| 2023-10-17 14:55:09,495 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:55:09,496 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): ElectraModel( | |
| (embeddings): ElectraEmbeddings( | |
| (word_embeddings): Embedding(32001, 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): ElectraEncoder( | |
| (layer): ModuleList( | |
| (0-11): 12 x ElectraLayer( | |
| (attention): ElectraAttention( | |
| (self): ElectraSelfAttention( | |
| (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): ElectraSelfOutput( | |
| (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): ElectraIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): ElectraOutput( | |
| (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) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=13, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 14:55:09,496 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:55:09,496 MultiCorpus: 7936 train + 992 dev + 992 test sentences | |
| - NER_ICDAR_EUROPEANA Corpus: 7936 train + 992 dev + 992 test sentences - /root/.flair/datasets/ner_icdar_europeana/fr | |
| 2023-10-17 14:55:09,496 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:55:09,497 Train: 7936 sentences | |
| 2023-10-17 14:55:09,497 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 14:55:09,497 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:55:09,497 Training Params: | |
| 2023-10-17 14:55:09,497 - learning_rate: "3e-05" | |
| 2023-10-17 14:55:09,497 - mini_batch_size: "8" | |
| 2023-10-17 14:55:09,497 - max_epochs: "10" | |
| 2023-10-17 14:55:09,497 - shuffle: "True" | |
| 2023-10-17 14:55:09,497 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:55:09,497 Plugins: | |
| 2023-10-17 14:55:09,497 - TensorboardLogger | |
| 2023-10-17 14:55:09,497 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 14:55:09,497 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:55:09,497 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 14:55:09,497 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 14:55:09,497 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:55:09,497 Computation: | |
| 2023-10-17 14:55:09,497 - compute on device: cuda:0 | |
| 2023-10-17 14:55:09,497 - embedding storage: none | |
| 2023-10-17 14:55:09,497 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:55:09,497 Model training base path: "hmbench-icdar/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 14:55:09,497 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:55:09,497 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:55:09,497 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 14:55:15,336 epoch 1 - iter 99/992 - loss 2.77233788 - time (sec): 5.84 - samples/sec: 2762.70 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 14:55:21,438 epoch 1 - iter 198/992 - loss 1.67037158 - time (sec): 11.94 - samples/sec: 2810.79 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 14:55:27,193 epoch 1 - iter 297/992 - loss 1.22191274 - time (sec): 17.69 - samples/sec: 2784.25 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 14:55:32,952 epoch 1 - iter 396/992 - loss 0.97575122 - time (sec): 23.45 - samples/sec: 2781.30 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 14:55:38,693 epoch 1 - iter 495/992 - loss 0.83006039 - time (sec): 29.19 - samples/sec: 2760.78 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 14:55:44,467 epoch 1 - iter 594/992 - loss 0.71867904 - time (sec): 34.97 - samples/sec: 2772.54 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 14:55:50,622 epoch 1 - iter 693/992 - loss 0.63373292 - time (sec): 41.12 - samples/sec: 2769.32 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 14:55:56,539 epoch 1 - iter 792/992 - loss 0.57062966 - time (sec): 47.04 - samples/sec: 2774.49 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 14:56:02,349 epoch 1 - iter 891/992 - loss 0.52216394 - time (sec): 52.85 - samples/sec: 2781.94 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 14:56:08,420 epoch 1 - iter 990/992 - loss 0.48106559 - time (sec): 58.92 - samples/sec: 2777.41 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 14:56:08,530 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:56:08,530 EPOCH 1 done: loss 0.4802 - lr: 0.000030 | |
| 2023-10-17 14:56:11,906 DEV : loss 0.09239894896745682 - f1-score (micro avg) 0.69 | |
