| 2024-03-26 11:21:23,580 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:21:23,580 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(30001, 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=17, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2024-03-26 11:21:23,580 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:21:23,580 Corpus: 758 train + 94 dev + 96 test sentences | |
| 2024-03-26 11:21:23,580 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:21:23,580 Train: 758 sentences | |
| 2024-03-26 11:21:23,581 (train_with_dev=False, train_with_test=False) | |
| 2024-03-26 11:21:23,581 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:21:23,581 Training Params: | |
| 2024-03-26 11:21:23,581 - learning_rate: "3e-05" | |
| 2024-03-26 11:21:23,581 - mini_batch_size: "8" | |
| 2024-03-26 11:21:23,581 - max_epochs: "10" | |
| 2024-03-26 11:21:23,581 - shuffle: "True" | |
| 2024-03-26 11:21:23,581 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:21:23,581 Plugins: | |
| 2024-03-26 11:21:23,581 - TensorboardLogger | |
| 2024-03-26 11:21:23,581 - LinearScheduler | warmup_fraction: '0.1' | |
| 2024-03-26 11:21:23,581 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:21:23,581 Final evaluation on model from best epoch (best-model.pt) | |
| 2024-03-26 11:21:23,581 - metric: "('micro avg', 'f1-score')" | |
| 2024-03-26 11:21:23,581 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:21:23,581 Computation: | |
| 2024-03-26 11:21:23,581 - compute on device: cuda:0 | |
| 2024-03-26 11:21:23,581 - embedding storage: none | |
| 2024-03-26 11:21:23,581 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:21:23,581 Model training base path: "flair-co-funer-german_bert_base-bs8-e10-lr3e-05-2" | |
| 2024-03-26 11:21:23,581 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:21:23,581 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:21:23,581 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2024-03-26 11:21:25,474 epoch 1 - iter 9/95 - loss 3.11557072 - time (sec): 1.89 - samples/sec: 1861.65 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 11:21:27,689 epoch 1 - iter 18/95 - loss 3.07674999 - time (sec): 4.11 - samples/sec: 1754.51 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 11:21:29,285 epoch 1 - iter 27/95 - loss 2.92205455 - time (sec): 5.70 - samples/sec: 1767.69 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 11:21:31,266 epoch 1 - iter 36/95 - loss 2.71661912 - time (sec): 7.69 - samples/sec: 1795.94 - lr: 0.000011 - momentum: 0.000000 | |
| 2024-03-26 11:21:33,385 epoch 1 - iter 45/95 - loss 2.53581484 - time (sec): 9.80 - samples/sec: 1739.09 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 11:21:35,431 epoch 1 - iter 54/95 - loss 2.36834659 - time (sec): 11.85 - samples/sec: 1713.63 - lr: 0.000017 - momentum: 0.000000 | |
| 2024-03-26 11:21:37,009 epoch 1 - iter 63/95 - loss 2.23517454 - time (sec): 13.43 - samples/sec: 1722.79 - lr: 0.000020 - momentum: 0.000000 | |
| 2024-03-26 11:21:38,320 epoch 1 - iter 72/95 - loss 2.10452943 - time (sec): 14.74 - samples/sec: 1774.24 - lr: 0.000022 - momentum: 0.000000 | |
| 2024-03-26 11:21:39,914 epoch 1 - iter 81/95 - loss 1.97687171 - time (sec): 16.33 - samples/sec: 1801.00 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 11:21:41,943 epoch 1 - iter 90/95 - loss 1.85329090 - time (sec): 18.36 - samples/sec: 1775.88 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 11:21:43,059 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:21:43,059 EPOCH 1 done: loss 1.7886 - lr: 0.000028 | |
