	loss 3.9471 (3.2725)	grad_norm 1.9239 (2.0529)	
[2022-01-24 08:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1230/1251]	eta 0:00:46 lr 0.000218	time 2.4788 (2.1961)	loss 2.9525 (3.2738)	grad_norm 2.3019 (2.0539)	
[2022-01-24 08:27:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1240/1251]	eta 0:00:24 lr 0.000218	time 2.3322 (2.1961)	loss 2.8130 (3.2724)	grad_norm 1.8595 (2.0537)	
[2022-01-24 08:27:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [208/300][1250/1251]	eta 0:00:02 lr 0.000218	time 1.1833 (2.1903)	loss 2.8683 (3.2713)	grad_norm 1.8099 (2.0541)	
[2022-01-24 08:27:53 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 208 training takes 0:45:40
[2022-01-24 08:28:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.112 (19.112)	Loss 0.9073 (0.9073)	Acc@1 78.125 (78.125)	Acc@5 94.727 (94.727)	
[2022-01-24 08:28:32 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.188 (3.561)	Loss 0.9049 (0.8996)	Acc@1 78.320 (78.427)	Acc@5 94.238 (94.877)	
[2022-01-24 08:28:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.310 (2.497)	Loss 0.8134 (0.8936)	Acc@1 79.395 (78.711)	Acc@5 96.387 (94.759)	
[2022-01-24 08:29:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.620 (2.274)	Loss 0.9747 (0.8982)	Acc@1 77.051 (78.648)	Acc@5 93.457 (94.623)	
[2022-01-24 08:29:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.421 (2.183)	Loss 0.8785 (0.8979)	Acc@1 78.809 (78.701)	Acc@5 95.508 (94.641)	
[2022-01-24 08:29:29 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.674 Acc@5 94.590
[2022-01-24 08:29:29 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.7%
[2022-01-24 08:29:29 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.81%
[2022-01-24 08:29:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][0/1251]	eta 7:27:49 lr 0.000218	time 21.4782 (21.4782)	loss 2.9806 (2.9806)	grad_norm 2.2072 (2.2072)	
[2022-01-24 08:30:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][10/1251]	eta 1:22:50 lr 0.000218	time 1.5293 (4.0054)	loss 3.3348 (3.2154)	grad_norm 1.9479 (2.0394)	
[2022-01-24 08:30:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][20/1251]	eta 1:06:09 lr 0.000218	time 1.3653 (3.2243)	loss 3.8241 (3.2811)	grad_norm 1.8992 (2.0655)	
[2022-01-24 08:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][30/1251]	eta 0:58:35 lr 0.000218	time 1.6533 (2.8794)	loss 3.2919 (3.2510)	grad_norm 2.3578 (2.1056)	
[2022-01-24 08:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][40/1251]	eta 0:54:53 lr 0.000218	time 2.9524 (2.7199)	loss 2.8269 (3.2573)	grad_norm 2.0271 (2.1399)	
[2022-01-24 08:31:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][50/1251]	eta 0:53:07 lr 0.000218	time 1.7750 (2.6541)	loss 3.2612 (3.2989)	grad_norm 1.9160 (2.1020)	
[2022-01-24 08:32:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][60/1251]	eta 0:51:39 lr 0.000218	time 1.6325 (2.6024)	loss 3.7124 (3.3060)	grad_norm 1.9457 (2.0842)	
[2022-01-24 08:32:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][70/1251]	eta 0:49:44 lr 0.000218	time 1.6778 (2.5271)	loss 2.7693 (3.3052)	grad_norm 2.0583 (2.0960)	
[2022-01-24 08:32:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][80/1251]	eta 0:48:25 lr 0.000218	time 3.1830 (2.4810)	loss 3.7551 (3.3205)	grad_norm 1.8592 (2.0828)	
[2022-01-24 08:33:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][90/1251]	eta 0:47:02 lr 0.000218	time 1.5420 (2.4310)	loss 3.6590 (3.3165)	grad_norm 2.0185 (2.0769)	
[2022-01-24 08:33:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][100/1251]	eta 0:46:22 lr 0.000218	time 1.5044 (2.4175)	loss 2.6715 (3.3416)	grad_norm 1.9920 (2.0708)	
[2022-01-24 08:33:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][110/1251]	eta 0:45:22 lr 0.000218	time 1.8014 (2.3859)	loss 3.3872 (3.3262)	grad_norm 2.0279 (2.0609)	
[2022-01-24 08:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][120/1251]	eta 0:44:41 lr 0.000218	time 3.1315 (2.3706)	loss 2.0664 (3.3080)	grad_norm 2.1468 (2.0644)	
[2022-01-24 08:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][130/1251]	eta 0:44:10 lr 0.000218	time 2.1652 (2.3647)	loss 2.5541 (3.3074)	grad_norm 1.9685 (2.0612)	
[2022-01-24 08:35:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][140/1251]	eta 0:43:34 lr 0.000218	time 2.2056 (2.3530)	loss 3.8390 (3.3297)	grad_norm 2.7610 (2.0611)	
[2022-01-24 08:35:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][150/1251]	eta 0:43:07 lr 0.000218	time 2.5810 (2.3499)	loss 3.4442 (3.3248)	grad_norm 2.0262 (2.0635)	
[2022-01-24 08:35:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][160/1251]	eta 0:42:41 lr 0.000218	time 3.0812 (2.3479)	loss 3.1393 (3.3101)	grad_norm 1.9569 (2.0639)	
[2022-01-24 08:36:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][170/1251]	eta 0:42:10 lr 0.000218	time 1.6328 (2.3412)	loss 3.0787 (3.3152)	grad_norm 2.3350 (2.0600)	
[2022-01-24 08:36:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][180/1251]	eta 0:41:33 lr 0.000218	time 1.7122 (2.3285)	loss 3.1537 (3.3093)	grad_norm 1.8798 (2.0544)	
[2022-01-24 08:36:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][190/1251]	eta 0:40:56 lr 0.000218	time 2.8833 (2.3150)	loss 3.4653 (3.3019)	grad_norm 1.9953 (2.0521)	
[2022-01-24 08:37:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][200/1251]	eta 0:40:18 lr 0.000218	time 2.2466 (2.3011)	loss 2.7160 (3.2924)	grad_norm 1.8610 (2.0460)	
[2022-01-24 08:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][210/1251]	eta 0:39:49 lr 0.000218	time 1.9082 (2.2950)	loss 3.1667 (3.2928)	grad_norm 1.9329 (2.0457)	
[2022-01-24 08:37:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][220/1251]	eta 0:39:26 lr 0.000218	time 3.4462 (2.2955)	loss 3.5948 (3.2880)	grad_norm 1.9656 (2.0420)	
[2022-01-24 08:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][230/1251]	eta 0:38:54 lr 0.000217	time 1.9110 (2.2862)	loss 2.5337 (3.2866)	grad_norm 1.9003 (2.0390)	
[2022-01-24 08:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][240/1251]	eta 0:38:23 lr 0.000217	time 1.8749 (2.2783)	loss 3.5222 (3.2788)	grad_norm 1.7178 (2.0416)	
[2022-01-24 08:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][250/1251]	eta 0:37:59 lr 0.000217	time 1.8627 (2.2776)	loss 3.1298 (3.2798)	grad_norm 2.0109 (2.0398)	
[2022-01-24 08:39:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][260/1251]	eta 0:37:33 lr 0.000217	time 2.5853 (2.2742)	loss 3.1962 (3.2880)	grad_norm 2.0375 (2.0462)	
[2022-01-24 08:39:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][270/1251]	eta 0:37:11 lr 0.000217	time 2.7089 (2.2743)	loss 2.4837 (3.2874)	grad_norm 1.9247 (2.0524)	
[2022-01-24 08:40:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][280/1251]	eta 0:36:47 lr 0.000217	time 2.0565 (2.2739)	loss 3.6381 (3.2883)	grad_norm 1.8985 (2.0514)	
[2022-01-24 08:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][290/1251]	eta 0:36:22 lr 0.000217	time 1.7371 (2.2715)	loss 2.9774 (3.2798)	grad_norm 2.7938 (2.0601)	
[2022-01-24 08:40:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][300/1251]	eta 0:35:52 lr 0.000217	time 1.9287 (2.2630)	loss 3.1502 (3.2737)	grad_norm 1.8035 (2.0596)	
[2022-01-24 08:41:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][310/1251]	eta 0:35:27 lr 0.000217	time 1.9475 (2.2604)	loss 3.4575 (3.2830)	grad_norm 2.8041 (2.0617)	
[2022-01-24 08:41:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][320/1251]	eta 0:35:04 lr 0.000217	time 1.9261 (2.2607)	loss 3.1096 (3.2825)	grad_norm 2.0609 (2.0612)	
[2022-01-24 08:41:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][330/1251]	eta 0:34:43 lr 0.000217	time 2.3992 (2.2626)	loss 3.2347 (3.2779)	grad_norm 2.2013 (2.0713)	
[2022-01-24 08:42:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][340/1251]	eta 0:34:22 lr 0.000217	time 2.1974 (2.2639)	loss 3.1068 (3.2748)	grad_norm 2.3299 (2.0706)	
[2022-01-24 08:42:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][350/1251]	eta 0:33:50 lr 0.000217	time 1.7916 (2.2541)	loss 3.4090 (3.2760)	grad_norm 1.9462 (2.0697)	
[2022-01-24 08:43:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][360/1251]	eta 0:33:24 lr 0.000217	time 1.8973 (2.2500)	loss 3.5419 (3.2751)	grad_norm 1.9717 (2.0682)	
[2022-01-24 08:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][370/1251]	eta 0:32:59 lr 0.000217	time 2.0708 (2.2464)	loss 4.0418 (3.2728)	grad_norm 2.0418 (2.0647)	
[2022-01-24 08:43:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][380/1251]	eta 0:32:32 lr 0.000217	time 1.9325 (2.2422)	loss 2.7443 (3.2730)	grad_norm 2.0301 (2.0697)	
[2022-01-24 08:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][390/1251]	eta 0:32:09 lr 0.000217	time 2.1758 (2.2414)	loss 3.7644 (3.2723)	grad_norm 2.6724 (2.0757)	
[2022-01-24 08:44:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][400/1251]	eta 0:31:45 lr 0.000217	time 1.8218 (2.2387)	loss 3.5979 (3.2723)	grad_norm 2.3640 (2.0791)	
[2022-01-24 08:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][410/1251]	eta 0:31:19 lr 0.000217	time 2.1670 (2.2349)	loss 3.2740 (3.2799)	grad_norm 2.1524 (2.0800)	
[2022-01-24 08:45:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][420/1251]	eta 0:30:57 lr 0.000217	time 2.7391 (2.2354)	loss 3.4202 (3.2778)	grad_norm 1.7549 (2.0793)	
[2022-01-24 08:45:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][430/1251]	eta 0:30:37 lr 0.000217	time 2.1214 (2.2378)	loss 3.4773 (3.2769)	grad_norm 1.7443 (2.0786)	
[2022-01-24 08:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][440/1251]	eta 0:30:17 lr 0.000217	time 2.7420 (2.2405)	loss 3.7465 (3.2758)	grad_norm 2.4088 (2.0870)	
[2022-01-24 08:46:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][450/1251]	eta 0:29:54 lr 0.000217	time 2.2448 (2.2400)	loss 3.4241 (3.2781)	grad_norm 1.8983 (2.0896)	
[2022-01-24 08:46:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][460/1251]	eta 0:29:28 lr 0.000217	time 1.5920 (2.2356)	loss 2.8717 (3.2784)	grad_norm 1.9701 (2.0892)	
[2022-01-24 08:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][470/1251]	eta 0:29:05 lr 0.000217	time 1.6198 (2.2351)	loss 3.2509 (3.2767)	grad_norm 2.0733 (2.0880)	
[2022-01-24 08:47:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][480/1251]	eta 0:28:42 lr 0.000217	time 2.4120 (2.2343)	loss 3.4323 (3.2719)	grad_norm 1.7953 (2.0850)	
[2022-01-24 08:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][490/1251]	eta 0:28:17 lr 0.000217	time 1.7217 (2.2311)	loss 4.2860 (3.2759)	grad_norm 2.0638 (2.0847)	
[2022-01-24 08:48:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][500/1251]	eta 0:27:54 lr 0.000217	time 1.9963 (2.2293)	loss 3.7190 (3.2799)	grad_norm 1.8410 (2.0864)	
[2022-01-24 08:48:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][510/1251]	eta 0:27:34 lr 0.000217	time 1.8914 (2.2324)	loss 3.5573 (3.2857)	grad_norm 1.9579 (2.0881)	
[2022-01-24 08:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][520/1251]	eta 0:27:12 lr 0.000217	time 2.5484 (2.2330)	loss 3.9621 (3.2792)	grad_norm 2.0149 (2.0954)	
[2022-01-24 08:49:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][530/1251]	eta 0:26:48 lr 0.000216	time 1.8705 (2.2315)	loss 3.1323 (3.2812)	grad_norm 2.2241 (2.0944)	
[2022-01-24 08:49:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][540/1251]	eta 0:26:24 lr 0.000216	time 1.9219 (2.2284)	loss 3.4599 (3.2820)	grad_norm 1.8530 (2.0927)	
[2022-01-24 08:49:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][550/1251]	eta 0:26:04 lr 0.000216	time 2.2496 (2.2324)	loss 3.6151 (3.2777)	grad_norm 2.3632 (2.0910)	
[2022-01-24 08:50:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][560/1251]	eta 0:25:40 lr 0.000216	time 1.8156 (2.2288)	loss 2.0074 (3.2724)	grad_norm 2.5414 (2.0926)	
[2022-01-24 08:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][570/1251]	eta 0:25:15 lr 0.000216	time 1.7966 (2.2251)	loss 3.8940 (3.2734)	grad_norm 2.1493 (2.0937)	
[2022-01-24 08:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][580/1251]	eta 0:24:51 lr 0.000216	time 1.9992 (2.2233)	loss 3.6048 (3.2749)	grad_norm 2.0031 (2.0911)	
[2022-01-24 08:51:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][590/1251]	eta 0:24:29 lr 0.000216	time 1.8695 (2.2229)	loss 3.5001 (3.2757)	grad_norm 1.9351 (2.0911)	
[2022-01-24 08:51:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][600/1251]	eta 0:24:07 lr 0.000216	time 2.1853 (2.2235)	loss 2.5564 (3.2696)	grad_norm 1.7756 (2.0914)	
[2022-01-24 08:52:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][610/1251]	eta 0:23:44 lr 0.000216	time 2.0438 (2.2216)	loss 3.3529 (3.2712)	grad_norm 1.8255 (2.0883)	
[2022-01-24 08:52:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][620/1251]	eta 0:23:22 lr 0.000216	time 2.2512 (2.2225)	loss 3.4371 (3.2721)	grad_norm 2.0475 (2.0871)	
[2022-01-24 08:52:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][630/1251]	eta 0:23:00 lr 0.000216	time 1.5875 (2.2233)	loss 3.4148 (3.2696)	grad_norm 2.2225 (2.0856)	
[2022-01-24 08:53:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][640/1251]	eta 0:22:36 lr 0.000216	time 1.5438 (2.2196)	loss 3.6164 (3.2744)	grad_norm 1.7755 (2.0839)	
[2022-01-24 08:53:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][650/1251]	eta 0:22:12 lr 0.000216	time 1.8712 (2.2170)	loss 3.3891 (3.2764)	grad_norm 2.2113 (2.0811)	
[2022-01-24 08:53:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][660/1251]	eta 0:21:49 lr 0.000216	time 2.3098 (2.2153)	loss 3.6850 (3.2754)	grad_norm 1.9827 (2.0806)	
[2022-01-24 08:54:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][670/1251]	eta 0:21:26 lr 0.000216	time 1.9599 (2.2149)	loss 3.6694 (3.2742)	grad_norm 2.0045 (2.0799)	
[2022-01-24 08:54:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][680/1251]	eta 0:21:04 lr 0.000216	time 2.1603 (2.2138)	loss 3.8872 (3.2681)	grad_norm 2.0048 (2.0794)	
[2022-01-24 08:54:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][690/1251]	eta 0:20:41 lr 0.000216	time 2.3272 (2.2127)	loss 3.0601 (3.2682)	grad_norm 2.1423 (2.0786)	
[2022-01-24 08:55:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][700/1251]	eta 0:20:18 lr 0.000216	time 1.9294 (2.2117)	loss 3.0133 (3.2727)	grad_norm 2.1532 (2.0783)	
[2022-01-24 08:55:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][710/1251]	eta 0:19:56 lr 0.000216	time 2.3329 (2.2109)	loss 2.7622 (3.2723)	grad_norm 1.9695 (2.0776)	
[2022-01-24 08:56:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][720/1251]	eta 0:19:34 lr 0.000216	time 3.1051 (2.2117)	loss 2.1512 (3.2744)	grad_norm 1.8858 (2.0780)	
[2022-01-24 08:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][730/1251]	eta 0:19:12 lr 0.000216	time 2.1517 (2.2125)	loss 2.8868 (3.2730)	grad_norm 1.9121 (2.0768)	
[2022-01-24 08:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][740/1251]	eta 0:18:51 lr 0.000216	time 2.5350 (2.2135)	loss 3.8990 (3.2743)	grad_norm 2.1668 (2.0772)	
[2022-01-24 08:57:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][750/1251]	eta 0:18:29 lr 0.000216	time 2.1905 (2.2141)	loss 3.0116 (3.2778)	grad_norm 2.0516 (2.0781)	
[2022-01-24 08:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][760/1251]	eta 0:18:08 lr 0.000216	time 3.1527 (2.2164)	loss 3.4955 (3.2770)	grad_norm 2.0587 (2.0770)	
[2022-01-24 08:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][770/1251]	eta 0:17:45 lr 0.000216	time 1.7728 (2.2145)	loss 2.7656 (3.2741)	grad_norm 1.7829 (2.0749)	
[2022-01-24 08:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][780/1251]	eta 0:17:22 lr 0.000216	time 1.7961 (2.2136)	loss 3.6517 (3.2752)	grad_norm 2.2096 (2.0754)	
[2022-01-24 08:58:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][790/1251]	eta 0:17:00 lr 0.000216	time 1.8266 (2.2128)	loss 2.9373 (3.2755)	grad_norm 1.9744 (2.0757)	
[2022-01-24 08:59:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][800/1251]	eta 0:16:37 lr 0.000216	time 2.0182 (2.2124)	loss 3.4135 (3.2780)	grad_norm 1.6727 (2.0756)	
[2022-01-24 08:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][810/1251]	eta 0:16:15 lr 0.000216	time 2.1252 (2.2128)	loss 3.0706 (3.2792)	grad_norm 1.9794 (2.0759)	
[2022-01-24 08:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][820/1251]	eta 0:15:52 lr 0.000215	time 1.6062 (2.2109)	loss 3.4040 (3.2805)	grad_norm 2.5887 (2.0771)	
[2022-01-24 09:00:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][830/1251]	eta 0:15:30 lr 0.000215	time 2.6299 (2.2096)	loss 3.5004 (3.2802)	grad_norm 1.8667 (2.0778)	
[2022-01-24 09:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][840/1251]	eta 0:15:07 lr 0.000215	time 1.8491 (2.2080)	loss 2.9658 (3.2770)	grad_norm 1.8227 (2.0781)	
[2022-01-24 09:00:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][850/1251]	eta 0:14:45 lr 0.000215	time 2.9396 (2.2090)	loss 2.5571 (3.2783)	grad_norm 1.9112 (2.0791)	
[2022-01-24 09:01:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][860/1251]	eta 0:14:23 lr 0.000215	time 1.8763 (2.2096)	loss 3.3933 (3.2772)	grad_norm 1.9651 (2.0798)	
[2022-01-24 09:01:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][870/1251]	eta 0:14:02 lr 0.000215	time 2.4265 (2.2106)	loss 3.0975 (3.2767)	grad_norm 2.6235 (2.0803)	
[2022-01-24 09:01:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][880/1251]	eta 0:13:39 lr 0.000215	time 1.6180 (2.2081)	loss 3.6955 (3.2757)	grad_norm 2.0313 (2.0815)	
[2022-01-24 09:02:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][890/1251]	eta 0:13:17 lr 0.000215	time 3.1915 (2.2080)	loss 2.5415 (3.2744)	grad_norm 1.9616 (2.0817)	
[2022-01-24 09:02:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][900/1251]	eta 0:12:54 lr 0.000215	time 1.8709 (2.2069)	loss 3.9600 (3.2757)	grad_norm 2.1485 (2.0816)	
[2022-01-24 09:03:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][910/1251]	eta 0:12:32 lr 0.000215	time 2.0342 (2.2074)	loss 3.1318 (3.2776)	grad_norm 1.8623 (2.0805)	
[2022-01-24 09:03:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][920/1251]	eta 0:12:10 lr 0.000215	time 1.6974 (2.2065)	loss 3.4146 (3.2775)	grad_norm 2.1487 (2.0808)	
[2022-01-24 09:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][930/1251]	eta 0:11:49 lr 0.000215	time 3.6637 (2.2087)	loss 3.5947 (3.2790)	grad_norm 2.1785 (2.0809)	
[2022-01-24 09:04:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][940/1251]	eta 0:11:26 lr 0.000215	time 2.2058 (2.2080)	loss 3.7518 (3.2803)	grad_norm 2.9654 (2.0815)	
[2022-01-24 09:04:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][950/1251]	eta 0:11:04 lr 0.000215	time 2.0083 (2.2080)	loss 3.2105 (3.2791)	grad_norm 2.1003 (2.0813)	
[2022-01-24 09:04:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][960/1251]	eta 0:10:42 lr 0.000215	time 1.9295 (2.2064)	loss 3.2492 (3.2803)	grad_norm 1.9329 (2.0811)	
[2022-01-24 09:05:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][970/1251]	eta 0:10:20 lr 0.000215	time 2.1733 (2.2069)	loss 3.9467 (3.2828)	grad_norm 1.9340 (2.0811)	
[2022-01-24 09:05:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][980/1251]	eta 0:09:57 lr 0.000215	time 1.6107 (2.2061)	loss 3.4776 (3.2833)	grad_norm 1.8926 (2.0808)	
[2022-01-24 09:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][990/1251]	eta 0:09:35 lr 0.000215	time 2.4396 (2.2061)	loss 4.0182 (3.2832)	grad_norm 2.5943 (2.0823)	
[2022-01-24 09:06:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1000/1251]	eta 0:09:13 lr 0.000215	time 2.1198 (2.2056)	loss 3.5797 (3.2852)	grad_norm 1.8704 (2.0823)	
[2022-01-24 09:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1010/1251]	eta 0:08:52 lr 0.000215	time 1.8525 (2.2075)	loss 2.9160 (3.2856)	grad_norm 1.7255 (2.0828)	
[2022-01-24 09:07:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1020/1251]	eta 0:08:29 lr 0.000215	time 1.6431 (2.2067)	loss 3.2082 (3.2860)	grad_norm 2.4973 (2.0837)	
[2022-01-24 09:07:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1030/1251]	eta 0:08:07 lr 0.000215	time 1.5714 (2.2061)	loss 3.4121 (3.2857)	grad_norm 1.8938 (2.0827)	
[2022-01-24 09:07:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1040/1251]	eta 0:07:45 lr 0.000215	time 1.6337 (2.2059)	loss 3.4295 (3.2866)	grad_norm 2.2182 (2.0818)	
[2022-01-24 09:08:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1050/1251]	eta 0:07:23 lr 0.000215	time 1.8534 (2.2055)	loss 3.1914 (3.2850)	grad_norm 2.1810 (2.0810)	
[2022-01-24 09:08:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1060/1251]	eta 0:07:01 lr 0.000215	time 2.1682 (2.2049)	loss 2.8361 (3.2876)	grad_norm 1.9891 (2.0806)	
[2022-01-24 09:08:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1070/1251]	eta 0:06:39 lr 0.000215	time 1.8605 (2.2050)	loss 3.5266 (3.2863)	grad_norm 1.9113 (2.0792)	
[2022-01-24 09:09:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1080/1251]	eta 0:06:17 lr 0.000215	time 1.6616 (2.2051)	loss 3.4372 (3.2856)	grad_norm 2.1049 (2.0783)	
[2022-01-24 09:09:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1090/1251]	eta 0:05:54 lr 0.000215	time 2.1233 (2.2045)	loss 2.5970 (3.2858)	grad_norm 1.6788 (2.0783)	
[2022-01-24 09:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1100/1251]	eta 0:05:32 lr 0.000215	time 2.0358 (2.2027)	loss 3.3521 (3.2869)	grad_norm 1.8179 (2.0775)	
[2022-01-24 09:10:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1110/1251]	eta 0:05:10 lr 0.000215	time 1.9809 (2.2014)	loss 3.2780 (3.2860)	grad_norm 1.9329 (2.0769)	
[2022-01-24 09:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1120/1251]	eta 0:04:48 lr 0.000214	time 2.2159 (2.2012)	loss 3.5062 (3.2852)	grad_norm 1.8259 (2.0765)	
[2022-01-24 09:10:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1130/1251]	eta 0:04:26 lr 0.000214	time 1.9261 (2.2006)	loss 3.4971 (3.2859)	grad_norm 2.1430 (2.0756)	
[2022-01-24 09:11:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1140/1251]	eta 0:04:04 lr 0.000214	time 2.2509 (2.2015)	loss 3.4892 (3.2855)	grad_norm 1.9353 (2.0754)	
[2022-01-24 09:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1150/1251]	eta 0:03:42 lr 0.000214	time 2.5765 (2.2022)	loss 3.0701 (3.2837)	grad_norm 2.1228 (2.0744)	
[2022-01-24 09:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1160/1251]	eta 0:03:20 lr 0.000214	time 2.8362 (2.2036)	loss 3.7425 (3.2840)	grad_norm 2.0309 (2.0734)	
[2022-01-24 09:12:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1170/1251]	eta 0:02:58 lr 0.000214	time 1.7146 (2.2022)	loss 3.1336 (3.2834)	grad_norm 1.9017 (2.0736)	
[2022-01-24 09:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1180/1251]	eta 0:02:36 lr 0.000214	time 1.5289 (2.2011)	loss 3.0909 (3.2841)	grad_norm 2.1290 (2.0746)	
[2022-01-24 09:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1190/1251]	eta 0:02:14 lr 0.000214	time 2.1527 (2.2008)	loss 2.2446 (3.2844)	grad_norm 2.0689 (2.0738)	
[2022-01-24 09:13:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1200/1251]	eta 0:01:52 lr 0.000214	time 2.5390 (2.2026)	loss 3.5326 (3.2853)	grad_norm 2.2726 (2.0739)	
[2022-01-24 09:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1210/1251]	eta 0:01:30 lr 0.000214	time 1.5646 (2.2024)	loss 2.6266 (3.2830)	grad_norm 2.0028 (2.0737)	
[2022-01-24 09:14:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1220/1251]	eta 0:01:08 lr 0.000214	time 2.0077 (2.2027)	loss 3.0140 (3.2834)	grad_norm 2.0485 (2.0725)	
[2022-01-24 09:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1230/1251]	eta 0:00:46 lr 0.000214	time 2.5248 (2.2019)	loss 3.5526 (3.2826)	grad_norm 2.0144 (2.0719)	
[2022-01-24 09:15:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1240/1251]	eta 0:00:24 lr 0.000214	time 1.4375 (2.2005)	loss 3.6555 (3.2821)	grad_norm 2.1519 (2.0713)	
[2022-01-24 09:15:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [209/300][1250/1251]	eta 0:00:02 lr 0.000214	time 1.3693 (2.1947)	loss 2.6880 (3.2810)	grad_norm 1.8899 (2.0705)	
[2022-01-24 09:15:15 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 209 training takes 0:45:45
[2022-01-24 09:15:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.718 (18.718)	Loss 0.9510 (0.9510)	Acc@1 77.344 (77.344)	Acc@5 94.238 (94.238)	
[2022-01-24 09:15:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.640 (3.286)	Loss 0.8692 (0.8971)	Acc@1 77.344 (78.471)	Acc@5 95.996 (94.656)	
[2022-01-24 09:16:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.891 (2.670)	Loss 0.8107 (0.8930)	Acc@1 81.250 (78.795)	Acc@5 95.020 (94.582)	
[2022-01-24 09:16:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.621 (2.230)	Loss 0.8737 (0.8922)	Acc@1 80.566 (78.818)	Acc@5 95.020 (94.553)	
[2022-01-24 09:16:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.595 (2.139)	Loss 0.8904 (0.8940)	Acc@1 79.395 (78.828)	Acc@5 94.531 (94.534)	
[2022-01-24 09:16:50 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.672 Acc@5 94.534
[2022-01-24 09:16:50 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.7%
[2022-01-24 09:16:50 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.81%
[2022-01-24 09:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][0/1251]	eta 7:32:43 lr 0.000214	time 21.7138 (21.7138)	loss 3.9093 (3.9093)	grad_norm 2.1001 (2.1001)	
[2022-01-24 09:17:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][10/1251]	eta 1:25:31 lr 0.000214	time 2.6639 (4.1346)	loss 2.0653 (3.0143)	grad_norm 2.0301 (2.0256)	
[2022-01-24 09:17:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][20/1251]	eta 1:04:13 lr 0.000214	time 1.5465 (3.1301)	loss 2.4858 (3.1835)	grad_norm 1.9098 (2.0731)	
[2022-01-24 09:18:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][30/1251]	eta 0:58:36 lr 0.000214	time 1.4624 (2.8797)	loss 3.0705 (3.2922)	grad_norm 1.9665 (2.0867)	
[2022-01-24 09:18:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][40/1251]	eta 0:55:26 lr 0.000214	time 3.1850 (2.7467)	loss 3.6509 (3.2748)	grad_norm 1.7903 (2.0962)	
[2022-01-24 09:19:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][50/1251]	eta 0:52:56 lr 0.000214	time 2.7317 (2.6448)	loss 3.0984 (3.2323)	grad_norm 2.1684 (2.0839)	
[2022-01-24 09:19:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][60/1251]	eta 0:50:57 lr 0.000214	time 1.8397 (2.5674)	loss 3.0800 (3.2188)	grad_norm 1.7822 (2.0724)	
[2022-01-24 09:19:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][70/1251]	eta 0:49:16 lr 0.000214	time 1.9766 (2.5033)	loss 3.7760 (3.2541)	grad_norm 2.6749 (2.0839)	
[2022-01-24 09:20:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][80/1251]	eta 0:48:08 lr 0.000214	time 2.9449 (2.4665)	loss 3.8735 (3.2511)	grad_norm 2.2320 (2.0844)	
[2022-01-24 09:20:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][90/1251]	eta 0:47:42 lr 0.000214	time 2.7686 (2.4659)	loss 3.7050 (3.2082)	grad_norm 1.9863 (2.0826)	
[2022-01-24 09:20:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][100/1251]	eta 0:46:48 lr 0.000214	time 1.9344 (2.4402)	loss 2.1101 (3.2117)	grad_norm 2.0752 (2.0766)	
[2022-01-24 09:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][110/1251]	eta 0:45:37 lr 0.000214	time 1.6469 (2.3990)	loss 3.5350 (3.2111)	grad_norm 1.7698 (2.0736)	
[2022-01-24 09:21:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][120/1251]	eta 0:44:28 lr 0.000214	time 1.9951 (2.3598)	loss 3.9140 (3.2043)	grad_norm 1.9270 (2.0723)	
[2022-01-24 09:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][130/1251]	eta 0:43:45 lr 0.000214	time 1.8866 (2.3418)	loss 3.5458 (3.2117)	grad_norm 2.8622 (2.0720)	
[2022-01-24 09:22:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][140/1251]	eta 0:43:12 lr 0.000214	time 2.2809 (2.3334)	loss 2.5478 (3.2152)	grad_norm 2.5348 (2.0811)	
[2022-01-24 09:22:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][150/1251]	eta 0:42:34 lr 0.000214	time 2.0808 (2.3198)	loss 3.7238 (3.2239)	grad_norm 2.0186 (2.0953)	
[2022-01-24 09:23:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][160/1251]	eta 0:41:55 lr 0.000214	time 2.1000 (2.3057)	loss 2.5694 (3.2302)	grad_norm 1.7238 (2.0909)	
[2022-01-24 09:23:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][170/1251]	eta 0:41:25 lr 0.000213	time 2.5572 (2.2997)	loss 3.3762 (3.2315)	grad_norm 2.0857 (2.0879)	
[2022-01-24 09:23:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][180/1251]	eta 0:40:54 lr 0.000213	time 2.1990 (2.2921)	loss 3.4665 (3.2459)	grad_norm 2.1717 (2.0802)	
[2022-01-24 09:24:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][190/1251]	eta 0:40:28 lr 0.000213	time 1.8635 (2.2890)	loss 3.4695 (3.2530)	grad_norm 1.9618 (2.0718)	
[2022-01-24 09:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][200/1251]	eta 0:40:06 lr 0.000213	time 2.2197 (2.2901)	loss 3.4138 (3.2498)	grad_norm 2.1143 (2.0742)	
[2022-01-24 09:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][210/1251]	eta 0:39:42 lr 0.000213	time 3.0515 (2.2885)	loss 4.1082 (3.2735)	grad_norm 1.8845 (2.0712)	
[2022-01-24 09:25:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][220/1251]	eta 0:39:10 lr 0.000213	time 2.5792 (2.2800)	loss 2.6401 (3.2670)	grad_norm 2.0039 (2.0734)	
[2022-01-24 09:25:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][230/1251]	eta 0:38:42 lr 0.000213	time 2.4684 (2.2744)	loss 3.7601 (3.2793)	grad_norm 2.2667 (2.0666)	
[2022-01-24 09:25:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][240/1251]	eta 0:38:07 lr 0.000213	time 1.9657 (2.2629)	loss 3.7102 (3.2851)	grad_norm 1.8185 (2.0605)	
[2022-01-24 09:26:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][250/1251]	eta 0:37:37 lr 0.000213	time 2.3883 (2.2550)	loss 3.6427 (3.2831)	grad_norm 1.8899 (2.0580)	
[2022-01-24 09:26:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][260/1251]	eta 0:37:22 lr 0.000213	time 2.5610 (2.2626)	loss 3.9383 (3.2808)	grad_norm 2.1431 (2.0585)	
[2022-01-24 09:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][270/1251]	eta 0:36:55 lr 0.000213	time 1.9056 (2.2579)	loss 2.5533 (3.2717)	grad_norm 1.9264 (2.0589)	
[2022-01-24 09:27:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][280/1251]	eta 0:36:27 lr 0.000213	time 1.8814 (2.2525)	loss 3.5254 (3.2673)	grad_norm 2.1700 (2.0595)	
[2022-01-24 09:27:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][290/1251]	eta 0:36:04 lr 0.000213	time 2.8306 (2.2521)	loss 2.6721 (3.2782)	grad_norm 2.0098 (2.0637)	
[2022-01-24 09:28:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][300/1251]	eta 0:35:42 lr 0.000213	time 2.4098 (2.2524)	loss 4.0830 (3.2788)	grad_norm 1.7882 (2.0612)	
[2022-01-24 09:28:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][310/1251]	eta 0:35:20 lr 0.000213	time 3.2993 (2.2540)	loss 4.0772 (3.2877)	grad_norm 2.0128 (2.0616)	
[2022-01-24 09:28:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][320/1251]	eta 0:34:55 lr 0.000213	time 1.9525 (2.2504)	loss 3.6117 (3.2811)	grad_norm 2.0731 (2.0604)	
[2022-01-24 09:29:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][330/1251]	eta 0:34:28 lr 0.000213	time 1.9181 (2.2455)	loss 3.8647 (3.2932)	grad_norm 2.0169 (2.0604)	
[2022-01-24 09:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][340/1251]	eta 0:34:02 lr 0.000213	time 2.8135 (2.2424)	loss 2.8818 (3.2880)	grad_norm 2.0076 (2.0577)	
[2022-01-24 09:29:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][350/1251]	eta 0:33:44 lr 0.000213	time 3.8388 (2.2465)	loss 3.4656 (3.2886)	grad_norm 2.0129 (2.0555)	
[2022-01-24 09:30:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][360/1251]	eta 0:33:18 lr 0.000213	time 2.2814 (2.2430)	loss 3.6340 (3.2927)	grad_norm 2.1882 (2.0582)	
[2022-01-24 09:30:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][370/1251]	eta 0:32:53 lr 0.000213	time 1.5725 (2.2403)	loss 3.5740 (3.2941)	grad_norm 2.2920 (2.0579)	
[2022-01-24 09:31:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][380/1251]	eta 0:32:28 lr 0.000213	time 2.5294 (2.2370)	loss 3.6668 (3.2913)	grad_norm 1.8683 (2.0593)	
[2022-01-24 09:31:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][390/1251]	eta 0:32:05 lr 0.000213	time 2.4814 (2.2363)	loss 3.9566 (3.2897)	grad_norm 2.0135 (2.0594)	
[2022-01-24 09:31:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][400/1251]	eta 0:31:40 lr 0.000213	time 2.0414 (2.2338)	loss 3.4648 (3.2885)	grad_norm 1.9484 (2.0582)	
[2022-01-24 09:32:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][410/1251]	eta 0:31:13 lr 0.000213	time 2.0675 (2.2280)	loss 2.2502 (3.2908)	grad_norm 2.0240 (2.0555)	
[2022-01-24 09:32:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][420/1251]	eta 0:30:52 lr 0.000213	time 2.3553 (2.2295)	loss 3.2624 (3.2887)	grad_norm 2.0677 (2.0560)	
[2022-01-24 09:32:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][430/1251]	eta 0:30:30 lr 0.000213	time 2.7070 (2.2295)	loss 3.5668 (3.2942)	grad_norm 1.8495 (2.0569)	
[2022-01-24 09:33:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][440/1251]	eta 0:30:06 lr 0.000213	time 1.5132 (2.2274)	loss 3.3750 (3.2895)	grad_norm 1.9684 (2.0555)	
[2022-01-24 09:33:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][450/1251]	eta 0:29:47 lr 0.000213	time 2.9257 (2.2322)	loss 2.8981 (3.2811)	grad_norm 1.8832 (2.0547)	
[2022-01-24 09:33:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][460/1251]	eta 0:29:23 lr 0.000213	time 1.8681 (2.2296)	loss 2.1601 (3.2816)	grad_norm 2.1129 (2.0548)	
[2022-01-24 09:34:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][470/1251]	eta 0:29:00 lr 0.000212	time 2.4466 (2.2281)	loss 3.8011 (3.2785)	grad_norm 1.7112 (2.0537)	
[2022-01-24 09:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][480/1251]	eta 0:28:35 lr 0.000212	time 1.9726 (2.2252)	loss 2.6005 (3.2785)	grad_norm 1.9453 (2.0551)	
[2022-01-24 09:35:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][490/1251]	eta 0:28:13 lr 0.000212	time 2.7246 (2.2249)	loss 3.3601 (3.2817)	grad_norm 1.9232 (2.0556)	
[2022-01-24 09:35:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][500/1251]	eta 0:27:50 lr 0.000212	time 2.4048 (2.2240)	loss 3.4390 (3.2818)	grad_norm 1.9329 (2.0539)	
[2022-01-24 09:35:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][510/1251]	eta 0:27:27 lr 0.000212	time 1.9090 (2.2228)	loss 3.3298 (3.2812)	grad_norm 1.8696 (2.0514)	
[2022-01-24 09:36:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][520/1251]	eta 0:27:05 lr 0.000212	time 2.5078 (2.2233)	loss 4.0680 (3.2858)	grad_norm 2.1740 (2.0502)	
[2022-01-24 09:36:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][530/1251]	eta 0:26:42 lr 0.000212	time 2.8146 (2.2224)	loss 3.7238 (3.2828)	grad_norm 1.9556 (2.0481)	
[2022-01-24 09:36:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][540/1251]	eta 0:26:16 lr 0.000212	time 1.9443 (2.2178)	loss 3.6062 (3.2834)	grad_norm 2.0421 (2.0483)	
[2022-01-24 09:37:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][550/1251]	eta 0:25:51 lr 0.000212	time 1.9232 (2.2135)	loss 2.8218 (3.2845)	grad_norm 1.8000 (2.0468)	
[2022-01-24 09:37:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][560/1251]	eta 0:25:27 lr 0.000212	time 2.7663 (2.2111)	loss 3.6599 (3.2869)	grad_norm 2.3998 (2.0475)	
[2022-01-24 09:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][570/1251]	eta 0:25:06 lr 0.000212	time 3.1505 (2.2128)	loss 3.8794 (3.2885)	grad_norm 2.2842 (2.0464)	
[2022-01-24 09:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][580/1251]	eta 0:24:45 lr 0.000212	time 2.1315 (2.2134)	loss 3.6051 (3.2886)	grad_norm 1.9179 (2.0462)	
[2022-01-24 09:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][590/1251]	eta 0:24:22 lr 0.000212	time 2.1090 (2.2132)	loss 2.8419 (3.2909)	grad_norm 1.8880 (2.0452)	
[2022-01-24 09:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][600/1251]	eta 0:24:01 lr 0.000212	time 1.9075 (2.2144)	loss 3.6559 (3.2864)	grad_norm 1.9924 (2.0478)	
[2022-01-24 09:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][610/1251]	eta 0:23:40 lr 0.000212	time 2.4700 (2.2157)	loss 3.9071 (3.2876)	grad_norm 2.2452 (2.0477)	
[2022-01-24 09:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][620/1251]	eta 0:23:17 lr 0.000212	time 2.5500 (2.2141)	loss 3.1694 (3.2896)	grad_norm 1.8795 (2.0470)	
[2022-01-24 09:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][630/1251]	eta 0:22:53 lr 0.000212	time 1.5867 (2.2112)	loss 3.0126 (3.2919)	grad_norm 2.0916 (2.0483)	
[2022-01-24 09:40:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][640/1251]	eta 0:22:32 lr 0.000212	time 1.9128 (2.2130)	loss 3.3739 (3.2939)	grad_norm 2.0169 (2.0475)	
[2022-01-24 09:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][650/1251]	eta 0:22:09 lr 0.000212	time 2.2191 (2.2124)	loss 2.6720 (3.2969)	grad_norm 2.0451 (2.0467)	
[2022-01-24 09:41:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][660/1251]	eta 0:21:47 lr 0.000212	time 2.2821 (2.2129)	loss 2.5285 (3.2974)	grad_norm 1.9317 (2.0468)	
[2022-01-24 09:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][670/1251]	eta 0:21:24 lr 0.000212	time 2.2060 (2.2114)	loss 2.8422 (3.2964)	grad_norm 1.8045 (2.0472)	
[2022-01-24 09:41:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][680/1251]	eta 0:21:02 lr 0.000212	time 1.6854 (2.2103)	loss 2.6297 (3.2964)	grad_norm 1.9640 (2.0488)	
[2022-01-24 09:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][690/1251]	eta 0:20:39 lr 0.000212	time 2.5221 (2.2098)	loss 2.9380 (3.2993)	grad_norm 1.9018 (2.0491)	
[2022-01-24 09:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][700/1251]	eta 0:20:17 lr 0.000212	time 1.5138 (2.2088)	loss 3.7174 (3.2977)	grad_norm 1.9328 (2.0484)	
[2022-01-24 09:42:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][710/1251]	eta 0:19:54 lr 0.000212	time 1.6063 (2.2073)	loss 3.2150 (3.2988)	grad_norm 2.1725 (2.0484)	
[2022-01-24 09:43:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][720/1251]	eta 0:19:32 lr 0.000212	time 2.2554 (2.2074)	loss 3.5686 (3.2995)	grad_norm 2.9752 (2.0483)	
[2022-01-24 09:43:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][730/1251]	eta 0:19:09 lr 0.000212	time 2.1833 (2.2069)	loss 3.5938 (3.3029)	grad_norm 1.9725 (2.0504)	
[2022-01-24 09:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][740/1251]	eta 0:18:47 lr 0.000212	time 2.0166 (2.2072)	loss 4.0381 (3.3023)	grad_norm 1.9282 (2.0508)	
[2022-01-24 09:44:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][750/1251]	eta 0:18:25 lr 0.000212	time 1.7877 (2.2059)	loss 3.8133 (3.2994)	grad_norm 2.0713 (2.0525)	
[2022-01-24 09:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][760/1251]	eta 0:18:03 lr 0.000212	time 2.5247 (2.2061)	loss 3.7085 (3.2960)	grad_norm 2.2334 (2.0530)	
[2022-01-24 09:45:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][770/1251]	eta 0:17:40 lr 0.000211	time 2.1163 (2.2051)	loss 2.8642 (3.2956)	grad_norm 3.2006 (2.0551)	
[2022-01-24 09:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][780/1251]	eta 0:17:18 lr 0.000211	time 1.8145 (2.2049)	loss 3.5481 (3.2976)	grad_norm 1.9236 (2.0547)	
[2022-01-24 09:45:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][790/1251]	eta 0:16:56 lr 0.000211	time 2.2264 (2.2052)	loss 3.4508 (3.2942)	grad_norm 1.8417 (2.0534)	
[2022-01-24 09:46:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][800/1251]	eta 0:16:34 lr 0.000211	time 2.0824 (2.2040)	loss 2.4213 (3.2947)	grad_norm 2.0139 (2.0536)	
[2022-01-24 09:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][810/1251]	eta 0:16:12 lr 0.000211	time 1.5569 (2.2043)	loss 3.0778 (3.2937)	grad_norm 2.3342 (2.0542)	
[2022-01-24 09:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][820/1251]	eta 0:15:50 lr 0.000211	time 2.4095 (2.2043)	loss 3.4961 (3.2931)	grad_norm 2.0911 (2.0535)	
[2022-01-24 09:47:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][830/1251]	eta 0:15:27 lr 0.000211	time 3.0367 (2.2036)	loss 3.5911 (3.2930)	grad_norm 1.7978 (2.0530)	
[2022-01-24 09:47:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][840/1251]	eta 0:15:05 lr 0.000211	time 2.0575 (2.2031)	loss 3.5283 (3.2950)	grad_norm 1.8995 (2.0536)	
[2022-01-24 09:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][850/1251]	eta 0:14:42 lr 0.000211	time 2.0169 (2.2006)	loss 3.0597 (3.2974)	grad_norm 2.0983 (2.0532)	
[2022-01-24 09:48:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][860/1251]	eta 0:14:20 lr 0.000211	time 1.9920 (2.1999)	loss 4.0309 (3.2985)	grad_norm 2.1513 (2.0530)	
[2022-01-24 09:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][870/1251]	eta 0:13:58 lr 0.000211	time 2.3784 (2.2008)	loss 3.6877 (3.3004)	grad_norm 1.8162 (2.0527)	
[2022-01-24 09:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][880/1251]	eta 0:13:37 lr 0.000211	time 2.1538 (2.2027)	loss 3.6369 (3.3012)	grad_norm 2.0744 (2.0530)	
[2022-01-24 09:49:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][890/1251]	eta 0:13:15 lr 0.000211	time 1.9019 (2.2027)	loss 3.7054 (3.3016)	grad_norm 2.1986 (2.0533)	
[2022-01-24 09:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][900/1251]	eta 0:12:52 lr 0.000211	time 1.9054 (2.2008)	loss 3.4430 (3.3028)	grad_norm 1.7343 (2.0528)	
[2022-01-24 09:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][910/1251]	eta 0:12:31 lr 0.000211	time 2.7884 (2.2024)	loss 3.6256 (3.3019)	grad_norm 1.9707 (2.0528)	
[2022-01-24 09:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][920/1251]	eta 0:12:09 lr 0.000211	time 1.6195 (2.2036)	loss 3.8338 (3.3028)	grad_norm 2.1987 (2.0534)	
[2022-01-24 09:50:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][930/1251]	eta 0:11:46 lr 0.000211	time 1.6660 (2.2011)	loss 2.5806 (3.2999)	grad_norm 2.2120 (2.0542)	
[2022-01-24 09:51:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][940/1251]	eta 0:11:24 lr 0.000211	time 1.6391 (2.2002)	loss 3.6271 (3.2985)	grad_norm 2.3251 (2.0553)	
[2022-01-24 09:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][950/1251]	eta 0:11:02 lr 0.000211	time 3.4136 (2.2005)	loss 3.4041 (3.3015)	grad_norm 1.7660 (2.0550)	
[2022-01-24 09:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][960/1251]	eta 0:10:40 lr 0.000211	time 2.0175 (2.2020)	loss 3.1130 (3.3005)	grad_norm 1.8938 (2.0565)	
[2022-01-24 09:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][970/1251]	eta 0:10:18 lr 0.000211	time 2.5250 (2.2019)	loss 3.0141 (3.2994)	grad_norm 2.3947 (2.0579)	
[2022-01-24 09:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][980/1251]	eta 0:09:56 lr 0.000211	time 1.8491 (2.1999)	loss 2.1156 (3.2988)	grad_norm 2.0381 (2.0579)	
[2022-01-24 09:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][990/1251]	eta 0:09:34 lr 0.000211	time 2.1801 (2.1999)	loss 2.7374 (3.2967)	grad_norm 2.1753 (2.0581)	
[2022-01-24 09:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1000/1251]	eta 0:09:12 lr 0.000211	time 2.5222 (2.1994)	loss 3.3030 (3.2990)	grad_norm 2.2697 (2.0589)	
[2022-01-24 09:53:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1010/1251]	eta 0:08:49 lr 0.000211	time 2.5570 (2.1989)	loss 3.5490 (3.2982)	grad_norm 2.1456 (2.0594)	
[2022-01-24 09:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1020/1251]	eta 0:08:27 lr 0.000211	time 2.3539 (2.1983)	loss 3.5117 (3.2999)	grad_norm 1.7977 (2.0582)	
[2022-01-24 09:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1030/1251]	eta 0:08:06 lr 0.000211	time 2.0383 (2.1996)	loss 2.5926 (3.2983)	grad_norm 2.5447 (2.0590)	
[2022-01-24 09:55:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1040/1251]	eta 0:07:44 lr 0.000211	time 1.7667 (2.2024)	loss 3.1779 (3.2982)	grad_norm 2.2656 (2.0581)	
[2022-01-24 09:55:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1050/1251]	eta 0:07:22 lr 0.000211	time 1.7785 (2.2029)	loss 3.5126 (3.2990)	grad_norm 1.9397 (2.0577)	
[2022-01-24 09:55:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1060/1251]	eta 0:07:00 lr 0.000211	time 2.2269 (2.2023)	loss 2.3365 (3.2994)	grad_norm 2.2591 (2.0581)	
[2022-01-24 09:56:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1070/1251]	eta 0:06:38 lr 0.000210	time 1.7292 (2.2001)	loss 3.3113 (3.2995)	grad_norm 2.0988 (2.0581)	
[2022-01-24 09:56:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1080/1251]	eta 0:06:15 lr 0.000210	time 1.9093 (2.1984)	loss 2.5532 (3.2977)	grad_norm 2.2086 (2.0576)	
[2022-01-24 09:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1090/1251]	eta 0:05:54 lr 0.000210	time 1.9936 (2.1998)	loss 3.7649 (3.2970)	grad_norm 2.1546 (2.0596)	
[2022-01-24 09:57:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1100/1251]	eta 0:05:32 lr 0.000210	time 2.4210 (2.1996)	loss 3.4613 (3.2965)	grad_norm 2.2372 (2.0598)	
[2022-01-24 09:57:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1110/1251]	eta 0:05:10 lr 0.000210	time 1.8279 (2.1991)	loss 3.5309 (3.2984)	grad_norm 2.0773 (2.0599)	
[2022-01-24 09:57:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1120/1251]	eta 0:04:48 lr 0.000210	time 3.1344 (2.1996)	loss 3.3910 (3.2979)	grad_norm 1.9466 (2.0605)	
[2022-01-24 09:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1130/1251]	eta 0:04:26 lr 0.000210	time 1.5932 (2.1999)	loss 2.1799 (3.2977)	grad_norm 1.8841 (2.0617)	
[2022-01-24 09:58:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1140/1251]	eta 0:04:04 lr 0.000210	time 1.6200 (2.1990)	loss 2.3267 (3.2962)	grad_norm 1.7705 (2.0615)	
[2022-01-24 09:58:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1150/1251]	eta 0:03:41 lr 0.000210	time 1.8243 (2.1974)	loss 3.0609 (3.2977)	grad_norm 2.2361 (2.0615)	
[2022-01-24 09:59:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1160/1251]	eta 0:03:20 lr 0.000210	time 4.3536 (2.1985)	loss 3.3785 (3.2978)	grad_norm 1.8142 (2.0613)	
[2022-01-24 09:59:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1170/1251]	eta 0:02:58 lr 0.000210	time 2.3502 (2.2024)	loss 3.4090 (3.2966)	grad_norm 2.0229 (2.0625)	
[2022-01-24 10:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1180/1251]	eta 0:02:36 lr 0.000210	time 1.4882 (2.2018)	loss 3.3507 (3.2966)	grad_norm 1.9379 (2.0629)	
[2022-01-24 10:00:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1190/1251]	eta 0:02:14 lr 0.000210	time 1.7892 (2.2008)	loss 2.9132 (3.2973)	grad_norm 2.0354 (2.0641)	
[2022-01-24 10:00:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1200/1251]	eta 0:01:52 lr 0.000210	time 2.4178 (2.2000)	loss 3.0918 (3.2968)	grad_norm 1.7350 (2.0633)	
[2022-01-24 10:01:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1210/1251]	eta 0:01:30 lr 0.000210	time 2.0035 (2.1982)	loss 2.8629 (3.2949)	grad_norm 1.7814 (2.0628)	
[2022-01-24 10:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1220/1251]	eta 0:01:08 lr 0.000210	time 2.0991 (2.1974)	loss 2.7881 (3.2928)	grad_norm 2.0553 (2.0630)	
[2022-01-24 10:01:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1230/1251]	eta 0:00:46 lr 0.000210	time 2.2209 (2.1979)	loss 3.6398 (3.2931)	grad_norm 1.9388 (2.0631)	
[2022-01-24 10:02:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1240/1251]	eta 0:00:24 lr 0.000210	time 1.8011 (2.1980)	loss 3.2891 (3.2907)	grad_norm 2.4736 (2.0640)	
[2022-01-24 10:02:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [210/300][1250/1251]	eta 0:00:02 lr 0.000210	time 1.1891 (2.1932)	loss 3.6029 (3.2914)	grad_norm 1.9857 (2.0639)	
[2022-01-24 10:02:34 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 210 training takes 0:45:44
[2022-01-24 10:02:34 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_210 saving......
[2022-01-24 10:02:45 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_210 saved !!!
[2022-01-24 10:03:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.974 (16.974)	Loss 0.9581 (0.9581)	Acc@1 77.441 (77.441)	Acc@5 94.531 (94.531)	
[2022-01-24 10:03:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.986 (2.915)	Loss 0.9014 (0.9062)	Acc@1 79.395 (78.267)	Acc@5 94.141 (94.513)	
[2022-01-24 10:03:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.333 (2.276)	Loss 0.9183 (0.9147)	Acc@1 78.906 (78.330)	Acc@5 94.141 (94.457)	
[2022-01-24 10:03:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.628 (2.096)	Loss 0.8534 (0.9068)	Acc@1 79.785 (78.497)	Acc@5 95.605 (94.512)	
[2022-01-24 10:04:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.657 (2.000)	Loss 0.9002 (0.9024)	Acc@1 78.809 (78.613)	Acc@5 94.238 (94.536)	
[2022-01-24 10:04:15 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.644 Acc@5 94.592
[2022-01-24 10:04:15 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.6%
[2022-01-24 10:04:15 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.81%
[2022-01-24 10:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][0/1251]	eta 7:29:04 lr 0.000210	time 21.5380 (21.5380)	loss 3.1223 (3.1223)	grad_norm 2.3635 (2.3635)	
[2022-01-24 10:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][10/1251]	eta 1:22:39 lr 0.000210	time 1.8316 (3.9961)	loss 3.6990 (3.1021)	grad_norm 2.1223 (2.0903)	
[2022-01-24 10:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][20/1251]	eta 1:03:09 lr 0.000210	time 1.8182 (3.0785)	loss 2.7987 (3.0326)	grad_norm 2.0127 (2.0653)	
[2022-01-24 10:05:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][30/1251]	eta 0:55:49 lr 0.000210	time 1.6647 (2.7435)	loss 2.9490 (3.1357)	grad_norm 3.1384 (2.1203)	
[2022-01-24 10:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][40/1251]	eta 0:54:37 lr 0.000210	time 5.9517 (2.7066)	loss 2.3178 (3.1530)	grad_norm 2.0575 (2.1568)	
[2022-01-24 10:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][50/1251]	eta 0:52:24 lr 0.000210	time 2.4109 (2.6184)	loss 2.8471 (3.1641)	grad_norm 2.2506 (2.1530)	
[2022-01-24 10:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][60/1251]	eta 0:50:34 lr 0.000210	time 1.5681 (2.5475)	loss 3.5718 (3.1912)	grad_norm 2.5842 (2.1410)	
[2022-01-24 10:07:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][70/1251]	eta 0:49:13 lr 0.000210	time 1.4904 (2.5011)	loss 3.4461 (3.1527)	grad_norm 1.9285 (2.1318)	
[2022-01-24 10:07:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][80/1251]	eta 0:48:38 lr 0.000210	time 3.8282 (2.4922)	loss 2.7581 (3.1652)	grad_norm 2.0121 (2.1160)	
[2022-01-24 10:08:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][90/1251]	eta 0:48:00 lr 0.000210	time 3.1829 (2.4809)	loss 3.2409 (3.1640)	grad_norm 1.8768 (2.1072)	
[2022-01-24 10:08:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][100/1251]	eta 0:47:08 lr 0.000210	time 1.5379 (2.4578)	loss 2.3557 (3.1770)	grad_norm 1.9294 (2.0996)	
[2022-01-24 10:08:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][110/1251]	eta 0:46:05 lr 0.000210	time 1.9281 (2.4236)	loss 3.3201 (3.1958)	grad_norm 1.8366 (2.0869)	
[2022-01-24 10:09:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][120/1251]	eta 0:44:57 lr 0.000209	time 2.4595 (2.3852)	loss 2.9987 (3.1940)	grad_norm 2.0713 (2.0784)	
[2022-01-24 10:09:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][130/1251]	eta 0:44:12 lr 0.000209	time 3.1077 (2.3664)	loss 3.7702 (3.1999)	grad_norm 2.1058 (2.0702)	
[2022-01-24 10:09:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][140/1251]	eta 0:43:42 lr 0.000209	time 2.5190 (2.3608)	loss 3.3820 (3.2035)	grad_norm 2.1884 (2.0696)	
[2022-01-24 10:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][150/1251]	eta 0:43:11 lr 0.000209	time 1.8099 (2.3537)	loss 3.9046 (3.1983)	grad_norm 2.3203 (2.0728)	
[2022-01-24 10:10:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][160/1251]	eta 0:42:53 lr 0.000209	time 2.6367 (2.3587)	loss 3.5133 (3.1970)	grad_norm 2.1113 (2.0680)	
[2022-01-24 10:10:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][170/1251]	eta 0:42:31 lr 0.000209	time 3.4259 (2.3601)	loss 2.7102 (3.1769)	grad_norm 2.0433 (2.0619)	
[2022-01-24 10:11:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][180/1251]	eta 0:41:53 lr 0.000209	time 2.2105 (2.3468)	loss 3.7229 (3.1786)	grad_norm 1.9858 (2.0561)	
[2022-01-24 10:11:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][190/1251]	eta 0:41:11 lr 0.000209	time 1.9859 (2.3292)	loss 2.9209 (3.1801)	grad_norm 1.8943 (2.0537)	
[2022-01-24 10:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][200/1251]	eta 0:40:26 lr 0.000209	time 1.9398 (2.3084)	loss 2.9984 (3.1717)	grad_norm 1.8584 (2.0544)	
[2022-01-24 10:12:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][210/1251]	eta 0:40:00 lr 0.000209	time 3.3622 (2.3057)	loss 3.3963 (3.1797)	grad_norm 2.0022 (2.0522)	
[2022-01-24 10:12:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][220/1251]	eta 0:39:28 lr 0.000209	time 2.2535 (2.2976)	loss 3.7424 (3.1978)	grad_norm 2.1520 (2.0608)	
[2022-01-24 10:13:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][230/1251]	eta 0:38:59 lr 0.000209	time 1.5852 (2.2913)	loss 3.6419 (3.2038)	grad_norm 2.2075 (2.0606)	
[2022-01-24 10:13:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][240/1251]	eta 0:38:27 lr 0.000209	time 1.9210 (2.2825)	loss 3.7857 (3.2110)	grad_norm 1.8670 (2.0579)	
[2022-01-24 10:13:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][250/1251]	eta 0:38:07 lr 0.000209	time 2.9048 (2.2857)	loss 3.2487 (3.2083)	grad_norm 1.8255 (2.0524)	
[2022-01-24 10:14:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][260/1251]	eta 0:37:45 lr 0.000209	time 1.8930 (2.2863)	loss 3.6620 (3.2012)	grad_norm 1.8703 (2.0474)	
[2022-01-24 10:14:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][270/1251]	eta 0:37:17 lr 0.000209	time 2.1820 (2.2813)	loss 3.5756 (3.1968)	grad_norm 1.8542 (2.0470)	
[2022-01-24 10:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][280/1251]	eta 0:36:54 lr 0.000209	time 2.4077 (2.2811)	loss 3.7041 (3.2097)	grad_norm 2.1280 (2.0484)	
[2022-01-24 10:15:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][290/1251]	eta 0:36:31 lr 0.000209	time 2.4044 (2.2804)	loss 3.6081 (3.2079)	grad_norm 2.0852 (2.0482)	
[2022-01-24 10:15:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][300/1251]	eta 0:36:04 lr 0.000209	time 2.5642 (2.2762)	loss 3.9712 (3.2156)	grad_norm 2.0821 (2.0502)	
[2022-01-24 10:16:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][310/1251]	eta 0:35:33 lr 0.000209	time 1.9547 (2.2677)	loss 3.7387 (3.2207)	grad_norm 2.1785 (2.0507)	
[2022-01-24 10:16:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][320/1251]	eta 0:35:09 lr 0.000209	time 2.2693 (2.2659)	loss 2.7838 (3.2209)	grad_norm 1.9484 (2.0507)	
[2022-01-24 10:16:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][330/1251]	eta 0:34:44 lr 0.000209	time 2.2014 (2.2632)	loss 3.4744 (3.2229)	grad_norm 1.9894 (2.0490)	
[2022-01-24 10:17:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][340/1251]	eta 0:34:18 lr 0.000209	time 2.8437 (2.2596)	loss 3.7709 (3.2246)	grad_norm 2.8327 (2.0522)	
[2022-01-24 10:17:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][350/1251]	eta 0:33:54 lr 0.000209	time 1.9097 (2.2584)	loss 3.4147 (3.2217)	grad_norm 1.8493 (2.0501)	
[2022-01-24 10:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][360/1251]	eta 0:33:29 lr 0.000209	time 2.1919 (2.2550)	loss 3.6993 (3.2147)	grad_norm 1.9517 (2.0474)	
[2022-01-24 10:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][370/1251]	eta 0:33:02 lr 0.000209	time 1.8461 (2.2497)	loss 3.1205 (3.2119)	grad_norm 2.3096 (2.0502)	
[2022-01-24 10:18:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][380/1251]	eta 0:32:37 lr 0.000209	time 1.9999 (2.2470)	loss 2.7797 (3.2167)	grad_norm 1.8394 (2.0527)	
[2022-01-24 10:18:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][390/1251]	eta 0:32:15 lr 0.000209	time 2.4346 (2.2477)	loss 2.9326 (3.2134)	grad_norm 2.6522 (2.0582)	
[2022-01-24 10:19:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][400/1251]	eta 0:31:50 lr 0.000209	time 2.1873 (2.2453)	loss 3.1138 (3.2220)	grad_norm 2.3067 (2.0568)	
[2022-01-24 10:19:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][410/1251]	eta 0:31:25 lr 0.000209	time 1.8597 (2.2417)	loss 2.9545 (3.2215)	grad_norm 2.0404 (2.0564)	
[2022-01-24 10:19:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][420/1251]	eta 0:31:00 lr 0.000208	time 2.6460 (2.2390)	loss 3.9799 (3.2299)	grad_norm 1.9339 (2.0555)	
[2022-01-24 10:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][430/1251]	eta 0:30:35 lr 0.000208	time 1.8642 (2.2362)	loss 2.6953 (3.2306)	grad_norm 2.1975 (2.0572)	
[2022-01-24 10:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][440/1251]	eta 0:30:14 lr 0.000208	time 2.3967 (2.2379)	loss 4.1543 (3.2378)	grad_norm 2.2933 (2.0571)	
[2022-01-24 10:21:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][450/1251]	eta 0:29:53 lr 0.000208	time 2.4884 (2.2386)	loss 2.1934 (3.2398)	grad_norm 1.9704 (2.0566)	
[2022-01-24 10:21:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][460/1251]	eta 0:29:29 lr 0.000208	time 2.5057 (2.2376)	loss 3.3756 (3.2443)	grad_norm 1.9383 (2.0563)	
[2022-01-24 10:21:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][470/1251]	eta 0:29:04 lr 0.000208	time 1.8802 (2.2341)	loss 3.8090 (3.2458)	grad_norm 2.4393 (2.0570)	
[2022-01-24 10:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][480/1251]	eta 0:28:41 lr 0.000208	time 2.1287 (2.2325)	loss 2.7582 (3.2406)	grad_norm 2.1043 (2.0573)	
[2022-01-24 10:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][490/1251]	eta 0:28:18 lr 0.000208	time 1.8780 (2.2316)	loss 3.3914 (3.2354)	grad_norm 1.8551 (2.0569)	
[2022-01-24 10:22:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][500/1251]	eta 0:27:58 lr 0.000208	time 2.5060 (2.2353)	loss 3.9737 (3.2327)	grad_norm 2.1230 (2.0566)	
[2022-01-24 10:23:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][510/1251]	eta 0:27:36 lr 0.000208	time 2.1644 (2.2352)	loss 3.3441 (3.2367)	grad_norm 2.4372 (2.0573)	
[2022-01-24 10:23:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][520/1251]	eta 0:27:12 lr 0.000208	time 2.7571 (2.2336)	loss 3.6462 (3.2403)	grad_norm 1.8058 (2.0571)	
[2022-01-24 10:24:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][530/1251]	eta 0:26:47 lr 0.000208	time 1.8698 (2.2301)	loss 4.0927 (3.2440)	grad_norm 1.7305 (2.0553)	
[2022-01-24 10:24:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][540/1251]	eta 0:26:24 lr 0.000208	time 2.7966 (2.2285)	loss 2.4814 (3.2468)	grad_norm 1.8861 (2.0558)	
[2022-01-24 10:24:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][550/1251]	eta 0:26:01 lr 0.000208	time 1.7677 (2.2270)	loss 2.5607 (3.2431)	grad_norm 2.1260 (2.0590)	
[2022-01-24 10:25:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][560/1251]	eta 0:25:38 lr 0.000208	time 2.2776 (2.2259)	loss 3.8107 (3.2456)	grad_norm 1.9933 (2.0621)	
[2022-01-24 10:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][570/1251]	eta 0:25:14 lr 0.000208	time 1.9588 (2.2247)	loss 2.5307 (3.2409)	grad_norm 1.9312 (2.0621)	
[2022-01-24 10:25:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][580/1251]	eta 0:24:54 lr 0.000208	time 3.6412 (2.2277)	loss 2.3555 (3.2346)	grad_norm 2.0902 (2.0619)	
[2022-01-24 10:26:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][590/1251]	eta 0:24:31 lr 0.000208	time 1.8436 (2.2265)	loss 3.0441 (3.2402)	grad_norm 1.9685 (2.0625)	
[2022-01-24 10:26:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][600/1251]	eta 0:24:08 lr 0.000208	time 1.8893 (2.2244)	loss 3.1884 (3.2416)	grad_norm 2.3100 (2.0644)	
[2022-01-24 10:26:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][610/1251]	eta 0:23:44 lr 0.000208	time 1.9531 (2.2223)	loss 3.7397 (3.2450)	grad_norm 1.8187 (2.0638)	
[2022-01-24 10:27:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][620/1251]	eta 0:23:23 lr 0.000208	time 3.0388 (2.2250)	loss 3.5715 (3.2477)	grad_norm 2.2325 (2.0637)	
[2022-01-24 10:27:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][630/1251]	eta 0:23:00 lr 0.000208	time 1.6415 (2.2224)	loss 3.3197 (3.2511)	grad_norm 2.5957 (2.0642)	
[2022-01-24 10:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][640/1251]	eta 0:22:37 lr 0.000208	time 1.8005 (2.2211)	loss 2.9891 (3.2475)	grad_norm 1.9266 (2.0651)	
[2022-01-24 10:28:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][650/1251]	eta 0:22:14 lr 0.000208	time 2.0979 (2.2206)	loss 3.6936 (3.2485)	grad_norm 1.9984 (2.0642)	
[2022-01-24 10:28:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][660/1251]	eta 0:21:52 lr 0.000208	time 2.7115 (2.2201)	loss 4.0053 (3.2472)	grad_norm 2.1760 (2.0636)	
[2022-01-24 10:29:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][670/1251]	eta 0:21:28 lr 0.000208	time 2.2926 (2.2172)	loss 3.2730 (3.2483)	grad_norm 2.6702 (2.0630)	
[2022-01-24 10:29:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][680/1251]	eta 0:21:06 lr 0.000208	time 1.8663 (2.2180)	loss 2.5736 (3.2479)	grad_norm 2.0417 (2.0622)	
[2022-01-24 10:29:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][690/1251]	eta 0:20:44 lr 0.000208	time 2.0914 (2.2191)	loss 3.1905 (3.2477)	grad_norm 2.2306 (2.0605)	
[2022-01-24 10:30:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][700/1251]	eta 0:20:22 lr 0.000208	time 2.1689 (2.2187)	loss 3.1038 (3.2498)	grad_norm 2.0156 (2.0610)	
[2022-01-24 10:30:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][710/1251]	eta 0:19:59 lr 0.000208	time 2.4524 (2.2175)	loss 3.1503 (3.2526)	grad_norm 2.0969 (2.0604)	
[2022-01-24 10:30:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][720/1251]	eta 0:19:37 lr 0.000207	time 1.9227 (2.2169)	loss 3.4421 (3.2543)	grad_norm 2.0555 (2.0599)	
[2022-01-24 10:31:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][730/1251]	eta 0:19:14 lr 0.000207	time 3.2413 (2.2158)	loss 3.8247 (3.2562)	grad_norm 1.9299 (2.0603)	
[2022-01-24 10:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][740/1251]	eta 0:18:53 lr 0.000207	time 2.2172 (2.2183)	loss 3.2691 (3.2575)	grad_norm 1.8248 (2.0596)	
[2022-01-24 10:32:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][750/1251]	eta 0:18:31 lr 0.000207	time 1.9433 (2.2185)	loss 3.4692 (3.2592)	grad_norm 1.9351 (2.0589)	
[2022-01-24 10:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][760/1251]	eta 0:18:09 lr 0.000207	time 1.8174 (2.2182)	loss 2.2415 (3.2592)	grad_norm 2.0351 (2.0595)	
[2022-01-24 10:32:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][770/1251]	eta 0:17:45 lr 0.000207	time 2.0491 (2.2157)	loss 3.5198 (3.2602)	grad_norm 2.2559 (2.0596)	
[2022-01-24 10:33:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][780/1251]	eta 0:17:23 lr 0.000207	time 1.9401 (2.2146)	loss 3.0263 (3.2580)	grad_norm 2.1245 (2.0606)	
[2022-01-24 10:33:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][790/1251]	eta 0:17:00 lr 0.000207	time 1.8452 (2.2128)	loss 3.4078 (3.2578)	grad_norm 2.1298 (2.0622)	
[2022-01-24 10:33:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][800/1251]	eta 0:16:37 lr 0.000207	time 2.1354 (2.2123)	loss 2.5768 (3.2569)	grad_norm 1.9909 (2.0631)	
[2022-01-24 10:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][810/1251]	eta 0:16:15 lr 0.000207	time 2.3636 (2.2118)	loss 4.2575 (3.2631)	grad_norm 2.3179 (2.0666)	
[2022-01-24 10:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][820/1251]	eta 0:15:53 lr 0.000207	time 2.5055 (2.2131)	loss 3.1723 (3.2625)	grad_norm 2.0880 (2.0678)	
[2022-01-24 10:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][830/1251]	eta 0:15:31 lr 0.000207	time 1.8481 (2.2127)	loss 3.0180 (3.2633)	grad_norm 1.9977 (2.0677)	
[2022-01-24 10:35:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][840/1251]	eta 0:15:10 lr 0.000207	time 3.1786 (2.2149)	loss 3.7148 (3.2648)	grad_norm 2.1260 (2.0675)	
[2022-01-24 10:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][850/1251]	eta 0:14:48 lr 0.000207	time 2.0378 (2.2151)	loss 3.9363 (3.2660)	grad_norm 2.2127 (2.0670)	
[2022-01-24 10:36:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][860/1251]	eta 0:14:25 lr 0.000207	time 2.3829 (2.2135)	loss 3.6383 (3.2658)	grad_norm 1.9352 (2.0664)	
[2022-01-24 10:36:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][870/1251]	eta 0:14:02 lr 0.000207	time 2.0399 (2.2117)	loss 3.3407 (3.2664)	grad_norm 1.8558 (2.0656)	
[2022-01-24 10:36:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][880/1251]	eta 0:13:40 lr 0.000207	time 2.2976 (2.2112)	loss 3.7810 (3.2655)	grad_norm 2.1703 (2.0651)	
[2022-01-24 10:37:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][890/1251]	eta 0:13:18 lr 0.000207	time 3.3775 (2.2112)	loss 3.2751 (3.2662)	grad_norm 2.1174 (2.0660)	
[2022-01-24 10:37:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][900/1251]	eta 0:12:55 lr 0.000207	time 2.2446 (2.2097)	loss 2.4281 (3.2668)	grad_norm 2.0137 (2.0679)	
[2022-01-24 10:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][910/1251]	eta 0:12:33 lr 0.000207	time 1.8711 (2.2095)	loss 2.9848 (3.2641)	grad_norm 2.2367 (2.0685)	
[2022-01-24 10:38:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][920/1251]	eta 0:12:11 lr 0.000207	time 1.9177 (2.2098)	loss 3.6917 (3.2657)	grad_norm 2.0928 (2.0689)	
[2022-01-24 10:38:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][930/1251]	eta 0:11:49 lr 0.000207	time 2.7592 (2.2107)	loss 3.1784 (3.2664)	grad_norm 1.8572 (2.0690)	
[2022-01-24 10:38:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][940/1251]	eta 0:11:27 lr 0.000207	time 1.9122 (2.2101)	loss 2.6437 (3.2659)	grad_norm 2.0924 (2.0694)	
[2022-01-24 10:39:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][950/1251]	eta 0:11:04 lr 0.000207	time 1.9495 (2.2090)	loss 2.9239 (3.2637)	grad_norm 1.8146 (2.0697)	
[2022-01-24 10:39:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][960/1251]	eta 0:10:41 lr 0.000207	time 2.0718 (2.2060)	loss 2.7746 (3.2638)	grad_norm 1.8445 (2.0699)	
[2022-01-24 10:39:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][970/1251]	eta 0:10:19 lr 0.000207	time 2.3053 (2.2040)	loss 3.1354 (3.2637)	grad_norm 2.1690 (2.0698)	
[2022-01-24 10:40:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][980/1251]	eta 0:09:57 lr 0.000207	time 1.5651 (2.2038)	loss 2.6073 (3.2651)	grad_norm 2.0789 (2.0695)	
[2022-01-24 10:40:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][990/1251]	eta 0:09:35 lr 0.000207	time 2.2144 (2.2048)	loss 3.6604 (3.2646)	grad_norm 2.1916 (2.0695)	
[2022-01-24 10:41:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1000/1251]	eta 0:09:13 lr 0.000207	time 1.9470 (2.2045)	loss 3.2736 (3.2651)	grad_norm 2.1582 (2.0686)	
[2022-01-24 10:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1010/1251]	eta 0:08:51 lr 0.000207	time 2.2071 (2.2056)	loss 1.9765 (3.2658)	grad_norm 1.8758 (2.0678)	
[2022-01-24 10:41:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1020/1251]	eta 0:08:29 lr 0.000206	time 2.2073 (2.2071)	loss 3.3702 (3.2664)	grad_norm 2.3433 (2.0681)	
[2022-01-24 10:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1030/1251]	eta 0:08:08 lr 0.000206	time 2.2215 (2.2091)	loss 3.5570 (3.2648)	grad_norm 2.6745 (2.0690)	
[2022-01-24 10:42:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1040/1251]	eta 0:07:45 lr 0.000206	time 1.5483 (2.2083)	loss 2.0177 (3.2622)	grad_norm 2.3258 (2.0697)	
[2022-01-24 10:42:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1050/1251]	eta 0:07:23 lr 0.000206	time 1.9726 (2.2082)	loss 3.2876 (3.2638)	grad_norm 2.3527 (2.0705)	
[2022-01-24 10:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1060/1251]	eta 0:07:01 lr 0.000206	time 2.2034 (2.2060)	loss 3.9507 (3.2648)	grad_norm 2.1200 (2.0713)	
[2022-01-24 10:43:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1070/1251]	eta 0:06:39 lr 0.000206	time 1.8616 (2.2050)	loss 3.0538 (3.2664)	grad_norm 1.8252 (2.0701)	
[2022-01-24 10:43:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1080/1251]	eta 0:06:16 lr 0.000206	time 1.5815 (2.2032)	loss 2.9533 (3.2651)	grad_norm 2.1202 (2.0713)	
[2022-01-24 10:44:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1090/1251]	eta 0:05:54 lr 0.000206	time 1.8750 (2.2030)	loss 2.0406 (3.2637)	grad_norm 2.1048 (2.0714)	
[2022-01-24 10:44:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1100/1251]	eta 0:05:32 lr 0.000206	time 1.9301 (2.2025)	loss 3.4804 (3.2611)	grad_norm 2.3732 (2.0711)	
[2022-01-24 10:45:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1110/1251]	eta 0:05:10 lr 0.000206	time 2.2323 (2.2031)	loss 2.3353 (3.2603)	grad_norm 2.4207 (2.0711)	
[2022-01-24 10:45:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1120/1251]	eta 0:04:48 lr 0.000206	time 2.8253 (2.2039)	loss 3.7684 (3.2598)	grad_norm 1.9767 (2.0731)	
[2022-01-24 10:45:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1130/1251]	eta 0:04:26 lr 0.000206	time 2.0733 (2.2041)	loss 3.8156 (3.2611)	grad_norm 1.8000 (2.0738)	
[2022-01-24 10:46:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1140/1251]	eta 0:04:04 lr 0.000206	time 1.5764 (2.2031)	loss 3.6302 (3.2608)	grad_norm 1.8696 (2.0732)	
[2022-01-24 10:46:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1150/1251]	eta 0:03:42 lr 0.000206	time 2.4945 (2.2038)	loss 2.3466 (3.2592)	grad_norm 2.1224 (2.0725)	
[2022-01-24 10:46:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1160/1251]	eta 0:03:20 lr 0.000206	time 2.9891 (2.2052)	loss 2.8185 (3.2590)	grad_norm 1.8080 (2.0719)	
[2022-01-24 10:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1170/1251]	eta 0:02:58 lr 0.000206	time 2.4502 (2.2061)	loss 2.8970 (3.2591)	grad_norm 1.9581 (2.0716)	
[2022-01-24 10:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1180/1251]	eta 0:02:36 lr 0.000206	time 1.8051 (2.2042)	loss 3.7032 (3.2586)	grad_norm 2.0801 (2.0713)	
[2022-01-24 10:47:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1190/1251]	eta 0:02:14 lr 0.000206	time 2.1394 (2.2018)	loss 2.7707 (3.2578)	grad_norm 1.9622 (2.0714)	
[2022-01-24 10:48:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1200/1251]	eta 0:01:52 lr 0.000206	time 1.8143 (2.2004)	loss 2.2991 (3.2561)	grad_norm 2.2683 (2.0717)	
[2022-01-24 10:48:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1210/1251]	eta 0:01:30 lr 0.000206	time 2.2015 (2.2012)	loss 2.3998 (3.2548)	grad_norm 1.9344 (2.0709)	
[2022-01-24 10:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1220/1251]	eta 0:01:08 lr 0.000206	time 2.7785 (2.2075)	loss 3.8388 (3.2547)	grad_norm 2.0391 (2.0696)	
[2022-01-24 10:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1230/1251]	eta 0:00:46 lr 0.000206	time 2.1351 (2.2081)	loss 3.0068 (3.2567)	grad_norm 1.8424 (2.0698)	
[2022-01-24 10:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1240/1251]	eta 0:00:24 lr 0.000206	time 1.4673 (2.2064)	loss 3.9126 (3.2572)	grad_norm 2.0397 (2.0691)	
[2022-01-24 10:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [211/300][1250/1251]	eta 0:00:02 lr 0.000206	time 1.1705 (2.2010)	loss 3.1837 (3.2580)	grad_norm 1.9289 (2.0693)	
[2022-01-24 10:50:09 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 211 training takes 0:45:53
[2022-01-24 10:50:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.099 (19.099)	Loss 0.8596 (0.8596)	Acc@1 81.641 (81.641)	Acc@5 94.922 (94.922)	
[2022-01-24 10:50:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.619 (3.486)	Loss 0.8122 (0.8593)	Acc@1 80.664 (79.892)	Acc@5 95.410 (94.895)	
[2022-01-24 10:51:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.962 (2.807)	Loss 0.8797 (0.8740)	Acc@1 79.395 (79.506)	Acc@5 94.336 (94.745)	
[2022-01-24 10:51:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.603 (2.342)	Loss 0.8715 (0.8853)	Acc@1 79.199 (79.300)	Acc@5 95.410 (94.629)	
[2022-01-24 10:51:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.171 (2.136)	Loss 1.0065 (0.8912)	Acc@1 75.000 (79.028)	Acc@5 93.945 (94.650)	
[2022-01-24 10:51:44 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.992 Acc@5 94.590
[2022-01-24 10:51:44 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.0%
[2022-01-24 10:51:44 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.99%
[2022-01-24 10:52:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][0/1251]	eta 7:25:47 lr 0.000206	time 21.3806 (21.3806)	loss 2.7056 (2.7056)	grad_norm 1.9276 (1.9276)	
[2022-01-24 10:52:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][10/1251]	eta 1:25:11 lr 0.000206	time 2.9424 (4.1186)	loss 2.9296 (3.1943)	grad_norm 2.1803 (2.0377)	
[2022-01-24 10:52:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][20/1251]	eta 1:06:25 lr 0.000206	time 1.4764 (3.2376)	loss 3.7462 (3.2666)	grad_norm 1.8668 (2.0402)	
[2022-01-24 10:53:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][30/1251]	eta 0:58:35 lr 0.000206	time 1.8790 (2.8794)	loss 2.8595 (3.2442)	grad_norm 2.4975 (2.1474)	
[2022-01-24 10:53:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][40/1251]	eta 0:55:09 lr 0.000206	time 3.7735 (2.7327)	loss 3.6546 (3.1941)	grad_norm 1.8901 (2.1518)	
[2022-01-24 10:54:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][50/1251]	eta 0:53:26 lr 0.000206	time 2.6793 (2.6695)	loss 3.0864 (3.2034)	grad_norm 2.1911 (2.1268)	
[2022-01-24 10:54:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][60/1251]	eta 0:51:39 lr 0.000206	time 1.3455 (2.6023)	loss 2.2272 (3.1769)	grad_norm 2.0513 (2.1150)	
[2022-01-24 10:54:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][70/1251]	eta 0:50:04 lr 0.000205	time 2.2007 (2.5439)	loss 3.2142 (3.2210)	grad_norm 3.0386 (2.1269)	
[2022-01-24 10:55:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][80/1251]	eta 0:48:52 lr 0.000205	time 2.9689 (2.5043)	loss 3.4472 (3.2272)	grad_norm 2.1379 (2.1139)	
[2022-01-24 10:55:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][90/1251]	eta 0:47:22 lr 0.000205	time 1.8754 (2.4486)	loss 3.4593 (3.2041)	grad_norm 2.1400 (2.1028)	
[2022-01-24 10:55:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][100/1251]	eta 0:46:07 lr 0.000205	time 1.9575 (2.4040)	loss 2.3071 (3.2183)	grad_norm 2.1644 (2.0941)	
[2022-01-24 10:56:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][110/1251]	eta 0:45:19 lr 0.000205	time 2.0656 (2.3832)	loss 2.1422 (3.2117)	grad_norm 1.8852 (2.0881)	
[2022-01-24 10:56:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][120/1251]	eta 0:44:34 lr 0.000205	time 1.9009 (2.3644)	loss 3.6141 (3.2168)	grad_norm 2.3692 (2.0883)	
[2022-01-24 10:56:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][130/1251]	eta 0:44:10 lr 0.000205	time 2.0192 (2.3643)	loss 3.7335 (3.2440)	grad_norm 1.9693 (2.0928)	
[2022-01-24 10:57:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][140/1251]	eta 0:43:37 lr 0.000205	time 2.4806 (2.3562)	loss 3.2989 (3.2491)	grad_norm 2.1702 (2.0868)	
[2022-01-24 10:57:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][150/1251]	eta 0:43:02 lr 0.000205	time 1.4946 (2.3456)	loss 3.7988 (3.2620)	grad_norm 2.2713 (2.0870)	
[2022-01-24 10:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][160/1251]	eta 0:42:24 lr 0.000205	time 1.7279 (2.3323)	loss 3.5466 (3.2700)	grad_norm 2.0627 (2.0955)	
[2022-01-24 10:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][170/1251]	eta 0:41:55 lr 0.000205	time 1.7087 (2.3272)	loss 3.6463 (3.2722)	grad_norm 2.0781 (2.0925)	
[2022-01-24 10:58:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][180/1251]	eta 0:41:23 lr 0.000205	time 1.6389 (2.3187)	loss 3.2434 (3.2617)	grad_norm 2.2328 (2.0907)	
[2022-01-24 10:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][190/1251]	eta 0:40:46 lr 0.000205	time 1.8247 (2.3054)	loss 3.0531 (3.2722)	grad_norm 1.9793 (2.0910)	
[2022-01-24 10:59:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][200/1251]	eta 0:40:12 lr 0.000205	time 1.6891 (2.2957)	loss 3.3658 (3.2799)	grad_norm 1.9762 (2.0887)	
[2022-01-24 10:59:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][210/1251]	eta 0:39:44 lr 0.000205	time 1.9325 (2.2910)	loss 2.9277 (3.2820)	grad_norm 2.0300 (2.0940)	
[2022-01-24 11:00:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][220/1251]	eta 0:39:14 lr 0.000205	time 1.8194 (2.2835)	loss 2.7289 (3.2743)	grad_norm 2.3738 (2.0960)	
[2022-01-24 11:00:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][230/1251]	eta 0:38:44 lr 0.000205	time 1.5691 (2.2770)	loss 2.4221 (3.2747)	grad_norm 1.9416 (2.0970)	
[2022-01-24 11:00:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][240/1251]	eta 0:38:21 lr 0.000205	time 1.6707 (2.2760)	loss 3.1343 (3.2626)	grad_norm 1.7872 (2.0944)	
[2022-01-24 11:01:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][250/1251]	eta 0:38:02 lr 0.000205	time 1.8976 (2.2799)	loss 3.3483 (3.2645)	grad_norm 2.0331 (2.0942)	
[2022-01-24 11:01:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][260/1251]	eta 0:37:32 lr 0.000205	time 1.5433 (2.2726)	loss 3.3377 (3.2574)	grad_norm 1.8366 (2.0937)	
[2022-01-24 11:01:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][270/1251]	eta 0:37:03 lr 0.000205	time 1.8317 (2.2667)	loss 3.3217 (3.2511)	grad_norm 1.9245 (2.0928)	
[2022-01-24 11:02:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][280/1251]	eta 0:36:34 lr 0.000205	time 1.7410 (2.2604)	loss 3.4473 (3.2442)	grad_norm 2.1846 (2.0925)	
[2022-01-24 11:02:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][290/1251]	eta 0:36:10 lr 0.000205	time 2.2470 (2.2584)	loss 3.9927 (3.2432)	grad_norm 2.1182 (2.0931)	
[2022-01-24 11:03:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][300/1251]	eta 0:35:43 lr 0.000205	time 1.8391 (2.2534)	loss 2.3324 (3.2385)	grad_norm 1.8742 (2.0900)	
[2022-01-24 11:03:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][310/1251]	eta 0:35:19 lr 0.000205	time 2.4603 (2.2524)	loss 3.9942 (3.2357)	grad_norm 2.2182 (2.0890)	
[2022-01-24 11:03:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][320/1251]	eta 0:34:49 lr 0.000205	time 1.8007 (2.2445)	loss 2.8763 (3.2299)	grad_norm 2.0106 (2.0901)	
[2022-01-24 11:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][330/1251]	eta 0:34:23 lr 0.000205	time 2.0088 (2.2405)	loss 3.9108 (3.2263)	grad_norm 2.1652 (2.0920)	
[2022-01-24 11:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][340/1251]	eta 0:33:59 lr 0.000205	time 2.5119 (2.2388)	loss 3.0145 (3.2241)	grad_norm 2.0739 (2.0909)	
[2022-01-24 11:04:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][350/1251]	eta 0:33:37 lr 0.000205	time 3.0105 (2.2393)	loss 3.7809 (3.2313)	grad_norm 2.5645 (2.0902)	
[2022-01-24 11:05:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][360/1251]	eta 0:33:15 lr 0.000205	time 1.8967 (2.2396)	loss 3.2346 (3.2368)	grad_norm 2.1038 (2.0914)	
[2022-01-24 11:05:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][370/1251]	eta 0:32:53 lr 0.000205	time 2.1287 (2.2406)	loss 2.6811 (3.2376)	grad_norm 2.0508 (2.0935)	
[2022-01-24 11:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][380/1251]	eta 0:32:30 lr 0.000204	time 2.2271 (2.2397)	loss 3.1756 (3.2341)	grad_norm 2.0579 (2.0953)	
[2022-01-24 11:06:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][390/1251]	eta 0:32:05 lr 0.000204	time 2.7213 (2.2366)	loss 2.3227 (3.2299)	grad_norm 1.9244 (2.0953)	
[2022-01-24 11:06:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][400/1251]	eta 0:31:42 lr 0.000204	time 2.0965 (2.2355)	loss 3.8395 (3.2329)	grad_norm 2.2190 (2.0965)	
[2022-01-24 11:07:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][410/1251]	eta 0:31:19 lr 0.000204	time 1.6509 (2.2344)	loss 2.4791 (3.2371)	grad_norm 2.1178 (2.0964)	
[2022-01-24 11:07:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][420/1251]	eta 0:30:57 lr 0.000204	time 2.2949 (2.2352)	loss 3.5030 (3.2305)	grad_norm 1.8582 (2.0966)	
[2022-01-24 11:07:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][430/1251]	eta 0:30:33 lr 0.000204	time 2.2281 (2.2334)	loss 2.6260 (3.2270)	grad_norm 2.2019 (2.0968)	
[2022-01-24 11:08:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][440/1251]	eta 0:30:09 lr 0.000204	time 2.0217 (2.2315)	loss 2.6955 (3.2272)	grad_norm 2.1112 (2.0946)	
[2022-01-24 11:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][450/1251]	eta 0:29:44 lr 0.000204	time 1.7607 (2.2274)	loss 3.9795 (3.2320)	grad_norm 1.9013 (2.0937)	
[2022-01-24 11:08:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][460/1251]	eta 0:29:20 lr 0.000204	time 2.5235 (2.2259)	loss 2.6791 (3.2296)	grad_norm 1.8575 (2.0904)	
[2022-01-24 11:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][470/1251]	eta 0:28:55 lr 0.000204	time 1.6075 (2.2224)	loss 3.4651 (3.2314)	grad_norm 1.7445 (2.0895)	
[2022-01-24 11:09:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][480/1251]	eta 0:28:36 lr 0.000204	time 2.7486 (2.2267)	loss 3.7977 (3.2333)	grad_norm 1.9038 (2.0881)	
[2022-01-24 11:09:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][490/1251]	eta 0:28:15 lr 0.000204	time 2.2986 (2.2278)	loss 2.9239 (3.2312)	grad_norm 1.8271 (2.0856)	
[2022-01-24 11:10:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][500/1251]	eta 0:27:53 lr 0.000204	time 2.8517 (2.2289)	loss 3.5495 (3.2300)	grad_norm 2.2967 (2.0964)	
[2022-01-24 11:10:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][510/1251]	eta 0:27:27 lr 0.000204	time 1.6392 (2.2239)	loss 3.7881 (3.2274)	grad_norm 2.0142 (2.0991)	
[2022-01-24 11:11:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][520/1251]	eta 0:27:05 lr 0.000204	time 1.6145 (2.2237)	loss 3.1188 (3.2303)	grad_norm 2.0077 (2.0993)	
[2022-01-24 11:11:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][530/1251]	eta 0:26:43 lr 0.000204	time 2.2513 (2.2240)	loss 3.4869 (3.2308)	grad_norm 1.9505 (2.0968)	
[2022-01-24 11:11:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][540/1251]	eta 0:26:22 lr 0.000204	time 2.9131 (2.2255)	loss 3.3207 (3.2329)	grad_norm 2.1465 (2.0965)	
[2022-01-24 11:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][550/1251]	eta 0:25:58 lr 0.000204	time 1.9571 (2.2233)	loss 3.4749 (3.2364)	grad_norm 3.0442 (2.0971)	
[2022-01-24 11:12:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][560/1251]	eta 0:25:36 lr 0.000204	time 2.3458 (2.2231)	loss 3.9738 (3.2380)	grad_norm 2.1659 (2.0967)	
[2022-01-24 11:12:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][570/1251]	eta 0:25:14 lr 0.000204	time 1.8023 (2.2238)	loss 3.4185 (3.2397)	grad_norm 2.1908 (2.0986)	
[2022-01-24 11:13:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][580/1251]	eta 0:24:53 lr 0.000204	time 2.4338 (2.2252)	loss 3.8527 (3.2392)	grad_norm 2.2408 (2.0986)	
[2022-01-24 11:13:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][590/1251]	eta 0:24:28 lr 0.000204	time 1.7479 (2.2218)	loss 2.4737 (3.2394)	grad_norm 2.5887 (2.1001)	
[2022-01-24 11:13:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][600/1251]	eta 0:24:06 lr 0.000204	time 3.0153 (2.2218)	loss 3.0067 (3.2425)	grad_norm 2.2557 (2.1003)	
[2022-01-24 11:14:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][610/1251]	eta 0:23:43 lr 0.000204	time 1.8805 (2.2207)	loss 2.9649 (3.2438)	grad_norm 1.9801 (2.1025)	
[2022-01-24 11:14:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][620/1251]	eta 0:23:20 lr 0.000204	time 2.2240 (2.2195)	loss 3.4816 (3.2458)	grad_norm 2.2783 (2.1018)	
[2022-01-24 11:15:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][630/1251]	eta 0:22:56 lr 0.000204	time 2.0158 (2.2173)	loss 3.4328 (3.2446)	grad_norm 2.3149 (2.1019)	
[2022-01-24 11:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][640/1251]	eta 0:22:34 lr 0.000204	time 3.2421 (2.2165)	loss 2.9015 (3.2438)	grad_norm 2.2289 (2.1002)	
[2022-01-24 11:15:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][650/1251]	eta 0:22:11 lr 0.000204	time 1.6237 (2.2150)	loss 3.4092 (3.2467)	grad_norm 1.7328 (2.0993)	
[2022-01-24 11:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][660/1251]	eta 0:21:48 lr 0.000204	time 2.5879 (2.2145)	loss 3.6336 (3.2491)	grad_norm 1.9077 (2.0995)	
[2022-01-24 11:16:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][670/1251]	eta 0:21:26 lr 0.000204	time 1.7888 (2.2135)	loss 3.6648 (3.2524)	grad_norm 1.7755 (2.0988)	
[2022-01-24 11:16:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][680/1251]	eta 0:21:04 lr 0.000203	time 3.2819 (2.2154)	loss 3.2726 (3.2505)	grad_norm 1.9869 (2.0978)	
[2022-01-24 11:17:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][690/1251]	eta 0:20:42 lr 0.000203	time 2.1384 (2.2141)	loss 2.3793 (3.2478)	grad_norm 2.0164 (2.0958)	
[2022-01-24 11:17:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][700/1251]	eta 0:20:18 lr 0.000203	time 2.1775 (2.2116)	loss 3.4017 (3.2491)	grad_norm 1.9460 (2.0946)	
[2022-01-24 11:17:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][710/1251]	eta 0:19:55 lr 0.000203	time 1.7119 (2.2098)	loss 3.6258 (3.2497)	grad_norm 2.1292 (2.0943)	
[2022-01-24 11:18:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][720/1251]	eta 0:19:33 lr 0.000203	time 2.4117 (2.2100)	loss 3.4107 (3.2510)	grad_norm 1.8571 (2.0930)	
[2022-01-24 11:18:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][730/1251]	eta 0:19:11 lr 0.000203	time 2.0781 (2.2103)	loss 3.3967 (3.2526)	grad_norm 1.8992 (2.0917)	
[2022-01-24 11:19:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][740/1251]	eta 0:18:48 lr 0.000203	time 1.5023 (2.2076)	loss 3.3777 (3.2487)	grad_norm 1.8361 (2.0924)	
[2022-01-24 11:19:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][750/1251]	eta 0:18:25 lr 0.000203	time 1.7204 (2.2067)	loss 3.1438 (3.2491)	grad_norm 4.0929 (2.0948)	
[2022-01-24 11:19:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][760/1251]	eta 0:18:02 lr 0.000203	time 2.5107 (2.2053)	loss 2.8994 (3.2470)	grad_norm 2.1588 (2.0994)	
[2022-01-24 11:20:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][770/1251]	eta 0:17:41 lr 0.000203	time 2.7180 (2.2060)	loss 3.1699 (3.2466)	grad_norm 1.9069 (2.1001)	
[2022-01-24 11:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][780/1251]	eta 0:17:19 lr 0.000203	time 2.2001 (2.2069)	loss 3.7850 (3.2470)	grad_norm 1.9801 (2.1005)	
[2022-01-24 11:20:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][790/1251]	eta 0:16:58 lr 0.000203	time 2.1818 (2.2085)	loss 2.8122 (3.2497)	grad_norm 1.8471 (2.1013)	
[2022-01-24 11:21:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][800/1251]	eta 0:16:36 lr 0.000203	time 2.6232 (2.2087)	loss 3.5347 (3.2520)	grad_norm 2.0829 (2.1016)	
[2022-01-24 11:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][810/1251]	eta 0:16:14 lr 0.000203	time 2.0902 (2.2092)	loss 3.0415 (3.2526)	grad_norm 2.0818 (2.1026)	
[2022-01-24 11:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][820/1251]	eta 0:15:51 lr 0.000203	time 2.2165 (2.2088)	loss 3.1775 (3.2507)	grad_norm 2.3202 (2.1042)	
[2022-01-24 11:22:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][830/1251]	eta 0:15:29 lr 0.000203	time 1.8587 (2.2089)	loss 2.6761 (3.2508)	grad_norm 3.6402 (2.1068)	
[2022-01-24 11:22:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][840/1251]	eta 0:15:07 lr 0.000203	time 2.2753 (2.2076)	loss 3.0645 (3.2488)	grad_norm 2.2958 (2.1083)	
[2022-01-24 11:23:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][850/1251]	eta 0:14:45 lr 0.000203	time 2.4773 (2.2077)	loss 3.1430 (3.2508)	grad_norm 1.8836 (2.1080)	
[2022-01-24 11:23:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][860/1251]	eta 0:14:23 lr 0.000203	time 1.9426 (2.2079)	loss 2.9684 (3.2501)	grad_norm 1.8946 (2.1080)	
[2022-01-24 11:23:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][870/1251]	eta 0:14:00 lr 0.000203	time 2.0132 (2.2065)	loss 3.6531 (3.2499)	grad_norm 1.9987 (2.1072)	
[2022-01-24 11:24:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][880/1251]	eta 0:13:38 lr 0.000203	time 2.2561 (2.2058)	loss 3.7657 (3.2548)	grad_norm 2.4375 (2.1076)	
[2022-01-24 11:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][890/1251]	eta 0:13:16 lr 0.000203	time 2.4024 (2.2053)	loss 2.7977 (3.2534)	grad_norm 1.8033 (2.1066)	
[2022-01-24 11:24:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][900/1251]	eta 0:12:54 lr 0.000203	time 2.2671 (2.2062)	loss 3.5463 (3.2554)	grad_norm 2.0289 (2.1056)	
[2022-01-24 11:25:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][910/1251]	eta 0:12:32 lr 0.000203	time 2.3506 (2.2064)	loss 3.0529 (3.2557)	grad_norm 1.9284 (2.1036)	
[2022-01-24 11:25:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][920/1251]	eta 0:12:10 lr 0.000203	time 1.5941 (2.2065)	loss 3.5442 (3.2553)	grad_norm 1.8877 (2.1018)	
[2022-01-24 11:25:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][930/1251]	eta 0:11:47 lr 0.000203	time 2.4378 (2.2054)	loss 3.7480 (3.2567)	grad_norm 1.9153 (2.1011)	
[2022-01-24 11:26:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][940/1251]	eta 0:11:25 lr 0.000203	time 1.9135 (2.2036)	loss 3.2976 (3.2558)	grad_norm 1.9955 (2.1003)	
[2022-01-24 11:26:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][950/1251]	eta 0:11:02 lr 0.000203	time 2.5064 (2.2017)	loss 2.3261 (3.2546)	grad_norm 1.9199 (2.1001)	
[2022-01-24 11:26:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][960/1251]	eta 0:10:40 lr 0.000203	time 2.1914 (2.2010)	loss 2.8592 (3.2545)	grad_norm 2.1314 (2.1002)	
[2022-01-24 11:27:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][970/1251]	eta 0:10:18 lr 0.000203	time 2.1783 (2.2005)	loss 2.8518 (3.2547)	grad_norm 2.0089 (2.1010)	
[2022-01-24 11:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][980/1251]	eta 0:09:56 lr 0.000202	time 2.1479 (2.2016)	loss 2.2337 (3.2537)	grad_norm 1.8193 (2.1014)	
[2022-01-24 11:28:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][990/1251]	eta 0:09:34 lr 0.000202	time 2.3790 (2.2022)	loss 2.3210 (3.2540)	grad_norm 1.8609 (2.1015)	
[2022-01-24 11:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1000/1251]	eta 0:09:12 lr 0.000202	time 1.9519 (2.2028)	loss 3.6915 (3.2544)	grad_norm 2.5283 (2.1011)	
[2022-01-24 11:28:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1010/1251]	eta 0:08:50 lr 0.000202	time 2.4369 (2.2028)	loss 3.2272 (3.2556)	grad_norm 1.7953 (2.1017)	
[2022-01-24 11:29:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1020/1251]	eta 0:08:28 lr 0.000202	time 2.6250 (2.2033)	loss 2.2375 (3.2537)	grad_norm 2.0195 (2.1020)	
[2022-01-24 11:29:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1030/1251]	eta 0:08:06 lr 0.000202	time 2.4657 (2.2019)	loss 2.9277 (3.2525)	grad_norm 2.1718 (2.1015)	
[2022-01-24 11:29:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1040/1251]	eta 0:07:44 lr 0.000202	time 2.0264 (2.2016)	loss 2.9641 (3.2523)	grad_norm 2.4401 (2.1011)	
[2022-01-24 11:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1050/1251]	eta 0:07:22 lr 0.000202	time 2.5429 (2.2017)	loss 2.8570 (3.2503)	grad_norm 1.9764 (2.1000)	
[2022-01-24 11:30:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1060/1251]	eta 0:07:00 lr 0.000202	time 1.4956 (2.2015)	loss 3.7222 (3.2529)	grad_norm 2.0955 (2.0991)	
[2022-01-24 11:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1070/1251]	eta 0:06:38 lr 0.000202	time 2.1749 (2.2013)	loss 3.1336 (3.2528)	grad_norm 2.0293 (2.0983)	
[2022-01-24 11:31:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1080/1251]	eta 0:06:16 lr 0.000202	time 1.9285 (2.2005)	loss 2.3322 (3.2536)	grad_norm 1.9555 (2.0987)	
[2022-01-24 11:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1090/1251]	eta 0:05:54 lr 0.000202	time 1.8858 (2.1989)	loss 3.4875 (3.2537)	grad_norm 2.1312 (2.0978)	
[2022-01-24 11:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1100/1251]	eta 0:05:31 lr 0.000202	time 1.9133 (2.1985)	loss 2.6949 (3.2528)	grad_norm 2.1274 (2.0974)	
[2022-01-24 11:32:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1110/1251]	eta 0:05:10 lr 0.000202	time 1.9157 (2.1986)	loss 3.2318 (3.2537)	grad_norm 1.9520 (2.0971)	
[2022-01-24 11:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1120/1251]	eta 0:04:48 lr 0.000202	time 1.4664 (2.1988)	loss 3.5434 (3.2544)	grad_norm 1.8905 (2.0971)	
[2022-01-24 11:33:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1130/1251]	eta 0:04:26 lr 0.000202	time 1.6880 (2.1996)	loss 3.2723 (3.2528)	grad_norm 2.0851 (2.0965)	
[2022-01-24 11:33:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1140/1251]	eta 0:04:04 lr 0.000202	time 2.2504 (2.1993)	loss 2.5049 (3.2538)	grad_norm 1.9478 (2.0960)	
[2022-01-24 11:33:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1150/1251]	eta 0:03:42 lr 0.000202	time 1.9125 (2.1991)	loss 3.6959 (3.2544)	grad_norm 1.9663 (2.0953)	
[2022-01-24 11:34:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1160/1251]	eta 0:03:20 lr 0.000202	time 1.8044 (2.1994)	loss 3.4860 (3.2552)	grad_norm 2.2297 (2.0951)	
[2022-01-24 11:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1170/1251]	eta 0:02:58 lr 0.000202	time 1.8214 (2.1981)	loss 3.2746 (3.2526)	grad_norm 2.0207 (2.0956)	
[2022-01-24 11:34:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1180/1251]	eta 0:02:35 lr 0.000202	time 1.9068 (2.1963)	loss 3.3278 (3.2526)	grad_norm 1.9168 (2.0953)	
[2022-01-24 11:35:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1190/1251]	eta 0:02:13 lr 0.000202	time 1.9107 (2.1956)	loss 2.6508 (3.2542)	grad_norm 2.0501 (2.0955)	
[2022-01-24 11:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1200/1251]	eta 0:01:51 lr 0.000202	time 2.4942 (2.1953)	loss 3.1255 (3.2543)	grad_norm 1.8272 (2.0947)	
[2022-01-24 11:36:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1210/1251]	eta 0:01:30 lr 0.000202	time 2.1543 (2.1956)	loss 4.1128 (3.2547)	grad_norm 2.2594 (2.0943)	
[2022-01-24 11:36:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1220/1251]	eta 0:01:08 lr 0.000202	time 1.9777 (2.1960)	loss 3.6914 (3.2562)	grad_norm 2.0490 (2.0941)	
[2022-01-24 11:36:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1230/1251]	eta 0:00:46 lr 0.000202	time 2.1268 (2.1968)	loss 2.3055 (3.2555)	grad_norm 1.8290 (2.0938)	
[2022-01-24 11:37:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1240/1251]	eta 0:00:24 lr 0.000202	time 2.2258 (2.1970)	loss 3.0579 (3.2542)	grad_norm 2.0384 (2.0934)	
[2022-01-24 11:37:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [212/300][1250/1251]	eta 0:00:02 lr 0.000202	time 1.1213 (2.1910)	loss 2.7309 (3.2533)	grad_norm 1.8407 (2.0923)	
[2022-01-24 11:37:25 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 212 training takes 0:45:41
[2022-01-24 11:37:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.312 (18.312)	Loss 0.8599 (0.8599)	Acc@1 80.371 (80.371)	Acc@5 94.824 (94.824)	
[2022-01-24 11:38:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.084 (3.170)	Loss 0.8966 (0.9214)	Acc@1 79.102 (78.622)	Acc@5 95.117 (94.158)	
[2022-01-24 11:38:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.984 (2.629)	Loss 0.7919 (0.9000)	Acc@1 80.957 (78.790)	Acc@5 96.289 (94.522)	
[2022-01-24 11:38:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.612 (2.286)	Loss 0.8953 (0.9033)	Acc@1 78.125 (78.676)	Acc@5 94.336 (94.509)	
[2022-01-24 11:38:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.874 (2.141)	Loss 0.8564 (0.8979)	Acc@1 78.809 (78.699)	Acc@5 94.922 (94.617)	
[2022-01-24 11:39:00 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.772 Acc@5 94.690
[2022-01-24 11:39:00 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.8%
[2022-01-24 11:39:00 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.99%
[2022-01-24 11:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][0/1251]	eta 7:25:30 lr 0.000202	time 21.3674 (21.3674)	loss 4.0257 (4.0257)	grad_norm 1.9693 (1.9693)	
[2022-01-24 11:39:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][10/1251]	eta 1:23:30 lr 0.000202	time 2.8040 (4.0374)	loss 3.6266 (3.5017)	grad_norm 1.7509 (1.9910)	
[2022-01-24 11:40:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][20/1251]	eta 1:06:34 lr 0.000202	time 2.2534 (3.2449)	loss 3.5933 (3.3634)	grad_norm 1.6066 (1.9769)	
[2022-01-24 11:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][30/1251]	eta 0:59:09 lr 0.000202	time 1.9334 (2.9073)	loss 2.3558 (3.2668)	grad_norm 2.0998 (2.0238)	
[2022-01-24 11:40:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][40/1251]	eta 0:55:25 lr 0.000201	time 2.8307 (2.7458)	loss 2.6545 (3.2595)	grad_norm 1.8916 (2.0426)	
[2022-01-24 11:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][50/1251]	eta 0:53:13 lr 0.000201	time 2.8394 (2.6588)	loss 2.8593 (3.2418)	grad_norm 1.8676 (2.0669)	
[2022-01-24 11:41:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][60/1251]	eta 0:51:25 lr 0.000201	time 2.2516 (2.5911)	loss 2.4738 (3.2142)	grad_norm 2.4219 (2.0665)	
[2022-01-24 11:42:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][70/1251]	eta 0:49:47 lr 0.000201	time 1.8324 (2.5296)	loss 3.8636 (3.2290)	grad_norm 1.9039 (2.0969)	
[2022-01-24 11:42:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][80/1251]	eta 0:48:25 lr 0.000201	time 2.2702 (2.4811)	loss 3.5954 (3.2160)	grad_norm 2.0054 (2.0905)	
[2022-01-24 11:42:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][90/1251]	eta 0:47:21 lr 0.000201	time 2.5108 (2.4473)	loss 3.5384 (3.2158)	grad_norm 2.1599 (2.0966)	
[2022-01-24 11:43:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][100/1251]	eta 0:46:12 lr 0.000201	time 1.6127 (2.4088)	loss 3.7901 (3.2305)	grad_norm 2.0824 (2.0926)	
[2022-01-24 11:43:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][110/1251]	eta 0:45:27 lr 0.000201	time 2.2752 (2.3905)	loss 3.5236 (3.2368)	grad_norm 2.6630 (2.0910)	
[2022-01-24 11:43:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][120/1251]	eta 0:44:48 lr 0.000201	time 2.2734 (2.3770)	loss 4.1097 (3.2563)	grad_norm 2.0655 (2.0935)	
[2022-01-24 11:44:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][130/1251]	eta 0:44:07 lr 0.000201	time 1.8303 (2.3621)	loss 3.1261 (3.2664)	grad_norm 2.2770 (2.0972)	
[2022-01-24 11:44:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][140/1251]	eta 0:43:29 lr 0.000201	time 1.5053 (2.3492)	loss 2.4570 (3.2609)	grad_norm 2.2137 (2.0940)	
[2022-01-24 11:44:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][150/1251]	eta 0:43:00 lr 0.000201	time 2.1336 (2.3440)	loss 2.6829 (3.2636)	grad_norm 1.8256 (2.1176)	
[2022-01-24 11:45:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][160/1251]	eta 0:42:37 lr 0.000201	time 2.8827 (2.3441)	loss 2.7422 (3.2625)	grad_norm 2.4474 (2.1193)	
[2022-01-24 11:45:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][170/1251]	eta 0:42:05 lr 0.000201	time 2.1807 (2.3362)	loss 3.8141 (3.2471)	grad_norm 2.4293 (2.1151)	
[2022-01-24 11:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][180/1251]	eta 0:41:23 lr 0.000201	time 1.8868 (2.3191)	loss 3.3322 (3.2520)	grad_norm 2.4364 (2.1150)	
[2022-01-24 11:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][190/1251]	eta 0:40:33 lr 0.000201	time 1.8270 (2.2933)	loss 3.1304 (3.2618)	grad_norm 1.8315 (2.1214)	
[2022-01-24 11:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][200/1251]	eta 0:39:53 lr 0.000201	time 1.6234 (2.2776)	loss 3.9246 (3.2689)	grad_norm 2.2104 (2.1169)	
[2022-01-24 11:46:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][210/1251]	eta 0:39:21 lr 0.000201	time 2.2855 (2.2689)	loss 2.1884 (3.2631)	grad_norm 2.2248 (2.1186)	
[2022-01-24 11:47:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][220/1251]	eta 0:38:55 lr 0.000201	time 2.5363 (2.2653)	loss 2.8294 (3.2605)	grad_norm 1.9513 (2.1147)	
[2022-01-24 11:47:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][230/1251]	eta 0:38:35 lr 0.000201	time 2.8205 (2.2684)	loss 3.6800 (3.2596)	grad_norm 2.4890 (2.1144)	
[2022-01-24 11:48:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][240/1251]	eta 0:38:12 lr 0.000201	time 1.5833 (2.2671)	loss 3.6764 (3.2745)	grad_norm 1.9943 (2.1210)	
[2022-01-24 11:48:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][250/1251]	eta 0:37:54 lr 0.000201	time 1.8380 (2.2718)	loss 3.6781 (3.2687)	grad_norm 2.0059 (2.1222)	
[2022-01-24 11:48:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][260/1251]	eta 0:37:34 lr 0.000201	time 1.7547 (2.2749)	loss 3.3613 (3.2825)	grad_norm 2.1863 (2.1208)	
[2022-01-24 11:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][270/1251]	eta 0:37:11 lr 0.000201	time 2.5125 (2.2747)	loss 3.4796 (3.2819)	grad_norm 1.9020 (2.1208)	
[2022-01-24 11:49:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][280/1251]	eta 0:36:41 lr 0.000201	time 1.6668 (2.2672)	loss 3.6492 (3.2786)	grad_norm 1.8462 (2.1214)	
[2022-01-24 11:49:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][290/1251]	eta 0:36:11 lr 0.000201	time 1.9366 (2.2601)	loss 3.3084 (3.2841)	grad_norm 2.1012 (2.1196)	
[2022-01-24 11:50:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][300/1251]	eta 0:35:44 lr 0.000201	time 2.2324 (2.2548)	loss 3.6876 (3.2840)	grad_norm 2.0664 (2.1144)	
[2022-01-24 11:50:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][310/1251]	eta 0:35:22 lr 0.000201	time 2.6409 (2.2561)	loss 3.5298 (3.2855)	grad_norm 1.9078 (2.1097)	
[2022-01-24 11:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][320/1251]	eta 0:35:00 lr 0.000201	time 1.5132 (2.2558)	loss 3.6972 (3.2815)	grad_norm 1.8012 (2.1064)	
[2022-01-24 11:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][330/1251]	eta 0:34:37 lr 0.000201	time 1.8472 (2.2555)	loss 2.7664 (3.2798)	grad_norm 2.2128 (2.1036)	
[2022-01-24 11:51:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][340/1251]	eta 0:34:14 lr 0.000200	time 2.5353 (2.2548)	loss 3.5573 (3.2694)	grad_norm 1.8728 (2.1003)	
[2022-01-24 11:52:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][350/1251]	eta 0:33:48 lr 0.000200	time 2.1463 (2.2518)	loss 3.2110 (3.2680)	grad_norm 1.8744 (2.0980)	
[2022-01-24 11:52:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][360/1251]	eta 0:33:20 lr 0.000200	time 1.5400 (2.2450)	loss 3.7806 (3.2667)	grad_norm 2.1022 (2.0965)	
[2022-01-24 11:52:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][370/1251]	eta 0:32:52 lr 0.000200	time 2.0750 (2.2392)	loss 3.0035 (3.2679)	grad_norm 2.0663 (2.0966)	
[2022-01-24 11:53:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][380/1251]	eta 0:32:32 lr 0.000200	time 2.3888 (2.2422)	loss 3.5675 (3.2667)	grad_norm 1.8333 (2.0953)	
[2022-01-24 11:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][390/1251]	eta 0:32:13 lr 0.000200	time 2.8031 (2.2457)	loss 3.5599 (3.2682)	grad_norm 2.0631 (2.0968)	
[2022-01-24 11:54:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][400/1251]	eta 0:31:55 lr 0.000200	time 1.7922 (2.2504)	loss 2.4312 (3.2689)	grad_norm 2.1342 (2.0978)	
[2022-01-24 11:54:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][410/1251]	eta 0:31:29 lr 0.000200	time 2.2000 (2.2473)	loss 3.2364 (3.2716)	grad_norm 2.6933 (2.0979)	
[2022-01-24 11:54:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][420/1251]	eta 0:31:00 lr 0.000200	time 1.8899 (2.2390)	loss 2.6606 (3.2697)	grad_norm 1.9661 (2.0957)	
[2022-01-24 11:55:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][430/1251]	eta 0:30:32 lr 0.000200	time 2.1919 (2.2325)	loss 3.2031 (3.2705)	grad_norm 1.9157 (2.0933)	
[2022-01-24 11:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][440/1251]	eta 0:30:07 lr 0.000200	time 1.7489 (2.2284)	loss 3.4239 (3.2715)	grad_norm 2.8851 (2.0989)	
[2022-01-24 11:55:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][450/1251]	eta 0:29:44 lr 0.000200	time 2.7663 (2.2279)	loss 2.2512 (3.2664)	grad_norm 1.9682 (2.1012)	
[2022-01-24 11:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][460/1251]	eta 0:29:22 lr 0.000200	time 2.4979 (2.2283)	loss 2.8681 (3.2627)	grad_norm 2.3054 (2.1027)	
[2022-01-24 11:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][470/1251]	eta 0:28:58 lr 0.000200	time 1.8277 (2.2260)	loss 3.3917 (3.2566)	grad_norm 2.2046 (2.1028)	
[2022-01-24 11:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][480/1251]	eta 0:28:36 lr 0.000200	time 2.2610 (2.2260)	loss 3.7033 (3.2517)	grad_norm 2.0345 (2.1022)	
[2022-01-24 11:57:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][490/1251]	eta 0:28:13 lr 0.000200	time 2.2201 (2.2259)	loss 3.6427 (3.2502)	grad_norm 2.0213 (2.1031)	
[2022-01-24 11:57:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][500/1251]	eta 0:27:55 lr 0.000200	time 3.1121 (2.2307)	loss 2.1223 (3.2464)	grad_norm 1.9207 (2.1041)	
[2022-01-24 11:58:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][510/1251]	eta 0:27:33 lr 0.000200	time 1.5733 (2.2308)	loss 3.8046 (3.2471)	grad_norm 2.0787 (2.1048)	
[2022-01-24 11:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][520/1251]	eta 0:27:10 lr 0.000200	time 2.2267 (2.2310)	loss 3.5418 (3.2472)	grad_norm 2.0258 (2.1064)	
[2022-01-24 11:58:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][530/1251]	eta 0:26:45 lr 0.000200	time 1.6012 (2.2272)	loss 3.7068 (3.2475)	grad_norm 1.9876 (2.1086)	
[2022-01-24 11:59:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][540/1251]	eta 0:26:20 lr 0.000200	time 2.4461 (2.2225)	loss 3.3557 (3.2468)	grad_norm 2.2411 (2.1111)	
[2022-01-24 11:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][550/1251]	eta 0:25:56 lr 0.000200	time 1.8582 (2.2209)	loss 3.8374 (3.2462)	grad_norm 2.2849 (2.1126)	
[2022-01-24 11:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][560/1251]	eta 0:25:33 lr 0.000200	time 1.6213 (2.2198)	loss 2.9072 (3.2463)	grad_norm 2.3518 (2.1147)	
[2022-01-24 12:00:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][570/1251]	eta 0:25:10 lr 0.000200	time 1.6047 (2.2184)	loss 3.6724 (3.2513)	grad_norm 2.0481 (2.1155)	
[2022-01-24 12:00:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][580/1251]	eta 0:24:52 lr 0.000200	time 3.3984 (2.2236)	loss 3.6871 (3.2536)	grad_norm 1.9786 (2.1147)	
[2022-01-24 12:00:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][590/1251]	eta 0:24:30 lr 0.000200	time 2.1741 (2.2245)	loss 3.6214 (3.2545)	grad_norm 1.8002 (2.1152)	
[2022-01-24 12:01:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][600/1251]	eta 0:24:09 lr 0.000200	time 2.0330 (2.2260)	loss 3.6288 (3.2550)	grad_norm 2.2983 (2.1166)	
[2022-01-24 12:01:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][610/1251]	eta 0:23:46 lr 0.000200	time 1.9680 (2.2248)	loss 3.7401 (3.2592)	grad_norm 2.0200 (2.1161)	
[2022-01-24 12:02:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][620/1251]	eta 0:23:23 lr 0.000200	time 2.5225 (2.2236)	loss 3.5382 (3.2563)	grad_norm 2.2317 (2.1148)	
[2022-01-24 12:02:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][630/1251]	eta 0:22:59 lr 0.000200	time 1.9901 (2.2208)	loss 2.4526 (3.2569)	grad_norm 2.4854 (2.1161)	
[2022-01-24 12:02:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][640/1251]	eta 0:22:36 lr 0.000200	time 2.2902 (2.2208)	loss 3.7695 (3.2586)	grad_norm 2.0520 (2.1143)	
[2022-01-24 12:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][650/1251]	eta 0:22:13 lr 0.000199	time 1.5783 (2.2190)	loss 3.2016 (3.2585)	grad_norm 1.9891 (2.1112)	
[2022-01-24 12:03:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][660/1251]	eta 0:21:53 lr 0.000199	time 2.2149 (2.2225)	loss 3.7942 (3.2601)	grad_norm 2.3381 (2.1108)	
[2022-01-24 12:03:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][670/1251]	eta 0:21:30 lr 0.000199	time 2.0209 (2.2211)	loss 3.9162 (3.2648)	grad_norm 2.6178 (2.1099)	
[2022-01-24 12:04:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][680/1251]	eta 0:21:07 lr 0.000199	time 2.1714 (2.2198)	loss 3.5726 (3.2649)	grad_norm 1.8724 (2.1088)	
[2022-01-24 12:04:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][690/1251]	eta 0:20:43 lr 0.000199	time 1.9351 (2.2170)	loss 3.6808 (3.2675)	grad_norm 1.7562 (2.1075)	
[2022-01-24 12:04:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][700/1251]	eta 0:20:20 lr 0.000199	time 1.9371 (2.2157)	loss 2.3523 (3.2659)	grad_norm 2.0338 (2.1059)	
[2022-01-24 12:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][710/1251]	eta 0:19:58 lr 0.000199	time 2.2765 (2.2151)	loss 2.3187 (3.2676)	grad_norm 2.1756 (2.1044)	
[2022-01-24 12:05:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][720/1251]	eta 0:19:35 lr 0.000199	time 2.4904 (2.2141)	loss 3.0583 (3.2619)	grad_norm 2.1163 (2.1057)	
[2022-01-24 12:05:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][730/1251]	eta 0:19:13 lr 0.000199	time 2.0795 (2.2140)	loss 3.4279 (3.2601)	grad_norm 1.9672 (2.1061)	
[2022-01-24 12:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][740/1251]	eta 0:18:50 lr 0.000199	time 1.7275 (2.2120)	loss 2.1576 (3.2604)	grad_norm 2.0711 (2.1067)	
[2022-01-24 12:06:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][750/1251]	eta 0:18:28 lr 0.000199	time 2.4641 (2.2126)	loss 3.7916 (3.2630)	grad_norm 2.2076 (2.1069)	
[2022-01-24 12:07:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][760/1251]	eta 0:18:05 lr 0.000199	time 1.6926 (2.2114)	loss 3.4751 (3.2628)	grad_norm 2.7298 (2.1069)	
[2022-01-24 12:07:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][770/1251]	eta 0:17:43 lr 0.000199	time 2.8172 (2.2103)	loss 3.0142 (3.2624)	grad_norm 2.1899 (2.1072)	
[2022-01-24 12:07:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][780/1251]	eta 0:17:20 lr 0.000199	time 1.6614 (2.2098)	loss 3.4921 (3.2568)	grad_norm 1.8710 (2.1076)	
[2022-01-24 12:08:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][790/1251]	eta 0:17:00 lr 0.000199	time 2.4475 (2.2137)	loss 2.6022 (3.2576)	grad_norm 2.1330 (2.1073)	
[2022-01-24 12:08:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][800/1251]	eta 0:16:37 lr 0.000199	time 2.2972 (2.2128)	loss 3.6859 (3.2590)	grad_norm 2.1583 (2.1079)	
[2022-01-24 12:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][810/1251]	eta 0:16:16 lr 0.000199	time 2.4634 (2.2135)	loss 2.0900 (3.2579)	grad_norm 1.8993 (2.1092)	
[2022-01-24 12:09:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][820/1251]	eta 0:15:52 lr 0.000199	time 1.6330 (2.2103)	loss 3.5895 (3.2613)	grad_norm 2.0204 (2.1101)	
[2022-01-24 12:09:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][830/1251]	eta 0:15:29 lr 0.000199	time 2.0704 (2.2084)	loss 3.1334 (3.2624)	grad_norm 2.2321 (2.1096)	
[2022-01-24 12:09:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][840/1251]	eta 0:15:07 lr 0.000199	time 1.8497 (2.2072)	loss 3.6518 (3.2629)	grad_norm 2.0131 (2.1093)	
[2022-01-24 12:10:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][850/1251]	eta 0:14:45 lr 0.000199	time 2.6656 (2.2086)	loss 3.2464 (3.2620)	grad_norm 2.0493 (2.1092)	
[2022-01-24 12:10:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][860/1251]	eta 0:14:23 lr 0.000199	time 2.1822 (2.2084)	loss 3.0275 (3.2603)	grad_norm 2.3506 (2.1089)	
[2022-01-24 12:11:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][870/1251]	eta 0:14:01 lr 0.000199	time 2.2638 (2.2074)	loss 3.4964 (3.2569)	grad_norm 2.0733 (2.1088)	
[2022-01-24 12:11:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][880/1251]	eta 0:13:38 lr 0.000199	time 2.2531 (2.2065)	loss 3.6139 (3.2568)	grad_norm 2.1281 (2.1092)	
[2022-01-24 12:11:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][890/1251]	eta 0:13:16 lr 0.000199	time 2.5942 (2.2075)	loss 3.6527 (3.2575)	grad_norm 1.7478 (2.1086)	
[2022-01-24 12:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][900/1251]	eta 0:12:54 lr 0.000199	time 1.8808 (2.2069)	loss 3.7978 (3.2570)	grad_norm 2.3248 (2.1085)	
[2022-01-24 12:12:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][910/1251]	eta 0:12:32 lr 0.000199	time 1.7464 (2.2071)	loss 2.5734 (3.2563)	grad_norm 1.8987 (2.1076)	
[2022-01-24 12:12:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][920/1251]	eta 0:12:10 lr 0.000199	time 2.1905 (2.2070)	loss 2.1956 (3.2566)	grad_norm 1.9947 (2.1065)	
[2022-01-24 12:13:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][930/1251]	eta 0:11:48 lr 0.000199	time 2.2818 (2.2065)	loss 3.0752 (3.2583)	grad_norm 2.5309 (2.1062)	
[2022-01-24 12:13:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][940/1251]	eta 0:11:25 lr 0.000199	time 2.0257 (2.2043)	loss 3.4397 (3.2576)	grad_norm 2.5285 (2.1082)	
[2022-01-24 12:13:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][950/1251]	eta 0:11:03 lr 0.000199	time 1.9533 (2.2031)	loss 3.2872 (3.2584)	grad_norm 2.2995 (2.1088)	
[2022-01-24 12:14:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][960/1251]	eta 0:10:41 lr 0.000198	time 2.7444 (2.2032)	loss 3.2731 (3.2568)	grad_norm 2.1395 (2.1083)	
[2022-01-24 12:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][970/1251]	eta 0:10:19 lr 0.000198	time 2.7350 (2.2042)	loss 3.3858 (3.2566)	grad_norm 1.9676 (2.1073)	
[2022-01-24 12:15:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][980/1251]	eta 0:09:57 lr 0.000198	time 2.7973 (2.2051)	loss 4.0565 (3.2543)	grad_norm 2.4930 (2.1068)	
[2022-01-24 12:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][990/1251]	eta 0:09:35 lr 0.000198	time 1.5965 (2.2044)	loss 3.5580 (3.2549)	grad_norm 2.4364 (2.1071)	
[2022-01-24 12:15:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1000/1251]	eta 0:09:13 lr 0.000198	time 2.4270 (2.2050)	loss 3.0369 (3.2535)	grad_norm 2.2503 (2.1063)	
[2022-01-24 12:16:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1010/1251]	eta 0:08:51 lr 0.000198	time 3.0440 (2.2053)	loss 3.5165 (3.2555)	grad_norm 2.1305 (2.1062)	
[2022-01-24 12:16:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1020/1251]	eta 0:08:29 lr 0.000198	time 2.5629 (2.2044)	loss 3.0350 (3.2559)	grad_norm 2.0437 (2.1074)	
[2022-01-24 12:16:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1030/1251]	eta 0:08:07 lr 0.000198	time 1.8201 (2.2048)	loss 2.4245 (3.2537)	grad_norm 2.0686 (2.1071)	
[2022-01-24 12:17:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1040/1251]	eta 0:07:45 lr 0.000198	time 1.6690 (2.2051)	loss 2.8250 (3.2558)	grad_norm 3.0366 (2.1086)	
[2022-01-24 12:17:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1050/1251]	eta 0:07:23 lr 0.000198	time 4.2857 (2.2052)	loss 3.6415 (3.2570)	grad_norm 2.0502 (2.1094)	
[2022-01-24 12:17:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1060/1251]	eta 0:07:00 lr 0.000198	time 1.5681 (2.2037)	loss 3.6264 (3.2567)	grad_norm 2.1630 (2.1094)	
[2022-01-24 12:18:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1070/1251]	eta 0:06:38 lr 0.000198	time 2.2651 (2.2037)	loss 3.6511 (3.2584)	grad_norm 2.2263 (2.1078)	
[2022-01-24 12:18:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1080/1251]	eta 0:06:16 lr 0.000198	time 2.1497 (2.2024)	loss 3.5853 (3.2592)	grad_norm 2.0820 (2.1070)	
[2022-01-24 12:19:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1090/1251]	eta 0:05:54 lr 0.000198	time 3.2629 (2.2027)	loss 3.0856 (3.2608)	grad_norm 1.9740 (2.1062)	
[2022-01-24 12:19:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1100/1251]	eta 0:05:32 lr 0.000198	time 1.7914 (2.2028)	loss 3.8161 (3.2619)	grad_norm 2.3828 (2.1058)	
[2022-01-24 12:19:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1110/1251]	eta 0:05:10 lr 0.000198	time 2.1856 (2.2011)	loss 3.7079 (3.2615)	grad_norm 2.1474 (2.1053)	
[2022-01-24 12:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1120/1251]	eta 0:04:48 lr 0.000198	time 2.1535 (2.2005)	loss 3.7607 (3.2598)	grad_norm 2.0761 (2.1051)	
[2022-01-24 12:20:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1130/1251]	eta 0:04:26 lr 0.000198	time 3.5134 (2.2017)	loss 2.5458 (3.2598)	grad_norm 2.3014 (2.1058)	
[2022-01-24 12:20:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1140/1251]	eta 0:04:04 lr 0.000198	time 2.6045 (2.2021)	loss 3.1593 (3.2583)	grad_norm 2.1136 (2.1054)	
[2022-01-24 12:21:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1150/1251]	eta 0:03:42 lr 0.000198	time 1.8893 (2.2018)	loss 2.9038 (3.2590)	grad_norm 1.8923 (2.1049)	
[2022-01-24 12:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1160/1251]	eta 0:03:20 lr 0.000198	time 1.6453 (2.2005)	loss 3.1220 (3.2592)	grad_norm 2.3304 (2.1054)	
[2022-01-24 12:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1170/1251]	eta 0:02:58 lr 0.000198	time 2.5268 (2.2000)	loss 3.6199 (3.2565)	grad_norm 2.1953 (2.1042)	
[2022-01-24 12:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1180/1251]	eta 0:02:36 lr 0.000198	time 1.9573 (2.1998)	loss 3.5464 (3.2588)	grad_norm 2.1419 (2.1040)	
[2022-01-24 12:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1190/1251]	eta 0:02:14 lr 0.000198	time 2.2718 (2.1990)	loss 3.6723 (3.2585)	grad_norm 1.8676 (2.1046)	
[2022-01-24 12:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1200/1251]	eta 0:01:52 lr 0.000198	time 2.1559 (2.1982)	loss 3.9697 (3.2591)	grad_norm 1.8410 (2.1038)	
[2022-01-24 12:23:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1210/1251]	eta 0:01:30 lr 0.000198	time 3.1946 (2.1992)	loss 3.6241 (3.2608)	grad_norm 1.7386 (2.1020)	
[2022-01-24 12:23:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1220/1251]	eta 0:01:08 lr 0.000198	time 1.8093 (2.1983)	loss 3.2412 (3.2610)	grad_norm 2.0727 (2.1015)	
[2022-01-24 12:24:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1230/1251]	eta 0:00:46 lr 0.000198	time 2.9823 (2.1997)	loss 3.7410 (3.2629)	grad_norm 1.9630 (2.1005)	
[2022-01-24 12:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1240/1251]	eta 0:00:24 lr 0.000198	time 1.4185 (2.1989)	loss 4.0193 (3.2643)	grad_norm 2.3757 (2.1005)	
[2022-01-24 12:24:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [213/300][1250/1251]	eta 0:00:02 lr 0.000198	time 1.1831 (2.1934)	loss 2.3688 (3.2638)	grad_norm 2.0285 (2.1011)	
[2022-01-24 12:24:44 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 213 training takes 0:45:44
[2022-01-24 12:25:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.747 (18.747)	Loss 0.8982 (0.8982)	Acc@1 76.855 (76.855)	Acc@5 95.020 (95.020)	
[2022-01-24 12:25:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.628 (3.504)	Loss 0.8635 (0.8759)	Acc@1 78.613 (79.119)	Acc@5 95.996 (94.949)	
[2022-01-24 12:25:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.603 (2.635)	Loss 0.8253 (0.8838)	Acc@1 79.883 (78.869)	Acc@5 95.898 (94.820)	
[2022-01-24 12:25:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.595 (2.320)	Loss 0.8048 (0.8913)	Acc@1 80.957 (78.821)	Acc@5 95.801 (94.698)	
[2022-01-24 12:26:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.588 (2.150)	Loss 0.8524 (0.8940)	Acc@1 80.273 (78.821)	Acc@5 94.336 (94.681)	
[2022-01-24 12:26:20 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 78.802 Acc@5 94.664
[2022-01-24 12:26:20 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 78.8%
[2022-01-24 12:26:20 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 78.99%
[2022-01-24 12:26:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][0/1251]	eta 7:21:54 lr 0.000198	time 21.1950 (21.1950)	loss 3.4745 (3.4745)	grad_norm 2.0076 (2.0076)	
[2022-01-24 12:27:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][10/1251]	eta 1:26:40 lr 0.000197	time 2.2411 (4.1904)	loss 3.0502 (3.4342)	grad_norm 2.0079 (2.0585)	
[2022-01-24 12:27:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][20/1251]	eta 1:05:49 lr 0.000197	time 1.5052 (3.2087)	loss 3.4281 (3.3620)	grad_norm 2.4422 (2.1285)	
[2022-01-24 12:27:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][30/1251]	eta 0:58:55 lr 0.000197	time 1.3733 (2.8954)	loss 3.7898 (3.3809)	grad_norm 2.2064 (2.1461)	
[2022-01-24 12:28:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][40/1251]	eta 0:55:42 lr 0.000197	time 3.2931 (2.7600)	loss 3.2344 (3.3122)	grad_norm 2.1856 (2.1194)	
[2022-01-24 12:28:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][50/1251]	eta 0:54:16 lr 0.000197	time 3.3103 (2.7111)	loss 3.1805 (3.2844)	grad_norm 2.1631 (2.1243)	
[2022-01-24 12:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][60/1251]	eta 0:52:35 lr 0.000197	time 1.7275 (2.6495)	loss 3.1436 (3.2849)	grad_norm 2.0887 (2.1066)	
[2022-01-24 12:29:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][70/1251]	eta 0:50:49 lr 0.000197	time 1.8924 (2.5819)	loss 3.4628 (3.2648)	grad_norm 1.9787 (2.0915)	
[2022-01-24 12:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][80/1251]	eta 0:49:02 lr 0.000197	time 2.4977 (2.5127)	loss 2.6069 (3.2621)	grad_norm 2.2157 (2.1043)	
[2022-01-24 12:30:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][90/1251]	eta 0:47:25 lr 0.000197	time 2.0112 (2.4505)	loss 3.2206 (3.2795)	grad_norm 2.2706 (2.0953)	
[2022-01-24 12:30:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][100/1251]	eta 0:46:03 lr 0.000197	time 2.2753 (2.4014)	loss 3.9181 (3.2740)	grad_norm 2.2308 (2.0998)	
[2022-01-24 12:30:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][110/1251]	eta 0:45:18 lr 0.000197	time 2.2464 (2.3823)	loss 3.1360 (3.2713)	grad_norm 1.9799 (2.1064)	
[2022-01-24 12:31:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][120/1251]	eta 0:44:38 lr 0.000197	time 1.9689 (2.3680)	loss 4.0574 (3.2994)	grad_norm 2.5664 (2.1049)	
[2022-01-24 12:31:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][130/1251]	eta 0:44:04 lr 0.000197	time 1.8462 (2.3589)	loss 2.0883 (3.2811)	grad_norm 1.9918 (2.1058)	
[2022-01-24 12:31:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][140/1251]	eta 0:43:36 lr 0.000197	time 2.5447 (2.3549)	loss 3.5179 (3.2851)	grad_norm 1.9246 (2.0991)	
[2022-01-24 12:32:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][150/1251]	eta 0:43:02 lr 0.000197	time 2.2367 (2.3452)	loss 3.3863 (3.2699)	grad_norm 1.8378 (2.0929)	
[2022-01-24 12:32:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][160/1251]	eta 0:42:32 lr 0.000197	time 1.9701 (2.3391)	loss 3.1824 (3.2744)	grad_norm 1.5871 (2.0834)	
[2022-01-24 12:33:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][170/1251]	eta 0:42:09 lr 0.000197	time 2.0672 (2.3400)	loss 3.4858 (3.2762)	grad_norm 2.0608 (2.0793)	
[2022-01-24 12:33:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][180/1251]	eta 0:41:34 lr 0.000197	time 2.5185 (2.3290)	loss 3.3664 (3.2636)	grad_norm 2.3608 (2.0818)	
[2022-01-24 12:33:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][190/1251]	eta 0:40:54 lr 0.000197	time 2.0472 (2.3130)	loss 2.9828 (3.2565)	grad_norm 1.8504 (2.0816)	
[2022-01-24 12:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][200/1251]	eta 0:40:16 lr 0.000197	time 2.0484 (2.2996)	loss 3.3733 (3.2629)	grad_norm 2.0357 (2.0867)	
[2022-01-24 12:34:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][210/1251]	eta 0:39:49 lr 0.000197	time 2.2139 (2.2950)	loss 2.9427 (3.2699)	grad_norm 2.0679 (2.0850)	
[2022-01-24 12:34:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][220/1251]	eta 0:39:18 lr 0.000197	time 2.0457 (2.2874)	loss 3.8900 (3.2738)	grad_norm 2.0717 (2.0871)	
[2022-01-24 12:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][230/1251]	eta 0:38:48 lr 0.000197	time 2.1920 (2.2806)	loss 3.2908 (3.2657)	grad_norm 1.8997 (2.0929)	
[2022-01-24 12:35:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][240/1251]	eta 0:38:19 lr 0.000197	time 1.6803 (2.2746)	loss 3.4089 (3.2657)	grad_norm 1.9558 (2.0961)	
[2022-01-24 12:35:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][250/1251]	eta 0:37:51 lr 0.000197	time 1.8935 (2.2690)	loss 2.2715 (3.2648)	grad_norm 2.1781 (2.0940)	
[2022-01-24 12:36:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][260/1251]	eta 0:37:24 lr 0.000197	time 2.2134 (2.2647)	loss 3.4084 (3.2746)	grad_norm 1.9907 (2.0926)	
[2022-01-24 12:36:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][270/1251]	eta 0:36:56 lr 0.000197	time 2.1276 (2.2591)	loss 2.4295 (3.2761)	grad_norm 1.8084 (2.0986)	
[2022-01-24 12:36:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][280/1251]	eta 0:36:33 lr 0.000197	time 2.1830 (2.2589)	loss 3.8509 (3.2763)	grad_norm 1.9304 (2.0967)	
[2022-01-24 12:37:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][290/1251]	eta 0:36:15 lr 0.000197	time 2.1971 (2.2640)	loss 2.8886 (3.2842)	grad_norm 2.0727 (2.0953)	
[2022-01-24 12:37:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][300/1251]	eta 0:35:57 lr 0.000197	time 3.1605 (2.2691)	loss 3.3285 (3.2811)	grad_norm 2.1641 (2.0948)	
[2022-01-24 12:38:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][310/1251]	eta 0:35:29 lr 0.000197	time 2.0469 (2.2630)	loss 3.9320 (3.2725)	grad_norm 2.0494 (2.0915)	
[2022-01-24 12:38:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][320/1251]	eta 0:34:58 lr 0.000196	time 1.7314 (2.2543)	loss 2.3054 (3.2707)	grad_norm 2.0414 (2.0926)	
[2022-01-24 12:38:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][330/1251]	eta 0:34:26 lr 0.000196	time 1.9711 (2.2440)	loss 3.4492 (3.2759)	grad_norm 2.1495 (2.0930)	
[2022-01-24 12:39:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][340/1251]	eta 0:33:58 lr 0.000196	time 2.7253 (2.2375)	loss 2.9309 (3.2662)	grad_norm 2.0176 (2.0909)	
[2022-01-24 12:39:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][350/1251]	eta 0:33:33 lr 0.000196	time 2.2349 (2.2348)	loss 3.4712 (3.2546)	grad_norm 2.1265 (2.0872)	
[2022-01-24 12:39:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][360/1251]	eta 0:33:10 lr 0.000196	time 2.3025 (2.2342)	loss 3.1031 (3.2612)	grad_norm 1.8520 (2.0846)	
[2022-01-24 12:40:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][370/1251]	eta 0:32:45 lr 0.000196	time 1.7998 (2.2309)	loss 3.1708 (3.2528)	grad_norm 2.3077 (2.0899)	
[2022-01-24 12:40:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][380/1251]	eta 0:32:25 lr 0.000196	time 2.8178 (2.2333)	loss 2.3813 (3.2462)	grad_norm 2.2046 (2.0902)	
[2022-01-24 12:40:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][390/1251]	eta 0:32:02 lr 0.000196	time 1.7813 (2.2325)	loss 3.8084 (3.2577)	grad_norm 2.1405 (2.0936)	
[2022-01-24 12:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][400/1251]	eta 0:31:40 lr 0.000196	time 2.8373 (2.2336)	loss 3.7632 (3.2635)	grad_norm 2.0321 (2.0936)	
[2022-01-24 12:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][410/1251]	eta 0:31:16 lr 0.000196	time 1.8592 (2.2309)	loss 2.4089 (3.2635)	grad_norm 2.2927 (2.0950)	
[2022-01-24 12:42:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][420/1251]	eta 0:30:55 lr 0.000196	time 3.1622 (2.2334)	loss 3.8610 (3.2703)	grad_norm 2.2671 (2.0978)	
[2022-01-24 12:42:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][430/1251]	eta 0:30:32 lr 0.000196	time 2.1049 (2.2318)	loss 3.5543 (3.2675)	grad_norm 2.0697 (2.0995)	
[2022-01-24 12:42:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][440/1251]	eta 0:30:11 lr 0.000196	time 2.5697 (2.2337)	loss 3.3723 (3.2693)	grad_norm 2.4586 (2.1009)	
[2022-01-24 12:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][450/1251]	eta 0:29:49 lr 0.000196	time 1.5865 (2.2340)	loss 3.2231 (3.2663)	grad_norm 1.9027 (2.1031)	
[2022-01-24 12:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][460/1251]	eta 0:29:28 lr 0.000196	time 3.5539 (2.2357)	loss 3.8590 (3.2665)	grad_norm 2.1283 (2.1037)	
[2022-01-24 12:43:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][470/1251]	eta 0:29:03 lr 0.000196	time 2.8554 (2.2329)	loss 3.5429 (3.2658)	grad_norm 1.9312 (2.1014)	
[2022-01-24 12:44:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][480/1251]	eta 0:28:37 lr 0.000196	time 2.1383 (2.2278)	loss 3.7012 (3.2647)	grad_norm 2.2458 (2.1039)	
[2022-01-24 12:44:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][490/1251]	eta 0:28:15 lr 0.000196	time 2.7665 (2.2284)	loss 3.6074 (3.2657)	grad_norm 2.1052 (2.1057)	
[2022-01-24 12:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][500/1251]	eta 0:27:53 lr 0.000196	time 1.9693 (2.2280)	loss 3.0684 (3.2652)	grad_norm 2.2992 (2.1085)	
[2022-01-24 12:45:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][510/1251]	eta 0:27:28 lr 0.000196	time 2.1613 (2.2250)	loss 4.0787 (3.2667)	grad_norm 2.1382 (2.1072)	
[2022-01-24 12:45:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][520/1251]	eta 0:27:08 lr 0.000196	time 2.5109 (2.2278)	loss 3.4998 (3.2730)	grad_norm 2.9951 (2.1101)	
[2022-01-24 12:46:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][530/1251]	eta 0:26:46 lr 0.000196	time 2.7307 (2.2277)	loss 3.0804 (3.2685)	grad_norm 2.0034 (2.1092)	
[2022-01-24 12:46:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][540/1251]	eta 0:26:23 lr 0.000196	time 1.9218 (2.2271)	loss 3.4790 (3.2710)	grad_norm 1.8975 (2.1115)	
[2022-01-24 12:46:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][550/1251]	eta 0:25:58 lr 0.000196	time 1.9793 (2.2230)	loss 3.8073 (3.2726)	grad_norm 2.1459 (2.1117)	
[2022-01-24 12:47:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][560/1251]	eta 0:25:34 lr 0.000196	time 1.8615 (2.2200)	loss 3.4314 (3.2771)	grad_norm 2.2610 (2.1134)	
[2022-01-24 12:47:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][570/1251]	eta 0:25:10 lr 0.000196	time 2.9572 (2.2187)	loss 3.5300 (3.2770)	grad_norm 2.8489 (2.1150)	
[2022-01-24 12:47:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][580/1251]	eta 0:24:46 lr 0.000196	time 1.5990 (2.2157)	loss 3.5595 (3.2754)	grad_norm 1.9266 (2.1141)	
[2022-01-24 12:48:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][590/1251]	eta 0:24:26 lr 0.000196	time 2.2632 (2.2191)	loss 2.7790 (3.2783)	grad_norm 2.1506 (2.1133)	
[2022-01-24 12:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][600/1251]	eta 0:24:06 lr 0.000196	time 2.4072 (2.2214)	loss 3.4863 (3.2804)	grad_norm 2.4058 (2.1123)	
[2022-01-24 12:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][610/1251]	eta 0:23:45 lr 0.000196	time 3.6329 (2.2238)	loss 3.5251 (3.2818)	grad_norm 1.8309 (2.1125)	
[2022-01-24 12:49:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][620/1251]	eta 0:23:22 lr 0.000196	time 2.0509 (2.2227)	loss 2.6886 (3.2801)	grad_norm 1.9360 (2.1120)	
[2022-01-24 12:49:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][630/1251]	eta 0:22:58 lr 0.000195	time 1.6230 (2.2199)	loss 2.9179 (3.2754)	grad_norm 2.3247 (2.1149)	
[2022-01-24 12:50:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][640/1251]	eta 0:22:34 lr 0.000195	time 2.0635 (2.2172)	loss 3.9106 (3.2773)	grad_norm 2.1791 (2.1161)	
[2022-01-24 12:50:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][650/1251]	eta 0:22:13 lr 0.000195	time 3.7090 (2.2195)	loss 3.4365 (3.2766)	grad_norm 1.9204 (2.1152)	
[2022-01-24 12:50:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][660/1251]	eta 0:21:52 lr 0.000195	time 2.2147 (2.2200)	loss 2.8752 (3.2729)	grad_norm 1.9339 (2.1145)	
[2022-01-24 12:51:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][670/1251]	eta 0:21:29 lr 0.000195	time 1.6235 (2.2195)	loss 3.1418 (3.2738)	grad_norm 2.0106 (2.1153)	
[2022-01-24 12:51:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][680/1251]	eta 0:21:07 lr 0.000195	time 2.3692 (2.2192)	loss 3.3862 (3.2709)	grad_norm 2.2887 (2.1171)	
[2022-01-24 12:51:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][690/1251]	eta 0:20:43 lr 0.000195	time 3.0876 (2.2169)	loss 2.7502 (3.2683)	grad_norm 2.2272 (2.1169)	
[2022-01-24 12:52:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][700/1251]	eta 0:20:20 lr 0.000195	time 1.6383 (2.2145)	loss 4.1345 (3.2685)	grad_norm 2.2483 (2.1162)	
[2022-01-24 12:52:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][710/1251]	eta 0:19:57 lr 0.000195	time 1.8716 (2.2127)	loss 3.3899 (3.2699)	grad_norm 2.1042 (2.1165)	
[2022-01-24 12:52:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][720/1251]	eta 0:19:34 lr 0.000195	time 2.5806 (2.2121)	loss 3.3854 (3.2712)	grad_norm 2.1026 (2.1173)	
[2022-01-24 12:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][730/1251]	eta 0:19:12 lr 0.000195	time 1.8374 (2.2112)	loss 2.6127 (3.2700)	grad_norm 2.3860 (2.1180)	
[2022-01-24 12:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][740/1251]	eta 0:18:49 lr 0.000195	time 1.8393 (2.2105)	loss 3.9638 (3.2720)	grad_norm 2.0489 (2.1181)	
[2022-01-24 12:54:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][750/1251]	eta 0:18:27 lr 0.000195	time 1.8825 (2.2099)	loss 2.7340 (3.2708)	grad_norm 1.9442 (2.1192)	
[2022-01-24 12:54:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][760/1251]	eta 0:18:05 lr 0.000195	time 2.1954 (2.2102)	loss 3.3390 (3.2690)	grad_norm 1.9914 (2.1197)	
[2022-01-24 12:54:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][770/1251]	eta 0:17:43 lr 0.000195	time 2.0435 (2.2106)	loss 3.4367 (3.2671)	grad_norm 2.0243 (2.1191)	
[2022-01-24 12:55:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][780/1251]	eta 0:17:20 lr 0.000195	time 2.2315 (2.2092)	loss 3.8176 (3.2713)	grad_norm 2.0142 (2.1194)	
[2022-01-24 12:55:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][790/1251]	eta 0:16:58 lr 0.000195	time 1.8860 (2.2094)	loss 2.4711 (3.2711)	grad_norm 1.9812 (2.1181)	
[2022-01-24 12:55:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][800/1251]	eta 0:16:36 lr 0.000195	time 2.3772 (2.2093)	loss 3.0847 (3.2731)	grad_norm 1.9132 (2.1175)	
[2022-01-24 12:56:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][810/1251]	eta 0:16:14 lr 0.000195	time 1.8935 (2.2098)	loss 2.5815 (3.2733)	grad_norm 1.9136 (2.1176)	
[2022-01-24 12:56:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][820/1251]	eta 0:15:53 lr 0.000195	time 2.5449 (2.2125)	loss 3.8467 (3.2760)	grad_norm 2.1587 (2.1181)	
[2022-01-24 12:56:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][830/1251]	eta 0:15:31 lr 0.000195	time 1.9064 (2.2128)	loss 3.7735 (3.2779)	grad_norm 1.9452 (2.1179)	
[2022-01-24 12:57:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][840/1251]	eta 0:15:09 lr 0.000195	time 2.7305 (2.2131)	loss 3.7284 (3.2768)	grad_norm 2.1533 (2.1196)	
[2022-01-24 12:57:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][850/1251]	eta 0:14:46 lr 0.000195	time 1.5115 (2.2110)	loss 3.1221 (3.2749)	grad_norm 2.1752 (2.1194)	
[2022-01-24 12:58:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][860/1251]	eta 0:14:23 lr 0.000195	time 1.9268 (2.2095)	loss 3.3516 (3.2759)	grad_norm 2.0605 (2.1195)	
[2022-01-24 12:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][870/1251]	eta 0:14:00 lr 0.000195	time 1.5872 (2.2066)	loss 3.3904 (3.2750)	grad_norm 2.0884 (2.1231)	
[2022-01-24 12:58:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][880/1251]	eta 0:13:38 lr 0.000195	time 2.1173 (2.2069)	loss 3.5668 (3.2766)	grad_norm 1.9824 (2.1257)	
[2022-01-24 12:59:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][890/1251]	eta 0:13:16 lr 0.000195	time 2.2515 (2.2069)	loss 3.3475 (3.2772)	grad_norm 2.2713 (2.1270)	
[2022-01-24 12:59:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][900/1251]	eta 0:12:55 lr 0.000195	time 2.2501 (2.2080)	loss 3.9270 (3.2780)	grad_norm 2.1727 (2.1278)	
[2022-01-24 12:59:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][910/1251]	eta 0:12:32 lr 0.000195	time 2.5852 (2.2074)	loss 3.0906 (3.2780)	grad_norm 2.0633 (2.1280)	
[2022-01-24 13:00:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][920/1251]	eta 0:12:10 lr 0.000195	time 1.4942 (2.2064)	loss 3.8599 (3.2794)	grad_norm 2.2829 (2.1273)	
[2022-01-24 13:00:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][930/1251]	eta 0:11:47 lr 0.000195	time 1.9026 (2.2049)	loss 3.5984 (3.2775)	grad_norm 2.0447 (2.1276)	
[2022-01-24 13:00:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][940/1251]	eta 0:11:25 lr 0.000194	time 1.9234 (2.2056)	loss 3.0282 (3.2771)	grad_norm 2.5880 (2.1284)	
[2022-01-24 13:01:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][950/1251]	eta 0:11:03 lr 0.000194	time 2.4172 (2.2055)	loss 3.6807 (3.2796)	grad_norm 2.1239 (2.1280)	
[2022-01-24 13:01:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][960/1251]	eta 0:10:41 lr 0.000194	time 1.7855 (2.2055)	loss 3.8391 (3.2801)	grad_norm 2.1947 (2.1293)	
[2022-01-24 13:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][970/1251]	eta 0:10:19 lr 0.000194	time 1.7711 (2.2061)	loss 3.0849 (3.2771)	grad_norm 2.3395 (2.1294)	
[2022-01-24 13:02:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][980/1251]	eta 0:09:58 lr 0.000194	time 1.5656 (2.2067)	loss 3.3590 (3.2793)	grad_norm 2.0292 (2.1301)	
[2022-01-24 13:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][990/1251]	eta 0:09:35 lr 0.000194	time 2.8077 (2.2069)	loss 2.5174 (3.2791)	grad_norm 1.9916 (2.1293)	
[2022-01-24 13:03:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1000/1251]	eta 0:09:13 lr 0.000194	time 1.7950 (2.2059)	loss 3.1239 (3.2799)	grad_norm 1.9213 (2.1288)	
[2022-01-24 13:03:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1010/1251]	eta 0:08:51 lr 0.000194	time 1.8251 (2.2050)	loss 3.7215 (3.2810)	grad_norm 2.1241 (2.1286)	
[2022-01-24 13:03:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1020/1251]	eta 0:08:29 lr 0.000194	time 1.8802 (2.2037)	loss 3.0156 (3.2820)	grad_norm 1.9444 (2.1284)	
[2022-01-24 13:04:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1030/1251]	eta 0:08:06 lr 0.000194	time 2.1648 (2.2031)	loss 3.9947 (3.2812)	grad_norm 2.3017 (2.1298)	
[2022-01-24 13:04:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1040/1251]	eta 0:07:44 lr 0.000194	time 2.6897 (2.2025)	loss 3.7705 (3.2829)	grad_norm 2.0718 (2.1282)	
[2022-01-24 13:04:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1050/1251]	eta 0:07:22 lr 0.000194	time 2.4888 (2.2033)	loss 3.3101 (3.2833)	grad_norm 2.3380 (2.1282)	
[2022-01-24 13:05:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1060/1251]	eta 0:07:00 lr 0.000194	time 2.1384 (2.2040)	loss 2.5657 (3.2813)	grad_norm 1.8820 (2.1279)	
[2022-01-24 13:05:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1070/1251]	eta 0:06:38 lr 0.000194	time 2.9258 (2.2032)	loss 2.9384 (3.2808)	grad_norm 1.9305 (2.1272)	
[2022-01-24 13:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1080/1251]	eta 0:06:16 lr 0.000194	time 2.6108 (2.2027)	loss 2.9189 (3.2800)	grad_norm 1.8534 (2.1262)	
[2022-01-24 13:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1090/1251]	eta 0:05:54 lr 0.000194	time 1.5594 (2.2029)	loss 3.9463 (3.2787)	grad_norm 2.3886 (2.1258)	
[2022-01-24 13:06:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1100/1251]	eta 0:05:32 lr 0.000194	time 2.2365 (2.2027)	loss 2.4544 (3.2778)	grad_norm 2.1527 (2.1253)	
[2022-01-24 13:07:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1110/1251]	eta 0:05:10 lr 0.000194	time 2.2632 (2.2021)	loss 3.7053 (3.2789)	grad_norm 2.1097 (2.1242)	
[2022-01-24 13:07:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1120/1251]	eta 0:04:48 lr 0.000194	time 2.2793 (2.2010)	loss 4.0612 (3.2800)	grad_norm 2.3616 (2.1229)	
[2022-01-24 13:07:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1130/1251]	eta 0:04:26 lr 0.000194	time 1.9381 (2.2015)	loss 3.9511 (3.2810)	grad_norm 2.1420 (2.1230)	
[2022-01-24 13:08:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1140/1251]	eta 0:04:04 lr 0.000194	time 1.9898 (2.2012)	loss 3.4805 (3.2792)	grad_norm 2.0486 (2.1228)	
[2022-01-24 13:08:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1150/1251]	eta 0:03:42 lr 0.000194	time 2.5998 (2.2018)	loss 4.0427 (3.2792)	grad_norm 2.2098 (2.1237)	
[2022-01-24 13:08:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1160/1251]	eta 0:03:20 lr 0.000194	time 1.5956 (2.2016)	loss 2.3010 (3.2773)	grad_norm 2.1590 (2.1233)	
[2022-01-24 13:09:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1170/1251]	eta 0:02:58 lr 0.000194	time 1.9525 (2.2013)	loss 3.3313 (3.2772)	grad_norm 2.3594 (2.1236)	
[2022-01-24 13:09:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1180/1251]	eta 0:02:36 lr 0.000194	time 1.5472 (2.2011)	loss 2.9169 (3.2760)	grad_norm 1.9140 (2.1229)	
[2022-01-24 13:10:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1190/1251]	eta 0:02:14 lr 0.000194	time 2.5574 (2.2011)	loss 3.0661 (3.2759)	grad_norm 2.3034 (2.1232)	
[2022-01-24 13:10:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1200/1251]	eta 0:01:52 lr 0.000194	time 1.8665 (2.1995)	loss 3.5106 (3.2764)	grad_norm 1.9888 (2.1240)	
[2022-01-24 13:10:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1210/1251]	eta 0:01:30 lr 0.000194	time 1.6170 (2.1989)	loss 3.7752 (3.2770)	grad_norm 2.0003 (2.1238)	
[2022-01-24 13:11:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1220/1251]	eta 0:01:08 lr 0.000194	time 2.0073 (2.1984)	loss 2.4938 (3.2751)	grad_norm 2.1877 (2.1238)	
[2022-01-24 13:11:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1230/1251]	eta 0:00:46 lr 0.000194	time 3.1860 (2.1989)	loss 4.2196 (3.2767)	grad_norm 2.2774 (2.1237)	
[2022-01-24 13:11:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1240/1251]	eta 0:00:24 lr 0.000194	time 1.7565 (2.1982)	loss 2.2170 (3.2776)	grad_norm 2.2571 (2.1223)	
[2022-01-24 13:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [214/300][1250/1251]	eta 0:00:02 lr 0.000193	time 1.1375 (2.1931)	loss 2.5008 (3.2755)	grad_norm 2.1296 (2.1230)	
[2022-01-24 13:12:04 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 214 training takes 0:45:43
[2022-01-24 13:12:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.021 (18.021)	Loss 0.8609 (0.8609)	Acc@1 79.004 (79.004)	Acc@5 95.703 (95.703)	
[2022-01-24 13:12:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.851 (3.311)	Loss 0.9749 (0.9014)	Acc@1 77.051 (79.128)	Acc@5 94.727 (94.593)	
[2022-01-24 13:13:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.484 (2.688)	Loss 0.7989 (0.8970)	Acc@1 80.469 (78.818)	Acc@5 95.801 (94.806)	
[2022-01-24 13:13:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.611 (2.354)	Loss 0.8645 (0.8953)	Acc@1 80.957 (78.799)	Acc@5 95.117 (94.777)	
[2022-01-24 13:13:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.314 (2.280)	Loss 0.8610 (0.8852)	Acc@1 80.469 (79.121)	Acc@5 94.629 (94.843)	
[2022-01-24 13:13:45 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.074 Acc@5 94.758
[2022-01-24 13:13:45 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.1%
[2022-01-24 13:13:45 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.07%
[2022-01-24 13:14:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][0/1251]	eta 7:30:53 lr 0.000193	time 21.6252 (21.6252)	loss 2.5657 (2.5657)	grad_norm 2.2340 (2.2340)	
[2022-01-24 13:14:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][10/1251]	eta 1:22:18 lr 0.000193	time 2.2058 (3.9796)	loss 3.4944 (3.3854)	grad_norm 2.2546 (2.0955)	
[2022-01-24 13:14:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][20/1251]	eta 1:05:07 lr 0.000193	time 2.2629 (3.1743)	loss 3.8282 (3.3795)	grad_norm 1.9804 (2.0661)	
[2022-01-24 13:15:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][30/1251]	eta 0:57:47 lr 0.000193	time 1.3780 (2.8402)	loss 3.7563 (3.4209)	grad_norm 2.1549 (2.0676)	
[2022-01-24 13:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][40/1251]	eta 0:54:51 lr 0.000193	time 3.8060 (2.7176)	loss 3.6084 (3.3911)	grad_norm 1.8937 (2.0709)	
[2022-01-24 13:16:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][50/1251]	eta 0:52:58 lr 0.000193	time 3.0861 (2.6468)	loss 3.3562 (3.3904)	grad_norm 2.0853 (2.0619)	
[2022-01-24 13:16:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][60/1251]	eta 0:51:05 lr 0.000193	time 2.1047 (2.5736)	loss 3.2278 (3.3217)	grad_norm 2.1174 (2.0745)	
[2022-01-24 13:16:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][70/1251]	eta 0:49:41 lr 0.000193	time 1.8902 (2.5249)	loss 3.3590 (3.3366)	grad_norm 2.7598 (2.0953)	
[2022-01-24 13:17:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][80/1251]	eta 0:48:32 lr 0.000193	time 2.7705 (2.4875)	loss 2.5223 (3.3128)	grad_norm 1.9266 (2.0953)	
[2022-01-24 13:17:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][90/1251]	eta 0:47:17 lr 0.000193	time 2.1829 (2.4437)	loss 3.7843 (3.3010)	grad_norm 2.0562 (2.0893)	
[2022-01-24 13:17:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][100/1251]	eta 0:46:08 lr 0.000193	time 1.9145 (2.4050)	loss 3.6694 (3.2775)	grad_norm 2.0162 (2.1045)	
[2022-01-24 13:18:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][110/1251]	eta 0:45:22 lr 0.000193	time 2.0305 (2.3862)	loss 2.2444 (3.2802)	grad_norm 1.7525 (2.1014)	
[2022-01-24 13:18:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][120/1251]	eta 0:44:38 lr 0.000193	time 2.5708 (2.3681)	loss 2.8948 (3.2724)	grad_norm 2.9112 (2.1076)	
[2022-01-24 13:18:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][130/1251]	eta 0:43:57 lr 0.000193	time 2.0510 (2.3529)	loss 3.2666 (3.2699)	grad_norm 2.3321 (2.1158)	
[2022-01-24 13:19:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][140/1251]	eta 0:43:19 lr 0.000193	time 1.5319 (2.3401)	loss 3.6120 (3.2622)	grad_norm 2.0337 (2.1101)	
[2022-01-24 13:19:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][150/1251]	eta 0:42:47 lr 0.000193	time 1.9446 (2.3319)	loss 2.6950 (3.2618)	grad_norm 2.4192 (2.1251)	
[2022-01-24 13:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][160/1251]	eta 0:42:19 lr 0.000193	time 3.4174 (2.3276)	loss 2.6032 (3.2536)	grad_norm 2.2453 (2.1323)	
[2022-01-24 13:20:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][170/1251]	eta 0:41:47 lr 0.000193	time 1.9261 (2.3193)	loss 3.0947 (3.2481)	grad_norm 2.1535 (2.1353)	
[2022-01-24 13:20:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][180/1251]	eta 0:41:21 lr 0.000193	time 1.8463 (2.3166)	loss 3.1353 (3.2516)	grad_norm 1.9731 (2.1289)	
[2022-01-24 13:21:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][190/1251]	eta 0:40:45 lr 0.000193	time 1.7404 (2.3048)	loss 3.9435 (3.2530)	grad_norm 1.9620 (2.1320)	
[2022-01-24 13:21:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][200/1251]	eta 0:40:24 lr 0.000193	time 3.7083 (2.3064)	loss 4.1079 (3.2571)	grad_norm 2.0427 (2.1349)	
[2022-01-24 13:21:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][210/1251]	eta 0:39:51 lr 0.000193	time 1.8224 (2.2970)	loss 2.9651 (3.2645)	grad_norm 2.6858 (2.1396)	
[2022-01-24 13:22:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][220/1251]	eta 0:39:29 lr 0.000193	time 1.8652 (2.2984)	loss 3.0985 (3.2548)	grad_norm 2.2539 (2.1382)	
[2022-01-24 13:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][230/1251]	eta 0:39:03 lr 0.000193	time 2.0058 (2.2957)	loss 3.8657 (3.2501)	grad_norm 2.1549 (2.1404)	
[2022-01-24 13:22:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][240/1251]	eta 0:38:37 lr 0.000193	time 2.4960 (2.2919)	loss 3.9071 (3.2462)	grad_norm 2.1169 (2.1415)	
[2022-01-24 13:23:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][250/1251]	eta 0:38:03 lr 0.000193	time 1.6042 (2.2807)	loss 3.2484 (3.2519)	grad_norm 1.7596 (2.1519)	
[2022-01-24 13:23:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][260/1251]	eta 0:37:37 lr 0.000193	time 2.2135 (2.2776)	loss 3.6975 (3.2496)	grad_norm 1.7862 (2.1518)	
[2022-01-24 13:24:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][270/1251]	eta 0:37:07 lr 0.000193	time 2.1852 (2.2702)	loss 2.3680 (3.2422)	grad_norm 1.9647 (2.1553)	
[2022-01-24 13:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][280/1251]	eta 0:36:41 lr 0.000193	time 2.2267 (2.2676)	loss 3.7354 (3.2478)	grad_norm 2.4459 (2.1573)	
[2022-01-24 13:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][290/1251]	eta 0:36:14 lr 0.000193	time 1.9321 (2.2628)	loss 3.2350 (3.2513)	grad_norm 2.1128 (2.1635)	
[2022-01-24 13:25:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][300/1251]	eta 0:35:47 lr 0.000193	time 2.6399 (2.2580)	loss 3.4292 (3.2561)	grad_norm 2.0201 (2.1638)	
[2022-01-24 13:25:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][310/1251]	eta 0:35:19 lr 0.000192	time 2.2388 (2.2523)	loss 2.5641 (3.2513)	grad_norm 2.3783 (2.1640)	
[2022-01-24 13:25:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][320/1251]	eta 0:34:52 lr 0.000192	time 2.1096 (2.2475)	loss 2.0823 (3.2515)	grad_norm 2.1416 (2.1653)	
[2022-01-24 13:26:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][330/1251]	eta 0:34:29 lr 0.000192	time 1.7476 (2.2465)	loss 3.3273 (3.2467)	grad_norm 2.3081 (2.1662)	
[2022-01-24 13:26:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][340/1251]	eta 0:34:09 lr 0.000192	time 2.5196 (2.2501)	loss 3.2431 (3.2518)	grad_norm 1.9465 (2.1676)	
[2022-01-24 13:26:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][350/1251]	eta 0:33:46 lr 0.000192	time 2.2343 (2.2490)	loss 2.3099 (3.2520)	grad_norm 1.9886 (2.1646)	
[2022-01-24 13:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][360/1251]	eta 0:33:21 lr 0.000192	time 2.6364 (2.2466)	loss 3.6576 (3.2528)	grad_norm 2.1670 (2.1627)	
[2022-01-24 13:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][370/1251]	eta 0:32:55 lr 0.000192	time 1.6069 (2.2422)	loss 3.9051 (3.2569)	grad_norm 2.3860 (2.1620)	
[2022-01-24 13:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][380/1251]	eta 0:32:33 lr 0.000192	time 2.0057 (2.2427)	loss 3.6269 (3.2632)	grad_norm 2.0691 (2.1608)	
[2022-01-24 13:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][390/1251]	eta 0:32:07 lr 0.000192	time 2.1069 (2.2390)	loss 3.8399 (3.2666)	grad_norm 2.5464 (2.1641)	
[2022-01-24 13:28:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][400/1251]	eta 0:31:45 lr 0.000192	time 2.4067 (2.2393)	loss 3.1993 (3.2673)	grad_norm 2.0406 (2.1629)	
[2022-01-24 13:29:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][410/1251]	eta 0:31:24 lr 0.000192	time 1.8963 (2.2409)	loss 3.7023 (3.2629)	grad_norm 2.1020 (2.1644)	
[2022-01-24 13:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][420/1251]	eta 0:31:01 lr 0.000192	time 1.8922 (2.2402)	loss 3.9292 (3.2650)	grad_norm 1.9175 (2.1627)	
[2022-01-24 13:29:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][430/1251]	eta 0:30:35 lr 0.000192	time 2.0619 (2.2360)	loss 4.1165 (3.2741)	grad_norm 1.7960 (2.1610)	
[2022-01-24 13:30:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][440/1251]	eta 0:30:10 lr 0.000192	time 2.0225 (2.2328)	loss 2.3261 (3.2734)	grad_norm 2.0872 (2.1594)	
[2022-01-24 13:30:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][450/1251]	eta 0:29:45 lr 0.000192	time 1.9370 (2.2287)	loss 3.3367 (3.2766)	grad_norm 2.0252 (2.1588)	
[2022-01-24 13:30:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][460/1251]	eta 0:29:20 lr 0.000192	time 2.1845 (2.2255)	loss 3.0689 (3.2739)	grad_norm 2.2162 (2.1574)	
[2022-01-24 13:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][470/1251]	eta 0:28:55 lr 0.000192	time 2.0187 (2.2227)	loss 2.9801 (3.2727)	grad_norm 1.9097 (2.1556)	
[2022-01-24 13:31:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][480/1251]	eta 0:28:34 lr 0.000192	time 2.7500 (2.2233)	loss 3.9587 (3.2754)	grad_norm 2.0357 (2.1529)	
[2022-01-24 13:31:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][490/1251]	eta 0:28:12 lr 0.000192	time 2.4417 (2.2235)	loss 3.5231 (3.2735)	grad_norm 1.7494 (2.1511)	
[2022-01-24 13:32:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][500/1251]	eta 0:27:50 lr 0.000192	time 2.2193 (2.2243)	loss 3.2160 (3.2713)	grad_norm 2.3712 (2.1544)	
[2022-01-24 13:32:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][510/1251]	eta 0:27:28 lr 0.000192	time 2.4677 (2.2252)	loss 2.7766 (3.2703)	grad_norm 2.2177 (2.1576)	
[2022-01-24 13:33:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][520/1251]	eta 0:27:07 lr 0.000192	time 3.5562 (2.2266)	loss 3.6215 (3.2720)	grad_norm 2.0675 (2.1617)	
[2022-01-24 13:33:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][530/1251]	eta 0:26:45 lr 0.000192	time 2.1252 (2.2262)	loss 3.3287 (3.2677)	grad_norm 1.9572 (2.1606)	
[2022-01-24 13:33:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][540/1251]	eta 0:26:21 lr 0.000192	time 2.3284 (2.2249)	loss 3.1649 (3.2661)	grad_norm 2.2645 (2.1626)	
[2022-01-24 13:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][550/1251]	eta 0:25:59 lr 0.000192	time 2.5076 (2.2244)	loss 2.6326 (3.2632)	grad_norm 2.1980 (2.1637)	
[2022-01-24 13:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][560/1251]	eta 0:25:35 lr 0.000192	time 2.6554 (2.2228)	loss 2.6216 (3.2667)	grad_norm 2.3081 (2.1653)	
[2022-01-24 13:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][570/1251]	eta 0:25:13 lr 0.000192	time 2.4950 (2.2218)	loss 3.5173 (3.2648)	grad_norm 2.4356 (2.1653)	
[2022-01-24 13:35:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][580/1251]	eta 0:24:50 lr 0.000192	time 2.5255 (2.2211)	loss 2.7084 (3.2654)	grad_norm 2.0243 (2.1626)	
[2022-01-24 13:35:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][590/1251]	eta 0:24:27 lr 0.000192	time 1.8242 (2.2207)	loss 3.3803 (3.2705)	grad_norm 2.9317 (2.1647)	
[2022-01-24 13:36:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][600/1251]	eta 0:24:06 lr 0.000192	time 2.8466 (2.2223)	loss 2.2579 (3.2666)	grad_norm 2.5451 (2.1663)	
[2022-01-24 13:36:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][610/1251]	eta 0:23:44 lr 0.000192	time 2.8693 (2.2216)	loss 3.6671 (3.2639)	grad_norm 2.3181 (2.1654)	
[2022-01-24 13:36:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][620/1251]	eta 0:23:19 lr 0.000191	time 2.0326 (2.2181)	loss 3.7041 (3.2676)	grad_norm 1.9693 (2.1641)	
[2022-01-24 13:37:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][630/1251]	eta 0:22:55 lr 0.000191	time 1.8634 (2.2157)	loss 2.5493 (3.2688)	grad_norm 2.0547 (2.1642)	
[2022-01-24 13:37:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][640/1251]	eta 0:22:33 lr 0.000191	time 1.8595 (2.2157)	loss 3.8864 (3.2676)	grad_norm 2.1368 (2.1636)	
[2022-01-24 13:37:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][650/1251]	eta 0:22:11 lr 0.000191	time 1.6307 (2.2155)	loss 3.9443 (3.2651)	grad_norm 2.0608 (2.1628)	
[2022-01-24 13:38:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][660/1251]	eta 0:21:50 lr 0.000191	time 2.6876 (2.2177)	loss 3.7016 (3.2648)	grad_norm 2.0675 (2.1629)	
[2022-01-24 13:38:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][670/1251]	eta 0:21:29 lr 0.000191	time 1.8683 (2.2196)	loss 3.5658 (3.2647)	grad_norm 1.9744 (2.1642)	
[2022-01-24 13:38:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][680/1251]	eta 0:21:05 lr 0.000191	time 2.0325 (2.2160)	loss 2.6127 (3.2647)	grad_norm 3.0389 (2.1655)	
[2022-01-24 13:39:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][690/1251]	eta 0:20:41 lr 0.000191	time 1.6120 (2.2122)	loss 3.4305 (3.2662)	grad_norm 1.9592 (2.1652)	
[2022-01-24 13:39:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][700/1251]	eta 0:20:17 lr 0.000191	time 2.1123 (2.2099)	loss 2.2865 (3.2619)	grad_norm 2.6665 (2.1657)	
[2022-01-24 13:39:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][710/1251]	eta 0:19:53 lr 0.000191	time 1.8350 (2.2062)	loss 2.9205 (3.2632)	grad_norm 2.1138 (2.1647)	
[2022-01-24 13:40:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][720/1251]	eta 0:19:30 lr 0.000191	time 2.6350 (2.2052)	loss 3.6412 (3.2640)	grad_norm 2.0154 (2.1621)	
[2022-01-24 13:40:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][730/1251]	eta 0:19:09 lr 0.000191	time 2.4413 (2.2059)	loss 3.4666 (3.2638)	grad_norm 2.2772 (2.1618)	
[2022-01-24 13:41:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][740/1251]	eta 0:18:47 lr 0.000191	time 1.5800 (2.2061)	loss 2.3657 (3.2637)	grad_norm 2.0093 (2.1619)	
[2022-01-24 13:41:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][750/1251]	eta 0:18:27 lr 0.000191	time 2.8149 (2.2098)	loss 3.4708 (3.2680)	grad_norm 1.9665 (2.1630)	
[2022-01-24 13:41:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][760/1251]	eta 0:18:05 lr 0.000191	time 1.8891 (2.2102)	loss 2.3783 (3.2653)	grad_norm 2.2604 (2.1629)	
[2022-01-24 13:42:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][770/1251]	eta 0:17:44 lr 0.000191	time 1.7772 (2.2126)	loss 3.4056 (3.2669)	grad_norm 1.9362 (2.1621)	
[2022-01-24 13:42:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][780/1251]	eta 0:17:21 lr 0.000191	time 1.7228 (2.2120)	loss 3.3189 (3.2661)	grad_norm 2.2788 (2.1615)	
[2022-01-24 13:42:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][790/1251]	eta 0:16:59 lr 0.000191	time 2.3111 (2.2125)	loss 2.9825 (3.2654)	grad_norm 2.3005 (2.1619)	
[2022-01-24 13:43:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][800/1251]	eta 0:16:37 lr 0.000191	time 1.8191 (2.2121)	loss 3.4088 (3.2644)	grad_norm 1.8812 (2.1612)	
[2022-01-24 13:43:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][810/1251]	eta 0:16:15 lr 0.000191	time 1.5978 (2.2128)	loss 3.5994 (3.2643)	grad_norm 2.2994 (2.1612)	
[2022-01-24 13:44:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][820/1251]	eta 0:15:52 lr 0.000191	time 1.8783 (2.2109)	loss 3.6234 (3.2638)	grad_norm 2.5372 (2.1629)	
[2022-01-24 13:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][830/1251]	eta 0:15:30 lr 0.000191	time 1.9698 (2.2094)	loss 3.6279 (3.2623)	grad_norm 2.0986 (2.1628)	
[2022-01-24 13:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][840/1251]	eta 0:15:07 lr 0.000191	time 1.9995 (2.2078)	loss 3.5074 (3.2651)	grad_norm 1.9736 (2.1626)	
[2022-01-24 13:45:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][850/1251]	eta 0:14:45 lr 0.000191	time 2.0228 (2.2070)	loss 3.3034 (3.2646)	grad_norm 1.9617 (2.1619)	
[2022-01-24 13:45:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][860/1251]	eta 0:14:22 lr 0.000191	time 1.9423 (2.2067)	loss 3.4615 (3.2639)	grad_norm 2.1481 (2.1604)	
[2022-01-24 13:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][870/1251]	eta 0:14:00 lr 0.000191	time 2.3242 (2.2063)	loss 3.7125 (3.2645)	grad_norm 2.1358 (2.1593)	
[2022-01-24 13:46:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][880/1251]	eta 0:13:38 lr 0.000191	time 1.8619 (2.2073)	loss 3.3475 (3.2664)	grad_norm 2.0064 (2.1589)	
[2022-01-24 13:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][890/1251]	eta 0:13:17 lr 0.000191	time 3.2436 (2.2100)	loss 3.9364 (3.2678)	grad_norm 2.0049 (2.1576)	
[2022-01-24 13:46:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][900/1251]	eta 0:12:55 lr 0.000191	time 1.8542 (2.2103)	loss 3.1722 (3.2700)	grad_norm 1.9095 (2.1571)	
[2022-01-24 13:47:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][910/1251]	eta 0:12:33 lr 0.000191	time 1.5750 (2.2088)	loss 2.5999 (3.2695)	grad_norm 1.9327 (2.1568)	
[2022-01-24 13:47:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][920/1251]	eta 0:12:10 lr 0.000191	time 1.6630 (2.2072)	loss 3.4579 (3.2700)	grad_norm 2.1040 (2.1565)	
[2022-01-24 13:48:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][930/1251]	eta 0:11:48 lr 0.000191	time 1.9555 (2.2078)	loss 2.7484 (3.2692)	grad_norm 1.9796 (2.1559)	
[2022-01-24 13:48:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][940/1251]	eta 0:11:27 lr 0.000190	time 2.4410 (2.2100)	loss 3.4217 (3.2709)	grad_norm 2.1921 (2.1559)	
[2022-01-24 13:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][950/1251]	eta 0:11:05 lr 0.000190	time 1.5292 (2.2105)	loss 3.5795 (3.2680)	grad_norm 1.8051 (2.1549)	
[2022-01-24 13:49:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][960/1251]	eta 0:10:42 lr 0.000190	time 1.7396 (2.2090)	loss 3.5409 (3.2692)	grad_norm 2.0129 (2.1550)	
[2022-01-24 13:49:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][970/1251]	eta 0:10:19 lr 0.000190	time 1.6758 (2.2058)	loss 3.5063 (3.2672)	grad_norm 2.3884 (2.1549)	
[2022-01-24 13:49:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][980/1251]	eta 0:09:57 lr 0.000190	time 2.2273 (2.2045)	loss 3.6411 (3.2677)	grad_norm 2.4530 (2.1536)	
[2022-01-24 13:50:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][990/1251]	eta 0:09:34 lr 0.000190	time 2.2075 (2.2026)	loss 2.3549 (3.2660)	grad_norm 2.0427 (2.1522)	
[2022-01-24 13:50:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1000/1251]	eta 0:09:12 lr 0.000190	time 1.9204 (2.2002)	loss 3.5009 (3.2668)	grad_norm 1.9381 (2.1510)	
[2022-01-24 13:50:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1010/1251]	eta 0:08:50 lr 0.000190	time 2.4258 (2.2014)	loss 3.7507 (3.2659)	grad_norm 1.9613 (2.1503)	
[2022-01-24 13:51:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1020/1251]	eta 0:08:28 lr 0.000190	time 2.4613 (2.2014)	loss 2.9422 (3.2656)	grad_norm 1.9981 (2.1511)	
[2022-01-24 13:51:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1030/1251]	eta 0:08:06 lr 0.000190	time 1.9631 (2.2020)	loss 3.5750 (3.2680)	grad_norm 1.9107 (2.1531)	
[2022-01-24 13:51:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1040/1251]	eta 0:07:44 lr 0.000190	time 1.6946 (2.2019)	loss 3.7103 (3.2695)	grad_norm 2.2001 (2.1525)	
[2022-01-24 13:52:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1050/1251]	eta 0:07:23 lr 0.000190	time 3.3714 (2.2040)	loss 3.3060 (3.2713)	grad_norm 2.0179 (2.1516)	
[2022-01-24 13:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1060/1251]	eta 0:07:00 lr 0.000190	time 2.5089 (2.2030)	loss 3.7620 (3.2704)	grad_norm 1.8973 (2.1502)	
[2022-01-24 13:53:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1070/1251]	eta 0:06:38 lr 0.000190	time 2.0550 (2.2032)	loss 3.5181 (3.2700)	grad_norm 1.8189 (2.1486)	
[2022-01-24 13:53:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1080/1251]	eta 0:06:16 lr 0.000190	time 1.5706 (2.2027)	loss 3.5323 (3.2703)	grad_norm 2.4462 (2.1483)	
[2022-01-24 13:53:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1090/1251]	eta 0:05:54 lr 0.000190	time 2.5501 (2.2039)	loss 2.7937 (3.2678)	grad_norm 2.1201 (2.1482)	
[2022-01-24 13:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1100/1251]	eta 0:05:33 lr 0.000190	time 1.8236 (2.2063)	loss 2.3470 (3.2695)	grad_norm 1.9629 (2.1470)	
[2022-01-24 13:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1110/1251]	eta 0:05:11 lr 0.000190	time 2.5291 (2.2076)	loss 2.7103 (3.2720)	grad_norm 2.0368 (2.1461)	
[2022-01-24 13:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1120/1251]	eta 0:04:49 lr 0.000190	time 1.8342 (2.2083)	loss 2.6005 (3.2713)	grad_norm 1.9235 (2.1450)	
[2022-01-24 13:55:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1130/1251]	eta 0:04:26 lr 0.000190	time 2.0193 (2.2065)	loss 3.3714 (3.2719)	grad_norm 1.9579 (2.1443)	
[2022-01-24 13:55:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1140/1251]	eta 0:04:04 lr 0.000190	time 2.0402 (2.2034)	loss 2.0346 (3.2698)	grad_norm 1.8567 (2.1434)	
[2022-01-24 13:55:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1150/1251]	eta 0:03:42 lr 0.000190	time 1.8850 (2.2011)	loss 3.3238 (3.2694)	grad_norm 1.9125 (2.1420)	
[2022-01-24 13:56:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1160/1251]	eta 0:03:20 lr 0.000190	time 2.1969 (2.2008)	loss 3.6472 (3.2691)	grad_norm 2.5416 (2.1416)	
[2022-01-24 13:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1170/1251]	eta 0:02:58 lr 0.000190	time 1.9269 (2.1992)	loss 2.7083 (3.2655)	grad_norm 2.3731 (2.1410)	
[2022-01-24 13:57:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1180/1251]	eta 0:02:36 lr 0.000190	time 1.7602 (2.1992)	loss 3.5324 (3.2674)	grad_norm 2.0180 (2.1409)	
[2022-01-24 13:57:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1190/1251]	eta 0:02:14 lr 0.000190	time 2.3704 (2.2010)	loss 3.3831 (3.2658)	grad_norm 2.5002 (2.1408)	
[2022-01-24 13:57:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1200/1251]	eta 0:01:52 lr 0.000190	time 2.0424 (2.2025)	loss 3.6196 (3.2653)	grad_norm 1.9118 (2.1400)	
[2022-01-24 13:58:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1210/1251]	eta 0:01:30 lr 0.000190	time 2.0148 (2.2025)	loss 3.4027 (3.2650)	grad_norm 2.2161 (2.1392)	
[2022-01-24 13:58:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1220/1251]	eta 0:01:08 lr 0.000190	time 1.6268 (2.2026)	loss 3.6660 (3.2669)	grad_norm 1.9738 (2.1379)	
[2022-01-24 13:58:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1230/1251]	eta 0:00:46 lr 0.000190	time 2.1491 (2.2019)	loss 3.6905 (3.2662)	grad_norm 2.0811 (2.1383)	
[2022-01-24 13:59:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1240/1251]	eta 0:00:24 lr 0.000190	time 1.8566 (2.2011)	loss 3.3305 (3.2649)	grad_norm 2.3411 (2.1380)	
[2022-01-24 13:59:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [215/300][1250/1251]	eta 0:00:02 lr 0.000189	time 1.1122 (2.1958)	loss 2.9131 (3.2628)	grad_norm 2.1034 (2.1373)	
[2022-01-24 13:59:32 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 215 training takes 0:45:47
[2022-01-24 13:59:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.153 (18.153)	Loss 0.8920 (0.8920)	Acc@1 78.906 (78.906)	Acc@5 95.020 (95.020)	
[2022-01-24 14:00:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.537 (3.609)	Loss 0.8682 (0.8923)	Acc@1 79.004 (79.084)	Acc@5 95.508 (94.664)	
[2022-01-24 14:00:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.288 (2.776)	Loss 0.8549 (0.8881)	Acc@1 79.883 (78.999)	Acc@5 95.508 (94.713)	
[2022-01-24 14:00:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.332 (2.355)	Loss 0.9004 (0.8918)	Acc@1 78.711 (78.919)	Acc@5 94.922 (94.660)	
[2022-01-24 14:01:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.981 (2.223)	Loss 0.7950 (0.8858)	Acc@1 81.445 (79.090)	Acc@5 95.508 (94.729)	
[2022-01-24 14:01:11 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.122 Acc@5 94.732
[2022-01-24 14:01:11 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.1%
[2022-01-24 14:01:11 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.12%
[2022-01-24 14:01:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][0/1251]	eta 7:22:51 lr 0.000189	time 21.2402 (21.2402)	loss 3.0005 (3.0005)	grad_norm 2.2580 (2.2580)	
[2022-01-24 14:01:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][10/1251]	eta 1:23:03 lr 0.000189	time 1.6767 (4.0160)	loss 3.5449 (3.2837)	grad_norm 1.7628 (2.0439)	
[2022-01-24 14:02:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][20/1251]	eta 1:05:19 lr 0.000189	time 1.9591 (3.1841)	loss 3.5514 (3.3921)	grad_norm 2.1648 (2.0453)	
[2022-01-24 14:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][30/1251]	eta 0:57:54 lr 0.000189	time 1.3064 (2.8456)	loss 3.8240 (3.3117)	grad_norm 2.5925 (2.0611)	
[2022-01-24 14:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][40/1251]	eta 0:55:00 lr 0.000189	time 3.4428 (2.7254)	loss 3.6785 (3.2771)	grad_norm 1.8177 (2.0613)	
[2022-01-24 14:03:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][50/1251]	eta 0:53:42 lr 0.000189	time 2.9065 (2.6829)	loss 3.1798 (3.2578)	grad_norm 2.1328 (2.0732)	
[2022-01-24 14:03:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][60/1251]	eta 0:51:40 lr 0.000189	time 1.9976 (2.6035)	loss 3.4899 (3.2516)	grad_norm 1.7487 (2.0781)	
[2022-01-24 14:04:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][70/1251]	eta 0:49:50 lr 0.000189	time 1.5885 (2.5323)	loss 2.7870 (3.2547)	grad_norm 2.2570 (2.1218)	
[2022-01-24 14:04:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][80/1251]	eta 0:48:34 lr 0.000189	time 2.5518 (2.4888)	loss 3.3860 (3.2258)	grad_norm 1.9997 (2.1261)	
[2022-01-24 14:04:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][90/1251]	eta 0:47:23 lr 0.000189	time 2.1381 (2.4488)	loss 3.3442 (3.2227)	grad_norm 2.0712 (2.1278)	
[2022-01-24 14:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][100/1251]	eta 0:46:17 lr 0.000189	time 2.1094 (2.4134)	loss 3.8182 (3.2375)	grad_norm 2.1396 (2.1205)	
[2022-01-24 14:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][110/1251]	eta 0:45:29 lr 0.000189	time 1.9192 (2.3922)	loss 3.3756 (3.2460)	grad_norm 1.7547 (2.1182)	
[2022-01-24 14:05:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][120/1251]	eta 0:44:41 lr 0.000189	time 2.4603 (2.3713)	loss 2.4748 (3.2272)	grad_norm 2.2197 (2.1181)	
[2022-01-24 14:06:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][130/1251]	eta 0:43:49 lr 0.000189	time 1.6259 (2.3454)	loss 3.2737 (3.2239)	grad_norm 2.4089 (2.1320)	
[2022-01-24 14:06:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][140/1251]	eta 0:43:02 lr 0.000189	time 2.0977 (2.3247)	loss 2.0139 (3.1942)	grad_norm 1.9318 (2.1257)	
[2022-01-24 14:07:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][150/1251]	eta 0:42:30 lr 0.000189	time 1.8905 (2.3164)	loss 2.7554 (3.1910)	grad_norm 2.3781 (2.1324)	
[2022-01-24 14:07:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][160/1251]	eta 0:42:12 lr 0.000189	time 3.3324 (2.3209)	loss 3.8282 (3.2046)	grad_norm 2.0848 (2.1328)	
[2022-01-24 14:07:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][170/1251]	eta 0:41:39 lr 0.000189	time 1.9538 (2.3121)	loss 3.5495 (3.2033)	grad_norm 3.5875 (2.1400)	
[2022-01-24 14:08:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][180/1251]	eta 0:41:12 lr 0.000189	time 2.3669 (2.3086)	loss 2.8429 (3.2016)	grad_norm 2.3198 (2.1337)	
[2022-01-24 14:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][190/1251]	eta 0:40:39 lr 0.000189	time 1.9347 (2.2995)	loss 3.9446 (3.2029)	grad_norm 2.0333 (2.1254)	
[2022-01-24 14:08:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][200/1251]	eta 0:40:09 lr 0.000189	time 2.4476 (2.2930)	loss 3.3751 (3.2045)	grad_norm 2.1436 (2.1215)	
[2022-01-24 14:09:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][210/1251]	eta 0:39:34 lr 0.000189	time 1.9821 (2.2808)	loss 2.8239 (3.2012)	grad_norm 2.2257 (2.1221)	
[2022-01-24 14:09:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][220/1251]	eta 0:39:05 lr 0.000189	time 2.1680 (2.2745)	loss 2.7439 (3.1955)	grad_norm 1.9847 (2.1197)	
[2022-01-24 14:09:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][230/1251]	eta 0:38:48 lr 0.000189	time 2.6199 (2.2806)	loss 3.6205 (3.1960)	grad_norm 2.1555 (2.1170)	
[2022-01-24 14:10:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][240/1251]	eta 0:38:25 lr 0.000189	time 2.1431 (2.2802)	loss 3.3375 (3.1903)	grad_norm 2.2107 (2.1229)	
[2022-01-24 14:10:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][250/1251]	eta 0:38:03 lr 0.000189	time 2.1738 (2.2814)	loss 3.4883 (3.1894)	grad_norm 2.2450 (2.1227)	
[2022-01-24 14:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][260/1251]	eta 0:37:32 lr 0.000189	time 2.2434 (2.2728)	loss 3.8934 (3.1881)	grad_norm 2.8328 (2.1268)	
[2022-01-24 14:11:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][270/1251]	eta 0:36:58 lr 0.000189	time 2.3189 (2.2612)	loss 3.4098 (3.1946)	grad_norm 2.2553 (2.1342)	
[2022-01-24 14:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][280/1251]	eta 0:36:30 lr 0.000189	time 2.4748 (2.2562)	loss 2.2589 (3.1995)	grad_norm 2.0224 (2.1385)	
[2022-01-24 14:12:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][290/1251]	eta 0:36:01 lr 0.000189	time 2.5072 (2.2494)	loss 3.5804 (3.2028)	grad_norm 2.2377 (2.1382)	
[2022-01-24 14:12:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][300/1251]	eta 0:35:37 lr 0.000189	time 2.4701 (2.2471)	loss 3.3375 (3.2056)	grad_norm 2.2475 (2.1416)	
[2022-01-24 14:12:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][310/1251]	eta 0:35:13 lr 0.000188	time 2.7642 (2.2460)	loss 2.6901 (3.1965)	grad_norm 2.3500 (2.1450)	
[2022-01-24 14:13:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][320/1251]	eta 0:34:50 lr 0.000188	time 2.0741 (2.2459)	loss 2.5897 (3.1934)	grad_norm 2.4943 (2.1472)	
[2022-01-24 14:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][330/1251]	eta 0:34:31 lr 0.000188	time 2.4580 (2.2494)	loss 3.8693 (3.1982)	grad_norm 2.3919 (2.1477)	
[2022-01-24 14:13:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][340/1251]	eta 0:34:11 lr 0.000188	time 2.4218 (2.2514)	loss 2.7581 (3.1991)	grad_norm 2.0759 (2.1461)	
[2022-01-24 14:14:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][350/1251]	eta 0:33:47 lr 0.000188	time 2.5211 (2.2507)	loss 2.6755 (3.1999)	grad_norm 2.0208 (2.1478)	
[2022-01-24 14:14:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][360/1251]	eta 0:33:21 lr 0.000188	time 1.8245 (2.2469)	loss 3.3119 (3.2035)	grad_norm 2.1329 (2.1474)	
[2022-01-24 14:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][370/1251]	eta 0:32:53 lr 0.000188	time 2.1268 (2.2397)	loss 2.1200 (3.2029)	grad_norm 1.9841 (2.1485)	
[2022-01-24 14:15:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][380/1251]	eta 0:32:24 lr 0.000188	time 1.9723 (2.2326)	loss 3.6873 (3.2119)	grad_norm 2.1003 (2.1523)	
[2022-01-24 14:15:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][390/1251]	eta 0:31:57 lr 0.000188	time 2.0874 (2.2273)	loss 3.1720 (3.2151)	grad_norm 2.3339 (2.1509)	
[2022-01-24 14:16:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][400/1251]	eta 0:31:31 lr 0.000188	time 1.5778 (2.2224)	loss 3.6452 (3.2196)	grad_norm 1.8728 (2.1524)	
[2022-01-24 14:16:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][410/1251]	eta 0:31:09 lr 0.000188	time 1.9676 (2.2231)	loss 2.3684 (3.2151)	grad_norm 2.0180 (2.1526)	
[2022-01-24 14:16:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][420/1251]	eta 0:30:51 lr 0.000188	time 1.8430 (2.2285)	loss 3.4379 (3.2145)	grad_norm 2.1320 (2.1521)	
[2022-01-24 14:17:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][430/1251]	eta 0:30:36 lr 0.000188	time 3.3145 (2.2364)	loss 3.2056 (3.2120)	grad_norm 1.7804 (2.1521)	
[2022-01-24 14:17:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][440/1251]	eta 0:30:18 lr 0.000188	time 2.1690 (2.2420)	loss 2.4969 (3.2139)	grad_norm 2.1259 (2.1524)	
[2022-01-24 14:18:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][450/1251]	eta 0:29:51 lr 0.000188	time 1.7724 (2.2367)	loss 3.5729 (3.2151)	grad_norm 2.6715 (2.1527)	
[2022-01-24 14:18:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][460/1251]	eta 0:29:23 lr 0.000188	time 1.9614 (2.2299)	loss 3.8773 (3.2186)	grad_norm 2.3153 (2.1543)	
[2022-01-24 14:18:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][470/1251]	eta 0:28:57 lr 0.000188	time 1.8349 (2.2242)	loss 3.0044 (3.2179)	grad_norm 2.1099 (2.1528)	
[2022-01-24 14:18:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][480/1251]	eta 0:28:30 lr 0.000188	time 2.0210 (2.2190)	loss 3.0526 (3.2168)	grad_norm 2.4013 (2.1546)	
[2022-01-24 14:19:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][490/1251]	eta 0:28:08 lr 0.000188	time 2.4995 (2.2188)	loss 3.2752 (3.2205)	grad_norm 2.3414 (2.1526)	
[2022-01-24 14:19:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][500/1251]	eta 0:27:47 lr 0.000188	time 1.8163 (2.2204)	loss 3.2350 (3.2251)	grad_norm 1.8598 (2.1504)	
[2022-01-24 14:20:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][510/1251]	eta 0:27:24 lr 0.000188	time 1.9339 (2.2194)	loss 3.4504 (3.2262)	grad_norm 2.7696 (2.1517)	
[2022-01-24 14:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][520/1251]	eta 0:27:01 lr 0.000188	time 2.1954 (2.2181)	loss 2.9758 (3.2244)	grad_norm 2.5731 (2.1527)	
[2022-01-24 14:20:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][530/1251]	eta 0:26:42 lr 0.000188	time 4.1327 (2.2224)	loss 2.2491 (3.2240)	grad_norm 3.7213 (2.1570)	
[2022-01-24 14:21:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][540/1251]	eta 0:26:20 lr 0.000188	time 2.6555 (2.2231)	loss 2.3320 (3.2183)	grad_norm 2.2926 (2.1593)	
[2022-01-24 14:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][550/1251]	eta 0:25:57 lr 0.000188	time 1.5246 (2.2218)	loss 3.8383 (3.2203)	grad_norm 2.1728 (2.1583)	
[2022-01-24 14:21:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][560/1251]	eta 0:25:35 lr 0.000188	time 2.1772 (2.2228)	loss 3.3388 (3.2225)	grad_norm 2.3752 (2.1589)	
[2022-01-24 14:22:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][570/1251]	eta 0:25:15 lr 0.000188	time 3.5034 (2.2257)	loss 3.2155 (3.2222)	grad_norm 1.8932 (2.1572)	
[2022-01-24 14:22:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][580/1251]	eta 0:24:49 lr 0.000188	time 1.9271 (2.2205)	loss 2.3600 (3.2141)	grad_norm 1.9789 (2.1542)	
[2022-01-24 14:23:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][590/1251]	eta 0:24:26 lr 0.000188	time 1.9380 (2.2189)	loss 3.7390 (3.2123)	grad_norm 2.3099 (2.1541)	
[2022-01-24 14:23:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][600/1251]	eta 0:24:03 lr 0.000188	time 1.4680 (2.2176)	loss 3.3880 (3.2088)	grad_norm 1.8686 (2.1527)	
[2022-01-24 14:23:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][610/1251]	eta 0:23:43 lr 0.000188	time 3.6141 (2.2208)	loss 3.9716 (3.2074)	grad_norm 2.3365 (2.1519)	
[2022-01-24 14:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][620/1251]	eta 0:23:21 lr 0.000187	time 1.7399 (2.2206)	loss 2.4513 (3.2066)	grad_norm 2.1006 (2.1505)	
[2022-01-24 14:24:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][630/1251]	eta 0:22:59 lr 0.000187	time 1.8692 (2.2213)	loss 3.6425 (3.2066)	grad_norm 2.1070 (2.1499)	
[2022-01-24 14:24:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][640/1251]	eta 0:22:36 lr 0.000187	time 1.9224 (2.2205)	loss 2.9671 (3.2095)	grad_norm 2.1477 (2.1501)	
[2022-01-24 14:25:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][650/1251]	eta 0:22:15 lr 0.000187	time 3.6741 (2.2217)	loss 3.4984 (3.2098)	grad_norm 1.9521 (2.1502)	
[2022-01-24 14:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][660/1251]	eta 0:21:51 lr 0.000187	time 1.7872 (2.2188)	loss 3.6175 (3.2118)	grad_norm 2.0605 (2.1498)	
[2022-01-24 14:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][670/1251]	eta 0:21:27 lr 0.000187	time 1.9290 (2.2164)	loss 2.0646 (3.2096)	grad_norm 1.9912 (2.1472)	
[2022-01-24 14:26:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][680/1251]	eta 0:21:04 lr 0.000187	time 2.0889 (2.2149)	loss 2.2990 (3.2075)	grad_norm 2.2158 (2.1460)	
[2022-01-24 14:26:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][690/1251]	eta 0:20:43 lr 0.000187	time 3.1557 (2.2168)	loss 3.0588 (3.2102)	grad_norm 2.0004 (2.1459)	
[2022-01-24 14:27:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][700/1251]	eta 0:20:21 lr 0.000187	time 1.6287 (2.2174)	loss 3.6736 (3.2095)	grad_norm 2.1994 (2.1441)	
[2022-01-24 14:27:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][710/1251]	eta 0:19:59 lr 0.000187	time 2.5076 (2.2177)	loss 2.7414 (3.2092)	grad_norm 2.7296 (2.1465)	
[2022-01-24 14:27:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][720/1251]	eta 0:19:37 lr 0.000187	time 2.0294 (2.2179)	loss 3.6186 (3.2076)	grad_norm 2.4257 (2.1475)	
[2022-01-24 14:28:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][730/1251]	eta 0:19:15 lr 0.000187	time 2.4755 (2.2169)	loss 3.3860 (3.2072)	grad_norm 2.0643 (2.1486)	
[2022-01-24 14:28:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][740/1251]	eta 0:18:51 lr 0.000187	time 1.5972 (2.2142)	loss 2.6138 (3.2065)	grad_norm 1.8598 (2.1489)	
[2022-01-24 14:28:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][750/1251]	eta 0:18:27 lr 0.000187	time 2.2008 (2.2115)	loss 3.3920 (3.2092)	grad_norm 2.1033 (2.1488)	
[2022-01-24 14:29:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][760/1251]	eta 0:18:04 lr 0.000187	time 1.9549 (2.2097)	loss 2.9414 (3.2096)	grad_norm 2.1906 (2.1494)	
[2022-01-24 14:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][770/1251]	eta 0:17:42 lr 0.000187	time 2.2163 (2.2094)	loss 3.6564 (3.2129)	grad_norm 2.4399 (2.1513)	
[2022-01-24 14:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][780/1251]	eta 0:17:20 lr 0.000187	time 2.5448 (2.2093)	loss 3.3311 (3.2119)	grad_norm 2.1297 (2.1521)	
[2022-01-24 14:30:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][790/1251]	eta 0:16:58 lr 0.000187	time 2.7870 (2.2103)	loss 2.3381 (3.2087)	grad_norm 2.1942 (2.1524)	
[2022-01-24 14:30:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][800/1251]	eta 0:16:36 lr 0.000187	time 2.3970 (2.2098)	loss 2.8523 (3.2099)	grad_norm 2.0265 (2.1526)	
[2022-01-24 14:31:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][810/1251]	eta 0:16:14 lr 0.000187	time 2.1831 (2.2094)	loss 3.7550 (3.2120)	grad_norm 2.3230 (2.1522)	
[2022-01-24 14:31:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][820/1251]	eta 0:15:52 lr 0.000187	time 1.9861 (2.2091)	loss 2.1881 (3.2094)	grad_norm 2.3213 (2.1538)	
[2022-01-24 14:31:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][830/1251]	eta 0:15:31 lr 0.000187	time 2.7268 (2.2118)	loss 3.1872 (3.2090)	grad_norm 1.9124 (2.1543)	
[2022-01-24 14:32:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][840/1251]	eta 0:15:10 lr 0.000187	time 2.1062 (2.2151)	loss 2.0998 (3.2077)	grad_norm 2.0207 (2.1534)	
[2022-01-24 14:32:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][850/1251]	eta 0:14:48 lr 0.000187	time 1.9114 (2.2164)	loss 2.2784 (3.2055)	grad_norm 2.2846 (2.1548)	
[2022-01-24 14:32:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][860/1251]	eta 0:14:25 lr 0.000187	time 1.6037 (2.2139)	loss 3.6696 (3.2079)	grad_norm 1.9581 (2.1539)	
[2022-01-24 14:33:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][870/1251]	eta 0:14:02 lr 0.000187	time 1.9167 (2.2102)	loss 2.4444 (3.2091)	grad_norm 2.2948 (2.1528)	
[2022-01-24 14:33:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][880/1251]	eta 0:13:39 lr 0.000187	time 1.6742 (2.2083)	loss 4.0200 (3.2130)	grad_norm 2.5622 (2.1554)	
[2022-01-24 14:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][890/1251]	eta 0:13:17 lr 0.000187	time 2.3516 (2.2091)	loss 3.8352 (3.2154)	grad_norm 2.1974 (2.1563)	
[2022-01-24 14:34:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][900/1251]	eta 0:12:55 lr 0.000187	time 1.9275 (2.2105)	loss 3.2537 (3.2140)	grad_norm 1.9867 (2.1557)	
[2022-01-24 14:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][910/1251]	eta 0:12:33 lr 0.000187	time 2.1896 (2.2105)	loss 4.1567 (3.2156)	grad_norm 1.8038 (2.1552)	
[2022-01-24 14:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][920/1251]	eta 0:12:11 lr 0.000187	time 2.1907 (2.2108)	loss 2.9635 (3.2151)	grad_norm 2.1685 (2.1547)	
[2022-01-24 14:35:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][930/1251]	eta 0:11:49 lr 0.000187	time 2.2825 (2.2106)	loss 3.3900 (3.2146)	grad_norm 2.0792 (2.1536)	
[2022-01-24 14:35:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][940/1251]	eta 0:11:27 lr 0.000186	time 1.9317 (2.2101)	loss 3.7328 (3.2168)	grad_norm 2.5398 (2.1555)	
[2022-01-24 14:36:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][950/1251]	eta 0:11:04 lr 0.000186	time 1.8466 (2.2091)	loss 3.6400 (3.2202)	grad_norm 2.0142 (2.1558)	
[2022-01-24 14:36:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][960/1251]	eta 0:10:42 lr 0.000186	time 1.9839 (2.2073)	loss 3.1466 (3.2189)	grad_norm 2.2262 (2.1553)	
[2022-01-24 14:36:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][970/1251]	eta 0:10:20 lr 0.000186	time 1.6473 (2.2078)	loss 3.6701 (3.2212)	grad_norm 2.5805 (2.1546)	
[2022-01-24 14:37:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][980/1251]	eta 0:09:58 lr 0.000186	time 2.4802 (2.2077)	loss 3.5428 (3.2197)	grad_norm 2.1149 (2.1537)	
[2022-01-24 14:37:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][990/1251]	eta 0:09:36 lr 0.000186	time 1.5256 (2.2079)	loss 2.5425 (3.2202)	grad_norm 2.0947 (2.1541)	
[2022-01-24 14:38:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1000/1251]	eta 0:09:14 lr 0.000186	time 2.8112 (2.2097)	loss 2.8678 (3.2190)	grad_norm 2.0026 (2.1533)	
[2022-01-24 14:38:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1010/1251]	eta 0:08:52 lr 0.000186	time 2.1664 (2.2115)	loss 4.0458 (3.2203)	grad_norm 2.0950 (2.1544)	
[2022-01-24 14:38:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1020/1251]	eta 0:08:30 lr 0.000186	time 2.0503 (2.2113)	loss 3.2400 (3.2204)	grad_norm 2.5957 (2.1547)	
[2022-01-24 14:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1030/1251]	eta 0:08:08 lr 0.000186	time 1.9066 (2.2104)	loss 3.2270 (3.2203)	grad_norm 2.6309 (2.1546)	
[2022-01-24 14:39:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1040/1251]	eta 0:07:45 lr 0.000186	time 1.5428 (2.2062)	loss 3.9163 (3.2220)	grad_norm 2.2052 (2.1537)	
[2022-01-24 14:39:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1050/1251]	eta 0:07:22 lr 0.000186	time 1.7907 (2.2035)	loss 3.5955 (3.2223)	grad_norm 2.0394 (2.1544)	
[2022-01-24 14:40:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1060/1251]	eta 0:07:00 lr 0.000186	time 2.2668 (2.2015)	loss 3.7461 (3.2249)	grad_norm 2.1680 (2.1548)	
[2022-01-24 14:40:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1070/1251]	eta 0:06:38 lr 0.000186	time 1.7751 (2.2002)	loss 3.8464 (3.2263)	grad_norm 2.0687 (2.1543)	
[2022-01-24 14:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1080/1251]	eta 0:06:16 lr 0.000186	time 2.4985 (2.2003)	loss 4.0984 (3.2282)	grad_norm 1.9546 (2.1533)	
[2022-01-24 14:41:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1090/1251]	eta 0:05:54 lr 0.000186	time 2.2112 (2.2011)	loss 3.8611 (3.2320)	grad_norm 2.2678 (2.1543)	
[2022-01-24 14:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1100/1251]	eta 0:05:32 lr 0.000186	time 2.1868 (2.2003)	loss 3.6349 (3.2348)	grad_norm 2.0452 (2.1533)	
[2022-01-24 14:41:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1110/1251]	eta 0:05:10 lr 0.000186	time 1.6029 (2.2009)	loss 3.7286 (3.2347)	grad_norm 2.5600 (2.1530)	
[2022-01-24 14:42:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1120/1251]	eta 0:04:48 lr 0.000186	time 2.8650 (2.2027)	loss 2.2410 (3.2363)	grad_norm 2.0141 (2.1529)	
[2022-01-24 14:42:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1130/1251]	eta 0:04:26 lr 0.000186	time 2.0694 (2.2052)	loss 3.4992 (3.2363)	grad_norm 2.3439 (2.1519)	
[2022-01-24 14:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1140/1251]	eta 0:04:04 lr 0.000186	time 1.8581 (2.2059)	loss 2.7855 (3.2366)	grad_norm 1.9797 (2.1513)	
[2022-01-24 14:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1150/1251]	eta 0:03:42 lr 0.000186	time 2.0287 (2.2067)	loss 2.7934 (3.2354)	grad_norm 2.1053 (2.1503)	
[2022-01-24 14:43:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1160/1251]	eta 0:03:20 lr 0.000186	time 1.9965 (2.2082)	loss 3.2925 (3.2344)	grad_norm 2.0771 (2.1502)	
[2022-01-24 14:44:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1170/1251]	eta 0:02:58 lr 0.000186	time 1.8064 (2.2073)	loss 2.5618 (3.2328)	grad_norm 2.2078 (2.1503)	
[2022-01-24 14:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1180/1251]	eta 0:02:36 lr 0.000186	time 2.7628 (2.2062)	loss 3.7009 (3.2351)	grad_norm 2.3517 (2.1509)	
[2022-01-24 14:44:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1190/1251]	eta 0:02:14 lr 0.000186	time 1.9449 (2.2038)	loss 3.4956 (3.2355)	grad_norm 2.4277 (2.1527)	
[2022-01-24 14:45:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1200/1251]	eta 0:01:52 lr 0.000186	time 2.6504 (2.2024)	loss 3.8871 (3.2366)	grad_norm 2.1006 (2.1531)	
[2022-01-24 14:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1210/1251]	eta 0:01:30 lr 0.000186	time 2.3812 (2.2008)	loss 2.4377 (3.2370)	grad_norm 2.1887 (2.1524)	
[2022-01-24 14:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1220/1251]	eta 0:01:08 lr 0.000186	time 2.1909 (2.2020)	loss 3.2745 (3.2378)	grad_norm 1.9226 (2.1519)	
[2022-01-24 14:46:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1230/1251]	eta 0:00:46 lr 0.000186	time 2.8634 (2.2032)	loss 2.5343 (3.2371)	grad_norm 2.0620 (2.1524)	
[2022-01-24 14:46:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1240/1251]	eta 0:00:24 lr 0.000186	time 1.7151 (2.2028)	loss 4.1531 (3.2381)	grad_norm 2.3903 (2.1535)	
[2022-01-24 14:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [216/300][1250/1251]	eta 0:00:02 lr 0.000186	time 1.1440 (2.1979)	loss 3.8492 (3.2388)	grad_norm 2.1218 (2.1535)	
[2022-01-24 14:47:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 216 training takes 0:45:49
[2022-01-24 14:47:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.341 (18.341)	Loss 0.8897 (0.8897)	Acc@1 79.102 (79.102)	Acc@5 94.238 (94.238)	
[2022-01-24 14:47:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.945 (3.302)	Loss 0.8770 (0.8869)	Acc@1 79.590 (79.537)	Acc@5 95.020 (94.869)	
[2022-01-24 14:47:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.328 (2.563)	Loss 0.9506 (0.8946)	Acc@1 77.539 (79.167)	Acc@5 93.262 (94.782)	
[2022-01-24 14:48:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.612 (2.307)	Loss 0.8876 (0.8900)	Acc@1 79.395 (79.265)	Acc@5 94.922 (94.771)	
[2022-01-24 14:48:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.191 (2.162)	Loss 0.8168 (0.8906)	Acc@1 80.762 (79.194)	Acc@5 95.215 (94.734)	
[2022-01-24 14:48:37 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.068 Acc@5 94.716
[2022-01-24 14:48:37 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.1%
[2022-01-24 14:48:37 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.12%
[2022-01-24 14:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][0/1251]	eta 7:31:47 lr 0.000185	time 21.6684 (21.6684)	loss 3.2664 (3.2664)	grad_norm 2.1834 (2.1834)	
[2022-01-24 14:49:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][10/1251]	eta 1:22:59 lr 0.000185	time 2.0373 (4.0124)	loss 2.7787 (3.0718)	grad_norm 1.9227 (2.1562)	
[2022-01-24 14:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][20/1251]	eta 1:05:47 lr 0.000185	time 1.5428 (3.2069)	loss 3.7871 (3.3508)	grad_norm 2.1579 (2.1532)	
[2022-01-24 14:50:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][30/1251]	eta 0:57:50 lr 0.000185	time 1.4103 (2.8422)	loss 2.6087 (3.2373)	grad_norm 2.1298 (2.1779)	
[2022-01-24 14:50:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][40/1251]	eta 0:54:37 lr 0.000185	time 3.5455 (2.7061)	loss 2.5342 (3.2123)	grad_norm 1.9292 (2.1531)	
[2022-01-24 14:50:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][50/1251]	eta 0:53:05 lr 0.000185	time 2.5608 (2.6520)	loss 3.3615 (3.1626)	grad_norm 1.9775 (2.1248)	
[2022-01-24 14:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][60/1251]	eta 0:51:17 lr 0.000185	time 1.6822 (2.5837)	loss 2.5753 (3.1701)	grad_norm 1.9292 (2.1342)	
[2022-01-24 14:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][70/1251]	eta 0:49:25 lr 0.000185	time 1.9088 (2.5112)	loss 3.8386 (3.1954)	grad_norm 2.3317 (2.1381)	
[2022-01-24 14:51:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][80/1251]	eta 0:48:10 lr 0.000185	time 2.6347 (2.4681)	loss 3.5088 (3.2061)	grad_norm 2.2606 (2.1397)	
[2022-01-24 14:52:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][90/1251]	eta 0:47:32 lr 0.000185	time 3.2226 (2.4572)	loss 2.5262 (3.1843)	grad_norm 2.0567 (2.1385)	
[2022-01-24 14:52:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][100/1251]	eta 0:46:48 lr 0.000185	time 1.8372 (2.4399)	loss 3.5018 (3.2005)	grad_norm 2.6236 (2.1402)	
[2022-01-24 14:53:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][110/1251]	eta 0:45:49 lr 0.000185	time 1.5879 (2.4098)	loss 3.4368 (3.2176)	grad_norm 2.2154 (2.1448)	
[2022-01-24 14:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][120/1251]	eta 0:44:53 lr 0.000185	time 1.6930 (2.3812)	loss 2.1338 (3.1853)	grad_norm 2.3105 (2.1431)	
[2022-01-24 14:53:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][130/1251]	eta 0:44:38 lr 0.000185	time 3.8558 (2.3889)	loss 3.6505 (3.2160)	grad_norm 2.2634 (2.1500)	
[2022-01-24 14:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][140/1251]	eta 0:44:11 lr 0.000185	time 1.9532 (2.3866)	loss 2.5603 (3.2171)	grad_norm 2.2415 (2.1487)	
[2022-01-24 14:54:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][150/1251]	eta 0:43:26 lr 0.000185	time 1.6169 (2.3675)	loss 2.4795 (3.2160)	grad_norm 2.2261 (2.1655)	
[2022-01-24 14:54:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][160/1251]	eta 0:42:43 lr 0.000185	time 1.8572 (2.3499)	loss 3.2850 (3.2148)	grad_norm 1.9659 (2.1653)	
[2022-01-24 14:55:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][170/1251]	eta 0:42:08 lr 0.000185	time 2.8222 (2.3390)	loss 3.6532 (3.2269)	grad_norm 2.1155 (2.1674)	
[2022-01-24 14:55:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][180/1251]	eta 0:41:35 lr 0.000185	time 1.8908 (2.3298)	loss 3.5707 (3.2255)	grad_norm 2.1920 (2.1663)	
[2022-01-24 14:55:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][190/1251]	eta 0:40:52 lr 0.000185	time 1.9435 (2.3114)	loss 2.8318 (3.2309)	grad_norm 1.9793 (2.1648)	
[2022-01-24 14:56:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][200/1251]	eta 0:40:17 lr 0.000185	time 2.0305 (2.3006)	loss 3.5414 (3.2255)	grad_norm 2.2674 (2.1618)	
[2022-01-24 14:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][210/1251]	eta 0:39:43 lr 0.000185	time 2.1601 (2.2897)	loss 3.5397 (3.2422)	grad_norm 1.9784 (2.1551)	
[2022-01-24 14:57:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][220/1251]	eta 0:39:15 lr 0.000185	time 2.2124 (2.2845)	loss 3.8072 (3.2414)	grad_norm 2.5869 (2.1564)	
[2022-01-24 14:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][230/1251]	eta 0:38:47 lr 0.000185	time 1.9274 (2.2799)	loss 2.7489 (3.2276)	grad_norm 2.7199 (2.1687)	
[2022-01-24 14:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][240/1251]	eta 0:38:21 lr 0.000185	time 2.4585 (2.2768)	loss 3.4825 (3.2303)	grad_norm 2.4433 (2.1673)	
[2022-01-24 14:58:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][250/1251]	eta 0:37:58 lr 0.000185	time 1.8333 (2.2761)	loss 3.3940 (3.2214)	grad_norm 2.1953 (2.1655)	
[2022-01-24 14:58:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][260/1251]	eta 0:37:39 lr 0.000185	time 2.7575 (2.2803)	loss 3.1003 (3.2129)	grad_norm 2.4278 (2.1680)	
[2022-01-24 14:58:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][270/1251]	eta 0:37:18 lr 0.000185	time 2.2323 (2.2819)	loss 3.8619 (3.2121)	grad_norm 2.1373 (2.1722)	
[2022-01-24 14:59:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][280/1251]	eta 0:36:52 lr 0.000185	time 2.0621 (2.2786)	loss 2.2873 (3.2174)	grad_norm 1.9143 (2.1682)	
[2022-01-24 14:59:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][290/1251]	eta 0:36:20 lr 0.000185	time 1.7074 (2.2692)	loss 3.1632 (3.2138)	grad_norm 1.8506 (2.1660)	
[2022-01-24 14:59:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][300/1251]	eta 0:35:46 lr 0.000185	time 1.9692 (2.2573)	loss 3.0958 (3.2119)	grad_norm 1.6737 (2.1626)	
[2022-01-24 15:00:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][310/1251]	eta 0:35:21 lr 0.000185	time 1.7580 (2.2546)	loss 3.6179 (3.2142)	grad_norm 2.0978 (2.1595)	
[2022-01-24 15:00:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][320/1251]	eta 0:34:56 lr 0.000184	time 2.1766 (2.2518)	loss 3.1315 (3.2158)	grad_norm 2.4291 (2.1587)	
[2022-01-24 15:01:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][330/1251]	eta 0:34:28 lr 0.000184	time 2.2589 (2.2464)	loss 2.1292 (3.2181)	grad_norm 1.9966 (2.1579)	
[2022-01-24 15:01:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][340/1251]	eta 0:33:59 lr 0.000184	time 1.6487 (2.2391)	loss 2.8787 (3.2157)	grad_norm 2.0690 (2.1558)	
[2022-01-24 15:01:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][350/1251]	eta 0:33:40 lr 0.000184	time 2.2059 (2.2423)	loss 3.5422 (3.2268)	grad_norm 2.0849 (2.1554)	
[2022-01-24 15:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][360/1251]	eta 0:33:17 lr 0.000184	time 1.8907 (2.2420)	loss 2.2417 (3.2257)	grad_norm 2.1912 (2.1524)	
[2022-01-24 15:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][370/1251]	eta 0:32:53 lr 0.000184	time 1.9277 (2.2406)	loss 2.4980 (3.2242)	grad_norm 1.9077 (2.1508)	
[2022-01-24 15:02:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][380/1251]	eta 0:32:34 lr 0.000184	time 2.9634 (2.2439)	loss 2.3235 (3.2255)	grad_norm 1.7574 (2.1490)	
[2022-01-24 15:03:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][390/1251]	eta 0:32:13 lr 0.000184	time 1.5673 (2.2454)	loss 3.3016 (3.2252)	grad_norm 2.0562 (2.1497)	
[2022-01-24 15:03:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][400/1251]	eta 0:31:49 lr 0.000184	time 1.6193 (2.2443)	loss 3.3563 (3.2248)	grad_norm 2.3707 (2.1524)	
[2022-01-24 15:04:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][410/1251]	eta 0:31:27 lr 0.000184	time 1.8261 (2.2444)	loss 2.2804 (3.2218)	grad_norm 2.5579 (2.1531)	
[2022-01-24 15:04:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][420/1251]	eta 0:31:03 lr 0.000184	time 2.5707 (2.2422)	loss 3.5374 (3.2218)	grad_norm 1.9610 (2.1546)	
[2022-01-24 15:04:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][430/1251]	eta 0:30:39 lr 0.000184	time 2.1763 (2.2408)	loss 3.5662 (3.2239)	grad_norm 1.8573 (2.1531)	
[2022-01-24 15:05:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][440/1251]	eta 0:30:17 lr 0.000184	time 1.9519 (2.2413)	loss 3.4163 (3.2220)	grad_norm 2.0910 (2.1537)	
[2022-01-24 15:05:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][450/1251]	eta 0:29:55 lr 0.000184	time 1.9716 (2.2413)	loss 2.9378 (3.2209)	grad_norm 2.0281 (2.1554)	
[2022-01-24 15:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][460/1251]	eta 0:29:33 lr 0.000184	time 1.7973 (2.2419)	loss 3.5535 (3.2238)	grad_norm 2.0045 (2.1537)	
[2022-01-24 15:06:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][470/1251]	eta 0:29:09 lr 0.000184	time 1.6024 (2.2403)	loss 4.0448 (3.2280)	grad_norm 2.2758 (2.1527)	
[2022-01-24 15:06:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][480/1251]	eta 0:28:43 lr 0.000184	time 2.0577 (2.2356)	loss 3.5636 (3.2274)	grad_norm 2.1448 (2.1522)	
[2022-01-24 15:06:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][490/1251]	eta 0:28:19 lr 0.000184	time 1.9799 (2.2328)	loss 3.5487 (3.2293)	grad_norm 2.2222 (2.1523)	
[2022-01-24 15:07:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][500/1251]	eta 0:27:55 lr 0.000184	time 2.1663 (2.2310)	loss 2.6717 (3.2322)	grad_norm 1.9632 (2.1513)	
[2022-01-24 15:07:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][510/1251]	eta 0:27:32 lr 0.000184	time 2.5189 (2.2303)	loss 2.1564 (3.2322)	grad_norm 1.8254 (2.1507)	
[2022-01-24 15:07:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][520/1251]	eta 0:27:09 lr 0.000184	time 2.3652 (2.2290)	loss 3.2940 (3.2312)	grad_norm 2.2454 (2.1507)	
[2022-01-24 15:08:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][530/1251]	eta 0:26:46 lr 0.000184	time 2.1641 (2.2287)	loss 3.2133 (3.2341)	grad_norm 2.1048 (2.1524)	
[2022-01-24 15:08:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][540/1251]	eta 0:26:25 lr 0.000184	time 2.1587 (2.2306)	loss 2.5658 (3.2329)	grad_norm 2.4995 (2.1525)	
[2022-01-24 15:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][550/1251]	eta 0:26:01 lr 0.000184	time 1.9707 (2.2279)	loss 3.2663 (3.2383)	grad_norm 2.1768 (2.1543)	
[2022-01-24 15:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][560/1251]	eta 0:25:38 lr 0.000184	time 1.8089 (2.2261)	loss 3.2316 (3.2400)	grad_norm 2.0447 (2.1552)	
[2022-01-24 15:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][570/1251]	eta 0:25:16 lr 0.000184	time 2.0632 (2.2265)	loss 2.2717 (3.2396)	grad_norm 2.0562 (2.1551)	
[2022-01-24 15:10:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][580/1251]	eta 0:24:53 lr 0.000184	time 2.5464 (2.2255)	loss 3.1053 (3.2428)	grad_norm 2.0778 (2.1566)	
[2022-01-24 15:10:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][590/1251]	eta 0:24:31 lr 0.000184	time 2.0874 (2.2256)	loss 2.6330 (3.2431)	grad_norm 2.3274 (2.1570)	
[2022-01-24 15:10:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][600/1251]	eta 0:24:08 lr 0.000184	time 2.4781 (2.2244)	loss 3.2047 (3.2426)	grad_norm 2.0269 (2.1576)	
[2022-01-24 15:11:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][610/1251]	eta 0:23:44 lr 0.000184	time 1.8710 (2.2223)	loss 3.1361 (3.2413)	grad_norm 2.0887 (2.1586)	
[2022-01-24 15:11:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][620/1251]	eta 0:23:20 lr 0.000184	time 1.9383 (2.2194)	loss 3.9977 (3.2428)	grad_norm 2.1324 (2.1585)	
[2022-01-24 15:11:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][630/1251]	eta 0:22:57 lr 0.000184	time 1.8381 (2.2179)	loss 2.7685 (3.2424)	grad_norm 2.6262 (2.1582)	
[2022-01-24 15:12:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][640/1251]	eta 0:22:35 lr 0.000183	time 2.1970 (2.2179)	loss 3.3526 (3.2426)	grad_norm 2.6945 (2.1586)	
[2022-01-24 15:12:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][650/1251]	eta 0:22:13 lr 0.000183	time 2.7506 (2.2186)	loss 3.3746 (3.2474)	grad_norm 2.1639 (2.1589)	
[2022-01-24 15:13:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][660/1251]	eta 0:21:51 lr 0.000183	time 2.2489 (2.2184)	loss 4.0345 (3.2478)	grad_norm 1.9345 (2.1584)	
[2022-01-24 15:13:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][670/1251]	eta 0:21:29 lr 0.000183	time 2.5539 (2.2188)	loss 3.9412 (3.2469)	grad_norm 2.0666 (2.1595)	
[2022-01-24 15:13:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][680/1251]	eta 0:21:08 lr 0.000183	time 2.8250 (2.2209)	loss 2.8987 (3.2485)	grad_norm 1.9810 (2.1581)	
[2022-01-24 15:14:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][690/1251]	eta 0:20:45 lr 0.000183	time 2.7671 (2.2208)	loss 2.3566 (3.2448)	grad_norm 2.3519 (2.1582)	
[2022-01-24 15:14:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][700/1251]	eta 0:20:21 lr 0.000183	time 1.6446 (2.2169)	loss 3.4906 (3.2455)	grad_norm 2.2674 (2.1571)	
[2022-01-24 15:14:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][710/1251]	eta 0:19:58 lr 0.000183	time 2.1682 (2.2150)	loss 3.8095 (3.2457)	grad_norm 2.4315 (2.1595)	
[2022-01-24 15:15:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][720/1251]	eta 0:19:35 lr 0.000183	time 2.5463 (2.2134)	loss 3.7163 (3.2452)	grad_norm 2.1952 (2.1598)	
[2022-01-24 15:15:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][730/1251]	eta 0:19:12 lr 0.000183	time 2.5204 (2.2126)	loss 3.5664 (3.2444)	grad_norm 2.3528 (2.1615)	
[2022-01-24 15:15:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][740/1251]	eta 0:18:49 lr 0.000183	time 1.7137 (2.2110)	loss 2.3482 (3.2421)	grad_norm 1.9338 (2.1612)	
[2022-01-24 15:16:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][750/1251]	eta 0:18:27 lr 0.000183	time 1.9115 (2.2104)	loss 3.0559 (3.2401)	grad_norm 2.0900 (2.1611)	
[2022-01-24 15:16:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][760/1251]	eta 0:18:06 lr 0.000183	time 2.7871 (2.2122)	loss 4.0789 (3.2445)	grad_norm 2.2338 (2.1613)	
[2022-01-24 15:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][770/1251]	eta 0:17:44 lr 0.000183	time 2.5276 (2.2140)	loss 4.0647 (3.2478)	grad_norm 2.2398 (2.1617)	
[2022-01-24 15:17:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][780/1251]	eta 0:17:22 lr 0.000183	time 2.2229 (2.2140)	loss 2.2809 (3.2477)	grad_norm 1.8917 (2.1611)	
[2022-01-24 15:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][790/1251]	eta 0:17:00 lr 0.000183	time 1.8275 (2.2139)	loss 2.9813 (3.2449)	grad_norm 2.0640 (2.1608)	
[2022-01-24 15:18:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][800/1251]	eta 0:16:39 lr 0.000183	time 2.8308 (2.2159)	loss 2.4414 (3.2465)	grad_norm 1.8928 (2.1593)	
[2022-01-24 15:18:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][810/1251]	eta 0:16:16 lr 0.000183	time 1.9217 (2.2148)	loss 3.3105 (3.2458)	grad_norm 2.4686 (2.1628)	
[2022-01-24 15:18:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][820/1251]	eta 0:15:53 lr 0.000183	time 1.8496 (2.2125)	loss 3.8298 (3.2424)	grad_norm 2.4147 (2.1631)	
[2022-01-24 15:19:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][830/1251]	eta 0:15:30 lr 0.000183	time 1.9734 (2.2104)	loss 3.1313 (3.2416)	grad_norm 2.0707 (2.1628)	
[2022-01-24 15:19:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][840/1251]	eta 0:15:08 lr 0.000183	time 2.7793 (2.2095)	loss 3.6611 (3.2388)	grad_norm 2.1933 (2.1627)	
[2022-01-24 15:19:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][850/1251]	eta 0:14:45 lr 0.000183	time 2.3192 (2.2087)	loss 3.8607 (3.2404)	grad_norm 2.0060 (2.1640)	
[2022-01-24 15:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][860/1251]	eta 0:14:23 lr 0.000183	time 2.1522 (2.2086)	loss 3.6061 (3.2407)	grad_norm 2.1825 (2.1642)	
[2022-01-24 15:20:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][870/1251]	eta 0:14:01 lr 0.000183	time 2.2139 (2.2074)	loss 3.4191 (3.2395)	grad_norm 1.9255 (2.1631)	
[2022-01-24 15:21:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][880/1251]	eta 0:13:39 lr 0.000183	time 2.5517 (2.2091)	loss 3.4825 (3.2378)	grad_norm 1.9257 (2.1630)	
[2022-01-24 15:21:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][890/1251]	eta 0:13:18 lr 0.000183	time 2.1622 (2.2106)	loss 3.6246 (3.2392)	grad_norm 2.1808 (2.1612)	
[2022-01-24 15:21:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][900/1251]	eta 0:12:55 lr 0.000183	time 1.8540 (2.2093)	loss 3.5364 (3.2393)	grad_norm 1.8246 (2.1597)	
[2022-01-24 15:22:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][910/1251]	eta 0:12:33 lr 0.000183	time 3.4161 (2.2095)	loss 3.2069 (3.2392)	grad_norm 2.0011 (2.1592)	
[2022-01-24 15:22:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][920/1251]	eta 0:12:11 lr 0.000183	time 2.6612 (2.2094)	loss 3.3502 (3.2360)	grad_norm 1.8264 (2.1569)	
[2022-01-24 15:22:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][930/1251]	eta 0:11:49 lr 0.000183	time 2.1507 (2.2091)	loss 2.7403 (3.2351)	grad_norm 1.9580 (2.1561)	
[2022-01-24 15:23:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][940/1251]	eta 0:11:27 lr 0.000183	time 1.7012 (2.2094)	loss 3.7157 (3.2372)	grad_norm 1.9955 (2.1566)	
[2022-01-24 15:23:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][950/1251]	eta 0:11:05 lr 0.000183	time 3.3015 (2.2102)	loss 3.0086 (3.2391)	grad_norm 1.9487 (2.1562)	
[2022-01-24 15:24:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][960/1251]	eta 0:10:42 lr 0.000182	time 1.9212 (2.2084)	loss 3.5109 (3.2387)	grad_norm 1.9388 (2.1559)	
[2022-01-24 15:24:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][970/1251]	eta 0:10:20 lr 0.000182	time 1.8916 (2.2066)	loss 3.6300 (3.2398)	grad_norm 2.2540 (2.1560)	
[2022-01-24 15:24:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][980/1251]	eta 0:09:58 lr 0.000182	time 2.1773 (2.2070)	loss 2.9355 (3.2381)	grad_norm 1.9975 (2.1566)	
[2022-01-24 15:25:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][990/1251]	eta 0:09:36 lr 0.000182	time 2.8911 (2.2077)	loss 2.6968 (3.2354)	grad_norm 2.3922 (2.1568)	
[2022-01-24 15:25:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1000/1251]	eta 0:09:14 lr 0.000182	time 1.8666 (2.2074)	loss 3.6394 (3.2359)	grad_norm 1.9796 (2.1565)	
[2022-01-24 15:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1010/1251]	eta 0:08:51 lr 0.000182	time 2.0185 (2.2060)	loss 3.0443 (3.2362)	grad_norm 1.9526 (2.1561)	
[2022-01-24 15:26:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1020/1251]	eta 0:08:29 lr 0.000182	time 1.9997 (2.2066)	loss 3.1657 (3.2364)	grad_norm 2.2510 (2.1573)	
[2022-01-24 15:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1030/1251]	eta 0:08:08 lr 0.000182	time 3.0694 (2.2082)	loss 3.7604 (3.2355)	grad_norm 2.0341 (2.1572)	
[2022-01-24 15:26:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1040/1251]	eta 0:07:45 lr 0.000182	time 1.8436 (2.2081)	loss 2.0121 (3.2333)	grad_norm 2.3862 (2.1571)	
[2022-01-24 15:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1050/1251]	eta 0:07:23 lr 0.000182	time 1.7682 (2.2062)	loss 3.0895 (3.2320)	grad_norm 2.2650 (2.1569)	
[2022-01-24 15:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1060/1251]	eta 0:07:01 lr 0.000182	time 1.7357 (2.2050)	loss 3.7628 (3.2298)	grad_norm 2.2405 (2.1566)	
[2022-01-24 15:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1070/1251]	eta 0:06:39 lr 0.000182	time 3.1215 (2.2049)	loss 3.2965 (3.2259)	grad_norm 2.2402 (2.1557)	
[2022-01-24 15:28:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1080/1251]	eta 0:06:17 lr 0.000182	time 2.2305 (2.2051)	loss 2.0675 (3.2247)	grad_norm 1.9263 (2.1551)	
[2022-01-24 15:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1090/1251]	eta 0:05:54 lr 0.000182	time 1.8332 (2.2034)	loss 2.6741 (3.2240)	grad_norm 2.2093 (2.1548)	
[2022-01-24 15:29:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1100/1251]	eta 0:05:32 lr 0.000182	time 2.1018 (2.2029)	loss 3.1731 (3.2232)	grad_norm 2.0833 (2.1547)	
[2022-01-24 15:29:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1110/1251]	eta 0:05:10 lr 0.000182	time 1.8884 (2.2029)	loss 2.7197 (3.2200)	grad_norm 2.1634 (2.1543)	
[2022-01-24 15:29:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1120/1251]	eta 0:04:48 lr 0.000182	time 2.1783 (2.2018)	loss 3.6733 (3.2197)	grad_norm 2.1039 (2.1541)	
[2022-01-24 15:30:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1130/1251]	eta 0:04:26 lr 0.000182	time 3.0607 (2.2018)	loss 2.3584 (3.2220)	grad_norm 1.9053 (2.1534)	
[2022-01-24 15:30:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1140/1251]	eta 0:04:04 lr 0.000182	time 2.0060 (2.2023)	loss 2.4953 (3.2221)	grad_norm 2.1725 (2.1535)	
[2022-01-24 15:30:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1150/1251]	eta 0:03:42 lr 0.000182	time 1.8407 (2.2035)	loss 3.4574 (3.2237)	grad_norm 2.2755 (2.1524)	
[2022-01-24 15:31:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1160/1251]	eta 0:03:20 lr 0.000182	time 2.1812 (2.2041)	loss 3.6650 (3.2229)	grad_norm 1.9747 (2.1534)	
[2022-01-24 15:31:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1170/1251]	eta 0:02:58 lr 0.000182	time 3.5137 (2.2059)	loss 2.6802 (3.2231)	grad_norm 2.2768 (2.1541)	
[2022-01-24 15:32:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1180/1251]	eta 0:02:36 lr 0.000182	time 2.1694 (2.2058)	loss 3.1369 (3.2236)	grad_norm 2.1476 (2.1542)	
[2022-01-24 15:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1190/1251]	eta 0:02:14 lr 0.000182	time 1.5394 (2.2045)	loss 3.4894 (3.2238)	grad_norm 1.9697 (2.1541)	
[2022-01-24 15:32:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1200/1251]	eta 0:01:52 lr 0.000182	time 2.0835 (2.2023)	loss 3.2487 (3.2228)	grad_norm 1.9790 (2.1534)	
[2022-01-24 15:33:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1210/1251]	eta 0:01:30 lr 0.000182	time 2.0684 (2.2011)	loss 2.8881 (3.2231)	grad_norm 1.8208 (2.1522)	
[2022-01-24 15:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1220/1251]	eta 0:01:08 lr 0.000182	time 2.2480 (2.2003)	loss 3.8166 (3.2238)	grad_norm 2.0612 (2.1510)	
[2022-01-24 15:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1230/1251]	eta 0:00:46 lr 0.000182	time 2.1843 (2.2001)	loss 3.5641 (3.2259)	grad_norm 2.1420 (2.1500)	
[2022-01-24 15:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1240/1251]	eta 0:00:24 lr 0.000182	time 1.3270 (2.1989)	loss 2.1355 (3.2263)	grad_norm 2.2813 (2.1497)	
[2022-01-24 15:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [217/300][1250/1251]	eta 0:00:02 lr 0.000182	time 1.1731 (2.1940)	loss 3.3313 (3.2277)	grad_norm 2.0179 (2.1496)	
[2022-01-24 15:34:23 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 217 training takes 0:45:45
[2022-01-24 15:34:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.844 (18.844)	Loss 0.8222 (0.8222)	Acc@1 80.957 (80.957)	Acc@5 94.629 (94.629)	
[2022-01-24 15:34:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.647 (3.318)	Loss 0.8501 (0.8859)	Acc@1 78.418 (78.702)	Acc@5 94.922 (94.256)	
[2022-01-24 15:35:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.545 (2.723)	Loss 0.9020 (0.8722)	Acc@1 78.711 (79.078)	Acc@5 94.824 (94.587)	
[2022-01-24 15:35:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.584 (2.379)	Loss 0.8246 (0.8712)	Acc@1 80.762 (79.083)	Acc@5 94.434 (94.585)	
[2022-01-24 15:35:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.707 (2.249)	Loss 0.8570 (0.8757)	Acc@1 80.664 (79.054)	Acc@5 95.020 (94.600)	
[2022-01-24 15:36:02 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.000 Acc@5 94.666
[2022-01-24 15:36:02 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.0%
[2022-01-24 15:36:02 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.12%
[2022-01-24 15:36:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][0/1251]	eta 7:28:49 lr 0.000182	time 21.5261 (21.5261)	loss 3.4507 (3.4507)	grad_norm 2.2672 (2.2672)	
[2022-01-24 15:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][10/1251]	eta 1:22:47 lr 0.000182	time 1.5424 (4.0027)	loss 2.2346 (3.2469)	grad_norm 1.8180 (2.1526)	
[2022-01-24 15:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][20/1251]	eta 1:03:29 lr 0.000181	time 1.6986 (3.0947)	loss 3.1994 (3.3582)	grad_norm 2.1580 (2.1421)	
[2022-01-24 15:37:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][30/1251]	eta 0:56:01 lr 0.000181	time 1.9765 (2.7533)	loss 2.5522 (3.2700)	grad_norm 2.0921 (2.1305)	
[2022-01-24 15:37:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][40/1251]	eta 0:53:24 lr 0.000181	time 3.6880 (2.6459)	loss 3.8042 (3.3548)	grad_norm 2.0469 (2.1736)	
[2022-01-24 15:38:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][50/1251]	eta 0:51:13 lr 0.000181	time 1.9229 (2.5591)	loss 2.7307 (3.3079)	grad_norm 2.1248 (2.1920)	
[2022-01-24 15:38:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][60/1251]	eta 0:48:42 lr 0.000181	time 1.5455 (2.4542)	loss 3.0527 (3.2626)	grad_norm 1.8313 (2.1743)	
[2022-01-24 15:38:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][70/1251]	eta 0:47:37 lr 0.000181	time 2.1328 (2.4198)	loss 3.7892 (3.2705)	grad_norm 1.8352 (2.1695)	
[2022-01-24 15:39:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][80/1251]	eta 0:46:46 lr 0.000181	time 2.8719 (2.3970)	loss 3.8016 (3.2741)	grad_norm 2.7218 (2.1628)	
[2022-01-24 15:39:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][90/1251]	eta 0:45:52 lr 0.000181	time 2.0397 (2.3709)	loss 2.3105 (3.2670)	grad_norm 2.4156 (2.1653)	
[2022-01-24 15:39:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][100/1251]	eta 0:45:00 lr 0.000181	time 1.5183 (2.3459)	loss 2.2943 (3.2521)	grad_norm 2.0551 (2.1550)	
[2022-01-24 15:40:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][110/1251]	eta 0:44:35 lr 0.000181	time 2.6656 (2.3452)	loss 4.0308 (3.2558)	grad_norm 1.8582 (2.1482)	
[2022-01-24 15:40:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][120/1251]	eta 0:44:08 lr 0.000181	time 2.8149 (2.3418)	loss 3.4459 (3.2569)	grad_norm 2.2467 (2.1538)	
[2022-01-24 15:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][130/1251]	eta 0:43:47 lr 0.000181	time 3.3838 (2.3436)	loss 3.2723 (3.2520)	grad_norm 1.8878 (2.1451)	
[2022-01-24 15:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][140/1251]	eta 0:43:05 lr 0.000181	time 1.6191 (2.3270)	loss 3.2459 (3.2477)	grad_norm 2.1280 (2.1389)	
[2022-01-24 15:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][150/1251]	eta 0:42:41 lr 0.000181	time 3.6074 (2.3264)	loss 3.5134 (3.2352)	grad_norm 1.8650 (2.1401)	
[2022-01-24 15:42:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][160/1251]	eta 0:42:07 lr 0.000181	time 1.8880 (2.3167)	loss 2.5337 (3.2441)	grad_norm 1.8372 (2.1396)	
[2022-01-24 15:42:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][170/1251]	eta 0:41:51 lr 0.000181	time 2.5539 (2.3233)	loss 3.0492 (3.2423)	grad_norm 1.9564 (2.1315)	
[2022-01-24 15:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][180/1251]	eta 0:41:12 lr 0.000181	time 1.6420 (2.3086)	loss 3.7864 (3.2429)	grad_norm 2.3859 (2.1361)	
[2022-01-24 15:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][190/1251]	eta 0:40:39 lr 0.000181	time 3.1528 (2.2996)	loss 3.6760 (3.2470)	grad_norm 2.1990 (2.1364)	
[2022-01-24 15:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][200/1251]	eta 0:40:04 lr 0.000181	time 1.9741 (2.2880)	loss 3.2972 (3.2659)	grad_norm 2.1493 (2.1388)	
[2022-01-24 15:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][210/1251]	eta 0:39:46 lr 0.000181	time 2.1691 (2.2926)	loss 3.7157 (3.2722)	grad_norm 2.2302 (2.1443)	
[2022-01-24 15:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][220/1251]	eta 0:39:21 lr 0.000181	time 2.1995 (2.2908)	loss 3.5373 (3.2732)	grad_norm 2.0208 (2.1467)	
[2022-01-24 15:44:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][230/1251]	eta 0:39:03 lr 0.000181	time 2.5485 (2.2951)	loss 3.2715 (3.2635)	grad_norm 2.3352 (2.1482)	
[2022-01-24 15:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][240/1251]	eta 0:38:35 lr 0.000181	time 2.4168 (2.2906)	loss 3.6982 (3.2690)	grad_norm 1.9492 (2.1429)	
[2022-01-24 15:45:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][250/1251]	eta 0:38:01 lr 0.000181	time 1.8760 (2.2792)	loss 3.7904 (3.2706)	grad_norm 2.1458 (2.1400)	
[2022-01-24 15:45:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][260/1251]	eta 0:37:30 lr 0.000181	time 2.2468 (2.2710)	loss 2.9264 (3.2658)	grad_norm 2.0609 (2.1366)	
[2022-01-24 15:46:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][270/1251]	eta 0:37:01 lr 0.000181	time 2.1945 (2.2647)	loss 2.6117 (3.2571)	grad_norm 1.8513 (2.1376)	
[2022-01-24 15:46:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][280/1251]	eta 0:36:35 lr 0.000181	time 1.9215 (2.2614)	loss 2.5030 (3.2517)	grad_norm 1.9716 (2.1338)	
[2022-01-24 15:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][290/1251]	eta 0:36:15 lr 0.000181	time 2.2211 (2.2636)	loss 3.2702 (3.2376)	grad_norm 2.1205 (2.1316)	
[2022-01-24 15:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][300/1251]	eta 0:35:52 lr 0.000181	time 1.8751 (2.2631)	loss 3.5991 (3.2432)	grad_norm 1.9162 (2.1270)	
[2022-01-24 15:47:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][310/1251]	eta 0:35:33 lr 0.000181	time 3.5365 (2.2670)	loss 2.3667 (3.2409)	grad_norm 2.2878 (2.1262)	
[2022-01-24 15:48:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][320/1251]	eta 0:35:05 lr 0.000181	time 1.8984 (2.2612)	loss 3.8140 (3.2387)	grad_norm 2.6636 (2.1269)	
[2022-01-24 15:48:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][330/1251]	eta 0:34:38 lr 0.000181	time 1.9470 (2.2564)	loss 3.3189 (3.2418)	grad_norm 2.0391 (2.1263)	
[2022-01-24 15:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][340/1251]	eta 0:34:07 lr 0.000180	time 1.8576 (2.2481)	loss 4.1457 (3.2464)	grad_norm 2.1356 (2.1272)	
[2022-01-24 15:49:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][350/1251]	eta 0:33:42 lr 0.000180	time 2.2331 (2.2449)	loss 2.9955 (3.2488)	grad_norm 2.2641 (2.1257)	
[2022-01-24 15:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][360/1251]	eta 0:33:17 lr 0.000180	time 2.1893 (2.2419)	loss 2.7884 (3.2520)	grad_norm 1.9948 (2.1247)	
[2022-01-24 15:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][370/1251]	eta 0:32:53 lr 0.000180	time 2.8994 (2.2405)	loss 3.6328 (3.2529)	grad_norm 2.2320 (2.1257)	
[2022-01-24 15:50:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][380/1251]	eta 0:32:28 lr 0.000180	time 1.9532 (2.2374)	loss 3.6359 (3.2463)	grad_norm 2.2971 (2.1278)	
[2022-01-24 15:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][390/1251]	eta 0:32:08 lr 0.000180	time 2.9277 (2.2399)	loss 2.6218 (3.2432)	grad_norm 1.9069 (2.1326)	
[2022-01-24 15:51:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][400/1251]	eta 0:31:49 lr 0.000180	time 2.1418 (2.2434)	loss 3.4626 (3.2417)	grad_norm 1.8876 (2.1359)	
[2022-01-24 15:51:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][410/1251]	eta 0:31:30 lr 0.000180	time 3.4559 (2.2476)	loss 3.4383 (3.2381)	grad_norm 2.0610 (2.1395)	
[2022-01-24 15:51:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][420/1251]	eta 0:31:06 lr 0.000180	time 2.4307 (2.2467)	loss 2.6689 (3.2429)	grad_norm 2.0198 (2.1428)	
[2022-01-24 15:52:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][430/1251]	eta 0:30:40 lr 0.000180	time 1.8404 (2.2423)	loss 3.4282 (3.2421)	grad_norm 2.0724 (2.1425)	
[2022-01-24 15:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][440/1251]	eta 0:30:12 lr 0.000180	time 1.9423 (2.2353)	loss 3.6117 (3.2424)	grad_norm 2.1884 (2.1413)	
[2022-01-24 15:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][450/1251]	eta 0:29:46 lr 0.000180	time 1.8916 (2.2306)	loss 3.5935 (3.2431)	grad_norm 2.0122 (2.1379)	
[2022-01-24 15:53:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][460/1251]	eta 0:29:21 lr 0.000180	time 1.8933 (2.2272)	loss 3.6048 (3.2459)	grad_norm 1.9039 (2.1366)	
[2022-01-24 15:53:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][470/1251]	eta 0:28:58 lr 0.000180	time 2.2584 (2.2256)	loss 3.2980 (3.2443)	grad_norm 1.9714 (2.1343)	
[2022-01-24 15:53:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][480/1251]	eta 0:28:38 lr 0.000180	time 2.5216 (2.2283)	loss 3.2142 (3.2441)	grad_norm 2.1655 (2.1342)	
[2022-01-24 15:54:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][490/1251]	eta 0:28:15 lr 0.000180	time 1.9313 (2.2280)	loss 2.9409 (3.2422)	grad_norm 1.9777 (2.1339)	
[2022-01-24 15:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][500/1251]	eta 0:27:52 lr 0.000180	time 1.9606 (2.2273)	loss 3.0678 (3.2427)	grad_norm 1.8220 (2.1354)	
[2022-01-24 15:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][510/1251]	eta 0:27:30 lr 0.000180	time 1.9620 (2.2280)	loss 3.7077 (3.2434)	grad_norm 1.8822 (2.1336)	
[2022-01-24 15:55:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][520/1251]	eta 0:27:11 lr 0.000180	time 3.0971 (2.2313)	loss 2.9843 (3.2423)	grad_norm 2.1404 (2.1336)	
[2022-01-24 15:55:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][530/1251]	eta 0:26:46 lr 0.000180	time 1.8563 (2.2277)	loss 3.8476 (3.2434)	grad_norm 1.7831 (2.1348)	
[2022-01-24 15:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][540/1251]	eta 0:26:20 lr 0.000180	time 1.8543 (2.2235)	loss 3.7109 (3.2471)	grad_norm 2.5373 (2.1399)	
[2022-01-24 15:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][550/1251]	eta 0:25:58 lr 0.000180	time 2.3023 (2.2236)	loss 2.9482 (3.2471)	grad_norm 2.4941 (2.1409)	
[2022-01-24 15:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][560/1251]	eta 0:25:38 lr 0.000180	time 2.8738 (2.2259)	loss 3.5815 (3.2479)	grad_norm 1.8420 (2.1425)	
[2022-01-24 15:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][570/1251]	eta 0:25:13 lr 0.000180	time 2.2255 (2.2232)	loss 2.3896 (3.2404)	grad_norm 2.0468 (2.1413)	
[2022-01-24 15:57:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][580/1251]	eta 0:24:50 lr 0.000180	time 1.8617 (2.2217)	loss 3.6199 (3.2443)	grad_norm 1.9353 (2.1407)	
[2022-01-24 15:57:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][590/1251]	eta 0:24:28 lr 0.000180	time 2.2356 (2.2213)	loss 3.7076 (3.2466)	grad_norm 2.1350 (2.1409)	
[2022-01-24 15:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][600/1251]	eta 0:24:06 lr 0.000180	time 3.0914 (2.2224)	loss 3.9208 (3.2481)	grad_norm 1.9613 (2.1395)	
[2022-01-24 15:58:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][610/1251]	eta 0:23:44 lr 0.000180	time 1.9251 (2.2220)	loss 3.3262 (3.2459)	grad_norm 2.6476 (2.1409)	
[2022-01-24 15:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][620/1251]	eta 0:23:21 lr 0.000180	time 1.8349 (2.2211)	loss 3.3782 (3.2474)	grad_norm 2.3085 (2.1401)	
[2022-01-24 15:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][630/1251]	eta 0:22:58 lr 0.000180	time 2.5283 (2.2205)	loss 2.3430 (3.2494)	grad_norm 1.9981 (2.1391)	
[2022-01-24 15:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][640/1251]	eta 0:22:36 lr 0.000180	time 2.4904 (2.2204)	loss 3.4659 (3.2447)	grad_norm 2.1612 (2.1388)	
[2022-01-24 16:00:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][650/1251]	eta 0:22:12 lr 0.000180	time 2.1793 (2.2178)	loss 3.6543 (3.2480)	grad_norm 2.2501 (2.1406)	
[2022-01-24 16:00:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][660/1251]	eta 0:21:50 lr 0.000179	time 2.2888 (2.2177)	loss 3.1297 (3.2483)	grad_norm 1.8523 (2.1408)	
[2022-01-24 16:00:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][670/1251]	eta 0:21:27 lr 0.000179	time 2.4926 (2.2167)	loss 2.2418 (3.2474)	grad_norm 2.2097 (2.1393)	
[2022-01-24 16:01:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][680/1251]	eta 0:21:04 lr 0.000179	time 2.1165 (2.2141)	loss 3.2522 (3.2488)	grad_norm 2.1067 (2.1381)	
[2022-01-24 16:01:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][690/1251]	eta 0:20:41 lr 0.000179	time 1.9119 (2.2127)	loss 3.5650 (3.2480)	grad_norm 2.1651 (2.1385)	
[2022-01-24 16:01:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][700/1251]	eta 0:20:19 lr 0.000179	time 2.4347 (2.2131)	loss 3.3260 (3.2506)	grad_norm 2.0355 (2.1386)	
[2022-01-24 16:02:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][710/1251]	eta 0:19:57 lr 0.000179	time 2.4526 (2.2136)	loss 2.4198 (3.2479)	grad_norm 1.9015 (2.1373)	
[2022-01-24 16:02:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][720/1251]	eta 0:19:35 lr 0.000179	time 2.3175 (2.2140)	loss 3.3116 (3.2453)	grad_norm 1.9340 (2.1366)	
[2022-01-24 16:03:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][730/1251]	eta 0:19:13 lr 0.000179	time 2.0814 (2.2131)	loss 3.8571 (3.2457)	grad_norm 2.0412 (2.1388)	
[2022-01-24 16:03:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][740/1251]	eta 0:18:50 lr 0.000179	time 1.8452 (2.2126)	loss 2.8832 (3.2500)	grad_norm 2.1777 (2.1394)	
[2022-01-24 16:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][750/1251]	eta 0:18:28 lr 0.000179	time 2.3671 (2.2116)	loss 2.3865 (3.2497)	grad_norm 2.1134 (2.1391)	
[2022-01-24 16:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][760/1251]	eta 0:18:05 lr 0.000179	time 1.6192 (2.2113)	loss 3.2838 (3.2523)	grad_norm 2.1038 (2.1401)	
[2022-01-24 16:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][770/1251]	eta 0:17:43 lr 0.000179	time 2.5913 (2.2108)	loss 3.4607 (3.2501)	grad_norm 2.3395 (2.1398)	
[2022-01-24 16:04:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][780/1251]	eta 0:17:20 lr 0.000179	time 1.8239 (2.2099)	loss 3.7552 (3.2509)	grad_norm 1.9700 (2.1432)	
[2022-01-24 16:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][790/1251]	eta 0:16:58 lr 0.000179	time 2.2301 (2.2094)	loss 2.4590 (3.2500)	grad_norm 2.0878 (2.1430)	
[2022-01-24 16:05:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][800/1251]	eta 0:16:36 lr 0.000179	time 1.7330 (2.2087)	loss 3.3698 (3.2518)	grad_norm 1.9292 (2.1432)	
[2022-01-24 16:05:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][810/1251]	eta 0:16:14 lr 0.000179	time 2.6268 (2.2089)	loss 3.0920 (3.2523)	grad_norm 2.2253 (2.1422)	
[2022-01-24 16:06:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][820/1251]	eta 0:15:51 lr 0.000179	time 1.5169 (2.2083)	loss 3.7420 (3.2524)	grad_norm 1.9918 (2.1420)	
[2022-01-24 16:06:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][830/1251]	eta 0:15:30 lr 0.000179	time 2.2070 (2.2100)	loss 3.3388 (3.2532)	grad_norm 2.0985 (2.1424)	
[2022-01-24 16:07:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][840/1251]	eta 0:15:08 lr 0.000179	time 1.7951 (2.2093)	loss 3.4959 (3.2546)	grad_norm 1.9946 (2.1416)	
[2022-01-24 16:07:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][850/1251]	eta 0:14:45 lr 0.000179	time 1.9737 (2.2080)	loss 3.3316 (3.2569)	grad_norm 2.0414 (2.1424)	
[2022-01-24 16:07:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][860/1251]	eta 0:14:22 lr 0.000179	time 1.7193 (2.2071)	loss 3.2177 (3.2540)	grad_norm 2.0077 (2.1423)	
[2022-01-24 16:08:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][870/1251]	eta 0:14:01 lr 0.000179	time 2.8915 (2.2086)	loss 3.9106 (3.2512)	grad_norm 2.1473 (2.1417)	
[2022-01-24 16:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][880/1251]	eta 0:13:39 lr 0.000179	time 2.4199 (2.2086)	loss 3.9361 (3.2512)	grad_norm 2.2812 (2.1426)	
[2022-01-24 16:08:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][890/1251]	eta 0:13:17 lr 0.000179	time 2.3117 (2.2085)	loss 2.6134 (3.2526)	grad_norm 2.0588 (2.1421)	
[2022-01-24 16:09:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][900/1251]	eta 0:12:54 lr 0.000179	time 2.0238 (2.2068)	loss 3.4624 (3.2534)	grad_norm 2.3107 (2.1469)	
[2022-01-24 16:09:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][910/1251]	eta 0:12:31 lr 0.000179	time 2.0017 (2.2051)	loss 3.6019 (3.2534)	grad_norm 1.9868 (2.1463)	
[2022-01-24 16:09:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][920/1251]	eta 0:12:09 lr 0.000179	time 1.8196 (2.2034)	loss 3.6656 (3.2546)	grad_norm 2.0215 (2.1464)	
[2022-01-24 16:10:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][930/1251]	eta 0:11:47 lr 0.000179	time 1.6881 (2.2027)	loss 3.7132 (3.2546)	grad_norm 1.8569 (2.1459)	
[2022-01-24 16:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][940/1251]	eta 0:11:25 lr 0.000179	time 2.3636 (2.2036)	loss 3.4191 (3.2539)	grad_norm 2.4570 (2.1467)	
[2022-01-24 16:10:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][950/1251]	eta 0:11:03 lr 0.000179	time 2.2952 (2.2048)	loss 2.2094 (3.2509)	grad_norm 1.9145 (2.1470)	
[2022-01-24 16:11:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][960/1251]	eta 0:10:41 lr 0.000179	time 2.2046 (2.2051)	loss 3.3858 (3.2486)	grad_norm 1.9684 (2.1471)	
[2022-01-24 16:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][970/1251]	eta 0:10:19 lr 0.000179	time 1.9022 (2.2060)	loss 2.9684 (3.2481)	grad_norm 1.9527 (2.1471)	
[2022-01-24 16:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][980/1251]	eta 0:09:58 lr 0.000178	time 2.3625 (2.2068)	loss 3.2005 (3.2498)	grad_norm 1.9281 (2.1470)	
[2022-01-24 16:12:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][990/1251]	eta 0:09:35 lr 0.000178	time 1.7214 (2.2063)	loss 2.8465 (3.2499)	grad_norm 2.1646 (2.1480)	
[2022-01-24 16:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1000/1251]	eta 0:09:13 lr 0.000178	time 1.8850 (2.2047)	loss 3.1346 (3.2483)	grad_norm 2.1291 (2.1493)	
[2022-01-24 16:13:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1010/1251]	eta 0:08:50 lr 0.000178	time 1.8685 (2.2032)	loss 3.0647 (3.2478)	grad_norm 1.9926 (2.1493)	
[2022-01-24 16:13:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1020/1251]	eta 0:08:28 lr 0.000178	time 2.6805 (2.2031)	loss 3.0398 (3.2467)	grad_norm 1.8225 (2.1490)	
[2022-01-24 16:13:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1030/1251]	eta 0:08:06 lr 0.000178	time 2.1382 (2.2036)	loss 3.5980 (3.2477)	grad_norm 2.3494 (2.1488)	
[2022-01-24 16:14:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1040/1251]	eta 0:07:44 lr 0.000178	time 1.8318 (2.2026)	loss 3.5793 (3.2439)	grad_norm 2.2406 (2.1487)	
[2022-01-24 16:14:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1050/1251]	eta 0:07:22 lr 0.000178	time 1.8647 (2.2016)	loss 3.4439 (3.2433)	grad_norm 2.2073 (2.1495)	
[2022-01-24 16:14:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1060/1251]	eta 0:07:00 lr 0.000178	time 2.2385 (2.2008)	loss 3.3885 (3.2449)	grad_norm 2.2327 (2.1499)	
[2022-01-24 16:15:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1070/1251]	eta 0:06:38 lr 0.000178	time 2.5342 (2.2007)	loss 3.7889 (3.2464)	grad_norm 2.0181 (2.1511)	
[2022-01-24 16:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1080/1251]	eta 0:06:16 lr 0.000178	time 1.8213 (2.2005)	loss 3.0802 (3.2483)	grad_norm 2.1269 (2.1514)	
[2022-01-24 16:16:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1090/1251]	eta 0:05:54 lr 0.000178	time 2.8447 (2.2008)	loss 3.7605 (3.2490)	grad_norm 2.2728 (2.1521)	
[2022-01-24 16:16:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1100/1251]	eta 0:05:32 lr 0.000178	time 2.0026 (2.2006)	loss 2.4624 (3.2475)	grad_norm 2.0817 (2.1515)	
[2022-01-24 16:16:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1110/1251]	eta 0:05:10 lr 0.000178	time 2.1910 (2.2005)	loss 3.2183 (3.2482)	grad_norm 2.1992 (2.1517)	
[2022-01-24 16:17:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1120/1251]	eta 0:04:48 lr 0.000178	time 1.8521 (2.2007)	loss 3.5156 (3.2464)	grad_norm 2.2832 (2.1523)	
[2022-01-24 16:17:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1130/1251]	eta 0:04:26 lr 0.000178	time 2.3432 (2.2011)	loss 3.4407 (3.2470)	grad_norm 2.3314 (2.1522)	
[2022-01-24 16:17:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1140/1251]	eta 0:04:04 lr 0.000178	time 2.1581 (2.2011)	loss 3.6411 (3.2474)	grad_norm 2.3699 (2.1522)	
[2022-01-24 16:18:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1150/1251]	eta 0:03:42 lr 0.000178	time 2.3198 (2.1994)	loss 3.4404 (3.2471)	grad_norm 2.3105 (2.1522)	
[2022-01-24 16:18:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1160/1251]	eta 0:03:20 lr 0.000178	time 2.1875 (2.1998)	loss 2.1382 (3.2451)	grad_norm 2.1844 (2.1521)	
[2022-01-24 16:18:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1170/1251]	eta 0:02:58 lr 0.000178	time 1.9574 (2.1995)	loss 3.6780 (3.2473)	grad_norm 2.0195 (2.1515)	
[2022-01-24 16:19:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1180/1251]	eta 0:02:36 lr 0.000178	time 1.8619 (2.2002)	loss 2.4888 (3.2464)	grad_norm 2.1859 (2.1531)	
[2022-01-24 16:19:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1190/1251]	eta 0:02:14 lr 0.000178	time 2.0138 (2.2002)	loss 3.7192 (3.2469)	grad_norm 2.1881 (2.1537)	
[2022-01-24 16:20:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1200/1251]	eta 0:01:52 lr 0.000178	time 1.5711 (2.1995)	loss 3.5438 (3.2484)	grad_norm 1.9930 (2.1550)	
[2022-01-24 16:20:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1210/1251]	eta 0:01:30 lr 0.000178	time 1.6985 (2.1980)	loss 2.8947 (3.2474)	grad_norm 2.1703 (2.1554)	
[2022-01-24 16:20:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1220/1251]	eta 0:01:08 lr 0.000178	time 2.0025 (2.1973)	loss 3.7321 (3.2447)	grad_norm 2.9766 (2.1558)	
[2022-01-24 16:21:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1230/1251]	eta 0:00:46 lr 0.000178	time 1.9363 (2.1967)	loss 2.8941 (3.2446)	grad_norm 3.2184 (2.1564)	
[2022-01-24 16:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1240/1251]	eta 0:00:24 lr 0.000178	time 1.8968 (2.1973)	loss 3.5824 (3.2459)	grad_norm 2.1372 (2.1587)	
[2022-01-24 16:21:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [218/300][1250/1251]	eta 0:00:02 lr 0.000178	time 1.1734 (2.1927)	loss 3.0007 (3.2473)	grad_norm 2.1861 (2.1580)	
[2022-01-24 16:21:46 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 218 training takes 0:45:43
[2022-01-24 16:22:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.390 (18.390)	Loss 0.8453 (0.8453)	Acc@1 78.711 (78.711)	Acc@5 95.605 (95.605)	
[2022-01-24 16:22:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.318 (3.499)	Loss 0.8664 (0.8651)	Acc@1 80.078 (79.812)	Acc@5 94.727 (94.949)	
[2022-01-24 16:22:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.264 (2.596)	Loss 0.8445 (0.8683)	Acc@1 79.785 (79.655)	Acc@5 95.508 (94.899)	
[2022-01-24 16:22:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.315 (2.345)	Loss 0.9344 (0.8753)	Acc@1 79.199 (79.435)	Acc@5 94.629 (94.783)	
[2022-01-24 16:23:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.953 (2.209)	Loss 0.9008 (0.8761)	Acc@1 78.516 (79.333)	Acc@5 94.531 (94.808)	
[2022-01-24 16:23:23 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.330 Acc@5 94.786
[2022-01-24 16:23:23 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.3%
[2022-01-24 16:23:23 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.33%
[2022-01-24 16:23:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][0/1251]	eta 7:32:40 lr 0.000178	time 21.7114 (21.7114)	loss 3.6318 (3.6318)	grad_norm 2.0835 (2.0835)	
[2022-01-24 16:24:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][10/1251]	eta 1:23:42 lr 0.000178	time 2.6467 (4.0474)	loss 2.5784 (3.2955)	grad_norm 2.1430 (2.1083)	
[2022-01-24 16:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][20/1251]	eta 1:05:03 lr 0.000178	time 2.1241 (3.1707)	loss 2.0808 (3.2125)	grad_norm 2.0875 (2.1215)	
[2022-01-24 16:24:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][30/1251]	eta 0:59:32 lr 0.000178	time 1.6637 (2.9256)	loss 3.7196 (3.2478)	grad_norm 2.0958 (2.1319)	
[2022-01-24 16:25:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][40/1251]	eta 0:56:11 lr 0.000178	time 2.9872 (2.7841)	loss 3.7137 (3.2603)	grad_norm 1.9617 (2.1302)	
[2022-01-24 16:25:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][50/1251]	eta 0:53:46 lr 0.000177	time 2.2439 (2.6865)	loss 3.3097 (3.2786)	grad_norm 2.2318 (2.1111)	
[2022-01-24 16:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][60/1251]	eta 0:51:58 lr 0.000177	time 2.7128 (2.6184)	loss 2.2078 (3.2492)	grad_norm 2.1778 (2.1073)	
[2022-01-24 16:26:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][70/1251]	eta 0:50:04 lr 0.000177	time 1.6825 (2.5441)	loss 3.6491 (3.2494)	grad_norm 3.0568 (2.1533)	
[2022-01-24 16:26:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][80/1251]	eta 0:48:42 lr 0.000177	time 2.4719 (2.4961)	loss 2.2755 (3.2395)	grad_norm 1.9595 (2.1478)	
[2022-01-24 16:27:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][90/1251]	eta 0:47:39 lr 0.000177	time 3.1386 (2.4633)	loss 3.5432 (3.2468)	grad_norm 2.1517 (2.2198)	
[2022-01-24 16:27:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][100/1251]	eta 0:46:33 lr 0.000177	time 2.4112 (2.4271)	loss 2.6031 (3.2354)	grad_norm 2.1484 (2.2274)	
[2022-01-24 16:27:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][110/1251]	eta 0:45:27 lr 0.000177	time 1.8852 (2.3902)	loss 3.5914 (3.2602)	grad_norm 2.1832 (2.2236)	
[2022-01-24 16:28:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][120/1251]	eta 0:44:33 lr 0.000177	time 1.8807 (2.3635)	loss 3.4463 (3.2546)	grad_norm 2.5525 (2.2267)	
[2022-01-24 16:28:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][130/1251]	eta 0:43:56 lr 0.000177	time 2.9256 (2.3522)	loss 3.4210 (3.2525)	grad_norm 1.9485 (2.2197)	
[2022-01-24 16:28:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][140/1251]	eta 0:43:12 lr 0.000177	time 2.1972 (2.3339)	loss 3.7753 (3.2348)	grad_norm 2.4783 (2.2168)	
[2022-01-24 16:29:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][150/1251]	eta 0:42:33 lr 0.000177	time 2.2747 (2.3189)	loss 2.4581 (3.2525)	grad_norm 2.1872 (2.2147)	
[2022-01-24 16:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][160/1251]	eta 0:42:00 lr 0.000177	time 2.2592 (2.3102)	loss 3.7724 (3.2656)	grad_norm 1.9959 (2.2128)	
[2022-01-24 16:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][170/1251]	eta 0:41:26 lr 0.000177	time 2.8027 (2.3002)	loss 3.6406 (3.2666)	grad_norm 2.4400 (2.2110)	
[2022-01-24 16:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][180/1251]	eta 0:40:52 lr 0.000177	time 1.8966 (2.2897)	loss 2.7682 (3.2743)	grad_norm 2.1996 (2.2043)	
[2022-01-24 16:30:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][190/1251]	eta 0:40:20 lr 0.000177	time 1.9753 (2.2817)	loss 3.2161 (3.2638)	grad_norm 2.1567 (2.2049)	
[2022-01-24 16:31:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][200/1251]	eta 0:40:02 lr 0.000177	time 1.5532 (2.2856)	loss 3.6557 (3.2539)	grad_norm 2.3488 (2.2048)	
[2022-01-24 16:31:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][210/1251]	eta 0:39:29 lr 0.000177	time 2.1370 (2.2764)	loss 3.6166 (3.2586)	grad_norm 1.9054 (2.2005)	
[2022-01-24 16:31:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][220/1251]	eta 0:39:02 lr 0.000177	time 2.2976 (2.2720)	loss 3.3091 (3.2608)	grad_norm 2.3214 (2.1966)	
[2022-01-24 16:32:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][230/1251]	eta 0:38:36 lr 0.000177	time 2.0037 (2.2687)	loss 3.4699 (3.2515)	grad_norm 2.6061 (2.1975)	
[2022-01-24 16:32:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][240/1251]	eta 0:38:14 lr 0.000177	time 2.5523 (2.2699)	loss 2.2230 (3.2548)	grad_norm 2.3918 (2.2004)	
[2022-01-24 16:32:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][250/1251]	eta 0:37:49 lr 0.000177	time 2.2902 (2.2676)	loss 3.7453 (3.2563)	grad_norm 2.3789 (2.1972)	
[2022-01-24 16:33:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][260/1251]	eta 0:37:27 lr 0.000177	time 2.8829 (2.2678)	loss 3.1045 (3.2596)	grad_norm 2.1554 (2.1976)	
[2022-01-24 16:33:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][270/1251]	eta 0:36:59 lr 0.000177	time 1.5953 (2.2628)	loss 3.5318 (3.2535)	grad_norm 2.1952 (2.2009)	
[2022-01-24 16:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][280/1251]	eta 0:36:37 lr 0.000177	time 2.1540 (2.2630)	loss 3.5554 (3.2550)	grad_norm 1.9488 (2.1984)	
[2022-01-24 16:34:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][290/1251]	eta 0:36:09 lr 0.000177	time 2.2552 (2.2578)	loss 3.3908 (3.2524)	grad_norm 2.0273 (2.1959)	
[2022-01-24 16:34:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][300/1251]	eta 0:35:41 lr 0.000177	time 2.6463 (2.2518)	loss 2.8582 (3.2515)	grad_norm 2.0498 (2.1952)	
[2022-01-24 16:35:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][310/1251]	eta 0:35:10 lr 0.000177	time 1.7042 (2.2429)	loss 3.5567 (3.2477)	grad_norm 2.6410 (2.1979)	
[2022-01-24 16:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][320/1251]	eta 0:34:44 lr 0.000177	time 1.8828 (2.2390)	loss 3.7059 (3.2487)	grad_norm 2.5020 (2.1983)	
[2022-01-24 16:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][330/1251]	eta 0:34:22 lr 0.000177	time 2.2281 (2.2392)	loss 2.8616 (3.2414)	grad_norm 2.1297 (2.1971)	
[2022-01-24 16:36:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][340/1251]	eta 0:34:00 lr 0.000177	time 2.5715 (2.2400)	loss 3.4970 (3.2360)	grad_norm 2.0309 (2.1933)	
[2022-01-24 16:36:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][350/1251]	eta 0:33:40 lr 0.000177	time 2.1627 (2.2420)	loss 3.7513 (3.2413)	grad_norm 2.2759 (2.1952)	
[2022-01-24 16:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][360/1251]	eta 0:33:14 lr 0.000177	time 1.9202 (2.2382)	loss 3.6403 (3.2393)	grad_norm 2.0829 (2.1929)	
[2022-01-24 16:37:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][370/1251]	eta 0:32:47 lr 0.000177	time 1.8146 (2.2332)	loss 3.4765 (3.2427)	grad_norm 2.1541 (2.1937)	
[2022-01-24 16:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][380/1251]	eta 0:32:25 lr 0.000176	time 2.3954 (2.2341)	loss 3.5745 (3.2439)	grad_norm 2.0081 (2.1920)	
[2022-01-24 16:37:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][390/1251]	eta 0:32:04 lr 0.000176	time 2.0954 (2.2356)	loss 3.2755 (3.2464)	grad_norm 2.3632 (2.1917)	
[2022-01-24 16:38:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][400/1251]	eta 0:31:42 lr 0.000176	time 1.6025 (2.2352)	loss 3.6556 (3.2482)	grad_norm 2.2245 (2.1924)	
[2022-01-24 16:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][410/1251]	eta 0:31:17 lr 0.000176	time 2.1439 (2.2327)	loss 3.1619 (3.2522)	grad_norm 3.6598 (2.2051)	
[2022-01-24 16:39:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][420/1251]	eta 0:30:53 lr 0.000176	time 2.2608 (2.2306)	loss 3.5741 (3.2549)	grad_norm 2.0863 (2.2063)	
[2022-01-24 16:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][430/1251]	eta 0:30:29 lr 0.000176	time 1.6319 (2.2281)	loss 3.3184 (3.2498)	grad_norm 1.9738 (2.2059)	
[2022-01-24 16:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][440/1251]	eta 0:30:05 lr 0.000176	time 2.1219 (2.2265)	loss 3.3702 (3.2483)	grad_norm 2.6177 (2.2057)	
[2022-01-24 16:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][450/1251]	eta 0:29:39 lr 0.000176	time 2.0739 (2.2214)	loss 2.8874 (3.2424)	grad_norm 2.0853 (2.2054)	
[2022-01-24 16:40:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][460/1251]	eta 0:29:18 lr 0.000176	time 2.2715 (2.2234)	loss 2.9917 (3.2372)	grad_norm 2.1780 (2.2036)	
[2022-01-24 16:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][470/1251]	eta 0:28:55 lr 0.000176	time 2.1887 (2.2225)	loss 3.6498 (3.2384)	grad_norm 1.9542 (2.2010)	
[2022-01-24 16:41:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][480/1251]	eta 0:28:33 lr 0.000176	time 1.5916 (2.2230)	loss 2.6162 (3.2269)	grad_norm 2.1368 (2.2011)	
[2022-01-24 16:41:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][490/1251]	eta 0:28:12 lr 0.000176	time 1.9500 (2.2238)	loss 3.7841 (3.2316)	grad_norm 2.1807 (2.1991)	
[2022-01-24 16:41:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][500/1251]	eta 0:27:50 lr 0.000176	time 1.9566 (2.2241)	loss 2.3284 (3.2340)	grad_norm 2.0999 (2.1986)	
[2022-01-24 16:42:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][510/1251]	eta 0:27:29 lr 0.000176	time 1.9336 (2.2260)	loss 2.4380 (3.2334)	grad_norm 2.1456 (2.1983)	
[2022-01-24 16:42:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][520/1251]	eta 0:27:04 lr 0.000176	time 1.6498 (2.2225)	loss 2.4284 (3.2346)	grad_norm 2.2749 (2.2009)	
[2022-01-24 16:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][530/1251]	eta 0:26:38 lr 0.000176	time 2.1249 (2.2167)	loss 3.9242 (3.2339)	grad_norm 2.0862 (2.2015)	
[2022-01-24 16:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][540/1251]	eta 0:26:16 lr 0.000176	time 1.8916 (2.2170)	loss 3.3337 (3.2308)	grad_norm 2.3588 (2.2018)	
[2022-01-24 16:43:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][550/1251]	eta 0:25:53 lr 0.000176	time 1.9525 (2.2162)	loss 2.6630 (3.2345)	grad_norm 1.9575 (2.2016)	
[2022-01-24 16:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][560/1251]	eta 0:25:31 lr 0.000176	time 2.3325 (2.2159)	loss 3.6798 (3.2370)	grad_norm 2.1847 (2.2012)	
[2022-01-24 16:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][570/1251]	eta 0:25:07 lr 0.000176	time 2.5042 (2.2142)	loss 3.3621 (3.2436)	grad_norm 2.4556 (2.2043)	
[2022-01-24 16:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][580/1251]	eta 0:24:45 lr 0.000176	time 1.5067 (2.2137)	loss 2.0539 (3.2442)	grad_norm 2.0985 (2.2041)	
[2022-01-24 16:45:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][590/1251]	eta 0:24:23 lr 0.000176	time 2.8467 (2.2135)	loss 2.3062 (3.2388)	grad_norm 2.1615 (2.2038)	
[2022-01-24 16:45:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][600/1251]	eta 0:24:02 lr 0.000176	time 2.1457 (2.2151)	loss 3.5123 (3.2381)	grad_norm 2.1316 (2.2017)	
[2022-01-24 16:45:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][610/1251]	eta 0:23:39 lr 0.000176	time 2.0516 (2.2140)	loss 3.3265 (3.2335)	grad_norm 2.3653 (2.2002)	
[2022-01-24 16:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][620/1251]	eta 0:23:17 lr 0.000176	time 1.9103 (2.2142)	loss 2.3669 (3.2344)	grad_norm 2.1804 (2.1984)	
[2022-01-24 16:46:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][630/1251]	eta 0:22:54 lr 0.000176	time 1.9111 (2.2127)	loss 2.5821 (3.2359)	grad_norm 2.0632 (2.1969)	
[2022-01-24 16:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][640/1251]	eta 0:22:30 lr 0.000176	time 1.8148 (2.2100)	loss 2.4400 (3.2323)	grad_norm 2.0522 (2.1968)	
[2022-01-24 16:47:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][650/1251]	eta 0:22:07 lr 0.000176	time 1.8050 (2.2082)	loss 3.6828 (3.2314)	grad_norm 2.0819 (2.1955)	
[2022-01-24 16:47:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][660/1251]	eta 0:21:45 lr 0.000176	time 2.0811 (2.2094)	loss 3.5086 (3.2336)	grad_norm 2.0471 (2.1949)	
[2022-01-24 16:48:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][670/1251]	eta 0:21:24 lr 0.000176	time 2.1628 (2.2101)	loss 3.8296 (3.2365)	grad_norm 2.2041 (2.1953)	
[2022-01-24 16:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][680/1251]	eta 0:21:01 lr 0.000176	time 2.0921 (2.2099)	loss 3.3754 (3.2373)	grad_norm 2.2822 (2.1953)	
[2022-01-24 16:48:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][690/1251]	eta 0:20:40 lr 0.000176	time 2.0421 (2.2112)	loss 3.5465 (3.2366)	grad_norm 2.3845 (2.1945)	
[2022-01-24 16:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][700/1251]	eta 0:20:17 lr 0.000175	time 2.1999 (2.2094)	loss 3.3613 (3.2373)	grad_norm 2.3193 (2.1932)	
[2022-01-24 16:49:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][710/1251]	eta 0:19:54 lr 0.000175	time 1.8311 (2.2075)	loss 3.6089 (3.2352)	grad_norm 1.8678 (2.1914)	
[2022-01-24 16:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][720/1251]	eta 0:19:32 lr 0.000175	time 1.9280 (2.2075)	loss 3.7950 (3.2341)	grad_norm 2.2472 (2.1911)	
[2022-01-24 16:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][730/1251]	eta 0:19:08 lr 0.000175	time 1.9841 (2.2053)	loss 3.7131 (3.2326)	grad_norm 2.1891 (2.1913)	
[2022-01-24 16:50:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][740/1251]	eta 0:18:46 lr 0.000175	time 2.3542 (2.2054)	loss 3.6108 (3.2354)	grad_norm 2.0177 (2.1917)	
[2022-01-24 16:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][750/1251]	eta 0:18:25 lr 0.000175	time 2.7777 (2.2070)	loss 3.6711 (3.2348)	grad_norm 2.3523 (2.1928)	
[2022-01-24 16:51:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][760/1251]	eta 0:18:03 lr 0.000175	time 1.9226 (2.2072)	loss 3.5294 (3.2359)	grad_norm 2.0780 (2.1922)	
[2022-01-24 16:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][770/1251]	eta 0:17:40 lr 0.000175	time 2.0054 (2.2053)	loss 3.7408 (3.2347)	grad_norm 2.0014 (2.1913)	
[2022-01-24 16:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][780/1251]	eta 0:17:18 lr 0.000175	time 2.4300 (2.2056)	loss 3.2057 (3.2350)	grad_norm 2.2630 (2.1916)	
[2022-01-24 16:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][790/1251]	eta 0:16:56 lr 0.000175	time 2.1549 (2.2044)	loss 3.5386 (3.2357)	grad_norm 2.2379 (2.1913)	
[2022-01-24 16:52:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][800/1251]	eta 0:16:33 lr 0.000175	time 1.7645 (2.2025)	loss 3.1243 (3.2344)	grad_norm 2.0357 (2.1909)	
[2022-01-24 16:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][810/1251]	eta 0:16:11 lr 0.000175	time 2.0447 (2.2029)	loss 3.6435 (3.2351)	grad_norm 2.0839 (2.1903)	
[2022-01-24 16:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][820/1251]	eta 0:15:49 lr 0.000175	time 2.2355 (2.2030)	loss 3.6992 (3.2345)	grad_norm 2.3264 (2.1889)	
[2022-01-24 16:53:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][830/1251]	eta 0:15:27 lr 0.000175	time 2.2545 (2.2030)	loss 3.4030 (3.2361)	grad_norm 1.9315 (2.1897)	
[2022-01-24 16:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][840/1251]	eta 0:15:04 lr 0.000175	time 1.9076 (2.2012)	loss 2.0646 (3.2366)	grad_norm 2.0268 (2.1892)	
[2022-01-24 16:54:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][850/1251]	eta 0:14:42 lr 0.000175	time 2.0822 (2.2016)	loss 3.9379 (3.2347)	grad_norm 2.4266 (2.1878)	
[2022-01-24 16:54:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][860/1251]	eta 0:14:20 lr 0.000175	time 2.2361 (2.2010)	loss 3.9630 (3.2376)	grad_norm 2.1847 (2.1873)	
[2022-01-24 16:55:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][870/1251]	eta 0:13:58 lr 0.000175	time 1.7044 (2.2011)	loss 2.7066 (3.2352)	grad_norm 2.1189 (2.1865)	
[2022-01-24 16:55:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][880/1251]	eta 0:13:36 lr 0.000175	time 1.7322 (2.1996)	loss 4.0370 (3.2368)	grad_norm 2.2706 (2.1867)	
[2022-01-24 16:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][890/1251]	eta 0:13:14 lr 0.000175	time 1.8511 (2.1995)	loss 2.3201 (3.2399)	grad_norm 2.2490 (2.1878)	
[2022-01-24 16:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][900/1251]	eta 0:12:52 lr 0.000175	time 2.1447 (2.2014)	loss 3.3271 (3.2367)	grad_norm 1.8105 (2.1877)	
[2022-01-24 16:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][910/1251]	eta 0:12:31 lr 0.000175	time 2.4833 (2.2031)	loss 3.8331 (3.2380)	grad_norm 2.1581 (2.1884)	
[2022-01-24 16:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][920/1251]	eta 0:12:08 lr 0.000175	time 2.2023 (2.2013)	loss 3.5572 (3.2399)	grad_norm 2.3332 (2.1890)	
[2022-01-24 16:57:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][930/1251]	eta 0:11:45 lr 0.000175	time 1.9430 (2.1994)	loss 3.9046 (3.2406)	grad_norm 2.3618 (2.1902)	
[2022-01-24 16:57:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][940/1251]	eta 0:11:23 lr 0.000175	time 2.4053 (2.1987)	loss 3.7562 (3.2401)	grad_norm 3.0115 (2.1924)	
[2022-01-24 16:58:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][950/1251]	eta 0:11:02 lr 0.000175	time 2.2940 (2.1996)	loss 3.8909 (3.2422)	grad_norm 2.2271 (2.1940)	
[2022-01-24 16:58:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][960/1251]	eta 0:10:40 lr 0.000175	time 2.0758 (2.2000)	loss 2.6476 (3.2361)	grad_norm 2.3940 (2.1945)	
[2022-01-24 16:58:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][970/1251]	eta 0:10:18 lr 0.000175	time 2.0662 (2.1995)	loss 3.3727 (3.2370)	grad_norm 1.9901 (2.1947)	
[2022-01-24 16:59:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][980/1251]	eta 0:09:55 lr 0.000175	time 2.0866 (2.1986)	loss 3.2508 (3.2375)	grad_norm 2.2190 (2.1958)	
[2022-01-24 16:59:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][990/1251]	eta 0:09:33 lr 0.000175	time 2.3186 (2.1987)	loss 3.3099 (3.2373)	grad_norm 2.0524 (2.1949)	
[2022-01-24 17:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1000/1251]	eta 0:09:11 lr 0.000175	time 1.8336 (2.1983)	loss 2.8395 (3.2369)	grad_norm 1.8978 (2.1947)	
[2022-01-24 17:00:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1010/1251]	eta 0:08:49 lr 0.000175	time 1.8520 (2.1980)	loss 3.5693 (3.2361)	grad_norm 2.1317 (2.1941)	
[2022-01-24 17:00:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1020/1251]	eta 0:08:27 lr 0.000174	time 2.5537 (2.1982)	loss 3.6134 (3.2336)	grad_norm 2.2437 (2.1944)	
[2022-01-24 17:01:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1030/1251]	eta 0:08:05 lr 0.000174	time 1.6316 (2.1985)	loss 2.9672 (3.2352)	grad_norm 2.2906 (2.1946)	
[2022-01-24 17:01:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1040/1251]	eta 0:07:43 lr 0.000174	time 2.1030 (2.1975)	loss 3.6117 (3.2350)	grad_norm 2.2967 (2.1946)	
[2022-01-24 17:01:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1050/1251]	eta 0:07:21 lr 0.000174	time 1.8982 (2.1970)	loss 3.4485 (3.2341)	grad_norm 2.0801 (2.1930)	
[2022-01-24 17:02:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1060/1251]	eta 0:06:59 lr 0.000174	time 2.2560 (2.1961)	loss 3.6284 (3.2357)	grad_norm 2.2501 (2.1933)	
[2022-01-24 17:02:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1070/1251]	eta 0:06:37 lr 0.000174	time 1.8523 (2.1960)	loss 3.6057 (3.2354)	grad_norm 1.9970 (2.1928)	
[2022-01-24 17:02:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1080/1251]	eta 0:06:15 lr 0.000174	time 2.2586 (2.1955)	loss 3.2310 (3.2328)	grad_norm 2.0218 (2.1937)	
[2022-01-24 17:03:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1090/1251]	eta 0:05:53 lr 0.000174	time 2.0962 (2.1943)	loss 3.7252 (3.2347)	grad_norm 2.0104 (2.1925)	
[2022-01-24 17:03:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1100/1251]	eta 0:05:31 lr 0.000174	time 2.2227 (2.1943)	loss 2.7332 (3.2361)	grad_norm 2.1209 (2.1918)	
[2022-01-24 17:04:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1110/1251]	eta 0:05:09 lr 0.000174	time 2.0726 (2.1938)	loss 3.3056 (3.2368)	grad_norm 1.9168 (2.1909)	
[2022-01-24 17:04:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1120/1251]	eta 0:04:47 lr 0.000174	time 1.8766 (2.1943)	loss 3.3238 (3.2376)	grad_norm 1.8850 (2.1909)	
[2022-01-24 17:04:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1130/1251]	eta 0:04:25 lr 0.000174	time 2.4951 (2.1952)	loss 3.4920 (3.2358)	grad_norm 2.5837 (2.1930)	
[2022-01-24 17:05:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1140/1251]	eta 0:04:03 lr 0.000174	time 2.2186 (2.1944)	loss 2.6474 (3.2341)	grad_norm 1.9652 (2.1927)	
[2022-01-24 17:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1150/1251]	eta 0:03:41 lr 0.000174	time 1.8512 (2.1941)	loss 3.2439 (3.2340)	grad_norm 2.1224 (2.1917)	
[2022-01-24 17:05:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1160/1251]	eta 0:03:19 lr 0.000174	time 1.6612 (2.1930)	loss 3.8198 (3.2341)	grad_norm 2.3695 (2.1912)	
[2022-01-24 17:06:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1170/1251]	eta 0:02:57 lr 0.000174	time 2.2766 (2.1935)	loss 2.2702 (3.2328)	grad_norm 1.9731 (2.1914)	
[2022-01-24 17:06:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1180/1251]	eta 0:02:35 lr 0.000174	time 2.5108 (2.1933)	loss 3.2470 (3.2338)	grad_norm 2.2965 (2.1915)	
[2022-01-24 17:06:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1190/1251]	eta 0:02:13 lr 0.000174	time 2.4790 (2.1936)	loss 3.8501 (3.2333)	grad_norm 2.5590 (2.1911)	
[2022-01-24 17:07:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1200/1251]	eta 0:01:51 lr 0.000174	time 1.8569 (2.1936)	loss 2.6128 (3.2307)	grad_norm 2.6175 (2.1908)	
[2022-01-24 17:07:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1210/1251]	eta 0:01:29 lr 0.000174	time 2.2221 (2.1941)	loss 3.4969 (3.2288)	grad_norm 2.1601 (2.1908)	
[2022-01-24 17:08:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1220/1251]	eta 0:01:08 lr 0.000174	time 2.2077 (2.1942)	loss 3.3621 (3.2302)	grad_norm 1.9327 (2.1905)	
[2022-01-24 17:08:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1230/1251]	eta 0:00:46 lr 0.000174	time 1.5587 (2.1948)	loss 3.5087 (3.2288)	grad_norm 1.9266 (2.1898)	
[2022-01-24 17:08:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1240/1251]	eta 0:00:24 lr 0.000174	time 1.6404 (2.1938)	loss 3.4606 (3.2298)	grad_norm 2.3797 (2.1892)	
[2022-01-24 17:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [219/300][1250/1251]	eta 0:00:02 lr 0.000174	time 1.2114 (2.1881)	loss 3.3137 (3.2308)	grad_norm 2.6252 (2.1891)	
[2022-01-24 17:09:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 219 training takes 0:45:37
[2022-01-24 17:09:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.596 (18.596)	Loss 0.8955 (0.8955)	Acc@1 78.809 (78.809)	Acc@5 95.117 (95.117)	
[2022-01-24 17:09:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.256 (3.546)	Loss 0.9703 (0.8777)	Acc@1 76.855 (79.510)	Acc@5 94.238 (94.869)	
[2022-01-24 17:09:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.958 (2.489)	Loss 0.9320 (0.8839)	Acc@1 78.223 (79.204)	Acc@5 93.555 (94.754)	
[2022-01-24 17:10:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.609 (2.274)	Loss 0.9073 (0.8874)	Acc@1 78.613 (79.080)	Acc@5 94.727 (94.749)	
[2022-01-24 17:10:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.322 (2.156)	Loss 0.9206 (0.8805)	Acc@1 78.516 (79.137)	Acc@5 95.020 (94.841)	
[2022-01-24 17:10:36 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.114 Acc@5 94.804
[2022-01-24 17:10:36 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.1%
[2022-01-24 17:10:36 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.33%
[2022-01-24 17:10:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][0/1251]	eta 7:42:31 lr 0.000174	time 22.1832 (22.1832)	loss 3.5796 (3.5796)	grad_norm 2.1415 (2.1415)	
[2022-01-24 17:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][10/1251]	eta 1:25:46 lr 0.000174	time 2.1815 (4.1469)	loss 2.5628 (3.0022)	grad_norm 2.1401 (2.0717)	
[2022-01-24 17:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][20/1251]	eta 1:06:34 lr 0.000174	time 1.8366 (3.2446)	loss 3.0910 (3.0801)	grad_norm 2.0984 (2.0924)	
[2022-01-24 17:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][30/1251]	eta 0:59:27 lr 0.000174	time 1.3596 (2.9215)	loss 3.1349 (3.1199)	grad_norm 2.2102 (2.1065)	
[2022-01-24 17:12:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][40/1251]	eta 0:56:29 lr 0.000174	time 3.6465 (2.7990)	loss 2.9250 (3.1404)	grad_norm 2.2572 (2.1176)	
[2022-01-24 17:12:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][50/1251]	eta 0:53:45 lr 0.000174	time 2.6540 (2.6860)	loss 3.6443 (3.2017)	grad_norm 2.0592 (2.1413)	
[2022-01-24 17:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][60/1251]	eta 0:51:37 lr 0.000174	time 1.8831 (2.6009)	loss 3.4727 (3.1963)	grad_norm 2.0984 (2.1397)	
[2022-01-24 17:13:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][70/1251]	eta 0:49:18 lr 0.000174	time 1.6576 (2.5052)	loss 3.6240 (3.1797)	grad_norm 1.9545 (2.1335)	
[2022-01-24 17:13:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][80/1251]	eta 0:47:54 lr 0.000174	time 2.9793 (2.4545)	loss 3.6377 (3.2048)	grad_norm 1.8877 (2.1436)	
[2022-01-24 17:14:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][90/1251]	eta 0:46:57 lr 0.000174	time 1.6164 (2.4272)	loss 3.9704 (3.2186)	grad_norm 2.3425 (2.1628)	
[2022-01-24 17:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][100/1251]	eta 0:46:12 lr 0.000173	time 2.1982 (2.4085)	loss 3.4480 (3.2146)	grad_norm 2.1514 (2.1759)	
[2022-01-24 17:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][110/1251]	eta 0:45:25 lr 0.000173	time 2.2183 (2.3887)	loss 2.9503 (3.2034)	grad_norm 2.0133 (2.1711)	
[2022-01-24 17:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][120/1251]	eta 0:44:58 lr 0.000173	time 2.7140 (2.3860)	loss 4.0875 (3.2254)	grad_norm 2.5870 (2.1855)	
[2022-01-24 17:15:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][130/1251]	eta 0:44:39 lr 0.000173	time 2.7657 (2.3900)	loss 3.6757 (3.2255)	grad_norm 2.1735 (2.1865)	
[2022-01-24 17:16:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][140/1251]	eta 0:43:58 lr 0.000173	time 1.8780 (2.3753)	loss 2.8915 (3.2310)	grad_norm 2.5457 (2.1849)	
[2022-01-24 17:16:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][150/1251]	eta 0:43:18 lr 0.000173	time 1.8141 (2.3600)	loss 3.8566 (3.2480)	grad_norm 2.4633 (2.1938)	
[2022-01-24 17:16:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][160/1251]	eta 0:42:24 lr 0.000173	time 1.9363 (2.3321)	loss 3.6746 (3.2661)	grad_norm 1.8456 (2.1993)	
[2022-01-24 17:17:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][170/1251]	eta 0:41:45 lr 0.000173	time 2.7714 (2.3178)	loss 2.7806 (3.2666)	grad_norm 2.2944 (2.2009)	
[2022-01-24 17:17:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][180/1251]	eta 0:41:09 lr 0.000173	time 1.9686 (2.3056)	loss 2.8485 (3.2424)	grad_norm 1.9489 (2.1949)	
[2022-01-24 17:17:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][190/1251]	eta 0:40:34 lr 0.000173	time 2.0116 (2.2944)	loss 3.6566 (3.2493)	grad_norm 2.4524 (2.1910)	
[2022-01-24 17:18:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][200/1251]	eta 0:39:57 lr 0.000173	time 2.1853 (2.2808)	loss 3.5859 (3.2560)	grad_norm 2.6293 (2.1959)	
[2022-01-24 17:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][210/1251]	eta 0:39:32 lr 0.000173	time 2.1516 (2.2792)	loss 3.8111 (3.2488)	grad_norm 2.1419 (2.2037)	
[2022-01-24 17:19:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][220/1251]	eta 0:39:14 lr 0.000173	time 1.9166 (2.2834)	loss 1.8896 (3.2484)	grad_norm 2.3537 (2.2068)	
[2022-01-24 17:19:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][230/1251]	eta 0:38:49 lr 0.000173	time 2.5617 (2.2813)	loss 3.6519 (3.2454)	grad_norm 2.0225 (2.2026)	
[2022-01-24 17:19:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][240/1251]	eta 0:38:24 lr 0.000173	time 1.8526 (2.2794)	loss 3.4216 (3.2539)	grad_norm 2.1770 (2.2015)	
[2022-01-24 17:20:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][250/1251]	eta 0:38:07 lr 0.000173	time 3.4058 (2.2852)	loss 3.3802 (3.2589)	grad_norm 2.1356 (2.2012)	
[2022-01-24 17:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][260/1251]	eta 0:37:45 lr 0.000173	time 2.1449 (2.2860)	loss 2.8300 (3.2562)	grad_norm 2.0751 (2.2020)	
[2022-01-24 17:20:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][270/1251]	eta 0:37:15 lr 0.000173	time 1.7960 (2.2789)	loss 2.5844 (3.2529)	grad_norm 2.0106 (2.1983)	
[2022-01-24 17:21:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][280/1251]	eta 0:36:43 lr 0.000173	time 1.8408 (2.2692)	loss 3.3777 (3.2571)	grad_norm 2.1862 (2.1980)	
[2022-01-24 17:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][290/1251]	eta 0:36:13 lr 0.000173	time 2.8279 (2.2616)	loss 3.1654 (3.2487)	grad_norm 2.0758 (2.2001)	
[2022-01-24 17:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][300/1251]	eta 0:35:41 lr 0.000173	time 1.8907 (2.2519)	loss 3.1130 (3.2438)	grad_norm 2.0705 (2.1967)	
[2022-01-24 17:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][310/1251]	eta 0:35:16 lr 0.000173	time 2.4243 (2.2490)	loss 2.3655 (3.2326)	grad_norm 2.1473 (2.1928)	
[2022-01-24 17:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][320/1251]	eta 0:34:55 lr 0.000173	time 1.8485 (2.2503)	loss 3.6914 (3.2323)	grad_norm 2.1952 (2.1914)	
[2022-01-24 17:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][330/1251]	eta 0:34:29 lr 0.000173	time 2.1042 (2.2466)	loss 3.7955 (3.2400)	grad_norm 2.5786 (2.1917)	
[2022-01-24 17:23:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][340/1251]	eta 0:34:08 lr 0.000173	time 2.6719 (2.2481)	loss 3.0458 (3.2282)	grad_norm 2.5249 (2.1949)	
[2022-01-24 17:23:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][350/1251]	eta 0:33:46 lr 0.000173	time 3.3016 (2.2493)	loss 3.6773 (3.2313)	grad_norm 2.9394 (2.1985)	
[2022-01-24 17:24:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][360/1251]	eta 0:33:25 lr 0.000173	time 2.5881 (2.2504)	loss 3.3549 (3.2374)	grad_norm 1.9881 (2.1991)	
[2022-01-24 17:24:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][370/1251]	eta 0:33:01 lr 0.000173	time 2.1188 (2.2494)	loss 3.6308 (3.2357)	grad_norm 2.1052 (2.1994)	
[2022-01-24 17:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][380/1251]	eta 0:32:37 lr 0.000173	time 1.8676 (2.2479)	loss 3.4342 (3.2375)	grad_norm 2.5894 (2.1998)	
[2022-01-24 17:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][390/1251]	eta 0:32:16 lr 0.000173	time 3.4632 (2.2489)	loss 3.7536 (3.2336)	grad_norm 3.1420 (2.2076)	
[2022-01-24 17:25:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][400/1251]	eta 0:31:52 lr 0.000173	time 2.4252 (2.2471)	loss 2.1958 (3.2360)	grad_norm 2.6347 (2.2114)	
[2022-01-24 17:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][410/1251]	eta 0:31:25 lr 0.000173	time 1.8705 (2.2426)	loss 2.0605 (3.2316)	grad_norm 2.7625 (2.2141)	
[2022-01-24 17:26:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][420/1251]	eta 0:31:00 lr 0.000172	time 2.8744 (2.2393)	loss 3.2866 (3.2379)	grad_norm 2.0216 (2.2128)	
[2022-01-24 17:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][430/1251]	eta 0:30:33 lr 0.000172	time 1.5965 (2.2336)	loss 2.7958 (3.2332)	grad_norm 2.3146 (2.2096)	
[2022-01-24 17:27:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][440/1251]	eta 0:30:10 lr 0.000172	time 2.2023 (2.2328)	loss 1.9147 (3.2283)	grad_norm 2.1692 (2.2088)	
[2022-01-24 17:27:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][450/1251]	eta 0:29:46 lr 0.000172	time 2.6508 (2.2303)	loss 2.6040 (3.2232)	grad_norm 2.1059 (2.2105)	
[2022-01-24 17:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][460/1251]	eta 0:29:22 lr 0.000172	time 2.4820 (2.2281)	loss 3.3245 (3.2211)	grad_norm 2.1307 (2.2105)	
[2022-01-24 17:28:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][470/1251]	eta 0:29:00 lr 0.000172	time 1.9799 (2.2287)	loss 3.0617 (3.2205)	grad_norm 1.9856 (2.2087)	
[2022-01-24 17:28:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][480/1251]	eta 0:28:40 lr 0.000172	time 2.6980 (2.2318)	loss 4.1736 (3.2275)	grad_norm 2.3556 (2.2069)	
[2022-01-24 17:28:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][490/1251]	eta 0:28:19 lr 0.000172	time 1.9068 (2.2339)	loss 2.5904 (3.2304)	grad_norm 2.1757 (2.2095)	
[2022-01-24 17:29:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][500/1251]	eta 0:27:57 lr 0.000172	time 2.4524 (2.2335)	loss 3.4784 (3.2272)	grad_norm 2.1214 (2.2120)	
[2022-01-24 17:29:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][510/1251]	eta 0:27:30 lr 0.000172	time 1.5981 (2.2281)	loss 3.6583 (3.2295)	grad_norm 2.2046 (2.2114)	
[2022-01-24 17:29:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][520/1251]	eta 0:27:05 lr 0.000172	time 1.9188 (2.2233)	loss 2.8958 (3.2272)	grad_norm 2.1342 (2.2130)	
[2022-01-24 17:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][530/1251]	eta 0:26:41 lr 0.000172	time 2.5992 (2.2210)	loss 2.1244 (3.2253)	grad_norm 1.9554 (2.2108)	
[2022-01-24 17:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][540/1251]	eta 0:26:17 lr 0.000172	time 2.2829 (2.2182)	loss 3.4786 (3.2259)	grad_norm 2.1992 (2.2108)	
[2022-01-24 17:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][550/1251]	eta 0:25:55 lr 0.000172	time 2.5271 (2.2184)	loss 3.1248 (3.2268)	grad_norm 1.7758 (2.2093)	
[2022-01-24 17:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][560/1251]	eta 0:25:34 lr 0.000172	time 1.8971 (2.2203)	loss 3.6092 (3.2266)	grad_norm 2.2348 (2.2094)	
[2022-01-24 17:31:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][570/1251]	eta 0:25:13 lr 0.000172	time 2.3621 (2.2231)	loss 3.6862 (3.2246)	grad_norm 2.2347 (2.2075)	
[2022-01-24 17:32:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][580/1251]	eta 0:24:50 lr 0.000172	time 2.4973 (2.2214)	loss 3.4901 (3.2278)	grad_norm 2.2023 (2.2060)	
[2022-01-24 17:32:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][590/1251]	eta 0:24:26 lr 0.000172	time 1.5660 (2.2181)	loss 3.8668 (3.2259)	grad_norm 1.9695 (2.2064)	
[2022-01-24 17:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][600/1251]	eta 0:24:03 lr 0.000172	time 1.8899 (2.2176)	loss 3.2697 (3.2213)	grad_norm 1.9155 (2.2073)	
[2022-01-24 17:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][610/1251]	eta 0:23:40 lr 0.000172	time 1.9200 (2.2157)	loss 2.9919 (3.2229)	grad_norm 2.0960 (2.2078)	
[2022-01-24 17:33:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][620/1251]	eta 0:23:17 lr 0.000172	time 2.1180 (2.2149)	loss 3.7204 (3.2235)	grad_norm 1.9896 (2.2077)	
[2022-01-24 17:33:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][630/1251]	eta 0:22:55 lr 0.000172	time 2.4476 (2.2150)	loss 3.6641 (3.2250)	grad_norm 2.2792 (2.2070)	
[2022-01-24 17:34:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][640/1251]	eta 0:22:34 lr 0.000172	time 2.8355 (2.2163)	loss 3.7761 (3.2268)	grad_norm 2.1452 (2.2055)	
[2022-01-24 17:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][650/1251]	eta 0:22:11 lr 0.000172	time 1.5101 (2.2157)	loss 3.3720 (3.2276)	grad_norm 2.1116 (2.2043)	
[2022-01-24 17:35:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][660/1251]	eta 0:21:49 lr 0.000172	time 2.2428 (2.2166)	loss 3.7093 (3.2278)	grad_norm 1.8480 (2.2028)	
[2022-01-24 17:35:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][670/1251]	eta 0:21:27 lr 0.000172	time 2.0582 (2.2162)	loss 3.9687 (3.2324)	grad_norm 2.1656 (2.2015)	
[2022-01-24 17:35:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][680/1251]	eta 0:21:05 lr 0.000172	time 1.8907 (2.2164)	loss 2.7656 (3.2315)	grad_norm 2.5581 (2.2025)	
[2022-01-24 17:36:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][690/1251]	eta 0:20:43 lr 0.000172	time 2.1238 (2.2174)	loss 2.8461 (3.2308)	grad_norm 2.2671 (2.2018)	
[2022-01-24 17:36:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][700/1251]	eta 0:20:20 lr 0.000172	time 2.1780 (2.2158)	loss 3.7655 (3.2320)	grad_norm 2.2917 (2.2019)	
[2022-01-24 17:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][710/1251]	eta 0:19:58 lr 0.000172	time 2.5991 (2.2146)	loss 2.1199 (3.2321)	grad_norm 1.9789 (2.2005)	
[2022-01-24 17:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][720/1251]	eta 0:19:34 lr 0.000172	time 2.0015 (2.2123)	loss 3.6407 (3.2352)	grad_norm 2.0146 (2.1984)	
[2022-01-24 17:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][730/1251]	eta 0:19:12 lr 0.000172	time 2.2431 (2.2127)	loss 3.2965 (3.2364)	grad_norm 2.2211 (2.1979)	
[2022-01-24 17:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][740/1251]	eta 0:18:50 lr 0.000172	time 2.1427 (2.2120)	loss 2.6172 (3.2334)	grad_norm 2.1567 (2.1980)	
[2022-01-24 17:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][750/1251]	eta 0:18:26 lr 0.000171	time 2.1812 (2.2094)	loss 3.4995 (3.2363)	grad_norm 2.2012 (2.1969)	
[2022-01-24 17:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][760/1251]	eta 0:18:05 lr 0.000171	time 2.1872 (2.2098)	loss 2.6407 (3.2339)	grad_norm 2.0741 (2.1984)	
[2022-01-24 17:39:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][770/1251]	eta 0:17:43 lr 0.000171	time 2.1513 (2.2101)	loss 3.6288 (3.2348)	grad_norm 2.1249 (2.1982)	
[2022-01-24 17:39:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][780/1251]	eta 0:17:20 lr 0.000171	time 1.8676 (2.2098)	loss 3.2386 (3.2355)	grad_norm 2.0213 (2.1995)	
[2022-01-24 17:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][790/1251]	eta 0:16:58 lr 0.000171	time 1.8232 (2.2104)	loss 3.6274 (3.2343)	grad_norm 2.1945 (2.1996)	
[2022-01-24 17:40:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][800/1251]	eta 0:16:36 lr 0.000171	time 1.8827 (2.2095)	loss 3.1176 (3.2347)	grad_norm 1.8734 (2.1997)	
[2022-01-24 17:40:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][810/1251]	eta 0:16:13 lr 0.000171	time 1.9492 (2.2079)	loss 3.4664 (3.2368)	grad_norm 1.9669 (2.1988)	
[2022-01-24 17:40:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][820/1251]	eta 0:15:51 lr 0.000171	time 2.2145 (2.2082)	loss 2.1177 (3.2336)	grad_norm 2.4170 (2.1979)	
[2022-01-24 17:41:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][830/1251]	eta 0:15:28 lr 0.000171	time 1.9352 (2.2065)	loss 2.6384 (3.2342)	grad_norm 2.3869 (2.1984)	
[2022-01-24 17:41:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][840/1251]	eta 0:15:06 lr 0.000171	time 1.9415 (2.2047)	loss 3.1617 (3.2359)	grad_norm 1.8970 (2.1983)	
[2022-01-24 17:41:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][850/1251]	eta 0:14:43 lr 0.000171	time 1.5066 (2.2027)	loss 3.3097 (3.2361)	grad_norm 2.2215 (2.1976)	
[2022-01-24 17:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][860/1251]	eta 0:14:21 lr 0.000171	time 1.9410 (2.2025)	loss 2.3531 (3.2362)	grad_norm 1.8528 (2.1981)	
[2022-01-24 17:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][870/1251]	eta 0:13:59 lr 0.000171	time 2.4655 (2.2027)	loss 3.5702 (3.2374)	grad_norm 2.4518 (2.1968)	
[2022-01-24 17:42:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][880/1251]	eta 0:13:37 lr 0.000171	time 2.8152 (2.2035)	loss 3.7115 (3.2382)	grad_norm 1.9887 (2.1983)	
[2022-01-24 17:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][890/1251]	eta 0:13:15 lr 0.000171	time 1.7450 (2.2042)	loss 2.4412 (3.2373)	grad_norm 2.0903 (2.1998)	
[2022-01-24 17:43:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][900/1251]	eta 0:12:54 lr 0.000171	time 1.8030 (2.2054)	loss 2.8351 (3.2374)	grad_norm 2.1980 (2.2006)	
[2022-01-24 17:44:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][910/1251]	eta 0:12:32 lr 0.000171	time 2.6393 (2.2053)	loss 2.6728 (3.2356)	grad_norm 2.3203 (2.2014)	
[2022-01-24 17:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][920/1251]	eta 0:12:09 lr 0.000171	time 1.9581 (2.2035)	loss 3.9625 (3.2347)	grad_norm 2.1603 (2.2012)	
[2022-01-24 17:44:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][930/1251]	eta 0:11:47 lr 0.000171	time 1.6919 (2.2056)	loss 4.0681 (3.2369)	grad_norm 2.1713 (2.2017)	
[2022-01-24 17:45:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][940/1251]	eta 0:11:26 lr 0.000171	time 2.8422 (2.2067)	loss 3.3642 (3.2395)	grad_norm 2.4103 (2.2025)	
[2022-01-24 17:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][950/1251]	eta 0:11:03 lr 0.000171	time 1.7011 (2.2040)	loss 3.2222 (3.2392)	grad_norm 2.2323 (2.2039)	
[2022-01-24 17:45:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][960/1251]	eta 0:10:40 lr 0.000171	time 1.7070 (2.2018)	loss 3.3692 (3.2408)	grad_norm 2.1355 (2.2038)	
[2022-01-24 17:46:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][970/1251]	eta 0:10:18 lr 0.000171	time 1.9174 (2.2007)	loss 3.6083 (3.2408)	grad_norm 2.5293 (2.2034)	
[2022-01-24 17:46:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][980/1251]	eta 0:09:56 lr 0.000171	time 2.3244 (2.2004)	loss 3.4803 (3.2414)	grad_norm 1.9344 (2.2030)	
[2022-01-24 17:46:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][990/1251]	eta 0:09:34 lr 0.000171	time 2.5558 (2.2005)	loss 3.9460 (3.2434)	grad_norm 2.5147 (2.2021)	
[2022-01-24 17:47:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1000/1251]	eta 0:09:12 lr 0.000171	time 1.8307 (2.1993)	loss 2.2933 (3.2420)	grad_norm 2.1819 (2.2045)	
[2022-01-24 17:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1010/1251]	eta 0:08:50 lr 0.000171	time 1.8732 (2.2002)	loss 3.5424 (3.2419)	grad_norm 2.1261 (2.2055)	
[2022-01-24 17:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1020/1251]	eta 0:08:28 lr 0.000171	time 2.5675 (2.2001)	loss 3.7544 (3.2407)	grad_norm 1.9883 (2.2086)	
[2022-01-24 17:48:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1030/1251]	eta 0:08:05 lr 0.000171	time 2.2826 (2.1987)	loss 3.6344 (3.2417)	grad_norm 2.3755 (2.2086)	
[2022-01-24 17:48:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1040/1251]	eta 0:07:43 lr 0.000171	time 2.7793 (2.1985)	loss 3.5364 (3.2412)	grad_norm 1.9540 (2.2080)	
[2022-01-24 17:49:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1050/1251]	eta 0:07:21 lr 0.000171	time 1.5340 (2.1975)	loss 2.6868 (3.2407)	grad_norm 2.0652 (2.2075)	
[2022-01-24 17:49:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1060/1251]	eta 0:06:59 lr 0.000171	time 3.1755 (2.1987)	loss 3.7696 (3.2407)	grad_norm 2.0176 (2.2065)	
[2022-01-24 17:49:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1070/1251]	eta 0:06:38 lr 0.000170	time 2.7801 (2.1997)	loss 2.8181 (3.2391)	grad_norm 2.4014 (2.2059)	
[2022-01-24 17:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1080/1251]	eta 0:06:16 lr 0.000170	time 2.8110 (2.2005)	loss 2.9410 (3.2405)	grad_norm 2.0942 (2.2054)	
[2022-01-24 17:50:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1090/1251]	eta 0:05:54 lr 0.000170	time 1.9396 (2.2024)	loss 3.0933 (3.2377)	grad_norm 2.2147 (2.2052)	
[2022-01-24 17:51:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1100/1251]	eta 0:05:32 lr 0.000170	time 2.8730 (2.2032)	loss 2.7012 (3.2320)	grad_norm 2.4560 (2.2048)	
[2022-01-24 17:51:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1110/1251]	eta 0:05:10 lr 0.000170	time 2.4842 (2.2026)	loss 2.7500 (3.2327)	grad_norm 2.0332 (2.2055)	
[2022-01-24 17:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1120/1251]	eta 0:04:48 lr 0.000170	time 1.8094 (2.2009)	loss 3.0973 (3.2317)	grad_norm 2.0052 (2.2047)	
[2022-01-24 17:52:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1130/1251]	eta 0:04:26 lr 0.000170	time 2.0129 (2.2001)	loss 3.5519 (3.2315)	grad_norm 2.0253 (2.2052)	
[2022-01-24 17:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1140/1251]	eta 0:04:04 lr 0.000170	time 1.9374 (2.2002)	loss 3.3209 (3.2323)	grad_norm 2.4959 (2.2056)	
[2022-01-24 17:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1150/1251]	eta 0:03:42 lr 0.000170	time 2.1950 (2.2006)	loss 2.5331 (3.2321)	grad_norm 2.1206 (2.2052)	
[2022-01-24 17:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1160/1251]	eta 0:03:20 lr 0.000170	time 2.2036 (2.2005)	loss 4.0414 (3.2337)	grad_norm 2.3828 (2.2049)	
[2022-01-24 17:53:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1170/1251]	eta 0:02:58 lr 0.000170	time 2.5687 (2.2012)	loss 3.0613 (3.2333)	grad_norm 2.0944 (2.2054)	
[2022-01-24 17:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1180/1251]	eta 0:02:36 lr 0.000170	time 1.8229 (2.2003)	loss 3.5631 (3.2343)	grad_norm 2.1110 (2.2052)	
[2022-01-24 17:54:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1190/1251]	eta 0:02:14 lr 0.000170	time 1.6246 (2.1984)	loss 3.5797 (3.2336)	grad_norm 1.9337 (2.2040)	
[2022-01-24 17:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1200/1251]	eta 0:01:52 lr 0.000170	time 2.2580 (2.1978)	loss 3.7878 (3.2343)	grad_norm 2.1734 (2.2038)	
[2022-01-24 17:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1210/1251]	eta 0:01:30 lr 0.000170	time 1.7411 (2.1971)	loss 3.2028 (3.2332)	grad_norm 2.0150 (2.2026)	
[2022-01-24 17:55:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1220/1251]	eta 0:01:08 lr 0.000170	time 2.0950 (2.1981)	loss 3.7416 (3.2335)	grad_norm 2.1368 (2.2017)	
[2022-01-24 17:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1230/1251]	eta 0:00:46 lr 0.000170	time 2.2231 (2.1982)	loss 3.4977 (3.2339)	grad_norm 2.1283 (2.2016)	
[2022-01-24 17:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1240/1251]	eta 0:00:24 lr 0.000170	time 1.5583 (2.1972)	loss 3.7258 (3.2364)	grad_norm 2.5200 (2.2058)	
[2022-01-24 17:56:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [220/300][1250/1251]	eta 0:00:02 lr 0.000170	time 1.3029 (2.1930)	loss 3.7074 (3.2368)	grad_norm 2.1697 (2.2058)	
[2022-01-24 17:56:20 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 220 training takes 0:45:43
[2022-01-24 17:56:20 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_220 saving......
