| 2023-10-13 08:14:01,768 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:01,769 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 08:14:01,769 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:01,769 MultiCorpus: 1100 train + 206 dev + 240 test sentences | |
| - NER_HIPE_2022 Corpus: 1100 train + 206 dev + 240 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/de/with_doc_seperator | |
| 2023-10-13 08:14:01,769 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:01,769 Train: 1100 sentences | |
| 2023-10-13 08:14:01,769 (train_with_dev=False, train_with_test=False) | |
| 2023-10-13 08:14:01,769 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:01,769 Training Params: | |
| 2023-10-13 08:14:01,769 - learning_rate: "5e-05" | |
| 2023-10-13 08:14:01,769 - mini_batch_size: "4" | |
| 2023-10-13 08:14:01,769 - max_epochs: "10" | |
| 2023-10-13 08:14:01,769 - shuffle: "True" | |
| 2023-10-13 08:14:01,769 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:01,769 Plugins: | |
| 2023-10-13 08:14:01,769 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-13 08:14:01,769 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:01,770 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-13 08:14:01,770 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-13 08:14:01,770 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:01,770 Computation: | |
| 2023-10-13 08:14:01,770 - compute on device: cuda:0 | |
| 2023-10-13 08:14:01,770 - embedding storage: none | |
| 2023-10-13 08:14:01,770 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:01,770 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-13 08:14:01,770 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:01,770 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:03,001 epoch 1 - iter 27/275 - loss 3.33558083 - time (sec): 1.23 - samples/sec: 1631.73 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 08:14:04,224 epoch 1 - iter 54/275 - loss 2.67411401 - time (sec): 2.45 - samples/sec: 1753.52 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 08:14:05,459 epoch 1 - iter 81/275 - loss 2.11284940 - time (sec): 3.69 - samples/sec: 1788.25 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 08:14:06,669 epoch 1 - iter 108/275 - loss 1.76614819 - time (sec): 4.90 - samples/sec: 1774.02 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-13 08:14:07,829 epoch 1 - iter 135/275 - loss 1.51034631 - time (sec): 6.06 - samples/sec: 1813.01 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 08:14:08,967 epoch 1 - iter 162/275 - loss 1.32202341 - time (sec): 7.20 - samples/sec: 1835.54 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 08:14:10,099 epoch 1 - iter 189/275 - loss 1.18186350 - time (sec): 8.33 - samples/sec: 1866.28 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-13 08:14:11,297 epoch 1 - iter 216/275 - loss 1.07761205 - time (sec): 9.53 - samples/sec: 1852.79 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-13 08:14:12,562 epoch 1 - iter 243/275 - loss 0.99262472 - time (sec): 10.79 - samples/sec: 1850.08 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-13 08:14:13,753 epoch 1 - iter 270/275 - loss 0.91954943 - time (sec): 11.98 - samples/sec: 1866.59 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-13 08:14:13,967 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:13,967 EPOCH 1 done: loss 0.9096 - lr: 0.000049 | |
| 2023-10-13 08:14:14,722 DEV : loss 0.250717431306839 - f1-score (micro avg) 0.6667 | |
| 2023-10-13 08:14:14,727 saving best model | |
| 2023-10-13 08:14:15,052 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:16,208 epoch 2 - iter 27/275 - loss 0.23410146 - time (sec): 1.15 - samples/sec: 1777.65 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-13 08:14:17,411 epoch 2 - iter 54/275 - loss 0.24637708 - time (sec): 2.36 - samples/sec: 1806.62 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-13 08:14:18,643 epoch 2 - iter 81/275 - loss 0.22152461 - time (sec): 3.59 - samples/sec: 1741.02 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-13 08:14:19,832 epoch 2 - iter 108/275 - loss 0.21036926 - time (sec): 4.78 - samples/sec: 1792.53 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-13 