| 2023-10-17 18:32:42,717 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:42,719 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 18:32:42,719 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:42,719 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 18:32:42,719 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:42,719 Train: 1166 sentences | |
| 2023-10-17 18:32:42,719 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 18:32:42,719 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:42,719 Training Params: | |
| 2023-10-17 18:32:42,719 - learning_rate: "5e-05" | |
| 2023-10-17 18:32:42,719 - mini_batch_size: "8" | |
| 2023-10-17 18:32:42,719 - max_epochs: "10" | |
| 2023-10-17 18:32:42,719 - shuffle: "True" | |
| 2023-10-17 18:32:42,719 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:42,719 Plugins: | |
| 2023-10-17 18:32:42,719 - TensorboardLogger | |
| 2023-10-17 18:32:42,719 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 18:32:42,719 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:42,719 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 18:32:42,719 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 18:32:42,719 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:42,719 Computation: | |
| 2023-10-17 18:32:42,719 - compute on device: cuda:0 | |
| 2023-10-17 18:32:42,719 - embedding storage: none | |
| 2023-10-17 18:32:42,719 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:42,720 Model training base path: "hmbench-newseye/fi-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 18:32:42,720 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:42,720 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:42,720 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 18:32:44,237 epoch 1 - iter 14/146 - loss 3.44721500 - time (sec): 1.52 - samples/sec: 2772.49 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:32:45,581 epoch 1 - iter 28/146 - loss 3.01929126 - time (sec): 2.86 - samples/sec: 2955.98 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:32:47,142 epoch 1 - iter 42/146 - loss 2.43085235 - time (sec): 4.42 - samples/sec: 2879.15 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:32:48,528 epoch 1 - iter 56/146 - loss 1.99245657 - time (sec): 5.81 - samples/sec: 2860.18 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:32:50,024 epoch 1 - iter 70/146 - loss 1.68208133 - time (sec): 7.30 - samples/sec: 2856.46 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:32:51,369 epoch 1 - iter 84/146 - loss 1.49120249 - time (sec): 8.65 - samples/sec: 2896.45 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:32:53,228 epoch 1 - iter 98/146 - loss 1.31372117 - time (sec): 10.51 - samples/sec: 2851.91 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 18:32:54,696 epoch 1 - iter 112/146 - loss 1.17868847 - time (sec): 11.98 - samples/sec: 2877.10 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 18:32:55,929 epoch 1 - iter 126/146 - loss 1.08469627 - time (sec): 13.21 - samples/sec: 2896.82 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 18:32:57,204 epoch 1 - iter 140/146 - loss 1.01543642 - time (sec): 14.48 - samples/sec: 2889.85 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 18:32:58,041 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:32:58,041 EPOCH 1 done: loss 0.9658 - lr: 0.000048 | |
| 2023-10-17 18:32:59,291 DEV : loss 0.18053634464740753 - f1-score (micro avg) 0.4883 | |
| 2023-10-17 18:32:59,298 saving best model | |