[2022-01-24 17:56:32 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_220 saved !!!
[2022-01-24 17:56:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 15.981 (15.981)	Loss 0.9069 (0.9069)	Acc@1 79.004 (79.004)	Acc@5 94.824 (94.824)	
[2022-01-24 17:57:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.007 (2.777)	Loss 0.7858 (0.8978)	Acc@1 81.152 (79.102)	Acc@5 95.703 (94.407)	
[2022-01-24 17:57:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.683 (2.157)	Loss 0.9166 (0.8902)	Acc@1 78.516 (79.069)	Acc@5 94.727 (94.568)	
[2022-01-24 17:57:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.293 (2.118)	Loss 0.8327 (0.8859)	Acc@1 79.883 (79.124)	Acc@5 95.410 (94.689)	
[2022-01-24 17:57:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 0.782 (2.001)	Loss 0.9387 (0.8872)	Acc@1 77.832 (79.087)	Acc@5 94.922 (94.708)	
[2022-01-24 17:58:02 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.050 Acc@5 94.690
[2022-01-24 17:58:02 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.1%
[2022-01-24 17:58:02 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.33%
[2022-01-24 17:58:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][0/1251]	eta 6:40:44 lr 0.000170	time 19.2203 (19.2203)	loss 2.5398 (2.5398)	grad_norm 1.9492 (1.9492)	
[2022-01-24 17:58:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][10/1251]	eta 1:20:57 lr 0.000170	time 3.0608 (3.9139)	loss 3.7172 (3.2383)	grad_norm 2.5091 (2.2931)	
[2022-01-24 17:59:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][20/1251]	eta 1:02:57 lr 0.000170	time 1.5685 (3.0688)	loss 2.2388 (3.2672)	grad_norm 2.3940 (2.2887)	
[2022-01-24 17:59:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][30/1251]	eta 0:56:51 lr 0.000170	time 1.8213 (2.7938)	loss 2.8686 (3.2587)	grad_norm 2.3339 (2.2711)	
[2022-01-24 17:59:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][40/1251]	eta 0:53:33 lr 0.000170	time 2.7647 (2.6540)	loss 3.2541 (3.3176)	grad_norm 1.9733 (2.2514)	
[2022-01-24 18:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][50/1251]	eta 0:52:31 lr 0.000170	time 2.0072 (2.6242)	loss 2.8615 (3.3229)	grad_norm 1.9430 (2.2190)	
[2022-01-24 18:00:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][60/1251]	eta 0:50:40 lr 0.000170	time 1.8574 (2.5529)	loss 3.2293 (3.3079)	grad_norm 2.4655 (2.2110)	
[2022-01-24 18:00:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][70/1251]	eta 0:49:00 lr 0.000170	time 2.2119 (2.4899)	loss 3.2919 (3.2687)	grad_norm 2.1133 (2.2091)	
[2022-01-24 18:01:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][80/1251]	eta 0:47:43 lr 0.000170	time 2.3013 (2.4457)	loss 3.8670 (3.2832)	grad_norm 2.0821 (2.2204)	
[2022-01-24 18:01:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][90/1251]	eta 0:46:53 lr 0.000170	time 1.8262 (2.4235)	loss 3.0910 (3.2566)	grad_norm 2.5757 (2.2215)	
[2022-01-24 18:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][100/1251]	eta 0:46:43 lr 0.000170	time 2.4665 (2.4355)	loss 2.0437 (3.2186)	grad_norm 2.3165 (2.2205)	
[2022-01-24 18:02:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][110/1251]	eta 0:45:53 lr 0.000170	time 2.1184 (2.4135)	loss 3.2755 (3.2205)	grad_norm 2.1895 (2.2258)	
[2022-01-24 18:02:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][120/1251]	eta 0:44:54 lr 0.000170	time 1.6281 (2.3825)	loss 2.5885 (3.2165)	grad_norm 2.4936 (2.2384)	
[2022-01-24 18:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][130/1251]	eta 0:44:02 lr 0.000170	time 2.1866 (2.3575)	loss 3.6036 (3.2110)	grad_norm 2.4755 (2.2324)	
[2022-01-24 18:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][140/1251]	eta 0:43:23 lr 0.000170	time 2.4186 (2.3434)	loss 3.3821 (3.2159)	grad_norm 1.9742 (2.2143)	
[2022-01-24 18:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][150/1251]	eta 0:42:57 lr 0.000169	time 2.2366 (2.3410)	loss 3.1703 (3.2082)	grad_norm 2.1049 (2.2156)	
[2022-01-24 18:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][160/1251]	eta 0:42:24 lr 0.000169	time 2.2023 (2.3322)	loss 3.6713 (3.2290)	grad_norm 2.4035 (2.2135)	
[2022-01-24 18:04:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][170/1251]	eta 0:41:43 lr 0.000169	time 2.4134 (2.3161)	loss 3.2239 (3.2224)	grad_norm 2.1248 (2.2127)	
[2022-01-24 18:05:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][180/1251]	eta 0:41:18 lr 0.000169	time 1.8179 (2.3145)	loss 2.1172 (3.2144)	grad_norm 2.0899 (2.2032)	
[2022-01-24 18:05:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][190/1251]	eta 0:40:52 lr 0.000169	time 1.8399 (2.3119)	loss 3.2326 (3.2126)	grad_norm 2.1542 (2.1986)	
[2022-01-24 18:05:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][200/1251]	eta 0:40:21 lr 0.000169	time 1.8486 (2.3037)	loss 2.8907 (3.2256)	grad_norm 2.9340 (2.2025)	
[2022-01-24 18:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][210/1251]	eta 0:39:48 lr 0.000169	time 2.3779 (2.2944)	loss 3.8883 (3.2293)	grad_norm 2.1711 (2.2035)	
[2022-01-24 18:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][220/1251]	eta 0:39:14 lr 0.000169	time 2.0085 (2.2834)	loss 2.0378 (3.2154)	grad_norm 2.5911 (2.2103)	
[2022-01-24 18:06:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][230/1251]	eta 0:38:48 lr 0.000169	time 1.9637 (2.2807)	loss 3.2767 (3.2207)	grad_norm 2.3368 (2.2122)	
[2022-01-24 18:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][240/1251]	eta 0:38:18 lr 0.000169	time 2.0642 (2.2734)	loss 2.9463 (3.2270)	grad_norm 2.3373 (2.2154)	
[2022-01-24 18:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][250/1251]	eta 0:37:54 lr 0.000169	time 2.4521 (2.2725)	loss 3.6825 (3.2320)	grad_norm 1.9389 (2.2123)	
[2022-01-24 18:07:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][260/1251]	eta 0:37:29 lr 0.000169	time 1.9473 (2.2696)	loss 3.4680 (3.2397)	grad_norm 1.9371 (2.2170)	
[2022-01-24 18:08:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][270/1251]	eta 0:37:04 lr 0.000169	time 2.1544 (2.2674)	loss 3.6146 (3.2483)	grad_norm 2.3014 (2.2186)	
[2022-01-24 18:08:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][280/1251]	eta 0:36:38 lr 0.000169	time 1.8657 (2.2642)	loss 2.3189 (3.2412)	grad_norm 1.8368 (2.2192)	
[2022-01-24 18:09:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][290/1251]	eta 0:36:13 lr 0.000169	time 2.3871 (2.2621)	loss 3.3848 (3.2308)	grad_norm 2.3995 (2.2242)	
[2022-01-24 18:09:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][300/1251]	eta 0:35:47 lr 0.000169	time 1.9479 (2.2584)	loss 3.6108 (3.2285)	grad_norm 1.9685 (2.2251)	
[2022-01-24 18:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][310/1251]	eta 0:35:22 lr 0.000169	time 2.8258 (2.2559)	loss 3.3679 (3.2221)	grad_norm 2.0650 (2.2230)	
[2022-01-24 18:10:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][320/1251]	eta 0:34:53 lr 0.000169	time 1.7472 (2.2491)	loss 3.4812 (3.2264)	grad_norm 2.3429 (2.2199)	
[2022-01-24 18:10:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][330/1251]	eta 0:34:28 lr 0.000169	time 2.0418 (2.2455)	loss 3.3021 (3.2236)	grad_norm 2.3037 (2.2194)	
[2022-01-24 18:10:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][340/1251]	eta 0:34:02 lr 0.000169	time 2.4837 (2.2425)	loss 3.2772 (3.2273)	grad_norm 2.0877 (2.2171)	
[2022-01-24 18:11:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][350/1251]	eta 0:33:44 lr 0.000169	time 3.8002 (2.2468)	loss 2.8564 (3.2236)	grad_norm 5.5822 (2.2294)	
[2022-01-24 18:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][360/1251]	eta 0:33:20 lr 0.000169	time 1.6038 (2.2455)	loss 2.3111 (3.2220)	grad_norm 2.0824 (2.2282)	
[2022-01-24 18:11:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][370/1251]	eta 0:33:03 lr 0.000169	time 3.2571 (2.2510)	loss 2.9963 (3.2181)	grad_norm 1.9551 (2.2259)	
[2022-01-24 18:12:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][380/1251]	eta 0:32:37 lr 0.000169	time 1.7973 (2.2476)	loss 4.1475 (3.2206)	grad_norm 2.0325 (2.2276)	
[2022-01-24 18:12:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][390/1251]	eta 0:32:11 lr 0.000169	time 2.2338 (2.2433)	loss 3.6897 (3.2176)	grad_norm 2.3201 (2.2302)	
[2022-01-24 18:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][400/1251]	eta 0:31:43 lr 0.000169	time 1.8544 (2.2362)	loss 3.8254 (3.2251)	grad_norm 2.3959 (2.2320)	
[2022-01-24 18:13:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][410/1251]	eta 0:31:15 lr 0.000169	time 1.9497 (2.2301)	loss 3.8469 (3.2224)	grad_norm 2.0921 (2.2358)	
[2022-01-24 18:13:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][420/1251]	eta 0:30:48 lr 0.000169	time 1.9437 (2.2245)	loss 3.6177 (3.2195)	grad_norm 1.8350 (2.2331)	
[2022-01-24 18:13:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][430/1251]	eta 0:30:22 lr 0.000169	time 1.9637 (2.2198)	loss 3.9583 (3.2153)	grad_norm 2.2728 (2.2315)	
[2022-01-24 18:14:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][440/1251]	eta 0:30:01 lr 0.000169	time 2.0039 (2.2212)	loss 3.2573 (3.2106)	grad_norm 2.1520 (2.2278)	
[2022-01-24 18:14:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][450/1251]	eta 0:29:39 lr 0.000169	time 2.4706 (2.2221)	loss 2.8609 (3.2126)	grad_norm 1.9484 (2.2247)	
[2022-01-24 18:15:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][460/1251]	eta 0:29:18 lr 0.000169	time 2.6928 (2.2237)	loss 3.4083 (3.2183)	grad_norm 2.4431 (2.2239)	
[2022-01-24 18:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][470/1251]	eta 0:29:01 lr 0.000169	time 2.9383 (2.2302)	loss 3.2054 (3.2167)	grad_norm 2.3386 (2.2227)	
[2022-01-24 18:15:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][480/1251]	eta 0:28:45 lr 0.000168	time 2.7787 (2.2384)	loss 3.5110 (3.2150)	grad_norm 2.4129 (2.2244)	
[2022-01-24 18:16:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][490/1251]	eta 0:28:24 lr 0.000168	time 2.3707 (2.2402)	loss 3.3183 (3.2189)	grad_norm 2.1821 (2.2241)	
[2022-01-24 18:16:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][500/1251]	eta 0:28:00 lr 0.000168	time 2.2401 (2.2373)	loss 3.6078 (3.2164)	grad_norm 2.8812 (2.2262)	
[2022-01-24 18:17:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][510/1251]	eta 0:27:32 lr 0.000168	time 1.7604 (2.2301)	loss 2.3422 (3.2181)	grad_norm 2.1330 (2.2254)	
[2022-01-24 18:17:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][520/1251]	eta 0:27:04 lr 0.000168	time 1.7220 (2.2230)	loss 2.4907 (3.2187)	grad_norm 2.3272 (2.2261)	
[2022-01-24 18:17:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][530/1251]	eta 0:26:39 lr 0.000168	time 2.0871 (2.2191)	loss 3.6856 (3.2226)	grad_norm 1.9234 (2.2256)	
[2022-01-24 18:18:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][540/1251]	eta 0:26:15 lr 0.000168	time 1.9714 (2.2164)	loss 3.5513 (3.2236)	grad_norm 2.0308 (2.2265)	
[2022-01-24 18:18:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][550/1251]	eta 0:25:54 lr 0.000168	time 1.5757 (2.2180)	loss 3.2656 (3.2243)	grad_norm 2.2492 (2.2250)	
[2022-01-24 18:18:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][560/1251]	eta 0:25:32 lr 0.000168	time 1.8529 (2.2185)	loss 2.2212 (3.2261)	grad_norm 2.7193 (2.2291)	
[2022-01-24 18:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][570/1251]	eta 0:25:14 lr 0.000168	time 2.8477 (2.2238)	loss 3.5832 (3.2310)	grad_norm 2.3800 (2.2297)	
[2022-01-24 18:19:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][580/1251]	eta 0:24:54 lr 0.000168	time 2.0814 (2.2267)	loss 3.8977 (3.2282)	grad_norm 2.3064 (2.2300)	
[2022-01-24 18:20:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][590/1251]	eta 0:24:34 lr 0.000168	time 2.0802 (2.2312)	loss 4.0719 (3.2286)	grad_norm 2.1122 (2.2307)	
[2022-01-24 18:20:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][600/1251]	eta 0:24:12 lr 0.000168	time 1.7042 (2.2307)	loss 3.4641 (3.2288)	grad_norm 2.2695 (2.2310)	
[2022-01-24 18:20:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][610/1251]	eta 0:23:47 lr 0.000168	time 2.2718 (2.2274)	loss 3.0031 (3.2281)	grad_norm 2.1958 (2.2307)	
[2022-01-24 18:21:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][620/1251]	eta 0:23:22 lr 0.000168	time 2.0480 (2.2226)	loss 2.4109 (3.2286)	grad_norm 2.3488 (2.2294)	
[2022-01-24 18:21:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][630/1251]	eta 0:22:59 lr 0.000168	time 2.2111 (2.2206)	loss 3.1111 (3.2290)	grad_norm 2.5419 (2.2305)	
[2022-01-24 18:21:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][640/1251]	eta 0:22:35 lr 0.000168	time 2.6025 (2.2182)	loss 2.6803 (3.2326)	grad_norm 1.8515 (2.2280)	
[2022-01-24 18:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][650/1251]	eta 0:22:13 lr 0.000168	time 2.2561 (2.2186)	loss 3.4881 (3.2337)	grad_norm 2.3941 (2.2289)	
[2022-01-24 18:22:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][660/1251]	eta 0:21:51 lr 0.000168	time 2.7161 (2.2191)	loss 3.9186 (3.2390)	grad_norm 2.1141 (2.2271)	
[2022-01-24 18:22:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][670/1251]	eta 0:21:29 lr 0.000168	time 1.5152 (2.2188)	loss 2.7294 (3.2348)	grad_norm 2.3326 (2.2265)	
[2022-01-24 18:23:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][680/1251]	eta 0:21:05 lr 0.000168	time 2.0153 (2.2170)	loss 3.6329 (3.2345)	grad_norm 1.9283 (2.2252)	
[2022-01-24 18:23:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][690/1251]	eta 0:20:44 lr 0.000168	time 1.9063 (2.2180)	loss 4.1636 (3.2358)	grad_norm 1.9809 (2.2230)	
[2022-01-24 18:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][700/1251]	eta 0:20:22 lr 0.000168	time 2.6558 (2.2184)	loss 3.7308 (3.2378)	grad_norm 2.1078 (2.2208)	
[2022-01-24 18:24:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][710/1251]	eta 0:20:00 lr 0.000168	time 1.5153 (2.2188)	loss 3.7104 (3.2380)	grad_norm 2.2607 (2.2197)	
[2022-01-24 18:24:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][720/1251]	eta 0:19:37 lr 0.000168	time 1.9161 (2.2170)	loss 3.5150 (3.2367)	grad_norm 2.2399 (2.2190)	
[2022-01-24 18:25:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][730/1251]	eta 0:19:15 lr 0.000168	time 2.0879 (2.2180)	loss 3.4557 (3.2393)	grad_norm 2.7489 (2.2200)	
[2022-01-24 18:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][740/1251]	eta 0:18:53 lr 0.000168	time 2.8115 (2.2186)	loss 2.6350 (3.2398)	grad_norm 2.3039 (2.2197)	
[2022-01-24 18:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][750/1251]	eta 0:18:31 lr 0.000168	time 1.7812 (2.2183)	loss 3.5939 (3.2365)	grad_norm 2.3207 (2.2202)	
[2022-01-24 18:26:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][760/1251]	eta 0:18:08 lr 0.000168	time 1.8632 (2.2170)	loss 2.3897 (3.2342)	grad_norm 2.1247 (2.2207)	
[2022-01-24 18:26:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][770/1251]	eta 0:17:46 lr 0.000168	time 1.6023 (2.2168)	loss 3.3352 (3.2323)	grad_norm 2.0814 (2.2186)	
[2022-01-24 18:26:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][780/1251]	eta 0:17:23 lr 0.000168	time 2.7940 (2.2157)	loss 3.3768 (3.2325)	grad_norm 2.3581 (2.2185)	
[2022-01-24 18:27:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][790/1251]	eta 0:17:01 lr 0.000168	time 3.3999 (2.2156)	loss 3.2449 (3.2333)	grad_norm 2.2053 (2.2169)	
[2022-01-24 18:27:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][800/1251]	eta 0:16:40 lr 0.000168	time 2.8254 (2.2175)	loss 3.3974 (3.2324)	grad_norm 2.2493 (2.2159)	
[2022-01-24 18:28:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][810/1251]	eta 0:16:17 lr 0.000167	time 1.7426 (2.2170)	loss 3.4246 (3.2292)	grad_norm 2.0656 (2.2154)	
[2022-01-24 18:28:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][820/1251]	eta 0:15:55 lr 0.000167	time 2.4676 (2.2180)	loss 2.2931 (3.2279)	grad_norm 2.2708 (2.2155)	
[2022-01-24 18:28:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][830/1251]	eta 0:15:33 lr 0.000167	time 2.3207 (2.2184)	loss 2.9176 (3.2255)	grad_norm 2.3298 (2.2149)	
[2022-01-24 18:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][840/1251]	eta 0:15:11 lr 0.000167	time 2.1446 (2.2176)	loss 3.2403 (3.2234)	grad_norm 1.8744 (2.2144)	
[2022-01-24 18:29:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][850/1251]	eta 0:14:47 lr 0.000167	time 1.9319 (2.2137)	loss 2.9664 (3.2207)	grad_norm 2.0670 (2.2134)	
[2022-01-24 18:29:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][860/1251]	eta 0:14:24 lr 0.000167	time 2.4117 (2.2116)	loss 3.6763 (3.2224)	grad_norm 2.2933 (2.2147)	
[2022-01-24 18:30:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][870/1251]	eta 0:14:03 lr 0.000167	time 2.7252 (2.2138)	loss 2.9773 (3.2216)	grad_norm 2.1407 (2.2139)	
[2022-01-24 18:30:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][880/1251]	eta 0:13:41 lr 0.000167	time 2.2837 (2.2151)	loss 3.8851 (3.2241)	grad_norm 2.1675 (2.2150)	
[2022-01-24 18:30:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][890/1251]	eta 0:13:20 lr 0.000167	time 1.8205 (2.2180)	loss 2.3935 (3.2218)	grad_norm 2.4429 (2.2149)	
[2022-01-24 18:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][900/1251]	eta 0:12:58 lr 0.000167	time 1.9092 (2.2170)	loss 3.1808 (3.2209)	grad_norm 2.0701 (2.2142)	
[2022-01-24 18:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][910/1251]	eta 0:12:35 lr 0.000167	time 2.8219 (2.2165)	loss 3.4026 (3.2199)	grad_norm 1.9471 (2.2140)	
[2022-01-24 18:32:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][920/1251]	eta 0:12:12 lr 0.000167	time 1.9095 (2.2137)	loss 2.9538 (3.2196)	grad_norm 1.9184 (2.2129)	
[2022-01-24 18:32:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][930/1251]	eta 0:11:49 lr 0.000167	time 2.2591 (2.2108)	loss 3.8843 (3.2213)	grad_norm 2.2859 (2.2115)	
[2022-01-24 18:32:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][940/1251]	eta 0:11:27 lr 0.000167	time 2.1256 (2.2101)	loss 3.3145 (3.2197)	grad_norm 2.5821 (2.2126)	
[2022-01-24 18:33:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][950/1251]	eta 0:11:05 lr 0.000167	time 2.5611 (2.2097)	loss 3.2994 (3.2204)	grad_norm 2.2178 (2.2128)	
[2022-01-24 18:33:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][960/1251]	eta 0:10:42 lr 0.000167	time 2.4276 (2.2088)	loss 2.4377 (3.2199)	grad_norm 2.2120 (2.2134)	
[2022-01-24 18:33:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][970/1251]	eta 0:10:21 lr 0.000167	time 2.3217 (2.2111)	loss 2.1465 (3.2222)	grad_norm 2.1792 (2.2141)	
[2022-01-24 18:34:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][980/1251]	eta 0:09:59 lr 0.000167	time 1.7307 (2.2112)	loss 3.2840 (3.2216)	grad_norm 2.1662 (2.2141)	
[2022-01-24 18:34:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][990/1251]	eta 0:09:37 lr 0.000167	time 2.4388 (2.2124)	loss 3.9233 (3.2208)	grad_norm 2.1375 (2.2145)	
[2022-01-24 18:34:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1000/1251]	eta 0:09:15 lr 0.000167	time 1.9337 (2.2136)	loss 3.6398 (3.2236)	grad_norm 2.2133 (2.2137)	
[2022-01-24 18:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1010/1251]	eta 0:08:53 lr 0.000167	time 2.5404 (2.2142)	loss 3.8525 (3.2246)	grad_norm 2.4059 (2.2131)	
[2022-01-24 18:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1020/1251]	eta 0:08:31 lr 0.000167	time 1.7478 (2.2136)	loss 3.2584 (3.2225)	grad_norm 1.9780 (2.2112)	
[2022-01-24 18:36:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1030/1251]	eta 0:08:08 lr 0.000167	time 1.6782 (2.2118)	loss 3.5140 (3.2232)	grad_norm 2.0622 (2.2096)	
[2022-01-24 18:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1040/1251]	eta 0:07:46 lr 0.000167	time 2.0106 (2.2103)	loss 2.1992 (3.2212)	grad_norm 2.8417 (2.2102)	
[2022-01-24 18:36:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1050/1251]	eta 0:07:24 lr 0.000167	time 2.1869 (2.2099)	loss 3.0736 (3.2219)	grad_norm 1.9383 (2.2093)	
[2022-01-24 18:37:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1060/1251]	eta 0:07:02 lr 0.000167	time 2.5619 (2.2109)	loss 3.4413 (3.2214)	grad_norm 2.3847 (2.2092)	
[2022-01-24 18:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1070/1251]	eta 0:06:40 lr 0.000167	time 1.9108 (2.2123)	loss 3.1271 (3.2230)	grad_norm 1.8214 (2.2072)	
[2022-01-24 18:37:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1080/1251]	eta 0:06:18 lr 0.000167	time 1.9349 (2.2113)	loss 3.5124 (3.2239)	grad_norm 2.5147 (2.2074)	
[2022-01-24 18:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1090/1251]	eta 0:05:55 lr 0.000167	time 2.2046 (2.2107)	loss 1.8793 (3.2205)	grad_norm 2.2500 (2.2062)	
[2022-01-24 18:38:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1100/1251]	eta 0:05:33 lr 0.000167	time 2.0980 (2.2091)	loss 2.1297 (3.2219)	grad_norm 2.0062 (2.2065)	
[2022-01-24 18:38:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1110/1251]	eta 0:05:11 lr 0.000167	time 2.1904 (2.2084)	loss 3.3932 (3.2218)	grad_norm 2.2319 (2.2062)	
[2022-01-24 18:39:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1120/1251]	eta 0:04:49 lr 0.000167	time 2.2561 (2.2074)	loss 3.4140 (3.2221)	grad_norm 2.4099 (2.2062)	
[2022-01-24 18:39:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1130/1251]	eta 0:04:26 lr 0.000167	time 2.2316 (2.2065)	loss 3.6136 (3.2229)	grad_norm 2.2333 (2.2053)	
[2022-01-24 18:40:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1140/1251]	eta 0:04:05 lr 0.000166	time 2.6007 (2.2083)	loss 3.2605 (3.2223)	grad_norm 2.1666 (2.2038)	
[2022-01-24 18:40:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1150/1251]	eta 0:03:42 lr 0.000166	time 1.7838 (2.2074)	loss 2.6596 (3.2208)	grad_norm 2.0418 (2.2037)	
[2022-01-24 18:40:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1160/1251]	eta 0:03:20 lr 0.000166	time 2.3101 (2.2066)	loss 2.4874 (3.2201)	grad_norm 2.0597 (2.2055)	
[2022-01-24 18:41:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1170/1251]	eta 0:02:58 lr 0.000166	time 2.4335 (2.2075)	loss 3.0600 (3.2195)	grad_norm 2.1474 (2.2059)	
[2022-01-24 18:41:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1180/1251]	eta 0:02:36 lr 0.000166	time 1.8473 (2.2088)	loss 2.3633 (3.2174)	grad_norm 2.4792 (2.2070)	
[2022-01-24 18:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1190/1251]	eta 0:02:14 lr 0.000166	time 1.8671 (2.2084)	loss 2.3080 (3.2174)	grad_norm 1.9939 (2.2065)	
[2022-01-24 18:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1200/1251]	eta 0:01:52 lr 0.000166	time 2.0298 (2.2076)	loss 3.6034 (3.2198)	grad_norm 2.2597 (2.2076)	
[2022-01-24 18:42:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1210/1251]	eta 0:01:30 lr 0.000166	time 1.7397 (2.2064)	loss 3.4144 (3.2192)	grad_norm 2.2616 (2.2074)	
[2022-01-24 18:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1220/1251]	eta 0:01:08 lr 0.000166	time 1.9201 (2.2070)	loss 3.5400 (3.2199)	grad_norm 2.1417 (2.2070)	
[2022-01-24 18:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1230/1251]	eta 0:00:46 lr 0.000166	time 2.6132 (2.2076)	loss 3.4725 (3.2195)	grad_norm 2.1633 (2.2064)	
[2022-01-24 18:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1240/1251]	eta 0:00:24 lr 0.000166	time 1.2340 (2.2062)	loss 2.3274 (3.2203)	grad_norm 2.2245 (2.2071)	
[2022-01-24 18:43:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [221/300][1250/1251]	eta 0:00:02 lr 0.000166	time 1.1905 (2.2007)	loss 3.0767 (3.2193)	grad_norm 2.8741 (2.2113)	
[2022-01-24 18:43:55 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 221 training takes 0:45:53
[2022-01-24 18:44:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.262 (19.262)	Loss 0.8242 (0.8242)	Acc@1 80.176 (80.176)	Acc@5 95.703 (95.703)	
[2022-01-24 18:44:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.591 (3.273)	Loss 0.8716 (0.8839)	Acc@1 80.664 (79.093)	Acc@5 94.824 (94.957)	
[2022-01-24 18:44:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.613 (2.519)	Loss 0.9105 (0.8733)	Acc@1 78.809 (79.422)	Acc@5 94.922 (94.978)	
[2022-01-24 18:45:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.828 (2.226)	Loss 0.8731 (0.8732)	Acc@1 78.711 (79.407)	Acc@5 95.312 (94.938)	
[2022-01-24 18:45:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.302 (2.189)	Loss 0.8513 (0.8733)	Acc@1 79.785 (79.335)	Acc@5 94.629 (94.970)	
[2022-01-24 18:45:32 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.304 Acc@5 94.920
[2022-01-24 18:45:32 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.3%
[2022-01-24 18:45:32 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.33%
[2022-01-24 18:45:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][0/1251]	eta 8:19:26 lr 0.000166	time 23.9539 (23.9539)	loss 3.6238 (3.6238)	grad_norm 2.3955 (2.3955)	
[2022-01-24 18:46:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][10/1251]	eta 1:30:21 lr 0.000166	time 1.7124 (4.3684)	loss 3.5957 (3.4349)	grad_norm 2.4772 (2.2588)	
[2022-01-24 18:46:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][20/1251]	eta 1:06:44 lr 0.000166	time 1.2296 (3.2527)	loss 2.2585 (3.2970)	grad_norm 1.9385 (2.2235)	
[2022-01-24 18:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][30/1251]	eta 0:59:23 lr 0.000166	time 1.5748 (2.9184)	loss 3.1311 (3.3300)	grad_norm 2.1703 (2.2117)	
[2022-01-24 18:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][40/1251]	eta 0:56:06 lr 0.000166	time 4.2852 (2.7800)	loss 2.5619 (3.3113)	grad_norm 2.2025 (2.1799)	
[2022-01-24 18:47:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][50/1251]	eta 0:54:36 lr 0.000166	time 2.4501 (2.7278)	loss 3.2028 (3.2623)	grad_norm 2.0660 (2.1837)	
[2022-01-24 18:48:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][60/1251]	eta 0:52:07 lr 0.000166	time 1.8927 (2.6260)	loss 3.3196 (3.1965)	grad_norm 2.0957 (2.1918)	
[2022-01-24 18:48:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][70/1251]	eta 0:50:23 lr 0.000166	time 1.7557 (2.5604)	loss 2.8250 (3.2034)	grad_norm 2.4407 (2.1952)	
[2022-01-24 18:48:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][80/1251]	eta 0:49:29 lr 0.000166	time 3.4650 (2.5358)	loss 3.6282 (3.2295)	grad_norm 2.1132 (2.2216)	
[2022-01-24 18:49:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][90/1251]	eta 0:48:32 lr 0.000166	time 2.1676 (2.5082)	loss 2.5158 (3.1780)	grad_norm 2.1838 (2.2353)	
[2022-01-24 18:49:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][100/1251]	eta 0:47:22 lr 0.000166	time 1.8843 (2.4695)	loss 3.5723 (3.1421)	grad_norm 2.1857 (2.2346)	
[2022-01-24 18:50:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][110/1251]	eta 0:46:14 lr 0.000166	time 1.8322 (2.4319)	loss 3.3750 (3.1321)	grad_norm 2.0212 (2.2210)	
[2022-01-24 18:50:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][120/1251]	eta 0:45:16 lr 0.000166	time 1.6055 (2.4018)	loss 2.8998 (3.1335)	grad_norm 2.2058 (2.2174)	
[2022-01-24 18:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][130/1251]	eta 0:44:21 lr 0.000166	time 1.8283 (2.3743)	loss 3.6970 (3.1464)	grad_norm 2.2131 (2.2127)	
[2022-01-24 18:51:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][140/1251]	eta 0:43:42 lr 0.000166	time 1.8774 (2.3601)	loss 3.3792 (3.1468)	grad_norm 2.3250 (2.2138)	
[2022-01-24 18:51:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][150/1251]	eta 0:43:12 lr 0.000166	time 3.2037 (2.3549)	loss 3.5245 (3.1429)	grad_norm 1.7711 (2.2103)	
[2022-01-24 18:51:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][160/1251]	eta 0:42:40 lr 0.000166	time 2.8029 (2.3472)	loss 3.2875 (3.1470)	grad_norm 2.1662 (2.2150)	
[2022-01-24 18:52:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][170/1251]	eta 0:42:14 lr 0.000166	time 2.1688 (2.3443)	loss 3.6438 (3.1541)	grad_norm 2.4467 (2.2127)	
[2022-01-24 18:52:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][180/1251]	eta 0:41:41 lr 0.000166	time 1.5788 (2.3361)	loss 3.2620 (3.1495)	grad_norm 2.0934 (2.2089)	
[2022-01-24 18:52:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][190/1251]	eta 0:41:09 lr 0.000166	time 2.7631 (2.3276)	loss 3.9083 (3.1492)	grad_norm 2.3142 (2.2070)	
[2022-01-24 18:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][200/1251]	eta 0:40:40 lr 0.000166	time 2.5224 (2.3217)	loss 3.7335 (3.1532)	grad_norm 1.9250 (2.2078)	
[2022-01-24 18:53:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][210/1251]	eta 0:40:13 lr 0.000166	time 2.8825 (2.3180)	loss 3.7484 (3.1705)	grad_norm 2.0363 (2.2111)	
[2022-01-24 18:54:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][220/1251]	eta 0:39:40 lr 0.000165	time 1.6525 (2.3087)	loss 2.9312 (3.1713)	grad_norm 2.4704 (2.2171)	
[2022-01-24 18:54:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][230/1251]	eta 0:39:11 lr 0.000165	time 2.4879 (2.3033)	loss 3.7551 (3.1652)	grad_norm 2.3783 (2.2210)	
[2022-01-24 18:54:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][240/1251]	eta 0:38:42 lr 0.000165	time 2.1981 (2.2975)	loss 3.7211 (3.1644)	grad_norm 2.2337 (2.2202)	
[2022-01-24 18:55:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][250/1251]	eta 0:38:04 lr 0.000165	time 1.9508 (2.2818)	loss 3.5084 (3.1745)	grad_norm 2.1059 (2.2181)	
[2022-01-24 18:55:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][260/1251]	eta 0:37:31 lr 0.000165	time 1.6277 (2.2721)	loss 2.8228 (3.1726)	grad_norm 2.2611 (2.2179)	
[2022-01-24 18:55:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][270/1251]	eta 0:37:05 lr 0.000165	time 1.8813 (2.2687)	loss 3.3849 (3.1778)	grad_norm 1.8847 (2.2180)	
[2022-01-24 18:56:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][280/1251]	eta 0:36:39 lr 0.000165	time 2.4526 (2.2647)	loss 2.9537 (3.1820)	grad_norm 2.0780 (2.2165)	
[2022-01-24 18:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][290/1251]	eta 0:36:18 lr 0.000165	time 2.5135 (2.2671)	loss 2.8461 (3.1883)	grad_norm 2.0788 (2.2178)	
[2022-01-24 18:56:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][300/1251]	eta 0:36:01 lr 0.000165	time 2.0470 (2.2724)	loss 2.2724 (3.1783)	grad_norm 1.9479 (2.2148)	
[2022-01-24 18:57:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][310/1251]	eta 0:35:41 lr 0.000165	time 1.9613 (2.2754)	loss 3.4086 (3.1724)	grad_norm 2.5521 (2.2145)	
[2022-01-24 18:57:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][320/1251]	eta 0:35:16 lr 0.000165	time 2.1833 (2.2736)	loss 2.6556 (3.1681)	grad_norm 2.3353 (2.2139)	
[2022-01-24 18:58:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][330/1251]	eta 0:34:50 lr 0.000165	time 1.9188 (2.2701)	loss 3.8180 (3.1704)	grad_norm 2.1760 (2.2135)	
[2022-01-24 18:58:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][340/1251]	eta 0:34:19 lr 0.000165	time 1.6094 (2.2602)	loss 3.4297 (3.1713)	grad_norm 2.2409 (2.2123)	
[2022-01-24 18:58:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][350/1251]	eta 0:33:50 lr 0.000165	time 1.9017 (2.2536)	loss 2.8409 (3.1682)	grad_norm 2.4335 (2.2124)	
[2022-01-24 18:59:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][360/1251]	eta 0:33:25 lr 0.000165	time 2.4851 (2.2507)	loss 2.2631 (3.1698)	grad_norm 2.4446 (2.2131)	
[2022-01-24 18:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][370/1251]	eta 0:33:04 lr 0.000165	time 1.8999 (2.2524)	loss 3.7422 (3.1744)	grad_norm 2.3985 (2.2143)	
[2022-01-24 18:59:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][380/1251]	eta 0:32:42 lr 0.000165	time 2.1116 (2.2535)	loss 3.1632 (3.1668)	grad_norm 2.2835 (2.2136)	
[2022-01-24 19:00:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][390/1251]	eta 0:32:21 lr 0.000165	time 1.9839 (2.2545)	loss 2.8731 (3.1700)	grad_norm 2.1630 (2.2190)	
[2022-01-24 19:00:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][400/1251]	eta 0:32:00 lr 0.000165	time 2.0548 (2.2567)	loss 3.1191 (3.1728)	grad_norm 1.9147 (2.2181)	
[2022-01-24 19:00:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][410/1251]	eta 0:31:35 lr 0.000165	time 1.5954 (2.2543)	loss 2.4713 (3.1695)	grad_norm 2.0558 (2.2143)	
[2022-01-24 19:01:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][420/1251]	eta 0:31:09 lr 0.000165	time 1.5635 (2.2501)	loss 3.4561 (3.1734)	grad_norm 1.9476 (2.2196)	
[2022-01-24 19:01:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][430/1251]	eta 0:30:43 lr 0.000165	time 1.9171 (2.2452)	loss 3.8911 (3.1786)	grad_norm 2.2833 (2.2228)	
[2022-01-24 19:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][440/1251]	eta 0:30:19 lr 0.000165	time 2.5378 (2.2437)	loss 3.4378 (3.1758)	grad_norm 2.4436 (2.2230)	
[2022-01-24 19:02:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][450/1251]	eta 0:29:58 lr 0.000165	time 2.2201 (2.2449)	loss 2.6024 (3.1736)	grad_norm 2.4588 (2.2229)	
[2022-01-24 19:02:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][460/1251]	eta 0:29:33 lr 0.000165	time 2.1162 (2.2420)	loss 3.1859 (3.1758)	grad_norm 2.1710 (2.2211)	
[2022-01-24 19:03:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][470/1251]	eta 0:29:12 lr 0.000165	time 2.6376 (2.2439)	loss 2.3951 (3.1710)	grad_norm 2.1704 (2.2179)	
[2022-01-24 19:03:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][480/1251]	eta 0:28:48 lr 0.000165	time 2.1769 (2.2423)	loss 3.8891 (3.1761)	grad_norm 2.2039 (2.2204)	
[2022-01-24 19:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][490/1251]	eta 0:28:26 lr 0.000165	time 1.9792 (2.2426)	loss 3.2902 (3.1744)	grad_norm 2.2765 (2.2234)	
[2022-01-24 19:04:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][500/1251]	eta 0:28:01 lr 0.000165	time 1.6498 (2.2385)	loss 2.2349 (3.1694)	grad_norm 2.1947 (2.2259)	
[2022-01-24 19:04:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][510/1251]	eta 0:27:35 lr 0.000165	time 2.0920 (2.2336)	loss 3.5501 (3.1704)	grad_norm 2.5951 (2.2269)	
[2022-01-24 19:04:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][520/1251]	eta 0:27:09 lr 0.000165	time 1.6860 (2.2289)	loss 3.5005 (3.1697)	grad_norm 2.1156 (2.2266)	
[2022-01-24 19:05:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][530/1251]	eta 0:26:48 lr 0.000165	time 2.2301 (2.2306)	loss 3.6675 (3.1678)	grad_norm 2.1328 (2.2260)	
[2022-01-24 19:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][540/1251]	eta 0:26:25 lr 0.000165	time 2.4738 (2.2302)	loss 2.6450 (3.1669)	grad_norm 2.1472 (2.2267)	
[2022-01-24 19:06:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][550/1251]	eta 0:26:04 lr 0.000164	time 2.4750 (2.2316)	loss 2.6646 (3.1634)	grad_norm 2.5999 (2.2280)	
[2022-01-24 19:06:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][560/1251]	eta 0:25:42 lr 0.000164	time 2.7643 (2.2326)	loss 3.4214 (3.1709)	grad_norm 2.2776 (2.2268)	
[2022-01-24 19:06:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][570/1251]	eta 0:25:23 lr 0.000164	time 3.0885 (2.2367)	loss 3.4610 (3.1724)	grad_norm 2.5025 (2.2281)	
[2022-01-24 19:07:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][580/1251]	eta 0:25:00 lr 0.000164	time 1.7652 (2.2366)	loss 3.0018 (3.1731)	grad_norm 2.3989 (2.2328)	
[2022-01-24 19:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][590/1251]	eta 0:24:36 lr 0.000164	time 2.1466 (2.2343)	loss 2.3677 (3.1725)	grad_norm 3.5020 (2.2373)	
[2022-01-24 19:07:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][600/1251]	eta 0:24:11 lr 0.000164	time 1.9615 (2.2303)	loss 3.4729 (3.1739)	grad_norm 1.9948 (2.2379)	
[2022-01-24 19:08:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][610/1251]	eta 0:23:46 lr 0.000164	time 1.5758 (2.2261)	loss 3.3772 (3.1761)	grad_norm 2.3304 (2.2364)	
[2022-01-24 19:08:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][620/1251]	eta 0:23:23 lr 0.000164	time 1.7916 (2.2237)	loss 2.3557 (3.1739)	grad_norm 2.1885 (2.2349)	
[2022-01-24 19:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][630/1251]	eta 0:23:02 lr 0.000164	time 2.5439 (2.2259)	loss 3.2991 (3.1739)	grad_norm 2.3988 (2.2361)	
[2022-01-24 19:09:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][640/1251]	eta 0:22:40 lr 0.000164	time 2.4723 (2.2263)	loss 2.4200 (3.1728)	grad_norm 2.3484 (2.2364)	
[2022-01-24 19:09:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][650/1251]	eta 0:22:19 lr 0.000164	time 2.1734 (2.2293)	loss 3.4771 (3.1708)	grad_norm 1.9920 (2.2348)	
[2022-01-24 19:10:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][660/1251]	eta 0:21:58 lr 0.000164	time 2.2446 (2.2303)	loss 2.3724 (3.1695)	grad_norm 2.3936 (2.2337)	
[2022-01-24 19:10:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][670/1251]	eta 0:21:34 lr 0.000164	time 2.3256 (2.2288)	loss 3.4792 (3.1714)	grad_norm 2.0676 (2.2334)	
[2022-01-24 19:10:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][680/1251]	eta 0:21:10 lr 0.000164	time 2.1923 (2.2252)	loss 2.7251 (3.1712)	grad_norm 2.3890 (2.2335)	
[2022-01-24 19:11:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][690/1251]	eta 0:20:47 lr 0.000164	time 2.3076 (2.2232)	loss 3.8199 (3.1696)	grad_norm 2.3291 (2.2315)	
[2022-01-24 19:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][700/1251]	eta 0:20:23 lr 0.000164	time 1.7057 (2.2208)	loss 3.5562 (3.1692)	grad_norm 2.0278 (2.2310)	
[2022-01-24 19:11:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][710/1251]	eta 0:20:01 lr 0.000164	time 2.5222 (2.2216)	loss 1.9425 (3.1649)	grad_norm 2.3204 (2.2319)	
[2022-01-24 19:12:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][720/1251]	eta 0:19:39 lr 0.000164	time 2.7989 (2.2213)	loss 3.5169 (3.1664)	grad_norm 2.2789 (2.2309)	
[2022-01-24 19:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][730/1251]	eta 0:19:16 lr 0.000164	time 1.8621 (2.2206)	loss 3.5587 (3.1661)	grad_norm 2.1124 (2.2305)	
[2022-01-24 19:12:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][740/1251]	eta 0:18:54 lr 0.000164	time 2.2109 (2.2208)	loss 3.1033 (3.1650)	grad_norm 2.0044 (2.2296)	
[2022-01-24 19:13:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][750/1251]	eta 0:18:33 lr 0.000164	time 2.2995 (2.2221)	loss 3.2465 (3.1671)	grad_norm 2.2071 (2.2306)	
[2022-01-24 19:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][760/1251]	eta 0:18:11 lr 0.000164	time 1.6357 (2.2234)	loss 3.0293 (3.1687)	grad_norm 2.1936 (2.2321)	
[2022-01-24 19:14:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][770/1251]	eta 0:17:48 lr 0.000164	time 1.9036 (2.2218)	loss 3.5948 (3.1685)	grad_norm 2.0446 (2.2336)	
[2022-01-24 19:14:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][780/1251]	eta 0:17:24 lr 0.000164	time 1.5742 (2.2182)	loss 3.9362 (3.1701)	grad_norm 2.2009 (2.2332)	
[2022-01-24 19:14:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][790/1251]	eta 0:17:02 lr 0.000164	time 2.2780 (2.2181)	loss 3.1730 (3.1669)	grad_norm 1.9781 (2.2323)	
[2022-01-24 19:15:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][800/1251]	eta 0:16:41 lr 0.000164	time 2.4807 (2.2203)	loss 4.0408 (3.1684)	grad_norm 2.1317 (2.2312)	
[2022-01-24 19:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][810/1251]	eta 0:16:18 lr 0.000164	time 2.4697 (2.2198)	loss 2.4382 (3.1692)	grad_norm 2.0959 (2.2311)	
[2022-01-24 19:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][820/1251]	eta 0:15:56 lr 0.000164	time 1.8566 (2.2186)	loss 3.4880 (3.1722)	grad_norm 2.0961 (2.2304)	
[2022-01-24 19:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][830/1251]	eta 0:15:34 lr 0.000164	time 2.4372 (2.2188)	loss 3.6593 (3.1735)	grad_norm 2.0585 (2.2290)	
[2022-01-24 19:16:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][840/1251]	eta 0:15:12 lr 0.000164	time 1.6867 (2.2198)	loss 3.3305 (3.1734)	grad_norm 1.9252 (2.2272)	
[2022-01-24 19:17:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][850/1251]	eta 0:14:49 lr 0.000164	time 1.6574 (2.2182)	loss 3.0250 (3.1751)	grad_norm 2.1543 (2.2292)	
[2022-01-24 19:17:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][860/1251]	eta 0:14:27 lr 0.000164	time 2.1380 (2.2177)	loss 3.6867 (3.1778)	grad_norm 2.1956 (2.2308)	
[2022-01-24 19:17:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][870/1251]	eta 0:14:05 lr 0.000164	time 1.8958 (2.2187)	loss 3.2211 (3.1774)	grad_norm 2.1708 (2.2302)	
[2022-01-24 19:18:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][880/1251]	eta 0:13:43 lr 0.000164	time 2.0609 (2.2202)	loss 3.3474 (3.1776)	grad_norm 2.1206 (2.2305)	
[2022-01-24 19:18:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][890/1251]	eta 0:13:20 lr 0.000163	time 1.5256 (2.2175)	loss 3.5890 (3.1794)	grad_norm 2.4503 (2.2306)	
[2022-01-24 19:18:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][900/1251]	eta 0:12:58 lr 0.000163	time 1.7910 (2.2175)	loss 2.1399 (3.1792)	grad_norm 2.2278 (2.2315)	
[2022-01-24 19:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][910/1251]	eta 0:12:35 lr 0.000163	time 1.9074 (2.2168)	loss 3.9053 (3.1777)	grad_norm 2.3691 (2.2313)	
[2022-01-24 19:19:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][920/1251]	eta 0:12:14 lr 0.000163	time 1.9058 (2.2184)	loss 2.9762 (3.1804)	grad_norm 1.9941 (2.2315)	
[2022-01-24 19:19:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][930/1251]	eta 0:11:51 lr 0.000163	time 1.8954 (2.2179)	loss 3.9517 (3.1811)	grad_norm 2.2873 (2.2305)	
[2022-01-24 19:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][940/1251]	eta 0:11:29 lr 0.000163	time 1.7126 (2.2179)	loss 3.5616 (3.1791)	grad_norm 2.6675 (2.2304)	
[2022-01-24 19:20:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][950/1251]	eta 0:11:07 lr 0.000163	time 1.8695 (2.2174)	loss 3.1744 (3.1801)	grad_norm 2.3282 (2.2301)	
[2022-01-24 19:21:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][960/1251]	eta 0:10:44 lr 0.000163	time 1.6785 (2.2160)	loss 3.5417 (3.1829)	grad_norm 2.0128 (2.2302)	
[2022-01-24 19:21:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][970/1251]	eta 0:10:22 lr 0.000163	time 2.6293 (2.2143)	loss 3.1044 (3.1846)	grad_norm 2.4532 (2.2303)	
[2022-01-24 19:21:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][980/1251]	eta 0:09:59 lr 0.000163	time 1.5984 (2.2131)	loss 2.6912 (3.1857)	grad_norm 2.2191 (2.2301)	
[2022-01-24 19:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][990/1251]	eta 0:09:37 lr 0.000163	time 2.1479 (2.2134)	loss 3.9232 (3.1843)	grad_norm 2.1873 (2.2314)	
[2022-01-24 19:22:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1000/1251]	eta 0:09:15 lr 0.000163	time 2.1766 (2.2128)	loss 3.5901 (3.1832)	grad_norm 2.4305 (2.2329)	
[2022-01-24 19:22:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1010/1251]	eta 0:08:53 lr 0.000163	time 2.8569 (2.2127)	loss 2.1225 (3.1812)	grad_norm 2.1279 (2.2322)	
[2022-01-24 19:23:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1020/1251]	eta 0:08:31 lr 0.000163	time 2.1621 (2.2131)	loss 2.8159 (3.1828)	grad_norm 2.1482 (2.2334)	
[2022-01-24 19:23:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1030/1251]	eta 0:08:09 lr 0.000163	time 2.6105 (2.2140)	loss 2.6174 (3.1819)	grad_norm 2.3715 (2.2344)	
[2022-01-24 19:23:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1040/1251]	eta 0:07:46 lr 0.000163	time 2.1135 (2.2127)	loss 3.4987 (3.1808)	grad_norm 2.4902 (2.2334)	
[2022-01-24 19:24:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1050/1251]	eta 0:07:24 lr 0.000163	time 2.0152 (2.2128)	loss 3.0045 (3.1821)	grad_norm 1.9326 (2.2319)	
[2022-01-24 19:24:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1060/1251]	eta 0:07:02 lr 0.000163	time 1.8958 (2.2122)	loss 2.5772 (3.1788)	grad_norm 2.1105 (2.2324)	
[2022-01-24 19:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1070/1251]	eta 0:06:40 lr 0.000163	time 1.9897 (2.2114)	loss 3.5842 (3.1793)	grad_norm 2.2867 (2.2325)	
[2022-01-24 19:25:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1080/1251]	eta 0:06:18 lr 0.000163	time 2.2269 (2.2116)	loss 3.4724 (3.1810)	grad_norm 2.3602 (2.2324)	
[2022-01-24 19:25:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1090/1251]	eta 0:05:55 lr 0.000163	time 1.7957 (2.2102)	loss 3.3462 (3.1810)	grad_norm 2.2084 (2.2314)	
[2022-01-24 19:26:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1100/1251]	eta 0:05:33 lr 0.000163	time 2.2179 (2.2097)	loss 3.1700 (3.1823)	grad_norm 2.3587 (2.2315)	
[2022-01-24 19:26:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1110/1251]	eta 0:05:11 lr 0.000163	time 2.2184 (2.2083)	loss 3.7677 (3.1831)	grad_norm 2.1120 (2.2306)	
[2022-01-24 19:26:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1120/1251]	eta 0:04:49 lr 0.000163	time 2.5801 (2.2085)	loss 3.4136 (3.1833)	grad_norm 3.0054 (2.2310)	
[2022-01-24 19:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1130/1251]	eta 0:04:27 lr 0.000163	time 1.6871 (2.2084)	loss 3.7222 (3.1867)	grad_norm 2.1727 (2.2311)	
[2022-01-24 19:27:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1140/1251]	eta 0:04:05 lr 0.000163	time 2.4800 (2.2081)	loss 2.6086 (3.1863)	grad_norm 2.4726 (2.2333)	
[2022-01-24 19:27:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1150/1251]	eta 0:03:42 lr 0.000163	time 2.0469 (2.2077)	loss 3.6267 (3.1882)	grad_norm 2.0670 (2.2330)	
[2022-01-24 19:28:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1160/1251]	eta 0:03:20 lr 0.000163	time 2.3010 (2.2087)	loss 3.2507 (3.1871)	grad_norm 2.1880 (2.2347)	
[2022-01-24 19:28:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1170/1251]	eta 0:02:58 lr 0.000163	time 1.9811 (2.2083)	loss 3.3452 (3.1848)	grad_norm 2.0588 (2.2348)	
[2022-01-24 19:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1180/1251]	eta 0:02:36 lr 0.000163	time 2.0462 (2.2097)	loss 2.9886 (3.1851)	grad_norm 1.8893 (2.2358)	
[2022-01-24 19:29:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1190/1251]	eta 0:02:14 lr 0.000163	time 1.5869 (2.2092)	loss 3.4933 (3.1868)	grad_norm 2.3224 (2.2368)	
[2022-01-24 19:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1200/1251]	eta 0:01:52 lr 0.000163	time 1.9576 (2.2080)	loss 3.2538 (3.1870)	grad_norm 2.2615 (2.2361)	
[2022-01-24 19:30:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1210/1251]	eta 0:01:30 lr 0.000163	time 2.2214 (2.2072)	loss 3.8485 (3.1867)	grad_norm 1.8325 (2.2355)	
[2022-01-24 19:30:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1220/1251]	eta 0:01:08 lr 0.000162	time 2.1978 (2.2069)	loss 2.9771 (3.1881)	grad_norm 2.2128 (2.2360)	
[2022-01-24 19:30:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1230/1251]	eta 0:00:46 lr 0.000162	time 2.1695 (2.2059)	loss 2.3868 (3.1883)	grad_norm 2.2047 (2.2356)	
[2022-01-24 19:31:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1240/1251]	eta 0:00:24 lr 0.000162	time 1.3368 (2.2046)	loss 3.4552 (3.1877)	grad_norm 2.0956 (2.2361)	
[2022-01-24 19:31:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [222/300][1250/1251]	eta 0:00:02 lr 0.000162	time 1.1616 (2.1995)	loss 3.1439 (3.1868)	grad_norm 2.2189 (2.2360)	
[2022-01-24 19:31:24 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 222 training takes 0:45:52
[2022-01-24 19:31:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.737 (18.737)	Loss 0.8487 (0.8487)	Acc@1 80.469 (80.469)	Acc@5 95.312 (95.312)	
[2022-01-24 19:32:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.948 (3.468)	Loss 0.8388 (0.8933)	Acc@1 81.348 (79.439)	Acc@5 94.434 (94.718)	
[2022-01-24 19:32:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.956 (2.592)	Loss 0.9526 (0.8941)	Acc@1 77.051 (79.260)	Acc@5 94.141 (94.745)	
[2022-01-24 19:32:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.607 (2.287)	Loss 0.8682 (0.8923)	Acc@1 79.492 (79.193)	Acc@5 94.824 (94.761)	
[2022-01-24 19:32:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.822 (2.190)	Loss 0.8212 (0.8920)	Acc@1 80.469 (79.161)	Acc@5 95.410 (94.746)	
[2022-01-24 19:33:01 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.230 Acc@5 94.806
[2022-01-24 19:33:01 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.2%
[2022-01-24 19:33:01 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.33%
[2022-01-24 19:33:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][0/1251]	eta 7:28:19 lr 0.000162	time 21.5024 (21.5024)	loss 3.6230 (3.6230)	grad_norm 2.1886 (2.1886)	
[2022-01-24 19:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][10/1251]	eta 1:24:08 lr 0.000162	time 1.6449 (4.0678)	loss 2.6501 (2.9597)	grad_norm 2.2895 (2.1727)	
[2022-01-24 19:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][20/1251]	eta 1:03:18 lr 0.000162	time 1.5010 (3.0856)	loss 3.3629 (3.0720)	grad_norm 2.0908 (2.2081)	
[2022-01-24 19:34:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][30/1251]	eta 0:56:54 lr 0.000162	time 1.7185 (2.7962)	loss 3.8442 (3.1658)	grad_norm 2.4510 (2.1923)	
[2022-01-24 19:34:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][40/1251]	eta 0:54:30 lr 0.000162	time 3.3307 (2.7006)	loss 3.5247 (3.1702)	grad_norm 2.2322 (2.2022)	
[2022-01-24 19:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][50/1251]	eta 0:54:29 lr 0.000162	time 2.5057 (2.7225)	loss 3.6873 (3.1651)	grad_norm 2.2046 (2.2139)	
[2022-01-24 19:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][60/1251]	eta 0:52:18 lr 0.000162	time 1.6461 (2.6354)	loss 3.4707 (3.1604)	grad_norm 2.2851 (2.2286)	
[2022-01-24 19:36:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][70/1251]	eta 0:50:15 lr 0.000162	time 1.8370 (2.5530)	loss 3.4385 (3.1756)	grad_norm 2.5821 (2.2666)	
[2022-01-24 19:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][80/1251]	eta 0:48:36 lr 0.000162	time 2.0443 (2.4910)	loss 3.8642 (3.1892)	grad_norm 2.2342 (2.2964)	
[2022-01-24 19:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][90/1251]	eta 0:47:49 lr 0.000162	time 1.9344 (2.4717)	loss 3.3454 (3.1993)	grad_norm 2.5060 (2.2957)	
[2022-01-24 19:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][100/1251]	eta 0:47:28 lr 0.000162	time 1.7391 (2.4746)	loss 2.5928 (3.1939)	grad_norm 2.0804 (2.3029)	
[2022-01-24 19:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][110/1251]	eta 0:46:21 lr 0.000162	time 1.6171 (2.4381)	loss 2.6904 (3.1947)	grad_norm 1.9432 (2.2837)	
[2022-01-24 19:37:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][120/1251]	eta 0:45:18 lr 0.000162	time 1.5639 (2.4040)	loss 2.1807 (3.1746)	grad_norm 2.5117 (2.2873)	
[2022-01-24 19:38:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][130/1251]	eta 0:44:43 lr 0.000162	time 1.8632 (2.3940)	loss 3.1933 (3.1814)	grad_norm 2.5930 (2.2808)	
[2022-01-24 19:38:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][140/1251]	eta 0:43:55 lr 0.000162	time 1.9007 (2.3723)	loss 3.1159 (3.1868)	grad_norm 2.1677 (2.2761)	
[2022-01-24 19:38:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][150/1251]	eta 0:43:11 lr 0.000162	time 1.8102 (2.3542)	loss 3.0739 (3.1853)	grad_norm 2.0670 (2.2790)	
[2022-01-24 19:39:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][160/1251]	eta 0:42:39 lr 0.000162	time 1.9625 (2.3461)	loss 3.8148 (3.1850)	grad_norm 1.9659 (2.2701)	
[2022-01-24 19:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][170/1251]	eta 0:42:07 lr 0.000162	time 2.2607 (2.3377)	loss 2.1202 (3.1698)	grad_norm 2.3998 (2.2701)	
[2022-01-24 19:40:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][180/1251]	eta 0:41:31 lr 0.000162	time 1.8777 (2.3265)	loss 3.3683 (3.1852)	grad_norm 2.3522 (2.2642)	
[2022-01-24 19:40:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][190/1251]	eta 0:40:59 lr 0.000162	time 2.2926 (2.3185)	loss 3.7647 (3.1813)	grad_norm 2.4125 (2.2608)	
[2022-01-24 19:40:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][200/1251]	eta 0:40:24 lr 0.000162	time 1.5825 (2.3064)	loss 3.5506 (3.1892)	grad_norm 2.1951 (2.2645)	
[2022-01-24 19:41:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][210/1251]	eta 0:39:52 lr 0.000162	time 2.5240 (2.2980)	loss 3.4117 (3.1913)	grad_norm 1.9468 (2.2607)	
[2022-01-24 19:41:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][220/1251]	eta 0:39:22 lr 0.000162	time 1.9167 (2.2917)	loss 2.0786 (3.1880)	grad_norm 2.2328 (2.2548)	
[2022-01-24 19:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][230/1251]	eta 0:39:08 lr 0.000162	time 2.2135 (2.2999)	loss 3.8925 (3.2068)	grad_norm 2.4188 (2.2610)	
[2022-01-24 19:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][240/1251]	eta 0:38:34 lr 0.000162	time 1.6610 (2.2892)	loss 2.3780 (3.2067)	grad_norm 2.0552 (2.2659)	
[2022-01-24 19:42:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][250/1251]	eta 0:38:06 lr 0.000162	time 3.0058 (2.2845)	loss 3.2825 (3.1934)	grad_norm 1.9746 (2.2658)	
[2022-01-24 19:42:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][260/1251]	eta 0:37:34 lr 0.000162	time 1.8581 (2.2754)	loss 3.3719 (3.2065)	grad_norm 1.9378 (2.2666)	
[2022-01-24 19:43:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][270/1251]	eta 0:37:12 lr 0.000162	time 1.7048 (2.2757)	loss 2.8514 (3.2062)	grad_norm 2.0145 (2.2626)	
[2022-01-24 19:43:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][280/1251]	eta 0:36:45 lr 0.000162	time 1.9035 (2.2712)	loss 3.4116 (3.1991)	grad_norm 2.0809 (2.2600)	
[2022-01-24 19:44:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][290/1251]	eta 0:36:18 lr 0.000162	time 2.5813 (2.2673)	loss 2.9331 (3.1838)	grad_norm 2.3597 (2.2560)	
[2022-01-24 19:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][300/1251]	eta 0:35:50 lr 0.000161	time 2.1674 (2.2611)	loss 3.5290 (3.1781)	grad_norm 2.0605 (2.2496)	
[2022-01-24 19:44:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][310/1251]	eta 0:35:28 lr 0.000161	time 1.8416 (2.2620)	loss 3.3283 (3.1816)	grad_norm 2.2386 (2.2480)	
[2022-01-24 19:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][320/1251]	eta 0:35:07 lr 0.000161	time 2.2715 (2.2642)	loss 3.7878 (3.1842)	grad_norm 2.2587 (2.2458)	
[2022-01-24 19:45:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][330/1251]	eta 0:34:45 lr 0.000161	time 2.8438 (2.2643)	loss 3.1693 (3.1857)	grad_norm 2.2865 (2.2426)	
[2022-01-24 19:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][340/1251]	eta 0:34:17 lr 0.000161	time 2.1272 (2.2590)	loss 4.0504 (3.1901)	grad_norm 2.1199 (2.2420)	
[2022-01-24 19:46:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][350/1251]	eta 0:33:53 lr 0.000161	time 1.9003 (2.2573)	loss 2.7467 (3.1995)	grad_norm 2.2622 (2.2450)	
[2022-01-24 19:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][360/1251]	eta 0:33:26 lr 0.000161	time 1.8532 (2.2514)	loss 3.0670 (3.2004)	grad_norm 1.8082 (2.2429)	
[2022-01-24 19:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][370/1251]	eta 0:33:00 lr 0.000161	time 2.5088 (2.2482)	loss 3.6569 (3.2008)	grad_norm 2.5202 (2.2441)	
[2022-01-24 19:47:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][380/1251]	eta 0:32:36 lr 0.000161	time 2.3572 (2.2464)	loss 3.2080 (3.2007)	grad_norm 1.8818 (2.2394)	
[2022-01-24 19:47:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][390/1251]	eta 0:32:12 lr 0.000161	time 1.5250 (2.2440)	loss 2.6616 (3.2018)	grad_norm 2.4492 (2.2414)	
[2022-01-24 19:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][400/1251]	eta 0:31:45 lr 0.000161	time 2.1592 (2.2397)	loss 3.5904 (3.2042)	grad_norm 2.0758 (2.2417)	
[2022-01-24 19:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][410/1251]	eta 0:31:21 lr 0.000161	time 2.2191 (2.2375)	loss 3.3521 (3.2111)	grad_norm 2.6178 (2.2419)	
[2022-01-24 19:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][420/1251]	eta 0:30:59 lr 0.000161	time 1.9533 (2.2381)	loss 3.9231 (3.2201)	grad_norm 2.1179 (2.2442)	
[2022-01-24 19:49:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][430/1251]	eta 0:30:37 lr 0.000161	time 1.8276 (2.2384)	loss 3.1292 (3.2155)	grad_norm 2.1767 (2.2410)	
[2022-01-24 19:49:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][440/1251]	eta 0:30:13 lr 0.000161	time 2.8607 (2.2360)	loss 3.6250 (3.2168)	grad_norm 2.8950 (2.2417)	
[2022-01-24 19:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][450/1251]	eta 0:29:49 lr 0.000161	time 1.9140 (2.2343)	loss 2.2426 (3.2205)	grad_norm 2.3130 (2.2399)	
[2022-01-24 19:50:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][460/1251]	eta 0:29:26 lr 0.000161	time 2.2072 (2.2339)	loss 3.4932 (3.2224)	grad_norm 2.2755 (2.2420)	
[2022-01-24 19:50:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][470/1251]	eta 0:29:05 lr 0.000161	time 1.5836 (2.2355)	loss 3.5493 (3.2225)	grad_norm 3.1575 (2.2419)	
[2022-01-24 19:50:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][480/1251]	eta 0:28:44 lr 0.000161	time 2.9194 (2.2370)	loss 3.4803 (3.2267)	grad_norm 2.3137 (2.2410)	
[2022-01-24 19:51:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][490/1251]	eta 0:28:22 lr 0.000161	time 1.8316 (2.2368)	loss 3.7610 (3.2199)	grad_norm 2.0641 (2.2401)	
[2022-01-24 19:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][500/1251]	eta 0:27:58 lr 0.000161	time 1.7577 (2.2348)	loss 3.4406 (3.2203)	grad_norm 2.4533 (2.2395)	
[2022-01-24 19:52:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][510/1251]	eta 0:27:35 lr 0.000161	time 1.6494 (2.2346)	loss 3.5853 (3.2231)	grad_norm 2.0791 (2.2409)	
[2022-01-24 19:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][520/1251]	eta 0:27:12 lr 0.000161	time 2.6280 (2.2339)	loss 3.4898 (3.2233)	grad_norm 2.1326 (2.2417)	
[2022-01-24 19:52:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][530/1251]	eta 0:26:48 lr 0.000161	time 1.5775 (2.2309)	loss 3.4153 (3.2224)	grad_norm 2.1699 (2.2424)	
[2022-01-24 19:53:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][540/1251]	eta 0:26:24 lr 0.000161	time 1.7562 (2.2279)	loss 3.4139 (3.2199)	grad_norm 2.0986 (2.2444)	
[2022-01-24 19:53:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][550/1251]	eta 0:26:04 lr 0.000161	time 2.5451 (2.2315)	loss 3.8879 (3.2189)	grad_norm 2.4097 (2.2429)	
[2022-01-24 19:53:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][560/1251]	eta 0:25:40 lr 0.000161	time 2.3483 (2.2297)	loss 3.9947 (3.2247)	grad_norm 2.3603 (2.2450)	
[2022-01-24 19:54:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][570/1251]	eta 0:25:16 lr 0.000161	time 1.9855 (2.2274)	loss 3.0024 (3.2284)	grad_norm 3.1443 (2.2472)	
[2022-01-24 19:54:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][580/1251]	eta 0:24:53 lr 0.000161	time 2.2681 (2.2262)	loss 2.6227 (3.2285)	grad_norm 2.1435 (2.2461)	
[2022-01-24 19:54:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][590/1251]	eta 0:24:30 lr 0.000161	time 1.9160 (2.2240)	loss 2.8720 (3.2270)	grad_norm 2.2396 (2.2476)	
[2022-01-24 19:55:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][600/1251]	eta 0:24:08 lr 0.000161	time 2.5675 (2.2249)	loss 3.2090 (3.2290)	grad_norm 2.1667 (2.2488)	
[2022-01-24 19:55:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][610/1251]	eta 0:23:46 lr 0.000161	time 1.9410 (2.2259)	loss 3.7319 (3.2312)	grad_norm 2.2882 (2.2512)	
[2022-01-24 19:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][620/1251]	eta 0:23:24 lr 0.000161	time 2.4450 (2.2255)	loss 3.0298 (3.2327)	grad_norm 2.2368 (2.2514)	
[2022-01-24 19:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][630/1251]	eta 0:22:59 lr 0.000161	time 1.9440 (2.2220)	loss 3.5678 (3.2348)	grad_norm 2.8045 (2.2503)	
[2022-01-24 19:56:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][640/1251]	eta 0:22:36 lr 0.000160	time 2.2469 (2.2204)	loss 2.6351 (3.2372)	grad_norm 1.8209 (2.2492)	
[2022-01-24 19:57:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][650/1251]	eta 0:22:13 lr 0.000160	time 1.5861 (2.2184)	loss 3.9658 (3.2372)	grad_norm 2.3004 (2.2478)	
[2022-01-24 19:57:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][660/1251]	eta 0:21:51 lr 0.000160	time 2.4677 (2.2184)	loss 3.3514 (3.2367)	grad_norm 2.0424 (2.2450)	
[2022-01-24 19:57:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][670/1251]	eta 0:21:28 lr 0.000160	time 2.1670 (2.2182)	loss 3.1549 (3.2357)	grad_norm 1.9509 (2.2433)	
[2022-01-24 19:58:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][680/1251]	eta 0:21:07 lr 0.000160	time 2.5764 (2.2189)	loss 3.1015 (3.2375)	grad_norm 2.0021 (2.2413)	
[2022-01-24 19:58:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][690/1251]	eta 0:20:44 lr 0.000160	time 1.6148 (2.2185)	loss 2.8735 (3.2374)	grad_norm 2.0000 (2.2447)	
[2022-01-24 19:58:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][700/1251]	eta 0:20:23 lr 0.000160	time 2.4596 (2.2200)	loss 3.8115 (3.2405)	grad_norm 2.2415 (2.2433)	
[2022-01-24 19:59:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][710/1251]	eta 0:20:01 lr 0.000160	time 1.9025 (2.2202)	loss 3.5043 (3.2397)	grad_norm 2.2080 (2.2437)	
[2022-01-24 19:59:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][720/1251]	eta 0:19:40 lr 0.000160	time 3.7407 (2.2236)	loss 3.5308 (3.2381)	grad_norm 2.2451 (2.2441)	
[2022-01-24 20:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][730/1251]	eta 0:19:17 lr 0.000160	time 1.7146 (2.2216)	loss 2.8942 (3.2391)	grad_norm 2.3446 (2.2441)	
[2022-01-24 20:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][740/1251]	eta 0:18:54 lr 0.000160	time 1.8265 (2.2202)	loss 3.0878 (3.2354)	grad_norm 2.2813 (2.2444)	
[2022-01-24 20:00:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][750/1251]	eta 0:18:31 lr 0.000160	time 1.9076 (2.2178)	loss 3.4800 (3.2371)	grad_norm 2.1896 (2.2446)	
[2022-01-24 20:01:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][760/1251]	eta 0:18:08 lr 0.000160	time 3.1974 (2.2168)	loss 3.0934 (3.2386)	grad_norm 2.2544 (2.2441)	
[2022-01-24 20:01:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][770/1251]	eta 0:17:45 lr 0.000160	time 1.9394 (2.2153)	loss 3.0306 (3.2366)	grad_norm 2.2344 (2.2433)	
[2022-01-24 20:01:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][780/1251]	eta 0:17:23 lr 0.000160	time 2.7443 (2.2163)	loss 3.4977 (3.2359)	grad_norm 2.1733 (2.2434)	
[2022-01-24 20:02:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][790/1251]	eta 0:17:01 lr 0.000160	time 1.5329 (2.2162)	loss 2.8221 (3.2311)	grad_norm 2.0292 (2.2428)	
[2022-01-24 20:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][800/1251]	eta 0:16:41 lr 0.000160	time 2.0104 (2.2201)	loss 3.2488 (3.2295)	grad_norm 1.9500 (2.2424)	
[2022-01-24 20:03:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][810/1251]	eta 0:16:19 lr 0.000160	time 2.9480 (2.2203)	loss 3.1845 (3.2290)	grad_norm 2.0252 (2.2418)	
[2022-01-24 20:03:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][820/1251]	eta 0:15:56 lr 0.000160	time 1.5415 (2.2188)	loss 2.8806 (3.2262)	grad_norm 2.7637 (2.2413)	
[2022-01-24 20:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][830/1251]	eta 0:15:33 lr 0.000160	time 1.9429 (2.2166)	loss 2.7622 (3.2260)	grad_norm 2.0009 (2.2407)	
[2022-01-24 20:04:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][840/1251]	eta 0:15:10 lr 0.000160	time 1.8608 (2.2153)	loss 3.4316 (3.2262)	grad_norm 2.2817 (2.2413)	
[2022-01-24 20:04:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][850/1251]	eta 0:14:47 lr 0.000160	time 2.0593 (2.2144)	loss 2.9176 (3.2260)	grad_norm 2.2289 (2.2403)	
[2022-01-24 20:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][860/1251]	eta 0:14:25 lr 0.000160	time 2.6412 (2.2137)	loss 2.3773 (3.2261)	grad_norm 2.3925 (2.2407)	
[2022-01-24 20:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][870/1251]	eta 0:14:03 lr 0.000160	time 2.2892 (2.2151)	loss 3.2067 (3.2271)	grad_norm 2.4632 (2.2411)	
[2022-01-24 20:05:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][880/1251]	eta 0:13:41 lr 0.000160	time 2.1517 (2.2131)	loss 2.6088 (3.2247)	grad_norm 2.0356 (2.2428)	
[2022-01-24 20:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][890/1251]	eta 0:13:18 lr 0.000160	time 2.1197 (2.2114)	loss 3.1668 (3.2246)	grad_norm 2.9518 (2.2450)	
[2022-01-24 20:06:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][900/1251]	eta 0:12:55 lr 0.000160	time 1.8816 (2.2105)	loss 3.4328 (3.2235)	grad_norm 2.3047 (2.2475)	
[2022-01-24 20:06:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][910/1251]	eta 0:12:33 lr 0.000160	time 2.2107 (2.2105)	loss 3.0906 (3.2255)	grad_norm 1.8752 (2.2469)	
[2022-01-24 20:06:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][920/1251]	eta 0:12:11 lr 0.000160	time 2.4624 (2.2099)	loss 3.4260 (3.2242)	grad_norm 2.1805 (2.2462)	
[2022-01-24 20:07:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][930/1251]	eta 0:11:49 lr 0.000160	time 2.5455 (2.2089)	loss 3.0888 (3.2235)	grad_norm 2.3762 (2.2458)	
[2022-01-24 20:07:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][940/1251]	eta 0:11:27 lr 0.000160	time 3.0927 (2.2114)	loss 2.9967 (3.2236)	grad_norm 2.6161 (2.2456)	
[2022-01-24 20:08:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][950/1251]	eta 0:11:06 lr 0.000160	time 2.7524 (2.2129)	loss 2.8801 (3.2210)	grad_norm 2.0890 (2.2454)	
[2022-01-24 20:08:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][960/1251]	eta 0:10:43 lr 0.000160	time 1.7916 (2.2118)	loss 3.9149 (3.2218)	grad_norm 2.0043 (2.2439)	
[2022-01-24 20:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][970/1251]	eta 0:10:21 lr 0.000159	time 1.8290 (2.2105)	loss 3.7489 (3.2233)	grad_norm 2.1335 (2.2425)	
[2022-01-24 20:09:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][980/1251]	eta 0:09:58 lr 0.000159	time 1.8901 (2.2086)	loss 3.0320 (3.2223)	grad_norm 2.2730 (2.2422)	
[2022-01-24 20:09:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][990/1251]	eta 0:09:36 lr 0.000159	time 2.4618 (2.2097)	loss 3.4117 (3.2240)	grad_norm 2.1894 (2.2420)	
[2022-01-24 20:09:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1000/1251]	eta 0:09:14 lr 0.000159	time 2.3288 (2.2095)	loss 3.8474 (3.2250)	grad_norm 2.0657 (2.2432)	
[2022-01-24 20:10:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1010/1251]	eta 0:08:52 lr 0.000159	time 1.8167 (2.2091)	loss 3.1685 (3.2271)	grad_norm 2.5144 (2.2430)	
[2022-01-24 20:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1020/1251]	eta 0:08:30 lr 0.000159	time 1.5106 (2.2091)	loss 3.5898 (3.2287)	grad_norm 2.3687 (2.2419)	
[2022-01-24 20:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1030/1251]	eta 0:08:08 lr 0.000159	time 3.1321 (2.2119)	loss 3.9106 (3.2296)	grad_norm 2.0644 (2.2421)	
[2022-01-24 20:11:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1040/1251]	eta 0:07:46 lr 0.000159	time 1.5719 (2.2119)	loss 2.0821 (3.2283)	grad_norm 2.6145 (2.2414)	
[2022-01-24 20:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1050/1251]	eta 0:07:24 lr 0.000159	time 1.5593 (2.2111)	loss 2.3322 (3.2261)	grad_norm 2.1817 (2.2406)	
[2022-01-24 20:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1060/1251]	eta 0:07:02 lr 0.000159	time 1.9223 (2.2107)	loss 2.9508 (3.2261)	grad_norm 1.9879 (2.2412)	
[2022-01-24 20:12:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1070/1251]	eta 0:06:40 lr 0.000159	time 2.5623 (2.2108)	loss 3.5270 (3.2276)	grad_norm 2.1325 (2.2401)	
[2022-01-24 20:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1080/1251]	eta 0:06:17 lr 0.000159	time 1.6961 (2.2092)	loss 3.9386 (3.2281)	grad_norm 2.4857 (2.2394)	
[2022-01-24 20:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1090/1251]	eta 0:05:55 lr 0.000159	time 2.1475 (2.2091)	loss 3.1671 (3.2281)	grad_norm 2.5052 (2.2391)	
[2022-01-24 20:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1100/1251]	eta 0:05:33 lr 0.000159	time 2.0424 (2.2080)	loss 1.9273 (3.2276)	grad_norm 2.2054 (2.2385)	
[2022-01-24 20:13:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1110/1251]	eta 0:05:11 lr 0.000159	time 1.8437 (2.2076)	loss 3.4134 (3.2253)	grad_norm 2.1198 (2.2394)	
[2022-01-24 20:14:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1120/1251]	eta 0:04:49 lr 0.000159	time 2.0591 (2.2071)	loss 3.2760 (3.2249)	grad_norm 2.7713 (2.2394)	
[2022-01-24 20:14:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1130/1251]	eta 0:04:27 lr 0.000159	time 1.6007 (2.2071)	loss 3.7063 (3.2260)	grad_norm 2.2484 (2.2394)	
[2022-01-24 20:15:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1140/1251]	eta 0:04:05 lr 0.000159	time 2.0198 (2.2074)	loss 4.1012 (3.2259)	grad_norm 2.1605 (2.2393)	
[2022-01-24 20:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1150/1251]	eta 0:03:43 lr 0.000159	time 2.6890 (2.2083)	loss 3.1171 (3.2265)	grad_norm 2.3404 (2.2401)	
[2022-01-24 20:15:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1160/1251]	eta 0:03:20 lr 0.000159	time 1.6942 (2.2071)	loss 2.6120 (3.2237)	grad_norm 2.1096 (2.2402)	
[2022-01-24 20:16:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1170/1251]	eta 0:02:58 lr 0.000159	time 1.8988 (2.2074)	loss 3.2427 (3.2220)	grad_norm 2.0535 (2.2391)	
[2022-01-24 20:16:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1180/1251]	eta 0:02:36 lr 0.000159	time 1.6121 (2.2066)	loss 3.6299 (3.2233)	grad_norm 2.1708 (2.2396)	
[2022-01-24 20:16:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1190/1251]	eta 0:02:14 lr 0.000159	time 2.5334 (2.2056)	loss 3.7536 (3.2235)	grad_norm 2.1498 (2.2413)	
[2022-01-24 20:17:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1200/1251]	eta 0:01:52 lr 0.000159	time 1.4417 (2.2047)	loss 1.9496 (3.2214)	grad_norm 1.9732 (2.2423)	
[2022-01-24 20:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1210/1251]	eta 0:01:30 lr 0.000159	time 2.1635 (2.2042)	loss 3.4705 (3.2223)	grad_norm 2.4036 (2.2439)	
[2022-01-24 20:17:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1220/1251]	eta 0:01:08 lr 0.000159	time 1.8211 (2.2046)	loss 3.4362 (3.2228)	grad_norm 2.1672 (2.2440)	
[2022-01-24 20:18:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1230/1251]	eta 0:00:46 lr 0.000159	time 2.6418 (2.2060)	loss 3.5132 (3.2227)	grad_norm 2.2996 (2.2448)	
[2022-01-24 20:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1240/1251]	eta 0:00:24 lr 0.000159	time 1.3738 (2.2049)	loss 3.9572 (3.2219)	grad_norm 2.1844 (2.2445)	
[2022-01-24 20:18:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [223/300][1250/1251]	eta 0:00:02 lr 0.000159	time 1.2003 (2.1991)	loss 2.9332 (3.2229)	grad_norm 2.0266 (2.2431)	
[2022-01-24 20:18:53 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 223 training takes 0:45:51
[2022-01-24 20:19:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 20.794 (20.794)	Loss 0.8937 (0.8937)	Acc@1 78.418 (78.418)	Acc@5 94.727 (94.727)	
[2022-01-24 20:19:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.257 (3.344)	Loss 0.8668 (0.8824)	Acc@1 79.004 (79.226)	Acc@5 95.117 (94.771)	
[2022-01-24 20:19:49 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.905 (2.673)	Loss 0.9081 (0.8701)	Acc@1 78.320 (79.492)	Acc@5 94.922 (94.913)	
[2022-01-24 20:20:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.569 (2.230)	Loss 0.8705 (0.8696)	Acc@1 79.297 (79.458)	Acc@5 95.215 (94.960)	
[2022-01-24 20:20:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.289 (2.161)	Loss 0.8525 (0.8699)	Acc@1 81.055 (79.549)	Acc@5 94.727 (94.941)	
[2022-01-24 20:20:29 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.472 Acc@5 94.876
[2022-01-24 20:20:29 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.5%
[2022-01-24 20:20:29 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.47%
[2022-01-24 20:20:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][0/1251]	eta 7:34:41 lr 0.000159	time 21.8080 (21.8080)	loss 3.2592 (3.2592)	grad_norm 1.9753 (1.9753)	
[2022-01-24 20:21:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][10/1251]	eta 1:26:50 lr 0.000159	time 2.2680 (4.1985)	loss 3.2202 (3.2945)	grad_norm 2.9437 (2.2582)	
[2022-01-24 20:21:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][20/1251]	eta 1:04:49 lr 0.000159	time 1.5275 (3.1592)	loss 3.0373 (3.2501)	grad_norm 1.9614 (2.2124)	
[2022-01-24 20:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][30/1251]	eta 0:57:36 lr 0.000159	time 1.6891 (2.8306)	loss 2.1628 (3.2618)	grad_norm 2.1459 (2.2382)	
[2022-01-24 20:22:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][40/1251]	eta 0:54:25 lr 0.000159	time 3.1137 (2.6964)	loss 3.6812 (3.2735)	grad_norm 2.0940 (2.2538)	
[2022-01-24 20:22:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][50/1251]	eta 0:53:37 lr 0.000159	time 3.2565 (2.6789)	loss 2.7451 (3.2976)	grad_norm 2.0048 (2.2609)	
[2022-01-24 20:23:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][60/1251]	eta 0:51:42 lr 0.000158	time 1.8139 (2.6052)	loss 3.6754 (3.2943)	grad_norm 2.0690 (2.2447)	
[2022-01-24 20:23:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][70/1251]	eta 0:49:55 lr 0.000158	time 1.5681 (2.5368)	loss 3.2496 (3.2654)	grad_norm 2.4453 (2.2695)	
[2022-01-24 20:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][80/1251]	eta 0:48:41 lr 0.000158	time 3.0862 (2.4950)	loss 3.8203 (3.2866)	grad_norm 2.1963 (2.2690)	
[2022-01-24 20:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][90/1251]	eta 0:47:21 lr 0.000158	time 1.9926 (2.4479)	loss 4.0965 (3.2732)	grad_norm 2.3455 (2.2648)	
[2022-01-24 20:24:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][100/1251]	eta 0:46:17 lr 0.000158	time 1.8951 (2.4130)	loss 3.6922 (3.2903)	grad_norm 1.9948 (2.2565)	
[2022-01-24 20:24:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][110/1251]	eta 0:45:07 lr 0.000158	time 2.0256 (2.3733)	loss 2.1692 (3.2878)	grad_norm 2.2153 (2.2441)	
[2022-01-24 20:25:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][120/1251]	eta 0:44:21 lr 0.000158	time 2.2103 (2.3528)	loss 2.1812 (3.2869)	grad_norm 2.0766 (2.2429)	
[2022-01-24 20:25:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][130/1251]	eta 0:43:39 lr 0.000158	time 2.1954 (2.3366)	loss 3.2851 (3.2640)	grad_norm 2.3143 (2.2521)	
[2022-01-24 20:25:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][140/1251]	eta 0:43:04 lr 0.000158	time 1.5737 (2.3263)	loss 2.4775 (3.2442)	grad_norm 2.1075 (2.2436)	
[2022-01-24 20:26:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][150/1251]	eta 0:42:35 lr 0.000158	time 2.4188 (2.3214)	loss 2.0620 (3.2349)	grad_norm 1.9714 (2.2388)	
[2022-01-24 20:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][160/1251]	eta 0:42:23 lr 0.000158	time 3.1942 (2.3313)	loss 2.7038 (3.2060)	grad_norm 2.0285 (2.2381)	
[2022-01-24 20:27:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][170/1251]	eta 0:42:01 lr 0.000158	time 2.4647 (2.3329)	loss 3.1705 (3.1999)	grad_norm 2.4618 (2.2405)	
[2022-01-24 20:27:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][180/1251]	eta 0:41:31 lr 0.000158	time 1.7645 (2.3268)	loss 2.4003 (3.1753)	grad_norm 2.5240 (2.2349)	
[2022-01-24 20:27:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][190/1251]	eta 0:41:03 lr 0.000158	time 2.4259 (2.3216)	loss 3.4887 (3.1792)	grad_norm 2.1392 (2.2303)	
[2022-01-24 20:28:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][200/1251]	eta 0:40:20 lr 0.000158	time 1.5669 (2.3031)	loss 3.0646 (3.1819)	grad_norm 2.5148 (2.2332)	
[2022-01-24 20:28:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][210/1251]	eta 0:39:44 lr 0.000158	time 1.9118 (2.2905)	loss 3.4818 (3.1922)	grad_norm 1.9719 (2.2316)	
[2022-01-24 20:28:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][220/1251]	eta 0:39:10 lr 0.000158	time 2.1982 (2.2802)	loss 2.0449 (3.1816)	grad_norm 2.0889 (2.2367)	
[2022-01-24 20:29:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][230/1251]	eta 0:38:41 lr 0.000158	time 1.9683 (2.2735)	loss 2.9463 (3.1828)	grad_norm 2.4293 (2.2363)	
[2022-01-24 20:29:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][240/1251]	eta 0:38:15 lr 0.000158	time 1.9591 (2.2702)	loss 2.4044 (3.1889)	grad_norm 2.2230 (2.2419)	
[2022-01-24 20:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][250/1251]	eta 0:37:47 lr 0.000158	time 2.5074 (2.2652)	loss 3.4129 (3.1884)	grad_norm 2.0935 (2.2417)	
[2022-01-24 20:30:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][260/1251]	eta 0:37:24 lr 0.000158	time 2.7208 (2.2647)	loss 2.2571 (3.1828)	grad_norm 1.9602 (2.2443)	
[2022-01-24 20:30:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][270/1251]	eta 0:37:03 lr 0.000158	time 3.0608 (2.2663)	loss 2.9521 (3.1916)	grad_norm 2.2018 (2.2425)	
[2022-01-24 20:31:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][280/1251]	eta 0:36:48 lr 0.000158	time 1.4354 (2.2740)	loss 3.3736 (3.1973)	grad_norm 2.1448 (2.2427)	
[2022-01-24 20:31:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][290/1251]	eta 0:36:26 lr 0.000158	time 2.2146 (2.2752)	loss 3.8054 (3.2029)	grad_norm 2.4639 (2.2457)	
[2022-01-24 20:31:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][300/1251]	eta 0:35:57 lr 0.000158	time 2.2830 (2.2688)	loss 3.7484 (3.2018)	grad_norm 2.2976 (2.2433)	
[2022-01-24 20:32:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][310/1251]	eta 0:35:27 lr 0.000158	time 2.1529 (2.2607)	loss 3.5199 (3.2047)	grad_norm 2.2665 (2.2461)	
[2022-01-24 20:32:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][320/1251]	eta 0:34:59 lr 0.000158	time 1.8337 (2.2549)	loss 3.4337 (3.2134)	grad_norm 1.8580 (2.2462)	
[2022-01-24 20:32:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][330/1251]	eta 0:34:36 lr 0.000158	time 2.3823 (2.2546)	loss 3.5928 (3.2161)	grad_norm 2.6901 (2.2470)	
[2022-01-24 20:33:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][340/1251]	eta 0:34:07 lr 0.000158	time 1.9244 (2.2477)	loss 3.6332 (3.2141)	grad_norm 2.5318 (2.2466)	
[2022-01-24 20:33:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][350/1251]	eta 0:33:46 lr 0.000158	time 2.5818 (2.2491)	loss 2.6397 (3.2068)	grad_norm 2.0940 (2.2474)	
[2022-01-24 20:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][360/1251]	eta 0:33:22 lr 0.000158	time 2.1650 (2.2474)	loss 3.2842 (3.2074)	grad_norm 2.3043 (2.2520)	
[2022-01-24 20:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][370/1251]	eta 0:32:59 lr 0.000158	time 2.5038 (2.2469)	loss 2.8773 (3.2089)	grad_norm 2.3444 (2.2536)	
[2022-01-24 20:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][380/1251]	eta 0:32:38 lr 0.000158	time 2.4516 (2.2487)	loss 2.5721 (3.2052)	grad_norm 2.0624 (2.2530)	
[2022-01-24 20:35:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][390/1251]	eta 0:32:17 lr 0.000158	time 2.1813 (2.2497)	loss 3.3086 (3.2058)	grad_norm 2.3698 (2.2550)	
[2022-01-24 20:35:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][400/1251]	eta 0:31:49 lr 0.000157	time 1.7995 (2.2439)	loss 3.1273 (3.2033)	grad_norm 2.1125 (2.2550)	
[2022-01-24 20:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][410/1251]	eta 0:31:21 lr 0.000157	time 1.6064 (2.2376)	loss 3.3111 (3.2016)	grad_norm 2.1945 (2.2544)	
[2022-01-24 20:36:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][420/1251]	eta 0:30:56 lr 0.000157	time 1.9465 (2.2336)	loss 2.9123 (3.2047)	grad_norm 2.2584 (2.2551)	
[2022-01-24 20:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][430/1251]	eta 0:30:30 lr 0.000157	time 1.8681 (2.2295)	loss 2.6688 (3.2000)	grad_norm 2.2915 (2.2528)	
[2022-01-24 20:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][440/1251]	eta 0:30:06 lr 0.000157	time 1.7903 (2.2272)	loss 3.3429 (3.2011)	grad_norm 2.5296 (2.2527)	
[2022-01-24 20:37:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][450/1251]	eta 0:29:43 lr 0.000157	time 1.8941 (2.2270)	loss 3.9246 (3.2091)	grad_norm 2.2627 (2.2577)	
[2022-01-24 20:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][460/1251]	eta 0:29:22 lr 0.000157	time 2.2741 (2.2285)	loss 3.8699 (3.2124)	grad_norm 2.3338 (2.2606)	
[2022-01-24 20:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][470/1251]	eta 0:28:59 lr 0.000157	time 2.0781 (2.2271)	loss 3.6160 (3.2177)	grad_norm 2.1227 (2.2577)	
[2022-01-24 20:38:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][480/1251]	eta 0:28:36 lr 0.000157	time 1.6314 (2.2265)	loss 3.7076 (3.2166)	grad_norm 2.2562 (2.2551)	
[2022-01-24 20:38:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][490/1251]	eta 0:28:15 lr 0.000157	time 1.6587 (2.2278)	loss 2.6019 (3.2168)	grad_norm 2.4443 (2.2549)	
[2022-01-24 20:39:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][500/1251]	eta 0:27:55 lr 0.000157	time 1.9664 (2.2315)	loss 2.9806 (3.2181)	grad_norm 2.2152 (2.2547)	
[2022-01-24 20:39:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][510/1251]	eta 0:27:32 lr 0.000157	time 1.5242 (2.2302)	loss 1.9185 (3.2166)	grad_norm 2.3333 (2.2534)	
[2022-01-24 20:39:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][520/1251]	eta 0:27:08 lr 0.000157	time 1.7729 (2.2276)	loss 3.7075 (3.2158)	grad_norm 2.4046 (2.2524)	
[2022-01-24 20:40:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][530/1251]	eta 0:26:43 lr 0.000157	time 1.9059 (2.2243)	loss 2.8540 (3.2152)	grad_norm 2.1720 (2.2502)	
[2022-01-24 20:40:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][540/1251]	eta 0:26:22 lr 0.000157	time 2.5417 (2.2251)	loss 3.5577 (3.2186)	grad_norm 1.9322 (2.2499)	
[2022-01-24 20:40:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][550/1251]	eta 0:25:59 lr 0.000157	time 2.1582 (2.2246)	loss 2.2592 (3.2195)	grad_norm 2.5314 (2.2506)	
[2022-01-24 20:41:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][560/1251]	eta 0:25:35 lr 0.000157	time 1.8458 (2.2224)	loss 2.3696 (3.2152)	grad_norm 1.9106 (2.2502)	
[2022-01-24 20:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][570/1251]	eta 0:25:12 lr 0.000157	time 2.1965 (2.2212)	loss 3.6352 (3.2194)	grad_norm 2.3065 (2.2508)	
[2022-01-24 20:41:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][580/1251]	eta 0:24:48 lr 0.000157	time 2.2408 (2.2189)	loss 2.7043 (3.2164)	grad_norm 2.0914 (2.2497)	
[2022-01-24 20:42:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][590/1251]	eta 0:24:24 lr 0.000157	time 1.9101 (2.2153)	loss 3.1059 (3.2171)	grad_norm 2.3657 (2.2514)	
[2022-01-24 20:42:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][600/1251]	eta 0:24:01 lr 0.000157	time 1.9612 (2.2139)	loss 3.5133 (3.2175)	grad_norm 2.1687 (2.2526)	
[2022-01-24 20:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][610/1251]	eta 0:23:37 lr 0.000157	time 2.1909 (2.2116)	loss 3.6668 (3.2158)	grad_norm 2.5166 (2.2524)	
[2022-01-24 20:43:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][620/1251]	eta 0:23:15 lr 0.000157	time 2.5792 (2.2115)	loss 3.7227 (3.2086)	grad_norm 1.9155 (2.2494)	
[2022-01-24 20:43:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][630/1251]	eta 0:22:52 lr 0.000157	time 2.4878 (2.2107)	loss 3.1234 (3.2103)	grad_norm 2.3341 (2.2480)	
[2022-01-24 20:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][640/1251]	eta 0:22:30 lr 0.000157	time 2.0676 (2.2111)	loss 2.4575 (3.2073)	grad_norm 2.1258 (2.2464)	
[2022-01-24 20:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][650/1251]	eta 0:22:09 lr 0.000157	time 2.6210 (2.2115)	loss 3.3181 (3.2067)	grad_norm 2.0185 (2.2462)	
[2022-01-24 20:44:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][660/1251]	eta 0:21:47 lr 0.000157	time 2.2737 (2.2116)	loss 3.4628 (3.2071)	grad_norm 2.0827 (2.2450)	
[2022-01-24 20:45:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][670/1251]	eta 0:21:25 lr 0.000157	time 2.1822 (2.2119)	loss 3.9223 (3.2118)	grad_norm 2.2367 (2.2435)	
[2022-01-24 20:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][680/1251]	eta 0:21:03 lr 0.000157	time 2.7994 (2.2136)	loss 3.8178 (3.2129)	grad_norm 2.4806 (2.2425)	
[2022-01-24 20:45:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][690/1251]	eta 0:20:41 lr 0.000157	time 3.0835 (2.2135)	loss 3.7994 (3.2123)	grad_norm 2.0185 (2.2427)	
[2022-01-24 20:46:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][700/1251]	eta 0:20:19 lr 0.000157	time 2.0749 (2.2130)	loss 3.4598 (3.2104)	grad_norm 2.5426 (2.2424)	
[2022-01-24 20:46:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][710/1251]	eta 0:19:57 lr 0.000157	time 1.7955 (2.2127)	loss 2.8735 (3.2094)	grad_norm 2.3529 (2.2445)	
[2022-01-24 20:47:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][720/1251]	eta 0:19:36 lr 0.000157	time 2.5483 (2.2150)	loss 3.5491 (3.2094)	grad_norm 2.3205 (2.2454)	
[2022-01-24 20:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][730/1251]	eta 0:19:12 lr 0.000157	time 1.9025 (2.2130)	loss 3.6124 (3.2082)	grad_norm 2.1320 (2.2445)	
[2022-01-24 20:47:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][740/1251]	eta 0:18:49 lr 0.000156	time 1.7977 (2.2110)	loss 2.5646 (3.2092)	grad_norm 1.9860 (2.2431)	
[2022-01-24 20:48:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][750/1251]	eta 0:18:27 lr 0.000156	time 1.8870 (2.2096)	loss 3.2911 (3.2068)	grad_norm 2.4119 (2.2442)	
[2022-01-24 20:48:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][760/1251]	eta 0:18:04 lr 0.000156	time 2.5953 (2.2086)	loss 3.5749 (3.2045)	grad_norm 2.1850 (2.2449)	
[2022-01-24 20:48:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][770/1251]	eta 0:17:41 lr 0.000156	time 2.1352 (2.2063)	loss 3.5632 (3.2032)	grad_norm 2.2439 (2.2457)	
[2022-01-24 20:49:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][780/1251]	eta 0:17:18 lr 0.000156	time 1.6925 (2.2047)	loss 3.4874 (3.2033)	grad_norm 2.2287 (2.2461)	
[2022-01-24 20:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][790/1251]	eta 0:16:56 lr 0.000156	time 1.8976 (2.2042)	loss 2.7109 (3.2018)	grad_norm 2.0841 (2.2456)	
[2022-01-24 20:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][800/1251]	eta 0:16:34 lr 0.000156	time 2.1349 (2.2043)	loss 2.5704 (3.2003)	grad_norm 1.8662 (2.2439)	
[2022-01-24 20:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][810/1251]	eta 0:16:12 lr 0.000156	time 2.8788 (2.2041)	loss 3.5362 (3.2009)	grad_norm 2.5290 (2.2438)	
[2022-01-24 20:50:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][820/1251]	eta 0:15:50 lr 0.000156	time 2.7758 (2.2047)	loss 2.8148 (3.2001)	grad_norm 2.2063 (2.2440)	
[2022-01-24 20:51:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][830/1251]	eta 0:15:28 lr 0.000156	time 2.4720 (2.2058)	loss 4.1346 (3.2031)	grad_norm 2.1238 (2.2433)	
[2022-01-24 20:51:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][840/1251]	eta 0:15:06 lr 0.000156	time 2.3289 (2.2063)	loss 2.4443 (3.2037)	grad_norm 1.9603 (2.2441)	
[2022-01-24 20:51:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][850/1251]	eta 0:14:45 lr 0.000156	time 3.1036 (2.2079)	loss 3.8499 (3.2059)	grad_norm 2.3891 (2.2445)	
[2022-01-24 20:52:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][860/1251]	eta 0:14:22 lr 0.000156	time 2.6720 (2.2071)	loss 3.4538 (3.2058)	grad_norm 2.2624 (2.2440)	
[2022-01-24 20:52:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][870/1251]	eta 0:14:00 lr 0.000156	time 2.2325 (2.2063)	loss 2.6315 (3.2068)	grad_norm 2.4672 (2.2440)	
[2022-01-24 20:52:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][880/1251]	eta 0:13:38 lr 0.000156	time 1.9031 (2.2066)	loss 3.6984 (3.2084)	grad_norm 2.1296 (2.2448)	
[2022-01-24 20:53:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][890/1251]	eta 0:13:16 lr 0.000156	time 2.3709 (2.2063)	loss 3.8531 (3.2090)	grad_norm 2.5151 (2.2441)	
[2022-01-24 20:53:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][900/1251]	eta 0:12:54 lr 0.000156	time 2.5766 (2.2060)	loss 3.4658 (3.2125)	grad_norm 1.8593 (2.2437)	
[2022-01-24 20:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][910/1251]	eta 0:12:32 lr 0.000156	time 2.5814 (2.2063)	loss 3.6657 (3.2098)	grad_norm 2.0041 (2.2434)	
[2022-01-24 20:54:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][920/1251]	eta 0:12:10 lr 0.000156	time 1.5628 (2.2063)	loss 3.5730 (3.2111)	grad_norm 2.1947 (2.2443)	
[2022-01-24 20:54:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][930/1251]	eta 0:11:47 lr 0.000156	time 1.5690 (2.2049)	loss 1.9627 (3.2079)	grad_norm 2.2111 (2.2448)	
[2022-01-24 20:55:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][940/1251]	eta 0:11:26 lr 0.000156	time 3.0909 (2.2074)	loss 2.5745 (3.2084)	grad_norm 2.1485 (2.2445)	
[2022-01-24 20:55:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][950/1251]	eta 0:11:03 lr 0.000156	time 1.9507 (2.2054)	loss 3.8904 (3.2120)	grad_norm 2.3543 (2.2450)	
[2022-01-24 20:55:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][960/1251]	eta 0:10:41 lr 0.000156	time 1.8529 (2.2040)	loss 3.5679 (3.2128)	grad_norm 1.9750 (2.2458)	
[2022-01-24 20:56:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][970/1251]	eta 0:10:19 lr 0.000156	time 2.1341 (2.2038)	loss 3.6331 (3.2110)	grad_norm 2.0507 (2.2459)	
[2022-01-24 20:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][980/1251]	eta 0:09:57 lr 0.000156	time 2.9688 (2.2051)	loss 3.8179 (3.2120)	grad_norm 2.0448 (2.2466)	
[2022-01-24 20:56:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][990/1251]	eta 0:09:35 lr 0.000156	time 1.7631 (2.2054)	loss 3.6421 (3.2139)	grad_norm 2.5381 (2.2466)	
[2022-01-24 20:57:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1000/1251]	eta 0:09:13 lr 0.000156	time 2.1523 (2.2071)	loss 3.5847 (3.2123)	grad_norm 2.2218 (2.2464)	
[2022-01-24 20:57:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1010/1251]	eta 0:08:51 lr 0.000156	time 1.5408 (2.2056)	loss 3.5332 (3.2120)	grad_norm 2.3850 (2.2466)	
[2022-01-24 20:57:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1020/1251]	eta 0:08:29 lr 0.000156	time 1.7754 (2.2035)	loss 4.1649 (3.2119)	grad_norm 2.0844 (2.2464)	
[2022-01-24 20:58:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1030/1251]	eta 0:08:06 lr 0.000156	time 2.5488 (2.2036)	loss 3.2098 (3.2108)	grad_norm 2.2338 (2.2457)	
[2022-01-24 20:58:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1040/1251]	eta 0:07:44 lr 0.000156	time 2.6439 (2.2037)	loss 3.5810 (3.2110)	grad_norm 2.4558 (2.2463)	
[2022-01-24 20:59:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1050/1251]	eta 0:07:22 lr 0.000156	time 1.8644 (2.2025)	loss 3.5529 (3.2120)	grad_norm 2.4194 (2.2476)	
[2022-01-24 20:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1060/1251]	eta 0:07:00 lr 0.000156	time 1.8865 (2.2011)	loss 3.3723 (3.2133)	grad_norm 2.6724 (2.2485)	
[2022-01-24 20:59:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1070/1251]	eta 0:06:38 lr 0.000156	time 1.8848 (2.2010)	loss 2.6322 (3.2098)	grad_norm 2.4890 (2.2479)	
[2022-01-24 21:00:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1080/1251]	eta 0:06:16 lr 0.000155	time 2.3649 (2.2011)	loss 3.2504 (3.2111)	grad_norm 2.7091 (2.2515)	
[2022-01-24 21:00:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1090/1251]	eta 0:05:54 lr 0.000155	time 1.6965 (2.2010)	loss 2.2356 (3.2094)	grad_norm 2.0993 (2.2510)	
[2022-01-24 21:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1100/1251]	eta 0:05:32 lr 0.000155	time 1.5821 (2.2001)	loss 3.5762 (3.2105)	grad_norm 2.2254 (2.2513)	
[2022-01-24 21:01:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1110/1251]	eta 0:05:10 lr 0.000155	time 1.9132 (2.1997)	loss 3.5792 (3.2095)	grad_norm 2.2419 (2.2514)	
[2022-01-24 21:01:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1120/1251]	eta 0:04:48 lr 0.000155	time 2.6252 (2.1999)	loss 3.6343 (3.2072)	grad_norm 2.2200 (2.2508)	
[2022-01-24 21:01:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1130/1251]	eta 0:04:26 lr 0.000155	time 2.0066 (2.1997)	loss 2.8782 (3.2064)	grad_norm 2.6225 (2.2528)	
[2022-01-24 21:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1140/1251]	eta 0:04:04 lr 0.000155	time 2.5786 (2.2008)	loss 2.5912 (3.2073)	grad_norm 2.1321 (2.2525)	
[2022-01-24 21:02:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1150/1251]	eta 0:03:42 lr 0.000155	time 2.1174 (2.2007)	loss 3.2308 (3.2085)	grad_norm 2.0586 (2.2526)	
[2022-01-24 21:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1160/1251]	eta 0:03:20 lr 0.000155	time 3.0375 (2.2019)	loss 3.5589 (3.2083)	grad_norm 2.0233 (2.2531)	
[2022-01-24 21:03:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1170/1251]	eta 0:02:58 lr 0.000155	time 1.9079 (2.2006)	loss 3.4246 (3.2102)	grad_norm 2.0038 (2.2532)	
[2022-01-24 21:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1180/1251]	eta 0:02:36 lr 0.000155	time 2.4288 (2.1995)	loss 2.3039 (3.2100)	grad_norm 2.7303 (2.2537)	
[2022-01-24 21:04:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1190/1251]	eta 0:02:14 lr 0.000155	time 1.6003 (2.1993)	loss 3.4620 (3.2084)	grad_norm 2.3334 (2.2563)	
[2022-01-24 21:04:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1200/1251]	eta 0:01:52 lr 0.000155	time 2.4863 (2.1997)	loss 3.7870 (3.2090)	grad_norm 1.9880 (2.2562)	
[2022-01-24 21:04:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1210/1251]	eta 0:01:30 lr 0.000155	time 2.1346 (2.1999)	loss 3.2118 (3.2094)	grad_norm 2.0995 (2.2559)	
[2022-01-24 21:05:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1220/1251]	eta 0:01:08 lr 0.000155	time 2.2297 (2.1992)	loss 2.2105 (3.2084)	grad_norm 1.9362 (2.2559)	
[2022-01-24 21:05:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1230/1251]	eta 0:00:46 lr 0.000155	time 1.9708 (2.1986)	loss 3.3203 (3.2076)	grad_norm 1.9860 (2.2564)	
[2022-01-24 21:05:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1240/1251]	eta 0:00:24 lr 0.000155	time 2.3118 (2.1969)	loss 3.2991 (3.2090)	grad_norm 2.2235 (2.2561)	
[2022-01-24 21:06:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [224/300][1250/1251]	eta 0:00:02 lr 0.000155	time 1.1695 (2.1913)	loss 2.4333 (3.2078)	grad_norm 2.0343 (2.2551)	
[2022-01-24 21:06:10 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 224 training takes 0:45:41
[2022-01-24 21:06:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.266 (18.266)	Loss 0.8687 (0.8687)	Acc@1 80.176 (80.176)	Acc@5 94.922 (94.922)	
[2022-01-24 21:06:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.248 (3.348)	Loss 0.8367 (0.8631)	Acc@1 79.980 (79.510)	Acc@5 96.191 (95.339)	
[2022-01-24 21:07:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.593 (2.505)	Loss 0.9022 (0.8733)	Acc@1 79.590 (79.488)	Acc@5 94.434 (95.061)	
[2022-01-24 21:07:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.646 (2.245)	Loss 0.8610 (0.8754)	Acc@1 78.906 (79.366)	Acc@5 95.215 (95.029)	
[2022-01-24 21:07:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.212 (2.204)	Loss 0.8697 (0.8742)	Acc@1 78.516 (79.349)	Acc@5 95.508 (95.034)	
[2022-01-24 21:07:48 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.408 Acc@5 95.042
[2022-01-24 21:07:48 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.4%
[2022-01-24 21:07:48 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.47%
[2022-01-24 21:08:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][0/1251]	eta 7:37:23 lr 0.000155	time 21.9372 (21.9372)	loss 2.5172 (2.5172)	grad_norm 2.2710 (2.2710)	
[2022-01-24 21:08:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][10/1251]	eta 1:24:15 lr 0.000155	time 1.6556 (4.0740)	loss 3.2099 (3.0797)	grad_norm 2.5376 (2.1313)	
[2022-01-24 21:08:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][20/1251]	eta 1:04:39 lr 0.000155	time 1.4744 (3.1516)	loss 3.0752 (2.9729)	grad_norm 2.1100 (2.1520)	
[2022-01-24 21:09:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][30/1251]	eta 0:57:20 lr 0.000155	time 1.3689 (2.8182)	loss 3.5352 (2.9152)	grad_norm 2.3735 (2.1651)	
[2022-01-24 21:09:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][40/1251]	eta 0:54:16 lr 0.000155	time 3.9623 (2.6892)	loss 3.3258 (2.9187)	grad_norm 2.1400 (2.1710)	
[2022-01-24 21:10:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][50/1251]	eta 0:52:09 lr 0.000155	time 2.1074 (2.6058)	loss 2.7331 (2.9585)	grad_norm 2.5033 (2.1802)	
[2022-01-24 21:10:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][60/1251]	eta 0:50:28 lr 0.000155	time 2.5098 (2.5432)	loss 2.5824 (3.0377)	grad_norm 2.6193 (2.2098)	
[2022-01-24 21:10:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][70/1251]	eta 0:48:37 lr 0.000155	time 1.5766 (2.4707)	loss 2.8406 (3.0289)	grad_norm 2.1321 (2.2189)	
[2022-01-24 21:11:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][80/1251]	eta 0:47:47 lr 0.000155	time 3.9351 (2.4486)	loss 3.1554 (3.0260)	grad_norm 2.2500 (2.2293)	
[2022-01-24 21:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][90/1251]	eta 0:47:05 lr 0.000155	time 3.0186 (2.4337)	loss 3.7929 (3.0573)	grad_norm 2.1829 (2.2401)	
[2022-01-24 21:11:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][100/1251]	eta 0:46:32 lr 0.000155	time 2.4512 (2.4260)	loss 3.1459 (3.0867)	grad_norm 2.2738 (2.2484)	
[2022-01-24 21:12:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][110/1251]	eta 0:45:47 lr 0.000155	time 1.8924 (2.4076)	loss 3.2402 (3.1013)	grad_norm 2.1443 (2.2596)	
[2022-01-24 21:12:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][120/1251]	eta 0:44:58 lr 0.000155	time 2.2178 (2.3857)	loss 3.0197 (3.1098)	grad_norm 2.4856 (2.2598)	
[2022-01-24 21:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][130/1251]	eta 0:44:19 lr 0.000155	time 3.0588 (2.3723)	loss 3.5664 (3.0997)	grad_norm 2.4288 (2.2542)	
[2022-01-24 21:13:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][140/1251]	eta 0:43:26 lr 0.000155	time 1.7024 (2.3458)	loss 3.1775 (3.0984)	grad_norm 2.1772 (2.2433)	
[2022-01-24 21:13:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][150/1251]	eta 0:42:40 lr 0.000155	time 2.2246 (2.3253)	loss 2.9747 (3.1067)	grad_norm 2.0309 (2.2389)	
[2022-01-24 21:14:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][160/1251]	eta 0:42:12 lr 0.000155	time 2.8322 (2.3214)	loss 2.3622 (3.1022)	grad_norm 2.1680 (2.2376)	
[2022-01-24 21:14:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][170/1251]	eta 0:41:39 lr 0.000154	time 2.1624 (2.3124)	loss 2.4123 (3.1098)	grad_norm 2.1442 (2.2394)	
[2022-01-24 21:14:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][180/1251]	eta 0:41:16 lr 0.000154	time 2.3598 (2.3122)	loss 3.5630 (3.1024)	grad_norm 2.2508 (2.2387)	
[2022-01-24 21:15:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][190/1251]	eta 0:40:45 lr 0.000154	time 2.1276 (2.3048)	loss 4.0711 (3.1088)	grad_norm 2.2392 (2.2388)	
[2022-01-24 21:15:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][200/1251]	eta 0:40:11 lr 0.000154	time 2.8284 (2.2941)	loss 3.3573 (3.1134)	grad_norm 2.2321 (2.2427)	
[2022-01-24 21:15:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][210/1251]	eta 0:39:32 lr 0.000154	time 1.8934 (2.2790)	loss 3.6923 (3.1205)	grad_norm 2.6301 (2.2417)	
[2022-01-24 21:16:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][220/1251]	eta 0:38:59 lr 0.000154	time 1.9079 (2.2693)	loss 2.1169 (3.1138)	grad_norm 2.4258 (2.2459)	
[2022-01-24 21:16:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][230/1251]	eta 0:38:33 lr 0.000154	time 3.1733 (2.2655)	loss 3.2878 (3.1204)	grad_norm 2.1891 (2.2468)	
[2022-01-24 21:16:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][240/1251]	eta 0:38:11 lr 0.000154	time 1.5211 (2.2666)	loss 3.5426 (3.1314)	grad_norm 2.0119 (2.2504)	
[2022-01-24 21:17:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][250/1251]	eta 0:37:47 lr 0.000154	time 1.8785 (2.2649)	loss 3.2781 (3.1312)	grad_norm 2.0223 (2.2482)	
[2022-01-24 21:17:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][260/1251]	eta 0:37:20 lr 0.000154	time 1.9499 (2.2605)	loss 2.4589 (3.1363)	grad_norm 2.3587 (2.2492)	
[2022-01-24 21:17:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][270/1251]	eta 0:36:52 lr 0.000154	time 2.6150 (2.2549)	loss 3.4720 (3.1362)	grad_norm 1.9771 (2.2515)	
[2022-01-24 21:18:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][280/1251]	eta 0:36:26 lr 0.000154	time 1.9243 (2.2521)	loss 3.6826 (3.1290)	grad_norm 2.3511 (2.2488)	
[2022-01-24 21:18:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][290/1251]	eta 0:36:02 lr 0.000154	time 2.4451 (2.2501)	loss 3.2762 (3.1315)	grad_norm 2.2662 (2.2445)	
[2022-01-24 21:19:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][300/1251]	eta 0:35:40 lr 0.000154	time 3.0149 (2.2509)	loss 2.2798 (3.1282)	grad_norm 1.8439 (2.2408)	
[2022-01-24 21:19:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][310/1251]	eta 0:35:16 lr 0.000154	time 2.4830 (2.2496)	loss 3.7071 (3.1191)	grad_norm 2.1410 (2.2389)	
[2022-01-24 21:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][320/1251]	eta 0:34:53 lr 0.000154	time 1.7862 (2.2491)	loss 3.0854 (3.1197)	grad_norm 1.9016 (2.2373)	
[2022-01-24 21:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][330/1251]	eta 0:34:30 lr 0.000154	time 2.5014 (2.2482)	loss 3.7746 (3.1143)	grad_norm 2.5567 (2.2400)	
[2022-01-24 21:20:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][340/1251]	eta 0:34:06 lr 0.000154	time 2.4969 (2.2464)	loss 3.1851 (3.1077)	grad_norm 2.1268 (2.2386)	
[2022-01-24 21:20:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][350/1251]	eta 0:33:40 lr 0.000154	time 2.8096 (2.2427)	loss 3.5156 (3.1099)	grad_norm 2.3001 (2.2359)	
[2022-01-24 21:21:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][360/1251]	eta 0:33:12 lr 0.000154	time 2.0232 (2.2368)	loss 3.7702 (3.1078)	grad_norm 2.2464 (2.2355)	
[2022-01-24 21:21:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][370/1251]	eta 0:32:46 lr 0.000154	time 1.6274 (2.2317)	loss 3.0494 (3.1035)	grad_norm 1.9185 (2.2352)	
[2022-01-24 21:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][380/1251]	eta 0:32:21 lr 0.000154	time 2.6016 (2.2287)	loss 2.4989 (3.1076)	grad_norm 2.4094 (2.2389)	
[2022-01-24 21:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][390/1251]	eta 0:31:56 lr 0.000154	time 1.8987 (2.2254)	loss 3.0191 (3.1142)	grad_norm 2.1944 (2.2419)	
[2022-01-24 21:22:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][400/1251]	eta 0:31:32 lr 0.000154	time 1.7719 (2.2237)	loss 3.4324 (3.1143)	grad_norm 1.9573 (2.2428)	
[2022-01-24 21:23:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][410/1251]	eta 0:31:11 lr 0.000154	time 1.8558 (2.2255)	loss 3.1084 (3.1161)	grad_norm 2.2535 (2.2438)	
[2022-01-24 21:23:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][420/1251]	eta 0:30:49 lr 0.000154	time 2.7218 (2.2256)	loss 3.1204 (3.1217)	grad_norm 2.0681 (2.2452)	
[2022-01-24 21:23:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][430/1251]	eta 0:30:26 lr 0.000154	time 2.5913 (2.2253)	loss 2.6909 (3.1241)	grad_norm 2.0856 (2.2444)	
[2022-01-24 21:24:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][440/1251]	eta 0:30:02 lr 0.000154	time 1.5857 (2.2224)	loss 2.5073 (3.1297)	grad_norm 2.4421 (2.2449)	
[2022-01-24 21:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][450/1251]	eta 0:29:40 lr 0.000154	time 1.9245 (2.2223)	loss 3.7279 (3.1299)	grad_norm 2.0935 (2.2424)	
[2022-01-24 21:24:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][460/1251]	eta 0:29:15 lr 0.000154	time 1.7212 (2.2194)	loss 3.2991 (3.1346)	grad_norm 3.0205 (2.2461)	
[2022-01-24 21:25:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][470/1251]	eta 0:28:54 lr 0.000154	time 2.7379 (2.2205)	loss 3.1777 (3.1323)	grad_norm 2.0750 (2.2437)	
[2022-01-24 21:25:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][480/1251]	eta 0:28:31 lr 0.000154	time 1.8820 (2.2203)	loss 3.5412 (3.1353)	grad_norm 2.2764 (2.2430)	
[2022-01-24 21:26:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][490/1251]	eta 0:28:12 lr 0.000154	time 3.1867 (2.2236)	loss 3.5538 (3.1364)	grad_norm 1.9745 (2.2406)	
[2022-01-24 21:26:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][500/1251]	eta 0:27:49 lr 0.000154	time 2.1970 (2.2224)	loss 3.4692 (3.1357)	grad_norm 2.0370 (2.2403)	
[2022-01-24 21:26:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][510/1251]	eta 0:27:29 lr 0.000153	time 3.9627 (2.2259)	loss 3.1338 (3.1332)	grad_norm 2.2103 (2.2407)	
[2022-01-24 21:27:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][520/1251]	eta 0:27:05 lr 0.000153	time 2.5431 (2.2231)	loss 3.7268 (3.1360)	grad_norm 2.5297 (2.2422)	
[2022-01-24 21:27:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][530/1251]	eta 0:26:40 lr 0.000153	time 2.1938 (2.2205)	loss 3.7984 (3.1365)	grad_norm 2.0802 (2.2416)	
[2022-01-24 21:27:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][540/1251]	eta 0:26:18 lr 0.000153	time 1.6236 (2.2202)	loss 4.0589 (3.1369)	grad_norm 2.2077 (2.2433)	
[2022-01-24 21:28:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][550/1251]	eta 0:25:55 lr 0.000153	time 2.5746 (2.2183)	loss 3.3464 (3.1413)	grad_norm 2.1296 (2.2416)	
[2022-01-24 21:28:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][560/1251]	eta 0:25:33 lr 0.000153	time 3.1333 (2.2193)	loss 2.4899 (3.1419)	grad_norm 2.2732 (2.2407)	
[2022-01-24 21:28:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][570/1251]	eta 0:25:09 lr 0.000153	time 1.5701 (2.2172)	loss 3.4111 (3.1449)	grad_norm 2.2990 (2.2416)	
[2022-01-24 21:29:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][580/1251]	eta 0:24:46 lr 0.000153	time 1.9212 (2.2155)	loss 3.5191 (3.1440)	grad_norm 2.5584 (2.2417)	
[2022-01-24 21:29:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][590/1251]	eta 0:24:22 lr 0.000153	time 1.6003 (2.2129)	loss 2.5716 (3.1446)	grad_norm 2.2916 (2.2403)	
[2022-01-24 21:29:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][600/1251]	eta 0:24:01 lr 0.000153	time 3.0716 (2.2136)	loss 2.3042 (3.1439)	grad_norm 2.3332 (2.2414)	
[2022-01-24 21:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][610/1251]	eta 0:23:36 lr 0.000153	time 1.6237 (2.2104)	loss 3.4052 (3.1454)	grad_norm 2.0647 (2.2422)	
[2022-01-24 21:30:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][620/1251]	eta 0:23:14 lr 0.000153	time 2.1351 (2.2094)	loss 3.1788 (3.1443)	grad_norm 2.2016 (2.2403)	
[2022-01-24 21:31:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][630/1251]	eta 0:22:54 lr 0.000153	time 2.1773 (2.2127)	loss 3.0718 (3.1451)	grad_norm 2.5279 (2.2404)	
[2022-01-24 21:31:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][640/1251]	eta 0:22:32 lr 0.000153	time 2.9507 (2.2143)	loss 3.7801 (3.1473)	grad_norm 2.1920 (2.2391)	
[2022-01-24 21:31:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][650/1251]	eta 0:22:11 lr 0.000153	time 2.1413 (2.2148)	loss 3.0765 (3.1477)	grad_norm 2.4026 (2.2372)	
[2022-01-24 21:32:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][660/1251]	eta 0:21:48 lr 0.000153	time 2.2665 (2.2133)	loss 2.9645 (3.1491)	grad_norm 2.2520 (2.2373)	
[2022-01-24 21:32:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][670/1251]	eta 0:21:26 lr 0.000153	time 1.6011 (2.2145)	loss 3.3754 (3.1540)	grad_norm 2.1468 (2.2377)	
[2022-01-24 21:32:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][680/1251]	eta 0:21:03 lr 0.000153	time 2.2214 (2.2123)	loss 2.7343 (3.1544)	grad_norm 2.6316 (2.2391)	
[2022-01-24 21:33:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][690/1251]	eta 0:20:40 lr 0.000153	time 1.7852 (2.2108)	loss 2.5113 (3.1578)	grad_norm 2.1319 (2.2393)	
[2022-01-24 21:33:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][700/1251]	eta 0:20:18 lr 0.000153	time 2.9070 (2.2110)	loss 1.9796 (3.1552)	grad_norm 2.2047 (2.2387)	
[2022-01-24 21:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][710/1251]	eta 0:19:55 lr 0.000153	time 1.9032 (2.2102)	loss 3.8424 (3.1582)	grad_norm 2.2142 (2.2396)	
[2022-01-24 21:34:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][720/1251]	eta 0:19:32 lr 0.000153	time 2.4516 (2.2087)	loss 3.7338 (3.1607)	grad_norm 2.3889 (2.2407)	
[2022-01-24 21:34:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][730/1251]	eta 0:19:10 lr 0.000153	time 1.9510 (2.2079)	loss 2.1193 (3.1592)	grad_norm 2.4018 (2.2420)	
[2022-01-24 21:35:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][740/1251]	eta 0:18:47 lr 0.000153	time 2.5589 (2.2073)	loss 2.8719 (3.1614)	grad_norm 2.2165 (2.2439)	
[2022-01-24 21:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][750/1251]	eta 0:18:26 lr 0.000153	time 1.7875 (2.2080)	loss 2.4633 (3.1615)	grad_norm 2.2896 (2.2452)	
[2022-01-24 21:35:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][760/1251]	eta 0:18:04 lr 0.000153	time 2.4644 (2.2092)	loss 3.4700 (3.1606)	grad_norm 2.2801 (2.2462)	
[2022-01-24 21:36:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][770/1251]	eta 0:17:41 lr 0.000153	time 1.7840 (2.2060)	loss 2.4290 (3.1580)	grad_norm 2.3776 (2.2468)	
[2022-01-24 21:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][780/1251]	eta 0:17:18 lr 0.000153	time 2.4045 (2.2042)	loss 3.1537 (3.1570)	grad_norm 2.1952 (2.2478)	
[2022-01-24 21:36:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][790/1251]	eta 0:16:56 lr 0.000153	time 2.7027 (2.2051)	loss 3.3955 (3.1577)	grad_norm 2.0543 (2.2465)	
[2022-01-24 21:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][800/1251]	eta 0:16:34 lr 0.000153	time 2.1873 (2.2044)	loss 3.4590 (3.1612)	grad_norm 2.1439 (2.2465)	
[2022-01-24 21:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][810/1251]	eta 0:16:12 lr 0.000153	time 2.1664 (2.2054)	loss 2.8414 (3.1648)	grad_norm 2.2266 (2.2470)	
[2022-01-24 21:37:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][820/1251]	eta 0:15:50 lr 0.000153	time 1.7884 (2.2057)	loss 2.6296 (3.1634)	grad_norm 2.2921 (2.2483)	
[2022-01-24 21:38:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][830/1251]	eta 0:15:29 lr 0.000153	time 1.8637 (2.2071)	loss 2.9431 (3.1635)	grad_norm 2.2553 (2.2487)	
[2022-01-24 21:38:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][840/1251]	eta 0:15:06 lr 0.000153	time 1.6746 (2.2061)	loss 3.5401 (3.1658)	grad_norm 2.2528 (2.2495)	
[2022-01-24 21:39:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][850/1251]	eta 0:14:44 lr 0.000153	time 2.7899 (2.2049)	loss 3.6551 (3.1684)	grad_norm 1.9455 (2.2487)	
[2022-01-24 21:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][860/1251]	eta 0:14:21 lr 0.000152	time 2.0600 (2.2025)	loss 2.6553 (3.1675)	grad_norm 1.9917 (2.2488)	
[2022-01-24 21:39:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][870/1251]	eta 0:13:59 lr 0.000152	time 1.8959 (2.2032)	loss 3.1654 (3.1670)	grad_norm 2.2162 (2.2485)	
[2022-01-24 21:40:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][880/1251]	eta 0:13:37 lr 0.000152	time 2.2200 (2.2041)	loss 3.5493 (3.1684)	grad_norm 2.1277 (2.2493)	
[2022-01-24 21:40:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][890/1251]	eta 0:13:16 lr 0.000152	time 1.9608 (2.2055)	loss 3.5044 (3.1663)	grad_norm 2.4473 (2.2499)	
[2022-01-24 21:40:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][900/1251]	eta 0:12:54 lr 0.000152	time 2.1532 (2.2074)	loss 2.4740 (3.1666)	grad_norm 2.1089 (2.2511)	
[2022-01-24 21:41:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][910/1251]	eta 0:12:32 lr 0.000152	time 1.8325 (2.2067)	loss 3.1758 (3.1688)	grad_norm 2.1091 (2.2545)	
[2022-01-24 21:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][920/1251]	eta 0:12:09 lr 0.000152	time 1.6091 (2.2035)	loss 3.3135 (3.1696)	grad_norm 2.1071 (2.2551)	
[2022-01-24 21:41:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][930/1251]	eta 0:11:46 lr 0.000152	time 2.2046 (2.2006)	loss 3.2104 (3.1709)	grad_norm 2.6143 (2.2558)	
[2022-01-24 21:42:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][940/1251]	eta 0:11:23 lr 0.000152	time 1.7977 (2.1993)	loss 3.2476 (3.1716)	grad_norm 2.3271 (2.2550)	
[2022-01-24 21:42:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][950/1251]	eta 0:11:02 lr 0.000152	time 2.5412 (2.1997)	loss 2.9145 (3.1727)	grad_norm 2.4870 (2.2548)	
[2022-01-24 21:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][960/1251]	eta 0:10:39 lr 0.000152	time 2.4910 (2.1985)	loss 2.8240 (3.1685)	grad_norm 1.9922 (2.2536)	
[2022-01-24 21:43:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][970/1251]	eta 0:10:17 lr 0.000152	time 2.5414 (2.1975)	loss 2.8067 (3.1695)	grad_norm 2.0789 (2.2547)	
[2022-01-24 21:43:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][980/1251]	eta 0:09:55 lr 0.000152	time 2.8079 (2.1977)	loss 3.9386 (3.1708)	grad_norm 2.3103 (2.2544)	
[2022-01-24 21:44:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][990/1251]	eta 0:09:34 lr 0.000152	time 2.0731 (2.1998)	loss 3.7059 (3.1707)	grad_norm 2.4401 (2.2551)	
[2022-01-24 21:44:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1000/1251]	eta 0:09:12 lr 0.000152	time 2.5862 (2.2005)	loss 2.9470 (3.1714)	grad_norm 2.3176 (2.2555)	
[2022-01-24 21:44:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1010/1251]	eta 0:08:50 lr 0.000152	time 2.9862 (2.2009)	loss 3.6293 (3.1730)	grad_norm 2.2035 (2.2543)	
[2022-01-24 21:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1020/1251]	eta 0:08:28 lr 0.000152	time 1.8679 (2.2000)	loss 3.2777 (3.1743)	grad_norm 2.1593 (2.2548)	
[2022-01-24 21:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1030/1251]	eta 0:08:06 lr 0.000152	time 2.5087 (2.1999)	loss 3.2079 (3.1734)	grad_norm 2.2534 (2.2539)	
[2022-01-24 21:45:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1040/1251]	eta 0:07:44 lr 0.000152	time 2.2309 (2.2013)	loss 3.3314 (3.1744)	grad_norm 2.0916 (2.2535)	
[2022-01-24 21:46:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1050/1251]	eta 0:07:23 lr 0.000152	time 3.1519 (2.2040)	loss 3.1618 (3.1758)	grad_norm 2.3098 (2.2538)	
[2022-01-24 21:46:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1060/1251]	eta 0:07:00 lr 0.000152	time 1.5507 (2.2033)	loss 3.0608 (3.1749)	grad_norm 2.2578 (2.2553)	
[2022-01-24 21:47:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1070/1251]	eta 0:06:38 lr 0.000152	time 1.9176 (2.2021)	loss 3.7353 (3.1760)	grad_norm 2.2143 (2.2548)	
[2022-01-24 21:47:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1080/1251]	eta 0:06:16 lr 0.000152	time 1.9619 (2.2005)	loss 3.5446 (3.1788)	grad_norm 2.1683 (2.2562)	
[2022-01-24 21:47:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1090/1251]	eta 0:05:54 lr 0.000152	time 2.9641 (2.2000)	loss 3.7130 (3.1795)	grad_norm 2.1167 (2.2560)	
[2022-01-24 21:48:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1100/1251]	eta 0:05:32 lr 0.000152	time 2.3609 (2.2003)	loss 3.3183 (3.1797)	grad_norm 2.0416 (2.2551)	
[2022-01-24 21:48:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1110/1251]	eta 0:05:10 lr 0.000152	time 2.2007 (2.2009)	loss 2.1088 (3.1790)	grad_norm 2.1969 (2.2544)	
[2022-01-24 21:48:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1120/1251]	eta 0:04:48 lr 0.000152	time 2.5029 (2.2018)	loss 2.9401 (3.1786)	grad_norm 2.2506 (2.2539)	
[2022-01-24 21:49:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1130/1251]	eta 0:04:26 lr 0.000152	time 2.2464 (2.2007)	loss 3.5367 (3.1789)	grad_norm 2.2714 (2.2556)	
[2022-01-24 21:49:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1140/1251]	eta 0:04:04 lr 0.000152	time 2.1864 (2.1996)	loss 2.8355 (3.1759)	grad_norm 2.2682 (2.2558)	
[2022-01-24 21:49:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1150/1251]	eta 0:03:42 lr 0.000152	time 2.2485 (2.1988)	loss 3.7355 (3.1781)	grad_norm 2.1679 (2.2561)	
[2022-01-24 21:50:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1160/1251]	eta 0:03:19 lr 0.000152	time 2.1983 (2.1978)	loss 3.5879 (3.1811)	grad_norm 2.3033 (2.2563)	
[2022-01-24 21:50:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1170/1251]	eta 0:02:57 lr 0.000152	time 1.7322 (2.1957)	loss 3.7959 (3.1796)	grad_norm 2.1746 (2.2557)	
[2022-01-24 21:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1180/1251]	eta 0:02:35 lr 0.000152	time 2.2913 (2.1954)	loss 3.4601 (3.1808)	grad_norm 2.1765 (2.2566)	
[2022-01-24 21:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1190/1251]	eta 0:02:13 lr 0.000152	time 2.3796 (2.1950)	loss 3.7152 (3.1809)	grad_norm 2.2815 (2.2564)	
[2022-01-24 21:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1200/1251]	eta 0:01:51 lr 0.000151	time 2.3646 (2.1953)	loss 3.5766 (3.1802)	grad_norm 2.0967 (2.2564)	
[2022-01-24 21:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1210/1251]	eta 0:01:29 lr 0.000151	time 2.1363 (2.1951)	loss 2.2195 (3.1793)	grad_norm 2.1270 (2.2564)	
[2022-01-24 21:52:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1220/1251]	eta 0:01:08 lr 0.000151	time 3.3053 (2.1971)	loss 3.4564 (3.1796)	grad_norm 2.3111 (2.2582)	
[2022-01-24 21:52:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1230/1251]	eta 0:00:46 lr 0.000151	time 2.2694 (2.1981)	loss 2.8528 (3.1783)	grad_norm 2.2860 (2.2587)	
[2022-01-24 21:53:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1240/1251]	eta 0:00:24 lr 0.000151	time 1.7601 (2.1976)	loss 3.2459 (3.1808)	grad_norm 2.0774 (2.2598)	
[2022-01-24 21:53:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [225/300][1250/1251]	eta 0:00:02 lr 0.000151	time 1.3302 (2.1926)	loss 3.7087 (3.1814)	grad_norm 2.4755 (2.2601)	
[2022-01-24 21:53:31 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 225 training takes 0:45:43
[2022-01-24 21:53:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.620 (18.620)	Loss 0.8211 (0.8211)	Acc@1 80.566 (80.566)	Acc@5 95.801 (95.801)	
[2022-01-24 21:54:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.942 (3.547)	Loss 0.9401 (0.8640)	Acc@1 77.734 (79.545)	Acc@5 93.848 (94.886)	
[2022-01-24 21:54:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.545 (2.711)	Loss 0.8953 (0.8625)	Acc@1 77.734 (79.590)	Acc@5 95.215 (94.899)	
[2022-01-24 21:54:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.922 (2.331)	Loss 0.9125 (0.8685)	Acc@1 79.395 (79.458)	Acc@5 93.262 (94.824)	
[2022-01-24 21:55:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.249 (2.236)	Loss 0.9060 (0.8675)	Acc@1 77.344 (79.445)	Acc@5 94.238 (94.815)	
[2022-01-24 21:55:10 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.476 Acc@5 94.864
[2022-01-24 21:55:10 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.5%
[2022-01-24 21:55:10 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.48%
[2022-01-24 21:55:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][0/1251]	eta 7:24:49 lr 0.000151	time 21.3346 (21.3346)	loss 3.6159 (3.6159)	grad_norm 2.6968 (2.6968)	
[2022-01-24 21:55:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][10/1251]	eta 1:22:17 lr 0.000151	time 1.5255 (3.9783)	loss 3.2595 (3.1271)	grad_norm 2.3097 (2.1910)	
[2022-01-24 21:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][20/1251]	eta 1:05:21 lr 0.000151	time 1.3379 (3.1857)	loss 2.6081 (3.0377)	grad_norm 2.2824 (2.2430)	
[2022-01-24 21:56:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][30/1251]	eta 0:57:05 lr 0.000151	time 1.5052 (2.8053)	loss 2.5649 (3.1250)	grad_norm 2.5818 (2.2820)	
[2022-01-24 21:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][40/1251]	eta 0:54:45 lr 0.000151	time 3.6788 (2.7128)	loss 3.8672 (3.1503)	grad_norm 2.1562 (2.2736)	
[2022-01-24 21:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][50/1251]	eta 0:52:54 lr 0.000151	time 2.8368 (2.6433)	loss 3.4749 (3.1871)	grad_norm 2.0072 (2.2702)	
[2022-01-24 21:57:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][60/1251]	eta 0:51:03 lr 0.000151	time 2.0382 (2.5721)	loss 2.9982 (3.1304)	grad_norm 2.0189 (2.2483)	
[2022-01-24 21:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][70/1251]	eta 0:49:15 lr 0.000151	time 1.6539 (2.5024)	loss 3.1856 (3.1595)	grad_norm 3.2571 (2.2528)	
[2022-01-24 21:58:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][80/1251]	eta 0:48:21 lr 0.000151	time 3.0945 (2.4780)	loss 3.6879 (3.1699)	grad_norm 2.5812 (2.2579)	
[2022-01-24 21:58:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][90/1251]	eta 0:47:26 lr 0.000151	time 1.8883 (2.4522)	loss 3.5935 (3.1978)	grad_norm 2.4856 (2.2512)	
[2022-01-24 21:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][100/1251]	eta 0:46:18 lr 0.000151	time 2.0053 (2.4142)	loss 2.4958 (3.1790)	grad_norm 2.2553 (2.2642)	
[2022-01-24 21:59:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][110/1251]	eta 0:45:25 lr 0.000151	time 1.5809 (2.3884)	loss 3.5022 (3.1885)	grad_norm 2.2622 (2.2599)	
[2022-01-24 21:59:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][120/1251]	eta 0:44:49 lr 0.000151	time 2.1840 (2.3782)	loss 3.6468 (3.2029)	grad_norm 2.5216 (2.2661)	
[2022-01-24 22:00:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][130/1251]	eta 0:44:19 lr 0.000151	time 1.9189 (2.3725)	loss 3.2761 (3.1927)	grad_norm 2.0901 (2.2586)	
[2022-01-24 22:00:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][140/1251]	eta 0:43:29 lr 0.000151	time 1.9207 (2.3486)	loss 2.7103 (3.1992)	grad_norm 2.3802 (2.2607)	
[2022-01-24 22:01:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][150/1251]	eta 0:42:42 lr 0.000151	time 2.1046 (2.3273)	loss 2.7279 (3.1895)	grad_norm 2.1589 (2.2642)	
[2022-01-24 22:01:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][160/1251]	eta 0:42:24 lr 0.000151	time 2.0377 (2.3323)	loss 3.8213 (3.1929)	grad_norm 2.2024 (2.2604)	
[2022-01-24 22:01:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][170/1251]	eta 0:42:02 lr 0.000151	time 2.1686 (2.3331)	loss 3.4436 (3.2045)	grad_norm 2.6978 (2.2629)	
[2022-01-24 22:02:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][180/1251]	eta 0:41:35 lr 0.000151	time 1.8496 (2.3297)	loss 3.3406 (3.2043)	grad_norm 2.6943 (2.2635)	
[2022-01-24 22:02:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][190/1251]	eta 0:40:54 lr 0.000151	time 1.6368 (2.3137)	loss 3.5228 (3.1954)	grad_norm 2.1198 (2.2718)	
[2022-01-24 22:02:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][200/1251]	eta 0:40:13 lr 0.000151	time 1.9174 (2.2964)	loss 3.7752 (3.1944)	grad_norm 2.4126 (2.2787)	
[2022-01-24 22:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][210/1251]	eta 0:39:31 lr 0.000151	time 2.2479 (2.2785)	loss 2.5228 (3.1767)	grad_norm 1.9404 (2.2745)	
[2022-01-24 22:03:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][220/1251]	eta 0:38:57 lr 0.000151	time 2.4742 (2.2676)	loss 3.1048 (3.1685)	grad_norm 2.2602 (2.2749)	
[2022-01-24 22:03:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][230/1251]	eta 0:38:30 lr 0.000151	time 2.1644 (2.2627)	loss 3.3096 (3.1729)	grad_norm 2.5772 (2.2805)	
[2022-01-24 22:04:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][240/1251]	eta 0:38:08 lr 0.000151	time 2.0164 (2.2638)	loss 3.9213 (3.1771)	grad_norm 2.7685 (2.2836)	
[2022-01-24 22:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][250/1251]	eta 0:37:42 lr 0.000151	time 1.9065 (2.2598)	loss 3.3657 (3.1776)	grad_norm 2.1007 (2.2811)	
[2022-01-24 22:05:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][260/1251]	eta 0:37:23 lr 0.000151	time 2.3378 (2.2639)	loss 2.8274 (3.1720)	grad_norm 1.9851 (2.2798)	
[2022-01-24 22:05:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][270/1251]	eta 0:37:08 lr 0.000151	time 2.2086 (2.2717)	loss 3.4712 (3.1740)	grad_norm 2.1539 (2.2817)	
[2022-01-24 22:05:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][280/1251]	eta 0:36:49 lr 0.000151	time 2.4197 (2.2758)	loss 3.9139 (3.1835)	grad_norm 2.0705 (2.2791)	
[2022-01-24 22:06:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][290/1251]	eta 0:36:22 lr 0.000150	time 1.8682 (2.2716)	loss 2.4352 (3.1753)	grad_norm 2.4409 (2.2807)	
[2022-01-24 22:06:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][300/1251]	eta 0:35:51 lr 0.000150	time 1.9477 (2.2627)	loss 3.3089 (3.1796)	grad_norm 2.0859 (2.2781)	
[2022-01-24 22:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][310/1251]	eta 0:35:17 lr 0.000150	time 1.9828 (2.2502)	loss 3.4685 (3.1857)	grad_norm 2.4747 (2.2788)	
[2022-01-24 22:07:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][320/1251]	eta 0:34:47 lr 0.000150	time 1.8791 (2.2419)	loss 3.5266 (3.1896)	grad_norm 2.0780 (2.2798)	
[2022-01-24 22:07:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][330/1251]	eta 0:34:19 lr 0.000150	time 2.1587 (2.2366)	loss 3.0724 (3.1848)	grad_norm 2.2906 (2.2793)	
[2022-01-24 22:07:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][340/1251]	eta 0:33:53 lr 0.000150	time 1.6346 (2.2327)	loss 2.3298 (3.1778)	grad_norm 1.9987 (2.2781)	
[2022-01-24 22:08:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][350/1251]	eta 0:33:28 lr 0.000150	time 2.1503 (2.2297)	loss 3.8178 (3.1849)	grad_norm 2.2568 (2.2782)	
[2022-01-24 22:08:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][360/1251]	eta 0:33:19 lr 0.000150	time 2.8444 (2.2446)	loss 3.7472 (3.1849)	grad_norm 2.0461 (2.2805)	
[2022-01-24 22:09:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][370/1251]	eta 0:33:06 lr 0.000150	time 2.5177 (2.2550)	loss 3.5413 (3.1832)	grad_norm 2.5129 (2.2814)	
[2022-01-24 22:09:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][380/1251]	eta 0:32:41 lr 0.000150	time 1.4766 (2.2515)	loss 3.3629 (3.1768)	grad_norm 2.1518 (2.2792)	
[2022-01-24 22:09:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][390/1251]	eta 0:32:14 lr 0.000150	time 1.8092 (2.2471)	loss 3.4140 (3.1797)	grad_norm 2.3427 (2.2792)	
[2022-01-24 22:10:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][400/1251]	eta 0:31:49 lr 0.000150	time 1.9112 (2.2433)	loss 3.3420 (3.1858)	grad_norm 2.1332 (2.2779)	
[2022-01-24 22:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][410/1251]	eta 0:31:21 lr 0.000150	time 1.8436 (2.2371)	loss 3.1716 (3.1897)	grad_norm 2.4099 (2.2774)	
[2022-01-24 22:10:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][420/1251]	eta 0:31:01 lr 0.000150	time 1.9081 (2.2402)	loss 3.4321 (3.1894)	grad_norm 1.9536 (2.2739)	
[2022-01-24 22:11:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][430/1251]	eta 0:30:37 lr 0.000150	time 1.9533 (2.2380)	loss 3.7148 (3.1904)	grad_norm 2.4889 (2.2730)	
[2022-01-24 22:11:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][440/1251]	eta 0:30:16 lr 0.000150	time 2.1840 (2.2395)	loss 3.0959 (3.1899)	grad_norm 2.4400 (2.2835)	
[2022-01-24 22:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][450/1251]	eta 0:29:51 lr 0.000150	time 1.9034 (2.2370)	loss 3.0116 (3.1902)	grad_norm 2.2106 (2.2851)	
[2022-01-24 22:12:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][460/1251]	eta 0:29:26 lr 0.000150	time 1.6676 (2.2336)	loss 3.5829 (3.1913)	grad_norm 2.9512 (2.2863)	
[2022-01-24 22:12:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][470/1251]	eta 0:29:03 lr 0.000150	time 1.4844 (2.2327)	loss 3.5968 (3.1979)	grad_norm 2.3202 (2.2866)	
[2022-01-24 22:13:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][480/1251]	eta 0:28:43 lr 0.000150	time 2.1657 (2.2358)	loss 3.7678 (3.1931)	grad_norm 2.5115 (2.2867)	
[2022-01-24 22:13:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][490/1251]	eta 0:28:19 lr 0.000150	time 2.2448 (2.2337)	loss 2.4183 (3.1848)	grad_norm 2.2816 (2.2885)	
[2022-01-24 22:13:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][500/1251]	eta 0:27:56 lr 0.000150	time 2.2914 (2.2329)	loss 3.3503 (3.1887)	grad_norm 2.0491 (2.2866)	
[2022-01-24 22:14:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][510/1251]	eta 0:27:31 lr 0.000150	time 1.5442 (2.2292)	loss 2.3968 (3.1795)	grad_norm 2.1713 (2.2849)	
[2022-01-24 22:14:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][520/1251]	eta 0:27:09 lr 0.000150	time 1.8812 (2.2297)	loss 2.7455 (3.1799)	grad_norm 2.1711 (2.2874)	
[2022-01-24 22:14:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][530/1251]	eta 0:26:47 lr 0.000150	time 1.5395 (2.2298)	loss 4.0097 (3.1772)	grad_norm 2.3949 (2.2884)	
[2022-01-24 22:15:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][540/1251]	eta 0:26:23 lr 0.000150	time 2.3113 (2.2275)	loss 3.8834 (3.1748)	grad_norm 2.5227 (2.2907)	
[2022-01-24 22:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][550/1251]	eta 0:25:59 lr 0.000150	time 1.5879 (2.2249)	loss 3.6419 (3.1748)	grad_norm 2.1729 (2.2898)	
[2022-01-24 22:15:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][560/1251]	eta 0:25:35 lr 0.000150	time 2.0300 (2.2227)	loss 3.9047 (3.1768)	grad_norm 2.7006 (2.2927)	
[2022-01-24 22:16:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][570/1251]	eta 0:25:13 lr 0.000150	time 1.9971 (2.2221)	loss 2.8217 (3.1812)	grad_norm 2.3183 (2.2971)	
[2022-01-24 22:16:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][580/1251]	eta 0:24:49 lr 0.000150	time 1.9535 (2.2205)	loss 2.5002 (3.1797)	grad_norm 2.2203 (2.2979)	
[2022-01-24 22:17:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][590/1251]	eta 0:24:27 lr 0.000150	time 2.2131 (2.2206)	loss 3.3747 (3.1818)	grad_norm 2.0898 (2.2972)	
[2022-01-24 22:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][600/1251]	eta 0:24:04 lr 0.000150	time 2.2531 (2.2195)	loss 3.2611 (3.1782)	grad_norm 2.0031 (2.2977)	
[2022-01-24 22:17:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][610/1251]	eta 0:23:41 lr 0.000150	time 1.5669 (2.2181)	loss 3.5230 (3.1812)	grad_norm 2.3499 (2.2981)	
[2022-01-24 22:18:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][620/1251]	eta 0:23:19 lr 0.000150	time 2.6695 (2.2186)	loss 3.7209 (3.1792)	grad_norm 1.9306 (2.2957)	
[2022-01-24 22:18:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][630/1251]	eta 0:22:56 lr 0.000150	time 1.5333 (2.2160)	loss 3.5308 (3.1812)	grad_norm 2.6065 (2.2957)	
[2022-01-24 22:18:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][640/1251]	eta 0:22:33 lr 0.000149	time 2.2203 (2.2155)	loss 2.5690 (3.1840)	grad_norm 2.3392 (2.2956)	
[2022-01-24 22:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][650/1251]	eta 0:22:11 lr 0.000149	time 1.5911 (2.2155)	loss 3.3742 (3.1851)	grad_norm 2.2027 (2.2970)	
[2022-01-24 22:19:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][660/1251]	eta 0:21:50 lr 0.000149	time 2.9585 (2.2173)	loss 3.2400 (3.1853)	grad_norm 1.9557 (2.2972)	
[2022-01-24 22:19:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][670/1251]	eta 0:21:28 lr 0.000149	time 1.6418 (2.2172)	loss 2.9579 (3.1838)	grad_norm 2.2159 (2.2990)	
[2022-01-24 22:20:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][680/1251]	eta 0:21:06 lr 0.000149	time 2.2063 (2.2182)	loss 3.0744 (3.1833)	grad_norm 2.2964 (2.3000)	
[2022-01-24 22:20:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][690/1251]	eta 0:20:44 lr 0.000149	time 1.8786 (2.2187)	loss 2.7170 (3.1817)	grad_norm 2.7300 (2.2996)	
[2022-01-24 22:21:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][700/1251]	eta 0:20:21 lr 0.000149	time 1.8799 (2.2168)	loss 3.0098 (3.1845)	grad_norm 1.9129 (2.2994)	
[2022-01-24 22:21:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][710/1251]	eta 0:19:58 lr 0.000149	time 1.5899 (2.2147)	loss 2.9711 (3.1822)	grad_norm 2.3701 (2.2989)	
[2022-01-24 22:21:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][720/1251]	eta 0:19:35 lr 0.000149	time 1.9797 (2.2133)	loss 3.4606 (3.1844)	grad_norm 2.2211 (2.2970)	
[2022-01-24 22:22:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][730/1251]	eta 0:19:15 lr 0.000149	time 2.1138 (2.2173)	loss 2.8452 (3.1854)	grad_norm 2.4160 (2.2986)	
[2022-01-24 22:22:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][740/1251]	eta 0:18:52 lr 0.000149	time 1.9192 (2.2162)	loss 3.7178 (3.1844)	grad_norm 2.0974 (2.2989)	
[2022-01-24 22:22:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][750/1251]	eta 0:18:30 lr 0.000149	time 1.6091 (2.2165)	loss 3.6131 (3.1880)	grad_norm 2.5331 (2.2986)	
[2022-01-24 22:23:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][760/1251]	eta 0:18:07 lr 0.000149	time 1.7229 (2.2143)	loss 3.7344 (3.1928)	grad_norm 2.2200 (2.3005)	
[2022-01-24 22:23:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][770/1251]	eta 0:17:44 lr 0.000149	time 1.9124 (2.2131)	loss 3.5637 (3.1956)	grad_norm 2.0302 (2.3026)	
[2022-01-24 22:24:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][780/1251]	eta 0:17:23 lr 0.000149	time 2.1689 (2.2152)	loss 4.0137 (3.2002)	grad_norm 2.6450 (2.3032)	
[2022-01-24 22:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][790/1251]	eta 0:17:01 lr 0.000149	time 2.1992 (2.2161)	loss 3.5648 (3.1987)	grad_norm 2.3260 (2.3056)	
[2022-01-24 22:24:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][800/1251]	eta 0:16:38 lr 0.000149	time 1.9075 (2.2147)	loss 3.6751 (3.1981)	grad_norm 2.2751 (2.3057)	
[2022-01-24 22:25:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][810/1251]	eta 0:16:16 lr 0.000149	time 1.9069 (2.2152)	loss 3.3833 (3.1990)	grad_norm 2.1533 (2.3059)	
[2022-01-24 22:25:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][820/1251]	eta 0:15:54 lr 0.000149	time 1.6095 (2.2146)	loss 3.7516 (3.1983)	grad_norm 2.4488 (2.3107)	
[2022-01-24 22:25:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][830/1251]	eta 0:15:31 lr 0.000149	time 2.1338 (2.2137)	loss 4.1143 (3.2014)	grad_norm 2.7887 (2.3120)	
[2022-01-24 22:26:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][840/1251]	eta 0:15:09 lr 0.000149	time 1.8923 (2.2136)	loss 3.5707 (3.2033)	grad_norm 2.3194 (2.3110)	
[2022-01-24 22:26:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][850/1251]	eta 0:14:47 lr 0.000149	time 1.9140 (2.2123)	loss 3.5701 (3.2046)	grad_norm 1.8035 (2.3088)	
[2022-01-24 22:26:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][860/1251]	eta 0:14:24 lr 0.000149	time 1.6728 (2.2110)	loss 3.7495 (3.2052)	grad_norm 2.6223 (2.3076)	
[2022-01-24 22:27:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][870/1251]	eta 0:14:01 lr 0.000149	time 2.0588 (2.2096)	loss 3.3096 (3.2081)	grad_norm 2.2244 (2.3082)	
[2022-01-24 22:27:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][880/1251]	eta 0:13:38 lr 0.000149	time 1.9509 (2.2069)	loss 2.0632 (3.2087)	grad_norm 2.1757 (2.3075)	
[2022-01-24 22:27:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][890/1251]	eta 0:13:16 lr 0.000149	time 1.8386 (2.2065)	loss 3.2360 (3.2100)	grad_norm 2.4963 (2.3083)	
[2022-01-24 22:28:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][900/1251]	eta 0:12:54 lr 0.000149	time 2.4804 (2.2071)	loss 3.0243 (3.2125)	grad_norm 1.9241 (2.3082)	
[2022-01-24 22:28:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][910/1251]	eta 0:12:32 lr 0.000149	time 2.5686 (2.2077)	loss 3.5748 (3.2152)	grad_norm 2.0658 (2.3089)	
[2022-01-24 22:29:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][920/1251]	eta 0:12:10 lr 0.000149	time 2.8231 (2.2081)	loss 3.6176 (3.2139)	grad_norm 2.1157 (2.3073)	
[2022-01-24 22:29:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][930/1251]	eta 0:11:49 lr 0.000149	time 2.0120 (2.2091)	loss 3.2403 (3.2134)	grad_norm 2.1427 (2.3069)	
[2022-01-24 22:29:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][940/1251]	eta 0:11:27 lr 0.000149	time 2.4447 (2.2091)	loss 3.0322 (3.2134)	grad_norm 2.3121 (2.3072)	
[2022-01-24 22:30:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][950/1251]	eta 0:11:04 lr 0.000149	time 2.4737 (2.2085)	loss 3.1044 (3.2111)	grad_norm 1.8875 (2.3059)	
[2022-01-24 22:30:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][960/1251]	eta 0:10:43 lr 0.000149	time 3.1052 (2.2099)	loss 3.4460 (3.2106)	grad_norm 2.0188 (2.3062)	
[2022-01-24 22:30:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][970/1251]	eta 0:10:20 lr 0.000149	time 2.1645 (2.2093)	loss 2.2392 (3.2100)	grad_norm 2.9642 (2.3068)	
[2022-01-24 22:31:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][980/1251]	eta 0:09:58 lr 0.000149	time 2.0042 (2.2083)	loss 3.3457 (3.2113)	grad_norm 2.4226 (2.3064)	
[2022-01-24 22:31:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][990/1251]	eta 0:09:36 lr 0.000148	time 1.6882 (2.2071)	loss 2.5618 (3.2109)	grad_norm 2.1955 (2.3053)	
[2022-01-24 22:31:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1000/1251]	eta 0:09:14 lr 0.000148	time 2.6932 (2.2075)	loss 2.6194 (3.2108)	grad_norm 2.2991 (2.3049)	
[2022-01-24 22:32:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1010/1251]	eta 0:08:51 lr 0.000148	time 1.9592 (2.2067)	loss 3.3157 (3.2111)	grad_norm 2.2459 (2.3050)	
[2022-01-24 22:32:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1020/1251]	eta 0:08:29 lr 0.000148	time 2.2926 (2.2071)	loss 2.1675 (3.2117)	grad_norm 2.2412 (2.3041)	
[2022-01-24 22:33:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1030/1251]	eta 0:08:07 lr 0.000148	time 1.6580 (2.2062)	loss 3.4466 (3.2110)	grad_norm 2.1994 (2.3033)	
[2022-01-24 22:33:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1040/1251]	eta 0:07:45 lr 0.000148	time 2.5057 (2.2071)	loss 3.0394 (3.2107)	grad_norm 2.9067 (2.3040)	
[2022-01-24 22:33:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1050/1251]	eta 0:07:23 lr 0.000148	time 2.4402 (2.2072)	loss 3.6785 (3.2098)	grad_norm 2.5231 (2.3034)	
[2022-01-24 22:34:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1060/1251]	eta 0:07:01 lr 0.000148	time 2.2868 (2.2061)	loss 3.8176 (3.2088)	grad_norm 2.3048 (2.3029)	
[2022-01-24 22:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1070/1251]	eta 0:06:39 lr 0.000148	time 2.7800 (2.2054)	loss 3.1520 (3.2077)	grad_norm 2.2312 (2.3038)	
[2022-01-24 22:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1080/1251]	eta 0:06:17 lr 0.000148	time 1.4725 (2.2055)	loss 2.1403 (3.2060)	grad_norm 2.4693 (2.3037)	
[2022-01-24 22:35:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1090/1251]	eta 0:05:55 lr 0.000148	time 1.8910 (2.2057)	loss 2.7696 (3.2065)	grad_norm 2.0202 (2.3034)	
[2022-01-24 22:35:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1100/1251]	eta 0:05:33 lr 0.000148	time 2.7268 (2.2058)	loss 3.7101 (3.2075)	grad_norm 2.1062 (2.3032)	
[2022-01-24 22:36:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1110/1251]	eta 0:05:10 lr 0.000148	time 2.0277 (2.2054)	loss 3.8753 (3.2076)	grad_norm 2.0035 (2.3023)	
[2022-01-24 22:36:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1120/1251]	eta 0:04:48 lr 0.000148	time 1.6204 (2.2048)	loss 3.1936 (3.2071)	grad_norm 2.4909 (2.3014)	
[2022-01-24 22:36:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1130/1251]	eta 0:04:26 lr 0.000148	time 2.0865 (2.2038)	loss 3.6467 (3.2066)	grad_norm 2.2664 (2.3026)	
[2022-01-24 22:37:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1140/1251]	eta 0:04:04 lr 0.000148	time 3.2360 (2.2044)	loss 3.4979 (3.2061)	grad_norm 2.2038 (2.3022)	
[2022-01-24 22:37:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1150/1251]	eta 0:03:42 lr 0.000148	time 2.7710 (2.2047)	loss 3.4819 (3.2064)	grad_norm 2.5226 (2.3021)	
[2022-01-24 22:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1160/1251]	eta 0:03:20 lr 0.000148	time 2.1628 (2.2037)	loss 3.6185 (3.2057)	grad_norm 2.1887 (2.3026)	
[2022-01-24 22:38:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1170/1251]	eta 0:02:58 lr 0.000148	time 2.1542 (2.2030)	loss 3.0943 (3.2056)	grad_norm 1.9498 (2.3029)	
[2022-01-24 22:38:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1180/1251]	eta 0:02:36 lr 0.000148	time 2.6891 (2.2031)	loss 3.6754 (3.2074)	grad_norm 2.0213 (2.3034)	
[2022-01-24 22:38:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1190/1251]	eta 0:02:14 lr 0.000148	time 1.9382 (2.2032)	loss 3.4913 (3.2068)	grad_norm 2.2893 (2.3035)	
[2022-01-24 22:39:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1200/1251]	eta 0:01:52 lr 0.000148	time 2.2063 (2.2019)	loss 3.5585 (3.2077)	grad_norm 2.4134 (2.3051)	
[2022-01-24 22:39:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1210/1251]	eta 0:01:30 lr 0.000148	time 2.8111 (2.2020)	loss 3.7559 (3.2069)	grad_norm 2.0981 (2.3048)	
[2022-01-24 22:40:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1220/1251]	eta 0:01:08 lr 0.000148	time 2.7006 (2.2032)	loss 3.2827 (3.2079)	grad_norm 2.3927 (2.3062)	
[2022-01-24 22:40:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1230/1251]	eta 0:00:46 lr 0.000148	time 1.8460 (2.2027)	loss 3.5041 (3.2072)	grad_norm 2.5793 (2.3080)	
[2022-01-24 22:40:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1240/1251]	eta 0:00:24 lr 0.000148	time 1.8960 (2.2019)	loss 3.2991 (3.2079)	grad_norm 2.3238 (2.3087)	
[2022-01-24 22:40:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [226/300][1250/1251]	eta 0:00:02 lr 0.000148	time 1.1989 (2.1973)	loss 3.1709 (3.2087)	grad_norm 1.9571 (2.3075)	
[2022-01-24 22:40:59 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 226 training takes 0:45:49
[2022-01-24 22:41:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.693 (17.693)	Loss 0.7876 (0.7876)	Acc@1 81.055 (81.055)	Acc@5 96.289 (96.289)	
[2022-01-24 22:41:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.249 (3.220)	Loss 0.8408 (0.8458)	Acc@1 80.371 (80.265)	Acc@5 95.703 (95.046)	
[2022-01-24 22:41:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.896 (2.458)	Loss 0.8188 (0.8576)	Acc@1 82.031 (79.869)	Acc@5 95.410 (95.020)	
[2022-01-24 22:42:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.301 (2.253)	Loss 0.8592 (0.8633)	Acc@1 79.980 (79.580)	Acc@5 94.629 (94.994)	
[2022-01-24 22:42:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.074 (2.115)	Loss 0.8511 (0.8638)	Acc@1 79.102 (79.597)	Acc@5 95.508 (94.936)	
[2022-01-24 22:42:33 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.534 Acc@5 94.946
[2022-01-24 22:42:33 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.5%
[2022-01-24 22:42:33 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.53%
[2022-01-24 22:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][0/1251]	eta 8:22:59 lr 0.000148	time 24.1245 (24.1245)	loss 2.4193 (2.4193)	grad_norm 2.9269 (2.9269)	
[2022-01-24 22:43:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][10/1251]	eta 1:32:17 lr 0.000148	time 2.9682 (4.4622)	loss 3.3749 (2.8975)	grad_norm 2.3632 (2.2892)	
[2022-01-24 22:43:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][20/1251]	eta 1:10:45 lr 0.000148	time 1.4650 (3.4490)	loss 3.2783 (3.1948)	grad_norm 2.2424 (2.3230)	
[2022-01-24 22:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][30/1251]	eta 1:01:47 lr 0.000148	time 1.6258 (3.0362)	loss 3.8314 (3.1884)	grad_norm 2.5553 (2.3220)	
[2022-01-24 22:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][40/1251]	eta 0:56:49 lr 0.000148	time 2.2639 (2.8154)	loss 3.5412 (3.1934)	grad_norm 2.4323 (2.3147)	
[2022-01-24 22:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][50/1251]	eta 0:53:37 lr 0.000148	time 2.0037 (2.6790)	loss 3.8849 (3.1833)	grad_norm 2.2709 (2.3137)	
[2022-01-24 22:45:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][60/1251]	eta 0:51:13 lr 0.000148	time 1.8121 (2.5806)	loss 3.5073 (3.2096)	grad_norm 2.6165 (2.3102)	
[2022-01-24 22:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][70/1251]	eta 0:49:23 lr 0.000148	time 2.2368 (2.5090)	loss 3.8156 (3.2457)	grad_norm 2.1310 (2.3189)	
[2022-01-24 22:45:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][80/1251]	eta 0:47:59 lr 0.000147	time 1.8952 (2.4592)	loss 3.5119 (3.2570)	grad_norm 2.3732 (2.3137)	
[2022-01-24 22:46:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][90/1251]	eta 0:46:56 lr 0.000147	time 1.5661 (2.4259)	loss 3.0409 (3.2574)	grad_norm 2.4659 (2.3039)	
[2022-01-24 22:46:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][100/1251]	eta 0:46:05 lr 0.000147	time 2.8226 (2.4026)	loss 2.8871 (3.2229)	grad_norm 2.7098 (2.3122)	
[2022-01-24 22:46:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][110/1251]	eta 0:45:10 lr 0.000147	time 2.2480 (2.3756)	loss 3.3848 (3.2381)	grad_norm 2.0163 (2.3247)	
[2022-01-24 22:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][120/1251]	eta 0:44:29 lr 0.000147	time 2.1344 (2.3607)	loss 3.4918 (3.2416)	grad_norm 2.4268 (2.3322)	
[2022-01-24 22:47:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][130/1251]	eta 0:43:47 lr 0.000147	time 1.8062 (2.3435)	loss 2.8667 (3.2294)	grad_norm 2.5494 (2.3321)	
[2022-01-24 22:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][140/1251]	eta 0:43:20 lr 0.000147	time 2.2015 (2.3407)	loss 2.8762 (3.2216)	grad_norm 2.4974 (2.3301)	
[2022-01-24 22:48:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][150/1251]	eta 0:43:04 lr 0.000147	time 2.3573 (2.3477)	loss 3.3195 (3.2289)	grad_norm 2.4283 (2.3302)	
[2022-01-24 22:48:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][160/1251]	eta 0:42:38 lr 0.000147	time 2.0947 (2.3450)	loss 4.0052 (3.2266)	grad_norm 2.5041 (2.3263)	
[2022-01-24 22:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][170/1251]	eta 0:42:03 lr 0.000147	time 1.7703 (2.3341)	loss 3.5806 (3.2266)	grad_norm 2.8352 (2.3259)	
[2022-01-24 22:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][180/1251]	eta 0:41:32 lr 0.000147	time 3.2549 (2.3277)	loss 3.4527 (3.2327)	grad_norm 2.1549 (2.3284)	
[2022-01-24 22:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][190/1251]	eta 0:40:58 lr 0.000147	time 2.1653 (2.3170)	loss 3.6274 (3.2419)	grad_norm 2.0931 (2.3254)	
[2022-01-24 22:50:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][200/1251]	eta 0:40:27 lr 0.000147	time 2.2530 (2.3094)	loss 3.0362 (3.2373)	grad_norm 2.0677 (2.3187)	
[2022-01-24 22:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][210/1251]	eta 0:39:51 lr 0.000147	time 1.6920 (2.2976)	loss 3.2677 (3.2254)	grad_norm 2.2378 (2.3149)	
[2022-01-24 22:50:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][220/1251]	eta 0:39:16 lr 0.000147	time 2.2124 (2.2855)	loss 2.6201 (3.2280)	grad_norm 2.8887 (2.3135)	
[2022-01-24 22:51:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][230/1251]	eta 0:38:49 lr 0.000147	time 2.0551 (2.2818)	loss 2.5021 (3.2122)	grad_norm 2.2817 (2.3128)	
[2022-01-24 22:51:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][240/1251]	eta 0:38:24 lr 0.000147	time 2.2306 (2.2791)	loss 3.9680 (3.2160)	grad_norm 2.2555 (2.3111)	
[2022-01-24 22:52:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][250/1251]	eta 0:37:59 lr 0.000147	time 1.8975 (2.2770)	loss 2.8573 (3.2152)	grad_norm 2.2413 (2.3098)	
[2022-01-24 22:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][260/1251]	eta 0:37:35 lr 0.000147	time 2.9594 (2.2765)	loss 2.3201 (3.2103)	grad_norm 2.3646 (2.3070)	
[2022-01-24 22:52:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][270/1251]	eta 0:37:13 lr 0.000147	time 2.8123 (2.2768)	loss 2.6901 (3.2128)	grad_norm 1.9980 (2.3061)	
[2022-01-24 22:53:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][280/1251]	eta 0:36:48 lr 0.000147	time 2.4099 (2.2747)	loss 3.1259 (3.2071)	grad_norm 1.8046 (2.3012)	
[2022-01-24 22:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][290/1251]	eta 0:36:18 lr 0.000147	time 1.9541 (2.2665)	loss 2.3912 (3.2003)	grad_norm 2.2117 (2.2980)	
[2022-01-24 22:53:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][300/1251]	eta 0:35:52 lr 0.000147	time 2.6537 (2.2632)	loss 3.2547 (3.2059)	grad_norm 2.3429 (2.3028)	
[2022-01-24 22:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][310/1251]	eta 0:35:22 lr 0.000147	time 1.7691 (2.2551)	loss 4.0794 (3.2076)	grad_norm 2.7915 (2.3086)	
[2022-01-24 22:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][320/1251]	eta 0:35:01 lr 0.000147	time 2.5929 (2.2578)	loss 2.8053 (3.2009)	grad_norm 2.8694 (2.3104)	
[2022-01-24 22:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][330/1251]	eta 0:34:39 lr 0.000147	time 2.7635 (2.2575)	loss 3.3505 (3.2026)	grad_norm 2.1854 (2.3163)	
[2022-01-24 22:55:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][340/1251]	eta 0:34:12 lr 0.000147	time 2.3065 (2.2535)	loss 2.2480 (3.2042)	grad_norm 1.9588 (2.3135)	
[2022-01-24 22:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][350/1251]	eta 0:33:47 lr 0.000147	time 2.1552 (2.2505)	loss 3.8317 (3.2061)	grad_norm 2.2816 (2.3115)	
[2022-01-24 22:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][360/1251]	eta 0:33:23 lr 0.000147	time 2.5381 (2.2491)	loss 3.3381 (3.2052)	grad_norm 2.1882 (2.3094)	
[2022-01-24 22:56:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][370/1251]	eta 0:32:56 lr 0.000147	time 1.8216 (2.2431)	loss 3.6254 (3.2026)	grad_norm 2.1942 (2.3101)	
[2022-01-24 22:56:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][380/1251]	eta 0:32:28 lr 0.000147	time 1.9294 (2.2370)	loss 2.6625 (3.1972)	grad_norm 2.4093 (2.3104)	
[2022-01-24 22:57:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][390/1251]	eta 0:32:03 lr 0.000147	time 2.3556 (2.2340)	loss 3.6280 (3.2006)	grad_norm 2.0127 (2.3116)	
[2022-01-24 22:57:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][400/1251]	eta 0:31:42 lr 0.000147	time 2.2325 (2.2360)	loss 2.7327 (3.1940)	grad_norm 3.0252 (2.3149)	
[2022-01-24 22:57:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][410/1251]	eta 0:31:20 lr 0.000147	time 2.2184 (2.2361)	loss 3.1708 (3.1926)	grad_norm 2.7334 (2.3157)	
[2022-01-24 22:58:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][420/1251]	eta 0:30:58 lr 0.000147	time 2.5101 (2.2365)	loss 3.4688 (3.1948)	grad_norm 2.4475 (2.3139)	
[2022-01-24 22:58:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][430/1251]	eta 0:30:36 lr 0.000146	time 2.1801 (2.2363)	loss 3.7119 (3.1990)	grad_norm 2.5495 (2.3131)	
[2022-01-24 22:58:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][440/1251]	eta 0:30:13 lr 0.000146	time 2.5405 (2.2356)	loss 2.9659 (3.2001)	grad_norm 2.1247 (2.3167)	
[2022-01-24 22:59:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][450/1251]	eta 0:29:49 lr 0.000146	time 2.0131 (2.2338)	loss 3.1803 (3.2021)	grad_norm 2.3468 (2.3171)	
[2022-01-24 22:59:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][460/1251]	eta 0:29:23 lr 0.000146	time 2.1877 (2.2296)	loss 3.8430 (3.2080)	grad_norm 2.6667 (2.3165)	
[2022-01-24 23:00:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][470/1251]	eta 0:28:58 lr 0.000146	time 2.1540 (2.2258)	loss 3.2096 (3.2043)	grad_norm 2.1000 (2.3185)	
[2022-01-24 23:00:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][480/1251]	eta 0:28:34 lr 0.000146	time 2.0397 (2.2233)	loss 2.5197 (3.2024)	grad_norm 2.2384 (2.3201)	
[2022-01-24 23:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][490/1251]	eta 0:28:12 lr 0.000146	time 2.3280 (2.2241)	loss 3.1217 (3.1991)	grad_norm 2.3149 (2.3219)	
[2022-01-24 23:01:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][500/1251]	eta 0:27:50 lr 0.000146	time 2.1712 (2.2238)	loss 3.5668 (3.1986)	grad_norm 2.3698 (2.3212)	
[2022-01-24 23:01:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][510/1251]	eta 0:27:29 lr 0.000146	time 2.7120 (2.2258)	loss 3.2590 (3.1978)	grad_norm 2.1744 (2.3204)	
[2022-01-24 23:01:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][520/1251]	eta 0:27:06 lr 0.000146	time 2.8481 (2.2248)	loss 3.5211 (3.1994)	grad_norm 2.3508 (2.3213)	
[2022-01-24 23:02:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][530/1251]	eta 0:26:42 lr 0.000146	time 2.4926 (2.2227)	loss 3.4671 (3.1999)	grad_norm 2.0332 (2.3182)	
[2022-01-24 23:02:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][540/1251]	eta 0:26:18 lr 0.000146	time 1.9064 (2.2205)	loss 2.3387 (3.1997)	grad_norm 2.3661 (2.3187)	
[2022-01-24 23:02:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][550/1251]	eta 0:25:58 lr 0.000146	time 3.0794 (2.2236)	loss 2.3858 (3.1977)	grad_norm 2.0339 (2.3180)	
[2022-01-24 23:03:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][560/1251]	eta 0:25:36 lr 0.000146	time 2.1444 (2.2239)	loss 2.4235 (3.1970)	grad_norm 2.3224 (2.3174)	
[2022-01-24 23:03:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][570/1251]	eta 0:25:15 lr 0.000146	time 2.5335 (2.2257)	loss 3.7974 (3.1980)	grad_norm 2.6757 (2.3168)	
[2022-01-24 23:04:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][580/1251]	eta 0:24:50 lr 0.000146	time 1.6703 (2.2214)	loss 3.4337 (3.1968)	grad_norm 2.1908 (2.3170)	
[2022-01-24 23:04:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][590/1251]	eta 0:24:27 lr 0.000146	time 3.3336 (2.2197)	loss 2.6398 (3.1920)	grad_norm 2.3688 (2.3168)	
[2022-01-24 23:04:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][600/1251]	eta 0:24:02 lr 0.000146	time 1.8124 (2.2159)	loss 3.6051 (3.1925)	grad_norm 2.3771 (2.3184)	
[2022-01-24 23:05:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][610/1251]	eta 0:23:40 lr 0.000146	time 2.2123 (2.2159)	loss 2.6414 (3.1912)	grad_norm 2.5476 (2.3194)	
[2022-01-24 23:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][620/1251]	eta 0:23:18 lr 0.000146	time 1.8474 (2.2165)	loss 2.9871 (3.1902)	grad_norm 2.1607 (2.3186)	
[2022-01-24 23:05:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][630/1251]	eta 0:22:58 lr 0.000146	time 3.0108 (2.2193)	loss 2.4594 (3.1925)	grad_norm 2.1213 (2.3166)	
[2022-01-24 23:06:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][640/1251]	eta 0:22:36 lr 0.000146	time 2.1842 (2.2200)	loss 2.6391 (3.1936)	grad_norm 2.1632 (2.3153)	
[2022-01-24 23:06:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][650/1251]	eta 0:22:15 lr 0.000146	time 3.1532 (2.2221)	loss 3.3995 (3.1955)	grad_norm 2.5400 (2.3138)	
[2022-01-24 23:07:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][660/1251]	eta 0:21:52 lr 0.000146	time 1.7483 (2.2213)	loss 3.2520 (3.1957)	grad_norm 2.7379 (2.3130)	
[2022-01-24 23:07:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][670/1251]	eta 0:21:31 lr 0.000146	time 3.3885 (2.2225)	loss 3.2648 (3.1927)	grad_norm 2.1394 (2.3129)	
[2022-01-24 23:07:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][680/1251]	eta 0:21:07 lr 0.000146	time 1.8721 (2.2199)	loss 2.4653 (3.1943)	grad_norm 2.6547 (2.3115)	
[2022-01-24 23:08:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][690/1251]	eta 0:20:43 lr 0.000146	time 2.3474 (2.2168)	loss 3.6706 (3.1950)	grad_norm 2.5421 (2.3118)	
[2022-01-24 23:08:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][700/1251]	eta 0:20:20 lr 0.000146	time 1.9568 (2.2145)	loss 3.6644 (3.1956)	grad_norm 2.2164 (2.3122)	
[2022-01-24 23:08:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][710/1251]	eta 0:19:56 lr 0.000146	time 2.4734 (2.2120)	loss 3.5817 (3.1965)	grad_norm 2.2666 (2.3110)	
[2022-01-24 23:09:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][720/1251]	eta 0:19:34 lr 0.000146	time 2.2420 (2.2112)	loss 3.2086 (3.1922)	grad_norm 2.3625 (2.3104)	
[2022-01-24 23:09:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][730/1251]	eta 0:19:11 lr 0.000146	time 2.2326 (2.2108)	loss 3.2915 (3.1947)	grad_norm 2.2929 (2.3083)	
[2022-01-24 23:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][740/1251]	eta 0:18:48 lr 0.000146	time 1.5780 (2.2083)	loss 3.5724 (3.1968)	grad_norm 2.4955 (2.3079)	
[2022-01-24 23:10:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][750/1251]	eta 0:18:27 lr 0.000146	time 2.3467 (2.2111)	loss 3.3865 (3.1982)	grad_norm 2.3600 (2.3080)	
[2022-01-24 23:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][760/1251]	eta 0:18:06 lr 0.000146	time 1.9528 (2.2127)	loss 3.6249 (3.1998)	grad_norm 2.3591 (2.3081)	
[2022-01-24 23:11:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][770/1251]	eta 0:17:45 lr 0.000146	time 2.2415 (2.2144)	loss 3.4937 (3.2023)	grad_norm 2.3703 (2.3097)	
[2022-01-24 23:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][780/1251]	eta 0:17:23 lr 0.000145	time 2.4556 (2.2158)	loss 3.8625 (3.2050)	grad_norm 2.3670 (2.3110)	
[2022-01-24 23:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][790/1251]	eta 0:17:01 lr 0.000145	time 1.8642 (2.2151)	loss 3.7107 (3.2029)	grad_norm 2.6577 (2.3106)	
[2022-01-24 23:12:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][800/1251]	eta 0:16:37 lr 0.000145	time 1.8684 (2.2121)	loss 3.4494 (3.2039)	grad_norm 1.9977 (2.3095)	
[2022-01-24 23:12:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][810/1251]	eta 0:16:14 lr 0.000145	time 1.8679 (2.2093)	loss 3.5886 (3.2039)	grad_norm 2.1690 (2.3095)	
[2022-01-24 23:12:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][820/1251]	eta 0:15:51 lr 0.000145	time 1.8938 (2.2068)	loss 2.6486 (3.2049)	grad_norm 2.2370 (2.3097)	
[2022-01-24 23:13:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][830/1251]	eta 0:15:29 lr 0.000145	time 2.2923 (2.2078)	loss 2.9111 (3.2085)	grad_norm 2.2947 (2.3090)	
[2022-01-24 23:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][840/1251]	eta 0:15:08 lr 0.000145	time 2.8853 (2.2101)	loss 2.3561 (3.2084)	grad_norm 2.0630 (2.3080)	
[2022-01-24 23:13:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][850/1251]	eta 0:14:46 lr 0.000145	time 2.4631 (2.2116)	loss 2.6275 (3.2062)	grad_norm 2.1736 (2.3071)	
[2022-01-24 23:14:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][860/1251]	eta 0:14:24 lr 0.000145	time 1.9188 (2.2121)	loss 3.4190 (3.2098)	grad_norm 1.9793 (2.3073)	
[2022-01-24 23:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][870/1251]	eta 0:14:02 lr 0.000145	time 1.9384 (2.2124)	loss 2.3894 (3.2064)	grad_norm 2.2286 (2.3068)	
[2022-01-24 23:15:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][880/1251]	eta 0:13:40 lr 0.000145	time 2.5349 (2.2109)	loss 2.1685 (3.2056)	grad_norm 2.1418 (2.3058)	
[2022-01-24 23:15:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][890/1251]	eta 0:13:17 lr 0.000145	time 2.1691 (2.2092)	loss 3.3663 (3.2074)	grad_norm 2.2537 (2.3092)	
[2022-01-24 23:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][900/1251]	eta 0:12:54 lr 0.000145	time 1.9238 (2.2065)	loss 3.2122 (3.2085)	grad_norm 2.1341 (2.3094)	
[2022-01-24 23:16:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][910/1251]	eta 0:12:31 lr 0.000145	time 2.1478 (2.2051)	loss 2.1197 (3.2079)	grad_norm 2.1394 (2.3094)	
[2022-01-24 23:16:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][920/1251]	eta 0:12:09 lr 0.000145	time 2.2169 (2.2041)	loss 3.8975 (3.2034)	grad_norm 2.0836 (2.3080)	
[2022-01-24 23:16:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][930/1251]	eta 0:11:47 lr 0.000145	time 2.2719 (2.2040)	loss 3.6197 (3.2055)	grad_norm 2.0971 (2.3072)	
[2022-01-24 23:17:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][940/1251]	eta 0:11:25 lr 0.000145	time 2.2429 (2.2030)	loss 3.1174 (3.2027)	grad_norm 2.1963 (2.3070)	
[2022-01-24 23:17:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][950/1251]	eta 0:11:03 lr 0.000145	time 2.1409 (2.2059)	loss 2.1704 (3.1984)	grad_norm 2.0149 (2.3064)	
[2022-01-24 23:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][960/1251]	eta 0:10:42 lr 0.000145	time 2.2248 (2.2068)	loss 2.7666 (3.1946)	grad_norm 1.9769 (2.3060)	
[2022-01-24 23:18:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][970/1251]	eta 0:10:20 lr 0.000145	time 2.5853 (2.2086)	loss 3.1567 (3.1954)	grad_norm 2.0784 (2.3058)	
[2022-01-24 23:18:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][980/1251]	eta 0:09:58 lr 0.000145	time 1.8126 (2.2080)	loss 3.1977 (3.1941)	grad_norm 2.3410 (2.3066)	
[2022-01-24 23:18:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][990/1251]	eta 0:09:35 lr 0.000145	time 2.0264 (2.2063)	loss 3.5179 (3.1929)	grad_norm 2.5546 (2.3096)	
[2022-01-24 23:19:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1000/1251]	eta 0:09:13 lr 0.000145	time 1.6927 (2.2046)	loss 3.5046 (3.1950)	grad_norm 2.1356 (2.3105)	
[2022-01-24 23:19:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1010/1251]	eta 0:08:51 lr 0.000145	time 2.1690 (2.2041)	loss 2.8658 (3.1950)	grad_norm 2.2243 (2.3087)	
[2022-01-24 23:20:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1020/1251]	eta 0:08:29 lr 0.000145	time 2.2253 (2.2043)	loss 2.9035 (3.1950)	grad_norm 2.3960 (2.3077)	
[2022-01-24 23:20:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1030/1251]	eta 0:08:07 lr 0.000145	time 2.1671 (2.2038)	loss 3.7574 (3.1958)	grad_norm 2.4024 (2.3071)	
[2022-01-24 23:20:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1040/1251]	eta 0:07:44 lr 0.000145	time 1.8754 (2.2036)	loss 3.4639 (3.1977)	grad_norm 2.9595 (2.3070)	
[2022-01-24 23:21:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1050/1251]	eta 0:07:23 lr 0.000145	time 1.8541 (2.2043)	loss 3.6895 (3.2006)	grad_norm 2.5190 (2.3066)	
[2022-01-24 23:21:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1060/1251]	eta 0:07:01 lr 0.000145	time 2.1538 (2.2051)	loss 2.3412 (3.1985)	grad_norm 5.9715 (2.3108)	
[2022-01-24 23:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1070/1251]	eta 0:06:39 lr 0.000145	time 3.0406 (2.2075)	loss 2.7877 (3.2002)	grad_norm 2.3976 (2.3132)	
[2022-01-24 23:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1080/1251]	eta 0:06:17 lr 0.000145	time 1.6054 (2.2064)	loss 3.1387 (3.1995)	grad_norm 2.5124 (2.3127)	
[2022-01-24 23:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1090/1251]	eta 0:05:55 lr 0.000145	time 2.1737 (2.2052)	loss 2.6943 (3.2004)	grad_norm 2.8613 (2.3133)	
[2022-01-24 23:22:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1100/1251]	eta 0:05:32 lr 0.000145	time 1.5564 (2.2033)	loss 2.6279 (3.1992)	grad_norm 2.0745 (2.3131)	
[2022-01-24 23:23:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1110/1251]	eta 0:05:10 lr 0.000145	time 2.2848 (2.2028)	loss 3.5041 (3.1975)	grad_norm 2.0579 (2.3124)	
[2022-01-24 23:23:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1120/1251]	eta 0:04:48 lr 0.000145	time 2.2970 (2.2009)	loss 2.4944 (3.1954)	grad_norm 2.1600 (2.3123)	
[2022-01-24 23:24:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1130/1251]	eta 0:04:26 lr 0.000145	time 2.1352 (2.2004)	loss 2.3114 (3.1958)	grad_norm 2.4536 (2.3116)	
[2022-01-24 23:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1140/1251]	eta 0:04:04 lr 0.000144	time 1.8782 (2.2003)	loss 2.6263 (3.1968)	grad_norm 2.3596 (2.3107)	
[2022-01-24 23:24:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1150/1251]	eta 0:03:42 lr 0.000144	time 2.7487 (2.2012)	loss 3.7796 (3.1971)	grad_norm 2.0960 (2.3093)	
[2022-01-24 23:25:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1160/1251]	eta 0:03:20 lr 0.000144	time 2.0052 (2.2004)	loss 3.0713 (3.1981)	grad_norm 1.9110 (2.3077)	
[2022-01-24 23:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1170/1251]	eta 0:02:58 lr 0.000144	time 1.4910 (2.2012)	loss 3.5729 (3.1984)	grad_norm 2.2578 (2.3069)	
[2022-01-24 23:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1180/1251]	eta 0:02:36 lr 0.000144	time 1.8026 (2.2008)	loss 2.3784 (3.1983)	grad_norm 2.6290 (2.3059)	
[2022-01-24 23:26:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1190/1251]	eta 0:02:14 lr 0.000144	time 1.7610 (2.2014)	loss 3.6992 (3.1997)	grad_norm 1.9239 (2.3045)	
[2022-01-24 23:26:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1200/1251]	eta 0:01:52 lr 0.000144	time 1.7978 (2.2015)	loss 2.2222 (3.1988)	grad_norm 2.3048 (2.3041)	
[2022-01-24 23:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1210/1251]	eta 0:01:30 lr 0.000144	time 1.7369 (2.2022)	loss 3.7983 (3.1982)	grad_norm 2.2299 (2.3036)	
[2022-01-24 23:27:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1220/1251]	eta 0:01:08 lr 0.000144	time 1.5427 (2.2011)	loss 2.6554 (3.1985)	grad_norm 2.0930 (2.3033)	
[2022-01-24 23:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1230/1251]	eta 0:00:46 lr 0.000144	time 1.9199 (2.2002)	loss 3.2535 (3.1970)	grad_norm 2.4405 (2.3028)	
[2022-01-24 23:28:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1240/1251]	eta 0:00:24 lr 0.000144	time 1.7275 (2.1990)	loss 2.9755 (3.1942)	grad_norm 2.2136 (2.3023)	
[2022-01-24 23:28:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [227/300][1250/1251]	eta 0:00:02 lr 0.000144	time 1.1866 (2.1931)	loss 2.1249 (3.1933)	grad_norm 2.1209 (2.3015)	
[2022-01-24 23:28:17 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 227 training takes 0:45:44
[2022-01-24 23:28:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.976 (18.976)	Loss 0.9365 (0.9365)	Acc@1 79.297 (79.297)	Acc@5 94.336 (94.336)	
[2022-01-24 23:28:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.285 (3.485)	Loss 0.8839 (0.8707)	Acc@1 79.102 (79.545)	Acc@5 94.824 (95.108)	
[2022-01-24 23:29:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.963 (2.553)	Loss 0.8897 (0.8679)	Acc@1 78.418 (79.515)	Acc@5 94.629 (94.950)	
[2022-01-24 23:29:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.279 (2.294)	Loss 0.8273 (0.8729)	Acc@1 81.250 (79.432)	Acc@5 95.898 (94.963)	
[2022-01-24 23:29:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.786 (2.191)	Loss 0.8261 (0.8662)	Acc@1 81.250 (79.502)	Acc@5 95.801 (95.000)	
[2022-01-24 23:29:53 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.500 Acc@5 95.072
[2022-01-24 23:29:53 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.5%
[2022-01-24 23:29:53 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.53%
[2022-01-24 23:30:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][0/1251]	eta 7:28:32 lr 0.000144	time 21.5125 (21.5125)	loss 3.7372 (3.7372)	grad_norm 2.3888 (2.3888)	
[2022-01-24 23:30:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][10/1251]	eta 1:25:01 lr 0.000144	time 1.7522 (4.1111)	loss 3.4710 (3.2793)	grad_norm 2.6413 (2.3823)	
[2022-01-24 23:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][20/1251]	eta 1:04:21 lr 0.000144	time 1.2991 (3.1368)	loss 2.8613 (3.2829)	grad_norm 2.2348 (2.3531)	
[2022-01-24 23:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][30/1251]	eta 0:57:30 lr 0.000144	time 1.8727 (2.8259)	loss 2.4965 (3.3358)	grad_norm 2.7260 (2.3859)	
[2022-01-24 23:31:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][40/1251]	eta 0:55:37 lr 0.000144	time 4.3931 (2.7562)	loss 3.1784 (3.3063)	grad_norm 2.4777 (2.3896)	
[2022-01-24 23:32:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][50/1251]	eta 0:52:44 lr 0.000144	time 1.2256 (2.6347)	loss 1.9991 (3.2679)	grad_norm 2.4324 (2.3364)	
[2022-01-24 23:32:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][60/1251]	eta 0:50:23 lr 0.000144	time 1.6598 (2.5385)	loss 3.5837 (3.2749)	grad_norm 2.2514 (2.3186)	
[2022-01-24 23:32:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][70/1251]	eta 0:48:24 lr 0.000144	time 1.9231 (2.4594)	loss 2.8895 (3.2294)	grad_norm 2.0710 (2.3261)	
[2022-01-24 23:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][80/1251]	eta 0:47:23 lr 0.000144	time 3.3298 (2.4287)	loss 3.6384 (3.2323)	grad_norm 3.0948 (2.3481)	
[2022-01-24 23:33:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][90/1251]	eta 0:46:16 lr 0.000144	time 1.4112 (2.3917)	loss 2.7528 (3.2184)	grad_norm 1.9453 (2.3498)	
[2022-01-24 23:33:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][100/1251]	eta 0:45:18 lr 0.000144	time 1.7233 (2.3622)	loss 3.6056 (3.2446)	grad_norm 2.4414 (2.3511)	
[2022-01-24 23:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][110/1251]	eta 0:44:58 lr 0.000144	time 1.7816 (2.3650)	loss 3.5609 (3.2114)	grad_norm 2.7013 (2.3506)	
[2022-01-24 23:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][120/1251]	eta 0:44:34 lr 0.000144	time 3.2375 (2.3651)	loss 3.7442 (3.2131)	grad_norm 2.1091 (2.3504)	
[2022-01-24 23:35:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][130/1251]	eta 0:43:48 lr 0.000144	time 1.2318 (2.3447)	loss 3.8583 (3.2186)	grad_norm 2.2422 (2.3426)	
[2022-01-24 23:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][140/1251]	eta 0:43:06 lr 0.000144	time 1.8794 (2.3279)	loss 3.2229 (3.1969)	grad_norm 2.7452 (2.3370)	
[2022-01-24 23:35:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][150/1251]	eta 0:42:30 lr 0.000144	time 2.0452 (2.3165)	loss 2.3254 (3.1884)	grad_norm 2.2174 (2.3383)	
[2022-01-24 23:36:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][160/1251]	eta 0:42:01 lr 0.000144	time 3.5252 (2.3109)	loss 2.3835 (3.1959)	grad_norm 3.0883 (2.3407)	
[2022-01-24 23:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][170/1251]	eta 0:41:32 lr 0.000144	time 2.1706 (2.3062)	loss 2.7348 (3.1964)	grad_norm 2.4631 (2.3411)	
[2022-01-24 23:36:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][180/1251]	eta 0:41:08 lr 0.000144	time 2.1440 (2.3048)	loss 2.9722 (3.1845)	grad_norm 2.6385 (2.3456)	
[2022-01-24 23:37:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][190/1251]	eta 0:40:38 lr 0.000144	time 2.2436 (2.2981)	loss 2.8879 (3.1801)	grad_norm 2.1901 (2.3465)	
[2022-01-24 23:37:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][200/1251]	eta 0:40:16 lr 0.000144	time 2.9467 (2.2990)	loss 2.5630 (3.1900)	grad_norm 2.0399 (2.3455)	
[2022-01-24 23:37:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][210/1251]	eta 0:39:46 lr 0.000144	time 1.7982 (2.2927)	loss 2.6923 (3.1952)	grad_norm 2.2671 (2.3431)	
[2022-01-24 23:38:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][220/1251]	eta 0:39:16 lr 0.000144	time 2.1157 (2.2861)	loss 2.8649 (3.1965)	grad_norm 2.6181 (2.3396)	
[2022-01-24 23:38:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][230/1251]	eta 0:38:43 lr 0.000144	time 1.9574 (2.2753)	loss 3.7851 (3.1987)	grad_norm 2.2582 (2.3356)	
[2022-01-24 23:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][240/1251]	eta 0:38:16 lr 0.000143	time 3.2973 (2.2718)	loss 3.6469 (3.2110)	grad_norm 2.1383 (2.3391)	
[2022-01-24 23:39:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][250/1251]	eta 0:37:46 lr 0.000143	time 1.7918 (2.2639)	loss 2.7771 (3.2071)	grad_norm 2.1979 (2.3374)	
[2022-01-24 23:39:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][260/1251]	eta 0:37:16 lr 0.000143	time 1.8013 (2.2564)	loss 2.6984 (3.2019)	grad_norm 2.3188 (2.3325)	
[2022-01-24 23:40:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][270/1251]	eta 0:36:49 lr 0.000143	time 1.8060 (2.2521)	loss 3.3349 (3.2044)	grad_norm 2.0902 (2.3320)	
[2022-01-24 23:40:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][280/1251]	eta 0:36:26 lr 0.000143	time 3.1845 (2.2521)	loss 2.9708 (3.2160)	grad_norm 2.0011 (2.3304)	
[2022-01-24 23:40:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][290/1251]	eta 0:36:00 lr 0.000143	time 2.0965 (2.2482)	loss 3.2587 (3.2129)	grad_norm 2.1998 (2.3309)	
[2022-01-24 23:41:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][300/1251]	eta 0:35:31 lr 0.000143	time 1.8562 (2.2412)	loss 3.8058 (3.2196)	grad_norm 2.1912 (2.3260)	
[2022-01-24 23:41:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][310/1251]	eta 0:35:04 lr 0.000143	time 1.9762 (2.2367)	loss 2.8893 (3.2195)	grad_norm 2.5496 (2.3253)	
[2022-01-24 23:41:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][320/1251]	eta 0:34:39 lr 0.000143	time 2.3188 (2.2331)	loss 2.5629 (3.2184)	grad_norm 2.1172 (2.3228)	
[2022-01-24 23:42:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][330/1251]	eta 0:34:12 lr 0.000143	time 1.7824 (2.2285)	loss 3.8796 (3.2159)	grad_norm 2.3350 (2.3244)	
[2022-01-24 23:42:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][340/1251]	eta 0:33:48 lr 0.000143	time 2.1141 (2.2272)	loss 3.0421 (3.2072)	grad_norm 2.3888 (2.3237)	
[2022-01-24 23:42:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][350/1251]	eta 0:33:25 lr 0.000143	time 2.2293 (2.2263)	loss 3.3187 (3.2110)	grad_norm 2.3140 (2.3247)	
[2022-01-24 23:43:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][360/1251]	eta 0:33:04 lr 0.000143	time 1.9854 (2.2277)	loss 3.3420 (3.2086)	grad_norm 2.7973 (2.3259)	
[2022-01-24 23:43:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][370/1251]	eta 0:32:45 lr 0.000143	time 2.6852 (2.2306)	loss 3.2589 (3.2111)	grad_norm 2.8360 (2.3324)	
[2022-01-24 23:44:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][380/1251]	eta 0:32:27 lr 0.000143	time 2.5563 (2.2360)	loss 2.8813 (3.2106)	grad_norm 2.0005 (2.3368)	
[2022-01-24 23:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][390/1251]	eta 0:32:01 lr 0.000143	time 1.8778 (2.2321)	loss 3.8151 (3.2054)	grad_norm 2.4712 (2.3381)	
[2022-01-24 23:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][400/1251]	eta 0:31:37 lr 0.000143	time 1.9267 (2.2301)	loss 3.7754 (3.2021)	grad_norm 2.1897 (2.3380)	
[2022-01-24 23:45:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][410/1251]	eta 0:31:16 lr 0.000143	time 2.1649 (2.2309)	loss 3.5092 (3.2002)	grad_norm 2.4126 (2.3375)	
[2022-01-24 23:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][420/1251]	eta 0:30:50 lr 0.000143	time 1.8768 (2.2274)	loss 3.6718 (3.2030)	grad_norm 3.0028 (2.3375)	
[2022-01-24 23:45:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][430/1251]	eta 0:30:27 lr 0.000143	time 2.2385 (2.2265)	loss 3.8245 (3.2010)	grad_norm 2.7406 (2.3398)	
[2022-01-24 23:46:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][440/1251]	eta 0:30:05 lr 0.000143	time 2.2116 (2.2262)	loss 3.3821 (3.2067)	grad_norm 2.2939 (2.3396)	
[2022-01-24 23:46:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][450/1251]	eta 0:29:42 lr 0.000143	time 2.5854 (2.2250)	loss 3.6396 (3.2024)	grad_norm 2.4462 (2.3399)	
[2022-01-24 23:46:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][460/1251]	eta 0:29:17 lr 0.000143	time 1.5386 (2.2214)	loss 4.0204 (3.2053)	grad_norm 2.2593 (2.3387)	
[2022-01-24 23:47:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][470/1251]	eta 0:28:56 lr 0.000143	time 2.4310 (2.2234)	loss 3.6331 (3.2089)	grad_norm 2.8262 (2.3385)	
[2022-01-24 23:47:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][480/1251]	eta 0:28:36 lr 0.000143	time 2.5901 (2.2266)	loss 2.9958 (3.2070)	grad_norm 2.2821 (2.3355)	
[2022-01-24 23:48:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][490/1251]	eta 0:28:12 lr 0.000143	time 2.3309 (2.2245)	loss 2.9254 (3.2037)	grad_norm 2.2350 (2.3318)	
[2022-01-24 23:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][500/1251]	eta 0:27:46 lr 0.000143	time 1.9718 (2.2195)	loss 2.9641 (3.2048)	grad_norm 2.2990 (2.3299)	
[2022-01-24 23:48:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][510/1251]	eta 0:27:21 lr 0.000143	time 2.1314 (2.2149)	loss 4.0380 (3.2076)	grad_norm 2.8139 (2.3307)	
[2022-01-24 23:49:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][520/1251]	eta 0:26:57 lr 0.000143	time 2.2623 (2.2132)	loss 3.6891 (3.2029)	grad_norm 2.3587 (2.3308)	
[2022-01-24 23:49:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][530/1251]	eta 0:26:37 lr 0.000143	time 2.2325 (2.2155)	loss 2.5953 (3.2042)	grad_norm 2.3212 (2.3299)	
[2022-01-24 23:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][540/1251]	eta 0:26:17 lr 0.000143	time 2.0378 (2.2186)	loss 3.7087 (3.2056)	grad_norm 2.2348 (2.3306)	
[2022-01-24 23:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][550/1251]	eta 0:25:54 lr 0.000143	time 1.8637 (2.2178)	loss 3.4346 (3.2054)	grad_norm 1.9911 (2.3313)	
[2022-01-24 23:50:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][560/1251]	eta 0:25:32 lr 0.000143	time 3.2162 (2.2174)	loss 3.3443 (3.2016)	grad_norm 2.1247 (2.3319)	
[2022-01-24 23:50:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][570/1251]	eta 0:25:10 lr 0.000143	time 1.8564 (2.2174)	loss 2.8956 (3.1989)	grad_norm 2.3939 (2.3326)	
[2022-01-24 23:51:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][580/1251]	eta 0:24:46 lr 0.000143	time 1.7812 (2.2160)	loss 3.8977 (3.1984)	grad_norm 2.4476 (2.3339)	
[2022-01-24 23:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][590/1251]	eta 0:24:24 lr 0.000142	time 2.2580 (2.2155)	loss 3.8879 (3.2017)	grad_norm 2.7249 (2.3335)	
[2022-01-24 23:52:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][600/1251]	eta 0:24:02 lr 0.000142	time 3.1800 (2.2155)	loss 3.5244 (3.2050)	grad_norm 2.2362 (2.3347)	
[2022-01-24 23:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][610/1251]	eta 0:23:40 lr 0.000142	time 1.7004 (2.2153)	loss 3.3288 (3.2040)	grad_norm 2.5870 (2.3346)	
[2022-01-24 23:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][620/1251]	eta 0:23:18 lr 0.000142	time 1.9202 (2.2157)	loss 3.4970 (3.2046)	grad_norm 2.4772 (2.3351)	
[2022-01-24 23:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][630/1251]	eta 0:22:55 lr 0.000142	time 1.6442 (2.2143)	loss 2.2631 (3.2045)	grad_norm 2.2838 (2.3369)	
[2022-01-24 23:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][640/1251]	eta 0:22:32 lr 0.000142	time 2.8230 (2.2131)	loss 3.8486 (3.2090)	grad_norm 2.1779 (2.3358)	
[2022-01-24 23:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][650/1251]	eta 0:22:10 lr 0.000142	time 2.1701 (2.2141)	loss 3.4115 (3.2110)	grad_norm 1.9754 (2.3343)	
[2022-01-24 23:54:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][660/1251]	eta 0:21:48 lr 0.000142	time 1.7953 (2.2133)	loss 3.0641 (3.2138)	grad_norm 2.0214 (2.3336)	
[2022-01-24 23:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][670/1251]	eta 0:21:25 lr 0.000142	time 1.8279 (2.2128)	loss 3.5836 (3.2110)	grad_norm 2.2853 (2.3352)	
[2022-01-24 23:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][680/1251]	eta 0:21:01 lr 0.000142	time 1.7639 (2.2085)	loss 3.9093 (3.2103)	grad_norm 2.4971 (2.3331)	
[2022-01-24 23:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][690/1251]	eta 0:20:38 lr 0.000142	time 2.8727 (2.2080)	loss 3.5461 (3.2115)	grad_norm 2.3891 (2.3335)	
[2022-01-24 23:55:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][700/1251]	eta 0:20:16 lr 0.000142	time 2.2128 (2.2072)	loss 3.2801 (3.2127)	grad_norm 2.3380 (2.3323)	
[2022-01-24 23:56:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][710/1251]	eta 0:19:53 lr 0.000142	time 1.8247 (2.2066)	loss 2.6157 (3.2100)	grad_norm 2.4467 (2.3329)	
[2022-01-24 23:56:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][720/1251]	eta 0:19:32 lr 0.000142	time 2.8110 (2.2089)	loss 3.3774 (3.2107)	grad_norm 2.2736 (2.3328)	
[2022-01-24 23:56:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][730/1251]	eta 0:19:10 lr 0.000142	time 2.3048 (2.2092)	loss 3.6991 (3.2109)	grad_norm 2.1942 (2.3329)	
[2022-01-24 23:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][740/1251]	eta 0:18:49 lr 0.000142	time 2.6192 (2.2103)	loss 3.1901 (3.2128)	grad_norm 2.2607 (2.3334)	
[2022-01-24 23:57:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][750/1251]	eta 0:18:28 lr 0.000142	time 2.3673 (2.2120)	loss 2.5394 (3.2097)	grad_norm 2.3606 (2.3325)	
[2022-01-24 23:57:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][760/1251]	eta 0:18:06 lr 0.000142	time 2.8040 (2.2138)	loss 3.6976 (3.2078)	grad_norm 2.2031 (2.3323)	
[2022-01-24 23:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][770/1251]	eta 0:17:43 lr 0.000142	time 2.0723 (2.2120)	loss 3.7542 (3.2088)	grad_norm 2.2446 (2.3305)	
[2022-01-24 23:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][780/1251]	eta 0:17:20 lr 0.000142	time 1.7976 (2.2088)	loss 2.2650 (3.2061)	grad_norm 2.0117 (2.3312)	
[2022-01-24 23:58:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][790/1251]	eta 0:16:57 lr 0.000142	time 2.2517 (2.2074)	loss 2.2797 (3.2018)	grad_norm 2.1999 (2.3322)	
[2022-01-24 23:59:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][800/1251]	eta 0:16:35 lr 0.000142	time 2.7091 (2.2066)	loss 3.4316 (3.2010)	grad_norm 1.9886 (2.3321)	
[2022-01-24 23:59:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][810/1251]	eta 0:16:13 lr 0.000142	time 2.8832 (2.2070)	loss 3.4319 (3.2021)	grad_norm 2.2942 (2.3314)	
[2022-01-25 00:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][820/1251]	eta 0:15:50 lr 0.000142	time 2.5688 (2.2062)	loss 3.3553 (3.2022)	grad_norm 2.1287 (2.3307)	
[2022-01-25 00:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][830/1251]	eta 0:15:28 lr 0.000142	time 2.1786 (2.2049)	loss 3.2732 (3.2015)	grad_norm 2.2777 (2.3304)	
[2022-01-25 00:00:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][840/1251]	eta 0:15:06 lr 0.000142	time 1.7581 (2.2052)	loss 3.1286 (3.2031)	grad_norm 1.9211 (2.3290)	
[2022-01-25 00:01:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][850/1251]	eta 0:14:44 lr 0.000142	time 2.3976 (2.2058)	loss 3.5443 (3.2037)	grad_norm 2.4356 (2.3282)	
[2022-01-25 00:01:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][860/1251]	eta 0:14:22 lr 0.000142	time 2.3431 (2.2054)	loss 3.5735 (3.2033)	grad_norm 2.0013 (2.3296)	
[2022-01-25 00:01:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][870/1251]	eta 0:14:00 lr 0.000142	time 2.7687 (2.2059)	loss 3.6761 (3.2054)	grad_norm 2.5752 (2.3290)	
[2022-01-25 00:02:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][880/1251]	eta 0:13:38 lr 0.000142	time 2.4608 (2.2055)	loss 2.2449 (3.2044)	grad_norm 2.5308 (2.3300)	
[2022-01-25 00:02:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][890/1251]	eta 0:13:15 lr 0.000142	time 2.1678 (2.2042)	loss 2.6946 (3.2004)	grad_norm 2.3114 (2.3308)	
[2022-01-25 00:02:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][900/1251]	eta 0:12:53 lr 0.000142	time 1.9949 (2.2037)	loss 2.0811 (3.2011)	grad_norm 2.0529 (2.3301)	
[2022-01-25 00:03:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][910/1251]	eta 0:12:32 lr 0.000142	time 2.4681 (2.2073)	loss 3.4263 (3.2022)	grad_norm 2.5475 (2.3290)	
[2022-01-25 00:03:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][920/1251]	eta 0:12:11 lr 0.000142	time 2.0499 (2.2087)	loss 2.6509 (3.2033)	grad_norm 2.1070 (2.3274)	
[2022-01-25 00:04:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][930/1251]	eta 0:11:49 lr 0.000142	time 2.4078 (2.2087)	loss 2.4372 (3.2038)	grad_norm 2.2216 (2.3261)	
[2022-01-25 00:04:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][940/1251]	eta 0:11:26 lr 0.000142	time 1.9028 (2.2084)	loss 3.7851 (3.2043)	grad_norm 2.1976 (2.3263)	
[2022-01-25 00:04:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][950/1251]	eta 0:11:04 lr 0.000141	time 1.8898 (2.2068)	loss 2.9902 (3.1993)	grad_norm 3.7422 (2.3277)	
[2022-01-25 00:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][960/1251]	eta 0:10:41 lr 0.000141	time 1.9155 (2.2029)	loss 3.5862 (3.2019)	grad_norm 2.0484 (2.3273)	
[2022-01-25 00:05:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][970/1251]	eta 0:10:18 lr 0.000141	time 1.7187 (2.2011)	loss 3.3536 (3.2028)	grad_norm 3.1678 (2.3345)	
[2022-01-25 00:05:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][980/1251]	eta 0:09:56 lr 0.000141	time 2.1392 (2.2005)	loss 3.5935 (3.2053)	grad_norm 2.2169 (2.3369)	
[2022-01-25 00:06:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][990/1251]	eta 0:09:33 lr 0.000141	time 1.9363 (2.1989)	loss 4.0664 (3.2060)	grad_norm 2.1465 (2.3362)	
[2022-01-25 00:06:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1000/1251]	eta 0:09:11 lr 0.000141	time 2.2530 (2.1981)	loss 2.0199 (3.2046)	grad_norm 2.4327 (2.3357)	
[2022-01-25 00:06:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1010/1251]	eta 0:08:49 lr 0.000141	time 2.0979 (2.1981)	loss 3.4185 (3.2069)	grad_norm 2.0314 (2.3348)	
[2022-01-25 00:07:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1020/1251]	eta 0:08:27 lr 0.000141	time 2.2800 (2.1976)	loss 1.9041 (3.2064)	grad_norm 2.0939 (2.3352)	
[2022-01-25 00:07:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1030/1251]	eta 0:08:05 lr 0.000141	time 1.6979 (2.1989)	loss 3.8958 (3.2077)	grad_norm 2.3945 (2.3339)	
[2022-01-25 00:08:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1040/1251]	eta 0:07:44 lr 0.000141	time 2.2606 (2.2002)	loss 3.6631 (3.2090)	grad_norm 3.0288 (2.3346)	
[2022-01-25 00:08:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1050/1251]	eta 0:07:22 lr 0.000141	time 2.1642 (2.2006)	loss 3.8932 (3.2081)	grad_norm 2.5211 (2.3333)	
[2022-01-25 00:08:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1060/1251]	eta 0:07:01 lr 0.000141	time 3.4401 (2.2050)	loss 3.5343 (3.2071)	grad_norm 2.3717 (2.3321)	
[2022-01-25 00:09:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1070/1251]	eta 0:06:39 lr 0.000141	time 1.5101 (2.2060)	loss 3.5037 (3.2088)	grad_norm 2.3462 (2.3323)	
[2022-01-25 00:09:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1080/1251]	eta 0:06:17 lr 0.000141	time 2.0266 (2.2051)	loss 2.5488 (3.2084)	grad_norm 2.5051 (2.3327)	
[2022-01-25 00:09:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1090/1251]	eta 0:05:54 lr 0.000141	time 1.8491 (2.2038)	loss 3.8677 (3.2093)	grad_norm 2.3882 (2.3315)	
[2022-01-25 00:10:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1100/1251]	eta 0:05:32 lr 0.000141	time 1.7140 (2.2027)	loss 3.4734 (3.2106)	grad_norm 2.2765 (2.3311)	
[2022-01-25 00:10:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1110/1251]	eta 0:05:10 lr 0.000141	time 1.8680 (2.2006)	loss 3.1899 (3.2107)	grad_norm 2.3967 (2.3304)	
[2022-01-25 00:11:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1120/1251]	eta 0:04:48 lr 0.000141	time 2.1063 (2.2004)	loss 3.6806 (3.2118)	grad_norm 2.3551 (2.3310)	
[2022-01-25 00:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1130/1251]	eta 0:04:26 lr 0.000141	time 1.8561 (2.2004)	loss 3.8072 (3.2111)	grad_norm 2.1462 (2.3311)	
[2022-01-25 00:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1140/1251]	eta 0:04:04 lr 0.000141	time 1.8463 (2.2003)	loss 2.4579 (3.2090)	grad_norm 2.3389 (2.3311)	
[2022-01-25 00:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1150/1251]	eta 0:03:42 lr 0.000141	time 2.8622 (2.2017)	loss 3.9280 (3.2075)	grad_norm 2.1177 (2.3310)	
[2022-01-25 00:12:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1160/1251]	eta 0:03:20 lr 0.000141	time 1.6581 (2.2015)	loss 3.4984 (3.2084)	grad_norm 2.2738 (2.3306)	
[2022-01-25 00:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1170/1251]	eta 0:02:58 lr 0.000141	time 2.1699 (2.2020)	loss 3.3368 (3.2097)	grad_norm 2.1537 (2.3301)	
[2022-01-25 00:13:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1180/1251]	eta 0:02:36 lr 0.000141	time 2.5352 (2.2025)	loss 2.4026 (3.2095)	grad_norm 2.0866 (2.3292)	
[2022-01-25 00:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1190/1251]	eta 0:02:14 lr 0.000141	time 2.1885 (2.2022)	loss 3.1236 (3.2099)	grad_norm 2.4750 (2.3293)	
[2022-01-25 00:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1200/1251]	eta 0:01:52 lr 0.000141	time 2.0326 (2.2011)	loss 3.9773 (3.2115)	grad_norm 2.1915 (2.3294)	
[2022-01-25 00:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1210/1251]	eta 0:01:30 lr 0.000141	time 1.8673 (2.2005)	loss 3.4576 (3.2122)	grad_norm 2.1291 (2.3296)	
[2022-01-25 00:14:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1220/1251]	eta 0:01:08 lr 0.000141	time 2.1675 (2.1994)	loss 3.5886 (3.2090)	grad_norm 2.3801 (2.3298)	
[2022-01-25 00:15:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1230/1251]	eta 0:00:46 lr 0.000141	time 2.5197 (2.1993)	loss 2.3632 (3.2075)	grad_norm 2.2646 (2.3287)	
[2022-01-25 00:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1240/1251]	eta 0:00:24 lr 0.000141	time 1.4299 (2.1997)	loss 3.3746 (3.2080)	grad_norm 2.2624 (2.3288)	
[2022-01-25 00:15:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [228/300][1250/1251]	eta 0:00:02 lr 0.000141	time 1.1785 (2.1949)	loss 3.5195 (3.2061)	grad_norm 2.2959 (2.3330)	
[2022-01-25 00:15:40 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 228 training takes 0:45:46
[2022-01-25 00:15:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.097 (19.097)	Loss 0.8507 (0.8507)	Acc@1 80.566 (80.566)	Acc@5 95.605 (95.605)	
[2022-01-25 00:16:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.024 (3.210)	Loss 0.8872 (0.8730)	Acc@1 77.734 (78.915)	Acc@5 94.922 (95.215)	
[2022-01-25 00:16:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.995 (2.606)	Loss 0.8952 (0.8683)	Acc@1 80.078 (79.367)	Acc@5 94.238 (95.178)	
[2022-01-25 00:16:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.306 (2.353)	Loss 0.8168 (0.8685)	Acc@1 80.566 (79.413)	Acc@5 95.605 (95.136)	
[2022-01-25 00:17:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.221 (2.230)	Loss 0.8911 (0.8693)	Acc@1 78.809 (79.456)	Acc@5 94.141 (95.029)	
[2022-01-25 00:17:18 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.510 Acc@5 95.014
[2022-01-25 00:17:18 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.5%
[2022-01-25 00:17:18 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.53%
[2022-01-25 00:17:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][0/1251]	eta 7:33:03 lr 0.000141	time 21.7291 (21.7291)	loss 2.2374 (2.2374)	grad_norm 2.8203 (2.8203)	
[2022-01-25 00:18:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][10/1251]	eta 1:25:59 lr 0.000141	time 2.5971 (4.1579)	loss 3.1250 (3.0771)	grad_norm 2.0164 (2.3464)	
[2022-01-25 00:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][20/1251]	eta 1:06:46 lr 0.000141	time 1.5224 (3.2547)	loss 3.2928 (3.1774)	grad_norm 2.4284 (2.4160)	
[2022-01-25 00:18:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][30/1251]	eta 1:00:24 lr 0.000141	time 1.7960 (2.9688)	loss 3.3205 (3.1767)	grad_norm 2.3434 (2.4526)	
[2022-01-25 00:19:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][40/1251]	eta 0:57:00 lr 0.000141	time 3.9340 (2.8243)	loss 3.9202 (3.1722)	grad_norm 2.2807 (2.4327)	
[2022-01-25 00:19:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][50/1251]	eta 0:53:55 lr 0.000140	time 2.1865 (2.6937)	loss 2.5310 (3.1511)	grad_norm 2.4715 (2.4079)	
[2022-01-25 00:19:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][60/1251]	eta 0:51:41 lr 0.000140	time 1.8350 (2.6041)	loss 2.5510 (3.1294)	grad_norm 2.3889 (2.3782)	
[2022-01-25 00:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][70/1251]	eta 0:50:10 lr 0.000140	time 1.9152 (2.5491)	loss 2.7146 (3.0984)	grad_norm 2.4258 (2.3832)	
[2022-01-25 00:20:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][80/1251]	eta 0:49:27 lr 0.000140	time 3.5555 (2.5339)	loss 3.5301 (3.1192)	grad_norm 2.2555 (2.3771)	
[2022-01-25 00:21:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][90/1251]	eta 0:48:17 lr 0.000140	time 1.5045 (2.4960)	loss 3.7095 (3.1161)	grad_norm 2.1372 (2.3582)	
[2022-01-25 00:21:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][100/1251]	eta 0:46:54 lr 0.000140	time 1.9352 (2.4451)	loss 3.3157 (3.1493)	grad_norm 2.3139 (2.3415)	
[2022-01-25 00:21:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][110/1251]	eta 0:45:59 lr 0.000140	time 1.9791 (2.4188)	loss 3.6486 (3.1464)	grad_norm 2.0995 (2.3204)	
[2022-01-25 00:22:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][120/1251]	eta 0:44:58 lr 0.000140	time 2.2710 (2.3860)	loss 3.7098 (3.1253)	grad_norm 2.8921 (2.3141)	
[2022-01-25 00:22:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][130/1251]	eta 0:44:12 lr 0.000140	time 2.1558 (2.3665)	loss 3.5869 (3.1251)	grad_norm 2.5308 (2.3037)	
[2022-01-25 00:22:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][140/1251]	eta 0:43:28 lr 0.000140	time 2.4047 (2.3483)	loss 3.4003 (3.1304)	grad_norm 2.1747 (2.2999)	
[2022-01-25 00:23:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][150/1251]	eta 0:42:59 lr 0.000140	time 2.1369 (2.3432)	loss 3.1419 (3.1228)	grad_norm 2.0446 (2.2925)	
[2022-01-25 00:23:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][160/1251]	eta 0:42:36 lr 0.000140	time 3.1066 (2.3430)	loss 3.9676 (3.1455)	grad_norm 2.1874 (2.2967)	
[2022-01-25 00:23:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][170/1251]	eta 0:42:12 lr 0.000140	time 2.5546 (2.3423)	loss 3.9476 (3.1573)	grad_norm 2.4816 (2.2996)	
[2022-01-25 00:24:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][180/1251]	eta 0:41:35 lr 0.000140	time 1.8419 (2.3302)	loss 3.5113 (3.1697)	grad_norm 2.3786 (2.3020)	
[2022-01-25 00:24:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][190/1251]	eta 0:40:55 lr 0.000140	time 1.9333 (2.3143)	loss 2.5562 (3.1520)	grad_norm 2.1409 (2.3002)	
[2022-01-25 00:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][200/1251]	eta 0:40:19 lr 0.000140	time 2.4217 (2.3021)	loss 3.1031 (3.1574)	grad_norm 2.3239 (2.2977)	
[2022-01-25 00:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][210/1251]	eta 0:39:39 lr 0.000140	time 1.8644 (2.2862)	loss 3.4529 (3.1573)	grad_norm 2.5003 (2.2989)	
[2022-01-25 00:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][220/1251]	eta 0:39:09 lr 0.000140	time 2.1895 (2.2786)	loss 2.5693 (3.1687)	grad_norm 2.4794 (2.3005)	
[2022-01-25 00:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][230/1251]	eta 0:38:37 lr 0.000140	time 2.7619 (2.2701)	loss 3.1227 (3.1649)	grad_norm 2.5122 (2.2969)	
[2022-01-25 00:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][240/1251]	eta 0:38:05 lr 0.000140	time 1.9650 (2.2611)	loss 3.4851 (3.1720)	grad_norm 2.1353 (2.2979)	
[2022-01-25 00:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][250/1251]	eta 0:37:48 lr 0.000140	time 3.1897 (2.2666)	loss 3.3190 (3.1611)	grad_norm 2.1708 (2.2998)	
[2022-01-25 00:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][260/1251]	eta 0:37:26 lr 0.000140	time 1.8491 (2.2669)	loss 2.6530 (3.1619)	grad_norm 2.2410 (2.3015)	
[2022-01-25 00:27:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][270/1251]	eta 0:37:12 lr 0.000140	time 2.4504 (2.2755)	loss 3.6234 (3.1634)	grad_norm 2.3475 (2.3050)	
[2022-01-25 00:27:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][280/1251]	eta 0:36:45 lr 0.000140	time 2.6300 (2.2709)	loss 3.9025 (3.1634)	grad_norm 2.2886 (2.3075)	
[2022-01-25 00:28:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][290/1251]	eta 0:36:18 lr 0.000140	time 3.1910 (2.2672)	loss 3.1246 (3.1719)	grad_norm 2.3253 (2.3092)	
[2022-01-25 00:28:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][300/1251]	eta 0:35:54 lr 0.000140	time 2.1209 (2.2657)	loss 3.7102 (3.1740)	grad_norm 2.0793 (2.3091)	
[2022-01-25 00:29:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][310/1251]	eta 0:35:31 lr 0.000140	time 2.5112 (2.2653)	loss 3.5678 (3.1724)	grad_norm 2.3459 (2.3114)	
[2022-01-25 00:29:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][320/1251]	eta 0:35:06 lr 0.000140	time 2.1680 (2.2627)	loss 3.4011 (3.1660)	grad_norm 2.4184 (2.3100)	
[2022-01-25 00:29:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][330/1251]	eta 0:34:38 lr 0.000140	time 1.9109 (2.2563)	loss 2.8414 (3.1649)	grad_norm 2.0425 (2.3114)	
[2022-01-25 00:30:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][340/1251]	eta 0:34:12 lr 0.000140	time 1.5009 (2.2529)	loss 3.6055 (3.1704)	grad_norm 2.0922 (2.3126)	
[2022-01-25 00:30:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][350/1251]	eta 0:33:45 lr 0.000140	time 1.9227 (2.2482)	loss 3.5710 (3.1678)	grad_norm 2.2926 (2.3129)	
[2022-01-25 00:30:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][360/1251]	eta 0:33:22 lr 0.000140	time 2.1936 (2.2475)	loss 3.4263 (3.1725)	grad_norm 2.2427 (2.3110)	
[2022-01-25 00:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][370/1251]	eta 0:33:00 lr 0.000140	time 2.1096 (2.2484)	loss 3.2679 (3.1733)	grad_norm 2.2415 (2.3084)	
[2022-01-25 00:31:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][380/1251]	eta 0:32:41 lr 0.000140	time 1.8666 (2.2523)	loss 2.4268 (3.1667)	grad_norm 2.2990 (2.3063)	
[2022-01-25 00:31:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][390/1251]	eta 0:32:15 lr 0.000140	time 1.5904 (2.2480)	loss 3.2821 (3.1610)	grad_norm 1.9624 (2.3045)	
[2022-01-25 00:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][400/1251]	eta 0:31:48 lr 0.000140	time 1.9817 (2.2431)	loss 3.1918 (3.1598)	grad_norm 2.2573 (2.3045)	
[2022-01-25 00:32:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][410/1251]	eta 0:31:22 lr 0.000139	time 2.5306 (2.2387)	loss 3.7775 (3.1591)	grad_norm 2.2127 (2.3031)	
[2022-01-25 00:33:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][420/1251]	eta 0:30:59 lr 0.000139	time 1.8891 (2.2382)	loss 2.8426 (3.1546)	grad_norm 2.1412 (2.3034)	
[2022-01-25 00:33:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][430/1251]	eta 0:30:36 lr 0.000139	time 1.8160 (2.2367)	loss 2.6920 (3.1452)	grad_norm 2.2631 (2.3003)	
[2022-01-25 00:33:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][440/1251]	eta 0:30:12 lr 0.000139	time 1.7451 (2.2344)	loss 3.7466 (3.1445)	grad_norm 2.9307 (2.3049)	
[2022-01-25 00:34:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][450/1251]	eta 0:29:51 lr 0.000139	time 3.0492 (2.2365)	loss 2.2495 (3.1401)	grad_norm 2.2241 (2.3089)	
[2022-01-25 00:34:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][460/1251]	eta 0:29:27 lr 0.000139	time 1.9028 (2.2348)	loss 3.1343 (3.1433)	grad_norm 2.1537 (2.3084)	
[2022-01-25 00:34:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][470/1251]	eta 0:29:05 lr 0.000139	time 1.9298 (2.2345)	loss 3.2717 (3.1471)	grad_norm 2.5471 (2.3082)	
[2022-01-25 00:35:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][480/1251]	eta 0:28:43 lr 0.000139	time 2.5689 (2.2352)	loss 3.0133 (3.1487)	grad_norm 2.2340 (2.3077)	
[2022-01-25 00:35:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][490/1251]	eta 0:28:18 lr 0.000139	time 2.1854 (2.2318)	loss 3.4674 (3.1522)	grad_norm 2.0018 (2.3061)	
[2022-01-25 00:35:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][500/1251]	eta 0:27:52 lr 0.000139	time 2.1822 (2.2265)	loss 2.8031 (3.1472)	grad_norm 2.0112 (2.3026)	
[2022-01-25 00:36:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][510/1251]	eta 0:27:27 lr 0.000139	time 2.3694 (2.2234)	loss 2.5689 (3.1497)	grad_norm 2.1463 (2.3017)	
[2022-01-25 00:36:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][520/1251]	eta 0:27:05 lr 0.000139	time 2.7297 (2.2231)	loss 3.6341 (3.1539)	grad_norm 2.7215 (2.3069)	
[2022-01-25 00:36:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][530/1251]	eta 0:26:43 lr 0.000139	time 2.6348 (2.2235)	loss 2.2773 (3.1537)	grad_norm 2.5975 (2.3106)	
[2022-01-25 00:37:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][540/1251]	eta 0:26:19 lr 0.000139	time 1.9876 (2.2220)	loss 3.5190 (3.1565)	grad_norm 2.1215 (2.3137)	
[2022-01-25 00:37:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][550/1251]	eta 0:25:57 lr 0.000139	time 1.8578 (2.2214)	loss 3.1661 (3.1614)	grad_norm 2.3408 (2.3169)	
[2022-01-25 00:38:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][560/1251]	eta 0:25:35 lr 0.000139	time 2.7525 (2.2227)	loss 3.7122 (3.1646)	grad_norm 2.2132 (2.3159)	
[2022-01-25 00:38:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][570/1251]	eta 0:25:12 lr 0.000139	time 2.5438 (2.2215)	loss 3.4685 (3.1681)	grad_norm 2.1154 (2.3186)	
[2022-01-25 00:38:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][580/1251]	eta 0:24:49 lr 0.000139	time 1.6386 (2.2204)	loss 2.2790 (3.1673)	grad_norm 2.1129 (2.3180)	
[2022-01-25 00:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][590/1251]	eta 0:24:27 lr 0.000139	time 2.2671 (2.2203)	loss 2.5755 (3.1636)	grad_norm 2.2805 (2.3161)	
[2022-01-25 00:39:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][600/1251]	eta 0:24:05 lr 0.000139	time 3.4543 (2.2211)	loss 3.5034 (3.1594)	grad_norm 2.1410 (2.3185)	
[2022-01-25 00:39:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][610/1251]	eta 0:23:42 lr 0.000139	time 2.5853 (2.2189)	loss 3.4649 (3.1628)	grad_norm 2.0223 (2.3185)	
[2022-01-25 00:40:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][620/1251]	eta 0:23:19 lr 0.000139	time 1.6317 (2.2173)	loss 2.9178 (3.1625)	grad_norm 2.1771 (2.3193)	
[2022-01-25 00:40:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][630/1251]	eta 0:22:56 lr 0.000139	time 1.8320 (2.2174)	loss 2.8615 (3.1645)	grad_norm 2.1812 (2.3176)	
[2022-01-25 00:41:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][640/1251]	eta 0:22:35 lr 0.000139	time 4.1321 (2.2185)	loss 3.7912 (3.1681)	grad_norm 2.1863 (2.3201)	
[2022-01-25 00:41:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][650/1251]	eta 0:22:13 lr 0.000139	time 2.0453 (2.2190)	loss 3.8237 (3.1692)	grad_norm 2.3845 (2.3186)	
[2022-01-25 00:41:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][660/1251]	eta 0:21:50 lr 0.000139	time 1.6077 (2.2170)	loss 3.7009 (3.1706)	grad_norm 2.4504 (2.3175)	
[2022-01-25 00:42:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][670/1251]	eta 0:21:27 lr 0.000139	time 1.9737 (2.2160)	loss 3.6112 (3.1699)	grad_norm 2.0930 (2.3167)	
[2022-01-25 00:42:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][680/1251]	eta 0:21:04 lr 0.000139	time 2.0905 (2.2145)	loss 3.0566 (3.1689)	grad_norm 2.2330 (2.3166)	
[2022-01-25 00:42:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][690/1251]	eta 0:20:41 lr 0.000139	time 2.2779 (2.2123)	loss 3.5112 (3.1688)	grad_norm 2.3719 (2.3147)	
[2022-01-25 00:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][700/1251]	eta 0:20:17 lr 0.000139	time 1.6308 (2.2103)	loss 3.5614 (3.1685)	grad_norm 2.2548 (2.3146)	
[2022-01-25 00:43:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][710/1251]	eta 0:19:56 lr 0.000139	time 1.7368 (2.2107)	loss 2.7799 (3.1664)	grad_norm 2.3560 (2.3171)	
[2022-01-25 00:43:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][720/1251]	eta 0:19:34 lr 0.000139	time 2.2823 (2.2128)	loss 3.2304 (3.1683)	grad_norm 2.2118 (2.3160)	
[2022-01-25 00:44:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][730/1251]	eta 0:19:12 lr 0.000139	time 2.5431 (2.2121)	loss 2.5622 (3.1668)	grad_norm 2.1487 (2.3171)	
[2022-01-25 00:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][740/1251]	eta 0:18:50 lr 0.000139	time 1.6131 (2.2122)	loss 2.0919 (3.1661)	grad_norm 2.1805 (2.3197)	
[2022-01-25 00:44:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][750/1251]	eta 0:18:27 lr 0.000139	time 2.0155 (2.2104)	loss 2.1409 (3.1642)	grad_norm 2.1340 (2.3207)	
[2022-01-25 00:45:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][760/1251]	eta 0:18:05 lr 0.000139	time 2.1587 (2.2108)	loss 3.3235 (3.1623)	grad_norm 2.1103 (2.3200)	
[2022-01-25 00:45:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][770/1251]	eta 0:17:43 lr 0.000138	time 2.4985 (2.2109)	loss 3.7733 (3.1613)	grad_norm 2.2826 (2.3198)	
[2022-01-25 00:46:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][780/1251]	eta 0:17:21 lr 0.000138	time 2.3216 (2.2108)	loss 2.9982 (3.1595)	grad_norm 2.1146 (2.3214)	
[2022-01-25 00:46:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][790/1251]	eta 0:16:58 lr 0.000138	time 1.5694 (2.2101)	loss 2.6730 (3.1529)	grad_norm 2.0194 (2.3205)	
[2022-01-25 00:46:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][800/1251]	eta 0:16:36 lr 0.000138	time 2.3481 (2.2090)	loss 2.9183 (3.1528)	grad_norm 2.2281 (2.3186)	
[2022-01-25 00:47:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][810/1251]	eta 0:16:13 lr 0.000138	time 2.2496 (2.2086)	loss 2.2368 (3.1523)	grad_norm 2.7214 (2.3200)	
[2022-01-25 00:47:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][820/1251]	eta 0:15:52 lr 0.000138	time 2.2024 (2.2101)	loss 3.6155 (3.1523)	grad_norm 2.6367 (2.3210)	
[2022-01-25 00:47:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][830/1251]	eta 0:15:30 lr 0.000138	time 1.8280 (2.2091)	loss 3.5700 (3.1539)	grad_norm 2.3040 (2.3217)	
[2022-01-25 00:48:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][840/1251]	eta 0:15:07 lr 0.000138	time 1.9546 (2.2092)	loss 3.2805 (3.1569)	grad_norm 2.1876 (2.3221)	
[2022-01-25 00:48:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][850/1251]	eta 0:14:46 lr 0.000138	time 2.8904 (2.2101)	loss 3.2478 (3.1547)	grad_norm 2.2497 (2.3221)	
[2022-01-25 00:49:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][860/1251]	eta 0:14:24 lr 0.000138	time 2.0507 (2.2107)	loss 3.0883 (3.1542)	grad_norm 2.3179 (2.3232)	
[2022-01-25 00:49:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][870/1251]	eta 0:14:01 lr 0.000138	time 2.0396 (2.2097)	loss 2.6370 (3.1524)	grad_norm 3.1135 (2.3252)	
[2022-01-25 00:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][880/1251]	eta 0:13:39 lr 0.000138	time 2.2626 (2.2096)	loss 3.9475 (3.1511)	grad_norm 2.3893 (2.3263)	
[2022-01-25 00:50:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][890/1251]	eta 0:13:17 lr 0.000138	time 2.9592 (2.2091)	loss 2.3592 (3.1525)	grad_norm 2.5609 (2.3247)	
[2022-01-25 00:50:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][900/1251]	eta 0:12:54 lr 0.000138	time 1.9444 (2.2073)	loss 3.3692 (3.1549)	grad_norm 2.1238 (2.3255)	
[2022-01-25 00:50:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][910/1251]	eta 0:12:31 lr 0.000138	time 1.9023 (2.2052)	loss 3.5299 (3.1551)	grad_norm 2.4346 (2.3264)	
[2022-01-25 00:51:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][920/1251]	eta 0:12:09 lr 0.000138	time 2.2150 (2.2050)	loss 3.5662 (3.1530)	grad_norm 2.4448 (2.3323)	
[2022-01-25 00:51:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][930/1251]	eta 0:11:47 lr 0.000138	time 2.5224 (2.2049)	loss 3.1225 (3.1555)	grad_norm 2.8469 (2.3333)	
[2022-01-25 00:51:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][940/1251]	eta 0:11:25 lr 0.000138	time 2.2168 (2.2045)	loss 3.6551 (3.1552)	grad_norm 2.5662 (2.3331)	
[2022-01-25 00:52:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][950/1251]	eta 0:11:03 lr 0.000138	time 2.4808 (2.2055)	loss 3.0393 (3.1542)	grad_norm 2.2605 (2.3342)	
[2022-01-25 00:52:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][960/1251]	eta 0:10:42 lr 0.000138	time 2.1645 (2.2066)	loss 3.2444 (3.1553)	grad_norm 2.2705 (2.3369)	
[2022-01-25 00:53:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][970/1251]	eta 0:10:20 lr 0.000138	time 2.8247 (2.2085)	loss 3.3147 (3.1551)	grad_norm 2.5141 (2.3375)	
[2022-01-25 00:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][980/1251]	eta 0:09:58 lr 0.000138	time 2.1784 (2.2090)	loss 3.1614 (3.1546)	grad_norm 2.0491 (2.3379)	
[2022-01-25 00:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][990/1251]	eta 0:09:36 lr 0.000138	time 2.5213 (2.2081)	loss 3.2237 (3.1533)	grad_norm 2.2534 (2.3383)	
[2022-01-25 00:54:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1000/1251]	eta 0:09:13 lr 0.000138	time 1.8098 (2.2061)	loss 2.6266 (3.1551)	grad_norm 2.0049 (2.3396)	
[2022-01-25 00:54:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1010/1251]	eta 0:08:51 lr 0.000138	time 2.7939 (2.2050)	loss 3.6176 (3.1543)	grad_norm 2.2400 (2.3389)	
[2022-01-25 00:54:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1020/1251]	eta 0:08:29 lr 0.000138	time 2.2117 (2.2055)	loss 3.6356 (3.1558)	grad_norm 2.2372 (2.3377)	
[2022-01-25 00:55:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1030/1251]	eta 0:08:07 lr 0.000138	time 1.8852 (2.2062)	loss 3.3420 (3.1572)	grad_norm 2.3085 (2.3366)	
[2022-01-25 00:55:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1040/1251]	eta 0:07:45 lr 0.000138	time 2.2138 (2.2060)	loss 2.5148 (3.1559)	grad_norm 2.8918 (2.3369)	
[2022-01-25 00:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1050/1251]	eta 0:07:23 lr 0.000138	time 2.9779 (2.2050)	loss 3.4889 (3.1584)	grad_norm 2.9462 (2.3367)	
[2022-01-25 00:56:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1060/1251]	eta 0:07:00 lr 0.000138	time 1.8250 (2.2033)	loss 2.9334 (3.1588)	grad_norm 2.4866 (2.3365)	
[2022-01-25 00:56:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1070/1251]	eta 0:06:38 lr 0.000138	time 2.4838 (2.2035)	loss 3.2339 (3.1587)	grad_norm 2.1221 (2.3354)	
[2022-01-25 00:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1080/1251]	eta 0:06:16 lr 0.000138	time 2.2740 (2.2043)	loss 3.8507 (3.1618)	grad_norm 2.1611 (2.3357)	
[2022-01-25 00:57:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1090/1251]	eta 0:05:54 lr 0.000138	time 2.9539 (2.2043)	loss 3.6442 (3.1623)	grad_norm 2.5221 (2.3372)	
[2022-01-25 00:57:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1100/1251]	eta 0:05:32 lr 0.000138	time 1.8140 (2.2042)	loss 3.0351 (3.1643)	grad_norm 3.2912 (2.3394)	
[2022-01-25 00:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1110/1251]	eta 0:05:10 lr 0.000138	time 2.6268 (2.2045)	loss 3.0975 (3.1632)	grad_norm 3.0813 (2.3402)	
[2022-01-25 00:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1120/1251]	eta 0:04:48 lr 0.000138	time 2.2365 (2.2041)	loss 3.4388 (3.1628)	grad_norm 2.1389 (2.3419)	
[2022-01-25 00:58:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1130/1251]	eta 0:04:26 lr 0.000137	time 1.8053 (2.2042)	loss 3.6777 (3.1640)	grad_norm 2.4487 (2.3420)	
[2022-01-25 00:59:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1140/1251]	eta 0:04:04 lr 0.000137	time 2.3048 (2.2036)	loss 3.2998 (3.1631)	grad_norm 2.2234 (2.3408)	
[2022-01-25 00:59:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1150/1251]	eta 0:03:42 lr 0.000137	time 3.1191 (2.2048)	loss 2.1856 (3.1646)	grad_norm 2.0776 (2.3405)	
[2022-01-25 00:59:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1160/1251]	eta 0:03:20 lr 0.000137	time 1.9466 (2.2036)	loss 3.5155 (3.1670)	grad_norm 2.0789 (2.3398)	
[2022-01-25 01:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1170/1251]	eta 0:02:58 lr 0.000137	time 1.9803 (2.2015)	loss 2.9798 (3.1680)	grad_norm 2.0133 (2.3392)	
[2022-01-25 01:00:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1180/1251]	eta 0:02:36 lr 0.000137	time 2.2378 (2.2008)	loss 3.1598 (3.1692)	grad_norm 1.9962 (2.3379)	
[2022-01-25 01:01:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1190/1251]	eta 0:02:14 lr 0.000137	time 2.2349 (2.2019)	loss 2.0419 (3.1693)	grad_norm 2.3506 (2.3371)	
[2022-01-25 01:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1200/1251]	eta 0:01:52 lr 0.000137	time 2.1063 (2.2028)	loss 3.3649 (3.1712)	grad_norm 2.4005 (2.3362)	
[2022-01-25 01:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1210/1251]	eta 0:01:30 lr 0.000137	time 1.9721 (2.2024)	loss 3.4014 (3.1712)	grad_norm 3.0230 (2.3360)	
[2022-01-25 01:02:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1220/1251]	eta 0:01:08 lr 0.000137	time 1.9838 (2.2016)	loss 2.1417 (3.1690)	grad_norm 2.4781 (2.3360)	
[2022-01-25 01:02:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1230/1251]	eta 0:00:46 lr 0.000137	time 2.7690 (2.2010)	loss 3.4279 (3.1700)	grad_norm 2.2922 (2.3353)	
[2022-01-25 01:02:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1240/1251]	eta 0:00:24 lr 0.000137	time 1.4777 (2.1999)	loss 3.6354 (3.1710)	grad_norm 2.1053 (2.3353)	
[2022-01-25 01:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [229/300][1250/1251]	eta 0:00:02 lr 0.000137	time 1.2907 (2.1943)	loss 2.2293 (3.1703)	grad_norm 2.3088 (2.3350)	
[2022-01-25 01:03:04 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 229 training takes 0:45:45
[2022-01-25 01:03:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.999 (18.999)	Loss 0.9517 (0.9517)	Acc@1 77.246 (77.246)	Acc@5 93.945 (93.945)	
[2022-01-25 01:03:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.363 (3.350)	Loss 0.8263 (0.8602)	Acc@1 80.469 (79.714)	Acc@5 95.703 (95.046)	
[2022-01-25 01:04:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.634 (2.668)	Loss 0.8497 (0.8648)	Acc@1 80.371 (79.567)	Acc@5 95.117 (94.996)	
[2022-01-25 01:04:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.656 (2.357)	Loss 0.8293 (0.8699)	Acc@1 79.688 (79.442)	Acc@5 94.629 (94.912)	
[2022-01-25 01:04:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.378 (2.221)	Loss 0.7644 (0.8595)	Acc@1 82.031 (79.671)	Acc@5 94.922 (94.981)	
[2022-01-25 01:04:43 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.692 Acc@5 95.028
[2022-01-25 01:04:43 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.7%
[2022-01-25 01:04:43 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.69%
[2022-01-25 01:05:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][0/1251]	eta 7:30:03 lr 0.000137	time 21.5857 (21.5857)	loss 3.3694 (3.3694)	grad_norm 2.4170 (2.4170)	
[2022-01-25 01:05:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][10/1251]	eta 1:22:44 lr 0.000137	time 2.1433 (4.0005)	loss 3.4034 (3.2918)	grad_norm 2.2425 (2.4662)	
[2022-01-25 01:05:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][20/1251]	eta 1:05:27 lr 0.000137	time 1.6778 (3.1908)	loss 3.6075 (3.1199)	grad_norm 2.2003 (2.3779)	
[2022-01-25 01:06:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][30/1251]	eta 0:58:49 lr 0.000137	time 1.4905 (2.8907)	loss 3.2057 (3.1401)	grad_norm 2.4696 (2.3768)	
[2022-01-25 01:06:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][40/1251]	eta 0:55:24 lr 0.000137	time 3.8861 (2.7451)	loss 3.8234 (3.1458)	grad_norm 2.2242 (2.3816)	
[2022-01-25 01:06:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][50/1251]	eta 0:52:58 lr 0.000137	time 2.8052 (2.6461)	loss 3.6125 (3.1172)	grad_norm 2.4124 (2.3644)	
[2022-01-25 01:07:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][60/1251]	eta 0:51:37 lr 0.000137	time 1.8469 (2.6004)	loss 2.4139 (3.1061)	grad_norm 2.5529 (2.3543)	
[2022-01-25 01:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][70/1251]	eta 0:50:07 lr 0.000137	time 1.9348 (2.5465)	loss 3.5284 (3.0760)	grad_norm 2.3644 (2.3619)	
[2022-01-25 01:08:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][80/1251]	eta 0:49:09 lr 0.000137	time 3.3492 (2.5190)	loss 3.6375 (3.0945)	grad_norm 2.4319 (2.3556)	
[2022-01-25 01:08:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][90/1251]	eta 0:48:02 lr 0.000137	time 2.8228 (2.4827)	loss 3.0557 (3.1020)	grad_norm 2.1304 (2.3443)	
[2022-01-25 01:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][100/1251]	eta 0:46:24 lr 0.000137	time 1.9900 (2.4193)	loss 2.5663 (3.1048)	grad_norm 2.0972 (2.3287)	
[2022-01-25 01:09:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][110/1251]	eta 0:45:26 lr 0.000137	time 1.6048 (2.3892)	loss 3.4343 (3.1098)	grad_norm 2.1324 (2.3272)	
[2022-01-25 01:09:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][120/1251]	eta 0:44:51 lr 0.000137	time 2.8266 (2.3801)	loss 2.7487 (3.1083)	grad_norm 2.8111 (2.3299)	
[2022-01-25 01:09:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][130/1251]	eta 0:44:04 lr 0.000137	time 2.5295 (2.3589)	loss 2.1057 (3.1051)	grad_norm 2.5272 (2.3513)	
[2022-01-25 01:10:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][140/1251]	eta 0:43:28 lr 0.000137	time 1.9097 (2.3482)	loss 3.5125 (3.1116)	grad_norm 3.5339 (2.3684)	
[2022-01-25 01:10:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][150/1251]	eta 0:42:51 lr 0.000137	time 1.8876 (2.3359)	loss 3.4542 (3.1181)	grad_norm 2.3501 (2.3737)	
[2022-01-25 01:10:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][160/1251]	eta 0:42:25 lr 0.000137	time 2.8299 (2.3334)	loss 3.2824 (3.1213)	grad_norm 2.3479 (2.3830)	
[2022-01-25 01:11:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][170/1251]	eta 0:41:47 lr 0.000137	time 2.3002 (2.3200)	loss 3.0130 (3.1177)	grad_norm 2.8623 (2.3906)	
[2022-01-25 01:11:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][180/1251]	eta 0:41:15 lr 0.000137	time 1.8697 (2.3117)	loss 1.9324 (3.1030)	grad_norm 2.4959 (2.4093)	
[2022-01-25 01:12:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][190/1251]	eta 0:40:45 lr 0.000137	time 1.8326 (2.3045)	loss 2.9436 (3.1004)	grad_norm 2.5540 (2.4084)	
[2022-01-25 01:12:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][200/1251]	eta 0:40:19 lr 0.000137	time 2.7560 (2.3022)	loss 3.6041 (3.1124)	grad_norm 2.4750 (2.4037)	
[2022-01-25 01:12:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][210/1251]	eta 0:39:48 lr 0.000137	time 1.9444 (2.2944)	loss 2.1815 (3.1172)	grad_norm 2.1385 (2.3984)	
[2022-01-25 01:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][220/1251]	eta 0:39:24 lr 0.000137	time 2.7156 (2.2931)	loss 2.1484 (3.1220)	grad_norm 2.2700 (2.3944)	
[2022-01-25 01:13:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][230/1251]	eta 0:39:04 lr 0.000137	time 2.4999 (2.2962)	loss 2.6936 (3.1099)	grad_norm 2.5053 (2.3961)	
[2022-01-25 01:13:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][240/1251]	eta 0:38:34 lr 0.000136	time 2.0363 (2.2895)	loss 3.6550 (3.1082)	grad_norm 2.1772 (2.3905)	
[2022-01-25 01:14:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][250/1251]	eta 0:37:58 lr 0.000136	time 2.2593 (2.2767)	loss 3.0903 (3.0990)	grad_norm 2.5623 (2.3853)	
[2022-01-25 01:14:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][260/1251]	eta 0:37:31 lr 0.000136	time 2.1958 (2.2718)	loss 2.5635 (3.0959)	grad_norm 2.1133 (2.3779)	
[2022-01-25 01:14:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][270/1251]	eta 0:37:04 lr 0.000136	time 2.6872 (2.2680)	loss 3.7323 (3.0956)	grad_norm 2.1485 (2.3761)	
[2022-01-25 01:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][280/1251]	eta 0:36:41 lr 0.000136	time 3.3551 (2.2668)	loss 2.6804 (3.1001)	grad_norm 2.0750 (2.3744)	
[2022-01-25 01:15:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][290/1251]	eta 0:36:20 lr 0.000136	time 1.8173 (2.2691)	loss 3.3064 (3.0957)	grad_norm 2.3485 (2.3759)	
[2022-01-25 01:16:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][300/1251]	eta 0:35:56 lr 0.000136	time 1.8340 (2.2674)	loss 3.3641 (3.0942)	grad_norm 2.2420 (2.3750)	
[2022-01-25 01:16:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][310/1251]	eta 0:35:30 lr 0.000136	time 2.8127 (2.2642)	loss 3.8769 (3.0965)	grad_norm 2.4492 (2.3786)	
[2022-01-25 01:16:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][320/1251]	eta 0:35:00 lr 0.000136	time 2.0538 (2.2565)	loss 3.1844 (3.0994)	grad_norm 2.2382 (2.3747)	
[2022-01-25 01:17:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][330/1251]	eta 0:34:29 lr 0.000136	time 2.3276 (2.2474)	loss 3.2332 (3.0950)	grad_norm 2.3650 (2.3717)	
[2022-01-25 01:17:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][340/1251]	eta 0:34:01 lr 0.000136	time 1.7712 (2.2407)	loss 3.6543 (3.0989)	grad_norm 2.2103 (2.3646)	
[2022-01-25 01:17:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][350/1251]	eta 0:33:32 lr 0.000136	time 1.9538 (2.2339)	loss 2.1430 (3.1001)	grad_norm 2.0506 (2.3611)	
[2022-01-25 01:18:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][360/1251]	eta 0:33:11 lr 0.000136	time 2.8314 (2.2346)	loss 2.0743 (3.0996)	grad_norm 2.6947 (2.3642)	
[2022-01-25 01:18:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][370/1251]	eta 0:32:46 lr 0.000136	time 2.7588 (2.2318)	loss 2.2930 (3.0993)	grad_norm 2.2015 (2.3647)	
[2022-01-25 01:18:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][380/1251]	eta 0:32:25 lr 0.000136	time 2.3043 (2.2340)	loss 3.8450 (3.1002)	grad_norm 2.6299 (2.3629)	
[2022-01-25 01:19:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][390/1251]	eta 0:32:06 lr 0.000136	time 1.9065 (2.2370)	loss 2.2630 (3.0995)	grad_norm 2.8853 (2.3663)	
[2022-01-25 01:19:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][400/1251]	eta 0:31:50 lr 0.000136	time 2.5322 (2.2444)	loss 3.4987 (3.1038)	grad_norm 2.2186 (2.3654)	
[2022-01-25 01:20:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][410/1251]	eta 0:31:28 lr 0.000136	time 2.8978 (2.2451)	loss 2.9052 (3.1014)	grad_norm 3.0362 (2.3666)	
[2022-01-25 01:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][420/1251]	eta 0:31:04 lr 0.000136	time 1.8648 (2.2436)	loss 2.1146 (3.1038)	grad_norm 2.3855 (2.3671)	
[2022-01-25 01:20:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][430/1251]	eta 0:30:37 lr 0.000136	time 2.1438 (2.2382)	loss 3.4635 (3.1024)	grad_norm 2.4076 (2.3649)	
[2022-01-25 01:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][440/1251]	eta 0:30:11 lr 0.000136	time 1.8820 (2.2331)	loss 3.1945 (3.1010)	grad_norm 2.4939 (2.3630)	
[2022-01-25 01:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][450/1251]	eta 0:29:46 lr 0.000136	time 2.1278 (2.2301)	loss 2.5019 (3.1014)	grad_norm 2.1940 (2.3625)	
[2022-01-25 01:21:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][460/1251]	eta 0:29:22 lr 0.000136	time 2.2230 (2.2286)	loss 2.4329 (3.1007)	grad_norm 2.5968 (2.3668)	
[2022-01-25 01:22:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][470/1251]	eta 0:29:00 lr 0.000136	time 2.8150 (2.2283)	loss 3.7709 (3.1010)	grad_norm 2.6373 (2.3658)	
[2022-01-25 01:22:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][480/1251]	eta 0:28:37 lr 0.000136	time 2.2336 (2.2274)	loss 3.0370 (3.1015)	grad_norm 2.3917 (2.3636)	
[2022-01-25 01:22:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][490/1251]	eta 0:28:14 lr 0.000136	time 2.1934 (2.2267)	loss 3.9650 (3.1039)	grad_norm 2.5199 (2.3660)	
[2022-01-25 01:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][500/1251]	eta 0:27:52 lr 0.000136	time 2.8610 (2.2273)	loss 3.6448 (3.1099)	grad_norm 2.2889 (2.3645)	
[2022-01-25 01:23:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][510/1251]	eta 0:27:30 lr 0.000136	time 1.9036 (2.2272)	loss 2.2609 (3.1123)	grad_norm 2.6756 (2.3648)	
[2022-01-25 01:24:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][520/1251]	eta 0:27:09 lr 0.000136	time 1.7964 (2.2294)	loss 3.2933 (3.1140)	grad_norm 3.2933 (2.3661)	
[2022-01-25 01:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][530/1251]	eta 0:26:46 lr 0.000136	time 2.5456 (2.2286)	loss 3.2312 (3.1155)	grad_norm 4.5226 (2.3738)	
[2022-01-25 01:24:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][540/1251]	eta 0:26:24 lr 0.000136	time 2.6738 (2.2279)	loss 3.7051 (3.1157)	grad_norm 2.0665 (2.3821)	
[2022-01-25 01:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][550/1251]	eta 0:26:00 lr 0.000136	time 2.1566 (2.2255)	loss 3.5650 (3.1188)	grad_norm 2.4955 (2.3820)	
[2022-01-25 01:25:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][560/1251]	eta 0:25:34 lr 0.000136	time 1.8949 (2.2212)	loss 3.7529 (3.1232)	grad_norm 2.2748 (2.3853)	
[2022-01-25 01:25:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][570/1251]	eta 0:25:10 lr 0.000136	time 2.0928 (2.2176)	loss 3.3093 (3.1277)	grad_norm 2.6209 (2.3846)	
[2022-01-25 01:26:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][580/1251]	eta 0:24:47 lr 0.000136	time 2.6577 (2.2171)	loss 3.7595 (3.1297)	grad_norm 2.7713 (2.3857)	
[2022-01-25 01:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][590/1251]	eta 0:24:26 lr 0.000136	time 2.9953 (2.2190)	loss 3.5705 (3.1299)	grad_norm 2.3422 (2.3846)	
[2022-01-25 01:26:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][600/1251]	eta 0:24:04 lr 0.000135	time 1.8151 (2.2187)	loss 3.2546 (3.1297)	grad_norm 2.4167 (2.3847)	
[2022-01-25 01:27:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][610/1251]	eta 0:23:42 lr 0.000135	time 1.7279 (2.2184)	loss 3.7961 (3.1308)	grad_norm 2.2728 (2.3855)	
[2022-01-25 01:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][620/1251]	eta 0:23:20 lr 0.000135	time 1.9954 (2.2197)	loss 3.0201 (3.1295)	grad_norm 2.2218 (2.3843)	
[2022-01-25 01:28:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][630/1251]	eta 0:23:00 lr 0.000135	time 3.2840 (2.2227)	loss 2.8495 (3.1299)	grad_norm 2.0868 (2.3815)	
[2022-01-25 01:28:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][640/1251]	eta 0:22:37 lr 0.000135	time 1.9186 (2.2225)	loss 3.1135 (3.1296)	grad_norm 2.0329 (2.3776)	
[2022-01-25 01:28:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][650/1251]	eta 0:22:13 lr 0.000135	time 1.8633 (2.2185)	loss 2.5886 (3.1312)	grad_norm 2.1172 (2.3759)	
[2022-01-25 01:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][660/1251]	eta 0:21:49 lr 0.000135	time 2.1995 (2.2162)	loss 2.8218 (3.1271)	grad_norm 2.1745 (2.3734)	
[2022-01-25 01:29:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][670/1251]	eta 0:21:27 lr 0.000135	time 2.1532 (2.2156)	loss 3.1815 (3.1307)	grad_norm 2.0094 (2.3730)	
[2022-01-25 01:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][680/1251]	eta 0:21:05 lr 0.000135	time 1.8967 (2.2156)	loss 3.2700 (3.1283)	grad_norm 2.3402 (2.3723)	
[2022-01-25 01:30:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][690/1251]	eta 0:20:43 lr 0.000135	time 2.0884 (2.2157)	loss 2.0774 (3.1244)	grad_norm 2.0872 (2.3697)	
[2022-01-25 01:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][700/1251]	eta 0:20:21 lr 0.000135	time 2.3568 (2.2162)	loss 3.3438 (3.1236)	grad_norm 2.5349 (2.3695)	
[2022-01-25 01:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][710/1251]	eta 0:19:59 lr 0.000135	time 1.6690 (2.2165)	loss 3.6882 (3.1274)	grad_norm 2.2936 (2.3689)	
[2022-01-25 01:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][720/1251]	eta 0:19:38 lr 0.000135	time 2.2310 (2.2187)	loss 3.7760 (3.1287)	grad_norm 2.0860 (2.3677)	
[2022-01-25 01:31:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][730/1251]	eta 0:19:15 lr 0.000135	time 2.2592 (2.2181)	loss 3.2114 (3.1283)	grad_norm 2.2087 (2.3675)	
[2022-01-25 01:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][740/1251]	eta 0:18:51 lr 0.000135	time 1.6666 (2.2142)	loss 3.6553 (3.1301)	grad_norm 2.0205 (2.3661)	
[2022-01-25 01:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][750/1251]	eta 0:18:27 lr 0.000135	time 1.6344 (2.2108)	loss 3.4237 (3.1330)	grad_norm 2.4826 (2.3684)	
[2022-01-25 01:32:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][760/1251]	eta 0:18:05 lr 0.000135	time 2.5439 (2.2111)	loss 3.1666 (3.1305)	grad_norm 2.6337 (2.3707)	
[2022-01-25 01:33:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][770/1251]	eta 0:17:43 lr 0.000135	time 1.9427 (2.2101)	loss 3.5542 (3.1316)	grad_norm 2.3467 (2.3709)	
[2022-01-25 01:33:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][780/1251]	eta 0:17:20 lr 0.000135	time 1.8699 (2.2081)	loss 2.5304 (3.1299)	grad_norm 2.2397 (2.3689)	
[2022-01-25 01:33:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][790/1251]	eta 0:16:57 lr 0.000135	time 2.8599 (2.2079)	loss 2.6309 (3.1295)	grad_norm 2.0036 (2.3683)	
[2022-01-25 01:34:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][800/1251]	eta 0:16:35 lr 0.000135	time 1.9088 (2.2074)	loss 2.8906 (3.1292)	grad_norm 2.0978 (2.3687)	
[2022-01-25 01:34:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][810/1251]	eta 0:16:13 lr 0.000135	time 2.4989 (2.2085)	loss 3.6868 (3.1271)	grad_norm 2.4937 (2.3684)	
[2022-01-25 01:34:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][820/1251]	eta 0:15:51 lr 0.000135	time 2.2196 (2.2081)	loss 3.6532 (3.1286)	grad_norm 2.5204 (2.3688)	
[2022-01-25 01:35:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][830/1251]	eta 0:15:30 lr 0.000135	time 2.8724 (2.2101)	loss 3.3054 (3.1251)	grad_norm 2.5701 (2.3708)	
[2022-01-25 01:35:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][840/1251]	eta 0:15:08 lr 0.000135	time 2.0384 (2.2098)	loss 3.3011 (3.1255)	grad_norm 2.2392 (2.3718)	
[2022-01-25 01:36:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][850/1251]	eta 0:14:47 lr 0.000135	time 3.0011 (2.2141)	loss 2.3813 (3.1277)	grad_norm 2.3508 (2.3722)	
[2022-01-25 01:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][860/1251]	eta 0:14:25 lr 0.000135	time 1.9395 (2.2129)	loss 2.0823 (3.1280)	grad_norm 2.2655 (2.3716)	
[2022-01-25 01:36:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][870/1251]	eta 0:14:02 lr 0.000135	time 1.8768 (2.2105)	loss 2.8625 (3.1252)	grad_norm 2.3577 (2.3694)	
[2022-01-25 01:37:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][880/1251]	eta 0:13:39 lr 0.000135	time 1.8556 (2.2082)	loss 3.1618 (3.1254)	grad_norm 2.4546 (2.3697)	
[2022-01-25 01:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][890/1251]	eta 0:13:17 lr 0.000135	time 3.0521 (2.2090)	loss 3.6542 (3.1288)	grad_norm 2.3700 (2.3698)	
[2022-01-25 01:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][900/1251]	eta 0:12:55 lr 0.000135	time 2.1378 (2.2088)	loss 3.6452 (3.1268)	grad_norm 2.0425 (2.3678)	
[2022-01-25 01:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][910/1251]	eta 0:12:32 lr 0.000135	time 1.6212 (2.2078)	loss 3.6530 (3.1264)	grad_norm 2.3828 (2.3666)	
[2022-01-25 01:38:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][920/1251]	eta 0:12:10 lr 0.000135	time 2.1495 (2.2079)	loss 2.8862 (3.1276)	grad_norm 2.1085 (2.3663)	
[2022-01-25 01:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][930/1251]	eta 0:11:49 lr 0.000135	time 3.3117 (2.2105)	loss 3.4547 (3.1268)	grad_norm 2.0265 (2.3659)	
[2022-01-25 01:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][940/1251]	eta 0:11:27 lr 0.000135	time 2.2773 (2.2122)	loss 3.2359 (3.1300)	grad_norm 2.3157 (2.3670)	
[2022-01-25 01:39:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][950/1251]	eta 0:11:05 lr 0.000135	time 1.8798 (2.2114)	loss 3.3229 (3.1289)	grad_norm 2.0882 (2.3662)	
[2022-01-25 01:40:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][960/1251]	eta 0:10:42 lr 0.000134	time 1.9186 (2.2095)	loss 3.5450 (3.1285)	grad_norm 2.2698 (2.3656)	
[2022-01-25 01:40:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][970/1251]	eta 0:10:20 lr 0.000134	time 2.8341 (2.2084)	loss 3.5995 (3.1287)	grad_norm 2.0439 (2.3640)	
[2022-01-25 01:40:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][980/1251]	eta 0:09:58 lr 0.000134	time 1.9772 (2.2082)	loss 3.2246 (3.1306)	grad_norm 2.2962 (2.3674)	
[2022-01-25 01:41:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][990/1251]	eta 0:09:36 lr 0.000134	time 2.5399 (2.2082)	loss 3.5344 (3.1333)	grad_norm 2.1845 (2.3663)	
[2022-01-25 01:41:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1000/1251]	eta 0:09:14 lr 0.000134	time 2.2144 (2.2076)	loss 3.6125 (3.1362)	grad_norm 2.3013 (2.3656)	
[2022-01-25 01:41:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1010/1251]	eta 0:08:51 lr 0.000134	time 2.7812 (2.2072)	loss 3.6670 (3.1367)	grad_norm 2.1145 (2.3658)	
[2022-01-25 01:42:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1020/1251]	eta 0:08:29 lr 0.000134	time 2.4927 (2.2061)	loss 3.3424 (3.1392)	grad_norm 2.5969 (2.3656)	
[2022-01-25 01:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1030/1251]	eta 0:08:07 lr 0.000134	time 2.1720 (2.2063)	loss 3.1411 (3.1412)	grad_norm 2.4793 (2.3666)	
[2022-01-25 01:42:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1040/1251]	eta 0:07:45 lr 0.000134	time 2.4901 (2.2059)	loss 3.0400 (3.1379)	grad_norm 2.9234 (2.3666)	
[2022-01-25 01:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1050/1251]	eta 0:07:23 lr 0.000134	time 2.1865 (2.2056)	loss 2.6848 (3.1379)	grad_norm 2.4959 (2.3669)	
[2022-01-25 01:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1060/1251]	eta 0:07:01 lr 0.000134	time 2.1402 (2.2048)	loss 3.0074 (3.1404)	grad_norm 2.5194 (2.3658)	
[2022-01-25 01:44:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1070/1251]	eta 0:06:39 lr 0.000134	time 2.7401 (2.2047)	loss 3.6219 (3.1406)	grad_norm 2.1154 (2.3653)	
[2022-01-25 01:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1080/1251]	eta 0:06:16 lr 0.000134	time 2.2391 (2.2043)	loss 3.5133 (3.1397)	grad_norm 2.4466 (2.3642)	
[2022-01-25 01:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1090/1251]	eta 0:05:54 lr 0.000134	time 2.4608 (2.2045)	loss 2.6826 (3.1400)	grad_norm 2.3792 (2.3645)	
[2022-01-25 01:45:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1100/1251]	eta 0:05:32 lr 0.000134	time 1.9288 (2.2040)	loss 3.0926 (3.1421)	grad_norm 2.3712 (2.3645)	
[2022-01-25 01:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1110/1251]	eta 0:05:10 lr 0.000134	time 2.0992 (2.2043)	loss 2.8556 (3.1403)	grad_norm 2.2132 (2.3631)	
[2022-01-25 01:45:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1120/1251]	eta 0:04:48 lr 0.000134	time 2.3187 (2.2034)	loss 2.4061 (3.1395)	grad_norm 2.6693 (2.3626)	
[2022-01-25 01:46:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1130/1251]	eta 0:04:26 lr 0.000134	time 2.4947 (2.2031)	loss 2.9301 (3.1377)	grad_norm 2.5455 (2.3622)	
[2022-01-25 01:46:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1140/1251]	eta 0:04:04 lr 0.000134	time 1.8191 (2.2027)	loss 3.0307 (3.1393)	grad_norm 2.3362 (2.3611)	
[2022-01-25 01:46:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1150/1251]	eta 0:03:42 lr 0.000134	time 2.9603 (2.2023)	loss 3.5177 (3.1403)	grad_norm 2.1729 (2.3608)	
[2022-01-25 01:47:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1160/1251]	eta 0:03:20 lr 0.000134	time 2.5966 (2.2024)	loss 2.3328 (3.1418)	grad_norm 2.1471 (2.3600)	
[2022-01-25 01:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1170/1251]	eta 0:02:58 lr 0.000134	time 2.0410 (2.2014)	loss 3.2738 (3.1431)	grad_norm 2.2137 (2.3591)	
[2022-01-25 01:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1180/1251]	eta 0:02:36 lr 0.000134	time 2.3610 (2.2015)	loss 3.5594 (3.1442)	grad_norm 2.3475 (2.3591)	
[2022-01-25 01:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1190/1251]	eta 0:02:14 lr 0.000134	time 2.2042 (2.2015)	loss 3.2812 (3.1464)	grad_norm 2.0934 (2.3582)	
[2022-01-25 01:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1200/1251]	eta 0:01:52 lr 0.000134	time 2.4187 (2.2019)	loss 3.6204 (3.1469)	grad_norm 2.9997 (2.3585)	
[2022-01-25 01:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1210/1251]	eta 0:01:30 lr 0.000134	time 1.9012 (2.2017)	loss 2.5361 (3.1479)	grad_norm 2.2681 (2.3580)	
[2022-01-25 01:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1220/1251]	eta 0:01:08 lr 0.000134	time 1.6295 (2.2024)	loss 3.6546 (3.1487)	grad_norm 2.2014 (2.3572)	
[2022-01-25 01:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1230/1251]	eta 0:00:46 lr 0.000134	time 2.1895 (2.2017)	loss 3.3263 (3.1494)	grad_norm 2.3556 (2.3566)	
[2022-01-25 01:50:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1240/1251]	eta 0:00:24 lr 0.000134	time 2.2258 (2.2012)	loss 3.7425 (3.1490)	grad_norm 2.2381 (2.3551)	
[2022-01-25 01:50:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [230/300][1250/1251]	eta 0:00:02 lr 0.000134	time 1.3514 (2.1953)	loss 3.3165 (3.1510)	grad_norm 2.2233 (2.3544)	
[2022-01-25 01:50:29 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 230 training takes 0:45:46
[2022-01-25 01:50:29 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_230 saving......
[2022-01-25 01:50:41 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_230 saved !!!
