| 2023-10-17 13:14:59,271 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:14:59,272 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 13:14:59,272 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:14:59,273 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 13:14:59,273 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:14:59,273 Train: 7936 sentences | |
| 2023-10-17 13:14:59,273 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 13:14:59,273 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:14:59,273 Training Params: | |
| 2023-10-17 13:14:59,273 - learning_rate: "5e-05" | |
| 2023-10-17 13:14:59,273 - mini_batch_size: "8" | |
| 2023-10-17 13:14:59,273 - max_epochs: "10" | |
| 2023-10-17 13:14:59,273 - shuffle: "True" | |
| 2023-10-17 13:14:59,273 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:14:59,273 Plugins: | |
| 2023-10-17 13:14:59,273 - TensorboardLogger | |
| 2023-10-17 13:14:59,273 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 13:14:59,273 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:14:59,273 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 13:14:59,273 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 13:14:59,273 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:14:59,273 Computation: | |
| 2023-10-17 13:14:59,273 - compute on device: cuda:0 | |
| 2023-10-17 13:14:59,273 - embedding storage: none | |
| 2023-10-17 13:14:59,273 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:14:59,273 Model training base path: "hmbench-icdar/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-17 13:14:59,273 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:14:59,273 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:14:59,273 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 13:15:05,295 epoch 1 - iter 99/992 - loss 2.37029663 - time (sec): 6.02 - samples/sec: 2836.14 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 13:15:11,137 epoch 1 - iter 198/992 - loss 1.42416275 - time (sec): 11.86 - samples/sec: 2784.92 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 13:15:17,507 epoch 1 - iter 297/992 - loss 1.03740415 - time (sec): 18.23 - samples/sec: 2744.60 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 13:15:23,330 epoch 1 - iter 396/992 - loss 0.83714066 - time (sec): 24.06 - samples/sec: 2738.69 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 13:15:29,614 epoch 1 - iter 495/992 - loss 0.69593175 - time (sec): 30.34 - samples/sec: 2736.27 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 13:15:35,822 epoch 1 - iter 594/992 - loss 0.59927064 - time (sec): 36.55 - samples/sec: 2749.66 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 13:15:42,169 epoch 1 - iter 693/992 - loss 0.53186441 - time (sec): 42.89 - samples/sec: 2742.71 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 13:15:48,050 epoch 1 - iter 792/992 - loss 0.48827616 - time (sec): 48.78 - samples/sec: 2725.13 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 13:15:53,920 epoch 1 - iter 891/992 - loss 0.45262959 - time (sec): 54.65 - samples/sec: 2708.63 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 13:15:59,754 epoch 1 - iter 990/992 - loss 0.42092898 - time (sec): 60.48 - samples/sec: 2706.81 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-17 13:15:59,862 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:15:59,862 EPOCH 1 done: loss 0.4209 - lr: 0.000050 | |
| 2023-10-17 13:16:03,260 DEV : loss 0.08556017279624939 - f1-score (micro avg) 0.7181 | |
| 2023-10-17 13:16:03,284 saving best model | |
