| 2023-10-17 18:22:08,334 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:08,335 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 18:22:08,336 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:08,336 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 18:22:08,336 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:08,336 Train: 1166 sentences | |
| 2023-10-17 18:22:08,336 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 18:22:08,336 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:08,336 Training Params: | |
| 2023-10-17 18:22:08,336 - learning_rate: "3e-05" | |
| 2023-10-17 18:22:08,336 - mini_batch_size: "4" | |
| 2023-10-17 18:22:08,336 - max_epochs: "10" | |
| 2023-10-17 18:22:08,336 - shuffle: "True" | |
| 2023-10-17 18:22:08,336 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:08,336 Plugins: | |
| 2023-10-17 18:22:08,336 - TensorboardLogger | |
| 2023-10-17 18:22:08,336 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 18:22:08,336 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:08,336 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 18:22:08,336 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 18:22:08,336 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:08,336 Computation: | |
| 2023-10-17 18:22:08,336 - compute on device: cuda:0 | |
| 2023-10-17 18:22:08,336 - embedding storage: none | |
| 2023-10-17 18:22:08,337 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:08,337 Model training base path: "hmbench-newseye/fi-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 18:22:08,337 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:08,337 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:08,337 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 18:22:10,053 epoch 1 - iter 29/292 - loss 3.29075352 - time (sec): 1.71 - samples/sec: 2529.78 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:22:11,718 epoch 1 - iter 58/292 - loss 2.81746381 - time (sec): 3.38 - samples/sec: 2685.26 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:22:13,288 epoch 1 - iter 87/292 - loss 2.22634437 - time (sec): 4.95 - samples/sec: 2663.13 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:22:14,926 epoch 1 - iter 116/292 - loss 1.80283354 - time (sec): 6.59 - samples/sec: 2663.05 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:22:16,496 epoch 1 - iter 145/292 - loss 1.56272639 - time (sec): 8.16 - samples/sec: 2641.34 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:22:18,110 epoch 1 - iter 174/292 - loss 1.38891179 - time (sec): 9.77 - samples/sec: 2642.90 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:22:20,065 epoch 1 - iter 203/292 - loss 1.21331209 - time (sec): 11.73 - samples/sec: 2676.70 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:22:21,688 epoch 1 - iter 232/292 - loss 1.09882571 - time (sec): 13.35 - samples/sec: 2669.49 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:22:23,225 epoch 1 - iter 261/292 - loss 1.01402133 - time (sec): 14.89 - samples/sec: 2658.37 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:22:25,033 epoch 1 - iter 290/292 - loss 0.92983375 - time (sec): 16.70 - samples/sec: 2650.54 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:22:25,121 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:25,121 EPOCH 1 done: loss 0.9276 - lr: 0.000030 | |
| 2023-10-17 18:22:26,443 DEV : loss 0.1775444895029068 - f1-score (micro avg) 0.5148 | |
| 2023-10-17 18:22:26,450 saving best model | |
| 2023-10-17 18:22:26,868 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:28,503 epoch 2 - iter 29/292 - loss 0.19367025 - time (sec): 1.63 - samples/sec: 2651.22 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:22:30,294 epoch 2 - iter 58/292 - loss 0.28925208 - time (sec): 3.42 - samples/sec: 2797.41 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:22:31,929 epoch 2 - iter 87/292 - loss 0.25382216 - time (sec): 5.06 - samples/sec: 2779.74 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:22:33,588 epoch 2 - iter 116/292 - loss 0.23765017 - time (sec): 6.72 - samples/sec: 2748.33 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:22:35,478 epoch 2 - iter 145/292 - loss 0.22656271 - time (sec): 8.61 - samples/sec: 2709.18 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:22:37,097 epoch 2 - iter 174/292 - loss 0.21665063 - time (sec): 10.23 - samples/sec: 2637.37 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:22:38,621 epoch 2 - iter 203/292 - loss 0.20686273 - time (sec): 11.75 - samples/sec: 2643.01 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:22:40,328 epoch 2 - iter 232/292 - loss 0.20255896 - time (sec): 13.46 - samples/sec: 2662.00 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:22:41,991 epoch 2 - iter 261/292 - loss 0.19422242 - time (sec): 15.12 - samples/sec: 2642.25 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:22:43,690 epoch 2 - iter 290/292 - loss 0.19259531 - time (sec): 16.82 - samples/sec: 2623.71 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:22:43,786 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:43,786 EPOCH 2 done: loss 0.1923 - lr: 0.000027 | |
