| 2023-10-18 16:47:00,554 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:00,554 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(32001, 128) | |
| (position_embeddings): Embedding(512, 128) | |
| (token_type_embeddings): Embedding(2, 128) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (encoder): BertEncoder( | |
| (layer): ModuleList( | |
| (0-1): 2 x BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=128, out_features=128, bias=True) | |
| (key): Linear(in_features=128, out_features=128, bias=True) | |
| (value): Linear(in_features=128, out_features=128, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=128, out_features=128, bias=True) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=128, out_features=512, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=512, out_features=128, bias=True) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): BertPooler( | |
| (dense): Linear(in_features=128, out_features=128, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=128, out_features=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-18 16:47:00,554 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:00,554 MultiCorpus: 966 train + 219 dev + 204 test sentences | |
| - NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator | |
| 2023-10-18 16:47:00,554 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:00,554 Train: 966 sentences | |
| 2023-10-18 16:47:00,554 (train_with_dev=False, train_with_test=False) | |
| 2023-10-18 16:47:00,554 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:00,555 Training Params: | |
| 2023-10-18 16:47:00,555 - learning_rate: "3e-05" | |
| 2023-10-18 16:47:00,555 - mini_batch_size: "4" | |
| 2023-10-18 16:47:00,555 - max_epochs: "10" | |
| 2023-10-18 16:47:00,555 - shuffle: "True" | |
| 2023-10-18 16:47:00,555 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:00,555 Plugins: | |
| 2023-10-18 16:47:00,555 - TensorboardLogger | |
| 2023-10-18 16:47:00,555 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-18 16:47:00,555 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:00,555 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-18 16:47:00,555 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-18 16:47:00,555 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:00,555 Computation: | |
| 2023-10-18 16:47:00,555 - compute on device: cuda:0 | |
| 2023-10-18 16:47:00,555 - embedding storage: none | |
| 2023-10-18 16:47:00,555 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:00,555 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-18 16:47:00,555 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:00,555 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:00,555 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-18 16:47:00,951 epoch 1 - iter 24/242 - loss 3.76639759 - time (sec): 0.40 - samples/sec: 5880.53 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 16:47:01,330 epoch 1 - iter 48/242 - loss 3.73342428 - time (sec): 0.77 - samples/sec: 5556.56 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:47:01,703 epoch 1 - iter 72/242 - loss 3.64725163 - time (sec): 1.15 - samples/sec: 6229.41 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:47:02,079 epoch 1 - iter 96/242 - loss 3.55247058 - time (sec): 1.52 - samples/sec: 6230.21 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 16:47:02,467 epoch 1 - iter 120/242 - loss 3.44348324 - time (sec): 1.91 - samples/sec: 6242.24 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:47:02,831 epoch 1 - iter 144/242 - loss 3.30204480 - time (sec): 2.28 - samples/sec: 6172.26 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 16:47:03,226 epoch 1 - iter 168/242 - loss 3.09396194 - time (sec): 2.67 - samples/sec: 6289.56 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:47:03,631 epoch 1 - iter 192/242 - loss 2.86781813 - time (sec): 3.08 - samples/sec: 6409.18 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:47:04,029 epoch 1 - iter 216/242 - loss 2.66454985 - time (sec): 3.47 - samples/sec: 6420.56 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 16:47:04,403 epoch 1 - iter 240/242 - loss 2.50993096 - time (sec): 3.85 - samples/sec: 6407.86 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-18 16:47:04,427 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:04,427 EPOCH 1 done: loss 2.5068 - lr: 0.000030 | |