[2022-01-25 01:50:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 15.392 (15.392)	Loss 0.9035 (0.9035)	Acc@1 78.125 (78.125)	Acc@5 95.508 (95.508)	
[2022-01-25 01:51:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.594 (2.701)	Loss 0.7920 (0.8529)	Acc@1 81.055 (79.954)	Acc@5 95.996 (95.197)	
[2022-01-25 01:51:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 3.737 (2.362)	Loss 0.8335 (0.8602)	Acc@1 78.809 (79.539)	Acc@5 95.508 (95.043)	
[2022-01-25 01:51:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.340 (2.178)	Loss 0.8556 (0.8635)	Acc@1 80.469 (79.672)	Acc@5 95.410 (94.947)	
[2022-01-25 01:52:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.185 (1.971)	Loss 0.8234 (0.8583)	Acc@1 79.492 (79.699)	Acc@5 96.289 (95.029)	
[2022-01-25 01:52:10 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.662 Acc@5 95.032
[2022-01-25 01:52:10 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.7%
[2022-01-25 01:52:10 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.69%
[2022-01-25 01:52:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][0/1251]	eta 7:30:21 lr 0.000134	time 21.6000 (21.6000)	loss 2.6835 (2.6835)	grad_norm 2.2602 (2.2602)	
[2022-01-25 01:52:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][10/1251]	eta 1:26:04 lr 0.000134	time 2.8546 (4.1616)	loss 3.6429 (3.1572)	grad_norm 2.1971 (2.2318)	
[2022-01-25 01:53:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][20/1251]	eta 1:06:54 lr 0.000134	time 1.4694 (3.2612)	loss 3.2075 (3.1906)	grad_norm 2.2571 (2.2480)	
[2022-01-25 01:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][30/1251]	eta 0:58:19 lr 0.000134	time 1.5493 (2.8662)	loss 3.2982 (3.1548)	grad_norm 2.2781 (2.2652)	
[2022-01-25 01:54:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][40/1251]	eta 0:55:43 lr 0.000134	time 3.7374 (2.7611)	loss 2.9925 (3.1399)	grad_norm 2.2631 (2.2603)	
[2022-01-25 01:54:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][50/1251]	eta 0:53:49 lr 0.000134	time 3.1336 (2.6886)	loss 3.4653 (3.1432)	grad_norm 2.2264 (2.2775)	
[2022-01-25 01:54:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][60/1251]	eta 0:51:24 lr 0.000134	time 1.7028 (2.5901)	loss 3.6728 (3.2008)	grad_norm 2.5240 (2.2918)	
[2022-01-25 01:55:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][70/1251]	eta 0:49:18 lr 0.000134	time 1.7934 (2.5050)	loss 3.3198 (3.2224)	grad_norm 2.2242 (2.2944)	
[2022-01-25 01:55:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][80/1251]	eta 0:48:04 lr 0.000133	time 3.2397 (2.4634)	loss 2.6162 (3.2362)	grad_norm 2.5794 (2.3119)	
[2022-01-25 01:55:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][90/1251]	eta 0:47:04 lr 0.000133	time 2.7928 (2.4327)	loss 2.8720 (3.2263)	grad_norm 2.3925 (2.3203)	
[2022-01-25 01:56:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][100/1251]	eta 0:46:12 lr 0.000133	time 2.1111 (2.4089)	loss 3.4048 (3.2405)	grad_norm 2.0369 (2.3214)	
[2022-01-25 01:56:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][110/1251]	eta 0:45:39 lr 0.000133	time 1.5825 (2.4006)	loss 2.1719 (3.2251)	grad_norm 2.3496 (2.3196)	
[2022-01-25 01:57:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][120/1251]	eta 0:45:12 lr 0.000133	time 3.1837 (2.3982)	loss 2.7552 (3.2093)	grad_norm 2.2571 (2.3281)	
[2022-01-25 01:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][130/1251]	eta 0:45:02 lr 0.000133	time 3.1320 (2.4105)	loss 3.4973 (3.2125)	grad_norm 2.7298 (2.3300)	
[2022-01-25 01:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][140/1251]	eta 0:44:09 lr 0.000133	time 1.8747 (2.3848)	loss 3.5788 (3.2252)	grad_norm 2.2050 (2.3209)	
[2022-01-25 01:58:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][150/1251]	eta 0:43:10 lr 0.000133	time 2.0219 (2.3526)	loss 3.6001 (3.2307)	grad_norm 2.3709 (2.3161)	
[2022-01-25 01:58:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][160/1251]	eta 0:42:16 lr 0.000133	time 1.8455 (2.3250)	loss 3.3522 (3.2337)	grad_norm 2.3854 (2.3168)	
[2022-01-25 01:58:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][170/1251]	eta 0:41:34 lr 0.000133	time 2.0544 (2.3079)	loss 3.6912 (3.2293)	grad_norm 2.2403 (2.3147)	
[2022-01-25 01:59:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][180/1251]	eta 0:41:06 lr 0.000133	time 2.9182 (2.3026)	loss 2.0806 (3.2217)	grad_norm 2.1967 (2.3122)	
[2022-01-25 01:59:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][190/1251]	eta 0:40:34 lr 0.000133	time 1.9697 (2.2946)	loss 3.3335 (3.2253)	grad_norm 2.4754 (2.3192)	
[2022-01-25 01:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][200/1251]	eta 0:40:06 lr 0.000133	time 2.1625 (2.2901)	loss 2.9564 (3.2317)	grad_norm 2.1606 (2.3344)	
[2022-01-25 02:00:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][210/1251]	eta 0:39:47 lr 0.000133	time 2.4748 (2.2933)	loss 3.7422 (3.2275)	grad_norm 2.1116 (2.3343)	
[2022-01-25 02:00:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][220/1251]	eta 0:39:39 lr 0.000133	time 3.1237 (2.3081)	loss 3.4823 (3.2276)	grad_norm 2.6065 (2.3312)	
[2022-01-25 02:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][230/1251]	eta 0:39:13 lr 0.000133	time 2.2602 (2.3052)	loss 3.3116 (3.2299)	grad_norm 2.2673 (2.3278)	
[2022-01-25 02:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][240/1251]	eta 0:38:41 lr 0.000133	time 1.8767 (2.2958)	loss 2.9179 (3.2180)	grad_norm 2.2344 (2.3238)	
[2022-01-25 02:01:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][250/1251]	eta 0:38:05 lr 0.000133	time 1.8867 (2.2834)	loss 2.7389 (3.2062)	grad_norm 2.0406 (2.3209)	
[2022-01-25 02:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][260/1251]	eta 0:37:30 lr 0.000133	time 1.9790 (2.2713)	loss 2.9141 (3.2058)	grad_norm 2.1330 (2.3182)	
[2022-01-25 02:02:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][270/1251]	eta 0:37:01 lr 0.000133	time 1.8514 (2.2646)	loss 2.7133 (3.2001)	grad_norm 2.4193 (2.3204)	
[2022-01-25 02:02:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][280/1251]	eta 0:36:38 lr 0.000133	time 3.3307 (2.2639)	loss 3.7579 (3.2014)	grad_norm 2.2982 (2.3264)	
[2022-01-25 02:03:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][290/1251]	eta 0:36:12 lr 0.000133	time 2.0968 (2.2607)	loss 2.4587 (3.1876)	grad_norm 2.5643 (2.3338)	
[2022-01-25 02:03:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][300/1251]	eta 0:35:48 lr 0.000133	time 2.3283 (2.2596)	loss 3.4755 (3.1861)	grad_norm 2.3153 (2.3351)	
[2022-01-25 02:03:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][310/1251]	eta 0:35:25 lr 0.000133	time 1.5969 (2.2592)	loss 2.8968 (3.1831)	grad_norm 2.8449 (2.3385)	
[2022-01-25 02:04:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][320/1251]	eta 0:35:04 lr 0.000133	time 2.8647 (2.2603)	loss 3.9066 (3.1850)	grad_norm 2.2669 (2.3420)	
[2022-01-25 02:04:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][330/1251]	eta 0:34:39 lr 0.000133	time 2.0421 (2.2576)	loss 3.3326 (3.1816)	grad_norm 2.0074 (2.3405)	
[2022-01-25 02:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][340/1251]	eta 0:34:15 lr 0.000133	time 2.6920 (2.2566)	loss 3.9335 (3.1808)	grad_norm 2.2415 (2.3451)	
[2022-01-25 02:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][350/1251]	eta 0:33:47 lr 0.000133	time 1.5873 (2.2508)	loss 3.5744 (3.1744)	grad_norm 2.7395 (2.3456)	
[2022-01-25 02:05:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][360/1251]	eta 0:33:18 lr 0.000133	time 2.0413 (2.2435)	loss 3.3108 (3.1681)	grad_norm 2.8635 (2.3461)	
[2022-01-25 02:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][370/1251]	eta 0:32:55 lr 0.000133	time 2.1762 (2.2422)	loss 2.9542 (3.1676)	grad_norm 2.4241 (2.3466)	
[2022-01-25 02:06:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][380/1251]	eta 0:32:30 lr 0.000133	time 2.3008 (2.2396)	loss 3.4540 (3.1697)	grad_norm 1.9916 (2.3467)	
[2022-01-25 02:06:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][390/1251]	eta 0:32:07 lr 0.000133	time 1.7803 (2.2382)	loss 3.3849 (3.1731)	grad_norm 2.8849 (2.3466)	
[2022-01-25 02:07:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][400/1251]	eta 0:31:49 lr 0.000133	time 2.1748 (2.2435)	loss 3.3321 (3.1772)	grad_norm 2.2808 (2.3436)	
[2022-01-25 02:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][410/1251]	eta 0:31:28 lr 0.000133	time 2.0178 (2.2451)	loss 3.6776 (3.1773)	grad_norm 2.6718 (2.3437)	
[2022-01-25 02:07:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][420/1251]	eta 0:31:04 lr 0.000133	time 1.9125 (2.2436)	loss 2.5731 (3.1793)	grad_norm 2.1255 (2.3414)	
[2022-01-25 02:08:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][430/1251]	eta 0:30:37 lr 0.000133	time 1.9318 (2.2383)	loss 2.9114 (3.1707)	grad_norm 2.4576 (2.3423)	
[2022-01-25 02:08:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][440/1251]	eta 0:30:11 lr 0.000132	time 2.2539 (2.2339)	loss 3.8291 (3.1751)	grad_norm 3.1721 (2.3424)	
[2022-01-25 02:08:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][450/1251]	eta 0:29:46 lr 0.000132	time 1.9121 (2.2309)	loss 3.3602 (3.1770)	grad_norm 2.1384 (2.3431)	
[2022-01-25 02:09:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][460/1251]	eta 0:29:24 lr 0.000132	time 1.9605 (2.2312)	loss 3.4212 (3.1802)	grad_norm 2.3503 (2.3461)	
[2022-01-25 02:09:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][470/1251]	eta 0:29:03 lr 0.000132	time 1.8841 (2.2329)	loss 2.6672 (3.1795)	grad_norm 1.9866 (2.3436)	
[2022-01-25 02:10:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][480/1251]	eta 0:28:39 lr 0.000132	time 1.6175 (2.2306)	loss 3.1805 (3.1769)	grad_norm 2.8064 (2.3472)	
[2022-01-25 02:10:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][490/1251]	eta 0:28:16 lr 0.000132	time 1.9970 (2.2298)	loss 3.4994 (3.1769)	grad_norm 2.1156 (2.3458)	
[2022-01-25 02:10:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][500/1251]	eta 0:27:52 lr 0.000132	time 2.1527 (2.2265)	loss 3.7376 (3.1780)	grad_norm 2.1204 (2.3460)	
[2022-01-25 02:11:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][510/1251]	eta 0:27:26 lr 0.000132	time 1.6207 (2.2226)	loss 2.9570 (3.1765)	grad_norm 2.5641 (2.3496)	
[2022-01-25 02:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][520/1251]	eta 0:27:03 lr 0.000132	time 2.1573 (2.2203)	loss 3.4548 (3.1787)	grad_norm 2.2286 (2.3506)	
[2022-01-25 02:11:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][530/1251]	eta 0:26:40 lr 0.000132	time 2.0514 (2.2201)	loss 3.5042 (3.1843)	grad_norm 2.1952 (2.3487)	
[2022-01-25 02:12:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][540/1251]	eta 0:26:20 lr 0.000132	time 2.7699 (2.2224)	loss 4.1612 (3.1891)	grad_norm 2.2371 (2.3455)	
[2022-01-25 02:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][550/1251]	eta 0:25:58 lr 0.000132	time 2.0319 (2.2232)	loss 3.3323 (3.1853)	grad_norm 2.3182 (2.3430)	
[2022-01-25 02:12:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][560/1251]	eta 0:25:37 lr 0.000132	time 2.4835 (2.2255)	loss 3.6271 (3.1817)	grad_norm 2.3822 (2.3426)	
[2022-01-25 02:13:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][570/1251]	eta 0:25:15 lr 0.000132	time 1.6623 (2.2258)	loss 3.6487 (3.1774)	grad_norm 2.7758 (2.3457)	
[2022-01-25 02:13:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][580/1251]	eta 0:24:51 lr 0.000132	time 2.2831 (2.2232)	loss 3.3826 (3.1754)	grad_norm 2.0312 (2.3458)	
[2022-01-25 02:14:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][590/1251]	eta 0:24:26 lr 0.000132	time 2.2198 (2.2191)	loss 2.5230 (3.1730)	grad_norm 2.2556 (2.3455)	
[2022-01-25 02:14:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][600/1251]	eta 0:24:02 lr 0.000132	time 1.9896 (2.2153)	loss 3.3961 (3.1755)	grad_norm 2.2667 (2.3460)	
[2022-01-25 02:14:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][610/1251]	eta 0:23:39 lr 0.000132	time 1.8788 (2.2146)	loss 2.9822 (3.1786)	grad_norm 2.1142 (2.3456)	
[2022-01-25 02:15:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][620/1251]	eta 0:23:19 lr 0.000132	time 2.4569 (2.2177)	loss 3.5197 (3.1811)	grad_norm 2.3041 (2.3431)	
[2022-01-25 02:15:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][630/1251]	eta 0:22:58 lr 0.000132	time 2.1619 (2.2200)	loss 3.2474 (3.1780)	grad_norm 2.2070 (2.3409)	
[2022-01-25 02:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][640/1251]	eta 0:22:38 lr 0.000132	time 2.4181 (2.2226)	loss 3.2915 (3.1776)	grad_norm 1.9946 (2.3411)	
[2022-01-25 02:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][650/1251]	eta 0:22:15 lr 0.000132	time 1.9231 (2.2224)	loss 3.6075 (3.1811)	grad_norm 2.1326 (2.3410)	
[2022-01-25 02:16:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][660/1251]	eta 0:21:53 lr 0.000132	time 2.5383 (2.2220)	loss 3.4868 (3.1835)	grad_norm 2.3457 (2.3400)	
[2022-01-25 02:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][670/1251]	eta 0:21:29 lr 0.000132	time 2.3898 (2.2199)	loss 3.1593 (3.1806)	grad_norm 2.4651 (2.3390)	
[2022-01-25 02:17:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][680/1251]	eta 0:21:06 lr 0.000132	time 2.1920 (2.2181)	loss 3.0453 (3.1766)	grad_norm 2.0243 (2.3367)	
[2022-01-25 02:17:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][690/1251]	eta 0:20:42 lr 0.000132	time 1.7106 (2.2154)	loss 2.9947 (3.1743)	grad_norm 1.9353 (2.3357)	
[2022-01-25 02:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][700/1251]	eta 0:20:21 lr 0.000132	time 2.9594 (2.2165)	loss 2.6936 (3.1732)	grad_norm 2.6592 (2.3362)	
[2022-01-25 02:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][710/1251]	eta 0:19:59 lr 0.000132	time 2.3710 (2.2170)	loss 3.6207 (3.1755)	grad_norm 2.5999 (2.3354)	
[2022-01-25 02:18:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][720/1251]	eta 0:19:36 lr 0.000132	time 2.4161 (2.2160)	loss 3.4777 (3.1773)	grad_norm 2.4639 (2.3338)	
[2022-01-25 02:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][730/1251]	eta 0:19:14 lr 0.000132	time 1.8620 (2.2161)	loss 3.4761 (3.1818)	grad_norm 2.0901 (2.3343)	
[2022-01-25 02:19:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][740/1251]	eta 0:18:52 lr 0.000132	time 2.4726 (2.2167)	loss 3.1394 (3.1781)	grad_norm 2.3520 (2.3332)	
[2022-01-25 02:19:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][750/1251]	eta 0:18:30 lr 0.000132	time 2.5489 (2.2173)	loss 3.6022 (3.1767)	grad_norm 2.4653 (2.3351)	
[2022-01-25 02:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][760/1251]	eta 0:18:09 lr 0.000132	time 2.2513 (2.2193)	loss 3.1902 (3.1768)	grad_norm 2.3164 (2.3349)	
[2022-01-25 02:20:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][770/1251]	eta 0:17:46 lr 0.000132	time 1.5917 (2.2178)	loss 2.0115 (3.1777)	grad_norm 2.0892 (2.3355)	
[2022-01-25 02:21:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][780/1251]	eta 0:17:23 lr 0.000132	time 1.6086 (2.2156)	loss 3.0580 (3.1775)	grad_norm 2.3165 (2.3398)	
[2022-01-25 02:21:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][790/1251]	eta 0:17:00 lr 0.000132	time 2.1006 (2.2132)	loss 3.4567 (3.1799)	grad_norm 2.6137 (2.3416)	
[2022-01-25 02:21:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][800/1251]	eta 0:16:36 lr 0.000132	time 2.1240 (2.2104)	loss 3.3811 (3.1820)	grad_norm 2.1548 (2.3416)	
[2022-01-25 02:22:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][810/1251]	eta 0:16:13 lr 0.000131	time 1.9246 (2.2083)	loss 3.2851 (3.1839)	grad_norm 1.9768 (2.3410)	
[2022-01-25 02:22:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][820/1251]	eta 0:15:51 lr 0.000131	time 2.4649 (2.2078)	loss 3.7728 (3.1806)	grad_norm 2.3520 (2.3413)	
[2022-01-25 02:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][830/1251]	eta 0:15:29 lr 0.000131	time 1.6999 (2.2077)	loss 2.8101 (3.1805)	grad_norm 2.4037 (2.3415)	
[2022-01-25 02:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][840/1251]	eta 0:15:09 lr 0.000131	time 2.8764 (2.2120)	loss 3.6308 (3.1825)	grad_norm 2.0231 (2.3415)	
[2022-01-25 02:23:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][850/1251]	eta 0:14:47 lr 0.000131	time 1.8825 (2.2129)	loss 3.4280 (3.1817)	grad_norm 1.9274 (2.3406)	
[2022-01-25 02:23:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][860/1251]	eta 0:14:25 lr 0.000131	time 2.0889 (2.2135)	loss 3.3122 (3.1792)	grad_norm 2.1459 (2.3402)	
[2022-01-25 02:24:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][870/1251]	eta 0:14:02 lr 0.000131	time 1.9032 (2.2122)	loss 3.8197 (3.1779)	grad_norm 2.3051 (2.3393)	
[2022-01-25 02:24:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][880/1251]	eta 0:13:40 lr 0.000131	time 2.5571 (2.2108)	loss 3.9839 (3.1798)	grad_norm 2.6605 (2.3414)	
[2022-01-25 02:24:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][890/1251]	eta 0:13:17 lr 0.000131	time 1.9506 (2.2085)	loss 2.9718 (3.1758)	grad_norm 2.2972 (2.3427)	
[2022-01-25 02:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][900/1251]	eta 0:12:54 lr 0.000131	time 2.2518 (2.2074)	loss 3.1819 (3.1756)	grad_norm 2.0214 (2.3422)	
[2022-01-25 02:25:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][910/1251]	eta 0:12:32 lr 0.000131	time 1.8476 (2.2058)	loss 3.4662 (3.1744)	grad_norm 2.2797 (2.3421)	
[2022-01-25 02:26:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][920/1251]	eta 0:12:10 lr 0.000131	time 2.6396 (2.2070)	loss 2.6342 (3.1741)	grad_norm 2.2189 (2.3426)	
[2022-01-25 02:26:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][930/1251]	eta 0:11:48 lr 0.000131	time 2.2667 (2.2066)	loss 3.3054 (3.1710)	grad_norm 2.2438 (2.3415)	
[2022-01-25 02:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][940/1251]	eta 0:11:26 lr 0.000131	time 2.4552 (2.2076)	loss 3.5755 (3.1717)	grad_norm 2.3016 (2.3425)	
[2022-01-25 02:27:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][950/1251]	eta 0:11:04 lr 0.000131	time 1.5012 (2.2078)	loss 3.3486 (3.1733)	grad_norm 2.1969 (2.3420)	
[2022-01-25 02:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][960/1251]	eta 0:10:42 lr 0.000131	time 3.4534 (2.2079)	loss 2.8374 (3.1711)	grad_norm 2.1363 (2.3418)	
[2022-01-25 02:27:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][970/1251]	eta 0:10:20 lr 0.000131	time 1.6533 (2.2074)	loss 2.7289 (3.1681)	grad_norm 2.2580 (2.3412)	
[2022-01-25 02:28:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][980/1251]	eta 0:09:58 lr 0.000131	time 1.5832 (2.2081)	loss 2.4541 (3.1695)	grad_norm 2.2344 (2.3409)	
[2022-01-25 02:28:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][990/1251]	eta 0:09:36 lr 0.000131	time 1.9067 (2.2082)	loss 3.8542 (3.1702)	grad_norm 2.4269 (2.3413)	
[2022-01-25 02:29:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1000/1251]	eta 0:09:14 lr 0.000131	time 3.3488 (2.2090)	loss 3.3000 (3.1710)	grad_norm 2.1824 (2.3407)	
[2022-01-25 02:29:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1010/1251]	eta 0:08:51 lr 0.000131	time 1.6743 (2.2072)	loss 3.3228 (3.1697)	grad_norm 2.2363 (2.3401)	
[2022-01-25 02:29:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1020/1251]	eta 0:08:29 lr 0.000131	time 1.8077 (2.2055)	loss 2.8554 (3.1673)	grad_norm 2.3203 (2.3399)	
[2022-01-25 02:30:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1030/1251]	eta 0:08:07 lr 0.000131	time 1.6429 (2.2055)	loss 2.3403 (3.1683)	grad_norm 2.4486 (2.3399)	
[2022-01-25 02:30:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1040/1251]	eta 0:07:45 lr 0.000131	time 3.6756 (2.2076)	loss 2.8030 (3.1666)	grad_norm 2.7631 (2.3403)	
[2022-01-25 02:30:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1050/1251]	eta 0:07:23 lr 0.000131	time 1.9105 (2.2071)	loss 3.7053 (3.1639)	grad_norm 2.5744 (2.3406)	
[2022-01-25 02:31:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1060/1251]	eta 0:07:01 lr 0.000131	time 1.8614 (2.2070)	loss 3.2727 (3.1644)	grad_norm 2.5839 (2.3399)	
[2022-01-25 02:31:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1070/1251]	eta 0:06:39 lr 0.000131	time 1.6777 (2.2056)	loss 3.3981 (3.1670)	grad_norm 2.1506 (2.3394)	
[2022-01-25 02:31:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1080/1251]	eta 0:06:17 lr 0.000131	time 3.5355 (2.2067)	loss 2.1425 (3.1657)	grad_norm 2.4922 (2.3394)	
[2022-01-25 02:32:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1090/1251]	eta 0:05:55 lr 0.000131	time 1.9889 (2.2063)	loss 2.8110 (3.1652)	grad_norm 2.2963 (2.3396)	
[2022-01-25 02:32:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1100/1251]	eta 0:05:33 lr 0.000131	time 1.9930 (2.2054)	loss 2.5780 (3.1651)	grad_norm 2.1692 (2.3396)	
[2022-01-25 02:32:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1110/1251]	eta 0:05:10 lr 0.000131	time 2.2100 (2.2036)	loss 3.1602 (3.1635)	grad_norm 2.2813 (2.3383)	
[2022-01-25 02:33:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1120/1251]	eta 0:04:48 lr 0.000131	time 2.5838 (2.2044)	loss 3.5904 (3.1662)	grad_norm 2.6559 (2.3375)	
[2022-01-25 02:33:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1130/1251]	eta 0:04:26 lr 0.000131	time 3.0961 (2.2045)	loss 3.3240 (3.1671)	grad_norm 2.1866 (2.3367)	
[2022-01-25 02:34:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1140/1251]	eta 0:04:04 lr 0.000131	time 1.5452 (2.2049)	loss 3.8056 (3.1674)	grad_norm 1.9799 (2.3363)	
[2022-01-25 02:34:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1150/1251]	eta 0:03:42 lr 0.000131	time 1.8766 (2.2039)	loss 3.8715 (3.1680)	grad_norm 2.3335 (2.3364)	
[2022-01-25 02:34:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1160/1251]	eta 0:03:20 lr 0.000131	time 1.6121 (2.2029)	loss 3.0037 (3.1693)	grad_norm 2.3417 (2.3355)	
[2022-01-25 02:35:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1170/1251]	eta 0:02:58 lr 0.000131	time 1.6143 (2.2022)	loss 2.6898 (3.1691)	grad_norm 2.1518 (2.3354)	
[2022-01-25 02:35:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1180/1251]	eta 0:02:36 lr 0.000130	time 1.9065 (2.2035)	loss 3.2808 (3.1694)	grad_norm 2.4071 (2.3369)	
[2022-01-25 02:35:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1190/1251]	eta 0:02:14 lr 0.000130	time 1.8960 (2.2035)	loss 3.3747 (3.1696)	grad_norm 2.4506 (2.3378)	
[2022-01-25 02:36:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1200/1251]	eta 0:01:52 lr 0.000130	time 2.2493 (2.2043)	loss 3.2994 (3.1713)	grad_norm 2.7377 (2.3380)	
[2022-01-25 02:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1210/1251]	eta 0:01:30 lr 0.000130	time 1.9267 (2.2042)	loss 3.3978 (3.1711)	grad_norm 2.2668 (2.3379)	
[2022-01-25 02:37:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1220/1251]	eta 0:01:08 lr 0.000130	time 2.2238 (2.2045)	loss 3.5116 (3.1697)	grad_norm 2.2915 (2.3384)	
[2022-01-25 02:37:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1230/1251]	eta 0:00:46 lr 0.000130	time 1.5707 (2.2023)	loss 3.2543 (3.1718)	grad_norm 2.0692 (2.3386)	
[2022-01-25 02:37:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1240/1251]	eta 0:00:24 lr 0.000130	time 1.3007 (2.2002)	loss 3.4329 (3.1722)	grad_norm 1.8928 (2.3375)	
[2022-01-25 02:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [231/300][1250/1251]	eta 0:00:02 lr 0.000130	time 1.1903 (2.1944)	loss 3.3331 (3.1742)	grad_norm 2.4322 (2.3369)	
[2022-01-25 02:37:55 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 231 training takes 0:45:45
[2022-01-25 02:38:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.460 (18.460)	Loss 0.8310 (0.8310)	Acc@1 79.004 (79.004)	Acc@5 95.605 (95.605)	
[2022-01-25 02:38:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.198 (3.426)	Loss 0.9158 (0.8703)	Acc@1 78.320 (79.492)	Acc@5 94.238 (94.984)	
[2022-01-25 02:38:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.530 (2.626)	Loss 0.8025 (0.8621)	Acc@1 80.273 (79.636)	Acc@5 95.605 (95.085)	
[2022-01-25 02:39:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.646 (2.232)	Loss 0.8866 (0.8668)	Acc@1 78.125 (79.543)	Acc@5 94.922 (94.994)	
[2022-01-25 02:39:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.365 (2.200)	Loss 0.8401 (0.8640)	Acc@1 78.027 (79.509)	Acc@5 95.117 (95.020)	
[2022-01-25 02:39:33 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.520 Acc@5 95.050
[2022-01-25 02:39:33 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.5%
[2022-01-25 02:39:33 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.69%
[2022-01-25 02:39:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][0/1251]	eta 7:25:09 lr 0.000130	time 21.3503 (21.3503)	loss 3.5116 (3.5116)	grad_norm 2.1936 (2.1936)	
[2022-01-25 02:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][10/1251]	eta 1:20:07 lr 0.000130	time 1.8982 (3.8743)	loss 3.4772 (3.2882)	grad_norm 2.0999 (2.2972)	
[2022-01-25 02:40:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][20/1251]	eta 1:03:32 lr 0.000130	time 1.4587 (3.0972)	loss 3.5401 (3.2763)	grad_norm 2.0306 (2.3193)	
[2022-01-25 02:40:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][30/1251]	eta 0:55:43 lr 0.000130	time 1.3952 (2.7383)	loss 3.9275 (3.3194)	grad_norm 2.5227 (2.3418)	
[2022-01-25 02:41:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][40/1251]	eta 0:52:46 lr 0.000130	time 3.3469 (2.6146)	loss 3.3869 (3.2930)	grad_norm 2.0565 (2.3565)	
[2022-01-25 02:41:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][50/1251]	eta 0:51:33 lr 0.000130	time 2.6126 (2.5756)	loss 2.9199 (3.2509)	grad_norm 2.3377 (2.3595)	
[2022-01-25 02:42:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][60/1251]	eta 0:50:02 lr 0.000130	time 1.4730 (2.5211)	loss 3.9121 (3.2411)	grad_norm 2.4281 (2.3357)	
[2022-01-25 02:42:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][70/1251]	eta 0:48:55 lr 0.000130	time 1.5779 (2.4854)	loss 3.1796 (3.2122)	grad_norm 2.4330 (2.3800)	
[2022-01-25 02:42:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][80/1251]	eta 0:48:18 lr 0.000130	time 2.5833 (2.4749)	loss 3.2902 (3.2157)	grad_norm 2.7044 (2.3800)	
[2022-01-25 02:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][90/1251]	eta 0:47:29 lr 0.000130	time 1.8815 (2.4546)	loss 3.2409 (3.2180)	grad_norm 2.0108 (2.3888)	
[2022-01-25 02:43:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][100/1251]	eta 0:46:19 lr 0.000130	time 1.5751 (2.4145)	loss 3.0085 (3.2067)	grad_norm 2.6577 (2.3884)	
[2022-01-25 02:43:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][110/1251]	eta 0:45:20 lr 0.000130	time 2.0644 (2.3841)	loss 3.0039 (3.1934)	grad_norm 1.9449 (2.3770)	
[2022-01-25 02:44:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][120/1251]	eta 0:44:40 lr 0.000130	time 1.8798 (2.3704)	loss 3.3899 (3.1922)	grad_norm 2.6692 (2.3712)	
[2022-01-25 02:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][130/1251]	eta 0:44:37 lr 0.000130	time 3.7036 (2.3885)	loss 2.6465 (3.1753)	grad_norm 2.3547 (2.3561)	
[2022-01-25 02:45:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][140/1251]	eta 0:44:11 lr 0.000130	time 2.3440 (2.3863)	loss 3.6237 (3.1749)	grad_norm 2.1028 (2.3583)	
[2022-01-25 02:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][150/1251]	eta 0:43:34 lr 0.000130	time 1.8591 (2.3748)	loss 2.6761 (3.1643)	grad_norm 2.1767 (2.3562)	
[2022-01-25 02:45:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][160/1251]	eta 0:43:07 lr 0.000130	time 2.1391 (2.3720)	loss 2.5807 (3.1417)	grad_norm 2.1521 (2.3485)	
[2022-01-25 02:46:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][170/1251]	eta 0:42:17 lr 0.000130	time 1.6236 (2.3469)	loss 3.1666 (3.1351)	grad_norm 2.2421 (2.3412)	
[2022-01-25 02:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][180/1251]	eta 0:41:30 lr 0.000130	time 1.7733 (2.3257)	loss 3.7232 (3.1320)	grad_norm 2.2055 (2.3366)	
[2022-01-25 02:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][190/1251]	eta 0:40:56 lr 0.000130	time 2.1834 (2.3154)	loss 3.6767 (3.1413)	grad_norm 2.1535 (2.3302)	
[2022-01-25 02:47:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][200/1251]	eta 0:40:30 lr 0.000130	time 2.6147 (2.3123)	loss 3.7333 (3.1483)	grad_norm 2.2068 (2.3302)	
[2022-01-25 02:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][210/1251]	eta 0:40:08 lr 0.000130	time 2.2589 (2.3135)	loss 2.1726 (3.1471)	grad_norm 2.2938 (2.3310)	
[2022-01-25 02:48:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][220/1251]	eta 0:39:47 lr 0.000130	time 2.7059 (2.3153)	loss 3.3065 (3.1498)	grad_norm 2.1722 (2.3337)	
[2022-01-25 02:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][230/1251]	eta 0:39:23 lr 0.000130	time 2.5234 (2.3151)	loss 3.6494 (3.1513)	grad_norm 2.2184 (2.3364)	
[2022-01-25 02:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][240/1251]	eta 0:38:53 lr 0.000130	time 1.8988 (2.3083)	loss 3.2246 (3.1507)	grad_norm 2.3225 (2.3340)	
[2022-01-25 02:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][250/1251]	eta 0:38:15 lr 0.000130	time 1.9290 (2.2937)	loss 3.7878 (3.1579)	grad_norm 2.1430 (2.3310)	
[2022-01-25 02:49:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][260/1251]	eta 0:37:44 lr 0.000130	time 1.8625 (2.2855)	loss 2.1399 (3.1633)	grad_norm 2.0773 (2.3321)	
[2022-01-25 02:49:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][270/1251]	eta 0:37:16 lr 0.000130	time 1.8280 (2.2794)	loss 3.6163 (3.1629)	grad_norm 2.1092 (2.3274)	
[2022-01-25 02:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][280/1251]	eta 0:36:58 lr 0.000130	time 2.7347 (2.2847)	loss 2.7938 (3.1627)	grad_norm 2.0640 (2.3256)	
[2022-01-25 02:50:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][290/1251]	eta 0:36:31 lr 0.000130	time 1.8620 (2.2802)	loss 3.4863 (3.1549)	grad_norm 2.1501 (2.3255)	
[2022-01-25 02:50:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][300/1251]	eta 0:36:06 lr 0.000129	time 2.0262 (2.2780)	loss 2.3564 (3.1596)	grad_norm 2.1040 (2.3245)	
[2022-01-25 02:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][310/1251]	eta 0:35:46 lr 0.000129	time 2.5730 (2.2813)	loss 3.1036 (3.1506)	grad_norm 2.6651 (2.3246)	
[2022-01-25 02:51:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][320/1251]	eta 0:35:22 lr 0.000129	time 2.3328 (2.2800)	loss 3.0210 (3.1460)	grad_norm 2.8062 (2.3262)	
[2022-01-25 02:52:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][330/1251]	eta 0:34:53 lr 0.000129	time 2.2535 (2.2732)	loss 3.6939 (3.1488)	grad_norm 2.2697 (2.3292)	
[2022-01-25 02:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][340/1251]	eta 0:34:21 lr 0.000129	time 2.1006 (2.2633)	loss 3.3114 (3.1537)	grad_norm 2.0627 (2.3300)	
[2022-01-25 02:52:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][350/1251]	eta 0:33:53 lr 0.000129	time 1.8436 (2.2570)	loss 2.2573 (3.1501)	grad_norm 2.7443 (2.3321)	
[2022-01-25 02:53:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][360/1251]	eta 0:33:27 lr 0.000129	time 1.9059 (2.2534)	loss 2.7309 (3.1511)	grad_norm 2.5814 (2.3336)	
[2022-01-25 02:53:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][370/1251]	eta 0:33:01 lr 0.000129	time 1.9626 (2.2489)	loss 3.3930 (3.1556)	grad_norm 2.7214 (2.3372)	
[2022-01-25 02:53:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][380/1251]	eta 0:32:39 lr 0.000129	time 2.8729 (2.2493)	loss 3.1343 (3.1559)	grad_norm 2.5339 (2.3393)	
[2022-01-25 02:54:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][390/1251]	eta 0:32:22 lr 0.000129	time 2.5699 (2.2556)	loss 2.2068 (3.1529)	grad_norm 2.1485 (2.3386)	
[2022-01-25 02:54:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][400/1251]	eta 0:31:58 lr 0.000129	time 1.8567 (2.2548)	loss 2.8635 (3.1545)	grad_norm 2.3409 (2.3372)	
[2022-01-25 02:54:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][410/1251]	eta 0:31:35 lr 0.000129	time 1.5941 (2.2539)	loss 3.3858 (3.1519)	grad_norm 2.4627 (2.3354)	
[2022-01-25 02:55:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][420/1251]	eta 0:31:11 lr 0.000129	time 2.1539 (2.2523)	loss 3.0915 (3.1582)	grad_norm 2.3912 (2.3366)	
[2022-01-25 02:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][430/1251]	eta 0:30:45 lr 0.000129	time 2.0965 (2.2484)	loss 3.1985 (3.1586)	grad_norm 2.0122 (2.3340)	
[2022-01-25 02:56:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][440/1251]	eta 0:30:22 lr 0.000129	time 1.5345 (2.2477)	loss 2.5093 (3.1513)	grad_norm 2.1926 (2.3304)	
[2022-01-25 02:56:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][450/1251]	eta 0:29:59 lr 0.000129	time 1.7328 (2.2463)	loss 3.1990 (3.1516)	grad_norm 2.0072 (2.3280)	
[2022-01-25 02:56:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][460/1251]	eta 0:29:36 lr 0.000129	time 1.8519 (2.2455)	loss 3.4190 (3.1545)	grad_norm 2.2338 (2.3263)	
[2022-01-25 02:57:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][470/1251]	eta 0:29:13 lr 0.000129	time 1.6283 (2.2450)	loss 3.5463 (3.1550)	grad_norm 2.2866 (2.3235)	
[2022-01-25 02:57:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][480/1251]	eta 0:28:49 lr 0.000129	time 1.8446 (2.2437)	loss 2.2388 (3.1500)	grad_norm 2.9000 (2.3242)	
[2022-01-25 02:57:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][490/1251]	eta 0:28:29 lr 0.000129	time 2.7218 (2.2461)	loss 3.8033 (3.1507)	grad_norm 2.3552 (2.3242)	
[2022-01-25 02:58:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][500/1251]	eta 0:28:04 lr 0.000129	time 1.9122 (2.2430)	loss 3.1849 (3.1523)	grad_norm 2.4384 (2.3256)	
[2022-01-25 02:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][510/1251]	eta 0:27:40 lr 0.000129	time 1.6794 (2.2414)	loss 2.5542 (3.1507)	grad_norm 2.7710 (2.3270)	
[2022-01-25 02:59:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][520/1251]	eta 0:27:16 lr 0.000129	time 2.1822 (2.2394)	loss 3.2961 (3.1567)	grad_norm 2.4028 (2.3255)	
[2022-01-25 02:59:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][530/1251]	eta 0:26:53 lr 0.000129	time 2.2512 (2.2378)	loss 3.3615 (3.1579)	grad_norm 2.2703 (2.3238)	
[2022-01-25 02:59:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][540/1251]	eta 0:26:31 lr 0.000129	time 2.2370 (2.2385)	loss 3.4406 (3.1604)	grad_norm 2.0998 (2.3222)	
[2022-01-25 03:00:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][550/1251]	eta 0:26:11 lr 0.000129	time 2.1310 (2.2413)	loss 3.8957 (3.1618)	grad_norm 2.3758 (2.3234)	
[2022-01-25 03:00:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][560/1251]	eta 0:25:48 lr 0.000129	time 1.9486 (2.2415)	loss 3.2895 (3.1578)	grad_norm 2.3326 (2.3254)	
[2022-01-25 03:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][570/1251]	eta 0:25:23 lr 0.000129	time 1.8255 (2.2378)	loss 2.7058 (3.1528)	grad_norm 2.5497 (2.3278)	
[2022-01-25 03:01:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][580/1251]	eta 0:24:58 lr 0.000129	time 1.7244 (2.2327)	loss 3.3609 (3.1546)	grad_norm 2.0650 (2.3278)	
[2022-01-25 03:01:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][590/1251]	eta 0:24:36 lr 0.000129	time 1.9303 (2.2340)	loss 3.3652 (3.1524)	grad_norm 3.3477 (2.3353)	
[2022-01-25 03:01:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][600/1251]	eta 0:24:14 lr 0.000129	time 2.5009 (2.2346)	loss 3.8720 (3.1542)	grad_norm 2.3465 (2.3387)	
[2022-01-25 03:02:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][610/1251]	eta 0:23:51 lr 0.000129	time 1.8703 (2.2338)	loss 3.5099 (3.1551)	grad_norm 2.5339 (2.3403)	
[2022-01-25 03:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][620/1251]	eta 0:23:28 lr 0.000129	time 1.9019 (2.2326)	loss 2.6357 (3.1533)	grad_norm 2.4416 (2.3403)	
[2022-01-25 03:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][630/1251]	eta 0:23:07 lr 0.000129	time 2.2773 (2.2351)	loss 3.4527 (3.1514)	grad_norm 2.3618 (2.3411)	
[2022-01-25 03:03:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][640/1251]	eta 0:22:44 lr 0.000129	time 2.0613 (2.2330)	loss 3.3580 (3.1527)	grad_norm 2.1059 (2.3406)	
[2022-01-25 03:03:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][650/1251]	eta 0:22:20 lr 0.000129	time 1.5812 (2.2304)	loss 3.1411 (3.1572)	grad_norm 2.4608 (2.3405)	
[2022-01-25 03:04:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][660/1251]	eta 0:21:57 lr 0.000129	time 2.4755 (2.2285)	loss 3.0674 (3.1594)	grad_norm 2.2404 (2.3406)	
[2022-01-25 03:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][670/1251]	eta 0:21:33 lr 0.000128	time 1.6232 (2.2266)	loss 3.8153 (3.1619)	grad_norm 2.2034 (2.3402)	
[2022-01-25 03:04:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][680/1251]	eta 0:21:12 lr 0.000128	time 2.1461 (2.2280)	loss 3.2127 (3.1598)	grad_norm 2.4495 (2.3402)	
[2022-01-25 03:05:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][690/1251]	eta 0:20:49 lr 0.000128	time 1.8083 (2.2276)	loss 3.5427 (3.1617)	grad_norm 2.3782 (2.3393)	
[2022-01-25 03:05:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][700/1251]	eta 0:20:27 lr 0.000128	time 2.4512 (2.2272)	loss 3.5361 (3.1657)	grad_norm 2.3131 (2.3384)	
[2022-01-25 03:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][710/1251]	eta 0:20:04 lr 0.000128	time 1.5852 (2.2272)	loss 3.7008 (3.1603)	grad_norm 2.5382 (2.3384)	
[2022-01-25 03:06:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][720/1251]	eta 0:19:42 lr 0.000128	time 1.9083 (2.2265)	loss 3.4243 (3.1623)	grad_norm 2.2656 (2.3377)	
[2022-01-25 03:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][730/1251]	eta 0:19:20 lr 0.000128	time 1.8954 (2.2278)	loss 2.6366 (3.1619)	grad_norm 2.2557 (2.3387)	
[2022-01-25 03:07:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][740/1251]	eta 0:18:58 lr 0.000128	time 2.2186 (2.2276)	loss 3.4314 (3.1605)	grad_norm 2.2142 (2.3380)	
[2022-01-25 03:07:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][750/1251]	eta 0:18:34 lr 0.000128	time 1.8727 (2.2237)	loss 3.5657 (3.1616)	grad_norm 2.3725 (2.3382)	
[2022-01-25 03:07:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][760/1251]	eta 0:18:10 lr 0.000128	time 1.8196 (2.2202)	loss 3.5147 (3.1631)	grad_norm 2.6215 (2.3389)	
[2022-01-25 03:08:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][770/1251]	eta 0:17:46 lr 0.000128	time 1.9190 (2.2169)	loss 2.8289 (3.1623)	grad_norm 2.4011 (2.3392)	
[2022-01-25 03:08:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][780/1251]	eta 0:17:24 lr 0.000128	time 2.2465 (2.2176)	loss 1.9695 (3.1601)	grad_norm 2.2161 (2.3421)	
[2022-01-25 03:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][790/1251]	eta 0:17:02 lr 0.000128	time 2.0489 (2.2176)	loss 2.7810 (3.1606)	grad_norm 2.2326 (2.3438)	
[2022-01-25 03:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][800/1251]	eta 0:16:40 lr 0.000128	time 2.4574 (2.2194)	loss 3.3370 (3.1608)	grad_norm 1.8720 (2.3448)	
[2022-01-25 03:09:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][810/1251]	eta 0:16:20 lr 0.000128	time 3.2195 (2.2234)	loss 2.7120 (3.1604)	grad_norm 2.5750 (2.3441)	
[2022-01-25 03:09:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][820/1251]	eta 0:15:58 lr 0.000128	time 1.7229 (2.2236)	loss 3.0572 (3.1607)	grad_norm 2.3727 (2.3431)	
[2022-01-25 03:10:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][830/1251]	eta 0:15:35 lr 0.000128	time 1.6520 (2.2226)	loss 3.2918 (3.1612)	grad_norm 2.1674 (2.3432)	
[2022-01-25 03:10:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][840/1251]	eta 0:15:12 lr 0.000128	time 1.7464 (2.2208)	loss 2.3598 (3.1580)	grad_norm 2.0770 (2.3413)	
[2022-01-25 03:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][850/1251]	eta 0:14:50 lr 0.000128	time 3.3511 (2.2218)	loss 3.2300 (3.1554)	grad_norm 2.1481 (2.3423)	
[2022-01-25 03:11:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][860/1251]	eta 0:14:28 lr 0.000128	time 1.5970 (2.2208)	loss 3.4105 (3.1562)	grad_norm 2.2202 (2.3412)	
[2022-01-25 03:11:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][870/1251]	eta 0:14:06 lr 0.000128	time 2.2863 (2.2209)	loss 3.0608 (3.1537)	grad_norm 2.2576 (2.3392)	
[2022-01-25 03:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][880/1251]	eta 0:13:43 lr 0.000128	time 1.9187 (2.2207)	loss 3.4761 (3.1505)	grad_norm 2.1955 (2.3386)	
[2022-01-25 03:12:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][890/1251]	eta 0:13:21 lr 0.000128	time 3.3738 (2.2202)	loss 2.5426 (3.1488)	grad_norm 2.2748 (2.3396)	
[2022-01-25 03:12:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][900/1251]	eta 0:12:58 lr 0.000128	time 1.8556 (2.2178)	loss 2.2351 (3.1491)	grad_norm 2.5204 (2.3405)	
[2022-01-25 03:13:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][910/1251]	eta 0:12:36 lr 0.000128	time 2.2307 (2.2172)	loss 3.1294 (3.1478)	grad_norm 2.6672 (2.3428)	
[2022-01-25 03:13:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][920/1251]	eta 0:12:13 lr 0.000128	time 2.1954 (2.2168)	loss 2.9227 (3.1470)	grad_norm 2.0979 (2.3431)	
[2022-01-25 03:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][930/1251]	eta 0:11:51 lr 0.000128	time 2.5428 (2.2167)	loss 3.8037 (3.1487)	grad_norm 2.6106 (2.3446)	
[2022-01-25 03:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][940/1251]	eta 0:11:29 lr 0.000128	time 2.3766 (2.2162)	loss 3.4278 (3.1517)	grad_norm 2.3786 (2.3486)	
[2022-01-25 03:14:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][950/1251]	eta 0:11:07 lr 0.000128	time 2.6894 (2.2176)	loss 3.4886 (3.1534)	grad_norm 2.3920 (2.3499)	
[2022-01-25 03:15:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][960/1251]	eta 0:10:45 lr 0.000128	time 2.1916 (2.2171)	loss 3.9640 (3.1529)	grad_norm 2.3770 (2.3483)	
[2022-01-25 03:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][970/1251]	eta 0:10:22 lr 0.000128	time 2.6818 (2.2166)	loss 2.7066 (3.1513)	grad_norm 2.2724 (2.3470)	
[2022-01-25 03:15:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][980/1251]	eta 0:10:00 lr 0.000128	time 1.6010 (2.2142)	loss 3.4074 (3.1534)	grad_norm 2.1194 (2.3474)	
[2022-01-25 03:16:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][990/1251]	eta 0:09:37 lr 0.000128	time 2.9369 (2.2136)	loss 3.2305 (3.1549)	grad_norm 2.1280 (2.3457)	
[2022-01-25 03:16:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1000/1251]	eta 0:09:15 lr 0.000128	time 2.8148 (2.2127)	loss 3.5281 (3.1546)	grad_norm 2.1521 (2.3448)	
[2022-01-25 03:16:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1010/1251]	eta 0:08:53 lr 0.000128	time 2.6443 (2.2143)	loss 3.7641 (3.1560)	grad_norm 2.0724 (2.3452)	
[2022-01-25 03:17:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1020/1251]	eta 0:08:31 lr 0.000128	time 1.8141 (2.2135)	loss 2.6170 (3.1559)	grad_norm 2.1820 (2.3458)	
[2022-01-25 03:17:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1030/1251]	eta 0:08:09 lr 0.000128	time 2.0235 (2.2136)	loss 3.1403 (3.1561)	grad_norm 2.2280 (2.3442)	
[2022-01-25 03:17:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1040/1251]	eta 0:07:47 lr 0.000127	time 2.9767 (2.2142)	loss 3.5192 (3.1573)	grad_norm 2.9718 (2.3459)	
[2022-01-25 03:18:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1050/1251]	eta 0:07:25 lr 0.000127	time 2.1949 (2.2141)	loss 3.4617 (3.1558)	grad_norm 2.3837 (2.3468)	
[2022-01-25 03:18:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1060/1251]	eta 0:07:02 lr 0.000127	time 2.4633 (2.2136)	loss 2.3454 (3.1566)	grad_norm 2.3824 (2.3478)	
[2022-01-25 03:19:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1070/1251]	eta 0:06:40 lr 0.000127	time 1.6342 (2.2127)	loss 3.3330 (3.1569)	grad_norm 2.4446 (2.3484)	
[2022-01-25 03:19:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1080/1251]	eta 0:06:18 lr 0.000127	time 1.5619 (2.2113)	loss 2.0831 (3.1573)	grad_norm 2.3593 (2.3482)	
[2022-01-25 03:19:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1090/1251]	eta 0:05:56 lr 0.000127	time 3.5627 (2.2132)	loss 2.9036 (3.1577)	grad_norm 2.4867 (2.3478)	
[2022-01-25 03:20:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1100/1251]	eta 0:05:34 lr 0.000127	time 1.8486 (2.2123)	loss 3.2581 (3.1543)	grad_norm 2.7183 (2.3472)	
[2022-01-25 03:20:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1110/1251]	eta 0:05:11 lr 0.000127	time 1.8178 (2.2122)	loss 3.5947 (3.1541)	grad_norm 2.2715 (2.3467)	
[2022-01-25 03:20:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1120/1251]	eta 0:04:49 lr 0.000127	time 1.7355 (2.2129)	loss 3.5755 (3.1556)	grad_norm 2.3394 (2.3473)	
[2022-01-25 03:21:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1130/1251]	eta 0:04:27 lr 0.000127	time 2.4581 (2.2125)	loss 2.3379 (3.1543)	grad_norm 2.4511 (2.3479)	
[2022-01-25 03:21:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1140/1251]	eta 0:04:05 lr 0.000127	time 2.2277 (2.2111)	loss 3.3687 (3.1542)	grad_norm 2.0052 (2.3471)	
[2022-01-25 03:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1150/1251]	eta 0:03:43 lr 0.000127	time 1.6082 (2.2091)	loss 3.5557 (3.1548)	grad_norm 2.3229 (2.3471)	
[2022-01-25 03:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1160/1251]	eta 0:03:21 lr 0.000127	time 2.5536 (2.2098)	loss 2.7727 (3.1539)	grad_norm 2.2945 (2.3473)	
[2022-01-25 03:22:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1170/1251]	eta 0:02:58 lr 0.000127	time 2.0170 (2.2096)	loss 3.2814 (3.1522)	grad_norm 2.0856 (2.3467)	
[2022-01-25 03:23:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1180/1251]	eta 0:02:36 lr 0.000127	time 2.2641 (2.2097)	loss 2.0894 (3.1504)	grad_norm 2.5530 (2.3472)	
[2022-01-25 03:23:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1190/1251]	eta 0:02:14 lr 0.000127	time 1.8306 (2.2090)	loss 2.0510 (3.1495)	grad_norm 2.3442 (2.3472)	
[2022-01-25 03:23:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1200/1251]	eta 0:01:52 lr 0.000127	time 2.1374 (2.2090)	loss 3.3711 (3.1503)	grad_norm 2.0957 (2.3473)	
[2022-01-25 03:24:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1210/1251]	eta 0:01:30 lr 0.000127	time 2.0357 (2.2082)	loss 3.2355 (3.1516)	grad_norm 2.5313 (2.3464)	
[2022-01-25 03:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1220/1251]	eta 0:01:08 lr 0.000127	time 2.0303 (2.2078)	loss 3.9119 (3.1520)	grad_norm 2.3044 (2.3456)	
[2022-01-25 03:24:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1230/1251]	eta 0:00:46 lr 0.000127	time 1.8018 (2.2082)	loss 3.4686 (3.1511)	grad_norm 2.0803 (2.3450)	
[2022-01-25 03:25:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1240/1251]	eta 0:00:24 lr 0.000127	time 1.5308 (2.2076)	loss 3.4203 (3.1518)	grad_norm 2.6616 (2.3460)	
[2022-01-25 03:25:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [232/300][1250/1251]	eta 0:00:02 lr 0.000127	time 1.1946 (2.2019)	loss 3.7425 (3.1545)	grad_norm 2.4328 (2.3458)	
[2022-01-25 03:25:28 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 232 training takes 0:45:55
[2022-01-25 03:25:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.731 (18.731)	Loss 0.8285 (0.8285)	Acc@1 80.957 (80.957)	Acc@5 96.191 (96.191)	
[2022-01-25 03:26:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.257 (3.537)	Loss 0.8153 (0.8472)	Acc@1 81.348 (80.114)	Acc@5 95.703 (95.295)	
[2022-01-25 03:26:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.272 (2.566)	Loss 0.9183 (0.8556)	Acc@1 77.734 (79.734)	Acc@5 94.629 (95.206)	
[2022-01-25 03:26:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.315 (2.281)	Loss 0.8665 (0.8573)	Acc@1 80.273 (79.801)	Acc@5 95.020 (95.149)	
[2022-01-25 03:26:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.230 (2.174)	Loss 0.8544 (0.8571)	Acc@1 79.590 (79.783)	Acc@5 95.312 (95.127)	
[2022-01-25 03:27:04 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.778 Acc@5 95.160
[2022-01-25 03:27:04 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.8%
[2022-01-25 03:27:04 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.78%
[2022-01-25 03:27:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][0/1251]	eta 7:24:03 lr 0.000127	time 21.2975 (21.2975)	loss 2.9436 (2.9436)	grad_norm 2.2815 (2.2815)	
[2022-01-25 03:27:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][10/1251]	eta 1:27:25 lr 0.000127	time 1.9929 (4.2267)	loss 3.5668 (3.3209)	grad_norm 2.1790 (2.2919)	
[2022-01-25 03:28:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][20/1251]	eta 1:06:10 lr 0.000127	time 1.2172 (3.2256)	loss 3.5573 (3.3094)	grad_norm 2.3957 (2.2849)	
[2022-01-25 03:28:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][30/1251]	eta 0:59:03 lr 0.000127	time 1.5416 (2.9020)	loss 3.1455 (3.2749)	grad_norm 2.4911 (2.3093)	
[2022-01-25 03:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][40/1251]	eta 0:55:42 lr 0.000127	time 3.3125 (2.7602)	loss 3.5444 (3.2622)	grad_norm 1.9437 (2.3145)	
[2022-01-25 03:29:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][50/1251]	eta 0:53:20 lr 0.000127	time 2.2671 (2.6646)	loss 3.7977 (3.2882)	grad_norm 2.1527 (2.3124)	
[2022-01-25 03:29:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][60/1251]	eta 0:51:10 lr 0.000127	time 1.7159 (2.5782)	loss 3.5440 (3.2956)	grad_norm 2.6883 (2.3858)	
[2022-01-25 03:30:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][70/1251]	eta 0:49:31 lr 0.000127	time 1.7409 (2.5162)	loss 3.7329 (3.3067)	grad_norm 2.5196 (2.3900)	
[2022-01-25 03:30:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][80/1251]	eta 0:48:35 lr 0.000127	time 3.5898 (2.4896)	loss 3.5127 (3.2838)	grad_norm 3.2433 (2.4092)	
[2022-01-25 03:30:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][90/1251]	eta 0:47:40 lr 0.000127	time 1.9143 (2.4641)	loss 3.5287 (3.2791)	grad_norm 2.4750 (2.4209)	
[2022-01-25 03:31:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][100/1251]	eta 0:46:37 lr 0.000127	time 1.7606 (2.4301)	loss 2.3196 (3.2277)	grad_norm 2.6098 (2.4486)	
[2022-01-25 03:31:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][110/1251]	eta 0:45:52 lr 0.000127	time 1.6248 (2.4122)	loss 3.6518 (3.2312)	grad_norm 2.0396 (2.4389)	
[2022-01-25 03:31:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][120/1251]	eta 0:45:00 lr 0.000127	time 2.3639 (2.3874)	loss 2.5418 (3.2283)	grad_norm 2.4389 (2.4449)	
[2022-01-25 03:32:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][130/1251]	eta 0:44:16 lr 0.000127	time 2.1977 (2.3700)	loss 3.0282 (3.2305)	grad_norm 2.3701 (2.4276)	
[2022-01-25 03:32:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][140/1251]	eta 0:43:36 lr 0.000127	time 2.0967 (2.3552)	loss 3.4579 (3.2438)	grad_norm 2.4600 (2.4266)	
[2022-01-25 03:32:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][150/1251]	eta 0:43:08 lr 0.000127	time 2.0967 (2.3515)	loss 2.5341 (3.2493)	grad_norm 2.6053 (2.4379)	
[2022-01-25 03:33:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][160/1251]	eta 0:42:38 lr 0.000126	time 2.1937 (2.3453)	loss 2.3250 (3.2479)	grad_norm 2.4302 (2.4373)	
[2022-01-25 03:33:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][170/1251]	eta 0:42:04 lr 0.000126	time 1.8695 (2.3352)	loss 2.3838 (3.2442)	grad_norm 2.5062 (2.4289)	
[2022-01-25 03:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][180/1251]	eta 0:41:17 lr 0.000126	time 1.9278 (2.3137)	loss 2.5498 (3.2362)	grad_norm 2.1889 (2.4243)	
[2022-01-25 03:34:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][190/1251]	eta 0:40:43 lr 0.000126	time 1.8617 (2.3033)	loss 2.1376 (3.2289)	grad_norm 2.0276 (2.4238)	
[2022-01-25 03:34:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][200/1251]	eta 0:40:11 lr 0.000126	time 2.0636 (2.2944)	loss 3.8156 (3.2297)	grad_norm 2.1656 (2.4201)	
[2022-01-25 03:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][210/1251]	eta 0:39:40 lr 0.000126	time 1.9300 (2.2868)	loss 3.3701 (3.2363)	grad_norm 2.2957 (2.4208)	
[2022-01-25 03:35:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][220/1251]	eta 0:39:11 lr 0.000126	time 2.2266 (2.2804)	loss 3.3918 (3.2334)	grad_norm 2.5050 (2.4150)	
[2022-01-25 03:35:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][230/1251]	eta 0:38:48 lr 0.000126	time 1.5633 (2.2809)	loss 3.8739 (3.2441)	grad_norm 2.4066 (2.4123)	
[2022-01-25 03:36:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][240/1251]	eta 0:38:25 lr 0.000126	time 2.5365 (2.2808)	loss 3.1220 (3.2282)	grad_norm 2.4565 (2.4085)	
[2022-01-25 03:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][250/1251]	eta 0:38:02 lr 0.000126	time 2.1544 (2.2804)	loss 3.2608 (3.2199)	grad_norm 2.6381 (2.4059)	
[2022-01-25 03:36:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][260/1251]	eta 0:37:34 lr 0.000126	time 2.2363 (2.2745)	loss 3.2652 (3.2193)	grad_norm 2.7397 (2.4092)	
[2022-01-25 03:37:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][270/1251]	eta 0:37:08 lr 0.000126	time 1.9526 (2.2716)	loss 3.2228 (3.2171)	grad_norm 2.1757 (2.4035)	
[2022-01-25 03:37:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][280/1251]	eta 0:36:37 lr 0.000126	time 2.2116 (2.2632)	loss 2.8559 (3.2149)	grad_norm 2.2930 (2.3976)	
[2022-01-25 03:38:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][290/1251]	eta 0:36:09 lr 0.000126	time 1.9867 (2.2577)	loss 2.9641 (3.2028)	grad_norm 2.4330 (2.3943)	
[2022-01-25 03:38:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][300/1251]	eta 0:35:44 lr 0.000126	time 2.1015 (2.2547)	loss 3.7399 (3.2012)	grad_norm 2.4358 (2.3957)	
[2022-01-25 03:38:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][310/1251]	eta 0:35:29 lr 0.000126	time 1.9031 (2.2626)	loss 3.8232 (3.2030)	grad_norm 2.3042 (2.3940)	
[2022-01-25 03:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][320/1251]	eta 0:35:05 lr 0.000126	time 1.9604 (2.2616)	loss 3.8304 (3.2005)	grad_norm 2.0497 (2.3883)	
[2022-01-25 03:39:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][330/1251]	eta 0:34:37 lr 0.000126	time 1.9783 (2.2556)	loss 3.5536 (3.1984)	grad_norm 2.0920 (2.3862)	
[2022-01-25 03:39:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][340/1251]	eta 0:34:08 lr 0.000126	time 1.6535 (2.2492)	loss 2.9216 (3.1989)	grad_norm 2.1756 (2.3843)	
[2022-01-25 03:40:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][350/1251]	eta 0:33:43 lr 0.000126	time 1.8454 (2.2458)	loss 3.5994 (3.2054)	grad_norm 2.2274 (2.3845)	
[2022-01-25 03:40:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][360/1251]	eta 0:33:19 lr 0.000126	time 2.2041 (2.2440)	loss 3.3476 (3.2087)	grad_norm 2.3249 (2.3877)	
[2022-01-25 03:40:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][370/1251]	eta 0:32:56 lr 0.000126	time 1.9088 (2.2436)	loss 2.5934 (3.2035)	grad_norm 2.3546 (2.3905)	
[2022-01-25 03:41:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][380/1251]	eta 0:32:37 lr 0.000126	time 2.8768 (2.2470)	loss 2.2198 (3.2054)	grad_norm 2.4947 (2.3917)	
[2022-01-25 03:41:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][390/1251]	eta 0:32:15 lr 0.000126	time 1.4781 (2.2480)	loss 3.1013 (3.2023)	grad_norm 2.6272 (2.3895)	
[2022-01-25 03:42:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][400/1251]	eta 0:31:50 lr 0.000126	time 2.5810 (2.2451)	loss 3.5540 (3.2121)	grad_norm 2.4322 (2.3891)	
[2022-01-25 03:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][410/1251]	eta 0:31:22 lr 0.000126	time 1.8181 (2.2385)	loss 3.6630 (3.2183)	grad_norm 2.2030 (2.3880)	
[2022-01-25 03:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][420/1251]	eta 0:30:55 lr 0.000126	time 1.9593 (2.2327)	loss 3.3769 (3.2213)	grad_norm 2.2195 (2.3879)	
[2022-01-25 03:43:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][430/1251]	eta 0:30:32 lr 0.000126	time 2.2197 (2.2323)	loss 3.7689 (3.2287)	grad_norm 2.3799 (2.3905)	
[2022-01-25 03:43:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][440/1251]	eta 0:30:09 lr 0.000126	time 1.9581 (2.2308)	loss 2.7166 (3.2222)	grad_norm 2.4586 (2.3926)	
[2022-01-25 03:43:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][450/1251]	eta 0:29:46 lr 0.000126	time 1.8725 (2.2297)	loss 3.8022 (3.2217)	grad_norm 2.2918 (2.3917)	
[2022-01-25 03:44:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][460/1251]	eta 0:29:22 lr 0.000126	time 1.9164 (2.2279)	loss 3.1144 (3.2219)	grad_norm 2.0315 (2.3888)	
[2022-01-25 03:44:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][470/1251]	eta 0:29:00 lr 0.000126	time 2.1527 (2.2292)	loss 2.7454 (3.2229)	grad_norm 2.4170 (2.3852)	
[2022-01-25 03:44:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][480/1251]	eta 0:28:36 lr 0.000126	time 1.6025 (2.2264)	loss 3.8203 (3.2247)	grad_norm 2.7468 (2.3835)	
[2022-01-25 03:45:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][490/1251]	eta 0:28:14 lr 0.000126	time 2.4907 (2.2263)	loss 3.4151 (3.2230)	grad_norm 2.1750 (2.3849)	
[2022-01-25 03:45:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][500/1251]	eta 0:27:51 lr 0.000126	time 2.1291 (2.2258)	loss 3.0999 (3.2230)	grad_norm 2.9238 (2.3877)	
[2022-01-25 03:46:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][510/1251]	eta 0:27:29 lr 0.000126	time 2.3278 (2.2259)	loss 3.1502 (3.2238)	grad_norm 2.1545 (2.3874)	
[2022-01-25 03:46:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][520/1251]	eta 0:27:03 lr 0.000126	time 1.7613 (2.2203)	loss 3.1734 (3.2240)	grad_norm 2.0614 (2.3864)	
[2022-01-25 03:46:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][530/1251]	eta 0:26:40 lr 0.000126	time 1.7546 (2.2195)	loss 3.9514 (3.2282)	grad_norm 2.4154 (2.3857)	
[2022-01-25 03:47:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][540/1251]	eta 0:26:16 lr 0.000125	time 1.9215 (2.2173)	loss 3.4933 (3.2292)	grad_norm 2.1956 (2.3871)	
[2022-01-25 03:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][550/1251]	eta 0:25:54 lr 0.000125	time 3.2920 (2.2177)	loss 3.8011 (3.2306)	grad_norm 2.1791 (2.3853)	
[2022-01-25 03:47:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][560/1251]	eta 0:25:34 lr 0.000125	time 1.5030 (2.2212)	loss 2.5743 (3.2273)	grad_norm 2.2037 (2.3857)	
[2022-01-25 03:48:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][570/1251]	eta 0:25:13 lr 0.000125	time 2.3524 (2.2218)	loss 3.3447 (3.2302)	grad_norm 2.1180 (2.3854)	
[2022-01-25 03:48:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][580/1251]	eta 0:24:48 lr 0.000125	time 1.8099 (2.2178)	loss 1.9719 (3.2260)	grad_norm 2.0163 (2.3820)	
[2022-01-25 03:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][590/1251]	eta 0:24:23 lr 0.000125	time 2.7472 (2.2145)	loss 3.4467 (3.2201)	grad_norm 2.3865 (2.3811)	
[2022-01-25 03:49:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][600/1251]	eta 0:24:00 lr 0.000125	time 1.6642 (2.2123)	loss 3.1493 (3.2192)	grad_norm 2.2561 (2.3817)	
[2022-01-25 03:49:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][610/1251]	eta 0:23:38 lr 0.000125	time 1.9595 (2.2127)	loss 2.2206 (3.2152)	grad_norm 1.9976 (2.3822)	
[2022-01-25 03:50:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][620/1251]	eta 0:23:17 lr 0.000125	time 2.4702 (2.2149)	loss 3.1610 (3.2130)	grad_norm 2.2217 (2.3837)	
[2022-01-25 03:50:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][630/1251]	eta 0:22:55 lr 0.000125	time 1.8620 (2.2154)	loss 3.2972 (3.2155)	grad_norm 2.4631 (2.3838)	
[2022-01-25 03:50:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][640/1251]	eta 0:22:34 lr 0.000125	time 1.8579 (2.2172)	loss 3.0672 (3.2149)	grad_norm 2.5330 (2.3838)	
[2022-01-25 03:51:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][650/1251]	eta 0:22:12 lr 0.000125	time 2.2608 (2.2169)	loss 3.5372 (3.2108)	grad_norm 2.0644 (2.3807)	
[2022-01-25 03:51:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][660/1251]	eta 0:21:48 lr 0.000125	time 1.8546 (2.2139)	loss 3.0378 (3.2106)	grad_norm 2.3895 (2.3830)	
[2022-01-25 03:51:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][670/1251]	eta 0:21:24 lr 0.000125	time 1.7990 (2.2101)	loss 3.7354 (3.2074)	grad_norm 2.2111 (2.3825)	
[2022-01-25 03:52:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][680/1251]	eta 0:21:00 lr 0.000125	time 1.9250 (2.2082)	loss 3.5520 (3.2089)	grad_norm 2.9066 (2.3879)	
[2022-01-25 03:52:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][690/1251]	eta 0:20:39 lr 0.000125	time 2.4560 (2.2087)	loss 3.5231 (3.2089)	grad_norm 2.4715 (2.3875)	
[2022-01-25 03:52:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][700/1251]	eta 0:20:18 lr 0.000125	time 2.9299 (2.2109)	loss 3.1353 (3.2086)	grad_norm 2.2634 (2.3854)	
[2022-01-25 03:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][710/1251]	eta 0:19:56 lr 0.000125	time 2.9139 (2.2119)	loss 3.8528 (3.2091)	grad_norm 5.0563 (2.3881)	
[2022-01-25 03:53:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][720/1251]	eta 0:19:34 lr 0.000125	time 3.5294 (2.2120)	loss 2.9814 (3.2044)	grad_norm 2.4751 (2.3900)	
[2022-01-25 03:54:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][730/1251]	eta 0:19:12 lr 0.000125	time 1.6951 (2.2121)	loss 3.8146 (3.2069)	grad_norm 2.3887 (2.3894)	
[2022-01-25 03:54:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][740/1251]	eta 0:18:50 lr 0.000125	time 2.4354 (2.2127)	loss 3.2879 (3.2076)	grad_norm 2.3896 (2.3886)	
[2022-01-25 03:54:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][750/1251]	eta 0:18:29 lr 0.000125	time 3.4372 (2.2147)	loss 2.6446 (3.2062)	grad_norm 2.5042 (2.3878)	
[2022-01-25 03:55:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][760/1251]	eta 0:18:08 lr 0.000125	time 3.8946 (2.2168)	loss 3.5940 (3.2033)	grad_norm 2.9672 (2.3886)	
[2022-01-25 03:55:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][770/1251]	eta 0:17:45 lr 0.000125	time 1.8039 (2.2143)	loss 3.3833 (3.2020)	grad_norm 2.3406 (2.3881)	
[2022-01-25 03:55:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][780/1251]	eta 0:17:21 lr 0.000125	time 1.8873 (2.2105)	loss 2.7813 (3.1993)	grad_norm 2.2269 (2.3877)	
[2022-01-25 03:56:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][790/1251]	eta 0:16:57 lr 0.000125	time 1.7913 (2.2082)	loss 4.0460 (3.2002)	grad_norm 2.4186 (2.3879)	
[2022-01-25 03:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][800/1251]	eta 0:16:35 lr 0.000125	time 2.8679 (2.2070)	loss 3.5679 (3.1985)	grad_norm 2.3900 (2.3874)	
[2022-01-25 03:56:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][810/1251]	eta 0:16:12 lr 0.000125	time 2.0094 (2.2061)	loss 3.7760 (3.2023)	grad_norm 2.4844 (2.3880)	
[2022-01-25 03:57:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][820/1251]	eta 0:15:51 lr 0.000125	time 2.7712 (2.2068)	loss 3.4808 (3.2031)	grad_norm 2.8626 (2.3890)	
[2022-01-25 03:57:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][830/1251]	eta 0:15:28 lr 0.000125	time 2.6117 (2.2059)	loss 3.4481 (3.2011)	grad_norm 2.1588 (2.3911)	
[2022-01-25 03:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][840/1251]	eta 0:15:06 lr 0.000125	time 1.9184 (2.2053)	loss 3.6132 (3.2032)	grad_norm 2.0222 (2.3904)	
[2022-01-25 03:58:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][850/1251]	eta 0:14:45 lr 0.000125	time 2.1487 (2.2074)	loss 3.3019 (3.2036)	grad_norm 3.2327 (2.3914)	
[2022-01-25 03:58:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][860/1251]	eta 0:14:24 lr 0.000125	time 2.3359 (2.2107)	loss 2.0723 (3.2034)	grad_norm 2.8663 (2.3932)	
[2022-01-25 03:59:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][870/1251]	eta 0:14:02 lr 0.000125	time 3.2130 (2.2120)	loss 3.1936 (3.1975)	grad_norm 2.5075 (2.3929)	
[2022-01-25 03:59:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][880/1251]	eta 0:13:40 lr 0.000125	time 1.8986 (2.2108)	loss 3.4752 (3.1981)	grad_norm 2.7617 (2.3942)	
[2022-01-25 03:59:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][890/1251]	eta 0:13:17 lr 0.000125	time 1.8966 (2.2086)	loss 2.8661 (3.1961)	grad_norm 2.9255 (2.3954)	
[2022-01-25 04:00:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][900/1251]	eta 0:12:54 lr 0.000125	time 2.2244 (2.2070)	loss 3.5885 (3.1958)	grad_norm 2.1593 (2.3965)	
[2022-01-25 04:00:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][910/1251]	eta 0:12:32 lr 0.000124	time 3.5074 (2.2076)	loss 3.3889 (3.1976)	grad_norm 2.3369 (2.3968)	
[2022-01-25 04:00:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][920/1251]	eta 0:12:10 lr 0.000124	time 1.8663 (2.2068)	loss 2.1396 (3.1984)	grad_norm 2.4351 (2.3963)	
[2022-01-25 04:01:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][930/1251]	eta 0:11:48 lr 0.000124	time 1.9548 (2.2066)	loss 3.3567 (3.2001)	grad_norm 2.2314 (2.3956)	
[2022-01-25 04:01:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][940/1251]	eta 0:11:26 lr 0.000124	time 2.5226 (2.2063)	loss 2.0025 (3.2001)	grad_norm 2.3505 (2.3955)	
[2022-01-25 04:02:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][950/1251]	eta 0:11:04 lr 0.000124	time 3.1326 (2.2066)	loss 2.6900 (3.1991)	grad_norm 2.2686 (2.3951)	
[2022-01-25 04:02:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][960/1251]	eta 0:10:42 lr 0.000124	time 2.3562 (2.2065)	loss 2.2044 (3.1990)	grad_norm 2.4271 (2.3945)	
[2022-01-25 04:02:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][970/1251]	eta 0:10:19 lr 0.000124	time 1.9038 (2.2048)	loss 3.0280 (3.1995)	grad_norm 2.4752 (2.3947)	
[2022-01-25 04:03:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][980/1251]	eta 0:09:57 lr 0.000124	time 2.0083 (2.2056)	loss 3.8962 (3.2006)	grad_norm 2.5372 (2.3936)	
[2022-01-25 04:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][990/1251]	eta 0:09:36 lr 0.000124	time 2.6021 (2.2071)	loss 3.5246 (3.2022)	grad_norm 2.5883 (2.3934)	
[2022-01-25 04:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1000/1251]	eta 0:09:13 lr 0.000124	time 2.4955 (2.2067)	loss 2.4257 (3.2011)	grad_norm 2.2592 (2.3941)	
[2022-01-25 04:04:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1010/1251]	eta 0:08:51 lr 0.000124	time 1.6930 (2.2047)	loss 3.2808 (3.2022)	grad_norm 2.3389 (2.3954)	
[2022-01-25 04:04:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1020/1251]	eta 0:08:28 lr 0.000124	time 1.8266 (2.2025)	loss 3.8403 (3.2042)	grad_norm 2.4744 (2.3951)	
[2022-01-25 04:04:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1030/1251]	eta 0:08:06 lr 0.000124	time 1.8983 (2.2004)	loss 2.9130 (3.2042)	grad_norm 2.3368 (2.3946)	
[2022-01-25 04:05:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1040/1251]	eta 0:07:44 lr 0.000124	time 2.6306 (2.2012)	loss 3.4243 (3.2052)	grad_norm 2.9417 (2.4001)	
[2022-01-25 04:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1050/1251]	eta 0:07:22 lr 0.000124	time 2.1321 (2.2026)	loss 2.4222 (3.2063)	grad_norm 2.7700 (2.4010)	
[2022-01-25 04:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1060/1251]	eta 0:07:00 lr 0.000124	time 2.5383 (2.2023)	loss 3.4468 (3.2072)	grad_norm 2.5282 (2.4002)	
[2022-01-25 04:06:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1070/1251]	eta 0:06:38 lr 0.000124	time 1.9172 (2.2007)	loss 2.7552 (3.2089)	grad_norm 2.0004 (2.3985)	
[2022-01-25 04:06:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1080/1251]	eta 0:06:16 lr 0.000124	time 1.9594 (2.1992)	loss 2.9174 (3.2059)	grad_norm 2.5146 (2.3988)	
[2022-01-25 04:07:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1090/1251]	eta 0:05:54 lr 0.000124	time 2.3794 (2.1991)	loss 3.5766 (3.2070)	grad_norm 2.3767 (2.4002)	
[2022-01-25 04:07:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1100/1251]	eta 0:05:31 lr 0.000124	time 1.5831 (2.1983)	loss 3.3754 (3.2099)	grad_norm 2.2577 (2.4009)	
[2022-01-25 04:07:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1110/1251]	eta 0:05:09 lr 0.000124	time 1.9516 (2.1977)	loss 3.6533 (3.2116)	grad_norm 2.4788 (2.4007)	
[2022-01-25 04:08:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1120/1251]	eta 0:04:48 lr 0.000124	time 1.8560 (2.1988)	loss 3.3869 (3.2111)	grad_norm 2.5743 (2.4028)	
[2022-01-25 04:08:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1130/1251]	eta 0:04:26 lr 0.000124	time 2.5609 (2.2001)	loss 3.6039 (3.2116)	grad_norm 2.2927 (2.4026)	
[2022-01-25 04:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1140/1251]	eta 0:04:04 lr 0.000124	time 2.2157 (2.2005)	loss 3.5748 (3.2089)	grad_norm 2.4341 (2.4036)	
[2022-01-25 04:09:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1150/1251]	eta 0:03:42 lr 0.000124	time 2.2179 (2.2009)	loss 2.4299 (3.2097)	grad_norm 2.5721 (2.4042)	
[2022-01-25 04:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1160/1251]	eta 0:03:20 lr 0.000124	time 1.7099 (2.2007)	loss 3.3596 (3.2093)	grad_norm 2.2611 (2.4041)	
[2022-01-25 04:10:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1170/1251]	eta 0:02:58 lr 0.000124	time 1.8978 (2.1999)	loss 3.1768 (3.2097)	grad_norm 2.4642 (2.4036)	
[2022-01-25 04:10:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1180/1251]	eta 0:02:36 lr 0.000124	time 1.9500 (2.1986)	loss 2.9915 (3.2120)	grad_norm 2.1326 (2.4037)	
[2022-01-25 04:10:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1190/1251]	eta 0:02:14 lr 0.000124	time 2.4551 (2.1981)	loss 2.9952 (3.2115)	grad_norm 2.3189 (2.4036)	
[2022-01-25 04:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1200/1251]	eta 0:01:52 lr 0.000124	time 1.9376 (2.1978)	loss 3.6256 (3.2117)	grad_norm 2.6557 (2.4049)	
[2022-01-25 04:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1210/1251]	eta 0:01:30 lr 0.000124	time 2.2027 (2.1979)	loss 3.3747 (3.2116)	grad_norm 2.0692 (2.4045)	
[2022-01-25 04:11:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1220/1251]	eta 0:01:08 lr 0.000124	time 2.1497 (2.1986)	loss 3.0128 (3.2117)	grad_norm 2.3516 (2.4040)	
[2022-01-25 04:12:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1230/1251]	eta 0:00:46 lr 0.000124	time 2.4150 (2.2003)	loss 2.2109 (3.2091)	grad_norm 2.5257 (2.4028)	
[2022-01-25 04:12:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1240/1251]	eta 0:00:24 lr 0.000124	time 1.8955 (2.1988)	loss 3.4220 (3.2112)	grad_norm 2.2809 (2.4030)	
[2022-01-25 04:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [233/300][1250/1251]	eta 0:00:02 lr 0.000124	time 1.2129 (2.1933)	loss 3.5124 (3.2134)	grad_norm 2.5301 (2.4033)	
[2022-01-25 04:12:49 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 233 training takes 0:45:44
[2022-01-25 04:13:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.767 (18.767)	Loss 0.8802 (0.8802)	Acc@1 78.613 (78.613)	Acc@5 95.508 (95.508)	
[2022-01-25 04:13:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.900 (3.524)	Loss 0.8189 (0.8463)	Acc@1 81.055 (79.980)	Acc@5 95.020 (95.162)	
[2022-01-25 04:13:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.640 (2.679)	Loss 0.8554 (0.8729)	Acc@1 79.883 (79.548)	Acc@5 95.215 (94.987)	
[2022-01-25 04:14:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.659 (2.300)	Loss 0.8309 (0.8695)	Acc@1 80.371 (79.602)	Acc@5 95.605 (94.947)	
[2022-01-25 04:14:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.161 (2.221)	Loss 0.8156 (0.8657)	Acc@1 81.250 (79.716)	Acc@5 96.289 (95.024)	
[2022-01-25 04:14:28 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.736 Acc@5 95.042
[2022-01-25 04:14:28 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.7%
[2022-01-25 04:14:28 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.78%
[2022-01-25 04:14:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][0/1251]	eta 8:21:37 lr 0.000124	time 24.0585 (24.0585)	loss 3.6809 (3.6809)	grad_norm 2.0408 (2.0408)	
[2022-01-25 04:15:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][10/1251]	eta 1:26:08 lr 0.000124	time 1.2514 (4.1647)	loss 2.9889 (3.4350)	grad_norm 2.2403 (2.3999)	
[2022-01-25 04:15:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][20/1251]	eta 1:04:06 lr 0.000124	time 1.5313 (3.1251)	loss 3.4927 (3.4315)	grad_norm 2.1731 (2.4164)	
[2022-01-25 04:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][30/1251]	eta 0:56:52 lr 0.000124	time 1.7459 (2.7945)	loss 3.5010 (3.3405)	grad_norm 2.8640 (2.4106)	
[2022-01-25 04:16:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][40/1251]	eta 0:55:05 lr 0.000123	time 4.2146 (2.7298)	loss 3.2174 (3.3480)	grad_norm 2.4866 (2.4578)	
[2022-01-25 04:16:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][50/1251]	eta 0:52:55 lr 0.000123	time 1.8921 (2.6437)	loss 3.1874 (3.3646)	grad_norm 2.4254 (2.4444)	
[2022-01-25 04:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][60/1251]	eta 0:50:55 lr 0.000123	time 1.2959 (2.5658)	loss 3.2460 (3.2868)	grad_norm 2.3184 (2.4188)	
[2022-01-25 04:17:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][70/1251]	eta 0:49:33 lr 0.000123	time 1.5830 (2.5181)	loss 2.9814 (3.2861)	grad_norm 2.2292 (2.4043)	
[2022-01-25 04:17:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][80/1251]	eta 0:48:41 lr 0.000123	time 3.5175 (2.4946)	loss 2.7747 (3.2883)	grad_norm 2.4666 (2.3947)	
[2022-01-25 04:18:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][90/1251]	eta 0:47:45 lr 0.000123	time 1.5510 (2.4677)	loss 3.6839 (3.2821)	grad_norm 2.2879 (2.4258)	
[2022-01-25 04:18:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][100/1251]	eta 0:46:38 lr 0.000123	time 1.8167 (2.4316)	loss 3.5344 (3.2828)	grad_norm 2.2205 (2.4234)	
[2022-01-25 04:18:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][110/1251]	eta 0:45:33 lr 0.000123	time 1.5222 (2.3955)	loss 1.9417 (3.2577)	grad_norm 2.1793 (2.4155)	
[2022-01-25 04:19:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][120/1251]	eta 0:44:41 lr 0.000123	time 2.1446 (2.3713)	loss 3.7606 (3.2577)	grad_norm 2.5037 (2.4104)	
[2022-01-25 04:19:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][130/1251]	eta 0:44:25 lr 0.000123	time 2.5343 (2.3776)	loss 3.3552 (3.2495)	grad_norm 2.4863 (2.4039)	
[2022-01-25 04:20:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][140/1251]	eta 0:43:42 lr 0.000123	time 1.5885 (2.3609)	loss 2.9954 (3.2415)	grad_norm 2.7456 (2.4050)	
[2022-01-25 04:20:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][150/1251]	eta 0:43:06 lr 0.000123	time 1.8408 (2.3488)	loss 2.3308 (3.2367)	grad_norm 2.2239 (2.4088)	
[2022-01-25 04:20:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][160/1251]	eta 0:42:25 lr 0.000123	time 1.8065 (2.3330)	loss 2.5953 (3.2309)	grad_norm 2.0508 (2.4048)	
[2022-01-25 04:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][170/1251]	eta 0:42:06 lr 0.000123	time 2.5488 (2.3374)	loss 2.2219 (3.2128)	grad_norm 2.8225 (2.4044)	
[2022-01-25 04:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][180/1251]	eta 0:41:30 lr 0.000123	time 1.6190 (2.3256)	loss 3.4162 (3.2161)	grad_norm 2.4708 (2.4026)	
[2022-01-25 04:21:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][190/1251]	eta 0:40:45 lr 0.000123	time 1.7667 (2.3046)	loss 3.4406 (3.2117)	grad_norm 2.3358 (2.4024)	
[2022-01-25 04:22:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][200/1251]	eta 0:40:07 lr 0.000123	time 1.9297 (2.2906)	loss 2.6929 (3.1995)	grad_norm 2.4456 (2.4047)	
[2022-01-25 04:22:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][210/1251]	eta 0:39:34 lr 0.000123	time 2.1831 (2.2807)	loss 3.5516 (3.1853)	grad_norm 2.5694 (2.4029)	
[2022-01-25 04:22:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][220/1251]	eta 0:39:12 lr 0.000123	time 2.7172 (2.2815)	loss 3.5537 (3.1840)	grad_norm 2.2933 (2.4019)	
[2022-01-25 04:23:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][230/1251]	eta 0:38:50 lr 0.000123	time 2.2815 (2.2822)	loss 2.6277 (3.1862)	grad_norm 2.6065 (2.3999)	
[2022-01-25 04:23:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][240/1251]	eta 0:38:26 lr 0.000123	time 1.9849 (2.2816)	loss 3.7205 (3.1877)	grad_norm 2.2712 (2.4013)	
[2022-01-25 04:24:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][250/1251]	eta 0:38:04 lr 0.000123	time 2.5376 (2.2826)	loss 3.6496 (3.1887)	grad_norm 2.2605 (2.3957)	
[2022-01-25 04:24:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][260/1251]	eta 0:37:43 lr 0.000123	time 2.5713 (2.2836)	loss 2.7383 (3.1802)	grad_norm 2.0211 (2.4004)	
[2022-01-25 04:24:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][270/1251]	eta 0:37:11 lr 0.000123	time 1.6347 (2.2750)	loss 3.2399 (3.1777)	grad_norm 2.4679 (2.4039)	
[2022-01-25 04:25:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][280/1251]	eta 0:36:37 lr 0.000123	time 1.9125 (2.2636)	loss 3.4383 (3.1713)	grad_norm 2.0027 (2.3995)	
[2022-01-25 04:25:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][290/1251]	eta 0:36:07 lr 0.000123	time 1.9795 (2.2550)	loss 3.5024 (3.1653)	grad_norm 2.2947 (2.3974)	
[2022-01-25 04:25:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][300/1251]	eta 0:35:41 lr 0.000123	time 1.9792 (2.2523)	loss 3.5536 (3.1690)	grad_norm 4.0659 (2.4104)	
[2022-01-25 04:26:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][310/1251]	eta 0:35:18 lr 0.000123	time 1.9514 (2.2517)	loss 3.0961 (3.1741)	grad_norm 2.3497 (2.4082)	
[2022-01-25 04:26:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][320/1251]	eta 0:34:53 lr 0.000123	time 2.0834 (2.2491)	loss 3.5336 (3.1739)	grad_norm 2.3280 (2.4092)	
[2022-01-25 04:26:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][330/1251]	eta 0:34:32 lr 0.000123	time 2.1892 (2.2503)	loss 3.2777 (3.1788)	grad_norm 2.1128 (2.4129)	
[2022-01-25 04:27:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][340/1251]	eta 0:34:08 lr 0.000123	time 1.7434 (2.2483)	loss 2.9750 (3.1822)	grad_norm 2.7651 (2.4219)	
[2022-01-25 04:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][350/1251]	eta 0:33:46 lr 0.000123	time 2.3398 (2.2488)	loss 2.5608 (3.1742)	grad_norm 3.1204 (2.4231)	
[2022-01-25 04:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][360/1251]	eta 0:33:23 lr 0.000123	time 1.9682 (2.2481)	loss 3.3457 (3.1641)	grad_norm 2.1174 (2.4566)	
[2022-01-25 04:28:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][370/1251]	eta 0:33:02 lr 0.000123	time 3.0630 (2.2505)	loss 3.7352 (3.1699)	grad_norm 2.4309 (2.4579)	
[2022-01-25 04:28:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][380/1251]	eta 0:32:36 lr 0.000123	time 2.1158 (2.2464)	loss 2.5036 (3.1725)	grad_norm 2.5055 (2.4583)	
[2022-01-25 04:29:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][390/1251]	eta 0:32:12 lr 0.000123	time 2.5216 (2.2446)	loss 2.3075 (3.1738)	grad_norm 2.4880 (2.4584)	
[2022-01-25 04:29:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][400/1251]	eta 0:31:44 lr 0.000123	time 1.9072 (2.2383)	loss 2.8021 (3.1757)	grad_norm 2.4145 (2.4597)	
[2022-01-25 04:29:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][410/1251]	eta 0:31:21 lr 0.000123	time 2.8203 (2.2375)	loss 2.5128 (3.1746)	grad_norm 3.3081 (2.4587)	
[2022-01-25 04:30:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][420/1251]	eta 0:31:00 lr 0.000122	time 2.5721 (2.2392)	loss 3.9677 (3.1758)	grad_norm 2.1857 (2.4588)	
[2022-01-25 04:30:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][430/1251]	eta 0:30:36 lr 0.000122	time 2.0691 (2.2374)	loss 2.3760 (3.1697)	grad_norm 2.3384 (2.4584)	
[2022-01-25 04:30:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][440/1251]	eta 0:30:13 lr 0.000122	time 1.7755 (2.2362)	loss 2.7152 (3.1652)	grad_norm 2.5933 (2.4629)	
[2022-01-25 04:31:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][450/1251]	eta 0:29:50 lr 0.000122	time 3.0058 (2.2359)	loss 3.2752 (3.1664)	grad_norm 2.2182 (2.4613)	
[2022-01-25 04:31:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][460/1251]	eta 0:29:27 lr 0.000122	time 1.8172 (2.2350)	loss 3.7933 (3.1654)	grad_norm 2.1775 (2.4576)	
[2022-01-25 04:31:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][470/1251]	eta 0:29:01 lr 0.000122	time 1.9026 (2.2292)	loss 2.0513 (3.1638)	grad_norm 2.2845 (2.4532)	
[2022-01-25 04:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][480/1251]	eta 0:28:35 lr 0.000122	time 1.8615 (2.2253)	loss 2.6321 (3.1630)	grad_norm 2.4547 (2.4509)	
[2022-01-25 04:32:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][490/1251]	eta 0:28:11 lr 0.000122	time 2.5193 (2.2225)	loss 3.8147 (3.1638)	grad_norm 2.4130 (2.4499)	
[2022-01-25 04:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][500/1251]	eta 0:27:48 lr 0.000122	time 2.4952 (2.2216)	loss 3.4222 (3.1668)	grad_norm 2.0862 (2.4525)	
[2022-01-25 04:33:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][510/1251]	eta 0:27:25 lr 0.000122	time 2.5490 (2.2207)	loss 3.1850 (3.1684)	grad_norm 2.2928 (2.4550)	
[2022-01-25 04:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][520/1251]	eta 0:27:04 lr 0.000122	time 2.2943 (2.2221)	loss 3.7108 (3.1681)	grad_norm 2.5640 (2.4552)	
[2022-01-25 04:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][530/1251]	eta 0:26:43 lr 0.000122	time 2.4195 (2.2242)	loss 3.3366 (3.1704)	grad_norm 3.0059 (2.4546)	
[2022-01-25 04:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][540/1251]	eta 0:26:22 lr 0.000122	time 2.0952 (2.2261)	loss 3.6812 (3.1749)	grad_norm 2.3636 (2.4566)	
[2022-01-25 04:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][550/1251]	eta 0:26:00 lr 0.000122	time 1.9055 (2.2256)	loss 3.6432 (3.1754)	grad_norm 2.3017 (2.4559)	
[2022-01-25 04:35:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][560/1251]	eta 0:25:37 lr 0.000122	time 2.7966 (2.2250)	loss 3.0400 (3.1756)	grad_norm 2.6308 (2.4546)	
[2022-01-25 04:35:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][570/1251]	eta 0:25:13 lr 0.000122	time 2.0262 (2.2225)	loss 3.5328 (3.1758)	grad_norm 2.4611 (2.4535)	
[2022-01-25 04:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][580/1251]	eta 0:24:50 lr 0.000122	time 2.6900 (2.2211)	loss 3.1639 (3.1735)	grad_norm 2.3436 (2.4508)	
[2022-01-25 04:36:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][590/1251]	eta 0:24:28 lr 0.000122	time 2.0639 (2.2215)	loss 3.1941 (3.1736)	grad_norm 2.8523 (2.4510)	
[2022-01-25 04:36:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][600/1251]	eta 0:24:07 lr 0.000122	time 2.5947 (2.2231)	loss 3.6235 (3.1740)	grad_norm 2.3068 (2.4505)	
[2022-01-25 04:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][610/1251]	eta 0:23:45 lr 0.000122	time 2.1856 (2.2240)	loss 2.1935 (3.1739)	grad_norm 2.0747 (2.4498)	
[2022-01-25 04:37:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][620/1251]	eta 0:23:20 lr 0.000122	time 2.4415 (2.2202)	loss 3.5578 (3.1725)	grad_norm 2.5738 (2.4471)	
[2022-01-25 04:37:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][630/1251]	eta 0:22:55 lr 0.000122	time 1.6059 (2.2154)	loss 2.6673 (3.1703)	grad_norm 2.6835 (2.4451)	
[2022-01-25 04:38:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][640/1251]	eta 0:22:33 lr 0.000122	time 2.8380 (2.2157)	loss 3.3823 (3.1676)	grad_norm 2.2579 (2.4418)	
[2022-01-25 04:38:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][650/1251]	eta 0:22:12 lr 0.000122	time 2.6886 (2.2179)	loss 3.1570 (3.1676)	grad_norm 2.1843 (2.4388)	
[2022-01-25 04:38:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][660/1251]	eta 0:21:51 lr 0.000122	time 1.8982 (2.2198)	loss 3.0620 (3.1689)	grad_norm 2.1926 (2.4376)	
[2022-01-25 04:39:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][670/1251]	eta 0:21:29 lr 0.000122	time 2.1351 (2.2189)	loss 3.5696 (3.1694)	grad_norm 2.6149 (2.4349)	
[2022-01-25 04:39:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][680/1251]	eta 0:21:06 lr 0.000122	time 3.2413 (2.2184)	loss 3.3954 (3.1704)	grad_norm 2.8051 (2.4364)	
[2022-01-25 04:40:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][690/1251]	eta 0:20:43 lr 0.000122	time 2.3600 (2.2172)	loss 2.1403 (3.1696)	grad_norm 2.2304 (2.4357)	
[2022-01-25 04:40:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][700/1251]	eta 0:20:19 lr 0.000122	time 2.4650 (2.2139)	loss 3.4137 (3.1695)	grad_norm 2.6560 (2.4353)	
[2022-01-25 04:40:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][710/1251]	eta 0:19:56 lr 0.000122	time 2.2085 (2.2121)	loss 3.5210 (3.1708)	grad_norm 2.5430 (2.4346)	
[2022-01-25 04:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][720/1251]	eta 0:19:35 lr 0.000122	time 2.9890 (2.2131)	loss 3.4734 (3.1704)	grad_norm 2.0599 (2.4326)	
[2022-01-25 04:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][730/1251]	eta 0:19:12 lr 0.000122	time 1.8249 (2.2117)	loss 3.2168 (3.1709)	grad_norm 2.1950 (2.4349)	
[2022-01-25 04:41:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][740/1251]	eta 0:18:49 lr 0.000122	time 2.5688 (2.2107)	loss 2.4829 (3.1696)	grad_norm 2.5715 (2.4367)	
[2022-01-25 04:42:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][750/1251]	eta 0:18:27 lr 0.000122	time 1.8633 (2.2102)	loss 3.4774 (3.1690)	grad_norm 2.6621 (2.4372)	
[2022-01-25 04:42:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][760/1251]	eta 0:18:05 lr 0.000122	time 2.0234 (2.2102)	loss 3.6210 (3.1706)	grad_norm 2.3097 (2.4359)	
[2022-01-25 04:42:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][770/1251]	eta 0:17:43 lr 0.000122	time 1.8456 (2.2114)	loss 3.4978 (3.1724)	grad_norm 2.5320 (2.4375)	
[2022-01-25 04:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][780/1251]	eta 0:17:22 lr 0.000122	time 2.7305 (2.2128)	loss 3.5095 (3.1751)	grad_norm 2.3653 (2.4390)	
[2022-01-25 04:43:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][790/1251]	eta 0:16:59 lr 0.000122	time 1.5666 (2.2118)	loss 2.0875 (3.1756)	grad_norm 2.3911 (2.4412)	
[2022-01-25 04:43:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][800/1251]	eta 0:16:37 lr 0.000121	time 1.9712 (2.2112)	loss 2.6552 (3.1740)	grad_norm 2.1322 (2.4404)	
[2022-01-25 04:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][810/1251]	eta 0:16:15 lr 0.000121	time 1.6709 (2.2109)	loss 3.4575 (3.1756)	grad_norm 2.4159 (2.4416)	
[2022-01-25 04:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][820/1251]	eta 0:15:52 lr 0.000121	time 2.3190 (2.2108)	loss 3.2598 (3.1732)	grad_norm 2.4399 (2.4420)	
[2022-01-25 04:45:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][830/1251]	eta 0:15:29 lr 0.000121	time 1.6289 (2.2090)	loss 3.4166 (3.1746)	grad_norm 2.1878 (2.4405)	
[2022-01-25 04:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][840/1251]	eta 0:15:07 lr 0.000121	time 2.2214 (2.2071)	loss 2.4537 (3.1729)	grad_norm 2.2166 (2.4398)	
[2022-01-25 04:45:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][850/1251]	eta 0:14:45 lr 0.000121	time 2.2386 (2.2078)	loss 3.0274 (3.1717)	grad_norm 2.1928 (2.4381)	
[2022-01-25 04:46:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][860/1251]	eta 0:14:22 lr 0.000121	time 1.9787 (2.2071)	loss 2.5054 (3.1722)	grad_norm 2.1112 (2.4380)	
[2022-01-25 04:46:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][870/1251]	eta 0:14:00 lr 0.000121	time 1.8542 (2.2063)	loss 3.3035 (3.1731)	grad_norm 2.8555 (2.4363)	
[2022-01-25 04:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][880/1251]	eta 0:13:38 lr 0.000121	time 2.2176 (2.2060)	loss 3.2946 (3.1722)	grad_norm 2.6640 (2.4357)	
[2022-01-25 04:47:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][890/1251]	eta 0:13:15 lr 0.000121	time 2.1393 (2.2049)	loss 3.1631 (3.1749)	grad_norm 2.0585 (2.4347)	
[2022-01-25 04:47:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][900/1251]	eta 0:12:53 lr 0.000121	time 2.1712 (2.2029)	loss 3.6201 (3.1773)	grad_norm 2.0268 (2.4335)	
[2022-01-25 04:47:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][910/1251]	eta 0:12:31 lr 0.000121	time 1.8143 (2.2029)	loss 3.2942 (3.1781)	grad_norm 2.8005 (2.4329)	
[2022-01-25 04:48:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][920/1251]	eta 0:12:09 lr 0.000121	time 2.8624 (2.2025)	loss 3.6844 (3.1773)	grad_norm 2.3870 (2.4322)	
[2022-01-25 04:48:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][930/1251]	eta 0:11:47 lr 0.000121	time 3.1994 (2.2044)	loss 2.6060 (3.1768)	grad_norm 2.2123 (2.4302)	
[2022-01-25 04:49:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][940/1251]	eta 0:11:26 lr 0.000121	time 2.9640 (2.2064)	loss 3.3625 (3.1782)	grad_norm 2.4303 (2.4315)	
[2022-01-25 04:49:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][950/1251]	eta 0:11:04 lr 0.000121	time 1.7027 (2.2061)	loss 2.5800 (3.1772)	grad_norm 2.4095 (2.4322)	
[2022-01-25 04:49:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][960/1251]	eta 0:10:41 lr 0.000121	time 1.6024 (2.2044)	loss 3.3900 (3.1757)	grad_norm 2.0880 (2.4329)	
[2022-01-25 04:50:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][970/1251]	eta 0:10:19 lr 0.000121	time 2.2065 (2.2032)	loss 3.8853 (3.1772)	grad_norm 3.1297 (2.4342)	
[2022-01-25 04:50:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][980/1251]	eta 0:09:56 lr 0.000121	time 2.2343 (2.2016)	loss 3.8046 (3.1771)	grad_norm 2.3148 (2.4345)	
[2022-01-25 04:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][990/1251]	eta 0:09:34 lr 0.000121	time 2.2481 (2.2006)	loss 3.0891 (3.1758)	grad_norm 2.2940 (2.4332)	
[2022-01-25 04:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1000/1251]	eta 0:09:12 lr 0.000121	time 2.4792 (2.2009)	loss 3.5743 (3.1756)	grad_norm 2.1428 (2.4320)	
[2022-01-25 04:51:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1010/1251]	eta 0:08:50 lr 0.000121	time 1.6130 (2.1994)	loss 3.0374 (3.1747)	grad_norm 2.4230 (2.4308)	
[2022-01-25 04:51:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1020/1251]	eta 0:08:28 lr 0.000121	time 2.5794 (2.2021)	loss 2.9361 (3.1729)	grad_norm 2.0613 (2.4300)	
[2022-01-25 04:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1030/1251]	eta 0:08:06 lr 0.000121	time 2.4604 (2.2024)	loss 3.0847 (3.1736)	grad_norm 2.3261 (2.4285)	
[2022-01-25 04:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1040/1251]	eta 0:07:44 lr 0.000121	time 2.6961 (2.2037)	loss 2.6542 (3.1718)	grad_norm 2.6359 (2.4278)	
[2022-01-25 04:53:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1050/1251]	eta 0:07:22 lr 0.000121	time 2.0235 (2.2028)	loss 3.4175 (3.1748)	grad_norm 2.7026 (2.4275)	
[2022-01-25 04:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1060/1251]	eta 0:07:00 lr 0.000121	time 2.1198 (2.2032)	loss 3.2478 (3.1757)	grad_norm 2.3508 (2.4277)	
[2022-01-25 04:53:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1070/1251]	eta 0:06:38 lr 0.000121	time 3.0418 (2.2037)	loss 3.7436 (3.1781)	grad_norm 2.6591 (2.4275)	
[2022-01-25 04:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1080/1251]	eta 0:06:16 lr 0.000121	time 1.6563 (2.2013)	loss 2.4809 (3.1770)	grad_norm 3.5896 (2.4286)	
[2022-01-25 04:54:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1090/1251]	eta 0:05:54 lr 0.000121	time 1.6975 (2.1993)	loss 3.1405 (3.1789)	grad_norm 2.1887 (2.4292)	
[2022-01-25 04:54:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1100/1251]	eta 0:05:32 lr 0.000121	time 2.3965 (2.1996)	loss 3.6919 (3.1785)	grad_norm 2.4054 (2.4298)	
[2022-01-25 04:55:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1110/1251]	eta 0:05:10 lr 0.000121	time 3.6264 (2.2025)	loss 3.7226 (3.1789)	grad_norm 2.3851 (2.4359)	
[2022-01-25 04:55:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1120/1251]	eta 0:04:48 lr 0.000121	time 1.9573 (2.2028)	loss 3.0546 (3.1790)	grad_norm 2.5968 (2.4350)	
[2022-01-25 04:55:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1130/1251]	eta 0:04:26 lr 0.000121	time 1.6263 (2.2018)	loss 2.7937 (3.1760)	grad_norm 2.5934 (2.4353)	
[2022-01-25 04:56:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1140/1251]	eta 0:04:04 lr 0.000121	time 1.8288 (2.2019)	loss 3.2331 (3.1768)	grad_norm 1.9799 (2.4334)	
[2022-01-25 04:56:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1150/1251]	eta 0:03:42 lr 0.000121	time 2.9299 (2.2020)	loss 3.6037 (3.1758)	grad_norm 2.2034 (2.4332)	
[2022-01-25 04:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1160/1251]	eta 0:03:20 lr 0.000121	time 2.4499 (2.2004)	loss 3.6275 (3.1748)	grad_norm 2.6573 (2.4333)	
[2022-01-25 04:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1170/1251]	eta 0:02:58 lr 0.000121	time 1.7966 (2.1997)	loss 2.6196 (3.1751)	grad_norm 2.2626 (2.4330)	
[2022-01-25 04:57:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1180/1251]	eta 0:02:36 lr 0.000120	time 2.0097 (2.1991)	loss 2.6418 (3.1740)	grad_norm 2.4631 (2.4331)	
[2022-01-25 04:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1190/1251]	eta 0:02:14 lr 0.000120	time 2.2251 (2.1989)	loss 2.3859 (3.1730)	grad_norm 2.1988 (2.4347)	
[2022-01-25 04:58:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1200/1251]	eta 0:01:52 lr 0.000120	time 2.1621 (2.1981)	loss 3.0288 (3.1737)	grad_norm 2.1913 (2.4338)	
[2022-01-25 04:58:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1210/1251]	eta 0:01:30 lr 0.000120	time 2.5565 (2.1980)	loss 3.0264 (3.1728)	grad_norm 2.1208 (2.4323)	
[2022-01-25 04:59:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1220/1251]	eta 0:01:08 lr 0.000120	time 2.4800 (2.1976)	loss 2.9933 (3.1699)	grad_norm 2.1253 (2.4318)	
[2022-01-25 04:59:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1230/1251]	eta 0:00:46 lr 0.000120	time 1.8303 (2.1975)	loss 3.0404 (3.1701)	grad_norm 2.0733 (2.4320)	
[2022-01-25 04:59:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1240/1251]	eta 0:00:24 lr 0.000120	time 1.7105 (2.1968)	loss 3.5568 (3.1702)	grad_norm 2.1938 (2.4323)	
[2022-01-25 05:00:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [234/300][1250/1251]	eta 0:00:02 lr 0.000120	time 1.1737 (2.1913)	loss 3.5128 (3.1713)	grad_norm 2.2568 (2.4328)	
[2022-01-25 05:00:10 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 234 training takes 0:45:41
[2022-01-25 05:00:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.898 (18.898)	Loss 0.9800 (0.9800)	Acc@1 77.441 (77.441)	Acc@5 93.359 (93.359)	
[2022-01-25 05:00:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.316 (3.450)	Loss 0.9190 (0.8766)	Acc@1 78.223 (79.785)	Acc@5 94.629 (94.691)	
[2022-01-25 05:01:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.318 (2.627)	Loss 0.8707 (0.8681)	Acc@1 79.883 (79.832)	Acc@5 95.312 (94.927)	
[2022-01-25 05:01:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.597 (2.259)	Loss 0.7989 (0.8644)	Acc@1 80.273 (79.895)	Acc@5 95.898 (94.988)	
[2022-01-25 05:01:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 5.029 (2.213)	Loss 0.8360 (0.8565)	Acc@1 81.348 (79.904)	Acc@5 95.117 (95.091)	
[2022-01-25 05:01:47 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.818 Acc@5 95.022
[2022-01-25 05:01:47 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.8%
[2022-01-25 05:01:47 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.82%
[2022-01-25 05:02:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][0/1251]	eta 8:32:11 lr 0.000120	time 24.5653 (24.5653)	loss 3.1984 (3.1984)	grad_norm 2.4376 (2.4376)	
[2022-01-25 05:02:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][10/1251]	eta 1:26:07 lr 0.000120	time 2.2451 (4.1638)	loss 3.1736 (3.0965)	grad_norm 2.8175 (2.4483)	
[2022-01-25 05:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][20/1251]	eta 1:04:19 lr 0.000120	time 1.8043 (3.1353)	loss 3.4154 (3.1305)	grad_norm 2.1756 (2.4206)	
[2022-01-25 05:03:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][30/1251]	eta 0:57:51 lr 0.000120	time 1.6830 (2.8434)	loss 3.2143 (3.1522)	grad_norm 2.9608 (2.4586)	
[2022-01-25 05:03:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][40/1251]	eta 0:54:38 lr 0.000120	time 4.6911 (2.7071)	loss 3.5268 (3.2086)	grad_norm 2.4708 (2.4649)	
[2022-01-25 05:04:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][50/1251]	eta 0:52:14 lr 0.000120	time 2.1862 (2.6096)	loss 3.5714 (3.2066)	grad_norm 2.7695 (2.4909)	
[2022-01-25 05:04:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][60/1251]	eta 0:49:57 lr 0.000120	time 1.2671 (2.5168)	loss 2.9989 (3.1577)	grad_norm 2.3714 (2.4895)	
[2022-01-25 05:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][70/1251]	eta 0:49:42 lr 0.000120	time 1.2827 (2.5253)	loss 3.5279 (3.1785)	grad_norm 1.9567 (2.4926)	
[2022-01-25 05:05:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][80/1251]	eta 0:49:00 lr 0.000120	time 3.6010 (2.5108)	loss 3.6307 (3.1459)	grad_norm 2.5227 (2.4746)	
[2022-01-25 05:05:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][90/1251]	eta 0:47:33 lr 0.000120	time 1.5352 (2.4580)	loss 2.2214 (3.1507)	grad_norm 2.5915 (2.4598)	
[2022-01-25 05:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][100/1251]	eta 0:46:21 lr 0.000120	time 1.5379 (2.4162)	loss 3.6305 (3.1307)	grad_norm 2.4331 (2.4645)	
[2022-01-25 05:06:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][110/1251]	eta 0:45:20 lr 0.000120	time 1.5986 (2.3847)	loss 3.4983 (3.1116)	grad_norm 2.5583 (2.4539)	
[2022-01-25 05:06:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][120/1251]	eta 0:44:59 lr 0.000120	time 3.1287 (2.3869)	loss 3.3405 (3.1074)	grad_norm 2.1778 (2.4514)	
[2022-01-25 05:07:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][130/1251]	eta 0:44:33 lr 0.000120	time 1.6599 (2.3853)	loss 3.5951 (3.1181)	grad_norm 2.3878 (2.4413)	
[2022-01-25 05:07:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][140/1251]	eta 0:43:57 lr 0.000120	time 2.2245 (2.3738)	loss 2.3879 (3.1268)	grad_norm 2.3121 (2.4313)	
[2022-01-25 05:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][150/1251]	eta 0:43:20 lr 0.000120	time 1.7834 (2.3621)	loss 3.4617 (3.1252)	grad_norm 2.2955 (2.4404)	
[2022-01-25 05:08:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][160/1251]	eta 0:42:55 lr 0.000120	time 3.1159 (2.3609)	loss 3.4890 (3.1143)	grad_norm 2.3777 (2.4451)	
[2022-01-25 05:08:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][170/1251]	eta 0:42:04 lr 0.000120	time 1.8536 (2.3353)	loss 3.6848 (3.1251)	grad_norm 2.2625 (2.4383)	
[2022-01-25 05:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][180/1251]	eta 0:41:25 lr 0.000120	time 1.9682 (2.3206)	loss 2.7918 (3.1315)	grad_norm 2.8847 (2.4386)	
[2022-01-25 05:09:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][190/1251]	eta 0:40:53 lr 0.000120	time 2.1715 (2.3123)	loss 3.7704 (3.1387)	grad_norm 2.5980 (2.4401)	
[2022-01-25 05:09:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][200/1251]	eta 0:40:21 lr 0.000120	time 2.3686 (2.3044)	loss 3.0977 (3.1510)	grad_norm 2.5313 (2.4358)	
[2022-01-25 05:09:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][210/1251]	eta 0:39:54 lr 0.000120	time 2.4308 (2.3000)	loss 3.6209 (3.1512)	grad_norm 5.8504 (2.4500)	
[2022-01-25 05:10:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][220/1251]	eta 0:39:22 lr 0.000120	time 2.1354 (2.2910)	loss 3.4697 (3.1517)	grad_norm 2.2307 (2.4506)	
[2022-01-25 05:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][230/1251]	eta 0:39:00 lr 0.000120	time 2.5167 (2.2924)	loss 3.7793 (3.1425)	grad_norm 2.4641 (2.4549)	
[2022-01-25 05:11:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][240/1251]	eta 0:38:37 lr 0.000120	time 3.0740 (2.2927)	loss 3.6358 (3.1463)	grad_norm 2.2007 (2.4517)	
[2022-01-25 05:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][250/1251]	eta 0:38:11 lr 0.000120	time 1.5226 (2.2892)	loss 3.3646 (3.1445)	grad_norm 2.7331 (2.4516)	
[2022-01-25 05:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][260/1251]	eta 0:37:44 lr 0.000120	time 2.2123 (2.2847)	loss 3.7175 (3.1464)	grad_norm 2.3720 (2.4502)	
[2022-01-25 05:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][270/1251]	eta 0:37:12 lr 0.000120	time 1.5942 (2.2757)	loss 2.7969 (3.1523)	grad_norm 2.2945 (2.4443)	
[2022-01-25 05:12:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][280/1251]	eta 0:36:46 lr 0.000120	time 2.4578 (2.2720)	loss 2.7254 (3.1534)	grad_norm 2.2215 (2.4435)	
[2022-01-25 05:12:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][290/1251]	eta 0:36:18 lr 0.000120	time 1.8204 (2.2669)	loss 3.2158 (3.1517)	grad_norm 2.2428 (2.4398)	
[2022-01-25 05:13:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][300/1251]	eta 0:35:54 lr 0.000120	time 2.2492 (2.2654)	loss 3.5377 (3.1589)	grad_norm 2.2662 (2.4359)	
[2022-01-25 05:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][310/1251]	eta 0:35:32 lr 0.000120	time 3.0462 (2.2667)	loss 2.2741 (3.1621)	grad_norm 2.5778 (2.4362)	
[2022-01-25 05:13:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][320/1251]	eta 0:35:13 lr 0.000119	time 3.2507 (2.2700)	loss 3.6779 (3.1662)	grad_norm 2.4835 (2.4365)	
[2022-01-25 05:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][330/1251]	eta 0:34:49 lr 0.000119	time 1.9146 (2.2686)	loss 3.6149 (3.1668)	grad_norm 2.5702 (2.4345)	
[2022-01-25 05:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][340/1251]	eta 0:34:26 lr 0.000119	time 2.2527 (2.2688)	loss 3.0667 (3.1637)	grad_norm 2.2935 (2.4349)	
[2022-01-25 05:15:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][350/1251]	eta 0:33:57 lr 0.000119	time 2.2012 (2.2613)	loss 2.0889 (3.1563)	grad_norm 2.2708 (2.4329)	
[2022-01-25 05:15:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][360/1251]	eta 0:33:26 lr 0.000119	time 2.1886 (2.2519)	loss 3.5366 (3.1563)	grad_norm 2.0986 (2.4296)	
[2022-01-25 05:15:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][370/1251]	eta 0:32:55 lr 0.000119	time 1.6540 (2.2422)	loss 3.4914 (3.1586)	grad_norm 2.4457 (2.4337)	
[2022-01-25 05:16:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][380/1251]	eta 0:32:30 lr 0.000119	time 2.1742 (2.2393)	loss 3.4752 (3.1563)	grad_norm 3.3934 (2.4400)	
[2022-01-25 05:16:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][390/1251]	eta 0:32:05 lr 0.000119	time 2.5391 (2.2363)	loss 1.8612 (3.1523)	grad_norm 2.2915 (2.4432)	
[2022-01-25 05:16:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][400/1251]	eta 0:31:42 lr 0.000119	time 2.7542 (2.2355)	loss 3.1192 (3.1473)	grad_norm 2.3714 (2.4436)	
[2022-01-25 05:17:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][410/1251]	eta 0:31:21 lr 0.000119	time 1.8150 (2.2366)	loss 3.0314 (3.1448)	grad_norm 2.2558 (2.4440)	
[2022-01-25 05:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][420/1251]	eta 0:31:00 lr 0.000119	time 1.8329 (2.2393)	loss 3.1689 (3.1448)	grad_norm 2.3335 (2.4465)	
[2022-01-25 05:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][430/1251]	eta 0:30:40 lr 0.000119	time 1.8837 (2.2417)	loss 3.6817 (3.1465)	grad_norm 2.3102 (2.4455)	
[2022-01-25 05:18:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][440/1251]	eta 0:30:16 lr 0.000119	time 2.2158 (2.2398)	loss 3.4565 (3.1455)	grad_norm 2.3955 (2.4449)	
[2022-01-25 05:18:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][450/1251]	eta 0:29:57 lr 0.000119	time 3.0079 (2.2441)	loss 3.7295 (3.1448)	grad_norm 2.3966 (2.4457)	
[2022-01-25 05:19:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][460/1251]	eta 0:29:34 lr 0.000119	time 2.0418 (2.2435)	loss 3.1382 (3.1431)	grad_norm 2.5694 (2.4442)	
[2022-01-25 05:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][470/1251]	eta 0:29:09 lr 0.000119	time 1.8616 (2.2396)	loss 3.3752 (3.1432)	grad_norm 2.6371 (2.4499)	
[2022-01-25 05:19:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][480/1251]	eta 0:28:42 lr 0.000119	time 1.9754 (2.2343)	loss 2.5778 (3.1395)	grad_norm 2.0214 (2.4450)	
[2022-01-25 05:20:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][490/1251]	eta 0:28:18 lr 0.000119	time 2.4345 (2.2316)	loss 2.0907 (3.1385)	grad_norm 2.2994 (2.4458)	
[2022-01-25 05:20:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][500/1251]	eta 0:27:56 lr 0.000119	time 2.5267 (2.2324)	loss 2.8475 (3.1380)	grad_norm 2.1093 (2.4457)	
[2022-01-25 05:20:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][510/1251]	eta 0:27:32 lr 0.000119	time 2.1161 (2.2302)	loss 2.3453 (3.1393)	grad_norm 2.3158 (2.4460)	
[2022-01-25 05:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][520/1251]	eta 0:27:09 lr 0.000119	time 2.5056 (2.2296)	loss 2.2013 (3.1380)	grad_norm 2.6026 (2.4471)	
[2022-01-25 05:21:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][530/1251]	eta 0:26:47 lr 0.000119	time 2.4215 (2.2302)	loss 2.6654 (3.1424)	grad_norm 2.0216 (2.4439)	
[2022-01-25 05:21:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][540/1251]	eta 0:26:23 lr 0.000119	time 2.2925 (2.2272)	loss 3.3547 (3.1467)	grad_norm 2.3313 (2.4437)	
[2022-01-25 05:22:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][550/1251]	eta 0:25:59 lr 0.000119	time 2.5176 (2.2247)	loss 3.1857 (3.1501)	grad_norm 2.0536 (2.4414)	
[2022-01-25 05:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][560/1251]	eta 0:25:36 lr 0.000119	time 2.1829 (2.2230)	loss 3.4799 (3.1486)	grad_norm 2.6584 (2.4402)	
[2022-01-25 05:22:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][570/1251]	eta 0:25:14 lr 0.000119	time 1.8235 (2.2236)	loss 3.5920 (3.1501)	grad_norm 2.7174 (2.4399)	
[2022-01-25 05:23:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][580/1251]	eta 0:24:52 lr 0.000119	time 2.0119 (2.2242)	loss 2.8438 (3.1474)	grad_norm 2.3506 (2.4379)	
[2022-01-25 05:23:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][590/1251]	eta 0:24:28 lr 0.000119	time 2.4696 (2.2219)	loss 3.1563 (3.1476)	grad_norm 3.0962 (2.4379)	
[2022-01-25 05:24:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][600/1251]	eta 0:24:04 lr 0.000119	time 2.1805 (2.2183)	loss 3.3957 (3.1532)	grad_norm 2.2984 (2.4447)	
[2022-01-25 05:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][610/1251]	eta 0:23:40 lr 0.000119	time 1.9101 (2.2168)	loss 2.6071 (3.1522)	grad_norm 2.5371 (2.4432)	
[2022-01-25 05:24:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][620/1251]	eta 0:23:20 lr 0.000119	time 3.2398 (2.2197)	loss 3.0453 (3.1548)	grad_norm 2.5086 (2.4448)	
[2022-01-25 05:25:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][630/1251]	eta 0:22:58 lr 0.000119	time 2.5429 (2.2204)	loss 2.9007 (3.1553)	grad_norm 2.3037 (2.4481)	
[2022-01-25 05:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][640/1251]	eta 0:22:36 lr 0.000119	time 2.1047 (2.2201)	loss 3.8382 (3.1583)	grad_norm 2.2667 (2.4484)	
[2022-01-25 05:25:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][650/1251]	eta 0:22:12 lr 0.000119	time 2.5399 (2.2175)	loss 3.3128 (3.1563)	grad_norm 2.1528 (2.4474)	
[2022-01-25 05:26:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][660/1251]	eta 0:21:50 lr 0.000119	time 2.7359 (2.2166)	loss 2.7883 (3.1571)	grad_norm 2.4496 (2.4467)	
[2022-01-25 05:26:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][670/1251]	eta 0:21:25 lr 0.000119	time 1.5574 (2.2132)	loss 2.0718 (3.1552)	grad_norm 2.2972 (2.4468)	
[2022-01-25 05:26:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][680/1251]	eta 0:21:02 lr 0.000119	time 1.8999 (2.2114)	loss 2.5981 (3.1526)	grad_norm 2.2244 (2.4468)	
[2022-01-25 05:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][690/1251]	eta 0:20:40 lr 0.000119	time 2.4906 (2.2114)	loss 3.4607 (3.1508)	grad_norm 2.2334 (2.4450)	
[2022-01-25 05:27:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][700/1251]	eta 0:20:19 lr 0.000118	time 3.2027 (2.2135)	loss 3.5777 (3.1527)	grad_norm 2.5437 (2.4431)	
[2022-01-25 05:28:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][710/1251]	eta 0:19:57 lr 0.000118	time 1.7958 (2.2131)	loss 3.5214 (3.1537)	grad_norm 2.5471 (2.4442)	
[2022-01-25 05:28:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][720/1251]	eta 0:19:34 lr 0.000118	time 1.6438 (2.2128)	loss 3.2397 (3.1535)	grad_norm 2.4536 (2.4445)	
[2022-01-25 05:28:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][730/1251]	eta 0:19:12 lr 0.000118	time 1.6174 (2.2114)	loss 2.2644 (3.1509)	grad_norm 2.3380 (2.4424)	
[2022-01-25 05:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][740/1251]	eta 0:18:50 lr 0.000118	time 2.5760 (2.2124)	loss 3.8056 (3.1507)	grad_norm 2.7631 (2.4421)	
[2022-01-25 05:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][750/1251]	eta 0:18:27 lr 0.000118	time 2.6376 (2.2116)	loss 2.2941 (3.1507)	grad_norm 2.3098 (2.4416)	
[2022-01-25 05:29:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][760/1251]	eta 0:18:04 lr 0.000118	time 2.1189 (2.2096)	loss 2.3738 (3.1518)	grad_norm 2.2025 (2.4429)	
[2022-01-25 05:30:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][770/1251]	eta 0:17:42 lr 0.000118	time 2.2183 (2.2089)	loss 3.3852 (3.1523)	grad_norm 2.5886 (2.4427)	
[2022-01-25 05:30:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][780/1251]	eta 0:17:19 lr 0.000118	time 2.5127 (2.2076)	loss 2.9430 (3.1502)	grad_norm 2.3443 (2.4435)	
[2022-01-25 05:30:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][790/1251]	eta 0:16:57 lr 0.000118	time 1.8924 (2.2082)	loss 3.3850 (3.1514)	grad_norm 2.6752 (2.4481)	
[2022-01-25 05:31:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][800/1251]	eta 0:16:36 lr 0.000118	time 2.8333 (2.2096)	loss 3.5554 (3.1529)	grad_norm 2.2754 (2.4483)	
[2022-01-25 05:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][810/1251]	eta 0:16:15 lr 0.000118	time 2.1428 (2.2111)	loss 2.4377 (3.1530)	grad_norm 2.8126 (2.4481)	
[2022-01-25 05:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][820/1251]	eta 0:15:53 lr 0.000118	time 2.3800 (2.2125)	loss 3.5981 (3.1533)	grad_norm 3.2207 (2.4494)	
[2022-01-25 05:32:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][830/1251]	eta 0:15:32 lr 0.000118	time 2.1530 (2.2147)	loss 3.4473 (3.1545)	grad_norm 2.4835 (2.4494)	
[2022-01-25 05:32:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][840/1251]	eta 0:15:10 lr 0.000118	time 2.7654 (2.2147)	loss 3.6405 (3.1562)	grad_norm 2.4837 (2.4509)	
[2022-01-25 05:33:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][850/1251]	eta 0:14:46 lr 0.000118	time 1.8483 (2.2111)	loss 3.1410 (3.1585)	grad_norm 2.4368 (2.4509)	
[2022-01-25 05:33:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][860/1251]	eta 0:14:23 lr 0.000118	time 1.7605 (2.2076)	loss 3.7510 (3.1605)	grad_norm 2.5832 (2.4511)	
[2022-01-25 05:33:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][870/1251]	eta 0:14:00 lr 0.000118	time 2.0169 (2.2068)	loss 3.3522 (3.1611)	grad_norm 2.5884 (2.4497)	
[2022-01-25 05:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][880/1251]	eta 0:13:38 lr 0.000118	time 2.4530 (2.2053)	loss 3.6005 (3.1609)	grad_norm 2.5875 (2.4506)	
[2022-01-25 05:34:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][890/1251]	eta 0:13:16 lr 0.000118	time 2.5125 (2.2059)	loss 2.1491 (3.1588)	grad_norm 2.3343 (2.4537)	
[2022-01-25 05:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][900/1251]	eta 0:12:54 lr 0.000118	time 1.8511 (2.2054)	loss 3.7142 (3.1610)	grad_norm 2.3356 (2.4532)	
[2022-01-25 05:35:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][910/1251]	eta 0:12:32 lr 0.000118	time 2.8396 (2.2070)	loss 2.6352 (3.1586)	grad_norm 2.3439 (2.4530)	
[2022-01-25 05:35:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][920/1251]	eta 0:12:10 lr 0.000118	time 2.3045 (2.2062)	loss 3.1917 (3.1587)	grad_norm 2.4378 (2.4518)	
[2022-01-25 05:36:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][930/1251]	eta 0:11:48 lr 0.000118	time 2.2445 (2.2059)	loss 3.3895 (3.1573)	grad_norm 2.5570 (2.4545)	
[2022-01-25 05:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][940/1251]	eta 0:11:25 lr 0.000118	time 2.2152 (2.2058)	loss 3.1046 (3.1573)	grad_norm 2.6715 (2.4553)	
[2022-01-25 05:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][950/1251]	eta 0:11:04 lr 0.000118	time 2.2115 (2.2069)	loss 2.9969 (3.1562)	grad_norm 1.9798 (2.4546)	
[2022-01-25 05:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][960/1251]	eta 0:10:42 lr 0.000118	time 2.1872 (2.2080)	loss 3.0251 (3.1553)	grad_norm 2.1473 (2.4532)	
[2022-01-25 05:37:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][970/1251]	eta 0:10:20 lr 0.000118	time 2.3766 (2.2092)	loss 3.3571 (3.1578)	grad_norm 2.8976 (2.4548)	
[2022-01-25 05:37:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][980/1251]	eta 0:09:58 lr 0.000118	time 1.6113 (2.2069)	loss 3.6120 (3.1593)	grad_norm 2.8342 (2.4545)	
[2022-01-25 05:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][990/1251]	eta 0:09:35 lr 0.000118	time 1.9011 (2.2062)	loss 3.2132 (3.1601)	grad_norm 2.4288 (2.4549)	
[2022-01-25 05:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1000/1251]	eta 0:09:14 lr 0.000118	time 4.1511 (2.2078)	loss 3.1235 (3.1591)	grad_norm 2.2043 (2.4544)	
[2022-01-25 05:39:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1010/1251]	eta 0:08:52 lr 0.000118	time 1.8320 (2.2086)	loss 3.3958 (3.1600)	grad_norm 2.5672 (2.4547)	
[2022-01-25 05:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1020/1251]	eta 0:08:29 lr 0.000118	time 1.8051 (2.2075)	loss 3.7945 (3.1590)	grad_norm 2.6838 (2.4583)	
[2022-01-25 05:39:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1030/1251]	eta 0:08:07 lr 0.000118	time 2.7117 (2.2065)	loss 3.2500 (3.1596)	grad_norm 2.7380 (2.4579)	
[2022-01-25 05:40:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1040/1251]	eta 0:07:45 lr 0.000118	time 2.0571 (2.2053)	loss 3.7247 (3.1624)	grad_norm 2.9468 (2.4573)	
[2022-01-25 05:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1050/1251]	eta 0:07:23 lr 0.000118	time 1.8438 (2.2052)	loss 3.8657 (3.1638)	grad_norm 2.7073 (2.4581)	
[2022-01-25 05:40:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1060/1251]	eta 0:07:01 lr 0.000118	time 1.4642 (2.2066)	loss 3.4457 (3.1651)	grad_norm 2.2973 (2.4577)	
[2022-01-25 05:41:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1070/1251]	eta 0:06:39 lr 0.000118	time 2.6213 (2.2068)	loss 4.0777 (3.1644)	grad_norm 2.6085 (2.4569)	
[2022-01-25 05:41:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1080/1251]	eta 0:06:17 lr 0.000118	time 1.9289 (2.2064)	loss 3.1124 (3.1651)	grad_norm 2.2685 (2.4573)	
[2022-01-25 05:41:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1090/1251]	eta 0:05:55 lr 0.000117	time 2.2041 (2.2059)	loss 3.2722 (3.1640)	grad_norm 2.5098 (2.4577)	
[2022-01-25 05:42:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1100/1251]	eta 0:05:32 lr 0.000117	time 1.5802 (2.2037)	loss 3.1492 (3.1651)	grad_norm 2.2042 (2.4572)	
[2022-01-25 05:42:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1110/1251]	eta 0:05:10 lr 0.000117	time 1.9794 (2.2020)	loss 3.4035 (3.1656)	grad_norm 2.3952 (2.4560)	
[2022-01-25 05:42:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1120/1251]	eta 0:04:48 lr 0.000117	time 1.8238 (2.2013)	loss 3.3923 (3.1664)	grad_norm 2.2747 (2.4556)	
[2022-01-25 05:43:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1130/1251]	eta 0:04:26 lr 0.000117	time 1.8688 (2.2012)	loss 2.7592 (3.1656)	grad_norm 2.2270 (2.4542)	
[2022-01-25 05:43:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1140/1251]	eta 0:04:04 lr 0.000117	time 2.0001 (2.2010)	loss 3.2708 (3.1652)	grad_norm 2.1791 (2.4531)	
[2022-01-25 05:44:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1150/1251]	eta 0:03:42 lr 0.000117	time 1.9683 (2.2003)	loss 3.3120 (3.1633)	grad_norm 2.3537 (2.4539)	
[2022-01-25 05:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1160/1251]	eta 0:03:20 lr 0.000117	time 1.9496 (2.1995)	loss 2.9656 (3.1632)	grad_norm 2.6741 (2.4528)	
[2022-01-25 05:44:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1170/1251]	eta 0:02:58 lr 0.000117	time 1.9916 (2.2004)	loss 3.8089 (3.1646)	grad_norm 2.3038 (2.4522)	
[2022-01-25 05:45:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1180/1251]	eta 0:02:36 lr 0.000117	time 2.1038 (2.2011)	loss 3.5532 (3.1647)	grad_norm 2.3465 (2.4517)	
[2022-01-25 05:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1190/1251]	eta 0:02:14 lr 0.000117	time 2.2351 (2.2025)	loss 2.3387 (3.1657)	grad_norm 2.2393 (2.4503)	
[2022-01-25 05:45:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1200/1251]	eta 0:01:52 lr 0.000117	time 1.5571 (2.2039)	loss 2.3841 (3.1635)	grad_norm 2.2627 (2.4492)	
[2022-01-25 05:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1210/1251]	eta 0:01:30 lr 0.000117	time 2.1016 (2.2049)	loss 2.1104 (3.1591)	grad_norm 2.5299 (2.4489)	
[2022-01-25 05:46:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1220/1251]	eta 0:01:08 lr 0.000117	time 2.2767 (2.2046)	loss 3.8160 (3.1584)	grad_norm 2.2120 (2.4470)	
[2022-01-25 05:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1230/1251]	eta 0:00:46 lr 0.000117	time 1.6680 (2.2035)	loss 2.3143 (3.1567)	grad_norm 2.3360 (2.4464)	
[2022-01-25 05:47:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1240/1251]	eta 0:00:24 lr 0.000117	time 1.7428 (2.2016)	loss 3.6903 (3.1550)	grad_norm 3.1517 (2.4466)	
[2022-01-25 05:47:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [235/300][1250/1251]	eta 0:00:02 lr 0.000117	time 1.1839 (2.1960)	loss 3.5083 (3.1557)	grad_norm 2.9964 (2.4463)	
[2022-01-25 05:47:35 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 235 training takes 0:45:47
[2022-01-25 05:47:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.154 (18.154)	Loss 0.8595 (0.8595)	Acc@1 79.980 (79.980)	Acc@5 95.410 (95.410)	
[2022-01-25 05:48:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.593 (3.365)	Loss 0.7828 (0.8599)	Acc@1 82.324 (79.918)	Acc@5 95.605 (94.966)	
[2022-01-25 05:48:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.232 (2.492)	Loss 0.8376 (0.8613)	Acc@1 80.176 (79.869)	Acc@5 95.605 (94.959)	
[2022-01-25 05:48:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.319 (2.310)	Loss 0.8577 (0.8712)	Acc@1 78.906 (79.606)	Acc@5 95.410 (94.934)	
[2022-01-25 05:49:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.009 (2.180)	Loss 0.8477 (0.8666)	Acc@1 80.566 (79.690)	Acc@5 94.824 (95.015)	
[2022-01-25 05:49:11 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.764 Acc@5 95.004
[2022-01-25 05:49:11 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.8%
[2022-01-25 05:49:11 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.82%
[2022-01-25 05:49:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][0/1251]	eta 7:27:05 lr 0.000117	time 21.4430 (21.4430)	loss 3.6914 (3.6914)	grad_norm 2.3261 (2.3261)	
[2022-01-25 05:49:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][10/1251]	eta 1:26:47 lr 0.000117	time 2.2863 (4.1959)	loss 3.5459 (3.3956)	grad_norm 2.2529 (2.3106)	
[2022-01-25 05:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][20/1251]	eta 1:05:21 lr 0.000117	time 1.4721 (3.1853)	loss 2.5710 (3.2049)	grad_norm 2.3350 (2.3599)	
[2022-01-25 05:50:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][30/1251]	eta 0:58:30 lr 0.000117	time 1.2640 (2.8750)	loss 2.7756 (3.2298)	grad_norm 2.5076 (2.3522)	
[2022-01-25 05:51:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][40/1251]	eta 0:54:58 lr 0.000117	time 3.6634 (2.7238)	loss 3.9548 (3.2692)	grad_norm 2.2092 (2.3486)	
[2022-01-25 05:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][50/1251]	eta 0:53:06 lr 0.000117	time 2.6113 (2.6532)	loss 3.6569 (3.2447)	grad_norm 2.7298 (2.3756)	
[2022-01-25 05:51:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][60/1251]	eta 0:50:57 lr 0.000117	time 1.5416 (2.5670)	loss 3.4589 (3.2751)	grad_norm 2.4144 (2.3953)	
[2022-01-25 05:52:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][70/1251]	eta 0:49:38 lr 0.000117	time 2.0967 (2.5217)	loss 3.7822 (3.2452)	grad_norm 2.3583 (2.3948)	
[2022-01-25 05:52:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][80/1251]	eta 0:48:37 lr 0.000117	time 3.8419 (2.4912)	loss 3.6673 (3.2317)	grad_norm 2.4252 (2.3906)	
[2022-01-25 05:52:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][90/1251]	eta 0:47:47 lr 0.000117	time 3.2448 (2.4702)	loss 2.6763 (3.2150)	grad_norm 2.4018 (2.3905)	
[2022-01-25 05:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][100/1251]	eta 0:46:35 lr 0.000117	time 2.1139 (2.4288)	loss 2.8246 (3.2066)	grad_norm 2.3968 (2.3859)	
[2022-01-25 05:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][110/1251]	eta 0:45:41 lr 0.000117	time 1.6291 (2.4028)	loss 3.5262 (3.1824)	grad_norm 2.2388 (2.3976)	
[2022-01-25 05:54:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][120/1251]	eta 0:45:14 lr 0.000117	time 3.5028 (2.4004)	loss 2.8373 (3.1907)	grad_norm 2.5223 (2.3921)	
[2022-01-25 05:54:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][130/1251]	eta 0:44:26 lr 0.000117	time 2.5965 (2.3789)	loss 3.6262 (3.2049)	grad_norm 2.8946 (2.3973)	
[2022-01-25 05:54:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][140/1251]	eta 0:43:32 lr 0.000117	time 1.8836 (2.3518)	loss 2.7812 (3.1969)	grad_norm 2.3930 (2.4172)	
[2022-01-25 05:55:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][150/1251]	eta 0:43:06 lr 0.000117	time 2.2876 (2.3497)	loss 3.2058 (3.1933)	grad_norm 3.2814 (2.4213)	
[2022-01-25 05:55:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][160/1251]	eta 0:42:38 lr 0.000117	time 3.0691 (2.3450)	loss 3.3858 (3.1764)	grad_norm 2.1515 (2.4168)	
[2022-01-25 05:55:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][170/1251]	eta 0:42:07 lr 0.000117	time 2.5515 (2.3382)	loss 3.3806 (3.1732)	grad_norm 2.6658 (2.4219)	
[2022-01-25 05:56:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][180/1251]	eta 0:41:33 lr 0.000117	time 2.2898 (2.3284)	loss 3.4250 (3.1701)	grad_norm 2.6583 (2.4224)	
[2022-01-25 05:56:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][190/1251]	eta 0:40:55 lr 0.000117	time 1.9682 (2.3143)	loss 3.5813 (3.1661)	grad_norm 2.4803 (2.4208)	
[2022-01-25 05:56:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][200/1251]	eta 0:40:16 lr 0.000117	time 2.4627 (2.2992)	loss 3.6547 (3.1720)	grad_norm 2.5226 (2.4216)	
[2022-01-25 05:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][210/1251]	eta 0:39:44 lr 0.000117	time 2.1109 (2.2905)	loss 3.3524 (3.1788)	grad_norm 2.5698 (2.4196)	
[2022-01-25 05:57:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][220/1251]	eta 0:39:08 lr 0.000117	time 2.0072 (2.2781)	loss 3.3888 (3.1654)	grad_norm 2.1080 (2.4171)	
[2022-01-25 05:57:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][230/1251]	eta 0:38:36 lr 0.000116	time 1.8935 (2.2690)	loss 2.3994 (3.1660)	grad_norm 2.4295 (2.4131)	
[2022-01-25 05:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][240/1251]	eta 0:38:10 lr 0.000116	time 2.0757 (2.2658)	loss 2.9524 (3.1662)	grad_norm 2.4562 (2.4268)	
[2022-01-25 05:58:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][250/1251]	eta 0:37:45 lr 0.000116	time 2.6579 (2.2628)	loss 3.2019 (3.1485)	grad_norm 2.3389 (2.4259)	
[2022-01-25 05:59:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][260/1251]	eta 0:37:20 lr 0.000116	time 2.1415 (2.2610)	loss 3.1063 (3.1380)	grad_norm 2.1799 (2.4246)	
[2022-01-25 05:59:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][270/1251]	eta 0:37:00 lr 0.000116	time 2.3627 (2.2635)	loss 2.0604 (3.1366)	grad_norm 2.4152 (2.4294)	
[2022-01-25 05:59:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][280/1251]	eta 0:36:42 lr 0.000116	time 2.0765 (2.2681)	loss 2.3640 (3.1341)	grad_norm 2.1971 (2.4282)	
[2022-01-25 06:00:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][290/1251]	eta 0:36:21 lr 0.000116	time 3.1893 (2.2698)	loss 3.4265 (3.1403)	grad_norm 2.2397 (2.4282)	
[2022-01-25 06:00:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][300/1251]	eta 0:35:54 lr 0.000116	time 2.0470 (2.2656)	loss 3.6254 (3.1516)	grad_norm 2.0834 (2.4295)	
[2022-01-25 06:00:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][310/1251]	eta 0:35:27 lr 0.000116	time 1.7128 (2.2612)	loss 3.1966 (3.1561)	grad_norm 2.2386 (2.4300)	
[2022-01-25 06:01:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][320/1251]	eta 0:34:58 lr 0.000116	time 1.6277 (2.2543)	loss 3.4991 (3.1610)	grad_norm 2.6078 (2.4341)	
[2022-01-25 06:01:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][330/1251]	eta 0:34:41 lr 0.000116	time 3.6671 (2.2604)	loss 2.2851 (3.1621)	grad_norm 2.2542 (2.4331)	
[2022-01-25 06:02:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][340/1251]	eta 0:34:21 lr 0.000116	time 1.8970 (2.2626)	loss 3.3407 (3.1594)	grad_norm 2.6464 (2.4332)	
[2022-01-25 06:02:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][350/1251]	eta 0:34:00 lr 0.000116	time 1.7382 (2.2643)	loss 3.1477 (3.1596)	grad_norm 2.2141 (2.4302)	
[2022-01-25 06:02:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][360/1251]	eta 0:33:31 lr 0.000116	time 1.6441 (2.2571)	loss 3.6842 (3.1576)	grad_norm 2.2884 (2.4298)	
[2022-01-25 06:03:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][370/1251]	eta 0:33:02 lr 0.000116	time 2.5174 (2.2502)	loss 3.7232 (3.1560)	grad_norm 2.3548 (2.4251)	
[2022-01-25 06:03:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][380/1251]	eta 0:32:34 lr 0.000116	time 1.9306 (2.2445)	loss 3.2050 (3.1523)	grad_norm 2.1713 (2.4288)	
[2022-01-25 06:03:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][390/1251]	eta 0:32:08 lr 0.000116	time 1.5687 (2.2394)	loss 2.6256 (3.1578)	grad_norm 2.3815 (2.4286)	
[2022-01-25 06:04:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][400/1251]	eta 0:31:43 lr 0.000116	time 2.1194 (2.2366)	loss 3.2851 (3.1569)	grad_norm 2.6911 (2.4279)	
[2022-01-25 06:04:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][410/1251]	eta 0:31:18 lr 0.000116	time 2.2033 (2.2338)	loss 2.6716 (3.1575)	grad_norm 2.3037 (2.4276)	
[2022-01-25 06:04:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][420/1251]	eta 0:30:55 lr 0.000116	time 2.6274 (2.2333)	loss 3.3585 (3.1596)	grad_norm 2.2298 (2.4289)	
[2022-01-25 06:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][430/1251]	eta 0:30:34 lr 0.000116	time 2.2597 (2.2344)	loss 2.3207 (3.1524)	grad_norm 2.9200 (2.4307)	
[2022-01-25 06:05:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][440/1251]	eta 0:30:18 lr 0.000116	time 2.1517 (2.2422)	loss 3.5438 (3.1582)	grad_norm 2.2968 (2.4284)	
[2022-01-25 06:06:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][450/1251]	eta 0:29:58 lr 0.000116	time 2.5765 (2.2451)	loss 3.2198 (3.1597)	grad_norm 2.2844 (2.4292)	
[2022-01-25 06:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][460/1251]	eta 0:29:36 lr 0.000116	time 2.2495 (2.2454)	loss 3.6462 (3.1574)	grad_norm 2.2887 (2.4319)	
[2022-01-25 06:06:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][470/1251]	eta 0:29:13 lr 0.000116	time 1.5954 (2.2448)	loss 2.0472 (3.1568)	grad_norm 2.4309 (2.4308)	
[2022-01-25 06:07:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][480/1251]	eta 0:28:47 lr 0.000116	time 1.9034 (2.2400)	loss 3.3429 (3.1551)	grad_norm 2.7170 (2.4345)	
[2022-01-25 06:07:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][490/1251]	eta 0:28:20 lr 0.000116	time 1.8025 (2.2348)	loss 3.3165 (3.1571)	grad_norm 2.5351 (2.4361)	
[2022-01-25 06:07:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][500/1251]	eta 0:27:56 lr 0.000116	time 2.3238 (2.2319)	loss 2.2254 (3.1537)	grad_norm 2.1634 (2.4364)	
[2022-01-25 06:08:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][510/1251]	eta 0:27:33 lr 0.000116	time 3.1396 (2.2317)	loss 2.6697 (3.1511)	grad_norm 2.4536 (2.4347)	
[2022-01-25 06:08:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][520/1251]	eta 0:27:11 lr 0.000116	time 1.8650 (2.2315)	loss 3.4613 (3.1500)	grad_norm 2.4806 (2.4357)	
[2022-01-25 06:08:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][530/1251]	eta 0:26:50 lr 0.000116	time 1.9618 (2.2336)	loss 3.6492 (3.1494)	grad_norm 2.3959 (2.4338)	
[2022-01-25 06:09:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][540/1251]	eta 0:26:28 lr 0.000116	time 2.5726 (2.2339)	loss 3.8472 (3.1546)	grad_norm 2.5318 (2.4398)	
[2022-01-25 06:09:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][550/1251]	eta 0:26:07 lr 0.000116	time 2.2371 (2.2355)	loss 3.2695 (3.1548)	grad_norm 2.2015 (2.4406)	
[2022-01-25 06:10:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][560/1251]	eta 0:25:42 lr 0.000116	time 2.8013 (2.2317)	loss 3.0706 (3.1498)	grad_norm 2.2184 (2.4417)	
[2022-01-25 06:10:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][570/1251]	eta 0:25:18 lr 0.000116	time 2.1428 (2.2301)	loss 3.1530 (3.1495)	grad_norm 2.4968 (2.4418)	
[2022-01-25 06:10:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][580/1251]	eta 0:24:53 lr 0.000116	time 1.9025 (2.2258)	loss 3.5982 (3.1469)	grad_norm 2.8583 (2.4452)	
[2022-01-25 06:11:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][590/1251]	eta 0:24:29 lr 0.000116	time 2.2021 (2.2239)	loss 3.5715 (3.1494)	grad_norm 2.2572 (2.4479)	
[2022-01-25 06:11:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][600/1251]	eta 0:24:07 lr 0.000116	time 2.4299 (2.2240)	loss 3.3496 (3.1489)	grad_norm 2.9086 (2.4494)	
[2022-01-25 06:11:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][610/1251]	eta 0:23:47 lr 0.000116	time 2.3177 (2.2267)	loss 3.7518 (3.1483)	grad_norm 2.3947 (2.4473)	
[2022-01-25 06:12:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][620/1251]	eta 0:23:23 lr 0.000115	time 1.6040 (2.2236)	loss 3.5902 (3.1506)	grad_norm 2.3926 (2.4460)	
[2022-01-25 06:12:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][630/1251]	eta 0:22:59 lr 0.000115	time 1.9292 (2.2216)	loss 2.5959 (3.1507)	grad_norm 2.4748 (2.4460)	
[2022-01-25 06:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][640/1251]	eta 0:22:39 lr 0.000115	time 2.7678 (2.2243)	loss 2.0915 (3.1487)	grad_norm 2.1129 (2.4424)	
[2022-01-25 06:13:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][650/1251]	eta 0:22:17 lr 0.000115	time 2.8434 (2.2248)	loss 3.5438 (3.1483)	grad_norm 2.2858 (2.4405)	
[2022-01-25 06:13:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][660/1251]	eta 0:21:53 lr 0.000115	time 1.8615 (2.2233)	loss 3.8965 (3.1503)	grad_norm 2.5059 (2.4411)	
[2022-01-25 06:14:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][670/1251]	eta 0:21:30 lr 0.000115	time 1.6208 (2.2206)	loss 3.4546 (3.1458)	grad_norm 2.7629 (2.4401)	
[2022-01-25 06:14:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][680/1251]	eta 0:21:06 lr 0.000115	time 2.4723 (2.2189)	loss 3.6135 (3.1414)	grad_norm 2.3711 (2.4412)	
[2022-01-25 06:14:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][690/1251]	eta 0:20:45 lr 0.000115	time 3.8167 (2.2203)	loss 3.3592 (3.1436)	grad_norm 2.3613 (2.4407)	
[2022-01-25 06:15:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][700/1251]	eta 0:20:23 lr 0.000115	time 1.9569 (2.2207)	loss 3.2981 (3.1424)	grad_norm 2.6629 (2.4374)	
[2022-01-25 06:15:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][710/1251]	eta 0:20:00 lr 0.000115	time 1.6699 (2.2194)	loss 3.0433 (3.1428)	grad_norm 2.2164 (2.4366)	
[2022-01-25 06:15:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][720/1251]	eta 0:19:38 lr 0.000115	time 2.7027 (2.2196)	loss 3.4293 (3.1435)	grad_norm 2.2607 (2.4355)	
[2022-01-25 06:16:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][730/1251]	eta 0:19:14 lr 0.000115	time 2.5507 (2.2166)	loss 3.2917 (3.1472)	grad_norm 2.4161 (2.4361)	
[2022-01-25 06:16:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][740/1251]	eta 0:18:52 lr 0.000115	time 2.0415 (2.2163)	loss 2.6130 (3.1465)	grad_norm 2.2907 (2.4381)	
[2022-01-25 06:16:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][750/1251]	eta 0:18:29 lr 0.000115	time 1.6708 (2.2142)	loss 3.3197 (3.1458)	grad_norm 2.3448 (2.4374)	
[2022-01-25 06:17:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][760/1251]	eta 0:18:07 lr 0.000115	time 2.7762 (2.2154)	loss 3.2738 (3.1465)	grad_norm 2.4106 (2.4374)	
[2022-01-25 06:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][770/1251]	eta 0:17:45 lr 0.000115	time 1.8624 (2.2151)	loss 2.2040 (3.1453)	grad_norm 2.6986 (2.4382)	
[2022-01-25 06:18:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][780/1251]	eta 0:17:23 lr 0.000115	time 1.9416 (2.2146)	loss 2.5893 (3.1448)	grad_norm 2.4333 (2.4374)	
[2022-01-25 06:18:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][790/1251]	eta 0:17:00 lr 0.000115	time 2.6720 (2.2139)	loss 3.2029 (3.1465)	grad_norm 2.5672 (2.4375)	
[2022-01-25 06:18:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][800/1251]	eta 0:16:37 lr 0.000115	time 2.3206 (2.2127)	loss 3.1254 (3.1444)	grad_norm 2.1813 (2.4357)	
[2022-01-25 06:19:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][810/1251]	eta 0:16:14 lr 0.000115	time 1.9253 (2.2102)	loss 2.4848 (3.1441)	grad_norm 2.2828 (2.4368)	
[2022-01-25 06:19:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][820/1251]	eta 0:15:51 lr 0.000115	time 1.8559 (2.2083)	loss 2.7359 (3.1432)	grad_norm 2.6245 (2.4376)	
[2022-01-25 06:19:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][830/1251]	eta 0:15:29 lr 0.000115	time 2.6785 (2.2072)	loss 2.4547 (3.1430)	grad_norm 2.8852 (2.4382)	
[2022-01-25 06:20:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][840/1251]	eta 0:15:07 lr 0.000115	time 2.2383 (2.2071)	loss 2.5814 (3.1412)	grad_norm 2.0504 (2.4366)	
[2022-01-25 06:20:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][850/1251]	eta 0:14:45 lr 0.000115	time 2.2236 (2.2074)	loss 3.8506 (3.1429)	grad_norm 2.5970 (2.4360)	
[2022-01-25 06:20:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][860/1251]	eta 0:14:23 lr 0.000115	time 2.5277 (2.2095)	loss 2.6773 (3.1413)	grad_norm 2.1105 (2.4369)	
[2022-01-25 06:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][870/1251]	eta 0:14:02 lr 0.000115	time 2.6302 (2.2101)	loss 2.9705 (3.1416)	grad_norm 2.2597 (2.4358)	
[2022-01-25 06:21:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][880/1251]	eta 0:13:40 lr 0.000115	time 2.4530 (2.2102)	loss 3.8196 (3.1416)	grad_norm 2.4044 (2.4365)	
[2022-01-25 06:22:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][890/1251]	eta 0:13:18 lr 0.000115	time 1.8415 (2.2107)	loss 3.3362 (3.1419)	grad_norm 2.7000 (2.4368)	
[2022-01-25 06:22:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][900/1251]	eta 0:12:56 lr 0.000115	time 3.1080 (2.2123)	loss 3.0003 (3.1408)	grad_norm 2.9376 (2.4387)	
[2022-01-25 06:22:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][910/1251]	eta 0:12:34 lr 0.000115	time 3.1546 (2.2139)	loss 3.0347 (3.1416)	grad_norm 2.3420 (2.4395)	
[2022-01-25 06:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][920/1251]	eta 0:12:12 lr 0.000115	time 2.2739 (2.2129)	loss 2.4200 (3.1427)	grad_norm 2.1046 (2.4388)	
[2022-01-25 06:23:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][930/1251]	eta 0:11:49 lr 0.000115	time 1.7191 (2.2096)	loss 3.4684 (3.1434)	grad_norm 2.3874 (2.4389)	
[2022-01-25 06:23:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][940/1251]	eta 0:11:26 lr 0.000115	time 2.6584 (2.2078)	loss 3.1759 (3.1429)	grad_norm 2.5688 (2.4378)	
[2022-01-25 06:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][950/1251]	eta 0:11:04 lr 0.000115	time 2.7959 (2.2082)	loss 3.7984 (3.1447)	grad_norm 2.4469 (2.4395)	
[2022-01-25 06:24:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][960/1251]	eta 0:10:42 lr 0.000115	time 2.2327 (2.2086)	loss 3.2843 (3.1447)	grad_norm 2.1699 (2.4400)	
[2022-01-25 06:24:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][970/1251]	eta 0:10:20 lr 0.000115	time 1.9867 (2.2094)	loss 3.1464 (3.1434)	grad_norm 2.3010 (2.4398)	
[2022-01-25 06:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][980/1251]	eta 0:09:58 lr 0.000115	time 2.9018 (2.2097)	loss 3.1673 (3.1424)	grad_norm 2.5482 (2.4399)	
[2022-01-25 06:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][990/1251]	eta 0:09:36 lr 0.000115	time 2.9419 (2.2099)	loss 3.4955 (3.1442)	grad_norm 2.3922 (2.4400)	
[2022-01-25 06:26:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1000/1251]	eta 0:09:14 lr 0.000115	time 1.6418 (2.2082)	loss 3.6151 (3.1435)	grad_norm 2.9677 (2.4399)	
[2022-01-25 06:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1010/1251]	eta 0:08:51 lr 0.000114	time 2.6464 (2.2073)	loss 2.4418 (3.1434)	grad_norm 2.4190 (2.4393)	
[2022-01-25 06:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1020/1251]	eta 0:08:29 lr 0.000114	time 1.8816 (2.2066)	loss 3.4347 (3.1459)	grad_norm 2.5876 (2.4385)	
[2022-01-25 06:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1030/1251]	eta 0:08:07 lr 0.000114	time 3.6309 (2.2078)	loss 3.3432 (3.1451)	grad_norm 3.6013 (2.4398)	
[2022-01-25 06:27:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1040/1251]	eta 0:07:45 lr 0.000114	time 1.8099 (2.2071)	loss 2.8673 (3.1447)	grad_norm 2.5256 (2.4400)	
[2022-01-25 06:27:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1050/1251]	eta 0:07:23 lr 0.000114	time 1.4772 (2.2078)	loss 3.6368 (3.1454)	grad_norm 2.2712 (2.4404)	
[2022-01-25 06:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1060/1251]	eta 0:07:01 lr 0.000114	time 2.0681 (2.2083)	loss 2.8177 (3.1436)	grad_norm 2.3489 (2.4400)	
[2022-01-25 06:28:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1070/1251]	eta 0:06:40 lr 0.000114	time 3.6714 (2.2103)	loss 3.0250 (3.1430)	grad_norm 2.2563 (2.4388)	
[2022-01-25 06:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1080/1251]	eta 0:06:17 lr 0.000114	time 1.6057 (2.2081)	loss 3.3713 (3.1445)	grad_norm 2.6550 (2.4389)	
[2022-01-25 06:29:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1090/1251]	eta 0:05:55 lr 0.000114	time 1.7331 (2.2050)	loss 3.6422 (3.1464)	grad_norm 2.3057 (2.4380)	
[2022-01-25 06:29:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1100/1251]	eta 0:05:32 lr 0.000114	time 1.9744 (2.2047)	loss 3.0217 (3.1470)	grad_norm 2.5041 (2.4372)	
[2022-01-25 06:30:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1110/1251]	eta 0:05:10 lr 0.000114	time 2.0494 (2.2043)	loss 2.5204 (3.1471)	grad_norm 2.3532 (2.4364)	
[2022-01-25 06:30:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1120/1251]	eta 0:04:48 lr 0.000114	time 1.9157 (2.2035)	loss 3.3696 (3.1483)	grad_norm 2.1575 (2.4358)	
[2022-01-25 06:30:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1130/1251]	eta 0:04:26 lr 0.000114	time 1.9514 (2.2033)	loss 3.5032 (3.1465)	grad_norm 1.9566 (2.4355)	
[2022-01-25 06:31:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1140/1251]	eta 0:04:04 lr 0.000114	time 2.2469 (2.2039)	loss 3.4323 (3.1475)	grad_norm 2.0997 (2.4341)	
[2022-01-25 06:31:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1150/1251]	eta 0:03:42 lr 0.000114	time 3.2132 (2.2052)	loss 3.1723 (3.1493)	grad_norm 2.2922 (2.4370)	
[2022-01-25 06:31:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1160/1251]	eta 0:03:20 lr 0.000114	time 1.9880 (2.2054)	loss 3.3309 (3.1495)	grad_norm 2.2898 (2.4365)	
[2022-01-25 06:32:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1170/1251]	eta 0:02:58 lr 0.000114	time 1.9412 (2.2047)	loss 3.4584 (3.1501)	grad_norm 2.5540 (2.4362)	
[2022-01-25 06:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1180/1251]	eta 0:02:36 lr 0.000114	time 1.8897 (2.2045)	loss 2.1868 (3.1501)	grad_norm 2.4094 (2.4372)	
[2022-01-25 06:32:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1190/1251]	eta 0:02:14 lr 0.000114	time 3.5973 (2.2039)	loss 3.2356 (3.1504)	grad_norm 2.1998 (2.4367)	
[2022-01-25 06:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1200/1251]	eta 0:01:52 lr 0.000114	time 1.8931 (2.2030)	loss 3.7313 (3.1506)	grad_norm 2.4863 (2.4359)	
[2022-01-25 06:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1210/1251]	eta 0:01:30 lr 0.000114	time 2.2240 (2.2038)	loss 3.2249 (3.1528)	grad_norm 2.4381 (2.4356)	
[2022-01-25 06:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1220/1251]	eta 0:01:08 lr 0.000114	time 2.2320 (2.2042)	loss 3.4210 (3.1517)	grad_norm 2.2819 (2.4349)	
[2022-01-25 06:34:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1230/1251]	eta 0:00:46 lr 0.000114	time 3.7326 (2.2053)	loss 3.4405 (3.1536)	grad_norm 2.2725 (2.4349)	
[2022-01-25 06:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1240/1251]	eta 0:00:24 lr 0.000114	time 1.3208 (2.2026)	loss 3.3329 (3.1554)	grad_norm 2.3399 (2.4352)	
[2022-01-25 06:35:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [236/300][1250/1251]	eta 0:00:02 lr 0.000114	time 1.3517 (2.1967)	loss 3.2923 (3.1543)	grad_norm 2.1666 (2.4340)	
[2022-01-25 06:35:00 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 236 training takes 0:45:48
[2022-01-25 06:35:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.675 (18.675)	Loss 0.8514 (0.8514)	Acc@1 78.906 (78.906)	Acc@5 95.410 (95.410)	
[2022-01-25 06:35:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.321 (3.505)	Loss 0.8083 (0.8349)	Acc@1 79.980 (80.167)	Acc@5 95.508 (95.250)	
[2022-01-25 06:35:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.593 (2.587)	Loss 0.8576 (0.8454)	Acc@1 79.297 (79.999)	Acc@5 94.238 (95.196)	
[2022-01-25 06:36:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.611 (2.265)	Loss 0.8823 (0.8549)	Acc@1 80.176 (79.952)	Acc@5 94.434 (95.123)	
[2022-01-25 06:36:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.309 (2.190)	Loss 0.8963 (0.8563)	Acc@1 79.297 (79.864)	Acc@5 95.117 (95.096)	
[2022-01-25 06:36:37 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.818 Acc@5 95.102
[2022-01-25 06:36:37 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.8%
[2022-01-25 06:36:37 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.82%
[2022-01-25 06:36:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][0/1251]	eta 7:34:10 lr 0.000114	time 21.7827 (21.7827)	loss 2.8402 (2.8402)	grad_norm 2.6889 (2.6889)	
[2022-01-25 06:37:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][10/1251]	eta 1:25:09 lr 0.000114	time 2.7250 (4.1169)	loss 3.5471 (3.3300)	grad_norm 2.5100 (2.5043)	
[2022-01-25 06:37:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][20/1251]	eta 1:06:45 lr 0.000114	time 2.3520 (3.2541)	loss 2.6081 (3.1329)	grad_norm 2.6271 (2.4961)	
[2022-01-25 06:38:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][30/1251]	eta 1:00:26 lr 0.000114	time 1.9338 (2.9704)	loss 2.9925 (3.1205)	grad_norm 2.3114 (2.4840)	
[2022-01-25 06:38:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][40/1251]	eta 0:57:20 lr 0.000114	time 3.5608 (2.8408)	loss 3.5548 (3.1443)	grad_norm 2.0109 (2.4531)	
[2022-01-25 06:38:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][50/1251]	eta 0:55:02 lr 0.000114	time 2.0429 (2.7499)	loss 3.4941 (3.1417)	grad_norm 2.2164 (2.4309)	
[2022-01-25 06:39:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][60/1251]	eta 0:52:08 lr 0.000114	time 1.5879 (2.6264)	loss 3.3315 (3.1047)	grad_norm 2.1446 (2.4337)	
[2022-01-25 06:39:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][70/1251]	eta 0:49:57 lr 0.000114	time 1.9431 (2.5382)	loss 2.9476 (3.0978)	grad_norm 2.3296 (2.4157)	
[2022-01-25 06:39:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][80/1251]	eta 0:48:01 lr 0.000114	time 1.9360 (2.4608)	loss 2.7590 (3.0708)	grad_norm 2.3060 (2.4069)	
[2022-01-25 06:40:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][90/1251]	eta 0:47:11 lr 0.000114	time 1.9613 (2.4389)	loss 3.3379 (3.0777)	grad_norm 2.2996 (2.4004)	
[2022-01-25 06:40:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][100/1251]	eta 0:46:25 lr 0.000114	time 2.2987 (2.4201)	loss 2.5788 (3.0658)	grad_norm 2.2990 (2.3999)	
[2022-01-25 06:41:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][110/1251]	eta 0:45:34 lr 0.000114	time 2.2646 (2.3962)	loss 2.0673 (3.0561)	grad_norm 2.3530 (2.4025)	
[2022-01-25 06:41:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][120/1251]	eta 0:44:58 lr 0.000114	time 2.6733 (2.3858)	loss 3.5138 (3.0609)	grad_norm 2.8944 (2.4027)	
[2022-01-25 06:41:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][130/1251]	eta 0:44:14 lr 0.000114	time 1.5519 (2.3679)	loss 2.1258 (3.0309)	grad_norm 2.8809 (2.3975)	
[2022-01-25 06:42:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][140/1251]	eta 0:43:39 lr 0.000114	time 2.6285 (2.3577)	loss 2.7085 (3.0229)	grad_norm 2.8948 (2.4108)	
[2022-01-25 06:42:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][150/1251]	eta 0:43:11 lr 0.000113	time 2.1081 (2.3535)	loss 3.3780 (3.0389)	grad_norm 2.8549 (2.4276)	
[2022-01-25 06:42:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][160/1251]	eta 0:42:37 lr 0.000113	time 1.9208 (2.3444)	loss 3.3881 (3.0530)	grad_norm 2.1478 (2.4312)	
[2022-01-25 06:43:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][170/1251]	eta 0:41:56 lr 0.000113	time 1.9953 (2.3279)	loss 2.6488 (3.0588)	grad_norm 2.8234 (2.4337)	
[2022-01-25 06:43:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][180/1251]	eta 0:41:18 lr 0.000113	time 2.2404 (2.3138)	loss 3.1572 (3.0750)	grad_norm 2.6011 (2.4359)	
[2022-01-25 06:43:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][190/1251]	eta 0:40:46 lr 0.000113	time 1.6652 (2.3061)	loss 2.3631 (3.0821)	grad_norm 2.4290 (2.4386)	
[2022-01-25 06:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][200/1251]	eta 0:40:25 lr 0.000113	time 2.1621 (2.3082)	loss 3.3539 (3.0794)	grad_norm 2.2251 (2.4288)	
[2022-01-25 06:44:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][210/1251]	eta 0:40:01 lr 0.000113	time 2.2556 (2.3065)	loss 1.9719 (3.0720)	grad_norm 2.3007 (2.4286)	
[2022-01-25 06:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][220/1251]	eta 0:39:30 lr 0.000113	time 1.9408 (2.2992)	loss 3.2933 (3.0669)	grad_norm 2.1183 (2.4404)	
[2022-01-25 06:45:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][230/1251]	eta 0:38:55 lr 0.000113	time 1.7055 (2.2870)	loss 3.7754 (3.0755)	grad_norm 2.6517 (2.4375)	
[2022-01-25 06:45:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][240/1251]	eta 0:38:18 lr 0.000113	time 1.8518 (2.2733)	loss 3.3407 (3.0825)	grad_norm 2.8530 (2.4376)	
[2022-01-25 06:46:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][250/1251]	eta 0:37:47 lr 0.000113	time 1.8998 (2.2656)	loss 3.6012 (3.0892)	grad_norm 2.6559 (2.4395)	
[2022-01-25 06:46:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][260/1251]	eta 0:37:27 lr 0.000113	time 1.7903 (2.2675)	loss 3.4781 (3.0990)	grad_norm 2.3135 (2.4421)	
[2022-01-25 06:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][270/1251]	eta 0:37:02 lr 0.000113	time 2.1058 (2.2660)	loss 3.5996 (3.0961)	grad_norm 2.2703 (2.4403)	
[2022-01-25 06:47:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][280/1251]	eta 0:36:41 lr 0.000113	time 1.6413 (2.2671)	loss 3.4419 (3.1047)	grad_norm 2.3484 (2.4410)	
[2022-01-25 06:47:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][290/1251]	eta 0:36:15 lr 0.000113	time 1.8781 (2.2636)	loss 2.3821 (3.0988)	grad_norm 2.6916 (2.4419)	
[2022-01-25 06:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][300/1251]	eta 0:35:54 lr 0.000113	time 1.9524 (2.2655)	loss 3.8596 (3.1049)	grad_norm 2.6400 (2.4393)	
[2022-01-25 06:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][310/1251]	eta 0:35:30 lr 0.000113	time 1.6628 (2.2646)	loss 3.5960 (3.1066)	grad_norm 2.2171 (2.4393)	
[2022-01-25 06:48:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][320/1251]	eta 0:35:03 lr 0.000113	time 1.8741 (2.2598)	loss 2.6940 (3.1085)	grad_norm 2.6125 (2.4377)	
[2022-01-25 06:49:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][330/1251]	eta 0:34:36 lr 0.000113	time 1.8631 (2.2544)	loss 2.5271 (3.1064)	grad_norm 2.3983 (2.4385)	
[2022-01-25 06:49:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][340/1251]	eta 0:34:10 lr 0.000113	time 2.0110 (2.2507)	loss 2.8278 (3.1036)	grad_norm 2.3685 (2.4409)	
[2022-01-25 06:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][350/1251]	eta 0:33:43 lr 0.000113	time 1.9255 (2.2458)	loss 2.9739 (3.1027)	grad_norm 2.6451 (2.4406)	
[2022-01-25 06:50:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][360/1251]	eta 0:33:15 lr 0.000113	time 1.7784 (2.2398)	loss 3.6831 (3.1106)	grad_norm 2.5478 (2.4423)	
[2022-01-25 06:50:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][370/1251]	eta 0:32:54 lr 0.000113	time 2.4793 (2.2416)	loss 3.1972 (3.1127)	grad_norm 3.5599 (2.4478)	
[2022-01-25 06:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][380/1251]	eta 0:32:35 lr 0.000113	time 3.4756 (2.2449)	loss 2.9270 (3.1130)	grad_norm 2.1379 (2.4480)	
[2022-01-25 06:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][390/1251]	eta 0:32:14 lr 0.000113	time 1.7749 (2.2464)	loss 2.5624 (3.1125)	grad_norm 2.3846 (2.4485)	
[2022-01-25 06:51:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][400/1251]	eta 0:31:51 lr 0.000113	time 2.2414 (2.2460)	loss 3.0269 (3.1158)	grad_norm 2.2840 (2.4554)	
[2022-01-25 06:52:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][410/1251]	eta 0:31:28 lr 0.000113	time 2.5323 (2.2453)	loss 3.1809 (3.1160)	grad_norm 2.7868 (2.4540)	
[2022-01-25 06:52:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][420/1251]	eta 0:31:00 lr 0.000113	time 1.9500 (2.2394)	loss 2.9045 (3.1203)	grad_norm 2.3632 (2.4513)	
[2022-01-25 06:52:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][430/1251]	eta 0:30:35 lr 0.000113	time 1.8750 (2.2357)	loss 2.8194 (3.1209)	grad_norm 2.4512 (2.4488)	
[2022-01-25 06:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][440/1251]	eta 0:30:11 lr 0.000113	time 1.7984 (2.2331)	loss 3.5390 (3.1198)	grad_norm 2.6032 (2.4511)	
[2022-01-25 06:53:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][450/1251]	eta 0:29:47 lr 0.000113	time 2.0910 (2.2312)	loss 3.5698 (3.1243)	grad_norm 2.3209 (2.4528)	
[2022-01-25 06:53:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][460/1251]	eta 0:29:24 lr 0.000113	time 2.8128 (2.2306)	loss 2.2157 (3.1218)	grad_norm 2.3639 (2.4510)	
[2022-01-25 06:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][470/1251]	eta 0:29:01 lr 0.000113	time 2.6470 (2.2303)	loss 3.1141 (3.1202)	grad_norm 2.1052 (2.4503)	
[2022-01-25 06:54:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][480/1251]	eta 0:28:41 lr 0.000113	time 2.2181 (2.2322)	loss 3.1318 (3.1209)	grad_norm 2.2034 (2.4490)	
[2022-01-25 06:54:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][490/1251]	eta 0:28:19 lr 0.000113	time 2.0573 (2.2330)	loss 2.3635 (3.1220)	grad_norm 2.1861 (2.4479)	
[2022-01-25 06:55:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][500/1251]	eta 0:27:56 lr 0.000113	time 2.4904 (2.2321)	loss 3.0635 (3.1206)	grad_norm 2.3141 (2.4510)	
[2022-01-25 06:55:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][510/1251]	eta 0:27:36 lr 0.000113	time 3.2473 (2.2349)	loss 2.3460 (3.1196)	grad_norm 2.4380 (2.4551)	
[2022-01-25 06:55:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][520/1251]	eta 0:27:10 lr 0.000113	time 1.7211 (2.2311)	loss 3.5470 (3.1221)	grad_norm 3.2367 (2.4589)	
[2022-01-25 06:56:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][530/1251]	eta 0:26:45 lr 0.000113	time 1.8358 (2.2262)	loss 2.1295 (3.1222)	grad_norm 2.4938 (2.4594)	
[2022-01-25 06:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][540/1251]	eta 0:26:21 lr 0.000113	time 2.1864 (2.2246)	loss 3.4396 (3.1232)	grad_norm 2.1013 (2.4634)	
[2022-01-25 06:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][550/1251]	eta 0:25:59 lr 0.000112	time 3.1889 (2.2246)	loss 2.6964 (3.1211)	grad_norm 2.2118 (2.4623)	
[2022-01-25 06:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][560/1251]	eta 0:25:35 lr 0.000112	time 2.1436 (2.2224)	loss 2.8751 (3.1215)	grad_norm 2.5031 (2.4615)	
[2022-01-25 06:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][570/1251]	eta 0:25:13 lr 0.000112	time 1.9357 (2.2218)	loss 3.2306 (3.1227)	grad_norm 2.5652 (2.4628)	
[2022-01-25 06:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][580/1251]	eta 0:24:51 lr 0.000112	time 3.1770 (2.2227)	loss 3.0873 (3.1266)	grad_norm 2.5884 (2.4650)	
[2022-01-25 06:58:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][590/1251]	eta 0:24:28 lr 0.000112	time 2.3702 (2.2221)	loss 3.7102 (3.1304)	grad_norm 2.5472 (2.4661)	
[2022-01-25 06:58:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][600/1251]	eta 0:24:05 lr 0.000112	time 2.1902 (2.2212)	loss 3.6671 (3.1325)	grad_norm 2.2747 (2.4662)	
[2022-01-25 06:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][610/1251]	eta 0:23:43 lr 0.000112	time 2.8178 (2.2208)	loss 2.5481 (3.1316)	grad_norm 2.4990 (2.4670)	
[2022-01-25 06:59:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][620/1251]	eta 0:23:18 lr 0.000112	time 1.5789 (2.2166)	loss 3.1934 (3.1371)	grad_norm 2.3382 (2.4652)	
[2022-01-25 06:59:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][630/1251]	eta 0:22:56 lr 0.000112	time 2.2665 (2.2161)	loss 3.6274 (3.1361)	grad_norm 2.8988 (2.4665)	
[2022-01-25 07:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][640/1251]	eta 0:22:32 lr 0.000112	time 2.1692 (2.2138)	loss 2.1817 (3.1349)	grad_norm 2.5035 (2.4644)	
[2022-01-25 07:00:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][650/1251]	eta 0:22:10 lr 0.000112	time 2.9103 (2.2142)	loss 3.2513 (3.1326)	grad_norm 2.5059 (2.4620)	
[2022-01-25 07:01:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][660/1251]	eta 0:21:48 lr 0.000112	time 1.8498 (2.2148)	loss 2.6459 (3.1331)	grad_norm 2.8311 (2.4612)	
[2022-01-25 07:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][670/1251]	eta 0:21:26 lr 0.000112	time 2.3950 (2.2143)	loss 3.2282 (3.1324)	grad_norm 2.5961 (2.4623)	
[2022-01-25 07:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][680/1251]	eta 0:21:04 lr 0.000112	time 2.2726 (2.2139)	loss 2.6286 (3.1320)	grad_norm 2.7223 (2.4626)	
[2022-01-25 07:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][690/1251]	eta 0:20:42 lr 0.000112	time 1.6700 (2.2146)	loss 3.2561 (3.1294)	grad_norm 2.3285 (2.4642)	
[2022-01-25 07:02:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][700/1251]	eta 0:20:20 lr 0.000112	time 1.6654 (2.2154)	loss 3.6608 (3.1304)	grad_norm 2.5325 (2.4629)	
[2022-01-25 07:02:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][710/1251]	eta 0:19:58 lr 0.000112	time 3.1459 (2.2159)	loss 2.1290 (3.1307)	grad_norm 2.5769 (2.4671)	
[2022-01-25 07:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][720/1251]	eta 0:19:36 lr 0.000112	time 2.4188 (2.2149)	loss 1.9125 (3.1283)	grad_norm 2.1422 (2.4671)	
[2022-01-25 07:03:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][730/1251]	eta 0:19:13 lr 0.000112	time 1.5864 (2.2147)	loss 2.4788 (3.1296)	grad_norm 2.6177 (2.4680)	
[2022-01-25 07:03:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][740/1251]	eta 0:18:52 lr 0.000112	time 2.0717 (2.2161)	loss 3.8686 (3.1274)	grad_norm 2.5352 (2.4687)	
[2022-01-25 07:04:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][750/1251]	eta 0:18:30 lr 0.000112	time 2.8116 (2.2171)	loss 3.3045 (3.1279)	grad_norm 2.3012 (2.4698)	
[2022-01-25 07:04:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][760/1251]	eta 0:18:07 lr 0.000112	time 2.1154 (2.2148)	loss 3.9515 (3.1265)	grad_norm 2.3922 (2.4678)	
[2022-01-25 07:05:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][770/1251]	eta 0:17:45 lr 0.000112	time 1.7935 (2.2145)	loss 3.4453 (3.1289)	grad_norm 2.3183 (2.4672)	
[2022-01-25 07:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][780/1251]	eta 0:17:22 lr 0.000112	time 1.7881 (2.2140)	loss 3.0239 (3.1292)	grad_norm 2.1490 (2.4681)	
[2022-01-25 07:05:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][790/1251]	eta 0:17:00 lr 0.000112	time 2.2488 (2.2139)	loss 2.2552 (3.1298)	grad_norm 2.1178 (2.4677)	
[2022-01-25 07:06:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][800/1251]	eta 0:16:38 lr 0.000112	time 2.8203 (2.2149)	loss 3.6425 (3.1317)	grad_norm 2.6369 (2.4679)	
[2022-01-25 07:06:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][810/1251]	eta 0:16:16 lr 0.000112	time 1.5709 (2.2145)	loss 3.4493 (3.1337)	grad_norm 2.5447 (2.4685)	
[2022-01-25 07:06:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][820/1251]	eta 0:15:53 lr 0.000112	time 1.9159 (2.2122)	loss 3.7591 (3.1317)	grad_norm 3.0828 (2.4694)	
[2022-01-25 07:07:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][830/1251]	eta 0:15:30 lr 0.000112	time 1.5743 (2.2105)	loss 3.5831 (3.1319)	grad_norm 2.2226 (2.4692)	
[2022-01-25 07:07:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][840/1251]	eta 0:15:08 lr 0.000112	time 2.3327 (2.2107)	loss 2.3237 (3.1294)	grad_norm 2.9877 (2.4702)	
[2022-01-25 07:07:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][850/1251]	eta 0:14:46 lr 0.000112	time 1.9065 (2.2109)	loss 3.5124 (3.1296)	grad_norm 2.4970 (2.4682)	
[2022-01-25 07:08:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][860/1251]	eta 0:14:24 lr 0.000112	time 2.2361 (2.2120)	loss 3.6221 (3.1319)	grad_norm 3.0555 (2.4716)	
[2022-01-25 07:08:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][870/1251]	eta 0:14:03 lr 0.000112	time 1.7842 (2.2131)	loss 2.4633 (3.1324)	grad_norm 2.2036 (2.4700)	
[2022-01-25 07:09:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][880/1251]	eta 0:13:42 lr 0.000112	time 2.5782 (2.2163)	loss 3.9955 (3.1321)	grad_norm 2.5120 (2.4704)	
[2022-01-25 07:09:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][890/1251]	eta 0:13:19 lr 0.000112	time 1.9155 (2.2145)	loss 2.3562 (3.1327)	grad_norm 2.0164 (2.4701)	
[2022-01-25 07:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][900/1251]	eta 0:12:56 lr 0.000112	time 1.8488 (2.2110)	loss 2.0696 (3.1330)	grad_norm 2.1620 (2.4687)	
[2022-01-25 07:10:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][910/1251]	eta 0:12:33 lr 0.000112	time 2.3109 (2.2090)	loss 3.2284 (3.1336)	grad_norm 2.3210 (2.4665)	
[2022-01-25 07:10:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][920/1251]	eta 0:12:10 lr 0.000112	time 1.8986 (2.2077)	loss 3.4641 (3.1326)	grad_norm 2.4253 (2.4651)	
[2022-01-25 07:10:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][930/1251]	eta 0:11:48 lr 0.000112	time 2.2785 (2.2064)	loss 3.8335 (3.1327)	grad_norm 2.5475 (2.4638)	
[2022-01-25 07:11:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][940/1251]	eta 0:11:26 lr 0.000111	time 1.9083 (2.2061)	loss 3.0090 (3.1307)	grad_norm 2.2860 (2.4745)	
[2022-01-25 07:11:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][950/1251]	eta 0:11:04 lr 0.000111	time 2.4661 (2.2060)	loss 3.7606 (3.1349)	grad_norm 2.3621 (2.4742)	
[2022-01-25 07:11:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][960/1251]	eta 0:10:42 lr 0.000111	time 1.8504 (2.2069)	loss 2.8915 (3.1345)	grad_norm 2.1622 (2.4740)	
[2022-01-25 07:12:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][970/1251]	eta 0:10:20 lr 0.000111	time 1.6437 (2.2069)	loss 3.7593 (3.1334)	grad_norm 3.4222 (2.4740)	
[2022-01-25 07:12:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][980/1251]	eta 0:09:58 lr 0.000111	time 2.5122 (2.2077)	loss 3.6189 (3.1338)	grad_norm 2.2324 (2.4721)	
[2022-01-25 07:13:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][990/1251]	eta 0:09:36 lr 0.000111	time 3.0335 (2.2098)	loss 3.7050 (3.1361)	grad_norm 2.5680 (2.4717)	
[2022-01-25 07:13:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1000/1251]	eta 0:09:14 lr 0.000111	time 1.5018 (2.2102)	loss 2.9765 (3.1359)	grad_norm 1.9743 (2.4702)	
[2022-01-25 07:13:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1010/1251]	eta 0:08:52 lr 0.000111	time 1.9215 (2.2103)	loss 3.0327 (3.1348)	grad_norm 2.1981 (2.4683)	
[2022-01-25 07:14:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1020/1251]	eta 0:08:30 lr 0.000111	time 2.8462 (2.2101)	loss 3.4551 (3.1361)	grad_norm 2.3953 (2.4670)	
[2022-01-25 07:14:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1030/1251]	eta 0:08:08 lr 0.000111	time 1.8869 (2.2097)	loss 2.5160 (3.1332)	grad_norm 2.5775 (2.4672)	
[2022-01-25 07:15:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1040/1251]	eta 0:07:46 lr 0.000111	time 1.5869 (2.2123)	loss 3.3747 (3.1349)	grad_norm 3.1440 (2.4663)	
[2022-01-25 07:15:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1050/1251]	eta 0:07:24 lr 0.000111	time 1.7571 (2.2118)	loss 2.8282 (3.1361)	grad_norm 2.1441 (2.4647)	
[2022-01-25 07:15:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1060/1251]	eta 0:07:02 lr 0.000111	time 2.1635 (2.2105)	loss 2.4814 (3.1340)	grad_norm 2.3983 (2.4636)	
[2022-01-25 07:16:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1070/1251]	eta 0:06:39 lr 0.000111	time 1.9039 (2.2083)	loss 1.9545 (3.1349)	grad_norm 2.0874 (2.4623)	
[2022-01-25 07:16:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1080/1251]	eta 0:06:17 lr 0.000111	time 1.8194 (2.2075)	loss 3.3184 (3.1318)	grad_norm 2.5123 (2.4621)	
[2022-01-25 07:16:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1090/1251]	eta 0:05:55 lr 0.000111	time 2.4576 (2.2098)	loss 3.4345 (3.1326)	grad_norm 2.7825 (2.4620)	
[2022-01-25 07:17:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1100/1251]	eta 0:05:33 lr 0.000111	time 1.9976 (2.2102)	loss 3.0036 (3.1334)	grad_norm 2.1739 (2.4624)	
[2022-01-25 07:17:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1110/1251]	eta 0:05:11 lr 0.000111	time 2.6341 (2.2112)	loss 3.5265 (3.1346)	grad_norm 2.1467 (2.4623)	
[2022-01-25 07:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1120/1251]	eta 0:04:49 lr 0.000111	time 1.8271 (2.2101)	loss 3.5093 (3.1350)	grad_norm 2.7659 (2.4626)	
[2022-01-25 07:18:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1130/1251]	eta 0:04:27 lr 0.000111	time 2.2349 (2.2097)	loss 2.5516 (3.1354)	grad_norm 2.1512 (2.4619)	
[2022-01-25 07:18:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1140/1251]	eta 0:04:05 lr 0.000111	time 1.5991 (2.2074)	loss 3.1670 (3.1356)	grad_norm 2.3034 (2.4630)	
[2022-01-25 07:18:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1150/1251]	eta 0:03:42 lr 0.000111	time 2.2153 (2.2075)	loss 2.3985 (3.1344)	grad_norm 2.5705 (2.4632)	
[2022-01-25 07:19:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1160/1251]	eta 0:03:20 lr 0.000111	time 1.9041 (2.2077)	loss 3.1339 (3.1336)	grad_norm 2.1481 (2.4632)	
[2022-01-25 07:19:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1170/1251]	eta 0:02:58 lr 0.000111	time 2.9001 (2.2095)	loss 3.3363 (3.1343)	grad_norm 2.3590 (2.4626)	
[2022-01-25 07:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1180/1251]	eta 0:02:36 lr 0.000111	time 2.3949 (2.2100)	loss 3.5452 (3.1347)	grad_norm 2.3223 (2.4620)	
[2022-01-25 07:20:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1190/1251]	eta 0:02:14 lr 0.000111	time 1.8979 (2.2094)	loss 3.3002 (3.1350)	grad_norm 2.3814 (2.4622)	
[2022-01-25 07:20:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1200/1251]	eta 0:01:52 lr 0.000111	time 1.8886 (2.2083)	loss 3.4629 (3.1354)	grad_norm 2.1037 (2.4616)	
[2022-01-25 07:21:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1210/1251]	eta 0:01:30 lr 0.000111	time 2.2058 (2.2086)	loss 3.3425 (3.1369)	grad_norm 2.2219 (2.4613)	
[2022-01-25 07:21:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1220/1251]	eta 0:01:08 lr 0.000111	time 1.7866 (2.2089)	loss 3.2994 (3.1357)	grad_norm 2.6042 (2.4629)	
[2022-01-25 07:21:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1230/1251]	eta 0:00:46 lr 0.000111	time 1.6361 (2.2077)	loss 3.3614 (3.1364)	grad_norm 2.4023 (2.4622)	
[2022-01-25 07:22:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1240/1251]	eta 0:00:24 lr 0.000111	time 1.4953 (2.2061)	loss 3.4240 (3.1377)	grad_norm 2.4158 (2.4618)	
[2022-01-25 07:22:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [237/300][1250/1251]	eta 0:00:02 lr 0.000111	time 1.2066 (2.2003)	loss 3.2838 (3.1382)	grad_norm 2.3517 (2.4607)	
[2022-01-25 07:22:30 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 237 training takes 0:45:52
[2022-01-25 07:22:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.246 (18.246)	Loss 0.8670 (0.8670)	Acc@1 78.613 (78.613)	Acc@5 95.410 (95.410)	
[2022-01-25 07:23:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.552 (3.566)	Loss 0.8543 (0.8529)	Acc@1 79.492 (79.750)	Acc@5 95.312 (95.091)	
[2022-01-25 07:23:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.952 (2.744)	Loss 0.8141 (0.8586)	Acc@1 81.543 (79.669)	Acc@5 95.312 (95.066)	
[2022-01-25 07:23:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.889 (2.296)	Loss 0.8438 (0.8632)	Acc@1 80.078 (79.700)	Acc@5 95.215 (95.010)	
[2022-01-25 07:24:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.073 (2.198)	Loss 0.9800 (0.8650)	Acc@1 77.539 (79.597)	Acc@5 94.043 (95.022)	
[2022-01-25 07:24:08 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.768 Acc@5 95.098
[2022-01-25 07:24:08 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.8%
[2022-01-25 07:24:08 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.82%
[2022-01-25 07:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][0/1251]	eta 7:36:30 lr 0.000111	time 21.8949 (21.8949)	loss 3.4373 (3.4373)	grad_norm 2.4441 (2.4441)	
[2022-01-25 07:24:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][10/1251]	eta 1:22:05 lr 0.000111	time 2.5082 (3.9690)	loss 2.1429 (3.1066)	grad_norm 2.1792 (2.3482)	
[2022-01-25 07:25:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][20/1251]	eta 1:04:14 lr 0.000111	time 1.4547 (3.1308)	loss 2.9025 (3.2156)	grad_norm 2.5066 (2.4801)	
[2022-01-25 07:25:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][30/1251]	eta 0:56:59 lr 0.000111	time 1.6495 (2.8007)	loss 3.0443 (3.1977)	grad_norm 2.5545 (2.4472)	
[2022-01-25 07:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][40/1251]	eta 0:54:01 lr 0.000111	time 3.5953 (2.6763)	loss 3.5445 (3.2420)	grad_norm 2.3193 (2.4319)	
[2022-01-25 07:26:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][50/1251]	eta 0:52:27 lr 0.000111	time 2.8543 (2.6205)	loss 3.8680 (3.2230)	grad_norm 2.9045 (2.4233)	
[2022-01-25 07:26:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][60/1251]	eta 0:50:27 lr 0.000111	time 2.1526 (2.5420)	loss 3.3819 (3.2159)	grad_norm 2.3844 (2.4362)	
[2022-01-25 07:27:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][70/1251]	eta 0:48:56 lr 0.000111	time 1.8295 (2.4868)	loss 3.4661 (3.2159)	grad_norm 2.2607 (2.4366)	
[2022-01-25 07:27:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][80/1251]	eta 0:48:04 lr 0.000111	time 3.5848 (2.4637)	loss 2.8513 (3.2119)	grad_norm 2.2396 (2.4346)	
[2022-01-25 07:27:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][90/1251]	eta 0:47:11 lr 0.000110	time 1.8252 (2.4385)	loss 3.3485 (3.2000)	grad_norm 2.1680 (2.4400)	
[2022-01-25 07:28:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][100/1251]	eta 0:46:06 lr 0.000110	time 1.7512 (2.4032)	loss 3.2676 (3.2032)	grad_norm 2.3195 (2.4564)	
[2022-01-25 07:28:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][110/1251]	eta 0:44:58 lr 0.000110	time 1.5438 (2.3655)	loss 2.5625 (3.1782)	grad_norm 2.6664 (2.4545)	
[2022-01-25 07:28:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][120/1251]	eta 0:44:43 lr 0.000110	time 2.8641 (2.3730)	loss 3.6620 (3.1666)	grad_norm 2.8548 (2.4685)	
[2022-01-25 07:29:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][130/1251]	eta 0:44:17 lr 0.000110	time 1.8460 (2.3705)	loss 3.2544 (3.1672)	grad_norm 3.5742 (2.4751)	
[2022-01-25 07:29:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][140/1251]	eta 0:43:46 lr 0.000110	time 2.4969 (2.3641)	loss 3.3491 (3.1657)	grad_norm 2.5659 (2.4666)	
[2022-01-25 07:30:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][150/1251]	eta 0:43:09 lr 0.000110	time 1.5725 (2.3521)	loss 2.2694 (3.1638)	grad_norm 2.3716 (2.4653)	
[2022-01-25 07:30:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][160/1251]	eta 0:42:33 lr 0.000110	time 2.8967 (2.3406)	loss 2.9668 (3.1809)	grad_norm 2.5788 (2.4669)	
[2022-01-25 07:30:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][170/1251]	eta 0:41:40 lr 0.000110	time 1.8948 (2.3131)	loss 3.1870 (3.1767)	grad_norm 2.6234 (2.4695)	
[2022-01-25 07:31:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][180/1251]	eta 0:40:57 lr 0.000110	time 1.7896 (2.2944)	loss 3.2149 (3.1826)	grad_norm 2.7019 (2.4740)	
[2022-01-25 07:31:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][190/1251]	eta 0:40:22 lr 0.000110	time 1.8736 (2.2829)	loss 3.2390 (3.1851)	grad_norm 2.3780 (2.4668)	
[2022-01-25 07:31:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][200/1251]	eta 0:40:00 lr 0.000110	time 2.5284 (2.2841)	loss 3.3776 (3.1780)	grad_norm 2.2667 (2.4617)	
[2022-01-25 07:32:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][210/1251]	eta 0:39:45 lr 0.000110	time 2.8106 (2.2916)	loss 3.4969 (3.1861)	grad_norm 2.3205 (2.4661)	
[2022-01-25 07:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][220/1251]	eta 0:39:22 lr 0.000110	time 1.5755 (2.2917)	loss 2.9200 (3.1875)	grad_norm 2.3591 (2.4650)	
[2022-01-25 07:32:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][230/1251]	eta 0:38:54 lr 0.000110	time 1.9865 (2.2864)	loss 2.8115 (3.1806)	grad_norm 2.4475 (2.4574)	
[2022-01-25 07:33:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][240/1251]	eta 0:38:27 lr 0.000110	time 1.9043 (2.2827)	loss 3.2409 (3.1797)	grad_norm 2.7564 (2.4684)	
[2022-01-25 07:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][250/1251]	eta 0:37:59 lr 0.000110	time 2.1509 (2.2770)	loss 2.2383 (3.1727)	grad_norm 2.6408 (2.4791)	
[2022-01-25 07:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][260/1251]	eta 0:37:28 lr 0.000110	time 1.8400 (2.2693)	loss 2.6961 (3.1704)	grad_norm 3.2505 (2.4919)	
[2022-01-25 07:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][270/1251]	eta 0:37:03 lr 0.000110	time 2.5040 (2.2669)	loss 2.0576 (3.1547)	grad_norm 2.2406 (2.4914)	
[2022-01-25 07:34:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][280/1251]	eta 0:36:35 lr 0.000110	time 1.9981 (2.2606)	loss 3.7511 (3.1585)	grad_norm 2.5447 (2.5267)	
[2022-01-25 07:35:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][290/1251]	eta 0:36:09 lr 0.000110	time 2.6007 (2.2580)	loss 3.3767 (3.1609)	grad_norm 2.6639 (2.5318)	
[2022-01-25 07:35:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][300/1251]	eta 0:35:46 lr 0.000110	time 1.8793 (2.2573)	loss 3.4937 (3.1578)	grad_norm 2.6356 (2.5274)	
[2022-01-25 07:35:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][310/1251]	eta 0:35:22 lr 0.000110	time 2.4472 (2.2561)	loss 2.9092 (3.1634)	grad_norm 2.3944 (2.5240)	
[2022-01-25 07:36:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][320/1251]	eta 0:35:03 lr 0.000110	time 2.3189 (2.2591)	loss 2.4552 (3.1634)	grad_norm 2.1944 (2.5203)	
[2022-01-25 07:36:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][330/1251]	eta 0:34:39 lr 0.000110	time 2.8711 (2.2583)	loss 3.7286 (3.1699)	grad_norm 2.6799 (2.5174)	
[2022-01-25 07:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][340/1251]	eta 0:34:12 lr 0.000110	time 1.6365 (2.2525)	loss 3.9431 (3.1621)	grad_norm 2.5914 (2.5154)	
[2022-01-25 07:37:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][350/1251]	eta 0:33:41 lr 0.000110	time 1.9100 (2.2432)	loss 3.7135 (3.1682)	grad_norm 2.0625 (2.5145)	
[2022-01-25 07:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][360/1251]	eta 0:33:14 lr 0.000110	time 2.4662 (2.2383)	loss 2.6993 (3.1701)	grad_norm 2.3679 (2.5156)	
[2022-01-25 07:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][370/1251]	eta 0:32:50 lr 0.000110	time 2.5492 (2.2367)	loss 2.2468 (3.1703)	grad_norm 2.7227 (2.5190)	
[2022-01-25 07:38:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][380/1251]	eta 0:32:27 lr 0.000110	time 1.6361 (2.2357)	loss 4.1723 (3.1757)	grad_norm 2.4463 (2.5215)	
[2022-01-25 07:38:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][390/1251]	eta 0:32:03 lr 0.000110	time 2.3049 (2.2346)	loss 3.7814 (3.1758)	grad_norm 2.6645 (2.5267)	
[2022-01-25 07:39:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][400/1251]	eta 0:31:41 lr 0.000110	time 2.4138 (2.2347)	loss 3.4246 (3.1822)	grad_norm 2.7218 (2.5333)	
[2022-01-25 07:39:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][410/1251]	eta 0:31:19 lr 0.000110	time 2.1127 (2.2347)	loss 2.4926 (3.1708)	grad_norm 1.9329 (2.5351)	
[2022-01-25 07:39:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][420/1251]	eta 0:30:58 lr 0.000110	time 2.1458 (2.2362)	loss 2.3156 (3.1676)	grad_norm 2.3750 (2.5341)	
[2022-01-25 07:40:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][430/1251]	eta 0:30:35 lr 0.000110	time 2.2834 (2.2359)	loss 2.7004 (3.1663)	grad_norm 2.4061 (2.5313)	
[2022-01-25 07:40:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][440/1251]	eta 0:30:11 lr 0.000110	time 2.1612 (2.2333)	loss 2.6533 (3.1647)	grad_norm 2.6618 (2.5308)	
[2022-01-25 07:40:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][450/1251]	eta 0:29:46 lr 0.000110	time 2.0729 (2.2301)	loss 3.2728 (3.1673)	grad_norm 2.2616 (2.5266)	
[2022-01-25 07:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][460/1251]	eta 0:29:23 lr 0.000110	time 2.8911 (2.2290)	loss 3.6758 (3.1637)	grad_norm 2.2236 (2.5268)	
[2022-01-25 07:41:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][470/1251]	eta 0:29:02 lr 0.000110	time 2.1179 (2.2305)	loss 2.9495 (3.1636)	grad_norm 3.0642 (2.5292)	
[2022-01-25 07:42:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][480/1251]	eta 0:28:40 lr 0.000110	time 2.6092 (2.2313)	loss 3.4351 (3.1620)	grad_norm 2.3825 (2.5313)	
[2022-01-25 07:42:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][490/1251]	eta 0:28:17 lr 0.000109	time 2.0132 (2.2306)	loss 2.9365 (3.1503)	grad_norm 4.6021 (2.5347)	
[2022-01-25 07:42:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][500/1251]	eta 0:27:55 lr 0.000109	time 2.6232 (2.2312)	loss 3.2053 (3.1467)	grad_norm 2.3154 (2.5361)	
[2022-01-25 07:43:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][510/1251]	eta 0:27:28 lr 0.000109	time 1.9184 (2.2249)	loss 2.9926 (3.1478)	grad_norm 2.6789 (2.5383)	
[2022-01-25 07:43:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][520/1251]	eta 0:27:02 lr 0.000109	time 1.9157 (2.2199)	loss 3.6973 (3.1499)	grad_norm 2.3549 (2.5407)	
[2022-01-25 07:43:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][530/1251]	eta 0:26:38 lr 0.000109	time 1.8811 (2.2174)	loss 3.6576 (3.1519)	grad_norm 3.5533 (2.5427)	
[2022-01-25 07:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][540/1251]	eta 0:26:15 lr 0.000109	time 2.4783 (2.2155)	loss 3.5597 (3.1512)	grad_norm 2.1289 (2.5418)	
[2022-01-25 07:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][550/1251]	eta 0:25:52 lr 0.000109	time 2.6000 (2.2145)	loss 3.1386 (3.1512)	grad_norm 2.3545 (2.5400)	
[2022-01-25 07:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][560/1251]	eta 0:25:29 lr 0.000109	time 1.7159 (2.2128)	loss 3.6901 (3.1505)	grad_norm 2.5304 (2.5401)	
[2022-01-25 07:45:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][570/1251]	eta 0:25:07 lr 0.000109	time 2.0522 (2.2143)	loss 3.0204 (3.1498)	grad_norm 2.5473 (2.5417)	
[2022-01-25 07:45:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][580/1251]	eta 0:24:46 lr 0.000109	time 1.9634 (2.2158)	loss 3.2370 (3.1478)	grad_norm 2.5460 (2.5418)	
[2022-01-25 07:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][590/1251]	eta 0:24:24 lr 0.000109	time 2.5558 (2.2152)	loss 2.8109 (3.1509)	grad_norm 2.9618 (2.5428)	
[2022-01-25 07:46:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][600/1251]	eta 0:24:03 lr 0.000109	time 2.8510 (2.2167)	loss 2.3434 (3.1498)	grad_norm 2.5985 (2.5412)	
[2022-01-25 07:46:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][610/1251]	eta 0:23:41 lr 0.000109	time 1.8636 (2.2176)	loss 4.0594 (3.1503)	grad_norm 2.3196 (2.5412)	
[2022-01-25 07:47:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][620/1251]	eta 0:23:18 lr 0.000109	time 2.4577 (2.2171)	loss 3.6207 (3.1529)	grad_norm 2.3577 (2.5387)	
[2022-01-25 07:47:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][630/1251]	eta 0:22:55 lr 0.000109	time 2.0662 (2.2143)	loss 2.3397 (3.1550)	grad_norm 2.0471 (2.5368)	
[2022-01-25 07:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][640/1251]	eta 0:22:31 lr 0.000109	time 1.9191 (2.2123)	loss 3.0656 (3.1533)	grad_norm 2.2841 (2.5332)	
[2022-01-25 07:48:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][650/1251]	eta 0:22:09 lr 0.000109	time 1.8696 (2.2114)	loss 2.7514 (3.1548)	grad_norm 2.1928 (2.5324)	
[2022-01-25 07:48:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][660/1251]	eta 0:21:47 lr 0.000109	time 3.1573 (2.2131)	loss 2.2156 (3.1512)	grad_norm 2.1982 (2.5296)	
[2022-01-25 07:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][670/1251]	eta 0:21:25 lr 0.000109	time 2.1112 (2.2125)	loss 2.7960 (3.1509)	grad_norm 2.0926 (2.5269)	
[2022-01-25 07:49:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][680/1251]	eta 0:21:03 lr 0.000109	time 2.1218 (2.2128)	loss 2.2922 (3.1480)	grad_norm 2.2941 (2.5249)	
[2022-01-25 07:49:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][690/1251]	eta 0:20:41 lr 0.000109	time 1.7151 (2.2128)	loss 3.1983 (3.1468)	grad_norm 2.1519 (2.5216)	
[2022-01-25 07:50:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][700/1251]	eta 0:20:19 lr 0.000109	time 2.1901 (2.2135)	loss 3.2511 (3.1472)	grad_norm 2.2311 (2.5186)	
[2022-01-25 07:50:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][710/1251]	eta 0:19:58 lr 0.000109	time 2.5024 (2.2157)	loss 3.4699 (3.1501)	grad_norm 2.5762 (2.5184)	
[2022-01-25 07:50:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][720/1251]	eta 0:19:35 lr 0.000109	time 2.5656 (2.2139)	loss 3.4989 (3.1510)	grad_norm 3.7551 (2.5183)	
[2022-01-25 07:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][730/1251]	eta 0:19:11 lr 0.000109	time 1.8575 (2.2108)	loss 3.3748 (3.1547)	grad_norm 2.2673 (2.5165)	
[2022-01-25 07:51:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][740/1251]	eta 0:18:48 lr 0.000109	time 2.0356 (2.2091)	loss 3.3821 (3.1503)	grad_norm 2.1395 (2.5147)	
[2022-01-25 07:51:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][750/1251]	eta 0:18:26 lr 0.000109	time 2.3679 (2.2080)	loss 2.7996 (3.1511)	grad_norm 2.4331 (2.5147)	
[2022-01-25 07:52:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][760/1251]	eta 0:18:03 lr 0.000109	time 2.1967 (2.2075)	loss 3.3468 (3.1499)	grad_norm 2.2558 (2.5161)	
[2022-01-25 07:52:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][770/1251]	eta 0:17:42 lr 0.000109	time 2.3230 (2.2080)	loss 3.5087 (3.1506)	grad_norm 2.6242 (2.5162)	
[2022-01-25 07:52:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][780/1251]	eta 0:17:19 lr 0.000109	time 1.8501 (2.2066)	loss 3.7491 (3.1528)	grad_norm 2.2082 (2.5182)	
[2022-01-25 07:53:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][790/1251]	eta 0:16:57 lr 0.000109	time 2.4654 (2.2075)	loss 3.2477 (3.1559)	grad_norm 2.2957 (2.5217)	
[2022-01-25 07:53:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][800/1251]	eta 0:16:36 lr 0.000109	time 2.6019 (2.2085)	loss 3.3698 (3.1541)	grad_norm 2.4342 (2.5256)	
[2022-01-25 07:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][810/1251]	eta 0:16:13 lr 0.000109	time 2.2270 (2.2085)	loss 2.3728 (3.1543)	grad_norm 2.4770 (2.5296)	
[2022-01-25 07:54:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][820/1251]	eta 0:15:51 lr 0.000109	time 1.9310 (2.2065)	loss 2.5572 (3.1540)	grad_norm 2.6842 (2.5331)	
[2022-01-25 07:54:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][830/1251]	eta 0:15:28 lr 0.000109	time 2.4586 (2.2062)	loss 2.4004 (3.1519)	grad_norm 2.5327 (2.5357)	
[2022-01-25 07:55:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][840/1251]	eta 0:15:06 lr 0.000109	time 1.8017 (2.2048)	loss 3.3875 (3.1543)	grad_norm 2.7157 (2.5360)	
[2022-01-25 07:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][850/1251]	eta 0:14:43 lr 0.000109	time 1.6700 (2.2029)	loss 3.3646 (3.1547)	grad_norm 3.2369 (2.5370)	
[2022-01-25 07:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][860/1251]	eta 0:14:21 lr 0.000109	time 1.6375 (2.2026)	loss 2.3284 (3.1530)	grad_norm 2.2798 (2.5379)	
[2022-01-25 07:56:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][870/1251]	eta 0:13:59 lr 0.000109	time 2.2717 (2.2041)	loss 3.0757 (3.1521)	grad_norm 2.1373 (2.5361)	
[2022-01-25 07:56:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][880/1251]	eta 0:13:37 lr 0.000109	time 2.3074 (2.2047)	loss 3.6232 (3.1494)	grad_norm 2.4779 (2.5350)	
[2022-01-25 07:56:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][890/1251]	eta 0:13:16 lr 0.000108	time 1.9241 (2.2057)	loss 3.3159 (3.1499)	grad_norm 2.2779 (2.5332)	
[2022-01-25 07:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][900/1251]	eta 0:12:54 lr 0.000108	time 1.8278 (2.2057)	loss 3.1676 (3.1522)	grad_norm 2.2621 (2.5319)	
[2022-01-25 07:57:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][910/1251]	eta 0:12:32 lr 0.000108	time 2.2867 (2.2053)	loss 3.2979 (3.1533)	grad_norm 2.4544 (2.5311)	
[2022-01-25 07:57:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][920/1251]	eta 0:12:09 lr 0.000108	time 1.6568 (2.2031)	loss 3.1962 (3.1535)	grad_norm 2.1641 (2.5295)	
[2022-01-25 07:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][930/1251]	eta 0:11:46 lr 0.000108	time 1.9814 (2.2016)	loss 3.2256 (3.1540)	grad_norm 2.4349 (2.5276)	
[2022-01-25 07:58:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][940/1251]	eta 0:11:24 lr 0.000108	time 2.6065 (2.2006)	loss 2.9088 (3.1538)	grad_norm 2.2800 (2.5262)	
[2022-01-25 07:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][950/1251]	eta 0:11:02 lr 0.000108	time 2.2277 (2.2006)	loss 3.3271 (3.1544)	grad_norm 2.1956 (2.5249)	
[2022-01-25 07:59:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][960/1251]	eta 0:10:40 lr 0.000108	time 1.5242 (2.1999)	loss 3.4304 (3.1570)	grad_norm 2.3490 (2.5228)	
[2022-01-25 07:59:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][970/1251]	eta 0:10:18 lr 0.000108	time 1.7990 (2.2002)	loss 3.3284 (3.1556)	grad_norm 2.4823 (2.5254)	
[2022-01-25 08:00:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][980/1251]	eta 0:09:56 lr 0.000108	time 1.6801 (2.1999)	loss 2.9173 (3.1574)	grad_norm 2.1516 (2.5240)	
[2022-01-25 08:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][990/1251]	eta 0:09:34 lr 0.000108	time 2.6384 (2.2003)	loss 3.1491 (3.1593)	grad_norm 2.6820 (2.5237)	
[2022-01-25 08:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1000/1251]	eta 0:09:12 lr 0.000108	time 1.7828 (2.2003)	loss 3.2795 (3.1568)	grad_norm 2.3689 (2.5219)	
[2022-01-25 08:01:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1010/1251]	eta 0:08:50 lr 0.000108	time 1.6659 (2.2013)	loss 3.2713 (3.1575)	grad_norm 2.6604 (2.5211)	
[2022-01-25 08:01:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1020/1251]	eta 0:08:28 lr 0.000108	time 1.7744 (2.2021)	loss 3.1480 (3.1594)	grad_norm 2.5525 (2.5200)	
[2022-01-25 08:01:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1030/1251]	eta 0:08:06 lr 0.000108	time 2.1621 (2.2022)	loss 2.8290 (3.1590)	grad_norm 2.4906 (2.5203)	
[2022-01-25 08:02:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1040/1251]	eta 0:07:44 lr 0.000108	time 1.5156 (2.2008)	loss 2.4957 (3.1583)	grad_norm 2.0647 (2.5214)	
[2022-01-25 08:02:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1050/1251]	eta 0:07:22 lr 0.000108	time 2.0060 (2.2020)	loss 3.7747 (3.1599)	grad_norm 2.2981 (2.5215)	
[2022-01-25 08:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1060/1251]	eta 0:07:00 lr 0.000108	time 2.4697 (2.2029)	loss 2.6761 (3.1589)	grad_norm 2.2613 (2.5220)	
[2022-01-25 08:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1070/1251]	eta 0:06:38 lr 0.000108	time 1.6199 (2.2014)	loss 3.3028 (3.1582)	grad_norm 3.0464 (2.5214)	
[2022-01-25 08:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1080/1251]	eta 0:06:16 lr 0.000108	time 1.8436 (2.1994)	loss 3.5483 (3.1610)	grad_norm 2.3026 (2.5209)	
[2022-01-25 08:04:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1090/1251]	eta 0:05:53 lr 0.000108	time 2.1795 (2.1987)	loss 2.8296 (3.1574)	grad_norm 2.5062 (2.5211)	
[2022-01-25 08:04:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1100/1251]	eta 0:05:31 lr 0.000108	time 1.8473 (2.1977)	loss 3.5372 (3.1590)	grad_norm 2.5373 (2.5208)	
[2022-01-25 08:04:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1110/1251]	eta 0:05:09 lr 0.000108	time 2.2417 (2.1981)	loss 3.5771 (3.1572)	grad_norm 2.9655 (2.5216)	
[2022-01-25 08:05:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1120/1251]	eta 0:04:47 lr 0.000108	time 1.8737 (2.1969)	loss 3.2258 (3.1580)	grad_norm 2.5198 (2.5203)	
[2022-01-25 08:05:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1130/1251]	eta 0:04:25 lr 0.000108	time 1.9905 (2.1972)	loss 3.2948 (3.1584)	grad_norm 2.4877 (2.5204)	
[2022-01-25 08:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1140/1251]	eta 0:04:03 lr 0.000108	time 2.6048 (2.1981)	loss 3.5182 (3.1571)	grad_norm 2.2997 (2.5193)	
[2022-01-25 08:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1150/1251]	eta 0:03:42 lr 0.000108	time 1.6231 (2.1986)	loss 3.4681 (3.1573)	grad_norm 2.3050 (2.5182)	
[2022-01-25 08:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1160/1251]	eta 0:03:20 lr 0.000108	time 1.5158 (2.1991)	loss 3.0572 (3.1590)	grad_norm 2.9515 (2.5180)	
[2022-01-25 08:07:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1170/1251]	eta 0:02:58 lr 0.000108	time 2.1052 (2.2002)	loss 2.3582 (3.1578)	grad_norm 2.5472 (2.5170)	
[2022-01-25 08:07:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1180/1251]	eta 0:02:36 lr 0.000108	time 1.7164 (2.1982)	loss 3.4632 (3.1568)	grad_norm 2.5508 (2.5166)	
[2022-01-25 08:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1190/1251]	eta 0:02:14 lr 0.000108	time 1.8644 (2.1968)	loss 3.7466 (3.1582)	grad_norm 2.4849 (2.5177)	
[2022-01-25 08:08:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1200/1251]	eta 0:01:51 lr 0.000108	time 1.5961 (2.1951)	loss 3.3933 (3.1580)	grad_norm 2.6268 (2.5179)	
[2022-01-25 08:08:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1210/1251]	eta 0:01:29 lr 0.000108	time 1.4835 (2.1948)	loss 3.1835 (3.1571)	grad_norm 2.2799 (2.5166)	
[2022-01-25 08:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1220/1251]	eta 0:01:08 lr 0.000108	time 1.8263 (2.1941)	loss 3.5609 (3.1554)	grad_norm 2.4743 (2.5172)	
[2022-01-25 08:09:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1230/1251]	eta 0:00:46 lr 0.000108	time 1.5314 (2.1937)	loss 3.2467 (3.1538)	grad_norm 2.1620 (2.5168)	
[2022-01-25 08:09:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1240/1251]	eta 0:00:24 lr 0.000108	time 1.6951 (2.1927)	loss 3.7489 (3.1535)	grad_norm 2.6824 (2.5156)	
[2022-01-25 08:09:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [238/300][1250/1251]	eta 0:00:02 lr 0.000108	time 1.1705 (2.1877)	loss 3.0972 (3.1541)	grad_norm 2.4639 (2.5154)	
[2022-01-25 08:09:45 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 238 training takes 0:45:37
[2022-01-25 08:10:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.434 (18.434)	Loss 0.9483 (0.9483)	Acc@1 79.199 (79.199)	Acc@5 93.066 (93.066)	
[2022-01-25 08:10:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.744 (3.538)	Loss 0.8801 (0.8743)	Acc@1 79.297 (79.643)	Acc@5 95.312 (94.709)	
[2022-01-25 08:10:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.866 (2.676)	Loss 0.8617 (0.8667)	Acc@1 79.883 (79.794)	Acc@5 94.922 (94.945)	
[2022-01-25 08:10:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.297 (2.364)	Loss 0.8502 (0.8575)	Acc@1 79.199 (79.921)	Acc@5 95.996 (95.171)	
[2022-01-25 08:11:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.626 (2.216)	Loss 0.8501 (0.8591)	Acc@1 80.176 (79.899)	Acc@5 95.605 (95.120)	
[2022-01-25 08:11:24 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.922 Acc@5 95.070
[2022-01-25 08:11:24 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.9%
[2022-01-25 08:11:24 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 79.92%
[2022-01-25 08:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][0/1251]	eta 7:20:57 lr 0.000108	time 21.1487 (21.1487)	loss 3.4380 (3.4380)	grad_norm 2.3685 (2.3685)	
[2022-01-25 08:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][10/1251]	eta 1:23:24 lr 0.000108	time 3.1903 (4.0326)	loss 3.4159 (3.0547)	grad_norm 2.3904 (2.4008)	
[2022-01-25 08:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][20/1251]	eta 1:04:03 lr 0.000108	time 1.8078 (3.1222)	loss 3.2039 (2.9961)	grad_norm 2.2445 (2.4382)	
[2022-01-25 08:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][30/1251]	eta 0:57:46 lr 0.000108	time 1.5196 (2.8394)	loss 2.4024 (2.9509)	grad_norm 2.4534 (2.4275)	
[2022-01-25 08:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][40/1251]	eta 0:54:40 lr 0.000108	time 3.8081 (2.7090)	loss 3.5361 (3.0147)	grad_norm 2.3878 (2.4201)	
[2022-01-25 08:13:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][50/1251]	eta 0:52:51 lr 0.000107	time 2.7374 (2.6410)	loss 3.4862 (3.0645)	grad_norm 2.2847 (2.4062)	
[2022-01-25 08:14:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][60/1251]	eta 0:50:37 lr 0.000107	time 1.2232 (2.5500)	loss 3.3882 (3.0551)	grad_norm 2.6038 (2.4283)	
[2022-01-25 08:14:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][70/1251]	eta 0:49:26 lr 0.000107	time 1.8715 (2.5119)	loss 2.6117 (3.0590)	grad_norm 2.1303 (2.4484)	
[2022-01-25 08:14:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][80/1251]	eta 0:48:39 lr 0.000107	time 3.3653 (2.4929)	loss 3.1766 (3.0448)	grad_norm 2.2857 (2.4396)	
[2022-01-25 08:15:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][90/1251]	eta 0:48:20 lr 0.000107	time 2.4642 (2.4980)	loss 3.0811 (3.0551)	grad_norm 2.7195 (2.4501)	
[2022-01-25 08:15:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][100/1251]	eta 0:47:21 lr 0.000107	time 1.8832 (2.4684)	loss 2.4017 (3.0630)	grad_norm 2.4789 (2.4496)	
[2022-01-25 08:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][110/1251]	eta 0:46:18 lr 0.000107	time 1.8156 (2.4348)	loss 2.1896 (3.0567)	grad_norm 2.3058 (2.4591)	
[2022-01-25 08:16:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][120/1251]	eta 0:45:19 lr 0.000107	time 2.5087 (2.4043)	loss 3.5781 (3.0754)	grad_norm 2.9436 (2.4729)	
[2022-01-25 08:16:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][130/1251]	eta 0:44:16 lr 0.000107	time 1.8941 (2.3693)	loss 3.1984 (3.0967)	grad_norm 2.4099 (2.4708)	
[2022-01-25 08:16:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][140/1251]	eta 0:43:29 lr 0.000107	time 1.9185 (2.3491)	loss 2.2385 (3.0973)	grad_norm 2.5440 (2.4759)	
[2022-01-25 08:17:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][150/1251]	eta 0:42:55 lr 0.000107	time 2.2180 (2.3393)	loss 3.4160 (3.1221)	grad_norm 2.4126 (2.4800)	
[2022-01-25 08:17:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][160/1251]	eta 0:42:35 lr 0.000107	time 2.9083 (2.3419)	loss 3.3625 (3.1303)	grad_norm 2.1777 (2.4744)	
[2022-01-25 08:18:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][170/1251]	eta 0:42:13 lr 0.000107	time 2.3956 (2.3440)	loss 3.2971 (3.1486)	grad_norm 2.5317 (2.4701)	
[2022-01-25 08:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][180/1251]	eta 0:41:43 lr 0.000107	time 2.1576 (2.3372)	loss 3.7718 (3.1452)	grad_norm 2.3428 (2.4768)	
[2022-01-25 08:18:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][190/1251]	eta 0:41:03 lr 0.000107	time 2.2061 (2.3218)	loss 2.3882 (3.1477)	grad_norm 2.5417 (2.4772)	
[2022-01-25 08:19:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][200/1251]	eta 0:40:30 lr 0.000107	time 2.1859 (2.3124)	loss 2.5257 (3.1599)	grad_norm 2.4015 (2.4781)	
[2022-01-25 08:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][210/1251]	eta 0:39:55 lr 0.000107	time 1.6799 (2.3011)	loss 2.2548 (3.1599)	grad_norm 2.0651 (2.4839)	
[2022-01-25 08:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][220/1251]	eta 0:39:23 lr 0.000107	time 2.0055 (2.2927)	loss 3.1490 (3.1677)	grad_norm 3.0236 (2.4847)	
[2022-01-25 08:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][230/1251]	eta 0:38:55 lr 0.000107	time 1.8605 (2.2878)	loss 3.4044 (3.1665)	grad_norm 2.9253 (2.4865)	
[2022-01-25 08:20:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][240/1251]	eta 0:38:38 lr 0.000107	time 2.3874 (2.2936)	loss 3.1874 (3.1714)	grad_norm 2.6477 (2.4919)	
[2022-01-25 08:20:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][250/1251]	eta 0:38:15 lr 0.000107	time 1.6100 (2.2928)	loss 3.4318 (3.1700)	grad_norm 2.3211 (2.4934)	
[2022-01-25 08:21:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][260/1251]	eta 0:37:50 lr 0.000107	time 2.3065 (2.2911)	loss 3.3705 (3.1631)	grad_norm 2.1821 (2.4948)	
[2022-01-25 08:21:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][270/1251]	eta 0:37:15 lr 0.000107	time 1.7002 (2.2791)	loss 2.6858 (3.1588)	grad_norm 2.8132 (2.4965)	
[2022-01-25 08:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][280/1251]	eta 0:36:45 lr 0.000107	time 1.7803 (2.2713)	loss 3.4092 (3.1683)	grad_norm 2.6822 (2.4972)	
[2022-01-25 08:22:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][290/1251]	eta 0:36:15 lr 0.000107	time 1.8991 (2.2637)	loss 2.5802 (3.1669)	grad_norm 2.3928 (2.5035)	
[2022-01-25 08:22:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][300/1251]	eta 0:35:55 lr 0.000107	time 1.8872 (2.2661)	loss 3.4057 (3.1646)	grad_norm 2.8818 (2.5121)	
[2022-01-25 08:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][310/1251]	eta 0:35:35 lr 0.000107	time 2.2023 (2.2699)	loss 3.5353 (3.1640)	grad_norm 2.7759 (2.5097)	
[2022-01-25 08:23:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][320/1251]	eta 0:35:16 lr 0.000107	time 2.0282 (2.2735)	loss 2.4324 (3.1615)	grad_norm 2.2898 (2.5058)	
[2022-01-25 08:23:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][330/1251]	eta 0:34:51 lr 0.000107	time 2.0996 (2.2713)	loss 3.2372 (3.1670)	grad_norm 2.4663 (2.5045)	
[2022-01-25 08:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][340/1251]	eta 0:34:24 lr 0.000107	time 1.8839 (2.2661)	loss 3.0922 (3.1697)	grad_norm 2.1400 (2.5050)	
[2022-01-25 08:24:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][350/1251]	eta 0:33:53 lr 0.000107	time 2.1560 (2.2574)	loss 3.0404 (3.1727)	grad_norm 2.3733 (2.5006)	
[2022-01-25 08:24:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][360/1251]	eta 0:33:24 lr 0.000107	time 2.1647 (2.2500)	loss 2.8969 (3.1704)	grad_norm 2.8917 (2.5069)	
[2022-01-25 08:25:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][370/1251]	eta 0:32:59 lr 0.000107	time 2.4384 (2.2473)	loss 3.5241 (3.1662)	grad_norm 2.4373 (2.5078)	
[2022-01-25 08:25:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][380/1251]	eta 0:32:34 lr 0.000107	time 2.2395 (2.2437)	loss 3.2014 (3.1660)	grad_norm 3.0636 (2.5096)	
[2022-01-25 08:26:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][390/1251]	eta 0:32:09 lr 0.000107	time 1.8908 (2.2405)	loss 3.5812 (3.1654)	grad_norm 2.2295 (2.5127)	
[2022-01-25 08:26:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][400/1251]	eta 0:31:43 lr 0.000107	time 2.1301 (2.2366)	loss 3.2722 (3.1729)	grad_norm 3.5402 (2.5143)	
[2022-01-25 08:26:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][410/1251]	eta 0:31:21 lr 0.000107	time 3.0601 (2.2370)	loss 3.2821 (3.1714)	grad_norm 2.8281 (2.5193)	
[2022-01-25 08:27:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][420/1251]	eta 0:30:57 lr 0.000107	time 2.1131 (2.2353)	loss 3.7262 (3.1656)	grad_norm 2.2234 (2.5186)	
[2022-01-25 08:27:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][430/1251]	eta 0:30:35 lr 0.000107	time 1.8415 (2.2354)	loss 3.3708 (3.1646)	grad_norm 3.1502 (2.5196)	
[2022-01-25 08:27:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][440/1251]	eta 0:30:15 lr 0.000107	time 2.7275 (2.2383)	loss 2.6170 (3.1672)	grad_norm 2.9563 (2.5270)	
[2022-01-25 08:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][450/1251]	eta 0:29:55 lr 0.000106	time 3.0875 (2.2413)	loss 2.1382 (3.1659)	grad_norm 2.5317 (2.5235)	
[2022-01-25 08:28:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][460/1251]	eta 0:29:34 lr 0.000106	time 2.8105 (2.2434)	loss 3.9704 (3.1727)	grad_norm 3.4214 (2.5259)	
[2022-01-25 08:29:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][470/1251]	eta 0:29:10 lr 0.000106	time 1.8956 (2.2411)	loss 3.6697 (3.1763)	grad_norm 2.1913 (2.5251)	
[2022-01-25 08:29:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][480/1251]	eta 0:28:48 lr 0.000106	time 2.7567 (2.2421)	loss 2.1623 (3.1654)	grad_norm 2.4646 (2.5222)	
[2022-01-25 08:29:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][490/1251]	eta 0:28:22 lr 0.000106	time 1.7831 (2.2371)	loss 3.8423 (3.1669)	grad_norm 2.3005 (2.5206)	
[2022-01-25 08:30:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][500/1251]	eta 0:27:58 lr 0.000106	time 1.9073 (2.2354)	loss 2.9413 (3.1662)	grad_norm 2.0416 (2.5179)	
[2022-01-25 08:30:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][510/1251]	eta 0:27:35 lr 0.000106	time 2.1526 (2.2340)	loss 4.0694 (3.1663)	grad_norm 2.9236 (2.5200)	
[2022-01-25 08:30:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][520/1251]	eta 0:27:13 lr 0.000106	time 3.7778 (2.2345)	loss 3.6156 (3.1672)	grad_norm 2.5559 (2.5168)	
[2022-01-25 08:31:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][530/1251]	eta 0:26:50 lr 0.000106	time 2.1979 (2.2333)	loss 3.2945 (3.1675)	grad_norm 2.0955 (2.5133)	
[2022-01-25 08:31:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][540/1251]	eta 0:26:27 lr 0.000106	time 1.9316 (2.2325)	loss 3.2989 (3.1655)	grad_norm 2.4174 (2.5119)	
[2022-01-25 08:31:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][550/1251]	eta 0:26:06 lr 0.000106	time 2.2152 (2.2345)	loss 3.6256 (3.1661)	grad_norm 2.5926 (2.5102)	
[2022-01-25 08:32:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][560/1251]	eta 0:25:44 lr 0.000106	time 2.8558 (2.2355)	loss 2.7726 (3.1667)	grad_norm 2.6482 (2.5126)	
[2022-01-25 08:32:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][570/1251]	eta 0:25:20 lr 0.000106	time 1.5862 (2.2322)	loss 3.5054 (3.1678)	grad_norm 2.8216 (2.5157)	
[2022-01-25 08:32:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][580/1251]	eta 0:24:54 lr 0.000106	time 1.8330 (2.2272)	loss 3.0773 (3.1636)	grad_norm 2.3694 (2.5168)	
[2022-01-25 08:33:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][590/1251]	eta 0:24:30 lr 0.000106	time 2.0780 (2.2243)	loss 3.2961 (3.1634)	grad_norm 2.6939 (2.5176)	
[2022-01-25 08:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][600/1251]	eta 0:24:06 lr 0.000106	time 1.8827 (2.2226)	loss 3.6411 (3.1699)	grad_norm 2.3639 (2.5174)	
[2022-01-25 08:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][610/1251]	eta 0:23:45 lr 0.000106	time 3.0257 (2.2237)	loss 3.5792 (3.1721)	grad_norm 2.4794 (2.5176)	
[2022-01-25 08:34:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][620/1251]	eta 0:23:22 lr 0.000106	time 1.8916 (2.2221)	loss 3.4664 (3.1742)	grad_norm 2.4108 (2.5174)	
[2022-01-25 08:34:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][630/1251]	eta 0:22:59 lr 0.000106	time 2.8312 (2.2219)	loss 2.6518 (3.1685)	grad_norm 2.3897 (2.5195)	
[2022-01-25 08:35:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][640/1251]	eta 0:22:38 lr 0.000106	time 1.9759 (2.2228)	loss 3.9359 (3.1671)	grad_norm 2.5834 (2.5225)	
[2022-01-25 08:35:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][650/1251]	eta 0:22:16 lr 0.000106	time 2.5706 (2.2235)	loss 2.3503 (3.1679)	grad_norm 2.4721 (2.5208)	
[2022-01-25 08:35:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][660/1251]	eta 0:21:54 lr 0.000106	time 1.8859 (2.2237)	loss 3.3798 (3.1696)	grad_norm 2.4049 (2.5196)	
[2022-01-25 08:36:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][670/1251]	eta 0:21:30 lr 0.000106	time 1.6873 (2.2220)	loss 4.0027 (3.1657)	grad_norm 2.4136 (2.5184)	
[2022-01-25 08:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][680/1251]	eta 0:21:08 lr 0.000106	time 1.9000 (2.2210)	loss 3.8716 (3.1635)	grad_norm 2.8352 (2.5192)	
[2022-01-25 08:36:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][690/1251]	eta 0:20:45 lr 0.000106	time 2.4819 (2.2200)	loss 3.6232 (3.1645)	grad_norm 2.5465 (2.5185)	
[2022-01-25 08:37:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][700/1251]	eta 0:20:23 lr 0.000106	time 2.4535 (2.2199)	loss 3.8135 (3.1654)	grad_norm 2.5998 (2.5187)	
[2022-01-25 08:37:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][710/1251]	eta 0:19:59 lr 0.000106	time 2.0205 (2.2171)	loss 3.2720 (3.1631)	grad_norm 2.5552 (2.5196)	
[2022-01-25 08:38:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][720/1251]	eta 0:19:37 lr 0.000106	time 1.9157 (2.2182)	loss 3.3793 (3.1629)	grad_norm 2.3210 (2.5192)	
[2022-01-25 08:38:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][730/1251]	eta 0:19:16 lr 0.000106	time 3.0294 (2.2200)	loss 3.6393 (3.1630)	grad_norm 2.3958 (2.5177)	
[2022-01-25 08:38:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][740/1251]	eta 0:18:55 lr 0.000106	time 2.3275 (2.2214)	loss 2.9549 (3.1611)	grad_norm 2.4611 (2.5183)	
[2022-01-25 08:39:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][750/1251]	eta 0:18:32 lr 0.000106	time 1.6502 (2.2209)	loss 3.5216 (3.1632)	grad_norm 2.3697 (2.5217)	
[2022-01-25 08:39:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][760/1251]	eta 0:18:09 lr 0.000106	time 1.9565 (2.2191)	loss 2.6541 (3.1663)	grad_norm 2.1211 (2.5208)	
[2022-01-25 08:39:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][770/1251]	eta 0:17:45 lr 0.000106	time 2.2997 (2.2151)	loss 3.6113 (3.1676)	grad_norm 2.4794 (2.5218)	
[2022-01-25 08:40:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][780/1251]	eta 0:17:22 lr 0.000106	time 2.1350 (2.2128)	loss 3.5136 (3.1677)	grad_norm 2.3295 (2.5226)	
[2022-01-25 08:40:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][790/1251]	eta 0:16:59 lr 0.000106	time 1.6742 (2.2123)	loss 2.8448 (3.1691)	grad_norm 2.8664 (2.5220)	
[2022-01-25 08:40:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][800/1251]	eta 0:16:39 lr 0.000106	time 4.1404 (2.2161)	loss 3.8284 (3.1644)	grad_norm 2.2141 (2.5214)	
[2022-01-25 08:41:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][810/1251]	eta 0:16:18 lr 0.000106	time 1.8003 (2.2186)	loss 3.1871 (3.1633)	grad_norm 2.4525 (2.5206)	
[2022-01-25 08:41:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][820/1251]	eta 0:15:57 lr 0.000106	time 2.5434 (2.2213)	loss 3.7022 (3.1612)	grad_norm 2.7370 (2.5207)	
[2022-01-25 08:42:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][830/1251]	eta 0:15:35 lr 0.000106	time 1.8355 (2.2216)	loss 3.5548 (3.1646)	grad_norm 2.5708 (2.5210)	
[2022-01-25 08:42:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][840/1251]	eta 0:15:11 lr 0.000106	time 1.6460 (2.2184)	loss 3.4140 (3.1655)	grad_norm 2.1282 (2.5200)	
[2022-01-25 08:42:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][850/1251]	eta 0:14:48 lr 0.000106	time 2.1078 (2.2153)	loss 2.4749 (3.1652)	grad_norm 2.2607 (2.5197)	
[2022-01-25 08:43:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][860/1251]	eta 0:14:25 lr 0.000105	time 2.0261 (2.2125)	loss 3.2144 (3.1626)	grad_norm 2.4385 (2.5176)	
[2022-01-25 08:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][870/1251]	eta 0:14:02 lr 0.000105	time 2.3638 (2.2124)	loss 3.1611 (3.1621)	grad_norm 2.1127 (2.5149)	
[2022-01-25 08:43:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][880/1251]	eta 0:13:40 lr 0.000105	time 2.2409 (2.2122)	loss 3.8259 (3.1627)	grad_norm 2.4608 (2.5150)	
[2022-01-25 08:44:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][890/1251]	eta 0:13:18 lr 0.000105	time 2.1760 (2.2122)	loss 3.1420 (3.1633)	grad_norm 2.7261 (2.5152)	
[2022-01-25 08:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][900/1251]	eta 0:12:56 lr 0.000105	time 1.4697 (2.2115)	loss 2.1756 (3.1614)	grad_norm 2.0519 (2.5162)	
[2022-01-25 08:45:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][910/1251]	eta 0:12:34 lr 0.000105	time 2.9784 (2.2134)	loss 2.7871 (3.1603)	grad_norm 2.3576 (2.5134)	
[2022-01-25 08:45:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][920/1251]	eta 0:12:12 lr 0.000105	time 2.1469 (2.2137)	loss 3.0730 (3.1593)	grad_norm 2.3641 (2.5123)	
[2022-01-25 08:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][930/1251]	eta 0:11:50 lr 0.000105	time 2.2153 (2.2145)	loss 3.4705 (3.1562)	grad_norm 2.3133 (2.5142)	
[2022-01-25 08:46:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][940/1251]	eta 0:11:29 lr 0.000105	time 2.1042 (2.2156)	loss 3.5023 (3.1577)	grad_norm 2.3455 (2.5132)	
[2022-01-25 08:46:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][950/1251]	eta 0:11:07 lr 0.000105	time 2.6944 (2.2169)	loss 3.1981 (3.1556)	grad_norm 2.1836 (2.5120)	
[2022-01-25 08:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][960/1251]	eta 0:10:44 lr 0.000105	time 1.9743 (2.2135)	loss 3.1773 (3.1547)	grad_norm 2.2637 (2.5118)	
[2022-01-25 08:47:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][970/1251]	eta 0:10:21 lr 0.000105	time 2.1997 (2.2104)	loss 3.2468 (3.1531)	grad_norm 2.5090 (2.5111)	
[2022-01-25 08:47:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][980/1251]	eta 0:09:58 lr 0.000105	time 2.2007 (2.2082)	loss 3.3310 (3.1503)	grad_norm 2.6709 (2.5101)	
[2022-01-25 08:47:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][990/1251]	eta 0:09:36 lr 0.000105	time 2.2097 (2.2070)	loss 2.9103 (3.1455)	grad_norm 2.6766 (2.5090)	
[2022-01-25 08:48:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1000/1251]	eta 0:09:13 lr 0.000105	time 1.3824 (2.2062)	loss 3.2825 (3.1458)	grad_norm 2.4226 (2.5078)	
[2022-01-25 08:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1010/1251]	eta 0:08:51 lr 0.000105	time 2.1112 (2.2065)	loss 3.6401 (3.1485)	grad_norm 3.5692 (2.5091)	
[2022-01-25 08:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1020/1251]	eta 0:08:30 lr 0.000105	time 3.0505 (2.2089)	loss 2.2418 (3.1472)	grad_norm 2.5017 (2.5077)	
[2022-01-25 08:49:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1030/1251]	eta 0:08:08 lr 0.000105	time 2.5686 (2.2103)	loss 3.3154 (3.1457)	grad_norm 3.4753 (2.5079)	
[2022-01-25 08:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1040/1251]	eta 0:07:46 lr 0.000105	time 1.8965 (2.2103)	loss 2.6160 (3.1479)	grad_norm 3.1967 (2.5073)	
[2022-01-25 08:50:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1050/1251]	eta 0:07:24 lr 0.000105	time 2.3195 (2.2114)	loss 3.4539 (3.1464)	grad_norm 2.5694 (2.5067)	
[2022-01-25 08:50:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1060/1251]	eta 0:07:02 lr 0.000105	time 2.2069 (2.2124)	loss 3.1997 (3.1472)	grad_norm 2.5269 (2.5058)	
[2022-01-25 08:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1070/1251]	eta 0:06:40 lr 0.000105	time 1.8795 (2.2113)	loss 3.1643 (3.1472)	grad_norm 2.3817 (2.5050)	
[2022-01-25 08:51:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1080/1251]	eta 0:06:17 lr 0.000105	time 1.9191 (2.2096)	loss 3.4659 (3.1467)	grad_norm 2.4213 (2.5072)	
[2022-01-25 08:51:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1090/1251]	eta 0:05:55 lr 0.000105	time 2.2074 (2.2083)	loss 3.6496 (3.1457)	grad_norm 3.3356 (2.5067)	
[2022-01-25 08:51:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1100/1251]	eta 0:05:33 lr 0.000105	time 1.9506 (2.2061)	loss 3.2015 (3.1462)	grad_norm 2.7710 (2.5085)	
[2022-01-25 08:52:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1110/1251]	eta 0:05:11 lr 0.000105	time 1.9414 (2.2061)	loss 2.1378 (3.1469)	grad_norm 2.5964 (2.5095)	
[2022-01-25 08:52:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1120/1251]	eta 0:04:49 lr 0.000105	time 2.8804 (2.2077)	loss 3.0924 (3.1485)	grad_norm 2.3414 (2.5095)	
[2022-01-25 08:53:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1130/1251]	eta 0:04:27 lr 0.000105	time 3.0920 (2.2092)	loss 3.5471 (3.1492)	grad_norm 2.3724 (2.5090)	
[2022-01-25 08:53:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1140/1251]	eta 0:04:05 lr 0.000105	time 2.2214 (2.2082)	loss 3.4256 (3.1500)	grad_norm 2.5476 (2.5084)	
[2022-01-25 08:53:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1150/1251]	eta 0:03:43 lr 0.000105	time 2.1653 (2.2079)	loss 3.5755 (3.1503)	grad_norm 2.7127 (2.5073)	
[2022-01-25 08:54:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1160/1251]	eta 0:03:20 lr 0.000105	time 1.9271 (2.2063)	loss 3.4205 (3.1513)	grad_norm 2.6340 (2.5069)	
[2022-01-25 08:54:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1170/1251]	eta 0:02:58 lr 0.000105	time 1.6101 (2.2057)	loss 2.2966 (3.1495)	grad_norm 2.6729 (2.5072)	
[2022-01-25 08:54:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1180/1251]	eta 0:02:36 lr 0.000105	time 2.3238 (2.2067)	loss 3.0538 (3.1494)	grad_norm 2.2607 (2.5085)	
[2022-01-25 08:55:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1190/1251]	eta 0:02:14 lr 0.000105	time 2.2338 (2.2079)	loss 2.1202 (3.1496)	grad_norm 2.3601 (2.5080)	
[2022-01-25 08:55:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1200/1251]	eta 0:01:52 lr 0.000105	time 2.1900 (2.2073)	loss 3.3940 (3.1491)	grad_norm 2.2298 (2.5075)	
[2022-01-25 08:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1210/1251]	eta 0:01:30 lr 0.000105	time 1.7267 (2.2061)	loss 3.1681 (3.1489)	grad_norm 2.4853 (2.5071)	
[2022-01-25 08:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1220/1251]	eta 0:01:08 lr 0.000105	time 1.9090 (2.2059)	loss 3.2583 (3.1496)	grad_norm 2.5888 (2.5070)	
[2022-01-25 08:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1230/1251]	eta 0:00:46 lr 0.000105	time 1.5512 (2.2070)	loss 3.0997 (3.1500)	grad_norm 2.2454 (2.5069)	
[2022-01-25 08:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1240/1251]	eta 0:00:24 lr 0.000105	time 1.2471 (2.2057)	loss 3.7460 (3.1509)	grad_norm 2.4688 (2.5072)	
[2022-01-25 08:57:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [239/300][1250/1251]	eta 0:00:02 lr 0.000105	time 1.1943 (2.2003)	loss 3.6188 (3.1510)	grad_norm 2.8617 (2.5075)	
[2022-01-25 08:57:17 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 239 training takes 0:45:52
[2022-01-25 08:57:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.044 (19.044)	Loss 0.9090 (0.9090)	Acc@1 78.516 (78.516)	Acc@5 94.531 (94.531)	
[2022-01-25 08:57:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.574 (3.085)	Loss 0.8266 (0.8561)	Acc@1 79.395 (80.211)	Acc@5 95.898 (94.913)	
[2022-01-25 08:58:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.137 (2.480)	Loss 0.8003 (0.8670)	Acc@1 82.031 (79.915)	Acc@5 95.801 (94.875)	
[2022-01-25 08:58:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.657 (2.217)	Loss 0.8654 (0.8662)	Acc@1 79.395 (79.795)	Acc@5 95.020 (94.938)	
[2022-01-25 08:58:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.323 (2.176)	Loss 0.8300 (0.8626)	Acc@1 81.250 (79.985)	Acc@5 95.605 (94.965)	
[2022-01-25 08:58:53 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.012 Acc@5 94.990
[2022-01-25 08:58:53 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.0%
[2022-01-25 08:58:53 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.01%
[2022-01-25 08:59:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][0/1251]	eta 8:20:45 lr 0.000105	time 24.0171 (24.0171)	loss 2.5618 (2.5618)	grad_norm 3.0028 (3.0028)	
[2022-01-25 08:59:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][10/1251]	eta 1:29:08 lr 0.000105	time 2.8716 (4.3100)	loss 2.5498 (2.9577)	grad_norm 2.3128 (2.5327)	
[2022-01-25 09:00:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][20/1251]	eta 1:07:28 lr 0.000104	time 2.4729 (3.2888)	loss 3.4365 (3.1144)	grad_norm 3.3704 (2.4855)	
[2022-01-25 09:00:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][30/1251]	eta 1:00:01 lr 0.000104	time 1.6527 (2.9493)	loss 2.3851 (3.1388)	grad_norm 2.2905 (2.4669)	
[2022-01-25 09:00:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][40/1251]	eta 0:56:37 lr 0.000104	time 3.9086 (2.8054)	loss 3.3682 (3.1488)	grad_norm 1.8754 (2.4726)	
[2022-01-25 09:01:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][50/1251]	eta 0:53:19 lr 0.000104	time 2.1142 (2.6639)	loss 3.0302 (3.1448)	grad_norm 2.4803 (2.5017)	
[2022-01-25 09:01:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][60/1251]	eta 0:50:47 lr 0.000104	time 1.9003 (2.5584)	loss 3.2266 (3.1709)	grad_norm 2.4272 (2.4972)	
[2022-01-25 09:01:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][70/1251]	eta 0:49:06 lr 0.000104	time 1.5358 (2.4946)	loss 3.0392 (3.1812)	grad_norm 2.4176 (2.5221)	
[2022-01-25 09:02:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][80/1251]	eta 0:48:11 lr 0.000104	time 3.8402 (2.4693)	loss 3.5407 (3.1723)	grad_norm 2.5659 (2.5116)	
[2022-01-25 09:02:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][90/1251]	eta 0:47:10 lr 0.000104	time 1.5926 (2.4384)	loss 3.5248 (3.1735)	grad_norm 2.4192 (2.5088)	
[2022-01-25 09:02:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][100/1251]	eta 0:46:22 lr 0.000104	time 2.6927 (2.4178)	loss 3.5770 (3.1797)	grad_norm 2.5042 (2.5145)	
[2022-01-25 09:03:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][110/1251]	eta 0:45:49 lr 0.000104	time 2.1396 (2.4097)	loss 3.0182 (3.1822)	grad_norm 2.3456 (2.5114)	
[2022-01-25 09:03:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][120/1251]	eta 0:45:14 lr 0.000104	time 2.2387 (2.4003)	loss 2.7800 (3.1913)	grad_norm 2.6666 (2.5137)	
[2022-01-25 09:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][130/1251]	eta 0:44:24 lr 0.000104	time 2.1611 (2.3770)	loss 2.9205 (3.1914)	grad_norm 2.5638 (2.5206)	
[2022-01-25 09:04:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][140/1251]	eta 0:43:37 lr 0.000104	time 1.7685 (2.3563)	loss 3.6923 (3.1915)	grad_norm 2.4624 (2.5198)	
[2022-01-25 09:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][150/1251]	eta 0:42:59 lr 0.000104	time 2.2789 (2.3433)	loss 3.1228 (3.1860)	grad_norm 2.3456 (2.5257)	
[2022-01-25 09:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][160/1251]	eta 0:42:30 lr 0.000104	time 2.4637 (2.3379)	loss 3.5804 (3.1736)	grad_norm 2.2962 (2.5250)	
[2022-01-25 09:05:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][170/1251]	eta 0:41:53 lr 0.000104	time 2.0178 (2.3253)	loss 2.8302 (3.1596)	grad_norm 2.6943 (2.5230)	
[2022-01-25 09:05:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][180/1251]	eta 0:41:19 lr 0.000104	time 1.8915 (2.3152)	loss 1.9836 (3.1484)	grad_norm 3.0544 (2.5245)	
[2022-01-25 09:06:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][190/1251]	eta 0:40:48 lr 0.000104	time 2.3123 (2.3076)	loss 2.3504 (3.1400)	grad_norm 2.6913 (2.5373)	
[2022-01-25 09:06:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][200/1251]	eta 0:40:15 lr 0.000104	time 2.2936 (2.2986)	loss 3.4814 (3.1412)	grad_norm 2.0575 (2.5353)	
[2022-01-25 09:06:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][210/1251]	eta 0:39:58 lr 0.000104	time 3.4398 (2.3039)	loss 2.1836 (3.1407)	grad_norm 2.5028 (2.5310)	
[2022-01-25 09:07:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][220/1251]	eta 0:39:30 lr 0.000104	time 1.6091 (2.2992)	loss 3.5972 (3.1439)	grad_norm 2.2763 (2.5299)	
[2022-01-25 09:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][230/1251]	eta 0:39:04 lr 0.000104	time 2.4499 (2.2962)	loss 3.2474 (3.1510)	grad_norm 3.1000 (2.5309)	
[2022-01-25 09:08:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][240/1251]	eta 0:38:41 lr 0.000104	time 2.7765 (2.2960)	loss 3.3899 (3.1567)	grad_norm 2.1564 (2.5271)	
[2022-01-25 09:08:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][250/1251]	eta 0:38:07 lr 0.000104	time 2.1822 (2.2855)	loss 3.4306 (3.1503)	grad_norm 2.0774 (2.5211)	
[2022-01-25 09:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][260/1251]	eta 0:37:33 lr 0.000104	time 1.8941 (2.2744)	loss 3.0688 (3.1541)	grad_norm 2.4054 (2.5249)	
[2022-01-25 09:09:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][270/1251]	eta 0:37:01 lr 0.000104	time 1.5798 (2.2641)	loss 3.4656 (3.1543)	grad_norm 2.0031 (2.5199)	
[2022-01-25 09:09:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][280/1251]	eta 0:36:36 lr 0.000104	time 1.9650 (2.2623)	loss 3.1020 (3.1478)	grad_norm 2.6760 (2.5170)	
[2022-01-25 09:09:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][290/1251]	eta 0:36:15 lr 0.000104	time 2.7378 (2.2637)	loss 3.4432 (3.1551)	grad_norm 2.6880 (2.5148)	
[2022-01-25 09:10:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][300/1251]	eta 0:35:52 lr 0.000104	time 2.4500 (2.2639)	loss 2.7594 (3.1543)	grad_norm 2.0269 (2.5100)	
[2022-01-25 09:10:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][310/1251]	eta 0:35:23 lr 0.000104	time 2.1641 (2.2571)	loss 3.7242 (3.1552)	grad_norm 2.2117 (2.5070)	
[2022-01-25 09:10:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][320/1251]	eta 0:35:03 lr 0.000104	time 2.0900 (2.2593)	loss 2.9928 (3.1553)	grad_norm 2.6389 (2.5063)	
[2022-01-25 09:11:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][330/1251]	eta 0:34:39 lr 0.000104	time 2.2426 (2.2581)	loss 3.4542 (3.1557)	grad_norm 2.4147 (2.5026)	
[2022-01-25 09:11:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][340/1251]	eta 0:34:17 lr 0.000104	time 2.1316 (2.2586)	loss 2.9423 (3.1524)	grad_norm 2.2441 (2.4999)	
[2022-01-25 09:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][350/1251]	eta 0:33:49 lr 0.000104	time 1.7043 (2.2524)	loss 3.3560 (3.1467)	grad_norm 2.9557 (2.5044)	
[2022-01-25 09:12:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][360/1251]	eta 0:33:26 lr 0.000104	time 1.9510 (2.2518)	loss 3.0389 (3.1483)	grad_norm 2.2768 (2.5010)	
[2022-01-25 09:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][370/1251]	eta 0:33:04 lr 0.000104	time 2.5946 (2.2523)	loss 3.5939 (3.1525)	grad_norm 2.6491 (2.5015)	
[2022-01-25 09:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][380/1251]	eta 0:32:41 lr 0.000104	time 3.4320 (2.2526)	loss 3.5032 (3.1493)	grad_norm 2.7210 (2.5007)	
[2022-01-25 09:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][390/1251]	eta 0:32:16 lr 0.000104	time 1.6720 (2.2486)	loss 3.2155 (3.1480)	grad_norm 2.8065 (2.5003)	
[2022-01-25 09:13:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][400/1251]	eta 0:31:48 lr 0.000104	time 1.5640 (2.2428)	loss 3.7553 (3.1500)	grad_norm 2.4352 (2.4996)	
[2022-01-25 09:14:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][410/1251]	eta 0:31:23 lr 0.000104	time 1.9177 (2.2400)	loss 3.4337 (3.1519)	grad_norm 2.7717 (2.5065)	
[2022-01-25 09:14:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][420/1251]	eta 0:31:03 lr 0.000104	time 3.6994 (2.2431)	loss 3.4725 (3.1521)	grad_norm 2.1177 (2.5120)	
[2022-01-25 09:15:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][430/1251]	eta 0:30:42 lr 0.000103	time 1.8233 (2.2439)	loss 3.6604 (3.1516)	grad_norm 2.4123 (2.5154)	
[2022-01-25 09:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][440/1251]	eta 0:30:20 lr 0.000103	time 1.5787 (2.2445)	loss 2.5621 (3.1472)	grad_norm 2.9844 (2.5176)	
[2022-01-25 09:15:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][450/1251]	eta 0:29:55 lr 0.000103	time 2.1653 (2.2414)	loss 2.6250 (3.1506)	grad_norm 2.3727 (2.5176)	
[2022-01-25 09:16:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][460/1251]	eta 0:29:30 lr 0.000103	time 2.5427 (2.2385)	loss 1.8353 (3.1469)	grad_norm 2.5141 (2.5178)	
[2022-01-25 09:16:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][470/1251]	eta 0:29:08 lr 0.000103	time 2.5448 (2.2382)	loss 3.7236 (3.1456)	grad_norm 2.2916 (2.5175)	
[2022-01-25 09:16:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][480/1251]	eta 0:28:44 lr 0.000103	time 2.1479 (2.2371)	loss 2.5791 (3.1493)	grad_norm 2.4843 (2.5172)	
[2022-01-25 09:17:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][490/1251]	eta 0:28:19 lr 0.000103	time 1.9440 (2.2331)	loss 3.6755 (3.1551)	grad_norm 2.6021 (2.5177)	
[2022-01-25 09:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][500/1251]	eta 0:27:54 lr 0.000103	time 1.9601 (2.2297)	loss 2.5108 (3.1598)	grad_norm 2.3269 (2.5189)	
[2022-01-25 09:17:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][510/1251]	eta 0:27:28 lr 0.000103	time 1.9257 (2.2250)	loss 2.6465 (3.1558)	grad_norm 2.5634 (2.5210)	
[2022-01-25 09:18:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][520/1251]	eta 0:27:05 lr 0.000103	time 2.1868 (2.2233)	loss 2.2860 (3.1516)	grad_norm 2.5783 (2.5237)	
[2022-01-25 09:18:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][530/1251]	eta 0:26:42 lr 0.000103	time 2.3455 (2.2232)	loss 2.3995 (3.1497)	grad_norm 2.5662 (2.5214)	
[2022-01-25 09:18:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][540/1251]	eta 0:26:19 lr 0.000103	time 2.4168 (2.2221)	loss 2.9954 (3.1515)	grad_norm 2.7334 (2.5261)	
[2022-01-25 09:19:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][550/1251]	eta 0:25:58 lr 0.000103	time 1.9234 (2.2230)	loss 3.6638 (3.1515)	grad_norm 2.4795 (2.5262)	
[2022-01-25 09:19:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][560/1251]	eta 0:25:37 lr 0.000103	time 3.1053 (2.2245)	loss 3.4524 (3.1528)	grad_norm 2.5871 (2.5298)	
[2022-01-25 09:20:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][570/1251]	eta 0:25:16 lr 0.000103	time 2.5532 (2.2262)	loss 2.2857 (3.1521)	grad_norm 2.6383 (2.5324)	
[2022-01-25 09:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][580/1251]	eta 0:24:54 lr 0.000103	time 2.7476 (2.2268)	loss 3.6464 (3.1539)	grad_norm 2.6959 (2.5332)	
[2022-01-25 09:20:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][590/1251]	eta 0:24:31 lr 0.000103	time 2.3921 (2.2262)	loss 2.4803 (3.1527)	grad_norm 2.9573 (2.5343)	
[2022-01-25 09:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][600/1251]	eta 0:24:07 lr 0.000103	time 1.9733 (2.2230)	loss 2.9991 (3.1491)	grad_norm 2.6513 (2.5361)	
[2022-01-25 09:21:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][610/1251]	eta 0:23:43 lr 0.000103	time 2.2843 (2.2201)	loss 2.8247 (3.1489)	grad_norm 2.4690 (2.5363)	
[2022-01-25 09:21:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][620/1251]	eta 0:23:20 lr 0.000103	time 2.0963 (2.2194)	loss 3.2564 (3.1484)	grad_norm 2.3643 (2.5348)	
[2022-01-25 09:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][630/1251]	eta 0:22:58 lr 0.000103	time 2.8091 (2.2204)	loss 2.9433 (3.1498)	grad_norm 2.3424 (2.5325)	
[2022-01-25 09:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][640/1251]	eta 0:22:35 lr 0.000103	time 1.8430 (2.2178)	loss 3.5685 (3.1531)	grad_norm 2.4903 (2.5311)	
[2022-01-25 09:22:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][650/1251]	eta 0:22:13 lr 0.000103	time 2.6013 (2.2180)	loss 3.0442 (3.1525)	grad_norm 2.5177 (2.5294)	
[2022-01-25 09:23:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][660/1251]	eta 0:21:49 lr 0.000103	time 2.1939 (2.2156)	loss 2.0885 (3.1498)	grad_norm 2.3552 (2.5282)	
[2022-01-25 09:23:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][670/1251]	eta 0:21:26 lr 0.000103	time 2.1037 (2.2146)	loss 3.5859 (3.1507)	grad_norm 2.4576 (2.5281)	
[2022-01-25 09:24:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][680/1251]	eta 0:21:04 lr 0.000103	time 2.7542 (2.2142)	loss 3.4840 (3.1529)	grad_norm 2.4341 (2.5284)	
[2022-01-25 09:24:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][690/1251]	eta 0:20:42 lr 0.000103	time 1.5222 (2.2148)	loss 3.7156 (3.1525)	grad_norm 2.1027 (2.5271)	
[2022-01-25 09:24:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][700/1251]	eta 0:20:22 lr 0.000103	time 1.9003 (2.2179)	loss 2.4120 (3.1518)	grad_norm 2.4832 (2.5257)	
[2022-01-25 09:25:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][710/1251]	eta 0:20:00 lr 0.000103	time 1.9437 (2.2185)	loss 2.7693 (3.1492)	grad_norm 3.1529 (2.5261)	
[2022-01-25 09:25:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][720/1251]	eta 0:19:38 lr 0.000103	time 2.1711 (2.2188)	loss 3.7242 (3.1500)	grad_norm 2.6308 (2.5262)	
[2022-01-25 09:25:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][730/1251]	eta 0:19:14 lr 0.000103	time 1.6000 (2.2157)	loss 3.0360 (3.1498)	grad_norm 2.1426 (2.5265)	
[2022-01-25 09:26:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][740/1251]	eta 0:18:50 lr 0.000103	time 2.1891 (2.2132)	loss 2.7692 (3.1506)	grad_norm 2.0962 (2.5252)	
[2022-01-25 09:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][750/1251]	eta 0:18:27 lr 0.000103	time 2.5712 (2.2115)	loss 3.1535 (3.1515)	grad_norm 2.2463 (2.5245)	
[2022-01-25 09:26:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][760/1251]	eta 0:18:05 lr 0.000103	time 2.1868 (2.2116)	loss 3.2069 (3.1525)	grad_norm 2.8313 (2.5239)	
[2022-01-25 09:27:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][770/1251]	eta 0:17:43 lr 0.000103	time 2.1408 (2.2106)	loss 3.6966 (3.1511)	grad_norm 2.4515 (2.5235)	
[2022-01-25 09:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][780/1251]	eta 0:17:21 lr 0.000103	time 2.5817 (2.2123)	loss 2.7740 (3.1523)	grad_norm 2.4712 (2.5255)	
[2022-01-25 09:28:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][790/1251]	eta 0:17:00 lr 0.000103	time 1.9721 (2.2130)	loss 3.3833 (3.1518)	grad_norm 2.4567 (2.5250)	
[2022-01-25 09:28:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][800/1251]	eta 0:16:38 lr 0.000103	time 2.1421 (2.2141)	loss 2.2811 (3.1505)	grad_norm 2.3903 (2.5236)	
[2022-01-25 09:28:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][810/1251]	eta 0:16:15 lr 0.000103	time 2.2021 (2.2127)	loss 3.3920 (3.1487)	grad_norm 2.2298 (2.5218)	
[2022-01-25 09:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][820/1251]	eta 0:15:52 lr 0.000103	time 1.9538 (2.2108)	loss 3.4759 (3.1506)	grad_norm 2.5870 (2.5213)	
[2022-01-25 09:29:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][830/1251]	eta 0:15:31 lr 0.000103	time 1.9002 (2.2118)	loss 3.3118 (3.1517)	grad_norm 2.3416 (2.5202)	
[2022-01-25 09:29:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][840/1251]	eta 0:15:08 lr 0.000103	time 2.1318 (2.2116)	loss 2.7757 (3.1530)	grad_norm 3.0658 (2.5209)	
[2022-01-25 09:30:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][850/1251]	eta 0:14:45 lr 0.000102	time 2.0913 (2.2093)	loss 3.5621 (3.1535)	grad_norm 2.4919 (2.5202)	
[2022-01-25 09:30:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][860/1251]	eta 0:14:23 lr 0.000102	time 2.1044 (2.2088)	loss 2.8973 (3.1544)	grad_norm 2.6646 (2.5197)	
[2022-01-25 09:30:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][870/1251]	eta 0:14:01 lr 0.000102	time 2.5222 (2.2074)	loss 3.3043 (3.1565)	grad_norm 2.7196 (2.5180)	
[2022-01-25 09:31:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][880/1251]	eta 0:13:38 lr 0.000102	time 2.1690 (2.2074)	loss 3.3688 (3.1570)	grad_norm 2.1802 (2.5170)	
[2022-01-25 09:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][890/1251]	eta 0:13:17 lr 0.000102	time 1.9720 (2.2089)	loss 3.2652 (3.1576)	grad_norm 2.4344 (2.5190)	
[2022-01-25 09:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][900/1251]	eta 0:12:55 lr 0.000102	time 2.1978 (2.2084)	loss 3.9301 (3.1574)	grad_norm 2.4180 (2.5191)	
[2022-01-25 09:32:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][910/1251]	eta 0:12:33 lr 0.000102	time 1.8417 (2.2083)	loss 3.2340 (3.1564)	grad_norm 2.4944 (2.5176)	
[2022-01-25 09:32:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][920/1251]	eta 0:12:11 lr 0.000102	time 1.8236 (2.2087)	loss 2.9728 (3.1538)	grad_norm 2.4136 (2.5157)	
[2022-01-25 09:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][930/1251]	eta 0:11:49 lr 0.000102	time 1.9006 (2.2090)	loss 3.7593 (3.1512)	grad_norm 2.6283 (2.5138)	
[2022-01-25 09:33:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][940/1251]	eta 0:11:26 lr 0.000102	time 1.8652 (2.2080)	loss 2.8085 (3.1510)	grad_norm 2.5305 (2.5130)	
[2022-01-25 09:33:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][950/1251]	eta 0:11:04 lr 0.000102	time 1.6407 (2.2075)	loss 3.5770 (3.1497)	grad_norm 2.6935 (2.5129)	
[2022-01-25 09:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][960/1251]	eta 0:10:42 lr 0.000102	time 1.9161 (2.2067)	loss 2.8665 (3.1481)	grad_norm 2.1154 (2.5122)	
[2022-01-25 09:34:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][970/1251]	eta 0:10:19 lr 0.000102	time 2.2087 (2.2046)	loss 3.2476 (3.1496)	grad_norm 2.6199 (2.5121)	
[2022-01-25 09:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][980/1251]	eta 0:09:57 lr 0.000102	time 2.1024 (2.2031)	loss 3.4210 (3.1490)	grad_norm 2.1457 (2.5119)	
[2022-01-25 09:35:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][990/1251]	eta 0:09:34 lr 0.000102	time 2.1677 (2.2018)	loss 3.2435 (3.1502)	grad_norm 2.6445 (2.5111)	
[2022-01-25 09:35:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1000/1251]	eta 0:09:12 lr 0.000102	time 2.3300 (2.2016)	loss 3.3582 (3.1517)	grad_norm 2.2323 (2.5093)	
[2022-01-25 09:36:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1010/1251]	eta 0:08:50 lr 0.000102	time 2.5568 (2.2027)	loss 3.1356 (3.1516)	grad_norm 2.3576 (2.5084)	
[2022-01-25 09:36:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1020/1251]	eta 0:08:28 lr 0.000102	time 1.5334 (2.2030)	loss 3.5262 (3.1511)	grad_norm 2.6169 (2.5080)	
[2022-01-25 09:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1030/1251]	eta 0:08:07 lr 0.000102	time 2.5671 (2.2041)	loss 3.2530 (3.1507)	grad_norm 3.2078 (2.5093)	
[2022-01-25 09:37:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1040/1251]	eta 0:07:45 lr 0.000102	time 2.1676 (2.2045)	loss 3.1219 (3.1523)	grad_norm 2.5641 (2.5082)	
[2022-01-25 09:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1050/1251]	eta 0:07:23 lr 0.000102	time 2.5433 (2.2062)	loss 2.4259 (3.1526)	grad_norm 2.4604 (2.5084)	
[2022-01-25 09:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1060/1251]	eta 0:07:01 lr 0.000102	time 1.8830 (2.2068)	loss 2.9752 (3.1531)	grad_norm 2.5728 (2.5124)	
[2022-01-25 09:38:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1070/1251]	eta 0:06:39 lr 0.000102	time 1.9132 (2.2063)	loss 3.0940 (3.1524)	grad_norm 2.3952 (2.5120)	
[2022-01-25 09:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1080/1251]	eta 0:06:17 lr 0.000102	time 2.6222 (2.2054)	loss 2.5554 (3.1482)	grad_norm 3.0765 (2.5118)	
[2022-01-25 09:38:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1090/1251]	eta 0:05:54 lr 0.000102	time 1.8046 (2.2047)	loss 3.3803 (3.1482)	grad_norm 2.1782 (2.5105)	
[2022-01-25 09:39:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1100/1251]	eta 0:05:32 lr 0.000102	time 2.0209 (2.2026)	loss 3.4905 (3.1473)	grad_norm 2.6108 (2.5102)	
[2022-01-25 09:39:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1110/1251]	eta 0:05:10 lr 0.000102	time 1.8237 (2.2014)	loss 3.2385 (3.1465)	grad_norm 2.2211 (2.5110)	
[2022-01-25 09:40:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1120/1251]	eta 0:04:48 lr 0.000102	time 1.8527 (2.2004)	loss 2.6568 (3.1447)	grad_norm 3.0459 (2.5132)	
[2022-01-25 09:40:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1130/1251]	eta 0:04:26 lr 0.000102	time 2.9424 (2.2009)	loss 3.3297 (3.1442)	grad_norm 2.1306 (2.5125)	
[2022-01-25 09:40:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1140/1251]	eta 0:04:04 lr 0.000102	time 2.0663 (2.2014)	loss 2.9415 (3.1443)	grad_norm 2.6832 (2.5124)	
[2022-01-25 09:41:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1150/1251]	eta 0:03:42 lr 0.000102	time 2.0185 (2.2016)	loss 2.0245 (3.1448)	grad_norm 2.5116 (2.5124)	
[2022-01-25 09:41:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1160/1251]	eta 0:03:20 lr 0.000102	time 2.4622 (2.2028)	loss 3.4004 (3.1455)	grad_norm 2.7519 (2.5118)	
[2022-01-25 09:41:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1170/1251]	eta 0:02:58 lr 0.000102	time 2.5148 (2.2044)	loss 2.9308 (3.1459)	grad_norm 2.4703 (2.5112)	
[2022-01-25 09:42:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1180/1251]	eta 0:02:36 lr 0.000102	time 1.9350 (2.2035)	loss 3.2270 (3.1456)	grad_norm 3.5013 (2.5111)	
[2022-01-25 09:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1190/1251]	eta 0:02:14 lr 0.000102	time 2.0696 (2.2017)	loss 3.6754 (3.1457)	grad_norm 2.5386 (2.5111)	
[2022-01-25 09:42:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1200/1251]	eta 0:01:52 lr 0.000102	time 1.9786 (2.2005)	loss 2.6866 (3.1453)	grad_norm 2.1070 (2.5115)	
[2022-01-25 09:43:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1210/1251]	eta 0:01:30 lr 0.000102	time 2.5010 (2.2015)	loss 2.8305 (3.1448)	grad_norm 2.3849 (2.5111)	
[2022-01-25 09:43:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1220/1251]	eta 0:01:08 lr 0.000102	time 2.2872 (2.2012)	loss 2.8780 (3.1422)	grad_norm 3.8185 (2.5115)	
[2022-01-25 09:44:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1230/1251]	eta 0:00:46 lr 0.000102	time 1.8284 (2.2020)	loss 3.5261 (3.1430)	grad_norm 2.5226 (2.5106)	
[2022-01-25 09:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1240/1251]	eta 0:00:24 lr 0.000102	time 1.5363 (2.2010)	loss 2.6808 (3.1439)	grad_norm 2.0642 (2.5098)	
[2022-01-25 09:44:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [240/300][1250/1251]	eta 0:00:02 lr 0.000102	time 1.3498 (2.1957)	loss 2.5898 (3.1436)	grad_norm 2.0699 (2.5098)	
[2022-01-25 09:44:40 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 240 training takes 0:45:47
[2022-01-25 09:44:40 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_240 saving......
[2022-01-25 09:44:52 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_240 saved !!!