| 2023-10-17 14:56:11,928 saving best model | |
| 2023-10-17 14:56:12,272 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:56:18,363 epoch 2 - iter 99/992 - loss 0.11493867 - time (sec): 6.09 - samples/sec: 2798.64 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 14:56:24,274 epoch 2 - iter 198/992 - loss 0.10800470 - time (sec): 12.00 - samples/sec: 2785.06 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 14:56:29,911 epoch 2 - iter 297/992 - loss 0.10734803 - time (sec): 17.64 - samples/sec: 2820.64 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 14:56:35,592 epoch 2 - iter 396/992 - loss 0.10779127 - time (sec): 23.32 - samples/sec: 2799.07 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 14:56:41,915 epoch 2 - iter 495/992 - loss 0.10673539 - time (sec): 29.64 - samples/sec: 2769.34 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 14:56:47,905 epoch 2 - iter 594/992 - loss 0.10552213 - time (sec): 35.63 - samples/sec: 2749.29 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 14:56:53,856 epoch 2 - iter 693/992 - loss 0.10707402 - time (sec): 41.58 - samples/sec: 2740.93 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 14:56:59,581 epoch 2 - iter 792/992 - loss 0.10586383 - time (sec): 47.31 - samples/sec: 2751.71 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 14:57:05,744 epoch 2 - iter 891/992 - loss 0.10483571 - time (sec): 53.47 - samples/sec: 2753.62 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 14:57:11,629 epoch 2 - iter 990/992 - loss 0.10522458 - time (sec): 59.36 - samples/sec: 2757.89 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 14:57:11,744 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:57:11,744 EPOCH 2 done: loss 0.1052 - lr: 0.000027 | |
| 2023-10-17 14:57:15,729 DEV : loss 0.0876772329211235 - f1-score (micro avg) 0.7535 | |
| 2023-10-17 14:57:15,756 saving best model | |
| 2023-10-17 14:57:16,213 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:57:21,845 epoch 3 - iter 99/992 - loss 0.08022628 - time (sec): 5.63 - samples/sec: 2701.59 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 14:57:27,757 epoch 3 - iter 198/992 - loss 0.08031838 - time (sec): 11.54 - samples/sec: 2729.77 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 14:57:33,831 epoch 3 - iter 297/992 - loss 0.07836688 - time (sec): 17.61 - samples/sec: 2746.30 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 14:57:39,836 epoch 3 - iter 396/992 - loss 0.07442244 - time (sec): 23.62 - samples/sec: 2759.52 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 14:57:45,675 epoch 3 - iter 495/992 - loss 0.07411089 - time (sec): 29.46 - samples/sec: 2768.82 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 14:57:51,690 epoch 3 - iter 594/992 - loss 0.07456331 - time (sec): 35.47 - samples/sec: 2780.49 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 14:57:57,446 epoch 3 - iter 693/992 - loss 0.07434798 - time (sec): 41.23 - samples/sec: 2774.61 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 14:58:03,168 epoch 3 - iter 792/992 - loss 0.07472551 - time (sec): 46.95 - samples/sec: 2779.78 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 14:58:09,356 epoch 3 - iter 891/992 - loss 0.07318574 - time (sec): 53.14 - samples/sec: 2776.76 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 14:58:15,110 epoch 3 - iter 990/992 - loss 0.07399399 - time (sec): 58.89 - samples/sec: 2778.86 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 14:58:15,219 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:58:15,219 EPOCH 3 done: loss 0.0739 - lr: 0.000023 | |
| 2023-10-17 14:58:18,781 DEV : loss 0.08807346224784851 - f1-score (micro avg) 0.755 | |
| 2023-10-17 14:58:18,804 saving best model | |
