| 2023-10-17 19:55:17,598 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:17,599 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=17, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 19:55:17,599 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:17,599 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 | |
| 2023-10-17 19:55:17,600 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:17,600 Train: 1085 sentences | |
| 2023-10-17 19:55:17,600 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 19:55:17,600 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:17,600 Training Params: | |
| 2023-10-17 19:55:17,600 - learning_rate: "5e-05" | |
| 2023-10-17 19:55:17,600 - mini_batch_size: "4" | |
| 2023-10-17 19:55:17,600 - max_epochs: "10" | |
| 2023-10-17 19:55:17,600 - shuffle: "True" | |
| 2023-10-17 19:55:17,600 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:17,600 Plugins: | |
| 2023-10-17 19:55:17,600 - TensorboardLogger | |
| 2023-10-17 19:55:17,600 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 19:55:17,600 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:17,600 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 19:55:17,600 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 19:55:17,600 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:17,600 Computation: | |
| 2023-10-17 19:55:17,600 - compute on device: cuda:0 | |
| 2023-10-17 19:55:17,600 - embedding storage: none | |
| 2023-10-17 19:55:17,600 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:17,600 Model training base path: "hmbench-newseye/sv-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-17 19:55:17,600 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:17,600 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:17,600 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 19:55:19,282 epoch 1 - iter 27/272 - loss 3.58728212 - time (sec): 1.68 - samples/sec: 2875.12 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 19:55:20,859 epoch 1 - iter 54/272 - loss 2.90987069 - time (sec): 3.26 - samples/sec: 2798.59 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 19:55:22,545 epoch 1 - iter 81/272 - loss 2.01439903 - time (sec): 4.94 - samples/sec: 3024.91 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 19:55:24,177 epoch 1 - iter 108/272 - loss 1.60141995 - time (sec): 6.58 - samples/sec: 3053.99 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 19:55:25,873 epoch 1 - iter 135/272 - loss 1.37197230 - time (sec): 8.27 - samples/sec: 2982.26 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 19:55:27,586 epoch 1 - iter 162/272 - loss 1.17795991 - time (sec): 9.98 - samples/sec: 3036.39 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 19:55:29,228 epoch 1 - iter 189/272 - loss 1.04761031 - time (sec): 11.63 - samples/sec: 3047.62 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 19:55:31,116 epoch 1 - iter 216/272 - loss 0.91564911 - time (sec): 13.52 - samples/sec: 3097.94 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 19:55:32,744 epoch 1 - iter 243/272 - loss 0.84955575 - time (sec): 15.14 - samples/sec: 3086.63 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 19:55:34,439 epoch 1 - iter 270/272 - loss 0.78512022 - time (sec): 16.84 - samples/sec: 3075.68 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 19:55:34,560 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:34,561 EPOCH 1 done: loss 0.7830 - lr: 0.000049 | |
| 2023-10-17 19:55:35,793 DEV : loss 0.1515471190214157 - f1-score (micro avg) 0.6667 | |
| 2023-10-17 19:55:35,798 saving best model | |
