| 2023-10-17 22:17:58,269 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:17:58,270 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 22:17:58,270 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:17:58,270 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 22:17:58,270 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:17:58,270 Train: 5901 sentences | |
| 2023-10-17 22:17:58,270 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 22:17:58,270 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:17:58,270 Training Params: | |
| 2023-10-17 22:17:58,270 - learning_rate: "3e-05" | |
| 2023-10-17 22:17:58,270 - mini_batch_size: "8" | |
| 2023-10-17 22:17:58,271 - max_epochs: "10" | |
| 2023-10-17 22:17:58,271 - shuffle: "True" | |
| 2023-10-17 22:17:58,271 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:17:58,271 Plugins: | |
| 2023-10-17 22:17:58,271 - TensorboardLogger | |
| 2023-10-17 22:17:58,271 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 22:17:58,271 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:17:58,271 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 22:17:58,271 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 22:17:58,271 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:17:58,271 Computation: | |
| 2023-10-17 22:17:58,271 - compute on device: cuda:0 | |
| 2023-10-17 22:17:58,271 - embedding storage: none | |
| 2023-10-17 22:17:58,271 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:17:58,271 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4" | |
| 2023-10-17 22:17:58,271 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:17:58,271 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:17:58,271 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 22:18:03,711 epoch 1 - iter 73/738 - loss 3.29856726 - time (sec): 5.44 - samples/sec: 3110.15 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 22:18:08,234 epoch 1 - iter 146/738 - loss 2.33571635 - time (sec): 9.96 - samples/sec: 3178.58 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 22:18:12,850 epoch 1 - iter 219/738 - loss 1.75332585 - time (sec): 14.58 - samples/sec: 3213.49 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 22:18:18,033 epoch 1 - iter 292/738 - loss 1.40317593 - time (sec): 19.76 - samples/sec: 3232.65 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 22:18:23,401 epoch 1 - iter 365/738 - loss 1.16651775 - time (sec): 25.13 - samples/sec: 3272.08 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 22:18:28,709 epoch 1 - iter 438/738 - loss 1.01598306 - time (sec): 30.44 - samples/sec: 3263.18 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 22:18:33,237 epoch 1 - iter 511/738 - loss 0.91782187 - time (sec): 34.96 - samples/sec: 3270.54 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 22:18:38,084 epoch 1 - iter 584/738 - loss 0.82790203 - time (sec): 39.81 - samples/sec: 3283.28 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 22:18:43,295 epoch 1 - iter 657/738 - loss 0.75478792 - time (sec): 45.02 - samples/sec: 3276.03 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 22:18:48,480 epoch 1 - iter 730/738 - loss 0.69322064 - time (sec): 50.21 - samples/sec: 3287.16 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 22:18:48,934 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:18:48,934 EPOCH 1 done: loss 0.6891 - lr: 0.000030 | |
| 2023-10-17 22:18:55,359 DEV : loss 0.13255925476551056 - f1-score (micro avg) 0.7402 | |
| 2023-10-17 22:18:55,393 saving best model | |
| 2023-10-17 22:18:55,902 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:19:01,430 epoch 2 - iter 73/738 - loss 0.15669806 - time (sec): 5.53 - samples/sec: 3336.08 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 22:19:06,196 epoch 2 - iter 146/738 - loss 0.14591808 - time (sec): 10.29 - samples/sec: 3332.50 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 22:19:11,277 epoch 2 - iter 219/738 - loss 0.13948315 - time (sec): 15.37 - samples/sec: 3258.73 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 22:19:16,377 epoch 2 - iter 292/738 - loss 0.13359906 - time (sec): 20.47 - samples/sec: 3255.85 