| 2024-03-26 16:16:46,479 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:16:46,479 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(31103, 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 16:16:46,479 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:16:46,479 Corpus: 758 train + 94 dev + 96 test sentences | |
| 2024-03-26 16:16:46,479 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:16:46,479 Train: 758 sentences | |
| 2024-03-26 16:16:46,480 (train_with_dev=False, train_with_test=False) | |
| 2024-03-26 16:16:46,480 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:16:46,480 Training Params: | |
| 2024-03-26 16:16:46,480 - learning_rate: "5e-05" | |
| 2024-03-26 16:16:46,480 - mini_batch_size: "8" | |
| 2024-03-26 16:16:46,480 - max_epochs: "10" | |
| 2024-03-26 16:16:46,480 - shuffle: "True" | |
| 2024-03-26 16:16:46,480 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:16:46,480 Plugins: | |
| 2024-03-26 16:16:46,480 - TensorboardLogger | |
| 2024-03-26 16:16:46,480 - LinearScheduler | warmup_fraction: '0.1' | |
| 2024-03-26 16:16:46,480 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:16:46,480 Final evaluation on model from best epoch (best-model.pt) | |
| 2024-03-26 16:16:46,480 - metric: "('micro avg', 'f1-score')" | |
| 2024-03-26 16:16:46,480 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:16:46,480 Computation: | |
| 2024-03-26 16:16:46,480 - compute on device: cuda:0 | |
| 2024-03-26 16:16:46,480 - embedding storage: none | |
| 2024-03-26 16:16:46,480 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:16:46,480 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs8-e10-lr5e-05-4" | |
| 2024-03-26 16:16:46,480 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:16:46,480 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:16:46,480 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2024-03-26 16:16:47,838 epoch 1 - iter 9/95 - loss 3.00262350 - time (sec): 1.36 - samples/sec: 2136.27 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 16:16:49,226 epoch 1 - iter 18/95 - loss 2.86865129 - time (sec): 2.75 - samples/sec: 2008.21 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 16:16:50,851 epoch 1 - iter 27/95 - loss 2.63140926 - time (sec): 4.37 - samples/sec: 1962.15 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 16:16:52,827 epoch 1 - iter 36/95 - loss 2.40956991 - time (sec): 6.35 - samples/sec: 1880.94 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 16:16:54,688 epoch 1 - iter 45/95 - loss 2.22256453 - time (sec): 8.21 - samples/sec: 1899.81 - lr: 0.000023 - momentum: 0.000000 | |
| 2024-03-26 16:16:56,915 epoch 1 - iter 54/95 - loss 2.05453490 - time (sec): 10.44 - samples/sec: 1834.76 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 16:16:58,921 epoch 1 - iter 63/95 - loss 1.90050388 - time (sec): 12.44 - samples/sec: 1816.73 - lr: 0.000033 - momentum: 0.000000 | |
| 2024-03-26 16:16:59,900 epoch 1 - iter 72/95 - loss 1.81010731 - time (sec): 13.42 - samples/sec: 1861.47 - lr: 0.000037 - momentum: 0.000000 | |
| 2024-03-26 16:17:02,184 epoch 1 - iter 81/95 - loss 1.66282756 - time (sec): 15.70 - samples/sec: 1808.76 - lr: 0.000042 - momentum: 0.000000 | |
| 2024-03-26 16:17:03,533 epoch 1 - iter 90/95 - loss 1.52988728 - time (sec): 17.05 - samples/sec: 1874.19 - lr: 0.000047 - momentum: 0.000000 | |
| 2024-03-26 16:17:04,805 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:17:04,805 EPOCH 1 done: loss 1.4651 - lr: 0.000047 | |
