2023-07-10 20:55:15,059 transreid INFO: Saving model in the path :/groups/gaa50073/atom/mmsports-reid2023/logs/market1501/vit_clipreid-ViT-L14
2023-07-10 20:55:15,060 transreid INFO: Namespace(config_file='/groups/gaa50073/atom/mmsports-reid2023/CLIP-ReID/configs/person/vit_clipreid-ViT-L14.yml', local_rank=0, opts=[])
2023-07-10 20:55:15,060 transreid INFO: Loaded configuration file /groups/gaa50073/atom/mmsports-reid2023/CLIP-ReID/configs/person/vit_clipreid-ViT-L14.yml
2023-07-10 20:55:15,060 transreid INFO: 
MODEL:
  PRETRAIN_CHOICE: 'imagenet'
  METRIC_LOSS_TYPE: 'triplet'
  IF_LABELSMOOTH: 'on'
  IF_WITH_CENTER: 'no'
  NAME: 'ViT-L-14'
  STRIDE_SIZE: [14, 14]
  ID_LOSS_WEIGHT : 0.25
  TRIPLET_LOSS_WEIGHT : 1.0
  I2T_LOSS_WEIGHT : 1.0
  # SIE_CAMERA: True
  # SIE_COE : 1.0
  CTX_INIT: "A photo of a X X X X person."
  CTX_DIM: 768
  N_CTX: 4

INPUT:
  SIZE_TRAIN: [256, 128]
  SIZE_TEST: [256, 128]
  PROB: 0.5 # random horizontal flip
  RE_PROB: 0.5 # random erasing
  PADDING: 10
  PIXEL_MEAN: [0.5, 0.5, 0.5]
  PIXEL_STD: [0.5, 0.5, 0.5]
  PAD_NOT_RESIZE: False

DATALOADER:
  SAMPLER: 'softmax_triplet'
  NUM_INSTANCE: 4
  NUM_WORKERS: 8

SOLVER:
  STAGE1:
    IMS_PER_BATCH: 64
    OPTIMIZER_NAME: "Adam"
    BASE_LR: 0.00035
    WARMUP_LR_INIT: 0.00001
    LR_MIN: 1e-6
    WARMUP_METHOD: 'linear'
    WEIGHT_DECAY:  1e-4
    WEIGHT_DECAY_BIAS: 1e-4
    MAX_EPOCHS: 120
    CHECKPOINT_PERIOD: 120
    LOG_PERIOD: 50
    WARMUP_EPOCHS: 5
  
  STAGE2:
    IMS_PER_BATCH: 64
    OPTIMIZER_NAME: "Adam"
    BASE_LR: 0.000005
    WARMUP_METHOD: 'linear'
    WARMUP_ITERS: 10
    WARMUP_FACTOR: 0.1
    WEIGHT_DECAY:  0.0001
    WEIGHT_DECAY_BIAS: 0.0001
    LARGE_FC_LR: False
    MAX_EPOCHS: 60
    CHECKPOINT_PERIOD: 60
    LOG_PERIOD: 50
    EVAL_PERIOD: 60
    BIAS_LR_FACTOR: 2
    
    STEPS: [30, 50]
    GAMMA: 0.1

TEST:
  EVAL: True
  IMS_PER_BATCH: 64
  RE_RANKING: True
  WEIGHT: ''
  NECK_FEAT: 'before'
  FEAT_NORM: 'yes'

DATASETS:
  NAMES: ('market1501')
  ROOT_DIR: ('/groups/gaa50073/atom/mmsports-reid2023/datasets/market1501')
OUTPUT_DIR: '/groups/gaa50073/atom/mmsports-reid2023/logs/market1501/vit_clipreid-ViT-L14'

#   NAMES: ('dukemtmc')
#   ROOT_DIR: ('')
# OUTPUT_DIR: ''

#   NAMES: ('occ_duke')
#   ROOT_DIR: ('')
# OUTPUT_DIR: ''

#   NAMES: ('msmt17')
#   ROOT_DIR: ('')
# OUTPUT_DIR: ''

# CUDA_VISIBLE_DEVICES=3 python train_clipreid.py --config_file configs/person/vit_clipreid.yml

2023-07-10 20:55:15,061 transreid INFO: Running with config:
DATALOADER:
  NUM_INSTANCE: 4
  NUM_WORKERS: 8
  SAMPLER: softmax_triplet
DATASETS:
  NAMES: market1501
  ROOT_DIR: /groups/gaa50073/atom/mmsports-reid2023/datasets/market1501
INPUT:
  PADDING: 10
  PAD_NOT_RESIZE: False
  PIXEL_MEAN: [0.5, 0.5, 0.5]
  PIXEL_STD: [0.5, 0.5, 0.5]
  PROB: 0.5
  RE_PROB: 0.5
  SIZE_TEST: [256, 128]
  SIZE_TRAIN: [256, 128]
MODEL:
  ATT_DROP_RATE: 0.0
  COS_LAYER: False
  CTX_DIM: 768
  CTX_INIT: A photo of a X X X X person.
  DEVICE: cuda
  DEVICE_ID: 0
  DIST_TRAIN: False
  DROP_OUT: 0.0
  DROP_PATH: 0.1
  I2T_LOSS_WEIGHT: 1.0
  ID_LOSS_TYPE: softmax
  ID_LOSS_WEIGHT: 0.25
  IF_LABELSMOOTH: on
  IF_WITH_CENTER: no
  LAST_STRIDE: 1
  METRIC_LOSS_TYPE: triplet
  NAME: ViT-L-14
  NECK: bnneck
  NO_MARGIN: False
  N_CTX: 4
  PRETRAIN_CHOICE: imagenet
  PRETRAIN_PATH: 
  SIE_CAMERA: False
  SIE_COE: 3.0
  SIE_VIEW: False
  STRIDE_SIZE: [14, 14]
  TRANSFORMER_TYPE: None
  TRIPLET_LOSS_WEIGHT: 1.0
OUTPUT_DIR: /groups/gaa50073/atom/mmsports-reid2023/logs/market1501/vit_clipreid-ViT-L14
SOLVER:
  MARGIN: 0.3
  SEED: 1234
  STAGE1:
    BASE_LR: 0.00035
    CHECKPOINT_PERIOD: 120
    COSINE_MARGIN: 0.5
    COSINE_SCALE: 30
    EVAL_PERIOD: 10
    IMS_PER_BATCH: 64
    LOG_PERIOD: 50
    LR_MIN: 1e-06
    MAX_EPOCHS: 120
    MOMENTUM: 0.9
    OPTIMIZER_NAME: Adam
    WARMUP_EPOCHS: 5
    WARMUP_FACTOR: 0.01
    WARMUP_ITERS: 500
    WARMUP_LR_INIT: 1e-05
    WARMUP_METHOD: linear
    WEIGHT_DECAY: 0.0001
    WEIGHT_DECAY_BIAS: 0.0001
  STAGE2:
    BASE_LR: 5e-06
    BIAS_LR_FACTOR: 2
    CENTER_LOSS_WEIGHT: 0.0005
    CENTER_LR: 0.5
    CHECKPOINT_PERIOD: 60
    COSINE_MARGIN: 0.5
    COSINE_SCALE: 30
    EVAL_PERIOD: 60
    GAMMA: 0.1
    IMS_PER_BATCH: 64
    LARGE_FC_LR: False
    LOG_PERIOD: 50
    LR_MIN: 1.6e-05
    MAX_EPOCHS: 60
    MOMENTUM: 0.9
    OPTIMIZER_NAME: Adam
    STEPS: (30, 50)
    WARMUP_EPOCHS: 5
    WARMUP_FACTOR: 0.1
    WARMUP_ITERS: 10
    WARMUP_LR_INIT: 0.01
    WARMUP_METHOD: linear
    WEIGHT_DECAY: 0.0001
    WEIGHT_DECAY_BIAS: 0.0001
TEST:
  DIST_MAT: dist_mat.npy
  EVAL: True
  FEAT_NORM: yes
  IMS_PER_BATCH: 64
  NECK_FEAT: before
  RE_RANKING: True
  WEIGHT: 
2023-07-10 20:55:26,704 transreid.train INFO: start training
2023-07-10 20:55:26,712 transreid.train INFO: model: build_transformer(
  (classifier): Linear(in_features=1024, out_features=751, bias=False)
  (classifier_proj): Linear(in_features=768, out_features=751, bias=False)
  (bottleneck): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (bottleneck_proj): BatchNorm1d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (image_encoder): VisionTransformer(
    (conv1): Conv2d(3, 1024, kernel_size=(14, 14), stride=(14, 14), bias=False)
    (ln_pre): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
    (transformer): Transformer(
      (resblocks): Sequential(
        (0): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (1): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (2): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (3): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (4): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (5): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (6): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (7): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (8): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (9): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (10): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (11): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (12): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (13): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (14): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (15): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (16): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (17): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (18): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (19): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (20): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (21): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (22): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
        (23): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=1024, out_features=1024, bias=True)
          )
          (ln_1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=1024, out_features=4096, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=4096, out_features=1024, bias=True)
          )
          (ln_2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
      )
    )
    (ln_post): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
  )
  (prompt_learner): PromptLearner()
  (text_encoder): TextEncoder(
    (transformer): Transformer(
      (resblocks): Sequential(
        (0): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
          )
          (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=768, out_features=3072, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=3072, out_features=768, bias=True)
          )
          (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        )
        (1): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
          )
          (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=768, out_features=3072, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=3072, out_features=768, bias=True)
          )
          (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        )
        (2): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
          )
          (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=768, out_features=3072, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=3072, out_features=768, bias=True)
          )
          (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        )
        (3): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
          )
          (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=768, out_features=3072, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=3072, out_features=768, bias=True)
          )
          (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        )
        (4): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
          )
          (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=768, out_features=3072, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=3072, out_features=768, bias=True)
          )
          (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        )
        (5): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
          )
          (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=768, out_features=3072, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=3072, out_features=768, bias=True)
          )
          (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        )
        (6): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
          )
          (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=768, out_features=3072, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=3072, out_features=768, bias=True)
          )
          (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        )
        (7): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
          )
          (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=768, out_features=3072, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=3072, out_features=768, bias=True)
          )
          (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        )
        (8): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
          )
          (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=768, out_features=3072, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=3072, out_features=768, bias=True)
          )
          (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        )
        (9): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
          )
          (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=768, out_features=3072, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=3072, out_features=768, bias=True)
          )
          (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        )
        (10): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
          )
          (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=768, out_features=3072, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=3072, out_features=768, bias=True)
          )
          (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        )
        (11): ResidualAttentionBlock(
          (attn): MultiheadAttention(
            (out_proj): _LinearWithBias(in_features=768, out_features=768, bias=True)
          )
          (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          (mlp): Sequential(
            (c_fc): Linear(in_features=768, out_features=3072, bias=True)
            (gelu): QuickGELU()
