| 2023-10-18 14:40:31,010 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:31,010 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 14:40:31,010 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:31,011 MultiCorpus: 1100 train + 206 dev + 240 test sentences | |
| - NER_HIPE_2022 Corpus: 1100 train + 206 dev + 240 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/de/with_doc_seperator | |
| 2023-10-18 14:40:31,011 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:31,011 Train: 1100 sentences | |
| 2023-10-18 14:40:31,011 (train_with_dev=False, train_with_test=False) | |
| 2023-10-18 14:40:31,011 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:31,011 Training Params: | |
| 2023-10-18 14:40:31,011 - learning_rate: "5e-05" | |
| 2023-10-18 14:40:31,011 - mini_batch_size: "4" | |
| 2023-10-18 14:40:31,011 - max_epochs: "10" | |
| 2023-10-18 14:40:31,011 - shuffle: "True" | |
| 2023-10-18 14:40:31,011 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:31,011 Plugins: | |
| 2023-10-18 14:40:31,011 - TensorboardLogger | |
| 2023-10-18 14:40:31,011 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-18 14:40:31,011 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:31,011 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-18 14:40:31,011 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-18 14:40:31,011 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:31,011 Computation: | |
| 2023-10-18 14:40:31,011 - compute on device: cuda:0 | |
| 2023-10-18 14:40:31,011 - embedding storage: none | |
| 2023-10-18 14:40:31,011 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:31,011 Model training base path: "hmbench-ajmc/de-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-18 14:40:31,011 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:31,011 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:31,011 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-18 14:40:31,380 epoch 1 - iter 27/275 - loss 3.82857549 - time (sec): 0.37 - samples/sec: 6118.49 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 14:40:31,755 epoch 1 - iter 54/275 - loss 3.84181922 - time (sec): 0.74 - samples/sec: 5965.82 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 14:40:32,144 epoch 1 - iter 81/275 - loss 3.61759856 - time (sec): 1.13 - samples/sec: 5980.42 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 14:40:32,578 epoch 1 - iter 108/275 - loss 3.41470515 - time (sec): 1.57 - samples/sec: 5702.80 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 14:40:32,991 epoch 1 - iter 135/275 - loss 3.18722021 - time (sec): 1.98 - samples/sec: 5564.63 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 14:40:33,393 epoch 1 - iter 162/275 - loss 2.92161478 - time (sec): 2.38 - samples/sec: 5529.73 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 14:40:33,803 epoch 1 - iter 189/275 - loss 2.64414465 - time (sec): 2.79 - samples/sec: 5533.31 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-18 14:40:34,198 epoch 1 - iter 216/275 - loss 2.44943532 - time (sec): 3.19 - samples/sec: 5508.68 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-18 14:40:34,614 epoch 1 - iter 243/275 - loss 2.27870904 - time (sec): 3.60 - samples/sec: 5535.88 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-18 14:40:35,028 epoch 1 - iter 270/275 - loss 2.12379783 - time (sec): 4.02 - samples/sec: 5575.23 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-18 14:40:35,105 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:35,105 EPOCH 1 done: loss 2.1038 - lr: 0.000049 | |
| 2023-10-18 14:40:35,352 DEV : loss 0.8510130047798157 - f1-score (micro avg) 0.0 | |
