| 2023-10-11 08:46:31,837 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:46:31,840 Model: "SequenceTagger( | |
| (embeddings): ByT5Embeddings( | |
| (model): T5EncoderModel( | |
| (shared): Embedding(384, 1472) | |
| (encoder): T5Stack( | |
| (embed_tokens): Embedding(384, 1472) | |
| (block): ModuleList( | |
| (0): T5Block( | |
| (layer): ModuleList( | |
| (0): T5LayerSelfAttention( | |
| (SelfAttention): T5Attention( | |
| (q): Linear(in_features=1472, out_features=384, bias=False) | |
| (k): Linear(in_features=1472, out_features=384, bias=False) | |
| (v): Linear(in_features=1472, out_features=384, bias=False) | |
| (o): Linear(in_features=384, out_features=1472, bias=False) | |
| (relative_attention_bias): Embedding(32, 6) | |
| ) | |
| (layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (1): T5LayerFF( | |
| (DenseReluDense): T5DenseGatedActDense( | |
| (wi_0): Linear(in_features=1472, out_features=3584, bias=False) | |
| (wi_1): Linear(in_features=1472, out_features=3584, bias=False) | |
| (wo): Linear(in_features=3584, out_features=1472, bias=False) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| (act): NewGELUActivation() | |
| ) | |
| (layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| (1-11): 11 x T5Block( | |
| (layer): ModuleList( | |
| (0): T5LayerSelfAttention( | |
| (SelfAttention): T5Attention( | |
| (q): Linear(in_features=1472, out_features=384, bias=False) | |
| (k): Linear(in_features=1472, out_features=384, bias=False) | |
| (v): Linear(in_features=1472, out_features=384, bias=False) | |
| (o): Linear(in_features=384, out_features=1472, bias=False) | |
| ) | |
| (layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (1): T5LayerFF( | |
| (DenseReluDense): T5DenseGatedActDense( | |
| (wi_0): Linear(in_features=1472, out_features=3584, bias=False) | |
| (wi_1): Linear(in_features=1472, out_features=3584, bias=False) | |
| (wo): Linear(in_features=3584, out_features=1472, bias=False) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| (act): NewGELUActivation() | |
| ) | |
| (layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (final_layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=1472, out_features=17, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-11 08:46:31,840 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:46:31,840 MultiCorpus: 1085 train + 148 dev + 364 test sentences | |
| - NER_HIPE_2022 Corpus: 1085 train + 148 dev + 364 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/sv/with_doc_seperator | |
| 2023-10-11 08:46:31,840 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:46:31,840 Train: 1085 sentences | |
| 2023-10-11 08:46:31,840 (train_with_dev=False, train_with_test=False) | |
| 2023-10-11 08:46:31,840 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:46:31,840 Training Params: | |
| 2023-10-11 08:46:31,840 - learning_rate: "0.00016" | |
| 2023-10-11 08:46:31,841 - mini_batch_size: "4" | |
| 2023-10-11 08:46:31,841 - max_epochs: "10" | |
| 2023-10-11 08:46:31,841 - shuffle: "True" | |
| 2023-10-11 08:46:31,841 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:46:31,841 Plugins: | |
| 2023-10-11 08:46:31,841 - TensorboardLogger | |
