| 2023-10-23 18:12:46,441 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:12:46,443 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(64001, 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() | |
| )" | |
| 2023-10-23 18:12:46,443 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:12:46,443 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 | |
| 2023-10-23 18:12:46,443 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:12:46,443 Train: 1214 sentences | |
| 2023-10-23 18:12:46,443 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 18:12:46,443 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:12:46,443 Training Params: | |
| 2023-10-23 18:12:46,443 - learning_rate: "3e-05" | |
| 2023-10-23 18:12:46,443 - mini_batch_size: "4" | |
| 2023-10-23 18:12:46,443 - max_epochs: "10" | |
| 2023-10-23 18:12:46,443 - shuffle: "True" | |
| 2023-10-23 18:12:46,443 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:12:46,443 Plugins: | |
| 2023-10-23 18:12:46,443 - TensorboardLogger | |
| 2023-10-23 18:12:46,443 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 18:12:46,443 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:12:46,444 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 18:12:46,444 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 18:12:46,444 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:12:46,444 Computation: | |
| 2023-10-23 18:12:46,444 - compute on device: cuda:0 | |
| 2023-10-23 18:12:46,444 - embedding storage: none | |
| 2023-10-23 18:12:46,444 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:12:46,444 Model training base path: "hmbench-ajmc/en-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-23 18:12:46,444 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:12:46,444 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:12:46,444 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 18:12:48,068 epoch 1 - iter 30/304 - loss 2.98445592 - time (sec): 1.62 - samples/sec: 1875.96 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 18:12:49,686 epoch 1 - iter 60/304 - loss 2.22348022 - time (sec): 3.24 - samples/sec: 1822.80 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 18:12:51,322 epoch 1 - iter 90/304 - loss 1.68960332 - time (sec): 4.88 - samples/sec: 1825.97 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 18:12:52,950 epoch 1 - iter 120/304 - loss 1.40192310 - time (sec): 6.51 - samples/sec: 1841.80 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 18:12:54,582 epoch 1 - iter 150/304 - loss 1.19239185 - time (sec): 8.14 - samples/sec: 1850.78 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 18:12:56,204 epoch 1 - iter 180/304 - loss 1.05158409 - time (sec): 9.76 - samples/sec: 1862.20 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 18:12:57,837 epoch 1 - iter 210/304 - loss 0.93428074 - time (sec): 11.39 - samples/sec: 1869.74 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 18:12:59,457 epoch 1 - iter 240/304 - loss 0.85197867 - time (sec): 13.01 - samples/sec: 1871.71 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 18:13:01,033 epoch 1 - iter 270/304 - loss 0.76874976 - time (sec): 14.59 - samples/sec: 1891.39 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 18:13:02,662 epoch 1 - iter 300/304 - loss 0.71452414 - time (sec): 16.22 - samples/sec: 1885.87 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 18:13:02,876 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:13:02,876 EPOCH 1 done: loss 0.7077 - lr: 0.000030 | |
| 2023-10-23 18:13:03,837 DEV : loss 0.1715477705001831 - f1-score (micro avg) 0.6521 | |
| 2023-10-23 18:13:03,846 saving best model | |
