| 2024-03-26 16:33:19,133 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:33:19,133 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 16:33:19,133 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:33:19,133 Corpus: 758 train + 94 dev + 96 test sentences | |
| 2024-03-26 16:33:19,133 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:33:19,133 Train: 758 sentences | |
| 2024-03-26 16:33:19,133 (train_with_dev=False, train_with_test=False) | |
| 2024-03-26 16:33:19,133 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:33:19,133 Training Params: | |
| 2024-03-26 16:33:19,133 - learning_rate: "5e-05" | |
| 2024-03-26 16:33:19,133 - mini_batch_size: "8" | |
| 2024-03-26 16:33:19,133 - max_epochs: "10" | |
| 2024-03-26 16:33:19,133 - shuffle: "True" | |
| 2024-03-26 16:33:19,133 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:33:19,133 Plugins: | |
| 2024-03-26 16:33:19,133 - TensorboardLogger | |
| 2024-03-26 16:33:19,133 - LinearScheduler | warmup_fraction: '0.1' | |
| 2024-03-26 16:33:19,133 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:33:19,133 Final evaluation on model from best epoch (best-model.pt) | |
| 2024-03-26 16:33:19,133 - metric: "('micro avg', 'f1-score')" | |
| 2024-03-26 16:33:19,133 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:33:19,133 Computation: | |
| 2024-03-26 16:33:19,133 - compute on device: cuda:0 | |
| 2024-03-26 16:33:19,133 - embedding storage: none | |
| 2024-03-26 16:33:19,133 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:33:19,134 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs8-e10-lr5e-05-5" | |
| 2024-03-26 16:33:19,134 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:33:19,134 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:33:19,134 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2024-03-26 16:33:20,989 epoch 1 - iter 9/95 - loss 3.24854896 - time (sec): 1.86 - samples/sec: 1690.00 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 16:33:22,856 epoch 1 - iter 18/95 - loss 3.07358066 - time (sec): 3.72 - samples/sec: 1781.85 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 16:33:25,138 epoch 1 - iter 27/95 - loss 2.80252277 - time (sec): 6.00 - samples/sec: 1727.30 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 16:33:26,618 epoch 1 - iter 36/95 - loss 2.60668952 - time (sec): 7.48 - samples/sec: 1805.13 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 16:33:28,762 epoch 1 - iter 45/95 - loss 2.40409254 - time (sec): 9.63 - samples/sec: 1784.79 - lr: 0.000023 - momentum: 0.000000 | |
| 2024-03-26 16:33:30,337 epoch 1 - iter 54/95 - loss 2.22917451 - time (sec): 11.20 - samples/sec: 1806.10 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 16:33:31,959 epoch 1 - iter 63/95 - loss 2.07783198 - time (sec): 12.83 - samples/sec: 1824.75 - lr: 0.000033 - momentum: 0.000000 | |
| 2024-03-26 16:33:33,831 epoch 1 - iter 72/95 - loss 1.92712496 - time (sec): 14.70 - samples/sec: 1816.59 - lr: 0.000037 - momentum: 0.000000 | |
| 2024-03-26 16:33:35,888 epoch 1 - iter 81/95 - loss 1.77489410 - time (sec): 16.75 - samples/sec: 1799.51 - lr: 0.000042 - momentum: 0.000000 | |
| 2024-03-26 16:33:37,515 epoch 1 - iter 90/95 - loss 1.66711022 - time (sec): 18.38 - samples/sec: 1791.34 - lr: 0.000047 - momentum: 0.000000 | |
| 2024-03-26 16:33:38,262 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:33:38,262 EPOCH 1 done: loss 1.6139 - lr: 0.000047 | |
