| 2023-10-17 18:25:45,533 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:45,534 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 18:25:45,534 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:45,534 MultiCorpus: 1166 train + 165 dev + 415 test sentences | |
| - NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator | |
| 2023-10-17 18:25:45,534 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:45,534 Train: 1166 sentences | |
| 2023-10-17 18:25:45,534 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 18:25:45,534 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:45,534 Training Params: | |
| 2023-10-17 18:25:45,534 - learning_rate: "5e-05" | |
| 2023-10-17 18:25:45,534 - mini_batch_size: "4" | |
| 2023-10-17 18:25:45,534 - max_epochs: "10" | |
| 2023-10-17 18:25:45,534 - shuffle: "True" | |
| 2023-10-17 18:25:45,534 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:45,534 Plugins: | |
| 2023-10-17 18:25:45,535 - TensorboardLogger | |
| 2023-10-17 18:25:45,535 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 18:25:45,535 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:45,535 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 18:25:45,535 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 18:25:45,535 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:45,535 Computation: | |
| 2023-10-17 18:25:45,535 - compute on device: cuda:0 | |
| 2023-10-17 18:25:45,535 - embedding storage: none | |
| 2023-10-17 18:25:45,535 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:45,535 Model training base path: "hmbench-newseye/fi-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 18:25:45,535 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:45,535 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:45,535 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 18:25:47,165 epoch 1 - iter 29/292 - loss 3.18613740 - time (sec): 1.63 - samples/sec: 2662.20 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:25:48,817 epoch 1 - iter 58/292 - loss 2.43657915 - time (sec): 3.28 - samples/sec: 2766.25 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:25:50,393 epoch 1 - iter 87/292 - loss 1.87393139 - time (sec): 4.86 - samples/sec: 2713.82 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:25:52,069 epoch 1 - iter 116/292 - loss 1.51583859 - time (sec): 6.53 - samples/sec: 2685.38 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:25:53,670 epoch 1 - iter 145/292 - loss 1.30956907 - time (sec): 8.13 - samples/sec: 2649.30 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:25:55,270 epoch 1 - iter 174/292 - loss 1.16604373 - time (sec): 9.73 - samples/sec: 2653.26 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:25:57,294 epoch 1 - iter 203/292 - loss 1.01825246 - time (sec): 11.76 - samples/sec: 2669.69 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 18:25:59,016 epoch 1 - iter 232/292 - loss 0.92326663 - time (sec): 13.48 - samples/sec: 2643.86 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 18:26:00,632 epoch 1 - iter 261/292 - loss 0.85407885 - time (sec): 15.10 - samples/sec: 2621.57 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 18:26:02,467 epoch 1 - iter 290/292 - loss 0.78472776 - time (sec): 16.93 - samples/sec: 2613.62 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 18:26:02,561 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:26:02,561 EPOCH 1 done: loss 0.7827 - lr: 0.000049 | |
| 2023-10-17 18:26:03,434 DEV : loss 0.17612501978874207 - f1-score (micro avg) 0.5786 | |
| 2023-10-17 18:26:03,441 saving best model | |