| 2024-03-26 11:21:43,993 DEV : loss 0.5206313133239746 - f1-score (micro avg) 0.6482 | |
| 2024-03-26 11:21:43,994 saving best model | |
| 2024-03-26 11:21:44,253 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:21:45,596 epoch 2 - iter 9/95 - loss 0.67823346 - time (sec): 1.34 - samples/sec: 2417.26 - lr: 0.000030 - momentum: 0.000000 | |
| 2024-03-26 11:21:47,479 epoch 2 - iter 18/95 - loss 0.54760123 - time (sec): 3.22 - samples/sec: 2130.38 - lr: 0.000029 - momentum: 0.000000 | |
| 2024-03-26 11:21:50,351 epoch 2 - iter 27/95 - loss 0.46607815 - time (sec): 6.10 - samples/sec: 1895.87 - lr: 0.000029 - momentum: 0.000000 | |
| 2024-03-26 11:21:52,507 epoch 2 - iter 36/95 - loss 0.44210057 - time (sec): 8.25 - samples/sec: 1801.44 - lr: 0.000029 - momentum: 0.000000 | |
| 2024-03-26 11:21:54,309 epoch 2 - iter 45/95 - loss 0.41849252 - time (sec): 10.06 - samples/sec: 1787.61 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 11:21:56,470 epoch 2 - iter 54/95 - loss 0.40354492 - time (sec): 12.22 - samples/sec: 1741.72 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 11:21:58,102 epoch 2 - iter 63/95 - loss 0.40666529 - time (sec): 13.85 - samples/sec: 1757.53 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 11:21:59,637 epoch 2 - iter 72/95 - loss 0.40026895 - time (sec): 15.38 - samples/sec: 1783.27 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 11:22:00,816 epoch 2 - iter 81/95 - loss 0.39659236 - time (sec): 16.56 - samples/sec: 1819.08 - lr: 0.000027 - momentum: 0.000000 | |
| 2024-03-26 11:22:02,117 epoch 2 - iter 90/95 - loss 0.38998382 - time (sec): 17.86 - samples/sec: 1841.73 - lr: 0.000027 - momentum: 0.000000 | |
| 2024-03-26 11:22:03,109 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:22:03,109 EPOCH 2 done: loss 0.3799 - lr: 0.000027 | |
| 2024-03-26 11:22:04,036 DEV : loss 0.2723105847835541 - f1-score (micro avg) 0.8308 | |
| 2024-03-26 11:22:04,037 saving best model | |
| 2024-03-26 11:22:04,454 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:22:06,471 epoch 3 - iter 9/95 - loss 0.21258499 - time (sec): 2.01 - samples/sec: 1652.16 - lr: 0.000026 - momentum: 0.000000 | |
| 2024-03-26 11:22:08,586 epoch 3 - iter 18/95 - loss 0.22203275 - time (sec): 4.13 - samples/sec: 1758.63 - lr: 0.000026 - momentum: 0.000000 | |
| 2024-03-26 11:22:09,564 epoch 3 - iter 27/95 - loss 0.22177471 - time (sec): 5.11 - samples/sec: 1883.80 - lr: 0.000026 - momentum: 0.000000 | |
| 2024-03-26 11:22:11,324 epoch 3 - iter 36/95 - loss 0.21771092 - time (sec): 6.87 - samples/sec: 1847.68 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 11:22:12,606 epoch 3 - iter 45/95 - loss 0.23043711 - time (sec): 8.15 - samples/sec: 1889.83 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 11:22:14,664 epoch 3 - iter 54/95 - loss 0.22935549 - time (sec): 10.21 - samples/sec: 1831.51 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 11:22:16,315 epoch 3 - iter 63/95 - loss 0.22730811 - time (sec): 11.86 - samples/sec: 1840.55 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 11:22:17,888 epoch 3 - iter 72/95 - loss 0.22301907 - time (sec): 13.43 - samples/sec: 1844.66 - lr: 0.000024 - momentum: 0.000000 | |
| 2024-03-26 11:22:19,703 epoch 3 - iter 81/95 - loss 0.21456530 - time (sec): 15.25 - samples/sec: 1833.54 - lr: 0.000024 - momentum: 0.000000 | |
| 2024-03-26 11:22:22,391 epoch 3 - iter 90/95 - loss 0.19523106 - time (sec): 17.94 - samples/sec: 1823.40 - lr: 0.000024 - momentum: 0.000000 | |