| 2023-10-18 14:40:35,356 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:35,759 epoch 2 - iter 27/275 - loss 0.92573100 - time (sec): 0.40 - samples/sec: 6255.94 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-18 14:40:36,164 epoch 2 - iter 54/275 - loss 0.84697165 - time (sec): 0.81 - samples/sec: 5885.55 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-18 14:40:36,574 epoch 2 - iter 81/275 - loss 0.83721882 - time (sec): 1.22 - samples/sec: 5775.70 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-18 14:40:36,989 epoch 2 - iter 108/275 - loss 0.80279642 - time (sec): 1.63 - samples/sec: 5758.57 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-18 14:40:37,383 epoch 2 - iter 135/275 - loss 0.78651026 - time (sec): 2.03 - samples/sec: 5696.63 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-18 14:40:37,782 epoch 2 - iter 162/275 - loss 0.78413432 - time (sec): 2.43 - samples/sec: 5639.05 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-18 14:40:38,173 epoch 2 - iter 189/275 - loss 0.78034373 - time (sec): 2.82 - samples/sec: 5591.90 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-18 14:40:38,579 epoch 2 - iter 216/275 - loss 0.76946017 - time (sec): 3.22 - samples/sec: 5532.85 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-18 14:40:38,995 epoch 2 - iter 243/275 - loss 0.74242711 - time (sec): 3.64 - samples/sec: 5517.97 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-18 14:40:39,394 epoch 2 - iter 270/275 - loss 0.73524747 - time (sec): 4.04 - samples/sec: 5576.53 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-18 14:40:39,465 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:39,466 EPOCH 2 done: loss 0.7327 - lr: 0.000045 | |
| 2023-10-18 14:40:39,841 DEV : loss 0.5134971737861633 - f1-score (micro avg) 0.2517 | |
| 2023-10-18 14:40:39,847 saving best model | |
| 2023-10-18 14:40:39,879 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:40,312 epoch 3 - iter 27/275 - loss 0.56028137 - time (sec): 0.43 - samples/sec: 4985.08 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-18 14:40:40,745 epoch 3 - iter 54/275 - loss 0.56336075 - time (sec): 0.87 - samples/sec: 5017.81 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-18 14:40:41,160 epoch 3 - iter 81/275 - loss 0.54167284 - time (sec): 1.28 - samples/sec: 5138.97 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-18 14:40:41,578 epoch 3 - iter 108/275 - loss 0.53771609 - time (sec): 1.70 - samples/sec: 5356.03 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-18 14:40:41,987 epoch 3 - iter 135/275 - loss 0.54947511 - time (sec): 2.11 - samples/sec: 5410.55 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-18 14:40:42,388 epoch 3 - iter 162/275 - loss 0.53902988 - time (sec): 2.51 - samples/sec: 5393.83 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-18 14:40:42,778 epoch 3 - iter 189/275 - loss 0.53895579 - time (sec): 2.90 - samples/sec: 5452.16 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-18 14:40:43,181 epoch 3 - iter 216/275 - loss 0.52987756 - time (sec): 3.30 - samples/sec: 5486.49 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-18 14:40:43,582 epoch 3 - iter 243/275 - loss 0.53196670 - time (sec): 3.70 - samples/sec: 5452.97 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-18 14:40:43,976 epoch 3 - iter 270/275 - loss 0.52976961 - time (sec): 4.10 - samples/sec: 5415.56 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-18 14:40:44,057 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:44,057 EPOCH 3 done: loss 0.5312 - lr: 0.000039 | |
| 2023-10-18 14:40:44,537 DEV : loss 0.38242748379707336 - f1-score (micro avg) 0.5318 | |
| 2023-10-18 14:40:44,542 saving best model | |
| 2023-10-18 14:40:44,576 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:44,975 epoch 4 - iter 27/275 - loss 0.42796901 - time (sec): 0.40 - samples/sec: 5157.42 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-18 14:40:45,374 epoch 4 - iter 54/275 - loss 0.46218929 - time (sec): 0.80 - samples/sec: 5394.04 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-18 14:40:45,780 epoch 4 - iter 81/275 - loss 0.43111010 - time (sec): 1.20 - samples/sec: 5454.93 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-18 14:40:46,188 epoch 4 - iter 108/275 - loss 0.43723644 - time (sec): 1.61 - samples/sec: 5379.05 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-18 14:40:46,592 epoch 4 - iter 135/275 - loss 0.42632659 - time (sec): 2.01 - samples/sec: 5410.49 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-18 14:40:46,994 epoch 4 - iter 162/275 - loss 0.43888143 - time (sec): 2.42 - samples/sec: 5466.57 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-18 14:40:47,397 