2023-10-17 14:10:33,346 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:10:33,347 Model: "SequenceTagger( (embeddings): TransformerWordEmbeddings( (model): ElectraModel( (embeddings): ElectraEmbeddings( (word_embeddings): Embedding(32001, 768) (position_embeddings): Embedding(512, 768) (token_type_embeddings): Embedding(2, 768) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (encoder): ElectraEncoder( (layer): ModuleList( (0-11): 12 x ElectraLayer( (attention): ElectraAttention( (self): ElectraSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): ElectraSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): ElectraIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): ElectraOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) ) ) ) (locked_dropout): LockedDropout(p=0.5) (linear): Linear(in_features=768, out_features=13, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-17 14:10:33,347 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:10:33,347 MultiCorpus: 7936 train + 992 dev + 992 test sentences - NER_ICDAR_EUROPEANA Corpus: 7936 train + 992 dev + 992 test sentences - /root/.flair/datasets/ner_icdar_europeana/fr 2023-10-17 14:10:33,347 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:10:33,347 Train: 7936 sentences 2023-10-17 14:10:33,347 (train_with_dev=False, train_with_test=False) 2023-10-17 14:10:33,347 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:10:33,347 Training Params: 2023-10-17 14:10:33,347 - learning_rate: "5e-05" 2023-10-17 14:10:33,347 - mini_batch_size: "8" 2023-10-17 14:10:33,347 - max_epochs: "10" 2023-10-17 14:10:33,348 - shuffle: "True" 2023-10-17 14:10:33,348 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:10:33,348 Plugins: 2023-10-17 14:10:33,348 - TensorboardLogger 2023-10-17 14:10:33,348 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 14:10:33,348 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:10:33,348 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 14:10:33,348 - metric: "('micro avg', 'f1-score')" 2023-10-17 14:10:33,348 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:10:33,348 Computation: 2023-10-17 14:10:33,348 - compute on device: cuda:0 2023-10-17 14:10:33,348 - embedding storage: none 2023-10-17 14:10:33,348 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:10:33,348 Model training base path: "hmbench-icdar/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" 2023-10-17 14:10:33,348 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:10:33,348 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:10:33,348 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 14:10:39,222 epoch 1 - iter 99/992 - loss 2.56583698 - time (sec): 5.87 - samples/sec: 2821.57 - lr: 0.000005 - momentum: 0.000000 2023-10-17 14:10:45,260 epoch 1 - iter 198/992 - loss 1.44067154 - time (sec): 11.91 - samples/sec: 2815.77 - lr: 0.000010 - momentum: 0.000000 2023-10-17 14:10:50,904 epoch 1 - iter 297/992 - loss 1.06311481 - time (sec): 17.56 - samples/sec: 2793.50 - lr: 0.000015 - momentum: 0.000000 2023-10-17 14:10:56,606 epoch 1 - iter 396/992 - loss 0.85235507 - time (sec): 23.26 - samples/sec: 2791.92 - lr: 0.000020 - momentum: 0.000000 2023-10-17 14:11:02,780 epoch 1 - iter 495/992 - loss 0.70397019 - time (sec): 29.43 - samples/sec: 2809.19 - lr: 0.000025 - momentum: 0.000000 2023-10-17 14:11:08,842 epoch 1 - iter 594/992 - loss 0.61754102 - time (sec): 35.49 - samples/sec: 2781.20 - lr: 