| 2023-10-18 16:47:04,697 DEV : loss 0.6627914309501648 - f1-score (micro avg) 0.0 | |
| 2023-10-18 16:47:04,702 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:05,085 epoch 2 - iter 24/242 - loss 0.82122813 - time (sec): 0.38 - samples/sec: 5997.12 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-18 16:47:05,456 epoch 2 - iter 48/242 - loss 0.79828779 - time (sec): 0.75 - samples/sec: 6344.26 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 16:47:05,832 epoch 2 - iter 72/242 - loss 0.77306168 - time (sec): 1.13 - samples/sec: 6377.69 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 16:47:06,228 epoch 2 - iter 96/242 - loss 0.77914231 - time (sec): 1.53 - samples/sec: 6472.66 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 16:47:06,597 epoch 2 - iter 120/242 - loss 0.76849395 - time (sec): 1.90 - samples/sec: 6378.06 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 16:47:06,984 epoch 2 - iter 144/242 - loss 0.75503933 - time (sec): 2.28 - samples/sec: 6448.07 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 16:47:07,355 epoch 2 - iter 168/242 - loss 0.72024474 - time (sec): 2.65 - samples/sec: 6524.24 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 16:47:07,734 epoch 2 - iter 192/242 - loss 0.70701431 - time (sec): 3.03 - samples/sec: 6533.29 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 16:47:08,099 epoch 2 - iter 216/242 - loss 0.71119737 - time (sec): 3.40 - samples/sec: 6505.46 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 16:47:08,470 epoch 2 - iter 240/242 - loss 0.70468619 - time (sec): 3.77 - samples/sec: 6504.57 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 16:47:08,501 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:08,501 EPOCH 2 done: loss 0.7067 - lr: 0.000027 | |
| 2023-10-18 16:47:08,928 DEV : loss 0.5348415374755859 - f1-score (micro avg) 0.0 | |
| 2023-10-18 16:47:08,934 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:09,309 epoch 3 - iter 24/242 - loss 0.59689708 - time (sec): 0.37 - samples/sec: 6668.20 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 16:47:09,665 epoch 3 - iter 48/242 - loss 0.61770318 - time (sec): 0.73 - samples/sec: 6565.33 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 16:47:10,027 epoch 3 - iter 72/242 - loss 0.59676560 - time (sec): 1.09 - samples/sec: 6453.82 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 16:47:10,405 epoch 3 - iter 96/242 - loss 0.59375241 - time (sec): 1.47 - samples/sec: 6495.20 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 16:47:10,781 epoch 3 - iter 120/242 - loss 0.58355032 - time (sec): 1.85 - samples/sec: 6512.62 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 16:47:11,151 epoch 3 - iter 144/242 - loss 0.56794372 - time (sec): 2.22 - samples/sec: 6443.42 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 16:47:11,543 epoch 3 - iter 168/242 - loss 0.55662652 - time (sec): 2.61 - samples/sec: 6464.84 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:47:11,922 epoch 3 - iter 192/242 - loss 0.54741459 - time (sec): 2.99 - samples/sec: 6593.14 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:47:12,306 epoch 3 - iter 216/242 - loss 0.53634072 - time (sec): 3.37 - samples/sec: 6586.12 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:47:12,676 epoch 3 - iter 240/242 - loss 0.53625803 - time (sec): 3.74 - samples/sec: 6568.55 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 16:47:12,703 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:12,703 EPOCH 3 done: loss 0.5360 - lr: 0.000023 | |
| 2023-10-18 16:47:13,236 DEV : loss 0.4032635986804962 - f1-score (micro avg) 0.2232 | |
| 2023-10-18 16:47:13,241 saving best model | |
