| 2023-10-25 16:43:02,295 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:43:02,296 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(64001, 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): BertEncoder( | |
| (layer): ModuleList( | |
| (0-11): 12 x BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (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): BertSelfOutput( | |
| (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): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (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) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): BertPooler( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=17, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-25 16:43:02,296 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:43:02,297 MultiCorpus: 7142 train + 698 dev + 2570 test sentences | |
| - NER_HIPE_2022 Corpus: 7142 train + 698 dev + 2570 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fr/with_doc_seperator | |
| 2023-10-25 16:43:02,297 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:43:02,297 Train: 7142 sentences | |
| 2023-10-25 16:43:02,297 (train_with_dev=False, train_with_test=False) | |
| 2023-10-25 16:43:02,297 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:43:02,297 Training Params: | |
| 2023-10-25 16:43:02,297 - learning_rate: "5e-05" | |
| 2023-10-25 16:43:02,297 - mini_batch_size: "4" | |
| 2023-10-25 16:43:02,297 - max_epochs: "10" | |
| 2023-10-25 16:43:02,297 - shuffle: "True" | |
| 2023-10-25 16:43:02,297 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:43:02,297 Plugins: | |
| 2023-10-25 16:43:02,297 - TensorboardLogger | |
| 2023-10-25 16:43:02,297 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-25 16:43:02,297 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:43:02,297 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-25 16:43:02,297 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-25 16:43:02,297 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:43:02,297 Computation: | |
| 2023-10-25 16:43:02,297 - compute on device: cuda:0 | |
| 2023-10-25 16:43:02,297 - embedding storage: none | |
| 2023-10-25 16:43:02,297 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:43:02,297 Model training base path: "hmbench-newseye/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-25 16:43:02,297 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:43:02,297 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:43:02,298 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-25 16:43:11,289 epoch 1 - iter 178/1786 - loss 1.45378237 - time (sec): 8.99 - samples/sec: 2659.75 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 16:43:20,433 epoch 1 - iter 356/1786 - loss 0.93304178 - time (sec): 18.13 - samples/sec: 2682.54 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 16:43:29,477 epoch 1 - iter 534/1786 - loss 0.71566950 - time (sec): 27.18 - samples/sec: 2689.20 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 16:43:38,629 epoch 1 - iter 712/1786 - loss 0.57975235 - time (sec): 36.33 - samples/sec: 2740.65 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 16:43:47,914 epoch 1 - iter 890/1786 - loss 0.50005371 - time (sec): 45.62 - samples/sec: 2703.93 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 16:43:57,141 epoch 1 - iter 1068/1786 - loss 0.44373858 - time (sec): 54.84 - samples/sec: 2703.05 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 16:44:06,506 epoch 1 - iter 1246/1786 - loss 0.40101552 - time (sec): 64.21 - samples/sec: 2717.29 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 16:44:15,329 epoch 1 - iter 1424/1786 - loss 0.37063676 - time (sec): 73.03 - samples/sec: 2725.88 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 16:44:24,451 epoch 1 - iter 1602/1786 - loss 0.34742944 - time (sec): 82.15 - samples/sec: 2719.27 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 16:44:33,521 epoch 1 - iter 1780/1786 - loss 0.32963004 - time (sec): 91.22 - samples/sec: 2720.76 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-25 16:44:33,806 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:44:33,806 EPOCH 1 done: loss 0.3291 - lr: 0.000050 | |
| 2023-10-25 16:44:37,513 DEV : loss 0.12235512584447861 - f1-score (micro avg) 0.6977 | |
| 2023-10-25 16:44:37,535 saving best model | |
