| 2024-03-26 11:41:56,119 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:41:56,119 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 11:41:56,119 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:41:56,119 Corpus: 758 train + 94 dev + 96 test sentences | |
| 2024-03-26 11:41:56,119 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:41:56,119 Train: 758 sentences | |
| 2024-03-26 11:41:56,119 (train_with_dev=False, train_with_test=False) | |
| 2024-03-26 11:41:56,119 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:41:56,119 Training Params: | |
| 2024-03-26 11:41:56,119 - learning_rate: "5e-05" | |
| 2024-03-26 11:41:56,119 - mini_batch_size: "8" | |
| 2024-03-26 11:41:56,119 - max_epochs: "10" | |
| 2024-03-26 11:41:56,119 - shuffle: "True" | |
| 2024-03-26 11:41:56,119 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:41:56,119 Plugins: | |
| 2024-03-26 11:41:56,119 - TensorboardLogger | |
| 2024-03-26 11:41:56,119 - LinearScheduler | warmup_fraction: '0.1' | |
| 2024-03-26 11:41:56,119 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:41:56,119 Final evaluation on model from best epoch (best-model.pt) | |
| 2024-03-26 11:41:56,119 - metric: "('micro avg', 'f1-score')" | |
| 2024-03-26 11:41:56,119 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:41:56,119 Computation: | |
| 2024-03-26 11:41:56,119 - compute on device: cuda:0 | |
| 2024-03-26 11:41:56,119 - embedding storage: none | |
| 2024-03-26 11:41:56,119 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:41:56,120 Model training base path: "flair-co-funer-german_bert_base-bs8-e10-lr5e-05-3" | |
| 2024-03-26 11:41:56,120 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:41:56,120 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:41:56,120 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2024-03-26 11:41:57,551 epoch 1 - iter 9/95 - loss 2.98531268 - time (sec): 1.43 - samples/sec: 2229.09 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 11:41:59,510 epoch 1 - iter 18/95 - loss 2.85818160 - time (sec): 3.39 - samples/sec: 1862.53 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 11:42:01,481 epoch 1 - iter 27/95 - loss 2.62573431 - time (sec): 5.36 - samples/sec: 1842.70 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 11:42:02,897 epoch 1 - iter 36/95 - loss 2.42801287 - time (sec): 6.78 - samples/sec: 1866.86 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 11:42:04,861 epoch 1 - iter 45/95 - loss 2.26046296 - time (sec): 8.74 - samples/sec: 1855.81 - lr: 0.000023 - momentum: 0.000000 | |
| 2024-03-26 11:42:06,284 epoch 1 - iter 54/95 - loss 2.12403468 - time (sec): 10.16 - samples/sec: 1877.80 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 11:42:07,571 epoch 1 - iter 63/95 - loss 2.00022038 - time (sec): 11.45 - samples/sec: 1906.91 - lr: 0.000033 - momentum: 0.000000 | |
| 2024-03-26 11:42:09,548 epoch 1 - iter 72/95 - loss 1.83421116 - time (sec): 13.43 - samples/sec: 1900.47 - lr: 0.000037 - momentum: 0.000000 | |
| 2024-03-26 11:42:11,580 epoch 1 - iter 81/95 - loss 1.68618442 - time (sec): 15.46 - samples/sec: 1888.38 - lr: 0.000042 - momentum: 0.000000 | |
| 2024-03-26 11:42:13,120 epoch 1 - iter 90/95 - loss 1.57871779 - time (sec): 17.00 - samples/sec: 1910.76 - lr: 0.000047 - momentum: 0.000000 | |
| 2024-03-26 11:42:14,216 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:42:14,217 EPOCH 1 done: loss 1.5104 - lr: 0.000047 | |