| 2023-10-17 13:16:03,706 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:16:09,578 epoch 2 - iter 99/992 - loss 0.11844195 - time (sec): 5.87 - samples/sec: 2569.51 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 13:16:15,696 epoch 2 - iter 198/992 - loss 0.11939327 - time (sec): 11.99 - samples/sec: 2634.08 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 13:16:21,468 epoch 2 - iter 297/992 - loss 0.12037513 - time (sec): 17.76 - samples/sec: 2643.91 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 13:16:27,737 epoch 2 - iter 396/992 - loss 0.11645305 - time (sec): 24.03 - samples/sec: 2642.00 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 13:16:33,971 epoch 2 - iter 495/992 - loss 0.11602227 - time (sec): 30.26 - samples/sec: 2652.74 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 13:16:39,758 epoch 2 - iter 594/992 - loss 0.11405300 - time (sec): 36.05 - samples/sec: 2682.51 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 13:16:45,730 epoch 2 - iter 693/992 - loss 0.11194828 - time (sec): 42.02 - samples/sec: 2680.69 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 13:16:52,651 epoch 2 - iter 792/992 - loss 0.11137892 - time (sec): 48.94 - samples/sec: 2643.62 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 13:16:58,820 epoch 2 - iter 891/992 - loss 0.11016016 - time (sec): 55.11 - samples/sec: 2663.66 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 13:17:04,760 epoch 2 - iter 990/992 - loss 0.10803629 - time (sec): 61.05 - samples/sec: 2681.10 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 13:17:04,874 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:17:04,874 EPOCH 2 done: loss 0.1079 - lr: 0.000044 | |
| 2023-10-17 13:17:08,500 DEV : loss 0.09252572059631348 - f1-score (micro avg) 0.7468 | |
| 2023-10-17 13:17:08,522 saving best model | |
| 2023-10-17 13:17:09,023 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:17:14,747 epoch 3 - iter 99/992 - loss 0.07613487 - time (sec): 5.72 - samples/sec: 2785.56 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 13:17:20,906 epoch 3 - iter 198/992 - loss 0.07588141 - time (sec): 11.88 - samples/sec: 2751.47 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 13:17:26,809 epoch 3 - iter 297/992 - loss 0.07548816 - time (sec): 17.78 - samples/sec: 2755.77 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 13:17:32,924 epoch 3 - iter 396/992 - loss 0.07568375 - time (sec): 23.90 - samples/sec: 2731.38 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 13:17:38,727 epoch 3 - iter 495/992 - loss 0.07493804 - time (sec): 29.70 - samples/sec: 2720.87 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 13:17:44,768 epoch 3 - iter 594/992 - loss 0.07584050 - time (sec): 35.74 - samples/sec: 2711.17 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 13:17:50,762 epoch 3 - iter 693/992 - loss 0.07567410 - time (sec): 41.73 - samples/sec: 2722.75 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 13:17:57,136 epoch 3 - iter 792/992 - loss 0.07595643 - time (sec): 48.11 - samples/sec: 2735.76 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 13:18:02,952 epoch 3 - iter 891/992 - loss 0.07610041 - time (sec): 53.92 - samples/sec: 2740.07 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 13:18:08,940 epoch 3 - iter 990/992 - loss 0.07608824 - time (sec): 59.91 - samples/sec: 2732.03 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 13:18:09,067 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:18:09,067 EPOCH 3 done: loss 0.0760 - lr: 0.000039 | |
| 2023-10-17 13:18:12,705 DEV : loss 0.09796484559774399 - f1-score (micro avg) 0.743 | |
| 2023-10-17 13:18:12,728 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:18:18,838 epoch 4 - iter 99/992 - loss 0.05370749 - time (sec): 6.11 - samples/sec: 2803.21 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 13:18:24,824 epoch 4 - iter 198/992 - loss 0.05126212 - time (sec): 12.10 - samples/sec: 2722.25 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 13:18:30,600 epoch 4 - iter 297/992 - loss 0.04823145 - time (sec): 17.87 - samples/sec: 2740.59 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 13:18:36,555 epoch 4 - iter 396/992 - loss 0.05004986 - time (sec): 23.83 - samples/sec: 2729.66 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 13:18:42,757 epoch 4 - iter 495/992 - loss 0.05199699 - time (sec): 30.03 - samples/sec: 2726.05 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 13:18:48,709 epoch 4 - iter 594/992 - loss 0.05345247 - time (sec): 35.98 - samples/sec: 2711.17 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 13:18:55,097 epoch 4 - iter 693/992 - loss 0.05435726 - time (sec): 42.37 - samples/sec: 2701.73 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 13:19:01,303 epoch 4 - iter 792/992 - loss 0.05525748 - time (sec): 48.57 - samples/sec: 2696.82 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 13:19:07,402 epoch 4 - iter 891/992 - loss 0.05470790 - time (sec): 54.67 - samples/sec: 2696.65 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 13:19:13,257 epoch 4 - iter 990/992 - loss 0.05624270 - time (sec): 60.53 - samples/sec: 2703.77 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 13:19:13,374 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:19:13,375 EPOCH 4 done: loss 0.0563 - lr: 0.000033 | |