epoch 4 - iter 189/275 - loss 0.43186817 - time (sec): 2.82 - samples/sec: 5482.05 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-18 14:40:47,808 epoch 4 - iter 216/275 - loss 0.42983087 - time (sec): 3.23 - samples/sec: 5507.02 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-18 14:40:48,225 epoch 4 - iter 243/275 - loss 0.43610680 - time (sec): 3.65 - samples/sec: 5561.41 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-18 14:40:48,592 epoch 4 - iter 270/275 - loss 0.43794982 - time (sec): 4.01 - samples/sec: 5582.64 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-18 14:40:48,659 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:48,659 EPOCH 4 done: loss 0.4353 - lr: 0.000034 | |
| 2023-10-18 14:40:49,027 DEV : loss 0.3285386562347412 - f1-score (micro avg) 0.6023 | |
| 2023-10-18 14:40:49,031 saving best model | |
| 2023-10-18 14:40:49,069 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:49,440 epoch 5 - iter 27/275 - loss 0.45552210 - time (sec): 0.37 - samples/sec: 6218.27 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-18 14:40:49,819 epoch 5 - iter 54/275 - loss 0.39006122 - time (sec): 0.75 - samples/sec: 6136.24 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-18 14:40:50,186 epoch 5 - iter 81/275 - loss 0.37283090 - time (sec): 1.12 - samples/sec: 6221.51 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-18 14:40:50,561 epoch 5 - iter 108/275 - loss 0.35060510 - time (sec): 1.49 - samples/sec: 6140.18 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-18 14:40:50,929 epoch 5 - iter 135/275 - loss 0.35877295 - time (sec): 1.86 - samples/sec: 6114.87 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-18 14:40:51,303 epoch 5 - iter 162/275 - loss 0.36969233 - time (sec): 2.23 - samples/sec: 6089.50 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-18 14:40:51,671 epoch 5 - iter 189/275 - loss 0.37310279 - time (sec): 2.60 - samples/sec: 6038.63 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-18 14:40:52,052 epoch 5 - iter 216/275 - loss 0.37827156 - time (sec): 2.98 - samples/sec: 6040.39 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 14:40:52,424 epoch 5 - iter 243/275 - loss 0.37716191 - time (sec): 3.35 - samples/sec: 6038.33 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 14:40:52,789 epoch 5 - iter 270/275 - loss 0.38319303 - time (sec): 3.72 - samples/sec: 6000.02 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 14:40:52,858 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:52,858 EPOCH 5 done: loss 0.3844 - lr: 0.000028 | |
| 2023-10-18 14:40:53,224 DEV : loss 0.3060840368270874 - f1-score (micro avg) 0.6213 | |
| 2023-10-18 14:40:53,228 saving best model | |
| 2023-10-18 14:40:53,265 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:53,629 epoch 6 - iter 27/275 - loss 0.42303658 - time (sec): 0.36 - samples/sec: 5973.69 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 14:40:53,995 epoch 6 - iter 54/275 - loss 0.40469523 - time (sec): 0.73 - samples/sec: 6025.44 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 14:40:54,381 epoch 6 - iter 81/275 - loss 0.36906352 - time (sec): 1.12 - samples/sec: 6102.76 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 14:40:54,781 epoch 6 - iter 108/275 - loss 0.36723296 - time (sec): 1.52 - samples/sec: 6108.72 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 14:40:55,193 epoch 6 - iter 135/275 - loss 0.36666139 - time (sec): 1.93 - samples/sec: 5900.86 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 14:40:55,603 epoch 6 - iter 162/275 - loss 0.36710104 - time (sec): 2.34 - samples/sec: 5883.74 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 14:40:56,016 epoch 6 - iter 189/275 - loss 0.36750250 - time (sec): 2.75 - samples/sec: 5744.53 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 14:40:56,432 epoch 6 - iter 216/275 - loss 0.35775426 - time (sec): 3.17 - samples/sec: 5804.05 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 14:40:56,837 epoch 6 - iter 243/275 - loss 0.34863409 - time (sec): 3.57 - samples/sec: 5686.11 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 14:40:57,237 epoch 6 - iter 270/275 - loss 0.35605919 - time (sec): 3.97 - samples/sec: 5645.28 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 14:40:57,311 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:57,311 EPOCH 6 done: loss 0.3549 - lr: 0.000022 | |
