| 2023-10-24 10:48:14,850 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:48:14,851 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): 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) | |
| ) | |
| ) | |
| (1): 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) | |
| ) | |
| ) | |
| (2): 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) | |
| ) | |
| ) | |
| (3): 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) | |
| ) | |
| ) | |
| (4): 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) | |
| ) | |
| ) | |
| (5): 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) | |
| ) | |
| ) | |
| (6): 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) | |
| ) | |
| ) | |
| (7): 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) | |
| ) | |
| ) | |
| (8): 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) | |
| ) | |
| ) | |
| (9): 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) | |
| ) | |
| ) | |
| (10): 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) | |
| ) | |
| ) | |
| (11): 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=21, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-24 10:48:14,852 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:48:14,852 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences | |
| - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator | |
| 2023-10-24 10:48:14,852 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:48:14,852 Train: 5901 sentences | |
| 2023-10-24 10:48:14,852 (train_with_dev=False, train_with_test=False) | |
| 2023-10-24 10:48:14,852 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:48:14,852 Training Params: | |
| 2023-10-24 10:48:14,852 - learning_rate: "5e-05" | |
| 2023-10-24 10:48:14,852 - mini_batch_size: "4" | |
| 2023-10-24 10:48:14,852 - max_epochs: "10" | |
| 2023-10-24 10:48:14,852 - shuffle: "True" | |
| 2023-10-24 10:48:14,852 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:48:14,852 Plugins: | |
| 2023-10-24 10:48:14,852 - TensorboardLogger | |
| 2023-10-24 10:48:14,852 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-24 10:48:14,852 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:48:14,852 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-24 10:48:14,853 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-24 10:48:14,853 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:48:14,853 Computation: | |
| 2023-10-24 10:48:14,853 - compute on device: cuda:0 | |
| 2023-10-24 10:48:14,853 - embedding storage: none | |
| 2023-10-24 10:48:14,853 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:48:14,853 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-24 10:48:14,853 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:48:14,853 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:48:14,853 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-24 10:48:24,098 epoch 1 - iter 147/1476 - loss 1.65586929 - time (sec): 9.24 - samples/sec: 1730.95 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-24 10:48:33,391 epoch 1 - iter 294/1476 - loss 1.07991837 - time (sec): 18.54 - samples/sec: 1711.24 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-24 10:48:42,499 epoch 1 - iter 441/1476 - loss 0.87315512 - time (sec): 27.65 - samples/sec: 1663.26 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-24 10:48:52,399 epoch 1 - iter 588/1476 - loss 0.70884012 - time (sec): 37.55 - samples/sec: 1719.32 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-24 10:49:02,834 epoch 1 - iter 735/1476 - loss 0.59023179 - time (sec): 47.98 - samples/sec: 1759.57 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-24 10:49:12,304 epoch 1 - iter 882/1476 - loss 0.52815123 - time (sec): 57.45 - samples/sec: 1756.99 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-24 10:49:21,617 epoch 1 - iter 1029/1476 - loss 0.48116891 - time (sec): 66.76 - samples/sec: 1748.66 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-24 10:49:31,462 epoch 1 - iter 1176/1476 - loss 0.44141868 - time (sec): 76.61 - samples/sec: 1746.77 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-24 10:49:40,743 epoch 1 - iter 1323/1476 - loss 0.41530887 - time (sec): 85.89 - samples/sec: 1742.31 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-24 10:49:50,281 epoch 1 - iter 1470/1476 - loss 0.38978126 - time (sec): 95.43 - samples/sec: 1738.88 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-24 10:49:50,628 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:49:50,629 EPOCH 1 done: loss 0.3891 - lr: 0.000050 | |