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 22:19:20,965 epoch 2 - iter 365/738 - loss 0.13291857 - time (sec): 25.06 - samples/sec: 3242.43 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 22:19:25,892 epoch 2 - iter 438/738 - loss 0.13012451 - time (sec): 29.99 - samples/sec: 3243.07 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 22:19:30,436 epoch 2 - iter 511/738 - loss 0.12966906 - time (sec): 34.53 - samples/sec: 3257.63 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 22:19:35,185 epoch 2 - iter 584/738 - loss 0.12830147 - time (sec): 39.28 - samples/sec: 3267.36 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 22:19:40,433 epoch 2 - iter 657/738 - loss 0.12656911 - time (sec): 44.53 - samples/sec: 3257.61 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 22:19:45,722 epoch 2 - iter 730/738 - loss 0.12479095 - time (sec): 49.82 - samples/sec: 3269.78 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 22:19:46,699 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:19:46,699 EPOCH 2 done: loss 0.1235 - lr: 0.000027 | |
| 2023-10-17 22:19:58,228 DEV : loss 0.09971650689840317 - f1-score (micro avg) 0.817 | |
| 2023-10-17 22:19:58,261 saving best model | |
| 2023-10-17 22:19:58,768 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:20:04,492 epoch 3 - iter 73/738 - loss 0.07116535 - time (sec): 5.72 - samples/sec: 3233.60 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 22:20:09,448 epoch 3 - iter 146/738 - loss 0.07406823 - time (sec): 10.68 - samples/sec: 3243.52 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 22:20:13,950 epoch 3 - iter 219/738 - loss 0.07329993 - time (sec): 15.18 - samples/sec: 3243.08 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 22:20:18,731 epoch 3 - iter 292/738 - loss 0.07389833 - time (sec): 19.96 - samples/sec: 3268.77 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 22:20:23,577 epoch 3 - iter 365/738 - loss 0.07158038 - time (sec): 24.81 - samples/sec: 3265.55 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 22:20:28,864 epoch 3 - iter 438/738 - loss 0.06858546 - time (sec): 30.09 - samples/sec: 3262.43 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 22:20:33,985 epoch 3 - iter 511/738 - loss 0.06978305 - time (sec): 35.22 - samples/sec: 3281.19 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 22:20:38,696 epoch 3 - iter 584/738 - loss 0.07056297 - time (sec): 39.93 - samples/sec: 3272.55 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 22:20:43,925 epoch 3 - iter 657/738 - loss 0.06912465 - time (sec): 45.16 - samples/sec: 3256.00 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 22:20:49,502 epoch 3 - iter 730/738 - loss 0.06701772 - time (sec): 50.73 - samples/sec: 3242.59 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 22:20:50,032 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:20:50,033 EPOCH 3 done: loss 0.0666 - lr: 0.000023 | |
| 2023-10-17 22:21:01,393 DEV : loss 0.1249760165810585 - f1-score (micro avg) 0.8338 | |
| 2023-10-17 22:21:01,426 saving best model | |
| 2023-10-17 22:21:01,940 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:21:06,580 epoch 4 - iter 73/738 - loss 0.04457840 - time (sec): 4.63 - samples/sec: 3333.40 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 22:21:11,442 epoch 4 - iter 146/738 - loss 0.05230145 - time (sec): 9.50 - samples/sec: 3283.87 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 22:21:16,408 epoch 4 - iter 219/738 - loss 0.04716700 - time (sec): 14.46 - samples/sec: 3256.73 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 22:21:22,961 epoch 4 - iter 292/738 - loss 0.04717604 - time (sec): 21.02 - samples/sec: 3159.70 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 22:21:28,099 epoch 4 - iter 365/738 - loss 0.04565264 - time (sec): 26.15 - samples/sec: 3191.44 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 22:21:32,658 epoch 4 - iter 438/738 - loss 0.04666990 - time (sec): 30.71 - samples/sec: 3197.14 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 22:21:37,764 epoch 4 - iter 511/738 - loss 0.04569046 - time (sec): 35.82 - samples/sec: 3195.83 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 22:21:42,720 epoch 4 - iter 584/738 - loss 0.04409211 - time (sec): 40.77 - samples/sec: 3196.22 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 22:21:47,501 epoch 4 - iter 657/738 - loss 0.04454876 - time (sec): 45.56 - samples/sec: 3208.77 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 22:21:52,922 epoch 4 - iter 730/738 - loss 0.04582566 - time (sec): 50.98 - samples/sec: 3231.55 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 22:21:53,464 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:21:53,464 EPOCH 4 done: loss 0.0457 - lr: 0.000020 | |
