Skip to content
Permalink
Branch: master
Find file Copy path
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
1206 lines (1205 sloc) 92.8 KB
dataset.py:read_dataset: reading data from data/snli_1.0/train.txt
dataset.py:read_dataset: read 549367 examples
dataset.py:read_dataset: reading data from data/snli_1.0/dev.txt
dataset.py:read_dataset: read 9842 examples
main.py:train_model: {'gpu_id': 0, 'train_file': 'data/snli_1.0/train.txt', 'test_file': 'data/snli_1.0/dev.txt', 'max_num_examples': -1, 'batch_size': 32, 'print_interval': 5000, 'mode': 'train', 'lr': 0.025, 'epochs': 300, 'embedding': 'glove', 'embedding_source': 'glove.840B.300d', 'embedding_size': 300, 'hidden_size': 200, 'output_dir': 'output/snli-basic', 'model_dir': './output', 'seed': 0, 'dropout': 0.2, 'weight_decay': 1e-05, 'intra_attention': False}
main.py:train_model: [Epoch 0 Batch 5000/17173] loss=1.0987, acc=0.3307
main.py:train_model: [Epoch 0 Batch 10000/17173] loss=1.0986, acc=0.3317
main.py:train_model: [Epoch 0 Batch 15000/17173] loss=1.0986, acc=0.3338
main.py:train_model: [Epoch 0] valid loss=1.0986, valid acc=0.3377, best valid acc=0.3377
main.py:train_model: [Epoch 1 Batch 5000/17173] loss=1.0986, acc=0.3336
main.py:train_model: [Epoch 1 Batch 10000/17173] loss=1.0986, acc=0.3320
main.py:train_model: [Epoch 1 Batch 15000/17173] loss=1.0986, acc=0.3321
main.py:train_model: [Epoch 1] valid loss=1.0986, valid acc=0.3377, best valid acc=0.3377
main.py:train_model: [Epoch 2 Batch 5000/17173] loss=1.0986, acc=0.3341
main.py:train_model: [Epoch 2 Batch 10000/17173] loss=1.0986, acc=0.3333
main.py:train_model: [Epoch 2 Batch 15000/17173] loss=1.0986, acc=0.3332
main.py:train_model: [Epoch 2] valid loss=1.0986, valid acc=0.3377, best valid acc=0.3377
main.py:train_model: [Epoch 3 Batch 5000/17173] loss=1.0986, acc=0.3309
main.py:train_model: [Epoch 3 Batch 10000/17173] loss=1.0986, acc=0.3329
main.py:train_model: [Epoch 3 Batch 15000/17173] loss=1.0986, acc=0.3327
main.py:train_model: [Epoch 3] valid loss=1.0986, valid acc=0.3377, best valid acc=0.3377
main.py:train_model: [Epoch 4 Batch 5000/17173] loss=1.0986, acc=0.3332
main.py:train_model: [Epoch 4 Batch 10000/17173] loss=1.0986, acc=0.3339
main.py:train_model: [Epoch 4 Batch 15000/17173] loss=1.0986, acc=0.3322
main.py:train_model: [Epoch 4] valid loss=1.0986, valid acc=0.3377, best valid acc=0.3377
main.py:train_model: [Epoch 5 Batch 5000/17173] loss=1.0986, acc=0.3335
main.py:train_model: [Epoch 5 Batch 10000/17173] loss=1.0986, acc=0.3338
main.py:train_model: [Epoch 5 Batch 15000/17173] loss=1.0986, acc=0.3323
main.py:train_model: [Epoch 5] valid loss=1.0986, valid acc=0.3377, best valid acc=0.3377
main.py:train_model: [Epoch 6 Batch 5000/17173] loss=1.0986, acc=0.3344
main.py:train_model: [Epoch 6 Batch 10000/17173] loss=1.0986, acc=0.3325
main.py:train_model: [Epoch 6 Batch 15000/17173] loss=1.0986, acc=0.3348
main.py:train_model: [Epoch 6] valid loss=0.9901, valid acc=0.4870, best valid acc=0.4870
main.py:train_model: [Epoch 7 Batch 5000/17173] loss=0.9056, acc=0.5723
main.py:train_model: [Epoch 7 Batch 10000/17173] loss=0.8075, acc=0.6444
main.py:train_model: [Epoch 7 Batch 15000/17173] loss=0.7733, acc=0.6661
main.py:train_model: [Epoch 7] valid loss=0.6917, valid acc=0.7162, best valid acc=0.7162
main.py:train_model: [Epoch 8 Batch 5000/17173] loss=0.7263, acc=0.6933
main.py:train_model: [Epoch 8 Batch 10000/17173] loss=0.7108, acc=0.7012
main.py:train_model: [Epoch 8 Batch 15000/17173] loss=0.6886, acc=0.7132
main.py:train_model: [Epoch 8] valid loss=0.6107, valid acc=0.7510, best valid acc=0.7510
main.py:train_model: [Epoch 9 Batch 5000/17173] loss=0.6660, acc=0.7236
main.py:train_model: [Epoch 9 Batch 10000/17173] loss=0.6545, acc=0.7297
main.py:train_model: [Epoch 9 Batch 15000/17173] loss=0.6438, acc=0.7348
main.py:train_model: [Epoch 9] valid loss=0.5894, valid acc=0.7612, best valid acc=0.7612
main.py:train_model: [Epoch 10 Batch 5000/17173] loss=0.6342, acc=0.7394
main.py:train_model: [Epoch 10 Batch 10000/17173] loss=0.6281, acc=0.7437
main.py:train_model: [Epoch 10 Batch 15000/17173] loss=0.6262, acc=0.7430
main.py:train_model: [Epoch 10] valid loss=0.5729, valid acc=0.7716, best valid acc=0.7716
main.py:train_model: [Epoch 11 Batch 5000/17173] loss=0.6189, acc=0.7478
main.py:train_model: [Epoch 11 Batch 10000/17173] loss=0.6121, acc=0.7503
main.py:train_model: [Epoch 11 Batch 15000/17173] loss=0.6096, acc=0.7522
main.py:train_model: [Epoch 11] valid loss=0.5475, valid acc=0.7828, best valid acc=0.7828
main.py:train_model: [Epoch 12 Batch 5000/17173] loss=0.6042, acc=0.7548
main.py:train_model: [Epoch 12 Batch 10000/17173] loss=0.6011, acc=0.7559
main.py:train_model: [Epoch 12 Batch 15000/17173] loss=0.6016, acc=0.7549
main.py:train_model: [Epoch 12] valid loss=0.5607, valid acc=0.7775, best valid acc=0.7828
main.py:train_model: [Epoch 13 Batch 5000/17173] loss=0.5933, acc=0.7593
main.py:train_model: [Epoch 13 Batch 10000/17173] loss=0.5929, acc=0.7591
main.py:train_model: [Epoch 13 Batch 15000/17173] loss=0.5897, acc=0.7607
main.py:train_model: [Epoch 13] valid loss=0.5497, valid acc=0.7817, best valid acc=0.7828
main.py:train_model: [Epoch 14 Batch 5000/17173] loss=0.5867, acc=0.7621
main.py:train_model: [Epoch 14 Batch 10000/17173] loss=0.5859, acc=0.7625
main.py:train_model: [Epoch 14 Batch 15000/17173] loss=0.5824, acc=0.7647
main.py:train_model: [Epoch 14] valid loss=0.5321, valid acc=0.7858, best valid acc=0.7858
main.py:train_model: [Epoch 15 Batch 5000/17173] loss=0.5781, acc=0.7655
main.py:train_model: [Epoch 15 Batch 10000/17173] loss=0.5764, acc=0.7664
main.py:train_model: [Epoch 15 Batch 15000/17173] loss=0.5772, acc=0.7672
main.py:train_model: [Epoch 15] valid loss=0.5255, valid acc=0.7923, best valid acc=0.7923
main.py:train_model: [Epoch 16 Batch 5000/17173] loss=0.5722, acc=0.7681
main.py:train_model: [Epoch 16 Batch 10000/17173] loss=0.5711, acc=0.7710
main.py:train_model: [Epoch 16 Batch 15000/17173] loss=0.5673, acc=0.7714
main.py:train_model: [Epoch 16] valid loss=0.5266, valid acc=0.7919, best valid acc=0.7923
main.py:train_model: [Epoch 17 Batch 5000/17173] loss=0.5672, acc=0.7714
main.py:train_model: [Epoch 17 Batch 10000/17173] loss=0.5652, acc=0.7719
main.py:train_model: [Epoch 17 Batch 15000/17173] loss=0.5659, acc=0.7720
main.py:train_model: [Epoch 17] valid loss=0.5188, valid acc=0.7973, best valid acc=0.7973
main.py:train_model: [Epoch 18 Batch 5000/17173] loss=0.5635, acc=0.7728
main.py:train_model: [Epoch 18 Batch 10000/17173] loss=0.5631, acc=0.7731
main.py:train_model: [Epoch 18 Batch 15000/17173] loss=0.5590, acc=0.7745
main.py:train_model: [Epoch 18] valid loss=0.5220, valid acc=0.7941, best valid acc=0.7973
main.py:train_model: [Epoch 19 Batch 5000/17173] loss=0.5536, acc=0.7766
main.py:train_model: [Epoch 19 Batch 10000/17173] loss=0.5574, acc=0.7757
main.py:train_model: [Epoch 19 Batch 15000/17173] loss=0.5583, acc=0.7748
main.py:train_model: [Epoch 19] valid loss=0.5026, valid acc=0.8012, best valid acc=0.8012
main.py:train_model: [Epoch 20 Batch 5000/17173] loss=0.5538, acc=0.7773
main.py:train_model: [Epoch 20 Batch 10000/17173] loss=0.5510, acc=0.7782
main.py:train_model: [Epoch 20 Batch 15000/17173] loss=0.5507, acc=0.7791
main.py:train_model: [Epoch 20] valid loss=0.5043, valid acc=0.8027, best valid acc=0.8027
main.py:train_model: [Epoch 21 Batch 5000/17173] loss=0.5482, acc=0.7806
main.py:train_model: [Epoch 21 Batch 10000/17173] loss=0.5500, acc=0.7788
main.py:train_model: [Epoch 21 Batch 15000/17173] loss=0.5446, acc=0.7811
main.py:train_model: [Epoch 21] valid loss=0.5046, valid acc=0.8020, best valid acc=0.8027
main.py:train_model: [Epoch 22 Batch 5000/17173] loss=0.5469, acc=0.7811
main.py:train_model: [Epoch 22 Batch 10000/17173] loss=0.5448, acc=0.7810
main.py:train_model: [Epoch 22 Batch 15000/17173] loss=0.5421, acc=0.7822
main.py:train_model: [Epoch 22] valid loss=0.4927, valid acc=0.8075, best valid acc=0.8075
main.py:train_model: [Epoch 23 Batch 5000/17173] loss=0.5439, acc=0.7828
main.py:train_model: [Epoch 23 Batch 10000/17173] loss=0.5415, acc=0.7826
main.py:train_model: [Epoch 23 Batch 15000/17173] loss=0.5393, acc=0.7845
main.py:train_model: [Epoch 23] valid loss=0.5008, valid acc=0.8044, best valid acc=0.8075
main.py:train_model: [Epoch 24 Batch 5000/17173] loss=0.5399, acc=0.7829
main.py:train_model: [Epoch 24 Batch 10000/17173] loss=0.5362, acc=0.7853
main.py:train_model: [Epoch 24 Batch 15000/17173] loss=0.5355, acc=0.7860
main.py:train_model: [Epoch 24] valid loss=0.4924, valid acc=0.8061, best valid acc=0.8075
main.py:train_model: [Epoch 25 Batch 5000/17173] loss=0.5352, acc=0.7847
main.py:train_model: [Epoch 25 Batch 10000/17173] loss=0.5345, acc=0.7872
main.py:train_model: [Epoch 25 Batch 15000/17173] loss=0.5359, acc=0.7850
main.py:train_model: [Epoch 25] valid loss=0.4848, valid acc=0.8085, best valid acc=0.8085
main.py:train_model: [Epoch 26 Batch 5000/17173] loss=0.5297, acc=0.7892
main.py:train_model: [Epoch 26 Batch 10000/17173] loss=0.5330, acc=0.7861
main.py:train_model: [Epoch 26 Batch 15000/17173] loss=0.5298, acc=0.7878
main.py:train_model: [Epoch 26] valid loss=0.4842, valid acc=0.8098, best valid acc=0.8098
main.py:train_model: [Epoch 27 Batch 5000/17173] loss=0.5299, acc=0.7889
main.py:train_model: [Epoch 27 Batch 10000/17173] loss=0.5275, acc=0.7881
main.py:train_model: [Epoch 27 Batch 15000/17173] loss=0.5286, acc=0.7882
main.py:train_model: [Epoch 27] valid loss=0.4818, valid acc=0.8125, best valid acc=0.8125
main.py:train_model: [Epoch 28 Batch 5000/17173] loss=0.5256, acc=0.7895
main.py:train_model: [Epoch 28 Batch 10000/17173] loss=0.5256, acc=0.7897
main.py:train_model: [Epoch 28 Batch 15000/17173] loss=0.5265, acc=0.7890
main.py:train_model: [Epoch 28] valid loss=0.4899, valid acc=0.8099, best valid acc=0.8125
main.py:train_model: [Epoch 29 Batch 5000/17173] loss=0.5234, acc=0.7910
main.py:train_model: [Epoch 29 Batch 10000/17173] loss=0.5222, acc=0.7910
main.py:train_model: [Epoch 29 Batch 15000/17173] loss=0.5229, acc=0.7909
main.py:train_model: [Epoch 29] valid loss=0.4828, valid acc=0.8131, best valid acc=0.8131
main.py:train_model: [Epoch 30 Batch 5000/17173] loss=0.5197, acc=0.7923
main.py:train_model: [Epoch 30 Batch 10000/17173] loss=0.5213, acc=0.7915
main.py:train_model: [Epoch 30 Batch 15000/17173] loss=0.5222, acc=0.7917
main.py:train_model: [Epoch 30] valid loss=0.4688, valid acc=0.8178, best valid acc=0.8178
main.py:train_model: [Epoch 31 Batch 5000/17173] loss=0.5224, acc=0.7918
main.py:train_model: [Epoch 31 Batch 10000/17173] loss=0.5224, acc=0.7913
main.py:train_model: [Epoch 31 Batch 15000/17173] loss=0.5139, acc=0.7960
main.py:train_model: [Epoch 31] valid loss=0.4756, valid acc=0.8153, best valid acc=0.8178
main.py:train_model: [Epoch 32 Batch 5000/17173] loss=0.5145, acc=0.7950
main.py:train_model: [Epoch 32 Batch 10000/17173] loss=0.5140, acc=0.7945
main.py:train_model: [Epoch 32 Batch 15000/17173] loss=0.5193, acc=0.7924
main.py:train_model: [Epoch 32] valid loss=0.4727, valid acc=0.8180, best valid acc=0.8180
main.py:train_model: [Epoch 33 Batch 5000/17173] loss=0.5136, acc=0.7958
main.py:train_model: [Epoch 33 Batch 10000/17173] loss=0.5141, acc=0.7955
main.py:train_model: [Epoch 33 Batch 15000/17173] loss=0.5162, acc=0.7940
main.py:train_model: [Epoch 33] valid loss=0.4695, valid acc=0.8170, best valid acc=0.8180
main.py:train_model: [Epoch 34 Batch 5000/17173] loss=0.5133, acc=0.7965
main.py:train_model: [Epoch 34 Batch 10000/17173] loss=0.5129, acc=0.7951
main.py:train_model: [Epoch 34 Batch 15000/17173] loss=0.5136, acc=0.7959
main.py:train_model: [Epoch 34] valid loss=0.4703, valid acc=0.8182, best valid acc=0.8182
main.py:train_model: [Epoch 35 Batch 5000/17173] loss=0.5117, acc=0.7959
main.py:train_model: [Epoch 35 Batch 10000/17173] loss=0.5104, acc=0.7977
main.py:train_model: [Epoch 35 Batch 15000/17173] loss=0.5112, acc=0.7966
