| 2023-10-17 18:08:20,831 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:20,832 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 18:08:20,832 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:20,832 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 18:08:20,832 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:20,832 Train: 1166 sentences | |
| 2023-10-17 18:08:20,832 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 18:08:20,832 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:20,832 Training Params: | |
| 2023-10-17 18:08:20,832 - learning_rate: "3e-05" | |
| 2023-10-17 18:08:20,832 - mini_batch_size: "4" | |
| 2023-10-17 18:08:20,832 - max_epochs: "10" | |
| 2023-10-17 18:08:20,832 - shuffle: "True" | |
| 2023-10-17 18:08:20,832 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:20,832 Plugins: | |
| 2023-10-17 18:08:20,832 - TensorboardLogger | |
| 2023-10-17 18:08:20,832 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 18:08:20,832 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:20,832 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 18:08:20,832 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 18:08:20,832 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:20,832 Computation: | |
| 2023-10-17 18:08:20,832 - compute on device: cuda:0 | |
| 2023-10-17 18:08:20,832 - embedding storage: none | |
| 2023-10-17 18:08:20,833 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:20,833 Model training base path: "hmbench-newseye/fi-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4" | |
| 2023-10-17 18:08:20,833 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:20,833 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:20,833 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 18:08:22,668 epoch 1 - iter 29/292 - loss 3.83095474 - time (sec): 1.83 - samples/sec: 2821.52 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:08:24,296 epoch 1 - iter 58/292 - loss 3.23658540 - time (sec): 3.46 - samples/sec: 2713.21 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:08:25,947 epoch 1 - iter 87/292 - loss 2.54606603 - time (sec): 5.11 - samples/sec: 2640.12 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:08:27,753 epoch 1 - iter 116/292 - loss 2.06575240 - time (sec): 6.92 - samples/sec: 2708.68 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:08:29,506 epoch 1 - iter 145/292 - loss 1.72231768 - time (sec): 8.67 - samples/sec: 2751.32 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:08:31,136 epoch 1 - iter 174/292 - loss 1.52369828 - time (sec): 10.30 - samples/sec: 2745.06 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:08:32,635 epoch 1 - iter 203/292 - loss 1.39043738 - time (sec): 11.80 - samples/sec: 2745.15 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:08:34,112 epoch 1 - iter 232/292 - loss 1.27968694 - time (sec): 13.28 - samples/sec: 2716.28 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:08:35,587 epoch 1 - iter 261/292 - loss 1.19004896 - time (sec): 14.75 - samples/sec: 2691.85 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:08:37,377 epoch 1 - iter 290/292 - loss 1.09299373 - time (sec): 16.54 - samples/sec: 2678.21 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:08:37,468 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:37,469 EPOCH 1 done: loss 1.0906 - lr: 0.000030 | |
| 2023-10-17 18:08:38,354 DEV : loss 0.18845295906066895 - f1-score (micro avg) 0.4088 | |
| 2023-10-17 18:08:38,363 saving best model | |
| 2023-10-17 18:08:38,787 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:40,590 epoch 2 - iter 29/292 - loss 0.23954317 - time (sec): 1.80 - samples/sec: 2710.24 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:08:42,259 epoch 2 - iter 58/292 - loss 0.21325555 - time (sec): 3.47 - samples/sec: 2631.21 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:08:43,845 epoch 2 - iter 87/292 - loss 0.21658595 - time (sec): 5.05 - samples/sec: 2615.84 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:08:45,581 epoch 2 - iter 116/292 - loss 0.22084222 - time (sec): 6.79 - samples/sec: 2590.21 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:08:47,197 epoch 2 - iter 145/292 - loss 0.21637883 - time (sec): 8.41 - samples/sec: 2611.73 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:08:49,047 epoch 2 - iter 174/292 - loss 0.20713289 - time (sec): 10.26 - samples/sec: 2651.82 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:08:50,795 epoch 2 - iter 203/292 - loss 0.19540900 - time (sec): 12.00 - samples/sec: 2695.67 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:08:52,425 epoch 2 - iter 232/292 - loss 0.19774814 - time (sec): 13.63 - samples/sec: 2678.32 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:08:54,129 epoch 2 - iter 261/292 - loss 0.19336878 - time (sec): 15.34 - samples/sec: 2651.92 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:08:55,633 epoch 2 - iter 290/292 - loss 0.18836344 - time (sec): 16.84 - samples/sec: 2625.39 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:08:55,724 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:55,724 EPOCH 2 done: loss 0.1893 - lr: 0.000027 | |