| 2023-10-18 16:47:13,274 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:13,626 epoch 4 - iter 24/242 - loss 0.48847219 - time (sec): 0.35 - samples/sec: 5951.73 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 16:47:13,993 epoch 4 - iter 48/242 - loss 0.50216610 - time (sec): 0.72 - samples/sec: 6233.41 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 16:47:14,358 epoch 4 - iter 72/242 - loss 0.48281716 - time (sec): 1.08 - samples/sec: 6713.69 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 16:47:14,718 epoch 4 - iter 96/242 - loss 0.48917480 - time (sec): 1.44 - samples/sec: 6672.48 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 16:47:15,084 epoch 4 - iter 120/242 - loss 0.49062846 - time (sec): 1.81 - samples/sec: 6674.60 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 16:47:15,453 epoch 4 - iter 144/242 - loss 0.47928779 - time (sec): 2.18 - samples/sec: 6703.20 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:47:15,827 epoch 4 - iter 168/242 - loss 0.47758911 - time (sec): 2.55 - samples/sec: 6782.13 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:47:16,209 epoch 4 - iter 192/242 - loss 0.46633417 - time (sec): 2.93 - samples/sec: 6741.43 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:47:16,604 epoch 4 - iter 216/242 - loss 0.47357903 - time (sec): 3.33 - samples/sec: 6679.64 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 16:47:16,978 epoch 4 - iter 240/242 - loss 0.46532823 - time (sec): 3.70 - samples/sec: 6660.06 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 16:47:17,002 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:17,003 EPOCH 4 done: loss 0.4648 - lr: 0.000020 | |
| 2023-10-18 16:47:17,431 DEV : loss 0.365567684173584 - f1-score (micro avg) 0.4485 | |
| 2023-10-18 16:47:17,436 saving best model | |
| 2023-10-18 16:47:17,476 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:17,844 epoch 5 - iter 24/242 - loss 0.44890096 - time (sec): 0.37 - samples/sec: 6696.85 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 16:47:18,246 epoch 5 - iter 48/242 - loss 0.44130695 - time (sec): 0.77 - samples/sec: 6543.27 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 16:47:18,626 epoch 5 - iter 72/242 - loss 0.42853703 - time (sec): 1.15 - samples/sec: 6549.01 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 16:47:19,000 epoch 5 - iter 96/242 - loss 0.43923635 - time (sec): 1.52 - samples/sec: 6681.63 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 16:47:19,374 epoch 5 - iter 120/242 - loss 0.44049106 - time (sec): 1.90 - samples/sec: 6637.26 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 16:47:19,742 epoch 5 - iter 144/242 - loss 0.43757294 - time (sec): 2.27 - samples/sec: 6625.48 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 16:47:20,110 epoch 5 - iter 168/242 - loss 0.42993655 - time (sec): 2.63 - samples/sec: 6618.99 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 16:47:20,479 epoch 5 - iter 192/242 - loss 0.42908651 - time (sec): 3.00 - samples/sec: 6641.72 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 16:47:20,837 epoch 5 - iter 216/242 - loss 0.41548288 - time (sec): 3.36 - samples/sec: 6639.30 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 16:47:21,212 epoch 5 - iter 240/242 - loss 0.41362927 - time (sec): 3.74 - samples/sec: 6593.89 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 16:47:21,242 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:21,242 EPOCH 5 done: loss 0.4141 - lr: 0.000017 | |
| 2023-10-18 16:47:21,666 DEV : loss 0.3212338984012604 - f1-score (micro avg) 0.4986 | |
| 2023-10-18 16:47:21,670 saving best model | |
| 2023-10-18 16:47:21,706 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:22,086 epoch 6 - iter 24/242 - loss 0.40059705 - time (sec): 0.38 - samples/sec: 6774.81 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 16:47:22,455 epoch 6 - iter 48/242 - loss 0.39378742 - time (sec): 0.75 - samples/sec: 6698.45 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 16:47:22,826 epoch 6 - iter 72/242 - loss 0.40630980 - time (sec): 1.12 - samples/sec: 6737.98 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 16:47:23,189 epoch 6 - iter 96/242 - loss 0.36909927 - time (sec): 1.48 - samples/sec: 6580.10 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:47:23,570 epoch 6 - iter 120/242 - loss 0.36797436 - time (sec): 1.86 - samples/sec: 6597.95 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:47:23,949 epoch 6 - iter 144/242 - loss 0.37121158 - time (sec): 2.24 - samples/sec: 6592.68 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:47:24,319 epoch 6 - iter 168/242 - loss 0.37691583 - time (sec): 2.61 - samples/sec: 6557.87 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 16:47:24,694 epoch 6 - iter 192/242 - loss 0.37827567 - time (sec): 2.99 - samples/sec: 6587.30 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 16:47:25,051 epoch 6 - iter 216/242 - loss 0.38100322 - time (sec): 3.34 - samples/sec: 6560.87 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 16:47:25,450 epoch 6 - iter 240/242 - loss 0.38145838 - time (sec): 3.74 - samples/sec: 6562.11 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 16:47:25,481 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:25,481 EPOCH 6 done: loss 0.3823 - lr: 0.000013 | |