| 2023-10-17 22:22:04,771 DEV : loss 0.12631914019584656 - f1-score (micro avg) 0.8452 | |
| 2023-10-17 22:22:04,802 saving best model | |
| 2023-10-17 22:22:05,391 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:22:10,171 epoch 5 - iter 73/738 - loss 0.02247467 - time (sec): 4.78 - samples/sec: 3314.26 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 22:22:15,222 epoch 5 - iter 146/738 - loss 0.03077292 - time (sec): 9.83 - samples/sec: 3172.84 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 22:22:20,517 epoch 5 - iter 219/738 - loss 0.03063812 - time (sec): 15.12 - samples/sec: 3176.91 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 22:22:25,684 epoch 5 - iter 292/738 - loss 0.03017627 - time (sec): 20.29 - samples/sec: 3216.73 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 22:22:30,743 epoch 5 - iter 365/738 - loss 0.03372599 - time (sec): 25.35 - samples/sec: 3247.86 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 22:22:35,678 epoch 5 - iter 438/738 - loss 0.03334869 - time (sec): 30.28 - samples/sec: 3269.32 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 22:22:40,611 epoch 5 - iter 511/738 - loss 0.03334476 - time (sec): 35.22 - samples/sec: 3260.70 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 22:22:46,659 epoch 5 - iter 584/738 - loss 0.03429929 - time (sec): 41.27 - samples/sec: 3248.90 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 22:22:51,433 epoch 5 - iter 657/738 - loss 0.03350050 - time (sec): 46.04 - samples/sec: 3246.21 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 22:22:56,086 epoch 5 - iter 730/738 - loss 0.03335451 - time (sec): 50.69 - samples/sec: 3256.79 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 22:22:56,533 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:22:56,534 EPOCH 5 done: loss 0.0331 - lr: 0.000017 | |
| 2023-10-17 22:23:08,073 DEV : loss 0.1511925756931305 - f1-score (micro avg) 0.8464 | |
| 2023-10-17 22:23:08,105 saving best model | |
| 2023-10-17 22:23:08,626 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:23:13,333 epoch 6 - iter 73/738 - loss 0.02501103 - time (sec): 4.71 - samples/sec: 3408.10 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 22:23:18,271 epoch 6 - iter 146/738 - loss 0.02769990 - time (sec): 9.64 - samples/sec: 3353.82 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 22:23:23,633 epoch 6 - iter 219/738 - loss 0.02205354 - time (sec): 15.00 - samples/sec: 3319.75 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 22:23:28,283 epoch 6 - iter 292/738 - loss 0.02205683 - time (sec): 19.65 - samples/sec: 3304.94 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 22:23:33,101 epoch 6 - iter 365/738 - loss 0.02395615 - time (sec): 24.47 - samples/sec: 3305.73 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 22:23:38,617 epoch 6 - iter 438/738 - loss 0.02594836 - time (sec): 29.99 - samples/sec: 3287.54 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 22:23:43,343 epoch 6 - iter 511/738 - loss 0.02560500 - time (sec): 34.72 - samples/sec: 3280.34 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 22:23:48,409 epoch 6 - iter 584/738 - loss 0.02533246 - time (sec): 39.78 - samples/sec: 3283.32 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 22:23:54,327 epoch 6 - iter 657/738 - loss 0.02438802 - time (sec): 45.70 - samples/sec: 3258.92 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 22:23:59,212 epoch 6 - iter 730/738 - loss 0.02343369 - time (sec): 50.58 - samples/sec: 3259.66 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 22:23:59,653 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:23:59,653 EPOCH 6 done: loss 0.0233 - lr: 0.000013 | |