| 2024-03-26 11:42:15,178 DEV : loss 0.45259279012680054 - f1-score (micro avg) 0.7077 | |
| 2024-03-26 11:42:15,181 saving best model | |
| 2024-03-26 11:42:15,475 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:42:16,898 epoch 2 - iter 9/95 - loss 0.44373371 - time (sec): 1.42 - samples/sec: 1926.19 - lr: 0.000050 - momentum: 0.000000 | |
| 2024-03-26 11:42:18,795 epoch 2 - iter 18/95 - loss 0.37916467 - time (sec): 3.32 - samples/sec: 1840.39 - lr: 0.000049 - momentum: 0.000000 | |
| 2024-03-26 11:42:20,007 epoch 2 - iter 27/95 - loss 0.38336252 - time (sec): 4.53 - samples/sec: 1893.64 - lr: 0.000048 - momentum: 0.000000 | |
| 2024-03-26 11:42:22,319 epoch 2 - iter 36/95 - loss 0.35569118 - time (sec): 6.84 - samples/sec: 1852.74 - lr: 0.000048 - momentum: 0.000000 | |
| 2024-03-26 11:42:24,292 epoch 2 - iter 45/95 - loss 0.34697390 - time (sec): 8.82 - samples/sec: 1865.19 - lr: 0.000047 - momentum: 0.000000 | |
| 2024-03-26 11:42:26,552 epoch 2 - iter 54/95 - loss 0.33937698 - time (sec): 11.08 - samples/sec: 1831.59 - lr: 0.000047 - momentum: 0.000000 | |
| 2024-03-26 11:42:28,617 epoch 2 - iter 63/95 - loss 0.32583403 - time (sec): 13.14 - samples/sec: 1788.68 - lr: 0.000046 - momentum: 0.000000 | |
| 2024-03-26 11:42:30,187 epoch 2 - iter 72/95 - loss 0.32710942 - time (sec): 14.71 - samples/sec: 1795.62 - lr: 0.000046 - momentum: 0.000000 | |
| 2024-03-26 11:42:31,664 epoch 2 - iter 81/95 - loss 0.33105206 - time (sec): 16.19 - samples/sec: 1819.71 - lr: 0.000045 - momentum: 0.000000 | |
| 2024-03-26 11:42:34,031 epoch 2 - iter 90/95 - loss 0.31864283 - time (sec): 18.56 - samples/sec: 1787.63 - lr: 0.000045 - momentum: 0.000000 | |
| 2024-03-26 11:42:34,678 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:42:34,678 EPOCH 2 done: loss 0.3160 - lr: 0.000045 | |
| 2024-03-26 11:42:35,616 DEV : loss 0.25337713956832886 - f1-score (micro avg) 0.8517 | |
| 2024-03-26 11:42:35,618 saving best model | |
| 2024-03-26 11:42:36,073 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:42:37,752 epoch 3 - iter 9/95 - loss 0.16812656 - time (sec): 1.68 - samples/sec: 1780.13 - lr: 0.000044 - momentum: 0.000000 | |
| 2024-03-26 11:42:39,594 epoch 3 - iter 18/95 - loss 0.15920408 - time (sec): 3.52 - samples/sec: 1798.52 - lr: 0.000043 - momentum: 0.000000 | |
| 2024-03-26 11:42:40,825 epoch 3 - iter 27/95 - loss 0.16872134 - time (sec): 4.75 - samples/sec: 1966.68 - lr: 0.000043 - momentum: 0.000000 | |
| 2024-03-26 11:42:42,410 epoch 3 - iter 36/95 - loss 0.16893319 - time (sec): 6.34 - samples/sec: 1960.85 - lr: 0.000042 - momentum: 0.000000 | |
| 2024-03-26 11:42:43,896 epoch 3 - iter 45/95 - loss 0.17276018 - time (sec): 7.82 - samples/sec: 1959.75 - lr: 0.000042 - momentum: 0.000000 | |
| 2024-03-26 11:42:45,951 epoch 3 - iter 54/95 - loss 0.16842614 - time (sec): 9.88 - samples/sec: 1913.47 - lr: 0.000041 - momentum: 0.000000 | |
| 2024-03-26 11:42:48,002 epoch 3 - iter 63/95 - loss 0.16467077 - time (sec): 11.93 - samples/sec: 1866.41 - lr: 0.000041 - momentum: 0.000000 | |
| 2024-03-26 11:42:49,892 epoch 3 - iter 72/95 - loss 0.16937138 - time (sec): 13.82 - samples/sec: 1851.04 - lr: 0.000040 - momentum: 0.000000 | |
| 2024-03-26 11:42:51,947 epoch 3 - iter 81/95 - loss 0.16182392 - time (sec): 15.87 - samples/sec: 1826.48 - lr: 0.000040 - momentum: 0.000000 | |
| 2024-03-26 11:42:53,971 epoch 3 - iter 90/95 - loss 0.16878367 - time (sec): 17.90 - samples/sec: 1826.88 - lr: 0.000039 - momentum: 0.000000 | |