| 2023-10-18 16:47:25,912 DEV : loss 0.31136083602905273 - f1-score (micro avg) 0.4986 | |
| 2023-10-18 16:47:25,917 saving best model | |
| 2023-10-18 16:47:25,950 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:26,327 epoch 7 - iter 24/242 - loss 0.43051851 - time (sec): 0.38 - samples/sec: 6853.70 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 16:47:26,690 epoch 7 - iter 48/242 - loss 0.43701943 - time (sec): 0.74 - samples/sec: 6349.38 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 16:47:27,057 epoch 7 - iter 72/242 - loss 0.40358477 - time (sec): 1.11 - samples/sec: 6392.77 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 16:47:27,425 epoch 7 - iter 96/242 - loss 0.38468774 - time (sec): 1.47 - samples/sec: 6380.23 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 16:47:27,799 epoch 7 - iter 120/242 - loss 0.37050174 - time (sec): 1.85 - samples/sec: 6444.78 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 16:47:28,162 epoch 7 - iter 144/242 - loss 0.36178147 - time (sec): 2.21 - samples/sec: 6554.91 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 16:47:28,525 epoch 7 - iter 168/242 - loss 0.35972132 - time (sec): 2.57 - samples/sec: 6582.76 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 16:47:28,909 epoch 7 - iter 192/242 - loss 0.35756300 - time (sec): 2.96 - samples/sec: 6721.86 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 16:47:29,263 epoch 7 - iter 216/242 - loss 0.35542774 - time (sec): 3.31 - samples/sec: 6696.91 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 16:47:29,626 epoch 7 - iter 240/242 - loss 0.36168146 - time (sec): 3.67 - samples/sec: 6678.40 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 16:47:29,656 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:29,656 EPOCH 7 done: loss 0.3632 - lr: 0.000010 | |
| 2023-10-18 16:47:30,086 DEV : loss 0.29230672121047974 - f1-score (micro avg) 0.4961 | |
| 2023-10-18 16:47:30,090 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:30,466 epoch 8 - iter 24/242 - loss 0.33046592 - time (sec): 0.38 - samples/sec: 7100.41 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 16:47:30,832 epoch 8 - iter 48/242 - loss 0.34592806 - time (sec): 0.74 - samples/sec: 7052.48 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:47:31,203 epoch 8 - iter 72/242 - loss 0.36987575 - time (sec): 1.11 - samples/sec: 6745.81 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:47:31,567 epoch 8 - iter 96/242 - loss 0.36029067 - time (sec): 1.48 - samples/sec: 6672.03 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:47:31,944 epoch 8 - iter 120/242 - loss 0.35377072 - time (sec): 1.85 - samples/sec: 6689.21 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 16:47:32,339 epoch 8 - iter 144/242 - loss 0.36792821 - time (sec): 2.25 - samples/sec: 6716.35 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 16:47:32,702 epoch 8 - iter 168/242 - loss 0.36873922 - time (sec): 2.61 - samples/sec: 6649.56 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 16:47:33,065 epoch 8 - iter 192/242 - loss 0.35932191 - time (sec): 2.97 - samples/sec: 6636.88 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 16:47:33,434 epoch 8 - iter 216/242 - loss 0.35430138 - time (sec): 3.34 - samples/sec: 6652.25 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 16:47:33,802 epoch 8 - iter 240/242 - loss 0.35415251 - time (sec): 3.71 - samples/sec: 6625.50 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 16:47:33,832 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:33,832 EPOCH 8 done: loss 0.3559 - lr: 0.000007 | |
| 2023-10-18 16:47:34,259 DEV : loss 0.29471439123153687 - f1-score (micro avg) 0.4902 | |