| 2024-03-26 11:22:23,574 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:22:23,574 EPOCH 3 done: loss 0.1913 - lr: 0.000024 | |
| 2024-03-26 11:22:24,510 DEV : loss 0.240545853972435 - f1-score (micro avg) 0.8746 | |
| 2024-03-26 11:22:24,511 saving best model | |
| 2024-03-26 11:22:24,945 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:22:26,686 epoch 4 - iter 9/95 - loss 0.17933388 - time (sec): 1.74 - samples/sec: 1848.00 - lr: 0.000023 - momentum: 0.000000 | |
| 2024-03-26 11:22:28,783 epoch 4 - iter 18/95 - loss 0.14876494 - time (sec): 3.84 - samples/sec: 1755.97 - lr: 0.000023 - momentum: 0.000000 | |
| 2024-03-26 11:22:30,025 epoch 4 - iter 27/95 - loss 0.13968538 - time (sec): 5.08 - samples/sec: 1853.38 - lr: 0.000022 - momentum: 0.000000 | |
| 2024-03-26 11:22:31,729 epoch 4 - iter 36/95 - loss 0.13484846 - time (sec): 6.78 - samples/sec: 1830.28 - lr: 0.000022 - momentum: 0.000000 | |
| 2024-03-26 11:22:33,950 epoch 4 - iter 45/95 - loss 0.13656782 - time (sec): 9.00 - samples/sec: 1773.50 - lr: 0.000022 - momentum: 0.000000 | |
| 2024-03-26 11:22:35,519 epoch 4 - iter 54/95 - loss 0.14503066 - time (sec): 10.57 - samples/sec: 1785.26 - lr: 0.000022 - momentum: 0.000000 | |
| 2024-03-26 11:22:38,032 epoch 4 - iter 63/95 - loss 0.13934337 - time (sec): 13.08 - samples/sec: 1742.44 - lr: 0.000021 - momentum: 0.000000 | |
| 2024-03-26 11:22:40,579 epoch 4 - iter 72/95 - loss 0.12999178 - time (sec): 15.63 - samples/sec: 1711.27 - lr: 0.000021 - momentum: 0.000000 | |
| 2024-03-26 11:22:42,044 epoch 4 - iter 81/95 - loss 0.12819267 - time (sec): 17.10 - samples/sec: 1718.80 - lr: 0.000021 - momentum: 0.000000 | |
| 2024-03-26 11:22:43,874 epoch 4 - iter 90/95 - loss 0.12899945 - time (sec): 18.93 - samples/sec: 1718.76 - lr: 0.000020 - momentum: 0.000000 | |
| 2024-03-26 11:22:45,041 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:22:45,041 EPOCH 4 done: loss 0.1254 - lr: 0.000020 | |
| 2024-03-26 11:22:45,970 DEV : loss 0.20030681788921356 - f1-score (micro avg) 0.8864 | |
| 2024-03-26 11:22:45,971 saving best model | |
| 2024-03-26 11:22:46,388 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:22:47,357 epoch 5 - iter 9/95 - loss 0.06968794 - time (sec): 0.97 - samples/sec: 2130.62 - lr: 0.000020 - momentum: 0.000000 | |
| 2024-03-26 11:22:48,987 epoch 5 - iter 18/95 - loss 0.08422334 - time (sec): 2.60 - samples/sec: 2049.60 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 11:22:51,634 epoch 5 - iter 27/95 - loss 0.08687954 - time (sec): 5.24 - samples/sec: 1738.57 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 11:22:53,530 epoch 5 - iter 36/95 - loss 0.08428394 - time (sec): 7.14 - samples/sec: 1737.79 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 11:22:55,536 epoch 5 - iter 45/95 - loss 0.08119957 - time (sec): 9.15 - samples/sec: 1709.01 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 11:22:57,188 epoch 5 - iter 54/95 - loss 0.08334333 - time (sec): 10.80 - samples/sec: 1745.18 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 11:22:59,620 epoch 5 - iter 63/95 - loss 0.08575493 - time (sec): 13.23 - samples/sec: 1731.33 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 11:23:01,050 epoch 5 - iter 72/95 - loss 0.09325589 - time (sec): 14.66 - samples/sec: 1752.28 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 11:23:02,976 epoch 5 - iter 81/95 - loss 0.08887188 - time (sec): 16.59 - samples/sec: 1731.37 - lr: 0.000017 - momentum: 0.000000 | |