0.000030 - momentum: 0.000000 2023-10-17 14:11:14,877 epoch 1 - iter 693/992 - loss 0.55425408 - time (sec): 41.53 - samples/sec: 2767.88 - lr: 0.000035 - momentum: 0.000000 2023-10-17 14:11:21,011 epoch 1 - iter 792/992 - loss 0.50304327 - time (sec): 47.66 - samples/sec: 2761.17 - lr: 0.000040 - momentum: 0.000000 2023-10-17 14:11:26,898 epoch 1 - iter 891/992 - loss 0.46403461 - time (sec): 53.55 - samples/sec: 2766.86 - lr: 0.000045 - momentum: 0.000000 2023-10-17 14:11:33,013 epoch 1 - iter 990/992 - loss 0.43242766 - time (sec): 59.66 - samples/sec: 2743.63 - lr: 0.000050 - momentum: 0.000000 2023-10-17 14:11:33,117 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:11:33,117 EPOCH 1 done: loss 0.4321 - lr: 0.000050 2023-10-17 14:11:36,203 DEV : loss 0.08887125551700592 - f1-score (micro avg) 0.7233 2023-10-17 14:11:36,224 saving best model 2023-10-17 14:11:36,696 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:11:42,469 epoch 2 - iter 99/992 - loss 0.11598058 - time (sec): 5.77 - samples/sec: 2830.44 - lr: 0.000049 - momentum: 0.000000 2023-10-17 14:11:48,383 epoch 2 - iter 198/992 - loss 0.11266582 - time (sec): 11.69 - samples/sec: 2820.53 - lr: 0.000049 - momentum: 0.000000 2023-10-17 14:11:54,000 epoch 2 - iter 297/992 - loss 0.11132229 - time (sec): 17.30 - samples/sec: 2803.21 - lr: 0.000048 - momentum: 0.000000 2023-10-17 14:11:59,687 epoch 2 - iter 396/992 - loss 0.11223753 - time (sec): 22.99 - samples/sec: 2812.50 - lr: 0.000048 - momentum: 0.000000 2023-10-17 14:12:05,527 epoch 2 - iter 495/992 - loss 0.10847458 - time (sec): 28.83 - samples/sec: 2810.26 - lr: 0.000047 - momentum: 0.000000 2023-10-17 14:12:11,595 epoch 2 - iter 594/992 - loss 0.10790183 - time (sec): 34.90 - samples/sec: 2794.95 - lr: 0.000047 - momentum: 0.000000 2023-10-17 14:12:17,710 epoch 2 - iter 693/992 - loss 0.10908683 - time (sec): 41.01 - samples/sec: 2796.29 - lr: 0.000046 - momentum: 0.000000 2023-10-17 14:12:23,919 epoch 2 - iter 792/992 - loss 0.10920125 - time (sec): 47.22 - samples/sec: 2773.55 - lr: 0.000046 - momentum: 0.000000 2023-10-17 14:12:29,935 epoch 2 - iter 891/992 - loss 0.10838687 - time (sec): 53.24 - samples/sec: 2760.47 - lr: 0.000045 - momentum: 0.000000 2023-10-17 14:12:35,919 epoch 2 - iter 990/992 - loss 0.10734045 - time (sec): 59.22 - samples/sec: 2766.07 - lr: 0.000044 - momentum: 0.000000 2023-10-17 14:12:36,025 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:12:36,025 EPOCH 2 done: loss 0.1074 - lr: 0.000044 2023-10-17 14:12:39,465 DEV : loss 0.08363784104585648 - f1-score (micro avg) 0.7596 2023-10-17 14:12:39,487 saving best model 2023-10-17 14:12:40,074 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:12:46,174 epoch 3 - iter 99/992 - loss 0.07378378 - time (sec): 6.10 - samples/sec: 2782.50 - lr: 0.000044 - momentum: 0.000000 2023-10-17 14:12:52,120 epoch 3 - iter 198/992 - loss 0.07492355 - time (sec): 12.04 - samples/sec: 2770.67 - lr: 0.000043 - momentum: 0.000000 2023-10-17 14:12:57,854 epoch 3 - iter 297/992 - loss 0.07489005 - time (sec): 17.78 - samples/sec: 2780.55 - lr: 0.000043 - momentum: 0.000000 2023-10-17 14:13:03,942 epoch 3 - iter 396/992 - loss 0.07422590 - time (sec): 23.87 - samples/sec: 2761.11 - lr: 0.000042 - momentum: 0.000000 2023-10-17 14:13:09,975 epoch 3 - iter 495/992 - loss 0.07723264 - time (sec): 29.90 - samples/sec: 2764.56 - lr: 0.000042 - momentum: 0.000000 2023-10-17 14:13:16,155 epoch 3 - iter 