            (c_proj): Linear(in_features=3072, out_features=768, bias=True)
          )
          (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        )
      )
    )
    (ln_final): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
  )
)
2023-07-10 20:55:57,435 transreid.train INFO: Epoch[1] Iteration[50/203] Loss: 18.839, Base Lr: 7.80e-05
2023-07-10 20:56:01,815 transreid.train INFO: Epoch[1] Iteration[100/203] Loss: 16.740, Base Lr: 7.80e-05
2023-07-10 20:56:06,199 transreid.train INFO: Epoch[1] Iteration[150/203] Loss: 15.454, Base Lr: 7.80e-05
2023-07-10 20:56:10,579 transreid.train INFO: Epoch[1] Iteration[200/203] Loss: 14.518, Base Lr: 7.80e-05
2023-07-10 20:56:15,181 transreid.train INFO: Epoch[2] Iteration[50/203] Loss: 10.843, Base Lr: 1.46e-04
2023-07-10 20:56:19,568 transreid.train INFO: Epoch[2] Iteration[100/203] Loss: 11.259, Base Lr: 1.46e-04
2023-07-10 20:56:23,953 transreid.train INFO: Epoch[2] Iteration[150/203] Loss: 11.188, Base Lr: 1.46e-04
2023-07-10 20:56:28,336 transreid.train INFO: Epoch[2] Iteration[200/203] Loss: 11.045, Base Lr: 1.46e-04
2023-07-10 20:56:32,917 transreid.train INFO: Epoch[3] Iteration[50/203] Loss: 9.796, Base Lr: 2.14e-04
2023-07-10 20:56:37,302 transreid.train INFO: Epoch[3] Iteration[100/203] Loss: 10.279, Base Lr: 2.14e-04
2023-07-10 20:56:41,692 transreid.train INFO: Epoch[3] Iteration[150/203] Loss: 10.196, Base Lr: 2.14e-04
2023-07-10 20:56:46,077 transreid.train INFO: Epoch[3] Iteration[200/203] Loss: 10.081, Base Lr: 2.14e-04
2023-07-10 20:56:50,665 transreid.train INFO: Epoch[4] Iteration[50/203] Loss: 9.214, Base Lr: 2.82e-04
2023-07-10 20:56:55,050 transreid.train INFO: Epoch[4] Iteration[100/203] Loss: 9.277, Base Lr: 2.82e-04
2023-07-10 20:56:59,434 transreid.train INFO: Epoch[4] Iteration[150/203] Loss: 9.317, Base Lr: 2.82e-04
2023-07-10 20:57:03,822 transreid.train INFO: Epoch[4] Iteration[200/203] Loss: 9.254, Base Lr: 2.82e-04
2023-07-10 20:57:08,411 transreid.train INFO: Epoch[5] Iteration[50/203] Loss: 8.736, Base Lr: 3.49e-04
2023-07-10 20:57:12,799 transreid.train INFO: Epoch[5] Iteration[100/203] Loss: 8.878, Base Lr: 3.49e-04
2023-07-10 20:57:17,181 transreid.train INFO: Epoch[5] Iteration[150/203] Loss: 8.809, Base Lr: 3.49e-04
2023-07-10 20:57:21,563 transreid.train INFO: Epoch[5] Iteration[200/203] Loss: 8.668, Base Lr: 3.49e-04
2023-07-10 20:57:26,146 transreid.train INFO: Epoch[6] Iteration[50/203] Loss: 7.252, Base Lr: 3.48e-04
2023-07-10 20:57:30,529 transreid.train INFO: Epoch[6] Iteration[100/203] Loss: 7.219, Base Lr: 3.48e-04
2023-07-10 20:57:34,913 transreid.train INFO: Epoch[6] Iteration[150/203] Loss: 7.162, Base Lr: 3.48e-04
2023-07-10 20:57:39,302 transreid.train INFO: Epoch[6] Iteration[200/203] Loss: 7.049, Base Lr: 3.48e-04
2023-07-10 20:57:43,885 transreid.train INFO: Epoch[7] Iteration[50/203] Loss: 5.873, Base Lr: 3.47e-04
2023-07-10 20:57:48,269 transreid.train INFO: Epoch[7] Iteration[100/203] Loss: 5.862, Base Lr: 3.47e-04
2023-07-10 20:57:52,651 transreid.train INFO: Epoch[7] Iteration[150/203] Loss: 5.806, Base Lr: 3.47e-04
2023-07-10 20:57:57,034 transreid.train INFO: Epoch[7] Iteration[200/203] Loss: 5.731, Base Lr: 3.47e-04
2023-07-10 20:58:01,619 transreid.train INFO: Epoch[8] Iteration[50/203] Loss: 4.970, Base Lr: 3.46e-04
2023-07-10 20:58:06,010 transreid.train INFO: Epoch[8] Iteration[100/203] Loss: 4.902, Base Lr: 3.46e-04
2023-07-10 20:58:10,396 transreid.train INFO: Epoch[8] Iteration[150/203] Loss: 4.889, Base Lr: 3.46e-04
2023-07-10 20:58:14,783 transreid.train INFO: Epoch[8] Iteration[200/203] Loss: 4.861, Base Lr: 3.46e-04
2023-07-10 20:58:19,366 transreid.train INFO: Epoch[9] Iteration[50/203] Loss: 4.103, Base Lr: 3.45e-04
2023-07-10 20:58:23,750 transreid.train INFO: Epoch[9] Iteration[100/203] Loss: 4.062, Base Lr: 3.45e-04
2023-07-10 20:58:28,133 transreid.train INFO: Epoch[9] Iteration[150/203] Loss: 4.095, Base Lr: 3.45e-04
2023-07-10 20:58:32,516 transreid.train INFO: Epoch[9] Iteration[200/203] Loss: 4.131, Base Lr: 3.45e-04
2023-07-10 20:58:37,103 transreid.train INFO: Epoch[10] Iteration[50/203] Loss: 3.648, Base Lr: 3.44e-04
2023-07-10 20:58:41,491 transreid.train INFO: Epoch[10] Iteration[100/203] Loss: 3.674, Base Lr: 3.44e-04
2023-07-10 20:58:45,876 transreid.train INFO: Epoch[10] Iteration[150/203] Loss: 3.723, Base Lr: 3.44e-04
2023-07-10 20:58:50,262 transreid.train INFO: Epoch[10] Iteration[200/203] Loss: 3.744, Base Lr: 3.44e-04
2023-07-10 20:58:54,848 transreid.train INFO: Epoch[11] Iteration[50/203] Loss: 3.076, Base Lr: 3.43e-04
2023-07-10 20:58:59,232 transreid.train INFO: Epoch[11] Iteration[100/203] Loss: 3.208, Base Lr: 3.43e-04
2023-07-10 20:59:03,618 transreid.train INFO: Epoch[11] Iteration[150/203] Loss: 3.245, Base Lr: 3.43e-04
2023-07-10 20:59:08,003 transreid.train INFO: Epoch[11] Iteration[200/203] Loss: 3.338, Base Lr: 3.43e-04
2023-07-10 20:59:12,588 transreid.train INFO: Epoch[12] Iteration[50/203] Loss: 2.977, Base Lr: 3.41e-04
2023-07-10 20:59:16,973 transreid.train INFO: Epoch[12] Iteration[100/203] Loss: 2.986, Base Lr: 3.41e-04
2023-07-10 20:59:21,356 transreid.train INFO: Epoch[12] Iteration[150/203] Loss: 2.996, Base Lr: 3.41e-04
2023-07-10 20:59:25,739 transreid.train INFO: Epoch[12] Iteration[200/203] Loss: 3.051, Base Lr: 3.41e-04
2023-07-10 20:59:30,322 transreid.train INFO: Epoch[13] Iteration[50/203] Loss: 2.845, Base Lr: 3.40e-04
2023-07-10 20:59:34,705 transreid.train INFO: Epoch[13] Iteration[100/203] Loss: 2.941, Base Lr: 3.40e-04
2023-07-10 20:59:39,093 transreid.train INFO: Epoch[13] Iteration[150/203] Loss: 2.922, Base Lr: 3.40e-04
2023-07-10 20:59:43,476 transreid.train INFO: Epoch[13] Iteration[200/203] Loss: 2.943, Base Lr: 3.40e-04
2023-07-10 20:59:48,062 transreid.train INFO: Epoch[14] Iteration[50/203] Loss: 2.420, Base Lr: 3.38e-04
2023-07-10 20:59:52,448 transreid.train INFO: Epoch[14] Iteration[100/203] Loss: 2.532, Base Lr: 3.38e-04
2023-07-10 20:59:56,833 transreid.train INFO: Epoch[14] Iteration[150/203] Loss: 2.577, Base Lr: 3.38e-04
2023-07-10 21:00:01,217 transreid.train INFO: Epoch[14] Iteration[200/203] Loss: 2.632, Base Lr: 3.38e-04
2023-07-10 21:00:05,805 transreid.train INFO: Epoch[15] Iteration[50/203] Loss: 2.378, Base Lr: 3.37e-04
2023-07-10 21:00:10,189 transreid.train INFO: Epoch[15] Iteration[100/203] Loss: 2.343, Base Lr: 3.37e-04
2023-07-10 21:00:14,572 transreid.train INFO: Epoch[15] Iteration[150/203] Loss: 2.387, Base Lr: 3.37e-04
2023-07-10 21:00:18,957 transreid.train INFO: Epoch[15] Iteration[200/203] Loss: 2.419, Base Lr: 3.37e-04
2023-07-10 21:00:23,544 transreid.train INFO: Epoch[16] Iteration[50/203] Loss: 2.087, Base Lr: 3.35e-04
2023-07-10 21:00:27,926 transreid.train INFO: Epoch[16] Iteration[100/203] Loss: 2.136, Base Lr: 3.35e-04
2023-07-10 21:00:32,309 transreid.train INFO: Epoch[16] Iteration[150/203] Loss: 2.176, Base Lr: 3.35e-04
2023-07-10 21:00:36,691 transreid.train INFO: Epoch[16] Iteration[200/203] Loss: 2.218, Base Lr: 3.35e-04
2023-07-10 21:00:41,276 transreid.train INFO: Epoch[17] Iteration[50/203] Loss: 2.062, Base Lr: 3.33e-04
2023-07-10 21:00:45,658 transreid.train INFO: Epoch[17] Iteration[100/203] Loss: 2.066, Base Lr: 3.33e-04
2023-07-10 21:00:50,041 transreid.train INFO: Epoch[17] Iteration[150/203] Loss: 2.100, Base Lr: 3.33e-04
2023-07-10 21:00:54,425 transreid.train INFO: Epoch[17] Iteration[200/203] Loss: 2.139, Base Lr: 3.33e-04
2023-07-10 21:00:59,008 transreid.train INFO: Epoch[18] Iteration[50/203] Loss: 2.058, Base Lr: 3.31e-04
2023-07-10 21:01:03,391 transreid.train INFO: Epoch[18] Iteration[100/203] Loss: 2.042, Base Lr: 3.31e-04
2023-07-10 21:01:07,781 transreid.train INFO: Epoch[18] Iteration[150/203] Loss: 2.051, Base Lr: 3.31e-04
2023-07-10 21:01:12,169 transreid.train INFO: Epoch[18] Iteration[200/203] Loss: 2.100, Base Lr: 3.31e-04
2023-07-10 21:01:16,756 transreid.train INFO: Epoch[19] Iteration[50/203] Loss: 1.972, Base Lr: 3.29e-04
2023-07-10 21:01:21,143 transreid.train INFO: Epoch[19] Iteration[100/203] Loss: 1.909, Base Lr: 3.29e-04
2023-07-10 21:01:25,530 transreid.train INFO: Epoch[19] Iteration[150/203] Loss: 1.946, Base Lr: 3.29e-04
2023-07-10 21:01:29,912 transreid.train INFO: Epoch[19] Iteration[200/203] Loss: 2.006, Base Lr: 3.29e-04
2023-07-10 21:01:34,455 transreid.train INFO: Epoch[20] Iteration[50/203] Loss: 1.710, Base Lr: 3.27e-04
2023-07-10 21:01:38,827 transreid.train INFO: Epoch[20] Iteration[100/203] Loss: 1.814, Base Lr: 3.27e-04
2023-07-10 21:01:43,227 transreid.train INFO: Epoch[20] Iteration[150/203] Loss: 1.812, Base Lr: 3.27e-04
2023-07-10 21:01:47,631 transreid.train INFO: Epoch[20] Iteration[200/203] Loss: 1.853, Base Lr: 3.27e-04
2023-07-10 21:01:52,243 transreid.train INFO: Epoch[21] Iteration[50/203] Loss: 1.712, Base Lr: 3.24e-04
2023-07-10 21:01:56,652 transreid.train INFO: Epoch[21] Iteration[100/203] Loss: 1.721, Base Lr: 3.24e-04
2023-07-10 21:02:01,068 transreid.train INFO: Epoch[21] Iteration[150/203] Loss: 1.763, Base Lr: 3.24e-04
2023-07-10 21:02:05,484 transreid.train INFO: Epoch[21] Iteration[200/203] Loss: 1.814, Base Lr: 3.24e-04
2023-07-10 21:02:10,104 transreid.train INFO: Epoch[22] Iteration[50/203] Loss: 1.559, Base Lr: 3.22e-04
2023-07-10 21:02:14,518 transreid.train INFO: Epoch[22] Iteration[100/203] Loss: 1.623, Base Lr: 3.22e-04
2023-07-10 21:02:18,889 transreid.train INFO: Epoch[22] Iteration[150/203] Loss: 1.661, Base Lr: 3.22e-04
2023-07-10 21:02:23,271 transreid.train INFO: Epoch[22] Iteration[200/203] Loss: 1.689, Base Lr: 3.22e-04
2023-07-10 21:02:27,855 transreid.train INFO: Epoch[23] Iteration[50/203] Loss: 1.492, Base Lr: 3.19e-04
2023-07-10 21:02:32,244 transreid.train INFO: Epoch[23] Iteration[100/203] Loss: 1.583, Base Lr: 3.19e-04
2023-07-10 21:02:36,631 transreid.train INFO: Epoch[23] Iteration[150/203] Loss: 1.626, Base Lr: 3.19e-04
2023-07-10 21:02:41,017 transreid.train INFO: Epoch[23] Iteration[200/203] Loss: 1.646, Base Lr: 3.19e-04
2023-07-10 21:02:45,604 transreid.train INFO: Epoch[24] Iteration[50/203] Loss: 1.409, Base Lr: 3.17e-04
2023-07-10 21:02:49,999 transreid.train INFO: Epoch[24] Iteration[100/203] Loss: 1.480, Base Lr: 3.17e-04
2023-07-10 21:02:54,391 transreid.train INFO: Epoch[24] Iteration[150/203] Loss: 1.510, Base Lr: 3.17e-04
2023-07-10 21:02:58,776 transreid.train INFO: Epoch[24] Iteration[200/203] Loss: 1.539, Base Lr: 3.17e-04
2023-07-10 21:03:03,370 transreid.train INFO: Epoch[25] Iteration[50/203] Loss: 1.387, Base Lr: 3.14e-04
2023-07-10 21:03:07,712 transreid.train INFO: Epoch[25] Iteration[100/203] Loss: 1.356, Base Lr: 3.14e-04
2023-07-10 21:03:12,057 transreid.train INFO: Epoch[25] Iteration[150/203] Loss: 1.388, Base Lr: 3.14e-04
2023-07-10 21:03:16,403 transreid.train INFO: Epoch[25] Iteration[200/203] Loss: 1.443, Base Lr: 3.14e-04
2023-07-10 21:03:20,948 transreid.train INFO: Epoch[26] Iteration[50/203] Loss: 1.399, Base Lr: 3.11e-04
2023-07-10 21:03:25,293 transreid.train INFO: Epoch[26] Iteration[100/203] Loss: 1.354, Base Lr: 3.11e-04
2023-07-10 21:03:29,636 transreid.train INFO: Epoch[26] Iteration[150/203] Loss: 1.420, Base Lr: 3.11e-04
2023-07-10 21:03:33,981 transreid.train INFO: Epoch[26] Iteration[200/203] Loss: 1.460, Base Lr: 3.11e-04
2023-07-10 21:03:38,520 transreid.train INFO: Epoch[27] Iteration[50/203] Loss: 1.197, Base Lr: 3.08e-04
2023-07-10 21:03:42,868 transreid.train INFO: Epoch[27] Iteration[100/203] Loss: 1.207, Base Lr: 3.08e-04