| 2024-03-26 11:23:04,876 epoch 5 - iter 90/95 - loss 0.09027369 - time (sec): 18.49 - samples/sec: 1733.99 - lr: 0.000017 - momentum: 0.000000 | |
| 2024-03-26 11:23:06,246 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:23:06,246 EPOCH 5 done: loss 0.0912 - lr: 0.000017 | |
| 2024-03-26 11:23:07,179 DEV : loss 0.21548356115818024 - f1-score (micro avg) 0.9065 | |
| 2024-03-26 11:23:07,180 saving best model | |
| 2024-03-26 11:23:07,618 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:23:09,068 epoch 6 - iter 9/95 - loss 0.06991012 - time (sec): 1.45 - samples/sec: 1987.50 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 11:23:11,278 epoch 6 - iter 18/95 - loss 0.06426227 - time (sec): 3.66 - samples/sec: 1959.95 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 11:23:12,875 epoch 6 - iter 27/95 - loss 0.06315170 - time (sec): 5.26 - samples/sec: 1910.70 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 11:23:14,916 epoch 6 - iter 36/95 - loss 0.06999208 - time (sec): 7.30 - samples/sec: 1850.41 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 11:23:17,134 epoch 6 - iter 45/95 - loss 0.08174634 - time (sec): 9.51 - samples/sec: 1867.15 - lr: 0.000015 - momentum: 0.000000 | |
| 2024-03-26 11:23:18,345 epoch 6 - iter 54/95 - loss 0.07922099 - time (sec): 10.73 - samples/sec: 1884.83 - lr: 0.000015 - momentum: 0.000000 | |
| 2024-03-26 11:23:19,439 epoch 6 - iter 63/95 - loss 0.07926444 - time (sec): 11.82 - samples/sec: 1904.88 - lr: 0.000015 - momentum: 0.000000 | |
| 2024-03-26 11:23:21,006 epoch 6 - iter 72/95 - loss 0.07362739 - time (sec): 13.39 - samples/sec: 1907.35 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 11:23:23,060 epoch 6 - iter 81/95 - loss 0.07358180 - time (sec): 15.44 - samples/sec: 1893.48 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 11:23:25,114 epoch 6 - iter 90/95 - loss 0.07329242 - time (sec): 17.49 - samples/sec: 1880.01 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 11:23:26,077 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:23:26,077 EPOCH 6 done: loss 0.0711 - lr: 0.000014 | |
| 2024-03-26 11:23:27,018 DEV : loss 0.19396518170833588 - f1-score (micro avg) 0.9188 | |
| 2024-03-26 11:23:27,020 saving best model | |
| 2024-03-26 11:23:27,446 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:23:28,896 epoch 7 - iter 9/95 - loss 0.03784945 - time (sec): 1.45 - samples/sec: 1835.43 - lr: 0.000013 - momentum: 0.000000 | |
| 2024-03-26 11:23:30,765 epoch 7 - iter 18/95 - loss 0.05259004 - time (sec): 3.32 - samples/sec: 1747.20 - lr: 0.000013 - momentum: 0.000000 | |
| 2024-03-26 11:23:32,415 epoch 7 - iter 27/95 - loss 0.04797867 - time (sec): 4.97 - samples/sec: 1836.54 - lr: 0.000013 - momentum: 0.000000 | |
| 2024-03-26 11:23:34,192 epoch 7 - iter 36/95 - loss 0.04941735 - time (sec): 6.74 - samples/sec: 1783.27 - lr: 0.000012 - momentum: 0.000000 | |
| 2024-03-26 11:23:35,573 epoch 7 - iter 45/95 - loss 0.04881865 - time (sec): 8.13 - samples/sec: 1804.48 - lr: 0.000012 - momentum: 0.000000 | |
| 2024-03-26 11:23:37,685 epoch 7 - iter 54/95 - loss 0.04949831 - time (sec): 10.24 - samples/sec: 1751.01 - lr: 0.000012 - momentum: 0.000000 | |
| 2024-03-26 11:23:39,986 epoch 7 - iter 63/95 - loss 0.04927595 - time (sec): 12.54 - samples/sec: 1702.76 - lr: 0.000011 - momentum: 0.000000 | |
| 2024-03-26 11:23:42,684 epoch 7 - iter 72/95 - loss 0.05611880 - time (sec): 15.24 - samples/sec: 1691.98 - lr: 0.000011 - momentum: 0.000000 | |