| 2023-10-17 19:55:36,227 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:37,920 epoch 2 - iter 27/272 - loss 0.12924177 - time (sec): 1.69 - samples/sec: 3053.54 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 19:55:39,505 epoch 2 - iter 54/272 - loss 0.14622270 - time (sec): 3.28 - samples/sec: 3212.70 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 19:55:41,201 epoch 2 - iter 81/272 - loss 0.15508578 - time (sec): 4.97 - samples/sec: 3232.69 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 19:55:42,823 epoch 2 - iter 108/272 - loss 0.15526673 - time (sec): 6.59 - samples/sec: 3233.37 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 19:55:44,296 epoch 2 - iter 135/272 - loss 0.14945571 - time (sec): 8.07 - samples/sec: 3198.57 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 19:55:45,967 epoch 2 - iter 162/272 - loss 0.15751951 - time (sec): 9.74 - samples/sec: 3202.41 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 19:55:47,469 epoch 2 - iter 189/272 - loss 0.15270059 - time (sec): 11.24 - samples/sec: 3171.02 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 19:55:49,098 epoch 2 - iter 216/272 - loss 0.14321390 - time (sec): 12.87 - samples/sec: 3212.17 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 19:55:50,812 epoch 2 - iter 243/272 - loss 0.13815810 - time (sec): 14.58 - samples/sec: 3193.14 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 19:55:52,345 epoch 2 - iter 270/272 - loss 0.13549913 - time (sec): 16.12 - samples/sec: 3208.84 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 19:55:52,441 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:52,441 EPOCH 2 done: loss 0.1351 - lr: 0.000045 | |
| 2023-10-17 19:55:53,883 DEV : loss 0.10580824315547943 - f1-score (micro avg) 0.7726 | |
| 2023-10-17 19:55:53,888 saving best model | |
| 2023-10-17 19:55:54,391 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:55:56,140 epoch 3 - iter 27/272 - loss 0.07036557 - time (sec): 1.74 - samples/sec: 3130.71 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 19:55:57,793 epoch 3 - iter 54/272 - loss 0.07600464 - time (sec): 3.40 - samples/sec: 3299.42 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 19:55:59,344 epoch 3 - iter 81/272 - loss 0.07559162 - time (sec): 4.95 - samples/sec: 3335.05 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 19:56:00,940 epoch 3 - iter 108/272 - loss 0.08826217 - time (sec): 6.55 - samples/sec: 3351.87 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 19:56:02,554 epoch 3 - iter 135/272 - loss 0.08009279 - time (sec): 8.16 - samples/sec: 3341.18 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 19:56:04,082 epoch 3 - iter 162/272 - loss 0.08296104 - time (sec): 9.69 - samples/sec: 3313.53 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 19:56:05,656 epoch 3 - iter 189/272 - loss 0.08693437 - time (sec): 11.26 - samples/sec: 3302.14 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 19:56:07,084 epoch 3 - iter 216/272 - loss 0.08846207 - time (sec): 12.69 - samples/sec: 3275.61 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 19:56:08,705 epoch 3 - iter 243/272 - loss 0.08394891 - time (sec): 14.31 - samples/sec: 3290.12 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 19:56:10,183 epoch 3 - iter 270/272 - loss 0.08317210 - time (sec): 15.79 - samples/sec: 3282.51 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 19:56:10,276 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:56:10,277 EPOCH 3 done: loss 0.0829 - lr: 0.000039 | |
| 2023-10-17 19:56:11,707 DEV : loss 0.10402542352676392 - f1-score (micro avg) 0.8043 | |
| 2023-10-17 19:56:11,712 saving best model | |
| 2023-10-17 19:56:12,213 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:56:13,938 epoch 4 - iter 27/272 - loss 0.03477530 - time (sec): 1.72 - samples/sec: 2832.62 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 19:56:15,671 epoch 4 - iter 54/272 - loss 0.03856732 - time (sec): 3.45 - samples/sec: 2877.04 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 19:56:17,462 epoch 4 - iter 81/272 - loss 0.04308053 - time (sec): 5.25 - samples/sec: 3020.32 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 19:56:18,885 epoch 4 - iter 108/272 - loss 0.04002880 - time (sec): 6.67 - samples/sec: 3025.83 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 19:56:20,446 epoch 4 - iter 135/272 - loss 0.04038678 - time (sec): 8.23 - samples/sec: 3063.84 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 19:56:22,343 epoch 4 - iter 162/272 - loss 0.04511288 - time (sec): 10.13 - samples/sec: 3062.76 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 19:56:23,947 epoch 4 - iter 189/272 - loss 0.04671298 - time (sec): 11.73 - samples/sec: 3072.60 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 19:56:25,610 epoch 4 - iter 216/272 - loss 0.04939325 - time (sec): 13.39 - samples/sec: 3080.46 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 19:56:27,178 epoch 4 - iter 243/272 - loss 0.05098514 - time (sec): 14.96 - samples/sec: 3100.74 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 19:56:28,751 epoch 4 - iter 270/272 - loss 0.05096145 - time (sec): 16.53 - samples/sec: 3129.77 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 19:56:28,851 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:56:28,852 EPOCH 4 done: loss 0.0511 - lr: 0.000033 | |
| 2023-10-17 19:56:30,341 DEV : loss 0.12085414677858353 - f1-score (micro avg) 0.8052 | |
| 2023-10-17 19:56:30,347 saving best model | |
| 2023-10-17 19:56:30,865 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:56:32,517 epoch 5 - iter 27/272 - loss 0.02111467 - time (sec): 1.65 - samples/sec: 3295.06 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 19:56:34,213 epoch 5 - iter 54/272 - loss 0.02884558 - time (sec): 3.34 - samples/sec: 3241.32 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 19:56:35,887 epoch 5 - iter 81/272 - loss 0.03350373 - time (sec): 5.02 - samples/sec: 3199.38 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 19:56:37,661 epoch 5 - iter 108/272 - loss 0.03765684 - time (sec): 6.79 - samples/sec: 3099.04 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 19:56:39,470 epoch 5 - iter 135/272 - loss 0.03526537 - time (sec): 8.60 - samples/sec: 3039.27 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 19:56:41,155 epoch 5 - iter 162/272 - loss 0.03255842 - time (sec): 10.29 - samples/sec: 3040.16 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 19:56:42,833 epoch 5 - iter 189/272 - loss 0.03591230 - time (sec): 11.96 - samples/sec: 3028.25 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 19:56:44,469 epoch 5 - iter 216/272 - loss 0.03429439 - time (sec): 13.60 - samples/sec: 3062.62 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 19:56:46,013 epoch 5 - iter 243/272 - loss 0.03432142 - time (sec): 15.15 - samples/sec: 3056.50 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 19:56:47,629 epoch 5 - iter 270/272 - loss 0.03306242 - time (sec): 16.76 - samples/sec: 3093.88 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 19:56:47,714 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:56:47,714 EPOCH 5 done: loss 0.0331 - lr: 0.000028 | |
| 2023-10-17 19:56:49,198 DEV : loss 0.16374681890010834 - f1-score (micro avg) 0.7731 | |
| 2023-10-17 19:56:49,205 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:56:50,796 epoch 6 - iter 27/272 - loss 0.01795708 - time (sec): 1.59 - samples/sec: 2942.56 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 19:56:52,589 epoch 6 - iter 54/272 - loss 0.02307386 - time (sec): 3.38 - samples/sec: 2914.30 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 19:56:54,348 epoch 6 - iter 81/272 - loss 0.02335478 - time (sec): 5.14 - samples/sec: 2954.02 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 19:56:56,062 epoch 6 - iter 108/272 - loss 0.02168575 - time (sec): 6.85 - samples/sec: 2958.19 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 19:56:57,770 epoch 6 - iter 135/272 - loss 0.02071478 - time (sec): 8.56 - samples/sec: 3025.61 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 19:56:59,511 epoch 6 - iter 162/272 - loss 0.02139419 - time (sec): 10.30 - samples/sec: 3098.72 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 19:57:01,179 epoch 6 - iter 189/272 - loss 0.02154034 - time (sec): 11.97 - samples/sec: 3090.78 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 19:57:02,732 epoch 6 - iter 216/272 - loss 0.02158152 - time (sec): 13.52 - samples/sec: 3084.52 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 19:57:04,267 epoch 6 - iter 243/272 - loss 0.02043382 - time (sec): 15.06 - samples/sec: 3093.99 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 19:57:05,846 epoch 6 - iter 270/272 - loss 0.02340166 - time (sec): 16.64 - samples/sec: 3114.02 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 19:57:05,945 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:57:05,946 EPOCH 6 done: loss 0.0233 - lr: 0.000022 | |
