| 2023-10-11 23:01:47,070 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:01:47,072 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=13, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-11 23:01:47,072 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:01:47,072 MultiCorpus: 5777 train + 722 dev + 723 test sentences | |
| - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl | |
| 2023-10-11 23:01:47,072 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:01:47,072 Train: 5777 sentences | |
| 2023-10-11 23:01:47,073 (train_with_dev=False, train_with_test=False) | |
| 2023-10-11 23:01:47,073 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:01:47,073 Training Params: | |
| 2023-10-11 23:01:47,073 - learning_rate: "0.00016" | |
| 2023-10-11 23:01:47,073 - mini_batch_size: "4" | |
| 2023-10-11 23:01:47,073 - max_epochs: "10" | |
| 2023-10-11 23:01:47,073 - shuffle: "True" | |
| 2023-10-11 23:01:47,073 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:01:47,073 Plugins: | |
| 2023-10-11 23:01:47,073 - TensorboardLogger | |
| 2023-10-11 23:01:47,073 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-11 23:01:47,073 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:01:47,073 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-11 23:01:47,073 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-11 23:01:47,073 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:01:47,073 Computation: | |
| 2023-10-11 23:01:47,074 - compute on device: cuda:0 | |
| 2023-10-11 23:01:47,074 - embedding storage: none | |
| 2023-10-11 23:01:47,074 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:01:47,074 Model training base path: "hmbench-icdar/nl-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-11 23:01:47,074 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:01:47,074 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:01:47,074 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-11 23:02:29,577 epoch 1 - iter 144/1445 - loss 2.56504692 - time (sec): 42.50 - samples/sec: 437.44 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-11 23:03:12,798 epoch 1 - iter 288/1445 - loss 2.44150093 - time (sec): 85.72 - samples/sec: 416.17 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-11 23:03:56,536 epoch 1 - iter 432/1445 - loss 2.16436375 - time (sec): 129.46 - samples/sec: 416.45 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-11 23:04:38,360 epoch 1 - iter 576/1445 - loss 1.86790557 - time (sec): 171.28 - samples/sec: 416.44 - lr: 0.000064 - momentum: 0.000000 | |
| 2023-10-11 23:05:20,176 epoch 1 - iter 720/1445 - loss 1.58401234 - time (sec): 213.10 - samples/sec: 418.18 - lr: 0.000080 - momentum: 0.000000 | |
| 2023-10-11 23:06:04,468 epoch 1 - iter 864/1445 - loss 1.36702605 - time (sec): 257.39 - samples/sec: 414.93 - lr: 0.000096 - momentum: 0.000000 | |
| 2023-10-11 23:06:47,420 epoch 1 - iter 1008/1445 - loss 1.20723711 - time (sec): 300.34 - samples/sec: 415.07 - lr: 0.000112 - momentum: 0.000000 | |
| 2023-10-11 23:07:28,055 epoch 1 - iter 1152/1445 - loss 1.08380572 - time (sec): 340.98 - samples/sec: 415.54 - lr: 0.000127 - momentum: 0.000000 | |
| 2023-10-11 23:08:10,527 epoch 1 - iter 1296/1445 - loss 0.98304740 - time (sec): 383.45 - samples/sec: 415.51 - lr: 0.000143 - momentum: 0.000000 | |
| 2023-10-11 23:08:51,785 epoch 1 - iter 1440/1445 - loss 0.90575201 - time (sec): 424.71 - samples/sec: 413.89 - lr: 0.000159 - momentum: 0.000000 | |