| 2023-10-25 16:44:37,963 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:44:47,753 epoch 2 - iter 178/1786 - loss 0.11009699 - time (sec): 9.79 - samples/sec: 2572.43 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 16:44:56,942 epoch 2 - iter 356/1786 - loss 0.12454625 - time (sec): 18.98 - samples/sec: 2484.94 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 16:45:06,456 epoch 2 - iter 534/1786 - loss 0.12080083 - time (sec): 28.49 - samples/sec: 2540.42 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 16:45:16,189 epoch 2 - iter 712/1786 - loss 0.11952422 - time (sec): 38.22 - samples/sec: 2617.38 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 16:45:26,053 epoch 2 - iter 890/1786 - loss 0.12030277 - time (sec): 48.09 - samples/sec: 2591.09 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 16:45:35,690 epoch 2 - iter 1068/1786 - loss 0.12522982 - time (sec): 57.73 - samples/sec: 2576.11 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 16:45:45,520 epoch 2 - iter 1246/1786 - loss 0.12482694 - time (sec): 67.56 - samples/sec: 2571.93 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 16:45:55,287 epoch 2 - iter 1424/1786 - loss 0.12485904 - time (sec): 77.32 - samples/sec: 2556.90 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 16:46:04,934 epoch 2 - iter 1602/1786 - loss 0.12360576 - time (sec): 86.97 - samples/sec: 2567.48 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 16:46:14,635 epoch 2 - iter 1780/1786 - loss 0.12374358 - time (sec): 96.67 - samples/sec: 2565.28 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 16:46:14,962 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:46:14,962 EPOCH 2 done: loss 0.1238 - lr: 0.000044 | |
| 2023-10-25 16:46:20,240 DEV : loss 0.134212926030159 - f1-score (micro avg) 0.7343 | |
| 2023-10-25 16:46:20,263 saving best model | |
| 2023-10-25 16:46:20,926 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:46:30,366 epoch 3 - iter 178/1786 - loss 0.08791366 - time (sec): 9.44 - samples/sec: 2519.39 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 16:46:39,716 epoch 3 - iter 356/1786 - loss 0.08112124 - time (sec): 18.79 - samples/sec: 2566.74 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 16:46:49,214 epoch 3 - iter 534/1786 - loss 0.08541966 - time (sec): 28.28 - samples/sec: 2571.20 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 16:46:58,625 epoch 3 - iter 712/1786 - loss 0.08736614 - time (sec): 37.70 - samples/sec: 2548.74 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 16:47:07,261 epoch 3 - iter 890/1786 - loss 0.08744138 - time (sec): 46.33 - samples/sec: 2588.27 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 16:47:16,568 epoch 3 - iter 1068/1786 - loss 0.08990279 - time (sec): 55.64 - samples/sec: 2612.41 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 16:47:25,876 epoch 3 - iter 1246/1786 - loss 0.08782874 - time (sec): 64.95 - samples/sec: 2626.69 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 16:47:35,000 epoch 3 - iter 1424/1786 - loss 0.08769815 - time (sec): 74.07 - samples/sec: 2664.16 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 16:47:44,314 epoch 3 - iter 1602/1786 - loss 0.08681656 - time (sec): 83.38 - samples/sec: 2671.97 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 16:47:54,170 epoch 3 - iter 1780/1786 - loss 0.08576985 - time (sec): 93.24 - samples/sec: 2659.07 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 16:47:54,479 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:47:54,480 EPOCH 3 done: loss 0.0858 - lr: 0.000039 | |
| 2023-10-25 16:47:58,576 DEV : loss 0.12481703609228134 - f1-score (micro avg) 0.7755 | |
| 2023-10-25 16:47:58,596 saving best model | |
| 2023-10-25 16:47:59,214 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:48:08,403 epoch 4 - iter 178/1786 - loss 0.05743631 - time (sec): 9.19 - samples/sec: 2586.25 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 16:48:17,685 epoch 4 - iter 356/1786 - loss 0.06039085 - time (sec): 18.47 - samples/sec: 2609.33 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 16:48:26,917 epoch 4 - iter 534/1786 - loss 0.06503086 - time (sec): 27.70 - samples/sec: 2577.70 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 16:48:36,509 epoch 4 - iter 712/1786 - loss 0.06256415 - time (sec): 37.29 - samples/sec: 2616.03 