| 2023-10-17 21:26:40,875 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:26:40,876 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=21, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 21:26:40,876 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:26:40,876 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences | |
| - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator | |
| 2023-10-17 21:26:40,876 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:26:40,876 Train: 5901 sentences | |
| 2023-10-17 21:26:40,876 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 21:26:40,876 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:26:40,876 Training Params: | |
| 2023-10-17 21:26:40,876 - learning_rate: "3e-05" | |
| 2023-10-17 21:26:40,876 - mini_batch_size: "8" | |
| 2023-10-17 21:26:40,876 - max_epochs: "10" | |
| 2023-10-17 21:26:40,876 - shuffle: "True" | |
| 2023-10-17 21:26:40,876 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:26:40,876 Plugins: | |
| 2023-10-17 21:26:40,877 - TensorboardLogger | |
| 2023-10-17 21:26:40,877 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 21:26:40,877 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:26:40,877 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 21:26:40,877 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 21:26:40,877 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:26:40,877 Computation: | |
| 2023-10-17 21:26:40,877 - compute on device: cuda:0 | |
| 2023-10-17 21:26:40,877 - embedding storage: none | |
| 2023-10-17 21:26:40,877 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:26:40,877 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-17 21:26:40,877 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:26:40,877 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:26:40,877 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 21:26:45,615 epoch 1 - iter 73/738 - loss 3.49952752 - time (sec): 4.74 - samples/sec: 3401.60 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 21:26:51,525 epoch 1 - iter 146/738 - loss 2.16207004 - time (sec): 10.65 - samples/sec: 3375.23 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 21:26:56,443 epoch 1 - iter 219/738 - loss 1.66274405 - time (sec): 15.56 - samples/sec: 3326.52 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 21:27:00,716 epoch 1 - iter 292/738 - loss 1.38721801 - time (sec): 19.84 - samples/sec: 3357.65 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 21:27:05,522 epoch 1 - iter 365/738 - loss 1.18355146 - time (sec): 24.64 - samples/sec: 3350.31 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 21:27:10,816 epoch 1 - iter 438/738 - loss 1.02870123 - time (sec): 29.94 - samples/sec: 3358.32 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 21:27:15,600 epoch 1 - iter 511/738 - loss 0.91506435 - time (sec): 34.72 - samples/sec: 3358.58 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 21:27:20,128 epoch 1 - iter 584/738 - loss 0.83281866 - time (sec): 39.25 - samples/sec: 3372.24 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 21:27:24,700 epoch 1 - iter 657/738 - loss 0.76709624 - time (sec): 43.82 - samples/sec: 3378.50 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 21:27:29,463 epoch 1 - iter 730/738 - loss 0.70974504 - time (sec): 48.59 - samples/sec: 3382.19 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 21:27:29,971 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:27:29,972 EPOCH 1 done: loss 0.7025 - lr: 0.000030 | |
| 2023-10-17 21:27:35,758 DEV : loss 0.11762610077857971 - f1-score (micro avg) 0.7482 | |
| 2023-10-17 21:27:35,791 saving best model | |