| 2024-03-26 11:23:44,691 epoch 7 - iter 81/95 - loss 0.06216960 - time (sec): 17.24 - samples/sec: 1699.79 - lr: 0.000011 - momentum: 0.000000 | |
| 2024-03-26 11:23:46,711 epoch 7 - iter 90/95 - loss 0.06210809 - time (sec): 19.26 - samples/sec: 1701.56 - lr: 0.000010 - momentum: 0.000000 | |
| 2024-03-26 11:23:47,666 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:23:47,666 EPOCH 7 done: loss 0.0607 - lr: 0.000010 | |
| 2024-03-26 11:23:48,604 DEV : loss 0.18384647369384766 - f1-score (micro avg) 0.9245 | |
| 2024-03-26 11:23:48,605 saving best model | |
| 2024-03-26 11:23:49,027 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:23:51,337 epoch 8 - iter 9/95 - loss 0.05530984 - time (sec): 2.31 - samples/sec: 1640.94 - lr: 0.000010 - momentum: 0.000000 | |
| 2024-03-26 11:23:52,924 epoch 8 - iter 18/95 - loss 0.05076397 - time (sec): 3.90 - samples/sec: 1769.13 - lr: 0.000010 - momentum: 0.000000 | |
| 2024-03-26 11:23:55,113 epoch 8 - iter 27/95 - loss 0.05844996 - time (sec): 6.08 - samples/sec: 1737.74 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 11:23:56,689 epoch 8 - iter 36/95 - loss 0.05317296 - time (sec): 7.66 - samples/sec: 1761.32 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 11:23:58,620 epoch 8 - iter 45/95 - loss 0.04686965 - time (sec): 9.59 - samples/sec: 1735.73 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 11:24:00,380 epoch 8 - iter 54/95 - loss 0.04922465 - time (sec): 11.35 - samples/sec: 1740.26 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 11:24:02,193 epoch 8 - iter 63/95 - loss 0.04837573 - time (sec): 13.16 - samples/sec: 1744.40 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 11:24:03,520 epoch 8 - iter 72/95 - loss 0.04744390 - time (sec): 14.49 - samples/sec: 1765.34 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 11:24:05,405 epoch 8 - iter 81/95 - loss 0.04838397 - time (sec): 16.38 - samples/sec: 1787.88 - lr: 0.000007 - momentum: 0.000000 | |
| 2024-03-26 11:24:07,937 epoch 8 - iter 90/95 - loss 0.04553123 - time (sec): 18.91 - samples/sec: 1744.50 - lr: 0.000007 - momentum: 0.000000 | |
| 2024-03-26 11:24:08,789 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:24:08,789 EPOCH 8 done: loss 0.0458 - lr: 0.000007 | |
| 2024-03-26 11:24:09,737 DEV : loss 0.20191706717014313 - f1-score (micro avg) 0.9334 | |
| 2024-03-26 11:24:09,738 saving best model | |
| 2024-03-26 11:24:10,138 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:24:11,917 epoch 9 - iter 9/95 - loss 0.04832010 - time (sec): 1.78 - samples/sec: 1911.27 - lr: 0.000007 - momentum: 0.000000 | |
| 2024-03-26 11:24:14,236 epoch 9 - iter 18/95 - loss 0.03665657 - time (sec): 4.10 - samples/sec: 1692.76 - lr: 0.000006 - momentum: 0.000000 | |
| 2024-03-26 11:24:16,172 epoch 9 - iter 27/95 - loss 0.04227514 - time (sec): 6.03 - samples/sec: 1729.90 - lr: 0.000006 - momentum: 0.000000 | |
| 2024-03-26 11:24:17,756 epoch 9 - iter 36/95 - loss 0.04242815 - time (sec): 7.62 - samples/sec: 1743.09 - lr: 0.000006 - momentum: 0.000000 | |