| 2024-03-26 16:17:05,646 DEV : loss 0.43743523955345154 - f1-score (micro avg) 0.6884 | |
| 2024-03-26 16:17:05,647 saving best model | |
| 2024-03-26 16:17:05,931 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:17:07,529 epoch 2 - iter 9/95 - loss 0.51277770 - time (sec): 1.60 - samples/sec: 1804.41 - lr: 0.000050 - momentum: 0.000000 | |
| 2024-03-26 16:17:09,176 epoch 2 - iter 18/95 - loss 0.42088332 - time (sec): 3.24 - samples/sec: 1905.21 - lr: 0.000049 - momentum: 0.000000 | |
| 2024-03-26 16:17:10,963 epoch 2 - iter 27/95 - loss 0.37975632 - time (sec): 5.03 - samples/sec: 1879.49 - lr: 0.000048 - momentum: 0.000000 | |
| 2024-03-26 16:17:13,348 epoch 2 - iter 36/95 - loss 0.32956882 - time (sec): 7.42 - samples/sec: 1759.32 - lr: 0.000048 - momentum: 0.000000 | |
| 2024-03-26 16:17:15,313 epoch 2 - iter 45/95 - loss 0.31872249 - time (sec): 9.38 - samples/sec: 1758.76 - lr: 0.000047 - momentum: 0.000000 | |
| 2024-03-26 16:17:17,066 epoch 2 - iter 54/95 - loss 0.33330241 - time (sec): 11.13 - samples/sec: 1781.26 - lr: 0.000047 - momentum: 0.000000 | |
| 2024-03-26 16:17:19,485 epoch 2 - iter 63/95 - loss 0.31620779 - time (sec): 13.55 - samples/sec: 1764.22 - lr: 0.000046 - momentum: 0.000000 | |
| 2024-03-26 16:17:21,313 epoch 2 - iter 72/95 - loss 0.31691850 - time (sec): 15.38 - samples/sec: 1758.20 - lr: 0.000046 - momentum: 0.000000 | |
| 2024-03-26 16:17:23,486 epoch 2 - iter 81/95 - loss 0.30645467 - time (sec): 17.55 - samples/sec: 1742.75 - lr: 0.000045 - momentum: 0.000000 | |
| 2024-03-26 16:17:24,779 epoch 2 - iter 90/95 - loss 0.30584570 - time (sec): 18.85 - samples/sec: 1767.74 - lr: 0.000045 - momentum: 0.000000 | |
| 2024-03-26 16:17:25,228 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:17:25,229 EPOCH 2 done: loss 0.3034 - lr: 0.000045 | |
| 2024-03-26 16:17:26,171 DEV : loss 0.2551613748073578 - f1-score (micro avg) 0.858 | |
| 2024-03-26 16:17:26,172 saving best model | |
| 2024-03-26 16:17:26,631 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:17:28,219 epoch 3 - iter 9/95 - loss 0.19929203 - time (sec): 1.59 - samples/sec: 1670.30 - lr: 0.000044 - momentum: 0.000000 | |
| 2024-03-26 16:17:29,946 epoch 3 - iter 18/95 - loss 0.16484069 - time (sec): 3.31 - samples/sec: 1686.74 - lr: 0.000043 - momentum: 0.000000 | |
| 2024-03-26 16:17:31,786 epoch 3 - iter 27/95 - loss 0.17282286 - time (sec): 5.15 - samples/sec: 1727.88 - lr: 0.000043 - momentum: 0.000000 | |
| 2024-03-26 16:17:33,566 epoch 3 - iter 36/95 - loss 0.17904644 - time (sec): 6.93 - samples/sec: 1740.98 - lr: 0.000042 - momentum: 0.000000 | |
| 2024-03-26 16:17:35,568 epoch 3 - iter 45/95 - loss 0.18041617 - time (sec): 8.94 - samples/sec: 1766.89 - lr: 0.000042 - momentum: 0.000000 | |
| 2024-03-26 16:17:37,791 epoch 3 - iter 54/95 - loss 0.17709416 - time (sec): 11.16 - samples/sec: 1735.74 - lr: 0.000041 - momentum: 0.000000 | |
| 2024-03-26 16:17:39,504 epoch 3 - iter 63/95 - loss 0.17142452 - time (sec): 12.87 - samples/sec: 1738.04 - lr: 0.000041 - momentum: 0.000000 | |
| 2024-03-26 16:17:41,461 epoch 3 - iter 72/95 - loss 0.16783064 - time (sec): 14.83 - samples/sec: 1745.68 - lr: 0.000040 - momentum: 0.000000 | |
| 2024-03-26 16:17:43,425 epoch 3 - iter 81/95 - loss 0.17363582 - time (sec): 16.79 - samples/sec: 1763.70 - lr: 0.000040 - momentum: 0.000000 | |
