| 2023-10-17 23:20:48,607 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:20:48,608 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 23:20:48,608 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:20:48,609 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 23:20:48,609 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:20:48,609 Train: 5901 sentences | |
| 2023-10-17 23:20:48,609 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 23:20:48,609 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:20:48,609 Training Params: | |
| 2023-10-17 23:20:48,609 - learning_rate: "5e-05" | |
| 2023-10-17 23:20:48,609 - mini_batch_size: "8" | |
| 2023-10-17 23:20:48,609 - max_epochs: "10" | |
| 2023-10-17 23:20:48,609 - shuffle: "True" | |
| 2023-10-17 23:20:48,609 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:20:48,609 Plugins: | |
| 2023-10-17 23:20:48,609 - TensorboardLogger | |
| 2023-10-17 23:20:48,609 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 23:20:48,609 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:20:48,609 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 23:20:48,609 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 23:20:48,609 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:20:48,609 Computation: | |
| 2023-10-17 23:20:48,610 - compute on device: cuda:0 | |
| 2023-10-17 23:20:48,610 - embedding storage: none | |
| 2023-10-17 23:20:48,610 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:20:48,610 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 23:20:48,610 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:20:48,610 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:20:48,610 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 23:20:53,860 epoch 1 - iter 73/738 - loss 2.85474195 - time (sec): 5.25 - samples/sec: 3208.60 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 23:20:59,150 epoch 1 - iter 146/738 - loss 1.78283901 - time (sec): 10.54 - samples/sec: 3224.58 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 23:21:04,724 epoch 1 - iter 219/738 - loss 1.30841453 - time (sec): 16.11 - samples/sec: 3226.08 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 23:21:09,914 epoch 1 - iter 292/738 - loss 1.06896886 - time (sec): 21.30 - samples/sec: 3231.26 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 23:21:15,039 epoch 1 - iter 365/738 - loss 0.91894998 - time (sec): 26.43 - samples/sec: 3222.58 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 23:21:19,675 epoch 1 - iter 438/738 - loss 0.81887551 - time (sec): 31.06 - samples/sec: 3219.41 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 23:21:24,221 epoch 1 - iter 511/738 - loss 0.73797567 - time (sec): 35.61 - samples/sec: 3237.14 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 23:21:29,755 epoch 1 - iter 584/738 - loss 0.66529868 - time (sec): 41.14 - samples/sec: 3255.58 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 23:21:34,453 epoch 1 - iter 657/738 - loss 0.61811551 - time (sec): 45.84 - samples/sec: 3244.08 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 23:21:39,299 epoch 1 - iter 730/738 - loss 0.57233422 - time (sec): 50.69 - samples/sec: 3252.08 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 23:21:39,786 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:21:39,786 EPOCH 1 done: loss 0.5687 - lr: 0.000049 | |
| 2023-10-17 23:21:46,270 DEV : loss 0.10680218786001205 - f1-score (micro avg) 0.7621 | |
| 2023-10-17 23:21:46,307 saving best model | |
| 2023-10-17 23:21:46,722 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:21:52,044 epoch 2 - iter 73/738 - loss 0.12994419 - time (sec): 5.32 - samples/sec: 3181.55 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 23:21:57,252 epoch 2 - iter 146/738 - loss 0.11822578 - time (sec): 10.53 - samples/sec: 3134.72 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 23:22:02,033 epoch 2 - iter 219/738 - loss 0.11707730 - time (sec): 15.31 - samples/sec: 3223.08 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 23:22:06,854 epoch 2 - iter 292/738 - loss 0.12130436 - time (sec): 20.13 - samples/sec: 3238.62 