| 2023-10-17 13:19:17,015 DEV : loss 0.13502389192581177 - f1-score (micro avg) 0.7351 | |
| 2023-10-17 13:19:17,039 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:19:23,271 epoch 5 - iter 99/992 - loss 0.04548482 - time (sec): 6.23 - samples/sec: 2647.00 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 13:19:29,232 epoch 5 - iter 198/992 - loss 0.03764309 - time (sec): 12.19 - samples/sec: 2709.56 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 13:19:34,819 epoch 5 - iter 297/992 - loss 0.04076199 - time (sec): 17.78 - samples/sec: 2739.34 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 13:19:40,687 epoch 5 - iter 396/992 - loss 0.04113845 - time (sec): 23.65 - samples/sec: 2743.63 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 13:19:46,682 epoch 5 - iter 495/992 - loss 0.04216041 - time (sec): 29.64 - samples/sec: 2746.99 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 13:19:52,359 epoch 5 - iter 594/992 - loss 0.04162863 - time (sec): 35.32 - samples/sec: 2738.04 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 13:19:58,468 epoch 5 - iter 693/992 - loss 0.04196048 - time (sec): 41.43 - samples/sec: 2747.11 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 13:20:04,661 epoch 5 - iter 792/992 - loss 0.04200273 - time (sec): 47.62 - samples/sec: 2733.11 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 13:20:10,825 epoch 5 - iter 891/992 - loss 0.04111233 - time (sec): 53.78 - samples/sec: 2728.76 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 13:20:17,147 epoch 5 - iter 990/992 - loss 0.04120519 - time (sec): 60.11 - samples/sec: 2722.68 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 13:20:17,252 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:20:17,252 EPOCH 5 done: loss 0.0413 - lr: 0.000028 | |
| 2023-10-17 13:20:21,297 DEV : loss 0.16693313419818878 - f1-score (micro avg) 0.7468 | |
| 2023-10-17 13:20:21,318 saving best model | |
| 2023-10-17 13:20:21,823 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:20:27,842 epoch 6 - iter 99/992 - loss 0.03143511 - time (sec): 6.01 - samples/sec: 2723.17 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 13:20:33,977 epoch 6 - iter 198/992 - loss 0.03222403 - time (sec): 12.14 - samples/sec: 2689.22 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 13:20:39,814 epoch 6 - iter 297/992 - loss 0.03239315 - time (sec): 17.98 - samples/sec: 2738.44 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 13:20:46,020 epoch 6 - iter 396/992 - loss 0.03107293 - time (sec): 24.18 - samples/sec: 2718.08 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 13:20:51,966 epoch 6 - iter 495/992 - loss 0.03192172 - time (sec): 30.13 - samples/sec: 2704.51 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 13:20:57,687 epoch 6 - iter 594/992 - loss 0.03209592 - time (sec): 35.85 - samples/sec: 2691.46 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 13:21:03,674 epoch 6 - iter 693/992 - loss 0.03197057 - time (sec): 41.84 - samples/sec: 2698.71 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 13:21:09,768 epoch 6 - iter 792/992 - loss 0.03184049 - time (sec): 47.93 - samples/sec: 2719.96 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 13:21:15,647 epoch 6 - iter 891/992 - loss 0.03193054 - time (sec): 53.81 - samples/sec: 2718.30 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 13:21:21,836 epoch 6 - iter 990/992 - loss 0.03148429 - time (sec): 60.00 - samples/sec: 2727.29 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 13:21:21,978 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:21:21,979 EPOCH 6 done: loss 0.0314 - lr: 0.000022 | |