| 2023-10-11 08:46:31,841 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-11 08:46:31,841 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:46:31,841 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-11 08:46:31,841 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-11 08:46:31,841 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:46:31,841 Computation: | |
| 2023-10-11 08:46:31,841 - compute on device: cuda:0 | |
| 2023-10-11 08:46:31,841 - embedding storage: none | |
| 2023-10-11 08:46:31,841 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:46:31,842 Model training base path: "hmbench-newseye/sv-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-11 08:46:31,842 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:46:31,842 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:46:31,842 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-11 08:46:41,628 epoch 1 - iter 27/272 - loss 2.82503855 - time (sec): 9.78 - samples/sec: 533.20 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-11 08:46:51,677 epoch 1 - iter 54/272 - loss 2.81479736 - time (sec): 19.83 - samples/sec: 549.38 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-11 08:47:01,623 epoch 1 - iter 81/272 - loss 2.79445131 - time (sec): 29.78 - samples/sec: 542.15 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-11 08:47:11,987 epoch 1 - iter 108/272 - loss 2.74143790 - time (sec): 40.14 - samples/sec: 545.49 - lr: 0.000063 - momentum: 0.000000 | |
| 2023-10-11 08:47:21,335 epoch 1 - iter 135/272 - loss 2.67294473 - time (sec): 49.49 - samples/sec: 526.82 - lr: 0.000079 - momentum: 0.000000 | |
| 2023-10-11 08:47:32,016 epoch 1 - iter 162/272 - loss 2.56753769 - time (sec): 60.17 - samples/sec: 523.44 - lr: 0.000095 - momentum: 0.000000 | |
| 2023-10-11 08:47:42,898 epoch 1 - iter 189/272 - loss 2.45166255 - time (sec): 71.05 - samples/sec: 519.49 - lr: 0.000111 - momentum: 0.000000 | |
| 2023-10-11 08:47:53,558 epoch 1 - iter 216/272 - loss 2.33252461 - time (sec): 81.71 - samples/sec: 517.21 - lr: 0.000126 - momentum: 0.000000 | |
| 2023-10-11 08:48:03,842 epoch 1 - iter 243/272 - loss 2.21679175 - time (sec): 92.00 - samples/sec: 514.16 - lr: 0.000142 - momentum: 0.000000 | |
| 2023-10-11 08:48:13,393 epoch 1 - iter 270/272 - loss 2.10793293 - time (sec): 101.55 - samples/sec: 509.85 - lr: 0.000158 - momentum: 0.000000 | |
| 2023-10-11 08:48:13,897 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:48:13,897 EPOCH 1 done: loss 2.1029 - lr: 0.000158 | |
| 2023-10-11 08:48:19,678 DEV : loss 0.7420206069946289 - f1-score (micro avg) 0.0 | |
| 2023-10-11 08:48:19,686 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:48:29,235 epoch 2 - iter 27/272 - loss 0.73201408 - time (sec): 9.55 - samples/sec: 508.44 - lr: 0.000158 - momentum: 0.000000 | |
| 2023-10-11 08:48:39,028 epoch 2 - iter 54/272 - loss 0.64365181 - time (sec): 19.34 - samples/sec: 518.40 - lr: 0.000157 - momentum: 0.000000 | |
| 2023-10-11 08:48:48,747 epoch 2 - iter 81/272 - loss 0.62581360 - time (sec): 29.06 - samples/sec: 532.06 - lr: 0.000155 - momentum: 0.000000 | |
| 2023-10-11 08:48:58,318 epoch 2 - iter 108/272 - loss 0.57402681 - time (sec): 38.63 - samples/sec: 534.90 - lr: 0.000153 - momentum: 0.000000 | |
| 2023-10-11 08:49:08,050 epoch 2 - iter 135/272 - loss 0.55461793 - time (sec): 48.36 - samples/sec: 519.02 - lr: 0.000151 - momentum: 0.000000 | |
