| 2023-10-17 15:45:56,057 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:45:56,058 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 15:45:56,058 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:45:56,058 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 | |
| 2023-10-17 15:45:56,058 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:45:56,058 Train: 5777 sentences | |
| 2023-10-17 15:45:56,058 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 15:45:56,058 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:45:56,058 Training Params: | |
| 2023-10-17 15:45:56,058 - learning_rate: "3e-05" | |
| 2023-10-17 15:45:56,058 - mini_batch_size: "8" | |
| 2023-10-17 15:45:56,058 - max_epochs: "10" | |
| 2023-10-17 15:45:56,059 - shuffle: "True" | |
| 2023-10-17 15:45:56,059 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:45:56,059 Plugins: | |
| 2023-10-17 15:45:56,059 - TensorboardLogger | |
| 2023-10-17 15:45:56,059 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 15:45:56,059 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:45:56,059 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 15:45:56,059 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 15:45:56,059 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:45:56,059 Computation: | |
| 2023-10-17 15:45:56,059 - compute on device: cuda:0 | |
| 2023-10-17 15:45:56,059 - embedding storage: none | |
| 2023-10-17 15:45:56,059 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:45:56,059 Model training base path: "hmbench-icdar/nl-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-17 15:45:56,059 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:45:56,059 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:45:56,059 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 15:46:01,673 epoch 1 - iter 72/723 - loss 2.68178164 - time (sec): 5.61 - samples/sec: 3306.04 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 15:46:06,739 epoch 1 - iter 144/723 - loss 1.73320094 - time (sec): 10.68 - samples/sec: 3225.17 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 15:46:11,826 epoch 1 - iter 216/723 - loss 1.21849321 - time (sec): 15.77 - samples/sec: 3304.87 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 15:46:16,933 epoch 1 - iter 288/723 - loss 0.96972971 - time (sec): 20.87 - samples/sec: 3271.28 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 15:46:22,048 epoch 1 - iter 360/723 - loss 0.80187891 - time (sec): 25.99 - samples/sec: 3328.59 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 15:46:27,686 epoch 1 - iter 432/723 - loss 0.68438615 - time (sec): 31.63 - samples/sec: 3336.27 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 15:46:32,804 epoch 1 - iter 504/723 - loss 0.60522849 - time (sec): 36.74 - samples/sec: 3351.30 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 15:46:38,353 epoch 1 - iter 576/723 - loss 0.54423736 - time (sec): 42.29 - samples/sec: 3336.85 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 15:46:43,466 epoch 1 - iter 648/723 - loss 0.49945669 - time (sec): 47.41 - samples/sec: 3343.86 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 15:46:48,680 epoch 1 - iter 720/723 - loss 0.46320595 - time (sec): 52.62 - samples/sec: 3338.49 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 15:46:48,865 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:46:48,866 EPOCH 1 done: loss 0.4621 - lr: 0.000030 | |
| 2023-10-17 15:46:51,668 DEV : loss 0.083634153008461 - f1-score (micro avg) 0.7678 | |
| 2023-10-17 15:46:51,699 saving best model | |