main.py:train_model: [Epoch 35] valid loss=0.4759, valid acc=0.8162, best valid acc=0.8182
main.py:train_model: [Epoch 36 Batch 5000/17173] loss=0.5065, acc=0.7999
main.py:train_model: [Epoch 36 Batch 10000/17173] loss=0.5117, acc=0.7958
main.py:train_model: [Epoch 36 Batch 15000/17173] loss=0.5119, acc=0.7961
main.py:train_model: [Epoch 36] valid loss=0.4687, valid acc=0.8185, best valid acc=0.8185
main.py:train_model: [Epoch 37 Batch 5000/17173] loss=0.5081, acc=0.7979
main.py:train_model: [Epoch 37 Batch 10000/17173] loss=0.5069, acc=0.7975
main.py:train_model: [Epoch 37 Batch 15000/17173] loss=0.5095, acc=0.7971
main.py:train_model: [Epoch 37] valid loss=0.4607, valid acc=0.8221, best valid acc=0.8221
main.py:train_model: [Epoch 38 Batch 5000/17173] loss=0.5059, acc=0.7986
main.py:train_model: [Epoch 38 Batch 10000/17173] loss=0.5052, acc=0.7989
main.py:train_model: [Epoch 38 Batch 15000/17173] loss=0.5058, acc=0.7988
main.py:train_model: [Epoch 38] valid loss=0.4602, valid acc=0.8218, best valid acc=0.8221
main.py:train_model: [Epoch 39 Batch 5000/17173] loss=0.5026, acc=0.8010
main.py:train_model: [Epoch 39 Batch 10000/17173] loss=0.5059, acc=0.7981
main.py:train_model: [Epoch 39 Batch 15000/17173] loss=0.5063, acc=0.7991
main.py:train_model: [Epoch 39] valid loss=0.4627, valid acc=0.8221, best valid acc=0.8221
main.py:train_model: [Epoch 40 Batch 5000/17173] loss=0.5040, acc=0.7997
main.py:train_model: [Epoch 40 Batch 10000/17173] loss=0.5020, acc=0.8006
main.py:train_model: [Epoch 40 Batch 15000/17173] loss=0.5022, acc=0.7997
main.py:train_model: [Epoch 40] valid loss=0.4597, valid acc=0.8223, best valid acc=0.8223
main.py:train_model: [Epoch 41 Batch 5000/17173] loss=0.5025, acc=0.8007
main.py:train_model: [Epoch 41 Batch 10000/17173] loss=0.5026, acc=0.8003
main.py:train_model: [Epoch 41 Batch 15000/17173] loss=0.5002, acc=0.8011
main.py:train_model: [Epoch 41] valid loss=0.4678, valid acc=0.8197, best valid acc=0.8223
main.py:train_model: [Epoch 42 Batch 5000/17173] loss=0.5003, acc=0.8024
main.py:train_model: [Epoch 42 Batch 10000/17173] loss=0.5010, acc=0.8009
main.py:train_model: [Epoch 42 Batch 15000/17173] loss=0.5018, acc=0.8015
main.py:train_model: [Epoch 42] valid loss=0.4559, valid acc=0.8239, best valid acc=0.8239
main.py:train_model: [Epoch 43 Batch 5000/17173] loss=0.4964, acc=0.8036
main.py:train_model: [Epoch 43 Batch 10000/17173] loss=0.5014, acc=0.8008
main.py:train_model: [Epoch 43 Batch 15000/17173] loss=0.4998, acc=0.8029
main.py:train_model: [Epoch 43] valid loss=0.4610, valid acc=0.8236, best valid acc=0.8239
main.py:train_model: [Epoch 44 Batch 5000/17173] loss=0.4965, acc=0.8040
main.py:train_model: [Epoch 44 Batch 10000/17173] loss=0.5016, acc=0.8004
main.py:train_model: [Epoch 44 Batch 15000/17173] loss=0.4972, acc=0.8027
main.py:train_model: [Epoch 44] valid loss=0.4548, valid acc=0.8232, best valid acc=0.8239
main.py:train_model: [Epoch 45 Batch 5000/17173] loss=0.4985, acc=0.8018
main.py:train_model: [Epoch 45 Batch 10000/17173] loss=0.4984, acc=0.8024
main.py:train_model: [Epoch 45 Batch 15000/17173] loss=0.4973, acc=0.8023
main.py:train_model: [Epoch 45] valid loss=0.4553, valid acc=0.8253, best valid acc=0.8253
main.py:train_model: [Epoch 46 Batch 5000/17173] loss=0.4952, acc=0.8044
main.py:train_model: [Epoch 46 Batch 10000/17173] loss=0.4966, acc=0.8031
main.py:train_model: [Epoch 46 Batch 15000/17173] loss=0.4957, acc=0.8044
main.py:train_model: [Epoch 46] valid loss=0.4546, valid acc=0.8267, best valid acc=0.8267
main.py:train_model: [Epoch 47 Batch 5000/17173] loss=0.4930, acc=0.8061
main.py:train_model: [Epoch 47 Batch 10000/17173] loss=0.4933, acc=0.8035
main.py:train_model: [Epoch 47 Batch 15000/17173] loss=0.4956, acc=0.8032
main.py:train_model: [Epoch 47] valid loss=0.4553, valid acc=0.8257, best valid acc=0.8267
main.py:train_model: [Epoch 48 Batch 5000/17173] loss=0.4923, acc=0.8056
main.py:train_model: [Epoch 48 Batch 10000/17173] loss=0.4951, acc=0.8038
main.py:train_model: [Epoch 48 Batch 15000/17173] loss=0.4943, acc=0.8035
main.py:train_model: [Epoch 48] valid loss=0.4486, valid acc=0.8279, best valid acc=0.8279
main.py:train_model: [Epoch 49 Batch 5000/17173] loss=0.4952, acc=0.8030
main.py:train_model: [Epoch 49 Batch 10000/17173] loss=0.4939, acc=0.8053
main.py:train_model: [Epoch 49 Batch 15000/17173] loss=0.4909, acc=0.8066
main.py:train_model: [Epoch 49] valid loss=0.4533, valid acc=0.8269, best valid acc=0.8279
main.py:train_model: [Epoch 50 Batch 5000/17173] loss=0.4902, acc=0.8073
main.py:train_model: [Epoch 50 Batch 10000/17173] loss=0.4900, acc=0.8054
main.py:train_model: [Epoch 50 Batch 15000/17173] loss=0.4920, acc=0.8063
main.py:train_model: [Epoch 50] valid loss=0.4517, valid acc=0.8269, best valid acc=0.8279
main.py:train_model: [Epoch 51 Batch 5000/17173] loss=0.4895, acc=0.8072
main.py:train_model: [Epoch 51 Batch 10000/17173] loss=0.4897, acc=0.8063
main.py:train_model: [Epoch 51 Batch 15000/17173] loss=0.4908, acc=0.8059
main.py:train_model: [Epoch 51] valid loss=0.4498, valid acc=0.8293, best valid acc=0.8293
main.py:train_model: [Epoch 52 Batch 5000/17173] loss=0.4890, acc=0.8069
main.py:train_model: [Epoch 52 Batch 10000/17173] loss=0.4875, acc=0.8066
main.py:train_model: [Epoch 52 Batch 15000/17173] loss=0.4908, acc=0.8046
main.py:train_model: [Epoch 52] valid loss=0.4437, valid acc=0.8312, best valid acc=0.8312
main.py:train_model: [Epoch 53 Batch 5000/17173] loss=0.4879, acc=0.8068
main.py:train_model: [Epoch 53 Batch 10000/17173] loss=0.4872, acc=0.8073
main.py:train_model: [Epoch 53 Batch 15000/17173] loss=0.4888, acc=0.8075
main.py:train_model: [Epoch 53] valid loss=0.4486, valid acc=0.8288, best valid acc=0.8312
main.py:train_model: [Epoch 54 Batch 5000/17173] loss=0.4889, acc=0.8066
main.py:train_model: [Epoch 54 Batch 10000/17173] loss=0.4867, acc=0.8083
main.py:train_model: [Epoch 54 Batch 15000/17173] loss=0.4867, acc=0.8082
main.py:train_model: [Epoch 54] valid loss=0.4513, valid acc=0.8282, best valid acc=0.8312
main.py:train_model: [Epoch 55 Batch 5000/17173] loss=0.4866, acc=0.8075
main.py:train_model: [Epoch 55 Batch 10000/17173] loss=0.4877, acc=0.8075
main.py:train_model: [Epoch 55 Batch 15000/17173] loss=0.4852, acc=0.8080
main.py:train_model: [Epoch 55] valid loss=0.4428, valid acc=0.8297, best valid acc=0.8312
main.py:train_model: [Epoch 56 Batch 5000/17173] loss=0.4859, acc=0.8084
main.py:train_model: [Epoch 56 Batch 10000/17173] loss=0.4868, acc=0.8077
main.py:train_model: [Epoch 56 Batch 15000/17173] loss=0.4849, acc=0.8079
main.py:train_model: [Epoch 56] valid loss=0.4459, valid acc=0.8296, best valid acc=0.8312
main.py:train_model: [Epoch 57 Batch 5000/17173] loss=0.4847, acc=0.8090
main.py:train_model: [Epoch 57 Batch 10000/17173] loss=0.4827, acc=0.8088
main.py:train_model: [Epoch 57 Batch 15000/17173] loss=0.4854, acc=0.8087
main.py:train_model: [Epoch 57] valid loss=0.4445, valid acc=0.8307, best valid acc=0.8312
main.py:train_model: [Epoch 58 Batch 5000/17173] loss=0.4854, acc=0.8090
main.py:train_model: [Epoch 58 Batch 10000/17173] loss=0.4842, acc=0.8079
main.py:train_model: [Epoch 58 Batch 15000/17173] loss=0.4852, acc=0.8086
main.py:train_model: [Epoch 58] valid loss=0.4444, valid acc=0.8309, best valid acc=0.8312
main.py:train_model: [Epoch 59 Batch 5000/17173] loss=0.4832, acc=0.8093
main.py:train_model: [Epoch 59 Batch 10000/17173] loss=0.4849, acc=0.8083
main.py:train_model: [Epoch 59 Batch 15000/17173] loss=0.4804, acc=0.8112
main.py:train_model: [Epoch 59] valid loss=0.4428, valid acc=0.8323, best valid acc=0.8323
main.py:train_model: [Epoch 60 Batch 5000/17173] loss=0.4839, acc=0.8089
main.py:train_model: [Epoch 60 Batch 10000/17173] loss=0.4826, acc=0.8099
main.py:train_model: [Epoch 60 Batch 15000/17173] loss=0.4808, acc=0.8099
main.py:train_model: [Epoch 60] valid loss=0.4464, valid acc=0.8309, best valid acc=0.8323
main.py:train_model: [Epoch 61 Batch 5000/17173] loss=0.4825, acc=0.8091
main.py:train_model: [Epoch 61 Batch 10000/17173] loss=0.4812, acc=0.8091
main.py:train_model: [Epoch 61 Batch 15000/17173] loss=0.4816, acc=0.8104
main.py:train_model: [Epoch 61] valid loss=0.4426, valid acc=0.8316, best valid acc=0.8323
main.py:train_model: [Epoch 62 Batch 5000/17173] loss=0.4786, acc=0.8107
main.py:train_model: [Epoch 62 Batch 10000/17173] loss=0.4817, acc=0.8104
main.py:train_model: [Epoch 62 Batch 15000/17173] loss=0.4825, acc=0.8094
main.py:train_model: [Epoch 62] valid loss=0.4353, valid acc=0.8349, best valid acc=0.8349
main.py:train_model: [Epoch 63 Batch 5000/17173] loss=0.4798, acc=0.8113
main.py:train_model: [Epoch 63 Batch 10000/17173] loss=0.4794, acc=0.8103
main.py:train_model: [Epoch 63 Batch 15000/17173] loss=0.4806, acc=0.8098
main.py:train_model: [Epoch 63] valid loss=0.4358, valid acc=0.8325, best valid acc=0.8349
main.py:train_model: [Epoch 64 Batch 5000/17173] loss=0.4794, acc=0.8117
main.py:train_model: [Epoch 64 Batch 10000/17173] loss=0.4786, acc=0.8112
main.py:train_model: [Epoch 64 Batch 15000/17173] loss=0.4803, acc=0.8113
main.py:train_model: [Epoch 64] valid loss=0.4376, valid acc=0.8351, best valid acc=0.8351
main.py:train_model: [Epoch 65 Batch 5000/17173] loss=0.4815, acc=0.8100
main.py:train_model: [Epoch 65 Batch 10000/17173] loss=0.4806, acc=0.8112
main.py:train_model: [Epoch 65 Batch 15000/17173] loss=0.4783, acc=0.8121
main.py:train_model: [Epoch 65] valid loss=0.4361, valid acc=0.8351, best valid acc=0.8351
main.py:train_model: [Epoch 66 Batch 5000/17173] loss=0.4796, acc=0.8112
main.py:train_model: [Epoch 66 Batch 10000/17173] loss=0.4764, acc=0.8128
main.py:train_model: [Epoch 66 Batch 15000/17173] loss=0.4774, acc=0.8120
main.py:train_model: [Epoch 66] valid loss=0.4364, valid acc=0.8353, best valid acc=0.8353
main.py:train_model: [Epoch 67 Batch 5000/17173] loss=0.4792, acc=0.8121
main.py:train_model: [Epoch 67 Batch 10000/17173] loss=0.4771, acc=0.8127
main.py:train_model: [Epoch 67 Batch 15000/17173] loss=0.4774, acc=0.8119
main.py:train_model: [Epoch 67] valid loss=0.4349, valid acc=0.8330, best valid acc=0.8353
main.py:train_model: [Epoch 68 Batch 5000/17173] loss=0.4753, acc=0.8140
main.py:train_model: [Epoch 68 Batch 10000/17173] loss=0.4792, acc=0.8114
main.py:train_model: [Epoch 68 Batch 15000/17173] loss=0.4751, acc=0.8125
main.py:train_model: [Epoch 68] valid loss=0.4357, valid acc=0.8347, best valid acc=0.8353
main.py:train_model: [Epoch 69 Batch 5000/17173] loss=0.4756, acc=0.8134
main.py:train_model: [Epoch 69 Batch 10000/17173] loss=0.4774, acc=0.8119
main.py:train_model: [Epoch 69 Batch 15000/17173] loss=0.4741, acc=0.8135
main.py:train_model: [Epoch 69] valid loss=0.4337, valid acc=0.8367, best valid acc=0.8367
main.py:train_model: [Epoch 70 Batch 5000/17173] loss=0.4775, acc=0.8119
main.py:train_model: [Epoch 70 Batch 10000/17173] loss=0.4742, acc=0.8133
main.py:train_model: [Epoch 70 Batch 15000/17173] loss=0.4746, acc=0.8138
main.py:train_model: [Epoch 70] valid loss=0.4360, valid acc=0.8339, best valid acc=0.8367
main.py:train_model: [Epoch 71 Batch 5000/17173] loss=0.4748, acc=0.8143
main.py:train_model: [Epoch 71 Batch 10000/17173] loss=0.4736, acc=0.8138
main.py:train_model: [Epoch 71 Batch 15000/17173] loss=0.4775, acc=0.8125
main.py:train_model: [Epoch 71] valid loss=0.4324, valid acc=0.8361, best valid acc=0.8367
main.py:train_model: [Epoch 72 Batch 5000/17173] loss=0.4746, acc=0.8130
main.py:train_model: [Epoch 72 Batch 10000/17173] loss=0.4745, acc=0.8134
main.py:train_model: [Epoch 72 Batch 15000/17173] loss=0.4739, acc=0.8136
main.py:train_model: [Epoch 72] valid loss=0.4327, valid acc=0.8361, best valid acc=0.8367
main.py:train_model: [Epoch 73 Batch 5000/17173] loss=0.4736, acc=0.8142
main.py:train_model: [Epoch 73 Batch 10000/17173] loss=0.4736, acc=0.8137
main.py:train_model: [Epoch 73 Batch 15000/17173] loss=0.4734, acc=0.8140