| 2024-03-26 16:33:39,161 DEV : loss 0.4351406395435333 - f1-score (micro avg) 0.7212 | |
| 2024-03-26 16:33:39,162 saving best model | |
| 2024-03-26 16:33:39,430 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:33:41,682 epoch 2 - iter 9/95 - loss 0.45840955 - time (sec): 2.25 - samples/sec: 1694.88 - lr: 0.000050 - momentum: 0.000000 | |
| 2024-03-26 16:33:43,575 epoch 2 - iter 18/95 - loss 0.41958130 - time (sec): 4.14 - samples/sec: 1687.67 - lr: 0.000049 - momentum: 0.000000 | |
| 2024-03-26 16:33:45,878 epoch 2 - iter 27/95 - loss 0.38281852 - time (sec): 6.45 - samples/sec: 1659.07 - lr: 0.000048 - momentum: 0.000000 | |
| 2024-03-26 16:33:47,237 epoch 2 - iter 36/95 - loss 0.38193994 - time (sec): 7.81 - samples/sec: 1770.34 - lr: 0.000048 - momentum: 0.000000 | |
| 2024-03-26 16:33:49,178 epoch 2 - iter 45/95 - loss 0.35971712 - time (sec): 9.75 - samples/sec: 1731.63 - lr: 0.000047 - momentum: 0.000000 | |
| 2024-03-26 16:33:50,489 epoch 2 - iter 54/95 - loss 0.35603409 - time (sec): 11.06 - samples/sec: 1777.46 - lr: 0.000047 - momentum: 0.000000 | |
| 2024-03-26 16:33:52,045 epoch 2 - iter 63/95 - loss 0.34355218 - time (sec): 12.61 - samples/sec: 1794.13 - lr: 0.000046 - momentum: 0.000000 | |
| 2024-03-26 16:33:54,098 epoch 2 - iter 72/95 - loss 0.33787014 - time (sec): 14.67 - samples/sec: 1786.93 - lr: 0.000046 - momentum: 0.000000 | |
| 2024-03-26 16:33:55,994 epoch 2 - iter 81/95 - loss 0.34238730 - time (sec): 16.56 - samples/sec: 1786.65 - lr: 0.000045 - momentum: 0.000000 | |
| 2024-03-26 16:33:57,912 epoch 2 - iter 90/95 - loss 0.32998840 - time (sec): 18.48 - samples/sec: 1789.66 - lr: 0.000045 - momentum: 0.000000 | |
| 2024-03-26 16:33:58,495 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:33:58,495 EPOCH 2 done: loss 0.3291 - lr: 0.000045 | |
| 2024-03-26 16:33:59,391 DEV : loss 0.27971890568733215 - f1-score (micro avg) 0.8157 | |
| 2024-03-26 16:33:59,394 saving best model | |
| 2024-03-26 16:33:59,877 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:34:01,083 epoch 3 - iter 9/95 - loss 0.28513758 - time (sec): 1.20 - samples/sec: 2154.65 - lr: 0.000044 - momentum: 0.000000 | |
| 2024-03-26 16:34:03,315 epoch 3 - iter 18/95 - loss 0.21533520 - time (sec): 3.44 - samples/sec: 1868.50 - lr: 0.000043 - momentum: 0.000000 | |
| 2024-03-26 16:34:05,003 epoch 3 - iter 27/95 - loss 0.21474052 - time (sec): 5.12 - samples/sec: 1904.62 - lr: 0.000043 - momentum: 0.000000 | |
| 2024-03-26 16:34:06,685 epoch 3 - iter 36/95 - loss 0.19999637 - time (sec): 6.81 - samples/sec: 1935.08 - lr: 0.000042 - momentum: 0.000000 | |
| 2024-03-26 16:34:08,123 epoch 3 - iter 45/95 - loss 0.18922890 - time (sec): 8.24 - samples/sec: 1926.51 - lr: 0.000042 - momentum: 0.000000 | |
| 2024-03-26 16:34:10,232 epoch 3 - iter 54/95 - loss 0.18514483 - time (sec): 10.35 - samples/sec: 1866.13 - lr: 0.000041 - momentum: 0.000000 | |
| 2024-03-26 16:34:11,896 epoch 3 - iter 63/95 - loss 0.18888961 - time (sec): 12.02 - samples/sec: 1852.20 - lr: 0.000041 - momentum: 0.000000 | |
| 2024-03-26 16:34:14,159 epoch 3 - iter 72/95 - loss 0.17931067 - time (sec): 14.28 - samples/sec: 1816.53 - lr: 0.000040 - momentum: 0.000000 | |
| 2024-03-26 16:34:16,324 epoch 3 - iter 81/95 - loss 0.18087446 - time (sec): 16.44 - samples/sec: 1810.10 - lr: 0.000040 - momentum: 0.000000 | |
| 2024-03-26 16:34:18,062 epoch 3 - iter 90/95 - loss 0.17560689 - time (sec): 18.18 - samples/sec: 1799.62 - lr: 0.000039 - momentum: 0.000000 | |
