2023-10-13 20:53:18,545 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:53:18,546 Model: "SequenceTagger( (embeddings): TransformerWordEmbeddings( (model): BertModel( (embeddings): BertEmbeddings( (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): BertEncoder( (layer): ModuleList( (0-11): 12 x BertLayer( (attention): BertAttention( (self): BertSelfAttention( (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): BertSelfOutput( (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): BertIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): BertOutput( (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) ) ) ) ) (pooler): BertPooler( (dense): Linear(in_features=768, out_features=768, bias=True) (activation): Tanh() ) ) ) (locked_dropout): LockedDropout(p=0.5) (linear): Linear(in_features=768, out_features=13, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-13 20:53:18,546 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:53:18,547 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 2023-10-13 20:53:18,547 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:53:18,547 Train: 7936 sentences 2023-10-13 20:53:18,547 (train_with_dev=False, train_with_test=False) 2023-10-13 20:53:18,547 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:53:18,547 Training Params: 2023-10-13 20:53:18,547 - learning_rate: "3e-05" 2023-10-13 20:53:18,547 - mini_batch_size: "4" 2023-10-13 20:53:18,547 - max_epochs: "10" 2023-10-13 20:53:18,547 - shuffle: "True" 2023-10-13 20:53:18,547 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:53:18,547 Plugins: 2023-10-13 20:53:18,547 - LinearScheduler | warmup_fraction: '0.1' 2023-10-13 20:53:18,547 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:53:18,547 Final evaluation on model from best epoch (best-model.pt) 2023-10-13 20:53:18,547 - metric: "('micro avg', 'f1-score')" 2023-10-13 20:53:18,547 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:53:18,547 Computation: 2023-10-13 20:53:18,547 - compute on device: cuda:0 2023-10-13 20:53:18,547 - embedding storage: none 2023-10-13 20:53:18,547 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:53:18,547 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1" 2023-10-13 20:53:18,547 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:53:18,547 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:53:28,676 epoch 1 - iter 198/1984 - loss 1.88770718 - time (sec): 10.13 - samples/sec: 1587.68 - lr: 0.000003 - momentum: 0.000000 2023-10-13 20:53:37,508 epoch 1 - iter 396/1984 - loss 1.12484439 - time (sec): 18.96 - samples/sec: 1717.72 - lr: 0.000006 - momentum: 0.000000 2023-10-13 20:53:46,295 epoch 1 - iter 594/1984 - loss 0.83522090 - time (sec): 27.75 - samples/sec: 1772.35 - lr: 0.000009 - momentum: 0.000000 2023-10-13 20:53:54,959 epoch 1 - iter 792/1984 - loss 0.67679270 - time (sec): 36.41 - samples/sec: 1793.37 - lr: 0.000012 - momentum: 0.000000 2023-10-13 20:54:03,579 epoch 1 - iter 990/1984 - loss 0.57703210 - time (sec): 45.03 - samples/sec: 1807.87 - lr: 