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 23:22:11,419 epoch 2 - iter 365/738 - loss 0.12325461 - time (sec): 24.70 - samples/sec: 3254.74 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 23:22:16,413 epoch 2 - iter 438/738 - loss 0.12007044 - time (sec): 29.69 - samples/sec: 3274.88 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 23:22:21,264 epoch 2 - iter 511/738 - loss 0.11944053 - time (sec): 34.54 - samples/sec: 3296.37 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 23:22:27,327 epoch 2 - iter 584/738 - loss 0.11685937 - time (sec): 40.60 - samples/sec: 3287.09 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 23:22:32,387 epoch 2 - iter 657/738 - loss 0.11755883 - time (sec): 45.66 - samples/sec: 3277.59 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 23:22:36,985 epoch 2 - iter 730/738 - loss 0.11821850 - time (sec): 50.26 - samples/sec: 3280.65 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 23:22:37,406 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:22:37,406 EPOCH 2 done: loss 0.1178 - lr: 0.000045 | |
| 2023-10-17 23:22:49,212 DEV : loss 0.13957878947257996 - f1-score (micro avg) 0.7821 | |
| 2023-10-17 23:22:49,247 saving best model | |
| 2023-10-17 23:22:49,771 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:22:54,738 epoch 3 - iter 73/738 - loss 0.06730250 - time (sec): 4.96 - samples/sec: 3249.69 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 23:22:59,596 epoch 3 - iter 146/738 - loss 0.06639160 - time (sec): 9.82 - samples/sec: 3249.10 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 23:23:04,665 epoch 3 - iter 219/738 - loss 0.06940105 - time (sec): 14.89 - samples/sec: 3211.31 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 23:23:09,789 epoch 3 - iter 292/738 - loss 0.07344307 - time (sec): 20.02 - samples/sec: 3212.38 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 23:23:15,097 epoch 3 - iter 365/738 - loss 0.07364186 - time (sec): 25.32 - samples/sec: 3235.78 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 23:23:19,723 epoch 3 - iter 438/738 - loss 0.07290238 - time (sec): 29.95 - samples/sec: 3255.49 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 23:23:25,283 epoch 3 - iter 511/738 - loss 0.07401442 - time (sec): 35.51 - samples/sec: 3264.76 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 23:23:30,236 epoch 3 - iter 584/738 - loss 0.07353939 - time (sec): 40.46 - samples/sec: 3251.95 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 23:23:35,032 epoch 3 - iter 657/738 - loss 0.07127111 - time (sec): 45.26 - samples/sec: 3266.17 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 23:23:40,375 epoch 3 - iter 730/738 - loss 0.07266252 - time (sec): 50.60 - samples/sec: 3260.30 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 23:23:40,800 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:23:40,800 EPOCH 3 done: loss 0.0737 - lr: 0.000039 | |
| 2023-10-17 23:23:52,463 DEV : loss 0.12460250407457352 - f1-score (micro avg) 0.8136 | |
| 2023-10-17 23:23:52,497 saving best model | |
| 2023-10-17 23:23:53,038 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:23:58,038 epoch 4 - iter 73/738 - loss 0.03370323 - time (sec): 5.00 - samples/sec: 3418.52 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 23:24:02,660 epoch 4 - iter 146/738 - loss 0.04562321 - time (sec): 9.62 - samples/sec: 3364.30 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 23:24:08,381 epoch 4 - iter 219/738 - loss 0.04852262 - time (sec): 15.34 - samples/sec: 3309.97 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 23:24:13,478 epoch 4 - iter 292/738 - loss 0.05147819 - time (sec): 20.44 - samples/sec: 3325.35 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 23:24:18,159 epoch 4 - iter 365/738 - loss 0.04853046 - time (sec): 25.12 - samples/sec: 3315.02 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 23:24:22,760 epoch 4 - iter 438/738 - loss 0.04928914 - time (sec): 29.72 - samples/sec: 3294.20 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 23:24:27,929 epoch 4 - iter 511/738 - loss 0.04904117 - time (sec): 34.89 - samples/sec: 3290.30 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 23:24:33,404 epoch 4 - iter 584/738 - loss 0.04995549 - time (sec): 40.36 - samples/sec: 3262.97 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 23:24:38,303 epoch 4 - iter 657/738 - loss 0.04972125 - time (sec): 45.26 - samples/sec: 3252.44 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 23:24:43,566 epoch 4 - iter 730/738 - loss 0.05043296 - time (sec): 50.53 - samples/sec: 3250.06 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 23:24:44,260 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:24:44,260 EPOCH 4 done: loss 0.0506 - lr: 0.000033 | |