| 2023-10-17 14:58:19,266 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:58:25,033 epoch 4 - iter 99/992 - loss 0.04956166 - time (sec): 5.76 - samples/sec: 2737.94 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 14:58:31,264 epoch 4 - iter 198/992 - loss 0.05434284 - time (sec): 11.99 - samples/sec: 2716.72 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 14:58:36,836 epoch 4 - iter 297/992 - loss 0.05733946 - time (sec): 17.56 - samples/sec: 2758.90 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 14:58:42,898 epoch 4 - iter 396/992 - loss 0.05426292 - time (sec): 23.63 - samples/sec: 2756.56 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 14:58:48,800 epoch 4 - iter 495/992 - loss 0.05485342 - time (sec): 29.53 - samples/sec: 2765.68 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 14:58:54,693 epoch 4 - iter 594/992 - loss 0.05628478 - time (sec): 35.42 - samples/sec: 2760.51 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 14:59:00,816 epoch 4 - iter 693/992 - loss 0.05626172 - time (sec): 41.54 - samples/sec: 2750.81 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 14:59:06,690 epoch 4 - iter 792/992 - loss 0.05709857 - time (sec): 47.42 - samples/sec: 2751.91 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 14:59:12,827 epoch 4 - iter 891/992 - loss 0.05685953 - time (sec): 53.56 - samples/sec: 2750.63 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 14:59:18,691 epoch 4 - iter 990/992 - loss 0.05615262 - time (sec): 59.42 - samples/sec: 2754.59 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 14:59:18,816 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:59:18,816 EPOCH 4 done: loss 0.0563 - lr: 0.000020 | |
| 2023-10-17 14:59:22,248 DEV : loss 0.12442335486412048 - f1-score (micro avg) 0.754 | |
| 2023-10-17 14:59:22,269 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 14:59:27,842 epoch 5 - iter 99/992 - loss 0.04149832 - time (sec): 5.57 - samples/sec: 2872.15 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 14:59:34,016 epoch 5 - iter 198/992 - loss 0.04152572 - time (sec): 11.75 - samples/sec: 2793.52 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 14:59:40,734 epoch 5 - iter 297/992 - loss 0.04103463 - time (sec): 18.46 - samples/sec: 2714.78 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 14:59:46,580 epoch 5 - iter 396/992 - loss 0.04204274 - time (sec): 24.31 - samples/sec: 2727.02 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 14:59:52,832 epoch 5 - iter 495/992 - loss 0.04310676 - time (sec): 30.56 - samples/sec: 2737.91 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 14:59:58,758 epoch 5 - iter 594/992 - loss 0.04258103 - time (sec): 36.49 - samples/sec: 2726.69 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 15:00:05,057 epoch 5 - iter 693/992 - loss 0.04329139 - time (sec): 42.79 - samples/sec: 2719.01 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 15:00:11,054 epoch 5 - iter 792/992 - loss 0.04291426 - time (sec): 48.78 - samples/sec: 2704.32 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 15:00:16,943 epoch 5 - iter 891/992 - loss 0.04170637 - time (sec): 54.67 - samples/sec: 2700.67 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 15:00:23,012 epoch 5 - iter 990/992 - loss 0.04090239 - time (sec): 60.74 - samples/sec: 2694.20 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 15:00:23,123 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:00:23,123 EPOCH 5 done: loss 0.0408 - lr: 0.000017 | |
| 2023-10-17 15:00:26,694 DEV : loss 0.1553419977426529 - f1-score (micro avg) 0.757 | |
| 2023-10-17 15:00:26,717 saving best model | |
| 2023-10-17 15:00:27,166 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:00:33,331 epoch 6 - iter 99/992 - loss 0.02513130 - time (sec): 6.16 - samples/sec: 2689.96 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 15:00:39,188 epoch 6 - iter 198/992 - loss 0.02780468 - time (sec): 12.01 - samples/sec: 2785.50 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 15:00:44,948 epoch 6 - iter 297/992 - loss 0.02839834 - time (sec): 17.77 - samples/sec: 2822.68 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 15:00:50,855 epoch 6 - iter 396/992 - loss 0.02785029 - time (sec): 23.68 - samples/sec: 2822.21 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 15:00:56,852 epoch 6 - iter 495/992 - loss 0.03132603 - time (sec): 29.68 - samples/sec: 2802.51 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 15:01:03,041 epoch 6 - iter 594/992 - loss 0.03290732 - time (sec): 35.87 - samples/sec: 2800.06 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 15:01:08,750 epoch 6 - iter 693/992 - loss 0.03275845 - time (sec): 41.58 - samples/sec: 2788.17 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 15:01:14,597 epoch 6 - iter 792/992 - loss 0.03349634 - time (sec): 47.42 - samples/sec: 2773.28 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 15:01:20,458 epoch 6 - iter 891/992 - loss 0.03345707 - time (sec): 53.28 - samples/sec: 2773.30 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 15:01:26,307 epoch 6 - iter 990/992 - loss 0.03373942 - time (sec): 59.13 - samples/sec: 2767.63 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 15:01:26,419 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:01:26,419 EPOCH 6 done: loss 0.0338 - lr: 0.000013 | |