| 2023-10-17 18:26:03,830 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:26:05,581 epoch 2 - iter 29/292 - loss 0.20013544 - time (sec): 1.75 - samples/sec: 2475.90 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 18:26:07,446 epoch 2 - iter 58/292 - loss 0.25035285 - time (sec): 3.61 - samples/sec: 2650.36 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 18:26:09,063 epoch 2 - iter 87/292 - loss 0.22557746 - time (sec): 5.23 - samples/sec: 2688.22 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 18:26:10,662 epoch 2 - iter 116/292 - loss 0.21409449 - time (sec): 6.83 - samples/sec: 2703.16 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 18:26:12,474 epoch 2 - iter 145/292 - loss 0.20313262 - time (sec): 8.64 - samples/sec: 2698.64 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 18:26:14,042 epoch 2 - iter 174/292 - loss 0.19702803 - time (sec): 10.21 - samples/sec: 2641.85 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 18:26:15,644 epoch 2 - iter 203/292 - loss 0.18980094 - time (sec): 11.81 - samples/sec: 2629.38 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 18:26:17,356 epoch 2 - iter 232/292 - loss 0.18574347 - time (sec): 13.52 - samples/sec: 2649.14 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 18:26:18,971 epoch 2 - iter 261/292 - loss 0.17750905 - time (sec): 15.14 - samples/sec: 2639.15 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 18:26:20,686 epoch 2 - iter 290/292 - loss 0.17483348 - time (sec): 16.85 - samples/sec: 2618.46 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 18:26:20,781 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:26:20,781 EPOCH 2 done: loss 0.1747 - lr: 0.000045 | |
| 2023-10-17 18:26:22,105 DEV : loss 0.1112222746014595 - f1-score (micro avg) 0.6821 | |
| 2023-10-17 18:26:22,111 saving best model | |
| 2023-10-17 18:26:22,854 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:26:24,792 epoch 3 - iter 29/292 - loss 0.14188516 - time (sec): 1.94 - samples/sec: 2662.35 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 18:26:26,334 epoch 3 - iter 58/292 - loss 0.12052340 - time (sec): 3.48 - samples/sec: 2564.63 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 18:26:28,136 epoch 3 - iter 87/292 - loss 0.09757828 - time (sec): 5.28 - samples/sec: 2689.14 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 18:26:29,949 epoch 3 - iter 116/292 - loss 0.11370992 - time (sec): 7.09 - samples/sec: 2686.96 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 18:26:31,453 epoch 3 - iter 145/292 - loss 0.11373678 - time (sec): 8.60 - samples/sec: 2665.05 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 18:26:33,064 epoch 3 - iter 174/292 - loss 0.11464492 - time (sec): 10.21 - samples/sec: 2660.64 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 18:26:34,676 epoch 3 - iter 203/292 - loss 0.11659179 - time (sec): 11.82 - samples/sec: 2646.95 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 18:26:36,324 epoch 3 - iter 232/292 - loss 0.11916598 - time (sec): 13.47 - samples/sec: 2631.25 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 18:26:38,045 epoch 3 - iter 261/292 - loss 0.11235015 - time (sec): 15.19 - samples/sec: 2635.79 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 18:26:39,575 epoch 3 - iter 290/292 - loss 0.11019339 - time (sec): 16.72 - samples/sec: 2628.29 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 18:26:39,748 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:26:39,749 EPOCH 3 done: loss 0.1097 - lr: 0.000039 | |
| 2023-10-17 18:26:41,038 DEV : loss 0.12327136099338531 - f1-score (micro avg) 0.7175 | |
| 2023-10-17 18:26:41,044 saving best model | |
| 2023-10-17 18:26:41,510 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:26:43,259 epoch 4 - iter 29/292 - loss 0.05780006 - time (sec): 1.75 - samples/sec: 3003.01 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 18:26:44,937 epoch 4 - iter 58/292 - loss 0.06586664 - time (sec): 3.43 - samples/sec: 2807.21 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 18:26:46,495 epoch 4 - iter 87/292 - loss 0.06533887 - time (sec): 4.98 - samples/sec: 2698.98 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 18:26:48,066 epoch 4 - iter 116/292 - loss 0.06867545 - time (sec): 6.55 - samples/sec: 2709.32 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 18:26:49,928 epoch 4 - iter 145/292 - loss 0.06992338 - time (sec): 8.42 - samples/sec: 2659.85 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 18:26:51,600 epoch 4 - iter 174/292 - loss 0.07315040 - time (sec): 10.09 - samples/sec: 2631.67 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 18:26:53,250 