| 2023-10-11 08:49:18,508 epoch 2 - iter 162/272 - loss 0.54159163 - time (sec): 58.82 - samples/sec: 527.05 - lr: 0.000149 - momentum: 0.000000 | |
| 2023-10-11 08:49:28,016 epoch 2 - iter 189/272 - loss 0.52812425 - time (sec): 68.33 - samples/sec: 527.76 - lr: 0.000148 - momentum: 0.000000 | |
| 2023-10-11 08:49:38,503 epoch 2 - iter 216/272 - loss 0.48929605 - time (sec): 78.82 - samples/sec: 535.29 - lr: 0.000146 - momentum: 0.000000 | |
| 2023-10-11 08:49:48,000 epoch 2 - iter 243/272 - loss 0.46843836 - time (sec): 88.31 - samples/sec: 534.95 - lr: 0.000144 - momentum: 0.000000 | |
| 2023-10-11 08:49:56,928 epoch 2 - iter 270/272 - loss 0.45538103 - time (sec): 97.24 - samples/sec: 531.77 - lr: 0.000142 - momentum: 0.000000 | |
| 2023-10-11 08:49:57,467 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:49:57,467 EPOCH 2 done: loss 0.4541 - lr: 0.000142 | |
| 2023-10-11 08:50:03,637 DEV : loss 0.2795553505420685 - f1-score (micro avg) 0.2799 | |
| 2023-10-11 08:50:03,645 saving best model | |
| 2023-10-11 08:50:04,536 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:50:13,001 epoch 3 - iter 27/272 - loss 0.30926344 - time (sec): 8.46 - samples/sec: 471.49 - lr: 0.000141 - momentum: 0.000000 | |
| 2023-10-11 08:50:22,688 epoch 3 - iter 54/272 - loss 0.28010891 - time (sec): 18.15 - samples/sec: 508.98 - lr: 0.000139 - momentum: 0.000000 | |
| 2023-10-11 08:50:32,156 epoch 3 - iter 81/272 - loss 0.26941339 - time (sec): 27.62 - samples/sec: 520.25 - lr: 0.000137 - momentum: 0.000000 | |
| 2023-10-11 08:50:42,087 epoch 3 - iter 108/272 - loss 0.26957336 - time (sec): 37.55 - samples/sec: 519.09 - lr: 0.000135 - momentum: 0.000000 | |
| 2023-10-11 08:50:52,114 epoch 3 - iter 135/272 - loss 0.27237190 - time (sec): 47.58 - samples/sec: 528.62 - lr: 0.000133 - momentum: 0.000000 | |
| 2023-10-11 08:51:02,110 epoch 3 - iter 162/272 - loss 0.26668477 - time (sec): 57.57 - samples/sec: 536.22 - lr: 0.000132 - momentum: 0.000000 | |
| 2023-10-11 08:51:11,906 epoch 3 - iter 189/272 - loss 0.26973989 - time (sec): 67.37 - samples/sec: 538.76 - lr: 0.000130 - momentum: 0.000000 | |
| 2023-10-11 08:51:21,268 epoch 3 - iter 216/272 - loss 0.26714766 - time (sec): 76.73 - samples/sec: 533.69 - lr: 0.000128 - momentum: 0.000000 | |
| 2023-10-11 08:51:31,787 epoch 3 - iter 243/272 - loss 0.25771325 - time (sec): 87.25 - samples/sec: 539.86 - lr: 0.000126 - momentum: 0.000000 | |
| 2023-10-11 08:51:41,141 epoch 3 - iter 270/272 - loss 0.25337985 - time (sec): 96.60 - samples/sec: 535.67 - lr: 0.000125 - momentum: 0.000000 | |
| 2023-10-11 08:51:41,589 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:51:41,589 EPOCH 3 done: loss 0.2536 - lr: 0.000125 | |
| 2023-10-11 08:51:48,529 DEV : loss 0.18771013617515564 - f1-score (micro avg) 0.5978 | |
| 2023-10-11 08:51:48,538 saving best model | |
| 2023-10-11 08:51:51,138 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:52:00,134 epoch 4 - iter 27/272 - loss 0.20637994 - time (sec): 8.99 - samples/sec: 526.18 - lr: 0.000123 - momentum: 0.000000 | |
| 2023-10-11 08:52:10,291 epoch 4 - iter 54/272 - loss 0.18402262 - time (sec): 19.15 - samples/sec: 551.44 - lr: 0.000121 - momentum: 0.000000 | |