| 2023-10-17 21:27:36,662 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:27:41,652 epoch 2 - iter 73/738 - loss 0.14984083 - time (sec): 4.99 - samples/sec: 3222.14 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 21:27:46,811 epoch 2 - iter 146/738 - loss 0.15409294 - time (sec): 10.15 - samples/sec: 3379.77 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 21:27:51,908 epoch 2 - iter 219/738 - loss 0.14322277 - time (sec): 15.24 - samples/sec: 3332.70 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 21:27:56,414 epoch 2 - iter 292/738 - loss 0.13804033 - time (sec): 19.75 - samples/sec: 3368.52 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 21:28:01,318 epoch 2 - iter 365/738 - loss 0.13219670 - time (sec): 24.65 - samples/sec: 3397.53 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 21:28:06,597 epoch 2 - iter 438/738 - loss 0.13134819 - time (sec): 29.93 - samples/sec: 3363.86 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 21:28:11,528 epoch 2 - iter 511/738 - loss 0.12866441 - time (sec): 34.86 - samples/sec: 3359.08 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 21:28:16,885 epoch 2 - iter 584/738 - loss 0.12449709 - time (sec): 40.22 - samples/sec: 3326.61 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 21:28:21,525 epoch 2 - iter 657/738 - loss 0.12254254 - time (sec): 44.86 - samples/sec: 3341.34 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 21:28:26,153 epoch 2 - iter 730/738 - loss 0.12293368 - time (sec): 49.49 - samples/sec: 3330.98 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 21:28:26,639 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:28:26,639 EPOCH 2 done: loss 0.1226 - lr: 0.000027 | |
| 2023-10-17 21:28:37,830 DEV : loss 0.08953238278627396 - f1-score (micro avg) 0.8325 | |
| 2023-10-17 21:28:37,863 saving best model | |
| 2023-10-17 21:28:38,345 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:28:43,166 epoch 3 - iter 73/738 - loss 0.06498284 - time (sec): 4.82 - samples/sec: 3316.94 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 21:28:48,268 epoch 3 - iter 146/738 - loss 0.07253182 - time (sec): 9.92 - samples/sec: 3292.11 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 21:28:53,207 epoch 3 - iter 219/738 - loss 0.07369571 - time (sec): 14.86 - samples/sec: 3307.50 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 21:28:58,390 epoch 3 - iter 292/738 - loss 0.07104734 - time (sec): 20.04 - samples/sec: 3291.04 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 21:29:03,747 epoch 3 - iter 365/738 - loss 0.07010578 - time (sec): 25.40 - samples/sec: 3289.69 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 21:29:08,795 epoch 3 - iter 438/738 - loss 0.07173198 - time (sec): 30.44 - samples/sec: 3280.44 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 21:29:13,423 epoch 3 - iter 511/738 - loss 0.07041391 - time (sec): 35.07 - samples/sec: 3281.82 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 21:29:18,816 epoch 3 - iter 584/738 - loss 0.06977851 - time (sec): 40.47 - samples/sec: 3282.39 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 21:29:23,695 epoch 3 - iter 657/738 - loss 0.06917953 - time (sec): 45.34 - samples/sec: 3292.70 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 21:29:28,226 epoch 3 - iter 730/738 - loss 0.07009721 - time (sec): 49.87 - samples/sec: 3304.46 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 21:29:28,708 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:29:28,709 EPOCH 3 done: loss 0.0701 - lr: 0.000023 | |
| 2023-10-17 21:29:40,107 DEV : loss 0.1102706640958786 - f1-score (micro avg) 0.8405 | |
| 2023-10-17 21:29:40,146 saving best model | |
| 2023-10-17 21:29:40,654 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:29:45,608 epoch 4 - iter 73/738 - loss 0.02968515 - time (sec): 4.95 - samples/sec: 3166.16 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 21:29:50,421 epoch 4 - iter 146/738 - loss 0.03527936 - time (sec): 9.76 - samples/sec: 3318.65 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 21:29:55,855 epoch 4 - iter 219/738 - loss 0.03661792 - time (sec): 15.20 - samples/sec: 3291.89 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 21:30:00,595 epoch 4 - iter 292/738 - loss 0.04111833 - time (sec): 19.94 - samples/sec: 3293.63 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 21:30:04,902 epoch 4 - iter 365/738 - loss 0.04094378 - time (sec): 24.25 - samples/sec: 3299.44 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 21:30:09,927 epoch 4 - iter 438/738 - loss 0.04325232 - time (sec): 29.27 - samples/sec: 3265.15 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 21:30:15,565 epoch 4 - iter 511/738 - loss 0.04681831 - time (sec): 34.91 - samples/sec: 3290.65 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 21:30:20,255 epoch 4 - iter 584/738 - loss 0.04786698 - time (sec): 39.60 - samples/sec: 3290.40 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 21:30:25,799 epoch 4 - iter 657/738 - loss 0.04774352 - time (sec): 45.14 - samples/sec: 3279.63 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 21:30:30,533 epoch 4 - iter 730/738 - loss 0.04825194 - time (sec): 49.88 - samples/sec: 3292.97 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 21:30:31,199 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:30:31,199 EPOCH 4 done: loss 0.0483 - lr: 0.000020 | |
| 2023-10-17 21:30:42,413 DEV : loss 0.1353892683982849 - f1-score (micro avg) 0.8416 | |
| 2023-10-17 21:30:42,446 saving best model | |
| 2023-10-17 21:30:42,928 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:30:47,459 epoch 5 - iter 73/738 - loss 0.03440303 - time (sec): 4.53 - samples/sec: 3382.11 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 21:30:52,224 epoch 5 - iter 146/738 - loss 0.03591970 - time (sec): 9.29 - samples/sec: 3346.20 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 21:30:57,359 epoch 5 - iter 219/738 - loss 0.03487105 - time (sec): 14.43 - samples/sec: 3341.94 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 21:31:02,051 epoch 5 - iter 292/738 - loss 0.03396132 - time (sec): 19.12 - samples/sec: 3302.02 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 21:31:07,353 epoch 5 - iter 365/738 - loss 0.03575017 - time (sec): 24.42 - samples/sec: 3292.46 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 21:31:13,225 epoch 5 - iter 438/738 - loss 0.03630382 - time (sec): 30.29 - samples/sec: 3317.94 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 21:31:17,948 epoch 5 - iter 511/738 - loss 0.03628542 - time (sec): 35.02 - samples/sec: 3306.47 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 21:31:22,791 epoch 5 - iter 584/738 - loss 0.03570918 - time (sec): 39.86 - samples/sec: 3311.13 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 21:31:27,930 epoch 5 - iter 657/738 - loss 0.03596680 - time (sec): 45.00 - samples/sec: 3295.33 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 21:31:32,885 epoch 5 - iter 730/738 - loss 0.03568567 - time (sec): 49.95 - samples/sec: 3298.95 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 21:31:33,323 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:31:33,323 EPOCH 5 done: loss 0.0355 - lr: 0.000017 | |
| 2023-10-17 21:31:44,632 DEV : loss 0.14825424551963806 - f1-score (micro avg) 0.8515 | |
| 2023-10-17 21:31:44,669 saving best model | |
| 2023-10-17 21:31:45,155 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:31:50,379 epoch 6 - iter 73/738 - loss 0.01815114 - time (sec): 5.22 - samples/sec: 3277.80 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 21:31:54,804 epoch 6 - iter 146/738 - loss 0.02485180 - time (sec): 9.64 - samples/sec: 3307.68 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 21:32:00,352 epoch 6 - iter 219/738 - loss 0.02316966 - time (sec): 15.19 - samples/sec: 3156.11 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 21:32:05,025 epoch 6 - iter 292/738 - loss 0.02044324 - time (sec): 19.87 - samples/sec: 3184.54 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 21:32:09,801 epoch 6 - iter 365/738 - loss 0.01978515 - time (sec): 24.64 - samples/sec: 3225.44 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 21:32:15,135 epoch 6 - iter 438/738 - loss 0.02024243 - time (sec): 29.98 - samples/sec: 3213.94 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 21:32:20,409 epoch 6 - iter 511/738 - loss 0.02251455 - time (sec): 35.25 - samples/sec: 3211.11 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 21:32:25,237 epoch 6 - iter 584/738 - loss 0.02378898 - time (sec): 40.08 - samples/sec: 3234.89 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 21:32:30,304 epoch 6 - iter 657/738 - loss 0.02399881 - time (sec): 45.14 - samples/sec: 3248.20 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 21:32:35,259 epoch 6 - iter 730/738 - loss 0.02430477 - time (sec): 50.10 - samples/sec: 3248.64 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 21:32:36,208 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:32:36,208 EPOCH 6 done: loss 0.0249 - lr: 0.000013 | |