| 2024-03-26 16:17:45,653 epoch 3 - iter 90/95 - loss 0.16703518 - time (sec): 19.02 - samples/sec: 1743.54 - lr: 0.000039 - momentum: 0.000000 | |
| 2024-03-26 16:17:46,270 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:17:46,270 EPOCH 3 done: loss 0.1695 - lr: 0.000039 | |
| 2024-03-26 16:17:47,172 DEV : loss 0.1839575171470642 - f1-score (micro avg) 0.8961 | |
| 2024-03-26 16:17:47,173 saving best model | |
| 2024-03-26 16:17:47,627 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:17:50,006 epoch 4 - iter 9/95 - loss 0.05728205 - time (sec): 2.38 - samples/sec: 1663.06 - lr: 0.000039 - momentum: 0.000000 | |
| 2024-03-26 16:17:51,172 epoch 4 - iter 18/95 - loss 0.08157196 - time (sec): 3.54 - samples/sec: 1805.96 - lr: 0.000038 - momentum: 0.000000 | |
| 2024-03-26 16:17:53,286 epoch 4 - iter 27/95 - loss 0.09339161 - time (sec): 5.66 - samples/sec: 1837.92 - lr: 0.000037 - momentum: 0.000000 | |
| 2024-03-26 16:17:54,770 epoch 4 - iter 36/95 - loss 0.10074164 - time (sec): 7.14 - samples/sec: 1867.92 - lr: 0.000037 - momentum: 0.000000 | |
| 2024-03-26 16:17:56,073 epoch 4 - iter 45/95 - loss 0.09879610 - time (sec): 8.45 - samples/sec: 1900.17 - lr: 0.000036 - momentum: 0.000000 | |
| 2024-03-26 16:17:58,115 epoch 4 - iter 54/95 - loss 0.09811905 - time (sec): 10.49 - samples/sec: 1845.66 - lr: 0.000036 - momentum: 0.000000 | |
| 2024-03-26 16:18:00,366 epoch 4 - iter 63/95 - loss 0.11314807 - time (sec): 12.74 - samples/sec: 1817.60 - lr: 0.000035 - momentum: 0.000000 | |
| 2024-03-26 16:18:01,812 epoch 4 - iter 72/95 - loss 0.11201398 - time (sec): 14.18 - samples/sec: 1852.70 - lr: 0.000035 - momentum: 0.000000 | |
| 2024-03-26 16:18:03,404 epoch 4 - iter 81/95 - loss 0.10950966 - time (sec): 15.78 - samples/sec: 1882.73 - lr: 0.000034 - momentum: 0.000000 | |
| 2024-03-26 16:18:05,006 epoch 4 - iter 90/95 - loss 0.10868240 - time (sec): 17.38 - samples/sec: 1910.85 - lr: 0.000034 - momentum: 0.000000 | |
| 2024-03-26 16:18:05,629 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:18:05,629 EPOCH 4 done: loss 0.1093 - lr: 0.000034 | |
| 2024-03-26 16:18:06,542 DEV : loss 0.1929311454296112 - f1-score (micro avg) 0.9018 | |
| 2024-03-26 16:18:06,544 saving best model | |
| 2024-03-26 16:18:07,019 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:18:08,211 epoch 5 - iter 9/95 - loss 0.13206801 - time (sec): 1.19 - samples/sec: 2481.33 - lr: 0.000033 - momentum: 0.000000 | |
| 2024-03-26 16:18:09,650 epoch 5 - iter 18/95 - loss 0.10335413 - time (sec): 2.63 - samples/sec: 2215.56 - lr: 0.000032 - momentum: 0.000000 | |
| 2024-03-26 16:18:11,630 epoch 5 - iter 27/95 - loss 0.09796425 - time (sec): 4.61 - samples/sec: 1994.76 - lr: 0.000032 - momentum: 0.000000 | |
| 2024-03-26 16:18:14,031 epoch 5 - iter 36/95 - loss 0.09235968 - time (sec): 7.01 - samples/sec: 1811.48 - lr: 0.000031 - momentum: 0.000000 | |
| 2024-03-26 16:18:15,260 epoch 5 - iter 45/95 - loss 0.09846890 - time (sec): 8.24 - samples/sec: 1853.46 - lr: 0.000031 - momentum: 0.000000 | |
| 2024-03-26 16:18:17,112 epoch 5 - iter 54/95 - loss 0.09331254 - time (sec): 10.09 - samples/sec: 1896.66 - lr: 0.000030 - momentum: 0.000000 | |
| 2024-03-26 16:18:19,174 epoch 5 - iter 63/95 - loss 0.08754826 - time (sec): 12.15 - samples/sec: 1880.16 - lr: 0.000030 - momentum: 0.000000 | |
| 2024-03-26 16:18:20,430 epoch 5 - iter 72/95 - loss 0.08687357 - time (sec): 13.41 - samples/sec: 1908.90 - lr: 0.000029 - momentum: 0.000000 | |