2023-07-10 21:03:47,259 transreid.train INFO: Epoch[27] Iteration[150/203] Loss: 1.258, Base Lr: 3.08e-04
2023-07-10 21:03:51,644 transreid.train INFO: Epoch[27] Iteration[200/203] Loss: 1.310, Base Lr: 3.08e-04
2023-07-10 21:03:56,213 transreid.train INFO: Epoch[28] Iteration[50/203] Loss: 1.195, Base Lr: 3.05e-04
2023-07-10 21:04:00,568 transreid.train INFO: Epoch[28] Iteration[100/203] Loss: 1.243, Base Lr: 3.05e-04
2023-07-10 21:04:04,926 transreid.train INFO: Epoch[28] Iteration[150/203] Loss: 1.232, Base Lr: 3.05e-04
2023-07-10 21:04:09,281 transreid.train INFO: Epoch[28] Iteration[200/203] Loss: 1.265, Base Lr: 3.05e-04
2023-07-10 21:04:13,820 transreid.train INFO: Epoch[29] Iteration[50/203] Loss: 1.112, Base Lr: 3.02e-04
2023-07-10 21:04:18,169 transreid.train INFO: Epoch[29] Iteration[100/203] Loss: 1.116, Base Lr: 3.02e-04
2023-07-10 21:04:22,516 transreid.train INFO: Epoch[29] Iteration[150/203] Loss: 1.162, Base Lr: 3.02e-04
2023-07-10 21:04:26,863 transreid.train INFO: Epoch[29] Iteration[200/203] Loss: 1.204, Base Lr: 3.02e-04
2023-07-10 21:04:31,412 transreid.train INFO: Epoch[30] Iteration[50/203] Loss: 1.184, Base Lr: 2.99e-04
2023-07-10 21:04:35,762 transreid.train INFO: Epoch[30] Iteration[100/203] Loss: 1.187, Base Lr: 2.99e-04
2023-07-10 21:04:40,111 transreid.train INFO: Epoch[30] Iteration[150/203] Loss: 1.223, Base Lr: 2.99e-04
2023-07-10 21:04:44,455 transreid.train INFO: Epoch[30] Iteration[200/203] Loss: 1.262, Base Lr: 2.99e-04
2023-07-10 21:04:49,006 transreid.train INFO: Epoch[31] Iteration[50/203] Loss: 1.122, Base Lr: 2.96e-04
2023-07-10 21:04:53,359 transreid.train INFO: Epoch[31] Iteration[100/203] Loss: 1.127, Base Lr: 2.96e-04
2023-07-10 21:04:57,713 transreid.train INFO: Epoch[31] Iteration[150/203] Loss: 1.174, Base Lr: 2.96e-04
2023-07-10 21:05:02,066 transreid.train INFO: Epoch[31] Iteration[200/203] Loss: 1.205, Base Lr: 2.96e-04
2023-07-10 21:05:06,616 transreid.train INFO: Epoch[32] Iteration[50/203] Loss: 1.104, Base Lr: 2.92e-04
2023-07-10 21:05:10,967 transreid.train INFO: Epoch[32] Iteration[100/203] Loss: 1.124, Base Lr: 2.92e-04
2023-07-10 21:05:15,313 transreid.train INFO: Epoch[32] Iteration[150/203] Loss: 1.135, Base Lr: 2.92e-04
2023-07-10 21:05:19,669 transreid.train INFO: Epoch[32] Iteration[200/203] Loss: 1.180, Base Lr: 2.92e-04
2023-07-10 21:05:24,215 transreid.train INFO: Epoch[33] Iteration[50/203] Loss: 1.088, Base Lr: 2.89e-04
2023-07-10 21:05:28,557 transreid.train INFO: Epoch[33] Iteration[100/203] Loss: 1.087, Base Lr: 2.89e-04
2023-07-10 21:05:32,913 transreid.train INFO: Epoch[33] Iteration[150/203] Loss: 1.085, Base Lr: 2.89e-04
2023-07-10 21:05:37,267 transreid.train INFO: Epoch[33] Iteration[200/203] Loss: 1.122, Base Lr: 2.89e-04
2023-07-10 21:05:41,818 transreid.train INFO: Epoch[34] Iteration[50/203] Loss: 0.960, Base Lr: 2.85e-04
2023-07-10 21:05:46,165 transreid.train INFO: Epoch[34] Iteration[100/203] Loss: 0.939, Base Lr: 2.85e-04
2023-07-10 21:05:50,518 transreid.train INFO: Epoch[34] Iteration[150/203] Loss: 0.963, Base Lr: 2.85e-04
2023-07-10 21:05:54,879 transreid.train INFO: Epoch[34] Iteration[200/203] Loss: 0.998, Base Lr: 2.85e-04
2023-07-10 21:05:59,430 transreid.train INFO: Epoch[35] Iteration[50/203] Loss: 0.908, Base Lr: 2.82e-04
2023-07-10 21:06:03,784 transreid.train INFO: Epoch[35] Iteration[100/203] Loss: 0.897, Base Lr: 2.82e-04
2023-07-10 21:06:08,133 transreid.train INFO: Epoch[35] Iteration[150/203] Loss: 0.933, Base Lr: 2.82e-04
2023-07-10 21:06:12,481 transreid.train INFO: Epoch[35] Iteration[200/203] Loss: 0.993, Base Lr: 2.82e-04
2023-07-10 21:06:17,030 transreid.train INFO: Epoch[36] Iteration[50/203] Loss: 0.937, Base Lr: 2.78e-04
2023-07-10 21:06:21,397 transreid.train INFO: Epoch[36] Iteration[100/203] Loss: 0.945, Base Lr: 2.78e-04
2023-07-10 21:06:25,749 transreid.train INFO: Epoch[36] Iteration[150/203] Loss: 0.951, Base Lr: 2.78e-04
2023-07-10 21:06:30,096 transreid.train INFO: Epoch[36] Iteration[200/203] Loss: 0.974, Base Lr: 2.78e-04
2023-07-10 21:06:34,647 transreid.train INFO: Epoch[37] Iteration[50/203] Loss: 0.857, Base Lr: 2.74e-04
2023-07-10 21:06:38,993 transreid.train INFO: Epoch[37] Iteration[100/203] Loss: 0.915, Base Lr: 2.74e-04
2023-07-10 21:06:43,344 transreid.train INFO: Epoch[37] Iteration[150/203] Loss: 0.945, Base Lr: 2.74e-04
2023-07-10 21:06:47,697 transreid.train INFO: Epoch[37] Iteration[200/203] Loss: 0.960, Base Lr: 2.74e-04
2023-07-10 21:06:52,268 transreid.train INFO: Epoch[38] Iteration[50/203] Loss: 0.895, Base Lr: 2.71e-04
2023-07-10 21:06:56,622 transreid.train INFO: Epoch[38] Iteration[100/203] Loss: 0.898, Base Lr: 2.71e-04
2023-07-10 21:07:00,970 transreid.train INFO: Epoch[38] Iteration[150/203] Loss: 0.917, Base Lr: 2.71e-04
2023-07-10 21:07:05,323 transreid.train INFO: Epoch[38] Iteration[200/203] Loss: 0.951, Base Lr: 2.71e-04
2023-07-10 21:07:09,884 transreid.train INFO: Epoch[39] Iteration[50/203] Loss: 0.827, Base Lr: 2.67e-04
2023-07-10 21:07:14,237 transreid.train INFO: Epoch[39] Iteration[100/203] Loss: 0.863, Base Lr: 2.67e-04
2023-07-10 21:07:18,590 transreid.train INFO: Epoch[39] Iteration[150/203] Loss: 0.869, Base Lr: 2.67e-04
2023-07-10 21:07:22,940 transreid.train INFO: Epoch[39] Iteration[200/203] Loss: 0.902, Base Lr: 2.67e-04
2023-07-10 21:07:27,491 transreid.train INFO: Epoch[40] Iteration[50/203] Loss: 0.723, Base Lr: 2.63e-04
2023-07-10 21:07:31,861 transreid.train INFO: Epoch[40] Iteration[100/203] Loss: 0.747, Base Lr: 2.63e-04
2023-07-10 21:07:36,209 transreid.train INFO: Epoch[40] Iteration[150/203] Loss: 0.844, Base Lr: 2.63e-04
2023-07-10 21:07:40,557 transreid.train INFO: Epoch[40] Iteration[200/203] Loss: 0.881, Base Lr: 2.63e-04
2023-07-10 21:07:45,106 transreid.train INFO: Epoch[41] Iteration[50/203] Loss: 0.811, Base Lr: 2.59e-04
2023-07-10 21:07:49,459 transreid.train INFO: Epoch[41] Iteration[100/203] Loss: 0.844, Base Lr: 2.59e-04
2023-07-10 21:07:53,812 transreid.train INFO: Epoch[41] Iteration[150/203] Loss: 0.875, Base Lr: 2.59e-04
2023-07-10 21:07:58,162 transreid.train INFO: Epoch[41] Iteration[200/203] Loss: 0.899, Base Lr: 2.59e-04
2023-07-10 21:08:02,715 transreid.train INFO: Epoch[42] Iteration[50/203] Loss: 0.714, Base Lr: 2.55e-04
2023-07-10 21:08:07,064 transreid.train INFO: Epoch[42] Iteration[100/203] Loss: 0.756, Base Lr: 2.55e-04
2023-07-10 21:08:11,416 transreid.train INFO: Epoch[42] Iteration[150/203] Loss: 0.770, Base Lr: 2.55e-04
2023-07-10 21:08:15,773 transreid.train INFO: Epoch[42] Iteration[200/203] Loss: 0.796, Base Lr: 2.55e-04
2023-07-10 21:08:20,349 transreid.train INFO: Epoch[43] Iteration[50/203] Loss: 0.706, Base Lr: 2.51e-04
2023-07-10 21:08:24,699 transreid.train INFO: Epoch[43] Iteration[100/203] Loss: 0.697, Base Lr: 2.51e-04
2023-07-10 21:08:29,058 transreid.train INFO: Epoch[43] Iteration[150/203] Loss: 0.682, Base Lr: 2.51e-04
2023-07-10 21:08:33,409 transreid.train INFO: Epoch[43] Iteration[200/203] Loss: 0.698, Base Lr: 2.51e-04
2023-07-10 21:08:37,957 transreid.train INFO: Epoch[44] Iteration[50/203] Loss: 0.673, Base Lr: 2.46e-04
2023-07-10 21:08:42,303 transreid.train INFO: Epoch[44] Iteration[100/203] Loss: 0.668, Base Lr: 2.46e-04
2023-07-10 21:08:46,657 transreid.train INFO: Epoch[44] Iteration[150/203] Loss: 0.681, Base Lr: 2.46e-04
2023-07-10 21:08:51,012 transreid.train INFO: Epoch[44] Iteration[200/203] Loss: 0.715, Base Lr: 2.46e-04
2023-07-10 21:08:55,562 transreid.train INFO: Epoch[45] Iteration[50/203] Loss: 0.662, Base Lr: 2.42e-04
2023-07-10 21:08:59,915 transreid.train INFO: Epoch[45] Iteration[100/203] Loss: 0.653, Base Lr: 2.42e-04
2023-07-10 21:09:04,273 transreid.train INFO: Epoch[45] Iteration[150/203] Loss: 0.664, Base Lr: 2.42e-04
2023-07-10 21:09:08,623 transreid.train INFO: Epoch[45] Iteration[200/203] Loss: 0.692, Base Lr: 2.42e-04
2023-07-10 21:09:13,172 transreid.train INFO: Epoch[46] Iteration[50/203] Loss: 0.688, Base Lr: 2.38e-04
2023-07-10 21:09:17,542 transreid.train INFO: Epoch[46] Iteration[100/203] Loss: 0.657, Base Lr: 2.38e-04
2023-07-10 21:09:21,914 transreid.train INFO: Epoch[46] Iteration[150/203] Loss: 0.657, Base Lr: 2.38e-04
2023-07-10 21:09:26,267 transreid.train INFO: Epoch[46] Iteration[200/203] Loss: 0.670, Base Lr: 2.38e-04
2023-07-10 21:09:30,817 transreid.train INFO: Epoch[47] Iteration[50/203] Loss: 0.571, Base Lr: 2.34e-04
2023-07-10 21:09:35,167 transreid.train INFO: Epoch[47] Iteration[100/203] Loss: 0.583, Base Lr: 2.34e-04
2023-07-10 21:09:39,516 transreid.train INFO: Epoch[47] Iteration[150/203] Loss: 0.609, Base Lr: 2.34e-04
2023-07-10 21:09:43,867 transreid.train INFO: Epoch[47] Iteration[200/203] Loss: 0.643, Base Lr: 2.34e-04
2023-07-10 21:09:48,416 transreid.train INFO: Epoch[48] Iteration[50/203] Loss: 0.589, Base Lr: 2.29e-04
2023-07-10 21:09:52,772 transreid.train INFO: Epoch[48] Iteration[100/203] Loss: 0.586, Base Lr: 2.29e-04
2023-07-10 21:09:57,119 transreid.train INFO: Epoch[48] Iteration[150/203] Loss: 0.600, Base Lr: 2.29e-04
2023-07-10 21:10:01,472 transreid.train INFO: Epoch[48] Iteration[200/203] Loss: 0.629, Base Lr: 2.29e-04
2023-07-10 21:10:06,026 transreid.train INFO: Epoch[49] Iteration[50/203] Loss: 0.594, Base Lr: 2.25e-04
2023-07-10 21:10:10,378 transreid.train INFO: Epoch[49] Iteration[100/203] Loss: 0.627, Base Lr: 2.25e-04
2023-07-10 21:10:14,727 transreid.train INFO: Epoch[49] Iteration[150/203] Loss: 0.662, Base Lr: 2.25e-04
2023-07-10 21:10:19,078 transreid.train INFO: Epoch[49] Iteration[200/203] Loss: 0.676, Base Lr: 2.25e-04
2023-07-10 21:10:23,628 transreid.train INFO: Epoch[50] Iteration[50/203] Loss: 0.633, Base Lr: 2.21e-04
2023-07-10 21:10:27,986 transreid.train INFO: Epoch[50] Iteration[100/203] Loss: 0.625, Base Lr: 2.21e-04
2023-07-10 21:10:32,355 transreid.train INFO: Epoch[50] Iteration[150/203] Loss: 0.620, Base Lr: 2.21e-04
2023-07-10 21:10:36,735 transreid.train INFO: Epoch[50] Iteration[200/203] Loss: 0.621, Base Lr: 2.21e-04
2023-07-10 21:10:41,289 transreid.train INFO: Epoch[51] Iteration[50/203] Loss: 0.561, Base Lr: 2.16e-04
2023-07-10 21:10:45,635 transreid.train INFO: Epoch[51] Iteration[100/203] Loss: 0.561, Base Lr: 2.16e-04
2023-07-10 21:10:49,983 transreid.train INFO: Epoch[51] Iteration[150/203] Loss: 0.574, Base Lr: 2.16e-04
2023-07-10 21:10:54,333 transreid.train INFO: Epoch[51] Iteration[200/203] Loss: 0.589, Base Lr: 2.16e-04
2023-07-10 21:10:58,876 transreid.train INFO: Epoch[52] Iteration[50/203] Loss: 0.547, Base Lr: 2.12e-04
2023-07-10 21:11:03,232 transreid.train INFO: Epoch[52] Iteration[100/203] Loss: 0.536, Base Lr: 2.12e-04
2023-07-10 21:11:07,582 transreid.train INFO: Epoch[52] Iteration[150/203] Loss: 0.548, Base Lr: 2.12e-04
2023-07-10 21:11:11,929 transreid.train INFO: Epoch[52] Iteration[200/203] Loss: 0.553, Base Lr: 2.12e-04
2023-07-10 21:11:16,477 transreid.train INFO: Epoch[53] Iteration[50/203] Loss: 0.495, Base Lr: 2.07e-04
2023-07-10 21:11:20,828 transreid.train INFO: Epoch[53] Iteration[100/203] Loss: 0.517, Base Lr: 2.07e-04
2023-07-10 21:11:25,181 transreid.train INFO: Epoch[53] Iteration[150/203] Loss: 0.517, Base Lr: 2.07e-04
2023-07-10 21:11:29,526 transreid.train INFO: Epoch[53] Iteration[200/203] Loss: 0.527, Base Lr: 2.07e-04
2023-07-10 21:11:34,071 transreid.train INFO: Epoch[54] Iteration[50/203] Loss: 0.473, Base Lr: 2.03e-04
2023-07-10 21:11:38,430 transreid.train INFO: Epoch[54] Iteration[100/203] Loss: 0.468, Base Lr: 2.03e-04