08:14:21,000 epoch 2 - iter 135/275 - loss 0.19577919 - time (sec): 5.95 - samples/sec: 1848.62 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-13 08:14:22,189 epoch 2 - iter 162/275 - loss 0.18918108 - time (sec): 7.14 - samples/sec: 1835.57 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-13 08:14:23,371 epoch 2 - iter 189/275 - loss 0.17818824 - time (sec): 8.32 - samples/sec: 1852.51 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-13 08:14:24,558 epoch 2 - iter 216/275 - loss 0.17039517 - time (sec): 9.50 - samples/sec: 1863.17 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-13 08:14:25,744 epoch 2 - iter 243/275 - loss 0.16347807 - time (sec): 10.69 - samples/sec: 1865.43 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-13 08:14:26,931 epoch 2 - iter 270/275 - loss 0.17165927 - time (sec): 11.88 - samples/sec: 1882.03 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-13 08:14:27,148 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:27,149 EPOCH 2 done: loss 0.1701 - lr: 0.000045 | |
| 2023-10-13 08:14:27,838 DEV : loss 0.14587247371673584 - f1-score (micro avg) 0.8206 | |
| 2023-10-13 08:14:27,842 saving best model | |
| 2023-10-13 08:14:28,275 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:29,496 epoch 3 - iter 27/275 - loss 0.13383562 - time (sec): 1.22 - samples/sec: 1736.08 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-13 08:14:30,722 epoch 3 - iter 54/275 - loss 0.10313550 - time (sec): 2.44 - samples/sec: 1826.42 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-13 08:14:31,906 epoch 3 - iter 81/275 - loss 0.11209919 - time (sec): 3.63 - samples/sec: 1857.33 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-13 08:14:33,096 epoch 3 - iter 108/275 - loss 0.11891061 - time (sec): 4.82 - samples/sec: 1896.16 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-13 08:14:34,241 epoch 3 - iter 135/275 - loss 0.11566765 - time (sec): 5.96 - samples/sec: 1893.17 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-13 08:14:35,385 epoch 3 - iter 162/275 - loss 0.10788338 - time (sec): 7.11 - samples/sec: 1890.39 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-13 08:14:36,539 epoch 3 - iter 189/275 - loss 0.10759457 - time (sec): 8.26 - samples/sec: 1912.29 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-13 08:14:37,694 epoch 3 - iter 216/275 - loss 0.11295502 - time (sec): 9.42 - samples/sec: 1923.17 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-13 08:14:38,838 epoch 3 - iter 243/275 - loss 0.10740960 - time (sec): 10.56 - samples/sec: 1901.57 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-13 08:14:39,981 epoch 3 - iter 270/275 - loss 0.11235786 - time (sec): 11.70 - samples/sec: 1908.93 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-13 08:14:40,189 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:40,189 EPOCH 3 done: loss 0.1140 - lr: 0.000039 | |
| 2023-10-13 08:14:40,903 DEV : loss 0.18647150695323944 - f1-score (micro avg) 0.8102 | |
| 2023-10-13 08:14:40,908 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:42,097 epoch 4 - iter 27/275 - loss 0.08370121 - time (sec): 1.19 - samples/sec: 1973.50 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-13 08:14:43,326 epoch 4 - iter 54/275 - loss 0.06789951 - time (sec): 2.42 - samples/sec: 1979.25 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-13 08:14:44,586 epoch 4 - iter 81/275 - loss 0.08149310 - time (sec): 3.68 - samples/sec: 1910.29 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-13 08:14:45,811 epoch 4 - iter 108/275 - loss 0.08272403 - time (sec): 4.90 - samples/sec: 1831.94 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-13 08:14:46,982 epoch 4 - iter 135/275 - loss 0.07998629 - time (sec): 6.07 - samples/sec: 1854.92 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-13 08:14:48,158 epoch 4 - iter 162/275 - loss 0.08178955 - time (sec): 7.25 - samples/sec: 1849.81 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-13 08:14:49,350 epoch 4 - iter 189/275 - loss 0.08232270 - time (sec): 8.44 - samples/sec: 1860.12 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-13 08:14:50,618 epoch 4 - iter 216/275 - loss 0.07685133 - time (sec): 9.71 - samples/sec: 1826.69 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-13 08:14:51,855 epoch 4 - iter 243/275 - loss 0.07707240 - time (sec): 10.95 - samples/sec: 1824.96 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-13 08:14:53,065 epoch 4 - iter 270/275 - loss 0.08226021 - time (sec): 12.16 - samples/sec: 1840.06 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-13 08:14:53,281 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:53,281 EPOCH 4 done: loss 0.0833 - lr: 0.000034 | |
