2023-10-17 10:37:47,590 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:37:47,591 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 10:37:47,591 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:37:47,591 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 10:37:47,591 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:37:47,591 Train: 7936 sentences 2023-10-17 10:37:47,591 (train_with_dev=False, train_with_test=False) 2023-10-17 10:37:47,592 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:37:47,592 Training Params: 2023-10-17 10:37:47,592 - learning_rate: "3e-05" 2023-10-17 10:37:47,592 - mini_batch_size: "4" 2023-10-17 10:37:47,592 - max_epochs: "10" 2023-10-17 10:37:47,592 - shuffle: "True" 2023-10-17 10:37:47,592 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:37:47,592 Plugins: 2023-10-17 10:37:47,592 - TensorboardLogger 2023-10-17 10:37:47,592 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 10:37:47,592 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:37:47,592 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 10:37:47,592 - metric: "('micro avg', 'f1-score')" 2023-10-17 10:37:47,592 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:37:47,592 Computation: 2023-10-17 10:37:47,592 - compute on device: cuda:0 2023-10-17 10:37:47,592 - embedding storage: none 2023-10-17 10:37:47,592 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:37:47,592 Model training base path: "hmbench-icdar/fr-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1" 2023-10-17 10:37:47,592 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:37:47,592 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:37:47,592 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 10:37:57,473 epoch 1 - iter 198/1984 - loss 1.96262558 - time (sec): 9.88 - samples/sec: 1637.74 - lr: 0.000003 - momentum: 0.000000 2023-10-17 10:38:06,276 epoch 1 - iter 396/1984 - loss 1.14353968 - time (sec): 18.68 - samples/sec: 1779.11 - lr: 0.000006 - momentum: 0.000000 2023-10-17 10:38:15,247 epoch 1 - iter 594/1984 - loss 0.85110538 - time (sec): 27.65 - samples/sec: 1794.33 - lr: 0.000009 - momentum: 0.000000 2023-10-17 10:38:23,912 epoch 1 - iter 792/1984 - loss 0.69733723 - time (sec): 36.32 - samples/sec: 1800.50 - lr: 0.000012 - momentum: 0.000000 2023-10-17 10:38:32,916 epoch 1 - iter 990/1984 - loss 0.59220786 - time (sec): 45.32 - samples/sec: 1805.64 - lr: 0.000015 - momentum: 0.000000 2023-10-17 10:38:41,867 epoch 1 - iter 1188/1984 - loss 0.51720323 - time (sec): 54.27 - samples/sec: 1817.61 - lr: 0.000018 - momentum: 0.000000 2023-10-17 10:38:50,819 epoch 1 - iter 1386/1984 - loss 0.46529206 - time (sec): 63.23 - samples/sec: 1815.63 - lr: 0.000021 - momentum: 0.000000 2023-10-17 10:38:59,939 epoch 1 - iter 1584/1984 - loss 0.42634007 - time (sec): 72.35 - samples/sec: 1814.85 - lr: 0.000024 - momentum: 0.000000 2023-10-17 10:39:09,082 epoch 1 - iter 1782/1984 - loss 0.39543817 - time (sec): 81.49 - samples/sec: 1806.96 - lr: 0.000027 - momentum: 0.000000 2023-10-17 10:39:18,133 epoch 1 - iter 1980/1984 - loss 0.37002480 - time (sec): 90.54 - samples/sec: 1807.55 - lr: 0.000030 - momentum: 0.000000 2023-10-17 10:39:18,315 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:39:18,315 EPOCH 1 done: loss 0.3695 - lr: 0.000030 