| 2024-03-26 11:42:55,109 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:42:55,109 EPOCH 3 done: loss 0.1651 - lr: 0.000039 | |
| 2024-03-26 11:42:56,049 DEV : loss 0.20585086941719055 - f1-score (micro avg) 0.8694 | |
| 2024-03-26 11:42:56,051 saving best model | |
| 2024-03-26 11:42:56,491 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:42:57,810 epoch 4 - iter 9/95 - loss 0.13194118 - time (sec): 1.32 - samples/sec: 2106.20 - lr: 0.000039 - momentum: 0.000000 | |
| 2024-03-26 11:42:59,733 epoch 4 - iter 18/95 - loss 0.11635540 - time (sec): 3.24 - samples/sec: 1896.31 - lr: 0.000038 - momentum: 0.000000 | |
| 2024-03-26 11:43:01,806 epoch 4 - iter 27/95 - loss 0.11616374 - time (sec): 5.31 - samples/sec: 1817.17 - lr: 0.000037 - momentum: 0.000000 | |
| 2024-03-26 11:43:03,352 epoch 4 - iter 36/95 - loss 0.11100008 - time (sec): 6.86 - samples/sec: 1828.51 - lr: 0.000037 - momentum: 0.000000 | |
| 2024-03-26 11:43:05,888 epoch 4 - iter 45/95 - loss 0.10535501 - time (sec): 9.40 - samples/sec: 1758.68 - lr: 0.000036 - momentum: 0.000000 | |
| 2024-03-26 11:43:07,797 epoch 4 - iter 54/95 - loss 0.10029654 - time (sec): 11.30 - samples/sec: 1745.70 - lr: 0.000036 - momentum: 0.000000 | |
| 2024-03-26 11:43:09,822 epoch 4 - iter 63/95 - loss 0.09898514 - time (sec): 13.33 - samples/sec: 1725.30 - lr: 0.000035 - momentum: 0.000000 | |
| 2024-03-26 11:43:11,758 epoch 4 - iter 72/95 - loss 0.10453018 - time (sec): 15.27 - samples/sec: 1742.83 - lr: 0.000035 - momentum: 0.000000 | |
| 2024-03-26 11:43:13,833 epoch 4 - iter 81/95 - loss 0.11020391 - time (sec): 17.34 - samples/sec: 1743.51 - lr: 0.000034 - momentum: 0.000000 | |
| 2024-03-26 11:43:14,852 epoch 4 - iter 90/95 - loss 0.10933303 - time (sec): 18.36 - samples/sec: 1781.31 - lr: 0.000034 - momentum: 0.000000 | |
| 2024-03-26 11:43:15,901 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:43:15,901 EPOCH 4 done: loss 0.1085 - lr: 0.000034 | |
| 2024-03-26 11:43:16,845 DEV : loss 0.21658340096473694 - f1-score (micro avg) 0.8922 | |
| 2024-03-26 11:43:16,846 saving best model | |
| 2024-03-26 11:43:17,284 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:43:19,178 epoch 5 - iter 9/95 - loss 0.08765859 - time (sec): 1.89 - samples/sec: 1816.78 - lr: 0.000033 - momentum: 0.000000 | |
| 2024-03-26 11:43:20,627 epoch 5 - iter 18/95 - loss 0.08461158 - time (sec): 3.34 - samples/sec: 1872.82 - lr: 0.000032 - momentum: 0.000000 | |
| 2024-03-26 11:43:22,000 epoch 5 - iter 27/95 - loss 0.08758849 - time (sec): 4.71 - samples/sec: 1915.74 - lr: 0.000032 - momentum: 0.000000 | |
| 2024-03-26 11:43:23,943 epoch 5 - iter 36/95 - loss 0.09087793 - time (sec): 6.66 - samples/sec: 1843.47 - lr: 0.000031 - momentum: 0.000000 | |
| 2024-03-26 11:43:26,240 epoch 5 - iter 45/95 - loss 0.08947032 - time (sec): 8.95 - samples/sec: 1818.21 - lr: 0.000031 - momentum: 0.000000 | |
| 2024-03-26 11:43:28,756 epoch 5 - iter 54/95 - loss 0.08289016 - time (sec): 11.47 - samples/sec: 1770.76 - lr: 0.000030 - momentum: 0.000000 | |
| 2024-03-26 11:43:30,466 epoch 5 - iter 63/95 - loss 0.08016941 - time (sec): 13.18 - samples/sec: 1762.63 - lr: 0.000030 - momentum: 0.000000 | |
| 2024-03-26 11:43:32,299 epoch 5 - iter 72/95 - loss 0.07857856 - time (sec): 15.01 - samples/sec: 1761.48 - lr: 0.000029 - momentum: 0.000000 | |