| 2023-10-17 13:21:25,589 DEV : loss 0.20110860466957092 - f1-score (micro avg) 0.7578 | |
| 2023-10-17 13:21:25,610 saving best model | |
| 2023-10-17 13:21:26,155 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:21:31,969 epoch 7 - iter 99/992 - loss 0.02399857 - time (sec): 5.81 - samples/sec: 2688.29 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 13:21:38,459 epoch 7 - iter 198/992 - loss 0.02332968 - time (sec): 12.30 - samples/sec: 2696.87 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 13:21:44,257 epoch 7 - iter 297/992 - loss 0.02310479 - time (sec): 18.10 - samples/sec: 2722.47 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 13:21:50,142 epoch 7 - iter 396/992 - loss 0.02381511 - time (sec): 23.98 - samples/sec: 2716.04 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 13:21:56,060 epoch 7 - iter 495/992 - loss 0.02318505 - time (sec): 29.90 - samples/sec: 2723.81 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 13:22:02,276 epoch 7 - iter 594/992 - loss 0.02242971 - time (sec): 36.12 - samples/sec: 2720.51 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 13:22:08,501 epoch 7 - iter 693/992 - loss 0.02235423 - time (sec): 42.34 - samples/sec: 2721.65 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 13:22:14,887 epoch 7 - iter 792/992 - loss 0.02243338 - time (sec): 48.73 - samples/sec: 2696.54 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 13:22:20,929 epoch 7 - iter 891/992 - loss 0.02280661 - time (sec): 54.77 - samples/sec: 2692.86 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 13:22:26,941 epoch 7 - iter 990/992 - loss 0.02265879 - time (sec): 60.78 - samples/sec: 2693.46 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 13:22:27,063 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:22:27,063 EPOCH 7 done: loss 0.0226 - lr: 0.000017 | |
| 2023-10-17 13:22:30,642 DEV : loss 0.2132951319217682 - f1-score (micro avg) 0.7572 | |
| 2023-10-17 13:22:30,665 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:22:36,466 epoch 8 - iter 99/992 - loss 0.01675590 - time (sec): 5.80 - samples/sec: 2772.29 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 13:22:42,460 epoch 8 - iter 198/992 - loss 0.01668702 - time (sec): 11.79 - samples/sec: 2722.69 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 13:22:48,546 epoch 8 - iter 297/992 - loss 0.01664626 - time (sec): 17.88 - samples/sec: 2703.17 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 13:22:54,477 epoch 8 - iter 396/992 - loss 0.01673593 - time (sec): 23.81 - samples/sec: 2725.71 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 13:23:00,709 epoch 8 - iter 495/992 - loss 0.01742427 - time (sec): 30.04 - samples/sec: 2724.28 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 13:23:06,647 epoch 8 - iter 594/992 - loss 0.01770378 - time (sec): 35.98 - samples/sec: 2703.27 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 13:23:13,013 epoch 8 - iter 693/992 - loss 0.01737786 - time (sec): 42.35 - samples/sec: 2700.66 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 13:23:19,165 epoch 8 - iter 792/992 - loss 0.01656451 - time (sec): 48.50 - samples/sec: 2710.43 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 13:23:25,236 epoch 8 - iter 891/992 - loss 0.01664994 - time (sec): 54.57 - samples/sec: 2708.08 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 13:23:31,064 epoch 8 - iter 990/992 - loss 0.01632570 - time (sec): 60.40 - samples/sec: 2709.31 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 13:23:31,205 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:23:31,205 EPOCH 8 done: loss 0.0163 - lr: 0.000011 | |
| 2023-10-17 13:23:34,873 DEV : loss 0.23159745335578918 - f1-score (micro avg) 0.759 | |
| 2023-10-17 13:23:34,896 saving best model | |