[2022-01-25 09:45:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 12.674 (12.674)	Loss 0.7978 (0.7978)	Acc@1 80.762 (80.762)	Acc@5 95.312 (95.312)	
[2022-01-25 09:45:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 5.144 (2.747)	Loss 0.8025 (0.8550)	Acc@1 80.371 (79.652)	Acc@5 95.898 (94.789)	
[2022-01-25 09:45:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.315 (2.297)	Loss 0.8432 (0.8476)	Acc@1 81.250 (79.985)	Acc@5 95.215 (94.968)	
[2022-01-25 09:45:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.358 (2.028)	Loss 0.8279 (0.8425)	Acc@1 81.055 (80.182)	Acc@5 95.312 (94.982)	
[2022-01-25 09:46:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.728 (1.945)	Loss 0.7870 (0.8431)	Acc@1 82.227 (80.119)	Acc@5 95.410 (95.070)	
[2022-01-25 09:46:19 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.056 Acc@5 95.104
[2022-01-25 09:46:19 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.1%
[2022-01-25 09:46:19 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.06%
[2022-01-25 09:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][0/1251]	eta 7:53:26 lr 0.000102	time 22.7069 (22.7069)	loss 3.1795 (3.1795)	grad_norm 2.4521 (2.4521)	
[2022-01-25 09:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][10/1251]	eta 1:24:01 lr 0.000101	time 2.0596 (4.0623)	loss 2.7249 (2.8975)	grad_norm 2.4075 (2.3606)	
[2022-01-25 09:47:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][20/1251]	eta 1:05:59 lr 0.000101	time 1.4446 (3.2167)	loss 3.5472 (2.9722)	grad_norm 2.5757 (2.4223)	
[2022-01-25 09:47:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][30/1251]	eta 0:59:19 lr 0.000101	time 1.3924 (2.9153)	loss 3.5622 (3.0804)	grad_norm 2.2860 (2.4111)	
[2022-01-25 09:48:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][40/1251]	eta 0:56:07 lr 0.000101	time 3.6283 (2.7810)	loss 3.1770 (3.0955)	grad_norm 1.9434 (2.3987)	
[2022-01-25 09:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][50/1251]	eta 0:53:32 lr 0.000101	time 2.3613 (2.6749)	loss 3.0542 (3.0971)	grad_norm 2.2143 (2.3867)	
[2022-01-25 09:48:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][60/1251]	eta 0:51:34 lr 0.000101	time 1.5925 (2.5981)	loss 3.2810 (3.1031)	grad_norm 2.4043 (2.3892)	
[2022-01-25 09:49:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][70/1251]	eta 0:49:41 lr 0.000101	time 1.6004 (2.5242)	loss 2.2318 (3.0816)	grad_norm 2.2017 (2.4185)	
[2022-01-25 09:49:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][80/1251]	eta 0:48:23 lr 0.000101	time 2.4863 (2.4795)	loss 3.4800 (3.0816)	grad_norm 2.3206 (2.4480)	
[2022-01-25 09:50:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][90/1251]	eta 0:47:17 lr 0.000101	time 1.6226 (2.4439)	loss 3.1958 (3.1173)	grad_norm 2.5818 (2.4491)	
[2022-01-25 09:50:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][100/1251]	eta 0:46:29 lr 0.000101	time 1.5918 (2.4235)	loss 3.4727 (3.1398)	grad_norm 2.3889 (2.4652)	
[2022-01-25 09:50:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][110/1251]	eta 0:45:45 lr 0.000101	time 1.6369 (2.4065)	loss 2.8185 (3.1517)	grad_norm 2.3910 (2.4668)	
[2022-01-25 09:51:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][120/1251]	eta 0:45:00 lr 0.000101	time 3.3947 (2.3874)	loss 2.1529 (3.1512)	grad_norm 3.2111 (2.4784)	
[2022-01-25 09:51:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][130/1251]	eta 0:44:16 lr 0.000101	time 1.7148 (2.3693)	loss 3.2353 (3.1655)	grad_norm 2.5117 (2.4846)	
[2022-01-25 09:51:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][140/1251]	eta 0:43:33 lr 0.000101	time 1.7457 (2.3528)	loss 3.5860 (3.1593)	grad_norm 2.7923 (2.4871)	
[2022-01-25 09:52:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][150/1251]	eta 0:42:52 lr 0.000101	time 2.0009 (2.3365)	loss 3.6733 (3.1708)	grad_norm 2.3988 (2.4844)	
[2022-01-25 09:52:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][160/1251]	eta 0:42:27 lr 0.000101	time 2.8995 (2.3346)	loss 3.2167 (3.1713)	grad_norm 2.3437 (2.4913)	
[2022-01-25 09:52:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][170/1251]	eta 0:41:55 lr 0.000101	time 2.0121 (2.3270)	loss 3.4066 (3.1649)	grad_norm 2.3360 (2.4875)	
[2022-01-25 09:53:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][180/1251]	eta 0:41:30 lr 0.000101	time 1.6639 (2.3255)	loss 3.3547 (3.1638)	grad_norm 2.9326 (2.4861)	
[2022-01-25 09:53:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][190/1251]	eta 0:40:51 lr 0.000101	time 2.2172 (2.3106)	loss 3.2324 (3.1552)	grad_norm 2.0503 (2.4929)	
[2022-01-25 09:54:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][200/1251]	eta 0:40:15 lr 0.000101	time 1.6549 (2.2981)	loss 3.5477 (3.1515)	grad_norm 3.0249 (2.4960)	
[2022-01-25 09:54:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][210/1251]	eta 0:39:58 lr 0.000101	time 2.2789 (2.3037)	loss 3.5898 (3.1589)	grad_norm 2.3467 (2.4960)	
[2022-01-25 09:54:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][220/1251]	eta 0:39:34 lr 0.000101	time 2.1547 (2.3027)	loss 3.4922 (3.1599)	grad_norm 2.8721 (2.4993)	
[2022-01-25 09:55:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][230/1251]	eta 0:39:06 lr 0.000101	time 2.3468 (2.2987)	loss 3.3797 (3.1625)	grad_norm 2.2318 (2.5041)	
[2022-01-25 09:55:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][240/1251]	eta 0:38:37 lr 0.000101	time 1.6701 (2.2923)	loss 3.4755 (3.1605)	grad_norm 2.5578 (2.4978)	
[2022-01-25 09:55:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][250/1251]	eta 0:38:07 lr 0.000101	time 1.6144 (2.2855)	loss 3.1356 (3.1591)	grad_norm 2.6104 (2.5001)	
[2022-01-25 09:56:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][260/1251]	eta 0:37:34 lr 0.000101	time 1.9644 (2.2748)	loss 3.0691 (3.1621)	grad_norm 2.1211 (2.4927)	
[2022-01-25 09:56:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][270/1251]	eta 0:37:13 lr 0.000101	time 2.7339 (2.2767)	loss 1.9737 (3.1623)	grad_norm 2.3154 (2.4916)	
[2022-01-25 09:56:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][280/1251]	eta 0:36:43 lr 0.000101	time 1.9361 (2.2698)	loss 2.8133 (3.1512)	grad_norm 2.6018 (2.4903)	
[2022-01-25 09:57:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][290/1251]	eta 0:36:21 lr 0.000101	time 1.8633 (2.2704)	loss 3.8552 (3.1509)	grad_norm 2.5003 (2.4887)	
[2022-01-25 09:57:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][300/1251]	eta 0:35:57 lr 0.000101	time 2.2570 (2.2687)	loss 3.1372 (3.1495)	grad_norm 2.4080 (2.4874)	
[2022-01-25 09:58:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][310/1251]	eta 0:35:32 lr 0.000101	time 2.2016 (2.2666)	loss 2.3430 (3.1447)	grad_norm 2.4574 (2.4892)	
[2022-01-25 09:58:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][320/1251]	eta 0:35:03 lr 0.000101	time 1.7029 (2.2597)	loss 3.6883 (3.1399)	grad_norm 2.3088 (2.4870)	
[2022-01-25 09:58:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][330/1251]	eta 0:34:44 lr 0.000101	time 2.0418 (2.2634)	loss 2.5753 (3.1380)	grad_norm 2.7708 (2.4864)	
[2022-01-25 09:59:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][340/1251]	eta 0:34:20 lr 0.000101	time 1.6370 (2.2614)	loss 2.6062 (3.1341)	grad_norm 2.5530 (2.4888)	
[2022-01-25 09:59:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][350/1251]	eta 0:33:54 lr 0.000101	time 1.9423 (2.2586)	loss 3.2254 (3.1406)	grad_norm 2.3399 (2.4867)	
[2022-01-25 09:59:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][360/1251]	eta 0:33:28 lr 0.000101	time 1.7477 (2.2541)	loss 3.1309 (3.1400)	grad_norm 2.4445 (2.4878)	
[2022-01-25 10:00:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][370/1251]	eta 0:33:04 lr 0.000101	time 1.9893 (2.2520)	loss 2.0719 (3.1374)	grad_norm 2.3995 (2.4899)	
[2022-01-25 10:00:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][380/1251]	eta 0:32:37 lr 0.000101	time 2.5259 (2.2470)	loss 2.2574 (3.1388)	grad_norm 2.2999 (2.4891)	
[2022-01-25 10:00:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][390/1251]	eta 0:32:10 lr 0.000101	time 1.9123 (2.2420)	loss 3.3841 (3.1417)	grad_norm 2.4338 (2.4900)	
[2022-01-25 10:01:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][400/1251]	eta 0:31:41 lr 0.000101	time 2.2894 (2.2347)	loss 3.7821 (3.1402)	grad_norm 2.6521 (2.4996)	
[2022-01-25 10:01:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][410/1251]	eta 0:31:18 lr 0.000101	time 2.4330 (2.2340)	loss 3.1415 (3.1426)	grad_norm 2.8201 (2.5021)	
[2022-01-25 10:01:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][420/1251]	eta 0:30:54 lr 0.000101	time 1.7200 (2.2318)	loss 3.6479 (3.1460)	grad_norm 2.5107 (2.5104)	
[2022-01-25 10:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][430/1251]	eta 0:30:30 lr 0.000100	time 1.6163 (2.2295)	loss 2.5333 (3.1452)	grad_norm 2.7242 (2.5119)	
[2022-01-25 10:02:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][440/1251]	eta 0:30:12 lr 0.000100	time 2.7553 (2.2344)	loss 3.3788 (3.1510)	grad_norm 2.3537 (2.5103)	
[2022-01-25 10:03:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][450/1251]	eta 0:29:52 lr 0.000100	time 2.1967 (2.2373)	loss 3.3411 (3.1518)	grad_norm 2.7256 (2.5090)	
[2022-01-25 10:03:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][460/1251]	eta 0:29:29 lr 0.000100	time 2.5276 (2.2365)	loss 3.4875 (3.1527)	grad_norm 2.4704 (2.5069)	
[2022-01-25 10:03:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][470/1251]	eta 0:29:06 lr 0.000100	time 2.2458 (2.2368)	loss 2.5965 (3.1560)	grad_norm 2.8805 (2.5051)	
[2022-01-25 10:04:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][480/1251]	eta 0:28:43 lr 0.000100	time 2.7278 (2.2353)	loss 2.5103 (3.1559)	grad_norm 2.6243 (2.5035)	
[2022-01-25 10:04:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][490/1251]	eta 0:28:18 lr 0.000100	time 1.9885 (2.2324)	loss 3.7699 (3.1614)	grad_norm 2.5412 (2.5037)	
[2022-01-25 10:04:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][500/1251]	eta 0:27:55 lr 0.000100	time 2.7289 (2.2311)	loss 2.4293 (3.1569)	grad_norm 2.2233 (2.5033)	
[2022-01-25 10:05:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][510/1251]	eta 0:27:32 lr 0.000100	time 1.8718 (2.2295)	loss 3.2934 (3.1552)	grad_norm 2.2032 (2.5009)	
[2022-01-25 10:05:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][520/1251]	eta 0:27:08 lr 0.000100	time 2.2874 (2.2278)	loss 3.1232 (3.1523)	grad_norm 2.9417 (2.5000)	
[2022-01-25 10:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][530/1251]	eta 0:26:44 lr 0.000100	time 2.3184 (2.2257)	loss 3.6699 (3.1507)	grad_norm 2.6322 (2.5067)	
[2022-01-25 10:06:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][540/1251]	eta 0:26:20 lr 0.000100	time 2.0783 (2.2236)	loss 2.5647 (3.1461)	grad_norm 2.3885 (2.5143)	
[2022-01-25 10:06:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][550/1251]	eta 0:25:58 lr 0.000100	time 1.6708 (2.2230)	loss 3.4530 (3.1452)	grad_norm 2.1122 (2.5128)	
[2022-01-25 10:07:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][560/1251]	eta 0:25:35 lr 0.000100	time 2.2306 (2.2217)	loss 3.2795 (3.1507)	grad_norm 2.3930 (2.5150)	
[2022-01-25 10:07:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][570/1251]	eta 0:25:12 lr 0.000100	time 2.6453 (2.2207)	loss 2.2201 (3.1488)	grad_norm 3.3290 (2.5185)	
[2022-01-25 10:07:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][580/1251]	eta 0:24:49 lr 0.000100	time 2.5739 (2.2195)	loss 1.9871 (3.1451)	grad_norm 2.2692 (2.5194)	
[2022-01-25 10:08:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][590/1251]	eta 0:24:27 lr 0.000100	time 1.9143 (2.2204)	loss 3.3985 (3.1447)	grad_norm 2.8730 (2.5196)	
[2022-01-25 10:08:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][600/1251]	eta 0:24:04 lr 0.000100	time 1.9778 (2.2190)	loss 3.4314 (3.1481)	grad_norm 2.1261 (2.5231)	
[2022-01-25 10:08:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][610/1251]	eta 0:23:43 lr 0.000100	time 2.5288 (2.2206)	loss 3.5135 (3.1493)	grad_norm 2.8895 (2.5225)	
[2022-01-25 10:09:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][620/1251]	eta 0:23:21 lr 0.000100	time 1.7616 (2.2203)	loss 3.0539 (3.1488)	grad_norm 2.9100 (2.5231)	
[2022-01-25 10:09:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][630/1251]	eta 0:22:58 lr 0.000100	time 2.4591 (2.2204)	loss 3.4832 (3.1476)	grad_norm 2.7225 (2.5229)	
[2022-01-25 10:09:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][640/1251]	eta 0:22:34 lr 0.000100	time 1.8275 (2.2161)	loss 3.1875 (3.1455)	grad_norm 2.1456 (2.5218)	
[2022-01-25 10:10:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][650/1251]	eta 0:22:10 lr 0.000100	time 1.9392 (2.2141)	loss 2.5240 (3.1440)	grad_norm 2.4548 (2.5217)	
[2022-01-25 10:10:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][660/1251]	eta 0:21:48 lr 0.000100	time 1.7901 (2.2136)	loss 3.3574 (3.1459)	grad_norm 2.4627 (2.5234)	
[2022-01-25 10:11:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][670/1251]	eta 0:21:29 lr 0.000100	time 6.5860 (2.2193)	loss 2.8346 (3.1477)	grad_norm 2.1299 (2.5229)	
[2022-01-25 10:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][680/1251]	eta 0:21:05 lr 0.000100	time 1.5866 (2.2171)	loss 3.0986 (3.1441)	grad_norm 2.7667 (2.5226)	
[2022-01-25 10:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][690/1251]	eta 0:20:44 lr 0.000100	time 2.6218 (2.2177)	loss 3.4734 (3.1391)	grad_norm 2.4673 (2.5248)	
[2022-01-25 10:12:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][700/1251]	eta 0:20:20 lr 0.000100	time 1.5648 (2.2156)	loss 2.7353 (3.1365)	grad_norm 3.1163 (2.5272)	
[2022-01-25 10:12:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][710/1251]	eta 0:19:57 lr 0.000100	time 2.6412 (2.2143)	loss 3.3200 (3.1390)	grad_norm 2.7130 (2.5294)	
[2022-01-25 10:12:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][720/1251]	eta 0:19:34 lr 0.000100	time 1.9367 (2.2121)	loss 3.7553 (3.1395)	grad_norm 2.0034 (2.5279)	
[2022-01-25 10:13:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][730/1251]	eta 0:19:13 lr 0.000100	time 2.7711 (2.2142)	loss 2.1211 (3.1380)	grad_norm 2.0065 (2.5276)	
[2022-01-25 10:13:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][740/1251]	eta 0:18:51 lr 0.000100	time 1.9741 (2.2144)	loss 3.1022 (3.1404)	grad_norm 2.5435 (2.5304)	
[2022-01-25 10:14:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][750/1251]	eta 0:18:28 lr 0.000100	time 3.3134 (2.2130)	loss 2.8618 (3.1419)	grad_norm 2.3108 (2.5285)	
[2022-01-25 10:14:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][760/1251]	eta 0:18:06 lr 0.000100	time 1.8320 (2.2130)	loss 3.7374 (3.1435)	grad_norm 2.3659 (2.5265)	
[2022-01-25 10:14:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][770/1251]	eta 0:17:44 lr 0.000100	time 2.5141 (2.2128)	loss 2.8805 (3.1441)	grad_norm 2.1989 (2.5250)	
[2022-01-25 10:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][780/1251]	eta 0:17:21 lr 0.000100	time 1.9224 (2.2108)	loss 3.0315 (3.1436)	grad_norm 2.4439 (2.5256)	
[2022-01-25 10:15:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][790/1251]	eta 0:16:58 lr 0.000100	time 1.9226 (2.2093)	loss 3.2089 (3.1421)	grad_norm 2.3148 (2.5233)	
[2022-01-25 10:15:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][800/1251]	eta 0:16:35 lr 0.000100	time 1.9504 (2.2079)	loss 3.5259 (3.1450)	grad_norm 2.2567 (2.5223)	
[2022-01-25 10:16:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][810/1251]	eta 0:16:14 lr 0.000100	time 2.4695 (2.2089)	loss 2.1661 (3.1432)	grad_norm 2.4707 (2.5218)	
[2022-01-25 10:16:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][820/1251]	eta 0:15:52 lr 0.000100	time 1.5613 (2.2090)	loss 3.5858 (3.1419)	grad_norm 2.6640 (2.5209)	
[2022-01-25 10:16:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][830/1251]	eta 0:15:30 lr 0.000100	time 2.1142 (2.2099)	loss 2.4818 (3.1427)	grad_norm 2.4421 (2.5193)	
[2022-01-25 10:17:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][840/1251]	eta 0:15:07 lr 0.000100	time 1.7575 (2.2084)	loss 3.2634 (3.1389)	grad_norm 3.2268 (2.5195)	
[2022-01-25 10:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][850/1251]	eta 0:14:46 lr 0.000099	time 2.0232 (2.2095)	loss 3.3123 (3.1407)	grad_norm 3.0373 (2.5195)	
[2022-01-25 10:18:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][860/1251]	eta 0:14:23 lr 0.000099	time 1.5435 (2.2083)	loss 3.5272 (3.1430)	grad_norm 2.5608 (2.5200)	
[2022-01-25 10:18:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][870/1251]	eta 0:14:00 lr 0.000099	time 2.5246 (2.2070)	loss 3.2857 (3.1449)	grad_norm 2.2190 (2.5207)	
[2022-01-25 10:18:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][880/1251]	eta 0:13:38 lr 0.000099	time 1.5873 (2.2055)	loss 3.7284 (3.1486)	grad_norm 2.7203 (2.5217)	
[2022-01-25 10:19:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][890/1251]	eta 0:13:16 lr 0.000099	time 1.8410 (2.2055)	loss 3.3221 (3.1487)	grad_norm 2.6005 (2.5226)	
[2022-01-25 10:19:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][900/1251]	eta 0:12:53 lr 0.000099	time 1.8525 (2.2044)	loss 3.1116 (3.1499)	grad_norm 2.2886 (2.5223)	
[2022-01-25 10:19:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][910/1251]	eta 0:12:31 lr 0.000099	time 2.4663 (2.2048)	loss 3.0613 (3.1497)	grad_norm 2.3320 (2.5219)	
[2022-01-25 10:20:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][920/1251]	eta 0:12:10 lr 0.000099	time 2.2472 (2.2066)	loss 3.3458 (3.1508)	grad_norm 2.7958 (2.5229)	
[2022-01-25 10:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][930/1251]	eta 0:11:48 lr 0.000099	time 2.4853 (2.2069)	loss 3.3872 (3.1534)	grad_norm 2.9758 (2.5222)	
[2022-01-25 10:20:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][940/1251]	eta 0:11:26 lr 0.000099	time 2.1117 (2.2064)	loss 3.5547 (3.1535)	grad_norm 2.4803 (2.5227)	
[2022-01-25 10:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][950/1251]	eta 0:11:03 lr 0.000099	time 2.9597 (2.2058)	loss 2.1929 (3.1516)	grad_norm 2.2274 (2.5229)	
[2022-01-25 10:21:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][960/1251]	eta 0:10:41 lr 0.000099	time 1.7172 (2.2053)	loss 2.9726 (3.1509)	grad_norm 2.6623 (2.5218)	
[2022-01-25 10:21:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][970/1251]	eta 0:10:19 lr 0.000099	time 2.0723 (2.2046)	loss 3.2229 (3.1486)	grad_norm 2.7225 (2.5239)	
[2022-01-25 10:22:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][980/1251]	eta 0:09:57 lr 0.000099	time 1.6097 (2.2050)	loss 3.3847 (3.1503)	grad_norm 2.5857 (2.5233)	
[2022-01-25 10:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][990/1251]	eta 0:09:35 lr 0.000099	time 1.7684 (2.2046)	loss 2.4232 (3.1488)	grad_norm 7.1774 (2.5286)	
[2022-01-25 10:23:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1000/1251]	eta 0:09:13 lr 0.000099	time 1.8816 (2.2058)	loss 2.4116 (3.1480)	grad_norm 2.0781 (2.5301)	
[2022-01-25 10:23:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1010/1251]	eta 0:08:51 lr 0.000099	time 2.2367 (2.2056)	loss 2.0055 (3.1453)	grad_norm 2.6623 (2.5315)	
[2022-01-25 10:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1020/1251]	eta 0:08:29 lr 0.000099	time 1.6280 (2.2050)	loss 2.6422 (3.1443)	grad_norm 3.2212 (2.5311)	
[2022-01-25 10:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1030/1251]	eta 0:08:07 lr 0.000099	time 1.8069 (2.2043)	loss 3.4028 (3.1440)	grad_norm 2.5010 (2.5307)	
[2022-01-25 10:24:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1040/1251]	eta 0:07:45 lr 0.000099	time 1.9936 (2.2045)	loss 3.1713 (3.1443)	grad_norm 2.6755 (2.5305)	
[2022-01-25 10:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1050/1251]	eta 0:07:22 lr 0.000099	time 1.8533 (2.2034)	loss 3.3910 (3.1464)	grad_norm 3.0620 (2.5329)	
[2022-01-25 10:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1060/1251]	eta 0:07:00 lr 0.000099	time 2.2604 (2.2030)	loss 3.5800 (3.1458)	grad_norm 2.4696 (2.5328)	
[2022-01-25 10:25:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1070/1251]	eta 0:06:38 lr 0.000099	time 2.3257 (2.2023)	loss 2.9343 (3.1453)	grad_norm 2.5724 (2.5315)	
[2022-01-25 10:26:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1080/1251]	eta 0:06:16 lr 0.000099	time 2.5274 (2.2034)	loss 3.3301 (3.1469)	grad_norm 2.9359 (2.5311)	
[2022-01-25 10:26:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1090/1251]	eta 0:05:54 lr 0.000099	time 2.1921 (2.2023)	loss 3.5829 (3.1459)	grad_norm 2.3967 (2.5332)	
[2022-01-25 10:26:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1100/1251]	eta 0:05:32 lr 0.000099	time 2.2302 (2.2017)	loss 3.4479 (3.1443)	grad_norm 2.1991 (2.5326)	
[2022-01-25 10:27:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1110/1251]	eta 0:05:10 lr 0.000099	time 2.2546 (2.2017)	loss 3.4476 (3.1443)	grad_norm 2.2321 (2.5321)	
[2022-01-25 10:27:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1120/1251]	eta 0:04:48 lr 0.000099	time 2.3613 (2.2013)	loss 3.5095 (3.1450)	grad_norm 2.6360 (2.5328)	
[2022-01-25 10:27:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1130/1251]	eta 0:04:26 lr 0.000099	time 1.6939 (2.1998)	loss 3.9698 (3.1442)	grad_norm 2.6433 (2.5338)	
[2022-01-25 10:28:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1140/1251]	eta 0:04:04 lr 0.000099	time 2.5283 (2.1994)	loss 3.7364 (3.1438)	grad_norm 2.3532 (2.5342)	
[2022-01-25 10:28:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1150/1251]	eta 0:03:42 lr 0.000099	time 1.8272 (2.1993)	loss 3.3082 (3.1430)	grad_norm 2.3179 (2.5330)	
[2022-01-25 10:28:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1160/1251]	eta 0:03:20 lr 0.000099	time 1.6345 (2.1987)	loss 2.7970 (3.1427)	grad_norm 2.3746 (2.5327)	
[2022-01-25 10:29:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1170/1251]	eta 0:02:58 lr 0.000099	time 1.5878 (2.1982)	loss 3.3060 (3.1436)	grad_norm 2.8407 (2.5320)	
[2022-01-25 10:29:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1180/1251]	eta 0:02:36 lr 0.000099	time 2.7892 (2.1990)	loss 3.6621 (3.1438)	grad_norm 2.0861 (2.5314)	
[2022-01-25 10:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1190/1251]	eta 0:02:14 lr 0.000099	time 2.0503 (2.1987)	loss 3.3901 (3.1459)	grad_norm 2.3555 (2.5320)	
[2022-01-25 10:30:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1200/1251]	eta 0:01:52 lr 0.000099	time 2.2254 (2.1993)	loss 3.0956 (3.1447)	grad_norm 2.3913 (2.5326)	
[2022-01-25 10:30:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1210/1251]	eta 0:01:30 lr 0.000099	time 1.6324 (2.1995)	loss 2.9270 (3.1456)	grad_norm 2.5496 (2.5321)	
[2022-01-25 10:31:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1220/1251]	eta 0:01:08 lr 0.000099	time 2.4935 (2.1983)	loss 3.1525 (3.1463)	grad_norm 2.7516 (2.5330)	
[2022-01-25 10:31:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1230/1251]	eta 0:00:46 lr 0.000099	time 2.3885 (2.1992)	loss 2.3913 (3.1450)	grad_norm 2.3960 (2.5314)	
[2022-01-25 10:31:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1240/1251]	eta 0:00:24 lr 0.000099	time 1.3883 (2.1985)	loss 3.5973 (3.1467)	grad_norm 2.5221 (2.5303)	
[2022-01-25 10:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [241/300][1250/1251]	eta 0:00:02 lr 0.000099	time 1.1627 (2.1933)	loss 3.0019 (3.1485)	grad_norm 2.6380 (2.5313)	
[2022-01-25 10:32:03 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 241 training takes 0:45:44
[2022-01-25 10:32:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.969 (17.969)	Loss 0.8704 (0.8704)	Acc@1 80.078 (80.078)	Acc@5 94.238 (94.238)	
[2022-01-25 10:32:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.950 (3.566)	Loss 0.8612 (0.8533)	Acc@1 78.516 (79.679)	Acc@5 95.020 (95.162)	
[2022-01-25 10:32:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.583 (2.561)	Loss 0.8320 (0.8440)	Acc@1 81.934 (80.046)	Acc@5 94.824 (95.257)	
[2022-01-25 10:33:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.992 (2.311)	Loss 0.8614 (0.8466)	Acc@1 80.371 (79.968)	Acc@5 95.020 (95.183)	
[2022-01-25 10:33:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.652 (2.121)	Loss 0.8234 (0.8481)	Acc@1 80.664 (79.921)	Acc@5 95.703 (95.160)	
[2022-01-25 10:33:38 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 79.916 Acc@5 95.166
[2022-01-25 10:33:38 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 79.9%
[2022-01-25 10:33:38 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.06%
[2022-01-25 10:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][0/1251]	eta 7:27:43 lr 0.000099	time 21.4734 (21.4734)	loss 3.4207 (3.4207)	grad_norm 2.4850 (2.4850)	
[2022-01-25 10:34:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][10/1251]	eta 1:25:05 lr 0.000099	time 1.7274 (4.1142)	loss 3.0752 (2.9072)	grad_norm 2.5080 (2.4365)	
[2022-01-25 10:34:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][20/1251]	eta 1:05:54 lr 0.000098	time 2.6868 (3.2124)	loss 2.4842 (2.9876)	grad_norm 2.3381 (2.4489)	
[2022-01-25 10:35:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][30/1251]	eta 0:57:47 lr 0.000098	time 1.5934 (2.8398)	loss 2.7366 (3.1271)	grad_norm 2.6542 (2.4660)	
[2022-01-25 10:35:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][40/1251]	eta 0:54:28 lr 0.000098	time 3.7714 (2.6991)	loss 2.9097 (3.1082)	grad_norm 2.1777 (2.4573)	
[2022-01-25 10:35:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][50/1251]	eta 0:52:58 lr 0.000098	time 1.8279 (2.6467)	loss 2.0619 (3.0586)	grad_norm 2.7223 (2.4579)	
[2022-01-25 10:36:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][60/1251]	eta 0:51:29 lr 0.000098	time 2.6845 (2.5941)	loss 3.6932 (3.0389)	grad_norm 2.4476 (2.4746)	
[2022-01-25 10:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][70/1251]	eta 0:49:40 lr 0.000098	time 1.9677 (2.5241)	loss 3.5694 (3.0657)	grad_norm 2.4136 (2.4789)	
[2022-01-25 10:37:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][80/1251]	eta 0:48:39 lr 0.000098	time 2.9072 (2.4929)	loss 3.6769 (3.0849)	grad_norm 2.4323 (2.4713)	
[2022-01-25 10:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][90/1251]	eta 0:47:47 lr 0.000098	time 2.1914 (2.4700)	loss 2.8509 (3.1061)	grad_norm 2.4040 (2.4802)	
[2022-01-25 10:37:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][100/1251]	eta 0:46:33 lr 0.000098	time 1.7618 (2.4266)	loss 3.5775 (3.0991)	grad_norm 2.3735 (2.4693)	
[2022-01-25 10:38:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][110/1251]	eta 0:45:31 lr 0.000098	time 1.9356 (2.3938)	loss 3.3510 (3.1069)	grad_norm 2.2397 (2.4655)	
[2022-01-25 10:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][120/1251]	eta 0:44:45 lr 0.000098	time 1.9738 (2.3746)	loss 3.5422 (3.1117)	grad_norm 2.5722 (2.4676)	
[2022-01-25 10:38:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][130/1251]	eta 0:44:13 lr 0.000098	time 2.4905 (2.3670)	loss 2.5138 (3.1137)	grad_norm 2.6265 (2.4725)	
[2022-01-25 10:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][140/1251]	eta 0:43:31 lr 0.000098	time 1.6506 (2.3508)	loss 3.4810 (3.0983)	grad_norm 2.5402 (2.4538)	
[2022-01-25 10:39:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][150/1251]	eta 0:42:59 lr 0.000098	time 1.7494 (2.3430)	loss 3.1953 (3.1112)	grad_norm 2.6741 (2.4618)	
[2022-01-25 10:39:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][160/1251]	eta 0:42:25 lr 0.000098	time 2.5731 (2.3328)	loss 2.5621 (3.1135)	grad_norm 2.8504 (2.4663)	
[2022-01-25 10:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][170/1251]	eta 0:41:45 lr 0.000098	time 2.0057 (2.3179)	loss 3.7360 (3.1195)	grad_norm 2.6570 (2.4655)	
[2022-01-25 10:40:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][180/1251]	eta 0:41:07 lr 0.000098	time 2.0444 (2.3038)	loss 3.3480 (3.1120)	grad_norm 2.7323 (2.4650)	
[2022-01-25 10:40:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][190/1251]	eta 0:40:31 lr 0.000098	time 1.6321 (2.2918)	loss 3.4907 (3.1070)	grad_norm 2.3754 (2.4679)	
[2022-01-25 10:41:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][200/1251]	eta 0:40:04 lr 0.000098	time 3.4549 (2.2875)	loss 3.4470 (3.1080)	grad_norm 2.9932 (2.4698)	
[2022-01-25 10:41:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][210/1251]	eta 0:39:38 lr 0.000098	time 1.5309 (2.2852)	loss 3.0078 (3.1087)	grad_norm 2.7559 (2.4766)	
[2022-01-25 10:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][220/1251]	eta 0:39:15 lr 0.000098	time 2.2318 (2.2850)	loss 3.4934 (3.1235)	grad_norm 2.3780 (2.4774)	
[2022-01-25 10:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][230/1251]	eta 0:38:47 lr 0.000098	time 1.5575 (2.2798)	loss 3.4362 (3.1263)	grad_norm 2.5778 (2.4766)	
[2022-01-25 10:42:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][240/1251]	eta 0:38:27 lr 0.000098	time 3.6529 (2.2826)	loss 3.0332 (3.1072)	grad_norm 2.6494 (2.4784)	
[2022-01-25 10:43:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][250/1251]	eta 0:38:08 lr 0.000098	time 1.8672 (2.2861)	loss 3.4269 (3.1128)	grad_norm 2.5215 (2.4815)	
[2022-01-25 10:43:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][260/1251]	eta 0:37:36 lr 0.000098	time 1.6002 (2.2774)	loss 3.3470 (3.1120)	grad_norm 2.3261 (2.4854)	
[2022-01-25 10:43:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][270/1251]	eta 0:37:06 lr 0.000098	time 1.7712 (2.2692)	loss 3.1638 (3.1070)	grad_norm 2.1792 (2.4849)	
[2022-01-25 10:44:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][280/1251]	eta 0:36:40 lr 0.000098	time 2.8301 (2.2662)	loss 2.2915 (3.1039)	grad_norm 2.4663 (2.4865)	
[2022-01-25 10:44:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][290/1251]	eta 0:36:14 lr 0.000098	time 1.8233 (2.2624)	loss 3.6045 (3.0998)	grad_norm 2.7454 (2.4849)	
[2022-01-25 10:44:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][300/1251]	eta 0:35:46 lr 0.000098	time 1.5952 (2.2572)	loss 3.3479 (3.0999)	grad_norm 2.5741 (2.4862)	
[2022-01-25 10:45:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][310/1251]	eta 0:35:18 lr 0.000098	time 1.7761 (2.2518)	loss 2.5750 (3.0924)	grad_norm 2.5156 (2.4897)	
[2022-01-25 10:45:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][320/1251]	eta 0:34:51 lr 0.000098	time 2.2475 (2.2470)	loss 3.9922 (3.0959)	grad_norm 2.3719 (2.4869)	
[2022-01-25 10:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][330/1251]	eta 0:34:24 lr 0.000098	time 1.5934 (2.2412)	loss 3.6706 (3.1001)	grad_norm 2.2814 (2.4823)	
[2022-01-25 10:46:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][340/1251]	eta 0:34:01 lr 0.000098	time 2.0241 (2.2410)	loss 3.4664 (3.1028)	grad_norm 2.1765 (2.4816)	
[2022-01-25 10:46:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][350/1251]	eta 0:33:40 lr 0.000098	time 2.5778 (2.2428)	loss 3.7375 (3.1023)	grad_norm 2.2082 (2.4858)	
[2022-01-25 10:47:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][360/1251]	eta 0:33:18 lr 0.000098	time 2.5501 (2.2431)	loss 3.3497 (3.1036)	grad_norm 2.4749 (2.4864)	
[2022-01-25 10:47:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][370/1251]	eta 0:32:55 lr 0.000098	time 1.8683 (2.2418)	loss 3.4109 (3.0992)	grad_norm 2.3133 (2.4858)	
[2022-01-25 10:47:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][380/1251]	eta 0:32:33 lr 0.000098	time 2.0647 (2.2428)	loss 3.8145 (3.1009)	grad_norm 2.5234 (2.4870)	
[2022-01-25 10:48:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][390/1251]	eta 0:32:11 lr 0.000098	time 2.7544 (2.2433)	loss 2.8765 (3.0992)	grad_norm 2.8006 (2.4924)	
[2022-01-25 10:48:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][400/1251]	eta 0:31:47 lr 0.000098	time 1.7224 (2.2410)	loss 3.8284 (3.0967)	grad_norm 2.6963 (2.4935)	
[2022-01-25 10:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][410/1251]	eta 0:31:25 lr 0.000098	time 1.8294 (2.2414)	loss 3.7369 (3.1016)	grad_norm 3.1534 (2.4990)	
[2022-01-25 10:49:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][420/1251]	eta 0:30:59 lr 0.000098	time 2.2805 (2.2375)	loss 3.4303 (3.1049)	grad_norm 2.4181 (2.5019)	
[2022-01-25 10:49:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][430/1251]	eta 0:30:36 lr 0.000098	time 2.3236 (2.2363)	loss 3.6228 (3.1050)	grad_norm 2.5002 (2.5015)	
[2022-01-25 10:50:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][440/1251]	eta 0:30:10 lr 0.000097	time 1.9426 (2.2329)	loss 3.4692 (3.1076)	grad_norm 2.4925 (2.5014)	
[2022-01-25 10:50:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][450/1251]	eta 0:29:49 lr 0.000097	time 2.3478 (2.2345)	loss 3.1002 (3.1132)	grad_norm 2.3814 (2.5014)	
[2022-01-25 10:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][460/1251]	eta 0:29:29 lr 0.000097	time 1.8323 (2.2369)	loss 3.3356 (3.1083)	grad_norm 2.4280 (2.5005)	
[2022-01-25 10:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][470/1251]	eta 0:29:06 lr 0.000097	time 1.8932 (2.2367)	loss 3.5455 (3.1109)	grad_norm 2.4568 (2.5006)	
[2022-01-25 10:51:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][480/1251]	eta 0:28:44 lr 0.000097	time 1.8074 (2.2361)	loss 3.4790 (3.1123)	grad_norm 2.1573 (2.5003)	
[2022-01-25 10:51:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][490/1251]	eta 0:28:18 lr 0.000097	time 2.2030 (2.2319)	loss 2.7436 (3.1126)	grad_norm 2.7440 (2.4987)	
[2022-01-25 10:52:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][500/1251]	eta 0:27:52 lr 0.000097	time 2.1773 (2.2274)	loss 3.2796 (3.1096)	grad_norm 2.4109 (2.4994)	
[2022-01-25 10:52:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][510/1251]	eta 0:27:28 lr 0.000097	time 1.9151 (2.2243)	loss 3.2820 (3.1151)	grad_norm 2.6500 (2.5030)	
[2022-01-25 10:52:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][520/1251]	eta 0:27:07 lr 0.000097	time 2.5065 (2.2259)	loss 3.3653 (3.1180)	grad_norm 2.2824 (2.5050)	
[2022-01-25 10:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][530/1251]	eta 0:26:44 lr 0.000097	time 1.9077 (2.2251)	loss 3.4265 (3.1210)	grad_norm 2.4460 (2.5065)	
[2022-01-25 10:53:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][540/1251]	eta 0:26:22 lr 0.000097	time 2.1158 (2.2263)	loss 3.5669 (3.1190)	grad_norm 2.3360 (2.5089)	
[2022-01-25 10:54:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][550/1251]	eta 0:26:01 lr 0.000097	time 2.3720 (2.2269)	loss 2.1502 (3.1168)	grad_norm 2.2317 (2.5116)	
[2022-01-25 10:54:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][560/1251]	eta 0:25:38 lr 0.000097	time 2.2462 (2.2264)	loss 3.4761 (3.1189)	grad_norm 2.2332 (2.5142)	
[2022-01-25 10:54:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][570/1251]	eta 0:25:14 lr 0.000097	time 1.9104 (2.2240)	loss 3.5008 (3.1209)	grad_norm 2.3069 (2.5137)	
[2022-01-25 10:55:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][580/1251]	eta 0:24:51 lr 0.000097	time 1.6009 (2.2221)	loss 3.5258 (3.1219)	grad_norm 2.3954 (2.5172)	
[2022-01-25 10:55:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][590/1251]	eta 0:24:27 lr 0.000097	time 1.8011 (2.2202)	loss 3.1383 (3.1239)	grad_norm 2.7768 (2.5188)	
[2022-01-25 10:55:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][600/1251]	eta 0:24:03 lr 0.000097	time 2.2801 (2.2175)	loss 3.4641 (3.1224)	grad_norm 3.5699 (2.5210)	
[2022-01-25 10:56:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][610/1251]	eta 0:23:40 lr 0.000097	time 2.4975 (2.2158)	loss 3.7760 (3.1242)	grad_norm 2.5378 (2.5236)	
[2022-01-25 10:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][620/1251]	eta 0:23:16 lr 0.000097	time 1.6849 (2.2125)	loss 2.2165 (3.1258)	grad_norm 2.5242 (2.5259)	
[2022-01-25 10:56:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][630/1251]	eta 0:22:53 lr 0.000097	time 2.2550 (2.2118)	loss 2.5275 (3.1261)	grad_norm 2.9736 (2.5272)	
[2022-01-25 10:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][640/1251]	eta 0:22:30 lr 0.000097	time 2.0257 (2.2105)	loss 2.5744 (3.1250)	grad_norm 3.0554 (2.5270)	
[2022-01-25 10:57:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][650/1251]	eta 0:22:09 lr 0.000097	time 2.1645 (2.2113)	loss 3.2306 (3.1265)	grad_norm 2.4361 (2.5275)	
[2022-01-25 10:58:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][660/1251]	eta 0:21:47 lr 0.000097	time 2.0449 (2.2121)	loss 3.2094 (3.1265)	grad_norm 2.3123 (2.5268)	
[2022-01-25 10:58:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][670/1251]	eta 0:21:25 lr 0.000097	time 2.2824 (2.2128)	loss 3.1112 (3.1282)	grad_norm 3.0180 (2.5290)	
[2022-01-25 10:58:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][680/1251]	eta 0:21:03 lr 0.000097	time 2.1318 (2.2136)	loss 3.4936 (3.1271)	grad_norm 2.4074 (2.5304)	
[2022-01-25 10:59:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][690/1251]	eta 0:20:42 lr 0.000097	time 2.5059 (2.2155)	loss 2.5017 (3.1250)	grad_norm 2.9593 (2.5287)	
[2022-01-25 10:59:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][700/1251]	eta 0:20:21 lr 0.000097	time 1.8249 (2.2164)	loss 3.4470 (3.1236)	grad_norm 2.4919 (2.5308)	
[2022-01-25 10:59:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][710/1251]	eta 0:19:58 lr 0.000097	time 2.5221 (2.2146)	loss 2.2843 (3.1181)	grad_norm 2.3747 (2.5299)	
[2022-01-25 11:00:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][720/1251]	eta 0:19:34 lr 0.000097	time 1.5401 (2.2124)	loss 3.5045 (3.1164)	grad_norm 2.3589 (2.5293)	
[2022-01-25 11:00:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][730/1251]	eta 0:19:12 lr 0.000097	time 2.1531 (2.2121)	loss 2.7853 (3.1201)	grad_norm 2.3185 (2.5289)	
[2022-01-25 11:00:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][740/1251]	eta 0:18:50 lr 0.000097	time 2.2133 (2.2119)	loss 3.1986 (3.1198)	grad_norm 2.4130 (2.5292)	
[2022-01-25 11:01:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][750/1251]	eta 0:18:28 lr 0.000097	time 1.9447 (2.2132)	loss 3.4516 (3.1227)	grad_norm 3.0356 (2.5329)	
[2022-01-25 11:01:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][760/1251]	eta 0:18:05 lr 0.000097	time 2.1664 (2.2117)	loss 3.4745 (3.1257)	grad_norm 2.2341 (2.5329)	
[2022-01-25 11:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][770/1251]	eta 0:17:43 lr 0.000097	time 2.0100 (2.2100)	loss 3.1368 (3.1263)	grad_norm 2.4349 (2.5324)	
[2022-01-25 11:02:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][780/1251]	eta 0:17:22 lr 0.000097	time 2.4549 (2.2126)	loss 3.4098 (3.1241)	grad_norm 2.3619 (2.5316)	
[2022-01-25 11:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][790/1251]	eta 0:16:59 lr 0.000097	time 1.6580 (2.2109)	loss 3.4357 (3.1256)	grad_norm 2.4127 (2.5327)	
[2022-01-25 11:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][800/1251]	eta 0:16:38 lr 0.000097	time 3.1094 (2.2133)	loss 3.6001 (3.1271)	grad_norm 2.1476 (2.5332)	
[2022-01-25 11:03:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][810/1251]	eta 0:16:16 lr 0.000097	time 1.8793 (2.2144)	loss 2.3470 (3.1287)	grad_norm 2.3129 (2.5333)	
[2022-01-25 11:03:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][820/1251]	eta 0:15:55 lr 0.000097	time 2.4889 (2.2179)	loss 2.5106 (3.1272)	grad_norm 2.1315 (2.5330)	
[2022-01-25 11:04:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][830/1251]	eta 0:15:33 lr 0.000097	time 1.6850 (2.2171)	loss 3.7074 (3.1263)	grad_norm 2.3732 (2.5316)	
[2022-01-25 11:04:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][840/1251]	eta 0:15:10 lr 0.000097	time 1.8506 (2.2148)	loss 3.3498 (3.1267)	grad_norm 2.2837 (2.5303)	
[2022-01-25 11:05:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][850/1251]	eta 0:14:47 lr 0.000097	time 1.8209 (2.2126)	loss 3.4443 (3.1254)	grad_norm 2.4688 (2.5293)	
[2022-01-25 11:05:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][860/1251]	eta 0:14:25 lr 0.000097	time 1.9086 (2.2133)	loss 3.5675 (3.1269)	grad_norm 2.5982 (2.5303)	
[2022-01-25 11:05:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][870/1251]	eta 0:14:02 lr 0.000096	time 1.6032 (2.2123)	loss 3.4217 (3.1241)	grad_norm 2.5960 (2.5311)	
[2022-01-25 11:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][880/1251]	eta 0:13:40 lr 0.000096	time 1.9284 (2.2114)	loss 3.0049 (3.1231)	grad_norm 2.7987 (2.5320)	
[2022-01-25 11:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][890/1251]	eta 0:13:18 lr 0.000096	time 1.9336 (2.2114)	loss 3.2814 (3.1213)	grad_norm 2.2596 (2.5342)	
[2022-01-25 11:06:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][900/1251]	eta 0:12:57 lr 0.000096	time 2.0282 (2.2141)	loss 2.4584 (3.1194)	grad_norm 1.9587 (2.5321)	
[2022-01-25 11:07:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][910/1251]	eta 0:12:34 lr 0.000096	time 1.9379 (2.2132)	loss 3.3711 (3.1184)	grad_norm 2.8264 (2.5325)	
[2022-01-25 11:07:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][920/1251]	eta 0:12:12 lr 0.000096	time 1.5798 (2.2121)	loss 3.5438 (3.1168)	grad_norm 2.6835 (2.5313)	
[2022-01-25 11:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][930/1251]	eta 0:11:49 lr 0.000096	time 1.8499 (2.2110)	loss 3.4032 (3.1175)	grad_norm 2.7168 (2.5310)	
[2022-01-25 11:08:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][940/1251]	eta 0:11:27 lr 0.000096	time 1.7493 (2.2115)	loss 3.2430 (3.1151)	grad_norm 2.3995 (2.5305)	
[2022-01-25 11:08:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][950/1251]	eta 0:11:05 lr 0.000096	time 1.9707 (2.2104)	loss 3.2304 (3.1147)	grad_norm 2.5692 (2.5306)	
[2022-01-25 11:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][960/1251]	eta 0:10:42 lr 0.000096	time 1.9167 (2.2093)	loss 3.5273 (3.1160)	grad_norm 2.2872 (2.5303)	
[2022-01-25 11:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][970/1251]	eta 0:10:21 lr 0.000096	time 2.4551 (2.2106)	loss 2.4558 (3.1175)	grad_norm 2.0474 (2.5286)	
[2022-01-25 11:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][980/1251]	eta 0:09:59 lr 0.000096	time 2.1407 (2.2128)	loss 3.3429 (3.1169)	grad_norm 2.5351 (2.5281)	
[2022-01-25 11:10:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][990/1251]	eta 0:09:37 lr 0.000096	time 1.6146 (2.2123)	loss 3.6354 (3.1178)	grad_norm 2.6969 (2.5288)	
[2022-01-25 11:10:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1000/1251]	eta 0:09:15 lr 0.000096	time 1.8412 (2.2128)	loss 3.1931 (3.1199)	grad_norm 2.3118 (2.5287)	
[2022-01-25 11:10:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1010/1251]	eta 0:08:52 lr 0.000096	time 1.9976 (2.2110)	loss 2.4399 (3.1192)	grad_norm 2.2073 (2.5281)	
[2022-01-25 11:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1020/1251]	eta 0:08:30 lr 0.000096	time 1.8200 (2.2082)	loss 3.5833 (3.1186)	grad_norm 2.4325 (2.5277)	
[2022-01-25 11:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1030/1251]	eta 0:08:07 lr 0.000096	time 1.6925 (2.2071)	loss 3.4252 (3.1190)	grad_norm 2.4733 (2.5279)	
[2022-01-25 11:11:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1040/1251]	eta 0:07:45 lr 0.000096	time 1.9017 (2.2075)	loss 2.4642 (3.1184)	grad_norm 2.8678 (2.5275)	
[2022-01-25 11:12:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1050/1251]	eta 0:07:23 lr 0.000096	time 2.0592 (2.2080)	loss 2.6614 (3.1162)	grad_norm 2.6304 (2.5272)	
[2022-01-25 11:12:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1060/1251]	eta 0:07:01 lr 0.000096	time 1.6384 (2.2071)	loss 3.6207 (3.1159)	grad_norm 2.2930 (2.5272)	
[2022-01-25 11:13:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1070/1251]	eta 0:06:39 lr 0.000096	time 2.2757 (2.2063)	loss 2.3589 (3.1156)	grad_norm 2.3354 (2.5261)	
[2022-01-25 11:13:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1080/1251]	eta 0:06:17 lr 0.000096	time 1.9554 (2.2070)	loss 3.6886 (3.1164)	grad_norm 2.6916 (2.5260)	
[2022-01-25 11:13:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1090/1251]	eta 0:05:55 lr 0.000096	time 1.9117 (2.2065)	loss 3.5384 (3.1169)	grad_norm 2.5860 (2.5252)	
[2022-01-25 11:14:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1100/1251]	eta 0:05:33 lr 0.000096	time 1.9056 (2.2075)	loss 1.9059 (3.1126)	grad_norm 2.2239 (2.5264)	
[2022-01-25 11:14:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1110/1251]	eta 0:05:11 lr 0.000096	time 2.3848 (2.2082)	loss 2.1495 (3.1111)	grad_norm 2.6609 (2.5258)	
[2022-01-25 11:14:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1120/1251]	eta 0:04:49 lr 0.000096	time 1.8765 (2.2085)	loss 2.2787 (3.1096)	grad_norm 2.3243 (2.5260)	
[2022-01-25 11:15:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1130/1251]	eta 0:04:27 lr 0.000096	time 1.5945 (2.2076)	loss 3.6430 (3.1088)	grad_norm 2.5034 (2.5255)	
[2022-01-25 11:15:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1140/1251]	eta 0:04:04 lr 0.000096	time 2.2141 (2.2064)	loss 2.3096 (3.1080)	grad_norm 2.6082 (2.5247)	
[2022-01-25 11:15:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1150/1251]	eta 0:03:42 lr 0.000096	time 1.8553 (2.2054)	loss 2.4835 (3.1072)	grad_norm 2.5663 (2.5254)	
[2022-01-25 11:16:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1160/1251]	eta 0:03:20 lr 0.000096	time 2.4410 (2.2060)	loss 3.2722 (3.1072)	grad_norm 2.1621 (2.5252)	
[2022-01-25 11:16:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1170/1251]	eta 0:02:58 lr 0.000096	time 2.0340 (2.2060)	loss 3.7355 (3.1065)	grad_norm 2.6683 (2.5261)	
[2022-01-25 11:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1180/1251]	eta 0:02:36 lr 0.000096	time 2.3328 (2.2063)	loss 3.1617 (3.1062)	grad_norm 2.6462 (2.5274)	
[2022-01-25 11:17:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1190/1251]	eta 0:02:14 lr 0.000096	time 1.8488 (2.2063)	loss 3.5108 (3.1060)	grad_norm 3.2528 (2.5283)	
[2022-01-25 11:17:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1200/1251]	eta 0:01:52 lr 0.000096	time 2.4127 (2.2061)	loss 3.2213 (3.1044)	grad_norm 2.4820 (2.5300)	
[2022-01-25 11:18:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1210/1251]	eta 0:01:30 lr 0.000096	time 2.2067 (2.2048)	loss 3.4183 (3.1054)	grad_norm 2.3211 (2.5296)	
[2022-01-25 11:18:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1220/1251]	eta 0:01:08 lr 0.000096	time 2.2514 (2.2044)	loss 3.5218 (3.1057)	grad_norm 2.3360 (2.5289)	
[2022-01-25 11:18:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1230/1251]	eta 0:00:46 lr 0.000096	time 2.2995 (2.2043)	loss 3.4677 (3.1065)	grad_norm 2.3641 (2.5283)	
[2022-01-25 11:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1240/1251]	eta 0:00:24 lr 0.000096	time 1.8131 (2.2034)	loss 2.0062 (3.1048)	grad_norm 2.7965 (2.5276)	
[2022-01-25 11:19:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [242/300][1250/1251]	eta 0:00:02 lr 0.000096	time 1.3106 (2.1979)	loss 2.9487 (3.1030)	grad_norm 2.2183 (2.5278)	
[2022-01-25 11:19:28 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 242 training takes 0:45:49
[2022-01-25 11:19:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.211 (18.211)	Loss 0.8038 (0.8038)	Acc@1 81.641 (81.641)	Acc@5 95.898 (95.898)	
[2022-01-25 11:20:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 2.915 (3.539)	Loss 0.8612 (0.8557)	Acc@1 81.055 (80.273)	Acc@5 94.629 (95.082)	
[2022-01-25 11:20:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.918 (2.555)	Loss 0.8595 (0.8580)	Acc@1 79.883 (80.297)	Acc@5 95.215 (95.047)	
[2022-01-25 11:20:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.581 (2.302)	Loss 0.8871 (0.8588)	Acc@1 80.762 (80.192)	Acc@5 94.141 (95.038)	
[2022-01-25 11:20:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.025 (2.197)	Loss 0.8357 (0.8534)	Acc@1 81.348 (80.266)	Acc@5 95.508 (95.177)	
[2022-01-25 11:21:04 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.178 Acc@5 95.210
[2022-01-25 11:21:04 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.2%
[2022-01-25 11:21:04 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.18%
[2022-01-25 11:21:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][0/1251]	eta 7:36:09 lr 0.000096	time 21.8784 (21.8784)	loss 3.1021 (3.1021)	grad_norm 2.3601 (2.3601)	
[2022-01-25 11:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][10/1251]	eta 1:32:46 lr 0.000096	time 3.0743 (4.4853)	loss 2.9688 (3.2863)	grad_norm 2.6042 (2.5911)	
[2022-01-25 11:22:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][20/1251]	eta 1:09:53 lr 0.000096	time 1.4254 (3.4066)	loss 3.5267 (3.3651)	grad_norm 2.2954 (2.5423)	
[2022-01-25 11:22:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][30/1251]	eta 1:01:15 lr 0.000096	time 1.7230 (3.0105)	loss 3.3673 (3.3144)	grad_norm 3.1865 (2.4930)	
[2022-01-25 11:23:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][40/1251]	eta 0:57:04 lr 0.000096	time 2.8132 (2.8281)	loss 2.8818 (3.2718)	grad_norm 2.9283 (2.5053)	
[2022-01-25 11:23:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][50/1251]	eta 0:54:34 lr 0.000095	time 3.5257 (2.7264)	loss 3.3078 (3.2740)	grad_norm 2.3230 (2.5354)	
[2022-01-25 11:23:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][60/1251]	eta 0:51:48 lr 0.000095	time 1.9475 (2.6101)	loss 3.1153 (3.2554)	grad_norm 2.4104 (2.5388)	
[2022-01-25 11:24:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][70/1251]	eta 0:49:43 lr 0.000095	time 1.8194 (2.5264)	loss 2.6685 (3.1914)	grad_norm 2.6229 (2.5706)	
[2022-01-25 11:24:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][80/1251]	eta 0:48:40 lr 0.000095	time 1.8415 (2.4943)	loss 3.8458 (3.1991)	grad_norm 2.7688 (2.5933)	
[2022-01-25 11:24:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][90/1251]	eta 0:47:56 lr 0.000095	time 2.9245 (2.4772)	loss 3.6769 (3.1998)	grad_norm 2.5670 (2.5780)	
[2022-01-25 11:25:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][100/1251]	eta 0:47:04 lr 0.000095	time 1.9454 (2.4537)	loss 3.0746 (3.2241)	grad_norm 2.3912 (2.5717)	
[2022-01-25 11:25:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][110/1251]	eta 0:46:06 lr 0.000095	time 2.1908 (2.4245)	loss 2.8207 (3.2034)	grad_norm 2.3081 (2.5670)	
[2022-01-25 11:25:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][120/1251]	eta 0:45:07 lr 0.000095	time 2.4495 (2.3938)	loss 3.8684 (3.1770)	grad_norm 3.2823 (2.5563)	
[2022-01-25 11:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][130/1251]	eta 0:44:07 lr 0.000095	time 1.8218 (2.3621)	loss 2.7454 (3.1763)	grad_norm 2.5546 (2.5644)	
[2022-01-25 11:26:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][140/1251]	eta 0:43:25 lr 0.000095	time 2.2668 (2.3452)	loss 3.5285 (3.1805)	grad_norm 3.1744 (2.5599)	
[2022-01-25 11:26:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][150/1251]	eta 0:43:05 lr 0.000095	time 2.7242 (2.3482)	loss 2.8724 (3.1759)	grad_norm 2.4629 (2.5562)	
[2022-01-25 11:27:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][160/1251]	eta 0:42:44 lr 0.000095	time 2.1218 (2.3510)	loss 3.3561 (3.1765)	grad_norm 2.1085 (2.5511)	
[2022-01-25 11:27:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][170/1251]	eta 0:42:12 lr 0.000095	time 1.8850 (2.3429)	loss 3.3084 (3.1710)	grad_norm 2.0372 (2.5513)	
[2022-01-25 11:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][180/1251]	eta 0:41:38 lr 0.000095	time 1.6752 (2.3332)	loss 2.9835 (3.1657)	grad_norm 2.5852 (2.5541)	
[2022-01-25 11:28:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][190/1251]	eta 0:41:02 lr 0.000095	time 2.7199 (2.3213)	loss 3.7315 (3.1693)	grad_norm 2.4907 (2.5473)	
[2022-01-25 11:28:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][200/1251]	eta 0:40:35 lr 0.000095	time 1.8027 (2.3176)	loss 2.3953 (3.1651)	grad_norm 2.8211 (2.5456)	
[2022-01-25 11:29:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][210/1251]	eta 0:40:03 lr 0.000095	time 2.0164 (2.3086)	loss 2.6654 (3.1727)	grad_norm 2.6373 (2.5453)	
[2022-01-25 11:29:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][220/1251]	eta 0:39:31 lr 0.000095	time 1.8388 (2.3004)	loss 3.3631 (3.1732)	grad_norm 2.9075 (2.5435)	
[2022-01-25 11:29:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][230/1251]	eta 0:39:09 lr 0.000095	time 2.3930 (2.3007)	loss 2.2265 (3.1609)	grad_norm 2.5601 (2.5384)	
[2022-01-25 11:30:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][240/1251]	eta 0:38:50 lr 0.000095	time 1.8406 (2.3052)	loss 2.5338 (3.1554)	grad_norm 2.6208 (2.5458)	
[2022-01-25 11:30:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][250/1251]	eta 0:38:17 lr 0.000095	time 1.8661 (2.2952)	loss 3.4695 (3.1574)	grad_norm 2.1997 (2.5463)	
[2022-01-25 11:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][260/1251]	eta 0:37:46 lr 0.000095	time 1.9734 (2.2869)	loss 2.6624 (3.1547)	grad_norm 2.2089 (2.5502)	
[2022-01-25 11:31:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][270/1251]	eta 0:37:20 lr 0.000095	time 1.8691 (2.2838)	loss 3.4605 (3.1544)	grad_norm 2.2207 (2.5515)	
[2022-01-25 11:31:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][280/1251]	eta 0:37:01 lr 0.000095	time 1.8287 (2.2881)	loss 3.2896 (3.1483)	grad_norm 2.2175 (2.5475)	
[2022-01-25 11:32:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][290/1251]	eta 0:36:29 lr 0.000095	time 1.9183 (2.2783)	loss 3.4917 (3.1499)	grad_norm 2.2451 (2.5436)	
[2022-01-25 11:32:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][300/1251]	eta 0:36:01 lr 0.000095	time 1.8803 (2.2725)	loss 3.7665 (3.1501)	grad_norm 2.5860 (2.5409)	
[2022-01-25 11:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][310/1251]	eta 0:35:32 lr 0.000095	time 2.1516 (2.2666)	loss 3.2115 (3.1480)	grad_norm 3.0306 (2.5406)	
[2022-01-25 11:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][320/1251]	eta 0:35:15 lr 0.000095	time 2.3438 (2.2719)	loss 3.5295 (3.1461)	grad_norm 2.6416 (2.5449)	
[2022-01-25 11:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][330/1251]	eta 0:34:50 lr 0.000095	time 1.8773 (2.2695)	loss 3.8684 (3.1518)	grad_norm 3.0515 (2.5508)	
[2022-01-25 11:33:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][340/1251]	eta 0:34:25 lr 0.000095	time 2.1901 (2.2676)	loss 2.5997 (3.1448)	grad_norm 3.0560 (2.5513)	
[2022-01-25 11:34:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][350/1251]	eta 0:33:59 lr 0.000095	time 2.1627 (2.2635)	loss 3.5773 (3.1475)	grad_norm 2.5498 (2.5506)	
[2022-01-25 11:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][360/1251]	eta 0:33:31 lr 0.000095	time 1.7532 (2.2579)	loss 3.6030 (3.1443)	grad_norm 2.3290 (2.5493)	
[2022-01-25 11:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][370/1251]	eta 0:33:01 lr 0.000095	time 1.9090 (2.2492)	loss 3.6232 (3.1458)	grad_norm 3.0269 (2.5483)	
[2022-01-25 11:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][380/1251]	eta 0:32:35 lr 0.000095	time 2.1504 (2.2455)	loss 3.3827 (3.1497)	grad_norm 2.3944 (2.5456)	
[2022-01-25 11:35:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][390/1251]	eta 0:32:14 lr 0.000095	time 1.8016 (2.2471)	loss 2.8258 (3.1524)	grad_norm 2.8535 (2.5473)	
[2022-01-25 11:36:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][400/1251]	eta 0:31:52 lr 0.000095	time 2.2800 (2.2479)	loss 3.2646 (3.1583)	grad_norm 2.3974 (2.5457)	
[2022-01-25 11:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][410/1251]	eta 0:31:31 lr 0.000095	time 1.8784 (2.2490)	loss 2.5482 (3.1628)	grad_norm 2.4478 (2.5432)	
[2022-01-25 11:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][420/1251]	eta 0:31:09 lr 0.000095	time 1.8597 (2.2492)	loss 2.3916 (3.1589)	grad_norm 2.4473 (2.5410)	
[2022-01-25 11:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][430/1251]	eta 0:30:47 lr 0.000095	time 2.2627 (2.2502)	loss 2.4206 (3.1557)	grad_norm 2.2994 (2.5400)	
[2022-01-25 11:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][440/1251]	eta 0:30:23 lr 0.000095	time 2.0738 (2.2489)	loss 2.7983 (3.1484)	grad_norm 2.4705 (2.5382)	
[2022-01-25 11:37:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][450/1251]	eta 0:29:58 lr 0.000095	time 1.8457 (2.2456)	loss 3.1965 (3.1468)	grad_norm 2.6587 (2.5381)	
[2022-01-25 11:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][460/1251]	eta 0:29:33 lr 0.000095	time 1.9364 (2.2426)	loss 2.6200 (3.1431)	grad_norm 2.7661 (2.5373)	
[2022-01-25 11:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][470/1251]	eta 0:29:11 lr 0.000095	time 1.9469 (2.2423)	loss 3.3650 (3.1444)	grad_norm 2.4146 (2.5355)	
[2022-01-25 11:39:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][480/1251]	eta 0:28:48 lr 0.000094	time 2.7974 (2.2422)	loss 3.7249 (3.1423)	grad_norm 2.9058 (2.5337)	
[2022-01-25 11:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][490/1251]	eta 0:28:24 lr 0.000094	time 1.9149 (2.2398)	loss 2.2065 (3.1430)	grad_norm 2.6533 (2.5325)	
[2022-01-25 11:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][500/1251]	eta 0:27:59 lr 0.000094	time 1.8606 (2.2359)	loss 3.4317 (3.1461)	grad_norm 2.3044 (2.5299)	
[2022-01-25 11:40:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][510/1251]	eta 0:27:36 lr 0.000094	time 2.0898 (2.2351)	loss 3.4278 (3.1481)	grad_norm 2.3917 (2.5297)	
[2022-01-25 11:40:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][520/1251]	eta 0:27:12 lr 0.000094	time 2.0276 (2.2336)	loss 3.4394 (3.1490)	grad_norm 2.1791 (2.5292)	
[2022-01-25 11:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][530/1251]	eta 0:26:49 lr 0.000094	time 1.5937 (2.2323)	loss 3.9040 (3.1508)	grad_norm 2.7636 (2.5293)	
[2022-01-25 11:41:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][540/1251]	eta 0:26:24 lr 0.000094	time 2.0221 (2.2284)	loss 2.8949 (3.1513)	grad_norm 2.5995 (2.5312)	
[2022-01-25 11:41:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][550/1251]	eta 0:26:02 lr 0.000094	time 2.2071 (2.2296)	loss 2.5568 (3.1502)	grad_norm 2.3711 (2.5334)	
[2022-01-25 11:41:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][560/1251]	eta 0:25:39 lr 0.000094	time 2.1912 (2.2281)	loss 3.0503 (3.1490)	grad_norm 2.4962 (2.5362)	
[2022-01-25 11:42:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][570/1251]	eta 0:25:18 lr 0.000094	time 1.6410 (2.2298)	loss 1.8826 (3.1453)	grad_norm 2.6871 (2.5343)	
[2022-01-25 11:42:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][580/1251]	eta 0:24:56 lr 0.000094	time 1.9087 (2.2308)	loss 3.0103 (3.1459)	grad_norm 2.6772 (2.5369)	
[2022-01-25 11:43:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][590/1251]	eta 0:24:35 lr 0.000094	time 1.7841 (2.2316)	loss 3.3813 (3.1474)	grad_norm 3.1173 (2.5399)	
[2022-01-25 11:43:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][600/1251]	eta 0:24:11 lr 0.000094	time 1.5307 (2.2299)	loss 2.8460 (3.1472)	grad_norm 2.1904 (2.5373)	
[2022-01-25 11:43:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][610/1251]	eta 0:23:47 lr 0.000094	time 1.5363 (2.2265)	loss 3.2271 (3.1455)	grad_norm 2.2842 (2.5392)	
[2022-01-25 11:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][620/1251]	eta 0:23:23 lr 0.000094	time 1.9863 (2.2241)	loss 3.5193 (3.1480)	grad_norm 2.2887 (2.5422)	
[2022-01-25 11:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][630/1251]	eta 0:23:01 lr 0.000094	time 2.4204 (2.2250)	loss 3.0972 (3.1471)	grad_norm 2.2584 (2.5430)	
[2022-01-25 11:44:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][640/1251]	eta 0:22:38 lr 0.000094	time 2.1337 (2.2238)	loss 3.5237 (3.1467)	grad_norm 2.2018 (2.5419)	
[2022-01-25 11:45:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][650/1251]	eta 0:22:16 lr 0.000094	time 2.3164 (2.2242)	loss 2.9937 (3.1430)	grad_norm 2.3246 (2.5413)	
[2022-01-25 11:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][660/1251]	eta 0:21:52 lr 0.000094	time 1.6758 (2.2208)	loss 2.1439 (3.1390)	grad_norm 2.4702 (2.5384)	
[2022-01-25 11:45:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][670/1251]	eta 0:21:29 lr 0.000094	time 1.5672 (2.2197)	loss 3.4953 (3.1419)	grad_norm 2.8653 (2.5398)	
[2022-01-25 11:46:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][680/1251]	eta 0:21:06 lr 0.000094	time 1.9459 (2.2183)	loss 3.6130 (3.1427)	grad_norm 3.3127 (2.5402)	
[2022-01-25 11:46:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][690/1251]	eta 0:20:44 lr 0.000094	time 1.5900 (2.2176)	loss 3.3380 (3.1422)	grad_norm 2.3582 (2.5385)	
[2022-01-25 11:46:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][700/1251]	eta 0:20:21 lr 0.000094	time 1.9340 (2.2164)	loss 1.8811 (3.1396)	grad_norm 2.7574 (2.5389)	
[2022-01-25 11:47:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][710/1251]	eta 0:19:59 lr 0.000094	time 2.9689 (2.2174)	loss 3.5265 (3.1377)	grad_norm 2.7824 (2.5411)	
[2022-01-25 11:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][720/1251]	eta 0:19:38 lr 0.000094	time 2.5382 (2.2197)	loss 3.4861 (3.1360)	grad_norm 2.5338 (2.5393)	
[2022-01-25 11:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][730/1251]	eta 0:19:17 lr 0.000094	time 1.9636 (2.2219)	loss 2.4455 (3.1368)	grad_norm 2.5045 (2.5390)	
[2022-01-25 11:48:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][740/1251]	eta 0:18:54 lr 0.000094	time 1.6119 (2.2198)	loss 2.3494 (3.1326)	grad_norm 2.8708 (2.5405)	
[2022-01-25 11:48:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][750/1251]	eta 0:18:30 lr 0.000094	time 1.8662 (2.2176)	loss 2.2406 (3.1287)	grad_norm 2.2330 (2.5424)	
[2022-01-25 11:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][760/1251]	eta 0:18:08 lr 0.000094	time 1.8736 (2.2164)	loss 3.8446 (3.1281)	grad_norm 2.5056 (2.5438)	
[2022-01-25 11:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][770/1251]	eta 0:17:44 lr 0.000094	time 2.2475 (2.2140)	loss 2.3095 (3.1300)	grad_norm 2.6834 (2.5479)	
[2022-01-25 11:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][780/1251]	eta 0:17:22 lr 0.000094	time 2.1274 (2.2132)	loss 3.5434 (3.1274)	grad_norm 2.5941 (2.5482)	
[2022-01-25 11:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][790/1251]	eta 0:17:00 lr 0.000094	time 2.4533 (2.2133)	loss 3.7121 (3.1287)	grad_norm 2.3534 (2.5496)	
[2022-01-25 11:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][800/1251]	eta 0:16:39 lr 0.000094	time 2.1010 (2.2160)	loss 3.5745 (3.1302)	grad_norm 2.2037 (2.5468)	
[2022-01-25 11:51:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][810/1251]	eta 0:16:16 lr 0.000094	time 1.9439 (2.2150)	loss 3.4309 (3.1299)	grad_norm 2.5136 (2.5469)	
[2022-01-25 11:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][820/1251]	eta 0:15:54 lr 0.000094	time 2.1522 (2.2138)	loss 2.1421 (3.1292)	grad_norm 2.2542 (2.5480)	
[2022-01-25 11:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][830/1251]	eta 0:15:31 lr 0.000094	time 2.2122 (2.2135)	loss 2.0509 (3.1278)	grad_norm 2.4806 (2.5458)	
[2022-01-25 11:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][840/1251]	eta 0:15:09 lr 0.000094	time 2.2265 (2.2134)	loss 3.1311 (3.1269)	grad_norm 2.5644 (2.5453)	
[2022-01-25 11:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][850/1251]	eta 0:14:47 lr 0.000094	time 2.2570 (2.2123)	loss 3.4931 (3.1274)	grad_norm 2.1951 (2.5454)	
[2022-01-25 11:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][860/1251]	eta 0:14:24 lr 0.000094	time 1.5283 (2.2105)	loss 2.5557 (3.1241)	grad_norm 2.1614 (2.5450)	
[2022-01-25 11:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][870/1251]	eta 0:14:02 lr 0.000094	time 2.3766 (2.2101)	loss 2.4985 (3.1237)	grad_norm 2.5280 (2.5455)	
[2022-01-25 11:53:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][880/1251]	eta 0:13:40 lr 0.000094	time 2.2285 (2.2116)	loss 2.7100 (3.1232)	grad_norm 2.3411 (2.5444)	
[2022-01-25 11:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][890/1251]	eta 0:13:18 lr 0.000094	time 2.3126 (2.2120)	loss 3.1963 (3.1268)	grad_norm 2.3171 (2.5438)	
[2022-01-25 11:54:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][900/1251]	eta 0:12:56 lr 0.000094	time 1.5611 (2.2112)	loss 3.0154 (3.1262)	grad_norm 2.4985 (2.5443)	
[2022-01-25 11:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][910/1251]	eta 0:12:33 lr 0.000093	time 2.4219 (2.2107)	loss 2.4205 (3.1278)	grad_norm 2.3797 (2.5451)	
[2022-01-25 11:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][920/1251]	eta 0:12:11 lr 0.000093	time 2.2593 (2.2101)	loss 3.1876 (3.1290)	grad_norm 2.6990 (2.5443)	
[2022-01-25 11:55:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][930/1251]	eta 0:11:48 lr 0.000093	time 1.5445 (2.2087)	loss 3.2312 (3.1296)	grad_norm 2.4420 (2.5448)	
[2022-01-25 11:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][940/1251]	eta 0:11:26 lr 0.000093	time 2.2737 (2.2083)	loss 3.6310 (3.1319)	grad_norm 2.9185 (2.5463)	
[2022-01-25 11:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][950/1251]	eta 0:11:04 lr 0.000093	time 2.5042 (2.2087)	loss 2.0416 (3.1311)	grad_norm 2.5275 (2.5461)	
[2022-01-25 11:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][960/1251]	eta 0:10:42 lr 0.000093	time 2.2784 (2.2093)	loss 3.6575 (3.1319)	grad_norm 2.2847 (2.5455)	
[2022-01-25 11:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][970/1251]	eta 0:10:20 lr 0.000093	time 1.5606 (2.2093)	loss 2.2094 (3.1322)	grad_norm 2.8882 (2.5460)	
[2022-01-25 11:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][980/1251]	eta 0:09:58 lr 0.000093	time 1.9211 (2.2089)	loss 3.5748 (3.1343)	grad_norm 2.4526 (2.5455)	
[2022-01-25 11:57:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][990/1251]	eta 0:09:36 lr 0.000093	time 1.9277 (2.2073)	loss 3.3830 (3.1361)	grad_norm 2.5152 (2.5464)	
[2022-01-25 11:57:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1000/1251]	eta 0:09:13 lr 0.000093	time 2.3218 (2.2061)	loss 3.3569 (3.1351)	grad_norm 2.3837 (2.5459)	
[2022-01-25 11:58:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1010/1251]	eta 0:08:51 lr 0.000093	time 1.8751 (2.2058)	loss 3.2199 (3.1351)	grad_norm 2.1691 (2.5457)	
[2022-01-25 11:58:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1020/1251]	eta 0:08:29 lr 0.000093	time 2.4962 (2.2058)	loss 3.3722 (3.1363)	grad_norm 2.3091 (2.5448)	
[2022-01-25 11:58:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1030/1251]	eta 0:08:07 lr 0.000093	time 1.8316 (2.2050)	loss 3.3081 (3.1392)	grad_norm 2.6849 (2.5452)	
[2022-01-25 11:59:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1040/1251]	eta 0:07:45 lr 0.000093	time 2.1862 (2.2068)	loss 3.3836 (3.1421)	grad_norm 2.3071 (2.5446)	
[2022-01-25 11:59:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1050/1251]	eta 0:07:23 lr 0.000093	time 1.7499 (2.2072)	loss 2.8412 (3.1411)	grad_norm 2.6044 (2.5452)	
[2022-01-25 12:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1060/1251]	eta 0:07:01 lr 0.000093	time 2.2950 (2.2054)	loss 3.1499 (3.1397)	grad_norm 2.5149 (2.5451)	
[2022-01-25 12:00:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1070/1251]	eta 0:06:38 lr 0.000093	time 1.9005 (2.2039)	loss 3.3484 (3.1392)	grad_norm 2.2767 (2.5446)	
[2022-01-25 12:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1080/1251]	eta 0:06:16 lr 0.000093	time 1.5364 (2.2023)	loss 3.2309 (3.1410)	grad_norm 2.2812 (2.5452)	
[2022-01-25 12:01:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1090/1251]	eta 0:05:54 lr 0.000093	time 2.1054 (2.2015)	loss 3.7251 (3.1411)	grad_norm 2.5271 (2.5452)	
[2022-01-25 12:01:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1100/1251]	eta 0:05:32 lr 0.000093	time 2.4377 (2.2019)	loss 3.1612 (3.1396)	grad_norm 2.7869 (2.5460)	
[2022-01-25 12:01:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1110/1251]	eta 0:05:10 lr 0.000093	time 2.4603 (2.2043)	loss 3.1533 (3.1402)	grad_norm 2.4093 (2.5464)	
[2022-01-25 12:02:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1120/1251]	eta 0:04:48 lr 0.000093	time 2.2786 (2.2050)	loss 2.2989 (3.1363)	grad_norm 2.4970 (2.5462)	
[2022-01-25 12:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1130/1251]	eta 0:04:26 lr 0.000093	time 1.6465 (2.2057)	loss 3.4261 (3.1377)	grad_norm 2.9536 (2.5466)	
[2022-01-25 12:03:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1140/1251]	eta 0:04:04 lr 0.000093	time 2.5515 (2.2063)	loss 2.3249 (3.1376)	grad_norm 2.1530 (2.5473)	
[2022-01-25 12:03:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1150/1251]	eta 0:03:42 lr 0.000093	time 1.5672 (2.2054)	loss 3.2884 (3.1366)	grad_norm 2.6273 (2.5469)	
[2022-01-25 12:03:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1160/1251]	eta 0:03:20 lr 0.000093	time 1.6152 (2.2032)	loss 2.3334 (3.1330)	grad_norm 2.3923 (2.5467)	
[2022-01-25 12:04:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1170/1251]	eta 0:02:58 lr 0.000093	time 1.7814 (2.2022)	loss 3.0531 (3.1307)	grad_norm 2.7031 (2.5459)	
[2022-01-25 12:04:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1180/1251]	eta 0:02:36 lr 0.000093	time 2.2634 (2.2024)	loss 3.6183 (3.1295)	grad_norm 2.4948 (2.5467)	
[2022-01-25 12:04:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1190/1251]	eta 0:02:14 lr 0.000093	time 2.3237 (2.2037)	loss 3.3668 (3.1267)	grad_norm 2.3715 (2.5469)	
[2022-01-25 12:05:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1200/1251]	eta 0:01:52 lr 0.000093	time 2.0058 (2.2044)	loss 2.8303 (3.1247)	grad_norm 2.4491 (2.5475)	
[2022-01-25 12:05:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1210/1251]	eta 0:01:30 lr 0.000093	time 1.9154 (2.2046)	loss 2.6990 (3.1226)	grad_norm 2.2922 (2.5492)	
[2022-01-25 12:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1220/1251]	eta 0:01:08 lr 0.000093	time 1.8084 (2.2043)	loss 3.5545 (3.1230)	grad_norm 2.8382 (2.5485)	
[2022-01-25 12:06:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1230/1251]	eta 0:00:46 lr 0.000093	time 1.8329 (2.2037)	loss 3.5250 (3.1244)	grad_norm 2.2677 (2.5485)	
[2022-01-25 12:06:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1240/1251]	eta 0:00:24 lr 0.000093	time 1.4049 (2.2025)	loss 2.2527 (3.1232)	grad_norm 2.4791 (2.5488)	
[2022-01-25 12:06:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [243/300][1250/1251]	eta 0:00:02 lr 0.000093	time 1.2248 (2.1973)	loss 3.6898 (3.1229)	grad_norm 2.5496 (2.5489)	
[2022-01-25 12:06:54 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 243 training takes 0:45:49
[2022-01-25 12:07:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.765 (16.765)	Loss 0.7749 (0.7749)	Acc@1 80.371 (80.371)	Acc@5 95.898 (95.898)	
[2022-01-25 12:07:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.941 (3.233)	Loss 0.7812 (0.8491)	Acc@1 80.762 (79.980)	Acc@5 96.582 (95.028)	
[2022-01-25 12:07:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 2.042 (2.667)	Loss 0.8532 (0.8487)	Acc@1 78.711 (80.166)	Acc@5 94.922 (95.006)	
[2022-01-25 12:08:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.276 (2.298)	Loss 0.8369 (0.8471)	Acc@1 79.492 (80.163)	Acc@5 95.508 (95.035)	
[2022-01-25 12:08:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.399 (2.190)	Loss 0.8191 (0.8434)	Acc@1 81.348 (80.176)	Acc@5 95.117 (95.108)	
[2022-01-25 12:08:30 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.170 Acc@5 95.136
[2022-01-25 12:08:30 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.2%
[2022-01-25 12:08:30 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.18%
[2022-01-25 12:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][0/1251]	eta 8:32:00 lr 0.000093	time 24.5569 (24.5569)	loss 2.8486 (2.8486)	grad_norm 2.8268 (2.8268)	
[2022-01-25 12:09:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][10/1251]	eta 1:29:53 lr 0.000093	time 1.5640 (4.3457)	loss 3.2439 (3.1897)	grad_norm 2.2668 (2.8959)	
[2022-01-25 12:09:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][20/1251]	eta 1:11:04 lr 0.000093	time 1.1959 (3.4643)	loss 3.2946 (3.1941)	grad_norm 2.6047 (2.6963)	
[2022-01-25 12:10:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][30/1251]	eta 1:01:36 lr 0.000093	time 1.9741 (3.0278)	loss 3.2963 (3.2527)	grad_norm 2.4103 (2.6536)	
[2022-01-25 12:10:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][40/1251]	eta 0:56:45 lr 0.000093	time 2.8894 (2.8119)	loss 2.1302 (3.2437)	grad_norm 2.5168 (2.6666)	
[2022-01-25 12:10:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][50/1251]	eta 0:53:23 lr 0.000093	time 1.9442 (2.6674)	loss 3.2089 (3.1959)	grad_norm 2.5846 (2.6655)	
[2022-01-25 12:11:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][60/1251]	eta 0:51:15 lr 0.000093	time 2.1995 (2.5823)	loss 3.4380 (3.2096)	grad_norm 2.1215 (2.6544)	
[2022-01-25 12:11:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][70/1251]	eta 0:49:41 lr 0.000093	time 2.2924 (2.5246)	loss 3.3480 (3.2269)	grad_norm 2.6959 (2.6571)	
[2022-01-25 12:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][80/1251]	eta 0:48:23 lr 0.000093	time 2.6479 (2.4791)	loss 3.2768 (3.1975)	grad_norm 2.8307 (2.7463)	
[2022-01-25 12:12:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][90/1251]	eta 0:47:09 lr 0.000092	time 1.8689 (2.4368)	loss 3.8473 (3.1772)	grad_norm 2.8568 (2.7471)	
[2022-01-25 12:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][100/1251]	eta 0:46:24 lr 0.000092	time 2.2910 (2.4190)	loss 2.8875 (3.1863)	grad_norm 2.2730 (2.7404)	
[2022-01-25 12:12:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][110/1251]	eta 0:45:34 lr 0.000092	time 2.1197 (2.3965)	loss 3.1123 (3.1976)	grad_norm 2.3660 (2.7244)	
[2022-01-25 12:13:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][120/1251]	eta 0:44:50 lr 0.000092	time 2.8231 (2.3790)	loss 2.4364 (3.1954)	grad_norm 2.5889 (2.7087)	
[2022-01-25 12:13:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][130/1251]	eta 0:44:10 lr 0.000092	time 1.6469 (2.3646)	loss 2.7577 (3.1916)	grad_norm 3.0761 (2.7057)	
[2022-01-25 12:14:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][140/1251]	eta 0:43:33 lr 0.000092	time 2.4677 (2.3520)	loss 3.4634 (3.1705)	grad_norm 2.5120 (2.6836)	
[2022-01-25 12:14:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][150/1251]	eta 0:42:59 lr 0.000092	time 2.3115 (2.3429)	loss 2.2007 (3.1653)	grad_norm 3.1444 (2.6779)	
[2022-01-25 12:14:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][160/1251]	eta 0:42:31 lr 0.000092	time 2.3697 (2.3387)	loss 3.4829 (3.1602)	grad_norm 2.5208 (2.6670)	
[2022-01-25 12:15:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][170/1251]	eta 0:41:58 lr 0.000092	time 1.7218 (2.3294)	loss 3.0196 (3.1628)	grad_norm 2.7605 (2.6613)	
[2022-01-25 12:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][180/1251]	eta 0:41:35 lr 0.000092	time 3.3694 (2.3303)	loss 2.6510 (3.1541)	grad_norm 2.4559 (2.6450)	
[2022-01-25 12:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][190/1251]	eta 0:41:05 lr 0.000092	time 2.6035 (2.3239)	loss 2.4982 (3.1397)	grad_norm 2.2204 (2.6326)	
[2022-01-25 12:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][200/1251]	eta 0:40:32 lr 0.000092	time 1.7455 (2.3142)	loss 2.1169 (3.1341)	grad_norm 2.4742 (2.6279)	
[2022-01-25 12:16:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][210/1251]	eta 0:39:54 lr 0.000092	time 2.0287 (2.3004)	loss 3.8413 (3.1354)	grad_norm 2.8790 (2.6265)	
[2022-01-25 12:16:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][220/1251]	eta 0:39:24 lr 0.000092	time 2.7243 (2.2931)	loss 2.4333 (3.1274)	grad_norm 3.4712 (2.6237)	
[2022-01-25 12:17:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][230/1251]	eta 0:38:48 lr 0.000092	time 1.9711 (2.2809)	loss 2.3415 (3.1185)	grad_norm 2.8430 (2.6261)	
[2022-01-25 12:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][240/1251]	eta 0:38:21 lr 0.000092	time 2.5301 (2.2764)	loss 3.6166 (3.1305)	grad_norm 2.9146 (2.6288)	
[2022-01-25 12:18:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][250/1251]	eta 0:37:54 lr 0.000092	time 1.9180 (2.2724)	loss 2.5844 (3.1283)	grad_norm 2.3159 (2.6289)	
[2022-01-25 12:18:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][260/1251]	eta 0:37:30 lr 0.000092	time 2.2444 (2.2708)	loss 2.5493 (3.1263)	grad_norm 2.0823 (2.6218)	
[2022-01-25 12:18:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][270/1251]	eta 0:37:07 lr 0.000092	time 1.9312 (2.2706)	loss 3.8971 (3.1332)	grad_norm 2.2852 (2.6143)	
[2022-01-25 12:19:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][280/1251]	eta 0:36:41 lr 0.000092	time 2.4493 (2.2673)	loss 2.5507 (3.1256)	grad_norm 2.1028 (2.6076)	
[2022-01-25 12:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][290/1251]	eta 0:36:13 lr 0.000092	time 1.9453 (2.2619)	loss 3.1625 (3.1305)	grad_norm 2.5025 (2.6044)	
[2022-01-25 12:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][300/1251]	eta 0:35:45 lr 0.000092	time 2.0320 (2.2565)	loss 3.1978 (3.1279)	grad_norm 2.5068 (2.6081)	
[2022-01-25 12:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][310/1251]	eta 0:35:23 lr 0.000092	time 2.5330 (2.2561)	loss 3.5144 (3.1317)	grad_norm 2.6485 (2.6058)	
[2022-01-25 12:20:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][320/1251]	eta 0:35:03 lr 0.000092	time 2.3814 (2.2589)	loss 3.0234 (3.1354)	grad_norm 2.5371 (2.6058)	
[2022-01-25 12:20:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][330/1251]	eta 0:34:36 lr 0.000092	time 2.2149 (2.2547)	loss 3.3879 (3.1309)	grad_norm 2.3396 (2.6003)	
[2022-01-25 12:21:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][340/1251]	eta 0:34:10 lr 0.000092	time 2.2196 (2.2512)	loss 3.6329 (3.1301)	grad_norm 2.9416 (2.5976)	
[2022-01-25 12:21:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][350/1251]	eta 0:33:47 lr 0.000092	time 1.7711 (2.2505)	loss 3.1078 (3.1282)	grad_norm 2.3844 (2.5926)	
[2022-01-25 12:22:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][360/1251]	eta 0:33:27 lr 0.000092	time 2.3851 (2.2527)	loss 3.4791 (3.1349)	grad_norm 2.3128 (2.5875)	
[2022-01-25 12:22:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][370/1251]	eta 0:33:00 lr 0.000092	time 2.2161 (2.2481)	loss 3.1448 (3.1281)	grad_norm 2.7144 (2.5901)	
[2022-01-25 12:22:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][380/1251]	eta 0:32:35 lr 0.000092	time 1.9674 (2.2455)	loss 3.5720 (3.1297)	grad_norm 2.5507 (2.5934)	
[2022-01-25 12:23:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][390/1251]	eta 0:32:08 lr 0.000092	time 2.1481 (2.2399)	loss 2.6434 (3.1261)	grad_norm 2.4958 (2.5981)	
[2022-01-25 12:23:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][400/1251]	eta 0:31:44 lr 0.000092	time 2.6232 (2.2381)	loss 3.0259 (3.1200)	grad_norm 2.7266 (2.5989)	
[2022-01-25 12:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][410/1251]	eta 0:31:20 lr 0.000092	time 1.9547 (2.2365)	loss 3.0902 (3.1258)	grad_norm 3.0956 (2.5965)	
[2022-01-25 12:24:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][420/1251]	eta 0:30:57 lr 0.000092	time 2.2276 (2.2354)	loss 3.3617 (3.1255)	grad_norm 2.0636 (2.5954)	
[2022-01-25 12:24:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][430/1251]	eta 0:30:34 lr 0.000092	time 2.2051 (2.2344)	loss 2.6881 (3.1332)	grad_norm 2.2689 (2.5919)	
[2022-01-25 12:24:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][440/1251]	eta 0:30:13 lr 0.000092	time 2.4967 (2.2358)	loss 3.7623 (3.1327)	grad_norm 2.9430 (2.5934)	
[2022-01-25 12:25:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][450/1251]	eta 0:29:45 lr 0.000092	time 1.6018 (2.2291)	loss 2.1955 (3.1265)	grad_norm 2.4229 (2.5911)	
[2022-01-25 12:25:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][460/1251]	eta 0:29:20 lr 0.000092	time 2.2065 (2.2258)	loss 3.2137 (3.1274)	grad_norm 2.3899 (2.5905)	
[2022-01-25 12:25:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][470/1251]	eta 0:28:55 lr 0.000092	time 1.9788 (2.2222)	loss 2.2460 (3.1274)	grad_norm 2.5550 (2.5883)	
[2022-01-25 12:26:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][480/1251]	eta 0:28:35 lr 0.000092	time 2.6870 (2.2250)	loss 3.6161 (3.1301)	grad_norm 3.3894 (2.5884)	
[2022-01-25 12:26:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][490/1251]	eta 0:28:11 lr 0.000092	time 2.1665 (2.2228)	loss 3.6141 (3.1292)	grad_norm 2.2924 (2.5850)	
[2022-01-25 12:27:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][500/1251]	eta 0:27:49 lr 0.000092	time 2.5844 (2.2234)	loss 2.7586 (3.1251)	grad_norm 2.4298 (2.5835)	
[2022-01-25 12:27:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][510/1251]	eta 0:27:29 lr 0.000092	time 3.0719 (2.2257)	loss 3.7336 (3.1316)	grad_norm 2.3690 (2.5819)	
[2022-01-25 12:27:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][520/1251]	eta 0:27:09 lr 0.000092	time 2.2830 (2.2286)	loss 3.0598 (3.1292)	grad_norm 3.2539 (2.5820)	
[2022-01-25 12:28:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][530/1251]	eta 0:26:46 lr 0.000091	time 1.9723 (2.2282)	loss 3.8770 (3.1287)	grad_norm 2.1045 (2.5804)	
[2022-01-25 12:28:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][540/1251]	eta 0:26:24 lr 0.000091	time 2.6185 (2.2290)	loss 2.6694 (3.1252)	grad_norm 2.6087 (2.5832)	
[2022-01-25 12:28:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][550/1251]	eta 0:26:00 lr 0.000091	time 1.8692 (2.2258)	loss 3.6114 (3.1268)	grad_norm 2.6441 (2.5821)	
[2022-01-25 12:29:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][560/1251]	eta 0:25:37 lr 0.000091	time 2.2574 (2.2248)	loss 3.2150 (3.1246)	grad_norm 2.2015 (2.5806)	
[2022-01-25 12:29:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][570/1251]	eta 0:25:14 lr 0.000091	time 2.2356 (2.2238)	loss 2.6835 (3.1259)	grad_norm 2.3357 (2.5782)	
[2022-01-25 12:30:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][580/1251]	eta 0:24:52 lr 0.000091	time 2.4771 (2.2238)	loss 1.9886 (3.1215)	grad_norm 2.7417 (2.5776)	
[2022-01-25 12:30:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][590/1251]	eta 0:24:29 lr 0.000091	time 1.7684 (2.2236)	loss 2.6044 (3.1205)	grad_norm 2.3614 (2.5756)	
[2022-01-25 12:30:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][600/1251]	eta 0:24:08 lr 0.000091	time 1.9642 (2.2256)	loss 3.5269 (3.1238)	grad_norm 2.3091 (2.5757)	
[2022-01-25 12:31:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][610/1251]	eta 0:23:43 lr 0.000091	time 1.6023 (2.2214)	loss 3.5660 (3.1226)	grad_norm 2.5265 (2.5745)	
[2022-01-25 12:31:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][620/1251]	eta 0:23:20 lr 0.000091	time 2.2414 (2.2188)	loss 3.1935 (3.1264)	grad_norm 2.5652 (2.5737)	
[2022-01-25 12:31:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][630/1251]	eta 0:22:56 lr 0.000091	time 1.6987 (2.2171)	loss 1.9592 (3.1234)	grad_norm 2.9672 (2.5732)	
[2022-01-25 12:32:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][640/1251]	eta 0:22:35 lr 0.000091	time 2.5590 (2.2184)	loss 3.1764 (3.1192)	grad_norm 2.5420 (2.5720)	
[2022-01-25 12:32:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][650/1251]	eta 0:22:12 lr 0.000091	time 2.1403 (2.2171)	loss 3.4550 (3.1162)	grad_norm 2.4089 (2.5704)	
[2022-01-25 12:32:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][660/1251]	eta 0:21:52 lr 0.000091	time 2.2519 (2.2210)	loss 3.4499 (3.1157)	grad_norm 2.4061 (2.5698)	
[2022-01-25 12:33:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][670/1251]	eta 0:21:30 lr 0.000091	time 2.2756 (2.2205)	loss 3.5961 (3.1141)	grad_norm 2.7867 (2.5693)	
[2022-01-25 12:33:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][680/1251]	eta 0:21:08 lr 0.000091	time 2.3620 (2.2207)	loss 3.1044 (3.1149)	grad_norm 2.6058 (2.5711)	
[2022-01-25 12:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][690/1251]	eta 0:20:44 lr 0.000091	time 1.8568 (2.2183)	loss 3.4984 (3.1139)	grad_norm 2.3604 (2.5683)	
[2022-01-25 12:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][700/1251]	eta 0:20:19 lr 0.000091	time 2.2196 (2.2137)	loss 3.1346 (3.1147)	grad_norm 2.9716 (2.5679)	
[2022-01-25 12:34:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][710/1251]	eta 0:19:55 lr 0.000091	time 1.6748 (2.2103)	loss 3.3248 (3.1141)	grad_norm 2.7420 (2.5679)	
[2022-01-25 12:35:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][720/1251]	eta 0:19:32 lr 0.000091	time 2.1154 (2.2088)	loss 3.5243 (3.1139)	grad_norm 2.9370 (2.5668)	
[2022-01-25 12:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][730/1251]	eta 0:19:11 lr 0.000091	time 1.9925 (2.2096)	loss 2.3658 (3.1107)	grad_norm 2.7075 (2.5692)	
[2022-01-25 12:35:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][740/1251]	eta 0:18:50 lr 0.000091	time 2.8560 (2.2118)	loss 2.0373 (3.1070)	grad_norm 2.1269 (2.5703)	
[2022-01-25 12:36:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][750/1251]	eta 0:18:27 lr 0.000091	time 1.9475 (2.2114)	loss 2.8382 (3.1053)	grad_norm 2.2029 (2.5711)	
[2022-01-25 12:36:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][760/1251]	eta 0:18:05 lr 0.000091	time 2.0123 (2.2115)	loss 3.2711 (3.1029)	grad_norm 2.2116 (2.5703)	
[2022-01-25 12:36:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][770/1251]	eta 0:17:43 lr 0.000091	time 1.7586 (2.2105)	loss 2.4997 (3.1028)	grad_norm 2.3174 (2.5684)	
[2022-01-25 12:37:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][780/1251]	eta 0:17:21 lr 0.000091	time 1.7745 (2.2113)	loss 2.8208 (3.1050)	grad_norm 2.5542 (2.5688)	
[2022-01-25 12:37:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][790/1251]	eta 0:16:59 lr 0.000091	time 2.7883 (2.2121)	loss 2.8691 (3.1063)	grad_norm 2.5646 (2.5687)	
[2022-01-25 12:38:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][800/1251]	eta 0:16:37 lr 0.000091	time 1.9496 (2.2118)	loss 2.4873 (3.1072)	grad_norm 2.0898 (2.5669)	
[2022-01-25 12:38:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][810/1251]	eta 0:16:15 lr 0.000091	time 1.6235 (2.2111)	loss 3.7559 (3.1080)	grad_norm 2.7531 (2.5689)	
[2022-01-25 12:38:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][820/1251]	eta 0:15:52 lr 0.000091	time 2.2410 (2.2108)	loss 3.2182 (3.1080)	grad_norm 2.3210 (2.5673)	
[2022-01-25 12:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][830/1251]	eta 0:15:31 lr 0.000091	time 3.0327 (2.2133)	loss 3.2856 (3.1112)	grad_norm 2.2649 (2.5661)	
[2022-01-25 12:39:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][840/1251]	eta 0:15:09 lr 0.000091	time 2.1248 (2.2127)	loss 3.5047 (3.1123)	grad_norm 2.3194 (2.5659)	
[2022-01-25 12:39:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][850/1251]	eta 0:14:46 lr 0.000091	time 1.6493 (2.2116)	loss 3.1364 (3.1112)	grad_norm 2.0564 (2.5654)	
[2022-01-25 12:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][860/1251]	eta 0:14:24 lr 0.000091	time 1.6337 (2.2109)	loss 3.1049 (3.1121)	grad_norm 2.3299 (2.5652)	
[2022-01-25 12:40:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][870/1251]	eta 0:14:03 lr 0.000091	time 2.5700 (2.2127)	loss 2.7035 (3.1112)	grad_norm 2.2498 (2.5633)	
[2022-01-25 12:41:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][880/1251]	eta 0:13:40 lr 0.000091	time 1.7254 (2.2129)	loss 2.3775 (3.1116)	grad_norm 2.4862 (2.5640)	
[2022-01-25 12:41:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][890/1251]	eta 0:13:19 lr 0.000091	time 1.9745 (2.2135)	loss 2.2964 (3.1088)	grad_norm 2.5795 (2.5625)	
[2022-01-25 12:41:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][900/1251]	eta 0:12:56 lr 0.000091	time 1.9091 (2.2124)	loss 3.5015 (3.1119)	grad_norm 2.7868 (2.5623)	
[2022-01-25 12:42:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][910/1251]	eta 0:12:33 lr 0.000091	time 1.7647 (2.2111)	loss 3.3820 (3.1147)	grad_norm 2.4749 (2.5601)	
[2022-01-25 12:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][920/1251]	eta 0:12:10 lr 0.000091	time 1.8359 (2.2078)	loss 2.6614 (3.1133)	grad_norm 2.3019 (2.5621)	
[2022-01-25 12:42:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][930/1251]	eta 0:11:48 lr 0.000091	time 1.8399 (2.2064)	loss 2.9686 (3.1150)	grad_norm 2.6858 (2.5629)	
[2022-01-25 12:43:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][940/1251]	eta 0:11:25 lr 0.000091	time 2.2986 (2.2053)	loss 3.1049 (3.1162)	grad_norm 2.7148 (2.5618)	
[2022-01-25 12:43:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][950/1251]	eta 0:11:03 lr 0.000091	time 1.9590 (2.2044)	loss 3.2364 (3.1164)	grad_norm 2.2713 (2.5600)	
[2022-01-25 12:43:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][960/1251]	eta 0:10:41 lr 0.000091	time 2.1577 (2.2043)	loss 3.9675 (3.1173)	grad_norm 2.5167 (2.5598)	
[2022-01-25 12:44:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][970/1251]	eta 0:10:19 lr 0.000090	time 2.6492 (2.2057)	loss 3.0893 (3.1178)	grad_norm 2.4460 (2.5600)	
[2022-01-25 12:44:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][980/1251]	eta 0:09:58 lr 0.000090	time 2.5208 (2.2088)	loss 3.2979 (3.1181)	grad_norm 2.5064 (2.5594)	
[2022-01-25 12:45:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][990/1251]	eta 0:09:36 lr 0.000090	time 2.2012 (2.2100)	loss 3.8722 (3.1191)	grad_norm 3.1404 (2.5597)	
[2022-01-25 12:45:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1000/1251]	eta 0:09:14 lr 0.000090	time 1.8688 (2.2087)	loss 3.3102 (3.1191)	grad_norm 2.4050 (2.5585)	
[2022-01-25 12:45:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1010/1251]	eta 0:08:52 lr 0.000090	time 1.8367 (2.2076)	loss 3.3591 (3.1185)	grad_norm 2.5537 (2.5584)	
[2022-01-25 12:46:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1020/1251]	eta 0:08:29 lr 0.000090	time 2.3406 (2.2071)	loss 3.6271 (3.1210)	grad_norm 2.6180 (2.5586)	
[2022-01-25 12:46:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1030/1251]	eta 0:08:07 lr 0.000090	time 2.7516 (2.2073)	loss 3.6160 (3.1204)	grad_norm 3.6721 (2.5607)	
[2022-01-25 12:46:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1040/1251]	eta 0:07:45 lr 0.000090	time 1.8921 (2.2067)	loss 3.4678 (3.1199)	grad_norm 2.4812 (2.5609)	
[2022-01-25 12:47:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1050/1251]	eta 0:07:23 lr 0.000090	time 2.3109 (2.2067)	loss 2.2597 (3.1183)	grad_norm 2.5282 (2.5608)	
[2022-01-25 12:47:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1060/1251]	eta 0:07:01 lr 0.000090	time 2.2186 (2.2066)	loss 2.8884 (3.1202)	grad_norm 2.2131 (2.5599)	
[2022-01-25 12:47:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1070/1251]	eta 0:06:39 lr 0.000090	time 2.1579 (2.2069)	loss 3.1457 (3.1201)	grad_norm 3.6044 (2.5607)	
[2022-01-25 12:48:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1080/1251]	eta 0:06:17 lr 0.000090	time 1.8762 (2.2057)	loss 3.8355 (3.1198)	grad_norm 2.8970 (2.5617)	
[2022-01-25 12:48:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1090/1251]	eta 0:05:55 lr 0.000090	time 2.3308 (2.2052)	loss 2.3565 (3.1173)	grad_norm 2.5132 (2.5617)	
[2022-01-25 12:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1100/1251]	eta 0:05:33 lr 0.000090	time 2.0475 (2.2058)	loss 3.6068 (3.1181)	grad_norm 2.3754 (2.5620)	
[2022-01-25 12:49:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1110/1251]	eta 0:05:11 lr 0.000090	time 2.4742 (2.2076)	loss 2.0265 (3.1173)	grad_norm 2.7222 (2.5622)	
[2022-01-25 12:49:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1120/1251]	eta 0:04:49 lr 0.000090	time 1.9355 (2.2067)	loss 3.4952 (3.1174)	grad_norm 2.4655 (2.5622)	
[2022-01-25 12:50:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1130/1251]	eta 0:04:26 lr 0.000090	time 1.8768 (2.2051)	loss 3.5952 (3.1205)	grad_norm 2.2290 (2.5604)	
[2022-01-25 12:50:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1140/1251]	eta 0:04:04 lr 0.000090	time 1.7881 (2.2023)	loss 3.2489 (3.1203)	grad_norm 2.2488 (2.5591)	
[2022-01-25 12:50:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1150/1251]	eta 0:03:42 lr 0.000090	time 2.8894 (2.2026)	loss 3.5976 (3.1192)	grad_norm 2.6817 (2.5599)	
[2022-01-25 12:51:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1160/1251]	eta 0:03:20 lr 0.000090	time 2.4687 (2.2020)	loss 3.6345 (3.1193)	grad_norm 2.2614 (2.5592)	
[2022-01-25 12:51:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1170/1251]	eta 0:02:58 lr 0.000090	time 2.6095 (2.2028)	loss 3.1476 (3.1202)	grad_norm 2.8449 (2.5660)	
[2022-01-25 12:51:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1180/1251]	eta 0:02:36 lr 0.000090	time 3.0957 (2.2038)	loss 3.7627 (3.1205)	grad_norm 2.5093 (2.5689)	
[2022-01-25 12:52:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1190/1251]	eta 0:02:14 lr 0.000090	time 2.1886 (2.2046)	loss 3.5515 (3.1213)	grad_norm 2.7129 (2.5690)	
[2022-01-25 12:52:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1200/1251]	eta 0:01:52 lr 0.000090	time 2.1849 (2.2049)	loss 3.1553 (3.1211)	grad_norm 2.3840 (2.5689)	
[2022-01-25 12:53:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1210/1251]	eta 0:01:30 lr 0.000090	time 2.2412 (2.2042)	loss 3.0252 (3.1200)	grad_norm 2.7592 (2.5689)	
[2022-01-25 12:53:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1220/1251]	eta 0:01:08 lr 0.000090	time 2.9136 (2.2046)	loss 3.1410 (3.1216)	grad_norm 2.5095 (2.5692)	
[2022-01-25 12:53:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1230/1251]	eta 0:00:46 lr 0.000090	time 1.8976 (2.2028)	loss 3.3063 (3.1234)	grad_norm 2.3563 (2.5686)	
[2022-01-25 12:54:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1240/1251]	eta 0:00:24 lr 0.000090	time 1.6680 (2.2004)	loss 3.4708 (3.1230)	grad_norm 2.3919 (2.5689)	
[2022-01-25 12:54:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [244/300][1250/1251]	eta 0:00:02 lr 0.000090	time 1.1731 (2.1948)	loss 3.1933 (3.1224)	grad_norm 2.4051 (2.5682)	
[2022-01-25 12:54:17 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 244 training takes 0:45:46
[2022-01-25 12:54:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.239 (18.239)	Loss 0.8287 (0.8287)	Acc@1 80.469 (80.469)	Acc@5 95.020 (95.020)	
[2022-01-25 12:54:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.857 (3.294)	Loss 0.8109 (0.8316)	Acc@1 80.664 (80.433)	Acc@5 95.605 (95.437)	
[2022-01-25 12:55:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.887 (2.450)	Loss 0.7976 (0.8355)	Acc@1 80.664 (80.315)	Acc@5 95.605 (95.364)	
[2022-01-25 12:55:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.271 (2.239)	Loss 0.8676 (0.8359)	Acc@1 80.762 (80.343)	Acc@5 94.043 (95.294)	
[2022-01-25 12:55:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.201 (2.193)	Loss 0.8438 (0.8447)	Acc@1 80.176 (80.171)	Acc@5 95.312 (95.181)	
[2022-01-25 12:55:53 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.178 Acc@5 95.184
[2022-01-25 12:55:53 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.2%
[2022-01-25 12:55:53 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.18%
[2022-01-25 12:56:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][0/1251]	eta 7:37:21 lr 0.000090	time 21.9360 (21.9360)	loss 2.7362 (2.7362)	grad_norm 2.4632 (2.4632)	
[2022-01-25 12:56:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][10/1251]	eta 1:24:04 lr 0.000090	time 2.1667 (4.0645)	loss 2.1511 (3.0719)	grad_norm 2.1404 (2.5179)	
[2022-01-25 12:57:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][20/1251]	eta 1:04:36 lr 0.000090	time 2.2681 (3.1494)	loss 2.5608 (3.1192)	grad_norm 2.3979 (2.5190)	
[2022-01-25 12:57:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][30/1251]	eta 0:56:40 lr 0.000090	time 1.3749 (2.7847)	loss 3.1550 (3.1433)	grad_norm 2.8851 (2.5532)	
[2022-01-25 12:57:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][40/1251]	eta 0:54:39 lr 0.000090	time 3.3515 (2.7081)	loss 3.3673 (3.1057)	grad_norm 2.4307 (2.5544)	
[2022-01-25 12:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][50/1251]	eta 0:52:26 lr 0.000090	time 1.7521 (2.6196)	loss 3.2523 (3.1686)	grad_norm 3.1594 (2.6248)	
[2022-01-25 12:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][60/1251]	eta 0:50:38 lr 0.000090	time 2.4668 (2.5515)	loss 2.6574 (3.1429)	grad_norm 2.3557 (2.6165)	
[2022-01-25 12:58:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][70/1251]	eta 0:49:12 lr 0.000090	time 1.6821 (2.4996)	loss 3.0692 (3.1536)	grad_norm 2.6460 (2.6421)	
[2022-01-25 12:59:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][80/1251]	eta 0:48:05 lr 0.000090	time 2.8998 (2.4643)	loss 3.5809 (3.1480)	grad_norm 2.9169 (2.6249)	
[2022-01-25 12:59:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][90/1251]	eta 0:47:13 lr 0.000090	time 2.1580 (2.4404)	loss 3.2600 (3.1677)	grad_norm 2.8697 (2.6293)	
[2022-01-25 12:59:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][100/1251]	eta 0:46:18 lr 0.000090	time 2.0361 (2.4137)	loss 2.7225 (3.1605)	grad_norm 2.4620 (2.6208)	
[2022-01-25 13:00:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][110/1251]	eta 0:45:20 lr 0.000090	time 1.9697 (2.3847)	loss 2.2533 (3.1208)	grad_norm 2.5267 (2.6052)	
[2022-01-25 13:00:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][120/1251]	eta 0:44:36 lr 0.000090	time 2.9315 (2.3667)	loss 3.3420 (3.1150)	grad_norm 3.1308 (2.6012)	
[2022-01-25 13:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][130/1251]	eta 0:44:01 lr 0.000090	time 2.1275 (2.3560)	loss 3.4770 (3.1270)	grad_norm 2.6165 (2.5923)	
[2022-01-25 13:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][140/1251]	eta 0:43:17 lr 0.000090	time 1.7980 (2.3383)	loss 3.2942 (3.1226)	grad_norm 2.7756 (2.5861)	
[2022-01-25 13:01:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][150/1251]	eta 0:42:35 lr 0.000090	time 2.3101 (2.3213)	loss 3.5106 (3.1213)	grad_norm 2.5364 (2.5949)	
[2022-01-25 13:02:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][160/1251]	eta 0:42:04 lr 0.000089	time 2.3153 (2.3141)	loss 2.5329 (3.1148)	grad_norm 2.4761 (2.5991)	
[2022-01-25 13:02:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][170/1251]	eta 0:41:37 lr 0.000089	time 2.8056 (2.3104)	loss 3.7906 (3.1189)	grad_norm 2.5891 (2.5976)	
[2022-01-25 13:02:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][180/1251]	eta 0:41:05 lr 0.000089	time 1.8925 (2.3024)	loss 3.4082 (3.1095)	grad_norm 2.8160 (2.5983)	
[2022-01-25 13:03:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][190/1251]	eta 0:40:40 lr 0.000089	time 2.5438 (2.3000)	loss 3.1895 (3.1092)	grad_norm 2.3759 (2.6001)	
[2022-01-25 13:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][200/1251]	eta 0:40:15 lr 0.000089	time 2.8237 (2.2982)	loss 3.6677 (3.1156)	grad_norm 2.6031 (2.5971)	
[2022-01-25 13:03:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][210/1251]	eta 0:39:54 lr 0.000089	time 2.5371 (2.2998)	loss 2.7771 (3.1206)	grad_norm 2.5484 (2.6006)	
[2022-01-25 13:04:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][220/1251]	eta 0:39:17 lr 0.000089	time 1.8502 (2.2867)	loss 2.1223 (3.1200)	grad_norm 2.6847 (2.5995)	
[2022-01-25 13:04:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][230/1251]	eta 0:38:44 lr 0.000089	time 1.7563 (2.2769)	loss 3.3577 (3.1186)	grad_norm 2.4160 (2.5951)	
[2022-01-25 13:05:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][240/1251]	eta 0:38:10 lr 0.000089	time 1.8358 (2.2660)	loss 3.4691 (3.1097)	grad_norm 2.3510 (2.6015)	
[2022-01-25 13:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][250/1251]	eta 0:37:41 lr 0.000089	time 1.8737 (2.2588)	loss 3.0116 (3.0898)	grad_norm 2.5242 (2.5997)	
[2022-01-25 13:05:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][260/1251]	eta 0:37:18 lr 0.000089	time 3.1374 (2.2590)	loss 2.5747 (3.0919)	grad_norm 2.9256 (2.5995)	
[2022-01-25 13:06:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][270/1251]	eta 0:36:54 lr 0.000089	time 2.6834 (2.2573)	loss 3.5398 (3.0919)	grad_norm 2.4443 (2.5986)	
[2022-01-25 13:06:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][280/1251]	eta 0:36:26 lr 0.000089	time 1.9038 (2.2518)	loss 3.3317 (3.0932)	grad_norm 2.4034 (2.5974)	
[2022-01-25 13:06:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][290/1251]	eta 0:36:01 lr 0.000089	time 1.8355 (2.2489)	loss 3.7271 (3.0941)	grad_norm 2.6761 (2.5959)	
[2022-01-25 13:07:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][300/1251]	eta 0:35:42 lr 0.000089	time 3.1714 (2.2531)	loss 3.7254 (3.1001)	grad_norm 2.5253 (2.5937)	
[2022-01-25 13:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][310/1251]	eta 0:35:18 lr 0.000089	time 2.5082 (2.2510)	loss 3.4204 (3.0954)	grad_norm 2.7425 (2.5987)	
[2022-01-25 13:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][320/1251]	eta 0:34:54 lr 0.000089	time 1.9893 (2.2498)	loss 3.3616 (3.1034)	grad_norm 2.5741 (2.5962)	
[2022-01-25 13:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][330/1251]	eta 0:34:29 lr 0.000089	time 2.1781 (2.2470)	loss 3.0513 (3.1020)	grad_norm 2.2930 (2.5956)	
[2022-01-25 13:08:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][340/1251]	eta 0:34:08 lr 0.000089	time 3.5883 (2.2486)	loss 3.4947 (3.1008)	grad_norm 2.5544 (2.5997)	
[2022-01-25 13:09:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][350/1251]	eta 0:33:49 lr 0.000089	time 2.5579 (2.2525)	loss 2.9450 (3.1014)	grad_norm 2.4376 (2.5972)	
[2022-01-25 13:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][360/1251]	eta 0:33:19 lr 0.000089	time 2.0798 (2.2443)	loss 3.3049 (3.1064)	grad_norm 2.3947 (2.5962)	
[2022-01-25 13:09:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][370/1251]	eta 0:32:53 lr 0.000089	time 1.7563 (2.2402)	loss 3.3745 (3.1012)	grad_norm 2.8252 (2.5993)	
[2022-01-25 13:10:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][380/1251]	eta 0:32:26 lr 0.000089	time 2.1799 (2.2351)	loss 3.1393 (3.0977)	grad_norm 2.5831 (2.6027)	
[2022-01-25 13:10:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][390/1251]	eta 0:32:01 lr 0.000089	time 1.8558 (2.2322)	loss 2.9183 (3.1000)	grad_norm 2.5380 (2.6005)	
[2022-01-25 13:10:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][400/1251]	eta 0:31:37 lr 0.000089	time 1.8654 (2.2294)	loss 3.5705 (3.1013)	grad_norm 2.3881 (2.5996)	
[2022-01-25 13:11:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][410/1251]	eta 0:31:11 lr 0.000089	time 1.9394 (2.2258)	loss 3.4268 (3.1023)	grad_norm 2.4573 (2.6000)	
[2022-01-25 13:11:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][420/1251]	eta 0:30:49 lr 0.000089	time 2.3803 (2.2254)	loss 2.2935 (3.1048)	grad_norm 2.3462 (2.6018)	
[2022-01-25 13:11:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][430/1251]	eta 0:30:31 lr 0.000089	time 2.3274 (2.2306)	loss 2.7142 (3.0944)	grad_norm 2.5377 (2.6033)	
[2022-01-25 13:12:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][440/1251]	eta 0:30:08 lr 0.000089	time 1.4429 (2.2300)	loss 3.7534 (3.0976)	grad_norm 3.0943 (2.6014)	
[2022-01-25 13:12:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][450/1251]	eta 0:29:46 lr 0.000089	time 2.4477 (2.2306)	loss 2.2456 (3.0959)	grad_norm 2.4199 (2.5999)	
[2022-01-25 13:13:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][460/1251]	eta 0:29:24 lr 0.000089	time 3.0310 (2.2304)	loss 3.6495 (3.1018)	grad_norm 2.9995 (2.6026)	
[2022-01-25 13:13:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][470/1251]	eta 0:28:58 lr 0.000089	time 1.5663 (2.2256)	loss 2.1825 (3.1000)	grad_norm 3.2514 (2.6038)	
[2022-01-25 13:13:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][480/1251]	eta 0:28:32 lr 0.000089	time 2.2571 (2.2217)	loss 3.0950 (3.1008)	grad_norm 2.6227 (2.6008)	
[2022-01-25 13:14:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][490/1251]	eta 0:28:09 lr 0.000089	time 1.9245 (2.2203)	loss 3.2165 (3.1014)	grad_norm 2.5033 (2.5966)	
[2022-01-25 13:14:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][500/1251]	eta 0:27:48 lr 0.000089	time 3.0672 (2.2212)	loss 3.3955 (3.1028)	grad_norm 2.4622 (2.5934)	
[2022-01-25 13:14:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][510/1251]	eta 0:27:28 lr 0.000089	time 2.4996 (2.2249)	loss 3.2983 (3.0975)	grad_norm 2.3940 (2.5928)	
[2022-01-25 13:15:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][520/1251]	eta 0:27:05 lr 0.000089	time 2.1099 (2.2241)	loss 3.2083 (3.1022)	grad_norm 2.7199 (2.5942)	
[2022-01-25 13:15:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][530/1251]	eta 0:26:43 lr 0.000089	time 2.2092 (2.2240)	loss 3.4125 (3.0952)	grad_norm 2.4406 (2.5964)	
[2022-01-25 13:15:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][540/1251]	eta 0:26:20 lr 0.000089	time 3.5121 (2.2228)	loss 2.6971 (3.0957)	grad_norm 3.1992 (2.6022)	
[2022-01-25 13:16:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][550/1251]	eta 0:25:57 lr 0.000089	time 1.9353 (2.2218)	loss 3.3786 (3.0973)	grad_norm 2.4576 (2.6005)	
[2022-01-25 13:16:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][560/1251]	eta 0:25:33 lr 0.000089	time 2.2162 (2.2199)	loss 3.3446 (3.0990)	grad_norm 2.9121 (2.6004)	
[2022-01-25 13:17:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][570/1251]	eta 0:25:10 lr 0.000089	time 1.9051 (2.2178)	loss 2.9877 (3.1010)	grad_norm 3.0937 (2.5984)	
[2022-01-25 13:17:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][580/1251]	eta 0:24:47 lr 0.000089	time 2.3232 (2.2171)	loss 3.5551 (3.0980)	grad_norm 2.1474 (2.5973)	
[2022-01-25 13:17:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][590/1251]	eta 0:24:25 lr 0.000089	time 2.0397 (2.2166)	loss 2.1614 (3.0993)	grad_norm 3.0436 (2.5963)	
[2022-01-25 13:18:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][600/1251]	eta 0:24:02 lr 0.000089	time 2.2100 (2.2151)	loss 2.8196 (3.0998)	grad_norm 2.9008 (2.5982)	
[2022-01-25 13:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][610/1251]	eta 0:23:39 lr 0.000088	time 1.6014 (2.2144)	loss 2.5454 (3.0999)	grad_norm 2.5595 (2.5963)	
[2022-01-25 13:18:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][620/1251]	eta 0:23:17 lr 0.000088	time 2.5683 (2.2145)	loss 3.5898 (3.1003)	grad_norm 3.0173 (2.6023)	
[2022-01-25 13:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][630/1251]	eta 0:22:54 lr 0.000088	time 2.4493 (2.2141)	loss 3.2785 (3.0979)	grad_norm 2.6666 (2.6026)	
[2022-01-25 13:19:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][640/1251]	eta 0:22:34 lr 0.000088	time 3.3840 (2.2165)	loss 3.5165 (3.1013)	grad_norm 2.6159 (2.6017)	
[2022-01-25 13:19:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][650/1251]	eta 0:22:13 lr 0.000088	time 1.7360 (2.2187)	loss 3.1986 (3.1059)	grad_norm 2.6950 (2.6033)	
[2022-01-25 13:20:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][660/1251]	eta 0:21:52 lr 0.000088	time 2.5452 (2.2200)	loss 3.3051 (3.1089)	grad_norm 2.3994 (2.6016)	
[2022-01-25 13:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][670/1251]	eta 0:21:28 lr 0.000088	time 2.0235 (2.2181)	loss 3.3873 (3.1106)	grad_norm 2.3266 (2.6000)	
[2022-01-25 13:21:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][680/1251]	eta 0:21:04 lr 0.000088	time 2.4746 (2.2147)	loss 3.3271 (3.1098)	grad_norm 2.4352 (2.6001)	
[2022-01-25 13:21:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][690/1251]	eta 0:20:41 lr 0.000088	time 2.2120 (2.2133)	loss 3.5775 (3.1130)	grad_norm 2.4941 (2.5976)	
[2022-01-25 13:21:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][700/1251]	eta 0:20:18 lr 0.000088	time 2.1785 (2.2113)	loss 3.4125 (3.1171)	grad_norm 2.5362 (2.5985)	
[2022-01-25 13:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][710/1251]	eta 0:19:56 lr 0.000088	time 2.8456 (2.2111)	loss 2.8318 (3.1143)	grad_norm 3.0071 (2.6016)	
[2022-01-25 13:22:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][720/1251]	eta 0:19:35 lr 0.000088	time 2.9855 (2.2131)	loss 3.3737 (3.1161)	grad_norm 4.2584 (2.6038)	
[2022-01-25 13:22:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][730/1251]	eta 0:19:13 lr 0.000088	time 2.6737 (2.2140)	loss 2.5032 (3.1171)	grad_norm 2.4887 (2.6040)	
[2022-01-25 13:23:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][740/1251]	eta 0:18:50 lr 0.000088	time 1.8277 (2.2132)	loss 3.4003 (3.1172)	grad_norm 2.5856 (2.6033)	
[2022-01-25 13:23:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][750/1251]	eta 0:18:27 lr 0.000088	time 2.3748 (2.2114)	loss 3.5651 (3.1184)	grad_norm 2.4442 (2.6041)	
[2022-01-25 13:23:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][760/1251]	eta 0:18:05 lr 0.000088	time 2.8001 (2.2098)	loss 2.5061 (3.1202)	grad_norm 2.6684 (2.6058)	
[2022-01-25 13:24:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][770/1251]	eta 0:17:42 lr 0.000088	time 1.9502 (2.2089)	loss 3.5159 (3.1163)	grad_norm 2.3617 (2.6044)	
[2022-01-25 13:24:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][780/1251]	eta 0:17:19 lr 0.000088	time 2.4813 (2.2080)	loss 2.7905 (3.1132)	grad_norm 2.6175 (2.6036)	
[2022-01-25 13:24:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][790/1251]	eta 0:16:56 lr 0.000088	time 1.6180 (2.2054)	loss 2.8866 (3.1089)	grad_norm 2.2359 (2.6058)	
[2022-01-25 13:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][800/1251]	eta 0:16:34 lr 0.000088	time 2.3783 (2.2042)	loss 2.2523 (3.1055)	grad_norm 2.3152 (2.6056)	
[2022-01-25 13:25:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][810/1251]	eta 0:16:11 lr 0.000088	time 1.5778 (2.2033)	loss 3.0653 (3.1060)	grad_norm 2.4711 (2.6045)	
[2022-01-25 13:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][820/1251]	eta 0:15:49 lr 0.000088	time 2.8458 (2.2036)	loss 3.3667 (3.1073)	grad_norm 2.4902 (2.6038)	
[2022-01-25 13:26:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][830/1251]	eta 0:15:27 lr 0.000088	time 1.8706 (2.2034)	loss 2.2800 (3.1068)	grad_norm 2.5342 (2.6042)	
[2022-01-25 13:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][840/1251]	eta 0:15:05 lr 0.000088	time 2.7211 (2.2038)	loss 3.4101 (3.1088)	grad_norm 2.6195 (2.6104)	
[2022-01-25 13:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][850/1251]	eta 0:14:44 lr 0.000088	time 2.4664 (2.2054)	loss 2.7966 (3.1097)	grad_norm 2.7812 (2.6117)	
[2022-01-25 13:27:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][860/1251]	eta 0:14:22 lr 0.000088	time 2.4086 (2.2071)	loss 2.1176 (3.1055)	grad_norm 2.5654 (2.6100)	
[2022-01-25 13:27:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][870/1251]	eta 0:14:00 lr 0.000088	time 1.8544 (2.2064)	loss 2.9761 (3.1053)	grad_norm 2.3035 (2.6082)	
[2022-01-25 13:28:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][880/1251]	eta 0:13:38 lr 0.000088	time 3.4461 (2.2070)	loss 3.8113 (3.1064)	grad_norm 3.0314 (2.6096)	
[2022-01-25 13:28:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][890/1251]	eta 0:13:16 lr 0.000088	time 1.9102 (2.2067)	loss 3.7750 (3.1100)	grad_norm 2.5997 (2.6111)	
[2022-01-25 13:29:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][900/1251]	eta 0:12:54 lr 0.000088	time 2.4363 (2.2066)	loss 2.5341 (3.1082)	grad_norm 2.3157 (2.6107)	
[2022-01-25 13:29:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][910/1251]	eta 0:12:31 lr 0.000088	time 2.1954 (2.2051)	loss 2.3112 (3.1090)	grad_norm 3.0847 (2.6105)	
[2022-01-25 13:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][920/1251]	eta 0:12:09 lr 0.000088	time 3.6233 (2.2047)	loss 2.4314 (3.1076)	grad_norm 2.2418 (2.6091)	
[2022-01-25 13:30:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][930/1251]	eta 0:11:47 lr 0.000088	time 2.1656 (2.2035)	loss 3.2535 (3.1100)	grad_norm 3.1646 (2.6087)	
[2022-01-25 13:30:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][940/1251]	eta 0:11:25 lr 0.000088	time 2.2849 (2.2039)	loss 3.6214 (3.1081)	grad_norm 2.2094 (2.6100)	
[2022-01-25 13:30:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][950/1251]	eta 0:11:03 lr 0.000088	time 1.9118 (2.2032)	loss 3.8176 (3.1071)	grad_norm 2.4154 (2.6084)	
[2022-01-25 13:31:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][960/1251]	eta 0:10:41 lr 0.000088	time 3.2945 (2.2031)	loss 3.1355 (3.1043)	grad_norm 2.2696 (2.6073)	
[2022-01-25 13:31:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][970/1251]	eta 0:10:18 lr 0.000088	time 2.1703 (2.2023)	loss 3.0753 (3.1039)	grad_norm 2.8853 (2.6065)	
[2022-01-25 13:31:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][980/1251]	eta 0:09:56 lr 0.000088	time 2.2398 (2.2026)	loss 3.3949 (3.1028)	grad_norm 2.3973 (2.6095)	
[2022-01-25 13:32:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][990/1251]	eta 0:09:34 lr 0.000088	time 2.0892 (2.2023)	loss 3.3568 (3.1042)	grad_norm 2.6413 (2.6092)	
[2022-01-25 13:32:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1000/1251]	eta 0:09:13 lr 0.000088	time 4.9739 (2.2042)	loss 3.1754 (3.1037)	grad_norm 2.5494 (2.6083)	
[2022-01-25 13:33:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1010/1251]	eta 0:08:50 lr 0.000088	time 2.2082 (2.2023)	loss 3.2056 (3.1043)	grad_norm 2.2002 (2.6085)	
[2022-01-25 13:33:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1020/1251]	eta 0:08:28 lr 0.000088	time 1.4929 (2.2028)	loss 2.2745 (3.1046)	grad_norm 2.6987 (2.6081)	
[2022-01-25 13:33:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1030/1251]	eta 0:08:06 lr 0.000088	time 2.2074 (2.2015)	loss 3.7418 (3.1051)	grad_norm 4.2867 (2.6100)	
[2022-01-25 13:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1040/1251]	eta 0:07:44 lr 0.000088	time 3.4499 (2.2022)	loss 3.1940 (3.1073)	grad_norm 2.7701 (2.6108)	
[2022-01-25 13:34:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1050/1251]	eta 0:07:22 lr 0.000088	time 3.4436 (2.2034)	loss 3.6756 (3.1082)	grad_norm 2.2979 (2.6111)	
[2022-01-25 13:34:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1060/1251]	eta 0:07:00 lr 0.000087	time 1.8654 (2.2038)	loss 2.8708 (3.1079)	grad_norm 3.0143 (2.6111)	
[2022-01-25 13:35:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1070/1251]	eta 0:06:38 lr 0.000087	time 1.7686 (2.2032)	loss 3.2498 (3.1085)	grad_norm 2.6391 (2.6113)	
[2022-01-25 13:35:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1080/1251]	eta 0:06:16 lr 0.000087	time 2.4653 (2.2027)	loss 2.3304 (3.1064)	grad_norm 2.7620 (2.6101)	
[2022-01-25 13:35:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1090/1251]	eta 0:05:54 lr 0.000087	time 2.9024 (2.2011)	loss 3.3920 (3.1078)	grad_norm 2.9196 (2.6109)	
[2022-01-25 13:36:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1100/1251]	eta 0:05:32 lr 0.000087	time 1.9233 (2.2010)	loss 3.6203 (3.1051)	grad_norm 2.5191 (2.6105)	
[2022-01-25 13:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1110/1251]	eta 0:05:10 lr 0.000087	time 2.1856 (2.1999)	loss 3.1064 (3.1060)	grad_norm 2.5405 (2.6100)	
[2022-01-25 13:37:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1120/1251]	eta 0:04:48 lr 0.000087	time 2.5905 (2.2002)	loss 3.0090 (3.1063)	grad_norm 2.5580 (2.6099)	
[2022-01-25 13:37:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1130/1251]	eta 0:04:26 lr 0.000087	time 4.5491 (2.2023)	loss 3.5196 (3.1054)	grad_norm 2.4331 (2.6107)	
[2022-01-25 13:37:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1140/1251]	eta 0:04:04 lr 0.000087	time 1.5219 (2.2010)	loss 2.7768 (3.1052)	grad_norm 2.4816 (2.6099)	
[2022-01-25 13:38:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1150/1251]	eta 0:03:42 lr 0.000087	time 2.1892 (2.2001)	loss 3.4025 (3.1034)	grad_norm 2.5542 (2.6092)	
[2022-01-25 13:38:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1160/1251]	eta 0:03:20 lr 0.000087	time 1.8669 (2.2000)	loss 3.3403 (3.1047)	grad_norm 2.7048 (2.6112)	
[2022-01-25 13:38:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1170/1251]	eta 0:02:58 lr 0.000087	time 2.4930 (2.1996)	loss 3.4658 (3.1052)	grad_norm 2.3751 (2.6101)	
[2022-01-25 13:39:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1180/1251]	eta 0:02:36 lr 0.000087	time 2.1614 (2.1993)	loss 3.8028 (3.1067)	grad_norm 2.3464 (2.6101)	
[2022-01-25 13:39:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1190/1251]	eta 0:02:14 lr 0.000087	time 2.1707 (2.1995)	loss 3.6791 (3.1068)	grad_norm 2.3296 (2.6095)	
[2022-01-25 13:39:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1200/1251]	eta 0:01:52 lr 0.000087	time 2.5248 (2.1991)	loss 3.5000 (3.1083)	grad_norm 2.6837 (2.6112)	
[2022-01-25 13:40:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1210/1251]	eta 0:01:30 lr 0.000087	time 2.2196 (2.1991)	loss 3.0974 (3.1079)	grad_norm 2.4114 (2.6112)	
[2022-01-25 13:40:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1220/1251]	eta 0:01:08 lr 0.000087	time 2.2745 (2.1998)	loss 2.8948 (3.1096)	grad_norm 2.2218 (2.6103)	
[2022-01-25 13:41:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1230/1251]	eta 0:00:46 lr 0.000087	time 1.8295 (2.1997)	loss 2.5462 (3.1092)	grad_norm 2.2558 (2.6106)	
[2022-01-25 13:41:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1240/1251]	eta 0:00:24 lr 0.000087	time 1.4065 (2.1986)	loss 2.0744 (3.1080)	grad_norm 2.4358 (2.6108)	
[2022-01-25 13:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [245/300][1250/1251]	eta 0:00:02 lr 0.000087	time 1.3216 (2.1931)	loss 2.2117 (3.1082)	grad_norm 2.6990 (2.6099)	
[2022-01-25 13:41:37 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 245 training takes 0:45:43
[2022-01-25 13:41:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.441 (18.441)	Loss 0.9066 (0.9066)	Acc@1 77.344 (77.344)	Acc@5 94.922 (94.922)	
[2022-01-25 13:42:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.250 (3.260)	Loss 0.8385 (0.8632)	Acc@1 79.688 (79.537)	Acc@5 95.117 (95.259)	
[2022-01-25 13:42:32 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.535 (2.615)	Loss 0.8977 (0.8623)	Acc@1 79.199 (79.822)	Acc@5 95.215 (95.261)	
[2022-01-25 13:42:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.916 (2.278)	Loss 0.8045 (0.8605)	Acc@1 81.641 (79.880)	Acc@5 95.898 (95.196)	
[2022-01-25 13:43:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.572 (2.192)	Loss 0.7698 (0.8537)	Acc@1 80.859 (79.983)	Acc@5 96.289 (95.217)	
[2022-01-25 13:43:14 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.034 Acc@5 95.230
[2022-01-25 13:43:14 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.0%
[2022-01-25 13:43:14 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.18%
[2022-01-25 13:43:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][0/1251]	eta 7:40:36 lr 0.000087	time 22.0911 (22.0911)	loss 3.5991 (3.5991)	grad_norm 2.6240 (2.6240)	
[2022-01-25 13:43:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][10/1251]	eta 1:25:51 lr 0.000087	time 1.7730 (4.1508)	loss 3.3061 (3.2821)	grad_norm 2.5434 (2.5609)	
[2022-01-25 13:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][20/1251]	eta 1:10:19 lr 0.000087	time 1.6133 (3.4281)	loss 2.4001 (3.1447)	grad_norm 2.7339 (2.5226)	
[2022-01-25 13:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][30/1251]	eta 1:01:48 lr 0.000087	time 1.9444 (3.0370)	loss 3.2094 (3.1935)	grad_norm 2.7577 (2.5253)	
[2022-01-25 13:45:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][40/1251]	eta 0:57:11 lr 0.000087	time 2.7815 (2.8334)	loss 3.0791 (3.1524)	grad_norm 2.2851 (2.5132)	
[2022-01-25 13:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][50/1251]	eta 0:53:46 lr 0.000087	time 1.7934 (2.6869)	loss 2.1707 (3.1075)	grad_norm 2.5358 (2.4848)	
[2022-01-25 13:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][60/1251]	eta 0:51:12 lr 0.000087	time 2.1271 (2.5799)	loss 3.8175 (3.1315)	grad_norm 2.6024 (2.4950)	
[2022-01-25 13:46:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][70/1251]	eta 0:49:11 lr 0.000087	time 1.5622 (2.4994)	loss 3.1817 (3.1374)	grad_norm 2.3520 (2.5398)	
[2022-01-25 13:46:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][80/1251]	eta 0:47:54 lr 0.000087	time 2.4894 (2.4546)	loss 3.3840 (3.1382)	grad_norm 2.3433 (2.5526)	
[2022-01-25 13:46:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][90/1251]	eta 0:46:46 lr 0.000087	time 2.1709 (2.4175)	loss 2.4462 (3.0940)	grad_norm 2.2878 (2.5475)	
[2022-01-25 13:47:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][100/1251]	eta 0:46:06 lr 0.000087	time 1.7354 (2.4038)	loss 3.3768 (3.0973)	grad_norm 2.3214 (2.5474)	
[2022-01-25 13:47:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][110/1251]	eta 0:45:08 lr 0.000087	time 1.8628 (2.3739)	loss 3.2395 (3.0855)	grad_norm 2.4902 (2.5407)	
[2022-01-25 13:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][120/1251]	eta 0:44:57 lr 0.000087	time 3.4188 (2.3852)	loss 2.7612 (3.0850)	grad_norm 3.2711 (2.5501)	
[2022-01-25 13:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][130/1251]	eta 0:44:22 lr 0.000087	time 1.9213 (2.3753)	loss 2.8539 (3.0867)	grad_norm 2.9398 (2.5465)	
[2022-01-25 13:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][140/1251]	eta 0:43:44 lr 0.000087	time 1.8643 (2.3622)	loss 2.7624 (3.0798)	grad_norm 2.8690 (2.5522)	
[2022-01-25 13:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][150/1251]	eta 0:43:07 lr 0.000087	time 2.5657 (2.3501)	loss 3.4893 (3.0766)	grad_norm 2.8533 (2.5573)	
[2022-01-25 13:49:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][160/1251]	eta 0:42:25 lr 0.000087	time 1.8737 (2.3328)	loss 2.2375 (3.0917)	grad_norm 2.4892 (2.5622)	
[2022-01-25 13:49:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][170/1251]	eta 0:41:44 lr 0.000087	time 1.8795 (2.3164)	loss 2.3578 (3.0732)	grad_norm 2.4478 (2.5644)	
[2022-01-25 13:50:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][180/1251]	eta 0:41:06 lr 0.000087	time 1.9421 (2.3034)	loss 2.8208 (3.0738)	grad_norm 2.5245 (2.5569)	
[2022-01-25 13:50:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][190/1251]	eta 0:40:40 lr 0.000087	time 1.8508 (2.2999)	loss 2.9463 (3.0729)	grad_norm 2.3840 (2.5555)	
[2022-01-25 13:50:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][200/1251]	eta 0:40:21 lr 0.000087	time 1.9422 (2.3038)	loss 3.6108 (3.0779)	grad_norm 2.5523 (2.5548)	
[2022-01-25 13:51:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][210/1251]	eta 0:39:58 lr 0.000087	time 1.8124 (2.3036)	loss 2.1709 (3.0827)	grad_norm 2.5665 (2.5561)	
[2022-01-25 13:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][220/1251]	eta 0:39:26 lr 0.000087	time 1.6669 (2.2958)	loss 2.5182 (3.0922)	grad_norm 2.3921 (2.5552)	
[2022-01-25 13:52:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][230/1251]	eta 0:38:53 lr 0.000087	time 1.6988 (2.2853)	loss 2.2522 (3.0959)	grad_norm 2.8591 (2.5653)	
[2022-01-25 13:52:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][240/1251]	eta 0:38:27 lr 0.000087	time 1.6858 (2.2824)	loss 3.2289 (3.0927)	grad_norm 2.3621 (2.5628)	
[2022-01-25 13:52:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][250/1251]	eta 0:37:59 lr 0.000087	time 1.9373 (2.2770)	loss 3.5527 (3.0942)	grad_norm 2.6948 (2.5714)	
[2022-01-25 13:53:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][260/1251]	eta 0:37:39 lr 0.000086	time 2.0069 (2.2804)	loss 3.2972 (3.0976)	grad_norm 2.6819 (2.5730)	
[2022-01-25 13:53:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][270/1251]	eta 0:37:07 lr 0.000086	time 1.6046 (2.2705)	loss 2.5421 (3.0850)	grad_norm 3.2504 (2.5767)	
[2022-01-25 13:53:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][280/1251]	eta 0:36:35 lr 0.000086	time 1.8104 (2.2611)	loss 3.4169 (3.0918)	grad_norm 2.5919 (2.5782)	
[2022-01-25 13:54:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][290/1251]	eta 0:36:27 lr 0.000086	time 1.5463 (2.2764)	loss 3.1976 (3.0936)	grad_norm 2.7692 (2.5802)	
[2022-01-25 13:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][300/1251]	eta 0:36:01 lr 0.000086	time 1.5992 (2.2729)	loss 2.7785 (3.0887)	grad_norm 2.2027 (2.5795)	
[2022-01-25 13:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][310/1251]	eta 0:35:38 lr 0.000086	time 2.1203 (2.2724)	loss 3.5555 (3.1016)	grad_norm 2.5283 (2.5777)	
[2022-01-25 13:55:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][320/1251]	eta 0:35:07 lr 0.000086	time 1.8728 (2.2638)	loss 2.1372 (3.1005)	grad_norm 2.4231 (2.5770)	
[2022-01-25 13:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][330/1251]	eta 0:34:42 lr 0.000086	time 2.0058 (2.2612)	loss 3.3921 (3.1027)	grad_norm 2.4575 (2.5777)	
[2022-01-25 13:56:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][340/1251]	eta 0:34:28 lr 0.000086	time 1.9400 (2.2709)	loss 3.0814 (3.1081)	grad_norm 2.4734 (2.5762)	
[2022-01-25 13:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][350/1251]	eta 0:34:00 lr 0.000086	time 1.6990 (2.2652)	loss 3.4983 (3.1064)	grad_norm 2.6084 (2.5773)	
[2022-01-25 13:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][360/1251]	eta 0:33:33 lr 0.000086	time 1.9082 (2.2600)	loss 2.7072 (3.1083)	grad_norm 2.3233 (2.5754)	
[2022-01-25 13:57:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][370/1251]	eta 0:33:05 lr 0.000086	time 1.6334 (2.2533)	loss 1.9103 (3.1090)	grad_norm 2.3585 (2.5744)	
[2022-01-25 13:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][380/1251]	eta 0:32:45 lr 0.000086	time 2.1160 (2.2572)	loss 3.6555 (3.1114)	grad_norm 2.7469 (2.5729)	
[2022-01-25 13:57:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][390/1251]	eta 0:32:20 lr 0.000086	time 1.9141 (2.2538)	loss 3.2244 (3.1140)	grad_norm 2.9961 (2.5711)	
[2022-01-25 13:58:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][400/1251]	eta 0:31:54 lr 0.000086	time 2.5118 (2.2492)	loss 2.1600 (3.1076)	grad_norm 2.7792 (2.5697)	
[2022-01-25 13:58:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][410/1251]	eta 0:31:27 lr 0.000086	time 1.9052 (2.2438)	loss 3.7017 (3.1133)	grad_norm 2.5708 (2.5693)	
[2022-01-25 13:59:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][420/1251]	eta 0:31:08 lr 0.000086	time 2.1766 (2.2481)	loss 2.1081 (3.1104)	grad_norm 2.4666 (2.5720)	
[2022-01-25 13:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][430/1251]	eta 0:30:46 lr 0.000086	time 1.8531 (2.2491)	loss 3.4015 (3.1116)	grad_norm 2.5136 (2.5740)	
[2022-01-25 13:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][440/1251]	eta 0:30:22 lr 0.000086	time 1.7688 (2.2469)	loss 2.7256 (3.1151)	grad_norm 2.9214 (2.5729)	
[2022-01-25 14:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][450/1251]	eta 0:29:55 lr 0.000086	time 1.6048 (2.2413)	loss 3.6555 (3.1195)	grad_norm 2.4188 (2.5730)	
[2022-01-25 14:00:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][460/1251]	eta 0:29:30 lr 0.000086	time 1.8681 (2.2388)	loss 2.9307 (3.1206)	grad_norm 2.4690 (2.5725)	
[2022-01-25 14:00:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][470/1251]	eta 0:29:08 lr 0.000086	time 2.2937 (2.2389)	loss 3.1965 (3.1235)	grad_norm 2.6386 (2.5757)	
[2022-01-25 14:01:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][480/1251]	eta 0:28:43 lr 0.000086	time 2.1777 (2.2352)	loss 3.2564 (3.1289)	grad_norm 2.4625 (2.5745)	
[2022-01-25 14:01:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][490/1251]	eta 0:28:19 lr 0.000086	time 1.9953 (2.2332)	loss 3.6980 (3.1351)	grad_norm 2.5350 (2.5773)	
[2022-01-25 14:01:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][500/1251]	eta 0:27:54 lr 0.000086	time 2.4554 (2.2303)	loss 2.0814 (3.1297)	grad_norm 2.7134 (2.5828)	
[2022-01-25 14:02:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][510/1251]	eta 0:27:32 lr 0.000086	time 2.5418 (2.2300)	loss 2.7902 (3.1303)	grad_norm 3.1475 (2.5895)	
[2022-01-25 14:02:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][520/1251]	eta 0:27:09 lr 0.000086	time 1.5144 (2.2286)	loss 3.7314 (3.1282)	grad_norm 2.8299 (2.5948)	
[2022-01-25 14:02:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][530/1251]	eta 0:26:46 lr 0.000086	time 1.6506 (2.2276)	loss 3.6992 (3.1257)	grad_norm 2.6653 (2.5992)	
[2022-01-25 14:03:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][540/1251]	eta 0:26:24 lr 0.000086	time 2.0752 (2.2288)	loss 2.0313 (3.1212)	grad_norm 3.1870 (2.6036)	
[2022-01-25 14:03:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][550/1251]	eta 0:26:05 lr 0.000086	time 2.4919 (2.2329)	loss 3.8313 (3.1221)	grad_norm 2.9459 (2.6022)	
[2022-01-25 14:04:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][560/1251]	eta 0:25:43 lr 0.000086	time 1.4951 (2.2339)	loss 2.1813 (3.1169)	grad_norm 2.7201 (2.6021)	
[2022-01-25 14:04:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][570/1251]	eta 0:25:19 lr 0.000086	time 1.6590 (2.2313)	loss 3.3211 (3.1193)	grad_norm 6.6183 (2.6081)	
[2022-01-25 14:04:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][580/1251]	eta 0:24:54 lr 0.000086	time 1.8183 (2.2278)	loss 3.0168 (3.1172)	grad_norm 3.1116 (2.6075)	
[2022-01-25 14:05:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][590/1251]	eta 0:24:30 lr 0.000086	time 1.7744 (2.2242)	loss 2.3553 (3.1131)	grad_norm 2.9225 (2.6132)	
[2022-01-25 14:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][600/1251]	eta 0:24:06 lr 0.000086	time 1.8310 (2.2218)	loss 4.0332 (3.1116)	grad_norm 2.9877 (2.6129)	
[2022-01-25 14:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][610/1251]	eta 0:23:43 lr 0.000086	time 2.5185 (2.2206)	loss 3.9557 (3.1147)	grad_norm 2.8828 (2.6158)	
[2022-01-25 14:06:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][620/1251]	eta 0:23:20 lr 0.000086	time 2.4210 (2.2200)	loss 3.4679 (3.1191)	grad_norm 2.5506 (2.6156)	
[2022-01-25 14:06:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][630/1251]	eta 0:22:57 lr 0.000086	time 2.7771 (2.2189)	loss 3.1908 (3.1168)	grad_norm 2.5441 (2.6141)	
[2022-01-25 14:06:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][640/1251]	eta 0:22:35 lr 0.000086	time 1.6049 (2.2184)	loss 3.6141 (3.1160)	grad_norm 2.5875 (2.6136)	
[2022-01-25 14:07:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][650/1251]	eta 0:22:13 lr 0.000086	time 1.8955 (2.2190)	loss 3.2238 (3.1187)	grad_norm 2.2949 (2.6127)	
[2022-01-25 14:07:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][660/1251]	eta 0:21:52 lr 0.000086	time 2.2327 (2.2208)	loss 2.0985 (3.1137)	grad_norm 2.3570 (2.6123)	
[2022-01-25 14:08:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][670/1251]	eta 0:21:29 lr 0.000086	time 2.5191 (2.2201)	loss 2.5938 (3.1106)	grad_norm 2.4070 (2.6112)	
[2022-01-25 14:08:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][680/1251]	eta 0:21:07 lr 0.000086	time 1.5973 (2.2192)	loss 3.2383 (3.1097)	grad_norm 2.3744 (2.6097)	
[2022-01-25 14:08:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][690/1251]	eta 0:20:43 lr 0.000086	time 1.6376 (2.2165)	loss 2.1406 (3.1053)	grad_norm 2.5109 (2.6105)	
[2022-01-25 14:09:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][700/1251]	eta 0:20:20 lr 0.000086	time 2.5372 (2.2150)	loss 2.5862 (3.1011)	grad_norm 3.3490 (2.6099)	
[2022-01-25 14:09:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][710/1251]	eta 0:19:58 lr 0.000085	time 2.2278 (2.2153)	loss 3.3939 (3.0966)	grad_norm 2.9147 (2.6100)	
[2022-01-25 14:09:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][720/1251]	eta 0:19:36 lr 0.000085	time 2.1510 (2.2150)	loss 3.7696 (3.0965)	grad_norm 2.3534 (2.6097)	
[2022-01-25 14:10:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][730/1251]	eta 0:19:14 lr 0.000085	time 2.0136 (2.2159)	loss 3.2695 (3.0965)	grad_norm 2.4466 (2.6109)	
[2022-01-25 14:10:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][740/1251]	eta 0:18:52 lr 0.000085	time 1.7346 (2.2168)	loss 2.4443 (3.0985)	grad_norm 2.3380 (2.6124)	
[2022-01-25 14:10:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][750/1251]	eta 0:18:30 lr 0.000085	time 1.8202 (2.2174)	loss 2.3089 (3.0978)	grad_norm 4.0881 (2.6175)	
[2022-01-25 14:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][760/1251]	eta 0:18:09 lr 0.000085	time 3.2875 (2.2197)	loss 3.0239 (3.0976)	grad_norm 2.6713 (2.6232)	
[2022-01-25 14:11:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][770/1251]	eta 0:17:47 lr 0.000085	time 1.8253 (2.2186)	loss 2.4186 (3.0974)	grad_norm 3.5830 (2.6267)	
[2022-01-25 14:12:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][780/1251]	eta 0:17:24 lr 0.000085	time 1.8259 (2.2174)	loss 2.6277 (3.0967)	grad_norm 2.5759 (2.6252)	
[2022-01-25 14:12:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][790/1251]	eta 0:17:00 lr 0.000085	time 2.0152 (2.2147)	loss 3.3627 (3.0987)	grad_norm 2.3571 (2.6265)	
[2022-01-25 14:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][800/1251]	eta 0:16:38 lr 0.000085	time 2.7972 (2.2148)	loss 3.5880 (3.0999)	grad_norm 2.3577 (2.6248)	
[2022-01-25 14:13:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][810/1251]	eta 0:16:16 lr 0.000085	time 1.5591 (2.2142)	loss 2.7952 (3.1009)	grad_norm 2.1568 (2.6238)	
[2022-01-25 14:13:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][820/1251]	eta 0:15:53 lr 0.000085	time 1.6669 (2.2120)	loss 3.3821 (3.1024)	grad_norm 2.4058 (2.6223)	
[2022-01-25 14:13:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][830/1251]	eta 0:15:30 lr 0.000085	time 2.1711 (2.2112)	loss 2.7576 (3.0976)	grad_norm 2.7843 (2.6216)	
[2022-01-25 14:14:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][840/1251]	eta 0:15:08 lr 0.000085	time 3.4083 (2.2114)	loss 3.2700 (3.0980)	grad_norm 2.3321 (2.6204)	
[2022-01-25 14:14:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][850/1251]	eta 0:14:46 lr 0.000085	time 1.8165 (2.2111)	loss 2.7056 (3.0978)	grad_norm 2.5612 (2.6194)	
[2022-01-25 14:14:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][860/1251]	eta 0:14:25 lr 0.000085	time 2.1400 (2.2125)	loss 3.5215 (3.0996)	grad_norm 2.5713 (2.6197)	
[2022-01-25 14:15:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][870/1251]	eta 0:14:02 lr 0.000085	time 1.8075 (2.2121)	loss 3.2227 (3.1009)	grad_norm 2.2823 (2.6190)	
[2022-01-25 14:15:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][880/1251]	eta 0:13:40 lr 0.000085	time 2.9136 (2.2123)	loss 3.7100 (3.1026)	grad_norm 2.8172 (2.6189)	
[2022-01-25 14:16:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][890/1251]	eta 0:13:18 lr 0.000085	time 2.1897 (2.2109)	loss 2.9498 (3.1027)	grad_norm 2.8211 (2.6182)	
[2022-01-25 14:16:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][900/1251]	eta 0:12:56 lr 0.000085	time 2.2068 (2.2110)	loss 3.4245 (3.1025)	grad_norm 2.5879 (2.6178)	
[2022-01-25 14:16:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][910/1251]	eta 0:12:33 lr 0.000085	time 1.8610 (2.2106)	loss 2.9210 (3.1032)	grad_norm 2.7191 (2.6353)	
[2022-01-25 14:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][920/1251]	eta 0:12:12 lr 0.000085	time 3.1657 (2.2127)	loss 3.1816 (3.1049)	grad_norm 2.4740 (2.6352)	
[2022-01-25 14:17:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][930/1251]	eta 0:11:50 lr 0.000085	time 1.6803 (2.2124)	loss 3.4384 (3.1065)	grad_norm 2.2973 (2.6340)	
[2022-01-25 14:17:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][940/1251]	eta 0:11:27 lr 0.000085	time 1.7109 (2.2101)	loss 3.8020 (3.1069)	grad_norm 3.2251 (2.6363)	
[2022-01-25 14:18:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][950/1251]	eta 0:11:04 lr 0.000085	time 1.7748 (2.2093)	loss 3.3266 (3.1077)	grad_norm 2.1461 (2.6355)	
[2022-01-25 14:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][960/1251]	eta 0:10:43 lr 0.000085	time 2.9153 (2.2097)	loss 3.5992 (3.1085)	grad_norm 2.5024 (2.6338)	
[2022-01-25 14:18:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][970/1251]	eta 0:10:20 lr 0.000085	time 1.8924 (2.2096)	loss 3.2271 (3.1092)	grad_norm 2.3623 (2.6325)	
[2022-01-25 14:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][980/1251]	eta 0:09:58 lr 0.000085	time 2.5454 (2.2101)	loss 2.7194 (3.1091)	grad_norm 2.3337 (2.6321)	
[2022-01-25 14:19:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][990/1251]	eta 0:09:36 lr 0.000085	time 1.7521 (2.2091)	loss 2.7132 (3.1104)	grad_norm 2.7193 (2.6323)	
[2022-01-25 14:20:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1000/1251]	eta 0:09:14 lr 0.000085	time 2.9243 (2.2089)	loss 3.4377 (3.1096)	grad_norm 3.1863 (2.6305)	
[2022-01-25 14:20:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1010/1251]	eta 0:08:51 lr 0.000085	time 2.0492 (2.2063)	loss 3.1950 (3.1094)	grad_norm 2.3759 (2.6302)	
[2022-01-25 14:20:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1020/1251]	eta 0:08:29 lr 0.000085	time 1.8915 (2.2047)	loss 3.3179 (3.1083)	grad_norm 2.4133 (2.6283)	
[2022-01-25 14:21:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1030/1251]	eta 0:08:07 lr 0.000085	time 2.4158 (2.2041)	loss 3.7313 (3.1105)	grad_norm 2.3408 (2.6270)	
[2022-01-25 14:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1040/1251]	eta 0:07:45 lr 0.000085	time 2.5372 (2.2050)	loss 3.6151 (3.1097)	grad_norm 3.1029 (2.6275)	
[2022-01-25 14:21:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1050/1251]	eta 0:07:23 lr 0.000085	time 2.6605 (2.2057)	loss 3.5271 (3.1089)	grad_norm 2.7946 (2.6270)	
[2022-01-25 14:22:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1060/1251]	eta 0:07:01 lr 0.000085	time 2.5692 (2.2063)	loss 3.0233 (3.1089)	grad_norm 2.5847 (2.6279)	
[2022-01-25 14:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1070/1251]	eta 0:06:39 lr 0.000085	time 1.8210 (2.2051)	loss 2.6108 (3.1069)	grad_norm 3.1528 (2.6283)	
[2022-01-25 14:22:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1080/1251]	eta 0:06:17 lr 0.000085	time 3.2406 (2.2053)	loss 2.3801 (3.1051)	grad_norm 2.4708 (2.6269)	
[2022-01-25 14:23:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1090/1251]	eta 0:05:55 lr 0.000085	time 2.5018 (2.2052)	loss 2.9752 (3.1050)	grad_norm 2.6912 (2.6264)	
[2022-01-25 14:23:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1100/1251]	eta 0:05:32 lr 0.000085	time 1.6023 (2.2050)	loss 2.4631 (3.1036)	grad_norm 2.7107 (2.6270)	
[2022-01-25 14:24:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1110/1251]	eta 0:05:10 lr 0.000085	time 1.9649 (2.2030)	loss 2.9067 (3.1028)	grad_norm 3.2588 (2.6282)	
[2022-01-25 14:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1120/1251]	eta 0:04:48 lr 0.000085	time 4.1698 (2.2054)	loss 3.5013 (3.1057)	grad_norm 3.7326 (2.6316)	
[2022-01-25 14:24:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1130/1251]	eta 0:04:26 lr 0.000085	time 1.8564 (2.2038)	loss 2.9976 (3.1069)	grad_norm 2.5712 (2.6324)	
[2022-01-25 14:25:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1140/1251]	eta 0:04:04 lr 0.000085	time 2.2967 (2.2032)	loss 2.8150 (3.1066)	grad_norm 2.4349 (2.6316)	
[2022-01-25 14:25:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1150/1251]	eta 0:03:42 lr 0.000085	time 2.4739 (2.2033)	loss 2.6239 (3.1062)	grad_norm 3.7309 (2.6319)	
[2022-01-25 14:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1160/1251]	eta 0:03:20 lr 0.000085	time 3.0354 (2.2034)	loss 3.5319 (3.1054)	grad_norm 2.3681 (2.6319)	
[2022-01-25 14:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1170/1251]	eta 0:02:58 lr 0.000084	time 2.2634 (2.2034)	loss 3.1835 (3.1054)	grad_norm 2.2431 (2.6317)	
[2022-01-25 14:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1180/1251]	eta 0:02:36 lr 0.000084	time 1.6135 (2.2020)	loss 3.0775 (3.1072)	grad_norm 2.5538 (2.6308)	
[2022-01-25 14:26:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1190/1251]	eta 0:02:14 lr 0.000084	time 2.5493 (2.2012)	loss 2.2498 (3.1068)	grad_norm 2.1810 (2.6304)	
[2022-01-25 14:27:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1200/1251]	eta 0:01:52 lr 0.000084	time 3.1141 (2.2020)	loss 3.1838 (3.1080)	grad_norm 2.5916 (2.6300)	
[2022-01-25 14:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1210/1251]	eta 0:01:30 lr 0.000084	time 2.2786 (2.2025)	loss 2.1707 (3.1065)	grad_norm 2.9984 (2.6299)	
[2022-01-25 14:28:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1220/1251]	eta 0:01:08 lr 0.000084	time 2.0713 (2.2024)	loss 3.4349 (3.1062)	grad_norm 2.4985 (2.6287)	
[2022-01-25 14:28:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1230/1251]	eta 0:00:46 lr 0.000084	time 2.1012 (2.2020)	loss 2.3278 (3.1051)	grad_norm 2.4187 (2.6282)	
[2022-01-25 14:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1240/1251]	eta 0:00:24 lr 0.000084	time 2.3119 (2.2015)	loss 2.8854 (3.1062)	grad_norm 2.7494 (2.6281)	
[2022-01-25 14:29:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [246/300][1250/1251]	eta 0:00:02 lr 0.000084	time 1.1933 (2.1954)	loss 2.7437 (3.1070)	grad_norm 2.7939 (2.6284)	
[2022-01-25 14:29:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 246 training takes 0:45:46
[2022-01-25 14:29:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.579 (18.579)	Loss 0.7780 (0.7780)	Acc@1 80.371 (80.371)	Acc@5 95.898 (95.898)	
[2022-01-25 14:29:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.959 (3.342)	Loss 0.8974 (0.8541)	Acc@1 79.883 (79.616)	Acc@5 94.336 (95.135)	
[2022-01-25 14:29:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.259 (2.543)	Loss 0.8890 (0.8394)	Acc@1 78.027 (79.994)	Acc@5 93.750 (95.206)	
[2022-01-25 14:30:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.948 (2.285)	Loss 0.9194 (0.8307)	Acc@1 79.395 (80.232)	Acc@5 93.848 (95.325)	
[2022-01-25 14:30:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.189 (2.145)	Loss 0.7816 (0.8297)	Acc@1 81.348 (80.290)	Acc@5 95.801 (95.322)	
[2022-01-25 14:30:36 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.240 Acc@5 95.266
[2022-01-25 14:30:36 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.2%
[2022-01-25 14:30:36 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.24%
[2022-01-25 14:30:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][0/1251]	eta 7:29:30 lr 0.000084	time 21.5590 (21.5590)	loss 2.4366 (2.4366)	grad_norm 2.3305 (2.3305)	
[2022-01-25 14:31:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][10/1251]	eta 1:22:49 lr 0.000084	time 1.8364 (4.0041)	loss 3.3996 (3.2022)	grad_norm 2.5634 (2.6648)	
[2022-01-25 14:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][20/1251]	eta 1:03:23 lr 0.000084	time 1.9288 (3.0899)	loss 3.8158 (3.2126)	grad_norm 2.5840 (2.6420)	
[2022-01-25 14:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][30/1251]	eta 0:57:09 lr 0.000084	time 2.1994 (2.8084)	loss 3.1682 (3.1592)	grad_norm 2.6157 (2.6742)	
[2022-01-25 14:32:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][40/1251]	eta 0:54:30 lr 0.000084	time 3.6686 (2.7011)	loss 3.8071 (3.1461)	grad_norm 3.5084 (2.6574)	
[2022-01-25 14:32:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][50/1251]	eta 0:51:59 lr 0.000084	time 1.2629 (2.5975)	loss 3.6837 (3.1070)	grad_norm 2.2399 (2.6238)	
[2022-01-25 14:33:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][60/1251]	eta 0:50:46 lr 0.000084	time 2.7733 (2.5581)	loss 3.4494 (3.1143)	grad_norm 2.9068 (2.6416)	
[2022-01-25 14:33:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][70/1251]	eta 0:49:11 lr 0.000084	time 1.8660 (2.4990)	loss 3.4585 (3.1309)	grad_norm 2.3616 (2.6466)	
[2022-01-25 14:33:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][80/1251]	eta 0:48:16 lr 0.000084	time 3.4787 (2.4736)	loss 2.1368 (3.1020)	grad_norm 2.8118 (2.6569)	
[2022-01-25 14:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][90/1251]	eta 0:46:54 lr 0.000084	time 1.5687 (2.4241)	loss 2.6663 (3.0914)	grad_norm 2.4092 (2.6320)	
[2022-01-25 14:34:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][100/1251]	eta 0:45:53 lr 0.000084	time 2.2137 (2.3923)	loss 3.4566 (3.0902)	grad_norm 2.6535 (2.6259)	
[2022-01-25 14:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][110/1251]	eta 0:45:07 lr 0.000084	time 1.5997 (2.3731)	loss 2.3544 (3.0977)	grad_norm 2.4958 (2.6318)	
[2022-01-25 14:35:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][120/1251]	eta 0:44:54 lr 0.000084	time 3.9701 (2.3821)	loss 3.4369 (3.0814)	grad_norm 3.0640 (2.6495)	
[2022-01-25 14:35:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][130/1251]	eta 0:44:18 lr 0.000084	time 2.3202 (2.3714)	loss 3.3029 (3.0862)	grad_norm 2.5140 (2.6484)	
[2022-01-25 14:36:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][140/1251]	eta 0:43:44 lr 0.000084	time 2.1800 (2.3626)	loss 3.3870 (3.0927)	grad_norm 2.6790 (2.6424)	
[2022-01-25 14:36:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][150/1251]	eta 0:43:10 lr 0.000084	time 1.8315 (2.3532)	loss 2.9019 (3.0980)	grad_norm 2.5987 (2.6364)	
[2022-01-25 14:36:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][160/1251]	eta 0:42:32 lr 0.000084	time 3.1971 (2.3399)	loss 3.4434 (3.0858)	grad_norm 2.3962 (2.6435)	
[2022-01-25 14:37:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][170/1251]	eta 0:41:49 lr 0.000084	time 1.9085 (2.3213)	loss 2.7870 (3.0883)	grad_norm 2.3510 (2.6359)	
[2022-01-25 14:37:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][180/1251]	eta 0:41:15 lr 0.000084	time 1.9202 (2.3115)	loss 3.2854 (3.1023)	grad_norm 2.7386 (2.6349)	
[2022-01-25 14:37:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][190/1251]	eta 0:40:42 lr 0.000084	time 1.8752 (2.3025)	loss 2.2272 (3.0895)	grad_norm 2.1841 (2.6274)	
[2022-01-25 14:38:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][200/1251]	eta 0:40:11 lr 0.000084	time 1.9499 (2.2949)	loss 2.9371 (3.0814)	grad_norm 2.7751 (2.6376)	
[2022-01-25 14:38:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][210/1251]	eta 0:39:44 lr 0.000084	time 2.9043 (2.2906)	loss 3.1448 (3.0748)	grad_norm 2.6668 (2.6366)	
[2022-01-25 14:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][220/1251]	eta 0:39:18 lr 0.000084	time 2.5629 (2.2872)	loss 3.2847 (3.0891)	grad_norm 2.7169 (2.6372)	
[2022-01-25 14:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][230/1251]	eta 0:38:52 lr 0.000084	time 2.5431 (2.2849)	loss 3.2083 (3.0943)	grad_norm 2.8972 (2.6398)	
[2022-01-25 14:39:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][240/1251]	eta 0:38:26 lr 0.000084	time 2.2245 (2.2813)	loss 3.4160 (3.0959)	grad_norm 2.4131 (2.6468)	
[2022-01-25 14:40:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][250/1251]	eta 0:37:58 lr 0.000084	time 2.8554 (2.2760)	loss 3.6357 (3.0922)	grad_norm 2.3109 (2.6517)	
[2022-01-25 14:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][260/1251]	eta 0:37:36 lr 0.000084	time 1.7551 (2.2769)	loss 2.4610 (3.0962)	grad_norm 2.7437 (2.6614)	
[2022-01-25 14:40:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][270/1251]	eta 0:37:15 lr 0.000084	time 2.7921 (2.2791)	loss 3.2427 (3.0961)	grad_norm 2.6970 (2.6684)	
[2022-01-25 14:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][280/1251]	eta 0:36:53 lr 0.000084	time 2.5087 (2.2797)	loss 2.4646 (3.0921)	grad_norm 2.0172 (2.6626)	
[2022-01-25 14:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][290/1251]	eta 0:36:24 lr 0.000084	time 2.1502 (2.2727)	loss 3.5352 (3.0944)	grad_norm 2.3788 (2.6724)	
[2022-01-25 14:41:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][300/1251]	eta 0:35:53 lr 0.000084	time 2.0573 (2.2642)	loss 2.7916 (3.0950)	grad_norm 2.7675 (2.6758)	
[2022-01-25 14:42:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][310/1251]	eta 0:35:26 lr 0.000084	time 2.7648 (2.2599)	loss 3.3181 (3.0992)	grad_norm 2.4650 (2.6715)	
[2022-01-25 14:42:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][320/1251]	eta 0:35:02 lr 0.000084	time 2.2781 (2.2578)	loss 3.0861 (3.0982)	grad_norm 3.0099 (2.6711)	
[2022-01-25 14:43:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][330/1251]	eta 0:34:37 lr 0.000084	time 1.5289 (2.2556)	loss 2.8910 (3.1034)	grad_norm 2.6663 (2.6700)	
[2022-01-25 14:43:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][340/1251]	eta 0:34:15 lr 0.000084	time 1.9764 (2.2560)	loss 3.2583 (3.0996)	grad_norm 2.2702 (2.6644)	
[2022-01-25 14:43:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][350/1251]	eta 0:33:52 lr 0.000084	time 3.0852 (2.2553)	loss 3.7830 (3.1009)	grad_norm 2.5026 (2.6618)	
[2022-01-25 14:44:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][360/1251]	eta 0:33:30 lr 0.000084	time 3.5576 (2.2563)	loss 2.8484 (3.1003)	grad_norm 1.9987 (2.6563)	
[2022-01-25 14:44:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][370/1251]	eta 0:33:09 lr 0.000083	time 2.0945 (2.2581)	loss 2.8510 (3.0990)	grad_norm 2.6901 (2.6516)	
[2022-01-25 14:44:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][380/1251]	eta 0:32:45 lr 0.000083	time 1.9225 (2.2566)	loss 3.6611 (3.1020)	grad_norm 3.4089 (2.6530)	
[2022-01-25 14:45:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][390/1251]	eta 0:32:23 lr 0.000083	time 2.2049 (2.2568)	loss 2.3454 (3.1018)	grad_norm 2.4454 (2.6527)	
[2022-01-25 14:45:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][400/1251]	eta 0:31:58 lr 0.000083	time 3.3847 (2.2543)	loss 3.1364 (3.1008)	grad_norm 2.3933 (2.6530)	
[2022-01-25 14:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][410/1251]	eta 0:31:31 lr 0.000083	time 1.9751 (2.2496)	loss 3.6354 (3.1075)	grad_norm 2.7044 (2.6547)	
[2022-01-25 14:46:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][420/1251]	eta 0:31:07 lr 0.000083	time 2.1993 (2.2469)	loss 2.8646 (3.0997)	grad_norm 2.3216 (2.6555)	
[2022-01-25 14:46:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][430/1251]	eta 0:30:41 lr 0.000083	time 1.8373 (2.2428)	loss 3.5850 (3.0988)	grad_norm 3.5764 (2.6571)	
[2022-01-25 14:47:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][440/1251]	eta 0:30:22 lr 0.000083	time 3.7100 (2.2475)	loss 3.1489 (3.0987)	grad_norm 3.3556 (2.6572)	
[2022-01-25 14:47:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][450/1251]	eta 0:29:59 lr 0.000083	time 1.7036 (2.2470)	loss 2.2831 (3.0917)	grad_norm 2.5549 (2.6584)	
[2022-01-25 14:47:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][460/1251]	eta 0:29:37 lr 0.000083	time 2.9263 (2.2477)	loss 3.6126 (3.0884)	grad_norm 2.7256 (2.6614)	
[2022-01-25 14:48:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][470/1251]	eta 0:29:13 lr 0.000083	time 1.9977 (2.2450)	loss 3.6711 (3.0853)	grad_norm 2.4196 (2.6586)	
[2022-01-25 14:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][480/1251]	eta 0:28:49 lr 0.000083	time 2.0203 (2.2428)	loss 3.2180 (3.0865)	grad_norm 2.4527 (2.6535)	
[2022-01-25 14:48:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][490/1251]	eta 0:28:21 lr 0.000083	time 1.8462 (2.2359)	loss 3.2518 (3.0897)	grad_norm 2.9545 (2.6546)	
[2022-01-25 14:49:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][500/1251]	eta 0:27:55 lr 0.000083	time 2.2930 (2.2308)	loss 3.3250 (3.0898)	grad_norm 2.7412 (2.6561)	
[2022-01-25 14:49:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][510/1251]	eta 0:27:31 lr 0.000083	time 2.2948 (2.2288)	loss 3.4484 (3.0897)	grad_norm 2.7533 (2.6557)	
[2022-01-25 14:49:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][520/1251]	eta 0:27:10 lr 0.000083	time 3.0323 (2.2299)	loss 2.7932 (3.0892)	grad_norm 2.9168 (2.6600)	
[2022-01-25 14:50:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][530/1251]	eta 0:26:48 lr 0.000083	time 2.0962 (2.2311)	loss 3.1702 (3.0910)	grad_norm 2.8996 (2.6568)	
[2022-01-25 14:50:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][540/1251]	eta 0:26:28 lr 0.000083	time 2.8070 (2.2336)	loss 3.7289 (3.0923)	grad_norm 2.5864 (2.6539)	
[2022-01-25 14:51:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][550/1251]	eta 0:26:05 lr 0.000083	time 2.2095 (2.2338)	loss 3.4125 (3.0980)	grad_norm 2.6575 (2.6539)	
[2022-01-25 14:51:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][560/1251]	eta 0:25:45 lr 0.000083	time 2.9271 (2.2362)	loss 3.0620 (3.0979)	grad_norm 2.5028 (2.6538)	
[2022-01-25 14:51:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][570/1251]	eta 0:25:21 lr 0.000083	time 2.2456 (2.2342)	loss 3.1534 (3.0985)	grad_norm 4.2408 (2.6578)	
[2022-01-25 14:52:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][580/1251]	eta 0:24:56 lr 0.000083	time 2.0394 (2.2300)	loss 2.9166 (3.1005)	grad_norm 2.9481 (2.6560)	
[2022-01-25 14:52:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][590/1251]	eta 0:24:31 lr 0.000083	time 1.9185 (2.2269)	loss 2.4584 (3.1000)	grad_norm 2.6986 (2.6553)	
[2022-01-25 14:52:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][600/1251]	eta 0:24:08 lr 0.000083	time 2.5227 (2.2245)	loss 2.4345 (3.1008)	grad_norm 2.3784 (2.6529)	
[2022-01-25 14:53:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][610/1251]	eta 0:23:46 lr 0.000083	time 2.6211 (2.2256)	loss 3.6458 (3.1038)	grad_norm 2.8929 (2.6543)	
[2022-01-25 14:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][620/1251]	eta 0:23:24 lr 0.000083	time 2.4462 (2.2264)	loss 2.9637 (3.1040)	grad_norm 2.5021 (2.6529)	
[2022-01-25 14:54:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][630/1251]	eta 0:23:01 lr 0.000083	time 1.7576 (2.2249)	loss 3.6394 (3.1049)	grad_norm 2.5229 (2.6525)	
[2022-01-25 14:54:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][640/1251]	eta 0:22:39 lr 0.000083	time 2.1655 (2.2250)	loss 3.5417 (3.1033)	grad_norm 2.4728 (2.6529)	
[2022-01-25 14:54:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][650/1251]	eta 0:22:17 lr 0.000083	time 2.5485 (2.2250)	loss 3.3920 (3.1035)	grad_norm 2.4316 (2.6495)	
[2022-01-25 14:55:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][660/1251]	eta 0:21:54 lr 0.000083	time 2.2232 (2.2237)	loss 3.1178 (3.1032)	grad_norm 2.3740 (2.6486)	
[2022-01-25 14:55:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][670/1251]	eta 0:21:32 lr 0.000083	time 1.8718 (2.2238)	loss 3.4007 (3.1036)	grad_norm 2.2740 (2.6489)	
[2022-01-25 14:55:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][680/1251]	eta 0:21:09 lr 0.000083	time 2.3075 (2.2239)	loss 3.1646 (3.1005)	grad_norm 2.5130 (2.6484)	
[2022-01-25 14:56:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][690/1251]	eta 0:20:47 lr 0.000083	time 2.1163 (2.2232)	loss 3.1276 (3.1008)	grad_norm 2.4183 (2.6501)	
[2022-01-25 14:56:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][700/1251]	eta 0:20:24 lr 0.000083	time 2.4890 (2.2227)	loss 1.9933 (3.0992)	grad_norm 2.3814 (2.6484)	
[2022-01-25 14:56:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][710/1251]	eta 0:20:01 lr 0.000083	time 1.8582 (2.2216)	loss 3.0803 (3.1002)	grad_norm 3.2240 (2.6512)	
[2022-01-25 14:57:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][720/1251]	eta 0:19:38 lr 0.000083	time 1.8798 (2.2203)	loss 3.4345 (3.1009)	grad_norm 2.6226 (2.6497)	
[2022-01-25 14:57:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][730/1251]	eta 0:19:17 lr 0.000083	time 2.5862 (2.2223)	loss 3.5567 (3.1032)	grad_norm 2.9642 (2.6496)	
[2022-01-25 14:58:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][740/1251]	eta 0:18:54 lr 0.000083	time 1.6023 (2.2198)	loss 3.5512 (3.1056)	grad_norm 2.3764 (2.6489)	
[2022-01-25 14:58:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][750/1251]	eta 0:18:31 lr 0.000083	time 1.8930 (2.2179)	loss 3.0537 (3.1055)	grad_norm 2.5742 (2.6484)	
[2022-01-25 14:58:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][760/1251]	eta 0:18:08 lr 0.000083	time 2.2331 (2.2173)	loss 3.4606 (3.1065)	grad_norm 2.3425 (2.6480)	
[2022-01-25 14:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][770/1251]	eta 0:17:45 lr 0.000083	time 1.9412 (2.2157)	loss 3.7028 (3.1095)	grad_norm 2.7376 (2.6483)	
[2022-01-25 14:59:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][780/1251]	eta 0:17:22 lr 0.000083	time 2.1591 (2.2141)	loss 3.2689 (3.1128)	grad_norm 2.5433 (2.6470)	
[2022-01-25 14:59:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][790/1251]	eta 0:17:00 lr 0.000083	time 2.0809 (2.2127)	loss 3.2332 (3.1136)	grad_norm 2.3443 (2.6456)	
[2022-01-25 15:00:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][800/1251]	eta 0:16:37 lr 0.000083	time 2.3523 (2.2126)	loss 2.3804 (3.1112)	grad_norm 2.7514 (2.6455)	
[2022-01-25 15:00:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][810/1251]	eta 0:16:15 lr 0.000083	time 2.1373 (2.2128)	loss 3.6042 (3.1124)	grad_norm 2.5547 (2.6487)	
[2022-01-25 15:00:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][820/1251]	eta 0:15:53 lr 0.000083	time 1.6403 (2.2126)	loss 3.3510 (3.1127)	grad_norm 2.4466 (2.6467)	
[2022-01-25 15:01:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][830/1251]	eta 0:15:31 lr 0.000083	time 2.5475 (2.2132)	loss 3.2173 (3.1130)	grad_norm 2.6919 (2.6451)	
[2022-01-25 15:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][840/1251]	eta 0:15:10 lr 0.000082	time 2.3680 (2.2147)	loss 2.6584 (3.1140)	grad_norm 2.5321 (2.6439)	
[2022-01-25 15:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][850/1251]	eta 0:14:48 lr 0.000082	time 3.5187 (2.2160)	loss 3.3778 (3.1141)	grad_norm 3.0576 (2.6449)	
[2022-01-25 15:02:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][860/1251]	eta 0:14:26 lr 0.000082	time 1.8991 (2.2155)	loss 3.2525 (3.1164)	grad_norm 2.6356 (2.6445)	
[2022-01-25 15:02:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][870/1251]	eta 0:14:03 lr 0.000082	time 2.1983 (2.2142)	loss 2.8095 (3.1159)	grad_norm 2.6803 (2.6443)	
[2022-01-25 15:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][880/1251]	eta 0:13:40 lr 0.000082	time 2.3025 (2.2129)	loss 3.6053 (3.1174)	grad_norm 3.0473 (2.6458)	
[2022-01-25 15:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][890/1251]	eta 0:13:18 lr 0.000082	time 1.8752 (2.2115)	loss 3.0006 (3.1179)	grad_norm 2.3975 (2.6462)	
[2022-01-25 15:03:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][900/1251]	eta 0:12:55 lr 0.000082	time 2.3217 (2.2108)	loss 2.2015 (3.1176)	grad_norm 2.8603 (2.6477)	
[2022-01-25 15:04:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][910/1251]	eta 0:12:33 lr 0.000082	time 2.3525 (2.2103)	loss 3.5908 (3.1164)	grad_norm 2.4383 (2.6479)	
[2022-01-25 15:04:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][920/1251]	eta 0:12:11 lr 0.000082	time 1.9187 (2.2099)	loss 2.8506 (3.1189)	grad_norm 2.9038 (2.6466)	
[2022-01-25 15:04:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][930/1251]	eta 0:11:49 lr 0.000082	time 2.7316 (2.2101)	loss 2.8554 (3.1195)	grad_norm 2.6267 (2.6445)	
[2022-01-25 15:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][940/1251]	eta 0:11:27 lr 0.000082	time 2.2351 (2.2100)	loss 2.9516 (3.1191)	grad_norm 2.4133 (2.6447)	
[2022-01-25 15:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][950/1251]	eta 0:11:05 lr 0.000082	time 2.1349 (2.2098)	loss 2.9705 (3.1179)	grad_norm 2.4365 (2.6455)	
[2022-01-25 15:05:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][960/1251]	eta 0:10:42 lr 0.000082	time 2.6976 (2.2092)	loss 3.1832 (3.1204)	grad_norm 2.5716 (2.6454)	
[2022-01-25 15:06:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][970/1251]	eta 0:10:20 lr 0.000082	time 2.1650 (2.2080)	loss 2.5225 (3.1181)	grad_norm 2.7738 (2.6470)	
[2022-01-25 15:06:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][980/1251]	eta 0:09:58 lr 0.000082	time 2.4396 (2.2082)	loss 3.3424 (3.1203)	grad_norm 2.1515 (2.6485)	
[2022-01-25 15:07:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][990/1251]	eta 0:09:36 lr 0.000082	time 1.8079 (2.2083)	loss 2.8190 (3.1176)	grad_norm 2.5844 (2.6482)	
[2022-01-25 15:07:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1000/1251]	eta 0:09:14 lr 0.000082	time 3.0370 (2.2094)	loss 3.7862 (3.1153)	grad_norm 2.5786 (2.6467)	
[2022-01-25 15:07:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1010/1251]	eta 0:08:52 lr 0.000082	time 2.1608 (2.2083)	loss 2.0122 (3.1151)	grad_norm 2.3232 (2.6467)	
[2022-01-25 15:08:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1020/1251]	eta 0:08:29 lr 0.000082	time 2.2691 (2.2074)	loss 3.0227 (3.1146)	grad_norm 2.4177 (2.6440)	
[2022-01-25 15:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1030/1251]	eta 0:08:07 lr 0.000082	time 1.9187 (2.2061)	loss 3.5667 (3.1139)	grad_norm 2.2284 (2.6436)	
[2022-01-25 15:08:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1040/1251]	eta 0:07:45 lr 0.000082	time 2.9100 (2.2070)	loss 3.4831 (3.1139)	grad_norm 2.2974 (2.6435)	
[2022-01-25 15:09:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1050/1251]	eta 0:07:23 lr 0.000082	time 2.6906 (2.2080)	loss 3.4574 (3.1160)	grad_norm 2.4499 (2.6433)	
[2022-01-25 15:09:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1060/1251]	eta 0:07:01 lr 0.000082	time 2.1942 (2.2076)	loss 3.3283 (3.1157)	grad_norm 2.5564 (2.6478)	
[2022-01-25 15:09:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1070/1251]	eta 0:06:39 lr 0.000082	time 2.2149 (2.2062)	loss 2.0965 (3.1153)	grad_norm 2.5276 (2.6478)	
[2022-01-25 15:10:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1080/1251]	eta 0:06:17 lr 0.000082	time 2.2688 (2.2047)	loss 2.9494 (3.1159)	grad_norm 2.7658 (2.6476)	
[2022-01-25 15:10:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1090/1251]	eta 0:05:54 lr 0.000082	time 2.2102 (2.2035)	loss 3.1006 (3.1139)	grad_norm 2.8769 (2.6471)	
[2022-01-25 15:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1100/1251]	eta 0:05:32 lr 0.000082	time 2.0703 (2.2030)	loss 3.3636 (3.1165)	grad_norm 2.9269 (2.6464)	
[2022-01-25 15:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1110/1251]	eta 0:05:10 lr 0.000082	time 2.5826 (2.2024)	loss 3.1950 (3.1185)	grad_norm 2.4355 (2.6451)	
[2022-01-25 15:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1120/1251]	eta 0:04:48 lr 0.000082	time 2.6420 (2.2028)	loss 3.3044 (3.1178)	grad_norm 2.7306 (2.6445)	
[2022-01-25 15:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1130/1251]	eta 0:04:26 lr 0.000082	time 2.0628 (2.2025)	loss 2.2158 (3.1169)	grad_norm 2.4402 (2.6442)	
[2022-01-25 15:12:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1140/1251]	eta 0:04:04 lr 0.000082	time 1.8562 (2.2013)	loss 2.1819 (3.1157)	grad_norm 2.8637 (2.6449)	
[2022-01-25 15:12:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1150/1251]	eta 0:03:42 lr 0.000082	time 2.1933 (2.2023)	loss 3.4265 (3.1135)	grad_norm 2.4077 (2.6444)	
[2022-01-25 15:13:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1160/1251]	eta 0:03:20 lr 0.000082	time 3.3620 (2.2028)	loss 2.8697 (3.1120)	grad_norm 2.6509 (2.6437)	
[2022-01-25 15:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1170/1251]	eta 0:02:58 lr 0.000082	time 2.1410 (2.2035)	loss 3.7001 (3.1118)	grad_norm 2.7741 (2.6472)	
[2022-01-25 15:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1180/1251]	eta 0:02:36 lr 0.000082	time 1.7577 (2.2022)	loss 2.6068 (3.1098)	grad_norm 2.5620 (2.6480)	
[2022-01-25 15:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1190/1251]	eta 0:02:14 lr 0.000082	time 1.8668 (2.2014)	loss 2.6197 (3.1093)	grad_norm 4.1644 (2.6505)	
[2022-01-25 15:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1200/1251]	eta 0:01:52 lr 0.000082	time 2.7751 (2.2018)	loss 3.5716 (3.1109)	grad_norm 2.3840 (2.6512)	
[2022-01-25 15:15:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1210/1251]	eta 0:01:30 lr 0.000082	time 2.2975 (2.2011)	loss 2.3319 (3.1104)	grad_norm 2.4110 (2.6495)	
[2022-01-25 15:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1220/1251]	eta 0:01:08 lr 0.000082	time 2.2848 (2.2006)	loss 3.6228 (3.1111)	grad_norm 2.6155 (2.6489)	
[2022-01-25 15:15:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1230/1251]	eta 0:00:46 lr 0.000082	time 2.0289 (2.2004)	loss 2.9916 (3.1109)	grad_norm 2.4765 (2.6483)	
[2022-01-25 15:16:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1240/1251]	eta 0:00:24 lr 0.000082	time 1.4401 (2.2010)	loss 3.2095 (3.1098)	grad_norm 2.5995 (2.6476)	
[2022-01-25 15:16:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [247/300][1250/1251]	eta 0:00:02 lr 0.000082	time 1.2001 (2.1962)	loss 2.1662 (3.1105)	grad_norm 2.8000 (2.6460)	
[2022-01-25 15:16:24 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 247 training takes 0:45:47
[2022-01-25 15:16:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.276 (18.276)	Loss 0.8217 (0.8217)	Acc@1 80.762 (80.762)	Acc@5 95.703 (95.703)	
[2022-01-25 15:17:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.265 (3.341)	Loss 0.8787 (0.8225)	Acc@1 78.613 (80.176)	Acc@5 94.727 (95.446)	
[2022-01-25 15:17:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.595 (2.498)	Loss 0.8910 (0.8319)	Acc@1 79.883 (80.222)	Acc@5 95.215 (95.387)	
[2022-01-25 15:17:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.593 (2.232)	Loss 0.8687 (0.8302)	Acc@1 79.297 (80.289)	Acc@5 95.020 (95.372)	
[2022-01-25 15:17:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.833 (2.156)	Loss 0.7707 (0.8305)	Acc@1 82.324 (80.312)	Acc@5 95.898 (95.308)	
[2022-01-25 15:17:59 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.242 Acc@5 95.270
[2022-01-25 15:17:59 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.2%
[2022-01-25 15:17:59 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.24%
[2022-01-25 15:18:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][0/1251]	eta 7:36:39 lr 0.000082	time 21.9025 (21.9025)	loss 2.1089 (2.1089)	grad_norm 2.8887 (2.8887)	
[2022-01-25 15:18:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][10/1251]	eta 1:24:13 lr 0.000082	time 2.2215 (4.0719)	loss 3.5822 (3.0206)	grad_norm 3.3432 (2.7753)	
[2022-01-25 15:19:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][20/1251]	eta 1:06:14 lr 0.000082	time 1.8013 (3.2287)	loss 3.2627 (3.1255)	grad_norm 2.4227 (2.7216)	
[2022-01-25 15:19:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][30/1251]	eta 0:58:28 lr 0.000082	time 1.8949 (2.8733)	loss 3.0892 (3.0755)	grad_norm 2.5514 (2.6367)	
[2022-01-25 15:19:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][40/1251]	eta 0:56:11 lr 0.000082	time 4.4828 (2.7839)	loss 2.4223 (3.0776)	grad_norm 2.4029 (2.6085)	
[2022-01-25 15:20:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][50/1251]	eta 0:53:35 lr 0.000081	time 2.1886 (2.6771)	loss 2.1695 (3.0226)	grad_norm 2.6365 (2.6026)	
[2022-01-25 15:20:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][60/1251]	eta 0:51:42 lr 0.000081	time 1.8499 (2.6048)	loss 2.4370 (3.0082)	grad_norm 2.3888 (2.5777)	
[2022-01-25 15:21:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][70/1251]	eta 0:50:15 lr 0.000081	time 2.1290 (2.5534)	loss 3.9858 (3.0289)	grad_norm 2.5136 (2.5884)	
[2022-01-25 15:21:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][80/1251]	eta 0:49:09 lr 0.000081	time 3.5576 (2.5191)	loss 3.1836 (3.0522)	grad_norm 2.9652 (2.6722)	
[2022-01-25 15:21:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][90/1251]	eta 0:47:50 lr 0.000081	time 2.1186 (2.4723)	loss 3.3281 (3.0848)	grad_norm 2.7547 (2.6575)	
[2022-01-25 15:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][100/1251]	eta 0:46:46 lr 0.000081	time 1.6506 (2.4380)	loss 2.6955 (3.0722)	grad_norm 2.7044 (2.6690)	
[2022-01-25 15:22:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][110/1251]	eta 0:45:43 lr 0.000081	time 1.6812 (2.4042)	loss 2.8731 (3.0724)	grad_norm 2.4503 (2.6937)	
[2022-01-25 15:22:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][120/1251]	eta 0:44:50 lr 0.000081	time 3.1177 (2.3788)	loss 3.0237 (3.0598)	grad_norm 3.0487 (2.6873)	
[2022-01-25 15:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][130/1251]	eta 0:44:17 lr 0.000081	time 2.4232 (2.3710)	loss 3.5636 (3.0359)	grad_norm 2.8475 (2.6796)	
[2022-01-25 15:23:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][140/1251]	eta 0:43:39 lr 0.000081	time 2.2087 (2.3580)	loss 3.1416 (3.0514)	grad_norm 3.0476 (2.6685)	
[2022-01-25 15:23:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][150/1251]	eta 0:43:01 lr 0.000081	time 2.0510 (2.3445)	loss 1.9290 (3.0602)	grad_norm 2.6195 (2.6662)	
[2022-01-25 15:24:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][160/1251]	eta 0:42:25 lr 0.000081	time 2.2572 (2.3332)	loss 3.6093 (3.0645)	grad_norm 2.2934 (2.6602)	
[2022-01-25 15:24:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][170/1251]	eta 0:41:52 lr 0.000081	time 2.6075 (2.3239)	loss 3.4089 (3.0778)	grad_norm 2.4027 (2.6583)	
[2022-01-25 15:24:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][180/1251]	eta 0:41:15 lr 0.000081	time 1.6057 (2.3111)	loss 2.8580 (3.0770)	grad_norm 2.4853 (2.6609)	
[2022-01-25 15:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][190/1251]	eta 0:40:43 lr 0.000081	time 1.6645 (2.3026)	loss 3.8069 (3.0885)	grad_norm 2.4078 (2.6569)	
[2022-01-25 15:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][200/1251]	eta 0:40:16 lr 0.000081	time 3.5684 (2.2997)	loss 3.5325 (3.0992)	grad_norm 2.9283 (2.6596)	
[2022-01-25 15:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][210/1251]	eta 0:39:48 lr 0.000081	time 2.5498 (2.2944)	loss 1.8299 (3.1079)	grad_norm 2.3415 (2.6549)	
[2022-01-25 15:26:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][220/1251]	eta 0:39:18 lr 0.000081	time 1.7970 (2.2879)	loss 3.1988 (3.1104)	grad_norm 2.2094 (2.6480)	
[2022-01-25 15:26:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][230/1251]	eta 0:38:57 lr 0.000081	time 2.4445 (2.2898)	loss 2.9992 (3.1015)	grad_norm 2.4329 (2.6479)	
[2022-01-25 15:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][240/1251]	eta 0:38:31 lr 0.000081	time 2.2713 (2.2861)	loss 2.2508 (3.1041)	grad_norm 2.2906 (2.6406)	
[2022-01-25 15:27:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][250/1251]	eta 0:38:04 lr 0.000081	time 3.2406 (2.2821)	loss 2.1041 (3.1035)	grad_norm 2.4195 (2.6367)	
[2022-01-25 15:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][260/1251]	eta 0:37:37 lr 0.000081	time 1.6312 (2.2777)	loss 3.6533 (3.1046)	grad_norm 2.3849 (2.6373)	
[2022-01-25 15:28:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][270/1251]	eta 0:37:06 lr 0.000081	time 2.1153 (2.2698)	loss 2.8402 (3.0998)	grad_norm 2.7854 (2.6349)	
[2022-01-25 15:28:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][280/1251]	eta 0:36:35 lr 0.000081	time 2.2470 (2.2608)	loss 3.1596 (3.1045)	grad_norm 2.7588 (2.6400)	
[2022-01-25 15:28:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][290/1251]	eta 0:36:12 lr 0.000081	time 3.2728 (2.2611)	loss 3.1067 (3.1006)	grad_norm 2.4994 (2.6374)	
[2022-01-25 15:29:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][300/1251]	eta 0:35:47 lr 0.000081	time 2.3193 (2.2583)	loss 2.7474 (3.0959)	grad_norm 2.4082 (2.6338)	
[2022-01-25 15:29:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][310/1251]	eta 0:35:20 lr 0.000081	time 1.8319 (2.2537)	loss 2.9411 (3.0937)	grad_norm 2.8921 (2.6367)	
[2022-01-25 15:30:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][320/1251]	eta 0:34:53 lr 0.000081	time 2.8138 (2.2486)	loss 3.3784 (3.1002)	grad_norm 2.7919 (2.6367)	
[2022-01-25 15:30:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][330/1251]	eta 0:34:30 lr 0.000081	time 2.8280 (2.2480)	loss 2.7355 (3.0973)	grad_norm 2.7899 (2.6378)	
[2022-01-25 15:30:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][340/1251]	eta 0:34:08 lr 0.000081	time 1.8934 (2.2490)	loss 2.9811 (3.1000)	grad_norm 2.4581 (2.6330)	
[2022-01-25 15:31:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][350/1251]	eta 0:33:47 lr 0.000081	time 2.5325 (2.2504)	loss 2.8825 (3.0997)	grad_norm 2.5335 (2.6332)	
[2022-01-25 15:31:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][360/1251]	eta 0:33:22 lr 0.000081	time 2.1574 (2.2476)	loss 3.3302 (3.0928)	grad_norm 2.2867 (2.6313)	
[2022-01-25 15:31:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][370/1251]	eta 0:32:59 lr 0.000081	time 2.4036 (2.2471)	loss 3.2173 (3.0912)	grad_norm 2.8077 (2.6319)	
[2022-01-25 15:32:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][380/1251]	eta 0:32:35 lr 0.000081	time 1.9622 (2.2454)	loss 3.3775 (3.0957)	grad_norm 2.4216 (2.6356)	
[2022-01-25 15:32:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][390/1251]	eta 0:32:11 lr 0.000081	time 2.4657 (2.2428)	loss 3.7724 (3.1019)	grad_norm 3.5734 (2.6389)	
[2022-01-25 15:32:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][400/1251]	eta 0:31:45 lr 0.000081	time 2.3432 (2.2394)	loss 3.1847 (3.0984)	grad_norm 2.6671 (2.6413)	
[2022-01-25 15:33:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][410/1251]	eta 0:31:19 lr 0.000081	time 2.2609 (2.2348)	loss 3.0694 (3.0987)	grad_norm 2.6416 (2.6412)	
[2022-01-25 15:33:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][420/1251]	eta 0:30:54 lr 0.000081	time 2.1787 (2.2315)	loss 3.4270 (3.0999)	grad_norm 2.3054 (2.6401)	
[2022-01-25 15:34:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][430/1251]	eta 0:30:31 lr 0.000081	time 2.2644 (2.2312)	loss 3.3025 (3.1026)	grad_norm 2.4110 (2.6377)	
[2022-01-25 15:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][440/1251]	eta 0:30:06 lr 0.000081	time 2.2277 (2.2275)	loss 3.2731 (3.1014)	grad_norm 2.5745 (2.6347)	
[2022-01-25 15:34:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][450/1251]	eta 0:29:43 lr 0.000081	time 1.9072 (2.2262)	loss 2.5972 (3.0995)	grad_norm 2.5629 (2.6379)	
[2022-01-25 15:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][460/1251]	eta 0:29:23 lr 0.000081	time 2.3443 (2.2297)	loss 3.1573 (3.0946)	grad_norm 2.5942 (2.6360)	
[2022-01-25 15:35:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][470/1251]	eta 0:29:01 lr 0.000081	time 2.5547 (2.2300)	loss 3.7299 (3.0964)	grad_norm 2.7941 (2.6343)	
[2022-01-25 15:35:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][480/1251]	eta 0:28:38 lr 0.000081	time 3.1639 (2.2285)	loss 3.7460 (3.0948)	grad_norm 2.5860 (2.6352)	
[2022-01-25 15:36:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][490/1251]	eta 0:28:16 lr 0.000081	time 2.2423 (2.2288)	loss 2.1300 (3.0972)	grad_norm 2.3975 (2.6346)	
[2022-01-25 15:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][500/1251]	eta 0:27:55 lr 0.000081	time 1.9826 (2.2308)	loss 3.6746 (3.1038)	grad_norm 2.8889 (2.6426)	
[2022-01-25 15:36:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][510/1251]	eta 0:27:31 lr 0.000081	time 2.2380 (2.2291)	loss 2.2930 (3.1026)	grad_norm 2.2880 (2.6446)	
[2022-01-25 15:37:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][520/1251]	eta 0:27:11 lr 0.000080	time 3.6824 (2.2320)	loss 3.2333 (3.1035)	grad_norm 2.6931 (2.6469)	
[2022-01-25 15:37:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][530/1251]	eta 0:26:48 lr 0.000080	time 1.8417 (2.2313)	loss 3.9385 (3.1060)	grad_norm 2.2168 (2.6713)	
[2022-01-25 15:38:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][540/1251]	eta 0:26:23 lr 0.000080	time 1.6549 (2.2271)	loss 3.2122 (3.1061)	grad_norm 2.4923 (2.6728)	
[2022-01-25 15:38:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][550/1251]	eta 0:25:58 lr 0.000080	time 1.9210 (2.2230)	loss 2.2301 (3.1063)	grad_norm 2.4838 (2.6734)	
[2022-01-25 15:38:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][560/1251]	eta 0:25:39 lr 0.000080	time 5.7347 (2.2285)	loss 2.2356 (3.1053)	grad_norm 2.7847 (2.6752)	
[2022-01-25 15:39:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][570/1251]	eta 0:25:16 lr 0.000080	time 1.9119 (2.2268)	loss 3.4111 (3.1076)	grad_norm 4.1076 (2.6774)	
[2022-01-25 15:39:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][580/1251]	eta 0:24:53 lr 0.000080	time 1.7553 (2.2259)	loss 3.3263 (3.1086)	grad_norm 2.5630 (2.6789)	
[2022-01-25 15:39:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][590/1251]	eta 0:24:29 lr 0.000080	time 2.0934 (2.2235)	loss 3.5183 (3.1103)	grad_norm 2.6814 (2.6816)	
[2022-01-25 15:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][600/1251]	eta 0:24:06 lr 0.000080	time 2.9860 (2.2214)	loss 3.5569 (3.1093)	grad_norm 2.8720 (2.6841)	
[2022-01-25 15:40:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][610/1251]	eta 0:23:42 lr 0.000080	time 2.3172 (2.2191)	loss 3.4702 (3.1079)	grad_norm 3.3717 (2.6850)	
[2022-01-25 15:40:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][620/1251]	eta 0:23:19 lr 0.000080	time 1.8733 (2.2180)	loss 3.7067 (3.1105)	grad_norm 2.8344 (2.6814)	
[2022-01-25 15:41:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][630/1251]	eta 0:22:57 lr 0.000080	time 1.8992 (2.2183)	loss 2.8133 (3.1070)	grad_norm 2.9866 (2.6826)	
[2022-01-25 15:41:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][640/1251]	eta 0:22:36 lr 0.000080	time 3.2633 (2.2204)	loss 3.5528 (3.1092)	grad_norm 2.3727 (2.6810)	
[2022-01-25 15:42:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][650/1251]	eta 0:22:14 lr 0.000080	time 2.2582 (2.2212)	loss 3.1640 (3.1102)	grad_norm 2.9653 (2.6813)	
[2022-01-25 15:42:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][660/1251]	eta 0:21:50 lr 0.000080	time 1.9763 (2.2181)	loss 2.0571 (3.1075)	grad_norm 2.2132 (2.6807)	
[2022-01-25 15:42:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][670/1251]	eta 0:21:27 lr 0.000080	time 2.1863 (2.2168)	loss 3.1463 (3.1034)	grad_norm 2.5436 (2.6787)	
[2022-01-25 15:43:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][680/1251]	eta 0:21:06 lr 0.000080	time 3.0027 (2.2172)	loss 3.4627 (3.1025)	grad_norm 2.9874 (2.6784)	
[2022-01-25 15:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][690/1251]	eta 0:20:43 lr 0.000080	time 2.3203 (2.2171)	loss 3.0772 (3.1025)	grad_norm 2.5091 (2.6756)	
[2022-01-25 15:43:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][700/1251]	eta 0:20:20 lr 0.000080	time 1.8609 (2.2159)	loss 3.4775 (3.1033)	grad_norm 2.7050 (2.6748)	
[2022-01-25 15:44:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][710/1251]	eta 0:19:59 lr 0.000080	time 1.8392 (2.2169)	loss 3.5235 (3.1035)	grad_norm 2.8675 (2.6743)	
[2022-01-25 15:44:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][720/1251]	eta 0:19:37 lr 0.000080	time 3.0467 (2.2179)	loss 2.0991 (3.1001)	grad_norm 2.6587 (2.6727)	
[2022-01-25 15:45:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][730/1251]	eta 0:19:16 lr 0.000080	time 1.8442 (2.2189)	loss 3.3790 (3.0961)	grad_norm 3.0486 (2.6712)	
[2022-01-25 15:45:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][740/1251]	eta 0:18:52 lr 0.000080	time 1.6625 (2.2164)	loss 3.3814 (3.0928)	grad_norm 2.3780 (2.6712)	
[2022-01-25 15:45:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][750/1251]	eta 0:18:28 lr 0.000080	time 1.8786 (2.2129)	loss 3.6765 (3.0929)	grad_norm 2.5539 (2.6727)	
[2022-01-25 15:46:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][760/1251]	eta 0:18:05 lr 0.000080	time 2.1988 (2.2102)	loss 3.4519 (3.0957)	grad_norm 2.2591 (2.6707)	
[2022-01-25 15:46:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][770/1251]	eta 0:17:42 lr 0.000080	time 2.4658 (2.2097)	loss 3.8493 (3.0965)	grad_norm 2.4389 (2.6698)	
[2022-01-25 15:46:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][780/1251]	eta 0:17:20 lr 0.000080	time 2.1541 (2.2096)	loss 3.1698 (3.0957)	grad_norm 2.9814 (2.6705)	
[2022-01-25 15:47:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][790/1251]	eta 0:16:59 lr 0.000080	time 2.7830 (2.2114)	loss 3.2820 (3.0964)	grad_norm 2.4160 (2.6696)	
[2022-01-25 15:47:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][800/1251]	eta 0:16:37 lr 0.000080	time 2.5388 (2.2126)	loss 2.9436 (3.0970)	grad_norm 2.3736 (2.6706)	
[2022-01-25 15:47:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][810/1251]	eta 0:16:14 lr 0.000080	time 1.8112 (2.2102)	loss 3.6339 (3.0974)	grad_norm 2.6006 (2.6703)	
[2022-01-25 15:48:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][820/1251]	eta 0:15:51 lr 0.000080	time 2.1956 (2.2088)	loss 3.2804 (3.0967)	grad_norm 2.4647 (2.6691)	
[2022-01-25 15:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][830/1251]	eta 0:15:30 lr 0.000080	time 1.8948 (2.2096)	loss 2.1919 (3.0971)	grad_norm 2.4829 (2.6690)	
[2022-01-25 15:48:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][840/1251]	eta 0:15:08 lr 0.000080	time 3.1407 (2.2096)	loss 3.4142 (3.0968)	grad_norm 2.1976 (2.6672)	
[2022-01-25 15:49:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][850/1251]	eta 0:14:45 lr 0.000080	time 1.6039 (2.2083)	loss 3.3107 (3.1008)	grad_norm 2.7711 (2.6683)	
[2022-01-25 15:49:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][860/1251]	eta 0:14:23 lr 0.000080	time 2.1518 (2.2091)	loss 3.7249 (3.0991)	grad_norm 2.8427 (2.6668)	
[2022-01-25 15:50:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][870/1251]	eta 0:14:01 lr 0.000080	time 1.8130 (2.2095)	loss 2.8107 (3.0998)	grad_norm 2.4190 (2.6656)	
[2022-01-25 15:50:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][880/1251]	eta 0:13:39 lr 0.000080	time 2.8732 (2.2100)	loss 3.5458 (3.0998)	grad_norm 2.5981 (2.6644)	
[2022-01-25 15:50:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][890/1251]	eta 0:13:17 lr 0.000080	time 1.8723 (2.2080)	loss 2.5157 (3.0969)	grad_norm 2.5408 (2.6660)	
[2022-01-25 15:51:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][900/1251]	eta 0:12:54 lr 0.000080	time 1.8891 (2.2066)	loss 3.6846 (3.0987)	grad_norm 2.4464 (2.6665)	
[2022-01-25 15:51:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][910/1251]	eta 0:12:33 lr 0.000080	time 1.8701 (2.2087)	loss 2.3466 (3.0991)	grad_norm 2.5686 (2.6647)	
[2022-01-25 15:51:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][920/1251]	eta 0:12:11 lr 0.000080	time 2.9558 (2.2112)	loss 2.0011 (3.0997)	grad_norm 2.7723 (2.6643)	
[2022-01-25 15:52:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][930/1251]	eta 0:11:49 lr 0.000080	time 1.8279 (2.2093)	loss 2.4748 (3.0988)	grad_norm 2.9227 (2.6656)	
[2022-01-25 15:52:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][940/1251]	eta 0:11:26 lr 0.000080	time 1.9654 (2.2074)	loss 3.0041 (3.0974)	grad_norm 2.4402 (2.6646)	
[2022-01-25 15:52:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][950/1251]	eta 0:11:03 lr 0.000080	time 2.2318 (2.2055)	loss 2.4319 (3.0972)	grad_norm 2.2693 (2.6637)	
[2022-01-25 15:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][960/1251]	eta 0:10:41 lr 0.000080	time 2.4501 (2.2041)	loss 3.7176 (3.0990)	grad_norm 2.4643 (2.6634)	
[2022-01-25 15:53:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][970/1251]	eta 0:10:19 lr 0.000080	time 2.4830 (2.2038)	loss 2.4510 (3.0965)	grad_norm 3.2830 (2.6625)	
[2022-01-25 15:54:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][980/1251]	eta 0:09:57 lr 0.000080	time 2.2234 (2.2033)	loss 3.6408 (3.0979)	grad_norm 2.5181 (2.6621)	
[2022-01-25 15:54:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][990/1251]	eta 0:09:35 lr 0.000079	time 1.9541 (2.2057)	loss 3.6489 (3.1008)	grad_norm 5.2173 (2.6642)	
[2022-01-25 15:54:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1000/1251]	eta 0:09:13 lr 0.000079	time 2.9557 (2.2068)	loss 3.7808 (3.1044)	grad_norm 2.6605 (2.6634)	
[2022-01-25 15:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1010/1251]	eta 0:08:52 lr 0.000079	time 2.2576 (2.2083)	loss 2.5653 (3.1056)	grad_norm 2.4829 (2.6635)	
[2022-01-25 15:55:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1020/1251]	eta 0:08:30 lr 0.000079	time 1.5146 (2.2088)	loss 3.4224 (3.1051)	grad_norm 2.5158 (2.6615)	
[2022-01-25 15:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1030/1251]	eta 0:08:08 lr 0.000079	time 1.7312 (2.2086)	loss 2.4125 (3.1046)	grad_norm 2.6904 (2.6606)	
[2022-01-25 15:56:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1040/1251]	eta 0:07:45 lr 0.000079	time 3.3696 (2.2084)	loss 2.3970 (3.1052)	grad_norm 3.8166 (2.6612)	
[2022-01-25 15:56:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1050/1251]	eta 0:07:23 lr 0.000079	time 1.9564 (2.2065)	loss 3.3474 (3.1068)	grad_norm 2.5734 (2.6614)	
[2022-01-25 15:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1060/1251]	eta 0:07:01 lr 0.000079	time 2.2265 (2.2066)	loss 2.8438 (3.1086)	grad_norm 3.2981 (2.6621)	
[2022-01-25 15:57:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1070/1251]	eta 0:06:39 lr 0.000079	time 2.1658 (2.2058)	loss 3.6211 (3.1096)	grad_norm 2.8250 (2.6619)	
[2022-01-25 15:57:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1080/1251]	eta 0:06:17 lr 0.000079	time 3.2590 (2.2058)	loss 3.4195 (3.1123)	grad_norm 2.5535 (2.6613)	
[2022-01-25 15:58:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1090/1251]	eta 0:05:55 lr 0.000079	time 2.4567 (2.2055)	loss 3.5193 (3.1146)	grad_norm 2.3701 (2.6606)	
[2022-01-25 15:58:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1100/1251]	eta 0:05:32 lr 0.000079	time 2.2449 (2.2050)	loss 3.6501 (3.1179)	grad_norm 2.7567 (2.6607)	
[2022-01-25 15:58:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1110/1251]	eta 0:05:10 lr 0.000079	time 1.7465 (2.2041)	loss 2.7779 (3.1173)	grad_norm 2.7886 (2.6600)	
[2022-01-25 15:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1120/1251]	eta 0:04:49 lr 0.000079	time 3.9283 (2.2079)	loss 3.5165 (3.1188)	grad_norm 2.7086 (2.6612)	
[2022-01-25 15:59:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1130/1251]	eta 0:04:27 lr 0.000079	time 1.9119 (2.2072)	loss 2.6569 (3.1188)	grad_norm 2.8333 (2.6601)	
[2022-01-25 15:59:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1140/1251]	eta 0:04:04 lr 0.000079	time 2.1559 (2.2065)	loss 2.6567 (3.1180)	grad_norm 2.5268 (2.6593)	
[2022-01-25 16:00:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1150/1251]	eta 0:03:42 lr 0.000079	time 2.2440 (2.2052)	loss 2.5910 (3.1183)	grad_norm 2.4091 (2.6604)	
[2022-01-25 16:00:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1160/1251]	eta 0:03:20 lr 0.000079	time 3.6666 (2.2054)	loss 3.2079 (3.1165)	grad_norm 2.4215 (2.6598)	
[2022-01-25 16:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1170/1251]	eta 0:02:58 lr 0.000079	time 1.8697 (2.2054)	loss 2.7127 (3.1150)	grad_norm 2.0556 (2.6586)	
[2022-01-25 16:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1180/1251]	eta 0:02:36 lr 0.000079	time 2.2104 (2.2052)	loss 3.7509 (3.1147)	grad_norm 2.7165 (2.6595)	
[2022-01-25 16:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1190/1251]	eta 0:02:14 lr 0.000079	time 2.2803 (2.2054)	loss 2.0551 (3.1116)	grad_norm 2.5474 (2.6596)	
[2022-01-25 16:02:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1200/1251]	eta 0:01:52 lr 0.000079	time 3.6268 (2.2066)	loss 3.4765 (3.1107)	grad_norm 2.3167 (2.6593)	
[2022-01-25 16:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1210/1251]	eta 0:01:30 lr 0.000079	time 1.8382 (2.2049)	loss 3.2134 (3.1113)	grad_norm 2.4597 (2.6595)	
[2022-01-25 16:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1220/1251]	eta 0:01:08 lr 0.000079	time 2.1210 (2.2032)	loss 3.5255 (3.1116)	grad_norm 2.3001 (2.6589)	
[2022-01-25 16:03:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1230/1251]	eta 0:00:46 lr 0.000079	time 2.2616 (2.2011)	loss 2.7681 (3.1130)	grad_norm 2.4436 (2.6585)	
[2022-01-25 16:03:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1240/1251]	eta 0:00:24 lr 0.000079	time 2.2397 (2.2000)	loss 2.5310 (3.1130)	grad_norm 2.5951 (2.6577)	
[2022-01-25 16:03:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [248/300][1250/1251]	eta 0:00:02 lr 0.000079	time 1.1557 (2.1947)	loss 3.2875 (3.1117)	grad_norm 2.1227 (2.6571)	
[2022-01-25 16:03:45 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 248 training takes 0:45:45
[2022-01-25 16:04:03 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.211 (18.211)	Loss 0.7903 (0.7903)	Acc@1 82.129 (82.129)	Acc@5 95.898 (95.898)	
[2022-01-25 16:04:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.544 (3.405)	Loss 0.8219 (0.8344)	Acc@1 81.641 (80.575)	Acc@5 95.605 (95.508)	
[2022-01-25 16:04:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.305 (2.513)	Loss 0.8262 (0.8401)	Acc@1 80.664 (80.185)	Acc@5 95.020 (95.289)	
[2022-01-25 16:04:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.309 (2.263)	Loss 0.8578 (0.8385)	Acc@1 79.199 (80.343)	Acc@5 94.629 (95.265)	
[2022-01-25 16:05:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.170 (2.216)	Loss 0.8247 (0.8336)	Acc@1 81.738 (80.488)	Acc@5 95.117 (95.258)	
[2022-01-25 16:05:23 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.380 Acc@5 95.270
[2022-01-25 16:05:23 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.4%
[2022-01-25 16:05:23 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.38%
[2022-01-25 16:05:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][0/1251]	eta 7:20:12 lr 0.000079	time 21.1131 (21.1131)	loss 2.9155 (2.9155)	grad_norm 2.7112 (2.7112)	
[2022-01-25 16:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][10/1251]	eta 1:22:18 lr 0.000079	time 1.6092 (3.9796)	loss 2.9748 (3.0082)	grad_norm 2.1444 (2.7139)	
[2022-01-25 16:06:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][20/1251]	eta 1:05:17 lr 0.000079	time 1.8392 (3.1824)	loss 3.7834 (3.0210)	grad_norm 2.8007 (2.6965)	
[2022-01-25 16:06:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][30/1251]	eta 0:57:53 lr 0.000079	time 1.3882 (2.8445)	loss 2.6395 (3.0361)	grad_norm 2.6947 (2.6795)	
[2022-01-25 16:07:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][40/1251]	eta 0:55:21 lr 0.000079	time 3.9910 (2.7430)	loss 2.9917 (3.0133)	grad_norm 2.9196 (2.7142)	
[2022-01-25 16:07:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][50/1251]	eta 0:53:11 lr 0.000079	time 2.4494 (2.6577)	loss 3.4807 (2.9822)	grad_norm 2.5697 (2.6928)	
[2022-01-25 16:08:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][60/1251]	eta 0:51:29 lr 0.000079	time 2.4066 (2.5940)	loss 1.9839 (2.9836)	grad_norm 2.4224 (2.6819)	
[2022-01-25 16:08:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][70/1251]	eta 0:49:36 lr 0.000079	time 1.7370 (2.5200)	loss 2.6558 (2.9686)	grad_norm 2.8386 (2.6797)	
[2022-01-25 16:08:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][80/1251]	eta 0:48:24 lr 0.000079	time 3.4589 (2.4805)	loss 2.5824 (2.9678)	grad_norm 2.9428 (2.6858)	
[2022-01-25 16:09:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][90/1251]	eta 0:47:10 lr 0.000079	time 2.1606 (2.4380)	loss 2.5305 (2.9747)	grad_norm 3.4240 (2.7949)	
[2022-01-25 16:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][100/1251]	eta 0:46:07 lr 0.000079	time 2.0538 (2.4045)	loss 3.1025 (2.9738)	grad_norm 3.0795 (2.7811)	
[2022-01-25 16:09:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][110/1251]	eta 0:45:10 lr 0.000079	time 1.8803 (2.3756)	loss 3.0572 (2.9635)	grad_norm 2.4038 (2.7607)	
[2022-01-25 16:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][120/1251]	eta 0:44:49 lr 0.000079	time 3.1887 (2.3782)	loss 3.2384 (2.9603)	grad_norm 2.8176 (2.7603)	
[2022-01-25 16:10:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][130/1251]	eta 0:44:21 lr 0.000079	time 2.2141 (2.3743)	loss 2.3741 (2.9487)	grad_norm 2.8510 (2.7555)	
[2022-01-25 16:10:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][140/1251]	eta 0:43:52 lr 0.000079	time 1.6482 (2.3693)	loss 2.7580 (2.9633)	grad_norm 3.5679 (2.7462)	
[2022-01-25 16:11:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][150/1251]	eta 0:43:14 lr 0.000079	time 1.6734 (2.3565)	loss 3.4708 (2.9559)	grad_norm 2.8284 (2.7475)	
[2022-01-25 16:11:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][160/1251]	eta 0:42:46 lr 0.000079	time 3.6981 (2.3521)	loss 3.4325 (2.9667)	grad_norm 2.4457 (2.7334)	
[2022-01-25 16:12:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][170/1251]	eta 0:41:58 lr 0.000079	time 1.9396 (2.3294)	loss 3.0237 (2.9594)	grad_norm 2.6839 (2.7222)	
[2022-01-25 16:12:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][180/1251]	eta 0:41:16 lr 0.000079	time 2.0708 (2.3127)	loss 3.2530 (2.9682)	grad_norm 3.2772 (2.7108)	
[2022-01-25 16:12:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][190/1251]	eta 0:40:38 lr 0.000079	time 1.8716 (2.2985)	loss 3.6999 (2.9793)	grad_norm 2.8542 (2.7010)	
[2022-01-25 16:13:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][200/1251]	eta 0:40:07 lr 0.000079	time 2.5360 (2.2908)	loss 3.7569 (2.9951)	grad_norm 2.7734 (2.7046)	
[2022-01-25 16:13:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][210/1251]	eta 0:39:39 lr 0.000078	time 2.2948 (2.2862)	loss 3.5489 (3.0022)	grad_norm 2.3405 (2.6981)	
[2022-01-25 16:13:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][220/1251]	eta 0:39:13 lr 0.000078	time 1.9360 (2.2825)	loss 2.7807 (3.0147)	grad_norm 2.7987 (2.7064)	
[2022-01-25 16:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][230/1251]	eta 0:38:48 lr 0.000078	time 2.2026 (2.2807)	loss 3.3155 (3.0171)	grad_norm 3.0263 (2.7074)	
[2022-01-25 16:14:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][240/1251]	eta 0:38:27 lr 0.000078	time 3.0217 (2.2824)	loss 3.3014 (3.0308)	grad_norm 2.3924 (2.7052)	
[2022-01-25 16:14:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][250/1251]	eta 0:37:59 lr 0.000078	time 2.2232 (2.2768)	loss 3.0495 (3.0318)	grad_norm 2.5559 (2.6975)	
[2022-01-25 16:15:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][260/1251]	eta 0:37:34 lr 0.000078	time 2.7659 (2.2745)	loss 2.5061 (3.0284)	grad_norm 2.4270 (2.6992)	
[2022-01-25 16:15:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][270/1251]	eta 0:37:10 lr 0.000078	time 2.1670 (2.2742)	loss 3.4167 (3.0261)	grad_norm 2.4327 (2.6913)	
[2022-01-25 16:16:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][280/1251]	eta 0:36:51 lr 0.000078	time 3.6583 (2.2773)	loss 2.9081 (3.0309)	grad_norm 2.3493 (2.6890)	
[2022-01-25 16:16:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][290/1251]	eta 0:36:24 lr 0.000078	time 1.6318 (2.2727)	loss 3.4349 (3.0415)	grad_norm 2.7865 (2.6848)	
[2022-01-25 16:16:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][300/1251]	eta 0:35:53 lr 0.000078	time 1.8394 (2.2649)	loss 3.2146 (3.0351)	grad_norm 2.3761 (2.6797)	
[2022-01-25 16:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][310/1251]	eta 0:35:19 lr 0.000078	time 1.8934 (2.2528)	loss 3.2264 (3.0331)	grad_norm 2.8209 (2.6728)	
[2022-01-25 16:17:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][320/1251]	eta 0:34:56 lr 0.000078	time 2.8083 (2.2520)	loss 2.2874 (3.0310)	grad_norm 2.7210 (2.6732)	
[2022-01-25 16:17:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][330/1251]	eta 0:34:33 lr 0.000078	time 2.2690 (2.2517)	loss 3.3079 (3.0370)	grad_norm 2.4856 (2.6713)	
[2022-01-25 16:18:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][340/1251]	eta 0:34:10 lr 0.000078	time 2.1895 (2.2511)	loss 3.2889 (3.0367)	grad_norm 2.7836 (2.6701)	
[2022-01-25 16:18:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][350/1251]	eta 0:33:47 lr 0.000078	time 2.2224 (2.2507)	loss 3.5580 (3.0395)	grad_norm 3.0893 (2.6698)	
[2022-01-25 16:18:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][360/1251]	eta 0:33:25 lr 0.000078	time 3.1582 (2.2512)	loss 2.3402 (3.0395)	grad_norm 2.7588 (2.6731)	
[2022-01-25 16:19:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][370/1251]	eta 0:32:58 lr 0.000078	time 1.9613 (2.2458)	loss 2.4720 (3.0321)	grad_norm 2.8907 (2.6729)	
[2022-01-25 16:19:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][380/1251]	eta 0:32:31 lr 0.000078	time 2.6430 (2.2411)	loss 2.0284 (3.0317)	grad_norm 2.8353 (2.6703)	
[2022-01-25 16:19:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][390/1251]	eta 0:32:06 lr 0.000078	time 2.5158 (2.2378)	loss 3.4003 (3.0315)	grad_norm 2.2402 (2.6724)	
[2022-01-25 16:20:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][400/1251]	eta 0:31:45 lr 0.000078	time 2.1553 (2.2395)	loss 2.5782 (3.0308)	grad_norm 2.6446 (2.6671)	
[2022-01-25 16:20:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][410/1251]	eta 0:31:22 lr 0.000078	time 2.0039 (2.2383)	loss 3.0814 (3.0309)	grad_norm 2.6041 (2.6661)	
[2022-01-25 16:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][420/1251]	eta 0:31:04 lr 0.000078	time 3.4651 (2.2441)	loss 2.5135 (3.0305)	grad_norm 2.5207 (2.6649)	
[2022-01-25 16:21:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][430/1251]	eta 0:30:45 lr 0.000078	time 3.4039 (2.2482)	loss 3.6144 (3.0348)	grad_norm 2.5710 (2.6617)	
[2022-01-25 16:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][440/1251]	eta 0:30:21 lr 0.000078	time 2.5977 (2.2456)	loss 3.0376 (3.0298)	grad_norm 2.8276 (2.6638)	
[2022-01-25 16:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][450/1251]	eta 0:29:54 lr 0.000078	time 1.8870 (2.2399)	loss 3.0048 (3.0341)	grad_norm 2.5399 (2.6610)	
[2022-01-25 16:22:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][460/1251]	eta 0:29:27 lr 0.000078	time 2.0006 (2.2339)	loss 1.9449 (3.0358)	grad_norm 2.7360 (2.6624)	
[2022-01-25 16:22:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][470/1251]	eta 0:29:02 lr 0.000078	time 2.0039 (2.2312)	loss 3.7073 (3.0415)	grad_norm 3.0509 (2.6652)	
[2022-01-25 16:23:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][480/1251]	eta 0:28:38 lr 0.000078	time 2.4547 (2.2286)	loss 2.8681 (3.0435)	grad_norm 2.7078 (2.6640)	
[2022-01-25 16:23:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][490/1251]	eta 0:28:14 lr 0.000078	time 1.4721 (2.2271)	loss 3.4269 (3.0429)	grad_norm 2.8625 (2.6641)	
[2022-01-25 16:23:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][500/1251]	eta 0:27:51 lr 0.000078	time 2.1103 (2.2260)	loss 2.0869 (3.0400)	grad_norm 2.3552 (2.6601)	
[2022-01-25 16:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][510/1251]	eta 0:27:30 lr 0.000078	time 2.1566 (2.2280)	loss 3.4394 (3.0435)	grad_norm 2.5058 (2.6595)	
[2022-01-25 16:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][520/1251]	eta 0:27:13 lr 0.000078	time 2.7410 (2.2342)	loss 3.6281 (3.0506)	grad_norm 2.5460 (2.6599)	
[2022-01-25 16:25:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][530/1251]	eta 0:26:52 lr 0.000078	time 1.5045 (2.2358)	loss 3.4173 (3.0532)	grad_norm 2.2530 (2.6614)	
[2022-01-25 16:25:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][540/1251]	eta 0:26:28 lr 0.000078	time 1.5674 (2.2338)	loss 3.4327 (3.0560)	grad_norm 2.9787 (2.6656)	
[2022-01-25 16:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][550/1251]	eta 0:26:03 lr 0.000078	time 1.9111 (2.2304)	loss 3.3646 (3.0567)	grad_norm 2.8881 (2.6689)	
[2022-01-25 16:26:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][560/1251]	eta 0:25:37 lr 0.000078	time 2.0486 (2.2252)	loss 3.7510 (3.0599)	grad_norm 2.8254 (2.6747)	
[2022-01-25 16:26:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][570/1251]	eta 0:25:13 lr 0.000078	time 2.3832 (2.2222)	loss 3.5921 (3.0571)	grad_norm 2.8521 (2.6766)	
[2022-01-25 16:26:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][580/1251]	eta 0:24:51 lr 0.000078	time 2.5880 (2.2222)	loss 3.9008 (3.0601)	grad_norm 2.7800 (2.6776)	
[2022-01-25 16:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][590/1251]	eta 0:24:28 lr 0.000078	time 2.5428 (2.2217)	loss 3.2506 (3.0641)	grad_norm 2.2936 (2.6750)	
[2022-01-25 16:27:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][600/1251]	eta 0:24:07 lr 0.000078	time 2.4654 (2.2228)	loss 3.6558 (3.0684)	grad_norm 2.5093 (2.6768)	
[2022-01-25 16:28:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][610/1251]	eta 0:23:45 lr 0.000078	time 2.3578 (2.2232)	loss 3.7871 (3.0684)	grad_norm 3.0588 (2.6769)	
[2022-01-25 16:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][620/1251]	eta 0:23:23 lr 0.000078	time 2.7440 (2.2239)	loss 3.2698 (3.0718)	grad_norm 2.4032 (2.6756)	
[2022-01-25 16:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][630/1251]	eta 0:23:00 lr 0.000078	time 1.5863 (2.2223)	loss 3.5869 (3.0717)	grad_norm 2.8733 (2.6749)	
[2022-01-25 16:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][640/1251]	eta 0:22:37 lr 0.000078	time 2.2118 (2.2222)	loss 2.1225 (3.0683)	grad_norm 2.4394 (2.6742)	
[2022-01-25 16:29:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][650/1251]	eta 0:22:16 lr 0.000078	time 3.1327 (2.2238)	loss 3.2671 (3.0662)	grad_norm 2.5848 (2.6736)	
[2022-01-25 16:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][660/1251]	eta 0:21:53 lr 0.000078	time 1.6387 (2.2224)	loss 3.1218 (3.0669)	grad_norm 2.3978 (2.6798)	
[2022-01-25 16:30:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][670/1251]	eta 0:21:31 lr 0.000078	time 2.4851 (2.2221)	loss 3.5524 (3.0691)	grad_norm 2.2813 (2.6784)	
[2022-01-25 16:30:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][680/1251]	eta 0:21:09 lr 0.000078	time 2.4957 (2.2234)	loss 3.5546 (3.0716)	grad_norm 2.6647 (2.6796)	
[2022-01-25 16:31:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][690/1251]	eta 0:20:47 lr 0.000077	time 3.2235 (2.2233)	loss 3.7547 (3.0718)	grad_norm 2.8059 (2.6790)	
[2022-01-25 16:31:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][700/1251]	eta 0:20:22 lr 0.000077	time 1.7886 (2.2190)	loss 3.3810 (3.0742)	grad_norm 2.5119 (2.6798)	
[2022-01-25 16:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][710/1251]	eta 0:19:59 lr 0.000077	time 1.9447 (2.2163)	loss 3.0955 (3.0769)	grad_norm 2.7351 (2.6805)	
[2022-01-25 16:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][720/1251]	eta 0:19:38 lr 0.000077	time 3.2887 (2.2190)	loss 2.2637 (3.0757)	grad_norm 2.9299 (2.6844)	
[2022-01-25 16:32:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][730/1251]	eta 0:19:17 lr 0.000077	time 2.0654 (2.2209)	loss 3.3626 (3.0794)	grad_norm 3.0955 (2.6859)	
[2022-01-25 16:32:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][740/1251]	eta 0:18:54 lr 0.000077	time 2.1863 (2.2201)	loss 2.5990 (3.0783)	grad_norm 2.5593 (2.6842)	
[2022-01-25 16:33:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][750/1251]	eta 0:18:32 lr 0.000077	time 2.3588 (2.2200)	loss 3.2877 (3.0781)	grad_norm 2.4734 (2.6834)	
[2022-01-25 16:33:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][760/1251]	eta 0:18:08 lr 0.000077	time 1.5779 (2.2170)	loss 2.8922 (3.0799)	grad_norm 2.4588 (2.6856)	
[2022-01-25 16:33:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][770/1251]	eta 0:17:45 lr 0.000077	time 1.8562 (2.2154)	loss 3.8149 (3.0847)	grad_norm 2.8061 (2.6862)	
[2022-01-25 16:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][780/1251]	eta 0:17:23 lr 0.000077	time 2.1695 (2.2158)	loss 2.5266 (3.0829)	grad_norm 2.3415 (2.6863)	
[2022-01-25 16:34:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][790/1251]	eta 0:17:01 lr 0.000077	time 2.2075 (2.2158)	loss 2.9958 (3.0840)	grad_norm 2.8603 (2.6861)	
[2022-01-25 16:34:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][800/1251]	eta 0:16:39 lr 0.000077	time 1.8748 (2.2156)	loss 1.9174 (3.0829)	grad_norm 3.4985 (2.6866)	
[2022-01-25 16:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][810/1251]	eta 0:16:16 lr 0.000077	time 1.9071 (2.2152)	loss 2.5439 (3.0857)	grad_norm 2.5158 (2.6861)	
[2022-01-25 16:35:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][820/1251]	eta 0:15:55 lr 0.000077	time 1.8644 (2.2159)	loss 3.2678 (3.0875)	grad_norm 2.4862 (2.6868)	
[2022-01-25 16:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][830/1251]	eta 0:15:32 lr 0.000077	time 2.4915 (2.2155)	loss 3.2472 (3.0854)	grad_norm 2.5616 (2.6853)	
[2022-01-25 16:36:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][840/1251]	eta 0:15:09 lr 0.000077	time 1.9860 (2.2131)	loss 2.6648 (3.0860)	grad_norm 2.4047 (2.6841)	
[2022-01-25 16:36:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][850/1251]	eta 0:14:46 lr 0.000077	time 2.2366 (2.2103)	loss 2.7639 (3.0854)	grad_norm 2.9084 (2.6825)	
[2022-01-25 16:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][860/1251]	eta 0:14:24 lr 0.000077	time 2.1063 (2.2104)	loss 2.2929 (3.0844)	grad_norm 2.7531 (2.6968)	
[2022-01-25 16:37:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][870/1251]	eta 0:14:01 lr 0.000077	time 2.4882 (2.2090)	loss 3.2027 (3.0854)	grad_norm 3.7757 (2.7010)	
[2022-01-25 16:37:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][880/1251]	eta 0:13:39 lr 0.000077	time 1.5848 (2.2087)	loss 3.3443 (3.0867)	grad_norm 2.3055 (2.7058)	
[2022-01-25 16:38:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][890/1251]	eta 0:13:17 lr 0.000077	time 2.7351 (2.2090)	loss 2.6835 (3.0867)	grad_norm 2.3285 (2.7060)	
[2022-01-25 16:38:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][900/1251]	eta 0:12:55 lr 0.000077	time 1.9505 (2.2082)	loss 3.0690 (3.0886)	grad_norm 2.5732 (2.7071)	
[2022-01-25 16:38:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][910/1251]	eta 0:12:33 lr 0.000077	time 3.5774 (2.2104)	loss 2.0907 (3.0883)	grad_norm 2.6259 (2.7070)	
[2022-01-25 16:39:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][920/1251]	eta 0:12:12 lr 0.000077	time 2.2190 (2.2116)	loss 3.1746 (3.0898)	grad_norm 2.5236 (2.7059)	
[2022-01-25 16:39:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][930/1251]	eta 0:11:50 lr 0.000077	time 2.4726 (2.2127)	loss 3.4931 (3.0921)	grad_norm 2.5138 (2.7037)	
[2022-01-25 16:40:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][940/1251]	eta 0:11:28 lr 0.000077	time 1.7430 (2.2136)	loss 2.2957 (3.0909)	grad_norm 2.7585 (2.7022)	
[2022-01-25 16:40:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][950/1251]	eta 0:11:05 lr 0.000077	time 2.1668 (2.2118)	loss 2.9864 (3.0914)	grad_norm 2.9881 (2.7027)	
[2022-01-25 16:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][960/1251]	eta 0:10:42 lr 0.000077	time 1.5801 (2.2093)	loss 3.4240 (3.0921)	grad_norm 2.4489 (2.7024)	
[2022-01-25 16:41:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][970/1251]	eta 0:10:20 lr 0.000077	time 1.7711 (2.2076)	loss 2.3289 (3.0905)	grad_norm 2.5154 (2.7021)	
[2022-01-25 16:41:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][980/1251]	eta 0:09:57 lr 0.000077	time 1.9090 (2.2059)	loss 2.2908 (3.0857)	grad_norm 2.9334 (2.7020)	
[2022-01-25 16:41:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][990/1251]	eta 0:09:35 lr 0.000077	time 1.9618 (2.2048)	loss 2.7761 (3.0869)	grad_norm 2.5487 (2.7010)	
[2022-01-25 16:42:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1000/1251]	eta 0:09:13 lr 0.000077	time 2.5485 (2.2055)	loss 2.3601 (3.0848)	grad_norm 2.6294 (2.6999)	
[2022-01-25 16:42:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1010/1251]	eta 0:08:51 lr 0.000077	time 1.9349 (2.2066)	loss 2.7293 (3.0856)	grad_norm 2.5251 (2.7049)	
[2022-01-25 16:42:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1020/1251]	eta 0:08:30 lr 0.000077	time 1.8431 (2.2091)	loss 3.4185 (3.0887)	grad_norm 2.4102 (2.7050)	
[2022-01-25 16:43:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1030/1251]	eta 0:08:07 lr 0.000077	time 1.8713 (2.2072)	loss 2.8353 (3.0881)	grad_norm 2.6339 (2.7059)	
[2022-01-25 16:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1040/1251]	eta 0:07:45 lr 0.000077	time 2.5409 (2.2061)	loss 3.7059 (3.0883)	grad_norm 3.5458 (2.7066)	
[2022-01-25 16:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1050/1251]	eta 0:07:23 lr 0.000077	time 1.8970 (2.2057)	loss 3.0275 (3.0878)	grad_norm 6.3989 (2.7101)	
[2022-01-25 16:44:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1060/1251]	eta 0:07:01 lr 0.000077	time 1.8692 (2.2053)	loss 3.5473 (3.0886)	grad_norm 2.2664 (2.7105)	
[2022-01-25 16:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1070/1251]	eta 0:06:39 lr 0.000077	time 2.2844 (2.2063)	loss 2.9566 (3.0885)	grad_norm 2.8283 (2.7104)	
[2022-01-25 16:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1080/1251]	eta 0:06:17 lr 0.000077	time 1.7239 (2.2056)	loss 3.3122 (3.0909)	grad_norm 2.9330 (2.7112)	
[2022-01-25 16:45:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1090/1251]	eta 0:05:54 lr 0.000077	time 1.9634 (2.2049)	loss 3.4538 (3.0896)	grad_norm 2.5303 (2.7108)	
[2022-01-25 16:45:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1100/1251]	eta 0:05:32 lr 0.000077	time 1.8887 (2.2040)	loss 3.5072 (3.0892)	grad_norm 3.1296 (2.7104)	
[2022-01-25 16:46:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1110/1251]	eta 0:05:10 lr 0.000077	time 1.8786 (2.2036)	loss 2.5301 (3.0892)	grad_norm 2.7678 (2.7103)	
[2022-01-25 16:46:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1120/1251]	eta 0:04:48 lr 0.000077	time 2.1192 (2.2031)	loss 3.3527 (3.0907)	grad_norm 2.4139 (2.7094)	
[2022-01-25 16:46:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1130/1251]	eta 0:04:26 lr 0.000077	time 2.0253 (2.2044)	loss 2.4217 (3.0895)	grad_norm 2.5125 (2.7092)	
[2022-01-25 16:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1140/1251]	eta 0:04:04 lr 0.000077	time 1.4621 (2.2047)	loss 3.2276 (3.0904)	grad_norm 2.6219 (2.7091)	
[2022-01-25 16:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1150/1251]	eta 0:03:42 lr 0.000077	time 2.0040 (2.2047)	loss 2.0623 (3.0881)	grad_norm 3.0541 (2.7082)	
[2022-01-25 16:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1160/1251]	eta 0:03:20 lr 0.000077	time 2.5272 (2.2040)	loss 3.0923 (3.0872)	grad_norm 2.8437 (2.7086)	
[2022-01-25 16:48:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1170/1251]	eta 0:02:58 lr 0.000076	time 1.5277 (2.2031)	loss 3.7028 (3.0878)	grad_norm 2.3203 (2.7075)	
[2022-01-25 16:48:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1180/1251]	eta 0:02:36 lr 0.000076	time 1.8932 (2.2020)	loss 3.4032 (3.0866)	grad_norm 3.0152 (2.7072)	
[2022-01-25 16:49:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1190/1251]	eta 0:02:14 lr 0.000076	time 2.2937 (2.2017)	loss 3.4994 (3.0877)	grad_norm 2.6360 (2.7083)	
[2022-01-25 16:49:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1200/1251]	eta 0:01:52 lr 0.000076	time 2.7021 (2.2016)	loss 2.1471 (3.0862)	grad_norm 2.7473 (2.7068)	
[2022-01-25 16:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1210/1251]	eta 0:01:30 lr 0.000076	time 1.7403 (2.2016)	loss 3.1037 (3.0871)	grad_norm 3.2197 (2.7061)	
[2022-01-25 16:50:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1220/1251]	eta 0:01:08 lr 0.000076	time 2.4869 (2.2035)	loss 3.5623 (3.0894)	grad_norm 2.5618 (2.7050)	
[2022-01-25 16:50:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1230/1251]	eta 0:00:46 lr 0.000076	time 2.2941 (2.2034)	loss 3.1180 (3.0887)	grad_norm 2.5258 (2.7047)	
[2022-01-25 16:50:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1240/1251]	eta 0:00:24 lr 0.000076	time 2.1811 (2.2024)	loss 2.4184 (3.0863)	grad_norm 2.7223 (2.7044)	
[2022-01-25 16:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [249/300][1250/1251]	eta 0:00:02 lr 0.000076	time 1.3875 (2.1966)	loss 3.2849 (3.0865)	grad_norm 2.5753 (2.7039)	
[2022-01-25 16:51:12 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 249 training takes 0:45:48
[2022-01-25 16:51:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.259 (18.259)	Loss 0.7840 (0.7840)	Acc@1 81.934 (81.934)	Acc@5 95.410 (95.410)	
[2022-01-25 16:51:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.958 (3.311)	Loss 0.8695 (0.8204)	Acc@1 79.297 (80.824)	Acc@5 94.824 (95.410)	
[2022-01-25 16:52:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.628 (2.562)	Loss 0.8887 (0.8287)	Acc@1 78.809 (80.539)	Acc@5 95.117 (95.387)	
[2022-01-25 16:52:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.644 (2.257)	Loss 0.8877 (0.8400)	Acc@1 80.371 (80.390)	Acc@5 93.750 (95.231)	
[2022-01-25 16:52:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 5.438 (2.208)	Loss 0.6911 (0.8374)	Acc@1 84.668 (80.447)	Acc@5 96.484 (95.258)	
[2022-01-25 16:52:49 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.274 Acc@5 95.234
[2022-01-25 16:52:49 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.3%
[2022-01-25 16:52:49 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.38%
[2022-01-25 16:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][0/1251]	eta 7:26:37 lr 0.000076	time 21.4206 (21.4206)	loss 2.0666 (2.0666)	grad_norm 2.6323 (2.6323)	
[2022-01-25 16:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][10/1251]	eta 1:21:20 lr 0.000076	time 2.2161 (3.9326)	loss 3.5302 (2.8116)	grad_norm 3.3320 (2.7499)	
[2022-01-25 16:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][20/1251]	eta 1:04:12 lr 0.000076	time 2.2819 (3.1293)	loss 2.4683 (2.8855)	grad_norm 2.4968 (2.7095)	
[2022-01-25 16:54:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][30/1251]	eta 0:57:00 lr 0.000076	time 1.8189 (2.8013)	loss 2.8492 (2.9924)	grad_norm 2.7027 (2.7294)	
[2022-01-25 16:54:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][40/1251]	eta 0:55:05 lr 0.000076	time 5.2676 (2.7298)	loss 3.2524 (2.9966)	grad_norm 2.8288 (2.7681)	
[2022-01-25 16:55:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][50/1251]	eta 0:52:45 lr 0.000076	time 2.7541 (2.6353)	loss 3.4961 (3.0189)	grad_norm 2.7666 (2.7489)	
[2022-01-25 16:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][60/1251]	eta 0:50:10 lr 0.000076	time 1.8034 (2.5280)	loss 3.3998 (3.0033)	grad_norm 2.6375 (2.7620)	
[2022-01-25 16:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][70/1251]	eta 0:48:32 lr 0.000076	time 1.8466 (2.4664)	loss 2.7097 (3.0121)	grad_norm 2.5760 (2.7517)	
[2022-01-25 16:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][80/1251]	eta 0:47:16 lr 0.000076	time 2.2563 (2.4227)	loss 3.1617 (3.0396)	grad_norm 2.4804 (2.7277)	
[2022-01-25 16:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][90/1251]	eta 0:46:31 lr 0.000076	time 2.6445 (2.4042)	loss 2.5865 (3.0457)	grad_norm 3.0618 (2.7151)	
[2022-01-25 16:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][100/1251]	eta 0:45:52 lr 0.000076	time 1.9407 (2.3913)	loss 3.4356 (3.0169)	grad_norm 2.7251 (2.6992)	
[2022-01-25 16:57:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][110/1251]	eta 0:45:23 lr 0.000076	time 2.1076 (2.3871)	loss 2.8760 (3.0448)	grad_norm 2.4231 (2.6951)	
[2022-01-25 16:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][120/1251]	eta 0:44:43 lr 0.000076	time 2.2071 (2.3729)	loss 2.4246 (3.0366)	grad_norm 2.7453 (2.6885)	
[2022-01-25 16:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][130/1251]	eta 0:44:07 lr 0.000076	time 2.2987 (2.3616)	loss 3.0741 (3.0284)	grad_norm 3.6761 (2.6843)	
[2022-01-25 16:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][140/1251]	eta 0:43:18 lr 0.000076	time 1.7957 (2.3391)	loss 2.5137 (3.0247)	grad_norm 2.6545 (2.6834)	
[2022-01-25 16:58:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][150/1251]	eta 0:42:41 lr 0.000076	time 2.0403 (2.3269)	loss 3.5835 (3.0350)	grad_norm 2.7571 (2.6827)	
[2022-01-25 16:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][160/1251]	eta 0:42:02 lr 0.000076	time 2.2186 (2.3121)	loss 3.4123 (3.0462)	grad_norm 2.2560 (2.6914)	
[2022-01-25 16:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][170/1251]	eta 0:41:33 lr 0.000076	time 2.7104 (2.3068)	loss 3.6372 (3.0493)	grad_norm 2.5983 (2.6876)	
[2022-01-25 16:59:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][180/1251]	eta 0:41:08 lr 0.000076	time 2.1808 (2.3044)	loss 2.5874 (3.0580)	grad_norm 3.0885 (2.6943)	
[2022-01-25 17:00:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][190/1251]	eta 0:40:45 lr 0.000076	time 2.1271 (2.3050)	loss 3.0998 (3.0586)	grad_norm 2.2435 (2.6938)	
[2022-01-25 17:00:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][200/1251]	eta 0:40:14 lr 0.000076	time 2.9258 (2.2975)	loss 3.4565 (3.0619)	grad_norm 3.0684 (2.7049)	
[2022-01-25 17:00:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][210/1251]	eta 0:39:42 lr 0.000076	time 1.8902 (2.2885)	loss 2.9097 (3.0685)	grad_norm 2.4167 (2.7028)	
[2022-01-25 17:01:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][220/1251]	eta 0:39:14 lr 0.000076	time 2.1363 (2.2835)	loss 3.1655 (3.0734)	grad_norm 2.4807 (2.7004)	
[2022-01-25 17:01:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][230/1251]	eta 0:38:49 lr 0.000076	time 2.4461 (2.2814)	loss 3.6869 (3.0721)	grad_norm 3.2945 (2.7087)	
[2022-01-25 17:01:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][240/1251]	eta 0:38:18 lr 0.000076	time 2.1734 (2.2736)	loss 3.7131 (3.0725)	grad_norm 4.5603 (2.7135)	
[2022-01-25 17:02:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][250/1251]	eta 0:37:53 lr 0.000076	time 2.5702 (2.2716)	loss 3.1464 (3.0675)	grad_norm 2.8126 (2.7268)	
[2022-01-25 17:02:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][260/1251]	eta 0:37:30 lr 0.000076	time 2.2140 (2.2707)	loss 3.4169 (3.0649)	grad_norm 2.7248 (2.7238)	
[2022-01-25 17:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][270/1251]	eta 0:37:09 lr 0.000076	time 3.2295 (2.2725)	loss 3.1115 (3.0683)	grad_norm 2.6896 (2.7346)	
[2022-01-25 17:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][280/1251]	eta 0:36:40 lr 0.000076	time 2.0267 (2.2660)	loss 3.4673 (3.0677)	grad_norm 2.2833 (2.7318)	
[2022-01-25 17:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][290/1251]	eta 0:36:10 lr 0.000076	time 1.9744 (2.2585)	loss 2.9125 (3.0696)	grad_norm 2.5726 (2.7282)	
[2022-01-25 17:04:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][300/1251]	eta 0:35:40 lr 0.000076	time 2.3703 (2.2512)	loss 3.5952 (3.0681)	grad_norm 2.9855 (2.7300)	
[2022-01-25 17:04:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][310/1251]	eta 0:35:18 lr 0.000076	time 2.8732 (2.2516)	loss 2.5978 (3.0702)	grad_norm 3.1365 (2.7249)	
[2022-01-25 17:04:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][320/1251]	eta 0:34:56 lr 0.000076	time 1.9017 (2.2516)	loss 2.8687 (3.0656)	grad_norm 2.2143 (2.7155)	
[2022-01-25 17:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][330/1251]	eta 0:34:34 lr 0.000076	time 2.4485 (2.2520)	loss 3.6475 (3.0699)	grad_norm 2.7054 (2.7107)	
[2022-01-25 17:05:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][340/1251]	eta 0:34:09 lr 0.000076	time 1.8307 (2.2499)	loss 2.5312 (3.0678)	grad_norm 2.5325 (2.7064)	
[2022-01-25 17:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][350/1251]	eta 0:33:51 lr 0.000076	time 3.7193 (2.2546)	loss 3.6020 (3.0655)	grad_norm 2.4182 (2.7055)	
[2022-01-25 17:06:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][360/1251]	eta 0:33:26 lr 0.000076	time 1.7492 (2.2523)	loss 3.2960 (3.0717)	grad_norm 2.4750 (2.7055)	
[2022-01-25 17:06:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][370/1251]	eta 0:32:59 lr 0.000076	time 2.0251 (2.2474)	loss 2.2823 (3.0668)	grad_norm 2.7119 (2.7071)	
[2022-01-25 17:07:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][380/1251]	eta 0:32:33 lr 0.000076	time 2.0295 (2.2425)	loss 3.8676 (3.0723)	grad_norm 2.7662 (2.7109)	
[2022-01-25 17:07:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][390/1251]	eta 0:32:10 lr 0.000076	time 3.1226 (2.2423)	loss 3.3591 (3.0728)	grad_norm 2.5496 (2.7152)	
[2022-01-25 17:07:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][400/1251]	eta 0:31:43 lr 0.000075	time 2.0062 (2.2371)	loss 3.2356 (3.0736)	grad_norm 2.7610 (2.7164)	
[2022-01-25 17:08:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][410/1251]	eta 0:31:15 lr 0.000075	time 1.8348 (2.2306)	loss 2.0278 (3.0769)	grad_norm 2.8662 (2.7148)	
[2022-01-25 17:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][420/1251]	eta 0:30:52 lr 0.000075	time 2.2662 (2.2297)	loss 3.1639 (3.0779)	grad_norm 2.1494 (2.7124)	
[2022-01-25 17:08:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][430/1251]	eta 0:30:33 lr 0.000075	time 3.0703 (2.2337)	loss 2.0090 (3.0769)	grad_norm 3.1184 (2.7110)	
[2022-01-25 17:09:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][440/1251]	eta 0:30:14 lr 0.000075	time 2.8679 (2.2378)	loss 3.4910 (3.0740)	grad_norm 2.9692 (2.7128)	
[2022-01-25 17:09:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][450/1251]	eta 0:29:51 lr 0.000075	time 1.6032 (2.2371)	loss 3.4130 (3.0784)	grad_norm 2.7200 (2.7167)	
[2022-01-25 17:10:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][460/1251]	eta 0:29:28 lr 0.000075	time 1.9786 (2.2357)	loss 2.7774 (3.0771)	grad_norm 3.2008 (2.7152)	
[2022-01-25 17:10:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][470/1251]	eta 0:29:02 lr 0.000075	time 2.5699 (2.2310)	loss 2.4744 (3.0771)	grad_norm 2.6505 (2.7158)	
[2022-01-25 17:10:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][480/1251]	eta 0:28:36 lr 0.000075	time 2.2024 (2.2263)	loss 3.0790 (3.0794)	grad_norm 2.7836 (2.7126)	
[2022-01-25 17:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][490/1251]	eta 0:28:12 lr 0.000075	time 2.1490 (2.2241)	loss 2.6637 (3.0751)	grad_norm 2.6367 (2.7122)	
[2022-01-25 17:11:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][500/1251]	eta 0:27:51 lr 0.000075	time 2.1043 (2.2264)	loss 3.2326 (3.0782)	grad_norm 2.1994 (2.7091)	
[2022-01-25 17:11:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][510/1251]	eta 0:27:31 lr 0.000075	time 2.7621 (2.2288)	loss 3.4992 (3.0758)	grad_norm 2.3277 (2.7052)	
[2022-01-25 17:12:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][520/1251]	eta 0:27:09 lr 0.000075	time 2.1253 (2.2297)	loss 3.3574 (3.0727)	grad_norm 2.6754 (2.7034)	
[2022-01-25 17:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][530/1251]	eta 0:26:48 lr 0.000075	time 2.2120 (2.2304)	loss 3.1468 (3.0713)	grad_norm 3.0849 (2.7051)	
[2022-01-25 17:12:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][540/1251]	eta 0:26:23 lr 0.000075	time 1.9388 (2.2269)	loss 3.2474 (3.0754)	grad_norm 2.6800 (2.7107)	
[2022-01-25 17:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][550/1251]	eta 0:25:59 lr 0.000075	time 2.7392 (2.2247)	loss 2.7670 (3.0754)	grad_norm 2.4719 (2.7106)	
[2022-01-25 17:13:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][560/1251]	eta 0:25:34 lr 0.000075	time 1.7446 (2.2210)	loss 3.5193 (3.0804)	grad_norm 2.7246 (2.7085)	
[2022-01-25 17:13:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][570/1251]	eta 0:25:09 lr 0.000075	time 1.7534 (2.2162)	loss 2.7804 (3.0773)	grad_norm 2.9275 (2.7082)	
[2022-01-25 17:14:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][580/1251]	eta 0:24:45 lr 0.000075	time 1.8712 (2.2141)	loss 3.5936 (3.0781)	grad_norm 2.6014 (2.7086)	
[2022-01-25 17:14:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][590/1251]	eta 0:24:25 lr 0.000075	time 3.8006 (2.2167)	loss 3.3148 (3.0795)	grad_norm 2.9224 (2.7089)	
[2022-01-25 17:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][600/1251]	eta 0:24:03 lr 0.000075	time 2.1182 (2.2179)	loss 2.9210 (3.0800)	grad_norm 2.7907 (2.7097)	
[2022-01-25 17:15:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][610/1251]	eta 0:23:42 lr 0.000075	time 2.3716 (2.2199)	loss 3.3685 (3.0846)	grad_norm 2.2289 (2.7068)	
[2022-01-25 17:15:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][620/1251]	eta 0:23:21 lr 0.000075	time 2.8858 (2.2213)	loss 2.2310 (3.0823)	grad_norm 2.7368 (2.7052)	
[2022-01-25 17:16:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][630/1251]	eta 0:22:59 lr 0.000075	time 2.4906 (2.2218)	loss 3.1560 (3.0855)	grad_norm 2.5984 (2.7035)	
[2022-01-25 17:16:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][640/1251]	eta 0:22:36 lr 0.000075	time 1.8981 (2.2195)	loss 3.3858 (3.0870)	grad_norm 2.5348 (2.7010)	
[2022-01-25 17:16:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][650/1251]	eta 0:22:12 lr 0.000075	time 2.5882 (2.2176)	loss 3.4158 (3.0882)	grad_norm 2.3389 (2.6982)	
[2022-01-25 17:17:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][660/1251]	eta 0:21:49 lr 0.000075	time 2.1907 (2.2156)	loss 3.3968 (3.0915)	grad_norm 2.3848 (2.6971)	
[2022-01-25 17:17:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][670/1251]	eta 0:21:26 lr 0.000075	time 2.1735 (2.2143)	loss 3.2962 (3.0947)	grad_norm 2.5146 (2.7032)	
[2022-01-25 17:17:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][680/1251]	eta 0:21:03 lr 0.000075	time 2.2694 (2.2135)	loss 2.3508 (3.0935)	grad_norm 2.6119 (2.7079)	
[2022-01-25 17:18:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][690/1251]	eta 0:20:41 lr 0.000075	time 2.4437 (2.2138)	loss 3.4107 (3.0937)	grad_norm 3.0634 (2.7086)	
[2022-01-25 17:18:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][700/1251]	eta 0:20:19 lr 0.000075	time 2.2389 (2.2132)	loss 2.3055 (3.0918)	grad_norm 2.7343 (2.7075)	
[2022-01-25 17:19:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][710/1251]	eta 0:19:56 lr 0.000075	time 2.0712 (2.2107)	loss 2.4486 (3.0902)	grad_norm 3.7777 (2.7097)	
[2022-01-25 17:19:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][720/1251]	eta 0:19:35 lr 0.000075	time 1.8548 (2.2135)	loss 3.1287 (3.0902)	grad_norm 2.6951 (2.7090)	
[2022-01-25 17:19:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][730/1251]	eta 0:19:14 lr 0.000075	time 3.3583 (2.2155)	loss 2.8981 (3.0906)	grad_norm 2.5843 (2.7086)	
[2022-01-25 17:20:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][740/1251]	eta 0:18:51 lr 0.000075	time 1.8793 (2.2151)	loss 2.0982 (3.0879)	grad_norm 2.4612 (2.7054)	
[2022-01-25 17:20:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][750/1251]	eta 0:18:28 lr 0.000075	time 1.5697 (2.2127)	loss 3.1116 (3.0873)	grad_norm 3.1644 (2.7043)	
[2022-01-25 17:20:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][760/1251]	eta 0:18:07 lr 0.000075	time 2.3051 (2.2147)	loss 3.7512 (3.0890)	grad_norm 2.5879 (2.7024)	
[2022-01-25 17:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][770/1251]	eta 0:17:44 lr 0.000075	time 3.0475 (2.2140)	loss 3.4850 (3.0901)	grad_norm 2.6611 (2.7047)	
[2022-01-25 17:21:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][780/1251]	eta 0:17:21 lr 0.000075	time 1.6759 (2.2114)	loss 3.7912 (3.0935)	grad_norm 2.4305 (2.7055)	
[2022-01-25 17:21:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][790/1251]	eta 0:16:59 lr 0.000075	time 1.9230 (2.2106)	loss 2.7436 (3.0922)	grad_norm 2.7893 (2.7042)	
[2022-01-25 17:22:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][800/1251]	eta 0:16:36 lr 0.000075	time 2.5203 (2.2105)	loss 3.4353 (3.0954)	grad_norm 2.5891 (2.7052)	
[2022-01-25 17:22:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][810/1251]	eta 0:16:15 lr 0.000075	time 3.6753 (2.2115)	loss 3.0449 (3.0948)	grad_norm 2.6254 (2.7053)	
[2022-01-25 17:23:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][820/1251]	eta 0:15:53 lr 0.000075	time 2.0454 (2.2127)	loss 3.3353 (3.0959)	grad_norm 2.4815 (2.7061)	
[2022-01-25 17:23:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][830/1251]	eta 0:15:31 lr 0.000075	time 1.6911 (2.2121)	loss 3.3289 (3.0937)	grad_norm 2.3639 (2.7048)	
[2022-01-25 17:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][840/1251]	eta 0:15:09 lr 0.000075	time 2.2672 (2.2120)	loss 2.9043 (3.0941)	grad_norm 2.5437 (2.7083)	
[2022-01-25 17:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][850/1251]	eta 0:14:46 lr 0.000075	time 2.4851 (2.2111)	loss 3.4867 (3.0949)	grad_norm 2.8399 (2.7099)	
[2022-01-25 17:24:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][860/1251]	eta 0:14:24 lr 0.000075	time 1.9473 (2.2102)	loss 3.6859 (3.0968)	grad_norm 2.4780 (2.7097)	
[2022-01-25 17:24:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][870/1251]	eta 0:14:00 lr 0.000075	time 1.5224 (2.2070)	loss 3.4160 (3.0963)	grad_norm 2.5015 (2.7078)	
[2022-01-25 17:25:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][880/1251]	eta 0:13:38 lr 0.000075	time 1.5871 (2.2055)	loss 3.2912 (3.0948)	grad_norm 2.5833 (2.7088)	
[2022-01-25 17:25:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][890/1251]	eta 0:13:16 lr 0.000074	time 2.5796 (2.2056)	loss 3.3414 (3.0961)	grad_norm 2.5770 (2.7088)	
[2022-01-25 17:25:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][900/1251]	eta 0:12:55 lr 0.000074	time 3.2430 (2.2081)	loss 3.1651 (3.0949)	grad_norm 2.5962 (2.7090)	
[2022-01-25 17:26:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][910/1251]	eta 0:12:34 lr 0.000074	time 1.8837 (2.2129)	loss 3.4270 (3.0938)	grad_norm 2.5751 (2.7071)	
[2022-01-25 17:26:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][920/1251]	eta 0:12:13 lr 0.000074	time 1.5446 (2.2157)	loss 2.2284 (3.0921)	grad_norm 2.6079 (2.7060)	
[2022-01-25 17:27:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][930/1251]	eta 0:11:51 lr 0.000074	time 2.6845 (2.2174)	loss 3.5722 (3.0930)	grad_norm 2.7553 (2.7048)	
[2022-01-25 17:27:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][940/1251]	eta 0:11:29 lr 0.000074	time 2.3279 (2.2169)	loss 2.8125 (3.0964)	grad_norm 2.6916 (2.7066)	
[2022-01-25 17:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][950/1251]	eta 0:11:06 lr 0.000074	time 1.6283 (2.2132)	loss 2.8300 (3.0955)	grad_norm 3.0207 (2.7057)	
[2022-01-25 17:28:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][960/1251]	eta 0:10:42 lr 0.000074	time 2.2006 (2.2096)	loss 2.8423 (3.0924)	grad_norm 2.7074 (2.7052)	
[2022-01-25 17:28:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][970/1251]	eta 0:10:20 lr 0.000074	time 1.6598 (2.2080)	loss 3.3099 (3.0929)	grad_norm 2.5821 (2.7044)	
[2022-01-25 17:28:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][980/1251]	eta 0:09:58 lr 0.000074	time 2.2247 (2.2077)	loss 2.7626 (3.0924)	grad_norm 2.4208 (2.7038)	
[2022-01-25 17:29:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][990/1251]	eta 0:09:35 lr 0.000074	time 1.5847 (2.2053)	loss 2.8170 (3.0908)	grad_norm 2.7676 (2.7012)	
[2022-01-25 17:29:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1000/1251]	eta 0:09:13 lr 0.000074	time 2.9420 (2.2056)	loss 3.1038 (3.0908)	grad_norm 2.5294 (2.6995)	
[2022-01-25 17:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1010/1251]	eta 0:08:51 lr 0.000074	time 1.9546 (2.2039)	loss 2.5583 (3.0880)	grad_norm 2.2465 (2.6979)	
[2022-01-25 17:30:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1020/1251]	eta 0:08:29 lr 0.000074	time 1.8708 (2.2053)	loss 2.8870 (3.0865)	grad_norm 2.4575 (2.6955)	
[2022-01-25 17:30:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1030/1251]	eta 0:08:07 lr 0.000074	time 1.5919 (2.2066)	loss 3.6576 (3.0868)	grad_norm 2.5570 (2.6944)	
[2022-01-25 17:31:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1040/1251]	eta 0:07:46 lr 0.000074	time 3.3897 (2.2094)	loss 3.3621 (3.0864)	grad_norm 2.4987 (2.6939)	
[2022-01-25 17:31:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1050/1251]	eta 0:07:24 lr 0.000074	time 1.8020 (2.2091)	loss 2.1537 (3.0866)	grad_norm 2.4647 (2.6924)	
[2022-01-25 17:31:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1060/1251]	eta 0:07:02 lr 0.000074	time 2.0934 (2.2104)	loss 3.6841 (3.0881)	grad_norm 2.7166 (2.6915)	
[2022-01-25 17:32:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1070/1251]	eta 0:06:40 lr 0.000074	time 1.5498 (2.2103)	loss 2.1939 (3.0860)	grad_norm 2.4977 (2.6890)	
[2022-01-25 17:32:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1080/1251]	eta 0:06:17 lr 0.000074	time 2.5712 (2.2082)	loss 3.0822 (3.0854)	grad_norm 2.8141 (2.6892)	
[2022-01-25 17:32:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1090/1251]	eta 0:05:55 lr 0.000074	time 1.5491 (2.2064)	loss 3.3438 (3.0857)	grad_norm 2.9608 (2.6879)	
[2022-01-25 17:33:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1100/1251]	eta 0:05:32 lr 0.000074	time 1.8537 (2.2042)	loss 3.3893 (3.0872)	grad_norm 2.5084 (2.6881)	
[2022-01-25 17:33:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1110/1251]	eta 0:05:10 lr 0.000074	time 2.2283 (2.2039)	loss 3.3605 (3.0881)	grad_norm 2.6547 (2.6878)	
[2022-01-25 17:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1120/1251]	eta 0:04:48 lr 0.000074	time 3.0309 (2.2045)	loss 3.2020 (3.0887)	grad_norm 2.7579 (2.6897)	
[2022-01-25 17:34:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1130/1251]	eta 0:04:26 lr 0.000074	time 2.5408 (2.2052)	loss 3.5582 (3.0903)	grad_norm 2.6205 (2.6903)	
[2022-01-25 17:34:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1140/1251]	eta 0:04:04 lr 0.000074	time 2.1492 (2.2060)	loss 3.5428 (3.0905)	grad_norm 2.7804 (2.6889)	
[2022-01-25 17:35:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1150/1251]	eta 0:03:42 lr 0.000074	time 2.1681 (2.2063)	loss 3.2760 (3.0898)	grad_norm 2.4181 (2.6869)	
[2022-01-25 17:35:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1160/1251]	eta 0:03:20 lr 0.000074	time 2.5188 (2.2071)	loss 3.6778 (3.0895)	grad_norm 2.4188 (2.6868)	
[2022-01-25 17:35:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1170/1251]	eta 0:02:58 lr 0.000074	time 2.1690 (2.2068)	loss 3.5574 (3.0894)	grad_norm 2.4144 (2.6873)	
[2022-01-25 17:36:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1180/1251]	eta 0:02:36 lr 0.000074	time 2.7375 (2.2073)	loss 3.3793 (3.0890)	grad_norm 3.1106 (2.6902)	
[2022-01-25 17:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1190/1251]	eta 0:02:14 lr 0.000074	time 1.7261 (2.2060)	loss 3.1221 (3.0887)	grad_norm 2.5255 (2.6932)	
[2022-01-25 17:36:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1200/1251]	eta 0:01:52 lr 0.000074	time 1.9514 (2.2051)	loss 2.8182 (3.0850)	grad_norm 2.5319 (2.6924)	
[2022-01-25 17:37:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1210/1251]	eta 0:01:30 lr 0.000074	time 2.6915 (2.2036)	loss 2.6709 (3.0846)	grad_norm 2.9633 (2.6944)	
[2022-01-25 17:37:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1220/1251]	eta 0:01:08 lr 0.000074	time 2.2368 (2.2028)	loss 3.7113 (3.0827)	grad_norm 2.6085 (2.6940)	
[2022-01-25 17:38:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1230/1251]	eta 0:00:46 lr 0.000074	time 2.2128 (2.2023)	loss 3.0740 (3.0837)	grad_norm 2.7997 (2.6944)	
[2022-01-25 17:38:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1240/1251]	eta 0:00:24 lr 0.000074	time 1.7314 (2.2038)	loss 3.2493 (3.0855)	grad_norm 5.1413 (2.6971)	
[2022-01-25 17:38:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [250/300][1250/1251]	eta 0:00:02 lr 0.000074	time 1.2945 (2.1990)	loss 3.0503 (3.0839)	grad_norm 2.3196 (2.6958)	
[2022-01-25 17:38:41 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 250 training takes 0:45:51
[2022-01-25 17:38:41 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_250 saving......
[2022-01-25 17:38:52 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_250 saved !!!
[2022-01-25 17:39:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.041 (16.041)	Loss 0.8562 (0.8562)	Acc@1 79.883 (79.883)	Acc@5 95.020 (95.020)	
[2022-01-25 17:39:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.576 (2.886)	Loss 0.8290 (0.8548)	Acc@1 80.859 (80.238)	Acc@5 95.703 (95.153)	
[2022-01-25 17:39:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.351 (2.284)	Loss 0.8806 (0.8587)	Acc@1 81.152 (80.092)	Acc@5 94.629 (95.075)	
[2022-01-25 17:39:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.266 (2.028)	Loss 0.8730 (0.8505)	Acc@1 77.539 (80.214)	Acc@5 95.410 (95.174)	
[2022-01-25 17:40:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.503 (1.959)	Loss 0.8248 (0.8463)	Acc@1 81.934 (80.223)	Acc@5 95.312 (95.248)	
[2022-01-25 17:40:20 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.338 Acc@5 95.218
[2022-01-25 17:40:20 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.3%
[2022-01-25 17:40:20 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.38%
[2022-01-25 17:40:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][0/1251]	eta 7:22:04 lr 0.000074	time 21.2027 (21.2027)	loss 3.3103 (3.3103)	grad_norm 2.6894 (2.6894)	
[2022-01-25 17:41:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][10/1251]	eta 1:21:01 lr 0.000074	time 1.8798 (3.9171)	loss 3.0537 (2.9840)	grad_norm 2.6449 (2.5564)	
[2022-01-25 17:41:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][20/1251]	eta 1:01:56 lr 0.000074	time 2.2149 (3.0189)	loss 3.1151 (3.0556)	grad_norm 2.4238 (2.5077)	
[2022-01-25 17:41:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][30/1251]	eta 0:55:12 lr 0.000074	time 1.7796 (2.7133)	loss 3.6380 (3.0520)	grad_norm 2.7692 (2.5303)	
[2022-01-25 17:42:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][40/1251]	eta 0:53:42 lr 0.000074	time 3.6356 (2.6607)	loss 3.4964 (3.0083)	grad_norm 2.4988 (2.5540)	
[2022-01-25 17:42:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][50/1251]	eta 0:51:53 lr 0.000074	time 2.6689 (2.5928)	loss 3.5542 (3.0369)	grad_norm 3.4561 (2.6220)	
[2022-01-25 17:42:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][60/1251]	eta 0:50:00 lr 0.000074	time 2.1047 (2.5197)	loss 2.7152 (3.0030)	grad_norm 2.6057 (2.6520)	
[2022-01-25 17:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][70/1251]	eta 0:48:47 lr 0.000074	time 2.1911 (2.4785)	loss 3.5020 (3.0452)	grad_norm 2.5526 (2.6479)	
[2022-01-25 17:43:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][80/1251]	eta 0:48:26 lr 0.000074	time 4.2008 (2.4819)	loss 2.5651 (3.0390)	grad_norm 2.6121 (2.6357)	
[2022-01-25 17:44:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][90/1251]	eta 0:47:31 lr 0.000074	time 1.7072 (2.4560)	loss 3.3098 (3.0195)	grad_norm 2.6197 (2.6300)	
[2022-01-25 17:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][100/1251]	eta 0:46:25 lr 0.000074	time 1.9591 (2.4203)	loss 2.8037 (3.0256)	grad_norm 2.6183 (2.6338)	
[2022-01-25 17:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][110/1251]	eta 0:45:24 lr 0.000074	time 1.9231 (2.3880)	loss 3.1207 (3.0386)	grad_norm 2.3170 (2.6282)	
[2022-01-25 17:45:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][120/1251]	eta 0:44:38 lr 0.000074	time 2.5396 (2.3687)	loss 3.5490 (3.0395)	grad_norm 2.6802 (2.6199)	
[2022-01-25 17:45:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][130/1251]	eta 0:44:04 lr 0.000073	time 3.0727 (2.3587)	loss 2.2222 (3.0437)	grad_norm 2.5731 (2.6216)	
[2022-01-25 17:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][140/1251]	eta 0:43:29 lr 0.000073	time 2.1486 (2.3489)	loss 3.4090 (3.0361)	grad_norm 4.4999 (2.6472)	
[2022-01-25 17:46:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][150/1251]	eta 0:42:49 lr 0.000073	time 2.2731 (2.3335)	loss 2.6741 (3.0448)	grad_norm 2.5067 (2.6564)	
[2022-01-25 17:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][160/1251]	eta 0:42:10 lr 0.000073	time 2.6867 (2.3197)	loss 3.1495 (3.0356)	grad_norm 2.6288 (2.6636)	
[2022-01-25 17:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][170/1251]	eta 0:41:38 lr 0.000073	time 2.5365 (2.3111)	loss 3.2549 (3.0532)	grad_norm 2.5396 (2.6659)	
[2022-01-25 17:47:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][180/1251]	eta 0:41:03 lr 0.000073	time 2.2108 (2.2998)	loss 2.7472 (3.0596)	grad_norm 3.0632 (2.6632)	
[2022-01-25 17:47:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][190/1251]	eta 0:40:34 lr 0.000073	time 2.6104 (2.2948)	loss 2.9825 (3.0613)	grad_norm 2.3954 (2.6634)	
[2022-01-25 17:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][200/1251]	eta 0:39:57 lr 0.000073	time 2.2736 (2.2810)	loss 2.5825 (3.0674)	grad_norm 2.7771 (2.6643)	
[2022-01-25 17:48:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][210/1251]	eta 0:39:21 lr 0.000073	time 2.3116 (2.2689)	loss 2.0045 (3.0579)	grad_norm 3.6637 (2.6672)	
[2022-01-25 17:48:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][220/1251]	eta 0:38:56 lr 0.000073	time 2.2606 (2.2666)	loss 2.6428 (3.0558)	grad_norm 2.6846 (2.6789)	
[2022-01-25 17:49:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][230/1251]	eta 0:38:30 lr 0.000073	time 1.9355 (2.2629)	loss 3.0827 (3.0653)	grad_norm 3.1952 (2.6803)	
[2022-01-25 17:49:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][240/1251]	eta 0:38:06 lr 0.000073	time 1.7201 (2.2615)	loss 2.9195 (3.0508)	grad_norm 2.3725 (2.6786)	
[2022-01-25 17:49:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][250/1251]	eta 0:37:56 lr 0.000073	time 3.5102 (2.2741)	loss 2.2954 (3.0432)	grad_norm 2.2865 (2.6829)	
[2022-01-25 17:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][260/1251]	eta 0:37:37 lr 0.000073	time 1.9118 (2.2785)	loss 2.1753 (3.0498)	grad_norm 2.4889 (2.6821)	
[2022-01-25 17:50:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][270/1251]	eta 0:37:06 lr 0.000073	time 1.5700 (2.2696)	loss 3.5015 (3.0572)	grad_norm 2.1790 (2.6772)	
[2022-01-25 17:50:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][280/1251]	eta 0:36:33 lr 0.000073	time 2.0879 (2.2593)	loss 2.6775 (3.0588)	grad_norm 2.1974 (2.6755)	
[2022-01-25 17:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][290/1251]	eta 0:36:02 lr 0.000073	time 2.0173 (2.2503)	loss 3.1846 (3.0557)	grad_norm 2.5412 (2.6736)	
[2022-01-25 17:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][300/1251]	eta 0:35:36 lr 0.000073	time 1.8902 (2.2461)	loss 3.3002 (3.0584)	grad_norm 2.7861 (2.6737)	
[2022-01-25 17:51:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][310/1251]	eta 0:35:10 lr 0.000073	time 2.0969 (2.2427)	loss 3.6193 (3.0543)	grad_norm 2.6940 (2.6783)	
[2022-01-25 17:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][320/1251]	eta 0:34:45 lr 0.000073	time 1.9604 (2.2404)	loss 2.7357 (3.0580)	grad_norm 2.7594 (2.6873)	
[2022-01-25 17:52:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][330/1251]	eta 0:34:22 lr 0.000073	time 1.9271 (2.2393)	loss 3.3783 (3.0604)	grad_norm 2.6512 (2.6861)	
[2022-01-25 17:53:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][340/1251]	eta 0:34:03 lr 0.000073	time 2.4557 (2.2429)	loss 3.9619 (3.0541)	grad_norm 2.5341 (2.6867)	
[2022-01-25 17:53:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][350/1251]	eta 0:33:39 lr 0.000073	time 1.9268 (2.2417)	loss 3.7318 (3.0583)	grad_norm 2.7046 (2.6890)	
[2022-01-25 17:53:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][360/1251]	eta 0:33:17 lr 0.000073	time 2.1437 (2.2417)	loss 3.5779 (3.0646)	grad_norm 2.5742 (2.6900)	
[2022-01-25 17:54:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][370/1251]	eta 0:32:50 lr 0.000073	time 1.5797 (2.2366)	loss 3.5318 (3.0641)	grad_norm 2.4510 (2.6904)	
[2022-01-25 17:54:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][380/1251]	eta 0:32:28 lr 0.000073	time 2.9061 (2.2366)	loss 2.5310 (3.0611)	grad_norm 2.6391 (2.6954)	
[2022-01-25 17:54:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][390/1251]	eta 0:32:01 lr 0.000073	time 1.6453 (2.2316)	loss 3.0761 (3.0603)	grad_norm 2.6630 (2.7016)	
[2022-01-25 17:55:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][400/1251]	eta 0:31:36 lr 0.000073	time 1.9488 (2.2286)	loss 3.2026 (3.0646)	grad_norm 2.7037 (2.7010)	
[2022-01-25 17:55:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][410/1251]	eta 0:31:12 lr 0.000073	time 1.8629 (2.2270)	loss 3.0146 (3.0632)	grad_norm 2.6316 (2.6982)	
[2022-01-25 17:56:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][420/1251]	eta 0:30:54 lr 0.000073	time 2.8359 (2.2320)	loss 3.4991 (3.0720)	grad_norm 2.6307 (2.6992)	
[2022-01-25 17:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][430/1251]	eta 0:30:34 lr 0.000073	time 2.4158 (2.2346)	loss 2.8934 (3.0711)	grad_norm 2.6846 (2.7019)	
[2022-01-25 17:56:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][440/1251]	eta 0:30:12 lr 0.000073	time 1.8732 (2.2347)	loss 3.4464 (3.0745)	grad_norm 3.5453 (2.7027)	
[2022-01-25 17:57:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][450/1251]	eta 0:29:48 lr 0.000073	time 1.9046 (2.2327)	loss 2.3574 (3.0761)	grad_norm 2.5221 (2.7027)	
[2022-01-25 17:57:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][460/1251]	eta 0:29:21 lr 0.000073	time 1.8963 (2.2266)	loss 2.6495 (3.0766)	grad_norm 3.5593 (2.7092)	
[2022-01-25 17:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][470/1251]	eta 0:28:53 lr 0.000073	time 1.8596 (2.2197)	loss 3.4940 (3.0777)	grad_norm 3.0901 (2.7120)	
[2022-01-25 17:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][480/1251]	eta 0:28:30 lr 0.000073	time 2.0409 (2.2183)	loss 2.7662 (3.0765)	grad_norm 2.8298 (2.7132)	
[2022-01-25 17:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][490/1251]	eta 0:28:07 lr 0.000073	time 1.9020 (2.2180)	loss 3.3293 (3.0746)	grad_norm 2.8698 (2.7130)	
[2022-01-25 17:58:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][500/1251]	eta 0:27:45 lr 0.000073	time 2.3551 (2.2175)	loss 3.2478 (3.0707)	grad_norm 2.3733 (2.7132)	
[2022-01-25 17:59:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][510/1251]	eta 0:27:24 lr 0.000073	time 2.5142 (2.2196)	loss 3.3229 (3.0714)	grad_norm 2.3530 (2.7110)	
[2022-01-25 17:59:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][520/1251]	eta 0:27:03 lr 0.000073	time 2.4005 (2.2213)	loss 3.7807 (3.0737)	grad_norm 2.4955 (2.7128)	
[2022-01-25 17:59:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][530/1251]	eta 0:26:40 lr 0.000073	time 1.8593 (2.2193)	loss 3.5094 (3.0723)	grad_norm 2.3797 (2.7097)	
[2022-01-25 18:00:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][540/1251]	eta 0:26:18 lr 0.000073	time 2.8131 (2.2206)	loss 2.6778 (3.0736)	grad_norm 2.8729 (2.7137)	
[2022-01-25 18:00:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][550/1251]	eta 0:25:56 lr 0.000073	time 1.6840 (2.2209)	loss 3.4925 (3.0753)	grad_norm 2.7957 (2.7180)	
[2022-01-25 18:01:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][560/1251]	eta 0:25:33 lr 0.000073	time 1.6222 (2.2192)	loss 3.2435 (3.0724)	grad_norm 2.5944 (2.7207)	
[2022-01-25 18:01:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][570/1251]	eta 0:25:08 lr 0.000073	time 1.5741 (2.2152)	loss 2.9614 (3.0688)	grad_norm 2.7177 (2.7237)	
[2022-01-25 18:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][580/1251]	eta 0:24:45 lr 0.000073	time 2.5176 (2.2136)	loss 3.1380 (3.0670)	grad_norm 2.6919 (2.7229)	
[2022-01-25 18:02:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][590/1251]	eta 0:24:24 lr 0.000073	time 1.8813 (2.2155)	loss 2.4789 (3.0673)	grad_norm 2.6544 (2.7293)	
[2022-01-25 18:02:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][600/1251]	eta 0:24:02 lr 0.000073	time 1.9736 (2.2161)	loss 3.3713 (3.0691)	grad_norm 2.3956 (2.7280)	
[2022-01-25 18:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][610/1251]	eta 0:23:39 lr 0.000073	time 1.6165 (2.2149)	loss 3.0049 (3.0714)	grad_norm 2.1978 (2.7253)	
[2022-01-25 18:03:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][620/1251]	eta 0:23:16 lr 0.000072	time 2.2163 (2.2137)	loss 3.3325 (3.0667)	grad_norm 2.8047 (2.7244)	
[2022-01-25 18:03:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][630/1251]	eta 0:22:55 lr 0.000072	time 2.1702 (2.2149)	loss 3.2711 (3.0669)	grad_norm 3.0142 (2.7238)	
[2022-01-25 18:04:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][640/1251]	eta 0:22:33 lr 0.000072	time 2.5914 (2.2147)	loss 3.5937 (3.0635)	grad_norm 2.7703 (2.7234)	
[2022-01-25 18:04:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][650/1251]	eta 0:22:09 lr 0.000072	time 1.9192 (2.2126)	loss 3.6402 (3.0655)	grad_norm 2.5316 (2.7225)	
[2022-01-25 18:04:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][660/1251]	eta 0:21:47 lr 0.000072	time 1.9837 (2.2116)	loss 3.3489 (3.0653)	grad_norm 2.9372 (2.7231)	
[2022-01-25 18:05:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][670/1251]	eta 0:21:24 lr 0.000072	time 1.7588 (2.2114)	loss 3.6779 (3.0659)	grad_norm 2.7196 (2.7246)	
[2022-01-25 18:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][680/1251]	eta 0:21:02 lr 0.000072	time 2.3381 (2.2108)	loss 3.2911 (3.0659)	grad_norm 2.3102 (2.7228)	
[2022-01-25 18:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][690/1251]	eta 0:20:39 lr 0.000072	time 2.2492 (2.2094)	loss 2.6024 (3.0660)	grad_norm 2.8296 (2.7207)	
[2022-01-25 18:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][700/1251]	eta 0:20:16 lr 0.000072	time 1.9577 (2.2081)	loss 3.6278 (3.0660)	grad_norm 3.0546 (2.7202)	
[2022-01-25 18:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][710/1251]	eta 0:19:53 lr 0.000072	time 1.9309 (2.2064)	loss 3.4228 (3.0678)	grad_norm 2.9077 (2.7239)	
[2022-01-25 18:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][720/1251]	eta 0:19:31 lr 0.000072	time 2.5201 (2.2062)	loss 3.1903 (3.0669)	grad_norm 2.9443 (2.7230)	
[2022-01-25 18:07:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][730/1251]	eta 0:19:09 lr 0.000072	time 1.8207 (2.2056)	loss 3.5656 (3.0675)	grad_norm 2.4776 (2.7240)	
[2022-01-25 18:07:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][740/1251]	eta 0:18:46 lr 0.000072	time 2.0168 (2.2047)	loss 3.4719 (3.0709)	grad_norm 2.7961 (2.7292)	
[2022-01-25 18:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][750/1251]	eta 0:18:24 lr 0.000072	time 1.9247 (2.2054)	loss 2.2037 (3.0669)	grad_norm 2.3949 (2.7285)	
[2022-01-25 18:08:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][760/1251]	eta 0:18:03 lr 0.000072	time 3.1233 (2.2068)	loss 3.7677 (3.0700)	grad_norm 2.7306 (2.7264)	
[2022-01-25 18:08:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][770/1251]	eta 0:17:42 lr 0.000072	time 2.6210 (2.2091)	loss 2.7973 (3.0705)	grad_norm 2.6646 (2.7240)	
[2022-01-25 18:09:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][780/1251]	eta 0:17:19 lr 0.000072	time 1.5426 (2.2076)	loss 3.2714 (3.0686)	grad_norm 2.3818 (2.7255)	
[2022-01-25 18:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][790/1251]	eta 0:16:58 lr 0.000072	time 1.8436 (2.2083)	loss 2.7905 (3.0683)	grad_norm 2.4385 (2.7238)	
[2022-01-25 18:09:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][800/1251]	eta 0:16:35 lr 0.000072	time 1.5722 (2.2074)	loss 2.3420 (3.0711)	grad_norm 2.6958 (2.7227)	
[2022-01-25 18:10:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][810/1251]	eta 0:16:13 lr 0.000072	time 1.9192 (2.2076)	loss 2.8643 (3.0720)	grad_norm 2.4756 (2.7256)	
[2022-01-25 18:10:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][820/1251]	eta 0:15:50 lr 0.000072	time 1.7162 (2.2045)	loss 2.6396 (3.0751)	grad_norm 2.8892 (2.7297)	
[2022-01-25 18:10:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][830/1251]	eta 0:15:27 lr 0.000072	time 1.8957 (2.2035)	loss 3.5739 (3.0789)	grad_norm 2.3605 (2.7300)	
[2022-01-25 18:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][840/1251]	eta 0:15:05 lr 0.000072	time 2.0081 (2.2020)	loss 3.4041 (3.0753)	grad_norm 2.3671 (2.7289)	
[2022-01-25 18:11:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][850/1251]	eta 0:14:43 lr 0.000072	time 2.3115 (2.2026)	loss 3.4953 (3.0765)	grad_norm 2.3316 (2.7292)	
[2022-01-25 18:11:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][860/1251]	eta 0:14:21 lr 0.000072	time 2.1875 (2.2029)	loss 3.2768 (3.0743)	grad_norm 2.5347 (2.7290)	
[2022-01-25 18:12:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][870/1251]	eta 0:13:58 lr 0.000072	time 1.8690 (2.2019)	loss 3.3258 (3.0758)	grad_norm 3.2261 (2.7298)	
[2022-01-25 18:12:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][880/1251]	eta 0:13:37 lr 0.000072	time 2.2795 (2.2027)	loss 3.3101 (3.0735)	grad_norm 2.3964 (2.7306)	
[2022-01-25 18:13:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][890/1251]	eta 0:13:15 lr 0.000072	time 2.4224 (2.2027)	loss 3.4991 (3.0741)	grad_norm 3.4517 (2.7317)	
[2022-01-25 18:13:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][900/1251]	eta 0:12:53 lr 0.000072	time 2.8097 (2.2033)	loss 2.1260 (3.0747)	grad_norm 2.5616 (2.7317)	
[2022-01-25 18:13:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][910/1251]	eta 0:12:31 lr 0.000072	time 1.9882 (2.2031)	loss 2.2864 (3.0717)	grad_norm 3.0065 (2.7326)	
[2022-01-25 18:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][920/1251]	eta 0:12:09 lr 0.000072	time 1.9263 (2.2035)	loss 3.0529 (3.0710)	grad_norm 2.6687 (2.7304)	
[2022-01-25 18:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][930/1251]	eta 0:11:47 lr 0.000072	time 2.5309 (2.2044)	loss 3.0404 (3.0733)	grad_norm 2.4991 (2.7286)	
[2022-01-25 18:14:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][940/1251]	eta 0:11:25 lr 0.000072	time 2.1313 (2.2028)	loss 3.9722 (3.0728)	grad_norm 3.4880 (2.7284)	
[2022-01-25 18:15:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][950/1251]	eta 0:11:02 lr 0.000072	time 2.4099 (2.2005)	loss 3.5311 (3.0711)	grad_norm 2.3716 (2.7287)	
[2022-01-25 18:15:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][960/1251]	eta 0:10:39 lr 0.000072	time 1.7052 (2.1988)	loss 3.0747 (3.0702)	grad_norm 2.5468 (2.7289)	
[2022-01-25 18:15:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][970/1251]	eta 0:10:18 lr 0.000072	time 2.4490 (2.2006)	loss 3.6216 (3.0694)	grad_norm 2.5811 (2.7288)	
[2022-01-25 18:16:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][980/1251]	eta 0:09:56 lr 0.000072	time 2.2458 (2.2016)	loss 2.4868 (3.0688)	grad_norm 3.2623 (2.7290)	
[2022-01-25 18:16:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][990/1251]	eta 0:09:34 lr 0.000072	time 2.1740 (2.2029)	loss 3.7067 (3.0714)	grad_norm 2.8018 (2.7303)	
[2022-01-25 18:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1000/1251]	eta 0:09:12 lr 0.000072	time 1.4735 (2.2012)	loss 2.5148 (3.0702)	grad_norm 2.7267 (2.7317)	
[2022-01-25 18:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1010/1251]	eta 0:08:50 lr 0.000072	time 2.2704 (2.1995)	loss 2.2736 (3.0702)	grad_norm 2.4911 (2.7308)	
[2022-01-25 18:17:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1020/1251]	eta 0:08:27 lr 0.000072	time 2.2597 (2.1986)	loss 3.7817 (3.0690)	grad_norm 2.8262 (2.7306)	
[2022-01-25 18:18:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1030/1251]	eta 0:08:05 lr 0.000072	time 2.5917 (2.1981)	loss 3.5772 (3.0679)	grad_norm 2.6047 (2.7302)	
[2022-01-25 18:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1040/1251]	eta 0:07:43 lr 0.000072	time 1.8816 (2.1970)	loss 3.0258 (3.0693)	grad_norm 2.4863 (2.7292)	
[2022-01-25 18:18:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1050/1251]	eta 0:07:21 lr 0.000072	time 2.4350 (2.1976)	loss 3.3150 (3.0691)	grad_norm 2.3985 (2.7290)	
[2022-01-25 18:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1060/1251]	eta 0:06:59 lr 0.000072	time 1.8677 (2.1969)	loss 3.1049 (3.0725)	grad_norm 2.6895 (2.7293)	
[2022-01-25 18:19:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1070/1251]	eta 0:06:38 lr 0.000072	time 3.0765 (2.1994)	loss 2.2998 (3.0723)	grad_norm 2.4256 (2.7275)	
[2022-01-25 18:20:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1080/1251]	eta 0:06:16 lr 0.000072	time 2.0952 (2.2019)	loss 2.7975 (3.0719)	grad_norm 2.3636 (2.7273)	
[2022-01-25 18:20:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1090/1251]	eta 0:05:54 lr 0.000072	time 2.4885 (2.2025)	loss 3.2981 (3.0728)	grad_norm 2.6779 (2.7272)	
[2022-01-25 18:20:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1100/1251]	eta 0:05:32 lr 0.000072	time 2.1148 (2.2022)	loss 2.6346 (3.0735)	grad_norm 3.0824 (2.7276)	
[2022-01-25 18:21:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1110/1251]	eta 0:05:10 lr 0.000072	time 3.0959 (2.2015)	loss 3.2176 (3.0743)	grad_norm 2.7841 (2.7276)	
[2022-01-25 18:21:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1120/1251]	eta 0:04:48 lr 0.000071	time 1.8006 (2.1989)	loss 3.6200 (3.0755)	grad_norm 3.9472 (2.7320)	
[2022-01-25 18:21:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1130/1251]	eta 0:04:26 lr 0.000071	time 2.1515 (2.1985)	loss 2.9647 (3.0750)	grad_norm 2.8938 (2.7321)	
[2022-01-25 18:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1140/1251]	eta 0:04:04 lr 0.000071	time 2.5403 (2.1986)	loss 2.7127 (3.0746)	grad_norm 2.6242 (2.7337)	
[2022-01-25 18:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1150/1251]	eta 0:03:42 lr 0.000071	time 2.4505 (2.1991)	loss 3.2024 (3.0752)	grad_norm 2.8101 (2.7328)	
[2022-01-25 18:22:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1160/1251]	eta 0:03:20 lr 0.000071	time 1.5691 (2.1988)	loss 1.9178 (3.0732)	grad_norm 2.5503 (2.7316)	
[2022-01-25 18:23:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1170/1251]	eta 0:02:58 lr 0.000071	time 2.4892 (2.2001)	loss 3.4278 (3.0725)	grad_norm 2.3280 (2.7307)	
[2022-01-25 18:23:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1180/1251]	eta 0:02:36 lr 0.000071	time 2.6376 (2.1999)	loss 3.4271 (3.0692)	grad_norm 2.9007 (2.7312)	
[2022-01-25 18:23:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1190/1251]	eta 0:02:14 lr 0.000071	time 2.5221 (2.1983)	loss 3.1637 (3.0698)	grad_norm 2.7137 (2.7322)	
[2022-01-25 18:24:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1200/1251]	eta 0:01:52 lr 0.000071	time 2.2124 (2.1964)	loss 3.0059 (3.0699)	grad_norm 2.9619 (2.7321)	
[2022-01-25 18:24:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1210/1251]	eta 0:01:30 lr 0.000071	time 2.5716 (2.1956)	loss 2.9131 (3.0671)	grad_norm 2.8605 (2.7331)	
[2022-01-25 18:25:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1220/1251]	eta 0:01:08 lr 0.000071	time 1.9055 (2.1947)	loss 3.7702 (3.0684)	grad_norm 2.4848 (2.7324)	
[2022-01-25 18:25:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1230/1251]	eta 0:00:46 lr 0.000071	time 2.2038 (2.1949)	loss 2.5650 (3.0679)	grad_norm 2.4745 (2.7319)	
[2022-01-25 18:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1240/1251]	eta 0:00:24 lr 0.000071	time 1.7488 (2.1936)	loss 2.7295 (3.0667)	grad_norm 2.3253 (2.7327)	
[2022-01-25 18:25:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [251/300][1250/1251]	eta 0:00:02 lr 0.000071	time 1.1888 (2.1879)	loss 3.7419 (3.0659)	grad_norm 3.0234 (2.7329)	
[2022-01-25 18:25:58 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 251 training takes 0:45:37
[2022-01-25 18:26:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.919 (17.919)	Loss 0.8003 (0.8003)	Acc@1 79.492 (79.492)	Acc@5 95.801 (95.801)	
[2022-01-25 18:26:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.915 (3.551)	Loss 0.8680 (0.8414)	Acc@1 79.492 (80.229)	Acc@5 95.703 (95.250)	
[2022-01-25 18:26:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.619 (2.737)	Loss 0.8449 (0.8420)	Acc@1 80.664 (80.357)	Acc@5 95.410 (95.192)	
[2022-01-25 18:27:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.306 (2.413)	Loss 0.8645 (0.8458)	Acc@1 80.469 (80.255)	Acc@5 95.117 (95.171)	
[2022-01-25 18:27:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.634 (2.226)	Loss 0.8950 (0.8426)	Acc@1 79.688 (80.347)	Acc@5 94.922 (95.177)	
[2022-01-25 18:27:36 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.410 Acc@5 95.180
[2022-01-25 18:27:36 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.4%
[2022-01-25 18:27:36 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.41%
[2022-01-25 18:27:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][0/1251]	eta 7:36:02 lr 0.000071	time 21.8723 (21.8723)	loss 3.3761 (3.3761)	grad_norm 2.8983 (2.8983)	
[2022-01-25 18:28:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][10/1251]	eta 1:26:42 lr 0.000071	time 3.0213 (4.1922)	loss 3.3671 (2.9852)	grad_norm 2.2079 (2.5704)	
[2022-01-25 18:28:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][20/1251]	eta 1:04:28 lr 0.000071	time 1.2200 (3.1424)	loss 2.2887 (3.0027)	grad_norm 2.8244 (2.6060)	
[2022-01-25 18:29:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][30/1251]	eta 0:59:13 lr 0.000071	time 1.8250 (2.9103)	loss 2.6828 (3.0018)	grad_norm 2.9863 (2.7003)	
[2022-01-25 18:29:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][40/1251]	eta 0:55:54 lr 0.000071	time 3.9195 (2.7703)	loss 3.1102 (3.0333)	grad_norm 2.5701 (2.7119)	
[2022-01-25 18:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][50/1251]	eta 0:53:31 lr 0.000071	time 2.9011 (2.6742)	loss 2.5773 (2.9941)	grad_norm 2.6168 (2.7017)	
[2022-01-25 18:30:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][60/1251]	eta 0:51:41 lr 0.000071	time 1.7017 (2.6039)	loss 2.7986 (3.0062)	grad_norm 2.5339 (2.7051)	
[2022-01-25 18:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][70/1251]	eta 0:49:48 lr 0.000071	time 1.5973 (2.5305)	loss 3.7337 (2.9823)	grad_norm 2.8245 (2.7149)	
[2022-01-25 18:30:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][80/1251]	eta 0:48:20 lr 0.000071	time 2.1262 (2.4768)	loss 3.4881 (3.0268)	grad_norm 2.5800 (2.7101)	
[2022-01-25 18:31:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][90/1251]	eta 0:46:52 lr 0.000071	time 2.1595 (2.4221)	loss 3.3373 (3.0345)	grad_norm 2.8882 (2.7143)	
[2022-01-25 18:31:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][100/1251]	eta 0:45:58 lr 0.000071	time 1.9263 (2.3965)	loss 3.4802 (3.0584)	grad_norm 3.1407 (2.7207)	
[2022-01-25 18:31:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][110/1251]	eta 0:44:59 lr 0.000071	time 1.8353 (2.3658)	loss 2.1638 (3.0646)	grad_norm 3.0411 (2.7323)	
[2022-01-25 18:32:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][120/1251]	eta 0:44:27 lr 0.000071	time 2.5527 (2.3581)	loss 3.4235 (3.0787)	grad_norm 3.0441 (2.7355)	
[2022-01-25 18:32:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][130/1251]	eta 0:43:49 lr 0.000071	time 1.7086 (2.3456)	loss 2.6257 (3.0666)	grad_norm 3.1290 (2.7506)	
[2022-01-25 18:33:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][140/1251]	eta 0:43:23 lr 0.000071	time 1.8588 (2.3430)	loss 3.4296 (3.0625)	grad_norm 2.9957 (2.7428)	
[2022-01-25 18:33:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][150/1251]	eta 0:42:55 lr 0.000071	time 1.6746 (2.3396)	loss 3.5270 (3.0610)	grad_norm 2.7700 (2.7507)	
[2022-01-25 18:33:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][160/1251]	eta 0:42:18 lr 0.000071	time 2.3053 (2.3271)	loss 3.2437 (3.0588)	grad_norm 3.1953 (2.7581)	
[2022-01-25 18:34:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][170/1251]	eta 0:41:40 lr 0.000071	time 1.9017 (2.3133)	loss 3.1885 (3.0535)	grad_norm 3.0911 (2.7505)	
[2022-01-25 18:34:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][180/1251]	eta 0:41:11 lr 0.000071	time 2.0952 (2.3075)	loss 3.5273 (3.0695)	grad_norm 2.2892 (2.7488)	
[2022-01-25 18:34:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][190/1251]	eta 0:40:39 lr 0.000071	time 1.5876 (2.2992)	loss 3.6936 (3.0752)	grad_norm 2.7200 (2.7467)	
[2022-01-25 18:35:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][200/1251]	eta 0:40:11 lr 0.000071	time 2.0888 (2.2948)	loss 3.6002 (3.0781)	grad_norm 2.9325 (2.7473)	
[2022-01-25 18:35:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][210/1251]	eta 0:39:52 lr 0.000071	time 2.5320 (2.2984)	loss 3.5099 (3.0763)	grad_norm 2.5465 (2.7455)	
[2022-01-25 18:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][220/1251]	eta 0:39:31 lr 0.000071	time 2.0707 (2.3001)	loss 2.4305 (3.0771)	grad_norm 3.2236 (2.7494)	
[2022-01-25 18:36:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][230/1251]	eta 0:39:03 lr 0.000071	time 1.5165 (2.2953)	loss 3.2937 (3.0679)	grad_norm 2.7221 (2.7489)	
[2022-01-25 18:36:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][240/1251]	eta 0:38:30 lr 0.000071	time 1.5755 (2.2855)	loss 3.1181 (3.0637)	grad_norm 4.1922 (2.7601)	
[2022-01-25 18:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][250/1251]	eta 0:37:57 lr 0.000071	time 2.1505 (2.2749)	loss 3.0319 (3.0571)	grad_norm 2.4528 (2.7568)	
[2022-01-25 18:37:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][260/1251]	eta 0:37:27 lr 0.000071	time 2.0915 (2.2681)	loss 3.7104 (3.0607)	grad_norm 2.9419 (2.7527)	
[2022-01-25 18:37:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][270/1251]	eta 0:37:00 lr 0.000071	time 1.9318 (2.2640)	loss 3.3652 (3.0650)	grad_norm 2.3152 (2.7499)	
[2022-01-25 18:38:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][280/1251]	eta 0:36:38 lr 0.000071	time 2.6214 (2.2637)	loss 2.3123 (3.0663)	grad_norm 2.4766 (2.7464)	
[2022-01-25 18:38:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][290/1251]	eta 0:36:17 lr 0.000071	time 1.8040 (2.2663)	loss 2.5241 (3.0676)	grad_norm 2.9701 (2.7476)	
[2022-01-25 18:38:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][300/1251]	eta 0:35:51 lr 0.000071	time 1.9307 (2.2627)	loss 2.8970 (3.0722)	grad_norm 2.7432 (2.7485)	
[2022-01-25 18:39:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][310/1251]	eta 0:35:25 lr 0.000071	time 2.3146 (2.2591)	loss 3.3665 (3.0800)	grad_norm 2.6734 (2.7537)	
[2022-01-25 18:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][320/1251]	eta 0:35:02 lr 0.000071	time 3.1866 (2.2582)	loss 2.6225 (3.0854)	grad_norm 2.5488 (2.7466)	
[2022-01-25 18:40:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][330/1251]	eta 0:34:37 lr 0.000071	time 2.2440 (2.2559)	loss 2.1447 (3.0801)	grad_norm 2.5653 (2.7472)	
[2022-01-25 18:40:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][340/1251]	eta 0:34:10 lr 0.000071	time 1.9174 (2.2511)	loss 2.1896 (3.0826)	grad_norm 2.3576 (2.7456)	
[2022-01-25 18:40:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][350/1251]	eta 0:33:47 lr 0.000071	time 1.8480 (2.2505)	loss 2.6603 (3.0831)	grad_norm 3.4868 (2.7500)	
[2022-01-25 18:41:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][360/1251]	eta 0:33:22 lr 0.000071	time 2.6973 (2.2471)	loss 3.5817 (3.0812)	grad_norm 2.5618 (2.7560)	
[2022-01-25 18:41:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][370/1251]	eta 0:32:54 lr 0.000070	time 1.8378 (2.2409)	loss 3.3690 (3.0739)	grad_norm 2.4106 (2.7576)	
[2022-01-25 18:41:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][380/1251]	eta 0:32:27 lr 0.000070	time 2.6074 (2.2357)	loss 2.6234 (3.0735)	grad_norm 2.7047 (2.7567)	
[2022-01-25 18:42:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][390/1251]	eta 0:32:00 lr 0.000070	time 1.8528 (2.2304)	loss 3.7232 (3.0780)	grad_norm 2.8259 (2.7561)	
[2022-01-25 18:42:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][400/1251]	eta 0:31:35 lr 0.000070	time 2.1863 (2.2279)	loss 3.0997 (3.0812)	grad_norm 2.3540 (2.7539)	
[2022-01-25 18:42:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][410/1251]	eta 0:31:14 lr 0.000070	time 2.5974 (2.2286)	loss 2.2014 (3.0730)	grad_norm 2.8534 (2.7576)	
[2022-01-25 18:43:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][420/1251]	eta 0:30:51 lr 0.000070	time 2.9405 (2.2282)	loss 3.4504 (3.0757)	grad_norm 3.0190 (2.7544)	
[2022-01-25 18:43:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][430/1251]	eta 0:30:27 lr 0.000070	time 2.1253 (2.2261)	loss 2.0439 (3.0768)	grad_norm 2.7100 (2.7522)	
[2022-01-25 18:43:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][440/1251]	eta 0:30:03 lr 0.000070	time 2.1488 (2.2241)	loss 3.4461 (3.0795)	grad_norm 4.3755 (2.7537)	
[2022-01-25 18:44:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][450/1251]	eta 0:29:42 lr 0.000070	time 2.3677 (2.2250)	loss 3.1238 (3.0793)	grad_norm 2.5478 (2.7544)	
[2022-01-25 18:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][460/1251]	eta 0:29:22 lr 0.000070	time 3.3098 (2.2287)	loss 3.7154 (3.0778)	grad_norm 2.5977 (2.7560)	
[2022-01-25 18:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][470/1251]	eta 0:28:59 lr 0.000070	time 2.3259 (2.2271)	loss 3.3112 (3.0770)	grad_norm 2.4641 (2.7505)	
[2022-01-25 18:45:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][480/1251]	eta 0:28:36 lr 0.000070	time 1.9008 (2.2258)	loss 3.3176 (3.0748)	grad_norm 2.5371 (2.7485)	
[2022-01-25 18:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][490/1251]	eta 0:28:17 lr 0.000070	time 3.0784 (2.2307)	loss 3.5457 (3.0724)	grad_norm 2.7703 (2.7487)	
[2022-01-25 18:46:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][500/1251]	eta 0:27:54 lr 0.000070	time 2.4985 (2.2296)	loss 2.8621 (3.0741)	grad_norm 2.7233 (2.7554)	
[2022-01-25 18:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][510/1251]	eta 0:27:30 lr 0.000070	time 2.1747 (2.2278)	loss 3.5046 (3.0795)	grad_norm 3.1573 (2.7555)	
[2022-01-25 18:46:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][520/1251]	eta 0:27:05 lr 0.000070	time 1.9193 (2.2235)	loss 3.5321 (3.0840)	grad_norm 2.8384 (2.7537)	
[2022-01-25 18:47:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][530/1251]	eta 0:26:43 lr 0.000070	time 3.4054 (2.2245)	loss 2.8765 (3.0806)	grad_norm 2.9894 (2.7533)	
[2022-01-25 18:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][540/1251]	eta 0:26:21 lr 0.000070	time 2.1750 (2.2237)	loss 3.2859 (3.0752)	grad_norm 2.5778 (2.7513)	
[2022-01-25 18:48:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][550/1251]	eta 0:25:58 lr 0.000070	time 2.2039 (2.2235)	loss 3.5767 (3.0786)	grad_norm 3.9791 (2.7539)	
[2022-01-25 18:48:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][560/1251]	eta 0:25:34 lr 0.000070	time 1.7742 (2.2206)	loss 3.6657 (3.0777)	grad_norm 3.1571 (2.7547)	
[2022-01-25 18:48:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][570/1251]	eta 0:25:13 lr 0.000070	time 2.6978 (2.2218)	loss 2.4962 (3.0785)	grad_norm 3.3410 (2.7571)	
[2022-01-25 18:49:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][580/1251]	eta 0:24:49 lr 0.000070	time 2.1923 (2.2203)	loss 3.3621 (3.0801)	grad_norm 2.7350 (2.7562)	
[2022-01-25 18:49:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][590/1251]	eta 0:24:25 lr 0.000070	time 2.1771 (2.2171)	loss 2.7925 (3.0771)	grad_norm 2.8155 (2.7553)	
[2022-01-25 18:49:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][600/1251]	eta 0:24:02 lr 0.000070	time 2.2312 (2.2157)	loss 3.0451 (3.0780)	grad_norm 2.7985 (2.7559)	
[2022-01-25 18:50:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][610/1251]	eta 0:23:40 lr 0.000070	time 3.1286 (2.2155)	loss 2.8229 (3.0800)	grad_norm 3.6190 (2.7577)	
[2022-01-25 18:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][620/1251]	eta 0:23:16 lr 0.000070	time 1.9977 (2.2133)	loss 3.3287 (3.0775)	grad_norm 3.2094 (2.7610)	
[2022-01-25 18:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][630/1251]	eta 0:22:54 lr 0.000070	time 2.2236 (2.2130)	loss 3.4424 (3.0735)	grad_norm 2.5136 (2.7595)	
[2022-01-25 18:51:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][640/1251]	eta 0:22:31 lr 0.000070	time 1.6354 (2.2122)	loss 3.0963 (3.0768)	grad_norm 2.8439 (2.7575)	
[2022-01-25 18:51:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][650/1251]	eta 0:22:10 lr 0.000070	time 2.7814 (2.2133)	loss 3.4967 (3.0780)	grad_norm 2.6372 (2.7585)	
[2022-01-25 18:52:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][660/1251]	eta 0:21:49 lr 0.000070	time 2.9147 (2.2166)	loss 3.6778 (3.0759)	grad_norm 3.2425 (2.7602)	
[2022-01-25 18:52:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][670/1251]	eta 0:21:28 lr 0.000070	time 1.9485 (2.2180)	loss 3.0848 (3.0771)	grad_norm 2.7383 (2.7591)	
[2022-01-25 18:52:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][680/1251]	eta 0:21:06 lr 0.000070	time 2.2440 (2.2178)	loss 3.0856 (3.0759)	grad_norm 2.5826 (2.7579)	
[2022-01-25 18:53:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][690/1251]	eta 0:20:42 lr 0.000070	time 2.2854 (2.2148)	loss 2.4622 (3.0753)	grad_norm 2.3168 (2.7585)	
[2022-01-25 18:53:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][700/1251]	eta 0:20:19 lr 0.000070	time 2.5075 (2.2127)	loss 3.3809 (3.0734)	grad_norm 2.6588 (2.7587)	
[2022-01-25 18:53:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][710/1251]	eta 0:19:56 lr 0.000070	time 1.8842 (2.2117)	loss 3.0273 (3.0763)	grad_norm 2.9238 (2.7590)	
[2022-01-25 18:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][720/1251]	eta 0:19:33 lr 0.000070	time 2.2717 (2.2097)	loss 3.5105 (3.0780)	grad_norm 2.5509 (2.7562)	
[2022-01-25 18:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][730/1251]	eta 0:19:09 lr 0.000070	time 1.8605 (2.2069)	loss 2.5879 (3.0743)	grad_norm 2.6551 (2.7545)	
[2022-01-25 18:54:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][740/1251]	eta 0:18:47 lr 0.000070	time 2.4392 (2.2062)	loss 3.6825 (3.0756)	grad_norm 2.7483 (2.7571)	
[2022-01-25 18:55:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][750/1251]	eta 0:18:24 lr 0.000070	time 1.6087 (2.2045)	loss 3.3613 (3.0793)	grad_norm 2.7615 (2.7570)	
[2022-01-25 18:55:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][760/1251]	eta 0:18:01 lr 0.000070	time 2.0931 (2.2031)	loss 3.0023 (3.0763)	grad_norm 3.2445 (2.7590)	
[2022-01-25 18:55:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][770/1251]	eta 0:17:41 lr 0.000070	time 2.7804 (2.2065)	loss 3.4734 (3.0793)	grad_norm 2.3220 (2.7609)	
[2022-01-25 18:56:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][780/1251]	eta 0:17:19 lr 0.000070	time 2.9696 (2.2063)	loss 3.3451 (3.0829)	grad_norm 2.4309 (2.7630)	
[2022-01-25 18:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][790/1251]	eta 0:16:57 lr 0.000070	time 2.0973 (2.2061)	loss 3.0332 (3.0824)	grad_norm 2.7103 (2.7627)	
[2022-01-25 18:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][800/1251]	eta 0:16:34 lr 0.000070	time 2.4531 (2.2061)	loss 2.3921 (3.0832)	grad_norm 2.3140 (2.7624)	
[2022-01-25 18:57:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][810/1251]	eta 0:16:13 lr 0.000070	time 1.8953 (2.2067)	loss 3.5036 (3.0852)	grad_norm 2.6692 (2.7621)	
[2022-01-25 18:57:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][820/1251]	eta 0:15:51 lr 0.000070	time 3.0221 (2.2069)	loss 2.8918 (3.0841)	grad_norm 2.7252 (2.7615)	
[2022-01-25 18:58:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][830/1251]	eta 0:15:28 lr 0.000070	time 1.6537 (2.2055)	loss 2.8724 (3.0853)	grad_norm 2.5595 (2.7598)	
[2022-01-25 18:58:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][840/1251]	eta 0:15:06 lr 0.000070	time 2.5264 (2.2048)	loss 3.6354 (3.0872)	grad_norm 2.4012 (2.7593)	
[2022-01-25 18:58:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][850/1251]	eta 0:14:43 lr 0.000070	time 1.4850 (2.2035)	loss 3.7367 (3.0880)	grad_norm 2.8782 (2.7593)	
[2022-01-25 18:59:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][860/1251]	eta 0:14:21 lr 0.000070	time 2.5345 (2.2037)	loss 2.8052 (3.0904)	grad_norm 2.4655 (2.7580)	
[2022-01-25 18:59:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][870/1251]	eta 0:13:59 lr 0.000070	time 2.4942 (2.2047)	loss 3.2189 (3.0911)	grad_norm 2.9272 (2.7566)	
[2022-01-25 18:59:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][880/1251]	eta 0:13:38 lr 0.000069	time 2.5233 (2.2056)	loss 3.5063 (3.0900)	grad_norm 2.5201 (2.7540)	
[2022-01-25 19:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][890/1251]	eta 0:13:15 lr 0.000069	time 1.8420 (2.2047)	loss 2.3825 (3.0874)	grad_norm 2.6830 (2.7539)	
[2022-01-25 19:00:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][900/1251]	eta 0:12:53 lr 0.000069	time 2.7197 (2.2041)	loss 3.2370 (3.0900)	grad_norm 2.5544 (2.7529)	
[2022-01-25 19:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][910/1251]	eta 0:12:30 lr 0.000069	time 1.9242 (2.2020)	loss 3.0196 (3.0898)	grad_norm 2.4643 (2.7513)	
[2022-01-25 19:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][920/1251]	eta 0:12:08 lr 0.000069	time 1.8460 (2.2009)	loss 3.2590 (3.0911)	grad_norm 2.5471 (2.7497)	
[2022-01-25 19:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][930/1251]	eta 0:11:46 lr 0.000069	time 2.0656 (2.2008)	loss 3.6921 (3.0902)	grad_norm 2.9970 (2.7492)	
[2022-01-25 19:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][940/1251]	eta 0:11:24 lr 0.000069	time 2.2811 (2.2007)	loss 3.1330 (3.0901)	grad_norm 2.5653 (2.7486)	
[2022-01-25 19:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][950/1251]	eta 0:11:02 lr 0.000069	time 2.2053 (2.2012)	loss 2.9254 (3.0899)	grad_norm 2.5686 (2.7475)	
[2022-01-25 19:02:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][960/1251]	eta 0:10:40 lr 0.000069	time 2.3406 (2.2004)	loss 3.0919 (3.0901)	grad_norm 2.6154 (2.7463)	
[2022-01-25 19:03:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][970/1251]	eta 0:10:18 lr 0.000069	time 2.2140 (2.1994)	loss 2.8373 (3.0906)	grad_norm 2.8058 (2.7455)	
[2022-01-25 19:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][980/1251]	eta 0:09:55 lr 0.000069	time 2.2566 (2.1977)	loss 3.7495 (3.0919)	grad_norm 2.4637 (2.7441)	
[2022-01-25 19:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][990/1251]	eta 0:09:33 lr 0.000069	time 2.7629 (2.1986)	loss 3.5659 (3.0906)	grad_norm 2.8230 (2.7426)	
[2022-01-25 19:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1000/1251]	eta 0:09:11 lr 0.000069	time 2.2821 (2.1988)	loss 2.6508 (3.0896)	grad_norm 2.2753 (2.7410)	
[2022-01-25 19:04:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1010/1251]	eta 0:08:50 lr 0.000069	time 3.0232 (2.2003)	loss 3.3207 (3.0883)	grad_norm 2.8921 (2.7399)	
[2022-01-25 19:05:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1020/1251]	eta 0:08:28 lr 0.000069	time 2.1891 (2.2009)	loss 3.4235 (3.0898)	grad_norm 2.7406 (2.7398)	
[2022-01-25 19:05:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1030/1251]	eta 0:08:06 lr 0.000069	time 2.3675 (2.2005)	loss 3.4152 (3.0908)	grad_norm 2.4313 (2.7398)	
[2022-01-25 19:05:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1040/1251]	eta 0:07:44 lr 0.000069	time 2.1863 (2.2001)	loss 3.3070 (3.0902)	grad_norm 2.9788 (2.7400)	
[2022-01-25 19:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1050/1251]	eta 0:07:21 lr 0.000069	time 2.0990 (2.1983)	loss 2.7943 (3.0910)	grad_norm 3.0427 (2.7409)	
[2022-01-25 19:06:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1060/1251]	eta 0:06:59 lr 0.000069	time 2.1974 (2.1960)	loss 3.6256 (3.0894)	grad_norm 3.0987 (2.7412)	
[2022-01-25 19:06:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1070/1251]	eta 0:06:37 lr 0.000069	time 1.9518 (2.1946)	loss 3.0321 (3.0920)	grad_norm 2.4556 (2.7416)	
[2022-01-25 19:07:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1080/1251]	eta 0:06:15 lr 0.000069	time 1.9830 (2.1954)	loss 2.3478 (3.0919)	grad_norm 2.8932 (2.7416)	
[2022-01-25 19:07:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1090/1251]	eta 0:05:53 lr 0.000069	time 2.1099 (2.1971)	loss 2.9664 (3.0941)	grad_norm 2.5737 (2.7409)	
[2022-01-25 19:07:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1100/1251]	eta 0:05:32 lr 0.000069	time 3.7382 (2.1997)	loss 2.3361 (3.0936)	grad_norm 2.3423 (2.7401)	
[2022-01-25 19:08:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1110/1251]	eta 0:05:10 lr 0.000069	time 2.0947 (2.2011)	loss 2.6878 (3.0915)	grad_norm 2.9054 (2.7408)	
[2022-01-25 19:08:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1120/1251]	eta 0:04:48 lr 0.000069	time 1.6187 (2.2005)	loss 2.7664 (3.0911)	grad_norm 2.8873 (2.7416)	
[2022-01-25 19:09:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1130/1251]	eta 0:04:26 lr 0.000069	time 2.0427 (2.1997)	loss 3.4053 (3.0912)	grad_norm 2.8378 (2.7414)	
[2022-01-25 19:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1140/1251]	eta 0:04:04 lr 0.000069	time 3.3820 (2.1999)	loss 3.4001 (3.0915)	grad_norm 2.5639 (2.7416)	
[2022-01-25 19:09:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1150/1251]	eta 0:03:42 lr 0.000069	time 2.0891 (2.1991)	loss 3.4775 (3.0920)	grad_norm 2.9164 (2.7415)	
[2022-01-25 19:10:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1160/1251]	eta 0:03:20 lr 0.000069	time 1.7218 (2.1990)	loss 3.1612 (3.0914)	grad_norm 2.5314 (2.7404)	
[2022-01-25 19:10:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1170/1251]	eta 0:02:58 lr 0.000069	time 2.1067 (2.1991)	loss 2.8150 (3.0912)	grad_norm 2.5851 (2.7415)	
[2022-01-25 19:10:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1180/1251]	eta 0:02:36 lr 0.000069	time 3.6624 (2.2005)	loss 2.7623 (3.0908)	grad_norm 3.0995 (2.7465)	
[2022-01-25 19:11:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1190/1251]	eta 0:02:14 lr 0.000069	time 2.2337 (2.1999)	loss 2.7243 (3.0893)	grad_norm 2.5431 (2.7500)	
[2022-01-25 19:11:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1200/1251]	eta 0:01:52 lr 0.000069	time 1.8623 (2.1997)	loss 2.8583 (3.0898)	grad_norm 2.7974 (2.7510)	
[2022-01-25 19:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1210/1251]	eta 0:01:30 lr 0.000069	time 2.2494 (2.1993)	loss 2.2038 (3.0862)	grad_norm 2.8635 (2.7510)	
[2022-01-25 19:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1220/1251]	eta 0:01:08 lr 0.000069	time 3.0780 (2.1993)	loss 2.1510 (3.0852)	grad_norm 2.6476 (2.7498)	
[2022-01-25 19:12:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1230/1251]	eta 0:00:46 lr 0.000069	time 2.5452 (2.1985)	loss 3.2114 (3.0857)	grad_norm 3.2390 (2.7503)	
[2022-01-25 19:13:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1240/1251]	eta 0:00:24 lr 0.000069	time 1.3348 (2.1956)	loss 3.0522 (3.0852)	grad_norm 3.0220 (2.7501)	
[2022-01-25 19:13:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [252/300][1250/1251]	eta 0:00:02 lr 0.000069	time 1.1747 (2.1903)	loss 3.6735 (3.0869)	grad_norm 2.7134 (2.7498)	
[2022-01-25 19:13:17 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 252 training takes 0:45:40
[2022-01-25 19:13:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.975 (18.975)	Loss 0.7688 (0.7688)	Acc@1 82.520 (82.520)	Acc@5 96.484 (96.484)	
[2022-01-25 19:13:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.496 (3.226)	Loss 0.8804 (0.8464)	Acc@1 79.688 (80.060)	Acc@5 94.727 (95.357)	
[2022-01-25 19:14:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.981 (2.630)	Loss 0.9027 (0.8399)	Acc@1 78.809 (80.199)	Acc@5 93.555 (95.322)	
[2022-01-25 19:14:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.612 (2.280)	Loss 0.7859 (0.8362)	Acc@1 81.641 (80.491)	Acc@5 95.898 (95.300)	
[2022-01-25 19:14:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.185 (2.217)	Loss 0.8245 (0.8417)	Acc@1 81.641 (80.331)	Acc@5 95.605 (95.255)	
[2022-01-25 19:14:54 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.410 Acc@5 95.276
[2022-01-25 19:14:54 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.4%
[2022-01-25 19:14:54 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.41%
[2022-01-25 19:15:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][0/1251]	eta 7:34:40 lr 0.000069	time 21.8071 (21.8071)	loss 3.7644 (3.7644)	grad_norm 3.0354 (3.0354)	
[2022-01-25 19:15:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][10/1251]	eta 1:26:04 lr 0.000069	time 1.6353 (4.1616)	loss 3.1139 (2.9195)	grad_norm 2.6635 (2.6827)	
[2022-01-25 19:16:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][20/1251]	eta 1:06:01 lr 0.000069	time 1.6049 (3.2177)	loss 3.6098 (2.9919)	grad_norm 2.6035 (2.7036)	
[2022-01-25 19:16:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][30/1251]	eta 0:59:17 lr 0.000069	time 2.0826 (2.9135)	loss 3.6321 (3.0997)	grad_norm 3.8988 (2.6769)	
[2022-01-25 19:16:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][40/1251]	eta 0:56:15 lr 0.000069	time 3.6146 (2.7871)	loss 2.7783 (3.0482)	grad_norm 2.4736 (2.7080)	
[2022-01-25 19:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][50/1251]	eta 0:53:58 lr 0.000069	time 2.1734 (2.6965)	loss 3.7836 (3.0307)	grad_norm 2.9020 (2.7090)	
[2022-01-25 19:17:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][60/1251]	eta 0:52:29 lr 0.000069	time 2.4096 (2.6442)	loss 3.4872 (3.0657)	grad_norm 2.8739 (2.7057)	
[2022-01-25 19:17:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][70/1251]	eta 0:50:40 lr 0.000069	time 1.8470 (2.5749)	loss 2.5268 (3.0585)	grad_norm 2.6637 (2.7130)	
[2022-01-25 19:18:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][80/1251]	eta 0:49:23 lr 0.000069	time 2.9353 (2.5304)	loss 3.0554 (3.0373)	grad_norm 2.5361 (2.7021)	
[2022-01-25 19:18:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][90/1251]	eta 0:47:34 lr 0.000069	time 1.6100 (2.4589)	loss 2.2266 (3.0443)	grad_norm 2.5386 (2.6856)	
[2022-01-25 19:18:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][100/1251]	eta 0:46:20 lr 0.000069	time 2.1877 (2.4157)	loss 3.5131 (3.0280)	grad_norm 2.2853 (2.6775)	
[2022-01-25 19:19:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][110/1251]	eta 0:45:25 lr 0.000069	time 1.9490 (2.3883)	loss 3.3580 (3.0287)	grad_norm 2.4144 (2.6698)	
[2022-01-25 19:19:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][120/1251]	eta 0:44:40 lr 0.000069	time 2.4776 (2.3700)	loss 2.9891 (3.0189)	grad_norm 2.6635 (2.6743)	
[2022-01-25 19:20:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][130/1251]	eta 0:44:06 lr 0.000069	time 2.5341 (2.3609)	loss 3.6164 (3.0275)	grad_norm 3.0934 (2.6839)	
[2022-01-25 19:20:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][140/1251]	eta 0:43:34 lr 0.000068	time 1.6226 (2.3535)	loss 3.2252 (3.0333)	grad_norm 2.6506 (2.6983)	
[2022-01-25 19:20:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][150/1251]	eta 0:43:02 lr 0.000068	time 2.5718 (2.3451)	loss 2.1181 (3.0326)	grad_norm 3.0123 (2.7020)	
[2022-01-25 19:21:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][160/1251]	eta 0:42:34 lr 0.000068	time 2.4134 (2.3411)	loss 3.3334 (3.0402)	grad_norm 2.4684 (2.7027)	
[2022-01-25 19:21:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][170/1251]	eta 0:42:08 lr 0.000068	time 1.8729 (2.3392)	loss 3.6705 (3.0392)	grad_norm 2.4558 (2.7008)	
[2022-01-25 19:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][180/1251]	eta 0:41:38 lr 0.000068	time 1.8129 (2.3329)	loss 3.1517 (3.0401)	grad_norm 2.2583 (2.6861)	
[2022-01-25 19:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][190/1251]	eta 0:41:05 lr 0.000068	time 2.5554 (2.3237)	loss 3.1424 (3.0531)	grad_norm 2.5067 (2.6863)	
[2022-01-25 19:22:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][200/1251]	eta 0:40:32 lr 0.000068	time 2.7963 (2.3148)	loss 2.1062 (3.0464)	grad_norm 2.5748 (2.6841)	
[2022-01-25 19:23:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][210/1251]	eta 0:40:05 lr 0.000068	time 1.8648 (2.3104)	loss 3.2001 (3.0506)	grad_norm 2.7104 (2.6853)	
[2022-01-25 19:23:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][220/1251]	eta 0:39:29 lr 0.000068	time 1.8038 (2.2979)	loss 2.2019 (3.0537)	grad_norm 2.6826 (2.6794)	
[2022-01-25 19:23:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][230/1251]	eta 0:38:59 lr 0.000068	time 2.5320 (2.2915)	loss 3.5566 (3.0546)	grad_norm 2.8983 (2.6779)	
[2022-01-25 19:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][240/1251]	eta 0:38:36 lr 0.000068	time 3.1264 (2.2910)	loss 3.5312 (3.0636)	grad_norm 2.2730 (2.6729)	
[2022-01-25 19:24:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][250/1251]	eta 0:38:07 lr 0.000068	time 1.7809 (2.2852)	loss 3.1681 (3.0528)	grad_norm 2.3699 (2.6774)	
[2022-01-25 19:24:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][260/1251]	eta 0:37:42 lr 0.000068	time 2.6111 (2.2830)	loss 3.6404 (3.0587)	grad_norm 2.7059 (2.6819)	
[2022-01-25 19:25:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][270/1251]	eta 0:37:12 lr 0.000068	time 2.1923 (2.2754)	loss 3.4940 (3.0658)	grad_norm 2.5115 (2.6805)	
[2022-01-25 19:25:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][280/1251]	eta 0:36:44 lr 0.000068	time 2.5483 (2.2706)	loss 3.1482 (3.0619)	grad_norm 2.6989 (2.6769)	
[2022-01-25 19:25:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][290/1251]	eta 0:36:18 lr 0.000068	time 2.5957 (2.2672)	loss 3.1716 (3.0641)	grad_norm 3.0232 (2.6843)	
[2022-01-25 19:26:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][300/1251]	eta 0:35:57 lr 0.000068	time 2.9680 (2.2684)	loss 3.4504 (3.0670)	grad_norm 2.7697 (2.6877)	
[2022-01-25 19:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][310/1251]	eta 0:35:31 lr 0.000068	time 1.5882 (2.2654)	loss 3.3932 (3.0648)	grad_norm 2.5858 (2.6909)	
[2022-01-25 19:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][320/1251]	eta 0:35:05 lr 0.000068	time 2.7905 (2.2621)	loss 3.3476 (3.0653)	grad_norm 2.7444 (2.6895)	
[2022-01-25 19:27:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][330/1251]	eta 0:34:35 lr 0.000068	time 1.8320 (2.2535)	loss 2.8324 (3.0577)	grad_norm 4.0518 (2.6934)	
[2022-01-25 19:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][340/1251]	eta 0:34:09 lr 0.000068	time 1.8641 (2.2497)	loss 3.8103 (3.0620)	grad_norm 2.7315 (2.6944)	
[2022-01-25 19:28:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][350/1251]	eta 0:33:47 lr 0.000068	time 2.1754 (2.2507)	loss 2.0044 (3.0593)	grad_norm 3.0281 (2.6934)	
[2022-01-25 19:28:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][360/1251]	eta 0:33:20 lr 0.000068	time 2.2706 (2.2450)	loss 3.2044 (3.0686)	grad_norm 2.8748 (2.6962)	
[2022-01-25 19:28:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][370/1251]	eta 0:32:56 lr 0.000068	time 1.8602 (2.2437)	loss 2.0885 (3.0734)	grad_norm 3.9536 (2.7014)	
[2022-01-25 19:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][380/1251]	eta 0:32:32 lr 0.000068	time 1.8818 (2.2412)	loss 2.4296 (3.0701)	grad_norm 2.5672 (2.6994)	
[2022-01-25 19:29:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][390/1251]	eta 0:32:09 lr 0.000068	time 1.6681 (2.2414)	loss 2.9724 (3.0676)	grad_norm 2.4829 (2.7033)	
[2022-01-25 19:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][400/1251]	eta 0:31:45 lr 0.000068	time 2.5487 (2.2392)	loss 3.2596 (3.0660)	grad_norm 2.9080 (2.7054)	
[2022-01-25 19:30:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][410/1251]	eta 0:31:21 lr 0.000068	time 1.9222 (2.2376)	loss 3.8561 (3.0710)	grad_norm 3.3976 (2.7125)	
[2022-01-25 19:30:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][420/1251]	eta 0:31:00 lr 0.000068	time 2.1110 (2.2388)	loss 2.4580 (3.0690)	grad_norm 2.6215 (2.7147)	
[2022-01-25 19:31:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][430/1251]	eta 0:30:40 lr 0.000068	time 1.9491 (2.2414)	loss 2.3687 (3.0677)	grad_norm 2.8422 (2.7181)	
[2022-01-25 19:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][440/1251]	eta 0:30:17 lr 0.000068	time 2.1292 (2.2405)	loss 3.6610 (3.0696)	grad_norm 2.3091 (2.7239)	
[2022-01-25 19:31:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][450/1251]	eta 0:29:55 lr 0.000068	time 3.0407 (2.2413)	loss 3.8980 (3.0722)	grad_norm 3.1088 (2.7260)	
[2022-01-25 19:32:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][460/1251]	eta 0:29:28 lr 0.000068	time 1.9546 (2.2357)	loss 3.3357 (3.0756)	grad_norm 2.6878 (2.7230)	
[2022-01-25 19:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][470/1251]	eta 0:29:04 lr 0.000068	time 2.2581 (2.2331)	loss 3.0207 (3.0792)	grad_norm 2.6999 (2.7267)	
[2022-01-25 19:32:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][480/1251]	eta 0:28:38 lr 0.000068	time 1.5677 (2.2286)	loss 3.4069 (3.0769)	grad_norm 2.3310 (2.7239)	
[2022-01-25 19:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][490/1251]	eta 0:28:18 lr 0.000068	time 3.5614 (2.2314)	loss 2.4202 (3.0807)	grad_norm 2.4314 (2.7227)	
[2022-01-25 19:33:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][500/1251]	eta 0:27:54 lr 0.000068	time 1.6644 (2.2300)	loss 3.6746 (3.0802)	grad_norm 2.4143 (2.7214)	
[2022-01-25 19:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][510/1251]	eta 0:27:30 lr 0.000068	time 1.8243 (2.2274)	loss 3.3530 (3.0819)	grad_norm 2.7373 (2.7215)	
[2022-01-25 19:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][520/1251]	eta 0:27:06 lr 0.000068	time 2.1088 (2.2253)	loss 3.1586 (3.0851)	grad_norm 2.6628 (2.7216)	
[2022-01-25 19:34:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][530/1251]	eta 0:26:44 lr 0.000068	time 3.2486 (2.2254)	loss 3.6690 (3.0809)	grad_norm 3.1390 (2.7215)	
[2022-01-25 19:34:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][540/1251]	eta 0:26:22 lr 0.000068	time 2.5249 (2.2254)	loss 3.0590 (3.0778)	grad_norm 2.8240 (2.7255)	
[2022-01-25 19:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][550/1251]	eta 0:25:59 lr 0.000068	time 2.1083 (2.2249)	loss 3.1271 (3.0853)	grad_norm 3.1655 (2.7306)	
[2022-01-25 19:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][560/1251]	eta 0:25:36 lr 0.000068	time 2.2986 (2.2238)	loss 3.4013 (3.0870)	grad_norm 2.8965 (2.7312)	
[2022-01-25 19:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][570/1251]	eta 0:25:14 lr 0.000068	time 2.7037 (2.2240)	loss 3.4216 (3.0869)	grad_norm 3.2262 (2.7315)	
[2022-01-25 19:36:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][580/1251]	eta 0:24:50 lr 0.000068	time 1.5979 (2.2218)	loss 3.6129 (3.0914)	grad_norm 2.5985 (2.7330)	
[2022-01-25 19:36:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][590/1251]	eta 0:24:27 lr 0.000068	time 2.2057 (2.2206)	loss 3.3990 (3.0925)	grad_norm 3.3433 (2.7383)	
[2022-01-25 19:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][600/1251]	eta 0:24:05 lr 0.000068	time 2.6308 (2.2205)	loss 3.3805 (3.0929)	grad_norm 2.4676 (2.7373)	
[2022-01-25 19:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][610/1251]	eta 0:23:43 lr 0.000068	time 2.3284 (2.2206)	loss 3.6413 (3.0927)	grad_norm 2.3935 (2.7372)	