main.py:train_model: [Epoch 73] valid loss=0.4333, valid acc=0.8364, best valid acc=0.8367
main.py:train_model: [Epoch 74 Batch 5000/17173] loss=0.4734, acc=0.8144
main.py:train_model: [Epoch 74 Batch 10000/17173] loss=0.4743, acc=0.8132
main.py:train_model: [Epoch 74 Batch 15000/17173] loss=0.4721, acc=0.8153
main.py:train_model: [Epoch 74] valid loss=0.4278, valid acc=0.8373, best valid acc=0.8373
main.py:train_model: [Epoch 75 Batch 5000/17173] loss=0.4731, acc=0.8140
main.py:train_model: [Epoch 75 Batch 10000/17173] loss=0.4742, acc=0.8137
main.py:train_model: [Epoch 75 Batch 15000/17173] loss=0.4734, acc=0.8142
main.py:train_model: [Epoch 75] valid loss=0.4294, valid acc=0.8370, best valid acc=0.8373
main.py:train_model: [Epoch 76 Batch 5000/17173] loss=0.4711, acc=0.8147
main.py:train_model: [Epoch 76 Batch 10000/17173] loss=0.4721, acc=0.8141
main.py:train_model: [Epoch 76 Batch 15000/17173] loss=0.4732, acc=0.8139
main.py:train_model: [Epoch 76] valid loss=0.4334, valid acc=0.8354, best valid acc=0.8373
main.py:train_model: [Epoch 77 Batch 5000/17173] loss=0.4724, acc=0.8148
main.py:train_model: [Epoch 77 Batch 10000/17173] loss=0.4707, acc=0.8150
main.py:train_model: [Epoch 77 Batch 15000/17173] loss=0.4710, acc=0.8149
main.py:train_model: [Epoch 77] valid loss=0.4287, valid acc=0.8385, best valid acc=0.8385
main.py:train_model: [Epoch 78 Batch 5000/17173] loss=0.4688, acc=0.8157
main.py:train_model: [Epoch 78 Batch 10000/17173] loss=0.4718, acc=0.8159
main.py:train_model: [Epoch 78 Batch 15000/17173] loss=0.4714, acc=0.8146
main.py:train_model: [Epoch 78] valid loss=0.4291, valid acc=0.8384, best valid acc=0.8385
main.py:train_model: [Epoch 79 Batch 5000/17173] loss=0.4729, acc=0.8158
main.py:train_model: [Epoch 79 Batch 10000/17173] loss=0.4716, acc=0.8156
main.py:train_model: [Epoch 79 Batch 15000/17173] loss=0.4716, acc=0.8147
main.py:train_model: [Epoch 79] valid loss=0.4302, valid acc=0.8369, best valid acc=0.8385
main.py:train_model: [Epoch 80 Batch 5000/17173] loss=0.4686, acc=0.8160
main.py:train_model: [Epoch 80 Batch 10000/17173] loss=0.4716, acc=0.8141
main.py:train_model: [Epoch 80 Batch 15000/17173] loss=0.4719, acc=0.8148
main.py:train_model: [Epoch 80] valid loss=0.4300, valid acc=0.8390, best valid acc=0.8390
main.py:train_model: [Epoch 81 Batch 5000/17173] loss=0.4694, acc=0.8155
main.py:train_model: [Epoch 81 Batch 10000/17173] loss=0.4699, acc=0.8157
main.py:train_model: [Epoch 81 Batch 15000/17173] loss=0.4703, acc=0.8159
main.py:train_model: [Epoch 81] valid loss=0.4233, valid acc=0.8398, best valid acc=0.8398
main.py:train_model: [Epoch 82 Batch 5000/17173] loss=0.4654, acc=0.8169
main.py:train_model: [Epoch 82 Batch 10000/17173] loss=0.4714, acc=0.8151
main.py:train_model: [Epoch 82 Batch 15000/17173] loss=0.4704, acc=0.8144
main.py:train_model: [Epoch 82] valid loss=0.4285, valid acc=0.8390, best valid acc=0.8398
main.py:train_model: [Epoch 83 Batch 5000/17173] loss=0.4692, acc=0.8169
main.py:train_model: [Epoch 83 Batch 10000/17173] loss=0.4681, acc=0.8164
main.py:train_model: [Epoch 83 Batch 15000/17173] loss=0.4676, acc=0.8159
main.py:train_model: [Epoch 83] valid loss=0.4298, valid acc=0.8394, best valid acc=0.8398
main.py:train_model: [Epoch 84 Batch 5000/17173] loss=0.4659, acc=0.8177
main.py:train_model: [Epoch 84 Batch 10000/17173] loss=0.4687, acc=0.8159
main.py:train_model: [Epoch 84 Batch 15000/17173] loss=0.4699, acc=0.8150
main.py:train_model: [Epoch 84] valid loss=0.4291, valid acc=0.8382, best valid acc=0.8398
main.py:train_model: [Epoch 85 Batch 5000/17173] loss=0.4664, acc=0.8169
main.py:train_model: [Epoch 85 Batch 10000/17173] loss=0.4666, acc=0.8175
main.py:train_model: [Epoch 85 Batch 15000/17173] loss=0.4710, acc=0.8152
main.py:train_model: [Epoch 85] valid loss=0.4283, valid acc=0.8387, best valid acc=0.8398
main.py:train_model: [Epoch 86 Batch 5000/17173] loss=0.4669, acc=0.8166
main.py:train_model: [Epoch 86 Batch 10000/17173] loss=0.4662, acc=0.8160
main.py:train_model: [Epoch 86 Batch 15000/17173] loss=0.4654, acc=0.8186
main.py:train_model: [Epoch 86] valid loss=0.4243, valid acc=0.8409, best valid acc=0.8409
main.py:train_model: [Epoch 87 Batch 5000/17173] loss=0.4665, acc=0.8172
main.py:train_model: [Epoch 87 Batch 10000/17173] loss=0.4661, acc=0.8160
main.py:train_model: [Epoch 87 Batch 15000/17173] loss=0.4688, acc=0.8158
main.py:train_model: [Epoch 87] valid loss=0.4262, valid acc=0.8403, best valid acc=0.8409
main.py:train_model: [Epoch 88 Batch 5000/17173] loss=0.4692, acc=0.8157
main.py:train_model: [Epoch 88 Batch 10000/17173] loss=0.4668, acc=0.8169
main.py:train_model: [Epoch 88 Batch 15000/17173] loss=0.4662, acc=0.8170
main.py:train_model: [Epoch 88] valid loss=0.4364, valid acc=0.8353, best valid acc=0.8409
main.py:train_model: [Epoch 89 Batch 5000/17173] loss=0.4643, acc=0.8172
main.py:train_model: [Epoch 89 Batch 10000/17173] loss=0.4673, acc=0.8170
main.py:train_model: [Epoch 89 Batch 15000/17173] loss=0.4658, acc=0.8177
main.py:train_model: [Epoch 89] valid loss=0.4235, valid acc=0.8395, best valid acc=0.8409
main.py:train_model: [Epoch 90 Batch 5000/17173] loss=0.4652, acc=0.8169
main.py:train_model: [Epoch 90 Batch 10000/17173] loss=0.4659, acc=0.8176
main.py:train_model: [Epoch 90 Batch 15000/17173] loss=0.4668, acc=0.8166
main.py:train_model: [Epoch 90] valid loss=0.4220, valid acc=0.8413, best valid acc=0.8413
main.py:train_model: [Epoch 91 Batch 5000/17173] loss=0.4623, acc=0.8184
main.py:train_model: [Epoch 91 Batch 10000/17173] loss=0.4652, acc=0.8176
main.py:train_model: [Epoch 91 Batch 15000/17173] loss=0.4669, acc=0.8161
main.py:train_model: [Epoch 91] valid loss=0.4234, valid acc=0.8395, best valid acc=0.8413
main.py:train_model: [Epoch 92 Batch 5000/17173] loss=0.4632, acc=0.8186
main.py:train_model: [Epoch 92 Batch 10000/17173] loss=0.4630, acc=0.8191
main.py:train_model: [Epoch 92 Batch 15000/17173] loss=0.4678, acc=0.8167
main.py:train_model: [Epoch 92] valid loss=0.4211, valid acc=0.8406, best valid acc=0.8413
main.py:train_model: [Epoch 93 Batch 5000/17173] loss=0.4603, acc=0.8205
main.py:train_model: [Epoch 93 Batch 10000/17173] loss=0.4667, acc=0.8166
main.py:train_model: [Epoch 93 Batch 15000/17173] loss=0.4651, acc=0.8181
main.py:train_model: [Epoch 93] valid loss=0.4210, valid acc=0.8394, best valid acc=0.8413
main.py:train_model: [Epoch 94 Batch 5000/17173] loss=0.4642, acc=0.8183
main.py:train_model: [Epoch 94 Batch 10000/17173] loss=0.4643, acc=0.8183
main.py:train_model: [Epoch 94 Batch 15000/17173] loss=0.4660, acc=0.8163
main.py:train_model: [Epoch 94] valid loss=0.4215, valid acc=0.8407, best valid acc=0.8413
main.py:train_model: [Epoch 95 Batch 5000/17173] loss=0.4626, acc=0.8181
main.py:train_model: [Epoch 95 Batch 10000/17173] loss=0.4628, acc=0.8183
main.py:train_model: [Epoch 95 Batch 15000/17173] loss=0.4635, acc=0.8177
main.py:train_model: [Epoch 95] valid loss=0.4212, valid acc=0.8388, best valid acc=0.8413
main.py:train_model: [Epoch 96 Batch 5000/17173] loss=0.4648, acc=0.8180
main.py:train_model: [Epoch 96 Batch 10000/17173] loss=0.4605, acc=0.8199
main.py:train_model: [Epoch 96 Batch 15000/17173] loss=0.4622, acc=0.8186
main.py:train_model: [Epoch 96] valid loss=0.4244, valid acc=0.8392, best valid acc=0.8413
main.py:train_model: [Epoch 97 Batch 5000/17173] loss=0.4630, acc=0.8191
main.py:train_model: [Epoch 97 Batch 10000/17173] loss=0.4655, acc=0.8174
main.py:train_model: [Epoch 97 Batch 15000/17173] loss=0.4650, acc=0.8171
main.py:train_model: [Epoch 97] valid loss=0.4251, valid acc=0.8398, best valid acc=0.8413
main.py:train_model: [Epoch 98 Batch 5000/17173] loss=0.4592, acc=0.8207
main.py:train_model: [Epoch 98 Batch 10000/17173] loss=0.4637, acc=0.8187
main.py:train_model: [Epoch 98 Batch 15000/17173] loss=0.4632, acc=0.8193
main.py:train_model: [Epoch 98] valid loss=0.4182, valid acc=0.8420, best valid acc=0.8420
main.py:train_model: [Epoch 99 Batch 5000/17173] loss=0.4608, acc=0.8200
main.py:train_model: [Epoch 99 Batch 10000/17173] loss=0.4624, acc=0.8195
main.py:train_model: [Epoch 99 Batch 15000/17173] loss=0.4634, acc=0.8184
main.py:train_model: [Epoch 99] valid loss=0.4209, valid acc=0.8404, best valid acc=0.8420
main.py:train_model: [Epoch 100 Batch 5000/17173] loss=0.4643, acc=0.8174
main.py:train_model: [Epoch 100 Batch 10000/17173] loss=0.4609, acc=0.8198
main.py:train_model: [Epoch 100 Batch 15000/17173] loss=0.4595, acc=0.8204
main.py:train_model: [Epoch 100] valid loss=0.4178, valid acc=0.8419, best valid acc=0.8420
main.py:train_model: [Epoch 101 Batch 5000/17173] loss=0.4593, acc=0.8194
main.py:train_model: [Epoch 101 Batch 10000/17173] loss=0.4623, acc=0.8193
main.py:train_model: [Epoch 101 Batch 15000/17173] loss=0.4618, acc=0.8197
main.py:train_model: [Epoch 101] valid loss=0.4219, valid acc=0.8402, best valid acc=0.8420
main.py:train_model: [Epoch 102 Batch 5000/17173] loss=0.4586, acc=0.8207
main.py:train_model: [Epoch 102 Batch 10000/17173] loss=0.4596, acc=0.8196
main.py:train_model: [Epoch 102 Batch 15000/17173] loss=0.4623, acc=0.8199
main.py:train_model: [Epoch 102] valid loss=0.4157, valid acc=0.8432, best valid acc=0.8432
main.py:train_model: [Epoch 103 Batch 5000/17173] loss=0.4595, acc=0.8201
main.py:train_model: [Epoch 103 Batch 10000/17173] loss=0.4623, acc=0.8193
main.py:train_model: [Epoch 103 Batch 15000/17173] loss=0.4618, acc=0.8192
main.py:train_model: [Epoch 103] valid loss=0.4195, valid acc=0.8408, best valid acc=0.8432
main.py:train_model: [Epoch 104 Batch 5000/17173] loss=0.4595, acc=0.8196
main.py:train_model: [Epoch 104 Batch 10000/17173] loss=0.4607, acc=0.8187
main.py:train_model: [Epoch 104 Batch 15000/17173] loss=0.4597, acc=0.8198
main.py:train_model: [Epoch 104] valid loss=0.4182, valid acc=0.8410, best valid acc=0.8432
main.py:train_model: [Epoch 105 Batch 5000/17173] loss=0.4591, acc=0.8193
main.py:train_model: [Epoch 105 Batch 10000/17173] loss=0.4613, acc=0.8196
main.py:train_model: [Epoch 105 Batch 15000/17173] loss=0.4601, acc=0.8215
main.py:train_model: [Epoch 105] valid loss=0.4205, valid acc=0.8409, best valid acc=0.8432
main.py:train_model: [Epoch 106 Batch 5000/17173] loss=0.4572, acc=0.8214
main.py:train_model: [Epoch 106 Batch 10000/17173] loss=0.4593, acc=0.8209
main.py:train_model: [Epoch 106 Batch 15000/17173] loss=0.4606, acc=0.8192
main.py:train_model: [Epoch 106] valid loss=0.4178, valid acc=0.8415, best valid acc=0.8432
main.py:train_model: [Epoch 107 Batch 5000/17173] loss=0.4608, acc=0.8193
main.py:train_model: [Epoch 107 Batch 10000/17173] loss=0.4590, acc=0.8206
main.py:train_model: [Epoch 107 Batch 15000/17173] loss=0.4603, acc=0.8192
main.py:train_model: [Epoch 107] valid loss=0.4243, valid acc=0.8392, best valid acc=0.8432
main.py:train_model: [Epoch 108 Batch 5000/17173] loss=0.4574, acc=0.8209
main.py:train_model: [Epoch 108 Batch 10000/17173] loss=0.4594, acc=0.8200
main.py:train_model: [Epoch 108 Batch 15000/17173] loss=0.4602, acc=0.8203
main.py:train_model: [Epoch 108] valid loss=0.4180, valid acc=0.8421, best valid acc=0.8432
main.py:train_model: [Epoch 109 Batch 5000/17173] loss=0.4588, acc=0.8209
main.py:train_model: [Epoch 109 Batch 10000/17173] loss=0.4585, acc=0.8202
main.py:train_model: [Epoch 109 Batch 15000/17173] loss=0.4593, acc=0.8206
main.py:train_model: [Epoch 109] valid loss=0.4175, valid acc=0.8412, best valid acc=0.8432
main.py:train_model: [Epoch 110 Batch 5000/17173] loss=0.4574, acc=0.8205
main.py:train_model: [Epoch 110 Batch 10000/17173] loss=0.4572, acc=0.8213
main.py:train_model: [Epoch 110 Batch 15000/17173] loss=0.4605, acc=0.8199
main.py:train_model: [Epoch 110] valid loss=0.4186, valid acc=0.8402, best valid acc=0.8432
main.py:train_model: [Epoch 111 Batch 5000/17173] loss=0.4585, acc=0.8194
main.py:train_model: [Epoch 111 Batch 10000/17173] loss=0.4581, acc=0.8209
main.py:train_model: [Epoch 111 Batch 15000/17173] loss=0.4575, acc=0.8215