0.000015 - momentum: 0.000000 2023-10-13 20:54:12,160 epoch 1 - iter 1188/1984 - loss 0.50510842 - time (sec): 53.61 - samples/sec: 1819.73 - lr: 0.000018 - momentum: 0.000000 2023-10-13 20:54:20,861 epoch 1 - iter 1386/1984 - loss 0.45213988 - time (sec): 62.31 - samples/sec: 1840.43 - lr: 0.000021 - momentum: 0.000000 2023-10-13 20:54:30,522 epoch 1 - iter 1584/1984 - loss 0.41118920 - time (sec): 71.97 - samples/sec: 1836.31 - lr: 0.000024 - momentum: 0.000000 2023-10-13 20:54:41,080 epoch 1 - iter 1782/1984 - loss 0.38328017 - time (sec): 82.53 - samples/sec: 1794.37 - lr: 0.000027 - momentum: 0.000000 2023-10-13 20:54:50,731 epoch 1 - iter 1980/1984 - loss 0.35941678 - time (sec): 92.18 - samples/sec: 1776.70 - lr: 0.000030 - momentum: 0.000000 2023-10-13 20:54:50,895 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:54:50,895 EPOCH 1 done: loss 0.3590 - lr: 0.000030 2023-10-13 20:54:53,891 DEV : loss 0.10573934763669968 - f1-score (micro avg) 0.6591 2023-10-13 20:54:53,910 saving best model 2023-10-13 20:54:54,647 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:55:03,748 epoch 2 - iter 198/1984 - loss 0.12106577 - time (sec): 9.10 - samples/sec: 1896.84 - lr: 0.000030 - momentum: 0.000000 2023-10-13 20:55:12,515 epoch 2 - iter 396/1984 - loss 0.11964675 - time (sec): 17.87 - samples/sec: 1814.78 - lr: 0.000029 - momentum: 0.000000 2023-10-13 20:55:21,655 epoch 2 - iter 594/1984 - loss 0.11534460 - time (sec): 27.01 - samples/sec: 1845.31 - lr: 0.000029 - momentum: 0.000000 2023-10-13 20:55:30,327 epoch 2 - iter 792/1984 - loss 0.11408993 - time (sec): 35.68 - samples/sec: 1814.80 - lr: 0.000029 - momentum: 0.000000 2023-10-13 20:55:39,134 epoch 2 - iter 990/1984 - loss 0.11433753 - time (sec): 44.49 - samples/sec: 1846.50 - lr: 0.000028 - momentum: 0.000000 2023-10-13 20:55:47,726 epoch 2 - iter 1188/1984 - loss 0.11332009 - time (sec): 53.08 - samples/sec: 1848.33 - lr: 0.000028 - momentum: 0.000000 2023-10-13 20:55:57,506 epoch 2 - iter 1386/1984 - loss 0.11366621 - time (sec): 62.86 - samples/sec: 1823.09 - lr: 0.000028 - momentum: 0.000000 2023-10-13 20:56:08,043 epoch 2 - iter 1584/1984 - loss 0.11325580 - time (sec): 73.39 - samples/sec: 1778.70 - lr: 0.000027 - momentum: 0.000000 2023-10-13 20:56:18,565 epoch 2 - iter 1782/1984 - loss 0.11283397 - time (sec): 83.92 - samples/sec: 1755.40 - lr: 0.000027 - momentum: 0.000000 2023-10-13 20:56:28,780 epoch 2 - iter 1980/1984 - loss 0.11160017 - time (sec): 94.13 - samples/sec: 1739.67 - lr: 0.000027 - momentum: 0.000000 2023-10-13 20:56:28,992 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:56:28,992 EPOCH 2 done: loss 0.1115 - lr: 0.000027 2023-10-13 20:56:32,481 DEV : loss 0.1008807048201561 - f1-score (micro avg) 0.7066 2023-10-13 20:56:32,506 saving best model 2023-10-13 20:56:33,183 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:56:43,466 epoch 3 - iter 198/1984 - loss 0.07917549 - time (sec): 10.28 - samples/sec: 1593.09 - lr: 0.000026 - momentum: 0.000000 2023-10-13 20:56:52,745 epoch 3 - iter 396/1984 - loss 0.07784288 - time (sec): 19.56 - samples/sec: 1629.87 - lr: 0.000026 - momentum: 0.000000 2023-10-13 20:57:02,097 epoch 3 - iter 594/1984 - loss 0.07362250 - time (sec): 28.91 - samples/sec: 1709.82 - lr: 0.000026 - momentum: 0.000000 2023-10-13 20:57:11,220 epoch 3 - iter 792/1984 - loss 0.07809181 - time (sec): 38.04 - samples/sec: 1752.17 - lr: 0.000025 - momentum: 0.000000 2023-10-13 20:57:20,434 epoch 3 - iter 990/1984 - loss 0.08051703 - time (sec): 47.25 - samples/sec: 1753.43 - lr: 0.000025 - momentum: 0.000000 2023-10-13 20:57:29,676 epoch 3 - iter 1188/1984 - loss 0.08164550 - time (sec): 56.49 - samples/sec: 1752.99 - lr: 0.000025 - momentum: 0.000000 2023-10-13 20:57:38,750 epoch 3 - iter 1386/1984 - loss 0.08050737 - time (sec): 65.57 - samples/sec: 1753.84 - lr: 0.000024 - momentum: 0.000000 2023-10-13 20:57:47,724 epoch 3 - iter 1584/1984 - loss 0.08301541 - time (sec): 74.54 - samples/sec: 1764.39 - lr: 0.000024 - momentum: 0.000000 2023-10-13 20:57:56,733 epoch 3 - iter 1782/1984 - loss 0.08278631 - time (sec): 83.55 - samples/sec: 1768.46 - lr: 0.000024 - momentum: 0.000000 2023-10-13 20:58:05,774 epoch 3 - iter 1980/1984 - loss 0.08178188 - time (sec): 92.59 - samples/sec: 1766.44 - lr: 0.000023 - momentum: 0.000000 2023-10-13 20:58:05,956 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:58:05,956 EPOCH 3 done: loss 0.0817 - lr: 0.000023 2023-10-13 20:58:09,397 DEV : loss 0.14147229492664337 - f1-score (micro avg) 0.7464 2023-10-13 20:58:09,417 saving best model 2023-10-13 20:58:09,979 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:58:18,977 epoch 4 - iter 198/1984 - loss 0.05757599 - time (sec): 8.99 - samples/sec: 1838.23 - lr: 0.000023 - momentum: 0.000000 2023-10-13 20:58:28,176 epoch 4 - iter 396/1984 - loss 0.06403415 - time (sec): 18.19 - samples/sec: 1827.43 - lr: 0.000023 - momentum: 0.000000 2023-10-13 20:58:37,156 epoch 4 - iter 594/1984 - loss 0.06415865 - time (sec): 27.17 - samples/sec: 1805.48 - lr: 0.000022 - momentum: 0.000000 2023-10-13 20:58:46,425 epoch 4 - iter 792/1984 - loss 0.06303083 - time (sec): 36.44 - samples/sec: 1785.64 - lr: 0.000022 - momentum: 0.000000 2023-10-13 20:58:55,437 epoch 4 - iter 990/1984 - loss 0.06259595 - time (sec): 45.45 - samples/sec: 1791.39 - lr: 0.000022 - momentum: 0.000000 2023-10-13 20:59:04,506 epoch 4 - iter 1188/1984 - loss 0.06147075 - time (sec): 54.52 - samples/sec: 1791.86 - lr: 0.000021 - momentum: 0.000000 2023-10-13 20:59:13,860 epoch 4 - iter 1386/1984 - loss 0.06547581 - time (sec): 63.88 - samples/sec: 1784.41 - lr: 0.000021 - momentum: 0.000000 2023-10-13 20:59:23,431 epoch 4 - iter 1584/1984 - loss 0.06402360 - time (sec): 73.45 - samples/sec: 1769.42 - lr: 0.000021 - momentum: 0.000000 2023-10-13 20:59:32,955 epoch 4 - iter 1782/1984 - loss 0.06275327 - time (sec): 82.97 - samples/sec: 1766.30 - lr: 0.000020 - momentum: 0.000000 2023-10-13 20:59:42,166 epoch 4 - iter 1980/1984 - loss 0.06390400 - time (sec): 92.18 - samples/sec: 1776.30 - lr: 0.000020 - momentum: 0.000000 