594/992 - loss 0.07724225 - time (sec): 36.08 - samples/sec: 2761.92 - lr: 0.000041 - momentum: 0.000000 2023-10-17 14:13:22,176 epoch 3 - iter 693/992 - loss 0.07604513 - time (sec): 42.10 - samples/sec: 2774.23 - lr: 0.000041 - momentum: 0.000000 2023-10-17 14:13:28,294 epoch 3 - iter 792/992 - loss 0.07536649 - time (sec): 48.22 - samples/sec: 2761.96 - lr: 0.000040 - momentum: 0.000000 2023-10-17 14:13:34,071 epoch 3 - iter 891/992 - loss 0.07551830 - time (sec): 53.99 - samples/sec: 2754.35 - lr: 0.000039 - momentum: 0.000000 2023-10-17 14:13:39,833 epoch 3 - iter 990/992 - loss 0.07517252 - time (sec): 59.76 - samples/sec: 2739.02 - lr: 0.000039 - momentum: 0.000000 2023-10-17 14:13:39,973 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:13:39,974 EPOCH 3 done: loss 0.0751 - lr: 0.000039 2023-10-17 14:13:43,451 DEV : loss 0.1065104603767395 - f1-score (micro avg) 0.748 2023-10-17 14:13:43,475 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:13:49,475 epoch 4 - iter 99/992 - loss 0.04524979 - time (sec): 6.00 - samples/sec: 2803.07 - lr: 0.000038 - momentum: 0.000000 2023-10-17 14:13:55,680 epoch 4 - iter 198/992 - loss 0.05478362 - time (sec): 12.20 - samples/sec: 2690.30 - lr: 0.000038 - momentum: 0.000000 2023-10-17 14:14:01,531 epoch 4 - iter 297/992 - loss 0.05412289 - time (sec): 18.05 - samples/sec: 2698.58 - lr: 0.000037 - momentum: 0.000000 2023-10-17 14:14:07,545 epoch 4 - iter 396/992 - loss 0.05506235 - time (sec): 24.07 - samples/sec: 2730.99 - lr: 0.000037 - momentum: 0.000000 2023-10-17 14:14:13,343 epoch 4 - iter 495/992 - loss 0.05562356 - time (sec): 29.87 - samples/sec: 2748.67 - lr: 0.000036 - momentum: 0.000000 2023-10-17 14:14:19,477 epoch 4 - iter 594/992 - loss 0.05609226 - time (sec): 36.00 - samples/sec: 2751.59 - lr: 0.000036 - momentum: 0.000000 2023-10-17 14:14:25,172 epoch 4 - iter 693/992 - loss 0.05560238 - time (sec): 41.70 - samples/sec: 2758.09 - lr: 0.000035 - momentum: 0.000000 2023-10-17 14:14:31,622 epoch 4 - iter 792/992 - loss 0.05713362 - time (sec): 48.15 - samples/sec: 2727.19 - lr: 0.000034 - momentum: 0.000000 2023-10-17 14:14:37,562 epoch 4 - iter 891/992 - loss 0.05527867 - time (sec): 54.09 - samples/sec: 2723.46 - lr: 0.000034 - momentum: 0.000000 2023-10-17 14:14:43,601 epoch 4 - iter 990/992 - loss 0.05470377 - time (sec): 60.12 - samples/sec: 2723.71 - lr: 0.000033 - momentum: 0.000000 2023-10-17 14:14:43,697 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:14:43,697 EPOCH 4 done: loss 0.0547 - lr: 0.000033 2023-10-17 14:14:47,132 DEV : loss 0.13179177045822144 - f1-score (micro avg) 0.7556 2023-10-17 14:14:47,153 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:14:52,850 epoch 5 - iter 99/992 - loss 0.05176063 - time (sec): 5.70 - samples/sec: 2801.03 - lr: 0.000033 - momentum: 0.000000 2023-10-17 14:14:58,673 epoch 5 - iter 198/992 - loss 0.04599398 - time (sec): 11.52 - samples/sec: 2830.16 - lr: 0.000032 - momentum: 0.000000 2023-10-17 14:15:04,479 epoch 5 - iter 297/992 - loss 0.04300166 - time (sec): 17.32 - samples/sec: 2790.18 - lr: 0.000032 - momentum: 0.000000 2023-10-17 14:15:10,429 epoch 5 - iter 396/992 - loss 0.04689564 - time (sec): 23.27 - samples/sec: 2771.19 - lr: 0.000031 - momentum: 0.000000 2023-10-17 14:15:16,294 epoch 5 - iter 495/992 - loss 0.04522045 - time (sec): 29.14 - samples/sec: 2782.82 - lr: 0.000031 - momentum: 0.000000 2023-10-17 14:15:22,519 epoch 5 - iter 594/992 - loss 