| 2023-10-18 14:40:57,679 DEV : loss 0.2748379111289978 - f1-score (micro avg) 0.6321 | |
| 2023-10-18 14:40:57,683 saving best model | |
| 2023-10-18 14:40:57,722 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:40:58,124 epoch 7 - iter 27/275 - loss 0.34501133 - time (sec): 0.40 - samples/sec: 5997.64 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 14:40:58,525 epoch 7 - iter 54/275 - loss 0.30859008 - time (sec): 0.80 - samples/sec: 5727.92 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 14:40:58,948 epoch 7 - iter 81/275 - loss 0.31535085 - time (sec): 1.23 - samples/sec: 5864.30 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 14:40:59,348 epoch 7 - iter 108/275 - loss 0.32198679 - time (sec): 1.63 - samples/sec: 5786.93 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 14:40:59,751 epoch 7 - iter 135/275 - loss 0.31682507 - time (sec): 2.03 - samples/sec: 5671.59 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 14:41:00,153 epoch 7 - iter 162/275 - loss 0.33269893 - time (sec): 2.43 - samples/sec: 5611.49 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 14:41:00,548 epoch 7 - iter 189/275 - loss 0.32603403 - time (sec): 2.83 - samples/sec: 5615.96 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 14:41:00,961 epoch 7 - iter 216/275 - loss 0.33183434 - time (sec): 3.24 - samples/sec: 5493.63 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 14:41:01,378 epoch 7 - iter 243/275 - loss 0.32635976 - time (sec): 3.66 - samples/sec: 5485.17 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 14:41:01,779 epoch 7 - iter 270/275 - loss 0.32835832 - time (sec): 4.06 - samples/sec: 5516.77 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 14:41:01,858 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:41:01,858 EPOCH 7 done: loss 0.3275 - lr: 0.000017 | |
| 2023-10-18 14:41:02,238 DEV : loss 0.2629452645778656 - f1-score (micro avg) 0.6406 | |
| 2023-10-18 14:41:02,242 saving best model | |
| 2023-10-18 14:41:02,276 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:41:02,706 epoch 8 - iter 27/275 - loss 0.27925383 - time (sec): 0.43 - samples/sec: 5879.06 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 14:41:03,130 epoch 8 - iter 54/275 - loss 0.29962823 - time (sec): 0.85 - samples/sec: 5691.31 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 14:41:03,545 epoch 8 - iter 81/275 - loss 0.31346068 - time (sec): 1.27 - samples/sec: 5548.11 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 14:41:03,951 epoch 8 - iter 108/275 - loss 0.29988473 - time (sec): 1.67 - samples/sec: 5527.81 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 14:41:04,346 epoch 8 - iter 135/275 - loss 0.31463498 - time (sec): 2.07 - samples/sec: 5580.77 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 14:41:04,763 epoch 8 - iter 162/275 - loss 0.31298666 - time (sec): 2.49 - samples/sec: 5479.65 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 14:41:05,173 epoch 8 - iter 189/275 - loss 0.30692524 - time (sec): 2.90 - samples/sec: 5464.55 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 14:41:05,589 epoch 8 - iter 216/275 - loss 0.30398296 - time (sec): 3.31 - samples/sec: 5448.34 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 14:41:05,984 epoch 8 - iter 243/275 - loss 0.31205537 - time (sec): 3.71 - samples/sec: 5499.57 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 14:41:06,393 epoch 8 - iter 270/275 - loss 0.31599094 - time (sec): 4.12 - samples/sec: 5453.59 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 14:41:06,469 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:41:06,469 EPOCH 8 done: loss 0.3151 - lr: 0.000011 | |
| 2023-10-18 14:41:06,836 DEV : loss 0.2551087737083435 - f1-score (micro avg) 0.6277 | |