2023-10-13 20:59:42,347 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:59:42,347 EPOCH 4 done: loss 0.0639 - lr: 0.000020 2023-10-13 20:59:46,341 DEV : loss 0.14689981937408447 - f1-score (micro avg) 0.7489 2023-10-13 20:59:46,360 saving best model 2023-10-13 20:59:46,969 ---------------------------------------------------------------------------------------------------- 2023-10-13 20:59:56,191 epoch 5 - iter 198/1984 - loss 0.04771070 - time (sec): 9.22 - samples/sec: 1804.52 - lr: 0.000020 - momentum: 0.000000 2023-10-13 21:00:05,681 epoch 5 - iter 396/1984 - loss 0.04649118 - time (sec): 18.71 - samples/sec: 1761.13 - lr: 0.000019 - momentum: 0.000000 2023-10-13 21:00:15,005 epoch 5 - iter 594/1984 - loss 0.04834649 - time (sec): 28.03 - samples/sec: 1757.30 - lr: 0.000019 - momentum: 0.000000 2023-10-13 21:00:24,352 epoch 5 - iter 792/1984 - loss 0.04615015 - time (sec): 37.38 - samples/sec: 1783.56 - lr: 0.000019 - momentum: 0.000000 2023-10-13 21:00:33,340 epoch 5 - iter 990/1984 - loss 0.04648506 - time (sec): 46.37 - samples/sec: 1794.36 - lr: 0.000018 - momentum: 0.000000 2023-10-13 21:00:42,270 epoch 5 - iter 1188/1984 - loss 0.04468332 - time (sec): 55.30 - samples/sec: 1794.29 - lr: 0.000018 - momentum: 0.000000 2023-10-13 21:00:51,141 epoch 5 - iter 1386/1984 - loss 0.04510172 - time (sec): 64.17 - samples/sec: 1793.83 - lr: 0.000018 - momentum: 0.000000 2023-10-13 21:01:00,022 epoch 5 - iter 1584/1984 - loss 0.04472638 - time (sec): 73.05 - samples/sec: 1801.23 - lr: 0.000017 - momentum: 0.000000 2023-10-13 21:01:09,020 epoch 5 - iter 1782/1984 - loss 0.04570004 - time (sec): 82.05 - samples/sec: 1804.48 - lr: 0.000017 - momentum: 0.000000 2023-10-13 21:01:17,633 epoch 5 - iter 1980/1984 - loss 0.04591442 - time (sec): 90.66 - samples/sec: 1804.42 - lr: 0.000017 - momentum: 0.000000 2023-10-13 21:01:17,818 ---------------------------------------------------------------------------------------------------- 2023-10-13 21:01:17,818 EPOCH 5 done: loss 0.0460 - lr: 0.000017 2023-10-13 21:01:21,249 DEV : loss 0.16444256901741028 - f1-score (micro avg) 0.7731 2023-10-13 21:01:21,269 saving best model 2023-10-13 21:01:21,874 ---------------------------------------------------------------------------------------------------- 2023-10-13 21:01:30,982 epoch 6 - iter 198/1984 - loss 0.03290051 - time (sec): 9.11 - samples/sec: 1821.35 - lr: 0.000016 - momentum: 0.000000 2023-10-13 21:01:40,070 epoch 6 - iter 396/1984 - loss 0.03321950 - time (sec): 18.19 - samples/sec: 1858.59 - lr: 0.000016 - momentum: 0.000000 2023-10-13 21:01:49,239 epoch 6 - iter 594/1984 - loss 0.03311731 - time (sec): 27.36 - samples/sec: 1815.85 - lr: 0.000016 - momentum: 0.000000 2023-10-13 21:01:58,266 epoch 6 - iter 792/1984 - loss 0.03061596 - time (sec): 36.39 - samples/sec: 1801.60 - lr: 0.000015 - momentum: 0.000000 2023-10-13 21:02:07,399 epoch 6 - iter 990/1984 - loss 0.03289182 - time (sec): 45.52 - samples/sec: 1799.81 - lr: 0.000015 - momentum: 0.000000 2023-10-13 21:02:16,317 epoch 6 - iter 