| 2023-10-17 23:24:55,980 DEV : loss 0.15104417502880096 - f1-score (micro avg) 0.8221 | |
| 2023-10-17 23:24:56,015 saving best model | |
| 2023-10-17 23:24:56,592 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:25:01,650 epoch 5 - iter 73/738 - loss 0.03956590 - time (sec): 5.06 - samples/sec: 3136.97 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 23:25:06,581 epoch 5 - iter 146/738 - loss 0.03562984 - time (sec): 9.99 - samples/sec: 3167.84 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 23:25:11,371 epoch 5 - iter 219/738 - loss 0.03556496 - time (sec): 14.78 - samples/sec: 3244.94 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 23:25:16,291 epoch 5 - iter 292/738 - loss 0.03548706 - time (sec): 19.70 - samples/sec: 3287.46 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 23:25:21,008 epoch 5 - iter 365/738 - loss 0.03604989 - time (sec): 24.41 - samples/sec: 3289.09 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 23:25:27,506 epoch 5 - iter 438/738 - loss 0.03712954 - time (sec): 30.91 - samples/sec: 3245.75 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 23:25:32,944 epoch 5 - iter 511/738 - loss 0.03554041 - time (sec): 36.35 - samples/sec: 3245.90 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 23:25:37,745 epoch 5 - iter 584/738 - loss 0.03576331 - time (sec): 41.15 - samples/sec: 3231.39 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 23:25:42,074 epoch 5 - iter 657/738 - loss 0.03519494 - time (sec): 45.48 - samples/sec: 3234.17 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 23:25:47,319 epoch 5 - iter 730/738 - loss 0.03557902 - time (sec): 50.73 - samples/sec: 3247.21 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 23:25:47,884 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:25:47,884 EPOCH 5 done: loss 0.0357 - lr: 0.000028 | |
| 2023-10-17 23:25:59,681 DEV : loss 0.16061857342720032 - f1-score (micro avg) 0.8491 | |
| 2023-10-17 23:25:59,713 saving best model | |
| 2023-10-17 23:26:00,283 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:26:05,830 epoch 6 - iter 73/738 - loss 0.03118785 - time (sec): 5.55 - samples/sec: 3271.74 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 23:26:11,069 epoch 6 - iter 146/738 - loss 0.02616507 - time (sec): 10.78 - samples/sec: 3173.32 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 23:26:15,848 epoch 6 - iter 219/738 - loss 0.02339505 - time (sec): 15.56 - samples/sec: 3211.29 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 23:26:21,924 epoch 6 - iter 292/738 - loss 0.02435022 - time (sec): 21.64 - samples/sec: 3228.36 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 23:26:26,608 epoch 6 - iter 365/738 - loss 0.02549636 - time (sec): 26.32 - samples/sec: 3239.19 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 23:26:31,540 epoch 6 - iter 438/738 - loss 0.02512432 - time (sec): 31.26 - samples/sec: 3223.33 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 23:26:36,807 epoch 6 - iter 511/738 - loss 0.02472183 - time (sec): 36.52 - samples/sec: 3223.08 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 23:26:41,722 epoch 6 - iter 584/738 - loss 0.02355624 - time (sec): 41.44 - samples/sec: 3212.31 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 23:26:46,324 epoch 6 - iter 657/738 - loss 0.02348594 - time (sec): 46.04 - samples/sec: 3228.99 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 23:26:51,137 epoch 6 - iter 730/738 - loss 0.02428917 - time (sec): 50.85 - samples/sec: 3239.02 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 23:26:51,631 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:26:51,631 EPOCH 6 done: loss 0.0247 - lr: 0.000022 | |