| 2023-10-17 18:22:45,082 DEV : loss 0.11384982615709305 - f1-score (micro avg) 0.6875 | |
| 2023-10-17 18:22:45,091 saving best model | |
| 2023-10-17 18:22:45,666 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:47,733 epoch 3 - iter 29/292 - loss 0.12609457 - time (sec): 2.07 - samples/sec: 2495.80 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:22:49,343 epoch 3 - iter 58/292 - loss 0.11403106 - time (sec): 3.67 - samples/sec: 2427.26 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:22:51,129 epoch 3 - iter 87/292 - loss 0.09945726 - time (sec): 5.46 - samples/sec: 2600.62 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:22:52,898 epoch 3 - iter 116/292 - loss 0.11604692 - time (sec): 7.23 - samples/sec: 2636.42 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:22:54,383 epoch 3 - iter 145/292 - loss 0.11717357 - time (sec): 8.71 - samples/sec: 2629.09 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:22:55,956 epoch 3 - iter 174/292 - loss 0.11808605 - time (sec): 10.29 - samples/sec: 2640.12 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:22:57,541 epoch 3 - iter 203/292 - loss 0.12234197 - time (sec): 11.87 - samples/sec: 2635.35 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:22:59,154 epoch 3 - iter 232/292 - loss 0.12383806 - time (sec): 13.49 - samples/sec: 2627.86 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:23:00,925 epoch 3 - iter 261/292 - loss 0.11671173 - time (sec): 15.26 - samples/sec: 2624.03 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:23:02,462 epoch 3 - iter 290/292 - loss 0.11564586 - time (sec): 16.79 - samples/sec: 2616.71 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:23:02,628 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:23:02,629 EPOCH 3 done: loss 0.1151 - lr: 0.000023 | |
| 2023-10-17 18:23:03,924 DEV : loss 0.10733965039253235 - f1-score (micro avg) 0.7304 | |
| 2023-10-17 18:23:03,930 saving best model | |
| 2023-10-17 18:23:04,410 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:23:06,273 epoch 4 - iter 29/292 - loss 0.06862492 - time (sec): 1.86 - samples/sec: 2819.48 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:23:08,027 epoch 4 - iter 58/292 - loss 0.06978255 - time (sec): 3.61 - samples/sec: 2660.66 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:23:09,753 epoch 4 - iter 87/292 - loss 0.06502896 - time (sec): 5.34 - samples/sec: 2518.04 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:23:11,418 epoch 4 - iter 116/292 - loss 0.06528685 - time (sec): 7.01 - samples/sec: 2534.77 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:23:13,378 epoch 4 - iter 145/292 - loss 0.06746468 - time (sec): 8.97 - samples/sec: 2496.87 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:23:15,096 epoch 4 - iter 174/292 - loss 0.06978266 - time (sec): 10.68 - samples/sec: 2485.01 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:23:16,777 epoch 4 - iter 203/292 - loss 0.07330462 - time (sec): 12.36 - samples/sec: 2502.00 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:23:18,682 epoch 4 - iter 232/292 - loss 0.07255344 - time (sec): 14.27 - samples/sec: 2519.53 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:23:20,390 epoch 4 - iter 261/292 - loss 0.07636325 - time (sec): 15.98 - samples/sec: 2496.08 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:23:22,272 epoch 4 - iter 290/292 - loss 0.07363746 - time (sec): 17.86 - samples/sec: 2475.07 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:23:22,372 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:23:22,372 EPOCH 4 done: loss 0.0737 - lr: 0.000020 | |
| 2023-10-17 18:23:23,974 DEV : loss 0.12645508348941803 - f1-score (micro avg) 0.7176 | |
| 2023-10-17 18:23:23,981 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:23:25,982 epoch 5 - iter 29/292 - loss 0.04528808 - time (sec): 2.00 - samples/sec: 2699.83 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:23:27,540 epoch 5 - iter 58/292 - loss 0.04526513 - time (sec): 3.56 - samples/sec: 2532.24 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:23:29,069 epoch 5 - iter 87/292 - loss 0.04063193 - time (sec): 5.09 - samples/sec: 2508.69 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:23:30,896 epoch 5 - iter 116/292 - loss 0.04159612 - time (sec): 6.91 - samples/sec: 2539.02 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:23:32,631 epoch 5 - iter 145/292 - loss 0.04703466 - time (sec): 8.65 - samples/sec: 2565.18 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:23:34,258 epoch 5 - iter 174/292 - loss 0.05258129 - time (sec): 10.28 - samples/sec: 2596.51 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:23:35,870 epoch 5 - iter 203/292 - loss 0.05073233 - time (sec): 11.89 - samples/sec: 2612.89 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:23:37,437 epoch 5 - iter 232/292 - loss 0.04940808 - time (sec): 13.46 - samples/sec: 2596.12 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:23:39,027 epoch 5 - iter 261/292 - loss 0.05129740 - time (sec): 15.05 - samples/sec: 2595.94 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:23:40,862 epoch 5 - iter 290/292 - loss 0.05371207 - time (sec): 16.88 - samples/sec: 2614.18 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:23:40,962 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:23:40,962 EPOCH 5 done: loss 0.0534 - lr: 0.000017 | |
