| 2023-10-13 09:21:50,026 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:21:50,027 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=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-13 09:21:50,027 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:21:50,028 MultiCorpus: 1214 train + 266 dev + 251 test sentences | |
| - NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator | |
| 2023-10-13 09:21:50,028 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:21:50,028 Train: 1214 sentences | |
| 2023-10-13 09:21:50,028 (train_with_dev=False, train_with_test=False) | |
| 2023-10-13 09:21:50,028 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:21:50,028 Training Params: | |
| 2023-10-13 09:21:50,028 - learning_rate: "3e-05" | |
| 2023-10-13 09:21:50,028 - mini_batch_size: "4" | |
| 2023-10-13 09:21:50,028 - max_epochs: "10" | |
| 2023-10-13 09:21:50,028 - shuffle: "True" | |
| 2023-10-13 09:21:50,028 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:21:50,028 Plugins: | |
| 2023-10-13 09:21:50,028 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-13 09:21:50,028 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:21:50,028 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-13 09:21:50,028 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-13 09:21:50,028 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:21:50,028 Computation: | |
| 2023-10-13 09:21:50,028 - compute on device: cuda:0 | |
| 2023-10-13 09:21:50,028 - embedding storage: none | |
| 2023-10-13 09:21:50,028 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:21:50,028 Model training base path: "hmbench-ajmc/en-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-13 09:21:50,028 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:21:50,028 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:21:51,347 epoch 1 - iter 30/304 - loss 3.14643067 - time (sec): 1.32 - samples/sec: 2394.58 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 09:21:52,663 epoch 1 - iter 60/304 - loss 2.61196539 - time (sec): 2.63 - samples/sec: 2320.36 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 09:21:53,972 epoch 1 - iter 90/304 - loss 2.01396081 - time (sec): 3.94 - samples/sec: 2304.68 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 09:21:55,299 epoch 1 - iter 120/304 - loss 1.67837668 - time (sec): 5.27 - samples/sec: 2331.79 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 09:21:56,627 epoch 1 - iter 150/304 - loss 1.44538259 - time (sec): 6.60 - samples/sec: 2344.67 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 09:21:57,919 epoch 1 - iter 180/304 - loss 1.26593014 - time (sec): 7.89 - samples/sec: 2345.25 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 09:21:59,247 epoch 1 - iter 210/304 - loss 1.13260232 - time (sec): 9.22 - samples/sec: 2379.81 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 09:22:00,544 epoch 1 - iter 240/304 - loss 1.05180921 - time (sec): 10.51 - samples/sec: 2340.22 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 09:22:01,843 epoch 1 - iter 270/304 - loss 0.96892270 - time (sec): 11.81 - samples/sec: 2327.55 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 09:22:03,180 epoch 1 - iter 300/304 - loss 0.89480556 - time (sec): 13.15 - samples/sec: 2333.31 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-13 09:22:03,354 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:22:03,355 EPOCH 1 done: loss 0.8885 - lr: 0.000030 | |
| 2023-10-13 09:22:04,289 DEV : loss 0.2071554958820343 - f1-score (micro avg) 0.626 | |
| 2023-10-13 09:22:04,295 saving best model | |
