2023-10-17 20:39:11,480 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:11,481 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=17, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-17 20:39:11,481 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:11,481 MultiCorpus: 1085 train + 148 dev + 364 test sentences - NER_HIPE_2022 Corpus: 1085 train + 148 dev + 364 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/sv/with_doc_seperator 2023-10-17 20:39:11,481 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:11,481 Train: 1085 sentences 2023-10-17 20:39:11,482 (train_with_dev=False, train_with_test=False) 2023-10-17 20:39:11,482 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:11,482 Training Params: 2023-10-17 20:39:11,482 - learning_rate: "3e-05" 2023-10-17 20:39:11,482 - mini_batch_size: "8" 2023-10-17 20:39:11,482 - max_epochs: "10" 2023-10-17 20:39:11,482 - shuffle: "True" 2023-10-17 20:39:11,482 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:11,482 Plugins: 2023-10-17 20:39:11,482 - TensorboardLogger 2023-10-17 20:39:11,482 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 20:39:11,482 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:11,482 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 20:39:11,482 - metric: "('micro avg', 'f1-score')" 2023-10-17 20:39:11,482 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:11,482 Computation: 2023-10-17 20:39:11,482 - compute on device: cuda:0 2023-10-17 20:39:11,482 - embedding storage: none 2023-10-17 20:39:11,482 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:11,482 Model training base path: "hmbench-newseye/sv-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" 2023-10-17 20:39:11,482 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:11,482 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:11,482 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 20:39:12,671 epoch 1 - iter 13/136 - loss 3.66351920 - time (sec): 1.19 - samples/sec: 4185.66 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:39:14,181 epoch 1 - iter 26/136 - loss 3.35094627 - time (sec): 2.70 - samples/sec: 3722.76 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:39:15,811 epoch 1 - iter 39/136 - loss 2.78889854 - time (sec): 4.33 - samples/sec: 3789.25 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:39:17,138 epoch 1 - iter 52/136 - loss 2.32130470 - time (sec): 5.66 - samples/sec: 3843.28 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:39:18,491 epoch 1 - iter 65/136 - loss 2.05154624 - time (sec): 7.01 - samples/sec: 3723.34 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:39:19,960 epoch 1 - iter 78/136 - loss 1.82218984 - time (sec): 8.48 - samples/sec: 3638.21 - lr: 0.000017 - momentum: 0.000000 2023-10-17 20:39:21,219 epoch 1 - iter 91/136 - loss 1.64923175 - time (sec): 9.74 - samples/sec: 3622.53 - lr: 0.000020 - momentum: 0.000000 2023-10-17 20:39:22,378 epoch 1 - iter 104/136 - loss 1.49725228 - time (sec): 10.89 - samples/sec: 3659.34 - lr: 0.000023 - momentum: 0.000000 2023-10-17 20:39:23,642 epoch 1 - iter 117/136 - loss 1.36546981 - time (sec): 12.16 - samples/sec: 3680.93 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:39:25,121 epoch 1 - iter 130/136 - loss 1.23847244 - time (sec): 13.64 - samples/sec: 3690.28 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:39:25,573 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:25,574 EPOCH 1 done: loss 1.2071 - lr: 0.000028 2023-10-17 20:39:26,432 DEV : loss 0.20332075655460358 - f1-score (micro avg) 0.5808 2023-10-17 20:39:26,436 saving best model 2023-10-17 20:39:26,828 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:27,986 epoch 2 - iter 13/136 - loss 0.18587840 - time (sec): 1.16 - samples/sec: 4009.69 - lr: 0.000030 - momentum: 0.000000 2023-10-17 20:39:29,351 epoch 2 - iter 26/136 - loss 0.19781664 - time (sec): 2.52 - samples/sec: 3563.72 - lr: 0.000029 - momentum: 0.000000 2023-10-17 20:39:30,710 epoch 2 - iter 39/136 - loss 0.20407721 - time (sec): 3.88 - samples/sec: 3624.52 - lr: 0.000029 - momentum: 0.000000 2023-10-17 20:39:32,113 epoch 2 - iter 52/136 - loss 0.19101613 - time (sec): 5.28 - samples/sec: 3685.94 - lr: 0.000029 - momentum: 0.000000 2023-10-17 20:39:33,309 epoch 2 - iter 65/136 - loss 0.18614276 - time (sec): 6.48 - samples/sec: 3715.90 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:39:34,677 epoch 2 - iter 78/136 - loss 0.17566842 - time (sec): 7.85 - samples/sec: 3735.36 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:39:36,076 epoch 2 - iter 91/136 - loss 0.18694374 - time (sec): 9.25 - samples/sec: 3712.42 - lr: 0.000028 - momentum: 0.000000 2023-10-17 20:39:37,199 epoch 2 - iter 104/136 - loss 0.18726542 - time (sec): 10.37 - samples/sec: 3713.87 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:39:38,767 epoch 2 - iter 117/136 - loss 0.18197226 - time (sec): 11.94 - samples/sec: 3700.41 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:39:40,506 epoch 2 - iter 130/136 - loss 0.17741685 - time (sec): 13.68 - samples/sec: 3667.22 - lr: 0.000027 - momentum: 0.000000 2023-10-17 20:39:41,046 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:41,046 EPOCH 2 done: loss 0.1749 - lr: 0.000027 2023-10-17 20:39:42,770 DEV : loss 0.13270148634910583 - f1-score (micro avg) 0.7061 2023-10-17 20:39:42,774 saving best model 2023-10-17 20:39:43,238 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:44,421 epoch 3 - iter 13/136 - loss 0.12680936 - time (sec): 1.18 - samples/sec: 3578.39 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:39:45,887 epoch 3 - iter 26/136 - loss 0.10390425 - time (sec): 2.64 - samples/sec: 3589.08 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:39:47,329 epoch 3 - iter 39/136 - loss 0.10053727 - time (sec): 4.09 - samples/sec: 3574.81 - lr: 0.000026 - momentum: 0.000000 2023-10-17 20:39:48,540 epoch 3 - iter 52/136 - loss 0.10624829 - time (sec): 5.30 - samples/sec: 3648.00 - lr: 0.000025 - momentum: 0.000000 2023-10-17 20:39:49,952 epoch 3 - iter 65/136 - loss 0.10754921 - time (sec): 6.71 - samples/sec: 3654.59 - lr: 0.000025 - momentum: 0.000000 2023-10-17 20:39:51,355 epoch 3 - iter 78/136 - loss 0.10617729 - time (sec): 8.11 - samples/sec: 3717.01 - lr: 0.000025 - momentum: 0.000000 2023-10-17 20:39:52,709 epoch 3 - iter 91/136 - loss 0.10565851 - time (sec): 9.47 - samples/sec: 3679.73 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:39:54,070 epoch 3 - iter 104/136 - loss 0.10009536 - time (sec): 10.83 - samples/sec: 3660.77 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:39:55,781 epoch 3 - iter 117/136 - loss 0.09902985 - time (sec): 12.54 - samples/sec: 3632.31 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:39:57,000 epoch 3 - iter 130/136 - loss 0.09674527 - time (sec): 13.76 - samples/sec: 3644.38 - lr: 0.000024 - momentum: 0.000000 2023-10-17 20:39:57,560 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:39:57,560 EPOCH 3 done: loss 0.0993 - lr: 0.000024 2023-10-17 20:39:59,043 DEV : loss 0.0991288274526596 - f1-score (micro avg) 0.7614 2023-10-17 20:39:59,049 saving best model 2023-10-17 20:39:59,521 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:40:00,996 epoch 4 - iter 13/136 - loss 0.05282612 - time (sec): 1.47 - samples/sec: 3232.44 - lr: 0.000023 - momentum: 0.000000 2023-10-17 20:40:02,432 epoch 4 - iter 26/136 - loss 0.06127360 - time (sec): 2.91 - samples/sec: 3346.40 - lr: 0.000023 - momentum: 0.000000 2023-10-17 20:40:03,973 epoch 4 - iter 39/136 - loss 0.05866787 - time (sec): 4.45 - samples/sec: 3296.44 - lr: 0.000022 - momentum: 0.000000 2023-10-17 20:40:05,425 epoch 4 - iter 52/136 - loss 0.05512121 - time (sec): 5.90 - samples/sec: 3341.79 - lr: 0.000022 - momentum: 0.000000 2023-10-17 20:40:07,041 epoch 4 - iter 65/136 - loss 0.05533475 - time (sec): 7.52 - samples/sec: 3417.43 - lr: 0.000022 - momentum: 0.000000 2023-10-17 20:40:08,319 epoch 4 - iter 78/136 - loss 0.05593976 - time (sec): 8.80 - samples/sec: 3483.99 