| 2023-10-17 18:23:42,232 DEV : loss 0.11940745264291763 - f1-score (micro avg) 0.7759 | |
| 2023-10-17 18:23:42,239 saving best model | |
| 2023-10-17 18:23:42,727 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:23:44,728 epoch 6 - iter 29/292 - loss 0.06336152 - time (sec): 2.00 - samples/sec: 2809.12 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:23:46,222 epoch 6 - iter 58/292 - loss 0.04984604 - time (sec): 3.49 - samples/sec: 2664.89 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:23:48,037 epoch 6 - iter 87/292 - loss 0.04339346 - time (sec): 5.31 - samples/sec: 2646.12 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:23:49,752 epoch 6 - iter 116/292 - loss 0.04573025 - time (sec): 7.02 - samples/sec: 2690.52 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:23:51,307 epoch 6 - iter 145/292 - loss 0.04211581 - time (sec): 8.58 - samples/sec: 2648.93 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:23:53,077 epoch 6 - iter 174/292 - loss 0.04062692 - time (sec): 10.35 - samples/sec: 2636.85 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:23:54,688 epoch 6 - iter 203/292 - loss 0.03879493 - time (sec): 11.96 - samples/sec: 2612.05 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:23:56,342 epoch 6 - iter 232/292 - loss 0.04138779 - time (sec): 13.61 - samples/sec: 2617.60 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:23:57,903 epoch 6 - iter 261/292 - loss 0.03921456 - time (sec): 15.17 - samples/sec: 2635.69 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:23:59,507 epoch 6 - iter 290/292 - loss 0.03847237 - time (sec): 16.78 - samples/sec: 2629.93 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:23:59,620 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:23:59,620 EPOCH 6 done: loss 0.0383 - lr: 0.000013 | |
| 2023-10-17 18:24:00,937 DEV : loss 0.1452915370464325 - f1-score (micro avg) 0.7638 | |
| 2023-10-17 18:24:00,945 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:02,863 epoch 7 - iter 29/292 - loss 0.01800297 - time (sec): 1.92 - samples/sec: 2613.26 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:24:04,612 epoch 7 - iter 58/292 - loss 0.02732078 - time (sec): 3.67 - samples/sec: 2476.56 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:24:06,343 epoch 7 - iter 87/292 - loss 0.02475918 - time (sec): 5.40 - samples/sec: 2476.61 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:24:08,295 epoch 7 - iter 116/292 - loss 0.02385267 - time (sec): 7.35 - samples/sec: 2503.29 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:24:10,151 epoch 7 - iter 145/292 - loss 0.02314634 - time (sec): 9.20 - samples/sec: 2530.23 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:24:12,025 epoch 7 - iter 174/292 - loss 0.02813068 - time (sec): 11.08 - samples/sec: 2523.76 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:24:13,510 epoch 7 - iter 203/292 - loss 0.02705599 - time (sec): 12.56 - samples/sec: 2491.99 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:24:15,209 epoch 7 - iter 232/292 - loss 0.02818280 - time (sec): 14.26 - samples/sec: 2494.83 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:24:16,833 epoch 7 - iter 261/292 - loss 0.03043653 - time (sec): 15.89 - samples/sec: 2520.51 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:24:18,505 epoch 7 - iter 290/292 - loss 0.02929832 - time (sec): 17.56 - samples/sec: 2519.15 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:24:18,596 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:18,597 EPOCH 7 done: loss 0.0292 - lr: 0.000010 | |
| 2023-10-17 18:24:19,886 DEV : loss 0.1461927443742752 - f1-score (micro avg) 0.7742 | |
| 2023-10-17 18:24:19,891 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:21,646 epoch 8 - iter 29/292 - loss 0.03964611 - time (sec): 1.75 - samples/sec: 2658.25 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:24:23,335 epoch 8 - iter 58/292 - loss 0.03889202 - time (sec): 3.44 - samples/sec: 2646.02 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:24:25,092 epoch 8 - iter 87/292 - loss 0.02958935 - time (sec): 5.20 - samples/sec: 2789.28 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:24:26,913 epoch 8 - iter 116/292 - loss 0.02593733 - time (sec): 7.02 - samples/sec: 2775.65 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:24:28,631 epoch 8 - iter 145/292 - loss 0.02276293 - time (sec): 8.74 - samples/sec: 2748.87 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:24:30,309 epoch 8 - iter 174/292 - loss 0.01998816 - time (sec): 10.42 - samples/sec: 2708.65 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:24:31,954 epoch 8 - iter 203/292 - loss 0.01899104 - time (sec): 12.06 - samples/sec: 2670.48 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:24:33,562 epoch 8 - iter 232/292 - loss 0.01835548 - time (sec): 13.67 - samples/sec: 2619.08 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:24:35,287 epoch 8 - iter 261/292 - loss 0.01831061 - time (sec): 15.39 - samples/sec: 2611.58 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:24:37,075 epoch 8 - iter 290/292 - loss 0.02306213 - time (sec): 17.18 - samples/sec: 2580.44 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:24:37,178 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:37,179 EPOCH 8 done: loss 0.0230 - lr: 0.000007 | |