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 16:48:46,107 epoch 4 - iter 890/1786 - loss 0.06118770 - time (sec): 46.89 - samples/sec: 2594.71 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 16:48:55,636 epoch 4 - iter 1068/1786 - loss 0.05963180 - time (sec): 56.42 - samples/sec: 2607.15 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 16:49:04,855 epoch 4 - iter 1246/1786 - loss 0.05897814 - time (sec): 65.64 - samples/sec: 2625.60 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 16:49:14,206 epoch 4 - iter 1424/1786 - loss 0.05970310 - time (sec): 74.99 - samples/sec: 2647.47 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 16:49:23,487 epoch 4 - iter 1602/1786 - loss 0.06044374 - time (sec): 84.27 - samples/sec: 2641.39 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 16:49:32,546 epoch 4 - iter 1780/1786 - loss 0.06192366 - time (sec): 93.33 - samples/sec: 2659.21 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 16:49:32,845 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:49:32,845 EPOCH 4 done: loss 0.0619 - lr: 0.000033 | |
| 2023-10-25 16:49:38,355 DEV : loss 0.16044431924819946 - f1-score (micro avg) 0.7783 | |
| 2023-10-25 16:49:38,377 saving best model | |
| 2023-10-25 16:49:39,035 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:49:48,600 epoch 5 - iter 178/1786 - loss 0.04283270 - time (sec): 9.56 - samples/sec: 2536.11 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 16:49:58,109 epoch 5 - iter 356/1786 - loss 0.04236730 - time (sec): 19.07 - samples/sec: 2520.49 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 16:50:07,568 epoch 5 - iter 534/1786 - loss 0.04395019 - time (sec): 28.53 - samples/sec: 2554.66 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 16:50:16,987 epoch 5 - iter 712/1786 - loss 0.04509292 - time (sec): 37.95 - samples/sec: 2557.19 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 16:50:26,661 epoch 5 - iter 890/1786 - loss 0.04654452 - time (sec): 47.62 - samples/sec: 2531.00 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 16:50:35,855 epoch 5 - iter 1068/1786 - loss 0.04714761 - time (sec): 56.82 - samples/sec: 2544.60 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 16:50:45,270 epoch 5 - iter 1246/1786 - loss 0.04640989 - time (sec): 66.23 - samples/sec: 2576.37 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 16:50:54,610 epoch 5 - iter 1424/1786 - loss 0.04708893 - time (sec): 75.57 - samples/sec: 2583.88 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 16:51:04,080 epoch 5 - iter 1602/1786 - loss 0.04608268 - time (sec): 85.04 - samples/sec: 2618.42 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 16:51:13,475 epoch 5 - iter 1780/1786 - loss 0.04691280 - time (sec): 94.44 - samples/sec: 2627.61 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 16:51:13,782 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:51:13,782 EPOCH 5 done: loss 0.0470 - lr: 0.000028 | |
| 2023-10-25 16:51:18,567 DEV : loss 0.17284664511680603 - f1-score (micro avg) 0.7803 | |
| 2023-10-25 16:51:18,590 saving best model | |
| 2023-10-25 16:51:19,223 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:51:28,958 epoch 6 - iter 178/1786 - loss 0.02819640 - time (sec): 9.73 - samples/sec: 2444.80 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 16:51:39,162 epoch 6 - iter 356/1786 - loss 0.03229239 - time (sec): 19.93 - samples/sec: 2448.77 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 16:51:48,857 epoch 6 - iter 534/1786 - loss 0.03285797 - time (sec): 29.63 - samples/sec: 2480.74 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 16:51:58,387 epoch 6 - iter 712/1786 - loss 0.03248761 - time (sec): 39.16 - samples/sec: 2509.74 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 16:52:08,095 epoch 6 - iter 890/1786 - loss 0.03398336 - time (sec): 48.87 - samples/sec: 2528.28 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 16:52:17,520 epoch 6 - iter 1068/1786 - loss 0.03529381 - time (sec): 58.29 - samples/sec: 2535.57 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 16:52:26,944 epoch 6 - iter 1246/1786 - loss 0.03463349 - time (sec): 67.72 - samples/sec: 2551.34 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 16:52:35,802 epoch 6 - iter 1424/1786 - loss 0.03499563 - time (sec): 76.58 - samples/sec: 2595.86 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 16:52:44,941 epoch 6 - iter 1602/1786 - loss 0.03486030 - time (sec): 85.71 - samples/sec: 2601.21 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 16:52:54,233 epoch 6 - iter 1780/1786 - loss 0.03521717 - time (sec): 95.01 - samples/sec: 2610.73 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 16:52:54,564 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:52:54,565 EPOCH 6 done: loss 0.0352 - lr: 0.000022 | |