| 2023-10-11 23:08:53,040 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:08:53,041 EPOCH 1 done: loss 0.9041 - lr: 0.000159 | |
| 2023-10-11 23:09:12,824 DEV : loss 0.19637209177017212 - f1-score (micro avg) 0.337 | |
| 2023-10-11 23:09:12,864 saving best model | |
| 2023-10-11 23:09:13,889 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:09:55,884 epoch 2 - iter 144/1445 - loss 0.14820675 - time (sec): 41.99 - samples/sec: 405.54 - lr: 0.000158 - momentum: 0.000000 | |
| 2023-10-11 23:10:39,422 epoch 2 - iter 288/1445 - loss 0.14776595 - time (sec): 85.53 - samples/sec: 405.66 - lr: 0.000156 - momentum: 0.000000 | |
| 2023-10-11 23:11:20,957 epoch 2 - iter 432/1445 - loss 0.14142232 - time (sec): 127.07 - samples/sec: 417.19 - lr: 0.000155 - momentum: 0.000000 | |
| 2023-10-11 23:12:04,561 epoch 2 - iter 576/1445 - loss 0.14046314 - time (sec): 170.67 - samples/sec: 416.71 - lr: 0.000153 - momentum: 0.000000 | |
| 2023-10-11 23:12:47,276 epoch 2 - iter 720/1445 - loss 0.13346839 - time (sec): 213.39 - samples/sec: 415.77 - lr: 0.000151 - momentum: 0.000000 | |
| 2023-10-11 23:13:29,863 epoch 2 - iter 864/1445 - loss 0.12999825 - time (sec): 255.97 - samples/sec: 413.52 - lr: 0.000149 - momentum: 0.000000 | |
| 2023-10-11 23:14:11,807 epoch 2 - iter 1008/1445 - loss 0.12549631 - time (sec): 297.92 - samples/sec: 413.66 - lr: 0.000148 - momentum: 0.000000 | |
| 2023-10-11 23:14:55,284 epoch 2 - iter 1152/1445 - loss 0.12210863 - time (sec): 341.39 - samples/sec: 412.48 - lr: 0.000146 - momentum: 0.000000 | |
| 2023-10-11 23:15:44,328 epoch 2 - iter 1296/1445 - loss 0.11930857 - time (sec): 390.44 - samples/sec: 403.41 - lr: 0.000144 - momentum: 0.000000 | |
| 2023-10-11 23:16:29,752 epoch 2 - iter 1440/1445 - loss 0.11702306 - time (sec): 435.86 - samples/sec: 403.17 - lr: 0.000142 - momentum: 0.000000 | |
| 2023-10-11 23:16:31,116 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:16:31,117 EPOCH 2 done: loss 0.1170 - lr: 0.000142 | |
| 2023-10-11 23:16:52,882 DEV : loss 0.09597545862197876 - f1-score (micro avg) 0.7901 | |
| 2023-10-11 23:16:52,914 saving best model | |
| 2023-10-11 23:16:56,865 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:17:42,241 epoch 3 - iter 144/1445 - loss 0.08787870 - time (sec): 45.37 - samples/sec: 400.96 - lr: 0.000140 - momentum: 0.000000 | |
| 2023-10-11 23:18:24,660 epoch 3 - iter 288/1445 - loss 0.07849694 - time (sec): 87.79 - samples/sec: 402.17 - lr: 0.000139 - momentum: 0.000000 | |
| 2023-10-11 23:19:10,100 epoch 3 - iter 432/1445 - loss 0.07359975 - time (sec): 133.23 - samples/sec: 393.96 - lr: 0.000137 - momentum: 0.000000 | |
| 2023-10-11 23:19:54,534 epoch 3 - iter 576/1445 - loss 0.07148524 - time (sec): 177.66 - samples/sec: 390.16 - lr: 0.000135 - momentum: 0.000000 | |
| 2023-10-11 23:20:36,239 epoch 3 - iter 720/1445 - loss 0.06904176 - time (sec): 219.37 - samples/sec: 395.42 - lr: 0.000133 - momentum: 0.000000 | |
| 2023-10-11 23:21:20,175 epoch 3 - iter 864/1445 - loss 0.07225162 - time (sec): 263.30 - samples/sec: 401.89 - lr: 0.000132 - momentum: 0.000000 | |
| 2023-10-11 23:22:03,866 epoch 3 - iter 1008/1445 - loss 0.07242454 - time (sec): 306.99 - samples/sec: 400.44 - lr: 0.000130 - momentum: 0.000000 | |
| 2023-10-11 23:22:51,028 epoch 3 - iter 1152/1445 - loss 0.07061901 - time (sec): 354.16 - samples/sec: 395.86 - lr: 0.000128 - momentum: 0.000000 | |
| 2023-10-11 23:23:31,796 epoch 3 - iter 1296/1445 - loss 0.06930577 - time (sec): 394.92 - samples/sec: 397.98 - lr: 0.000126 - momentum: 0.000000 | |