2023-07-10 21:11:42,781 transreid.train INFO: Epoch[54] Iteration[150/203] Loss: 0.487, Base Lr: 2.03e-04
2023-07-10 21:11:47,137 transreid.train INFO: Epoch[54] Iteration[200/203] Loss: 0.509, Base Lr: 2.03e-04
2023-07-10 21:11:51,689 transreid.train INFO: Epoch[55] Iteration[50/203] Loss: 0.491, Base Lr: 1.98e-04
2023-07-10 21:11:56,050 transreid.train INFO: Epoch[55] Iteration[100/203] Loss: 0.485, Base Lr: 1.98e-04
2023-07-10 21:12:00,407 transreid.train INFO: Epoch[55] Iteration[150/203] Loss: 0.484, Base Lr: 1.98e-04
2023-07-10 21:12:04,770 transreid.train INFO: Epoch[55] Iteration[200/203] Loss: 0.501, Base Lr: 1.98e-04
2023-07-10 21:12:09,326 transreid.train INFO: Epoch[56] Iteration[50/203] Loss: 0.472, Base Lr: 1.94e-04
2023-07-10 21:12:13,686 transreid.train INFO: Epoch[56] Iteration[100/203] Loss: 0.464, Base Lr: 1.94e-04
2023-07-10 21:12:18,042 transreid.train INFO: Epoch[56] Iteration[150/203] Loss: 0.471, Base Lr: 1.94e-04
2023-07-10 21:12:22,397 transreid.train INFO: Epoch[56] Iteration[200/203] Loss: 0.481, Base Lr: 1.94e-04
2023-07-10 21:12:26,960 transreid.train INFO: Epoch[57] Iteration[50/203] Loss: 0.473, Base Lr: 1.89e-04
2023-07-10 21:12:31,310 transreid.train INFO: Epoch[57] Iteration[100/203] Loss: 0.478, Base Lr: 1.89e-04
2023-07-10 21:12:35,682 transreid.train INFO: Epoch[57] Iteration[150/203] Loss: 0.488, Base Lr: 1.89e-04
2023-07-10 21:12:40,033 transreid.train INFO: Epoch[57] Iteration[200/203] Loss: 0.493, Base Lr: 1.89e-04
2023-07-10 21:12:44,576 transreid.train INFO: Epoch[58] Iteration[50/203] Loss: 0.405, Base Lr: 1.85e-04
2023-07-10 21:12:48,924 transreid.train INFO: Epoch[58] Iteration[100/203] Loss: 0.430, Base Lr: 1.85e-04
2023-07-10 21:12:53,271 transreid.train INFO: Epoch[58] Iteration[150/203] Loss: 0.448, Base Lr: 1.85e-04
2023-07-10 21:12:57,627 transreid.train INFO: Epoch[58] Iteration[200/203] Loss: 0.467, Base Lr: 1.85e-04
2023-07-10 21:13:02,193 transreid.train INFO: Epoch[59] Iteration[50/203] Loss: 0.462, Base Lr: 1.80e-04
2023-07-10 21:13:06,545 transreid.train INFO: Epoch[59] Iteration[100/203] Loss: 0.461, Base Lr: 1.80e-04
2023-07-10 21:13:10,895 transreid.train INFO: Epoch[59] Iteration[150/203] Loss: 0.469, Base Lr: 1.80e-04
2023-07-10 21:13:15,242 transreid.train INFO: Epoch[59] Iteration[200/203] Loss: 0.476, Base Lr: 1.80e-04
2023-07-10 21:13:19,788 transreid.train INFO: Epoch[60] Iteration[50/203] Loss: 0.464, Base Lr: 1.76e-04
2023-07-10 21:13:24,137 transreid.train INFO: Epoch[60] Iteration[100/203] Loss: 0.467, Base Lr: 1.76e-04
2023-07-10 21:13:28,489 transreid.train INFO: Epoch[60] Iteration[150/203] Loss: 0.461, Base Lr: 1.76e-04
2023-07-10 21:13:32,841 transreid.train INFO: Epoch[60] Iteration[200/203] Loss: 0.468, Base Lr: 1.76e-04
2023-07-10 21:13:37,388 transreid.train INFO: Epoch[61] Iteration[50/203] Loss: 0.400, Base Lr: 1.71e-04
2023-07-10 21:13:41,751 transreid.train INFO: Epoch[61] Iteration[100/203] Loss: 0.405, Base Lr: 1.71e-04
2023-07-10 21:13:46,106 transreid.train INFO: Epoch[61] Iteration[150/203] Loss: 0.412, Base Lr: 1.71e-04
2023-07-10 21:13:50,479 transreid.train INFO: Epoch[61] Iteration[200/203] Loss: 0.413, Base Lr: 1.71e-04
2023-07-10 21:13:55,060 transreid.train INFO: Epoch[62] Iteration[50/203] Loss: 0.379, Base Lr: 1.66e-04
2023-07-10 21:13:59,439 transreid.train INFO: Epoch[62] Iteration[100/203] Loss: 0.386, Base Lr: 1.66e-04
2023-07-10 21:14:03,788 transreid.train INFO: Epoch[62] Iteration[150/203] Loss: 0.392, Base Lr: 1.66e-04
2023-07-10 21:14:08,136 transreid.train INFO: Epoch[62] Iteration[200/203] Loss: 0.412, Base Lr: 1.66e-04
2023-07-10 21:14:12,679 transreid.train INFO: Epoch[63] Iteration[50/203] Loss: 0.399, Base Lr: 1.62e-04
2023-07-10 21:14:17,024 transreid.train INFO: Epoch[63] Iteration[100/203] Loss: 0.398, Base Lr: 1.62e-04
2023-07-10 21:14:21,369 transreid.train INFO: Epoch[63] Iteration[150/203] Loss: 0.411, Base Lr: 1.62e-04
2023-07-10 21:14:25,712 transreid.train INFO: Epoch[63] Iteration[200/203] Loss: 0.420, Base Lr: 1.62e-04
2023-07-10 21:14:30,257 transreid.train INFO: Epoch[64] Iteration[50/203] Loss: 0.368, Base Lr: 1.57e-04
2023-07-10 21:14:34,604 transreid.train INFO: Epoch[64] Iteration[100/203] Loss: 0.394, Base Lr: 1.57e-04
2023-07-10 21:14:38,948 transreid.train INFO: Epoch[64] Iteration[150/203] Loss: 0.410, Base Lr: 1.57e-04
2023-07-10 21:14:43,296 transreid.train INFO: Epoch[64] Iteration[200/203] Loss: 0.418, Base Lr: 1.57e-04
2023-07-10 21:14:47,834 transreid.train INFO: Epoch[65] Iteration[50/203] Loss: 0.381, Base Lr: 1.53e-04
2023-07-10 21:14:52,173 transreid.train INFO: Epoch[65] Iteration[100/203] Loss: 0.380, Base Lr: 1.53e-04
2023-07-10 21:14:56,521 transreid.train INFO: Epoch[65] Iteration[150/203] Loss: 0.381, Base Lr: 1.53e-04
2023-07-10 21:15:00,872 transreid.train INFO: Epoch[65] Iteration[200/203] Loss: 0.389, Base Lr: 1.53e-04
2023-07-10 21:15:05,417 transreid.train INFO: Epoch[66] Iteration[50/203] Loss: 0.401, Base Lr: 1.48e-04
2023-07-10 21:15:09,759 transreid.train INFO: Epoch[66] Iteration[100/203] Loss: 0.408, Base Lr: 1.48e-04
2023-07-10 21:15:14,101 transreid.train INFO: Epoch[66] Iteration[150/203] Loss: 0.409, Base Lr: 1.48e-04
2023-07-10 21:15:18,445 transreid.train INFO: Epoch[66] Iteration[200/203] Loss: 0.414, Base Lr: 1.48e-04
2023-07-10 21:15:22,988 transreid.train INFO: Epoch[67] Iteration[50/203] Loss: 0.356, Base Lr: 1.44e-04
2023-07-10 21:15:27,336 transreid.train INFO: Epoch[67] Iteration[100/203] Loss: 0.381, Base Lr: 1.44e-04
2023-07-10 21:15:31,696 transreid.train INFO: Epoch[67] Iteration[150/203] Loss: 0.380, Base Lr: 1.44e-04
2023-07-10 21:15:36,036 transreid.train INFO: Epoch[67] Iteration[200/203] Loss: 0.387, Base Lr: 1.44e-04
2023-07-10 21:15:40,580 transreid.train INFO: Epoch[68] Iteration[50/203] Loss: 0.364, Base Lr: 1.39e-04
2023-07-10 21:15:44,939 transreid.train INFO: Epoch[68] Iteration[100/203] Loss: 0.377, Base Lr: 1.39e-04
2023-07-10 21:15:49,304 transreid.train INFO: Epoch[68] Iteration[150/203] Loss: 0.384, Base Lr: 1.39e-04
2023-07-10 21:15:53,667 transreid.train INFO: Epoch[68] Iteration[200/203] Loss: 0.392, Base Lr: 1.39e-04
2023-07-10 21:15:58,210 transreid.train INFO: Epoch[69] Iteration[50/203] Loss: 0.362, Base Lr: 1.35e-04
2023-07-10 21:16:02,569 transreid.train INFO: Epoch[69] Iteration[100/203] Loss: 0.367, Base Lr: 1.35e-04
2023-07-10 21:16:06,914 transreid.train INFO: Epoch[69] Iteration[150/203] Loss: 0.363, Base Lr: 1.35e-04
2023-07-10 21:16:11,260 transreid.train INFO: Epoch[69] Iteration[200/203] Loss: 0.368, Base Lr: 1.35e-04
2023-07-10 21:16:15,802 transreid.train INFO: Epoch[70] Iteration[50/203] Loss: 0.329, Base Lr: 1.30e-04
2023-07-10 21:16:20,145 transreid.train INFO: Epoch[70] Iteration[100/203] Loss: 0.338, Base Lr: 1.30e-04
2023-07-10 21:16:24,492 transreid.train INFO: Epoch[70] Iteration[150/203] Loss: 0.345, Base Lr: 1.30e-04
2023-07-10 21:16:28,841 transreid.train INFO: Epoch[70] Iteration[200/203] Loss: 0.351, Base Lr: 1.30e-04
2023-07-10 21:16:33,389 transreid.train INFO: Epoch[71] Iteration[50/203] Loss: 0.354, Base Lr: 1.26e-04
2023-07-10 21:16:37,731 transreid.train INFO: Epoch[71] Iteration[100/203] Loss: 0.346, Base Lr: 1.26e-04
2023-07-10 21:16:42,079 transreid.train INFO: Epoch[71] Iteration[150/203] Loss: 0.351, Base Lr: 1.26e-04
2023-07-10 21:16:46,426 transreid.train INFO: Epoch[71] Iteration[200/203] Loss: 0.354, Base Lr: 1.26e-04
2023-07-10 21:16:50,964 transreid.train INFO: Epoch[72] Iteration[50/203] Loss: 0.321, Base Lr: 1.22e-04
2023-07-10 21:16:55,307 transreid.train INFO: Epoch[72] Iteration[100/203] Loss: 0.322, Base Lr: 1.22e-04
2023-07-10 21:16:59,649 transreid.train INFO: Epoch[72] Iteration[150/203] Loss: 0.328, Base Lr: 1.22e-04
2023-07-10 21:17:04,003 transreid.train INFO: Epoch[72] Iteration[200/203] Loss: 0.337, Base Lr: 1.22e-04
2023-07-10 21:17:08,544 transreid.train INFO: Epoch[73] Iteration[50/203] Loss: 0.330, Base Lr: 1.17e-04
2023-07-10 21:17:12,888 transreid.train INFO: Epoch[73] Iteration[100/203] Loss: 0.328, Base Lr: 1.17e-04
2023-07-10 21:17:17,236 transreid.train INFO: Epoch[73] Iteration[150/203] Loss: 0.330, Base Lr: 1.17e-04
2023-07-10 21:17:21,575 transreid.train INFO: Epoch[73] Iteration[200/203] Loss: 0.333, Base Lr: 1.17e-04
2023-07-10 21:17:26,124 transreid.train INFO: Epoch[74] Iteration[50/203] Loss: 0.327, Base Lr: 1.13e-04
2023-07-10 21:17:30,467 transreid.train INFO: Epoch[74] Iteration[100/203] Loss: 0.323, Base Lr: 1.13e-04
2023-07-10 21:17:34,815 transreid.train INFO: Epoch[74] Iteration[150/203] Loss: 0.337, Base Lr: 1.13e-04
2023-07-10 21:17:39,159 transreid.train INFO: Epoch[74] Iteration[200/203] Loss: 0.342, Base Lr: 1.13e-04
2023-07-10 21:17:43,727 transreid.train INFO: Epoch[75] Iteration[50/203] Loss: 0.314, Base Lr: 1.09e-04
2023-07-10 21:17:48,086 transreid.train INFO: Epoch[75] Iteration[100/203] Loss: 0.322, Base Lr: 1.09e-04
2023-07-10 21:17:52,440 transreid.train INFO: Epoch[75] Iteration[150/203] Loss: 0.321, Base Lr: 1.09e-04
2023-07-10 21:17:56,798 transreid.train INFO: Epoch[75] Iteration[200/203] Loss: 0.326, Base Lr: 1.09e-04
2023-07-10 21:18:01,346 transreid.train INFO: Epoch[76] Iteration[50/203] Loss: 0.317, Base Lr: 1.05e-04
2023-07-10 21:18:05,709 transreid.train INFO: Epoch[76] Iteration[100/203] Loss: 0.323, Base Lr: 1.05e-04
2023-07-10 21:18:10,046 transreid.train INFO: Epoch[76] Iteration[150/203] Loss: 0.323, Base Lr: 1.05e-04
2023-07-10 21:18:14,388 transreid.train INFO: Epoch[76] Iteration[200/203] Loss: 0.333, Base Lr: 1.05e-04
2023-07-10 21:18:18,922 transreid.train INFO: Epoch[77] Iteration[50/203] Loss: 0.328, Base Lr: 1.00e-04
2023-07-10 21:18:23,265 transreid.train INFO: Epoch[77] Iteration[100/203] Loss: 0.317, Base Lr: 1.00e-04
2023-07-10 21:18:27,607 transreid.train INFO: Epoch[77] Iteration[150/203] Loss: 0.319, Base Lr: 1.00e-04
2023-07-10 21:18:31,949 transreid.train INFO: Epoch[77] Iteration[200/203] Loss: 0.321, Base Lr: 1.00e-04
2023-07-10 21:18:36,487 transreid.train INFO: Epoch[78] Iteration[50/203] Loss: 0.293, Base Lr: 9.63e-05
2023-07-10 21:18:40,827 transreid.train INFO: Epoch[78] Iteration[100/203] Loss: 0.307, Base Lr: 9.63e-05
2023-07-10 21:18:45,174 transreid.train INFO: Epoch[78] Iteration[150/203] Loss: 0.311, Base Lr: 9.63e-05
2023-07-10 21:18:49,511 transreid.train INFO: Epoch[78] Iteration[200/203] Loss: 0.319, Base Lr: 9.63e-05
2023-07-10 21:18:54,049 transreid.train INFO: Epoch[79] Iteration[50/203] Loss: 0.313, Base Lr: 9.22e-05
2023-07-10 21:18:58,393 transreid.train INFO: Epoch[79] Iteration[100/203] Loss: 0.306, Base Lr: 9.22e-05
2023-07-10 21:19:02,737 transreid.train INFO: Epoch[79] Iteration[150/203] Loss: 0.308, Base Lr: 9.22e-05
2023-07-10 21:19:07,083 transreid.train INFO: Epoch[79] Iteration[200/203] Loss: 0.312, Base Lr: 9.22e-05
2023-07-10 21:19:11,620 transreid.train INFO: Epoch[80] Iteration[50/203] Loss: 0.281, Base Lr: 8.83e-05
2023-07-10 21:19:15,963 transreid.train INFO: Epoch[80] Iteration[100/203] Loss: 0.306, Base Lr: 8.83e-05
2023-07-10 21:19:20,305 transreid.train INFO: Epoch[80] Iteration[150/203] Loss: 0.303, Base Lr: 8.83e-05
2023-07-10 21:19:24,646 transreid.train INFO: Epoch[80] Iteration[200/203] Loss: 0.302, Base Lr: 8.83e-05
2023-07-10 21:19:29,186 transreid.train INFO: Epoch[81] Iteration[50/203] Loss: 0.294, Base Lr: 8.43e-05
