| 2023-10-17 16:31:56,593 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:31:56,594 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=13, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 16:31:56,594 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:31:56,594 MultiCorpus: 5777 train + 722 dev + 723 test sentences | |
| - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl | |
| 2023-10-17 16:31:56,595 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:31:56,595 Train: 5777 sentences | |
| 2023-10-17 16:31:56,595 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 16:31:56,595 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:31:56,595 Training Params: | |
| 2023-10-17 16:31:56,595 - learning_rate: "3e-05" | |
| 2023-10-17 16:31:56,595 - mini_batch_size: "8" | |
| 2023-10-17 16:31:56,595 - max_epochs: "10" | |
| 2023-10-17 16:31:56,595 - shuffle: "True" | |
| 2023-10-17 16:31:56,595 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:31:56,595 Plugins: | |
| 2023-10-17 16:31:56,595 - TensorboardLogger | |
| 2023-10-17 16:31:56,595 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 16:31:56,595 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:31:56,595 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 16:31:56,595 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 16:31:56,595 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:31:56,595 Computation: | |
| 2023-10-17 16:31:56,595 - compute on device: cuda:0 | |
| 2023-10-17 16:31:56,595 - embedding storage: none | |
| 2023-10-17 16:31:56,595 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:31:56,595 Model training base path: "hmbench-icdar/nl-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-17 16:31:56,595 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:31:56,595 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:31:56,595 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 16:32:02,943 epoch 1 - iter 72/723 - loss 3.00768245 - time (sec): 6.35 - samples/sec: 2875.21 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 16:32:08,183 epoch 1 - iter 144/723 - loss 1.83377417 - time (sec): 11.59 - samples/sec: 3076.95 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 16:32:13,449 epoch 1 - iter 216/723 - loss 1.34809257 - time (sec): 16.85 - samples/sec: 3108.76 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 16:32:18,647 epoch 1 - iter 288/723 - loss 1.06011472 - time (sec): 22.05 - samples/sec: 3178.28 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 16:32:24,054 epoch 1 - iter 360/723 - loss 0.87287490 - time (sec): 27.46 - samples/sec: 3221.22 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 16:32:29,261 epoch 1 - iter 432/723 - loss 0.75621233 - time (sec): 32.66 - samples/sec: 3237.17 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 16:32:34,595 epoch 1 - iter 504/723 - loss 0.66869532 - time (sec): 38.00 - samples/sec: 3252.04 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 16:32:39,865 epoch 1 - iter 576/723 - loss 0.59841051 - time (sec): 43.27 - samples/sec: 3265.45 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 16:32:45,074 epoch 1 - iter 648/723 - loss 0.54748897 - time (sec): 48.48 - samples/sec: 3263.03 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 16:32:50,460 epoch 1 - iter 720/723 - loss 0.50420486 - time (sec): 53.86 - samples/sec: 3263.27 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 16:32:50,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:32:50,630 EPOCH 1 done: loss 0.5034 - lr: 0.000030 | |
| 2023-10-17 16:32:53,442 DEV : loss 0.09952846169471741 - f1-score (micro avg) 0.7835 | |
| 2023-10-17 16:32:53,458 saving best model | |