| 2023-10-11 23:24:17,693 epoch 3 - iter 1440/1445 - loss 0.06817481 - time (sec): 440.82 - samples/sec: 398.56 - lr: 0.000125 - momentum: 0.000000 | |
| 2023-10-11 23:24:18,983 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:24:18,984 EPOCH 3 done: loss 0.0681 - lr: 0.000125 | |
| 2023-10-11 23:24:41,500 DEV : loss 0.07571297883987427 - f1-score (micro avg) 0.8424 | |
| 2023-10-11 23:24:41,540 saving best model | |
| 2023-10-11 23:24:44,350 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:25:28,755 epoch 4 - iter 144/1445 - loss 0.05317648 - time (sec): 44.40 - samples/sec: 394.61 - lr: 0.000123 - momentum: 0.000000 | |
| 2023-10-11 23:26:14,399 epoch 4 - iter 288/1445 - loss 0.04776722 - time (sec): 90.05 - samples/sec: 394.64 - lr: 0.000121 - momentum: 0.000000 | |
| 2023-10-11 23:26:59,460 epoch 4 - iter 432/1445 - loss 0.04761497 - time (sec): 135.11 - samples/sec: 390.73 - lr: 0.000119 - momentum: 0.000000 | |
| 2023-10-11 23:27:43,444 epoch 4 - iter 576/1445 - loss 0.04723012 - time (sec): 179.09 - samples/sec: 392.28 - lr: 0.000117 - momentum: 0.000000 | |
| 2023-10-11 23:28:25,872 epoch 4 - iter 720/1445 - loss 0.05074390 - time (sec): 221.52 - samples/sec: 390.64 - lr: 0.000116 - momentum: 0.000000 | |
| 2023-10-11 23:29:09,101 epoch 4 - iter 864/1445 - loss 0.04975381 - time (sec): 264.75 - samples/sec: 395.49 - lr: 0.000114 - momentum: 0.000000 | |
| 2023-10-11 23:29:52,115 epoch 4 - iter 1008/1445 - loss 0.04920143 - time (sec): 307.76 - samples/sec: 399.94 - lr: 0.000112 - momentum: 0.000000 | |
| 2023-10-11 23:30:39,362 epoch 4 - iter 1152/1445 - loss 0.04742537 - time (sec): 355.01 - samples/sec: 396.13 - lr: 0.000110 - momentum: 0.000000 | |
| 2023-10-11 23:31:28,500 epoch 4 - iter 1296/1445 - loss 0.04477836 - time (sec): 404.15 - samples/sec: 395.10 - lr: 0.000109 - momentum: 0.000000 | |
| 2023-10-11 23:32:10,884 epoch 4 - iter 1440/1445 - loss 0.04528448 - time (sec): 446.53 - samples/sec: 393.84 - lr: 0.000107 - momentum: 0.000000 | |
| 2023-10-11 23:32:12,067 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:32:12,068 EPOCH 4 done: loss 0.0452 - lr: 0.000107 | |
| 2023-10-11 23:32:32,644 DEV : loss 0.07717934250831604 - f1-score (micro avg) 0.8654 | |
| 2023-10-11 23:32:32,675 saving best model | |
| 2023-10-11 23:32:35,406 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:33:19,520 epoch 5 - iter 144/1445 - loss 0.03679728 - time (sec): 44.11 - samples/sec: 400.38 - lr: 0.000105 - momentum: 0.000000 | |
| 2023-10-11 23:34:05,960 epoch 5 - iter 288/1445 - loss 0.03243108 - time (sec): 90.55 - samples/sec: 389.52 - lr: 0.000103 - momentum: 0.000000 | |
| 2023-10-11 23:34:49,836 epoch 5 - iter 432/1445 - loss 0.03251890 - time (sec): 134.43 - samples/sec: 397.93 - lr: 0.000101 - momentum: 0.000000 | |
| 2023-10-11 23:35:33,322 epoch 5 - iter 576/1445 - loss 0.03153095 - time (sec): 177.91 - samples/sec: 397.85 - lr: 0.000100 - momentum: 0.000000 | |
| 2023-10-11 23:36:19,573 epoch 5 - iter 720/1445 - loss 0.03166998 - time (sec): 224.16 - samples/sec: 399.23 - lr: 0.000098 - momentum: 0.000000 | |
| 2023-10-11 23:37:04,869 epoch 5 - iter 864/1445 - loss 0.03099000 - time (sec): 269.46 - samples/sec: 392.76 - lr: 0.000096 - momentum: 0.000000 | |
| 2023-10-11 23:37:50,323 epoch 5 - iter 1008/1445 - loss 0.03399168 - time (sec): 314.91 - samples/sec: 392.74 - lr: 0.000094 - momentum: 0.000000 | |
| 2023-10-11 23:38:33,420 epoch 5 - iter 1152/1445 - loss 0.03356007 - time (sec): 358.01 - samples/sec: 393.99 - lr: 0.000093 - momentum: 0.000000 | |