main.py:train_model: [Epoch 111] valid loss=0.4177, valid acc=0.8418, best valid acc=0.8432
main.py:train_model: [Epoch 112 Batch 5000/17173] loss=0.4572, acc=0.8208
main.py:train_model: [Epoch 112 Batch 10000/17173] loss=0.4582, acc=0.8205
main.py:train_model: [Epoch 112 Batch 15000/17173] loss=0.4595, acc=0.8206
main.py:train_model: [Epoch 112] valid loss=0.4171, valid acc=0.8417, best valid acc=0.8432
main.py:train_model: [Epoch 113 Batch 5000/17173] loss=0.4563, acc=0.8215
main.py:train_model: [Epoch 113 Batch 10000/17173] loss=0.4578, acc=0.8219
main.py:train_model: [Epoch 113 Batch 15000/17173] loss=0.4577, acc=0.8209
main.py:train_model: [Epoch 113] valid loss=0.4207, valid acc=0.8430, best valid acc=0.8432
main.py:train_model: [Epoch 114 Batch 5000/17173] loss=0.4536, acc=0.8230
main.py:train_model: [Epoch 114 Batch 10000/17173] loss=0.4560, acc=0.8214
main.py:train_model: [Epoch 114 Batch 15000/17173] loss=0.4588, acc=0.8203
main.py:train_model: [Epoch 114] valid loss=0.4259, valid acc=0.8402, best valid acc=0.8432
main.py:train_model: [Epoch 115 Batch 5000/17173] loss=0.4563, acc=0.8208
main.py:train_model: [Epoch 115 Batch 10000/17173] loss=0.4552, acc=0.8222
main.py:train_model: [Epoch 115 Batch 15000/17173] loss=0.4591, acc=0.8200
main.py:train_model: [Epoch 115] valid loss=0.4188, valid acc=0.8423, best valid acc=0.8432
main.py:train_model: [Epoch 116 Batch 5000/17173] loss=0.4551, acc=0.8221
main.py:train_model: [Epoch 116 Batch 10000/17173] loss=0.4600, acc=0.8205
main.py:train_model: [Epoch 116 Batch 15000/17173] loss=0.4563, acc=0.8223
main.py:train_model: [Epoch 116] valid loss=0.4150, valid acc=0.8427, best valid acc=0.8432
main.py:train_model: [Epoch 117 Batch 5000/17173] loss=0.4547, acc=0.8229
main.py:train_model: [Epoch 117 Batch 10000/17173] loss=0.4590, acc=0.8193
main.py:train_model: [Epoch 117 Batch 15000/17173] loss=0.4558, acc=0.8216
main.py:train_model: [Epoch 117] valid loss=0.4184, valid acc=0.8421, best valid acc=0.8432
main.py:train_model: [Epoch 118 Batch 5000/17173] loss=0.4546, acc=0.8230
main.py:train_model: [Epoch 118 Batch 10000/17173] loss=0.4590, acc=0.8202
main.py:train_model: [Epoch 118 Batch 15000/17173] loss=0.4553, acc=0.8229
main.py:train_model: [Epoch 118] valid loss=0.4171, valid acc=0.8437, best valid acc=0.8437
main.py:train_model: [Epoch 119 Batch 5000/17173] loss=0.4570, acc=0.8214
main.py:train_model: [Epoch 119 Batch 10000/17173] loss=0.4536, acc=0.8226
main.py:train_model: [Epoch 119 Batch 15000/17173] loss=0.4575, acc=0.8201
main.py:train_model: [Epoch 119] valid loss=0.4149, valid acc=0.8430, best valid acc=0.8437
main.py:train_model: [Epoch 120 Batch 5000/17173] loss=0.4548, acc=0.8230
main.py:train_model: [Epoch 120 Batch 10000/17173] loss=0.4565, acc=0.8210
main.py:train_model: [Epoch 120 Batch 15000/17173] loss=0.4543, acc=0.8228
main.py:train_model: [Epoch 120] valid loss=0.4166, valid acc=0.8429, best valid acc=0.8437
main.py:train_model: [Epoch 121 Batch 5000/17173] loss=0.4572, acc=0.8209
main.py:train_model: [Epoch 121 Batch 10000/17173] loss=0.4552, acc=0.8224
main.py:train_model: [Epoch 121 Batch 15000/17173] loss=0.4532, acc=0.8227
main.py:train_model: [Epoch 121] valid loss=0.4188, valid acc=0.8434, best valid acc=0.8437
main.py:train_model: [Epoch 122 Batch 5000/17173] loss=0.4519, acc=0.8233
main.py:train_model: [Epoch 122 Batch 10000/17173] loss=0.4544, acc=0.8213
main.py:train_model: [Epoch 122 Batch 15000/17173] loss=0.4548, acc=0.8214
main.py:train_model: [Epoch 122] valid loss=0.4160, valid acc=0.8435, best valid acc=0.8437
main.py:train_model: [Epoch 123 Batch 5000/17173] loss=0.4516, acc=0.8231
main.py:train_model: [Epoch 123 Batch 10000/17173] loss=0.4581, acc=0.8209
main.py:train_model: [Epoch 123 Batch 15000/17173] loss=0.4526, acc=0.8226
main.py:train_model: [Epoch 123] valid loss=0.4138, valid acc=0.8445, best valid acc=0.8445
main.py:train_model: [Epoch 124 Batch 5000/17173] loss=0.4538, acc=0.8231
main.py:train_model: [Epoch 124 Batch 10000/17173] loss=0.4556, acc=0.8213
main.py:train_model: [Epoch 124 Batch 15000/17173] loss=0.4519, acc=0.8237
main.py:train_model: [Epoch 124] valid loss=0.4158, valid acc=0.8447, best valid acc=0.8447
main.py:train_model: [Epoch 125 Batch 5000/17173] loss=0.4531, acc=0.8233
main.py:train_model: [Epoch 125 Batch 10000/17173] loss=0.4525, acc=0.8241
main.py:train_model: [Epoch 125 Batch 15000/17173] loss=0.4559, acc=0.8219
main.py:train_model: [Epoch 125] valid loss=0.4180, valid acc=0.8425, best valid acc=0.8447
main.py:train_model: [Epoch 126 Batch 5000/17173] loss=0.4529, acc=0.8235
main.py:train_model: [Epoch 126 Batch 10000/17173] loss=0.4546, acc=0.8225
main.py:train_model: [Epoch 126 Batch 15000/17173] loss=0.4545, acc=0.8232
main.py:train_model: [Epoch 126] valid loss=0.4128, valid acc=0.8446, best valid acc=0.8447
main.py:train_model: [Epoch 127 Batch 5000/17173] loss=0.4533, acc=0.8219
main.py:train_model: [Epoch 127 Batch 10000/17173] loss=0.4540, acc=0.8232
main.py:train_model: [Epoch 127 Batch 15000/17173] loss=0.4522, acc=0.8232
main.py:train_model: [Epoch 127] valid loss=0.4154, valid acc=0.8433, best valid acc=0.8447
main.py:train_model: [Epoch 128 Batch 5000/17173] loss=0.4536, acc=0.8223
main.py:train_model: [Epoch 128 Batch 10000/17173] loss=0.4520, acc=0.8234
main.py:train_model: [Epoch 128 Batch 15000/17173] loss=0.4554, acc=0.8216
main.py:train_model: [Epoch 128] valid loss=0.4159, valid acc=0.8429, best valid acc=0.8447
main.py:train_model: [Epoch 129 Batch 5000/17173] loss=0.4525, acc=0.8240
main.py:train_model: [Epoch 129 Batch 10000/17173] loss=0.4536, acc=0.8225
main.py:train_model: [Epoch 129 Batch 15000/17173] loss=0.4526, acc=0.8231
main.py:train_model: [Epoch 129] valid loss=0.4145, valid acc=0.8438, best valid acc=0.8447
main.py:train_model: [Epoch 130 Batch 5000/17173] loss=0.4529, acc=0.8235
main.py:train_model: [Epoch 130 Batch 10000/17173] loss=0.4542, acc=0.8227
main.py:train_model: [Epoch 130 Batch 15000/17173] loss=0.4491, acc=0.8240
main.py:train_model: [Epoch 130] valid loss=0.4125, valid acc=0.8428, best valid acc=0.8447
main.py:train_model: [Epoch 131 Batch 5000/17173] loss=0.4525, acc=0.8242
main.py:train_model: [Epoch 131 Batch 10000/17173] loss=0.4515, acc=0.8224
main.py:train_model: [Epoch 131 Batch 15000/17173] loss=0.4509, acc=0.8243
main.py:train_model: [Epoch 131] valid loss=0.4074, valid acc=0.8454, best valid acc=0.8454
main.py:train_model: [Epoch 132 Batch 5000/17173] loss=0.4516, acc=0.8236
main.py:train_model: [Epoch 132 Batch 10000/17173] loss=0.4509, acc=0.8235
main.py:train_model: [Epoch 132 Batch 15000/17173] loss=0.4517, acc=0.8232
main.py:train_model: [Epoch 132] valid loss=0.4133, valid acc=0.8446, best valid acc=0.8454
main.py:train_model: [Epoch 133 Batch 5000/17173] loss=0.4502, acc=0.8247
main.py:train_model: [Epoch 133 Batch 10000/17173] loss=0.4535, acc=0.8229
main.py:train_model: [Epoch 133 Batch 15000/17173] loss=0.4509, acc=0.8234
main.py:train_model: [Epoch 133] valid loss=0.4087, valid acc=0.8451, best valid acc=0.8454
main.py:train_model: [Epoch 134 Batch 5000/17173] loss=0.4486, acc=0.8254
main.py:train_model: [Epoch 134 Batch 10000/17173] loss=0.4521, acc=0.8228
main.py:train_model: [Epoch 134 Batch 15000/17173] loss=0.4552, acc=0.8222
main.py:train_model: [Epoch 134] valid loss=0.4080, valid acc=0.8450, best valid acc=0.8454
main.py:train_model: [Epoch 135 Batch 5000/17173] loss=0.4527, acc=0.8226
main.py:train_model: [Epoch 135 Batch 10000/17173] loss=0.4502, acc=0.8247
main.py:train_model: [Epoch 135 Batch 15000/17173] loss=0.4530, acc=0.8227
main.py:train_model: [Epoch 135] valid loss=0.4054, valid acc=0.8474, best valid acc=0.8474
main.py:train_model: [Epoch 136 Batch 5000/17173] loss=0.4517, acc=0.8242
main.py:train_model: [Epoch 136 Batch 10000/17173] loss=0.4513, acc=0.8235
main.py:train_model: [Epoch 136 Batch 15000/17173] loss=0.4518, acc=0.8231
main.py:train_model: [Epoch 136] valid loss=0.4106, valid acc=0.8447, best valid acc=0.8474
main.py:train_model: [Epoch 137 Batch 5000/17173] loss=0.4495, acc=0.8248
main.py:train_model: [Epoch 137 Batch 10000/17173] loss=0.4526, acc=0.8237
main.py:train_model: [Epoch 137 Batch 15000/17173] loss=0.4523, acc=0.8233
main.py:train_model: [Epoch 137] valid loss=0.4084, valid acc=0.8464, best valid acc=0.8474
main.py:train_model: [Epoch 138 Batch 5000/17173] loss=0.4488, acc=0.8239
main.py:train_model: [Epoch 138 Batch 10000/17173] loss=0.4514, acc=0.8234
main.py:train_model: [Epoch 138 Batch 15000/17173] loss=0.4542, acc=0.8230
main.py:train_model: [Epoch 138] valid loss=0.4150, valid acc=0.8444, best valid acc=0.8474
main.py:train_model: [Epoch 139 Batch 5000/17173] loss=0.4482, acc=0.8250
main.py:train_model: [Epoch 139 Batch 10000/17173] loss=0.4515, acc=0.8234
main.py:train_model: [Epoch 139 Batch 15000/17173] loss=0.4546, acc=0.8229
main.py:train_model: [Epoch 139] valid loss=0.4097, valid acc=0.8453, best valid acc=0.8474
main.py:train_model: [Epoch 140 Batch 5000/17173] loss=0.4491, acc=0.8243
main.py:train_model: [Epoch 140 Batch 10000/17173] loss=0.4511, acc=0.8234
main.py:train_model: [Epoch 140 Batch 15000/17173] loss=0.4506, acc=0.8245
main.py:train_model: [Epoch 140] valid loss=0.4120, valid acc=0.8447, best valid acc=0.8474
main.py:train_model: [Epoch 141 Batch 5000/17173] loss=0.4509, acc=0.8229
main.py:train_model: [Epoch 141 Batch 10000/17173] loss=0.4521, acc=0.8234
main.py:train_model: [Epoch 141 Batch 15000/17173] loss=0.4504, acc=0.8241
main.py:train_model: [Epoch 141] valid loss=0.4096, valid acc=0.8450, best valid acc=0.8474
main.py:train_model: [Epoch 142 Batch 5000/17173] loss=0.4501, acc=0.8255
main.py:train_model: [Epoch 142 Batch 10000/17173] loss=0.4487, acc=0.8242
main.py:train_model: [Epoch 142 Batch 15000/17173] loss=0.4493, acc=0.8248
main.py:train_model: [Epoch 142] valid loss=0.4140, valid acc=0.8441, best valid acc=0.8474
main.py:train_model: [Epoch 143 Batch 5000/17173] loss=0.4475, acc=0.8259
main.py:train_model: [Epoch 143 Batch 10000/17173] loss=0.4506, acc=0.8238
main.py:train_model: [Epoch 143 Batch 15000/17173] loss=0.4504, acc=0.8231
main.py:train_model: [Epoch 143] valid loss=0.4108, valid acc=0.8431, best valid acc=0.8474
main.py:train_model: [Epoch 144 Batch 5000/17173] loss=0.4474, acc=0.8255
main.py:train_model: [Epoch 144 Batch 10000/17173] loss=0.4502, acc=0.8245
main.py:train_model: [Epoch 144 Batch 15000/17173] loss=0.4491, acc=0.8248
main.py:train_model: [Epoch 144] valid loss=0.4065, valid acc=0.8446, best valid acc=0.8474
main.py:train_model: [Epoch 145 Batch 5000/17173] loss=0.4472, acc=0.8259
main.py:train_model: [Epoch 145 Batch 10000/17173] loss=0.4513, acc=0.8239
main.py:train_model: [Epoch 145 Batch 15000/17173] loss=0.4496, acc=0.8251
main.py:train_model: [Epoch 145] valid loss=0.4069, valid acc=0.8452, best valid acc=0.8474
main.py:train_model: [Epoch 146 Batch 5000/17173] loss=0.4473, acc=0.8253
main.py:train_model: [Epoch 146 Batch 10000/17173] loss=0.4509, acc=0.8240
main.py:train_model: [Epoch 146 Batch 15000/17173] loss=0.4507, acc=0.8241
main.py:train_model: [Epoch 146] valid loss=0.4097, valid acc=0.8426, best valid acc=0.8474
main.py:train_model: [Epoch 147 Batch 5000/17173] loss=0.4484, acc=0.8243
main.py:train_model: [Epoch 147 Batch 10000/17173] loss=0.4482, acc=0.8255
main.py:train_model: [Epoch 147 Batch 15000/17173] loss=0.4514, acc=0.8241
main.py:train_model: [Epoch 147] valid loss=0.4092, valid acc=0.8454, best valid acc=0.8474
main.py:train_model: [Epoch 148 Batch 5000/17173] loss=0.4516, acc=0.8229
main.py:train_model: [Epoch 148 Batch 10000/17173] loss=0.4477, acc=0.8245
main.py:train_model: [Epoch 148 Batch 15000/17173] loss=0.4483, acc=0.8250
main.py:train_model: [Epoch 148] valid loss=0.4087, valid acc=0.8452, best valid acc=0.8474
main.py:train_model: [Epoch 149 Batch 5000/17173] loss=0.4465, acc=0.8254
main.py:train_model: [Epoch 149 Batch 10000/17173] loss=0.4507, acc=0.8249