| 2023-10-24 10:49:56,936 DEV : loss 0.13457921147346497 - f1-score (micro avg) 0.7234 | |
| 2023-10-24 10:49:56,958 saving best model | |
| 2023-10-24 10:49:57,516 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:50:07,080 epoch 2 - iter 147/1476 - loss 0.12059972 - time (sec): 9.56 - samples/sec: 1765.14 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-24 10:50:16,285 epoch 2 - iter 294/1476 - loss 0.13797220 - time (sec): 18.77 - samples/sec: 1717.67 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-24 10:50:25,463 epoch 2 - iter 441/1476 - loss 0.14905127 - time (sec): 27.95 - samples/sec: 1679.87 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-24 10:50:35,219 epoch 2 - iter 588/1476 - loss 0.14142829 - time (sec): 37.70 - samples/sec: 1704.17 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-24 10:50:44,511 epoch 2 - iter 735/1476 - loss 0.13962946 - time (sec): 46.99 - samples/sec: 1694.23 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-24 10:50:54,152 epoch 2 - iter 882/1476 - loss 0.13959635 - time (sec): 56.63 - samples/sec: 1704.74 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-24 10:51:03,232 epoch 2 - iter 1029/1476 - loss 0.14077252 - time (sec): 65.71 - samples/sec: 1691.49 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-24 10:51:13,264 epoch 2 - iter 1176/1476 - loss 0.13763429 - time (sec): 75.75 - samples/sec: 1725.25 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-24 10:51:23,146 epoch 2 - iter 1323/1476 - loss 0.13938057 - time (sec): 85.63 - samples/sec: 1726.60 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-24 10:51:33,145 epoch 2 - iter 1470/1476 - loss 0.13778830 - time (sec): 95.63 - samples/sec: 1735.50 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-24 10:51:33,492 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:51:33,492 EPOCH 2 done: loss 0.1379 - lr: 0.000044 | |
| 2023-10-24 10:51:42,008 DEV : loss 0.14209164679050446 - f1-score (micro avg) 0.7784 | |
| 2023-10-24 10:51:42,029 saving best model | |
| 2023-10-24 10:51:42,735 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:51:52,069 epoch 3 - iter 147/1476 - loss 0.08832162 - time (sec): 9.33 - samples/sec: 1634.07 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-24 10:52:02,054 epoch 3 - iter 294/1476 - loss 0.08724963 - time (sec): 19.32 - samples/sec: 1723.32 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-24 10:52:11,502 epoch 3 - iter 441/1476 - loss 0.08766214 - time (sec): 28.77 - samples/sec: 1709.11 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-24 10:52:21,316 epoch 3 - iter 588/1476 - loss 0.08283332 - time (sec): 38.58 - samples/sec: 1746.55 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-24 10:52:30,589 epoch 3 - iter 735/1476 - loss 0.08143414 - time (sec): 47.85 - samples/sec: 1727.76 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-24 10:52:40,282 epoch 3 - iter 882/1476 - loss 0.08342790 - time (sec): 57.55 - samples/sec: 1738.12 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-24 10:52:49,830 epoch 3 - iter 1029/1476 - loss 0.08223349 - time (sec): 67.09 - samples/sec: 1733.72 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-24 10:52:59,223 epoch 3 - iter 1176/1476 - loss 0.08468750 - time (sec): 76.49 - samples/sec: 1729.40 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-24 10:53:09,193 epoch 3 - iter 1323/1476 - loss 0.09646163 - time (sec): 86.46 - samples/sec: 1745.87 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-24 10:53:18,392 epoch 3 - iter 1470/1476 - loss 0.09593820 - time (sec): 95.66 - samples/sec: 1736.12 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-24 10:53:18,728 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:53:18,728 EPOCH 3 done: loss 0.0959 - lr: 0.000039 | |
| 2023-10-24 10:53:27,143 DEV : loss 0.2701607942581177 - f1-score (micro avg) 0.763 | |