epoch 4 - iter 203/292 - loss 0.07702547 - time (sec): 11.74 - samples/sec: 2635.55 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 18:26:55,060 epoch 4 - iter 232/292 - loss 0.07423944 - time (sec): 13.55 - samples/sec: 2653.70 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 18:26:56,644 epoch 4 - iter 261/292 - loss 0.07810988 - time (sec): 15.13 - samples/sec: 2635.48 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 18:26:58,367 epoch 4 - iter 290/292 - loss 0.07631874 - time (sec): 16.86 - samples/sec: 2622.41 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 18:26:58,460 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:26:58,460 EPOCH 4 done: loss 0.0760 - lr: 0.000033 | |
| 2023-10-17 18:26:59,798 DEV : loss 0.1451079547405243 - f1-score (micro avg) 0.6847 | |
| 2023-10-17 18:26:59,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:27:01,799 epoch 5 - iter 29/292 - loss 0.05043828 - time (sec): 1.99 - samples/sec: 2707.27 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 18:27:03,335 epoch 5 - iter 58/292 - loss 0.04774432 - time (sec): 3.53 - samples/sec: 2551.85 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 18:27:04,870 epoch 5 - iter 87/292 - loss 0.04176879 - time (sec): 5.07 - samples/sec: 2519.28 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 18:27:06,673 epoch 5 - iter 116/292 - loss 0.04395725 - time (sec): 6.87 - samples/sec: 2556.07 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 18:27:08,466 epoch 5 - iter 145/292 - loss 0.05077261 - time (sec): 8.66 - samples/sec: 2561.60 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 18:27:10,124 epoch 5 - iter 174/292 - loss 0.05488791 - time (sec): 10.32 - samples/sec: 2585.74 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:27:11,774 epoch 5 - iter 203/292 - loss 0.05160195 - time (sec): 11.97 - samples/sec: 2595.34 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:27:13,358 epoch 5 - iter 232/292 - loss 0.04939300 - time (sec): 13.55 - samples/sec: 2577.38 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:27:14,931 epoch 5 - iter 261/292 - loss 0.05056291 - time (sec): 15.13 - samples/sec: 2582.10 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:27:16,706 epoch 5 - iter 290/292 - loss 0.05249665 - time (sec): 16.90 - samples/sec: 2610.92 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:27:16,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:27:16,804 EPOCH 5 done: loss 0.0521 - lr: 0.000028 | |
| 2023-10-17 18:27:18,127 DEV : loss 0.13175830245018005 - f1-score (micro avg) 0.7484 | |
| 2023-10-17 18:27:18,133 saving best model | |
| 2023-10-17 18:27:18,609 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:27:20,545 epoch 6 - iter 29/292 - loss 0.04749293 - time (sec): 1.93 - samples/sec: 2901.85 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:27:22,015 epoch 6 - iter 58/292 - loss 0.03467209 - time (sec): 3.40 - samples/sec: 2733.66 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:27:23,818 epoch 6 - iter 87/292 - loss 0.03004853 - time (sec): 5.21 - samples/sec: 2696.84 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:27:25,554 epoch 6 - iter 116/292 - loss 0.02909901 - time (sec): 6.94 - samples/sec: 2721.06 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:27:27,128 epoch 6 - iter 145/292 - loss 0.02745446 - time (sec): 8.52 - samples/sec: 2667.45 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:27:28,918 epoch 6 - iter 174/292 - loss 0.02868680 - time (sec): 10.31 - samples/sec: 2647.09 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:27:30,519 epoch 6 - iter 203/292 - loss 0.02780283 - time (sec): 11.91 - samples/sec: 2622.96 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:27:32,177 epoch 6 - iter 232/292 - loss 0.03151691 - time (sec): 13.56 - samples/sec: 2626.48 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:27:33,730 epoch 6 - iter 261/292 - loss 0.02991938 - time (sec): 15.12 - samples/sec: 2645.03 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:27:35,340 epoch 6 - iter 290/292 - loss 0.02982713 - time (sec): 16.73 - samples/sec: 2637.39 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:27:35,450 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:27:35,450 EPOCH 6 done: loss 0.0298 - lr: 0.000022 | |