| 2023-10-11 23:39:18,483 epoch 5 - iter 1296/1445 - loss 0.03705131 - time (sec): 403.07 - samples/sec: 393.32 - lr: 0.000091 - momentum: 0.000000 | |
| 2023-10-11 23:40:01,118 epoch 5 - iter 1440/1445 - loss 0.03691198 - time (sec): 445.71 - samples/sec: 393.96 - lr: 0.000089 - momentum: 0.000000 | |
| 2023-10-11 23:40:02,393 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:40:02,394 EPOCH 5 done: loss 0.0368 - lr: 0.000089 | |
| 2023-10-11 23:40:23,145 DEV : loss 0.10290254652500153 - f1-score (micro avg) 0.8485 | |
| 2023-10-11 23:40:23,176 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:41:06,055 epoch 6 - iter 144/1445 - loss 0.02233664 - time (sec): 42.88 - samples/sec: 433.91 - lr: 0.000087 - momentum: 0.000000 | |
| 2023-10-11 23:41:49,040 epoch 6 - iter 288/1445 - loss 0.01799245 - time (sec): 85.86 - samples/sec: 429.14 - lr: 0.000085 - momentum: 0.000000 | |
| 2023-10-11 23:42:30,919 epoch 6 - iter 432/1445 - loss 0.02283230 - time (sec): 127.74 - samples/sec: 415.18 - lr: 0.000084 - momentum: 0.000000 | |
| 2023-10-11 23:43:15,917 epoch 6 - iter 576/1445 - loss 0.02348982 - time (sec): 172.74 - samples/sec: 408.45 - lr: 0.000082 - momentum: 0.000000 | |
| 2023-10-11 23:44:02,655 epoch 6 - iter 720/1445 - loss 0.02282929 - time (sec): 219.48 - samples/sec: 395.58 - lr: 0.000080 - momentum: 0.000000 | |
| 2023-10-11 23:44:45,177 epoch 6 - iter 864/1445 - loss 0.02242678 - time (sec): 262.00 - samples/sec: 400.20 - lr: 0.000078 - momentum: 0.000000 | |
| 2023-10-11 23:45:28,671 epoch 6 - iter 1008/1445 - loss 0.02528479 - time (sec): 305.49 - samples/sec: 404.33 - lr: 0.000076 - momentum: 0.000000 | |
| 2023-10-11 23:46:11,961 epoch 6 - iter 1152/1445 - loss 0.02440097 - time (sec): 348.78 - samples/sec: 405.32 - lr: 0.000075 - momentum: 0.000000 | |
| 2023-10-11 23:46:55,331 epoch 6 - iter 1296/1445 - loss 0.02461694 - time (sec): 392.15 - samples/sec: 402.25 - lr: 0.000073 - momentum: 0.000000 | |
| 2023-10-11 23:47:40,310 epoch 6 - iter 1440/1445 - loss 0.02524712 - time (sec): 437.13 - samples/sec: 401.24 - lr: 0.000071 - momentum: 0.000000 | |
| 2023-10-11 23:47:42,045 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:47:42,045 EPOCH 6 done: loss 0.0253 - lr: 0.000071 | |
| 2023-10-11 23:48:04,506 DEV : loss 0.11330018192529678 - f1-score (micro avg) 0.8482 | |
| 2023-10-11 23:48:04,540 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:48:52,986 epoch 7 - iter 144/1445 - loss 0.01961613 - time (sec): 48.44 - samples/sec: 366.64 - lr: 0.000069 - momentum: 0.000000 | |
| 2023-10-11 23:49:39,670 epoch 7 - iter 288/1445 - loss 0.01737598 - time (sec): 95.13 - samples/sec: 359.72 - lr: 0.000068 - momentum: 0.000000 | |
| 2023-10-11 23:50:21,081 epoch 7 - iter 432/1445 - loss 0.01519697 - time (sec): 136.54 - samples/sec: 369.81 - lr: 0.000066 - momentum: 0.000000 | |
| 2023-10-11 23:51:06,573 epoch 7 - iter 576/1445 - loss 0.01797181 - time (sec): 182.03 - samples/sec: 383.46 - lr: 0.000064 - momentum: 0.000000 | |
| 2023-10-11 23:51:55,719 epoch 7 - iter 720/1445 - loss 0.02192375 - time (sec): 231.18 - samples/sec: 379.57 - lr: 0.000062 - momentum: 0.000000 | |
| 2023-10-11 23:52:42,777 epoch 7 - iter 864/1445 - loss 0.02114113 - time (sec): 278.23 - samples/sec: 380.61 - lr: 0.000060 - momentum: 0.000000 | |
| 2023-10-11 23:53:29,128 epoch 7 - iter 1008/1445 - loss 0.01941452 - time (sec): 324.58 - samples/sec: 378.01 - lr: 0.000059 - momentum: 0.000000 | |