2023-10-17 10:39:22,176 DEV : loss 0.09817007929086685 - f1-score (micro avg) 0.7151 2023-10-17 10:39:22,205 saving best model 2023-10-17 10:39:22,659 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:39:32,314 epoch 2 - iter 198/1984 - loss 0.11703805 - time (sec): 9.65 - samples/sec: 1751.29 - lr: 0.000030 - momentum: 0.000000 2023-10-17 10:39:41,399 epoch 2 - iter 396/1984 - loss 0.12135474 - time (sec): 18.74 - samples/sec: 1767.42 - lr: 0.000029 - momentum: 0.000000 2023-10-17 10:39:50,558 epoch 2 - iter 594/1984 - loss 0.12116589 - time (sec): 27.90 - samples/sec: 1778.79 - lr: 0.000029 - momentum: 0.000000 2023-10-17 10:39:59,873 epoch 2 - iter 792/1984 - loss 0.11894017 - time (sec): 37.21 - samples/sec: 1785.54 - lr: 0.000029 - momentum: 0.000000 2023-10-17 10:40:08,857 epoch 2 - iter 990/1984 - loss 0.11639961 - time (sec): 46.20 - samples/sec: 1787.34 - lr: 0.000028 - momentum: 0.000000 2023-10-17 10:40:18,317 epoch 2 - iter 1188/1984 - loss 0.11443201 - time (sec): 55.66 - samples/sec: 1784.94 - lr: 0.000028 - momentum: 0.000000 2023-10-17 10:40:27,227 epoch 2 - iter 1386/1984 - loss 0.11365206 - time (sec): 64.57 - samples/sec: 1796.15 - lr: 0.000028 - momentum: 0.000000 2023-10-17 10:40:36,279 epoch 2 - iter 1584/1984 - loss 0.11390623 - time (sec): 73.62 - samples/sec: 1788.69 - lr: 0.000027 - momentum: 0.000000 2023-10-17 10:40:45,274 epoch 2 - iter 1782/1984 - loss 0.11339437 - time (sec): 82.61 - samples/sec: 1782.61 - lr: 0.000027 - momentum: 0.000000 2023-10-17 10:40:54,345 epoch 2 - iter 1980/1984 - loss 0.11417783 - time (sec): 91.68 - samples/sec: 1784.96 - lr: 0.000027 - momentum: 0.000000 2023-10-17 10:40:54,529 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:40:54,529 EPOCH 2 done: loss 0.1142 - lr: 0.000027 2023-10-17 10:40:58,257 DEV : loss 0.09690196067094803 - f1-score (micro avg) 0.751 2023-10-17 10:40:58,286 saving best model 2023-10-17 10:40:58,864 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:41:08,525 epoch 3 - iter 198/1984 - loss 0.08243740 - time (sec): 9.66 - samples/sec: 1715.82 - lr: 0.000026 - momentum: 0.000000 2023-10-17 10:41:17,969 epoch 3 - iter 396/1984 - loss 0.08405210 - time (sec): 19.10 - samples/sec: 1720.39 - lr: 0.000026 - momentum: 0.000000 2023-10-17 10:41:28,471 epoch 3 - iter 594/1984 - loss 0.08612073 - time (sec): 29.60 - samples/sec: 1675.84 - lr: 0.000026 - momentum: 0.000000 2023-10-17 10:41:37,701 epoch 3 - iter 792/1984 - loss 0.08283051 - time (sec): 38.83 - samples/sec: 1710.41 - lr: 0.000025 - momentum: 0.000000 2023-10-17 10:41:46,586 epoch 3 - iter 990/1984 - loss 0.08274479 - time (sec): 47.72 - samples/sec: 1733.22 - lr: 0.000025 - momentum: 0.000000 2023-10-17 10:41:55,624 epoch 3 - iter 1188/1984 - loss 0.08251098 - time (sec): 56.76 - samples/sec: 1734.90 - lr: 0.000025 - momentum: 0.000000 2023-10-17 10:42:04,447 epoch 3 - iter 1386/1984 - loss 0.08323712 - time (sec): 65.58 - samples/sec: 1750.52 - lr: 0.000024 - momentum: 0.000000 2023-10-17 10:42:13,596 epoch 3 - iter 1584/1984 - loss 0.08296027 - time (sec): 74.73 - samples/sec: 1755.28 - lr: 0.000024 - momentum: 0.000000 2023-10-17 10:42:22,756 epoch 3 - iter 1782/1984 - loss 0.08247111 - time (sec): 83.89 - samples/sec: 1763.01 - lr: 0.000024 - momentum: 0.000000 2023-10-17 10:42:31,763 epoch 