| 2023-10-17 22:24:11,122 DEV : loss 0.1842828392982483 - f1-score (micro avg) 0.8485 | |
| 2023-10-17 22:24:11,171 saving best model | |
| 2023-10-17 22:24:11,733 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:24:17,378 epoch 7 - iter 73/738 - loss 0.02062174 - time (sec): 5.64 - samples/sec: 3347.89 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 22:24:22,554 epoch 7 - iter 146/738 - loss 0.01930789 - time (sec): 10.82 - samples/sec: 3269.16 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 22:24:27,385 epoch 7 - iter 219/738 - loss 0.01819226 - time (sec): 15.65 - samples/sec: 3263.35 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 22:24:32,643 epoch 7 - iter 292/738 - loss 0.01591563 - time (sec): 20.91 - samples/sec: 3257.11 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 22:24:37,190 epoch 7 - iter 365/738 - loss 0.01582028 - time (sec): 25.45 - samples/sec: 3268.49 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 22:24:42,306 epoch 7 - iter 438/738 - loss 0.01713951 - time (sec): 30.57 - samples/sec: 3257.47 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 22:24:47,433 epoch 7 - iter 511/738 - loss 0.01736950 - time (sec): 35.70 - samples/sec: 3243.43 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 22:24:52,326 epoch 7 - iter 584/738 - loss 0.01835725 - time (sec): 40.59 - samples/sec: 3255.75 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 22:24:57,475 epoch 7 - iter 657/738 - loss 0.01880709 - time (sec): 45.74 - samples/sec: 3246.52 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 22:25:02,359 epoch 7 - iter 730/738 - loss 0.01767309 - time (sec): 50.62 - samples/sec: 3251.60 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 22:25:02,913 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:25:02,913 EPOCH 7 done: loss 0.0175 - lr: 0.000010 | |
| 2023-10-17 22:25:14,455 DEV : loss 0.18417294323444366 - f1-score (micro avg) 0.8585 | |
| 2023-10-17 22:25:14,489 saving best model | |
| 2023-10-17 22:25:15,026 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:25:20,533 epoch 8 - iter 73/738 - loss 0.01643123 - time (sec): 5.50 - samples/sec: 3454.49 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 22:25:25,413 epoch 8 - iter 146/738 - loss 0.01512657 - time (sec): 10.38 - samples/sec: 3333.12 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 22:25:30,928 epoch 8 - iter 219/738 - loss 0.01565763 - time (sec): 15.90 - samples/sec: 3298.50 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 22:25:36,317 epoch 8 - iter 292/738 - loss 0.01365729 - time (sec): 21.29 - samples/sec: 3275.45 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 22:25:41,147 epoch 8 - iter 365/738 - loss 0.01335669 - time (sec): 26.12 - samples/sec: 3276.44 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 22:25:46,068 epoch 8 - iter 438/738 - loss 0.01331697 - time (sec): 31.04 - samples/sec: 3253.92 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 22:25:51,153 epoch 8 - iter 511/738 - loss 0.01254965 - time (sec): 36.12 - samples/sec: 3233.06 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 22:25:56,092 epoch 8 - iter 584/738 - loss 0.01257581 - time (sec): 41.06 - samples/sec: 3250.38 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 22:26:01,040 epoch 8 - iter 657/738 - loss 0.01233224 - time (sec): 46.01 - samples/sec: 3248.43 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 22:26:05,603 epoch 8 - iter 730/738 - loss 0.01166783 - time (sec): 50.57 - samples/sec: 3254.80 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 22:26:06,147 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:26:06,148 EPOCH 8 done: loss 0.0116 - lr: 0.000007 | |
| 2023-10-17 22:26:17,700 DEV : loss 0.19687536358833313 - f1-score (micro avg) 0.8521 | |