| 2023-10-23 18:13:04,262 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:13:05,887 epoch 2 - iter 30/304 - loss 0.16454595 - time (sec): 1.62 - samples/sec: 1908.65 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 18:13:07,528 epoch 2 - iter 60/304 - loss 0.14465478 - time (sec): 3.26 - samples/sec: 1930.97 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 18:13:09,167 epoch 2 - iter 90/304 - loss 0.13948154 - time (sec): 4.90 - samples/sec: 1877.81 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 18:13:10,811 epoch 2 - iter 120/304 - loss 0.13895752 - time (sec): 6.55 - samples/sec: 1864.80 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 18:13:12,406 epoch 2 - iter 150/304 - loss 0.14096606 - time (sec): 8.14 - samples/sec: 1857.62 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 18:13:14,052 epoch 2 - iter 180/304 - loss 0.13400557 - time (sec): 9.79 - samples/sec: 1860.88 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 18:13:15,685 epoch 2 - iter 210/304 - loss 0.13838672 - time (sec): 11.42 - samples/sec: 1833.38 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 18:13:17,338 epoch 2 - iter 240/304 - loss 0.13721522 - time (sec): 13.07 - samples/sec: 1849.68 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 18:13:18,976 epoch 2 - iter 270/304 - loss 0.13752883 - time (sec): 14.71 - samples/sec: 1855.39 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 18:13:20,607 epoch 2 - iter 300/304 - loss 0.13090121 - time (sec): 16.34 - samples/sec: 1874.02 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 18:13:20,823 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:13:20,823 EPOCH 2 done: loss 0.1302 - lr: 0.000027 | |
| 2023-10-23 18:13:21,706 DEV : loss 0.16064199805259705 - f1-score (micro avg) 0.8138 | |
| 2023-10-23 18:13:21,714 saving best model | |
| 2023-10-23 18:13:22,216 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:13:23,811 epoch 3 - iter 30/304 - loss 0.05475800 - time (sec): 1.59 - samples/sec: 1820.83 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 18:13:25,458 epoch 3 - iter 60/304 - loss 0.06229097 - time (sec): 3.24 - samples/sec: 1928.05 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 18:13:27,110 epoch 3 - iter 90/304 - loss 0.08416342 - time (sec): 4.89 - samples/sec: 1932.50 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 18:13:28,749 epoch 3 - iter 120/304 - loss 0.08385153 - time (sec): 6.53 - samples/sec: 1903.56 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 18:13:30,395 epoch 3 - iter 150/304 - loss 0.07573603 - time (sec): 8.18 - samples/sec: 1920.97 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 18:13:32,020 epoch 3 - iter 180/304 - loss 0.07699958 - time (sec): 9.80 - samples/sec: 1900.63 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 18:13:33,617 epoch 3 - iter 210/304 - loss 0.07824690 - time (sec): 11.40 - samples/sec: 1885.96 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 18:13:35,267 epoch 3 - iter 240/304 - loss 0.07568889 - time (sec): 13.05 - samples/sec: 1901.98 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 18:13:36,909 epoch 3 - iter 270/304 - loss 0.07464948 - time (sec): 14.69 - samples/sec: 1881.26 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 18:13:38,563 epoch 3 - iter 300/304 - loss 0.08036614 - time (sec): 16.35 - samples/sec: 1876.61 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 18:13:38,779 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:13:38,780 EPOCH 3 done: loss 0.0823 - lr: 0.000023 | |
| 2023-10-23 18:13:39,794 DEV : loss 0.15495248138904572 - f1-score (micro avg) 0.8122 | |
| 2023-10-23 18:13:39,801 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:13:41,439 epoch 4 - iter 30/304 - loss 0.04707249 - time (sec): 1.64 - samples/sec: 2059.62 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 18:13:43,080 epoch 4 - iter 60/304 - loss 0.04271187 - time (sec): 3.28 - samples/sec: 1983.84 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 18:13:44,719 epoch 4 - iter 90/304 - loss 0.05633248 - time (sec): 4.92 - samples/sec: 1895.38 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 18:13:46,363 epoch 4 - iter 120/304 - loss 0.04563425 - time (sec): 6.56 - samples/sec: 1903.34 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 18:13:48,003 epoch 4 - iter 150/304 - loss 0.04720628 - time (sec): 8.20 - samples/sec: 1887.96 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 18:13:49,652 epoch 4 - iter 180/304 - loss 0.05155600 - time (sec): 9.85 - samples/sec: 1882.05 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 18:13:51,294 epoch 4 - iter 210/304 - loss 0.05654426 - time (sec): 11.49 - samples/sec: 1883.09 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 18:13:52,942 epoch 4 - iter 240/304 - loss 0.05514680 - time (sec): 13.14 - samples/sec: 1876.42 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 18:13:54,584 epoch 4 - iter 270/304 - loss 0.05396017 - time (sec): 14.78 - samples/sec: 1872.14 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 18:13:56,220 epoch 4 - iter 300/304 - loss 0.05228844 - time (sec): 16.42 - samples/sec: 1863.03 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 18:13:56,435 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:13:56,436 EPOCH 4 done: loss 0.0518 - lr: 0.000020 | |
| 2023-10-23 18:13:57,309 DEV : loss 0.19193391501903534 - f1-score (micro avg) 0.809 | |
| 2023-10-23 18:13:57,316 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:13:58,960 epoch 5 - iter 30/304 - loss 0.03390289 - time (sec): 1.64 - samples/sec: 1913.03 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 18:14:00,600 epoch 5 - iter 60/304 - loss 0.04606974 - time (sec): 3.28 - samples/sec: 1858.67 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 18:14:02,257 epoch 5 - iter 90/304 - loss 0.04695528 - time (sec): 4.94 - samples/sec: 1892.28 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 18:14:03,883 epoch 5 - iter 120/304 - loss 0.04235888 - time (sec): 6.57 - samples/sec: 1880.87 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 18:14:05,526 epoch 5 - iter 150/304 - loss 0.04071583 - time (sec): 8.21 - samples/sec: 1911.76 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 18:14:07,153 epoch 5 - iter 180/304 - loss 0.03583492 - time (sec): 9.84 - samples/sec: 1899.00 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 18:14:08,767 epoch 5 - iter 210/304 - loss 0.03645264 - time (sec): 11.45 - samples/sec: 1894.36 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 18:14:10,387 epoch 5 - iter 240/304 - loss 0.03453267 - time (sec): 13.07 - samples/sec: 1891.71 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 18:14:12,015 epoch 5 - iter 270/304 - loss 0.03727819 - time (sec): 14.70 - samples/sec: 1878.18 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 18:14:13,650 epoch 5 - iter 300/304 - loss 0.03875291 - time (sec): 16.33 - samples/sec: 1869.00 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 18:14:13,866 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:14:13,866 EPOCH 5 done: loss 0.0393 - lr: 0.000017 | |
| 2023-10-23 18:14:14,722 DEV : loss 0.20043757557868958 - f1-score (micro avg) 0.8349 | |
| 2023-10-23 18:14:14,728 saving best model | |
| 2023-10-23 18:14:15,256 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:14:16,884 epoch 6 - iter 30/304 - loss 0.07028796 - time (sec): 1.63 - samples/sec: 1921.25 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 18:14:18,514 epoch 6 - iter 60/304 - loss 0.04781504 - time (sec): 3.26 - samples/sec: 1843.92 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 18:14:20,154 epoch 6 - iter 90/304 - loss 0.04475473 - time (sec): 4.90 - samples/sec: 1885.95 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 18:14:21,791 epoch 6 - iter 120/304 - loss 0.03578933 - time (sec): 6.53 - samples/sec: 1862.26 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 18:14:23,415 epoch 6 - iter 150/304 - loss 0.03712405 - time (sec): 8.16 - samples/sec: 1856.72 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 18:14:25,043 epoch 6 - iter 180/304 - loss 0.03222092 - time (sec): 9.79 - samples/sec: 1842.63 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 18:14:26,672 epoch 6 - iter 210/304 - loss 0.03272180 - time (sec): 11.41 - samples/sec: 1849.78 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 18:14:28,305 epoch 6 - iter 240/304 - loss 0.03111402 - time (sec): 13.05 - samples/sec: 1869.64 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 18:14:29,931 epoch 6 - iter 270/304 - loss 0.03162902 - time (sec): 14.67 - samples/sec: 1867.90 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 18:14:31,565 epoch 6 - iter 300/304 - loss 0.02944895 - time (sec): 16.31 - samples/sec: 1881.99 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 18:14:31,779 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:14:31,779 EPOCH 6 done: loss 0.0292 - lr: 0.000013 | |