| 2023-10-11 23:54:14,079 epoch 7 - iter 1152/1445 - loss 0.01868922 - time (sec): 369.54 - samples/sec: 380.56 - lr: 0.000057 - momentum: 0.000000 | |
| 2023-10-11 23:54:59,710 epoch 7 - iter 1296/1445 - loss 0.01897559 - time (sec): 415.17 - samples/sec: 381.19 - lr: 0.000055 - momentum: 0.000000 | |
| 2023-10-11 23:55:42,976 epoch 7 - iter 1440/1445 - loss 0.01837138 - time (sec): 458.43 - samples/sec: 382.79 - lr: 0.000053 - momentum: 0.000000 | |
| 2023-10-11 23:55:44,456 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:55:44,456 EPOCH 7 done: loss 0.0183 - lr: 0.000053 | |
| 2023-10-11 23:56:05,378 DEV : loss 0.1252562254667282 - f1-score (micro avg) 0.8553 | |
| 2023-10-11 23:56:05,414 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-11 23:56:52,075 epoch 8 - iter 144/1445 - loss 0.00746075 - time (sec): 46.66 - samples/sec: 384.79 - lr: 0.000052 - momentum: 0.000000 | |
| 2023-10-11 23:57:33,156 epoch 8 - iter 288/1445 - loss 0.01120551 - time (sec): 87.74 - samples/sec: 389.64 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-11 23:58:14,451 epoch 8 - iter 432/1445 - loss 0.01190775 - time (sec): 129.03 - samples/sec: 393.45 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-11 23:58:56,599 epoch 8 - iter 576/1445 - loss 0.01075084 - time (sec): 171.18 - samples/sec: 396.20 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-11 23:59:40,000 epoch 8 - iter 720/1445 - loss 0.01066676 - time (sec): 214.58 - samples/sec: 398.15 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-12 00:00:24,020 epoch 8 - iter 864/1445 - loss 0.01162819 - time (sec): 258.60 - samples/sec: 401.54 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-12 00:01:08,431 epoch 8 - iter 1008/1445 - loss 0.01257430 - time (sec): 303.01 - samples/sec: 404.82 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-12 00:01:51,744 epoch 8 - iter 1152/1445 - loss 0.01300952 - time (sec): 346.33 - samples/sec: 403.84 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-12 00:02:35,889 epoch 8 - iter 1296/1445 - loss 0.01290861 - time (sec): 390.47 - samples/sec: 405.12 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-12 00:03:22,108 epoch 8 - iter 1440/1445 - loss 0.01355414 - time (sec): 436.69 - samples/sec: 402.32 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-12 00:03:23,511 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-12 00:03:23,511 EPOCH 8 done: loss 0.0135 - lr: 0.000036 | |
| 2023-10-12 00:03:47,026 DEV : loss 0.15301184356212616 - f1-score (micro avg) 0.8507 | |
| 2023-10-12 00:03:47,058 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-12 00:04:31,022 epoch 9 - iter 144/1445 - loss 0.01407469 - time (sec): 43.96 - samples/sec: 390.32 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-12 00:05:14,446 epoch 9 - iter 288/1445 - loss 0.01237596 - time (sec): 87.39 - samples/sec: 389.46 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-12 00:05:56,362 epoch 9 - iter 432/1445 - loss 0.01114705 - time (sec): 129.30 - samples/sec: 395.67 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-12 00:06:39,472 epoch 9 - iter 576/1445 - loss 0.01148971 - time (sec): 172.41 - samples/sec: 404.79 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-12 00:07:23,878 epoch 9 - iter 720/1445 - loss 0.01198347 - time (sec): 216.82 - samples/sec: 408.58 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-12 00:08:07,659 epoch 9 - iter 864/1445 - loss 0.01175221 - time (sec): 260.60 - samples/sec: 407.94 