| 2023-10-17 18:08:57,214 DEV : loss 0.12409567087888718 - f1-score (micro avg) 0.7039 | |
| 2023-10-17 18:08:57,222 saving best model | |
| 2023-10-17 18:08:57,674 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:08:59,473 epoch 3 - iter 29/292 - loss 0.10343379 - time (sec): 1.79 - samples/sec: 2569.81 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:09:01,112 epoch 3 - iter 58/292 - loss 0.10878038 - time (sec): 3.43 - samples/sec: 2664.32 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:09:02,742 epoch 3 - iter 87/292 - loss 0.11194346 - time (sec): 5.06 - samples/sec: 2556.99 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:09:04,578 epoch 3 - iter 116/292 - loss 0.10777722 - time (sec): 6.90 - samples/sec: 2630.96 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:09:06,197 epoch 3 - iter 145/292 - loss 0.10578385 - time (sec): 8.52 - samples/sec: 2640.27 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:09:07,680 epoch 3 - iter 174/292 - loss 0.10165213 - time (sec): 10.00 - samples/sec: 2607.74 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:09:09,448 epoch 3 - iter 203/292 - loss 0.10049750 - time (sec): 11.77 - samples/sec: 2656.01 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:09:11,008 epoch 3 - iter 232/292 - loss 0.10804139 - time (sec): 13.33 - samples/sec: 2645.16 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:09:12,756 epoch 3 - iter 261/292 - loss 0.11308089 - time (sec): 15.08 - samples/sec: 2670.35 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:09:14,328 epoch 3 - iter 290/292 - loss 0.11125189 - time (sec): 16.65 - samples/sec: 2657.12 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:09:14,420 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:09:14,420 EPOCH 3 done: loss 0.1109 - lr: 0.000023 | |
| 2023-10-17 18:09:15,677 DEV : loss 0.1368805170059204 - f1-score (micro avg) 0.7664 | |
| 2023-10-17 18:09:15,683 saving best model | |
| 2023-10-17 18:09:16,127 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:09:17,772 epoch 4 - iter 29/292 - loss 0.07602933 - time (sec): 1.64 - samples/sec: 2710.92 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:09:19,506 epoch 4 - iter 58/292 - loss 0.06899111 - time (sec): 3.38 - samples/sec: 2704.75 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:09:21,191 epoch 4 - iter 87/292 - loss 0.06879207 - time (sec): 5.06 - samples/sec: 2690.07 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:09:22,832 epoch 4 - iter 116/292 - loss 0.06850169 - time (sec): 6.70 - samples/sec: 2615.43 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:09:24,556 epoch 4 - iter 145/292 - loss 0.06645933 - time (sec): 8.43 - samples/sec: 2638.53 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:09:26,057 epoch 4 - iter 174/292 - loss 0.06576952 - time (sec): 9.93 - samples/sec: 2611.46 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:09:27,849 epoch 4 - iter 203/292 - loss 0.07071067 - time (sec): 11.72 - samples/sec: 2638.15 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:09:29,650 epoch 4 - iter 232/292 - loss 0.07305983 - time (sec): 13.52 - samples/sec: 2644.58 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:09:31,248 epoch 4 - iter 261/292 - loss 0.07376713 - time (sec): 15.12 - samples/sec: 2625.02 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:09:32,875 epoch 4 - iter 290/292 - loss 0.07138872 - time (sec): 16.75 - samples/sec: 2643.47 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:09:32,964 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:09:32,964 EPOCH 4 done: loss 0.0712 - lr: 0.000020 | |
| 2023-10-17 18:09:34,213 DEV : loss 0.10807133466005325 - f1-score (micro avg) 0.7623 | |
| 2023-10-17 18:09:34,222 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:09:35,831 epoch 5 - iter 29/292 - loss 0.05834853 - time (sec): 1.61 - samples/sec: 2385.75 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:09:37,492 epoch 5 - iter 58/292 - loss 0.05588902 - time (sec): 3.27 - samples/sec: 2556.16 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:09:39,195 epoch 5 - iter 87/292 - loss 0.04660830 - time (sec): 4.97 - samples/sec: 2644.73 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:09:40,748 epoch 5 - iter 116/292 - loss 0.04283946 - time (sec): 6.52 - samples/sec: 2595.41 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:09:42,451 epoch 5 - iter 145/292 - loss 0.04946763 - time (sec): 8.23 - samples/sec: 2632.15 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:09:44,177 epoch 5 - iter 174/292 - loss 0.05168536 - time (sec): 9.95 - samples/sec: 2635.84 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:09:45,728 epoch 5 - iter 203/292 - loss 0.05007307 - time (sec): 11.50 - samples/sec: 2659.48 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:09:47,189 epoch 5 - iter 232/292 - loss 0.05154864 - time (sec): 12.97 - samples/sec: 2627.91 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:09:48,832 epoch 5 - iter 261/292 - loss 0.05190958 - time (sec): 14.61 - samples/sec: 2642.78 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:09:50,727 epoch 5 - iter 290/292 - loss 0.04837098 - time (sec): 16.50 - samples/sec: 2671.02 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:09:50,865 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:09:50,866 EPOCH 5 done: loss 0.0480 - lr: 0.000017 | |