1188/1984 - loss 0.03218297 - time (sec): 54.44 - samples/sec: 1807.03 - lr: 0.000015 - momentum: 0.000000 2023-10-13 21:02:25,287 epoch 6 - iter 1386/1984 - loss 0.03348283 - time (sec): 63.41 - samples/sec: 1815.90 - lr: 0.000014 - momentum: 0.000000 2023-10-13 21:02:34,604 epoch 6 - iter 1584/1984 - loss 0.03361440 - time (sec): 72.73 - samples/sec: 1807.15 - lr: 0.000014 - momentum: 0.000000 2023-10-13 21:02:43,949 epoch 6 - iter 1782/1984 - loss 0.03357184 - time (sec): 82.07 - samples/sec: 1796.19 - lr: 0.000014 - momentum: 0.000000 2023-10-13 21:02:53,471 epoch 6 - iter 1980/1984 - loss 0.03361402 - time (sec): 91.59 - samples/sec: 1786.91 - lr: 0.000013 - momentum: 0.000000 2023-10-13 21:02:53,648 ---------------------------------------------------------------------------------------------------- 2023-10-13 21:02:53,648 EPOCH 6 done: loss 0.0336 - lr: 0.000013 2023-10-13 21:02:57,584 DEV : loss 0.20081490278244019 - f1-score (micro avg) 0.7536 2023-10-13 21:02:57,604 ---------------------------------------------------------------------------------------------------- 2023-10-13 21:03:06,697 epoch 7 - iter 198/1984 - loss 0.02416311 - time (sec): 9.09 - samples/sec: 1689.96 - lr: 0.000013 - momentum: 0.000000 2023-10-13 21:03:15,884 epoch 7 - iter 396/1984 - loss 0.02612239 - time (sec): 18.28 - samples/sec: 1761.83 - lr: 0.000013 - momentum: 0.000000 2023-10-13 21:03:24,877 epoch 7 - iter 594/1984 - loss 0.02503909 - time (sec): 27.27 - samples/sec: 1752.06 - lr: 0.000012 - momentum: 0.000000 2023-10-13 21:03:33,834 epoch 7 - iter 792/1984 - loss 0.02544103 - time (sec): 36.23 - samples/sec: 1765.44 - lr: 0.000012 - momentum: 0.000000 2023-10-13 21:03:42,811 epoch 7 - iter 990/1984 - loss 0.02481477 - time (sec): 45.21 - samples/sec: 1795.09 - lr: 0.000012 - momentum: 0.000000 2023-10-13 21:03:52,055 epoch 7 - iter 1188/1984 - loss 0.02586965 - time (sec): 54.45 - samples/sec: 1808.49 - lr: 0.000011 - momentum: 0.000000 2023-10-13 21:04:01,424 epoch 7 - iter 1386/1984 - loss 0.02624069 - time (sec): 63.82 - samples/sec: 1781.30 - lr: 0.000011 - momentum: 0.000000 2023-10-13 21:04:10,658 epoch 7 - iter 1584/1984 - loss 0.02564693 - time (sec): 73.05 - samples/sec: 1788.89 - lr: 0.000011 - momentum: 0.000000 2023-10-13 21:04:19,928 epoch 7 - iter 1782/1984 - loss 0.02628502 - time (sec): 82.32 - samples/sec: 1786.06 - lr: 0.000010 - momentum: 0.000000 2023-10-13 21:04:29,051 epoch 7 - iter 1980/1984 - loss 0.02588685 - time (sec): 91.45 - samples/sec: 1788.99 - lr: 0.000010 - momentum: 0.000000 2023-10-13 21:04:29,240 ---------------------------------------------------------------------------------------------------- 2023-10-13 21:04:29,240 EPOCH 7 done: loss 0.0258 - lr: 0.000010 2023-10-13 21:04:32,591 DEV : loss 0.19746360182762146 - f1-score (micro avg) 0.7682 2023-10-13 21:04:32,611 ---------------------------------------------------------------------------------------------------- 2023-10-13 21:04:42,128 epoch 8 - iter 198/1984 - loss 0.01260002 - time (sec): 9.52 - samples/sec: 