| 2023-10-24 10:53:27,165 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:53:36,810 epoch 4 - iter 147/1476 - loss 0.12417453 - time (sec): 9.64 - samples/sec: 1745.60 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-24 10:53:46,534 epoch 4 - iter 294/1476 - loss 0.12118589 - time (sec): 19.37 - samples/sec: 1811.03 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-24 10:53:56,194 epoch 4 - iter 441/1476 - loss 0.10852964 - time (sec): 29.03 - samples/sec: 1781.74 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-24 10:54:05,524 epoch 4 - iter 588/1476 - loss 0.09519935 - time (sec): 38.36 - samples/sec: 1761.04 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-24 10:54:15,280 epoch 4 - iter 735/1476 - loss 0.09097434 - time (sec): 48.11 - samples/sec: 1766.24 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-24 10:54:24,715 epoch 4 - iter 882/1476 - loss 0.08614100 - time (sec): 57.55 - samples/sec: 1756.63 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-24 10:54:34,696 epoch 4 - iter 1029/1476 - loss 0.09487861 - time (sec): 67.53 - samples/sec: 1762.79 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-24 10:54:44,167 epoch 4 - iter 1176/1476 - loss 0.09394085 - time (sec): 77.00 - samples/sec: 1751.57 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-24 10:54:53,633 epoch 4 - iter 1323/1476 - loss 0.09504047 - time (sec): 86.47 - samples/sec: 1744.04 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-24 10:55:02,882 epoch 4 - iter 1470/1476 - loss 0.09448577 - time (sec): 95.72 - samples/sec: 1731.37 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-24 10:55:03,250 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:55:03,251 EPOCH 4 done: loss 0.0948 - lr: 0.000033 | |
| 2023-10-24 10:55:11,668 DEV : loss 0.27863532304763794 - f1-score (micro avg) 0.7293 | |
| 2023-10-24 10:55:11,689 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:55:21,448 epoch 5 - iter 147/1476 - loss 0.07291799 - time (sec): 9.76 - samples/sec: 1737.92 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-24 10:55:31,095 epoch 5 - iter 294/1476 - loss 0.11773689 - time (sec): 19.40 - samples/sec: 1770.59 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-24 10:55:40,949 epoch 5 - iter 441/1476 - loss 0.09833702 - time (sec): 29.26 - samples/sec: 1776.56 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-24 10:55:50,119 epoch 5 - iter 588/1476 - loss 0.08337112 - time (sec): 38.43 - samples/sec: 1746.88 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-24 10:56:00,122 epoch 5 - iter 735/1476 - loss 0.08978486 - time (sec): 48.43 - samples/sec: 1745.69 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-24 10:56:09,225 epoch 5 - iter 882/1476 - loss 0.08167065 - time (sec): 57.54 - samples/sec: 1723.59 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-24 10:56:18,288 epoch 5 - iter 1029/1476 - loss 0.07871689 - time (sec): 66.60 - samples/sec: 1719.04 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-24 10:56:27,625 epoch 5 - iter 1176/1476 - loss 0.07299931 - time (sec): 75.93 - samples/sec: 1704.49 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-24 10:56:37,116 epoch 5 - iter 1323/1476 - loss 0.07223057 - time (sec): 85.43 - samples/sec: 1710.28 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-24 10:56:47,474 epoch 5 - iter 1470/1476 - loss 0.07846900 - time (sec): 95.78 - samples/sec: 1733.07 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-24 10:56:47,814 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:56:47,815 EPOCH 5 done: loss 0.0784 - lr: 0.000028 | |
| 2023-10-24 10:56:56,241 DEV : loss 0.25809499621391296 - f1-score (micro avg) 0.7499 | |
| 2023-10-24 10:56:56,262 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:57:06,035 epoch 6 - iter 147/1476 - loss 0.05313087 - time (sec): 9.77 - samples/sec: 1824.29 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-24 10:57:15,603 epoch 6 - iter 294/1476 - loss 0.05439273 - time (sec): 19.34 - samples/sec: 1747.91 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-24 10:57:25,156 epoch 6 - iter 441/1476 - loss 0.04903707 - time (sec): 28.89 - samples/sec: 1733.35 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-24 10:57:34,744 epoch 6 - iter 588/1476 - loss 0.05877384 - time (sec): 38.48 - samples/sec: 1734.92 