| 2023-10-23 18:14:32,621 DEV : loss 0.20006847381591797 - f1-score (micro avg) 0.8369 | |
| 2023-10-23 18:14:32,628 saving best model | |
| 2023-10-23 18:14:33,142 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:14:34,780 epoch 7 - iter 30/304 - loss 0.01748835 - time (sec): 1.64 - samples/sec: 1916.44 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 18:14:36,421 epoch 7 - iter 60/304 - loss 0.01697280 - time (sec): 3.28 - samples/sec: 1880.73 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 18:14:38,068 epoch 7 - iter 90/304 - loss 0.01478209 - time (sec): 4.92 - samples/sec: 1888.36 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 18:14:39,726 epoch 7 - iter 120/304 - loss 0.01321084 - time (sec): 6.58 - samples/sec: 1912.13 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 18:14:41,368 epoch 7 - iter 150/304 - loss 0.01353593 - time (sec): 8.22 - samples/sec: 1893.45 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 18:14:43,000 epoch 7 - iter 180/304 - loss 0.01357105 - time (sec): 9.86 - samples/sec: 1888.99 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 18:14:44,619 epoch 7 - iter 210/304 - loss 0.01577979 - time (sec): 11.47 - samples/sec: 1880.71 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 18:14:46,231 epoch 7 - iter 240/304 - loss 0.01970489 - time (sec): 13.09 - samples/sec: 1863.38 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 18:14:47,836 epoch 7 - iter 270/304 - loss 0.02213724 - time (sec): 14.69 - samples/sec: 1892.70 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 18:14:49,364 epoch 7 - iter 300/304 - loss 0.02161108 - time (sec): 16.22 - samples/sec: 1892.57 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 18:14:49,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:14:49,575 EPOCH 7 done: loss 0.0214 - lr: 0.000010 | |
| 2023-10-23 18:14:50,431 DEV : loss 0.20860883593559265 - f1-score (micro avg) 0.8347 | |
| 2023-10-23 18:14:50,439 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:14:52,065 epoch 8 - iter 30/304 - loss 0.02968926 - time (sec): 1.63 - samples/sec: 1654.90 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 18:14:53,645 epoch 8 - iter 60/304 - loss 0.01406728 - time (sec): 3.21 - samples/sec: 1808.97 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 18:14:55,281 epoch 8 - iter 90/304 - loss 0.01843177 - time (sec): 4.84 - samples/sec: 1833.79 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 18:14:56,915 epoch 8 - iter 120/304 - loss 0.01640842 - time (sec): 6.47 - samples/sec: 1797.72 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 18:14:58,573 epoch 8 - iter 150/304 - loss 0.01538265 - time (sec): 8.13 - samples/sec: 1872.16 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 18:15:00,219 epoch 8 - iter 180/304 - loss 0.01963783 - time (sec): 9.78 - samples/sec: 1888.96 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 18:15:01,861 epoch 8 - iter 210/304 - loss 0.01959002 - time (sec): 11.42 - samples/sec: 1881.24 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 18:15:03,520 epoch 8 - iter 240/304 - loss 0.01694540 - time (sec): 13.08 - samples/sec: 1913.49 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 18:15:05,163 epoch 8 - iter 270/304 - loss 0.01613531 - time (sec): 14.72 - samples/sec: 1901.88 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 18:15:06,793 epoch 8 - iter 300/304 - loss 0.01531872 - time (sec): 16.35 - samples/sec: 1875.64 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 18:15:07,007 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:15:07,007 EPOCH 8 done: loss 0.0155 - lr: 0.000007 | |
| 2023-10-23 18:15:07,895 DEV : loss 0.21332137286663055 - f1-score (micro avg) 0.8513 | |
| 2023-10-23 18:15:07,902 saving best model | |