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:40:09,788 epoch 4 - iter 91/136 - loss 0.05569689 - time (sec): 10.26 - samples/sec: 3456.40 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:40:11,121 epoch 4 - iter 104/136 - loss 0.06146163 - time (sec): 11.60 - samples/sec: 3476.78 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:40:12,351 epoch 4 - iter 117/136 - loss 0.06045633 - time (sec): 12.83 - samples/sec: 3511.82 - lr: 0.000021 - momentum: 0.000000 2023-10-17 20:40:13,785 epoch 4 - iter 130/136 - loss 0.05823953 - time (sec): 14.26 - samples/sec: 3489.25 - lr: 0.000020 - momentum: 0.000000 2023-10-17 20:40:14,386 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:40:14,387 EPOCH 4 done: loss 0.0590 - lr: 0.000020 2023-10-17 20:40:15,849 DEV : loss 0.11398832499980927 - f1-score (micro avg) 0.7549 2023-10-17 20:40:15,853 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:40:17,373 epoch 5 - iter 13/136 - loss 0.05351999 - time (sec): 1.52 - samples/sec: 3707.76 - lr: 0.000020 - momentum: 0.000000 2023-10-17 20:40:18,839 epoch 5 - iter 26/136 - loss 0.04693685 - time (sec): 2.98 - samples/sec: 3751.47 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:40:20,118 epoch 5 - iter 39/136 - loss 0.04291263 - time (sec): 4.26 - samples/sec: 3676.75 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:40:21,617 epoch 5 - iter 52/136 - loss 0.03825795 - time (sec): 5.76 - samples/sec: 3663.68 - lr: 0.000019 - momentum: 0.000000 2023-10-17 20:40:23,117 epoch 5 - iter 65/136 - loss 0.04225632 - time (sec): 7.26 - samples/sec: 3631.33 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:40:24,348 epoch 5 - iter 78/136 - loss 0.04081450 - time (sec): 8.49 - samples/sec: 3627.04 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:40:25,720 epoch 5 - iter 91/136 - loss 0.04086109 - time (sec): 9.87 - samples/sec: 3608.81 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:40:26,858 epoch 5 - iter 104/136 - loss 0.04108347 - time (sec): 11.00 - samples/sec: 3646.16 - lr: 0.000018 - momentum: 0.000000 2023-10-17 20:40:28,307 epoch 5 - iter 117/136 - loss 0.04124379 - time (sec): 12.45 - samples/sec: 3647.78 - lr: 0.000017 - momentum: 0.000000 2023-10-17 20:40:29,651 epoch 5 - iter 130/136 - loss 0.04185840 - time (sec): 13.80 - samples/sec: 3638.10 - lr: 0.000017 - momentum: 0.000000 2023-10-17 20:40:30,172 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:40:30,172 EPOCH 5 done: loss 0.0429 - lr: 0.000017 2023-10-17 20:40:31,636 DEV : loss 0.12549878656864166 - f1-score (micro avg) 0.7956 2023-10-17 20:40:31,640 saving best model 2023-10-17 20:40:32,126 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:40:33,534 epoch 6 - iter 13/136 - loss 0.02881144 - time (sec): 1.41 - samples/sec: 3590.06 - lr: 0.000016 - momentum: 0.000000 2023-10-17 20:40:34,762 epoch 6 - iter 26/136 - loss 0.03664492 - time (sec): 2.63 - samples/sec: 3601.53 - lr: 0.000016 - momentum: 0.000000 2023-10-17 20:40:36,113 epoch 6 - iter 39/136 - loss 0.03420146 - time (sec): 3.98 - samples/sec: 3672.73 - lr: 0.000016 - momentum: 0.000000 2023-10-17 20:40:37,606 epoch 6 - iter 52/136 - loss 0.03091671 - time (sec): 5.48 - samples/sec: 3619.03 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:40:39,092 epoch 6 - iter 65/136 - loss 0.02845803 - time (sec): 6.96 - samples/sec: 3593.86 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:40:40,730 epoch 6 - iter 78/136 - loss 0.02735186 - time (sec): 8.60 - samples/sec: 3571.10 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:40:42,066 epoch 6 - iter 91/136 - loss 0.02646650 - time (sec): 9.94 - samples/sec: 3550.71 - lr: 0.000015 - momentum: 0.000000 2023-10-17 20:40:43,402 epoch 6 - iter 104/136 - loss 0.02865805 - time (sec): 11.27 - samples/sec: 3552.07 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:40:44,931 epoch 6 - iter 117/136 - loss 0.02748370 - time (sec): 12.80 - samples/sec: 3559.68 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:40:46,191 epoch 6 - iter 130/136 - loss 0.02689993 - time (sec): 14.06 - samples/sec: 3550.44 - lr: 0.000014 - momentum: 0.000000 2023-10-17 20:40:46,715 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:40:46,715 EPOCH 6 done: loss 0.0276 - lr: 0.000014 2023-10-17 20:40:48,167 DEV : loss 0.13069528341293335 - f1-score (micro avg) 0.8163 2023-10-17 20:40:48,172 saving best model 2023-10-17 20:40:48,648 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:40:50,165 epoch 7 - iter 13/136 - loss 0.00713212 - time (sec): 1.51 - samples/sec: 3240.87 - lr: 0.000013 - momentum: 0.000000 2023-10-17 20:40:51,776 epoch 7 - iter 26/136 - loss 0.00668770 - time (sec): 3.12 - samples/sec: 3534.48 - lr: 0.000013 - momentum: 0.000000 2023-10-17 20:40:53,147 epoch 7 - iter 39/136 - loss 0.00787348 - time (sec): 4.50 - samples/sec: 3413.47 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:40:54,368 epoch 7 - iter 52/136 - loss 0.00951842 - time (sec): 5.72 - samples/sec: 3414.41 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:40:55,775 epoch 7 - iter 65/136 - loss 0.01119866 - time (sec): 7.12 - samples/sec: 3514.76 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:40:57,162 epoch 7 - iter 78/136 - loss 0.01398365 - time (sec): 8.51 - samples/sec: 3598.78 - lr: 0.000012 - momentum: 0.000000 2023-10-17 20:40:58,452 epoch 7 - iter 91/136 - loss 0.01492819 - time (sec): 9.80 - samples/sec: 3635.85 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:40:59,830 epoch 7 - iter 104/136 - loss 0.01779001 - time (sec): 11.18 - samples/sec: 3604.09 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:41:01,229 epoch 7 - iter 117/136 - loss 0.01803445 - time (sec): 12.58 - samples/sec: 3603.26 - lr: 0.000011 - momentum: 0.000000 2023-10-17 20:41:02,773 epoch 7 - iter 130/136 - loss 0.01711632 - time (sec): 14.12 - samples/sec: 3570.66 - lr: 0.000010 - momentum: 0.000000 2023-10-17 20:41:03,311 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:41:03,311 EPOCH 7 done: loss 0.0176 - lr: 0.000010 2023-10-17 20:41:04,766 DEV : loss 0.14296813309192657 - f1-score (micro avg) 0.797 2023-10-17 20:41:04,771 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:41:06,137 epoch 8 - iter 13/136 - loss 0.02668612 - time (sec): 1.37 - samples/sec: 3487.77 - lr: 0.000010 - momentum: 0.000000 2023-10-17 20:41:07,516 epoch 8 - iter 26/136 - loss 0.01656597 - time (sec): 2.74 - samples/sec: 3517.33 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:41:08,875 epoch 8 - iter 39/136 - loss 0.02124971 - time (sec): 4.10 - samples/sec: 3480.74 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:41:10,335 epoch 8 - iter 52/136 - loss 0.01963592 - time (sec): 5.56 - samples/sec: 3450.91 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:41:11,663 epoch 8 - iter 65/136 - loss 0.01915559 - time (sec): 6.89 - samples/sec: 3486.70 - lr: 0.000009 - momentum: 0.000000 2023-10-17 20:41:13,484 epoch 8 - iter 78/136 - loss 0.01774397 - time (sec): 8.71 - samples/sec: 3471.36 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:41:14,773 epoch 8 - iter 91/136 - loss 0.01724397 - time (sec): 10.00 - samples/sec: 3499.29 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:41:16,117 epoch 8 - iter 104/136 - loss 0.01668140 - time (sec): 11.35 - samples/sec: 3552.04 - lr: 0.000008 - momentum: 0.000000 2023-10-17 20:41:17,408 epoch 8 - iter 117/136 - loss 0.01634825 - time (sec): 12.64 - samples/sec: 3538.35 - lr: 0.000007 - momentum: 0.000000 2023-10-17 20:41:18,726 epoch 8 - iter 130/136 - loss 0.01685340 - time (sec): 13.95 - samples/sec: 3587.79 - lr: 0.000007 - momentum: 0.000000 2023-10-17 20:41:19,222 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:41:19,222 EPOCH 8 done: loss 0.0163 - lr: 0.000007 2023-10-17 20:41:20,691 DEV : loss 0.15952429175376892 - f1-score (micro avg) 0.7905 2023-10-17 20:41:20,695 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:41:22,011 epoch 9 - iter 13/136 - loss 0.00850981 - time (sec): 1.31 - samples/sec: 3948.45 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:41:23,773 