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-24 10:57:44,061 epoch 6 - iter 735/1476 - loss 0.05051822 - time (sec): 47.80 - samples/sec: 1727.89 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-24 10:57:53,790 epoch 6 - iter 882/1476 - loss 0.04679481 - time (sec): 57.53 - samples/sec: 1737.86 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-24 10:58:03,065 epoch 6 - iter 1029/1476 - loss 0.04646404 - time (sec): 66.80 - samples/sec: 1721.46 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-24 10:58:12,451 epoch 6 - iter 1176/1476 - loss 0.05002079 - time (sec): 76.19 - samples/sec: 1723.74 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-24 10:58:22,558 epoch 6 - iter 1323/1476 - loss 0.06170524 - time (sec): 86.30 - samples/sec: 1736.56 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-24 10:58:32,083 epoch 6 - iter 1470/1476 - loss 0.06160170 - time (sec): 95.82 - samples/sec: 1731.81 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-24 10:58:32,426 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:58:32,427 EPOCH 6 done: loss 0.0614 - lr: 0.000022 | |
| 2023-10-24 10:58:40,876 DEV : loss 0.2634078860282898 - f1-score (micro avg) 0.772 | |
| 2023-10-24 10:58:40,897 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 10:58:50,465 epoch 7 - iter 147/1476 - loss 0.04507495 - time (sec): 9.57 - samples/sec: 1717.08 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-24 10:58:59,978 epoch 7 - iter 294/1476 - loss 0.04197351 - time (sec): 19.08 - samples/sec: 1702.46 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-24 10:59:09,686 epoch 7 - iter 441/1476 - loss 0.06505740 - time (sec): 28.79 - samples/sec: 1729.16 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-24 10:59:18,963 epoch 7 - iter 588/1476 - loss 0.05418034 - time (sec): 38.07 - samples/sec: 1711.68 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-24 10:59:28,157 epoch 7 - iter 735/1476 - loss 0.04622712 - time (sec): 47.26 - samples/sec: 1700.72 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-24 10:59:38,265 epoch 7 - iter 882/1476 - loss 0.05893413 - time (sec): 57.37 - samples/sec: 1727.44 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-24 10:59:47,775 epoch 7 - iter 1029/1476 - loss 0.05878999 - time (sec): 66.88 - samples/sec: 1727.73 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-24 10:59:57,450 epoch 7 - iter 1176/1476 - loss 0.05964465 - time (sec): 76.55 - samples/sec: 1727.83 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-24 11:00:07,100 epoch 7 - iter 1323/1476 - loss 0.05826532 - time (sec): 86.20 - samples/sec: 1732.09 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-24 11:00:16,614 epoch 7 - iter 1470/1476 - loss 0.06281126 - time (sec): 95.72 - samples/sec: 1732.15 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-24 11:00:16,990 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 11:00:16,990 EPOCH 7 done: loss 0.0626 - lr: 0.000017 | |
| 2023-10-24 11:00:25,435 DEV : loss 0.27169960737228394 - f1-score (micro avg) 0.7652 | |
| 2023-10-24 11:00:25,457 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 11:00:34,865 epoch 8 - iter 147/1476 - loss 0.04542037 - time (sec): 9.41 - samples/sec: 1696.00 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-24 11:00:44,003 epoch 8 - iter 294/1476 - loss 0.02861702 - time (sec): 18.55 - samples/sec: 1657.60 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-24 11:00:54,239 epoch 8 - iter 441/1476 - loss 0.06281701 - time (sec): 28.78 - samples/sec: 1758.67 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-24 11:01:03,793 epoch 8 - iter 588/1476 - loss 0.05883833 - time (sec): 38.34 - samples/sec: 1759.21 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-24 11:01:13,566 epoch 8 - iter 735/1476 - loss 0.05103042 - time (sec): 48.11 - samples/sec: 1753.77 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-24 11:01:23,641 epoch 8 - iter 882/1476 - loss 0.05585751 - time (sec): 58.18 - samples/sec: 1761.22 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-24 11:01:32,886 epoch 8 - iter 1029/1476 - loss 0.05420164 - time (sec): 67.43 - samples/sec: 1741.28 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-24 11:01:42,145 epoch 8 - iter 1176/1476 - loss 0.05014942 - time (sec): 76.69 - samples/sec: 1733.69 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-24 11:01:51,484 epoch 8 - iter 1323/1476 - loss 0.04821620 - time (sec): 86.03 - samples/sec: 1730.02 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-24 11:02:01,128 epoch 8 - iter 1470/1476 - loss 0.04480348 - time (sec): 95.67 - samples/sec: 1732.32 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-24 11:02:01,495 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 11:02:01,495 EPOCH 8 done: loss 0.0447 - lr: 0.000011 | |