| 2023-10-17 18:27:36,770 DEV : loss 0.15781861543655396 - f1-score (micro avg) 0.7865 | |
| 2023-10-17 18:27:36,779 saving best model | |
| 2023-10-17 18:27:37,290 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:27:39,110 epoch 7 - iter 29/292 - loss 0.02148952 - time (sec): 1.82 - samples/sec: 2757.10 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:27:40,712 epoch 7 - iter 58/292 - loss 0.02559648 - time (sec): 3.42 - samples/sec: 2654.81 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:27:42,272 epoch 7 - iter 87/292 - loss 0.02641341 - time (sec): 4.98 - samples/sec: 2684.28 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:27:44,067 epoch 7 - iter 116/292 - loss 0.02342479 - time (sec): 6.77 - samples/sec: 2715.46 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:27:45,759 epoch 7 - iter 145/292 - loss 0.02437908 - time (sec): 8.47 - samples/sec: 2750.66 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:27:47,547 epoch 7 - iter 174/292 - loss 0.02781368 - time (sec): 10.25 - samples/sec: 2726.62 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:27:48,995 epoch 7 - iter 203/292 - loss 0.02691320 - time (sec): 11.70 - samples/sec: 2675.32 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:27:50,680 epoch 7 - iter 232/292 - loss 0.02826580 - time (sec): 13.39 - samples/sec: 2657.91 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:27:52,288 epoch 7 - iter 261/292 - loss 0.02747478 - time (sec): 15.00 - samples/sec: 2670.22 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:27:53,936 epoch 7 - iter 290/292 - loss 0.02695769 - time (sec): 16.64 - samples/sec: 2657.66 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:27:54,026 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:27:54,026 EPOCH 7 done: loss 0.0268 - lr: 0.000017 | |
| 2023-10-17 18:27:55,525 DEV : loss 0.14636801183223724 - f1-score (micro avg) 0.7665 | |
| 2023-10-17 18:27:55,530 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:27:57,206 epoch 8 - iter 29/292 - loss 0.02328808 - time (sec): 1.67 - samples/sec: 2783.27 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:27:58,886 epoch 8 - iter 58/292 - loss 0.01688701 - time (sec): 3.35 - samples/sec: 2715.02 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:28:00,615 epoch 8 - iter 87/292 - loss 0.01377932 - time (sec): 5.08 - samples/sec: 2853.11 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:28:02,404 epoch 8 - iter 116/292 - loss 0.01455950 - time (sec): 6.87 - samples/sec: 2835.32 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:28:04,057 epoch 8 - iter 145/292 - loss 0.01354542 - time (sec): 8.53 - samples/sec: 2817.33 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:28:05,701 epoch 8 - iter 174/292 - loss 0.01222758 - time (sec): 10.17 - samples/sec: 2774.33 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:28:07,352 epoch 8 - iter 203/292 - loss 0.01195591 - time (sec): 11.82 - samples/sec: 2724.71 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:28:08,945 epoch 8 - iter 232/292 - loss 0.01153344 - time (sec): 13.41 - samples/sec: 2669.03 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:28:10,669 epoch 8 - iter 261/292 - loss 0.01160975 - time (sec): 15.14 - samples/sec: 2655.82 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:28:12,311 epoch 8 - iter 290/292 - loss 0.01611918 - time (sec): 16.78 - samples/sec: 2642.42 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:28:12,404 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:28:12,404 EPOCH 8 done: loss 0.0161 - lr: 0.000011 | |
| 2023-10-17 18:28:13,645 DEV : loss 0.1687784641981125 - f1-score (micro avg) 0.7753 | |