3 - iter 1980/1984 - loss 0.08393188 - time (sec): 92.90 - samples/sec: 1761.21 - lr: 0.000023 - momentum: 0.000000 2023-10-17 10:42:31,952 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:42:31,952 EPOCH 3 done: loss 0.0841 - lr: 0.000023 2023-10-17 10:42:35,645 DEV : loss 0.11184526234865189 - f1-score (micro avg) 0.7592 2023-10-17 10:42:35,669 saving best model 2023-10-17 10:42:36,275 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:42:45,911 epoch 4 - iter 198/1984 - loss 0.06238332 - time (sec): 9.63 - samples/sec: 1704.13 - lr: 0.000023 - momentum: 0.000000 2023-10-17 10:42:55,157 epoch 4 - iter 396/1984 - loss 0.06005836 - time (sec): 18.88 - samples/sec: 1808.83 - lr: 0.000023 - momentum: 0.000000 2023-10-17 10:43:04,798 epoch 4 - iter 594/1984 - loss 0.06300783 - time (sec): 28.52 - samples/sec: 1785.86 - lr: 0.000022 - momentum: 0.000000 2023-10-17 10:43:15,294 epoch 4 - iter 792/1984 - loss 0.06418959 - time (sec): 39.02 - samples/sec: 1728.50 - lr: 0.000022 - momentum: 0.000000 2023-10-17 10:43:25,402 epoch 4 - iter 990/1984 - loss 0.06410527 - time (sec): 49.12 - samples/sec: 1703.66 - lr: 0.000022 - momentum: 0.000000 2023-10-17 10:43:34,556 epoch 4 - iter 1188/1984 - loss 0.06627853 - time (sec): 58.28 - samples/sec: 1704.06 - lr: 0.000021 - momentum: 0.000000 2023-10-17 10:43:43,828 epoch 4 - iter 1386/1984 - loss 0.06493629 - time (sec): 67.55 - samples/sec: 1701.29 - lr: 0.000021 - momentum: 0.000000 2023-10-17 10:43:53,244 epoch 4 - iter 1584/1984 - loss 0.06437724 - time (sec): 76.97 - samples/sec: 1702.26 - lr: 0.000021 - momentum: 0.000000 2023-10-17 10:44:02,367 epoch 4 - iter 1782/1984 - loss 0.06554549 - time (sec): 86.09 - samples/sec: 1715.79 - lr: 0.000020 - momentum: 0.000000 2023-10-17 10:44:11,335 epoch 4 - iter 1980/1984 - loss 0.06532216 - time (sec): 95.06 - samples/sec: 1722.76 - lr: 0.000020 - momentum: 0.000000 2023-10-17 10:44:11,528 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:44:11,528 EPOCH 4 done: loss 0.0653 - lr: 0.000020 2023-10-17 10:44:15,291 DEV : loss 0.14710469543933868 - f1-score (micro avg) 0.7764 2023-10-17 10:44:15,314 saving best model 2023-10-17 10:44:15,834 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:44:24,991 epoch 5 - iter 198/1984 - loss 0.05310506 - time (sec): 9.16 - samples/sec: 1776.04 - lr: 0.000020 - momentum: 0.000000 2023-10-17 10:44:33,692 epoch 5 - iter 396/1984 - loss 0.05550943 - time (sec): 17.86 - samples/sec: 1876.49 - lr: 0.000019 - momentum: 0.000000 2023-10-17 10:44:42,752 epoch 5 - iter 594/1984 - loss 0.05128920 - time (sec): 26.92 - samples/sec: 1865.39 - lr: 0.000019 - momentum: 0.000000 2023-10-17 10:44:51,952 epoch 5 - iter 792/1984 - loss 0.05178507 - time (sec): 36.12 - samples/sec: 1875.12 - lr: 0.000019 - momentum: 0.000000 2023-10-17 10:45:01,073 epoch 5 - iter 990/1984 - loss 0.05015438 - time (sec): 45.24 - samples/sec: 1860.06 - lr: 0.000018 - momentum: 0.000000 2023-10-17 10:45:10,073 epoch 5 - iter 1188/1984 - loss 0.05003515 - time (sec): 54.24 - samples/sec: 1843.52 - lr: 0.000018 - momentum: 0.000000 2023-10-17 10:45:19,019 epoch 5 - iter 1386/1984 - loss 0.05017555 - time (sec): 63.18 - samples/sec: 1842.13 - lr: 0.000018 - momentum: 0.000000 2023-10-17 10:45:27,581 epoch 5 - iter 1584/1984 - loss 0.05031975 - time (sec): 71.75 - samples/sec: 1842.93 - lr: 0.000017 - momentum: 0.000000 2023-10-17 10:45:36,697 epoch 5 - iter 1782/1984 - loss 0.05007302 - time (sec): 80.86 - samples/sec: 1832.85 - lr: 0.000017 - momentum: 0.000000 2023-10-17 10:45:46,443 epoch 5 - iter 1980/1984 - loss 0.04916707 - time (sec): 90.61 - samples/sec: 1805.91 - lr: 0.000017 - momentum: 0.000000 2023-10-17 10:45:46,629 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:45:46,629 EPOCH 5 done: loss 0.0493 - lr: 0.000017 2023-10-17 10:45:50,160 DEV : loss 0.20937786996364594 - f1-score (micro avg) 0.761 2023-10-17 10:45:50,185 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:46:00,578 epoch 6 - iter 198/1984 - loss 0.03889353 - time (sec): 10.39 - samples/sec: 1582.61 - lr: 0.000016 - momentum: 0.000000 2023-10-17 10:46:09,604 epoch 6 - iter 396/1984 - loss 0.04124372 - time (sec): 19.42 - samples/sec: 1681.97 - lr: 0.000016 - momentum: 0.000000 2023-10-17 10:46:18,836 epoch 6 - iter 594/1984 - loss 0.04058583 - time (sec): 28.65 - samples/sec: 1753.98 - lr: 0.000016 - momentum: 0.000000 2023-10-17 10:46:27,818 epoch 6 - iter 792/1984 - loss 0.04104349 - time (sec): 37.63 - samples/sec: 1770.74 - lr: 0.000015 - momentum: 0.000000 2023-10-17 10:46:36,799 epoch 6 - iter 990/1984 - loss 0.03959461 - time (sec): 46.61 - samples/sec: 1789.31 - lr: 0.000015 - momentum: 0.000000 2023-10-17 10:46:45,771 epoch 6 - iter 1188/1984 - loss 0.03893122 - time (sec): 55.58 - samples/sec: 1793.74 - lr: 0.000015 - momentum: 0.000000 2023-10-17 10:46:54,632 epoch 6 - iter 1386/1984 - loss 0.03835506 - time (sec): 64.45 - samples/sec: 1789.43 - lr: 0.000014 - momentum: 0.000000 2023-10-17 10:47:03,663 epoch 6 - iter 1584/1984 - loss 0.03800712 - time (sec): 73.48 - samples/sec: 1785.14 - lr: 0.000014 - momentum: 0.000000 2023-10-17 10:47:12,792 epoch 6 - iter 1782/1984 - loss 0.03800912 - time (sec): 82.61 - samples/sec: 1783.20 - lr: 0.000014 - momentum: 0.000000 2023-10-17 10:47:21,770 epoch 6 - iter 1980/1984 - loss 0.03804788 - time (sec): 91.58 - samples/sec: 1786.04 - lr: 0.000013 - momentum: 0.000000 2023-10-17 10:47:21,950 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:47:21,950 EPOCH 6 done: loss 0.0380 - lr: 0.000013 2023-10-17 10:47:25,502 DEV : loss 0.20233358442783356 - f1-score (micro avg) 0.7609 2023-10-17 10:47:25,529 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:47:35,922 epoch 7 - iter 198/1984 - loss 0.02769256 - time (sec): 10.39 - samples/sec: 1568.34 - lr: 0.000013 - momentum: 0.000000 2023-10-17 10:47:45,345 epoch 7 - iter 396/1984 - loss 0.02809458 - time (sec): 19.81 - samples/sec: 1656.25 - lr: 0.000013 - momentum: 0.000000 2023-10-17 10:47:54,754 epoch 7 - iter 594/1984 - loss 0.02925218 - time (sec): 29.22 - samples/sec: 1696.02 - lr: 0.000012 - momentum: 0.000000 2023-10-17 10:48:03,765 epoch 7 - iter 792/1984 - loss 0.02875332 - time (sec): 38.23 - samples/sec: 1717.27 - lr: 0.000012 - momentum: 0.000000 2023-10-17 10:48:12,807 epoch 7 - iter 990/1984 - loss 0.02726148 - time (sec): 47.28 - samples/sec: 1733.61 - lr: 0.000012 - momentum: 0.000000 2023-10-17 10:48:21,730 epoch 7 - iter 1188/1984 - loss 0.02657124 - time (sec): 56.20 - samples/sec: 1751.52 - lr: 0.000011 - momentum: 0.000000 2023-10-17 10:48:30,737 epoch 7 - iter 1386/1984 - loss 