| 2023-10-13 09:22:04,643 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:22:05,962 epoch 2 - iter 30/304 - loss 0.21165856 - time (sec): 1.32 - samples/sec: 2085.34 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-13 09:22:07,290 epoch 2 - iter 60/304 - loss 0.19167315 - time (sec): 2.65 - samples/sec: 2177.23 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 09:22:08,603 epoch 2 - iter 90/304 - loss 0.19618877 - time (sec): 3.96 - samples/sec: 2182.10 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 09:22:09,912 epoch 2 - iter 120/304 - loss 0.18385430 - time (sec): 5.27 - samples/sec: 2263.49 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 09:22:11,252 epoch 2 - iter 150/304 - loss 0.17307524 - time (sec): 6.61 - samples/sec: 2299.07 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-13 09:22:12,562 epoch 2 - iter 180/304 - loss 0.16495184 - time (sec): 7.92 - samples/sec: 2298.84 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-13 09:22:13,913 epoch 2 - iter 210/304 - loss 0.16339515 - time (sec): 9.27 - samples/sec: 2311.24 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-13 09:22:15,244 epoch 2 - iter 240/304 - loss 0.15462700 - time (sec): 10.60 - samples/sec: 2298.68 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 09:22:16,566 epoch 2 - iter 270/304 - loss 0.14853881 - time (sec): 11.92 - samples/sec: 2313.61 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 09:22:17,894 epoch 2 - iter 300/304 - loss 0.15172585 - time (sec): 13.25 - samples/sec: 2316.42 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 09:22:18,065 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:22:18,065 EPOCH 2 done: loss 0.1509 - lr: 0.000027 | |
| 2023-10-13 09:22:19,099 DEV : loss 0.13263030350208282 - f1-score (micro avg) 0.8052 | |
| 2023-10-13 09:22:19,110 saving best model | |
| 2023-10-13 09:22:19,589 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:22:21,103 epoch 3 - iter 30/304 - loss 0.07128775 - time (sec): 1.51 - samples/sec: 1987.88 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 09:22:22,663 epoch 3 - iter 60/304 - loss 0.07924825 - time (sec): 3.07 - samples/sec: 1930.84 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 09:22:24,163 epoch 3 - iter 90/304 - loss 0.07419531 - time (sec): 4.57 - samples/sec: 1943.48 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 09:22:25,691 epoch 3 - iter 120/304 - loss 0.07614692 - time (sec): 6.10 - samples/sec: 1950.93 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 09:22:27,183 epoch 3 - iter 150/304 - loss 0.08194671 - time (sec): 7.59 - samples/sec: 1997.01 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 09:22:28,586 epoch 3 - iter 180/304 - loss 0.08323121 - time (sec): 8.99 - samples/sec: 2047.47 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 09:22:29,968 epoch 3 - iter 210/304 - loss 0.08266949 - time (sec): 10.37 - samples/sec: 2042.19 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 09:22:31,388 epoch 3 - iter 240/304 - loss 0.08267050 - time (sec): 11.79 - samples/sec: 2059.00 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 09:22:32,767 epoch 3 - iter 270/304 - loss 0.08498155 - time (sec): 13.17 - samples/sec: 2084.52 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 09:22:34,083 epoch 3 - iter 300/304 - loss 0.08168233 - time (sec): 14.49 - samples/sec: 2113.70 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-13 09:22:34,256 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:22:34,257 EPOCH 3 done: loss 0.0811 - lr: 0.000023 | |
| 2023-10-13 09:22:35,237 DEV : loss 0.1455976665019989 - f1-score (micro avg) 0.8345 | |
| 2023-10-13 09:22:35,246 saving best model | |
| 2023-10-13 09:22:35,742 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:22:37,314 epoch 4 - iter 30/304 - loss 0.06087788 - time (sec): 1.57 - samples/sec: 1853.33 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-13 09:22:38,837 epoch 4 - iter 60/304 - loss 0.04317911 - time (sec): 3.09 - samples/sec: 1902.45 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-13 09:22:40,372 epoch 4 - iter 90/304 - loss 0.05751885 - time (sec): 4.63 - samples/sec: 1943.09 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 09:22:41,690 epoch 4 - iter 120/304 - loss 0.06401069 - time (sec): 5.95 - samples/sec: 2064.48 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 09:22:43,014 epoch 4 - iter 150/304 - loss 0.06280668 - time (sec): 7.27 - samples/sec: 2103.03 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 09:22:44,311 epoch 4 - iter 180/304 - loss 0.05607160 - time (sec): 8.57 - samples/sec: 2118.71 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 09:22:45,613 epoch 4 - iter 210/304 - loss 0.05268029 - time (sec): 9.87 - samples/sec: 2158.42 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 09:22:46,916 epoch 4 - iter 240/304 - loss 0.05793622 - time (sec): 11.17 - samples/sec: 2187.86 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 09:22:48,214 epoch 4 - iter 270/304 - loss 0.05823567 - time (sec): 12.47 - samples/sec: 2197.64 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 09:22:49,522 epoch 4 - iter 300/304 - loss 0.05766621 - time (sec): 13.78 - samples/sec: 2217.65 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 09:22:49,700 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:22:49,700 EPOCH 4 done: loss 0.0590 - lr: 0.000020 | |