main.py:train_model: [Epoch 149 Batch 15000/17173] loss=0.4494, acc=0.8245
main.py:train_model: [Epoch 149] valid loss=0.4096, valid acc=0.8452, best valid acc=0.8474
main.py:train_model: [Epoch 150 Batch 5000/17173] loss=0.4482, acc=0.8247
main.py:train_model: [Epoch 150 Batch 10000/17173] loss=0.4474, acc=0.8259
main.py:train_model: [Epoch 150 Batch 15000/17173] loss=0.4462, acc=0.8270
main.py:train_model: [Epoch 150] valid loss=0.4073, valid acc=0.8458, best valid acc=0.8474
main.py:train_model: [Epoch 151 Batch 5000/17173] loss=0.4489, acc=0.8247
main.py:train_model: [Epoch 151 Batch 10000/17173] loss=0.4504, acc=0.8238
main.py:train_model: [Epoch 151 Batch 15000/17173] loss=0.4446, acc=0.8261
main.py:train_model: [Epoch 151] valid loss=0.4080, valid acc=0.8459, best valid acc=0.8474
main.py:train_model: [Epoch 152 Batch 5000/17173] loss=0.4477, acc=0.8256
main.py:train_model: [Epoch 152 Batch 10000/17173] loss=0.4496, acc=0.8246
main.py:train_model: [Epoch 152 Batch 15000/17173] loss=0.4472, acc=0.8260
main.py:train_model: [Epoch 152] valid loss=0.4071, valid acc=0.8459, best valid acc=0.8474
main.py:train_model: [Epoch 153 Batch 5000/17173] loss=0.4461, acc=0.8262
main.py:train_model: [Epoch 153 Batch 10000/17173] loss=0.4459, acc=0.8274
main.py:train_model: [Epoch 153 Batch 15000/17173] loss=0.4491, acc=0.8247
main.py:train_model: [Epoch 153] valid loss=0.4038, valid acc=0.8469, best valid acc=0.8474
main.py:train_model: [Epoch 154 Batch 5000/17173] loss=0.4472, acc=0.8256
main.py:train_model: [Epoch 154 Batch 10000/17173] loss=0.4473, acc=0.8263
main.py:train_model: [Epoch 154 Batch 15000/17173] loss=0.4491, acc=0.8245
main.py:train_model: [Epoch 154] valid loss=0.4075, valid acc=0.8470, best valid acc=0.8474
main.py:train_model: [Epoch 155 Batch 5000/17173] loss=0.4446, acc=0.8266
main.py:train_model: [Epoch 155 Batch 10000/17173] loss=0.4483, acc=0.8252
main.py:train_model: [Epoch 155 Batch 15000/17173] loss=0.4480, acc=0.8254
main.py:train_model: [Epoch 155] valid loss=0.4081, valid acc=0.8457, best valid acc=0.8474
main.py:train_model: [Epoch 156 Batch 5000/17173] loss=0.4503, acc=0.8250
main.py:train_model: [Epoch 156 Batch 10000/17173] loss=0.4452, acc=0.8261
main.py:train_model: [Epoch 156 Batch 15000/17173] loss=0.4448, acc=0.8267
main.py:train_model: [Epoch 156] valid loss=0.4080, valid acc=0.8456, best valid acc=0.8474
main.py:train_model: [Epoch 157 Batch 5000/17173] loss=0.4483, acc=0.8258
main.py:train_model: [Epoch 157 Batch 10000/17173] loss=0.4463, acc=0.8263
main.py:train_model: [Epoch 157 Batch 15000/17173] loss=0.4492, acc=0.8251
main.py:train_model: [Epoch 157] valid loss=0.4040, valid acc=0.8471, best valid acc=0.8474
main.py:train_model: [Epoch 158 Batch 5000/17173] loss=0.4438, acc=0.8277
main.py:train_model: [Epoch 158 Batch 10000/17173] loss=0.4473, acc=0.8256
main.py:train_model: [Epoch 158 Batch 15000/17173] loss=0.4476, acc=0.8255
main.py:train_model: [Epoch 158] valid loss=0.4111, valid acc=0.8455, best valid acc=0.8474
main.py:train_model: [Epoch 159 Batch 5000/17173] loss=0.4474, acc=0.8257
main.py:train_model: [Epoch 159 Batch 10000/17173] loss=0.4468, acc=0.8257
main.py:train_model: [Epoch 159 Batch 15000/17173] loss=0.4446, acc=0.8271
main.py:train_model: [Epoch 159] valid loss=0.4075, valid acc=0.8473, best valid acc=0.8474
main.py:train_model: [Epoch 160 Batch 5000/17173] loss=0.4443, acc=0.8273
main.py:train_model: [Epoch 160 Batch 10000/17173] loss=0.4444, acc=0.8264
main.py:train_model: [Epoch 160 Batch 15000/17173] loss=0.4486, acc=0.8247
main.py:train_model: [Epoch 160] valid loss=0.4066, valid acc=0.8461, best valid acc=0.8474
main.py:train_model: [Epoch 161 Batch 5000/17173] loss=0.4448, acc=0.8264
main.py:train_model: [Epoch 161 Batch 10000/17173] loss=0.4467, acc=0.8258
main.py:train_model: [Epoch 161 Batch 15000/17173] loss=0.4478, acc=0.8264
main.py:train_model: [Epoch 161] valid loss=0.4057, valid acc=0.8450, best valid acc=0.8474
main.py:train_model: [Epoch 162 Batch 5000/17173] loss=0.4462, acc=0.8256
main.py:train_model: [Epoch 162 Batch 10000/17173] loss=0.4459, acc=0.8265
main.py:train_model: [Epoch 162 Batch 15000/17173] loss=0.4453, acc=0.8260
main.py:train_model: [Epoch 162] valid loss=0.4068, valid acc=0.8463, best valid acc=0.8474
main.py:train_model: [Epoch 163 Batch 5000/17173] loss=0.4476, acc=0.8248
main.py:train_model: [Epoch 163 Batch 10000/17173] loss=0.4470, acc=0.8254
main.py:train_model: [Epoch 163 Batch 15000/17173] loss=0.4462, acc=0.8251
main.py:train_model: [Epoch 163] valid loss=0.4054, valid acc=0.8464, best valid acc=0.8474
main.py:train_model: [Epoch 164 Batch 5000/17173] loss=0.4452, acc=0.8259
main.py:train_model: [Epoch 164 Batch 10000/17173] loss=0.4482, acc=0.8257
main.py:train_model: [Epoch 164 Batch 15000/17173] loss=0.4461, acc=0.8259
main.py:train_model: [Epoch 164] valid loss=0.4065, valid acc=0.8450, best valid acc=0.8474
main.py:train_model: [Epoch 165 Batch 5000/17173] loss=0.4446, acc=0.8262
main.py:train_model: [Epoch 165 Batch 10000/17173] loss=0.4458, acc=0.8248
main.py:train_model: [Epoch 165 Batch 15000/17173] loss=0.4479, acc=0.8261
main.py:train_model: [Epoch 165] valid loss=0.4064, valid acc=0.8459, best valid acc=0.8474
main.py:train_model: [Epoch 166 Batch 5000/17173] loss=0.4461, acc=0.8264
main.py:train_model: [Epoch 166 Batch 10000/17173] loss=0.4467, acc=0.8261
main.py:train_model: [Epoch 166 Batch 15000/17173] loss=0.4474, acc=0.8250
main.py:train_model: [Epoch 166] valid loss=0.4063, valid acc=0.8478, best valid acc=0.8478
main.py:train_model: [Epoch 167 Batch 5000/17173] loss=0.4456, acc=0.8267
main.py:train_model: [Epoch 167 Batch 10000/17173] loss=0.4452, acc=0.8267
main.py:train_model: [Epoch 167 Batch 15000/17173] loss=0.4443, acc=0.8270
main.py:train_model: [Epoch 167] valid loss=0.4013, valid acc=0.8475, best valid acc=0.8478
main.py:train_model: [Epoch 168 Batch 5000/17173] loss=0.4484, acc=0.8245
main.py:train_model: [Epoch 168 Batch 10000/17173] loss=0.4460, acc=0.8259
main.py:train_model: [Epoch 168 Batch 15000/17173] loss=0.4443, acc=0.8266
main.py:train_model: [Epoch 168] valid loss=0.4032, valid acc=0.8463, best valid acc=0.8478
main.py:train_model: [Epoch 169 Batch 5000/17173] loss=0.4452, acc=0.8256
main.py:train_model: [Epoch 169 Batch 10000/17173] loss=0.4452, acc=0.8275
main.py:train_model: [Epoch 169 Batch 15000/17173] loss=0.4449, acc=0.8269
main.py:train_model: [Epoch 169] valid loss=0.4072, valid acc=0.8470, best valid acc=0.8478
main.py:train_model: [Epoch 170 Batch 5000/17173] loss=0.4455, acc=0.8255
main.py:train_model: [Epoch 170 Batch 10000/17173] loss=0.4437, acc=0.8270
main.py:train_model: [Epoch 170 Batch 15000/17173] loss=0.4483, acc=0.8246
main.py:train_model: [Epoch 170] valid loss=0.4041, valid acc=0.8464, best valid acc=0.8478
main.py:train_model: [Epoch 171 Batch 5000/17173] loss=0.4448, acc=0.8271
main.py:train_model: [Epoch 171 Batch 10000/17173] loss=0.4437, acc=0.8272
main.py:train_model: [Epoch 171 Batch 15000/17173] loss=0.4445, acc=0.8270
main.py:train_model: [Epoch 171] valid loss=0.4055, valid acc=0.8473, best valid acc=0.8478
main.py:train_model: [Epoch 172 Batch 5000/17173] loss=0.4459, acc=0.8256
main.py:train_model: [Epoch 172 Batch 10000/17173] loss=0.4438, acc=0.8268
main.py:train_model: [Epoch 172 Batch 15000/17173] loss=0.4430, acc=0.8275
main.py:train_model: [Epoch 172] valid loss=0.4037, valid acc=0.8461, best valid acc=0.8478
main.py:train_model: [Epoch 173 Batch 5000/17173] loss=0.4410, acc=0.8274
main.py:train_model: [Epoch 173 Batch 10000/17173] loss=0.4470, acc=0.8256
main.py:train_model: [Epoch 173 Batch 15000/17173] loss=0.4453, acc=0.8270
main.py:train_model: [Epoch 173] valid loss=0.4072, valid acc=0.8459, best valid acc=0.8478
main.py:train_model: [Epoch 174 Batch 5000/17173] loss=0.4448, acc=0.8270
main.py:train_model: [Epoch 174 Batch 10000/17173] loss=0.4427, acc=0.8278
main.py:train_model: [Epoch 174 Batch 15000/17173] loss=0.4446, acc=0.8278
main.py:train_model: [Epoch 174] valid loss=0.4055, valid acc=0.8467, best valid acc=0.8478
main.py:train_model: [Epoch 175 Batch 5000/17173] loss=0.4416, acc=0.8279
main.py:train_model: [Epoch 175 Batch 10000/17173] loss=0.4453, acc=0.8255
main.py:train_model: [Epoch 175 Batch 15000/17173] loss=0.4466, acc=0.8260
main.py:train_model: [Epoch 175] valid loss=0.4046, valid acc=0.8482, best valid acc=0.8482
main.py:train_model: [Epoch 176 Batch 5000/17173] loss=0.4436, acc=0.8262
main.py:train_model: [Epoch 176 Batch 10000/17173] loss=0.4483, acc=0.8254
main.py:train_model: [Epoch 176 Batch 15000/17173] loss=0.4420, acc=0.8279
main.py:train_model: [Epoch 176] valid loss=0.4036, valid acc=0.8474, best valid acc=0.8482
main.py:train_model: [Epoch 177 Batch 5000/17173] loss=0.4418, acc=0.8280
main.py:train_model: [Epoch 177 Batch 10000/17173] loss=0.4442, acc=0.8262
main.py:train_model: [Epoch 177 Batch 15000/17173] loss=0.4440, acc=0.8270
main.py:train_model: [Epoch 177] valid loss=0.4048, valid acc=0.8480, best valid acc=0.8482
main.py:train_model: [Epoch 178 Batch 5000/17173] loss=0.4409, acc=0.8289
main.py:train_model: [Epoch 178 Batch 10000/17173] loss=0.4443, acc=0.8264
main.py:train_model: [Epoch 178 Batch 15000/17173] loss=0.4461, acc=0.8268
main.py:train_model: [Epoch 178] valid loss=0.4027, valid acc=0.8468, best valid acc=0.8482
main.py:train_model: [Epoch 179 Batch 5000/17173] loss=0.4422, acc=0.8288
main.py:train_model: [Epoch 179 Batch 10000/17173] loss=0.4460, acc=0.8259
main.py:train_model: [Epoch 179 Batch 15000/17173] loss=0.4440, acc=0.8276
main.py:train_model: [Epoch 179] valid loss=0.3997, valid acc=0.8490, best valid acc=0.8490
main.py:train_model: [Epoch 180 Batch 5000/17173] loss=0.4452, acc=0.8268
main.py:train_model: [Epoch 180 Batch 10000/17173] loss=0.4398, acc=0.8292
main.py:train_model: [Epoch 180 Batch 15000/17173] loss=0.4464, acc=0.8260
main.py:train_model: [Epoch 180] valid loss=0.4021, valid acc=0.8486, best valid acc=0.8490
main.py:train_model: [Epoch 181 Batch 5000/17173] loss=0.4431, acc=0.8266
main.py:train_model: [Epoch 181 Batch 10000/17173] loss=0.4437, acc=0.8272
main.py:train_model: [Epoch 181 Batch 15000/17173] loss=0.4449, acc=0.8261
main.py:train_model: [Epoch 181] valid loss=0.4042, valid acc=0.8482, best valid acc=0.8490
main.py:train_model: [Epoch 182 Batch 5000/17173] loss=0.4443, acc=0.8258
main.py:train_model: [Epoch 182 Batch 10000/17173] loss=0.4413, acc=0.8282
main.py:train_model: [Epoch 182 Batch 15000/17173] loss=0.4445, acc=0.8270
main.py:train_model: [Epoch 182] valid loss=0.4006, valid acc=0.8491, best valid acc=0.8491
main.py:train_model: [Epoch 183 Batch 5000/17173] loss=0.4413, acc=0.8280
main.py:train_model: [Epoch 183 Batch 10000/17173] loss=0.4442, acc=0.8279
main.py:train_model: [Epoch 183 Batch 15000/17173] loss=0.4416, acc=0.8273
main.py:train_model: [Epoch 183] valid loss=0.4037, valid acc=0.8474, best valid acc=0.8491
main.py:train_model: [Epoch 184 Batch 5000/17173] loss=0.4432, acc=0.8276
main.py:train_model: [Epoch 184 Batch 10000/17173] loss=0.4413, acc=0.8284
main.py:train_model: [Epoch 184 Batch 15000/17173] loss=0.4446, acc=0.8265
main.py:train_model: [Epoch 184] valid loss=0.4013, valid acc=0.8480, best valid acc=0.8491
main.py:train_model: [Epoch 185 Batch 5000/17173] loss=0.4407, acc=0.8281
main.py:train_model: [Epoch 185 Batch 10000/17173] loss=0.4437, acc=0.8270
main.py:train_model: [Epoch 185 Batch 15000/17173] loss=0.4447, acc=0.8258
main.py:train_model: [Epoch 185] valid loss=0.4045, valid acc=0.8469, best valid acc=0.8491
main.py:train_model: [Epoch 186 Batch 5000/17173] loss=0.4417, acc=0.8289
main.py:train_model: [Epoch 186 Batch 10000/17173] loss=0.4424, acc=0.8275
main.py:train_model: [Epoch 186 Batch 15000/17173] loss=0.4458, acc=0.8257
main.py:train_model: [Epoch 186] valid loss=0.4016, valid acc=0.8477, best valid acc=0.8491
main.py:train_model: [Epoch 187 Batch 5000/17173] loss=0.4429, acc=0.8282