| 2023-10-17 18:24:38,457 DEV : loss 0.16589583456516266 - f1-score (micro avg) 0.7576 | |
| 2023-10-17 18:24:38,463 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:40,345 epoch 9 - iter 29/292 - loss 0.01221716 - time (sec): 1.88 - samples/sec: 2532.17 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:24:42,286 epoch 9 - iter 58/292 - loss 0.01392285 - time (sec): 3.82 - samples/sec: 2575.67 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:24:44,059 epoch 9 - iter 87/292 - loss 0.01599142 - time (sec): 5.59 - samples/sec: 2575.62 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:24:45,697 epoch 9 - iter 116/292 - loss 0.01608586 - time (sec): 7.23 - samples/sec: 2530.87 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:24:47,691 epoch 9 - iter 145/292 - loss 0.01384258 - time (sec): 9.23 - samples/sec: 2501.83 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:24:49,376 epoch 9 - iter 174/292 - loss 0.01495323 - time (sec): 10.91 - samples/sec: 2523.02 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:24:50,967 epoch 9 - iter 203/292 - loss 0.01795553 - time (sec): 12.50 - samples/sec: 2506.00 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:24:52,554 epoch 9 - iter 232/292 - loss 0.01783076 - time (sec): 14.09 - samples/sec: 2476.96 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:24:54,238 epoch 9 - iter 261/292 - loss 0.01670887 - time (sec): 15.77 - samples/sec: 2509.78 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:24:55,939 epoch 9 - iter 290/292 - loss 0.01876896 - time (sec): 17.48 - samples/sec: 2524.52 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:24:56,043 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:56,043 EPOCH 9 done: loss 0.0186 - lr: 0.000003 | |
| 2023-10-17 18:24:57,544 DEV : loss 0.1677304357290268 - f1-score (micro avg) 0.7592 | |
| 2023-10-17 18:24:57,549 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:59,366 epoch 10 - iter 29/292 - loss 0.00784158 - time (sec): 1.82 - samples/sec: 2728.00 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:25:01,066 epoch 10 - iter 58/292 - loss 0.02249789 - time (sec): 3.52 - samples/sec: 2635.67 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:25:02,622 epoch 10 - iter 87/292 - loss 0.02059791 - time (sec): 5.07 - samples/sec: 2559.88 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:25:04,353 epoch 10 - iter 116/292 - loss 0.02078976 - time (sec): 6.80 - samples/sec: 2614.57 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:25:06,078 epoch 10 - iter 145/292 - loss 0.01755985 - time (sec): 8.53 - samples/sec: 2630.15 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:25:07,773 epoch 10 - iter 174/292 - loss 0.01454950 - time (sec): 10.22 - samples/sec: 2670.86 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:25:09,340 epoch 10 - iter 203/292 - loss 0.01411050 - time (sec): 11.79 - samples/sec: 2663.23 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:25:10,842 epoch 10 - iter 232/292 - loss 0.01338063 - time (sec): 13.29 - samples/sec: 2664.45 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:25:12,449 epoch 10 - iter 261/292 - loss 0.01542384 - time (sec): 14.90 - samples/sec: 2666.82 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 18:25:14,092 epoch 10 - iter 290/292 - loss 0.01437749 - time (sec): 16.54 - samples/sec: 2670.08 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 18:25:14,205 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:14,205 EPOCH 10 done: loss 0.0149 - lr: 0.000000 | |
| 2023-10-17 18:25:15,518 DEV : loss 0.16656455397605896 - f1-score (micro avg) 0.7686 | |
| 2023-10-17 18:25:15,903 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:25:15,904 Loading model from best epoch ... | |
| 2023-10-17 18:25:18,148 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 18:25:21,021 | |
| Results: | |
| - F-score (micro) 0.757 | |
| - F-score (macro) 0.6877 | |
| - Accuracy 0.6327 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.7801 0.8563 0.8164 348 | |
| LOC 0.6565 0.8276 0.7322 261 | |
| ORG 0.5116 0.4231 0.4632 52 | |
| HumanProd 0.7083 0.7727 0.7391 22 | |
| micro avg 0.7108 0.8097 0.7570 683 | |
| macro avg 0.6642 0.7199 0.6877 683 | |
| weighted avg 0.7101 0.8097 0.7549 683 | |
| 2023-10-17 18:25:21,021 ---------------------------------------------------------------------------------------------------- | |