| 2024-03-26 11:24:19,202 epoch 9 - iter 45/95 - loss 0.03653640 - time (sec): 9.06 - samples/sec: 1780.07 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 11:24:20,629 epoch 9 - iter 54/95 - loss 0.03452892 - time (sec): 10.49 - samples/sec: 1833.64 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 11:24:22,536 epoch 9 - iter 63/95 - loss 0.03920444 - time (sec): 12.40 - samples/sec: 1833.45 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 11:24:24,590 epoch 9 - iter 72/95 - loss 0.04021237 - time (sec): 14.45 - samples/sec: 1807.68 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 11:24:26,931 epoch 9 - iter 81/95 - loss 0.04095813 - time (sec): 16.79 - samples/sec: 1767.62 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 11:24:28,720 epoch 9 - iter 90/95 - loss 0.04018029 - time (sec): 18.58 - samples/sec: 1781.36 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 11:24:29,321 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:24:29,321 EPOCH 9 done: loss 0.0401 - lr: 0.000004 | |
| 2024-03-26 11:24:30,254 DEV : loss 0.19197042286396027 - f1-score (micro avg) 0.9391 | |
| 2024-03-26 11:24:30,255 saving best model | |
| 2024-03-26 11:24:30,673 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:24:32,792 epoch 10 - iter 9/95 - loss 0.00978685 - time (sec): 2.12 - samples/sec: 1824.59 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 11:24:34,600 epoch 10 - iter 18/95 - loss 0.02419535 - time (sec): 3.92 - samples/sec: 1810.09 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 11:24:35,713 epoch 10 - iter 27/95 - loss 0.02107737 - time (sec): 5.04 - samples/sec: 1890.85 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 11:24:37,186 epoch 10 - iter 36/95 - loss 0.02692307 - time (sec): 6.51 - samples/sec: 1923.00 - lr: 0.000002 - momentum: 0.000000 | |
| 2024-03-26 11:24:39,247 epoch 10 - iter 45/95 - loss 0.03594101 - time (sec): 8.57 - samples/sec: 1841.70 - lr: 0.000002 - momentum: 0.000000 | |
| 2024-03-26 11:24:40,359 epoch 10 - iter 54/95 - loss 0.03803968 - time (sec): 9.68 - samples/sec: 1890.32 - lr: 0.000002 - momentum: 0.000000 | |
| 2024-03-26 11:24:41,627 epoch 10 - iter 63/95 - loss 0.03512331 - time (sec): 10.95 - samples/sec: 1915.96 - lr: 0.000001 - momentum: 0.000000 | |
| 2024-03-26 11:24:43,578 epoch 10 - iter 72/95 - loss 0.03520742 - time (sec): 12.90 - samples/sec: 1913.85 - lr: 0.000001 - momentum: 0.000000 | |
| 2024-03-26 11:24:46,230 epoch 10 - iter 81/95 - loss 0.03414263 - time (sec): 15.55 - samples/sec: 1883.19 - lr: 0.000001 - momentum: 0.000000 | |
| 2024-03-26 11:24:48,329 epoch 10 - iter 90/95 - loss 0.03430259 - time (sec): 17.65 - samples/sec: 1858.65 - lr: 0.000000 - momentum: 0.000000 | |
| 2024-03-26 11:24:49,281 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:24:49,281 EPOCH 10 done: loss 0.0340 - lr: 0.000000 | |
| 2024-03-26 11:24:50,220 DEV : loss 0.20091010630130768 - f1-score (micro avg) 0.9305 | |
| 2024-03-26 11:24:50,504 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:24:50,504 Loading model from best epoch ... | |
| 2024-03-26 11:24:51,344 SequenceTagger predicts: Dictionary with 17 tags: O, S-Unternehmen, B-Unternehmen, E-Unternehmen, I-Unternehmen, S-Auslagerung, B-Auslagerung, E-Auslagerung, I-Auslagerung, S-Ort, B-Ort, E-Ort, I-Ort, S-Software, B-Software, E-Software, I-Software | |
| 2024-03-26 11:24:52,097 | |
| Results: | |
| - F-score (micro) 0.9126 | |
| - F-score (macro) 0.6925 | |
| - Accuracy 0.8416 | |
| By class: | |
| precision recall f1-score support | |
| Unternehmen 0.9091 0.9023 0.9057 266 | |
| Auslagerung 0.8849 0.8956 0.8902 249 | |
| Ort 0.9635 0.9851 0.9742 134 | |
| Software 0.0000 0.0000 0.0000 0 | |
| micro avg 0.9084 0.9168 0.9126 649 | |
| macro avg 0.6894 0.6957 0.6925 649 | |
| weighted avg 0.9111 0.9168 0.9139 649 | |
| 2024-03-26 11:24:52,097 ---------------------------------------------------------------------------------------------------- | |