main.py:train_model: [Epoch 187 Batch 10000/17173] loss=0.4445, acc=0.8265
main.py:train_model: [Epoch 187 Batch 15000/17173] loss=0.4414, acc=0.8287
main.py:train_model: [Epoch 187] valid loss=0.4030, valid acc=0.8478, best valid acc=0.8491
main.py:train_model: [Epoch 188 Batch 5000/17173] loss=0.4399, acc=0.8292
main.py:train_model: [Epoch 188 Batch 10000/17173] loss=0.4438, acc=0.8273
main.py:train_model: [Epoch 188 Batch 15000/17173] loss=0.4409, acc=0.8289
main.py:train_model: [Epoch 188] valid loss=0.4021, valid acc=0.8468, best valid acc=0.8491
main.py:train_model: [Epoch 189 Batch 5000/17173] loss=0.4434, acc=0.8272
main.py:train_model: [Epoch 189 Batch 10000/17173] loss=0.4428, acc=0.8273
main.py:train_model: [Epoch 189 Batch 15000/17173] loss=0.4426, acc=0.8276
main.py:train_model: [Epoch 189] valid loss=0.4042, valid acc=0.8471, best valid acc=0.8491
main.py:train_model: [Epoch 190 Batch 5000/17173] loss=0.4414, acc=0.8277
main.py:train_model: [Epoch 190 Batch 10000/17173] loss=0.4447, acc=0.8268
main.py:train_model: [Epoch 190 Batch 15000/17173] loss=0.4430, acc=0.8276
main.py:train_model: [Epoch 190] valid loss=0.3996, valid acc=0.8491, best valid acc=0.8491
main.py:train_model: [Epoch 191 Batch 5000/17173] loss=0.4414, acc=0.8280
main.py:train_model: [Epoch 191 Batch 10000/17173] loss=0.4438, acc=0.8269
main.py:train_model: [Epoch 191 Batch 15000/17173] loss=0.4439, acc=0.8267
main.py:train_model: [Epoch 191] valid loss=0.4013, valid acc=0.8491, best valid acc=0.8491
main.py:train_model: [Epoch 192 Batch 5000/17173] loss=0.4425, acc=0.8271
main.py:train_model: [Epoch 192 Batch 10000/17173] loss=0.4418, acc=0.8287
main.py:train_model: [Epoch 192 Batch 15000/17173] loss=0.4421, acc=0.8280
main.py:train_model: [Epoch 192] valid loss=0.4003, valid acc=0.8475, best valid acc=0.8491
main.py:train_model: [Epoch 193 Batch 5000/17173] loss=0.4381, acc=0.8296
main.py:train_model: [Epoch 193 Batch 10000/17173] loss=0.4452, acc=0.8270
main.py:train_model: [Epoch 193 Batch 15000/17173] loss=0.4404, acc=0.8279
main.py:train_model: [Epoch 193] valid loss=0.4025, valid acc=0.8477, best valid acc=0.8491
main.py:train_model: [Epoch 194 Batch 5000/17173] loss=0.4411, acc=0.8288
main.py:train_model: [Epoch 194 Batch 10000/17173] loss=0.4421, acc=0.8282
main.py:train_model: [Epoch 194 Batch 15000/17173] loss=0.4409, acc=0.8276
main.py:train_model: [Epoch 194] valid loss=0.3994, valid acc=0.8486, best valid acc=0.8491
main.py:train_model: [Epoch 195 Batch 5000/17173] loss=0.4418, acc=0.8287
main.py:train_model: [Epoch 195 Batch 10000/17173] loss=0.4400, acc=0.8280
main.py:train_model: [Epoch 195 Batch 15000/17173] loss=0.4425, acc=0.8278
main.py:train_model: [Epoch 195] valid loss=0.4037, valid acc=0.8488, best valid acc=0.8491
main.py:train_model: [Epoch 196 Batch 5000/17173] loss=0.4376, acc=0.8296
main.py:train_model: [Epoch 196 Batch 10000/17173] loss=0.4441, acc=0.8283
main.py:train_model: [Epoch 196 Batch 15000/17173] loss=0.4411, acc=0.8283
main.py:train_model: [Epoch 196] valid loss=0.4011, valid acc=0.8487, best valid acc=0.8491
main.py:train_model: [Epoch 197 Batch 5000/17173] loss=0.4399, acc=0.8288
main.py:train_model: [Epoch 197 Batch 10000/17173] loss=0.4401, acc=0.8292
main.py:train_model: [Epoch 197 Batch 15000/17173] loss=0.4423, acc=0.8287
main.py:train_model: [Epoch 197] valid loss=0.4000, valid acc=0.8491, best valid acc=0.8491
main.py:train_model: [Epoch 198 Batch 5000/17173] loss=0.4415, acc=0.8285
main.py:train_model: [Epoch 198 Batch 10000/17173] loss=0.4396, acc=0.8298
main.py:train_model: [Epoch 198 Batch 15000/17173] loss=0.4421, acc=0.8269
main.py:train_model: [Epoch 198] valid loss=0.3973, valid acc=0.8496, best valid acc=0.8496
main.py:train_model: [Epoch 199 Batch 5000/17173] loss=0.4383, acc=0.8293
main.py:train_model: [Epoch 199 Batch 10000/17173] loss=0.4397, acc=0.8283
main.py:train_model: [Epoch 199 Batch 15000/17173] loss=0.4427, acc=0.8275
main.py:train_model: [Epoch 199] valid loss=0.3992, valid acc=0.8486, best valid acc=0.8496
main.py:train_model: [Epoch 200 Batch 5000/17173] loss=0.4379, acc=0.8298
main.py:train_model: [Epoch 200 Batch 10000/17173] loss=0.4409, acc=0.8278
main.py:train_model: [Epoch 200 Batch 15000/17173] loss=0.4436, acc=0.8278
main.py:train_model: [Epoch 200] valid loss=0.4013, valid acc=0.8489, best valid acc=0.8496
main.py:train_model: [Epoch 201 Batch 5000/17173] loss=0.4431, acc=0.8278
main.py:train_model: [Epoch 201 Batch 10000/17173] loss=0.4408, acc=0.8288
main.py:train_model: [Epoch 201 Batch 15000/17173] loss=0.4399, acc=0.8289
main.py:train_model: [Epoch 201] valid loss=0.4003, valid acc=0.8493, best valid acc=0.8496
main.py:train_model: [Epoch 202 Batch 5000/17173] loss=0.4386, acc=0.8297
main.py:train_model: [Epoch 202 Batch 10000/17173] loss=0.4421, acc=0.8282
main.py:train_model: [Epoch 202 Batch 15000/17173] loss=0.4405, acc=0.8280
main.py:train_model: [Epoch 202] valid loss=0.4023, valid acc=0.8496, best valid acc=0.8496
main.py:train_model: [Epoch 203 Batch 5000/17173] loss=0.4392, acc=0.8294
main.py:train_model: [Epoch 203 Batch 10000/17173] loss=0.4394, acc=0.8299
main.py:train_model: [Epoch 203 Batch 15000/17173] loss=0.4403, acc=0.8279
main.py:train_model: [Epoch 203] valid loss=0.3951, valid acc=0.8525, best valid acc=0.8525
main.py:train_model: [Epoch 204 Batch 5000/17173] loss=0.4417, acc=0.8279
main.py:train_model: [Epoch 204 Batch 10000/17173] loss=0.4394, acc=0.8293
main.py:train_model: [Epoch 204 Batch 15000/17173] loss=0.4425, acc=0.8278
main.py:train_model: [Epoch 204] valid loss=0.3953, valid acc=0.8538, best valid acc=0.8538
main.py:train_model: [Epoch 205 Batch 5000/17173] loss=0.4398, acc=0.8292
main.py:train_model: [Epoch 205 Batch 10000/17173] loss=0.4399, acc=0.8288
main.py:train_model: [Epoch 205 Batch 15000/17173] loss=0.4450, acc=0.8261
main.py:train_model: [Epoch 205] valid loss=0.3971, valid acc=0.8499, best valid acc=0.8538
main.py:train_model: [Epoch 206 Batch 5000/17173] loss=0.4386, acc=0.8294
main.py:train_model: [Epoch 206 Batch 10000/17173] loss=0.4411, acc=0.8283
main.py:train_model: [Epoch 206 Batch 15000/17173] loss=0.4398, acc=0.8289
main.py:train_model: [Epoch 206] valid loss=0.3997, valid acc=0.8496, best valid acc=0.8538
main.py:train_model: [Epoch 207 Batch 5000/17173] loss=0.4370, acc=0.8307
main.py:train_model: [Epoch 207 Batch 10000/17173] loss=0.4389, acc=0.8282
main.py:train_model: [Epoch 207 Batch 15000/17173] loss=0.4415, acc=0.8294
main.py:train_model: [Epoch 207] valid loss=0.3989, valid acc=0.8508, best valid acc=0.8538
main.py:train_model: [Epoch 208 Batch 5000/17173] loss=0.4407, acc=0.8293
main.py:train_model: [Epoch 208 Batch 10000/17173] loss=0.4382, acc=0.8293
main.py:train_model: [Epoch 208 Batch 15000/17173] loss=0.4418, acc=0.8280
main.py:train_model: [Epoch 208] valid loss=0.3970, valid acc=0.8495, best valid acc=0.8538
main.py:train_model: [Epoch 209 Batch 5000/17173] loss=0.4370, acc=0.8300
main.py:train_model: [Epoch 209 Batch 10000/17173] loss=0.4400, acc=0.8290
main.py:train_model: [Epoch 209 Batch 15000/17173] loss=0.4415, acc=0.8275
main.py:train_model: [Epoch 209] valid loss=0.3972, valid acc=0.8500, best valid acc=0.8538
main.py:train_model: [Epoch 210 Batch 5000/17173] loss=0.4375, acc=0.8301
main.py:train_model: [Epoch 210 Batch 10000/17173] loss=0.4397, acc=0.8284
main.py:train_model: [Epoch 210 Batch 15000/17173] loss=0.4402, acc=0.8279
main.py:train_model: [Epoch 210] valid loss=0.4017, valid acc=0.8485, best valid acc=0.8538
main.py:train_model: [Epoch 211 Batch 5000/17173] loss=0.4380, acc=0.8300
main.py:train_model: [Epoch 211 Batch 10000/17173] loss=0.4375, acc=0.8296
main.py:train_model: [Epoch 211 Batch 15000/17173] loss=0.4422, acc=0.8281
main.py:train_model: [Epoch 211] valid loss=0.4002, valid acc=0.8490, best valid acc=0.8538
main.py:train_model: [Epoch 212 Batch 5000/17173] loss=0.4409, acc=0.8294
main.py:train_model: [Epoch 212 Batch 10000/17173] loss=0.4384, acc=0.8290
main.py:train_model: [Epoch 212 Batch 15000/17173] loss=0.4405, acc=0.8280
main.py:train_model: [Epoch 212] valid loss=0.3985, valid acc=0.8501, best valid acc=0.8538
main.py:train_model: [Epoch 213 Batch 5000/17173] loss=0.4388, acc=0.8283
main.py:train_model: [Epoch 213 Batch 10000/17173] loss=0.4398, acc=0.8284
main.py:train_model: [Epoch 213 Batch 15000/17173] loss=0.4380, acc=0.8303
main.py:train_model: [Epoch 213] valid loss=0.3956, valid acc=0.8507, best valid acc=0.8538
main.py:train_model: [Epoch 214 Batch 5000/17173] loss=0.4379, acc=0.8290
main.py:train_model: [Epoch 214 Batch 10000/17173] loss=0.4384, acc=0.8294
main.py:train_model: [Epoch 214 Batch 15000/17173] loss=0.4398, acc=0.8290
main.py:train_model: [Epoch 214] valid loss=0.3954, valid acc=0.8496, best valid acc=0.8538
main.py:train_model: [Epoch 215 Batch 5000/17173] loss=0.4414, acc=0.8285
main.py:train_model: [Epoch 215 Batch 10000/17173] loss=0.4382, acc=0.8299
main.py:train_model: [Epoch 215 Batch 15000/17173] loss=0.4382, acc=0.8296
main.py:train_model: [Epoch 215] valid loss=0.4057, valid acc=0.8465, best valid acc=0.8538
main.py:train_model: [Epoch 216 Batch 5000/17173] loss=0.4352, acc=0.8308
main.py:train_model: [Epoch 216 Batch 10000/17173] loss=0.4394, acc=0.8294
main.py:train_model: [Epoch 216 Batch 15000/17173] loss=0.4418, acc=0.8285
main.py:train_model: [Epoch 216] valid loss=0.3958, valid acc=0.8527, best valid acc=0.8538
main.py:train_model: [Epoch 217 Batch 5000/17173] loss=0.4353, acc=0.8311
main.py:train_model: [Epoch 217 Batch 10000/17173] loss=0.4379, acc=0.8285
main.py:train_model: [Epoch 217 Batch 15000/17173] loss=0.4417, acc=0.8293
main.py:train_model: [Epoch 217] valid loss=0.3980, valid acc=0.8511, best valid acc=0.8538
main.py:train_model: [Epoch 218 Batch 5000/17173] loss=0.4381, acc=0.8303
main.py:train_model: [Epoch 218 Batch 10000/17173] loss=0.4370, acc=0.8303
main.py:train_model: [Epoch 218 Batch 15000/17173] loss=0.4375, acc=0.8291
main.py:train_model: [Epoch 218] valid loss=0.3979, valid acc=0.8513, best valid acc=0.8538
main.py:train_model: [Epoch 219 Batch 5000/17173] loss=0.4372, acc=0.8306
main.py:train_model: [Epoch 219 Batch 10000/17173] loss=0.4374, acc=0.8304
main.py:train_model: [Epoch 219 Batch 15000/17173] loss=0.4382, acc=0.8301
main.py:train_model: [Epoch 219] valid loss=0.4000, valid acc=0.8502, best valid acc=0.8538
main.py:train_model: [Epoch 220 Batch 5000/17173] loss=0.4360, acc=0.8313
main.py:train_model: [Epoch 220 Batch 10000/17173] loss=0.4415, acc=0.8286
main.py:train_model: [Epoch 220 Batch 15000/17173] loss=0.4402, acc=0.8293
main.py:train_model: [Epoch 220] valid loss=0.4002, valid acc=0.8504, best valid acc=0.8538
main.py:train_model: [Epoch 221 Batch 5000/17173] loss=0.4368, acc=0.8306
main.py:train_model: [Epoch 221 Batch 10000/17173] loss=0.4388, acc=0.8300
main.py:train_model: [Epoch 221 Batch 15000/17173] loss=0.4385, acc=0.8297
main.py:train_model: [Epoch 221] valid loss=0.3952, valid acc=0.8501, best valid acc=0.8538
main.py:train_model: [Epoch 222 Batch 5000/17173] loss=0.4343, acc=0.8307
main.py:train_model: [Epoch 222 Batch 10000/17173] loss=0.4431, acc=0.8271
main.py:train_model: [Epoch 222 Batch 15000/17173] loss=0.4380, acc=0.8302
main.py:train_model: [Epoch 222] valid loss=0.3957, valid acc=0.8505, best valid acc=0.8538
main.py:train_model: [Epoch 223 Batch 5000/17173] loss=0.4357, acc=0.8308
main.py:train_model: [Epoch 223 Batch 10000/17173] loss=0.4374, acc=0.8294
main.py:train_model: [Epoch 223 Batch 15000/17173] loss=0.4392, acc=0.8292
main.py:train_model: [Epoch 223] valid loss=0.3965, valid acc=0.8503, best valid acc=0.8538
main.py:train_model: [Epoch 224 Batch 5000/17173] loss=0.4369, acc=0.8298
main.py:train_model: [Epoch 224 Batch 10000/17173] loss=0.4374, acc=0.8295
main.py:train_model: [Epoch 224 Batch 15000/17173] loss=0.4405, acc=0.8287