2023-07-10 21:19:33,534 transreid.train INFO: Epoch[81] Iteration[100/203] Loss: 0.294, Base Lr: 8.43e-05
2023-07-10 21:19:37,888 transreid.train INFO: Epoch[81] Iteration[150/203] Loss: 0.287, Base Lr: 8.43e-05
2023-07-10 21:19:42,235 transreid.train INFO: Epoch[81] Iteration[200/203] Loss: 0.295, Base Lr: 8.43e-05
2023-07-10 21:19:46,778 transreid.train INFO: Epoch[82] Iteration[50/203] Loss: 0.277, Base Lr: 8.05e-05
2023-07-10 21:19:51,121 transreid.train INFO: Epoch[82] Iteration[100/203] Loss: 0.285, Base Lr: 8.05e-05
2023-07-10 21:19:55,464 transreid.train INFO: Epoch[82] Iteration[150/203] Loss: 0.290, Base Lr: 8.05e-05
2023-07-10 21:19:59,810 transreid.train INFO: Epoch[82] Iteration[200/203] Loss: 0.293, Base Lr: 8.05e-05
2023-07-10 21:20:04,357 transreid.train INFO: Epoch[83] Iteration[50/203] Loss: 0.297, Base Lr: 7.67e-05
2023-07-10 21:20:08,704 transreid.train INFO: Epoch[83] Iteration[100/203] Loss: 0.284, Base Lr: 7.67e-05
2023-07-10 21:20:13,051 transreid.train INFO: Epoch[83] Iteration[150/203] Loss: 0.294, Base Lr: 7.67e-05
2023-07-10 21:20:17,399 transreid.train INFO: Epoch[83] Iteration[200/203] Loss: 0.291, Base Lr: 7.67e-05
2023-07-10 21:20:21,941 transreid.train INFO: Epoch[84] Iteration[50/203] Loss: 0.288, Base Lr: 7.29e-05
2023-07-10 21:20:26,286 transreid.train INFO: Epoch[84] Iteration[100/203] Loss: 0.294, Base Lr: 7.29e-05
2023-07-10 21:20:30,631 transreid.train INFO: Epoch[84] Iteration[150/203] Loss: 0.287, Base Lr: 7.29e-05
2023-07-10 21:20:34,973 transreid.train INFO: Epoch[84] Iteration[200/203] Loss: 0.287, Base Lr: 7.29e-05
2023-07-10 21:20:39,517 transreid.train INFO: Epoch[85] Iteration[50/203] Loss: 0.274, Base Lr: 6.93e-05
2023-07-10 21:20:43,856 transreid.train INFO: Epoch[85] Iteration[100/203] Loss: 0.268, Base Lr: 6.93e-05
2023-07-10 21:20:48,206 transreid.train INFO: Epoch[85] Iteration[150/203] Loss: 0.273, Base Lr: 6.93e-05
2023-07-10 21:20:52,574 transreid.train INFO: Epoch[85] Iteration[200/203] Loss: 0.279, Base Lr: 6.93e-05
2023-07-10 21:20:57,115 transreid.train INFO: Epoch[86] Iteration[50/203] Loss: 0.252, Base Lr: 6.57e-05
2023-07-10 21:21:01,462 transreid.train INFO: Epoch[86] Iteration[100/203] Loss: 0.267, Base Lr: 6.57e-05
2023-07-10 21:21:05,804 transreid.train INFO: Epoch[86] Iteration[150/203] Loss: 0.264, Base Lr: 6.57e-05
2023-07-10 21:21:10,152 transreid.train INFO: Epoch[86] Iteration[200/203] Loss: 0.270, Base Lr: 6.57e-05
2023-07-10 21:21:14,690 transreid.train INFO: Epoch[87] Iteration[50/203] Loss: 0.255, Base Lr: 6.22e-05
2023-07-10 21:21:19,035 transreid.train INFO: Epoch[87] Iteration[100/203] Loss: 0.262, Base Lr: 6.22e-05
2023-07-10 21:21:23,378 transreid.train INFO: Epoch[87] Iteration[150/203] Loss: 0.265, Base Lr: 6.22e-05
2023-07-10 21:21:27,722 transreid.train INFO: Epoch[87] Iteration[200/203] Loss: 0.272, Base Lr: 6.22e-05
2023-07-10 21:21:32,269 transreid.train INFO: Epoch[88] Iteration[50/203] Loss: 0.267, Base Lr: 5.87e-05
2023-07-10 21:21:36,610 transreid.train INFO: Epoch[88] Iteration[100/203] Loss: 0.270, Base Lr: 5.87e-05
2023-07-10 21:21:40,956 transreid.train INFO: Epoch[88] Iteration[150/203] Loss: 0.275, Base Lr: 5.87e-05
2023-07-10 21:21:45,296 transreid.train INFO: Epoch[88] Iteration[200/203] Loss: 0.275, Base Lr: 5.87e-05
2023-07-10 21:21:49,840 transreid.train INFO: Epoch[89] Iteration[50/203] Loss: 0.262, Base Lr: 5.54e-05
2023-07-10 21:21:54,180 transreid.train INFO: Epoch[89] Iteration[100/203] Loss: 0.269, Base Lr: 5.54e-05
2023-07-10 21:21:58,526 transreid.train INFO: Epoch[89] Iteration[150/203] Loss: 0.271, Base Lr: 5.54e-05
2023-07-10 21:22:02,871 transreid.train INFO: Epoch[89] Iteration[200/203] Loss: 0.271, Base Lr: 5.54e-05
2023-07-10 21:22:07,415 transreid.train INFO: Epoch[90] Iteration[50/203] Loss: 0.270, Base Lr: 5.21e-05
2023-07-10 21:22:11,764 transreid.train INFO: Epoch[90] Iteration[100/203] Loss: 0.275, Base Lr: 5.21e-05
2023-07-10 21:22:16,108 transreid.train INFO: Epoch[90] Iteration[150/203] Loss: 0.275, Base Lr: 5.21e-05
2023-07-10 21:22:20,452 transreid.train INFO: Epoch[90] Iteration[200/203] Loss: 0.277, Base Lr: 5.21e-05
2023-07-10 21:22:24,994 transreid.train INFO: Epoch[91] Iteration[50/203] Loss: 0.275, Base Lr: 4.89e-05
2023-07-10 21:22:29,336 transreid.train INFO: Epoch[91] Iteration[100/203] Loss: 0.268, Base Lr: 4.89e-05
2023-07-10 21:22:33,677 transreid.train INFO: Epoch[91] Iteration[150/203] Loss: 0.267, Base Lr: 4.89e-05
2023-07-10 21:22:38,015 transreid.train INFO: Epoch[91] Iteration[200/203] Loss: 0.264, Base Lr: 4.89e-05
2023-07-10 21:22:42,556 transreid.train INFO: Epoch[92] Iteration[50/203] Loss: 0.243, Base Lr: 4.58e-05
2023-07-10 21:22:46,894 transreid.train INFO: Epoch[92] Iteration[100/203] Loss: 0.257, Base Lr: 4.58e-05
2023-07-10 21:22:51,239 transreid.train INFO: Epoch[92] Iteration[150/203] Loss: 0.263, Base Lr: 4.58e-05
2023-07-10 21:22:55,579 transreid.train INFO: Epoch[92] Iteration[200/203] Loss: 0.260, Base Lr: 4.58e-05
2023-07-10 21:23:00,120 transreid.train INFO: Epoch[93] Iteration[50/203] Loss: 0.247, Base Lr: 4.28e-05
2023-07-10 21:23:04,466 transreid.train INFO: Epoch[93] Iteration[100/203] Loss: 0.247, Base Lr: 4.28e-05
2023-07-10 21:23:08,806 transreid.train INFO: Epoch[93] Iteration[150/203] Loss: 0.255, Base Lr: 4.28e-05
2023-07-10 21:23:13,153 transreid.train INFO: Epoch[93] Iteration[200/203] Loss: 0.258, Base Lr: 4.28e-05
2023-07-10 21:23:17,694 transreid.train INFO: Epoch[94] Iteration[50/203] Loss: 0.245, Base Lr: 3.99e-05
2023-07-10 21:23:22,042 transreid.train INFO: Epoch[94] Iteration[100/203] Loss: 0.248, Base Lr: 3.99e-05
2023-07-10 21:23:26,397 transreid.train INFO: Epoch[94] Iteration[150/203] Loss: 0.254, Base Lr: 3.99e-05
2023-07-10 21:23:30,751 transreid.train INFO: Epoch[94] Iteration[200/203] Loss: 0.258, Base Lr: 3.99e-05
2023-07-10 21:23:35,297 transreid.train INFO: Epoch[95] Iteration[50/203] Loss: 0.270, Base Lr: 3.71e-05
2023-07-10 21:23:39,648 transreid.train INFO: Epoch[95] Iteration[100/203] Loss: 0.255, Base Lr: 3.71e-05
2023-07-10 21:23:43,995 transreid.train INFO: Epoch[95] Iteration[150/203] Loss: 0.260, Base Lr: 3.71e-05
2023-07-10 21:23:48,343 transreid.train INFO: Epoch[95] Iteration[200/203] Loss: 0.261, Base Lr: 3.71e-05
2023-07-10 21:23:52,894 transreid.train INFO: Epoch[96] Iteration[50/203] Loss: 0.251, Base Lr: 3.43e-05
2023-07-10 21:23:57,247 transreid.train INFO: Epoch[96] Iteration[100/203] Loss: 0.258, Base Lr: 3.43e-05
2023-07-10 21:24:01,606 transreid.train INFO: Epoch[96] Iteration[150/203] Loss: 0.260, Base Lr: 3.43e-05
2023-07-10 21:24:05,984 transreid.train INFO: Epoch[96] Iteration[200/203] Loss: 0.262, Base Lr: 3.43e-05
2023-07-10 21:24:10,570 transreid.train INFO: Epoch[97] Iteration[50/203] Loss: 0.242, Base Lr: 3.17e-05
2023-07-10 21:24:14,952 transreid.train INFO: Epoch[97] Iteration[100/203] Loss: 0.256, Base Lr: 3.17e-05
2023-07-10 21:24:19,332 transreid.train INFO: Epoch[97] Iteration[150/203] Loss: 0.258, Base Lr: 3.17e-05
2023-07-10 21:24:23,713 transreid.train INFO: Epoch[97] Iteration[200/203] Loss: 0.260, Base Lr: 3.17e-05
2023-07-10 21:24:28,291 transreid.train INFO: Epoch[98] Iteration[50/203] Loss: 0.245, Base Lr: 2.92e-05
2023-07-10 21:24:32,674 transreid.train INFO: Epoch[98] Iteration[100/203] Loss: 0.251, Base Lr: 2.92e-05
2023-07-10 21:24:37,055 transreid.train INFO: Epoch[98] Iteration[150/203] Loss: 0.247, Base Lr: 2.92e-05
2023-07-10 21:24:41,436 transreid.train INFO: Epoch[98] Iteration[200/203] Loss: 0.247, Base Lr: 2.92e-05
2023-07-10 21:24:46,021 transreid.train INFO: Epoch[99] Iteration[50/203] Loss: 0.232, Base Lr: 2.67e-05
2023-07-10 21:24:50,402 transreid.train INFO: Epoch[99] Iteration[100/203] Loss: 0.241, Base Lr: 2.67e-05
2023-07-10 21:24:54,786 transreid.train INFO: Epoch[99] Iteration[150/203] Loss: 0.243, Base Lr: 2.67e-05
2023-07-10 21:24:59,166 transreid.train INFO: Epoch[99] Iteration[200/203] Loss: 0.248, Base Lr: 2.67e-05
2023-07-10 21:25:03,748 transreid.train INFO: Epoch[100] Iteration[50/203] Loss: 0.247, Base Lr: 2.44e-05
2023-07-10 21:25:08,126 transreid.train INFO: Epoch[100] Iteration[100/203] Loss: 0.245, Base Lr: 2.44e-05
2023-07-10 21:25:12,504 transreid.train INFO: Epoch[100] Iteration[150/203] Loss: 0.244, Base Lr: 2.44e-05
2023-07-10 21:25:16,881 transreid.train INFO: Epoch[100] Iteration[200/203] Loss: 0.244, Base Lr: 2.44e-05
2023-07-10 21:25:21,459 transreid.train INFO: Epoch[101] Iteration[50/203] Loss: 0.232, Base Lr: 2.21e-05
2023-07-10 21:25:25,840 transreid.train INFO: Epoch[101] Iteration[100/203] Loss: 0.230, Base Lr: 2.21e-05
2023-07-10 21:25:30,217 transreid.train INFO: Epoch[101] Iteration[150/203] Loss: 0.232, Base Lr: 2.21e-05
2023-07-10 21:25:34,594 transreid.train INFO: Epoch[101] Iteration[200/203] Loss: 0.238, Base Lr: 2.21e-05
2023-07-10 21:25:39,174 transreid.train INFO: Epoch[102] Iteration[50/203] Loss: 0.244, Base Lr: 2.00e-05
2023-07-10 21:25:43,553 transreid.train INFO: Epoch[102] Iteration[100/203] Loss: 0.239, Base Lr: 2.00e-05
2023-07-10 21:25:47,932 transreid.train INFO: Epoch[102] Iteration[150/203] Loss: 0.246, Base Lr: 2.00e-05
2023-07-10 21:25:52,311 transreid.train INFO: Epoch[102] Iteration[200/203] Loss: 0.247, Base Lr: 2.00e-05
2023-07-10 21:25:56,892 transreid.train INFO: Epoch[103] Iteration[50/203] Loss: 0.261, Base Lr: 1.80e-05
2023-07-10 21:26:01,273 transreid.train INFO: Epoch[103] Iteration[100/203] Loss: 0.257, Base Lr: 1.80e-05
2023-07-10 21:26:05,659 transreid.train INFO: Epoch[103] Iteration[150/203] Loss: 0.247, Base Lr: 1.80e-05
2023-07-10 21:26:10,043 transreid.train INFO: Epoch[103] Iteration[200/203] Loss: 0.248, Base Lr: 1.80e-05
2023-07-10 21:26:14,628 transreid.train INFO: Epoch[104] Iteration[50/203] Loss: 0.242, Base Lr: 1.61e-05
2023-07-10 21:26:19,007 transreid.train INFO: Epoch[104] Iteration[100/203] Loss: 0.233, Base Lr: 1.61e-05
2023-07-10 21:26:23,386 transreid.train INFO: Epoch[104] Iteration[150/203] Loss: 0.235, Base Lr: 1.61e-05
2023-07-10 21:26:27,768 transreid.train INFO: Epoch[104] Iteration[200/203] Loss: 0.237, Base Lr: 1.61e-05
2023-07-10 21:26:32,347 transreid.train INFO: Epoch[105] Iteration[50/203] Loss: 0.233, Base Lr: 1.43e-05
2023-07-10 21:26:36,728 transreid.train INFO: Epoch[105] Iteration[100/203] Loss: 0.230, Base Lr: 1.43e-05
2023-07-10 21:26:41,107 transreid.train INFO: Epoch[105] Iteration[150/203] Loss: 0.242, Base Lr: 1.43e-05
2023-07-10 21:26:45,489 transreid.train INFO: Epoch[105] Iteration[200/203] Loss: 0.242, Base Lr: 1.43e-05
2023-07-10 21:26:50,068 transreid.train INFO: Epoch[106] Iteration[50/203] Loss: 0.214, Base Lr: 1.26e-05
2023-07-10 21:26:54,447 transreid.train INFO: Epoch[106] Iteration[100/203] Loss: 0.227, Base Lr: 1.26e-05
2023-07-10 21:26:58,827 transreid.train INFO: Epoch[106] Iteration[150/203] Loss: 0.231, Base Lr: 1.26e-05
2023-07-10 21:27:03,207 transreid.train INFO: Epoch[106] Iteration[200/203] Loss: 0.238, Base Lr: 1.26e-05
2023-07-10 21:27:07,784 transreid.train INFO: Epoch[107] Iteration[50/203] Loss: 0.243, Base Lr: 1.10e-05
2023-07-10 21:27:12,163 transreid.train INFO: Epoch[107] Iteration[100/203] Loss: 0.242, Base Lr: 1.10e-05
2023-07-10 21:27:16,543 transreid.train INFO: Epoch[107] Iteration[150/203] Loss: 0.244, Base Lr: 1.10e-05
2023-07-10 21:27:20,922 transreid.train INFO: Epoch[107] Iteration[200/203] Loss: 0.243, Base Lr: 1.10e-05
2023-07-10 21:27:25,502 transreid.train INFO: Epoch[108] Iteration[50/203] Loss: 0.231, Base Lr: 9.54e-06