| 2023-10-17 16:32:53,801 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:32:58,765 epoch 2 - iter 72/723 - loss 0.13271887 - time (sec): 4.96 - samples/sec: 3334.96 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 16:33:03,658 epoch 2 - iter 144/723 - loss 0.12163388 - time (sec): 9.86 - samples/sec: 3400.14 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 16:33:09,123 epoch 2 - iter 216/723 - loss 0.10850316 - time (sec): 15.32 - samples/sec: 3329.04 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 16:33:14,409 epoch 2 - iter 288/723 - loss 0.10125886 - time (sec): 20.61 - samples/sec: 3345.74 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 16:33:19,451 epoch 2 - iter 360/723 - loss 0.09796960 - time (sec): 25.65 - samples/sec: 3351.30 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 16:33:24,872 epoch 2 - iter 432/723 - loss 0.09334936 - time (sec): 31.07 - samples/sec: 3384.78 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 16:33:30,230 epoch 2 - iter 504/723 - loss 0.09221920 - time (sec): 36.43 - samples/sec: 3378.17 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 16:33:35,347 epoch 2 - iter 576/723 - loss 0.09019324 - time (sec): 41.55 - samples/sec: 3370.17 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 16:33:40,659 epoch 2 - iter 648/723 - loss 0.08963976 - time (sec): 46.86 - samples/sec: 3375.95 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 16:33:45,971 epoch 2 - iter 720/723 - loss 0.09017542 - time (sec): 52.17 - samples/sec: 3368.84 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 16:33:46,144 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:33:46,144 EPOCH 2 done: loss 0.0903 - lr: 0.000027 | |
| 2023-10-17 16:33:49,394 DEV : loss 0.09726935625076294 - f1-score (micro avg) 0.7537 | |
| 2023-10-17 16:33:49,411 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:33:55,148 epoch 3 - iter 72/723 - loss 0.07215370 - time (sec): 5.74 - samples/sec: 3173.83 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 16:34:00,300 epoch 3 - iter 144/723 - loss 0.06483466 - time (sec): 10.89 - samples/sec: 3249.51 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 16:34:05,931 epoch 3 - iter 216/723 - loss 0.06657008 - time (sec): 16.52 - samples/sec: 3294.95 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 16:34:11,026 epoch 3 - iter 288/723 - loss 0.06642041 - time (sec): 21.61 - samples/sec: 3298.27 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 16:34:16,051 epoch 3 - iter 360/723 - loss 0.06531288 - time (sec): 26.64 - samples/sec: 3330.33 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 16:34:21,370 epoch 3 - iter 432/723 - loss 0.06197145 - time (sec): 31.96 - samples/sec: 3347.61 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 16:34:26,222 epoch 3 - iter 504/723 - loss 0.06234391 - time (sec): 36.81 - samples/sec: 3352.64 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 16:34:31,001 epoch 3 - iter 576/723 - loss 0.06144159 - time (sec): 41.59 - samples/sec: 3362.47 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 16:34:36,364 epoch 3 - iter 648/723 - loss 0.06093836 - time (sec): 46.95 - samples/sec: 3359.96 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 16:34:41,970 epoch 3 - iter 720/723 - loss 0.06193645 - time (sec): 52.56 - samples/sec: 3339.84 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 16:34:42,210 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:34:42,210 EPOCH 3 done: loss 0.0619 - lr: 0.000023 | |
| 2023-10-17 16:34:45,535 DEV : loss 0.06067139655351639 - f1-score (micro avg) 0.8784 | |
| 2023-10-17 16:34:45,557 saving best model | |
| 2023-10-17 16:34:45,993 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:34:51,188 epoch 4 - iter 72/723 - loss 0.03604175 - time (sec): 5.19 - samples/sec: 3431.92 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 16:34:56,194 epoch 4 - iter 144/723 - loss 0.04356223 - time (sec): 10.20 - samples/sec: 3418.58 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 16:35:01,218 epoch 4 - iter 216/723 - loss 0.03967575 - time (sec): 15.22 - samples/sec: 3391.10 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 16:35:06,482 epoch 4 - iter 288/723 - loss 0.04323559 - time (sec): 20.48 - samples/sec: 3354.49 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 16:35:12,130 epoch 4 - iter 360/723 - loss 0.04616657 - time (sec): 26.13 - samples/sec: 3318.56 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 16:35:17,425 epoch 4 - iter 432/723 - loss 0.04481773 - time (sec): 31.43 - samples/sec: 3340.12 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 