| 2023-10-13 09:22:50,623 DEV : loss 0.17554476857185364 - f1-score (micro avg) 0.8324 | |
| 2023-10-13 09:22:50,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:22:51,944 epoch 5 - iter 30/304 - loss 0.07644765 - time (sec): 1.31 - samples/sec: 2338.51 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 09:22:53,253 epoch 5 - iter 60/304 - loss 0.05147929 - time (sec): 2.62 - samples/sec: 2405.54 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-13 09:22:54,567 epoch 5 - iter 90/304 - loss 0.04674362 - time (sec): 3.94 - samples/sec: 2330.04 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-13 09:22:55,839 epoch 5 - iter 120/304 - loss 0.04940268 - time (sec): 5.21 - samples/sec: 2349.29 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-13 09:22:57,125 epoch 5 - iter 150/304 - loss 0.04607070 - time (sec): 6.49 - samples/sec: 2377.87 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 09:22:58,443 epoch 5 - iter 180/304 - loss 0.04705798 - time (sec): 7.81 - samples/sec: 2370.34 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 09:22:59,726 epoch 5 - iter 210/304 - loss 0.05046955 - time (sec): 9.09 - samples/sec: 2377.87 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 09:23:01,069 epoch 5 - iter 240/304 - loss 0.04876882 - time (sec): 10.44 - samples/sec: 2374.22 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 09:23:02,391 epoch 5 - iter 270/304 - loss 0.04648397 - time (sec): 11.76 - samples/sec: 2340.06 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 09:23:03,687 epoch 5 - iter 300/304 - loss 0.04716439 - time (sec): 13.06 - samples/sec: 2349.29 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 09:23:03,855 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:23:03,855 EPOCH 5 done: loss 0.0479 - lr: 0.000017 | |
| 2023-10-13 09:23:04,819 DEV : loss 0.17705786228179932 - f1-score (micro avg) 0.8363 | |
| 2023-10-13 09:23:04,826 saving best model | |
| 2023-10-13 09:23:05,524 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:23:06,887 epoch 6 - iter 30/304 - loss 0.03136870 - time (sec): 1.36 - samples/sec: 2645.61 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 09:23:08,204 epoch 6 - iter 60/304 - loss 0.02093786 - time (sec): 2.67 - samples/sec: 2412.14 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 09:23:09,529 epoch 6 - iter 90/304 - loss 0.02007314 - time (sec): 4.00 - samples/sec: 2349.37 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 09:23:10,866 epoch 6 - iter 120/304 - loss 0.01858451 - time (sec): 5.34 - samples/sec: 2355.51 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 09:23:12,143 epoch 6 - iter 150/304 - loss 0.02451086 - time (sec): 6.61 - samples/sec: 2346.99 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 09:23:13,539 epoch 6 - iter 180/304 - loss 0.02743372 - time (sec): 8.01 - samples/sec: 2323.17 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 09:23:15,024 epoch 6 - iter 210/304 - loss 0.03072947 - time (sec): 9.49 - samples/sec: 2280.94 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-13 09:23:16,483 epoch 6 - iter 240/304 - loss 0.03654572 - time (sec): 10.95 - samples/sec: 2253.19 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-13 09:23:17,907 epoch 6 - iter 270/304 - loss 0.04018440 - time (sec): 12.38 - samples/sec: 2245.72 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-13 09:23:19,197 epoch 6 - iter 300/304 - loss 0.03728501 - time (sec): 13.67 - samples/sec: 2238.49 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-13 09:23:19,361 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:23:19,362 EPOCH 6 done: loss 0.0370 - lr: 0.000013 | |