| 2023-10-17 15:46:52,038 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:46:56,788 epoch 2 - iter 72/723 - loss 0.10554327 - time (sec): 4.75 - samples/sec: 3504.40 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 15:47:01,877 epoch 2 - iter 144/723 - loss 0.10289536 - time (sec): 9.84 - samples/sec: 3449.63 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 15:47:07,229 epoch 2 - iter 216/723 - loss 0.09591655 - time (sec): 15.19 - samples/sec: 3379.09 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 15:47:12,264 epoch 2 - iter 288/723 - loss 0.09172749 - time (sec): 20.22 - samples/sec: 3385.14 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 15:47:17,683 epoch 2 - iter 360/723 - loss 0.08913080 - time (sec): 25.64 - samples/sec: 3384.07 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 15:47:23,227 epoch 2 - iter 432/723 - loss 0.08592092 - time (sec): 31.19 - samples/sec: 3395.11 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 15:47:28,394 epoch 2 - iter 504/723 - loss 0.08558040 - time (sec): 36.35 - samples/sec: 3375.91 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 15:47:33,900 epoch 2 - iter 576/723 - loss 0.08586270 - time (sec): 41.86 - samples/sec: 3355.82 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 15:47:39,160 epoch 2 - iter 648/723 - loss 0.08631559 - time (sec): 47.12 - samples/sec: 3341.48 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 15:47:44,691 epoch 2 - iter 720/723 - loss 0.08442320 - time (sec): 52.65 - samples/sec: 3337.98 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 15:47:44,833 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:47:44,834 EPOCH 2 done: loss 0.0845 - lr: 0.000027 | |
| 2023-10-17 15:47:48,121 DEV : loss 0.07469072937965393 - f1-score (micro avg) 0.8009 | |
| 2023-10-17 15:47:48,138 saving best model | |
| 2023-10-17 15:47:48,600 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:47:53,799 epoch 3 - iter 72/723 - loss 0.06061902 - time (sec): 5.20 - samples/sec: 3343.37 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 15:47:58,758 epoch 3 - iter 144/723 - loss 0.06246632 - time (sec): 10.16 - samples/sec: 3410.06 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 15:48:04,289 epoch 3 - iter 216/723 - loss 0.05836782 - time (sec): 15.69 - samples/sec: 3416.83 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 15:48:09,294 epoch 3 - iter 288/723 - loss 0.06024793 - time (sec): 20.69 - samples/sec: 3418.32 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 15:48:14,102 epoch 3 - iter 360/723 - loss 0.05975732 - time (sec): 25.50 - samples/sec: 3431.01 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 15:48:19,583 epoch 3 - iter 432/723 - loss 0.05914523 - time (sec): 30.98 - samples/sec: 3399.25 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 15:48:24,777 epoch 3 - iter 504/723 - loss 0.05796925 - time (sec): 36.17 - samples/sec: 3373.49 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 15:48:29,852 epoch 3 - iter 576/723 - loss 0.05802209 - time (sec): 41.25 - samples/sec: 3381.28 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 15:48:35,266 epoch 3 - iter 648/723 - loss 0.05926008 - time (sec): 46.66 - samples/sec: 3378.08 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 15:48:40,649 epoch 3 - iter 720/723 - loss 0.05870783 - time (sec): 52.05 - samples/sec: 3377.67 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 15:48:40,818 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:48:40,818 EPOCH 3 done: loss 0.0589 - lr: 0.000023 | |
| 2023-10-17 15:48:44,093 DEV : loss 0.06352876126766205 - f1-score (micro avg) 0.8631 | |
| 2023-10-17 15:48:44,110 saving best model | |
| 2023-10-17 15:48:44,564 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:48:49,941 epoch 4 - iter 72/723 - loss 0.03603168 - time (sec): 5.37 - samples/sec: 3396.04 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 15:48:55,217 epoch 4 - iter 144/723 - loss 0.04465175 - time (sec): 10.65 - samples/sec: 3338.97 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 15:49:00,169 epoch 4 - iter 216/723 - loss 0.03818496 - time (sec): 15.60 - samples/sec: 3391.80 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 15:49:05,250 epoch 4 - iter 288/723 - loss 0.04002032 - time (sec): 20.68 - samples/sec: 3399.27 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 15:49:10,037 epoch 4 - iter 360/723 - loss 0.04084612 - time (sec): 25.47 - samples/sec: 3412.22 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 15:49:15,257 epoch 4 - iter 432/723 - loss 0.04029838 - time (sec): 30.69 - samples/sec: 3405.78 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 15:49:20,634 epoch 4 - iter 504/723 - loss 0.03969386 - time (sec): 36.07 - samples/sec: 3391.39 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 15:49:25,857 epoch 4 - iter 576/723 - loss 0.03975612 - time (sec): 41.29 - samples/sec: 3388.35 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 15:49:31,175 epoch 4 - iter 648/723 - loss 0.03963063 - time (sec): 46.61 - samples/sec: 3381.79 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 15:49:36,726 epoch 4 - iter 720/723 - loss 0.04156451 - time (sec): 52.16 - samples/sec: 3370.35 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 15:49:36,898 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:49:36,899 EPOCH 4 done: loss 0.0415 - lr: 0.000020 | |
| 2023-10-17 15:49:41,118 DEV : loss 0.06799901276826859 - f1-score (micro avg) 0.8746 | |
| 2023-10-17 15:49:41,141 saving best model | |
| 2023-10-17 15:49:41,679 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:49:47,167 epoch 5 - iter 72/723 - loss 0.02376358 - time (sec): 5.48 - samples/sec: 3226.12 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 15:49:52,615 epoch 5 - iter 144/723 - loss 0.02594860 - time (sec): 10.93 - samples/sec: 3287.37 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 15:49:57,962 epoch 5 - iter 216/723 - loss 0.02802592 - time (sec): 16.28 - samples/sec: 3301.19 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 15:50:02,837 epoch 5 - iter 288/723 - loss 0.02819628 - time (sec): 21.15 - samples/sec: 3331.14 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 15:50:08,174 epoch 5 - iter 360/723 - loss 0.02715481 - time (sec): 26.49 - samples/sec: 3314.58 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 15:50:13,371 epoch 5 - iter 432/723 - loss 0.02990002 - time (sec): 31.69 - samples/sec: 3310.19 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 15:50:18,582 epoch 5 - iter 504/723 - loss 0.03021850 - time (sec): 36.90 - samples/sec: 3307.86 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 15:50:24,122 epoch 5 - iter 576/723 - loss 0.03040793 - time (sec): 42.44 - samples/sec: 3313.10 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 15:50:29,149 epoch 5 - iter 648/723 - loss 0.03142248 - time (sec): 47.47 - samples/sec: 3325.10 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 15:50:34,566 epoch 5 - iter 720/723 - loss 0.03099853 - time (sec): 52.88 - samples/sec: 3321.54 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 15:50:34,755 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:50:34,755 EPOCH 5 done: loss 0.0309 - lr: 0.000017 | |
| 2023-10-17 15:50:38,119 DEV : loss 0.07522039115428925 - f1-score (micro avg) 0.8791 | |
| 2023-10-17 15:50:38,139 saving best model | |
| 2023-10-17 15:50:38,758 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:50:44,341 epoch 6 - iter 72/723 - loss 0.02298660 - time (sec): 5.58 - samples/sec: 3136.20 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 15:50:49,596 epoch 6 - iter 144/723 - loss 0.02602275 - time (sec): 10.84 - samples/sec: 3140.88 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 15:50:54,847 epoch 6 - iter 216/723 - loss 0.02355676 - time (sec): 16.09 - samples/sec: 3207.25 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 15:51:00,517 epoch 6 - iter 288/723 - loss 0.02151277 - time (sec): 21.76 - samples/sec: 3207.74 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 15:51:06,018 epoch 6 - iter 360/723 - loss 0.02188892 - time (sec): 27.26 - samples/sec: 3228.23 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 15:51:10,863 epoch 6 - iter 432/723 - loss 0.02227604 - time (sec): 32.10 - samples/sec: 3252.96 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 15:51:16,271 epoch 6 - iter 504/723 - loss 0.02192958 - time (sec): 37.51 - samples/sec: 3267.25 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 15:51:21,264 epoch 6 - iter 576/723 - loss 0.02222078 - time (sec): 42.50 - samples/sec: 3271.97 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 15:51:26,468 epoch 6 - iter 648/723 - loss 0.02271175 - time (sec): 47.71 - samples/sec: 3285.50 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 15:51:31,981 epoch 6 - iter 720/723 - loss 0.02243575 - time (sec): 53.22 - samples/sec: 3297.48 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 15:51:32,161 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:51:32,161 EPOCH 6 done: loss 0.0224 - lr: 0.000013 | |