| 2023-10-17 13:23:35,440 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:23:41,557 epoch 9 - iter 99/992 - loss 0.00768430 - time (sec): 6.11 - samples/sec: 2721.88 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 13:23:47,443 epoch 9 - iter 198/992 - loss 0.00767863 - time (sec): 12.00 - samples/sec: 2792.73 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 13:23:53,085 epoch 9 - iter 297/992 - loss 0.00921750 - time (sec): 17.64 - samples/sec: 2774.70 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 13:23:58,924 epoch 9 - iter 396/992 - loss 0.00997090 - time (sec): 23.48 - samples/sec: 2787.79 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 13:24:04,964 epoch 9 - iter 495/992 - loss 0.01094716 - time (sec): 29.52 - samples/sec: 2776.73 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 13:24:11,173 epoch 9 - iter 594/992 - loss 0.01122230 - time (sec): 35.73 - samples/sec: 2773.13 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 13:24:16,929 epoch 9 - iter 693/992 - loss 0.01035585 - time (sec): 41.49 - samples/sec: 2762.10 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 13:24:23,057 epoch 9 - iter 792/992 - loss 0.01060860 - time (sec): 47.61 - samples/sec: 2749.82 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 13:24:29,027 epoch 9 - iter 891/992 - loss 0.01051512 - time (sec): 53.58 - samples/sec: 2744.37 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 13:24:35,147 epoch 9 - iter 990/992 - loss 0.01045569 - time (sec): 59.70 - samples/sec: 2738.58 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 13:24:35,288 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:24:35,288 EPOCH 9 done: loss 0.0106 - lr: 0.000006 | |
| 2023-10-17 13:24:39,270 DEV : loss 0.25076672434806824 - f1-score (micro avg) 0.7642 | |
| 2023-10-17 13:24:39,295 saving best model | |
| 2023-10-17 13:24:39,818 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:24:45,647 epoch 10 - iter 99/992 - loss 0.00464891 - time (sec): 5.83 - samples/sec: 2759.88 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 13:24:51,594 epoch 10 - iter 198/992 - loss 0.00654277 - time (sec): 11.77 - samples/sec: 2755.86 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 13:24:57,739 epoch 10 - iter 297/992 - loss 0.00598182 - time (sec): 17.92 - samples/sec: 2784.81 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 13:25:03,780 epoch 10 - iter 396/992 - loss 0.00599650 - time (sec): 23.96 - samples/sec: 2760.42 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 13:25:09,987 epoch 10 - iter 495/992 - loss 0.00613028 - time (sec): 30.17 - samples/sec: 2724.26 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 13:25:16,059 epoch 10 - iter 594/992 - loss 0.00732373 - time (sec): 36.24 - samples/sec: 2717.20 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 13:25:21,937 epoch 10 - iter 693/992 - loss 0.00697744 - time (sec): 42.12 - samples/sec: 2720.67 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 13:25:27,971 epoch 10 - iter 792/992 - loss 0.00723983 - time (sec): 48.15 - samples/sec: 2736.85 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 13:25:33,810 epoch 10 - iter 891/992 - loss 0.00699368 - time (sec): 53.99 - samples/sec: 2739.57 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 13:25:39,728 epoch 10 - iter 990/992 - loss 0.00715494 - time (sec): 59.91 - samples/sec: 2733.12 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 13:25:39,836 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:25:39,836 EPOCH 10 done: loss 0.0072 - lr: 0.000000 | |
| 2023-10-17 13:25:43,265 DEV : loss 0.25413334369659424 - f1-score (micro avg) 0.7654 | |
| 2023-10-17 13:25:43,286 saving best model | |
| 2023-10-17 13:25:44,230 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 13:25:44,231 Loading model from best epoch ... | |
| 2023-10-17 13:25:45,694 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 13:25:49,114 | |
| Results: | |
| - F-score (micro) 0.7775 | |
| - F-score (macro) 0.6973 | |
| - Accuracy 0.6586 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.8221 0.8534 0.8375 655 | |
| PER 0.6783 0.7848 0.7277 223 | |
| ORG 0.6082 0.4646 0.5268 127 | |
| micro avg 0.7662 0.7891 0.7775 1005 | |
| macro avg 0.7029 0.7009 0.6973 1005 | |
| weighted avg 0.7631 0.7891 0.7738 1005 | |
| 2023-10-17 13:25:49,114 ---------------------------------------------------------------------------------------------------- | |