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-12 00:08:51,892 epoch 9 - iter 1008/1445 - loss 0.01179629 - time (sec): 304.83 - samples/sec: 407.14 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-12 00:09:41,030 epoch 9 - iter 1152/1445 - loss 0.01124818 - time (sec): 353.97 - samples/sec: 400.00 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-12 00:10:25,562 epoch 9 - iter 1296/1445 - loss 0.01114700 - time (sec): 398.50 - samples/sec: 397.74 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-12 00:11:09,740 epoch 9 - iter 1440/1445 - loss 0.01070460 - time (sec): 442.68 - samples/sec: 396.70 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-12 00:11:11,213 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-12 00:11:11,214 EPOCH 9 done: loss 0.0107 - lr: 0.000018 | |
| 2023-10-12 00:11:32,499 DEV : loss 0.14755892753601074 - f1-score (micro avg) 0.8556 | |
| 2023-10-12 00:11:32,530 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-12 00:12:16,419 epoch 10 - iter 144/1445 - loss 0.00621849 - time (sec): 43.89 - samples/sec: 410.35 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-12 00:13:00,915 epoch 10 - iter 288/1445 - loss 0.00813280 - time (sec): 88.38 - samples/sec: 410.23 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-12 00:13:46,203 epoch 10 - iter 432/1445 - loss 0.00928314 - time (sec): 133.67 - samples/sec: 414.42 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-12 00:14:30,616 epoch 10 - iter 576/1445 - loss 0.00802405 - time (sec): 178.08 - samples/sec: 409.80 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-12 00:15:14,826 epoch 10 - iter 720/1445 - loss 0.00735469 - time (sec): 222.29 - samples/sec: 409.84 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-12 00:15:58,215 epoch 10 - iter 864/1445 - loss 0.00740270 - time (sec): 265.68 - samples/sec: 404.22 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-12 00:16:46,891 epoch 10 - iter 1008/1445 - loss 0.00785369 - time (sec): 314.36 - samples/sec: 395.84 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-12 00:17:31,973 epoch 10 - iter 1152/1445 - loss 0.00750830 - time (sec): 359.44 - samples/sec: 394.28 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-12 00:18:16,241 epoch 10 - iter 1296/1445 - loss 0.00743922 - time (sec): 403.71 - samples/sec: 393.59 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-12 00:19:00,020 epoch 10 - iter 1440/1445 - loss 0.00777974 - time (sec): 447.49 - samples/sec: 392.69 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-12 00:19:01,330 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-12 00:19:01,331 EPOCH 10 done: loss 0.0078 - lr: 0.000000 | |
| 2023-10-12 00:19:23,771 DEV : loss 0.15156520903110504 - f1-score (micro avg) 0.8564 | |
| 2023-10-12 00:19:24,773 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-12 00:19:24,775 Loading model from best epoch ... | |
| 2023-10-12 00:19:28,666 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG | |
| 2023-10-12 00:19:50,872 | |
| Results: | |
| - F-score (micro) 0.8487 | |
| - F-score (macro) 0.7431 | |
| - Accuracy 0.7507 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.8300 0.8714 0.8502 482 | |
| LOC 0.8894 0.8952 0.8923 458 | |
| ORG 0.6087 0.4058 0.4870 69 | |
| micro avg 0.8470 0.8503 0.8487 1009 | |
| macro avg 0.7760 0.7241 0.7431 1009 | |
| weighted avg 0.8418 0.8503 0.8445 1009 | |
| 2023-10-12 00:19:50,872 ---------------------------------------------------------------------------------------------------- | |