| 2023-10-13 09:23:20,415 DEV : loss 0.19094179570674896 - f1-score (micro avg) 0.8287 | |
| 2023-10-13 09:23:20,427 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:23:22,066 epoch 7 - iter 30/304 - loss 0.01848195 - time (sec): 1.64 - samples/sec: 1834.21 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-13 09:23:23,748 epoch 7 - iter 60/304 - loss 0.02331449 - time (sec): 3.32 - samples/sec: 1805.55 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-13 09:23:25,094 epoch 7 - iter 90/304 - loss 0.02308868 - time (sec): 4.67 - samples/sec: 1936.04 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 09:23:26,460 epoch 7 - iter 120/304 - loss 0.02624437 - time (sec): 6.03 - samples/sec: 2001.63 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 09:23:27,835 epoch 7 - iter 150/304 - loss 0.02699705 - time (sec): 7.41 - samples/sec: 2041.57 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 09:23:29,196 epoch 7 - iter 180/304 - loss 0.02687898 - time (sec): 8.77 - samples/sec: 2063.46 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 09:23:30,504 epoch 7 - iter 210/304 - loss 0.02865865 - time (sec): 10.07 - samples/sec: 2096.03 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 09:23:31,815 epoch 7 - iter 240/304 - loss 0.02588328 - time (sec): 11.39 - samples/sec: 2134.69 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 09:23:33,166 epoch 7 - iter 270/304 - loss 0.02512052 - time (sec): 12.74 - samples/sec: 2170.84 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 09:23:34,468 epoch 7 - iter 300/304 - loss 0.02644548 - time (sec): 14.04 - samples/sec: 2186.89 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 09:23:34,632 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:23:34,632 EPOCH 7 done: loss 0.0275 - lr: 0.000010 | |
| 2023-10-13 09:23:35,685 DEV : loss 0.18863379955291748 - f1-score (micro avg) 0.8395 | |
| 2023-10-13 09:23:35,694 saving best model | |
| 2023-10-13 09:23:36,158 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:23:37,648 epoch 8 - iter 30/304 - loss 0.01643243 - time (sec): 1.48 - samples/sec: 2065.29 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 09:23:39,041 epoch 8 - iter 60/304 - loss 0.03486728 - time (sec): 2.88 - samples/sec: 2260.90 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 09:23:40,513 epoch 8 - iter 90/304 - loss 0.03618987 - time (sec): 4.35 - samples/sec: 2160.67 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 09:23:41,996 epoch 8 - iter 120/304 - loss 0.02810914 - time (sec): 5.83 - samples/sec: 2101.68 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 09:23:43,503 epoch 8 - iter 150/304 - loss 0.02495396 - time (sec): 7.34 - samples/sec: 2068.28 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-13 09:23:44,887 epoch 8 - iter 180/304 - loss 0.02475730 - time (sec): 8.72 - samples/sec: 2105.50 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-13 09:23:46,252 epoch 8 - iter 210/304 - loss 0.02227638 - time (sec): 10.09 - samples/sec: 2115.65 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-13 09:23:47,603 epoch 8 - iter 240/304 - loss 0.02349592 - time (sec): 11.44 - samples/sec: 2134.70 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 09:23:48,966 epoch 8 - iter 270/304 - loss 0.02182563 - time (sec): 12.80 - samples/sec: 2151.68 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 09:23:50,327 epoch 8 - iter 300/304 - loss 0.01983000 - time (sec): 14.16 - samples/sec: 2160.03 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 09:23:50,502 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:23:50,503 EPOCH 8 done: loss 0.0196 - lr: 0.000007 | |
| 2023-10-13 09:23:51,493 DEV : loss 0.19373896718025208 - f1-score (micro avg) 0.8424 | |
| 2023-10-13 09:23:51,501 saving best model | |