2023-07-10 21:27:29,880 transreid.train INFO: Epoch[108] Iteration[100/203] Loss: 0.234, Base Lr: 9.54e-06
2023-07-10 21:27:34,259 transreid.train INFO: Epoch[108] Iteration[150/203] Loss: 0.239, Base Lr: 9.54e-06
2023-07-10 21:27:38,638 transreid.train INFO: Epoch[108] Iteration[200/203] Loss: 0.238, Base Lr: 9.54e-06
2023-07-10 21:27:43,218 transreid.train INFO: Epoch[109] Iteration[50/203] Loss: 0.259, Base Lr: 8.19e-06
2023-07-10 21:27:47,600 transreid.train INFO: Epoch[109] Iteration[100/203] Loss: 0.246, Base Lr: 8.19e-06
2023-07-10 21:27:52,001 transreid.train INFO: Epoch[109] Iteration[150/203] Loss: 0.238, Base Lr: 8.19e-06
2023-07-10 21:27:56,404 transreid.train INFO: Epoch[109] Iteration[200/203] Loss: 0.240, Base Lr: 8.19e-06
2023-07-10 21:28:01,011 transreid.train INFO: Epoch[110] Iteration[50/203] Loss: 0.226, Base Lr: 6.95e-06
2023-07-10 21:28:05,417 transreid.train INFO: Epoch[110] Iteration[100/203] Loss: 0.226, Base Lr: 6.95e-06
2023-07-10 21:28:09,823 transreid.train INFO: Epoch[110] Iteration[150/203] Loss: 0.228, Base Lr: 6.95e-06
2023-07-10 21:28:14,229 transreid.train INFO: Epoch[110] Iteration[200/203] Loss: 0.232, Base Lr: 6.95e-06
2023-07-10 21:28:18,833 transreid.train INFO: Epoch[111] Iteration[50/203] Loss: 0.242, Base Lr: 5.82e-06
2023-07-10 21:28:23,234 transreid.train INFO: Epoch[111] Iteration[100/203] Loss: 0.238, Base Lr: 5.82e-06
2023-07-10 21:28:27,589 transreid.train INFO: Epoch[111] Iteration[150/203] Loss: 0.231, Base Lr: 5.82e-06
2023-07-10 21:28:31,945 transreid.train INFO: Epoch[111] Iteration[200/203] Loss: 0.237, Base Lr: 5.82e-06
2023-07-10 21:28:36,482 transreid.train INFO: Epoch[112] Iteration[50/203] Loss: 0.229, Base Lr: 4.81e-06
2023-07-10 21:28:40,816 transreid.train INFO: Epoch[112] Iteration[100/203] Loss: 0.234, Base Lr: 4.81e-06
2023-07-10 21:28:45,155 transreid.train INFO: Epoch[112] Iteration[150/203] Loss: 0.230, Base Lr: 4.81e-06
2023-07-10 21:28:49,494 transreid.train INFO: Epoch[112] Iteration[200/203] Loss: 0.232, Base Lr: 4.81e-06
2023-07-10 21:28:54,030 transreid.train INFO: Epoch[113] Iteration[50/203] Loss: 0.255, Base Lr: 3.92e-06
2023-07-10 21:28:58,367 transreid.train INFO: Epoch[113] Iteration[100/203] Loss: 0.248, Base Lr: 3.92e-06
2023-07-10 21:29:02,705 transreid.train INFO: Epoch[113] Iteration[150/203] Loss: 0.244, Base Lr: 3.92e-06
2023-07-10 21:29:07,042 transreid.train INFO: Epoch[113] Iteration[200/203] Loss: 0.239, Base Lr: 3.92e-06
2023-07-10 21:29:11,583 transreid.train INFO: Epoch[114] Iteration[50/203] Loss: 0.240, Base Lr: 3.15e-06
2023-07-10 21:29:15,924 transreid.train INFO: Epoch[114] Iteration[100/203] Loss: 0.241, Base Lr: 3.15e-06
2023-07-10 21:29:20,266 transreid.train INFO: Epoch[114] Iteration[150/203] Loss: 0.231, Base Lr: 3.15e-06
2023-07-10 21:29:24,606 transreid.train INFO: Epoch[114] Iteration[200/203] Loss: 0.234, Base Lr: 3.15e-06
2023-07-10 21:29:29,143 transreid.train INFO: Epoch[115] Iteration[50/203] Loss: 0.242, Base Lr: 2.49e-06
2023-07-10 21:29:33,485 transreid.train INFO: Epoch[115] Iteration[100/203] Loss: 0.229, Base Lr: 2.49e-06
2023-07-10 21:29:37,826 transreid.train INFO: Epoch[115] Iteration[150/203] Loss: 0.231, Base Lr: 2.49e-06
2023-07-10 21:29:42,169 transreid.train INFO: Epoch[115] Iteration[200/203] Loss: 0.236, Base Lr: 2.49e-06
2023-07-10 21:29:46,704 transreid.train INFO: Epoch[116] Iteration[50/203] Loss: 0.227, Base Lr: 1.96e-06
2023-07-10 21:29:51,047 transreid.train INFO: Epoch[116] Iteration[100/203] Loss: 0.229, Base Lr: 1.96e-06
2023-07-10 21:29:55,388 transreid.train INFO: Epoch[116] Iteration[150/203] Loss: 0.224, Base Lr: 1.96e-06
2023-07-10 21:29:59,732 transreid.train INFO: Epoch[116] Iteration[200/203] Loss: 0.226, Base Lr: 1.96e-06
2023-07-10 21:30:04,280 transreid.train INFO: Epoch[117] Iteration[50/203] Loss: 0.220, Base Lr: 1.54e-06
2023-07-10 21:30:08,619 transreid.train INFO: Epoch[117] Iteration[100/203] Loss: 0.234, Base Lr: 1.54e-06
2023-07-10 21:30:12,962 transreid.train INFO: Epoch[117] Iteration[150/203] Loss: 0.234, Base Lr: 1.54e-06
2023-07-10 21:30:17,301 transreid.train INFO: Epoch[117] Iteration[200/203] Loss: 0.232, Base Lr: 1.54e-06
2023-07-10 21:30:21,838 transreid.train INFO: Epoch[118] Iteration[50/203] Loss: 0.257, Base Lr: 1.24e-06
2023-07-10 21:30:26,176 transreid.train INFO: Epoch[118] Iteration[100/203] Loss: 0.241, Base Lr: 1.24e-06
2023-07-10 21:30:30,515 transreid.train INFO: Epoch[118] Iteration[150/203] Loss: 0.240, Base Lr: 1.24e-06
2023-07-10 21:30:34,856 transreid.train INFO: Epoch[118] Iteration[200/203] Loss: 0.233, Base Lr: 1.24e-06
2023-07-10 21:30:39,390 transreid.train INFO: Epoch[119] Iteration[50/203] Loss: 0.240, Base Lr: 1.06e-06
2023-07-10 21:30:43,731 transreid.train INFO: Epoch[119] Iteration[100/203] Loss: 0.232, Base Lr: 1.06e-06
2023-07-10 21:30:48,069 transreid.train INFO: Epoch[119] Iteration[150/203] Loss: 0.230, Base Lr: 1.06e-06
2023-07-10 21:30:52,411 transreid.train INFO: Epoch[119] Iteration[200/203] Loss: 0.234, Base Lr: 1.06e-06
2023-07-10 21:30:56,945 transreid.train INFO: Epoch[120] Iteration[50/203] Loss: 0.232, Base Lr: 1.00e-06
2023-07-10 21:31:01,283 transreid.train INFO: Epoch[120] Iteration[100/203] Loss: 0.233, Base Lr: 1.00e-06
2023-07-10 21:31:05,625 transreid.train INFO: Epoch[120] Iteration[150/203] Loss: 0.241, Base Lr: 1.00e-06
2023-07-10 21:31:09,962 transreid.train INFO: Epoch[120] Iteration[200/203] Loss: 0.240, Base Lr: 1.00e-06
2023-07-10 21:31:12,505 transreid.train INFO: Stage1 running time: 0:35:45.793878
2023-07-10 21:31:12,526 transreid.train INFO: start training
2023-07-10 21:31:30,841 transreid.train INFO: Epoch[1] Iteration[50/186] Loss: 18.577, Acc: 0.326, Base Lr: 9.50e-07
2023-07-10 21:31:47,386 transreid.train INFO: Epoch[1] Iteration[100/186] Loss: 14.988, Acc: 0.455, Base Lr: 9.50e-07
2023-07-10 21:32:03,986 transreid.train INFO: Epoch[1] Iteration[150/186] Loss: 13.298, Acc: 0.528, Base Lr: 9.50e-07
2023-07-10 21:32:14,539 transreid.train INFO: Epoch 1 done. Time per batch: 0.337[s] Speed: 190.0[samples/s]
2023-07-10 21:32:32,134 transreid.train INFO: Epoch[2] Iteration[50/186] Loss: 8.867, Acc: 0.641, Base Lr: 1.40e-06
2023-07-10 21:32:48,647 transreid.train INFO: Epoch[2] Iteration[100/186] Loss: 8.625, Acc: 0.680, Base Lr: 1.40e-06
2023-07-10 21:33:05,154 transreid.train INFO: Epoch[2] Iteration[150/186] Loss: 8.409, Acc: 0.708, Base Lr: 1.40e-06
2023-07-10 21:33:15,556 transreid.train INFO: Epoch 2 done. Time per batch: 0.333[s] Speed: 191.9[samples/s]
2023-07-10 21:33:32,961 transreid.train INFO: Epoch[3] Iteration[50/186] Loss: 7.779, Acc: 0.687, Base Lr: 1.85e-06
2023-07-10 21:33:49,776 transreid.train INFO: Epoch[3] Iteration[100/186] Loss: 7.616, Acc: 0.719, Base Lr: 1.85e-06
2023-07-10 21:34:06,430 transreid.train INFO: Epoch[3] Iteration[150/186] Loss: 7.489, Acc: 0.743, Base Lr: 1.85e-06
2023-07-10 21:34:17,309 transreid.train INFO: Epoch 3 done. Time per batch: 0.336[s] Speed: 190.7[samples/s]
2023-07-10 21:34:34,995 transreid.train INFO: Epoch[4] Iteration[50/186] Loss: 7.141, Acc: 0.722, Base Lr: 2.30e-06
2023-07-10 21:34:51,475 transreid.train INFO: Epoch[4] Iteration[100/186] Loss: 7.009, Acc: 0.761, Base Lr: 2.30e-06
2023-07-10 21:35:08,092 transreid.train INFO: Epoch[4] Iteration[150/186] Loss: 6.881, Acc: 0.788, Base Lr: 2.30e-06
2023-07-10 21:35:18,940 transreid.train INFO: Epoch 4 done. Time per batch: 0.335[s] Speed: 191.1[samples/s]
2023-07-10 21:35:36,676 transreid.train INFO: Epoch[5] Iteration[50/186] Loss: 6.687, Acc: 0.766, Base Lr: 2.75e-06
2023-07-10 21:35:53,227 transreid.train INFO: Epoch[5] Iteration[100/186] Loss: 6.617, Acc: 0.788, Base Lr: 2.75e-06
2023-07-10 21:36:09,791 transreid.train INFO: Epoch[5] Iteration[150/186] Loss: 6.550, Acc: 0.814, Base Lr: 2.75e-06
2023-07-10 21:36:20,322 transreid.train INFO: Epoch 5 done. Time per batch: 0.335[s] Speed: 190.8[samples/s]
2023-07-10 21:36:37,899 transreid.train INFO: Epoch[6] Iteration[50/186] Loss: 6.535, Acc: 0.788, Base Lr: 3.20e-06
2023-07-10 21:36:54,532 transreid.train INFO: Epoch[6] Iteration[100/186] Loss: 6.406, Acc: 0.815, Base Lr: 3.20e-06
2023-07-10 21:37:11,134 transreid.train INFO: Epoch[6] Iteration[150/186] Loss: 6.311, Acc: 0.837, Base Lr: 3.20e-06
2023-07-10 21:37:21,693 transreid.train INFO: Epoch 6 done. Time per batch: 0.335[s] Speed: 190.8[samples/s]
2023-07-10 21:37:39,286 transreid.train INFO: Epoch[7] Iteration[50/186] Loss: 6.064, Acc: 0.829, Base Lr: 3.65e-06
2023-07-10 21:37:55,789 transreid.train INFO: Epoch[7] Iteration[100/186] Loss: 6.071, Acc: 0.847, Base Lr: 3.65e-06
2023-07-10 21:38:12,039 transreid.train INFO: Epoch[7] Iteration[150/186] Loss: 5.988, Acc: 0.866, Base Lr: 3.65e-06
2023-07-10 21:38:23,066 transreid.train INFO: Epoch 7 done. Time per batch: 0.334[s] Speed: 191.9[samples/s]
2023-07-10 21:38:40,711 transreid.train INFO: Epoch[8] Iteration[50/186] Loss: 5.998, Acc: 0.834, Base Lr: 4.10e-06
2023-07-10 21:38:57,332 transreid.train INFO: Epoch[8] Iteration[100/186] Loss: 5.923, Acc: 0.859, Base Lr: 4.10e-06
2023-07-10 21:39:14,010 transreid.train INFO: Epoch[8] Iteration[150/186] Loss: 5.828, Acc: 0.879, Base Lr: 4.10e-06
2023-07-10 21:39:24,963 transreid.train INFO: Epoch 8 done. Time per batch: 0.336[s] Speed: 190.3[samples/s]
2023-07-10 21:39:42,554 transreid.train INFO: Epoch[9] Iteration[50/186] Loss: 5.862, Acc: 0.852, Base Lr: 4.55e-06
2023-07-10 21:39:59,047 transreid.train INFO: Epoch[9] Iteration[100/186] Loss: 5.777, Acc: 0.870, Base Lr: 4.55e-06
2023-07-10 21:40:15,858 transreid.train INFO: Epoch[9] Iteration[150/186] Loss: 5.694, Acc: 0.886, Base Lr: 4.55e-06
2023-07-10 21:40:26,510 transreid.train INFO: Epoch 9 done. Time per batch: 0.336[s] Speed: 190.3[samples/s]
2023-07-10 21:40:43,987 transreid.train INFO: Epoch[10] Iteration[50/186] Loss: 5.664, Acc: 0.871, Base Lr: 5.00e-06
2023-07-10 21:41:00,410 transreid.train INFO: Epoch[10] Iteration[100/186] Loss: 5.572, Acc: 0.888, Base Lr: 5.00e-06
2023-07-10 21:41:16,962 transreid.train INFO: Epoch[10] Iteration[150/186] Loss: 5.519, Acc: 0.901, Base Lr: 5.00e-06
2023-07-10 21:41:27,442 transreid.train INFO: Epoch 10 done. Time per batch: 0.333[s] Speed: 192.2[samples/s]
2023-07-10 21:41:45,253 transreid.train INFO: Epoch[11] Iteration[50/186] Loss: 5.554, Acc: 0.891, Base Lr: 5.00e-06
2023-07-10 21:42:01,894 transreid.train INFO: Epoch[11] Iteration[100/186] Loss: 5.448, Acc: 0.907, Base Lr: 5.00e-06
2023-07-10 21:42:18,550 transreid.train INFO: Epoch[11] Iteration[150/186] Loss: 5.370, Acc: 0.918, Base Lr: 5.00e-06
2023-07-10 21:42:29,399 transreid.train INFO: Epoch 11 done. Time per batch: 0.337[s] Speed: 190.1[samples/s]
2023-07-10 21:42:47,256 transreid.train INFO: Epoch[12] Iteration[50/186] Loss: 5.375, Acc: 0.906, Base Lr: 5.00e-06
2023-07-10 21:43:04,088 transreid.train INFO: Epoch[12] Iteration[100/186] Loss: 5.299, Acc: 0.922, Base Lr: 5.00e-06
2023-07-10 21:43:20,736 transreid.train INFO: Epoch[12] Iteration[150/186] Loss: 5.253, Acc: 0.930, Base Lr: 5.00e-06
2023-07-10 21:43:31,656 transreid.train INFO: Epoch 12 done. Time per batch: 0.338[s] Speed: 189.2[samples/s]
2023-07-10 21:43:49,144 transreid.train INFO: Epoch[13] Iteration[50/186] Loss: 5.229, Acc: 0.921, Base Lr: 5.00e-06
2023-07-10 21:44:05,645 transreid.train INFO: Epoch[13] Iteration[100/186] Loss: 5.194, Acc: 0.929, Base Lr: 5.00e-06