[2022-01-25 19:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][620/1251]	eta 0:23:20 lr 0.000068	time 1.8735 (2.2195)	loss 3.5466 (3.0932)	grad_norm 3.0997 (2.7380)	
[2022-01-25 19:38:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][630/1251]	eta 0:22:56 lr 0.000068	time 1.9889 (2.2174)	loss 3.3172 (3.0931)	grad_norm 2.4917 (2.7410)	
[2022-01-25 19:38:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][640/1251]	eta 0:22:33 lr 0.000068	time 2.3673 (2.2158)	loss 3.3394 (3.0955)	grad_norm 3.1597 (2.7416)	
[2022-01-25 19:38:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][650/1251]	eta 0:22:10 lr 0.000067	time 1.9097 (2.2141)	loss 3.2717 (3.0930)	grad_norm 2.4754 (2.7484)	
[2022-01-25 19:39:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][660/1251]	eta 0:21:47 lr 0.000067	time 1.8986 (2.2127)	loss 3.3571 (3.0947)	grad_norm 2.4477 (2.7521)	
[2022-01-25 19:39:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][670/1251]	eta 0:21:25 lr 0.000067	time 1.7314 (2.2123)	loss 3.0056 (3.0963)	grad_norm 2.8630 (2.7533)	
[2022-01-25 19:40:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][680/1251]	eta 0:21:05 lr 0.000067	time 3.6895 (2.2168)	loss 3.1247 (3.0993)	grad_norm 2.6924 (2.7523)	
[2022-01-25 19:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][690/1251]	eta 0:20:43 lr 0.000067	time 1.9012 (2.2159)	loss 3.4710 (3.1008)	grad_norm 2.5163 (2.7517)	
[2022-01-25 19:40:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][700/1251]	eta 0:20:21 lr 0.000067	time 2.1928 (2.2163)	loss 2.9011 (3.0997)	grad_norm 3.6662 (2.7514)	
[2022-01-25 19:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][710/1251]	eta 0:19:57 lr 0.000067	time 1.5841 (2.2141)	loss 2.2058 (3.0979)	grad_norm 2.8157 (2.7522)	
[2022-01-25 19:41:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][720/1251]	eta 0:19:35 lr 0.000067	time 2.6955 (2.2142)	loss 3.3992 (3.0957)	grad_norm 2.5679 (2.7521)	
[2022-01-25 19:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][730/1251]	eta 0:19:12 lr 0.000067	time 1.8457 (2.2130)	loss 2.6453 (3.0925)	grad_norm 4.2693 (2.7541)	
[2022-01-25 19:42:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][740/1251]	eta 0:18:50 lr 0.000067	time 2.8671 (2.2124)	loss 3.2662 (3.0913)	grad_norm 2.8171 (2.7553)	
[2022-01-25 19:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][750/1251]	eta 0:18:27 lr 0.000067	time 2.0338 (2.2112)	loss 3.1954 (3.0941)	grad_norm 4.0589 (2.7557)	
[2022-01-25 19:42:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][760/1251]	eta 0:18:05 lr 0.000067	time 1.9521 (2.2099)	loss 3.4071 (3.0874)	grad_norm 2.3868 (2.7540)	
[2022-01-25 19:43:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][770/1251]	eta 0:17:43 lr 0.000067	time 1.8921 (2.2105)	loss 3.3594 (3.0879)	grad_norm 2.3845 (2.7549)	
[2022-01-25 19:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][780/1251]	eta 0:17:20 lr 0.000067	time 2.0197 (2.2102)	loss 3.3375 (3.0865)	grad_norm 2.9630 (2.7577)	
[2022-01-25 19:44:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][790/1251]	eta 0:16:57 lr 0.000067	time 2.0049 (2.2081)	loss 3.4380 (3.0894)	grad_norm 2.6322 (2.7558)	
[2022-01-25 19:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][800/1251]	eta 0:16:35 lr 0.000067	time 1.9743 (2.2066)	loss 2.4109 (3.0880)	grad_norm 2.8018 (2.7543)	
[2022-01-25 19:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][810/1251]	eta 0:16:13 lr 0.000067	time 1.8713 (2.2081)	loss 3.6625 (3.0890)	grad_norm 2.8356 (2.7536)	
[2022-01-25 19:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][820/1251]	eta 0:15:52 lr 0.000067	time 1.9718 (2.2092)	loss 2.9925 (3.0900)	grad_norm 2.4213 (2.7521)	
[2022-01-25 19:45:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][830/1251]	eta 0:15:30 lr 0.000067	time 2.2264 (2.2091)	loss 3.4440 (3.0920)	grad_norm 2.7278 (2.7518)	
[2022-01-25 19:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][840/1251]	eta 0:15:07 lr 0.000067	time 2.6163 (2.2081)	loss 2.6807 (3.0924)	grad_norm 2.4976 (2.7508)	
[2022-01-25 19:46:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][850/1251]	eta 0:14:45 lr 0.000067	time 2.4851 (2.2093)	loss 3.6163 (3.0959)	grad_norm 2.8144 (2.7518)	
[2022-01-25 19:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][860/1251]	eta 0:14:24 lr 0.000067	time 2.4983 (2.2107)	loss 2.5568 (3.0936)	grad_norm 2.4295 (2.7522)	
[2022-01-25 19:46:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][870/1251]	eta 0:14:01 lr 0.000067	time 3.1220 (2.2099)	loss 3.6532 (3.0926)	grad_norm 2.6637 (2.7497)	
[2022-01-25 19:47:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][880/1251]	eta 0:13:39 lr 0.000067	time 2.5715 (2.2091)	loss 2.7693 (3.0929)	grad_norm 2.6775 (2.7495)	
[2022-01-25 19:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][890/1251]	eta 0:13:16 lr 0.000067	time 1.7678 (2.2077)	loss 2.7578 (3.0909)	grad_norm 2.5047 (2.7488)	
[2022-01-25 19:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][900/1251]	eta 0:12:55 lr 0.000067	time 2.0637 (2.2080)	loss 2.4064 (3.0897)	grad_norm 2.4383 (2.7478)	
[2022-01-25 19:48:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][910/1251]	eta 0:12:32 lr 0.000067	time 2.2035 (2.2059)	loss 3.7602 (3.0875)	grad_norm 2.9073 (2.7477)	
[2022-01-25 19:48:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][920/1251]	eta 0:12:09 lr 0.000067	time 2.1999 (2.2050)	loss 3.1232 (3.0846)	grad_norm 2.2641 (2.7462)	
[2022-01-25 19:49:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][930/1251]	eta 0:11:47 lr 0.000067	time 1.9609 (2.2029)	loss 2.0947 (3.0822)	grad_norm 3.1093 (2.7467)	
[2022-01-25 19:49:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][940/1251]	eta 0:11:24 lr 0.000067	time 1.9232 (2.2012)	loss 3.4945 (3.0813)	grad_norm 2.6619 (2.7484)	
[2022-01-25 19:49:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][950/1251]	eta 0:11:02 lr 0.000067	time 1.8250 (2.2003)	loss 3.1342 (3.0822)	grad_norm 2.2473 (2.7492)	
[2022-01-25 19:50:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][960/1251]	eta 0:10:39 lr 0.000067	time 1.8933 (2.1992)	loss 2.3168 (3.0817)	grad_norm 2.2854 (2.7481)	
[2022-01-25 19:50:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][970/1251]	eta 0:10:17 lr 0.000067	time 2.1578 (2.1980)	loss 3.7269 (3.0820)	grad_norm 3.2047 (2.7479)	
[2022-01-25 19:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][980/1251]	eta 0:09:56 lr 0.000067	time 1.7119 (2.1995)	loss 3.6979 (3.0846)	grad_norm 2.8530 (2.7472)	
[2022-01-25 19:51:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][990/1251]	eta 0:09:34 lr 0.000067	time 1.8670 (2.1998)	loss 3.6993 (3.0855)	grad_norm 2.5885 (2.7474)	
[2022-01-25 19:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1000/1251]	eta 0:09:12 lr 0.000067	time 2.2297 (2.1994)	loss 2.0425 (3.0833)	grad_norm 2.5546 (2.7464)	
[2022-01-25 19:51:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1010/1251]	eta 0:08:50 lr 0.000067	time 2.6423 (2.2003)	loss 3.6919 (3.0828)	grad_norm 2.5392 (2.7450)	
[2022-01-25 19:52:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1020/1251]	eta 0:08:28 lr 0.000067	time 2.1700 (2.2003)	loss 3.1845 (3.0836)	grad_norm 2.3223 (2.7443)	
[2022-01-25 19:52:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1030/1251]	eta 0:08:06 lr 0.000067	time 2.5453 (2.2007)	loss 3.4914 (3.0845)	grad_norm 2.8682 (2.7446)	
[2022-01-25 19:53:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1040/1251]	eta 0:07:44 lr 0.000067	time 2.8338 (2.2019)	loss 3.1904 (3.0861)	grad_norm 3.1615 (2.7427)	
[2022-01-25 19:53:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1050/1251]	eta 0:07:22 lr 0.000067	time 2.2152 (2.2014)	loss 2.0769 (3.0861)	grad_norm 2.5937 (2.7420)	
[2022-01-25 19:53:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1060/1251]	eta 0:07:00 lr 0.000067	time 1.5861 (2.2001)	loss 2.4309 (3.0844)	grad_norm 3.3501 (2.7413)	
[2022-01-25 19:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1070/1251]	eta 0:06:37 lr 0.000067	time 1.6678 (2.1987)	loss 3.6449 (3.0836)	grad_norm 2.8285 (2.7402)	
[2022-01-25 19:54:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1080/1251]	eta 0:06:15 lr 0.000067	time 2.0279 (2.1980)	loss 2.9245 (3.0828)	grad_norm 2.4642 (2.7390)	
[2022-01-25 19:54:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1090/1251]	eta 0:05:53 lr 0.000067	time 2.2444 (2.1981)	loss 3.4736 (3.0823)	grad_norm 2.2878 (2.7411)	
[2022-01-25 19:55:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1100/1251]	eta 0:05:31 lr 0.000067	time 1.9083 (2.1976)	loss 3.2312 (3.0834)	grad_norm 2.4865 (2.7428)	
[2022-01-25 19:55:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1110/1251]	eta 0:05:09 lr 0.000067	time 2.2045 (2.1964)	loss 2.4316 (3.0814)	grad_norm 3.1801 (2.7444)	
[2022-01-25 19:55:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1120/1251]	eta 0:04:47 lr 0.000067	time 2.7519 (2.1973)	loss 3.3085 (3.0808)	grad_norm 2.7291 (2.7458)	
[2022-01-25 19:56:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1130/1251]	eta 0:04:26 lr 0.000067	time 2.9245 (2.1989)	loss 3.3364 (3.0805)	grad_norm 2.9097 (2.7462)	
[2022-01-25 19:56:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1140/1251]	eta 0:04:04 lr 0.000067	time 1.8025 (2.1991)	loss 2.9729 (3.0780)	grad_norm 2.5323 (2.7471)	
[2022-01-25 19:57:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1150/1251]	eta 0:03:42 lr 0.000067	time 1.9003 (2.1989)	loss 2.2589 (3.0773)	grad_norm 2.7798 (2.7462)	
[2022-01-25 19:57:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1160/1251]	eta 0:03:20 lr 0.000067	time 1.8671 (2.1989)	loss 2.3910 (3.0766)	grad_norm 2.5799 (2.7459)	
[2022-01-25 19:57:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1170/1251]	eta 0:02:58 lr 0.000066	time 1.6486 (2.1984)	loss 3.5455 (3.0758)	grad_norm 3.4827 (2.7469)	
[2022-01-25 19:58:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1180/1251]	eta 0:02:36 lr 0.000066	time 2.4398 (2.1982)	loss 3.0076 (3.0770)	grad_norm 2.5884 (2.7491)	
[2022-01-25 19:58:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1190/1251]	eta 0:02:14 lr 0.000066	time 1.9399 (2.1982)	loss 2.1049 (3.0743)	grad_norm 2.6490 (2.7494)	
[2022-01-25 19:58:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1200/1251]	eta 0:01:52 lr 0.000066	time 1.7727 (2.1988)	loss 2.6713 (3.0744)	grad_norm 2.6043 (2.7491)	
[2022-01-25 19:59:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1210/1251]	eta 0:01:30 lr 0.000066	time 2.6891 (2.2002)	loss 3.4396 (3.0735)	grad_norm 2.3340 (2.7472)	
[2022-01-25 19:59:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1220/1251]	eta 0:01:08 lr 0.000066	time 1.7911 (2.2003)	loss 1.9606 (3.0718)	grad_norm 3.0120 (2.7477)	
[2022-01-25 20:00:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1230/1251]	eta 0:00:46 lr 0.000066	time 1.6869 (2.1989)	loss 3.3801 (3.0732)	grad_norm 2.4982 (2.7478)	
[2022-01-25 20:00:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1240/1251]	eta 0:00:24 lr 0.000066	time 1.2607 (2.1963)	loss 3.4766 (3.0718)	grad_norm 3.4724 (2.7473)	
[2022-01-25 20:00:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [253/300][1250/1251]	eta 0:00:02 lr 0.000066	time 1.2106 (2.1903)	loss 3.3700 (3.0709)	grad_norm 2.6495 (2.7463)	
[2022-01-25 20:00:35 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 253 training takes 0:45:40
[2022-01-25 20:00:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 20.740 (20.740)	Loss 0.7796 (0.7796)	Acc@1 80.762 (80.762)	Acc@5 96.973 (96.973)	
[2022-01-25 20:01:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.606 (3.330)	Loss 0.8375 (0.8146)	Acc@1 79.883 (81.037)	Acc@5 94.922 (95.277)	
[2022-01-25 20:01:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.602 (2.562)	Loss 0.8559 (0.8194)	Acc@1 79.883 (80.780)	Acc@5 95.410 (95.387)	
[2022-01-25 20:01:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.600 (2.311)	Loss 0.9164 (0.8360)	Acc@1 79.492 (80.516)	Acc@5 94.629 (95.253)	
[2022-01-25 20:02:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.877 (2.173)	Loss 0.8450 (0.8389)	Acc@1 79.590 (80.428)	Acc@5 95.312 (95.179)	
[2022-01-25 20:02:12 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.422 Acc@5 95.270
[2022-01-25 20:02:12 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.4%
[2022-01-25 20:02:12 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.42%
[2022-01-25 20:02:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][0/1251]	eta 7:30:20 lr 0.000066	time 21.5994 (21.5994)	loss 3.4099 (3.4099)	grad_norm 2.5842 (2.5842)	
[2022-01-25 20:02:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][10/1251]	eta 1:25:32 lr 0.000066	time 1.6155 (4.1361)	loss 3.4044 (3.2584)	grad_norm 2.6107 (3.0834)	
[2022-01-25 20:03:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][20/1251]	eta 1:06:13 lr 0.000066	time 2.3105 (3.2280)	loss 3.5580 (3.1761)	grad_norm 2.6790 (3.0308)	
[2022-01-25 20:03:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][30/1251]	eta 0:57:54 lr 0.000066	time 1.5655 (2.8458)	loss 3.4322 (3.1277)	grad_norm 2.7297 (2.9679)	
[2022-01-25 20:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][40/1251]	eta 0:55:53 lr 0.000066	time 4.0695 (2.7689)	loss 3.1835 (3.1505)	grad_norm 2.6208 (2.9628)	
[2022-01-25 20:04:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][50/1251]	eta 0:53:09 lr 0.000066	time 1.6263 (2.6554)	loss 3.3075 (3.1408)	grad_norm 2.5868 (2.9245)	
[2022-01-25 20:04:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][60/1251]	eta 0:50:53 lr 0.000066	time 2.1194 (2.5635)	loss 3.1668 (3.1252)	grad_norm 2.7498 (2.8837)	
[2022-01-25 20:05:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][70/1251]	eta 0:48:57 lr 0.000066	time 1.7627 (2.4869)	loss 3.3457 (3.1329)	grad_norm 2.6267 (2.8978)	
[2022-01-25 20:05:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][80/1251]	eta 0:48:07 lr 0.000066	time 3.8124 (2.4661)	loss 3.4517 (3.1349)	grad_norm 2.9130 (2.8724)	
[2022-01-25 20:05:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][90/1251]	eta 0:47:06 lr 0.000066	time 1.5713 (2.4343)	loss 3.3012 (3.1242)	grad_norm 2.5700 (2.8638)	
[2022-01-25 20:06:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][100/1251]	eta 0:46:09 lr 0.000066	time 1.8520 (2.4058)	loss 3.4080 (3.1038)	grad_norm 2.4196 (2.8555)	
[2022-01-25 20:06:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][110/1251]	eta 0:45:12 lr 0.000066	time 1.8465 (2.3776)	loss 2.3914 (3.0712)	grad_norm 3.1212 (2.8416)	
[2022-01-25 20:06:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][120/1251]	eta 0:44:35 lr 0.000066	time 3.5060 (2.3657)	loss 3.3533 (3.0898)	grad_norm 4.1298 (2.8426)	
[2022-01-25 20:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][130/1251]	eta 0:43:58 lr 0.000066	time 2.3837 (2.3540)	loss 2.0110 (3.0654)	grad_norm 3.4504 (2.8376)	
[2022-01-25 20:07:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][140/1251]	eta 0:43:29 lr 0.000066	time 2.0559 (2.3491)	loss 3.2000 (3.0860)	grad_norm 2.9921 (2.8413)	
[2022-01-25 20:08:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][150/1251]	eta 0:42:55 lr 0.000066	time 1.8123 (2.3393)	loss 2.8434 (3.0883)	grad_norm 3.0088 (2.8492)	
[2022-01-25 20:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][160/1251]	eta 0:42:30 lr 0.000066	time 3.1653 (2.3374)	loss 3.7540 (3.0975)	grad_norm 2.8783 (2.8472)	
[2022-01-25 20:08:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][170/1251]	eta 0:41:55 lr 0.000066	time 1.8576 (2.3274)	loss 3.5630 (3.0847)	grad_norm 2.9131 (2.8477)	
[2022-01-25 20:09:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][180/1251]	eta 0:41:17 lr 0.000066	time 1.6415 (2.3129)	loss 2.4169 (3.0699)	grad_norm 2.7379 (2.8386)	
[2022-01-25 20:09:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][190/1251]	eta 0:40:42 lr 0.000066	time 1.9181 (2.3019)	loss 3.2448 (3.0656)	grad_norm 2.8519 (2.8321)	
[2022-01-25 20:09:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][200/1251]	eta 0:40:15 lr 0.000066	time 3.5939 (2.2983)	loss 3.2997 (3.0521)	grad_norm 2.9720 (2.8296)	
[2022-01-25 20:10:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][210/1251]	eta 0:39:51 lr 0.000066	time 1.8699 (2.2972)	loss 2.8319 (3.0597)	grad_norm 2.9516 (2.8287)	
[2022-01-25 20:10:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][220/1251]	eta 0:39:27 lr 0.000066	time 1.4679 (2.2963)	loss 3.0527 (3.0520)	grad_norm 2.3597 (2.8257)	
[2022-01-25 20:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][230/1251]	eta 0:39:01 lr 0.000066	time 1.4638 (2.2930)	loss 2.6445 (3.0438)	grad_norm 2.8068 (2.8193)	
[2022-01-25 20:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][240/1251]	eta 0:38:47 lr 0.000066	time 3.0145 (2.3017)	loss 2.3511 (3.0317)	grad_norm 2.5085 (2.8141)	
[2022-01-25 20:11:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][250/1251]	eta 0:38:14 lr 0.000066	time 1.6563 (2.2918)	loss 2.9124 (3.0283)	grad_norm 2.8444 (2.8151)	
[2022-01-25 20:12:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][260/1251]	eta 0:37:39 lr 0.000066	time 1.6678 (2.2805)	loss 2.5956 (3.0328)	grad_norm 2.7530 (2.8136)	
[2022-01-25 20:12:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][270/1251]	eta 0:37:13 lr 0.000066	time 1.9437 (2.2769)	loss 2.1532 (3.0300)	grad_norm 2.6102 (2.8100)	
[2022-01-25 20:12:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][280/1251]	eta 0:37:01 lr 0.000066	time 2.0541 (2.2878)	loss 3.7835 (3.0319)	grad_norm 2.6420 (2.8065)	
[2022-01-25 20:13:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][290/1251]	eta 0:36:35 lr 0.000066	time 1.8680 (2.2849)	loss 2.3412 (3.0385)	grad_norm 2.5257 (2.7987)	
[2022-01-25 20:13:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][300/1251]	eta 0:36:05 lr 0.000066	time 1.6321 (2.2772)	loss 2.1286 (3.0371)	grad_norm 2.6311 (2.7901)	
[2022-01-25 20:13:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][310/1251]	eta 0:35:39 lr 0.000066	time 1.8386 (2.2733)	loss 2.2037 (3.0347)	grad_norm 2.8480 (2.7910)	
[2022-01-25 20:14:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][320/1251]	eta 0:35:25 lr 0.000066	time 1.7733 (2.2832)	loss 3.3244 (3.0345)	grad_norm 2.9714 (2.7877)	
[2022-01-25 20:14:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][330/1251]	eta 0:34:55 lr 0.000066	time 1.6541 (2.2748)	loss 3.5254 (3.0352)	grad_norm 2.5779 (2.7873)	
[2022-01-25 20:15:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][340/1251]	eta 0:34:26 lr 0.000066	time 1.7365 (2.2688)	loss 2.7437 (3.0305)	grad_norm 2.6685 (2.7842)	
[2022-01-25 20:15:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][350/1251]	eta 0:33:59 lr 0.000066	time 2.0648 (2.2635)	loss 1.9954 (3.0348)	grad_norm 3.0427 (2.7844)	
[2022-01-25 20:15:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][360/1251]	eta 0:33:33 lr 0.000066	time 1.8783 (2.2603)	loss 2.8065 (3.0341)	grad_norm 2.5154 (2.7830)	
[2022-01-25 20:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][370/1251]	eta 0:33:06 lr 0.000066	time 2.2264 (2.2545)	loss 3.6931 (3.0421)	grad_norm 2.8182 (2.7812)	
[2022-01-25 20:16:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][380/1251]	eta 0:32:39 lr 0.000066	time 2.3814 (2.2502)	loss 3.0651 (3.0369)	grad_norm 2.7466 (2.7796)	
[2022-01-25 20:16:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][390/1251]	eta 0:32:18 lr 0.000066	time 3.0946 (2.2509)	loss 2.6525 (3.0385)	grad_norm 2.7165 (2.7838)	
[2022-01-25 20:17:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][400/1251]	eta 0:31:57 lr 0.000066	time 2.1432 (2.2531)	loss 2.4715 (3.0355)	grad_norm 2.9698 (2.7838)	
[2022-01-25 20:17:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][410/1251]	eta 0:31:36 lr 0.000066	time 2.4435 (2.2551)	loss 3.5087 (3.0430)	grad_norm 2.7837 (2.7839)	
[2022-01-25 20:18:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][420/1251]	eta 0:31:15 lr 0.000066	time 3.1105 (2.2572)	loss 1.8674 (3.0416)	grad_norm 1.9526 (2.7800)	
[2022-01-25 20:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][430/1251]	eta 0:30:55 lr 0.000066	time 2.8280 (2.2601)	loss 2.7473 (3.0464)	grad_norm 3.4871 (2.7782)	
[2022-01-25 20:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][440/1251]	eta 0:30:27 lr 0.000065	time 1.9405 (2.2536)	loss 3.3720 (3.0402)	grad_norm 2.7341 (2.7764)	
[2022-01-25 20:19:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][450/1251]	eta 0:30:02 lr 0.000065	time 1.8653 (2.2499)	loss 2.7320 (3.0364)	grad_norm 2.5755 (2.7770)	
[2022-01-25 20:19:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][460/1251]	eta 0:29:38 lr 0.000065	time 2.5860 (2.2484)	loss 3.1087 (3.0328)	grad_norm 2.6435 (2.7779)	
[2022-01-25 20:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][470/1251]	eta 0:29:14 lr 0.000065	time 2.2167 (2.2470)	loss 2.3068 (3.0318)	grad_norm 2.4467 (2.7747)	
[2022-01-25 20:20:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][480/1251]	eta 0:28:50 lr 0.000065	time 1.9411 (2.2450)	loss 3.1849 (3.0338)	grad_norm 2.7915 (2.7745)	
[2022-01-25 20:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][490/1251]	eta 0:28:26 lr 0.000065	time 1.8840 (2.2430)	loss 3.2047 (3.0364)	grad_norm 2.4636 (2.7710)	
[2022-01-25 20:20:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][500/1251]	eta 0:28:04 lr 0.000065	time 1.9112 (2.2433)	loss 3.0982 (3.0352)	grad_norm 2.4486 (2.7692)	
[2022-01-25 20:21:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][510/1251]	eta 0:27:40 lr 0.000065	time 2.3188 (2.2412)	loss 3.5278 (3.0339)	grad_norm 2.8488 (2.7707)	
[2022-01-25 20:21:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][520/1251]	eta 0:27:17 lr 0.000065	time 2.5664 (2.2403)	loss 2.3546 (3.0324)	grad_norm 2.5321 (2.7693)	
[2022-01-25 20:22:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][530/1251]	eta 0:26:54 lr 0.000065	time 1.5538 (2.2386)	loss 2.9993 (3.0292)	grad_norm 2.5567 (2.7651)	
[2022-01-25 20:22:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][540/1251]	eta 0:26:31 lr 0.000065	time 2.3326 (2.2386)	loss 3.5750 (3.0307)	grad_norm 2.7381 (2.7688)	
[2022-01-25 20:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][550/1251]	eta 0:26:08 lr 0.000065	time 2.8051 (2.2371)	loss 1.9185 (3.0313)	grad_norm 2.5974 (2.7659)	
[2022-01-25 20:23:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][560/1251]	eta 0:25:44 lr 0.000065	time 2.2784 (2.2353)	loss 2.3693 (3.0366)	grad_norm 2.9395 (2.7662)	
[2022-01-25 20:23:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][570/1251]	eta 0:25:21 lr 0.000065	time 1.8774 (2.2337)	loss 3.1140 (3.0366)	grad_norm 2.8080 (2.7689)	
[2022-01-25 20:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][580/1251]	eta 0:24:59 lr 0.000065	time 2.2930 (2.2341)	loss 3.2074 (3.0350)	grad_norm 2.4273 (2.7668)	
[2022-01-25 20:24:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][590/1251]	eta 0:24:37 lr 0.000065	time 3.5961 (2.2352)	loss 3.1057 (3.0333)	grad_norm 2.8197 (2.7739)	
[2022-01-25 20:24:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][600/1251]	eta 0:24:13 lr 0.000065	time 2.4750 (2.2330)	loss 3.7701 (3.0347)	grad_norm 2.4398 (2.7745)	
[2022-01-25 20:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][610/1251]	eta 0:23:50 lr 0.000065	time 1.9276 (2.2310)	loss 3.6180 (3.0314)	grad_norm 2.8233 (2.7771)	
[2022-01-25 20:25:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][620/1251]	eta 0:23:27 lr 0.000065	time 2.8412 (2.2304)	loss 3.6484 (3.0298)	grad_norm 3.0651 (2.7758)	
[2022-01-25 20:25:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][630/1251]	eta 0:23:05 lr 0.000065	time 2.9086 (2.2317)	loss 3.7201 (3.0348)	grad_norm 3.1484 (2.7767)	
[2022-01-25 20:26:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][640/1251]	eta 0:22:43 lr 0.000065	time 2.6021 (2.2314)	loss 3.2596 (3.0359)	grad_norm 2.6139 (2.7750)	
[2022-01-25 20:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][650/1251]	eta 0:22:20 lr 0.000065	time 2.4885 (2.2301)	loss 3.4752 (3.0384)	grad_norm 3.0502 (2.7758)	
[2022-01-25 20:26:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][660/1251]	eta 0:21:55 lr 0.000065	time 1.7524 (2.2262)	loss 2.9682 (3.0359)	grad_norm 2.4965 (2.7760)	
[2022-01-25 20:27:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][670/1251]	eta 0:21:32 lr 0.000065	time 2.6308 (2.2244)	loss 3.3388 (3.0380)	grad_norm 2.3927 (2.7755)	
[2022-01-25 20:27:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][680/1251]	eta 0:21:10 lr 0.000065	time 2.2695 (2.2251)	loss 3.5963 (3.0350)	grad_norm 3.4143 (2.7765)	
[2022-01-25 20:27:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][690/1251]	eta 0:20:47 lr 0.000065	time 2.4880 (2.2237)	loss 3.8564 (3.0373)	grad_norm 2.8179 (2.7744)	
[2022-01-25 20:28:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][700/1251]	eta 0:20:23 lr 0.000065	time 2.4044 (2.2214)	loss 3.3082 (3.0385)	grad_norm 2.3212 (2.7710)	
[2022-01-25 20:28:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][710/1251]	eta 0:20:02 lr 0.000065	time 2.4593 (2.2227)	loss 3.0444 (3.0372)	grad_norm 2.6873 (2.7702)	
[2022-01-25 20:28:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][720/1251]	eta 0:19:41 lr 0.000065	time 2.2498 (2.2250)	loss 2.3578 (3.0345)	grad_norm 2.7700 (2.7680)	
[2022-01-25 20:29:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][730/1251]	eta 0:19:18 lr 0.000065	time 1.8269 (2.2232)	loss 2.9759 (3.0333)	grad_norm 2.8585 (2.7683)	
[2022-01-25 20:29:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][740/1251]	eta 0:18:57 lr 0.000065	time 4.0115 (2.2258)	loss 3.0698 (3.0342)	grad_norm 2.4311 (2.7690)	
[2022-01-25 20:30:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][750/1251]	eta 0:18:34 lr 0.000065	time 1.6081 (2.2247)	loss 2.6650 (3.0331)	grad_norm 2.5035 (2.7674)	
[2022-01-25 20:30:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][760/1251]	eta 0:18:11 lr 0.000065	time 1.7755 (2.2238)	loss 2.9272 (3.0352)	grad_norm 2.8655 (2.7681)	
[2022-01-25 20:30:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][770/1251]	eta 0:17:49 lr 0.000065	time 1.8979 (2.2235)	loss 2.8189 (3.0298)	grad_norm 2.5225 (2.7681)	
[2022-01-25 20:31:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][780/1251]	eta 0:17:27 lr 0.000065	time 3.7263 (2.2246)	loss 2.9112 (3.0292)	grad_norm 2.5167 (2.7679)	
[2022-01-25 20:31:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][790/1251]	eta 0:17:04 lr 0.000065	time 1.8960 (2.2231)	loss 2.6030 (3.0298)	grad_norm 3.8306 (2.7690)	
[2022-01-25 20:31:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][800/1251]	eta 0:16:41 lr 0.000065	time 2.1381 (2.2217)	loss 3.1010 (3.0322)	grad_norm 2.8429 (2.7692)	
[2022-01-25 20:32:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][810/1251]	eta 0:16:18 lr 0.000065	time 1.7578 (2.2189)	loss 2.8083 (3.0346)	grad_norm 2.9796 (2.7720)	
[2022-01-25 20:32:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][820/1251]	eta 0:15:55 lr 0.000065	time 1.9099 (2.2167)	loss 3.1352 (3.0334)	grad_norm 2.9802 (2.7726)	
[2022-01-25 20:32:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][830/1251]	eta 0:15:32 lr 0.000065	time 1.9120 (2.2157)	loss 3.0157 (3.0340)	grad_norm 2.6130 (2.7766)	
[2022-01-25 20:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][840/1251]	eta 0:15:10 lr 0.000065	time 1.8526 (2.2146)	loss 2.3356 (3.0359)	grad_norm 2.8549 (2.7756)	
[2022-01-25 20:33:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][850/1251]	eta 0:14:48 lr 0.000065	time 2.4721 (2.2157)	loss 2.2042 (3.0372)	grad_norm 2.6511 (2.7752)	
[2022-01-25 20:34:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][860/1251]	eta 0:14:26 lr 0.000065	time 2.7763 (2.2168)	loss 2.8218 (3.0368)	grad_norm 2.7145 (2.7763)	
[2022-01-25 20:34:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][870/1251]	eta 0:14:04 lr 0.000065	time 1.9740 (2.2170)	loss 3.0818 (3.0375)	grad_norm 2.3933 (2.7744)	
[2022-01-25 20:34:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][880/1251]	eta 0:13:41 lr 0.000065	time 1.5182 (2.2151)	loss 2.7663 (3.0378)	grad_norm 4.8598 (2.7765)	
[2022-01-25 20:35:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][890/1251]	eta 0:13:19 lr 0.000065	time 1.8875 (2.2151)	loss 3.2295 (3.0412)	grad_norm 2.3115 (2.7749)	
[2022-01-25 20:35:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][900/1251]	eta 0:12:57 lr 0.000065	time 2.0499 (2.2142)	loss 3.2668 (3.0428)	grad_norm 2.3073 (2.7737)	
[2022-01-25 20:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][910/1251]	eta 0:12:34 lr 0.000065	time 1.9045 (2.2139)	loss 3.8583 (3.0416)	grad_norm 2.7250 (2.7736)	
[2022-01-25 20:36:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][920/1251]	eta 0:12:12 lr 0.000065	time 2.1820 (2.2131)	loss 3.5249 (3.0427)	grad_norm 3.3505 (2.7735)	
[2022-01-25 20:36:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][930/1251]	eta 0:11:50 lr 0.000065	time 1.9854 (2.2133)	loss 2.7511 (3.0447)	grad_norm 2.6595 (2.7735)	
[2022-01-25 20:36:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][940/1251]	eta 0:11:28 lr 0.000065	time 1.6008 (2.2124)	loss 3.5240 (3.0459)	grad_norm 2.6472 (2.7728)	
[2022-01-25 20:37:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][950/1251]	eta 0:11:06 lr 0.000065	time 1.5272 (2.2134)	loss 3.4649 (3.0480)	grad_norm 2.6758 (2.7711)	
[2022-01-25 20:37:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][960/1251]	eta 0:10:43 lr 0.000065	time 1.9965 (2.2128)	loss 3.2675 (3.0493)	grad_norm 2.8239 (2.7704)	
[2022-01-25 20:38:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][970/1251]	eta 0:10:21 lr 0.000064	time 1.8852 (2.2130)	loss 3.4608 (3.0504)	grad_norm 2.8220 (2.7695)	
[2022-01-25 20:38:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][980/1251]	eta 0:09:59 lr 0.000064	time 1.8116 (2.2121)	loss 3.6006 (3.0518)	grad_norm 2.6578 (2.7690)	
[2022-01-25 20:38:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][990/1251]	eta 0:09:37 lr 0.000064	time 1.9069 (2.2114)	loss 3.2374 (3.0529)	grad_norm 2.3435 (2.7691)	
[2022-01-25 20:39:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1000/1251]	eta 0:09:14 lr 0.000064	time 1.7044 (2.2089)	loss 3.3679 (3.0546)	grad_norm 3.6488 (2.7707)	
[2022-01-25 20:39:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1010/1251]	eta 0:08:52 lr 0.000064	time 2.1190 (2.2094)	loss 3.5404 (3.0552)	grad_norm 2.5214 (2.7721)	
[2022-01-25 20:39:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1020/1251]	eta 0:08:30 lr 0.000064	time 2.2236 (2.2085)	loss 2.9660 (3.0572)	grad_norm 2.3513 (2.7729)	
[2022-01-25 20:40:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1030/1251]	eta 0:08:08 lr 0.000064	time 2.2538 (2.2088)	loss 3.4233 (3.0536)	grad_norm 3.0322 (2.7777)	
[2022-01-25 20:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1040/1251]	eta 0:07:45 lr 0.000064	time 1.6073 (2.2082)	loss 3.3453 (3.0547)	grad_norm 2.3005 (2.7768)	
[2022-01-25 20:40:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1050/1251]	eta 0:07:24 lr 0.000064	time 2.5219 (2.2102)	loss 2.3568 (3.0557)	grad_norm 2.6688 (2.7761)	
[2022-01-25 20:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1060/1251]	eta 0:07:02 lr 0.000064	time 1.8305 (2.2098)	loss 2.4000 (3.0551)	grad_norm 3.2095 (2.7770)	
[2022-01-25 20:41:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1070/1251]	eta 0:06:40 lr 0.000064	time 2.4883 (2.2114)	loss 3.3162 (3.0554)	grad_norm 2.9323 (2.7772)	
[2022-01-25 20:42:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1080/1251]	eta 0:06:17 lr 0.000064	time 1.7655 (2.2103)	loss 2.7822 (3.0554)	grad_norm 2.4914 (2.7767)	
[2022-01-25 20:42:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1090/1251]	eta 0:05:55 lr 0.000064	time 1.9112 (2.2091)	loss 2.7312 (3.0557)	grad_norm 2.8559 (2.7773)	
[2022-01-25 20:42:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1100/1251]	eta 0:05:33 lr 0.000064	time 1.8300 (2.2079)	loss 2.1850 (3.0558)	grad_norm 2.3238 (2.7782)	
[2022-01-25 20:43:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1110/1251]	eta 0:05:11 lr 0.000064	time 1.7053 (2.2076)	loss 2.5493 (3.0561)	grad_norm 2.4812 (2.7769)	
[2022-01-25 20:43:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1120/1251]	eta 0:04:49 lr 0.000064	time 2.2458 (2.2075)	loss 2.9680 (3.0559)	grad_norm 2.8386 (2.7777)	
[2022-01-25 20:43:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1130/1251]	eta 0:04:27 lr 0.000064	time 2.0439 (2.2071)	loss 2.8523 (3.0543)	grad_norm 2.8895 (2.7788)	
[2022-01-25 20:44:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1140/1251]	eta 0:04:04 lr 0.000064	time 1.7745 (2.2065)	loss 1.9991 (3.0538)	grad_norm 2.8913 (2.7799)	
[2022-01-25 20:44:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1150/1251]	eta 0:03:42 lr 0.000064	time 2.4644 (2.2067)	loss 3.0438 (3.0529)	grad_norm 2.6242 (2.7789)	
[2022-01-25 20:44:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1160/1251]	eta 0:03:20 lr 0.000064	time 2.7054 (2.2069)	loss 3.4952 (3.0526)	grad_norm 2.9598 (2.7786)	
[2022-01-25 20:45:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1170/1251]	eta 0:02:58 lr 0.000064	time 2.1656 (2.2063)	loss 3.0451 (3.0516)	grad_norm 2.7880 (2.7776)	
[2022-01-25 20:45:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1180/1251]	eta 0:02:36 lr 0.000064	time 1.8023 (2.2054)	loss 3.4048 (3.0517)	grad_norm 2.5733 (2.7776)	
[2022-01-25 20:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1190/1251]	eta 0:02:14 lr 0.000064	time 2.1450 (2.2045)	loss 3.2963 (3.0533)	grad_norm 3.1052 (2.7774)	
[2022-01-25 20:46:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1200/1251]	eta 0:01:52 lr 0.000064	time 3.0427 (2.2065)	loss 2.6193 (3.0522)	grad_norm 2.5691 (2.7759)	
[2022-01-25 20:46:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1210/1251]	eta 0:01:30 lr 0.000064	time 2.3975 (2.2052)	loss 3.1087 (3.0533)	grad_norm 2.5473 (2.7746)	
[2022-01-25 20:47:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1220/1251]	eta 0:01:08 lr 0.000064	time 1.6017 (2.2046)	loss 3.3231 (3.0531)	grad_norm 2.5532 (2.7731)	
[2022-01-25 20:47:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1230/1251]	eta 0:00:46 lr 0.000064	time 1.8300 (2.2041)	loss 3.1937 (3.0530)	grad_norm 2.8224 (2.7727)	
[2022-01-25 20:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1240/1251]	eta 0:00:24 lr 0.000064	time 2.4507 (2.2029)	loss 3.2834 (3.0538)	grad_norm 2.4563 (2.7719)	
[2022-01-25 20:48:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [254/300][1250/1251]	eta 0:00:02 lr 0.000064	time 1.1772 (2.1971)	loss 2.4371 (3.0529)	grad_norm 2.7952 (2.7700)	
[2022-01-25 20:48:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 254 training takes 0:45:49
[2022-01-25 20:48:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.442 (18.442)	Loss 0.9094 (0.9094)	Acc@1 79.395 (79.395)	Acc@5 94.238 (94.238)	
[2022-01-25 20:48:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.936 (3.272)	Loss 0.8450 (0.8394)	Acc@1 79.590 (79.998)	Acc@5 95.020 (95.117)	
[2022-01-25 20:48:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.928 (2.548)	Loss 0.8362 (0.8253)	Acc@1 81.641 (80.697)	Acc@5 95.605 (95.229)	
[2022-01-25 20:49:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.229 (2.249)	Loss 0.8091 (0.8259)	Acc@1 81.543 (80.598)	Acc@5 94.824 (95.275)	
[2022-01-25 20:49:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.668 (2.172)	Loss 0.8091 (0.8291)	Acc@1 79.883 (80.476)	Acc@5 96.191 (95.272)	
[2022-01-25 20:49:37 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.422 Acc@5 95.266
[2022-01-25 20:49:37 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.4%
[2022-01-25 20:49:37 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.42%
[2022-01-25 20:49:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][0/1251]	eta 7:47:45 lr 0.000064	time 22.4344 (22.4344)	loss 3.4811 (3.4811)	grad_norm 2.7659 (2.7659)	
[2022-01-25 20:50:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][10/1251]	eta 1:24:27 lr 0.000064	time 1.8323 (4.0831)	loss 3.0519 (2.9894)	grad_norm 2.8823 (2.6735)	
[2022-01-25 20:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][20/1251]	eta 1:04:22 lr 0.000064	time 1.5338 (3.1380)	loss 3.1882 (3.0526)	grad_norm 2.7415 (2.7811)	
[2022-01-25 20:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][30/1251]	eta 0:57:23 lr 0.000064	time 1.5941 (2.8201)	loss 3.3854 (3.0224)	grad_norm 2.6119 (2.7890)	
[2022-01-25 20:51:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][40/1251]	eta 0:53:49 lr 0.000064	time 3.7766 (2.6664)	loss 3.0528 (3.0342)	grad_norm 2.9704 (2.7983)	
[2022-01-25 20:51:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][50/1251]	eta 0:51:35 lr 0.000064	time 2.6371 (2.5771)	loss 2.1473 (3.0720)	grad_norm 2.4404 (2.7672)	
[2022-01-25 20:52:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][60/1251]	eta 0:50:01 lr 0.000064	time 2.1331 (2.5198)	loss 2.9689 (3.0800)	grad_norm 2.7949 (2.7535)	
[2022-01-25 20:52:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][70/1251]	eta 0:48:31 lr 0.000064	time 1.5634 (2.4650)	loss 3.3130 (3.1108)	grad_norm 2.8805 (2.7375)	
[2022-01-25 20:52:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][80/1251]	eta 0:47:52 lr 0.000064	time 3.8031 (2.4534)	loss 3.2165 (3.1018)	grad_norm 3.0365 (2.7411)	
[2022-01-25 20:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][90/1251]	eta 0:47:11 lr 0.000064	time 3.4441 (2.4384)	loss 2.3603 (3.1034)	grad_norm 2.5389 (2.7394)	
[2022-01-25 20:53:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][100/1251]	eta 0:46:15 lr 0.000064	time 1.5445 (2.4114)	loss 3.3885 (3.0995)	grad_norm 2.6557 (2.7842)	
[2022-01-25 20:54:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][110/1251]	eta 0:45:26 lr 0.000064	time 1.5872 (2.3898)	loss 3.2620 (3.1047)	grad_norm 2.7726 (2.8183)	
[2022-01-25 20:54:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][120/1251]	eta 0:44:46 lr 0.000064	time 2.6537 (2.3749)	loss 3.5153 (3.1058)	grad_norm 4.3046 (2.8284)	
[2022-01-25 20:54:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][130/1251]	eta 0:44:18 lr 0.000064	time 3.5218 (2.3711)	loss 3.4616 (3.1119)	grad_norm 2.5380 (2.8159)	
[2022-01-25 20:55:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][140/1251]	eta 0:43:38 lr 0.000064	time 1.5905 (2.3573)	loss 3.4391 (3.1174)	grad_norm 2.5551 (2.8150)	
[2022-01-25 20:55:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][150/1251]	eta 0:43:03 lr 0.000064	time 2.3522 (2.3464)	loss 2.7264 (3.0984)	grad_norm 3.4456 (2.8125)	
[2022-01-25 20:55:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][160/1251]	eta 0:42:30 lr 0.000064	time 3.1562 (2.3380)	loss 3.5142 (3.0933)	grad_norm 2.9378 (2.8136)	
[2022-01-25 20:56:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][170/1251]	eta 0:42:08 lr 0.000064	time 2.6832 (2.3394)	loss 3.3854 (3.0780)	grad_norm 3.0732 (2.8098)	
[2022-01-25 20:56:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][180/1251]	eta 0:41:21 lr 0.000064	time 1.5733 (2.3168)	loss 2.9281 (3.0788)	grad_norm 3.1958 (2.8212)	
[2022-01-25 20:56:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][190/1251]	eta 0:40:42 lr 0.000064	time 2.2255 (2.3023)	loss 2.5773 (3.0750)	grad_norm 2.9180 (2.8271)	
[2022-01-25 20:57:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][200/1251]	eta 0:40:08 lr 0.000064	time 1.8581 (2.2915)	loss 2.2315 (3.0700)	grad_norm 2.9950 (2.8369)	
[2022-01-25 20:57:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][210/1251]	eta 0:39:40 lr 0.000064	time 1.7913 (2.2868)	loss 3.4157 (3.0769)	grad_norm 2.4830 (2.8327)	
[2022-01-25 20:58:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][220/1251]	eta 0:39:08 lr 0.000064	time 1.4671 (2.2780)	loss 2.4915 (3.0752)	grad_norm 2.5350 (2.8278)	
[2022-01-25 20:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][230/1251]	eta 0:38:42 lr 0.000064	time 2.2634 (2.2748)	loss 3.3482 (3.0710)	grad_norm 2.9211 (2.8281)	
[2022-01-25 20:58:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][240/1251]	eta 0:38:23 lr 0.000064	time 2.3228 (2.2789)	loss 3.4988 (3.0720)	grad_norm 2.6628 (2.8339)	
[2022-01-25 20:59:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][250/1251]	eta 0:38:00 lr 0.000063	time 1.5848 (2.2780)	loss 3.3402 (3.0662)	grad_norm 2.9054 (2.8301)	
[2022-01-25 20:59:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][260/1251]	eta 0:37:29 lr 0.000063	time 1.3466 (2.2704)	loss 3.4831 (3.0620)	grad_norm 2.4620 (2.8221)	
[2022-01-25 20:59:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][270/1251]	eta 0:37:02 lr 0.000063	time 2.5448 (2.2659)	loss 2.0931 (3.0625)	grad_norm 2.9408 (2.8215)	
[2022-01-25 21:00:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][280/1251]	eta 0:36:39 lr 0.000063	time 1.8816 (2.2652)	loss 3.4692 (3.0595)	grad_norm 2.9302 (2.8284)	
[2022-01-25 21:00:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][290/1251]	eta 0:36:16 lr 0.000063	time 1.8677 (2.2643)	loss 2.3965 (3.0539)	grad_norm 2.7345 (2.8325)	
[2022-01-25 21:00:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][300/1251]	eta 0:35:49 lr 0.000063	time 2.2676 (2.2606)	loss 2.2937 (3.0533)	grad_norm 2.3226 (2.8338)	
[2022-01-25 21:01:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][310/1251]	eta 0:35:22 lr 0.000063	time 2.7839 (2.2560)	loss 2.1993 (3.0585)	grad_norm 2.5968 (2.8297)	
[2022-01-25 21:01:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][320/1251]	eta 0:35:03 lr 0.000063	time 1.9962 (2.2590)	loss 2.8544 (3.0585)	grad_norm 3.0700 (2.8261)	
[2022-01-25 21:02:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][330/1251]	eta 0:34:41 lr 0.000063	time 1.9481 (2.2595)	loss 3.7592 (3.0603)	grad_norm 2.8470 (2.8261)	
[2022-01-25 21:02:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][340/1251]	eta 0:34:17 lr 0.000063	time 2.3046 (2.2586)	loss 2.8424 (3.0647)	grad_norm 2.3495 (2.8203)	
[2022-01-25 21:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][350/1251]	eta 0:33:52 lr 0.000063	time 2.2246 (2.2562)	loss 3.4730 (3.0632)	grad_norm 2.5861 (2.8136)	
[2022-01-25 21:03:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][360/1251]	eta 0:33:25 lr 0.000063	time 1.5512 (2.2508)	loss 3.0337 (3.0663)	grad_norm 2.3746 (2.8129)	
[2022-01-25 21:03:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][370/1251]	eta 0:32:57 lr 0.000063	time 1.8414 (2.2450)	loss 2.9179 (3.0642)	grad_norm 2.9370 (2.8193)	
[2022-01-25 21:03:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][380/1251]	eta 0:32:32 lr 0.000063	time 2.2844 (2.2414)	loss 2.0617 (3.0638)	grad_norm 2.8482 (2.8169)	
[2022-01-25 21:04:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][390/1251]	eta 0:32:07 lr 0.000063	time 1.8254 (2.2382)	loss 2.7733 (3.0688)	grad_norm 3.1199 (2.8158)	
[2022-01-25 21:04:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][400/1251]	eta 0:31:44 lr 0.000063	time 1.7714 (2.2374)	loss 3.4063 (3.0714)	grad_norm 2.7069 (2.8137)	
[2022-01-25 21:04:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][410/1251]	eta 0:31:21 lr 0.000063	time 2.5140 (2.2367)	loss 3.1566 (3.0700)	grad_norm 2.8693 (2.8089)	
[2022-01-25 21:05:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][420/1251]	eta 0:30:58 lr 0.000063	time 2.5084 (2.2365)	loss 2.1463 (3.0677)	grad_norm 2.2402 (2.8042)	
[2022-01-25 21:05:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][430/1251]	eta 0:30:38 lr 0.000063	time 2.2900 (2.2389)	loss 2.1597 (3.0611)	grad_norm 2.4820 (2.8000)	
[2022-01-25 21:06:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][440/1251]	eta 0:30:16 lr 0.000063	time 2.1113 (2.2397)	loss 3.5164 (3.0546)	grad_norm 3.5959 (2.8025)	
[2022-01-25 21:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][450/1251]	eta 0:29:55 lr 0.000063	time 2.1557 (2.2417)	loss 3.1041 (3.0518)	grad_norm 2.6614 (2.7998)	
[2022-01-25 21:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][460/1251]	eta 0:29:32 lr 0.000063	time 2.1920 (2.2406)	loss 2.9428 (3.0508)	grad_norm 3.1969 (2.8024)	
[2022-01-25 21:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][470/1251]	eta 0:29:05 lr 0.000063	time 1.6679 (2.2355)	loss 2.2207 (3.0482)	grad_norm 2.9810 (2.7972)	
[2022-01-25 21:07:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][480/1251]	eta 0:28:41 lr 0.000063	time 2.3616 (2.2326)	loss 2.6829 (3.0454)	grad_norm 2.7503 (2.7918)	
[2022-01-25 21:07:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][490/1251]	eta 0:28:13 lr 0.000063	time 1.8664 (2.2257)	loss 2.1440 (3.0399)	grad_norm 2.4927 (2.7969)	
[2022-01-25 21:08:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][500/1251]	eta 0:27:48 lr 0.000063	time 1.6299 (2.2223)	loss 3.1725 (3.0446)	grad_norm 2.4667 (2.7995)	
[2022-01-25 21:08:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][510/1251]	eta 0:27:26 lr 0.000063	time 1.8735 (2.2218)	loss 1.9817 (3.0456)	grad_norm 3.1901 (2.8004)	
[2022-01-25 21:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][520/1251]	eta 0:27:05 lr 0.000063	time 2.1373 (2.2234)	loss 3.5575 (3.0469)	grad_norm 2.8300 (2.7998)	
[2022-01-25 21:09:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][530/1251]	eta 0:26:44 lr 0.000063	time 1.8356 (2.2252)	loss 3.4316 (3.0500)	grad_norm 2.8334 (2.7998)	
[2022-01-25 21:09:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][540/1251]	eta 0:26:23 lr 0.000063	time 2.2677 (2.2271)	loss 3.1927 (3.0494)	grad_norm 2.7477 (2.8015)	
[2022-01-25 21:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][550/1251]	eta 0:26:04 lr 0.000063	time 2.4664 (2.2321)	loss 3.4968 (3.0559)	grad_norm 2.7881 (2.7996)	
[2022-01-25 21:10:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][560/1251]	eta 0:25:44 lr 0.000063	time 2.2008 (2.2352)	loss 2.9233 (3.0568)	grad_norm 2.7157 (2.7948)	
[2022-01-25 21:10:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][570/1251]	eta 0:25:20 lr 0.000063	time 1.9448 (2.2333)	loss 3.3898 (3.0542)	grad_norm 2.7208 (2.7937)	
[2022-01-25 21:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][580/1251]	eta 0:24:55 lr 0.000063	time 1.9535 (2.2287)	loss 2.3109 (3.0539)	grad_norm 3.1637 (2.7914)	
[2022-01-25 21:11:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][590/1251]	eta 0:24:29 lr 0.000063	time 1.6881 (2.2236)	loss 2.6841 (3.0564)	grad_norm 2.4532 (2.7888)	
[2022-01-25 21:11:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][600/1251]	eta 0:24:07 lr 0.000063	time 2.6097 (2.2239)	loss 3.5102 (3.0577)	grad_norm 2.5014 (2.7899)	
[2022-01-25 21:12:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][610/1251]	eta 0:23:46 lr 0.000063	time 2.1438 (2.2253)	loss 2.0409 (3.0503)	grad_norm 2.5035 (2.7890)	
[2022-01-25 21:12:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][620/1251]	eta 0:23:24 lr 0.000063	time 2.1760 (2.2264)	loss 3.3110 (3.0506)	grad_norm 2.9024 (2.7900)	
[2022-01-25 21:13:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][630/1251]	eta 0:23:02 lr 0.000063	time 1.6818 (2.2257)	loss 3.4852 (3.0515)	grad_norm 3.7152 (2.7963)	
[2022-01-25 21:13:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][640/1251]	eta 0:22:40 lr 0.000063	time 2.5467 (2.2264)	loss 3.0260 (3.0512)	grad_norm 2.4499 (2.7931)	
[2022-01-25 21:13:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][650/1251]	eta 0:22:16 lr 0.000063	time 1.7449 (2.2246)	loss 2.3357 (3.0521)	grad_norm 3.0376 (2.7932)	
[2022-01-25 21:14:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][660/1251]	eta 0:21:53 lr 0.000063	time 2.1818 (2.2227)	loss 2.9990 (3.0490)	grad_norm 2.6708 (2.7927)	
[2022-01-25 21:14:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][670/1251]	eta 0:21:30 lr 0.000063	time 1.9106 (2.2208)	loss 2.6189 (3.0501)	grad_norm 2.9745 (2.7906)	
[2022-01-25 21:14:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][680/1251]	eta 0:21:07 lr 0.000063	time 2.3151 (2.2204)	loss 2.8163 (3.0536)	grad_norm 2.9735 (2.7899)	
[2022-01-25 21:15:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][690/1251]	eta 0:20:45 lr 0.000063	time 1.8961 (2.2204)	loss 3.8372 (3.0521)	grad_norm 2.7610 (2.7893)	
[2022-01-25 21:15:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][700/1251]	eta 0:20:22 lr 0.000063	time 2.2590 (2.2194)	loss 3.2956 (3.0517)	grad_norm 2.6712 (2.7872)	
[2022-01-25 21:15:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][710/1251]	eta 0:19:59 lr 0.000063	time 1.9286 (2.2174)	loss 3.3341 (3.0523)	grad_norm 2.3130 (2.7871)	
[2022-01-25 21:16:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][720/1251]	eta 0:19:37 lr 0.000063	time 2.2915 (2.2173)	loss 3.4703 (3.0541)	grad_norm 3.1662 (2.7870)	
[2022-01-25 21:16:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][730/1251]	eta 0:19:16 lr 0.000063	time 1.9569 (2.2191)	loss 3.4356 (3.0562)	grad_norm 2.7518 (2.7881)	
[2022-01-25 21:17:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][740/1251]	eta 0:18:56 lr 0.000063	time 2.6887 (2.2242)	loss 3.1773 (3.0558)	grad_norm 2.3301 (2.7888)	
[2022-01-25 21:17:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][750/1251]	eta 0:18:34 lr 0.000063	time 1.9362 (2.2252)	loss 2.4242 (3.0548)	grad_norm 2.8971 (2.7923)	
[2022-01-25 21:17:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][760/1251]	eta 0:18:12 lr 0.000063	time 1.9296 (2.2249)	loss 3.6287 (3.0550)	grad_norm 2.8153 (2.7909)	
[2022-01-25 21:18:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][770/1251]	eta 0:17:49 lr 0.000063	time 1.9461 (2.2235)	loss 3.0562 (3.0556)	grad_norm 2.9563 (2.7919)	
[2022-01-25 21:18:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][780/1251]	eta 0:17:25 lr 0.000062	time 2.5372 (2.2202)	loss 2.7564 (3.0574)	grad_norm 2.7034 (2.7943)	
[2022-01-25 21:18:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][790/1251]	eta 0:17:02 lr 0.000062	time 2.0520 (2.2173)	loss 3.5807 (3.0551)	grad_norm 2.9602 (2.7938)	
[2022-01-25 21:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][800/1251]	eta 0:16:39 lr 0.000062	time 1.9013 (2.2166)	loss 3.4850 (3.0540)	grad_norm 2.5570 (2.7923)	
[2022-01-25 21:19:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][810/1251]	eta 0:16:17 lr 0.000062	time 2.6627 (2.2174)	loss 3.5224 (3.0547)	grad_norm 3.0238 (2.7911)	
[2022-01-25 21:19:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][820/1251]	eta 0:15:56 lr 0.000062	time 1.9944 (2.2183)	loss 2.1818 (3.0550)	grad_norm 3.2465 (2.7921)	
[2022-01-25 21:20:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][830/1251]	eta 0:15:34 lr 0.000062	time 2.2746 (2.2192)	loss 3.4629 (3.0554)	grad_norm 2.9110 (2.7913)	
[2022-01-25 21:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][840/1251]	eta 0:15:11 lr 0.000062	time 1.6862 (2.2176)	loss 3.5158 (3.0550)	grad_norm 2.4568 (2.7904)	
[2022-01-25 21:21:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][850/1251]	eta 0:14:49 lr 0.000062	time 2.6134 (2.2175)	loss 2.8020 (3.0553)	grad_norm 2.6276 (2.7900)	
[2022-01-25 21:21:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][860/1251]	eta 0:14:26 lr 0.000062	time 2.0880 (2.2172)	loss 3.2885 (3.0554)	grad_norm 2.6709 (2.7889)	
[2022-01-25 21:21:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][870/1251]	eta 0:14:04 lr 0.000062	time 2.4714 (2.2171)	loss 3.0140 (3.0532)	grad_norm 2.6837 (2.7857)	
[2022-01-25 21:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][880/1251]	eta 0:13:42 lr 0.000062	time 1.9061 (2.2163)	loss 2.7166 (3.0532)	grad_norm 2.5962 (2.7871)	
[2022-01-25 21:22:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][890/1251]	eta 0:13:21 lr 0.000062	time 3.3708 (2.2194)	loss 3.2239 (3.0537)	grad_norm 3.1390 (2.7864)	
[2022-01-25 21:22:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][900/1251]	eta 0:12:59 lr 0.000062	time 1.8329 (2.2207)	loss 3.1149 (3.0541)	grad_norm 2.9533 (2.7861)	
[2022-01-25 21:23:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][910/1251]	eta 0:12:37 lr 0.000062	time 2.2412 (2.2206)	loss 3.1962 (3.0556)	grad_norm 3.2031 (2.7859)	
[2022-01-25 21:23:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][920/1251]	eta 0:12:14 lr 0.000062	time 2.0292 (2.2185)	loss 2.7490 (3.0564)	grad_norm 2.7542 (2.7850)	
[2022-01-25 21:24:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][930/1251]	eta 0:11:51 lr 0.000062	time 1.9195 (2.2164)	loss 3.1669 (3.0570)	grad_norm 2.7087 (2.7912)	
[2022-01-25 21:24:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][940/1251]	eta 0:11:28 lr 0.000062	time 1.6208 (2.2137)	loss 3.1672 (3.0583)	grad_norm 2.6811 (2.7918)	
[2022-01-25 21:24:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][950/1251]	eta 0:11:06 lr 0.000062	time 2.3686 (2.2127)	loss 2.8674 (3.0597)	grad_norm 2.6108 (2.7906)	
[2022-01-25 21:25:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][960/1251]	eta 0:10:43 lr 0.000062	time 1.7459 (2.2117)	loss 2.5540 (3.0599)	grad_norm 2.4792 (2.7887)	
[2022-01-25 21:25:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][970/1251]	eta 0:10:21 lr 0.000062	time 1.6817 (2.2131)	loss 3.2239 (3.0622)	grad_norm 2.6169 (2.7882)	
[2022-01-25 21:25:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][980/1251]	eta 0:10:00 lr 0.000062	time 2.6873 (2.2163)	loss 3.7101 (3.0637)	grad_norm 2.2923 (2.7873)	
[2022-01-25 21:26:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][990/1251]	eta 0:09:38 lr 0.000062	time 1.8239 (2.2180)	loss 3.1964 (3.0618)	grad_norm 3.0771 (2.7875)	
[2022-01-25 21:26:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1000/1251]	eta 0:09:16 lr 0.000062	time 1.9233 (2.2182)	loss 2.2018 (3.0609)	grad_norm 2.7658 (2.7858)	
[2022-01-25 21:26:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1010/1251]	eta 0:08:54 lr 0.000062	time 1.5695 (2.2159)	loss 2.6999 (3.0610)	grad_norm 2.5007 (2.7838)	
[2022-01-25 21:27:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1020/1251]	eta 0:08:31 lr 0.000062	time 1.8379 (2.2127)	loss 3.2864 (3.0611)	grad_norm 2.7455 (2.7855)	
[2022-01-25 21:27:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1030/1251]	eta 0:08:08 lr 0.000062	time 1.9344 (2.2106)	loss 3.5218 (3.0609)	grad_norm 3.2266 (2.7855)	
[2022-01-25 21:27:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1040/1251]	eta 0:07:45 lr 0.000062	time 1.7754 (2.2083)	loss 3.5759 (3.0605)	grad_norm 2.5348 (2.7850)	
[2022-01-25 21:28:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1050/1251]	eta 0:07:23 lr 0.000062	time 1.8715 (2.2063)	loss 3.3248 (3.0615)	grad_norm 2.8975 (2.7842)	
[2022-01-25 21:28:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1060/1251]	eta 0:07:01 lr 0.000062	time 2.2403 (2.2057)	loss 2.9825 (3.0614)	grad_norm 3.1780 (2.7874)	
[2022-01-25 21:29:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1070/1251]	eta 0:06:39 lr 0.000062	time 2.6235 (2.2063)	loss 3.0477 (3.0617)	grad_norm 2.4019 (2.7852)	
[2022-01-25 21:29:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1080/1251]	eta 0:06:18 lr 0.000062	time 3.5713 (2.2107)	loss 2.1244 (3.0597)	grad_norm 2.6961 (2.7843)	
[2022-01-25 21:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1090/1251]	eta 0:05:56 lr 0.000062	time 2.7611 (2.2135)	loss 3.0136 (3.0625)	grad_norm 2.8322 (2.7834)	
[2022-01-25 21:30:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1100/1251]	eta 0:05:34 lr 0.000062	time 2.0742 (2.2166)	loss 3.5449 (3.0617)	grad_norm 2.5132 (2.7840)	
[2022-01-25 21:30:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1110/1251]	eta 0:05:12 lr 0.000062	time 1.8203 (2.2168)	loss 2.5474 (3.0609)	grad_norm 3.0116 (2.7836)	
[2022-01-25 21:31:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1120/1251]	eta 0:04:50 lr 0.000062	time 2.8343 (2.2167)	loss 3.3935 (3.0622)	grad_norm 2.6313 (2.7821)	
[2022-01-25 21:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1130/1251]	eta 0:04:27 lr 0.000062	time 2.0584 (2.2142)	loss 3.4828 (3.0642)	grad_norm 2.6481 (2.7818)	
[2022-01-25 21:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1140/1251]	eta 0:04:05 lr 0.000062	time 2.5276 (2.2127)	loss 2.5755 (3.0654)	grad_norm 2.7042 (2.7811)	
[2022-01-25 21:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1150/1251]	eta 0:03:43 lr 0.000062	time 2.0373 (2.2124)	loss 3.4866 (3.0646)	grad_norm 2.5570 (2.7804)	
[2022-01-25 21:32:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1160/1251]	eta 0:03:21 lr 0.000062	time 3.5768 (2.2137)	loss 2.6688 (3.0647)	grad_norm 2.4683 (2.7800)	
[2022-01-25 21:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1170/1251]	eta 0:02:59 lr 0.000062	time 1.8954 (2.2139)	loss 3.2028 (3.0660)	grad_norm 2.7781 (2.7823)	
[2022-01-25 21:33:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1180/1251]	eta 0:02:37 lr 0.000062	time 2.2679 (2.2137)	loss 3.4649 (3.0676)	grad_norm 3.1911 (2.7830)	
[2022-01-25 21:33:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1190/1251]	eta 0:02:14 lr 0.000062	time 1.8914 (2.2120)	loss 2.3704 (3.0690)	grad_norm 2.5421 (2.7849)	
[2022-01-25 21:33:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1200/1251]	eta 0:01:52 lr 0.000062	time 2.5447 (2.2100)	loss 3.1054 (3.0683)	grad_norm 2.5982 (2.7845)	
[2022-01-25 21:34:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1210/1251]	eta 0:01:30 lr 0.000062	time 1.8860 (2.2095)	loss 3.4453 (3.0680)	grad_norm 2.8087 (2.7837)	
[2022-01-25 21:34:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1220/1251]	eta 0:01:08 lr 0.000062	time 2.4252 (2.2089)	loss 2.3057 (3.0674)	grad_norm 2.6343 (2.7827)	
[2022-01-25 21:34:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1230/1251]	eta 0:00:46 lr 0.000062	time 2.1061 (2.2080)	loss 2.8402 (3.0677)	grad_norm 2.4472 (2.7814)	
[2022-01-25 21:35:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1240/1251]	eta 0:00:24 lr 0.000062	time 2.8787 (2.2088)	loss 3.2947 (3.0676)	grad_norm 2.5243 (2.7810)	
[2022-01-25 21:35:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [255/300][1250/1251]	eta 0:00:02 lr 0.000062	time 1.1686 (2.2038)	loss 3.2375 (3.0693)	grad_norm 2.4003 (2.7799)	
[2022-01-25 21:35:34 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 255 training takes 0:45:57
[2022-01-25 21:35:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.026 (19.026)	Loss 0.8877 (0.8877)	Acc@1 79.004 (79.004)	Acc@5 94.922 (94.922)	
[2022-01-25 21:36:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.976 (3.485)	Loss 0.9401 (0.8443)	Acc@1 77.539 (80.256)	Acc@5 95.117 (95.286)	
[2022-01-25 21:36:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.635 (2.650)	Loss 0.8761 (0.8414)	Acc@1 79.688 (80.339)	Acc@5 94.531 (95.196)	
[2022-01-25 21:36:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.602 (2.277)	Loss 0.7854 (0.8407)	Acc@1 81.250 (80.349)	Acc@5 95.703 (95.196)	
[2022-01-25 21:37:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.258 (2.193)	Loss 0.7920 (0.8336)	Acc@1 79.688 (80.454)	Acc@5 95.898 (95.289)	
[2022-01-25 21:37:11 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.494 Acc@5 95.288
[2022-01-25 21:37:11 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.5%
[2022-01-25 21:37:11 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.49%
[2022-01-25 21:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][0/1251]	eta 7:08:40 lr 0.000062	time 20.5602 (20.5602)	loss 3.3498 (3.3498)	grad_norm 3.4109 (3.4109)	
[2022-01-25 21:37:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][10/1251]	eta 1:24:04 lr 0.000062	time 3.0941 (4.0646)	loss 3.0650 (3.2037)	grad_norm 2.6466 (2.6679)	
[2022-01-25 21:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][20/1251]	eta 1:05:38 lr 0.000062	time 1.9986 (3.1997)	loss 2.2073 (3.1554)	grad_norm 2.4280 (2.6848)	
[2022-01-25 21:38:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][30/1251]	eta 0:58:45 lr 0.000062	time 1.3216 (2.8877)	loss 3.3629 (3.1928)	grad_norm 2.9331 (2.7826)	
[2022-01-25 21:39:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][40/1251]	eta 0:55:18 lr 0.000062	time 3.3276 (2.7406)	loss 3.2309 (3.1602)	grad_norm 2.5927 (2.8520)	
[2022-01-25 21:39:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][50/1251]	eta 0:53:59 lr 0.000062	time 2.0991 (2.6973)	loss 2.7641 (3.0668)	grad_norm 2.7761 (2.8137)	
[2022-01-25 21:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][60/1251]	eta 0:51:12 lr 0.000062	time 1.9690 (2.5798)	loss 1.9896 (3.0340)	grad_norm 3.2704 (2.8078)	
[2022-01-25 21:40:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][70/1251]	eta 0:49:16 lr 0.000061	time 1.5529 (2.5033)	loss 2.5930 (3.0342)	grad_norm 2.8451 (2.8072)	
[2022-01-25 21:40:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][80/1251]	eta 0:48:18 lr 0.000061	time 3.0280 (2.4754)	loss 3.2437 (3.0488)	grad_norm 2.9023 (2.7909)	
[2022-01-25 21:40:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][90/1251]	eta 0:47:41 lr 0.000061	time 1.9168 (2.4643)	loss 3.0942 (3.0345)	grad_norm 2.6660 (2.7933)	
[2022-01-25 21:41:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][100/1251]	eta 0:46:51 lr 0.000061	time 2.3369 (2.4430)	loss 3.4901 (3.0140)	grad_norm 2.7849 (2.8007)	
[2022-01-25 21:41:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][110/1251]	eta 0:45:54 lr 0.000061	time 1.8930 (2.4138)	loss 3.2207 (3.0194)	grad_norm 2.8919 (2.7860)	
[2022-01-25 21:42:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][120/1251]	eta 0:45:00 lr 0.000061	time 2.7634 (2.3876)	loss 3.7962 (3.0149)	grad_norm 2.7123 (2.7908)	
[2022-01-25 21:42:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][130/1251]	eta 0:44:03 lr 0.000061	time 2.1198 (2.3584)	loss 3.6805 (3.0113)	grad_norm 2.9045 (2.7864)	
[2022-01-25 21:42:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][140/1251]	eta 0:43:19 lr 0.000061	time 1.5801 (2.3401)	loss 3.1412 (3.0175)	grad_norm 2.6378 (2.7797)	
[2022-01-25 21:43:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][150/1251]	eta 0:42:39 lr 0.000061	time 1.9009 (2.3251)	loss 2.9768 (3.0292)	grad_norm 2.4961 (2.7850)	
[2022-01-25 21:43:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][160/1251]	eta 0:42:10 lr 0.000061	time 2.9920 (2.3198)	loss 3.7186 (3.0359)	grad_norm 2.5152 (2.7728)	
[2022-01-25 21:43:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][170/1251]	eta 0:41:53 lr 0.000061	time 2.1952 (2.3254)	loss 2.4703 (3.0338)	grad_norm 2.5869 (2.7677)	
[2022-01-25 21:44:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][180/1251]	eta 0:41:32 lr 0.000061	time 1.7062 (2.3273)	loss 3.0662 (3.0351)	grad_norm 3.1735 (2.7771)	
[2022-01-25 21:44:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][190/1251]	eta 0:41:05 lr 0.000061	time 1.8650 (2.3235)	loss 3.4157 (3.0362)	grad_norm 2.7071 (2.7747)	
[2022-01-25 21:44:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][200/1251]	eta 0:40:31 lr 0.000061	time 1.9342 (2.3139)	loss 2.3742 (3.0391)	grad_norm 2.5933 (2.7746)	
[2022-01-25 21:45:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][210/1251]	eta 0:40:03 lr 0.000061	time 2.6057 (2.3093)	loss 2.1501 (3.0298)	grad_norm 2.5906 (2.7663)	
[2022-01-25 21:45:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][220/1251]	eta 0:39:35 lr 0.000061	time 1.6627 (2.3045)	loss 3.2242 (3.0335)	grad_norm 2.9647 (2.7655)	
[2022-01-25 21:46:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][230/1251]	eta 0:39:02 lr 0.000061	time 1.7226 (2.2940)	loss 1.9535 (3.0409)	grad_norm 2.8808 (2.7624)	
[2022-01-25 21:46:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][240/1251]	eta 0:38:32 lr 0.000061	time 2.3214 (2.2872)	loss 3.4143 (3.0389)	grad_norm 2.5285 (2.7663)	
[2022-01-25 21:46:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][250/1251]	eta 0:38:05 lr 0.000061	time 2.5527 (2.2832)	loss 2.6193 (3.0257)	grad_norm 2.7132 (2.7643)	
[2022-01-25 21:47:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][260/1251]	eta 0:37:37 lr 0.000061	time 2.0200 (2.2784)	loss 2.9688 (3.0322)	grad_norm 2.2212 (2.7593)	
[2022-01-25 21:47:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][270/1251]	eta 0:37:15 lr 0.000061	time 2.4582 (2.2784)	loss 2.3268 (3.0260)	grad_norm 2.5906 (2.7627)	
[2022-01-25 21:47:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][280/1251]	eta 0:36:48 lr 0.000061	time 2.3551 (2.2749)	loss 3.3816 (3.0231)	grad_norm 2.6605 (2.7571)	
[2022-01-25 21:48:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][290/1251]	eta 0:36:22 lr 0.000061	time 2.9478 (2.2706)	loss 2.1935 (3.0206)	grad_norm 2.7265 (2.7638)	
[2022-01-25 21:48:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][300/1251]	eta 0:35:52 lr 0.000061	time 1.6035 (2.2636)	loss 3.0476 (3.0279)	grad_norm 2.3393 (2.7697)	
[2022-01-25 21:48:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][310/1251]	eta 0:35:29 lr 0.000061	time 2.4467 (2.2635)	loss 3.6317 (3.0302)	grad_norm 3.4816 (2.7685)	
[2022-01-25 21:49:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][320/1251]	eta 0:35:03 lr 0.000061	time 2.6413 (2.2599)	loss 2.3008 (3.0340)	grad_norm 2.9010 (2.7674)	
[2022-01-25 21:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][330/1251]	eta 0:34:40 lr 0.000061	time 2.6004 (2.2590)	loss 3.5350 (3.0416)	grad_norm 2.8805 (2.7918)	
[2022-01-25 21:50:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][340/1251]	eta 0:34:16 lr 0.000061	time 1.6012 (2.2573)	loss 3.6096 (3.0461)	grad_norm 2.7904 (2.7913)	
[2022-01-25 21:50:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][350/1251]	eta 0:33:52 lr 0.000061	time 2.2685 (2.2554)	loss 3.8346 (3.0530)	grad_norm 2.4433 (2.7882)	
[2022-01-25 21:50:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][360/1251]	eta 0:33:25 lr 0.000061	time 1.8981 (2.2508)	loss 3.3786 (3.0550)	grad_norm 2.8148 (2.7863)	
[2022-01-25 21:51:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][370/1251]	eta 0:33:04 lr 0.000061	time 3.5375 (2.2522)	loss 3.2812 (3.0552)	grad_norm 2.6983 (2.7893)	
[2022-01-25 21:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][380/1251]	eta 0:32:37 lr 0.000061	time 1.9009 (2.2470)	loss 3.2508 (3.0644)	grad_norm 2.8319 (2.7883)	
[2022-01-25 21:51:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][390/1251]	eta 0:32:12 lr 0.000061	time 2.2493 (2.2449)	loss 3.1450 (3.0612)	grad_norm 2.5353 (2.7924)	
[2022-01-25 21:52:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][400/1251]	eta 0:31:46 lr 0.000061	time 2.0458 (2.2404)	loss 2.4279 (3.0552)	grad_norm 2.4937 (2.7942)	
[2022-01-25 21:52:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][410/1251]	eta 0:31:24 lr 0.000061	time 3.0474 (2.2408)	loss 1.8877 (3.0579)	grad_norm 3.1813 (2.7966)	
[2022-01-25 21:52:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][420/1251]	eta 0:31:01 lr 0.000061	time 1.7887 (2.2403)	loss 3.4914 (3.0559)	grad_norm 2.5109 (2.7971)	
[2022-01-25 21:53:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][430/1251]	eta 0:30:38 lr 0.000061	time 2.8133 (2.2394)	loss 3.4307 (3.0580)	grad_norm 3.6479 (2.7977)	
[2022-01-25 21:53:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][440/1251]	eta 0:30:15 lr 0.000061	time 2.4234 (2.2387)	loss 2.8629 (3.0581)	grad_norm 3.2250 (2.7966)	
[2022-01-25 21:54:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][450/1251]	eta 0:29:51 lr 0.000061	time 2.8999 (2.2362)	loss 2.9199 (3.0606)	grad_norm 2.6221 (2.7942)	
[2022-01-25 21:54:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][460/1251]	eta 0:29:27 lr 0.000061	time 2.0352 (2.2340)	loss 3.4454 (3.0560)	grad_norm 2.7336 (2.7926)	
[2022-01-25 21:54:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][470/1251]	eta 0:29:04 lr 0.000061	time 2.1964 (2.2331)	loss 3.5030 (3.0628)	grad_norm 3.0455 (2.7936)	
[2022-01-25 21:55:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][480/1251]	eta 0:28:41 lr 0.000061	time 2.1271 (2.2333)	loss 3.3222 (3.0632)	grad_norm 3.4467 (2.7946)	
[2022-01-25 21:55:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][490/1251]	eta 0:28:19 lr 0.000061	time 2.5749 (2.2337)	loss 3.1166 (3.0619)	grad_norm 2.5615 (2.7949)	
[2022-01-25 21:55:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][500/1251]	eta 0:27:55 lr 0.000061	time 1.8203 (2.2306)	loss 3.3869 (3.0654)	grad_norm 3.2072 (2.8090)	
[2022-01-25 21:56:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][510/1251]	eta 0:27:29 lr 0.000061	time 1.9551 (2.2261)	loss 2.1670 (3.0643)	grad_norm 2.6235 (2.8085)	
[2022-01-25 21:56:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][520/1251]	eta 0:27:06 lr 0.000061	time 2.4629 (2.2251)	loss 3.3544 (3.0628)	grad_norm 2.7949 (2.8103)	
[2022-01-25 21:56:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][530/1251]	eta 0:26:45 lr 0.000061	time 1.9590 (2.2266)	loss 3.6209 (3.0657)	grad_norm 2.9736 (2.8153)	
[2022-01-25 21:57:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][540/1251]	eta 0:26:23 lr 0.000061	time 2.1958 (2.2270)	loss 3.4479 (3.0633)	grad_norm 2.7134 (2.8249)	
[2022-01-25 21:57:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][550/1251]	eta 0:25:59 lr 0.000061	time 2.2695 (2.2252)	loss 3.2442 (3.0579)	grad_norm 2.7439 (2.8255)	
[2022-01-25 21:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][560/1251]	eta 0:25:37 lr 0.000061	time 2.4543 (2.2253)	loss 2.1059 (3.0551)	grad_norm 2.6466 (2.8240)	
[2022-01-25 21:58:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][570/1251]	eta 0:25:16 lr 0.000061	time 2.0329 (2.2274)	loss 3.7543 (3.0507)	grad_norm 3.0453 (2.8238)	
[2022-01-25 21:58:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][580/1251]	eta 0:24:53 lr 0.000061	time 2.6043 (2.2265)	loss 2.8884 (3.0526)	grad_norm 2.9874 (2.8241)	
[2022-01-25 21:59:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][590/1251]	eta 0:24:29 lr 0.000061	time 1.8666 (2.2231)	loss 3.3458 (3.0547)	grad_norm 2.6696 (2.8216)	
[2022-01-25 21:59:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][600/1251]	eta 0:24:05 lr 0.000061	time 2.9468 (2.2208)	loss 3.7104 (3.0556)	grad_norm 2.6605 (2.8217)	
[2022-01-25 21:59:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][610/1251]	eta 0:23:42 lr 0.000061	time 2.1025 (2.2198)	loss 3.3490 (3.0556)	grad_norm 2.6647 (2.8208)	
[2022-01-25 22:00:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][620/1251]	eta 0:23:20 lr 0.000060	time 2.4267 (2.2198)	loss 2.7017 (3.0589)	grad_norm 2.4624 (2.8190)	
[2022-01-25 22:00:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][630/1251]	eta 0:22:58 lr 0.000060	time 2.0981 (2.2204)	loss 3.3569 (3.0622)	grad_norm 3.0214 (2.8167)	
[2022-01-25 22:00:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][640/1251]	eta 0:22:35 lr 0.000060	time 1.6082 (2.2184)	loss 3.4739 (3.0579)	grad_norm 2.6525 (2.8126)	
[2022-01-25 22:01:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][650/1251]	eta 0:22:12 lr 0.000060	time 1.8643 (2.2167)	loss 3.6966 (3.0561)	grad_norm 3.4676 (2.8100)	
[2022-01-25 22:01:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][660/1251]	eta 0:21:50 lr 0.000060	time 2.6788 (2.2180)	loss 2.8252 (3.0530)	grad_norm 2.7178 (2.8094)	
[2022-01-25 22:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][670/1251]	eta 0:21:28 lr 0.000060	time 2.3330 (2.2182)	loss 2.1997 (3.0522)	grad_norm 2.3534 (2.8068)	
[2022-01-25 22:02:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][680/1251]	eta 0:21:06 lr 0.000060	time 1.7074 (2.2173)	loss 3.5164 (3.0545)	grad_norm 2.2057 (2.8065)	
[2022-01-25 22:02:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][690/1251]	eta 0:20:43 lr 0.000060	time 1.8836 (2.2157)	loss 2.1882 (3.0548)	grad_norm 5.4129 (2.8078)	
[2022-01-25 22:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][700/1251]	eta 0:20:21 lr 0.000060	time 2.4742 (2.2164)	loss 3.9675 (3.0565)	grad_norm 2.9551 (2.8076)	
[2022-01-25 22:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][710/1251]	eta 0:19:58 lr 0.000060	time 1.8593 (2.2157)	loss 3.1783 (3.0578)	grad_norm 2.8573 (2.8118)	
[2022-01-25 22:03:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][720/1251]	eta 0:19:36 lr 0.000060	time 2.0879 (2.2156)	loss 3.1891 (3.0532)	grad_norm 3.4257 (2.8095)	
[2022-01-25 22:04:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][730/1251]	eta 0:19:13 lr 0.000060	time 2.4820 (2.2144)	loss 3.4895 (3.0540)	grad_norm 2.2903 (2.8129)	
[2022-01-25 22:04:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][740/1251]	eta 0:18:50 lr 0.000060	time 2.1179 (2.2131)	loss 3.4149 (3.0560)	grad_norm 2.4875 (2.8124)	
[2022-01-25 22:04:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][750/1251]	eta 0:18:29 lr 0.000060	time 2.7746 (2.2139)	loss 2.5125 (3.0562)	grad_norm 2.6394 (2.8182)	
[2022-01-25 22:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][760/1251]	eta 0:18:06 lr 0.000060	time 1.8452 (2.2132)	loss 2.2390 (3.0549)	grad_norm 2.6578 (2.8209)	
[2022-01-25 22:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][770/1251]	eta 0:17:44 lr 0.000060	time 2.4805 (2.2123)	loss 2.9333 (3.0564)	grad_norm 3.4400 (2.8219)	
[2022-01-25 22:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][780/1251]	eta 0:17:20 lr 0.000060	time 1.8140 (2.2101)	loss 3.5389 (3.0596)	grad_norm 2.9005 (2.8226)	
[2022-01-25 22:06:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][790/1251]	eta 0:17:00 lr 0.000060	time 2.3188 (2.2126)	loss 3.4483 (3.0585)	grad_norm 2.5736 (2.8230)	
[2022-01-25 22:06:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][800/1251]	eta 0:16:37 lr 0.000060	time 1.9738 (2.2122)	loss 2.6795 (3.0591)	grad_norm 2.8387 (2.8229)	
[2022-01-25 22:07:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][810/1251]	eta 0:16:15 lr 0.000060	time 2.1675 (2.2113)	loss 3.4956 (3.0572)	grad_norm 2.6227 (2.8222)	
[2022-01-25 22:07:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][820/1251]	eta 0:15:51 lr 0.000060	time 1.5992 (2.2085)	loss 3.5218 (3.0594)	grad_norm 2.7194 (2.8241)	
[2022-01-25 22:07:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][830/1251]	eta 0:15:29 lr 0.000060	time 1.8939 (2.2089)	loss 3.3211 (3.0587)	grad_norm 2.5424 (2.8220)	
[2022-01-25 22:08:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][840/1251]	eta 0:15:07 lr 0.000060	time 1.7015 (2.2071)	loss 3.1476 (3.0595)	grad_norm 2.6832 (2.8203)	
[2022-01-25 22:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][850/1251]	eta 0:14:45 lr 0.000060	time 2.4348 (2.2086)	loss 2.4286 (3.0574)	grad_norm 3.0530 (2.8182)	
[2022-01-25 22:08:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][860/1251]	eta 0:14:23 lr 0.000060	time 1.6369 (2.2082)	loss 3.2996 (3.0600)	grad_norm 2.9827 (2.8174)	
[2022-01-25 22:09:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][870/1251]	eta 0:14:01 lr 0.000060	time 1.8558 (2.2084)	loss 2.3520 (3.0595)	grad_norm 2.5222 (2.8159)	
[2022-01-25 22:09:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][880/1251]	eta 0:13:38 lr 0.000060	time 1.8487 (2.2065)	loss 3.3659 (3.0605)	grad_norm 3.0735 (2.8182)	
[2022-01-25 22:09:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][890/1251]	eta 0:13:16 lr 0.000060	time 2.3912 (2.2074)	loss 2.9937 (3.0606)	grad_norm 2.9840 (2.8192)	
[2022-01-25 22:10:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][900/1251]	eta 0:12:54 lr 0.000060	time 2.0122 (2.2076)	loss 3.6103 (3.0604)	grad_norm 2.7305 (2.8200)	
[2022-01-25 22:10:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][910/1251]	eta 0:12:33 lr 0.000060	time 2.5396 (2.2095)	loss 2.7335 (3.0595)	grad_norm 2.6045 (2.8177)	
[2022-01-25 22:11:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][920/1251]	eta 0:12:11 lr 0.000060	time 2.1951 (2.2102)	loss 2.8309 (3.0548)	grad_norm 3.3046 (2.8181)	
[2022-01-25 22:11:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][930/1251]	eta 0:11:49 lr 0.000060	time 1.8054 (2.2100)	loss 3.3502 (3.0548)	grad_norm 3.0882 (2.8181)	
[2022-01-25 22:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][940/1251]	eta 0:11:27 lr 0.000060	time 2.0631 (2.2100)	loss 3.7128 (3.0556)	grad_norm 2.7577 (2.8168)	
[2022-01-25 22:12:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][950/1251]	eta 0:11:04 lr 0.000060	time 1.7153 (2.2075)	loss 2.9232 (3.0563)	grad_norm 2.6585 (2.8164)	
[2022-01-25 22:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][960/1251]	eta 0:10:41 lr 0.000060	time 2.0456 (2.2049)	loss 3.2796 (3.0564)	grad_norm 2.5041 (2.8155)	
[2022-01-25 22:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][970/1251]	eta 0:10:19 lr 0.000060	time 2.5410 (2.2047)	loss 3.4344 (3.0572)	grad_norm 3.2659 (2.8134)	
[2022-01-25 22:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][980/1251]	eta 0:09:57 lr 0.000060	time 2.8896 (2.2062)	loss 3.3540 (3.0582)	grad_norm 2.2391 (2.8114)	
[2022-01-25 22:13:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][990/1251]	eta 0:09:35 lr 0.000060	time 2.2240 (2.2056)	loss 3.7916 (3.0587)	grad_norm 3.7220 (2.8120)	
[2022-01-25 22:13:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1000/1251]	eta 0:09:13 lr 0.000060	time 2.6220 (2.2060)	loss 3.2147 (3.0594)	grad_norm 2.4623 (2.8123)	
[2022-01-25 22:14:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1010/1251]	eta 0:08:51 lr 0.000060	time 3.4201 (2.2068)	loss 2.6706 (3.0594)	grad_norm 2.9505 (2.8120)	
[2022-01-25 22:14:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1020/1251]	eta 0:08:29 lr 0.000060	time 1.5798 (2.2058)	loss 3.0237 (3.0607)	grad_norm 2.5359 (2.8129)	
[2022-01-25 22:15:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1030/1251]	eta 0:08:07 lr 0.000060	time 2.2059 (2.2050)	loss 3.8073 (3.0616)	grad_norm 3.1108 (2.8127)	
[2022-01-25 22:15:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1040/1251]	eta 0:07:45 lr 0.000060	time 2.5289 (2.2053)	loss 3.7449 (3.0613)	grad_norm 3.3264 (2.8128)	
[2022-01-25 22:15:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1050/1251]	eta 0:07:23 lr 0.000060	time 2.7522 (2.2057)	loss 3.3627 (3.0619)	grad_norm 2.9134 (2.8115)	
[2022-01-25 22:16:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1060/1251]	eta 0:07:01 lr 0.000060	time 1.7711 (2.2044)	loss 2.4073 (3.0612)	grad_norm 2.4812 (2.8120)	
[2022-01-25 22:16:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1070/1251]	eta 0:06:38 lr 0.000060	time 2.9563 (2.2038)	loss 2.6319 (3.0606)	grad_norm 2.7152 (2.8109)	
[2022-01-25 22:16:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1080/1251]	eta 0:06:16 lr 0.000060	time 2.2020 (2.2036)	loss 3.3148 (3.0624)	grad_norm 2.4986 (2.8107)	
[2022-01-25 22:17:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1090/1251]	eta 0:05:54 lr 0.000060	time 2.9060 (2.2030)	loss 3.2195 (3.0635)	grad_norm 2.7498 (2.8086)	
[2022-01-25 22:17:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1100/1251]	eta 0:05:32 lr 0.000060	time 2.2755 (2.2023)	loss 3.3838 (3.0651)	grad_norm 2.5032 (2.8068)	
[2022-01-25 22:17:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1110/1251]	eta 0:05:10 lr 0.000060	time 2.5083 (2.2021)	loss 3.2253 (3.0667)	grad_norm 3.1587 (2.8062)	
[2022-01-25 22:18:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1120/1251]	eta 0:04:48 lr 0.000060	time 1.9851 (2.2021)	loss 3.3079 (3.0655)	grad_norm 2.8352 (2.8060)	
[2022-01-25 22:18:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1130/1251]	eta 0:04:26 lr 0.000060	time 2.7801 (2.2019)	loss 2.1648 (3.0644)	grad_norm 2.7611 (2.8059)	
[2022-01-25 22:19:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1140/1251]	eta 0:04:04 lr 0.000060	time 1.7321 (2.2028)	loss 3.2908 (3.0631)	grad_norm 2.7833 (2.8044)	
[2022-01-25 22:19:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1150/1251]	eta 0:03:42 lr 0.000060	time 1.9865 (2.2024)	loss 3.1552 (3.0619)	grad_norm 2.9303 (2.8051)	
[2022-01-25 22:19:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1160/1251]	eta 0:03:20 lr 0.000060	time 1.6000 (2.2023)	loss 2.8619 (3.0590)	grad_norm 3.5130 (2.8062)	
[2022-01-25 22:20:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1170/1251]	eta 0:02:58 lr 0.000059	time 2.2585 (2.2017)	loss 2.7950 (3.0600)	grad_norm 2.4431 (2.8051)	
[2022-01-25 22:20:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1180/1251]	eta 0:02:36 lr 0.000059	time 2.2210 (2.2027)	loss 3.0411 (3.0614)	grad_norm 2.5943 (2.8046)	
[2022-01-25 22:20:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1190/1251]	eta 0:02:14 lr 0.000059	time 2.1071 (2.2023)	loss 2.7791 (3.0623)	grad_norm 2.4764 (2.8042)	
[2022-01-25 22:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1200/1251]	eta 0:01:52 lr 0.000059	time 1.7409 (2.2024)	loss 3.3948 (3.0638)	grad_norm 2.8022 (2.8027)	
[2022-01-25 22:21:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1210/1251]	eta 0:01:30 lr 0.000059	time 1.8925 (2.2019)	loss 3.3051 (3.0643)	grad_norm 2.3280 (2.8018)	
[2022-01-25 22:21:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1220/1251]	eta 0:01:08 lr 0.000059	time 1.6193 (2.2018)	loss 2.7911 (3.0647)	grad_norm 4.1609 (2.8011)	
[2022-01-25 22:22:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1230/1251]	eta 0:00:46 lr 0.000059	time 1.9532 (2.2010)	loss 3.9477 (3.0658)	grad_norm 2.7069 (2.8023)	
[2022-01-25 22:22:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1240/1251]	eta 0:00:24 lr 0.000059	time 1.7032 (2.2014)	loss 2.2105 (3.0665)	grad_norm 2.6403 (2.8022)	
[2022-01-25 22:22:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [256/300][1250/1251]	eta 0:00:02 lr 0.000059	time 1.1774 (2.1956)	loss 2.4228 (3.0666)	grad_norm 2.5497 (2.8015)	
[2022-01-25 22:22:58 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 256 training takes 0:45:47
[2022-01-25 22:23:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.601 (18.601)	Loss 0.7585 (0.7585)	Acc@1 82.324 (82.324)	Acc@5 96.289 (96.289)	
[2022-01-25 22:23:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.873 (3.501)	Loss 0.8824 (0.8289)	Acc@1 79.395 (80.460)	Acc@5 94.922 (95.277)	
[2022-01-25 22:23:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.530 (2.709)	Loss 0.8237 (0.8314)	Acc@1 81.738 (80.534)	Acc@5 95.117 (95.257)	
[2022-01-25 22:24:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.017 (2.428)	Loss 0.8319 (0.8334)	Acc@1 80.664 (80.570)	Acc@5 96.484 (95.316)	
[2022-01-25 22:24:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.733 (2.184)	Loss 0.8619 (0.8339)	Acc@1 80.176 (80.585)	Acc@5 95.410 (95.312)	
[2022-01-25 22:24:36 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.578 Acc@5 95.310
[2022-01-25 22:24:36 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.6%
[2022-01-25 22:24:36 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.58%
[2022-01-25 22:24:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][0/1251]	eta 7:40:16 lr 0.000059	time 22.0752 (22.0752)	loss 3.3979 (3.3979)	grad_norm 2.5734 (2.5734)	
[2022-01-25 22:25:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][10/1251]	eta 1:26:11 lr 0.000059	time 2.2003 (4.1675)	loss 3.4728 (3.1001)	grad_norm 2.8384 (2.5894)	
[2022-01-25 22:25:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][20/1251]	eta 1:07:14 lr 0.000059	time 2.0865 (3.2772)	loss 2.5553 (2.9978)	grad_norm 2.6069 (2.6192)	
[2022-01-25 22:26:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][30/1251]	eta 0:59:11 lr 0.000059	time 1.5380 (2.9083)	loss 3.5777 (3.0399)	grad_norm 3.1029 (2.7639)	
[2022-01-25 22:26:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][40/1251]	eta 0:55:06 lr 0.000059	time 3.6773 (2.7307)	loss 3.0363 (3.0296)	grad_norm 2.5033 (2.7635)	
[2022-01-25 22:26:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][50/1251]	eta 0:52:15 lr 0.000059	time 1.4696 (2.6110)	loss 3.3375 (3.0469)	grad_norm 3.0263 (2.7762)	
[2022-01-25 22:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][60/1251]	eta 0:50:04 lr 0.000059	time 2.3345 (2.5230)	loss 3.4585 (3.0466)	grad_norm 2.3988 (2.8578)	
[2022-01-25 22:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][70/1251]	eta 0:48:35 lr 0.000059	time 1.6218 (2.4686)	loss 3.5194 (3.0352)	grad_norm 2.8450 (2.8603)	
[2022-01-25 22:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][80/1251]	eta 0:47:43 lr 0.000059	time 2.8271 (2.4457)	loss 3.2471 (3.0679)	grad_norm 3.4193 (2.8726)	
[2022-01-25 22:28:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][90/1251]	eta 0:47:06 lr 0.000059	time 2.5042 (2.4348)	loss 3.3709 (3.0595)	grad_norm 2.5489 (2.8347)	
[2022-01-25 22:28:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][100/1251]	eta 0:46:07 lr 0.000059	time 2.2148 (2.4041)	loss 3.5164 (3.0602)	grad_norm 2.9019 (2.8356)	
[2022-01-25 22:29:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][110/1251]	eta 0:45:15 lr 0.000059	time 1.5516 (2.3799)	loss 3.1804 (3.0503)	grad_norm 2.5673 (2.8154)	
[2022-01-25 22:29:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][120/1251]	eta 0:44:38 lr 0.000059	time 2.8867 (2.3686)	loss 3.5114 (3.0453)	grad_norm 2.9176 (2.8068)	
[2022-01-25 22:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][130/1251]	eta 0:44:01 lr 0.000059	time 1.8149 (2.3568)	loss 3.2992 (3.0488)	grad_norm 3.0793 (2.8039)	
[2022-01-25 22:30:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][140/1251]	eta 0:43:25 lr 0.000059	time 2.1179 (2.3448)	loss 3.2269 (3.0489)	grad_norm 2.9927 (2.7983)	
[2022-01-25 22:30:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][150/1251]	eta 0:42:51 lr 0.000059	time 1.5938 (2.3352)	loss 2.8715 (3.0438)	grad_norm 2.9113 (2.7937)	
[2022-01-25 22:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][160/1251]	eta 0:42:26 lr 0.000059	time 3.4273 (2.3343)	loss 1.9912 (3.0440)	grad_norm 2.6782 (2.7888)	
[2022-01-25 22:31:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][170/1251]	eta 0:41:54 lr 0.000059	time 1.8125 (2.3265)	loss 3.5530 (3.0521)	grad_norm 2.6658 (2.7834)	
[2022-01-25 22:31:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][180/1251]	eta 0:41:19 lr 0.000059	time 1.5965 (2.3155)	loss 3.1762 (3.0493)	grad_norm 2.7480 (2.7783)	
[2022-01-25 22:31:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][190/1251]	eta 0:40:45 lr 0.000059	time 1.4995 (2.3052)	loss 2.5440 (3.0418)	grad_norm 2.4767 (2.7637)	
[2022-01-25 22:32:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][200/1251]	eta 0:40:23 lr 0.000059	time 3.1200 (2.3062)	loss 2.4910 (3.0268)	grad_norm 2.6587 (2.7669)	
[2022-01-25 22:32:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][210/1251]	eta 0:39:51 lr 0.000059	time 1.7868 (2.2977)	loss 3.1677 (3.0375)	grad_norm 2.5812 (2.7764)	
[2022-01-25 22:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][220/1251]	eta 0:39:15 lr 0.000059	time 1.7905 (2.2849)	loss 3.3276 (3.0432)	grad_norm 2.4983 (2.7727)	
[2022-01-25 22:33:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][230/1251]	eta 0:38:43 lr 0.000059	time 1.9105 (2.2759)	loss 3.1075 (3.0414)	grad_norm 2.3474 (2.7756)	
[2022-01-25 22:33:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][240/1251]	eta 0:38:10 lr 0.000059	time 1.7365 (2.2656)	loss 2.7154 (3.0400)	grad_norm 3.5892 (2.7786)	
[2022-01-25 22:34:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][250/1251]	eta 0:37:41 lr 0.000059	time 1.5701 (2.2588)	loss 3.1779 (3.0306)	grad_norm 2.5258 (2.7741)	
[2022-01-25 22:34:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][260/1251]	eta 0:37:18 lr 0.000059	time 2.4640 (2.2587)	loss 2.5466 (3.0329)	grad_norm 2.4792 (2.7810)	
[2022-01-25 22:34:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][270/1251]	eta 0:37:02 lr 0.000059	time 2.3668 (2.2660)	loss 2.5315 (3.0351)	grad_norm 2.5227 (2.7825)	
[2022-01-25 22:35:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][280/1251]	eta 0:36:33 lr 0.000059	time 1.6716 (2.2592)	loss 3.6377 (3.0407)	grad_norm 2.6705 (2.7812)	
[2022-01-25 22:35:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][290/1251]	eta 0:36:10 lr 0.000059	time 2.2170 (2.2582)	loss 3.4435 (3.0397)	grad_norm 4.0514 (2.7868)	
[2022-01-25 22:35:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][300/1251]	eta 0:35:46 lr 0.000059	time 2.7923 (2.2573)	loss 3.3844 (3.0409)	grad_norm 2.8015 (2.7927)	
[2022-01-25 22:36:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][310/1251]	eta 0:35:31 lr 0.000059	time 2.5937 (2.2652)	loss 3.1870 (3.0443)	grad_norm 3.2450 (2.7897)	
[2022-01-25 22:36:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][320/1251]	eta 0:35:05 lr 0.000059	time 1.8715 (2.2618)	loss 2.3417 (3.0432)	grad_norm 2.5314 (2.7826)	
[2022-01-25 22:37:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][330/1251]	eta 0:34:37 lr 0.000059	time 2.0575 (2.2556)	loss 3.0834 (3.0435)	grad_norm 2.5570 (2.7807)	
[2022-01-25 22:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][340/1251]	eta 0:34:09 lr 0.000059	time 2.7008 (2.2493)	loss 3.9905 (3.0419)	grad_norm 2.5609 (2.7794)	
[2022-01-25 22:37:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][350/1251]	eta 0:33:42 lr 0.000059	time 2.1849 (2.2449)	loss 3.2609 (3.0366)	grad_norm 2.5902 (2.7783)	
[2022-01-25 22:38:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][360/1251]	eta 0:33:14 lr 0.000059	time 1.8937 (2.2384)	loss 3.3481 (3.0393)	grad_norm 2.3207 (2.7814)	
[2022-01-25 22:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][370/1251]	eta 0:32:48 lr 0.000059	time 2.2116 (2.2343)	loss 3.0324 (3.0347)	grad_norm 2.1798 (2.7849)	
[2022-01-25 22:38:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][380/1251]	eta 0:32:23 lr 0.000059	time 2.0578 (2.2310)	loss 2.8361 (3.0354)	grad_norm 2.6118 (2.7807)	
[2022-01-25 22:39:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][390/1251]	eta 0:32:00 lr 0.000059	time 2.6735 (2.2301)	loss 3.1488 (3.0344)	grad_norm 2.7725 (2.7786)	
[2022-01-25 22:39:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][400/1251]	eta 0:31:36 lr 0.000059	time 1.8475 (2.2287)	loss 3.4459 (3.0290)	grad_norm 2.7227 (2.7818)	
[2022-01-25 22:39:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][410/1251]	eta 0:31:16 lr 0.000059	time 1.5014 (2.2315)	loss 3.7762 (3.0284)	grad_norm 3.2159 (2.7787)	
[2022-01-25 22:40:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][420/1251]	eta 0:30:57 lr 0.000059	time 2.0985 (2.2354)	loss 2.1373 (3.0285)	grad_norm 2.7965 (2.7856)	
[2022-01-25 22:40:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][430/1251]	eta 0:30:37 lr 0.000059	time 2.8273 (2.2376)	loss 3.4643 (3.0272)	grad_norm 3.2416 (2.7866)	
[2022-01-25 22:41:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][440/1251]	eta 0:30:13 lr 0.000059	time 2.1919 (2.2364)	loss 2.7726 (3.0295)	grad_norm 3.0602 (2.7887)	
[2022-01-25 22:41:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][450/1251]	eta 0:29:48 lr 0.000059	time 1.5873 (2.2327)	loss 3.2574 (3.0310)	grad_norm 3.5582 (2.7895)	
[2022-01-25 22:41:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][460/1251]	eta 0:29:23 lr 0.000059	time 1.5885 (2.2297)	loss 3.8126 (3.0314)	grad_norm 2.9444 (2.7906)	
[2022-01-25 22:42:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][470/1251]	eta 0:29:03 lr 0.000058	time 2.2165 (2.2326)	loss 3.0176 (3.0381)	grad_norm 2.8386 (2.7914)	
[2022-01-25 22:42:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][480/1251]	eta 0:28:40 lr 0.000058	time 1.8931 (2.2310)	loss 3.1490 (3.0376)	grad_norm 2.6245 (2.7909)	
[2022-01-25 22:42:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][490/1251]	eta 0:28:16 lr 0.000058	time 1.5626 (2.2299)	loss 3.2296 (3.0362)	grad_norm 3.4370 (2.7897)	
[2022-01-25 22:43:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][500/1251]	eta 0:27:54 lr 0.000058	time 1.9036 (2.2293)	loss 2.8378 (3.0393)	grad_norm 2.6055 (2.7909)	
[2022-01-25 22:43:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][510/1251]	eta 0:27:35 lr 0.000058	time 2.1153 (2.2340)	loss 3.3584 (3.0409)	grad_norm 2.7702 (2.7916)	
[2022-01-25 22:43:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][520/1251]	eta 0:27:10 lr 0.000058	time 1.9497 (2.2298)	loss 3.1200 (3.0436)	grad_norm 2.4850 (2.7900)	
[2022-01-25 22:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][530/1251]	eta 0:26:45 lr 0.000058	time 1.9262 (2.2273)	loss 3.1762 (3.0426)	grad_norm 2.4632 (2.7927)	
[2022-01-25 22:44:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][540/1251]	eta 0:26:21 lr 0.000058	time 2.0525 (2.2244)	loss 3.1257 (3.0430)	grad_norm 2.7110 (2.7949)	
[2022-01-25 22:45:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][550/1251]	eta 0:25:59 lr 0.000058	time 2.2281 (2.2242)	loss 3.1564 (3.0464)	grad_norm 2.7001 (2.7939)	
[2022-01-25 22:45:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][560/1251]	eta 0:25:35 lr 0.000058	time 1.7105 (2.2224)	loss 2.6169 (3.0479)	grad_norm 3.3780 (2.7949)	
[2022-01-25 22:45:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][570/1251]	eta 0:25:10 lr 0.000058	time 1.8045 (2.2176)	loss 3.2876 (3.0506)	grad_norm 3.0824 (2.8003)	
[2022-01-25 22:46:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][580/1251]	eta 0:24:47 lr 0.000058	time 1.9994 (2.2164)	loss 2.4628 (3.0504)	grad_norm 2.4423 (2.8011)	
[2022-01-25 22:46:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][590/1251]	eta 0:24:26 lr 0.000058	time 2.1556 (2.2183)	loss 1.9229 (3.0475)	grad_norm 2.9988 (2.8024)	
[2022-01-25 22:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][600/1251]	eta 0:24:06 lr 0.000058	time 2.5916 (2.2218)	loss 3.3705 (3.0474)	grad_norm 2.9873 (2.8009)	
[2022-01-25 22:47:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][610/1251]	eta 0:23:45 lr 0.000058	time 2.4534 (2.2245)	loss 2.4825 (3.0422)	grad_norm 2.6146 (2.7998)	
[2022-01-25 22:47:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][620/1251]	eta 0:23:26 lr 0.000058	time 2.7683 (2.2283)	loss 3.0641 (3.0414)	grad_norm 2.4790 (2.7980)	
[2022-01-25 22:48:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][630/1251]	eta 0:23:03 lr 0.000058	time 2.5565 (2.2278)	loss 2.0333 (3.0406)	grad_norm 2.6706 (2.8012)	
[2022-01-25 22:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][640/1251]	eta 0:22:38 lr 0.000058	time 1.9227 (2.2234)	loss 3.5794 (3.0422)	grad_norm 2.8580 (2.8012)	
[2022-01-25 22:48:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][650/1251]	eta 0:22:12 lr 0.000058	time 1.9684 (2.2178)	loss 3.7609 (3.0461)	grad_norm 2.4841 (2.8083)	
[2022-01-25 22:49:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][660/1251]	eta 0:21:48 lr 0.000058	time 2.1842 (2.2148)	loss 2.8855 (3.0510)	grad_norm 2.6038 (2.8088)	
[2022-01-25 22:49:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][670/1251]	eta 0:21:24 lr 0.000058	time 2.1603 (2.2110)	loss 3.3673 (3.0511)	grad_norm 2.5377 (2.8076)	
[2022-01-25 22:49:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][680/1251]	eta 0:21:02 lr 0.000058	time 2.2882 (2.2104)	loss 2.6861 (3.0504)	grad_norm 2.6225 (2.8080)	
[2022-01-25 22:50:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][690/1251]	eta 0:20:40 lr 0.000058	time 2.6731 (2.2107)	loss 3.2148 (3.0544)	grad_norm 2.3981 (2.8093)	
[2022-01-25 22:50:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][700/1251]	eta 0:20:19 lr 0.000058	time 2.5023 (2.2139)	loss 3.9070 (3.0567)	grad_norm 3.0217 (2.8085)	
[2022-01-25 22:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][710/1251]	eta 0:19:59 lr 0.000058	time 2.3949 (2.2166)	loss 3.1663 (3.0538)	grad_norm 2.5706 (2.8071)	
[2022-01-25 22:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][720/1251]	eta 0:19:37 lr 0.000058	time 2.4944 (2.2184)	loss 3.7280 (3.0527)	grad_norm 2.7593 (2.8069)	
[2022-01-25 22:51:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][730/1251]	eta 0:19:15 lr 0.000058	time 2.2242 (2.2182)	loss 3.6041 (3.0562)	grad_norm 2.6555 (2.8060)	
[2022-01-25 22:51:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][740/1251]	eta 0:18:52 lr 0.000058	time 1.8941 (2.2160)	loss 2.9204 (3.0596)	grad_norm 2.7332 (2.8051)	
[2022-01-25 22:52:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][750/1251]	eta 0:18:29 lr 0.000058	time 2.2455 (2.2139)	loss 3.5002 (3.0580)	grad_norm 2.8008 (2.8056)	
[2022-01-25 22:52:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][760/1251]	eta 0:18:07 lr 0.000058	time 2.0089 (2.2142)	loss 3.7943 (3.0592)	grad_norm 2.5483 (2.8065)	
[2022-01-25 22:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][770/1251]	eta 0:17:44 lr 0.000058	time 1.8762 (2.2129)	loss 2.9321 (3.0593)	grad_norm 2.3878 (2.8050)	
[2022-01-25 22:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][780/1251]	eta 0:17:22 lr 0.000058	time 1.6172 (2.2137)	loss 3.3948 (3.0615)	grad_norm 2.3545 (2.8038)	
[2022-01-25 22:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][790/1251]	eta 0:16:59 lr 0.000058	time 1.7983 (2.2122)	loss 3.7156 (3.0624)	grad_norm 2.7515 (2.8037)	
[2022-01-25 22:54:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][800/1251]	eta 0:16:38 lr 0.000058	time 2.1885 (2.2131)	loss 3.3573 (3.0633)	grad_norm 2.3748 (2.8025)	
[2022-01-25 22:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][810/1251]	eta 0:16:15 lr 0.000058	time 1.9426 (2.2111)	loss 3.3465 (3.0633)	grad_norm 2.7395 (2.8015)	
[2022-01-25 22:54:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][820/1251]	eta 0:15:53 lr 0.000058	time 2.1024 (2.2113)	loss 2.1524 (3.0610)	grad_norm 2.8896 (2.8012)	
[2022-01-25 22:55:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][830/1251]	eta 0:15:31 lr 0.000058	time 2.2615 (2.2120)	loss 3.4943 (3.0602)	grad_norm 3.0624 (2.7999)	
[2022-01-25 22:55:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][840/1251]	eta 0:15:09 lr 0.000058	time 2.0612 (2.2117)	loss 3.0510 (3.0625)	grad_norm 2.6830 (2.7985)	
[2022-01-25 22:55:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][850/1251]	eta 0:14:46 lr 0.000058	time 1.9037 (2.2105)	loss 2.7203 (3.0624)	grad_norm 3.1476 (2.7989)	
[2022-01-25 22:56:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][860/1251]	eta 0:14:24 lr 0.000058	time 1.4347 (2.2120)	loss 2.3765 (3.0616)	grad_norm 2.7134 (2.7988)	
[2022-01-25 22:56:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][870/1251]	eta 0:14:02 lr 0.000058	time 2.1561 (2.2121)	loss 3.4338 (3.0638)	grad_norm 3.4809 (2.7999)	
[2022-01-25 22:57:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][880/1251]	eta 0:13:40 lr 0.000058	time 1.5709 (2.2113)	loss 3.3863 (3.0652)	grad_norm 2.6298 (2.8003)	
[2022-01-25 22:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][890/1251]	eta 0:13:17 lr 0.000058	time 1.7266 (2.2100)	loss 2.7627 (3.0670)	grad_norm 2.5065 (2.8005)	
[2022-01-25 22:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][900/1251]	eta 0:12:55 lr 0.000058	time 2.2080 (2.2091)	loss 3.0465 (3.0680)	grad_norm 2.6560 (2.8014)	
[2022-01-25 22:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][910/1251]	eta 0:12:32 lr 0.000058	time 1.9005 (2.2073)	loss 3.3435 (3.0674)	grad_norm 2.7181 (2.8000)	
[2022-01-25 22:58:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][920/1251]	eta 0:12:09 lr 0.000058	time 1.8493 (2.2052)	loss 3.2663 (3.0693)	grad_norm 2.9581 (2.8002)	
[2022-01-25 22:58:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][930/1251]	eta 0:11:47 lr 0.000058	time 1.9195 (2.2048)	loss 3.0760 (3.0692)	grad_norm 2.3971 (2.8016)	
[2022-01-25 22:59:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][940/1251]	eta 0:11:26 lr 0.000058	time 2.7853 (2.2065)	loss 2.7947 (3.0693)	grad_norm 3.0990 (2.8084)	
[2022-01-25 22:59:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][950/1251]	eta 0:11:04 lr 0.000058	time 1.8146 (2.2064)	loss 2.5908 (3.0670)	grad_norm 2.7299 (2.8086)	
[2022-01-25 22:59:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][960/1251]	eta 0:10:41 lr 0.000058	time 2.2512 (2.2058)	loss 1.9819 (3.0660)	grad_norm 2.7394 (2.8078)	
[2022-01-25 23:00:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][970/1251]	eta 0:10:19 lr 0.000058	time 1.5793 (2.2059)	loss 3.5177 (3.0670)	grad_norm 2.9711 (2.8069)	
[2022-01-25 23:00:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][980/1251]	eta 0:09:58 lr 0.000058	time 1.7595 (2.2070)	loss 1.9092 (3.0668)	grad_norm 3.5194 (2.8077)	
[2022-01-25 23:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][990/1251]	eta 0:09:35 lr 0.000058	time 2.1954 (2.2063)	loss 2.4828 (3.0648)	grad_norm 3.0141 (2.8120)	
[2022-01-25 23:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1000/1251]	eta 0:09:13 lr 0.000058	time 2.2117 (2.2060)	loss 3.3722 (3.0659)	grad_norm 2.8897 (2.8125)	
[2022-01-25 23:01:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1010/1251]	eta 0:08:51 lr 0.000058	time 1.6034 (2.2052)	loss 2.8361 (3.0648)	grad_norm 3.0164 (2.8126)	
[2022-01-25 23:02:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1020/1251]	eta 0:08:29 lr 0.000058	time 1.8657 (2.2073)	loss 2.9549 (3.0648)	grad_norm 3.0003 (2.8161)	
[2022-01-25 23:02:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1030/1251]	eta 0:08:08 lr 0.000058	time 2.9400 (2.2091)	loss 3.2839 (3.0653)	grad_norm 2.9704 (2.8164)	
[2022-01-25 23:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1040/1251]	eta 0:07:45 lr 0.000057	time 1.6056 (2.2072)	loss 3.6574 (3.0656)	grad_norm 3.6428 (2.8166)	
[2022-01-25 23:03:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1050/1251]	eta 0:07:23 lr 0.000057	time 1.6942 (2.2065)	loss 3.2207 (3.0640)	grad_norm 2.7801 (2.8166)	
[2022-01-25 23:03:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1060/1251]	eta 0:07:01 lr 0.000057	time 1.8751 (2.2067)	loss 2.5251 (3.0636)	grad_norm 2.6352 (2.8171)	
[2022-01-25 23:03:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1070/1251]	eta 0:06:38 lr 0.000057	time 1.9228 (2.2043)	loss 2.7611 (3.0633)	grad_norm 2.5066 (2.8151)	
[2022-01-25 23:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1080/1251]	eta 0:06:16 lr 0.000057	time 2.5677 (2.2028)	loss 3.2671 (3.0619)	grad_norm 3.7073 (2.8167)	
[2022-01-25 23:04:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1090/1251]	eta 0:05:54 lr 0.000057	time 2.2376 (2.2033)	loss 3.6057 (3.0617)	grad_norm 2.7623 (2.8160)	
[2022-01-25 23:05:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1100/1251]	eta 0:05:32 lr 0.000057	time 2.1487 (2.2038)	loss 3.0877 (3.0627)	grad_norm 2.8630 (2.8155)	
[2022-01-25 23:05:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1110/1251]	eta 0:05:10 lr 0.000057	time 2.1464 (2.2044)	loss 2.1273 (3.0606)	grad_norm 2.7139 (2.8137)	
[2022-01-25 23:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1120/1251]	eta 0:04:48 lr 0.000057	time 2.3649 (2.2048)	loss 3.0954 (3.0626)	grad_norm 2.5281 (2.8143)	
[2022-01-25 23:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1130/1251]	eta 0:04:26 lr 0.000057	time 1.8437 (2.2038)	loss 2.7450 (3.0626)	grad_norm 3.0038 (2.8151)	
[2022-01-25 23:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1140/1251]	eta 0:04:04 lr 0.000057	time 1.5667 (2.2031)	loss 2.3112 (3.0623)	grad_norm 2.5541 (2.8135)	
[2022-01-25 23:06:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1150/1251]	eta 0:03:42 lr 0.000057	time 1.5647 (2.2012)	loss 3.3525 (3.0638)	grad_norm 2.6225 (2.8121)	
[2022-01-25 23:07:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1160/1251]	eta 0:03:20 lr 0.000057	time 2.2141 (2.2006)	loss 2.9316 (3.0638)	grad_norm 2.9263 (2.8129)	
[2022-01-25 23:07:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1170/1251]	eta 0:02:58 lr 0.000057	time 2.4161 (2.2058)	loss 2.5191 (3.0640)	grad_norm 2.3835 (2.8114)	
[2022-01-25 23:08:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1180/1251]	eta 0:02:36 lr 0.000057	time 1.5400 (2.2053)	loss 2.6382 (3.0663)	grad_norm 2.8199 (2.8112)	
[2022-01-25 23:08:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1190/1251]	eta 0:02:14 lr 0.000057	time 1.8625 (2.2056)	loss 3.5931 (3.0676)	grad_norm 2.9413 (2.8128)	
[2022-01-25 23:08:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1200/1251]	eta 0:01:52 lr 0.000057	time 1.8139 (2.2044)	loss 3.5443 (3.0678)	grad_norm 2.7003 (2.8110)	
[2022-01-25 23:09:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1210/1251]	eta 0:01:30 lr 0.000057	time 1.8098 (2.2054)	loss 3.2209 (3.0695)	grad_norm 2.4984 (2.8099)	
[2022-01-25 23:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1220/1251]	eta 0:01:08 lr 0.000057	time 1.5964 (2.2043)	loss 2.7410 (3.0710)	grad_norm 2.5984 (2.8098)	
[2022-01-25 23:09:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1230/1251]	eta 0:00:46 lr 0.000057	time 1.7933 (2.2059)	loss 3.3928 (3.0725)	grad_norm 2.5739 (2.8088)	
[2022-01-25 23:10:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1240/1251]	eta 0:00:24 lr 0.000057	time 1.4719 (2.2037)	loss 2.6615 (3.0698)	grad_norm 2.5739 (2.8082)	
[2022-01-25 23:10:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [257/300][1250/1251]	eta 0:00:02 lr 0.000057	time 1.2096 (2.1977)	loss 2.8785 (3.0708)	grad_norm 2.3716 (2.8076)	
[2022-01-25 23:10:26 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 257 training takes 0:45:49
[2022-01-25 23:10:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.236 (18.236)	Loss 0.8174 (0.8174)	Acc@1 81.543 (81.543)	Acc@5 95.410 (95.410)	
[2022-01-25 23:11:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.656 (3.545)	Loss 0.9008 (0.8207)	Acc@1 79.492 (80.850)	Acc@5 94.434 (95.419)	
[2022-01-25 23:11:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.337 (2.555)	Loss 0.9262 (0.8220)	Acc@1 77.930 (80.915)	Acc@5 94.336 (95.359)	
[2022-01-25 23:11:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.635 (2.217)	Loss 0.8038 (0.8252)	Acc@1 81.445 (80.891)	Acc@5 95.801 (95.319)	
[2022-01-25 23:11:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.358 (2.163)	Loss 0.8481 (0.8240)	Acc@1 79.297 (80.895)	Acc@5 94.824 (95.343)	
[2022-01-25 23:12:01 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.776 Acc@5 95.310
[2022-01-25 23:12:01 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.8%
[2022-01-25 23:12:01 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.78%
[2022-01-25 23:12:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][0/1251]	eta 7:35:43 lr 0.000057	time 21.8577 (21.8577)	loss 3.3874 (3.3874)	grad_norm 2.5509 (2.5509)	
[2022-01-25 23:12:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][10/1251]	eta 1:21:24 lr 0.000057	time 1.5733 (3.9357)	loss 2.7470 (3.1054)	grad_norm 2.7077 (2.6789)	
[2022-01-25 23:13:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][20/1251]	eta 1:03:55 lr 0.000057	time 1.5728 (3.1161)	loss 2.4842 (2.9822)	grad_norm 3.0616 (2.7206)	
[2022-01-25 23:13:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][30/1251]	eta 0:58:55 lr 0.000057	time 1.4219 (2.8960)	loss 3.8003 (3.0724)	grad_norm 2.5296 (2.7748)	
[2022-01-25 23:13:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][40/1251]	eta 0:55:02 lr 0.000057	time 3.8790 (2.7269)	loss 3.5139 (3.0372)	grad_norm 3.3496 (2.7951)	
[2022-01-25 23:14:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][50/1251]	eta 0:53:01 lr 0.000057	time 3.0218 (2.6487)	loss 3.6568 (3.0456)	grad_norm 3.0619 (2.8045)	
[2022-01-25 23:14:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][60/1251]	eta 0:50:30 lr 0.000057	time 1.5816 (2.5447)	loss 3.1431 (3.0484)	grad_norm 2.8100 (2.7853)	
[2022-01-25 23:15:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][70/1251]	eta 0:49:30 lr 0.000057	time 1.9089 (2.5156)	loss 2.4148 (3.0296)	grad_norm 3.0737 (2.8003)	
[2022-01-25 23:15:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][80/1251]	eta 0:48:53 lr 0.000057	time 3.7347 (2.5053)	loss 3.5082 (3.0289)	grad_norm 2.8937 (2.7812)	
[2022-01-25 23:15:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][90/1251]	eta 0:47:43 lr 0.000057	time 2.5339 (2.4661)	loss 3.1652 (3.0153)	grad_norm 2.5257 (2.7944)	
[2022-01-25 23:16:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][100/1251]	eta 0:46:38 lr 0.000057	time 1.6753 (2.4311)	loss 3.2622 (3.0285)	grad_norm 2.7547 (2.7953)	
[2022-01-25 23:16:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][110/1251]	eta 0:45:42 lr 0.000057	time 1.7892 (2.4040)	loss 2.8868 (3.0427)	grad_norm 2.6010 (2.7758)	
[2022-01-25 23:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][120/1251]	eta 0:45:04 lr 0.000057	time 3.4572 (2.3913)	loss 2.8106 (3.0372)	grad_norm 3.2757 (2.7940)	
[2022-01-25 23:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][130/1251]	eta 0:44:19 lr 0.000057	time 2.8298 (2.3725)	loss 3.0449 (3.0454)	grad_norm 3.1313 (2.8018)	
[2022-01-25 23:17:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][140/1251]	eta 0:43:27 lr 0.000057	time 1.9744 (2.3470)	loss 1.7794 (3.0370)	grad_norm 2.7192 (2.7947)	
[2022-01-25 23:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][150/1251]	eta 0:42:51 lr 0.000057	time 1.8597 (2.3352)	loss 3.4371 (3.0449)	grad_norm 2.9381 (2.7925)	
[2022-01-25 23:18:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][160/1251]	eta 0:42:18 lr 0.000057	time 2.9275 (2.3270)	loss 3.2356 (3.0450)	grad_norm 2.6428 (2.7940)	
[2022-01-25 23:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][170/1251]	eta 0:41:38 lr 0.000057	time 1.8895 (2.3112)	loss 2.2488 (3.0489)	grad_norm 2.7590 (2.7786)	
[2022-01-25 23:18:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][180/1251]	eta 0:41:07 lr 0.000057	time 1.9702 (2.3041)	loss 2.9827 (3.0362)	grad_norm 3.0083 (2.7755)	
[2022-01-25 23:19:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][190/1251]	eta 0:40:44 lr 0.000057	time 1.3513 (2.3043)	loss 3.2485 (3.0458)	grad_norm 3.3408 (2.7647)	
[2022-01-25 23:19:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][200/1251]	eta 0:40:24 lr 0.000057	time 3.5230 (2.3072)	loss 3.4162 (3.0543)	grad_norm 3.0218 (2.7658)	
[2022-01-25 23:20:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][210/1251]	eta 0:39:47 lr 0.000057	time 1.8881 (2.2937)	loss 3.3906 (3.0616)	grad_norm 2.8034 (2.7654)	
[2022-01-25 23:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][220/1251]	eta 0:39:17 lr 0.000057	time 1.6819 (2.2867)	loss 3.3627 (3.0602)	grad_norm 2.8647 (2.7683)	
[2022-01-25 23:20:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][230/1251]	eta 0:38:52 lr 0.000057	time 2.1411 (2.2844)	loss 2.7117 (3.0455)	grad_norm 2.9934 (2.7725)	
[2022-01-25 23:21:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][240/1251]	eta 0:38:31 lr 0.000057	time 3.4068 (2.2862)	loss 3.5029 (3.0521)	grad_norm 2.7147 (2.7726)	
[2022-01-25 23:21:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][250/1251]	eta 0:37:58 lr 0.000057	time 1.8202 (2.2762)	loss 2.7474 (3.0447)	grad_norm 3.4616 (2.7805)	
[2022-01-25 23:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][260/1251]	eta 0:37:36 lr 0.000057	time 2.2335 (2.2775)	loss 3.3615 (3.0357)	grad_norm 2.8189 (2.7837)	
[2022-01-25 23:22:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][270/1251]	eta 0:37:10 lr 0.000057	time 1.8954 (2.2735)	loss 2.0596 (3.0312)	grad_norm 2.7875 (2.7915)	
[2022-01-25 23:22:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][280/1251]	eta 0:36:50 lr 0.000057	time 3.3987 (2.2766)	loss 3.0209 (3.0362)	grad_norm 2.7811 (2.7966)	
[2022-01-25 23:23:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][290/1251]	eta 0:36:24 lr 0.000057	time 2.2111 (2.2727)	loss 3.1273 (3.0430)	grad_norm 2.7597 (2.7959)	
[2022-01-25 23:23:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][300/1251]	eta 0:35:53 lr 0.000057	time 1.9998 (2.2648)	loss 3.3650 (3.0399)	grad_norm 2.9503 (2.7925)	
[2022-01-25 23:23:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][310/1251]	eta 0:35:25 lr 0.000057	time 2.4837 (2.2584)	loss 3.1150 (3.0439)	grad_norm 2.4727 (2.7918)	
[2022-01-25 23:24:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][320/1251]	eta 0:35:05 lr 0.000057	time 3.3542 (2.2613)	loss 2.2414 (3.0459)	grad_norm 2.6574 (2.7875)	
[2022-01-25 23:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][330/1251]	eta 0:34:38 lr 0.000057	time 1.8865 (2.2572)	loss 3.2551 (3.0542)	grad_norm 2.8689 (2.7874)	
[2022-01-25 23:24:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][340/1251]	eta 0:34:13 lr 0.000057	time 2.2384 (2.2544)	loss 3.1383 (3.0554)	grad_norm 2.5562 (2.7843)	
[2022-01-25 23:25:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][350/1251]	eta 0:33:47 lr 0.000056	time 2.1586 (2.2500)	loss 3.3696 (3.0550)	grad_norm 3.0652 (2.7851)	
[2022-01-25 23:25:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][360/1251]	eta 0:33:21 lr 0.000056	time 2.6193 (2.2468)	loss 3.1615 (3.0484)	grad_norm 2.1694 (2.7813)	
[2022-01-25 23:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][370/1251]	eta 0:32:52 lr 0.000056	time 1.7864 (2.2386)	loss 2.7640 (3.0441)	grad_norm 3.0279 (2.7839)	
[2022-01-25 23:26:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][380/1251]	eta 0:32:27 lr 0.000056	time 2.2922 (2.2358)	loss 3.4556 (3.0382)	grad_norm 2.7434 (2.7819)	
[2022-01-25 23:26:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][390/1251]	eta 0:32:04 lr 0.000056	time 1.8684 (2.2357)	loss 2.9382 (3.0405)	grad_norm 2.5361 (2.7827)	
[2022-01-25 23:26:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][400/1251]	eta 0:31:42 lr 0.000056	time 2.8715 (2.2360)	loss 3.3867 (3.0285)	grad_norm 2.9588 (2.7833)	
[2022-01-25 23:27:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][410/1251]	eta 0:31:17 lr 0.000056	time 1.9140 (2.2325)	loss 3.2435 (3.0332)	grad_norm 2.6430 (2.7847)	
[2022-01-25 23:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][420/1251]	eta 0:30:54 lr 0.000056	time 2.5290 (2.2311)	loss 3.3799 (3.0380)	grad_norm 2.6400 (2.7861)	
[2022-01-25 23:28:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][430/1251]	eta 0:30:32 lr 0.000056	time 1.4511 (2.2316)	loss 3.5774 (3.0271)	grad_norm 2.5442 (2.7856)	
[2022-01-25 23:28:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][440/1251]	eta 0:30:13 lr 0.000056	time 2.4098 (2.2361)	loss 2.5784 (3.0288)	grad_norm 3.6031 (2.7888)	
[2022-01-25 23:28:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][450/1251]	eta 0:29:49 lr 0.000056	time 1.6231 (2.2340)	loss 2.7701 (3.0302)	grad_norm 2.6942 (2.7892)	
[2022-01-25 23:29:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][460/1251]	eta 0:29:26 lr 0.000056	time 2.3242 (2.2327)	loss 3.1756 (3.0285)	grad_norm 2.7774 (2.7893)	
[2022-01-25 23:29:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][470/1251]	eta 0:29:05 lr 0.000056	time 2.0324 (2.2344)	loss 3.1897 (3.0266)	grad_norm 2.4048 (2.7865)	
[2022-01-25 23:29:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][480/1251]	eta 0:28:42 lr 0.000056	time 1.8695 (2.2346)	loss 3.6163 (3.0302)	grad_norm 3.0444 (2.7835)	
[2022-01-25 23:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][490/1251]	eta 0:28:16 lr 0.000056	time 1.9471 (2.2288)	loss 3.2046 (3.0341)	grad_norm 2.6960 (2.7805)	
[2022-01-25 23:30:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][500/1251]	eta 0:27:52 lr 0.000056	time 2.2485 (2.2270)	loss 2.5139 (3.0324)	grad_norm 2.4044 (2.7821)	
[2022-01-25 23:30:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][510/1251]	eta 0:27:28 lr 0.000056	time 2.4877 (2.2244)	loss 3.6874 (3.0318)	grad_norm 2.7808 (2.7834)	
[2022-01-25 23:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][520/1251]	eta 0:27:06 lr 0.000056	time 2.2493 (2.2249)	loss 3.5591 (3.0334)	grad_norm 2.5267 (2.7841)	
[2022-01-25 23:31:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][530/1251]	eta 0:26:45 lr 0.000056	time 2.2261 (2.2264)	loss 3.6022 (3.0360)	grad_norm 3.2403 (2.7858)	
[2022-01-25 23:32:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][540/1251]	eta 0:26:23 lr 0.000056	time 2.5040 (2.2271)	loss 3.4243 (3.0394)	grad_norm 2.7238 (2.7872)	
[2022-01-25 23:32:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][550/1251]	eta 0:26:02 lr 0.000056	time 2.3350 (2.2288)	loss 2.2825 (3.0344)	grad_norm 2.6214 (2.7892)	
[2022-01-25 23:32:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][560/1251]	eta 0:25:39 lr 0.000056	time 1.9660 (2.2283)	loss 3.4507 (3.0340)	grad_norm 2.7755 (2.7898)	
[2022-01-25 23:33:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][570/1251]	eta 0:25:14 lr 0.000056	time 2.2311 (2.2241)	loss 2.7926 (3.0326)	grad_norm 2.6114 (2.7895)	
[2022-01-25 23:33:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][580/1251]	eta 0:24:50 lr 0.000056	time 1.9566 (2.2209)	loss 2.1347 (3.0327)	grad_norm 2.9300 (2.7892)	
[2022-01-25 23:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][590/1251]	eta 0:24:26 lr 0.000056	time 2.3338 (2.2193)	loss 3.4020 (3.0363)	grad_norm 2.8191 (2.7912)	
[2022-01-25 23:34:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][600/1251]	eta 0:24:04 lr 0.000056	time 2.3346 (2.2183)	loss 3.8863 (3.0377)	grad_norm 2.6302 (2.7951)	
[2022-01-25 23:34:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][610/1251]	eta 0:23:41 lr 0.000056	time 1.8458 (2.2177)	loss 2.2115 (3.0363)	grad_norm 2.6235 (2.7935)	
[2022-01-25 23:35:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][620/1251]	eta 0:23:20 lr 0.000056	time 2.2691 (2.2199)	loss 3.2838 (3.0328)	grad_norm 2.8242 (2.7931)	
[2022-01-25 23:35:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][630/1251]	eta 0:22:59 lr 0.000056	time 2.5655 (2.2207)	loss 3.1595 (3.0375)	grad_norm 2.8366 (2.7959)	
[2022-01-25 23:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][640/1251]	eta 0:22:36 lr 0.000056	time 2.8524 (2.2194)	loss 2.8669 (3.0391)	grad_norm 2.2793 (2.7939)	
[2022-01-25 23:36:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][650/1251]	eta 0:22:12 lr 0.000056	time 2.0310 (2.2169)	loss 2.9875 (3.0401)	grad_norm 2.6117 (2.7921)	
[2022-01-25 23:36:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][660/1251]	eta 0:21:48 lr 0.000056	time 1.5781 (2.2145)	loss 3.1867 (3.0441)	grad_norm 2.5730 (2.7915)	
[2022-01-25 23:36:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][670/1251]	eta 0:21:26 lr 0.000056	time 2.1885 (2.2136)	loss 3.2393 (3.0438)	grad_norm 2.8230 (2.7918)	
[2022-01-25 23:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][680/1251]	eta 0:21:04 lr 0.000056	time 2.7334 (2.2144)	loss 2.5955 (3.0401)	grad_norm 3.3236 (2.7916)	
[2022-01-25 23:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][690/1251]	eta 0:20:41 lr 0.000056	time 2.0621 (2.2136)	loss 2.0774 (3.0372)	grad_norm 2.5287 (2.7895)	
[2022-01-25 23:37:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][700/1251]	eta 0:20:18 lr 0.000056	time 2.5184 (2.2123)	loss 3.6907 (3.0374)	grad_norm 3.1221 (2.7866)	
[2022-01-25 23:38:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][710/1251]	eta 0:19:56 lr 0.000056	time 2.4513 (2.2116)	loss 3.1998 (3.0353)	grad_norm 3.0409 (2.7863)	
[2022-01-25 23:38:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][720/1251]	eta 0:19:34 lr 0.000056	time 1.4998 (2.2115)	loss 3.8468 (3.0354)	grad_norm 2.5308 (2.7858)	
[2022-01-25 23:39:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][730/1251]	eta 0:19:13 lr 0.000056	time 2.2455 (2.2137)	loss 3.5241 (3.0353)	grad_norm 2.5967 (2.7868)	
[2022-01-25 23:39:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][740/1251]	eta 0:18:51 lr 0.000056	time 2.2505 (2.2137)	loss 2.7127 (3.0353)	grad_norm 2.5776 (2.7876)	
[2022-01-25 23:39:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][750/1251]	eta 0:18:29 lr 0.000056	time 2.7353 (2.2140)	loss 3.1200 (3.0378)	grad_norm 2.8247 (2.7864)	
[2022-01-25 23:40:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][760/1251]	eta 0:18:06 lr 0.000056	time 1.5186 (2.2132)	loss 3.1779 (3.0410)	grad_norm 2.8656 (2.7861)	
[2022-01-25 23:40:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][770/1251]	eta 0:17:44 lr 0.000056	time 2.2240 (2.2141)	loss 3.2421 (3.0426)	grad_norm 3.3765 (2.7890)	
[2022-01-25 23:40:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][780/1251]	eta 0:17:21 lr 0.000056	time 1.9403 (2.2118)	loss 2.4283 (3.0378)	grad_norm 3.3383 (2.7919)	
[2022-01-25 23:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][790/1251]	eta 0:16:58 lr 0.000056	time 2.1066 (2.2093)	loss 3.0806 (3.0378)	grad_norm 2.8947 (2.7968)	
[2022-01-25 23:41:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][800/1251]	eta 0:16:36 lr 0.000056	time 1.9344 (2.2093)	loss 2.8122 (3.0384)	grad_norm 2.2168 (2.7970)	
[2022-01-25 23:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][810/1251]	eta 0:16:13 lr 0.000056	time 2.1989 (2.2076)	loss 3.3882 (3.0404)	grad_norm 2.8937 (2.7972)	
[2022-01-25 23:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][820/1251]	eta 0:15:50 lr 0.000056	time 1.9485 (2.2060)	loss 2.9620 (3.0402)	grad_norm 2.6567 (2.7993)	
[2022-01-25 23:42:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][830/1251]	eta 0:15:28 lr 0.000056	time 1.7576 (2.2061)	loss 3.1926 (3.0392)	grad_norm 2.5603 (2.7972)	
[2022-01-25 23:42:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][840/1251]	eta 0:15:06 lr 0.000056	time 1.9155 (2.2056)	loss 2.9268 (3.0424)	grad_norm 2.4716 (2.7962)	
[2022-01-25 23:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][850/1251]	eta 0:14:45 lr 0.000056	time 5.0562 (2.2084)	loss 2.8458 (3.0428)	grad_norm 2.9622 (2.7962)	
[2022-01-25 23:43:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][860/1251]	eta 0:14:23 lr 0.000056	time 1.6353 (2.2087)	loss 2.6940 (3.0443)	grad_norm 2.8103 (2.7973)	
[2022-01-25 23:44:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][870/1251]	eta 0:14:01 lr 0.000056	time 1.9226 (2.2077)	loss 2.5133 (3.0451)	grad_norm 2.5308 (2.7992)	
[2022-01-25 23:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][880/1251]	eta 0:13:38 lr 0.000056	time 2.0949 (2.2068)	loss 2.1431 (3.0436)	grad_norm 2.7870 (2.8005)	
[2022-01-25 23:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][890/1251]	eta 0:13:17 lr 0.000056	time 3.6445 (2.2080)	loss 2.3323 (3.0438)	grad_norm 2.4863 (2.7993)	
[2022-01-25 23:45:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][900/1251]	eta 0:12:54 lr 0.000056	time 2.0856 (2.2078)	loss 3.1684 (3.0444)	grad_norm 2.4910 (2.7994)	
[2022-01-25 23:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][910/1251]	eta 0:12:32 lr 0.000056	time 2.2540 (2.2069)	loss 2.4083 (3.0460)	grad_norm 2.7005 (2.7998)	
[2022-01-25 23:45:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][920/1251]	eta 0:12:09 lr 0.000056	time 1.7294 (2.2047)	loss 3.3384 (3.0444)	grad_norm 2.5514 (2.7987)	
[2022-01-25 23:46:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][930/1251]	eta 0:11:47 lr 0.000055	time 2.6967 (2.2038)	loss 3.2895 (3.0474)	grad_norm 2.8415 (2.7990)	
[2022-01-25 23:46:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][940/1251]	eta 0:11:24 lr 0.000055	time 1.5916 (2.2017)	loss 3.4362 (3.0480)	grad_norm 3.1565 (2.7989)	
[2022-01-25 23:46:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][950/1251]	eta 0:11:02 lr 0.000055	time 2.1866 (2.2021)	loss 2.0417 (3.0461)	grad_norm 2.6258 (2.7985)	
[2022-01-25 23:47:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][960/1251]	eta 0:10:41 lr 0.000055	time 2.0311 (2.2030)	loss 2.9696 (3.0476)	grad_norm 2.6514 (2.7964)	
[2022-01-25 23:47:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][970/1251]	eta 0:10:18 lr 0.000055	time 2.1373 (2.2020)	loss 3.1252 (3.0481)	grad_norm 2.8015 (2.7959)	
[2022-01-25 23:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][980/1251]	eta 0:09:56 lr 0.000055	time 2.3522 (2.2025)	loss 2.9348 (3.0479)	grad_norm 3.1196 (2.7959)	
[2022-01-25 23:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][990/1251]	eta 0:09:35 lr 0.000055	time 3.0002 (2.2036)	loss 3.3493 (3.0496)	grad_norm 2.6198 (2.7955)	
[2022-01-25 23:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1000/1251]	eta 0:09:13 lr 0.000055	time 1.8868 (2.2035)	loss 3.2581 (3.0471)	grad_norm 2.9320 (2.7953)	
[2022-01-25 23:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1010/1251]	eta 0:08:51 lr 0.000055	time 2.1794 (2.2038)	loss 2.1976 (3.0466)	grad_norm 2.6527 (2.7953)	
[2022-01-25 23:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1020/1251]	eta 0:08:28 lr 0.000055	time 2.1871 (2.2034)	loss 3.4387 (3.0447)	grad_norm 2.7172 (2.7964)	
[2022-01-25 23:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1030/1251]	eta 0:08:07 lr 0.000055	time 2.5486 (2.2043)	loss 3.0503 (3.0428)	grad_norm 2.9201 (2.7958)	
[2022-01-25 23:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1040/1251]	eta 0:07:44 lr 0.000055	time 1.8407 (2.2030)	loss 3.3707 (3.0416)	grad_norm 3.2318 (2.7963)	
[2022-01-25 23:50:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1050/1251]	eta 0:07:22 lr 0.000055	time 2.2829 (2.2007)	loss 3.2702 (3.0449)	grad_norm 2.6478 (2.7960)	
[2022-01-25 23:50:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1060/1251]	eta 0:07:00 lr 0.000055	time 2.0854 (2.1993)	loss 2.1509 (3.0455)	grad_norm 2.7916 (2.7948)	
[2022-01-25 23:51:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1070/1251]	eta 0:06:37 lr 0.000055	time 1.8563 (2.1982)	loss 2.9451 (3.0441)	grad_norm 2.4825 (2.7945)	
[2022-01-25 23:51:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1080/1251]	eta 0:06:15 lr 0.000055	time 2.3227 (2.1979)	loss 3.2244 (3.0442)	grad_norm 3.0686 (2.7956)	
[2022-01-25 23:52:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1090/1251]	eta 0:05:53 lr 0.000055	time 2.5696 (2.1985)	loss 3.2522 (3.0459)	grad_norm 2.8048 (2.7964)	
[2022-01-25 23:52:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1100/1251]	eta 0:05:31 lr 0.000055	time 1.6458 (2.1984)	loss 3.4962 (3.0465)	grad_norm 2.6706 (2.7973)	
[2022-01-25 23:52:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1110/1251]	eta 0:05:09 lr 0.000055	time 1.7051 (2.1981)	loss 2.4566 (3.0444)	grad_norm 3.1982 (2.7998)	
[2022-01-25 23:53:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1120/1251]	eta 0:04:48 lr 0.000055	time 2.9611 (2.2001)	loss 3.4783 (3.0455)	grad_norm 2.7386 (2.7996)	
[2022-01-25 23:53:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1130/1251]	eta 0:04:26 lr 0.000055	time 2.1918 (2.2009)	loss 2.7565 (3.0457)	grad_norm 3.2838 (2.7990)	
[2022-01-25 23:53:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1140/1251]	eta 0:04:04 lr 0.000055	time 1.5948 (2.2009)	loss 3.3913 (3.0452)	grad_norm 2.7745 (2.7988)	
[2022-01-25 23:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1150/1251]	eta 0:03:42 lr 0.000055	time 2.4246 (2.2007)	loss 3.2779 (3.0433)	grad_norm 2.9490 (2.8026)	
[2022-01-25 23:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1160/1251]	eta 0:03:20 lr 0.000055	time 2.5358 (2.2005)	loss 3.0912 (3.0427)	grad_norm 2.5413 (2.8044)	
[2022-01-25 23:54:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1170/1251]	eta 0:02:58 lr 0.000055	time 1.5440 (2.1984)	loss 2.2485 (3.0434)	grad_norm 2.4505 (2.8030)	
[2022-01-25 23:55:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1180/1251]	eta 0:02:35 lr 0.000055	time 1.6838 (2.1968)	loss 3.7461 (3.0424)	grad_norm 2.4811 (2.8030)	
[2022-01-25 23:55:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1190/1251]	eta 0:02:14 lr 0.000055	time 2.2205 (2.1973)	loss 2.4743 (3.0413)	grad_norm 2.9067 (2.8031)	
[2022-01-25 23:56:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1200/1251]	eta 0:01:52 lr 0.000055	time 2.2595 (2.1976)	loss 3.7193 (3.0418)	grad_norm 2.6869 (2.8028)	
[2022-01-25 23:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1210/1251]	eta 0:01:30 lr 0.000055	time 2.1883 (2.1982)	loss 2.2487 (3.0415)	grad_norm 2.4509 (2.8016)	
[2022-01-25 23:56:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1220/1251]	eta 0:01:08 lr 0.000055	time 2.8113 (2.1987)	loss 3.2506 (3.0405)	grad_norm 2.4118 (2.8011)	
[2022-01-25 23:57:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1230/1251]	eta 0:00:46 lr 0.000055	time 2.2237 (2.2003)	loss 3.6859 (3.0406)	grad_norm 2.7219 (2.7997)	
[2022-01-25 23:57:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1240/1251]	eta 0:00:24 lr 0.000055	time 1.2055 (2.1982)	loss 3.6645 (3.0418)	grad_norm 2.8941 (2.7990)	
[2022-01-25 23:57:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [258/300][1250/1251]	eta 0:00:02 lr 0.000055	time 1.1926 (2.1927)	loss 2.0123 (3.0420)	grad_norm 3.2318 (2.7994)	
[2022-01-25 23:57:45 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 258 training takes 0:45:43
[2022-01-25 23:58:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 20.296 (20.296)	Loss 0.7725 (0.7725)	Acc@1 82.227 (82.227)	Acc@5 96.582 (96.582)	
[2022-01-25 23:58:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.283 (3.334)	Loss 0.8748 (0.8086)	Acc@1 80.469 (80.859)	Acc@5 95.020 (95.534)	
[2022-01-25 23:58:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.298 (2.510)	Loss 0.8212 (0.8085)	Acc@1 80.859 (80.850)	Acc@5 95.801 (95.508)	
[2022-01-25 23:58:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.367 (2.259)	Loss 0.8207 (0.8154)	Acc@1 81.250 (80.696)	Acc@5 95.020 (95.413)	
[2022-01-25 23:59:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.699 (2.183)	Loss 0.8322 (0.8183)	Acc@1 80.859 (80.535)	Acc@5 95.410 (95.405)	
[2022-01-25 23:59:21 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.628 Acc@5 95.368
[2022-01-25 23:59:21 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.6%
[2022-01-25 23:59:21 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.78%
[2022-01-25 23:59:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][0/1251]	eta 7:32:16 lr 0.000055	time 21.6917 (21.6917)	loss 2.3914 (2.3914)	grad_norm 2.7446 (2.7446)	
[2022-01-26 00:00:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][10/1251]	eta 1:24:51 lr 0.000055	time 2.8412 (4.1026)	loss 3.3862 (2.8507)	grad_norm 2.5014 (2.6056)	
[2022-01-26 00:00:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][20/1251]	eta 1:05:22 lr 0.000055	time 1.2524 (3.1864)	loss 2.3643 (2.8944)	grad_norm 2.4360 (2.7368)	
[2022-01-26 00:00:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][30/1251]	eta 0:58:20 lr 0.000055	time 1.9406 (2.8668)	loss 2.4576 (2.9958)	grad_norm 3.6069 (2.8420)	
[2022-01-26 00:01:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][40/1251]	eta 0:56:20 lr 0.000055	time 5.8938 (2.7911)	loss 2.6510 (3.0252)	grad_norm 2.7001 (2.8534)	
[2022-01-26 00:01:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][50/1251]	eta 0:53:51 lr 0.000055	time 1.8634 (2.6907)	loss 3.1281 (3.0031)	grad_norm 2.5694 (2.9031)	
[2022-01-26 00:02:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][60/1251]	eta 0:51:53 lr 0.000055	time 1.6916 (2.6143)	loss 1.8815 (2.9520)	grad_norm 2.5953 (2.8912)	
[2022-01-26 00:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][70/1251]	eta 0:49:59 lr 0.000055	time 1.8722 (2.5394)	loss 2.6405 (2.9736)	grad_norm 2.9015 (2.9291)	
[2022-01-26 00:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][80/1251]	eta 0:49:33 lr 0.000055	time 6.2673 (2.5395)	loss 3.4321 (3.0027)	grad_norm 3.4317 (2.9097)	
[2022-01-26 00:03:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][90/1251]	eta 0:48:18 lr 0.000055	time 1.5875 (2.4969)	loss 3.2561 (3.0377)	grad_norm 2.5172 (2.9115)	
[2022-01-26 00:03:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][100/1251]	eta 0:47:03 lr 0.000055	time 1.8617 (2.4528)	loss 3.2657 (3.0332)	grad_norm 2.8752 (2.9061)	
[2022-01-26 00:03:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][110/1251]	eta 0:45:47 lr 0.000055	time 1.5892 (2.4076)	loss 3.7310 (3.0431)	grad_norm 2.8616 (2.8886)	
[2022-01-26 00:04:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][120/1251]	eta 0:45:24 lr 0.000055	time 3.6626 (2.4092)	loss 3.3209 (3.0557)	grad_norm 2.6981 (2.8761)	
[2022-01-26 00:04:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][130/1251]	eta 0:44:35 lr 0.000055	time 1.6126 (2.3865)	loss 3.3059 (3.0638)	grad_norm 2.6434 (2.8639)	
[2022-01-26 00:04:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][140/1251]	eta 0:44:04 lr 0.000055	time 1.6816 (2.3800)	loss 3.6157 (3.0721)	grad_norm 3.1517 (2.8782)	
[2022-01-26 00:05:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][150/1251]	eta 0:43:22 lr 0.000055	time 2.3247 (2.3639)	loss 2.7018 (3.0718)	grad_norm 2.8001 (2.8718)	
[2022-01-26 00:05:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][160/1251]	eta 0:43:16 lr 0.000055	time 6.8807 (2.3797)	loss 3.5216 (3.0729)	grad_norm 2.9939 (2.8706)	
[2022-01-26 00:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][170/1251]	eta 0:42:37 lr 0.000055	time 1.8967 (2.3655)	loss 3.5553 (3.0754)	grad_norm 3.2361 (2.8748)	
[2022-01-26 00:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][180/1251]	eta 0:42:05 lr 0.000055	time 1.6750 (2.3580)	loss 3.2528 (3.0691)	grad_norm 2.7193 (2.8770)	
[2022-01-26 00:06:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][190/1251]	eta 0:41:22 lr 0.000055	time 1.8962 (2.3396)	loss 3.4439 (3.0671)	grad_norm 3.0407 (2.8756)	
[2022-01-26 00:07:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][200/1251]	eta 0:40:50 lr 0.000055	time 3.6399 (2.3317)	loss 2.0083 (3.0554)	grad_norm 2.9473 (2.8707)	
[2022-01-26 00:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][210/1251]	eta 0:40:18 lr 0.000055	time 2.0727 (2.3236)	loss 3.2739 (3.0427)	grad_norm 3.0832 (2.8661)	
[2022-01-26 00:07:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][220/1251]	eta 0:39:39 lr 0.000055	time 1.8602 (2.3082)	loss 1.8714 (3.0355)	grad_norm 2.6538 (2.8647)	
[2022-01-26 00:08:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][230/1251]	eta 0:39:04 lr 0.000055	time 1.7102 (2.2964)	loss 3.7437 (3.0379)	grad_norm 3.2320 (2.8680)	
[2022-01-26 00:08:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][240/1251]	eta 0:38:38 lr 0.000055	time 3.1514 (2.2929)	loss 3.2937 (3.0392)	grad_norm 7.7157 (2.8848)	
[2022-01-26 00:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][250/1251]	eta 0:38:15 lr 0.000054	time 2.8403 (2.2930)	loss 2.0669 (3.0388)	grad_norm 3.0218 (2.8819)	
[2022-01-26 00:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][260/1251]	eta 0:37:55 lr 0.000054	time 2.5744 (2.2959)	loss 3.4408 (3.0501)	grad_norm 2.5158 (2.8762)	
[2022-01-26 00:09:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][270/1251]	eta 0:37:28 lr 0.000054	time 2.2771 (2.2916)	loss 2.9081 (3.0416)	grad_norm 2.4515 (2.8698)	
[2022-01-26 00:10:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][280/1251]	eta 0:37:05 lr 0.000054	time 3.0958 (2.2924)	loss 2.2169 (3.0321)	grad_norm 2.6979 (2.8657)	
[2022-01-26 00:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][290/1251]	eta 0:36:43 lr 0.000054	time 2.9413 (2.2929)	loss 2.4761 (3.0319)	grad_norm 3.2577 (2.8689)	
[2022-01-26 00:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][300/1251]	eta 0:36:10 lr 0.000054	time 1.6097 (2.2829)	loss 3.1745 (3.0242)	grad_norm 2.6290 (2.8642)	
[2022-01-26 00:11:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][310/1251]	eta 0:35:42 lr 0.000054	time 1.8500 (2.2766)	loss 2.6167 (3.0169)	grad_norm 2.6860 (2.8625)	
[2022-01-26 00:11:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][320/1251]	eta 0:35:26 lr 0.000054	time 4.7783 (2.2840)	loss 3.2317 (3.0199)	grad_norm 2.6297 (2.8601)	
[2022-01-26 00:11:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][330/1251]	eta 0:35:05 lr 0.000054	time 2.6444 (2.2861)	loss 3.0039 (3.0218)	grad_norm 3.1410 (2.8619)	
[2022-01-26 00:12:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][340/1251]	eta 0:34:39 lr 0.000054	time 1.7051 (2.2824)	loss 3.4847 (3.0290)	grad_norm 2.8293 (2.8646)	
[2022-01-26 00:12:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][350/1251]	eta 0:34:07 lr 0.000054	time 1.9143 (2.2724)	loss 2.6405 (3.0351)	grad_norm 2.4989 (2.8666)	
[2022-01-26 00:13:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][360/1251]	eta 0:33:41 lr 0.000054	time 3.4315 (2.2685)	loss 2.9037 (3.0357)	grad_norm 2.6409 (2.8677)	
[2022-01-26 00:13:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][370/1251]	eta 0:33:16 lr 0.000054	time 2.3799 (2.2657)	loss 2.2449 (3.0339)	grad_norm 3.3485 (2.8674)	
[2022-01-26 00:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][380/1251]	eta 0:32:52 lr 0.000054	time 1.8459 (2.2645)	loss 3.3617 (3.0304)	grad_norm 2.7183 (2.8704)	
[2022-01-26 00:14:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][390/1251]	eta 0:32:32 lr 0.000054	time 2.1288 (2.2677)	loss 2.1038 (3.0304)	grad_norm 2.9105 (2.8699)	
[2022-01-26 00:14:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][400/1251]	eta 0:32:09 lr 0.000054	time 3.5836 (2.2673)	loss 3.1870 (3.0320)	grad_norm 2.8359 (2.8694)	
[2022-01-26 00:14:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][410/1251]	eta 0:31:44 lr 0.000054	time 1.8594 (2.2646)	loss 2.7994 (3.0290)	grad_norm 2.6927 (2.8716)	
[2022-01-26 00:15:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][420/1251]	eta 0:31:17 lr 0.000054	time 1.7729 (2.2596)	loss 3.2468 (3.0291)	grad_norm 2.8441 (2.8715)	
[2022-01-26 00:15:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][430/1251]	eta 0:30:51 lr 0.000054	time 1.6212 (2.2546)	loss 3.6056 (3.0395)	grad_norm 2.5477 (2.8701)	
[2022-01-26 00:15:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][440/1251]	eta 0:30:29 lr 0.000054	time 2.9583 (2.2553)	loss 2.3537 (3.0395)	grad_norm 2.5534 (2.8676)	
[2022-01-26 00:16:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][450/1251]	eta 0:30:05 lr 0.000054	time 1.9699 (2.2539)	loss 3.4271 (3.0358)	grad_norm 2.9697 (2.8660)	
[2022-01-26 00:16:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][460/1251]	eta 0:29:43 lr 0.000054	time 2.8499 (2.2543)	loss 2.8117 (3.0376)	grad_norm 2.8313 (2.8634)	
[2022-01-26 00:17:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][470/1251]	eta 0:29:17 lr 0.000054	time 1.9545 (2.2501)	loss 2.0587 (3.0431)	grad_norm 4.2130 (2.8651)	
[2022-01-26 00:17:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][480/1251]	eta 0:28:54 lr 0.000054	time 2.7559 (2.2496)	loss 3.2595 (3.0435)	grad_norm 3.0938 (2.8662)	
[2022-01-26 00:17:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][490/1251]	eta 0:28:29 lr 0.000054	time 2.0199 (2.2458)	loss 3.4407 (3.0383)	grad_norm 2.7824 (2.8653)	
[2022-01-26 00:18:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][500/1251]	eta 0:28:05 lr 0.000054	time 2.6282 (2.2448)	loss 3.3061 (3.0387)	grad_norm 2.3701 (2.8614)	
[2022-01-26 00:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][510/1251]	eta 0:27:41 lr 0.000054	time 2.1516 (2.2417)	loss 3.0418 (3.0369)	grad_norm 2.5294 (2.8614)	
[2022-01-26 00:18:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][520/1251]	eta 0:27:17 lr 0.000054	time 2.5020 (2.2404)	loss 3.2301 (3.0361)	grad_norm 3.1305 (2.8639)	
[2022-01-26 00:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][530/1251]	eta 0:26:54 lr 0.000054	time 2.5084 (2.2392)	loss 3.3497 (3.0383)	grad_norm 2.7055 (2.8643)	
[2022-01-26 00:19:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][540/1251]	eta 0:26:30 lr 0.000054	time 2.2264 (2.2368)	loss 3.3155 (3.0374)	grad_norm 2.7114 (2.8617)	
[2022-01-26 00:19:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][550/1251]	eta 0:26:05 lr 0.000054	time 1.8006 (2.2339)	loss 2.9735 (3.0345)	grad_norm 3.3036 (2.8588)	
[2022-01-26 00:20:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][560/1251]	eta 0:25:42 lr 0.000054	time 2.8003 (2.2325)	loss 3.2813 (3.0371)	grad_norm 2.5486 (2.8601)	
[2022-01-26 00:20:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][570/1251]	eta 0:25:20 lr 0.000054	time 2.7299 (2.2333)	loss 3.2553 (3.0354)	grad_norm 2.8851 (2.8627)	
[2022-01-26 00:20:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][580/1251]	eta 0:24:57 lr 0.000054	time 2.2369 (2.2321)	loss 1.8695 (3.0336)	grad_norm 2.5999 (2.8617)	
[2022-01-26 00:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][590/1251]	eta 0:24:34 lr 0.000054	time 1.5894 (2.2301)	loss 2.9723 (3.0313)	grad_norm 2.6250 (2.8607)	
[2022-01-26 00:21:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][600/1251]	eta 0:24:16 lr 0.000054	time 4.0773 (2.2374)	loss 3.3775 (3.0306)	grad_norm 2.4253 (2.8587)	
[2022-01-26 00:22:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][610/1251]	eta 0:23:53 lr 0.000054	time 2.1780 (2.2366)	loss 3.0396 (3.0262)	grad_norm 2.9436 (2.8585)	
[2022-01-26 00:22:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][620/1251]	eta 0:23:29 lr 0.000054	time 1.8402 (2.2340)	loss 2.8536 (3.0221)	grad_norm 2.3544 (2.8549)	
[2022-01-26 00:22:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][630/1251]	eta 0:23:06 lr 0.000054	time 1.9534 (2.2327)	loss 2.7254 (3.0196)	grad_norm 3.6681 (2.8521)	
[2022-01-26 00:23:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][640/1251]	eta 0:22:44 lr 0.000054	time 3.7221 (2.2336)	loss 3.3961 (3.0157)	grad_norm 2.6573 (2.8511)	
[2022-01-26 00:23:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][650/1251]	eta 0:22:22 lr 0.000054	time 3.2270 (2.2346)	loss 2.6929 (3.0138)	grad_norm 2.5380 (2.8485)	
[2022-01-26 00:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][660/1251]	eta 0:21:59 lr 0.000054	time 2.1907 (2.2322)	loss 3.2544 (3.0152)	grad_norm 2.3736 (2.8448)	
[2022-01-26 00:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][670/1251]	eta 0:21:34 lr 0.000054	time 1.7771 (2.2286)	loss 3.0741 (3.0156)	grad_norm 2.5375 (2.8410)	
[2022-01-26 00:24:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][680/1251]	eta 0:21:12 lr 0.000054	time 2.6964 (2.2294)	loss 2.8973 (3.0187)	grad_norm 2.5099 (2.8417)	
[2022-01-26 00:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][690/1251]	eta 0:20:49 lr 0.000054	time 1.8408 (2.2277)	loss 3.7864 (3.0214)	grad_norm 3.0010 (2.8381)	
[2022-01-26 00:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][700/1251]	eta 0:20:25 lr 0.000054	time 1.8673 (2.2250)	loss 3.3259 (3.0186)	grad_norm 2.6785 (2.8363)	
[2022-01-26 00:25:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][710/1251]	eta 0:20:04 lr 0.000054	time 2.8748 (2.2256)	loss 3.4950 (3.0186)	grad_norm 2.8842 (2.8369)	
[2022-01-26 00:26:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][720/1251]	eta 0:19:41 lr 0.000054	time 2.3290 (2.2257)	loss 3.0070 (3.0207)	grad_norm 3.8507 (2.8380)	
[2022-01-26 00:26:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][730/1251]	eta 0:19:18 lr 0.000054	time 1.5932 (2.2237)	loss 2.2311 (3.0175)	grad_norm 2.5436 (2.8382)	
[2022-01-26 00:26:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][740/1251]	eta 0:18:56 lr 0.000054	time 1.5457 (2.2234)	loss 3.7285 (3.0177)	grad_norm 2.7890 (2.8368)	
[2022-01-26 00:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][750/1251]	eta 0:18:33 lr 0.000054	time 1.8783 (2.2226)	loss 2.8733 (3.0208)	grad_norm 2.7509 (2.8391)	
[2022-01-26 00:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][760/1251]	eta 0:18:10 lr 0.000054	time 1.7958 (2.2209)	loss 3.3473 (3.0225)	grad_norm 2.8043 (2.8413)	
[2022-01-26 00:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][770/1251]	eta 0:17:48 lr 0.000054	time 1.7267 (2.2219)	loss 3.3831 (3.0211)	grad_norm 2.6160 (2.8394)	
[2022-01-26 00:28:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][780/1251]	eta 0:17:26 lr 0.000054	time 1.6985 (2.2218)	loss 3.0674 (3.0244)	grad_norm 2.6017 (2.8402)	
[2022-01-26 00:28:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][790/1251]	eta 0:17:04 lr 0.000054	time 1.6380 (2.2219)	loss 2.6450 (3.0236)	grad_norm 2.6680 (2.8369)	
[2022-01-26 00:29:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][800/1251]	eta 0:16:41 lr 0.000054	time 1.9720 (2.2217)	loss 2.0400 (3.0196)	grad_norm 2.5691 (2.8354)	
[2022-01-26 00:29:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][810/1251]	eta 0:16:19 lr 0.000054	time 1.8437 (2.2210)	loss 3.1132 (3.0213)	grad_norm 3.5413 (2.8359)	
[2022-01-26 00:29:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][820/1251]	eta 0:15:57 lr 0.000054	time 1.8447 (2.2218)	loss 3.2481 (3.0212)	grad_norm 2.9857 (2.8352)	
[2022-01-26 00:30:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][830/1251]	eta 0:15:35 lr 0.000054	time 1.6321 (2.2218)	loss 3.3538 (3.0204)	grad_norm 2.8723 (2.8330)	
[2022-01-26 00:30:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][840/1251]	eta 0:15:13 lr 0.000053	time 2.3771 (2.2228)	loss 2.7469 (3.0199)	grad_norm 2.5664 (2.8309)	
[2022-01-26 00:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][850/1251]	eta 0:14:50 lr 0.000053	time 1.9381 (2.2216)	loss 2.3220 (3.0205)	grad_norm 2.7635 (2.8301)	
[2022-01-26 00:31:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][860/1251]	eta 0:14:28 lr 0.000053	time 1.8604 (2.2202)	loss 2.4260 (3.0182)	grad_norm 2.8187 (2.8276)	
[2022-01-26 00:31:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][870/1251]	eta 0:14:04 lr 0.000053	time 1.8856 (2.2175)	loss 2.3359 (3.0165)	grad_norm 2.8014 (2.8256)	
[2022-01-26 00:31:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][880/1251]	eta 0:13:42 lr 0.000053	time 1.9647 (2.2165)	loss 3.3224 (3.0182)	grad_norm 3.4265 (2.8241)	
[2022-01-26 00:32:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][890/1251]	eta 0:13:19 lr 0.000053	time 2.3844 (2.2157)	loss 3.4300 (3.0201)	grad_norm 2.4289 (2.8225)	
[2022-01-26 00:32:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][900/1251]	eta 0:12:57 lr 0.000053	time 1.9079 (2.2165)	loss 1.8294 (3.0195)	grad_norm 2.9116 (2.8237)	
[2022-01-26 00:32:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][910/1251]	eta 0:12:35 lr 0.000053	time 1.8525 (2.2143)	loss 3.2417 (3.0202)	grad_norm 2.4997 (2.8217)	
[2022-01-26 00:33:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][920/1251]	eta 0:12:12 lr 0.000053	time 2.0056 (2.2127)	loss 3.5421 (3.0204)	grad_norm 2.9266 (2.8214)	
[2022-01-26 00:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][930/1251]	eta 0:11:49 lr 0.000053	time 1.8334 (2.2117)	loss 3.4098 (3.0183)	grad_norm 2.7079 (2.8197)	
[2022-01-26 00:34:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][940/1251]	eta 0:11:27 lr 0.000053	time 1.9011 (2.2107)	loss 3.7944 (3.0208)	grad_norm 2.9318 (2.8192)	
[2022-01-26 00:34:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][950/1251]	eta 0:11:05 lr 0.000053	time 1.9863 (2.2104)	loss 2.6812 (3.0225)	grad_norm 2.3373 (2.8203)	
[2022-01-26 00:34:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][960/1251]	eta 0:10:43 lr 0.000053	time 2.6620 (2.2106)	loss 3.3022 (3.0227)	grad_norm 2.5617 (2.8186)	
[2022-01-26 00:35:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][970/1251]	eta 0:10:21 lr 0.000053	time 1.4977 (2.2106)	loss 3.1495 (3.0246)	grad_norm 2.5265 (2.8189)	
[2022-01-26 00:35:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][980/1251]	eta 0:09:59 lr 0.000053	time 2.1678 (2.2121)	loss 2.9331 (3.0259)	grad_norm 2.8075 (2.8186)	
[2022-01-26 00:35:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][990/1251]	eta 0:09:37 lr 0.000053	time 2.8023 (2.2131)	loss 2.6949 (3.0261)	grad_norm 3.4226 (2.8187)	
[2022-01-26 00:36:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1000/1251]	eta 0:09:15 lr 0.000053	time 1.9131 (2.2137)	loss 2.5302 (3.0268)	grad_norm 2.5549 (2.8166)	
[2022-01-26 00:36:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1010/1251]	eta 0:08:53 lr 0.000053	time 1.9136 (2.2145)	loss 3.4533 (3.0257)	grad_norm 2.9086 (2.8154)	
[2022-01-26 00:37:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1020/1251]	eta 0:08:31 lr 0.000053	time 1.9002 (2.2145)	loss 2.8689 (3.0263)	grad_norm 3.3240 (2.8176)	
[2022-01-26 00:37:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1030/1251]	eta 0:08:09 lr 0.000053	time 1.7925 (2.2141)	loss 2.5133 (3.0262)	grad_norm 3.0286 (2.8174)	
[2022-01-26 00:37:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1040/1251]	eta 0:07:46 lr 0.000053	time 2.2120 (2.2115)	loss 2.3026 (3.0262)	grad_norm 2.7887 (2.8175)	
[2022-01-26 00:38:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1050/1251]	eta 0:07:24 lr 0.000053	time 1.8945 (2.2092)	loss 3.2505 (3.0284)	grad_norm 3.1993 (2.8166)	
[2022-01-26 00:38:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1060/1251]	eta 0:07:02 lr 0.000053	time 2.2131 (2.2103)	loss 2.2755 (3.0252)	grad_norm 2.7594 (2.8162)	
[2022-01-26 00:38:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1070/1251]	eta 0:06:40 lr 0.000053	time 2.4667 (2.2120)	loss 2.9974 (3.0254)	grad_norm 2.8569 (2.8144)	
[2022-01-26 00:39:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1080/1251]	eta 0:06:18 lr 0.000053	time 2.2064 (2.2111)	loss 2.9524 (3.0258)	grad_norm 2.4156 (2.8138)	
[2022-01-26 00:39:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1090/1251]	eta 0:05:55 lr 0.000053	time 1.9448 (2.2091)	loss 2.1904 (3.0263)	grad_norm 2.6552 (2.8138)	
[2022-01-26 00:39:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1100/1251]	eta 0:05:33 lr 0.000053	time 1.8584 (2.2085)	loss 2.8464 (3.0276)	grad_norm 2.8838 (2.8132)	
[2022-01-26 00:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1110/1251]	eta 0:05:11 lr 0.000053	time 2.0200 (2.2075)	loss 3.1404 (3.0280)	grad_norm 2.7272 (2.8123)	
[2022-01-26 00:40:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1120/1251]	eta 0:04:49 lr 0.000053	time 2.1763 (2.2071)	loss 2.3528 (3.0284)	grad_norm 2.9666 (2.8151)	
[2022-01-26 00:40:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1130/1251]	eta 0:04:27 lr 0.000053	time 1.7189 (2.2078)	loss 3.1817 (3.0290)	grad_norm 2.5062 (2.8177)	
[2022-01-26 00:41:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1140/1251]	eta 0:04:05 lr 0.000053	time 3.4947 (2.2106)	loss 2.9668 (3.0288)	grad_norm 3.0274 (2.8188)	
[2022-01-26 00:41:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1150/1251]	eta 0:03:43 lr 0.000053	time 1.9095 (2.2115)	loss 3.0227 (3.0288)	grad_norm 4.1310 (2.8198)	
[2022-01-26 00:42:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1160/1251]	eta 0:03:21 lr 0.000053	time 2.1540 (2.2115)	loss 3.1016 (3.0296)	grad_norm 2.4970 (2.8198)	
[2022-01-26 00:42:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1170/1251]	eta 0:02:58 lr 0.000053	time 1.7631 (2.2095)	loss 2.8491 (3.0296)	grad_norm 2.7238 (2.8196)	
[2022-01-26 00:42:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1180/1251]	eta 0:02:36 lr 0.000053	time 2.0077 (2.2071)	loss 3.2188 (3.0315)	grad_norm 2.4332 (2.8192)	
[2022-01-26 00:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1190/1251]	eta 0:02:14 lr 0.000053	time 2.4814 (2.2058)	loss 3.3070 (3.0325)	grad_norm 2.5543 (2.8194)	
[2022-01-26 00:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1200/1251]	eta 0:01:52 lr 0.000053	time 2.1978 (2.2063)	loss 2.3212 (3.0336)	grad_norm 2.7192 (2.8198)	
[2022-01-26 00:43:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1210/1251]	eta 0:01:30 lr 0.000053	time 1.8977 (2.2061)	loss 3.3119 (3.0323)	grad_norm 2.5953 (2.8204)	
[2022-01-26 00:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1220/1251]	eta 0:01:08 lr 0.000053	time 2.8137 (2.2082)	loss 2.0977 (3.0315)	grad_norm 2.8602 (2.8215)	
[2022-01-26 00:44:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1230/1251]	eta 0:00:46 lr 0.000053	time 2.1643 (2.2075)	loss 2.9880 (3.0333)	grad_norm 2.9400 (2.8216)	
[2022-01-26 00:44:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1240/1251]	eta 0:00:24 lr 0.000053	time 1.9788 (2.2061)	loss 2.7724 (3.0305)	grad_norm 2.8021 (2.8206)	
[2022-01-26 00:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [259/300][1250/1251]	eta 0:00:02 lr 0.000053	time 1.1663 (2.2005)	loss 2.9373 (3.0316)	grad_norm 2.9665 (2.8217)	
[2022-01-26 00:45:15 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 259 training takes 0:45:53
[2022-01-26 00:45:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.808 (18.808)	Loss 0.8146 (0.8146)	Acc@1 81.641 (81.641)	Acc@5 95.801 (95.801)	
[2022-01-26 00:45:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.923 (3.537)	Loss 0.8613 (0.8423)	Acc@1 79.004 (80.407)	Acc@5 95.703 (95.162)	
[2022-01-26 00:46:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.595 (2.793)	Loss 0.8281 (0.8334)	Acc@1 79.883 (80.673)	Acc@5 95.801 (95.252)	
[2022-01-26 00:46:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.622 (2.389)	Loss 0.8546 (0.8305)	Acc@1 81.641 (80.777)	Acc@5 95.508 (95.319)	
[2022-01-26 00:46:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.236 (2.229)	Loss 0.8596 (0.8302)	Acc@1 81.250 (80.850)	Acc@5 94.141 (95.322)	
[2022-01-26 00:46:54 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.658 Acc@5 95.320
[2022-01-26 00:46:54 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.7%
[2022-01-26 00:46:54 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.78%
[2022-01-26 00:47:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][0/1251]	eta 7:15:08 lr 0.000053	time 20.8698 (20.8698)	loss 3.3487 (3.3487)	grad_norm 3.0546 (3.0546)	
[2022-01-26 00:47:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][10/1251]	eta 1:23:53 lr 0.000053	time 2.9049 (4.0563)	loss 3.4197 (3.1551)	grad_norm 2.6545 (2.7308)	
[2022-01-26 00:48:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][20/1251]	eta 1:05:10 lr 0.000053	time 2.1003 (3.1768)	loss 3.2098 (3.1029)	grad_norm 2.5827 (2.7097)	
[2022-01-26 00:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][30/1251]	eta 0:57:06 lr 0.000053	time 1.4420 (2.8062)	loss 3.5912 (3.2176)	grad_norm 3.4367 (2.7451)	
[2022-01-26 00:48:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][40/1251]	eta 0:54:26 lr 0.000053	time 4.1815 (2.6972)	loss 2.0189 (3.1535)	grad_norm 2.5802 (2.7762)	
[2022-01-26 00:49:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][50/1251]	eta 0:52:36 lr 0.000053	time 2.1863 (2.6279)	loss 3.5073 (3.1159)	grad_norm 3.2313 (2.7613)	
[2022-01-26 00:49:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][60/1251]	eta 0:50:29 lr 0.000053	time 2.6116 (2.5434)	loss 3.4335 (3.1180)	grad_norm 2.4499 (2.7652)	
[2022-01-26 00:49:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][70/1251]	eta 0:48:56 lr 0.000053	time 1.8826 (2.4866)	loss 3.3176 (3.1046)	grad_norm 2.6438 (2.7666)	
[2022-01-26 00:50:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][80/1251]	eta 0:48:10 lr 0.000053	time 2.9506 (2.4684)	loss 2.8254 (3.0779)	grad_norm 2.7223 (2.7880)	
[2022-01-26 00:50:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][90/1251]	eta 0:47:24 lr 0.000053	time 1.7818 (2.4498)	loss 3.4704 (3.0782)	grad_norm 2.6977 (2.8026)	
[2022-01-26 00:50:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][100/1251]	eta 0:46:12 lr 0.000053	time 1.8801 (2.4088)	loss 3.3826 (3.0862)	grad_norm 2.8210 (2.8074)	
[2022-01-26 00:51:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][110/1251]	eta 0:45:19 lr 0.000053	time 1.8914 (2.3834)	loss 2.7356 (3.0815)	grad_norm 2.6764 (2.8010)	
[2022-01-26 00:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][120/1251]	eta 0:44:45 lr 0.000053	time 3.3524 (2.3748)	loss 3.4479 (3.0877)	grad_norm 3.1969 (2.7932)	
[2022-01-26 00:52:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][130/1251]	eta 0:44:21 lr 0.000053	time 2.0648 (2.3745)	loss 3.3112 (3.0949)	grad_norm 3.2543 (2.7970)	
[2022-01-26 00:52:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][140/1251]	eta 0:43:37 lr 0.000053	time 2.0994 (2.3561)	loss 3.1034 (3.0987)	grad_norm 2.5592 (2.7924)	
[2022-01-26 00:52:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][150/1251]	eta 0:42:54 lr 0.000053	time 1.9611 (2.3383)	loss 3.0483 (3.0908)	grad_norm 2.8729 (2.8084)	
[2022-01-26 00:53:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][160/1251]	eta 0:42:08 lr 0.000053	time 2.5215 (2.3178)	loss 3.4890 (3.0815)	grad_norm 2.8179 (2.8191)	
[2022-01-26 00:53:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][170/1251]	eta 0:41:29 lr 0.000053	time 1.9231 (2.3033)	loss 2.7185 (3.0768)	grad_norm 2.3935 (2.8221)	
[2022-01-26 00:53:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][180/1251]	eta 0:40:59 lr 0.000052	time 2.2401 (2.2967)	loss 3.2362 (3.0698)	grad_norm 3.4059 (2.8193)	
[2022-01-26 00:54:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][190/1251]	eta 0:40:38 lr 0.000052	time 2.4927 (2.2980)	loss 3.1576 (3.0665)	grad_norm 2.4945 (2.8216)	
[2022-01-26 00:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][200/1251]	eta 0:40:15 lr 0.000052	time 2.7547 (2.2984)	loss 3.4645 (3.0572)	grad_norm 2.5970 (2.8230)	
[2022-01-26 00:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][210/1251]	eta 0:39:45 lr 0.000052	time 1.6776 (2.2917)	loss 2.9690 (3.0680)	grad_norm 2.7879 (2.8272)	
[2022-01-26 00:55:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][220/1251]	eta 0:39:17 lr 0.000052	time 2.1593 (2.2871)	loss 3.1662 (3.0633)	grad_norm 2.8480 (2.8344)	
[2022-01-26 00:55:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][230/1251]	eta 0:38:48 lr 0.000052	time 1.9539 (2.2810)	loss 3.3363 (3.0614)	grad_norm 3.0226 (2.8376)	
[2022-01-26 00:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][240/1251]	eta 0:38:22 lr 0.000052	time 3.0846 (2.2772)	loss 3.3389 (3.0678)	grad_norm 3.1590 (2.8483)	
[2022-01-26 00:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][250/1251]	eta 0:37:49 lr 0.000052	time 1.9056 (2.2676)	loss 3.4466 (3.0726)	grad_norm 2.9188 (2.8479)	
[2022-01-26 00:56:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][260/1251]	eta 0:37:23 lr 0.000052	time 2.1092 (2.2639)	loss 2.7049 (3.0648)	grad_norm 2.5956 (2.8468)	
[2022-01-26 00:57:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][270/1251]	eta 0:36:58 lr 0.000052	time 1.8482 (2.2611)	loss 3.4062 (3.0687)	grad_norm 3.4468 (2.8449)	
[2022-01-26 00:57:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][280/1251]	eta 0:36:36 lr 0.000052	time 2.7719 (2.2624)	loss 3.2018 (3.0696)	grad_norm 2.9661 (2.8517)	
[2022-01-26 00:57:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][290/1251]	eta 0:36:07 lr 0.000052	time 1.9457 (2.2557)	loss 2.9468 (3.0633)	grad_norm 2.6510 (2.8506)	
[2022-01-26 00:58:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][300/1251]	eta 0:35:40 lr 0.000052	time 1.6306 (2.2503)	loss 2.3054 (3.0614)	grad_norm 2.5011 (2.8511)	
[2022-01-26 00:58:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][310/1251]	eta 0:35:12 lr 0.000052	time 1.9995 (2.2447)	loss 3.5511 (3.0621)	grad_norm 2.8089 (2.8520)	
[2022-01-26 00:58:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][320/1251]	eta 0:34:47 lr 0.000052	time 2.2924 (2.2420)	loss 3.5964 (3.0590)	grad_norm 3.1109 (2.8543)	
[2022-01-26 00:59:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][330/1251]	eta 0:34:28 lr 0.000052	time 1.9939 (2.2464)	loss 2.2629 (3.0567)	grad_norm 3.1935 (2.8605)	
[2022-01-26 00:59:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][340/1251]	eta 0:34:04 lr 0.000052	time 1.9813 (2.2446)	loss 3.7056 (3.0594)	grad_norm 2.6619 (2.8566)	
[2022-01-26 01:00:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][350/1251]	eta 0:33:42 lr 0.000052	time 2.9195 (2.2444)	loss 2.6398 (3.0627)	grad_norm 2.4132 (2.8568)	
[2022-01-26 01:00:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][360/1251]	eta 0:33:18 lr 0.000052	time 2.7053 (2.2425)	loss 3.5310 (3.0626)	grad_norm 3.3074 (2.8583)	
[2022-01-26 01:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][370/1251]	eta 0:32:53 lr 0.000052	time 1.8755 (2.2406)	loss 2.9380 (3.0658)	grad_norm 2.7183 (2.8590)	
[2022-01-26 01:01:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][380/1251]	eta 0:32:28 lr 0.000052	time 2.1737 (2.2369)	loss 3.4985 (3.0683)	grad_norm 2.3529 (2.8536)	
[2022-01-26 01:01:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][390/1251]	eta 0:32:02 lr 0.000052	time 1.7437 (2.2332)	loss 3.2085 (3.0638)	grad_norm 3.1218 (2.8555)	
[2022-01-26 01:01:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][400/1251]	eta 0:31:36 lr 0.000052	time 1.8944 (2.2283)	loss 3.4900 (3.0685)	grad_norm 2.3804 (2.8547)	
[2022-01-26 01:02:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][410/1251]	eta 0:31:11 lr 0.000052	time 1.7123 (2.2258)	loss 3.0936 (3.0692)	grad_norm 2.7037 (2.8548)	
[2022-01-26 01:02:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][420/1251]	eta 0:30:53 lr 0.000052	time 2.5583 (2.2310)	loss 2.9596 (3.0725)	grad_norm 3.2224 (2.8581)	
[2022-01-26 01:02:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][430/1251]	eta 0:30:34 lr 0.000052	time 2.7946 (2.2341)	loss 2.7906 (3.0737)	grad_norm 2.8527 (2.8531)	
[2022-01-26 01:03:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][440/1251]	eta 0:30:09 lr 0.000052	time 1.7069 (2.2318)	loss 3.4692 (3.0725)	grad_norm 4.1502 (2.8563)	
[2022-01-26 01:03:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][450/1251]	eta 0:29:45 lr 0.000052	time 1.9586 (2.2293)	loss 3.3263 (3.0684)	grad_norm 2.2658 (2.8524)	
[2022-01-26 01:04:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][460/1251]	eta 0:29:22 lr 0.000052	time 1.8328 (2.2278)	loss 3.0559 (3.0635)	grad_norm 2.6976 (2.8517)	
[2022-01-26 01:04:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][470/1251]	eta 0:29:01 lr 0.000052	time 3.2884 (2.2301)	loss 2.5473 (3.0628)	grad_norm 3.1278 (2.8503)	
[2022-01-26 01:04:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][480/1251]	eta 0:28:36 lr 0.000052	time 1.6558 (2.2267)	loss 2.3721 (3.0605)	grad_norm 2.4788 (2.8496)	
[2022-01-26 01:05:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][490/1251]	eta 0:28:14 lr 0.000052	time 1.5995 (2.2264)	loss 2.9958 (3.0616)	grad_norm 2.8803 (2.8522)	
[2022-01-26 01:05:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][500/1251]	eta 0:27:52 lr 0.000052	time 1.8878 (2.2269)	loss 2.4818 (3.0615)	grad_norm 2.4052 (2.8492)	
[2022-01-26 01:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][510/1251]	eta 0:27:29 lr 0.000052	time 3.3140 (2.2260)	loss 2.8938 (3.0581)	grad_norm 2.5503 (2.8488)	
[2022-01-26 01:06:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][520/1251]	eta 0:27:05 lr 0.000052	time 1.8825 (2.2237)	loss 3.3580 (3.0579)	grad_norm 2.7075 (2.8486)	
[2022-01-26 01:06:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][530/1251]	eta 0:26:42 lr 0.000052	time 1.6102 (2.2223)	loss 3.1706 (3.0575)	grad_norm 2.6695 (2.8501)	
[2022-01-26 01:06:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][540/1251]	eta 0:26:20 lr 0.000052	time 2.3669 (2.2234)	loss 3.2959 (3.0580)	grad_norm 3.1594 (2.8594)	
[2022-01-26 01:07:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][550/1251]	eta 0:25:56 lr 0.000052	time 2.2077 (2.2199)	loss 3.2551 (3.0598)	grad_norm 2.9754 (2.8582)	
[2022-01-26 01:07:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][560/1251]	eta 0:25:31 lr 0.000052	time 1.8968 (2.2158)	loss 3.4510 (3.0616)	grad_norm 2.7211 (2.8563)	
[2022-01-26 01:07:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][570/1251]	eta 0:25:07 lr 0.000052	time 2.6666 (2.2139)	loss 2.7976 (3.0593)	grad_norm 2.4531 (2.8581)	
[2022-01-26 01:08:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][580/1251]	eta 0:24:43 lr 0.000052	time 2.6170 (2.2114)	loss 3.2421 (3.0573)	grad_norm 2.5659 (2.8598)	
[2022-01-26 01:08:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][590/1251]	eta 0:24:22 lr 0.000052	time 3.1773 (2.2123)	loss 3.6448 (3.0605)	grad_norm 2.7303 (2.8600)	
[2022-01-26 01:09:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][600/1251]	eta 0:24:00 lr 0.000052	time 2.3801 (2.2131)	loss 3.2077 (3.0626)	grad_norm 2.5009 (2.8586)	
[2022-01-26 01:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][610/1251]	eta 0:23:38 lr 0.000052	time 2.5038 (2.2124)	loss 3.0687 (3.0610)	grad_norm 2.5443 (2.8553)	
[2022-01-26 01:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][620/1251]	eta 0:23:17 lr 0.000052	time 2.2871 (2.2141)	loss 3.3998 (3.0613)	grad_norm 2.9937 (2.8534)	
[2022-01-26 01:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][630/1251]	eta 0:22:55 lr 0.000052	time 2.5152 (2.2143)	loss 2.8977 (3.0579)	grad_norm 3.0065 (2.8533)	
[2022-01-26 01:10:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][640/1251]	eta 0:22:33 lr 0.000052	time 2.4180 (2.2148)	loss 2.3646 (3.0552)	grad_norm 2.9975 (2.8529)	
[2022-01-26 01:10:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][650/1251]	eta 0:22:10 lr 0.000052	time 1.8748 (2.2141)	loss 2.1054 (3.0551)	grad_norm 2.7190 (2.8528)	
[2022-01-26 01:11:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][660/1251]	eta 0:21:48 lr 0.000052	time 1.9459 (2.2146)	loss 2.4454 (3.0560)	grad_norm 3.0049 (2.8542)	
[2022-01-26 01:11:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][670/1251]	eta 0:21:26 lr 0.000052	time 2.0218 (2.2138)	loss 3.4814 (3.0604)	grad_norm 3.1064 (2.8558)	
[2022-01-26 01:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][680/1251]	eta 0:21:02 lr 0.000052	time 1.6389 (2.2109)	loss 3.6178 (3.0616)	grad_norm 3.0436 (2.8557)	
[2022-01-26 01:12:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][690/1251]	eta 0:20:39 lr 0.000052	time 1.5598 (2.2087)	loss 3.0331 (3.0635)	grad_norm 2.9497 (2.8552)	
[2022-01-26 01:12:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][700/1251]	eta 0:20:17 lr 0.000052	time 2.9613 (2.2097)	loss 3.4530 (3.0652)	grad_norm 3.0975 (2.8552)	
[2022-01-26 01:13:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][710/1251]	eta 0:19:55 lr 0.000052	time 1.8870 (2.2099)	loss 3.0942 (3.0647)	grad_norm 2.4888 (2.8556)	
[2022-01-26 01:13:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][720/1251]	eta 0:19:34 lr 0.000052	time 1.9136 (2.2113)	loss 3.2530 (3.0641)	grad_norm 3.3396 (2.8560)	
[2022-01-26 01:13:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][730/1251]	eta 0:19:14 lr 0.000052	time 1.6060 (2.2151)	loss 2.5841 (3.0645)	grad_norm 2.8406 (2.8568)	
[2022-01-26 01:14:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][740/1251]	eta 0:18:52 lr 0.000052	time 2.8317 (2.2167)	loss 2.7603 (3.0676)	grad_norm 2.6856 (2.8557)	
[2022-01-26 01:14:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][750/1251]	eta 0:18:29 lr 0.000052	time 2.1304 (2.2151)	loss 2.6759 (3.0661)	grad_norm 2.6978 (2.8569)	
[2022-01-26 01:14:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][760/1251]	eta 0:18:06 lr 0.000052	time 1.8519 (2.2125)	loss 3.4042 (3.0686)	grad_norm 2.4593 (2.8574)	
[2022-01-26 01:15:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][770/1251]	eta 0:17:44 lr 0.000052	time 1.9005 (2.2122)	loss 3.2907 (3.0683)	grad_norm 2.9576 (2.8600)	
[2022-01-26 01:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][780/1251]	eta 0:17:21 lr 0.000051	time 2.7720 (2.2122)	loss 3.2678 (3.0663)	grad_norm 2.5167 (2.8606)	
[2022-01-26 01:16:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][790/1251]	eta 0:17:00 lr 0.000051	time 2.1447 (2.2130)	loss 3.2137 (3.0666)	grad_norm 2.7567 (2.8602)	
[2022-01-26 01:16:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][800/1251]	eta 0:16:37 lr 0.000051	time 1.9177 (2.2114)	loss 2.9406 (3.0710)	grad_norm 2.3176 (2.8650)	
[2022-01-26 01:16:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][810/1251]	eta 0:16:14 lr 0.000051	time 1.9789 (2.2098)	loss 3.5288 (3.0700)	grad_norm 2.6780 (2.8655)	
[2022-01-26 01:17:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][820/1251]	eta 0:15:51 lr 0.000051	time 2.1961 (2.2085)	loss 2.2891 (3.0720)	grad_norm 2.9628 (2.8657)	
[2022-01-26 01:17:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][830/1251]	eta 0:15:29 lr 0.000051	time 3.0889 (2.2090)	loss 2.2308 (3.0702)	grad_norm 2.6144 (2.8634)	
[2022-01-26 01:17:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][840/1251]	eta 0:15:08 lr 0.000051	time 2.5037 (2.2101)	loss 2.5802 (3.0700)	grad_norm 2.5809 (2.8634)	
[2022-01-26 01:18:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][850/1251]	eta 0:14:45 lr 0.000051	time 1.9465 (2.2092)	loss 3.6644 (3.0709)	grad_norm 2.7686 (2.8632)	
[2022-01-26 01:18:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][860/1251]	eta 0:14:23 lr 0.000051	time 2.3774 (2.2090)	loss 3.3627 (3.0680)	grad_norm 2.8604 (2.8615)	
[2022-01-26 01:18:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][870/1251]	eta 0:14:01 lr 0.000051	time 2.2756 (2.2093)	loss 2.0705 (3.0669)	grad_norm 2.5647 (2.8603)	
[2022-01-26 01:19:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][880/1251]	eta 0:13:39 lr 0.000051	time 1.7761 (2.2085)	loss 3.2588 (3.0665)	grad_norm 2.7274 (2.8595)	
[2022-01-26 01:19:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][890/1251]	eta 0:13:16 lr 0.000051	time 2.2066 (2.2076)	loss 3.4175 (3.0674)	grad_norm 2.5797 (2.8582)	
[2022-01-26 01:20:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][900/1251]	eta 0:12:54 lr 0.000051	time 2.5464 (2.2064)	loss 2.4734 (3.0645)	grad_norm 2.7066 (2.8569)	
[2022-01-26 01:20:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][910/1251]	eta 0:12:32 lr 0.000051	time 1.9387 (2.2058)	loss 2.4434 (3.0650)	grad_norm 2.1318 (2.8582)	
[2022-01-26 01:20:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][920/1251]	eta 0:12:09 lr 0.000051	time 2.1676 (2.2044)	loss 2.8099 (3.0626)	grad_norm 2.4789 (2.8563)	
[2022-01-26 01:21:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][930/1251]	eta 0:11:47 lr 0.000051	time 1.9584 (2.2055)	loss 2.3125 (3.0635)	grad_norm 2.8822 (2.8571)	
[2022-01-26 01:21:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][940/1251]	eta 0:11:26 lr 0.000051	time 2.7209 (2.2059)	loss 3.3889 (3.0642)	grad_norm 2.5078 (2.8575)	
[2022-01-26 01:21:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][950/1251]	eta 0:11:04 lr 0.000051	time 2.8564 (2.2060)	loss 3.1249 (3.0634)	grad_norm 2.7135 (2.8572)	
[2022-01-26 01:22:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][960/1251]	eta 0:10:41 lr 0.000051	time 1.6112 (2.2053)	loss 2.6047 (3.0589)	grad_norm 2.3522 (2.8562)	
[2022-01-26 01:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][970/1251]	eta 0:10:19 lr 0.000051	time 1.5660 (2.2055)	loss 3.5748 (3.0608)	grad_norm 3.3105 (2.8558)	
[2022-01-26 01:22:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][980/1251]	eta 0:09:57 lr 0.000051	time 3.1103 (2.2060)	loss 2.8409 (3.0584)	grad_norm 2.9205 (2.8563)	
[2022-01-26 01:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][990/1251]	eta 0:09:35 lr 0.000051	time 2.7910 (2.2055)	loss 3.2570 (3.0592)	grad_norm 3.3809 (2.8574)	
[2022-01-26 01:23:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1000/1251]	eta 0:09:13 lr 0.000051	time 1.8638 (2.2046)	loss 2.7204 (3.0571)	grad_norm 2.4480 (2.8561)	
[2022-01-26 01:24:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1010/1251]	eta 0:08:50 lr 0.000051	time 1.9278 (2.2033)	loss 3.2638 (3.0576)	grad_norm 3.1551 (2.8552)	
[2022-01-26 01:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1020/1251]	eta 0:08:28 lr 0.000051	time 2.2380 (2.2028)	loss 3.7043 (3.0568)	grad_norm 3.7100 (2.8571)	
[2022-01-26 01:24:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1030/1251]	eta 0:08:06 lr 0.000051	time 3.3391 (2.2036)	loss 3.2732 (3.0587)	grad_norm 3.2106 (2.8565)	
[2022-01-26 01:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1040/1251]	eta 0:07:45 lr 0.000051	time 2.1021 (2.2053)	loss 3.7364 (3.0598)	grad_norm 3.5807 (2.8571)	
[2022-01-26 01:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1050/1251]	eta 0:07:23 lr 0.000051	time 2.5226 (2.2051)	loss 3.5184 (3.0595)	grad_norm 3.2138 (2.8579)	
[2022-01-26 01:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1060/1251]	eta 0:07:00 lr 0.000051	time 1.9716 (2.2036)	loss 3.5519 (3.0604)	grad_norm 2.7322 (2.8579)	
[2022-01-26 01:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1070/1251]	eta 0:06:38 lr 0.000051	time 3.3651 (2.2038)	loss 3.5509 (3.0592)	grad_norm 2.7254 (2.8581)	
[2022-01-26 01:26:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1080/1251]	eta 0:06:16 lr 0.000051	time 2.1821 (2.2031)	loss 2.8984 (3.0587)	grad_norm 3.7107 (2.8572)	
[2022-01-26 01:26:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1090/1251]	eta 0:05:54 lr 0.000051	time 2.3845 (2.2027)	loss 2.8452 (3.0572)	grad_norm 2.8919 (2.8579)	
[2022-01-26 01:27:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1100/1251]	eta 0:05:32 lr 0.000051	time 2.0936 (2.2033)	loss 2.1153 (3.0581)	grad_norm 2.7685 (2.8565)	
[2022-01-26 01:27:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1110/1251]	eta 0:05:10 lr 0.000051	time 3.1567 (2.2039)	loss 3.1648 (3.0552)	grad_norm 4.2947 (2.8580)	
[2022-01-26 01:28:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1120/1251]	eta 0:04:48 lr 0.000051	time 2.2225 (2.2040)	loss 3.7020 (3.0547)	grad_norm 2.6892 (2.8579)	
[2022-01-26 01:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1130/1251]	eta 0:04:26 lr 0.000051	time 1.9285 (2.2021)	loss 3.4624 (3.0561)	grad_norm 2.7849 (2.8583)	
[2022-01-26 01:28:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1140/1251]	eta 0:04:04 lr 0.000051	time 2.3714 (2.2010)	loss 3.0413 (3.0569)	grad_norm 2.4853 (2.8564)	
[2022-01-26 01:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1150/1251]	eta 0:03:42 lr 0.000051	time 2.5111 (2.2007)	loss 3.6496 (3.0567)	grad_norm 2.8281 (2.8548)	
[2022-01-26 01:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1160/1251]	eta 0:03:20 lr 0.000051	time 1.9502 (2.2000)	loss 3.4454 (3.0568)	grad_norm 2.9021 (2.8539)	
[2022-01-26 01:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1170/1251]	eta 0:02:58 lr 0.000051	time 2.2003 (2.2000)	loss 3.1110 (3.0583)	grad_norm 2.3865 (2.8542)	
[2022-01-26 01:30:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1180/1251]	eta 0:02:36 lr 0.000051	time 2.9922 (2.2006)	loss 2.2605 (3.0557)	grad_norm 2.9920 (2.8538)	
[2022-01-26 01:30:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1190/1251]	eta 0:02:14 lr 0.000051	time 2.3020 (2.2011)	loss 3.3360 (3.0574)	grad_norm 2.7899 (2.8566)	
[2022-01-26 01:30:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1200/1251]	eta 0:01:52 lr 0.000051	time 2.4724 (2.2019)	loss 3.0763 (3.0575)	grad_norm 2.5197 (2.8561)	
[2022-01-26 01:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1210/1251]	eta 0:01:30 lr 0.000051	time 2.2232 (2.2023)	loss 2.3539 (3.0588)	grad_norm 2.6590 (2.8561)	
[2022-01-26 01:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1220/1251]	eta 0:01:08 lr 0.000051	time 3.1808 (2.2025)	loss 2.8517 (3.0590)	grad_norm 3.2597 (2.8561)	
[2022-01-26 01:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1230/1251]	eta 0:00:46 lr 0.000051	time 1.9019 (2.2013)	loss 3.1880 (3.0606)	grad_norm 2.9226 (2.8560)	
[2022-01-26 01:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1240/1251]	eta 0:00:24 lr 0.000051	time 1.2730 (2.1992)	loss 2.6307 (3.0599)	grad_norm 2.7704 (2.8558)	
[2022-01-26 01:32:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [260/300][1250/1251]	eta 0:00:02 lr 0.000051	time 1.3305 (2.1936)	loss 2.0655 (3.0573)	grad_norm 2.8272 (2.8565)	
[2022-01-26 01:32:38 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 260 training takes 0:45:44
[2022-01-26 01:32:38 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_260 saving......
[2022-01-26 01:32:50 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_260 saved !!!
[2022-01-26 01:33:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.497 (16.497)	Loss 0.7885 (0.7885)	Acc@1 81.836 (81.836)	Acc@5 95.996 (95.996)	
[2022-01-26 01:33:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.263 (3.011)	Loss 0.7805 (0.8286)	Acc@1 81.543 (80.726)	Acc@5 96.094 (95.543)	
[2022-01-26 01:33:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.935 (2.413)	Loss 0.6847 (0.8131)	Acc@1 83.789 (80.855)	Acc@5 96.582 (95.522)	
[2022-01-26 01:33:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.662 (2.131)	Loss 0.7754 (0.8167)	Acc@1 81.445 (80.844)	Acc@5 96.289 (95.505)	
[2022-01-26 01:34:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.138 (1.993)	Loss 0.8651 (0.8229)	Acc@1 79.590 (80.664)	Acc@5 94.141 (95.401)	
[2022-01-26 01:34:19 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.640 Acc@5 95.364
[2022-01-26 01:34:19 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.6%
[2022-01-26 01:34:19 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.78%
[2022-01-26 01:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][0/1251]	eta 7:14:08 lr 0.000051	time 20.8222 (20.8222)	loss 3.4855 (3.4855)	grad_norm 3.0142 (3.0142)	
[2022-01-26 01:35:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][10/1251]	eta 1:23:29 lr 0.000051	time 2.7828 (4.0364)	loss 2.8494 (2.9937)	grad_norm 2.5835 (2.7920)	
[2022-01-26 01:35:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][20/1251]	eta 1:03:58 lr 0.000051	time 1.4168 (3.1185)	loss 3.6601 (3.1223)	grad_norm 3.1124 (2.8771)	
[2022-01-26 01:35:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][30/1251]	eta 0:57:24 lr 0.000051	time 1.9519 (2.8208)	loss 3.5192 (3.0456)	grad_norm 2.8293 (2.8883)	
[2022-01-26 01:36:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][40/1251]	eta 0:54:55 lr 0.000051	time 3.1144 (2.7209)	loss 2.5985 (3.0802)	grad_norm 2.2309 (2.8873)	
[2022-01-26 01:36:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][50/1251]	eta 0:53:09 lr 0.000051	time 2.2290 (2.6554)	loss 3.0841 (3.0234)	grad_norm 2.9522 (2.8536)	
[2022-01-26 01:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][60/1251]	eta 0:51:01 lr 0.000051	time 2.4366 (2.5706)	loss 3.3127 (2.9978)	grad_norm 2.8841 (2.8450)	
[2022-01-26 01:37:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][70/1251]	eta 0:49:11 lr 0.000051	time 1.9295 (2.4993)	loss 2.6253 (2.9972)	grad_norm 2.9804 (2.8675)	
[2022-01-26 01:37:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][80/1251]	eta 0:48:16 lr 0.000051	time 2.4570 (2.4739)	loss 1.9503 (2.9620)	grad_norm 2.8142 (2.8611)	
[2022-01-26 01:38:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][90/1251]	eta 0:47:15 lr 0.000051	time 2.1011 (2.4421)	loss 3.2293 (2.9687)	grad_norm 2.9042 (2.8538)	
[2022-01-26 01:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][100/1251]	eta 0:46:38 lr 0.000051	time 3.3618 (2.4311)	loss 3.5273 (2.9757)	grad_norm 2.8136 (2.8436)	
[2022-01-26 01:38:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][110/1251]	eta 0:45:50 lr 0.000051	time 1.9146 (2.4104)	loss 3.3155 (2.9764)	grad_norm 2.4592 (2.8457)	
[2022-01-26 01:39:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][120/1251]	eta 0:44:55 lr 0.000051	time 2.1266 (2.3835)	loss 3.2370 (2.9796)	grad_norm 2.3817 (2.8377)	
[2022-01-26 01:39:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][130/1251]	eta 0:44:25 lr 0.000050	time 2.3895 (2.3774)	loss 2.9669 (2.9932)	grad_norm 3.7700 (2.8442)	
[2022-01-26 01:39:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][140/1251]	eta 0:43:59 lr 0.000050	time 3.3446 (2.3756)	loss 1.9987 (2.9924)	grad_norm 2.6936 (2.8398)	
[2022-01-26 01:40:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][150/1251]	eta 0:43:06 lr 0.000050	time 1.5980 (2.3494)	loss 2.9597 (3.0151)	grad_norm 2.7154 (2.8446)	
[2022-01-26 01:40:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][160/1251]	eta 0:42:22 lr 0.000050	time 1.8527 (2.3301)	loss 3.2968 (3.0265)	grad_norm 2.4334 (2.8444)	
[2022-01-26 01:40:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][170/1251]	eta 0:41:58 lr 0.000050	time 2.8120 (2.3299)	loss 2.2765 (3.0271)	grad_norm 3.4480 (2.9059)	
[2022-01-26 01:41:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][180/1251]	eta 0:41:27 lr 0.000050	time 2.2180 (2.3230)	loss 2.9673 (3.0212)	grad_norm 3.1598 (2.9044)	
[2022-01-26 01:41:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][190/1251]	eta 0:40:54 lr 0.000050	time 2.1209 (2.3132)	loss 2.9312 (3.0225)	grad_norm 3.0723 (2.9053)	
[2022-01-26 01:42:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][200/1251]	eta 0:40:32 lr 0.000050	time 1.6005 (2.3143)	loss 3.4181 (3.0254)	grad_norm 2.5592 (2.9101)	
[2022-01-26 01:42:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][210/1251]	eta 0:40:08 lr 0.000050	time 2.7156 (2.3133)	loss 3.1880 (3.0259)	grad_norm 2.6953 (2.9184)	
[2022-01-26 01:42:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][220/1251]	eta 0:39:30 lr 0.000050	time 1.8237 (2.2992)	loss 3.2241 (3.0390)	grad_norm 2.7058 (2.9179)	
[2022-01-26 01:43:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][230/1251]	eta 0:38:52 lr 0.000050	time 2.1578 (2.2845)	loss 2.4674 (3.0349)	grad_norm 3.2089 (2.9282)	
[2022-01-26 01:43:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][240/1251]	eta 0:38:23 lr 0.000050	time 2.0474 (2.2783)	loss 3.5783 (3.0352)	grad_norm 2.4323 (2.9264)	
[2022-01-26 01:43:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][250/1251]	eta 0:38:04 lr 0.000050	time 3.0583 (2.2822)	loss 2.2326 (3.0254)	grad_norm 3.1482 (2.9189)	
[2022-01-26 01:44:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][260/1251]	eta 0:37:42 lr 0.000050	time 1.9898 (2.2835)	loss 3.1024 (3.0188)	grad_norm 2.8721 (2.9268)	
[2022-01-26 01:44:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][270/1251]	eta 0:37:18 lr 0.000050	time 2.0460 (2.2819)	loss 3.2439 (3.0240)	grad_norm 2.7619 (2.9247)	
[2022-01-26 01:44:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][280/1251]	eta 0:36:50 lr 0.000050	time 1.7439 (2.2765)	loss 2.8170 (3.0235)	grad_norm 2.6511 (2.9189)	
[2022-01-26 01:45:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][290/1251]	eta 0:36:27 lr 0.000050	time 2.9578 (2.2758)	loss 3.5762 (3.0285)	grad_norm 2.5977 (2.9131)	
[2022-01-26 01:45:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][300/1251]	eta 0:35:54 lr 0.000050	time 1.9297 (2.2660)	loss 3.0725 (3.0277)	grad_norm 2.8158 (2.9084)	
[2022-01-26 01:46:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][310/1251]	eta 0:35:27 lr 0.000050	time 2.2138 (2.2609)	loss 3.4361 (3.0287)	grad_norm 2.5450 (2.9021)	
[2022-01-26 01:46:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][320/1251]	eta 0:35:02 lr 0.000050	time 2.1718 (2.2580)	loss 2.6314 (3.0306)	grad_norm 2.5340 (2.8992)	
[2022-01-26 01:46:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][330/1251]	eta 0:34:39 lr 0.000050	time 2.8365 (2.2583)	loss 1.9267 (3.0320)	grad_norm 2.8277 (2.9010)	
[2022-01-26 01:47:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][340/1251]	eta 0:34:19 lr 0.000050	time 2.0652 (2.2604)	loss 2.7404 (3.0245)	grad_norm 2.6418 (2.9019)	
[2022-01-26 01:47:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][350/1251]	eta 0:33:57 lr 0.000050	time 1.6480 (2.2614)	loss 3.2812 (3.0268)	grad_norm 2.7175 (2.8995)	
[2022-01-26 01:47:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][360/1251]	eta 0:33:35 lr 0.000050	time 2.5675 (2.2624)	loss 3.1616 (3.0211)	grad_norm 3.7608 (2.9011)	
[2022-01-26 01:48:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][370/1251]	eta 0:33:12 lr 0.000050	time 3.4044 (2.2614)	loss 2.8469 (3.0252)	grad_norm 2.6088 (2.9023)	
[2022-01-26 01:48:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][380/1251]	eta 0:32:43 lr 0.000050	time 1.6375 (2.2543)	loss 3.5019 (3.0273)	grad_norm 2.7862 (2.8964)	
[2022-01-26 01:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][390/1251]	eta 0:32:17 lr 0.000050	time 2.5018 (2.2506)	loss 2.2677 (3.0233)	grad_norm 2.7786 (2.8927)	
[2022-01-26 01:49:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][400/1251]	eta 0:31:49 lr 0.000050	time 1.8362 (2.2440)	loss 2.8223 (3.0282)	grad_norm 2.7597 (2.8872)	
[2022-01-26 01:49:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][410/1251]	eta 0:31:27 lr 0.000050	time 3.4275 (2.2440)	loss 3.1926 (3.0251)	grad_norm 2.4696 (2.8901)	
[2022-01-26 01:50:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][420/1251]	eta 0:31:04 lr 0.000050	time 2.3053 (2.2436)	loss 1.8963 (3.0257)	grad_norm 2.7623 (2.8880)	
[2022-01-26 01:50:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][430/1251]	eta 0:30:44 lr 0.000050	time 2.7179 (2.2465)	loss 3.2759 (3.0245)	grad_norm 2.4387 (2.8871)	
[2022-01-26 01:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][440/1251]	eta 0:30:19 lr 0.000050	time 2.1699 (2.2438)	loss 2.4424 (3.0264)	grad_norm 3.1672 (2.8829)	
[2022-01-26 01:51:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][450/1251]	eta 0:29:58 lr 0.000050	time 2.7142 (2.2447)	loss 3.3341 (3.0263)	grad_norm 3.0078 (2.8826)	
[2022-01-26 01:51:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][460/1251]	eta 0:29:33 lr 0.000050	time 2.3508 (2.2417)	loss 2.5903 (3.0218)	grad_norm 3.5432 (2.8845)	
[2022-01-26 01:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][470/1251]	eta 0:29:10 lr 0.000050	time 1.7190 (2.2417)	loss 3.3593 (3.0218)	grad_norm 2.4858 (2.8839)	
[2022-01-26 01:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][480/1251]	eta 0:28:47 lr 0.000050	time 1.5416 (2.2410)	loss 2.1070 (3.0220)	grad_norm 5.7927 (2.8912)	
[2022-01-26 01:52:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][490/1251]	eta 0:28:24 lr 0.000050	time 2.4397 (2.2400)	loss 2.5351 (3.0188)	grad_norm 3.3374 (2.8938)	
[2022-01-26 01:53:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][500/1251]	eta 0:27:59 lr 0.000050	time 2.1116 (2.2365)	loss 3.1367 (3.0197)	grad_norm 2.5423 (2.8971)	
[2022-01-26 01:53:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][510/1251]	eta 0:27:36 lr 0.000050	time 1.4982 (2.2349)	loss 2.1611 (3.0168)	grad_norm 3.3035 (2.9023)	
[2022-01-26 01:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][520/1251]	eta 0:27:16 lr 0.000050	time 2.3154 (2.2385)	loss 3.7404 (3.0178)	grad_norm 2.9127 (2.9025)	
[2022-01-26 01:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][530/1251]	eta 0:26:53 lr 0.000050	time 2.3142 (2.2373)	loss 2.9001 (3.0247)	grad_norm 2.6121 (2.9017)	
[2022-01-26 01:54:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][540/1251]	eta 0:26:27 lr 0.000050	time 1.7677 (2.2331)	loss 3.1355 (3.0212)	grad_norm 2.8078 (2.9003)	
[2022-01-26 01:54:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][550/1251]	eta 0:26:03 lr 0.000050	time 1.5392 (2.2309)	loss 2.0486 (3.0210)	grad_norm 2.9648 (2.9003)	
[2022-01-26 01:55:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][560/1251]	eta 0:25:39 lr 0.000050	time 1.6026 (2.2275)	loss 3.6311 (3.0208)	grad_norm 2.8316 (2.9009)	
[2022-01-26 01:55:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][570/1251]	eta 0:25:16 lr 0.000050	time 1.8392 (2.2270)	loss 2.6336 (3.0224)	grad_norm 2.9306 (2.9023)	
[2022-01-26 01:55:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][580/1251]	eta 0:24:53 lr 0.000050	time 1.9183 (2.2257)	loss 2.1905 (3.0203)	grad_norm 2.8285 (2.9007)	
[2022-01-26 01:56:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][590/1251]	eta 0:24:31 lr 0.000050	time 1.8578 (2.2268)	loss 2.6307 (3.0215)	grad_norm 3.0102 (2.9074)	
[2022-01-26 01:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][600/1251]	eta 0:24:12 lr 0.000050	time 2.7687 (2.2309)	loss 2.7142 (3.0246)	grad_norm 2.8217 (2.9056)	
[2022-01-26 01:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][610/1251]	eta 0:23:50 lr 0.000050	time 1.8312 (2.2313)	loss 2.8995 (3.0255)	grad_norm 2.7186 (2.9046)	
[2022-01-26 01:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][620/1251]	eta 0:23:27 lr 0.000050	time 1.9680 (2.2302)	loss 3.1851 (3.0272)	grad_norm 2.8168 (2.9035)	
[2022-01-26 01:57:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][630/1251]	eta 0:23:03 lr 0.000050	time 1.9138 (2.2284)	loss 2.8926 (3.0303)	grad_norm 3.3384 (2.9053)	
[2022-01-26 01:58:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][640/1251]	eta 0:22:40 lr 0.000050	time 3.1196 (2.2275)	loss 2.9413 (3.0308)	grad_norm 2.4689 (2.9033)	
[2022-01-26 01:58:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][650/1251]	eta 0:22:17 lr 0.000050	time 2.1767 (2.2254)	loss 2.0226 (3.0303)	grad_norm 2.6358 (2.9025)	
[2022-01-26 01:58:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][660/1251]	eta 0:21:53 lr 0.000050	time 1.8564 (2.2228)	loss 2.9265 (3.0274)	grad_norm 3.0187 (2.9037)	
[2022-01-26 01:59:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][670/1251]	eta 0:21:30 lr 0.000050	time 2.1668 (2.2203)	loss 3.0397 (3.0274)	grad_norm 2.3611 (2.9048)	
[2022-01-26 01:59:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][680/1251]	eta 0:21:06 lr 0.000050	time 2.1749 (2.2188)	loss 2.8746 (3.0289)	grad_norm 2.6868 (2.9025)	
[2022-01-26 01:59:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][690/1251]	eta 0:20:43 lr 0.000050	time 2.2633 (2.2173)	loss 3.0303 (3.0291)	grad_norm 2.5327 (2.9015)	
[2022-01-26 02:00:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][700/1251]	eta 0:20:21 lr 0.000050	time 2.4989 (2.2177)	loss 3.3230 (3.0314)	grad_norm 3.0712 (2.8998)	
[2022-01-26 02:00:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][710/1251]	eta 0:19:59 lr 0.000050	time 2.1800 (2.2174)	loss 2.5814 (3.0319)	grad_norm 2.6844 (2.8999)	
[2022-01-26 02:00:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][720/1251]	eta 0:19:37 lr 0.000050	time 2.5284 (2.2182)	loss 2.7512 (3.0343)	grad_norm 2.9140 (2.9006)	
[2022-01-26 02:01:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][730/1251]	eta 0:19:17 lr 0.000050	time 3.0806 (2.2208)	loss 2.8797 (3.0382)	grad_norm 2.8183 (2.9015)	
[2022-01-26 02:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][740/1251]	eta 0:18:55 lr 0.000050	time 2.7718 (2.2225)	loss 2.3255 (3.0372)	grad_norm 2.5004 (2.8985)	
[2022-01-26 02:02:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][750/1251]	eta 0:18:33 lr 0.000049	time 2.1569 (2.2228)	loss 3.0410 (3.0347)	grad_norm 2.4997 (2.8972)	
[2022-01-26 02:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][760/1251]	eta 0:18:10 lr 0.000049	time 1.8690 (2.2208)	loss 2.6270 (3.0319)	grad_norm 2.9819 (2.8971)	
[2022-01-26 02:02:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][770/1251]	eta 0:17:46 lr 0.000049	time 2.2405 (2.2169)	loss 3.2774 (3.0300)	grad_norm 2.4226 (2.8976)	
[2022-01-26 02:03:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][780/1251]	eta 0:17:23 lr 0.000049	time 1.9411 (2.2148)	loss 2.4441 (3.0316)	grad_norm 2.9961 (2.8985)	
[2022-01-26 02:03:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][790/1251]	eta 0:17:00 lr 0.000049	time 2.2047 (2.2135)	loss 2.1004 (3.0340)	grad_norm 2.7014 (2.8986)	
[2022-01-26 02:03:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][800/1251]	eta 0:16:38 lr 0.000049	time 1.9708 (2.2129)	loss 3.6547 (3.0334)	grad_norm 2.8610 (2.8977)	
[2022-01-26 02:04:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][810/1251]	eta 0:16:16 lr 0.000049	time 1.9210 (2.2136)	loss 3.2594 (3.0345)	grad_norm 2.7921 (2.8989)	
[2022-01-26 02:04:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][820/1251]	eta 0:15:53 lr 0.000049	time 1.6835 (2.2133)	loss 2.8626 (3.0357)	grad_norm 3.4832 (2.8995)	
[2022-01-26 02:04:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][830/1251]	eta 0:15:31 lr 0.000049	time 2.1728 (2.2128)	loss 3.2745 (3.0389)	grad_norm 2.7967 (2.8997)	
[2022-01-26 02:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][840/1251]	eta 0:15:09 lr 0.000049	time 1.6970 (2.2129)	loss 3.0929 (3.0398)	grad_norm 2.6335 (2.8976)	
[2022-01-26 02:05:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][850/1251]	eta 0:14:47 lr 0.000049	time 2.6992 (2.2128)	loss 3.7079 (3.0421)	grad_norm 4.1636 (2.8983)	
[2022-01-26 02:06:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][860/1251]	eta 0:14:25 lr 0.000049	time 1.9439 (2.2129)	loss 1.9220 (3.0389)	grad_norm 2.6178 (2.8994)	
[2022-01-26 02:06:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][870/1251]	eta 0:14:03 lr 0.000049	time 2.3318 (2.2127)	loss 3.1644 (3.0392)	grad_norm 2.8795 (2.8980)	
[2022-01-26 02:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][880/1251]	eta 0:13:41 lr 0.000049	time 1.5854 (2.2140)	loss 2.4014 (3.0379)	grad_norm 2.6604 (2.8991)	
[2022-01-26 02:07:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][890/1251]	eta 0:13:19 lr 0.000049	time 1.9178 (2.2142)	loss 2.5199 (3.0364)	grad_norm 2.7452 (2.8987)	
[2022-01-26 02:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][900/1251]	eta 0:12:56 lr 0.000049	time 1.6215 (2.2111)	loss 3.1710 (3.0391)	grad_norm 3.2765 (2.8973)	
[2022-01-26 02:07:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][910/1251]	eta 0:12:33 lr 0.000049	time 2.4577 (2.2107)	loss 3.1732 (3.0388)	grad_norm 2.8059 (2.8970)	
[2022-01-26 02:08:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][920/1251]	eta 0:12:11 lr 0.000049	time 1.8341 (2.2098)	loss 3.3564 (3.0381)	grad_norm 2.4254 (2.8951)	
[2022-01-26 02:08:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][930/1251]	eta 0:11:48 lr 0.000049	time 1.5849 (2.2083)	loss 3.3852 (3.0401)	grad_norm 2.4905 (2.8938)	
[2022-01-26 02:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][940/1251]	eta 0:11:26 lr 0.000049	time 1.9486 (2.2075)	loss 2.8095 (3.0415)	grad_norm 2.7415 (2.8933)	
[2022-01-26 02:09:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][950/1251]	eta 0:11:04 lr 0.000049	time 2.4099 (2.2078)	loss 2.4227 (3.0410)	grad_norm 2.8684 (2.8931)	
[2022-01-26 02:09:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][960/1251]	eta 0:10:42 lr 0.000049	time 2.5751 (2.2086)	loss 3.8162 (3.0424)	grad_norm 2.8242 (2.8925)	
[2022-01-26 02:10:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][970/1251]	eta 0:10:20 lr 0.000049	time 1.9449 (2.2097)	loss 3.0287 (3.0447)	grad_norm 3.5293 (2.8937)	
[2022-01-26 02:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][980/1251]	eta 0:09:59 lr 0.000049	time 2.5051 (2.2112)	loss 2.5772 (3.0442)	grad_norm 2.4104 (2.8916)	
[2022-01-26 02:10:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][990/1251]	eta 0:09:37 lr 0.000049	time 3.9172 (2.2145)	loss 3.2981 (3.0451)	grad_norm 3.2025 (2.8919)	
[2022-01-26 02:11:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1000/1251]	eta 0:09:15 lr 0.000049	time 2.6745 (2.2145)	loss 3.1637 (3.0462)	grad_norm 2.5895 (2.8936)	
[2022-01-26 02:11:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1010/1251]	eta 0:08:53 lr 0.000049	time 1.8250 (2.2134)	loss 2.3035 (3.0450)	grad_norm 2.5052 (2.8930)	
[2022-01-26 02:11:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1020/1251]	eta 0:08:30 lr 0.000049	time 1.6201 (2.2103)	loss 3.1757 (3.0444)	grad_norm 2.6106 (2.8917)	
[2022-01-26 02:12:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1030/1251]	eta 0:08:08 lr 0.000049	time 2.6096 (2.2086)	loss 3.7806 (3.0447)	grad_norm 2.9652 (2.8915)	
[2022-01-26 02:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1040/1251]	eta 0:07:45 lr 0.000049	time 2.2113 (2.2074)	loss 2.9398 (3.0441)	grad_norm 3.7673 (2.8930)	
[2022-01-26 02:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1050/1251]	eta 0:07:23 lr 0.000049	time 1.8124 (2.2076)	loss 3.4351 (3.0435)	grad_norm 2.9285 (2.8946)	
[2022-01-26 02:13:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1060/1251]	eta 0:07:01 lr 0.000049	time 3.0648 (2.2090)	loss 3.2542 (3.0448)	grad_norm 2.8279 (2.8940)	
[2022-01-26 02:13:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1070/1251]	eta 0:06:40 lr 0.000049	time 1.9720 (2.2102)	loss 2.3591 (3.0456)	grad_norm 3.0384 (2.8939)	
[2022-01-26 02:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1080/1251]	eta 0:06:18 lr 0.000049	time 1.8828 (2.2119)	loss 3.0205 (3.0461)	grad_norm 4.0653 (2.8953)	
[2022-01-26 02:14:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1090/1251]	eta 0:05:56 lr 0.000049	time 1.5193 (2.2117)	loss 2.1410 (3.0451)	grad_norm 2.9244 (2.8944)	
[2022-01-26 02:14:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1100/1251]	eta 0:05:33 lr 0.000049	time 1.9228 (2.2106)	loss 2.8178 (3.0470)	grad_norm 2.9517 (2.8931)	
[2022-01-26 02:15:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1110/1251]	eta 0:05:11 lr 0.000049	time 1.8482 (2.2083)	loss 2.4168 (3.0469)	grad_norm 2.7542 (2.8921)	
[2022-01-26 02:15:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1120/1251]	eta 0:04:49 lr 0.000049	time 2.2326 (2.2075)	loss 3.3879 (3.0461)	grad_norm 3.0298 (2.8918)	
[2022-01-26 02:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1130/1251]	eta 0:04:27 lr 0.000049	time 1.6983 (2.2066)	loss 3.4429 (3.0481)	grad_norm 3.0261 (2.8917)	
[2022-01-26 02:16:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1140/1251]	eta 0:04:04 lr 0.000049	time 2.4468 (2.2066)	loss 2.5278 (3.0481)	grad_norm 2.4206 (2.8881)	
[2022-01-26 02:16:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1150/1251]	eta 0:03:42 lr 0.000049	time 2.5700 (2.2060)	loss 2.2526 (3.0479)	grad_norm 2.3109 (2.8867)	
[2022-01-26 02:17:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1160/1251]	eta 0:03:20 lr 0.000049	time 1.8619 (2.2065)	loss 3.1766 (3.0487)	grad_norm 3.1821 (2.8877)	
[2022-01-26 02:17:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1170/1251]	eta 0:02:58 lr 0.000049	time 1.5193 (2.2054)	loss 3.2436 (3.0487)	grad_norm 2.6420 (2.8878)	
[2022-01-26 02:17:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1180/1251]	eta 0:02:36 lr 0.000049	time 2.9255 (2.2052)	loss 3.5661 (3.0502)	grad_norm 2.8372 (2.8871)	
[2022-01-26 02:18:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1190/1251]	eta 0:02:14 lr 0.000049	time 2.5165 (2.2065)	loss 3.3530 (3.0515)	grad_norm 2.5036 (2.8869)	
[2022-01-26 02:18:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1200/1251]	eta 0:01:52 lr 0.000049	time 2.7017 (2.2072)	loss 3.3854 (3.0511)	grad_norm 2.9512 (2.8864)	
[2022-01-26 02:18:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1210/1251]	eta 0:01:30 lr 0.000049	time 2.2350 (2.2072)	loss 3.2751 (3.0494)	grad_norm 2.8506 (2.8847)	
[2022-01-26 02:19:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1220/1251]	eta 0:01:08 lr 0.000049	time 2.2061 (2.2072)	loss 3.5558 (3.0509)	grad_norm 2.8573 (2.8834)	
[2022-01-26 02:19:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1230/1251]	eta 0:00:46 lr 0.000049	time 2.2793 (2.2064)	loss 2.8225 (3.0508)	grad_norm 4.0268 (2.8835)	
[2022-01-26 02:19:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1240/1251]	eta 0:00:24 lr 0.000049	time 1.6246 (2.2042)	loss 2.3441 (3.0526)	grad_norm 2.8456 (2.8818)	
[2022-01-26 02:20:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [261/300][1250/1251]	eta 0:00:02 lr 0.000049	time 1.1797 (2.1982)	loss 3.3828 (3.0527)	grad_norm 3.1654 (2.8817)	
[2022-01-26 02:20:10 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 261 training takes 0:45:50
[2022-01-26 02:20:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.792 (18.792)	Loss 0.8787 (0.8787)	Acc@1 80.762 (80.762)	Acc@5 94.043 (94.043)	
[2022-01-26 02:20:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.946 (3.480)	Loss 0.7680 (0.8403)	Acc@1 82.422 (80.691)	Acc@5 96.094 (95.091)	
[2022-01-26 02:21:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.193 (2.679)	Loss 0.8194 (0.8384)	Acc@1 80.566 (80.408)	Acc@5 94.922 (95.103)	
[2022-01-26 02:21:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.628 (2.341)	Loss 0.8658 (0.8371)	Acc@1 80.078 (80.462)	Acc@5 94.629 (95.190)	
[2022-01-26 02:21:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.368 (2.221)	Loss 0.7909 (0.8299)	Acc@1 81.445 (80.597)	Acc@5 95.215 (95.279)	
[2022-01-26 02:21:48 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.644 Acc@5 95.346
[2022-01-26 02:21:48 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.6%
[2022-01-26 02:21:48 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.78%
[2022-01-26 02:22:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][0/1251]	eta 7:39:35 lr 0.000049	time 22.0430 (22.0430)	loss 3.1568 (3.1568)	grad_norm 2.6349 (2.6349)	
[2022-01-26 02:22:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][10/1251]	eta 1:25:49 lr 0.000049	time 3.0236 (4.1493)	loss 3.3845 (3.1079)	grad_norm 3.1798 (2.8634)	
[2022-01-26 02:22:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][20/1251]	eta 1:05:31 lr 0.000049	time 1.8067 (3.1941)	loss 3.1294 (3.0445)	grad_norm 2.5836 (2.8602)	
[2022-01-26 02:23:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][30/1251]	eta 0:57:53 lr 0.000049	time 1.7571 (2.8450)	loss 3.5190 (3.0689)	grad_norm 3.5143 (2.8157)	
[2022-01-26 02:23:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][40/1251]	eta 0:53:51 lr 0.000049	time 2.9830 (2.6683)	loss 2.8153 (3.0462)	grad_norm 2.5073 (2.7802)	
[2022-01-26 02:24:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][50/1251]	eta 0:52:16 lr 0.000049	time 2.3548 (2.6116)	loss 3.3482 (3.0336)	grad_norm 2.6765 (2.7882)	
[2022-01-26 02:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][60/1251]	eta 0:50:35 lr 0.000049	time 1.9177 (2.5487)	loss 3.7546 (3.0032)	grad_norm 2.7621 (2.8218)	
[2022-01-26 02:24:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][70/1251]	eta 0:49:03 lr 0.000049	time 1.5601 (2.4924)	loss 1.9767 (3.0153)	grad_norm 2.5520 (2.8473)	
[2022-01-26 02:25:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][80/1251]	eta 0:48:07 lr 0.000049	time 2.9281 (2.4656)	loss 3.0608 (2.9869)	grad_norm 2.8946 (2.8540)	
[2022-01-26 02:25:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][90/1251]	eta 0:47:21 lr 0.000049	time 2.0146 (2.4475)	loss 3.4120 (2.9975)	grad_norm 3.0593 (2.8708)	
[2022-01-26 02:25:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][100/1251]	eta 0:46:27 lr 0.000049	time 1.9129 (2.4221)	loss 3.2207 (2.9959)	grad_norm 2.6258 (2.8700)	
[2022-01-26 02:26:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][110/1251]	eta 0:45:28 lr 0.000049	time 1.7055 (2.3915)	loss 2.4599 (2.9815)	grad_norm 2.4071 (2.8663)	
[2022-01-26 02:26:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][120/1251]	eta 0:44:42 lr 0.000048	time 3.0018 (2.3722)	loss 3.5874 (2.9770)	grad_norm 3.8319 (2.8767)	
[2022-01-26 02:26:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][130/1251]	eta 0:44:01 lr 0.000048	time 1.6491 (2.3566)	loss 3.2024 (2.9879)	grad_norm 2.8112 (2.8704)	
[2022-01-26 02:27:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][140/1251]	eta 0:43:23 lr 0.000048	time 1.9243 (2.3435)	loss 3.4057 (2.9837)	grad_norm 2.8641 (2.8623)	
[2022-01-26 02:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][150/1251]	eta 0:42:59 lr 0.000048	time 2.4587 (2.3429)	loss 3.5668 (2.9914)	grad_norm 4.5459 (2.8758)	
[2022-01-26 02:28:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][160/1251]	eta 0:42:29 lr 0.000048	time 2.8900 (2.3366)	loss 2.1691 (2.9946)	grad_norm 2.4586 (2.8812)	
[2022-01-26 02:28:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][170/1251]	eta 0:42:04 lr 0.000048	time 1.5169 (2.3355)	loss 2.7324 (2.9986)	grad_norm 2.9498 (2.8782)	
[2022-01-26 02:28:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][180/1251]	eta 0:41:18 lr 0.000048	time 1.8722 (2.3143)	loss 3.0501 (3.0100)	grad_norm 2.8445 (2.8724)	
[2022-01-26 02:29:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][190/1251]	eta 0:40:53 lr 0.000048	time 2.2227 (2.3120)	loss 2.2717 (3.0167)	grad_norm 2.4466 (2.8617)	
[2022-01-26 02:29:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][200/1251]	eta 0:40:25 lr 0.000048	time 2.4366 (2.3075)	loss 3.5302 (3.0189)	grad_norm 2.8572 (2.8579)	
[2022-01-26 02:29:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][210/1251]	eta 0:40:00 lr 0.000048	time 1.5944 (2.3056)	loss 2.9179 (3.0081)	grad_norm 2.8167 (2.8569)	
[2022-01-26 02:30:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][220/1251]	eta 0:39:34 lr 0.000048	time 1.5040 (2.3029)	loss 2.7273 (3.0089)	grad_norm 3.0152 (2.8558)	
[2022-01-26 02:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][230/1251]	eta 0:39:06 lr 0.000048	time 2.1313 (2.2979)	loss 2.5670 (3.0001)	grad_norm 3.3712 (2.8532)	
[2022-01-26 02:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][240/1251]	eta 0:38:31 lr 0.000048	time 1.7477 (2.2866)	loss 2.8667 (2.9970)	grad_norm 3.1494 (2.8534)	
[2022-01-26 02:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][250/1251]	eta 0:38:04 lr 0.000048	time 1.7323 (2.2826)	loss 3.4720 (2.9911)	grad_norm 2.9288 (2.8501)	
[2022-01-26 02:31:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][260/1251]	eta 0:37:35 lr 0.000048	time 2.1161 (2.2759)	loss 3.1580 (2.9947)	grad_norm 2.8285 (2.8510)	
[2022-01-26 02:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][270/1251]	eta 0:37:09 lr 0.000048	time 1.9482 (2.2725)	loss 3.3574 (3.0058)	grad_norm 2.8419 (2.8564)	
[2022-01-26 02:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][280/1251]	eta 0:36:45 lr 0.000048	time 2.0012 (2.2712)	loss 2.8954 (3.0011)	grad_norm 2.5248 (2.8530)	
[2022-01-26 02:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][290/1251]	eta 0:36:24 lr 0.000048	time 2.2109 (2.2733)	loss 3.3797 (3.0034)	grad_norm 2.6475 (2.8570)	
[2022-01-26 02:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][300/1251]	eta 0:35:56 lr 0.000048	time 1.9389 (2.2677)	loss 1.8784 (3.0011)	grad_norm 2.6196 (2.8579)	
[2022-01-26 02:33:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][310/1251]	eta 0:35:30 lr 0.000048	time 2.1831 (2.2644)	loss 3.6448 (3.0038)	grad_norm 2.9498 (2.8860)	
[2022-01-26 02:33:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][320/1251]	eta 0:35:06 lr 0.000048	time 2.1163 (2.2631)	loss 3.4107 (3.0017)	grad_norm 2.8877 (2.8905)	
[2022-01-26 02:34:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][330/1251]	eta 0:34:46 lr 0.000048	time 2.0717 (2.2657)	loss 3.4873 (3.0012)	grad_norm 2.6796 (2.8940)	
[2022-01-26 02:34:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][340/1251]	eta 0:34:26 lr 0.000048	time 3.1867 (2.2688)	loss 3.3269 (2.9964)	grad_norm 2.5590 (2.8943)	
[2022-01-26 02:35:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][350/1251]	eta 0:33:58 lr 0.000048	time 1.7864 (2.2623)	loss 3.1088 (3.0027)	grad_norm 2.6350 (2.8887)	
[2022-01-26 02:35:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][360/1251]	eta 0:33:26 lr 0.000048	time 1.6898 (2.2525)	loss 2.9718 (2.9927)	grad_norm 2.8473 (2.8880)	
[2022-01-26 02:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][370/1251]	eta 0:32:55 lr 0.000048	time 1.9098 (2.2428)	loss 3.0025 (3.0034)	grad_norm 3.1358 (2.8900)	
[2022-01-26 02:36:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][380/1251]	eta 0:32:31 lr 0.000048	time 2.5379 (2.2409)	loss 3.4633 (3.0051)	grad_norm 2.6708 (2.8949)	
[2022-01-26 02:36:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][390/1251]	eta 0:32:09 lr 0.000048	time 2.4213 (2.2407)	loss 2.5763 (3.0110)	grad_norm 2.7462 (2.9074)	
[2022-01-26 02:36:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][400/1251]	eta 0:31:49 lr 0.000048	time 2.0657 (2.2435)	loss 1.9999 (3.0076)	grad_norm 2.9414 (2.9084)	
[2022-01-26 02:37:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][410/1251]	eta 0:31:30 lr 0.000048	time 2.8326 (2.2480)	loss 3.3936 (3.0169)	grad_norm 2.7906 (2.9098)	
[2022-01-26 02:37:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][420/1251]	eta 0:31:06 lr 0.000048	time 2.3938 (2.2463)	loss 3.5071 (3.0199)	grad_norm 2.6528 (2.9104)	
[2022-01-26 02:37:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][430/1251]	eta 0:30:43 lr 0.000048	time 1.7457 (2.2460)	loss 3.0658 (3.0235)	grad_norm 2.9653 (2.9142)	
[2022-01-26 02:38:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][440/1251]	eta 0:30:23 lr 0.000048	time 1.8381 (2.2480)	loss 3.3809 (3.0198)	grad_norm 3.5228 (2.9160)	
[2022-01-26 02:38:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][450/1251]	eta 0:30:01 lr 0.000048	time 3.3565 (2.2495)	loss 1.8897 (3.0225)	grad_norm 2.7504 (2.9146)	
[2022-01-26 02:39:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][460/1251]	eta 0:29:38 lr 0.000048	time 2.4634 (2.2481)	loss 3.4968 (3.0250)	grad_norm 3.3242 (2.9126)	
[2022-01-26 02:39:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][470/1251]	eta 0:29:12 lr 0.000048	time 1.8990 (2.2443)	loss 3.2434 (3.0215)	grad_norm 2.8968 (2.9128)	
[2022-01-26 02:39:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][480/1251]	eta 0:28:49 lr 0.000048	time 1.9160 (2.2437)	loss 3.5620 (3.0227)	grad_norm 3.1131 (2.9121)	
[2022-01-26 02:40:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][490/1251]	eta 0:28:28 lr 0.000048	time 3.2088 (2.2451)	loss 3.5290 (3.0234)	grad_norm 2.8886 (2.9083)	
[2022-01-26 02:40:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][500/1251]	eta 0:28:05 lr 0.000048	time 2.7379 (2.2448)	loss 3.1779 (3.0239)	grad_norm 2.8911 (2.9061)	
[2022-01-26 02:40:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][510/1251]	eta 0:27:42 lr 0.000048	time 1.9224 (2.2441)	loss 3.2484 (3.0261)	grad_norm 2.8117 (2.9110)	
[2022-01-26 02:41:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][520/1251]	eta 0:27:17 lr 0.000048	time 1.5802 (2.2395)	loss 2.1097 (3.0248)	grad_norm 2.9022 (2.9094)	
[2022-01-26 02:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][530/1251]	eta 0:26:54 lr 0.000048	time 3.4371 (2.2392)	loss 3.4283 (3.0269)	grad_norm 2.5636 (2.9087)	
[2022-01-26 02:41:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][540/1251]	eta 0:26:29 lr 0.000048	time 1.8994 (2.2357)	loss 3.3138 (3.0295)	grad_norm 2.8563 (2.9057)	
[2022-01-26 02:42:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][550/1251]	eta 0:26:06 lr 0.000048	time 2.4335 (2.2347)	loss 3.2586 (3.0269)	grad_norm 2.7204 (2.9023)	
[2022-01-26 02:42:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][560/1251]	eta 0:25:43 lr 0.000048	time 1.9912 (2.2342)	loss 2.1396 (3.0242)	grad_norm 2.6082 (2.9022)	
[2022-01-26 02:43:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][570/1251]	eta 0:25:21 lr 0.000048	time 2.9889 (2.2340)	loss 3.4755 (3.0291)	grad_norm 2.9213 (2.9033)	
[2022-01-26 02:43:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][580/1251]	eta 0:24:58 lr 0.000048	time 2.1637 (2.2329)	loss 1.9558 (3.0338)	grad_norm 2.7538 (2.9018)	
[2022-01-26 02:43:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][590/1251]	eta 0:24:35 lr 0.000048	time 2.2001 (2.2315)	loss 3.1461 (3.0340)	grad_norm 3.0554 (2.9043)	
[2022-01-26 02:44:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][600/1251]	eta 0:24:12 lr 0.000048	time 1.6330 (2.2314)	loss 3.0888 (3.0369)	grad_norm 3.2883 (2.9030)	
[2022-01-26 02:44:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][610/1251]	eta 0:23:49 lr 0.000048	time 2.7568 (2.2303)	loss 3.0785 (3.0409)	grad_norm 2.4931 (2.9037)	
[2022-01-26 02:44:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][620/1251]	eta 0:23:26 lr 0.000048	time 1.8616 (2.2296)	loss 3.0935 (3.0426)	grad_norm 3.2094 (2.9008)	
[2022-01-26 02:45:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][630/1251]	eta 0:23:05 lr 0.000048	time 2.4938 (2.2306)	loss 3.2767 (3.0445)	grad_norm 2.7304 (2.8981)	
[2022-01-26 02:45:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][640/1251]	eta 0:22:42 lr 0.000048	time 1.8612 (2.2302)	loss 2.6259 (3.0432)	grad_norm 2.6612 (2.8969)	
[2022-01-26 02:45:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][650/1251]	eta 0:22:19 lr 0.000048	time 2.1518 (2.2289)	loss 2.1902 (3.0370)	grad_norm 3.3558 (2.8963)	
[2022-01-26 02:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][660/1251]	eta 0:21:54 lr 0.000048	time 1.9132 (2.2238)	loss 2.6614 (3.0368)	grad_norm 2.6007 (2.8944)	
[2022-01-26 02:46:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][670/1251]	eta 0:21:31 lr 0.000048	time 2.2245 (2.2227)	loss 2.4684 (3.0380)	grad_norm 3.0949 (2.8950)	
[2022-01-26 02:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][680/1251]	eta 0:21:08 lr 0.000048	time 2.1711 (2.2222)	loss 2.5243 (3.0396)	grad_norm 2.7205 (2.8948)	
[2022-01-26 02:47:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][690/1251]	eta 0:20:47 lr 0.000048	time 1.5545 (2.2229)	loss 2.4066 (3.0399)	grad_norm 3.0084 (2.8934)	
[2022-01-26 02:47:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][700/1251]	eta 0:20:25 lr 0.000048	time 2.0834 (2.2245)	loss 3.1135 (3.0353)	grad_norm 3.2111 (2.8928)	
[2022-01-26 02:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][710/1251]	eta 0:20:03 lr 0.000048	time 1.9575 (2.2241)	loss 3.5967 (3.0336)	grad_norm 3.1367 (2.8915)	
[2022-01-26 02:48:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][720/1251]	eta 0:19:40 lr 0.000048	time 1.8697 (2.2233)	loss 3.4764 (3.0320)	grad_norm 2.5663 (2.8896)	
[2022-01-26 02:48:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][730/1251]	eta 0:19:17 lr 0.000048	time 1.5700 (2.2225)	loss 3.2321 (3.0331)	grad_norm 2.7412 (2.8895)	
[2022-01-26 02:49:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][740/1251]	eta 0:18:57 lr 0.000047	time 3.1147 (2.2266)	loss 3.1575 (3.0303)	grad_norm 2.8390 (2.8890)	
[2022-01-26 02:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][750/1251]	eta 0:18:35 lr 0.000047	time 1.5471 (2.2258)	loss 3.4026 (3.0298)	grad_norm 2.8248 (2.8904)	
[2022-01-26 02:50:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][760/1251]	eta 0:18:11 lr 0.000047	time 2.0563 (2.2235)	loss 3.3076 (3.0320)	grad_norm 2.8260 (2.8917)	
[2022-01-26 02:50:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][770/1251]	eta 0:17:48 lr 0.000047	time 1.9891 (2.2216)	loss 3.4911 (3.0331)	grad_norm 2.9776 (2.8912)	
[2022-01-26 02:50:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][780/1251]	eta 0:17:26 lr 0.000047	time 2.6979 (2.2209)	loss 3.3890 (3.0336)	grad_norm 2.7178 (2.8943)	
[2022-01-26 02:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][790/1251]	eta 0:17:03 lr 0.000047	time 1.6199 (2.2202)	loss 3.7381 (3.0344)	grad_norm 2.6693 (2.8959)	
[2022-01-26 02:51:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][800/1251]	eta 0:16:40 lr 0.000047	time 2.9455 (2.2194)	loss 3.5668 (3.0368)	grad_norm 2.9023 (2.8976)	
[2022-01-26 02:51:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][810/1251]	eta 0:16:18 lr 0.000047	time 2.2668 (2.2183)	loss 1.8940 (3.0383)	grad_norm 2.6370 (2.8965)	
[2022-01-26 02:52:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][820/1251]	eta 0:15:55 lr 0.000047	time 2.1324 (2.2171)	loss 3.3257 (3.0399)	grad_norm 2.8673 (2.8969)	
[2022-01-26 02:52:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][830/1251]	eta 0:15:33 lr 0.000047	time 2.5018 (2.2176)	loss 3.3772 (3.0423)	grad_norm 3.2074 (2.8974)	
[2022-01-26 02:52:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][840/1251]	eta 0:15:12 lr 0.000047	time 2.6384 (2.2203)	loss 3.3170 (3.0406)	grad_norm 2.9095 (2.8981)	
[2022-01-26 02:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][850/1251]	eta 0:14:50 lr 0.000047	time 2.6210 (2.2198)	loss 3.0726 (3.0415)	grad_norm 2.8176 (2.9008)	
[2022-01-26 02:53:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][860/1251]	eta 0:14:27 lr 0.000047	time 1.6033 (2.2177)	loss 3.3263 (3.0425)	grad_norm 2.7829 (2.9017)	
[2022-01-26 02:53:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][870/1251]	eta 0:14:04 lr 0.000047	time 1.9631 (2.2157)	loss 3.1945 (3.0433)	grad_norm 2.5531 (2.8991)	
[2022-01-26 02:54:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][880/1251]	eta 0:13:41 lr 0.000047	time 1.9765 (2.2145)	loss 1.9194 (3.0432)	grad_norm 2.6349 (2.9021)	
[2022-01-26 02:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][890/1251]	eta 0:13:18 lr 0.000047	time 1.7069 (2.2120)	loss 2.3244 (3.0426)	grad_norm 3.0298 (2.9083)	
[2022-01-26 02:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][900/1251]	eta 0:12:56 lr 0.000047	time 2.2248 (2.2112)	loss 3.5988 (3.0433)	grad_norm 2.4754 (2.9085)	
[2022-01-26 02:55:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][910/1251]	eta 0:12:33 lr 0.000047	time 2.2391 (2.2094)	loss 3.1191 (3.0440)	grad_norm 2.9110 (2.9075)	
[2022-01-26 02:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][920/1251]	eta 0:12:11 lr 0.000047	time 1.6514 (2.2085)	loss 3.3129 (3.0448)	grad_norm 2.8439 (2.9068)	
[2022-01-26 02:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][930/1251]	eta 0:11:48 lr 0.000047	time 2.1390 (2.2071)	loss 3.3766 (3.0472)	grad_norm 2.6670 (2.9061)	
[2022-01-26 02:56:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][940/1251]	eta 0:11:27 lr 0.000047	time 1.8209 (2.2092)	loss 3.1480 (3.0460)	grad_norm 3.7754 (2.9084)	
[2022-01-26 02:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][950/1251]	eta 0:11:05 lr 0.000047	time 2.1108 (2.2111)	loss 3.5065 (3.0474)	grad_norm 3.1160 (2.9079)	
[2022-01-26 02:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][960/1251]	eta 0:10:44 lr 0.000047	time 2.3616 (2.2135)	loss 3.1978 (3.0484)	grad_norm 2.4455 (2.9071)	
[2022-01-26 02:57:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][970/1251]	eta 0:10:22 lr 0.000047	time 2.1037 (2.2143)	loss 3.4559 (3.0492)	grad_norm 3.5378 (2.9066)	
[2022-01-26 02:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][980/1251]	eta 0:09:59 lr 0.000047	time 1.5939 (2.2132)	loss 3.1988 (3.0511)	grad_norm 3.0306 (2.9069)	
[2022-01-26 02:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][990/1251]	eta 0:09:37 lr 0.000047	time 1.6763 (2.2115)	loss 3.2962 (3.0490)	grad_norm 2.7969 (2.9176)	
[2022-01-26 02:58:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1000/1251]	eta 0:09:15 lr 0.000047	time 1.9818 (2.2144)	loss 3.0783 (3.0499)	grad_norm 3.3529 (2.9192)	
[2022-01-26 02:59:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1010/1251]	eta 0:08:53 lr 0.000047	time 1.7588 (2.2135)	loss 3.5976 (3.0525)	grad_norm 2.6044 (2.9185)	
[2022-01-26 02:59:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1020/1251]	eta 0:08:30 lr 0.000047	time 1.9174 (2.2108)	loss 3.5685 (3.0556)	grad_norm 3.1618 (2.9197)	
[2022-01-26 02:59:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1030/1251]	eta 0:08:08 lr 0.000047	time 2.2543 (2.2111)	loss 2.9515 (3.0552)	grad_norm 2.8875 (2.9209)	
[2022-01-26 03:00:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1040/1251]	eta 0:07:47 lr 0.000047	time 1.5887 (2.2133)	loss 2.9945 (3.0566)	grad_norm 2.9773 (2.9202)	
[2022-01-26 03:00:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1050/1251]	eta 0:07:24 lr 0.000047	time 2.1441 (2.2127)	loss 2.7712 (3.0553)	grad_norm 2.7970 (2.9193)	
[2022-01-26 03:00:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1060/1251]	eta 0:07:02 lr 0.000047	time 1.9448 (2.2112)	loss 2.4362 (3.0548)	grad_norm 2.9024 (2.9188)	
[2022-01-26 03:01:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1070/1251]	eta 0:06:40 lr 0.000047	time 1.8389 (2.2102)	loss 3.3513 (3.0531)	grad_norm 3.0148 (2.9186)	
[2022-01-26 03:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1080/1251]	eta 0:06:18 lr 0.000047	time 1.8685 (2.2109)	loss 2.3850 (3.0493)	grad_norm 2.4463 (2.9179)	
[2022-01-26 03:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1090/1251]	eta 0:05:55 lr 0.000047	time 2.0704 (2.2106)	loss 3.4750 (3.0486)	grad_norm 3.0429 (2.9224)	
[2022-01-26 03:02:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1100/1251]	eta 0:05:33 lr 0.000047	time 1.8954 (2.2101)	loss 2.3270 (3.0486)	grad_norm 2.6728 (2.9221)	
[2022-01-26 03:02:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1110/1251]	eta 0:05:11 lr 0.000047	time 1.8923 (2.2088)	loss 3.3429 (3.0491)	grad_norm 2.7185 (2.9209)	
[2022-01-26 03:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1120/1251]	eta 0:04:49 lr 0.000047	time 1.5879 (2.2081)	loss 3.3848 (3.0505)	grad_norm 3.2917 (2.9204)	
[2022-01-26 03:03:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1130/1251]	eta 0:04:27 lr 0.000047	time 1.5394 (2.2072)	loss 3.5529 (3.0518)	grad_norm 3.3437 (2.9225)	
[2022-01-26 03:03:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1140/1251]	eta 0:04:05 lr 0.000047	time 2.8095 (2.2077)	loss 2.8948 (3.0526)	grad_norm 2.9310 (2.9228)	
[2022-01-26 03:04:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1150/1251]	eta 0:03:43 lr 0.000047	time 2.6353 (2.2081)	loss 2.7679 (3.0516)	grad_norm 3.6695 (2.9260)	
[2022-01-26 03:04:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1160/1251]	eta 0:03:20 lr 0.000047	time 1.8641 (2.2071)	loss 3.2553 (3.0520)	grad_norm 3.4809 (2.9272)	
[2022-01-26 03:04:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1170/1251]	eta 0:02:58 lr 0.000047	time 2.1453 (2.2063)	loss 3.7321 (3.0533)	grad_norm 2.4361 (2.9260)	
[2022-01-26 03:05:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1180/1251]	eta 0:02:36 lr 0.000047	time 3.3297 (2.2062)	loss 3.1266 (3.0526)	grad_norm 2.8094 (2.9275)	
[2022-01-26 03:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1190/1251]	eta 0:02:14 lr 0.000047	time 2.7500 (2.2073)	loss 3.2055 (3.0510)	grad_norm 3.3200 (2.9282)	
[2022-01-26 03:05:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1200/1251]	eta 0:01:52 lr 0.000047	time 1.4893 (2.2078)	loss 2.5581 (3.0515)	grad_norm 3.1259 (2.9282)	
[2022-01-26 03:06:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1210/1251]	eta 0:01:30 lr 0.000047	time 2.0656 (2.2075)	loss 2.7562 (3.0502)	grad_norm 2.9988 (2.9288)	
[2022-01-26 03:06:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1220/1251]	eta 0:01:08 lr 0.000047	time 3.3788 (2.2088)	loss 3.3047 (3.0495)	grad_norm 2.6661 (2.9278)	
[2022-01-26 03:07:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1230/1251]	eta 0:00:46 lr 0.000047	time 2.1759 (2.2091)	loss 3.1005 (3.0497)	grad_norm 2.7371 (2.9263)	
[2022-01-26 03:07:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1240/1251]	eta 0:00:24 lr 0.000047	time 1.2958 (2.2068)	loss 2.5931 (3.0496)	grad_norm 2.9054 (2.9269)	
[2022-01-26 03:07:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [262/300][1250/1251]	eta 0:00:02 lr 0.000047	time 1.2264 (2.2006)	loss 2.9327 (3.0492)	grad_norm 2.6760 (2.9268)	
[2022-01-26 03:07:41 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 262 training takes 0:45:53
[2022-01-26 03:08:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.543 (18.543)	Loss 0.7929 (0.7929)	Acc@1 81.641 (81.641)	Acc@5 96.191 (96.191)	
[2022-01-26 03:08:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.973 (3.324)	Loss 0.8548 (0.8193)	Acc@1 79.395 (80.939)	Acc@5 95.215 (95.534)	
[2022-01-26 03:08:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.614 (2.495)	Loss 0.7727 (0.8204)	Acc@1 81.055 (80.915)	Acc@5 96.484 (95.359)	
[2022-01-26 03:08:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.199 (2.237)	Loss 0.8711 (0.8266)	Acc@1 80.371 (80.727)	Acc@5 95.312 (95.360)	
[2022-01-26 03:09:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.644 (2.179)	Loss 0.9082 (0.8293)	Acc@1 78.613 (80.674)	Acc@5 93.555 (95.267)	
[2022-01-26 03:09:17 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.744 Acc@5 95.316
[2022-01-26 03:09:17 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.7%
[2022-01-26 03:09:17 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.78%
[2022-01-26 03:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][0/1251]	eta 7:29:20 lr 0.000047	time 21.5514 (21.5514)	loss 3.2931 (3.2931)	grad_norm 3.5627 (3.5627)	
[2022-01-26 03:10:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][10/1251]	eta 1:24:07 lr 0.000047	time 3.3395 (4.0676)	loss 2.1487 (2.8991)	grad_norm 2.7583 (2.9047)	
[2022-01-26 03:10:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][20/1251]	eta 1:05:01 lr 0.000047	time 2.6251 (3.1690)	loss 3.3177 (3.0197)	grad_norm 2.7271 (2.8532)	
[2022-01-26 03:10:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][30/1251]	eta 0:57:36 lr 0.000047	time 1.5688 (2.8307)	loss 2.1178 (2.9853)	grad_norm 2.8653 (2.8150)	
[2022-01-26 03:11:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][40/1251]	eta 0:55:00 lr 0.000047	time 3.9819 (2.7251)	loss 3.5445 (3.0398)	grad_norm 2.7175 (2.8262)	
[2022-01-26 03:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][50/1251]	eta 0:53:04 lr 0.000047	time 3.1678 (2.6516)	loss 2.9684 (3.0161)	grad_norm 2.8269 (2.8063)	
[2022-01-26 03:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][60/1251]	eta 0:51:02 lr 0.000047	time 2.2935 (2.5714)	loss 3.2051 (3.0249)	grad_norm 2.5015 (2.8000)	
[2022-01-26 03:12:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][70/1251]	eta 0:49:19 lr 0.000047	time 1.9190 (2.5055)	loss 2.2413 (3.0089)	grad_norm 2.8195 (2.8199)	
[2022-01-26 03:12:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][80/1251]	eta 0:48:27 lr 0.000047	time 3.9062 (2.4826)	loss 2.7972 (3.0080)	grad_norm 2.4389 (2.8007)	
[2022-01-26 03:12:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][90/1251]	eta 0:47:10 lr 0.000047	time 1.6273 (2.4378)	loss 2.0667 (2.9997)	grad_norm 2.8092 (2.8024)	
[2022-01-26 03:13:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][100/1251]	eta 0:46:17 lr 0.000047	time 3.1512 (2.4127)	loss 3.0531 (3.0148)	grad_norm 3.0834 (2.8104)	
[2022-01-26 03:13:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][110/1251]	eta 0:45:41 lr 0.000047	time 1.8342 (2.4025)	loss 3.7219 (3.0122)	grad_norm 5.3260 (2.8321)	
[2022-01-26 03:14:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][120/1251]	eta 0:45:11 lr 0.000047	time 4.0465 (2.3972)	loss 2.0789 (2.9972)	grad_norm 4.7017 (2.8358)	
[2022-01-26 03:14:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][130/1251]	eta 0:44:20 lr 0.000046	time 1.8624 (2.3737)	loss 3.5296 (2.9931)	grad_norm 3.2945 (2.8421)	
[2022-01-26 03:14:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][140/1251]	eta 0:43:33 lr 0.000046	time 2.1251 (2.3527)	loss 2.7811 (2.9866)	grad_norm 3.3224 (2.8399)	
[2022-01-26 03:15:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][150/1251]	eta 0:42:52 lr 0.000046	time 1.9188 (2.3369)	loss 3.4632 (2.9949)	grad_norm 2.8055 (2.8324)	
[2022-01-26 03:15:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][160/1251]	eta 0:42:36 lr 0.000046	time 3.6384 (2.3436)	loss 2.9289 (3.0008)	grad_norm 2.7073 (2.8296)	
[2022-01-26 03:15:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][170/1251]	eta 0:42:05 lr 0.000046	time 2.8363 (2.3366)	loss 3.3122 (3.0100)	grad_norm 2.4353 (2.8166)	
[2022-01-26 03:16:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][180/1251]	eta 0:41:31 lr 0.000046	time 1.8377 (2.3261)	loss 3.6072 (3.0100)	grad_norm 2.6783 (2.8115)	
[2022-01-26 03:16:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][190/1251]	eta 0:40:49 lr 0.000046	time 1.9853 (2.3090)	loss 2.3648 (3.0132)	grad_norm 3.1525 (2.8145)	
[2022-01-26 03:17:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][200/1251]	eta 0:40:28 lr 0.000046	time 3.9088 (2.3102)	loss 3.3914 (3.0166)	grad_norm 2.7127 (2.8118)	
[2022-01-26 03:17:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][210/1251]	eta 0:39:54 lr 0.000046	time 2.3608 (2.3003)	loss 3.4638 (3.0172)	grad_norm 2.7354 (2.8128)	
[2022-01-26 03:17:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][220/1251]	eta 0:39:25 lr 0.000046	time 2.0709 (2.2944)	loss 3.3543 (3.0245)	grad_norm 2.7835 (2.8176)	
[2022-01-26 03:18:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][230/1251]	eta 0:38:52 lr 0.000046	time 1.6205 (2.2843)	loss 3.4733 (3.0241)	grad_norm 3.0156 (2.8178)	
[2022-01-26 03:18:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][240/1251]	eta 0:38:39 lr 0.000046	time 3.5455 (2.2947)	loss 3.3454 (3.0204)	grad_norm 2.6281 (2.8181)	
[2022-01-26 03:18:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][250/1251]	eta 0:38:14 lr 0.000046	time 1.5928 (2.2921)	loss 3.0457 (3.0092)	grad_norm 4.7138 (2.8295)	
[2022-01-26 03:19:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][260/1251]	eta 0:37:40 lr 0.000046	time 1.5929 (2.2805)	loss 3.0362 (3.0008)	grad_norm 2.7331 (2.8296)	
[2022-01-26 03:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][270/1251]	eta 0:37:08 lr 0.000046	time 2.0555 (2.2714)	loss 2.4125 (2.9978)	grad_norm 2.6820 (2.8328)	
[2022-01-26 03:19:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][280/1251]	eta 0:36:43 lr 0.000046	time 3.0983 (2.2690)	loss 3.3016 (3.0074)	grad_norm 2.7519 (2.8302)	
[2022-01-26 03:20:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][290/1251]	eta 0:36:22 lr 0.000046	time 3.1174 (2.2712)	loss 3.2067 (3.0118)	grad_norm 2.6507 (2.8331)	
[2022-01-26 03:20:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][300/1251]	eta 0:35:53 lr 0.000046	time 2.4035 (2.2649)	loss 3.0135 (3.0086)	grad_norm 2.4647 (2.8315)	
[2022-01-26 03:21:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][310/1251]	eta 0:35:25 lr 0.000046	time 2.2227 (2.2590)	loss 3.6302 (3.0148)	grad_norm 2.6283 (2.8368)	
[2022-01-26 03:21:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][320/1251]	eta 0:35:01 lr 0.000046	time 3.2438 (2.2577)	loss 2.2886 (3.0165)	grad_norm 3.0680 (2.8342)	
[2022-01-26 03:21:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][330/1251]	eta 0:34:35 lr 0.000046	time 1.9317 (2.2533)	loss 3.9164 (3.0207)	grad_norm 2.9445 (2.8366)	
[2022-01-26 03:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][340/1251]	eta 0:34:14 lr 0.000046	time 2.9074 (2.2553)	loss 3.2620 (3.0211)	grad_norm 3.0591 (2.8397)	
[2022-01-26 03:22:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][350/1251]	eta 0:33:52 lr 0.000046	time 2.2651 (2.2554)	loss 3.5801 (3.0265)	grad_norm 3.0139 (2.8391)	
[2022-01-26 03:22:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][360/1251]	eta 0:33:27 lr 0.000046	time 2.7957 (2.2526)	loss 3.4063 (3.0241)	grad_norm 2.9305 (2.8434)	
[2022-01-26 03:23:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][370/1251]	eta 0:33:01 lr 0.000046	time 1.7933 (2.2490)	loss 3.1504 (3.0239)	grad_norm 2.7909 (2.8522)	
[2022-01-26 03:23:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][380/1251]	eta 0:32:39 lr 0.000046	time 2.5966 (2.2492)	loss 3.5013 (3.0225)	grad_norm 3.0430 (2.8606)	
[2022-01-26 03:23:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][390/1251]	eta 0:32:13 lr 0.000046	time 1.8903 (2.2451)	loss 2.3204 (3.0221)	grad_norm 2.6545 (2.8653)	
[2022-01-26 03:24:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][400/1251]	eta 0:31:47 lr 0.000046	time 2.5262 (2.2413)	loss 3.3234 (3.0260)	grad_norm 2.8005 (2.8632)	
[2022-01-26 03:24:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][410/1251]	eta 0:31:24 lr 0.000046	time 2.5079 (2.2410)	loss 2.4103 (3.0225)	grad_norm 2.6134 (2.8716)	
[2022-01-26 03:25:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][420/1251]	eta 0:30:59 lr 0.000046	time 2.2181 (2.2380)	loss 2.4341 (3.0207)	grad_norm 2.8044 (2.8748)	
[2022-01-26 03:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][430/1251]	eta 0:30:36 lr 0.000046	time 1.9405 (2.2366)	loss 2.4302 (3.0250)	grad_norm 2.9448 (2.8753)	
[2022-01-26 03:25:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][440/1251]	eta 0:30:14 lr 0.000046	time 2.0339 (2.2370)	loss 3.3878 (3.0272)	grad_norm 3.1545 (2.8756)	
[2022-01-26 03:26:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][450/1251]	eta 0:29:49 lr 0.000046	time 2.3172 (2.2343)	loss 3.3987 (3.0258)	grad_norm 2.5805 (2.8854)	
[2022-01-26 03:26:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][460/1251]	eta 0:29:28 lr 0.000046	time 2.6337 (2.2358)	loss 3.4126 (3.0217)	grad_norm 3.4393 (2.8863)	
[2022-01-26 03:26:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][470/1251]	eta 0:29:04 lr 0.000046	time 2.1514 (2.2336)	loss 3.3085 (3.0238)	grad_norm 2.8033 (2.8829)	
[2022-01-26 03:27:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][480/1251]	eta 0:28:41 lr 0.000046	time 1.8982 (2.2323)	loss 3.0527 (3.0248)	grad_norm 2.6700 (2.8825)	
[2022-01-26 03:27:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][490/1251]	eta 0:28:21 lr 0.000046	time 2.8709 (2.2358)	loss 3.5508 (3.0268)	grad_norm 2.5975 (2.8813)	
[2022-01-26 03:27:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][500/1251]	eta 0:27:58 lr 0.000046	time 1.7309 (2.2350)	loss 3.0098 (3.0248)	grad_norm 3.0275 (2.8815)	
[2022-01-26 03:28:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][510/1251]	eta 0:27:32 lr 0.000046	time 1.8136 (2.2305)	loss 3.4951 (3.0278)	grad_norm 3.9212 (2.8848)	
[2022-01-26 03:28:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][520/1251]	eta 0:27:08 lr 0.000046	time 1.9351 (2.2283)	loss 3.2146 (3.0273)	grad_norm 3.3492 (2.8884)	
[2022-01-26 03:29:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][530/1251]	eta 0:26:45 lr 0.000046	time 2.3271 (2.2266)	loss 3.3309 (3.0246)	grad_norm 2.7451 (2.8943)	
[2022-01-26 03:29:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][540/1251]	eta 0:26:21 lr 0.000046	time 2.5597 (2.2248)	loss 3.5702 (3.0246)	grad_norm 2.4506 (2.9004)	
[2022-01-26 03:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][550/1251]	eta 0:25:59 lr 0.000046	time 1.9090 (2.2253)	loss 3.1556 (3.0241)	grad_norm 3.0196 (2.8992)	
[2022-01-26 03:30:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][560/1251]	eta 0:25:37 lr 0.000046	time 2.5137 (2.2249)	loss 2.8005 (3.0257)	grad_norm 2.7223 (2.9007)	
[2022-01-26 03:30:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][570/1251]	eta 0:25:14 lr 0.000046	time 2.2180 (2.2243)	loss 3.5422 (3.0290)	grad_norm 5.3694 (2.9069)	
[2022-01-26 03:30:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][580/1251]	eta 0:24:52 lr 0.000046	time 3.0949 (2.2237)	loss 1.8430 (3.0291)	grad_norm 2.9437 (2.9074)	
[2022-01-26 03:31:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][590/1251]	eta 0:24:28 lr 0.000046	time 1.6879 (2.2217)	loss 3.3157 (3.0321)	grad_norm 2.9334 (2.9078)	
[2022-01-26 03:31:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][600/1251]	eta 0:24:05 lr 0.000046	time 1.6784 (2.2212)	loss 2.3243 (3.0280)	grad_norm 2.6583 (2.9084)	
[2022-01-26 03:31:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][610/1251]	eta 0:23:42 lr 0.000046	time 2.2804 (2.2192)	loss 3.3240 (3.0297)	grad_norm 2.5177 (2.9069)	
[2022-01-26 03:32:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][620/1251]	eta 0:23:21 lr 0.000046	time 3.1048 (2.2218)	loss 2.9910 (3.0313)	grad_norm 2.8409 (2.9055)	
[2022-01-26 03:32:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][630/1251]	eta 0:22:56 lr 0.000046	time 1.6472 (2.2165)	loss 2.5693 (3.0297)	grad_norm 3.4848 (2.9037)	
[2022-01-26 03:32:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][640/1251]	eta 0:22:33 lr 0.000046	time 1.4785 (2.2156)	loss 1.8976 (3.0280)	grad_norm 2.5190 (2.9035)	
[2022-01-26 03:33:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][650/1251]	eta 0:22:10 lr 0.000046	time 2.3222 (2.2135)	loss 3.2768 (3.0337)	grad_norm 2.6535 (2.9020)	
[2022-01-26 03:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][660/1251]	eta 0:21:47 lr 0.000046	time 2.6498 (2.2126)	loss 3.0905 (3.0325)	grad_norm 2.5327 (2.9009)	
[2022-01-26 03:34:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][670/1251]	eta 0:21:25 lr 0.000046	time 1.6899 (2.2125)	loss 3.5399 (3.0356)	grad_norm 2.7973 (2.9025)	
[2022-01-26 03:34:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][680/1251]	eta 0:21:02 lr 0.000046	time 1.5888 (2.2108)	loss 3.6247 (3.0382)	grad_norm 2.5556 (2.9031)	
[2022-01-26 03:34:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][690/1251]	eta 0:20:39 lr 0.000046	time 1.9508 (2.2100)	loss 2.7612 (3.0399)	grad_norm 2.6196 (2.9000)	
[2022-01-26 03:35:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][700/1251]	eta 0:20:19 lr 0.000046	time 3.3989 (2.2126)	loss 2.2639 (3.0377)	grad_norm 2.7344 (2.8984)	
[2022-01-26 03:35:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][710/1251]	eta 0:19:57 lr 0.000046	time 2.6827 (2.2130)	loss 2.4607 (3.0356)	grad_norm 2.6360 (2.9007)	
[2022-01-26 03:35:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][720/1251]	eta 0:19:35 lr 0.000046	time 1.4683 (2.2147)	loss 2.7308 (3.0330)	grad_norm 3.9175 (2.9005)	
[2022-01-26 03:36:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][730/1251]	eta 0:19:14 lr 0.000046	time 2.1700 (2.2165)	loss 2.7405 (3.0346)	grad_norm 3.2534 (2.9033)	
[2022-01-26 03:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][740/1251]	eta 0:18:51 lr 0.000046	time 1.5758 (2.2150)	loss 3.0931 (3.0377)	grad_norm 2.8960 (2.9050)	
[2022-01-26 03:36:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][750/1251]	eta 0:18:28 lr 0.000046	time 1.8838 (2.2126)	loss 2.9829 (3.0388)	grad_norm 2.5414 (2.9062)	
[2022-01-26 03:37:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][760/1251]	eta 0:18:05 lr 0.000046	time 1.7055 (2.2102)	loss 3.7167 (3.0397)	grad_norm 2.5175 (2.9070)	
[2022-01-26 03:37:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][770/1251]	eta 0:17:42 lr 0.000045	time 2.1335 (2.2094)	loss 2.2043 (3.0397)	grad_norm 2.6041 (2.9073)	
[2022-01-26 03:38:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][780/1251]	eta 0:17:20 lr 0.000045	time 2.2028 (2.2096)	loss 3.2886 (3.0408)	grad_norm 3.0411 (2.9067)	
[2022-01-26 03:38:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][790/1251]	eta 0:16:58 lr 0.000045	time 2.2045 (2.2086)	loss 2.5674 (3.0387)	grad_norm 2.6142 (2.9070)	
[2022-01-26 03:38:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][800/1251]	eta 0:16:35 lr 0.000045	time 1.9121 (2.2066)	loss 3.1147 (3.0391)	grad_norm 2.4385 (2.9063)	
[2022-01-26 03:39:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][810/1251]	eta 0:16:13 lr 0.000045	time 3.0366 (2.2077)	loss 2.4342 (3.0392)	grad_norm 2.7382 (2.9074)	
[2022-01-26 03:39:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][820/1251]	eta 0:15:51 lr 0.000045	time 1.6740 (2.2087)	loss 2.7591 (3.0353)	grad_norm 3.2149 (2.9088)	
[2022-01-26 03:39:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][830/1251]	eta 0:15:30 lr 0.000045	time 1.8106 (2.2100)	loss 3.4909 (3.0325)	grad_norm 2.6923 (2.9080)	
[2022-01-26 03:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][840/1251]	eta 0:15:08 lr 0.000045	time 1.7856 (2.2099)	loss 3.4546 (3.0335)	grad_norm 3.7183 (2.9093)	
[2022-01-26 03:40:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][850/1251]	eta 0:14:45 lr 0.000045	time 1.9844 (2.2085)	loss 3.1961 (3.0322)	grad_norm 2.6268 (2.9108)	
[2022-01-26 03:40:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][860/1251]	eta 0:14:22 lr 0.000045	time 1.7173 (2.2060)	loss 2.7325 (3.0335)	grad_norm 2.6064 (2.9095)	
[2022-01-26 03:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][870/1251]	eta 0:13:59 lr 0.000045	time 2.0746 (2.2033)	loss 2.3979 (3.0319)	grad_norm 2.9144 (2.9097)	
[2022-01-26 03:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][880/1251]	eta 0:13:36 lr 0.000045	time 1.8983 (2.2019)	loss 3.1336 (3.0331)	grad_norm 2.9537 (2.9103)	
[2022-01-26 03:41:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][890/1251]	eta 0:13:14 lr 0.000045	time 2.2060 (2.2012)	loss 2.8011 (3.0308)	grad_norm 2.6471 (2.9204)	
[2022-01-26 03:42:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][900/1251]	eta 0:12:52 lr 0.000045	time 2.3824 (2.2020)	loss 2.7674 (3.0315)	grad_norm 2.3514 (2.9215)	
[2022-01-26 03:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][910/1251]	eta 0:12:30 lr 0.000045	time 1.4516 (2.2022)	loss 1.8311 (3.0289)	grad_norm 2.3001 (2.9197)	
[2022-01-26 03:43:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][920/1251]	eta 0:12:09 lr 0.000045	time 2.0818 (2.2029)	loss 3.1372 (3.0289)	grad_norm 2.7641 (2.9190)	
[2022-01-26 03:43:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][930/1251]	eta 0:11:47 lr 0.000045	time 2.5945 (2.2043)	loss 2.5330 (3.0308)	grad_norm 2.8193 (2.9222)	
[2022-01-26 03:43:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][940/1251]	eta 0:11:26 lr 0.000045	time 2.7152 (2.2089)	loss 1.9800 (3.0311)	grad_norm 2.9324 (2.9233)	
[2022-01-26 03:44:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][950/1251]	eta 0:11:05 lr 0.000045	time 1.7465 (2.2101)	loss 3.2885 (3.0329)	grad_norm 2.9335 (2.9231)	
[2022-01-26 03:44:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][960/1251]	eta 0:10:42 lr 0.000045	time 1.8566 (2.2089)	loss 3.7464 (3.0355)	grad_norm 2.9157 (2.9225)	
[2022-01-26 03:45:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][970/1251]	eta 0:10:20 lr 0.000045	time 1.9569 (2.2075)	loss 3.1198 (3.0338)	grad_norm 2.9833 (2.9213)	
[2022-01-26 03:45:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][980/1251]	eta 0:09:57 lr 0.000045	time 2.1801 (2.2046)	loss 3.3035 (3.0338)	grad_norm 2.9500 (2.9204)	
[2022-01-26 03:45:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][990/1251]	eta 0:09:34 lr 0.000045	time 1.8264 (2.2029)	loss 3.2799 (3.0349)	grad_norm 2.9511 (2.9210)	
[2022-01-26 03:46:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1000/1251]	eta 0:09:12 lr 0.000045	time 2.2266 (2.2020)	loss 3.3558 (3.0362)	grad_norm 2.3549 (2.9198)	
[2022-01-26 03:46:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1010/1251]	eta 0:08:50 lr 0.000045	time 2.0497 (2.2012)	loss 3.4584 (3.0341)	grad_norm 3.0578 (2.9184)	
[2022-01-26 03:46:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1020/1251]	eta 0:08:28 lr 0.000045	time 2.9097 (2.2024)	loss 2.8051 (3.0341)	grad_norm 2.6366 (2.9172)	
[2022-01-26 03:47:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1030/1251]	eta 0:08:06 lr 0.000045	time 1.7691 (2.2018)	loss 3.2513 (3.0345)	grad_norm 2.5825 (2.9154)	
[2022-01-26 03:47:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1040/1251]	eta 0:07:44 lr 0.000045	time 2.4397 (2.2027)	loss 3.2797 (3.0356)	grad_norm 2.2802 (2.9154)	
[2022-01-26 03:47:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1050/1251]	eta 0:07:22 lr 0.000045	time 1.8455 (2.2018)	loss 2.0100 (3.0309)	grad_norm 2.7652 (2.9135)	
[2022-01-26 03:48:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1060/1251]	eta 0:07:00 lr 0.000045	time 3.0653 (2.2036)	loss 2.4533 (3.0309)	grad_norm 3.0072 (2.9129)	
[2022-01-26 03:48:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1070/1251]	eta 0:06:38 lr 0.000045	time 1.7032 (2.2026)	loss 2.8522 (3.0310)	grad_norm 3.5010 (2.9114)	
[2022-01-26 03:48:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1080/1251]	eta 0:06:16 lr 0.000045	time 2.4769 (2.2033)	loss 2.7454 (3.0326)	grad_norm 2.6392 (2.9131)	
[2022-01-26 03:49:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1090/1251]	eta 0:05:54 lr 0.000045	time 1.8588 (2.2029)	loss 3.4638 (3.0320)	grad_norm 2.6207 (2.9139)	
[2022-01-26 03:49:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1100/1251]	eta 0:05:32 lr 0.000045	time 3.4428 (2.2020)	loss 2.8951 (3.0324)	grad_norm 3.0910 (2.9138)	
[2022-01-26 03:50:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1110/1251]	eta 0:05:10 lr 0.000045	time 1.5920 (2.2022)	loss 3.5263 (3.0315)	grad_norm 3.1735 (2.9151)	
[2022-01-26 03:50:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1120/1251]	eta 0:04:48 lr 0.000045	time 1.9507 (2.2023)	loss 3.1460 (3.0317)	grad_norm 3.2245 (2.9170)	
[2022-01-26 03:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1130/1251]	eta 0:04:26 lr 0.000045	time 3.4952 (2.2030)	loss 3.2483 (3.0306)	grad_norm 3.2587 (2.9168)	
[2022-01-26 03:51:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1140/1251]	eta 0:04:04 lr 0.000045	time 3.5953 (2.2047)	loss 3.4085 (3.0310)	grad_norm 3.0118 (2.9168)	
[2022-01-26 03:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1150/1251]	eta 0:03:42 lr 0.000045	time 2.2008 (2.2054)	loss 3.3765 (3.0288)	grad_norm 3.6947 (2.9165)	
[2022-01-26 03:51:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1160/1251]	eta 0:03:20 lr 0.000045	time 1.6348 (2.2038)	loss 3.0854 (3.0275)	grad_norm 3.0352 (2.9179)	
[2022-01-26 03:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1170/1251]	eta 0:02:58 lr 0.000045	time 1.9044 (2.2029)	loss 2.4248 (3.0273)	grad_norm 2.8061 (2.9163)	
[2022-01-26 03:52:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1180/1251]	eta 0:02:36 lr 0.000045	time 2.8713 (2.2020)	loss 3.5659 (3.0284)	grad_norm 2.6901 (2.9170)	
[2022-01-26 03:52:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1190/1251]	eta 0:02:14 lr 0.000045	time 2.0291 (2.2016)	loss 1.9983 (3.0295)	grad_norm 2.4677 (2.9157)	
[2022-01-26 03:53:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1200/1251]	eta 0:01:52 lr 0.000045	time 2.3900 (2.2018)	loss 3.4989 (3.0315)	grad_norm 3.7109 (2.9159)	
[2022-01-26 03:53:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1210/1251]	eta 0:01:30 lr 0.000045	time 2.1278 (2.2016)	loss 2.9094 (3.0311)	grad_norm 2.6746 (2.9146)	
[2022-01-26 03:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1220/1251]	eta 0:01:08 lr 0.000045	time 3.8803 (2.2027)	loss 3.5026 (3.0305)	grad_norm 2.7120 (2.9141)	
[2022-01-26 03:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1230/1251]	eta 0:00:46 lr 0.000045	time 1.7743 (2.2030)	loss 3.0905 (3.0316)	grad_norm 2.5552 (2.9140)	
[2022-01-26 03:54:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1240/1251]	eta 0:00:24 lr 0.000045	time 1.6172 (2.2016)	loss 3.3165 (3.0343)	grad_norm 2.9830 (2.9132)	
[2022-01-26 03:55:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [263/300][1250/1251]	eta 0:00:02 lr 0.000045	time 1.2011 (2.1956)	loss 2.4920 (3.0357)	grad_norm 4.1379 (2.9140)	
[2022-01-26 03:55:04 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 263 training takes 0:45:47
[2022-01-26 03:55:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.642 (18.642)	Loss 0.8785 (0.8785)	Acc@1 80.176 (80.176)	Acc@5 94.824 (94.824)	
[2022-01-26 03:55:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.569 (3.474)	Loss 0.9242 (0.8486)	Acc@1 77.637 (80.247)	Acc@5 94.727 (95.002)	
[2022-01-26 03:56:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.993 (2.693)	Loss 0.8262 (0.8449)	Acc@1 80.859 (80.418)	Acc@5 95.898 (95.136)	
[2022-01-26 03:56:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.269 (2.258)	Loss 0.9505 (0.8456)	Acc@1 76.953 (80.346)	Acc@5 94.043 (95.086)	
[2022-01-26 03:56:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.141 (2.185)	Loss 0.9149 (0.8341)	Acc@1 79.590 (80.671)	Acc@5 94.336 (95.174)	
[2022-01-26 03:56:41 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.750 Acc@5 95.242
[2022-01-26 03:56:41 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.8%
[2022-01-26 03:56:41 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.78%
[2022-01-26 03:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][0/1251]	eta 7:38:24 lr 0.000045	time 21.9857 (21.9857)	loss 3.3300 (3.3300)	grad_norm 3.0825 (3.0825)	
[2022-01-26 03:57:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][10/1251]	eta 1:23:48 lr 0.000045	time 2.3250 (4.0523)	loss 3.3910 (3.0742)	grad_norm 2.5938 (2.9030)	
[2022-01-26 03:57:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][20/1251]	eta 1:04:25 lr 0.000045	time 1.8245 (3.1403)	loss 2.3590 (3.0216)	grad_norm 3.0992 (2.9155)	
[2022-01-26 03:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][30/1251]	eta 0:56:53 lr 0.000045	time 1.5430 (2.7953)	loss 3.4429 (2.9893)	grad_norm 2.9965 (2.9144)	
[2022-01-26 03:58:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][40/1251]	eta 0:54:19 lr 0.000045	time 3.8363 (2.6912)	loss 3.5361 (2.9845)	grad_norm 3.0156 (2.8918)	
[2022-01-26 03:58:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][50/1251]	eta 0:52:27 lr 0.000045	time 3.0143 (2.6204)	loss 3.1441 (2.9789)	grad_norm 2.7133 (2.8852)	
[2022-01-26 03:59:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][60/1251]	eta 0:50:46 lr 0.000045	time 2.1857 (2.5576)	loss 3.2699 (2.9458)	grad_norm 2.9942 (2.8794)	
[2022-01-26 03:59:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][70/1251]	eta 0:49:09 lr 0.000045	time 1.9851 (2.4974)	loss 2.2287 (2.9432)	grad_norm 3.0336 (2.8943)	
[2022-01-26 04:00:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][80/1251]	eta 0:48:14 lr 0.000045	time 3.7329 (2.4716)	loss 3.5246 (2.9865)	grad_norm 3.1702 (2.8964)	
[2022-01-26 04:00:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][90/1251]	eta 0:47:18 lr 0.000045	time 1.5668 (2.4451)	loss 3.2520 (3.0108)	grad_norm 3.0025 (2.9260)	
[2022-01-26 04:00:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][100/1251]	eta 0:46:16 lr 0.000045	time 1.9034 (2.4125)	loss 2.6237 (3.0254)	grad_norm 3.0035 (2.9285)	
[2022-01-26 04:01:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][110/1251]	eta 0:45:36 lr 0.000045	time 2.5327 (2.3982)	loss 3.1048 (3.0246)	grad_norm 3.0235 (2.9354)	
[2022-01-26 04:01:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][120/1251]	eta 0:44:52 lr 0.000045	time 3.1468 (2.3806)	loss 2.1883 (3.0076)	grad_norm 5.0347 (2.9639)	
[2022-01-26 04:01:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][130/1251]	eta 0:44:08 lr 0.000045	time 1.7262 (2.3623)	loss 2.9421 (3.0145)	grad_norm 3.3681 (2.9557)	
[2022-01-26 04:02:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][140/1251]	eta 0:43:23 lr 0.000045	time 1.9455 (2.3430)	loss 3.6370 (3.0214)	grad_norm 2.9240 (2.9520)	
[2022-01-26 04:02:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][150/1251]	eta 0:42:41 lr 0.000045	time 2.1208 (2.3266)	loss 1.8623 (3.0287)	grad_norm 3.0730 (2.9430)	
[2022-01-26 04:02:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][160/1251]	eta 0:42:13 lr 0.000045	time 3.1982 (2.3226)	loss 3.3622 (3.0187)	grad_norm 2.5188 (2.9307)	
[2022-01-26 04:03:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][170/1251]	eta 0:41:40 lr 0.000045	time 1.7995 (2.3129)	loss 3.4548 (3.0295)	grad_norm 2.9254 (2.9360)	
[2022-01-26 04:03:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][180/1251]	eta 0:41:13 lr 0.000044	time 2.1730 (2.3096)	loss 3.4232 (3.0405)	grad_norm 2.7869 (2.9230)	
[2022-01-26 04:04:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][190/1251]	eta 0:40:43 lr 0.000044	time 1.8982 (2.3028)	loss 2.9269 (3.0342)	grad_norm 2.8850 (2.9226)	
[2022-01-26 04:04:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][200/1251]	eta 0:40:22 lr 0.000044	time 3.1356 (2.3045)	loss 3.0910 (3.0305)	grad_norm 3.1713 (2.9293)	
[2022-01-26 04:04:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][210/1251]	eta 0:39:52 lr 0.000044	time 1.6274 (2.2982)	loss 2.6726 (3.0241)	grad_norm 2.4335 (2.9223)	
[2022-01-26 04:05:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][220/1251]	eta 0:39:20 lr 0.000044	time 2.1352 (2.2896)	loss 3.1422 (3.0305)	grad_norm 2.8833 (2.9297)	
[2022-01-26 04:05:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][230/1251]	eta 0:38:47 lr 0.000044	time 1.6454 (2.2796)	loss 3.6681 (3.0344)	grad_norm 3.1570 (2.9293)	
[2022-01-26 04:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][240/1251]	eta 0:38:27 lr 0.000044	time 3.6163 (2.2829)	loss 2.6497 (3.0285)	grad_norm 2.8875 (2.9324)	
[2022-01-26 04:06:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][250/1251]	eta 0:38:02 lr 0.000044	time 1.6394 (2.2806)	loss 3.2589 (3.0295)	grad_norm 2.6566 (2.9320)	
[2022-01-26 04:06:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][260/1251]	eta 0:37:36 lr 0.000044	time 2.9115 (2.2768)	loss 3.1746 (3.0299)	grad_norm 2.7593 (2.9265)	
[2022-01-26 04:06:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][270/1251]	eta 0:37:10 lr 0.000044	time 1.8311 (2.2733)	loss 2.4644 (3.0321)	grad_norm 2.6107 (2.9253)	
[2022-01-26 04:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][280/1251]	eta 0:36:47 lr 0.000044	time 3.0133 (2.2733)	loss 3.6502 (3.0287)	grad_norm 4.1650 (2.9248)	
[2022-01-26 04:07:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][290/1251]	eta 0:36:18 lr 0.000044	time 1.6111 (2.2670)	loss 2.6058 (3.0275)	grad_norm 2.9640 (2.9206)	
[2022-01-26 04:08:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][300/1251]	eta 0:35:51 lr 0.000044	time 2.5749 (2.2624)	loss 2.8882 (3.0246)	grad_norm 2.6735 (2.9270)	
[2022-01-26 04:08:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][310/1251]	eta 0:35:24 lr 0.000044	time 2.4416 (2.2581)	loss 2.2124 (3.0224)	grad_norm 2.9549 (2.9262)	
[2022-01-26 04:08:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][320/1251]	eta 0:35:01 lr 0.000044	time 2.8682 (2.2570)	loss 2.7107 (3.0248)	grad_norm 2.9102 (2.9283)	
[2022-01-26 04:09:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][330/1251]	eta 0:34:37 lr 0.000044	time 1.9604 (2.2560)	loss 3.5464 (3.0246)	grad_norm 2.5249 (2.9292)	
[2022-01-26 04:09:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][340/1251]	eta 0:34:12 lr 0.000044	time 2.2167 (2.2534)	loss 3.3536 (3.0234)	grad_norm 2.7102 (2.9283)	
[2022-01-26 04:09:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][350/1251]	eta 0:33:47 lr 0.000044	time 2.5665 (2.2499)	loss 3.0356 (3.0216)	grad_norm 2.5415 (2.9351)	
[2022-01-26 04:10:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][360/1251]	eta 0:33:21 lr 0.000044	time 2.0606 (2.2460)	loss 3.2926 (3.0227)	grad_norm 3.1221 (2.9380)	
[2022-01-26 04:10:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][370/1251]	eta 0:32:57 lr 0.000044	time 1.8441 (2.2445)	loss 2.3620 (3.0254)	grad_norm 3.0664 (2.9382)	
[2022-01-26 04:10:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][380/1251]	eta 0:32:33 lr 0.000044	time 1.5237 (2.2429)	loss 3.1888 (3.0312)	grad_norm 2.8696 (2.9376)	
[2022-01-26 04:11:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][390/1251]	eta 0:32:09 lr 0.000044	time 2.6211 (2.2405)	loss 3.3398 (3.0316)	grad_norm 2.9384 (2.9533)	
[2022-01-26 04:11:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][400/1251]	eta 0:31:44 lr 0.000044	time 1.8151 (2.2377)	loss 3.0464 (3.0332)	grad_norm 3.0801 (2.9582)	
[2022-01-26 04:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][410/1251]	eta 0:31:18 lr 0.000044	time 1.6651 (2.2342)	loss 3.5907 (3.0330)	grad_norm 3.0465 (2.9575)	
[2022-01-26 04:12:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][420/1251]	eta 0:30:56 lr 0.000044	time 2.1552 (2.2339)	loss 3.2288 (3.0335)	grad_norm 2.5388 (2.9516)	
[2022-01-26 04:12:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][430/1251]	eta 0:30:33 lr 0.000044	time 2.7628 (2.2329)	loss 3.2959 (3.0412)	grad_norm 3.0660 (2.9489)	
[2022-01-26 04:13:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][440/1251]	eta 0:30:12 lr 0.000044	time 2.5006 (2.2347)	loss 3.0273 (3.0370)	grad_norm 3.1855 (2.9535)	
[2022-01-26 04:13:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][450/1251]	eta 0:29:48 lr 0.000044	time 2.7741 (2.2334)	loss 2.8426 (3.0402)	grad_norm 2.5421 (2.9495)	
[2022-01-26 04:13:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][460/1251]	eta 0:29:25 lr 0.000044	time 2.1105 (2.2324)	loss 2.6051 (3.0414)	grad_norm 2.8070 (2.9496)	
[2022-01-26 04:14:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][470/1251]	eta 0:29:02 lr 0.000044	time 2.9433 (2.2312)	loss 2.6900 (3.0438)	grad_norm 2.9623 (2.9517)	
[2022-01-26 04:14:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][480/1251]	eta 0:28:39 lr 0.000044	time 1.9485 (2.2304)	loss 2.2537 (3.0337)	grad_norm 2.9156 (2.9469)	
[2022-01-26 04:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][490/1251]	eta 0:28:16 lr 0.000044	time 1.8585 (2.2290)	loss 3.1498 (3.0240)	grad_norm 2.5397 (2.9430)	
[2022-01-26 04:15:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][500/1251]	eta 0:27:53 lr 0.000044	time 1.8818 (2.2286)	loss 2.9571 (3.0225)	grad_norm 2.6900 (2.9397)	
[2022-01-26 04:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][510/1251]	eta 0:27:32 lr 0.000044	time 2.2177 (2.2300)	loss 3.4446 (3.0264)	grad_norm 2.8550 (2.9372)	
[2022-01-26 04:16:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][520/1251]	eta 0:27:10 lr 0.000044	time 2.2168 (2.2299)	loss 2.3635 (3.0251)	grad_norm 3.5011 (2.9381)	
[2022-01-26 04:16:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][530/1251]	eta 0:26:45 lr 0.000044	time 1.8003 (2.2275)	loss 3.2363 (3.0235)	grad_norm 2.8491 (2.9435)	
[2022-01-26 04:16:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][540/1251]	eta 0:26:24 lr 0.000044	time 1.8089 (2.2284)	loss 3.3207 (3.0235)	grad_norm 2.7973 (2.9471)	
[2022-01-26 04:17:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][550/1251]	eta 0:26:02 lr 0.000044	time 1.9340 (2.2288)	loss 2.5244 (3.0239)	grad_norm 2.2173 (2.9454)	
[2022-01-26 04:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][560/1251]	eta 0:25:38 lr 0.000044	time 2.4990 (2.2270)	loss 3.7089 (3.0292)	grad_norm 2.7560 (2.9492)	
[2022-01-26 04:17:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][570/1251]	eta 0:25:13 lr 0.000044	time 1.9882 (2.2229)	loss 3.2444 (3.0276)	grad_norm 3.0751 (2.9493)	
[2022-01-26 04:18:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][580/1251]	eta 0:24:50 lr 0.000044	time 2.2429 (2.2211)	loss 3.1358 (3.0320)	grad_norm 2.4587 (2.9477)	
[2022-01-26 04:18:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][590/1251]	eta 0:24:29 lr 0.000044	time 1.8764 (2.2233)	loss 2.6098 (3.0313)	grad_norm 3.8849 (2.9474)	
[2022-01-26 04:18:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][600/1251]	eta 0:24:08 lr 0.000044	time 2.4030 (2.2246)	loss 2.8500 (3.0294)	grad_norm 2.5138 (2.9459)	
[2022-01-26 04:19:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][610/1251]	eta 0:23:46 lr 0.000044	time 1.5393 (2.2258)	loss 3.5030 (3.0307)	grad_norm 2.9848 (2.9460)	
[2022-01-26 04:19:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][620/1251]	eta 0:23:24 lr 0.000044	time 1.5997 (2.2252)	loss 1.8711 (3.0288)	grad_norm 2.7333 (2.9420)	
[2022-01-26 04:20:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][630/1251]	eta 0:23:00 lr 0.000044	time 2.5079 (2.2229)	loss 2.9704 (3.0285)	grad_norm 2.9486 (2.9408)	
[2022-01-26 04:20:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][640/1251]	eta 0:22:37 lr 0.000044	time 2.4547 (2.2211)	loss 3.4946 (3.0288)	grad_norm 3.3564 (2.9395)	
[2022-01-26 04:20:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][650/1251]	eta 0:22:13 lr 0.000044	time 1.9218 (2.2187)	loss 3.2950 (3.0307)	grad_norm 2.7967 (2.9374)	
[2022-01-26 04:21:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][660/1251]	eta 0:21:50 lr 0.000044	time 1.7861 (2.2174)	loss 2.2322 (3.0234)	grad_norm 2.9828 (2.9375)	
[2022-01-26 04:21:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][670/1251]	eta 0:21:28 lr 0.000044	time 2.5738 (2.2183)	loss 3.6425 (3.0273)	grad_norm 3.4082 (2.9381)	
[2022-01-26 04:21:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][680/1251]	eta 0:21:06 lr 0.000044	time 3.0934 (2.2180)	loss 3.0612 (3.0266)	grad_norm 3.0407 (2.9385)	
[2022-01-26 04:22:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][690/1251]	eta 0:20:43 lr 0.000044	time 1.6371 (2.2161)	loss 3.3405 (3.0261)	grad_norm 2.7864 (2.9373)	
[2022-01-26 04:22:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][700/1251]	eta 0:20:22 lr 0.000044	time 2.6912 (2.2180)	loss 3.1901 (3.0274)	grad_norm 3.3163 (2.9374)	
[2022-01-26 04:22:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][710/1251]	eta 0:19:59 lr 0.000044	time 1.6639 (2.2165)	loss 3.4439 (3.0265)	grad_norm 2.8008 (2.9378)	
[2022-01-26 04:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][720/1251]	eta 0:19:36 lr 0.000044	time 2.5122 (2.2157)	loss 3.1271 (3.0278)	grad_norm 2.7975 (2.9365)	
[2022-01-26 04:23:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][730/1251]	eta 0:19:13 lr 0.000044	time 1.6273 (2.2135)	loss 2.2043 (3.0274)	grad_norm 2.6621 (2.9337)	
[2022-01-26 04:24:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][740/1251]	eta 0:18:50 lr 0.000044	time 2.1776 (2.2118)	loss 2.6808 (3.0260)	grad_norm 2.6078 (2.9333)	
[2022-01-26 04:24:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][750/1251]	eta 0:18:27 lr 0.000044	time 1.5129 (2.2105)	loss 3.2026 (3.0247)	grad_norm 3.0691 (2.9354)	
[2022-01-26 04:24:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][760/1251]	eta 0:18:05 lr 0.000044	time 2.9291 (2.2114)	loss 2.7729 (3.0232)	grad_norm 2.5582 (2.9390)	
[2022-01-26 04:25:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][770/1251]	eta 0:17:43 lr 0.000044	time 1.9654 (2.2108)	loss 3.6199 (3.0240)	grad_norm 3.0114 (2.9383)	
[2022-01-26 04:25:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][780/1251]	eta 0:17:21 lr 0.000044	time 2.2749 (2.2119)	loss 2.5182 (3.0214)	grad_norm 2.9868 (2.9359)	
[2022-01-26 04:25:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][790/1251]	eta 0:16:59 lr 0.000044	time 1.5996 (2.2115)	loss 2.5458 (3.0197)	grad_norm 2.9126 (2.9370)	
[2022-01-26 04:26:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][800/1251]	eta 0:16:37 lr 0.000044	time 2.5866 (2.2108)	loss 2.6888 (3.0192)	grad_norm 3.0156 (2.9359)	
[2022-01-26 04:26:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][810/1251]	eta 0:16:14 lr 0.000044	time 1.8525 (2.2093)	loss 3.3844 (3.0224)	grad_norm 2.7344 (2.9358)	
[2022-01-26 04:26:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][820/1251]	eta 0:15:52 lr 0.000044	time 2.8350 (2.2106)	loss 2.5358 (3.0213)	grad_norm 3.7168 (2.9366)	
[2022-01-26 04:27:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][830/1251]	eta 0:15:30 lr 0.000044	time 1.8093 (2.2113)	loss 2.9566 (3.0191)	grad_norm 3.0881 (2.9369)	
[2022-01-26 04:27:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][840/1251]	eta 0:15:09 lr 0.000043	time 2.4917 (2.2117)	loss 3.1441 (3.0185)	grad_norm 3.1627 (2.9380)	
[2022-01-26 04:28:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][850/1251]	eta 0:14:46 lr 0.000043	time 1.7876 (2.2104)	loss 3.2963 (3.0204)	grad_norm 2.9987 (2.9370)	
[2022-01-26 04:28:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][860/1251]	eta 0:14:23 lr 0.000043	time 1.8334 (2.2079)	loss 2.3658 (3.0179)	grad_norm 2.5781 (2.9360)	
[2022-01-26 04:28:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][870/1251]	eta 0:14:00 lr 0.000043	time 2.0629 (2.2073)	loss 3.3158 (3.0167)	grad_norm 2.8834 (2.9351)	
[2022-01-26 04:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][880/1251]	eta 0:13:39 lr 0.000043	time 2.8375 (2.2084)	loss 3.9276 (3.0208)	grad_norm 2.8193 (2.9351)	
[2022-01-26 04:29:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][890/1251]	eta 0:13:17 lr 0.000043	time 1.7580 (2.2093)	loss 1.8029 (3.0206)	grad_norm 3.0805 (2.9348)	
[2022-01-26 04:29:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][900/1251]	eta 0:12:55 lr 0.000043	time 1.8576 (2.2083)	loss 3.5950 (3.0231)	grad_norm 2.9373 (2.9344)	
[2022-01-26 04:30:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][910/1251]	eta 0:12:32 lr 0.000043	time 2.2060 (2.2074)	loss 3.5661 (3.0242)	grad_norm 2.4425 (2.9324)	
[2022-01-26 04:30:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][920/1251]	eta 0:12:10 lr 0.000043	time 2.3908 (2.2066)	loss 3.6675 (3.0268)	grad_norm 2.8422 (2.9311)	
[2022-01-26 04:30:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][930/1251]	eta 0:11:48 lr 0.000043	time 2.0897 (2.2074)	loss 3.2848 (3.0283)	grad_norm 3.0706 (2.9307)	
[2022-01-26 04:31:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][940/1251]	eta 0:11:26 lr 0.000043	time 1.8261 (2.2076)	loss 3.0487 (3.0265)	grad_norm 3.2191 (2.9319)	
[2022-01-26 04:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][950/1251]	eta 0:11:04 lr 0.000043	time 2.5975 (2.2081)	loss 3.4361 (3.0272)	grad_norm 2.7064 (2.9320)	
[2022-01-26 04:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][960/1251]	eta 0:10:42 lr 0.000043	time 2.3737 (2.2080)	loss 3.4717 (3.0247)	grad_norm 2.8017 (2.9303)	
[2022-01-26 04:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][970/1251]	eta 0:10:20 lr 0.000043	time 3.1129 (2.2085)	loss 2.6209 (3.0268)	grad_norm 2.7826 (2.9297)	
[2022-01-26 04:32:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][980/1251]	eta 0:09:58 lr 0.000043	time 1.9156 (2.2077)	loss 3.3714 (3.0279)	grad_norm 3.0727 (2.9296)	
[2022-01-26 04:33:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][990/1251]	eta 0:09:35 lr 0.000043	time 1.9356 (2.2057)	loss 2.2377 (3.0255)	grad_norm 2.9229 (2.9323)	
[2022-01-26 04:33:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1000/1251]	eta 0:09:13 lr 0.000043	time 1.9164 (2.2040)	loss 2.7888 (3.0250)	grad_norm 3.1555 (2.9354)	
[2022-01-26 04:33:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1010/1251]	eta 0:08:50 lr 0.000043	time 2.1582 (2.2029)	loss 2.8133 (3.0233)	grad_norm 2.3856 (2.9340)	
[2022-01-26 04:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1020/1251]	eta 0:08:28 lr 0.000043	time 2.1711 (2.2027)	loss 3.5036 (3.0228)	grad_norm 2.8345 (2.9336)	
[2022-01-26 04:34:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1030/1251]	eta 0:08:06 lr 0.000043	time 2.2218 (2.2035)	loss 2.5386 (3.0221)	grad_norm 3.2530 (2.9334)	
[2022-01-26 04:34:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1040/1251]	eta 0:07:45 lr 0.000043	time 1.8481 (2.2057)	loss 3.3352 (3.0246)	grad_norm 2.9199 (2.9341)	
[2022-01-26 04:35:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1050/1251]	eta 0:07:23 lr 0.000043	time 2.5072 (2.2058)	loss 2.9906 (3.0261)	grad_norm 3.1423 (2.9336)	
[2022-01-26 04:35:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1060/1251]	eta 0:07:01 lr 0.000043	time 1.8949 (2.2055)	loss 2.4704 (3.0267)	grad_norm 2.8538 (2.9346)	
[2022-01-26 04:36:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1070/1251]	eta 0:06:39 lr 0.000043	time 2.8936 (2.2057)	loss 3.4318 (3.0269)	grad_norm 2.8386 (2.9338)	
[2022-01-26 04:36:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1080/1251]	eta 0:06:16 lr 0.000043	time 1.8785 (2.2041)	loss 3.7664 (3.0269)	grad_norm 2.8086 (2.9338)	
[2022-01-26 04:36:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1090/1251]	eta 0:05:54 lr 0.000043	time 1.8965 (2.2027)	loss 2.2420 (3.0278)	grad_norm 3.7013 (2.9327)	
[2022-01-26 04:37:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1100/1251]	eta 0:05:32 lr 0.000043	time 1.9736 (2.2022)	loss 3.7710 (3.0291)	grad_norm 3.0274 (2.9328)	
[2022-01-26 04:37:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1110/1251]	eta 0:05:10 lr 0.000043	time 2.6637 (2.2028)	loss 3.5113 (3.0297)	grad_norm 2.9131 (2.9323)	
[2022-01-26 04:37:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1120/1251]	eta 0:04:48 lr 0.000043	time 1.8581 (2.2026)	loss 3.0076 (3.0299)	grad_norm 2.5384 (2.9313)	
[2022-01-26 04:38:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1130/1251]	eta 0:04:26 lr 0.000043	time 1.8773 (2.2020)	loss 3.2523 (3.0294)	grad_norm 2.7646 (2.9320)	
[2022-01-26 04:38:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1140/1251]	eta 0:04:04 lr 0.000043	time 2.2170 (2.2017)	loss 2.9755 (3.0285)	grad_norm 3.4031 (2.9318)	
[2022-01-26 04:38:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1150/1251]	eta 0:03:42 lr 0.000043	time 3.4711 (2.2031)	loss 3.0201 (3.0291)	grad_norm 2.5082 (2.9303)	
[2022-01-26 04:39:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1160/1251]	eta 0:03:20 lr 0.000043	time 2.1621 (2.2035)	loss 3.1678 (3.0296)	grad_norm 3.9406 (2.9319)	
[2022-01-26 04:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1170/1251]	eta 0:02:58 lr 0.000043	time 1.7169 (2.2029)	loss 2.0244 (3.0301)	grad_norm 3.0145 (2.9342)	
[2022-01-26 04:40:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1180/1251]	eta 0:02:36 lr 0.000043	time 2.5908 (2.2038)	loss 3.4771 (3.0305)	grad_norm 2.6113 (2.9347)	
[2022-01-26 04:40:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1190/1251]	eta 0:02:14 lr 0.000043	time 2.7832 (2.2041)	loss 3.1381 (3.0313)	grad_norm 2.8540 (2.9342)	
[2022-01-26 04:40:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1200/1251]	eta 0:01:52 lr 0.000043	time 1.6494 (2.2027)	loss 3.5125 (3.0309)	grad_norm 2.7474 (2.9332)	
[2022-01-26 04:41:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1210/1251]	eta 0:01:30 lr 0.000043	time 1.8468 (2.2014)	loss 1.7502 (3.0287)	grad_norm 3.8595 (2.9332)	
[2022-01-26 04:41:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1220/1251]	eta 0:01:08 lr 0.000043	time 2.4819 (2.2016)	loss 3.6836 (3.0307)	grad_norm 2.6048 (2.9315)	
[2022-01-26 04:41:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1230/1251]	eta 0:00:46 lr 0.000043	time 1.9446 (2.2009)	loss 3.5495 (3.0302)	grad_norm 2.5966 (2.9295)	
[2022-01-26 04:42:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1240/1251]	eta 0:00:24 lr 0.000043	time 1.4666 (2.2001)	loss 3.2520 (3.0322)	grad_norm 2.9643 (2.9303)	
[2022-01-26 04:42:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [264/300][1250/1251]	eta 0:00:02 lr 0.000043	time 1.2081 (2.1947)	loss 3.2808 (3.0333)	grad_norm 2.3927 (2.9297)	
[2022-01-26 04:42:27 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 264 training takes 0:45:45
[2022-01-26 04:42:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.904 (18.904)	Loss 0.8278 (0.8278)	Acc@1 80.664 (80.664)	Acc@5 95.117 (95.117)	
[2022-01-26 04:43:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.185 (3.408)	Loss 0.8184 (0.8183)	Acc@1 81.152 (81.188)	Acc@5 95.215 (95.446)	
[2022-01-26 04:43:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.607 (2.607)	Loss 0.8131 (0.8146)	Acc@1 79.395 (80.878)	Acc@5 95.215 (95.443)	
[2022-01-26 04:43:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.958 (2.333)	Loss 0.7996 (0.8139)	Acc@1 82.422 (80.888)	Acc@5 95.703 (95.432)	
[2022-01-26 04:43:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.102 (2.193)	Loss 0.8678 (0.8222)	Acc@1 79.785 (80.707)	Acc@5 94.922 (95.320)	
[2022-01-26 04:44:04 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.690 Acc@5 95.312
[2022-01-26 04:44:04 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.7%
[2022-01-26 04:44:04 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.78%
[2022-01-26 04:44:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][0/1251]	eta 7:38:20 lr 0.000043	time 21.9826 (21.9826)	loss 3.4197 (3.4197)	grad_norm 3.5022 (3.5022)	
[2022-01-26 04:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][10/1251]	eta 1:21:49 lr 0.000043	time 1.9970 (3.9558)	loss 3.4082 (3.1308)	grad_norm 2.5047 (2.8877)	
[2022-01-26 04:45:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][20/1251]	eta 1:04:06 lr 0.000043	time 1.2691 (3.1243)	loss 2.3869 (3.1269)	grad_norm 4.6879 (2.9488)	
[2022-01-26 04:45:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][30/1251]	eta 0:56:15 lr 0.000043	time 1.3723 (2.7649)	loss 3.2132 (3.1601)	grad_norm 2.4907 (2.9194)	
[2022-01-26 04:45:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][40/1251]	eta 0:54:51 lr 0.000043	time 4.0340 (2.7177)	loss 2.3783 (3.1688)	grad_norm 2.8234 (2.9697)	
[2022-01-26 04:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][50/1251]	eta 0:52:19 lr 0.000043	time 2.3997 (2.6142)	loss 3.8204 (3.1532)	grad_norm 2.4887 (2.9418)	
[2022-01-26 04:46:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][60/1251]	eta 0:50:48 lr 0.000043	time 2.0993 (2.5593)	loss 2.6439 (3.1528)	grad_norm 2.7566 (2.9288)	
[2022-01-26 04:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][70/1251]	eta 0:49:23 lr 0.000043	time 1.5697 (2.5091)	loss 2.2569 (3.1390)	grad_norm 2.5935 (2.9392)	
[2022-01-26 04:47:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][80/1251]	eta 0:48:53 lr 0.000043	time 3.9448 (2.5049)	loss 3.5488 (3.0877)	grad_norm 3.2136 (2.9333)	
[2022-01-26 04:47:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][90/1251]	eta 0:48:02 lr 0.000043	time 1.9193 (2.4831)	loss 3.4142 (3.0992)	grad_norm 2.7508 (2.9298)	
[2022-01-26 04:48:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][100/1251]	eta 0:46:45 lr 0.000043	time 1.8579 (2.4374)	loss 3.0481 (3.0864)	grad_norm 2.5871 (2.9419)	
[2022-01-26 04:48:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][110/1251]	eta 0:45:37 lr 0.000043	time 1.9328 (2.3991)	loss 3.0946 (3.0924)	grad_norm 2.5342 (2.9490)	
[2022-01-26 04:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][120/1251]	eta 0:45:01 lr 0.000043	time 3.1739 (2.3885)	loss 3.1776 (3.0955)	grad_norm 2.9148 (2.9401)	
[2022-01-26 04:49:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][130/1251]	eta 0:44:28 lr 0.000043	time 2.6805 (2.3800)	loss 2.3077 (3.0903)	grad_norm 2.7807 (2.9492)	
[2022-01-26 04:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][140/1251]	eta 0:43:55 lr 0.000043	time 2.0901 (2.3719)	loss 3.5095 (3.0842)	grad_norm 3.0241 (2.9425)	
[2022-01-26 04:50:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][150/1251]	eta 0:43:12 lr 0.000043	time 1.5591 (2.3549)	loss 2.3131 (3.0696)	grad_norm 3.9217 (2.9603)	
[2022-01-26 04:50:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][160/1251]	eta 0:42:32 lr 0.000043	time 2.9168 (2.3393)	loss 2.1436 (3.0665)	grad_norm 2.5035 (2.9556)	
[2022-01-26 04:50:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][170/1251]	eta 0:41:59 lr 0.000043	time 1.9037 (2.3311)	loss 2.0948 (3.0496)	grad_norm 2.4394 (2.9537)	
[2022-01-26 04:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][180/1251]	eta 0:41:23 lr 0.000043	time 1.8569 (2.3188)	loss 3.5729 (3.0437)	grad_norm 3.7116 (2.9491)	
[2022-01-26 04:51:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][190/1251]	eta 0:40:51 lr 0.000043	time 1.8676 (2.3106)	loss 3.4940 (3.0473)	grad_norm 2.9469 (2.9545)	
[2022-01-26 04:51:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][200/1251]	eta 0:40:21 lr 0.000043	time 2.8233 (2.3043)	loss 3.3395 (3.0471)	grad_norm 2.8850 (2.9582)	
[2022-01-26 04:52:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][210/1251]	eta 0:39:54 lr 0.000043	time 2.7423 (2.2998)	loss 2.5755 (3.0385)	grad_norm 2.9405 (2.9568)	
[2022-01-26 04:52:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][220/1251]	eta 0:39:24 lr 0.000043	time 2.2410 (2.2933)	loss 3.1345 (3.0355)	grad_norm 3.0922 (2.9526)	
[2022-01-26 04:52:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][230/1251]	eta 0:39:03 lr 0.000043	time 3.1442 (2.2951)	loss 3.0134 (3.0286)	grad_norm 3.4097 (2.9631)	
[2022-01-26 04:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][240/1251]	eta 0:38:37 lr 0.000043	time 2.5393 (2.2919)	loss 1.7709 (3.0193)	grad_norm 2.8813 (2.9582)	
[2022-01-26 04:53:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][250/1251]	eta 0:38:13 lr 0.000043	time 2.4756 (2.2917)	loss 3.1324 (3.0209)	grad_norm 2.6099 (2.9600)	
[2022-01-26 04:54:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][260/1251]	eta 0:37:45 lr 0.000042	time 1.8782 (2.2857)	loss 3.5759 (3.0216)	grad_norm 2.7537 (2.9637)	
[2022-01-26 04:54:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][270/1251]	eta 0:37:09 lr 0.000042	time 2.1244 (2.2728)	loss 3.3929 (3.0338)	grad_norm 3.5420 (2.9662)	
[2022-01-26 04:54:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][280/1251]	eta 0:36:36 lr 0.000042	time 1.7549 (2.2624)	loss 2.0555 (3.0298)	grad_norm 2.7341 (2.9634)	
[2022-01-26 04:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][290/1251]	eta 0:36:07 lr 0.000042	time 1.6811 (2.2551)	loss 3.1971 (3.0297)	grad_norm 3.1894 (2.9615)	
[2022-01-26 04:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][300/1251]	eta 0:35:42 lr 0.000042	time 2.0947 (2.2532)	loss 2.8158 (3.0366)	grad_norm 2.5158 (2.9553)	
[2022-01-26 04:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][310/1251]	eta 0:35:16 lr 0.000042	time 2.0077 (2.2488)	loss 3.6124 (3.0338)	grad_norm 3.0070 (2.9526)	
[2022-01-26 04:56:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][320/1251]	eta 0:34:49 lr 0.000042	time 1.8816 (2.2441)	loss 3.3385 (3.0373)	grad_norm 3.1017 (2.9565)	
[2022-01-26 04:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][330/1251]	eta 0:34:26 lr 0.000042	time 1.9926 (2.2437)	loss 3.3252 (3.0387)	grad_norm 2.6917 (2.9516)	
[2022-01-26 04:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][340/1251]	eta 0:34:08 lr 0.000042	time 2.1643 (2.2487)	loss 3.5686 (3.0437)	grad_norm 2.5721 (2.9476)	
[2022-01-26 04:57:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][350/1251]	eta 0:33:48 lr 0.000042	time 1.7285 (2.2508)	loss 2.8058 (3.0430)	grad_norm 2.7973 (2.9499)	
[2022-01-26 04:57:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][360/1251]	eta 0:33:30 lr 0.000042	time 2.5829 (2.2560)	loss 2.8275 (3.0431)	grad_norm 2.7823 (2.9487)	
[2022-01-26 04:58:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][370/1251]	eta 0:33:06 lr 0.000042	time 2.1236 (2.2544)	loss 2.1754 (3.0439)	grad_norm 3.0967 (2.9521)	
[2022-01-26 04:58:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][380/1251]	eta 0:32:37 lr 0.000042	time 1.8006 (2.2477)	loss 2.8252 (3.0447)	grad_norm 3.1822 (2.9465)	
[2022-01-26 04:58:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][390/1251]	eta 0:32:09 lr 0.000042	time 1.9791 (2.2414)	loss 3.2221 (3.0520)	grad_norm 2.7686 (2.9487)	
[2022-01-26 04:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][400/1251]	eta 0:31:43 lr 0.000042	time 2.1944 (2.2368)	loss 3.1899 (3.0542)	grad_norm 2.6595 (2.9511)	
[2022-01-26 04:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][410/1251]	eta 0:31:19 lr 0.000042	time 1.7884 (2.2343)	loss 2.7789 (3.0495)	grad_norm 2.7330 (2.9498)	
[2022-01-26 04:59:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][420/1251]	eta 0:30:58 lr 0.000042	time 2.0783 (2.2361)	loss 2.9765 (3.0425)	grad_norm 2.4466 (2.9471)	
[2022-01-26 05:00:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][430/1251]	eta 0:30:37 lr 0.000042	time 1.8753 (2.2380)	loss 2.8969 (3.0404)	grad_norm 2.9115 (2.9495)	
[2022-01-26 05:00:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][440/1251]	eta 0:30:16 lr 0.000042	time 1.9521 (2.2396)	loss 3.3659 (3.0417)	grad_norm 3.0806 (2.9483)	
[2022-01-26 05:00:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][450/1251]	eta 0:29:53 lr 0.000042	time 2.1734 (2.2397)	loss 3.4699 (3.0415)	grad_norm 2.5773 (2.9478)	
[2022-01-26 05:01:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][460/1251]	eta 0:29:31 lr 0.000042	time 1.9510 (2.2397)	loss 3.2702 (3.0420)	grad_norm 6.0591 (2.9526)	
[2022-01-26 05:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][470/1251]	eta 0:29:07 lr 0.000042	time 2.1665 (2.2373)	loss 2.1231 (3.0401)	grad_norm 2.4417 (2.9502)	
[2022-01-26 05:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][480/1251]	eta 0:28:42 lr 0.000042	time 1.7211 (2.2336)	loss 3.3381 (3.0346)	grad_norm 2.4978 (2.9466)	
[2022-01-26 05:02:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][490/1251]	eta 0:28:17 lr 0.000042	time 2.1922 (2.2306)	loss 3.0044 (3.0361)	grad_norm 2.9221 (2.9434)	
[2022-01-26 05:02:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][500/1251]	eta 0:27:56 lr 0.000042	time 1.9857 (2.2320)	loss 2.5708 (3.0362)	grad_norm 2.6733 (2.9438)	
[2022-01-26 05:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][510/1251]	eta 0:27:33 lr 0.000042	time 2.2964 (2.2319)	loss 2.1929 (3.0315)	grad_norm 2.6846 (2.9411)	
[2022-01-26 05:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][520/1251]	eta 0:27:09 lr 0.000042	time 1.4910 (2.2295)	loss 3.2791 (3.0299)	grad_norm 2.7377 (2.9420)	
[2022-01-26 05:03:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][530/1251]	eta 0:26:47 lr 0.000042	time 1.9063 (2.2296)	loss 3.2990 (3.0308)	grad_norm 2.8696 (2.9390)	
[2022-01-26 05:04:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][540/1251]	eta 0:26:26 lr 0.000042	time 2.2896 (2.2316)	loss 3.4099 (3.0311)	grad_norm 3.0451 (2.9414)	
[2022-01-26 05:04:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][550/1251]	eta 0:26:02 lr 0.000042	time 2.2494 (2.2294)	loss 3.3324 (3.0294)	grad_norm 3.1791 (2.9390)	
[2022-01-26 05:04:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][560/1251]	eta 0:25:38 lr 0.000042	time 1.9171 (2.2258)	loss 3.6367 (3.0254)	grad_norm 2.6532 (2.9369)	
[2022-01-26 05:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][570/1251]	eta 0:25:14 lr 0.000042	time 2.8243 (2.2246)	loss 3.6083 (3.0258)	grad_norm 2.9671 (2.9367)	
[2022-01-26 05:05:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][580/1251]	eta 0:24:51 lr 0.000042	time 1.6167 (2.2231)	loss 2.3073 (3.0234)	grad_norm 2.9362 (2.9379)	
[2022-01-26 05:05:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][590/1251]	eta 0:24:28 lr 0.000042	time 2.0702 (2.2220)	loss 1.9921 (3.0197)	grad_norm 3.2494 (2.9396)	
[2022-01-26 05:06:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][600/1251]	eta 0:24:06 lr 0.000042	time 2.2319 (2.2219)	loss 3.5601 (3.0237)	grad_norm 3.3961 (2.9393)	
[2022-01-26 05:06:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][610/1251]	eta 0:23:45 lr 0.000042	time 2.9233 (2.2232)	loss 2.6553 (3.0238)	grad_norm 3.2213 (2.9427)	
[2022-01-26 05:07:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][620/1251]	eta 0:23:24 lr 0.000042	time 1.6769 (2.2252)	loss 3.4279 (3.0213)	grad_norm 2.9903 (2.9419)	
[2022-01-26 05:07:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][630/1251]	eta 0:23:02 lr 0.000042	time 1.8811 (2.2257)	loss 3.1099 (3.0236)	grad_norm 3.0874 (2.9448)	
[2022-01-26 05:07:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][640/1251]	eta 0:22:39 lr 0.000042	time 1.9192 (2.2243)	loss 3.4644 (3.0221)	grad_norm 3.0323 (2.9450)	
[2022-01-26 05:08:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][650/1251]	eta 0:22:16 lr 0.000042	time 2.4435 (2.2234)	loss 3.3292 (3.0228)	grad_norm 2.5474 (2.9423)	
[2022-01-26 05:08:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][660/1251]	eta 0:21:52 lr 0.000042	time 2.1720 (2.2216)	loss 1.9723 (3.0226)	grad_norm 2.8260 (2.9427)	
[2022-01-26 05:08:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][670/1251]	eta 0:21:29 lr 0.000042	time 1.6077 (2.2202)	loss 2.3524 (3.0214)	grad_norm 2.7375 (2.9454)	
[2022-01-26 05:09:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][680/1251]	eta 0:21:08 lr 0.000042	time 2.2173 (2.2222)	loss 3.6118 (3.0240)	grad_norm 3.1487 (2.9462)	
[2022-01-26 05:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][690/1251]	eta 0:20:46 lr 0.000042	time 2.2140 (2.2213)	loss 1.8350 (3.0208)	grad_norm 2.9959 (2.9443)	
[2022-01-26 05:10:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][700/1251]	eta 0:20:23 lr 0.000042	time 2.5114 (2.2212)	loss 3.1985 (3.0198)	grad_norm 2.5922 (2.9405)	
[2022-01-26 05:10:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][710/1251]	eta 0:20:00 lr 0.000042	time 1.9738 (2.2184)	loss 2.4028 (3.0184)	grad_norm 2.9541 (2.9390)	
[2022-01-26 05:10:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][720/1251]	eta 0:19:38 lr 0.000042	time 2.7873 (2.2188)	loss 3.3161 (3.0186)	grad_norm 2.5350 (2.9383)	
[2022-01-26 05:11:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][730/1251]	eta 0:19:16 lr 0.000042	time 2.2331 (2.2198)	loss 3.6390 (3.0165)	grad_norm 3.0681 (2.9401)	
[2022-01-26 05:11:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][740/1251]	eta 0:18:55 lr 0.000042	time 1.8595 (2.2225)	loss 3.1923 (3.0160)	grad_norm 3.2052 (2.9416)	
[2022-01-26 05:11:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][750/1251]	eta 0:18:33 lr 0.000042	time 1.9477 (2.2224)	loss 2.6952 (3.0167)	grad_norm 2.7282 (2.9410)	
[2022-01-26 05:12:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][760/1251]	eta 0:18:10 lr 0.000042	time 2.1369 (2.2211)	loss 2.9641 (3.0153)	grad_norm 3.8058 (2.9456)	
[2022-01-26 05:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][770/1251]	eta 0:17:46 lr 0.000042	time 1.8278 (2.2178)	loss 3.5547 (3.0161)	grad_norm 2.5637 (2.9444)	
[2022-01-26 05:12:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][780/1251]	eta 0:17:24 lr 0.000042	time 1.9509 (2.2170)	loss 2.8414 (3.0139)	grad_norm 2.7544 (2.9444)	
[2022-01-26 05:13:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][790/1251]	eta 0:17:02 lr 0.000042	time 2.4558 (2.2172)	loss 3.0420 (3.0148)	grad_norm 2.6273 (2.9463)	
[2022-01-26 05:13:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][800/1251]	eta 0:16:40 lr 0.000042	time 1.9164 (2.2179)	loss 3.0942 (3.0132)	grad_norm 2.5831 (2.9474)	
[2022-01-26 05:14:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][810/1251]	eta 0:16:18 lr 0.000042	time 2.1917 (2.2188)	loss 3.4739 (3.0149)	grad_norm 3.3308 (2.9475)	
[2022-01-26 05:14:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][820/1251]	eta 0:15:56 lr 0.000042	time 2.0095 (2.2204)	loss 3.9433 (3.0166)	grad_norm 2.6549 (2.9491)	
[2022-01-26 05:14:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][830/1251]	eta 0:15:34 lr 0.000042	time 2.4462 (2.2197)	loss 3.0484 (3.0163)	grad_norm 3.1437 (2.9477)	
[2022-01-26 05:15:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][840/1251]	eta 0:15:11 lr 0.000042	time 2.0176 (2.2184)	loss 3.4075 (3.0170)	grad_norm 2.4369 (2.9470)	
[2022-01-26 05:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][850/1251]	eta 0:14:49 lr 0.000042	time 1.8808 (2.2177)	loss 2.2285 (3.0157)	grad_norm 2.9741 (2.9465)	
[2022-01-26 05:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][860/1251]	eta 0:14:27 lr 0.000042	time 2.1899 (2.2189)	loss 3.4680 (3.0174)	grad_norm 3.2701 (2.9464)	
[2022-01-26 05:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][870/1251]	eta 0:14:05 lr 0.000042	time 1.8967 (2.2182)	loss 3.4568 (3.0159)	grad_norm 2.6058 (2.9463)	
[2022-01-26 05:16:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][880/1251]	eta 0:13:42 lr 0.000042	time 1.6404 (2.2167)	loss 3.5340 (3.0175)	grad_norm 3.3893 (2.9481)	
[2022-01-26 05:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][890/1251]	eta 0:13:20 lr 0.000042	time 1.8771 (2.2168)	loss 3.5616 (3.0176)	grad_norm 2.8164 (2.9475)	
[2022-01-26 05:17:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][900/1251]	eta 0:12:58 lr 0.000042	time 1.8999 (2.2178)	loss 2.6973 (3.0150)	grad_norm 2.4755 (2.9450)	
[2022-01-26 05:17:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][910/1251]	eta 0:12:36 lr 0.000042	time 2.5588 (2.2183)	loss 2.6615 (3.0159)	grad_norm 3.3405 (2.9444)	
[2022-01-26 05:18:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][920/1251]	eta 0:12:14 lr 0.000042	time 1.7852 (2.2177)	loss 2.9951 (3.0144)	grad_norm 2.4534 (2.9443)	
[2022-01-26 05:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][930/1251]	eta 0:11:51 lr 0.000042	time 1.8689 (2.2158)	loss 2.7047 (3.0110)	grad_norm 3.2595 (2.9426)	
[2022-01-26 05:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][940/1251]	eta 0:11:28 lr 0.000041	time 1.9517 (2.2141)	loss 3.6931 (3.0128)	grad_norm 3.4681 (2.9428)	
[2022-01-26 05:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][950/1251]	eta 0:11:06 lr 0.000041	time 2.3426 (2.2153)	loss 3.0659 (3.0130)	grad_norm 2.5868 (2.9421)	
[2022-01-26 05:19:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][960/1251]	eta 0:10:45 lr 0.000041	time 2.0096 (2.2171)	loss 1.8283 (3.0140)	grad_norm 3.6023 (2.9441)	
[2022-01-26 05:19:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][970/1251]	eta 0:10:23 lr 0.000041	time 2.3325 (2.2174)	loss 3.1832 (3.0148)	grad_norm 2.6043 (2.9454)	
[2022-01-26 05:20:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][980/1251]	eta 0:10:00 lr 0.000041	time 1.9530 (2.2156)	loss 3.0670 (3.0155)	grad_norm 2.6602 (2.9445)	
[2022-01-26 05:20:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][990/1251]	eta 0:09:38 lr 0.000041	time 2.6878 (2.2151)	loss 2.4373 (3.0167)	grad_norm 3.0193 (2.9440)	
[2022-01-26 05:21:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1000/1251]	eta 0:09:15 lr 0.000041	time 2.0867 (2.2149)	loss 2.9780 (3.0167)	grad_norm 3.1976 (2.9465)	
[2022-01-26 05:21:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1010/1251]	eta 0:08:53 lr 0.000041	time 1.8450 (2.2143)	loss 3.1566 (3.0158)	grad_norm 2.6492 (2.9463)	
[2022-01-26 05:21:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1020/1251]	eta 0:08:31 lr 0.000041	time 2.2470 (2.2138)	loss 2.9761 (3.0178)	grad_norm 3.1753 (2.9465)	
[2022-01-26 05:22:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1030/1251]	eta 0:08:09 lr 0.000041	time 2.2601 (2.2132)	loss 2.2526 (3.0164)	grad_norm 3.3938 (2.9461)	
[2022-01-26 05:22:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1040/1251]	eta 0:07:46 lr 0.000041	time 1.7372 (2.2132)	loss 2.9972 (3.0163)	grad_norm 3.4005 (2.9465)	
[2022-01-26 05:22:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1050/1251]	eta 0:07:24 lr 0.000041	time 1.8825 (2.2122)	loss 3.6558 (3.0194)	grad_norm 2.7674 (2.9459)	
[2022-01-26 05:23:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1060/1251]	eta 0:07:02 lr 0.000041	time 2.5190 (2.2125)	loss 2.9135 (3.0204)	grad_norm 3.1123 (2.9454)	
[2022-01-26 05:23:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1070/1251]	eta 0:06:40 lr 0.000041	time 2.8444 (2.2121)	loss 2.5924 (3.0204)	grad_norm 2.9405 (2.9441)	
[2022-01-26 05:23:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1080/1251]	eta 0:06:18 lr 0.000041	time 1.8918 (2.2124)	loss 2.5026 (3.0196)	grad_norm 2.8443 (2.9438)	
[2022-01-26 05:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1090/1251]	eta 0:05:56 lr 0.000041	time 1.6714 (2.2116)	loss 2.5150 (3.0203)	grad_norm 2.7215 (2.9449)	
[2022-01-26 05:24:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1100/1251]	eta 0:05:33 lr 0.000041	time 1.9218 (2.2114)	loss 3.3844 (3.0204)	grad_norm 2.7292 (2.9449)	
[2022-01-26 05:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1110/1251]	eta 0:05:11 lr 0.000041	time 2.8690 (2.2109)	loss 3.1097 (3.0204)	grad_norm 2.6091 (2.9441)	
[2022-01-26 05:25:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1120/1251]	eta 0:04:49 lr 0.000041	time 2.1082 (2.2103)	loss 2.8720 (3.0205)	grad_norm 3.3052 (2.9446)	
[2022-01-26 05:25:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1130/1251]	eta 0:04:27 lr 0.000041	time 2.4949 (2.2112)	loss 3.3549 (3.0218)	grad_norm 2.7956 (2.9456)	
[2022-01-26 05:26:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1140/1251]	eta 0:04:05 lr 0.000041	time 1.8823 (2.2099)	loss 3.3389 (3.0220)	grad_norm 2.9658 (2.9448)	
[2022-01-26 05:26:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1150/1251]	eta 0:03:43 lr 0.000041	time 2.8218 (2.2105)	loss 3.0052 (3.0201)	grad_norm 2.7769 (2.9440)	
[2022-01-26 05:26:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1160/1251]	eta 0:03:21 lr 0.000041	time 1.6014 (2.2090)	loss 3.5830 (3.0208)	grad_norm 2.7978 (2.9433)	
[2022-01-26 05:27:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1170/1251]	eta 0:02:58 lr 0.000041	time 2.4212 (2.2088)	loss 3.2719 (3.0201)	grad_norm 2.9475 (2.9449)	
[2022-01-26 05:27:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1180/1251]	eta 0:02:36 lr 0.000041	time 1.6666 (2.2080)	loss 3.3033 (3.0205)	grad_norm 3.4656 (2.9452)	
[2022-01-26 05:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1190/1251]	eta 0:02:14 lr 0.000041	time 2.7927 (2.2080)	loss 2.2263 (3.0210)	grad_norm 2.5007 (2.9445)	
[2022-01-26 05:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1200/1251]	eta 0:01:52 lr 0.000041	time 1.9608 (2.2074)	loss 3.6933 (3.0231)	grad_norm 2.6010 (2.9430)	
[2022-01-26 05:28:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1210/1251]	eta 0:01:30 lr 0.000041	time 1.9493 (2.2075)	loss 2.9458 (3.0223)	grad_norm 2.5943 (2.9414)	
[2022-01-26 05:28:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1220/1251]	eta 0:01:08 lr 0.000041	time 2.1307 (2.2069)	loss 3.5483 (3.0228)	grad_norm 2.8496 (2.9414)	
[2022-01-26 05:29:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1230/1251]	eta 0:00:46 lr 0.000041	time 2.8975 (2.2074)	loss 3.1877 (3.0230)	grad_norm 2.7535 (2.9413)	
[2022-01-26 05:29:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1240/1251]	eta 0:00:24 lr 0.000041	time 1.4437 (2.2058)	loss 3.1859 (3.0218)	grad_norm 3.0121 (2.9407)	
[2022-01-26 05:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [265/300][1250/1251]	eta 0:00:02 lr 0.000041	time 1.1648 (2.2008)	loss 2.6836 (3.0209)	grad_norm 3.1174 (2.9405)	
[2022-01-26 05:29:58 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 265 training takes 0:45:53
[2022-01-26 05:30:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.714 (18.714)	Loss 0.7705 (0.7705)	Acc@1 80.176 (80.176)	Acc@5 96.289 (96.289)	
[2022-01-26 05:30:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.308 (3.366)	Loss 0.8313 (0.8205)	Acc@1 80.957 (80.744)	Acc@5 94.922 (95.339)	