| 2023-10-11 08:52:19,753 epoch 4 - iter 81/272 - loss 0.17988604 - time (sec): 28.61 - samples/sec: 543.96 - lr: 0.000119 - momentum: 0.000000 | |
| 2023-10-11 08:52:29,681 epoch 4 - iter 108/272 - loss 0.17262483 - time (sec): 38.54 - samples/sec: 551.29 - lr: 0.000117 - momentum: 0.000000 | |
| 2023-10-11 08:52:39,149 epoch 4 - iter 135/272 - loss 0.16177249 - time (sec): 48.01 - samples/sec: 552.24 - lr: 0.000116 - momentum: 0.000000 | |
| 2023-10-11 08:52:48,606 epoch 4 - iter 162/272 - loss 0.15861681 - time (sec): 57.46 - samples/sec: 546.29 - lr: 0.000114 - momentum: 0.000000 | |
| 2023-10-11 08:52:59,370 epoch 4 - iter 189/272 - loss 0.15138177 - time (sec): 68.23 - samples/sec: 550.75 - lr: 0.000112 - momentum: 0.000000 | |
| 2023-10-11 08:53:09,261 epoch 4 - iter 216/272 - loss 0.15344235 - time (sec): 78.12 - samples/sec: 547.59 - lr: 0.000110 - momentum: 0.000000 | |
| 2023-10-11 08:53:18,585 epoch 4 - iter 243/272 - loss 0.15540389 - time (sec): 87.44 - samples/sec: 543.27 - lr: 0.000109 - momentum: 0.000000 | |
| 2023-10-11 08:53:27,569 epoch 4 - iter 270/272 - loss 0.15515638 - time (sec): 96.43 - samples/sec: 537.32 - lr: 0.000107 - momentum: 0.000000 | |
| 2023-10-11 08:53:27,987 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:53:27,988 EPOCH 4 done: loss 0.1550 - lr: 0.000107 | |
| 2023-10-11 08:53:33,816 DEV : loss 0.14752107858657837 - f1-score (micro avg) 0.658 | |
| 2023-10-11 08:53:33,826 saving best model | |
| 2023-10-11 08:53:36,632 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:53:46,312 epoch 5 - iter 27/272 - loss 0.11436262 - time (sec): 9.68 - samples/sec: 572.18 - lr: 0.000105 - momentum: 0.000000 | |
| 2023-10-11 08:53:55,676 epoch 5 - iter 54/272 - loss 0.11963874 - time (sec): 19.04 - samples/sec: 549.11 - lr: 0.000103 - momentum: 0.000000 | |
| 2023-10-11 08:54:04,374 epoch 5 - iter 81/272 - loss 0.12040345 - time (sec): 27.74 - samples/sec: 535.16 - lr: 0.000101 - momentum: 0.000000 | |
| 2023-10-11 08:54:13,474 epoch 5 - iter 108/272 - loss 0.11406206 - time (sec): 36.84 - samples/sec: 540.48 - lr: 0.000100 - momentum: 0.000000 | |
| 2023-10-11 08:54:23,142 epoch 5 - iter 135/272 - loss 0.11208839 - time (sec): 46.51 - samples/sec: 547.59 - lr: 0.000098 - momentum: 0.000000 | |
| 2023-10-11 08:54:32,283 epoch 5 - iter 162/272 - loss 0.10997584 - time (sec): 55.65 - samples/sec: 546.65 - lr: 0.000096 - momentum: 0.000000 | |
| 2023-10-11 08:54:41,397 epoch 5 - iter 189/272 - loss 0.10698639 - time (sec): 64.76 - samples/sec: 547.20 - lr: 0.000094 - momentum: 0.000000 | |
| 2023-10-11 08:54:51,151 epoch 5 - iter 216/272 - loss 0.10437260 - time (sec): 74.51 - samples/sec: 553.36 - lr: 0.000093 - momentum: 0.000000 | |
| 2023-10-11 08:55:00,218 epoch 5 - iter 243/272 - loss 0.10669928 - time (sec): 83.58 - samples/sec: 550.74 - lr: 0.000091 - momentum: 0.000000 | |
| 2023-10-11 08:55:09,997 epoch 5 - iter 270/272 - loss 0.10536589 - time (sec): 93.36 - samples/sec: 554.39 - lr: 0.000089 - momentum: 0.000000 | |
| 2023-10-11 08:55:10,430 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:55:10,431 EPOCH 5 done: loss 0.1055 - lr: 0.000089 | |
| 2023-10-11 08:55:16,000 DEV : loss 0.13927499949932098 - f1-score (micro avg) 0.7678 | |
| 2023-10-11 08:55:16,010 saving best model | |