| 2023-10-17 19:57:07,395 DEV : loss 0.18149712681770325 - f1-score (micro avg) 0.7712 | |
| 2023-10-17 19:57:07,400 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:57:09,258 epoch 7 - iter 27/272 - loss 0.01987005 - time (sec): 1.86 - samples/sec: 3361.98 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 19:57:10,786 epoch 7 - iter 54/272 - loss 0.02048753 - time (sec): 3.38 - samples/sec: 3357.29 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 19:57:12,194 epoch 7 - iter 81/272 - loss 0.01675398 - time (sec): 4.79 - samples/sec: 3296.25 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 19:57:13,715 epoch 7 - iter 108/272 - loss 0.01410873 - time (sec): 6.31 - samples/sec: 3195.56 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 19:57:15,339 epoch 7 - iter 135/272 - loss 0.01440026 - time (sec): 7.94 - samples/sec: 3167.80 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 19:57:16,937 epoch 7 - iter 162/272 - loss 0.01524027 - time (sec): 9.54 - samples/sec: 3181.29 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 19:57:18,475 epoch 7 - iter 189/272 - loss 0.01363766 - time (sec): 11.07 - samples/sec: 3223.90 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 19:57:20,051 epoch 7 - iter 216/272 - loss 0.01279916 - time (sec): 12.65 - samples/sec: 3247.31 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 19:57:21,757 epoch 7 - iter 243/272 - loss 0.01479402 - time (sec): 14.36 - samples/sec: 3231.58 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 19:57:23,391 epoch 7 - iter 270/272 - loss 0.01589460 - time (sec): 15.99 - samples/sec: 3231.65 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 19:57:23,498 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:57:23,498 EPOCH 7 done: loss 0.0158 - lr: 0.000017 | |
| 2023-10-17 19:57:24,944 DEV : loss 0.16515286266803741 - f1-score (micro avg) 0.814 | |
| 2023-10-17 19:57:24,951 saving best model | |
| 2023-10-17 19:57:25,573 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:57:27,265 epoch 8 - iter 27/272 - loss 0.00723031 - time (sec): 1.69 - samples/sec: 2942.52 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 19:57:29,114 epoch 8 - iter 54/272 - loss 0.01039951 - time (sec): 3.54 - samples/sec: 3105.30 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 19:57:30,841 epoch 8 - iter 81/272 - loss 0.01020122 - time (sec): 5.26 - samples/sec: 3104.25 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 19:57:32,550 epoch 8 - iter 108/272 - loss 0.01100986 - time (sec): 6.97 - samples/sec: 2990.26 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 19:57:34,626 epoch 8 - iter 135/272 - loss 0.01325530 - time (sec): 9.05 - samples/sec: 2913.62 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 19:57:36,295 epoch 8 - iter 162/272 - loss 0.01235273 - time (sec): 10.72 - samples/sec: 2947.60 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 19:57:38,102 epoch 8 - iter 189/272 - loss 0.01435970 - time (sec): 12.53 - samples/sec: 3020.99 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 19:57:39,541 epoch 8 - iter 216/272 - loss 0.01417857 - time (sec): 13.96 - samples/sec: 3006.09 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 19:57:41,022 epoch 8 - iter 243/272 - loss 0.01414234 - time (sec): 15.45 - samples/sec: 2994.35 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 19:57:42,698 epoch 8 - iter 270/272 - loss 0.01356212 - time (sec): 17.12 - samples/sec: 3023.14 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 19:57:42,788 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:57:42,789 EPOCH 8 done: loss 0.0136 - lr: 0.000011 | |
| 2023-10-17 19:57:44,251 DEV : loss 0.17592966556549072 - f1-score (micro avg) 0.8222 | |
| 2023-10-17 19:57:44,256 saving best model | |