| 2024-03-26 16:34:18,932 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:34:18,932 EPOCH 3 done: loss 0.1744 - lr: 0.000039 | |
| 2024-03-26 16:34:19,825 DEV : loss 0.23761968314647675 - f1-score (micro avg) 0.8655 | |
| 2024-03-26 16:34:19,826 saving best model | |
| 2024-03-26 16:34:20,292 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:34:23,059 epoch 4 - iter 9/95 - loss 0.09834786 - time (sec): 2.76 - samples/sec: 1543.55 - lr: 0.000039 - momentum: 0.000000 | |
| 2024-03-26 16:34:24,091 epoch 4 - iter 18/95 - loss 0.13033853 - time (sec): 3.80 - samples/sec: 1752.42 - lr: 0.000038 - momentum: 0.000000 | |
| 2024-03-26 16:34:26,586 epoch 4 - iter 27/95 - loss 0.11939331 - time (sec): 6.29 - samples/sec: 1690.80 - lr: 0.000037 - momentum: 0.000000 | |
| 2024-03-26 16:34:29,194 epoch 4 - iter 36/95 - loss 0.11628526 - time (sec): 8.90 - samples/sec: 1630.71 - lr: 0.000037 - momentum: 0.000000 | |
| 2024-03-26 16:34:30,888 epoch 4 - iter 45/95 - loss 0.10860399 - time (sec): 10.59 - samples/sec: 1662.50 - lr: 0.000036 - momentum: 0.000000 | |
| 2024-03-26 16:34:32,590 epoch 4 - iter 54/95 - loss 0.11019024 - time (sec): 12.30 - samples/sec: 1675.39 - lr: 0.000036 - momentum: 0.000000 | |
| 2024-03-26 16:34:34,490 epoch 4 - iter 63/95 - loss 0.10937511 - time (sec): 14.20 - samples/sec: 1701.64 - lr: 0.000035 - momentum: 0.000000 | |
| 2024-03-26 16:34:36,158 epoch 4 - iter 72/95 - loss 0.11112580 - time (sec): 15.86 - samples/sec: 1749.69 - lr: 0.000035 - momentum: 0.000000 | |
| 2024-03-26 16:34:37,187 epoch 4 - iter 81/95 - loss 0.11246023 - time (sec): 16.89 - samples/sec: 1788.59 - lr: 0.000034 - momentum: 0.000000 | |
| 2024-03-26 16:34:38,590 epoch 4 - iter 90/95 - loss 0.11310225 - time (sec): 18.30 - samples/sec: 1813.96 - lr: 0.000034 - momentum: 0.000000 | |
| 2024-03-26 16:34:39,123 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:34:39,123 EPOCH 4 done: loss 0.1155 - lr: 0.000034 | |
| 2024-03-26 16:34:40,019 DEV : loss 0.1822824329137802 - f1-score (micro avg) 0.8987 | |
| 2024-03-26 16:34:40,020 saving best model | |
| 2024-03-26 16:34:40,469 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:34:42,116 epoch 5 - iter 9/95 - loss 0.10147143 - time (sec): 1.65 - samples/sec: 1990.52 - lr: 0.000033 - momentum: 0.000000 | |
| 2024-03-26 16:34:44,068 epoch 5 - iter 18/95 - loss 0.09338652 - time (sec): 3.60 - samples/sec: 1979.21 - lr: 0.000032 - momentum: 0.000000 | |
| 2024-03-26 16:34:46,183 epoch 5 - iter 27/95 - loss 0.07607096 - time (sec): 5.71 - samples/sec: 1853.46 - lr: 0.000032 - momentum: 0.000000 | |
| 2024-03-26 16:34:47,507 epoch 5 - iter 36/95 - loss 0.08827446 - time (sec): 7.04 - samples/sec: 1910.63 - lr: 0.000031 - momentum: 0.000000 | |
| 2024-03-26 16:34:49,587 epoch 5 - iter 45/95 - loss 0.08470804 - time (sec): 9.12 - samples/sec: 1869.04 - lr: 0.000031 - momentum: 0.000000 | |
| 2024-03-26 16:34:50,755 epoch 5 - iter 54/95 - loss 0.08922696 - time (sec): 10.28 - samples/sec: 1903.76 - lr: 0.000030 - momentum: 0.000000 | |
| 2024-03-26 16:34:52,219 epoch 5 - iter 63/95 - loss 0.09288529 - time (sec): 11.75 - samples/sec: 1918.98 - lr: 0.000030 - momentum: 0.000000 | |
| 2024-03-26 16:34:54,145 epoch 5 - iter 72/95 - loss 0.09210498 - time (sec): 13.67 - samples/sec: 1888.50 - lr: 0.000029 - momentum: 0.000000 | |