| 2024-03-26 11:43:34,629 epoch 5 - iter 81/95 - loss 0.07793911 - time (sec): 17.34 - samples/sec: 1739.81 - lr: 0.000029 - momentum: 0.000000 | |
| 2024-03-26 11:43:36,053 epoch 5 - iter 90/95 - loss 0.08006927 - time (sec): 18.77 - samples/sec: 1756.16 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 11:43:36,853 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:43:36,853 EPOCH 5 done: loss 0.0783 - lr: 0.000028 | |
| 2024-03-26 11:43:37,901 DEV : loss 0.2107645571231842 - f1-score (micro avg) 0.8962 | |
| 2024-03-26 11:43:37,904 saving best model | |
| 2024-03-26 11:43:38,328 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:43:40,303 epoch 6 - iter 9/95 - loss 0.06558960 - time (sec): 1.97 - samples/sec: 1767.62 - lr: 0.000027 - momentum: 0.000000 | |
| 2024-03-26 11:43:41,904 epoch 6 - iter 18/95 - loss 0.05924394 - time (sec): 3.57 - samples/sec: 1779.28 - lr: 0.000027 - momentum: 0.000000 | |
| 2024-03-26 11:43:43,873 epoch 6 - iter 27/95 - loss 0.05582816 - time (sec): 5.54 - samples/sec: 1783.78 - lr: 0.000026 - momentum: 0.000000 | |
| 2024-03-26 11:43:45,492 epoch 6 - iter 36/95 - loss 0.05713882 - time (sec): 7.16 - samples/sec: 1780.31 - lr: 0.000026 - momentum: 0.000000 | |
| 2024-03-26 11:43:46,974 epoch 6 - iter 45/95 - loss 0.05759581 - time (sec): 8.64 - samples/sec: 1819.13 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 11:43:48,460 epoch 6 - iter 54/95 - loss 0.05489937 - time (sec): 10.13 - samples/sec: 1818.01 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 11:43:49,780 epoch 6 - iter 63/95 - loss 0.05343196 - time (sec): 11.45 - samples/sec: 1877.58 - lr: 0.000024 - momentum: 0.000000 | |
| 2024-03-26 11:43:52,126 epoch 6 - iter 72/95 - loss 0.06130712 - time (sec): 13.80 - samples/sec: 1840.46 - lr: 0.000024 - momentum: 0.000000 | |
| 2024-03-26 11:43:53,766 epoch 6 - iter 81/95 - loss 0.05884556 - time (sec): 15.44 - samples/sec: 1856.30 - lr: 0.000023 - momentum: 0.000000 | |
| 2024-03-26 11:43:55,527 epoch 6 - iter 90/95 - loss 0.06110209 - time (sec): 17.20 - samples/sec: 1874.14 - lr: 0.000023 - momentum: 0.000000 | |
| 2024-03-26 11:43:56,911 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:43:56,911 EPOCH 6 done: loss 0.0620 - lr: 0.000023 | |
| 2024-03-26 11:43:57,864 DEV : loss 0.207626074552536 - f1-score (micro avg) 0.9134 | |
| 2024-03-26 11:43:57,865 saving best model | |
| 2024-03-26 11:43:58,302 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:44:00,339 epoch 7 - iter 9/95 - loss 0.04872148 - time (sec): 2.04 - samples/sec: 1559.83 - lr: 0.000022 - momentum: 0.000000 | |
| 2024-03-26 11:44:02,401 epoch 7 - iter 18/95 - loss 0.03440985 - time (sec): 4.10 - samples/sec: 1599.86 - lr: 0.000021 - momentum: 0.000000 | |
| 2024-03-26 11:44:04,004 epoch 7 - iter 27/95 - loss 0.03042082 - time (sec): 5.70 - samples/sec: 1715.86 - lr: 0.000021 - momentum: 0.000000 | |
| 2024-03-26 11:44:06,048 epoch 7 - iter 36/95 - loss 0.02930015 - time (sec): 7.75 - samples/sec: 1701.29 - lr: 0.000020 - momentum: 0.000000 | |
| 2024-03-26 11:44:08,462 epoch 7 - iter 45/95 - loss 0.03113366 - time (sec): 10.16 - samples/sec: 1706.92 - lr: 0.000020 - momentum: 0.000000 | |