[2022-01-26 05:30:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.280 (2.530)	Loss 0.7625 (0.8074)	Acc@1 81.934 (81.031)	Acc@5 96.289 (95.447)	
[2022-01-26 05:31:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.299 (2.246)	Loss 0.8548 (0.8107)	Acc@1 80.664 (80.995)	Acc@5 95.020 (95.341)	
[2022-01-26 05:31:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.279 (2.191)	Loss 0.8471 (0.8125)	Acc@1 80.176 (80.952)	Acc@5 94.336 (95.301)	
[2022-01-26 05:31:35 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.834 Acc@5 95.318
[2022-01-26 05:31:35 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.8%
[2022-01-26 05:31:35 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.83%
[2022-01-26 05:31:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][0/1251]	eta 7:26:50 lr 0.000041	time 21.4315 (21.4315)	loss 3.5499 (3.5499)	grad_norm 3.3968 (3.3968)	
[2022-01-26 05:32:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][10/1251]	eta 1:22:10 lr 0.000041	time 1.6081 (3.9732)	loss 3.2425 (3.1291)	grad_norm 3.1999 (2.8083)	
[2022-01-26 05:32:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][20/1251]	eta 1:03:51 lr 0.000041	time 1.7008 (3.1127)	loss 3.2880 (3.1753)	grad_norm 3.0398 (2.8002)	
[2022-01-26 05:33:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][30/1251]	eta 0:57:00 lr 0.000041	time 1.5069 (2.8013)	loss 2.1852 (3.0559)	grad_norm 2.9794 (2.8552)	
[2022-01-26 05:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][40/1251]	eta 0:53:49 lr 0.000041	time 3.1983 (2.6665)	loss 3.1587 (3.0186)	grad_norm 2.6264 (2.8454)	
[2022-01-26 05:33:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][50/1251]	eta 0:52:01 lr 0.000041	time 1.5271 (2.5992)	loss 3.5181 (3.0316)	grad_norm 2.8704 (2.8504)	
[2022-01-26 05:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][60/1251]	eta 0:50:25 lr 0.000041	time 2.1205 (2.5404)	loss 3.1744 (3.0623)	grad_norm 2.9578 (2.8683)	
[2022-01-26 05:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][70/1251]	eta 0:49:06 lr 0.000041	time 1.8651 (2.4949)	loss 3.3558 (3.0174)	grad_norm 3.0455 (2.8872)	
[2022-01-26 05:34:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][80/1251]	eta 0:48:22 lr 0.000041	time 3.0888 (2.4789)	loss 3.1941 (2.9932)	grad_norm 3.1839 (2.9351)	
[2022-01-26 05:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][90/1251]	eta 0:47:47 lr 0.000041	time 1.5376 (2.4696)	loss 2.4117 (3.0000)	grad_norm 3.0547 (2.9647)	
[2022-01-26 05:35:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][100/1251]	eta 0:47:03 lr 0.000041	time 1.8497 (2.4532)	loss 3.1186 (3.0056)	grad_norm 2.7955 (2.9755)	
[2022-01-26 05:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][110/1251]	eta 0:46:01 lr 0.000041	time 1.8433 (2.4200)	loss 3.3455 (3.0000)	grad_norm 2.9616 (2.9563)	
[2022-01-26 05:36:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][120/1251]	eta 0:45:05 lr 0.000041	time 2.0430 (2.3926)	loss 3.2378 (3.0107)	grad_norm 3.0983 (2.9545)	
[2022-01-26 05:36:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][130/1251]	eta 0:44:08 lr 0.000041	time 2.1966 (2.3629)	loss 3.3608 (2.9922)	grad_norm 3.0169 (2.9566)	
[2022-01-26 05:37:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][140/1251]	eta 0:43:16 lr 0.000041	time 1.9506 (2.3372)	loss 2.2189 (2.9980)	grad_norm 2.9770 (2.9503)	
[2022-01-26 05:37:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][150/1251]	eta 0:42:32 lr 0.000041	time 1.7530 (2.3179)	loss 3.0766 (3.0131)	grad_norm 3.8322 (2.9881)	
[2022-01-26 05:37:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][160/1251]	eta 0:41:57 lr 0.000041	time 2.3055 (2.3071)	loss 3.0319 (3.0141)	grad_norm 2.7783 (2.9823)	
[2022-01-26 05:38:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][170/1251]	eta 0:41:31 lr 0.000041	time 1.7782 (2.3053)	loss 3.4508 (3.0204)	grad_norm 3.1353 (2.9802)	
[2022-01-26 05:38:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][180/1251]	eta 0:41:06 lr 0.000041	time 2.1715 (2.3031)	loss 2.8501 (3.0114)	grad_norm 3.0406 (2.9799)	
[2022-01-26 05:38:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][190/1251]	eta 0:40:37 lr 0.000041	time 1.8351 (2.2975)	loss 3.2971 (3.0211)	grad_norm 2.5373 (2.9711)	
[2022-01-26 05:39:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][200/1251]	eta 0:40:11 lr 0.000041	time 3.1331 (2.2947)	loss 2.8495 (3.0095)	grad_norm 2.6450 (2.9684)	
[2022-01-26 05:39:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][210/1251]	eta 0:39:48 lr 0.000041	time 3.2337 (2.2948)	loss 3.0693 (3.0020)	grad_norm 3.3915 (2.9669)	
[2022-01-26 05:40:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][220/1251]	eta 0:39:28 lr 0.000041	time 1.8131 (2.2974)	loss 2.8478 (3.0069)	grad_norm 3.3472 (2.9671)	
[2022-01-26 05:40:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][230/1251]	eta 0:39:08 lr 0.000041	time 1.8912 (2.3005)	loss 2.9851 (3.0085)	grad_norm 3.0184 (2.9653)	
[2022-01-26 05:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][240/1251]	eta 0:38:47 lr 0.000041	time 2.7925 (2.3019)	loss 3.2016 (3.0164)	grad_norm 2.8008 (2.9625)	
[2022-01-26 05:41:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][250/1251]	eta 0:38:11 lr 0.000041	time 1.6040 (2.2896)	loss 3.6548 (3.0303)	grad_norm 2.9144 (2.9685)	
[2022-01-26 05:41:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][260/1251]	eta 0:37:36 lr 0.000041	time 1.9501 (2.2773)	loss 3.3970 (3.0318)	grad_norm 2.9756 (2.9682)	
[2022-01-26 05:41:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][270/1251]	eta 0:37:08 lr 0.000041	time 1.9491 (2.2717)	loss 3.5075 (3.0481)	grad_norm 2.7240 (2.9693)	
[2022-01-26 05:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][280/1251]	eta 0:36:43 lr 0.000041	time 2.3527 (2.2695)	loss 2.4870 (3.0395)	grad_norm 3.0372 (2.9720)	
[2022-01-26 05:42:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][290/1251]	eta 0:36:21 lr 0.000041	time 2.0056 (2.2702)	loss 1.8073 (3.0382)	grad_norm 2.7475 (2.9830)	
[2022-01-26 05:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][300/1251]	eta 0:35:55 lr 0.000041	time 2.3791 (2.2664)	loss 2.9593 (3.0197)	grad_norm 2.6849 (2.9855)	
[2022-01-26 05:43:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][310/1251]	eta 0:35:28 lr 0.000041	time 2.2038 (2.2622)	loss 2.2715 (3.0245)	grad_norm 2.8242 (2.9843)	
[2022-01-26 05:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][320/1251]	eta 0:35:03 lr 0.000041	time 2.8777 (2.2590)	loss 3.2958 (3.0289)	grad_norm 2.9482 (2.9773)	
[2022-01-26 05:44:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][330/1251]	eta 0:34:37 lr 0.000041	time 2.2799 (2.2553)	loss 3.9489 (3.0277)	grad_norm 3.1183 (2.9761)	
[2022-01-26 05:44:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][340/1251]	eta 0:34:14 lr 0.000041	time 2.2533 (2.2554)	loss 3.4301 (3.0290)	grad_norm 2.6466 (2.9746)	
[2022-01-26 05:44:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][350/1251]	eta 0:33:50 lr 0.000041	time 2.4875 (2.2537)	loss 3.0621 (3.0253)	grad_norm 3.3978 (2.9919)	
[2022-01-26 05:45:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][360/1251]	eta 0:33:29 lr 0.000041	time 1.8354 (2.2554)	loss 3.1826 (3.0246)	grad_norm 3.1656 (2.9894)	
[2022-01-26 05:45:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][370/1251]	eta 0:33:07 lr 0.000041	time 1.8993 (2.2555)	loss 2.1343 (3.0138)	grad_norm 4.0241 (2.9938)	
[2022-01-26 05:45:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][380/1251]	eta 0:32:42 lr 0.000040	time 1.9834 (2.2528)	loss 3.1572 (3.0189)	grad_norm 2.9418 (2.9953)	
[2022-01-26 05:46:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][390/1251]	eta 0:32:15 lr 0.000040	time 2.1835 (2.2478)	loss 3.6271 (3.0219)	grad_norm 4.7899 (3.0020)	
[2022-01-26 05:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][400/1251]	eta 0:31:47 lr 0.000040	time 1.8718 (2.2418)	loss 3.1520 (3.0239)	grad_norm 3.2675 (2.9998)	
[2022-01-26 05:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][410/1251]	eta 0:31:22 lr 0.000040	time 2.0659 (2.2384)	loss 2.4012 (3.0250)	grad_norm 2.9587 (2.9972)	
[2022-01-26 05:47:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][420/1251]	eta 0:30:56 lr 0.000040	time 1.6861 (2.2342)	loss 3.2084 (3.0266)	grad_norm 2.4963 (2.9928)	
[2022-01-26 05:47:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][430/1251]	eta 0:30:32 lr 0.000040	time 2.3107 (2.2318)	loss 2.4410 (3.0268)	grad_norm 3.2060 (2.9862)	
[2022-01-26 05:48:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][440/1251]	eta 0:30:11 lr 0.000040	time 2.7878 (2.2332)	loss 3.4783 (3.0328)	grad_norm 2.7987 (2.9822)	
[2022-01-26 05:48:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][450/1251]	eta 0:29:48 lr 0.000040	time 2.6051 (2.2323)	loss 3.7318 (3.0350)	grad_norm 2.5567 (2.9796)	
[2022-01-26 05:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][460/1251]	eta 0:29:24 lr 0.000040	time 2.2119 (2.2312)	loss 3.1031 (3.0320)	grad_norm 2.5733 (2.9806)	
[2022-01-26 05:49:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][470/1251]	eta 0:29:03 lr 0.000040	time 3.0664 (2.2319)	loss 3.2323 (3.0285)	grad_norm 2.8775 (2.9840)	
[2022-01-26 05:49:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][480/1251]	eta 0:28:42 lr 0.000040	time 3.5025 (2.2342)	loss 2.2807 (3.0262)	grad_norm 2.7988 (2.9912)	
[2022-01-26 05:49:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][490/1251]	eta 0:28:20 lr 0.000040	time 1.3838 (2.2342)	loss 2.1777 (3.0151)	grad_norm 2.7634 (2.9919)	
[2022-01-26 05:50:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][500/1251]	eta 0:27:58 lr 0.000040	time 1.4391 (2.2351)	loss 2.8857 (3.0138)	grad_norm 2.4535 (2.9903)	
[2022-01-26 05:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][510/1251]	eta 0:27:37 lr 0.000040	time 2.6227 (2.2362)	loss 2.3221 (3.0082)	grad_norm 2.9758 (2.9886)	
[2022-01-26 05:50:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][520/1251]	eta 0:27:13 lr 0.000040	time 2.2600 (2.2346)	loss 2.4699 (3.0112)	grad_norm 3.4040 (2.9920)	
[2022-01-26 05:51:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][530/1251]	eta 0:26:48 lr 0.000040	time 1.7157 (2.2315)	loss 3.4005 (3.0087)	grad_norm 2.7917 (2.9907)	
[2022-01-26 05:51:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][540/1251]	eta 0:26:22 lr 0.000040	time 1.8329 (2.2260)	loss 2.9590 (3.0074)	grad_norm 2.6878 (2.9896)	
[2022-01-26 05:52:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][550/1251]	eta 0:25:58 lr 0.000040	time 2.0457 (2.2236)	loss 2.4366 (3.0073)	grad_norm 3.5890 (2.9870)	
[2022-01-26 05:52:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][560/1251]	eta 0:25:37 lr 0.000040	time 3.0505 (2.2249)	loss 3.4383 (3.0058)	grad_norm 3.0214 (2.9849)	
[2022-01-26 05:52:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][570/1251]	eta 0:25:15 lr 0.000040	time 2.6980 (2.2261)	loss 2.3972 (3.0045)	grad_norm 3.6992 (2.9853)	
[2022-01-26 05:53:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][580/1251]	eta 0:24:54 lr 0.000040	time 1.6563 (2.2269)	loss 2.6530 (3.0064)	grad_norm 2.8627 (2.9798)	
[2022-01-26 05:53:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][590/1251]	eta 0:24:32 lr 0.000040	time 2.3829 (2.2282)	loss 2.5370 (3.0052)	grad_norm 3.7029 (2.9784)	
[2022-01-26 05:53:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][600/1251]	eta 0:24:09 lr 0.000040	time 2.5485 (2.2269)	loss 3.2525 (3.0014)	grad_norm 2.5198 (2.9777)	
[2022-01-26 05:54:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][610/1251]	eta 0:23:45 lr 0.000040	time 2.2470 (2.2235)	loss 3.3566 (3.0030)	grad_norm 2.5755 (2.9776)	
[2022-01-26 05:54:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][620/1251]	eta 0:23:21 lr 0.000040	time 2.4318 (2.2204)	loss 3.0345 (2.9991)	grad_norm 2.4854 (2.9752)	
[2022-01-26 05:54:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][630/1251]	eta 0:22:57 lr 0.000040	time 2.1801 (2.2183)	loss 3.2097 (3.0012)	grad_norm 2.7835 (2.9760)	
[2022-01-26 05:55:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][640/1251]	eta 0:22:34 lr 0.000040	time 1.5885 (2.2165)	loss 3.3233 (2.9999)	grad_norm 2.7646 (2.9746)	
[2022-01-26 05:55:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][650/1251]	eta 0:22:10 lr 0.000040	time 1.8578 (2.2133)	loss 2.8064 (2.9993)	grad_norm 2.5987 (2.9723)	
[2022-01-26 05:55:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][660/1251]	eta 0:21:46 lr 0.000040	time 1.9911 (2.2114)	loss 2.5533 (2.9950)	grad_norm 2.6859 (2.9704)	
[2022-01-26 05:56:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][670/1251]	eta 0:21:24 lr 0.000040	time 2.8690 (2.2109)	loss 3.3381 (3.0009)	grad_norm 2.5979 (2.9696)	
[2022-01-26 05:56:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][680/1251]	eta 0:21:01 lr 0.000040	time 1.8879 (2.2089)	loss 2.6617 (3.0020)	grad_norm 2.8559 (2.9686)	
[2022-01-26 05:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][690/1251]	eta 0:20:39 lr 0.000040	time 2.5761 (2.2092)	loss 3.4916 (2.9994)	grad_norm 2.7599 (2.9661)	
[2022-01-26 05:57:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][700/1251]	eta 0:20:18 lr 0.000040	time 2.1252 (2.2107)	loss 3.3954 (2.9968)	grad_norm 3.1024 (2.9656)	
[2022-01-26 05:57:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][710/1251]	eta 0:19:57 lr 0.000040	time 2.8964 (2.2132)	loss 3.2494 (3.0000)	grad_norm 2.8781 (2.9644)	
[2022-01-26 05:58:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][720/1251]	eta 0:19:35 lr 0.000040	time 1.8913 (2.2141)	loss 2.9942 (2.9947)	grad_norm 3.1003 (2.9624)	
[2022-01-26 05:58:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][730/1251]	eta 0:19:14 lr 0.000040	time 2.7755 (2.2168)	loss 3.1125 (2.9945)	grad_norm 2.8137 (2.9609)	
[2022-01-26 05:58:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][740/1251]	eta 0:18:52 lr 0.000040	time 2.2829 (2.2157)	loss 3.4777 (2.9948)	grad_norm 2.9155 (2.9595)	
[2022-01-26 05:59:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][750/1251]	eta 0:18:29 lr 0.000040	time 1.9597 (2.2145)	loss 3.4311 (2.9977)	grad_norm 2.4684 (2.9579)	
[2022-01-26 05:59:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][760/1251]	eta 0:18:06 lr 0.000040	time 2.2326 (2.2120)	loss 3.3818 (2.9979)	grad_norm 2.7953 (2.9557)	
[2022-01-26 06:00:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][770/1251]	eta 0:17:44 lr 0.000040	time 2.5982 (2.2135)	loss 2.5997 (2.9965)	grad_norm 2.8417 (2.9567)	
[2022-01-26 06:00:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][780/1251]	eta 0:17:22 lr 0.000040	time 2.8602 (2.2139)	loss 1.8696 (2.9928)	grad_norm 2.9064 (2.9581)	
[2022-01-26 06:00:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][790/1251]	eta 0:17:00 lr 0.000040	time 2.0153 (2.2133)	loss 3.4681 (2.9920)	grad_norm 2.4795 (2.9577)	
[2022-01-26 06:01:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][800/1251]	eta 0:16:36 lr 0.000040	time 2.2394 (2.2100)	loss 3.0844 (2.9905)	grad_norm 3.0079 (2.9568)	
[2022-01-26 06:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][810/1251]	eta 0:16:14 lr 0.000040	time 2.2755 (2.2089)	loss 3.1141 (2.9915)	grad_norm 3.1663 (2.9579)	
[2022-01-26 06:01:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][820/1251]	eta 0:15:51 lr 0.000040	time 2.2644 (2.2088)	loss 3.3323 (2.9908)	grad_norm 2.9001 (2.9567)	
[2022-01-26 06:02:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][830/1251]	eta 0:15:30 lr 0.000040	time 2.3280 (2.2091)	loss 3.4096 (2.9925)	grad_norm 3.0784 (2.9567)	
[2022-01-26 06:02:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][840/1251]	eta 0:15:08 lr 0.000040	time 2.5203 (2.2096)	loss 3.1282 (2.9954)	grad_norm 2.4591 (2.9575)	
[2022-01-26 06:02:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][850/1251]	eta 0:14:46 lr 0.000040	time 2.2187 (2.2096)	loss 2.1813 (2.9968)	grad_norm 2.7054 (2.9567)	
[2022-01-26 06:03:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][860/1251]	eta 0:14:24 lr 0.000040	time 2.2767 (2.2111)	loss 3.2405 (2.9978)	grad_norm 2.6248 (2.9572)	
[2022-01-26 06:03:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][870/1251]	eta 0:14:01 lr 0.000040	time 2.2330 (2.2099)	loss 3.7164 (2.9986)	grad_norm 2.7238 (2.9548)	
[2022-01-26 06:04:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][880/1251]	eta 0:13:39 lr 0.000040	time 2.2528 (2.2078)	loss 1.7780 (2.9974)	grad_norm 3.0758 (2.9573)	
[2022-01-26 06:04:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][890/1251]	eta 0:13:16 lr 0.000040	time 1.8297 (2.2068)	loss 3.6275 (3.0006)	grad_norm 2.6497 (2.9549)	
[2022-01-26 06:04:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][900/1251]	eta 0:12:54 lr 0.000040	time 2.0037 (2.2056)	loss 3.1948 (3.0034)	grad_norm 2.9334 (2.9553)	
[2022-01-26 06:05:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][910/1251]	eta 0:12:32 lr 0.000040	time 1.9341 (2.2073)	loss 2.9044 (3.0055)	grad_norm 2.5332 (2.9539)	
[2022-01-26 06:05:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][920/1251]	eta 0:12:10 lr 0.000040	time 2.8733 (2.2079)	loss 3.0648 (3.0048)	grad_norm 2.6860 (2.9529)	
[2022-01-26 06:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][930/1251]	eta 0:11:48 lr 0.000040	time 1.7105 (2.2082)	loss 3.5919 (3.0059)	grad_norm 2.8391 (2.9521)	
[2022-01-26 06:06:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][940/1251]	eta 0:11:26 lr 0.000040	time 1.9382 (2.2090)	loss 3.4110 (3.0070)	grad_norm 2.6640 (2.9499)	
[2022-01-26 06:06:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][950/1251]	eta 0:11:04 lr 0.000040	time 1.6486 (2.2069)	loss 3.4909 (3.0048)	grad_norm 2.8754 (2.9500)	
[2022-01-26 06:06:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][960/1251]	eta 0:10:41 lr 0.000040	time 2.5161 (2.2060)	loss 3.3767 (3.0055)	grad_norm 3.1845 (2.9522)	
[2022-01-26 06:07:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][970/1251]	eta 0:10:19 lr 0.000040	time 1.5954 (2.2040)	loss 3.0155 (3.0061)	grad_norm 2.4414 (2.9524)	
[2022-01-26 06:07:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][980/1251]	eta 0:09:57 lr 0.000040	time 2.5363 (2.2049)	loss 2.9950 (3.0045)	grad_norm 2.6165 (2.9510)	
[2022-01-26 06:07:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][990/1251]	eta 0:09:35 lr 0.000040	time 2.2114 (2.2037)	loss 2.7018 (3.0044)	grad_norm 3.0224 (2.9505)	
[2022-01-26 06:08:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1000/1251]	eta 0:09:12 lr 0.000040	time 2.6046 (2.2031)	loss 2.1938 (3.0022)	grad_norm 2.5578 (2.9476)	
[2022-01-26 06:08:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1010/1251]	eta 0:08:51 lr 0.000040	time 2.3850 (2.2039)	loss 2.9641 (3.0013)	grad_norm 2.3969 (2.9482)	
[2022-01-26 06:09:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1020/1251]	eta 0:08:29 lr 0.000040	time 2.2356 (2.2043)	loss 2.0336 (3.0008)	grad_norm 2.3230 (2.9467)	
[2022-01-26 06:09:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1030/1251]	eta 0:08:07 lr 0.000040	time 2.2474 (2.2046)	loss 2.9897 (3.0008)	grad_norm 2.7670 (2.9493)	
[2022-01-26 06:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1040/1251]	eta 0:07:44 lr 0.000040	time 2.1887 (2.2037)	loss 3.5351 (3.0011)	grad_norm 3.1385 (2.9487)	
[2022-01-26 06:10:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1050/1251]	eta 0:07:22 lr 0.000040	time 1.9634 (2.2030)	loss 2.9666 (3.0026)	grad_norm 3.0054 (2.9501)	
[2022-01-26 06:10:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1060/1251]	eta 0:07:00 lr 0.000040	time 1.8115 (2.2030)	loss 3.0487 (3.0045)	grad_norm 2.9477 (2.9488)	
[2022-01-26 06:10:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1070/1251]	eta 0:06:38 lr 0.000040	time 2.2192 (2.2042)	loss 3.0024 (3.0056)	grad_norm 2.7495 (2.9476)	
[2022-01-26 06:11:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1080/1251]	eta 0:06:16 lr 0.000040	time 1.9170 (2.2043)	loss 3.6934 (3.0079)	grad_norm 3.3336 (2.9499)	
[2022-01-26 06:11:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1090/1251]	eta 0:05:54 lr 0.000039	time 2.8503 (2.2049)	loss 3.1943 (3.0086)	grad_norm 3.2468 (2.9499)	
[2022-01-26 06:12:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1100/1251]	eta 0:05:32 lr 0.000039	time 1.9820 (2.2039)	loss 3.0407 (3.0097)	grad_norm 3.0887 (2.9505)	
[2022-01-26 06:12:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1110/1251]	eta 0:05:10 lr 0.000039	time 1.9001 (2.2028)	loss 3.6601 (3.0113)	grad_norm 3.5266 (2.9513)	
[2022-01-26 06:12:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1120/1251]	eta 0:04:48 lr 0.000039	time 2.3641 (2.2016)	loss 3.4749 (3.0129)	grad_norm 3.2001 (2.9516)	
[2022-01-26 06:13:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1130/1251]	eta 0:04:26 lr 0.000039	time 2.1520 (2.2002)	loss 3.4808 (3.0127)	grad_norm 3.3407 (2.9542)	
[2022-01-26 06:13:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1140/1251]	eta 0:04:04 lr 0.000039	time 2.4362 (2.2003)	loss 2.8613 (3.0121)	grad_norm 3.5429 (2.9547)	
[2022-01-26 06:13:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1150/1251]	eta 0:03:42 lr 0.000039	time 1.8178 (2.2009)	loss 2.9139 (3.0126)	grad_norm 2.9817 (2.9541)	
[2022-01-26 06:14:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1160/1251]	eta 0:03:20 lr 0.000039	time 2.3419 (2.2018)	loss 3.2087 (3.0129)	grad_norm 2.6010 (2.9539)	
[2022-01-26 06:14:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1170/1251]	eta 0:02:58 lr 0.000039	time 1.6115 (2.2013)	loss 3.2294 (3.0132)	grad_norm 2.5900 (2.9524)	
[2022-01-26 06:14:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1180/1251]	eta 0:02:36 lr 0.000039	time 2.5906 (2.2003)	loss 2.7620 (3.0121)	grad_norm 3.0546 (2.9531)	
[2022-01-26 06:15:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1190/1251]	eta 0:02:14 lr 0.000039	time 1.6897 (2.1989)	loss 3.2268 (3.0147)	grad_norm 2.6836 (2.9519)	
[2022-01-26 06:15:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1200/1251]	eta 0:01:52 lr 0.000039	time 2.4647 (2.1978)	loss 3.1404 (3.0164)	grad_norm 2.9014 (2.9526)	
[2022-01-26 06:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1210/1251]	eta 0:01:30 lr 0.000039	time 1.7626 (2.1968)	loss 3.5960 (3.0190)	grad_norm 2.8007 (2.9519)	
[2022-01-26 06:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1220/1251]	eta 0:01:08 lr 0.000039	time 2.2198 (2.1958)	loss 3.2009 (3.0174)	grad_norm 3.2077 (2.9513)	
[2022-01-26 06:16:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1230/1251]	eta 0:00:46 lr 0.000039	time 1.5453 (2.1952)	loss 3.4614 (3.0180)	grad_norm 3.0305 (2.9506)	
[2022-01-26 06:17:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1240/1251]	eta 0:00:24 lr 0.000039	time 1.6905 (2.1982)	loss 3.2566 (3.0178)	grad_norm 2.9400 (2.9505)	
[2022-01-26 06:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [266/300][1250/1251]	eta 0:00:02 lr 0.000039	time 1.1604 (2.1936)	loss 3.1105 (3.0168)	grad_norm 3.3963 (2.9517)	
[2022-01-26 06:17:19 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 266 training takes 0:45:44
[2022-01-26 06:17:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.419 (18.419)	Loss 0.8860 (0.8860)	Acc@1 78.906 (78.906)	Acc@5 94.629 (94.629)	
[2022-01-26 06:17:55 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.002 (3.255)	Loss 0.7922 (0.8301)	Acc@1 81.445 (80.824)	Acc@5 95.703 (95.446)	
[2022-01-26 06:18:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.350 (2.560)	Loss 0.8693 (0.8390)	Acc@1 79.199 (80.627)	Acc@5 94.629 (95.089)	
[2022-01-26 06:18:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.498 (2.295)	Loss 0.8020 (0.8256)	Acc@1 79.492 (80.759)	Acc@5 95.312 (95.272)	
[2022-01-26 06:18:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.494 (2.169)	Loss 0.8216 (0.8222)	Acc@1 81.543 (80.895)	Acc@5 94.727 (95.293)	
[2022-01-26 06:18:55 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.822 Acc@5 95.296
[2022-01-26 06:18:55 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.8%
[2022-01-26 06:18:55 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.83%
[2022-01-26 06:19:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][0/1251]	eta 7:31:18 lr 0.000039	time 21.6459 (21.6459)	loss 3.0939 (3.0939)	grad_norm 3.3763 (3.3763)	
[2022-01-26 06:19:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][10/1251]	eta 1:25:07 lr 0.000039	time 2.1459 (4.1155)	loss 3.4416 (3.0446)	grad_norm 2.6248 (2.8866)	
[2022-01-26 06:20:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][20/1251]	eta 1:05:19 lr 0.000039	time 1.8079 (3.1843)	loss 2.8469 (3.0602)	grad_norm 2.8430 (2.9124)	
[2022-01-26 06:20:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][30/1251]	eta 0:57:45 lr 0.000039	time 1.8105 (2.8383)	loss 3.6388 (3.0300)	grad_norm 3.4466 (2.9505)	
[2022-01-26 06:20:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][40/1251]	eta 0:54:58 lr 0.000039	time 3.0205 (2.7235)	loss 1.9409 (2.9745)	grad_norm 2.3548 (2.9685)	
[2022-01-26 06:21:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][50/1251]	eta 0:53:52 lr 0.000039	time 2.9779 (2.6913)	loss 3.2928 (2.9942)	grad_norm 3.1943 (2.9568)	
[2022-01-26 06:21:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][60/1251]	eta 0:51:47 lr 0.000039	time 1.9986 (2.6090)	loss 3.8918 (3.0193)	grad_norm 2.7056 (2.9497)	
[2022-01-26 06:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][70/1251]	eta 0:49:38 lr 0.000039	time 2.3132 (2.5220)	loss 2.7965 (3.0136)	grad_norm 2.7927 (2.9570)	
[2022-01-26 06:22:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][80/1251]	eta 0:48:02 lr 0.000039	time 2.2681 (2.4619)	loss 2.5959 (3.0108)	grad_norm 3.4326 (2.9598)	
[2022-01-26 06:22:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][90/1251]	eta 0:46:55 lr 0.000039	time 1.7095 (2.4247)	loss 3.5488 (3.0232)	grad_norm 2.8313 (2.9592)	
[2022-01-26 06:22:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][100/1251]	eta 0:45:59 lr 0.000039	time 2.1919 (2.3979)	loss 3.3861 (3.0420)	grad_norm 2.5473 (2.9487)	
[2022-01-26 06:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][110/1251]	eta 0:45:08 lr 0.000039	time 1.5901 (2.3740)	loss 2.5557 (3.0182)	grad_norm 2.4864 (2.9445)	
[2022-01-26 06:23:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][120/1251]	eta 0:44:40 lr 0.000039	time 2.2255 (2.3703)	loss 3.1166 (3.0191)	grad_norm 3.3626 (2.9416)	
[2022-01-26 06:24:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][130/1251]	eta 0:44:09 lr 0.000039	time 2.2764 (2.3635)	loss 3.5381 (3.0319)	grad_norm 3.1007 (2.9391)	
[2022-01-26 06:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][140/1251]	eta 0:43:27 lr 0.000039	time 2.2462 (2.3468)	loss 2.8517 (3.0406)	grad_norm 3.2651 (2.9470)	
[2022-01-26 06:24:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][150/1251]	eta 0:42:50 lr 0.000039	time 1.8547 (2.3344)	loss 2.7746 (3.0661)	grad_norm 2.7941 (2.9531)	
[2022-01-26 06:25:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][160/1251]	eta 0:42:11 lr 0.000039	time 1.8516 (2.3204)	loss 3.1435 (3.0773)	grad_norm 2.9449 (2.9591)	
[2022-01-26 06:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][170/1251]	eta 0:41:43 lr 0.000039	time 2.2155 (2.3158)	loss 3.3948 (3.0708)	grad_norm 3.0738 (2.9675)	
[2022-01-26 06:25:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][180/1251]	eta 0:41:16 lr 0.000039	time 1.8713 (2.3123)	loss 3.0242 (3.0548)	grad_norm 2.9762 (2.9794)	
[2022-01-26 06:26:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][190/1251]	eta 0:40:45 lr 0.000039	time 1.8451 (2.3047)	loss 2.9347 (3.0642)	grad_norm 3.0265 (2.9968)	
[2022-01-26 06:26:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][200/1251]	eta 0:40:14 lr 0.000039	time 1.9522 (2.2975)	loss 3.5637 (3.0591)	grad_norm 3.1507 (2.9938)	
[2022-01-26 06:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][210/1251]	eta 0:39:50 lr 0.000039	time 2.0735 (2.2961)	loss 3.4061 (3.0563)	grad_norm 2.5633 (2.9894)	
[2022-01-26 06:27:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][220/1251]	eta 0:39:18 lr 0.000039	time 1.6334 (2.2875)	loss 3.2497 (3.0616)	grad_norm 2.4704 (2.9847)	
[2022-01-26 06:27:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][230/1251]	eta 0:38:41 lr 0.000039	time 2.2714 (2.2742)	loss 3.9682 (3.0631)	grad_norm 3.3155 (2.9840)	
[2022-01-26 06:28:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][240/1251]	eta 0:38:13 lr 0.000039	time 1.6706 (2.2689)	loss 2.8027 (3.0640)	grad_norm 2.7157 (2.9871)	
[2022-01-26 06:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][250/1251]	eta 0:37:49 lr 0.000039	time 2.3968 (2.2668)	loss 3.3519 (3.0672)	grad_norm 2.8447 (2.9865)	
[2022-01-26 06:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][260/1251]	eta 0:37:22 lr 0.000039	time 1.9152 (2.2632)	loss 2.5577 (3.0649)	grad_norm 2.7870 (2.9844)	
[2022-01-26 06:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][270/1251]	eta 0:36:53 lr 0.000039	time 1.8714 (2.2560)	loss 3.6941 (3.0602)	grad_norm 2.8375 (2.9828)	
[2022-01-26 06:29:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][280/1251]	eta 0:36:24 lr 0.000039	time 1.6775 (2.2493)	loss 2.6130 (3.0602)	grad_norm 2.6988 (2.9748)	
[2022-01-26 06:29:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][290/1251]	eta 0:36:02 lr 0.000039	time 2.9554 (2.2507)	loss 2.1055 (3.0501)	grad_norm 3.2511 (2.9712)	
[2022-01-26 06:30:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][300/1251]	eta 0:35:41 lr 0.000039	time 2.1507 (2.2516)	loss 2.8382 (3.0492)	grad_norm 2.8617 (2.9733)	
[2022-01-26 06:30:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][310/1251]	eta 0:35:17 lr 0.000039	time 1.7110 (2.2502)	loss 3.4169 (3.0497)	grad_norm 2.7596 (2.9699)	
[2022-01-26 06:30:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][320/1251]	eta 0:34:54 lr 0.000039	time 1.4786 (2.2497)	loss 2.0350 (3.0453)	grad_norm 2.5696 (2.9654)	
[2022-01-26 06:31:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][330/1251]	eta 0:34:33 lr 0.000039	time 2.9011 (2.2509)	loss 2.9657 (3.0413)	grad_norm 2.6661 (2.9606)	
[2022-01-26 06:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][340/1251]	eta 0:34:05 lr 0.000039	time 1.8978 (2.2448)	loss 3.4113 (3.0477)	grad_norm 3.8762 (2.9632)	
[2022-01-26 06:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][350/1251]	eta 0:33:42 lr 0.000039	time 1.8551 (2.2447)	loss 3.5736 (3.0498)	grad_norm 2.7468 (2.9671)	
[2022-01-26 06:32:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][360/1251]	eta 0:33:17 lr 0.000039	time 1.6357 (2.2413)	loss 2.7019 (3.0433)	grad_norm 2.6006 (2.9740)	
[2022-01-26 06:32:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][370/1251]	eta 0:32:54 lr 0.000039	time 3.0339 (2.2407)	loss 1.9964 (3.0435)	grad_norm 3.4106 (2.9813)	
[2022-01-26 06:33:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][380/1251]	eta 0:32:28 lr 0.000039	time 2.2155 (2.2375)	loss 3.4593 (3.0376)	grad_norm 3.0191 (2.9803)	
[2022-01-26 06:33:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][390/1251]	eta 0:32:06 lr 0.000039	time 1.9125 (2.2379)	loss 3.3538 (3.0304)	grad_norm 3.6792 (2.9835)	
[2022-01-26 06:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][400/1251]	eta 0:31:44 lr 0.000039	time 1.6444 (2.2384)	loss 2.0265 (3.0255)	grad_norm 2.8812 (2.9892)	
[2022-01-26 06:34:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][410/1251]	eta 0:31:25 lr 0.000039	time 3.5552 (2.2422)	loss 1.8935 (3.0218)	grad_norm 3.2489 (2.9896)	
[2022-01-26 06:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][420/1251]	eta 0:31:05 lr 0.000039	time 3.5960 (2.2447)	loss 3.0924 (3.0233)	grad_norm 2.5239 (2.9893)	
[2022-01-26 06:35:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][430/1251]	eta 0:30:40 lr 0.000039	time 2.1375 (2.2414)	loss 2.9467 (3.0242)	grad_norm 3.7054 (2.9860)	
[2022-01-26 06:35:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][440/1251]	eta 0:30:14 lr 0.000039	time 1.7034 (2.2369)	loss 2.5172 (3.0258)	grad_norm 5.0332 (2.9893)	
[2022-01-26 06:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][450/1251]	eta 0:29:48 lr 0.000039	time 1.9701 (2.2332)	loss 3.5594 (3.0261)	grad_norm 2.5905 (2.9880)	
[2022-01-26 06:36:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][460/1251]	eta 0:29:29 lr 0.000039	time 4.8470 (2.2376)	loss 2.6863 (3.0277)	grad_norm 2.9352 (2.9855)	
[2022-01-26 06:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][470/1251]	eta 0:29:06 lr 0.000039	time 2.4642 (2.2362)	loss 3.3472 (3.0229)	grad_norm 2.5040 (2.9836)	
[2022-01-26 06:36:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][480/1251]	eta 0:28:42 lr 0.000039	time 1.9197 (2.2340)	loss 3.0435 (3.0228)	grad_norm 2.9712 (2.9818)	
[2022-01-26 06:37:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][490/1251]	eta 0:28:17 lr 0.000039	time 2.0980 (2.2308)	loss 2.9214 (3.0209)	grad_norm 2.9785 (2.9835)	
[2022-01-26 06:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][500/1251]	eta 0:27:53 lr 0.000039	time 3.4248 (2.2288)	loss 2.6741 (3.0207)	grad_norm 2.6111 (2.9856)	
[2022-01-26 06:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][510/1251]	eta 0:27:29 lr 0.000039	time 1.8251 (2.2265)	loss 3.4768 (3.0218)	grad_norm 3.2691 (2.9849)	
[2022-01-26 06:38:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][520/1251]	eta 0:27:09 lr 0.000039	time 2.7306 (2.2294)	loss 3.3250 (3.0296)	grad_norm 2.9538 (2.9860)	
[2022-01-26 06:38:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][530/1251]	eta 0:26:47 lr 0.000039	time 2.2245 (2.2290)	loss 3.6995 (3.0332)	grad_norm 3.2304 (2.9893)	
[2022-01-26 06:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][540/1251]	eta 0:26:24 lr 0.000039	time 2.5831 (2.2281)	loss 2.5366 (3.0308)	grad_norm 2.8822 (2.9889)	
[2022-01-26 06:39:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][550/1251]	eta 0:25:58 lr 0.000038	time 2.2497 (2.2231)	loss 3.5985 (3.0348)	grad_norm 2.8027 (2.9873)	
[2022-01-26 06:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][560/1251]	eta 0:25:34 lr 0.000038	time 2.7134 (2.2211)	loss 3.4107 (3.0359)	grad_norm 2.6150 (2.9862)	
[2022-01-26 06:40:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][570/1251]	eta 0:25:11 lr 0.000038	time 2.1030 (2.2192)	loss 3.4743 (3.0386)	grad_norm 3.5101 (2.9921)	
[2022-01-26 06:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][580/1251]	eta 0:24:49 lr 0.000038	time 2.1670 (2.2200)	loss 2.3001 (3.0413)	grad_norm 2.3741 (2.9893)	
[2022-01-26 06:40:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][590/1251]	eta 0:24:28 lr 0.000038	time 2.8211 (2.2216)	loss 3.0619 (3.0462)	grad_norm 3.0449 (2.9912)	
[2022-01-26 06:41:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][600/1251]	eta 0:24:07 lr 0.000038	time 2.5048 (2.2230)	loss 3.4952 (3.0508)	grad_norm 3.4136 (2.9916)	
[2022-01-26 06:41:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][610/1251]	eta 0:23:44 lr 0.000038	time 2.2433 (2.2230)	loss 3.5905 (3.0556)	grad_norm 3.1809 (2.9940)	
[2022-01-26 06:41:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][620/1251]	eta 0:23:22 lr 0.000038	time 2.1552 (2.2230)	loss 3.2380 (3.0558)	grad_norm 2.8337 (2.9916)	
[2022-01-26 06:42:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][630/1251]	eta 0:22:59 lr 0.000038	time 2.2790 (2.2207)	loss 1.8152 (3.0547)	grad_norm 3.3397 (2.9914)	
[2022-01-26 06:42:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][640/1251]	eta 0:22:34 lr 0.000038	time 2.5229 (2.2164)	loss 3.2653 (3.0539)	grad_norm 2.4402 (2.9880)	
[2022-01-26 06:42:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][650/1251]	eta 0:22:10 lr 0.000038	time 2.0027 (2.2131)	loss 3.1687 (3.0521)	grad_norm 2.8472 (2.9882)	
[2022-01-26 06:43:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][660/1251]	eta 0:21:46 lr 0.000038	time 1.6026 (2.2108)	loss 3.6414 (3.0524)	grad_norm 3.0040 (2.9904)	
[2022-01-26 06:43:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][670/1251]	eta 0:21:23 lr 0.000038	time 2.1562 (2.2089)	loss 3.6815 (3.0488)	grad_norm 3.2340 (2.9924)	
[2022-01-26 06:43:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][680/1251]	eta 0:21:00 lr 0.000038	time 1.8628 (2.2077)	loss 3.3343 (3.0502)	grad_norm 3.0026 (2.9913)	
[2022-01-26 06:44:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][690/1251]	eta 0:20:37 lr 0.000038	time 2.1978 (2.2057)	loss 3.2141 (3.0547)	grad_norm 2.5109 (2.9894)	
[2022-01-26 06:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][700/1251]	eta 0:20:15 lr 0.000038	time 2.1160 (2.2060)	loss 3.5418 (3.0582)	grad_norm 2.9627 (2.9878)	
[2022-01-26 06:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][710/1251]	eta 0:19:54 lr 0.000038	time 2.4014 (2.2083)	loss 3.5897 (3.0562)	grad_norm 2.7111 (2.9879)	
[2022-01-26 06:45:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][720/1251]	eta 0:19:34 lr 0.000038	time 2.1014 (2.2110)	loss 1.8298 (3.0525)	grad_norm 2.9270 (2.9862)	
[2022-01-26 06:45:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][730/1251]	eta 0:19:13 lr 0.000038	time 2.8332 (2.2131)	loss 3.1434 (3.0508)	grad_norm 2.8419 (2.9861)	
[2022-01-26 06:46:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][740/1251]	eta 0:18:52 lr 0.000038	time 1.7560 (2.2153)	loss 3.3844 (3.0507)	grad_norm 2.8700 (2.9848)	
[2022-01-26 06:46:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][750/1251]	eta 0:18:30 lr 0.000038	time 2.7292 (2.2164)	loss 3.3949 (3.0517)	grad_norm 2.9397 (2.9847)	
[2022-01-26 06:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][760/1251]	eta 0:18:07 lr 0.000038	time 1.6080 (2.2139)	loss 3.0637 (3.0531)	grad_norm 3.0653 (2.9887)	
[2022-01-26 06:47:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][770/1251]	eta 0:17:44 lr 0.000038	time 2.4881 (2.2121)	loss 3.2141 (3.0509)	grad_norm 2.7964 (2.9882)	
[2022-01-26 06:47:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][780/1251]	eta 0:17:21 lr 0.000038	time 2.1887 (2.2110)	loss 2.8620 (3.0524)	grad_norm 3.3896 (2.9887)	
[2022-01-26 06:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][790/1251]	eta 0:16:58 lr 0.000038	time 2.2250 (2.2097)	loss 2.9129 (3.0528)	grad_norm 3.4648 (2.9898)	
[2022-01-26 06:48:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][800/1251]	eta 0:16:37 lr 0.000038	time 2.4734 (2.2107)	loss 3.2873 (3.0505)	grad_norm 2.5508 (2.9869)	
[2022-01-26 06:48:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][810/1251]	eta 0:16:14 lr 0.000038	time 2.2344 (2.2104)	loss 2.6635 (3.0507)	grad_norm 2.8020 (2.9892)	
[2022-01-26 06:49:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][820/1251]	eta 0:15:53 lr 0.000038	time 2.3327 (2.2116)	loss 3.1279 (3.0504)	grad_norm 2.7070 (2.9888)	
[2022-01-26 06:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][830/1251]	eta 0:15:30 lr 0.000038	time 1.9175 (2.2106)	loss 3.0586 (3.0492)	grad_norm 2.6235 (2.9901)	
[2022-01-26 06:49:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][840/1251]	eta 0:15:08 lr 0.000038	time 2.1410 (2.2100)	loss 3.2242 (3.0483)	grad_norm 2.4658 (2.9879)	
[2022-01-26 06:50:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][850/1251]	eta 0:14:45 lr 0.000038	time 2.2314 (2.2081)	loss 3.5335 (3.0487)	grad_norm 2.6536 (2.9883)	
[2022-01-26 06:50:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][860/1251]	eta 0:14:22 lr 0.000038	time 1.8925 (2.2066)	loss 3.2734 (3.0472)	grad_norm 3.6020 (2.9909)	
[2022-01-26 06:50:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][870/1251]	eta 0:14:00 lr 0.000038	time 1.9168 (2.2073)	loss 2.8766 (3.0456)	grad_norm 2.9136 (2.9898)	
[2022-01-26 06:51:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][880/1251]	eta 0:13:38 lr 0.000038	time 2.3351 (2.2063)	loss 2.7309 (3.0443)	grad_norm 3.7434 (2.9902)	
[2022-01-26 06:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][890/1251]	eta 0:13:16 lr 0.000038	time 2.2256 (2.2069)	loss 2.0438 (3.0436)	grad_norm 3.1769 (2.9896)	
[2022-01-26 06:52:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][900/1251]	eta 0:12:54 lr 0.000038	time 1.8911 (2.2058)	loss 3.1590 (3.0428)	grad_norm 3.3696 (2.9898)	
[2022-01-26 06:52:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][910/1251]	eta 0:12:31 lr 0.000038	time 2.1558 (2.2051)	loss 2.9867 (3.0435)	grad_norm 2.9120 (2.9908)	
[2022-01-26 06:52:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][920/1251]	eta 0:12:10 lr 0.000038	time 2.1944 (2.2063)	loss 2.1673 (3.0424)	grad_norm 2.9313 (2.9905)	
[2022-01-26 06:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][930/1251]	eta 0:11:48 lr 0.000038	time 1.9448 (2.2068)	loss 3.1950 (3.0431)	grad_norm 2.7368 (2.9888)	
[2022-01-26 06:53:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][940/1251]	eta 0:11:26 lr 0.000038	time 1.9613 (2.2085)	loss 2.9748 (3.0406)	grad_norm 3.2754 (2.9901)	
[2022-01-26 06:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][950/1251]	eta 0:11:04 lr 0.000038	time 1.9404 (2.2085)	loss 3.2212 (3.0413)	grad_norm 2.6345 (2.9895)	
[2022-01-26 06:54:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][960/1251]	eta 0:10:42 lr 0.000038	time 1.8957 (2.2064)	loss 2.2678 (3.0409)	grad_norm 2.5114 (2.9861)	
[2022-01-26 06:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][970/1251]	eta 0:10:19 lr 0.000038	time 1.9496 (2.2044)	loss 2.5150 (3.0426)	grad_norm 2.5796 (2.9845)	
[2022-01-26 06:54:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][980/1251]	eta 0:09:57 lr 0.000038	time 2.7946 (2.2036)	loss 3.7277 (3.0408)	grad_norm 2.5242 (2.9827)	
[2022-01-26 06:55:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][990/1251]	eta 0:09:34 lr 0.000038	time 1.8575 (2.2025)	loss 3.2462 (3.0401)	grad_norm 3.0414 (2.9817)	
[2022-01-26 06:55:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1000/1251]	eta 0:09:12 lr 0.000038	time 2.5402 (2.2029)	loss 3.4012 (3.0410)	grad_norm 2.7524 (2.9871)	
[2022-01-26 06:56:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1010/1251]	eta 0:08:50 lr 0.000038	time 2.4849 (2.2021)	loss 3.1750 (3.0423)	grad_norm 2.8275 (2.9852)	
[2022-01-26 06:56:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1020/1251]	eta 0:08:28 lr 0.000038	time 2.2654 (2.2025)	loss 3.1901 (3.0447)	grad_norm 2.6410 (2.9850)	
[2022-01-26 06:56:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1030/1251]	eta 0:08:06 lr 0.000038	time 2.2504 (2.2029)	loss 2.5534 (3.0463)	grad_norm 2.8529 (2.9868)	
[2022-01-26 06:57:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1040/1251]	eta 0:07:45 lr 0.000038	time 2.9484 (2.2046)	loss 3.2283 (3.0470)	grad_norm 2.8320 (2.9861)	
[2022-01-26 06:57:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1050/1251]	eta 0:07:23 lr 0.000038	time 2.4928 (2.2058)	loss 3.3546 (3.0481)	grad_norm 2.9337 (2.9859)	
[2022-01-26 06:57:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1060/1251]	eta 0:07:01 lr 0.000038	time 1.8200 (2.2054)	loss 2.6464 (3.0484)	grad_norm 2.8850 (2.9856)	
[2022-01-26 06:58:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1070/1251]	eta 0:06:38 lr 0.000038	time 2.1302 (2.2042)	loss 3.0477 (3.0488)	grad_norm 3.0344 (2.9841)	
[2022-01-26 06:58:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1080/1251]	eta 0:06:16 lr 0.000038	time 1.8847 (2.2030)	loss 3.0466 (3.0480)	grad_norm 3.5049 (2.9840)	
[2022-01-26 06:58:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1090/1251]	eta 0:05:54 lr 0.000038	time 2.1460 (2.2035)	loss 3.3117 (3.0481)	grad_norm 3.1593 (2.9836)	
[2022-01-26 06:59:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1100/1251]	eta 0:05:32 lr 0.000038	time 1.6082 (2.2027)	loss 2.7759 (3.0476)	grad_norm 2.9476 (2.9818)	
[2022-01-26 06:59:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1110/1251]	eta 0:05:10 lr 0.000038	time 1.8827 (2.2038)	loss 2.3958 (3.0471)	grad_norm 3.8326 (2.9811)	
[2022-01-26 07:00:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1120/1251]	eta 0:04:48 lr 0.000038	time 1.6106 (2.2033)	loss 2.5151 (3.0467)	grad_norm 3.2871 (2.9802)	
[2022-01-26 07:00:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1130/1251]	eta 0:04:26 lr 0.000038	time 2.4978 (2.2034)	loss 3.4160 (3.0454)	grad_norm 3.0657 (2.9789)	
[2022-01-26 07:00:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1140/1251]	eta 0:04:04 lr 0.000038	time 1.5137 (2.2034)	loss 2.2584 (3.0446)	grad_norm 2.8698 (2.9774)	
[2022-01-26 07:01:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1150/1251]	eta 0:03:42 lr 0.000038	time 1.8807 (2.2043)	loss 2.2720 (3.0447)	grad_norm 2.9642 (2.9764)	
[2022-01-26 07:01:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1160/1251]	eta 0:03:20 lr 0.000038	time 1.8147 (2.2026)	loss 3.1245 (3.0443)	grad_norm 2.2503 (2.9774)	
[2022-01-26 07:01:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1170/1251]	eta 0:02:58 lr 0.000038	time 2.1505 (2.2023)	loss 3.4434 (3.0452)	grad_norm 2.6395 (2.9761)	
[2022-01-26 07:02:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1180/1251]	eta 0:02:36 lr 0.000038	time 1.6276 (2.2012)	loss 3.1611 (3.0456)	grad_norm 2.8294 (2.9755)	
[2022-01-26 07:02:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1190/1251]	eta 0:02:14 lr 0.000038	time 2.1292 (2.2006)	loss 3.6030 (3.0462)	grad_norm 2.8740 (2.9760)	
[2022-01-26 07:02:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1200/1251]	eta 0:01:52 lr 0.000038	time 2.1740 (2.2008)	loss 3.0200 (3.0471)	grad_norm 3.1305 (2.9760)	
[2022-01-26 07:03:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1210/1251]	eta 0:01:30 lr 0.000038	time 1.8806 (2.1998)	loss 3.1199 (3.0451)	grad_norm 2.7742 (2.9750)	
[2022-01-26 07:03:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1220/1251]	eta 0:01:08 lr 0.000038	time 1.9722 (2.1987)	loss 2.7443 (3.0453)	grad_norm 3.3230 (2.9748)	
[2022-01-26 07:04:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1230/1251]	eta 0:00:46 lr 0.000038	time 2.1624 (2.1989)	loss 3.2040 (3.0460)	grad_norm 2.8073 (2.9741)	
[2022-01-26 07:04:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1240/1251]	eta 0:00:24 lr 0.000038	time 2.0395 (2.1987)	loss 2.8893 (3.0435)	grad_norm 3.0264 (2.9722)	
[2022-01-26 07:04:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [267/300][1250/1251]	eta 0:00:02 lr 0.000038	time 1.1581 (2.1937)	loss 2.8696 (3.0428)	grad_norm 2.5335 (2.9706)	
[2022-01-26 07:04:40 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 267 training takes 0:45:44
[2022-01-26 07:04:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.321 (18.321)	Loss 0.7838 (0.7838)	Acc@1 81.543 (81.543)	Acc@5 95.410 (95.410)	
[2022-01-26 07:05:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.215 (3.415)	Loss 0.8316 (0.7948)	Acc@1 80.566 (81.081)	Acc@5 95.020 (95.703)	
[2022-01-26 07:05:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.311 (2.740)	Loss 0.8136 (0.8087)	Acc@1 80.762 (80.897)	Acc@5 95.410 (95.471)	
[2022-01-26 07:05:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.928 (2.337)	Loss 0.8415 (0.8183)	Acc@1 80.273 (80.825)	Acc@5 94.824 (95.325)	
[2022-01-26 07:06:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.214 (2.215)	Loss 0.8498 (0.8206)	Acc@1 78.711 (80.886)	Acc@5 95.508 (95.284)	
[2022-01-26 07:06:18 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.906 Acc@5 95.302
[2022-01-26 07:06:18 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.9%
[2022-01-26 07:06:18 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.91%
[2022-01-26 07:06:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][0/1251]	eta 7:35:49 lr 0.000038	time 21.8619 (21.8619)	loss 3.3108 (3.3108)	grad_norm 2.6245 (2.6245)	
[2022-01-26 07:07:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][10/1251]	eta 1:24:22 lr 0.000038	time 1.5336 (4.0790)	loss 3.4109 (3.1472)	grad_norm 2.6521 (2.8644)	
[2022-01-26 07:07:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][20/1251]	eta 1:02:11 lr 0.000038	time 1.5473 (3.0313)	loss 3.0022 (3.1901)	grad_norm 3.0458 (2.9358)	
[2022-01-26 07:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][30/1251]	eta 0:56:27 lr 0.000037	time 1.7192 (2.7741)	loss 3.7898 (3.1271)	grad_norm 2.9764 (2.9920)	
[2022-01-26 07:08:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][40/1251]	eta 0:54:33 lr 0.000037	time 4.0779 (2.7035)	loss 2.0308 (3.1099)	grad_norm 2.7084 (3.0047)	
[2022-01-26 07:08:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][50/1251]	eta 0:51:55 lr 0.000037	time 2.2389 (2.5939)	loss 2.2443 (3.0729)	grad_norm 2.7124 (2.9979)	
[2022-01-26 07:08:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][60/1251]	eta 0:50:14 lr 0.000037	time 1.5713 (2.5311)	loss 3.2769 (3.0854)	grad_norm 2.7418 (2.9811)	
[2022-01-26 07:09:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][70/1251]	eta 0:49:14 lr 0.000037	time 2.4587 (2.5016)	loss 2.8882 (3.0698)	grad_norm 2.6481 (2.9760)	
[2022-01-26 07:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][80/1251]	eta 0:48:34 lr 0.000037	time 3.7567 (2.4886)	loss 2.1299 (3.0684)	grad_norm 3.1199 (2.9685)	
[2022-01-26 07:10:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][90/1251]	eta 0:47:26 lr 0.000037	time 1.6225 (2.4519)	loss 2.9584 (3.0701)	grad_norm 2.9615 (2.9616)	
[2022-01-26 07:10:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][100/1251]	eta 0:46:22 lr 0.000037	time 1.6798 (2.4176)	loss 2.5329 (3.0180)	grad_norm 2.9043 (2.9761)	
[2022-01-26 07:10:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][110/1251]	eta 0:45:37 lr 0.000037	time 2.0034 (2.3994)	loss 3.2900 (3.0378)	grad_norm 2.6275 (2.9838)	
[2022-01-26 07:11:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][120/1251]	eta 0:44:56 lr 0.000037	time 3.6673 (2.3844)	loss 3.0167 (3.0323)	grad_norm 4.1268 (2.9842)	
[2022-01-26 07:11:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][130/1251]	eta 0:44:09 lr 0.000037	time 1.8188 (2.3636)	loss 3.3941 (3.0406)	grad_norm 4.3678 (2.9929)	
[2022-01-26 07:11:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][140/1251]	eta 0:43:21 lr 0.000037	time 1.8700 (2.3412)	loss 3.4202 (3.0344)	grad_norm 2.9016 (2.9804)	
[2022-01-26 07:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][150/1251]	eta 0:42:42 lr 0.000037	time 2.0732 (2.3272)	loss 2.6856 (3.0282)	grad_norm 2.9720 (2.9821)	
[2022-01-26 07:12:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][160/1251]	eta 0:42:18 lr 0.000037	time 3.5942 (2.3270)	loss 3.0067 (3.0400)	grad_norm 2.7571 (2.9721)	
[2022-01-26 07:12:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][170/1251]	eta 0:41:44 lr 0.000037	time 1.8953 (2.3171)	loss 2.7513 (3.0323)	grad_norm 3.2961 (2.9783)	
[2022-01-26 07:13:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][180/1251]	eta 0:41:13 lr 0.000037	time 2.1833 (2.3099)	loss 3.1074 (3.0226)	grad_norm 2.8906 (2.9746)	
[2022-01-26 07:13:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][190/1251]	eta 0:40:46 lr 0.000037	time 2.1433 (2.3058)	loss 3.1972 (3.0271)	grad_norm 2.8129 (2.9599)	
[2022-01-26 07:14:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][200/1251]	eta 0:40:19 lr 0.000037	time 3.5865 (2.3018)	loss 2.8118 (3.0158)	grad_norm 3.3547 (2.9612)	
[2022-01-26 07:14:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][210/1251]	eta 0:39:48 lr 0.000037	time 2.2164 (2.2942)	loss 3.3797 (3.0175)	grad_norm 2.8335 (2.9636)	
[2022-01-26 07:14:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][220/1251]	eta 0:39:17 lr 0.000037	time 1.8600 (2.2861)	loss 3.4043 (3.0217)	grad_norm 2.4594 (2.9622)	
[2022-01-26 07:15:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][230/1251]	eta 0:38:46 lr 0.000037	time 1.8077 (2.2783)	loss 1.9506 (3.0211)	grad_norm 3.9823 (2.9650)	
[2022-01-26 07:15:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][240/1251]	eta 0:38:16 lr 0.000037	time 3.0452 (2.2720)	loss 2.9027 (3.0267)	grad_norm 3.0113 (2.9578)	
[2022-01-26 07:15:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][250/1251]	eta 0:37:41 lr 0.000037	time 1.9047 (2.2592)	loss 3.0505 (3.0210)	grad_norm 3.0231 (2.9548)	
[2022-01-26 07:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][260/1251]	eta 0:37:19 lr 0.000037	time 2.7932 (2.2594)	loss 3.3463 (3.0243)	grad_norm 3.0802 (2.9493)	
[2022-01-26 07:16:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][270/1251]	eta 0:36:54 lr 0.000037	time 2.3668 (2.2575)	loss 3.2484 (3.0244)	grad_norm 2.9966 (2.9468)	
[2022-01-26 07:16:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][280/1251]	eta 0:36:35 lr 0.000037	time 2.7673 (2.2610)	loss 3.3006 (3.0260)	grad_norm 2.3842 (2.9434)	
[2022-01-26 07:17:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][290/1251]	eta 0:36:14 lr 0.000037	time 1.5844 (2.2630)	loss 3.1274 (3.0197)	grad_norm 2.9551 (2.9438)	
[2022-01-26 07:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][300/1251]	eta 0:35:53 lr 0.000037	time 2.7163 (2.2641)	loss 2.3133 (3.0241)	grad_norm 2.7709 (2.9420)	
[2022-01-26 07:18:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][310/1251]	eta 0:35:28 lr 0.000037	time 3.0889 (2.2617)	loss 2.8554 (3.0143)	grad_norm 2.9874 (2.9404)	
[2022-01-26 07:18:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][320/1251]	eta 0:34:57 lr 0.000037	time 1.8430 (2.2524)	loss 2.2267 (3.0171)	grad_norm 3.0432 (2.9407)	
[2022-01-26 07:18:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][330/1251]	eta 0:34:29 lr 0.000037	time 2.3348 (2.2472)	loss 3.4329 (3.0236)	grad_norm 2.8246 (2.9419)	
[2022-01-26 07:19:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][340/1251]	eta 0:34:03 lr 0.000037	time 2.0731 (2.2430)	loss 2.7180 (3.0299)	grad_norm 2.8412 (2.9425)	
[2022-01-26 07:19:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][350/1251]	eta 0:33:40 lr 0.000037	time 2.2921 (2.2423)	loss 2.7764 (3.0309)	grad_norm 3.1948 (2.9430)	
[2022-01-26 07:19:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][360/1251]	eta 0:33:17 lr 0.000037	time 2.5224 (2.2423)	loss 2.8038 (3.0231)	grad_norm 2.9799 (2.9368)	
[2022-01-26 07:20:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][370/1251]	eta 0:32:54 lr 0.000037	time 1.5639 (2.2413)	loss 3.0853 (3.0287)	grad_norm 3.6904 (2.9469)	
[2022-01-26 07:20:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][380/1251]	eta 0:32:30 lr 0.000037	time 1.9508 (2.2396)	loss 3.1363 (3.0302)	grad_norm 2.5850 (2.9491)	
[2022-01-26 07:20:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][390/1251]	eta 0:32:08 lr 0.000037	time 1.8036 (2.2396)	loss 2.8393 (3.0347)	grad_norm 3.8138 (2.9533)	
[2022-01-26 07:21:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][400/1251]	eta 0:31:42 lr 0.000037	time 2.1605 (2.2357)	loss 3.8525 (3.0402)	grad_norm 2.9006 (2.9527)	
[2022-01-26 07:21:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][410/1251]	eta 0:31:19 lr 0.000037	time 2.3344 (2.2347)	loss 3.5827 (3.0378)	grad_norm 3.1125 (2.9531)	
[2022-01-26 07:21:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][420/1251]	eta 0:30:54 lr 0.000037	time 1.7927 (2.2315)	loss 3.4020 (3.0382)	grad_norm 2.3997 (2.9564)	
[2022-01-26 07:22:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][430/1251]	eta 0:30:31 lr 0.000037	time 2.0030 (2.2307)	loss 3.2187 (3.0427)	grad_norm 3.2895 (2.9566)	
[2022-01-26 07:22:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][440/1251]	eta 0:30:08 lr 0.000037	time 1.8371 (2.2301)	loss 3.2945 (3.0402)	grad_norm 3.1811 (2.9564)	
[2022-01-26 07:23:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][450/1251]	eta 0:29:46 lr 0.000037	time 1.8473 (2.2300)	loss 3.4240 (3.0320)	grad_norm 2.5053 (2.9549)	
[2022-01-26 07:23:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][460/1251]	eta 0:29:21 lr 0.000037	time 1.6230 (2.2273)	loss 3.2171 (3.0347)	grad_norm 2.9824 (2.9549)	
[2022-01-26 07:23:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][470/1251]	eta 0:29:01 lr 0.000037	time 2.0997 (2.2295)	loss 2.0625 (3.0303)	grad_norm 3.1762 (2.9511)	
[2022-01-26 07:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][480/1251]	eta 0:28:37 lr 0.000037	time 2.0597 (2.2282)	loss 3.2126 (3.0254)	grad_norm 3.4759 (2.9517)	
[2022-01-26 07:24:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][490/1251]	eta 0:28:17 lr 0.000037	time 2.4879 (2.2309)	loss 2.8115 (3.0257)	grad_norm 2.9082 (2.9495)	
[2022-01-26 07:24:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][500/1251]	eta 0:27:52 lr 0.000037	time 1.9154 (2.2270)	loss 2.9462 (3.0271)	grad_norm 2.9915 (2.9500)	
[2022-01-26 07:25:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][510/1251]	eta 0:27:29 lr 0.000037	time 2.3607 (2.2261)	loss 3.3632 (3.0278)	grad_norm 2.8202 (2.9493)	
[2022-01-26 07:25:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][520/1251]	eta 0:27:04 lr 0.000037	time 2.0953 (2.2223)	loss 2.8762 (3.0286)	grad_norm 3.1253 (2.9531)	
[2022-01-26 07:25:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][530/1251]	eta 0:26:40 lr 0.000037	time 2.2134 (2.2195)	loss 3.3530 (3.0246)	grad_norm 2.7694 (2.9542)	
[2022-01-26 07:26:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][540/1251]	eta 0:26:18 lr 0.000037	time 2.1839 (2.2202)	loss 3.0728 (3.0278)	grad_norm 2.5889 (2.9536)	
[2022-01-26 07:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][550/1251]	eta 0:25:59 lr 0.000037	time 2.7231 (2.2252)	loss 2.6505 (3.0276)	grad_norm 2.6611 (2.9530)	
[2022-01-26 07:27:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][560/1251]	eta 0:25:38 lr 0.000037	time 2.1495 (2.2269)	loss 3.3467 (3.0267)	grad_norm 2.5670 (2.9559)	
[2022-01-26 07:27:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][570/1251]	eta 0:25:15 lr 0.000037	time 1.8041 (2.2259)	loss 3.8125 (3.0269)	grad_norm 2.9956 (2.9565)	
[2022-01-26 07:27:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][580/1251]	eta 0:24:51 lr 0.000037	time 1.7190 (2.2232)	loss 1.9983 (3.0260)	grad_norm 2.8693 (2.9561)	
[2022-01-26 07:28:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][590/1251]	eta 0:24:26 lr 0.000037	time 1.6321 (2.2185)	loss 3.2530 (3.0249)	grad_norm 3.2706 (2.9575)	
[2022-01-26 07:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][600/1251]	eta 0:24:01 lr 0.000037	time 1.8731 (2.2144)	loss 3.5992 (3.0224)	grad_norm 2.6246 (2.9553)	
[2022-01-26 07:28:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][610/1251]	eta 0:23:39 lr 0.000037	time 2.5443 (2.2138)	loss 3.7393 (3.0250)	grad_norm 2.6223 (2.9504)	
[2022-01-26 07:29:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][620/1251]	eta 0:23:18 lr 0.000037	time 2.1861 (2.2158)	loss 2.5134 (3.0288)	grad_norm 2.8742 (2.9484)	
[2022-01-26 07:29:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][630/1251]	eta 0:22:57 lr 0.000037	time 2.1233 (2.2178)	loss 3.2092 (3.0318)	grad_norm 3.3832 (2.9489)	
[2022-01-26 07:30:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][640/1251]	eta 0:22:35 lr 0.000037	time 2.1389 (2.2181)	loss 3.4194 (3.0312)	grad_norm 2.5854 (2.9452)	
[2022-01-26 07:30:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][650/1251]	eta 0:22:13 lr 0.000037	time 2.4464 (2.2190)	loss 3.4929 (3.0349)	grad_norm 2.8230 (2.9434)	
[2022-01-26 07:30:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][660/1251]	eta 0:21:50 lr 0.000037	time 1.8037 (2.2178)	loss 3.5141 (3.0347)	grad_norm 2.8473 (2.9461)	
[2022-01-26 07:31:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][670/1251]	eta 0:21:28 lr 0.000037	time 2.5255 (2.2183)	loss 2.7835 (3.0325)	grad_norm 3.0079 (2.9454)	
[2022-01-26 07:31:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][680/1251]	eta 0:21:05 lr 0.000037	time 1.5923 (2.2166)	loss 3.3150 (3.0291)	grad_norm 2.6684 (2.9476)	
[2022-01-26 07:31:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][690/1251]	eta 0:20:42 lr 0.000037	time 1.8667 (2.2146)	loss 2.8764 (3.0297)	grad_norm 3.3182 (2.9537)	
[2022-01-26 07:32:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][700/1251]	eta 0:20:19 lr 0.000037	time 2.2066 (2.2126)	loss 3.3015 (3.0307)	grad_norm 3.0495 (2.9573)	
[2022-01-26 07:32:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][710/1251]	eta 0:19:58 lr 0.000037	time 1.9418 (2.2146)	loss 3.3978 (3.0314)	grad_norm 2.7467 (2.9604)	
[2022-01-26 07:32:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][720/1251]	eta 0:19:34 lr 0.000037	time 1.8816 (2.2128)	loss 3.6558 (3.0335)	grad_norm 2.7606 (2.9598)	
[2022-01-26 07:33:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][730/1251]	eta 0:19:12 lr 0.000037	time 1.9745 (2.2125)	loss 3.2626 (3.0370)	grad_norm 3.0289 (2.9611)	
[2022-01-26 07:33:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][740/1251]	eta 0:18:50 lr 0.000037	time 1.8677 (2.2121)	loss 2.9831 (3.0370)	grad_norm 2.7659 (2.9591)	
[2022-01-26 07:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][750/1251]	eta 0:18:28 lr 0.000037	time 2.2231 (2.2118)	loss 3.5642 (3.0372)	grad_norm 3.1790 (2.9597)	
[2022-01-26 07:34:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][760/1251]	eta 0:18:06 lr 0.000037	time 1.9555 (2.2120)	loss 3.7645 (3.0360)	grad_norm 2.5608 (2.9598)	
[2022-01-26 07:34:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][770/1251]	eta 0:17:43 lr 0.000036	time 2.4403 (2.2115)	loss 2.1048 (3.0341)	grad_norm 2.9791 (2.9594)	
[2022-01-26 07:35:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][780/1251]	eta 0:17:21 lr 0.000036	time 2.4721 (2.2107)	loss 2.8937 (3.0351)	grad_norm 2.8107 (2.9581)	
[2022-01-26 07:35:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][790/1251]	eta 0:16:59 lr 0.000036	time 1.8199 (2.2114)	loss 3.0534 (3.0320)	grad_norm 2.9318 (2.9561)	
[2022-01-26 07:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][800/1251]	eta 0:16:36 lr 0.000036	time 2.1224 (2.2100)	loss 3.4243 (3.0346)	grad_norm 2.7867 (2.9556)	
[2022-01-26 07:36:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][810/1251]	eta 0:16:14 lr 0.000036	time 2.4701 (2.2105)	loss 3.4615 (3.0353)	grad_norm 2.6924 (2.9548)	
[2022-01-26 07:36:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][820/1251]	eta 0:15:52 lr 0.000036	time 2.2611 (2.2092)	loss 3.0521 (3.0348)	grad_norm 2.4472 (2.9536)	
[2022-01-26 07:36:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][830/1251]	eta 0:15:29 lr 0.000036	time 1.7541 (2.2074)	loss 3.3403 (3.0341)	grad_norm 2.8679 (2.9555)	
[2022-01-26 07:37:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][840/1251]	eta 0:15:08 lr 0.000036	time 2.0339 (2.2095)	loss 2.2770 (3.0301)	grad_norm 2.6558 (2.9542)	
[2022-01-26 07:37:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][850/1251]	eta 0:14:47 lr 0.000036	time 2.2658 (2.2137)	loss 3.3428 (3.0298)	grad_norm 3.0007 (2.9563)	
[2022-01-26 07:38:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][860/1251]	eta 0:14:25 lr 0.000036	time 2.2184 (2.2125)	loss 3.2855 (3.0281)	grad_norm 2.4269 (2.9570)	
[2022-01-26 07:38:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][870/1251]	eta 0:14:02 lr 0.000036	time 2.4619 (2.2110)	loss 2.2728 (3.0264)	grad_norm 2.5252 (2.9540)	
[2022-01-26 07:38:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][880/1251]	eta 0:13:39 lr 0.000036	time 1.5969 (2.2085)	loss 3.3615 (3.0280)	grad_norm 2.9012 (2.9543)	
[2022-01-26 07:39:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][890/1251]	eta 0:13:16 lr 0.000036	time 1.5545 (2.2056)	loss 2.8622 (3.0286)	grad_norm 2.9967 (2.9567)	
[2022-01-26 07:39:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][900/1251]	eta 0:12:54 lr 0.000036	time 2.8596 (2.2052)	loss 3.1626 (3.0301)	grad_norm 2.4629 (2.9568)	
[2022-01-26 07:39:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][910/1251]	eta 0:12:32 lr 0.000036	time 2.6532 (2.2057)	loss 2.6826 (3.0294)	grad_norm 2.6455 (2.9566)	
[2022-01-26 07:40:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][920/1251]	eta 0:12:10 lr 0.000036	time 2.1952 (2.2061)	loss 3.5143 (3.0269)	grad_norm 2.8858 (2.9585)	
[2022-01-26 07:40:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][930/1251]	eta 0:11:48 lr 0.000036	time 2.6417 (2.2061)	loss 3.2720 (3.0255)	grad_norm 3.0904 (2.9578)	
[2022-01-26 07:40:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][940/1251]	eta 0:11:25 lr 0.000036	time 2.8300 (2.2052)	loss 3.4491 (3.0248)	grad_norm 3.6838 (2.9624)	
[2022-01-26 07:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][950/1251]	eta 0:11:04 lr 0.000036	time 2.5064 (2.2062)	loss 2.5183 (3.0261)	grad_norm 2.5057 (2.9622)	
[2022-01-26 07:41:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][960/1251]	eta 0:10:42 lr 0.000036	time 2.6120 (2.2068)	loss 3.2806 (3.0251)	grad_norm 2.7467 (2.9620)	
[2022-01-26 07:42:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][970/1251]	eta 0:10:20 lr 0.000036	time 2.2364 (2.2072)	loss 3.0918 (3.0236)	grad_norm 3.3516 (2.9615)	
[2022-01-26 07:42:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][980/1251]	eta 0:09:58 lr 0.000036	time 2.1908 (2.2082)	loss 3.0844 (3.0224)	grad_norm 3.1912 (2.9619)	
[2022-01-26 07:42:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][990/1251]	eta 0:09:36 lr 0.000036	time 2.8191 (2.2078)	loss 2.5253 (3.0219)	grad_norm 2.6889 (2.9617)	
[2022-01-26 07:43:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1000/1251]	eta 0:09:13 lr 0.000036	time 1.7316 (2.2064)	loss 2.3761 (3.0213)	grad_norm 3.1689 (2.9618)	
[2022-01-26 07:43:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1010/1251]	eta 0:08:51 lr 0.000036	time 2.7280 (2.2056)	loss 3.1762 (3.0189)	grad_norm 2.6704 (2.9604)	
[2022-01-26 07:43:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1020/1251]	eta 0:08:29 lr 0.000036	time 1.7766 (2.2047)	loss 2.8062 (3.0208)	grad_norm 2.6261 (2.9595)	
[2022-01-26 07:44:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1030/1251]	eta 0:08:07 lr 0.000036	time 2.8428 (2.2057)	loss 3.2600 (3.0215)	grad_norm 2.7400 (2.9585)	
[2022-01-26 07:44:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1040/1251]	eta 0:07:45 lr 0.000036	time 1.4656 (2.2044)	loss 2.6471 (3.0200)	grad_norm 3.1392 (2.9583)	
[2022-01-26 07:44:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1050/1251]	eta 0:07:22 lr 0.000036	time 2.2149 (2.2039)	loss 3.5239 (3.0215)	grad_norm 2.7429 (2.9593)	
[2022-01-26 07:45:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1060/1251]	eta 0:07:01 lr 0.000036	time 2.4523 (2.2046)	loss 3.7507 (3.0236)	grad_norm 3.0322 (2.9591)	
[2022-01-26 07:45:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1070/1251]	eta 0:06:39 lr 0.000036	time 2.0146 (2.2049)	loss 2.6828 (3.0238)	grad_norm 2.8461 (2.9605)	
[2022-01-26 07:46:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1080/1251]	eta 0:06:17 lr 0.000036	time 1.7786 (2.2048)	loss 3.3530 (3.0256)	grad_norm 4.3516 (2.9635)	
[2022-01-26 07:46:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1090/1251]	eta 0:05:54 lr 0.000036	time 2.0428 (2.2042)	loss 3.6980 (3.0255)	grad_norm 2.8824 (2.9644)	
[2022-01-26 07:46:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1100/1251]	eta 0:05:32 lr 0.000036	time 3.1334 (2.2044)	loss 3.6412 (3.0235)	grad_norm 3.2462 (2.9640)	
[2022-01-26 07:47:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1110/1251]	eta 0:05:10 lr 0.000036	time 3.1291 (2.2048)	loss 3.1962 (3.0238)	grad_norm 3.1500 (2.9636)	
[2022-01-26 07:47:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1120/1251]	eta 0:04:48 lr 0.000036	time 1.7342 (2.2038)	loss 3.1468 (3.0248)	grad_norm 3.0195 (2.9638)	
[2022-01-26 07:47:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1130/1251]	eta 0:04:26 lr 0.000036	time 1.9153 (2.2021)	loss 2.9874 (3.0259)	grad_norm 2.6747 (2.9634)	
[2022-01-26 07:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1140/1251]	eta 0:04:04 lr 0.000036	time 1.9716 (2.2005)	loss 3.4333 (3.0263)	grad_norm 3.0894 (2.9642)	
[2022-01-26 07:48:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1150/1251]	eta 0:03:42 lr 0.000036	time 2.8185 (2.2005)	loss 3.2823 (3.0255)	grad_norm 3.6496 (2.9649)	
[2022-01-26 07:48:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1160/1251]	eta 0:03:20 lr 0.000036	time 1.8255 (2.1993)	loss 2.7945 (3.0233)	grad_norm 2.5928 (2.9659)	
[2022-01-26 07:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1170/1251]	eta 0:02:58 lr 0.000036	time 2.0800 (2.1985)	loss 3.3343 (3.0229)	grad_norm 2.9244 (2.9646)	
[2022-01-26 07:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1180/1251]	eta 0:02:36 lr 0.000036	time 2.7766 (2.1983)	loss 2.7869 (3.0226)	grad_norm 3.1735 (2.9658)	
[2022-01-26 07:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1190/1251]	eta 0:02:14 lr 0.000036	time 2.6704 (2.1977)	loss 3.4904 (3.0229)	grad_norm 2.7660 (2.9647)	
[2022-01-26 07:50:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1200/1251]	eta 0:01:52 lr 0.000036	time 2.4550 (2.1999)	loss 3.2406 (3.0211)	grad_norm 2.6369 (2.9644)	
[2022-01-26 07:50:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1210/1251]	eta 0:01:30 lr 0.000036	time 2.1891 (2.1995)	loss 2.6560 (3.0214)	grad_norm 2.8438 (2.9650)	
[2022-01-26 07:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1220/1251]	eta 0:01:08 lr 0.000036	time 2.6697 (2.2000)	loss 3.3969 (3.0197)	grad_norm 2.8066 (2.9643)	
[2022-01-26 07:51:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1230/1251]	eta 0:00:46 lr 0.000036	time 2.5229 (2.1999)	loss 3.3659 (3.0198)	grad_norm 3.2405 (2.9670)	
[2022-01-26 07:51:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1240/1251]	eta 0:00:24 lr 0.000036	time 2.2493 (2.1988)	loss 3.3776 (3.0201)	grad_norm 2.7000 (2.9670)	
[2022-01-26 07:52:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [268/300][1250/1251]	eta 0:00:02 lr 0.000036	time 1.1824 (2.1930)	loss 2.9785 (3.0215)	grad_norm 3.1540 (2.9663)	
[2022-01-26 07:52:02 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 268 training takes 0:45:43
[2022-01-26 07:52:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.731 (18.731)	Loss 0.7943 (0.7943)	Acc@1 81.836 (81.836)	Acc@5 95.508 (95.508)	
[2022-01-26 07:52:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.926 (3.217)	Loss 0.8258 (0.8166)	Acc@1 80.566 (81.143)	Acc@5 95.117 (95.428)	
[2022-01-26 07:52:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.019 (2.478)	Loss 0.8422 (0.8234)	Acc@1 79.980 (80.850)	Acc@5 94.727 (95.350)	
[2022-01-26 07:53:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.604 (2.121)	Loss 0.8148 (0.8298)	Acc@1 80.957 (80.661)	Acc@5 95.117 (95.262)	
[2022-01-26 07:53:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.762 (2.089)	Loss 0.8162 (0.8218)	Acc@1 81.348 (80.788)	Acc@5 95.508 (95.353)	
[2022-01-26 07:53:34 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.826 Acc@5 95.378
[2022-01-26 07:53:34 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.8%
[2022-01-26 07:53:34 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.91%
[2022-01-26 07:53:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][0/1251]	eta 7:21:55 lr 0.000036	time 21.1953 (21.1953)	loss 3.4336 (3.4336)	grad_norm 3.0550 (3.0550)	
[2022-01-26 07:54:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][10/1251]	eta 1:21:47 lr 0.000036	time 2.2669 (3.9548)	loss 3.2940 (2.8159)	grad_norm 2.6865 (2.8766)	
[2022-01-26 07:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][20/1251]	eta 1:02:47 lr 0.000036	time 1.4248 (3.0609)	loss 3.3259 (3.0142)	grad_norm 2.5651 (2.8255)	
[2022-01-26 07:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][30/1251]	eta 0:56:53 lr 0.000036	time 2.1282 (2.7958)	loss 3.3533 (3.0604)	grad_norm 2.3638 (2.8854)	
[2022-01-26 07:55:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][40/1251]	eta 0:53:46 lr 0.000036	time 4.0798 (2.6643)	loss 3.0458 (3.0830)	grad_norm 2.6446 (2.9331)	
[2022-01-26 07:55:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][50/1251]	eta 0:51:43 lr 0.000036	time 1.8289 (2.5842)	loss 3.1059 (3.0746)	grad_norm 2.8596 (2.9238)	
[2022-01-26 07:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][60/1251]	eta 0:49:33 lr 0.000036	time 1.3657 (2.4963)	loss 2.3100 (3.0676)	grad_norm 2.9409 (2.8812)	
[2022-01-26 07:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][70/1251]	eta 0:48:00 lr 0.000036	time 1.7336 (2.4389)	loss 3.2223 (3.0322)	grad_norm 3.4480 (2.9055)	
[2022-01-26 07:56:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][80/1251]	eta 0:46:56 lr 0.000036	time 3.2050 (2.4054)	loss 3.5904 (3.0385)	grad_norm 3.4771 (2.9161)	
[2022-01-26 07:57:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][90/1251]	eta 0:46:17 lr 0.000036	time 1.5913 (2.3923)	loss 3.3777 (3.0129)	grad_norm 2.8169 (2.9428)	
[2022-01-26 07:57:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][100/1251]	eta 0:45:21 lr 0.000036	time 2.1496 (2.3647)	loss 3.3039 (3.0232)	grad_norm 3.3632 (2.9892)	
[2022-01-26 07:57:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][110/1251]	eta 0:44:40 lr 0.000036	time 1.4575 (2.3496)	loss 2.3548 (3.0190)	grad_norm 2.9197 (3.0029)	
[2022-01-26 07:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][120/1251]	eta 0:44:17 lr 0.000036	time 3.1437 (2.3496)	loss 3.3066 (3.0120)	grad_norm 3.6240 (3.0262)	
[2022-01-26 07:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][130/1251]	eta 0:43:52 lr 0.000036	time 1.6786 (2.3485)	loss 2.9585 (3.0192)	grad_norm 3.1803 (3.0228)	
[2022-01-26 07:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][140/1251]	eta 0:43:15 lr 0.000036	time 2.2726 (2.3366)	loss 3.0145 (3.0225)	grad_norm 2.6980 (3.0238)	
[2022-01-26 07:59:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][150/1251]	eta 0:42:49 lr 0.000036	time 1.5508 (2.3336)	loss 2.4323 (3.0305)	grad_norm 2.7995 (3.0260)	
[2022-01-26 07:59:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][160/1251]	eta 0:42:14 lr 0.000036	time 2.2717 (2.3227)	loss 2.3077 (3.0326)	grad_norm 2.6828 (3.0172)	
[2022-01-26 08:00:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][170/1251]	eta 0:41:30 lr 0.000036	time 1.9689 (2.3042)	loss 3.4886 (3.0247)	grad_norm 2.9859 (3.0150)	
[2022-01-26 08:00:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][180/1251]	eta 0:40:48 lr 0.000036	time 2.4675 (2.2866)	loss 3.2766 (3.0120)	grad_norm 2.8790 (3.0141)	
[2022-01-26 08:00:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][190/1251]	eta 0:40:21 lr 0.000036	time 1.9258 (2.2826)	loss 3.5897 (3.0150)	grad_norm 3.0828 (3.0109)	
[2022-01-26 08:01:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][200/1251]	eta 0:40:02 lr 0.000036	time 2.5574 (2.2859)	loss 2.8848 (3.0175)	grad_norm 2.7770 (3.0033)	
[2022-01-26 08:01:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][210/1251]	eta 0:39:42 lr 0.000036	time 2.7800 (2.2883)	loss 1.9888 (3.0156)	grad_norm 2.3302 (3.0004)	
[2022-01-26 08:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][220/1251]	eta 0:39:19 lr 0.000036	time 2.6655 (2.2886)	loss 2.9590 (3.0224)	grad_norm 3.0986 (3.0000)	
[2022-01-26 08:02:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][230/1251]	eta 0:38:47 lr 0.000036	time 1.6125 (2.2799)	loss 3.4201 (3.0187)	grad_norm 3.0241 (3.0015)	
[2022-01-26 08:02:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][240/1251]	eta 0:38:12 lr 0.000036	time 2.1264 (2.2672)	loss 3.4493 (3.0206)	grad_norm 2.5369 (2.9982)	
[2022-01-26 08:03:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][250/1251]	eta 0:37:40 lr 0.000036	time 1.5862 (2.2580)	loss 2.5450 (3.0199)	grad_norm 2.7583 (2.9966)	
[2022-01-26 08:03:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][260/1251]	eta 0:37:14 lr 0.000036	time 1.9497 (2.2545)	loss 3.2700 (3.0266)	grad_norm 3.0816 (3.0218)	
[2022-01-26 08:03:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][270/1251]	eta 0:36:46 lr 0.000035	time 1.8690 (2.2491)	loss 3.0403 (3.0282)	grad_norm 2.7913 (3.0170)	
[2022-01-26 08:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][280/1251]	eta 0:36:19 lr 0.000035	time 2.2491 (2.2445)	loss 2.2722 (3.0101)	grad_norm 2.8277 (3.0176)	
[2022-01-26 08:04:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][290/1251]	eta 0:35:58 lr 0.000035	time 1.7755 (2.2456)	loss 2.3558 (2.9964)	grad_norm 2.7425 (3.0129)	
[2022-01-26 08:04:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][300/1251]	eta 0:35:35 lr 0.000035	time 2.2212 (2.2460)	loss 3.2840 (2.9937)	grad_norm 2.5031 (3.0159)	
[2022-01-26 08:05:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][310/1251]	eta 0:35:08 lr 0.000035	time 2.0972 (2.2409)	loss 3.4595 (2.9929)	grad_norm 3.8161 (3.0176)	
[2022-01-26 08:05:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][320/1251]	eta 0:34:46 lr 0.000035	time 2.1953 (2.2409)	loss 3.5992 (3.0000)	grad_norm 2.4895 (3.0091)	
[2022-01-26 08:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][330/1251]	eta 0:34:25 lr 0.000035	time 2.1878 (2.2429)	loss 3.2102 (2.9945)	grad_norm 2.5236 (3.0058)	
[2022-01-26 08:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][340/1251]	eta 0:34:01 lr 0.000035	time 1.9375 (2.2413)	loss 3.5394 (2.9957)	grad_norm 2.8639 (3.0004)	
[2022-01-26 08:06:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][350/1251]	eta 0:33:35 lr 0.000035	time 2.2254 (2.2371)	loss 3.2720 (2.9853)	grad_norm 3.0804 (2.9978)	
[2022-01-26 08:06:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][360/1251]	eta 0:33:05 lr 0.000035	time 2.0017 (2.2284)	loss 2.8688 (2.9860)	grad_norm 2.4423 (2.9909)	
[2022-01-26 08:07:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][370/1251]	eta 0:32:40 lr 0.000035	time 2.1836 (2.2254)	loss 3.4994 (2.9919)	grad_norm 2.7349 (2.9900)	
[2022-01-26 08:07:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][380/1251]	eta 0:32:15 lr 0.000035	time 1.6164 (2.2219)	loss 2.9403 (2.9900)	grad_norm 2.8792 (2.9902)	
[2022-01-26 08:08:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][390/1251]	eta 0:31:52 lr 0.000035	time 2.6284 (2.2211)	loss 3.3470 (2.9877)	grad_norm 3.7102 (2.9995)	
[2022-01-26 08:08:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][400/1251]	eta 0:31:27 lr 0.000035	time 2.5891 (2.2184)	loss 2.0631 (2.9810)	grad_norm 2.3738 (2.9950)	
[2022-01-26 08:08:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][410/1251]	eta 0:31:06 lr 0.000035	time 2.7034 (2.2189)	loss 3.4699 (2.9812)	grad_norm 3.3731 (2.9931)	
[2022-01-26 08:09:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][420/1251]	eta 0:30:44 lr 0.000035	time 1.8990 (2.2202)	loss 2.6005 (2.9816)	grad_norm 2.9373 (2.9956)	
[2022-01-26 08:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][430/1251]	eta 0:30:25 lr 0.000035	time 2.2687 (2.2234)	loss 3.4662 (2.9874)	grad_norm 2.9120 (2.9933)	
[2022-01-26 08:09:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][440/1251]	eta 0:30:03 lr 0.000035	time 2.5879 (2.2239)	loss 2.7981 (2.9867)	grad_norm 2.6115 (2.9924)	
[2022-01-26 08:10:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][450/1251]	eta 0:29:42 lr 0.000035	time 2.3411 (2.2257)	loss 2.2859 (2.9898)	grad_norm 2.7371 (2.9940)	
[2022-01-26 08:10:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][460/1251]	eta 0:29:18 lr 0.000035	time 1.5926 (2.2231)	loss 3.4733 (2.9934)	grad_norm 4.0872 (3.0021)	
[2022-01-26 08:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][470/1251]	eta 0:28:55 lr 0.000035	time 1.8174 (2.2224)	loss 2.3803 (2.9927)	grad_norm 2.5691 (2.9996)	
[2022-01-26 08:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][480/1251]	eta 0:28:32 lr 0.000035	time 2.5201 (2.2209)	loss 3.6471 (2.9980)	grad_norm 3.1904 (2.9956)	
[2022-01-26 08:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][490/1251]	eta 0:28:10 lr 0.000035	time 2.5198 (2.2209)	loss 3.4625 (2.9978)	grad_norm 3.0658 (2.9975)	
[2022-01-26 08:12:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][500/1251]	eta 0:27:45 lr 0.000035	time 2.4981 (2.2184)	loss 2.7052 (2.9948)	grad_norm 2.4293 (2.9960)	
[2022-01-26 08:12:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][510/1251]	eta 0:27:23 lr 0.000035	time 2.1817 (2.2181)	loss 3.4939 (2.9983)	grad_norm 2.7969 (2.9910)	
[2022-01-26 08:12:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][520/1251]	eta 0:27:01 lr 0.000035	time 2.5124 (2.2181)	loss 3.0108 (2.9972)	grad_norm 2.4077 (2.9900)	
[2022-01-26 08:13:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][530/1251]	eta 0:26:38 lr 0.000035	time 2.4246 (2.2175)	loss 2.4159 (2.9968)	grad_norm 2.9468 (2.9876)	
[2022-01-26 08:13:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][540/1251]	eta 0:26:14 lr 0.000035	time 2.2902 (2.2152)	loss 2.7418 (2.9943)	grad_norm 2.7232 (2.9884)	
[2022-01-26 08:13:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][550/1251]	eta 0:25:51 lr 0.000035	time 1.6216 (2.2129)	loss 3.8399 (2.9936)	grad_norm 3.1634 (2.9873)	
[2022-01-26 08:14:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][560/1251]	eta 0:25:28 lr 0.000035	time 1.9231 (2.2114)	loss 3.4879 (2.9981)	grad_norm 3.4819 (2.9884)	
[2022-01-26 08:14:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][570/1251]	eta 0:25:05 lr 0.000035	time 1.9344 (2.2113)	loss 3.4086 (3.0056)	grad_norm 3.3399 (2.9875)	
[2022-01-26 08:15:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][580/1251]	eta 0:24:44 lr 0.000035	time 2.6860 (2.2130)	loss 2.3173 (3.0017)	grad_norm 2.5929 (2.9846)	
[2022-01-26 08:15:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][590/1251]	eta 0:24:21 lr 0.000035	time 1.8965 (2.2110)	loss 2.8935 (3.0022)	grad_norm 2.8153 (2.9855)	
[2022-01-26 08:15:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][600/1251]	eta 0:23:59 lr 0.000035	time 2.3616 (2.2107)	loss 3.2661 (3.0040)	grad_norm 2.5412 (2.9873)	
[2022-01-26 08:16:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][610/1251]	eta 0:23:36 lr 0.000035	time 1.9294 (2.2094)	loss 2.5673 (3.0008)	grad_norm 3.1657 (2.9889)	
[2022-01-26 08:16:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][620/1251]	eta 0:23:15 lr 0.000035	time 3.4492 (2.2120)	loss 3.3001 (3.0052)	grad_norm 2.7835 (2.9866)	
[2022-01-26 08:16:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][630/1251]	eta 0:22:52 lr 0.000035	time 1.5674 (2.2095)	loss 2.2181 (3.0060)	grad_norm 2.8887 (2.9873)	
[2022-01-26 08:17:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][640/1251]	eta 0:22:29 lr 0.000035	time 1.5668 (2.2079)	loss 3.6686 (3.0077)	grad_norm 2.8591 (2.9865)	
[2022-01-26 08:17:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][650/1251]	eta 0:22:07 lr 0.000035	time 2.2309 (2.2093)	loss 2.7223 (3.0111)	grad_norm 2.9727 (2.9871)	
[2022-01-26 08:17:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][660/1251]	eta 0:21:46 lr 0.000035	time 2.0855 (2.2108)	loss 2.8824 (3.0107)	grad_norm 2.7123 (2.9893)	
[2022-01-26 08:18:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][670/1251]	eta 0:21:23 lr 0.000035	time 1.6461 (2.2096)	loss 2.6011 (3.0122)	grad_norm 2.8694 (2.9885)	
[2022-01-26 08:18:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][680/1251]	eta 0:21:01 lr 0.000035	time 1.6312 (2.2088)	loss 2.7628 (3.0137)	grad_norm 3.0257 (2.9886)	
[2022-01-26 08:19:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][690/1251]	eta 0:20:39 lr 0.000035	time 1.9328 (2.2103)	loss 3.6635 (3.0156)	grad_norm 3.5552 (2.9927)	
[2022-01-26 08:19:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][700/1251]	eta 0:20:17 lr 0.000035	time 1.8870 (2.2096)	loss 2.9822 (3.0172)	grad_norm 2.7538 (2.9937)	
[2022-01-26 08:19:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][710/1251]	eta 0:19:54 lr 0.000035	time 1.6361 (2.2081)	loss 3.7125 (3.0199)	grad_norm 2.4577 (2.9898)	
[2022-01-26 08:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][720/1251]	eta 0:19:32 lr 0.000035	time 1.9020 (2.2085)	loss 3.2300 (3.0229)	grad_norm 3.3633 (2.9897)	
[2022-01-26 08:20:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][730/1251]	eta 0:19:10 lr 0.000035	time 1.8754 (2.2088)	loss 3.0635 (3.0231)	grad_norm 2.7330 (2.9891)	
[2022-01-26 08:20:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][740/1251]	eta 0:18:48 lr 0.000035	time 2.3385 (2.2093)	loss 3.1882 (3.0243)	grad_norm 2.7615 (2.9887)	
[2022-01-26 08:21:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][750/1251]	eta 0:18:25 lr 0.000035	time 1.6830 (2.2073)	loss 2.6067 (3.0254)	grad_norm 2.7190 (2.9901)	
[2022-01-26 08:21:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][760/1251]	eta 0:18:03 lr 0.000035	time 1.5955 (2.2067)	loss 2.7587 (3.0241)	grad_norm 3.1429 (2.9895)	
[2022-01-26 08:21:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][770/1251]	eta 0:17:41 lr 0.000035	time 1.8869 (2.2074)	loss 2.5680 (3.0237)	grad_norm 3.0588 (2.9883)	
[2022-01-26 08:22:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][780/1251]	eta 0:17:18 lr 0.000035	time 2.1904 (2.2055)	loss 2.6591 (3.0225)	grad_norm 2.7727 (2.9904)	
[2022-01-26 08:22:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][790/1251]	eta 0:16:56 lr 0.000035	time 2.0769 (2.2053)	loss 3.0963 (3.0233)	grad_norm 2.7482 (2.9900)	
[2022-01-26 08:23:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][800/1251]	eta 0:16:34 lr 0.000035	time 2.4480 (2.2049)	loss 2.3971 (3.0199)	grad_norm 2.9692 (2.9881)	
[2022-01-26 08:23:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][810/1251]	eta 0:16:12 lr 0.000035	time 1.6760 (2.2050)	loss 3.4502 (3.0238)	grad_norm 2.7029 (2.9930)	
[2022-01-26 08:23:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][820/1251]	eta 0:15:49 lr 0.000035	time 1.9970 (2.2040)	loss 3.7747 (3.0282)	grad_norm 4.4796 (2.9953)	
[2022-01-26 08:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][830/1251]	eta 0:15:27 lr 0.000035	time 1.9084 (2.2036)	loss 2.7424 (3.0291)	grad_norm 2.7682 (2.9936)	
[2022-01-26 08:24:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][840/1251]	eta 0:15:05 lr 0.000035	time 3.1050 (2.2040)	loss 3.3074 (3.0270)	grad_norm 2.4010 (2.9930)	
[2022-01-26 08:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][850/1251]	eta 0:14:45 lr 0.000035	time 2.3258 (2.2074)	loss 2.9606 (3.0237)	grad_norm 2.5715 (2.9936)	
[2022-01-26 08:25:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][860/1251]	eta 0:14:23 lr 0.000035	time 2.0262 (2.2076)	loss 3.2125 (3.0246)	grad_norm 2.6713 (2.9925)	
[2022-01-26 08:25:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][870/1251]	eta 0:14:00 lr 0.000035	time 1.8229 (2.2057)	loss 3.8189 (3.0261)	grad_norm 3.1197 (2.9911)	
[2022-01-26 08:25:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][880/1251]	eta 0:13:37 lr 0.000035	time 1.8042 (2.2031)	loss 2.7418 (3.0258)	grad_norm 3.1585 (2.9927)	
[2022-01-26 08:26:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][890/1251]	eta 0:13:14 lr 0.000035	time 1.8210 (2.2012)	loss 2.8910 (3.0243)	grad_norm 3.3171 (2.9926)	
[2022-01-26 08:26:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][900/1251]	eta 0:12:52 lr 0.000035	time 2.5812 (2.2010)	loss 2.1483 (3.0244)	grad_norm 2.9750 (2.9919)	
[2022-01-26 08:27:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][910/1251]	eta 0:12:30 lr 0.000035	time 1.7395 (2.2012)	loss 3.3313 (3.0248)	grad_norm 3.4228 (2.9906)	
[2022-01-26 08:27:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][920/1251]	eta 0:12:08 lr 0.000035	time 1.7730 (2.2016)	loss 3.1565 (3.0246)	grad_norm 2.7926 (2.9900)	
[2022-01-26 08:27:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][930/1251]	eta 0:11:46 lr 0.000035	time 2.4910 (2.2013)	loss 3.3217 (3.0266)	grad_norm 2.7015 (2.9884)	
[2022-01-26 08:28:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][940/1251]	eta 0:11:24 lr 0.000035	time 3.0959 (2.2015)	loss 3.3379 (3.0275)	grad_norm 2.8547 (2.9881)	
[2022-01-26 08:28:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][950/1251]	eta 0:11:03 lr 0.000035	time 2.2498 (2.2032)	loss 3.0999 (3.0263)	grad_norm 2.7703 (2.9884)	
[2022-01-26 08:28:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][960/1251]	eta 0:10:41 lr 0.000035	time 1.6199 (2.2031)	loss 3.1999 (3.0277)	grad_norm 3.0287 (2.9907)	
[2022-01-26 08:29:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][970/1251]	eta 0:10:19 lr 0.000035	time 1.6057 (2.2031)	loss 3.3371 (3.0250)	grad_norm 2.7482 (2.9908)	
[2022-01-26 08:29:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][980/1251]	eta 0:09:57 lr 0.000035	time 3.4236 (2.2031)	loss 2.2806 (3.0244)	grad_norm 2.6663 (2.9915)	
[2022-01-26 08:29:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][990/1251]	eta 0:09:34 lr 0.000035	time 1.7230 (2.2015)	loss 3.3366 (3.0229)	grad_norm 6.3214 (2.9947)	
[2022-01-26 08:30:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1000/1251]	eta 0:09:12 lr 0.000035	time 1.9223 (2.2005)	loss 2.5707 (3.0206)	grad_norm 2.7330 (2.9950)	
[2022-01-26 08:30:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1010/1251]	eta 0:08:50 lr 0.000035	time 2.1896 (2.2002)	loss 2.8868 (3.0202)	grad_norm 2.6433 (2.9948)	
[2022-01-26 08:31:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1020/1251]	eta 0:08:28 lr 0.000035	time 2.3435 (2.1999)	loss 2.9060 (3.0200)	grad_norm 2.7671 (2.9944)	
[2022-01-26 08:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1030/1251]	eta 0:08:05 lr 0.000035	time 1.8476 (2.1981)	loss 2.7210 (3.0211)	grad_norm 2.8177 (2.9947)	
[2022-01-26 08:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1040/1251]	eta 0:07:43 lr 0.000034	time 2.5581 (2.1987)	loss 3.4821 (3.0220)	grad_norm 3.6928 (2.9994)	
[2022-01-26 08:32:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1050/1251]	eta 0:07:22 lr 0.000034	time 2.6872 (2.2006)	loss 2.3924 (3.0203)	grad_norm 3.1685 (2.9984)	
[2022-01-26 08:32:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1060/1251]	eta 0:07:00 lr 0.000034	time 2.3712 (2.2005)	loss 3.2306 (3.0206)	grad_norm 2.5444 (2.9984)	
[2022-01-26 08:32:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1070/1251]	eta 0:06:38 lr 0.000034	time 1.5626 (2.1999)	loss 2.1693 (3.0205)	grad_norm 2.5924 (2.9973)	
[2022-01-26 08:33:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1080/1251]	eta 0:06:16 lr 0.000034	time 2.3977 (2.1999)	loss 3.5021 (3.0214)	grad_norm 3.3237 (2.9986)	
[2022-01-26 08:33:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1090/1251]	eta 0:05:54 lr 0.000034	time 1.9193 (2.2003)	loss 2.0560 (3.0233)	grad_norm 3.3253 (2.9980)	
[2022-01-26 08:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1100/1251]	eta 0:05:32 lr 0.000034	time 2.1350 (2.2003)	loss 2.5882 (3.0242)	grad_norm 2.5771 (2.9977)	
[2022-01-26 08:34:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1110/1251]	eta 0:05:10 lr 0.000034	time 2.1471 (2.2002)	loss 3.6214 (3.0231)	grad_norm 3.1589 (2.9968)	
[2022-01-26 08:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1120/1251]	eta 0:04:48 lr 0.000034	time 1.6280 (2.1989)	loss 2.9517 (3.0207)	grad_norm 3.3781 (3.0002)	
[2022-01-26 08:35:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1130/1251]	eta 0:04:26 lr 0.000034	time 2.7939 (2.2004)	loss 3.1051 (3.0204)	grad_norm 4.0285 (3.0032)	
[2022-01-26 08:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1140/1251]	eta 0:04:04 lr 0.000034	time 1.9781 (2.2009)	loss 3.3781 (3.0214)	grad_norm 3.3545 (3.0029)	
[2022-01-26 08:35:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1150/1251]	eta 0:03:42 lr 0.000034	time 2.2244 (2.2006)	loss 3.2302 (3.0218)	grad_norm 3.1332 (3.0024)	
[2022-01-26 08:36:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1160/1251]	eta 0:03:20 lr 0.000034	time 1.9702 (2.1991)	loss 3.1769 (3.0206)	grad_norm 3.0287 (3.0031)	
[2022-01-26 08:36:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1170/1251]	eta 0:02:58 lr 0.000034	time 2.1647 (2.1995)	loss 3.1888 (3.0224)	grad_norm 3.0045 (3.0066)	
[2022-01-26 08:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1180/1251]	eta 0:02:36 lr 0.000034	time 1.8375 (2.1984)	loss 3.1954 (3.0212)	grad_norm 3.1110 (3.0081)	
[2022-01-26 08:37:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1190/1251]	eta 0:02:14 lr 0.000034	time 2.6232 (2.1975)	loss 2.5472 (3.0209)	grad_norm 3.0008 (3.0103)	
[2022-01-26 08:37:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1200/1251]	eta 0:01:52 lr 0.000034	time 2.1157 (2.1972)	loss 3.3764 (3.0208)	grad_norm 3.3725 (3.0097)	
[2022-01-26 08:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1210/1251]	eta 0:01:30 lr 0.000034	time 1.9484 (2.1967)	loss 3.5399 (3.0224)	grad_norm 2.6810 (3.0094)	
[2022-01-26 08:38:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1220/1251]	eta 0:01:08 lr 0.000034	time 1.8435 (2.1957)	loss 2.3936 (3.0220)	grad_norm 2.8871 (3.0083)	
[2022-01-26 08:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1230/1251]	eta 0:00:46 lr 0.000034	time 1.8879 (2.1952)	loss 3.2477 (3.0223)	grad_norm 2.7547 (3.0085)	
[2022-01-26 08:38:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1240/1251]	eta 0:00:24 lr 0.000034	time 1.2450 (2.1949)	loss 3.2957 (3.0216)	grad_norm 3.1890 (3.0085)	
[2022-01-26 08:39:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [269/300][1250/1251]	eta 0:00:02 lr 0.000034	time 1.2158 (2.1898)	loss 3.7261 (3.0224)	grad_norm 3.0940 (3.0081)	
[2022-01-26 08:39:14 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 269 training takes 0:45:39
[2022-01-26 08:39:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.533 (18.533)	Loss 0.8116 (0.8116)	Acc@1 80.957 (80.957)	Acc@5 95.801 (95.801)	
[2022-01-26 08:39:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.817 (3.351)	Loss 0.7853 (0.8256)	Acc@1 81.836 (80.806)	Acc@5 95.508 (95.339)	
[2022-01-26 08:40:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.355 (2.516)	Loss 0.7720 (0.8157)	Acc@1 82.324 (81.017)	Acc@5 96.094 (95.429)	
[2022-01-26 08:40:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.929 (2.296)	Loss 0.9064 (0.8232)	Acc@1 79.883 (80.752)	Acc@5 94.141 (95.363)	
[2022-01-26 08:40:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.003 (2.203)	Loss 0.7805 (0.8236)	Acc@1 82.422 (80.840)	Acc@5 94.629 (95.308)	
[2022-01-26 08:40:52 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.920 Acc@5 95.366
[2022-01-26 08:40:52 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.9%
[2022-01-26 08:40:52 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 80.92%
[2022-01-26 08:41:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][0/1251]	eta 7:19:36 lr 0.000034	time 21.0842 (21.0842)	loss 3.5123 (3.5123)	grad_norm 3.1271 (3.1271)	
[2022-01-26 08:41:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][10/1251]	eta 1:26:02 lr 0.000034	time 2.2131 (4.1601)	loss 2.5290 (3.0208)	grad_norm 2.6744 (2.9324)	
[2022-01-26 08:42:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][20/1251]	eta 1:07:08 lr 0.000034	time 2.2471 (3.2722)	loss 3.1268 (3.1039)	grad_norm 2.8554 (2.9389)	
[2022-01-26 08:42:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][30/1251]	eta 0:59:23 lr 0.000034	time 1.9662 (2.9185)	loss 2.2957 (3.1138)	grad_norm 2.8846 (2.9547)	
[2022-01-26 08:42:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][40/1251]	eta 0:55:19 lr 0.000034	time 2.3870 (2.7411)	loss 3.2540 (3.0609)	grad_norm 2.8474 (2.9464)	
[2022-01-26 08:43:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][50/1251]	eta 0:53:16 lr 0.000034	time 2.2227 (2.6613)	loss 3.2975 (3.0749)	grad_norm 2.9140 (2.9190)	
[2022-01-26 08:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][60/1251]	eta 0:51:38 lr 0.000034	time 2.6999 (2.6014)	loss 2.8060 (3.1044)	grad_norm 3.3065 (2.9503)	
[2022-01-26 08:43:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][70/1251]	eta 0:49:48 lr 0.000034	time 1.9218 (2.5307)	loss 2.9914 (3.0861)	grad_norm 2.6656 (2.9754)	
[2022-01-26 08:44:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][80/1251]	eta 0:48:10 lr 0.000034	time 1.9814 (2.4682)	loss 2.3505 (3.0597)	grad_norm 2.9597 (2.9591)	
[2022-01-26 08:44:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][90/1251]	eta 0:46:46 lr 0.000034	time 1.9473 (2.4177)	loss 2.4174 (3.0613)	grad_norm 3.2323 (2.9806)	
[2022-01-26 08:44:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][100/1251]	eta 0:45:55 lr 0.000034	time 2.4845 (2.3943)	loss 3.1831 (3.0596)	grad_norm 2.7647 (2.9856)	
[2022-01-26 08:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][110/1251]	eta 0:44:51 lr 0.000034	time 1.3177 (2.3592)	loss 2.9617 (3.0505)	grad_norm 3.2354 (2.9664)	
[2022-01-26 08:45:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][120/1251]	eta 0:44:15 lr 0.000034	time 2.2233 (2.3479)	loss 3.5446 (3.0444)	grad_norm 2.4804 (2.9679)	
[2022-01-26 08:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][130/1251]	eta 0:43:47 lr 0.000034	time 2.1830 (2.3437)	loss 2.4691 (3.0196)	grad_norm 3.3166 (2.9804)	
[2022-01-26 08:46:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][140/1251]	eta 0:43:25 lr 0.000034	time 2.6719 (2.3456)	loss 3.6103 (3.0226)	grad_norm 3.2816 (3.0379)	
[2022-01-26 08:46:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][150/1251]	eta 0:42:59 lr 0.000034	time 1.7821 (2.3425)	loss 2.8997 (3.0242)	grad_norm 2.8700 (3.0520)	
[2022-01-26 08:47:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][160/1251]	eta 0:42:36 lr 0.000034	time 2.4240 (2.3432)	loss 2.3505 (3.0268)	grad_norm 3.0745 (3.0492)	
[2022-01-26 08:47:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][170/1251]	eta 0:41:57 lr 0.000034	time 1.6838 (2.3284)	loss 2.7705 (3.0320)	grad_norm 3.2059 (3.0462)	
[2022-01-26 08:47:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][180/1251]	eta 0:41:14 lr 0.000034	time 2.2836 (2.3102)	loss 3.7800 (3.0407)	grad_norm 3.0991 (3.0397)	
[2022-01-26 08:48:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][190/1251]	eta 0:40:49 lr 0.000034	time 2.2174 (2.3085)	loss 3.1815 (3.0286)	grad_norm 2.8410 (3.0354)	
[2022-01-26 08:48:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][200/1251]	eta 0:40:27 lr 0.000034	time 3.0793 (2.3096)	loss 3.0175 (3.0334)	grad_norm 2.8127 (3.0368)	
[2022-01-26 08:48:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][210/1251]	eta 0:39:48 lr 0.000034	time 1.5131 (2.2948)	loss 3.2378 (3.0283)	grad_norm 2.7639 (3.0360)	
[2022-01-26 08:49:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][220/1251]	eta 0:39:17 lr 0.000034	time 1.9496 (2.2867)	loss 1.9027 (3.0171)	grad_norm 3.4449 (3.0425)	
[2022-01-26 08:49:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][230/1251]	eta 0:38:47 lr 0.000034	time 2.2526 (2.2792)	loss 2.4611 (3.0132)	grad_norm 3.1802 (3.0485)	
[2022-01-26 08:50:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][240/1251]	eta 0:38:23 lr 0.000034	time 2.6399 (2.2780)	loss 3.6068 (3.0147)	grad_norm 3.6946 (3.0715)	
[2022-01-26 08:50:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][250/1251]	eta 0:37:59 lr 0.000034	time 1.9910 (2.2773)	loss 3.1657 (3.0124)	grad_norm 3.1798 (3.0671)	
[2022-01-26 08:50:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][260/1251]	eta 0:37:33 lr 0.000034	time 1.9243 (2.2741)	loss 3.3764 (3.0149)	grad_norm 3.8068 (3.0700)	
[2022-01-26 08:51:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][270/1251]	eta 0:37:06 lr 0.000034	time 1.8696 (2.2692)	loss 3.1772 (3.0154)	grad_norm 2.7606 (3.0622)	
[2022-01-26 08:51:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][280/1251]	eta 0:36:35 lr 0.000034	time 1.8210 (2.2607)	loss 3.5066 (3.0230)	grad_norm 2.6231 (3.0545)	
[2022-01-26 08:51:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][290/1251]	eta 0:35:59 lr 0.000034	time 2.2152 (2.2474)	loss 3.0863 (3.0136)	grad_norm 2.9248 (3.0528)	
[2022-01-26 08:52:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][300/1251]	eta 0:35:33 lr 0.000034	time 2.1654 (2.2430)	loss 2.2275 (3.0134)	grad_norm 2.7187 (3.0508)	
[2022-01-26 08:52:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][310/1251]	eta 0:35:11 lr 0.000034	time 2.2446 (2.2441)	loss 3.4718 (3.0242)	grad_norm 3.4511 (3.0520)	
[2022-01-26 08:52:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][320/1251]	eta 0:34:48 lr 0.000034	time 1.9501 (2.2429)	loss 3.3007 (3.0240)	grad_norm 3.1497 (3.0677)	
[2022-01-26 08:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][330/1251]	eta 0:34:32 lr 0.000034	time 2.1395 (2.2504)	loss 3.4956 (3.0166)	grad_norm 3.0179 (3.0742)	
[2022-01-26 08:53:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][340/1251]	eta 0:34:12 lr 0.000034	time 2.3884 (2.2526)	loss 3.1030 (3.0121)	grad_norm 2.8406 (3.0784)	
[2022-01-26 08:54:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][350/1251]	eta 0:33:51 lr 0.000034	time 2.1273 (2.2543)	loss 2.9559 (3.0116)	grad_norm 4.0936 (3.0769)	
[2022-01-26 08:54:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][360/1251]	eta 0:33:27 lr 0.000034	time 1.8872 (2.2533)	loss 3.1663 (3.0118)	grad_norm 3.5002 (3.0788)	
[2022-01-26 08:54:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][370/1251]	eta 0:33:01 lr 0.000034	time 1.9525 (2.2497)	loss 3.3797 (3.0138)	grad_norm 2.6968 (3.0749)	
[2022-01-26 08:55:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][380/1251]	eta 0:32:30 lr 0.000034	time 1.7106 (2.2389)	loss 2.9677 (3.0124)	grad_norm 2.8904 (3.0782)	
[2022-01-26 08:55:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][390/1251]	eta 0:32:01 lr 0.000034	time 1.8594 (2.2323)	loss 3.1429 (3.0138)	grad_norm 3.3484 (3.0847)	
[2022-01-26 08:55:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][400/1251]	eta 0:31:35 lr 0.000034	time 2.2137 (2.2274)	loss 3.0583 (3.0179)	grad_norm 3.4052 (3.0868)	
[2022-01-26 08:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][410/1251]	eta 0:31:11 lr 0.000034	time 1.8555 (2.2250)	loss 2.9853 (3.0195)	grad_norm 3.1062 (3.0846)	
[2022-01-26 08:56:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][420/1251]	eta 0:30:49 lr 0.000034	time 1.5567 (2.2257)	loss 2.0506 (3.0190)	grad_norm 2.8001 (3.0844)	
[2022-01-26 08:56:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][430/1251]	eta 0:30:27 lr 0.000034	time 2.2314 (2.2263)	loss 3.2833 (3.0224)	grad_norm 4.3086 (3.0862)	
[2022-01-26 08:57:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][440/1251]	eta 0:30:05 lr 0.000034	time 2.1751 (2.2264)	loss 2.7908 (3.0227)	grad_norm 3.2375 (3.0847)	
[2022-01-26 08:57:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][450/1251]	eta 0:29:43 lr 0.000034	time 1.8906 (2.2263)	loss 3.0882 (3.0215)	grad_norm 3.0337 (3.0802)	
[2022-01-26 08:58:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][460/1251]	eta 0:29:22 lr 0.000034	time 1.6373 (2.2287)	loss 2.6375 (3.0184)	grad_norm 3.4666 (3.0778)	
[2022-01-26 08:58:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][470/1251]	eta 0:29:01 lr 0.000034	time 2.5718 (2.2295)	loss 3.2227 (3.0155)	grad_norm 2.7196 (3.0725)	
[2022-01-26 08:58:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][480/1251]	eta 0:28:38 lr 0.000034	time 1.6011 (2.2287)	loss 2.6112 (3.0098)	grad_norm 3.2307 (3.0699)	
[2022-01-26 08:59:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][490/1251]	eta 0:28:17 lr 0.000034	time 2.4711 (2.2303)	loss 2.4942 (3.0138)	grad_norm 3.3854 (3.0695)	
[2022-01-26 08:59:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][500/1251]	eta 0:27:53 lr 0.000034	time 1.6556 (2.2280)	loss 2.9045 (3.0145)	grad_norm 2.5599 (3.0666)	
[2022-01-26 08:59:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][510/1251]	eta 0:27:29 lr 0.000034	time 1.8127 (2.2258)	loss 3.3935 (3.0118)	grad_norm 3.3356 (3.0647)	
[2022-01-26 09:00:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][520/1251]	eta 0:27:05 lr 0.000034	time 2.2555 (2.2241)	loss 2.0019 (3.0095)	grad_norm 3.7768 (3.0660)	
[2022-01-26 09:00:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][530/1251]	eta 0:26:42 lr 0.000034	time 1.8508 (2.2229)	loss 2.9179 (3.0094)	grad_norm 3.4544 (3.0633)	
[2022-01-26 09:00:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][540/1251]	eta 0:26:21 lr 0.000034	time 2.1532 (2.2249)	loss 2.7566 (3.0042)	grad_norm 3.1388 (3.0621)	
[2022-01-26 09:01:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][550/1251]	eta 0:25:57 lr 0.000034	time 1.8679 (2.2223)	loss 3.0104 (3.0034)	grad_norm 2.7609 (3.0586)	
[2022-01-26 09:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][560/1251]	eta 0:25:33 lr 0.000034	time 1.8830 (2.2193)	loss 3.4221 (3.0071)	grad_norm 2.4190 (3.0551)	
[2022-01-26 09:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][570/1251]	eta 0:25:10 lr 0.000034	time 2.0617 (2.2175)	loss 3.1894 (3.0089)	grad_norm 2.7453 (3.0552)	
[2022-01-26 09:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][580/1251]	eta 0:24:49 lr 0.000033	time 2.4337 (2.2195)	loss 2.4242 (3.0114)	grad_norm 2.9714 (3.0595)	
[2022-01-26 09:02:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][590/1251]	eta 0:24:28 lr 0.000033	time 2.8056 (2.2210)	loss 3.3481 (3.0121)	grad_norm 2.9374 (3.0598)	
[2022-01-26 09:03:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][600/1251]	eta 0:24:05 lr 0.000033	time 1.9423 (2.2206)	loss 3.2737 (3.0130)	grad_norm 3.1812 (3.0604)	
[2022-01-26 09:03:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][610/1251]	eta 0:23:43 lr 0.000033	time 1.8928 (2.2212)	loss 2.7019 (3.0130)	grad_norm 3.6347 (3.0605)	
[2022-01-26 09:03:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][620/1251]	eta 0:23:21 lr 0.000033	time 2.1942 (2.2203)	loss 3.4015 (3.0132)	grad_norm 3.4842 (3.0639)	
[2022-01-26 09:04:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][630/1251]	eta 0:22:57 lr 0.000033	time 3.0669 (2.2177)	loss 3.1084 (3.0164)	grad_norm 3.0656 (3.0659)	
[2022-01-26 09:04:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][640/1251]	eta 0:22:32 lr 0.000033	time 1.9353 (2.2131)	loss 3.0323 (3.0216)	grad_norm 2.7282 (3.0663)	
[2022-01-26 09:04:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][650/1251]	eta 0:22:09 lr 0.000033	time 2.2067 (2.2125)	loss 3.3621 (3.0215)	grad_norm 2.7770 (3.0647)	
[2022-01-26 09:05:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][660/1251]	eta 0:21:48 lr 0.000033	time 1.6771 (2.2136)	loss 3.2580 (3.0208)	grad_norm 2.5521 (3.0676)	
[2022-01-26 09:05:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][670/1251]	eta 0:21:27 lr 0.000033	time 4.4225 (2.2162)	loss 3.3785 (3.0165)	grad_norm 2.9458 (3.0657)	
[2022-01-26 09:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][680/1251]	eta 0:21:04 lr 0.000033	time 2.0100 (2.2145)	loss 2.2257 (3.0179)	grad_norm 2.9140 (3.0677)	
[2022-01-26 09:06:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][690/1251]	eta 0:20:41 lr 0.000033	time 2.1395 (2.2136)	loss 3.4659 (3.0213)	grad_norm 3.4887 (3.0680)	
[2022-01-26 09:06:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][700/1251]	eta 0:20:19 lr 0.000033	time 1.6120 (2.2135)	loss 2.6012 (3.0179)	grad_norm 2.9020 (3.0692)	
[2022-01-26 09:07:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][710/1251]	eta 0:19:58 lr 0.000033	time 3.3965 (2.2148)	loss 3.2201 (3.0185)	grad_norm 2.8847 (3.0694)	
[2022-01-26 09:07:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][720/1251]	eta 0:19:34 lr 0.000033	time 2.2112 (2.2126)	loss 3.3111 (3.0186)	grad_norm 2.8450 (3.0687)	
[2022-01-26 09:07:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][730/1251]	eta 0:19:12 lr 0.000033	time 1.9956 (2.2115)	loss 2.2444 (3.0179)	grad_norm 3.2441 (3.0672)	
[2022-01-26 09:08:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][740/1251]	eta 0:18:48 lr 0.000033	time 1.9281 (2.2092)	loss 3.6064 (3.0195)	grad_norm 2.8922 (3.0685)	
[2022-01-26 09:08:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][750/1251]	eta 0:18:26 lr 0.000033	time 2.7762 (2.2092)	loss 3.3916 (3.0219)	grad_norm 3.3939 (3.0678)	
[2022-01-26 09:08:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][760/1251]	eta 0:18:04 lr 0.000033	time 1.8510 (2.2093)	loss 2.8401 (3.0217)	grad_norm 2.6983 (3.0703)	
[2022-01-26 09:09:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][770/1251]	eta 0:17:42 lr 0.000033	time 1.9816 (2.2082)	loss 2.2402 (3.0184)	grad_norm 2.7391 (3.0710)	
[2022-01-26 09:09:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][780/1251]	eta 0:17:19 lr 0.000033	time 1.8552 (2.2076)	loss 3.2016 (3.0194)	grad_norm 3.0221 (3.0696)	
[2022-01-26 09:10:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][790/1251]	eta 0:16:58 lr 0.000033	time 3.4721 (2.2099)	loss 2.9597 (3.0217)	grad_norm 3.2628 (3.0696)	
[2022-01-26 09:10:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][800/1251]	eta 0:16:36 lr 0.000033	time 2.2314 (2.2097)	loss 3.0856 (3.0239)	grad_norm 2.8324 (3.0686)	
[2022-01-26 09:10:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][810/1251]	eta 0:16:13 lr 0.000033	time 1.5573 (2.2086)	loss 3.6301 (3.0266)	grad_norm 3.1913 (3.0668)	
[2022-01-26 09:11:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][820/1251]	eta 0:15:51 lr 0.000033	time 1.8812 (2.2073)	loss 3.3866 (3.0274)	grad_norm 3.5599 (3.0679)	
[2022-01-26 09:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][830/1251]	eta 0:15:28 lr 0.000033	time 2.5465 (2.2065)	loss 3.5856 (3.0278)	grad_norm 3.2375 (3.0682)	
[2022-01-26 09:11:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][840/1251]	eta 0:15:06 lr 0.000033	time 1.6452 (2.2045)	loss 3.5152 (3.0277)	grad_norm 3.0121 (3.0658)	
[2022-01-26 09:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][850/1251]	eta 0:14:44 lr 0.000033	time 1.9133 (2.2046)	loss 2.5353 (3.0239)	grad_norm 3.0937 (3.0667)	
[2022-01-26 09:12:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][860/1251]	eta 0:14:21 lr 0.000033	time 1.5787 (2.2037)	loss 3.3111 (3.0230)	grad_norm 2.5006 (3.0657)	
[2022-01-26 09:12:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][870/1251]	eta 0:13:59 lr 0.000033	time 1.8953 (2.2030)	loss 3.1600 (3.0228)	grad_norm 2.8369 (3.0627)	
[2022-01-26 09:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][880/1251]	eta 0:13:37 lr 0.000033	time 3.1529 (2.2047)	loss 3.3571 (3.0242)	grad_norm 3.4902 (3.0672)	
[2022-01-26 09:13:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][890/1251]	eta 0:13:17 lr 0.000033	time 3.3901 (2.2085)	loss 3.5070 (3.0251)	grad_norm 3.1867 (3.0648)	
[2022-01-26 09:14:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][900/1251]	eta 0:12:55 lr 0.000033	time 1.5973 (2.2101)	loss 2.9084 (3.0236)	grad_norm 2.4429 (3.0634)	
[2022-01-26 09:14:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][910/1251]	eta 0:12:33 lr 0.000033	time 2.4823 (2.2105)	loss 2.1437 (3.0234)	grad_norm 3.2221 (3.0631)	
[2022-01-26 09:14:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][920/1251]	eta 0:12:11 lr 0.000033	time 2.4936 (2.2090)	loss 2.5078 (3.0235)	grad_norm 2.6626 (3.0621)	
[2022-01-26 09:15:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][930/1251]	eta 0:11:48 lr 0.000033	time 2.6887 (2.2068)	loss 3.2705 (3.0238)	grad_norm 3.2948 (3.0633)	
[2022-01-26 09:15:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][940/1251]	eta 0:11:25 lr 0.000033	time 1.9528 (2.2051)	loss 2.8985 (3.0251)	grad_norm 2.8303 (3.0623)	
[2022-01-26 09:15:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][950/1251]	eta 0:11:03 lr 0.000033	time 2.2463 (2.2037)	loss 2.8181 (3.0261)	grad_norm 3.5162 (3.0628)	
[2022-01-26 09:16:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][960/1251]	eta 0:10:41 lr 0.000033	time 2.3112 (2.2028)	loss 2.4547 (3.0254)	grad_norm 2.6548 (3.0611)	
[2022-01-26 09:16:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][970/1251]	eta 0:10:18 lr 0.000033	time 2.4045 (2.2022)	loss 2.5738 (3.0230)	grad_norm 2.7216 (3.0597)	
[2022-01-26 09:16:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][980/1251]	eta 0:09:56 lr 0.000033	time 2.4341 (2.2009)	loss 2.1293 (3.0224)	grad_norm 2.8017 (3.0587)	
[2022-01-26 09:17:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][990/1251]	eta 0:09:34 lr 0.000033	time 2.4834 (2.2009)	loss 3.1592 (3.0232)	grad_norm 3.1592 (3.0592)	
[2022-01-26 09:17:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1000/1251]	eta 0:09:12 lr 0.000033	time 1.8643 (2.2013)	loss 2.1354 (3.0223)	grad_norm 2.7718 (3.0571)	
[2022-01-26 09:18:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1010/1251]	eta 0:08:51 lr 0.000033	time 3.0028 (2.2037)	loss 2.8249 (3.0235)	grad_norm 2.5889 (3.0565)	
[2022-01-26 09:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1020/1251]	eta 0:08:29 lr 0.000033	time 1.9901 (2.2073)	loss 2.3992 (3.0209)	grad_norm 2.7410 (3.0564)	
[2022-01-26 09:18:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1030/1251]	eta 0:08:08 lr 0.000033	time 2.1062 (2.2089)	loss 3.1057 (3.0233)	grad_norm 2.8707 (3.0553)	
[2022-01-26 09:19:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1040/1251]	eta 0:07:45 lr 0.000033	time 2.1277 (2.2083)	loss 1.9686 (3.0217)	grad_norm 6.1662 (3.0573)	
[2022-01-26 09:19:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1050/1251]	eta 0:07:23 lr 0.000033	time 1.9758 (2.2055)	loss 3.2083 (3.0230)	grad_norm 2.9482 (3.0569)	
[2022-01-26 09:19:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1060/1251]	eta 0:07:00 lr 0.000033	time 1.8837 (2.2029)	loss 3.4675 (3.0241)	grad_norm 3.0792 (3.0578)	
[2022-01-26 09:20:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1070/1251]	eta 0:06:38 lr 0.000033	time 2.4243 (2.2022)	loss 3.3849 (3.0239)	grad_norm 2.9148 (3.0596)	
[2022-01-26 09:20:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1080/1251]	eta 0:06:16 lr 0.000033	time 2.3096 (2.2016)	loss 3.4651 (3.0237)	grad_norm 3.3982 (3.0577)	
[2022-01-26 09:20:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1090/1251]	eta 0:05:54 lr 0.000033	time 1.4816 (2.2004)	loss 3.4197 (3.0234)	grad_norm 3.0296 (3.0574)	
[2022-01-26 09:21:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1100/1251]	eta 0:05:32 lr 0.000033	time 1.5768 (2.2004)	loss 2.9651 (3.0247)	grad_norm 3.5666 (3.0578)	
[2022-01-26 09:21:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1110/1251]	eta 0:05:10 lr 0.000033	time 2.7318 (2.2019)	loss 2.9358 (3.0274)	grad_norm 2.5496 (3.0565)	
[2022-01-26 09:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1120/1251]	eta 0:04:48 lr 0.000033	time 2.4260 (2.2032)	loss 2.7427 (3.0283)	grad_norm 2.9347 (3.0556)	
[2022-01-26 09:22:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1130/1251]	eta 0:04:26 lr 0.000033	time 1.5306 (2.2039)	loss 3.6280 (3.0275)	grad_norm 3.0681 (3.0551)	
[2022-01-26 09:22:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1140/1251]	eta 0:04:04 lr 0.000033	time 1.4971 (2.2029)	loss 2.7673 (3.0273)	grad_norm 2.7226 (3.0552)	
[2022-01-26 09:23:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1150/1251]	eta 0:03:42 lr 0.000033	time 1.8602 (2.2022)	loss 2.2157 (3.0260)	grad_norm 3.2576 (3.0556)	
[2022-01-26 09:23:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1160/1251]	eta 0:03:20 lr 0.000033	time 2.1137 (2.2021)	loss 3.2916 (3.0276)	grad_norm 2.9869 (3.0551)	
[2022-01-26 09:23:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1170/1251]	eta 0:02:58 lr 0.000033	time 1.7946 (2.2027)	loss 3.3075 (3.0268)	grad_norm 3.1259 (3.0549)	
[2022-01-26 09:24:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1180/1251]	eta 0:02:36 lr 0.000033	time 1.5832 (2.2027)	loss 2.0347 (3.0248)	grad_norm 2.9185 (3.0534)	
[2022-01-26 09:24:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1190/1251]	eta 0:02:14 lr 0.000033	time 2.2840 (2.2039)	loss 2.0151 (3.0250)	grad_norm 2.6779 (3.0533)	
[2022-01-26 09:25:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1200/1251]	eta 0:01:52 lr 0.000033	time 2.5956 (2.2042)	loss 2.9663 (3.0263)	grad_norm 2.9684 (3.0532)	
[2022-01-26 09:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1210/1251]	eta 0:01:30 lr 0.000033	time 1.5621 (2.2020)	loss 3.0868 (3.0244)	grad_norm 3.2811 (3.0524)	
[2022-01-26 09:25:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1220/1251]	eta 0:01:08 lr 0.000033	time 2.0775 (2.1999)	loss 3.0021 (3.0239)	grad_norm 2.7305 (3.0507)	
[2022-01-26 09:26:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1230/1251]	eta 0:00:46 lr 0.000033	time 2.2283 (2.1999)	loss 2.8088 (3.0250)	grad_norm 2.6795 (3.0505)	
[2022-01-26 09:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1240/1251]	eta 0:00:24 lr 0.000033	time 2.2417 (2.2000)	loss 3.1325 (3.0256)	grad_norm 2.8258 (3.0492)	
[2022-01-26 09:26:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [270/300][1250/1251]	eta 0:00:02 lr 0.000033	time 1.1533 (2.1946)	loss 2.6731 (3.0264)	grad_norm 2.7019 (3.0491)	
[2022-01-26 09:26:38 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 270 training takes 0:45:45
[2022-01-26 09:26:38 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_270 saving......
[2022-01-26 09:26:50 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_270 saved !!!
[2022-01-26 09:27:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 11.660 (11.660)	Loss 0.7942 (0.7942)	Acc@1 82.031 (82.031)	Acc@5 95.801 (95.801)	
[2022-01-26 09:27:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 4.334 (3.072)	Loss 0.8123 (0.7977)	Acc@1 81.152 (81.188)	Acc@5 95.410 (95.748)	
[2022-01-26 09:27:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.633 (2.413)	Loss 0.8552 (0.8024)	Acc@1 79.004 (81.283)	Acc@5 94.922 (95.578)	
[2022-01-26 09:27:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.661 (2.057)	Loss 0.7452 (0.7962)	Acc@1 82.422 (81.231)	Acc@5 95.996 (95.618)	
[2022-01-26 09:28:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.478 (2.037)	Loss 0.7790 (0.8052)	Acc@1 81.934 (81.159)	Acc@5 95.410 (95.470)	
[2022-01-26 09:28:21 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.016 Acc@5 95.420
[2022-01-26 09:28:21 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.0%
[2022-01-26 09:28:21 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.02%
[2022-01-26 09:28:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][0/1251]	eta 7:26:57 lr 0.000033	time 21.4365 (21.4365)	loss 3.4832 (3.4832)	grad_norm 3.7759 (3.7759)	
[2022-01-26 09:29:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][10/1251]	eta 1:23:53 lr 0.000033	time 1.8495 (4.0557)	loss 3.3633 (3.0461)	grad_norm 2.9059 (2.9550)	
[2022-01-26 09:29:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][20/1251]	eta 1:03:55 lr 0.000033	time 1.2418 (3.1158)	loss 2.7753 (3.0351)	grad_norm 2.6026 (2.9204)	
[2022-01-26 09:29:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][30/1251]	eta 0:56:21 lr 0.000033	time 1.6498 (2.7692)	loss 2.4747 (2.9653)	grad_norm 2.9180 (2.9527)	
[2022-01-26 09:30:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][40/1251]	eta 0:54:17 lr 0.000033	time 5.3797 (2.6897)	loss 2.9694 (2.9539)	grad_norm 2.7409 (2.9701)	
[2022-01-26 09:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][50/1251]	eta 0:53:08 lr 0.000033	time 2.1478 (2.6551)	loss 3.6135 (2.9399)	grad_norm 3.3003 (2.9704)	
[2022-01-26 09:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][60/1251]	eta 0:51:34 lr 0.000033	time 1.8160 (2.5979)	loss 3.4334 (2.9021)	grad_norm 2.8702 (2.9807)	
[2022-01-26 09:31:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][70/1251]	eta 0:49:38 lr 0.000033	time 1.5408 (2.5223)	loss 2.9916 (2.9224)	grad_norm 2.8303 (3.0147)	
[2022-01-26 09:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][80/1251]	eta 0:48:35 lr 0.000033	time 3.4651 (2.4901)	loss 3.3937 (2.9448)	grad_norm 2.7312 (3.0142)	
[2022-01-26 09:32:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][90/1251]	eta 0:46:55 lr 0.000033	time 1.5378 (2.4252)	loss 3.4409 (2.9570)	grad_norm 3.1569 (3.0138)	
[2022-01-26 09:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][100/1251]	eta 0:45:54 lr 0.000033	time 2.2766 (2.3935)	loss 3.4788 (2.9755)	grad_norm 2.6296 (3.0267)	
[2022-01-26 09:32:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][110/1251]	eta 0:45:03 lr 0.000033	time 1.9084 (2.3691)	loss 3.6479 (2.9637)	grad_norm 3.1513 (3.0198)	
[2022-01-26 09:33:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][120/1251]	eta 0:44:30 lr 0.000033	time 3.2306 (2.3614)	loss 2.6318 (2.9751)	grad_norm 3.0345 (3.0140)	
[2022-01-26 09:33:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][130/1251]	eta 0:43:57 lr 0.000032	time 2.1186 (2.3528)	loss 3.1881 (2.9899)	grad_norm 3.1339 (3.0085)	
[2022-01-26 09:33:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][140/1251]	eta 0:43:20 lr 0.000032	time 1.5331 (2.3409)	loss 3.3675 (3.0026)	grad_norm 3.0527 (3.0065)	
[2022-01-26 09:34:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][150/1251]	eta 0:42:44 lr 0.000032	time 1.8490 (2.3290)	loss 2.9808 (3.0076)	grad_norm 3.0564 (3.0253)	
[2022-01-26 09:34:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][160/1251]	eta 0:42:20 lr 0.000032	time 2.5748 (2.3287)	loss 3.3977 (3.0128)	grad_norm 2.9087 (3.0394)	
[2022-01-26 09:34:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][170/1251]	eta 0:41:53 lr 0.000032	time 1.6358 (2.3253)	loss 2.9594 (3.0038)	grad_norm 3.3661 (3.0531)	
[2022-01-26 09:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][180/1251]	eta 0:41:22 lr 0.000032	time 1.5622 (2.3179)	loss 2.4502 (2.9990)	grad_norm 2.8816 (3.0444)	
[2022-01-26 09:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][190/1251]	eta 0:40:52 lr 0.000032	time 2.6358 (2.3116)	loss 3.3604 (2.9948)	grad_norm 3.0735 (3.0461)	
[2022-01-26 09:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][200/1251]	eta 0:40:20 lr 0.000032	time 2.2983 (2.3031)	loss 3.3955 (2.9982)	grad_norm 2.6612 (3.0401)	
[2022-01-26 09:36:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][210/1251]	eta 0:39:52 lr 0.000032	time 1.8161 (2.2982)	loss 3.0297 (3.0015)	grad_norm 3.0710 (3.0322)	
[2022-01-26 09:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][220/1251]	eta 0:39:17 lr 0.000032	time 1.7885 (2.2865)	loss 2.8282 (2.9960)	grad_norm 3.0940 (3.0330)	
[2022-01-26 09:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][230/1251]	eta 0:38:46 lr 0.000032	time 1.8698 (2.2783)	loss 3.2803 (2.9993)	grad_norm 2.8300 (3.0366)	
[2022-01-26 09:37:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][240/1251]	eta 0:38:20 lr 0.000032	time 2.7979 (2.2751)	loss 3.2028 (3.0027)	grad_norm 3.0787 (3.0570)	
[2022-01-26 09:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][250/1251]	eta 0:38:01 lr 0.000032	time 2.5894 (2.2796)	loss 3.1330 (2.9986)	grad_norm 3.3477 (3.0572)	
[2022-01-26 09:38:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][260/1251]	eta 0:37:28 lr 0.000032	time 1.5708 (2.2690)	loss 3.2285 (2.9914)	grad_norm 2.7225 (3.0585)	
[2022-01-26 09:38:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][270/1251]	eta 0:36:58 lr 0.000032	time 2.1391 (2.2619)	loss 3.2640 (2.9867)	grad_norm 2.8054 (3.0535)	
[2022-01-26 09:38:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][280/1251]	eta 0:36:34 lr 0.000032	time 3.2350 (2.2600)	loss 3.4425 (2.9818)	grad_norm 2.7634 (3.0489)	
[2022-01-26 09:39:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][290/1251]	eta 0:36:14 lr 0.000032	time 2.9884 (2.2632)	loss 3.5141 (2.9819)	grad_norm 2.6864 (3.0521)	
[2022-01-26 09:39:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][300/1251]	eta 0:35:55 lr 0.000032	time 2.3418 (2.2662)	loss 3.1789 (2.9818)	grad_norm 3.8308 (3.0506)	
[2022-01-26 09:40:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][310/1251]	eta 0:35:32 lr 0.000032	time 1.8395 (2.2662)	loss 2.0140 (2.9778)	grad_norm 3.0357 (3.0492)	
[2022-01-26 09:40:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][320/1251]	eta 0:35:06 lr 0.000032	time 2.6464 (2.2629)	loss 2.3763 (2.9820)	grad_norm 3.6908 (3.0512)	
[2022-01-26 09:40:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][330/1251]	eta 0:34:35 lr 0.000032	time 1.9443 (2.2533)	loss 2.7107 (2.9859)	grad_norm 3.3211 (3.0647)	
[2022-01-26 09:41:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][340/1251]	eta 0:34:07 lr 0.000032	time 2.3788 (2.2470)	loss 3.2333 (2.9895)	grad_norm 2.8557 (3.0604)	
[2022-01-26 09:41:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][350/1251]	eta 0:33:39 lr 0.000032	time 1.8521 (2.2418)	loss 2.1664 (2.9893)	grad_norm 3.2125 (3.0634)	
[2022-01-26 09:41:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][360/1251]	eta 0:33:15 lr 0.000032	time 1.8323 (2.2393)	loss 3.0856 (2.9949)	grad_norm 2.5454 (3.0608)	
[2022-01-26 09:42:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][370/1251]	eta 0:32:54 lr 0.000032	time 2.1616 (2.2408)	loss 1.9640 (2.9931)	grad_norm 3.2991 (3.0592)	
[2022-01-26 09:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][380/1251]	eta 0:32:36 lr 0.000032	time 2.5398 (2.2466)	loss 1.9213 (2.9910)	grad_norm 3.0377 (3.0559)	
[2022-01-26 09:42:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][390/1251]	eta 0:32:13 lr 0.000032	time 1.4923 (2.2454)	loss 3.4939 (2.9890)	grad_norm 3.1412 (3.0592)	
[2022-01-26 09:43:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][400/1251]	eta 0:31:48 lr 0.000032	time 2.1975 (2.2423)	loss 2.2189 (2.9902)	grad_norm 2.8335 (3.0581)	
[2022-01-26 09:43:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][410/1251]	eta 0:31:23 lr 0.000032	time 1.9481 (2.2392)	loss 3.0464 (2.9919)	grad_norm 2.8683 (3.0537)	
[2022-01-26 09:44:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][420/1251]	eta 0:30:56 lr 0.000032	time 2.1845 (2.2339)	loss 3.3196 (2.9913)	grad_norm 3.1722 (3.0535)	
[2022-01-26 09:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][430/1251]	eta 0:30:29 lr 0.000032	time 1.5869 (2.2283)	loss 2.9149 (2.9926)	grad_norm 4.0305 (3.0569)	
[2022-01-26 09:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][440/1251]	eta 0:30:04 lr 0.000032	time 2.0328 (2.2256)	loss 3.1762 (2.9954)	grad_norm 3.2106 (3.0589)	
[2022-01-26 09:45:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][450/1251]	eta 0:29:45 lr 0.000032	time 2.9237 (2.2286)	loss 3.0096 (2.9972)	grad_norm 2.5627 (3.0591)	
[2022-01-26 09:45:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][460/1251]	eta 0:29:23 lr 0.000032	time 2.7598 (2.2297)	loss 3.0281 (2.9972)	grad_norm 3.0189 (3.0612)	
[2022-01-26 09:45:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][470/1251]	eta 0:29:00 lr 0.000032	time 1.8966 (2.2280)	loss 2.5764 (2.9951)	grad_norm 3.0611 (3.0596)	
[2022-01-26 09:46:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][480/1251]	eta 0:28:36 lr 0.000032	time 2.1838 (2.2269)	loss 3.0217 (2.9937)	grad_norm 2.5905 (3.0564)	
[2022-01-26 09:46:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][490/1251]	eta 0:28:14 lr 0.000032	time 2.1823 (2.2262)	loss 2.9192 (2.9918)	grad_norm 2.5905 (3.0559)	
[2022-01-26 09:46:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][500/1251]	eta 0:27:49 lr 0.000032	time 1.6724 (2.2230)	loss 3.3564 (2.9884)	grad_norm 3.0394 (3.0563)	
[2022-01-26 09:47:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][510/1251]	eta 0:27:25 lr 0.000032	time 1.6252 (2.2204)	loss 3.5337 (2.9907)	grad_norm 3.5461 (3.0553)	
[2022-01-26 09:47:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][520/1251]	eta 0:27:02 lr 0.000032	time 1.8649 (2.2196)	loss 3.6580 (2.9941)	grad_norm 2.9255 (3.0540)	
[2022-01-26 09:47:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][530/1251]	eta 0:26:38 lr 0.000032	time 2.2874 (2.2171)	loss 3.6911 (2.9987)	grad_norm 3.0935 (3.0514)	
[2022-01-26 09:48:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][540/1251]	eta 0:26:16 lr 0.000032	time 2.2648 (2.2174)	loss 3.5029 (2.9993)	grad_norm 2.8604 (3.0504)	
[2022-01-26 09:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][550/1251]	eta 0:25:54 lr 0.000032	time 2.2516 (2.2180)	loss 2.7943 (2.9983)	grad_norm 2.8255 (3.0481)	
[2022-01-26 09:49:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][560/1251]	eta 0:25:33 lr 0.000032	time 2.7396 (2.2191)	loss 3.3227 (3.0019)	grad_norm 3.0353 (3.0474)	
[2022-01-26 09:49:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][570/1251]	eta 0:25:11 lr 0.000032	time 1.9310 (2.2188)	loss 3.4148 (3.0046)	grad_norm 2.9118 (3.0451)	
[2022-01-26 09:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][580/1251]	eta 0:24:47 lr 0.000032	time 1.8920 (2.2169)	loss 3.3965 (3.0050)	grad_norm 2.7619 (3.0415)	
[2022-01-26 09:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][590/1251]	eta 0:24:22 lr 0.000032	time 1.7769 (2.2128)	loss 2.2571 (3.0087)	grad_norm 2.9885 (3.0402)	
[2022-01-26 09:50:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][600/1251]	eta 0:24:00 lr 0.000032	time 2.1665 (2.2124)	loss 3.3564 (3.0085)	grad_norm 3.1908 (3.0413)	
[2022-01-26 09:50:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][610/1251]	eta 0:23:38 lr 0.000032	time 2.1280 (2.2126)	loss 1.9677 (3.0061)	grad_norm 2.8076 (3.0395)	
[2022-01-26 09:51:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][620/1251]	eta 0:23:17 lr 0.000032	time 2.5196 (2.2147)	loss 3.1480 (3.0047)	grad_norm 2.9061 (3.0381)	
[2022-01-26 09:51:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][630/1251]	eta 0:22:54 lr 0.000032	time 1.9754 (2.2136)	loss 3.4871 (3.0039)	grad_norm 3.0002 (3.0376)	
[2022-01-26 09:52:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][640/1251]	eta 0:22:33 lr 0.000032	time 2.5384 (2.2146)	loss 2.9236 (3.0064)	grad_norm 2.6039 (3.0368)	
[2022-01-26 09:52:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][650/1251]	eta 0:22:10 lr 0.000032	time 1.6140 (2.2133)	loss 3.2807 (3.0087)	grad_norm 2.7147 (3.0347)	
[2022-01-26 09:52:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][660/1251]	eta 0:21:48 lr 0.000032	time 2.4233 (2.2138)	loss 3.3230 (3.0090)	grad_norm 2.6115 (3.0317)	
[2022-01-26 09:53:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][670/1251]	eta 0:21:24 lr 0.000032	time 1.8553 (2.2113)	loss 2.7526 (3.0119)	grad_norm 3.0547 (3.0294)	
[2022-01-26 09:53:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][680/1251]	eta 0:21:02 lr 0.000032	time 2.5599 (2.2116)	loss 3.3360 (3.0141)	grad_norm 2.7850 (3.0281)	
[2022-01-26 09:53:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][690/1251]	eta 0:20:40 lr 0.000032	time 1.9026 (2.2109)	loss 2.7859 (3.0163)	grad_norm 2.8841 (3.0262)	
[2022-01-26 09:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][700/1251]	eta 0:20:18 lr 0.000032	time 1.9376 (2.2122)	loss 2.2116 (3.0177)	grad_norm 2.7331 (3.0252)	
[2022-01-26 09:54:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][710/1251]	eta 0:19:56 lr 0.000032	time 2.1287 (2.2119)	loss 3.3238 (3.0208)	grad_norm 2.9870 (3.0248)	
[2022-01-26 09:54:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][720/1251]	eta 0:19:34 lr 0.000032	time 2.4955 (2.2114)	loss 3.5313 (3.0186)	grad_norm 3.0153 (3.0248)	
[2022-01-26 09:55:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][730/1251]	eta 0:19:11 lr 0.000032	time 1.6841 (2.2104)	loss 2.8181 (3.0198)	grad_norm 2.8572 (3.0272)	
[2022-01-26 09:55:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][740/1251]	eta 0:18:49 lr 0.000032	time 1.8022 (2.2104)	loss 2.4847 (3.0171)	grad_norm 2.9869 (3.0293)	
[2022-01-26 09:56:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][750/1251]	eta 0:18:27 lr 0.000032	time 2.6829 (2.2104)	loss 2.9010 (3.0143)	grad_norm 2.7384 (3.0295)	
[2022-01-26 09:56:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][760/1251]	eta 0:18:05 lr 0.000032	time 2.4788 (2.2102)	loss 2.5985 (3.0133)	grad_norm 2.6740 (3.0260)	
[2022-01-26 09:56:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][770/1251]	eta 0:17:42 lr 0.000032	time 1.6881 (2.2095)	loss 3.4923 (3.0141)	grad_norm 3.1296 (3.0244)	
[2022-01-26 09:57:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][780/1251]	eta 0:17:20 lr 0.000032	time 1.9539 (2.2097)	loss 3.0787 (3.0140)	grad_norm 2.7438 (3.0286)	
[2022-01-26 09:57:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][790/1251]	eta 0:16:59 lr 0.000032	time 2.6385 (2.2104)	loss 2.9110 (3.0135)	grad_norm 3.6587 (3.0286)	
[2022-01-26 09:57:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][800/1251]	eta 0:16:36 lr 0.000032	time 2.8100 (2.2094)	loss 2.6435 (3.0135)	grad_norm 3.4802 (3.0276)	
[2022-01-26 09:58:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][810/1251]	eta 0:16:13 lr 0.000032	time 2.0589 (2.2073)	loss 2.6058 (3.0114)	grad_norm 2.7032 (3.0273)	
[2022-01-26 09:58:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][820/1251]	eta 0:15:51 lr 0.000032	time 2.6035 (2.2076)	loss 3.2061 (3.0158)	grad_norm 3.0366 (3.0280)	
[2022-01-26 09:58:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][830/1251]	eta 0:15:29 lr 0.000032	time 2.0004 (2.2080)	loss 2.1065 (3.0154)	grad_norm 3.6373 (3.0274)	
[2022-01-26 09:59:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][840/1251]	eta 0:15:08 lr 0.000032	time 3.2231 (2.2094)	loss 3.1462 (3.0155)	grad_norm 2.7876 (3.0265)	
[2022-01-26 09:59:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][850/1251]	eta 0:14:45 lr 0.000032	time 2.5317 (2.2085)	loss 2.5631 (3.0150)	grad_norm 2.8740 (3.0253)	
[2022-01-26 10:00:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][860/1251]	eta 0:14:23 lr 0.000032	time 1.9492 (2.2075)	loss 2.2774 (3.0130)	grad_norm 2.5659 (3.0250)	
[2022-01-26 10:00:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][870/1251]	eta 0:14:00 lr 0.000032	time 1.8856 (2.2062)	loss 2.8751 (3.0096)	grad_norm 3.0133 (3.0259)	
[2022-01-26 10:00:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][880/1251]	eta 0:13:38 lr 0.000032	time 2.2070 (2.2050)	loss 2.7164 (3.0085)	grad_norm 3.4124 (3.0255)	
[2022-01-26 10:01:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][890/1251]	eta 0:13:16 lr 0.000032	time 2.2102 (2.2055)	loss 3.0005 (3.0095)	grad_norm 2.8643 (3.0266)	
[2022-01-26 10:01:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][900/1251]	eta 0:12:54 lr 0.000032	time 2.9772 (2.2075)	loss 3.3702 (3.0109)	grad_norm 2.7557 (3.0277)	
[2022-01-26 10:01:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][910/1251]	eta 0:12:32 lr 0.000032	time 2.0906 (2.2071)	loss 1.8532 (3.0078)	grad_norm 2.5663 (3.0287)	
[2022-01-26 10:02:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][920/1251]	eta 0:12:10 lr 0.000032	time 2.7776 (2.2057)	loss 3.3152 (3.0081)	grad_norm 2.6584 (3.0292)	
[2022-01-26 10:02:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][930/1251]	eta 0:11:47 lr 0.000032	time 1.6868 (2.2032)	loss 2.9247 (3.0062)	grad_norm 3.2430 (3.0309)	
[2022-01-26 10:02:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][940/1251]	eta 0:11:24 lr 0.000032	time 1.9845 (2.2015)	loss 3.0633 (3.0057)	grad_norm 3.5563 (3.0327)	
[2022-01-26 10:03:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][950/1251]	eta 0:11:02 lr 0.000031	time 1.9130 (2.2002)	loss 3.2836 (3.0074)	grad_norm 2.9253 (3.0322)	
[2022-01-26 10:03:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][960/1251]	eta 0:10:40 lr 0.000031	time 2.9500 (2.2017)	loss 2.3398 (3.0051)	grad_norm 2.6382 (3.0303)	
[2022-01-26 10:03:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][970/1251]	eta 0:10:18 lr 0.000031	time 1.7381 (2.2008)	loss 3.4252 (3.0064)	grad_norm 2.7489 (3.0318)	
[2022-01-26 10:04:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][980/1251]	eta 0:09:56 lr 0.000031	time 2.5508 (2.2000)	loss 2.8041 (3.0060)	grad_norm 3.1140 (3.0320)	
[2022-01-26 10:04:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][990/1251]	eta 0:09:34 lr 0.000031	time 2.2645 (2.1997)	loss 2.5465 (3.0043)	grad_norm 3.0095 (3.0308)	
[2022-01-26 10:05:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1000/1251]	eta 0:09:12 lr 0.000031	time 3.3412 (2.2027)	loss 2.4221 (3.0016)	grad_norm 2.4987 (3.0293)	
[2022-01-26 10:05:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1010/1251]	eta 0:08:51 lr 0.000031	time 1.6242 (2.2044)	loss 3.2396 (3.0016)	grad_norm 2.5273 (3.0319)	
[2022-01-26 10:05:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1020/1251]	eta 0:08:29 lr 0.000031	time 1.9048 (2.2041)	loss 3.0812 (3.0015)	grad_norm 2.7352 (3.0327)	
[2022-01-26 10:06:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1030/1251]	eta 0:08:06 lr 0.000031	time 2.2042 (2.2028)	loss 2.4546 (2.9992)	grad_norm 3.2759 (3.0328)	
[2022-01-26 10:06:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1040/1251]	eta 0:07:44 lr 0.000031	time 1.9036 (2.2012)	loss 3.3571 (2.9990)	grad_norm 4.2413 (3.0340)	
[2022-01-26 10:06:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1050/1251]	eta 0:07:22 lr 0.000031	time 1.9173 (2.1995)	loss 3.3208 (3.0012)	grad_norm 3.0274 (3.0336)	
[2022-01-26 10:07:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1060/1251]	eta 0:07:00 lr 0.000031	time 2.6243 (2.1992)	loss 2.0648 (3.0005)	grad_norm 2.8807 (3.0326)	
[2022-01-26 10:07:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1070/1251]	eta 0:06:38 lr 0.000031	time 2.5143 (2.1995)	loss 3.0209 (2.9995)	grad_norm 3.5139 (3.0323)	
[2022-01-26 10:07:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1080/1251]	eta 0:06:16 lr 0.000031	time 2.1999 (2.1996)	loss 3.1986 (3.0010)	grad_norm 3.7273 (3.0329)	
[2022-01-26 10:08:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1090/1251]	eta 0:05:54 lr 0.000031	time 2.5077 (2.2011)	loss 3.9130 (3.0021)	grad_norm 2.9324 (3.0329)	
[2022-01-26 10:08:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1100/1251]	eta 0:05:32 lr 0.000031	time 2.8864 (2.2022)	loss 3.9543 (3.0047)	grad_norm 3.1208 (3.0324)	
[2022-01-26 10:09:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1110/1251]	eta 0:05:10 lr 0.000031	time 2.0718 (2.2019)	loss 3.0862 (3.0051)	grad_norm 3.0944 (3.0325)	
[2022-01-26 10:09:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1120/1251]	eta 0:04:48 lr 0.000031	time 1.8893 (2.2001)	loss 3.1302 (3.0047)	grad_norm 3.1402 (3.0329)	
[2022-01-26 10:09:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1130/1251]	eta 0:04:26 lr 0.000031	time 2.1982 (2.2005)	loss 3.6515 (3.0065)	grad_norm 2.8901 (3.0327)	
[2022-01-26 10:10:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1140/1251]	eta 0:04:04 lr 0.000031	time 2.5144 (2.2004)	loss 3.4255 (3.0067)	grad_norm 2.6573 (3.0320)	
[2022-01-26 10:10:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1150/1251]	eta 0:03:42 lr 0.000031	time 1.9005 (2.1997)	loss 2.8575 (3.0040)	grad_norm 2.7298 (3.0316)	
[2022-01-26 10:10:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1160/1251]	eta 0:03:20 lr 0.000031	time 2.6899 (2.1998)	loss 2.4093 (3.0030)	grad_norm 2.5639 (3.0308)	
[2022-01-26 10:11:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1170/1251]	eta 0:02:58 lr 0.000031	time 1.8257 (2.1993)	loss 3.2976 (3.0035)	grad_norm 2.7322 (3.0298)	
[2022-01-26 10:11:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1180/1251]	eta 0:02:36 lr 0.000031	time 1.9244 (2.1984)	loss 3.3020 (3.0018)	grad_norm 2.7419 (3.0303)	
[2022-01-26 10:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1190/1251]	eta 0:02:14 lr 0.000031	time 1.9187 (2.1979)	loss 3.4190 (3.0023)	grad_norm 2.6979 (3.0303)	
[2022-01-26 10:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1200/1251]	eta 0:01:52 lr 0.000031	time 2.8858 (2.1981)	loss 3.5080 (3.0030)	grad_norm 2.9014 (3.0297)	
[2022-01-26 10:12:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1210/1251]	eta 0:01:30 lr 0.000031	time 1.8265 (2.1978)	loss 2.4305 (3.0015)	grad_norm 2.5846 (3.0284)	
[2022-01-26 10:13:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1220/1251]	eta 0:01:08 lr 0.000031	time 2.0777 (2.1975)	loss 3.2106 (3.0030)	grad_norm 3.0474 (3.0273)	
[2022-01-26 10:13:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1230/1251]	eta 0:00:46 lr 0.000031	time 1.5845 (2.1975)	loss 3.0047 (3.0036)	grad_norm 3.0506 (3.0278)	
[2022-01-26 10:13:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1240/1251]	eta 0:00:24 lr 0.000031	time 1.8027 (2.1965)	loss 3.3464 (3.0008)	grad_norm 4.4396 (3.0303)	
[2022-01-26 10:14:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [271/300][1250/1251]	eta 0:00:02 lr 0.000031	time 1.1713 (2.1902)	loss 3.3855 (3.0013)	grad_norm 3.1891 (3.0312)	
[2022-01-26 10:14:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 271 training takes 0:45:40
[2022-01-26 10:14:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.038 (19.038)	Loss 0.7767 (0.7767)	Acc@1 81.348 (81.348)	Acc@5 95.508 (95.508)	
[2022-01-26 10:14:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.289 (3.457)	Loss 0.8405 (0.8004)	Acc@1 80.664 (81.312)	Acc@5 95.020 (95.579)	
[2022-01-26 10:14:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.616 (2.533)	Loss 0.8035 (0.8059)	Acc@1 81.445 (81.078)	Acc@5 95.410 (95.536)	
[2022-01-26 10:15:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.621 (2.337)	Loss 0.8222 (0.8044)	Acc@1 80.273 (81.159)	Acc@5 95.703 (95.442)	
[2022-01-26 10:15:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.532 (2.196)	Loss 0.7320 (0.8064)	Acc@1 82.324 (81.098)	Acc@5 95.996 (95.424)	
[2022-01-26 10:15:38 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.074 Acc@5 95.382
[2022-01-26 10:15:38 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.1%
[2022-01-26 10:15:38 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.07%
[2022-01-26 10:16:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][0/1251]	eta 7:26:27 lr 0.000031	time 21.4129 (21.4129)	loss 3.1754 (3.1754)	grad_norm 3.5541 (3.5541)	
[2022-01-26 10:16:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][10/1251]	eta 1:23:52 lr 0.000031	time 2.5489 (4.0548)	loss 3.3228 (3.1840)	grad_norm 2.3596 (3.1280)	
[2022-01-26 10:16:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][20/1251]	eta 1:03:32 lr 0.000031	time 1.3011 (3.0968)	loss 2.9206 (3.1239)	grad_norm 2.8136 (3.1250)	
[2022-01-26 10:17:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][30/1251]	eta 0:56:36 lr 0.000031	time 1.7896 (2.7821)	loss 3.6335 (3.0365)	grad_norm 3.5069 (3.1180)	
[2022-01-26 10:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][40/1251]	eta 0:54:59 lr 0.000031	time 4.0052 (2.7247)	loss 3.3973 (3.0675)	grad_norm 2.6571 (3.1483)	
[2022-01-26 10:17:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][50/1251]	eta 0:52:03 lr 0.000031	time 1.7632 (2.6004)	loss 2.4626 (3.0136)	grad_norm 2.7489 (3.1049)	
[2022-01-26 10:18:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][60/1251]	eta 0:50:04 lr 0.000031	time 2.0884 (2.5229)	loss 2.0180 (3.0120)	grad_norm 2.5430 (3.0834)	
[2022-01-26 10:18:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][70/1251]	eta 0:48:26 lr 0.000031	time 1.5081 (2.4614)	loss 3.3495 (3.0257)	grad_norm 3.5858 (3.1098)	
[2022-01-26 10:18:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][80/1251]	eta 0:47:52 lr 0.000031	time 3.3307 (2.4533)	loss 3.3095 (3.0124)	grad_norm 3.2500 (3.1151)	
[2022-01-26 10:19:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][90/1251]	eta 0:47:10 lr 0.000031	time 1.9326 (2.4383)	loss 3.1443 (2.9857)	grad_norm 3.2550 (3.1510)	
[2022-01-26 10:19:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][100/1251]	eta 0:46:26 lr 0.000031	time 2.4374 (2.4209)	loss 3.6388 (3.0095)	grad_norm 3.0660 (3.1511)	
[2022-01-26 10:20:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][110/1251]	eta 0:45:36 lr 0.000031	time 1.6918 (2.3981)	loss 2.5987 (3.0143)	grad_norm 2.6252 (3.1272)	
[2022-01-26 10:20:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][120/1251]	eta 0:44:39 lr 0.000031	time 2.3399 (2.3691)	loss 3.1519 (3.0301)	grad_norm 2.9600 (3.1132)	
[2022-01-26 10:20:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][130/1251]	eta 0:43:44 lr 0.000031	time 1.8778 (2.3411)	loss 3.3987 (3.0532)	grad_norm 3.3589 (3.1204)	
[2022-01-26 10:21:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][140/1251]	eta 0:42:59 lr 0.000031	time 2.7429 (2.3217)	loss 3.4430 (3.0358)	grad_norm 2.8431 (3.1147)	
[2022-01-26 10:21:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][150/1251]	eta 0:42:19 lr 0.000031	time 2.1411 (2.3069)	loss 3.4608 (3.0289)	grad_norm 2.9713 (3.1145)	
[2022-01-26 10:21:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][160/1251]	eta 0:41:47 lr 0.000031	time 2.8759 (2.2980)	loss 3.1350 (3.0297)	grad_norm 2.7860 (3.1057)	
[2022-01-26 10:22:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][170/1251]	eta 0:41:11 lr 0.000031	time 1.7460 (2.2866)	loss 2.6155 (3.0340)	grad_norm 3.1938 (3.1076)	
[2022-01-26 10:22:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][180/1251]	eta 0:40:43 lr 0.000031	time 2.1968 (2.2817)	loss 2.4527 (3.0317)	grad_norm 3.4015 (3.0996)	
[2022-01-26 10:22:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][190/1251]	eta 0:40:26 lr 0.000031	time 2.2959 (2.2867)	loss 2.8820 (3.0222)	grad_norm 2.5057 (3.0903)	
[2022-01-26 10:23:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][200/1251]	eta 0:40:01 lr 0.000031	time 2.8011 (2.2852)	loss 2.9231 (3.0251)	grad_norm 3.1078 (3.0879)	
[2022-01-26 10:23:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][210/1251]	eta 0:39:39 lr 0.000031	time 1.5578 (2.2862)	loss 2.8039 (3.0366)	grad_norm 2.7210 (3.0849)	
[2022-01-26 10:24:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][220/1251]	eta 0:39:15 lr 0.000031	time 2.5542 (2.2845)	loss 3.1898 (3.0394)	grad_norm 3.1225 (3.0827)	
[2022-01-26 10:24:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][230/1251]	eta 0:38:50 lr 0.000031	time 1.8630 (2.2824)	loss 3.5683 (3.0459)	grad_norm 4.0807 (3.0859)	
[2022-01-26 10:24:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][240/1251]	eta 0:38:19 lr 0.000031	time 2.6879 (2.2747)	loss 3.2058 (3.0506)	grad_norm 3.1747 (3.0843)	
[2022-01-26 10:25:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][250/1251]	eta 0:37:45 lr 0.000031	time 1.8502 (2.2634)	loss 2.3226 (3.0436)	grad_norm 2.5133 (3.0788)	
[2022-01-26 10:25:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][260/1251]	eta 0:37:21 lr 0.000031	time 2.1907 (2.2616)	loss 3.4729 (3.0471)	grad_norm 2.6094 (3.0738)	
[2022-01-26 10:25:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][270/1251]	eta 0:36:56 lr 0.000031	time 2.3229 (2.2599)	loss 3.2340 (3.0415)	grad_norm 3.6827 (3.0782)	
[2022-01-26 10:26:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][280/1251]	eta 0:36:28 lr 0.000031	time 2.4662 (2.2534)	loss 3.5510 (3.0421)	grad_norm 2.6971 (3.0705)	
[2022-01-26 10:26:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][290/1251]	eta 0:35:59 lr 0.000031	time 2.1380 (2.2467)	loss 2.7696 (3.0354)	grad_norm 2.9929 (3.0685)	
[2022-01-26 10:26:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][300/1251]	eta 0:35:32 lr 0.000031	time 2.4860 (2.2420)	loss 3.3150 (3.0301)	grad_norm 3.5631 (3.0649)	
[2022-01-26 10:27:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][310/1251]	eta 0:35:06 lr 0.000031	time 2.0682 (2.2381)	loss 3.2252 (3.0273)	grad_norm 3.0169 (3.0607)	
[2022-01-26 10:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][320/1251]	eta 0:34:44 lr 0.000031	time 2.7999 (2.2389)	loss 3.3369 (3.0322)	grad_norm 3.1175 (3.0517)	
[2022-01-26 10:28:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][330/1251]	eta 0:34:22 lr 0.000031	time 2.1181 (2.2396)	loss 3.1134 (3.0328)	grad_norm 3.5007 (3.0578)	
[2022-01-26 10:28:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][340/1251]	eta 0:33:57 lr 0.000031	time 2.3601 (2.2369)	loss 3.3433 (3.0338)	grad_norm 2.9043 (3.0532)	
[2022-01-26 10:28:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][350/1251]	eta 0:33:34 lr 0.000031	time 1.5980 (2.2358)	loss 3.6408 (3.0413)	grad_norm 3.3005 (3.0500)	
[2022-01-26 10:29:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][360/1251]	eta 0:33:22 lr 0.000031	time 3.6016 (2.2475)	loss 3.3251 (3.0456)	grad_norm 2.8786 (3.0519)	
[2022-01-26 10:29:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][370/1251]	eta 0:33:01 lr 0.000031	time 1.9145 (2.2487)	loss 3.5577 (3.0494)	grad_norm 3.2860 (3.0502)	
[2022-01-26 10:29:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][380/1251]	eta 0:32:38 lr 0.000031	time 1.8038 (2.2485)	loss 2.9893 (3.0500)	grad_norm 3.4979 (3.0575)	
[2022-01-26 10:30:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][390/1251]	eta 0:32:10 lr 0.000031	time 1.7144 (2.2427)	loss 3.4343 (3.0409)	grad_norm 3.3550 (3.0641)	
[2022-01-26 10:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][400/1251]	eta 0:31:43 lr 0.000031	time 2.6695 (2.2371)	loss 2.9719 (3.0367)	grad_norm 3.1268 (3.0622)	
[2022-01-26 10:30:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][410/1251]	eta 0:31:20 lr 0.000031	time 2.7982 (2.2357)	loss 2.2647 (3.0349)	grad_norm 3.3391 (3.0637)	
[2022-01-26 10:31:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][420/1251]	eta 0:30:55 lr 0.000031	time 2.2658 (2.2326)	loss 2.6163 (3.0362)	grad_norm 2.7374 (3.0669)	
[2022-01-26 10:31:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][430/1251]	eta 0:30:31 lr 0.000031	time 1.8347 (2.2309)	loss 2.7052 (3.0305)	grad_norm 2.8172 (3.0642)	
[2022-01-26 10:32:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][440/1251]	eta 0:30:07 lr 0.000031	time 1.8739 (2.2283)	loss 2.0398 (3.0295)	grad_norm 3.8646 (3.0618)	
[2022-01-26 10:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][450/1251]	eta 0:29:43 lr 0.000031	time 2.2342 (2.2266)	loss 3.2156 (3.0339)	grad_norm 3.1152 (3.0576)	
[2022-01-26 10:32:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][460/1251]	eta 0:29:21 lr 0.000031	time 2.1922 (2.2274)	loss 3.5041 (3.0316)	grad_norm 3.3280 (3.0596)	
[2022-01-26 10:33:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][470/1251]	eta 0:28:59 lr 0.000031	time 1.6422 (2.2274)	loss 2.3644 (3.0333)	grad_norm 2.7502 (3.0551)	
[2022-01-26 10:33:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][480/1251]	eta 0:28:36 lr 0.000031	time 1.8765 (2.2265)	loss 2.9319 (3.0314)	grad_norm 3.7078 (3.0558)	
[2022-01-26 10:33:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][490/1251]	eta 0:28:14 lr 0.000031	time 2.3239 (2.2263)	loss 3.1553 (3.0368)	grad_norm 2.8513 (3.0527)	
[2022-01-26 10:34:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][500/1251]	eta 0:27:52 lr 0.000031	time 2.0071 (2.2276)	loss 2.7811 (3.0396)	grad_norm 2.4292 (3.0520)	
[2022-01-26 10:34:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][510/1251]	eta 0:27:30 lr 0.000031	time 1.7787 (2.2277)	loss 2.8067 (3.0378)	grad_norm 3.1323 (3.0540)	
[2022-01-26 10:34:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][520/1251]	eta 0:27:05 lr 0.000031	time 2.1556 (2.2239)	loss 3.1825 (3.0391)	grad_norm 3.2809 (3.0538)	
[2022-01-26 10:35:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][530/1251]	eta 0:26:41 lr 0.000030	time 2.0109 (2.2219)	loss 2.4630 (3.0375)	grad_norm 2.8438 (3.0525)	
[2022-01-26 10:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][540/1251]	eta 0:26:19 lr 0.000030	time 2.1760 (2.2218)	loss 3.4483 (3.0365)	grad_norm 2.7773 (3.0503)	
[2022-01-26 10:36:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][550/1251]	eta 0:25:55 lr 0.000030	time 1.9166 (2.2196)	loss 2.8330 (3.0353)	grad_norm 3.0264 (3.0490)	
[2022-01-26 10:36:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][560/1251]	eta 0:25:31 lr 0.000030	time 1.9524 (2.2167)	loss 3.0693 (3.0355)	grad_norm 3.1217 (3.0503)	
[2022-01-26 10:36:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][570/1251]	eta 0:25:08 lr 0.000030	time 2.0142 (2.2152)	loss 3.2680 (3.0348)	grad_norm 3.4154 (3.0511)	
[2022-01-26 10:37:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][580/1251]	eta 0:24:46 lr 0.000030	time 2.5792 (2.2151)	loss 3.1935 (3.0364)	grad_norm 2.9969 (3.0503)	
[2022-01-26 10:37:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][590/1251]	eta 0:24:24 lr 0.000030	time 1.9009 (2.2163)	loss 3.0557 (3.0374)	grad_norm 3.3634 (3.0506)	
[2022-01-26 10:37:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][600/1251]	eta 0:24:04 lr 0.000030	time 2.7754 (2.2183)	loss 2.2013 (3.0344)	grad_norm 3.4224 (3.0516)	
[2022-01-26 10:38:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][610/1251]	eta 0:23:43 lr 0.000030	time 2.2274 (2.2201)	loss 3.6091 (3.0344)	grad_norm 2.7095 (3.0513)	
[2022-01-26 10:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][620/1251]	eta 0:23:20 lr 0.000030	time 2.2082 (2.2201)	loss 3.1649 (3.0333)	grad_norm 2.9404 (3.0526)	
[2022-01-26 10:38:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][630/1251]	eta 0:22:57 lr 0.000030	time 1.8799 (2.2188)	loss 3.6089 (3.0329)	grad_norm 3.7707 (3.0565)	
[2022-01-26 10:39:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][640/1251]	eta 0:22:35 lr 0.000030	time 2.8701 (2.2177)	loss 3.0419 (3.0348)	grad_norm 2.7980 (3.0570)	
[2022-01-26 10:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][650/1251]	eta 0:22:11 lr 0.000030	time 2.0577 (2.2156)	loss 2.2012 (3.0323)	grad_norm 2.8070 (3.0566)	
[2022-01-26 10:40:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][660/1251]	eta 0:21:49 lr 0.000030	time 2.9137 (2.2151)	loss 2.8441 (3.0299)	grad_norm 2.7664 (3.0609)	
[2022-01-26 10:40:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][670/1251]	eta 0:21:29 lr 0.000030	time 3.0208 (2.2194)	loss 2.8017 (3.0298)	grad_norm 2.9177 (3.0619)	
[2022-01-26 10:40:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][680/1251]	eta 0:21:08 lr 0.000030	time 2.5357 (2.2213)	loss 3.0690 (3.0280)	grad_norm 4.4120 (3.0657)	
[2022-01-26 10:41:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][690/1251]	eta 0:20:45 lr 0.000030	time 2.0063 (2.2205)	loss 2.7784 (3.0281)	grad_norm 3.1419 (3.0638)	
[2022-01-26 10:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][700/1251]	eta 0:20:23 lr 0.000030	time 2.0043 (2.2197)	loss 2.6712 (3.0261)	grad_norm 3.6595 (3.0640)	
[2022-01-26 10:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][710/1251]	eta 0:19:57 lr 0.000030	time 1.6196 (2.2143)	loss 3.1648 (3.0231)	grad_norm 3.4856 (3.0631)	
[2022-01-26 10:42:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][720/1251]	eta 0:19:33 lr 0.000030	time 1.7929 (2.2106)	loss 3.2034 (3.0223)	grad_norm 2.5894 (3.0601)	
[2022-01-26 10:42:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][730/1251]	eta 0:19:10 lr 0.000030	time 1.9007 (2.2084)	loss 3.4104 (3.0202)	grad_norm 2.9265 (3.0605)	
[2022-01-26 10:42:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][740/1251]	eta 0:18:48 lr 0.000030	time 2.2586 (2.2075)	loss 2.7429 (3.0224)	grad_norm 3.2881 (3.0607)	
[2022-01-26 10:43:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][750/1251]	eta 0:18:26 lr 0.000030	time 2.4965 (2.2081)	loss 2.7612 (3.0205)	grad_norm 3.5018 (3.0606)	
[2022-01-26 10:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][760/1251]	eta 0:18:05 lr 0.000030	time 2.5231 (2.2101)	loss 2.4764 (3.0223)	grad_norm 2.6573 (3.0592)	
[2022-01-26 10:44:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][770/1251]	eta 0:17:43 lr 0.000030	time 1.8977 (2.2101)	loss 3.4059 (3.0201)	grad_norm 2.8193 (3.0560)	
[2022-01-26 10:44:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][780/1251]	eta 0:17:20 lr 0.000030	time 2.5616 (2.2101)	loss 2.9582 (3.0190)	grad_norm 2.8936 (3.0591)	
[2022-01-26 10:44:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][790/1251]	eta 0:16:59 lr 0.000030	time 2.8632 (2.2117)	loss 2.5842 (3.0174)	grad_norm 3.8341 (3.0609)	
[2022-01-26 10:45:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][800/1251]	eta 0:16:37 lr 0.000030	time 1.5959 (2.2117)	loss 3.3989 (3.0166)	grad_norm 2.5487 (3.0606)	
[2022-01-26 10:45:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][810/1251]	eta 0:16:15 lr 0.000030	time 2.2453 (2.2123)	loss 2.2887 (3.0152)	grad_norm 3.4019 (3.0600)	
[2022-01-26 10:45:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][820/1251]	eta 0:15:53 lr 0.000030	time 2.4963 (2.2117)	loss 2.9175 (3.0131)	grad_norm 3.5734 (3.0634)	
[2022-01-26 10:46:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][830/1251]	eta 0:15:30 lr 0.000030	time 1.9459 (2.2100)	loss 2.5789 (3.0136)	grad_norm 3.3287 (3.0635)	
[2022-01-26 10:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][840/1251]	eta 0:15:08 lr 0.000030	time 1.8842 (2.2107)	loss 3.3700 (3.0133)	grad_norm 2.8022 (3.0625)	
[2022-01-26 10:46:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][850/1251]	eta 0:14:46 lr 0.000030	time 1.8426 (2.2103)	loss 3.4589 (3.0153)	grad_norm 2.8256 (3.0611)	
[2022-01-26 10:47:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][860/1251]	eta 0:14:24 lr 0.000030	time 3.0042 (2.2108)	loss 3.3185 (3.0175)	grad_norm 2.9731 (3.0591)	
[2022-01-26 10:47:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][870/1251]	eta 0:14:01 lr 0.000030	time 2.0193 (2.2099)	loss 3.5295 (3.0186)	grad_norm 3.4152 (3.0624)	
[2022-01-26 10:48:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][880/1251]	eta 0:13:39 lr 0.000030	time 1.9045 (2.2100)	loss 3.2109 (3.0200)	grad_norm 2.8802 (3.0669)	
[2022-01-26 10:48:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][890/1251]	eta 0:13:17 lr 0.000030	time 1.9540 (2.2089)	loss 2.9569 (3.0147)	grad_norm 2.9796 (3.0661)	
[2022-01-26 10:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][900/1251]	eta 0:12:55 lr 0.000030	time 3.2570 (2.2088)	loss 3.2835 (3.0139)	grad_norm 2.9988 (3.0660)	
[2022-01-26 10:49:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][910/1251]	eta 0:12:32 lr 0.000030	time 1.8361 (2.2078)	loss 3.1370 (3.0151)	grad_norm 2.7372 (3.0642)	
[2022-01-26 10:49:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][920/1251]	eta 0:12:10 lr 0.000030	time 1.8537 (2.2071)	loss 3.0673 (3.0127)	grad_norm 2.9768 (3.0639)	
[2022-01-26 10:49:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][930/1251]	eta 0:11:48 lr 0.000030	time 1.5973 (2.2061)	loss 3.2263 (3.0123)	grad_norm 2.7266 (3.0632)	
[2022-01-26 10:50:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][940/1251]	eta 0:11:26 lr 0.000030	time 2.2027 (2.2059)	loss 3.4170 (3.0124)	grad_norm 3.2065 (3.0649)	
[2022-01-26 10:50:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][950/1251]	eta 0:11:03 lr 0.000030	time 1.9596 (2.2058)	loss 2.5941 (3.0139)	grad_norm 3.2121 (3.0645)	
[2022-01-26 10:50:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][960/1251]	eta 0:10:41 lr 0.000030	time 2.1638 (2.2059)	loss 3.6657 (3.0123)	grad_norm 2.7404 (3.0618)	
[2022-01-26 10:51:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][970/1251]	eta 0:10:19 lr 0.000030	time 1.8115 (2.2058)	loss 3.4159 (3.0105)	grad_norm 3.2395 (3.0607)	
[2022-01-26 10:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][980/1251]	eta 0:09:58 lr 0.000030	time 2.4194 (2.2068)	loss 3.5744 (3.0122)	grad_norm 2.9284 (3.0593)	
[2022-01-26 10:52:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][990/1251]	eta 0:09:35 lr 0.000030	time 2.1599 (2.2066)	loss 3.0763 (3.0121)	grad_norm 2.8744 (3.0622)	
[2022-01-26 10:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1000/1251]	eta 0:09:14 lr 0.000030	time 1.9315 (2.2074)	loss 1.7087 (3.0115)	grad_norm 3.0043 (3.0611)	
[2022-01-26 10:52:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1010/1251]	eta 0:08:51 lr 0.000030	time 2.2684 (2.2054)	loss 2.1484 (3.0094)	grad_norm 2.9494 (3.0607)	
[2022-01-26 10:53:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1020/1251]	eta 0:08:29 lr 0.000030	time 1.9878 (2.2053)	loss 3.5070 (3.0105)	grad_norm 5.4885 (3.0628)	
[2022-01-26 10:53:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1030/1251]	eta 0:08:07 lr 0.000030	time 2.1916 (2.2039)	loss 3.1337 (3.0098)	grad_norm 3.1799 (3.0621)	
[2022-01-26 10:53:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1040/1251]	eta 0:07:45 lr 0.000030	time 1.9005 (2.2044)	loss 2.7344 (3.0114)	grad_norm 3.1891 (3.0654)	
[2022-01-26 10:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1050/1251]	eta 0:07:22 lr 0.000030	time 1.8671 (2.2034)	loss 2.7803 (3.0122)	grad_norm 3.0461 (3.0654)	
[2022-01-26 10:54:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1060/1251]	eta 0:07:00 lr 0.000030	time 2.1723 (2.2032)	loss 3.4621 (3.0111)	grad_norm 3.0650 (3.0661)	
[2022-01-26 10:54:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1070/1251]	eta 0:06:38 lr 0.000030	time 1.7750 (2.2030)	loss 3.5973 (3.0099)	grad_norm 2.6970 (3.0636)	
[2022-01-26 10:55:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1080/1251]	eta 0:06:16 lr 0.000030	time 1.9488 (2.2040)	loss 3.0205 (3.0131)	grad_norm 3.3574 (3.0632)	
[2022-01-26 10:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1090/1251]	eta 0:05:54 lr 0.000030	time 2.1055 (2.2036)	loss 1.9274 (3.0126)	grad_norm 3.0031 (3.0630)	
[2022-01-26 10:56:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1100/1251]	eta 0:05:32 lr 0.000030	time 2.0199 (2.2031)	loss 1.8363 (3.0116)	grad_norm 2.9792 (3.0627)	
[2022-01-26 10:56:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1110/1251]	eta 0:05:10 lr 0.000030	time 2.1546 (2.2037)	loss 3.2933 (3.0130)	grad_norm 3.0462 (3.0618)	
[2022-01-26 10:56:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1120/1251]	eta 0:04:48 lr 0.000030	time 1.6089 (2.2034)	loss 3.6511 (3.0153)	grad_norm 3.4296 (3.0619)	
[2022-01-26 10:57:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1130/1251]	eta 0:04:26 lr 0.000030	time 3.0741 (2.2032)	loss 2.8114 (3.0138)	grad_norm 2.8067 (3.0613)	
[2022-01-26 10:57:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1140/1251]	eta 0:04:04 lr 0.000030	time 2.1706 (2.2032)	loss 2.6495 (3.0129)	grad_norm 2.9372 (3.0607)	
[2022-01-26 10:57:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1150/1251]	eta 0:03:42 lr 0.000030	time 1.8827 (2.2021)	loss 2.3413 (3.0102)	grad_norm 2.8722 (3.0609)	
[2022-01-26 10:58:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1160/1251]	eta 0:03:20 lr 0.000030	time 2.7826 (2.2019)	loss 2.9990 (3.0104)	grad_norm 2.8972 (3.0601)	
[2022-01-26 10:58:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1170/1251]	eta 0:02:58 lr 0.000030	time 1.8467 (2.2010)	loss 2.5895 (3.0091)	grad_norm 3.5119 (3.0609)	
[2022-01-26 10:58:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1180/1251]	eta 0:02:36 lr 0.000030	time 2.4313 (2.2011)	loss 2.3748 (3.0080)	grad_norm 2.7782 (3.0611)	
[2022-01-26 10:59:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1190/1251]	eta 0:02:14 lr 0.000030	time 2.2542 (2.2004)	loss 2.2416 (3.0081)	grad_norm 3.2273 (3.0601)	
[2022-01-26 10:59:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1200/1251]	eta 0:01:52 lr 0.000030	time 2.4575 (2.2005)	loss 3.0029 (3.0067)	grad_norm 2.8900 (3.0590)	
[2022-01-26 11:00:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1210/1251]	eta 0:01:30 lr 0.000030	time 2.0941 (2.2002)	loss 2.3088 (3.0043)	grad_norm 2.8115 (3.0588)	
[2022-01-26 11:00:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1220/1251]	eta 0:01:08 lr 0.000030	time 1.8164 (2.1987)	loss 2.4871 (3.0043)	grad_norm 3.1465 (3.0591)	
[2022-01-26 11:00:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1230/1251]	eta 0:00:46 lr 0.000030	time 2.3761 (2.1991)	loss 2.1308 (3.0024)	grad_norm 2.7056 (3.0576)	
[2022-01-26 11:01:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1240/1251]	eta 0:00:24 lr 0.000030	time 1.7537 (2.1981)	loss 3.0183 (3.0018)	grad_norm 2.7926 (3.0574)	
[2022-01-26 11:01:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [272/300][1250/1251]	eta 0:00:02 lr 0.000030	time 1.1987 (2.1929)	loss 2.4911 (3.0012)	grad_norm 3.7361 (3.0575)	
[2022-01-26 11:01:22 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 272 training takes 0:45:43
[2022-01-26 11:01:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.595 (18.595)	Loss 0.8299 (0.8299)	Acc@1 81.055 (81.055)	Acc@5 94.922 (94.922)	
[2022-01-26 11:01:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.259 (3.138)	Loss 0.7303 (0.7986)	Acc@1 83.496 (81.587)	Acc@5 95.801 (95.543)	
[2022-01-26 11:02:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.618 (2.441)	Loss 0.8285 (0.8050)	Acc@1 79.883 (81.231)	Acc@5 95.996 (95.573)	
[2022-01-26 11:02:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 3.739 (2.296)	Loss 0.8399 (0.8099)	Acc@1 79.297 (81.061)	Acc@5 95.312 (95.520)	
[2022-01-26 11:02:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.372 (2.148)	Loss 0.8010 (0.8146)	Acc@1 81.934 (80.967)	Acc@5 95.996 (95.405)	
[2022-01-26 11:02:57 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.960 Acc@5 95.418
[2022-01-26 11:02:57 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.0%
[2022-01-26 11:02:57 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.07%
[2022-01-26 11:03:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][0/1251]	eta 7:29:05 lr 0.000030	time 21.5388 (21.5388)	loss 3.4755 (3.4755)	grad_norm 2.5972 (2.5972)	
[2022-01-26 11:03:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][10/1251]	eta 1:26:04 lr 0.000030	time 3.0901 (4.1620)	loss 2.0348 (2.8759)	grad_norm 3.1292 (2.9732)	
[2022-01-26 11:04:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][20/1251]	eta 1:05:50 lr 0.000030	time 1.3031 (3.2089)	loss 3.3221 (2.9650)	grad_norm 2.8969 (2.9771)	
[2022-01-26 11:04:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][30/1251]	eta 1:00:19 lr 0.000030	time 1.5287 (2.9643)	loss 3.5092 (3.0379)	grad_norm 3.2923 (2.9873)	
[2022-01-26 11:04:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][40/1251]	eta 0:56:56 lr 0.000030	time 2.6940 (2.8210)	loss 3.5259 (3.0190)	grad_norm 2.8390 (2.9844)	
[2022-01-26 11:05:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][50/1251]	eta 0:53:42 lr 0.000030	time 2.5032 (2.6832)	loss 2.8753 (2.9823)	grad_norm 2.7389 (2.9418)	
[2022-01-26 11:05:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][60/1251]	eta 0:50:41 lr 0.000030	time 1.9641 (2.5539)	loss 3.4198 (3.0075)	grad_norm 2.5226 (2.9540)	
[2022-01-26 11:05:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][70/1251]	eta 0:48:32 lr 0.000030	time 1.9529 (2.4662)	loss 3.3260 (3.0080)	grad_norm 2.9134 (2.9752)	
[2022-01-26 11:06:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][80/1251]	eta 0:47:20 lr 0.000030	time 2.2550 (2.4253)	loss 3.3950 (3.0122)	grad_norm 3.3528 (2.9950)	
[2022-01-26 11:06:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][90/1251]	eta 0:46:45 lr 0.000030	time 3.1576 (2.4166)	loss 2.8077 (3.0169)	grad_norm 2.8418 (2.9999)	
[2022-01-26 11:06:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][100/1251]	eta 0:45:59 lr 0.000030	time 2.0017 (2.3977)	loss 2.6185 (2.9936)	grad_norm 3.4688 (2.9876)	
[2022-01-26 11:07:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][110/1251]	eta 0:45:13 lr 0.000030	time 2.4465 (2.3780)	loss 3.0034 (2.9938)	grad_norm 3.2385 (2.9954)	
[2022-01-26 11:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][120/1251]	eta 0:44:40 lr 0.000030	time 2.2009 (2.3700)	loss 3.3160 (3.0027)	grad_norm 3.3191 (2.9816)	
[2022-01-26 11:08:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][130/1251]	eta 0:43:55 lr 0.000030	time 2.3363 (2.3515)	loss 2.6389 (2.9776)	grad_norm 2.8018 (2.9708)	
[2022-01-26 11:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][140/1251]	eta 0:43:23 lr 0.000029	time 2.2346 (2.3434)	loss 2.1084 (2.9857)	grad_norm 3.1546 (2.9675)	
[2022-01-26 11:08:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][150/1251]	eta 0:42:52 lr 0.000029	time 2.4966 (2.3368)	loss 2.7908 (3.0003)	grad_norm 2.5820 (2.9827)	
[2022-01-26 11:09:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][160/1251]	eta 0:42:12 lr 0.000029	time 1.5939 (2.3212)	loss 2.3911 (2.9843)	grad_norm 3.3396 (2.9912)	
[2022-01-26 11:09:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][170/1251]	eta 0:41:34 lr 0.000029	time 2.1668 (2.3074)	loss 3.5189 (2.9861)	grad_norm 3.2281 (3.0050)	
[2022-01-26 11:09:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][180/1251]	eta 0:41:03 lr 0.000029	time 2.2295 (2.3001)	loss 2.4021 (2.9692)	grad_norm 3.6973 (3.0038)	
[2022-01-26 11:10:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][190/1251]	eta 0:40:40 lr 0.000029	time 2.9920 (2.3000)	loss 3.3719 (2.9676)	grad_norm 3.2110 (3.0142)	
[2022-01-26 11:10:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][200/1251]	eta 0:40:11 lr 0.000029	time 1.9891 (2.2946)	loss 3.6432 (2.9709)	grad_norm 3.0022 (3.0179)	
[2022-01-26 11:10:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][210/1251]	eta 0:39:39 lr 0.000029	time 2.2053 (2.2861)	loss 3.3309 (2.9802)	grad_norm 2.9400 (3.0218)	
[2022-01-26 11:11:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][220/1251]	eta 0:39:16 lr 0.000029	time 2.2062 (2.2859)	loss 3.4750 (2.9787)	grad_norm 3.2121 (3.0289)	
[2022-01-26 11:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][230/1251]	eta 0:38:51 lr 0.000029	time 2.8639 (2.2835)	loss 3.2066 (2.9778)	grad_norm 3.6174 (3.0484)	
[2022-01-26 11:12:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][240/1251]	eta 0:38:30 lr 0.000029	time 3.3725 (2.2858)	loss 2.4140 (2.9806)	grad_norm 3.2157 (3.0537)	
[2022-01-26 11:12:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][250/1251]	eta 0:38:01 lr 0.000029	time 1.8433 (2.2790)	loss 1.8951 (2.9715)	grad_norm 2.7745 (3.0529)	
[2022-01-26 11:12:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][260/1251]	eta 0:37:26 lr 0.000029	time 1.7204 (2.2674)	loss 3.6083 (2.9782)	grad_norm 2.9312 (3.0482)	
[2022-01-26 11:13:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][270/1251]	eta 0:36:57 lr 0.000029	time 1.6231 (2.2607)	loss 3.1119 (2.9912)	grad_norm 3.0264 (3.0463)	
[2022-01-26 11:13:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][280/1251]	eta 0:36:34 lr 0.000029	time 2.7080 (2.2596)	loss 2.8859 (2.9896)	grad_norm 2.5746 (3.0437)	
[2022-01-26 11:13:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][290/1251]	eta 0:36:06 lr 0.000029	time 2.1373 (2.2549)	loss 2.1665 (2.9838)	grad_norm 3.1871 (3.0444)	
[2022-01-26 11:14:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][300/1251]	eta 0:35:40 lr 0.000029	time 2.0964 (2.2513)	loss 3.4857 (2.9796)	grad_norm 2.8763 (3.0414)	
[2022-01-26 11:14:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][310/1251]	eta 0:35:14 lr 0.000029	time 2.4659 (2.2469)	loss 3.0903 (2.9869)	grad_norm 3.0365 (3.0390)	
[2022-01-26 11:14:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][320/1251]	eta 0:34:50 lr 0.000029	time 2.5578 (2.2452)	loss 2.7509 (2.9850)	grad_norm 2.9886 (3.0412)	
[2022-01-26 11:15:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][330/1251]	eta 0:34:29 lr 0.000029	time 2.4572 (2.2466)	loss 2.2501 (2.9793)	grad_norm 3.1890 (3.0375)	
[2022-01-26 11:15:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][340/1251]	eta 0:34:06 lr 0.000029	time 1.5086 (2.2469)	loss 3.0943 (2.9832)	grad_norm 3.7019 (3.0402)	
[2022-01-26 11:16:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][350/1251]	eta 0:33:43 lr 0.000029	time 2.1083 (2.2459)	loss 3.6447 (2.9850)	grad_norm 2.7539 (3.0390)	
[2022-01-26 11:16:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][360/1251]	eta 0:33:21 lr 0.000029	time 1.8450 (2.2463)	loss 1.9253 (2.9789)	grad_norm 2.8080 (3.0341)	
[2022-01-26 11:16:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][370/1251]	eta 0:32:57 lr 0.000029	time 2.4845 (2.2451)	loss 3.7039 (2.9780)	grad_norm 3.0041 (3.0376)	
[2022-01-26 11:17:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][380/1251]	eta 0:32:30 lr 0.000029	time 1.8401 (2.2390)	loss 3.5126 (2.9783)	grad_norm 3.4178 (3.0558)	
[2022-01-26 11:17:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][390/1251]	eta 0:32:05 lr 0.000029	time 2.8303 (2.2361)	loss 3.4204 (2.9836)	grad_norm 3.5229 (3.0627)	
[2022-01-26 11:17:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][400/1251]	eta 0:31:38 lr 0.000029	time 1.8738 (2.2311)	loss 3.1249 (2.9857)	grad_norm 3.1169 (3.0659)	
[2022-01-26 11:18:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][410/1251]	eta 0:31:18 lr 0.000029	time 3.0313 (2.2336)	loss 3.3349 (2.9872)	grad_norm 2.9206 (3.0666)	
[2022-01-26 11:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][420/1251]	eta 0:30:55 lr 0.000029	time 2.1165 (2.2330)	loss 2.4003 (2.9817)	grad_norm 3.2944 (3.0752)	
[2022-01-26 11:19:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][430/1251]	eta 0:30:37 lr 0.000029	time 3.4490 (2.2384)	loss 2.3156 (2.9777)	grad_norm 3.1757 (3.0733)	
[2022-01-26 11:19:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][440/1251]	eta 0:30:15 lr 0.000029	time 2.2284 (2.2382)	loss 3.1169 (2.9820)	grad_norm 3.0275 (3.0846)	
[2022-01-26 11:19:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][450/1251]	eta 0:29:50 lr 0.000029	time 1.8788 (2.2351)	loss 3.6543 (2.9804)	grad_norm 3.2952 (3.0839)	
[2022-01-26 11:20:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][460/1251]	eta 0:29:23 lr 0.000029	time 1.7114 (2.2295)	loss 3.5515 (2.9800)	grad_norm 3.0113 (3.0855)	
[2022-01-26 11:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][470/1251]	eta 0:29:00 lr 0.000029	time 2.7670 (2.2286)	loss 3.0201 (2.9802)	grad_norm 3.4944 (3.0837)	
[2022-01-26 11:20:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][480/1251]	eta 0:28:37 lr 0.000029	time 2.6308 (2.2276)	loss 2.1431 (2.9830)	grad_norm 3.3959 (3.0839)	
[2022-01-26 11:21:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][490/1251]	eta 0:28:14 lr 0.000029	time 1.8590 (2.2266)	loss 3.1593 (2.9824)	grad_norm 3.1610 (3.0803)	
[2022-01-26 11:21:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][500/1251]	eta 0:27:50 lr 0.000029	time 2.6464 (2.2246)	loss 2.6541 (2.9841)	grad_norm 2.7393 (3.0806)	
[2022-01-26 11:21:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][510/1251]	eta 0:27:28 lr 0.000029	time 2.2214 (2.2244)	loss 3.3709 (2.9887)	grad_norm 3.2648 (3.0816)	
[2022-01-26 11:22:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][520/1251]	eta 0:27:05 lr 0.000029	time 2.3146 (2.2231)	loss 3.4555 (2.9911)	grad_norm 3.1379 (3.0799)	
[2022-01-26 11:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][530/1251]	eta 0:26:39 lr 0.000029	time 1.6810 (2.2190)	loss 3.1817 (2.9874)	grad_norm 3.9445 (3.0837)	
[2022-01-26 11:22:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][540/1251]	eta 0:26:16 lr 0.000029	time 1.5932 (2.2180)	loss 3.3879 (2.9868)	grad_norm 2.9086 (3.0839)	
[2022-01-26 11:23:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][550/1251]	eta 0:25:52 lr 0.000029	time 2.0558 (2.2148)	loss 2.3325 (2.9880)	grad_norm 3.0681 (3.0897)	
[2022-01-26 11:23:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][560/1251]	eta 0:25:32 lr 0.000029	time 2.1660 (2.2173)	loss 3.6038 (2.9894)	grad_norm 2.9098 (3.0862)	
[2022-01-26 11:24:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][570/1251]	eta 0:25:12 lr 0.000029	time 2.4061 (2.2217)	loss 2.2540 (2.9837)	grad_norm 3.4458 (3.0856)	
[2022-01-26 11:24:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][580/1251]	eta 0:24:49 lr 0.000029	time 1.9049 (2.2198)	loss 2.9231 (2.9840)	grad_norm 2.7113 (3.0851)	
[2022-01-26 11:24:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][590/1251]	eta 0:24:26 lr 0.000029	time 1.9271 (2.2185)	loss 2.9139 (2.9862)	grad_norm 2.7794 (3.0837)	
[2022-01-26 11:25:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][600/1251]	eta 0:24:04 lr 0.000029	time 2.1672 (2.2186)	loss 3.4247 (2.9851)	grad_norm 3.4755 (3.0830)	
[2022-01-26 11:25:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][610/1251]	eta 0:23:40 lr 0.000029	time 1.5931 (2.2160)	loss 3.5186 (2.9890)	grad_norm 2.9819 (3.0824)	
[2022-01-26 11:25:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][620/1251]	eta 0:23:18 lr 0.000029	time 2.2519 (2.2159)	loss 2.5342 (2.9879)	grad_norm 3.8823 (3.0813)	
[2022-01-26 11:26:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][630/1251]	eta 0:22:54 lr 0.000029	time 1.9368 (2.2137)	loss 2.2314 (2.9880)	grad_norm 2.8391 (3.0821)	
[2022-01-26 11:26:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][640/1251]	eta 0:22:31 lr 0.000029	time 1.8477 (2.2124)	loss 3.2591 (2.9893)	grad_norm 2.9107 (3.0791)	
[2022-01-26 11:26:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][650/1251]	eta 0:22:09 lr 0.000029	time 1.9037 (2.2115)	loss 2.9569 (2.9929)	grad_norm 3.0243 (3.0777)	
[2022-01-26 11:27:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][660/1251]	eta 0:21:46 lr 0.000029	time 1.8947 (2.2103)	loss 2.8061 (2.9923)	grad_norm 2.9566 (3.0774)	
[2022-01-26 11:27:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][670/1251]	eta 0:21:22 lr 0.000029	time 1.5893 (2.2080)	loss 3.4169 (2.9939)	grad_norm 2.6433 (3.0767)	
[2022-01-26 11:27:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][680/1251]	eta 0:20:59 lr 0.000029	time 2.0236 (2.2058)	loss 3.2146 (2.9935)	grad_norm 3.1509 (3.0767)	
[2022-01-26 11:28:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][690/1251]	eta 0:20:38 lr 0.000029	time 2.1062 (2.2071)	loss 3.0956 (2.9909)	grad_norm 3.1676 (3.0735)	
[2022-01-26 11:28:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][700/1251]	eta 0:20:16 lr 0.000029	time 2.5414 (2.2082)	loss 2.7109 (2.9883)	grad_norm 2.7957 (3.0731)	
[2022-01-26 11:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][710/1251]	eta 0:19:55 lr 0.000029	time 2.9251 (2.2096)	loss 2.8010 (2.9906)	grad_norm 2.5946 (3.0741)	
[2022-01-26 11:29:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][720/1251]	eta 0:19:33 lr 0.000029	time 2.1352 (2.2099)	loss 3.1403 (2.9907)	grad_norm 3.1518 (3.0732)	
[2022-01-26 11:29:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][730/1251]	eta 0:19:11 lr 0.000029	time 1.5535 (2.2105)	loss 2.0329 (2.9914)	grad_norm 2.4184 (3.0724)	
[2022-01-26 11:30:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][740/1251]	eta 0:18:49 lr 0.000029	time 3.0563 (2.2103)	loss 2.6723 (2.9868)	grad_norm 2.7271 (3.0707)	
[2022-01-26 11:30:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][750/1251]	eta 0:18:27 lr 0.000029	time 2.8974 (2.2099)	loss 3.3564 (2.9877)	grad_norm 2.7506 (3.0706)	
[2022-01-26 11:30:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][760/1251]	eta 0:18:03 lr 0.000029	time 1.9030 (2.2066)	loss 1.9862 (2.9861)	grad_norm 3.2922 (3.0697)	
[2022-01-26 11:31:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][770/1251]	eta 0:17:40 lr 0.000029	time 1.9129 (2.2057)	loss 2.8226 (2.9833)	grad_norm 3.2311 (3.0692)	
[2022-01-26 11:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][780/1251]	eta 0:17:18 lr 0.000029	time 2.2511 (2.2044)	loss 2.1190 (2.9831)	grad_norm 2.7971 (3.0706)	
[2022-01-26 11:32:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][790/1251]	eta 0:16:56 lr 0.000029	time 2.2594 (2.2048)	loss 3.3907 (2.9864)	grad_norm 2.6676 (3.0682)	
[2022-01-26 11:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][800/1251]	eta 0:16:34 lr 0.000029	time 1.8896 (2.2042)	loss 3.2048 (2.9847)	grad_norm 2.8960 (3.0690)	
[2022-01-26 11:32:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][810/1251]	eta 0:16:12 lr 0.000029	time 2.3935 (2.2048)	loss 3.3302 (2.9831)	grad_norm 2.4536 (3.0721)	
[2022-01-26 11:33:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][820/1251]	eta 0:15:49 lr 0.000029	time 2.4590 (2.2036)	loss 3.5981 (2.9857)	grad_norm 3.3121 (3.0750)	
[2022-01-26 11:33:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][830/1251]	eta 0:15:28 lr 0.000029	time 2.8271 (2.2053)	loss 2.4351 (2.9844)	grad_norm 3.2564 (3.0753)	
[2022-01-26 11:33:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][840/1251]	eta 0:15:07 lr 0.000029	time 2.5332 (2.2074)	loss 3.5819 (2.9853)	grad_norm 2.5359 (3.0724)	
[2022-01-26 11:34:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][850/1251]	eta 0:14:45 lr 0.000029	time 2.0857 (2.2089)	loss 3.4482 (2.9865)	grad_norm 2.8155 (3.0714)	
[2022-01-26 11:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][860/1251]	eta 0:14:23 lr 0.000029	time 2.2074 (2.2080)	loss 3.5870 (2.9877)	grad_norm 3.0543 (3.0718)	
[2022-01-26 11:34:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][870/1251]	eta 0:13:59 lr 0.000029	time 1.5994 (2.2044)	loss 2.7685 (2.9893)	grad_norm 2.9884 (3.0716)	
[2022-01-26 11:35:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][880/1251]	eta 0:13:36 lr 0.000029	time 1.8928 (2.2014)	loss 3.4625 (2.9917)	grad_norm 2.9721 (3.0731)	
[2022-01-26 11:35:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][890/1251]	eta 0:13:14 lr 0.000029	time 2.0528 (2.1999)	loss 2.2071 (2.9932)	grad_norm 3.1916 (3.0744)	
[2022-01-26 11:36:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][900/1251]	eta 0:12:52 lr 0.000029	time 2.4257 (2.2008)	loss 2.8752 (2.9942)	grad_norm 2.5898 (3.0732)	
[2022-01-26 11:36:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][910/1251]	eta 0:12:30 lr 0.000029	time 2.5174 (2.2002)	loss 2.9015 (2.9943)	grad_norm 2.5517 (3.0739)	
[2022-01-26 11:36:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][920/1251]	eta 0:12:08 lr 0.000029	time 2.0280 (2.2007)	loss 3.2950 (2.9944)	grad_norm 3.5941 (3.0746)	
[2022-01-26 11:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][930/1251]	eta 0:11:46 lr 0.000029	time 1.7584 (2.2013)	loss 2.9590 (2.9939)	grad_norm 3.6187 (3.0744)	
[2022-01-26 11:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][940/1251]	eta 0:11:25 lr 0.000029	time 1.6369 (2.2043)	loss 3.2589 (2.9944)	grad_norm 3.1356 (3.0738)	
[2022-01-26 11:37:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][950/1251]	eta 0:11:04 lr 0.000029	time 2.4800 (2.2071)	loss 3.2142 (2.9966)	grad_norm 3.1724 (3.0731)	
[2022-01-26 11:38:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][960/1251]	eta 0:10:41 lr 0.000029	time 1.9880 (2.2061)	loss 3.0742 (2.9941)	grad_norm 2.9872 (3.0735)	
[2022-01-26 11:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][970/1251]	eta 0:10:19 lr 0.000029	time 1.9836 (2.2042)	loss 2.8885 (2.9919)	grad_norm 3.3416 (3.0729)	
[2022-01-26 11:38:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][980/1251]	eta 0:09:56 lr 0.000029	time 1.8866 (2.2013)	loss 3.6748 (2.9949)	grad_norm 2.8089 (3.0715)	
[2022-01-26 11:39:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][990/1251]	eta 0:09:33 lr 0.000029	time 1.9371 (2.1982)	loss 3.2433 (2.9954)	grad_norm 4.2060 (3.0743)	
[2022-01-26 11:39:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1000/1251]	eta 0:09:11 lr 0.000029	time 2.3844 (2.1967)	loss 2.9276 (2.9961)	grad_norm 3.6993 (3.0742)	
[2022-01-26 11:39:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1010/1251]	eta 0:08:49 lr 0.000029	time 5.0687 (2.1982)	loss 2.9715 (2.9970)	grad_norm 2.9949 (3.0745)	
[2022-01-26 11:40:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1020/1251]	eta 0:08:28 lr 0.000028	time 2.6726 (2.2025)	loss 3.2731 (2.9960)	grad_norm 2.7242 (3.0790)	
[2022-01-26 11:40:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1030/1251]	eta 0:08:06 lr 0.000028	time 2.2005 (2.2036)	loss 3.0928 (2.9941)	grad_norm 3.1315 (3.0795)	
[2022-01-26 11:41:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1040/1251]	eta 0:07:44 lr 0.000028	time 2.8542 (2.2036)	loss 2.5968 (2.9934)	grad_norm 3.1572 (3.0783)	
[2022-01-26 11:41:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1050/1251]	eta 0:07:22 lr 0.000028	time 2.5212 (2.2028)	loss 3.0796 (2.9939)	grad_norm 2.9225 (3.0777)	
[2022-01-26 11:41:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1060/1251]	eta 0:07:00 lr 0.000028	time 1.9165 (2.2009)	loss 2.5422 (2.9950)	grad_norm 3.6221 (3.0772)	
[2022-01-26 11:42:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1070/1251]	eta 0:06:38 lr 0.000028	time 2.8142 (2.1999)	loss 2.9011 (2.9933)	grad_norm 3.5341 (3.0802)	
[2022-01-26 11:42:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1080/1251]	eta 0:06:15 lr 0.000028	time 2.6050 (2.1986)	loss 3.4514 (2.9954)	grad_norm 4.1698 (3.0857)	
[2022-01-26 11:42:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1090/1251]	eta 0:05:53 lr 0.000028	time 2.6191 (2.1975)	loss 3.6783 (2.9957)	grad_norm 3.2197 (3.0884)	
[2022-01-26 11:43:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1100/1251]	eta 0:05:31 lr 0.000028	time 2.2410 (2.1959)	loss 3.3725 (2.9967)	grad_norm 3.1263 (3.0884)	
[2022-01-26 11:43:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1110/1251]	eta 0:05:09 lr 0.000028	time 3.1640 (2.1967)	loss 3.2634 (2.9952)	grad_norm 2.7870 (3.0867)	
[2022-01-26 11:43:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1120/1251]	eta 0:04:47 lr 0.000028	time 2.2918 (2.1965)	loss 2.2846 (2.9927)	grad_norm 3.0009 (3.0852)	
[2022-01-26 11:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1130/1251]	eta 0:04:25 lr 0.000028	time 2.2927 (2.1972)	loss 3.1944 (2.9932)	grad_norm 2.8662 (3.0840)	
[2022-01-26 11:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1140/1251]	eta 0:04:03 lr 0.000028	time 2.7317 (2.1982)	loss 3.0767 (2.9956)	grad_norm 3.2739 (3.0858)	
[2022-01-26 11:45:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1150/1251]	eta 0:03:42 lr 0.000028	time 2.2719 (2.1986)	loss 3.0539 (2.9938)	grad_norm 3.4508 (3.0861)	
[2022-01-26 11:45:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1160/1251]	eta 0:03:19 lr 0.000028	time 2.1006 (2.1970)	loss 3.2920 (2.9952)	grad_norm 2.9842 (3.0852)	
[2022-01-26 11:45:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1170/1251]	eta 0:02:57 lr 0.000028	time 1.8484 (2.1956)	loss 2.8351 (2.9950)	grad_norm 2.6362 (3.0841)	
[2022-01-26 11:46:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1180/1251]	eta 0:02:35 lr 0.000028	time 2.5232 (2.1961)	loss 2.4542 (2.9960)	grad_norm 3.2268 (3.0835)	
[2022-01-26 11:46:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1190/1251]	eta 0:02:13 lr 0.000028	time 1.8186 (2.1962)	loss 2.4811 (2.9948)	grad_norm 2.8650 (3.0848)	
[2022-01-26 11:46:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1200/1251]	eta 0:01:52 lr 0.000028	time 3.2807 (2.1981)	loss 3.5080 (2.9962)	grad_norm 3.4644 (3.0855)	
[2022-01-26 11:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1210/1251]	eta 0:01:30 lr 0.000028	time 1.8784 (2.1982)	loss 2.9351 (2.9968)	grad_norm 3.9355 (3.0863)	
[2022-01-26 11:47:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1220/1251]	eta 0:01:08 lr 0.000028	time 1.8854 (2.1986)	loss 2.3555 (2.9968)	grad_norm 2.7058 (3.0862)	
[2022-01-26 11:48:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1230/1251]	eta 0:00:46 lr 0.000028	time 1.8610 (2.1976)	loss 2.9887 (2.9971)	grad_norm 3.1064 (3.0872)	
[2022-01-26 11:48:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1240/1251]	eta 0:00:24 lr 0.000028	time 2.5881 (2.1974)	loss 2.8959 (2.9978)	grad_norm 2.8867 (3.0868)	
[2022-01-26 11:48:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [273/300][1250/1251]	eta 0:00:02 lr 0.000028	time 1.2165 (2.1915)	loss 3.4568 (3.0001)	grad_norm 2.6816 (3.0857)	
[2022-01-26 11:48:39 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 273 training takes 0:45:42
[2022-01-26 11:48:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.533 (18.533)	Loss 0.9255 (0.9255)	Acc@1 78.223 (78.223)	Acc@5 94.434 (94.434)	
[2022-01-26 11:49:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.911 (3.622)	Loss 0.8438 (0.8289)	Acc@1 80.273 (80.895)	Acc@5 94.238 (95.046)	
[2022-01-26 11:49:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.266 (2.569)	Loss 0.8231 (0.8204)	Acc@1 81.055 (80.971)	Acc@5 94.434 (95.168)	
[2022-01-26 11:49:51 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.311 (2.326)	Loss 0.8427 (0.8171)	Acc@1 79.883 (81.007)	Acc@5 95.117 (95.319)	
[2022-01-26 11:50:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.038 (2.156)	Loss 0.8627 (0.8168)	Acc@1 79.883 (80.909)	Acc@5 94.629 (95.312)	
[2022-01-26 11:50:15 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.986 Acc@5 95.366
[2022-01-26 11:50:15 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.0%
[2022-01-26 11:50:15 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.07%
[2022-01-26 11:50:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][0/1251]	eta 7:27:13 lr 0.000028	time 21.4495 (21.4495)	loss 3.5361 (3.5361)	grad_norm 2.8465 (2.8465)	
[2022-01-26 11:51:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][10/1251]	eta 1:25:18 lr 0.000028	time 2.1305 (4.1243)	loss 3.0983 (2.8831)	grad_norm 2.7064 (2.8594)	
[2022-01-26 11:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][20/1251]	eta 1:05:15 lr 0.000028	time 1.5807 (3.1811)	loss 3.7746 (2.8970)	grad_norm 3.0950 (2.9886)	
[2022-01-26 11:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][30/1251]	eta 0:57:40 lr 0.000028	time 1.7488 (2.8345)	loss 2.5330 (2.9120)	grad_norm 3.3668 (3.0631)	
[2022-01-26 11:52:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][40/1251]	eta 0:54:38 lr 0.000028	time 3.9830 (2.7073)	loss 2.6641 (2.8492)	grad_norm 2.7224 (3.0465)	
[2022-01-26 11:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][50/1251]	eta 0:52:10 lr 0.000028	time 2.1914 (2.6067)	loss 3.1331 (2.9121)	grad_norm 2.8636 (3.0320)	
[2022-01-26 11:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][60/1251]	eta 0:50:07 lr 0.000028	time 2.1925 (2.5253)	loss 3.1451 (2.9189)	grad_norm 3.1013 (3.0526)	
[2022-01-26 11:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][70/1251]	eta 0:48:46 lr 0.000028	time 2.1196 (2.4783)	loss 2.9460 (2.9121)	grad_norm 3.3679 (3.0914)	
[2022-01-26 11:53:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][80/1251]	eta 0:47:45 lr 0.000028	time 3.4888 (2.4471)	loss 3.0228 (2.8887)	grad_norm 2.8088 (3.0690)	
[2022-01-26 11:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][90/1251]	eta 0:46:55 lr 0.000028	time 1.5630 (2.4250)	loss 3.0894 (2.9015)	grad_norm 3.3134 (3.0656)	
[2022-01-26 11:54:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][100/1251]	eta 0:45:53 lr 0.000028	time 2.3205 (2.3921)	loss 3.2552 (2.9250)	grad_norm 2.9114 (3.0659)	
[2022-01-26 11:54:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][110/1251]	eta 0:45:16 lr 0.000028	time 2.5049 (2.3809)	loss 2.6831 (2.9269)	grad_norm 3.1814 (3.0419)	
[2022-01-26 11:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][120/1251]	eta 0:44:39 lr 0.000028	time 2.7852 (2.3695)	loss 2.2827 (2.9255)	grad_norm 4.1371 (3.0494)	
[2022-01-26 11:55:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][130/1251]	eta 0:44:05 lr 0.000028	time 2.2541 (2.3599)	loss 3.3506 (2.8975)	grad_norm 3.6006 (3.0552)	
[2022-01-26 11:55:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][140/1251]	eta 0:43:21 lr 0.000028	time 2.5686 (2.3412)	loss 2.9494 (2.9028)	grad_norm 2.5520 (3.0403)	
[2022-01-26 11:56:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][150/1251]	eta 0:42:41 lr 0.000028	time 2.1445 (2.3263)	loss 3.3915 (2.9080)	grad_norm 2.7403 (3.0483)	
[2022-01-26 11:56:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][160/1251]	eta 0:42:20 lr 0.000028	time 3.2876 (2.3289)	loss 2.8000 (2.9145)	grad_norm 2.6680 (3.0550)	
[2022-01-26 11:56:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][170/1251]	eta 0:41:59 lr 0.000028	time 1.7588 (2.3306)	loss 2.9452 (2.9048)	grad_norm 3.5135 (3.0543)	
[2022-01-26 11:57:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][180/1251]	eta 0:41:32 lr 0.000028	time 2.2881 (2.3277)	loss 2.3837 (2.8920)	grad_norm 3.2844 (3.0615)	
[2022-01-26 11:57:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][190/1251]	eta 0:40:55 lr 0.000028	time 1.9582 (2.3144)	loss 3.3631 (2.9046)	grad_norm 3.1526 (3.0775)	
[2022-01-26 11:57:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][200/1251]	eta 0:40:20 lr 0.000028	time 2.5645 (2.3027)	loss 3.2228 (2.9110)	grad_norm 2.6959 (3.0803)	
[2022-01-26 11:58:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][210/1251]	eta 0:39:41 lr 0.000028	time 1.9244 (2.2874)	loss 3.7309 (2.9155)	grad_norm 3.0754 (3.0763)	
[2022-01-26 11:58:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][220/1251]	eta 0:39:11 lr 0.000028	time 2.7236 (2.2812)	loss 2.1826 (2.9232)	grad_norm 2.4975 (3.0685)	
[2022-01-26 11:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][230/1251]	eta 0:38:44 lr 0.000028	time 2.4895 (2.2764)	loss 2.6120 (2.9229)	grad_norm 3.5407 (3.0654)	
[2022-01-26 11:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][240/1251]	eta 0:38:21 lr 0.000028	time 2.6666 (2.2766)	loss 2.8536 (2.9280)	grad_norm 3.2004 (3.1149)	
[2022-01-26 11:59:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][250/1251]	eta 0:38:02 lr 0.000028	time 2.8845 (2.2805)	loss 3.0842 (2.9346)	grad_norm 2.7872 (3.1122)	
[2022-01-26 12:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][260/1251]	eta 0:37:38 lr 0.000028	time 2.7866 (2.2795)	loss 2.1677 (2.9257)	grad_norm 2.9289 (3.1136)	
[2022-01-26 12:00:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][270/1251]	eta 0:37:09 lr 0.000028	time 2.1922 (2.2723)	loss 2.9853 (2.9278)	grad_norm 3.1241 (3.1089)	
[2022-01-26 12:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][280/1251]	eta 0:36:38 lr 0.000028	time 2.5186 (2.2644)	loss 2.4682 (2.9251)	grad_norm 2.6271 (3.1014)	
[2022-01-26 12:01:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][290/1251]	eta 0:36:09 lr 0.000028	time 2.1322 (2.2578)	loss 3.0651 (2.9278)	grad_norm 3.0608 (3.0956)	
[2022-01-26 12:01:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][300/1251]	eta 0:35:50 lr 0.000028	time 2.8823 (2.2612)	loss 3.5624 (2.9331)	grad_norm 2.7192 (3.0944)	
[2022-01-26 12:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][310/1251]	eta 0:35:30 lr 0.000028	time 1.6138 (2.2644)	loss 2.0470 (2.9292)	grad_norm 2.9323 (3.0909)	
[2022-01-26 12:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][320/1251]	eta 0:35:09 lr 0.000028	time 1.8781 (2.2657)	loss 2.2428 (2.9415)	grad_norm 2.7374 (3.0951)	
[2022-01-26 12:02:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][330/1251]	eta 0:34:42 lr 0.000028	time 2.1932 (2.2609)	loss 2.8453 (2.9450)	grad_norm 3.2119 (3.0937)	
[2022-01-26 12:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][340/1251]	eta 0:34:13 lr 0.000028	time 1.8255 (2.2538)	loss 3.3920 (2.9469)	grad_norm 2.7291 (3.0857)	
[2022-01-26 12:03:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][350/1251]	eta 0:33:46 lr 0.000028	time 1.5815 (2.2491)	loss 3.0594 (2.9546)	grad_norm 2.8512 (3.0846)	
[2022-01-26 12:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][360/1251]	eta 0:33:22 lr 0.000028	time 2.2552 (2.2475)	loss 3.4631 (2.9606)	grad_norm 2.6356 (3.0846)	
[2022-01-26 12:04:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][370/1251]	eta 0:33:00 lr 0.000028	time 1.8900 (2.2479)	loss 1.8979 (2.9602)	grad_norm 3.2188 (3.0824)	
[2022-01-26 12:04:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][380/1251]	eta 0:32:37 lr 0.000028	time 2.3635 (2.2469)	loss 3.3968 (2.9638)	grad_norm 2.9465 (3.0911)	
[2022-01-26 12:04:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][390/1251]	eta 0:32:12 lr 0.000028	time 1.8078 (2.2450)	loss 2.7450 (2.9687)	grad_norm 2.6791 (3.0937)	
[2022-01-26 12:05:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][400/1251]	eta 0:31:47 lr 0.000028	time 1.8846 (2.2411)	loss 2.9415 (2.9718)	grad_norm 2.8637 (3.0940)	
[2022-01-26 12:05:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][410/1251]	eta 0:31:23 lr 0.000028	time 1.9183 (2.2390)	loss 2.4147 (2.9760)	grad_norm 4.0715 (3.0991)	
[2022-01-26 12:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][420/1251]	eta 0:30:57 lr 0.000028	time 2.6375 (2.2354)	loss 3.2398 (2.9785)	grad_norm 3.0775 (3.1025)	
[2022-01-26 12:06:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][430/1251]	eta 0:30:33 lr 0.000028	time 2.4807 (2.2336)	loss 3.3908 (2.9742)	grad_norm 2.8383 (3.1047)	
[2022-01-26 12:06:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][440/1251]	eta 0:30:10 lr 0.000028	time 2.1320 (2.2328)	loss 3.6569 (2.9786)	grad_norm 2.8282 (3.1052)	
[2022-01-26 12:07:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][450/1251]	eta 0:29:51 lr 0.000028	time 2.6279 (2.2366)	loss 1.9913 (2.9780)	grad_norm 2.6215 (3.1029)	
[2022-01-26 12:07:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][460/1251]	eta 0:29:28 lr 0.000028	time 2.3089 (2.2356)	loss 3.3484 (2.9785)	grad_norm 2.8277 (3.0991)	
[2022-01-26 12:07:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][470/1251]	eta 0:29:10 lr 0.000028	time 1.4581 (2.2418)	loss 3.2463 (2.9808)	grad_norm 2.9738 (3.0974)	
[2022-01-26 12:08:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][480/1251]	eta 0:28:44 lr 0.000028	time 1.9201 (2.2368)	loss 3.2734 (2.9801)	grad_norm 2.9633 (3.0963)	
[2022-01-26 12:08:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][490/1251]	eta 0:28:21 lr 0.000028	time 1.9220 (2.2362)	loss 3.5661 (2.9832)	grad_norm 2.7344 (3.0934)	
[2022-01-26 12:08:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][500/1251]	eta 0:27:57 lr 0.000028	time 1.7640 (2.2337)	loss 2.9267 (2.9857)	grad_norm 2.6003 (3.0935)	
[2022-01-26 12:09:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][510/1251]	eta 0:27:35 lr 0.000028	time 1.8488 (2.2341)	loss 2.2158 (2.9859)	grad_norm 3.4326 (3.1004)	
[2022-01-26 12:09:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][520/1251]	eta 0:27:14 lr 0.000028	time 2.1378 (2.2364)	loss 2.5563 (2.9841)	grad_norm 3.0503 (3.1011)	
[2022-01-26 12:10:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][530/1251]	eta 0:26:51 lr 0.000028	time 1.8895 (2.2357)	loss 3.1581 (2.9826)	grad_norm 2.8404 (3.1016)	
[2022-01-26 12:10:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][540/1251]	eta 0:26:26 lr 0.000028	time 2.1754 (2.2307)	loss 2.4107 (2.9833)	grad_norm 2.7446 (3.0990)	
[2022-01-26 12:10:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][550/1251]	eta 0:26:02 lr 0.000028	time 2.2615 (2.2290)	loss 2.3907 (2.9853)	grad_norm 3.7193 (3.0981)	
[2022-01-26 12:11:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][560/1251]	eta 0:25:39 lr 0.000028	time 2.1019 (2.2284)	loss 3.0009 (2.9824)	grad_norm 3.5016 (3.0994)	
[2022-01-26 12:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][570/1251]	eta 0:25:19 lr 0.000028	time 2.0318 (2.2312)	loss 3.7697 (2.9833)	grad_norm 3.4876 (3.1000)	
[2022-01-26 12:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][580/1251]	eta 0:24:56 lr 0.000028	time 1.5583 (2.2306)	loss 3.3429 (2.9851)	grad_norm 3.4162 (3.0964)	
[2022-01-26 12:12:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][590/1251]	eta 0:24:33 lr 0.000028	time 1.7339 (2.2286)	loss 3.6060 (2.9874)	grad_norm 2.9039 (3.0983)	
[2022-01-26 12:12:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][600/1251]	eta 0:24:08 lr 0.000028	time 1.9521 (2.2256)	loss 3.0138 (2.9842)	grad_norm 3.3383 (3.1025)	
[2022-01-26 12:12:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][610/1251]	eta 0:23:46 lr 0.000028	time 2.4565 (2.2258)	loss 3.7161 (2.9852)	grad_norm 3.0824 (3.1036)	
[2022-01-26 12:13:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][620/1251]	eta 0:23:23 lr 0.000028	time 1.9252 (2.2239)	loss 3.3369 (2.9861)	grad_norm 3.1027 (3.1048)	
[2022-01-26 12:13:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][630/1251]	eta 0:23:01 lr 0.000028	time 1.8707 (2.2247)	loss 3.5204 (2.9901)	grad_norm 3.0960 (3.1102)	
[2022-01-26 12:14:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][640/1251]	eta 0:22:39 lr 0.000028	time 1.8145 (2.2246)	loss 3.3803 (2.9883)	grad_norm 2.8570 (3.1106)	
[2022-01-26 12:14:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][650/1251]	eta 0:22:17 lr 0.000028	time 1.8746 (2.2261)	loss 3.4289 (2.9867)	grad_norm 3.1950 (3.1097)	
[2022-01-26 12:14:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][660/1251]	eta 0:21:55 lr 0.000028	time 1.8644 (2.2253)	loss 2.5070 (2.9886)	grad_norm 3.0959 (3.1100)	
[2022-01-26 12:15:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][670/1251]	eta 0:21:31 lr 0.000027	time 1.9256 (2.2230)	loss 3.4706 (2.9885)	grad_norm 2.9260 (3.1115)	
[2022-01-26 12:15:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][680/1251]	eta 0:21:07 lr 0.000027	time 1.9058 (2.2203)	loss 2.6389 (2.9903)	grad_norm 3.2019 (3.1114)	
[2022-01-26 12:15:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][690/1251]	eta 0:20:45 lr 0.000027	time 1.6626 (2.2201)	loss 1.7729 (2.9892)	grad_norm 2.5019 (3.1081)	
[2022-01-26 12:16:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][700/1251]	eta 0:20:23 lr 0.000027	time 1.8977 (2.2199)	loss 3.3481 (2.9887)	grad_norm 2.9821 (3.1111)	
[2022-01-26 12:16:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][710/1251]	eta 0:20:00 lr 0.000027	time 2.6856 (2.2192)	loss 3.0246 (2.9875)	grad_norm 2.5718 (3.1095)	
[2022-01-26 12:16:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][720/1251]	eta 0:19:37 lr 0.000027	time 1.9511 (2.2183)	loss 3.0058 (2.9911)	grad_norm 3.3202 (3.1098)	
[2022-01-26 12:17:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][730/1251]	eta 0:19:15 lr 0.000027	time 1.8920 (2.2183)	loss 3.4077 (2.9949)	grad_norm 2.9688 (3.1084)	
[2022-01-26 12:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][740/1251]	eta 0:18:53 lr 0.000027	time 2.2366 (2.2187)	loss 3.5593 (2.9944)	grad_norm 3.1165 (3.1091)	
[2022-01-26 12:18:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][750/1251]	eta 0:18:30 lr 0.000027	time 1.6158 (2.2169)	loss 3.4493 (2.9970)	grad_norm 2.7730 (3.1084)	
[2022-01-26 12:18:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][760/1251]	eta 0:18:08 lr 0.000027	time 2.0703 (2.2162)	loss 3.2671 (2.9987)	grad_norm 2.8698 (3.1075)	
[2022-01-26 12:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][770/1251]	eta 0:17:46 lr 0.000027	time 1.8535 (2.2178)	loss 3.3064 (3.0009)	grad_norm 2.7288 (3.1068)	
[2022-01-26 12:19:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][780/1251]	eta 0:17:24 lr 0.000027	time 2.1294 (2.2167)	loss 3.0712 (2.9991)	grad_norm 3.4214 (3.1075)	
[2022-01-26 12:19:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][790/1251]	eta 0:17:01 lr 0.000027	time 1.5793 (2.2162)	loss 3.5617 (3.0016)	grad_norm 3.5018 (3.1072)	
[2022-01-26 12:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][800/1251]	eta 0:16:39 lr 0.000027	time 3.1069 (2.2172)	loss 3.2331 (3.0021)	grad_norm 2.7249 (3.1041)	
[2022-01-26 12:20:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][810/1251]	eta 0:16:17 lr 0.000027	time 2.0732 (2.2160)	loss 3.4608 (3.0045)	grad_norm 3.1015 (3.1040)	
[2022-01-26 12:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][820/1251]	eta 0:15:54 lr 0.000027	time 2.4581 (2.2147)	loss 3.5044 (3.0052)	grad_norm 2.9436 (3.1040)	
[2022-01-26 12:20:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][830/1251]	eta 0:15:32 lr 0.000027	time 1.9320 (2.2147)	loss 3.4330 (3.0065)	grad_norm 2.6461 (3.1021)	
[2022-01-26 12:21:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][840/1251]	eta 0:15:09 lr 0.000027	time 2.6277 (2.2128)	loss 3.5391 (3.0060)	grad_norm 3.6391 (3.1014)	
[2022-01-26 12:21:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][850/1251]	eta 0:14:47 lr 0.000027	time 1.9035 (2.2124)	loss 2.0437 (3.0051)	grad_norm 2.5531 (3.1006)	
[2022-01-26 12:21:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][860/1251]	eta 0:14:24 lr 0.000027	time 1.9071 (2.2116)	loss 3.4197 (3.0063)	grad_norm 2.7134 (3.1003)	
[2022-01-26 12:22:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][870/1251]	eta 0:14:02 lr 0.000027	time 1.8912 (2.2121)	loss 2.1449 (3.0074)	grad_norm 3.7773 (3.0990)	
[2022-01-26 12:22:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][880/1251]	eta 0:13:40 lr 0.000027	time 2.3235 (2.2120)	loss 3.5513 (3.0066)	grad_norm 3.2657 (3.1001)	
[2022-01-26 12:23:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][890/1251]	eta 0:13:18 lr 0.000027	time 1.8307 (2.2111)	loss 3.2577 (3.0061)	grad_norm 3.1378 (3.0993)	
[2022-01-26 12:23:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][900/1251]	eta 0:12:56 lr 0.000027	time 1.9691 (2.2115)	loss 2.6974 (3.0059)	grad_norm 3.3276 (3.1000)	
[2022-01-26 12:23:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][910/1251]	eta 0:12:33 lr 0.000027	time 1.8875 (2.2106)	loss 3.2801 (3.0073)	grad_norm 2.8280 (3.0980)	
[2022-01-26 12:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][920/1251]	eta 0:12:11 lr 0.000027	time 1.5946 (2.2097)	loss 3.5122 (3.0085)	grad_norm 3.3266 (3.0975)	
[2022-01-26 12:24:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][930/1251]	eta 0:11:49 lr 0.000027	time 2.8032 (2.2090)	loss 3.2352 (3.0097)	grad_norm 3.1940 (3.0993)	
[2022-01-26 12:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][940/1251]	eta 0:11:26 lr 0.000027	time 1.6445 (2.2089)	loss 2.9225 (3.0091)	grad_norm 4.0308 (3.0991)	
[2022-01-26 12:25:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][950/1251]	eta 0:11:04 lr 0.000027	time 1.5135 (2.2085)	loss 3.1494 (3.0097)	grad_norm 3.3465 (3.0990)	
[2022-01-26 12:25:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][960/1251]	eta 0:10:42 lr 0.000027	time 1.5338 (2.2081)	loss 3.3665 (3.0087)	grad_norm 3.2981 (3.1009)	
[2022-01-26 12:25:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][970/1251]	eta 0:10:20 lr 0.000027	time 2.5861 (2.2084)	loss 2.5906 (3.0089)	grad_norm 3.6332 (3.1024)	
[2022-01-26 12:26:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][980/1251]	eta 0:09:58 lr 0.000027	time 1.8263 (2.2100)	loss 3.5647 (3.0093)	grad_norm 2.8244 (3.1015)	
[2022-01-26 12:26:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][990/1251]	eta 0:09:37 lr 0.000027	time 2.8390 (2.2117)	loss 1.9333 (3.0078)	grad_norm 2.6786 (3.1011)	
[2022-01-26 12:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1000/1251]	eta 0:09:14 lr 0.000027	time 1.8603 (2.2108)	loss 3.0837 (3.0077)	grad_norm 2.5725 (3.0990)	
[2022-01-26 12:27:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1010/1251]	eta 0:08:52 lr 0.000027	time 2.4075 (2.2111)	loss 3.6344 (3.0071)	grad_norm 4.0815 (3.0993)	
[2022-01-26 12:27:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1020/1251]	eta 0:08:30 lr 0.000027	time 1.4887 (2.2097)	loss 3.0626 (3.0061)	grad_norm 3.0402 (3.0971)	
[2022-01-26 12:28:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1030/1251]	eta 0:08:07 lr 0.000027	time 1.6416 (2.2077)	loss 3.4737 (3.0067)	grad_norm 2.8760 (3.0960)	
[2022-01-26 12:28:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1040/1251]	eta 0:07:45 lr 0.000027	time 2.0703 (2.2065)	loss 3.5547 (3.0090)	grad_norm 2.9165 (3.0962)	
[2022-01-26 12:28:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1050/1251]	eta 0:07:23 lr 0.000027	time 2.2813 (2.2058)	loss 3.4449 (3.0093)	grad_norm 2.7994 (3.0946)	
[2022-01-26 12:29:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1060/1251]	eta 0:07:01 lr 0.000027	time 2.1879 (2.2050)	loss 3.1041 (3.0087)	grad_norm 2.9550 (3.0951)	
[2022-01-26 12:29:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1070/1251]	eta 0:06:39 lr 0.000027	time 2.4777 (2.2051)	loss 2.8355 (3.0100)	grad_norm 2.5840 (3.0991)	
[2022-01-26 12:29:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1080/1251]	eta 0:06:17 lr 0.000027	time 2.1178 (2.2058)	loss 3.3340 (3.0073)	grad_norm 2.8450 (3.0984)	
[2022-01-26 12:30:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1090/1251]	eta 0:05:55 lr 0.000027	time 2.3425 (2.2055)	loss 3.4654 (3.0077)	grad_norm 3.0231 (3.0962)	
[2022-01-26 12:30:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1100/1251]	eta 0:05:33 lr 0.000027	time 1.8794 (2.2054)	loss 2.1339 (3.0039)	grad_norm 3.8511 (3.0958)	
[2022-01-26 12:31:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1110/1251]	eta 0:05:11 lr 0.000027	time 2.3157 (2.2061)	loss 2.1283 (3.0022)	grad_norm 2.7708 (3.0952)	
[2022-01-26 12:31:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1120/1251]	eta 0:04:49 lr 0.000027	time 2.4555 (2.2076)	loss 2.2885 (3.0018)	grad_norm 3.1163 (3.0949)	
[2022-01-26 12:31:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1130/1251]	eta 0:04:27 lr 0.000027	time 2.2495 (2.2068)	loss 3.3720 (3.0026)	grad_norm 2.9564 (3.0943)	
[2022-01-26 12:32:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1140/1251]	eta 0:04:04 lr 0.000027	time 1.8817 (2.2052)	loss 2.3691 (3.0019)	grad_norm 2.6450 (3.0953)	
[2022-01-26 12:32:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1150/1251]	eta 0:03:42 lr 0.000027	time 2.2616 (2.2044)	loss 1.9013 (3.0004)	grad_norm 2.9070 (3.0972)	
[2022-01-26 12:32:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1160/1251]	eta 0:03:20 lr 0.000027	time 3.4824 (2.2044)	loss 3.2721 (3.0013)	grad_norm 2.8587 (3.0962)	
[2022-01-26 12:33:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1170/1251]	eta 0:02:58 lr 0.000027	time 2.9115 (2.2053)	loss 3.4490 (3.0013)	grad_norm 2.8537 (3.0953)	
[2022-01-26 12:33:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1180/1251]	eta 0:02:36 lr 0.000027	time 2.5266 (2.2053)	loss 2.0595 (3.0001)	grad_norm 3.2088 (3.0958)	
[2022-01-26 12:34:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1190/1251]	eta 0:02:14 lr 0.000027	time 2.2309 (2.2062)	loss 3.7402 (3.0012)	grad_norm 3.2045 (3.1011)	
[2022-01-26 12:34:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1200/1251]	eta 0:01:52 lr 0.000027	time 2.0610 (2.2053)	loss 3.0790 (3.0004)	grad_norm 3.0407 (3.1011)	
[2022-01-26 12:34:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1210/1251]	eta 0:01:30 lr 0.000027	time 3.1521 (2.2058)	loss 3.3128 (3.0009)	grad_norm 2.9059 (3.1016)	
[2022-01-26 12:35:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1220/1251]	eta 0:01:08 lr 0.000027	time 1.5827 (2.2063)	loss 3.7075 (3.0023)	grad_norm 3.0070 (3.1016)	
[2022-01-26 12:35:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1230/1251]	eta 0:00:46 lr 0.000027	time 1.9268 (2.2067)	loss 2.8862 (3.0028)	grad_norm 2.6082 (3.1007)	
[2022-01-26 12:35:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1240/1251]	eta 0:00:24 lr 0.000027	time 1.2141 (2.2051)	loss 3.4332 (3.0047)	grad_norm 2.8874 (3.1008)	
[2022-01-26 12:36:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [274/300][1250/1251]	eta 0:00:02 lr 0.000027	time 1.2101 (2.1990)	loss 2.8984 (3.0040)	grad_norm 2.8171 (3.1007)	
[2022-01-26 12:36:06 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 274 training takes 0:45:51
[2022-01-26 12:36:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.184 (18.184)	Loss 0.8122 (0.8122)	Acc@1 82.031 (82.031)	Acc@5 94.727 (94.727)	
[2022-01-26 12:36:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.227 (3.379)	Loss 0.8963 (0.8208)	Acc@1 79.199 (81.081)	Acc@5 94.629 (95.348)	
[2022-01-26 12:36:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.896 (2.534)	Loss 0.8327 (0.8124)	Acc@1 80.762 (80.948)	Acc@5 94.238 (95.461)	
[2022-01-26 12:37:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.271 (2.270)	Loss 0.8699 (0.8155)	Acc@1 78.711 (80.869)	Acc@5 95.117 (95.423)	
[2022-01-26 12:37:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.948 (2.147)	Loss 0.8493 (0.8135)	Acc@1 80.664 (80.919)	Acc@5 94.824 (95.474)	
[2022-01-26 12:37:41 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 80.938 Acc@5 95.440
[2022-01-26 12:37:41 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 80.9%
[2022-01-26 12:37:41 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.07%
[2022-01-26 12:38:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][0/1251]	eta 7:23:00 lr 0.000027	time 21.2472 (21.2472)	loss 3.2269 (3.2269)	grad_norm 3.1365 (3.1365)	
[2022-01-26 12:38:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][10/1251]	eta 1:25:09 lr 0.000027	time 2.2800 (4.1171)	loss 3.1076 (3.0414)	grad_norm 3.3708 (3.2595)	
[2022-01-26 12:38:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][20/1251]	eta 1:03:46 lr 0.000027	time 1.2549 (3.1086)	loss 3.4293 (3.0385)	grad_norm 2.9073 (3.0792)	
[2022-01-26 12:39:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][30/1251]	eta 0:58:12 lr 0.000027	time 1.5136 (2.8602)	loss 3.0988 (3.0557)	grad_norm 3.1067 (3.0745)	
[2022-01-26 12:39:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][40/1251]	eta 0:55:19 lr 0.000027	time 3.6442 (2.7412)	loss 2.6915 (3.0565)	grad_norm 3.4818 (3.1295)	
[2022-01-26 12:39:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][50/1251]	eta 0:53:46 lr 0.000027	time 2.5933 (2.6865)	loss 3.0342 (3.0744)	grad_norm 3.2174 (3.0939)	
[2022-01-26 12:40:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][60/1251]	eta 0:52:12 lr 0.000027	time 1.7794 (2.6300)	loss 3.1006 (3.0694)	grad_norm 4.0371 (3.1386)	
[2022-01-26 12:40:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][70/1251]	eta 0:50:30 lr 0.000027	time 1.6784 (2.5659)	loss 1.9572 (3.0611)	grad_norm 3.0461 (3.1497)	
[2022-01-26 12:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][80/1251]	eta 0:48:54 lr 0.000027	time 2.3010 (2.5062)	loss 3.0305 (3.0314)	grad_norm 3.2158 (3.1265)	
[2022-01-26 12:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][90/1251]	eta 0:47:31 lr 0.000027	time 1.5718 (2.4562)	loss 3.1091 (3.0236)	grad_norm 3.3217 (3.1510)	
[2022-01-26 12:41:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][100/1251]	eta 0:46:12 lr 0.000027	time 1.9002 (2.4091)	loss 3.2735 (3.0402)	grad_norm 3.1243 (3.1685)	
[2022-01-26 12:42:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][110/1251]	eta 0:45:10 lr 0.000027	time 1.9341 (2.3751)	loss 2.7890 (3.0396)	grad_norm 2.6884 (3.1526)	
[2022-01-26 12:42:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][120/1251]	eta 0:44:17 lr 0.000027	time 1.8749 (2.3501)	loss 3.5563 (3.0378)	grad_norm 3.7852 (3.1532)	
[2022-01-26 12:42:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][130/1251]	eta 0:43:47 lr 0.000027	time 2.5421 (2.3435)	loss 2.2563 (3.0294)	grad_norm 2.8733 (3.1349)	
[2022-01-26 12:43:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][140/1251]	eta 0:43:15 lr 0.000027	time 2.0813 (2.3361)	loss 2.9539 (3.0071)	grad_norm 3.0909 (3.1250)	
[2022-01-26 12:43:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][150/1251]	eta 0:42:42 lr 0.000027	time 1.8034 (2.3272)	loss 3.3447 (3.0048)	grad_norm 2.8142 (3.1092)	
[2022-01-26 12:43:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][160/1251]	eta 0:42:14 lr 0.000027	time 2.0786 (2.3229)	loss 3.4643 (2.9977)	grad_norm 3.3765 (3.1075)	
[2022-01-26 12:44:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][170/1251]	eta 0:42:02 lr 0.000027	time 2.4160 (2.3337)	loss 3.1860 (3.0013)	grad_norm 2.9556 (3.1070)	
[2022-01-26 12:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][180/1251]	eta 0:41:36 lr 0.000027	time 2.6341 (2.3309)	loss 2.5302 (2.9995)	grad_norm 2.7128 (3.1041)	
[2022-01-26 12:45:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][190/1251]	eta 0:41:02 lr 0.000027	time 1.5721 (2.3206)	loss 2.2646 (2.9927)	grad_norm 3.1885 (3.0983)	
[2022-01-26 12:45:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][200/1251]	eta 0:40:31 lr 0.000027	time 1.8214 (2.3133)	loss 3.2721 (2.9978)	grad_norm 3.3145 (3.1017)	
[2022-01-26 12:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][210/1251]	eta 0:39:51 lr 0.000027	time 1.9165 (2.2977)	loss 2.7243 (2.9972)	grad_norm 4.2755 (3.1237)	
[2022-01-26 12:46:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][220/1251]	eta 0:39:16 lr 0.000027	time 2.5183 (2.2858)	loss 3.0917 (3.0032)	grad_norm 3.0383 (3.1307)	
[2022-01-26 12:46:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][230/1251]	eta 0:38:42 lr 0.000027	time 2.2601 (2.2748)	loss 2.5483 (2.9946)	grad_norm 3.0977 (3.1577)	
[2022-01-26 12:46:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][240/1251]	eta 0:38:07 lr 0.000027	time 1.6713 (2.2622)	loss 3.3271 (2.9935)	grad_norm 3.3222 (3.1603)	
[2022-01-26 12:47:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][250/1251]	eta 0:37:41 lr 0.000027	time 2.1434 (2.2595)	loss 3.2847 (2.9973)	grad_norm 2.9398 (3.1493)	
[2022-01-26 12:47:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][260/1251]	eta 0:37:09 lr 0.000027	time 2.2365 (2.2502)	loss 2.1600 (2.9912)	grad_norm 2.5659 (3.1466)	
[2022-01-26 12:47:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][270/1251]	eta 0:36:44 lr 0.000027	time 2.2878 (2.2471)	loss 3.1778 (2.9956)	grad_norm 3.2727 (3.1482)	
[2022-01-26 12:48:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][280/1251]	eta 0:36:27 lr 0.000027	time 3.5324 (2.2531)	loss 2.3801 (2.9948)	grad_norm 3.1751 (3.1439)	
[2022-01-26 12:48:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][290/1251]	eta 0:36:13 lr 0.000027	time 1.8005 (2.2613)	loss 2.9569 (2.9937)	grad_norm 2.9369 (3.1470)	
[2022-01-26 12:49:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][300/1251]	eta 0:35:55 lr 0.000027	time 2.6705 (2.2660)	loss 2.9993 (2.9909)	grad_norm 3.1332 (3.1484)	
[2022-01-26 12:49:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][310/1251]	eta 0:35:31 lr 0.000027	time 3.1170 (2.2652)	loss 3.1149 (2.9865)	grad_norm 2.7518 (3.1473)	
[2022-01-26 12:49:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][320/1251]	eta 0:35:08 lr 0.000027	time 3.1365 (2.2646)	loss 2.1092 (2.9764)	grad_norm 2.9140 (3.1458)	
[2022-01-26 12:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][330/1251]	eta 0:34:41 lr 0.000027	time 1.5914 (2.2602)	loss 3.0341 (2.9773)	grad_norm 2.8926 (3.1550)	
[2022-01-26 12:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][340/1251]	eta 0:34:14 lr 0.000027	time 1.9025 (2.2555)	loss 2.7777 (2.9770)	grad_norm 2.8238 (3.1576)	
[2022-01-26 12:50:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][350/1251]	eta 0:33:48 lr 0.000026	time 2.7579 (2.2510)	loss 2.8813 (2.9773)	grad_norm 2.9122 (3.1494)	
[2022-01-26 12:51:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][360/1251]	eta 0:33:28 lr 0.000026	time 3.2314 (2.2543)	loss 2.2011 (2.9752)	grad_norm 2.8470 (3.1653)	
[2022-01-26 12:51:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][370/1251]	eta 0:33:06 lr 0.000026	time 1.7524 (2.2550)	loss 3.3457 (2.9809)	grad_norm 3.2658 (3.1666)	
[2022-01-26 12:51:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][380/1251]	eta 0:32:41 lr 0.000026	time 1.9570 (2.2525)	loss 2.2308 (2.9797)	grad_norm 3.0233 (3.1670)	
[2022-01-26 12:52:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][390/1251]	eta 0:32:15 lr 0.000026	time 2.3890 (2.2485)	loss 2.9663 (2.9833)	grad_norm 3.4812 (3.1629)	
[2022-01-26 12:52:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][400/1251]	eta 0:31:49 lr 0.000026	time 2.7314 (2.2440)	loss 3.1227 (2.9850)	grad_norm 2.8059 (3.1582)	
[2022-01-26 12:53:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][410/1251]	eta 0:31:23 lr 0.000026	time 1.5615 (2.2392)	loss 3.2755 (2.9863)	grad_norm 2.7864 (3.1608)	
[2022-01-26 12:53:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][420/1251]	eta 0:30:58 lr 0.000026	time 2.1087 (2.2365)	loss 3.3191 (2.9914)	grad_norm 2.9374 (3.1557)	
[2022-01-26 12:53:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][430/1251]	eta 0:30:35 lr 0.000026	time 2.5322 (2.2361)	loss 3.1898 (2.9878)	grad_norm 3.0035 (3.1528)	
[2022-01-26 12:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][440/1251]	eta 0:30:15 lr 0.000026	time 3.3500 (2.2389)	loss 1.9619 (2.9878)	grad_norm 3.1465 (3.1499)	
[2022-01-26 12:54:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][450/1251]	eta 0:29:54 lr 0.000026	time 2.1957 (2.2398)	loss 3.7611 (2.9909)	grad_norm 2.7756 (3.1469)	
[2022-01-26 12:54:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][460/1251]	eta 0:29:32 lr 0.000026	time 2.5832 (2.2404)	loss 2.5031 (2.9919)	grad_norm 2.9365 (3.1443)	
[2022-01-26 12:55:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][470/1251]	eta 0:29:09 lr 0.000026	time 1.9946 (2.2396)	loss 2.7509 (2.9908)	grad_norm 2.7265 (3.1421)	
[2022-01-26 12:55:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][480/1251]	eta 0:28:47 lr 0.000026	time 3.7176 (2.2406)	loss 3.2470 (2.9932)	grad_norm 3.4105 (3.1415)	
[2022-01-26 12:55:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][490/1251]	eta 0:28:21 lr 0.000026	time 1.9887 (2.2363)	loss 3.4111 (2.9901)	grad_norm 2.6339 (3.1490)	
[2022-01-26 12:56:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][500/1251]	eta 0:27:55 lr 0.000026	time 1.9043 (2.2311)	loss 2.2120 (2.9813)	grad_norm 3.0992 (3.1480)	
[2022-01-26 12:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][510/1251]	eta 0:27:33 lr 0.000026	time 1.8371 (2.2309)	loss 3.0075 (2.9844)	grad_norm 3.1279 (3.1469)	
[2022-01-26 12:57:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][520/1251]	eta 0:27:11 lr 0.000026	time 3.1709 (2.2316)	loss 3.2866 (2.9856)	grad_norm 2.8514 (3.1477)	
[2022-01-26 12:57:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][530/1251]	eta 0:26:48 lr 0.000026	time 2.0164 (2.2315)	loss 3.4156 (2.9844)	grad_norm 2.9760 (3.1441)	
[2022-01-26 12:57:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][540/1251]	eta 0:26:24 lr 0.000026	time 1.6877 (2.2288)	loss 3.2884 (2.9833)	grad_norm 2.8551 (3.1429)	
[2022-01-26 12:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][550/1251]	eta 0:26:01 lr 0.000026	time 1.9284 (2.2273)	loss 3.2563 (2.9844)	grad_norm 2.7905 (3.1431)	
[2022-01-26 12:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][560/1251]	eta 0:25:37 lr 0.000026	time 2.6818 (2.2243)	loss 3.3534 (2.9863)	grad_norm 2.9348 (3.1436)	
[2022-01-26 12:58:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][570/1251]	eta 0:25:12 lr 0.000026	time 1.8429 (2.2206)	loss 3.3958 (2.9901)	grad_norm 2.8929 (3.1423)	
[2022-01-26 12:59:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][580/1251]	eta 0:24:49 lr 0.000026	time 2.1640 (2.2194)	loss 2.0528 (2.9892)	grad_norm 2.7937 (3.1396)	
[2022-01-26 12:59:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][590/1251]	eta 0:24:27 lr 0.000026	time 1.4963 (2.2195)	loss 1.9306 (2.9898)	grad_norm 3.1204 (3.1391)	
[2022-01-26 12:59:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][600/1251]	eta 0:24:05 lr 0.000026	time 1.8457 (2.2206)	loss 2.8279 (2.9863)	grad_norm 3.1838 (3.1390)	
[2022-01-26 13:00:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][610/1251]	eta 0:23:43 lr 0.000026	time 1.4980 (2.2201)	loss 3.5497 (2.9845)	grad_norm 2.8987 (3.1381)	
[2022-01-26 13:00:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][620/1251]	eta 0:23:22 lr 0.000026	time 2.2226 (2.2220)	loss 2.1429 (2.9831)	grad_norm 2.5986 (3.1347)	
[2022-01-26 13:01:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][630/1251]	eta 0:23:01 lr 0.000026	time 2.4455 (2.2245)	loss 3.4227 (2.9826)	grad_norm 3.0087 (3.1301)	
[2022-01-26 13:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][640/1251]	eta 0:22:38 lr 0.000026	time 2.5569 (2.2236)	loss 2.2778 (2.9799)	grad_norm 2.8725 (3.1353)	
[2022-01-26 13:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][650/1251]	eta 0:22:13 lr 0.000026	time 1.9246 (2.2189)	loss 3.2817 (2.9817)	grad_norm 3.4065 (3.1334)	
[2022-01-26 13:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][660/1251]	eta 0:21:50 lr 0.000026	time 2.4370 (2.2175)	loss 3.1366 (2.9778)	grad_norm 2.6593 (3.1317)	
[2022-01-26 13:02:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][670/1251]	eta 0:21:27 lr 0.000026	time 2.1002 (2.2158)	loss 2.2455 (2.9755)	grad_norm 3.2043 (3.1297)	
[2022-01-26 13:02:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][680/1251]	eta 0:21:05 lr 0.000026	time 2.1602 (2.2158)	loss 2.1216 (2.9757)	grad_norm 3.0642 (3.1349)	
[2022-01-26 13:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][690/1251]	eta 0:20:42 lr 0.000026	time 2.3057 (2.2142)	loss 2.1263 (2.9746)	grad_norm 3.4471 (3.1347)	
[2022-01-26 13:03:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][700/1251]	eta 0:20:20 lr 0.000026	time 1.7045 (2.2152)	loss 1.8716 (2.9760)	grad_norm 2.8885 (3.1319)	
[2022-01-26 13:03:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][710/1251]	eta 0:19:58 lr 0.000026	time 2.4221 (2.2162)	loss 2.9756 (2.9782)	grad_norm 2.7168 (3.1290)	
[2022-01-26 13:04:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][720/1251]	eta 0:19:36 lr 0.000026	time 1.5001 (2.2151)	loss 3.7567 (2.9823)	grad_norm 3.0729 (3.1299)	
[2022-01-26 13:04:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][730/1251]	eta 0:19:13 lr 0.000026	time 2.3194 (2.2139)	loss 3.3146 (2.9830)	grad_norm 3.1756 (3.1277)	
[2022-01-26 13:05:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][740/1251]	eta 0:18:51 lr 0.000026	time 1.8243 (2.2138)	loss 2.8277 (2.9860)	grad_norm 3.0222 (3.1289)	
[2022-01-26 13:05:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][750/1251]	eta 0:18:31 lr 0.000026	time 3.0383 (2.2176)	loss 2.1621 (2.9851)	grad_norm 3.0218 (3.1281)	
[2022-01-26 13:05:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][760/1251]	eta 0:18:08 lr 0.000026	time 1.7659 (2.2159)	loss 3.0468 (2.9828)	grad_norm 2.9147 (3.1300)	
[2022-01-26 13:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][770/1251]	eta 0:17:44 lr 0.000026	time 1.9612 (2.2132)	loss 3.0471 (2.9865)	grad_norm 3.2398 (3.1300)	
[2022-01-26 13:06:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][780/1251]	eta 0:17:21 lr 0.000026	time 1.6361 (2.2104)	loss 3.0849 (2.9869)	grad_norm 2.7826 (3.1361)	
[2022-01-26 13:06:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][790/1251]	eta 0:16:58 lr 0.000026	time 1.8692 (2.2083)	loss 2.9920 (2.9860)	grad_norm 2.8013 (3.1365)	
[2022-01-26 13:07:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][800/1251]	eta 0:16:37 lr 0.000026	time 5.1481 (2.2108)	loss 2.4016 (2.9877)	grad_norm 2.7519 (3.1353)	
[2022-01-26 13:07:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][810/1251]	eta 0:16:14 lr 0.000026	time 2.1628 (2.2106)	loss 2.4069 (2.9905)	grad_norm 3.0387 (3.1344)	
[2022-01-26 13:07:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][820/1251]	eta 0:15:53 lr 0.000026	time 1.4902 (2.2119)	loss 3.5298 (2.9897)	grad_norm 3.5940 (3.1368)	
[2022-01-26 13:08:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][830/1251]	eta 0:15:31 lr 0.000026	time 2.2605 (2.2119)	loss 3.3409 (2.9885)	grad_norm 3.0246 (3.1369)	
[2022-01-26 13:08:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][840/1251]	eta 0:15:08 lr 0.000026	time 2.4875 (2.2109)	loss 3.1195 (2.9893)	grad_norm 2.8406 (3.1369)	
[2022-01-26 13:09:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][850/1251]	eta 0:14:46 lr 0.000026	time 2.7756 (2.2104)	loss 3.2091 (2.9879)	grad_norm 3.5219 (3.1343)	
[2022-01-26 13:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][860/1251]	eta 0:14:24 lr 0.000026	time 2.0466 (2.2104)	loss 3.3661 (2.9846)	grad_norm 2.9410 (3.1328)	
[2022-01-26 13:09:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][870/1251]	eta 0:14:02 lr 0.000026	time 2.5821 (2.2125)	loss 2.8047 (2.9840)	grad_norm 2.9067 (3.1322)	
[2022-01-26 13:10:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][880/1251]	eta 0:13:40 lr 0.000026	time 2.6923 (2.2112)	loss 3.7034 (2.9830)	grad_norm 3.3127 (3.1325)	
[2022-01-26 13:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][890/1251]	eta 0:13:17 lr 0.000026	time 2.1881 (2.2089)	loss 2.9770 (2.9842)	grad_norm 2.6801 (3.1338)	
[2022-01-26 13:10:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][900/1251]	eta 0:12:54 lr 0.000026	time 1.9332 (2.2062)	loss 3.4274 (2.9856)	grad_norm 2.8269 (3.1342)	
[2022-01-26 13:11:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][910/1251]	eta 0:12:32 lr 0.000026	time 1.3536 (2.2054)	loss 2.9995 (2.9852)	grad_norm 3.1006 (3.1328)	
[2022-01-26 13:11:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][920/1251]	eta 0:12:10 lr 0.000026	time 2.3032 (2.2062)	loss 3.5481 (2.9857)	grad_norm 2.8235 (3.1325)	
[2022-01-26 13:11:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][930/1251]	eta 0:11:48 lr 0.000026	time 2.2257 (2.2080)	loss 2.3229 (2.9861)	grad_norm 3.1236 (3.1316)	
[2022-01-26 13:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][940/1251]	eta 0:11:27 lr 0.000026	time 2.7350 (2.2100)	loss 3.3611 (2.9886)	grad_norm 3.0874 (3.1317)	
[2022-01-26 13:12:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][950/1251]	eta 0:11:04 lr 0.000026	time 1.7417 (2.2090)	loss 2.2747 (2.9889)	grad_norm 2.6956 (3.1310)	
[2022-01-26 13:13:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][960/1251]	eta 0:10:42 lr 0.000026	time 2.2973 (2.2087)	loss 2.6737 (2.9887)	grad_norm 3.1115 (3.1330)	
[2022-01-26 13:13:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][970/1251]	eta 0:10:19 lr 0.000026	time 1.8308 (2.2057)	loss 3.0230 (2.9877)	grad_norm 8.9726 (3.1394)	
[2022-01-26 13:13:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][980/1251]	eta 0:09:57 lr 0.000026	time 1.6181 (2.2037)	loss 3.3114 (2.9874)	grad_norm 2.5682 (3.1364)	
[2022-01-26 13:14:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][990/1251]	eta 0:09:34 lr 0.000026	time 1.7323 (2.2020)	loss 3.0323 (2.9874)	grad_norm 2.8259 (3.1342)	
[2022-01-26 13:14:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1000/1251]	eta 0:09:12 lr 0.000026	time 2.4273 (2.2014)	loss 2.8871 (2.9872)	grad_norm 2.9947 (3.1320)	
[2022-01-26 13:14:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1010/1251]	eta 0:08:50 lr 0.000026	time 1.8991 (2.2018)	loss 3.2237 (2.9868)	grad_norm 2.8764 (3.1297)	
[2022-01-26 13:15:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1020/1251]	eta 0:08:28 lr 0.000026	time 1.8267 (2.2016)	loss 3.7616 (2.9884)	grad_norm 3.0889 (3.1288)	
[2022-01-26 13:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1030/1251]	eta 0:08:06 lr 0.000026	time 2.4373 (2.2026)	loss 3.3666 (2.9879)	grad_norm 2.8712 (3.1271)	
[2022-01-26 13:15:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1040/1251]	eta 0:07:45 lr 0.000026	time 1.9523 (2.2039)	loss 2.7175 (2.9889)	grad_norm 3.2536 (3.1262)	
[2022-01-26 13:16:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1050/1251]	eta 0:07:23 lr 0.000026	time 2.2612 (2.2054)	loss 2.8487 (2.9860)	grad_norm 3.0731 (3.1252)	
[2022-01-26 13:16:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1060/1251]	eta 0:07:01 lr 0.000026	time 1.5663 (2.2049)	loss 2.6913 (2.9869)	grad_norm 3.1683 (3.1241)	
[2022-01-26 13:17:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1070/1251]	eta 0:06:38 lr 0.000026	time 2.3393 (2.2038)	loss 3.1438 (2.9877)	grad_norm 2.7581 (3.1225)	
[2022-01-26 13:17:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1080/1251]	eta 0:06:16 lr 0.000026	time 1.6019 (2.2031)	loss 2.3329 (2.9870)	grad_norm 3.1746 (3.1226)	
[2022-01-26 13:17:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1090/1251]	eta 0:05:54 lr 0.000026	time 2.4127 (2.2033)	loss 3.2502 (2.9897)	grad_norm 2.7012 (3.1207)	
[2022-01-26 13:18:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1100/1251]	eta 0:05:32 lr 0.000026	time 1.6907 (2.2015)	loss 2.9069 (2.9919)	grad_norm 2.7841 (3.1201)	
[2022-01-26 13:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1110/1251]	eta 0:05:10 lr 0.000026	time 2.6595 (2.2013)	loss 3.0517 (2.9922)	grad_norm 3.6928 (3.1220)	
[2022-01-26 13:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1120/1251]	eta 0:04:48 lr 0.000026	time 1.5626 (2.2008)	loss 2.8399 (2.9934)	grad_norm 3.2723 (3.1246)	
[2022-01-26 13:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1130/1251]	eta 0:04:26 lr 0.000026	time 2.1343 (2.2022)	loss 2.7902 (2.9930)	grad_norm 2.9288 (3.1254)	
[2022-01-26 13:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1140/1251]	eta 0:04:04 lr 0.000026	time 1.9107 (2.2015)	loss 3.2740 (2.9917)	grad_norm 2.6117 (3.1230)	
[2022-01-26 13:19:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1150/1251]	eta 0:03:42 lr 0.000026	time 1.6380 (2.2003)	loss 2.5567 (2.9942)	grad_norm 3.1187 (3.1233)	
[2022-01-26 13:20:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1160/1251]	eta 0:03:20 lr 0.000026	time 2.3172 (2.2003)	loss 3.0854 (2.9953)	grad_norm 2.7680 (3.1233)	
[2022-01-26 13:20:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1170/1251]	eta 0:02:58 lr 0.000026	time 2.7331 (2.2016)	loss 2.9727 (2.9957)	grad_norm 3.1531 (3.1229)	
[2022-01-26 13:21:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1180/1251]	eta 0:02:36 lr 0.000026	time 2.3948 (2.2012)	loss 3.5883 (2.9981)	grad_norm 2.6911 (3.1216)	
[2022-01-26 13:21:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1190/1251]	eta 0:02:14 lr 0.000026	time 2.2344 (2.2002)	loss 2.8039 (2.9977)	grad_norm 2.6922 (3.1223)	
[2022-01-26 13:21:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1200/1251]	eta 0:01:52 lr 0.000026	time 2.1812 (2.2002)	loss 2.5957 (2.9975)	grad_norm 3.0760 (3.1198)	
[2022-01-26 13:22:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1210/1251]	eta 0:01:30 lr 0.000026	time 2.0190 (2.2015)	loss 3.1459 (2.9959)	grad_norm 3.3206 (3.1195)	
[2022-01-26 13:22:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1220/1251]	eta 0:01:08 lr 0.000026	time 1.9171 (2.2000)	loss 2.4612 (2.9931)	grad_norm 3.5738 (3.1196)	
[2022-01-26 13:22:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1230/1251]	eta 0:00:46 lr 0.000026	time 2.7379 (2.2000)	loss 3.1623 (2.9928)	grad_norm 3.3741 (3.1199)	
[2022-01-26 13:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1240/1251]	eta 0:00:24 lr 0.000026	time 2.1524 (2.1992)	loss 2.9277 (2.9940)	grad_norm 3.4495 (3.1195)	
[2022-01-26 13:23:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [275/300][1250/1251]	eta 0:00:02 lr 0.000026	time 1.2887 (2.1940)	loss 3.0344 (2.9930)	grad_norm 2.8280 (3.1214)	
[2022-01-26 13:23:26 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 275 training takes 0:45:45
[2022-01-26 13:23:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 17.977 (17.977)	Loss 0.8128 (0.8128)	Acc@1 81.641 (81.641)	Acc@5 94.727 (94.727)	
[2022-01-26 13:24:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.973 (3.291)	Loss 0.8705 (0.8063)	Acc@1 80.078 (81.090)	Acc@5 94.531 (95.419)	
[2022-01-26 13:24:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.318 (2.538)	Loss 0.8451 (0.8093)	Acc@1 80.762 (81.129)	Acc@5 95.508 (95.382)	
[2022-01-26 13:24:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.589 (2.326)	Loss 0.8646 (0.8119)	Acc@1 82.227 (81.105)	Acc@5 94.531 (95.357)	
[2022-01-26 13:24:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.125 (2.178)	Loss 0.7637 (0.8147)	Acc@1 82.129 (80.926)	Acc@5 95.801 (95.384)	
[2022-01-26 13:25:03 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.010 Acc@5 95.418
[2022-01-26 13:25:03 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.0%
[2022-01-26 13:25:03 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.07%
[2022-01-26 13:25:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][0/1251]	eta 7:36:40 lr 0.000026	time 21.9032 (21.9032)	loss 3.5102 (3.5102)	grad_norm 3.3729 (3.3729)	
[2022-01-26 13:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][10/1251]	eta 1:24:32 lr 0.000026	time 2.8538 (4.0874)	loss 3.1797 (2.9037)	grad_norm 2.6437 (3.1744)	
[2022-01-26 13:26:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][20/1251]	eta 1:04:42 lr 0.000026	time 1.5220 (3.1543)	loss 3.2677 (2.8688)	grad_norm 2.8352 (3.1178)	
[2022-01-26 13:26:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][30/1251]	eta 0:58:22 lr 0.000026	time 1.8688 (2.8686)	loss 3.4888 (2.9882)	grad_norm 3.7372 (3.1673)	
[2022-01-26 13:26:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][40/1251]	eta 0:55:10 lr 0.000026	time 3.3526 (2.7337)	loss 3.4322 (3.0281)	grad_norm 2.5048 (3.1100)	
[2022-01-26 13:27:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][50/1251]	eta 0:53:39 lr 0.000025	time 2.4841 (2.6805)	loss 3.3373 (3.0248)	grad_norm 2.7033 (3.0958)	
[2022-01-26 13:27:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][60/1251]	eta 0:51:49 lr 0.000025	time 1.9184 (2.6105)	loss 2.4638 (2.9642)	grad_norm 4.1675 (3.1133)	
[2022-01-26 13:28:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][70/1251]	eta 0:50:49 lr 0.000025	time 1.5034 (2.5820)	loss 2.7592 (2.9826)	grad_norm 2.7741 (3.1367)	
[2022-01-26 13:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][80/1251]	eta 0:49:36 lr 0.000025	time 3.0131 (2.5417)	loss 2.5838 (2.9920)	grad_norm 2.6997 (3.1540)	
[2022-01-26 13:28:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][90/1251]	eta 0:48:18 lr 0.000025	time 1.9671 (2.4961)	loss 3.7111 (3.0032)	grad_norm 3.5033 (3.1880)	
[2022-01-26 13:29:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][100/1251]	eta 0:46:58 lr 0.000025	time 1.8280 (2.4486)	loss 3.4437 (3.0130)	grad_norm 2.4688 (3.1553)	
[2022-01-26 13:29:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][110/1251]	eta 0:46:08 lr 0.000025	time 1.8962 (2.4265)	loss 2.5639 (3.0070)	grad_norm 2.8004 (3.1307)	
[2022-01-26 13:29:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][120/1251]	eta 0:45:21 lr 0.000025	time 2.7663 (2.4066)	loss 3.2850 (2.9851)	grad_norm 3.6949 (3.1189)	
[2022-01-26 13:30:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][130/1251]	eta 0:44:39 lr 0.000025	time 1.8193 (2.3899)	loss 3.4224 (2.9993)	grad_norm 7.1061 (3.1370)	
[2022-01-26 13:30:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][140/1251]	eta 0:43:48 lr 0.000025	time 2.2211 (2.3658)	loss 3.2667 (3.0131)	grad_norm 2.9787 (3.1425)	
[2022-01-26 13:30:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][150/1251]	eta 0:43:12 lr 0.000025	time 2.2579 (2.3551)	loss 2.2768 (2.9980)	grad_norm 2.7171 (3.1533)	
[2022-01-26 13:31:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][160/1251]	eta 0:42:40 lr 0.000025	time 2.5703 (2.3471)	loss 3.2405 (3.0085)	grad_norm 3.1749 (3.1448)	
[2022-01-26 13:31:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][170/1251]	eta 0:42:09 lr 0.000025	time 2.2943 (2.3397)	loss 3.3103 (3.0070)	grad_norm 3.0331 (3.1499)	
[2022-01-26 13:32:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][180/1251]	eta 0:41:30 lr 0.000025	time 2.2499 (2.3251)	loss 2.8936 (2.9980)	grad_norm 4.1222 (3.1444)	
[2022-01-26 13:32:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][190/1251]	eta 0:40:57 lr 0.000025	time 1.8242 (2.3167)	loss 3.2398 (2.9988)	grad_norm 3.4105 (3.1449)	
[2022-01-26 13:32:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][200/1251]	eta 0:40:29 lr 0.000025	time 3.3211 (2.3118)	loss 3.4161 (3.0151)	grad_norm 3.1773 (3.1581)	
[2022-01-26 13:33:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][210/1251]	eta 0:39:53 lr 0.000025	time 1.7786 (2.2997)	loss 2.7036 (3.0115)	grad_norm 2.7377 (3.1575)	
[2022-01-26 13:33:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][220/1251]	eta 0:39:21 lr 0.000025	time 1.7195 (2.2907)	loss 3.2452 (3.0234)	grad_norm 2.9548 (3.1528)	
[2022-01-26 13:33:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][230/1251]	eta 0:38:56 lr 0.000025	time 2.0990 (2.2887)	loss 3.5696 (3.0343)	grad_norm 3.3132 (3.1578)	
[2022-01-26 13:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][240/1251]	eta 0:38:41 lr 0.000025	time 3.4426 (2.2967)	loss 2.6148 (3.0330)	grad_norm 4.0261 (3.1646)	
[2022-01-26 13:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][250/1251]	eta 0:38:16 lr 0.000025	time 1.4408 (2.2939)	loss 2.3538 (3.0212)	grad_norm 3.0561 (3.1574)	
[2022-01-26 13:35:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][260/1251]	eta 0:37:49 lr 0.000025	time 2.2029 (2.2897)	loss 2.8972 (3.0257)	grad_norm 2.9378 (3.1553)	
[2022-01-26 13:35:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][270/1251]	eta 0:37:18 lr 0.000025	time 1.8352 (2.2818)	loss 2.8166 (3.0137)	grad_norm 2.7538 (3.1562)	
[2022-01-26 13:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][280/1251]	eta 0:36:54 lr 0.000025	time 2.8286 (2.2806)	loss 2.1462 (3.0055)	grad_norm 2.8226 (3.1536)	
[2022-01-26 13:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][290/1251]	eta 0:36:23 lr 0.000025	time 1.7312 (2.2724)	loss 2.3060 (2.9960)	grad_norm 3.1136 (3.1495)	
[2022-01-26 13:36:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][300/1251]	eta 0:35:56 lr 0.000025	time 1.7218 (2.2679)	loss 3.4636 (2.9985)	grad_norm 2.9374 (3.1518)	
[2022-01-26 13:36:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][310/1251]	eta 0:35:32 lr 0.000025	time 2.1897 (2.2658)	loss 2.0296 (3.0034)	grad_norm 3.0797 (3.1497)	
[2022-01-26 13:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][320/1251]	eta 0:35:12 lr 0.000025	time 3.1766 (2.2691)	loss 3.1080 (3.0046)	grad_norm 2.9519 (3.1562)	
[2022-01-26 13:37:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][330/1251]	eta 0:34:47 lr 0.000025	time 1.5558 (2.2671)	loss 3.3336 (3.0094)	grad_norm 3.8186 (3.1549)	
[2022-01-26 13:37:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][340/1251]	eta 0:34:22 lr 0.000025	time 2.2296 (2.2638)	loss 1.8976 (3.0083)	grad_norm 3.1896 (3.1540)	
[2022-01-26 13:38:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][350/1251]	eta 0:33:54 lr 0.000025	time 1.8160 (2.2584)	loss 3.3436 (3.0203)	grad_norm 3.4831 (3.1581)	
[2022-01-26 13:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][360/1251]	eta 0:33:33 lr 0.000025	time 2.7034 (2.2596)	loss 2.5438 (3.0186)	grad_norm 3.1087 (3.1548)	
[2022-01-26 13:38:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][370/1251]	eta 0:33:06 lr 0.000025	time 1.6612 (2.2550)	loss 2.0714 (3.0194)	grad_norm 2.8685 (3.1570)	
[2022-01-26 13:39:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][380/1251]	eta 0:32:45 lr 0.000025	time 2.4592 (2.2568)	loss 3.5801 (3.0260)	grad_norm 2.7418 (3.1518)	
[2022-01-26 13:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][390/1251]	eta 0:32:21 lr 0.000025	time 2.3376 (2.2555)	loss 3.2340 (3.0222)	grad_norm 2.8488 (3.1576)	
[2022-01-26 13:40:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][400/1251]	eta 0:31:59 lr 0.000025	time 2.6069 (2.2552)	loss 3.2813 (3.0219)	grad_norm 3.1105 (3.1545)	
[2022-01-26 13:40:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][410/1251]	eta 0:31:32 lr 0.000025	time 1.9616 (2.2508)	loss 3.3701 (3.0257)	grad_norm 3.3374 (3.1516)	
[2022-01-26 13:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][420/1251]	eta 0:31:09 lr 0.000025	time 1.8584 (2.2497)	loss 2.5164 (3.0218)	grad_norm 3.0387 (3.1577)	
[2022-01-26 13:41:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][430/1251]	eta 0:30:44 lr 0.000025	time 2.0384 (2.2469)	loss 3.2624 (3.0222)	grad_norm 3.1930 (3.1564)	
[2022-01-26 13:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][440/1251]	eta 0:30:22 lr 0.000025	time 2.4964 (2.2478)	loss 3.4368 (3.0255)	grad_norm 2.9328 (3.1546)	
[2022-01-26 13:41:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][450/1251]	eta 0:29:59 lr 0.000025	time 1.5403 (2.2470)	loss 3.1400 (3.0258)	grad_norm 2.7268 (3.1490)	
[2022-01-26 13:42:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][460/1251]	eta 0:29:35 lr 0.000025	time 2.2311 (2.2452)	loss 2.7233 (3.0233)	grad_norm 3.4359 (3.1496)	
[2022-01-26 13:42:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][470/1251]	eta 0:29:12 lr 0.000025	time 1.7596 (2.2433)	loss 2.0148 (3.0191)	grad_norm 3.6160 (3.1473)	
[2022-01-26 13:43:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][480/1251]	eta 0:28:51 lr 0.000025	time 3.1284 (2.2453)	loss 3.4843 (3.0202)	grad_norm 3.4043 (3.1465)	
[2022-01-26 13:43:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][490/1251]	eta 0:28:28 lr 0.000025	time 2.1638 (2.2453)	loss 3.6496 (3.0216)	grad_norm 3.2431 (3.1480)	
[2022-01-26 13:43:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][500/1251]	eta 0:28:03 lr 0.000025	time 2.0195 (2.2423)	loss 3.3613 (3.0198)	grad_norm 2.5765 (3.1430)	
[2022-01-26 13:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][510/1251]	eta 0:27:39 lr 0.000025	time 1.8952 (2.2397)	loss 3.7358 (3.0177)	grad_norm 3.0319 (3.1416)	
[2022-01-26 13:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][520/1251]	eta 0:27:15 lr 0.000025	time 1.9076 (2.2372)	loss 3.4036 (3.0195)	grad_norm 3.0493 (3.1400)	
[2022-01-26 13:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][530/1251]	eta 0:26:50 lr 0.000025	time 1.5201 (2.2341)	loss 3.4441 (3.0203)	grad_norm 3.0608 (3.1407)	
[2022-01-26 13:45:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][540/1251]	eta 0:26:27 lr 0.000025	time 1.8594 (2.2332)	loss 3.4905 (3.0254)	grad_norm 3.4104 (3.1412)	
[2022-01-26 13:45:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][550/1251]	eta 0:26:04 lr 0.000025	time 2.2699 (2.2325)	loss 3.1626 (3.0242)	grad_norm 2.8418 (3.1391)	
[2022-01-26 13:45:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][560/1251]	eta 0:25:42 lr 0.000025	time 2.1636 (2.2326)	loss 2.5533 (3.0232)	grad_norm 3.2384 (3.1417)	
[2022-01-26 13:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][570/1251]	eta 0:25:20 lr 0.000025	time 1.8928 (2.2333)	loss 3.3022 (3.0265)	grad_norm 3.0399 (3.1462)	
[2022-01-26 13:46:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][580/1251]	eta 0:24:57 lr 0.000025	time 1.9243 (2.2312)	loss 3.1125 (3.0300)	grad_norm 4.1273 (3.1494)	
[2022-01-26 13:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][590/1251]	eta 0:24:34 lr 0.000025	time 2.2144 (2.2301)	loss 2.9077 (3.0266)	grad_norm 3.0838 (3.1481)	
[2022-01-26 13:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][600/1251]	eta 0:24:11 lr 0.000025	time 1.6962 (2.2302)	loss 3.0645 (3.0273)	grad_norm 2.8336 (3.1476)	
[2022-01-26 13:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][610/1251]	eta 0:23:49 lr 0.000025	time 1.9319 (2.2307)	loss 2.0508 (3.0237)	grad_norm 2.9468 (3.1464)	
[2022-01-26 13:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][620/1251]	eta 0:23:26 lr 0.000025	time 1.5986 (2.2283)	loss 2.8582 (3.0201)	grad_norm 3.0828 (3.1448)	
[2022-01-26 13:48:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][630/1251]	eta 0:23:03 lr 0.000025	time 2.1631 (2.2284)	loss 1.8018 (3.0218)	grad_norm 2.9724 (3.1411)	
[2022-01-26 13:48:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][640/1251]	eta 0:22:42 lr 0.000025	time 1.8546 (2.2299)	loss 2.7347 (3.0220)	grad_norm 2.7852 (3.1389)	
[2022-01-26 13:49:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][650/1251]	eta 0:22:20 lr 0.000025	time 3.0292 (2.2309)	loss 3.3806 (3.0181)	grad_norm 3.2828 (3.1367)	
[2022-01-26 13:49:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][660/1251]	eta 0:21:56 lr 0.000025	time 1.9034 (2.2274)	loss 3.3956 (3.0200)	grad_norm 3.3108 (3.1356)	
[2022-01-26 13:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][670/1251]	eta 0:21:32 lr 0.000025	time 2.2429 (2.2241)	loss 2.8489 (3.0199)	grad_norm 2.8406 (3.1363)	
[2022-01-26 13:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][680/1251]	eta 0:21:08 lr 0.000025	time 2.1703 (2.2221)	loss 2.2465 (3.0159)	grad_norm 3.0055 (3.1348)	
[2022-01-26 13:50:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][690/1251]	eta 0:20:47 lr 0.000025	time 2.9930 (2.2239)	loss 2.1701 (3.0154)	grad_norm 3.0695 (3.1342)	
[2022-01-26 13:51:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][700/1251]	eta 0:20:26 lr 0.000025	time 1.8810 (2.2264)	loss 2.5607 (3.0142)	grad_norm 4.1841 (3.1383)	
[2022-01-26 13:51:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][710/1251]	eta 0:20:07 lr 0.000025	time 1.8501 (2.2317)	loss 3.5143 (3.0172)	grad_norm 3.0944 (3.1400)	
[2022-01-26 13:51:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][720/1251]	eta 0:19:46 lr 0.000025	time 3.1156 (2.2351)	loss 3.4381 (3.0189)	grad_norm 2.9564 (3.1372)	
[2022-01-26 13:52:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][730/1251]	eta 0:19:23 lr 0.000025	time 2.1098 (2.2341)	loss 2.2285 (3.0208)	grad_norm 3.0426 (3.1383)	
[2022-01-26 13:52:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][740/1251]	eta 0:19:00 lr 0.000025	time 2.0081 (2.2327)	loss 3.1567 (3.0206)	grad_norm 2.9517 (3.1367)	
[2022-01-26 13:52:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][750/1251]	eta 0:18:36 lr 0.000025	time 1.9845 (2.2283)	loss 2.9664 (3.0197)	grad_norm 3.4781 (3.1383)	
[2022-01-26 13:53:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][760/1251]	eta 0:18:13 lr 0.000025	time 3.1175 (2.2267)	loss 3.3077 (3.0208)	grad_norm 4.0783 (3.1406)	
[2022-01-26 13:53:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][770/1251]	eta 0:17:50 lr 0.000025	time 1.6516 (2.2254)	loss 2.9747 (3.0211)	grad_norm 3.0281 (3.1411)	
[2022-01-26 13:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][780/1251]	eta 0:17:27 lr 0.000025	time 2.3220 (2.2236)	loss 3.1784 (3.0194)	grad_norm 3.0627 (3.1436)	
[2022-01-26 13:54:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][790/1251]	eta 0:17:04 lr 0.000025	time 2.2310 (2.2216)	loss 3.6746 (3.0224)	grad_norm 3.0297 (3.1429)	
[2022-01-26 13:54:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][800/1251]	eta 0:16:42 lr 0.000025	time 3.0038 (2.2220)	loss 1.9124 (3.0211)	grad_norm 2.7564 (3.1434)	
[2022-01-26 13:55:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][810/1251]	eta 0:16:19 lr 0.000025	time 1.8115 (2.2200)	loss 2.6291 (3.0211)	grad_norm 3.0937 (3.1446)	
[2022-01-26 13:55:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][820/1251]	eta 0:15:57 lr 0.000025	time 2.3078 (2.2208)	loss 2.1411 (3.0185)	grad_norm 3.6025 (3.1462)	
[2022-01-26 13:55:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][830/1251]	eta 0:15:34 lr 0.000025	time 2.2361 (2.2202)	loss 3.0902 (3.0166)	grad_norm 3.1206 (3.1468)	
[2022-01-26 13:56:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][840/1251]	eta 0:15:13 lr 0.000025	time 3.4587 (2.2219)	loss 2.8318 (3.0155)	grad_norm 2.6373 (3.1470)	
[2022-01-26 13:56:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][850/1251]	eta 0:14:51 lr 0.000025	time 2.5406 (2.2230)	loss 3.4631 (3.0171)	grad_norm 3.3555 (3.1484)	
[2022-01-26 13:56:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][860/1251]	eta 0:14:30 lr 0.000025	time 2.4529 (2.2252)	loss 3.3053 (3.0184)	grad_norm 3.1019 (3.1479)	
[2022-01-26 13:57:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][870/1251]	eta 0:14:08 lr 0.000025	time 2.1785 (2.2269)	loss 2.7352 (3.0173)	grad_norm 3.1245 (3.1460)	
[2022-01-26 13:57:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][880/1251]	eta 0:13:46 lr 0.000025	time 1.8639 (2.2271)	loss 2.9451 (3.0193)	grad_norm 3.3315 (3.1476)	
[2022-01-26 13:58:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][890/1251]	eta 0:13:22 lr 0.000025	time 1.6976 (2.2231)	loss 2.1195 (3.0202)	grad_norm 2.8412 (3.1468)	
[2022-01-26 13:58:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][900/1251]	eta 0:12:58 lr 0.000025	time 2.1986 (2.2191)	loss 3.3673 (3.0210)	grad_norm 2.7419 (3.1475)	
[2022-01-26 13:58:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][910/1251]	eta 0:12:35 lr 0.000025	time 1.9634 (2.2161)	loss 3.1781 (3.0193)	grad_norm 2.7480 (3.1447)	
[2022-01-26 13:59:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][920/1251]	eta 0:12:13 lr 0.000025	time 2.2763 (2.2150)	loss 3.5612 (3.0181)	grad_norm 3.2080 (3.1446)	
[2022-01-26 13:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][930/1251]	eta 0:11:50 lr 0.000025	time 1.8547 (2.2142)	loss 3.1793 (3.0171)	grad_norm 3.6825 (3.1427)	
[2022-01-26 13:59:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][940/1251]	eta 0:11:28 lr 0.000025	time 2.5869 (2.2136)	loss 3.2158 (3.0155)	grad_norm 3.2283 (3.1413)	
[2022-01-26 14:00:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][950/1251]	eta 0:11:05 lr 0.000025	time 1.6646 (2.2123)	loss 3.1266 (3.0174)	grad_norm 2.7671 (3.1399)	
[2022-01-26 14:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][960/1251]	eta 0:10:43 lr 0.000025	time 2.4293 (2.2122)	loss 3.3386 (3.0166)	grad_norm 2.9570 (3.1396)	
[2022-01-26 14:00:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][970/1251]	eta 0:10:21 lr 0.000025	time 1.8532 (2.2116)	loss 3.1668 (3.0153)	grad_norm 3.0372 (3.1418)	
[2022-01-26 14:01:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][980/1251]	eta 0:09:59 lr 0.000025	time 2.6706 (2.2128)	loss 2.9511 (3.0170)	grad_norm 3.3770 (3.1418)	
[2022-01-26 14:01:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][990/1251]	eta 0:09:37 lr 0.000025	time 1.6873 (2.2121)	loss 3.5864 (3.0163)	grad_norm 3.4954 (3.1405)	
[2022-01-26 14:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1000/1251]	eta 0:09:15 lr 0.000025	time 2.1932 (2.2137)	loss 1.9156 (3.0156)	grad_norm 2.8218 (3.1386)	
[2022-01-26 14:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1010/1251]	eta 0:08:53 lr 0.000025	time 1.8576 (2.2133)	loss 2.9376 (3.0163)	grad_norm 2.8237 (3.1394)	
[2022-01-26 14:02:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1020/1251]	eta 0:08:31 lr 0.000025	time 3.2821 (2.2146)	loss 2.3730 (3.0152)	grad_norm 2.5828 (3.1389)	
[2022-01-26 14:03:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1030/1251]	eta 0:08:09 lr 0.000025	time 1.8783 (2.2143)	loss 2.0675 (3.0152)	grad_norm 3.1926 (3.1376)	
[2022-01-26 14:03:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1040/1251]	eta 0:07:47 lr 0.000024	time 1.2489 (2.2170)	loss 3.4010 (3.0145)	grad_norm 2.8705 (3.1370)	
[2022-01-26 14:03:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1050/1251]	eta 0:07:25 lr 0.000024	time 1.9802 (2.2179)	loss 3.3290 (3.0137)	grad_norm 3.3786 (3.1382)	
[2022-01-26 14:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1060/1251]	eta 0:07:03 lr 0.000024	time 3.2267 (2.2188)	loss 3.6246 (3.0145)	grad_norm 3.6481 (3.1386)	
[2022-01-26 14:04:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1070/1251]	eta 0:06:41 lr 0.000024	time 1.5754 (2.2174)	loss 2.2843 (3.0128)	grad_norm 2.7111 (3.1382)	
[2022-01-26 14:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1080/1251]	eta 0:06:19 lr 0.000024	time 1.9142 (2.2168)	loss 2.8097 (3.0132)	grad_norm 3.6732 (3.1374)	
[2022-01-26 14:05:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1090/1251]	eta 0:05:56 lr 0.000024	time 1.6108 (2.2158)	loss 3.1155 (3.0136)	grad_norm 3.2048 (3.1370)	
[2022-01-26 14:05:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1100/1251]	eta 0:05:34 lr 0.000024	time 2.2648 (2.2158)	loss 3.2113 (3.0134)	grad_norm 4.1996 (3.1398)	
[2022-01-26 14:06:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1110/1251]	eta 0:05:12 lr 0.000024	time 1.9529 (2.2151)	loss 3.1424 (3.0142)	grad_norm 2.7544 (3.1428)	
[2022-01-26 14:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1120/1251]	eta 0:04:50 lr 0.000024	time 1.9849 (2.2138)	loss 3.3964 (3.0161)	grad_norm 3.3853 (3.1447)	
[2022-01-26 14:06:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1130/1251]	eta 0:04:27 lr 0.000024	time 1.6135 (2.2119)	loss 2.2323 (3.0150)	grad_norm 3.0761 (3.1447)	
[2022-01-26 14:07:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1140/1251]	eta 0:04:05 lr 0.000024	time 2.1711 (2.2112)	loss 3.5799 (3.0164)	grad_norm 2.9724 (3.1451)	
[2022-01-26 14:07:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1150/1251]	eta 0:03:43 lr 0.000024	time 2.4963 (2.2115)	loss 3.0547 (3.0148)	grad_norm 3.1572 (3.1441)	
[2022-01-26 14:07:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1160/1251]	eta 0:03:21 lr 0.000024	time 2.2015 (2.2114)	loss 2.5087 (3.0138)	grad_norm 2.6878 (3.1420)	
[2022-01-26 14:08:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1170/1251]	eta 0:02:59 lr 0.000024	time 1.8257 (2.2108)	loss 2.7389 (3.0137)	grad_norm 2.8942 (3.1426)	
[2022-01-26 14:08:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1180/1251]	eta 0:02:36 lr 0.000024	time 1.9815 (2.2108)	loss 1.9163 (3.0130)	grad_norm 3.7316 (3.1443)	
[2022-01-26 14:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1190/1251]	eta 0:02:14 lr 0.000024	time 1.9569 (2.2118)	loss 2.8298 (3.0136)	grad_norm 2.9586 (3.1444)	
[2022-01-26 14:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1200/1251]	eta 0:01:52 lr 0.000024	time 2.7025 (2.2132)	loss 3.2175 (3.0122)	grad_norm 3.3891 (3.1432)	
[2022-01-26 14:09:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1210/1251]	eta 0:01:30 lr 0.000024	time 1.7937 (2.2136)	loss 3.2669 (3.0116)	grad_norm 5.3746 (3.1447)	
[2022-01-26 14:10:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1220/1251]	eta 0:01:08 lr 0.000024	time 1.5899 (2.2126)	loss 2.8369 (3.0130)	grad_norm 2.6353 (3.1437)	
[2022-01-26 14:10:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1230/1251]	eta 0:00:46 lr 0.000024	time 1.6328 (2.2110)	loss 2.4070 (3.0127)	grad_norm 2.9759 (3.1445)	
[2022-01-26 14:10:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1240/1251]	eta 0:00:24 lr 0.000024	time 1.9095 (2.2112)	loss 3.1504 (3.0110)	grad_norm 3.0428 (3.1440)	
[2022-01-26 14:11:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [276/300][1250/1251]	eta 0:00:02 lr 0.000024	time 1.2099 (2.2057)	loss 2.1457 (3.0092)	grad_norm 2.9362 (3.1425)	
[2022-01-26 14:11:03 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 276 training takes 0:45:59
[2022-01-26 14:11:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.001 (18.001)	Loss 0.7028 (0.7028)	Acc@1 84.375 (84.375)	Acc@5 96.387 (96.387)	
[2022-01-26 14:11:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.812 (3.376)	Loss 0.8725 (0.7891)	Acc@1 80.273 (81.809)	Acc@5 94.434 (95.739)	
[2022-01-26 14:11:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.595 (2.619)	Loss 0.8424 (0.8062)	Acc@1 80.762 (81.445)	Acc@5 94.727 (95.503)	
[2022-01-26 14:12:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.928 (2.316)	Loss 0.8009 (0.8091)	Acc@1 81.738 (81.370)	Acc@5 96.484 (95.508)	
[2022-01-26 14:12:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.925 (2.231)	Loss 0.8641 (0.8189)	Acc@1 79.980 (81.014)	Acc@5 94.824 (95.410)	
[2022-01-26 14:12:41 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.048 Acc@5 95.400
[2022-01-26 14:12:41 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.0%
[2022-01-26 14:12:41 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.07%
[2022-01-26 14:13:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][0/1251]	eta 7:47:34 lr 0.000024	time 22.4257 (22.4257)	loss 2.3425 (2.3425)	grad_norm 2.5916 (2.5916)	
[2022-01-26 14:13:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][10/1251]	eta 1:25:55 lr 0.000024	time 2.0921 (4.1544)	loss 3.2997 (2.7977)	grad_norm 2.8175 (3.6182)	
[2022-01-26 14:13:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][20/1251]	eta 1:06:52 lr 0.000024	time 1.3449 (3.2596)	loss 3.4921 (2.9226)	grad_norm 2.5747 (3.3823)	
[2022-01-26 14:14:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][30/1251]	eta 0:58:40 lr 0.000024	time 1.9790 (2.8833)	loss 3.4842 (2.9483)	grad_norm 3.4301 (3.2882)	
[2022-01-26 14:14:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][40/1251]	eta 0:54:57 lr 0.000024	time 3.6918 (2.7228)	loss 2.4267 (2.9356)	grad_norm 2.6797 (3.3073)	
[2022-01-26 14:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][50/1251]	eta 0:52:53 lr 0.000024	time 3.1875 (2.6425)	loss 3.0000 (2.9253)	grad_norm 2.9403 (3.2514)	
[2022-01-26 14:15:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][60/1251]	eta 0:51:06 lr 0.000024	time 1.9353 (2.5745)	loss 3.1122 (2.9399)	grad_norm 2.9837 (3.2324)	
[2022-01-26 14:15:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][70/1251]	eta 0:49:35 lr 0.000024	time 1.7740 (2.5197)	loss 2.8620 (2.9759)	grad_norm 3.1008 (3.2445)	
[2022-01-26 14:16:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][80/1251]	eta 0:48:40 lr 0.000024	time 3.7200 (2.4939)	loss 3.1670 (2.9680)	grad_norm 3.6180 (3.2165)	
[2022-01-26 14:16:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][90/1251]	eta 0:47:39 lr 0.000024	time 2.7794 (2.4632)	loss 3.7549 (2.9853)	grad_norm 2.9806 (3.2119)	
[2022-01-26 14:16:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][100/1251]	eta 0:46:39 lr 0.000024	time 1.9365 (2.4320)	loss 3.1617 (2.9686)	grad_norm 3.0352 (3.1894)	
[2022-01-26 14:17:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][110/1251]	eta 0:45:38 lr 0.000024	time 1.8161 (2.3999)	loss 2.7411 (2.9744)	grad_norm 3.3020 (3.1982)	
[2022-01-26 14:17:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][120/1251]	eta 0:45:01 lr 0.000024	time 3.1605 (2.3884)	loss 2.3530 (2.9786)	grad_norm 3.2879 (3.1939)	
[2022-01-26 14:17:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][130/1251]	eta 0:44:23 lr 0.000024	time 2.1784 (2.3761)	loss 3.5526 (2.9892)	grad_norm 3.3594 (3.1875)	
[2022-01-26 14:18:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][140/1251]	eta 0:43:26 lr 0.000024	time 1.8096 (2.3461)	loss 3.4152 (2.9921)	grad_norm 2.7056 (3.1739)	
[2022-01-26 14:18:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][150/1251]	eta 0:42:40 lr 0.000024	time 2.4788 (2.3260)	loss 1.9761 (2.9870)	grad_norm 3.0646 (3.1887)	
[2022-01-26 14:18:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][160/1251]	eta 0:42:15 lr 0.000024	time 3.0434 (2.3241)	loss 3.5042 (2.9877)	grad_norm 2.7198 (3.1772)	
[2022-01-26 14:19:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][170/1251]	eta 0:41:44 lr 0.000024	time 1.8455 (2.3172)	loss 3.0850 (2.9825)	grad_norm 2.9580 (3.1796)	
[2022-01-26 14:19:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][180/1251]	eta 0:41:17 lr 0.000024	time 1.8919 (2.3129)	loss 2.7157 (2.9757)	grad_norm 2.7737 (3.1701)	
[2022-01-26 14:20:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][190/1251]	eta 0:40:50 lr 0.000024	time 2.0495 (2.3094)	loss 2.0130 (2.9644)	grad_norm 3.5766 (3.1688)	
[2022-01-26 14:20:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][200/1251]	eta 0:40:28 lr 0.000024	time 3.1301 (2.3102)	loss 2.3069 (2.9561)	grad_norm 2.9585 (3.1640)	
[2022-01-26 14:20:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][210/1251]	eta 0:39:56 lr 0.000024	time 1.8238 (2.3019)	loss 3.5725 (2.9496)	grad_norm 2.7430 (3.1641)	
[2022-01-26 14:21:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][220/1251]	eta 0:39:25 lr 0.000024	time 1.6188 (2.2941)	loss 2.7182 (2.9566)	grad_norm 3.3870 (3.1720)	
[2022-01-26 14:21:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][230/1251]	eta 0:38:55 lr 0.000024	time 2.1936 (2.2874)	loss 3.0944 (2.9676)	grad_norm 3.1307 (3.1838)	
[2022-01-26 14:21:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][240/1251]	eta 0:38:33 lr 0.000024	time 3.0236 (2.2883)	loss 3.0966 (2.9789)	grad_norm 2.7179 (3.1764)	
[2022-01-26 14:22:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][250/1251]	eta 0:38:01 lr 0.000024	time 1.9947 (2.2790)	loss 3.2205 (2.9801)	grad_norm 3.0536 (3.1751)	
[2022-01-26 14:22:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][260/1251]	eta 0:37:30 lr 0.000024	time 1.8619 (2.2714)	loss 3.0241 (2.9796)	grad_norm 2.9887 (3.1719)	
[2022-01-26 14:22:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][270/1251]	eta 0:37:00 lr 0.000024	time 1.8774 (2.2635)	loss 2.1036 (2.9715)	grad_norm 2.9044 (3.1663)	
[2022-01-26 14:23:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][280/1251]	eta 0:36:26 lr 0.000024	time 1.7883 (2.2520)	loss 3.4477 (2.9804)	grad_norm 3.0083 (3.1642)	
[2022-01-26 14:23:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][290/1251]	eta 0:35:55 lr 0.000024	time 1.5769 (2.2428)	loss 2.9500 (2.9818)	grad_norm 3.3073 (3.1662)	
[2022-01-26 14:23:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][300/1251]	eta 0:35:28 lr 0.000024	time 1.8714 (2.2377)	loss 2.6884 (2.9771)	grad_norm 3.4370 (3.1659)	
[2022-01-26 14:24:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][310/1251]	eta 0:35:09 lr 0.000024	time 2.5613 (2.2413)	loss 3.3869 (2.9778)	grad_norm 3.4011 (3.1656)	
[2022-01-26 14:24:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][320/1251]	eta 0:34:46 lr 0.000024	time 2.1385 (2.2406)	loss 3.5694 (2.9733)	grad_norm 3.3631 (3.1605)	
[2022-01-26 14:25:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][330/1251]	eta 0:34:32 lr 0.000024	time 2.2262 (2.2504)	loss 3.1761 (2.9695)	grad_norm 3.5035 (3.1648)	
[2022-01-26 14:25:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][340/1251]	eta 0:34:22 lr 0.000024	time 2.3161 (2.2636)	loss 3.4555 (2.9765)	grad_norm 3.2051 (3.1640)	
[2022-01-26 14:25:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][350/1251]	eta 0:34:03 lr 0.000024	time 2.1398 (2.2681)	loss 3.2533 (2.9811)	grad_norm 3.1943 (3.1620)	
[2022-01-26 14:26:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][360/1251]	eta 0:33:37 lr 0.000024	time 1.5395 (2.2647)	loss 3.1981 (2.9877)	grad_norm 3.5898 (3.1623)	
[2022-01-26 14:26:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][370/1251]	eta 0:33:08 lr 0.000024	time 1.6605 (2.2574)	loss 2.6724 (2.9893)	grad_norm 3.4121 (3.1663)	
[2022-01-26 14:26:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][380/1251]	eta 0:32:41 lr 0.000024	time 1.8438 (2.2526)	loss 3.3620 (2.9900)	grad_norm 3.1585 (3.1653)	
[2022-01-26 14:27:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][390/1251]	eta 0:32:21 lr 0.000024	time 1.9326 (2.2550)	loss 3.3263 (2.9942)	grad_norm 3.9427 (3.1666)	
[2022-01-26 14:27:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][400/1251]	eta 0:31:53 lr 0.000024	time 1.7742 (2.2491)	loss 3.4408 (2.9932)	grad_norm 5.4052 (3.1726)	
[2022-01-26 14:28:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][410/1251]	eta 0:31:27 lr 0.000024	time 1.9041 (2.2441)	loss 3.0999 (2.9883)	grad_norm 3.6807 (3.1813)	
[2022-01-26 14:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][420/1251]	eta 0:31:01 lr 0.000024	time 1.5563 (2.2400)	loss 2.8513 (2.9933)	grad_norm 2.6660 (3.1774)	
[2022-01-26 14:28:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][430/1251]	eta 0:30:34 lr 0.000024	time 2.4053 (2.2349)	loss 2.3732 (2.9879)	grad_norm 3.0605 (3.1710)	
[2022-01-26 14:29:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][440/1251]	eta 0:30:13 lr 0.000024	time 2.7629 (2.2362)	loss 3.4735 (2.9887)	grad_norm 3.8324 (3.1692)	
[2022-01-26 14:29:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][450/1251]	eta 0:29:51 lr 0.000024	time 2.3748 (2.2369)	loss 3.6594 (2.9923)	grad_norm 3.4664 (3.1682)	
[2022-01-26 14:29:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][460/1251]	eta 0:29:27 lr 0.000024	time 2.8888 (2.2346)	loss 3.8966 (2.9988)	grad_norm 3.1515 (3.1651)	
[2022-01-26 14:30:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][470/1251]	eta 0:29:05 lr 0.000024	time 2.7633 (2.2355)	loss 3.6056 (3.0012)	grad_norm 3.1438 (3.1626)	
[2022-01-26 14:30:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][480/1251]	eta 0:28:43 lr 0.000024	time 1.6836 (2.2358)	loss 3.4243 (3.0043)	grad_norm 3.5443 (3.1642)	
[2022-01-26 14:31:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][490/1251]	eta 0:28:22 lr 0.000024	time 2.5446 (2.2370)	loss 3.1405 (3.0075)	grad_norm 3.1965 (3.1782)	
[2022-01-26 14:31:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][500/1251]	eta 0:27:57 lr 0.000024	time 2.6583 (2.2342)	loss 3.0040 (3.0039)	grad_norm 2.9515 (3.1783)	
[2022-01-26 14:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][510/1251]	eta 0:27:32 lr 0.000024	time 2.1524 (2.2298)	loss 2.8187 (3.0048)	grad_norm 2.8028 (3.1799)	
[2022-01-26 14:32:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][520/1251]	eta 0:27:07 lr 0.000024	time 2.4880 (2.2267)	loss 3.6548 (3.0035)	grad_norm 3.4452 (3.1803)	
[2022-01-26 14:32:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][530/1251]	eta 0:26:45 lr 0.000024	time 2.3295 (2.2261)	loss 2.1542 (3.0024)	grad_norm 3.4709 (3.1775)	
[2022-01-26 14:32:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][540/1251]	eta 0:26:23 lr 0.000024	time 2.4619 (2.2277)	loss 3.3860 (3.0059)	grad_norm 3.1973 (3.1781)	
[2022-01-26 14:33:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][550/1251]	eta 0:26:00 lr 0.000024	time 1.6382 (2.2256)	loss 3.2923 (3.0061)	grad_norm 3.6253 (3.1772)	
[2022-01-26 14:33:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][560/1251]	eta 0:25:38 lr 0.000024	time 2.6647 (2.2270)	loss 2.3984 (3.0057)	grad_norm 3.3226 (3.1771)	
[2022-01-26 14:33:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][570/1251]	eta 0:25:15 lr 0.000024	time 2.5419 (2.2256)	loss 3.5465 (3.0094)	grad_norm 3.5095 (3.1813)	
[2022-01-26 14:34:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][580/1251]	eta 0:24:54 lr 0.000024	time 1.9802 (2.2268)	loss 3.1807 (3.0089)	grad_norm 2.9920 (3.1826)	
[2022-01-26 14:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][590/1251]	eta 0:24:32 lr 0.000024	time 1.8522 (2.2282)	loss 3.1187 (3.0091)	grad_norm 3.4129 (3.1801)	
[2022-01-26 14:34:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][600/1251]	eta 0:24:09 lr 0.000024	time 2.2874 (2.2269)	loss 2.7731 (3.0063)	grad_norm 3.6674 (3.1823)	
[2022-01-26 14:35:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][610/1251]	eta 0:23:45 lr 0.000024	time 2.8458 (2.2240)	loss 1.9170 (3.0040)	grad_norm 3.0488 (3.1807)	
[2022-01-26 14:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][620/1251]	eta 0:23:20 lr 0.000024	time 1.5988 (2.2197)	loss 2.9778 (3.0057)	grad_norm 2.6804 (3.1772)	
[2022-01-26 14:36:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][630/1251]	eta 0:22:58 lr 0.000024	time 1.9197 (2.2201)	loss 2.6223 (3.0041)	grad_norm 3.6702 (3.1768)	
[2022-01-26 14:36:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][640/1251]	eta 0:22:35 lr 0.000024	time 2.2398 (2.2182)	loss 2.6033 (3.0028)	grad_norm 2.9535 (3.1769)	
[2022-01-26 14:36:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][650/1251]	eta 0:22:13 lr 0.000024	time 2.8690 (2.2183)	loss 2.7214 (3.0031)	grad_norm 2.5405 (3.1720)	
[2022-01-26 14:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][660/1251]	eta 0:21:50 lr 0.000024	time 2.3788 (2.2177)	loss 3.5358 (3.0019)	grad_norm 3.5702 (3.1697)	
[2022-01-26 14:37:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][670/1251]	eta 0:21:28 lr 0.000024	time 2.6304 (2.2185)	loss 3.4879 (3.0019)	grad_norm 3.2886 (3.1684)	
[2022-01-26 14:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][680/1251]	eta 0:21:07 lr 0.000024	time 2.2395 (2.2203)	loss 3.5407 (3.0003)	grad_norm 3.6392 (3.1716)	
[2022-01-26 14:38:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][690/1251]	eta 0:20:46 lr 0.000024	time 2.0647 (2.2224)	loss 2.7681 (3.0035)	grad_norm 2.8983 (3.1678)	
[2022-01-26 14:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][700/1251]	eta 0:20:23 lr 0.000024	time 1.7814 (2.2205)	loss 2.9048 (3.0040)	grad_norm 3.7125 (3.1657)	
[2022-01-26 14:38:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][710/1251]	eta 0:19:59 lr 0.000024	time 1.6037 (2.2180)	loss 2.2150 (3.0017)	grad_norm 3.9869 (3.1667)	
[2022-01-26 14:39:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][720/1251]	eta 0:19:36 lr 0.000024	time 1.9533 (2.2162)	loss 2.4622 (3.0022)	grad_norm 3.3163 (3.1646)	
[2022-01-26 14:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][730/1251]	eta 0:19:14 lr 0.000024	time 2.4976 (2.2155)	loss 2.8148 (3.0020)	grad_norm 3.3973 (3.1649)	
[2022-01-26 14:40:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][740/1251]	eta 0:18:51 lr 0.000024	time 1.5812 (2.2140)	loss 3.2823 (3.0037)	grad_norm 3.1787 (3.1662)	
[2022-01-26 14:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][750/1251]	eta 0:18:30 lr 0.000024	time 1.9776 (2.2160)	loss 3.4059 (3.0061)	grad_norm 3.0299 (3.1656)	
[2022-01-26 14:40:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][760/1251]	eta 0:18:07 lr 0.000024	time 2.2391 (2.2152)	loss 2.9943 (3.0029)	grad_norm 3.1326 (3.1661)	
[2022-01-26 14:41:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][770/1251]	eta 0:17:45 lr 0.000024	time 2.5126 (2.2145)	loss 3.5545 (3.0061)	grad_norm 3.0600 (3.1667)	
[2022-01-26 14:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][780/1251]	eta 0:17:22 lr 0.000024	time 1.5360 (2.2137)	loss 3.4317 (3.0066)	grad_norm 3.1558 (3.1713)	
[2022-01-26 14:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][790/1251]	eta 0:17:00 lr 0.000024	time 2.1507 (2.2142)	loss 3.6177 (3.0053)	grad_norm 3.0919 (3.1721)	
[2022-01-26 14:42:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][800/1251]	eta 0:16:38 lr 0.000024	time 1.6817 (2.2134)	loss 3.3774 (3.0057)	grad_norm 2.7958 (3.1710)	
[2022-01-26 14:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][810/1251]	eta 0:16:16 lr 0.000023	time 3.2409 (2.2150)	loss 2.2828 (3.0042)	grad_norm 2.7678 (3.1712)	
[2022-01-26 14:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][820/1251]	eta 0:15:54 lr 0.000023	time 1.9438 (2.2149)	loss 3.1921 (3.0048)	grad_norm 2.9650 (3.1720)	
[2022-01-26 14:43:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][830/1251]	eta 0:15:32 lr 0.000023	time 1.8348 (2.2140)	loss 3.4492 (3.0082)	grad_norm 2.9923 (3.1732)	
[2022-01-26 14:43:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][840/1251]	eta 0:15:09 lr 0.000023	time 1.8291 (2.2129)	loss 2.7322 (3.0094)	grad_norm 2.7567 (3.1726)	
[2022-01-26 14:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][850/1251]	eta 0:14:48 lr 0.000023	time 2.7129 (2.2146)	loss 3.2681 (3.0092)	grad_norm 3.2708 (3.1731)	
[2022-01-26 14:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][860/1251]	eta 0:14:25 lr 0.000023	time 1.5844 (2.2143)	loss 2.6090 (3.0083)	grad_norm 3.1027 (3.1736)	
[2022-01-26 14:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][870/1251]	eta 0:14:03 lr 0.000023	time 1.8866 (2.2138)	loss 2.8908 (3.0081)	grad_norm 3.1673 (3.1712)	
[2022-01-26 14:45:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][880/1251]	eta 0:13:40 lr 0.000023	time 1.5728 (2.2119)	loss 3.6606 (3.0091)	grad_norm 3.0833 (3.1699)	
[2022-01-26 14:45:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][890/1251]	eta 0:13:18 lr 0.000023	time 2.4937 (2.2132)	loss 2.8477 (3.0100)	grad_norm 2.7779 (3.1679)	
[2022-01-26 14:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][900/1251]	eta 0:12:57 lr 0.000023	time 1.9229 (2.2151)	loss 2.5902 (3.0093)	grad_norm 2.8644 (3.1660)	
[2022-01-26 14:46:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][910/1251]	eta 0:12:35 lr 0.000023	time 2.1349 (2.2161)	loss 3.3061 (3.0081)	grad_norm 3.3187 (3.1643)	
[2022-01-26 14:46:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][920/1251]	eta 0:12:12 lr 0.000023	time 1.7807 (2.2131)	loss 2.4904 (3.0062)	grad_norm 3.2475 (3.1635)	
[2022-01-26 14:46:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][930/1251]	eta 0:11:49 lr 0.000023	time 1.8007 (2.2098)	loss 3.4036 (3.0069)	grad_norm 4.0474 (3.1651)	
[2022-01-26 14:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][940/1251]	eta 0:11:26 lr 0.000023	time 1.9852 (2.2078)	loss 3.4879 (3.0091)	grad_norm 3.2698 (3.1646)	
[2022-01-26 14:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][950/1251]	eta 0:11:04 lr 0.000023	time 2.2385 (2.2081)	loss 3.5297 (3.0079)	grad_norm 3.1428 (3.1636)	
[2022-01-26 14:48:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][960/1251]	eta 0:10:42 lr 0.000023	time 1.7644 (2.2076)	loss 2.4891 (3.0042)	grad_norm 3.0684 (3.1630)	
[2022-01-26 14:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][970/1251]	eta 0:10:20 lr 0.000023	time 2.5157 (2.2079)	loss 3.4609 (3.0062)	grad_norm 3.0530 (3.1647)	
[2022-01-26 14:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][980/1251]	eta 0:09:58 lr 0.000023	time 2.1217 (2.2075)	loss 3.5521 (3.0049)	grad_norm 4.2449 (3.1664)	
[2022-01-26 14:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][990/1251]	eta 0:09:36 lr 0.000023	time 1.5180 (2.2074)	loss 3.3641 (3.0034)	grad_norm 3.0821 (3.1649)	
[2022-01-26 14:49:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1000/1251]	eta 0:09:14 lr 0.000023	time 2.2318 (2.2099)	loss 2.7696 (3.0027)	grad_norm 2.7208 (3.1638)	
[2022-01-26 14:49:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1010/1251]	eta 0:08:52 lr 0.000023	time 1.8074 (2.2112)	loss 3.1805 (3.0008)	grad_norm 2.8132 (3.1632)	
[2022-01-26 14:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1020/1251]	eta 0:08:30 lr 0.000023	time 1.8651 (2.2105)	loss 2.0895 (2.9993)	grad_norm 3.1312 (3.1623)	
[2022-01-26 14:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1030/1251]	eta 0:08:08 lr 0.000023	time 1.6516 (2.2082)	loss 3.3491 (2.9986)	grad_norm 2.7538 (3.1610)	
[2022-01-26 14:50:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1040/1251]	eta 0:07:45 lr 0.000023	time 1.6917 (2.2061)	loss 1.8731 (2.9967)	grad_norm 3.6812 (3.1624)	
[2022-01-26 14:51:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1050/1251]	eta 0:07:23 lr 0.000023	time 1.8970 (2.2052)	loss 3.2845 (2.9953)	grad_norm 3.1841 (3.1645)	
[2022-01-26 14:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1060/1251]	eta 0:07:01 lr 0.000023	time 2.7774 (2.2055)	loss 3.6237 (2.9984)	grad_norm 3.4183 (3.1640)	
[2022-01-26 14:52:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1070/1251]	eta 0:06:39 lr 0.000023	time 1.6793 (2.2059)	loss 3.3054 (2.9980)	grad_norm 2.9966 (3.1626)	
[2022-01-26 14:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1080/1251]	eta 0:06:17 lr 0.000023	time 2.5271 (2.2076)	loss 3.1842 (3.0002)	grad_norm 2.8498 (3.1605)	
[2022-01-26 14:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1090/1251]	eta 0:05:55 lr 0.000023	time 1.8496 (2.2069)	loss 3.6880 (3.0007)	grad_norm 3.0253 (3.1600)	
[2022-01-26 14:53:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1100/1251]	eta 0:05:33 lr 0.000023	time 1.5432 (2.2068)	loss 2.5698 (3.0000)	grad_norm 2.7983 (3.1597)	
[2022-01-26 14:53:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1110/1251]	eta 0:05:11 lr 0.000023	time 1.5786 (2.2066)	loss 3.1606 (3.0005)	grad_norm 5.8369 (3.1610)	
[2022-01-26 14:53:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1120/1251]	eta 0:04:49 lr 0.000023	time 1.7765 (2.2067)	loss 2.9090 (3.0004)	grad_norm 2.8010 (3.1771)	
[2022-01-26 14:54:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1130/1251]	eta 0:04:26 lr 0.000023	time 1.8535 (2.2052)	loss 3.1582 (3.0004)	grad_norm 2.7525 (3.1750)	
[2022-01-26 14:54:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1140/1251]	eta 0:04:04 lr 0.000023	time 1.8193 (2.2055)	loss 2.9845 (2.9985)	grad_norm 4.6418 (3.1751)	
[2022-01-26 14:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1150/1251]	eta 0:03:42 lr 0.000023	time 1.8847 (2.2066)	loss 3.4159 (2.9984)	grad_norm 2.9830 (3.1746)	
[2022-01-26 14:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1160/1251]	eta 0:03:20 lr 0.000023	time 2.2021 (2.2065)	loss 3.4071 (2.9971)	grad_norm 2.6163 (3.1729)	
[2022-01-26 14:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1170/1251]	eta 0:02:58 lr 0.000023	time 2.0069 (2.2052)	loss 2.9878 (2.9964)	grad_norm 2.9621 (3.1710)	
[2022-01-26 14:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1180/1251]	eta 0:02:36 lr 0.000023	time 2.1331 (2.2062)	loss 3.5758 (2.9981)	grad_norm 3.0336 (3.1720)	
[2022-01-26 14:56:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1190/1251]	eta 0:02:14 lr 0.000023	time 1.5594 (2.2068)	loss 2.6985 (2.9984)	grad_norm 2.9797 (3.1717)	
[2022-01-26 14:56:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1200/1251]	eta 0:01:52 lr 0.000023	time 1.8543 (2.2066)	loss 2.3458 (2.9977)	grad_norm 3.1459 (3.1707)	
[2022-01-26 14:57:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1210/1251]	eta 0:01:30 lr 0.000023	time 1.8991 (2.2045)	loss 3.3744 (2.9990)	grad_norm 2.7382 (3.1701)	
[2022-01-26 14:57:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1220/1251]	eta 0:01:08 lr 0.000023	time 2.1700 (2.2041)	loss 2.8579 (2.9991)	grad_norm 3.0496 (3.1719)	
[2022-01-26 14:57:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1230/1251]	eta 0:00:46 lr 0.000023	time 2.4290 (2.2038)	loss 2.1286 (3.0005)	grad_norm 2.7509 (3.1726)	
[2022-01-26 14:58:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1240/1251]	eta 0:00:24 lr 0.000023	time 2.0495 (2.2029)	loss 3.2615 (3.0026)	grad_norm 2.9948 (3.1744)	
[2022-01-26 14:58:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [277/300][1250/1251]	eta 0:00:02 lr 0.000023	time 1.1284 (2.1982)	loss 3.0327 (3.0006)	grad_norm 2.7407 (3.1736)	
[2022-01-26 14:58:31 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 277 training takes 0:45:50
[2022-01-26 14:58:50 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.315 (18.315)	Loss 0.9665 (0.9665)	Acc@1 78.516 (78.516)	Acc@5 94.531 (94.531)	
[2022-01-26 14:59:10 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.321 (3.500)	Loss 0.7511 (0.8187)	Acc@1 82.324 (80.753)	Acc@5 95.410 (95.490)	
[2022-01-26 14:59:27 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.571 (2.650)	Loss 0.8202 (0.8097)	Acc@1 80.762 (80.897)	Acc@5 95.410 (95.489)	
[2022-01-26 14:59:43 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.651 (2.297)	Loss 0.7858 (0.8115)	Acc@1 81.738 (80.834)	Acc@5 95.801 (95.407)	
[2022-01-26 15:00:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.155 (2.211)	Loss 0.8420 (0.8099)	Acc@1 80.762 (80.928)	Acc@5 95.410 (95.439)	
[2022-01-26 15:00:10 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.008 Acc@5 95.376
[2022-01-26 15:00:10 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.0%
[2022-01-26 15:00:10 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.07%
[2022-01-26 15:00:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][0/1251]	eta 7:28:52 lr 0.000023	time 21.5289 (21.5289)	loss 3.3051 (3.3051)	grad_norm 3.2581 (3.2581)	
[2022-01-26 15:00:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][10/1251]	eta 1:23:57 lr 0.000023	time 2.1002 (4.0596)	loss 3.4471 (3.1360)	grad_norm 2.9568 (3.0001)	
[2022-01-26 15:01:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][20/1251]	eta 1:04:42 lr 0.000023	time 1.6778 (3.1541)	loss 3.4094 (3.0231)	grad_norm 3.0483 (3.1167)	
[2022-01-26 15:01:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][30/1251]	eta 0:58:39 lr 0.000023	time 1.8736 (2.8825)	loss 2.4791 (3.0019)	grad_norm 3.7406 (3.1129)	
[2022-01-26 15:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][40/1251]	eta 0:55:33 lr 0.000023	time 4.2041 (2.7527)	loss 3.4982 (3.0263)	grad_norm 3.0881 (3.1246)	
[2022-01-26 15:02:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][50/1251]	eta 0:52:54 lr 0.000023	time 2.1285 (2.6433)	loss 2.8424 (2.9806)	grad_norm 2.7931 (3.1102)	
[2022-01-26 15:02:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][60/1251]	eta 0:50:49 lr 0.000023	time 1.5470 (2.5602)	loss 2.6107 (2.9575)	grad_norm 3.5473 (3.0975)	
[2022-01-26 15:03:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][70/1251]	eta 0:49:44 lr 0.000023	time 2.1329 (2.5269)	loss 3.4746 (3.0011)	grad_norm 2.9019 (3.1186)	
[2022-01-26 15:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][80/1251]	eta 0:48:52 lr 0.000023	time 3.8673 (2.5046)	loss 4.0039 (2.9902)	grad_norm 3.3129 (3.1143)	
[2022-01-26 15:03:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][90/1251]	eta 0:47:34 lr 0.000023	time 2.2638 (2.4588)	loss 2.1828 (2.9917)	grad_norm 3.2341 (3.1537)	
[2022-01-26 15:04:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][100/1251]	eta 0:46:41 lr 0.000023	time 1.7264 (2.4341)	loss 3.1633 (3.0114)	grad_norm 2.8371 (3.1795)	
[2022-01-26 15:04:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][110/1251]	eta 0:46:08 lr 0.000023	time 2.9904 (2.4267)	loss 3.1129 (3.0153)	grad_norm 2.8880 (3.1583)	
[2022-01-26 15:05:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][120/1251]	eta 0:45:23 lr 0.000023	time 2.6275 (2.4078)	loss 3.1059 (3.0110)	grad_norm 3.7171 (3.1624)	
[2022-01-26 15:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][130/1251]	eta 0:44:30 lr 0.000023	time 1.5669 (2.3822)	loss 3.5280 (3.0157)	grad_norm 3.0359 (3.1450)	
[2022-01-26 15:05:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][140/1251]	eta 0:43:55 lr 0.000023	time 1.9229 (2.3721)	loss 2.9026 (3.0115)	grad_norm 3.3129 (3.1433)	
[2022-01-26 15:06:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][150/1251]	eta 0:43:30 lr 0.000023	time 3.0716 (2.3712)	loss 2.8288 (3.0047)	grad_norm 3.4225 (3.1407)	
[2022-01-26 15:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][160/1251]	eta 0:42:53 lr 0.000023	time 2.4939 (2.3584)	loss 3.3374 (3.0106)	grad_norm 2.8227 (3.1288)	
[2022-01-26 15:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][170/1251]	eta 0:42:09 lr 0.000023	time 1.9747 (2.3400)	loss 2.7429 (3.0034)	grad_norm 3.5043 (3.1236)	
[2022-01-26 15:07:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][180/1251]	eta 0:41:32 lr 0.000023	time 2.2476 (2.3271)	loss 2.9663 (2.9935)	grad_norm 2.6342 (3.1113)	
[2022-01-26 15:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][190/1251]	eta 0:40:55 lr 0.000023	time 2.2348 (2.3146)	loss 2.7303 (2.9906)	grad_norm 3.7243 (3.1190)	
[2022-01-26 15:07:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][200/1251]	eta 0:40:22 lr 0.000023	time 2.2303 (2.3053)	loss 3.6426 (2.9895)	grad_norm 3.4666 (3.1120)	
[2022-01-26 15:08:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][210/1251]	eta 0:39:51 lr 0.000023	time 2.2693 (2.2971)	loss 3.2332 (2.9941)	grad_norm 3.1669 (3.1130)	
[2022-01-26 15:08:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][220/1251]	eta 0:39:23 lr 0.000023	time 2.3616 (2.2920)	loss 3.2143 (2.9852)	grad_norm 3.3409 (3.1083)	
[2022-01-26 15:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][230/1251]	eta 0:38:49 lr 0.000023	time 1.7379 (2.2819)	loss 3.1230 (2.9811)	grad_norm 3.7611 (3.1120)	
[2022-01-26 15:09:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][240/1251]	eta 0:38:26 lr 0.000023	time 2.4923 (2.2813)	loss 3.3339 (2.9734)	grad_norm 3.0228 (3.1264)	
[2022-01-26 15:09:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][250/1251]	eta 0:38:02 lr 0.000023	time 2.6131 (2.2798)	loss 2.9353 (2.9817)	grad_norm 2.7266 (3.1287)	
[2022-01-26 15:10:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][260/1251]	eta 0:37:35 lr 0.000023	time 2.8620 (2.2764)	loss 1.9599 (2.9833)	grad_norm 3.7247 (3.1269)	
[2022-01-26 15:10:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][270/1251]	eta 0:37:04 lr 0.000023	time 1.8338 (2.2681)	loss 3.2092 (2.9861)	grad_norm 2.8548 (3.1215)	
[2022-01-26 15:10:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][280/1251]	eta 0:36:40 lr 0.000023	time 2.7678 (2.2663)	loss 2.0069 (2.9803)	grad_norm 2.9814 (3.1234)	
[2022-01-26 15:11:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][290/1251]	eta 0:36:12 lr 0.000023	time 2.1894 (2.2602)	loss 3.4096 (2.9817)	grad_norm 3.1855 (3.1194)	
[2022-01-26 15:11:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][300/1251]	eta 0:35:46 lr 0.000023	time 3.0997 (2.2574)	loss 3.6442 (2.9809)	grad_norm 5.0991 (3.1239)	
[2022-01-26 15:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][310/1251]	eta 0:35:20 lr 0.000023	time 2.0117 (2.2537)	loss 3.3089 (2.9878)	grad_norm 3.0511 (3.1225)	
[2022-01-26 15:12:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][320/1251]	eta 0:34:57 lr 0.000023	time 2.1594 (2.2528)	loss 3.4959 (2.9914)	grad_norm 3.0605 (3.1227)	
[2022-01-26 15:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][330/1251]	eta 0:34:33 lr 0.000023	time 2.4278 (2.2510)	loss 3.2690 (3.0006)	grad_norm 3.0559 (3.1188)	
[2022-01-26 15:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][340/1251]	eta 0:34:11 lr 0.000023	time 2.5778 (2.2514)	loss 2.4696 (3.0011)	grad_norm 3.4778 (3.1244)	
[2022-01-26 15:13:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][350/1251]	eta 0:33:49 lr 0.000023	time 1.5505 (2.2529)	loss 3.5020 (3.0031)	grad_norm 2.6118 (3.1228)	
[2022-01-26 15:13:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][360/1251]	eta 0:33:24 lr 0.000023	time 1.8979 (2.2495)	loss 3.2461 (3.0038)	grad_norm 3.2096 (3.1229)	
[2022-01-26 15:14:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][370/1251]	eta 0:33:00 lr 0.000023	time 2.2130 (2.2485)	loss 3.0214 (3.0095)	grad_norm 3.2915 (3.1232)	
[2022-01-26 15:14:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][380/1251]	eta 0:32:35 lr 0.000023	time 2.5429 (2.2452)	loss 2.4285 (3.0000)	grad_norm 3.3794 (3.1198)	
[2022-01-26 15:14:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][390/1251]	eta 0:32:10 lr 0.000023	time 1.5662 (2.2426)	loss 3.5800 (2.9989)	grad_norm 4.1698 (3.1280)	
[2022-01-26 15:15:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][400/1251]	eta 0:31:47 lr 0.000023	time 1.8888 (2.2417)	loss 3.0917 (3.0000)	grad_norm 3.7372 (3.1318)	
[2022-01-26 15:15:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][410/1251]	eta 0:31:22 lr 0.000023	time 1.8736 (2.2389)	loss 1.8664 (2.9909)	grad_norm 3.6941 (3.1304)	
[2022-01-26 15:15:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][420/1251]	eta 0:31:00 lr 0.000023	time 1.9853 (2.2386)	loss 3.1003 (2.9893)	grad_norm 2.8408 (3.1316)	
[2022-01-26 15:16:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][430/1251]	eta 0:30:39 lr 0.000023	time 1.7969 (2.2408)	loss 3.5207 (2.9928)	grad_norm 3.0132 (3.1326)	
[2022-01-26 15:16:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][440/1251]	eta 0:30:15 lr 0.000023	time 1.8422 (2.2389)	loss 3.1192 (2.9922)	grad_norm 4.5380 (3.1346)	
[2022-01-26 15:17:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][450/1251]	eta 0:29:54 lr 0.000023	time 2.1725 (2.2404)	loss 3.1822 (2.9942)	grad_norm 2.7979 (3.1326)	
[2022-01-26 15:17:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][460/1251]	eta 0:29:29 lr 0.000023	time 1.9333 (2.2366)	loss 3.6204 (3.0010)	grad_norm 3.7555 (3.1342)	
[2022-01-26 15:17:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][470/1251]	eta 0:29:05 lr 0.000023	time 1.8723 (2.2351)	loss 3.1056 (3.0054)	grad_norm 3.2376 (3.1335)	
[2022-01-26 15:18:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][480/1251]	eta 0:28:41 lr 0.000023	time 1.8917 (2.2331)	loss 3.3502 (3.0059)	grad_norm 3.2421 (3.1312)	
[2022-01-26 15:18:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][490/1251]	eta 0:28:15 lr 0.000023	time 1.8914 (2.2285)	loss 3.7480 (3.0056)	grad_norm 3.0595 (3.1350)	
[2022-01-26 15:18:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][500/1251]	eta 0:27:52 lr 0.000023	time 2.0226 (2.2267)	loss 3.2708 (3.0050)	grad_norm 2.5360 (3.1356)	
[2022-01-26 15:19:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][510/1251]	eta 0:27:30 lr 0.000023	time 2.2379 (2.2276)	loss 3.5638 (3.0033)	grad_norm 3.1362 (3.1374)	
[2022-01-26 15:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][520/1251]	eta 0:27:11 lr 0.000023	time 3.0133 (2.2323)	loss 3.6373 (2.9995)	grad_norm 3.4554 (3.1538)	
[2022-01-26 15:19:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][530/1251]	eta 0:26:49 lr 0.000023	time 2.0523 (2.2319)	loss 2.7469 (2.9983)	grad_norm 3.1259 (3.1589)	
[2022-01-26 15:20:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][540/1251]	eta 0:26:25 lr 0.000023	time 1.9306 (2.2301)	loss 3.4512 (2.9973)	grad_norm 3.2176 (3.1644)	
[2022-01-26 15:20:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][550/1251]	eta 0:26:00 lr 0.000023	time 1.7228 (2.2258)	loss 2.5105 (2.9973)	grad_norm 2.7741 (3.1695)	
[2022-01-26 15:20:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][560/1251]	eta 0:25:37 lr 0.000023	time 3.0151 (2.2245)	loss 3.3312 (3.0009)	grad_norm 3.0954 (3.1705)	
[2022-01-26 15:21:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][570/1251]	eta 0:25:13 lr 0.000023	time 2.0338 (2.2221)	loss 3.3577 (3.0055)	grad_norm 3.0821 (3.1690)	
[2022-01-26 15:21:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][580/1251]	eta 0:24:51 lr 0.000023	time 2.3310 (2.2231)	loss 2.5189 (3.0056)	grad_norm 3.0072 (3.1673)	
[2022-01-26 15:22:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][590/1251]	eta 0:24:29 lr 0.000023	time 1.5245 (2.2233)	loss 2.4395 (3.0043)	grad_norm 3.3649 (3.1682)	
[2022-01-26 15:22:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][600/1251]	eta 0:24:05 lr 0.000023	time 1.5146 (2.2209)	loss 3.4049 (3.0066)	grad_norm 3.8913 (3.1723)	
[2022-01-26 15:22:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][610/1251]	eta 0:23:41 lr 0.000023	time 2.0299 (2.2177)	loss 3.3052 (3.0082)	grad_norm 3.0218 (3.1717)	