0.02702982 - time (sec): 65.21 - samples/sec: 1759.96 - lr: 0.000011 - momentum: 0.000000 2023-10-17 10:48:39,970 epoch 7 - iter 1584/1984 - loss 0.02650602 - time (sec): 74.44 - samples/sec: 1750.60 - lr: 0.000011 - momentum: 0.000000 2023-10-17 10:48:49,162 epoch 7 - iter 1782/1984 - loss 0.02844952 - time (sec): 83.63 - samples/sec: 1762.76 - lr: 0.000010 - momentum: 0.000000 2023-10-17 10:48:58,295 epoch 7 - iter 1980/1984 - loss 0.02825356 - time (sec): 92.76 - samples/sec: 1764.63 - lr: 0.000010 - momentum: 0.000000 2023-10-17 10:48:58,477 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:48:58,477 EPOCH 7 done: loss 0.0282 - lr: 0.000010 2023-10-17 10:49:01,991 DEV : loss 0.21014443039894104 - f1-score (micro avg) 0.7593 2023-10-17 10:49:02,014 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:49:10,679 epoch 8 - iter 198/1984 - loss 0.01310734 - time (sec): 8.66 - samples/sec: 1889.48 - lr: 0.000010 - momentum: 0.000000 2023-10-17 10:49:19,332 epoch 8 - iter 396/1984 - loss 0.01617564 - time (sec): 17.32 - samples/sec: 1870.85 - lr: 0.000009 - momentum: 0.000000 2023-10-17 10:49:28,226 epoch 8 - iter 594/1984 - loss 0.01587113 - time (sec): 26.21 - samples/sec: 1908.46 - lr: 0.000009 - momentum: 0.000000 2023-10-17 10:49:36,913 epoch 8 - iter 792/1984 - loss 0.01491232 - time (sec): 34.90 - samples/sec: 1893.99 - lr: 0.000009 - momentum: 0.000000 2023-10-17 10:49:45,623 epoch 8 - iter 990/1984 - loss 0.01558421 - time (sec): 43.61 - samples/sec: 1907.85 - lr: 0.000008 - momentum: 0.000000 2023-10-17 10:49:54,766 epoch 8 - iter 1188/1984 - loss 0.01606079 - time (sec): 52.75 - samples/sec: 1894.03 - lr: 0.000008 - momentum: 0.000000 2023-10-17 10:50:03,951 epoch 8 - iter 1386/1984 - loss 0.01694365 - time (sec): 61.94 - samples/sec: 1866.52 - lr: 0.000008 - momentum: 0.000000 2023-10-17 10:50:13,283 epoch 8 - iter 1584/1984 - loss 0.01809506 - time (sec): 71.27 - samples/sec: 1832.48 - lr: 0.000007 - momentum: 0.000000 2023-10-17 10:50:22,600 epoch 8 - iter 1782/1984 - loss 0.01857775 - time (sec): 80.58 - samples/sec: 1826.78 - lr: 0.000007 - momentum: 0.000000 2023-10-17 10:50:31,758 epoch 8 - iter 1980/1984 - loss 0.01906275 - time (sec): 89.74 - samples/sec: 1823.40 - lr: 0.000007 - momentum: 0.000000 2023-10-17 10:50:31,947 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:50:31,947 EPOCH 8 done: loss 0.0191 - lr: 0.000007 2023-10-17 10:50:35,465 DEV : loss 0.2338264435529709 - f1-score (micro avg) 0.7676 2023-10-17 10:50:35,489 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:50:44,512 epoch 9 - iter 198/1984 - loss 0.01453751 - time (sec): 9.02 - samples/sec: 1755.79 - lr: 0.000006 - momentum: 0.000000 2023-10-17 10:50:53,683 epoch 9 - iter 396/1984 - loss 0.01196746 - time (sec): 18.19 - samples/sec: 1825.23 - lr: 0.000006 - momentum: 0.000000 2023-10-17 10:51:03,022 epoch 9 - iter 594/1984 - loss 0.01160464 - time (sec): 27.53 - samples/sec: 1831.16 - lr: 0.000006 - momentum: 0.000000 2023-10-17 10:51:12,214 epoch 9 - iter 792/1984 - loss 0.01106266 - time (sec): 36.72 - samples/sec: 1815.83 - lr: 0.000005 - momentum: 0.000000 2023-10-17 10:51:21,261 epoch 9 - iter 990/1984 - loss 0.01089225 - time (sec): 45.77 - samples/sec: 1803.84 - lr: 0.000005 - momentum: 0.000000 2023-10-17 10:51:30,381 epoch 9 - iter 