| 2024-03-26 16:18:22,971 epoch 5 - iter 81/95 - loss 0.08065071 - time (sec): 15.95 - samples/sec: 1841.25 - lr: 0.000029 - momentum: 0.000000 | |
| 2024-03-26 16:18:25,001 epoch 5 - iter 90/95 - loss 0.07883050 - time (sec): 17.98 - samples/sec: 1820.88 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 16:18:25,867 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:18:25,868 EPOCH 5 done: loss 0.0800 - lr: 0.000028 | |
| 2024-03-26 16:18:26,761 DEV : loss 0.15941660106182098 - f1-score (micro avg) 0.9261 | |
| 2024-03-26 16:18:26,762 saving best model | |
| 2024-03-26 16:18:27,217 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:18:28,866 epoch 6 - iter 9/95 - loss 0.11886282 - time (sec): 1.65 - samples/sec: 2013.01 - lr: 0.000027 - momentum: 0.000000 | |
| 2024-03-26 16:18:30,914 epoch 6 - iter 18/95 - loss 0.07533932 - time (sec): 3.70 - samples/sec: 1834.10 - lr: 0.000027 - momentum: 0.000000 | |
| 2024-03-26 16:18:32,340 epoch 6 - iter 27/95 - loss 0.07074169 - time (sec): 5.12 - samples/sec: 1865.99 - lr: 0.000026 - momentum: 0.000000 | |
| 2024-03-26 16:18:34,658 epoch 6 - iter 36/95 - loss 0.05744451 - time (sec): 7.44 - samples/sec: 1726.36 - lr: 0.000026 - momentum: 0.000000 | |
| 2024-03-26 16:18:36,422 epoch 6 - iter 45/95 - loss 0.05462378 - time (sec): 9.20 - samples/sec: 1748.10 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 16:18:38,887 epoch 6 - iter 54/95 - loss 0.06498712 - time (sec): 11.67 - samples/sec: 1725.51 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 16:18:40,389 epoch 6 - iter 63/95 - loss 0.06417750 - time (sec): 13.17 - samples/sec: 1743.00 - lr: 0.000024 - momentum: 0.000000 | |
| 2024-03-26 16:18:41,922 epoch 6 - iter 72/95 - loss 0.06288103 - time (sec): 14.70 - samples/sec: 1764.28 - lr: 0.000024 - momentum: 0.000000 | |
| 2024-03-26 16:18:43,996 epoch 6 - iter 81/95 - loss 0.06385600 - time (sec): 16.78 - samples/sec: 1757.25 - lr: 0.000023 - momentum: 0.000000 | |
| 2024-03-26 16:18:45,182 epoch 6 - iter 90/95 - loss 0.06585962 - time (sec): 17.96 - samples/sec: 1800.68 - lr: 0.000023 - momentum: 0.000000 | |
| 2024-03-26 16:18:46,511 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:18:46,511 EPOCH 6 done: loss 0.0643 - lr: 0.000023 | |
| 2024-03-26 16:18:47,424 DEV : loss 0.17195448279380798 - f1-score (micro avg) 0.9238 | |
| 2024-03-26 16:18:47,426 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:18:48,790 epoch 7 - iter 9/95 - loss 0.03530178 - time (sec): 1.36 - samples/sec: 2325.10 - lr: 0.000022 - momentum: 0.000000 | |
| 2024-03-26 16:18:50,925 epoch 7 - iter 18/95 - loss 0.03302929 - time (sec): 3.50 - samples/sec: 1926.67 - lr: 0.000021 - momentum: 0.000000 | |
| 2024-03-26 16:18:52,890 epoch 7 - iter 27/95 - loss 0.04450097 - time (sec): 5.46 - samples/sec: 1788.82 - lr: 0.000021 - momentum: 0.000000 | |
| 2024-03-26 16:18:54,176 epoch 7 - iter 36/95 - loss 0.04363758 - time (sec): 6.75 - samples/sec: 1853.12 - lr: 0.000020 - momentum: 0.000000 | |
| 2024-03-26 16:18:55,871 epoch 7 - iter 45/95 - loss 0.04190499 - time (sec): 8.44 - samples/sec: 1863.18 - lr: 0.000020 - momentum: 0.000000 | |