| 2023-10-17 22:26:17,736 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:26:22,366 epoch 9 - iter 73/738 - loss 0.00486432 - time (sec): 4.63 - samples/sec: 3229.34 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 22:26:27,808 epoch 9 - iter 146/738 - loss 0.00507713 - time (sec): 10.07 - samples/sec: 3082.45 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 22:26:33,811 epoch 9 - iter 219/738 - loss 0.00936116 - time (sec): 16.07 - samples/sec: 3209.27 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 22:26:38,157 epoch 9 - iter 292/738 - loss 0.00850298 - time (sec): 20.42 - samples/sec: 3240.02 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 22:26:42,888 epoch 9 - iter 365/738 - loss 0.00832296 - time (sec): 25.15 - samples/sec: 3248.21 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 22:26:48,421 epoch 9 - iter 438/738 - loss 0.00848425 - time (sec): 30.68 - samples/sec: 3254.44 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 22:26:53,031 epoch 9 - iter 511/738 - loss 0.00798555 - time (sec): 35.29 - samples/sec: 3253.29 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 22:26:58,207 epoch 9 - iter 584/738 - loss 0.00871976 - time (sec): 40.47 - samples/sec: 3247.62 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 22:27:03,682 epoch 9 - iter 657/738 - loss 0.00955549 - time (sec): 45.94 - samples/sec: 3238.12 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 22:27:08,494 epoch 9 - iter 730/738 - loss 0.00896685 - time (sec): 50.76 - samples/sec: 3244.01 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 22:27:09,001 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:27:09,002 EPOCH 9 done: loss 0.0089 - lr: 0.000003 | |
| 2023-10-17 22:27:21,204 DEV : loss 0.19589132070541382 - f1-score (micro avg) 0.8512 | |
| 2023-10-17 22:27:21,252 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:27:25,999 epoch 10 - iter 73/738 - loss 0.00385619 - time (sec): 4.74 - samples/sec: 3098.93 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 22:27:31,695 epoch 10 - iter 146/738 - loss 0.00416269 - time (sec): 10.44 - samples/sec: 2937.71 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 22:27:36,741 epoch 10 - iter 219/738 - loss 0.00402096 - time (sec): 15.49 - samples/sec: 2997.62 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 22:27:42,509 epoch 10 - iter 292/738 - loss 0.00542373 - time (sec): 21.26 - samples/sec: 3082.73 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 22:27:47,400 epoch 10 - iter 365/738 - loss 0.00527929 - time (sec): 26.15 - samples/sec: 3098.61 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 22:27:52,727 epoch 10 - iter 438/738 - loss 0.00704477 - time (sec): 31.47 - samples/sec: 3109.61 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 22:27:57,662 epoch 10 - iter 511/738 - loss 0.00638262 - time (sec): 36.41 - samples/sec: 3124.98 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 22:28:02,588 epoch 10 - iter 584/738 - loss 0.00622954 - time (sec): 41.33 - samples/sec: 3138.83 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 22:28:08,385 epoch 10 - iter 657/738 - loss 0.00637380 - time (sec): 47.13 - samples/sec: 3154.57 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 22:28:13,259 epoch 10 - iter 730/738 - loss 0.00610510 - time (sec): 52.01 - samples/sec: 3155.24 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 22:28:13,909 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:28:13,909 EPOCH 10 done: loss 0.0061 - lr: 0.000000 | |
| 2023-10-17 22:28:26,042 DEV : loss 0.19979998469352722 - f1-score (micro avg) 0.8524 | |
| 2023-10-17 22:28:26,475 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:28:26,477 Loading model from best epoch ... | |
| 2023-10-17 22:28:28,117 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 22:28:34,813 | |
| Results: | |
| - F-score (micro) 0.8089 | |
| - F-score (macro) 0.7054 | |
| - Accuracy 0.6961 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8651 0.8823 0.8736 858 | |
| pers 0.7865 0.8026 0.7945 537 | |
| org 0.6293 0.5530 0.5887 132 | |
| prod 0.6562 0.6885 0.6720 61 | |
| time 0.5556 0.6481 0.5983 54 | |
| micro avg 0.8031 0.8149 0.8089 1642 | |
| macro avg 0.6986 0.7149 0.7054 1642 | |
| weighted avg 0.8025 0.8149 0.8083 1642 | |
| 2023-10-17 22:28:34,813 ---------------------------------------------------------------------------------------------------- | |