| 2023-10-17 15:51:35,411 DEV : loss 0.0899529755115509 - f1-score (micro avg) 0.8669 | |
| 2023-10-17 15:51:35,428 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:51:40,615 epoch 7 - iter 72/723 - loss 0.02639271 - time (sec): 5.19 - samples/sec: 3330.13 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 15:51:45,594 epoch 7 - iter 144/723 - loss 0.02336250 - time (sec): 10.16 - samples/sec: 3347.60 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 15:51:51,011 epoch 7 - iter 216/723 - loss 0.02344656 - time (sec): 15.58 - samples/sec: 3334.04 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 15:51:56,570 epoch 7 - iter 288/723 - loss 0.02259809 - time (sec): 21.14 - samples/sec: 3312.26 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 15:52:01,822 epoch 7 - iter 360/723 - loss 0.02097885 - time (sec): 26.39 - samples/sec: 3308.99 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 15:52:07,186 epoch 7 - iter 432/723 - loss 0.02029519 - time (sec): 31.76 - samples/sec: 3338.21 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 15:52:12,489 epoch 7 - iter 504/723 - loss 0.01871245 - time (sec): 37.06 - samples/sec: 3322.53 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 15:52:17,453 epoch 7 - iter 576/723 - loss 0.01758688 - time (sec): 42.02 - samples/sec: 3336.67 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 15:52:22,949 epoch 7 - iter 648/723 - loss 0.01786632 - time (sec): 47.52 - samples/sec: 3326.85 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 15:52:28,120 epoch 7 - iter 720/723 - loss 0.01774989 - time (sec): 52.69 - samples/sec: 3336.16 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 15:52:28,292 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:52:28,292 EPOCH 7 done: loss 0.0177 - lr: 0.000010 | |
| 2023-10-17 15:52:31,922 DEV : loss 0.11688686162233353 - f1-score (micro avg) 0.8596 | |
| 2023-10-17 15:52:31,938 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:52:37,064 epoch 8 - iter 72/723 - loss 0.00919413 - time (sec): 5.12 - samples/sec: 3151.46 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 15:52:42,635 epoch 8 - iter 144/723 - loss 0.01083441 - time (sec): 10.70 - samples/sec: 3230.53 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 15:52:47,538 epoch 8 - iter 216/723 - loss 0.00989999 - time (sec): 15.60 - samples/sec: 3353.03 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 15:52:52,785 epoch 8 - iter 288/723 - loss 0.01247336 - time (sec): 20.85 - samples/sec: 3311.76 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 15:52:58,034 epoch 8 - iter 360/723 - loss 0.01235182 - time (sec): 26.09 - samples/sec: 3299.45 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 15:53:03,779 epoch 8 - iter 432/723 - loss 0.01184060 - time (sec): 31.84 - samples/sec: 3284.45 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 15:53:08,859 epoch 8 - iter 504/723 - loss 0.01254325 - time (sec): 36.92 - samples/sec: 3315.05 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 15:53:13,896 epoch 8 - iter 576/723 - loss 0.01301608 - time (sec): 41.96 - samples/sec: 3319.64 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 15:53:19,337 epoch 8 - iter 648/723 - loss 0.01254319 - time (sec): 47.40 - samples/sec: 3330.23 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 15:53:24,575 epoch 8 - iter 720/723 - loss 0.01246900 - time (sec): 52.64 - samples/sec: 3333.78 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 15:53:24,822 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:53:24,823 EPOCH 8 done: loss 0.0124 - lr: 0.000007 | |
| 2023-10-17 15:53:28,074 DEV : loss 0.13734176754951477 - f1-score (micro avg) 0.8504 | |