0.04434071 - time (sec): 35.36 - samples/sec: 2778.12 - lr: 0.000030 - momentum: 0.000000 2023-10-17 14:15:28,400 epoch 5 - iter 693/992 - loss 0.04509966 - time (sec): 41.25 - samples/sec: 2783.70 - lr: 0.000029 - momentum: 0.000000 2023-10-17 14:15:34,527 epoch 5 - iter 792/992 - loss 0.04488398 - time (sec): 47.37 - samples/sec: 2777.19 - lr: 0.000029 - momentum: 0.000000 2023-10-17 14:15:40,289 epoch 5 - iter 891/992 - loss 0.04506764 - time (sec): 53.13 - samples/sec: 2779.31 - lr: 0.000028 - momentum: 0.000000 2023-10-17 14:15:46,075 epoch 5 - iter 990/992 - loss 0.04560631 - time (sec): 58.92 - samples/sec: 2776.63 - lr: 0.000028 - momentum: 0.000000 2023-10-17 14:15:46,209 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:15:46,209 EPOCH 5 done: loss 0.0455 - lr: 0.000028 2023-10-17 14:15:49,653 DEV : loss 0.16570182144641876 - f1-score (micro avg) 0.7598 2023-10-17 14:15:49,677 saving best model 2023-10-17 14:15:50,266 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:15:56,488 epoch 6 - iter 99/992 - loss 0.03548701 - time (sec): 6.22 - samples/sec: 2691.46 - lr: 0.000027 - momentum: 0.000000 2023-10-17 14:16:02,509 epoch 6 - iter 198/992 - loss 0.03164832 - time (sec): 12.24 - samples/sec: 2707.48 - lr: 0.000027 - momentum: 0.000000 2023-10-17 14:16:08,671 epoch 6 - iter 297/992 - loss 0.03207736 - time (sec): 18.40 - samples/sec: 2692.61 - lr: 0.000026 - momentum: 0.000000 2023-10-17 14:16:14,599 epoch 6 - iter 396/992 - loss 0.03177863 - time (sec): 24.33 - samples/sec: 2718.45 - lr: 0.000026 - momentum: 0.000000 2023-10-17 14:16:20,727 epoch 6 - iter 495/992 - loss 0.03190660 - time (sec): 30.46 - samples/sec: 2725.37 - lr: 0.000025 - momentum: 0.000000 2023-10-17 14:16:26,730 epoch 6 - iter 594/992 - loss 0.03263403 - time (sec): 36.46 - samples/sec: 2715.91 - lr: 0.000024 - momentum: 0.000000 2023-10-17 14:16:32,715 epoch 6 - iter 693/992 - loss 0.03190880 - time (sec): 42.45 - samples/sec: 2743.76 - lr: 0.000024 - momentum: 0.000000 2023-10-17 14:16:38,628 epoch 6 - iter 792/992 - loss 0.03117610 - time (sec): 48.36 - samples/sec: 2738.62 - lr: 0.000023 - momentum: 0.000000 2023-10-17 14:16:44,371 epoch 6 - iter 891/992 - loss 0.03097983 - time (sec): 54.10 - samples/sec: 2738.45 - lr: 0.000023 - momentum: 0.000000 2023-10-17 14:16:50,118 epoch 6 - iter 990/992 - loss 0.03122063 - time (sec): 59.85 - samples/sec: 2734.90 - lr: 0.000022 - momentum: 0.000000 2023-10-17 14:16:50,219 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:16:50,219 EPOCH 6 done: loss 0.0312 - lr: 0.000022 2023-10-17 14:16:53,684 DEV : loss 0.18113002181053162 - f1-score (micro avg) 0.767 2023-10-17 14:16:53,705 saving best model 2023-10-17 14:16:54,157 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:16:59,988 epoch 7 - iter 99/992 - loss 0.02597015 - time (sec): 5.83 - samples/sec: 2684.60 - lr: 0.000022 - momentum: 0.000000 2023-10-17 14:17:06,231 epoch 7 - iter 198/992 - loss 0.02169306 - time (sec): 12.07 - samples/sec: 2712.41 - lr: 0.000021 - momentum: 0.000000 2023-10-17 14:17:12,255 epoch 7 - iter 297/992 - loss 0.02197468 - time (sec): 18.10 - samples/sec: 2712.38 - lr: 0.000021 - momentum: 0.000000 2023-10-17 14:17:18,365 epoch 7 - iter 396/992 - loss 0.02241929 - time (sec): 24.21 - samples/sec: 2694.37 - lr: 0.000020 - momentum: 0.000000 2023-10-17 14:17:24,253 epoch 7 - iter 495/992 - loss 0.02267823 - time (sec): 30.10 - samples/sec: 2714.40 - lr: 0.000019 - momentum: 0.000000 2023-10-17 14:17:30,023 epoch 7 - iter 594/992 - loss 0.02246580 - time (sec): 35.87 - samples/sec: 2715.96 - lr: 0.000019 - momentum: 0.000000 2023-10-17 14:17:35,851 epoch 7 - iter 693/992 - loss 0.02190549 - time (sec): 41.69 - samples/sec: 2716.69 - lr: 0.000018 - momentum: 0.000000 2023-10-17 14:17:41,839 epoch 7 - iter 792/992 - loss 0.02218982 - time (sec): 47.68 - samples/sec: 2718.42 - lr: 0.000018 - momentum: 0.000000 2023-10-17 14:17:47,671 epoch 7 - iter 891/992 - loss 0.02196221 - time (sec): 53.51 - samples/sec: 2725.79 - lr: 0.000017 - momentum: 0.000000 2023-10-17 14:17:54,071 epoch 7 - iter 990/992 - loss 0.02230131 - time (sec): 59.91 - samples/sec: 2731.72 - lr: 0.000017 - momentum: 0.000000 2023-10-17 14:17:54,194 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:17:54,194 EPOCH 7 done: loss 0.0223 - lr: 0.000017 2023-10-17 14:17:58,301 DEV : loss 0.19615165889263153 - f1-score (micro avg) 0.7561 2023-10-17 14:17:58,323 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:18:04,361 epoch 8 - iter 99/992 - loss 0.01117805 - time (sec): 6.04 - samples/sec: 2648.12 - lr: 0.000016 - momentum: 0.000000 2023-10-17 14:18:10,390 epoch 8 - iter 198/992 - loss 0.01283703 - time (sec): 12.07 - samples/sec: 2680.35 - lr: 0.000016 - momentum: 0.000000 2023-10-17 14:18:16,340 epoch 8 - iter 297/992 - loss 0.01697295 - time (sec): 18.02 - samples/sec: 2662.18 - lr: 0.000015 - momentum: 0.000000 2023-10-17 14:18:22,180 epoch 8 - iter 396/992 - loss 0.01691545 - time (sec): 23.86 - samples/sec: 2686.17 - lr: 0.000014 - momentum: 0.000000 2023-10-17 14:18:28,167 epoch 8 - iter 495/992 - loss 0.01590682 - time (sec): 29.84 - samples/sec: 2703.03 - lr: 0.000014 - momentum: 0.000000 2023-10-17 14:18:34,030 epoch 8 - iter 594/992 - loss 0.01525603 - time (sec): 35.71 - samples/sec: 2727.45 - lr: 0.000013 - momentum: 0.000000 2023-10-17 14:18:39,887 epoch 8 - iter 693/992 - loss 0.01579587 - time (sec): 41.56 - samples/sec: 2718.25 - lr: 0.000013 - momentum: 0.000000 2023-10-17 14:18:46,164 epoch 8 - iter 792/992 - loss 0.01527372 - time (sec): 47.84 - samples/sec: 2719.87 - lr: 0.000012 - momentum: 0.000000 2023-10-17 14:18:52,001 epoch 8 - iter 891/992 - loss 0.01527021 - time (sec): 53.68 - samples/sec: 2733.81 - lr: 0.000012 - momentum: 0.000000 2023-10-17 14:18:58,203 epoch 8 - iter 990/992 - loss 0.01606507 - time (sec): 59.88 - samples/sec: 2733.60 - lr: 0.000011 - momentum: 0.000000 2023-10-17 14:18:58,303 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:18:58,303 EPOCH 8 done: loss 0.0160 - lr: 0.000011 2023-10-17 14:19:01,691 DEV : loss 0.22577238082885742 - f1-score (micro avg) 0.7635 2023-10-17 14:19:01,712 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:19:07,524 epoch 9 - iter 99/992 - loss 0.00989044 - time (sec): 5.81 - samples/sec: 2697.63 - lr: 0.000011 - momentum: 0.000000 2023-10-17 14:19:13,330 epoch 9 - iter 198/992 - loss 0.01505293 - time (sec): 11.62 - samples/sec: 2783.58 - lr: 0.000010 - momentum: 0.000000 2023-10-17 14:19:19,081 epoch 9 - iter 297/992 - loss 0.01350984 - time (sec): 17.37 - samples/sec: 2745.86 - lr: 0.000009 - momentum: 0.000000 2023-10-17 14:19:25,043 epoch 9 - iter 396/992 - loss 0.01226420 - time (sec): 23.33 - samples/sec: 2731.47 - lr: 0.000009 - momentum: 0.000000 2023-10-17 14:19:30,941 epoch 9 - iter 495/992 - loss 0.01239703 - time (sec): 29.23 - samples/sec: 2743.58 - lr: 0.000008 - momentum: 