epoch 9 - iter 26/136 - loss 0.01655706 - time (sec): 3.08 - samples/sec: 3611.56 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:41:25,267 epoch 9 - iter 39/136 - loss 0.01193651 - time (sec): 4.57 - samples/sec: 3492.51 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:41:26,512 epoch 9 - iter 52/136 - loss 0.01210586 - time (sec): 5.82 - samples/sec: 3470.20 - lr: 0.000006 - momentum: 0.000000 2023-10-17 20:41:27,734 epoch 9 - iter 65/136 - loss 0.01443710 - time (sec): 7.04 - samples/sec: 3551.11 - lr: 0.000005 - momentum: 0.000000 2023-10-17 20:41:29,126 epoch 9 - iter 78/136 - loss 0.01276575 - time (sec): 8.43 - samples/sec: 3597.34 - lr: 0.000005 - momentum: 0.000000 2023-10-17 20:41:30,478 epoch 9 - iter 91/136 - loss 0.01220159 - time (sec): 9.78 - samples/sec: 3619.11 - lr: 0.000005 - momentum: 0.000000 2023-10-17 20:41:31,831 epoch 9 - iter 104/136 - loss 0.01241011 - time (sec): 11.13 - samples/sec: 3601.88 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:41:33,200 epoch 9 - iter 117/136 - loss 0.01124102 - time (sec): 12.50 - samples/sec: 3620.61 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:41:34,577 epoch 9 - iter 130/136 - loss 0.01118786 - time (sec): 13.88 - samples/sec: 3620.04 - lr: 0.000004 - momentum: 0.000000 2023-10-17 20:41:35,049 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:41:35,049 EPOCH 9 done: loss 0.0118 - lr: 0.000004 2023-10-17 20:41:36,509 DEV : loss 0.16205447912216187 - f1-score (micro avg) 0.792 2023-10-17 20:41:36,513 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:41:37,852 epoch 10 - iter 13/136 - loss 0.00911916 - time (sec): 1.34 - samples/sec: 4035.17 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:41:39,113 epoch 10 - iter 26/136 - loss 0.00708093 - time (sec): 2.60 - samples/sec: 3932.63 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:41:40,383 epoch 10 - iter 39/136 - loss 0.00680133 - time (sec): 3.87 - samples/sec: 3881.20 - lr: 0.000003 - momentum: 0.000000 2023-10-17 20:41:41,593 epoch 10 - iter 52/136 - loss 0.00961504 - time (sec): 5.08 - samples/sec: 3714.43 - lr: 0.000002 - momentum: 0.000000 2023-10-17 20:41:43,057 epoch 10 - iter 65/136 - loss 0.00876011 - time (sec): 6.54 - samples/sec: 3690.96 - lr: 0.000002 - momentum: 0.000000 2023-10-17 20:41:44,433 epoch 10 - iter 78/136 - loss 0.01025725 - time (sec): 7.92 - samples/sec: 3679.74 - lr: 0.000002 - momentum: 0.000000 2023-10-17 20:41:45,670 epoch 10 - iter 91/136 - loss 0.01108971 - time (sec): 9.16 - samples/sec: 3682.38 - lr: 0.000001 - momentum: 0.000000 2023-10-17 20:41:47,314 epoch 10 - iter 104/136 - loss 0.01226546 - time (sec): 10.80 - samples/sec: 3660.82 - lr: 0.000001 - momentum: 0.000000 2023-10-17 20:41:48,790 epoch 10 - iter 117/136 - loss 0.01149985 - time (sec): 12.28 - samples/sec: 3654.50 - lr: 0.000001 - momentum: 0.000000 2023-10-17 20:41:50,022 epoch 10 - iter 130/136 - loss 0.01055171 - time (sec): 13.51 - samples/sec: 3687.81 - lr: 0.000000 - momentum: 0.000000 2023-10-17 20:41:50,580 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:41:50,580 EPOCH 10 done: loss 0.0107 - lr: 0.000000 2023-10-17 20:41:52,064 DEV : loss 0.17041459679603577 - f1-score (micro avg) 0.7898 2023-10-17 20:41:52,460 ---------------------------------------------------------------------------------------------------- 2023-10-17 20:41:52,462 Loading model from best epoch ... 2023-10-17 20:41:54,118 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd, S-ORG, B-ORG, E-ORG, I-ORG 2023-10-17 20:41:56,326 Results: - F-score (micro) 0.8073 - F-score (macro) 0.7683 - Accuracy 0.6924 By class: precision recall f1-score support LOC 0.8567 0.8814 0.8689 312 PER 0.7011 0.8798 0.7804 208 ORG 0.5254 0.5636 0.5439 55 HumanProd 0.7857 1.0000 0.8800 22 micro avg 0.7638 0.8559 0.8073 597 macro avg 0.7172 0.8312 0.7683 597 weighted avg 0.7694 0.8559 0.8085 597 2023-10-17 20:41:56,326 ----------------------------------------------------------------------------------------------------