| 2023-10-18 16:47:34,264 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:34,614 epoch 9 - iter 24/242 - loss 0.31338016 - time (sec): 0.35 - samples/sec: 5813.80 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:47:34,977 epoch 9 - iter 48/242 - loss 0.32685717 - time (sec): 0.71 - samples/sec: 6323.49 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:47:35,341 epoch 9 - iter 72/242 - loss 0.34641912 - time (sec): 1.08 - samples/sec: 6627.05 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:47:35,705 epoch 9 - iter 96/242 - loss 0.37020098 - time (sec): 1.44 - samples/sec: 6656.11 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 16:47:36,061 epoch 9 - iter 120/242 - loss 0.37255005 - time (sec): 1.80 - samples/sec: 6704.84 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 16:47:36,426 epoch 9 - iter 144/242 - loss 0.35340386 - time (sec): 2.16 - samples/sec: 6606.85 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 16:47:36,790 epoch 9 - iter 168/242 - loss 0.35863686 - time (sec): 2.53 - samples/sec: 6529.80 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 16:47:37,152 epoch 9 - iter 192/242 - loss 0.35692543 - time (sec): 2.89 - samples/sec: 6659.77 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 16:47:37,534 epoch 9 - iter 216/242 - loss 0.34917275 - time (sec): 3.27 - samples/sec: 6725.22 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 16:47:37,913 epoch 9 - iter 240/242 - loss 0.34647813 - time (sec): 3.65 - samples/sec: 6770.33 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 16:47:37,940 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:37,940 EPOCH 9 done: loss 0.3466 - lr: 0.000003 | |
| 2023-10-18 16:47:38,368 DEV : loss 0.283136248588562 - f1-score (micro avg) 0.493 | |
| 2023-10-18 16:47:38,372 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:38,757 epoch 10 - iter 24/242 - loss 0.31872653 - time (sec): 0.39 - samples/sec: 5826.81 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 16:47:39,134 epoch 10 - iter 48/242 - loss 0.31888086 - time (sec): 0.76 - samples/sec: 6154.12 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 16:47:39,499 epoch 10 - iter 72/242 - loss 0.32437333 - time (sec): 1.13 - samples/sec: 6316.66 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 16:47:39,866 epoch 10 - iter 96/242 - loss 0.31755177 - time (sec): 1.49 - samples/sec: 6487.64 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 16:47:40,249 epoch 10 - iter 120/242 - loss 0.33455278 - time (sec): 1.88 - samples/sec: 6404.49 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 16:47:40,638 epoch 10 - iter 144/242 - loss 0.34757879 - time (sec): 2.27 - samples/sec: 6518.36 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 16:47:41,000 epoch 10 - iter 168/242 - loss 0.33389621 - time (sec): 2.63 - samples/sec: 6563.72 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 16:47:41,364 epoch 10 - iter 192/242 - loss 0.33747535 - time (sec): 2.99 - samples/sec: 6567.69 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 16:47:41,735 epoch 10 - iter 216/242 - loss 0.33639765 - time (sec): 3.36 - samples/sec: 6583.43 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-18 16:47:42,099 epoch 10 - iter 240/242 - loss 0.34423205 - time (sec): 3.73 - samples/sec: 6589.06 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-18 16:47:42,134 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:42,134 EPOCH 10 done: loss 0.3424 - lr: 0.000000 | |
| 2023-10-18 16:47:42,567 DEV : loss 0.28324687480926514 - f1-score (micro avg) 0.491 | |
| 2023-10-18 16:47:42,601 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:47:42,601 Loading model from best epoch ... | |
| 2023-10-18 16:47:42,681 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date | |
| 2023-10-18 16:47:43,093 | |
| Results: | |
| - F-score (micro) 0.4451 | |
| - F-score (macro) 0.2046 | |
| - Accuracy 0.3029 | |
| By class: | |
| precision recall f1-score support | |
| pers 0.5220 0.6835 0.5919 139 | |
| scope 0.3961 0.4729 0.4311 129 | |
| work 0.0000 0.0000 0.0000 80 | |
| loc 0.0000 0.0000 0.0000 9 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.4575 0.4333 0.4451 360 | |
| macro avg 0.1836 0.2313 0.2046 360 | |
| weighted avg 0.3435 0.4333 0.3830 360 | |
| 2023-10-18 16:47:43,093 ---------------------------------------------------------------------------------------------------- | |