main.py:train_model: [Epoch 224] valid loss=0.3947, valid acc=0.8518, best valid acc=0.8538
main.py:train_model: [Epoch 225 Batch 5000/17173] loss=0.4375, acc=0.8299
main.py:train_model: [Epoch 225 Batch 10000/17173] loss=0.4412, acc=0.8280
main.py:train_model: [Epoch 225 Batch 15000/17173] loss=0.4388, acc=0.8290
main.py:train_model: [Epoch 225] valid loss=0.3957, valid acc=0.8531, best valid acc=0.8538
main.py:train_model: [Epoch 226 Batch 5000/17173] loss=0.4355, acc=0.8311
main.py:train_model: [Epoch 226 Batch 10000/17173] loss=0.4392, acc=0.8293
main.py:train_model: [Epoch 226 Batch 15000/17173] loss=0.4364, acc=0.8301
main.py:train_model: [Epoch 226] valid loss=0.3966, valid acc=0.8509, best valid acc=0.8538
main.py:train_model: [Epoch 227 Batch 5000/17173] loss=0.4376, acc=0.8302
main.py:train_model: [Epoch 227 Batch 10000/17173] loss=0.4383, acc=0.8298
main.py:train_model: [Epoch 227 Batch 15000/17173] loss=0.4381, acc=0.8298
main.py:train_model: [Epoch 227] valid loss=0.3970, valid acc=0.8505, best valid acc=0.8538
main.py:train_model: [Epoch 228 Batch 5000/17173] loss=0.4396, acc=0.8301
main.py:train_model: [Epoch 228 Batch 10000/17173] loss=0.4352, acc=0.8307
main.py:train_model: [Epoch 228 Batch 15000/17173] loss=0.4367, acc=0.8306
main.py:train_model: [Epoch 228] valid loss=0.3983, valid acc=0.8512, best valid acc=0.8538
main.py:train_model: [Epoch 229 Batch 5000/17173] loss=0.4381, acc=0.8298
main.py:train_model: [Epoch 229 Batch 10000/17173] loss=0.4382, acc=0.8304
main.py:train_model: [Epoch 229 Batch 15000/17173] loss=0.4394, acc=0.8295
main.py:train_model: [Epoch 229] valid loss=0.3928, valid acc=0.8532, best valid acc=0.8538
main.py:train_model: [Epoch 230 Batch 5000/17173] loss=0.4375, acc=0.8301
main.py:train_model: [Epoch 230 Batch 10000/17173] loss=0.4405, acc=0.8285
main.py:train_model: [Epoch 230 Batch 15000/17173] loss=0.4375, acc=0.8295
main.py:train_model: [Epoch 230] valid loss=0.3978, valid acc=0.8505, best valid acc=0.8538
main.py:train_model: [Epoch 231 Batch 5000/17173] loss=0.4375, acc=0.8298
main.py:train_model: [Epoch 231 Batch 10000/17173] loss=0.4363, acc=0.8304
main.py:train_model: [Epoch 231 Batch 15000/17173] loss=0.4379, acc=0.8291
main.py:train_model: [Epoch 231] valid loss=0.3947, valid acc=0.8516, best valid acc=0.8538
main.py:train_model: [Epoch 232 Batch 5000/17173] loss=0.4366, acc=0.8305
main.py:train_model: [Epoch 232 Batch 10000/17173] loss=0.4366, acc=0.8305
main.py:train_model: [Epoch 232 Batch 15000/17173] loss=0.4395, acc=0.8285
main.py:train_model: [Epoch 232] valid loss=0.3923, valid acc=0.8532, best valid acc=0.8538
main.py:train_model: [Epoch 233 Batch 5000/17173] loss=0.4368, acc=0.8296
main.py:train_model: [Epoch 233 Batch 10000/17173] loss=0.4372, acc=0.8310
main.py:train_model: [Epoch 233 Batch 15000/17173] loss=0.4364, acc=0.8298
main.py:train_model: [Epoch 233] valid loss=0.3919, valid acc=0.8525, best valid acc=0.8538
main.py:train_model: [Epoch 234 Batch 5000/17173] loss=0.4369, acc=0.8299
main.py:train_model: [Epoch 234 Batch 10000/17173] loss=0.4367, acc=0.8300
main.py:train_model: [Epoch 234 Batch 15000/17173] loss=0.4390, acc=0.8288
main.py:train_model: [Epoch 234] valid loss=0.3922, valid acc=0.8525, best valid acc=0.8538
main.py:train_model: [Epoch 235 Batch 5000/17173] loss=0.4355, acc=0.8307
main.py:train_model: [Epoch 235 Batch 10000/17173] loss=0.4359, acc=0.8311
main.py:train_model: [Epoch 235 Batch 15000/17173] loss=0.4385, acc=0.8292
main.py:train_model: [Epoch 235] valid loss=0.3932, valid acc=0.8508, best valid acc=0.8538
main.py:train_model: [Epoch 236 Batch 5000/17173] loss=0.4362, acc=0.8305
main.py:train_model: [Epoch 236 Batch 10000/17173] loss=0.4415, acc=0.8286
main.py:train_model: [Epoch 236 Batch 15000/17173] loss=0.4363, acc=0.8293
main.py:train_model: [Epoch 236] valid loss=0.3932, valid acc=0.8524, best valid acc=0.8538
main.py:train_model: [Epoch 237 Batch 5000/17173] loss=0.4386, acc=0.8294
main.py:train_model: [Epoch 237 Batch 10000/17173] loss=0.4369, acc=0.8299
main.py:train_model: [Epoch 237 Batch 15000/17173] loss=0.4345, acc=0.8316
main.py:train_model: [Epoch 237] valid loss=0.3934, valid acc=0.8511, best valid acc=0.8538
main.py:train_model: [Epoch 238 Batch 5000/17173] loss=0.4385, acc=0.8300
main.py:train_model: [Epoch 238 Batch 10000/17173] loss=0.4364, acc=0.8297
main.py:train_model: [Epoch 238 Batch 15000/17173] loss=0.4362, acc=0.8299
main.py:train_model: [Epoch 238] valid loss=0.3929, valid acc=0.8533, best valid acc=0.8538
main.py:train_model: [Epoch 239 Batch 5000/17173] loss=0.4339, acc=0.8314
main.py:train_model: [Epoch 239 Batch 10000/17173] loss=0.4373, acc=0.8297
main.py:train_model: [Epoch 239 Batch 15000/17173] loss=0.4379, acc=0.8293
main.py:train_model: [Epoch 239] valid loss=0.3918, valid acc=0.8539, best valid acc=0.8539
main.py:train_model: [Epoch 240 Batch 5000/17173] loss=0.4377, acc=0.8299
main.py:train_model: [Epoch 240 Batch 10000/17173] loss=0.4351, acc=0.8309
main.py:train_model: [Epoch 240 Batch 15000/17173] loss=0.4374, acc=0.8301
main.py:train_model: [Epoch 240] valid loss=0.3955, valid acc=0.8523, best valid acc=0.8539
main.py:train_model: [Epoch 241 Batch 5000/17173] loss=0.4358, acc=0.8310
main.py:train_model: [Epoch 241 Batch 10000/17173] loss=0.4378, acc=0.8303
main.py:train_model: [Epoch 241 Batch 15000/17173] loss=0.4350, acc=0.8316
main.py:train_model: [Epoch 241] valid loss=0.3912, valid acc=0.8520, best valid acc=0.8539
main.py:train_model: [Epoch 242 Batch 5000/17173] loss=0.4349, acc=0.8308
main.py:train_model: [Epoch 242 Batch 10000/17173] loss=0.4376, acc=0.8302
main.py:train_model: [Epoch 242 Batch 15000/17173] loss=0.4383, acc=0.8292
main.py:train_model: [Epoch 242] valid loss=0.3960, valid acc=0.8531, best valid acc=0.8539
main.py:train_model: [Epoch 243 Batch 5000/17173] loss=0.4347, acc=0.8312
main.py:train_model: [Epoch 243 Batch 10000/17173] loss=0.4393, acc=0.8297
main.py:train_model: [Epoch 243 Batch 15000/17173] loss=0.4376, acc=0.8297
main.py:train_model: [Epoch 243] valid loss=0.3946, valid acc=0.8531, best valid acc=0.8539
main.py:train_model: [Epoch 244 Batch 5000/17173] loss=0.4382, acc=0.8298
main.py:train_model: [Epoch 244 Batch 10000/17173] loss=0.4344, acc=0.8311
main.py:train_model: [Epoch 244 Batch 15000/17173] loss=0.4362, acc=0.8309
main.py:train_model: [Epoch 244] valid loss=0.3965, valid acc=0.8525, best valid acc=0.8539
main.py:train_model: [Epoch 245 Batch 5000/17173] loss=0.4361, acc=0.8308
main.py:train_model: [Epoch 245 Batch 10000/17173] loss=0.4344, acc=0.8315
main.py:train_model: [Epoch 245 Batch 15000/17173] loss=0.4384, acc=0.8301
main.py:train_model: [Epoch 245] valid loss=0.3944, valid acc=0.8534, best valid acc=0.8539
main.py:train_model: [Epoch 246 Batch 5000/17173] loss=0.4359, acc=0.8307
main.py:train_model: [Epoch 246 Batch 10000/17173] loss=0.4366, acc=0.8308
main.py:train_model: [Epoch 246 Batch 15000/17173] loss=0.4359, acc=0.8304
main.py:train_model: [Epoch 246] valid loss=0.3946, valid acc=0.8523, best valid acc=0.8539
main.py:train_model: [Epoch 247 Batch 5000/17173] loss=0.4358, acc=0.8312
main.py:train_model: [Epoch 247 Batch 10000/17173] loss=0.4356, acc=0.8304
main.py:train_model: [Epoch 247 Batch 15000/17173] loss=0.4366, acc=0.8298
main.py:train_model: [Epoch 247] valid loss=0.3932, valid acc=0.8505, best valid acc=0.8539
main.py:train_model: [Epoch 248 Batch 5000/17173] loss=0.4352, acc=0.8323
main.py:train_model: [Epoch 248 Batch 10000/17173] loss=0.4333, acc=0.8326
main.py:train_model: [Epoch 248 Batch 15000/17173] loss=0.4369, acc=0.8303
main.py:train_model: [Epoch 248] valid loss=0.3961, valid acc=0.8507, best valid acc=0.8539
main.py:train_model: [Epoch 249 Batch 5000/17173] loss=0.4351, acc=0.8314
main.py:train_model: [Epoch 249 Batch 10000/17173] loss=0.4320, acc=0.8325
main.py:train_model: [Epoch 249 Batch 15000/17173] loss=0.4359, acc=0.8301
main.py:train_model: [Epoch 249] valid loss=0.3914, valid acc=0.8521, best valid acc=0.8539
main.py:train_model: [Epoch 250 Batch 5000/17173] loss=0.4369, acc=0.8303
main.py:train_model: [Epoch 250 Batch 10000/17173] loss=0.4359, acc=0.8307
main.py:train_model: [Epoch 250 Batch 15000/17173] loss=0.4369, acc=0.8309
main.py:train_model: [Epoch 250] valid loss=0.3964, valid acc=0.8516, best valid acc=0.8539
main.py:train_model: [Epoch 251 Batch 5000/17173] loss=0.4362, acc=0.8303
main.py:train_model: [Epoch 251 Batch 10000/17173] loss=0.4338, acc=0.8309
main.py:train_model: [Epoch 251 Batch 15000/17173] loss=0.4357, acc=0.8308
main.py:train_model: [Epoch 251] valid loss=0.3946, valid acc=0.8522, best valid acc=0.8539
main.py:train_model: [Epoch 252 Batch 5000/17173] loss=0.4354, acc=0.8306
main.py:train_model: [Epoch 252 Batch 10000/17173] loss=0.4372, acc=0.8309
main.py:train_model: [Epoch 252 Batch 15000/17173] loss=0.4356, acc=0.8317
main.py:train_model: [Epoch 252] valid loss=0.3917, valid acc=0.8539, best valid acc=0.8539
main.py:train_model: [Epoch 253 Batch 5000/17173] loss=0.4360, acc=0.8304
main.py:train_model: [Epoch 253 Batch 10000/17173] loss=0.4340, acc=0.8316
main.py:train_model: [Epoch 253 Batch 15000/17173] loss=0.4381, acc=0.8297
main.py:train_model: [Epoch 253] valid loss=0.3924, valid acc=0.8557, best valid acc=0.8557
main.py:train_model: [Epoch 254 Batch 5000/17173] loss=0.4356, acc=0.8306
main.py:train_model: [Epoch 254 Batch 10000/17173] loss=0.4357, acc=0.8307
main.py:train_model: [Epoch 254 Batch 15000/17173] loss=0.4344, acc=0.8305
main.py:train_model: [Epoch 254] valid loss=0.3921, valid acc=0.8528, best valid acc=0.8557
main.py:train_model: [Epoch 255 Batch 5000/17173] loss=0.4363, acc=0.8306
main.py:train_model: [Epoch 255 Batch 10000/17173] loss=0.4337, acc=0.8320
main.py:train_model: [Epoch 255 Batch 15000/17173] loss=0.4356, acc=0.8302
main.py:train_model: [Epoch 255] valid loss=0.3943, valid acc=0.8540, best valid acc=0.8557
main.py:train_model: [Epoch 256 Batch 5000/17173] loss=0.4371, acc=0.8306
main.py:train_model: [Epoch 256 Batch 10000/17173] loss=0.4329, acc=0.8312
main.py:train_model: [Epoch 256 Batch 15000/17173] loss=0.4357, acc=0.8306
main.py:train_model: [Epoch 256] valid loss=0.3918, valid acc=0.8535, best valid acc=0.8557
main.py:train_model: [Epoch 257 Batch 5000/17173] loss=0.4337, acc=0.8323
main.py:train_model: [Epoch 257 Batch 10000/17173] loss=0.4357, acc=0.8302
main.py:train_model: [Epoch 257 Batch 15000/17173] loss=0.4332, acc=0.8319
main.py:train_model: [Epoch 257] valid loss=0.3949, valid acc=0.8527, best valid acc=0.8557
main.py:train_model: [Epoch 258 Batch 5000/17173] loss=0.4329, acc=0.8321
main.py:train_model: [Epoch 258 Batch 10000/17173] loss=0.4337, acc=0.8315
main.py:train_model: [Epoch 258 Batch 15000/17173] loss=0.4362, acc=0.8306
main.py:train_model: [Epoch 258] valid loss=0.3908, valid acc=0.8528, best valid acc=0.8557
main.py:train_model: [Epoch 259 Batch 5000/17173] loss=0.4327, acc=0.8315
main.py:train_model: [Epoch 259 Batch 10000/17173] loss=0.4360, acc=0.8303
main.py:train_model: [Epoch 259 Batch 15000/17173] loss=0.4385, acc=0.8296
main.py:train_model: [Epoch 259] valid loss=0.3965, valid acc=0.8510, best valid acc=0.8557
main.py:train_model: [Epoch 260 Batch 5000/17173] loss=0.4340, acc=0.8323
main.py:train_model: [Epoch 260 Batch 10000/17173] loss=0.4324, acc=0.8324
main.py:train_model: [Epoch 260 Batch 15000/17173] loss=0.4374, acc=0.8301
main.py:train_model: [Epoch 260] valid loss=0.3932, valid acc=0.8539, best valid acc=0.8557
main.py:train_model: [Epoch 261 Batch 5000/17173] loss=0.4354, acc=0.8307
main.py:train_model: [Epoch 261 Batch 10000/17173] loss=0.4291, acc=0.8329
main.py:train_model: [Epoch 261 Batch 15000/17173] loss=0.4374, acc=0.8300
main.py:train_model: [Epoch 261] valid loss=0.3941, valid acc=0.8544, best valid acc=0.8557
main.py:train_model: [Epoch 262 Batch 5000/17173] loss=0.4351, acc=0.8311
main.py:train_model: [Epoch 262 Batch 10000/17173] loss=0.4345, acc=0.8318