2023-07-10 21:44:22,138 transreid.train INFO: Epoch[13] Iteration[150/186] Loss: 5.126, Acc: 0.940, Base Lr: 5.00e-06
2023-07-10 21:44:32,828 transreid.train INFO: Epoch 13 done. Time per batch: 0.334[s] Speed: 191.5[samples/s]
2023-07-10 21:44:50,749 transreid.train INFO: Epoch[14] Iteration[50/186] Loss: 5.173, Acc: 0.932, Base Lr: 5.00e-06
2023-07-10 21:45:07,347 transreid.train INFO: Epoch[14] Iteration[100/186] Loss: 5.080, Acc: 0.941, Base Lr: 5.00e-06
2023-07-10 21:45:23,894 transreid.train INFO: Epoch[14] Iteration[150/186] Loss: 5.010, Acc: 0.948, Base Lr: 5.00e-06
2023-07-10 21:45:34,541 transreid.train INFO: Epoch 14 done. Time per batch: 0.337[s] Speed: 189.8[samples/s]
2023-07-10 21:45:52,157 transreid.train INFO: Epoch[15] Iteration[50/186] Loss: 5.029, Acc: 0.938, Base Lr: 5.00e-06
2023-07-10 21:46:08,781 transreid.train INFO: Epoch[15] Iteration[100/186] Loss: 4.976, Acc: 0.947, Base Lr: 5.00e-06
2023-07-10 21:46:25,344 transreid.train INFO: Epoch[15] Iteration[150/186] Loss: 4.952, Acc: 0.951, Base Lr: 5.00e-06
2023-07-10 21:46:36,261 transreid.train INFO: Epoch 15 done. Time per batch: 0.335[s] Speed: 190.8[samples/s]
2023-07-10 21:46:54,135 transreid.train INFO: Epoch[16] Iteration[50/186] Loss: 4.940, Acc: 0.958, Base Lr: 5.00e-06
2023-07-10 21:47:10,659 transreid.train INFO: Epoch[16] Iteration[100/186] Loss: 4.892, Acc: 0.962, Base Lr: 5.00e-06
2023-07-10 21:47:27,363 transreid.train INFO: Epoch[16] Iteration[150/186] Loss: 4.845, Acc: 0.962, Base Lr: 5.00e-06
2023-07-10 21:47:37,910 transreid.train INFO: Epoch 16 done. Time per batch: 0.337[s] Speed: 190.0[samples/s]
2023-07-10 21:47:55,471 transreid.train INFO: Epoch[17] Iteration[50/186] Loss: 4.828, Acc: 0.948, Base Lr: 5.00e-06
2023-07-10 21:48:12,176 transreid.train INFO: Epoch[17] Iteration[100/186] Loss: 4.818, Acc: 0.955, Base Lr: 5.00e-06
2023-07-10 21:48:28,938 transreid.train INFO: Epoch[17] Iteration[150/186] Loss: 4.783, Acc: 0.959, Base Lr: 5.00e-06
2023-07-10 21:48:39,944 transreid.train INFO: Epoch 17 done. Time per batch: 0.337[s] Speed: 189.8[samples/s]
2023-07-10 21:48:57,527 transreid.train INFO: Epoch[18] Iteration[50/186] Loss: 4.854, Acc: 0.953, Base Lr: 5.00e-06
2023-07-10 21:49:13,979 transreid.train INFO: Epoch[18] Iteration[100/186] Loss: 4.790, Acc: 0.961, Base Lr: 5.00e-06
2023-07-10 21:49:30,729 transreid.train INFO: Epoch[18] Iteration[150/186] Loss: 4.728, Acc: 0.966, Base Lr: 5.00e-06
2023-07-10 21:49:41,273 transreid.train INFO: Epoch 18 done. Time per batch: 0.335[s] Speed: 191.0[samples/s]
2023-07-10 21:49:58,932 transreid.train INFO: Epoch[19] Iteration[50/186] Loss: 4.742, Acc: 0.958, Base Lr: 5.00e-06
2023-07-10 21:50:15,578 transreid.train INFO: Epoch[19] Iteration[100/186] Loss: 4.704, Acc: 0.962, Base Lr: 5.00e-06
2023-07-10 21:50:32,121 transreid.train INFO: Epoch[19] Iteration[150/186] Loss: 4.638, Acc: 0.968, Base Lr: 5.00e-06
2023-07-10 21:50:42,656 transreid.train INFO: Epoch 19 done. Time per batch: 0.335[s] Speed: 190.8[samples/s]
2023-07-10 21:51:00,341 transreid.train INFO: Epoch[20] Iteration[50/186] Loss: 4.673, Acc: 0.969, Base Lr: 5.00e-06
2023-07-10 21:51:16,967 transreid.train INFO: Epoch[20] Iteration[100/186] Loss: 4.610, Acc: 0.973, Base Lr: 5.00e-06
2023-07-10 21:51:33,641 transreid.train INFO: Epoch[20] Iteration[150/186] Loss: 4.570, Acc: 0.975, Base Lr: 5.00e-06
2023-07-10 21:51:44,564 transreid.train INFO: Epoch 20 done. Time per batch: 0.336[s] Speed: 190.2[samples/s]
2023-07-10 21:52:02,247 transreid.train INFO: Epoch[21] Iteration[50/186] Loss: 4.599, Acc: 0.967, Base Lr: 5.00e-06
2023-07-10 21:52:18,853 transreid.train INFO: Epoch[21] Iteration[100/186] Loss: 4.554, Acc: 0.969, Base Lr: 5.00e-06
2023-07-10 21:52:35,496 transreid.train INFO: Epoch[21] Iteration[150/186] Loss: 4.503, Acc: 0.972, Base Lr: 5.00e-06
2023-07-10 21:52:46,041 transreid.train INFO: Epoch 21 done. Time per batch: 0.336[s] Speed: 190.5[samples/s]
2023-07-10 21:53:03,745 transreid.train INFO: Epoch[22] Iteration[50/186] Loss: 4.543, Acc: 0.972, Base Lr: 5.00e-06
2023-07-10 21:53:20,431 transreid.train INFO: Epoch[22] Iteration[100/186] Loss: 4.491, Acc: 0.974, Base Lr: 5.00e-06
2023-07-10 21:53:36,954 transreid.train INFO: Epoch[22] Iteration[150/186] Loss: 4.437, Acc: 0.978, Base Lr: 5.00e-06
2023-07-10 21:53:47,555 transreid.train INFO: Epoch 22 done. Time per batch: 0.336[s] Speed: 190.4[samples/s]
2023-07-10 21:54:05,189 transreid.train INFO: Epoch[23] Iteration[50/186] Loss: 4.514, Acc: 0.976, Base Lr: 5.00e-06
2023-07-10 21:54:21,681 transreid.train INFO: Epoch[23] Iteration[100/186] Loss: 4.465, Acc: 0.977, Base Lr: 5.00e-06
2023-07-10 21:54:38,312 transreid.train INFO: Epoch[23] Iteration[150/186] Loss: 4.409, Acc: 0.980, Base Lr: 5.00e-06
2023-07-10 21:54:49,198 transreid.train INFO: Epoch 23 done. Time per batch: 0.335[s] Speed: 191.0[samples/s]
2023-07-10 21:55:06,783 transreid.train INFO: Epoch[24] Iteration[50/186] Loss: 4.453, Acc: 0.972, Base Lr: 5.00e-06
2023-07-10 21:55:23,492 transreid.train INFO: Epoch[24] Iteration[100/186] Loss: 4.413, Acc: 0.978, Base Lr: 5.00e-06
2023-07-10 21:55:39,926 transreid.train INFO: Epoch[24] Iteration[150/186] Loss: 4.348, Acc: 0.981, Base Lr: 5.00e-06
2023-07-10 21:55:50,624 transreid.train INFO: Epoch 24 done. Time per batch: 0.336[s] Speed: 190.7[samples/s]
2023-07-10 21:56:08,366 transreid.train INFO: Epoch[25] Iteration[50/186] Loss: 4.431, Acc: 0.975, Base Lr: 5.00e-06
2023-07-10 21:56:24,937 transreid.train INFO: Epoch[25] Iteration[100/186] Loss: 4.383, Acc: 0.977, Base Lr: 5.00e-06
2023-07-10 21:56:41,430 transreid.train INFO: Epoch[25] Iteration[150/186] Loss: 4.315, Acc: 0.981, Base Lr: 5.00e-06
2023-07-10 21:56:52,327 transreid.train INFO: Epoch 25 done. Time per batch: 0.335[s] Speed: 190.9[samples/s]
2023-07-10 21:57:09,940 transreid.train INFO: Epoch[26] Iteration[50/186] Loss: 4.329, Acc: 0.979, Base Lr: 5.00e-06
2023-07-10 21:57:26,546 transreid.train INFO: Epoch[26] Iteration[100/186] Loss: 4.286, Acc: 0.981, Base Lr: 5.00e-06
2023-07-10 21:57:43,154 transreid.train INFO: Epoch[26] Iteration[150/186] Loss: 4.239, Acc: 0.983, Base Lr: 5.00e-06
2023-07-10 21:57:53,725 transreid.train INFO: Epoch 26 done. Time per batch: 0.336[s] Speed: 190.8[samples/s]
2023-07-10 21:58:11,317 transreid.train INFO: Epoch[27] Iteration[50/186] Loss: 4.331, Acc: 0.983, Base Lr: 5.00e-06
2023-07-10 21:58:27,848 transreid.train INFO: Epoch[27] Iteration[100/186] Loss: 4.246, Acc: 0.987, Base Lr: 5.00e-06
2023-07-10 21:58:44,663 transreid.train INFO: Epoch[27] Iteration[150/186] Loss: 4.188, Acc: 0.986, Base Lr: 5.00e-06
2023-07-10 21:58:55,320 transreid.train INFO: Epoch 27 done. Time per batch: 0.337[s] Speed: 190.1[samples/s]
2023-07-10 21:59:12,761 transreid.train INFO: Epoch[28] Iteration[50/186] Loss: 4.240, Acc: 0.982, Base Lr: 5.00e-06
2023-07-10 21:59:29,302 transreid.train INFO: Epoch[28] Iteration[100/186] Loss: 4.205, Acc: 0.985, Base Lr: 5.00e-06
2023-07-10 21:59:45,903 transreid.train INFO: Epoch[28] Iteration[150/186] Loss: 4.146, Acc: 0.985, Base Lr: 5.00e-06
2023-07-10 21:59:56,177 transreid.train INFO: Epoch 28 done. Time per batch: 0.334[s] Speed: 191.4[samples/s]
2023-07-10 22:00:13,785 transreid.train INFO: Epoch[29] Iteration[50/186] Loss: 4.195, Acc: 0.983, Base Lr: 5.00e-06
2023-07-10 22:00:30,419 transreid.train INFO: Epoch[29] Iteration[100/186] Loss: 4.155, Acc: 0.984, Base Lr: 5.00e-06
2023-07-10 22:00:47,050 transreid.train INFO: Epoch[29] Iteration[150/186] Loss: 4.097, Acc: 0.985, Base Lr: 5.00e-06
2023-07-10 22:00:57,274 transreid.train INFO: Epoch 29 done. Time per batch: 0.336[s] Speed: 190.6[samples/s]
2023-07-10 22:01:15,015 transreid.train INFO: Epoch[30] Iteration[50/186] Loss: 4.124, Acc: 0.984, Base Lr: 5.00e-07
2023-07-10 22:01:31,553 transreid.train INFO: Epoch[30] Iteration[100/186] Loss: 4.081, Acc: 0.988, Base Lr: 5.00e-07
2023-07-10 22:01:48,054 transreid.train INFO: Epoch[30] Iteration[150/186] Loss: 4.021, Acc: 0.990, Base Lr: 5.00e-07
2023-07-10 22:01:58,956 transreid.train INFO: Epoch 30 done. Time per batch: 0.335[s] Speed: 190.9[samples/s]
2023-07-10 22:02:16,644 transreid.train INFO: Epoch[31] Iteration[50/186] Loss: 4.104, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:02:33,158 transreid.train INFO: Epoch[31] Iteration[100/186] Loss: 4.060, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:02:49,839 transreid.train INFO: Epoch[31] Iteration[150/186] Loss: 3.986, Acc: 0.996, Base Lr: 5.00e-07
2023-07-10 22:03:00,386 transreid.train INFO: Epoch 31 done. Time per batch: 0.336[s] Speed: 190.7[samples/s]
2023-07-10 22:03:17,871 transreid.train INFO: Epoch[32] Iteration[50/186] Loss: 4.081, Acc: 0.993, Base Lr: 5.00e-07
2023-07-10 22:03:34,430 transreid.train INFO: Epoch[32] Iteration[100/186] Loss: 4.019, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:03:50,925 transreid.train INFO: Epoch[32] Iteration[150/186] Loss: 3.962, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:04:01,857 transreid.train INFO: Epoch 32 done. Time per batch: 0.334[s] Speed: 191.6[samples/s]
2023-07-10 22:04:19,363 transreid.train INFO: Epoch[33] Iteration[50/186] Loss: 4.107, Acc: 0.989, Base Lr: 5.00e-07
2023-07-10 22:04:35,953 transreid.train INFO: Epoch[33] Iteration[100/186] Loss: 4.054, Acc: 0.992, Base Lr: 5.00e-07
2023-07-10 22:04:52,338 transreid.train INFO: Epoch[33] Iteration[150/186] Loss: 3.978, Acc: 0.993, Base Lr: 5.00e-07
2023-07-10 22:05:03,271 transreid.train INFO: Epoch 33 done. Time per batch: 0.334[s] Speed: 191.8[samples/s]
2023-07-10 22:05:20,839 transreid.train INFO: Epoch[34] Iteration[50/186] Loss: 4.053, Acc: 0.993, Base Lr: 5.00e-07
2023-07-10 22:05:37,366 transreid.train INFO: Epoch[34] Iteration[100/186] Loss: 4.013, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:05:53,837 transreid.train INFO: Epoch[34] Iteration[150/186] Loss: 3.945, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:06:04,449 transreid.train INFO: Epoch 34 done. Time per batch: 0.334[s] Speed: 191.4[samples/s]
2023-07-10 22:06:22,147 transreid.train INFO: Epoch[35] Iteration[50/186] Loss: 4.033, Acc: 0.993, Base Lr: 5.00e-07
2023-07-10 22:06:38,731 transreid.train INFO: Epoch[35] Iteration[100/186] Loss: 3.981, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:06:55,319 transreid.train INFO: Epoch[35] Iteration[150/186] Loss: 3.935, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:07:05,932 transreid.train INFO: Epoch 35 done. Time per batch: 0.336[s] Speed: 190.5[samples/s]
2023-07-10 22:07:23,695 transreid.train INFO: Epoch[36] Iteration[50/186] Loss: 4.072, Acc: 0.992, Base Lr: 5.00e-07
2023-07-10 22:07:40,430 transreid.train INFO: Epoch[36] Iteration[100/186] Loss: 4.000, Acc: 0.993, Base Lr: 5.00e-07
2023-07-10 22:07:56,855 transreid.train INFO: Epoch[36] Iteration[150/186] Loss: 3.939, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:08:07,450 transreid.train INFO: Epoch 36 done. Time per batch: 0.336[s] Speed: 190.4[samples/s]
2023-07-10 22:08:25,079 transreid.train INFO: Epoch[37] Iteration[50/186] Loss: 4.064, Acc: 0.993, Base Lr: 5.00e-07
2023-07-10 22:08:41,633 transreid.train INFO: Epoch[37] Iteration[100/186] Loss: 3.985, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:08:58,289 transreid.train INFO: Epoch[37] Iteration[150/186] Loss: 3.931, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:09:09,287 transreid.train INFO: Epoch 37 done. Time per batch: 0.336[s] Speed: 190.4[samples/s]