| 2023-10-17 18:09:52,174 DEV : loss 0.14370526373386383 - f1-score (micro avg) 0.7589 | |
| 2023-10-17 18:09:52,182 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:09:53,762 epoch 6 - iter 29/292 - loss 0.02581687 - time (sec): 1.58 - samples/sec: 2547.80 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:09:55,422 epoch 6 - iter 58/292 - loss 0.02827170 - time (sec): 3.24 - samples/sec: 2570.39 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:09:57,156 epoch 6 - iter 87/292 - loss 0.02844652 - time (sec): 4.97 - samples/sec: 2620.17 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:09:58,882 epoch 6 - iter 116/292 - loss 0.03172945 - time (sec): 6.70 - samples/sec: 2642.15 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:10:00,513 epoch 6 - iter 145/292 - loss 0.03178169 - time (sec): 8.33 - samples/sec: 2614.11 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:10:02,214 epoch 6 - iter 174/292 - loss 0.03164753 - time (sec): 10.03 - samples/sec: 2592.78 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:10:03,769 epoch 6 - iter 203/292 - loss 0.03087760 - time (sec): 11.59 - samples/sec: 2624.66 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:10:05,645 epoch 6 - iter 232/292 - loss 0.03350463 - time (sec): 13.46 - samples/sec: 2650.21 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:10:07,312 epoch 6 - iter 261/292 - loss 0.03346027 - time (sec): 15.13 - samples/sec: 2651.04 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:10:08,915 epoch 6 - iter 290/292 - loss 0.03440584 - time (sec): 16.73 - samples/sec: 2648.35 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:10:09,006 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:10:09,007 EPOCH 6 done: loss 0.0343 - lr: 0.000013 | |
| 2023-10-17 18:10:10,343 DEV : loss 0.14083223044872284 - f1-score (micro avg) 0.7277 | |
| 2023-10-17 18:10:10,348 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:10:12,061 epoch 7 - iter 29/292 - loss 0.02684070 - time (sec): 1.71 - samples/sec: 2449.55 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:10:13,716 epoch 7 - iter 58/292 - loss 0.02804202 - time (sec): 3.37 - samples/sec: 2601.88 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:10:15,396 epoch 7 - iter 87/292 - loss 0.02728816 - time (sec): 5.05 - samples/sec: 2533.64 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:10:17,025 epoch 7 - iter 116/292 - loss 0.02959221 - time (sec): 6.68 - samples/sec: 2518.88 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:10:18,802 epoch 7 - iter 145/292 - loss 0.02635240 - time (sec): 8.45 - samples/sec: 2598.73 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:10:20,511 epoch 7 - iter 174/292 - loss 0.02532558 - time (sec): 10.16 - samples/sec: 2604.77 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:10:22,109 epoch 7 - iter 203/292 - loss 0.02582429 - time (sec): 11.76 - samples/sec: 2608.96 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:10:23,786 epoch 7 - iter 232/292 - loss 0.02531994 - time (sec): 13.44 - samples/sec: 2622.46 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:10:25,608 epoch 7 - iter 261/292 - loss 0.02453137 - time (sec): 15.26 - samples/sec: 2652.54 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:10:27,172 epoch 7 - iter 290/292 - loss 0.02590830 - time (sec): 16.82 - samples/sec: 2622.54 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:10:27,280 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:10:27,280 EPOCH 7 done: loss 0.0258 - lr: 0.000010 | |
| 2023-10-17 18:10:28,530 DEV : loss 0.1593863070011139 - f1-score (micro avg) 0.755 | |
| 2023-10-17 18:10:28,536 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:10:30,524 epoch 8 - iter 29/292 - loss 0.02520487 - time (sec): 1.99 - samples/sec: 2309.62 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:10:32,414 epoch 8 - iter 58/292 - loss 0.02786812 - time (sec): 3.88 - samples/sec: 2523.46 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:10:34,001 epoch 8 - iter 87/292 - loss 0.02098684 - time (sec): 5.46 - samples/sec: 2578.86 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:10:35,714 epoch 8 - iter 116/292 - loss 0.01947693 - time (sec): 7.18 - samples/sec: 2632.57 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:10:37,312 epoch 8 - iter 145/292 - loss 0.01741232 - time (sec): 8.77 - samples/sec: 2604.14 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:10:38,895 epoch 8 - iter 174/292 - loss 0.02044811 - time (sec): 10.36 - samples/sec: 2612.55 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:10:40,581 epoch 8 - iter 203/292 - loss 0.02099220 - time (sec): 12.04 - samples/sec: 2680.30 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:10:42,079 epoch 8 - iter 232/292 - loss 0.02151490 - time (sec): 13.54 - samples/sec: 2639.95 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:10:43,602 epoch 8 - iter 261/292 - loss 0.02058897 - time (sec): 15.07 - samples/sec: 2620.07 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:10:45,364 epoch 8 - iter 290/292 - loss 0.01989925 - time (sec): 16.83 - samples/sec: 2633.04 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:10:45,451 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:10:45,451 EPOCH 8 done: loss 0.0198 - lr: 0.000007 | |