| 2023-10-17 23:27:03,285 DEV : loss 0.1864573210477829 - f1-score (micro avg) 0.8343 | |
| 2023-10-17 23:27:03,320 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:27:07,808 epoch 7 - iter 73/738 - loss 0.01908871 - time (sec): 4.49 - samples/sec: 3418.41 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 23:27:12,781 epoch 7 - iter 146/738 - loss 0.01731582 - time (sec): 9.46 - samples/sec: 3340.36 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 23:27:17,560 epoch 7 - iter 219/738 - loss 0.01576750 - time (sec): 14.24 - samples/sec: 3300.59 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 23:27:22,548 epoch 7 - iter 292/738 - loss 0.01585694 - time (sec): 19.23 - samples/sec: 3243.91 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 23:27:28,246 epoch 7 - iter 365/738 - loss 0.01552307 - time (sec): 24.93 - samples/sec: 3245.65 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 23:27:32,869 epoch 7 - iter 438/738 - loss 0.01447850 - time (sec): 29.55 - samples/sec: 3246.80 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 23:27:38,122 epoch 7 - iter 511/738 - loss 0.01650421 - time (sec): 34.80 - samples/sec: 3231.68 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 23:27:43,410 epoch 7 - iter 584/738 - loss 0.01625634 - time (sec): 40.09 - samples/sec: 3243.21 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 23:27:48,588 epoch 7 - iter 657/738 - loss 0.01672479 - time (sec): 45.27 - samples/sec: 3244.29 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 23:27:53,986 epoch 7 - iter 730/738 - loss 0.01610283 - time (sec): 50.67 - samples/sec: 3246.76 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 23:27:54,602 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:27:54,602 EPOCH 7 done: loss 0.0161 - lr: 0.000017 | |
| 2023-10-17 23:28:06,282 DEV : loss 0.1937481015920639 - f1-score (micro avg) 0.8363 | |
| 2023-10-17 23:28:06,316 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:28:11,106 epoch 8 - iter 73/738 - loss 0.00650832 - time (sec): 4.79 - samples/sec: 3384.54 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 23:28:15,525 epoch 8 - iter 146/738 - loss 0.00609167 - time (sec): 9.21 - samples/sec: 3324.21 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 23:28:21,030 epoch 8 - iter 219/738 - loss 0.00649774 - time (sec): 14.71 - samples/sec: 3312.05 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 23:28:25,843 epoch 8 - iter 292/738 - loss 0.00738941 - time (sec): 19.53 - samples/sec: 3261.54 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 23:28:31,461 epoch 8 - iter 365/738 - loss 0.00922834 - time (sec): 25.14 - samples/sec: 3260.92 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 23:28:36,767 epoch 8 - iter 438/738 - loss 0.01058127 - time (sec): 30.45 - samples/sec: 3229.20 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 23:28:41,311 epoch 8 - iter 511/738 - loss 0.01038329 - time (sec): 34.99 - samples/sec: 3244.01 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 23:28:45,794 epoch 8 - iter 584/738 - loss 0.01003015 - time (sec): 39.48 - samples/sec: 3265.71 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 23:28:50,264 epoch 8 - iter 657/738 - loss 0.01016964 - time (sec): 43.95 - samples/sec: 3276.86 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 23:28:55,761 epoch 8 - iter 730/738 - loss 0.00979342 - time (sec): 49.44 - samples/sec: 3287.76 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 23:28:56,757 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:28:56,757 EPOCH 8 done: loss 0.0099 - lr: 0.000011 | |
| 2023-10-17 23:29:08,393 DEV : loss 0.21192434430122375 - f1-score (micro avg) 0.845 | |