| 2024-03-26 16:34:55,901 epoch 5 - iter 81/95 - loss 0.08981069 - time (sec): 15.43 - samples/sec: 1877.15 - lr: 0.000029 - momentum: 0.000000 | |
| 2024-03-26 16:34:58,305 epoch 5 - iter 90/95 - loss 0.08713307 - time (sec): 17.83 - samples/sec: 1843.54 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 16:34:59,269 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:34:59,269 EPOCH 5 done: loss 0.0848 - lr: 0.000028 | |
| 2024-03-26 16:35:00,165 DEV : loss 0.20745961368083954 - f1-score (micro avg) 0.9146 | |
| 2024-03-26 16:35:00,166 saving best model | |
| 2024-03-26 16:35:00,613 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:35:02,546 epoch 6 - iter 9/95 - loss 0.06298504 - time (sec): 1.93 - samples/sec: 1688.35 - lr: 0.000027 - momentum: 0.000000 | |
| 2024-03-26 16:35:05,041 epoch 6 - iter 18/95 - loss 0.06865678 - time (sec): 4.43 - samples/sec: 1675.17 - lr: 0.000027 - momentum: 0.000000 | |
| 2024-03-26 16:35:06,182 epoch 6 - iter 27/95 - loss 0.08561234 - time (sec): 5.57 - samples/sec: 1775.90 - lr: 0.000026 - momentum: 0.000000 | |
| 2024-03-26 16:35:07,777 epoch 6 - iter 36/95 - loss 0.07632065 - time (sec): 7.16 - samples/sec: 1801.53 - lr: 0.000026 - momentum: 0.000000 | |
| 2024-03-26 16:35:09,716 epoch 6 - iter 45/95 - loss 0.07129585 - time (sec): 9.10 - samples/sec: 1795.11 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 16:35:11,849 epoch 6 - iter 54/95 - loss 0.06756906 - time (sec): 11.23 - samples/sec: 1761.43 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 16:35:13,520 epoch 6 - iter 63/95 - loss 0.07022057 - time (sec): 12.91 - samples/sec: 1779.73 - lr: 0.000024 - momentum: 0.000000 | |
| 2024-03-26 16:35:15,066 epoch 6 - iter 72/95 - loss 0.06980907 - time (sec): 14.45 - samples/sec: 1802.03 - lr: 0.000024 - momentum: 0.000000 | |
| 2024-03-26 16:35:16,293 epoch 6 - iter 81/95 - loss 0.06957376 - time (sec): 15.68 - samples/sec: 1833.37 - lr: 0.000023 - momentum: 0.000000 | |
| 2024-03-26 16:35:18,155 epoch 6 - iter 90/95 - loss 0.06638177 - time (sec): 17.54 - samples/sec: 1831.90 - lr: 0.000023 - momentum: 0.000000 | |
| 2024-03-26 16:35:19,658 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:35:19,658 EPOCH 6 done: loss 0.0642 - lr: 0.000023 | |
| 2024-03-26 16:35:20,560 DEV : loss 0.23903107643127441 - f1-score (micro avg) 0.8977 | |
| 2024-03-26 16:35:20,561 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:35:22,226 epoch 7 - iter 9/95 - loss 0.03188809 - time (sec): 1.66 - samples/sec: 1891.74 - lr: 0.000022 - momentum: 0.000000 | |
| 2024-03-26 16:35:23,710 epoch 7 - iter 18/95 - loss 0.03992625 - time (sec): 3.15 - samples/sec: 1868.11 - lr: 0.000021 - momentum: 0.000000 | |
| 2024-03-26 16:35:24,993 epoch 7 - iter 27/95 - loss 0.05762778 - time (sec): 4.43 - samples/sec: 1910.82 - lr: 0.000021 - momentum: 0.000000 | |
| 2024-03-26 16:35:27,221 epoch 7 - iter 36/95 - loss 0.05070152 - time (sec): 6.66 - samples/sec: 1908.52 - lr: 0.000020 - momentum: 0.000000 | |
| 2024-03-26 16:35:29,115 epoch 7 - iter 45/95 - loss 0.05323369 - time (sec): 8.55 - samples/sec: 1903.57 - lr: 0.000020 - momentum: 0.000000 | |