| 2023-10-17 18:32:59,712 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:33:01,122 epoch 2 - iter 14/146 - loss 0.19521870 - time (sec): 1.41 - samples/sec: 2989.49 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-17 18:33:02,779 epoch 2 - iter 28/146 - loss 0.26696941 - time (sec): 3.06 - samples/sec: 2979.34 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 18:33:04,231 epoch 2 - iter 42/146 - loss 0.24556875 - time (sec): 4.52 - samples/sec: 3011.47 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 18:33:05,768 epoch 2 - iter 56/146 - loss 0.22549833 - time (sec): 6.05 - samples/sec: 2988.86 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 18:33:07,648 epoch 2 - iter 70/146 - loss 0.21672435 - time (sec): 7.93 - samples/sec: 2849.12 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 18:33:08,979 epoch 2 - iter 84/146 - loss 0.20594215 - time (sec): 9.26 - samples/sec: 2819.20 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 18:33:10,328 epoch 2 - iter 98/146 - loss 0.20138047 - time (sec): 10.61 - samples/sec: 2831.38 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 18:33:11,876 epoch 2 - iter 112/146 - loss 0.19331625 - time (sec): 12.16 - samples/sec: 2836.85 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 18:33:13,396 epoch 2 - iter 126/146 - loss 0.18895690 - time (sec): 13.68 - samples/sec: 2833.45 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 18:33:14,789 epoch 2 - iter 140/146 - loss 0.18610808 - time (sec): 15.08 - samples/sec: 2816.05 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 18:33:15,502 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:33:15,502 EPOCH 2 done: loss 0.1847 - lr: 0.000045 | |
| 2023-10-17 18:33:16,756 DEV : loss 0.11022156476974487 - f1-score (micro avg) 0.6517 | |
| 2023-10-17 18:33:16,761 saving best model | |
| 2023-10-17 18:33:17,198 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:33:18,831 epoch 3 - iter 14/146 - loss 0.13107967 - time (sec): 1.63 - samples/sec: 3074.78 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 18:33:20,000 epoch 3 - iter 28/146 - loss 0.12321225 - time (sec): 2.80 - samples/sec: 3129.35 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 18:33:21,626 epoch 3 - iter 42/146 - loss 0.10417679 - time (sec): 4.43 - samples/sec: 3090.88 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 18:33:23,095 epoch 3 - iter 56/146 - loss 0.11353587 - time (sec): 5.89 - samples/sec: 3049.43 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 18:33:24,480 epoch 3 - iter 70/146 - loss 0.11292059 - time (sec): 7.28 - samples/sec: 3088.21 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 18:33:25,660 epoch 3 - iter 84/146 - loss 0.11525650 - time (sec): 8.46 - samples/sec: 3084.38 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 18:33:27,132 epoch 3 - iter 98/146 - loss 0.11750890 - time (sec): 9.93 - samples/sec: 3075.07 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 18:33:28,580 epoch 3 - iter 112/146 - loss 0.11798660 - time (sec): 11.38 - samples/sec: 3030.07 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 18:33:29,970 epoch 3 - iter 126/146 - loss 0.11282492 - time (sec): 12.77 - samples/sec: 3020.79 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 18:33:31,273 epoch 3 - iter 140/146 - loss 0.10978467 - time (sec): 14.07 - samples/sec: 3036.73 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 18:33:31,853 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:33:31,854 EPOCH 3 done: loss 0.1075 - lr: 0.000039 | |
| 2023-10-17 18:33:33,152 DEV : loss 0.1118723452091217 - f1-score (micro avg) 0.7425 | |
| 2023-10-17 18:33:33,160 saving best model | |
| 2023-10-17 18:33:33,735 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:33:35,365 epoch 4 - iter 14/146 - loss 0.08288392 - time (sec): 1.63 - samples/sec: 3088.56 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 18:33:36,817 epoch 4 - iter 28/146 - loss 0.07072301 - time (sec): 3.08 - samples/sec: 3044.62 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 18:33:38,186 epoch 4 - iter 42/146 - loss 0.06783415 - time (sec): 4.45 - samples/sec: 2941.34 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 18:33:39,817 epoch 4 - iter 56/146 - loss 0.06713406 - time (sec): 6.08 - samples/sec: 2807.96 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 18:33:41,638 epoch 4 - iter 70/146 - loss 0.06785787 - time (sec): 7.90 - samples/sec: 2747.44 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 18:33:43,030 epoch 4 - iter 84/146 - loss 0.07005552 - time (sec): 9.29 - samples/sec: 2732.78 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 18:33:44,485 epoch 4 - iter 98/146 - loss 0.07304693 - time (sec): 10.75 - samples/sec: 2759.73 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 18:33:46,178 epoch 4 - iter 112/146 - loss 0.07014498 - time (sec): 12.44 - samples/sec: 2756.18 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 18:33:47,585 epoch 4 - iter 126/146 - loss 0.07006272 - time (sec): 13.85 - samples/sec: 2786.75 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 18:33:49,152 epoch 4 - iter 140/146 - loss 0.07019238 - time (sec): 15.41 - samples/sec: 2790.11 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 18:33:49,706 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:33:49,706 EPOCH 4 done: loss 0.0690 - lr: 0.000034 | |
| 2023-10-17 18:33:50,933 DEV : loss 0.10351864993572235 - f1-score (micro avg) 0.7398 | |
| 2023-10-17 18:33:50,938 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:33:52,938 epoch 5 - iter 14/146 - loss 0.04384680 - time (sec): 2.00 - samples/sec: 2628.61 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 18:33:54,137 epoch 5 - iter 28/146 - loss 0.04534817 - time (sec): 3.20 - samples/sec: 2691.58 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 18:33:55,438 epoch 5 - iter 42/146 - loss 0.04253725 - time (sec): 4.50 - samples/sec: 2715.69 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 18:33:57,098 epoch 5 - iter 56/146 - loss 0.04253393 - time (sec): 6.16 - samples/sec: 2697.89 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 18:33:58,628 epoch 5 - iter 70/146 - loss 0.04450004 - time (sec): 7.69 - samples/sec: 2802.33 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 18:33:59,988 epoch 5 - iter 84/146 - loss 0.04818641 - time (sec): 9.05 - samples/sec: 2850.62 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:34:01,363 epoch 5 - iter 98/146 - loss 0.04677106 - time (sec): 10.42 - samples/sec: 2848.72 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:34:02,648 epoch 5 - iter 112/146 - loss 0.04521279 - time (sec): 11.71 - samples/sec: 2864.81 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:34:04,034 epoch 5 - iter 126/146 - loss 0.04712952 - time (sec): 13.09 - samples/sec: 2889.35 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:34:05,510 epoch 5 - iter 140/146 - loss 0.04798974 - time (sec): 14.57 - samples/sec: 2921.07 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:34:06,203 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:34:06,203 EPOCH 5 done: loss 0.0466 - lr: 0.000028 | |
| 2023-10-17 18:34:07,478 DEV : loss 0.10968425124883652 - f1-score (micro avg) 0.7361 | |
| 2023-10-17 18:34:07,485 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:34:09,419 epoch 6 - iter 14/146 - loss 0.03514218 - time (sec): 1.93 - samples/sec: 2846.19 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:34:10,591 epoch 6 - iter 28/146 - loss 0.03242432 - time (sec): 3.10 - samples/sec: 2953.00 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:34:12,157 epoch 6 - iter 42/146 - loss 0.03032983 - time (sec): 4.67 - samples/sec: 2890.26 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:34:13,700 epoch 6 - iter 56/146 - loss 0.02748075 - time (sec): 6.21 - samples/sec: 2901.94 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:34:15,088 epoch 6 - iter 70/146 - loss 0.02612346 - time (sec): 7.60 - samples/sec: 2909.63 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:34:16,503 epoch 6 - iter 84/146 - loss 0.02494045 - time (sec): 9.02 - samples/sec: 2879.71 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:34:17,930 epoch 6 - iter 98/146 - loss 0.02559131 - time (sec): 10.44 - samples/sec: 2895.53 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:34:19,504 epoch 6 - iter 112/146 - loss 0.02864853 - time (sec): 12.02 - samples/sec: 2887.29 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:34:20,811 epoch 6 - iter 126/146 - loss 0.02888129 - time (sec): 13.32 - samples/sec: 2910.47 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:34:22,186 epoch 6 - iter 140/146 - loss 0.02827654 - time (sec): 14.70 - samples/sec: 2910.93 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:34:22,693 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:34:22,693 EPOCH 6 done: loss 0.0290 - lr: 0.000023 | |