16:35:22,592 epoch 4 - iter 504/723 - loss 0.04476274 - time (sec): 36.59 - samples/sec: 3354.14 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 16:35:27,892 epoch 4 - iter 576/723 - loss 0.04301556 - time (sec): 41.89 - samples/sec: 3352.09 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 16:35:33,137 epoch 4 - iter 648/723 - loss 0.04247650 - time (sec): 47.14 - samples/sec: 3352.96 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 16:35:38,436 epoch 4 - iter 720/723 - loss 0.04245231 - time (sec): 52.44 - samples/sec: 3351.38 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 16:35:38,580 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:35:38,580 EPOCH 4 done: loss 0.0424 - lr: 0.000020 | |
| 2023-10-17 16:35:42,472 DEV : loss 0.06585061550140381 - f1-score (micro avg) 0.88 | |
| 2023-10-17 16:35:42,489 saving best model | |
| 2023-10-17 16:35:42,962 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:35:47,869 epoch 5 - iter 72/723 - loss 0.04265918 - time (sec): 4.90 - samples/sec: 3353.74 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 16:35:53,060 epoch 5 - iter 144/723 - loss 0.03658285 - time (sec): 10.10 - samples/sec: 3370.07 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 16:35:58,295 epoch 5 - iter 216/723 - loss 0.03498816 - time (sec): 15.33 - samples/sec: 3369.09 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 16:36:03,141 epoch 5 - iter 288/723 - loss 0.03432794 - time (sec): 20.18 - samples/sec: 3361.53 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 16:36:08,503 epoch 5 - iter 360/723 - loss 0.03464982 - time (sec): 25.54 - samples/sec: 3369.88 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 16:36:13,602 epoch 5 - iter 432/723 - loss 0.03485007 - time (sec): 30.64 - samples/sec: 3380.28 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 16:36:19,327 epoch 5 - iter 504/723 - loss 0.03480689 - time (sec): 36.36 - samples/sec: 3367.59 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 16:36:25,026 epoch 5 - iter 576/723 - loss 0.03484667 - time (sec): 42.06 - samples/sec: 3362.37 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 16:36:30,154 epoch 5 - iter 648/723 - loss 0.03347624 - time (sec): 47.19 - samples/sec: 3371.81 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 16:36:35,020 epoch 5 - iter 720/723 - loss 0.03333207 - time (sec): 52.05 - samples/sec: 3372.78 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 16:36:35,222 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:36:35,222 EPOCH 5 done: loss 0.0333 - lr: 0.000017 | |
| 2023-10-17 16:36:38,511 DEV : loss 0.08196107298135757 - f1-score (micro avg) 0.8394 | |
| 2023-10-17 16:36:38,529 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:36:44,227 epoch 6 - iter 72/723 - loss 0.03440873 - time (sec): 5.70 - samples/sec: 3228.25 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 16:36:49,782 epoch 6 - iter 144/723 - loss 0.02600069 - time (sec): 11.25 - samples/sec: 3159.61 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 16:36:54,634 epoch 6 - iter 216/723 - loss 0.02505399 - time (sec): 16.10 - samples/sec: 3284.53 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 16:36:59,642 epoch 6 - iter 288/723 - loss 0.02392099 - time (sec): 21.11 - samples/sec: 3329.96 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 16:37:05,080 epoch 6 - iter 360/723 - loss 0.02284558 - time (sec): 26.55 - samples/sec: 3331.65 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 16:37:10,418 epoch 6 - iter 432/723 - loss 0.02214248 - time (sec): 31.89 - samples/sec: 3347.77 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 16:37:15,719 epoch 6 - iter 504/723 - loss 0.02141012 - time (sec): 37.19 - samples/sec: 3352.93 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 16:37:20,686 epoch 6 - iter 576/723 - loss 0.02233096 - time (sec): 42.16 - samples/sec: 3348.19 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 16:37:25,758 epoch 6 - iter 648/723 - loss 0.02339352 - time (sec): 47.23 - samples/sec: 3346.09 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 16:37:30,821 epoch 6 - iter 720/723 - loss 0.02328563 - time (sec): 52.29 - samples/sec: 3356.86 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 16:37:31,137 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:37:31,137 EPOCH 6 done: loss 0.0232 - lr: 0.000013 | |