| 2023-10-25 16:52:58,634 DEV : loss 0.20039449632167816 - f1-score (micro avg) 0.7776 | |
| 2023-10-25 16:52:58,654 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:53:08,459 epoch 7 - iter 178/1786 - loss 0.02293913 - time (sec): 9.80 - samples/sec: 2648.88 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 16:53:17,737 epoch 7 - iter 356/1786 - loss 0.02877433 - time (sec): 19.08 - samples/sec: 2696.39 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 16:53:26,727 epoch 7 - iter 534/1786 - loss 0.02882588 - time (sec): 28.07 - samples/sec: 2740.52 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 16:53:35,648 epoch 7 - iter 712/1786 - loss 0.02837660 - time (sec): 36.99 - samples/sec: 2758.54 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 16:53:44,446 epoch 7 - iter 890/1786 - loss 0.02902311 - time (sec): 45.79 - samples/sec: 2749.16 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 16:53:53,520 epoch 7 - iter 1068/1786 - loss 0.02846830 - time (sec): 54.86 - samples/sec: 2759.74 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 16:54:02,597 epoch 7 - iter 1246/1786 - loss 0.02876862 - time (sec): 63.94 - samples/sec: 2741.64 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 16:54:11,486 epoch 7 - iter 1424/1786 - loss 0.02932430 - time (sec): 72.83 - samples/sec: 2740.03 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 16:54:20,497 epoch 7 - iter 1602/1786 - loss 0.02841907 - time (sec): 81.84 - samples/sec: 2745.43 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 16:54:29,380 epoch 7 - iter 1780/1786 - loss 0.02858842 - time (sec): 90.72 - samples/sec: 2734.08 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 16:54:29,672 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:54:29,672 EPOCH 7 done: loss 0.0289 - lr: 0.000017 | |
| 2023-10-25 16:54:34,531 DEV : loss 0.22098971903324127 - f1-score (micro avg) 0.7876 | |
| 2023-10-25 16:54:34,551 saving best model | |
| 2023-10-25 16:54:35,194 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:54:44,572 epoch 8 - iter 178/1786 - loss 0.02169155 - time (sec): 9.38 - samples/sec: 2654.07 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 16:54:53,735 epoch 8 - iter 356/1786 - loss 0.01714173 - time (sec): 18.54 - samples/sec: 2589.20 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 16:55:03,349 epoch 8 - iter 534/1786 - loss 0.01731940 - time (sec): 28.15 - samples/sec: 2653.23 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 16:55:13,278 epoch 8 - iter 712/1786 - loss 0.01925732 - time (sec): 38.08 - samples/sec: 2600.12 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 16:55:23,123 epoch 8 - iter 890/1786 - loss 0.01944035 - time (sec): 47.93 - samples/sec: 2585.83 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 16:55:32,661 epoch 8 - iter 1068/1786 - loss 0.02028566 - time (sec): 57.47 - samples/sec: 2612.32 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 16:55:42,030 epoch 8 - iter 1246/1786 - loss 0.01959077 - time (sec): 66.83 - samples/sec: 2613.50 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 16:55:51,388 epoch 8 - iter 1424/1786 - loss 0.01983005 - time (sec): 76.19 - samples/sec: 2620.69 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 16:56:00,691 epoch 8 - iter 1602/1786 - loss 0.01957523 - time (sec): 85.49 - samples/sec: 2609.85 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 16:56:09,973 epoch 8 - iter 1780/1786 - loss 0.01982825 - time (sec): 94.78 - samples/sec: 2616.70 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 16:56:10,283 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:56:10,283 EPOCH 8 done: loss 0.0198 - lr: 0.000011 | |
| 2023-10-25 16:56:15,406 DEV : loss 0.20933707058429718 - f1-score (micro avg) 0.7974 | |
| 2023-10-25 16:56:15,428 saving best model | |