| 2023-10-17 21:32:47,447 DEV : loss 0.15200623869895935 - f1-score (micro avg) 0.8486 | |
| 2023-10-17 21:32:47,479 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:32:52,519 epoch 7 - iter 73/738 - loss 0.02120244 - time (sec): 5.04 - samples/sec: 3271.07 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 21:32:57,621 epoch 7 - iter 146/738 - loss 0.01625364 - time (sec): 10.14 - samples/sec: 3284.37 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 21:33:02,523 epoch 7 - iter 219/738 - loss 0.01923714 - time (sec): 15.04 - samples/sec: 3233.79 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 21:33:07,707 epoch 7 - iter 292/738 - loss 0.01798684 - time (sec): 20.23 - samples/sec: 3282.97 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 21:33:12,635 epoch 7 - iter 365/738 - loss 0.01737053 - time (sec): 25.15 - samples/sec: 3289.30 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 21:33:17,385 epoch 7 - iter 438/738 - loss 0.01786620 - time (sec): 29.91 - samples/sec: 3292.00 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 21:33:22,339 epoch 7 - iter 511/738 - loss 0.01716618 - time (sec): 34.86 - samples/sec: 3311.50 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 21:33:27,483 epoch 7 - iter 584/738 - loss 0.01905246 - time (sec): 40.00 - samples/sec: 3293.23 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 21:33:32,841 epoch 7 - iter 657/738 - loss 0.01919180 - time (sec): 45.36 - samples/sec: 3291.41 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 21:33:37,560 epoch 7 - iter 730/738 - loss 0.01935287 - time (sec): 50.08 - samples/sec: 3281.30 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 21:33:38,229 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:33:38,229 EPOCH 7 done: loss 0.0192 - lr: 0.000010 | |
| 2023-10-17 21:33:49,459 DEV : loss 0.18122123181819916 - f1-score (micro avg) 0.8484 | |
| 2023-10-17 21:33:49,490 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:33:54,535 epoch 8 - iter 73/738 - loss 0.01103084 - time (sec): 5.04 - samples/sec: 3291.02 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 21:33:59,503 epoch 8 - iter 146/738 - loss 0.01060912 - time (sec): 10.01 - samples/sec: 3400.07 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 21:34:04,704 epoch 8 - iter 219/738 - loss 0.01630488 - time (sec): 15.21 - samples/sec: 3383.60 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 21:34:09,971 epoch 8 - iter 292/738 - loss 0.01761086 - time (sec): 20.48 - samples/sec: 3348.32 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 21:34:14,862 epoch 8 - iter 365/738 - loss 0.01660792 - time (sec): 25.37 - samples/sec: 3308.23 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 21:34:19,664 epoch 8 - iter 438/738 - loss 0.01520866 - time (sec): 30.17 - samples/sec: 3293.22 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 21:34:24,642 epoch 8 - iter 511/738 - loss 0.01405476 - time (sec): 35.15 - samples/sec: 3290.91 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 21:34:29,213 epoch 8 - iter 584/738 - loss 0.01480907 - time (sec): 39.72 - samples/sec: 3303.80 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 21:34:33,873 epoch 8 - iter 657/738 - loss 0.01466298 - time (sec): 44.38 - samples/sec: 3304.79 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 21:34:39,470 epoch 8 - iter 730/738 - loss 0.01428222 - time (sec): 49.98 - samples/sec: 3289.07 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 21:34:40,123 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:34:40,123 EPOCH 8 done: loss 0.0141 - lr: 0.000007 | |
| 2023-10-17 21:34:51,322 DEV : loss 0.18850760161876678 - f1-score (micro avg) 0.8447 | |