| 2024-03-26 11:44:10,026 epoch 7 - iter 54/95 - loss 0.03136366 - time (sec): 11.72 - samples/sec: 1715.97 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 11:44:12,277 epoch 7 - iter 63/95 - loss 0.03476295 - time (sec): 13.97 - samples/sec: 1723.43 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 11:44:14,115 epoch 7 - iter 72/95 - loss 0.04176420 - time (sec): 15.81 - samples/sec: 1731.25 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 11:44:15,576 epoch 7 - iter 81/95 - loss 0.03898562 - time (sec): 17.27 - samples/sec: 1743.95 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 11:44:17,656 epoch 7 - iter 90/95 - loss 0.04260750 - time (sec): 19.35 - samples/sec: 1721.22 - lr: 0.000017 - momentum: 0.000000 | |
| 2024-03-26 11:44:18,129 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:44:18,129 EPOCH 7 done: loss 0.0426 - lr: 0.000017 | |
| 2024-03-26 11:44:19,058 DEV : loss 0.19692113995552063 - f1-score (micro avg) 0.9265 | |
| 2024-03-26 11:44:19,059 saving best model | |
| 2024-03-26 11:44:19,476 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:44:21,361 epoch 8 - iter 9/95 - loss 0.02324695 - time (sec): 1.88 - samples/sec: 1701.92 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 11:44:23,922 epoch 8 - iter 18/95 - loss 0.02314308 - time (sec): 4.44 - samples/sec: 1666.58 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 11:44:25,761 epoch 8 - iter 27/95 - loss 0.02004589 - time (sec): 6.28 - samples/sec: 1693.42 - lr: 0.000015 - momentum: 0.000000 | |
| 2024-03-26 11:44:27,364 epoch 8 - iter 36/95 - loss 0.02239681 - time (sec): 7.89 - samples/sec: 1681.07 - lr: 0.000015 - momentum: 0.000000 | |
| 2024-03-26 11:44:28,916 epoch 8 - iter 45/95 - loss 0.02059954 - time (sec): 9.44 - samples/sec: 1711.02 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 11:44:30,633 epoch 8 - iter 54/95 - loss 0.02199162 - time (sec): 11.16 - samples/sec: 1729.07 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 11:44:32,899 epoch 8 - iter 63/95 - loss 0.03012961 - time (sec): 13.42 - samples/sec: 1724.26 - lr: 0.000013 - momentum: 0.000000 | |
| 2024-03-26 11:44:35,247 epoch 8 - iter 72/95 - loss 0.03445933 - time (sec): 15.77 - samples/sec: 1701.85 - lr: 0.000013 - momentum: 0.000000 | |
| 2024-03-26 11:44:36,980 epoch 8 - iter 81/95 - loss 0.04080364 - time (sec): 17.50 - samples/sec: 1701.89 - lr: 0.000012 - momentum: 0.000000 | |
| 2024-03-26 11:44:38,290 epoch 8 - iter 90/95 - loss 0.03967245 - time (sec): 18.81 - samples/sec: 1745.22 - lr: 0.000012 - momentum: 0.000000 | |
| 2024-03-26 11:44:39,220 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:44:39,220 EPOCH 8 done: loss 0.0382 - lr: 0.000012 | |
| 2024-03-26 11:44:40,160 DEV : loss 0.20949774980545044 - f1-score (micro avg) 0.9225 | |
| 2024-03-26 11:44:40,163 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:44:42,192 epoch 9 - iter 9/95 - loss 0.00709184 - time (sec): 2.03 - samples/sec: 1738.96 - lr: 0.000011 - momentum: 0.000000 | |
| 2024-03-26 11:44:43,994 epoch 9 - iter 18/95 - loss 0.01806499 - time (sec): 3.83 - samples/sec: 1747.73 - lr: 0.000010 - momentum: 0.000000 | |
| 2024-03-26 11:44:45,936 epoch 9 - iter 27/95 - loss 0.01890732 - time (sec): 5.77 - samples/sec: 1769.95 - lr: 0.000010 - momentum: 0.000000 | |
| 2024-03-26 11:44:47,884 epoch 9 - iter 36/95 - loss 0.01966161 - time (sec): 7.72 - samples/sec: 1759.21 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 11:44:50,206 epoch 9 - iter 45/95 - loss 0.01858568 - time (sec): 10.04 - samples/sec: 1687.90 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 11:44:52,199 epoch 9 - iter 54/95 - loss 0.02246655 - time (sec): 12.04 - samples/sec: 1677.38 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 11:44:54,161 epoch 9 - iter 63/95 - loss 0.02234549 - time (sec): 14.00 - samples/sec: 1686.83 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 11:44:56,178 epoch 9 - iter 72/95 - loss 0.02615055 - time (sec): 16.01 - samples/sec: 1682.78 - lr: 0.000007 - momentum: 0.000000 | |