| 2023-10-17 18:34:24,038 DEV : loss 0.11068177223205566 - f1-score (micro avg) 0.7696 | |
| 2023-10-17 18:34:24,044 saving best model | |
| 2023-10-17 18:34:24,678 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:34:26,356 epoch 7 - iter 14/146 - loss 0.02230428 - time (sec): 1.68 - samples/sec: 2924.12 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:34:27,874 epoch 7 - iter 28/146 - loss 0.02787918 - time (sec): 3.19 - samples/sec: 2805.98 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:34:29,163 epoch 7 - iter 42/146 - loss 0.02138936 - time (sec): 4.48 - samples/sec: 2914.64 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:34:30,745 epoch 7 - iter 56/146 - loss 0.02189885 - time (sec): 6.06 - samples/sec: 2950.23 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:34:32,131 epoch 7 - iter 70/146 - loss 0.02030357 - time (sec): 7.45 - samples/sec: 2980.81 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:34:33,791 epoch 7 - iter 84/146 - loss 0.02090295 - time (sec): 9.11 - samples/sec: 2944.88 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:34:35,159 epoch 7 - iter 98/146 - loss 0.02278254 - time (sec): 10.48 - samples/sec: 2894.81 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:34:36,554 epoch 7 - iter 112/146 - loss 0.02456466 - time (sec): 11.87 - samples/sec: 2893.26 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:34:37,907 epoch 7 - iter 126/146 - loss 0.02333651 - time (sec): 13.23 - samples/sec: 2895.98 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:34:39,713 epoch 7 - iter 140/146 - loss 0.02205748 - time (sec): 15.03 - samples/sec: 2853.68 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:34:40,279 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:34:40,279 EPOCH 7 done: loss 0.0224 - lr: 0.000017 | |
| 2023-10-17 18:34:41,555 DEV : loss 0.11937715113162994 - f1-score (micro avg) 0.7716 | |
| 2023-10-17 18:34:41,560 saving best model | |
| 2023-10-17 18:34:42,061 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:34:43,547 epoch 8 - iter 14/146 - loss 0.02757955 - time (sec): 1.48 - samples/sec: 2973.09 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:34:45,020 epoch 8 - iter 28/146 - loss 0.02223759 - time (sec): 2.96 - samples/sec: 2910.84 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:34:46,608 epoch 8 - iter 42/146 - loss 0.01936289 - time (sec): 4.54 - samples/sec: 3095.57 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:34:48,219 epoch 8 - iter 56/146 - loss 0.01619699 - time (sec): 6.15 - samples/sec: 3060.94 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:34:49,574 epoch 8 - iter 70/146 - loss 0.01338593 - time (sec): 7.51 - samples/sec: 3081.20 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:34:51,018 epoch 8 - iter 84/146 - loss 0.01288682 - time (sec): 8.95 - samples/sec: 3035.27 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:34:52,559 epoch 8 - iter 98/146 - loss 0.01281177 - time (sec): 10.50 - samples/sec: 2979.26 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:34:53,900 epoch 8 - iter 112/146 - loss 0.01343863 - time (sec): 11.84 - samples/sec: 2940.78 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:34:55,230 epoch 8 - iter 126/146 - loss 0.01305752 - time (sec): 13.17 - samples/sec: 2950.47 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:34:56,904 epoch 8 - iter 140/146 - loss 0.01765526 - time (sec): 14.84 - samples/sec: 2913.93 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:34:57,379 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:34:57,380 EPOCH 8 done: loss 0.0178 - lr: 0.000012 | |
| 2023-10-17 18:34:58,661 DEV : loss 0.12875597178936005 - f1-score (micro avg) 0.777 | |
| 2023-10-17 18:34:58,666 saving best model | |