| 2023-10-17 15:53:28,090 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:53:33,549 epoch 9 - iter 72/723 - loss 0.00909466 - time (sec): 5.46 - samples/sec: 3518.82 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 15:53:38,524 epoch 9 - iter 144/723 - loss 0.00940547 - time (sec): 10.43 - samples/sec: 3364.03 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 15:53:44,259 epoch 9 - iter 216/723 - loss 0.01048964 - time (sec): 16.17 - samples/sec: 3349.94 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 15:53:49,765 epoch 9 - iter 288/723 - loss 0.00977033 - time (sec): 21.67 - samples/sec: 3342.19 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 15:53:54,956 epoch 9 - iter 360/723 - loss 0.01032154 - time (sec): 26.86 - samples/sec: 3334.04 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 15:53:59,778 epoch 9 - iter 432/723 - loss 0.00954858 - time (sec): 31.69 - samples/sec: 3331.01 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 15:54:05,113 epoch 9 - iter 504/723 - loss 0.00934623 - time (sec): 37.02 - samples/sec: 3327.57 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 15:54:10,656 epoch 9 - iter 576/723 - loss 0.00919239 - time (sec): 42.56 - samples/sec: 3320.20 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 15:54:15,842 epoch 9 - iter 648/723 - loss 0.00916243 - time (sec): 47.75 - samples/sec: 3328.89 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 15:54:20,519 epoch 9 - iter 720/723 - loss 0.00958573 - time (sec): 52.43 - samples/sec: 3346.41 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 15:54:20,785 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:54:20,785 EPOCH 9 done: loss 0.0095 - lr: 0.000003 | |
| 2023-10-17 15:54:24,408 DEV : loss 0.1309017837047577 - f1-score (micro avg) 0.868 | |
| 2023-10-17 15:54:24,424 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:54:29,477 epoch 10 - iter 72/723 - loss 0.01046618 - time (sec): 5.05 - samples/sec: 3453.62 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 15:54:34,691 epoch 10 - iter 144/723 - loss 0.00825176 - time (sec): 10.27 - samples/sec: 3414.55 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 15:54:39,628 epoch 10 - iter 216/723 - loss 0.00756983 - time (sec): 15.20 - samples/sec: 3400.23 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 15:54:44,560 epoch 10 - iter 288/723 - loss 0.00728100 - time (sec): 20.14 - samples/sec: 3374.43 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 15:54:50,251 epoch 10 - iter 360/723 - loss 0.00697531 - time (sec): 25.83 - samples/sec: 3356.39 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 15:54:55,716 epoch 10 - iter 432/723 - loss 0.00709396 - time (sec): 31.29 - samples/sec: 3368.09 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 15:55:00,829 epoch 10 - iter 504/723 - loss 0.00639323 - time (sec): 36.40 - samples/sec: 3352.43 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 15:55:06,443 epoch 10 - iter 576/723 - loss 0.00638631 - time (sec): 42.02 - samples/sec: 3334.30 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 15:55:11,652 epoch 10 - iter 648/723 - loss 0.00661275 - time (sec): 47.23 - samples/sec: 3347.94 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 15:55:16,942 epoch 10 - iter 720/723 - loss 0.00661983 - time (sec): 52.52 - samples/sec: 3346.42 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 15:55:17,097 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:55:17,098 EPOCH 10 done: loss 0.0066 - lr: 0.000000 | |
| 2023-10-17 15:55:20,489 DEV : loss 0.13723282516002655 - f1-score (micro avg) 0.8639 | |
| 2023-10-17 15:55:20,889 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 15:55:20,891 Loading model from best epoch ... | |
| 2023-10-17 15:55:22,430 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 | |
| 2023-10-17 15:55:25,740 | |
| Results: | |
| - F-score (micro) 0.855 | |
| - F-score (macro) 0.7682 | |
| - Accuracy 0.7567 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.8568 0.8320 0.8442 482 | |
| LOC 0.9278 0.8974 0.9123 458 | |
| ORG 0.5606 0.5362 0.5481 69 | |
| micro avg 0.8690 0.8414 0.8550 1009 | |
| macro avg 0.7817 0.7552 0.7682 1009 | |
| weighted avg 0.8688 0.8414 0.8549 1009 | |
| 2023-10-17 15:55:25,740 ---------------------------------------------------------------------------------------------------- | |