| 2023-10-25 16:56:16,096 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:56:25,740 epoch 9 - iter 178/1786 - loss 0.01146613 - time (sec): 9.64 - samples/sec: 2777.26 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 16:56:35,297 epoch 9 - iter 356/1786 - loss 0.01095974 - time (sec): 19.20 - samples/sec: 2706.00 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 16:56:44,858 epoch 9 - iter 534/1786 - loss 0.01109824 - time (sec): 28.76 - samples/sec: 2711.74 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 16:56:54,357 epoch 9 - iter 712/1786 - loss 0.01223294 - time (sec): 38.26 - samples/sec: 2646.45 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 16:57:03,245 epoch 9 - iter 890/1786 - loss 0.01428256 - time (sec): 47.15 - samples/sec: 2622.70 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 16:57:13,030 epoch 9 - iter 1068/1786 - loss 0.01408829 - time (sec): 56.93 - samples/sec: 2577.98 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 16:57:22,570 epoch 9 - iter 1246/1786 - loss 0.01364858 - time (sec): 66.47 - samples/sec: 2591.21 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 16:57:32,127 epoch 9 - iter 1424/1786 - loss 0.01415031 - time (sec): 76.03 - samples/sec: 2592.78 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 16:57:41,737 epoch 9 - iter 1602/1786 - loss 0.01407302 - time (sec): 85.64 - samples/sec: 2585.35 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 16:57:51,504 epoch 9 - iter 1780/1786 - loss 0.01349476 - time (sec): 95.41 - samples/sec: 2600.15 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 16:57:51,822 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:57:51,822 EPOCH 9 done: loss 0.0135 - lr: 0.000006 | |
| 2023-10-25 16:57:55,962 DEV : loss 0.22414454817771912 - f1-score (micro avg) 0.7875 | |
| 2023-10-25 16:57:55,985 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:58:05,491 epoch 10 - iter 178/1786 - loss 0.00869565 - time (sec): 9.50 - samples/sec: 2750.03 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 16:58:15,181 epoch 10 - iter 356/1786 - loss 0.01198228 - time (sec): 19.19 - samples/sec: 2617.47 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 16:58:24,834 epoch 10 - iter 534/1786 - loss 0.01085531 - time (sec): 28.85 - samples/sec: 2622.23 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 16:58:34,473 epoch 10 - iter 712/1786 - loss 0.01062124 - time (sec): 38.49 - samples/sec: 2583.11 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 16:58:44,048 epoch 10 - iter 890/1786 - loss 0.01027501 - time (sec): 48.06 - samples/sec: 2571.89 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 16:58:54,165 epoch 10 - iter 1068/1786 - loss 0.00904330 - time (sec): 58.18 - samples/sec: 2569.09 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 16:59:03,908 epoch 10 - iter 1246/1786 - loss 0.00884235 - time (sec): 67.92 - samples/sec: 2579.40 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 16:59:14,101 epoch 10 - iter 1424/1786 - loss 0.00828459 - time (sec): 78.11 - samples/sec: 2561.48 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 16:59:23,878 epoch 10 - iter 1602/1786 - loss 0.00846272 - time (sec): 87.89 - samples/sec: 2545.19 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 16:59:33,738 epoch 10 - iter 1780/1786 - loss 0.00805437 - time (sec): 97.75 - samples/sec: 2539.55 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 16:59:34,058 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:59:34,059 EPOCH 10 done: loss 0.0080 - lr: 0.000000 | |
| 2023-10-25 16:59:39,124 DEV : loss 0.2354690432548523 - f1-score (micro avg) 0.7925 | |
| 2023-10-25 16:59:39,628 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 16:59:39,629 Loading model from best epoch ... | |
| 2023-10-25 16:59:41,607 SequenceTagger predicts: Dictionary with 17 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd | |
| 2023-10-25 16:59:53,902 | |
| Results: | |
| - F-score (micro) 0.6776 | |
| - F-score (macro) 0.5945 | |
| - Accuracy 0.5288 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.6810 0.6804 0.6807 1095 | |
| PER 0.7603 0.7678 0.7640 1012 | |
| ORG 0.4243 0.5574 0.4818 357 | |
| HumanProd 0.3500 0.6364 0.4516 33 | |
| micro avg 0.6586 0.6976 0.6776 2497 | |
| macro avg 0.5539 0.6605 0.5945 2497 | |
| weighted avg 0.6720 0.6976 0.6830 2497 | |
| 2023-10-25 16:59:53,903 ---------------------------------------------------------------------------------------------------- | |