| 2023-10-13 08:14:53,986 DEV : loss 0.1847609579563141 - f1-score (micro avg) 0.8262 | |
| 2023-10-13 08:14:53,991 saving best model | |
| 2023-10-13 08:14:54,412 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:14:55,578 epoch 5 - iter 27/275 - loss 0.06092588 - time (sec): 1.16 - samples/sec: 1678.67 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-13 08:14:56,790 epoch 5 - iter 54/275 - loss 0.05263885 - time (sec): 2.37 - samples/sec: 1713.41 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-13 08:14:58,008 epoch 5 - iter 81/275 - loss 0.05221081 - time (sec): 3.59 - samples/sec: 1844.45 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-13 08:14:59,237 epoch 5 - iter 108/275 - loss 0.05548114 - time (sec): 4.82 - samples/sec: 1881.73 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-13 08:15:00,457 epoch 5 - iter 135/275 - loss 0.05277666 - time (sec): 6.04 - samples/sec: 1894.06 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-13 08:15:01,665 epoch 5 - iter 162/275 - loss 0.05535209 - time (sec): 7.25 - samples/sec: 1895.46 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-13 08:15:02,871 epoch 5 - iter 189/275 - loss 0.06133723 - time (sec): 8.45 - samples/sec: 1871.34 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-13 08:15:04,171 epoch 5 - iter 216/275 - loss 0.06711398 - time (sec): 9.75 - samples/sec: 1850.81 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 08:15:05,383 epoch 5 - iter 243/275 - loss 0.06827843 - time (sec): 10.96 - samples/sec: 1838.85 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-13 08:15:06,652 epoch 5 - iter 270/275 - loss 0.06420277 - time (sec): 12.23 - samples/sec: 1832.01 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-13 08:15:06,895 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:15:06,895 EPOCH 5 done: loss 0.0642 - lr: 0.000028 | |
| 2023-10-13 08:15:07,577 DEV : loss 0.14506205916404724 - f1-score (micro avg) 0.8708 | |
| 2023-10-13 08:15:07,582 saving best model | |
| 2023-10-13 08:15:08,019 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:15:09,224 epoch 6 - iter 27/275 - loss 0.05970436 - time (sec): 1.20 - samples/sec: 1721.93 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 08:15:10,459 epoch 6 - iter 54/275 - loss 0.04735020 - time (sec): 2.44 - samples/sec: 1796.11 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-13 08:15:11,622 epoch 6 - iter 81/275 - loss 0.04104958 - time (sec): 3.60 - samples/sec: 1812.76 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 08:15:12,835 epoch 6 - iter 108/275 - loss 0.04949143 - time (sec): 4.81 - samples/sec: 1836.10 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-13 08:15:14,017 epoch 6 - iter 135/275 - loss 0.04836931 - time (sec): 6.00 - samples/sec: 1839.95 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 08:15:15,221 epoch 6 - iter 162/275 - loss 0.04469466 - time (sec): 7.20 - samples/sec: 1843.17 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-13 08:15:16,430 epoch 6 - iter 189/275 - loss 0.03948178 - time (sec): 8.41 - samples/sec: 1856.16 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 08:15:17,594 epoch 6 - iter 216/275 - loss 0.03659484 - time (sec): 9.57 - samples/sec: 1851.46 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-13 08:15:18,778 epoch 6 - iter 243/275 - loss 0.03967343 - time (sec): 10.76 - samples/sec: 1857.83 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-13 08:15:19,960 epoch 6 - iter 270/275 - loss 0.04312660 - time (sec): 11.94 - samples/sec: 1876.85 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 08:15:20,179 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:15:20,179 EPOCH 6 done: loss 0.0427 - lr: 0.000022 | |