[2022-01-26 15:23:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][620/1251]	eta 0:23:17 lr 0.000022	time 2.2396 (2.2153)	loss 3.1832 (3.0054)	grad_norm 3.4162 (3.1693)	
[2022-01-26 15:23:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][630/1251]	eta 0:22:56 lr 0.000022	time 2.4313 (2.2166)	loss 2.9816 (3.0074)	grad_norm 3.1635 (3.1652)	
[2022-01-26 15:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][640/1251]	eta 0:22:34 lr 0.000022	time 2.3304 (2.2169)	loss 2.0672 (3.0045)	grad_norm 2.5997 (3.1615)	
[2022-01-26 15:24:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][650/1251]	eta 0:22:13 lr 0.000022	time 1.9457 (2.2185)	loss 2.8318 (3.0058)	grad_norm 2.8280 (3.1596)	
[2022-01-26 15:24:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][660/1251]	eta 0:21:51 lr 0.000022	time 2.1176 (2.2192)	loss 2.6437 (3.0073)	grad_norm 3.1128 (3.1605)	
[2022-01-26 15:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][670/1251]	eta 0:21:31 lr 0.000022	time 3.3945 (2.2234)	loss 2.3659 (3.0039)	grad_norm 2.7370 (3.1577)	
[2022-01-26 15:25:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][680/1251]	eta 0:21:09 lr 0.000022	time 1.9246 (2.2226)	loss 3.3593 (3.0026)	grad_norm 3.5026 (3.1595)	
[2022-01-26 15:25:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][690/1251]	eta 0:20:46 lr 0.000022	time 2.0021 (2.2215)	loss 2.3606 (3.0010)	grad_norm 3.3340 (3.1578)	
[2022-01-26 15:26:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][700/1251]	eta 0:20:22 lr 0.000022	time 1.7737 (2.2184)	loss 3.0453 (3.0026)	grad_norm 3.6946 (3.1582)	
[2022-01-26 15:26:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][710/1251]	eta 0:19:59 lr 0.000022	time 2.8621 (2.2175)	loss 3.7225 (3.0016)	grad_norm 3.1352 (3.1596)	
[2022-01-26 15:26:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][720/1251]	eta 0:19:36 lr 0.000022	time 2.0613 (2.2164)	loss 3.5722 (3.0009)	grad_norm 3.0345 (3.1598)	
[2022-01-26 15:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][730/1251]	eta 0:19:15 lr 0.000022	time 2.4272 (2.2171)	loss 2.5556 (2.9962)	grad_norm 2.9557 (3.1600)	
[2022-01-26 15:27:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][740/1251]	eta 0:18:53 lr 0.000022	time 1.7112 (2.2174)	loss 1.9962 (2.9971)	grad_norm 3.4946 (3.1639)	
[2022-01-26 15:27:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][750/1251]	eta 0:18:30 lr 0.000022	time 2.5947 (2.2172)	loss 3.2354 (2.9977)	grad_norm 3.2087 (3.1642)	
[2022-01-26 15:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][760/1251]	eta 0:18:07 lr 0.000022	time 2.1871 (2.2152)	loss 1.9167 (2.9969)	grad_norm 2.8732 (3.1646)	
[2022-01-26 15:28:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][770/1251]	eta 0:17:44 lr 0.000022	time 1.9171 (2.2140)	loss 3.1302 (2.9997)	grad_norm 3.1583 (3.1630)	
[2022-01-26 15:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][780/1251]	eta 0:17:22 lr 0.000022	time 2.4800 (2.2133)	loss 2.4412 (2.9986)	grad_norm 4.0321 (3.1636)	
[2022-01-26 15:29:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][790/1251]	eta 0:17:00 lr 0.000022	time 2.5985 (2.2141)	loss 2.8785 (3.0005)	grad_norm 2.9883 (3.1619)	
[2022-01-26 15:29:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][800/1251]	eta 0:16:38 lr 0.000022	time 2.1333 (2.2139)	loss 3.4693 (3.0030)	grad_norm 3.1166 (3.1616)	
[2022-01-26 15:30:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][810/1251]	eta 0:16:15 lr 0.000022	time 1.8293 (2.2128)	loss 3.3563 (3.0034)	grad_norm 2.9686 (3.1630)	
[2022-01-26 15:30:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][820/1251]	eta 0:15:53 lr 0.000022	time 1.9015 (2.2115)	loss 2.8704 (3.0070)	grad_norm 2.6483 (3.1666)	
[2022-01-26 15:30:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][830/1251]	eta 0:15:31 lr 0.000022	time 2.2172 (2.2127)	loss 3.2809 (3.0090)	grad_norm 3.2772 (3.1638)	
[2022-01-26 15:31:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][840/1251]	eta 0:15:09 lr 0.000022	time 2.1678 (2.2125)	loss 3.3051 (3.0106)	grad_norm 2.5627 (3.1646)	
[2022-01-26 15:31:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][850/1251]	eta 0:14:47 lr 0.000022	time 1.7760 (2.2121)	loss 2.0367 (3.0081)	grad_norm 2.8931 (3.1642)	
[2022-01-26 15:31:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][860/1251]	eta 0:14:24 lr 0.000022	time 2.0558 (2.2121)	loss 3.1030 (3.0081)	grad_norm 3.2792 (3.1640)	
[2022-01-26 15:32:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][870/1251]	eta 0:14:03 lr 0.000022	time 2.6639 (2.2132)	loss 3.1541 (3.0080)	grad_norm 3.6134 (3.1628)	
[2022-01-26 15:32:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][880/1251]	eta 0:13:40 lr 0.000022	time 1.6254 (2.2120)	loss 2.9195 (3.0097)	grad_norm 2.8659 (3.1631)	
[2022-01-26 15:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][890/1251]	eta 0:13:18 lr 0.000022	time 2.3335 (2.2130)	loss 3.3031 (3.0113)	grad_norm 3.5990 (3.1628)	
[2022-01-26 15:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][900/1251]	eta 0:12:56 lr 0.000022	time 1.8568 (2.2134)	loss 2.7403 (3.0132)	grad_norm 2.6368 (3.1630)	
[2022-01-26 15:33:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][910/1251]	eta 0:12:35 lr 0.000022	time 2.4042 (2.2152)	loss 3.3224 (3.0136)	grad_norm 2.9206 (3.1602)	
[2022-01-26 15:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][920/1251]	eta 0:12:12 lr 0.000022	time 1.7813 (2.2143)	loss 3.4447 (3.0152)	grad_norm 3.2306 (3.1622)	
[2022-01-26 15:34:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][930/1251]	eta 0:11:51 lr 0.000022	time 2.4912 (2.2153)	loss 2.4283 (3.0145)	grad_norm 2.9162 (3.1619)	
[2022-01-26 15:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][940/1251]	eta 0:11:28 lr 0.000022	time 1.9283 (2.2149)	loss 2.7931 (3.0138)	grad_norm 3.0326 (3.1652)	
[2022-01-26 15:35:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][950/1251]	eta 0:11:06 lr 0.000022	time 1.9178 (2.2134)	loss 2.7688 (3.0136)	grad_norm 2.7650 (3.1664)	
[2022-01-26 15:35:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][960/1251]	eta 0:10:43 lr 0.000022	time 1.7809 (2.2105)	loss 3.2362 (3.0127)	grad_norm 2.6759 (3.1653)	
[2022-01-26 15:35:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][970/1251]	eta 0:10:21 lr 0.000022	time 2.4946 (2.2106)	loss 1.9367 (3.0115)	grad_norm 3.2199 (3.1646)	
[2022-01-26 15:36:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][980/1251]	eta 0:09:59 lr 0.000022	time 2.2124 (2.2109)	loss 1.8505 (3.0118)	grad_norm 2.8283 (3.1626)	
[2022-01-26 15:36:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][990/1251]	eta 0:09:37 lr 0.000022	time 3.3762 (2.2121)	loss 3.2753 (3.0111)	grad_norm 3.2062 (3.1615)	
[2022-01-26 15:37:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1000/1251]	eta 0:09:15 lr 0.000022	time 2.0951 (2.2138)	loss 3.0382 (3.0110)	grad_norm 3.6274 (3.1612)	
[2022-01-26 15:37:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1010/1251]	eta 0:08:53 lr 0.000022	time 2.5486 (2.2147)	loss 3.5681 (3.0113)	grad_norm 3.2145 (3.1615)	
[2022-01-26 15:37:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1020/1251]	eta 0:08:31 lr 0.000022	time 1.9531 (2.2125)	loss 2.2629 (3.0129)	grad_norm 2.9032 (3.1615)	
[2022-01-26 15:38:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1030/1251]	eta 0:08:08 lr 0.000022	time 2.6592 (2.2103)	loss 3.4049 (3.0099)	grad_norm 3.1819 (3.1600)	
[2022-01-26 15:38:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1040/1251]	eta 0:07:45 lr 0.000022	time 1.6107 (2.2083)	loss 3.6004 (3.0083)	grad_norm 2.9983 (3.1599)	
[2022-01-26 15:38:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1050/1251]	eta 0:07:23 lr 0.000022	time 2.9552 (2.2083)	loss 2.5746 (3.0073)	grad_norm 2.8890 (3.1603)	
[2022-01-26 15:39:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1060/1251]	eta 0:07:01 lr 0.000022	time 1.9244 (2.2078)	loss 3.6104 (3.0074)	grad_norm 3.0455 (3.1608)	
[2022-01-26 15:39:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1070/1251]	eta 0:06:40 lr 0.000022	time 2.4966 (2.2102)	loss 2.9137 (3.0085)	grad_norm 3.3766 (3.1600)	
[2022-01-26 15:40:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1080/1251]	eta 0:06:18 lr 0.000022	time 1.4376 (2.2126)	loss 3.2604 (3.0078)	grad_norm 2.9972 (3.1588)	
[2022-01-26 15:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1090/1251]	eta 0:05:56 lr 0.000022	time 2.8531 (2.2137)	loss 2.6092 (3.0098)	grad_norm 2.4427 (3.1578)	
[2022-01-26 15:40:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1100/1251]	eta 0:05:34 lr 0.000022	time 1.8341 (2.2122)	loss 2.8551 (3.0091)	grad_norm 3.8539 (3.1574)	
[2022-01-26 15:41:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1110/1251]	eta 0:05:11 lr 0.000022	time 2.2375 (2.2103)	loss 3.7206 (3.0093)	grad_norm 3.8007 (3.1582)	
[2022-01-26 15:41:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1120/1251]	eta 0:04:49 lr 0.000022	time 1.8263 (2.2080)	loss 3.0368 (3.0092)	grad_norm 4.1958 (3.1621)	
[2022-01-26 15:41:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1130/1251]	eta 0:04:27 lr 0.000022	time 2.6018 (2.2075)	loss 3.2843 (3.0095)	grad_norm 2.8293 (3.1624)	
[2022-01-26 15:42:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1140/1251]	eta 0:04:05 lr 0.000022	time 2.1613 (2.2079)	loss 2.0181 (3.0090)	grad_norm 2.6331 (3.1601)	
[2022-01-26 15:42:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1150/1251]	eta 0:03:43 lr 0.000022	time 1.9518 (2.2083)	loss 3.2517 (3.0099)	grad_norm 3.2092 (3.1601)	
[2022-01-26 15:42:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1160/1251]	eta 0:03:20 lr 0.000022	time 2.5325 (2.2085)	loss 3.2522 (3.0094)	grad_norm 2.8888 (3.1590)	
[2022-01-26 15:43:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1170/1251]	eta 0:02:59 lr 0.000022	time 2.7024 (2.2109)	loss 3.1146 (3.0088)	grad_norm 3.2287 (3.1581)	
[2022-01-26 15:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1180/1251]	eta 0:02:36 lr 0.000022	time 2.0413 (2.2102)	loss 3.3670 (3.0070)	grad_norm 3.4352 (3.1578)	
[2022-01-26 15:44:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1190/1251]	eta 0:02:14 lr 0.000022	time 1.7290 (2.2097)	loss 2.9543 (3.0058)	grad_norm 2.8172 (3.1582)	
[2022-01-26 15:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1200/1251]	eta 0:01:52 lr 0.000022	time 2.1694 (2.2087)	loss 2.5541 (3.0060)	grad_norm 2.7478 (3.1591)	
[2022-01-26 15:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1210/1251]	eta 0:01:30 lr 0.000022	time 2.2684 (2.2075)	loss 3.1997 (3.0076)	grad_norm 2.8540 (3.1589)	
[2022-01-26 15:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1220/1251]	eta 0:01:08 lr 0.000022	time 3.0513 (2.2077)	loss 3.3051 (3.0086)	grad_norm 3.1887 (3.1573)	
[2022-01-26 15:45:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1230/1251]	eta 0:00:46 lr 0.000022	time 2.2372 (2.2082)	loss 2.6670 (3.0078)	grad_norm 2.8520 (3.1553)	
[2022-01-26 15:45:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1240/1251]	eta 0:00:24 lr 0.000022	time 1.1580 (2.2069)	loss 3.2663 (3.0090)	grad_norm 3.0074 (3.1548)	
[2022-01-26 15:46:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [278/300][1250/1251]	eta 0:00:02 lr 0.000022	time 1.3580 (2.2020)	loss 3.1462 (3.0074)	grad_norm 3.4590 (3.1547)	
[2022-01-26 15:46:05 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 278 training takes 0:45:55
[2022-01-26 15:46:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.278 (18.278)	Loss 0.8212 (0.8212)	Acc@1 81.543 (81.543)	Acc@5 95.508 (95.508)	
[2022-01-26 15:46:42 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.901 (3.406)	Loss 0.8245 (0.8003)	Acc@1 81.934 (81.401)	Acc@5 94.824 (95.188)	
[2022-01-26 15:47:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.936 (2.666)	Loss 0.8214 (0.8053)	Acc@1 80.859 (81.348)	Acc@5 95.020 (95.406)	
[2022-01-26 15:47:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.627 (2.346)	Loss 0.7907 (0.8109)	Acc@1 82.324 (81.269)	Acc@5 95.117 (95.347)	
[2022-01-26 15:47:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.348 (2.195)	Loss 0.7865 (0.8118)	Acc@1 80.469 (81.071)	Acc@5 96.191 (95.353)	
[2022-01-26 15:47:42 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.074 Acc@5 95.406
[2022-01-26 15:47:42 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.1%
[2022-01-26 15:47:42 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.07%
[2022-01-26 15:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][0/1251]	eta 7:30:29 lr 0.000022	time 21.6064 (21.6064)	loss 3.0292 (3.0292)	grad_norm 2.9771 (2.9771)	
[2022-01-26 15:48:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][10/1251]	eta 1:22:50 lr 0.000022	time 2.2121 (4.0056)	loss 3.4291 (3.0290)	grad_norm 2.8333 (3.1812)	
[2022-01-26 15:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][20/1251]	eta 1:03:47 lr 0.000022	time 1.5801 (3.1093)	loss 2.1437 (3.0603)	grad_norm 2.7640 (3.1186)	
[2022-01-26 15:49:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][30/1251]	eta 0:57:34 lr 0.000022	time 1.6226 (2.8290)	loss 3.7712 (2.9449)	grad_norm 3.1828 (3.1184)	
[2022-01-26 15:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][40/1251]	eta 0:55:12 lr 0.000022	time 3.7504 (2.7357)	loss 2.7868 (2.9573)	grad_norm 2.7734 (3.1200)	
[2022-01-26 15:49:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][50/1251]	eta 0:53:04 lr 0.000022	time 2.0721 (2.6517)	loss 1.9755 (2.9687)	grad_norm 2.8774 (3.0957)	
[2022-01-26 15:50:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][60/1251]	eta 0:51:01 lr 0.000022	time 1.4930 (2.5709)	loss 3.4847 (2.9849)	grad_norm 3.1563 (3.1083)	
[2022-01-26 15:50:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][70/1251]	eta 0:49:44 lr 0.000022	time 1.7648 (2.5275)	loss 3.0920 (2.9986)	grad_norm 3.0365 (3.1082)	
[2022-01-26 15:51:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][80/1251]	eta 0:48:55 lr 0.000022	time 3.0074 (2.5067)	loss 3.3251 (2.9990)	grad_norm 3.4247 (3.0957)	
[2022-01-26 15:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][90/1251]	eta 0:47:48 lr 0.000022	time 1.5172 (2.4710)	loss 2.9972 (3.0111)	grad_norm 2.8652 (3.1163)	
[2022-01-26 15:51:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][100/1251]	eta 0:46:36 lr 0.000022	time 1.8294 (2.4299)	loss 1.8963 (3.0089)	grad_norm 3.1271 (3.1311)	
[2022-01-26 15:52:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][110/1251]	eta 0:45:19 lr 0.000022	time 1.9692 (2.3832)	loss 3.0305 (3.0085)	grad_norm 2.7513 (3.1310)	
[2022-01-26 15:52:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][120/1251]	eta 0:44:21 lr 0.000022	time 2.4732 (2.3532)	loss 3.6031 (3.0016)	grad_norm 3.8176 (3.1330)	
[2022-01-26 15:52:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][130/1251]	eta 0:43:46 lr 0.000022	time 2.2816 (2.3431)	loss 3.2561 (2.9992)	grad_norm 3.9277 (3.1337)	
[2022-01-26 15:53:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][140/1251]	eta 0:43:23 lr 0.000022	time 2.3811 (2.3435)	loss 2.8302 (2.9719)	grad_norm 2.7710 (3.1246)	
[2022-01-26 15:53:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][150/1251]	eta 0:43:00 lr 0.000022	time 2.2238 (2.3441)	loss 3.3881 (2.9835)	grad_norm 2.6336 (3.1392)	
[2022-01-26 15:54:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][160/1251]	eta 0:42:48 lr 0.000022	time 2.7782 (2.3545)	loss 3.1149 (2.9800)	grad_norm 3.3324 (3.1449)	
[2022-01-26 15:54:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][170/1251]	eta 0:42:10 lr 0.000022	time 1.8887 (2.3408)	loss 3.0358 (2.9715)	grad_norm 3.2439 (3.1473)	
[2022-01-26 15:54:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][180/1251]	eta 0:41:32 lr 0.000022	time 1.9078 (2.3272)	loss 2.9963 (2.9671)	grad_norm 3.3773 (3.1415)	
[2022-01-26 15:55:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][190/1251]	eta 0:40:49 lr 0.000022	time 1.9623 (2.3090)	loss 3.5728 (2.9690)	grad_norm 3.7738 (3.1444)	
[2022-01-26 15:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][200/1251]	eta 0:40:10 lr 0.000022	time 1.9430 (2.2936)	loss 3.2626 (2.9753)	grad_norm 3.1019 (3.1469)	
[2022-01-26 15:55:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][210/1251]	eta 0:39:31 lr 0.000022	time 1.8075 (2.2782)	loss 2.6967 (2.9615)	grad_norm 2.6527 (3.1419)	
[2022-01-26 15:56:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][220/1251]	eta 0:38:58 lr 0.000022	time 2.0313 (2.2685)	loss 2.6964 (2.9701)	grad_norm 2.8472 (3.1430)	
[2022-01-26 15:56:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][230/1251]	eta 0:38:27 lr 0.000022	time 2.1558 (2.2598)	loss 3.3752 (2.9647)	grad_norm 4.2075 (3.1725)	
[2022-01-26 15:56:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][240/1251]	eta 0:38:09 lr 0.000022	time 3.0292 (2.2641)	loss 2.8708 (2.9737)	grad_norm 4.0674 (3.1762)	
[2022-01-26 15:57:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][250/1251]	eta 0:37:46 lr 0.000022	time 1.8228 (2.2643)	loss 3.1695 (2.9671)	grad_norm 3.2202 (3.1762)	
[2022-01-26 15:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][260/1251]	eta 0:37:25 lr 0.000022	time 2.1258 (2.2664)	loss 3.4348 (2.9660)	grad_norm 2.9295 (3.1829)	
[2022-01-26 15:57:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][270/1251]	eta 0:37:03 lr 0.000022	time 2.6051 (2.2668)	loss 2.4035 (2.9666)	grad_norm 2.9127 (3.1840)	
[2022-01-26 15:58:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][280/1251]	eta 0:36:48 lr 0.000022	time 2.5427 (2.2746)	loss 3.1775 (2.9703)	grad_norm 2.9748 (3.1789)	
[2022-01-26 15:58:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][290/1251]	eta 0:36:21 lr 0.000022	time 1.5546 (2.2704)	loss 2.8559 (2.9681)	grad_norm 2.9356 (3.1769)	
[2022-01-26 15:59:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][300/1251]	eta 0:35:56 lr 0.000022	time 1.9077 (2.2673)	loss 3.5934 (2.9754)	grad_norm 2.8427 (3.1804)	
[2022-01-26 15:59:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][310/1251]	eta 0:35:28 lr 0.000022	time 1.9500 (2.2616)	loss 2.9967 (2.9706)	grad_norm 3.0645 (3.1786)	
[2022-01-26 15:59:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][320/1251]	eta 0:35:06 lr 0.000022	time 2.7055 (2.2625)	loss 2.6376 (2.9730)	grad_norm 3.4215 (3.1767)	
[2022-01-26 16:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][330/1251]	eta 0:34:42 lr 0.000022	time 2.3634 (2.2610)	loss 3.3075 (2.9750)	grad_norm 2.9645 (3.1810)	
[2022-01-26 16:00:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][340/1251]	eta 0:34:14 lr 0.000022	time 1.8840 (2.2557)	loss 2.9151 (2.9798)	grad_norm 3.1571 (3.1847)	
[2022-01-26 16:00:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][350/1251]	eta 0:33:48 lr 0.000022	time 1.8966 (2.2510)	loss 3.4090 (2.9774)	grad_norm 3.3691 (3.1986)	
[2022-01-26 16:01:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][360/1251]	eta 0:33:29 lr 0.000022	time 2.8922 (2.2548)	loss 3.0886 (2.9734)	grad_norm 3.2341 (3.2020)	
[2022-01-26 16:01:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][370/1251]	eta 0:33:02 lr 0.000022	time 1.6459 (2.2505)	loss 2.6794 (2.9733)	grad_norm 2.7989 (3.2083)	
[2022-01-26 16:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][380/1251]	eta 0:32:38 lr 0.000022	time 2.2070 (2.2486)	loss 2.8371 (2.9778)	grad_norm 3.0854 (3.2164)	
[2022-01-26 16:02:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][390/1251]	eta 0:32:11 lr 0.000022	time 1.9148 (2.2433)	loss 3.1648 (2.9749)	grad_norm 3.2026 (3.2143)	
[2022-01-26 16:02:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][400/1251]	eta 0:31:45 lr 0.000022	time 2.2261 (2.2388)	loss 3.3740 (2.9716)	grad_norm 2.9523 (3.2123)	
[2022-01-26 16:03:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][410/1251]	eta 0:31:18 lr 0.000022	time 1.9236 (2.2339)	loss 3.3125 (2.9674)	grad_norm 2.8309 (3.2110)	
[2022-01-26 16:03:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][420/1251]	eta 0:30:54 lr 0.000022	time 3.0138 (2.2315)	loss 3.1666 (2.9727)	grad_norm 2.8378 (3.2090)	
[2022-01-26 16:03:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][430/1251]	eta 0:30:28 lr 0.000022	time 1.7968 (2.2272)	loss 3.2240 (2.9745)	grad_norm 2.9148 (3.2050)	
[2022-01-26 16:04:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][440/1251]	eta 0:30:06 lr 0.000022	time 2.6684 (2.2272)	loss 3.2872 (2.9776)	grad_norm 3.2874 (3.2010)	
[2022-01-26 16:04:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][450/1251]	eta 0:29:42 lr 0.000022	time 2.3868 (2.2259)	loss 3.2487 (2.9769)	grad_norm 3.5844 (3.2031)	
[2022-01-26 16:04:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][460/1251]	eta 0:29:22 lr 0.000022	time 3.0355 (2.2287)	loss 3.1342 (2.9787)	grad_norm 3.3484 (3.2020)	
[2022-01-26 16:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][470/1251]	eta 0:28:58 lr 0.000022	time 1.9278 (2.2259)	loss 3.2012 (2.9743)	grad_norm 3.1535 (3.2023)	
[2022-01-26 16:05:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][480/1251]	eta 0:28:38 lr 0.000021	time 3.6084 (2.2291)	loss 2.8437 (2.9705)	grad_norm 2.7910 (3.1992)	
[2022-01-26 16:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][490/1251]	eta 0:28:17 lr 0.000021	time 2.7885 (2.2300)	loss 3.2779 (2.9715)	grad_norm 2.7814 (3.1964)	
[2022-01-26 16:06:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][500/1251]	eta 0:27:53 lr 0.000021	time 1.8514 (2.2278)	loss 3.1244 (2.9675)	grad_norm 2.4381 (3.1940)	
[2022-01-26 16:06:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][510/1251]	eta 0:27:28 lr 0.000021	time 1.6776 (2.2246)	loss 3.6690 (2.9718)	grad_norm 3.4959 (3.1922)	
[2022-01-26 16:07:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][520/1251]	eta 0:27:05 lr 0.000021	time 2.3166 (2.2234)	loss 2.9784 (2.9743)	grad_norm 3.0713 (3.1901)	
[2022-01-26 16:07:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][530/1251]	eta 0:26:42 lr 0.000021	time 2.4701 (2.2233)	loss 3.4344 (2.9772)	grad_norm 3.0320 (3.1875)	
[2022-01-26 16:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][540/1251]	eta 0:26:19 lr 0.000021	time 1.7708 (2.2218)	loss 2.9130 (2.9767)	grad_norm 3.1070 (3.1880)	
[2022-01-26 16:08:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][550/1251]	eta 0:25:56 lr 0.000021	time 1.4867 (2.2202)	loss 3.0530 (2.9753)	grad_norm 2.8011 (3.1888)	
[2022-01-26 16:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][560/1251]	eta 0:25:34 lr 0.000021	time 2.0082 (2.2205)	loss 3.2324 (2.9739)	grad_norm 3.3418 (3.1896)	
[2022-01-26 16:08:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][570/1251]	eta 0:25:14 lr 0.000021	time 2.8016 (2.2238)	loss 3.4335 (2.9801)	grad_norm 2.9679 (3.1905)	
[2022-01-26 16:09:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][580/1251]	eta 0:24:54 lr 0.000021	time 2.6500 (2.2272)	loss 3.2720 (2.9825)	grad_norm 2.6594 (3.1919)	
[2022-01-26 16:09:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][590/1251]	eta 0:24:30 lr 0.000021	time 2.4614 (2.2253)	loss 2.6134 (2.9843)	grad_norm 3.4987 (3.1935)	
[2022-01-26 16:09:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][600/1251]	eta 0:24:07 lr 0.000021	time 2.3181 (2.2228)	loss 2.6375 (2.9865)	grad_norm 2.8601 (3.1986)	
[2022-01-26 16:10:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][610/1251]	eta 0:23:43 lr 0.000021	time 1.8032 (2.2206)	loss 2.5511 (2.9883)	grad_norm 3.2878 (3.1998)	
[2022-01-26 16:10:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][620/1251]	eta 0:23:20 lr 0.000021	time 1.6652 (2.2194)	loss 2.9894 (2.9907)	grad_norm 3.7927 (3.1997)	
[2022-01-26 16:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][630/1251]	eta 0:22:57 lr 0.000021	time 1.5785 (2.2175)	loss 3.5204 (2.9936)	grad_norm 3.8432 (3.1999)	
[2022-01-26 16:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][640/1251]	eta 0:22:34 lr 0.000021	time 2.5854 (2.2162)	loss 3.3340 (2.9971)	grad_norm 3.1779 (3.2024)	
[2022-01-26 16:11:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][650/1251]	eta 0:22:12 lr 0.000021	time 1.5493 (2.2178)	loss 3.5479 (2.9950)	grad_norm 3.6346 (3.2035)	
[2022-01-26 16:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][660/1251]	eta 0:21:51 lr 0.000021	time 1.5184 (2.2187)	loss 2.6654 (2.9971)	grad_norm 2.5262 (3.1991)	
[2022-01-26 16:12:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][670/1251]	eta 0:21:28 lr 0.000021	time 2.5493 (2.2183)	loss 3.0104 (2.9971)	grad_norm 3.0087 (3.1971)	
[2022-01-26 16:12:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][680/1251]	eta 0:21:07 lr 0.000021	time 2.8188 (2.2190)	loss 3.2050 (3.0009)	grad_norm 2.9827 (3.1943)	
[2022-01-26 16:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][690/1251]	eta 0:20:44 lr 0.000021	time 1.9455 (2.2180)	loss 3.8781 (2.9994)	grad_norm 3.1831 (3.1917)	
[2022-01-26 16:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][700/1251]	eta 0:20:21 lr 0.000021	time 1.6091 (2.2164)	loss 2.9818 (3.0003)	grad_norm 3.0828 (3.1940)	
[2022-01-26 16:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][710/1251]	eta 0:19:58 lr 0.000021	time 2.2164 (2.2154)	loss 3.1795 (3.0006)	grad_norm 4.0885 (3.1940)	
[2022-01-26 16:14:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][720/1251]	eta 0:19:37 lr 0.000021	time 3.8039 (2.2173)	loss 2.7377 (2.9978)	grad_norm 3.4142 (3.1948)	
[2022-01-26 16:14:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][730/1251]	eta 0:19:14 lr 0.000021	time 1.8964 (2.2159)	loss 2.8163 (2.9941)	grad_norm 2.8327 (3.1937)	
[2022-01-26 16:15:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][740/1251]	eta 0:18:53 lr 0.000021	time 1.8503 (2.2180)	loss 3.2903 (2.9938)	grad_norm 3.0037 (3.1925)	
[2022-01-26 16:15:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][750/1251]	eta 0:18:30 lr 0.000021	time 1.8173 (2.2169)	loss 3.2684 (2.9948)	grad_norm 2.8792 (3.1892)	
[2022-01-26 16:15:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][760/1251]	eta 0:18:08 lr 0.000021	time 3.7372 (2.2162)	loss 3.2213 (2.9938)	grad_norm 3.7278 (3.1879)	
[2022-01-26 16:16:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][770/1251]	eta 0:17:45 lr 0.000021	time 1.8149 (2.2156)	loss 2.9324 (2.9932)	grad_norm 3.5173 (3.1862)	
[2022-01-26 16:16:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][780/1251]	eta 0:17:24 lr 0.000021	time 2.0065 (2.2167)	loss 2.0630 (2.9922)	grad_norm 2.7619 (3.1869)	
[2022-01-26 16:16:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][790/1251]	eta 0:17:01 lr 0.000021	time 1.9299 (2.2168)	loss 3.2966 (2.9922)	grad_norm 3.2295 (3.1857)	
[2022-01-26 16:17:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][800/1251]	eta 0:16:39 lr 0.000021	time 3.5361 (2.2158)	loss 3.2904 (2.9955)	grad_norm 2.5229 (3.1842)	
[2022-01-26 16:17:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][810/1251]	eta 0:16:16 lr 0.000021	time 1.8349 (2.2138)	loss 3.3698 (2.9967)	grad_norm 3.3277 (3.1866)	
[2022-01-26 16:18:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][820/1251]	eta 0:15:54 lr 0.000021	time 1.5743 (2.2141)	loss 3.6723 (2.9999)	grad_norm 3.5460 (3.1930)	
[2022-01-26 16:18:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][830/1251]	eta 0:15:31 lr 0.000021	time 1.8309 (2.2136)	loss 3.0617 (3.0013)	grad_norm 3.7327 (3.1914)	
[2022-01-26 16:18:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][840/1251]	eta 0:15:09 lr 0.000021	time 3.6043 (2.2137)	loss 3.3102 (2.9996)	grad_norm 2.8453 (3.1880)	
[2022-01-26 16:19:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][850/1251]	eta 0:14:46 lr 0.000021	time 1.6366 (2.2115)	loss 2.6939 (2.9966)	grad_norm 2.6479 (3.1844)	
[2022-01-26 16:19:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][860/1251]	eta 0:14:24 lr 0.000021	time 2.2621 (2.2116)	loss 3.2035 (2.9965)	grad_norm 2.7210 (3.1842)	
[2022-01-26 16:19:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][870/1251]	eta 0:14:02 lr 0.000021	time 2.5605 (2.2112)	loss 2.8827 (2.9953)	grad_norm 4.1031 (3.1839)	
[2022-01-26 16:20:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][880/1251]	eta 0:13:40 lr 0.000021	time 2.8795 (2.2111)	loss 3.7862 (2.9971)	grad_norm 3.2646 (3.1834)	
[2022-01-26 16:20:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][890/1251]	eta 0:13:17 lr 0.000021	time 1.7311 (2.2102)	loss 3.7029 (2.9991)	grad_norm 3.8265 (3.1820)	
[2022-01-26 16:20:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][900/1251]	eta 0:12:55 lr 0.000021	time 1.5796 (2.2099)	loss 2.8176 (3.0011)	grad_norm 3.1707 (3.1824)	
[2022-01-26 16:21:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][910/1251]	eta 0:12:34 lr 0.000021	time 2.8292 (2.2131)	loss 3.1586 (3.0006)	grad_norm 3.5171 (3.1822)	
[2022-01-26 16:21:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][920/1251]	eta 0:12:12 lr 0.000021	time 1.6044 (2.2126)	loss 3.2734 (3.0010)	grad_norm 2.7297 (3.1814)	
[2022-01-26 16:22:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][930/1251]	eta 0:11:49 lr 0.000021	time 1.7152 (2.2111)	loss 2.3027 (3.0000)	grad_norm 2.6719 (3.1797)	
[2022-01-26 16:22:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][940/1251]	eta 0:11:26 lr 0.000021	time 1.7208 (2.2083)	loss 2.6512 (3.0000)	grad_norm 3.0380 (3.1807)	
[2022-01-26 16:22:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][950/1251]	eta 0:11:04 lr 0.000021	time 2.7246 (2.2080)	loss 2.7916 (3.0005)	grad_norm 2.8195 (3.1815)	
[2022-01-26 16:23:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][960/1251]	eta 0:10:42 lr 0.000021	time 1.5784 (2.2067)	loss 3.0885 (2.9988)	grad_norm 3.2493 (3.1818)	
[2022-01-26 16:23:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][970/1251]	eta 0:10:20 lr 0.000021	time 2.3143 (2.2068)	loss 3.2246 (3.0004)	grad_norm 3.6031 (3.1815)	
[2022-01-26 16:23:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][980/1251]	eta 0:09:58 lr 0.000021	time 1.8624 (2.2072)	loss 2.9874 (2.9991)	grad_norm 3.0288 (3.1817)	
[2022-01-26 16:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][990/1251]	eta 0:09:36 lr 0.000021	time 2.7659 (2.2078)	loss 3.2967 (2.9970)	grad_norm 3.2285 (3.1828)	
[2022-01-26 16:24:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1000/1251]	eta 0:09:14 lr 0.000021	time 1.8718 (2.2073)	loss 2.8817 (2.9948)	grad_norm 3.3336 (3.1829)	
[2022-01-26 16:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1010/1251]	eta 0:08:51 lr 0.000021	time 2.0615 (2.2064)	loss 2.5450 (2.9928)	grad_norm 3.1573 (3.1820)	
[2022-01-26 16:25:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1020/1251]	eta 0:08:29 lr 0.000021	time 1.8190 (2.2057)	loss 3.4229 (2.9951)	grad_norm 3.2200 (3.1818)	
[2022-01-26 16:25:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1030/1251]	eta 0:08:07 lr 0.000021	time 1.8738 (2.2066)	loss 2.9553 (2.9953)	grad_norm 2.9107 (3.1807)	
[2022-01-26 16:25:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1040/1251]	eta 0:07:45 lr 0.000021	time 1.5309 (2.2060)	loss 3.0287 (2.9955)	grad_norm 3.6445 (3.1829)	
[2022-01-26 16:26:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1050/1251]	eta 0:07:23 lr 0.000021	time 2.4661 (2.2054)	loss 3.1489 (2.9961)	grad_norm 3.4410 (3.1832)	
[2022-01-26 16:26:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1060/1251]	eta 0:07:00 lr 0.000021	time 1.5781 (2.2042)	loss 2.7006 (2.9964)	grad_norm 3.1837 (3.1843)	
[2022-01-26 16:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1070/1251]	eta 0:06:38 lr 0.000021	time 2.1102 (2.2030)	loss 2.0518 (2.9962)	grad_norm 3.1594 (3.1848)	
[2022-01-26 16:27:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1080/1251]	eta 0:06:16 lr 0.000021	time 2.2751 (2.2028)	loss 2.8435 (2.9955)	grad_norm 3.3374 (3.1860)	
[2022-01-26 16:27:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1090/1251]	eta 0:05:54 lr 0.000021	time 1.9285 (2.2023)	loss 2.9871 (2.9951)	grad_norm 3.0432 (3.1845)	
[2022-01-26 16:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1100/1251]	eta 0:05:32 lr 0.000021	time 1.6494 (2.2022)	loss 2.6534 (2.9956)	grad_norm 3.6295 (3.1846)	
[2022-01-26 16:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1110/1251]	eta 0:05:10 lr 0.000021	time 2.2915 (2.2023)	loss 3.5903 (2.9950)	grad_norm 2.9006 (3.1830)	
[2022-01-26 16:28:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1120/1251]	eta 0:04:48 lr 0.000021	time 2.2274 (2.2024)	loss 3.2613 (2.9926)	grad_norm 2.7902 (3.1837)	
[2022-01-26 16:29:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1130/1251]	eta 0:04:26 lr 0.000021	time 2.3853 (2.2017)	loss 2.4295 (2.9929)	grad_norm 3.0962 (3.1829)	
[2022-01-26 16:29:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1140/1251]	eta 0:04:04 lr 0.000021	time 1.8463 (2.2015)	loss 3.0501 (2.9915)	grad_norm 2.7503 (3.1823)	
[2022-01-26 16:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1150/1251]	eta 0:03:42 lr 0.000021	time 2.3933 (2.2023)	loss 3.3204 (2.9916)	grad_norm 3.6874 (3.1830)	
[2022-01-26 16:30:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1160/1251]	eta 0:03:20 lr 0.000021	time 2.3521 (2.2031)	loss 3.1213 (2.9914)	grad_norm 2.8086 (3.1834)	
[2022-01-26 16:30:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1170/1251]	eta 0:02:58 lr 0.000021	time 2.5621 (2.2033)	loss 2.3024 (2.9917)	grad_norm 2.9323 (3.1849)	
[2022-01-26 16:31:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1180/1251]	eta 0:02:36 lr 0.000021	time 1.8514 (2.2033)	loss 2.8194 (2.9925)	grad_norm 2.4870 (3.1834)	
[2022-01-26 16:31:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1190/1251]	eta 0:02:14 lr 0.000021	time 1.8278 (2.2040)	loss 3.4736 (2.9937)	grad_norm 3.2804 (3.1830)	
[2022-01-26 16:31:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1200/1251]	eta 0:01:52 lr 0.000021	time 1.9900 (2.2051)	loss 3.2293 (2.9952)	grad_norm 3.0842 (3.1838)	
[2022-01-26 16:32:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1210/1251]	eta 0:01:30 lr 0.000021	time 2.8250 (2.2045)	loss 2.4879 (2.9946)	grad_norm 3.2035 (3.1848)	
[2022-01-26 16:32:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1220/1251]	eta 0:01:08 lr 0.000021	time 1.6308 (2.2025)	loss 2.6577 (2.9953)	grad_norm 2.9798 (3.1839)	
[2022-01-26 16:32:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1230/1251]	eta 0:00:46 lr 0.000021	time 1.8905 (2.2008)	loss 2.5247 (2.9956)	grad_norm 3.3737 (3.1832)	
[2022-01-26 16:33:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1240/1251]	eta 0:00:24 lr 0.000021	time 1.8664 (2.2000)	loss 2.4105 (2.9959)	grad_norm 2.9932 (3.1839)	
[2022-01-26 16:33:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [279/300][1250/1251]	eta 0:00:02 lr 0.000021	time 1.1831 (2.1946)	loss 3.3730 (2.9948)	grad_norm 3.7785 (3.1829)	
[2022-01-26 16:33:28 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 279 training takes 0:45:45
[2022-01-26 16:33:46 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.218 (18.218)	Loss 0.8211 (0.8211)	Acc@1 81.055 (81.055)	Acc@5 95.312 (95.312)	
[2022-01-26 16:34:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.949 (3.476)	Loss 0.7841 (0.8094)	Acc@1 81.543 (81.090)	Acc@5 95.703 (95.543)	
[2022-01-26 16:34:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.577 (2.554)	Loss 0.7853 (0.8063)	Acc@1 80.078 (81.203)	Acc@5 95.605 (95.517)	
[2022-01-26 16:34:37 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.582 (2.223)	Loss 0.8770 (0.8105)	Acc@1 79.395 (81.149)	Acc@5 93.750 (95.461)	
[2022-01-26 16:34:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.229 (2.166)	Loss 0.7039 (0.8097)	Acc@1 83.398 (81.202)	Acc@5 95.996 (95.441)	
[2022-01-26 16:35:04 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.058 Acc@5 95.438
[2022-01-26 16:35:04 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.1%
[2022-01-26 16:35:04 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.07%
[2022-01-26 16:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][0/1251]	eta 7:41:15 lr 0.000021	time 22.1230 (22.1230)	loss 2.4879 (2.4879)	grad_norm 3.3937 (3.3937)	
[2022-01-26 16:35:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][10/1251]	eta 1:25:19 lr 0.000021	time 2.2370 (4.1252)	loss 3.1875 (2.8407)	grad_norm 2.9299 (3.1232)	
[2022-01-26 16:36:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][20/1251]	eta 1:04:47 lr 0.000021	time 1.4883 (3.1577)	loss 3.3846 (2.9796)	grad_norm 3.1192 (3.0782)	
[2022-01-26 16:36:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][30/1251]	eta 0:58:22 lr 0.000021	time 1.7308 (2.8685)	loss 2.7285 (2.9974)	grad_norm 3.3409 (3.1364)	
[2022-01-26 16:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][40/1251]	eta 0:55:21 lr 0.000021	time 3.2504 (2.7429)	loss 3.3739 (2.9886)	grad_norm 3.0980 (3.1440)	
[2022-01-26 16:37:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][50/1251]	eta 0:53:25 lr 0.000021	time 2.4890 (2.6690)	loss 3.4380 (2.9926)	grad_norm 3.1331 (3.1298)	
[2022-01-26 16:37:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][60/1251]	eta 0:51:10 lr 0.000021	time 2.0366 (2.5783)	loss 3.2572 (3.0135)	grad_norm 2.7867 (3.1307)	
[2022-01-26 16:38:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][70/1251]	eta 0:49:18 lr 0.000021	time 1.6674 (2.5054)	loss 3.2387 (3.0068)	grad_norm 3.1655 (3.1717)	
[2022-01-26 16:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][80/1251]	eta 0:48:22 lr 0.000021	time 3.4308 (2.4789)	loss 2.1475 (3.0195)	grad_norm 3.6777 (3.1558)	
[2022-01-26 16:38:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][90/1251]	eta 0:47:23 lr 0.000021	time 2.2289 (2.4491)	loss 3.8311 (3.0132)	grad_norm 3.1723 (3.1682)	
[2022-01-26 16:39:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][100/1251]	eta 0:46:18 lr 0.000021	time 1.5259 (2.4139)	loss 3.3006 (2.9973)	grad_norm 3.0907 (3.1901)	
[2022-01-26 16:39:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][110/1251]	eta 0:45:43 lr 0.000021	time 2.0618 (2.4041)	loss 3.2825 (2.9873)	grad_norm 3.3035 (3.1776)	
[2022-01-26 16:39:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][120/1251]	eta 0:45:04 lr 0.000021	time 3.0784 (2.3914)	loss 2.3268 (2.9755)	grad_norm 3.7647 (3.1652)	
[2022-01-26 16:40:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][130/1251]	eta 0:44:08 lr 0.000021	time 2.3461 (2.3623)	loss 3.6653 (2.9761)	grad_norm 3.5721 (3.1607)	
[2022-01-26 16:40:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][140/1251]	eta 0:43:13 lr 0.000021	time 1.6607 (2.3346)	loss 2.9380 (2.9806)	grad_norm 3.2641 (3.1479)	
[2022-01-26 16:40:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][150/1251]	eta 0:42:31 lr 0.000021	time 2.2802 (2.3177)	loss 3.5011 (2.9848)	grad_norm 3.5043 (3.1673)	
[2022-01-26 16:41:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][160/1251]	eta 0:41:56 lr 0.000021	time 1.9441 (2.3063)	loss 3.6140 (2.9968)	grad_norm 3.2807 (3.1721)	
[2022-01-26 16:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][170/1251]	eta 0:41:22 lr 0.000021	time 2.8839 (2.2969)	loss 3.5537 (3.0092)	grad_norm 4.4418 (3.1774)	
[2022-01-26 16:41:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][180/1251]	eta 0:40:48 lr 0.000021	time 1.9271 (2.2858)	loss 2.2641 (2.9863)	grad_norm 3.0137 (3.1712)	
[2022-01-26 16:42:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][190/1251]	eta 0:40:27 lr 0.000021	time 2.2502 (2.2875)	loss 2.7584 (2.9900)	grad_norm 2.7976 (3.1717)	
[2022-01-26 16:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][200/1251]	eta 0:40:05 lr 0.000021	time 2.8020 (2.2887)	loss 3.2943 (2.9872)	grad_norm 2.9002 (3.1672)	
[2022-01-26 16:43:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][210/1251]	eta 0:39:41 lr 0.000021	time 2.5040 (2.2879)	loss 2.8621 (2.9924)	grad_norm 2.9218 (3.1648)	
[2022-01-26 16:43:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][220/1251]	eta 0:39:18 lr 0.000021	time 1.9996 (2.2872)	loss 3.7539 (2.9984)	grad_norm 4.0425 (3.1733)	
[2022-01-26 16:43:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][230/1251]	eta 0:38:50 lr 0.000021	time 2.2737 (2.2829)	loss 3.2886 (3.0066)	grad_norm 2.8877 (3.1820)	
[2022-01-26 16:44:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][240/1251]	eta 0:38:21 lr 0.000021	time 1.9084 (2.2767)	loss 3.6827 (3.0043)	grad_norm 3.3527 (3.1803)	
[2022-01-26 16:44:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][250/1251]	eta 0:37:52 lr 0.000021	time 2.4462 (2.2701)	loss 3.2687 (3.0019)	grad_norm 2.9545 (3.1840)	
[2022-01-26 16:44:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][260/1251]	eta 0:37:27 lr 0.000021	time 1.6030 (2.2678)	loss 3.0050 (2.9985)	grad_norm 2.6404 (3.1857)	
[2022-01-26 16:45:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][270/1251]	eta 0:37:07 lr 0.000021	time 2.3899 (2.2707)	loss 3.1461 (2.9951)	grad_norm 2.9995 (3.1858)	
[2022-01-26 16:45:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][280/1251]	eta 0:36:40 lr 0.000021	time 1.6583 (2.2660)	loss 3.0052 (2.9997)	grad_norm 3.3780 (3.1856)	
[2022-01-26 16:46:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][290/1251]	eta 0:36:16 lr 0.000021	time 3.1112 (2.2653)	loss 3.1920 (3.0010)	grad_norm 2.9771 (3.1878)	
[2022-01-26 16:46:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][300/1251]	eta 0:35:52 lr 0.000021	time 1.8940 (2.2630)	loss 2.5441 (2.9998)	grad_norm 2.8232 (3.1811)	
[2022-01-26 16:46:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][310/1251]	eta 0:35:29 lr 0.000021	time 2.6030 (2.2628)	loss 3.4714 (2.9964)	grad_norm 3.0090 (3.1739)	
[2022-01-26 16:47:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][320/1251]	eta 0:35:04 lr 0.000021	time 2.2624 (2.2606)	loss 3.4205 (3.0005)	grad_norm 2.9176 (3.1725)	
[2022-01-26 16:47:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][330/1251]	eta 0:34:36 lr 0.000021	time 2.5225 (2.2546)	loss 3.1850 (3.0051)	grad_norm 2.7687 (3.1703)	
[2022-01-26 16:47:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][340/1251]	eta 0:34:06 lr 0.000021	time 2.2530 (2.2464)	loss 3.2870 (3.0036)	grad_norm 3.0363 (3.1643)	
[2022-01-26 16:48:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][350/1251]	eta 0:33:39 lr 0.000021	time 2.3505 (2.2412)	loss 3.6000 (3.0091)	grad_norm 2.8356 (3.1596)	
[2022-01-26 16:48:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][360/1251]	eta 0:33:13 lr 0.000021	time 2.1215 (2.2370)	loss 3.1595 (3.0144)	grad_norm 3.0477 (3.1656)	
[2022-01-26 16:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][370/1251]	eta 0:32:49 lr 0.000021	time 2.6711 (2.2356)	loss 2.5038 (3.0105)	grad_norm 4.0527 (3.1661)	
[2022-01-26 16:49:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][380/1251]	eta 0:32:26 lr 0.000020	time 3.0555 (2.2348)	loss 3.2832 (3.0107)	grad_norm 2.7730 (3.1714)	
[2022-01-26 16:49:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][390/1251]	eta 0:32:02 lr 0.000020	time 2.3900 (2.2325)	loss 2.2086 (3.0055)	grad_norm 3.3033 (3.1736)	
[2022-01-26 16:50:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][400/1251]	eta 0:31:40 lr 0.000020	time 2.5330 (2.2338)	loss 3.4754 (3.0064)	grad_norm 2.9641 (3.1723)	
[2022-01-26 16:50:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][410/1251]	eta 0:31:18 lr 0.000020	time 2.3347 (2.2336)	loss 2.5210 (3.0056)	grad_norm 3.2645 (3.1686)	
[2022-01-26 16:50:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][420/1251]	eta 0:30:59 lr 0.000020	time 2.8101 (2.2375)	loss 3.0669 (2.9995)	grad_norm 3.2439 (3.1673)	
[2022-01-26 16:51:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][430/1251]	eta 0:30:38 lr 0.000020	time 3.3058 (2.2398)	loss 3.1372 (3.0013)	grad_norm 3.4318 (3.1682)	
[2022-01-26 16:51:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][440/1251]	eta 0:30:16 lr 0.000020	time 2.1661 (2.2400)	loss 2.8380 (3.0001)	grad_norm 3.8379 (3.1724)	
[2022-01-26 16:51:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][450/1251]	eta 0:29:51 lr 0.000020	time 2.5540 (2.2371)	loss 3.5675 (3.0015)	grad_norm 3.2804 (3.1703)	
[2022-01-26 16:52:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][460/1251]	eta 0:29:26 lr 0.000020	time 2.1853 (2.2328)	loss 2.8692 (2.9980)	grad_norm 2.9904 (3.1762)	
[2022-01-26 16:52:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][470/1251]	eta 0:29:00 lr 0.000020	time 1.9250 (2.2282)	loss 2.1460 (2.9939)	grad_norm 2.9846 (3.1745)	
[2022-01-26 16:52:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][480/1251]	eta 0:28:37 lr 0.000020	time 2.0473 (2.2273)	loss 3.0606 (2.9899)	grad_norm 3.5532 (3.1747)	
[2022-01-26 16:53:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][490/1251]	eta 0:28:13 lr 0.000020	time 2.0255 (2.2252)	loss 3.1953 (2.9911)	grad_norm 3.6564 (3.1779)	
[2022-01-26 16:53:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][500/1251]	eta 0:27:52 lr 0.000020	time 2.1060 (2.2266)	loss 2.8325 (2.9894)	grad_norm 2.7847 (3.1773)	
[2022-01-26 16:54:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][510/1251]	eta 0:27:29 lr 0.000020	time 1.4544 (2.2257)	loss 3.4759 (2.9927)	grad_norm 3.1106 (3.1774)	
[2022-01-26 16:54:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][520/1251]	eta 0:27:05 lr 0.000020	time 2.1427 (2.2241)	loss 2.2272 (2.9905)	grad_norm 2.9446 (3.1763)	
[2022-01-26 16:54:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][530/1251]	eta 0:26:43 lr 0.000020	time 2.4804 (2.2246)	loss 2.2229 (2.9858)	grad_norm 3.2312 (3.1746)	
[2022-01-26 16:55:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][540/1251]	eta 0:26:22 lr 0.000020	time 1.8822 (2.2252)	loss 3.1994 (2.9881)	grad_norm 3.1481 (3.1764)	
[2022-01-26 16:55:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][550/1251]	eta 0:25:59 lr 0.000020	time 2.0989 (2.2252)	loss 2.9522 (2.9881)	grad_norm 2.9067 (3.1743)	
[2022-01-26 16:55:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][560/1251]	eta 0:25:37 lr 0.000020	time 2.0247 (2.2246)	loss 3.0630 (2.9884)	grad_norm 3.2143 (3.1717)	
[2022-01-26 16:56:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][570/1251]	eta 0:25:14 lr 0.000020	time 2.4374 (2.2240)	loss 3.2978 (2.9925)	grad_norm 3.2538 (3.1715)	
[2022-01-26 16:56:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][580/1251]	eta 0:24:49 lr 0.000020	time 1.8623 (2.2204)	loss 2.2821 (2.9931)	grad_norm 3.2258 (3.1689)	
[2022-01-26 16:56:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][590/1251]	eta 0:24:26 lr 0.000020	time 2.2643 (2.2190)	loss 3.0500 (2.9936)	grad_norm 2.8436 (3.1666)	
[2022-01-26 16:57:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][600/1251]	eta 0:24:02 lr 0.000020	time 1.6093 (2.2163)	loss 3.2959 (2.9955)	grad_norm 3.1586 (3.1674)	
[2022-01-26 16:57:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][610/1251]	eta 0:23:40 lr 0.000020	time 2.3069 (2.2153)	loss 2.0878 (2.9947)	grad_norm 2.7597 (3.1690)	
[2022-01-26 16:57:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][620/1251]	eta 0:23:16 lr 0.000020	time 1.9388 (2.2130)	loss 2.8210 (2.9930)	grad_norm 3.1049 (3.1669)	
[2022-01-26 16:58:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][630/1251]	eta 0:22:53 lr 0.000020	time 2.4808 (2.2120)	loss 3.1049 (2.9903)	grad_norm 3.5614 (3.1733)	
[2022-01-26 16:58:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][640/1251]	eta 0:22:30 lr 0.000020	time 2.4575 (2.2111)	loss 3.6475 (2.9941)	grad_norm 3.4188 (3.1702)	
[2022-01-26 16:59:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][650/1251]	eta 0:22:07 lr 0.000020	time 2.6337 (2.2095)	loss 1.8259 (2.9900)	grad_norm 2.9422 (3.1770)	
[2022-01-26 16:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][660/1251]	eta 0:21:45 lr 0.000020	time 1.8261 (2.2091)	loss 3.1335 (2.9909)	grad_norm 2.8933 (3.1740)	
[2022-01-26 16:59:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][670/1251]	eta 0:21:24 lr 0.000020	time 4.4504 (2.2110)	loss 2.6742 (2.9912)	grad_norm 2.8142 (3.1745)	
[2022-01-26 17:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][680/1251]	eta 0:21:02 lr 0.000020	time 2.1726 (2.2115)	loss 3.0857 (2.9885)	grad_norm 3.1696 (3.1768)	
[2022-01-26 17:00:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][690/1251]	eta 0:20:41 lr 0.000020	time 2.4759 (2.2135)	loss 3.0797 (2.9865)	grad_norm 2.8498 (3.1730)	
[2022-01-26 17:00:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][700/1251]	eta 0:20:20 lr 0.000020	time 2.3881 (2.2154)	loss 3.1425 (2.9895)	grad_norm 3.1720 (3.1706)	
[2022-01-26 17:01:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][710/1251]	eta 0:19:57 lr 0.000020	time 2.6736 (2.2137)	loss 3.2800 (2.9904)	grad_norm 3.1683 (3.1719)	
[2022-01-26 17:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][720/1251]	eta 0:19:33 lr 0.000020	time 1.8966 (2.2109)	loss 3.0160 (2.9909)	grad_norm 2.9466 (3.1750)	
[2022-01-26 17:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][730/1251]	eta 0:19:11 lr 0.000020	time 2.5909 (2.2103)	loss 2.3318 (2.9896)	grad_norm 3.1337 (3.1734)	
[2022-01-26 17:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][740/1251]	eta 0:18:48 lr 0.000020	time 1.8017 (2.2079)	loss 1.7862 (2.9919)	grad_norm 3.2868 (3.1747)	
[2022-01-26 17:02:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][750/1251]	eta 0:18:26 lr 0.000020	time 2.8669 (2.2085)	loss 2.2607 (2.9902)	grad_norm 3.1237 (3.1802)	
[2022-01-26 17:03:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][760/1251]	eta 0:18:04 lr 0.000020	time 2.3008 (2.2078)	loss 3.3818 (2.9934)	grad_norm 3.1678 (3.1805)	
[2022-01-26 17:03:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][770/1251]	eta 0:17:41 lr 0.000020	time 2.0539 (2.2069)	loss 3.5986 (2.9915)	grad_norm 2.9314 (3.1808)	
[2022-01-26 17:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][780/1251]	eta 0:17:18 lr 0.000020	time 1.8182 (2.2054)	loss 2.9800 (2.9907)	grad_norm 2.5895 (3.1783)	
[2022-01-26 17:04:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][790/1251]	eta 0:16:57 lr 0.000020	time 2.8186 (2.2071)	loss 2.8995 (2.9888)	grad_norm 2.9614 (3.1789)	
[2022-01-26 17:04:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][800/1251]	eta 0:16:36 lr 0.000020	time 2.8852 (2.2086)	loss 2.9133 (2.9874)	grad_norm 2.8796 (3.1826)	
[2022-01-26 17:04:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][810/1251]	eta 0:16:14 lr 0.000020	time 2.1858 (2.2090)	loss 3.5749 (2.9906)	grad_norm 3.6179 (3.1849)	
[2022-01-26 17:05:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][820/1251]	eta 0:15:51 lr 0.000020	time 1.8800 (2.2068)	loss 3.0344 (2.9916)	grad_norm 3.4618 (3.1857)	
[2022-01-26 17:05:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][830/1251]	eta 0:15:28 lr 0.000020	time 2.2784 (2.2051)	loss 2.8477 (2.9911)	grad_norm 2.8193 (3.1839)	
[2022-01-26 17:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][840/1251]	eta 0:15:05 lr 0.000020	time 1.7012 (2.2039)	loss 2.7455 (2.9921)	grad_norm 2.9304 (3.1828)	
[2022-01-26 17:06:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][850/1251]	eta 0:14:43 lr 0.000020	time 2.5132 (2.2033)	loss 3.3812 (2.9936)	grad_norm 2.7206 (3.1841)	
[2022-01-26 17:06:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][860/1251]	eta 0:14:21 lr 0.000020	time 2.2479 (2.2024)	loss 2.9399 (2.9941)	grad_norm 3.0638 (3.1866)	
[2022-01-26 17:07:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][870/1251]	eta 0:13:59 lr 0.000020	time 2.4939 (2.2023)	loss 3.5378 (2.9927)	grad_norm 3.4364 (3.1873)	
[2022-01-26 17:07:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][880/1251]	eta 0:13:36 lr 0.000020	time 1.8377 (2.2000)	loss 3.5859 (2.9945)	grad_norm 3.3849 (3.1873)	
[2022-01-26 17:07:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][890/1251]	eta 0:13:14 lr 0.000020	time 2.5572 (2.1996)	loss 3.2771 (2.9944)	grad_norm 4.5039 (3.1883)	
[2022-01-26 17:08:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][900/1251]	eta 0:12:52 lr 0.000020	time 1.9740 (2.1995)	loss 2.1620 (2.9941)	grad_norm 3.7631 (3.1886)	
[2022-01-26 17:08:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][910/1251]	eta 0:12:30 lr 0.000020	time 2.3706 (2.2005)	loss 3.4297 (2.9950)	grad_norm 2.7331 (3.1870)	
[2022-01-26 17:08:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][920/1251]	eta 0:12:08 lr 0.000020	time 1.8310 (2.2005)	loss 3.3214 (2.9942)	grad_norm 3.0923 (3.1869)	
[2022-01-26 17:09:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][930/1251]	eta 0:11:46 lr 0.000020	time 2.0787 (2.2014)	loss 3.2469 (2.9940)	grad_norm 3.5511 (3.1876)	
[2022-01-26 17:09:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][940/1251]	eta 0:11:24 lr 0.000020	time 2.7378 (2.2024)	loss 2.5573 (2.9945)	grad_norm 3.3514 (3.1887)	
[2022-01-26 17:09:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][950/1251]	eta 0:11:02 lr 0.000020	time 2.2378 (2.2024)	loss 2.5311 (2.9908)	grad_norm 8.0712 (3.1923)	
[2022-01-26 17:10:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][960/1251]	eta 0:10:39 lr 0.000020	time 1.6324 (2.1993)	loss 3.0970 (2.9923)	grad_norm 3.4665 (3.1929)	
[2022-01-26 17:10:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][970/1251]	eta 0:10:17 lr 0.000020	time 1.8939 (2.1985)	loss 2.3735 (2.9914)	grad_norm 3.0274 (3.1923)	
[2022-01-26 17:10:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][980/1251]	eta 0:09:55 lr 0.000020	time 1.9309 (2.1959)	loss 3.3836 (2.9926)	grad_norm 3.6955 (3.1897)	
[2022-01-26 17:11:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][990/1251]	eta 0:09:33 lr 0.000020	time 2.5636 (2.1957)	loss 3.2747 (2.9924)	grad_norm 3.7155 (3.1884)	
[2022-01-26 17:11:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1000/1251]	eta 0:09:11 lr 0.000020	time 2.2255 (2.1963)	loss 2.9922 (2.9937)	grad_norm 2.6448 (3.1906)	
[2022-01-26 17:12:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1010/1251]	eta 0:08:49 lr 0.000020	time 2.1591 (2.1974)	loss 3.2988 (2.9942)	grad_norm 3.2816 (3.1938)	
[2022-01-26 17:12:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1020/1251]	eta 0:08:27 lr 0.000020	time 2.0780 (2.1960)	loss 3.4962 (2.9953)	grad_norm 3.2717 (3.1951)	
[2022-01-26 17:12:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1030/1251]	eta 0:08:05 lr 0.000020	time 2.3621 (2.1975)	loss 2.6470 (2.9945)	grad_norm 3.0423 (3.1960)	
[2022-01-26 17:13:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1040/1251]	eta 0:07:43 lr 0.000020	time 2.4757 (2.1986)	loss 3.3866 (2.9958)	grad_norm 3.9855 (3.1956)	
[2022-01-26 17:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1050/1251]	eta 0:07:22 lr 0.000020	time 2.6929 (2.1997)	loss 3.5710 (2.9948)	grad_norm 3.5942 (3.1966)	
[2022-01-26 17:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1060/1251]	eta 0:06:59 lr 0.000020	time 1.8543 (2.1988)	loss 2.8188 (2.9932)	grad_norm 2.8250 (3.1962)	
[2022-01-26 17:14:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1070/1251]	eta 0:06:38 lr 0.000020	time 2.8218 (2.2009)	loss 2.9501 (2.9935)	grad_norm 4.8571 (3.1959)	
[2022-01-26 17:14:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1080/1251]	eta 0:06:16 lr 0.000020	time 1.8846 (2.2009)	loss 3.0922 (2.9942)	grad_norm 3.7805 (3.1974)	
[2022-01-26 17:15:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1090/1251]	eta 0:05:54 lr 0.000020	time 1.9604 (2.1992)	loss 3.3578 (2.9948)	grad_norm 2.9516 (3.1982)	
[2022-01-26 17:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1100/1251]	eta 0:05:31 lr 0.000020	time 1.8784 (2.1971)	loss 3.0764 (2.9956)	grad_norm 3.0517 (3.1977)	
[2022-01-26 17:15:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1110/1251]	eta 0:05:09 lr 0.000020	time 2.3575 (2.1955)	loss 3.0905 (2.9966)	grad_norm 2.8339 (3.1978)	
[2022-01-26 17:16:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1120/1251]	eta 0:04:47 lr 0.000020	time 1.9166 (2.1956)	loss 3.4078 (2.9961)	grad_norm 4.0690 (3.1988)	
[2022-01-26 17:16:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1130/1251]	eta 0:04:25 lr 0.000020	time 1.6442 (2.1963)	loss 3.3157 (2.9959)	grad_norm 3.3432 (3.1987)	
[2022-01-26 17:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1140/1251]	eta 0:04:03 lr 0.000020	time 1.9424 (2.1970)	loss 2.6736 (2.9945)	grad_norm 2.5988 (3.1955)	
[2022-01-26 17:17:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1150/1251]	eta 0:03:42 lr 0.000020	time 3.3453 (2.1985)	loss 3.3666 (2.9966)	grad_norm 3.5951 (3.1948)	
[2022-01-26 17:17:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1160/1251]	eta 0:03:20 lr 0.000020	time 2.3065 (2.1987)	loss 2.0180 (2.9957)	grad_norm 2.5296 (3.1942)	
[2022-01-26 17:17:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1170/1251]	eta 0:02:58 lr 0.000020	time 1.8930 (2.1983)	loss 2.6535 (2.9950)	grad_norm 3.0303 (3.1929)	
[2022-01-26 17:18:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1180/1251]	eta 0:02:36 lr 0.000020	time 2.2490 (2.1983)	loss 2.4269 (2.9942)	grad_norm 3.4468 (3.1964)	
[2022-01-26 17:18:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1190/1251]	eta 0:02:14 lr 0.000020	time 2.1636 (2.1977)	loss 3.0061 (2.9950)	grad_norm 2.7184 (3.1969)	
[2022-01-26 17:19:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1200/1251]	eta 0:01:52 lr 0.000020	time 2.2843 (2.1967)	loss 3.0724 (2.9947)	grad_norm 3.3957 (3.1962)	
[2022-01-26 17:19:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1210/1251]	eta 0:01:30 lr 0.000020	time 2.3316 (2.1967)	loss 2.0207 (2.9932)	grad_norm 3.1014 (3.1954)	
[2022-01-26 17:19:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1220/1251]	eta 0:01:08 lr 0.000020	time 2.2327 (2.1965)	loss 3.3042 (2.9931)	grad_norm 2.6544 (3.1944)	
[2022-01-26 17:20:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1230/1251]	eta 0:00:46 lr 0.000020	time 2.4418 (2.1959)	loss 2.5850 (2.9932)	grad_norm 3.2519 (3.1948)	
[2022-01-26 17:20:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1240/1251]	eta 0:00:24 lr 0.000020	time 1.5406 (2.1944)	loss 3.3581 (2.9938)	grad_norm 3.4996 (3.1944)	
[2022-01-26 17:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [280/300][1250/1251]	eta 0:00:02 lr 0.000020	time 1.1995 (2.1889)	loss 2.0809 (2.9942)	grad_norm 3.2373 (3.1949)	
[2022-01-26 17:20:43 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 280 training takes 0:45:38
[2022-01-26 17:20:43 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_280 saving......
[2022-01-26 17:20:54 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_280 saved !!!
[2022-01-26 17:21:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 15.662 (15.662)	Loss 0.8764 (0.8764)	Acc@1 79.004 (79.004)	Acc@5 94.727 (94.727)	
[2022-01-26 17:21:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.959 (2.666)	Loss 0.7884 (0.8428)	Acc@1 80.566 (80.478)	Acc@5 96.582 (95.206)	
[2022-01-26 17:21:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.195 (2.127)	Loss 0.8241 (0.8180)	Acc@1 80.957 (80.836)	Acc@5 95.117 (95.424)	
[2022-01-26 17:21:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.032 (1.998)	Loss 0.8150 (0.8110)	Acc@1 80.566 (81.014)	Acc@5 95.801 (95.473)	
[2022-01-26 17:22:14 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 0.860 (1.956)	Loss 0.7938 (0.8123)	Acc@1 81.836 (81.028)	Acc@5 95.508 (95.429)	
[2022-01-26 17:22:22 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.086 Acc@5 95.428
[2022-01-26 17:22:22 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.1%
[2022-01-26 17:22:22 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.09%
[2022-01-26 17:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][0/1251]	eta 7:38:01 lr 0.000020	time 21.9680 (21.9680)	loss 3.1432 (3.1432)	grad_norm 3.0744 (3.0744)	
[2022-01-26 17:23:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][10/1251]	eta 1:25:42 lr 0.000020	time 2.2329 (4.1435)	loss 2.0514 (2.8045)	grad_norm 3.0624 (3.1704)	
[2022-01-26 17:23:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][20/1251]	eta 1:07:37 lr 0.000020	time 2.1478 (3.2958)	loss 3.3966 (2.8781)	grad_norm 3.4343 (3.2006)	
[2022-01-26 17:23:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][30/1251]	eta 1:00:29 lr 0.000020	time 1.8485 (2.9729)	loss 1.8350 (2.8330)	grad_norm 3.7961 (3.2197)	
[2022-01-26 17:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][40/1251]	eta 0:56:52 lr 0.000020	time 3.5940 (2.8182)	loss 3.1309 (2.8398)	grad_norm 2.5266 (3.2115)	
[2022-01-26 17:24:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][50/1251]	eta 0:54:30 lr 0.000020	time 1.5453 (2.7235)	loss 3.1272 (2.9149)	grad_norm 3.4569 (3.2130)	
[2022-01-26 17:25:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][60/1251]	eta 0:52:11 lr 0.000020	time 1.8545 (2.6292)	loss 3.6645 (2.9605)	grad_norm 3.0060 (3.2398)	
[2022-01-26 17:25:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][70/1251]	eta 0:50:11 lr 0.000020	time 1.9492 (2.5497)	loss 3.4061 (2.9867)	grad_norm 3.5558 (3.2451)	
[2022-01-26 17:25:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][80/1251]	eta 0:48:43 lr 0.000020	time 2.5815 (2.4964)	loss 3.6348 (2.9694)	grad_norm 3.1023 (3.2129)	
[2022-01-26 17:26:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][90/1251]	eta 0:47:24 lr 0.000020	time 2.0471 (2.4504)	loss 3.2168 (2.9848)	grad_norm 2.7221 (3.2120)	
[2022-01-26 17:26:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][100/1251]	eta 0:46:16 lr 0.000020	time 1.9103 (2.4125)	loss 2.8896 (3.0002)	grad_norm 4.0088 (3.2345)	
[2022-01-26 17:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][110/1251]	eta 0:45:26 lr 0.000020	time 2.3107 (2.3893)	loss 3.3249 (3.0039)	grad_norm 2.9279 (3.2172)	
[2022-01-26 17:27:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][120/1251]	eta 0:44:34 lr 0.000020	time 2.7424 (2.3650)	loss 3.0279 (3.0052)	grad_norm 3.5718 (3.2156)	
[2022-01-26 17:27:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][130/1251]	eta 0:44:00 lr 0.000020	time 1.8168 (2.3555)	loss 3.1852 (3.0034)	grad_norm 3.2289 (3.2150)	
[2022-01-26 17:27:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][140/1251]	eta 0:43:26 lr 0.000020	time 2.1751 (2.3463)	loss 1.9546 (2.9847)	grad_norm 3.2027 (3.1937)	
[2022-01-26 17:28:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][150/1251]	eta 0:42:59 lr 0.000020	time 1.8764 (2.3429)	loss 3.1220 (2.9959)	grad_norm 2.7213 (3.2128)	
[2022-01-26 17:28:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][160/1251]	eta 0:42:45 lr 0.000020	time 4.6181 (2.3517)	loss 2.4714 (2.9882)	grad_norm 3.8209 (3.2103)	
[2022-01-26 17:29:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][170/1251]	eta 0:42:02 lr 0.000020	time 1.5561 (2.3334)	loss 2.9926 (2.9962)	grad_norm 2.8230 (3.2124)	
[2022-01-26 17:29:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][180/1251]	eta 0:41:29 lr 0.000020	time 2.4936 (2.3247)	loss 3.1124 (2.9959)	grad_norm 3.3575 (3.2024)	
[2022-01-26 17:29:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][190/1251]	eta 0:41:02 lr 0.000020	time 1.5248 (2.3209)	loss 3.3692 (2.9826)	grad_norm 3.3385 (3.1927)	
[2022-01-26 17:30:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][200/1251]	eta 0:40:38 lr 0.000020	time 3.4987 (2.3198)	loss 3.1374 (2.9899)	grad_norm 2.6169 (3.1940)	
[2022-01-26 17:30:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][210/1251]	eta 0:40:20 lr 0.000020	time 2.2692 (2.3247)	loss 1.9861 (2.9840)	grad_norm 2.8598 (3.1930)	
[2022-01-26 17:30:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][220/1251]	eta 0:39:40 lr 0.000020	time 1.9165 (2.3085)	loss 3.0750 (2.9937)	grad_norm 2.9835 (3.1918)	
[2022-01-26 17:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][230/1251]	eta 0:39:02 lr 0.000020	time 1.6228 (2.2939)	loss 2.9237 (2.9949)	grad_norm 3.5609 (3.1914)	
[2022-01-26 17:31:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][240/1251]	eta 0:38:26 lr 0.000020	time 2.2080 (2.2810)	loss 2.7944 (2.9904)	grad_norm 3.5238 (3.1886)	
[2022-01-26 17:31:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][250/1251]	eta 0:37:54 lr 0.000020	time 2.1456 (2.2718)	loss 3.3024 (2.9839)	grad_norm 3.2173 (3.1889)	
[2022-01-26 17:32:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][260/1251]	eta 0:37:26 lr 0.000020	time 2.1945 (2.2671)	loss 3.1214 (2.9800)	grad_norm 2.8061 (3.1926)	
[2022-01-26 17:32:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][270/1251]	eta 0:37:04 lr 0.000020	time 2.4931 (2.2680)	loss 3.1228 (2.9747)	grad_norm 2.8053 (3.1936)	
[2022-01-26 17:33:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][280/1251]	eta 0:36:45 lr 0.000020	time 2.3706 (2.2711)	loss 3.2757 (2.9791)	grad_norm 3.3133 (3.1904)	
[2022-01-26 17:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][290/1251]	eta 0:36:27 lr 0.000020	time 2.5179 (2.2759)	loss 3.2584 (2.9820)	grad_norm 3.3534 (3.1871)	
[2022-01-26 17:33:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][300/1251]	eta 0:35:57 lr 0.000020	time 1.5307 (2.2692)	loss 2.9284 (2.9806)	grad_norm 2.8644 (3.1775)	
[2022-01-26 17:34:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][310/1251]	eta 0:35:33 lr 0.000020	time 2.7147 (2.2671)	loss 2.8996 (2.9814)	grad_norm 3.2399 (3.1698)	
[2022-01-26 17:34:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][320/1251]	eta 0:35:04 lr 0.000020	time 1.8831 (2.2604)	loss 2.5059 (2.9786)	grad_norm 3.0447 (3.1681)	
[2022-01-26 17:34:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][330/1251]	eta 0:34:35 lr 0.000019	time 2.1303 (2.2539)	loss 2.9186 (2.9808)	grad_norm 2.9328 (3.1611)	
[2022-01-26 17:35:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][340/1251]	eta 0:34:07 lr 0.000019	time 1.5896 (2.2471)	loss 3.5324 (2.9831)	grad_norm 2.9250 (3.1647)	
[2022-01-26 17:35:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][350/1251]	eta 0:33:42 lr 0.000019	time 2.7731 (2.2444)	loss 3.1483 (2.9859)	grad_norm 3.4205 (3.1613)	
[2022-01-26 17:35:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][360/1251]	eta 0:33:19 lr 0.000019	time 1.8564 (2.2440)	loss 3.3245 (2.9848)	grad_norm 3.3938 (3.1571)	
[2022-01-26 17:36:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][370/1251]	eta 0:32:59 lr 0.000019	time 2.7019 (2.2465)	loss 2.9140 (2.9850)	grad_norm 2.8774 (3.1683)	
[2022-01-26 17:36:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][380/1251]	eta 0:32:37 lr 0.000019	time 2.2632 (2.2470)	loss 3.3004 (2.9811)	grad_norm 2.8612 (3.1828)	
[2022-01-26 17:37:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][390/1251]	eta 0:32:13 lr 0.000019	time 3.1890 (2.2457)	loss 2.6109 (2.9810)	grad_norm 3.0934 (3.1835)	
[2022-01-26 17:37:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][400/1251]	eta 0:31:49 lr 0.000019	time 2.1103 (2.2436)	loss 3.2579 (2.9764)	grad_norm 3.3252 (3.1816)	
[2022-01-26 17:37:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][410/1251]	eta 0:31:24 lr 0.000019	time 2.2345 (2.2413)	loss 2.5907 (2.9714)	grad_norm 3.1929 (3.1795)	
[2022-01-26 17:38:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][420/1251]	eta 0:30:59 lr 0.000019	time 1.8560 (2.2374)	loss 2.5813 (2.9736)	grad_norm 2.7695 (3.1803)	
[2022-01-26 17:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][430/1251]	eta 0:30:34 lr 0.000019	time 2.6442 (2.2339)	loss 3.0922 (2.9734)	grad_norm 3.0659 (3.1774)	
[2022-01-26 17:38:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][440/1251]	eta 0:30:09 lr 0.000019	time 2.1657 (2.2314)	loss 3.6149 (2.9754)	grad_norm 3.1487 (3.1805)	
[2022-01-26 17:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][450/1251]	eta 0:29:48 lr 0.000019	time 2.7774 (2.2325)	loss 2.1737 (2.9722)	grad_norm 3.4566 (3.1808)	
[2022-01-26 17:39:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][460/1251]	eta 0:29:28 lr 0.000019	time 2.5570 (2.2354)	loss 3.2844 (2.9671)	grad_norm 3.4402 (3.1800)	
[2022-01-26 17:39:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][470/1251]	eta 0:29:05 lr 0.000019	time 1.9197 (2.2352)	loss 3.4801 (2.9700)	grad_norm 2.7858 (3.1816)	
[2022-01-26 17:40:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][480/1251]	eta 0:28:43 lr 0.000019	time 1.9113 (2.2351)	loss 2.9915 (2.9717)	grad_norm 3.5371 (3.1834)	
[2022-01-26 17:40:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][490/1251]	eta 0:28:17 lr 0.000019	time 1.8850 (2.2312)	loss 3.4855 (2.9706)	grad_norm 2.9973 (3.1831)	
[2022-01-26 17:41:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][500/1251]	eta 0:27:55 lr 0.000019	time 2.5788 (2.2309)	loss 3.0623 (2.9689)	grad_norm 3.4676 (3.1856)	
[2022-01-26 17:41:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][510/1251]	eta 0:27:33 lr 0.000019	time 2.7241 (2.2315)	loss 2.9956 (2.9709)	grad_norm 2.8416 (3.1840)	
[2022-01-26 17:41:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][520/1251]	eta 0:27:11 lr 0.000019	time 2.5752 (2.2318)	loss 3.4726 (2.9740)	grad_norm 3.3378 (3.1831)	
[2022-01-26 17:42:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][530/1251]	eta 0:26:47 lr 0.000019	time 1.6196 (2.2295)	loss 2.8320 (2.9722)	grad_norm 2.8217 (3.1813)	
[2022-01-26 17:42:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][540/1251]	eta 0:26:22 lr 0.000019	time 1.6494 (2.2253)	loss 2.2075 (2.9653)	grad_norm 2.7687 (3.1828)	
[2022-01-26 17:42:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][550/1251]	eta 0:25:58 lr 0.000019	time 1.8369 (2.2226)	loss 3.6699 (2.9661)	grad_norm 3.3288 (3.1861)	
[2022-01-26 17:43:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][560/1251]	eta 0:25:35 lr 0.000019	time 1.8668 (2.2224)	loss 3.1468 (2.9643)	grad_norm 3.2811 (3.1878)	
[2022-01-26 17:43:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][570/1251]	eta 0:25:13 lr 0.000019	time 2.3481 (2.2218)	loss 3.0542 (2.9637)	grad_norm 3.3362 (3.1892)	
[2022-01-26 17:43:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][580/1251]	eta 0:24:51 lr 0.000019	time 2.2045 (2.2228)	loss 3.5762 (2.9615)	grad_norm 3.1145 (3.1876)	
[2022-01-26 17:44:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][590/1251]	eta 0:24:30 lr 0.000019	time 2.0747 (2.2245)	loss 3.2313 (2.9612)	grad_norm 3.2093 (3.1882)	
[2022-01-26 17:44:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][600/1251]	eta 0:24:07 lr 0.000019	time 2.2189 (2.2237)	loss 3.5212 (2.9647)	grad_norm 2.4957 (3.1849)	
[2022-01-26 17:44:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][610/1251]	eta 0:23:42 lr 0.000019	time 2.1941 (2.2196)	loss 2.6004 (2.9653)	grad_norm 3.6435 (3.1858)	
[2022-01-26 17:45:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][620/1251]	eta 0:23:18 lr 0.000019	time 2.1715 (2.2165)	loss 2.2030 (2.9612)	grad_norm 3.4362 (3.1847)	
[2022-01-26 17:45:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][630/1251]	eta 0:22:55 lr 0.000019	time 1.7955 (2.2152)	loss 3.0814 (2.9624)	grad_norm 2.9483 (3.1865)	
[2022-01-26 17:46:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][640/1251]	eta 0:22:32 lr 0.000019	time 2.4091 (2.2144)	loss 2.4608 (2.9649)	grad_norm 2.6806 (3.1849)	
[2022-01-26 17:46:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][650/1251]	eta 0:22:10 lr 0.000019	time 2.1255 (2.2145)	loss 2.1328 (2.9658)	grad_norm 3.1129 (3.1872)	
[2022-01-26 17:46:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][660/1251]	eta 0:21:49 lr 0.000019	time 2.5572 (2.2156)	loss 2.7517 (2.9670)	grad_norm 2.8732 (3.1863)	
[2022-01-26 17:47:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][670/1251]	eta 0:21:27 lr 0.000019	time 2.0410 (2.2165)	loss 3.6110 (2.9670)	grad_norm 3.2491 (3.1863)	
[2022-01-26 17:47:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][680/1251]	eta 0:21:06 lr 0.000019	time 2.7911 (2.2173)	loss 2.8463 (2.9688)	grad_norm 3.5415 (3.1863)	
[2022-01-26 17:47:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][690/1251]	eta 0:20:42 lr 0.000019	time 1.5523 (2.2145)	loss 2.6894 (2.9653)	grad_norm 6.9578 (3.1894)	
[2022-01-26 17:48:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][700/1251]	eta 0:20:19 lr 0.000019	time 1.6869 (2.2132)	loss 3.5324 (2.9666)	grad_norm 2.8450 (3.1854)	
[2022-01-26 17:48:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][710/1251]	eta 0:19:56 lr 0.000019	time 1.8016 (2.2123)	loss 2.4859 (2.9668)	grad_norm 3.2344 (3.1884)	
[2022-01-26 17:48:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][720/1251]	eta 0:19:34 lr 0.000019	time 2.4141 (2.2128)	loss 3.2908 (2.9675)	grad_norm 3.1581 (3.1885)	
[2022-01-26 17:49:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][730/1251]	eta 0:19:15 lr 0.000019	time 3.2041 (2.2173)	loss 3.2051 (2.9672)	grad_norm 3.5659 (3.1888)	
[2022-01-26 17:49:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][740/1251]	eta 0:18:51 lr 0.000019	time 2.2082 (2.2148)	loss 2.3046 (2.9662)	grad_norm 3.0494 (3.1906)	
[2022-01-26 17:50:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][750/1251]	eta 0:18:28 lr 0.000019	time 2.0243 (2.2127)	loss 2.8517 (2.9686)	grad_norm 3.3253 (3.1947)	
[2022-01-26 17:50:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][760/1251]	eta 0:18:06 lr 0.000019	time 2.2777 (2.2122)	loss 3.4728 (2.9688)	grad_norm 3.1550 (3.1958)	
[2022-01-26 17:50:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][770/1251]	eta 0:17:44 lr 0.000019	time 2.7041 (2.2123)	loss 3.1592 (2.9709)	grad_norm 2.6786 (3.1942)	
[2022-01-26 17:51:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][780/1251]	eta 0:17:22 lr 0.000019	time 2.2854 (2.2134)	loss 3.4313 (2.9728)	grad_norm 2.8520 (3.1930)	
[2022-01-26 17:51:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][790/1251]	eta 0:16:59 lr 0.000019	time 2.1493 (2.2125)	loss 3.2969 (2.9768)	grad_norm 2.6766 (3.1920)	
[2022-01-26 17:51:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][800/1251]	eta 0:16:36 lr 0.000019	time 1.8795 (2.2103)	loss 3.0486 (2.9780)	grad_norm 2.7066 (3.1907)	
[2022-01-26 17:52:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][810/1251]	eta 0:16:15 lr 0.000019	time 2.7212 (2.2121)	loss 2.2985 (2.9795)	grad_norm 2.5439 (3.1885)	
[2022-01-26 17:52:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][820/1251]	eta 0:15:52 lr 0.000019	time 1.9862 (2.2106)	loss 3.0460 (2.9798)	grad_norm 3.1625 (3.1878)	
[2022-01-26 17:52:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][830/1251]	eta 0:15:30 lr 0.000019	time 2.2628 (2.2096)	loss 3.7596 (2.9807)	grad_norm 2.9355 (3.1888)	
[2022-01-26 17:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][840/1251]	eta 0:15:07 lr 0.000019	time 2.0794 (2.2080)	loss 2.1905 (2.9790)	grad_norm 3.5581 (3.1900)	
[2022-01-26 17:53:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][850/1251]	eta 0:14:44 lr 0.000019	time 1.8422 (2.2060)	loss 3.0629 (2.9789)	grad_norm 2.6927 (3.1902)	
[2022-01-26 17:54:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][860/1251]	eta 0:14:21 lr 0.000019	time 1.9583 (2.2040)	loss 3.4749 (2.9804)	grad_norm 3.0704 (3.1922)	
[2022-01-26 17:54:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][870/1251]	eta 0:14:00 lr 0.000019	time 1.8579 (2.2048)	loss 3.2610 (2.9820)	grad_norm 2.8485 (3.1924)	
[2022-01-26 17:54:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][880/1251]	eta 0:13:38 lr 0.000019	time 2.8184 (2.2075)	loss 1.9738 (2.9779)	grad_norm 3.3099 (3.1928)	
[2022-01-26 17:55:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][890/1251]	eta 0:13:17 lr 0.000019	time 2.1578 (2.2091)	loss 1.9247 (2.9782)	grad_norm 2.8635 (3.1915)	
[2022-01-26 17:55:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][900/1251]	eta 0:12:55 lr 0.000019	time 2.3811 (2.2099)	loss 2.1637 (2.9770)	grad_norm 2.7941 (3.1896)	
[2022-01-26 17:55:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][910/1251]	eta 0:12:33 lr 0.000019	time 1.8418 (2.2082)	loss 3.4045 (2.9772)	grad_norm 2.7027 (3.1870)	
[2022-01-26 17:56:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][920/1251]	eta 0:12:10 lr 0.000019	time 2.0475 (2.2064)	loss 2.3527 (2.9771)	grad_norm 3.0724 (3.1845)	
[2022-01-26 17:56:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][930/1251]	eta 0:11:47 lr 0.000019	time 1.9365 (2.2047)	loss 3.1155 (2.9786)	grad_norm 3.3391 (3.1832)	
[2022-01-26 17:56:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][940/1251]	eta 0:11:25 lr 0.000019	time 2.2322 (2.2052)	loss 2.4259 (2.9778)	grad_norm 3.4521 (3.1826)	
[2022-01-26 17:57:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][950/1251]	eta 0:11:03 lr 0.000019	time 1.6419 (2.2043)	loss 3.0733 (2.9790)	grad_norm 2.8244 (3.1838)	
[2022-01-26 17:57:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][960/1251]	eta 0:10:41 lr 0.000019	time 2.5930 (2.2041)	loss 2.6087 (2.9755)	grad_norm 2.9724 (3.1822)	
[2022-01-26 17:58:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][970/1251]	eta 0:10:19 lr 0.000019	time 3.2974 (2.2049)	loss 3.2487 (2.9778)	grad_norm 2.9766 (3.1809)	
[2022-01-26 17:58:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][980/1251]	eta 0:09:57 lr 0.000019	time 2.2606 (2.2060)	loss 3.1424 (2.9803)	grad_norm 3.3418 (3.1796)	
[2022-01-26 17:58:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][990/1251]	eta 0:09:35 lr 0.000019	time 1.5786 (2.2056)	loss 3.2104 (2.9803)	grad_norm 3.0585 (3.1791)	
[2022-01-26 17:59:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1000/1251]	eta 0:09:13 lr 0.000019	time 2.1130 (2.2058)	loss 3.2400 (2.9804)	grad_norm 2.6890 (3.1773)	
[2022-01-26 17:59:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1010/1251]	eta 0:08:51 lr 0.000019	time 2.2828 (2.2049)	loss 1.9259 (2.9790)	grad_norm 3.2105 (3.1782)	
[2022-01-26 17:59:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1020/1251]	eta 0:08:29 lr 0.000019	time 2.5573 (2.2038)	loss 3.0323 (2.9809)	grad_norm 3.0941 (3.1792)	
[2022-01-26 18:00:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1030/1251]	eta 0:08:06 lr 0.000019	time 2.7616 (2.2030)	loss 3.4632 (2.9806)	grad_norm 3.0761 (3.1796)	
[2022-01-26 18:00:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1040/1251]	eta 0:07:44 lr 0.000019	time 2.2838 (2.2035)	loss 3.3867 (2.9801)	grad_norm 3.1242 (3.1805)	
[2022-01-26 18:00:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1050/1251]	eta 0:07:22 lr 0.000019	time 2.5162 (2.2037)	loss 3.2420 (2.9802)	grad_norm 3.2425 (3.1798)	
[2022-01-26 18:01:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1060/1251]	eta 0:07:00 lr 0.000019	time 1.7857 (2.2032)	loss 2.9797 (2.9794)	grad_norm 3.9018 (3.1817)	
[2022-01-26 18:01:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1070/1251]	eta 0:06:38 lr 0.000019	time 2.5145 (2.2035)	loss 3.0811 (2.9803)	grad_norm 2.7068 (3.1792)	
[2022-01-26 18:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1080/1251]	eta 0:06:16 lr 0.000019	time 1.9055 (2.2013)	loss 3.2705 (2.9796)	grad_norm 3.9924 (3.1798)	
[2022-01-26 18:02:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1090/1251]	eta 0:05:54 lr 0.000019	time 2.8585 (2.2002)	loss 3.0928 (2.9795)	grad_norm 3.2422 (3.1812)	
[2022-01-26 18:02:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1100/1251]	eta 0:05:31 lr 0.000019	time 1.7977 (2.1983)	loss 2.2468 (2.9784)	grad_norm 2.8766 (3.1804)	
[2022-01-26 18:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1110/1251]	eta 0:05:09 lr 0.000019	time 2.3177 (2.1975)	loss 3.0384 (2.9801)	grad_norm 3.0666 (3.1784)	
[2022-01-26 18:03:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1120/1251]	eta 0:04:47 lr 0.000019	time 2.2630 (2.1969)	loss 2.7695 (2.9805)	grad_norm 3.2621 (3.1781)	
[2022-01-26 18:03:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1130/1251]	eta 0:04:25 lr 0.000019	time 2.5660 (2.1978)	loss 3.4791 (2.9821)	grad_norm 3.1643 (3.1771)	
[2022-01-26 18:04:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1140/1251]	eta 0:04:03 lr 0.000019	time 1.7736 (2.1979)	loss 2.3791 (2.9798)	grad_norm 3.3905 (3.1781)	
[2022-01-26 18:04:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1150/1251]	eta 0:03:42 lr 0.000019	time 4.5768 (2.2019)	loss 3.2293 (2.9803)	grad_norm 2.8538 (3.1774)	
[2022-01-26 18:05:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1160/1251]	eta 0:03:20 lr 0.000019	time 2.0943 (2.2035)	loss 2.2511 (2.9780)	grad_norm 2.6808 (3.1771)	
[2022-01-26 18:05:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1170/1251]	eta 0:02:58 lr 0.000019	time 3.2706 (2.2043)	loss 3.1109 (2.9804)	grad_norm 3.0648 (3.1761)	
[2022-01-26 18:05:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1180/1251]	eta 0:02:36 lr 0.000019	time 1.5505 (2.2033)	loss 2.9439 (2.9808)	grad_norm 2.8517 (3.1758)	
[2022-01-26 18:06:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1190/1251]	eta 0:02:14 lr 0.000019	time 2.5065 (2.2017)	loss 2.8242 (2.9813)	grad_norm 2.5417 (3.1755)	
[2022-01-26 18:06:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1200/1251]	eta 0:01:52 lr 0.000019	time 2.7454 (2.2009)	loss 2.0401 (2.9795)	grad_norm 2.6354 (3.1738)	
[2022-01-26 18:06:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1210/1251]	eta 0:01:30 lr 0.000019	time 2.7693 (2.2014)	loss 2.6481 (2.9789)	grad_norm 3.1792 (3.1736)	
[2022-01-26 18:07:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1220/1251]	eta 0:01:08 lr 0.000019	time 1.9325 (2.2004)	loss 2.4942 (2.9766)	grad_norm 3.0530 (3.1739)	
[2022-01-26 18:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1230/1251]	eta 0:00:46 lr 0.000019	time 3.4931 (2.2016)	loss 2.5388 (2.9764)	grad_norm 2.7696 (3.1743)	
[2022-01-26 18:07:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1240/1251]	eta 0:00:24 lr 0.000019	time 2.1911 (2.2009)	loss 2.9427 (2.9778)	grad_norm 3.7134 (3.1734)	
[2022-01-26 18:08:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [281/300][1250/1251]	eta 0:00:02 lr 0.000019	time 1.3152 (2.1951)	loss 3.7016 (2.9804)	grad_norm 3.7285 (3.1737)	
[2022-01-26 18:08:08 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 281 training takes 0:45:46
[2022-01-26 18:08:26 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.109 (18.109)	Loss 0.8724 (0.8724)	Acc@1 78.613 (78.613)	Acc@5 94.824 (94.824)	
[2022-01-26 18:08:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.656 (3.219)	Loss 0.8498 (0.8207)	Acc@1 81.836 (80.859)	Acc@5 94.629 (95.286)	
[2022-01-26 18:09:02 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.588 (2.578)	Loss 0.7636 (0.8133)	Acc@1 82.031 (81.166)	Acc@5 96.484 (95.499)	
[2022-01-26 18:09:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.584 (2.387)	Loss 0.8121 (0.8146)	Acc@1 80.273 (81.086)	Acc@5 95.898 (95.486)	
[2022-01-26 18:09:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.198 (2.216)	Loss 0.8045 (0.8140)	Acc@1 81.738 (81.017)	Acc@5 94.922 (95.482)	
[2022-01-26 18:09:46 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.006 Acc@5 95.478
[2022-01-26 18:09:46 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.0%
[2022-01-26 18:09:46 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.09%
[2022-01-26 18:10:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][0/1251]	eta 8:24:09 lr 0.000019	time 24.1806 (24.1806)	loss 3.1594 (3.1594)	grad_norm 3.4827 (3.4827)	
[2022-01-26 18:10:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][10/1251]	eta 1:35:05 lr 0.000019	time 1.9074 (4.5978)	loss 3.4396 (3.0905)	grad_norm 2.7473 (2.9886)	
[2022-01-26 18:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][20/1251]	eta 1:13:06 lr 0.000019	time 1.1792 (3.5636)	loss 3.1100 (2.9658)	grad_norm 2.4931 (3.0637)	
[2022-01-26 18:11:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][30/1251]	eta 1:02:15 lr 0.000019	time 1.5926 (3.0591)	loss 2.6892 (3.0529)	grad_norm 3.1135 (3.1206)	
[2022-01-26 18:11:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][40/1251]	eta 0:57:08 lr 0.000019	time 3.4029 (2.8308)	loss 1.6963 (2.9619)	grad_norm 3.2026 (3.2144)	
[2022-01-26 18:12:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][50/1251]	eta 0:53:56 lr 0.000019	time 1.5787 (2.6951)	loss 2.7937 (2.9166)	grad_norm 3.2246 (3.2204)	
[2022-01-26 18:12:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][60/1251]	eta 0:51:47 lr 0.000019	time 2.2375 (2.6091)	loss 2.0840 (2.9281)	grad_norm 3.4396 (3.1990)	
[2022-01-26 18:12:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][70/1251]	eta 0:50:23 lr 0.000019	time 1.5381 (2.5605)	loss 2.5282 (2.9422)	grad_norm 3.1466 (3.1816)	
[2022-01-26 18:13:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][80/1251]	eta 0:49:20 lr 0.000019	time 3.1107 (2.5285)	loss 3.3333 (2.9334)	grad_norm 3.4609 (3.1885)	
[2022-01-26 18:13:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][90/1251]	eta 0:48:15 lr 0.000019	time 1.8999 (2.4943)	loss 2.8510 (2.9537)	grad_norm 3.3345 (3.2111)	
[2022-01-26 18:13:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][100/1251]	eta 0:47:31 lr 0.000019	time 2.5777 (2.4770)	loss 3.1134 (2.9547)	grad_norm 3.2247 (3.2156)	
[2022-01-26 18:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][110/1251]	eta 0:46:37 lr 0.000019	time 1.5987 (2.4514)	loss 3.2376 (2.9780)	grad_norm 2.9933 (3.2118)	
[2022-01-26 18:14:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][120/1251]	eta 0:45:32 lr 0.000019	time 2.0477 (2.4163)	loss 3.3916 (2.9895)	grad_norm 3.3434 (3.2299)	
[2022-01-26 18:15:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][130/1251]	eta 0:44:46 lr 0.000019	time 1.7724 (2.3963)	loss 3.4630 (2.9822)	grad_norm 3.4578 (3.2272)	
[2022-01-26 18:15:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][140/1251]	eta 0:43:55 lr 0.000019	time 2.8846 (2.3722)	loss 2.2190 (2.9833)	grad_norm 3.4930 (3.2179)	
[2022-01-26 18:15:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][150/1251]	eta 0:43:09 lr 0.000019	time 1.9580 (2.3521)	loss 2.8190 (2.9774)	grad_norm 3.1145 (3.2152)	
[2022-01-26 18:16:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][160/1251]	eta 0:43:21 lr 0.000019	time 1.9227 (2.3843)	loss 3.6689 (2.9745)	grad_norm 3.2642 (3.2040)	
[2022-01-26 18:16:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][170/1251]	eta 0:42:50 lr 0.000019	time 2.9315 (2.3779)	loss 2.7009 (2.9658)	grad_norm 3.2336 (3.2062)	
[2022-01-26 18:16:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][180/1251]	eta 0:42:12 lr 0.000019	time 1.8542 (2.3650)	loss 3.4220 (2.9614)	grad_norm 2.6153 (3.1982)	
[2022-01-26 18:17:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][190/1251]	eta 0:41:35 lr 0.000019	time 2.0341 (2.3517)	loss 2.4108 (2.9573)	grad_norm 3.0383 (3.2060)	
[2022-01-26 18:17:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][200/1251]	eta 0:41:02 lr 0.000019	time 1.7945 (2.3430)	loss 2.7701 (2.9530)	grad_norm 2.8776 (3.2015)	
[2022-01-26 18:17:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][210/1251]	eta 0:40:25 lr 0.000019	time 1.9520 (2.3301)	loss 2.0945 (2.9548)	grad_norm 3.2305 (3.1972)	
[2022-01-26 18:18:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][220/1251]	eta 0:39:49 lr 0.000019	time 2.4676 (2.3172)	loss 3.1775 (2.9696)	grad_norm 4.7554 (3.1994)	
[2022-01-26 18:18:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][230/1251]	eta 0:39:16 lr 0.000019	time 1.8772 (2.3077)	loss 2.9424 (2.9631)	grad_norm 2.9923 (3.1941)	
[2022-01-26 18:19:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][240/1251]	eta 0:38:45 lr 0.000019	time 1.9221 (2.2999)	loss 2.0027 (2.9519)	grad_norm 2.9916 (3.1884)	
[2022-01-26 18:19:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][250/1251]	eta 0:38:17 lr 0.000019	time 1.6246 (2.2954)	loss 3.4081 (2.9553)	grad_norm 2.9112 (3.1846)	
[2022-01-26 18:19:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][260/1251]	eta 0:37:49 lr 0.000019	time 1.8297 (2.2904)	loss 2.6371 (2.9567)	grad_norm 3.1467 (3.1824)	
[2022-01-26 18:20:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][270/1251]	eta 0:37:33 lr 0.000019	time 2.1850 (2.2967)	loss 2.2752 (2.9576)	grad_norm 3.4228 (3.1853)	
[2022-01-26 18:20:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][280/1251]	eta 0:37:09 lr 0.000019	time 1.6028 (2.2956)	loss 2.2767 (2.9504)	grad_norm 3.2389 (3.1926)	
[2022-01-26 18:20:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][290/1251]	eta 0:36:41 lr 0.000019	time 1.9587 (2.2909)	loss 2.4654 (2.9523)	grad_norm 4.1826 (3.1942)	
[2022-01-26 18:21:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][300/1251]	eta 0:36:11 lr 0.000019	time 1.5922 (2.2833)	loss 2.9730 (2.9599)	grad_norm 2.9430 (3.2053)	
[2022-01-26 18:21:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][310/1251]	eta 0:35:42 lr 0.000019	time 1.9177 (2.2766)	loss 3.3210 (2.9614)	grad_norm 3.6809 (3.2059)	
[2022-01-26 18:21:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][320/1251]	eta 0:35:13 lr 0.000019	time 2.1280 (2.2702)	loss 3.3012 (2.9689)	grad_norm 2.9805 (3.2041)	
[2022-01-26 18:22:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][330/1251]	eta 0:34:50 lr 0.000019	time 1.9217 (2.2697)	loss 3.6553 (2.9799)	grad_norm 3.3584 (3.2035)	
[2022-01-26 18:22:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][340/1251]	eta 0:34:29 lr 0.000019	time 2.4572 (2.2713)	loss 3.2436 (2.9786)	grad_norm 3.1707 (3.1984)	
[2022-01-26 18:23:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][350/1251]	eta 0:34:02 lr 0.000018	time 1.7496 (2.2668)	loss 2.9037 (2.9841)	grad_norm 3.1841 (3.1992)	
[2022-01-26 18:23:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][360/1251]	eta 0:33:41 lr 0.000018	time 2.1017 (2.2690)	loss 3.0576 (2.9856)	grad_norm 2.7129 (3.1961)	
[2022-01-26 18:23:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][370/1251]	eta 0:33:17 lr 0.000018	time 1.8717 (2.2673)	loss 2.7954 (2.9802)	grad_norm 2.7341 (3.2055)	
[2022-01-26 18:24:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][380/1251]	eta 0:32:52 lr 0.000018	time 2.2610 (2.2649)	loss 3.1113 (2.9808)	grad_norm 3.5095 (3.2070)	
[2022-01-26 18:24:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][390/1251]	eta 0:32:28 lr 0.000018	time 2.0469 (2.2628)	loss 3.1789 (2.9776)	grad_norm 2.9904 (3.2222)	
[2022-01-26 18:24:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][400/1251]	eta 0:32:03 lr 0.000018	time 1.9205 (2.2605)	loss 3.6949 (2.9793)	grad_norm 2.9601 (3.2183)	
[2022-01-26 18:25:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][410/1251]	eta 0:31:39 lr 0.000018	time 1.8265 (2.2584)	loss 2.6932 (2.9831)	grad_norm 2.8423 (3.2144)	
[2022-01-26 18:25:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][420/1251]	eta 0:31:14 lr 0.000018	time 2.2666 (2.2556)	loss 3.5340 (2.9862)	grad_norm 3.2331 (3.2115)	
[2022-01-26 18:25:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][430/1251]	eta 0:30:50 lr 0.000018	time 2.1920 (2.2535)	loss 2.4569 (2.9846)	grad_norm 2.6738 (3.2087)	
[2022-01-26 18:26:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][440/1251]	eta 0:30:26 lr 0.000018	time 1.9644 (2.2519)	loss 2.0347 (2.9745)	grad_norm 3.6032 (3.2067)	
[2022-01-26 18:26:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][450/1251]	eta 0:30:04 lr 0.000018	time 2.4015 (2.2526)	loss 3.5936 (2.9747)	grad_norm 3.1592 (3.2071)	
[2022-01-26 18:27:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][460/1251]	eta 0:29:41 lr 0.000018	time 1.9246 (2.2521)	loss 3.6105 (2.9787)	grad_norm 3.2666 (3.2039)	
[2022-01-26 18:27:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][470/1251]	eta 0:29:17 lr 0.000018	time 2.1777 (2.2509)	loss 2.7855 (2.9727)	grad_norm 2.8038 (3.2038)	
[2022-01-26 18:27:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][480/1251]	eta 0:28:52 lr 0.000018	time 2.1949 (2.2476)	loss 3.2655 (2.9706)	grad_norm 2.8070 (3.1979)	
[2022-01-26 18:28:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][490/1251]	eta 0:28:28 lr 0.000018	time 1.9194 (2.2452)	loss 3.2303 (2.9732)	grad_norm 3.1463 (3.1927)	
[2022-01-26 18:28:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][500/1251]	eta 0:28:05 lr 0.000018	time 2.2366 (2.2438)	loss 2.8442 (2.9756)	grad_norm 4.0192 (3.1938)	
[2022-01-26 18:28:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][510/1251]	eta 0:27:39 lr 0.000018	time 2.2867 (2.2394)	loss 2.3608 (2.9757)	grad_norm 3.1466 (3.1906)	
[2022-01-26 18:29:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][520/1251]	eta 0:27:14 lr 0.000018	time 2.2185 (2.2364)	loss 2.8087 (2.9728)	grad_norm 3.1428 (3.1985)	
[2022-01-26 18:29:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][530/1251]	eta 0:26:50 lr 0.000018	time 1.8120 (2.2335)	loss 2.8212 (2.9748)	grad_norm 3.6639 (3.2005)	
[2022-01-26 18:29:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][540/1251]	eta 0:26:30 lr 0.000018	time 3.0370 (2.2369)	loss 2.9539 (2.9756)	grad_norm 2.9703 (3.2045)	
[2022-01-26 18:30:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][550/1251]	eta 0:26:08 lr 0.000018	time 2.2378 (2.2377)	loss 2.1752 (2.9699)	grad_norm 3.1899 (3.2027)	
[2022-01-26 18:30:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][560/1251]	eta 0:25:46 lr 0.000018	time 2.5049 (2.2379)	loss 3.5302 (2.9730)	grad_norm 2.8343 (3.2052)	
[2022-01-26 18:31:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][570/1251]	eta 0:25:24 lr 0.000018	time 2.1849 (2.2385)	loss 3.3765 (2.9780)	grad_norm 3.4146 (3.2053)	
[2022-01-26 18:31:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][580/1251]	eta 0:25:01 lr 0.000018	time 2.5269 (2.2377)	loss 2.6146 (2.9743)	grad_norm 3.2595 (3.2033)	
[2022-01-26 18:31:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][590/1251]	eta 0:24:37 lr 0.000018	time 1.8402 (2.2346)	loss 3.0512 (2.9761)	grad_norm 3.6128 (3.2022)	
[2022-01-26 18:32:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][600/1251]	eta 0:24:13 lr 0.000018	time 2.4443 (2.2321)	loss 3.5202 (2.9761)	grad_norm 2.9418 (3.2028)	
[2022-01-26 18:32:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][610/1251]	eta 0:23:49 lr 0.000018	time 1.8419 (2.2304)	loss 3.2739 (2.9762)	grad_norm 3.0576 (3.2017)	
[2022-01-26 18:32:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][620/1251]	eta 0:23:25 lr 0.000018	time 1.9543 (2.2279)	loss 2.3350 (2.9697)	grad_norm 3.5307 (3.1995)	
[2022-01-26 18:33:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][630/1251]	eta 0:23:03 lr 0.000018	time 2.4573 (2.2281)	loss 3.1144 (2.9674)	grad_norm 3.1621 (3.1989)	
[2022-01-26 18:33:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][640/1251]	eta 0:22:41 lr 0.000018	time 2.1671 (2.2280)	loss 2.2767 (2.9700)	grad_norm 3.1803 (3.1989)	
[2022-01-26 18:33:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][650/1251]	eta 0:22:17 lr 0.000018	time 1.8430 (2.2251)	loss 3.0053 (2.9709)	grad_norm 2.4841 (3.1947)	
[2022-01-26 18:34:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][660/1251]	eta 0:21:53 lr 0.000018	time 1.7231 (2.2228)	loss 3.2800 (2.9700)	grad_norm 2.9190 (3.1905)	
[2022-01-26 18:34:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][670/1251]	eta 0:21:33 lr 0.000018	time 3.1288 (2.2255)	loss 3.0203 (2.9709)	grad_norm 2.8982 (3.1880)	
[2022-01-26 18:35:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][680/1251]	eta 0:21:12 lr 0.000018	time 1.7161 (2.2288)	loss 2.2502 (2.9692)	grad_norm 3.3071 (3.1878)	
[2022-01-26 18:35:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][690/1251]	eta 0:20:50 lr 0.000018	time 1.5171 (2.2286)	loss 3.3991 (2.9714)	grad_norm 2.8209 (3.1863)	
[2022-01-26 18:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][700/1251]	eta 0:20:27 lr 0.000018	time 2.1751 (2.2273)	loss 3.3490 (2.9724)	grad_norm 3.1644 (3.1858)	
[2022-01-26 18:36:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][710/1251]	eta 0:20:04 lr 0.000018	time 2.3522 (2.2258)	loss 3.2505 (2.9729)	grad_norm 3.3875 (3.1879)	
[2022-01-26 18:36:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][720/1251]	eta 0:19:41 lr 0.000018	time 1.9703 (2.2259)	loss 3.3189 (2.9753)	grad_norm 2.8912 (3.1850)	
[2022-01-26 18:36:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][730/1251]	eta 0:19:18 lr 0.000018	time 1.7794 (2.2239)	loss 3.5431 (2.9759)	grad_norm 2.7038 (3.1824)	
[2022-01-26 18:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][740/1251]	eta 0:18:56 lr 0.000018	time 1.9810 (2.2236)	loss 3.1093 (2.9748)	grad_norm 2.9254 (3.1802)	
[2022-01-26 18:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][750/1251]	eta 0:18:34 lr 0.000018	time 1.8614 (2.2239)	loss 3.3548 (2.9774)	grad_norm 3.0979 (3.1801)	
[2022-01-26 18:37:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][760/1251]	eta 0:18:12 lr 0.000018	time 1.8390 (2.2248)	loss 3.0823 (2.9766)	grad_norm 2.9169 (3.1780)	
[2022-01-26 18:38:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][770/1251]	eta 0:17:49 lr 0.000018	time 2.1001 (2.2243)	loss 3.2515 (2.9777)	grad_norm 2.7662 (3.1831)	
[2022-01-26 18:38:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][780/1251]	eta 0:17:25 lr 0.000018	time 1.9444 (2.2207)	loss 3.7515 (2.9791)	grad_norm 3.1583 (3.1815)	
[2022-01-26 18:39:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][790/1251]	eta 0:17:02 lr 0.000018	time 1.9362 (2.2190)	loss 3.3498 (2.9812)	grad_norm 2.9228 (3.1831)	
[2022-01-26 18:39:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][800/1251]	eta 0:16:40 lr 0.000018	time 2.2743 (2.2178)	loss 3.4197 (2.9810)	grad_norm 2.7499 (3.1819)	
[2022-01-26 18:39:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][810/1251]	eta 0:16:17 lr 0.000018	time 1.8720 (2.2161)	loss 3.4235 (2.9799)	grad_norm 3.1318 (3.1825)	
[2022-01-26 18:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][820/1251]	eta 0:15:54 lr 0.000018	time 2.4595 (2.2156)	loss 3.3649 (2.9823)	grad_norm 3.5443 (3.1850)	
[2022-01-26 18:40:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][830/1251]	eta 0:15:33 lr 0.000018	time 2.7476 (2.2174)	loss 3.7906 (2.9823)	grad_norm 2.7891 (3.1884)	
[2022-01-26 18:40:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][840/1251]	eta 0:15:12 lr 0.000018	time 3.0943 (2.2190)	loss 3.1199 (2.9812)	grad_norm 2.9655 (3.1877)	
[2022-01-26 18:41:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][850/1251]	eta 0:14:50 lr 0.000018	time 1.6326 (2.2201)	loss 2.8832 (2.9831)	grad_norm 3.1116 (3.1861)	
[2022-01-26 18:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][860/1251]	eta 0:14:27 lr 0.000018	time 1.9332 (2.2192)	loss 2.1907 (2.9809)	grad_norm 5.9905 (3.1911)	
[2022-01-26 18:41:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][870/1251]	eta 0:14:04 lr 0.000018	time 1.8340 (2.2174)	loss 2.1778 (2.9794)	grad_norm 3.2027 (3.1922)	
[2022-01-26 18:42:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][880/1251]	eta 0:13:41 lr 0.000018	time 2.3699 (2.2149)	loss 3.2739 (2.9804)	grad_norm 3.3536 (3.1934)	
[2022-01-26 18:42:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][890/1251]	eta 0:13:19 lr 0.000018	time 1.7215 (2.2153)	loss 3.7659 (2.9824)	grad_norm 3.2915 (3.1941)	
[2022-01-26 18:43:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][900/1251]	eta 0:12:57 lr 0.000018	time 2.3921 (2.2155)	loss 3.4926 (2.9851)	grad_norm 2.9023 (3.1970)	
[2022-01-26 18:43:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][910/1251]	eta 0:12:35 lr 0.000018	time 1.8631 (2.2150)	loss 3.4655 (2.9865)	grad_norm 2.8338 (3.1966)	
[2022-01-26 18:43:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][920/1251]	eta 0:12:13 lr 0.000018	time 1.6950 (2.2158)	loss 3.3990 (2.9861)	grad_norm 3.1688 (3.1965)	
[2022-01-26 18:44:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][930/1251]	eta 0:11:51 lr 0.000018	time 2.1367 (2.2156)	loss 3.2795 (2.9850)	grad_norm 2.9425 (3.1959)	
[2022-01-26 18:44:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][940/1251]	eta 0:11:29 lr 0.000018	time 2.5274 (2.2155)	loss 2.8464 (2.9825)	grad_norm 2.8154 (3.1955)	
[2022-01-26 18:44:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][950/1251]	eta 0:11:06 lr 0.000018	time 2.6865 (2.2151)	loss 3.0786 (2.9836)	grad_norm 2.8999 (3.1939)	
[2022-01-26 18:45:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][960/1251]	eta 0:10:44 lr 0.000018	time 2.1349 (2.2146)	loss 2.9954 (2.9831)	grad_norm 3.2853 (3.1934)	
[2022-01-26 18:45:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][970/1251]	eta 0:10:22 lr 0.000018	time 1.8904 (2.2150)	loss 3.3118 (2.9814)	grad_norm 2.8884 (3.1913)	
[2022-01-26 18:45:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][980/1251]	eta 0:10:00 lr 0.000018	time 2.8140 (2.2143)	loss 3.2390 (2.9812)	grad_norm 3.9963 (3.1913)	
[2022-01-26 18:46:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][990/1251]	eta 0:09:37 lr 0.000018	time 2.4365 (2.2134)	loss 2.8151 (2.9815)	grad_norm 2.9165 (3.1905)	
[2022-01-26 18:46:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1000/1251]	eta 0:09:15 lr 0.000018	time 1.8814 (2.2117)	loss 2.5276 (2.9837)	grad_norm 3.3768 (3.1903)	
[2022-01-26 18:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1010/1251]	eta 0:08:52 lr 0.000018	time 3.1188 (2.2113)	loss 3.2207 (2.9829)	grad_norm 2.8104 (3.1888)	
[2022-01-26 18:47:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1020/1251]	eta 0:08:30 lr 0.000018	time 1.9020 (2.2096)	loss 2.6592 (2.9828)	grad_norm 2.6479 (3.1878)	
[2022-01-26 18:47:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1030/1251]	eta 0:08:08 lr 0.000018	time 2.7552 (2.2102)	loss 3.3517 (2.9834)	grad_norm 3.3241 (3.1904)	
[2022-01-26 18:48:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1040/1251]	eta 0:07:46 lr 0.000018	time 2.5835 (2.2101)	loss 3.2661 (2.9842)	grad_norm 3.4554 (3.1891)	
[2022-01-26 18:48:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1050/1251]	eta 0:07:24 lr 0.000018	time 2.7903 (2.2117)	loss 3.3633 (2.9845)	grad_norm 3.2745 (3.1896)	
[2022-01-26 18:48:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1060/1251]	eta 0:07:02 lr 0.000018	time 1.9287 (2.2124)	loss 2.9077 (2.9860)	grad_norm 2.8770 (3.1896)	
[2022-01-26 18:49:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1070/1251]	eta 0:06:40 lr 0.000018	time 1.9240 (2.2106)	loss 3.5482 (2.9855)	grad_norm 2.9769 (3.1877)	
[2022-01-26 18:49:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1080/1251]	eta 0:06:17 lr 0.000018	time 1.9296 (2.2089)	loss 3.4278 (2.9870)	grad_norm 3.1043 (3.1866)	
[2022-01-26 18:49:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1090/1251]	eta 0:05:55 lr 0.000018	time 2.1250 (2.2076)	loss 2.9580 (2.9863)	grad_norm 3.2860 (3.1855)	
[2022-01-26 18:50:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1100/1251]	eta 0:05:33 lr 0.000018	time 2.0406 (2.2111)	loss 2.9930 (2.9859)	grad_norm 3.4453 (3.1835)	
[2022-01-26 18:50:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1110/1251]	eta 0:05:12 lr 0.000018	time 1.4992 (2.2137)	loss 2.7424 (2.9853)	grad_norm 3.0400 (3.1844)	
[2022-01-26 18:51:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1120/1251]	eta 0:04:49 lr 0.000018	time 1.6864 (2.2129)	loss 3.0884 (2.9853)	grad_norm 2.8381 (3.1850)	
[2022-01-26 18:51:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1130/1251]	eta 0:04:27 lr 0.000018	time 1.7952 (2.2118)	loss 2.9552 (2.9864)	grad_norm 3.0876 (3.1846)	
[2022-01-26 18:51:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1140/1251]	eta 0:04:05 lr 0.000018	time 1.9919 (2.2115)	loss 2.0484 (2.9864)	grad_norm 3.2902 (3.1832)	
[2022-01-26 18:52:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1150/1251]	eta 0:03:43 lr 0.000018	time 1.8433 (2.2101)	loss 3.6240 (2.9864)	grad_norm 2.9096 (3.1818)	
[2022-01-26 18:52:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1160/1251]	eta 0:03:21 lr 0.000018	time 1.8524 (2.2089)	loss 2.3463 (2.9850)	grad_norm 2.6608 (3.1795)	
[2022-01-26 18:52:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1170/1251]	eta 0:02:58 lr 0.000018	time 2.0205 (2.2094)	loss 3.2985 (2.9848)	grad_norm 2.9167 (3.1792)	
[2022-01-26 18:53:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1180/1251]	eta 0:02:36 lr 0.000018	time 2.1492 (2.2102)	loss 3.0012 (2.9868)	grad_norm 3.2926 (3.1790)	
[2022-01-26 18:53:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1190/1251]	eta 0:02:14 lr 0.000018	time 2.5677 (2.2105)	loss 3.0130 (2.9873)	grad_norm 3.2830 (3.1814)	
[2022-01-26 18:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1200/1251]	eta 0:01:52 lr 0.000018	time 1.6212 (2.2092)	loss 2.7704 (2.9881)	grad_norm 2.8411 (3.1803)	
[2022-01-26 18:54:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1210/1251]	eta 0:01:30 lr 0.000018	time 2.8741 (2.2090)	loss 1.7951 (2.9855)	grad_norm 3.1645 (3.1804)	
[2022-01-26 18:54:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1220/1251]	eta 0:01:08 lr 0.000018	time 1.8914 (2.2081)	loss 2.3040 (2.9854)	grad_norm 3.0495 (3.1801)	
[2022-01-26 18:55:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1230/1251]	eta 0:00:46 lr 0.000018	time 2.2455 (2.2083)	loss 3.2611 (2.9836)	grad_norm 3.0269 (3.1785)	
[2022-01-26 18:55:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1240/1251]	eta 0:00:24 lr 0.000018	time 1.4908 (2.2068)	loss 2.4431 (2.9839)	grad_norm 3.1828 (3.1792)	
[2022-01-26 18:55:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [282/300][1250/1251]	eta 0:00:02 lr 0.000018	time 1.2194 (2.2014)	loss 2.9074 (2.9848)	grad_norm 2.8784 (3.1785)	
[2022-01-26 18:55:41 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 282 training takes 0:45:54
[2022-01-26 18:55:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.008 (18.008)	Loss 0.8499 (0.8499)	Acc@1 80.273 (80.273)	Acc@5 95.410 (95.410)	
[2022-01-26 18:56:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.870 (3.191)	Loss 0.7982 (0.8040)	Acc@1 80.859 (81.463)	Acc@5 95.898 (95.588)	
[2022-01-26 18:56:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.313 (2.515)	Loss 0.7837 (0.8060)	Acc@1 81.738 (81.180)	Acc@5 95.898 (95.457)	
[2022-01-26 18:56:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.301 (2.294)	Loss 0.8533 (0.8054)	Acc@1 80.078 (81.168)	Acc@5 94.922 (95.558)	
[2022-01-26 18:57:08 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.323 (2.138)	Loss 0.7869 (0.8043)	Acc@1 80.273 (81.212)	Acc@5 95.996 (95.534)	
[2022-01-26 18:57:16 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.122 Acc@5 95.476
[2022-01-26 18:57:16 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.1%
[2022-01-26 18:57:16 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.12%
[2022-01-26 18:57:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][0/1251]	eta 7:25:10 lr 0.000018	time 21.3513 (21.3513)	loss 2.0182 (2.0182)	grad_norm 3.7964 (3.7964)	
[2022-01-26 18:58:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][10/1251]	eta 1:25:33 lr 0.000018	time 2.5411 (4.1370)	loss 3.2635 (2.9736)	grad_norm 2.6946 (3.2154)	
[2022-01-26 18:58:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][20/1251]	eta 1:07:06 lr 0.000018	time 1.8523 (3.2707)	loss 2.9956 (2.9179)	grad_norm 3.3501 (3.2407)	
[2022-01-26 18:58:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][30/1251]	eta 0:58:31 lr 0.000018	time 1.8639 (2.8759)	loss 3.6474 (2.9539)	grad_norm 2.8772 (3.3468)	
[2022-01-26 18:59:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][40/1251]	eta 0:55:10 lr 0.000018	time 3.1101 (2.7337)	loss 3.2599 (2.9195)	grad_norm 3.0236 (3.3178)	
[2022-01-26 18:59:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][50/1251]	eta 0:53:13 lr 0.000018	time 2.7843 (2.6589)	loss 2.0741 (2.9333)	grad_norm 3.2697 (3.2823)	
[2022-01-26 18:59:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][60/1251]	eta 0:51:20 lr 0.000018	time 2.0778 (2.5864)	loss 3.1788 (2.9577)	grad_norm 2.8797 (3.2762)	
[2022-01-26 19:00:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][70/1251]	eta 0:49:21 lr 0.000018	time 1.8493 (2.5079)	loss 3.2909 (2.9617)	grad_norm 3.2042 (3.2832)	
[2022-01-26 19:00:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][80/1251]	eta 0:48:10 lr 0.000018	time 3.2473 (2.4688)	loss 3.0864 (2.9611)	grad_norm 3.0399 (3.2641)	
[2022-01-26 19:00:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][90/1251]	eta 0:47:14 lr 0.000018	time 2.4774 (2.4411)	loss 2.2281 (2.9630)	grad_norm 3.0507 (3.2533)	
[2022-01-26 19:01:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][100/1251]	eta 0:46:21 lr 0.000018	time 1.5271 (2.4165)	loss 1.8306 (2.9419)	grad_norm 2.7993 (3.2409)	
[2022-01-26 19:01:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][110/1251]	eta 0:45:30 lr 0.000018	time 1.5280 (2.3931)	loss 3.4587 (2.9475)	grad_norm 3.2219 (3.2307)	
[2022-01-26 19:02:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][120/1251]	eta 0:44:41 lr 0.000018	time 2.2796 (2.3710)	loss 3.0167 (2.9400)	grad_norm 3.7508 (3.2401)	
[2022-01-26 19:02:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][130/1251]	eta 0:44:14 lr 0.000018	time 3.2738 (2.3683)	loss 2.6622 (2.9220)	grad_norm 3.1190 (3.2343)	
[2022-01-26 19:02:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][140/1251]	eta 0:43:29 lr 0.000018	time 1.9073 (2.3488)	loss 1.9119 (2.9163)	grad_norm 3.3838 (3.2215)	
[2022-01-26 19:03:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][150/1251]	eta 0:42:43 lr 0.000018	time 1.9190 (2.3285)	loss 2.1444 (2.9270)	grad_norm 3.1366 (3.2167)	
[2022-01-26 19:03:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][160/1251]	eta 0:41:55 lr 0.000018	time 1.9151 (2.3059)	loss 2.1169 (2.9267)	grad_norm 3.2733 (3.2183)	
[2022-01-26 19:03:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][170/1251]	eta 0:41:26 lr 0.000018	time 2.8670 (2.2999)	loss 2.6780 (2.9329)	grad_norm 3.4918 (3.2206)	
[2022-01-26 19:04:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][180/1251]	eta 0:40:56 lr 0.000018	time 1.7413 (2.2938)	loss 3.1420 (2.9429)	grad_norm 3.0613 (3.2237)	
[2022-01-26 19:04:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][190/1251]	eta 0:40:34 lr 0.000018	time 2.3461 (2.2945)	loss 3.3923 (2.9554)	grad_norm 3.2026 (3.2204)	
[2022-01-26 19:04:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][200/1251]	eta 0:40:17 lr 0.000018	time 3.4114 (2.3006)	loss 3.6283 (2.9750)	grad_norm 3.2681 (3.2168)	
[2022-01-26 19:05:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][210/1251]	eta 0:40:02 lr 0.000018	time 3.0917 (2.3077)	loss 2.4371 (2.9752)	grad_norm 3.6281 (3.2128)	
[2022-01-26 19:05:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][220/1251]	eta 0:39:24 lr 0.000018	time 2.0359 (2.2934)	loss 2.5878 (2.9773)	grad_norm 3.4168 (3.2232)	
[2022-01-26 19:06:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][230/1251]	eta 0:38:47 lr 0.000018	time 1.8767 (2.2797)	loss 3.0230 (2.9814)	grad_norm 3.7232 (3.2286)	
[2022-01-26 19:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][240/1251]	eta 0:38:16 lr 0.000018	time 2.5515 (2.2713)	loss 3.5627 (2.9924)	grad_norm 2.8325 (3.2273)	
[2022-01-26 19:06:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][250/1251]	eta 0:37:47 lr 0.000018	time 2.5213 (2.2652)	loss 2.1600 (2.9878)	grad_norm 3.3984 (3.2295)	
[2022-01-26 19:07:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][260/1251]	eta 0:37:26 lr 0.000018	time 2.6750 (2.2665)	loss 3.4357 (2.9839)	grad_norm 3.7051 (3.2278)	
[2022-01-26 19:07:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][270/1251]	eta 0:36:59 lr 0.000018	time 1.8365 (2.2622)	loss 3.4568 (2.9931)	grad_norm 3.0776 (3.2317)	
[2022-01-26 19:07:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][280/1251]	eta 0:36:46 lr 0.000018	time 3.0390 (2.2720)	loss 2.8177 (2.9943)	grad_norm 2.9491 (3.2306)	
[2022-01-26 19:08:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][290/1251]	eta 0:36:22 lr 0.000018	time 2.2091 (2.2714)	loss 3.1775 (2.9939)	grad_norm 2.8787 (3.2290)	
[2022-01-26 19:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][300/1251]	eta 0:35:55 lr 0.000018	time 2.4841 (2.2670)	loss 2.9302 (2.9963)	grad_norm 3.5052 (3.2345)	
[2022-01-26 19:08:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][310/1251]	eta 0:35:25 lr 0.000018	time 1.8873 (2.2586)	loss 2.2774 (2.9861)	grad_norm 3.1648 (3.2330)	
[2022-01-26 19:09:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][320/1251]	eta 0:34:57 lr 0.000018	time 2.8779 (2.2533)	loss 3.4089 (2.9944)	grad_norm 2.9704 (3.2250)	
[2022-01-26 19:09:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][330/1251]	eta 0:34:30 lr 0.000018	time 1.9550 (2.2485)	loss 4.0974 (2.9977)	grad_norm 3.6962 (3.2218)	
[2022-01-26 19:10:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][340/1251]	eta 0:34:09 lr 0.000018	time 2.4870 (2.2501)	loss 3.2468 (3.0038)	grad_norm 3.7910 (3.2246)	
[2022-01-26 19:10:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][350/1251]	eta 0:33:45 lr 0.000018	time 1.9437 (2.2479)	loss 2.4839 (2.9987)	grad_norm 3.1072 (3.2270)	
[2022-01-26 19:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][360/1251]	eta 0:33:24 lr 0.000018	time 2.9691 (2.2500)	loss 3.4650 (3.0002)	grad_norm 3.1781 (3.2224)	
[2022-01-26 19:11:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][370/1251]	eta 0:33:01 lr 0.000018	time 2.5637 (2.2487)	loss 2.6274 (2.9995)	grad_norm 3.1346 (3.2228)	
[2022-01-26 19:11:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][380/1251]	eta 0:32:33 lr 0.000018	time 2.2714 (2.2423)	loss 3.0306 (2.9905)	grad_norm 3.9744 (3.2279)	
[2022-01-26 19:11:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][390/1251]	eta 0:32:04 lr 0.000018	time 1.9230 (2.2351)	loss 2.9091 (2.9892)	grad_norm 3.1067 (3.2281)	
[2022-01-26 19:12:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][400/1251]	eta 0:31:41 lr 0.000018	time 2.4392 (2.2348)	loss 3.3032 (2.9946)	grad_norm 2.9231 (3.2269)	
[2022-01-26 19:12:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][410/1251]	eta 0:31:20 lr 0.000018	time 1.7275 (2.2361)	loss 2.5168 (2.9917)	grad_norm 3.4869 (3.2259)	
[2022-01-26 19:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][420/1251]	eta 0:30:57 lr 0.000018	time 2.1532 (2.2358)	loss 3.6418 (2.9927)	grad_norm 3.5104 (3.2242)	
[2022-01-26 19:13:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][430/1251]	eta 0:30:33 lr 0.000018	time 2.3100 (2.2329)	loss 2.5804 (2.9892)	grad_norm 2.9719 (3.2186)	
[2022-01-26 19:13:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][440/1251]	eta 0:30:11 lr 0.000018	time 2.1196 (2.2334)	loss 3.7132 (2.9935)	grad_norm 4.0819 (3.2201)	
[2022-01-26 19:14:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][450/1251]	eta 0:29:49 lr 0.000017	time 1.9983 (2.2336)	loss 2.9575 (2.9940)	grad_norm 3.1472 (3.2177)	
[2022-01-26 19:14:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][460/1251]	eta 0:29:23 lr 0.000017	time 1.6624 (2.2292)	loss 2.6073 (2.9907)	grad_norm 3.5712 (3.2189)	
[2022-01-26 19:14:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][470/1251]	eta 0:28:58 lr 0.000017	time 2.0499 (2.2261)	loss 3.4697 (2.9883)	grad_norm 3.4000 (3.2217)	
[2022-01-26 19:15:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][480/1251]	eta 0:28:34 lr 0.000017	time 2.4280 (2.2234)	loss 3.5403 (2.9822)	grad_norm 3.7637 (3.2277)	
[2022-01-26 19:15:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][490/1251]	eta 0:28:14 lr 0.000017	time 2.1486 (2.2272)	loss 3.3973 (2.9850)	grad_norm 3.1745 (3.2248)	
[2022-01-26 19:15:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][500/1251]	eta 0:27:52 lr 0.000017	time 1.8761 (2.2277)	loss 3.2407 (2.9844)	grad_norm 3.3173 (3.2246)	
[2022-01-26 19:16:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][510/1251]	eta 0:27:29 lr 0.000017	time 2.1197 (2.2258)	loss 3.3332 (2.9856)	grad_norm 2.8054 (3.2218)	
[2022-01-26 19:16:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][520/1251]	eta 0:27:06 lr 0.000017	time 2.5581 (2.2253)	loss 2.7072 (2.9882)	grad_norm 3.5020 (3.2198)	
[2022-01-26 19:16:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][530/1251]	eta 0:26:42 lr 0.000017	time 2.1853 (2.2226)	loss 3.2969 (2.9896)	grad_norm 3.3701 (3.2406)	
[2022-01-26 19:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][540/1251]	eta 0:26:20 lr 0.000017	time 2.6901 (2.2229)	loss 3.1320 (2.9875)	grad_norm 2.9230 (3.2417)	
[2022-01-26 19:17:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][550/1251]	eta 0:25:58 lr 0.000017	time 2.5110 (2.2231)	loss 3.5728 (2.9899)	grad_norm 2.7028 (3.2386)	
[2022-01-26 19:18:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][560/1251]	eta 0:25:34 lr 0.000017	time 2.0669 (2.2209)	loss 3.4464 (2.9928)	grad_norm 3.6755 (3.2536)	
[2022-01-26 19:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][570/1251]	eta 0:25:13 lr 0.000017	time 1.8372 (2.2225)	loss 2.1792 (2.9886)	grad_norm 3.3964 (3.2581)	
[2022-01-26 19:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][580/1251]	eta 0:24:51 lr 0.000017	time 2.2654 (2.2231)	loss 2.7497 (2.9885)	grad_norm 3.1785 (3.2572)	
[2022-01-26 19:19:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][590/1251]	eta 0:24:28 lr 0.000017	time 1.8818 (2.2212)	loss 2.4508 (2.9906)	grad_norm 3.2958 (3.2567)	
[2022-01-26 19:19:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][600/1251]	eta 0:24:03 lr 0.000017	time 1.8755 (2.2168)	loss 3.2899 (2.9912)	grad_norm 3.1231 (3.2585)	
[2022-01-26 19:19:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][610/1251]	eta 0:23:38 lr 0.000017	time 2.1066 (2.2135)	loss 3.5040 (2.9930)	grad_norm 3.2102 (3.2591)	
[2022-01-26 19:20:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][620/1251]	eta 0:23:15 lr 0.000017	time 2.1633 (2.2121)	loss 3.2142 (2.9954)	grad_norm 3.3594 (3.2609)	
[2022-01-26 19:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][630/1251]	eta 0:22:54 lr 0.000017	time 1.9629 (2.2131)	loss 3.2913 (2.9980)	grad_norm 3.3635 (3.2606)	
[2022-01-26 19:20:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][640/1251]	eta 0:22:34 lr 0.000017	time 1.6497 (2.2172)	loss 3.5275 (2.9947)	grad_norm 3.2090 (3.2573)	
[2022-01-26 19:21:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][650/1251]	eta 0:22:13 lr 0.000017	time 2.4817 (2.2180)	loss 3.1788 (2.9959)	grad_norm 2.5666 (3.2536)	
[2022-01-26 19:21:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][660/1251]	eta 0:21:49 lr 0.000017	time 1.7512 (2.2155)	loss 2.7446 (2.9936)	grad_norm 3.0772 (3.2517)	
[2022-01-26 19:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][670/1251]	eta 0:21:26 lr 0.000017	time 1.8578 (2.2143)	loss 3.4083 (2.9926)	grad_norm 2.9200 (3.2538)	
[2022-01-26 19:22:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][680/1251]	eta 0:21:03 lr 0.000017	time 1.9997 (2.2122)	loss 3.2423 (2.9926)	grad_norm 3.3216 (3.2605)	
[2022-01-26 19:22:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][690/1251]	eta 0:20:42 lr 0.000017	time 3.0833 (2.2142)	loss 3.4713 (2.9903)	grad_norm 3.0714 (3.2575)	
[2022-01-26 19:23:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][700/1251]	eta 0:20:19 lr 0.000017	time 2.1191 (2.2141)	loss 2.5591 (2.9904)	grad_norm 2.9657 (3.2569)	
[2022-01-26 19:23:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][710/1251]	eta 0:19:57 lr 0.000017	time 2.1863 (2.2131)	loss 3.4882 (2.9911)	grad_norm 3.2004 (3.2548)	
[2022-01-26 19:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][720/1251]	eta 0:19:33 lr 0.000017	time 2.2365 (2.2107)	loss 3.7578 (2.9925)	grad_norm 3.3625 (3.2527)	
[2022-01-26 19:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][730/1251]	eta 0:19:10 lr 0.000017	time 2.1685 (2.2076)	loss 3.3331 (2.9945)	grad_norm 3.4159 (3.2544)	
[2022-01-26 19:24:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][740/1251]	eta 0:18:46 lr 0.000017	time 2.0291 (2.2044)	loss 3.0468 (2.9963)	grad_norm 3.4683 (3.2522)	
[2022-01-26 19:24:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][750/1251]	eta 0:18:23 lr 0.000017	time 2.2411 (2.2034)	loss 2.1696 (2.9946)	grad_norm 4.6996 (3.2543)	
[2022-01-26 19:25:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][760/1251]	eta 0:18:02 lr 0.000017	time 2.7771 (2.2046)	loss 3.3672 (2.9968)	grad_norm 3.0259 (3.2544)	
[2022-01-26 19:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][770/1251]	eta 0:17:41 lr 0.000017	time 2.1575 (2.2075)	loss 2.6668 (2.9959)	grad_norm 3.2560 (3.2524)	
[2022-01-26 19:26:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][780/1251]	eta 0:17:20 lr 0.000017	time 1.9466 (2.2088)	loss 3.3001 (2.9952)	grad_norm 2.9256 (3.2554)	
[2022-01-26 19:26:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][790/1251]	eta 0:16:58 lr 0.000017	time 1.9014 (2.2097)	loss 2.8447 (2.9961)	grad_norm 2.8779 (3.2550)	
[2022-01-26 19:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][800/1251]	eta 0:16:36 lr 0.000017	time 1.5973 (2.2102)	loss 3.1614 (2.9957)	grad_norm 2.9658 (3.2534)	
[2022-01-26 19:27:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][810/1251]	eta 0:16:13 lr 0.000017	time 1.6041 (2.2079)	loss 2.0527 (2.9924)	grad_norm 2.9304 (3.2512)	
[2022-01-26 19:27:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][820/1251]	eta 0:15:51 lr 0.000017	time 1.9512 (2.2076)	loss 3.6677 (2.9933)	grad_norm 4.4456 (3.2531)	
[2022-01-26 19:27:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][830/1251]	eta 0:15:29 lr 0.000017	time 1.9551 (2.2075)	loss 3.7435 (2.9928)	grad_norm 3.2632 (3.2526)	
[2022-01-26 19:28:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][840/1251]	eta 0:15:06 lr 0.000017	time 1.8022 (2.2061)	loss 1.9469 (2.9912)	grad_norm 3.1246 (3.2519)	
[2022-01-26 19:28:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][850/1251]	eta 0:14:44 lr 0.000017	time 2.5078 (2.2060)	loss 2.3475 (2.9908)	grad_norm 3.3619 (3.2506)	
[2022-01-26 19:28:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][860/1251]	eta 0:14:22 lr 0.000017	time 1.7019 (2.2051)	loss 3.5198 (2.9921)	grad_norm 3.9180 (3.2523)	
[2022-01-26 19:29:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][870/1251]	eta 0:14:00 lr 0.000017	time 2.5979 (2.2073)	loss 2.8809 (2.9935)	grad_norm 3.2018 (3.2504)	
[2022-01-26 19:29:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][880/1251]	eta 0:13:39 lr 0.000017	time 2.4352 (2.2089)	loss 2.4408 (2.9929)	grad_norm 3.0572 (3.2509)	
[2022-01-26 19:30:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][890/1251]	eta 0:13:16 lr 0.000017	time 2.5175 (2.2076)	loss 2.7205 (2.9928)	grad_norm 3.2279 (3.2478)	
[2022-01-26 19:30:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][900/1251]	eta 0:12:53 lr 0.000017	time 1.6255 (2.2050)	loss 3.3681 (2.9908)	grad_norm 2.7226 (3.2463)	
[2022-01-26 19:30:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][910/1251]	eta 0:12:31 lr 0.000017	time 2.3817 (2.2042)	loss 3.0970 (2.9898)	grad_norm 3.5062 (3.2449)	
[2022-01-26 19:31:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][920/1251]	eta 0:12:09 lr 0.000017	time 1.9593 (2.2037)	loss 3.2253 (2.9898)	grad_norm 3.7380 (3.2446)	
[2022-01-26 19:31:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][930/1251]	eta 0:11:47 lr 0.000017	time 2.8178 (2.2048)	loss 3.5639 (2.9913)	grad_norm 3.5642 (3.2437)	
[2022-01-26 19:31:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][940/1251]	eta 0:11:25 lr 0.000017	time 1.8885 (2.2028)	loss 3.0529 (2.9888)	grad_norm 3.1950 (3.2463)	
[2022-01-26 19:32:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][950/1251]	eta 0:11:02 lr 0.000017	time 1.9219 (2.2022)	loss 3.1435 (2.9869)	grad_norm 3.9516 (3.2481)	
[2022-01-26 19:32:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][960/1251]	eta 0:10:41 lr 0.000017	time 2.5849 (2.2035)	loss 3.2102 (2.9879)	grad_norm 3.2681 (3.2468)	
[2022-01-26 19:32:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][970/1251]	eta 0:10:19 lr 0.000017	time 1.7199 (2.2034)	loss 1.8814 (2.9871)	grad_norm 3.4726 (3.2459)	
[2022-01-26 19:33:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][980/1251]	eta 0:09:57 lr 0.000017	time 2.7454 (2.2041)	loss 3.4023 (2.9866)	grad_norm 3.2653 (3.2448)	
[2022-01-26 19:33:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][990/1251]	eta 0:09:34 lr 0.000017	time 1.6332 (2.2029)	loss 2.8070 (2.9881)	grad_norm 2.8916 (3.2450)	
[2022-01-26 19:34:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1000/1251]	eta 0:09:13 lr 0.000017	time 2.7948 (2.2033)	loss 2.8451 (2.9866)	grad_norm 3.1252 (3.2477)	
[2022-01-26 19:34:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1010/1251]	eta 0:08:50 lr 0.000017	time 1.9836 (2.2021)	loss 3.3575 (2.9893)	grad_norm 3.0155 (3.2480)	
[2022-01-26 19:34:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1020/1251]	eta 0:08:28 lr 0.000017	time 1.9243 (2.2005)	loss 2.9484 (2.9883)	grad_norm 2.7920 (3.2453)	
[2022-01-26 19:35:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1030/1251]	eta 0:08:05 lr 0.000017	time 2.5506 (2.1985)	loss 3.3954 (2.9895)	grad_norm 2.7574 (3.2449)	
[2022-01-26 19:35:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1040/1251]	eta 0:07:43 lr 0.000017	time 1.8889 (2.1971)	loss 3.2001 (2.9871)	grad_norm 3.0973 (3.2450)	
[2022-01-26 19:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1050/1251]	eta 0:07:21 lr 0.000017	time 1.9227 (2.1962)	loss 3.5536 (2.9892)	grad_norm 3.3925 (3.2451)	
[2022-01-26 19:36:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1060/1251]	eta 0:06:59 lr 0.000017	time 2.5962 (2.1966)	loss 3.3138 (2.9910)	grad_norm 2.8427 (3.2476)	
[2022-01-26 19:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1070/1251]	eta 0:06:37 lr 0.000017	time 2.5483 (2.1972)	loss 3.0315 (2.9893)	grad_norm 3.4261 (3.2468)	
[2022-01-26 19:36:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1080/1251]	eta 0:06:15 lr 0.000017	time 2.2042 (2.1978)	loss 3.4017 (2.9892)	grad_norm 3.3330 (3.2456)	
[2022-01-26 19:37:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1090/1251]	eta 0:05:54 lr 0.000017	time 2.1605 (2.2001)	loss 2.8308 (2.9891)	grad_norm 3.8562 (3.2458)	
[2022-01-26 19:37:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1100/1251]	eta 0:05:32 lr 0.000017	time 3.0316 (2.2034)	loss 1.9911 (2.9870)	grad_norm 2.9210 (3.2439)	
[2022-01-26 19:38:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1110/1251]	eta 0:05:10 lr 0.000017	time 2.4706 (2.2047)	loss 2.1763 (2.9884)	grad_norm 3.5234 (3.2431)	
[2022-01-26 19:38:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1120/1251]	eta 0:04:48 lr 0.000017	time 1.5646 (2.2024)	loss 2.4431 (2.9892)	grad_norm 3.3421 (3.2426)	
[2022-01-26 19:38:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1130/1251]	eta 0:04:26 lr 0.000017	time 2.2540 (2.1995)	loss 3.0741 (2.9904)	grad_norm 3.1319 (3.2422)	
[2022-01-26 19:39:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1140/1251]	eta 0:04:03 lr 0.000017	time 1.6761 (2.1975)	loss 2.6413 (2.9893)	grad_norm 2.9745 (3.2408)	
[2022-01-26 19:39:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1150/1251]	eta 0:03:41 lr 0.000017	time 1.6121 (2.1973)	loss 3.1526 (2.9892)	grad_norm 3.4850 (3.2394)	
[2022-01-26 19:39:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1160/1251]	eta 0:03:19 lr 0.000017	time 2.1386 (2.1975)	loss 2.5033 (2.9888)	grad_norm 3.1438 (3.2384)	
[2022-01-26 19:40:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1170/1251]	eta 0:02:58 lr 0.000017	time 4.5503 (2.1989)	loss 2.7690 (2.9882)	grad_norm 2.7970 (3.2382)	
[2022-01-26 19:40:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1180/1251]	eta 0:02:36 lr 0.000017	time 1.5279 (2.2001)	loss 1.9119 (2.9875)	grad_norm 2.6376 (3.2390)	
[2022-01-26 19:40:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1190/1251]	eta 0:02:14 lr 0.000017	time 2.1322 (2.2011)	loss 2.4570 (2.9872)	grad_norm 3.6722 (3.2401)	
[2022-01-26 19:41:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1200/1251]	eta 0:01:52 lr 0.000017	time 2.1852 (2.2010)	loss 3.4861 (2.9875)	grad_norm 3.4393 (3.2398)	
[2022-01-26 19:41:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1210/1251]	eta 0:01:30 lr 0.000017	time 6.7036 (2.2039)	loss 2.9437 (2.9886)	grad_norm 3.4767 (3.2398)	
[2022-01-26 19:42:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1220/1251]	eta 0:01:08 lr 0.000017	time 1.9404 (2.2020)	loss 2.0660 (2.9874)	grad_norm 2.9701 (3.2399)	
[2022-01-26 19:42:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1230/1251]	eta 0:00:46 lr 0.000017	time 1.8864 (2.2006)	loss 3.2942 (2.9875)	grad_norm 2.9772 (3.2410)	
[2022-01-26 19:42:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1240/1251]	eta 0:00:24 lr 0.000017	time 1.5085 (2.1985)	loss 3.3230 (2.9879)	grad_norm 2.9686 (3.2407)	
[2022-01-26 19:43:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [283/300][1250/1251]	eta 0:00:02 lr 0.000017	time 1.2073 (2.1934)	loss 2.9152 (2.9876)	grad_norm 2.7937 (3.2395)	
[2022-01-26 19:43:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 283 training takes 0:45:44
[2022-01-26 19:43:20 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.177 (19.177)	Loss 0.8055 (0.8055)	Acc@1 81.738 (81.738)	Acc@5 95.020 (95.020)	
[2022-01-26 19:43:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.165 (3.440)	Loss 0.7974 (0.8268)	Acc@1 81.934 (80.700)	Acc@5 95.996 (95.153)	
[2022-01-26 19:43:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.592 (2.628)	Loss 0.8746 (0.8132)	Acc@1 79.590 (81.017)	Acc@5 94.824 (95.382)	
[2022-01-26 19:44:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.672 (2.283)	Loss 0.8128 (0.8041)	Acc@1 81.836 (81.206)	Acc@5 94.824 (95.489)	
[2022-01-26 19:44:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.114 (2.163)	Loss 0.7759 (0.8054)	Acc@1 82.031 (81.129)	Acc@5 95.312 (95.467)	
[2022-01-26 19:44:36 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.094 Acc@5 95.420
[2022-01-26 19:44:36 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.1%
[2022-01-26 19:44:36 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.12%
[2022-01-26 19:44:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][0/1251]	eta 7:38:21 lr 0.000017	time 21.9835 (21.9835)	loss 3.8739 (3.8739)	grad_norm 3.2706 (3.2706)	
[2022-01-26 19:45:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][10/1251]	eta 1:26:21 lr 0.000017	time 1.5419 (4.1749)	loss 2.6135 (3.0912)	grad_norm 2.9470 (3.2750)	
[2022-01-26 19:45:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][20/1251]	eta 1:04:28 lr 0.000017	time 1.6419 (3.1423)	loss 2.2333 (2.9027)	grad_norm 3.1347 (3.3082)	
[2022-01-26 19:46:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][30/1251]	eta 0:57:32 lr 0.000017	time 1.8898 (2.8272)	loss 2.7754 (2.9048)	grad_norm 3.3233 (3.3357)	
[2022-01-26 19:46:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][40/1251]	eta 0:54:32 lr 0.000017	time 3.5912 (2.7021)	loss 3.4845 (2.8963)	grad_norm 3.4373 (3.2886)	
[2022-01-26 19:46:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][50/1251]	eta 0:53:34 lr 0.000017	time 2.7811 (2.6761)	loss 2.5111 (2.8972)	grad_norm 3.0443 (3.3328)	
[2022-01-26 19:47:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][60/1251]	eta 0:51:49 lr 0.000017	time 2.4939 (2.6108)	loss 3.2338 (2.8844)	grad_norm 2.9726 (3.3105)	
[2022-01-26 19:47:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][70/1251]	eta 0:50:18 lr 0.000017	time 1.9103 (2.5559)	loss 3.4202 (2.9144)	grad_norm 2.7206 (3.3179)	
[2022-01-26 19:47:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][80/1251]	eta 0:48:49 lr 0.000017	time 1.9714 (2.5018)	loss 3.3835 (2.9245)	grad_norm 3.1381 (3.2804)	
[2022-01-26 19:48:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][90/1251]	eta 0:47:49 lr 0.000017	time 2.8569 (2.4717)	loss 2.9794 (2.9606)	grad_norm 2.8697 (3.2753)	
[2022-01-26 19:48:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][100/1251]	eta 0:46:34 lr 0.000017	time 1.8433 (2.4281)	loss 2.8044 (2.9448)	grad_norm 3.6095 (3.2684)	
[2022-01-26 19:49:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][110/1251]	eta 0:45:47 lr 0.000017	time 2.4170 (2.4080)	loss 3.5727 (2.9605)	grad_norm 3.1680 (3.2508)	
[2022-01-26 19:49:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][120/1251]	eta 0:45:05 lr 0.000017	time 1.7950 (2.3924)	loss 2.2372 (2.9553)	grad_norm 3.4356 (3.2555)	
[2022-01-26 19:49:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][130/1251]	eta 0:44:43 lr 0.000017	time 3.2448 (2.3942)	loss 3.3028 (2.9536)	grad_norm 3.7937 (3.2618)	
[2022-01-26 19:50:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][140/1251]	eta 0:43:54 lr 0.000017	time 1.6583 (2.3711)	loss 3.5177 (2.9721)	grad_norm 4.1672 (3.2427)	
[2022-01-26 19:50:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][150/1251]	eta 0:43:22 lr 0.000017	time 2.4909 (2.3637)	loss 3.3508 (2.9685)	grad_norm 2.9171 (3.2350)	
[2022-01-26 19:50:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][160/1251]	eta 0:42:41 lr 0.000017	time 1.8869 (2.3482)	loss 2.9798 (2.9625)	grad_norm 3.0781 (3.2478)	
[2022-01-26 19:51:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][170/1251]	eta 0:42:06 lr 0.000017	time 2.7638 (2.3367)	loss 3.1530 (2.9653)	grad_norm 3.7188 (3.2489)	
[2022-01-26 19:51:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][180/1251]	eta 0:41:19 lr 0.000017	time 1.5301 (2.3153)	loss 3.5224 (2.9834)	grad_norm 3.2059 (3.2423)	
[2022-01-26 19:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][190/1251]	eta 0:40:36 lr 0.000017	time 1.7772 (2.2968)	loss 3.1870 (2.9880)	grad_norm 3.3712 (3.2484)	
[2022-01-26 19:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][200/1251]	eta 0:40:08 lr 0.000017	time 2.3222 (2.2917)	loss 2.2799 (2.9836)	grad_norm 3.6495 (3.2507)	
[2022-01-26 19:52:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][210/1251]	eta 0:39:49 lr 0.000017	time 2.8941 (2.2953)	loss 3.0556 (2.9850)	grad_norm 3.1262 (3.2450)	
[2022-01-26 19:53:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][220/1251]	eta 0:39:28 lr 0.000017	time 2.1277 (2.2972)	loss 2.5546 (2.9820)	grad_norm 2.9982 (3.2477)	
[2022-01-26 19:53:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][230/1251]	eta 0:39:03 lr 0.000017	time 3.1588 (2.2952)	loss 3.4866 (2.9904)	grad_norm 3.8269 (3.2508)	
[2022-01-26 19:53:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][240/1251]	eta 0:38:40 lr 0.000017	time 2.6721 (2.2949)	loss 3.2193 (2.9838)	grad_norm 3.3655 (3.2573)	
[2022-01-26 19:54:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][250/1251]	eta 0:38:13 lr 0.000017	time 2.4839 (2.2911)	loss 2.9629 (2.9660)	grad_norm 3.0288 (3.2532)	
[2022-01-26 19:54:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][260/1251]	eta 0:37:43 lr 0.000017	time 1.7824 (2.2844)	loss 3.1769 (2.9680)	grad_norm 3.2442 (3.2476)	
[2022-01-26 19:54:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][270/1251]	eta 0:37:18 lr 0.000017	time 1.8942 (2.2815)	loss 3.4085 (2.9677)	grad_norm 3.5025 (3.2495)	
[2022-01-26 19:55:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][280/1251]	eta 0:36:53 lr 0.000017	time 1.9186 (2.2792)	loss 2.0093 (2.9655)	grad_norm 2.7057 (3.2472)	
[2022-01-26 19:55:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][290/1251]	eta 0:36:21 lr 0.000017	time 1.6183 (2.2701)	loss 2.2168 (2.9638)	grad_norm 3.4060 (3.2444)	
[2022-01-26 19:55:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][300/1251]	eta 0:35:54 lr 0.000017	time 2.5236 (2.2660)	loss 2.7650 (2.9704)	grad_norm 3.1000 (3.2702)	
[2022-01-26 19:56:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][310/1251]	eta 0:35:28 lr 0.000017	time 1.8282 (2.2618)	loss 3.3278 (2.9638)	grad_norm 3.4870 (3.2680)	
[2022-01-26 19:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][320/1251]	eta 0:35:03 lr 0.000017	time 2.2876 (2.2591)	loss 2.9475 (2.9616)	grad_norm 3.5700 (3.2675)	
[2022-01-26 19:57:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][330/1251]	eta 0:34:40 lr 0.000017	time 2.1781 (2.2595)	loss 3.3616 (2.9660)	grad_norm 3.1434 (3.2684)	
[2022-01-26 19:57:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][340/1251]	eta 0:34:18 lr 0.000017	time 2.1523 (2.2597)	loss 3.5394 (2.9662)	grad_norm 3.2313 (3.2640)	
[2022-01-26 19:57:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][350/1251]	eta 0:33:50 lr 0.000017	time 2.1865 (2.2534)	loss 3.1279 (2.9672)	grad_norm 3.0226 (3.2623)	
[2022-01-26 19:58:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][360/1251]	eta 0:33:23 lr 0.000017	time 2.0496 (2.2486)	loss 3.2832 (2.9716)	grad_norm 3.2215 (3.2599)	
[2022-01-26 19:58:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][370/1251]	eta 0:32:58 lr 0.000017	time 2.1759 (2.2454)	loss 3.2129 (2.9720)	grad_norm 3.2884 (3.2639)	
[2022-01-26 19:58:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][380/1251]	eta 0:32:34 lr 0.000017	time 1.8969 (2.2445)	loss 2.0220 (2.9709)	grad_norm 3.7892 (3.2639)	
[2022-01-26 19:59:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][390/1251]	eta 0:32:10 lr 0.000017	time 2.7394 (2.2425)	loss 2.8230 (2.9747)	grad_norm 3.2510 (3.2679)	
[2022-01-26 19:59:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][400/1251]	eta 0:31:45 lr 0.000017	time 1.9580 (2.2390)	loss 2.1183 (2.9684)	grad_norm 3.3083 (3.2683)	
[2022-01-26 19:59:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][410/1251]	eta 0:31:25 lr 0.000017	time 2.7868 (2.2420)	loss 2.4654 (2.9685)	grad_norm 3.4070 (3.2706)	
[2022-01-26 20:00:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][420/1251]	eta 0:31:05 lr 0.000017	time 2.7684 (2.2448)	loss 3.0650 (2.9681)	grad_norm 3.0321 (3.2665)	
[2022-01-26 20:00:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][430/1251]	eta 0:30:41 lr 0.000017	time 1.7586 (2.2430)	loss 3.6100 (2.9674)	grad_norm 3.3346 (3.2643)	
[2022-01-26 20:01:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][440/1251]	eta 0:30:17 lr 0.000017	time 1.6143 (2.2405)	loss 3.2522 (2.9726)	grad_norm 4.0566 (3.2634)	
[2022-01-26 20:01:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][450/1251]	eta 0:29:51 lr 0.000017	time 2.5013 (2.2372)	loss 3.2302 (2.9716)	grad_norm 3.2362 (3.2581)	
[2022-01-26 20:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][460/1251]	eta 0:29:27 lr 0.000017	time 2.5407 (2.2349)	loss 1.8949 (2.9706)	grad_norm 3.6513 (3.2567)	
[2022-01-26 20:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][470/1251]	eta 0:29:02 lr 0.000017	time 2.0055 (2.2308)	loss 2.4448 (2.9690)	grad_norm 3.4575 (3.2589)	
[2022-01-26 20:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][480/1251]	eta 0:28:39 lr 0.000017	time 2.2301 (2.2303)	loss 3.3054 (2.9729)	grad_norm 2.8973 (3.2564)	
[2022-01-26 20:02:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][490/1251]	eta 0:28:17 lr 0.000017	time 1.9388 (2.2305)	loss 3.3452 (2.9774)	grad_norm 2.3502 (3.2529)	
[2022-01-26 20:03:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][500/1251]	eta 0:27:56 lr 0.000017	time 3.1332 (2.2321)	loss 2.1482 (2.9756)	grad_norm 3.1843 (3.2532)	
[2022-01-26 20:03:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][510/1251]	eta 0:27:31 lr 0.000017	time 1.9822 (2.2291)	loss 2.1822 (2.9784)	grad_norm 3.1101 (3.2518)	
[2022-01-26 20:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][520/1251]	eta 0:27:05 lr 0.000017	time 2.6116 (2.2242)	loss 3.4836 (2.9767)	grad_norm 3.2168 (3.2527)	
[2022-01-26 20:04:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][530/1251]	eta 0:26:43 lr 0.000017	time 2.5343 (2.2238)	loss 3.3862 (2.9796)	grad_norm 3.2546 (3.2521)	
[2022-01-26 20:04:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][540/1251]	eta 0:26:19 lr 0.000017	time 1.8369 (2.2217)	loss 3.2964 (2.9817)	grad_norm 2.9837 (3.2529)	
[2022-01-26 20:05:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][550/1251]	eta 0:25:57 lr 0.000017	time 1.7004 (2.2214)	loss 2.4299 (2.9854)	grad_norm 3.0404 (3.2536)	
[2022-01-26 20:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][560/1251]	eta 0:25:35 lr 0.000017	time 2.3392 (2.2215)	loss 1.9374 (2.9838)	grad_norm 3.3237 (3.2540)	
[2022-01-26 20:05:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][570/1251]	eta 0:25:11 lr 0.000017	time 2.1557 (2.2199)	loss 3.3101 (2.9824)	grad_norm 3.7338 (3.2622)	
[2022-01-26 20:06:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][580/1251]	eta 0:24:49 lr 0.000017	time 1.5770 (2.2200)	loss 2.8311 (2.9820)	grad_norm 2.9228 (3.2625)	
[2022-01-26 20:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][590/1251]	eta 0:24:27 lr 0.000017	time 1.9079 (2.2207)	loss 3.1704 (2.9841)	grad_norm 3.3934 (3.2614)	
[2022-01-26 20:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][600/1251]	eta 0:24:05 lr 0.000017	time 2.1916 (2.2210)	loss 3.4737 (2.9861)	grad_norm 2.5937 (3.2597)	
[2022-01-26 20:07:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][610/1251]	eta 0:23:43 lr 0.000017	time 1.8033 (2.2212)	loss 3.1340 (2.9843)	grad_norm 3.1982 (3.2716)	
[2022-01-26 20:07:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][620/1251]	eta 0:23:20 lr 0.000017	time 1.8619 (2.2187)	loss 2.7907 (2.9819)	grad_norm 3.1105 (3.2689)	
[2022-01-26 20:07:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][630/1251]	eta 0:22:57 lr 0.000017	time 1.7357 (2.2186)	loss 2.1374 (2.9819)	grad_norm 2.9871 (3.2700)	
[2022-01-26 20:08:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][640/1251]	eta 0:22:36 lr 0.000016	time 2.1036 (2.2194)	loss 3.6371 (2.9811)	grad_norm 3.0415 (3.2701)	
[2022-01-26 20:08:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][650/1251]	eta 0:22:12 lr 0.000016	time 1.9416 (2.2178)	loss 2.3096 (2.9807)	grad_norm 4.7448 (3.2695)	
[2022-01-26 20:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][660/1251]	eta 0:21:50 lr 0.000016	time 2.4682 (2.2167)	loss 2.8746 (2.9803)	grad_norm 2.8990 (3.2653)	
[2022-01-26 20:09:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][670/1251]	eta 0:21:27 lr 0.000016	time 1.8681 (2.2166)	loss 3.3398 (2.9822)	grad_norm 3.8323 (3.2639)	
[2022-01-26 20:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][680/1251]	eta 0:21:04 lr 0.000016	time 1.9169 (2.2148)	loss 3.0741 (2.9816)	grad_norm 3.2894 (3.2615)	
[2022-01-26 20:10:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][690/1251]	eta 0:20:41 lr 0.000016	time 1.9413 (2.2139)	loss 2.7585 (2.9840)	grad_norm 2.9017 (3.2591)	
[2022-01-26 20:10:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][700/1251]	eta 0:20:20 lr 0.000016	time 1.8913 (2.2145)	loss 2.9717 (2.9857)	grad_norm 3.0009 (3.2580)	
[2022-01-26 20:10:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][710/1251]	eta 0:19:57 lr 0.000016	time 1.8471 (2.2131)	loss 3.4805 (2.9865)	grad_norm 2.6184 (3.2584)	
[2022-01-26 20:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][720/1251]	eta 0:19:34 lr 0.000016	time 2.2842 (2.2127)	loss 3.9120 (2.9916)	grad_norm 3.6765 (3.2579)	
[2022-01-26 20:11:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][730/1251]	eta 0:19:11 lr 0.000016	time 1.5575 (2.2106)	loss 2.3245 (2.9896)	grad_norm 3.1561 (3.2575)	
[2022-01-26 20:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][740/1251]	eta 0:18:49 lr 0.000016	time 1.8319 (2.2096)	loss 3.4375 (2.9904)	grad_norm 3.2135 (3.2579)	
[2022-01-26 20:12:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][750/1251]	eta 0:18:27 lr 0.000016	time 2.1213 (2.2098)	loss 3.1473 (2.9918)	grad_norm 2.9924 (3.2572)	
[2022-01-26 20:12:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][760/1251]	eta 0:18:05 lr 0.000016	time 2.7125 (2.2105)	loss 3.2027 (2.9891)	grad_norm 2.8662 (3.2547)	
[2022-01-26 20:13:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][770/1251]	eta 0:17:43 lr 0.000016	time 1.8537 (2.2114)	loss 2.8931 (2.9868)	grad_norm 3.2142 (3.2560)	
[2022-01-26 20:13:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][780/1251]	eta 0:17:21 lr 0.000016	time 1.5687 (2.2119)	loss 3.1846 (2.9856)	grad_norm 3.0242 (3.2533)	
[2022-01-26 20:13:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][790/1251]	eta 0:16:58 lr 0.000016	time 1.5560 (2.2104)	loss 2.3104 (2.9832)	grad_norm 2.9805 (3.2516)	
[2022-01-26 20:14:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][800/1251]	eta 0:16:36 lr 0.000016	time 3.0569 (2.2106)	loss 2.2275 (2.9823)	grad_norm 3.2306 (3.2541)	
[2022-01-26 20:14:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][810/1251]	eta 0:16:14 lr 0.000016	time 1.5161 (2.2090)	loss 3.3807 (2.9842)	grad_norm 2.8382 (3.2549)	
[2022-01-26 20:14:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][820/1251]	eta 0:15:52 lr 0.000016	time 2.8304 (2.2098)	loss 2.0349 (2.9844)	grad_norm 3.1503 (3.2545)	
[2022-01-26 20:15:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][830/1251]	eta 0:15:30 lr 0.000016	time 2.0193 (2.2092)	loss 3.6453 (2.9862)	grad_norm 2.9686 (3.2523)	
[2022-01-26 20:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][840/1251]	eta 0:15:08 lr 0.000016	time 3.0613 (2.2108)	loss 2.6269 (2.9868)	grad_norm 3.2068 (3.2499)	
[2022-01-26 20:15:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][850/1251]	eta 0:14:46 lr 0.000016	time 1.8996 (2.2096)	loss 3.1025 (2.9871)	grad_norm 3.1279 (3.2492)	
[2022-01-26 20:16:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][860/1251]	eta 0:14:23 lr 0.000016	time 2.2563 (2.2085)	loss 3.3986 (2.9907)	grad_norm 3.1944 (3.2483)	
[2022-01-26 20:16:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][870/1251]	eta 0:14:01 lr 0.000016	time 2.1843 (2.2074)	loss 2.9478 (2.9904)	grad_norm 3.4377 (3.2476)	
[2022-01-26 20:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][880/1251]	eta 0:13:38 lr 0.000016	time 2.2559 (2.2057)	loss 2.4210 (2.9902)	grad_norm 2.8424 (3.2460)	
[2022-01-26 20:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][890/1251]	eta 0:13:15 lr 0.000016	time 1.6024 (2.2033)	loss 3.1826 (2.9902)	grad_norm 3.3105 (3.2463)	
[2022-01-26 20:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][900/1251]	eta 0:12:52 lr 0.000016	time 1.8978 (2.2012)	loss 3.1268 (2.9892)	grad_norm 2.4934 (3.2443)	
[2022-01-26 20:18:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][910/1251]	eta 0:12:30 lr 0.000016	time 2.2060 (2.2003)	loss 3.2622 (2.9896)	grad_norm 3.5424 (3.2443)	
[2022-01-26 20:18:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][920/1251]	eta 0:12:08 lr 0.000016	time 1.7462 (2.2002)	loss 3.0261 (2.9911)	grad_norm 3.1753 (3.2423)	
[2022-01-26 20:18:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][930/1251]	eta 0:11:46 lr 0.000016	time 2.3293 (2.2017)	loss 2.0449 (2.9922)	grad_norm 3.1779 (3.2526)	
[2022-01-26 20:19:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][940/1251]	eta 0:11:24 lr 0.000016	time 1.8496 (2.2018)	loss 3.3296 (2.9927)	grad_norm 4.0548 (3.2549)	
[2022-01-26 20:19:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][950/1251]	eta 0:11:02 lr 0.000016	time 1.8413 (2.2016)	loss 3.5798 (2.9936)	grad_norm 3.1066 (3.2535)	
[2022-01-26 20:19:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][960/1251]	eta 0:10:40 lr 0.000016	time 1.9487 (2.2016)	loss 2.4424 (2.9928)	grad_norm 2.7552 (3.2550)	
[2022-01-26 20:20:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][970/1251]	eta 0:10:18 lr 0.000016	time 2.1798 (2.2028)	loss 3.1427 (2.9931)	grad_norm 3.0308 (3.2557)	
[2022-01-26 20:20:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][980/1251]	eta 0:09:57 lr 0.000016	time 2.7209 (2.2040)	loss 2.8761 (2.9915)	grad_norm 2.8391 (3.2557)	
[2022-01-26 20:21:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][990/1251]	eta 0:09:35 lr 0.000016	time 2.5937 (2.2051)	loss 2.9759 (2.9918)	grad_norm 3.4375 (3.2562)	
[2022-01-26 20:21:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1000/1251]	eta 0:09:13 lr 0.000016	time 1.8924 (2.2041)	loss 3.4195 (2.9913)	grad_norm 3.0915 (3.2555)	
[2022-01-26 20:21:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1010/1251]	eta 0:08:50 lr 0.000016	time 1.5962 (2.2029)	loss 3.2574 (2.9908)	grad_norm 2.6617 (3.2533)	
[2022-01-26 20:22:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1020/1251]	eta 0:08:28 lr 0.000016	time 2.2818 (2.2025)	loss 3.4259 (2.9920)	grad_norm 3.0843 (3.2516)	
[2022-01-26 20:22:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1030/1251]	eta 0:08:07 lr 0.000016	time 3.7205 (2.2036)	loss 3.5585 (2.9895)	grad_norm 3.2198 (3.2532)	
[2022-01-26 20:22:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1040/1251]	eta 0:07:44 lr 0.000016	time 2.1416 (2.2035)	loss 2.5454 (2.9879)	grad_norm 2.9127 (3.2517)	
[2022-01-26 20:23:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1050/1251]	eta 0:07:22 lr 0.000016	time 1.6647 (2.2036)	loss 2.5747 (2.9884)	grad_norm 3.7874 (3.2517)	
[2022-01-26 20:23:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1060/1251]	eta 0:07:00 lr 0.000016	time 2.2809 (2.2036)	loss 2.3033 (2.9863)	grad_norm 2.9461 (3.2513)	
[2022-01-26 20:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1070/1251]	eta 0:06:38 lr 0.000016	time 2.4455 (2.2040)	loss 2.4624 (2.9861)	grad_norm 2.9997 (3.2487)	
[2022-01-26 20:24:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1080/1251]	eta 0:06:16 lr 0.000016	time 1.8818 (2.2023)	loss 3.4530 (2.9866)	grad_norm 3.7339 (3.2496)	
[2022-01-26 20:24:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1090/1251]	eta 0:05:54 lr 0.000016	time 1.8369 (2.2026)	loss 3.0327 (2.9871)	grad_norm 3.4861 (3.2492)	
[2022-01-26 20:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1100/1251]	eta 0:05:32 lr 0.000016	time 1.9336 (2.2025)	loss 3.3310 (2.9894)	grad_norm 2.7146 (3.2493)	
[2022-01-26 20:25:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1110/1251]	eta 0:05:10 lr 0.000016	time 2.6953 (2.2024)	loss 3.0730 (2.9884)	grad_norm 2.8927 (3.2478)	
[2022-01-26 20:25:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1120/1251]	eta 0:04:48 lr 0.000016	time 2.9787 (2.2023)	loss 2.3968 (2.9890)	grad_norm 3.1345 (3.2480)	
[2022-01-26 20:26:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1130/1251]	eta 0:04:26 lr 0.000016	time 1.5846 (2.2022)	loss 2.6674 (2.9882)	grad_norm 3.2288 (3.2471)	
[2022-01-26 20:26:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1140/1251]	eta 0:04:04 lr 0.000016	time 1.9466 (2.2003)	loss 1.9321 (2.9856)	grad_norm 2.8216 (3.2465)	
[2022-01-26 20:26:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1150/1251]	eta 0:03:42 lr 0.000016	time 2.2472 (2.2005)	loss 3.2515 (2.9844)	grad_norm 3.1433 (3.2461)	
[2022-01-26 20:27:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1160/1251]	eta 0:03:20 lr 0.000016	time 1.6944 (2.1995)	loss 2.8034 (2.9835)	grad_norm 3.0157 (3.2460)	
[2022-01-26 20:27:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1170/1251]	eta 0:02:58 lr 0.000016	time 2.5511 (2.2000)	loss 2.9031 (2.9831)	grad_norm 3.1694 (3.2448)	
[2022-01-26 20:27:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1180/1251]	eta 0:02:36 lr 0.000016	time 2.2495 (2.2001)	loss 2.8393 (2.9828)	grad_norm 3.1046 (3.2448)	
[2022-01-26 20:28:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1190/1251]	eta 0:02:14 lr 0.000016	time 1.6567 (2.2004)	loss 2.7731 (2.9844)	grad_norm 3.7067 (3.2449)	
[2022-01-26 20:28:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1200/1251]	eta 0:01:52 lr 0.000016	time 1.9119 (2.2007)	loss 3.2139 (2.9838)	grad_norm 2.8328 (3.2429)	
[2022-01-26 20:29:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1210/1251]	eta 0:01:30 lr 0.000016	time 2.4462 (2.2003)	loss 3.2629 (2.9828)	grad_norm 2.7386 (3.2409)	
[2022-01-26 20:29:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1220/1251]	eta 0:01:08 lr 0.000016	time 2.4670 (2.1991)	loss 2.8490 (2.9835)	grad_norm 3.9804 (3.2418)	
[2022-01-26 20:29:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1230/1251]	eta 0:00:46 lr 0.000016	time 2.0143 (2.1995)	loss 2.6757 (2.9823)	grad_norm 3.3518 (3.2398)	
[2022-01-26 20:30:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1240/1251]	eta 0:00:24 lr 0.000016	time 1.7512 (2.1988)	loss 3.1944 (2.9809)	grad_norm 2.9472 (3.2412)	
[2022-01-26 20:30:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [284/300][1250/1251]	eta 0:00:02 lr 0.000016	time 1.1766 (2.1928)	loss 3.3686 (2.9799)	grad_norm 3.4767 (3.2410)	
[2022-01-26 20:30:20 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 284 training takes 0:45:43
[2022-01-26 20:30:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.392 (18.392)	Loss 0.8142 (0.8142)	Acc@1 80.273 (80.273)	Acc@5 95.801 (95.801)	
[2022-01-26 20:30:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.265 (3.280)	Loss 0.8877 (0.8193)	Acc@1 79.980 (80.975)	Acc@5 93.848 (95.348)	
[2022-01-26 20:31:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.614 (2.506)	Loss 0.8383 (0.8168)	Acc@1 79.004 (80.957)	Acc@5 95.801 (95.415)	
[2022-01-26 20:31:28 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.889 (2.186)	Loss 0.7528 (0.8112)	Acc@1 82.715 (81.039)	Acc@5 95.996 (95.407)	
[2022-01-26 20:31:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.763 (2.120)	Loss 0.8228 (0.8114)	Acc@1 80.176 (81.033)	Acc@5 95.312 (95.398)	
[2022-01-26 20:31:54 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.106 Acc@5 95.444
[2022-01-26 20:31:54 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.1%
[2022-01-26 20:31:54 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.12%
[2022-01-26 20:32:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][0/1251]	eta 7:28:08 lr 0.000016	time 21.4934 (21.4934)	loss 3.1062 (3.1062)	grad_norm 3.3720 (3.3720)	
[2022-01-26 20:32:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][10/1251]	eta 1:22:44 lr 0.000016	time 2.5470 (4.0000)	loss 3.3531 (2.9951)	grad_norm 2.9546 (3.0227)	
[2022-01-26 20:33:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][20/1251]	eta 1:04:07 lr 0.000016	time 2.1773 (3.1253)	loss 3.0714 (2.9377)	grad_norm 3.3835 (3.0853)	
[2022-01-26 20:33:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][30/1251]	eta 0:57:14 lr 0.000016	time 1.6105 (2.8131)	loss 3.4863 (3.0110)	grad_norm 3.2951 (3.1262)	
[2022-01-26 20:33:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][40/1251]	eta 0:55:06 lr 0.000016	time 3.6420 (2.7308)	loss 2.9621 (3.0444)	grad_norm 2.8505 (3.2098)	
[2022-01-26 20:34:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][50/1251]	eta 0:53:05 lr 0.000016	time 3.3731 (2.6523)	loss 2.8600 (3.0282)	grad_norm 2.5225 (3.1792)	
[2022-01-26 20:34:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][60/1251]	eta 0:50:42 lr 0.000016	time 2.4637 (2.5547)	loss 3.0395 (3.0156)	grad_norm 2.6656 (3.1726)	
[2022-01-26 20:34:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][70/1251]	eta 0:48:54 lr 0.000016	time 1.6759 (2.4845)	loss 2.2561 (3.0027)	grad_norm 2.8219 (3.1527)	
[2022-01-26 20:35:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][80/1251]	eta 0:47:32 lr 0.000016	time 2.6799 (2.4363)	loss 2.7231 (2.9913)	grad_norm 3.0848 (3.1618)	
[2022-01-26 20:35:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][90/1251]	eta 0:46:44 lr 0.000016	time 2.3739 (2.4160)	loss 3.4875 (2.9767)	grad_norm 2.8698 (3.1797)	
[2022-01-26 20:35:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][100/1251]	eta 0:46:05 lr 0.000016	time 2.7551 (2.4024)	loss 3.2759 (2.9863)	grad_norm 3.0075 (3.1671)	
[2022-01-26 20:36:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][110/1251]	eta 0:45:10 lr 0.000016	time 2.2075 (2.3752)	loss 3.3665 (3.0015)	grad_norm 2.7274 (3.1870)	
[2022-01-26 20:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][120/1251]	eta 0:44:29 lr 0.000016	time 2.5757 (2.3606)	loss 3.5563 (3.0015)	grad_norm 4.5432 (3.1893)	
[2022-01-26 20:37:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][130/1251]	eta 0:43:49 lr 0.000016	time 2.8416 (2.3453)	loss 3.2284 (3.0096)	grad_norm 3.4118 (3.1976)	
[2022-01-26 20:37:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][140/1251]	eta 0:43:15 lr 0.000016	time 2.6081 (2.3358)	loss 3.6312 (3.0040)	grad_norm 3.6049 (3.1999)	
[2022-01-26 20:37:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][150/1251]	eta 0:42:44 lr 0.000016	time 1.8948 (2.3293)	loss 3.3246 (2.9869)	grad_norm 3.3079 (3.2174)	
[2022-01-26 20:38:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][160/1251]	eta 0:42:24 lr 0.000016	time 2.5059 (2.3319)	loss 2.1944 (2.9910)	grad_norm 3.0746 (3.2138)	
[2022-01-26 20:38:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][170/1251]	eta 0:41:49 lr 0.000016	time 1.8655 (2.3217)	loss 3.1101 (3.0004)	grad_norm 2.9318 (3.2168)	
[2022-01-26 20:38:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][180/1251]	eta 0:41:15 lr 0.000016	time 2.5430 (2.3118)	loss 2.6495 (2.9748)	grad_norm 3.1048 (3.2141)	
[2022-01-26 20:39:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][190/1251]	eta 0:40:38 lr 0.000016	time 1.9516 (2.2980)	loss 2.2380 (2.9712)	grad_norm 3.2192 (3.2097)	
[2022-01-26 20:39:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][200/1251]	eta 0:40:06 lr 0.000016	time 2.1818 (2.2900)	loss 2.6725 (2.9578)	grad_norm 3.3221 (3.2059)	
[2022-01-26 20:39:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][210/1251]	eta 0:39:35 lr 0.000016	time 2.1702 (2.2824)	loss 2.8561 (2.9600)	grad_norm 5.6259 (3.2154)	
[2022-01-26 20:40:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][220/1251]	eta 0:39:05 lr 0.000016	time 2.4882 (2.2749)	loss 2.5025 (2.9523)	grad_norm 2.8381 (3.2050)	
[2022-01-26 20:40:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][230/1251]	eta 0:38:47 lr 0.000016	time 2.4701 (2.2800)	loss 2.7971 (2.9635)	grad_norm 3.7990 (3.1969)	
[2022-01-26 20:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][240/1251]	eta 0:38:28 lr 0.000016	time 2.8044 (2.2838)	loss 2.9959 (2.9691)	grad_norm 2.9157 (3.2085)	
[2022-01-26 20:41:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][250/1251]	eta 0:38:00 lr 0.000016	time 1.8823 (2.2784)	loss 2.4254 (2.9567)	grad_norm 3.4685 (3.2198)	
[2022-01-26 20:41:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][260/1251]	eta 0:37:34 lr 0.000016	time 2.7470 (2.2747)	loss 2.8268 (2.9594)	grad_norm 3.5993 (3.2291)	
[2022-01-26 20:42:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][270/1251]	eta 0:37:03 lr 0.000016	time 1.8988 (2.2669)	loss 3.3007 (2.9591)	grad_norm 3.0460 (3.2328)	
[2022-01-26 20:42:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][280/1251]	eta 0:36:35 lr 0.000016	time 1.8532 (2.2609)	loss 2.3451 (2.9635)	grad_norm 3.1192 (3.2354)	
[2022-01-26 20:42:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][290/1251]	eta 0:36:10 lr 0.000016	time 2.2812 (2.2588)	loss 2.4798 (2.9526)	grad_norm 4.1200 (3.2439)	
[2022-01-26 20:43:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][300/1251]	eta 0:35:43 lr 0.000016	time 1.7746 (2.2541)	loss 2.2458 (2.9528)	grad_norm 2.9534 (3.2425)	
[2022-01-26 20:43:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][310/1251]	eta 0:35:21 lr 0.000016	time 1.9412 (2.2541)	loss 3.2144 (2.9511)	grad_norm 3.6111 (3.2436)	
[2022-01-26 20:43:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][320/1251]	eta 0:34:56 lr 0.000016	time 1.8499 (2.2523)	loss 1.9503 (2.9565)	grad_norm 2.8596 (3.2416)	
[2022-01-26 20:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][330/1251]	eta 0:34:30 lr 0.000016	time 2.5569 (2.2480)	loss 3.7722 (2.9624)	grad_norm 3.4503 (3.2447)	
[2022-01-26 20:44:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][340/1251]	eta 0:34:05 lr 0.000016	time 2.1506 (2.2458)	loss 3.5563 (2.9693)	grad_norm 3.1966 (3.2395)	
[2022-01-26 20:45:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][350/1251]	eta 0:33:43 lr 0.000016	time 2.8211 (2.2460)	loss 3.0681 (2.9779)	grad_norm 3.2237 (3.2363)	
[2022-01-26 20:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][360/1251]	eta 0:33:20 lr 0.000016	time 2.1775 (2.2447)	loss 3.4714 (2.9798)	grad_norm 3.3250 (3.2382)	
[2022-01-26 20:45:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][370/1251]	eta 0:32:57 lr 0.000016	time 1.8930 (2.2449)	loss 3.5135 (2.9819)	grad_norm 3.5792 (3.2408)	
[2022-01-26 20:46:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][380/1251]	eta 0:32:32 lr 0.000016	time 2.0928 (2.2412)	loss 3.1051 (2.9882)	grad_norm 3.3760 (3.2354)	
[2022-01-26 20:46:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][390/1251]	eta 0:32:05 lr 0.000016	time 2.3008 (2.2363)	loss 2.2907 (2.9888)	grad_norm 3.3567 (3.2431)	
[2022-01-26 20:46:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][400/1251]	eta 0:31:40 lr 0.000016	time 1.8900 (2.2327)	loss 2.8890 (2.9836)	grad_norm 3.2346 (3.2367)	
[2022-01-26 20:47:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][410/1251]	eta 0:31:16 lr 0.000016	time 2.4743 (2.2316)	loss 2.6128 (2.9752)	grad_norm 2.8485 (3.2343)	
[2022-01-26 20:47:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][420/1251]	eta 0:30:49 lr 0.000016	time 1.8981 (2.2259)	loss 2.9945 (2.9786)	grad_norm 3.8419 (3.2367)	
[2022-01-26 20:47:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][430/1251]	eta 0:30:25 lr 0.000016	time 1.8907 (2.2239)	loss 2.0629 (2.9751)	grad_norm 3.4898 (3.2409)	
[2022-01-26 20:48:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][440/1251]	eta 0:30:02 lr 0.000016	time 2.8298 (2.2226)	loss 1.9646 (2.9705)	grad_norm 3.6146 (3.2418)	
[2022-01-26 20:48:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][450/1251]	eta 0:29:42 lr 0.000016	time 2.8099 (2.2255)	loss 3.2996 (2.9754)	grad_norm 3.1467 (3.2426)	
[2022-01-26 20:49:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][460/1251]	eta 0:29:20 lr 0.000016	time 2.3287 (2.2251)	loss 2.9369 (2.9719)	grad_norm 2.9622 (3.2429)	
[2022-01-26 20:49:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][470/1251]	eta 0:28:58 lr 0.000016	time 1.5057 (2.2259)	loss 3.6645 (2.9709)	grad_norm 3.2493 (3.2419)	
[2022-01-26 20:49:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][480/1251]	eta 0:28:36 lr 0.000016	time 2.2937 (2.2258)	loss 2.7873 (2.9699)	grad_norm 3.5574 (3.2402)	
[2022-01-26 20:50:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][490/1251]	eta 0:28:17 lr 0.000016	time 3.3519 (2.2306)	loss 3.2041 (2.9703)	grad_norm 3.5645 (3.2380)	
[2022-01-26 20:50:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][500/1251]	eta 0:27:55 lr 0.000016	time 2.8085 (2.2305)	loss 2.4928 (2.9719)	grad_norm 2.5339 (3.2360)	
[2022-01-26 20:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][510/1251]	eta 0:27:31 lr 0.000016	time 1.8894 (2.2282)	loss 2.9495 (2.9743)	grad_norm 3.4506 (3.2361)	
[2022-01-26 20:51:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][520/1251]	eta 0:27:08 lr 0.000016	time 2.3812 (2.2275)	loss 2.9238 (2.9717)	grad_norm 3.4782 (3.2394)	
[2022-01-26 20:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][530/1251]	eta 0:26:44 lr 0.000016	time 2.5034 (2.2257)	loss 3.5096 (2.9765)	grad_norm 3.3059 (3.2389)	
[2022-01-26 20:51:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][540/1251]	eta 0:26:21 lr 0.000016	time 2.4872 (2.2240)	loss 3.2280 (2.9792)	grad_norm 3.5536 (3.2407)	
[2022-01-26 20:52:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][550/1251]	eta 0:25:57 lr 0.000016	time 1.9316 (2.2224)	loss 3.3337 (2.9824)	grad_norm 3.2037 (3.2415)	
[2022-01-26 20:52:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][560/1251]	eta 0:25:35 lr 0.000016	time 1.9395 (2.2222)	loss 3.2581 (2.9860)	grad_norm 2.8525 (3.2383)	
[2022-01-26 20:53:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][570/1251]	eta 0:25:12 lr 0.000016	time 2.8278 (2.2208)	loss 2.3458 (2.9866)	grad_norm 3.6197 (3.2362)	
[2022-01-26 20:53:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][580/1251]	eta 0:24:50 lr 0.000016	time 2.0520 (2.2209)	loss 2.2368 (2.9838)	grad_norm 2.9227 (3.2343)	
[2022-01-26 20:53:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][590/1251]	eta 0:24:28 lr 0.000016	time 2.3806 (2.2219)	loss 2.6349 (2.9784)	grad_norm 4.8665 (3.2399)	
[2022-01-26 20:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][600/1251]	eta 0:24:06 lr 0.000016	time 1.7790 (2.2222)	loss 3.3068 (2.9794)	grad_norm 3.6840 (3.2409)	
[2022-01-26 20:54:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][610/1251]	eta 0:23:45 lr 0.000016	time 3.1118 (2.2244)	loss 2.6769 (2.9771)	grad_norm 3.0192 (3.2376)	
[2022-01-26 20:54:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][620/1251]	eta 0:23:21 lr 0.000016	time 1.9987 (2.2208)	loss 3.5150 (2.9782)	grad_norm 2.7792 (3.2325)	
[2022-01-26 20:55:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][630/1251]	eta 0:22:56 lr 0.000016	time 2.1668 (2.2173)	loss 3.5339 (2.9777)	grad_norm 2.9377 (3.2315)	
[2022-01-26 20:55:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][640/1251]	eta 0:22:33 lr 0.000016	time 1.8736 (2.2158)	loss 3.4121 (2.9771)	grad_norm 3.0840 (3.2295)	
[2022-01-26 20:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][650/1251]	eta 0:22:11 lr 0.000016	time 2.2604 (2.2155)	loss 3.2293 (2.9747)	grad_norm 3.4249 (3.2284)	
[2022-01-26 20:56:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][660/1251]	eta 0:21:49 lr 0.000016	time 2.2634 (2.2162)	loss 3.0510 (2.9725)	grad_norm 3.3441 (3.2258)	
[2022-01-26 20:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][670/1251]	eta 0:21:27 lr 0.000016	time 2.5005 (2.2164)	loss 2.5212 (2.9739)	grad_norm 3.3254 (3.2240)	
[2022-01-26 20:57:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][680/1251]	eta 0:21:04 lr 0.000016	time 1.5768 (2.2138)	loss 2.4860 (2.9742)	grad_norm 3.7231 (3.2262)	
[2022-01-26 20:57:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][690/1251]	eta 0:20:41 lr 0.000016	time 2.2366 (2.2132)	loss 2.9879 (2.9726)	grad_norm 3.0050 (3.2226)	
[2022-01-26 20:57:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][700/1251]	eta 0:20:19 lr 0.000016	time 2.4708 (2.2131)	loss 3.5031 (2.9742)	grad_norm 3.1451 (3.2228)	
[2022-01-26 20:58:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][710/1251]	eta 0:19:59 lr 0.000016	time 3.8230 (2.2173)	loss 3.6110 (2.9772)	grad_norm 4.5428 (3.2246)	
[2022-01-26 20:58:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][720/1251]	eta 0:19:37 lr 0.000016	time 1.6267 (2.2173)	loss 2.3325 (2.9765)	grad_norm 3.1239 (3.2247)	
[2022-01-26 20:58:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][730/1251]	eta 0:19:14 lr 0.000016	time 2.2564 (2.2168)	loss 3.3205 (2.9775)	grad_norm 3.2246 (3.2257)	
[2022-01-26 20:59:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][740/1251]	eta 0:18:51 lr 0.000016	time 1.7694 (2.2144)	loss 3.4074 (2.9779)	grad_norm 3.2641 (3.2307)	
[2022-01-26 20:59:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][750/1251]	eta 0:18:27 lr 0.000016	time 1.8628 (2.2112)	loss 3.1768 (2.9809)	grad_norm 3.2429 (3.2294)	
[2022-01-26 20:59:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][760/1251]	eta 0:18:05 lr 0.000016	time 2.1448 (2.2104)	loss 2.8950 (2.9804)	grad_norm 2.8724 (3.2334)	
[2022-01-26 21:00:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][770/1251]	eta 0:17:43 lr 0.000016	time 2.5984 (2.2100)	loss 3.7645 (2.9831)	grad_norm 3.0313 (3.2321)	
[2022-01-26 21:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][780/1251]	eta 0:17:20 lr 0.000016	time 1.7692 (2.2095)	loss 3.2061 (2.9859)	grad_norm 3.1590 (3.2371)	
[2022-01-26 21:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][790/1251]	eta 0:16:58 lr 0.000016	time 3.0974 (2.2097)	loss 2.3607 (2.9855)	grad_norm 3.1389 (3.2352)	
[2022-01-26 21:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][800/1251]	eta 0:16:38 lr 0.000016	time 2.4402 (2.2129)	loss 3.4405 (2.9877)	grad_norm 2.9734 (3.2362)	
[2022-01-26 21:01:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][810/1251]	eta 0:16:16 lr 0.000016	time 2.5500 (2.2145)	loss 2.6738 (2.9862)	grad_norm 2.7226 (3.2335)	
[2022-01-26 21:02:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][820/1251]	eta 0:15:53 lr 0.000016	time 1.8311 (2.2133)	loss 2.7504 (2.9891)	grad_norm 3.5546 (3.2346)	
[2022-01-26 21:02:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][830/1251]	eta 0:15:30 lr 0.000016	time 1.9274 (2.2102)	loss 2.1678 (2.9889)	grad_norm 3.0999 (3.2342)	
[2022-01-26 21:02:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][840/1251]	eta 0:15:08 lr 0.000016	time 2.2098 (2.2106)	loss 2.4795 (2.9849)	grad_norm 2.9444 (3.2330)	
[2022-01-26 21:03:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][850/1251]	eta 0:14:46 lr 0.000016	time 2.2012 (2.2102)	loss 3.4694 (2.9853)	grad_norm 3.1501 (3.2363)	
[2022-01-26 21:03:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][860/1251]	eta 0:14:23 lr 0.000016	time 1.7958 (2.2088)	loss 3.4945 (2.9853)	grad_norm 3.1117 (3.2355)	
[2022-01-26 21:03:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][870/1251]	eta 0:14:01 lr 0.000016	time 1.9684 (2.2082)	loss 2.2871 (2.9848)	grad_norm 3.6141 (3.2346)	
[2022-01-26 21:04:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][880/1251]	eta 0:13:39 lr 0.000016	time 1.7581 (2.2094)	loss 2.6901 (2.9851)	grad_norm 4.0443 (3.2341)	
[2022-01-26 21:04:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][890/1251]	eta 0:13:17 lr 0.000016	time 2.1090 (2.2089)	loss 2.3659 (2.9830)	grad_norm 2.9597 (3.2314)	
[2022-01-26 21:05:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][900/1251]	eta 0:12:55 lr 0.000016	time 2.4355 (2.2082)	loss 3.2581 (2.9828)	grad_norm 2.9232 (3.2293)	
[2022-01-26 21:05:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][910/1251]	eta 0:12:32 lr 0.000016	time 1.9452 (2.2075)	loss 3.3780 (2.9844)	grad_norm 3.0832 (3.2280)	
[2022-01-26 21:05:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][920/1251]	eta 0:12:09 lr 0.000016	time 1.9819 (2.2051)	loss 2.9871 (2.9860)	grad_norm 3.0138 (3.2277)	
[2022-01-26 21:06:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][930/1251]	eta 0:11:47 lr 0.000016	time 1.9117 (2.2031)	loss 1.9976 (2.9865)	grad_norm 3.7275 (3.2273)	
[2022-01-26 21:06:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][940/1251]	eta 0:11:24 lr 0.000016	time 1.8923 (2.2025)	loss 2.2445 (2.9877)	grad_norm 3.4202 (3.2263)	
[2022-01-26 21:06:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][950/1251]	eta 0:11:03 lr 0.000015	time 3.1953 (2.2044)	loss 2.0613 (2.9857)	grad_norm 2.9874 (3.2259)	
[2022-01-26 21:07:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][960/1251]	eta 0:10:41 lr 0.000015	time 1.7320 (2.2059)	loss 2.4177 (2.9845)	grad_norm 3.4519 (3.2273)	
[2022-01-26 21:07:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][970/1251]	eta 0:10:20 lr 0.000015	time 2.7799 (2.2087)	loss 3.0215 (2.9852)	grad_norm 3.1485 (3.2256)	
[2022-01-26 21:08:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][980/1251]	eta 0:09:58 lr 0.000015	time 2.5305 (2.2099)	loss 2.9271 (2.9861)	grad_norm 3.0704 (3.2244)	
[2022-01-26 21:08:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][990/1251]	eta 0:09:37 lr 0.000015	time 2.1221 (2.2111)	loss 3.6492 (2.9898)	grad_norm 4.0152 (3.2261)	
[2022-01-26 21:08:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1000/1251]	eta 0:09:14 lr 0.000015	time 1.9974 (2.2107)	loss 2.5575 (2.9893)	grad_norm 3.3955 (3.2267)	
[2022-01-26 21:09:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1010/1251]	eta 0:08:52 lr 0.000015	time 1.6671 (2.2078)	loss 2.2579 (2.9878)	grad_norm 3.1195 (3.2282)	
[2022-01-26 21:09:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1020/1251]	eta 0:08:29 lr 0.000015	time 1.6278 (2.2048)	loss 2.8828 (2.9877)	grad_norm 2.8322 (3.2278)	
[2022-01-26 21:09:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1030/1251]	eta 0:08:07 lr 0.000015	time 2.2877 (2.2045)	loss 3.6042 (2.9880)	grad_norm 3.2190 (3.2256)	
[2022-01-26 21:10:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1040/1251]	eta 0:07:44 lr 0.000015	time 1.5618 (2.2037)	loss 3.0809 (2.9880)	grad_norm 4.4176 (3.2253)	
[2022-01-26 21:10:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1050/1251]	eta 0:07:23 lr 0.000015	time 2.4187 (2.2056)	loss 2.7002 (2.9887)	grad_norm 3.3629 (3.2234)	
[2022-01-26 21:10:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1060/1251]	eta 0:07:01 lr 0.000015	time 2.0662 (2.2069)	loss 3.6547 (2.9887)	grad_norm 3.4369 (3.2236)	
[2022-01-26 21:11:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1070/1251]	eta 0:06:39 lr 0.000015	time 2.0484 (2.2056)	loss 2.9012 (2.9906)	grad_norm 3.4863 (3.2232)	
[2022-01-26 21:11:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1080/1251]	eta 0:06:17 lr 0.000015	time 2.8481 (2.2052)	loss 2.0607 (2.9907)	grad_norm 5.6787 (3.2257)	
[2022-01-26 21:11:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1090/1251]	eta 0:05:54 lr 0.000015	time 1.9457 (2.2044)	loss 3.1328 (2.9908)	grad_norm 3.0540 (3.2244)	
[2022-01-26 21:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1100/1251]	eta 0:05:32 lr 0.000015	time 2.0902 (2.2044)	loss 2.1667 (2.9906)	grad_norm 3.0857 (3.2230)	
[2022-01-26 21:12:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1110/1251]	eta 0:05:11 lr 0.000015	time 2.0519 (2.2058)	loss 3.0598 (2.9902)	grad_norm 3.0144 (3.2221)	
[2022-01-26 21:13:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1120/1251]	eta 0:04:49 lr 0.000015	time 2.8113 (2.2076)	loss 2.4855 (2.9873)	grad_norm 2.9141 (3.2203)	
[2022-01-26 21:13:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1130/1251]	eta 0:04:27 lr 0.000015	time 1.8283 (2.2070)	loss 3.3207 (2.9866)	grad_norm 3.5005 (3.2207)	
[2022-01-26 21:13:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1140/1251]	eta 0:04:04 lr 0.000015	time 1.6771 (2.2062)	loss 2.9315 (2.9858)	grad_norm 3.2191 (3.2190)	
[2022-01-26 21:14:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1150/1251]	eta 0:03:42 lr 0.000015	time 1.9476 (2.2048)	loss 2.9516 (2.9844)	grad_norm 3.1377 (3.2190)	
[2022-01-26 21:14:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1160/1251]	eta 0:03:20 lr 0.000015	time 2.7444 (2.2042)	loss 3.2611 (2.9856)	grad_norm 4.0544 (3.2224)	
[2022-01-26 21:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1170/1251]	eta 0:02:58 lr 0.000015	time 2.4560 (2.2048)	loss 3.5232 (2.9868)	grad_norm 3.0336 (3.2237)	
[2022-01-26 21:15:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1180/1251]	eta 0:02:36 lr 0.000015	time 1.9246 (2.2052)	loss 3.5511 (2.9883)	grad_norm 3.3260 (3.2249)	
[2022-01-26 21:15:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1190/1251]	eta 0:02:14 lr 0.000015	time 1.9288 (2.2039)	loss 2.7530 (2.9881)	grad_norm 3.8364 (3.2269)	
[2022-01-26 21:16:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1200/1251]	eta 0:01:52 lr 0.000015	time 2.4596 (2.2033)	loss 3.1589 (2.9864)	grad_norm 2.9803 (3.2259)	
[2022-01-26 21:16:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1210/1251]	eta 0:01:30 lr 0.000015	time 2.5681 (2.2026)	loss 2.8909 (2.9895)	grad_norm 3.7777 (3.2263)	
[2022-01-26 21:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1220/1251]	eta 0:01:08 lr 0.000015	time 1.8402 (2.2017)	loss 1.9670 (2.9887)	grad_norm 2.9491 (3.2256)	
[2022-01-26 21:17:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1230/1251]	eta 0:00:46 lr 0.000015	time 2.5287 (2.2012)	loss 2.7284 (2.9877)	grad_norm 2.9421 (3.2265)	
[2022-01-26 21:17:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1240/1251]	eta 0:00:24 lr 0.000015	time 1.2613 (2.2005)	loss 2.3668 (2.9859)	grad_norm 2.8227 (3.2253)	
[2022-01-26 21:17:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [285/300][1250/1251]	eta 0:00:02 lr 0.000015	time 1.2141 (2.1948)	loss 2.7006 (2.9877)	grad_norm 2.9449 (3.2244)	
[2022-01-26 21:17:40 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 285 training takes 0:45:46
[2022-01-26 21:17:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.729 (18.729)	Loss 0.8272 (0.8272)	Acc@1 79.980 (79.980)	Acc@5 95.508 (95.508)	
[2022-01-26 21:18:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.826 (3.371)	Loss 0.8258 (0.8092)	Acc@1 80.664 (81.072)	Acc@5 96.680 (95.552)	
[2022-01-26 21:18:35 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.599 (2.622)	Loss 0.6996 (0.8004)	Acc@1 83.496 (81.097)	Acc@5 96.191 (95.433)	
[2022-01-26 21:18:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.240 (2.394)	Loss 0.8144 (0.8029)	Acc@1 81.055 (81.165)	Acc@5 95.801 (95.426)	
[2022-01-26 21:19:12 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.313 (2.234)	Loss 0.8610 (0.8062)	Acc@1 79.980 (81.083)	Acc@5 95.605 (95.413)	
[2022-01-26 21:19:19 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.060 Acc@5 95.458
[2022-01-26 21:19:19 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.1%
[2022-01-26 21:19:19 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.12%
[2022-01-26 21:19:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][0/1251]	eta 7:34:32 lr 0.000015	time 21.8004 (21.8004)	loss 3.4645 (3.4645)	grad_norm 3.4415 (3.4415)	
[2022-01-26 21:20:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][10/1251]	eta 1:24:05 lr 0.000015	time 3.0235 (4.0660)	loss 1.9425 (2.9017)	grad_norm 3.0221 (3.0876)	
[2022-01-26 21:20:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][20/1251]	eta 1:03:11 lr 0.000015	time 1.7819 (3.0803)	loss 3.3008 (3.0435)	grad_norm 3.1654 (3.1630)	
[2022-01-26 21:20:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][30/1251]	eta 0:56:48 lr 0.000015	time 1.3951 (2.7916)	loss 2.5429 (3.0222)	grad_norm 3.5198 (3.1752)	
[2022-01-26 21:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][40/1251]	eta 0:54:28 lr 0.000015	time 4.0905 (2.6993)	loss 2.1162 (2.9781)	grad_norm 2.7946 (3.1936)	
[2022-01-26 21:21:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][50/1251]	eta 0:52:24 lr 0.000015	time 2.1075 (2.6178)	loss 2.8661 (3.0022)	grad_norm 2.8661 (3.1853)	
[2022-01-26 21:21:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][60/1251]	eta 0:50:12 lr 0.000015	time 1.3847 (2.5293)	loss 2.6120 (2.9947)	grad_norm 3.3797 (3.1981)	
[2022-01-26 21:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][70/1251]	eta 0:48:41 lr 0.000015	time 1.4032 (2.4737)	loss 1.9841 (2.9956)	grad_norm 2.9631 (3.2153)	
[2022-01-26 21:22:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][80/1251]	eta 0:48:03 lr 0.000015	time 4.2113 (2.4627)	loss 3.3175 (2.9931)	grad_norm 3.0635 (3.2173)	
[2022-01-26 21:23:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][90/1251]	eta 0:47:21 lr 0.000015	time 3.2798 (2.4477)	loss 3.5284 (3.0255)	grad_norm 3.0103 (3.2244)	
[2022-01-26 21:23:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][100/1251]	eta 0:45:58 lr 0.000015	time 1.8835 (2.3965)	loss 2.1374 (3.0136)	grad_norm 2.6410 (3.1972)	
[2022-01-26 21:23:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][110/1251]	eta 0:45:08 lr 0.000015	time 1.7436 (2.3737)	loss 3.1020 (2.9947)	grad_norm 2.6314 (3.1972)	
[2022-01-26 21:24:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][120/1251]	eta 0:44:53 lr 0.000015	time 3.9544 (2.3816)	loss 1.9569 (2.9936)	grad_norm 6.0314 (3.2183)	
[2022-01-26 21:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][130/1251]	eta 0:44:16 lr 0.000015	time 1.4916 (2.3697)	loss 3.6165 (3.0038)	grad_norm 3.1899 (3.2091)	
[2022-01-26 21:24:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][140/1251]	eta 0:43:28 lr 0.000015	time 1.9396 (2.3477)	loss 3.0567 (3.0111)	grad_norm 3.2154 (3.2110)	
[2022-01-26 21:25:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][150/1251]	eta 0:42:42 lr 0.000015	time 2.0797 (2.3276)	loss 3.1823 (3.0128)	grad_norm 2.9401 (3.2092)	
[2022-01-26 21:25:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][160/1251]	eta 0:42:08 lr 0.000015	time 3.1998 (2.3174)	loss 2.6087 (2.9987)	grad_norm 2.9712 (3.2050)	
[2022-01-26 21:25:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][170/1251]	eta 0:41:29 lr 0.000015	time 1.5174 (2.3029)	loss 3.4021 (2.9972)	grad_norm 3.0554 (3.1996)	
[2022-01-26 21:26:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][180/1251]	eta 0:41:06 lr 0.000015	time 1.7579 (2.3034)	loss 2.2358 (2.9962)	grad_norm 2.8854 (3.2067)	
[2022-01-26 21:26:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][190/1251]	eta 0:40:39 lr 0.000015	time 2.2264 (2.2993)	loss 3.3732 (3.0084)	grad_norm 3.6114 (3.2073)	
[2022-01-26 21:27:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][200/1251]	eta 0:40:16 lr 0.000015	time 2.5568 (2.2994)	loss 3.6031 (3.0110)	grad_norm 3.5270 (3.2072)	
[2022-01-26 21:27:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][210/1251]	eta 0:39:47 lr 0.000015	time 1.8853 (2.2939)	loss 3.2710 (3.0064)	grad_norm 2.5727 (3.2025)	
[2022-01-26 21:27:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][220/1251]	eta 0:39:25 lr 0.000015	time 1.5805 (2.2940)	loss 3.2782 (3.0114)	grad_norm 3.4922 (3.2082)	
[2022-01-26 21:28:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][230/1251]	eta 0:38:57 lr 0.000015	time 2.6145 (2.2894)	loss 3.1702 (3.0127)	grad_norm 3.6137 (3.2128)	
[2022-01-26 21:28:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][240/1251]	eta 0:38:27 lr 0.000015	time 1.8559 (2.2826)	loss 2.9951 (3.0122)	grad_norm 3.0060 (3.2081)	
[2022-01-26 21:28:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][250/1251]	eta 0:37:59 lr 0.000015	time 1.9555 (2.2775)	loss 3.4961 (3.0144)	grad_norm 2.9342 (3.2107)	
[2022-01-26 21:29:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][260/1251]	eta 0:37:35 lr 0.000015	time 1.8715 (2.2759)	loss 2.4933 (3.0128)	grad_norm 3.0102 (3.2105)	
[2022-01-26 21:29:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][270/1251]	eta 0:37:08 lr 0.000015	time 2.1308 (2.2713)	loss 2.8990 (3.0115)	grad_norm 2.6160 (3.2096)	
[2022-01-26 21:29:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][280/1251]	eta 0:36:42 lr 0.000015	time 1.8663 (2.2680)	loss 2.6359 (3.0086)	grad_norm 3.2134 (3.2019)	
[2022-01-26 21:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][290/1251]	eta 0:36:18 lr 0.000015	time 2.1409 (2.2667)	loss 2.3906 (3.0064)	grad_norm 2.6728 (3.1982)	
[2022-01-26 21:30:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][300/1251]	eta 0:35:47 lr 0.000015	time 1.6680 (2.2583)	loss 3.4816 (3.0113)	grad_norm 3.1137 (3.1966)	
[2022-01-26 21:30:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][310/1251]	eta 0:35:20 lr 0.000015	time 1.8289 (2.2531)	loss 3.1044 (3.0118)	grad_norm 2.9771 (3.1932)	
[2022-01-26 21:31:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][320/1251]	eta 0:35:01 lr 0.000015	time 2.6748 (2.2572)	loss 2.0596 (3.0067)	grad_norm 2.7164 (3.1869)	
[2022-01-26 21:31:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][330/1251]	eta 0:34:42 lr 0.000015	time 3.3682 (2.2617)	loss 2.9873 (3.0076)	grad_norm 2.8800 (3.1859)	
[2022-01-26 21:32:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][340/1251]	eta 0:34:19 lr 0.000015	time 1.9616 (2.2608)	loss 2.3211 (3.0024)	grad_norm 2.7417 (3.1912)	
[2022-01-26 21:32:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][350/1251]	eta 0:33:55 lr 0.000015	time 1.8740 (2.2587)	loss 2.3567 (2.9969)	grad_norm 2.9134 (3.1925)	
[2022-01-26 21:32:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][360/1251]	eta 0:33:30 lr 0.000015	time 2.8039 (2.2570)	loss 3.1123 (2.9968)	grad_norm 2.9846 (3.1928)	
[2022-01-26 21:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][370/1251]	eta 0:33:04 lr 0.000015	time 3.1624 (2.2526)	loss 2.1999 (2.9976)	grad_norm 3.0428 (3.1944)	
[2022-01-26 21:33:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][380/1251]	eta 0:32:37 lr 0.000015	time 1.7394 (2.2470)	loss 2.3908 (2.9940)	grad_norm 2.7832 (3.1946)	
[2022-01-26 21:33:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][390/1251]	eta 0:32:10 lr 0.000015	time 2.1826 (2.2426)	loss 3.5221 (2.9972)	grad_norm 3.4894 (3.1974)	
[2022-01-26 21:34:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][400/1251]	eta 0:31:45 lr 0.000015	time 1.8050 (2.2396)	loss 3.2180 (2.9908)	grad_norm 3.1905 (3.1979)	
[2022-01-26 21:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][410/1251]	eta 0:31:24 lr 0.000015	time 3.1294 (2.2413)	loss 2.4597 (2.9959)	grad_norm 2.9561 (3.1951)	
[2022-01-26 21:35:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][420/1251]	eta 0:31:05 lr 0.000015	time 2.5192 (2.2454)	loss 3.2120 (2.9995)	grad_norm 3.5158 (3.1967)	
[2022-01-26 21:35:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][430/1251]	eta 0:30:45 lr 0.000015	time 2.1140 (2.2480)	loss 2.9382 (2.9945)	grad_norm 3.1055 (3.1957)	
[2022-01-26 21:35:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][440/1251]	eta 0:30:21 lr 0.000015	time 1.9685 (2.2456)	loss 3.2641 (2.9991)	grad_norm 3.3553 (3.1982)	
[2022-01-26 21:36:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][450/1251]	eta 0:29:54 lr 0.000015	time 2.2199 (2.2408)	loss 3.3108 (2.9922)	grad_norm 3.2928 (3.2004)	
[2022-01-26 21:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][460/1251]	eta 0:29:27 lr 0.000015	time 1.8628 (2.2342)	loss 3.7892 (2.9959)	grad_norm 4.0813 (3.2016)	
[2022-01-26 21:36:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][470/1251]	eta 0:29:00 lr 0.000015	time 2.0193 (2.2287)	loss 3.1324 (2.9959)	grad_norm 3.0412 (3.2020)	
[2022-01-26 21:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][480/1251]	eta 0:28:35 lr 0.000015	time 1.9349 (2.2249)	loss 2.7115 (2.9958)	grad_norm 3.4321 (3.1985)	
[2022-01-26 21:37:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][490/1251]	eta 0:28:14 lr 0.000015	time 3.0985 (2.2261)	loss 3.2574 (2.9947)	grad_norm 3.0899 (3.1974)	
[2022-01-26 21:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][500/1251]	eta 0:27:52 lr 0.000015	time 2.2210 (2.2266)	loss 3.3441 (2.9965)	grad_norm 2.8471 (3.2089)	
[2022-01-26 21:38:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][510/1251]	eta 0:27:30 lr 0.000015	time 1.8751 (2.2270)	loss 3.3495 (2.9982)	grad_norm 3.7820 (3.2077)	
[2022-01-26 21:38:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][520/1251]	eta 0:27:08 lr 0.000015	time 2.0014 (2.2276)	loss 3.0087 (2.9994)	grad_norm 3.4867 (3.2172)	
[2022-01-26 21:39:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][530/1251]	eta 0:26:46 lr 0.000015	time 2.2283 (2.2280)	loss 3.4509 (3.0019)	grad_norm 3.6256 (3.2256)	
[2022-01-26 21:39:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][540/1251]	eta 0:26:24 lr 0.000015	time 2.4758 (2.2284)	loss 2.8453 (2.9981)	grad_norm 2.7307 (3.2275)	
[2022-01-26 21:39:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][550/1251]	eta 0:26:01 lr 0.000015	time 1.9293 (2.2281)	loss 3.3994 (2.9956)	grad_norm 2.9071 (3.2307)	
[2022-01-26 21:40:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][560/1251]	eta 0:25:39 lr 0.000015	time 2.0595 (2.2285)	loss 3.0369 (2.9987)	grad_norm 3.3583 (3.2313)	
[2022-01-26 21:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][570/1251]	eta 0:25:15 lr 0.000015	time 2.2043 (2.2256)	loss 2.0981 (2.9987)	grad_norm 5.3522 (3.2384)	
[2022-01-26 21:40:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][580/1251]	eta 0:24:51 lr 0.000015	time 1.9645 (2.2224)	loss 3.4761 (2.9978)	grad_norm 3.3546 (3.2391)	
[2022-01-26 21:41:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][590/1251]	eta 0:24:30 lr 0.000015	time 1.8972 (2.2249)	loss 2.8895 (2.9936)	grad_norm 3.6051 (3.2432)	
[2022-01-26 21:41:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][600/1251]	eta 0:24:09 lr 0.000015	time 2.7683 (2.2260)	loss 3.1607 (2.9927)	grad_norm 3.5202 (3.2444)	
[2022-01-26 21:41:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][610/1251]	eta 0:23:47 lr 0.000015	time 2.0590 (2.2267)	loss 3.3346 (2.9923)	grad_norm 5.2536 (3.2481)	
[2022-01-26 21:42:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][620/1251]	eta 0:23:23 lr 0.000015	time 1.8071 (2.2248)	loss 2.8935 (2.9945)	grad_norm 3.0396 (3.2459)	
[2022-01-26 21:42:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][630/1251]	eta 0:22:59 lr 0.000015	time 1.9734 (2.2208)	loss 2.9723 (2.9958)	grad_norm 3.1547 (3.2452)	
[2022-01-26 21:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][640/1251]	eta 0:22:35 lr 0.000015	time 2.5140 (2.2182)	loss 2.8425 (2.9942)	grad_norm 2.9247 (3.2415)	
[2022-01-26 21:43:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][650/1251]	eta 0:22:12 lr 0.000015	time 1.9651 (2.2167)	loss 3.3832 (2.9946)	grad_norm 3.3771 (3.2416)	
[2022-01-26 21:43:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][660/1251]	eta 0:21:49 lr 0.000015	time 2.2784 (2.2156)	loss 2.1521 (2.9960)	grad_norm 2.6915 (3.2418)	
[2022-01-26 21:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][670/1251]	eta 0:21:28 lr 0.000015	time 3.1236 (2.2177)	loss 2.8111 (2.9970)	grad_norm 2.7295 (3.2420)	
[2022-01-26 21:44:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][680/1251]	eta 0:21:06 lr 0.000015	time 2.8648 (2.2187)	loss 3.0661 (2.9949)	grad_norm 4.5214 (3.2460)	
[2022-01-26 21:44:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][690/1251]	eta 0:20:44 lr 0.000015	time 1.7192 (2.2179)	loss 1.9855 (2.9944)	grad_norm 2.9260 (3.2461)	
[2022-01-26 21:45:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][700/1251]	eta 0:20:21 lr 0.000015	time 2.3153 (2.2170)	loss 3.2458 (2.9905)	grad_norm 3.2011 (3.2452)	
[2022-01-26 21:45:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][710/1251]	eta 0:19:59 lr 0.000015	time 2.1573 (2.2166)	loss 2.9217 (2.9926)	grad_norm 3.0933 (3.2469)	
[2022-01-26 21:45:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][720/1251]	eta 0:19:37 lr 0.000015	time 3.0715 (2.2174)	loss 3.0328 (2.9920)	grad_norm 3.1457 (3.2467)	
[2022-01-26 21:46:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][730/1251]	eta 0:19:14 lr 0.000015	time 1.5712 (2.2157)	loss 2.9034 (2.9928)	grad_norm 3.2107 (3.2454)	
[2022-01-26 21:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][740/1251]	eta 0:18:52 lr 0.000015	time 2.4786 (2.2156)	loss 3.0858 (2.9949)	grad_norm 3.2248 (3.2454)	
[2022-01-26 21:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][750/1251]	eta 0:18:29 lr 0.000015	time 1.7968 (2.2146)	loss 3.0712 (2.9944)	grad_norm 3.1959 (3.2463)	
[2022-01-26 21:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][760/1251]	eta 0:18:06 lr 0.000015	time 1.6898 (2.2129)	loss 3.5231 (2.9938)	grad_norm 3.0867 (3.2482)	
[2022-01-26 21:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][770/1251]	eta 0:17:44 lr 0.000015	time 2.1600 (2.2137)	loss 3.3913 (2.9955)	grad_norm 2.9072 (3.2458)	
[2022-01-26 21:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][780/1251]	eta 0:17:23 lr 0.000015	time 3.5136 (2.2159)	loss 2.9408 (2.9962)	grad_norm 3.1436 (3.2453)	
[2022-01-26 21:48:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][790/1251]	eta 0:17:02 lr 0.000015	time 1.6956 (2.2186)	loss 3.3227 (2.9966)	grad_norm 3.1233 (3.2484)	
[2022-01-26 21:48:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][800/1251]	eta 0:16:40 lr 0.000015	time 1.6720 (2.2175)	loss 2.4251 (2.9950)	grad_norm 3.1066 (3.2469)	
[2022-01-26 21:49:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][810/1251]	eta 0:16:17 lr 0.000015	time 1.8544 (2.2166)	loss 3.0695 (2.9957)	grad_norm 3.0225 (3.2499)	
[2022-01-26 21:49:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][820/1251]	eta 0:15:54 lr 0.000015	time 1.9525 (2.2151)	loss 3.3028 (2.9973)	grad_norm 3.5936 (3.2521)	
[2022-01-26 21:49:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][830/1251]	eta 0:15:30 lr 0.000015	time 1.9044 (2.2114)	loss 2.5851 (2.9976)	grad_norm 3.2169 (3.2554)	
[2022-01-26 21:50:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][840/1251]	eta 0:15:08 lr 0.000015	time 1.8601 (2.2093)	loss 2.7083 (2.9963)	grad_norm 3.2606 (3.2551)	
[2022-01-26 21:50:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][850/1251]	eta 0:14:45 lr 0.000015	time 2.5533 (2.2094)	loss 2.8898 (2.9970)	grad_norm 3.0062 (3.2549)	
[2022-01-26 21:51:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][860/1251]	eta 0:14:23 lr 0.000015	time 2.0025 (2.2087)	loss 3.5547 (2.9981)	grad_norm 3.3434 (3.2562)	
[2022-01-26 21:51:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][870/1251]	eta 0:14:01 lr 0.000015	time 2.1715 (2.2087)	loss 3.3638 (2.9995)	grad_norm 2.9097 (3.2549)	
[2022-01-26 21:51:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][880/1251]	eta 0:13:39 lr 0.000015	time 2.1882 (2.2090)	loss 2.4662 (2.9997)	grad_norm 3.4790 (3.2563)	
[2022-01-26 21:52:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][890/1251]	eta 0:13:18 lr 0.000015	time 2.8682 (2.2112)	loss 2.7837 (3.0008)	grad_norm 3.2232 (3.2561)	
[2022-01-26 21:52:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][900/1251]	eta 0:12:55 lr 0.000015	time 2.1924 (2.2105)	loss 3.1258 (3.0035)	grad_norm 3.1100 (3.2547)	
[2022-01-26 21:52:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][910/1251]	eta 0:12:33 lr 0.000015	time 2.4865 (2.2111)	loss 1.8851 (3.0026)	grad_norm 2.8646 (3.2534)	
[2022-01-26 21:53:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][920/1251]	eta 0:12:11 lr 0.000015	time 1.8363 (2.2111)	loss 3.4864 (3.0044)	grad_norm 2.9423 (3.2518)	
[2022-01-26 21:53:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][930/1251]	eta 0:11:49 lr 0.000015	time 2.8574 (2.2107)	loss 3.0380 (3.0043)	grad_norm 3.1458 (3.2526)	
[2022-01-26 21:53:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][940/1251]	eta 0:11:26 lr 0.000015	time 1.9400 (2.2089)	loss 3.2546 (3.0041)	grad_norm 3.1184 (3.2514)	
[2022-01-26 21:54:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][950/1251]	eta 0:11:04 lr 0.000015	time 2.2194 (2.2078)	loss 3.5670 (3.0035)	grad_norm 3.2067 (3.2512)	
[2022-01-26 21:54:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][960/1251]	eta 0:10:42 lr 0.000015	time 1.8849 (2.2072)	loss 3.1315 (3.0039)	grad_norm 2.8109 (3.2505)	
[2022-01-26 21:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][970/1251]	eta 0:10:19 lr 0.000015	time 1.6917 (2.2056)	loss 2.9996 (3.0037)	grad_norm 2.6637 (3.2499)	
[2022-01-26 21:55:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][980/1251]	eta 0:09:57 lr 0.000015	time 2.0383 (2.2053)	loss 2.6813 (3.0040)	grad_norm 3.0952 (3.2501)	
[2022-01-26 21:55:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][990/1251]	eta 0:09:36 lr 0.000015	time 3.4122 (2.2079)	loss 2.7519 (3.0043)	grad_norm 3.3512 (3.2499)	
[2022-01-26 21:56:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1000/1251]	eta 0:09:14 lr 0.000015	time 2.0275 (2.2084)	loss 2.4872 (3.0024)	grad_norm 3.2879 (3.2497)	
[2022-01-26 21:56:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1010/1251]	eta 0:08:52 lr 0.000015	time 2.2270 (2.2079)	loss 3.1630 (3.0019)	grad_norm 2.9798 (3.2494)	
[2022-01-26 21:56:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1020/1251]	eta 0:08:30 lr 0.000015	time 2.0840 (2.2078)	loss 2.6141 (3.0014)	grad_norm 3.1886 (3.2489)	
[2022-01-26 21:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1030/1251]	eta 0:08:07 lr 0.000015	time 1.9073 (2.2075)	loss 3.3407 (3.0019)	grad_norm 3.3440 (3.2498)	
[2022-01-26 21:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1040/1251]	eta 0:07:45 lr 0.000015	time 1.9186 (2.2066)	loss 3.3344 (3.0022)	grad_norm 3.3620 (3.2480)	
[2022-01-26 21:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1050/1251]	eta 0:07:23 lr 0.000015	time 1.7758 (2.2077)	loss 2.1857 (3.0031)	grad_norm 3.4137 (3.2459)	
[2022-01-26 21:58:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1060/1251]	eta 0:07:01 lr 0.000015	time 1.8118 (2.2079)	loss 3.3179 (3.0012)	grad_norm 3.0243 (3.2467)	
[2022-01-26 21:58:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1070/1251]	eta 0:06:39 lr 0.000015	time 1.7971 (2.2079)	loss 2.2380 (3.0004)	grad_norm 2.8541 (3.2469)	
[2022-01-26 21:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1080/1251]	eta 0:06:17 lr 0.000015	time 2.0392 (2.2067)	loss 1.9574 (2.9999)	grad_norm 3.4672 (3.2468)	
[2022-01-26 21:59:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1090/1251]	eta 0:05:55 lr 0.000015	time 1.6583 (2.2054)	loss 3.0219 (3.0010)	grad_norm 3.0848 (3.2457)	
[2022-01-26 21:59:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1100/1251]	eta 0:05:32 lr 0.000015	time 2.1010 (2.2048)	loss 2.2468 (3.0008)	grad_norm 3.7157 (3.2476)	
[2022-01-26 22:00:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1110/1251]	eta 0:05:10 lr 0.000015	time 2.2301 (2.2042)	loss 3.4716 (3.0018)	grad_norm 3.0454 (3.2480)	
[2022-01-26 22:00:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1120/1251]	eta 0:04:48 lr 0.000015	time 1.8819 (2.2029)	loss 2.7849 (2.9997)	grad_norm 3.2030 (3.2463)	
[2022-01-26 22:00:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1130/1251]	eta 0:04:26 lr 0.000015	time 1.8254 (2.2046)	loss 3.0605 (2.9979)	grad_norm 2.9221 (3.2455)	
[2022-01-26 22:01:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1140/1251]	eta 0:04:04 lr 0.000015	time 2.1438 (2.2067)	loss 3.5868 (3.0000)	grad_norm 3.2697 (3.2445)	
[2022-01-26 22:01:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1150/1251]	eta 0:03:42 lr 0.000015	time 1.8177 (2.2067)	loss 2.4907 (2.9990)	grad_norm 3.1141 (3.2422)	
[2022-01-26 22:01:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1160/1251]	eta 0:03:20 lr 0.000015	time 1.5808 (2.2052)	loss 2.1150 (2.9963)	grad_norm 3.9956 (3.2433)	
[2022-01-26 22:02:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1170/1251]	eta 0:02:58 lr 0.000015	time 1.8733 (2.2048)	loss 2.7424 (2.9975)	grad_norm 2.6195 (3.2429)	
[2022-01-26 22:02:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1180/1251]	eta 0:02:36 lr 0.000015	time 3.1238 (2.2051)	loss 3.1263 (2.9976)	grad_norm 2.7128 (3.2422)	
[2022-01-26 22:03:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1190/1251]	eta 0:02:14 lr 0.000015	time 2.3462 (2.2048)	loss 1.8917 (2.9980)	grad_norm 3.2465 (3.2410)	
[2022-01-26 22:03:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1200/1251]	eta 0:01:52 lr 0.000015	time 1.8427 (2.2035)	loss 3.1287 (2.9971)	grad_norm 2.8488 (3.2418)	
[2022-01-26 22:03:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1210/1251]	eta 0:01:30 lr 0.000015	time 1.8547 (2.2031)	loss 3.1987 (2.9979)	grad_norm 3.0334 (3.2412)	
[2022-01-26 22:04:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1220/1251]	eta 0:01:08 lr 0.000015	time 2.3964 (2.2025)	loss 2.2582 (2.9965)	grad_norm 3.3777 (3.2402)	
[2022-01-26 22:04:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1230/1251]	eta 0:00:46 lr 0.000015	time 3.1078 (2.2021)	loss 3.4174 (2.9979)	grad_norm 2.9896 (3.2396)	
[2022-01-26 22:04:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1240/1251]	eta 0:00:24 lr 0.000015	time 1.5225 (2.2010)	loss 2.2833 (2.9962)	grad_norm 3.4350 (3.2448)	
[2022-01-26 22:05:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [286/300][1250/1251]	eta 0:00:02 lr 0.000015	time 1.1815 (2.1951)	loss 3.1702 (2.9979)	grad_norm 3.3473 (3.2442)	
[2022-01-26 22:05:05 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 286 training takes 0:45:46
[2022-01-26 22:05:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.658 (18.658)	Loss 0.8301 (0.8301)	Acc@1 81.055 (81.055)	Acc@5 95.410 (95.410)	
[2022-01-26 22:05:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.681 (3.564)	Loss 0.7716 (0.8185)	Acc@1 81.543 (80.788)	Acc@5 95.996 (95.188)	
[2022-01-26 22:06:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.274 (2.595)	Loss 0.8488 (0.8086)	Acc@1 80.371 (81.101)	Acc@5 95.117 (95.382)	
[2022-01-26 22:06:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.631 (2.316)	Loss 0.7627 (0.8071)	Acc@1 83.594 (81.178)	Acc@5 96.094 (95.410)	
[2022-01-26 22:06:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.282 (2.213)	Loss 0.8230 (0.8072)	Acc@1 80.762 (81.055)	Acc@5 94.434 (95.386)	
[2022-01-26 22:06:43 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.092 Acc@5 95.464
[2022-01-26 22:06:43 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.1%
[2022-01-26 22:06:43 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.12%
[2022-01-26 22:07:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][0/1251]	eta 7:30:23 lr 0.000015	time 21.6019 (21.6019)	loss 2.5287 (2.5287)	grad_norm 3.8747 (3.8747)	
[2022-01-26 22:07:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][10/1251]	eta 1:25:33 lr 0.000015	time 2.0018 (4.1370)	loss 3.2843 (2.9951)	grad_norm 3.2551 (3.3061)	
[2022-01-26 22:07:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][20/1251]	eta 1:06:10 lr 0.000015	time 2.1532 (3.2255)	loss 3.3137 (3.0501)	grad_norm 3.1576 (3.2526)	
[2022-01-26 22:08:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][30/1251]	eta 0:58:46 lr 0.000015	time 1.4767 (2.8880)	loss 2.9728 (3.0594)	grad_norm 2.9237 (3.2415)	
[2022-01-26 22:08:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][40/1251]	eta 0:58:41 lr 0.000015	time 8.5103 (2.9077)	loss 2.9129 (3.1057)	grad_norm 3.1955 (3.2574)	
[2022-01-26 22:09:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][50/1251]	eta 0:56:07 lr 0.000015	time 1.7088 (2.8039)	loss 3.4239 (3.0929)	grad_norm 3.1342 (3.2463)	
[2022-01-26 22:09:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][60/1251]	eta 0:53:41 lr 0.000015	time 2.0883 (2.7046)	loss 3.2529 (3.0316)	grad_norm 3.0364 (3.2274)	
[2022-01-26 22:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][70/1251]	eta 0:51:21 lr 0.000015	time 1.8947 (2.6089)	loss 3.1625 (3.0461)	grad_norm 3.1161 (3.2742)	
[2022-01-26 22:10:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][80/1251]	eta 0:49:52 lr 0.000015	time 3.3975 (2.5554)	loss 2.9445 (3.0061)	grad_norm 2.8452 (3.2670)	
[2022-01-26 22:10:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][90/1251]	eta 0:48:27 lr 0.000015	time 1.8368 (2.5045)	loss 3.5230 (2.9837)	grad_norm 3.5017 (3.2691)	
[2022-01-26 22:10:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][100/1251]	eta 0:47:13 lr 0.000015	time 1.5509 (2.4616)	loss 3.2263 (2.9948)	grad_norm 3.0323 (3.2592)	
[2022-01-26 22:11:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][110/1251]	eta 0:46:05 lr 0.000015	time 2.2864 (2.4238)	loss 3.3447 (2.9800)	grad_norm 3.4412 (3.2528)	
[2022-01-26 22:11:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][120/1251]	eta 0:45:18 lr 0.000015	time 1.9408 (2.4034)	loss 2.7798 (2.9952)	grad_norm 3.2151 (3.3123)	
[2022-01-26 22:11:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][130/1251]	eta 0:44:51 lr 0.000015	time 2.7017 (2.4005)	loss 2.6641 (2.9748)	grad_norm 3.5296 (3.3088)	
[2022-01-26 22:12:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][140/1251]	eta 0:44:15 lr 0.000015	time 2.2509 (2.3906)	loss 3.3607 (2.9870)	grad_norm 2.9889 (3.2830)	
[2022-01-26 22:12:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][150/1251]	eta 0:43:28 lr 0.000014	time 1.9348 (2.3696)	loss 2.8533 (2.9958)	grad_norm 2.7440 (3.2808)	
[2022-01-26 22:13:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][160/1251]	eta 0:42:50 lr 0.000014	time 1.9548 (2.3559)	loss 3.2242 (2.9974)	grad_norm 2.8171 (3.2680)	
[2022-01-26 22:13:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][170/1251]	eta 0:42:07 lr 0.000014	time 1.6240 (2.3377)	loss 2.7400 (2.9987)	grad_norm 3.1476 (3.2473)	
[2022-01-26 22:13:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][180/1251]	eta 0:41:44 lr 0.000014	time 2.8590 (2.3383)	loss 2.7094 (3.0053)	grad_norm 3.1179 (3.2406)	
[2022-01-26 22:14:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][190/1251]	eta 0:41:22 lr 0.000014	time 2.1549 (2.3397)	loss 2.2946 (2.9992)	grad_norm 3.2421 (3.2344)	
[2022-01-26 22:14:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][200/1251]	eta 0:41:05 lr 0.000014	time 3.2861 (2.3459)	loss 3.4929 (3.0035)	grad_norm 3.3614 (3.2353)	
[2022-01-26 22:14:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][210/1251]	eta 0:40:46 lr 0.000014	time 1.9224 (2.3498)	loss 2.6295 (2.9909)	grad_norm 2.8760 (3.2230)	
[2022-01-26 22:15:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][220/1251]	eta 0:40:15 lr 0.000014	time 1.9114 (2.3432)	loss 2.5233 (2.9923)	grad_norm 3.5048 (3.2262)	
[2022-01-26 22:15:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][230/1251]	eta 0:39:40 lr 0.000014	time 1.9389 (2.3313)	loss 3.3496 (2.9836)	grad_norm 3.3256 (3.2384)	
[2022-01-26 22:16:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][240/1251]	eta 0:39:02 lr 0.000014	time 2.3855 (2.3169)	loss 3.0324 (2.9956)	grad_norm 3.2593 (3.2472)	
[2022-01-26 22:16:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][250/1251]	eta 0:38:22 lr 0.000014	time 1.7853 (2.3004)	loss 3.3762 (3.0033)	grad_norm 3.1450 (3.2474)	
[2022-01-26 22:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][260/1251]	eta 0:37:53 lr 0.000014	time 2.2219 (2.2938)	loss 3.2984 (2.9999)	grad_norm 3.5293 (3.2564)	
[2022-01-26 22:17:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][270/1251]	eta 0:37:24 lr 0.000014	time 2.0850 (2.2876)	loss 3.2540 (3.0033)	grad_norm 2.7029 (3.2532)	
[2022-01-26 22:17:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][280/1251]	eta 0:37:00 lr 0.000014	time 1.7386 (2.2870)	loss 2.1463 (3.0063)	grad_norm 2.9771 (3.2528)	
[2022-01-26 22:17:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][290/1251]	eta 0:36:34 lr 0.000014	time 1.8676 (2.2834)	loss 3.2861 (3.0017)	grad_norm 3.3819 (3.2565)	
[2022-01-26 22:18:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][300/1251]	eta 0:36:16 lr 0.000014	time 3.1840 (2.2887)	loss 3.1176 (2.9980)	grad_norm 2.4785 (3.2529)	
[2022-01-26 22:18:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][310/1251]	eta 0:35:53 lr 0.000014	time 2.5164 (2.2888)	loss 3.0825 (2.9925)	grad_norm 2.9367 (3.2463)	
[2022-01-26 22:18:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][320/1251]	eta 0:35:27 lr 0.000014	time 1.7818 (2.2857)	loss 3.8338 (2.9934)	grad_norm 3.7318 (3.2523)	
[2022-01-26 22:19:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][330/1251]	eta 0:35:03 lr 0.000014	time 1.8870 (2.2843)	loss 3.1026 (2.9974)	grad_norm 2.8998 (3.2498)	
[2022-01-26 22:19:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][340/1251]	eta 0:34:36 lr 0.000014	time 2.1761 (2.2792)	loss 2.6464 (2.9989)	grad_norm 2.7250 (3.2416)	
[2022-01-26 22:20:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][350/1251]	eta 0:34:11 lr 0.000014	time 1.8672 (2.2771)	loss 3.4126 (2.9994)	grad_norm 3.2280 (3.2379)	
[2022-01-26 22:20:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][360/1251]	eta 0:33:48 lr 0.000014	time 1.7890 (2.2761)	loss 3.3201 (2.9973)	grad_norm 3.1857 (3.2384)	
[2022-01-26 22:20:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][370/1251]	eta 0:33:26 lr 0.000014	time 1.9176 (2.2772)	loss 2.5022 (3.0005)	grad_norm 3.8772 (3.2369)	
[2022-01-26 22:21:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][380/1251]	eta 0:33:00 lr 0.000014	time 2.4660 (2.2741)	loss 3.2301 (3.0067)	grad_norm 2.6508 (3.2383)	
[2022-01-26 22:21:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][390/1251]	eta 0:32:34 lr 0.000014	time 1.9018 (2.2702)	loss 2.5522 (3.0100)	grad_norm 2.8743 (3.2375)	
[2022-01-26 22:21:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][400/1251]	eta 0:32:08 lr 0.000014	time 2.0285 (2.2665)	loss 3.6582 (3.0085)	grad_norm 3.2168 (3.2336)	
[2022-01-26 22:22:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][410/1251]	eta 0:31:42 lr 0.000014	time 1.5335 (2.2622)	loss 3.1905 (3.0115)	grad_norm 3.4317 (3.2333)	
[2022-01-26 22:22:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][420/1251]	eta 0:31:18 lr 0.000014	time 2.4147 (2.2606)	loss 3.7917 (3.0135)	grad_norm 2.7519 (3.2315)	
[2022-01-26 22:22:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][430/1251]	eta 0:30:54 lr 0.000014	time 2.2311 (2.2584)	loss 3.3266 (3.0105)	grad_norm 3.0214 (3.2279)	
[2022-01-26 22:23:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][440/1251]	eta 0:30:30 lr 0.000014	time 2.2158 (2.2571)	loss 3.3504 (3.0084)	grad_norm 4.6994 (3.2372)	
[2022-01-26 22:23:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][450/1251]	eta 0:30:04 lr 0.000014	time 2.3109 (2.2532)	loss 3.1468 (3.0118)	grad_norm 2.9955 (3.2369)	
[2022-01-26 22:24:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][460/1251]	eta 0:29:40 lr 0.000014	time 1.9746 (2.2512)	loss 3.1882 (3.0139)	grad_norm 3.0932 (3.2425)	
[2022-01-26 22:24:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][470/1251]	eta 0:29:16 lr 0.000014	time 2.0512 (2.2487)	loss 3.0943 (3.0148)	grad_norm 2.7480 (3.2402)	
[2022-01-26 22:24:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][480/1251]	eta 0:28:51 lr 0.000014	time 2.2662 (2.2451)	loss 2.6521 (3.0154)	grad_norm 3.2180 (3.2418)	
[2022-01-26 22:25:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][490/1251]	eta 0:28:30 lr 0.000014	time 2.4794 (2.2472)	loss 2.7587 (3.0147)	grad_norm 3.0091 (3.2434)	
[2022-01-26 22:25:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][500/1251]	eta 0:28:06 lr 0.000014	time 1.9570 (2.2451)	loss 3.3977 (3.0161)	grad_norm 2.8827 (3.2511)	
[2022-01-26 22:25:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][510/1251]	eta 0:27:43 lr 0.000014	time 2.2765 (2.2444)	loss 2.6556 (3.0141)	grad_norm 3.7458 (3.2559)	
[2022-01-26 22:26:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][520/1251]	eta 0:27:19 lr 0.000014	time 2.5790 (2.2429)	loss 2.6488 (3.0079)	grad_norm 3.2293 (3.2578)	
[2022-01-26 22:26:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][530/1251]	eta 0:26:54 lr 0.000014	time 2.3236 (2.2391)	loss 3.4791 (3.0090)	grad_norm 2.7770 (3.2573)	
[2022-01-26 22:26:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][540/1251]	eta 0:26:28 lr 0.000014	time 2.3275 (2.2348)	loss 3.2708 (3.0131)	grad_norm 3.1570 (3.2633)	
[2022-01-26 22:27:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][550/1251]	eta 0:26:05 lr 0.000014	time 2.1829 (2.2327)	loss 3.0416 (3.0143)	grad_norm 3.4462 (3.2620)	
[2022-01-26 22:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][560/1251]	eta 0:25:44 lr 0.000014	time 3.2841 (2.2345)	loss 3.2202 (3.0147)	grad_norm 3.3266 (3.2623)	
[2022-01-26 22:28:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][570/1251]	eta 0:25:22 lr 0.000014	time 2.3617 (2.2353)	loss 3.0567 (3.0130)	grad_norm 3.2723 (3.2616)	
[2022-01-26 22:28:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][580/1251]	eta 0:24:59 lr 0.000014	time 2.5307 (2.2352)	loss 2.3133 (3.0117)	grad_norm 3.1615 (3.2611)	
[2022-01-26 22:28:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][590/1251]	eta 0:24:36 lr 0.000014	time 1.9286 (2.2338)	loss 3.2877 (3.0122)	grad_norm 3.6843 (3.2638)	
[2022-01-26 22:29:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][600/1251]	eta 0:24:14 lr 0.000014	time 2.2733 (2.2343)	loss 3.2856 (3.0125)	grad_norm 3.1807 (3.2637)	
[2022-01-26 22:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][610/1251]	eta 0:23:51 lr 0.000014	time 2.4143 (2.2329)	loss 2.2861 (3.0129)	grad_norm 3.2820 (3.2611)	
[2022-01-26 22:29:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][620/1251]	eta 0:23:27 lr 0.000014	time 2.3058 (2.2301)	loss 3.4413 (3.0103)	grad_norm 4.6274 (3.2596)	
[2022-01-26 22:30:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][630/1251]	eta 0:23:04 lr 0.000014	time 3.3902 (2.2303)	loss 3.0862 (3.0109)	grad_norm 3.8346 (3.2592)	
[2022-01-26 22:30:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][640/1251]	eta 0:22:42 lr 0.000014	time 2.1593 (2.2300)	loss 2.4593 (3.0101)	grad_norm 2.7238 (3.2593)	
[2022-01-26 22:30:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][650/1251]	eta 0:22:20 lr 0.000014	time 2.9766 (2.2308)	loss 2.9732 (3.0096)	grad_norm 3.6016 (3.2571)	
[2022-01-26 22:31:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][660/1251]	eta 0:21:57 lr 0.000014	time 1.9719 (2.2286)	loss 2.8607 (3.0121)	grad_norm 3.1939 (3.2537)	
[2022-01-26 22:31:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][670/1251]	eta 0:21:35 lr 0.000014	time 3.0094 (2.2291)	loss 3.3397 (3.0132)	grad_norm 3.0211 (3.2524)	
[2022-01-26 22:32:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][680/1251]	eta 0:21:13 lr 0.000014	time 1.8986 (2.2309)	loss 2.5677 (3.0119)	grad_norm 4.0037 (3.2522)	
[2022-01-26 22:32:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][690/1251]	eta 0:20:52 lr 0.000014	time 2.2345 (2.2327)	loss 2.6633 (3.0119)	grad_norm 2.7610 (3.2499)	
[2022-01-26 22:32:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][700/1251]	eta 0:20:29 lr 0.000014	time 2.2690 (2.2321)	loss 3.2253 (3.0156)	grad_norm 3.4264 (3.2517)	
[2022-01-26 22:33:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][710/1251]	eta 0:20:06 lr 0.000014	time 2.1657 (2.2301)	loss 3.1117 (3.0141)	grad_norm 2.8163 (3.2504)	
[2022-01-26 22:33:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][720/1251]	eta 0:19:42 lr 0.000014	time 1.7981 (2.2261)	loss 3.1699 (3.0165)	grad_norm 3.3491 (3.2502)	
[2022-01-26 22:33:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][730/1251]	eta 0:19:17 lr 0.000014	time 2.2783 (2.2225)	loss 3.2812 (3.0162)	grad_norm 2.9961 (3.2507)	
[2022-01-26 22:34:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][740/1251]	eta 0:18:54 lr 0.000014	time 1.9629 (2.2201)	loss 3.2390 (3.0170)	grad_norm 2.9002 (3.2524)	
[2022-01-26 22:34:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][750/1251]	eta 0:18:31 lr 0.000014	time 1.8832 (2.2191)	loss 3.5483 (3.0178)	grad_norm 2.9986 (3.2549)	
[2022-01-26 22:34:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][760/1251]	eta 0:18:10 lr 0.000014	time 1.6273 (2.2201)	loss 3.2908 (3.0195)	grad_norm 3.1622 (3.2558)	
[2022-01-26 22:35:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][770/1251]	eta 0:17:49 lr 0.000014	time 2.8055 (2.2236)	loss 2.4394 (3.0213)	grad_norm 3.7662 (3.2594)	
[2022-01-26 22:35:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][780/1251]	eta 0:17:28 lr 0.000014	time 2.1825 (2.2260)	loss 3.0795 (3.0224)	grad_norm 4.5675 (3.2636)	
[2022-01-26 22:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][790/1251]	eta 0:17:05 lr 0.000014	time 2.4596 (2.2255)	loss 2.8539 (3.0221)	grad_norm 3.1581 (3.2619)	
[2022-01-26 22:36:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][800/1251]	eta 0:16:42 lr 0.000014	time 1.9462 (2.2237)	loss 3.0845 (3.0229)	grad_norm 2.9047 (3.2606)	
[2022-01-26 22:36:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][810/1251]	eta 0:16:19 lr 0.000014	time 2.2377 (2.2221)	loss 3.1932 (3.0240)	grad_norm 3.3744 (3.2633)	
[2022-01-26 22:37:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][820/1251]	eta 0:15:57 lr 0.000014	time 1.4804 (2.2209)	loss 1.8259 (3.0205)	grad_norm 3.2865 (3.2644)	
[2022-01-26 22:37:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][830/1251]	eta 0:15:34 lr 0.000014	time 2.2167 (2.2192)	loss 2.7037 (3.0174)	grad_norm 3.4176 (3.2639)	
[2022-01-26 22:37:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][840/1251]	eta 0:15:11 lr 0.000014	time 1.7955 (2.2189)	loss 3.3197 (3.0147)	grad_norm 3.4739 (3.2625)	
[2022-01-26 22:38:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][850/1251]	eta 0:14:49 lr 0.000014	time 2.1593 (2.2191)	loss 3.1774 (3.0122)	grad_norm 2.9144 (3.2611)	
[2022-01-26 22:38:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][860/1251]	eta 0:14:28 lr 0.000014	time 1.8812 (2.2209)	loss 3.5352 (3.0111)	grad_norm 2.9086 (3.2578)	
[2022-01-26 22:38:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][870/1251]	eta 0:14:05 lr 0.000014	time 1.7964 (2.2185)	loss 2.8447 (3.0127)	grad_norm 2.7715 (3.2545)	
[2022-01-26 22:39:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][880/1251]	eta 0:13:42 lr 0.000014	time 2.1214 (2.2180)	loss 2.6328 (3.0120)	grad_norm 3.0005 (3.2595)	
[2022-01-26 22:39:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][890/1251]	eta 0:13:21 lr 0.000014	time 1.9448 (2.2200)	loss 2.5738 (3.0129)	grad_norm 3.4368 (3.2601)	
[2022-01-26 22:40:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][900/1251]	eta 0:12:59 lr 0.000014	time 1.9692 (2.2200)	loss 2.8620 (3.0135)	grad_norm 2.4334 (3.2589)	
[2022-01-26 22:40:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][910/1251]	eta 0:12:36 lr 0.000014	time 1.6794 (2.2179)	loss 3.3509 (3.0138)	grad_norm 2.9505 (3.2576)	
[2022-01-26 22:40:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][920/1251]	eta 0:12:13 lr 0.000014	time 1.8795 (2.2159)	loss 3.0719 (3.0131)	grad_norm 3.0827 (3.2564)	
[2022-01-26 22:41:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][930/1251]	eta 0:11:51 lr 0.000014	time 2.1190 (2.2173)	loss 2.8466 (3.0139)	grad_norm 2.8387 (3.2568)	
[2022-01-26 22:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][940/1251]	eta 0:11:30 lr 0.000014	time 4.2670 (2.2214)	loss 3.7089 (3.0152)	grad_norm 3.5678 (3.2588)	
[2022-01-26 22:41:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][950/1251]	eta 0:11:08 lr 0.000014	time 1.5896 (2.2194)	loss 2.4900 (3.0117)	grad_norm 2.7847 (3.2582)	
[2022-01-26 22:42:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][960/1251]	eta 0:10:45 lr 0.000014	time 1.9634 (2.2171)	loss 2.7803 (3.0091)	grad_norm 4.3715 (3.2602)	
[2022-01-26 22:42:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][970/1251]	eta 0:10:22 lr 0.000014	time 2.1228 (2.2151)	loss 3.5552 (3.0073)	grad_norm 3.6212 (3.2614)	
[2022-01-26 22:42:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][980/1251]	eta 0:10:00 lr 0.000014	time 2.8559 (2.2147)	loss 2.9051 (3.0083)	grad_norm 4.2474 (3.2651)	
[2022-01-26 22:43:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][990/1251]	eta 0:09:37 lr 0.000014	time 2.1199 (2.2145)	loss 1.9479 (3.0074)	grad_norm 3.6792 (3.2644)	
[2022-01-26 22:43:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1000/1251]	eta 0:09:15 lr 0.000014	time 2.3287 (2.2145)	loss 3.3128 (3.0055)	grad_norm 2.6988 (3.2654)	
[2022-01-26 22:44:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1010/1251]	eta 0:08:53 lr 0.000014	time 1.9347 (2.2132)	loss 3.4727 (3.0024)	grad_norm 3.0692 (3.2664)	
[2022-01-26 22:44:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1020/1251]	eta 0:08:31 lr 0.000014	time 1.7228 (2.2125)	loss 3.0102 (3.0021)	grad_norm 3.3400 (3.2659)	
[2022-01-26 22:44:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1030/1251]	eta 0:08:09 lr 0.000014	time 1.5379 (2.2128)	loss 3.2774 (3.0024)	grad_norm 3.0947 (3.2656)	
[2022-01-26 22:45:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1040/1251]	eta 0:07:46 lr 0.000014	time 1.8457 (2.2122)	loss 3.3276 (3.0008)	grad_norm 3.0865 (3.2674)	
[2022-01-26 22:45:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1050/1251]	eta 0:07:24 lr 0.000014	time 2.0513 (2.2138)	loss 2.9495 (3.0011)	grad_norm 2.9009 (3.2654)	
[2022-01-26 22:45:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1060/1251]	eta 0:07:02 lr 0.000014	time 1.6678 (2.2124)	loss 2.1735 (3.0001)	grad_norm 3.2097 (3.2639)	
[2022-01-26 22:46:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1070/1251]	eta 0:06:40 lr 0.000014	time 2.0393 (2.2122)	loss 1.9612 (2.9983)	grad_norm 3.0496 (3.2642)	
[2022-01-26 22:46:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1080/1251]	eta 0:06:18 lr 0.000014	time 2.0176 (2.2106)	loss 1.9943 (2.9987)	grad_norm 3.1051 (3.2636)	
[2022-01-26 22:46:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1090/1251]	eta 0:05:56 lr 0.000014	time 2.4673 (2.2112)	loss 3.1783 (2.9981)	grad_norm 3.7536 (3.2635)	
[2022-01-26 22:47:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1100/1251]	eta 0:05:34 lr 0.000014	time 2.0514 (2.2123)	loss 3.1929 (2.9979)	grad_norm 3.7709 (3.2638)	
[2022-01-26 22:47:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1110/1251]	eta 0:05:11 lr 0.000014	time 1.7013 (2.2121)	loss 3.3491 (2.9976)	grad_norm 3.2375 (3.2633)	
[2022-01-26 22:48:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1120/1251]	eta 0:04:49 lr 0.000014	time 2.1110 (2.2126)	loss 2.8472 (3.0001)	grad_norm 3.2197 (3.2626)	
[2022-01-26 22:48:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1130/1251]	eta 0:04:27 lr 0.000014	time 1.8928 (2.2129)	loss 2.2276 (2.9999)	grad_norm 3.2999 (3.2637)	
[2022-01-26 22:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1140/1251]	eta 0:04:05 lr 0.000014	time 1.8306 (2.2114)	loss 2.0608 (2.9993)	grad_norm 3.1988 (3.2619)	
[2022-01-26 22:49:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1150/1251]	eta 0:03:43 lr 0.000014	time 1.8004 (2.2138)	loss 3.2229 (3.0003)	grad_norm 2.9931 (3.2607)	
[2022-01-26 22:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1160/1251]	eta 0:03:21 lr 0.000014	time 1.8879 (2.2124)	loss 3.2236 (3.0010)	grad_norm 3.4408 (3.2597)	
[2022-01-26 22:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1170/1251]	eta 0:02:59 lr 0.000014	time 1.7047 (2.2117)	loss 3.3353 (3.0033)	grad_norm 3.4023 (3.2607)	
[2022-01-26 22:50:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1180/1251]	eta 0:02:36 lr 0.000014	time 1.9810 (2.2105)	loss 3.2649 (3.0029)	grad_norm 3.1291 (3.2613)	
[2022-01-26 22:50:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1190/1251]	eta 0:02:14 lr 0.000014	time 1.8665 (2.2113)	loss 3.3068 (3.0040)	grad_norm 3.2373 (3.2618)	
[2022-01-26 22:50:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1200/1251]	eta 0:01:52 lr 0.000014	time 1.9440 (2.2116)	loss 2.7608 (3.0040)	grad_norm 4.2766 (3.2614)	
[2022-01-26 22:51:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1210/1251]	eta 0:01:30 lr 0.000014	time 1.8860 (2.2118)	loss 3.3050 (3.0039)	grad_norm 2.7411 (3.2606)	
[2022-01-26 22:51:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1220/1251]	eta 0:01:08 lr 0.000014	time 1.6855 (2.2113)	loss 3.0539 (3.0031)	grad_norm 2.9068 (3.2597)	
[2022-01-26 22:52:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1230/1251]	eta 0:00:46 lr 0.000014	time 2.0491 (2.2133)	loss 2.9568 (3.0034)	grad_norm 2.9403 (3.2629)	
[2022-01-26 22:52:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1240/1251]	eta 0:00:24 lr 0.000014	time 1.3482 (2.2114)	loss 2.8228 (3.0047)	grad_norm 3.2333 (3.2641)	
[2022-01-26 22:52:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [287/300][1250/1251]	eta 0:00:02 lr 0.000014	time 1.1839 (2.2058)	loss 2.8199 (3.0048)	grad_norm 4.0195 (3.2640)	
[2022-01-26 22:52:43 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 287 training takes 0:45:59
[2022-01-26 22:53:01 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.106 (18.106)	Loss 0.7713 (0.7713)	Acc@1 81.445 (81.445)	Acc@5 95.996 (95.996)	
[2022-01-26 22:53:17 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.306 (3.089)	Loss 0.7379 (0.8014)	Acc@1 83.789 (81.410)	Acc@5 95.898 (95.685)	
[2022-01-26 22:53:36 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.923 (2.491)	Loss 0.7880 (0.8149)	Acc@1 80.762 (81.138)	Acc@5 95.117 (95.406)	
[2022-01-26 22:53:52 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.964 (2.230)	Loss 0.8210 (0.8152)	Acc@1 80.566 (81.168)	Acc@5 95.508 (95.410)	
[2022-01-26 22:54:13 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.339 (2.184)	Loss 0.8074 (0.8174)	Acc@1 80.957 (81.107)	Acc@5 95.410 (95.417)	
[2022-01-26 22:54:20 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.134 Acc@5 95.422
[2022-01-26 22:54:20 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.1%
[2022-01-26 22:54:20 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.13%
[2022-01-26 22:54:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][0/1251]	eta 7:22:09 lr 0.000014	time 21.2070 (21.2070)	loss 2.9392 (2.9392)	grad_norm 3.0540 (3.0540)	
[2022-01-26 22:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][10/1251]	eta 1:17:54 lr 0.000014	time 1.6800 (3.7669)	loss 3.1183 (3.0019)	grad_norm 2.8918 (3.1362)	
[2022-01-26 22:55:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][20/1251]	eta 1:04:04 lr 0.000014	time 2.1905 (3.1229)	loss 1.9133 (2.9317)	grad_norm 3.0741 (3.2209)	
[2022-01-26 22:55:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][30/1251]	eta 0:57:37 lr 0.000014	time 2.6764 (2.8317)	loss 2.6143 (2.9594)	grad_norm 2.8418 (3.1482)	
[2022-01-26 22:56:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][40/1251]	eta 0:55:00 lr 0.000014	time 3.7084 (2.7256)	loss 3.0105 (2.9552)	grad_norm 3.2430 (3.1817)	
[2022-01-26 22:56:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][50/1251]	eta 0:52:52 lr 0.000014	time 2.4084 (2.6419)	loss 2.7274 (2.9271)	grad_norm 3.3894 (3.1668)	
[2022-01-26 22:56:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][60/1251]	eta 0:51:40 lr 0.000014	time 2.2866 (2.6033)	loss 3.2218 (2.9004)	grad_norm 3.0624 (3.1500)	
[2022-01-26 22:57:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][70/1251]	eta 0:50:07 lr 0.000014	time 1.5710 (2.5465)	loss 3.3050 (2.9348)	grad_norm 2.5106 (3.1457)	
[2022-01-26 22:57:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][80/1251]	eta 0:48:41 lr 0.000014	time 3.3214 (2.4945)	loss 3.2512 (2.9217)	grad_norm 3.3915 (3.1469)	
[2022-01-26 22:58:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][90/1251]	eta 0:47:02 lr 0.000014	time 1.7580 (2.4314)	loss 3.5964 (2.9507)	grad_norm 3.5264 (3.1947)	
[2022-01-26 22:58:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][100/1251]	eta 0:46:06 lr 0.000014	time 2.2213 (2.4036)	loss 2.5313 (2.9680)	grad_norm 3.6844 (3.2108)	
[2022-01-26 22:58:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][110/1251]	eta 0:45:33 lr 0.000014	time 3.1973 (2.3957)	loss 3.0463 (2.9789)	grad_norm 3.1890 (3.2109)	
[2022-01-26 22:59:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][120/1251]	eta 0:44:51 lr 0.000014	time 2.2979 (2.3801)	loss 3.4658 (2.9946)	grad_norm 3.6555 (3.2182)	
[2022-01-26 22:59:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][130/1251]	eta 0:44:08 lr 0.000014	time 1.7442 (2.3629)	loss 2.7048 (2.9875)	grad_norm 3.9825 (3.2183)	
[2022-01-26 22:59:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][140/1251]	eta 0:43:39 lr 0.000014	time 2.3499 (2.3574)	loss 3.0588 (2.9910)	grad_norm 3.4899 (3.2178)	
[2022-01-26 23:00:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][150/1251]	eta 0:42:57 lr 0.000014	time 2.2243 (2.3411)	loss 3.1592 (3.0020)	grad_norm 2.9540 (3.2117)	
[2022-01-26 23:00:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][160/1251]	eta 0:42:19 lr 0.000014	time 2.1415 (2.3274)	loss 3.0340 (2.9992)	grad_norm 3.0704 (3.2137)	
[2022-01-26 23:00:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][170/1251]	eta 0:41:43 lr 0.000014	time 2.5993 (2.3157)	loss 2.3121 (2.9948)	grad_norm 3.6204 (3.2080)	
[2022-01-26 23:01:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][180/1251]	eta 0:41:01 lr 0.000014	time 1.8400 (2.2982)	loss 3.3998 (3.0030)	grad_norm 3.1810 (3.2080)	
[2022-01-26 23:01:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][190/1251]	eta 0:40:30 lr 0.000014	time 1.9812 (2.2909)	loss 3.0644 (2.9899)	grad_norm 3.1586 (3.2196)	
[2022-01-26 23:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][200/1251]	eta 0:40:06 lr 0.000014	time 2.8325 (2.2896)	loss 3.1970 (2.9920)	grad_norm 3.3959 (3.2228)	
[2022-01-26 23:02:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][210/1251]	eta 0:39:35 lr 0.000014	time 2.2412 (2.2824)	loss 2.3357 (2.9979)	grad_norm 3.0070 (3.2220)	
[2022-01-26 23:02:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][220/1251]	eta 0:39:01 lr 0.000014	time 1.6962 (2.2711)	loss 2.8106 (2.9996)	grad_norm 3.4321 (3.2244)	
[2022-01-26 23:03:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][230/1251]	eta 0:38:32 lr 0.000014	time 2.1678 (2.2654)	loss 2.9607 (2.9931)	grad_norm 2.8143 (3.2220)	
[2022-01-26 23:03:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][240/1251]	eta 0:38:18 lr 0.000014	time 2.9237 (2.2734)	loss 3.1571 (2.9994)	grad_norm 3.0961 (3.2222)	
[2022-01-26 23:03:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][250/1251]	eta 0:38:01 lr 0.000014	time 3.0111 (2.2790)	loss 3.3798 (3.0117)	grad_norm 3.2415 (3.2208)	
[2022-01-26 23:04:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][260/1251]	eta 0:37:36 lr 0.000014	time 1.6931 (2.2767)	loss 3.2101 (3.0061)	grad_norm 3.1720 (3.2309)	
[2022-01-26 23:04:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][270/1251]	eta 0:37:05 lr 0.000014	time 1.9435 (2.2688)	loss 2.3765 (3.0012)	grad_norm 3.0591 (3.2330)	
[2022-01-26 23:04:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][280/1251]	eta 0:36:32 lr 0.000014	time 1.8436 (2.2585)	loss 1.8417 (3.0005)	grad_norm 2.9372 (3.2355)	
[2022-01-26 23:05:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][290/1251]	eta 0:36:11 lr 0.000014	time 2.5265 (2.2592)	loss 3.2059 (2.9977)	grad_norm 3.4084 (3.2410)	
[2022-01-26 23:05:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][300/1251]	eta 0:35:47 lr 0.000014	time 2.0426 (2.2584)	loss 2.7580 (2.9930)	grad_norm 3.0744 (3.2394)	
[2022-01-26 23:06:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][310/1251]	eta 0:35:21 lr 0.000014	time 2.2524 (2.2550)	loss 2.3574 (2.9870)	grad_norm 3.4442 (3.2375)	
[2022-01-26 23:06:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][320/1251]	eta 0:34:55 lr 0.000014	time 2.6089 (2.2507)	loss 3.1401 (2.9919)	grad_norm 2.8327 (3.2351)	
[2022-01-26 23:06:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][330/1251]	eta 0:34:28 lr 0.000014	time 1.6178 (2.2455)	loss 1.8880 (2.9879)	grad_norm 2.9240 (3.2340)	
[2022-01-26 23:07:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][340/1251]	eta 0:34:02 lr 0.000014	time 2.1344 (2.2424)	loss 3.6720 (2.9842)	grad_norm 3.2848 (3.2329)	
[2022-01-26 23:07:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][350/1251]	eta 0:33:42 lr 0.000014	time 2.3965 (2.2451)	loss 3.2950 (2.9888)	grad_norm 3.8223 (3.2339)	
[2022-01-26 23:07:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][360/1251]	eta 0:33:15 lr 0.000014	time 1.7501 (2.2391)	loss 2.9693 (2.9895)	grad_norm 3.0682 (3.2344)	
[2022-01-26 23:08:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][370/1251]	eta 0:32:50 lr 0.000014	time 2.2016 (2.2364)	loss 2.7732 (2.9887)	grad_norm 3.1806 (3.2362)	
[2022-01-26 23:08:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][380/1251]	eta 0:32:27 lr 0.000014	time 1.9817 (2.2354)	loss 3.0383 (2.9907)	grad_norm 3.4343 (3.2391)	
[2022-01-26 23:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][390/1251]	eta 0:32:07 lr 0.000014	time 2.5864 (2.2385)	loss 2.5863 (2.9885)	grad_norm 4.7172 (3.2462)	
[2022-01-26 23:09:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][400/1251]	eta 0:31:43 lr 0.000014	time 1.6615 (2.2369)	loss 3.6413 (2.9887)	grad_norm 3.3016 (3.2519)	
[2022-01-26 23:09:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][410/1251]	eta 0:31:22 lr 0.000014	time 2.6180 (2.2388)	loss 3.3337 (2.9903)	grad_norm 3.7766 (3.2552)	
[2022-01-26 23:10:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][420/1251]	eta 0:30:57 lr 0.000014	time 1.7035 (2.2352)	loss 3.2244 (2.9922)	grad_norm 3.1206 (3.2594)	
[2022-01-26 23:10:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][430/1251]	eta 0:30:34 lr 0.000014	time 2.4847 (2.2340)	loss 3.1685 (2.9956)	grad_norm 2.9228 (3.2588)	
[2022-01-26 23:10:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][440/1251]	eta 0:30:09 lr 0.000014	time 1.8425 (2.2309)	loss 3.0977 (2.9980)	grad_norm 9.0441 (3.2700)	
[2022-01-26 23:11:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][450/1251]	eta 0:29:46 lr 0.000014	time 2.3804 (2.2309)	loss 3.4291 (2.9958)	grad_norm 3.3089 (3.2723)	
[2022-01-26 23:11:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][460/1251]	eta 0:29:23 lr 0.000014	time 1.6850 (2.2295)	loss 2.4741 (2.9931)	grad_norm 3.4681 (3.2765)	
[2022-01-26 23:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][470/1251]	eta 0:29:03 lr 0.000014	time 2.6647 (2.2324)	loss 3.4892 (2.9953)	grad_norm 3.4630 (3.2750)	
[2022-01-26 23:12:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][480/1251]	eta 0:28:39 lr 0.000014	time 1.5818 (2.2305)	loss 1.8862 (2.9936)	grad_norm 3.4257 (3.2719)	
[2022-01-26 23:12:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][490/1251]	eta 0:28:15 lr 0.000014	time 2.4957 (2.2280)	loss 3.4200 (2.9930)	grad_norm 3.2347 (3.2687)	
[2022-01-26 23:12:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][500/1251]	eta 0:27:52 lr 0.000014	time 1.8990 (2.2274)	loss 2.0120 (2.9927)	grad_norm 2.9383 (3.2755)	
[2022-01-26 23:13:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][510/1251]	eta 0:27:30 lr 0.000014	time 1.7993 (2.2271)	loss 3.0695 (2.9907)	grad_norm 3.0899 (3.2740)	
[2022-01-26 23:13:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][520/1251]	eta 0:27:07 lr 0.000014	time 1.9953 (2.2261)	loss 2.5341 (2.9879)	grad_norm 2.9080 (3.2752)	
[2022-01-26 23:14:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][530/1251]	eta 0:26:44 lr 0.000014	time 2.6274 (2.2260)	loss 3.5641 (2.9872)	grad_norm 3.4124 (3.2744)	
[2022-01-26 23:14:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][540/1251]	eta 0:26:21 lr 0.000014	time 1.9545 (2.2247)	loss 2.9428 (2.9877)	grad_norm 2.7947 (3.2771)	
[2022-01-26 23:14:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][550/1251]	eta 0:25:59 lr 0.000014	time 1.8544 (2.2250)	loss 3.3276 (2.9870)	grad_norm 2.8511 (3.2756)	
[2022-01-26 23:15:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][560/1251]	eta 0:25:36 lr 0.000014	time 1.8938 (2.2239)	loss 2.9903 (2.9860)	grad_norm 3.0910 (3.2788)	
[2022-01-26 23:15:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][570/1251]	eta 0:25:13 lr 0.000014	time 2.0794 (2.2229)	loss 2.9271 (2.9891)	grad_norm 4.1515 (3.2799)	
[2022-01-26 23:15:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][580/1251]	eta 0:24:51 lr 0.000014	time 2.1197 (2.2222)	loss 3.1408 (2.9939)	grad_norm 3.3944 (3.2777)	
[2022-01-26 23:16:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][590/1251]	eta 0:24:28 lr 0.000014	time 1.8997 (2.2210)	loss 2.5063 (2.9957)	grad_norm 2.8351 (3.2821)	
[2022-01-26 23:16:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][600/1251]	eta 0:24:04 lr 0.000014	time 2.2205 (2.2194)	loss 3.1232 (2.9973)	grad_norm 2.9730 (3.2859)	
[2022-01-26 23:16:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][610/1251]	eta 0:23:42 lr 0.000014	time 2.4959 (2.2190)	loss 3.3737 (2.9979)	grad_norm 3.6052 (3.2873)	
[2022-01-26 23:17:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][620/1251]	eta 0:23:20 lr 0.000014	time 2.1095 (2.2190)	loss 3.3775 (2.9985)	grad_norm 4.4275 (3.2843)	
[2022-01-26 23:17:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][630/1251]	eta 0:22:55 lr 0.000014	time 1.9876 (2.2156)	loss 3.4712 (3.0004)	grad_norm 4.1694 (3.2863)	
[2022-01-26 23:17:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][640/1251]	eta 0:22:31 lr 0.000014	time 1.9306 (2.2119)	loss 3.3415 (2.9993)	grad_norm 2.6142 (3.2823)	
[2022-01-26 23:18:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][650/1251]	eta 0:22:09 lr 0.000014	time 2.2140 (2.2123)	loss 2.6433 (3.0016)	grad_norm 2.9035 (3.2816)	
[2022-01-26 23:18:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][660/1251]	eta 0:21:46 lr 0.000014	time 1.9488 (2.2106)	loss 2.4207 (2.9995)	grad_norm 3.8856 (3.2828)	
[2022-01-26 23:19:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][670/1251]	eta 0:21:24 lr 0.000014	time 2.1893 (2.2101)	loss 3.3905 (2.9980)	grad_norm 3.1551 (3.2844)	
[2022-01-26 23:19:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][680/1251]	eta 0:21:02 lr 0.000014	time 2.1508 (2.2114)	loss 3.3869 (2.9954)	grad_norm 3.3852 (3.2843)	
[2022-01-26 23:19:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][690/1251]	eta 0:20:39 lr 0.000014	time 1.7720 (2.2093)	loss 3.6296 (2.9959)	grad_norm 3.1224 (3.2808)	
[2022-01-26 23:20:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][700/1251]	eta 0:20:17 lr 0.000014	time 1.8144 (2.2104)	loss 3.6014 (2.9917)	grad_norm 2.9007 (3.2784)	
[2022-01-26 23:20:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][710/1251]	eta 0:19:56 lr 0.000014	time 2.2913 (2.2115)	loss 3.2568 (2.9935)	grad_norm 3.2793 (3.2774)	
[2022-01-26 23:20:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][720/1251]	eta 0:19:34 lr 0.000014	time 2.2747 (2.2118)	loss 3.2732 (2.9898)	grad_norm 3.4181 (3.2783)	
[2022-01-26 23:21:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][730/1251]	eta 0:19:12 lr 0.000014	time 1.9061 (2.2126)	loss 3.5605 (2.9926)	grad_norm 2.6021 (3.2756)	
[2022-01-26 23:21:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][740/1251]	eta 0:18:50 lr 0.000014	time 1.6518 (2.2123)	loss 3.0436 (2.9911)	grad_norm 3.2255 (3.2761)	
[2022-01-26 23:22:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][750/1251]	eta 0:18:28 lr 0.000014	time 2.2353 (2.2130)	loss 3.4092 (2.9933)	grad_norm 3.3775 (3.2760)	
[2022-01-26 23:22:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][760/1251]	eta 0:18:04 lr 0.000014	time 1.8311 (2.2093)	loss 3.0521 (2.9947)	grad_norm 3.2882 (3.2776)	
[2022-01-26 23:22:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][770/1251]	eta 0:17:41 lr 0.000014	time 1.7761 (2.2070)	loss 2.6882 (2.9924)	grad_norm 3.5578 (3.2799)	
[2022-01-26 23:23:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][780/1251]	eta 0:17:18 lr 0.000014	time 1.8600 (2.2058)	loss 3.3335 (2.9939)	grad_norm 3.3396 (3.2819)	
[2022-01-26 23:23:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][790/1251]	eta 0:16:56 lr 0.000014	time 1.7919 (2.2045)	loss 2.7011 (2.9954)	grad_norm 3.2898 (3.2818)	
[2022-01-26 23:23:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][800/1251]	eta 0:16:34 lr 0.000013	time 1.5204 (2.2052)	loss 2.2750 (2.9925)	grad_norm 2.9556 (3.2804)	
[2022-01-26 23:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][810/1251]	eta 0:16:13 lr 0.000013	time 3.1732 (2.2068)	loss 2.3800 (2.9919)	grad_norm 3.4111 (3.2783)	
[2022-01-26 23:24:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][820/1251]	eta 0:15:51 lr 0.000013	time 2.7574 (2.2084)	loss 2.0171 (2.9907)	grad_norm 3.3664 (3.2801)	
[2022-01-26 23:24:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][830/1251]	eta 0:15:30 lr 0.000013	time 1.9315 (2.2099)	loss 3.4307 (2.9917)	grad_norm 2.8915 (3.2794)	
[2022-01-26 23:25:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][840/1251]	eta 0:15:07 lr 0.000013	time 1.6325 (2.2083)	loss 2.6973 (2.9926)	grad_norm 3.2343 (3.2775)	
[2022-01-26 23:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][850/1251]	eta 0:14:44 lr 0.000013	time 2.2278 (2.2066)	loss 2.4846 (2.9896)	grad_norm 2.8346 (3.2771)	
[2022-01-26 23:25:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][860/1251]	eta 0:14:22 lr 0.000013	time 2.1770 (2.2053)	loss 3.6255 (2.9920)	grad_norm 3.0525 (3.2772)	
[2022-01-26 23:26:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][870/1251]	eta 0:13:59 lr 0.000013	time 1.9366 (2.2043)	loss 3.2745 (2.9936)	grad_norm 3.1760 (3.2748)	
[2022-01-26 23:26:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][880/1251]	eta 0:13:37 lr 0.000013	time 2.4058 (2.2039)	loss 2.8580 (2.9928)	grad_norm 3.5289 (3.2764)	
[2022-01-26 23:27:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][890/1251]	eta 0:13:15 lr 0.000013	time 1.9785 (2.2028)	loss 3.3133 (2.9964)	grad_norm 3.2055 (3.2788)	
[2022-01-26 23:27:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][900/1251]	eta 0:12:53 lr 0.000013	time 3.2662 (2.2045)	loss 3.3622 (2.9953)	grad_norm 3.0913 (3.2768)	
[2022-01-26 23:27:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][910/1251]	eta 0:12:31 lr 0.000013	time 1.7690 (2.2045)	loss 2.2471 (2.9969)	grad_norm 3.2047 (3.2760)	
[2022-01-26 23:28:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][920/1251]	eta 0:12:09 lr 0.000013	time 2.1142 (2.2042)	loss 3.2452 (2.9978)	grad_norm 3.2106 (3.2793)	
[2022-01-26 23:28:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][930/1251]	eta 0:11:47 lr 0.000013	time 1.9070 (2.2039)	loss 3.0233 (2.9987)	grad_norm 2.9499 (3.2782)	
[2022-01-26 23:28:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][940/1251]	eta 0:11:25 lr 0.000013	time 2.0162 (2.2038)	loss 2.7904 (2.9977)	grad_norm 3.3206 (3.2773)	
[2022-01-26 23:29:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][950/1251]	eta 0:11:03 lr 0.000013	time 2.1911 (2.2035)	loss 3.3156 (2.9978)	grad_norm 3.0789 (3.2767)	
[2022-01-26 23:29:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][960/1251]	eta 0:10:41 lr 0.000013	time 2.8524 (2.2044)	loss 3.3387 (2.9962)	grad_norm 3.0232 (3.2772)	
[2022-01-26 23:29:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][970/1251]	eta 0:10:18 lr 0.000013	time 1.6694 (2.2025)	loss 1.8607 (2.9937)	grad_norm 3.3142 (3.2891)	
[2022-01-26 23:30:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][980/1251]	eta 0:09:56 lr 0.000013	time 1.9021 (2.2009)	loss 3.2663 (2.9929)	grad_norm 2.7577 (3.2912)	
[2022-01-26 23:30:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][990/1251]	eta 0:09:34 lr 0.000013	time 2.1285 (2.1998)	loss 2.2477 (2.9914)	grad_norm 3.1635 (3.2884)	
[2022-01-26 23:31:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1000/1251]	eta 0:09:11 lr 0.000013	time 1.8663 (2.1981)	loss 2.5266 (2.9875)	grad_norm 3.0656 (3.2884)	
[2022-01-26 23:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1010/1251]	eta 0:08:49 lr 0.000013	time 2.1627 (2.1979)	loss 2.9583 (2.9869)	grad_norm 3.0110 (3.2876)	
[2022-01-26 23:31:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1020/1251]	eta 0:08:27 lr 0.000013	time 2.0226 (2.1983)	loss 3.5279 (2.9844)	grad_norm 3.3208 (3.2881)	
[2022-01-26 23:32:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1030/1251]	eta 0:08:05 lr 0.000013	time 2.1087 (2.1979)	loss 3.1017 (2.9868)	grad_norm 3.8446 (3.2900)	
[2022-01-26 23:32:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1040/1251]	eta 0:07:43 lr 0.000013	time 2.1602 (2.1990)	loss 3.3635 (2.9868)	grad_norm 3.1041 (3.2887)	
[2022-01-26 23:32:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1050/1251]	eta 0:07:22 lr 0.000013	time 2.2137 (2.1999)	loss 2.2148 (2.9842)	grad_norm 3.0369 (3.2860)	
[2022-01-26 23:33:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1060/1251]	eta 0:07:00 lr 0.000013	time 2.0522 (2.2004)	loss 3.2419 (2.9831)	grad_norm 2.9634 (3.2856)	
[2022-01-26 23:33:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1070/1251]	eta 0:06:38 lr 0.000013	time 2.2328 (2.2013)	loss 3.0304 (2.9847)	grad_norm 3.4167 (3.2867)	
[2022-01-26 23:34:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1080/1251]	eta 0:06:16 lr 0.000013	time 2.8696 (2.2033)	loss 2.9094 (2.9853)	grad_norm 3.4032 (3.2887)	
[2022-01-26 23:34:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1090/1251]	eta 0:05:54 lr 0.000013	time 3.1572 (2.2045)	loss 3.3070 (2.9863)	grad_norm 3.8378 (3.2892)	
[2022-01-26 23:34:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1100/1251]	eta 0:05:32 lr 0.000013	time 1.9929 (2.2020)	loss 3.6609 (2.9875)	grad_norm 3.3397 (3.2885)	
[2022-01-26 23:35:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1110/1251]	eta 0:05:10 lr 0.000013	time 1.9131 (2.1988)	loss 2.4785 (2.9858)	grad_norm 3.4825 (3.2880)	
[2022-01-26 23:35:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1120/1251]	eta 0:04:47 lr 0.000013	time 2.5940 (2.1973)	loss 2.1038 (2.9849)	grad_norm 3.7163 (3.2869)	
[2022-01-26 23:35:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1130/1251]	eta 0:04:25 lr 0.000013	time 2.7487 (2.1977)	loss 3.2974 (2.9856)	grad_norm 3.2171 (3.2855)	
[2022-01-26 23:36:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1140/1251]	eta 0:04:03 lr 0.000013	time 1.5674 (2.1967)	loss 2.6994 (2.9827)	grad_norm 3.8031 (3.2856)	
[2022-01-26 23:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1150/1251]	eta 0:03:41 lr 0.000013	time 2.5517 (2.1970)	loss 2.2736 (2.9805)	grad_norm 2.9943 (3.2850)	
[2022-01-26 23:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1160/1251]	eta 0:03:19 lr 0.000013	time 2.3757 (2.1971)	loss 3.2061 (2.9793)	grad_norm 2.9125 (3.2840)	
[2022-01-26 23:37:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1170/1251]	eta 0:02:58 lr 0.000013	time 2.5628 (2.1976)	loss 2.5332 (2.9799)	grad_norm 3.1367 (3.2838)	
[2022-01-26 23:37:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1180/1251]	eta 0:02:36 lr 0.000013	time 1.9823 (2.1981)	loss 2.7735 (2.9805)	grad_norm 2.9327 (3.2812)	
[2022-01-26 23:37:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1190/1251]	eta 0:02:14 lr 0.000013	time 2.4960 (2.1987)	loss 3.3160 (2.9812)	grad_norm 3.0454 (3.2806)	
[2022-01-26 23:38:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1200/1251]	eta 0:01:52 lr 0.000013	time 3.3814 (2.2011)	loss 2.7519 (2.9833)	grad_norm 3.0083 (3.2787)	
[2022-01-26 23:38:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1210/1251]	eta 0:01:30 lr 0.000013	time 2.1928 (2.2017)	loss 3.1305 (2.9825)	grad_norm 2.8633 (3.2768)	
[2022-01-26 23:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1220/1251]	eta 0:01:08 lr 0.000013	time 1.8472 (2.2023)	loss 2.8093 (2.9821)	grad_norm 3.1547 (3.2753)	
[2022-01-26 23:39:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1230/1251]	eta 0:00:46 lr 0.000013	time 1.8982 (2.2006)	loss 2.1165 (2.9820)	grad_norm 2.5967 (3.2742)	
[2022-01-26 23:39:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1240/1251]	eta 0:00:24 lr 0.000013	time 2.0326 (2.1981)	loss 3.5239 (2.9832)	grad_norm 3.3634 (3.2741)	
[2022-01-26 23:40:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [288/300][1250/1251]	eta 0:00:02 lr 0.000013	time 1.2095 (2.1918)	loss 2.9077 (2.9826)	grad_norm 3.1282 (3.2736)	
[2022-01-26 23:40:02 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 288 training takes 0:45:42
[2022-01-26 23:40:21 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.368 (18.368)	Loss 0.8143 (0.8143)	Acc@1 81.152 (81.152)	Acc@5 95.508 (95.508)	
[2022-01-26 23:40:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.388 (3.307)	Loss 0.8247 (0.8287)	Acc@1 80.957 (80.513)	Acc@5 95.312 (95.321)	
[2022-01-26 23:40:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.921 (2.633)	Loss 0.7405 (0.8149)	Acc@1 83.203 (80.771)	Acc@5 96.289 (95.526)	
[2022-01-26 23:41:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.981 (2.384)	Loss 0.8253 (0.8142)	Acc@1 80.566 (80.922)	Acc@5 95.410 (95.423)	
[2022-01-26 23:41:32 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.554 (2.195)	Loss 0.7951 (0.8149)	Acc@1 81.055 (80.955)	Acc@5 95.898 (95.408)	
[2022-01-26 23:41:41 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.144 Acc@5 95.460
[2022-01-26 23:41:41 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.1%
[2022-01-26 23:41:41 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.14%
[2022-01-26 23:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][0/1251]	eta 7:33:40 lr 0.000013	time 21.7592 (21.7592)	loss 2.8313 (2.8313)	grad_norm 3.9046 (3.9046)	
[2022-01-26 23:42:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][10/1251]	eta 1:22:32 lr 0.000013	time 2.2460 (3.9909)	loss 2.8443 (2.8880)	grad_norm 3.2474 (4.0118)	
[2022-01-26 23:42:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][20/1251]	eta 1:04:27 lr 0.000013	time 1.5192 (3.1414)	loss 3.3149 (2.9019)	grad_norm 3.1799 (3.5471)	
[2022-01-26 23:43:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][30/1251]	eta 0:57:32 lr 0.000013	time 1.5841 (2.8280)	loss 2.7297 (2.8860)	grad_norm 3.3661 (3.4762)	
[2022-01-26 23:43:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][40/1251]	eta 0:55:24 lr 0.000013	time 3.7773 (2.7452)	loss 3.2264 (2.8762)	grad_norm 2.6097 (3.4599)	
[2022-01-26 23:43:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][50/1251]	eta 0:53:48 lr 0.000013	time 2.7439 (2.6878)	loss 2.3114 (2.8551)	grad_norm 2.9918 (3.3799)	
[2022-01-26 23:44:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][60/1251]	eta 0:51:54 lr 0.000013	time 1.9285 (2.6146)	loss 3.1804 (2.8661)	grad_norm 2.8682 (3.3555)	
[2022-01-26 23:44:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][70/1251]	eta 0:50:13 lr 0.000013	time 1.8501 (2.5512)	loss 2.0029 (2.8827)	grad_norm 3.1434 (3.3113)	
[2022-01-26 23:45:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][80/1251]	eta 0:48:44 lr 0.000013	time 2.1918 (2.4975)	loss 3.4541 (2.8902)	grad_norm 3.4055 (3.3116)	
[2022-01-26 23:45:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][90/1251]	eta 0:47:39 lr 0.000013	time 2.6787 (2.4630)	loss 3.1760 (2.8869)	grad_norm 3.0774 (3.3135)	
[2022-01-26 23:45:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][100/1251]	eta 0:46:44 lr 0.000013	time 2.2213 (2.4365)	loss 2.5383 (2.8920)	grad_norm 2.8249 (3.3194)	
[2022-01-26 23:46:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][110/1251]	eta 0:45:35 lr 0.000013	time 1.7834 (2.3975)	loss 3.0715 (2.9001)	grad_norm 3.0446 (3.3162)	
[2022-01-26 23:46:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][120/1251]	eta 0:44:46 lr 0.000013	time 2.5221 (2.3751)	loss 3.0857 (2.8945)	grad_norm 3.1816 (3.3213)	
[2022-01-26 23:46:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][130/1251]	eta 0:43:54 lr 0.000013	time 2.2374 (2.3498)	loss 2.0834 (2.8926)	grad_norm 3.3728 (3.3204)	
[2022-01-26 23:47:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][140/1251]	eta 0:43:18 lr 0.000013	time 2.7462 (2.3385)	loss 3.2446 (2.9097)	grad_norm 2.9157 (3.3180)	
[2022-01-26 23:47:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][150/1251]	eta 0:42:51 lr 0.000013	time 2.1446 (2.3357)	loss 3.3561 (2.9116)	grad_norm 2.8093 (3.3183)	
[2022-01-26 23:47:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][160/1251]	eta 0:42:29 lr 0.000013	time 3.2678 (2.3370)	loss 2.9563 (2.9209)	grad_norm 3.4766 (3.3153)	
[2022-01-26 23:48:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][170/1251]	eta 0:41:57 lr 0.000013	time 1.8813 (2.3291)	loss 2.5495 (2.9250)	grad_norm 3.6801 (3.3132)	
[2022-01-26 23:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][180/1251]	eta 0:41:37 lr 0.000013	time 3.3992 (2.3321)	loss 2.4780 (2.9207)	grad_norm 3.1909 (3.3100)	
[2022-01-26 23:49:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][190/1251]	eta 0:41:01 lr 0.000013	time 2.4505 (2.3196)	loss 3.0884 (2.9215)	grad_norm 3.3811 (3.3135)	
[2022-01-26 23:49:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][200/1251]	eta 0:40:22 lr 0.000013	time 2.1606 (2.3049)	loss 2.1656 (2.9115)	grad_norm 3.2131 (3.3010)	
[2022-01-26 23:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][210/1251]	eta 0:39:47 lr 0.000013	time 1.9479 (2.2937)	loss 2.2547 (2.9178)	grad_norm 3.0305 (3.2863)	
[2022-01-26 23:50:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][220/1251]	eta 0:39:21 lr 0.000013	time 1.7635 (2.2907)	loss 2.6245 (2.9318)	grad_norm 2.9516 (3.2835)	
[2022-01-26 23:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][230/1251]	eta 0:39:00 lr 0.000013	time 2.1343 (2.2922)	loss 3.1193 (2.9414)	grad_norm 3.1425 (3.2793)	
[2022-01-26 23:50:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][240/1251]	eta 0:38:33 lr 0.000013	time 2.4059 (2.2887)	loss 2.8371 (2.9438)	grad_norm 3.1385 (3.2821)	
[2022-01-26 23:51:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][250/1251]	eta 0:38:03 lr 0.000013	time 1.8989 (2.2814)	loss 2.4324 (2.9396)	grad_norm 3.2473 (3.2759)	
[2022-01-26 23:51:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][260/1251]	eta 0:37:32 lr 0.000013	time 1.7965 (2.2733)	loss 2.3463 (2.9395)	grad_norm 3.2189 (3.2701)	
[2022-01-26 23:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][270/1251]	eta 0:37:03 lr 0.000013	time 1.8541 (2.2663)	loss 2.9572 (2.9337)	grad_norm 3.0672 (3.2769)	
[2022-01-26 23:52:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][280/1251]	eta 0:36:35 lr 0.000013	time 1.7882 (2.2612)	loss 3.3526 (2.9350)	grad_norm 3.1017 (3.2784)	
[2022-01-26 23:52:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][290/1251]	eta 0:36:11 lr 0.000013	time 2.5978 (2.2601)	loss 3.4101 (2.9419)	grad_norm 3.1553 (3.2756)	
[2022-01-26 23:53:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][300/1251]	eta 0:35:46 lr 0.000013	time 1.5904 (2.2573)	loss 3.4157 (2.9440)	grad_norm 2.6826 (3.2732)	
[2022-01-26 23:53:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][310/1251]	eta 0:35:22 lr 0.000013	time 2.6089 (2.2558)	loss 3.2654 (2.9400)	grad_norm 3.7587 (3.2658)	
[2022-01-26 23:53:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][320/1251]	eta 0:34:57 lr 0.000013	time 1.8354 (2.2528)	loss 3.4477 (2.9430)	grad_norm 3.8919 (3.2706)	
[2022-01-26 23:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][330/1251]	eta 0:34:34 lr 0.000013	time 1.9065 (2.2523)	loss 3.1339 (2.9435)	grad_norm 3.0635 (3.2691)	
[2022-01-26 23:54:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][340/1251]	eta 0:34:07 lr 0.000013	time 1.9417 (2.2477)	loss 3.0221 (2.9441)	grad_norm 3.4044 (3.2715)	
[2022-01-26 23:54:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][350/1251]	eta 0:33:42 lr 0.000013	time 2.7838 (2.2444)	loss 3.0239 (2.9457)	grad_norm 2.8330 (3.2655)	
[2022-01-26 23:55:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][360/1251]	eta 0:33:15 lr 0.000013	time 1.9184 (2.2400)	loss 2.2543 (2.9486)	grad_norm 3.4190 (3.2676)	
[2022-01-26 23:55:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][370/1251]	eta 0:32:52 lr 0.000013	time 1.6026 (2.2391)	loss 3.5225 (2.9511)	grad_norm 4.7315 (3.2768)	
[2022-01-26 23:55:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][380/1251]	eta 0:32:28 lr 0.000013	time 2.0578 (2.2368)	loss 2.9984 (2.9442)	grad_norm 3.7329 (3.2793)	
[2022-01-26 23:56:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][390/1251]	eta 0:32:06 lr 0.000013	time 2.2730 (2.2379)	loss 3.9036 (2.9504)	grad_norm 3.5333 (3.2812)	
[2022-01-26 23:56:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][400/1251]	eta 0:31:47 lr 0.000013	time 1.7295 (2.2416)	loss 3.2330 (2.9492)	grad_norm 3.0227 (3.2815)	
[2022-01-26 23:57:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][410/1251]	eta 0:31:28 lr 0.000013	time 1.7577 (2.2450)	loss 3.2826 (2.9473)	grad_norm 3.3081 (3.2832)	
[2022-01-26 23:57:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][420/1251]	eta 0:31:02 lr 0.000013	time 1.6162 (2.2408)	loss 2.0560 (2.9416)	grad_norm 3.0812 (3.2801)	
[2022-01-26 23:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][430/1251]	eta 0:30:38 lr 0.000013	time 2.1934 (2.2393)	loss 2.8269 (2.9452)	grad_norm 3.2115 (3.2817)	
[2022-01-26 23:58:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][440/1251]	eta 0:30:11 lr 0.000013	time 1.6976 (2.2338)	loss 2.8896 (2.9445)	grad_norm 3.2532 (3.2823)	
[2022-01-26 23:58:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][450/1251]	eta 0:29:46 lr 0.000013	time 1.8097 (2.2304)	loss 2.2997 (2.9444)	grad_norm 3.4452 (3.2818)	
[2022-01-26 23:58:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][460/1251]	eta 0:29:25 lr 0.000013	time 2.1947 (2.2315)	loss 3.6025 (2.9442)	grad_norm 3.8731 (3.2789)	
[2022-01-26 23:59:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][470/1251]	eta 0:29:01 lr 0.000013	time 2.4205 (2.2301)	loss 2.8552 (2.9475)	grad_norm 3.1179 (3.2798)	
[2022-01-26 23:59:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][480/1251]	eta 0:28:37 lr 0.000013	time 1.8921 (2.2277)	loss 3.5833 (2.9495)	grad_norm 3.4786 (3.2781)	
[2022-01-26 23:59:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][490/1251]	eta 0:28:14 lr 0.000013	time 2.0803 (2.2264)	loss 2.1004 (2.9434)	grad_norm 3.4352 (3.2770)	
[2022-01-27 00:00:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][500/1251]	eta 0:27:53 lr 0.000013	time 2.4564 (2.2286)	loss 3.1737 (2.9482)	grad_norm 3.6717 (3.2768)	
[2022-01-27 00:00:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][510/1251]	eta 0:27:33 lr 0.000013	time 3.4023 (2.2316)	loss 2.0964 (2.9474)	grad_norm 2.9545 (3.2738)	
[2022-01-27 00:01:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][520/1251]	eta 0:27:12 lr 0.000013	time 1.5060 (2.2334)	loss 3.0595 (2.9514)	grad_norm 2.9523 (3.2745)	
[2022-01-27 00:01:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][530/1251]	eta 0:26:49 lr 0.000013	time 1.9220 (2.2324)	loss 3.1394 (2.9526)	grad_norm 3.2882 (3.2781)	
[2022-01-27 00:01:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][540/1251]	eta 0:26:24 lr 0.000013	time 1.7392 (2.2289)	loss 3.3540 (2.9557)	grad_norm 3.5920 (3.2785)	
[2022-01-27 00:02:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][550/1251]	eta 0:26:00 lr 0.000013	time 1.8894 (2.2264)	loss 3.2622 (2.9581)	grad_norm 3.4919 (3.2788)	
[2022-01-27 00:02:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][560/1251]	eta 0:25:37 lr 0.000013	time 1.9872 (2.2250)	loss 3.2510 (2.9581)	grad_norm 4.0691 (3.2789)	
[2022-01-27 00:02:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][570/1251]	eta 0:25:13 lr 0.000013	time 1.9224 (2.2218)	loss 2.7926 (2.9557)	grad_norm 4.2299 (3.2812)	
[2022-01-27 00:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][580/1251]	eta 0:24:50 lr 0.000013	time 1.8170 (2.2206)	loss 2.4947 (2.9591)	grad_norm 3.2033 (3.2820)	
[2022-01-27 00:03:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][590/1251]	eta 0:24:26 lr 0.000013	time 1.8960 (2.2186)	loss 3.5375 (2.9604)	grad_norm 3.6499 (3.2820)	
[2022-01-27 00:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][600/1251]	eta 0:24:05 lr 0.000013	time 2.0406 (2.2197)	loss 3.2126 (2.9594)	grad_norm 2.8086 (3.2798)	
[2022-01-27 00:04:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][610/1251]	eta 0:23:43 lr 0.000013	time 2.7263 (2.2209)	loss 3.5559 (2.9622)	grad_norm 3.6673 (3.2806)	
[2022-01-27 00:04:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][620/1251]	eta 0:23:20 lr 0.000013	time 2.2106 (2.2192)	loss 3.2546 (2.9623)	grad_norm 3.6535 (3.2812)	
[2022-01-27 00:05:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][630/1251]	eta 0:22:58 lr 0.000013	time 2.2327 (2.2192)	loss 3.5591 (2.9588)	grad_norm 3.3688 (3.2800)	
[2022-01-27 00:05:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][640/1251]	eta 0:22:34 lr 0.000013	time 1.5681 (2.2165)	loss 2.8184 (2.9576)	grad_norm 3.6991 (3.2825)	
[2022-01-27 00:05:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][650/1251]	eta 0:22:13 lr 0.000013	time 2.7486 (2.2182)	loss 3.1517 (2.9563)	grad_norm 3.4293 (3.2815)	
[2022-01-27 00:06:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][660/1251]	eta 0:21:50 lr 0.000013	time 2.1636 (2.2174)	loss 3.2140 (2.9578)	grad_norm 3.1645 (3.2837)	
[2022-01-27 00:06:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][670/1251]	eta 0:21:29 lr 0.000013	time 2.0714 (2.2188)	loss 3.0169 (2.9579)	grad_norm 2.8888 (3.2835)	
[2022-01-27 00:06:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][680/1251]	eta 0:21:07 lr 0.000013	time 1.8975 (2.2198)	loss 3.2255 (2.9562)	grad_norm 3.7114 (3.2885)	
[2022-01-27 00:07:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][690/1251]	eta 0:20:45 lr 0.000013	time 2.5084 (2.2202)	loss 2.5652 (2.9551)	grad_norm 3.1332 (3.2886)	
[2022-01-27 00:07:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][700/1251]	eta 0:20:22 lr 0.000013	time 1.5826 (2.2191)	loss 3.7356 (2.9567)	grad_norm 3.1988 (3.2866)	
[2022-01-27 00:07:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][710/1251]	eta 0:19:59 lr 0.000013	time 1.8154 (2.2163)	loss 2.6546 (2.9547)	grad_norm 2.8283 (3.2852)	
[2022-01-27 00:08:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][720/1251]	eta 0:19:34 lr 0.000013	time 1.9264 (2.2120)	loss 3.1352 (2.9545)	grad_norm 3.1333 (3.2833)	
[2022-01-27 00:08:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][730/1251]	eta 0:19:10 lr 0.000013	time 1.7221 (2.2083)	loss 3.0000 (2.9575)	grad_norm 2.9829 (3.2829)	
[2022-01-27 00:08:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][740/1251]	eta 0:18:47 lr 0.000013	time 2.0093 (2.2066)	loss 3.2018 (2.9555)	grad_norm 2.8173 (3.2813)	
[2022-01-27 00:09:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][750/1251]	eta 0:18:25 lr 0.000013	time 2.1702 (2.2064)	loss 3.4390 (2.9578)	grad_norm 3.2325 (3.2814)	
[2022-01-27 00:09:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][760/1251]	eta 0:18:02 lr 0.000013	time 1.4595 (2.2055)	loss 2.2417 (2.9602)	grad_norm 3.4255 (3.2820)	
[2022-01-27 00:10:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][770/1251]	eta 0:17:40 lr 0.000013	time 1.9955 (2.2047)	loss 3.0836 (2.9573)	grad_norm 3.4943 (3.2823)	
[2022-01-27 00:10:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][780/1251]	eta 0:17:18 lr 0.000013	time 2.7762 (2.2054)	loss 3.1839 (2.9602)	grad_norm 2.8293 (3.2827)	
[2022-01-27 00:10:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][790/1251]	eta 0:16:57 lr 0.000013	time 2.0731 (2.2067)	loss 1.8622 (2.9586)	grad_norm 2.8703 (3.2825)	
[2022-01-27 00:11:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][800/1251]	eta 0:16:35 lr 0.000013	time 1.9089 (2.2074)	loss 3.3829 (2.9601)	grad_norm 2.9359 (3.2820)	
[2022-01-27 00:11:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][810/1251]	eta 0:16:13 lr 0.000013	time 2.5386 (2.2086)	loss 3.5228 (2.9627)	grad_norm 3.4563 (3.2802)	
[2022-01-27 00:11:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][820/1251]	eta 0:15:52 lr 0.000013	time 2.5561 (2.2096)	loss 3.1703 (2.9651)	grad_norm 3.8098 (3.2801)	
[2022-01-27 00:12:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][830/1251]	eta 0:15:30 lr 0.000013	time 2.1588 (2.2095)	loss 2.7400 (2.9638)	grad_norm 3.0133 (3.2794)	
[2022-01-27 00:12:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][840/1251]	eta 0:15:08 lr 0.000013	time 2.3878 (2.2099)	loss 1.9477 (2.9618)	grad_norm 2.5566 (3.2782)	
[2022-01-27 00:13:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][850/1251]	eta 0:14:46 lr 0.000013	time 1.9335 (2.2118)	loss 2.9078 (2.9636)	grad_norm 4.7209 (3.2810)	
[2022-01-27 00:13:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][860/1251]	eta 0:14:25 lr 0.000013	time 3.0392 (2.2136)	loss 3.1279 (2.9668)	grad_norm 3.2657 (3.2802)	
[2022-01-27 00:13:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][870/1251]	eta 0:14:02 lr 0.000013	time 2.0977 (2.2124)	loss 2.7659 (2.9657)	grad_norm 3.4213 (3.2784)	
[2022-01-27 00:14:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][880/1251]	eta 0:13:39 lr 0.000013	time 1.8131 (2.2086)	loss 3.2248 (2.9677)	grad_norm 2.8497 (3.2784)	
[2022-01-27 00:14:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][890/1251]	eta 0:13:16 lr 0.000013	time 1.9061 (2.2066)	loss 3.6139 (2.9694)	grad_norm 3.1774 (3.2820)	
[2022-01-27 00:14:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][900/1251]	eta 0:12:54 lr 0.000013	time 2.3703 (2.2051)	loss 2.3319 (2.9669)	grad_norm 2.6517 (3.2793)	
[2022-01-27 00:15:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][910/1251]	eta 0:12:32 lr 0.000013	time 3.0604 (2.2053)	loss 2.5609 (2.9640)	grad_norm 3.0570 (3.2775)	
[2022-01-27 00:15:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][920/1251]	eta 0:12:10 lr 0.000013	time 2.1932 (2.2055)	loss 3.3070 (2.9648)	grad_norm 3.5555 (3.2771)	
[2022-01-27 00:15:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][930/1251]	eta 0:11:48 lr 0.000013	time 2.4702 (2.2076)	loss 3.5984 (2.9685)	grad_norm 3.2975 (3.2766)	
[2022-01-27 00:16:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][940/1251]	eta 0:11:26 lr 0.000013	time 1.8413 (2.2075)	loss 3.2539 (2.9690)	grad_norm 3.4933 (3.2782)	
[2022-01-27 00:16:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][950/1251]	eta 0:11:05 lr 0.000013	time 3.7248 (2.2096)	loss 2.9389 (2.9699)	grad_norm 2.6451 (3.2773)	
[2022-01-27 00:17:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][960/1251]	eta 0:10:42 lr 0.000013	time 1.7348 (2.2083)	loss 2.7984 (2.9686)	grad_norm 3.7093 (3.2752)	
[2022-01-27 00:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][970/1251]	eta 0:10:20 lr 0.000013	time 1.8901 (2.2074)	loss 3.1576 (2.9682)	grad_norm 3.5230 (3.2757)	
[2022-01-27 00:17:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][980/1251]	eta 0:09:58 lr 0.000013	time 1.9942 (2.2067)	loss 3.0274 (2.9684)	grad_norm 3.0463 (3.2739)	
[2022-01-27 00:18:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][990/1251]	eta 0:09:36 lr 0.000013	time 2.4346 (2.2069)	loss 2.3236 (2.9691)	grad_norm 3.6693 (3.2727)	
[2022-01-27 00:18:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1000/1251]	eta 0:09:13 lr 0.000013	time 2.0113 (2.2047)	loss 2.9220 (2.9696)	grad_norm 3.0831 (3.2760)	
[2022-01-27 00:18:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1010/1251]	eta 0:08:50 lr 0.000013	time 2.1663 (2.2031)	loss 2.9853 (2.9706)	grad_norm 2.6913 (3.2748)	
[2022-01-27 00:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1020/1251]	eta 0:08:28 lr 0.000013	time 1.9676 (2.2032)	loss 3.0641 (2.9708)	grad_norm 3.4319 (3.2769)	
[2022-01-27 00:19:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1030/1251]	eta 0:08:07 lr 0.000013	time 2.3701 (2.2037)	loss 3.1476 (2.9703)	grad_norm 3.4008 (3.2753)	
[2022-01-27 00:19:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1040/1251]	eta 0:07:45 lr 0.000013	time 2.3860 (2.2046)	loss 3.5545 (2.9704)	grad_norm 3.4613 (3.2749)	
[2022-01-27 00:20:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1050/1251]	eta 0:07:23 lr 0.000013	time 2.8015 (2.2055)	loss 2.8206 (2.9700)	grad_norm 3.1635 (3.2746)	
[2022-01-27 00:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1060/1251]	eta 0:07:01 lr 0.000013	time 1.5467 (2.2065)	loss 3.1726 (2.9698)	grad_norm 3.1088 (3.2760)	
[2022-01-27 00:21:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1070/1251]	eta 0:06:39 lr 0.000013	time 2.4362 (2.2081)	loss 3.3465 (2.9670)	grad_norm 3.0004 (3.2762)	
[2022-01-27 00:21:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1080/1251]	eta 0:06:17 lr 0.000013	time 1.6782 (2.2065)	loss 3.6873 (2.9685)	grad_norm 4.8611 (3.2787)	
[2022-01-27 00:21:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1090/1251]	eta 0:05:54 lr 0.000013	time 1.9247 (2.2039)	loss 3.2325 (2.9696)	grad_norm 3.2523 (3.2790)	
[2022-01-27 00:22:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1100/1251]	eta 0:05:32 lr 0.000013	time 1.8613 (2.2013)	loss 2.8059 (2.9697)	grad_norm 3.8744 (3.2782)	
[2022-01-27 00:22:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1110/1251]	eta 0:05:10 lr 0.000013	time 2.5885 (2.2017)	loss 3.3069 (2.9697)	grad_norm 4.2096 (3.2819)	
[2022-01-27 00:22:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1120/1251]	eta 0:04:48 lr 0.000013	time 1.9341 (2.2006)	loss 3.4095 (2.9694)	grad_norm 3.7759 (3.2840)	
[2022-01-27 00:23:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1130/1251]	eta 0:04:26 lr 0.000013	time 1.9344 (2.2004)	loss 3.5068 (2.9703)	grad_norm 3.6388 (3.2836)	
[2022-01-27 00:23:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1140/1251]	eta 0:04:04 lr 0.000013	time 1.7642 (2.2006)	loss 3.7875 (2.9700)	grad_norm 3.2351 (3.2825)	
[2022-01-27 00:23:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1150/1251]	eta 0:03:42 lr 0.000013	time 3.0524 (2.2027)	loss 2.0141 (2.9686)	grad_norm 3.1639 (3.2829)	
[2022-01-27 00:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1160/1251]	eta 0:03:20 lr 0.000013	time 3.2729 (2.2054)	loss 3.4635 (2.9699)	grad_norm 3.4382 (3.2830)	
[2022-01-27 00:24:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1170/1251]	eta 0:02:58 lr 0.000013	time 2.0760 (2.2059)	loss 3.0069 (2.9694)	grad_norm 3.0787 (3.2830)	
[2022-01-27 00:25:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1180/1251]	eta 0:02:36 lr 0.000013	time 1.5699 (2.2047)	loss 2.8213 (2.9693)	grad_norm 2.6017 (3.2813)	
[2022-01-27 00:25:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1190/1251]	eta 0:02:14 lr 0.000013	time 3.7565 (2.2044)	loss 3.3561 (2.9706)	grad_norm 2.8593 (3.2818)	
[2022-01-27 00:25:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1200/1251]	eta 0:01:52 lr 0.000013	time 2.7643 (2.2050)	loss 3.5890 (2.9716)	grad_norm 3.3966 (3.2813)	
[2022-01-27 00:26:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1210/1251]	eta 0:01:30 lr 0.000013	time 1.7925 (2.2035)	loss 3.2927 (2.9706)	grad_norm 3.4657 (3.2822)	
[2022-01-27 00:26:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1220/1251]	eta 0:01:08 lr 0.000013	time 1.9873 (2.2018)	loss 2.8017 (2.9705)	grad_norm 3.1469 (3.2822)	
[2022-01-27 00:26:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1230/1251]	eta 0:00:46 lr 0.000013	time 2.9786 (2.2025)	loss 2.9716 (2.9707)	grad_norm 2.6594 (3.2802)	
[2022-01-27 00:27:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1240/1251]	eta 0:00:24 lr 0.000013	time 1.9418 (2.2019)	loss 3.3323 (2.9700)	grad_norm 3.0583 (3.2803)	
[2022-01-27 00:27:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [289/300][1250/1251]	eta 0:00:02 lr 0.000013	time 1.1896 (2.1962)	loss 3.5848 (2.9704)	grad_norm 3.4274 (3.2801)	
[2022-01-27 00:27:29 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 289 training takes 0:45:48
[2022-01-27 00:27:47 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.446 (18.446)	Loss 0.8076 (0.8076)	Acc@1 79.980 (79.980)	Acc@5 95.703 (95.703)	
[2022-01-27 00:28:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.617 (3.481)	Loss 0.7912 (0.7929)	Acc@1 82.422 (81.490)	Acc@5 94.922 (95.801)	
[2022-01-27 00:28:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.609 (2.636)	Loss 0.8267 (0.8027)	Acc@1 81.250 (81.310)	Acc@5 95.410 (95.573)	
[2022-01-27 00:28:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.556 (2.244)	Loss 0.7450 (0.8062)	Acc@1 82.520 (81.272)	Acc@5 95.508 (95.483)	
[2022-01-27 00:29:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 4.151 (2.210)	Loss 0.7639 (0.8144)	Acc@1 82.715 (81.031)	Acc@5 95.996 (95.436)	
[2022-01-27 00:29:07 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.120 Acc@5 95.438
[2022-01-27 00:29:07 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.1%
[2022-01-27 00:29:07 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.14%
[2022-01-27 00:29:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][0/1251]	eta 7:29:58 lr 0.000013	time 21.5819 (21.5819)	loss 2.8772 (2.8772)	grad_norm 3.5191 (3.5191)	
[2022-01-27 00:29:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][10/1251]	eta 1:24:24 lr 0.000013	time 1.7598 (4.0808)	loss 3.1223 (3.0184)	grad_norm 3.1954 (3.5617)	
[2022-01-27 00:30:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][20/1251]	eta 1:05:56 lr 0.000013	time 1.7850 (3.2138)	loss 2.4755 (2.9764)	grad_norm 3.0638 (3.4252)	
[2022-01-27 00:30:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][30/1251]	eta 0:59:44 lr 0.000013	time 1.8864 (2.9360)	loss 2.3443 (2.9749)	grad_norm 3.1273 (3.3706)	
[2022-01-27 00:31:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][40/1251]	eta 0:55:53 lr 0.000013	time 3.4143 (2.7690)	loss 3.2203 (2.9718)	grad_norm 2.8046 (3.3606)	
[2022-01-27 00:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][50/1251]	eta 0:53:10 lr 0.000013	time 1.5638 (2.6564)	loss 2.4615 (2.9480)	grad_norm 2.9846 (3.3093)	
[2022-01-27 00:31:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][60/1251]	eta 0:51:14 lr 0.000013	time 1.5053 (2.5813)	loss 2.6444 (2.9140)	grad_norm 4.3990 (3.3033)	
[2022-01-27 00:32:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][70/1251]	eta 0:49:30 lr 0.000013	time 1.7788 (2.5151)	loss 3.0180 (2.8853)	grad_norm 2.4781 (3.2692)	
[2022-01-27 00:32:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][80/1251]	eta 0:48:34 lr 0.000013	time 3.5968 (2.4888)	loss 3.4362 (2.9051)	grad_norm 3.1447 (3.2786)	
[2022-01-27 00:32:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][90/1251]	eta 0:47:16 lr 0.000013	time 1.5403 (2.4431)	loss 2.1557 (2.9231)	grad_norm 3.0199 (3.2774)	
[2022-01-27 00:33:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][100/1251]	eta 0:46:13 lr 0.000013	time 2.3187 (2.4094)	loss 2.3253 (2.9266)	grad_norm 3.1371 (3.2786)	
[2022-01-27 00:33:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][110/1251]	eta 0:45:14 lr 0.000013	time 2.2481 (2.3791)	loss 2.1417 (2.9337)	grad_norm 3.4450 (3.2874)	
[2022-01-27 00:33:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][120/1251]	eta 0:44:42 lr 0.000013	time 3.1191 (2.3722)	loss 3.3475 (2.9523)	grad_norm 2.7359 (3.2758)	
[2022-01-27 00:34:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][130/1251]	eta 0:44:08 lr 0.000013	time 2.1602 (2.3630)	loss 3.5256 (2.9457)	grad_norm 2.9733 (3.2796)	
[2022-01-27 00:34:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][140/1251]	eta 0:43:32 lr 0.000013	time 2.0084 (2.3511)	loss 3.5011 (2.9562)	grad_norm 3.2465 (3.2755)	
[2022-01-27 00:35:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][150/1251]	eta 0:43:05 lr 0.000013	time 2.4367 (2.3481)	loss 3.5620 (2.9591)	grad_norm 2.8318 (3.2803)	
[2022-01-27 00:35:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][160/1251]	eta 0:42:46 lr 0.000013	time 3.1228 (2.3528)	loss 2.7937 (2.9622)	grad_norm 3.0558 (3.2832)	
[2022-01-27 00:35:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][170/1251]	eta 0:42:04 lr 0.000013	time 1.8546 (2.3356)	loss 3.0436 (2.9765)	grad_norm 4.2479 (3.2928)	
[2022-01-27 00:36:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][180/1251]	eta 0:41:28 lr 0.000013	time 1.8533 (2.3232)	loss 3.3024 (2.9808)	grad_norm 2.8141 (3.2822)	
[2022-01-27 00:36:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][190/1251]	eta 0:40:51 lr 0.000013	time 1.9868 (2.3107)	loss 3.1300 (2.9780)	grad_norm 2.9523 (3.2717)	
[2022-01-27 00:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][200/1251]	eta 0:40:26 lr 0.000013	time 2.2305 (2.3087)	loss 2.0250 (2.9750)	grad_norm 3.3126 (3.2712)	
[2022-01-27 00:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][210/1251]	eta 0:39:51 lr 0.000013	time 1.9160 (2.2976)	loss 3.1488 (2.9829)	grad_norm 3.1758 (3.2659)	
[2022-01-27 00:37:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][220/1251]	eta 0:39:20 lr 0.000013	time 1.8737 (2.2895)	loss 3.2565 (2.9706)	grad_norm 3.2808 (3.2728)	
[2022-01-27 00:37:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][230/1251]	eta 0:38:53 lr 0.000013	time 2.1101 (2.2851)	loss 3.1953 (2.9669)	grad_norm 3.7361 (3.2776)	
[2022-01-27 00:38:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][240/1251]	eta 0:38:36 lr 0.000013	time 1.9188 (2.2914)	loss 2.0283 (2.9641)	grad_norm 3.4675 (3.2714)	
[2022-01-27 00:38:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][250/1251]	eta 0:38:13 lr 0.000013	time 2.1539 (2.2913)	loss 3.3063 (2.9673)	grad_norm 3.1955 (3.2681)	
[2022-01-27 00:39:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][260/1251]	eta 0:37:41 lr 0.000013	time 1.7645 (2.2821)	loss 3.2938 (2.9776)	grad_norm 3.3253 (3.2747)	
[2022-01-27 00:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][270/1251]	eta 0:37:05 lr 0.000013	time 1.6631 (2.2687)	loss 2.9192 (2.9764)	grad_norm 3.1954 (3.2729)	
[2022-01-27 00:39:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][280/1251]	eta 0:36:40 lr 0.000013	time 2.1748 (2.2657)	loss 3.5630 (2.9830)	grad_norm 3.3373 (3.2692)	
[2022-01-27 00:40:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][290/1251]	eta 0:36:11 lr 0.000013	time 2.2346 (2.2598)	loss 2.6576 (2.9684)	grad_norm 3.6698 (3.2700)	
[2022-01-27 00:40:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][300/1251]	eta 0:35:46 lr 0.000013	time 2.1960 (2.2572)	loss 2.6347 (2.9634)	grad_norm 3.4328 (3.2676)	
[2022-01-27 00:40:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][310/1251]	eta 0:35:17 lr 0.000013	time 1.9124 (2.2506)	loss 3.3398 (2.9653)	grad_norm 3.6715 (3.2643)	
[2022-01-27 00:41:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][320/1251]	eta 0:34:51 lr 0.000013	time 2.2379 (2.2465)	loss 3.6236 (2.9666)	grad_norm 4.4460 (3.2633)	
[2022-01-27 00:41:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][330/1251]	eta 0:34:27 lr 0.000013	time 1.8530 (2.2452)	loss 3.3122 (2.9712)	grad_norm 2.8319 (3.2654)	
[2022-01-27 00:41:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][340/1251]	eta 0:34:06 lr 0.000013	time 2.8289 (2.2465)	loss 2.7428 (2.9735)	grad_norm 3.2241 (3.2701)	
[2022-01-27 00:42:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][350/1251]	eta 0:33:45 lr 0.000013	time 2.1665 (2.2477)	loss 2.9526 (2.9762)	grad_norm 3.4874 (3.2692)	
[2022-01-27 00:42:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][360/1251]	eta 0:33:22 lr 0.000013	time 1.8276 (2.2472)	loss 2.8924 (2.9744)	grad_norm 4.3950 (3.2680)	
[2022-01-27 00:43:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][370/1251]	eta 0:33:00 lr 0.000013	time 1.9606 (2.2479)	loss 3.3347 (2.9708)	grad_norm 2.8278 (3.2624)	
[2022-01-27 00:43:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][380/1251]	eta 0:32:38 lr 0.000013	time 3.0755 (2.2490)	loss 3.4046 (2.9762)	grad_norm 3.2993 (3.2653)	
[2022-01-27 00:43:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][390/1251]	eta 0:32:16 lr 0.000013	time 2.4752 (2.2493)	loss 3.2582 (2.9790)	grad_norm 3.7793 (3.2691)	
[2022-01-27 00:44:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][400/1251]	eta 0:31:51 lr 0.000013	time 1.8947 (2.2465)	loss 2.2233 (2.9752)	grad_norm 2.7704 (3.2707)	
[2022-01-27 00:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][410/1251]	eta 0:31:24 lr 0.000013	time 1.9994 (2.2412)	loss 2.8475 (2.9775)	grad_norm 4.0743 (3.2727)	
[2022-01-27 00:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][420/1251]	eta 0:31:00 lr 0.000013	time 2.6101 (2.2391)	loss 2.9287 (2.9777)	grad_norm 2.8529 (3.2753)	
[2022-01-27 00:45:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][430/1251]	eta 0:30:36 lr 0.000013	time 1.9194 (2.2366)	loss 2.9994 (2.9840)	grad_norm 2.8651 (3.2786)	
[2022-01-27 00:45:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][440/1251]	eta 0:30:14 lr 0.000013	time 1.5826 (2.2379)	loss 3.3027 (2.9861)	grad_norm 3.6403 (3.2819)	
[2022-01-27 00:45:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][450/1251]	eta 0:29:51 lr 0.000013	time 1.8974 (2.2365)	loss 3.2738 (2.9829)	grad_norm 3.9342 (3.2845)	
[2022-01-27 00:46:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][460/1251]	eta 0:29:28 lr 0.000013	time 1.8224 (2.2360)	loss 2.0670 (2.9838)	grad_norm 3.3959 (3.2844)	
[2022-01-27 00:46:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][470/1251]	eta 0:29:04 lr 0.000013	time 1.5787 (2.2332)	loss 2.0000 (2.9851)	grad_norm 3.1561 (3.2844)	
[2022-01-27 00:47:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][480/1251]	eta 0:28:39 lr 0.000013	time 1.5961 (2.2306)	loss 3.0369 (2.9874)	grad_norm 3.0634 (3.2808)	
[2022-01-27 00:47:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][490/1251]	eta 0:28:17 lr 0.000013	time 1.5325 (2.2301)	loss 3.4315 (2.9868)	grad_norm 3.3916 (3.2772)	
[2022-01-27 00:47:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][500/1251]	eta 0:27:55 lr 0.000012	time 1.8736 (2.2305)	loss 2.9210 (2.9825)	grad_norm 3.3133 (3.2759)	
[2022-01-27 00:48:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][510/1251]	eta 0:27:32 lr 0.000012	time 1.5734 (2.2300)	loss 1.9970 (2.9811)	grad_norm 2.8610 (3.2708)	
[2022-01-27 00:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][520/1251]	eta 0:27:10 lr 0.000012	time 2.0108 (2.2299)	loss 1.9949 (2.9786)	grad_norm 2.9770 (3.2755)	
[2022-01-27 00:48:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][530/1251]	eta 0:26:45 lr 0.000012	time 1.6314 (2.2271)	loss 2.2255 (2.9799)	grad_norm 3.0946 (3.2770)	
[2022-01-27 00:49:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][540/1251]	eta 0:26:21 lr 0.000012	time 1.9026 (2.2245)	loss 3.3192 (2.9737)	grad_norm 2.9705 (3.2846)	
[2022-01-27 00:49:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][550/1251]	eta 0:26:00 lr 0.000012	time 2.0455 (2.2256)	loss 2.7689 (2.9757)	grad_norm 2.8496 (3.2812)	
[2022-01-27 00:49:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][560/1251]	eta 0:25:38 lr 0.000012	time 1.8934 (2.2269)	loss 2.8948 (2.9780)	grad_norm 3.3339 (3.2873)	
[2022-01-27 00:50:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][570/1251]	eta 0:25:14 lr 0.000012	time 1.9256 (2.2241)	loss 3.2404 (2.9794)	grad_norm 4.1986 (3.2915)	
[2022-01-27 00:50:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][580/1251]	eta 0:24:49 lr 0.000012	time 1.7666 (2.2201)	loss 2.3860 (2.9788)	grad_norm 2.9504 (3.2918)	
[2022-01-27 00:51:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][590/1251]	eta 0:24:32 lr 0.000012	time 2.5037 (2.2281)	loss 2.3170 (2.9781)	grad_norm 3.3715 (3.2901)	
[2022-01-27 00:51:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][600/1251]	eta 0:24:11 lr 0.000012	time 1.8952 (2.2298)	loss 3.4599 (2.9801)	grad_norm 3.1826 (3.2905)	
[2022-01-27 00:51:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][610/1251]	eta 0:23:50 lr 0.000012	time 2.2126 (2.2313)	loss 2.2573 (2.9749)	grad_norm 3.4875 (3.2885)	
[2022-01-27 00:52:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][620/1251]	eta 0:23:27 lr 0.000012	time 2.2624 (2.2300)	loss 2.7975 (2.9771)	grad_norm 3.3202 (3.2919)	
[2022-01-27 00:52:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][630/1251]	eta 0:23:01 lr 0.000012	time 1.8261 (2.2246)	loss 2.3392 (2.9772)	grad_norm 2.9067 (3.2894)	
[2022-01-27 00:52:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][640/1251]	eta 0:22:37 lr 0.000012	time 2.6366 (2.2214)	loss 3.2552 (2.9783)	grad_norm 2.7951 (3.2883)	
[2022-01-27 00:53:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][650/1251]	eta 0:22:14 lr 0.000012	time 1.9899 (2.2212)	loss 2.9906 (2.9792)	grad_norm 3.1831 (3.2877)	
[2022-01-27 00:53:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][660/1251]	eta 0:21:52 lr 0.000012	time 1.8897 (2.2215)	loss 3.2999 (2.9754)	grad_norm 3.1435 (3.2854)	
[2022-01-27 00:53:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][670/1251]	eta 0:21:31 lr 0.000012	time 1.8756 (2.2235)	loss 2.3897 (2.9743)	grad_norm 3.0756 (3.2845)	
[2022-01-27 00:54:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][680/1251]	eta 0:21:10 lr 0.000012	time 2.6959 (2.2248)	loss 2.1920 (2.9701)	grad_norm 3.6734 (3.2829)	
[2022-01-27 00:54:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][690/1251]	eta 0:20:48 lr 0.000012	time 1.9843 (2.2249)	loss 3.3178 (2.9720)	grad_norm 2.7863 (3.2802)	
[2022-01-27 00:55:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][700/1251]	eta 0:20:24 lr 0.000012	time 1.9239 (2.2219)	loss 2.4291 (2.9753)	grad_norm 2.7544 (3.2777)	
[2022-01-27 00:55:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][710/1251]	eta 0:20:00 lr 0.000012	time 1.9212 (2.2196)	loss 2.5459 (2.9753)	grad_norm 2.9263 (3.2766)	
[2022-01-27 00:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][720/1251]	eta 0:19:36 lr 0.000012	time 1.9198 (2.2160)	loss 2.7556 (2.9756)	grad_norm 3.6773 (3.2805)	
[2022-01-27 00:56:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][730/1251]	eta 0:19:14 lr 0.000012	time 2.2960 (2.2158)	loss 3.2819 (2.9703)	grad_norm 2.7193 (3.2788)	
[2022-01-27 00:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][740/1251]	eta 0:18:52 lr 0.000012	time 2.1469 (2.2153)	loss 2.6756 (2.9702)	grad_norm 3.3452 (3.2808)	
[2022-01-27 00:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][750/1251]	eta 0:18:29 lr 0.000012	time 1.9376 (2.2154)	loss 2.0106 (2.9696)	grad_norm 3.3286 (3.2843)	
[2022-01-27 00:57:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][760/1251]	eta 0:18:07 lr 0.000012	time 1.8632 (2.2155)	loss 3.2219 (2.9700)	grad_norm 3.5656 (3.2841)	
[2022-01-27 00:57:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][770/1251]	eta 0:17:47 lr 0.000012	time 2.3932 (2.2191)	loss 2.2925 (2.9678)	grad_norm 4.2579 (3.2836)	
[2022-01-27 00:58:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][780/1251]	eta 0:17:25 lr 0.000012	time 2.1060 (2.2190)	loss 3.2234 (2.9686)	grad_norm 3.1361 (3.2851)	
[2022-01-27 00:58:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][790/1251]	eta 0:17:02 lr 0.000012	time 2.1994 (2.2176)	loss 2.9033 (2.9669)	grad_norm 2.7400 (3.2847)	
[2022-01-27 00:58:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][800/1251]	eta 0:16:39 lr 0.000012	time 1.9776 (2.2152)	loss 3.1693 (2.9693)	grad_norm 2.8980 (3.2827)	
[2022-01-27 00:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][810/1251]	eta 0:16:15 lr 0.000012	time 1.9696 (2.2122)	loss 3.4755 (2.9717)	grad_norm 3.1519 (3.2810)	
[2022-01-27 00:59:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][820/1251]	eta 0:15:52 lr 0.000012	time 1.9269 (2.2097)	loss 2.7787 (2.9710)	grad_norm 3.7016 (3.2878)	
[2022-01-27 00:59:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][830/1251]	eta 0:15:29 lr 0.000012	time 1.9254 (2.2090)	loss 3.2807 (2.9726)	grad_norm 2.9538 (3.2867)	
[2022-01-27 01:00:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][840/1251]	eta 0:15:07 lr 0.000012	time 1.9435 (2.2081)	loss 2.8886 (2.9728)	grad_norm 3.0710 (3.2847)	
[2022-01-27 01:00:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][850/1251]	eta 0:14:45 lr 0.000012	time 1.7679 (2.2075)	loss 3.1469 (2.9735)	grad_norm 3.5392 (3.2845)	
[2022-01-27 01:00:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][860/1251]	eta 0:14:24 lr 0.000012	time 1.9391 (2.2108)	loss 2.6307 (2.9739)	grad_norm 3.2848 (3.2851)	
[2022-01-27 01:01:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][870/1251]	eta 0:14:03 lr 0.000012	time 3.0864 (2.2131)	loss 3.3904 (2.9739)	grad_norm 3.3330 (3.2833)	
[2022-01-27 01:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][880/1251]	eta 0:13:41 lr 0.000012	time 1.8256 (2.2154)	loss 2.9587 (2.9719)	grad_norm 3.1854 (3.2834)	
[2022-01-27 01:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][890/1251]	eta 0:13:19 lr 0.000012	time 2.2476 (2.2149)	loss 1.8656 (2.9699)	grad_norm 2.9788 (3.2831)	
[2022-01-27 01:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][900/1251]	eta 0:12:56 lr 0.000012	time 1.8516 (2.2121)	loss 3.5303 (2.9707)	grad_norm 5.0108 (3.2836)	
[2022-01-27 01:02:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][910/1251]	eta 0:12:33 lr 0.000012	time 2.1495 (2.2108)	loss 2.3793 (2.9712)	grad_norm 2.8808 (3.2822)	
[2022-01-27 01:03:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][920/1251]	eta 0:12:11 lr 0.000012	time 1.9359 (2.2095)	loss 3.5837 (2.9727)	grad_norm 3.1937 (3.2815)	
[2022-01-27 01:03:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][930/1251]	eta 0:11:49 lr 0.000012	time 1.9033 (2.2089)	loss 1.9208 (2.9736)	grad_norm 3.7465 (3.2818)	
[2022-01-27 01:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][940/1251]	eta 0:11:27 lr 0.000012	time 1.8889 (2.2100)	loss 2.9621 (2.9734)	grad_norm 3.3211 (3.2821)	
[2022-01-27 01:04:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][950/1251]	eta 0:11:05 lr 0.000012	time 1.9065 (2.2096)	loss 2.0001 (2.9726)	grad_norm 3.1867 (3.2827)	
[2022-01-27 01:04:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][960/1251]	eta 0:10:43 lr 0.000012	time 1.7721 (2.2119)	loss 2.4660 (2.9725)	grad_norm 3.1049 (3.2807)	
[2022-01-27 01:04:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][970/1251]	eta 0:10:21 lr 0.000012	time 2.2183 (2.2115)	loss 3.1732 (2.9735)	grad_norm 3.3358 (3.2794)	
[2022-01-27 01:05:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][980/1251]	eta 0:09:59 lr 0.000012	time 2.2776 (2.2108)	loss 3.2208 (2.9746)	grad_norm 3.0699 (3.2797)	
[2022-01-27 01:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][990/1251]	eta 0:09:36 lr 0.000012	time 1.6001 (2.2099)	loss 2.9889 (2.9723)	grad_norm 3.4490 (3.2799)	
[2022-01-27 01:05:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1000/1251]	eta 0:09:14 lr 0.000012	time 1.6502 (2.2090)	loss 3.3723 (2.9701)	grad_norm 3.0917 (3.2798)	
[2022-01-27 01:06:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1010/1251]	eta 0:08:52 lr 0.000012	time 2.2659 (2.2089)	loss 3.3685 (2.9703)	grad_norm 5.0911 (3.2820)	
[2022-01-27 01:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1020/1251]	eta 0:08:30 lr 0.000012	time 1.9546 (2.2082)	loss 1.9527 (2.9684)	grad_norm 3.0746 (3.2820)	
[2022-01-27 01:07:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1030/1251]	eta 0:08:07 lr 0.000012	time 1.9088 (2.2063)	loss 2.0936 (2.9684)	grad_norm 3.1174 (3.2816)	
[2022-01-27 01:07:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1040/1251]	eta 0:07:45 lr 0.000012	time 2.1101 (2.2051)	loss 1.9883 (2.9685)	grad_norm 5.1182 (3.2829)	
[2022-01-27 01:07:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1050/1251]	eta 0:07:23 lr 0.000012	time 2.2721 (2.2058)	loss 3.3164 (2.9693)	grad_norm 3.7702 (3.2813)	
[2022-01-27 01:08:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1060/1251]	eta 0:07:01 lr 0.000012	time 1.7967 (2.2054)	loss 3.2188 (2.9686)	grad_norm 2.8566 (3.2816)	
[2022-01-27 01:08:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1070/1251]	eta 0:06:38 lr 0.000012	time 2.2574 (2.2044)	loss 2.9215 (2.9673)	grad_norm 3.0162 (3.2792)	
[2022-01-27 01:08:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1080/1251]	eta 0:06:17 lr 0.000012	time 1.5821 (2.2077)	loss 1.9404 (2.9678)	grad_norm 3.1437 (3.2799)	
[2022-01-27 01:09:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1090/1251]	eta 0:05:55 lr 0.000012	time 1.8189 (2.2087)	loss 3.4613 (2.9677)	grad_norm 4.0154 (3.2806)	
[2022-01-27 01:09:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1100/1251]	eta 0:05:33 lr 0.000012	time 1.8902 (2.2078)	loss 2.4093 (2.9660)	grad_norm 2.6563 (3.2786)	
[2022-01-27 01:10:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1110/1251]	eta 0:05:11 lr 0.000012	time 1.9469 (2.2079)	loss 3.1161 (2.9657)	grad_norm 3.1398 (3.2771)	
[2022-01-27 01:10:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1120/1251]	eta 0:04:49 lr 0.000012	time 1.6501 (2.2100)	loss 3.2311 (2.9637)	grad_norm 3.0526 (3.2753)	
[2022-01-27 01:10:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1130/1251]	eta 0:04:27 lr 0.000012	time 1.7115 (2.2079)	loss 3.1315 (2.9649)	grad_norm 3.2768 (3.2751)	
[2022-01-27 01:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1140/1251]	eta 0:04:04 lr 0.000012	time 1.7428 (2.2062)	loss 3.0491 (2.9641)	grad_norm 3.0116 (3.2742)	
[2022-01-27 01:11:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1150/1251]	eta 0:03:42 lr 0.000012	time 1.8931 (2.2051)	loss 2.6164 (2.9653)	grad_norm 3.6289 (3.2731)	
[2022-01-27 01:11:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1160/1251]	eta 0:03:20 lr 0.000012	time 2.2554 (2.2058)	loss 3.6536 (2.9628)	grad_norm 3.7712 (3.2735)	
[2022-01-27 01:12:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1170/1251]	eta 0:02:58 lr 0.000012	time 2.1768 (2.2058)	loss 3.4397 (2.9639)	grad_norm 2.9938 (3.2740)	
[2022-01-27 01:12:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1180/1251]	eta 0:02:36 lr 0.000012	time 2.4721 (2.2060)	loss 3.0637 (2.9655)	grad_norm 2.7686 (3.2751)	
[2022-01-27 01:12:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1190/1251]	eta 0:02:14 lr 0.000012	time 1.8766 (2.2049)	loss 2.1689 (2.9641)	grad_norm 2.7844 (3.2757)	
[2022-01-27 01:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1200/1251]	eta 0:01:52 lr 0.000012	time 1.6794 (2.2053)	loss 2.4336 (2.9641)	grad_norm 3.0774 (3.2757)	
[2022-01-27 01:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1210/1251]	eta 0:01:30 lr 0.000012	time 1.8762 (2.2046)	loss 2.4541 (2.9655)	grad_norm 2.5553 (3.2733)	
[2022-01-27 01:13:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1220/1251]	eta 0:01:08 lr 0.000012	time 1.9505 (2.2041)	loss 3.3279 (2.9668)	grad_norm 3.0109 (3.2708)	
[2022-01-27 01:14:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1230/1251]	eta 0:00:46 lr 0.000012	time 2.2453 (2.2041)	loss 3.2445 (2.9668)	grad_norm 3.1655 (3.2699)	
[2022-01-27 01:14:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1240/1251]	eta 0:00:24 lr 0.000012	time 1.2463 (2.2034)	loss 2.7795 (2.9676)	grad_norm 2.7776 (3.2691)	
[2022-01-27 01:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [290/300][1250/1251]	eta 0:00:02 lr 0.000012	time 1.2887 (2.1978)	loss 3.2564 (2.9657)	grad_norm 3.6787 (3.2688)	
[2022-01-27 01:14:56 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 290 training takes 0:45:49
[2022-01-27 01:14:56 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_290 saving......