| 2023-10-17 18:10:46,749 DEV : loss 0.16249039769172668 - f1-score (micro avg) 0.7335 | |
| 2023-10-17 18:10:46,755 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:10:48,382 epoch 9 - iter 29/292 - loss 0.00668975 - time (sec): 1.63 - samples/sec: 2507.95 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:10:50,068 epoch 9 - iter 58/292 - loss 0.01877431 - time (sec): 3.31 - samples/sec: 2774.90 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:10:51,767 epoch 9 - iter 87/292 - loss 0.01592873 - time (sec): 5.01 - samples/sec: 2794.63 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:10:53,379 epoch 9 - iter 116/292 - loss 0.01512380 - time (sec): 6.62 - samples/sec: 2752.74 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:10:55,042 epoch 9 - iter 145/292 - loss 0.01369025 - time (sec): 8.29 - samples/sec: 2723.12 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:10:56,664 epoch 9 - iter 174/292 - loss 0.01356662 - time (sec): 9.91 - samples/sec: 2658.39 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:10:58,319 epoch 9 - iter 203/292 - loss 0.01300736 - time (sec): 11.56 - samples/sec: 2644.31 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:11:00,072 epoch 9 - iter 232/292 - loss 0.01299119 - time (sec): 13.32 - samples/sec: 2661.66 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:11:01,819 epoch 9 - iter 261/292 - loss 0.01374651 - time (sec): 15.06 - samples/sec: 2629.91 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:11:03,765 epoch 9 - iter 290/292 - loss 0.01334354 - time (sec): 17.01 - samples/sec: 2605.18 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:11:03,860 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:11:03,860 EPOCH 9 done: loss 0.0134 - lr: 0.000003 | |
| 2023-10-17 18:11:05,174 DEV : loss 0.16921038925647736 - f1-score (micro avg) 0.7516 | |
| 2023-10-17 18:11:05,184 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:11:06,961 epoch 10 - iter 29/292 - loss 0.00890121 - time (sec): 1.78 - samples/sec: 2247.21 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:11:08,579 epoch 10 - iter 58/292 - loss 0.00743095 - time (sec): 3.39 - samples/sec: 2377.05 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:11:10,242 epoch 10 - iter 87/292 - loss 0.00759210 - time (sec): 5.06 - samples/sec: 2500.96 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:11:11,869 epoch 10 - iter 116/292 - loss 0.00820561 - time (sec): 6.68 - samples/sec: 2534.58 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:11:13,619 epoch 10 - iter 145/292 - loss 0.00773890 - time (sec): 8.43 - samples/sec: 2638.46 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:11:15,276 epoch 10 - iter 174/292 - loss 0.01031477 - time (sec): 10.09 - samples/sec: 2628.47 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:11:17,122 epoch 10 - iter 203/292 - loss 0.01109630 - time (sec): 11.94 - samples/sec: 2621.48 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:11:18,735 epoch 10 - iter 232/292 - loss 0.01091261 - time (sec): 13.55 - samples/sec: 2613.13 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:11:20,332 epoch 10 - iter 261/292 - loss 0.01138787 - time (sec): 15.15 - samples/sec: 2600.35 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 18:11:22,014 epoch 10 - iter 290/292 - loss 0.01147225 - time (sec): 16.83 - samples/sec: 2627.67 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 18:11:22,108 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:11:22,108 EPOCH 10 done: loss 0.0114 - lr: 0.000000 | |
| 2023-10-17 18:11:23,353 DEV : loss 0.16777698695659637 - f1-score (micro avg) 0.7565 | |
| 2023-10-17 18:11:23,699 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:11:23,700 Loading model from best epoch ... | |
| 2023-10-17 18:11:25,061 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 18:11:27,419 | |
| Results: | |
| - F-score (micro) 0.7545 | |
| - F-score (macro) 0.6648 | |
| - Accuracy 0.6275 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.8040 0.8132 0.8086 348 | |
| LOC 0.7419 0.7931 0.7667 261 | |
| ORG 0.3333 0.3462 0.3396 52 | |
| HumanProd 0.7619 0.7273 0.7442 22 | |
| micro avg 0.7422 0.7672 0.7545 683 | |
| macro avg 0.6603 0.6699 0.6648 683 | |
| weighted avg 0.7431 0.7672 0.7548 683 | |
| 2023-10-17 18:11:27,419 ---------------------------------------------------------------------------------------------------- | |