| 2023-10-13 08:15:20,904 DEV : loss 0.1451627016067505 - f1-score (micro avg) 0.864 | |
| 2023-10-13 08:15:20,909 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:15:22,173 epoch 7 - iter 27/275 - loss 0.01073423 - time (sec): 1.26 - samples/sec: 1910.92 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-13 08:15:23,430 epoch 7 - iter 54/275 - loss 0.02813451 - time (sec): 2.52 - samples/sec: 1752.36 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 08:15:24,731 epoch 7 - iter 81/275 - loss 0.02165146 - time (sec): 3.82 - samples/sec: 1660.75 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-13 08:15:25,997 epoch 7 - iter 108/275 - loss 0.03467252 - time (sec): 5.09 - samples/sec: 1699.00 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 08:15:27,259 epoch 7 - iter 135/275 - loss 0.03436861 - time (sec): 6.35 - samples/sec: 1684.38 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-13 08:15:28,481 epoch 7 - iter 162/275 - loss 0.02992802 - time (sec): 7.57 - samples/sec: 1720.58 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-13 08:15:29,724 epoch 7 - iter 189/275 - loss 0.02742828 - time (sec): 8.81 - samples/sec: 1743.29 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-13 08:15:30,987 epoch 7 - iter 216/275 - loss 0.02801723 - time (sec): 10.08 - samples/sec: 1760.11 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-13 08:15:32,227 epoch 7 - iter 243/275 - loss 0.02947050 - time (sec): 11.32 - samples/sec: 1745.03 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 08:15:33,422 epoch 7 - iter 270/275 - loss 0.03199856 - time (sec): 12.51 - samples/sec: 1781.65 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-13 08:15:33,636 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:15:33,636 EPOCH 7 done: loss 0.0323 - lr: 0.000017 | |
| 2023-10-13 08:15:34,393 DEV : loss 0.1610579639673233 - f1-score (micro avg) 0.8779 | |
| 2023-10-13 08:15:34,402 saving best model | |
| 2023-10-13 08:15:34,979 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:15:36,276 epoch 8 - iter 27/275 - loss 0.04070795 - time (sec): 1.29 - samples/sec: 1804.38 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 08:15:37,571 epoch 8 - iter 54/275 - loss 0.02618551 - time (sec): 2.59 - samples/sec: 1778.13 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-13 08:15:38,888 epoch 8 - iter 81/275 - loss 0.03158104 - time (sec): 3.91 - samples/sec: 1732.47 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 08:15:40,194 epoch 8 - iter 108/275 - loss 0.02666479 - time (sec): 5.21 - samples/sec: 1719.61 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-13 08:15:41,490 epoch 8 - iter 135/275 - loss 0.02914085 - time (sec): 6.51 - samples/sec: 1723.02 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-13 08:15:42,789 epoch 8 - iter 162/275 - loss 0.02758595 - time (sec): 7.81 - samples/sec: 1711.53 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-13 08:15:43,971 epoch 8 - iter 189/275 - loss 0.02407604 - time (sec): 8.99 - samples/sec: 1723.62 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-13 08:15:45,142 epoch 8 - iter 216/275 - loss 0.02445442 - time (sec): 10.16 - samples/sec: 1741.92 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 08:15:46,351 epoch 8 - iter 243/275 - loss 0.02435487 - time (sec): 11.37 - samples/sec: 1758.93 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-13 08:15:47,580 epoch 8 - iter 270/275 - loss 0.02374684 - time (sec): 12.60 - samples/sec: 1778.25 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 08:15:47,799 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:15:47,799 EPOCH 8 done: loss 0.0236 - lr: 0.000011 | |
| 2023-10-13 08:15:48,486 DEV : loss 0.16053281724452972 - f1-score (micro avg) 0.8937 | |
| 2023-10-13 08:15:48,491 saving best model | |