| 2024-03-26 16:18:58,083 epoch 7 - iter 54/95 - loss 0.04193570 - time (sec): 10.66 - samples/sec: 1838.49 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 16:19:00,128 epoch 7 - iter 63/95 - loss 0.04441541 - time (sec): 12.70 - samples/sec: 1792.46 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 16:19:02,249 epoch 7 - iter 72/95 - loss 0.04244818 - time (sec): 14.82 - samples/sec: 1770.31 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 16:19:03,772 epoch 7 - iter 81/95 - loss 0.04586669 - time (sec): 16.35 - samples/sec: 1776.56 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 16:19:05,650 epoch 7 - iter 90/95 - loss 0.05078658 - time (sec): 18.22 - samples/sec: 1804.80 - lr: 0.000017 - momentum: 0.000000 | |
| 2024-03-26 16:19:06,349 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:19:06,349 EPOCH 7 done: loss 0.0496 - lr: 0.000017 | |
| 2024-03-26 16:19:07,285 DEV : loss 0.18096165359020233 - f1-score (micro avg) 0.9374 | |
| 2024-03-26 16:19:07,286 saving best model | |
| 2024-03-26 16:19:07,772 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:19:09,421 epoch 8 - iter 9/95 - loss 0.02220779 - time (sec): 1.65 - samples/sec: 1784.88 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 16:19:11,555 epoch 8 - iter 18/95 - loss 0.02181199 - time (sec): 3.78 - samples/sec: 1752.93 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 16:19:13,408 epoch 8 - iter 27/95 - loss 0.03194019 - time (sec): 5.63 - samples/sec: 1722.39 - lr: 0.000015 - momentum: 0.000000 | |
| 2024-03-26 16:19:15,387 epoch 8 - iter 36/95 - loss 0.03072831 - time (sec): 7.61 - samples/sec: 1729.84 - lr: 0.000015 - momentum: 0.000000 | |
| 2024-03-26 16:19:16,420 epoch 8 - iter 45/95 - loss 0.04177717 - time (sec): 8.65 - samples/sec: 1814.20 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 16:19:18,363 epoch 8 - iter 54/95 - loss 0.04283646 - time (sec): 10.59 - samples/sec: 1803.72 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 16:19:20,599 epoch 8 - iter 63/95 - loss 0.04245969 - time (sec): 12.83 - samples/sec: 1786.91 - lr: 0.000013 - momentum: 0.000000 | |
| 2024-03-26 16:19:22,802 epoch 8 - iter 72/95 - loss 0.04307749 - time (sec): 15.03 - samples/sec: 1778.69 - lr: 0.000013 - momentum: 0.000000 | |
| 2024-03-26 16:19:24,523 epoch 8 - iter 81/95 - loss 0.04167099 - time (sec): 16.75 - samples/sec: 1781.78 - lr: 0.000012 - momentum: 0.000000 | |
| 2024-03-26 16:19:26,456 epoch 8 - iter 90/95 - loss 0.03893558 - time (sec): 18.68 - samples/sec: 1776.98 - lr: 0.000012 - momentum: 0.000000 | |
| 2024-03-26 16:19:27,059 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:19:27,060 EPOCH 8 done: loss 0.0395 - lr: 0.000012 | |
| 2024-03-26 16:19:27,991 DEV : loss 0.19180938601493835 - f1-score (micro avg) 0.9328 | |
| 2024-03-26 16:19:27,992 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:19:29,525 epoch 9 - iter 9/95 - loss 0.02551063 - time (sec): 1.53 - samples/sec: 2074.81 - lr: 0.000011 - momentum: 0.000000 | |
| 2024-03-26 16:19:31,827 epoch 9 - iter 18/95 - loss 0.02041207 - time (sec): 3.83 - samples/sec: 1776.05 - lr: 0.000010 - momentum: 0.000000 | |
| 2024-03-26 16:19:33,434 epoch 9 - iter 27/95 - loss 0.01720301 - time (sec): 5.44 - samples/sec: 1791.13 - lr: 0.000010 - momentum: 0.000000 | |
| 2024-03-26 16:19:35,752 epoch 9 - iter 36/95 - loss 0.02365288 - time (sec): 7.76 - samples/sec: 1748.34 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 16:19:37,655 epoch 9 - iter 45/95 - loss 0.02464645 - time (sec): 9.66 - samples/sec: 1721.92 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 16:19:39,039 epoch 9 - iter 54/95 - loss 0.02829044 - time (sec): 11.05 - samples/sec: 1766.46 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 16:19:41,123 epoch 9 - iter 63/95 - loss 0.02602905 - time (sec): 13.13 - samples/sec: 1746.05 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 16:19:42,354 epoch 9 - iter 72/95 - loss 0.03105579 - time (sec): 14.36 - samples/sec: 1779.91 - lr: 0.000007 - momentum: 0.000000 | |