| 2023-10-11 08:55:18,606 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:55:28,182 epoch 6 - iter 27/272 - loss 0.07850917 - time (sec): 9.57 - samples/sec: 560.10 - lr: 0.000087 - momentum: 0.000000 | |
| 2023-10-11 08:55:37,244 epoch 6 - iter 54/272 - loss 0.09402615 - time (sec): 18.63 - samples/sec: 543.70 - lr: 0.000085 - momentum: 0.000000 | |
| 2023-10-11 08:55:46,928 epoch 6 - iter 81/272 - loss 0.08988016 - time (sec): 28.32 - samples/sec: 557.28 - lr: 0.000084 - momentum: 0.000000 | |
| 2023-10-11 08:55:55,750 epoch 6 - iter 108/272 - loss 0.08253274 - time (sec): 37.14 - samples/sec: 554.07 - lr: 0.000082 - momentum: 0.000000 | |
| 2023-10-11 08:56:04,527 epoch 6 - iter 135/272 - loss 0.08701424 - time (sec): 45.92 - samples/sec: 544.31 - lr: 0.000080 - momentum: 0.000000 | |
| 2023-10-11 08:56:13,801 epoch 6 - iter 162/272 - loss 0.08101780 - time (sec): 55.19 - samples/sec: 544.89 - lr: 0.000078 - momentum: 0.000000 | |
| 2023-10-11 08:56:22,641 epoch 6 - iter 189/272 - loss 0.08041658 - time (sec): 64.03 - samples/sec: 543.08 - lr: 0.000077 - momentum: 0.000000 | |
| 2023-10-11 08:56:32,377 epoch 6 - iter 216/272 - loss 0.07945405 - time (sec): 73.77 - samples/sec: 548.07 - lr: 0.000075 - momentum: 0.000000 | |
| 2023-10-11 08:56:42,277 epoch 6 - iter 243/272 - loss 0.07521173 - time (sec): 83.67 - samples/sec: 551.06 - lr: 0.000073 - momentum: 0.000000 | |
| 2023-10-11 08:56:52,338 epoch 6 - iter 270/272 - loss 0.07280428 - time (sec): 93.73 - samples/sec: 550.66 - lr: 0.000071 - momentum: 0.000000 | |
| 2023-10-11 08:56:52,948 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:56:52,948 EPOCH 6 done: loss 0.0731 - lr: 0.000071 | |
| 2023-10-11 08:56:58,860 DEV : loss 0.13484491407871246 - f1-score (micro avg) 0.764 | |
| 2023-10-11 08:56:58,868 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:57:07,260 epoch 7 - iter 27/272 - loss 0.06214019 - time (sec): 8.39 - samples/sec: 464.28 - lr: 0.000069 - momentum: 0.000000 | |
| 2023-10-11 08:57:18,473 epoch 7 - iter 54/272 - loss 0.06815280 - time (sec): 19.60 - samples/sec: 534.52 - lr: 0.000068 - momentum: 0.000000 | |
| 2023-10-11 08:57:28,778 epoch 7 - iter 81/272 - loss 0.06037909 - time (sec): 29.91 - samples/sec: 549.25 - lr: 0.000066 - momentum: 0.000000 | |
| 2023-10-11 08:57:38,310 epoch 7 - iter 108/272 - loss 0.05637524 - time (sec): 39.44 - samples/sec: 549.32 - lr: 0.000064 - momentum: 0.000000 | |
| 2023-10-11 08:57:47,655 epoch 7 - iter 135/272 - loss 0.05750252 - time (sec): 48.78 - samples/sec: 551.32 - lr: 0.000062 - momentum: 0.000000 | |
| 2023-10-11 08:57:56,698 epoch 7 - iter 162/272 - loss 0.05648056 - time (sec): 57.83 - samples/sec: 545.48 - lr: 0.000061 - momentum: 0.000000 | |
| 2023-10-11 08:58:05,934 epoch 7 - iter 189/272 - loss 0.05468204 - time (sec): 67.06 - samples/sec: 547.25 - lr: 0.000059 - momentum: 0.000000 | |
| 2023-10-11 08:58:14,303 epoch 7 - iter 216/272 - loss 0.05367683 - time (sec): 75.43 - samples/sec: 543.46 - lr: 0.000057 - momentum: 0.000000 | |
| 2023-10-11 08:58:23,658 epoch 7 - iter 243/272 - loss 0.05396445 - time (sec): 84.79 - samples/sec: 546.11 - lr: 0.000055 - momentum: 0.000000 | |
| 2023-10-11 08:58:33,141 epoch 7 - iter 270/272 - loss 0.05372052 - time (sec): 94.27 - samples/sec: 548.66 - lr: 0.000054 - momentum: 0.000000 | |