[2022-01-27 01:15:08 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_290 saved !!!
[2022-01-27 01:15:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.690 (16.690)	Loss 0.8451 (0.8451)	Acc@1 79.785 (79.785)	Acc@5 95.312 (95.312)	
[2022-01-27 01:15:41 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.522 (3.078)	Loss 0.7920 (0.8105)	Acc@1 80.078 (81.161)	Acc@5 95.898 (95.419)	
[2022-01-27 01:15:54 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 1.510 (2.227)	Loss 0.8559 (0.8116)	Acc@1 79.883 (81.283)	Acc@5 94.727 (95.410)	
[2022-01-27 01:16:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.009 (2.048)	Loss 0.8161 (0.8083)	Acc@1 81.250 (81.297)	Acc@5 95.605 (95.492)	
[2022-01-27 01:16:29 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.719 (1.995)	Loss 0.7978 (0.8111)	Acc@1 81.934 (81.271)	Acc@5 96.289 (95.460)	
[2022-01-27 01:16:37 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.238 Acc@5 95.436
[2022-01-27 01:16:37 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.2%
[2022-01-27 01:16:37 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.24%
[2022-01-27 01:16:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][0/1251]	eta 7:18:10 lr 0.000012	time 21.0153 (21.0153)	loss 2.8622 (2.8622)	grad_norm 3.7472 (3.7472)	
[2022-01-27 01:17:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][10/1251]	eta 1:24:23 lr 0.000012	time 1.9319 (4.0800)	loss 3.3978 (3.0968)	grad_norm 3.4704 (3.3263)	
[2022-01-27 01:17:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][20/1251]	eta 1:05:37 lr 0.000012	time 1.4363 (3.1989)	loss 3.0916 (3.0236)	grad_norm 4.0449 (3.3326)	
[2022-01-27 01:18:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][30/1251]	eta 0:58:44 lr 0.000012	time 1.5320 (2.8863)	loss 3.2156 (2.9998)	grad_norm 3.0731 (3.3884)	
[2022-01-27 01:18:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][40/1251]	eta 0:55:56 lr 0.000012	time 3.8630 (2.7719)	loss 2.2528 (2.9467)	grad_norm 2.8265 (3.3532)	
[2022-01-27 01:18:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][50/1251]	eta 0:54:08 lr 0.000012	time 2.5737 (2.7050)	loss 2.2410 (2.9052)	grad_norm 3.2186 (3.3374)	
[2022-01-27 01:19:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][60/1251]	eta 0:51:57 lr 0.000012	time 2.0172 (2.6172)	loss 3.4174 (2.9072)	grad_norm 2.8910 (3.2946)	
[2022-01-27 01:19:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][70/1251]	eta 0:49:39 lr 0.000012	time 1.7615 (2.5226)	loss 2.3918 (2.9449)	grad_norm 3.1403 (3.2996)	
[2022-01-27 01:19:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][80/1251]	eta 0:48:20 lr 0.000012	time 3.0262 (2.4766)	loss 3.2577 (2.9732)	grad_norm 3.2991 (3.3319)	
[2022-01-27 01:20:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][90/1251]	eta 0:47:02 lr 0.000012	time 2.3798 (2.4307)	loss 2.7312 (2.9496)	grad_norm 3.3439 (3.3327)	
[2022-01-27 01:20:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][100/1251]	eta 0:46:23 lr 0.000012	time 3.5244 (2.4181)	loss 2.5419 (2.9710)	grad_norm 3.0818 (3.3284)	
[2022-01-27 01:21:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][110/1251]	eta 0:45:37 lr 0.000012	time 1.8983 (2.3994)	loss 2.7212 (2.9746)	grad_norm 2.7761 (3.3068)	
[2022-01-27 01:21:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][120/1251]	eta 0:45:02 lr 0.000012	time 2.7901 (2.3899)	loss 3.0991 (2.9640)	grad_norm 3.6177 (3.3117)	
[2022-01-27 01:21:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][130/1251]	eta 0:44:17 lr 0.000012	time 3.2319 (2.3706)	loss 3.2910 (2.9796)	grad_norm 3.5752 (3.3002)	
[2022-01-27 01:22:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][140/1251]	eta 0:43:28 lr 0.000012	time 2.1646 (2.3482)	loss 2.2937 (2.9794)	grad_norm 3.8549 (3.2967)	
[2022-01-27 01:22:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][150/1251]	eta 0:42:48 lr 0.000012	time 2.0156 (2.3332)	loss 3.4523 (2.9843)	grad_norm 4.0058 (3.3261)	
[2022-01-27 01:22:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][160/1251]	eta 0:42:22 lr 0.000012	time 2.9275 (2.3304)	loss 3.6178 (2.9725)	grad_norm 3.1112 (3.3283)	
[2022-01-27 01:23:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][170/1251]	eta 0:41:57 lr 0.000012	time 3.8042 (2.3285)	loss 3.0845 (2.9737)	grad_norm 3.7780 (3.3295)	
[2022-01-27 01:23:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][180/1251]	eta 0:41:22 lr 0.000012	time 1.9693 (2.3180)	loss 3.2235 (2.9788)	grad_norm 3.2860 (3.3210)	
[2022-01-27 01:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][190/1251]	eta 0:40:44 lr 0.000012	time 1.8734 (2.3040)	loss 2.9314 (2.9873)	grad_norm 3.3892 (3.3179)	
[2022-01-27 01:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][200/1251]	eta 0:40:29 lr 0.000012	time 2.2049 (2.3121)	loss 3.1020 (2.9814)	grad_norm 3.1898 (3.3128)	
[2022-01-27 01:24:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][210/1251]	eta 0:40:05 lr 0.000012	time 3.3218 (2.3107)	loss 3.1825 (2.9937)	grad_norm 3.5025 (3.3087)	
[2022-01-27 01:25:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][220/1251]	eta 0:39:27 lr 0.000012	time 1.6176 (2.2959)	loss 3.3969 (2.9935)	grad_norm 2.9051 (3.2932)	
[2022-01-27 01:25:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][230/1251]	eta 0:38:53 lr 0.000012	time 1.6918 (2.2851)	loss 3.0618 (2.9938)	grad_norm 3.6156 (3.2997)	
[2022-01-27 01:25:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][240/1251]	eta 0:38:30 lr 0.000012	time 1.9698 (2.2852)	loss 3.3518 (2.9994)	grad_norm 3.8720 (3.3168)	
[2022-01-27 01:26:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][250/1251]	eta 0:38:16 lr 0.000012	time 3.8378 (2.2945)	loss 2.6569 (3.0067)	grad_norm 2.9111 (3.3176)	
[2022-01-27 01:26:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][260/1251]	eta 0:37:52 lr 0.000012	time 1.6376 (2.2932)	loss 3.5172 (3.0136)	grad_norm 3.4934 (3.3195)	
[2022-01-27 01:26:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][270/1251]	eta 0:37:17 lr 0.000012	time 1.9214 (2.2810)	loss 3.4543 (3.0158)	grad_norm 2.8736 (3.3131)	
[2022-01-27 01:27:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][280/1251]	eta 0:36:44 lr 0.000012	time 1.9913 (2.2708)	loss 3.6688 (3.0120)	grad_norm 3.0490 (3.3236)	
[2022-01-27 01:27:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][290/1251]	eta 0:36:19 lr 0.000012	time 2.8133 (2.2680)	loss 2.7568 (3.0124)	grad_norm 3.1407 (3.3209)	
[2022-01-27 01:27:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][300/1251]	eta 0:35:51 lr 0.000012	time 1.9950 (2.2619)	loss 2.2785 (3.0089)	grad_norm 3.3681 (3.3212)	
[2022-01-27 01:28:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][310/1251]	eta 0:35:27 lr 0.000012	time 1.9350 (2.2612)	loss 2.1905 (3.0063)	grad_norm 4.1411 (3.3205)	
[2022-01-27 01:28:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][320/1251]	eta 0:35:07 lr 0.000012	time 2.3848 (2.2633)	loss 2.2992 (3.0092)	grad_norm 3.1997 (3.3207)	
[2022-01-27 01:29:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][330/1251]	eta 0:34:43 lr 0.000012	time 2.0880 (2.2623)	loss 3.1224 (3.0014)	grad_norm 2.8306 (3.3272)	
[2022-01-27 01:29:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][340/1251]	eta 0:34:16 lr 0.000012	time 1.9051 (2.2574)	loss 2.7196 (2.9943)	grad_norm 2.7606 (3.3202)	
[2022-01-27 01:29:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][350/1251]	eta 0:33:49 lr 0.000012	time 1.9041 (2.2521)	loss 2.6813 (2.9865)	grad_norm 3.2759 (3.3164)	
[2022-01-27 01:30:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][360/1251]	eta 0:33:22 lr 0.000012	time 2.4803 (2.2477)	loss 3.6589 (2.9917)	grad_norm 3.2332 (3.3153)	
[2022-01-27 01:30:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][370/1251]	eta 0:33:00 lr 0.000012	time 1.9413 (2.2475)	loss 2.9991 (2.9895)	grad_norm 3.5061 (3.3149)	
[2022-01-27 01:30:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][380/1251]	eta 0:32:32 lr 0.000012	time 2.1472 (2.2420)	loss 2.7472 (2.9910)	grad_norm 3.5894 (3.3175)	
[2022-01-27 01:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][390/1251]	eta 0:32:07 lr 0.000012	time 1.8892 (2.2391)	loss 3.0337 (2.9902)	grad_norm 2.9264 (3.3804)	
[2022-01-27 01:31:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][400/1251]	eta 0:31:48 lr 0.000012	time 2.7050 (2.2425)	loss 3.1155 (2.9892)	grad_norm 2.8930 (3.3749)	
[2022-01-27 01:31:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][410/1251]	eta 0:31:20 lr 0.000012	time 1.5077 (2.2357)	loss 3.0564 (2.9898)	grad_norm 3.3772 (3.3734)	
[2022-01-27 01:32:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][420/1251]	eta 0:30:56 lr 0.000012	time 1.7969 (2.2335)	loss 3.1506 (2.9946)	grad_norm 2.7143 (3.3706)	
[2022-01-27 01:32:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][430/1251]	eta 0:30:32 lr 0.000012	time 2.2166 (2.2323)	loss 3.4145 (2.9906)	grad_norm 3.5803 (3.3654)	
[2022-01-27 01:33:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][440/1251]	eta 0:30:11 lr 0.000012	time 4.0528 (2.2335)	loss 3.2383 (2.9946)	grad_norm 3.4467 (3.3649)	
[2022-01-27 01:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][450/1251]	eta 0:29:48 lr 0.000012	time 1.2486 (2.2330)	loss 3.1630 (2.9929)	grad_norm 3.2907 (3.3584)	
[2022-01-27 01:33:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][460/1251]	eta 0:29:27 lr 0.000012	time 1.5427 (2.2348)	loss 2.5912 (2.9900)	grad_norm 3.8214 (3.3563)	
[2022-01-27 01:34:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][470/1251]	eta 0:29:07 lr 0.000012	time 2.2361 (2.2373)	loss 2.8088 (2.9891)	grad_norm 2.8868 (3.3522)	
[2022-01-27 01:34:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][480/1251]	eta 0:28:45 lr 0.000012	time 4.0353 (2.2381)	loss 2.6048 (2.9890)	grad_norm 3.2775 (3.3493)	
[2022-01-27 01:34:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][490/1251]	eta 0:28:19 lr 0.000012	time 1.8113 (2.2337)	loss 3.0970 (2.9881)	grad_norm 3.1038 (3.3494)	
[2022-01-27 01:35:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][500/1251]	eta 0:27:54 lr 0.000012	time 1.5903 (2.2292)	loss 3.3659 (2.9852)	grad_norm 3.6355 (3.3516)	
[2022-01-27 01:35:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][510/1251]	eta 0:27:30 lr 0.000012	time 1.6313 (2.2278)	loss 3.1643 (2.9850)	grad_norm 2.8462 (3.3508)	
[2022-01-27 01:35:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][520/1251]	eta 0:27:10 lr 0.000012	time 3.4621 (2.2312)	loss 2.3447 (2.9789)	grad_norm 3.2567 (3.3492)	
[2022-01-27 01:36:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][530/1251]	eta 0:26:48 lr 0.000012	time 1.8653 (2.2314)	loss 2.3131 (2.9745)	grad_norm 2.9058 (3.3444)	
[2022-01-27 01:36:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][540/1251]	eta 0:26:27 lr 0.000012	time 1.6075 (2.2322)	loss 3.0687 (2.9729)	grad_norm 2.9047 (3.3435)	
[2022-01-27 01:37:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][550/1251]	eta 0:26:03 lr 0.000012	time 1.4737 (2.2307)	loss 3.4570 (2.9759)	grad_norm 3.5353 (3.3414)	
[2022-01-27 01:37:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][560/1251]	eta 0:25:40 lr 0.000012	time 2.4847 (2.2295)	loss 3.4390 (2.9759)	grad_norm 3.6407 (3.3546)	
[2022-01-27 01:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][570/1251]	eta 0:25:15 lr 0.000012	time 1.6024 (2.2258)	loss 2.3555 (2.9715)	grad_norm 3.2178 (3.3574)	
[2022-01-27 01:38:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][580/1251]	eta 0:24:51 lr 0.000012	time 2.2009 (2.2228)	loss 2.1751 (2.9704)	grad_norm 3.8386 (3.3595)	
[2022-01-27 01:38:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][590/1251]	eta 0:24:29 lr 0.000012	time 2.0195 (2.2235)	loss 2.1081 (2.9711)	grad_norm 4.2141 (3.3607)	
[2022-01-27 01:38:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][600/1251]	eta 0:24:08 lr 0.000012	time 2.4002 (2.2250)	loss 2.0199 (2.9710)	grad_norm 2.8825 (3.3610)	
[2022-01-27 01:39:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][610/1251]	eta 0:23:45 lr 0.000012	time 1.8398 (2.2237)	loss 3.4642 (2.9701)	grad_norm 3.5229 (3.3638)	
[2022-01-27 01:39:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][620/1251]	eta 0:23:21 lr 0.000012	time 1.9341 (2.2212)	loss 2.2242 (2.9677)	grad_norm 3.0166 (3.3592)	
[2022-01-27 01:39:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][630/1251]	eta 0:22:59 lr 0.000012	time 1.8869 (2.2207)	loss 2.8929 (2.9681)	grad_norm 4.9723 (3.3597)	
[2022-01-27 01:40:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][640/1251]	eta 0:22:36 lr 0.000012	time 2.6660 (2.2209)	loss 1.9806 (2.9689)	grad_norm 3.1961 (3.3574)	
[2022-01-27 01:40:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][650/1251]	eta 0:22:14 lr 0.000012	time 1.8433 (2.2204)	loss 2.6028 (2.9691)	grad_norm 3.3302 (3.3559)	
[2022-01-27 01:41:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][660/1251]	eta 0:21:51 lr 0.000012	time 2.5805 (2.2197)	loss 3.4334 (2.9719)	grad_norm 2.8253 (3.3575)	
[2022-01-27 01:41:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][670/1251]	eta 0:21:29 lr 0.000012	time 2.2366 (2.2191)	loss 3.4986 (2.9711)	grad_norm 3.0230 (3.3549)	
[2022-01-27 01:41:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][680/1251]	eta 0:21:05 lr 0.000012	time 2.1902 (2.2170)	loss 2.4375 (2.9700)	grad_norm 3.0096 (3.3560)	
[2022-01-27 01:42:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][690/1251]	eta 0:20:43 lr 0.000012	time 2.5123 (2.2157)	loss 3.2354 (2.9722)	grad_norm 3.1705 (3.3531)	
[2022-01-27 01:42:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][700/1251]	eta 0:20:22 lr 0.000012	time 2.1186 (2.2180)	loss 3.5922 (2.9751)	grad_norm 3.3551 (3.3520)	
[2022-01-27 01:42:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][710/1251]	eta 0:19:59 lr 0.000012	time 2.3580 (2.2169)	loss 3.4396 (2.9780)	grad_norm 3.3721 (3.3507)	
[2022-01-27 01:43:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][720/1251]	eta 0:19:37 lr 0.000012	time 2.3578 (2.2167)	loss 2.8016 (2.9764)	grad_norm 3.1615 (3.3521)	
[2022-01-27 01:43:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][730/1251]	eta 0:19:14 lr 0.000012	time 2.7047 (2.2154)	loss 3.1494 (2.9782)	grad_norm 3.7659 (3.3534)	
[2022-01-27 01:43:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][740/1251]	eta 0:18:51 lr 0.000012	time 2.0197 (2.2147)	loss 2.7870 (2.9771)	grad_norm 4.0522 (3.3537)	
[2022-01-27 01:44:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][750/1251]	eta 0:18:29 lr 0.000012	time 2.5338 (2.2148)	loss 3.2086 (2.9772)	grad_norm 3.3443 (3.3548)	
[2022-01-27 01:44:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][760/1251]	eta 0:18:08 lr 0.000012	time 1.8877 (2.2159)	loss 3.4379 (2.9797)	grad_norm 3.3976 (3.3546)	
[2022-01-27 01:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][770/1251]	eta 0:17:45 lr 0.000012	time 2.1201 (2.2151)	loss 2.2991 (2.9772)	grad_norm 3.0862 (3.3541)	
[2022-01-27 01:45:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][780/1251]	eta 0:17:23 lr 0.000012	time 2.3006 (2.2152)	loss 2.9924 (2.9788)	grad_norm 2.9262 (3.3523)	
[2022-01-27 01:45:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][790/1251]	eta 0:17:00 lr 0.000012	time 2.2591 (2.2131)	loss 3.5693 (2.9782)	grad_norm 2.8311 (3.3514)	
[2022-01-27 01:46:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][800/1251]	eta 0:16:37 lr 0.000012	time 1.9242 (2.2111)	loss 2.6698 (2.9789)	grad_norm 3.0235 (3.3506)	
[2022-01-27 01:46:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][810/1251]	eta 0:16:14 lr 0.000012	time 2.2300 (2.2099)	loss 2.9392 (2.9799)	grad_norm 3.2530 (3.3488)	
[2022-01-27 01:46:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][820/1251]	eta 0:15:52 lr 0.000012	time 2.0339 (2.2097)	loss 3.2631 (2.9810)	grad_norm 2.9259 (3.3487)	
[2022-01-27 01:47:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][830/1251]	eta 0:15:30 lr 0.000012	time 2.6779 (2.2102)	loss 2.9858 (2.9818)	grad_norm 2.9982 (3.3476)	
[2022-01-27 01:47:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][840/1251]	eta 0:15:08 lr 0.000012	time 2.1300 (2.2099)	loss 2.5103 (2.9811)	grad_norm 2.8525 (3.3464)	
[2022-01-27 01:47:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][850/1251]	eta 0:14:45 lr 0.000012	time 2.1552 (2.2091)	loss 2.5563 (2.9791)	grad_norm 2.8327 (3.3428)	
[2022-01-27 01:48:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][860/1251]	eta 0:14:24 lr 0.000012	time 2.9506 (2.2105)	loss 3.4992 (2.9819)	grad_norm 3.4762 (3.3410)	
[2022-01-27 01:48:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][870/1251]	eta 0:14:02 lr 0.000012	time 1.9298 (2.2112)	loss 3.2089 (2.9822)	grad_norm 3.3170 (3.3381)	
[2022-01-27 01:49:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][880/1251]	eta 0:13:40 lr 0.000012	time 2.7875 (2.2112)	loss 3.3719 (2.9831)	grad_norm 3.3619 (3.3379)	
[2022-01-27 01:49:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][890/1251]	eta 0:13:17 lr 0.000012	time 1.9832 (2.2090)	loss 3.3695 (2.9825)	grad_norm 2.9379 (3.3382)	
[2022-01-27 01:49:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][900/1251]	eta 0:12:54 lr 0.000012	time 1.5525 (2.2069)	loss 2.9642 (2.9827)	grad_norm 2.9036 (3.3363)	
[2022-01-27 01:50:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][910/1251]	eta 0:12:32 lr 0.000012	time 2.2402 (2.2072)	loss 2.9133 (2.9837)	grad_norm 2.8696 (3.3343)	
[2022-01-27 01:50:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][920/1251]	eta 0:12:09 lr 0.000012	time 1.9009 (2.2051)	loss 2.0598 (2.9837)	grad_norm 3.4905 (3.3320)	
[2022-01-27 01:50:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][930/1251]	eta 0:11:47 lr 0.000012	time 2.0926 (2.2045)	loss 2.5113 (2.9833)	grad_norm 3.3613 (3.3335)	
[2022-01-27 01:51:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][940/1251]	eta 0:11:25 lr 0.000012	time 2.7013 (2.2051)	loss 2.1307 (2.9851)	grad_norm 3.5115 (3.3370)	
[2022-01-27 01:51:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][950/1251]	eta 0:11:04 lr 0.000012	time 2.7223 (2.2071)	loss 3.3231 (2.9868)	grad_norm 2.9668 (3.3376)	
[2022-01-27 01:51:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][960/1251]	eta 0:10:42 lr 0.000012	time 2.4873 (2.2069)	loss 2.3033 (2.9828)	grad_norm 3.1483 (3.3351)	
[2022-01-27 01:52:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][970/1251]	eta 0:10:20 lr 0.000012	time 1.6241 (2.2072)	loss 1.8934 (2.9830)	grad_norm 3.8283 (3.3343)	
[2022-01-27 01:52:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][980/1251]	eta 0:09:58 lr 0.000012	time 1.8662 (2.2069)	loss 3.4449 (2.9852)	grad_norm 3.8387 (3.3326)	
[2022-01-27 01:53:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][990/1251]	eta 0:09:36 lr 0.000012	time 2.4925 (2.2072)	loss 2.7154 (2.9868)	grad_norm 2.9816 (3.3325)	
[2022-01-27 01:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1000/1251]	eta 0:09:13 lr 0.000012	time 2.3939 (2.2062)	loss 3.1573 (2.9870)	grad_norm 3.4433 (3.3299)	
[2022-01-27 01:53:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1010/1251]	eta 0:08:51 lr 0.000012	time 2.0023 (2.2051)	loss 3.0409 (2.9879)	grad_norm 3.8040 (3.3288)	
[2022-01-27 01:54:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1020/1251]	eta 0:08:29 lr 0.000012	time 1.8884 (2.2039)	loss 3.0971 (2.9894)	grad_norm 3.1532 (3.3290)	
[2022-01-27 01:54:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1030/1251]	eta 0:08:07 lr 0.000012	time 2.9326 (2.2039)	loss 2.2675 (2.9895)	grad_norm 2.8120 (3.3262)	
[2022-01-27 01:54:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1040/1251]	eta 0:07:45 lr 0.000012	time 2.4768 (2.2038)	loss 2.0992 (2.9908)	grad_norm 3.4079 (3.3259)	
[2022-01-27 01:55:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1050/1251]	eta 0:07:23 lr 0.000012	time 2.7954 (2.2057)	loss 3.3465 (2.9927)	grad_norm 3.3813 (3.3249)	
[2022-01-27 01:55:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1060/1251]	eta 0:07:01 lr 0.000012	time 2.3716 (2.2069)	loss 3.9002 (2.9956)	grad_norm 3.1434 (3.3231)	
[2022-01-27 01:56:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1070/1251]	eta 0:06:39 lr 0.000012	time 3.3546 (2.2075)	loss 2.6310 (2.9952)	grad_norm 3.2681 (3.3221)	
[2022-01-27 01:56:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1080/1251]	eta 0:06:17 lr 0.000012	time 1.8964 (2.2065)	loss 3.4030 (2.9954)	grad_norm 3.6201 (3.3222)	
[2022-01-27 01:56:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1090/1251]	eta 0:05:55 lr 0.000012	time 2.4257 (2.2050)	loss 3.2673 (2.9939)	grad_norm 3.9382 (3.3210)	
[2022-01-27 01:57:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1100/1251]	eta 0:05:32 lr 0.000012	time 2.0994 (2.2031)	loss 2.2793 (2.9928)	grad_norm 3.2857 (3.3212)	
[2022-01-27 01:57:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1110/1251]	eta 0:05:10 lr 0.000012	time 2.7989 (2.2043)	loss 3.2189 (2.9906)	grad_norm 3.1252 (3.3192)	
[2022-01-27 01:57:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1120/1251]	eta 0:04:48 lr 0.000012	time 1.8497 (2.2055)	loss 2.7158 (2.9917)	grad_norm 2.8649 (3.3161)	
[2022-01-27 01:58:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1130/1251]	eta 0:04:26 lr 0.000012	time 2.8276 (2.2057)	loss 2.3141 (2.9910)	grad_norm 3.4496 (3.3161)	
[2022-01-27 01:58:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1140/1251]	eta 0:04:04 lr 0.000012	time 1.6535 (2.2054)	loss 3.0581 (2.9908)	grad_norm 2.9212 (3.3152)	
[2022-01-27 01:58:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1150/1251]	eta 0:03:42 lr 0.000012	time 2.4608 (2.2052)	loss 2.9119 (2.9915)	grad_norm 3.6234 (3.3144)	
[2022-01-27 01:59:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1160/1251]	eta 0:03:20 lr 0.000012	time 1.8576 (2.2040)	loss 1.8640 (2.9909)	grad_norm 2.6821 (3.3264)	
[2022-01-27 01:59:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1170/1251]	eta 0:02:58 lr 0.000012	time 2.2725 (2.2033)	loss 2.3860 (2.9907)	grad_norm 3.1606 (3.3248)	
[2022-01-27 01:59:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1180/1251]	eta 0:02:36 lr 0.000012	time 1.9125 (2.2025)	loss 2.9871 (2.9912)	grad_norm 2.7447 (3.3242)	
[2022-01-27 02:00:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1190/1251]	eta 0:02:14 lr 0.000012	time 2.8933 (2.2016)	loss 1.8596 (2.9892)	grad_norm 3.3739 (3.3249)	
[2022-01-27 02:00:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1200/1251]	eta 0:01:52 lr 0.000012	time 1.7850 (2.2007)	loss 3.4628 (2.9908)	grad_norm 2.7822 (3.3231)	
[2022-01-27 02:01:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1210/1251]	eta 0:01:30 lr 0.000012	time 2.5346 (2.2010)	loss 3.1165 (2.9903)	grad_norm 2.9087 (3.3207)	
[2022-01-27 02:01:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1220/1251]	eta 0:01:08 lr 0.000012	time 1.9114 (2.2004)	loss 3.2209 (2.9894)	grad_norm 3.2744 (3.3191)	
[2022-01-27 02:01:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1230/1251]	eta 0:00:46 lr 0.000012	time 2.8633 (2.2010)	loss 2.7783 (2.9888)	grad_norm 2.7216 (3.3180)	
[2022-01-27 02:02:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1240/1251]	eta 0:00:24 lr 0.000012	time 1.7483 (2.2000)	loss 2.3744 (2.9906)	grad_norm 2.6183 (3.3171)	
[2022-01-27 02:02:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [291/300][1250/1251]	eta 0:00:02 lr 0.000012	time 1.1835 (2.1951)	loss 3.2547 (2.9912)	grad_norm 2.6405 (3.3167)	
[2022-01-27 02:02:23 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 291 training takes 0:45:46
[2022-01-27 02:02:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 15.969 (15.969)	Loss 0.8317 (0.8317)	Acc@1 80.176 (80.176)	Acc@5 95.703 (95.703)	
[2022-01-27 02:03:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.869 (3.309)	Loss 0.7940 (0.8092)	Acc@1 81.348 (81.170)	Acc@5 95.801 (95.570)	
[2022-01-27 02:03:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.888 (2.586)	Loss 0.7736 (0.8088)	Acc@1 82.324 (81.231)	Acc@5 95.605 (95.415)	
[2022-01-27 02:03:33 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.658 (2.259)	Loss 0.7926 (0.8053)	Acc@1 79.980 (81.209)	Acc@5 96.191 (95.476)	
[2022-01-27 02:03:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.820 (2.173)	Loss 0.8107 (0.8067)	Acc@1 81.543 (81.133)	Acc@5 95.312 (95.491)	
[2022-01-27 02:04:01 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.216 Acc@5 95.458
[2022-01-27 02:04:01 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.2%
[2022-01-27 02:04:01 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.24%
[2022-01-27 02:04:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][0/1251]	eta 7:30:23 lr 0.000012	time 21.6017 (21.6017)	loss 3.4057 (3.4057)	grad_norm 3.6475 (3.6475)	
[2022-01-27 02:04:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][10/1251]	eta 1:23:56 lr 0.000012	time 1.8462 (4.0582)	loss 3.4375 (3.1014)	grad_norm 3.6427 (3.3972)	
[2022-01-27 02:05:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][20/1251]	eta 1:05:24 lr 0.000012	time 1.3429 (3.1883)	loss 2.6855 (3.1262)	grad_norm 3.1132 (3.4020)	
[2022-01-27 02:05:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][30/1251]	eta 0:57:53 lr 0.000012	time 1.3984 (2.8448)	loss 3.2390 (3.0843)	grad_norm 3.2004 (3.3670)	
[2022-01-27 02:05:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][40/1251]	eta 0:54:59 lr 0.000012	time 3.7446 (2.7244)	loss 2.0072 (3.0239)	grad_norm 4.0019 (3.3282)	
[2022-01-27 02:06:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][50/1251]	eta 0:53:24 lr 0.000012	time 2.3823 (2.6679)	loss 3.6760 (3.0006)	grad_norm 3.7611 (3.2944)	
[2022-01-27 02:06:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][60/1251]	eta 0:51:49 lr 0.000012	time 2.7688 (2.6107)	loss 2.1433 (3.0158)	grad_norm 3.1116 (3.2811)	
[2022-01-27 02:07:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][70/1251]	eta 0:50:20 lr 0.000012	time 1.8071 (2.5578)	loss 3.1427 (3.0127)	grad_norm 3.5337 (3.3058)	
[2022-01-27 02:07:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][80/1251]	eta 0:49:13 lr 0.000012	time 3.4552 (2.5225)	loss 3.1053 (3.0090)	grad_norm 3.8443 (3.3354)	
[2022-01-27 02:07:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][90/1251]	eta 0:47:42 lr 0.000012	time 1.6397 (2.4658)	loss 2.9796 (3.0289)	grad_norm 3.2494 (3.3676)	
[2022-01-27 02:08:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][100/1251]	eta 0:46:33 lr 0.000012	time 1.9865 (2.4273)	loss 3.3667 (3.0259)	grad_norm 3.5031 (3.3519)	
[2022-01-27 02:08:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][110/1251]	eta 0:45:33 lr 0.000012	time 1.8639 (2.3959)	loss 3.2219 (3.0276)	grad_norm 3.1479 (3.3511)	
[2022-01-27 02:08:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][120/1251]	eta 0:45:06 lr 0.000012	time 3.4474 (2.3932)	loss 3.5197 (3.0365)	grad_norm 3.2421 (3.3451)	
[2022-01-27 02:09:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][130/1251]	eta 0:44:27 lr 0.000012	time 2.1818 (2.3798)	loss 3.1919 (3.0442)	grad_norm 3.2245 (3.3288)	
[2022-01-27 02:09:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][140/1251]	eta 0:44:01 lr 0.000012	time 2.4608 (2.3778)	loss 3.2727 (3.0549)	grad_norm 3.1775 (3.3227)	
[2022-01-27 02:09:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][150/1251]	eta 0:43:11 lr 0.000012	time 1.6700 (2.3537)	loss 3.1588 (3.0614)	grad_norm 2.9492 (3.3145)	
[2022-01-27 02:10:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][160/1251]	eta 0:42:40 lr 0.000012	time 2.8453 (2.3466)	loss 2.8128 (3.0571)	grad_norm 3.8538 (3.3061)	
[2022-01-27 02:10:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][170/1251]	eta 0:41:56 lr 0.000012	time 1.9487 (2.3280)	loss 2.8760 (3.0584)	grad_norm 3.4997 (3.3098)	
[2022-01-27 02:11:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][180/1251]	eta 0:41:31 lr 0.000012	time 2.7036 (2.3259)	loss 3.4932 (3.0644)	grad_norm 3.3810 (3.3144)	
[2022-01-27 02:11:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][190/1251]	eta 0:40:55 lr 0.000012	time 2.2891 (2.3146)	loss 2.0357 (3.0570)	grad_norm 3.2939 (3.3055)	
[2022-01-27 02:11:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][200/1251]	eta 0:40:22 lr 0.000012	time 2.5590 (2.3052)	loss 3.3273 (3.0565)	grad_norm 3.3051 (3.3050)	
[2022-01-27 02:12:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][210/1251]	eta 0:39:52 lr 0.000012	time 2.1890 (2.2983)	loss 3.1812 (3.0509)	grad_norm 2.8846 (3.3013)	
[2022-01-27 02:12:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][220/1251]	eta 0:39:26 lr 0.000012	time 1.8507 (2.2956)	loss 2.7824 (3.0510)	grad_norm 3.5136 (3.3031)	
[2022-01-27 02:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][230/1251]	eta 0:39:06 lr 0.000012	time 2.6743 (2.2986)	loss 3.2763 (3.0466)	grad_norm 3.0258 (3.3028)	
[2022-01-27 02:13:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][240/1251]	eta 0:38:41 lr 0.000012	time 2.8534 (2.2963)	loss 3.1557 (3.0514)	grad_norm 3.3338 (3.3058)	
[2022-01-27 02:13:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][250/1251]	eta 0:38:12 lr 0.000012	time 1.8643 (2.2901)	loss 3.1140 (3.0496)	grad_norm 3.1570 (3.3047)	
[2022-01-27 02:13:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][260/1251]	eta 0:37:40 lr 0.000012	time 2.2304 (2.2813)	loss 3.4683 (3.0499)	grad_norm 3.1457 (3.2991)	
[2022-01-27 02:14:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][270/1251]	eta 0:37:13 lr 0.000012	time 2.1604 (2.2764)	loss 2.4053 (3.0452)	grad_norm 3.9301 (3.2977)	
[2022-01-27 02:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][280/1251]	eta 0:36:45 lr 0.000012	time 1.8087 (2.2716)	loss 3.4635 (3.0438)	grad_norm 3.1454 (3.2950)	
[2022-01-27 02:15:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][290/1251]	eta 0:36:19 lr 0.000012	time 1.9551 (2.2684)	loss 3.1218 (3.0461)	grad_norm 3.3180 (3.3147)	
[2022-01-27 02:15:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][300/1251]	eta 0:35:54 lr 0.000012	time 2.5237 (2.2650)	loss 3.0433 (3.0464)	grad_norm 3.0215 (3.3171)	
[2022-01-27 02:15:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][310/1251]	eta 0:35:29 lr 0.000012	time 1.8474 (2.2625)	loss 3.0198 (3.0414)	grad_norm 4.1170 (3.3175)	
[2022-01-27 02:16:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][320/1251]	eta 0:35:05 lr 0.000012	time 2.2781 (2.2613)	loss 3.1935 (3.0345)	grad_norm 3.3872 (3.3198)	
[2022-01-27 02:16:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][330/1251]	eta 0:34:36 lr 0.000012	time 1.5469 (2.2543)	loss 3.5743 (3.0298)	grad_norm 3.1837 (3.3200)	
[2022-01-27 02:16:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][340/1251]	eta 0:34:11 lr 0.000012	time 1.7232 (2.2515)	loss 2.0692 (3.0267)	grad_norm 3.0637 (3.3203)	
[2022-01-27 02:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][350/1251]	eta 0:33:49 lr 0.000012	time 2.5939 (2.2523)	loss 3.6271 (3.0233)	grad_norm 3.4819 (3.3204)	
[2022-01-27 02:17:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][360/1251]	eta 0:33:23 lr 0.000012	time 2.0350 (2.2482)	loss 3.4959 (3.0291)	grad_norm 3.4309 (3.3170)	
[2022-01-27 02:17:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][370/1251]	eta 0:33:00 lr 0.000012	time 2.4021 (2.2483)	loss 3.3536 (3.0327)	grad_norm 3.6577 (3.3199)	
[2022-01-27 02:18:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][380/1251]	eta 0:32:38 lr 0.000012	time 1.5044 (2.2487)	loss 3.2144 (3.0306)	grad_norm 3.3117 (3.3226)	
[2022-01-27 02:18:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][390/1251]	eta 0:32:15 lr 0.000012	time 2.7069 (2.2478)	loss 3.0661 (3.0298)	grad_norm 4.2110 (3.3319)	
[2022-01-27 02:19:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][400/1251]	eta 0:31:51 lr 0.000012	time 2.1936 (2.2460)	loss 3.5411 (3.0273)	grad_norm 3.4078 (3.3283)	
[2022-01-27 02:19:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][410/1251]	eta 0:31:26 lr 0.000012	time 2.5849 (2.2435)	loss 2.8010 (3.0276)	grad_norm 3.2740 (3.3290)	
[2022-01-27 02:19:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][420/1251]	eta 0:31:01 lr 0.000012	time 2.1396 (2.2399)	loss 2.8014 (3.0290)	grad_norm 3.0811 (3.3361)	
[2022-01-27 02:20:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][430/1251]	eta 0:30:36 lr 0.000012	time 2.2622 (2.2367)	loss 3.2660 (3.0309)	grad_norm 3.4722 (3.3352)	
[2022-01-27 02:20:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][440/1251]	eta 0:30:13 lr 0.000012	time 2.2370 (2.2362)	loss 3.4549 (3.0356)	grad_norm 3.2336 (3.3373)	
[2022-01-27 02:20:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][450/1251]	eta 0:29:48 lr 0.000012	time 1.5935 (2.2325)	loss 3.3710 (3.0355)	grad_norm 3.6997 (3.3364)	
[2022-01-27 02:21:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][460/1251]	eta 0:29:23 lr 0.000012	time 1.8170 (2.2298)	loss 3.0813 (3.0332)	grad_norm 3.7551 (3.3380)	
[2022-01-27 02:21:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][470/1251]	eta 0:28:58 lr 0.000012	time 1.8494 (2.2266)	loss 3.1881 (3.0380)	grad_norm 3.2488 (3.3366)	
[2022-01-27 02:21:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][480/1251]	eta 0:28:37 lr 0.000012	time 2.5922 (2.2282)	loss 2.3459 (3.0350)	grad_norm 3.9799 (3.3363)	
[2022-01-27 02:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][490/1251]	eta 0:28:13 lr 0.000012	time 1.5221 (2.2257)	loss 2.8637 (3.0353)	grad_norm 3.1695 (3.3350)	
[2022-01-27 02:22:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][500/1251]	eta 0:27:51 lr 0.000012	time 2.6722 (2.2259)	loss 3.1105 (3.0355)	grad_norm 2.9363 (3.3325)	
[2022-01-27 02:23:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][510/1251]	eta 0:27:33 lr 0.000012	time 2.1842 (2.2308)	loss 3.2156 (3.0348)	grad_norm 3.1901 (3.3269)	
[2022-01-27 02:23:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][520/1251]	eta 0:27:13 lr 0.000012	time 2.9802 (2.2340)	loss 3.0524 (3.0376)	grad_norm 3.7751 (3.3288)	
[2022-01-27 02:23:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][530/1251]	eta 0:26:51 lr 0.000012	time 2.1979 (2.2346)	loss 3.3344 (3.0360)	grad_norm 3.3636 (3.3252)	
[2022-01-27 02:24:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][540/1251]	eta 0:26:27 lr 0.000012	time 1.9568 (2.2325)	loss 3.1165 (3.0367)	grad_norm 3.1983 (3.3264)	
[2022-01-27 02:24:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][550/1251]	eta 0:26:01 lr 0.000012	time 1.7114 (2.2280)	loss 2.9369 (3.0404)	grad_norm 2.7602 (3.3244)	
[2022-01-27 02:24:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][560/1251]	eta 0:25:37 lr 0.000012	time 2.2498 (2.2254)	loss 3.1973 (3.0365)	grad_norm 3.2426 (3.3217)	
[2022-01-27 02:25:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][570/1251]	eta 0:25:15 lr 0.000012	time 2.1831 (2.2247)	loss 2.6904 (3.0388)	grad_norm 3.7698 (3.3244)	
[2022-01-27 02:25:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][580/1251]	eta 0:24:52 lr 0.000012	time 1.8938 (2.2241)	loss 3.2057 (3.0349)	grad_norm 3.1756 (3.3262)	
[2022-01-27 02:25:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][590/1251]	eta 0:24:32 lr 0.000012	time 2.5893 (2.2282)	loss 2.0520 (3.0335)	grad_norm 3.3049 (3.3216)	
[2022-01-27 02:26:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][600/1251]	eta 0:24:09 lr 0.000012	time 1.7369 (2.2271)	loss 3.1371 (3.0334)	grad_norm 3.1023 (3.3266)	
[2022-01-27 02:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][610/1251]	eta 0:23:48 lr 0.000012	time 2.5090 (2.2291)	loss 2.1116 (3.0290)	grad_norm 2.9429 (3.3290)	
[2022-01-27 02:27:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][620/1251]	eta 0:23:27 lr 0.000012	time 2.5346 (2.2311)	loss 2.0688 (3.0250)	grad_norm 3.1491 (3.3302)	
[2022-01-27 02:27:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][630/1251]	eta 0:23:05 lr 0.000012	time 1.8282 (2.2304)	loss 3.2566 (3.0256)	grad_norm 3.4875 (3.3296)	
[2022-01-27 02:27:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][640/1251]	eta 0:22:39 lr 0.000012	time 1.8796 (2.2248)	loss 2.1119 (3.0235)	grad_norm 3.8464 (3.3293)	
[2022-01-27 02:28:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][650/1251]	eta 0:22:14 lr 0.000012	time 2.2379 (2.2203)	loss 2.5515 (3.0219)	grad_norm 2.6209 (3.3287)	
[2022-01-27 02:28:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][660/1251]	eta 0:21:50 lr 0.000012	time 2.2376 (2.2175)	loss 2.6380 (3.0210)	grad_norm 3.2114 (3.3275)	
[2022-01-27 02:28:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][670/1251]	eta 0:21:26 lr 0.000012	time 2.3759 (2.2149)	loss 2.8789 (3.0165)	grad_norm 2.9146 (3.3261)	
[2022-01-27 02:29:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][680/1251]	eta 0:21:05 lr 0.000012	time 2.3391 (2.2157)	loss 3.3467 (3.0154)	grad_norm 3.2991 (3.3278)	
[2022-01-27 02:29:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][690/1251]	eta 0:20:44 lr 0.000012	time 2.1659 (2.2177)	loss 2.0391 (3.0144)	grad_norm 2.7894 (3.3289)	
[2022-01-27 02:29:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][700/1251]	eta 0:20:21 lr 0.000012	time 2.0618 (2.2177)	loss 3.0470 (3.0142)	grad_norm 3.1986 (3.3383)	
[2022-01-27 02:30:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][710/1251]	eta 0:19:59 lr 0.000011	time 1.8823 (2.2173)	loss 3.5431 (3.0163)	grad_norm 3.7651 (3.3401)	
[2022-01-27 02:30:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][720/1251]	eta 0:19:37 lr 0.000011	time 2.2250 (2.2168)	loss 2.3929 (3.0128)	grad_norm 4.6873 (3.3390)	
[2022-01-27 02:31:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][730/1251]	eta 0:19:14 lr 0.000011	time 1.5535 (2.2163)	loss 3.3658 (3.0127)	grad_norm 3.6535 (3.3389)	
[2022-01-27 02:31:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][740/1251]	eta 0:18:52 lr 0.000011	time 2.1897 (2.2158)	loss 2.4127 (3.0100)	grad_norm 3.3970 (3.3374)	
[2022-01-27 02:31:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][750/1251]	eta 0:18:29 lr 0.000011	time 1.5544 (2.2151)	loss 2.1388 (3.0081)	grad_norm 2.9773 (3.3332)	
[2022-01-27 02:32:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][760/1251]	eta 0:18:07 lr 0.000011	time 2.3409 (2.2145)	loss 2.8501 (3.0052)	grad_norm 3.0527 (3.3331)	
[2022-01-27 02:32:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][770/1251]	eta 0:17:44 lr 0.000011	time 2.1346 (2.2138)	loss 2.7993 (3.0005)	grad_norm 3.0828 (3.3327)	
[2022-01-27 02:32:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][780/1251]	eta 0:17:22 lr 0.000011	time 2.2460 (2.2136)	loss 2.7588 (2.9979)	grad_norm 2.8679 (3.3309)	
[2022-01-27 02:33:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][790/1251]	eta 0:17:00 lr 0.000011	time 2.1561 (2.2141)	loss 3.1492 (2.9992)	grad_norm 2.7269 (3.3304)	
[2022-01-27 02:33:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][800/1251]	eta 0:16:39 lr 0.000011	time 2.9837 (2.2157)	loss 2.7295 (2.9990)	grad_norm 2.6846 (3.3271)	
[2022-01-27 02:33:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][810/1251]	eta 0:16:16 lr 0.000011	time 1.8741 (2.2142)	loss 3.3425 (2.9962)	grad_norm 3.0209 (3.3330)	
[2022-01-27 02:34:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][820/1251]	eta 0:15:54 lr 0.000011	time 2.1972 (2.2136)	loss 3.4724 (2.9978)	grad_norm 2.9565 (3.3335)	
[2022-01-27 02:34:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][830/1251]	eta 0:15:31 lr 0.000011	time 2.2294 (2.2123)	loss 3.1125 (2.9973)	grad_norm 3.0849 (3.3339)	
[2022-01-27 02:35:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][840/1251]	eta 0:15:08 lr 0.000011	time 2.4164 (2.2106)	loss 2.5677 (2.9987)	grad_norm 3.0169 (3.3325)	
[2022-01-27 02:35:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][850/1251]	eta 0:14:46 lr 0.000011	time 2.0896 (2.2106)	loss 3.3430 (2.9962)	grad_norm 3.1635 (3.3335)	
[2022-01-27 02:35:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][860/1251]	eta 0:14:24 lr 0.000011	time 2.1855 (2.2097)	loss 3.1761 (2.9965)	grad_norm 3.2584 (3.3339)	
[2022-01-27 02:36:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][870/1251]	eta 0:14:01 lr 0.000011	time 2.3160 (2.2088)	loss 2.7554 (2.9949)	grad_norm 3.2721 (3.3310)	
[2022-01-27 02:36:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][880/1251]	eta 0:13:40 lr 0.000011	time 3.3448 (2.2104)	loss 3.7246 (2.9967)	grad_norm 3.2865 (3.3311)	
[2022-01-27 02:36:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][890/1251]	eta 0:13:18 lr 0.000011	time 2.1467 (2.2110)	loss 3.0066 (2.9969)	grad_norm 2.9224 (3.3292)	
[2022-01-27 02:37:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][900/1251]	eta 0:12:56 lr 0.000011	time 2.0360 (2.2112)	loss 3.1543 (2.9948)	grad_norm 2.8402 (3.3285)	
[2022-01-27 02:37:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][910/1251]	eta 0:12:33 lr 0.000011	time 2.2934 (2.2105)	loss 3.0748 (2.9928)	grad_norm 3.1858 (3.3298)	
[2022-01-27 02:37:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][920/1251]	eta 0:12:11 lr 0.000011	time 2.2146 (2.2086)	loss 3.2159 (2.9907)	grad_norm 2.8984 (3.3280)	
[2022-01-27 02:38:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][930/1251]	eta 0:11:48 lr 0.000011	time 2.8412 (2.2084)	loss 2.9157 (2.9883)	grad_norm 4.2219 (3.3298)	
[2022-01-27 02:38:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][940/1251]	eta 0:11:26 lr 0.000011	time 2.2849 (2.2067)	loss 3.0757 (2.9853)	grad_norm 3.0686 (3.3279)	
[2022-01-27 02:39:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][950/1251]	eta 0:11:04 lr 0.000011	time 2.2636 (2.2064)	loss 2.7932 (2.9850)	grad_norm 3.0859 (3.3291)	
[2022-01-27 02:39:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][960/1251]	eta 0:10:42 lr 0.000011	time 2.9089 (2.2076)	loss 3.0186 (2.9842)	grad_norm 3.5127 (3.3294)	
[2022-01-27 02:39:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][970/1251]	eta 0:10:20 lr 0.000011	time 2.3339 (2.2080)	loss 3.0627 (2.9843)	grad_norm 3.6421 (3.3295)	
[2022-01-27 02:40:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][980/1251]	eta 0:09:58 lr 0.000011	time 2.1813 (2.2089)	loss 1.7694 (2.9827)	grad_norm 2.8185 (3.3273)	
[2022-01-27 02:40:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][990/1251]	eta 0:09:36 lr 0.000011	time 2.2310 (2.2080)	loss 3.3785 (2.9832)	grad_norm 3.6280 (3.3276)	
[2022-01-27 02:40:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1000/1251]	eta 0:09:13 lr 0.000011	time 1.8684 (2.2068)	loss 3.6390 (2.9824)	grad_norm 2.7183 (3.3255)	
[2022-01-27 02:41:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1010/1251]	eta 0:08:51 lr 0.000011	time 2.2573 (2.2071)	loss 2.8087 (2.9826)	grad_norm 3.4600 (3.3247)	
[2022-01-27 02:41:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1020/1251]	eta 0:08:29 lr 0.000011	time 1.6264 (2.2067)	loss 2.2917 (2.9825)	grad_norm 3.1006 (3.3268)	
[2022-01-27 02:41:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1030/1251]	eta 0:08:07 lr 0.000011	time 2.2300 (2.2062)	loss 2.3478 (2.9824)	grad_norm 3.2481 (3.3251)	
[2022-01-27 02:42:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1040/1251]	eta 0:07:45 lr 0.000011	time 1.7106 (2.2038)	loss 3.2332 (2.9816)	grad_norm 3.2322 (3.3229)	
[2022-01-27 02:42:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1050/1251]	eta 0:07:22 lr 0.000011	time 2.1958 (2.2028)	loss 2.7653 (2.9813)	grad_norm 2.9485 (3.3205)	
[2022-01-27 02:42:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1060/1251]	eta 0:07:00 lr 0.000011	time 1.6980 (2.2012)	loss 2.0996 (2.9806)	grad_norm 2.8854 (3.3181)	
[2022-01-27 02:43:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1070/1251]	eta 0:06:38 lr 0.000011	time 2.5260 (2.2014)	loss 2.4739 (2.9808)	grad_norm 3.7984 (3.3165)	
[2022-01-27 02:43:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1080/1251]	eta 0:06:16 lr 0.000011	time 2.2035 (2.2009)	loss 3.2859 (2.9804)	grad_norm 3.3740 (3.3182)	
[2022-01-27 02:44:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1090/1251]	eta 0:05:54 lr 0.000011	time 2.8691 (2.2020)	loss 3.3050 (2.9762)	grad_norm 3.4208 (3.3172)	
[2022-01-27 02:44:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1100/1251]	eta 0:05:32 lr 0.000011	time 1.9219 (2.2033)	loss 3.3696 (2.9749)	grad_norm 2.9011 (3.3175)	
[2022-01-27 02:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1110/1251]	eta 0:05:10 lr 0.000011	time 1.9254 (2.2030)	loss 2.6510 (2.9735)	grad_norm 3.1266 (3.3167)	
[2022-01-27 02:45:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1120/1251]	eta 0:04:48 lr 0.000011	time 1.8620 (2.2017)	loss 3.5404 (2.9740)	grad_norm 4.4734 (3.3185)	
[2022-01-27 02:45:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1130/1251]	eta 0:04:26 lr 0.000011	time 2.2108 (2.2015)	loss 3.3433 (2.9758)	grad_norm 3.3295 (3.3195)	
[2022-01-27 02:45:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1140/1251]	eta 0:04:04 lr 0.000011	time 2.1612 (2.2008)	loss 2.9237 (2.9768)	grad_norm 2.7443 (3.3193)	
[2022-01-27 02:46:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1150/1251]	eta 0:03:42 lr 0.000011	time 2.5061 (2.2012)	loss 3.3523 (2.9767)	grad_norm 2.9450 (3.3189)	
[2022-01-27 02:46:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1160/1251]	eta 0:03:20 lr 0.000011	time 1.9827 (2.2003)	loss 2.0778 (2.9772)	grad_norm 3.2161 (3.3205)	
[2022-01-27 02:46:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1170/1251]	eta 0:02:58 lr 0.000011	time 2.1533 (2.2005)	loss 3.2280 (2.9756)	grad_norm 2.8638 (3.3202)	
[2022-01-27 02:47:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1180/1251]	eta 0:02:36 lr 0.000011	time 1.8788 (2.1998)	loss 2.3152 (2.9737)	grad_norm 2.7724 (3.3190)	
[2022-01-27 02:47:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1190/1251]	eta 0:02:14 lr 0.000011	time 3.2073 (2.2006)	loss 3.1189 (2.9720)	grad_norm 2.8714 (3.3198)	
[2022-01-27 02:48:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1200/1251]	eta 0:01:52 lr 0.000011	time 2.3607 (2.2011)	loss 2.6357 (2.9726)	grad_norm 2.8144 (3.3198)	
[2022-01-27 02:48:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1210/1251]	eta 0:01:30 lr 0.000011	time 1.5643 (2.2020)	loss 3.1776 (2.9748)	grad_norm 3.4864 (3.3194)	
[2022-01-27 02:48:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1220/1251]	eta 0:01:08 lr 0.000011	time 1.9759 (2.2024)	loss 3.6868 (2.9757)	grad_norm 3.3605 (3.3192)	
[2022-01-27 02:49:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1230/1251]	eta 0:00:46 lr 0.000011	time 2.5445 (2.2030)	loss 2.6476 (2.9743)	grad_norm 3.4206 (3.3193)	
[2022-01-27 02:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1240/1251]	eta 0:00:24 lr 0.000011	time 1.2534 (2.2000)	loss 3.4282 (2.9758)	grad_norm 2.9775 (3.3191)	
[2022-01-27 02:49:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [292/300][1250/1251]	eta 0:00:02 lr 0.000011	time 1.1954 (2.1935)	loss 2.1785 (2.9740)	grad_norm 3.4329 (3.3184)	
[2022-01-27 02:49:46 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 292 training takes 0:45:44
[2022-01-27 02:50:05 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 19.187 (19.187)	Loss 0.8135 (0.8135)	Acc@1 80.762 (80.762)	Acc@5 94.629 (94.629)	
[2022-01-27 02:50:24 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.237 (3.415)	Loss 0.7571 (0.7901)	Acc@1 82.129 (81.365)	Acc@5 95.996 (95.517)	
[2022-01-27 02:50:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.300 (2.580)	Loss 0.7654 (0.7906)	Acc@1 82.715 (81.427)	Acc@5 95.801 (95.587)	
[2022-01-27 02:51:00 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.685 (2.387)	Loss 0.8732 (0.8024)	Acc@1 78.906 (81.244)	Acc@5 94.922 (95.464)	
[2022-01-27 02:51:18 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.307 (2.233)	Loss 0.7417 (0.7987)	Acc@1 82.812 (81.221)	Acc@5 95.703 (95.570)	
[2022-01-27 02:51:26 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.184 Acc@5 95.476
[2022-01-27 02:51:26 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.2%
[2022-01-27 02:51:26 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.24%
[2022-01-27 02:51:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][0/1251]	eta 8:12:52 lr 0.000011	time 23.6393 (23.6393)	loss 3.0192 (3.0192)	grad_norm 3.1149 (3.1149)	
[2022-01-27 02:52:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][10/1251]	eta 1:28:53 lr 0.000011	time 2.0564 (4.2977)	loss 2.4209 (2.9805)	grad_norm 2.9445 (3.0119)	
[2022-01-27 02:52:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][20/1251]	eta 1:05:51 lr 0.000011	time 1.5143 (3.2097)	loss 2.7065 (3.0553)	grad_norm 2.9736 (3.1855)	
[2022-01-27 02:52:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][30/1251]	eta 0:59:09 lr 0.000011	time 1.6485 (2.9068)	loss 3.1428 (2.9826)	grad_norm 3.9960 (3.2874)	
[2022-01-27 02:53:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][40/1251]	eta 0:55:31 lr 0.000011	time 3.8478 (2.7510)	loss 2.6789 (2.9330)	grad_norm 2.7372 (3.2609)	
[2022-01-27 02:53:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][50/1251]	eta 0:52:48 lr 0.000011	time 2.0815 (2.6379)	loss 3.1345 (2.9642)	grad_norm 3.9450 (3.2870)	
[2022-01-27 02:54:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][60/1251]	eta 0:50:50 lr 0.000011	time 1.6011 (2.5617)	loss 3.0680 (2.9610)	grad_norm 3.8433 (3.2782)	
[2022-01-27 02:54:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][70/1251]	eta 0:49:20 lr 0.000011	time 1.8135 (2.5064)	loss 2.6315 (2.9901)	grad_norm 2.8228 (3.3011)	
[2022-01-27 02:54:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][80/1251]	eta 0:48:17 lr 0.000011	time 3.5443 (2.4746)	loss 2.8132 (3.0016)	grad_norm 3.1616 (3.2947)	
[2022-01-27 02:55:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][90/1251]	eta 0:47:12 lr 0.000011	time 1.8905 (2.4400)	loss 3.4156 (3.0040)	grad_norm 3.6367 (3.3048)	
[2022-01-27 02:55:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][100/1251]	eta 0:46:19 lr 0.000011	time 2.1977 (2.4148)	loss 3.6240 (2.9739)	grad_norm 4.5367 (3.3305)	
[2022-01-27 02:55:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][110/1251]	eta 0:45:05 lr 0.000011	time 1.8190 (2.3712)	loss 3.4099 (2.9585)	grad_norm 3.3392 (3.3174)	
[2022-01-27 02:56:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][120/1251]	eta 0:44:25 lr 0.000011	time 3.0113 (2.3563)	loss 3.1507 (2.9419)	grad_norm 3.5864 (3.3161)	
[2022-01-27 02:56:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][130/1251]	eta 0:43:40 lr 0.000011	time 1.7266 (2.3373)	loss 1.9254 (2.9410)	grad_norm 3.3607 (3.3344)	
[2022-01-27 02:56:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][140/1251]	eta 0:43:04 lr 0.000011	time 2.4831 (2.3260)	loss 3.3248 (2.9590)	grad_norm 2.8816 (3.3415)	
[2022-01-27 02:57:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][150/1251]	eta 0:42:27 lr 0.000011	time 2.2880 (2.3140)	loss 2.8833 (2.9528)	grad_norm 4.1634 (3.3435)	
[2022-01-27 02:57:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][160/1251]	eta 0:41:50 lr 0.000011	time 2.4782 (2.3010)	loss 3.3552 (2.9477)	grad_norm 3.8082 (3.3435)	
[2022-01-27 02:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][170/1251]	eta 0:41:26 lr 0.000011	time 2.2076 (2.3002)	loss 1.9221 (2.9407)	grad_norm 3.1351 (3.3267)	
[2022-01-27 02:58:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][180/1251]	eta 0:40:54 lr 0.000011	time 2.1694 (2.2918)	loss 2.7143 (2.9411)	grad_norm 3.0705 (3.3248)	
[2022-01-27 02:58:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][190/1251]	eta 0:40:28 lr 0.000011	time 2.1959 (2.2884)	loss 2.8182 (2.9327)	grad_norm 2.7977 (3.3241)	
[2022-01-27 02:59:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][200/1251]	eta 0:40:04 lr 0.000011	time 2.9304 (2.2883)	loss 3.3732 (2.9466)	grad_norm 3.3561 (3.3307)	
[2022-01-27 02:59:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][210/1251]	eta 0:39:31 lr 0.000011	time 1.8431 (2.2783)	loss 3.3335 (2.9448)	grad_norm 2.9648 (3.3296)	
[2022-01-27 02:59:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][220/1251]	eta 0:38:59 lr 0.000011	time 2.2629 (2.2692)	loss 2.6335 (2.9473)	grad_norm 2.9243 (3.3257)	
[2022-01-27 03:00:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][230/1251]	eta 0:38:36 lr 0.000011	time 2.0304 (2.2687)	loss 2.2040 (2.9436)	grad_norm 3.2230 (3.3277)	
[2022-01-27 03:00:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][240/1251]	eta 0:38:14 lr 0.000011	time 2.9103 (2.2691)	loss 2.4540 (2.9441)	grad_norm 2.9508 (3.3278)	
[2022-01-27 03:00:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][250/1251]	eta 0:37:50 lr 0.000011	time 1.7485 (2.2679)	loss 3.6428 (2.9539)	grad_norm 3.0177 (3.3244)	
[2022-01-27 03:01:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][260/1251]	eta 0:37:20 lr 0.000011	time 1.8850 (2.2613)	loss 3.3838 (2.9657)	grad_norm 3.0497 (3.3232)	
[2022-01-27 03:01:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][270/1251]	eta 0:36:57 lr 0.000011	time 2.1744 (2.2600)	loss 3.2045 (2.9615)	grad_norm 3.2319 (3.3335)	
[2022-01-27 03:02:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][280/1251]	eta 0:36:31 lr 0.000011	time 2.8051 (2.2565)	loss 3.3895 (2.9591)	grad_norm 2.7285 (3.3263)	
[2022-01-27 03:02:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][290/1251]	eta 0:36:08 lr 0.000011	time 2.2264 (2.2566)	loss 2.9029 (2.9615)	grad_norm 3.6238 (3.3211)	
[2022-01-27 03:02:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][300/1251]	eta 0:35:41 lr 0.000011	time 2.1930 (2.2522)	loss 3.6252 (2.9578)	grad_norm 3.4917 (3.3164)	
[2022-01-27 03:03:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][310/1251]	eta 0:35:16 lr 0.000011	time 1.9365 (2.2495)	loss 3.1126 (2.9601)	grad_norm 3.1410 (3.3146)	
[2022-01-27 03:03:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][320/1251]	eta 0:34:48 lr 0.000011	time 1.6561 (2.2433)	loss 3.5191 (2.9616)	grad_norm 3.4204 (3.3148)	
[2022-01-27 03:03:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][330/1251]	eta 0:34:20 lr 0.000011	time 1.9324 (2.2370)	loss 3.2552 (2.9702)	grad_norm 3.2809 (3.3149)	
[2022-01-27 03:04:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][340/1251]	eta 0:33:57 lr 0.000011	time 1.9610 (2.2361)	loss 3.6681 (2.9751)	grad_norm 2.9387 (3.3149)	
[2022-01-27 03:04:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][350/1251]	eta 0:33:34 lr 0.000011	time 1.9368 (2.2357)	loss 3.4014 (2.9767)	grad_norm 2.8701 (3.3083)	
[2022-01-27 03:04:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][360/1251]	eta 0:33:11 lr 0.000011	time 2.5706 (2.2348)	loss 1.9846 (2.9802)	grad_norm 3.0493 (3.3101)	
[2022-01-27 03:05:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][370/1251]	eta 0:32:47 lr 0.000011	time 1.9824 (2.2331)	loss 3.4417 (2.9811)	grad_norm 4.6269 (3.3127)	
[2022-01-27 03:05:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][380/1251]	eta 0:32:23 lr 0.000011	time 1.9330 (2.2314)	loss 2.4620 (2.9766)	grad_norm 3.2972 (3.3150)	
[2022-01-27 03:05:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][390/1251]	eta 0:32:01 lr 0.000011	time 1.6728 (2.2320)	loss 1.9582 (2.9744)	grad_norm 3.0156 (3.3252)	
[2022-01-27 03:06:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][400/1251]	eta 0:31:45 lr 0.000011	time 2.0723 (2.2390)	loss 3.1326 (2.9779)	grad_norm 3.2611 (3.3207)	
[2022-01-27 03:06:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][410/1251]	eta 0:31:21 lr 0.000011	time 1.8456 (2.2375)	loss 3.5369 (2.9764)	grad_norm 3.3831 (3.3180)	
[2022-01-27 03:07:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][420/1251]	eta 0:30:53 lr 0.000011	time 1.9492 (2.2308)	loss 3.4885 (2.9763)	grad_norm 2.9693 (3.3184)	
[2022-01-27 03:07:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][430/1251]	eta 0:30:29 lr 0.000011	time 1.8842 (2.2285)	loss 3.1204 (2.9771)	grad_norm 3.3483 (3.3299)	
[2022-01-27 03:07:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][440/1251]	eta 0:30:06 lr 0.000011	time 1.8867 (2.2274)	loss 3.4403 (2.9813)	grad_norm 3.0141 (3.3304)	
[2022-01-27 03:08:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][450/1251]	eta 0:29:43 lr 0.000011	time 1.8018 (2.2268)	loss 3.5386 (2.9831)	grad_norm 3.0342 (3.3309)	
[2022-01-27 03:08:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][460/1251]	eta 0:29:22 lr 0.000011	time 2.1987 (2.2278)	loss 3.3990 (2.9832)	grad_norm 3.0501 (3.3350)	
[2022-01-27 03:08:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][470/1251]	eta 0:28:59 lr 0.000011	time 1.5701 (2.2267)	loss 2.3965 (2.9832)	grad_norm 3.6468 (3.3387)	
[2022-01-27 03:09:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][480/1251]	eta 0:28:36 lr 0.000011	time 1.8775 (2.2257)	loss 3.3477 (2.9826)	grad_norm 2.8178 (3.3332)	
[2022-01-27 03:09:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][490/1251]	eta 0:28:14 lr 0.000011	time 1.8521 (2.2273)	loss 3.0521 (2.9840)	grad_norm 4.3102 (3.3379)	
[2022-01-27 03:10:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][500/1251]	eta 0:27:54 lr 0.000011	time 3.0829 (2.2300)	loss 3.2344 (2.9820)	grad_norm 2.7763 (3.3354)	
[2022-01-27 03:10:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][510/1251]	eta 0:27:33 lr 0.000011	time 1.5951 (2.2310)	loss 3.3348 (2.9825)	grad_norm 3.1453 (3.3338)	
[2022-01-27 03:10:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][520/1251]	eta 0:27:08 lr 0.000011	time 1.5709 (2.2281)	loss 1.9544 (2.9791)	grad_norm 3.1141 (3.3307)	
[2022-01-27 03:11:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][530/1251]	eta 0:26:45 lr 0.000011	time 1.6896 (2.2266)	loss 2.7665 (2.9787)	grad_norm 3.5578 (3.3368)	
[2022-01-27 03:11:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][540/1251]	eta 0:26:22 lr 0.000011	time 1.7988 (2.2262)	loss 2.1277 (2.9763)	grad_norm 3.7642 (3.3462)	
[2022-01-27 03:11:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][550/1251]	eta 0:26:02 lr 0.000011	time 1.7381 (2.2292)	loss 3.3186 (2.9776)	grad_norm 3.0206 (3.3439)	
[2022-01-27 03:12:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][560/1251]	eta 0:25:37 lr 0.000011	time 1.6912 (2.2254)	loss 2.8445 (2.9760)	grad_norm 2.9920 (3.3467)	
[2022-01-27 03:12:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][570/1251]	eta 0:25:14 lr 0.000011	time 1.9794 (2.2245)	loss 3.2483 (2.9775)	grad_norm 3.4463 (3.3490)	
[2022-01-27 03:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][580/1251]	eta 0:24:51 lr 0.000011	time 1.5241 (2.2226)	loss 3.0019 (2.9808)	grad_norm 3.3302 (3.3657)	
[2022-01-27 03:13:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][590/1251]	eta 0:24:32 lr 0.000011	time 1.9127 (2.2272)	loss 3.0035 (2.9791)	grad_norm 3.2934 (3.3689)	
[2022-01-27 03:13:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][600/1251]	eta 0:24:08 lr 0.000011	time 1.9089 (2.2247)	loss 3.1721 (2.9776)	grad_norm 3.4424 (3.3700)	
[2022-01-27 03:14:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][610/1251]	eta 0:23:44 lr 0.000011	time 1.8989 (2.2222)	loss 3.4909 (2.9707)	grad_norm 3.4174 (3.3708)	
[2022-01-27 03:14:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][620/1251]	eta 0:23:20 lr 0.000011	time 1.7478 (2.2199)	loss 3.1100 (2.9686)	grad_norm 3.2000 (3.3778)	
[2022-01-27 03:14:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][630/1251]	eta 0:22:57 lr 0.000011	time 1.8705 (2.2176)	loss 3.0216 (2.9710)	grad_norm 2.9560 (3.3791)	
[2022-01-27 03:15:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][640/1251]	eta 0:22:33 lr 0.000011	time 2.5275 (2.2153)	loss 3.4276 (2.9700)	grad_norm 3.0116 (3.3792)	
[2022-01-27 03:15:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][650/1251]	eta 0:22:09 lr 0.000011	time 2.1121 (2.2129)	loss 2.3730 (2.9677)	grad_norm 3.6054 (3.3786)	
[2022-01-27 03:15:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][660/1251]	eta 0:21:47 lr 0.000011	time 1.9992 (2.2119)	loss 1.9207 (2.9659)	grad_norm 2.9423 (3.3771)	
[2022-01-27 03:16:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][670/1251]	eta 0:21:24 lr 0.000011	time 2.6373 (2.2117)	loss 2.4559 (2.9680)	grad_norm 2.6997 (3.3737)	
[2022-01-27 03:16:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][680/1251]	eta 0:21:02 lr 0.000011	time 1.9818 (2.2116)	loss 2.3345 (2.9711)	grad_norm 3.4456 (3.3714)	
[2022-01-27 03:16:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][690/1251]	eta 0:20:41 lr 0.000011	time 2.4845 (2.2127)	loss 3.2855 (2.9695)	grad_norm 3.2637 (3.3739)	
[2022-01-27 03:17:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][700/1251]	eta 0:20:20 lr 0.000011	time 1.9319 (2.2158)	loss 1.8644 (2.9681)	grad_norm 3.4753 (3.3717)	
[2022-01-27 03:17:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][710/1251]	eta 0:19:59 lr 0.000011	time 2.6551 (2.2167)	loss 1.9554 (2.9672)	grad_norm 3.3299 (3.3703)	
[2022-01-27 03:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][720/1251]	eta 0:19:36 lr 0.000011	time 1.9448 (2.2147)	loss 3.0862 (2.9640)	grad_norm 2.9619 (3.3701)	
[2022-01-27 03:18:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][730/1251]	eta 0:19:13 lr 0.000011	time 2.1503 (2.2148)	loss 2.7283 (2.9621)	grad_norm 3.2324 (3.3692)	
[2022-01-27 03:18:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][740/1251]	eta 0:18:51 lr 0.000011	time 1.7462 (2.2151)	loss 2.8354 (2.9623)	grad_norm 3.1213 (3.3701)	
[2022-01-27 03:19:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][750/1251]	eta 0:18:28 lr 0.000011	time 2.1212 (2.2127)	loss 2.6254 (2.9632)	grad_norm 3.0924 (3.3693)	
[2022-01-27 03:19:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][760/1251]	eta 0:18:05 lr 0.000011	time 1.7061 (2.2113)	loss 2.5167 (2.9609)	grad_norm 4.8815 (3.3706)	
[2022-01-27 03:19:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][770/1251]	eta 0:17:44 lr 0.000011	time 2.8984 (2.2134)	loss 3.2708 (2.9634)	grad_norm 3.5743 (3.3752)	
[2022-01-27 03:20:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][780/1251]	eta 0:17:23 lr 0.000011	time 2.5376 (2.2152)	loss 3.5442 (2.9647)	grad_norm 2.9995 (3.3746)	
[2022-01-27 03:20:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][790/1251]	eta 0:17:01 lr 0.000011	time 1.7684 (2.2150)	loss 2.6981 (2.9617)	grad_norm 3.0720 (3.3740)	
[2022-01-27 03:20:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][800/1251]	eta 0:16:38 lr 0.000011	time 1.7903 (2.2134)	loss 1.9479 (2.9630)	grad_norm 3.2749 (3.3747)	
[2022-01-27 03:21:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][810/1251]	eta 0:16:14 lr 0.000011	time 1.7137 (2.2103)	loss 2.7380 (2.9638)	grad_norm 3.3656 (3.3738)	
[2022-01-27 03:21:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][820/1251]	eta 0:15:52 lr 0.000011	time 2.2168 (2.2089)	loss 3.4449 (2.9649)	grad_norm 3.7243 (3.3735)	
[2022-01-27 03:22:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][830/1251]	eta 0:15:29 lr 0.000011	time 1.7891 (2.2084)	loss 2.7181 (2.9645)	grad_norm 4.6952 (3.3758)	
[2022-01-27 03:22:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][840/1251]	eta 0:15:07 lr 0.000011	time 2.2365 (2.2078)	loss 3.3525 (2.9634)	grad_norm 3.1123 (3.3740)	
[2022-01-27 03:22:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][850/1251]	eta 0:14:44 lr 0.000011	time 1.8841 (2.2068)	loss 2.2638 (2.9622)	grad_norm 3.3681 (3.3722)	
[2022-01-27 03:23:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][860/1251]	eta 0:14:22 lr 0.000011	time 2.5481 (2.2059)	loss 3.4697 (2.9637)	grad_norm 3.1348 (3.3719)	
[2022-01-27 03:23:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][870/1251]	eta 0:14:00 lr 0.000011	time 1.6822 (2.2056)	loss 3.1545 (2.9632)	grad_norm 2.9311 (3.3686)	
[2022-01-27 03:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][880/1251]	eta 0:13:38 lr 0.000011	time 2.6637 (2.2065)	loss 3.3246 (2.9636)	grad_norm 2.9101 (3.3689)	
[2022-01-27 03:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][890/1251]	eta 0:13:16 lr 0.000011	time 1.6053 (2.2055)	loss 3.0554 (2.9639)	grad_norm 3.6835 (3.3693)	
[2022-01-27 03:24:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][900/1251]	eta 0:12:53 lr 0.000011	time 2.1492 (2.2044)	loss 3.4043 (2.9626)	grad_norm 3.2867 (3.3670)	
[2022-01-27 03:24:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][910/1251]	eta 0:12:32 lr 0.000011	time 1.8975 (2.2058)	loss 2.8866 (2.9616)	grad_norm 3.2775 (3.3654)	
[2022-01-27 03:25:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][920/1251]	eta 0:12:10 lr 0.000011	time 2.5012 (2.2078)	loss 3.2641 (2.9634)	grad_norm 2.7746 (3.3648)	
[2022-01-27 03:25:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][930/1251]	eta 0:11:48 lr 0.000011	time 2.2293 (2.2069)	loss 3.4488 (2.9640)	grad_norm 3.2987 (3.3672)	
[2022-01-27 03:26:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][940/1251]	eta 0:11:26 lr 0.000011	time 1.9308 (2.2068)	loss 3.2970 (2.9657)	grad_norm 3.8949 (3.3681)	
[2022-01-27 03:26:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][950/1251]	eta 0:11:03 lr 0.000011	time 1.9030 (2.2045)	loss 2.9136 (2.9656)	grad_norm 2.8420 (3.3668)	
[2022-01-27 03:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][960/1251]	eta 0:10:41 lr 0.000011	time 2.5026 (2.2037)	loss 3.1678 (2.9648)	grad_norm 3.2323 (3.3650)	
[2022-01-27 03:27:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][970/1251]	eta 0:10:19 lr 0.000011	time 1.8885 (2.2046)	loss 3.1881 (2.9649)	grad_norm 3.2255 (3.3630)	
[2022-01-27 03:27:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][980/1251]	eta 0:09:57 lr 0.000011	time 2.2119 (2.2049)	loss 3.3589 (2.9663)	grad_norm 3.2262 (3.3615)	
[2022-01-27 03:27:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][990/1251]	eta 0:09:35 lr 0.000011	time 2.4106 (2.2063)	loss 2.5143 (2.9663)	grad_norm 4.0411 (3.3620)	
[2022-01-27 03:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1000/1251]	eta 0:09:13 lr 0.000011	time 3.3206 (2.2066)	loss 1.8266 (2.9642)	grad_norm 2.9485 (3.3606)	
[2022-01-27 03:28:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1010/1251]	eta 0:08:51 lr 0.000011	time 2.0889 (2.2054)	loss 3.1462 (2.9633)	grad_norm 3.6286 (3.3602)	
[2022-01-27 03:28:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1020/1251]	eta 0:08:29 lr 0.000011	time 1.9868 (2.2037)	loss 2.3872 (2.9613)	grad_norm 3.1890 (3.3582)	
[2022-01-27 03:29:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1030/1251]	eta 0:08:06 lr 0.000011	time 2.2101 (2.2033)	loss 2.9295 (2.9595)	grad_norm 3.0618 (3.3597)	
[2022-01-27 03:29:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1040/1251]	eta 0:07:44 lr 0.000011	time 2.4772 (2.2038)	loss 2.5454 (2.9597)	grad_norm 3.3125 (3.3613)	
[2022-01-27 03:30:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1050/1251]	eta 0:07:23 lr 0.000011	time 3.3999 (2.2052)	loss 2.4099 (2.9577)	grad_norm 3.4000 (3.3640)	
[2022-01-27 03:30:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1060/1251]	eta 0:07:01 lr 0.000011	time 2.2397 (2.2057)	loss 3.1990 (2.9573)	grad_norm 3.7954 (3.3636)	
[2022-01-27 03:30:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1070/1251]	eta 0:06:38 lr 0.000011	time 1.5652 (2.2038)	loss 1.9553 (2.9560)	grad_norm 4.2520 (3.3635)	
[2022-01-27 03:31:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1080/1251]	eta 0:06:16 lr 0.000011	time 1.9624 (2.2012)	loss 3.2125 (2.9566)	grad_norm 3.4446 (3.3638)	
[2022-01-27 03:31:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1090/1251]	eta 0:05:54 lr 0.000011	time 3.0673 (2.2008)	loss 3.6006 (2.9570)	grad_norm 3.0262 (3.3715)	
[2022-01-27 03:31:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1100/1251]	eta 0:05:32 lr 0.000011	time 1.9003 (2.1994)	loss 3.2348 (2.9581)	grad_norm 3.1169 (3.3748)	
[2022-01-27 03:32:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1110/1251]	eta 0:05:10 lr 0.000011	time 2.2157 (2.1988)	loss 2.0112 (2.9568)	grad_norm 3.2797 (3.3749)	
[2022-01-27 03:32:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1120/1251]	eta 0:04:48 lr 0.000011	time 2.3650 (2.1987)	loss 3.4382 (2.9578)	grad_norm 3.1957 (3.3743)	
[2022-01-27 03:32:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1130/1251]	eta 0:04:26 lr 0.000011	time 2.6568 (2.1998)	loss 3.6484 (2.9583)	grad_norm 3.4526 (3.3739)	
[2022-01-27 03:33:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1140/1251]	eta 0:04:04 lr 0.000011	time 2.2095 (2.2001)	loss 2.2251 (2.9567)	grad_norm 3.4256 (3.3737)	
[2022-01-27 03:33:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1150/1251]	eta 0:03:42 lr 0.000011	time 2.4995 (2.2022)	loss 3.3212 (2.9573)	grad_norm 3.1807 (3.3719)	
[2022-01-27 03:34:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1160/1251]	eta 0:03:20 lr 0.000011	time 2.6427 (2.2042)	loss 3.3140 (2.9556)	grad_norm 3.2087 (3.3704)	
[2022-01-27 03:34:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1170/1251]	eta 0:02:58 lr 0.000011	time 1.8390 (2.2041)	loss 2.5877 (2.9547)	grad_norm 3.8200 (3.3700)	
[2022-01-27 03:34:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1180/1251]	eta 0:02:36 lr 0.000011	time 1.5653 (2.2023)	loss 2.2088 (2.9522)	grad_norm 3.1593 (3.3694)	
[2022-01-27 03:35:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1190/1251]	eta 0:02:14 lr 0.000011	time 1.6136 (2.1995)	loss 3.8053 (2.9535)	grad_norm 3.1414 (3.3679)	
[2022-01-27 03:35:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1200/1251]	eta 0:01:52 lr 0.000011	time 2.7912 (2.1986)	loss 3.1576 (2.9530)	grad_norm 3.2795 (3.3724)	
[2022-01-27 03:35:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1210/1251]	eta 0:01:30 lr 0.000011	time 2.0761 (2.1982)	loss 2.1006 (2.9507)	grad_norm 3.7951 (3.3726)	
[2022-01-27 03:36:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1220/1251]	eta 0:01:08 lr 0.000011	time 2.1299 (2.1982)	loss 2.7772 (2.9516)	grad_norm 3.7241 (3.3745)	
[2022-01-27 03:36:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1230/1251]	eta 0:00:46 lr 0.000011	time 1.7363 (2.1991)	loss 2.8620 (2.9506)	grad_norm 3.5422 (3.3742)	
[2022-01-27 03:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1240/1251]	eta 0:00:24 lr 0.000011	time 1.6963 (2.1995)	loss 2.0234 (2.9513)	grad_norm 2.7401 (3.3742)	
[2022-01-27 03:37:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [293/300][1250/1251]	eta 0:00:02 lr 0.000011	time 1.2192 (2.1946)	loss 1.8022 (2.9504)	grad_norm 3.3364 (3.3747)	
[2022-01-27 03:37:12 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 293 training takes 0:45:45
[2022-01-27 03:37:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.499 (18.499)	Loss 0.7750 (0.7750)	Acc@1 82.129 (82.129)	Acc@5 95.605 (95.605)	
[2022-01-27 03:37:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.267 (3.295)	Loss 0.7886 (0.8096)	Acc@1 82.031 (81.241)	Acc@5 96.094 (95.490)	
[2022-01-27 03:38:04 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.297 (2.505)	Loss 0.7798 (0.8105)	Acc@1 82.227 (81.027)	Acc@5 95.117 (95.480)	
[2022-01-27 03:38:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.267 (2.163)	Loss 0.7799 (0.8000)	Acc@1 81.055 (81.250)	Acc@5 95.801 (95.621)	
[2022-01-27 03:38:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.312 (2.162)	Loss 0.7775 (0.8073)	Acc@1 81.641 (81.074)	Acc@5 96.094 (95.544)	
[2022-01-27 03:38:48 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.146 Acc@5 95.518
[2022-01-27 03:38:48 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.1%
[2022-01-27 03:38:48 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.24%
[2022-01-27 03:39:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][0/1251]	eta 7:35:34 lr 0.000011	time 21.8500 (21.8500)	loss 3.2696 (3.2696)	grad_norm 2.8930 (2.8930)	
[2022-01-27 03:39:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][10/1251]	eta 1:24:55 lr 0.000011	time 2.2713 (4.1058)	loss 3.5291 (3.1076)	grad_norm 3.5148 (3.3367)	
[2022-01-27 03:39:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][20/1251]	eta 1:04:28 lr 0.000011	time 1.4443 (3.1426)	loss 3.3036 (3.0814)	grad_norm 3.1402 (3.3631)	
[2022-01-27 03:40:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][30/1251]	eta 0:57:39 lr 0.000011	time 1.7879 (2.8334)	loss 3.1555 (3.0777)	grad_norm 3.0539 (3.4311)	
[2022-01-27 03:40:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][40/1251]	eta 0:55:30 lr 0.000011	time 4.2523 (2.7499)	loss 3.1246 (3.0710)	grad_norm 3.0102 (3.4066)	
[2022-01-27 03:41:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][50/1251]	eta 0:52:08 lr 0.000011	time 1.4625 (2.6051)	loss 2.1957 (3.0669)	grad_norm 8.8201 (3.4781)	
[2022-01-27 03:41:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][60/1251]	eta 0:50:38 lr 0.000011	time 2.3913 (2.5514)	loss 3.1455 (3.0063)	grad_norm 3.8300 (3.4359)	
[2022-01-27 03:41:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][70/1251]	eta 0:49:23 lr 0.000011	time 1.5314 (2.5092)	loss 2.4575 (3.0129)	grad_norm 3.0981 (3.4431)	
[2022-01-27 03:42:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][80/1251]	eta 0:48:43 lr 0.000011	time 3.8866 (2.4969)	loss 3.1216 (3.0034)	grad_norm 2.9884 (3.4308)	
[2022-01-27 03:42:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][90/1251]	eta 0:47:39 lr 0.000011	time 1.5430 (2.4628)	loss 2.0605 (2.9832)	grad_norm 2.8678 (3.4204)	
[2022-01-27 03:42:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][100/1251]	eta 0:46:22 lr 0.000011	time 1.6795 (2.4175)	loss 2.8034 (2.9858)	grad_norm 3.4476 (3.4150)	
[2022-01-27 03:43:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][110/1251]	eta 0:45:17 lr 0.000011	time 1.9323 (2.3813)	loss 2.7092 (2.9720)	grad_norm 3.1346 (3.3989)	
[2022-01-27 03:43:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][120/1251]	eta 0:44:28 lr 0.000011	time 3.4061 (2.3594)	loss 3.2477 (2.9919)	grad_norm 3.1338 (3.3894)	
[2022-01-27 03:43:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][130/1251]	eta 0:43:57 lr 0.000011	time 1.4975 (2.3532)	loss 2.4409 (2.9749)	grad_norm 3.6638 (3.3862)	
[2022-01-27 03:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][140/1251]	eta 0:43:23 lr 0.000011	time 2.5828 (2.3437)	loss 3.3722 (2.9938)	grad_norm 3.2894 (3.3720)	
[2022-01-27 03:44:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][150/1251]	eta 0:42:55 lr 0.000011	time 2.4919 (2.3395)	loss 2.8116 (2.9849)	grad_norm 3.3954 (3.3631)	
[2022-01-27 03:45:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][160/1251]	eta 0:42:28 lr 0.000011	time 3.5076 (2.3363)	loss 3.2058 (2.9908)	grad_norm 2.7123 (3.3520)	
[2022-01-27 03:45:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][170/1251]	eta 0:41:48 lr 0.000011	time 1.5287 (2.3207)	loss 3.4592 (2.9960)	grad_norm 4.0189 (3.3420)	
[2022-01-27 03:45:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][180/1251]	eta 0:41:18 lr 0.000011	time 1.5876 (2.3141)	loss 3.2382 (2.9990)	grad_norm 3.1391 (3.3310)	
[2022-01-27 03:46:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][190/1251]	eta 0:40:48 lr 0.000011	time 1.5933 (2.3075)	loss 3.2960 (3.0025)	grad_norm 3.3959 (3.3410)	
[2022-01-27 03:46:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][200/1251]	eta 0:40:29 lr 0.000011	time 4.1942 (2.3111)	loss 2.6070 (2.9970)	grad_norm 2.8701 (3.3445)	
[2022-01-27 03:46:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][210/1251]	eta 0:40:14 lr 0.000011	time 1.9627 (2.3198)	loss 2.7924 (2.9765)	grad_norm 2.8275 (3.3450)	
[2022-01-27 03:47:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][220/1251]	eta 0:39:35 lr 0.000011	time 1.6441 (2.3040)	loss 2.6324 (2.9792)	grad_norm 3.3055 (3.3348)	
[2022-01-27 03:47:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][230/1251]	eta 0:38:58 lr 0.000011	time 1.6429 (2.2906)	loss 2.4307 (2.9706)	grad_norm 2.8564 (3.3389)	
[2022-01-27 03:47:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][240/1251]	eta 0:38:28 lr 0.000011	time 2.7526 (2.2839)	loss 3.0877 (2.9732)	grad_norm 2.8369 (3.3363)	
[2022-01-27 03:48:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][250/1251]	eta 0:38:01 lr 0.000011	time 2.1031 (2.2795)	loss 3.2385 (2.9668)	grad_norm 3.2337 (3.3309)	
[2022-01-27 03:48:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][260/1251]	eta 0:37:34 lr 0.000011	time 1.8991 (2.2753)	loss 2.4289 (2.9643)	grad_norm 3.1113 (3.3290)	
[2022-01-27 03:49:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][270/1251]	eta 0:37:10 lr 0.000011	time 3.0169 (2.2739)	loss 3.2393 (2.9585)	grad_norm 3.3984 (3.3421)	
[2022-01-27 03:49:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][280/1251]	eta 0:36:47 lr 0.000011	time 2.9139 (2.2730)	loss 3.4110 (2.9672)	grad_norm 3.0685 (3.3358)	
[2022-01-27 03:49:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][290/1251]	eta 0:36:23 lr 0.000011	time 1.5798 (2.2717)	loss 2.7265 (2.9653)	grad_norm 2.9634 (3.3340)	
[2022-01-27 03:50:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][300/1251]	eta 0:36:00 lr 0.000011	time 1.6895 (2.2715)	loss 1.9768 (2.9614)	grad_norm 3.3623 (3.3291)	
[2022-01-27 03:50:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][310/1251]	eta 0:35:35 lr 0.000011	time 2.3912 (2.2692)	loss 3.1108 (2.9647)	grad_norm 3.3249 (3.3322)	
[2022-01-27 03:50:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][320/1251]	eta 0:35:04 lr 0.000011	time 1.8673 (2.2609)	loss 3.0323 (2.9669)	grad_norm 3.5908 (3.3272)	
[2022-01-27 03:51:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][330/1251]	eta 0:34:32 lr 0.000011	time 1.8754 (2.2504)	loss 3.2452 (2.9698)	grad_norm 3.1640 (3.3282)	
[2022-01-27 03:51:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][340/1251]	eta 0:34:03 lr 0.000011	time 1.8256 (2.2434)	loss 3.6822 (2.9700)	grad_norm 3.4756 (3.3295)	
[2022-01-27 03:51:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][350/1251]	eta 0:33:41 lr 0.000011	time 2.6192 (2.2432)	loss 3.4451 (2.9752)	grad_norm 3.2097 (3.3238)	
[2022-01-27 03:52:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][360/1251]	eta 0:33:17 lr 0.000011	time 2.5610 (2.2417)	loss 3.4937 (2.9730)	grad_norm 3.4022 (3.3253)	
[2022-01-27 03:52:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][370/1251]	eta 0:32:56 lr 0.000011	time 1.5615 (2.2431)	loss 3.6825 (2.9678)	grad_norm 3.0474 (3.3200)	
[2022-01-27 03:53:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][380/1251]	eta 0:32:36 lr 0.000011	time 2.9623 (2.2457)	loss 2.2769 (2.9679)	grad_norm 3.7677 (3.3272)	
[2022-01-27 03:53:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][390/1251]	eta 0:32:15 lr 0.000011	time 2.9313 (2.2484)	loss 2.7337 (2.9718)	grad_norm 3.1044 (3.3268)	
[2022-01-27 03:53:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][400/1251]	eta 0:31:55 lr 0.000011	time 2.2291 (2.2506)	loss 3.3453 (2.9739)	grad_norm 3.0993 (3.3282)	
[2022-01-27 03:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][410/1251]	eta 0:31:31 lr 0.000011	time 1.9026 (2.2490)	loss 2.6282 (2.9741)	grad_norm 3.4276 (3.3238)	
[2022-01-27 03:54:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][420/1251]	eta 0:31:08 lr 0.000011	time 3.3800 (2.2485)	loss 3.0410 (2.9742)	grad_norm 2.8666 (3.3194)	
[2022-01-27 03:54:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][430/1251]	eta 0:30:39 lr 0.000011	time 1.5915 (2.2403)	loss 2.5545 (2.9711)	grad_norm 3.0629 (3.3167)	
[2022-01-27 03:55:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][440/1251]	eta 0:30:14 lr 0.000011	time 2.5916 (2.2377)	loss 3.0711 (2.9690)	grad_norm 3.7493 (3.3243)	
[2022-01-27 03:55:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][450/1251]	eta 0:29:50 lr 0.000011	time 2.1977 (2.2351)	loss 3.2388 (2.9658)	grad_norm 3.0821 (3.3268)	
[2022-01-27 03:55:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][460/1251]	eta 0:29:29 lr 0.000011	time 1.9659 (2.2367)	loss 1.9762 (2.9588)	grad_norm 3.0924 (3.3242)	
[2022-01-27 03:56:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][470/1251]	eta 0:29:07 lr 0.000011	time 2.2991 (2.2373)	loss 2.7039 (2.9578)	grad_norm 3.1182 (3.3212)	
[2022-01-27 03:56:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][480/1251]	eta 0:28:47 lr 0.000011	time 3.4362 (2.2409)	loss 3.1209 (2.9564)	grad_norm 3.6214 (3.3194)	
[2022-01-27 03:57:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][490/1251]	eta 0:28:24 lr 0.000011	time 1.6176 (2.2402)	loss 3.3719 (2.9611)	grad_norm 3.1662 (3.3165)	
[2022-01-27 03:57:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][500/1251]	eta 0:28:02 lr 0.000011	time 1.9061 (2.2404)	loss 2.5404 (2.9606)	grad_norm 3.0029 (3.3206)	
[2022-01-27 03:57:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][510/1251]	eta 0:27:40 lr 0.000011	time 1.8807 (2.2408)	loss 3.5474 (2.9582)	grad_norm 4.1182 (3.3237)	
[2022-01-27 03:58:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][520/1251]	eta 0:27:15 lr 0.000011	time 2.4996 (2.2375)	loss 1.8617 (2.9544)	grad_norm 2.8959 (3.3229)	
[2022-01-27 03:58:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][530/1251]	eta 0:26:49 lr 0.000011	time 2.3234 (2.2317)	loss 2.5795 (2.9555)	grad_norm 3.2191 (3.3242)	
[2022-01-27 03:58:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][540/1251]	eta 0:26:25 lr 0.000011	time 2.1217 (2.2294)	loss 3.3483 (2.9600)	grad_norm 3.1890 (3.3293)	
[2022-01-27 03:59:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][550/1251]	eta 0:26:01 lr 0.000011	time 2.1588 (2.2280)	loss 3.2023 (2.9635)	grad_norm 3.0955 (3.3262)	
[2022-01-27 03:59:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][560/1251]	eta 0:25:39 lr 0.000011	time 1.8764 (2.2277)	loss 2.9287 (2.9642)	grad_norm 3.0842 (3.3296)	
[2022-01-27 03:59:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][570/1251]	eta 0:25:16 lr 0.000011	time 2.8090 (2.2266)	loss 2.9184 (2.9669)	grad_norm 2.9578 (3.3378)	
[2022-01-27 04:00:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][580/1251]	eta 0:24:55 lr 0.000011	time 2.5135 (2.2281)	loss 3.0767 (2.9619)	grad_norm 3.5660 (3.3361)	
[2022-01-27 04:00:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][590/1251]	eta 0:24:34 lr 0.000011	time 2.0209 (2.2302)	loss 3.2913 (2.9636)	grad_norm 3.3436 (3.3351)	
[2022-01-27 04:01:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][600/1251]	eta 0:24:12 lr 0.000011	time 2.2877 (2.2306)	loss 3.5092 (2.9616)	grad_norm 3.0001 (3.3368)	
[2022-01-27 04:01:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][610/1251]	eta 0:23:48 lr 0.000011	time 2.2063 (2.2289)	loss 3.6147 (2.9624)	grad_norm 3.9276 (3.3401)	
[2022-01-27 04:01:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][620/1251]	eta 0:23:25 lr 0.000011	time 2.1981 (2.2269)	loss 3.2373 (2.9618)	grad_norm 3.4063 (3.3357)	
[2022-01-27 04:02:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][630/1251]	eta 0:23:01 lr 0.000011	time 2.1831 (2.2245)	loss 2.6407 (2.9595)	grad_norm 3.8947 (3.3372)	
[2022-01-27 04:02:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][640/1251]	eta 0:22:37 lr 0.000011	time 1.6299 (2.2222)	loss 3.4276 (2.9645)	grad_norm 2.9513 (3.3342)	
[2022-01-27 04:02:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][650/1251]	eta 0:22:15 lr 0.000011	time 2.7949 (2.2216)	loss 2.7042 (2.9617)	grad_norm 3.4389 (3.3308)	
[2022-01-27 04:03:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][660/1251]	eta 0:21:53 lr 0.000011	time 2.3845 (2.2219)	loss 3.2256 (2.9646)	grad_norm 2.9326 (3.3268)	
[2022-01-27 04:03:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][670/1251]	eta 0:21:31 lr 0.000011	time 2.1504 (2.2226)	loss 3.1277 (2.9675)	grad_norm 2.9923 (3.3269)	
[2022-01-27 04:04:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][680/1251]	eta 0:21:09 lr 0.000011	time 2.4118 (2.2227)	loss 3.3721 (2.9701)	grad_norm 3.3952 (3.3288)	
[2022-01-27 04:04:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][690/1251]	eta 0:20:46 lr 0.000011	time 1.6920 (2.2222)	loss 3.2269 (2.9680)	grad_norm 4.1433 (3.3308)	
[2022-01-27 04:04:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][700/1251]	eta 0:20:22 lr 0.000011	time 1.6347 (2.2190)	loss 3.6544 (2.9657)	grad_norm 3.4489 (3.3288)	
[2022-01-27 04:05:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][710/1251]	eta 0:19:59 lr 0.000011	time 1.8571 (2.2172)	loss 3.1979 (2.9652)	grad_norm 2.9882 (3.3268)	
[2022-01-27 04:05:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][720/1251]	eta 0:19:36 lr 0.000011	time 1.9746 (2.2163)	loss 2.2323 (2.9667)	grad_norm 3.2164 (3.3265)	
[2022-01-27 04:05:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][730/1251]	eta 0:19:14 lr 0.000011	time 2.0936 (2.2163)	loss 2.8571 (2.9658)	grad_norm 2.9502 (3.3217)	
[2022-01-27 04:06:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][740/1251]	eta 0:18:52 lr 0.000011	time 1.9756 (2.2156)	loss 3.2146 (2.9681)	grad_norm 3.1337 (3.3240)	
[2022-01-27 04:06:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][750/1251]	eta 0:18:30 lr 0.000011	time 1.8888 (2.2165)	loss 3.1283 (2.9669)	grad_norm 3.0678 (3.3258)	
[2022-01-27 04:06:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][760/1251]	eta 0:18:09 lr 0.000011	time 1.9019 (2.2183)	loss 2.1966 (2.9667)	grad_norm 3.3126 (3.3265)	
[2022-01-27 04:07:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][770/1251]	eta 0:17:47 lr 0.000011	time 2.3132 (2.2190)	loss 2.9954 (2.9684)	grad_norm 3.2975 (3.3263)	
[2022-01-27 04:07:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][780/1251]	eta 0:17:24 lr 0.000011	time 1.9633 (2.2176)	loss 2.1368 (2.9662)	grad_norm 3.3936 (3.3285)	
[2022-01-27 04:08:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][790/1251]	eta 0:17:01 lr 0.000011	time 1.8056 (2.2158)	loss 3.0054 (2.9652)	grad_norm 3.0592 (3.3274)	
[2022-01-27 04:08:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][800/1251]	eta 0:16:38 lr 0.000011	time 1.8668 (2.2137)	loss 2.4160 (2.9628)	grad_norm 2.9287 (3.3269)	
[2022-01-27 04:08:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][810/1251]	eta 0:16:15 lr 0.000011	time 3.4013 (2.2129)	loss 3.0344 (2.9631)	grad_norm 3.0821 (3.3273)	
[2022-01-27 04:09:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][820/1251]	eta 0:15:53 lr 0.000011	time 2.2583 (2.2126)	loss 3.0262 (2.9644)	grad_norm 3.1829 (3.3278)	
[2022-01-27 04:09:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][830/1251]	eta 0:15:31 lr 0.000011	time 2.1264 (2.2123)	loss 3.1570 (2.9661)	grad_norm 2.7262 (3.3273)	
[2022-01-27 04:09:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][840/1251]	eta 0:15:09 lr 0.000011	time 2.2072 (2.2130)	loss 3.5698 (2.9674)	grad_norm 3.5201 (3.3254)	
[2022-01-27 04:10:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][850/1251]	eta 0:14:47 lr 0.000011	time 2.8157 (2.2143)	loss 3.4004 (2.9692)	grad_norm 3.5965 (3.3229)	
[2022-01-27 04:10:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][860/1251]	eta 0:14:25 lr 0.000011	time 2.2533 (2.2136)	loss 2.4765 (2.9674)	grad_norm 3.1191 (3.3238)	
[2022-01-27 04:10:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][870/1251]	eta 0:14:03 lr 0.000011	time 3.0951 (2.2142)	loss 3.4723 (2.9673)	grad_norm 3.2674 (3.3245)	
[2022-01-27 04:11:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][880/1251]	eta 0:13:40 lr 0.000011	time 1.7236 (2.2117)	loss 2.2833 (2.9658)	grad_norm 3.6335 (3.3277)	
[2022-01-27 04:11:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][890/1251]	eta 0:13:18 lr 0.000011	time 2.4513 (2.2116)	loss 3.0290 (2.9693)	grad_norm 2.8275 (3.3267)	
[2022-01-27 04:12:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][900/1251]	eta 0:12:56 lr 0.000011	time 2.4437 (2.2111)	loss 2.4965 (2.9682)	grad_norm 2.6134 (3.3254)	
[2022-01-27 04:12:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][910/1251]	eta 0:12:33 lr 0.000011	time 2.3434 (2.2104)	loss 3.0361 (2.9700)	grad_norm 3.0023 (3.3274)	
[2022-01-27 04:12:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][920/1251]	eta 0:12:11 lr 0.000011	time 1.8770 (2.2093)	loss 2.1106 (2.9654)	grad_norm 2.9288 (3.3267)	
[2022-01-27 04:13:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][930/1251]	eta 0:11:48 lr 0.000011	time 1.8361 (2.2080)	loss 3.3764 (2.9668)	grad_norm 3.4224 (3.3274)	
[2022-01-27 04:13:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][940/1251]	eta 0:11:26 lr 0.000011	time 2.1889 (2.2086)	loss 3.3809 (2.9676)	grad_norm 4.1375 (3.3290)	
[2022-01-27 04:13:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][950/1251]	eta 0:11:04 lr 0.000011	time 2.2465 (2.2091)	loss 3.0443 (2.9687)	grad_norm 2.8027 (3.3289)	
[2022-01-27 04:14:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][960/1251]	eta 0:10:42 lr 0.000011	time 2.4172 (2.2093)	loss 3.7288 (2.9685)	grad_norm 3.1264 (3.3284)	
[2022-01-27 04:14:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][970/1251]	eta 0:10:21 lr 0.000011	time 1.8795 (2.2112)	loss 2.0110 (2.9680)	grad_norm 3.2630 (3.3262)	
[2022-01-27 04:14:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][980/1251]	eta 0:09:58 lr 0.000011	time 1.9404 (2.2101)	loss 2.8100 (2.9671)	grad_norm 2.8200 (3.3244)	
[2022-01-27 04:15:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][990/1251]	eta 0:09:36 lr 0.000011	time 1.9385 (2.2079)	loss 2.6804 (2.9689)	grad_norm 3.5056 (3.3261)	
[2022-01-27 04:15:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1000/1251]	eta 0:09:13 lr 0.000011	time 1.9064 (2.2061)	loss 1.8569 (2.9684)	grad_norm 2.9616 (3.3252)	
[2022-01-27 04:15:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1010/1251]	eta 0:08:51 lr 0.000011	time 1.6077 (2.2060)	loss 3.3037 (2.9672)	grad_norm 2.9675 (3.3238)	
[2022-01-27 04:16:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1020/1251]	eta 0:08:29 lr 0.000011	time 1.8373 (2.2048)	loss 2.9951 (2.9665)	grad_norm 2.7940 (3.3289)	
[2022-01-27 04:16:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1030/1251]	eta 0:08:06 lr 0.000011	time 2.1563 (2.2034)	loss 3.4003 (2.9653)	grad_norm 3.1310 (3.3277)	
[2022-01-27 04:17:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1040/1251]	eta 0:07:44 lr 0.000011	time 2.0683 (2.2029)	loss 3.2230 (2.9640)	grad_norm 3.1381 (3.3274)	
[2022-01-27 04:17:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1050/1251]	eta 0:07:22 lr 0.000011	time 2.0260 (2.2036)	loss 2.9443 (2.9666)	grad_norm 4.6031 (3.3283)	
[2022-01-27 04:17:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1060/1251]	eta 0:07:00 lr 0.000011	time 2.1807 (2.2038)	loss 1.9578 (2.9663)	grad_norm 3.9561 (3.3280)	
[2022-01-27 04:18:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1070/1251]	eta 0:06:38 lr 0.000011	time 1.7962 (2.2029)	loss 2.7425 (2.9644)	grad_norm 3.7610 (3.3284)	
[2022-01-27 04:18:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1080/1251]	eta 0:06:16 lr 0.000011	time 3.0329 (2.2038)	loss 3.0269 (2.9654)	grad_norm 3.5621 (3.3276)	
[2022-01-27 04:18:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1090/1251]	eta 0:05:54 lr 0.000011	time 2.1843 (2.2043)	loss 2.9939 (2.9667)	grad_norm 2.9016 (3.3272)	
[2022-01-27 04:19:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1100/1251]	eta 0:05:32 lr 0.000011	time 1.7696 (2.2045)	loss 3.3125 (2.9654)	grad_norm 4.1972 (3.3274)	
[2022-01-27 04:19:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1110/1251]	eta 0:05:10 lr 0.000011	time 1.5600 (2.2035)	loss 2.7307 (2.9652)	grad_norm 3.5091 (3.3280)	
[2022-01-27 04:19:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1120/1251]	eta 0:04:48 lr 0.000011	time 2.8302 (2.2045)	loss 3.4645 (2.9652)	grad_norm 3.4524 (3.3269)	
[2022-01-27 04:20:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1130/1251]	eta 0:04:26 lr 0.000011	time 2.1640 (2.2049)	loss 3.2251 (2.9632)	grad_norm 2.8691 (3.3267)	
[2022-01-27 04:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1140/1251]	eta 0:04:04 lr 0.000011	time 1.9406 (2.2036)	loss 2.8194 (2.9622)	grad_norm 3.0933 (3.3264)	
[2022-01-27 04:21:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1150/1251]	eta 0:03:42 lr 0.000011	time 1.7074 (2.2033)	loss 2.2492 (2.9618)	grad_norm 2.9326 (3.3251)	
[2022-01-27 04:21:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1160/1251]	eta 0:03:20 lr 0.000011	time 3.0357 (2.2059)	loss 3.0818 (2.9642)	grad_norm 3.4093 (3.3264)	
[2022-01-27 04:21:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1170/1251]	eta 0:02:58 lr 0.000011	time 1.5954 (2.2065)	loss 3.5782 (2.9662)	grad_norm 3.2490 (3.3264)	
[2022-01-27 04:22:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1180/1251]	eta 0:02:36 lr 0.000011	time 1.6478 (2.2065)	loss 2.4690 (2.9650)	grad_norm 3.0184 (3.3254)	
[2022-01-27 04:22:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1190/1251]	eta 0:02:14 lr 0.000011	time 1.8636 (2.2046)	loss 2.4254 (2.9661)	grad_norm 2.9258 (3.3263)	
[2022-01-27 04:22:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1200/1251]	eta 0:01:52 lr 0.000011	time 2.1586 (2.2038)	loss 3.2194 (2.9677)	grad_norm 3.4460 (3.3282)	
[2022-01-27 04:23:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1210/1251]	eta 0:01:30 lr 0.000011	time 2.0538 (2.2036)	loss 2.7840 (2.9675)	grad_norm 2.9385 (3.3272)	
[2022-01-27 04:23:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1220/1251]	eta 0:01:08 lr 0.000011	time 2.2783 (2.2038)	loss 3.2443 (2.9677)	grad_norm 2.9480 (3.3262)	
[2022-01-27 04:24:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1230/1251]	eta 0:00:46 lr 0.000011	time 2.1118 (2.2042)	loss 3.4302 (2.9675)	grad_norm 3.1383 (3.3277)	
[2022-01-27 04:24:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1240/1251]	eta 0:00:24 lr 0.000011	time 1.5654 (2.2035)	loss 3.1377 (2.9669)	grad_norm 3.0381 (3.3269)	
[2022-01-27 04:24:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [294/300][1250/1251]	eta 0:00:02 lr 0.000011	time 1.1750 (2.1978)	loss 3.2254 (2.9673)	grad_norm 3.4772 (3.3252)	
[2022-01-27 04:24:38 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 294 training takes 0:45:49
[2022-01-27 04:24:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.204 (18.204)	Loss 0.8677 (0.8677)	Acc@1 80.762 (80.762)	Acc@5 94.922 (94.922)	
[2022-01-27 04:25:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.934 (3.411)	Loss 0.8606 (0.8247)	Acc@1 79.102 (80.868)	Acc@5 95.117 (95.197)	
[2022-01-27 04:25:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.912 (2.505)	Loss 0.8625 (0.8240)	Acc@1 81.250 (80.897)	Acc@5 94.824 (95.187)	
[2022-01-27 04:25:45 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.564 (2.175)	Loss 0.8414 (0.8138)	Acc@1 80.273 (81.074)	Acc@5 95.410 (95.420)	
[2022-01-27 04:26:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.132 (2.147)	Loss 0.8547 (0.8078)	Acc@1 81.055 (81.179)	Acc@5 95.703 (95.494)	
[2022-01-27 04:26:13 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.152 Acc@5 95.518
[2022-01-27 04:26:13 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.2%
[2022-01-27 04:26:13 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.24%
[2022-01-27 04:26:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][0/1251]	eta 7:27:37 lr 0.000011	time 21.4692 (21.4692)	loss 2.0425 (2.0425)	grad_norm 3.6455 (3.6455)	
[2022-01-27 04:26:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][10/1251]	eta 1:23:02 lr 0.000011	time 2.1750 (4.0147)	loss 3.5575 (3.1439)	grad_norm 2.8256 (3.2823)	
[2022-01-27 04:27:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][20/1251]	eta 1:04:16 lr 0.000011	time 2.0121 (3.1332)	loss 2.0388 (3.1226)	grad_norm 3.1543 (3.2064)	
[2022-01-27 04:27:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][30/1251]	eta 0:57:07 lr 0.000011	time 1.8458 (2.8074)	loss 3.4711 (3.1005)	grad_norm 3.3974 (3.2849)	
[2022-01-27 04:28:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][40/1251]	eta 0:54:06 lr 0.000011	time 3.5785 (2.6809)	loss 3.0643 (2.9859)	grad_norm 2.9488 (3.3039)	
[2022-01-27 04:28:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][50/1251]	eta 0:51:29 lr 0.000011	time 2.1192 (2.5721)	loss 2.9802 (2.9893)	grad_norm 3.2478 (3.3028)	
[2022-01-27 04:28:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][60/1251]	eta 0:49:56 lr 0.000011	time 1.3332 (2.5158)	loss 3.2584 (2.9620)	grad_norm 3.4382 (3.3079)	
[2022-01-27 04:29:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][70/1251]	eta 0:48:31 lr 0.000011	time 1.4277 (2.4650)	loss 2.2902 (2.9609)	grad_norm 3.2752 (3.3018)	
[2022-01-27 04:29:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][80/1251]	eta 0:47:30 lr 0.000011	time 2.4474 (2.4343)	loss 2.1688 (2.9603)	grad_norm 3.4197 (3.2856)	
[2022-01-27 04:29:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][90/1251]	eta 0:47:00 lr 0.000011	time 1.8937 (2.4290)	loss 3.0851 (2.9509)	grad_norm 2.9694 (3.2914)	
[2022-01-27 04:30:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][100/1251]	eta 0:46:24 lr 0.000011	time 2.1981 (2.4192)	loss 3.0594 (2.9580)	grad_norm 3.3749 (3.2771)	
[2022-01-27 04:30:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][110/1251]	eta 0:45:55 lr 0.000011	time 2.5435 (2.4147)	loss 3.2900 (2.9619)	grad_norm 3.4801 (3.2622)	
[2022-01-27 04:31:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][120/1251]	eta 0:45:08 lr 0.000011	time 2.7189 (2.3947)	loss 2.8134 (2.9678)	grad_norm 4.7829 (3.2793)	
[2022-01-27 04:31:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][130/1251]	eta 0:44:08 lr 0.000011	time 2.1685 (2.3624)	loss 2.4267 (2.9643)	grad_norm 3.1427 (3.2715)	
[2022-01-27 04:31:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][140/1251]	eta 0:43:06 lr 0.000011	time 1.8695 (2.3285)	loss 3.3937 (2.9719)	grad_norm 2.6012 (3.2600)	
[2022-01-27 04:32:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][150/1251]	eta 0:42:14 lr 0.000011	time 1.6497 (2.3020)	loss 3.4518 (2.9767)	grad_norm 3.4425 (3.2700)	
[2022-01-27 04:32:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][160/1251]	eta 0:41:35 lr 0.000011	time 2.1807 (2.2870)	loss 2.6600 (2.9893)	grad_norm 2.8866 (3.2833)	
[2022-01-27 04:32:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][170/1251]	eta 0:40:55 lr 0.000011	time 2.0655 (2.2715)	loss 3.5473 (2.9854)	grad_norm 3.4023 (3.2933)	
[2022-01-27 04:33:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][180/1251]	eta 0:40:32 lr 0.000011	time 2.8457 (2.2713)	loss 3.2226 (2.9893)	grad_norm 3.5658 (3.2916)	
[2022-01-27 04:33:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][190/1251]	eta 0:39:59 lr 0.000011	time 1.5709 (2.2619)	loss 3.3445 (2.9946)	grad_norm 3.3469 (3.2999)	
[2022-01-27 04:33:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][200/1251]	eta 0:39:38 lr 0.000011	time 2.5021 (2.2634)	loss 3.5137 (2.9921)	grad_norm 3.1041 (3.3018)	
[2022-01-27 04:34:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][210/1251]	eta 0:39:14 lr 0.000011	time 2.2803 (2.2615)	loss 2.3895 (2.9826)	grad_norm 3.2710 (3.3102)	
[2022-01-27 04:34:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][220/1251]	eta 0:38:54 lr 0.000011	time 2.6771 (2.2640)	loss 2.9192 (2.9785)	grad_norm 4.0641 (3.3130)	
[2022-01-27 04:34:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][230/1251]	eta 0:38:29 lr 0.000011	time 1.7687 (2.2617)	loss 3.2364 (2.9669)	grad_norm 2.7815 (3.3020)	
[2022-01-27 04:35:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][240/1251]	eta 0:38:09 lr 0.000011	time 2.8675 (2.2646)	loss 3.2829 (2.9627)	grad_norm 3.7690 (3.3258)	
[2022-01-27 04:35:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][250/1251]	eta 0:37:43 lr 0.000011	time 2.2828 (2.2610)	loss 2.1210 (2.9608)	grad_norm 3.5097 (3.3327)	
[2022-01-27 04:36:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][260/1251]	eta 0:37:24 lr 0.000011	time 2.4545 (2.2646)	loss 3.3505 (2.9686)	grad_norm 2.8971 (3.3300)	
[2022-01-27 04:36:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][270/1251]	eta 0:36:54 lr 0.000011	time 1.8248 (2.2574)	loss 3.6618 (2.9787)	grad_norm 3.4157 (3.3292)	
[2022-01-27 04:36:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][280/1251]	eta 0:36:30 lr 0.000011	time 2.4741 (2.2559)	loss 2.5390 (2.9815)	grad_norm 3.0170 (3.3321)	
[2022-01-27 04:37:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][290/1251]	eta 0:36:06 lr 0.000011	time 2.7360 (2.2541)	loss 3.1320 (2.9808)	grad_norm 2.8918 (3.3355)	
[2022-01-27 04:37:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][300/1251]	eta 0:35:42 lr 0.000011	time 2.2592 (2.2529)	loss 2.8618 (2.9744)	grad_norm 3.0958 (3.3376)	
[2022-01-27 04:37:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][310/1251]	eta 0:35:17 lr 0.000011	time 1.8634 (2.2504)	loss 3.1084 (2.9786)	grad_norm 2.9533 (3.3364)	
[2022-01-27 04:38:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][320/1251]	eta 0:34:48 lr 0.000011	time 1.6692 (2.2430)	loss 2.9448 (2.9803)	grad_norm 3.1326 (3.3329)	
[2022-01-27 04:38:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][330/1251]	eta 0:34:31 lr 0.000011	time 3.6087 (2.2494)	loss 3.2947 (2.9837)	grad_norm 3.0728 (3.3259)	
[2022-01-27 04:39:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][340/1251]	eta 0:34:15 lr 0.000011	time 2.9847 (2.2558)	loss 3.2077 (2.9877)	grad_norm 2.8135 (3.3199)	
[2022-01-27 04:39:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][350/1251]	eta 0:33:44 lr 0.000011	time 1.6438 (2.2466)	loss 1.8841 (2.9873)	grad_norm 3.3751 (3.3167)	
[2022-01-27 04:39:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][360/1251]	eta 0:33:17 lr 0.000011	time 1.9547 (2.2423)	loss 3.4371 (2.9824)	grad_norm 3.9945 (3.3200)	
[2022-01-27 04:40:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][370/1251]	eta 0:32:55 lr 0.000011	time 3.1334 (2.2421)	loss 3.4208 (2.9791)	grad_norm 3.1588 (3.3208)	
[2022-01-27 04:40:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][380/1251]	eta 0:32:29 lr 0.000011	time 1.9250 (2.2380)	loss 2.6720 (2.9767)	grad_norm 3.4753 (3.3245)	
[2022-01-27 04:40:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][390/1251]	eta 0:32:08 lr 0.000011	time 1.7600 (2.2396)	loss 2.1999 (2.9704)	grad_norm 3.6661 (3.3256)	
[2022-01-27 04:41:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][400/1251]	eta 0:31:47 lr 0.000011	time 1.5045 (2.2416)	loss 1.8114 (2.9642)	grad_norm 2.7590 (3.3204)	
[2022-01-27 04:41:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][410/1251]	eta 0:31:24 lr 0.000011	time 3.0854 (2.2413)	loss 3.0889 (2.9684)	grad_norm 3.2414 (3.3163)	
[2022-01-27 04:41:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][420/1251]	eta 0:30:59 lr 0.000011	time 1.9198 (2.2375)	loss 2.1844 (2.9659)	grad_norm 3.7742 (3.3168)	
[2022-01-27 04:42:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][430/1251]	eta 0:30:32 lr 0.000011	time 1.6160 (2.2321)	loss 2.4164 (2.9657)	grad_norm 3.1342 (3.3181)	
[2022-01-27 04:42:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][440/1251]	eta 0:30:08 lr 0.000011	time 2.2557 (2.2294)	loss 2.4671 (2.9626)	grad_norm 4.0267 (3.3216)	
[2022-01-27 04:42:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][450/1251]	eta 0:29:46 lr 0.000011	time 2.2190 (2.2298)	loss 3.3976 (2.9643)	grad_norm 3.9655 (3.3237)	
[2022-01-27 04:43:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][460/1251]	eta 0:29:25 lr 0.000011	time 2.8893 (2.2324)	loss 3.0605 (2.9660)	grad_norm 3.4446 (3.3257)	
[2022-01-27 04:43:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][470/1251]	eta 0:29:01 lr 0.000011	time 1.5935 (2.2302)	loss 2.8963 (2.9677)	grad_norm 3.4492 (3.3226)	
[2022-01-27 04:44:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][480/1251]	eta 0:28:40 lr 0.000011	time 2.4392 (2.2310)	loss 3.1901 (2.9647)	grad_norm 3.4744 (3.3204)	
[2022-01-27 04:44:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][490/1251]	eta 0:28:17 lr 0.000011	time 2.8555 (2.2313)	loss 2.1563 (2.9638)	grad_norm 3.5997 (3.3216)	
[2022-01-27 04:44:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][500/1251]	eta 0:27:52 lr 0.000011	time 1.9366 (2.2276)	loss 2.9447 (2.9588)	grad_norm 2.9416 (3.3219)	
[2022-01-27 04:45:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][510/1251]	eta 0:27:27 lr 0.000011	time 1.8992 (2.2234)	loss 2.1907 (2.9595)	grad_norm 3.2307 (3.3195)	
[2022-01-27 04:45:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][520/1251]	eta 0:27:02 lr 0.000011	time 2.1576 (2.2201)	loss 3.2577 (2.9648)	grad_norm 3.5599 (3.3179)	
[2022-01-27 04:45:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][530/1251]	eta 0:26:40 lr 0.000011	time 2.7370 (2.2204)	loss 3.4053 (2.9685)	grad_norm 3.3853 (3.3166)	
[2022-01-27 04:46:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][540/1251]	eta 0:26:19 lr 0.000011	time 1.4903 (2.2221)	loss 2.9119 (2.9677)	grad_norm 3.2725 (3.3156)	
[2022-01-27 04:46:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][550/1251]	eta 0:25:58 lr 0.000011	time 2.4952 (2.2227)	loss 2.6356 (2.9694)	grad_norm 2.7231 (3.3119)	
[2022-01-27 04:47:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][560/1251]	eta 0:25:36 lr 0.000011	time 3.1225 (2.2242)	loss 2.9074 (2.9707)	grad_norm 3.3517 (3.3137)	
[2022-01-27 04:47:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][570/1251]	eta 0:25:14 lr 0.000011	time 2.7506 (2.2247)	loss 3.4751 (2.9700)	grad_norm 3.9626 (3.3137)	
[2022-01-27 04:47:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][580/1251]	eta 0:24:51 lr 0.000011	time 1.5415 (2.2225)	loss 1.9423 (2.9629)	grad_norm 3.2464 (3.3098)	
[2022-01-27 04:48:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][590/1251]	eta 0:24:27 lr 0.000011	time 2.1347 (2.2206)	loss 2.5986 (2.9641)	grad_norm 3.9302 (3.3129)	
[2022-01-27 04:48:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][600/1251]	eta 0:24:03 lr 0.000011	time 2.1542 (2.2175)	loss 2.4286 (2.9651)	grad_norm 3.0851 (3.3141)	
[2022-01-27 04:48:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][610/1251]	eta 0:23:40 lr 0.000011	time 2.4857 (2.2164)	loss 3.5860 (2.9649)	grad_norm 3.0798 (3.3138)	
[2022-01-27 04:49:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][620/1251]	eta 0:23:17 lr 0.000011	time 1.8808 (2.2145)	loss 2.8661 (2.9657)	grad_norm 3.6385 (3.3143)	
[2022-01-27 04:49:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][630/1251]	eta 0:22:55 lr 0.000011	time 2.8771 (2.2144)	loss 3.2708 (2.9673)	grad_norm 3.5614 (3.3181)	
[2022-01-27 04:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][640/1251]	eta 0:22:33 lr 0.000011	time 2.4132 (2.2159)	loss 3.6212 (2.9656)	grad_norm 3.1019 (3.3150)	
[2022-01-27 04:50:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][650/1251]	eta 0:22:12 lr 0.000011	time 2.1499 (2.2167)	loss 3.2036 (2.9666)	grad_norm 3.0137 (3.3179)	
[2022-01-27 04:50:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][660/1251]	eta 0:21:49 lr 0.000011	time 2.0814 (2.2160)	loss 3.4117 (2.9663)	grad_norm 2.9390 (3.3153)	
[2022-01-27 04:51:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][670/1251]	eta 0:21:28 lr 0.000011	time 3.4457 (2.2169)	loss 2.3204 (2.9624)	grad_norm 3.2579 (3.3207)	
[2022-01-27 04:51:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][680/1251]	eta 0:21:04 lr 0.000011	time 1.6425 (2.2143)	loss 3.3083 (2.9629)	grad_norm 2.9790 (3.3226)	
[2022-01-27 04:51:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][690/1251]	eta 0:20:40 lr 0.000011	time 2.3018 (2.2119)	loss 1.9550 (2.9611)	grad_norm 2.9949 (3.3237)	
[2022-01-27 04:52:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][700/1251]	eta 0:20:18 lr 0.000011	time 2.2678 (2.2117)	loss 3.5551 (2.9638)	grad_norm 3.5666 (3.3233)	
[2022-01-27 04:52:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][710/1251]	eta 0:19:55 lr 0.000011	time 2.4058 (2.2089)	loss 2.1827 (2.9640)	grad_norm 3.4951 (3.3215)	
[2022-01-27 04:52:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][720/1251]	eta 0:19:31 lr 0.000011	time 2.0204 (2.2066)	loss 2.3347 (2.9590)	grad_norm 3.1951 (3.3221)	
[2022-01-27 04:53:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][730/1251]	eta 0:19:09 lr 0.000011	time 2.7660 (2.2063)	loss 2.4042 (2.9604)	grad_norm 3.1858 (3.3249)	
[2022-01-27 04:53:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][740/1251]	eta 0:18:47 lr 0.000011	time 2.5359 (2.2074)	loss 3.5839 (2.9620)	grad_norm 3.2435 (3.3303)	
[2022-01-27 04:53:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][750/1251]	eta 0:18:26 lr 0.000011	time 1.8446 (2.2080)	loss 3.3629 (2.9630)	grad_norm 3.0223 (3.3299)	
[2022-01-27 04:54:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][760/1251]	eta 0:18:03 lr 0.000011	time 1.4683 (2.2070)	loss 2.4747 (2.9631)	grad_norm 3.1205 (3.3304)	
[2022-01-27 04:54:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][770/1251]	eta 0:17:43 lr 0.000011	time 2.4839 (2.2102)	loss 3.1469 (2.9636)	grad_norm 3.2662 (3.3294)	
[2022-01-27 04:55:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][780/1251]	eta 0:17:22 lr 0.000011	time 1.8299 (2.2124)	loss 2.5371 (2.9606)	grad_norm 3.0139 (3.3286)	
[2022-01-27 04:55:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][790/1251]	eta 0:16:59 lr 0.000011	time 2.0103 (2.2123)	loss 3.8076 (2.9613)	grad_norm 3.3843 (3.3296)	
[2022-01-27 04:55:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][800/1251]	eta 0:16:36 lr 0.000011	time 1.6903 (2.2091)	loss 3.3141 (2.9621)	grad_norm 2.9117 (3.3317)	
[2022-01-27 04:56:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][810/1251]	eta 0:16:12 lr 0.000011	time 1.9546 (2.2058)	loss 2.0838 (2.9628)	grad_norm 2.7680 (3.3299)	
[2022-01-27 04:56:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][820/1251]	eta 0:15:50 lr 0.000011	time 1.9499 (2.2042)	loss 1.9761 (2.9612)	grad_norm 3.6647 (3.3311)	
[2022-01-27 04:56:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][830/1251]	eta 0:15:27 lr 0.000011	time 2.0428 (2.2029)	loss 3.4774 (2.9630)	grad_norm 3.3906 (3.3309)	
[2022-01-27 04:57:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][840/1251]	eta 0:15:05 lr 0.000011	time 1.8951 (2.2036)	loss 1.8858 (2.9593)	grad_norm 2.7439 (3.3278)	
[2022-01-27 04:57:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][850/1251]	eta 0:14:44 lr 0.000011	time 1.9304 (2.2047)	loss 2.7987 (2.9590)	grad_norm 2.9662 (3.3310)	
[2022-01-27 04:57:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][860/1251]	eta 0:14:24 lr 0.000011	time 1.9005 (2.2105)	loss 2.7262 (2.9588)	grad_norm 3.4596 (3.3302)	
[2022-01-27 04:58:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][870/1251]	eta 0:14:01 lr 0.000011	time 1.6405 (2.2095)	loss 3.3390 (2.9610)	grad_norm 3.1316 (3.3291)	
[2022-01-27 04:58:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][880/1251]	eta 0:13:39 lr 0.000011	time 2.0346 (2.2079)	loss 3.6235 (2.9614)	grad_norm 3.0036 (3.3287)	
[2022-01-27 04:59:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][890/1251]	eta 0:13:17 lr 0.000010	time 1.8219 (2.2079)	loss 3.2731 (2.9647)	grad_norm 3.7143 (3.3292)	
[2022-01-27 04:59:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][900/1251]	eta 0:12:55 lr 0.000010	time 1.7681 (2.2103)	loss 3.2583 (2.9635)	grad_norm 2.8274 (3.3289)	
[2022-01-27 04:59:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][910/1251]	eta 0:12:33 lr 0.000010	time 1.5684 (2.2093)	loss 3.5074 (2.9632)	grad_norm 3.0978 (3.3294)	
[2022-01-27 05:00:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][920/1251]	eta 0:12:10 lr 0.000010	time 2.2134 (2.2082)	loss 3.4200 (2.9651)	grad_norm 3.5376 (3.3301)	
[2022-01-27 05:00:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][930/1251]	eta 0:11:48 lr 0.000010	time 1.5347 (2.2080)	loss 3.1087 (2.9658)	grad_norm 3.5162 (3.3296)	
[2022-01-27 05:00:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][940/1251]	eta 0:11:27 lr 0.000010	time 2.8083 (2.2111)	loss 3.1384 (2.9667)	grad_norm 3.7084 (3.3296)	
[2022-01-27 05:01:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][950/1251]	eta 0:11:05 lr 0.000010	time 2.2956 (2.2094)	loss 3.1585 (2.9647)	grad_norm 3.2760 (3.3345)	
[2022-01-27 05:01:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][960/1251]	eta 0:10:42 lr 0.000010	time 1.7948 (2.2077)	loss 2.5965 (2.9648)	grad_norm 3.0378 (3.3355)	
[2022-01-27 05:01:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][970/1251]	eta 0:10:20 lr 0.000010	time 1.8221 (2.2068)	loss 3.2935 (2.9670)	grad_norm 2.8275 (3.3381)	
[2022-01-27 05:02:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][980/1251]	eta 0:09:58 lr 0.000010	time 2.6817 (2.2078)	loss 3.4010 (2.9670)	grad_norm 2.7896 (3.3380)	
[2022-01-27 05:02:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][990/1251]	eta 0:09:35 lr 0.000010	time 2.0857 (2.2062)	loss 3.0759 (2.9675)	grad_norm 3.7382 (3.3360)	
[2022-01-27 05:03:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1000/1251]	eta 0:09:13 lr 0.000010	time 2.0725 (2.2062)	loss 3.4829 (2.9686)	grad_norm 3.9741 (3.3352)	
[2022-01-27 05:03:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1010/1251]	eta 0:08:51 lr 0.000010	time 1.8184 (2.2057)	loss 2.2672 (2.9675)	grad_norm 3.9830 (3.3383)	
[2022-01-27 05:03:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1020/1251]	eta 0:08:29 lr 0.000010	time 2.0966 (2.2050)	loss 3.3123 (2.9687)	grad_norm 3.1023 (3.3382)	
[2022-01-27 05:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1030/1251]	eta 0:08:06 lr 0.000010	time 1.9843 (2.2036)	loss 3.7551 (2.9712)	grad_norm 3.2472 (3.3399)	
[2022-01-27 05:04:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1040/1251]	eta 0:07:44 lr 0.000010	time 1.5787 (2.2018)	loss 2.7186 (2.9732)	grad_norm 3.9653 (3.3424)	
[2022-01-27 05:04:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1050/1251]	eta 0:07:22 lr 0.000010	time 2.5722 (2.2023)	loss 3.2935 (2.9721)	grad_norm 4.0664 (3.3430)	
[2022-01-27 05:05:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1060/1251]	eta 0:07:00 lr 0.000010	time 3.0860 (2.2028)	loss 2.5729 (2.9715)	grad_norm 4.1195 (3.3427)	
[2022-01-27 05:05:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1070/1251]	eta 0:06:39 lr 0.000010	time 2.1113 (2.2047)	loss 3.4531 (2.9712)	grad_norm 3.2555 (3.3428)	
[2022-01-27 05:05:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1080/1251]	eta 0:06:17 lr 0.000010	time 1.8898 (2.2047)	loss 2.5603 (2.9699)	grad_norm 3.3025 (3.3444)	
[2022-01-27 05:06:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1090/1251]	eta 0:05:55 lr 0.000010	time 2.4916 (2.2068)	loss 3.0153 (2.9710)	grad_norm 3.2420 (3.3457)	
[2022-01-27 05:06:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1100/1251]	eta 0:05:33 lr 0.000010	time 3.2731 (2.2085)	loss 3.4216 (2.9720)	grad_norm 3.4426 (3.3457)	
[2022-01-27 05:07:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1110/1251]	eta 0:05:11 lr 0.000010	time 1.8870 (2.2083)	loss 2.1791 (2.9709)	grad_norm 3.6504 (3.3461)	
[2022-01-27 05:07:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1120/1251]	eta 0:04:49 lr 0.000010	time 1.8830 (2.2066)	loss 3.3202 (2.9712)	grad_norm 2.9497 (3.3453)	
[2022-01-27 05:07:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1130/1251]	eta 0:04:26 lr 0.000010	time 1.9650 (2.2039)	loss 3.3642 (2.9734)	grad_norm 3.4734 (3.3440)	
[2022-01-27 05:08:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1140/1251]	eta 0:04:04 lr 0.000010	time 2.7267 (2.2023)	loss 3.0069 (2.9720)	grad_norm 3.2741 (3.3468)	
[2022-01-27 05:08:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1150/1251]	eta 0:03:42 lr 0.000010	time 2.2029 (2.2016)	loss 3.5727 (2.9731)	grad_norm 3.7271 (3.3472)	
[2022-01-27 05:08:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1160/1251]	eta 0:03:20 lr 0.000010	time 1.9354 (2.2013)	loss 1.9002 (2.9712)	grad_norm 3.5181 (3.3506)	
[2022-01-27 05:09:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1170/1251]	eta 0:02:58 lr 0.000010	time 2.4009 (2.2022)	loss 3.3539 (2.9685)	grad_norm 3.2782 (3.3497)	
[2022-01-27 05:09:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1180/1251]	eta 0:02:36 lr 0.000010	time 2.8489 (2.2017)	loss 2.7511 (2.9707)	grad_norm 3.9986 (3.3505)	
[2022-01-27 05:09:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1190/1251]	eta 0:02:14 lr 0.000010	time 2.4985 (2.2024)	loss 2.4437 (2.9698)	grad_norm 3.0403 (3.3514)	
[2022-01-27 05:10:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1200/1251]	eta 0:01:52 lr 0.000010	time 2.1893 (2.2023)	loss 2.5223 (2.9701)	grad_norm 3.1628 (3.3528)	
[2022-01-27 05:10:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1210/1251]	eta 0:01:30 lr 0.000010	time 2.8473 (2.2039)	loss 3.1171 (2.9695)	grad_norm 3.0903 (3.3543)	
[2022-01-27 05:11:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1220/1251]	eta 0:01:08 lr 0.000010	time 1.8857 (2.2038)	loss 2.9954 (2.9691)	grad_norm 3.5574 (3.3562)	
[2022-01-27 05:11:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1230/1251]	eta 0:00:46 lr 0.000010	time 2.2295 (2.2038)	loss 3.2101 (2.9686)	grad_norm 2.9920 (3.3557)	
[2022-01-27 05:11:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1240/1251]	eta 0:00:24 lr 0.000010	time 1.4001 (2.2021)	loss 3.3953 (2.9696)	grad_norm 3.0838 (3.3548)	
[2022-01-27 05:12:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [295/300][1250/1251]	eta 0:00:02 lr 0.000010	time 1.2017 (2.1963)	loss 2.2394 (2.9680)	grad_norm 2.8070 (3.3539)	
[2022-01-27 05:12:01 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 295 training takes 0:45:48
[2022-01-27 05:12:19 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.498 (18.498)	Loss 0.7881 (0.7881)	Acc@1 82.129 (82.129)	Acc@5 95.410 (95.410)	
[2022-01-27 05:12:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.977 (3.497)	Loss 0.9269 (0.8238)	Acc@1 78.125 (80.877)	Acc@5 94.043 (95.224)	
[2022-01-27 05:12:56 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.612 (2.632)	Loss 0.8531 (0.8209)	Acc@1 78.906 (80.808)	Acc@5 95.020 (95.280)	
[2022-01-27 05:13:11 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.274 (2.251)	Loss 0.8854 (0.8184)	Acc@1 79.785 (80.963)	Acc@5 94.336 (95.325)	
[2022-01-27 05:13:30 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.547 (2.174)	Loss 0.7183 (0.8071)	Acc@1 83.984 (81.243)	Acc@5 96.094 (95.479)	
[2022-01-27 05:13:37 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.192 Acc@5 95.492
[2022-01-27 05:13:37 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.2%
[2022-01-27 05:13:37 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.24%
[2022-01-27 05:14:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][0/1251]	eta 7:43:13 lr 0.000010	time 22.2172 (22.2172)	loss 3.1717 (3.1717)	grad_norm 3.4666 (3.4666)	
[2022-01-27 05:14:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][10/1251]	eta 1:23:58 lr 0.000010	time 2.5653 (4.0603)	loss 3.9326 (3.0058)	grad_norm 2.9834 (3.3391)	
[2022-01-27 05:14:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][20/1251]	eta 1:04:37 lr 0.000010	time 1.1979 (3.1500)	loss 2.5584 (2.9966)	grad_norm 3.6232 (3.3300)	
[2022-01-27 05:15:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][30/1251]	eta 0:58:53 lr 0.000010	time 1.7208 (2.8939)	loss 2.6048 (2.9816)	grad_norm 3.7650 (3.3451)	
[2022-01-27 05:15:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][40/1251]	eta 0:55:24 lr 0.000010	time 2.8876 (2.7450)	loss 3.2046 (3.0407)	grad_norm 2.7628 (3.3488)	
[2022-01-27 05:15:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][50/1251]	eta 0:53:36 lr 0.000010	time 2.5394 (2.6785)	loss 3.4389 (3.0728)	grad_norm 3.1478 (3.3216)	
[2022-01-27 05:16:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][60/1251]	eta 0:51:22 lr 0.000010	time 1.5042 (2.5879)	loss 3.5213 (3.0629)	grad_norm 2.9336 (3.3106)	
[2022-01-27 05:16:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][70/1251]	eta 0:49:51 lr 0.000010	time 2.1096 (2.5334)	loss 2.0591 (3.0602)	grad_norm 3.5772 (3.3317)	
[2022-01-27 05:16:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][80/1251]	eta 0:48:41 lr 0.000010	time 2.6101 (2.4950)	loss 3.4339 (3.0453)	grad_norm 3.3776 (3.3314)	
[2022-01-27 05:17:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][90/1251]	eta 0:47:42 lr 0.000010	time 2.4682 (2.4658)	loss 2.9117 (3.0032)	grad_norm 3.3266 (3.3438)	
[2022-01-27 05:17:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][100/1251]	eta 0:46:50 lr 0.000010	time 2.2759 (2.4415)	loss 2.2484 (2.9741)	grad_norm 3.0550 (3.3283)	
[2022-01-27 05:18:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][110/1251]	eta 0:45:58 lr 0.000010	time 1.5980 (2.4172)	loss 2.4396 (2.9479)	grad_norm 3.3512 (3.3246)	
[2022-01-27 05:18:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][120/1251]	eta 0:45:08 lr 0.000010	time 1.7166 (2.3944)	loss 3.0195 (2.9486)	grad_norm 3.2257 (3.3059)	
[2022-01-27 05:18:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][130/1251]	eta 0:44:30 lr 0.000010	time 1.9436 (2.3818)	loss 3.4940 (2.9373)	grad_norm 3.6542 (3.3297)	
[2022-01-27 05:19:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][140/1251]	eta 0:43:55 lr 0.000010	time 2.0076 (2.3720)	loss 3.3332 (2.9449)	grad_norm 3.6304 (3.3261)	
[2022-01-27 05:19:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][150/1251]	eta 0:43:07 lr 0.000010	time 1.8991 (2.3504)	loss 3.0207 (2.9505)	grad_norm 2.9660 (3.3210)	
[2022-01-27 05:19:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][160/1251]	eta 0:42:29 lr 0.000010	time 1.8819 (2.3368)	loss 3.6999 (2.9515)	grad_norm 3.1634 (3.3189)	
[2022-01-27 05:20:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][170/1251]	eta 0:41:59 lr 0.000010	time 2.3955 (2.3304)	loss 3.2524 (2.9560)	grad_norm 3.6079 (3.3115)	
[2022-01-27 05:20:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][180/1251]	eta 0:41:28 lr 0.000010	time 1.9396 (2.3232)	loss 3.1807 (2.9552)	grad_norm 3.4069 (3.3111)	
[2022-01-27 05:20:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][190/1251]	eta 0:40:54 lr 0.000010	time 2.2490 (2.3135)	loss 3.3833 (2.9578)	grad_norm 3.0793 (3.3064)	
[2022-01-27 05:21:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][200/1251]	eta 0:40:21 lr 0.000010	time 1.9159 (2.3044)	loss 2.3153 (2.9508)	grad_norm 3.3717 (3.3038)	
[2022-01-27 05:21:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][210/1251]	eta 0:39:56 lr 0.000010	time 3.0245 (2.3025)	loss 3.2774 (2.9577)	grad_norm 3.2590 (3.3187)	
[2022-01-27 05:22:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][220/1251]	eta 0:39:27 lr 0.000010	time 1.8668 (2.2963)	loss 3.1156 (2.9639)	grad_norm 3.2130 (3.3301)	
[2022-01-27 05:22:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][230/1251]	eta 0:38:57 lr 0.000010	time 1.9311 (2.2890)	loss 3.2119 (2.9658)	grad_norm 3.2649 (3.3339)	
[2022-01-27 05:22:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][240/1251]	eta 0:38:22 lr 0.000010	time 1.8717 (2.2778)	loss 3.1924 (2.9710)	grad_norm 2.9424 (3.3329)	
[2022-01-27 05:23:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][250/1251]	eta 0:37:51 lr 0.000010	time 2.8295 (2.2697)	loss 3.8035 (2.9763)	grad_norm 3.2990 (3.3300)	
[2022-01-27 05:23:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][260/1251]	eta 0:37:22 lr 0.000010	time 2.2295 (2.2629)	loss 3.2849 (2.9800)	grad_norm 3.2852 (3.3323)	
[2022-01-27 05:23:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][270/1251]	eta 0:36:55 lr 0.000010	time 1.6785 (2.2589)	loss 3.4109 (2.9843)	grad_norm 3.1519 (3.3353)	
[2022-01-27 05:24:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][280/1251]	eta 0:36:30 lr 0.000010	time 1.7917 (2.2562)	loss 3.4639 (2.9881)	grad_norm 3.2768 (3.3326)	
[2022-01-27 05:24:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][290/1251]	eta 0:36:12 lr 0.000010	time 3.2936 (2.2606)	loss 2.8961 (2.9863)	grad_norm 2.8444 (3.3308)	
[2022-01-27 05:24:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][300/1251]	eta 0:35:53 lr 0.000010	time 2.2035 (2.2645)	loss 3.2153 (2.9827)	grad_norm 3.7046 (3.3346)	
[2022-01-27 05:25:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][310/1251]	eta 0:35:26 lr 0.000010	time 1.9735 (2.2600)	loss 2.2611 (2.9755)	grad_norm 3.2755 (3.3324)	
[2022-01-27 05:25:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][320/1251]	eta 0:35:01 lr 0.000010	time 1.8743 (2.2572)	loss 3.2891 (2.9751)	grad_norm 3.7051 (3.3329)	
[2022-01-27 05:26:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][330/1251]	eta 0:34:37 lr 0.000010	time 1.8126 (2.2552)	loss 3.4373 (2.9731)	grad_norm 3.3368 (3.3347)	
[2022-01-27 05:26:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][340/1251]	eta 0:34:09 lr 0.000010	time 1.5686 (2.2498)	loss 2.8316 (2.9707)	grad_norm 2.9052 (3.3313)	
[2022-01-27 05:26:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][350/1251]	eta 0:33:47 lr 0.000010	time 3.2503 (2.2500)	loss 2.2612 (2.9669)	grad_norm 3.0085 (3.3342)	
[2022-01-27 05:27:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][360/1251]	eta 0:33:22 lr 0.000010	time 1.7644 (2.2470)	loss 3.0855 (2.9687)	grad_norm 3.6048 (3.3364)	
[2022-01-27 05:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][370/1251]	eta 0:32:58 lr 0.000010	time 2.5005 (2.2457)	loss 2.9514 (2.9698)	grad_norm 3.6008 (3.3379)	
[2022-01-27 05:27:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][380/1251]	eta 0:32:34 lr 0.000010	time 1.8701 (2.2440)	loss 2.4991 (2.9698)	grad_norm 3.0734 (3.3353)	
[2022-01-27 05:28:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][390/1251]	eta 0:32:10 lr 0.000010	time 2.4496 (2.2418)	loss 3.2242 (2.9646)	grad_norm 3.0639 (3.3376)	
[2022-01-27 05:28:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][400/1251]	eta 0:31:44 lr 0.000010	time 2.2145 (2.2375)	loss 3.1042 (2.9656)	grad_norm 2.7963 (3.3481)	
[2022-01-27 05:28:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][410/1251]	eta 0:31:20 lr 0.000010	time 2.8498 (2.2362)	loss 2.4076 (2.9663)	grad_norm 2.8882 (3.3482)	
[2022-01-27 05:29:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][420/1251]	eta 0:30:58 lr 0.000010	time 1.6266 (2.2366)	loss 2.9431 (2.9617)	grad_norm 3.1456 (3.3446)	
[2022-01-27 05:29:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][430/1251]	eta 0:30:37 lr 0.000010	time 1.7195 (2.2375)	loss 3.3477 (2.9675)	grad_norm 3.4618 (3.3405)	
[2022-01-27 05:30:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][440/1251]	eta 0:30:14 lr 0.000010	time 2.4992 (2.2372)	loss 3.1184 (2.9683)	grad_norm 3.8491 (3.3391)	
[2022-01-27 05:30:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][450/1251]	eta 0:29:50 lr 0.000010	time 3.1409 (2.2356)	loss 2.7889 (2.9692)	grad_norm 3.2333 (3.3447)	
[2022-01-27 05:30:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][460/1251]	eta 0:29:26 lr 0.000010	time 2.0755 (2.2328)	loss 2.9629 (2.9679)	grad_norm 3.6501 (3.3446)	
[2022-01-27 05:31:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][470/1251]	eta 0:29:01 lr 0.000010	time 1.5123 (2.2293)	loss 3.3098 (2.9676)	grad_norm 3.7168 (3.3439)	
[2022-01-27 05:31:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][480/1251]	eta 0:28:37 lr 0.000010	time 1.9958 (2.2273)	loss 2.6722 (2.9683)	grad_norm 3.2015 (3.3420)	
[2022-01-27 05:31:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][490/1251]	eta 0:28:15 lr 0.000010	time 2.8323 (2.2284)	loss 3.1606 (2.9699)	grad_norm 3.6078 (3.3424)	
[2022-01-27 05:32:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][500/1251]	eta 0:27:53 lr 0.000010	time 2.0876 (2.2282)	loss 2.4856 (2.9693)	grad_norm 3.2131 (3.3478)	
[2022-01-27 05:32:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][510/1251]	eta 0:27:29 lr 0.000010	time 1.5385 (2.2264)	loss 2.3250 (2.9681)	grad_norm 4.2180 (3.3456)	
[2022-01-27 05:32:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][520/1251]	eta 0:27:06 lr 0.000010	time 2.5217 (2.2251)	loss 3.5732 (2.9706)	grad_norm 3.6841 (3.3482)	
[2022-01-27 05:33:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][530/1251]	eta 0:26:43 lr 0.000010	time 2.4487 (2.2238)	loss 2.5860 (2.9706)	grad_norm 3.2264 (3.3499)	
[2022-01-27 05:33:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][540/1251]	eta 0:26:20 lr 0.000010	time 2.2197 (2.2225)	loss 3.0490 (2.9679)	grad_norm 2.9722 (3.3779)	
[2022-01-27 05:34:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][550/1251]	eta 0:25:58 lr 0.000010	time 1.8765 (2.2226)	loss 3.6623 (2.9618)	grad_norm 3.0538 (3.3764)	
[2022-01-27 05:34:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][560/1251]	eta 0:25:37 lr 0.000010	time 2.7972 (2.2251)	loss 2.1851 (2.9629)	grad_norm 3.2633 (3.3812)	
[2022-01-27 05:34:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][570/1251]	eta 0:25:13 lr 0.000010	time 1.6207 (2.2226)	loss 3.0198 (2.9621)	grad_norm 3.6475 (3.3806)	
[2022-01-27 05:35:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][580/1251]	eta 0:24:49 lr 0.000010	time 2.2643 (2.2196)	loss 3.2258 (2.9613)	grad_norm 2.9912 (3.3779)	
[2022-01-27 05:35:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][590/1251]	eta 0:24:24 lr 0.000010	time 1.8191 (2.2154)	loss 2.6989 (2.9611)	grad_norm 3.2591 (3.3825)	
[2022-01-27 05:35:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][600/1251]	eta 0:24:00 lr 0.000010	time 1.6121 (2.2131)	loss 2.5537 (2.9629)	grad_norm 2.9909 (3.3795)	
[2022-01-27 05:36:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][610/1251]	eta 0:23:39 lr 0.000010	time 2.8855 (2.2152)	loss 2.9828 (2.9665)	grad_norm 3.5960 (3.3797)	
[2022-01-27 05:36:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][620/1251]	eta 0:23:19 lr 0.000010	time 2.8861 (2.2181)	loss 3.2955 (2.9691)	grad_norm 2.8712 (3.3770)	
[2022-01-27 05:36:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][630/1251]	eta 0:22:56 lr 0.000010	time 2.1630 (2.2165)	loss 2.9369 (2.9710)	grad_norm 3.1445 (3.3743)	
[2022-01-27 05:37:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][640/1251]	eta 0:22:33 lr 0.000010	time 1.8957 (2.2152)	loss 3.1883 (2.9744)	grad_norm 3.1408 (3.3705)	
[2022-01-27 05:37:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][650/1251]	eta 0:22:11 lr 0.000010	time 2.2484 (2.2154)	loss 3.1484 (2.9780)	grad_norm 2.6889 (3.3679)	
[2022-01-27 05:38:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][660/1251]	eta 0:21:49 lr 0.000010	time 2.8986 (2.2162)	loss 2.8140 (2.9747)	grad_norm 3.2806 (3.3692)	
[2022-01-27 05:38:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][670/1251]	eta 0:21:26 lr 0.000010	time 1.5917 (2.2146)	loss 3.2418 (2.9732)	grad_norm 3.2813 (3.3650)	
[2022-01-27 05:38:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][680/1251]	eta 0:21:04 lr 0.000010	time 2.2365 (2.2142)	loss 2.2700 (2.9744)	grad_norm 3.3679 (3.3641)	
[2022-01-27 05:39:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][690/1251]	eta 0:20:41 lr 0.000010	time 2.2941 (2.2137)	loss 3.2359 (2.9710)	grad_norm 2.6887 (3.3621)	
[2022-01-27 05:39:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][700/1251]	eta 0:20:19 lr 0.000010	time 3.4994 (2.2140)	loss 2.4869 (2.9642)	grad_norm 3.8492 (3.3789)	
[2022-01-27 05:39:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][710/1251]	eta 0:19:57 lr 0.000010	time 1.9893 (2.2139)	loss 2.6931 (2.9632)	grad_norm 3.3322 (3.3756)	
[2022-01-27 05:40:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][720/1251]	eta 0:19:35 lr 0.000010	time 1.9409 (2.2136)	loss 3.1733 (2.9604)	grad_norm 3.3540 (3.3747)	
[2022-01-27 05:40:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][730/1251]	eta 0:19:13 lr 0.000010	time 2.5700 (2.2136)	loss 2.9236 (2.9593)	grad_norm 3.3953 (3.3756)	
[2022-01-27 05:40:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][740/1251]	eta 0:18:50 lr 0.000010	time 2.3062 (2.2121)	loss 3.3866 (2.9608)	grad_norm 3.3337 (3.3756)	
[2022-01-27 05:41:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][750/1251]	eta 0:18:27 lr 0.000010	time 2.1786 (2.2108)	loss 2.4297 (2.9614)	grad_norm 3.4795 (3.3772)	
[2022-01-27 05:41:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][760/1251]	eta 0:18:05 lr 0.000010	time 3.0097 (2.2107)	loss 2.4631 (2.9615)	grad_norm 3.5539 (3.3741)	
[2022-01-27 05:42:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][770/1251]	eta 0:17:44 lr 0.000010	time 2.4276 (2.2128)	loss 3.6047 (2.9637)	grad_norm 3.5020 (3.3749)	
[2022-01-27 05:42:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][780/1251]	eta 0:17:21 lr 0.000010	time 2.1750 (2.2121)	loss 3.0683 (2.9642)	grad_norm 2.9770 (3.3770)	
[2022-01-27 05:42:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][790/1251]	eta 0:16:58 lr 0.000010	time 1.5606 (2.2095)	loss 2.8699 (2.9623)	grad_norm 3.2443 (3.3769)	
[2022-01-27 05:43:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][800/1251]	eta 0:16:35 lr 0.000010	time 2.0413 (2.2084)	loss 3.2048 (2.9628)	grad_norm 2.8857 (3.3768)	
[2022-01-27 05:43:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][810/1251]	eta 0:16:13 lr 0.000010	time 1.9926 (2.2082)	loss 3.3054 (2.9666)	grad_norm 3.0952 (3.3768)	
[2022-01-27 05:43:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][820/1251]	eta 0:15:51 lr 0.000010	time 2.2559 (2.2077)	loss 3.2134 (2.9654)	grad_norm 3.2421 (3.3771)	
[2022-01-27 05:44:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][830/1251]	eta 0:15:29 lr 0.000010	time 1.9882 (2.2067)	loss 1.9978 (2.9636)	grad_norm 3.0430 (3.3756)	
[2022-01-27 05:44:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][840/1251]	eta 0:15:06 lr 0.000010	time 1.8737 (2.2049)	loss 3.0220 (2.9591)	grad_norm 3.2762 (3.3758)	
[2022-01-27 05:44:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][850/1251]	eta 0:14:44 lr 0.000010	time 2.2076 (2.2052)	loss 3.1732 (2.9567)	grad_norm 3.1819 (3.3754)	
[2022-01-27 05:45:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][860/1251]	eta 0:14:22 lr 0.000010	time 1.5620 (2.2048)	loss 3.3461 (2.9530)	grad_norm 2.8366 (3.3730)	
[2022-01-27 05:45:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][870/1251]	eta 0:13:59 lr 0.000010	time 2.0451 (2.2044)	loss 3.0665 (2.9537)	grad_norm 5.0964 (3.3765)	
[2022-01-27 05:46:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][880/1251]	eta 0:13:38 lr 0.000010	time 2.6995 (2.2052)	loss 3.3467 (2.9546)	grad_norm 3.4047 (3.3765)	
[2022-01-27 05:46:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][890/1251]	eta 0:13:15 lr 0.000010	time 1.9554 (2.2034)	loss 3.3406 (2.9542)	grad_norm 3.6537 (3.3774)	
[2022-01-27 05:46:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][900/1251]	eta 0:12:52 lr 0.000010	time 1.9951 (2.2019)	loss 3.1437 (2.9540)	grad_norm 3.0477 (3.3772)	
[2022-01-27 05:47:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][910/1251]	eta 0:12:30 lr 0.000010	time 2.5602 (2.2008)	loss 2.9128 (2.9568)	grad_norm 3.5895 (3.3775)	
[2022-01-27 05:47:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][920/1251]	eta 0:12:08 lr 0.000010	time 2.2410 (2.2011)	loss 2.5133 (2.9565)	grad_norm 2.4946 (3.3767)	
[2022-01-27 05:47:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][930/1251]	eta 0:11:46 lr 0.000010	time 2.2585 (2.2010)	loss 2.4934 (2.9565)	grad_norm 2.8506 (3.3734)	
[2022-01-27 05:48:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][940/1251]	eta 0:11:24 lr 0.000010	time 2.1595 (2.2020)	loss 1.8170 (2.9572)	grad_norm 3.2157 (3.3731)	
[2022-01-27 05:48:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][950/1251]	eta 0:11:02 lr 0.000010	time 2.2937 (2.2019)	loss 3.2044 (2.9578)	grad_norm 2.8206 (3.3742)	
[2022-01-27 05:48:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][960/1251]	eta 0:10:40 lr 0.000010	time 1.8757 (2.2020)	loss 2.8364 (2.9568)	grad_norm 3.3384 (3.3756)	
[2022-01-27 05:49:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][970/1251]	eta 0:10:18 lr 0.000010	time 2.1973 (2.2008)	loss 3.4998 (2.9588)	grad_norm 3.7084 (3.3740)	
[2022-01-27 05:49:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][980/1251]	eta 0:09:56 lr 0.000010	time 2.2625 (2.2007)	loss 1.9703 (2.9567)	grad_norm 3.2798 (3.3722)	
[2022-01-27 05:49:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][990/1251]	eta 0:09:34 lr 0.000010	time 1.3911 (2.1996)	loss 2.5762 (2.9564)	grad_norm 4.1518 (3.3726)	
[2022-01-27 05:50:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1000/1251]	eta 0:09:11 lr 0.000010	time 2.2885 (2.1990)	loss 3.2446 (2.9589)	grad_norm 2.6848 (3.3733)	
[2022-01-27 05:50:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1010/1251]	eta 0:08:49 lr 0.000010	time 2.0769 (2.1986)	loss 3.0103 (2.9582)	grad_norm 2.8070 (3.3726)	
[2022-01-27 05:51:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1020/1251]	eta 0:08:28 lr 0.000010	time 2.7682 (2.2003)	loss 2.8180 (2.9599)	grad_norm 4.1998 (3.3731)	
[2022-01-27 05:51:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1030/1251]	eta 0:08:06 lr 0.000010	time 1.7612 (2.1999)	loss 3.4118 (2.9598)	grad_norm 3.5934 (3.3724)	
[2022-01-27 05:51:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1040/1251]	eta 0:07:44 lr 0.000010	time 1.9244 (2.2001)	loss 1.8481 (2.9600)	grad_norm 3.5503 (3.3700)	
[2022-01-27 05:52:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1050/1251]	eta 0:07:22 lr 0.000010	time 1.9034 (2.1993)	loss 3.3185 (2.9598)	grad_norm 3.1110 (3.3691)	
[2022-01-27 05:52:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1060/1251]	eta 0:06:59 lr 0.000010	time 2.1778 (2.1986)	loss 2.0498 (2.9600)	grad_norm 3.5570 (3.3700)	
[2022-01-27 05:52:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1070/1251]	eta 0:06:37 lr 0.000010	time 2.2124 (2.1983)	loss 2.9576 (2.9602)	grad_norm 3.3659 (3.3694)	
[2022-01-27 05:53:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1080/1251]	eta 0:06:15 lr 0.000010	time 1.9087 (2.1974)	loss 2.9784 (2.9614)	grad_norm 4.4913 (3.3701)	
[2022-01-27 05:53:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1090/1251]	eta 0:05:53 lr 0.000010	time 2.2533 (2.1982)	loss 3.1637 (2.9619)	grad_norm 3.0447 (3.3669)	
[2022-01-27 05:53:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1100/1251]	eta 0:05:31 lr 0.000010	time 1.7904 (2.1973)	loss 1.8122 (2.9612)	grad_norm 3.0345 (3.3637)	
[2022-01-27 05:54:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1110/1251]	eta 0:05:09 lr 0.000010	time 1.9009 (2.1970)	loss 2.4089 (2.9575)	grad_norm 3.3845 (3.3645)	
[2022-01-27 05:54:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1120/1251]	eta 0:04:47 lr 0.000010	time 2.1462 (2.1973)	loss 3.3837 (2.9564)	grad_norm 3.0899 (3.3635)	
[2022-01-27 05:55:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1130/1251]	eta 0:04:25 lr 0.000010	time 2.1742 (2.1977)	loss 3.3878 (2.9572)	grad_norm 3.4034 (3.3632)	
[2022-01-27 05:55:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1140/1251]	eta 0:04:04 lr 0.000010	time 2.6947 (2.1988)	loss 3.4131 (2.9574)	grad_norm 3.6287 (3.3624)	
[2022-01-27 05:55:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1150/1251]	eta 0:03:41 lr 0.000010	time 1.9603 (2.1961)	loss 3.1240 (2.9553)	grad_norm 4.0362 (3.3621)	
[2022-01-27 05:56:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1160/1251]	eta 0:03:19 lr 0.000010	time 2.5382 (2.1959)	loss 3.1021 (2.9546)	grad_norm 3.0499 (3.3622)	
[2022-01-27 05:56:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1170/1251]	eta 0:02:57 lr 0.000010	time 1.6005 (2.1956)	loss 2.5877 (2.9556)	grad_norm 3.1239 (3.3616)	
[2022-01-27 05:56:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1180/1251]	eta 0:02:35 lr 0.000010	time 1.5148 (2.1953)	loss 3.3039 (2.9570)	grad_norm 3.4948 (3.3618)	
[2022-01-27 05:57:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1190/1251]	eta 0:02:13 lr 0.000010	time 2.4871 (2.1957)	loss 3.2512 (2.9576)	grad_norm 3.1541 (3.3621)	
[2022-01-27 05:57:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1200/1251]	eta 0:01:51 lr 0.000010	time 2.3840 (2.1956)	loss 2.3237 (2.9565)	grad_norm 3.6866 (3.3622)	
[2022-01-27 05:57:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1210/1251]	eta 0:01:30 lr 0.000010	time 1.8149 (2.1957)	loss 2.9623 (2.9556)	grad_norm 3.4123 (3.3616)	
[2022-01-27 05:58:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1220/1251]	eta 0:01:08 lr 0.000010	time 1.9892 (2.1954)	loss 2.5254 (2.9556)	grad_norm 2.9278 (3.3611)	
[2022-01-27 05:58:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1230/1251]	eta 0:00:46 lr 0.000010	time 2.4024 (2.1967)	loss 3.2416 (2.9564)	grad_norm 3.8933 (3.3617)	
[2022-01-27 05:59:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1240/1251]	eta 0:00:24 lr 0.000010	time 2.3678 (2.1969)	loss 3.3728 (2.9584)	grad_norm 3.4352 (3.3599)	
[2022-01-27 05:59:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [296/300][1250/1251]	eta 0:00:02 lr 0.000010	time 1.1478 (2.1914)	loss 3.3430 (2.9590)	grad_norm 3.5942 (3.3606)	
[2022-01-27 05:59:19 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 296 training takes 0:45:41
[2022-01-27 05:59:38 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.683 (18.683)	Loss 0.8069 (0.8069)	Acc@1 80.371 (80.371)	Acc@5 96.191 (96.191)	
[2022-01-27 05:59:57 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.844 (3.458)	Loss 0.8155 (0.8052)	Acc@1 80.762 (81.072)	Acc@5 95.605 (95.605)	
[2022-01-27 06:00:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.598 (2.666)	Loss 0.7516 (0.8003)	Acc@1 82.031 (81.343)	Acc@5 96.484 (95.554)	
[2022-01-27 06:00:31 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.646 (2.301)	Loss 0.8118 (0.8029)	Acc@1 80.469 (81.439)	Acc@5 95.508 (95.558)	
[2022-01-27 06:00:48 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.169 (2.165)	Loss 0.8649 (0.8080)	Acc@1 79.980 (81.288)	Acc@5 94.629 (95.484)	
[2022-01-27 06:00:55 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.230 Acc@5 95.524
[2022-01-27 06:00:55 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.2%
[2022-01-27 06:00:55 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.24%
[2022-01-27 06:01:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][0/1251]	eta 7:19:20 lr 0.000010	time 21.0714 (21.0714)	loss 3.1432 (3.1432)	grad_norm 3.4505 (3.4505)	
[2022-01-27 06:01:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][10/1251]	eta 1:22:23 lr 0.000010	time 2.5958 (3.9833)	loss 2.1009 (2.9997)	grad_norm 3.0797 (3.2087)	
[2022-01-27 06:02:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][20/1251]	eta 1:04:34 lr 0.000010	time 2.0971 (3.1477)	loss 3.5762 (3.0404)	grad_norm 3.2183 (3.2009)	
[2022-01-27 06:02:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][30/1251]	eta 0:58:32 lr 0.000010	time 1.9526 (2.8768)	loss 3.5309 (3.1068)	grad_norm 3.4438 (3.2127)	
[2022-01-27 06:02:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][40/1251]	eta 0:55:37 lr 0.000010	time 3.7883 (2.7559)	loss 3.1536 (3.0787)	grad_norm 3.7205 (3.2669)	
[2022-01-27 06:03:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][50/1251]	eta 0:53:31 lr 0.000010	time 2.9890 (2.6737)	loss 3.5463 (3.0821)	grad_norm 3.4924 (3.2845)	
[2022-01-27 06:03:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][60/1251]	eta 0:51:23 lr 0.000010	time 2.2413 (2.5893)	loss 3.3551 (3.0803)	grad_norm 3.6774 (3.2990)	
[2022-01-27 06:03:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][70/1251]	eta 0:49:24 lr 0.000010	time 1.9525 (2.5102)	loss 3.2819 (3.0841)	grad_norm 3.6230 (3.3638)	
[2022-01-27 06:04:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][80/1251]	eta 0:47:56 lr 0.000010	time 2.8795 (2.4562)	loss 3.6577 (3.0782)	grad_norm 3.4897 (3.3692)	
[2022-01-27 06:04:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][90/1251]	eta 0:46:44 lr 0.000010	time 1.8980 (2.4159)	loss 3.6680 (3.0665)	grad_norm 3.6258 (3.4501)	
[2022-01-27 06:04:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][100/1251]	eta 0:45:44 lr 0.000010	time 1.9382 (2.3844)	loss 2.8878 (3.0612)	grad_norm 3.3160 (3.4376)	
[2022-01-27 06:05:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][110/1251]	eta 0:45:02 lr 0.000010	time 2.1623 (2.3689)	loss 3.0504 (3.0466)	grad_norm 4.1071 (3.4234)	
[2022-01-27 06:05:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][120/1251]	eta 0:44:32 lr 0.000010	time 3.6202 (2.3632)	loss 3.7610 (3.0502)	grad_norm 3.1847 (3.4047)	
[2022-01-27 06:06:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][130/1251]	eta 0:43:55 lr 0.000010	time 2.4792 (2.3513)	loss 3.4662 (3.0429)	grad_norm 4.9555 (3.4162)	
[2022-01-27 06:06:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][140/1251]	eta 0:43:19 lr 0.000010	time 2.2352 (2.3396)	loss 1.9927 (3.0374)	grad_norm 3.1957 (3.4159)	
[2022-01-27 06:06:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][150/1251]	eta 0:42:50 lr 0.000010	time 2.9547 (2.3347)	loss 3.3592 (3.0319)	grad_norm 3.2825 (3.3983)	
[2022-01-27 06:07:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][160/1251]	eta 0:42:26 lr 0.000010	time 3.4797 (2.3339)	loss 3.2905 (3.0279)	grad_norm 2.6587 (3.3898)	
[2022-01-27 06:07:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][170/1251]	eta 0:41:45 lr 0.000010	time 2.2307 (2.3179)	loss 2.3533 (3.0156)	grad_norm 2.9125 (3.3808)	
[2022-01-27 06:07:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][180/1251]	eta 0:41:04 lr 0.000010	time 1.6866 (2.3011)	loss 2.8215 (3.0104)	grad_norm 3.2826 (3.3848)	
[2022-01-27 06:08:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][190/1251]	eta 0:40:40 lr 0.000010	time 2.1330 (2.3002)	loss 2.8527 (2.9991)	grad_norm 3.6755 (3.3895)	
[2022-01-27 06:08:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][200/1251]	eta 0:40:23 lr 0.000010	time 3.7403 (2.3062)	loss 3.0687 (3.0039)	grad_norm 3.7519 (3.3954)	
[2022-01-27 06:09:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][210/1251]	eta 0:39:54 lr 0.000010	time 1.4843 (2.3001)	loss 3.1814 (3.0048)	grad_norm 3.0706 (3.3950)	
[2022-01-27 06:09:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][220/1251]	eta 0:39:22 lr 0.000010	time 1.5609 (2.2918)	loss 3.2219 (2.9997)	grad_norm 2.8928 (3.3853)	
[2022-01-27 06:09:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][230/1251]	eta 0:38:49 lr 0.000010	time 1.7137 (2.2819)	loss 3.1631 (2.9952)	grad_norm 2.8928 (3.3802)	
[2022-01-27 06:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][240/1251]	eta 0:38:31 lr 0.000010	time 3.3844 (2.2865)	loss 2.8833 (2.9923)	grad_norm 3.0707 (3.3928)	
[2022-01-27 06:10:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][250/1251]	eta 0:38:03 lr 0.000010	time 2.2222 (2.2808)	loss 3.5902 (2.9756)	grad_norm 3.0808 (3.3905)	
[2022-01-27 06:10:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][260/1251]	eta 0:37:28 lr 0.000010	time 1.7172 (2.2689)	loss 3.3334 (2.9730)	grad_norm 2.9980 (3.4091)	
[2022-01-27 06:11:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][270/1251]	eta 0:36:57 lr 0.000010	time 1.9402 (2.2607)	loss 3.6487 (2.9748)	grad_norm 3.2610 (3.4081)	
[2022-01-27 06:11:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][280/1251]	eta 0:36:32 lr 0.000010	time 2.2808 (2.2577)	loss 3.2722 (2.9819)	grad_norm 3.7162 (3.3977)	
[2022-01-27 06:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][290/1251]	eta 0:36:06 lr 0.000010	time 2.0165 (2.2541)	loss 1.8958 (2.9778)	grad_norm 3.3791 (3.3966)	
[2022-01-27 06:12:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][300/1251]	eta 0:35:38 lr 0.000010	time 2.1766 (2.2488)	loss 3.1278 (2.9824)	grad_norm 3.6457 (3.3932)	
[2022-01-27 06:12:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][310/1251]	eta 0:35:18 lr 0.000010	time 2.3712 (2.2514)	loss 3.0271 (2.9840)	grad_norm 3.1261 (3.3922)	
[2022-01-27 06:12:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][320/1251]	eta 0:34:56 lr 0.000010	time 2.4789 (2.2518)	loss 3.6356 (2.9808)	grad_norm 3.4638 (3.3890)	
[2022-01-27 06:13:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][330/1251]	eta 0:34:35 lr 0.000010	time 2.8357 (2.2539)	loss 2.7790 (2.9792)	grad_norm 2.8650 (3.3855)	
[2022-01-27 06:13:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][340/1251]	eta 0:34:05 lr 0.000010	time 2.1924 (2.2459)	loss 3.4685 (2.9824)	grad_norm 3.3613 (3.3846)	
[2022-01-27 06:14:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][350/1251]	eta 0:33:38 lr 0.000010	time 1.8491 (2.2405)	loss 2.4734 (2.9846)	grad_norm 3.4485 (3.3855)	
[2022-01-27 06:14:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][360/1251]	eta 0:33:15 lr 0.000010	time 2.8306 (2.2397)	loss 3.3792 (2.9842)	grad_norm 2.9988 (3.3784)	
[2022-01-27 06:14:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][370/1251]	eta 0:32:53 lr 0.000010	time 2.4498 (2.2397)	loss 3.0283 (2.9786)	grad_norm 3.3389 (3.3783)	
[2022-01-27 06:15:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][380/1251]	eta 0:32:33 lr 0.000010	time 2.5677 (2.2424)	loss 3.0951 (2.9798)	grad_norm 3.1996 (3.3789)	
[2022-01-27 06:15:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][390/1251]	eta 0:32:11 lr 0.000010	time 1.7507 (2.2432)	loss 2.8271 (2.9764)	grad_norm 3.1755 (3.3814)	
[2022-01-27 06:15:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][400/1251]	eta 0:31:50 lr 0.000010	time 2.2198 (2.2454)	loss 2.5838 (2.9766)	grad_norm 2.9067 (3.3832)	
[2022-01-27 06:16:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][410/1251]	eta 0:31:22 lr 0.000010	time 1.9515 (2.2384)	loss 3.4870 (2.9756)	grad_norm 3.6294 (3.3857)	
[2022-01-27 06:16:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][420/1251]	eta 0:30:54 lr 0.000010	time 1.8755 (2.2316)	loss 2.6268 (2.9764)	grad_norm 3.2763 (3.3853)	
[2022-01-27 06:16:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][430/1251]	eta 0:30:29 lr 0.000010	time 2.5388 (2.2283)	loss 3.2088 (2.9767)	grad_norm 3.9978 (3.3853)	
[2022-01-27 06:17:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][440/1251]	eta 0:30:06 lr 0.000010	time 2.2200 (2.2269)	loss 3.3273 (2.9809)	grad_norm 3.2521 (3.3989)	
[2022-01-27 06:17:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][450/1251]	eta 0:29:43 lr 0.000010	time 2.3799 (2.2260)	loss 3.5315 (2.9868)	grad_norm 3.0784 (3.3950)	
[2022-01-27 06:18:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][460/1251]	eta 0:29:22 lr 0.000010	time 2.7529 (2.2281)	loss 3.1720 (2.9901)	grad_norm 3.0154 (3.4069)	
[2022-01-27 06:18:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][470/1251]	eta 0:29:01 lr 0.000010	time 2.5821 (2.2295)	loss 3.2625 (2.9968)	grad_norm 2.8915 (3.4017)	
[2022-01-27 06:18:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][480/1251]	eta 0:28:37 lr 0.000010	time 2.1934 (2.2277)	loss 3.4880 (2.9909)	grad_norm 3.9124 (3.4053)	
[2022-01-27 06:19:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][490/1251]	eta 0:28:16 lr 0.000010	time 2.8689 (2.2291)	loss 3.3241 (2.9867)	grad_norm 3.1251 (3.3996)	
[2022-01-27 06:19:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][500/1251]	eta 0:27:56 lr 0.000010	time 2.7161 (2.2319)	loss 2.9648 (2.9820)	grad_norm 2.4445 (3.3997)	
[2022-01-27 06:19:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][510/1251]	eta 0:27:38 lr 0.000010	time 2.7397 (2.2381)	loss 3.5116 (2.9829)	grad_norm 2.8368 (3.3963)	
[2022-01-27 06:20:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][520/1251]	eta 0:27:17 lr 0.000010	time 2.3081 (2.2399)	loss 3.0893 (2.9862)	grad_norm 3.4456 (3.3966)	
[2022-01-27 06:20:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][530/1251]	eta 0:26:51 lr 0.000010	time 1.9537 (2.2350)	loss 3.2776 (2.9896)	grad_norm 3.4181 (3.3968)	
[2022-01-27 06:21:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][540/1251]	eta 0:26:23 lr 0.000010	time 1.8589 (2.2277)	loss 3.3310 (2.9854)	grad_norm 3.2902 (3.3992)	
[2022-01-27 06:21:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][550/1251]	eta 0:25:58 lr 0.000010	time 2.1618 (2.2238)	loss 3.3800 (2.9916)	grad_norm 2.9634 (3.3992)	
[2022-01-27 06:21:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][560/1251]	eta 0:25:35 lr 0.000010	time 2.4811 (2.2221)	loss 3.3829 (2.9937)	grad_norm 3.1560 (3.3969)	
[2022-01-27 06:22:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][570/1251]	eta 0:25:12 lr 0.000010	time 2.6166 (2.2213)	loss 3.6952 (2.9933)	grad_norm 4.0148 (3.4003)	
[2022-01-27 06:22:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][580/1251]	eta 0:24:51 lr 0.000010	time 2.2573 (2.2231)	loss 3.1048 (2.9926)	grad_norm 2.4835 (3.3962)	
[2022-01-27 06:22:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][590/1251]	eta 0:24:30 lr 0.000010	time 2.4087 (2.2246)	loss 2.3343 (2.9912)	grad_norm 2.9358 (3.3979)	
[2022-01-27 06:23:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][600/1251]	eta 0:24:07 lr 0.000010	time 1.8325 (2.2235)	loss 3.3336 (2.9935)	grad_norm 3.3052 (3.3951)	
[2022-01-27 06:23:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][610/1251]	eta 0:23:45 lr 0.000010	time 1.9505 (2.2238)	loss 3.0760 (2.9919)	grad_norm 3.4801 (3.3985)	
[2022-01-27 06:23:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][620/1251]	eta 0:23:24 lr 0.000010	time 2.0519 (2.2252)	loss 2.5682 (2.9919)	grad_norm 6.0883 (3.3982)	
[2022-01-27 06:24:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][630/1251]	eta 0:23:01 lr 0.000010	time 1.7363 (2.2241)	loss 2.7191 (2.9912)	grad_norm 4.1346 (3.3944)	
[2022-01-27 06:24:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][640/1251]	eta 0:22:38 lr 0.000010	time 1.9435 (2.2227)	loss 3.0836 (2.9876)	grad_norm 2.9509 (3.3904)	
[2022-01-27 06:25:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][650/1251]	eta 0:22:14 lr 0.000010	time 2.2360 (2.2203)	loss 2.2297 (2.9820)	grad_norm 2.6044 (3.3876)	
[2022-01-27 06:25:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][660/1251]	eta 0:21:50 lr 0.000010	time 1.8838 (2.2173)	loss 3.3511 (2.9829)	grad_norm 2.9451 (3.3877)	
[2022-01-27 06:25:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][670/1251]	eta 0:21:28 lr 0.000010	time 2.1285 (2.2169)	loss 2.4969 (2.9835)	grad_norm 3.2002 (3.3854)	
[2022-01-27 06:26:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][680/1251]	eta 0:21:05 lr 0.000010	time 1.6262 (2.2167)	loss 2.1330 (2.9817)	grad_norm 3.8362 (3.3843)	
[2022-01-27 06:26:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][690/1251]	eta 0:20:43 lr 0.000010	time 2.3461 (2.2169)	loss 3.1336 (2.9810)	grad_norm 3.3492 (3.3853)	
[2022-01-27 06:26:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][700/1251]	eta 0:20:21 lr 0.000010	time 1.5551 (2.2177)	loss 2.2560 (2.9812)	grad_norm 3.6541 (3.3853)	
[2022-01-27 06:27:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][710/1251]	eta 0:20:01 lr 0.000010	time 2.7268 (2.2200)	loss 2.7520 (2.9820)	grad_norm 3.2478 (3.3836)	
[2022-01-27 06:27:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][720/1251]	eta 0:19:37 lr 0.000010	time 2.2378 (2.2182)	loss 3.1170 (2.9811)	grad_norm 4.0299 (3.3820)	
[2022-01-27 06:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][730/1251]	eta 0:19:13 lr 0.000010	time 1.9257 (2.2142)	loss 2.8710 (2.9795)	grad_norm 3.0828 (3.3824)	
[2022-01-27 06:28:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][740/1251]	eta 0:18:50 lr 0.000010	time 2.2991 (2.2121)	loss 3.1669 (2.9827)	grad_norm 3.5954 (3.3813)	
[2022-01-27 06:28:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][750/1251]	eta 0:18:27 lr 0.000010	time 1.8563 (2.2114)	loss 2.7112 (2.9828)	grad_norm 2.8012 (3.3798)	
[2022-01-27 06:28:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][760/1251]	eta 0:18:05 lr 0.000010	time 2.4396 (2.2105)	loss 2.9357 (2.9855)	grad_norm 3.3402 (3.3783)	
[2022-01-27 06:29:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][770/1251]	eta 0:17:42 lr 0.000010	time 2.5669 (2.2086)	loss 2.3694 (2.9828)	grad_norm 3.4438 (3.3806)	
[2022-01-27 06:29:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][780/1251]	eta 0:17:20 lr 0.000010	time 2.0372 (2.2091)	loss 3.1144 (2.9847)	grad_norm 2.9565 (3.3810)	
[2022-01-27 06:30:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][790/1251]	eta 0:16:59 lr 0.000010	time 1.9042 (2.2115)	loss 2.6285 (2.9838)	grad_norm 3.7011 (3.3817)	
[2022-01-27 06:30:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][800/1251]	eta 0:16:37 lr 0.000010	time 2.5545 (2.2122)	loss 2.4050 (2.9830)	grad_norm 3.0190 (3.3789)	
[2022-01-27 06:30:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][810/1251]	eta 0:16:15 lr 0.000010	time 2.4384 (2.2131)	loss 3.3288 (2.9788)	grad_norm 2.9814 (3.3768)	
[2022-01-27 06:31:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][820/1251]	eta 0:15:53 lr 0.000010	time 2.4960 (2.2127)	loss 3.2891 (2.9811)	grad_norm 3.1495 (3.3749)	
[2022-01-27 06:31:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][830/1251]	eta 0:15:32 lr 0.000010	time 2.3718 (2.2149)	loss 3.4010 (2.9790)	grad_norm 3.3842 (3.3729)	
[2022-01-27 06:31:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][840/1251]	eta 0:15:10 lr 0.000010	time 3.0897 (2.2154)	loss 3.2176 (2.9765)	grad_norm 3.2954 (3.3712)	
[2022-01-27 06:32:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][850/1251]	eta 0:14:47 lr 0.000010	time 2.0763 (2.2131)	loss 2.0572 (2.9709)	grad_norm 3.0943 (3.3681)	
[2022-01-27 06:32:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][860/1251]	eta 0:14:24 lr 0.000010	time 1.8211 (2.2098)	loss 3.2485 (2.9704)	grad_norm 4.2295 (3.3682)	
[2022-01-27 06:33:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][870/1251]	eta 0:14:02 lr 0.000010	time 2.0009 (2.2102)	loss 2.6674 (2.9702)	grad_norm 3.2229 (3.3669)	
[2022-01-27 06:33:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][880/1251]	eta 0:13:40 lr 0.000010	time 2.9892 (2.2114)	loss 2.7535 (2.9687)	grad_norm 3.1566 (3.3681)	
[2022-01-27 06:33:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][890/1251]	eta 0:13:17 lr 0.000010	time 2.4843 (2.2104)	loss 3.2305 (2.9682)	grad_norm 2.8692 (3.3675)	
[2022-01-27 06:34:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][900/1251]	eta 0:12:55 lr 0.000010	time 1.7543 (2.2092)	loss 2.4809 (2.9669)	grad_norm 3.1422 (3.3657)	
[2022-01-27 06:34:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][910/1251]	eta 0:12:33 lr 0.000010	time 2.2816 (2.2097)	loss 3.0002 (2.9665)	grad_norm 3.2546 (3.3655)	
[2022-01-27 06:34:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][920/1251]	eta 0:12:11 lr 0.000010	time 2.3595 (2.2105)	loss 3.1598 (2.9667)	grad_norm 3.4971 (3.3664)	
[2022-01-27 06:35:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][930/1251]	eta 0:11:49 lr 0.000010	time 3.3683 (2.2114)	loss 2.7014 (2.9668)	grad_norm 3.2725 (3.3653)	
[2022-01-27 06:35:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][940/1251]	eta 0:11:27 lr 0.000010	time 1.9914 (2.2103)	loss 3.1775 (2.9680)	grad_norm 3.6160 (3.3663)	
[2022-01-27 06:35:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][950/1251]	eta 0:11:05 lr 0.000010	time 2.8217 (2.2112)	loss 3.4448 (2.9675)	grad_norm 2.9783 (3.3671)	
[2022-01-27 06:36:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][960/1251]	eta 0:10:43 lr 0.000010	time 1.7565 (2.2099)	loss 2.2041 (2.9672)	grad_norm 2.9509 (3.3646)	
[2022-01-27 06:36:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][970/1251]	eta 0:10:20 lr 0.000010	time 2.3392 (2.2077)	loss 3.2865 (2.9680)	grad_norm 3.2624 (3.3646)	
[2022-01-27 06:36:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][980/1251]	eta 0:09:57 lr 0.000010	time 1.7734 (2.2053)	loss 3.4875 (2.9682)	grad_norm 3.1776 (3.3629)	
[2022-01-27 06:37:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][990/1251]	eta 0:09:35 lr 0.000010	time 2.5178 (2.2054)	loss 3.1821 (2.9695)	grad_norm 3.4366 (3.3634)	
[2022-01-27 06:37:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1000/1251]	eta 0:09:13 lr 0.000010	time 1.6432 (2.2042)	loss 2.3845 (2.9697)	grad_norm 3.0997 (3.3644)	
[2022-01-27 06:38:03 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1010/1251]	eta 0:08:51 lr 0.000010	time 2.0917 (2.2034)	loss 2.9632 (2.9694)	grad_norm 3.5007 (3.3661)	
[2022-01-27 06:38:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1020/1251]	eta 0:08:29 lr 0.000010	time 2.2420 (2.2046)	loss 3.1483 (2.9696)	grad_norm 3.6095 (3.3686)	
[2022-01-27 06:38:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1030/1251]	eta 0:08:07 lr 0.000010	time 2.9757 (2.2062)	loss 3.4621 (2.9696)	grad_norm 3.3297 (3.3696)	
[2022-01-27 06:39:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1040/1251]	eta 0:07:45 lr 0.000010	time 1.5210 (2.2075)	loss 3.4466 (2.9700)	grad_norm 3.4727 (3.3709)	
[2022-01-27 06:39:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1050/1251]	eta 0:07:23 lr 0.000010	time 2.1869 (2.2077)	loss 2.0477 (2.9703)	grad_norm 3.3111 (3.3693)	
[2022-01-27 06:39:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1060/1251]	eta 0:07:01 lr 0.000010	time 2.2243 (2.2083)	loss 3.0439 (2.9716)	grad_norm 3.3194 (3.3709)	
[2022-01-27 06:40:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1070/1251]	eta 0:06:39 lr 0.000010	time 2.8560 (2.2083)	loss 2.9005 (2.9709)	grad_norm 3.3037 (3.3699)	
[2022-01-27 06:40:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1080/1251]	eta 0:06:17 lr 0.000010	time 1.9199 (2.2076)	loss 3.3845 (2.9686)	grad_norm 3.7324 (3.3693)	
[2022-01-27 06:41:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1090/1251]	eta 0:05:55 lr 0.000010	time 1.6193 (2.2062)	loss 2.9628 (2.9690)	grad_norm 3.5133 (3.3684)	
[2022-01-27 06:41:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1100/1251]	eta 0:05:33 lr 0.000010	time 1.9584 (2.2057)	loss 3.3214 (2.9720)	grad_norm 5.5862 (3.3705)	
[2022-01-27 06:41:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1110/1251]	eta 0:05:10 lr 0.000010	time 2.6803 (2.2051)	loss 3.1057 (2.9701)	grad_norm 3.4720 (3.3701)	
[2022-01-27 06:42:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1120/1251]	eta 0:04:48 lr 0.000010	time 1.8217 (2.2052)	loss 2.0349 (2.9676)	grad_norm 3.0173 (3.3733)	
[2022-01-27 06:42:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1130/1251]	eta 0:04:26 lr 0.000010	time 1.6541 (2.2039)	loss 3.2421 (2.9692)	grad_norm 3.8237 (3.3750)	
[2022-01-27 06:42:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1140/1251]	eta 0:04:04 lr 0.000010	time 1.9995 (2.2039)	loss 3.6807 (2.9697)	grad_norm 3.2359 (3.3756)	
[2022-01-27 06:43:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1150/1251]	eta 0:03:42 lr 0.000010	time 2.1951 (2.2048)	loss 3.1065 (2.9685)	grad_norm 3.6712 (3.3753)	
[2022-01-27 06:43:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1160/1251]	eta 0:03:20 lr 0.000010	time 2.4530 (2.2052)	loss 3.0486 (2.9693)	grad_norm 2.5285 (3.3746)	
[2022-01-27 06:43:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1170/1251]	eta 0:02:58 lr 0.000010	time 2.3269 (2.2054)	loss 3.0723 (2.9695)	grad_norm 4.2218 (3.3765)	
[2022-01-27 06:44:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1180/1251]	eta 0:02:36 lr 0.000010	time 1.6084 (2.2061)	loss 3.3312 (2.9685)	grad_norm 3.4072 (3.3797)	
[2022-01-27 06:44:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1190/1251]	eta 0:02:14 lr 0.000010	time 2.6243 (2.2069)	loss 2.1745 (2.9653)	grad_norm 3.1186 (3.3788)	
[2022-01-27 06:45:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1200/1251]	eta 0:01:52 lr 0.000010	time 1.7535 (2.2063)	loss 2.8648 (2.9659)	grad_norm 3.4690 (3.3780)	
[2022-01-27 06:45:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1210/1251]	eta 0:01:30 lr 0.000010	time 1.6348 (2.2048)	loss 2.9487 (2.9650)	grad_norm 2.8826 (3.3777)	
[2022-01-27 06:45:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1220/1251]	eta 0:01:08 lr 0.000010	time 1.9441 (2.2027)	loss 3.3013 (2.9670)	grad_norm 2.8833 (3.3772)	
[2022-01-27 06:46:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1230/1251]	eta 0:00:46 lr 0.000010	time 1.7174 (2.2026)	loss 2.6741 (2.9658)	grad_norm 3.2552 (3.3769)	
[2022-01-27 06:46:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1240/1251]	eta 0:00:24 lr 0.000010	time 1.9454 (2.2053)	loss 3.1173 (2.9650)	grad_norm 3.1041 (3.3828)	
[2022-01-27 06:46:47 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [297/300][1250/1251]	eta 0:00:02 lr 0.000010	time 1.1479 (2.1991)	loss 3.3281 (2.9637)	grad_norm 3.4161 (3.3820)	
[2022-01-27 06:46:47 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 297 training takes 0:45:51
[2022-01-27 06:47:06 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.571 (18.571)	Loss 0.8297 (0.8297)	Acc@1 80.859 (80.859)	Acc@5 94.922 (94.922)	
[2022-01-27 06:47:23 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 0.576 (3.273)	Loss 0.7897 (0.8246)	Acc@1 81.250 (80.602)	Acc@5 95.312 (95.295)	
[2022-01-27 06:47:40 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.298 (2.502)	Loss 0.7350 (0.8023)	Acc@1 82.520 (81.320)	Acc@5 96.387 (95.564)	
[2022-01-27 06:47:58 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.625 (2.305)	Loss 0.7509 (0.8052)	Acc@1 82.812 (81.272)	Acc@5 96.973 (95.634)	
[2022-01-27 06:48:16 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 3.682 (2.177)	Loss 0.8174 (0.8107)	Acc@1 81.250 (81.100)	Acc@5 95.605 (95.558)	
[2022-01-27 06:48:25 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.176 Acc@5 95.496
[2022-01-27 06:48:25 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.2%
[2022-01-27 06:48:25 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.24%
[2022-01-27 06:48:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][0/1251]	eta 7:23:11 lr 0.000010	time 21.2562 (21.2562)	loss 2.8303 (2.8303)	grad_norm 3.8410 (3.8410)	
[2022-01-27 06:49:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][10/1251]	eta 1:22:38 lr 0.000010	time 1.7080 (3.9956)	loss 2.4360 (2.9421)	grad_norm 3.0941 (3.7663)	
[2022-01-27 06:49:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][20/1251]	eta 1:06:15 lr 0.000010	time 2.0073 (3.2296)	loss 3.1003 (2.8824)	grad_norm 2.9146 (3.4782)	
[2022-01-27 06:49:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][30/1251]	eta 0:58:18 lr 0.000010	time 1.9480 (2.8653)	loss 3.5203 (2.9812)	grad_norm 4.6463 (3.4882)	
[2022-01-27 06:50:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][40/1251]	eta 0:55:58 lr 0.000010	time 3.8136 (2.7731)	loss 2.1764 (3.0204)	grad_norm 2.8641 (3.4550)	
[2022-01-27 06:50:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][50/1251]	eta 0:54:35 lr 0.000010	time 2.7123 (2.7274)	loss 3.4151 (3.0014)	grad_norm 2.7710 (3.4316)	
[2022-01-27 06:51:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][60/1251]	eta 0:52:15 lr 0.000010	time 2.0906 (2.6327)	loss 2.3945 (2.9499)	grad_norm 3.3960 (3.4255)	
[2022-01-27 06:51:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][70/1251]	eta 0:50:02 lr 0.000010	time 2.0599 (2.5420)	loss 3.3383 (2.9426)	grad_norm 4.2711 (3.4078)	
[2022-01-27 06:51:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][80/1251]	eta 0:48:07 lr 0.000010	time 1.9422 (2.4658)	loss 3.1780 (2.9370)	grad_norm 3.7093 (3.3944)	
[2022-01-27 06:52:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][90/1251]	eta 0:46:44 lr 0.000010	time 1.5249 (2.4156)	loss 3.1729 (2.9443)	grad_norm 3.2084 (3.4042)	
[2022-01-27 06:52:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][100/1251]	eta 0:45:38 lr 0.000010	time 1.8464 (2.3791)	loss 3.2166 (2.9530)	grad_norm 3.5560 (3.4112)	
[2022-01-27 06:52:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][110/1251]	eta 0:44:47 lr 0.000010	time 1.6104 (2.3554)	loss 3.2099 (2.9589)	grad_norm 3.0932 (3.3867)	
[2022-01-27 06:53:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][120/1251]	eta 0:44:01 lr 0.000010	time 2.3373 (2.3358)	loss 2.5171 (2.9373)	grad_norm 3.2511 (3.3789)	
[2022-01-27 06:53:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][130/1251]	eta 0:43:33 lr 0.000010	time 1.9943 (2.3310)	loss 3.5693 (2.9420)	grad_norm 4.0674 (3.3866)	
[2022-01-27 06:53:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][140/1251]	eta 0:42:54 lr 0.000010	time 1.4811 (2.3174)	loss 2.3542 (2.9429)	grad_norm 3.4663 (3.3690)	
[2022-01-27 06:54:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][150/1251]	eta 0:42:29 lr 0.000010	time 1.8902 (2.3157)	loss 3.4567 (2.9553)	grad_norm 3.3521 (3.3810)	
[2022-01-27 06:54:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][160/1251]	eta 0:42:03 lr 0.000010	time 2.3510 (2.3132)	loss 2.1815 (2.9696)	grad_norm 3.3962 (3.3865)	
[2022-01-27 06:55:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][170/1251]	eta 0:41:41 lr 0.000010	time 2.2003 (2.3136)	loss 3.5520 (2.9727)	grad_norm 4.0585 (3.4056)	
[2022-01-27 06:55:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][180/1251]	eta 0:41:11 lr 0.000010	time 1.5794 (2.3080)	loss 3.0441 (2.9800)	grad_norm 3.6594 (3.4001)	
[2022-01-27 06:55:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][190/1251]	eta 0:40:40 lr 0.000010	time 2.1541 (2.3001)	loss 2.9510 (2.9869)	grad_norm 3.0265 (3.4051)	
[2022-01-27 06:56:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][200/1251]	eta 0:40:20 lr 0.000010	time 2.8207 (2.3032)	loss 3.3977 (2.9833)	grad_norm 3.0813 (3.4021)	
[2022-01-27 06:56:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][210/1251]	eta 0:39:58 lr 0.000010	time 1.9534 (2.3037)	loss 3.1433 (2.9812)	grad_norm 3.2977 (3.4015)	
[2022-01-27 06:56:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][220/1251]	eta 0:39:29 lr 0.000010	time 1.9585 (2.2985)	loss 2.9292 (2.9781)	grad_norm 3.4402 (3.3941)	
[2022-01-27 06:57:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][230/1251]	eta 0:38:56 lr 0.000010	time 2.1804 (2.2885)	loss 2.5886 (2.9727)	grad_norm 3.1033 (3.3821)	
[2022-01-27 06:57:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][240/1251]	eta 0:38:29 lr 0.000010	time 2.0344 (2.2846)	loss 2.0449 (2.9688)	grad_norm 3.4186 (3.3768)	
[2022-01-27 06:57:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][250/1251]	eta 0:38:10 lr 0.000010	time 1.6680 (2.2879)	loss 2.8346 (2.9680)	grad_norm 3.2102 (3.4170)	
[2022-01-27 06:58:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][260/1251]	eta 0:37:35 lr 0.000010	time 1.8545 (2.2759)	loss 1.8881 (2.9689)	grad_norm 2.5000 (3.4157)	
[2022-01-27 06:58:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][270/1251]	eta 0:37:03 lr 0.000010	time 1.5945 (2.2664)	loss 3.3692 (2.9756)	grad_norm 3.2826 (3.4179)	
[2022-01-27 06:59:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][280/1251]	eta 0:36:40 lr 0.000010	time 1.9083 (2.2664)	loss 2.9539 (2.9800)	grad_norm 3.4266 (3.4154)	
[2022-01-27 06:59:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][290/1251]	eta 0:36:15 lr 0.000010	time 1.9268 (2.2640)	loss 3.5770 (2.9807)	grad_norm 3.0443 (3.4084)	
[2022-01-27 06:59:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][300/1251]	eta 0:35:54 lr 0.000010	time 2.7463 (2.2652)	loss 3.1756 (2.9801)	grad_norm 3.6743 (3.4082)	
[2022-01-27 07:00:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][310/1251]	eta 0:35:24 lr 0.000010	time 1.6184 (2.2577)	loss 3.3082 (2.9823)	grad_norm 3.5755 (3.4138)	
[2022-01-27 07:00:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][320/1251]	eta 0:34:59 lr 0.000010	time 2.2971 (2.2556)	loss 2.4058 (2.9837)	grad_norm 3.5429 (3.4112)	
[2022-01-27 07:00:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][330/1251]	eta 0:34:36 lr 0.000010	time 3.3994 (2.2544)	loss 3.2425 (2.9858)	grad_norm 3.2914 (3.4064)	
[2022-01-27 07:01:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][340/1251]	eta 0:34:11 lr 0.000010	time 2.1321 (2.2519)	loss 3.6587 (2.9881)	grad_norm 2.9657 (3.4046)	
[2022-01-27 07:01:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][350/1251]	eta 0:33:46 lr 0.000010	time 1.8652 (2.2496)	loss 2.8181 (2.9913)	grad_norm 2.8488 (3.4031)	
[2022-01-27 07:01:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][360/1251]	eta 0:33:28 lr 0.000010	time 2.1599 (2.2543)	loss 3.0982 (2.9928)	grad_norm 2.9822 (3.3958)	
[2022-01-27 07:02:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][370/1251]	eta 0:33:03 lr 0.000010	time 2.3361 (2.2519)	loss 3.1862 (2.9927)	grad_norm 3.2815 (3.4047)	
[2022-01-27 07:02:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][380/1251]	eta 0:32:34 lr 0.000010	time 2.2249 (2.2445)	loss 3.0016 (2.9935)	grad_norm 3.2090 (3.4063)	
[2022-01-27 07:03:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][390/1251]	eta 0:32:07 lr 0.000010	time 2.2590 (2.2388)	loss 3.2509 (2.9941)	grad_norm 3.3382 (3.4178)	
[2022-01-27 07:03:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][400/1251]	eta 0:31:42 lr 0.000010	time 2.2006 (2.2353)	loss 3.3394 (2.9976)	grad_norm 3.2746 (3.4132)	
[2022-01-27 07:03:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][410/1251]	eta 0:31:17 lr 0.000010	time 1.8853 (2.2328)	loss 3.3685 (2.9955)	grad_norm 2.9452 (3.4142)	
[2022-01-27 07:04:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][420/1251]	eta 0:30:55 lr 0.000010	time 1.5816 (2.2328)	loss 3.4510 (2.9913)	grad_norm 2.9656 (3.4128)	
[2022-01-27 07:04:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][430/1251]	eta 0:30:34 lr 0.000010	time 1.8477 (2.2342)	loss 3.3258 (2.9940)	grad_norm 2.6399 (3.4072)	
[2022-01-27 07:04:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][440/1251]	eta 0:30:13 lr 0.000010	time 2.2037 (2.2356)	loss 1.9830 (2.9935)	grad_norm 3.9111 (3.4031)	
[2022-01-27 07:05:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][450/1251]	eta 0:29:53 lr 0.000010	time 1.9380 (2.2389)	loss 2.7650 (2.9935)	grad_norm 3.2762 (3.4030)	
[2022-01-27 07:05:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][460/1251]	eta 0:29:30 lr 0.000010	time 1.9714 (2.2389)	loss 3.1396 (2.9921)	grad_norm 3.1826 (3.3976)	
[2022-01-27 07:05:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][470/1251]	eta 0:29:05 lr 0.000010	time 2.1549 (2.2350)	loss 2.4006 (2.9854)	grad_norm 3.5684 (3.3991)	
[2022-01-27 07:06:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][480/1251]	eta 0:28:40 lr 0.000010	time 1.9087 (2.2314)	loss 2.9208 (2.9799)	grad_norm 2.9937 (3.3954)	
[2022-01-27 07:06:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][490/1251]	eta 0:28:14 lr 0.000010	time 1.9459 (2.2265)	loss 2.7555 (2.9786)	grad_norm 2.9505 (3.3965)	
[2022-01-27 07:06:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][500/1251]	eta 0:27:49 lr 0.000010	time 1.7935 (2.2232)	loss 2.9545 (2.9751)	grad_norm 2.6137 (3.4068)	
[2022-01-27 07:07:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][510/1251]	eta 0:27:27 lr 0.000010	time 2.5457 (2.2235)	loss 3.3229 (2.9733)	grad_norm 3.2144 (3.4055)	
[2022-01-27 07:07:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][520/1251]	eta 0:27:03 lr 0.000010	time 1.4681 (2.2211)	loss 2.1846 (2.9720)	grad_norm 3.1139 (3.4062)	
[2022-01-27 07:08:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][530/1251]	eta 0:26:42 lr 0.000010	time 1.8335 (2.2222)	loss 3.6766 (2.9765)	grad_norm 3.3514 (3.4089)	
[2022-01-27 07:08:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][540/1251]	eta 0:26:22 lr 0.000010	time 2.4726 (2.2255)	loss 3.1538 (2.9704)	grad_norm 3.2814 (3.4125)	
[2022-01-27 07:08:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][550/1251]	eta 0:26:03 lr 0.000010	time 2.4319 (2.2304)	loss 3.2304 (2.9713)	grad_norm 3.0685 (3.4096)	
[2022-01-27 07:09:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][560/1251]	eta 0:25:40 lr 0.000010	time 1.4816 (2.2293)	loss 2.2205 (2.9699)	grad_norm 4.0511 (3.4118)	
[2022-01-27 07:09:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][570/1251]	eta 0:25:17 lr 0.000010	time 1.8382 (2.2291)	loss 2.6194 (2.9698)	grad_norm 3.6311 (3.4103)	
[2022-01-27 07:09:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][580/1251]	eta 0:24:54 lr 0.000010	time 2.4490 (2.2270)	loss 3.0721 (2.9686)	grad_norm 3.3238 (3.4067)	
[2022-01-27 07:10:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][590/1251]	eta 0:24:29 lr 0.000010	time 1.8326 (2.2224)	loss 3.1757 (2.9683)	grad_norm 3.3215 (3.4041)	
[2022-01-27 07:10:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][600/1251]	eta 0:24:04 lr 0.000010	time 1.8823 (2.2192)	loss 2.5811 (2.9685)	grad_norm 3.0548 (3.4044)	
[2022-01-27 07:11:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][610/1251]	eta 0:23:42 lr 0.000010	time 1.9318 (2.2192)	loss 3.2505 (2.9698)	grad_norm 3.5126 (3.4050)	
[2022-01-27 07:11:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][620/1251]	eta 0:23:20 lr 0.000010	time 2.8732 (2.2192)	loss 2.4202 (2.9689)	grad_norm 3.0844 (3.3993)	
[2022-01-27 07:11:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][630/1251]	eta 0:22:59 lr 0.000010	time 2.7650 (2.2214)	loss 3.3628 (2.9659)	grad_norm 3.3371 (3.3979)	
[2022-01-27 07:12:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][640/1251]	eta 0:22:37 lr 0.000010	time 1.7997 (2.2219)	loss 3.1689 (2.9642)	grad_norm 3.4809 (3.3983)	
[2022-01-27 07:12:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][650/1251]	eta 0:22:15 lr 0.000010	time 1.5971 (2.2215)	loss 1.8917 (2.9619)	grad_norm 2.9167 (3.3968)	
[2022-01-27 07:12:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][660/1251]	eta 0:21:51 lr 0.000010	time 1.9269 (2.2196)	loss 2.4205 (2.9588)	grad_norm 3.7994 (3.4001)	
[2022-01-27 07:13:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][670/1251]	eta 0:21:29 lr 0.000010	time 1.8836 (2.2191)	loss 3.2244 (2.9598)	grad_norm 3.5499 (3.4010)	
[2022-01-27 07:13:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][680/1251]	eta 0:21:06 lr 0.000010	time 1.9843 (2.2181)	loss 3.0401 (2.9579)	grad_norm 3.4881 (3.4010)	
[2022-01-27 07:13:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][690/1251]	eta 0:20:42 lr 0.000010	time 1.6349 (2.2142)	loss 2.5368 (2.9552)	grad_norm 3.0688 (3.3979)	
[2022-01-27 07:14:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][700/1251]	eta 0:20:20 lr 0.000010	time 1.9751 (2.2143)	loss 2.5918 (2.9517)	grad_norm 3.4297 (3.3967)	
[2022-01-27 07:14:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][710/1251]	eta 0:19:58 lr 0.000010	time 2.6086 (2.2159)	loss 3.2081 (2.9524)	grad_norm 3.1545 (3.3950)	
[2022-01-27 07:15:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][720/1251]	eta 0:19:35 lr 0.000010	time 1.8277 (2.2137)	loss 2.7976 (2.9541)	grad_norm 4.1525 (3.3952)	
[2022-01-27 07:15:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][730/1251]	eta 0:19:12 lr 0.000010	time 2.2253 (2.2130)	loss 3.0265 (2.9560)	grad_norm 3.5159 (3.3939)	
[2022-01-27 07:15:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][740/1251]	eta 0:18:50 lr 0.000010	time 1.8324 (2.2130)	loss 3.4137 (2.9579)	grad_norm 3.1850 (3.3950)	
[2022-01-27 07:16:08 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][750/1251]	eta 0:18:29 lr 0.000010	time 1.9548 (2.2142)	loss 2.3336 (2.9570)	grad_norm 3.4907 (3.3941)	
[2022-01-27 07:16:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][760/1251]	eta 0:18:07 lr 0.000010	time 2.1949 (2.2147)	loss 3.0086 (2.9566)	grad_norm 3.5925 (3.3935)	
[2022-01-27 07:16:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][770/1251]	eta 0:17:44 lr 0.000010	time 1.5464 (2.2138)	loss 3.4027 (2.9562)	grad_norm 3.4387 (3.3940)	
[2022-01-27 07:17:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][780/1251]	eta 0:17:21 lr 0.000010	time 1.7117 (2.2123)	loss 3.2463 (2.9597)	grad_norm 3.4305 (3.3957)	
[2022-01-27 07:17:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][790/1251]	eta 0:16:59 lr 0.000010	time 2.0599 (2.2111)	loss 1.9562 (2.9584)	grad_norm 3.6910 (3.3979)	
[2022-01-27 07:17:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][800/1251]	eta 0:16:36 lr 0.000010	time 2.1488 (2.2093)	loss 3.2786 (2.9601)	grad_norm 3.0377 (3.3963)	
[2022-01-27 07:18:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][810/1251]	eta 0:16:13 lr 0.000010	time 2.1762 (2.2077)	loss 2.2801 (2.9598)	grad_norm 3.3370 (3.3969)	
[2022-01-27 07:18:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][820/1251]	eta 0:15:51 lr 0.000010	time 1.9208 (2.2071)	loss 2.7466 (2.9573)	grad_norm 2.9338 (3.3953)	
[2022-01-27 07:19:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][830/1251]	eta 0:15:30 lr 0.000010	time 2.2106 (2.2093)	loss 3.2836 (2.9566)	grad_norm 3.4590 (3.3958)	
[2022-01-27 07:19:26 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][840/1251]	eta 0:15:09 lr 0.000010	time 3.4022 (2.2132)	loss 3.3237 (2.9547)	grad_norm 2.8757 (3.3926)	
[2022-01-27 07:19:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][850/1251]	eta 0:14:48 lr 0.000010	time 1.8925 (2.2167)	loss 2.8261 (2.9532)	grad_norm 3.0736 (3.3884)	
[2022-01-27 07:20:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][860/1251]	eta 0:14:26 lr 0.000010	time 1.9578 (2.2166)	loss 2.7429 (2.9501)	grad_norm 3.1592 (3.3854)	
[2022-01-27 07:20:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][870/1251]	eta 0:14:03 lr 0.000010	time 1.8604 (2.2144)	loss 2.5875 (2.9489)	grad_norm 3.5687 (3.3851)	
[2022-01-27 07:20:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][880/1251]	eta 0:13:40 lr 0.000010	time 1.8912 (2.2103)	loss 2.4720 (2.9506)	grad_norm 3.2556 (3.3866)	
[2022-01-27 07:21:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][890/1251]	eta 0:13:16 lr 0.000010	time 1.9159 (2.2069)	loss 3.4622 (2.9517)	grad_norm 3.2640 (3.3859)	
[2022-01-27 07:21:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][900/1251]	eta 0:12:54 lr 0.000010	time 2.2489 (2.2052)	loss 3.4647 (2.9506)	grad_norm 3.2107 (3.3887)	
[2022-01-27 07:21:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][910/1251]	eta 0:12:33 lr 0.000010	time 3.6396 (2.2097)	loss 1.8487 (2.9526)	grad_norm 3.3735 (3.3873)	
[2022-01-27 07:22:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][920/1251]	eta 0:12:12 lr 0.000010	time 1.5325 (2.2136)	loss 2.7234 (2.9487)	grad_norm 2.7466 (3.3874)	
[2022-01-27 07:22:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][930/1251]	eta 0:11:50 lr 0.000010	time 2.1571 (2.2134)	loss 3.0026 (2.9499)	grad_norm 3.5906 (3.3874)	
[2022-01-27 07:23:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][940/1251]	eta 0:11:28 lr 0.000010	time 1.9337 (2.2131)	loss 2.6585 (2.9488)	grad_norm 3.6057 (3.3895)	
[2022-01-27 07:23:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][950/1251]	eta 0:11:06 lr 0.000010	time 4.3189 (2.2141)	loss 3.4858 (2.9477)	grad_norm 3.5939 (3.3913)	
[2022-01-27 07:23:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][960/1251]	eta 0:10:43 lr 0.000010	time 2.2797 (2.2121)	loss 3.6054 (2.9490)	grad_norm 2.8811 (3.3896)	
[2022-01-27 07:24:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][970/1251]	eta 0:10:20 lr 0.000010	time 1.7717 (2.2095)	loss 2.5380 (2.9488)	grad_norm 3.0992 (3.3889)	
[2022-01-27 07:24:32 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][980/1251]	eta 0:09:58 lr 0.000010	time 1.8683 (2.2093)	loss 3.0502 (2.9492)	grad_norm 2.8578 (3.3878)	
[2022-01-27 07:24:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][990/1251]	eta 0:09:37 lr 0.000010	time 2.8824 (2.2108)	loss 3.2125 (2.9503)	grad_norm 3.0933 (3.3869)	
[2022-01-27 07:25:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1000/1251]	eta 0:09:14 lr 0.000010	time 1.9139 (2.2099)	loss 2.6128 (2.9488)	grad_norm 3.2417 (3.3867)	
[2022-01-27 07:25:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1010/1251]	eta 0:08:52 lr 0.000010	time 2.2772 (2.2093)	loss 3.0485 (2.9490)	grad_norm 3.0242 (3.3857)	
[2022-01-27 07:26:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1020/1251]	eta 0:08:30 lr 0.000010	time 1.6836 (2.2089)	loss 1.8703 (2.9505)	grad_norm 3.5087 (3.3864)	
[2022-01-27 07:26:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1030/1251]	eta 0:08:08 lr 0.000010	time 2.4678 (2.2085)	loss 3.1484 (2.9508)	grad_norm 3.1637 (3.3834)	
[2022-01-27 07:26:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1040/1251]	eta 0:07:46 lr 0.000010	time 2.6441 (2.2088)	loss 3.4932 (2.9495)	grad_norm 3.9783 (3.3834)	
[2022-01-27 07:27:05 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1050/1251]	eta 0:07:23 lr 0.000010	time 2.2776 (2.2078)	loss 2.5503 (2.9475)	grad_norm 3.6423 (3.3819)	
[2022-01-27 07:27:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1060/1251]	eta 0:07:02 lr 0.000010	time 1.7517 (2.2111)	loss 3.1776 (2.9489)	grad_norm 3.8060 (3.3816)	
[2022-01-27 07:27:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1070/1251]	eta 0:06:40 lr 0.000010	time 2.7804 (2.2120)	loss 3.2271 (2.9498)	grad_norm 3.5826 (3.3835)	
[2022-01-27 07:28:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1080/1251]	eta 0:06:17 lr 0.000010	time 2.0966 (2.2102)	loss 2.9938 (2.9512)	grad_norm 3.0103 (3.3826)	
[2022-01-27 07:28:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1090/1251]	eta 0:05:55 lr 0.000010	time 1.8579 (2.2072)	loss 3.3910 (2.9516)	grad_norm 4.0925 (3.3831)	
[2022-01-27 07:28:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1100/1251]	eta 0:05:33 lr 0.000010	time 1.6496 (2.2054)	loss 3.3356 (2.9533)	grad_norm 3.8068 (3.3864)	
[2022-01-27 07:29:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1110/1251]	eta 0:05:10 lr 0.000010	time 2.2412 (2.2045)	loss 3.3930 (2.9521)	grad_norm 3.2132 (3.3857)	
[2022-01-27 07:29:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1120/1251]	eta 0:04:48 lr 0.000010	time 1.9416 (2.2043)	loss 3.2509 (2.9527)	grad_norm 3.6708 (3.3850)	
[2022-01-27 07:29:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1130/1251]	eta 0:04:26 lr 0.000010	time 2.1130 (2.2040)	loss 2.5953 (2.9526)	grad_norm 3.2822 (3.3838)	
[2022-01-27 07:30:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1140/1251]	eta 0:04:04 lr 0.000010	time 2.2153 (2.2040)	loss 2.1867 (2.9520)	grad_norm 3.5745 (3.3829)	
[2022-01-27 07:30:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1150/1251]	eta 0:03:42 lr 0.000010	time 4.5028 (2.2059)	loss 2.2821 (2.9508)	grad_norm 4.4205 (3.3826)	
[2022-01-27 07:31:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1160/1251]	eta 0:03:20 lr 0.000010	time 1.9017 (2.2060)	loss 2.6335 (2.9520)	grad_norm 2.9714 (3.3840)	
[2022-01-27 07:31:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1170/1251]	eta 0:02:58 lr 0.000010	time 2.1443 (2.2078)	loss 3.6347 (2.9523)	grad_norm 3.6600 (3.3851)	
[2022-01-27 07:31:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1180/1251]	eta 0:02:36 lr 0.000010	time 1.8976 (2.2079)	loss 3.4157 (2.9552)	grad_norm 3.0704 (3.3860)	
[2022-01-27 07:32:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1190/1251]	eta 0:02:14 lr 0.000010	time 2.2489 (2.2085)	loss 2.1985 (2.9550)	grad_norm 3.1242 (3.3905)	
[2022-01-27 07:32:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1200/1251]	eta 0:01:52 lr 0.000010	time 1.6956 (2.2059)	loss 3.4503 (2.9563)	grad_norm 2.9409 (3.3898)	
[2022-01-27 07:32:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1210/1251]	eta 0:01:30 lr 0.000010	time 2.2729 (2.2040)	loss 1.7713 (2.9561)	grad_norm 2.8209 (3.3894)	
[2022-01-27 07:33:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1220/1251]	eta 0:01:08 lr 0.000010	time 2.2452 (2.2039)	loss 2.6080 (2.9556)	grad_norm 3.4671 (3.3879)	
[2022-01-27 07:33:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1230/1251]	eta 0:00:46 lr 0.000010	time 2.1287 (2.2039)	loss 2.9454 (2.9560)	grad_norm 3.3301 (3.3953)	
[2022-01-27 07:33:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1240/1251]	eta 0:00:24 lr 0.000010	time 1.9252 (2.2034)	loss 2.6918 (2.9566)	grad_norm 3.2138 (3.3991)	
[2022-01-27 07:34:15 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [298/300][1250/1251]	eta 0:00:02 lr 0.000010	time 1.1649 (2.1982)	loss 1.9931 (2.9555)	grad_norm 3.5387 (3.3983)	
[2022-01-27 07:34:15 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 298 training takes 0:45:50
[2022-01-27 07:34:34 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 18.684 (18.684)	Loss 0.8177 (0.8177)	Acc@1 81.738 (81.738)	Acc@5 94.824 (94.824)	
[2022-01-27 07:34:53 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.256 (3.449)	Loss 0.8198 (0.8185)	Acc@1 80.371 (80.540)	Acc@5 94.727 (95.179)	
[2022-01-27 07:35:09 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.590 (2.563)	Loss 0.8261 (0.8180)	Acc@1 81.641 (80.920)	Acc@5 94.434 (95.187)	
[2022-01-27 07:35:25 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 1.118 (2.258)	Loss 0.8260 (0.8133)	Acc@1 80.371 (81.143)	Acc@5 95.312 (95.341)	
[2022-01-27 07:35:44 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 1.901 (2.167)	Loss 0.7761 (0.8057)	Acc@1 82.031 (81.171)	Acc@5 95.703 (95.489)	
[2022-01-27 07:35:51 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.176 Acc@5 95.476
[2022-01-27 07:35:51 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.2%
[2022-01-27 07:35:51 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.24%
[2022-01-27 07:36:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][0/1251]	eta 7:47:54 lr 0.000010	time 22.4417 (22.4417)	loss 3.5195 (3.5195)	grad_norm 3.7918 (3.7918)	
[2022-01-27 07:36:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][10/1251]	eta 1:25:50 lr 0.000010	time 2.5548 (4.1502)	loss 3.2169 (3.3764)	grad_norm 2.8597 (3.4911)	
[2022-01-27 07:36:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][20/1251]	eta 1:06:22 lr 0.000010	time 1.8527 (3.2352)	loss 2.3575 (3.2690)	grad_norm 3.3942 (3.4172)	
[2022-01-27 07:37:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][30/1251]	eta 1:00:54 lr 0.000010	time 1.4704 (2.9929)	loss 3.7297 (3.1329)	grad_norm 6.0746 (3.5417)	
[2022-01-27 07:37:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][40/1251]	eta 0:57:25 lr 0.000010	time 3.8326 (2.8455)	loss 3.3526 (3.1054)	grad_norm 3.6715 (3.6121)	
[2022-01-27 07:38:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][50/1251]	eta 0:54:00 lr 0.000010	time 2.1012 (2.6984)	loss 2.6052 (3.0666)	grad_norm 3.2938 (3.5842)	
[2022-01-27 07:38:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][60/1251]	eta 0:51:19 lr 0.000010	time 1.6300 (2.5859)	loss 2.5761 (2.9991)	grad_norm 4.1657 (3.5453)	
[2022-01-27 07:38:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][70/1251]	eta 0:49:30 lr 0.000010	time 1.9104 (2.5156)	loss 3.2956 (3.0125)	grad_norm 3.4679 (3.5345)	
[2022-01-27 07:39:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][80/1251]	eta 0:48:56 lr 0.000010	time 3.6929 (2.5076)	loss 3.0570 (3.0128)	grad_norm 4.5577 (3.5320)	
[2022-01-27 07:39:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][90/1251]	eta 0:47:29 lr 0.000010	time 2.2106 (2.4541)	loss 2.6403 (3.0198)	grad_norm 3.4271 (3.5317)	
[2022-01-27 07:39:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][100/1251]	eta 0:46:12 lr 0.000010	time 1.5935 (2.4086)	loss 2.7861 (3.0183)	grad_norm 3.2701 (3.5207)	
[2022-01-27 07:40:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][110/1251]	eta 0:45:17 lr 0.000010	time 2.0074 (2.3821)	loss 3.1718 (3.0279)	grad_norm 3.1614 (3.5370)	
[2022-01-27 07:40:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][120/1251]	eta 0:44:29 lr 0.000010	time 3.1756 (2.3604)	loss 3.3493 (3.0432)	grad_norm 3.7269 (3.5437)	
[2022-01-27 07:40:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][130/1251]	eta 0:43:47 lr 0.000010	time 1.9650 (2.3436)	loss 2.2846 (3.0302)	grad_norm 4.5017 (3.5220)	
[2022-01-27 07:41:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][140/1251]	eta 0:43:16 lr 0.000010	time 2.2463 (2.3369)	loss 2.8691 (3.0356)	grad_norm 3.2695 (3.5064)	
[2022-01-27 07:41:42 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][150/1251]	eta 0:42:36 lr 0.000010	time 2.0203 (2.3220)	loss 2.9326 (3.0389)	grad_norm 3.8116 (3.5003)	
[2022-01-27 07:42:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][160/1251]	eta 0:42:10 lr 0.000010	time 2.8733 (2.3190)	loss 1.6164 (3.0221)	grad_norm 3.1383 (3.4850)	
[2022-01-27 07:42:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][170/1251]	eta 0:41:41 lr 0.000010	time 1.8938 (2.3140)	loss 2.8105 (3.0141)	grad_norm 2.8015 (3.4682)	
[2022-01-27 07:42:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][180/1251]	eta 0:41:25 lr 0.000010	time 2.6090 (2.3206)	loss 3.0606 (2.9971)	grad_norm 3.5509 (3.4488)	
[2022-01-27 07:43:12 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][190/1251]	eta 0:40:51 lr 0.000010	time 1.6747 (2.3106)	loss 2.8116 (2.9968)	grad_norm 3.1857 (3.4543)	
[2022-01-27 07:43:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][200/1251]	eta 0:40:27 lr 0.000010	time 2.7666 (2.3099)	loss 1.8664 (2.9934)	grad_norm 3.2511 (3.4451)	
[2022-01-27 07:43:58 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][210/1251]	eta 0:40:01 lr 0.000010	time 1.7169 (2.3073)	loss 3.0872 (2.9895)	grad_norm 3.3143 (3.4388)	
[2022-01-27 07:44:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][220/1251]	eta 0:39:26 lr 0.000010	time 1.9674 (2.2952)	loss 3.3397 (2.9783)	grad_norm 2.8598 (3.4300)	
[2022-01-27 07:44:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][230/1251]	eta 0:38:47 lr 0.000010	time 1.6213 (2.2795)	loss 2.2677 (2.9789)	grad_norm 3.8295 (3.4466)	
[2022-01-27 07:45:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][240/1251]	eta 0:38:22 lr 0.000010	time 3.0485 (2.2775)	loss 3.1771 (2.9743)	grad_norm 3.2985 (3.4437)	
[2022-01-27 07:45:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][250/1251]	eta 0:37:54 lr 0.000010	time 1.4852 (2.2725)	loss 3.3364 (2.9842)	grad_norm 3.2452 (3.4345)	
[2022-01-27 07:45:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][260/1251]	eta 0:37:30 lr 0.000010	time 2.3333 (2.2710)	loss 3.0655 (2.9856)	grad_norm 3.0203 (3.4288)	
[2022-01-27 07:46:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][270/1251]	eta 0:37:04 lr 0.000010	time 1.8592 (2.2677)	loss 2.0621 (2.9772)	grad_norm 3.3754 (3.4297)	
[2022-01-27 07:46:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][280/1251]	eta 0:36:45 lr 0.000010	time 2.8782 (2.2711)	loss 3.2113 (2.9713)	grad_norm 3.0817 (3.4349)	
[2022-01-27 07:46:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][290/1251]	eta 0:36:21 lr 0.000010	time 1.5875 (2.2699)	loss 2.9365 (2.9646)	grad_norm 3.4250 (3.4347)	
[2022-01-27 07:47:14 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][300/1251]	eta 0:35:58 lr 0.000010	time 2.4497 (2.2696)	loss 2.9664 (2.9590)	grad_norm 3.7740 (3.4412)	
[2022-01-27 07:47:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][310/1251]	eta 0:35:29 lr 0.000010	time 1.9276 (2.2635)	loss 2.8489 (2.9654)	grad_norm 3.6120 (3.4424)	
[2022-01-27 07:47:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][320/1251]	eta 0:35:05 lr 0.000010	time 2.2250 (2.2611)	loss 3.4189 (2.9624)	grad_norm 2.7345 (3.4409)	
[2022-01-27 07:48:18 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][330/1251]	eta 0:34:37 lr 0.000010	time 1.9720 (2.2554)	loss 3.4022 (2.9623)	grad_norm 3.0439 (3.4365)	
[2022-01-27 07:48:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][340/1251]	eta 0:34:13 lr 0.000010	time 2.9675 (2.2543)	loss 1.9470 (2.9628)	grad_norm 2.7013 (3.4414)	
[2022-01-27 07:49:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][350/1251]	eta 0:33:47 lr 0.000010	time 1.9903 (2.2505)	loss 3.4233 (2.9632)	grad_norm 3.1839 (3.4400)	
[2022-01-27 07:49:24 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][360/1251]	eta 0:33:25 lr 0.000010	time 2.1104 (2.2513)	loss 3.0109 (2.9665)	grad_norm 3.2719 (3.4391)	
[2022-01-27 07:49:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][370/1251]	eta 0:33:03 lr 0.000010	time 2.1751 (2.2509)	loss 3.2006 (2.9683)	grad_norm 3.6978 (3.4422)	
[2022-01-27 07:50:10 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][380/1251]	eta 0:32:43 lr 0.000010	time 3.0537 (2.2543)	loss 2.1803 (2.9652)	grad_norm 3.1651 (3.4401)	
[2022-01-27 07:50:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][390/1251]	eta 0:32:16 lr 0.000010	time 1.5136 (2.2488)	loss 3.2260 (2.9719)	grad_norm 3.0537 (3.4428)	
[2022-01-27 07:50:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][400/1251]	eta 0:31:51 lr 0.000010	time 1.7830 (2.2458)	loss 3.3269 (2.9730)	grad_norm 2.8458 (3.4408)	
[2022-01-27 07:51:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][410/1251]	eta 0:31:26 lr 0.000010	time 1.9253 (2.2428)	loss 3.4558 (2.9741)	grad_norm 3.9243 (3.4411)	
[2022-01-27 07:51:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][420/1251]	eta 0:31:06 lr 0.000010	time 3.3206 (2.2458)	loss 3.0354 (2.9750)	grad_norm 3.0345 (3.4446)	
[2022-01-27 07:51:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][430/1251]	eta 0:30:39 lr 0.000010	time 1.5981 (2.2409)	loss 3.5448 (2.9776)	grad_norm 3.4706 (3.4420)	
[2022-01-27 07:52:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][440/1251]	eta 0:30:17 lr 0.000010	time 2.1887 (2.2406)	loss 3.3011 (2.9746)	grad_norm 3.5684 (3.4392)	
[2022-01-27 07:52:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][450/1251]	eta 0:29:53 lr 0.000010	time 2.1544 (2.2392)	loss 3.5535 (2.9697)	grad_norm 3.1868 (3.4415)	
[2022-01-27 07:53:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][460/1251]	eta 0:29:31 lr 0.000010	time 2.8662 (2.2400)	loss 3.4732 (2.9728)	grad_norm 3.8299 (3.4439)	
[2022-01-27 07:53:25 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][470/1251]	eta 0:29:08 lr 0.000010	time 2.2184 (2.2385)	loss 3.0764 (2.9734)	grad_norm 3.2240 (3.4424)	
[2022-01-27 07:53:48 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][480/1251]	eta 0:28:46 lr 0.000010	time 2.4344 (2.2389)	loss 2.3764 (2.9714)	grad_norm 3.1389 (3.4426)	
[2022-01-27 07:54:09 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][490/1251]	eta 0:28:22 lr 0.000010	time 1.9010 (2.2369)	loss 3.3209 (2.9696)	grad_norm 3.1403 (3.4442)	
[2022-01-27 07:54:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][500/1251]	eta 0:27:58 lr 0.000010	time 2.2177 (2.2355)	loss 2.5358 (2.9646)	grad_norm 2.8474 (3.4510)	
[2022-01-27 07:54:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][510/1251]	eta 0:27:34 lr 0.000010	time 2.1900 (2.2329)	loss 3.4524 (2.9667)	grad_norm 3.7055 (3.4471)	
[2022-01-27 07:55:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][520/1251]	eta 0:27:10 lr 0.000010	time 2.4795 (2.2301)	loss 2.1275 (2.9669)	grad_norm 3.3183 (3.4495)	
[2022-01-27 07:55:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][530/1251]	eta 0:26:46 lr 0.000010	time 2.1299 (2.2287)	loss 3.2149 (2.9634)	grad_norm 3.4870 (3.4462)	
[2022-01-27 07:55:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][540/1251]	eta 0:26:23 lr 0.000010	time 1.8862 (2.2272)	loss 2.9480 (2.9644)	grad_norm 3.3381 (3.4488)	
[2022-01-27 07:56:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][550/1251]	eta 0:26:02 lr 0.000010	time 3.0933 (2.2284)	loss 3.1217 (2.9672)	grad_norm 3.5524 (3.4486)	
[2022-01-27 07:56:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][560/1251]	eta 0:25:39 lr 0.000010	time 2.7420 (2.2276)	loss 3.0968 (2.9705)	grad_norm 3.5097 (3.4447)	
[2022-01-27 07:57:02 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][570/1251]	eta 0:25:15 lr 0.000010	time 1.6197 (2.2259)	loss 2.6601 (2.9708)	grad_norm 3.8071 (3.4420)	
[2022-01-27 07:57:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][580/1251]	eta 0:24:52 lr 0.000010	time 1.7547 (2.2242)	loss 3.2957 (2.9758)	grad_norm 3.3294 (3.4432)	
[2022-01-27 07:57:46 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][590/1251]	eta 0:24:30 lr 0.000010	time 2.5880 (2.2245)	loss 2.3900 (2.9727)	grad_norm 3.2054 (3.4423)	
[2022-01-27 07:58:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][600/1251]	eta 0:24:06 lr 0.000010	time 1.9885 (2.2216)	loss 3.0535 (2.9733)	grad_norm 3.6377 (3.4442)	
[2022-01-27 07:58:27 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][610/1251]	eta 0:23:42 lr 0.000010	time 2.2070 (2.2197)	loss 3.1934 (2.9738)	grad_norm 3.2842 (3.4418)	
[2022-01-27 07:58:49 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][620/1251]	eta 0:23:20 lr 0.000010	time 1.8652 (2.2193)	loss 3.4784 (2.9742)	grad_norm 3.4720 (3.4384)	
[2022-01-27 07:59:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][630/1251]	eta 0:22:58 lr 0.000010	time 3.5264 (2.2191)	loss 3.1180 (2.9741)	grad_norm 3.5124 (3.4359)	
[2022-01-27 07:59:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][640/1251]	eta 0:22:35 lr 0.000010	time 2.7855 (2.2188)	loss 3.6135 (2.9763)	grad_norm 3.3208 (3.4349)	
[2022-01-27 07:59:54 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][650/1251]	eta 0:22:11 lr 0.000010	time 1.8932 (2.2163)	loss 3.1816 (2.9780)	grad_norm 3.3433 (3.4310)	
[2022-01-27 08:00:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][660/1251]	eta 0:21:50 lr 0.000010	time 2.2437 (2.2169)	loss 2.0290 (2.9783)	grad_norm 3.7733 (3.4322)	
[2022-01-27 08:00:39 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][670/1251]	eta 0:21:28 lr 0.000010	time 3.6714 (2.2174)	loss 3.4246 (2.9736)	grad_norm 2.9997 (3.4305)	
[2022-01-27 08:01:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][680/1251]	eta 0:21:06 lr 0.000010	time 2.0309 (2.2173)	loss 2.5811 (2.9741)	grad_norm 3.0202 (3.4277)	
[2022-01-27 08:01:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][690/1251]	eta 0:20:42 lr 0.000010	time 1.7654 (2.2153)	loss 2.8185 (2.9736)	grad_norm 3.2841 (3.4247)	
[2022-01-27 08:01:43 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][700/1251]	eta 0:20:20 lr 0.000010	time 2.1452 (2.2143)	loss 3.2202 (2.9722)	grad_norm 3.0495 (3.4219)	
[2022-01-27 08:02:06 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][710/1251]	eta 0:19:58 lr 0.000010	time 2.8731 (2.2150)	loss 3.1949 (2.9717)	grad_norm 3.3306 (3.4195)	
[2022-01-27 08:02:28 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][720/1251]	eta 0:19:36 lr 0.000010	time 2.5243 (2.2152)	loss 3.1213 (2.9716)	grad_norm 4.6640 (3.4194)	
[2022-01-27 08:02:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][730/1251]	eta 0:19:13 lr 0.000010	time 1.6952 (2.2149)	loss 2.2144 (2.9693)	grad_norm 3.7432 (3.4183)	
[2022-01-27 08:03:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][740/1251]	eta 0:18:51 lr 0.000010	time 2.1675 (2.2136)	loss 2.1021 (2.9705)	grad_norm 3.1596 (3.4178)	
[2022-01-27 08:03:33 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][750/1251]	eta 0:18:28 lr 0.000010	time 1.8336 (2.2125)	loss 2.1344 (2.9677)	grad_norm 3.2677 (3.4169)	
[2022-01-27 08:03:55 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][760/1251]	eta 0:18:06 lr 0.000010	time 2.7926 (2.2128)	loss 2.8694 (2.9678)	grad_norm 3.1293 (3.4162)	
[2022-01-27 08:04:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][770/1251]	eta 0:17:43 lr 0.000010	time 1.9648 (2.2109)	loss 3.0981 (2.9680)	grad_norm 3.2557 (3.4160)	
[2022-01-27 08:04:35 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][780/1251]	eta 0:17:19 lr 0.000010	time 2.2935 (2.2077)	loss 3.3661 (2.9681)	grad_norm 3.4341 (3.4154)	
[2022-01-27 08:04:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][790/1251]	eta 0:16:56 lr 0.000010	time 1.9620 (2.2061)	loss 3.3937 (2.9679)	grad_norm 2.9336 (3.4131)	
[2022-01-27 08:05:19 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][800/1251]	eta 0:16:35 lr 0.000010	time 2.2949 (2.2070)	loss 3.4825 (2.9666)	grad_norm 3.3463 (3.4122)	
[2022-01-27 08:05:41 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][810/1251]	eta 0:16:13 lr 0.000010	time 2.0027 (2.2070)	loss 3.3803 (2.9690)	grad_norm 2.9592 (3.4105)	
[2022-01-27 08:06:04 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][820/1251]	eta 0:15:51 lr 0.000010	time 1.8368 (2.2084)	loss 2.0299 (2.9670)	grad_norm 3.3722 (3.4121)	
[2022-01-27 08:06:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][830/1251]	eta 0:15:31 lr 0.000010	time 2.8460 (2.2116)	loss 3.6560 (2.9693)	grad_norm 2.8844 (3.4134)	
[2022-01-27 08:06:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][840/1251]	eta 0:15:08 lr 0.000010	time 1.8881 (2.2116)	loss 2.7636 (2.9693)	grad_norm 3.0815 (3.4113)	
[2022-01-27 08:07:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][850/1251]	eta 0:14:45 lr 0.000010	time 2.0241 (2.2093)	loss 2.9020 (2.9679)	grad_norm 4.1018 (3.4124)	
[2022-01-27 08:07:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][860/1251]	eta 0:14:22 lr 0.000010	time 2.0150 (2.2062)	loss 3.3282 (2.9683)	grad_norm 3.5498 (3.4133)	
[2022-01-27 08:07:50 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][870/1251]	eta 0:13:59 lr 0.000010	time 1.8004 (2.2028)	loss 2.9859 (2.9667)	grad_norm 3.4502 (3.4123)	
[2022-01-27 08:08:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][880/1251]	eta 0:13:36 lr 0.000010	time 1.9630 (2.2019)	loss 2.3206 (2.9674)	grad_norm 4.2322 (3.4131)	
[2022-01-27 08:08:34 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][890/1251]	eta 0:13:15 lr 0.000010	time 2.9759 (2.2029)	loss 3.0891 (2.9667)	grad_norm 3.2405 (3.4133)	
[2022-01-27 08:08:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][900/1251]	eta 0:12:53 lr 0.000010	time 2.5596 (2.2046)	loss 3.2481 (2.9682)	grad_norm 3.0996 (3.4142)	
[2022-01-27 08:09:21 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][910/1251]	eta 0:12:32 lr 0.000010	time 1.8413 (2.2059)	loss 3.5660 (2.9680)	grad_norm 3.0068 (3.4135)	
[2022-01-27 08:09:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][920/1251]	eta 0:12:10 lr 0.000010	time 1.8136 (2.2070)	loss 2.9678 (2.9677)	grad_norm 2.7395 (3.4118)	
[2022-01-27 08:10:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][930/1251]	eta 0:11:49 lr 0.000010	time 2.3095 (2.2087)	loss 3.4071 (2.9675)	grad_norm 4.0630 (3.4140)	
[2022-01-27 08:10:31 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][940/1251]	eta 0:11:27 lr 0.000010	time 2.2893 (2.2098)	loss 1.6990 (2.9652)	grad_norm 3.5997 (3.4142)	
[2022-01-27 08:10:52 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][950/1251]	eta 0:11:04 lr 0.000010	time 2.1725 (2.2087)	loss 2.7314 (2.9635)	grad_norm 3.1919 (3.4129)	
[2022-01-27 08:11:11 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][960/1251]	eta 0:10:41 lr 0.000010	time 1.9392 (2.2057)	loss 2.8224 (2.9628)	grad_norm 3.2771 (3.4119)	
[2022-01-27 08:11:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][970/1251]	eta 0:10:19 lr 0.000010	time 1.6065 (2.2030)	loss 2.4601 (2.9625)	grad_norm 3.0988 (3.4149)	
[2022-01-27 08:11:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][980/1251]	eta 0:09:56 lr 0.000010	time 1.9247 (2.2012)	loss 2.4273 (2.9626)	grad_norm 2.9868 (3.4141)	
[2022-01-27 08:12:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][990/1251]	eta 0:09:34 lr 0.000010	time 2.6570 (2.2013)	loss 3.2693 (2.9618)	grad_norm 3.5909 (3.4159)	
[2022-01-27 08:12:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1000/1251]	eta 0:09:13 lr 0.000010	time 2.3070 (2.2033)	loss 2.6000 (2.9605)	grad_norm 2.8040 (3.4180)	
[2022-01-27 08:12:57 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1010/1251]	eta 0:08:50 lr 0.000010	time 1.6304 (2.2019)	loss 3.1536 (2.9624)	grad_norm 3.1053 (3.4159)	
[2022-01-27 08:13:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1020/1251]	eta 0:08:28 lr 0.000010	time 2.1690 (2.2025)	loss 3.3261 (2.9642)	grad_norm 2.9467 (3.4156)	
[2022-01-27 08:13:45 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1030/1251]	eta 0:08:07 lr 0.000010	time 3.9991 (2.2057)	loss 3.2963 (2.9650)	grad_norm 3.3647 (3.4160)	
[2022-01-27 08:14:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1040/1251]	eta 0:07:45 lr 0.000010	time 2.5691 (2.2058)	loss 2.7281 (2.9634)	grad_norm 6.5141 (3.4181)	
[2022-01-27 08:14:30 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1050/1251]	eta 0:07:23 lr 0.000010	time 2.1230 (2.2065)	loss 3.4403 (2.9630)	grad_norm 3.7571 (3.4194)	
[2022-01-27 08:14:53 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1060/1251]	eta 0:07:01 lr 0.000010	time 1.8744 (2.2075)	loss 3.4284 (2.9638)	grad_norm 3.3393 (3.4198)	
[2022-01-27 08:15:17 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1070/1251]	eta 0:06:39 lr 0.000010	time 2.7529 (2.2092)	loss 2.8039 (2.9629)	grad_norm 3.2418 (3.4174)	
[2022-01-27 08:15:37 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1080/1251]	eta 0:06:17 lr 0.000010	time 1.9610 (2.2070)	loss 3.2414 (2.9613)	grad_norm 4.2373 (3.4174)	
[2022-01-27 08:15:56 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1090/1251]	eta 0:05:54 lr 0.000010	time 1.8770 (2.2045)	loss 2.3038 (2.9622)	grad_norm 4.0839 (3.4191)	
[2022-01-27 08:16:16 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1100/1251]	eta 0:05:32 lr 0.000010	time 1.8443 (2.2024)	loss 3.4875 (2.9632)	grad_norm 3.4094 (3.4195)	
[2022-01-27 08:16:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1110/1251]	eta 0:05:10 lr 0.000010	time 2.1531 (2.2010)	loss 2.5739 (2.9634)	grad_norm 3.0927 (3.4198)	
[2022-01-27 08:17:00 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1120/1251]	eta 0:04:48 lr 0.000010	time 2.5740 (2.2019)	loss 3.7719 (2.9621)	grad_norm 3.8752 (3.4199)	
[2022-01-27 08:17:22 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1130/1251]	eta 0:04:26 lr 0.000010	time 1.5825 (2.2020)	loss 3.6971 (2.9623)	grad_norm 3.4300 (3.4192)	
[2022-01-27 08:17:44 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1140/1251]	eta 0:04:04 lr 0.000010	time 2.1037 (2.2023)	loss 2.8016 (2.9618)	grad_norm 2.9688 (3.4190)	
[2022-01-27 08:18:07 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1150/1251]	eta 0:03:42 lr 0.000010	time 2.2160 (2.2031)	loss 3.1167 (2.9633)	grad_norm 3.0135 (3.4191)	
[2022-01-27 08:18:29 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1160/1251]	eta 0:03:20 lr 0.000010	time 2.2217 (2.2033)	loss 3.3234 (2.9628)	grad_norm 3.0519 (3.4202)	
[2022-01-27 08:18:51 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1170/1251]	eta 0:02:58 lr 0.000010	time 1.6111 (2.2029)	loss 3.0628 (2.9638)	grad_norm 2.7592 (3.4186)	
[2022-01-27 08:19:13 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1180/1251]	eta 0:02:36 lr 0.000010	time 2.4667 (2.2032)	loss 2.5581 (2.9638)	grad_norm 3.4046 (3.4184)	
[2022-01-27 08:19:36 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1190/1251]	eta 0:02:14 lr 0.000010	time 2.9441 (2.2039)	loss 2.1806 (2.9613)	grad_norm 3.0894 (3.4180)	
[2022-01-27 08:19:59 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1200/1251]	eta 0:01:52 lr 0.000010	time 1.6057 (2.2046)	loss 1.9344 (2.9593)	grad_norm 3.5985 (3.4181)	
[2022-01-27 08:20:20 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1210/1251]	eta 0:01:30 lr 0.000010	time 1.5986 (2.2042)	loss 2.5292 (2.9589)	grad_norm 4.3211 (3.4185)	
[2022-01-27 08:20:40 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1220/1251]	eta 0:01:08 lr 0.000010	time 2.0687 (2.2025)	loss 3.6108 (2.9593)	grad_norm 3.4971 (3.4184)	
[2022-01-27 08:21:01 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1230/1251]	eta 0:00:46 lr 0.000010	time 2.1768 (2.2016)	loss 3.5261 (2.9612)	grad_norm 2.7539 (3.4170)	
[2022-01-27 08:21:23 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1240/1251]	eta 0:00:24 lr 0.000010	time 2.2998 (2.2010)	loss 3.0398 (2.9602)	grad_norm 3.2236 (3.4184)	
[2022-01-27 08:21:38 swin_tiny_patch4_window7_224] (main.py 193): INFO Train: [299/300][1250/1251]	eta 0:00:02 lr 0.000010	time 1.1305 (2.1960)	loss 3.3680 (2.9617)	grad_norm 3.3097 (3.4199)	
[2022-01-27 08:21:39 swin_tiny_patch4_window7_224] (main.py 200): INFO EPOCH 299 training takes 0:45:47
[2022-01-27 08:21:39 swin_tiny_patch4_window7_224] (utils.py 47): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_299 saving......
[2022-01-27 08:21:50 swin_tiny_patch4_window7_224] (utils.py 49): INFO output/swin_tiny_patch4_window7_224/fix_ddp/model_299 saved !!!
[2022-01-27 08:22:07 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [0/49]	Time 16.666 (16.666)	Loss 0.8963 (0.8963)	Acc@1 80.664 (80.664)	Acc@5 93.652 (93.652)	
[2022-01-27 08:22:22 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [10/49]	Time 1.322 (2.870)	Loss 0.8306 (0.8232)	Acc@1 82.422 (81.472)	Acc@5 94.727 (95.206)	
[2022-01-27 08:22:39 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [20/49]	Time 0.996 (2.312)	Loss 0.7791 (0.8186)	Acc@1 79.590 (81.222)	Acc@5 95.703 (95.261)	
[2022-01-27 08:22:59 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [30/49]	Time 0.641 (2.204)	Loss 0.8344 (0.8144)	Acc@1 78.418 (81.080)	Acc@5 95.898 (95.385)	
[2022-01-27 08:23:15 swin_tiny_patch4_window7_224] (main.py 239): INFO Test: [40/49]	Time 2.972 (2.071)	Loss 0.7969 (0.8095)	Acc@1 82.031 (81.117)	Acc@5 95.703 (95.474)	
[2022-01-27 08:23:22 swin_tiny_patch4_window7_224] (main.py 245): INFO  * Acc@1 81.242 Acc@5 95.484
[2022-01-27 08:23:22 swin_tiny_patch4_window7_224] (main.py 132): INFO Accuracy of the network on the 50000 test images: 81.2%
[2022-01-27 08:23:22 swin_tiny_patch4_window7_224] (main.py 134): INFO Max accuracy: 81.24%
[2022-01-27 08:23:22 swin_tiny_patch4_window7_224] (main.py 138): INFO Training time 9 days, 20:54:17