| 2024-03-26 16:19:45,131 epoch 9 - iter 81/95 - loss 0.02971196 - time (sec): 17.14 - samples/sec: 1732.69 - lr: 0.000007 - momentum: 0.000000 | |
| 2024-03-26 16:19:46,775 epoch 9 - iter 90/95 - loss 0.02721575 - time (sec): 18.78 - samples/sec: 1753.95 - lr: 0.000006 - momentum: 0.000000 | |
| 2024-03-26 16:19:47,436 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:19:47,436 EPOCH 9 done: loss 0.0300 - lr: 0.000006 | |
| 2024-03-26 16:19:48,347 DEV : loss 0.20131999254226685 - f1-score (micro avg) 0.9279 | |
| 2024-03-26 16:19:48,348 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:19:50,202 epoch 10 - iter 9/95 - loss 0.03091050 - time (sec): 1.85 - samples/sec: 1672.95 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 16:19:52,390 epoch 10 - iter 18/95 - loss 0.03060304 - time (sec): 4.04 - samples/sec: 1649.22 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 16:19:53,812 epoch 10 - iter 27/95 - loss 0.02620574 - time (sec): 5.46 - samples/sec: 1795.39 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 16:19:55,530 epoch 10 - iter 36/95 - loss 0.02158266 - time (sec): 7.18 - samples/sec: 1837.63 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 16:19:56,956 epoch 10 - iter 45/95 - loss 0.02055081 - time (sec): 8.61 - samples/sec: 1865.79 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 16:19:57,985 epoch 10 - iter 54/95 - loss 0.01888960 - time (sec): 9.64 - samples/sec: 1936.51 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 16:19:59,789 epoch 10 - iter 63/95 - loss 0.01754753 - time (sec): 11.44 - samples/sec: 1910.67 - lr: 0.000002 - momentum: 0.000000 | |
| 2024-03-26 16:20:02,059 epoch 10 - iter 72/95 - loss 0.02462830 - time (sec): 13.71 - samples/sec: 1859.55 - lr: 0.000002 - momentum: 0.000000 | |
| 2024-03-26 16:20:03,695 epoch 10 - iter 81/95 - loss 0.02696906 - time (sec): 15.35 - samples/sec: 1851.50 - lr: 0.000001 - momentum: 0.000000 | |
| 2024-03-26 16:20:06,017 epoch 10 - iter 90/95 - loss 0.02524721 - time (sec): 17.67 - samples/sec: 1839.45 - lr: 0.000001 - momentum: 0.000000 | |
| 2024-03-26 16:20:07,264 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:20:07,264 EPOCH 10 done: loss 0.0269 - lr: 0.000001 | |
| 2024-03-26 16:20:08,197 DEV : loss 0.21133708953857422 - f1-score (micro avg) 0.9359 | |
| 2024-03-26 16:20:08,505 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:20:08,505 Loading model from best epoch ... | |
| 2024-03-26 16:20:09,531 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 16:20:10,310 | |
| Results: | |
| - F-score (micro) 0.8821 | |
| - F-score (macro) 0.6728 | |
| - Accuracy 0.7912 | |
| By class: | |
| precision recall f1-score support | |
| Unternehmen 0.9055 0.8647 0.8846 266 | |
| Auslagerung 0.8137 0.8594 0.8359 249 | |
| Ort 0.9565 0.9851 0.9706 134 | |
| Software 0.0000 0.0000 0.0000 0 | |
| micro avg 0.8767 0.8875 0.8821 649 | |
| macro avg 0.6689 0.6773 0.6728 649 | |
| weighted avg 0.8808 0.8875 0.8837 649 | |
| 2024-03-26 16:20:10,310 ---------------------------------------------------------------------------------------------------- | |