0.000000 2023-10-17 14:19:37,003 epoch 9 - iter 594/992 - loss 0.01210630 - time (sec): 35.29 - samples/sec: 2739.17 - lr: 0.000008 - momentum: 0.000000 2023-10-17 14:19:43,129 epoch 9 - iter 693/992 - loss 0.01202169 - time (sec): 41.42 - samples/sec: 2746.32 - lr: 0.000007 - momentum: 0.000000 2023-10-17 14:19:49,259 epoch 9 - iter 792/992 - loss 0.01182813 - time (sec): 47.55 - samples/sec: 2749.42 - lr: 0.000007 - momentum: 0.000000 2023-10-17 14:19:55,176 epoch 9 - iter 891/992 - loss 0.01183421 - time (sec): 53.46 - samples/sec: 2746.32 - lr: 0.000006 - momentum: 0.000000 2023-10-17 14:20:01,241 epoch 9 - iter 990/992 - loss 0.01157965 - time (sec): 59.53 - samples/sec: 2748.33 - lr: 0.000006 - momentum: 0.000000 2023-10-17 14:20:01,395 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:20:01,395 EPOCH 9 done: loss 0.0116 - lr: 0.000006 2023-10-17 14:20:04,942 DEV : loss 0.21687279641628265 - f1-score (micro avg) 0.7509 2023-10-17 14:20:04,963 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:20:10,822 epoch 10 - iter 99/992 - loss 0.00708023 - time (sec): 5.86 - samples/sec: 2779.19 - lr: 0.000005 - momentum: 0.000000 2023-10-17 14:20:16,971 epoch 10 - iter 198/992 - loss 0.00762459 - time (sec): 12.01 - samples/sec: 2789.93 - lr: 0.000004 - momentum: 0.000000 2023-10-17 14:20:22,928 epoch 10 - iter 297/992 - loss 0.00709401 - time (sec): 17.96 - samples/sec: 2760.24 - lr: 0.000004 - momentum: 0.000000 2023-10-17 14:20:28,815 epoch 10 - iter 396/992 - loss 0.00681691 - time (sec): 23.85 - samples/sec: 2739.23 - lr: 0.000003 - momentum: 0.000000 2023-10-17 14:20:34,724 epoch 10 - iter 495/992 - loss 0.00708234 - time (sec): 29.76 - samples/sec: 2750.97 - lr: 0.000003 - momentum: 0.000000 2023-10-17 14:20:40,813 epoch 10 - iter 594/992 - loss 0.00757164 - time (sec): 35.85 - samples/sec: 2743.70 - lr: 0.000002 - momentum: 0.000000 2023-10-17 14:20:46,718 epoch 10 - iter 693/992 - loss 0.00802286 - time (sec): 41.75 - samples/sec: 2750.56 - lr: 0.000002 - momentum: 0.000000 2023-10-17 14:20:52,723 epoch 10 - iter 792/992 - loss 0.00785135 - time (sec): 47.76 - samples/sec: 2749.46 - lr: 0.000001 - momentum: 0.000000 2023-10-17 14:20:58,677 epoch 10 - iter 891/992 - loss 0.00789678 - time (sec): 53.71 - samples/sec: 2743.95 - lr: 0.000001 - momentum: 0.000000 2023-10-17 14:21:04,642 epoch 10 - iter 990/992 - loss 0.00784035 - time (sec): 59.68 - samples/sec: 2743.80 - lr: 0.000000 - momentum: 0.000000 2023-10-17 14:21:04,763 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:21:04,763 EPOCH 10 done: loss 0.0078 - lr: 0.000000 2023-10-17 14:21:08,189 DEV : loss 0.23605531454086304 - f1-score (micro avg) 0.7495 2023-10-17 14:21:08,645 ---------------------------------------------------------------------------------------------------- 2023-10-17 14:21:08,646 Loading model from best epoch ... 2023-10-17 14:21:10,060 SequenceTagger predicts: Dictionary with 13 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG 2023-10-17 14:21:13,417 Results: - F-score (micro) 0.7731 - F-score (macro) 0.6853 - Accuracy 0.6466 By class: precision recall f1-score support LOC 0.8043 0.8534 0.8281 655 PER 0.7066 0.8206 0.7593 223 ORG 0.5474 0.4094 0.4685 127 micro avg 0.7569 0.7900 0.7731 1005 macro avg 0.6861 0.6945 0.6853 1005 weighted avg 0.7502 0.7900 0.7674 1005 2023-10-17 14:21:13,417 ----------------------------------------------------------------------------------------------------