| 2023-10-17 23:29:08,437 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:29:13,398 epoch 9 - iter 73/738 - loss 0.00572354 - time (sec): 4.96 - samples/sec: 3245.85 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 23:29:18,282 epoch 9 - iter 146/738 - loss 0.00771689 - time (sec): 9.84 - samples/sec: 3246.31 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 23:29:23,619 epoch 9 - iter 219/738 - loss 0.00686114 - time (sec): 15.18 - samples/sec: 3276.24 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 23:29:28,492 epoch 9 - iter 292/738 - loss 0.00626330 - time (sec): 20.05 - samples/sec: 3267.08 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 23:29:33,568 epoch 9 - iter 365/738 - loss 0.00726506 - time (sec): 25.13 - samples/sec: 3305.24 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 23:29:38,439 epoch 9 - iter 438/738 - loss 0.00887684 - time (sec): 30.00 - samples/sec: 3289.80 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 23:29:43,087 epoch 9 - iter 511/738 - loss 0.00852118 - time (sec): 34.65 - samples/sec: 3285.43 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 23:29:48,690 epoch 9 - iter 584/738 - loss 0.00774901 - time (sec): 40.25 - samples/sec: 3261.36 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 23:29:53,636 epoch 9 - iter 657/738 - loss 0.00716142 - time (sec): 45.20 - samples/sec: 3264.88 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 23:29:58,790 epoch 9 - iter 730/738 - loss 0.00709577 - time (sec): 50.35 - samples/sec: 3260.45 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 23:29:59,499 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:29:59,499 EPOCH 9 done: loss 0.0072 - lr: 0.000006 | |
| 2023-10-17 23:30:11,248 DEV : loss 0.20770353078842163 - f1-score (micro avg) 0.847 | |
| 2023-10-17 23:30:11,286 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:30:16,877 epoch 10 - iter 73/738 - loss 0.00364011 - time (sec): 5.59 - samples/sec: 3144.56 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 23:30:22,277 epoch 10 - iter 146/738 - loss 0.00694055 - time (sec): 10.99 - samples/sec: 3114.55 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 23:30:27,427 epoch 10 - iter 219/738 - loss 0.00565523 - time (sec): 16.14 - samples/sec: 3115.09 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 23:30:32,962 epoch 10 - iter 292/738 - loss 0.00642647 - time (sec): 21.67 - samples/sec: 3158.25 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 23:30:37,900 epoch 10 - iter 365/738 - loss 0.00548506 - time (sec): 26.61 - samples/sec: 3171.74 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 23:30:42,656 epoch 10 - iter 438/738 - loss 0.00523018 - time (sec): 31.37 - samples/sec: 3217.05 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 23:30:47,193 epoch 10 - iter 511/738 - loss 0.00494489 - time (sec): 35.91 - samples/sec: 3233.06 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 23:30:52,200 epoch 10 - iter 584/738 - loss 0.00451099 - time (sec): 40.91 - samples/sec: 3227.12 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 23:30:57,205 epoch 10 - iter 657/738 - loss 0.00453998 - time (sec): 45.92 - samples/sec: 3232.95 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 23:31:02,184 epoch 10 - iter 730/738 - loss 0.00471051 - time (sec): 50.90 - samples/sec: 3232.14 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 23:31:02,735 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:31:02,736 EPOCH 10 done: loss 0.0047 - lr: 0.000000 | |
| 2023-10-17 23:31:14,954 DEV : loss 0.21875163912773132 - f1-score (micro avg) 0.8505 | |
| 2023-10-17 23:31:14,994 saving best model | |
| 2023-10-17 23:31:15,959 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:31:15,960 Loading model from best epoch ... | |
| 2023-10-17 23:31:17,507 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 23:31:24,230 | |
| Results: | |
| - F-score (micro) 0.8068 | |
| - F-score (macro) 0.7197 | |
| - Accuracy 0.6964 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8642 0.8753 0.8697 858 | |
| pers 0.7603 0.8212 0.7896 537 | |
| org 0.5846 0.5758 0.5802 132 | |
| prod 0.7213 0.7213 0.7213 61 | |
| time 0.5968 0.6852 0.6379 54 | |
| micro avg 0.7926 0.8216 0.8068 1642 | |
| macro avg 0.7055 0.7358 0.7197 1642 | |
| weighted avg 0.7937 0.8216 0.8071 1642 | |
| 2023-10-17 23:31:24,230 ---------------------------------------------------------------------------------------------------- | |