| 2023-10-13 09:23:51,981 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:23:53,527 epoch 9 - iter 30/304 - loss 0.00606087 - time (sec): 1.54 - samples/sec: 1888.65 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 09:23:55,124 epoch 9 - iter 60/304 - loss 0.00478110 - time (sec): 3.14 - samples/sec: 1942.03 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 09:23:56,705 epoch 9 - iter 90/304 - loss 0.01683836 - time (sec): 4.72 - samples/sec: 1944.27 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 09:23:58,287 epoch 9 - iter 120/304 - loss 0.01382272 - time (sec): 6.30 - samples/sec: 1924.42 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 09:23:59,864 epoch 9 - iter 150/304 - loss 0.01245018 - time (sec): 7.88 - samples/sec: 1925.04 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 09:24:01,471 epoch 9 - iter 180/304 - loss 0.01679658 - time (sec): 9.49 - samples/sec: 1954.12 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 09:24:03,084 epoch 9 - iter 210/304 - loss 0.01442450 - time (sec): 11.10 - samples/sec: 1962.68 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-13 09:24:04,665 epoch 9 - iter 240/304 - loss 0.01529025 - time (sec): 12.68 - samples/sec: 1959.05 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-13 09:24:06,219 epoch 9 - iter 270/304 - loss 0.01588725 - time (sec): 14.24 - samples/sec: 1953.25 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-13 09:24:07,748 epoch 9 - iter 300/304 - loss 0.01546630 - time (sec): 15.76 - samples/sec: 1946.35 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 09:24:07,947 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:24:07,947 EPOCH 9 done: loss 0.0154 - lr: 0.000003 | |
| 2023-10-13 09:24:08,899 DEV : loss 0.19748911261558533 - f1-score (micro avg) 0.8431 | |
| 2023-10-13 09:24:08,908 saving best model | |
| 2023-10-13 09:24:09,414 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:24:10,978 epoch 10 - iter 30/304 - loss 0.00023281 - time (sec): 1.56 - samples/sec: 1924.70 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 09:24:12,582 epoch 10 - iter 60/304 - loss 0.01793737 - time (sec): 3.17 - samples/sec: 1894.23 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 09:24:14,159 epoch 10 - iter 90/304 - loss 0.01321813 - time (sec): 4.74 - samples/sec: 1953.07 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 09:24:15,739 epoch 10 - iter 120/304 - loss 0.01092258 - time (sec): 6.32 - samples/sec: 1941.40 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 09:24:17,285 epoch 10 - iter 150/304 - loss 0.00978840 - time (sec): 7.87 - samples/sec: 1936.01 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 09:24:18,836 epoch 10 - iter 180/304 - loss 0.01050595 - time (sec): 9.42 - samples/sec: 1936.97 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 09:24:20,424 epoch 10 - iter 210/304 - loss 0.01376533 - time (sec): 11.01 - samples/sec: 1935.12 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 09:24:21,997 epoch 10 - iter 240/304 - loss 0.01263724 - time (sec): 12.58 - samples/sec: 1952.40 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 09:24:23,529 epoch 10 - iter 270/304 - loss 0.01126673 - time (sec): 14.11 - samples/sec: 1957.66 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-13 09:24:25,035 epoch 10 - iter 300/304 - loss 0.01271255 - time (sec): 15.62 - samples/sec: 1963.63 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-13 09:24:25,242 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:24:25,242 EPOCH 10 done: loss 0.0126 - lr: 0.000000 | |
| 2023-10-13 09:24:26,200 DEV : loss 0.19666777551174164 - f1-score (micro avg) 0.8487 | |
| 2023-10-13 09:24:26,207 saving best model | |
| 2023-10-13 09:24:27,064 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 09:24:27,065 Loading model from best epoch ... | |
| 2023-10-13 09:24:28,683 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object | |
| 2023-10-13 09:24:29,772 | |
| Results: | |
| - F-score (micro) 0.786 | |
| - F-score (macro) 0.6385 | |
| - Accuracy 0.6532 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.7484 0.7881 0.7677 151 | |
| work 0.7069 0.8632 0.7773 95 | |
| pers 0.7807 0.9271 0.8476 96 | |
| date 0.0000 0.0000 0.0000 3 | |
| loc 1.0000 0.6667 0.8000 3 | |
| micro avg 0.7392 0.8391 0.7860 348 | |
| macro avg 0.6472 0.6490 0.6385 348 | |
| weighted avg 0.7417 0.8391 0.7860 348 | |
| 2023-10-13 09:24:29,772 ---------------------------------------------------------------------------------------------------- | |