| 2023-10-11 08:58:33,608 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:58:33,609 EPOCH 7 done: loss 0.0539 - lr: 0.000054 | |
| 2023-10-11 08:58:39,587 DEV : loss 0.12847252190113068 - f1-score (micro avg) 0.7792 | |
| 2023-10-11 08:58:39,595 saving best model | |
| 2023-10-11 08:58:42,149 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 08:58:51,228 epoch 8 - iter 27/272 - loss 0.03724604 - time (sec): 9.08 - samples/sec: 555.03 - lr: 0.000052 - momentum: 0.000000 | |
| 2023-10-11 08:59:00,208 epoch 8 - iter 54/272 - loss 0.03582304 - time (sec): 18.05 - samples/sec: 552.54 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-11 08:59:10,094 epoch 8 - iter 81/272 - loss 0.04189696 - time (sec): 27.94 - samples/sec: 572.81 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-11 08:59:19,038 epoch 8 - iter 108/272 - loss 0.04015146 - time (sec): 36.89 - samples/sec: 566.49 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-11 08:59:28,385 epoch 8 - iter 135/272 - loss 0.03937496 - time (sec): 46.23 - samples/sec: 563.96 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-11 08:59:37,864 epoch 8 - iter 162/272 - loss 0.03916141 - time (sec): 55.71 - samples/sec: 562.64 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-11 08:59:47,098 epoch 8 - iter 189/272 - loss 0.03951737 - time (sec): 64.95 - samples/sec: 555.42 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-11 08:59:56,915 epoch 8 - iter 216/272 - loss 0.03924256 - time (sec): 74.76 - samples/sec: 556.91 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-11 09:00:05,974 epoch 8 - iter 243/272 - loss 0.04242295 - time (sec): 83.82 - samples/sec: 553.15 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-11 09:00:15,555 epoch 8 - iter 270/272 - loss 0.04091031 - time (sec): 93.40 - samples/sec: 552.96 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-11 09:00:16,105 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 09:00:16,105 EPOCH 8 done: loss 0.0411 - lr: 0.000036 | |
| 2023-10-11 09:00:21,622 DEV : loss 0.1297326683998108 - f1-score (micro avg) 0.8015 | |
| 2023-10-11 09:00:21,630 saving best model | |
| 2023-10-11 09:00:24,195 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 09:00:32,880 epoch 9 - iter 27/272 - loss 0.02851045 - time (sec): 8.68 - samples/sec: 521.81 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-11 09:00:42,791 epoch 9 - iter 54/272 - loss 0.02545259 - time (sec): 18.59 - samples/sec: 555.82 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-11 09:00:52,267 epoch 9 - iter 81/272 - loss 0.02552757 - time (sec): 28.07 - samples/sec: 552.90 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-11 09:01:01,675 epoch 9 - iter 108/272 - loss 0.03169139 - time (sec): 37.48 - samples/sec: 550.18 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-11 09:01:11,062 epoch 9 - iter 135/272 - loss 0.03179437 - time (sec): 46.86 - samples/sec: 551.07 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-11 09:01:20,938 epoch 9 - iter 162/272 - loss 0.03091858 - time (sec): 56.74 - samples/sec: 555.52 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-11 09:01:29,941 epoch 9 - iter 189/272 - loss 0.03017751 - time (sec): 65.74 - samples/sec: 549.36 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-11 09:01:39,359 epoch 9 - iter 216/272 - loss 0.03227109 - time (sec): 75.16 - samples/sec: 551.30 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-11 09:01:48,473 epoch 9 - iter 243/272 - loss 0.03433461 - time (sec): 84.27 - samples/sec: 546.30 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-11 09:01:58,254 epoch 9 - iter 270/272 - loss 0.03343733 - time (sec): 94.06 - samples/sec: 549.00 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-11 09:01:58,817 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 09:01:58,817 EPOCH 9 done: loss 0.0333 - lr: 0.000018 | |
| 2023-10-11 09:02:04,280 DEV : loss 0.13128715753555298 - f1-score (micro avg) 0.7935 | |
| 2023-10-11 09:02:04,288 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 09:02:13,398 epoch 10 - iter 27/272 - loss 0.02099314 - time (sec): 9.11 - samples/sec: 517.83 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-11 09:02:22,257 epoch 10 - iter 54/272 - loss 0.02110070 - time (sec): 17.97 - samples/sec: 499.26 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-11 09:02:31,661 epoch 10 - iter 81/272 - loss 0.02719329 - time (sec): 27.37 - samples/sec: 499.66 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-11 09:02:41,814 epoch 10 - iter 108/272 - loss 0.02618643 - time (sec): 37.52 - samples/sec: 509.20 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-11 09:02:52,674 epoch 10 - iter 135/272 - loss 0.02521797 - time (sec): 48.38 - samples/sec: 527.51 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-11 09:03:03,562 epoch 10 - iter 162/272 - loss 0.02773592 - time (sec): 59.27 - samples/sec: 541.00 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-11 09:03:13,363 epoch 10 - iter 189/272 - loss 0.02935487 - time (sec): 69.07 - samples/sec: 543.40 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-11 09:03:22,530 epoch 10 - iter 216/272 - loss 0.02897761 - time (sec): 78.24 - samples/sec: 535.14 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-11 09:03:31,795 epoch 10 - iter 243/272 - loss 0.02896544 - time (sec): 87.50 - samples/sec: 531.38 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-11 09:03:41,537 epoch 10 - iter 270/272 - loss 0.02830754 - time (sec): 97.25 - samples/sec: 532.62 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-11 09:03:41,982 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 09:03:41,982 EPOCH 10 done: loss 0.0284 - lr: 0.000000 | |
| 2023-10-11 09:03:47,926 DEV : loss 0.1347367763519287 - f1-score (micro avg) 0.7913 | |
| 2023-10-11 09:03:48,832 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 09:03:48,834 Loading model from best epoch ... | |
| 2023-10-11 09:03:52,957 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd, S-ORG, B-ORG, E-ORG, I-ORG | |
| 2023-10-11 09:04:05,405 | |
| Results: | |
| - F-score (micro) 0.7686 | |
| - F-score (macro) 0.7157 | |
| - Accuracy 0.6437 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.7624 0.8846 0.8190 312 | |
| PER 0.6980 0.8558 0.7689 208 | |
| ORG 0.4231 0.4000 0.4112 55 | |
| HumanProd 0.8636 0.8636 0.8636 22 | |
| micro avg 0.7164 0.8291 0.7686 597 | |
| macro avg 0.6868 0.7510 0.7157 597 | |
| weighted avg 0.7125 0.8291 0.7656 597 | |
| 2023-10-11 09:04:05,405 ---------------------------------------------------------------------------------------------------- | |