| 2024-03-26 11:44:57,469 epoch 9 - iter 81/95 - loss 0.02729114 - time (sec): 17.31 - samples/sec: 1706.05 - lr: 0.000007 - momentum: 0.000000 | |
| 2024-03-26 11:44:58,945 epoch 9 - iter 90/95 - loss 0.03054163 - time (sec): 18.78 - samples/sec: 1725.62 - lr: 0.000006 - momentum: 0.000000 | |
| 2024-03-26 11:44:59,928 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:44:59,928 EPOCH 9 done: loss 0.0304 - lr: 0.000006 | |
| 2024-03-26 11:45:00,895 DEV : loss 0.2351907193660736 - f1-score (micro avg) 0.9233 | |
| 2024-03-26 11:45:00,897 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:45:03,122 epoch 10 - iter 9/95 - loss 0.01271718 - time (sec): 2.22 - samples/sec: 1714.23 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 11:45:04,449 epoch 10 - iter 18/95 - loss 0.01054011 - time (sec): 3.55 - samples/sec: 1823.00 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 11:45:05,826 epoch 10 - iter 27/95 - loss 0.02501471 - time (sec): 4.93 - samples/sec: 1924.44 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 11:45:07,249 epoch 10 - iter 36/95 - loss 0.02420587 - time (sec): 6.35 - samples/sec: 1942.16 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 11:45:09,261 epoch 10 - iter 45/95 - loss 0.01990443 - time (sec): 8.36 - samples/sec: 1904.24 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 11:45:10,946 epoch 10 - iter 54/95 - loss 0.01895113 - time (sec): 10.05 - samples/sec: 1886.59 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 11:45:13,542 epoch 10 - iter 63/95 - loss 0.02078384 - time (sec): 12.64 - samples/sec: 1818.35 - lr: 0.000002 - momentum: 0.000000 | |
| 2024-03-26 11:45:14,847 epoch 10 - iter 72/95 - loss 0.01996382 - time (sec): 13.95 - samples/sec: 1828.09 - lr: 0.000002 - momentum: 0.000000 | |
| 2024-03-26 11:45:17,272 epoch 10 - iter 81/95 - loss 0.01848243 - time (sec): 16.37 - samples/sec: 1779.04 - lr: 0.000001 - momentum: 0.000000 | |
| 2024-03-26 11:45:19,576 epoch 10 - iter 90/95 - loss 0.02313635 - time (sec): 18.68 - samples/sec: 1760.78 - lr: 0.000001 - momentum: 0.000000 | |
| 2024-03-26 11:45:20,666 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:45:20,666 EPOCH 10 done: loss 0.0239 - lr: 0.000001 | |
| 2024-03-26 11:45:21,614 DEV : loss 0.23291419446468353 - f1-score (micro avg) 0.9301 | |
| 2024-03-26 11:45:21,617 saving best model | |
| 2024-03-26 11:45:22,374 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 11:45:22,374 Loading model from best epoch ... | |
| 2024-03-26 11:45:23,249 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 11:45:24,026 | |
| Results: | |
| - F-score (micro) 0.9121 | |
| - F-score (macro) 0.6937 | |
| - Accuracy 0.8408 | |
| By class: | |
| precision recall f1-score support | |
| Unternehmen 0.9154 0.8947 0.9049 266 | |
| Auslagerung 0.8626 0.9076 0.8845 249 | |
| Ort 0.9779 0.9925 0.9852 134 | |
| Software 0.0000 0.0000 0.0000 0 | |
| micro avg 0.9045 0.9199 0.9121 649 | |
| macro avg 0.6890 0.6987 0.6937 649 | |
| weighted avg 0.9080 0.9199 0.9137 649 | |
| 2024-03-26 11:45:24,026 ---------------------------------------------------------------------------------------------------- | |