| 2023-10-17 16:37:34,605 DEV : loss 0.1128404513001442 - f1-score (micro avg) 0.8366 | |
| 2023-10-17 16:37:34,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:37:40,108 epoch 7 - iter 72/723 - loss 0.01703668 - time (sec): 5.48 - samples/sec: 3361.43 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 16:37:45,433 epoch 7 - iter 144/723 - loss 0.01533515 - time (sec): 10.80 - samples/sec: 3352.87 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 16:37:50,493 epoch 7 - iter 216/723 - loss 0.01594799 - time (sec): 15.86 - samples/sec: 3353.59 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 16:37:55,922 epoch 7 - iter 288/723 - loss 0.01731920 - time (sec): 21.29 - samples/sec: 3335.13 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 16:38:01,120 epoch 7 - iter 360/723 - loss 0.01755588 - time (sec): 26.49 - samples/sec: 3360.12 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 16:38:06,133 epoch 7 - iter 432/723 - loss 0.01741061 - time (sec): 31.50 - samples/sec: 3366.32 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 16:38:11,380 epoch 7 - iter 504/723 - loss 0.01882233 - time (sec): 36.75 - samples/sec: 3343.50 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 16:38:16,383 epoch 7 - iter 576/723 - loss 0.01883728 - time (sec): 41.75 - samples/sec: 3356.38 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 16:38:21,516 epoch 7 - iter 648/723 - loss 0.01884261 - time (sec): 46.88 - samples/sec: 3354.11 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 16:38:26,987 epoch 7 - iter 720/723 - loss 0.01918716 - time (sec): 52.36 - samples/sec: 3354.59 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 16:38:27,191 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:38:27,191 EPOCH 7 done: loss 0.0192 - lr: 0.000010 | |
| 2023-10-17 16:38:31,364 DEV : loss 0.10547000914812088 - f1-score (micro avg) 0.8758 | |
| 2023-10-17 16:38:31,408 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:38:36,744 epoch 8 - iter 72/723 - loss 0.01480279 - time (sec): 5.33 - samples/sec: 3207.05 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 16:38:42,026 epoch 8 - iter 144/723 - loss 0.01398233 - time (sec): 10.62 - samples/sec: 3223.61 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 16:38:47,455 epoch 8 - iter 216/723 - loss 0.01388295 - time (sec): 16.04 - samples/sec: 3243.82 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 16:38:52,719 epoch 8 - iter 288/723 - loss 0.01560830 - time (sec): 21.31 - samples/sec: 3253.01 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 16:38:57,608 epoch 8 - iter 360/723 - loss 0.01346550 - time (sec): 26.20 - samples/sec: 3262.82 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 16:39:03,090 epoch 8 - iter 432/723 - loss 0.01242414 - time (sec): 31.68 - samples/sec: 3281.19 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 16:39:08,362 epoch 8 - iter 504/723 - loss 0.01329213 - time (sec): 36.95 - samples/sec: 3308.45 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 16:39:13,433 epoch 8 - iter 576/723 - loss 0.01413418 - time (sec): 42.02 - samples/sec: 3319.59 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 16:39:18,797 epoch 8 - iter 648/723 - loss 0.01466463 - time (sec): 47.39 - samples/sec: 3330.57 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 16:39:24,125 epoch 8 - iter 720/723 - loss 0.01453908 - time (sec): 52.72 - samples/sec: 3331.91 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 16:39:24,294 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:39:24,295 EPOCH 8 done: loss 0.0146 - lr: 0.000007 | |
| 2023-10-17 16:39:27,548 DEV : loss 0.11225023120641708 - f1-score (micro avg) 0.8738 | |