main.py:train_model: [Epoch 262 Batch 15000/17173] loss=0.4346, acc=0.8310
main.py:train_model: [Epoch 262] valid loss=0.3910, valid acc=0.8543, best valid acc=0.8557
main.py:train_model: [Epoch 263 Batch 5000/17173] loss=0.4342, acc=0.8314
main.py:train_model: [Epoch 263 Batch 10000/17173] loss=0.4352, acc=0.8299
main.py:train_model: [Epoch 263 Batch 15000/17173] loss=0.4347, acc=0.8312
main.py:train_model: [Epoch 263] valid loss=0.3945, valid acc=0.8524, best valid acc=0.8557
main.py:train_model: [Epoch 264 Batch 5000/17173] loss=0.4316, acc=0.8324
main.py:train_model: [Epoch 264 Batch 10000/17173] loss=0.4368, acc=0.8300
main.py:train_model: [Epoch 264 Batch 15000/17173] loss=0.4368, acc=0.8305
main.py:train_model: [Epoch 264] valid loss=0.3930, valid acc=0.8520, best valid acc=0.8557
main.py:train_model: [Epoch 265 Batch 5000/17173] loss=0.4315, acc=0.8332
main.py:train_model: [Epoch 265 Batch 10000/17173] loss=0.4352, acc=0.8312
main.py:train_model: [Epoch 265 Batch 15000/17173] loss=0.4358, acc=0.8311
main.py:train_model: [Epoch 265] valid loss=0.3924, valid acc=0.8543, best valid acc=0.8557
main.py:train_model: [Epoch 266 Batch 5000/17173] loss=0.4348, acc=0.8322
main.py:train_model: [Epoch 266 Batch 10000/17173] loss=0.4344, acc=0.8314
main.py:train_model: [Epoch 266 Batch 15000/17173] loss=0.4327, acc=0.8316
main.py:train_model: [Epoch 266] valid loss=0.3917, valid acc=0.8535, best valid acc=0.8557
main.py:train_model: [Epoch 267 Batch 5000/17173] loss=0.4339, acc=0.8312
main.py:train_model: [Epoch 267 Batch 10000/17173] loss=0.4321, acc=0.8323
main.py:train_model: [Epoch 267 Batch 15000/17173] loss=0.4358, acc=0.8313
main.py:train_model: [Epoch 267] valid loss=0.3929, valid acc=0.8517, best valid acc=0.8557
main.py:train_model: [Epoch 268 Batch 5000/17173] loss=0.4327, acc=0.8324
main.py:train_model: [Epoch 268 Batch 10000/17173] loss=0.4335, acc=0.8313
main.py:train_model: [Epoch 268 Batch 15000/17173] loss=0.4365, acc=0.8305
main.py:train_model: [Epoch 268] valid loss=0.3933, valid acc=0.8540, best valid acc=0.8557
main.py:train_model: [Epoch 269 Batch 5000/17173] loss=0.4326, acc=0.8324
main.py:train_model: [Epoch 269 Batch 10000/17173] loss=0.4381, acc=0.8301
main.py:train_model: [Epoch 269 Batch 15000/17173] loss=0.4340, acc=0.8319
main.py:train_model: [Epoch 269] valid loss=0.3966, valid acc=0.8538, best valid acc=0.8557
main.py:train_model: [Epoch 270 Batch 5000/17173] loss=0.4354, acc=0.8303
main.py:train_model: [Epoch 270 Batch 10000/17173] loss=0.4330, acc=0.8317
main.py:train_model: [Epoch 270 Batch 15000/17173] loss=0.4340, acc=0.8308
main.py:train_model: [Epoch 270] valid loss=0.3910, valid acc=0.8542, best valid acc=0.8557
main.py:train_model: [Epoch 271 Batch 5000/17173] loss=0.4315, acc=0.8338
main.py:train_model: [Epoch 271 Batch 10000/17173] loss=0.4358, acc=0.8316
main.py:train_model: [Epoch 271 Batch 15000/17173] loss=0.4333, acc=0.8328
main.py:train_model: [Epoch 271] valid loss=0.3931, valid acc=0.8541, best valid acc=0.8557
main.py:train_model: [Epoch 272 Batch 5000/17173] loss=0.4294, acc=0.8340
main.py:train_model: [Epoch 272 Batch 10000/17173] loss=0.4334, acc=0.8324
main.py:train_model: [Epoch 272 Batch 15000/17173] loss=0.4358, acc=0.8310
main.py:train_model: [Epoch 272] valid loss=0.3913, valid acc=0.8541, best valid acc=0.8557
main.py:train_model: [Epoch 273 Batch 5000/17173] loss=0.4344, acc=0.8316
main.py:train_model: [Epoch 273 Batch 10000/17173] loss=0.4340, acc=0.8320
main.py:train_model: [Epoch 273 Batch 15000/17173] loss=0.4336, acc=0.8318
main.py:train_model: [Epoch 273] valid loss=0.3908, valid acc=0.8565, best valid acc=0.8565
main.py:train_model: [Epoch 274 Batch 5000/17173] loss=0.4311, acc=0.8332
main.py:train_model: [Epoch 274 Batch 10000/17173] loss=0.4348, acc=0.8319
main.py:train_model: [Epoch 274 Batch 15000/17173] loss=0.4318, acc=0.8320
main.py:train_model: [Epoch 274] valid loss=0.3916, valid acc=0.8537, best valid acc=0.8565
main.py:train_model: [Epoch 275 Batch 5000/17173] loss=0.4344, acc=0.8312
main.py:train_model: [Epoch 275 Batch 10000/17173] loss=0.4329, acc=0.8314
main.py:train_model: [Epoch 275 Batch 15000/17173] loss=0.4318, acc=0.8329
main.py:train_model: [Epoch 275] valid loss=0.3897, valid acc=0.8561, best valid acc=0.8565
main.py:train_model: [Epoch 276 Batch 5000/17173] loss=0.4313, acc=0.8323
main.py:train_model: [Epoch 276 Batch 10000/17173] loss=0.4343, acc=0.8314
main.py:train_model: [Epoch 276 Batch 15000/17173] loss=0.4351, acc=0.8314
main.py:train_model: [Epoch 276] valid loss=0.3909, valid acc=0.8551, best valid acc=0.8565
main.py:train_model: [Epoch 277 Batch 5000/17173] loss=0.4320, acc=0.8330
main.py:train_model: [Epoch 277 Batch 10000/17173] loss=0.4357, acc=0.8306
main.py:train_model: [Epoch 277 Batch 15000/17173] loss=0.4358, acc=0.8315
main.py:train_model: [Epoch 277] valid loss=0.3897, valid acc=0.8547, best valid acc=0.8565
main.py:train_model: [Epoch 278 Batch 5000/17173] loss=0.4353, acc=0.8311
main.py:train_model: [Epoch 278 Batch 10000/17173] loss=0.4333, acc=0.8320
main.py:train_model: [Epoch 278 Batch 15000/17173] loss=0.4330, acc=0.8311
main.py:train_model: [Epoch 278] valid loss=0.3910, valid acc=0.8536, best valid acc=0.8565
main.py:train_model: [Epoch 279 Batch 5000/17173] loss=0.4329, acc=0.8322
main.py:train_model: [Epoch 279 Batch 10000/17173] loss=0.4341, acc=0.8319
main.py:train_model: [Epoch 279 Batch 15000/17173] loss=0.4346, acc=0.8312
main.py:train_model: [Epoch 279] valid loss=0.3914, valid acc=0.8545, best valid acc=0.8565
main.py:train_model: [Epoch 280 Batch 5000/17173] loss=0.4344, acc=0.8308
main.py:train_model: [Epoch 280 Batch 10000/17173] loss=0.4334, acc=0.8313
main.py:train_model: [Epoch 280 Batch 15000/17173] loss=0.4329, acc=0.8321
main.py:train_model: [Epoch 280] valid loss=0.3893, valid acc=0.8538, best valid acc=0.8565
main.py:train_model: [Epoch 281 Batch 5000/17173] loss=0.4325, acc=0.8309
main.py:train_model: [Epoch 281 Batch 10000/17173] loss=0.4324, acc=0.8322
main.py:train_model: [Epoch 281 Batch 15000/17173] loss=0.4360, acc=0.8306
main.py:train_model: [Epoch 281] valid loss=0.3930, valid acc=0.8523, best valid acc=0.8565
main.py:train_model: [Epoch 282 Batch 5000/17173] loss=0.4302, acc=0.8337
main.py:train_model: [Epoch 282 Batch 10000/17173] loss=0.4349, acc=0.8309
main.py:train_model: [Epoch 282 Batch 15000/17173] loss=0.4342, acc=0.8311
main.py:train_model: [Epoch 282] valid loss=0.3905, valid acc=0.8549, best valid acc=0.8565
main.py:train_model: [Epoch 283 Batch 5000/17173] loss=0.4320, acc=0.8322
main.py:train_model: [Epoch 283 Batch 10000/17173] loss=0.4333, acc=0.8315
main.py:train_model: [Epoch 283 Batch 15000/17173] loss=0.4346, acc=0.8314
main.py:train_model: [Epoch 283] valid loss=0.3944, valid acc=0.8532, best valid acc=0.8565
main.py:train_model: [Epoch 284 Batch 5000/17173] loss=0.4339, acc=0.8318
main.py:train_model: [Epoch 284 Batch 10000/17173] loss=0.4328, acc=0.8320
main.py:train_model: [Epoch 284 Batch 15000/17173] loss=0.4329, acc=0.8327
main.py:train_model: [Epoch 284] valid loss=0.3926, valid acc=0.8543, best valid acc=0.8565
main.py:train_model: [Epoch 285 Batch 5000/17173] loss=0.4315, acc=0.8320
main.py:train_model: [Epoch 285 Batch 10000/17173] loss=0.4345, acc=0.8318
main.py:train_model: [Epoch 285 Batch 15000/17173] loss=0.4329, acc=0.8315
main.py:train_model: [Epoch 285] valid loss=0.3927, valid acc=0.8549, best valid acc=0.8565
main.py:train_model: [Epoch 286 Batch 5000/17173] loss=0.4332, acc=0.8315
main.py:train_model: [Epoch 286 Batch 10000/17173] loss=0.4311, acc=0.8327
main.py:train_model: [Epoch 286 Batch 15000/17173] loss=0.4321, acc=0.8319
main.py:train_model: [Epoch 286] valid loss=0.3942, valid acc=0.8547, best valid acc=0.8565
main.py:train_model: [Epoch 287 Batch 5000/17173] loss=0.4304, acc=0.8330
main.py:train_model: [Epoch 287 Batch 10000/17173] loss=0.4299, acc=0.8329
main.py:train_model: [Epoch 287 Batch 15000/17173] loss=0.4347, acc=0.8309
main.py:train_model: [Epoch 287] valid loss=0.3916, valid acc=0.8550, best valid acc=0.8565
main.py:train_model: [Epoch 288 Batch 5000/17173] loss=0.4344, acc=0.8313
main.py:train_model: [Epoch 288 Batch 10000/17173] loss=0.4333, acc=0.8319
main.py:train_model: [Epoch 288 Batch 15000/17173] loss=0.4326, acc=0.8322
main.py:train_model: [Epoch 288] valid loss=0.3906, valid acc=0.8542, best valid acc=0.8565
main.py:train_model: [Epoch 289 Batch 5000/17173] loss=0.4323, acc=0.8321
main.py:train_model: [Epoch 289 Batch 10000/17173] loss=0.4317, acc=0.8331
main.py:train_model: [Epoch 289 Batch 15000/17173] loss=0.4336, acc=0.8315
main.py:train_model: [Epoch 289] valid loss=0.3898, valid acc=0.8554, best valid acc=0.8565
main.py:train_model: [Epoch 290 Batch 5000/17173] loss=0.4347, acc=0.8304
main.py:train_model: [Epoch 290 Batch 10000/17173] loss=0.4338, acc=0.8317
main.py:train_model: [Epoch 290 Batch 15000/17173] loss=0.4280, acc=0.8337
main.py:train_model: [Epoch 290] valid loss=0.3917, valid acc=0.8526, best valid acc=0.8565
main.py:train_model: [Epoch 291 Batch 5000/17173] loss=0.4297, acc=0.8349
main.py:train_model: [Epoch 291 Batch 10000/17173] loss=0.4354, acc=0.8310
main.py:train_model: [Epoch 291 Batch 15000/17173] loss=0.4318, acc=0.8332
main.py:train_model: [Epoch 291] valid loss=0.3885, valid acc=0.8557, best valid acc=0.8565
main.py:train_model: [Epoch 292 Batch 5000/17173] loss=0.4305, acc=0.8324
main.py:train_model: [Epoch 292 Batch 10000/17173] loss=0.4322, acc=0.8327
main.py:train_model: [Epoch 292 Batch 15000/17173] loss=0.4349, acc=0.8304
main.py:train_model: [Epoch 292] valid loss=0.3928, valid acc=0.8521, best valid acc=0.8565
main.py:train_model: [Epoch 293 Batch 5000/17173] loss=0.4314, acc=0.8323
main.py:train_model: [Epoch 293 Batch 10000/17173] loss=0.4345, acc=0.8314
main.py:train_model: [Epoch 293 Batch 15000/17173] loss=0.4309, acc=0.8323
main.py:train_model: [Epoch 293] valid loss=0.3905, valid acc=0.8530, best valid acc=0.8565
main.py:train_model: [Epoch 294 Batch 5000/17173] loss=0.4314, acc=0.8330
main.py:train_model: [Epoch 294 Batch 10000/17173] loss=0.4344, acc=0.8312
main.py:train_model: [Epoch 294 Batch 15000/17173] loss=0.4319, acc=0.8325
main.py:train_model: [Epoch 294] valid loss=0.3912, valid acc=0.8539, best valid acc=0.8565
main.py:train_model: [Epoch 295 Batch 5000/17173] loss=0.4298, acc=0.8330
main.py:train_model: [Epoch 295 Batch 10000/17173] loss=0.4318, acc=0.8320
main.py:train_model: [Epoch 295 Batch 15000/17173] loss=0.4318, acc=0.8320
main.py:train_model: [Epoch 295] valid loss=0.3903, valid acc=0.8550, best valid acc=0.8565
main.py:train_model: [Epoch 296 Batch 5000/17173] loss=0.4324, acc=0.8316
main.py:train_model: [Epoch 296 Batch 10000/17173] loss=0.4321, acc=0.8320
main.py:train_model: [Epoch 296 Batch 15000/17173] loss=0.4345, acc=0.8314
main.py:train_model: [Epoch 296] valid loss=0.3897, valid acc=0.8550, best valid acc=0.8565
main.py:train_model: [Epoch 297 Batch 5000/17173] loss=0.4329, acc=0.8326
main.py:train_model: [Epoch 297 Batch 10000/17173] loss=0.4325, acc=0.8317
main.py:train_model: [Epoch 297 Batch 15000/17173] loss=0.4322, acc=0.8327
main.py:train_model: [Epoch 297] valid loss=0.3922, valid acc=0.8543, best valid acc=0.8565
main.py:train_model: [Epoch 298 Batch 5000/17173] loss=0.4309, acc=0.8322
main.py:train_model: [Epoch 298 Batch 10000/17173] loss=0.4322, acc=0.8328
main.py:train_model: [Epoch 298 Batch 15000/17173] loss=0.4343, acc=0.8312
main.py:train_model: [Epoch 298] valid loss=0.3892, valid acc=0.8552, best valid acc=0.8565
main.py:train_model: [Epoch 299 Batch 5000/17173] loss=0.4306, acc=0.8338
main.py:train_model: [Epoch 299 Batch 10000/17173] loss=0.4334, acc=0.8310
main.py:train_model: [Epoch 299 Batch 15000/17173] loss=0.4319, acc=0.8328
main.py:train_model: [Epoch 299] valid loss=0.3903, valid acc=0.8551, best valid acc=0.8565
You can’t perform that action at this time.