| 2023-10-17 21:34:51,355 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:34:56,327 epoch 9 - iter 73/738 - loss 0.00939305 - time (sec): 4.97 - samples/sec: 3353.78 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 21:35:01,986 epoch 9 - iter 146/738 - loss 0.00823870 - time (sec): 10.63 - samples/sec: 3284.37 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 21:35:07,616 epoch 9 - iter 219/738 - loss 0.00914707 - time (sec): 16.26 - samples/sec: 3291.38 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 21:35:12,908 epoch 9 - iter 292/738 - loss 0.00914178 - time (sec): 21.55 - samples/sec: 3324.64 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 21:35:17,828 epoch 9 - iter 365/738 - loss 0.00961735 - time (sec): 26.47 - samples/sec: 3320.82 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 21:35:22,462 epoch 9 - iter 438/738 - loss 0.01002769 - time (sec): 31.11 - samples/sec: 3325.10 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 21:35:27,590 epoch 9 - iter 511/738 - loss 0.01052868 - time (sec): 36.23 - samples/sec: 3303.82 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 21:35:32,468 epoch 9 - iter 584/738 - loss 0.01024063 - time (sec): 41.11 - samples/sec: 3277.99 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 21:35:37,124 epoch 9 - iter 657/738 - loss 0.01016591 - time (sec): 45.77 - samples/sec: 3273.54 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 21:35:41,638 epoch 9 - iter 730/738 - loss 0.00973227 - time (sec): 50.28 - samples/sec: 3279.12 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 21:35:42,121 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:35:42,122 EPOCH 9 done: loss 0.0096 - lr: 0.000003 | |
| 2023-10-17 21:35:53,382 DEV : loss 0.19131025671958923 - f1-score (micro avg) 0.8526 | |
| 2023-10-17 21:35:53,417 saving best model | |
| 2023-10-17 21:35:53,919 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:35:59,133 epoch 10 - iter 73/738 - loss 0.00368059 - time (sec): 5.21 - samples/sec: 3264.79 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 21:36:04,536 epoch 10 - iter 146/738 - loss 0.00688414 - time (sec): 10.61 - samples/sec: 3219.79 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 21:36:09,499 epoch 10 - iter 219/738 - loss 0.00600329 - time (sec): 15.58 - samples/sec: 3229.89 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 21:36:14,470 epoch 10 - iter 292/738 - loss 0.00593938 - time (sec): 20.55 - samples/sec: 3206.22 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 21:36:19,636 epoch 10 - iter 365/738 - loss 0.00609185 - time (sec): 25.71 - samples/sec: 3220.95 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 21:36:24,288 epoch 10 - iter 438/738 - loss 0.00665908 - time (sec): 30.36 - samples/sec: 3232.50 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 21:36:29,180 epoch 10 - iter 511/738 - loss 0.00605624 - time (sec): 35.26 - samples/sec: 3248.47 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 21:36:33,742 epoch 10 - iter 584/738 - loss 0.00606397 - time (sec): 39.82 - samples/sec: 3256.28 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 21:36:39,559 epoch 10 - iter 657/738 - loss 0.00643681 - time (sec): 45.64 - samples/sec: 3289.31 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 21:36:44,217 epoch 10 - iter 730/738 - loss 0.00772105 - time (sec): 50.29 - samples/sec: 3282.16 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 21:36:44,686 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:36:44,686 EPOCH 10 done: loss 0.0077 - lr: 0.000000 | |
| 2023-10-17 21:36:56,957 DEV : loss 0.19779689610004425 - f1-score (micro avg) 0.8516 | |
| 2023-10-17 21:36:57,390 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 21:36:57,391 Loading model from best epoch ... | |
| 2023-10-17 21:36:58,862 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod | |
| 2023-10-17 21:37:05,616 | |
| Results: | |
| - F-score (micro) 0.806 | |
| - F-score (macro) 0.7107 | |
| - Accuracy 0.694 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8910 0.8671 0.8789 858 | |
| pers 0.7539 0.8156 0.7835 537 | |
| org 0.5473 0.6136 0.5786 132 | |
| time 0.5556 0.6481 0.5983 54 | |
| prod 0.7843 0.6557 0.7143 61 | |
| micro avg 0.7974 0.8149 0.8060 1642 | |
| macro avg 0.7064 0.7201 0.7107 1642 | |
| weighted avg 0.8035 0.8149 0.8082 1642 | |
| 2023-10-17 21:37:05,616 ---------------------------------------------------------------------------------------------------- | |