| 2023-10-17 16:39:27,569 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:39:33,008 epoch 9 - iter 72/723 - loss 0.01105950 - time (sec): 5.44 - samples/sec: 3327.69 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 16:39:38,897 epoch 9 - iter 144/723 - loss 0.01071290 - time (sec): 11.33 - samples/sec: 3253.51 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 16:39:43,889 epoch 9 - iter 216/723 - loss 0.01095588 - time (sec): 16.32 - samples/sec: 3309.64 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 16:39:49,555 epoch 9 - iter 288/723 - loss 0.01087741 - time (sec): 21.98 - samples/sec: 3242.17 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 16:39:54,889 epoch 9 - iter 360/723 - loss 0.01075241 - time (sec): 27.32 - samples/sec: 3274.38 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 16:40:00,069 epoch 9 - iter 432/723 - loss 0.01016298 - time (sec): 32.50 - samples/sec: 3297.01 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 16:40:05,009 epoch 9 - iter 504/723 - loss 0.01061815 - time (sec): 37.44 - samples/sec: 3311.66 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 16:40:10,029 epoch 9 - iter 576/723 - loss 0.00974392 - time (sec): 42.46 - samples/sec: 3324.65 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 16:40:15,475 epoch 9 - iter 648/723 - loss 0.00992418 - time (sec): 47.90 - samples/sec: 3306.12 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 16:40:21,097 epoch 9 - iter 720/723 - loss 0.00977684 - time (sec): 53.53 - samples/sec: 3279.59 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 16:40:21,279 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:40:21,279 EPOCH 9 done: loss 0.0097 - lr: 0.000003 | |
| 2023-10-17 16:40:24,489 DEV : loss 0.12020541727542877 - f1-score (micro avg) 0.8718 | |
| 2023-10-17 16:40:24,506 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:40:29,889 epoch 10 - iter 72/723 - loss 0.00414168 - time (sec): 5.38 - samples/sec: 3371.93 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 16:40:34,809 epoch 10 - iter 144/723 - loss 0.00510478 - time (sec): 10.30 - samples/sec: 3386.67 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 16:40:39,459 epoch 10 - iter 216/723 - loss 0.00443617 - time (sec): 14.95 - samples/sec: 3354.89 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 16:40:45,030 epoch 10 - iter 288/723 - loss 0.00582761 - time (sec): 20.52 - samples/sec: 3301.79 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 16:40:50,363 epoch 10 - iter 360/723 - loss 0.00623510 - time (sec): 25.86 - samples/sec: 3317.75 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 16:40:55,508 epoch 10 - iter 432/723 - loss 0.00600288 - time (sec): 31.00 - samples/sec: 3317.56 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 16:41:00,864 epoch 10 - iter 504/723 - loss 0.00660354 - time (sec): 36.36 - samples/sec: 3320.53 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 16:41:06,132 epoch 10 - iter 576/723 - loss 0.00641511 - time (sec): 41.63 - samples/sec: 3326.39 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 16:41:11,678 epoch 10 - iter 648/723 - loss 0.00674726 - time (sec): 47.17 - samples/sec: 3325.81 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 16:41:17,289 epoch 10 - iter 720/723 - loss 0.00692422 - time (sec): 52.78 - samples/sec: 3328.41 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 16:41:17,478 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:41:17,479 EPOCH 10 done: loss 0.0070 - lr: 0.000000 | |
| 2023-10-17 16:41:21,045 DEV : loss 0.12641684710979462 - f1-score (micro avg) 0.8674 | |
| 2023-10-17 16:41:21,413 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 16:41:21,415 Loading model from best epoch ... | |
| 2023-10-17 16:41:22,773 SequenceTagger predicts: Dictionary with 13 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 | |
| 2023-10-17 16:41:25,530 | |
| Results: | |
| - F-score (micro) 0.8635 | |
| - F-score (macro) 0.7539 | |
| - Accuracy 0.7666 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.8607 0.8589 0.8598 482 | |
| LOC 0.9405 0.8974 0.9184 458 | |
| ORG 0.5686 0.4203 0.4833 69 | |
| micro avg 0.8813 0.8464 0.8635 1009 | |
| macro avg 0.7899 0.7255 0.7539 1009 | |
| weighted avg 0.8770 0.8464 0.8607 1009 | |
| 2023-10-17 16:41:25,531 ---------------------------------------------------------------------------------------------------- | |