| 2023-10-17 18:34:59,170 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:35:00,731 epoch 9 - iter 14/146 - loss 0.00793277 - time (sec): 1.56 - samples/sec: 2907.10 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:35:02,406 epoch 9 - iter 28/146 - loss 0.00780084 - time (sec): 3.23 - samples/sec: 2933.67 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:35:04,010 epoch 9 - iter 42/146 - loss 0.01119877 - time (sec): 4.84 - samples/sec: 2873.66 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:35:05,275 epoch 9 - iter 56/146 - loss 0.01053210 - time (sec): 6.10 - samples/sec: 2916.89 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:35:07,113 epoch 9 - iter 70/146 - loss 0.00945729 - time (sec): 7.94 - samples/sec: 2821.79 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:35:08,599 epoch 9 - iter 84/146 - loss 0.01012236 - time (sec): 9.43 - samples/sec: 2818.25 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:35:09,990 epoch 9 - iter 98/146 - loss 0.01351672 - time (sec): 10.82 - samples/sec: 2823.37 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:35:11,228 epoch 9 - iter 112/146 - loss 0.01405738 - time (sec): 12.06 - samples/sec: 2807.34 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:35:12,890 epoch 9 - iter 126/146 - loss 0.01276090 - time (sec): 13.72 - samples/sec: 2802.31 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:35:14,457 epoch 9 - iter 140/146 - loss 0.01273768 - time (sec): 15.29 - samples/sec: 2801.19 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:35:15,060 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:35:15,060 EPOCH 9 done: loss 0.0124 - lr: 0.000006 | |
| 2023-10-17 18:35:16,339 DEV : loss 0.12694209814071655 - f1-score (micro avg) 0.7815 | |
| 2023-10-17 18:35:16,344 saving best model | |
| 2023-10-17 18:35:16,844 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:35:18,562 epoch 10 - iter 14/146 - loss 0.00354045 - time (sec): 1.72 - samples/sec: 2833.65 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:35:19,975 epoch 10 - iter 28/146 - loss 0.01183736 - time (sec): 3.13 - samples/sec: 2855.53 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:35:21,397 epoch 10 - iter 42/146 - loss 0.01452345 - time (sec): 4.55 - samples/sec: 2763.23 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:35:22,965 epoch 10 - iter 56/146 - loss 0.01324616 - time (sec): 6.12 - samples/sec: 2797.27 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:35:24,599 epoch 10 - iter 70/146 - loss 0.01119466 - time (sec): 7.75 - samples/sec: 2804.22 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:35:25,980 epoch 10 - iter 84/146 - loss 0.00937811 - time (sec): 9.13 - samples/sec: 2872.00 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:35:27,520 epoch 10 - iter 98/146 - loss 0.00961423 - time (sec): 10.67 - samples/sec: 2849.67 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:35:29,048 epoch 10 - iter 112/146 - loss 0.00861973 - time (sec): 12.20 - samples/sec: 2815.11 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:35:30,426 epoch 10 - iter 126/146 - loss 0.00888169 - time (sec): 13.58 - samples/sec: 2829.81 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:35:31,841 epoch 10 - iter 140/146 - loss 0.00956492 - time (sec): 15.00 - samples/sec: 2845.01 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 18:35:32,503 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:35:32,504 EPOCH 10 done: loss 0.0097 - lr: 0.000000 | |
| 2023-10-17 18:35:33,785 DEV : loss 0.12970572710037231 - f1-score (micro avg) 0.7652 | |
| 2023-10-17 18:35:34,173 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:35:34,174 Loading model from best epoch ... | |
| 2023-10-17 18:35:35,857 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 18:35:38,423 | |
| Results: | |
| - F-score (micro) 0.7632 | |
| - F-score (macro) 0.6905 | |
| - Accuracy 0.6391 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.8137 0.8534 0.8331 348 | |
| LOC 0.6478 0.8314 0.7282 261 | |
| ORG 0.5333 0.4615 0.4948 52 | |
| HumanProd 0.6207 0.8182 0.7059 22 | |
| micro avg 0.7183 0.8141 0.7632 683 | |
| macro avg 0.6539 0.7411 0.6905 683 | |
| weighted avg 0.7227 0.8141 0.7632 683 | |
| 2023-10-17 18:35:38,423 ---------------------------------------------------------------------------------------------------- | |