1716.88 - lr: 0.000010 - momentum: 0.000000 2023-10-13 21:04:51,190 epoch 8 - iter 396/1984 - loss 0.01660345 - time (sec): 18.58 - samples/sec: 1773.92 - lr: 0.000009 - momentum: 0.000000 2023-10-13 21:05:00,514 epoch 8 - iter 594/1984 - loss 0.01395853 - time (sec): 27.90 - samples/sec: 1750.34 - lr: 0.000009 - momentum: 0.000000 2023-10-13 21:05:09,660 epoch 8 - iter 792/1984 - loss 0.01619325 - time (sec): 37.05 - samples/sec: 1776.28 - lr: 0.000009 - momentum: 0.000000 2023-10-13 21:05:18,644 epoch 8 - iter 990/1984 - loss 0.01676123 - time (sec): 46.03 - samples/sec: 1778.63 - lr: 0.000008 - momentum: 0.000000 2023-10-13 21:05:27,517 epoch 8 - iter 1188/1984 - loss 0.01715802 - time (sec): 54.91 - samples/sec: 1771.93 - lr: 0.000008 - momentum: 0.000000 2023-10-13 21:05:36,488 epoch 8 - iter 1386/1984 - loss 0.01772604 - time (sec): 63.88 - samples/sec: 1784.87 - lr: 0.000008 - momentum: 0.000000 2023-10-13 21:05:45,810 epoch 8 - iter 1584/1984 - loss 0.01778083 - time (sec): 73.20 - samples/sec: 1797.68 - lr: 0.000007 - momentum: 0.000000 2023-10-13 21:05:54,770 epoch 8 - iter 1782/1984 - loss 0.01759045 - time (sec): 82.16 - samples/sec: 1794.86 - lr: 0.000007 - momentum: 0.000000 2023-10-13 21:06:04,075 epoch 8 - iter 1980/1984 - loss 0.01768193 - time (sec): 91.46 - samples/sec: 1790.18 - lr: 0.000007 - momentum: 0.000000 2023-10-13 21:06:04,255 ---------------------------------------------------------------------------------------------------- 2023-10-13 21:06:04,255 EPOCH 8 done: loss 0.0177 - lr: 0.000007 2023-10-13 21:06:07,624 DEV : loss 0.2036585807800293 - f1-score (micro avg) 0.7669 2023-10-13 21:06:07,644 ---------------------------------------------------------------------------------------------------- 2023-10-13 21:06:16,928 epoch 9 - iter 198/1984 - loss 0.01121945 - time (sec): 9.28 - samples/sec: 1803.90 - lr: 0.000006 - momentum: 0.000000 2023-10-13 21:06:25,941 epoch 9 - iter 396/1984 - loss 0.00942507 - time (sec): 18.30 - samples/sec: 1791.88 - lr: 0.000006 - momentum: 0.000000 2023-10-13 21:06:34,795 epoch 9 - iter 594/1984 - loss 0.01115411 - time (sec): 27.15 - samples/sec: 1791.55 - lr: 0.000006 - momentum: 0.000000 2023-10-13 21:06:43,917 epoch 9 - iter 792/1984 - loss 0.01115229 - time (sec): 36.27 - samples/sec: 1813.41 - lr: 0.000005 - momentum: 0.000000 2023-10-13 21:06:53,144 epoch 9 - iter 990/1984 - loss 0.01139535 - time (sec): 45.50 - samples/sec: 1813.79 - lr: 0.000005 - momentum: 0.000000 2023-10-13 21:07:02,159 epoch 9 - iter 1188/1984 - loss 0.01109025 - time (sec): 54.51 - samples/sec: 1799.43 - lr: 0.000005 - momentum: 0.000000 2023-10-13 21:07:11,471 epoch 9 - iter 1386/1984 - loss 0.01120806 - time (sec): 63.83 - samples/sec: 1788.63 - lr: 0.000004 - momentum: 0.000000 2023-10-13 21:07:20,727 epoch 9 - iter 1584/1984 - loss 0.01155852 - time (sec): 73.08 - samples/sec: 1792.50 - lr: 0.000004 - momentum: 0.000000 2023-10-13 21:07:29,843 epoch 9 - iter 1782/1984 - loss 0.01241535 - time (sec): 82.20 - samples/sec: 1798.57 - lr: 