2023-07-10 22:09:26,766 transreid.train INFO: Epoch[38] Iteration[50/186] Loss: 4.060, Acc: 0.991, Base Lr: 5.00e-07
2023-07-10 22:09:43,392 transreid.train INFO: Epoch[38] Iteration[100/186] Loss: 3.993, Acc: 0.993, Base Lr: 5.00e-07
2023-07-10 22:09:59,873 transreid.train INFO: Epoch[38] Iteration[150/186] Loss: 3.934, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:10:10,807 transreid.train INFO: Epoch 38 done. Time per batch: 0.334[s] Speed: 191.4[samples/s]
2023-07-10 22:10:28,601 transreid.train INFO: Epoch[39] Iteration[50/186] Loss: 4.020, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:10:45,088 transreid.train INFO: Epoch[39] Iteration[100/186] Loss: 3.976, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:11:01,611 transreid.train INFO: Epoch[39] Iteration[150/186] Loss: 3.923, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:11:12,216 transreid.train INFO: Epoch 39 done. Time per batch: 0.336[s] Speed: 190.7[samples/s]
2023-07-10 22:11:29,925 transreid.train INFO: Epoch[40] Iteration[50/186] Loss: 4.017, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:11:46,571 transreid.train INFO: Epoch[40] Iteration[100/186] Loss: 3.978, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:12:03,356 transreid.train INFO: Epoch[40] Iteration[150/186] Loss: 3.928, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:12:14,254 transreid.train INFO: Epoch 40 done. Time per batch: 0.337[s] Speed: 189.8[samples/s]
2023-07-10 22:12:31,877 transreid.train INFO: Epoch[41] Iteration[50/186] Loss: 3.998, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:12:48,359 transreid.train INFO: Epoch[41] Iteration[100/186] Loss: 3.972, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:13:04,829 transreid.train INFO: Epoch[41] Iteration[150/186] Loss: 3.915, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:13:15,660 transreid.train INFO: Epoch 41 done. Time per batch: 0.334[s] Speed: 191.8[samples/s]
2023-07-10 22:13:33,264 transreid.train INFO: Epoch[42] Iteration[50/186] Loss: 4.016, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:13:49,855 transreid.train INFO: Epoch[42] Iteration[100/186] Loss: 3.964, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:14:06,384 transreid.train INFO: Epoch[42] Iteration[150/186] Loss: 3.912, Acc: 0.996, Base Lr: 5.00e-07
2023-07-10 22:14:17,245 transreid.train INFO: Epoch 42 done. Time per batch: 0.335[s] Speed: 191.2[samples/s]
2023-07-10 22:14:34,935 transreid.train INFO: Epoch[43] Iteration[50/186] Loss: 4.018, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:14:51,603 transreid.train INFO: Epoch[43] Iteration[100/186] Loss: 3.966, Acc: 0.996, Base Lr: 5.00e-07
2023-07-10 22:15:08,112 transreid.train INFO: Epoch[43] Iteration[150/186] Loss: 3.900, Acc: 0.996, Base Lr: 5.00e-07
2023-07-10 22:15:18,657 transreid.train INFO: Epoch 43 done. Time per batch: 0.336[s] Speed: 190.7[samples/s]
2023-07-10 22:15:36,298 transreid.train INFO: Epoch[44] Iteration[50/186] Loss: 3.969, Acc: 0.998, Base Lr: 5.00e-07
2023-07-10 22:15:52,750 transreid.train INFO: Epoch[44] Iteration[100/186] Loss: 3.935, Acc: 0.997, Base Lr: 5.00e-07
2023-07-10 22:16:09,447 transreid.train INFO: Epoch[44] Iteration[150/186] Loss: 3.882, Acc: 0.997, Base Lr: 5.00e-07
2023-07-10 22:16:20,424 transreid.train INFO: Epoch 44 done. Time per batch: 0.336[s] Speed: 190.7[samples/s]
2023-07-10 22:16:38,161 transreid.train INFO: Epoch[45] Iteration[50/186] Loss: 3.984, Acc: 0.993, Base Lr: 5.00e-07
2023-07-10 22:16:54,773 transreid.train INFO: Epoch[45] Iteration[100/186] Loss: 3.939, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:17:11,397 transreid.train INFO: Epoch[45] Iteration[150/186] Loss: 3.887, Acc: 0.996, Base Lr: 5.00e-07
2023-07-10 22:17:21,947 transreid.train INFO: Epoch 45 done. Time per batch: 0.336[s] Speed: 190.4[samples/s]
2023-07-10 22:17:39,618 transreid.train INFO: Epoch[46] Iteration[50/186] Loss: 3.994, Acc: 0.994, Base Lr: 5.00e-07
2023-07-10 22:17:56,112 transreid.train INFO: Epoch[46] Iteration[100/186] Loss: 3.946, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:18:12,625 transreid.train INFO: Epoch[46] Iteration[150/186] Loss: 3.896, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:18:22,863 transreid.train INFO: Epoch 46 done. Time per batch: 0.335[s] Speed: 191.2[samples/s]
2023-07-10 22:18:40,363 transreid.train INFO: Epoch[47] Iteration[50/186] Loss: 3.979, Acc: 0.996, Base Lr: 5.00e-07
2023-07-10 22:18:56,848 transreid.train INFO: Epoch[47] Iteration[100/186] Loss: 3.941, Acc: 0.996, Base Lr: 5.00e-07
2023-07-10 22:19:13,416 transreid.train INFO: Epoch[47] Iteration[150/186] Loss: 3.890, Acc: 0.997, Base Lr: 5.00e-07
2023-07-10 22:19:23,899 transreid.train INFO: Epoch 47 done. Time per batch: 0.334[s] Speed: 191.9[samples/s]
2023-07-10 22:19:41,546 transreid.train INFO: Epoch[48] Iteration[50/186] Loss: 3.975, Acc: 0.996, Base Lr: 5.00e-07
2023-07-10 22:19:58,104 transreid.train INFO: Epoch[48] Iteration[100/186] Loss: 3.943, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:20:14,607 transreid.train INFO: Epoch[48] Iteration[150/186] Loss: 3.873, Acc: 0.996, Base Lr: 5.00e-07
2023-07-10 22:20:25,572 transreid.train INFO: Epoch 48 done. Time per batch: 0.335[s] Speed: 190.9[samples/s]
2023-07-10 22:20:43,370 transreid.train INFO: Epoch[49] Iteration[50/186] Loss: 3.962, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:20:59,889 transreid.train INFO: Epoch[49] Iteration[100/186] Loss: 3.933, Acc: 0.995, Base Lr: 5.00e-07
2023-07-10 22:21:16,487 transreid.train INFO: Epoch[49] Iteration[150/186] Loss: 3.870, Acc: 0.996, Base Lr: 5.00e-07
2023-07-10 22:21:27,106 transreid.train INFO: Epoch 49 done. Time per batch: 0.336[s] Speed: 190.3[samples/s]
2023-07-10 22:21:44,826 transreid.train INFO: Epoch[50] Iteration[50/186] Loss: 3.964, Acc: 0.995, Base Lr: 5.00e-08
2023-07-10 22:22:01,359 transreid.train INFO: Epoch[50] Iteration[100/186] Loss: 3.915, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:22:17,911 transreid.train INFO: Epoch[50] Iteration[150/186] Loss: 3.855, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:22:28,412 transreid.train INFO: Epoch 50 done. Time per batch: 0.335[s] Speed: 191.0[samples/s]
2023-07-10 22:22:46,252 transreid.train INFO: Epoch[51] Iteration[50/186] Loss: 3.966, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:23:02,755 transreid.train INFO: Epoch[51] Iteration[100/186] Loss: 3.918, Acc: 0.997, Base Lr: 5.00e-08
2023-07-10 22:23:19,403 transreid.train INFO: Epoch[51] Iteration[150/186] Loss: 3.854, Acc: 0.997, Base Lr: 5.00e-08
2023-07-10 22:23:29,971 transreid.train INFO: Epoch 51 done. Time per batch: 0.336[s] Speed: 190.3[samples/s]
2023-07-10 22:23:47,747 transreid.train INFO: Epoch[52] Iteration[50/186] Loss: 3.996, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:24:04,221 transreid.train INFO: Epoch[52] Iteration[100/186] Loss: 3.935, Acc: 0.995, Base Lr: 5.00e-08
2023-07-10 22:24:20,813 transreid.train INFO: Epoch[52] Iteration[150/186] Loss: 3.868, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:24:31,413 transreid.train INFO: Epoch 52 done. Time per batch: 0.336[s] Speed: 190.6[samples/s]
2023-07-10 22:24:49,172 transreid.train INFO: Epoch[53] Iteration[50/186] Loss: 3.908, Acc: 0.997, Base Lr: 5.00e-08
2023-07-10 22:25:05,858 transreid.train INFO: Epoch[53] Iteration[100/186] Loss: 3.896, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:25:22,552 transreid.train INFO: Epoch[53] Iteration[150/186] Loss: 3.844, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:25:33,295 transreid.train INFO: Epoch 53 done. Time per batch: 0.338[s] Speed: 189.3[samples/s]
2023-07-10 22:25:51,032 transreid.train INFO: Epoch[54] Iteration[50/186] Loss: 3.963, Acc: 0.997, Base Lr: 5.00e-08
2023-07-10 22:26:07,581 transreid.train INFO: Epoch[54] Iteration[100/186] Loss: 3.930, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:26:24,269 transreid.train INFO: Epoch[54] Iteration[150/186] Loss: 3.860, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:26:35,544 transreid.train INFO: Epoch 54 done. Time per batch: 0.336[s] Speed: 190.2[samples/s]
2023-07-10 22:26:53,081 transreid.train INFO: Epoch[55] Iteration[50/186] Loss: 3.937, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:27:09,612 transreid.train INFO: Epoch[55] Iteration[100/186] Loss: 3.893, Acc: 0.997, Base Lr: 5.00e-08
2023-07-10 22:27:26,191 transreid.train INFO: Epoch[55] Iteration[150/186] Loss: 3.852, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:27:36,778 transreid.train INFO: Epoch 55 done. Time per batch: 0.335[s] Speed: 191.3[samples/s]
2023-07-10 22:27:54,519 transreid.train INFO: Epoch[56] Iteration[50/186] Loss: 3.958, Acc: 0.995, Base Lr: 5.00e-08
2023-07-10 22:28:11,122 transreid.train INFO: Epoch[56] Iteration[100/186] Loss: 3.923, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:28:27,724 transreid.train INFO: Epoch[56] Iteration[150/186] Loss: 3.864, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:28:38,587 transreid.train INFO: Epoch 56 done. Time per batch: 0.336[s] Speed: 190.5[samples/s]
2023-07-10 22:28:56,297 transreid.train INFO: Epoch[57] Iteration[50/186] Loss: 3.947, Acc: 0.995, Base Lr: 5.00e-08
2023-07-10 22:29:12,898 transreid.train INFO: Epoch[57] Iteration[100/186] Loss: 3.912, Acc: 0.995, Base Lr: 5.00e-08
2023-07-10 22:29:29,526 transreid.train INFO: Epoch[57] Iteration[150/186] Loss: 3.865, Acc: 0.995, Base Lr: 5.00e-08
2023-07-10 22:29:40,195 transreid.train INFO: Epoch 57 done. Time per batch: 0.337[s] Speed: 190.1[samples/s]
2023-07-10 22:29:57,752 transreid.train INFO: Epoch[58] Iteration[50/186] Loss: 3.991, Acc: 0.993, Base Lr: 5.00e-08
2023-07-10 22:30:14,238 transreid.train INFO: Epoch[58] Iteration[100/186] Loss: 3.939, Acc: 0.994, Base Lr: 5.00e-08
2023-07-10 22:30:30,861 transreid.train INFO: Epoch[58] Iteration[150/186] Loss: 3.871, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:30:41,392 transreid.train INFO: Epoch 58 done. Time per batch: 0.334[s] Speed: 191.4[samples/s]
2023-07-10 22:30:59,083 transreid.train INFO: Epoch[59] Iteration[50/186] Loss: 3.966, Acc: 0.993, Base Lr: 5.00e-08
2023-07-10 22:31:15,567 transreid.train INFO: Epoch[59] Iteration[100/186] Loss: 3.900, Acc: 0.995, Base Lr: 5.00e-08
2023-07-10 22:31:32,251 transreid.train INFO: Epoch[59] Iteration[150/186] Loss: 3.853, Acc: 0.996, Base Lr: 5.00e-08
2023-07-10 22:31:42,851 transreid.train INFO: Epoch 59 done. Time per batch: 0.336[s] Speed: 190.6[samples/s]
2023-07-10 22:32:00,550 transreid.train INFO: Epoch[60] Iteration[50/186] Loss: 3.982, Acc: 0.995, Base Lr: 5.00e-08
2023-07-10 22:32:17,129 transreid.train INFO: Epoch[60] Iteration[100/186] Loss: 3.941, Acc: 0.997, Base Lr: 5.00e-08
2023-07-10 22:32:33,798 transreid.train INFO: Epoch[60] Iteration[150/186] Loss: 3.877, Acc: 0.997, Base Lr: 5.00e-08
2023-07-10 22:32:44,704 transreid.train INFO: Epoch 60 done. Time per batch: 0.336[s] Speed: 190.4[samples/s]
2023-07-10 22:34:28,733 transreid.train INFO: Validation Results - Epoch: 60
2023-07-10 22:34:28,733 transreid.train INFO: mAP: 79.1%
2023-07-10 22:34:28,733 transreid.train INFO: CMC curve, Rank-1  :90.7%
2023-07-10 22:34:28,733 transreid.train INFO: CMC curve, Rank-5  :96.7%
2023-07-10 22:34:28,733 transreid.train INFO: CMC curve, Rank-10 :98.1%
2023-07-10 22:34:28,734 transreid.train INFO: Total running time: 1:03:16.204514