| 2023-10-18 14:41:06,840 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:41:07,247 epoch 9 - iter 27/275 - loss 0.30845632 - time (sec): 0.41 - samples/sec: 5633.81 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 14:41:07,658 epoch 9 - iter 54/275 - loss 0.31672871 - time (sec): 0.82 - samples/sec: 5620.09 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 14:41:08,064 epoch 9 - iter 81/275 - loss 0.32192987 - time (sec): 1.22 - samples/sec: 5450.72 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 14:41:08,478 epoch 9 - iter 108/275 - loss 0.32048576 - time (sec): 1.64 - samples/sec: 5546.40 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 14:41:08,890 epoch 9 - iter 135/275 - loss 0.30584522 - time (sec): 2.05 - samples/sec: 5601.61 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 14:41:09,292 epoch 9 - iter 162/275 - loss 0.31055760 - time (sec): 2.45 - samples/sec: 5523.67 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 14:41:09,690 epoch 9 - iter 189/275 - loss 0.31006539 - time (sec): 2.85 - samples/sec: 5482.87 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 14:41:10,101 epoch 9 - iter 216/275 - loss 0.30227590 - time (sec): 3.26 - samples/sec: 5481.70 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 14:41:10,514 epoch 9 - iter 243/275 - loss 0.30384086 - time (sec): 3.67 - samples/sec: 5497.32 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 14:41:10,930 epoch 9 - iter 270/275 - loss 0.30105393 - time (sec): 4.09 - samples/sec: 5444.14 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 14:41:11,013 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:41:11,014 EPOCH 9 done: loss 0.3008 - lr: 0.000006 | |
| 2023-10-18 14:41:11,379 DEV : loss 0.25126972794532776 - f1-score (micro avg) 0.6377 | |
| 2023-10-18 14:41:11,383 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:41:11,790 epoch 10 - iter 27/275 - loss 0.30520403 - time (sec): 0.41 - samples/sec: 5564.79 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 14:41:12,198 epoch 10 - iter 54/275 - loss 0.29929756 - time (sec): 0.81 - samples/sec: 5516.05 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 14:41:12,627 epoch 10 - iter 81/275 - loss 0.29003703 - time (sec): 1.24 - samples/sec: 5457.73 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 14:41:13,038 epoch 10 - iter 108/275 - loss 0.30940382 - time (sec): 1.65 - samples/sec: 5444.76 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 14:41:13,476 epoch 10 - iter 135/275 - loss 0.29472468 - time (sec): 2.09 - samples/sec: 5410.88 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 14:41:13,894 epoch 10 - iter 162/275 - loss 0.29688473 - time (sec): 2.51 - samples/sec: 5449.63 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 14:41:14,299 epoch 10 - iter 189/275 - loss 0.30450783 - time (sec): 2.92 - samples/sec: 5393.08 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 14:41:14,711 epoch 10 - iter 216/275 - loss 0.29965923 - time (sec): 3.33 - samples/sec: 5369.94 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 14:41:15,135 epoch 10 - iter 243/275 - loss 0.29704753 - time (sec): 3.75 - samples/sec: 5317.62 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 14:41:15,542 epoch 10 - iter 270/275 - loss 0.29746489 - time (sec): 4.16 - samples/sec: 5358.94 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-18 14:41:15,619 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:41:15,619 EPOCH 10 done: loss 0.2955 - lr: 0.000000 | |
| 2023-10-18 14:41:15,989 DEV : loss 0.25100967288017273 - f1-score (micro avg) 0.636 | |
| 2023-10-18 14:41:16,025 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 14:41:16,025 Loading model from best epoch ... | |
| 2023-10-18 14:41:16,109 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 14:41:16,397 | |
| Results: | |
| - F-score (micro) 0.6564 | |
| - F-score (macro) 0.3843 | |
| - Accuracy 0.4961 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.6402 0.6875 0.6630 176 | |
| pers 0.8103 0.7344 0.7705 128 | |
| work 0.4444 0.5405 0.4878 74 | |
| object 0.0000 0.0000 0.0000 2 | |
| loc 0.0000 0.0000 0.0000 2 | |
| micro avg 0.6456 0.6675 0.6564 382 | |
| macro avg 0.3790 0.3925 0.3843 382 | |
| weighted avg 0.6526 0.6675 0.6581 382 | |
| 2023-10-18 14:41:16,397 ---------------------------------------------------------------------------------------------------- | |