| 2023-10-17 18:28:13,650 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:28:15,344 epoch 9 - iter 29/292 - loss 0.00977249 - time (sec): 1.69 - samples/sec: 2813.22 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:28:17,190 epoch 9 - iter 58/292 - loss 0.01107080 - time (sec): 3.54 - samples/sec: 2782.07 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:28:18,895 epoch 9 - iter 87/292 - loss 0.01520586 - time (sec): 5.24 - samples/sec: 2748.10 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:28:20,445 epoch 9 - iter 116/292 - loss 0.01368771 - time (sec): 6.79 - samples/sec: 2694.79 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:28:22,349 epoch 9 - iter 145/292 - loss 0.01146764 - time (sec): 8.70 - samples/sec: 2654.00 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:28:24,061 epoch 9 - iter 174/292 - loss 0.01189676 - time (sec): 10.41 - samples/sec: 2644.78 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:28:25,648 epoch 9 - iter 203/292 - loss 0.01279915 - time (sec): 12.00 - samples/sec: 2611.75 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:28:27,270 epoch 9 - iter 232/292 - loss 0.01285283 - time (sec): 13.62 - samples/sec: 2562.58 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:28:28,970 epoch 9 - iter 261/292 - loss 0.01186853 - time (sec): 15.32 - samples/sec: 2584.42 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:28:30,676 epoch 9 - iter 290/292 - loss 0.01186286 - time (sec): 17.02 - samples/sec: 2591.33 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:28:30,781 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:28:30,781 EPOCH 9 done: loss 0.0119 - lr: 0.000006 | |
| 2023-10-17 18:28:32,093 DEV : loss 0.17384137213230133 - f1-score (micro avg) 0.7736 | |
| 2023-10-17 18:28:32,102 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:28:34,052 epoch 10 - iter 29/292 - loss 0.00470992 - time (sec): 1.95 - samples/sec: 2541.66 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:28:35,786 epoch 10 - iter 58/292 - loss 0.00996719 - time (sec): 3.68 - samples/sec: 2516.34 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:28:37,358 epoch 10 - iter 87/292 - loss 0.01088373 - time (sec): 5.26 - samples/sec: 2470.78 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:28:39,085 epoch 10 - iter 116/292 - loss 0.01143748 - time (sec): 6.98 - samples/sec: 2547.76 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:28:40,818 epoch 10 - iter 145/292 - loss 0.01011895 - time (sec): 8.72 - samples/sec: 2573.55 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:28:42,528 epoch 10 - iter 174/292 - loss 0.00838896 - time (sec): 10.42 - samples/sec: 2619.28 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:28:44,144 epoch 10 - iter 203/292 - loss 0.00844523 - time (sec): 12.04 - samples/sec: 2607.79 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:28:45,693 epoch 10 - iter 232/292 - loss 0.00810851 - time (sec): 13.59 - samples/sec: 2606.23 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:28:47,325 epoch 10 - iter 261/292 - loss 0.00982592 - time (sec): 15.22 - samples/sec: 2610.32 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:28:49,017 epoch 10 - iter 290/292 - loss 0.00896485 - time (sec): 16.91 - samples/sec: 2611.37 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 18:28:49,137 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:28:49,137 EPOCH 10 done: loss 0.0095 - lr: 0.000000 | |
| 2023-10-17 18:28:50,434 DEV : loss 0.17314526438713074 - f1-score (micro avg) 0.7665 | |
| 2023-10-17 18:28:50,792 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:28:50,793 Loading model from best epoch ... | |
| 2023-10-17 18:28:52,335 SequenceTagger predicts: Dictionary with 17 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, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd | |
| 2023-10-17 18:28:54,933 | |
| Results: | |
| - F-score (micro) 0.7471 | |
| - F-score (macro) 0.6863 | |
| - Accuracy 0.6187 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.8078 0.8333 0.8204 348 | |
| LOC 0.6246 0.8161 0.7076 261 | |
| ORG 0.4762 0.3846 0.4255 52 | |
| HumanProd 0.7308 0.8636 0.7917 22 | |
| micro avg 0.7057 0.7936 0.7471 683 | |
| macro avg 0.6598 0.7244 0.6863 683 | |
| weighted avg 0.7101 0.7936 0.7463 683 | |
| 2023-10-17 18:28:54,933 ---------------------------------------------------------------------------------------------------- | |