| 2024-03-26 16:35:30,786 epoch 7 - iter 54/95 - loss 0.05403030 - time (sec): 10.22 - samples/sec: 1896.56 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 16:35:32,336 epoch 7 - iter 63/95 - loss 0.05286632 - time (sec): 11.77 - samples/sec: 1914.22 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 16:35:33,836 epoch 7 - iter 72/95 - loss 0.05383539 - time (sec): 13.27 - samples/sec: 1904.23 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 16:35:36,517 epoch 7 - iter 81/95 - loss 0.05219211 - time (sec): 15.96 - samples/sec: 1841.30 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 16:35:38,113 epoch 7 - iter 90/95 - loss 0.05217584 - time (sec): 17.55 - samples/sec: 1850.36 - lr: 0.000017 - momentum: 0.000000 | |
| 2024-03-26 16:35:39,273 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:35:39,273 EPOCH 7 done: loss 0.0517 - lr: 0.000017 | |
| 2024-03-26 16:35:40,170 DEV : loss 0.20635825395584106 - f1-score (micro avg) 0.9314 | |
| 2024-03-26 16:35:40,171 saving best model | |
| 2024-03-26 16:35:40,618 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:35:42,763 epoch 8 - iter 9/95 - loss 0.05102066 - time (sec): 2.14 - samples/sec: 1577.33 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 16:35:44,258 epoch 8 - iter 18/95 - loss 0.03497137 - time (sec): 3.64 - samples/sec: 1677.58 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 16:35:46,235 epoch 8 - iter 27/95 - loss 0.03720698 - time (sec): 5.61 - samples/sec: 1747.52 - lr: 0.000015 - momentum: 0.000000 | |
| 2024-03-26 16:35:48,192 epoch 8 - iter 36/95 - loss 0.03472594 - time (sec): 7.57 - samples/sec: 1778.05 - lr: 0.000015 - momentum: 0.000000 | |
| 2024-03-26 16:35:49,597 epoch 8 - iter 45/95 - loss 0.03123332 - time (sec): 8.98 - samples/sec: 1833.42 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 16:35:51,078 epoch 8 - iter 54/95 - loss 0.03271144 - time (sec): 10.46 - samples/sec: 1900.25 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 16:35:52,630 epoch 8 - iter 63/95 - loss 0.03378471 - time (sec): 12.01 - samples/sec: 1893.53 - lr: 0.000013 - momentum: 0.000000 | |
| 2024-03-26 16:35:54,701 epoch 8 - iter 72/95 - loss 0.03345516 - time (sec): 14.08 - samples/sec: 1859.48 - lr: 0.000013 - momentum: 0.000000 | |
| 2024-03-26 16:35:56,255 epoch 8 - iter 81/95 - loss 0.03613973 - time (sec): 15.63 - samples/sec: 1883.43 - lr: 0.000012 - momentum: 0.000000 | |
| 2024-03-26 16:35:58,309 epoch 8 - iter 90/95 - loss 0.03668683 - time (sec): 17.69 - samples/sec: 1858.78 - lr: 0.000012 - momentum: 0.000000 | |
| 2024-03-26 16:35:58,941 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:35:58,941 EPOCH 8 done: loss 0.0367 - lr: 0.000012 | |
| 2024-03-26 16:35:59,840 DEV : loss 0.21807697415351868 - f1-score (micro avg) 0.9353 | |
| 2024-03-26 16:35:59,841 saving best model | |
| 2024-03-26 16:36:00,324 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:36:02,854 epoch 9 - iter 9/95 - loss 0.01698379 - time (sec): 2.53 - samples/sec: 1706.11 - lr: 0.000011 - momentum: 0.000000 | |
| 2024-03-26 16:36:04,400 epoch 9 - iter 18/95 - loss 0.02484097 - time (sec): 4.07 - samples/sec: 1775.05 - lr: 0.000010 - momentum: 0.000000 | |
| 2024-03-26 16:36:06,866 epoch 9 - iter 27/95 - loss 0.02660767 - time (sec): 6.54 - samples/sec: 1728.36 - lr: 0.000010 - momentum: 0.000000 | |
| 2024-03-26 16:36:08,677 epoch 9 - iter 36/95 - loss 0.03340323 - time (sec): 8.35 - samples/sec: 1735.27 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 16:36:09,836 epoch 9 - iter 45/95 - loss 0.03134273 - time (sec): 9.51 - samples/sec: 1793.48 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 16:36:11,581 epoch 9 - iter 54/95 - loss 0.02840040 - time (sec): 11.26 - samples/sec: 1782.53 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 16:36:12,959 epoch 9 - iter 63/95 - loss 0.02914536 - time (sec): 12.63 - samples/sec: 1828.49 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 16:36:14,120 epoch 9 - iter 72/95 - loss 0.02916945 - time (sec): 13.80 - samples/sec: 1878.07 - lr: 0.000007 - momentum: 0.000000 | |