| 2023-10-13 08:15:48,912 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:15:50,125 epoch 9 - iter 27/275 - loss 0.00901293 - time (sec): 1.20 - samples/sec: 1948.80 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-13 08:15:51,323 epoch 9 - iter 54/275 - loss 0.01143770 - time (sec): 2.40 - samples/sec: 1853.04 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 08:15:52,569 epoch 9 - iter 81/275 - loss 0.01790511 - time (sec): 3.65 - samples/sec: 1940.55 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-13 08:15:53,800 epoch 9 - iter 108/275 - loss 0.02044590 - time (sec): 4.88 - samples/sec: 1909.52 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 08:15:55,016 epoch 9 - iter 135/275 - loss 0.01775785 - time (sec): 6.09 - samples/sec: 1883.37 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-13 08:15:56,242 epoch 9 - iter 162/275 - loss 0.01993149 - time (sec): 7.32 - samples/sec: 1902.30 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-13 08:15:57,636 epoch 9 - iter 189/275 - loss 0.01763028 - time (sec): 8.71 - samples/sec: 1829.81 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 08:15:58,994 epoch 9 - iter 216/275 - loss 0.01660131 - time (sec): 10.07 - samples/sec: 1803.02 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-13 08:16:00,201 epoch 9 - iter 243/275 - loss 0.01609966 - time (sec): 11.28 - samples/sec: 1790.54 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 08:16:01,366 epoch 9 - iter 270/275 - loss 0.01741414 - time (sec): 12.44 - samples/sec: 1804.27 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-13 08:16:01,577 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:16:01,577 EPOCH 9 done: loss 0.0172 - lr: 0.000006 | |
| 2023-10-13 08:16:02,318 DEV : loss 0.1515495926141739 - f1-score (micro avg) 0.8884 | |
| 2023-10-13 08:16:02,324 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:16:03,697 epoch 10 - iter 27/275 - loss 0.00451258 - time (sec): 1.37 - samples/sec: 1688.11 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 08:16:05,107 epoch 10 - iter 54/275 - loss 0.00999560 - time (sec): 2.78 - samples/sec: 1733.84 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-13 08:16:06,383 epoch 10 - iter 81/275 - loss 0.00734492 - time (sec): 4.06 - samples/sec: 1746.50 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-13 08:16:07,725 epoch 10 - iter 108/275 - loss 0.00751331 - time (sec): 5.40 - samples/sec: 1714.94 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-13 08:16:08,972 epoch 10 - iter 135/275 - loss 0.00855730 - time (sec): 6.65 - samples/sec: 1748.53 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-13 08:16:10,185 epoch 10 - iter 162/275 - loss 0.00828564 - time (sec): 7.86 - samples/sec: 1738.79 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 08:16:11,430 epoch 10 - iter 189/275 - loss 0.00791182 - time (sec): 9.10 - samples/sec: 1738.66 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-13 08:16:12,698 epoch 10 - iter 216/275 - loss 0.01131091 - time (sec): 10.37 - samples/sec: 1734.08 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 08:16:13,950 epoch 10 - iter 243/275 - loss 0.01216239 - time (sec): 11.62 - samples/sec: 1742.57 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-13 08:16:15,183 epoch 10 - iter 270/275 - loss 0.01183371 - time (sec): 12.86 - samples/sec: 1741.89 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-13 08:16:15,408 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:16:15,409 EPOCH 10 done: loss 0.0116 - lr: 0.000000 | |
| 2023-10-13 08:16:16,126 DEV : loss 0.15584614872932434 - f1-score (micro avg) 0.8884 | |
| 2023-10-13 08:16:16,453 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-13 08:16:16,455 Loading model from best epoch ... | |
| 2023-10-13 08:16:18,073 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-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date | |
| 2023-10-13 08:16:18,744 | |
| Results: | |
| - F-score (micro) 0.9143 | |
| - F-score (macro) 0.879 | |
| - Accuracy 0.8585 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.8811 0.9261 0.9030 176 | |
| pers 0.9683 0.9531 0.9606 128 | |
| work 0.8649 0.8649 0.8649 74 | |
| object 1.0000 1.0000 1.0000 2 | |
| loc 1.0000 0.5000 0.6667 2 | |
| micro avg 0.9072 0.9215 0.9143 382 | |
| macro avg 0.9428 0.8488 0.8790 382 | |
| weighted avg 0.9084 0.9215 0.9142 382 | |
| 2023-10-13 08:16:18,744 ---------------------------------------------------------------------------------------------------- | |