0.000004 - momentum: 0.000000 2023-10-13 21:07:38,723 epoch 9 - iter 1980/1984 - loss 0.01230984 - time (sec): 91.08 - samples/sec: 1796.01 - lr: 0.000003 - momentum: 0.000000 2023-10-13 21:07:38,909 ---------------------------------------------------------------------------------------------------- 2023-10-13 21:07:38,909 EPOCH 9 done: loss 0.0123 - lr: 0.000003 2023-10-13 21:07:42,702 DEV : loss 0.21578332781791687 - f1-score (micro avg) 0.7644 2023-10-13 21:07:42,722 ---------------------------------------------------------------------------------------------------- 2023-10-13 21:07:52,175 epoch 10 - iter 198/1984 - loss 0.01257622 - time (sec): 9.45 - samples/sec: 1803.26 - lr: 0.000003 - momentum: 0.000000 2023-10-13 21:08:01,164 epoch 10 - iter 396/1984 - loss 0.01088765 - time (sec): 18.44 - samples/sec: 1777.14 - lr: 0.000003 - momentum: 0.000000 2023-10-13 21:08:10,229 epoch 10 - iter 594/1984 - loss 0.00982544 - time (sec): 27.51 - samples/sec: 1774.23 - lr: 0.000002 - momentum: 0.000000 2023-10-13 21:08:19,951 epoch 10 - iter 792/1984 - loss 0.00945824 - time (sec): 37.23 - samples/sec: 1758.02 - lr: 0.000002 - momentum: 0.000000 2023-10-13 21:08:29,388 epoch 10 - iter 990/1984 - loss 0.00969098 - time (sec): 46.66 - samples/sec: 1746.07 - lr: 0.000002 - momentum: 0.000000 2023-10-13 21:08:38,684 epoch 10 - iter 1188/1984 - loss 0.00953138 - time (sec): 55.96 - samples/sec: 1750.67 - lr: 0.000001 - momentum: 0.000000 2023-10-13 21:08:47,952 epoch 10 - iter 1386/1984 - loss 0.00928403 - time (sec): 65.23 - samples/sec: 1752.64 - lr: 0.000001 - momentum: 0.000000 2023-10-13 21:08:56,924 epoch 10 - iter 1584/1984 - loss 0.00941987 - time (sec): 74.20 - samples/sec: 1764.57 - lr: 0.000001 - momentum: 0.000000 2023-10-13 21:09:06,116 epoch 10 - iter 1782/1984 - loss 0.00912027 - time (sec): 83.39 - samples/sec: 1774.72 - lr: 0.000000 - momentum: 0.000000 2023-10-13 21:09:15,364 epoch 10 - iter 1980/1984 - loss 0.00877729 - time (sec): 92.64 - samples/sec: 1766.45 - lr: 0.000000 - momentum: 0.000000 2023-10-13 21:09:15,565 ---------------------------------------------------------------------------------------------------- 2023-10-13 21:09:15,565 EPOCH 10 done: loss 0.0088 - lr: 0.000000 2023-10-13 21:09:18,982 DEV : loss 0.22608202695846558 - f1-score (micro avg) 0.767 2023-10-13 21:09:19,478 ---------------------------------------------------------------------------------------------------- 2023-10-13 21:09:19,479 Loading model from best epoch ... 2023-10-13 21:09:21,398 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 2023-10-13 21:09:24,698 Results: - F-score (micro) 0.7846 - F-score (macro) 0.6793 - Accuracy 0.6641 By class: precision recall f1-score support LOC 0.8554 0.8489 0.8521 655 PER 0.7449 0.8117 0.7768 223 ORG 0.4694 0.3622 0.4089 127 micro avg 0.7901 0.7791 0.7846 1005 macro avg 0.6899 0.6742 0.6793 1005 weighted avg 0.7821 0.7791 0.7794 1005 2023-10-13 21:09:24,699 ----------------------------------------------------------------------------------------------------