| 2024-03-26 16:36:15,647 epoch 9 - iter 81/95 - loss 0.02734729 - time (sec): 15.32 - samples/sec: 1874.96 - lr: 0.000007 - momentum: 0.000000 | |
| 2024-03-26 16:36:18,381 epoch 9 - iter 90/95 - loss 0.03042663 - time (sec): 18.06 - samples/sec: 1826.28 - lr: 0.000006 - momentum: 0.000000 | |
| 2024-03-26 16:36:19,146 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:36:19,146 EPOCH 9 done: loss 0.0293 - lr: 0.000006 | |
| 2024-03-26 16:36:20,074 DEV : loss 0.2363407462835312 - f1-score (micro avg) 0.9318 | |
| 2024-03-26 16:36:20,075 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:36:22,516 epoch 10 - iter 9/95 - loss 0.01719432 - time (sec): 2.44 - samples/sec: 1653.22 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 16:36:24,089 epoch 10 - iter 18/95 - loss 0.01636941 - time (sec): 4.01 - samples/sec: 1737.00 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 16:36:26,052 epoch 10 - iter 27/95 - loss 0.01537360 - time (sec): 5.98 - samples/sec: 1686.18 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 16:36:28,118 epoch 10 - iter 36/95 - loss 0.01809330 - time (sec): 8.04 - samples/sec: 1696.81 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 16:36:29,963 epoch 10 - iter 45/95 - loss 0.02032623 - time (sec): 9.89 - samples/sec: 1715.48 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 16:36:31,080 epoch 10 - iter 54/95 - loss 0.02405996 - time (sec): 11.01 - samples/sec: 1780.21 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 16:36:32,694 epoch 10 - iter 63/95 - loss 0.02883736 - time (sec): 12.62 - samples/sec: 1803.44 - lr: 0.000002 - momentum: 0.000000 | |
| 2024-03-26 16:36:34,495 epoch 10 - iter 72/95 - loss 0.02729134 - time (sec): 14.42 - samples/sec: 1794.00 - lr: 0.000002 - momentum: 0.000000 | |
| 2024-03-26 16:36:36,161 epoch 10 - iter 81/95 - loss 0.02833043 - time (sec): 16.09 - samples/sec: 1805.05 - lr: 0.000001 - momentum: 0.000000 | |
| 2024-03-26 16:36:38,922 epoch 10 - iter 90/95 - loss 0.02634051 - time (sec): 18.85 - samples/sec: 1768.96 - lr: 0.000001 - momentum: 0.000000 | |
| 2024-03-26 16:36:39,478 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:36:39,478 EPOCH 10 done: loss 0.0266 - lr: 0.000001 | |
| 2024-03-26 16:36:40,374 DEV : loss 0.2326352298259735 - f1-score (micro avg) 0.9364 | |
| 2024-03-26 16:36:40,375 saving best model | |
| 2024-03-26 16:36:41,077 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 16:36:41,077 Loading model from best epoch ... | |
| 2024-03-26 16:36:41,933 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 16:36:42,672 | |
| Results: | |
| - F-score (micro) 0.9091 | |
| - F-score (macro) 0.6899 | |
| - Accuracy 0.8368 | |
| By class: | |
| precision recall f1-score support | |
| Unternehmen 0.9119 0.8947 0.9032 266 | |
| Auslagerung 0.8687 0.9036 0.8858 249 | |
| Ort 0.9565 0.9851 0.9706 134 | |
| Software 0.0000 0.0000 0.0000 0 | |
| micro avg 0.9015 0.9168 0.9091 649 | |
| macro avg 0.6843 0.6959 0.6899 649 | |
| weighted avg 0.9045 0.9168 0.9105 649 | |
| 2024-03-26 16:36:42,672 ---------------------------------------------------------------------------------------------------- | |