| 2023-10-17 19:57:44,791 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:57:46,426 epoch 9 - iter 27/272 - loss 0.00538360 - time (sec): 1.63 - samples/sec: 2942.35 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 19:57:48,183 epoch 9 - iter 54/272 - loss 0.00340815 - time (sec): 3.39 - samples/sec: 2946.64 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 19:57:49,700 epoch 9 - iter 81/272 - loss 0.00343662 - time (sec): 4.91 - samples/sec: 2873.13 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 19:57:51,553 epoch 9 - iter 108/272 - loss 0.00716874 - time (sec): 6.76 - samples/sec: 2978.89 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 19:57:53,125 epoch 9 - iter 135/272 - loss 0.00825452 - time (sec): 8.33 - samples/sec: 2975.95 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 19:57:54,779 epoch 9 - iter 162/272 - loss 0.00786866 - time (sec): 9.98 - samples/sec: 2975.76 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 19:57:56,585 epoch 9 - iter 189/272 - loss 0.00753915 - time (sec): 11.79 - samples/sec: 3091.69 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 19:57:58,248 epoch 9 - iter 216/272 - loss 0.00811762 - time (sec): 13.45 - samples/sec: 3103.59 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 19:57:59,862 epoch 9 - iter 243/272 - loss 0.00912190 - time (sec): 15.07 - samples/sec: 3068.80 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 19:58:01,590 epoch 9 - iter 270/272 - loss 0.00837205 - time (sec): 16.79 - samples/sec: 3084.14 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 19:58:01,677 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:58:01,678 EPOCH 9 done: loss 0.0083 - lr: 0.000006 | |
| 2023-10-17 19:58:03,185 DEV : loss 0.18768392503261566 - f1-score (micro avg) 0.7963 | |
| 2023-10-17 19:58:03,191 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:58:04,833 epoch 10 - iter 27/272 - loss 0.00264070 - time (sec): 1.64 - samples/sec: 3087.66 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 19:58:06,348 epoch 10 - iter 54/272 - loss 0.00313848 - time (sec): 3.16 - samples/sec: 3101.26 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 19:58:07,852 epoch 10 - iter 81/272 - loss 0.00255139 - time (sec): 4.66 - samples/sec: 3117.78 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 19:58:09,420 epoch 10 - iter 108/272 - loss 0.00238475 - time (sec): 6.23 - samples/sec: 3211.81 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 19:58:11,094 epoch 10 - iter 135/272 - loss 0.00263451 - time (sec): 7.90 - samples/sec: 3256.43 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 19:58:12,882 epoch 10 - iter 162/272 - loss 0.00305484 - time (sec): 9.69 - samples/sec: 3260.03 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 19:58:14,418 epoch 10 - iter 189/272 - loss 0.00319056 - time (sec): 11.23 - samples/sec: 3223.06 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 19:58:16,162 epoch 10 - iter 216/272 - loss 0.00368433 - time (sec): 12.97 - samples/sec: 3182.47 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 19:58:18,016 epoch 10 - iter 243/272 - loss 0.00572804 - time (sec): 14.82 - samples/sec: 3165.87 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 19:58:19,571 epoch 10 - iter 270/272 - loss 0.00528442 - time (sec): 16.38 - samples/sec: 3162.27 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 19:58:19,667 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:58:19,667 EPOCH 10 done: loss 0.0054 - lr: 0.000000 | |
| 2023-10-17 19:58:21,160 DEV : loss 0.18381302058696747 - f1-score (micro avg) 0.8037 | |
| 2023-10-17 19:58:21,585 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:58:21,586 Loading model from best epoch ... | |
| 2023-10-17 19:58:23,333 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 | |
| 2023-10-17 19:58:25,658 | |
| Results: | |
| - F-score (micro) 0.8069 | |
| - F-score (macro) 0.7678 | |
| - Accuracy 0.6937 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.8140 0.8974 0.8537 312 | |
| PER 0.7258 0.8654 0.7895 208 | |
| ORG 0.5818 0.5818 0.5818 55 | |
| HumanProd 0.7333 1.0000 0.8462 22 | |
| micro avg 0.7592 0.8610 0.8069 597 | |
| macro avg 0.7137 0.8362 0.7678 597 | |
| weighted avg 0.7589 0.8610 0.8060 597 | |
| 2023-10-17 19:58:25,658 ---------------------------------------------------------------------------------------------------- | |