| 2023-10-23 18:15:08,377 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:15:10,015 epoch 9 - iter 30/304 - loss 0.02369919 - time (sec): 1.64 - samples/sec: 2021.13 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 18:15:11,655 epoch 9 - iter 60/304 - loss 0.01598962 - time (sec): 3.28 - samples/sec: 1910.25 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 18:15:13,275 epoch 9 - iter 90/304 - loss 0.01792024 - time (sec): 4.90 - samples/sec: 1926.43 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 18:15:14,901 epoch 9 - iter 120/304 - loss 0.01711638 - time (sec): 6.52 - samples/sec: 1841.30 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 18:15:16,537 epoch 9 - iter 150/304 - loss 0.01403237 - time (sec): 8.16 - samples/sec: 1879.29 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 18:15:18,162 epoch 9 - iter 180/304 - loss 0.01255566 - time (sec): 9.78 - samples/sec: 1869.43 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 18:15:19,810 epoch 9 - iter 210/304 - loss 0.01332711 - time (sec): 11.43 - samples/sec: 1869.47 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 18:15:21,460 epoch 9 - iter 240/304 - loss 0.01325790 - time (sec): 13.08 - samples/sec: 1863.74 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 18:15:23,108 epoch 9 - iter 270/304 - loss 0.01199154 - time (sec): 14.73 - samples/sec: 1867.08 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 18:15:24,755 epoch 9 - iter 300/304 - loss 0.01200321 - time (sec): 16.38 - samples/sec: 1870.93 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 18:15:24,972 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:15:24,973 EPOCH 9 done: loss 0.0119 - lr: 0.000003 | |
| 2023-10-23 18:15:25,835 DEV : loss 0.21348616480827332 - f1-score (micro avg) 0.8415 | |
| 2023-10-23 18:15:25,842 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:15:27,477 epoch 10 - iter 30/304 - loss 0.01226683 - time (sec): 1.63 - samples/sec: 1858.91 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 18:15:29,124 epoch 10 - iter 60/304 - loss 0.01317451 - time (sec): 3.28 - samples/sec: 1868.24 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 18:15:30,776 epoch 10 - iter 90/304 - loss 0.01065899 - time (sec): 4.93 - samples/sec: 1894.11 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 18:15:32,405 epoch 10 - iter 120/304 - loss 0.01158533 - time (sec): 6.56 - samples/sec: 1861.05 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 18:15:34,044 epoch 10 - iter 150/304 - loss 0.01081262 - time (sec): 8.20 - samples/sec: 1876.54 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 18:15:35,682 epoch 10 - iter 180/304 - loss 0.01070216 - time (sec): 9.84 - samples/sec: 1873.61 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 18:15:37,317 epoch 10 - iter 210/304 - loss 0.01196506 - time (sec): 11.47 - samples/sec: 1865.90 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 18:15:38,958 epoch 10 - iter 240/304 - loss 0.01186978 - time (sec): 13.12 - samples/sec: 1888.09 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 18:15:40,534 epoch 10 - iter 270/304 - loss 0.01092989 - time (sec): 14.69 - samples/sec: 1879.86 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 18:15:42,171 epoch 10 - iter 300/304 - loss 0.00998623 - time (sec): 16.33 - samples/sec: 1874.49 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 18:15:42,387 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:15:42,387 EPOCH 10 done: loss 0.0099 - lr: 0.000000 | |
| 2023-10-23 18:15:43,251 DEV : loss 0.216822549700737 - f1-score (micro avg) 0.8431 | |
| 2023-10-23 18:15:43,667 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 18:15:43,669 Loading model from best epoch ... | |
| 2023-10-23 18:15:45,445 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 | |
| 2023-10-23 18:15:46,251 | |
| Results: | |
| - F-score (micro) 0.7967 | |
| - F-score (macro) 0.6456 | |
| - Accuracy 0.6728 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.7407 0.7947 0.7668 151 | |
| pers 0.7459 0.9479 0.8349 96 | |
| work 0.8020 0.8526 0.8265 95 | |
| date 0.0000 0.0000 0.0000 3 | |
| loc 1.0000 0.6667 0.8000 3 | |
| micro avg 0.7538 0.8448 0.7967 348 | |
| macro avg 0.6577 0.6524 0.6456 348 | |
| weighted avg 0.7547 0.8448 0.7955 348 | |
| 2023-10-23 18:15:46,251 ---------------------------------------------------------------------------------------------------- | |