1188/1984 - loss 0.01111371 - time (sec): 54.89 - samples/sec: 1798.55 - lr: 0.000005 - momentum: 0.000000 2023-10-17 10:51:39,368 epoch 9 - iter 1386/1984 - loss 0.01130474 - time (sec): 63.88 - samples/sec: 1796.78 - lr: 0.000004 - momentum: 0.000000 2023-10-17 10:51:48,561 epoch 9 - iter 1584/1984 - loss 0.01217727 - time (sec): 73.07 - samples/sec: 1800.21 - lr: 0.000004 - momentum: 0.000000 2023-10-17 10:51:57,852 epoch 9 - iter 1782/1984 - loss 0.01235461 - time (sec): 82.36 - samples/sec: 1793.51 - lr: 0.000004 - momentum: 0.000000 2023-10-17 10:52:07,034 epoch 9 - iter 1980/1984 - loss 0.01325613 - time (sec): 91.54 - samples/sec: 1788.07 - lr: 0.000003 - momentum: 0.000000 2023-10-17 10:52:07,211 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:52:07,212 EPOCH 9 done: loss 0.0132 - lr: 0.000003 2023-10-17 10:52:10,636 DEV : loss 0.2385382354259491 - f1-score (micro avg) 0.772 2023-10-17 10:52:10,663 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:52:19,890 epoch 10 - iter 198/1984 - loss 0.00637340 - time (sec): 9.23 - samples/sec: 1789.65 - lr: 0.000003 - momentum: 0.000000 2023-10-17 10:52:28,935 epoch 10 - iter 396/1984 - loss 0.00651409 - time (sec): 18.27 - samples/sec: 1759.71 - lr: 0.000003 - momentum: 0.000000 2023-10-17 10:52:38,136 epoch 10 - iter 594/1984 - loss 0.00741839 - time (sec): 27.47 - samples/sec: 1769.92 - lr: 0.000002 - momentum: 0.000000 2023-10-17 10:52:47,372 epoch 10 - iter 792/1984 - loss 0.00875355 - time (sec): 36.71 - samples/sec: 1765.52 - lr: 0.000002 - momentum: 0.000000 2023-10-17 10:52:56,770 epoch 10 - iter 990/1984 - loss 0.00887012 - time (sec): 46.11 - samples/sec: 1747.58 - lr: 0.000002 - momentum: 0.000000 2023-10-17 10:53:06,020 epoch 10 - iter 1188/1984 - loss 0.00809607 - time (sec): 55.36 - samples/sec: 1760.41 - lr: 0.000001 - momentum: 0.000000 2023-10-17 10:53:15,196 epoch 10 - iter 1386/1984 - loss 0.00842195 - time (sec): 64.53 - samples/sec: 1776.32 - lr: 0.000001 - momentum: 0.000000 2023-10-17 10:53:24,107 epoch 10 - iter 1584/1984 - loss 0.00846139 - time (sec): 73.44 - samples/sec: 1784.87 - lr: 0.000001 - momentum: 0.000000 2023-10-17 10:53:32,767 epoch 10 - iter 1782/1984 - loss 0.00886546 - time (sec): 82.10 - samples/sec: 1789.89 - lr: 0.000000 - momentum: 0.000000 2023-10-17 10:53:41,465 epoch 10 - iter 1980/1984 - loss 0.00947778 - time (sec): 90.80 - samples/sec: 1802.94 - lr: 0.000000 - momentum: 0.000000 2023-10-17 10:53:41,637 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:53:41,637 EPOCH 10 done: loss 0.0095 - lr: 0.000000 2023-10-17 10:53:45,532 DEV : loss 0.24614956974983215 - f1-score (micro avg) 0.7678 2023-10-17 10:53:45,963 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:53:45,964 Loading model from best epoch ... 2023-10-17 10:53:47,827 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 10:53:51,361 Results: - F-score (micro) 0.7855 - F-score (macro) 0.7063 - Accuracy 0.6667 By class: precision recall f1-score support LOC 0.8135 0.8656 0.8388 655 PER 0.7333 0.7892 0.7603 223 ORG 0.5900 0.4646 0.5198 127 micro avg 0.7734 0.7980 0.7855 1005 macro avg 0.7123 0.7065 0.7063 1005 weighted avg 0.7675 0.7980 0.7810 1005 2023-10-17 10:53:51,362 ----------------------------------------------------------------------------------------------------