| 2023-10-17 15:01:30,490 DEV : loss 0.16105015575885773 - f1-score (micro avg) 0.7726 | |
| 2023-10-17 15:01:30,511 saving best model | |
| 2023-10-17 15:01:30,955 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:01:36,828 epoch 7 - iter 99/992 - loss 0.02381798 - time (sec): 5.87 - samples/sec: 2705.66 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 15:01:42,830 epoch 7 - iter 198/992 - loss 0.02353458 - time (sec): 11.87 - samples/sec: 2738.73 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 15:01:48,749 epoch 7 - iter 297/992 - loss 0.02504263 - time (sec): 17.79 - samples/sec: 2747.14 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 15:01:55,101 epoch 7 - iter 396/992 - loss 0.02614405 - time (sec): 24.14 - samples/sec: 2749.97 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 15:02:01,604 epoch 7 - iter 495/992 - loss 0.02434582 - time (sec): 30.65 - samples/sec: 2751.51 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 15:02:07,430 epoch 7 - iter 594/992 - loss 0.02437965 - time (sec): 36.47 - samples/sec: 2754.37 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 15:02:13,086 epoch 7 - iter 693/992 - loss 0.02378273 - time (sec): 42.13 - samples/sec: 2757.97 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 15:02:19,137 epoch 7 - iter 792/992 - loss 0.02441024 - time (sec): 48.18 - samples/sec: 2743.72 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 15:02:25,086 epoch 7 - iter 891/992 - loss 0.02525223 - time (sec): 54.13 - samples/sec: 2737.86 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 15:02:30,788 epoch 7 - iter 990/992 - loss 0.02504337 - time (sec): 59.83 - samples/sec: 2734.40 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 15:02:30,903 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:02:30,903 EPOCH 7 done: loss 0.0252 - lr: 0.000010 | |
| 2023-10-17 15:02:34,466 DEV : loss 0.19216737151145935 - f1-score (micro avg) 0.7635 | |
| 2023-10-17 15:02:34,487 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:02:40,105 epoch 8 - iter 99/992 - loss 0.01270573 - time (sec): 5.62 - samples/sec: 2896.52 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 15:02:45,885 epoch 8 - iter 198/992 - loss 0.01300986 - time (sec): 11.40 - samples/sec: 2834.30 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 15:02:51,778 epoch 8 - iter 297/992 - loss 0.01459488 - time (sec): 17.29 - samples/sec: 2821.29 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 15:02:57,542 epoch 8 - iter 396/992 - loss 0.01561924 - time (sec): 23.05 - samples/sec: 2832.29 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 15:03:03,553 epoch 8 - iter 495/992 - loss 0.01691767 - time (sec): 29.06 - samples/sec: 2801.37 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 15:03:09,405 epoch 8 - iter 594/992 - loss 0.01739702 - time (sec): 34.92 - samples/sec: 2782.27 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 15:03:15,390 epoch 8 - iter 693/992 - loss 0.01752797 - time (sec): 40.90 - samples/sec: 2778.72 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 15:03:21,256 epoch 8 - iter 792/992 - loss 0.01832980 - time (sec): 46.77 - samples/sec: 2788.63 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 15:03:26,957 epoch 8 - iter 891/992 - loss 0.01848759 - time (sec): 52.47 - samples/sec: 2787.76 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 15:03:33,284 epoch 8 - iter 990/992 - loss 0.01807558 - time (sec): 58.80 - samples/sec: 2782.92 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 15:03:33,407 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:03:33,407 EPOCH 8 done: loss 0.0181 - lr: 0.000007 | |
| 2023-10-17 15:03:36,953 DEV : loss 0.20749090611934662 - f1-score (micro avg) 0.7613 | |
| 2023-10-17 15:03:36,977 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:03:42,840 epoch 9 - iter 99/992 - loss 0.01140057 - time (sec): 5.86 - samples/sec: 2871.72 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 15:03:48,743 epoch 9 - iter 198/992 - loss 0.01229614 - time (sec): 11.76 - samples/sec: 2870.30 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 15:03:54,675 epoch 9 - iter 297/992 - loss 0.01290086 - time (sec): 17.70 - samples/sec: 2835.09 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 15:04:00,390 epoch 9 - iter 396/992 - loss 0.01384047 - time (sec): 23.41 - samples/sec: 2833.12 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 15:04:06,550 epoch 9 - iter 495/992 - loss 0.01440933 - time (sec): 29.57 - samples/sec: 2816.04 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 15:04:12,304 epoch 9 - iter 594/992 - loss 0.01487478 - time (sec): 35.32 - samples/sec: 2805.99 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 15:04:18,764 epoch 9 - iter 693/992 - loss 0.01494095 - time (sec): 41.79 - samples/sec: 2766.97 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 15:04:25,004 epoch 9 - iter 792/992 - loss 0.01466637 - time (sec): 48.02 - samples/sec: 2744.42 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 15:04:31,488 epoch 9 - iter 891/992 - loss 0.01464725 - time (sec): 54.51 - samples/sec: 2711.33 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 15:04:37,644 epoch 9 - iter 990/992 - loss 0.01489035 - time (sec): 60.67 - samples/sec: 2698.37 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 15:04:37,757 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:04:37,757 EPOCH 9 done: loss 0.0149 - lr: 0.000003 | |
| 2023-10-17 15:04:41,294 DEV : loss 0.21198396384716034 - f1-score (micro avg) 0.7669 | |
| 2023-10-17 15:04:41,316 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:04:47,397 epoch 10 - iter 99/992 - loss 0.01491946 - time (sec): 6.08 - samples/sec: 2782.08 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 15:04:53,310 epoch 10 - iter 198/992 - loss 0.01291025 - time (sec): 11.99 - samples/sec: 2782.64 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 15:04:59,419 epoch 10 - iter 297/992 - loss 0.01185798 - time (sec): 18.10 - samples/sec: 2771.44 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 15:05:05,218 epoch 10 - iter 396/992 - loss 0.01205737 - time (sec): 23.90 - samples/sec: 2742.16 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 15:05:11,758 epoch 10 - iter 495/992 - loss 0.01209685 - time (sec): 30.44 - samples/sec: 2711.64 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 15:05:17,984 epoch 10 - iter 594/992 - loss 0.01139644 - time (sec): 36.67 - samples/sec: 2680.71 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 15:05:23,872 epoch 10 - iter 693/992 - loss 0.01165819 - time (sec): 42.55 - samples/sec: 2692.82 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 15:05:30,014 epoch 10 - iter 792/992 - loss 0.01139237 - time (sec): 48.70 - samples/sec: 2679.16 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 15:05:35,725 epoch 10 - iter 891/992 - loss 0.01100199 - time (sec): 54.41 - samples/sec: 2683.81 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 15:05:41,981 epoch 10 - iter 990/992 - loss 0.01054514 - time (sec): 60.66 - samples/sec: 2699.31 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 15:05:42,082 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:05:42,083 EPOCH 10 done: loss 0.0105 - lr: 0.000000 | |
| 2023-10-17 15:05:46,454 DEV : loss 0.21605056524276733 - f1-score (micro avg) 0.7578 | |
| 2023-10-17 15:05:46,824 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:05:46,825 Loading model from best epoch ... | |
| 2023-10-17 15:05:48,292 SequenceTagger predicts: Dictionary with 13 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG | |
| 2023-10-17 15:05:51,908 | |
| Results: | |
| - F-score (micro) 0.7745 | |
| - F-score (macro) 0.6864 | |
| - Accuracy 0.6529 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.8356 0.8534 0.8444 655 | |
| PER 0.7328 0.7623 0.7473 223 | |
| ORG 0.4552 0.4803 0.4674 127 | |
| micro avg 0.7633 0.7861 0.7745 1005 | |
| macro avg 0.6745 0.6987 0.6864 1005 | |
| weighted avg 0.7647 0.7861 0.7752 1005 | |
| 2023-10-17 15:05:51,908 ---------------------------------------------------------------------------------------------------- | |