| 2023-10-24 11:02:09,941 DEV : loss 0.30274227261543274 - f1-score (micro avg) 0.7626 | |
| 2023-10-24 11:02:09,962 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 11:02:19,368 epoch 9 - iter 147/1476 - loss 0.02455183 - time (sec): 9.40 - samples/sec: 1690.22 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-24 11:02:29,184 epoch 9 - iter 294/1476 - loss 0.02908119 - time (sec): 19.22 - samples/sec: 1766.79 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-24 11:02:38,447 epoch 9 - iter 441/1476 - loss 0.03060954 - time (sec): 28.48 - samples/sec: 1720.29 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-24 11:02:47,999 epoch 9 - iter 588/1476 - loss 0.02637177 - time (sec): 38.04 - samples/sec: 1682.20 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-24 11:02:57,224 epoch 9 - iter 735/1476 - loss 0.02532292 - time (sec): 47.26 - samples/sec: 1686.95 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-24 11:03:06,638 epoch 9 - iter 882/1476 - loss 0.02620936 - time (sec): 56.67 - samples/sec: 1688.27 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-24 11:03:16,146 epoch 9 - iter 1029/1476 - loss 0.02456485 - time (sec): 66.18 - samples/sec: 1700.19 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-24 11:03:26,166 epoch 9 - iter 1176/1476 - loss 0.03675836 - time (sec): 76.20 - samples/sec: 1722.03 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-24 11:03:36,323 epoch 9 - iter 1323/1476 - loss 0.04061899 - time (sec): 86.36 - samples/sec: 1730.99 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-24 11:03:45,828 epoch 9 - iter 1470/1476 - loss 0.04002423 - time (sec): 95.86 - samples/sec: 1731.00 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-24 11:03:46,171 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 11:03:46,171 EPOCH 9 done: loss 0.0399 - lr: 0.000006 | |
| 2023-10-24 11:03:54,596 DEV : loss 0.2963683307170868 - f1-score (micro avg) 0.7703 | |
| 2023-10-24 11:03:54,618 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 11:04:04,051 epoch 10 - iter 147/1476 - loss 0.02704804 - time (sec): 9.43 - samples/sec: 1717.54 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-24 11:04:13,428 epoch 10 - iter 294/1476 - loss 0.02279645 - time (sec): 18.81 - samples/sec: 1701.66 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-24 11:04:23,321 epoch 10 - iter 441/1476 - loss 0.02018937 - time (sec): 28.70 - samples/sec: 1740.66 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-24 11:04:33,017 epoch 10 - iter 588/1476 - loss 0.02530081 - time (sec): 38.40 - samples/sec: 1760.38 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-24 11:04:43,267 epoch 10 - iter 735/1476 - loss 0.04049497 - time (sec): 48.65 - samples/sec: 1775.63 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-24 11:04:52,714 epoch 10 - iter 882/1476 - loss 0.04282402 - time (sec): 58.10 - samples/sec: 1761.20 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-24 11:05:02,523 epoch 10 - iter 1029/1476 - loss 0.04621028 - time (sec): 67.90 - samples/sec: 1756.59 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-24 11:05:11,678 epoch 10 - iter 1176/1476 - loss 0.04170952 - time (sec): 77.06 - samples/sec: 1742.51 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-24 11:05:20,869 epoch 10 - iter 1323/1476 - loss 0.03916033 - time (sec): 86.25 - samples/sec: 1733.25 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-24 11:05:30,215 epoch 10 - iter 1470/1476 - loss 0.03566834 - time (sec): 95.60 - samples/sec: 1735.21 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-24 11:05:30,559 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 11:05:30,559 EPOCH 10 done: loss 0.0356 - lr: 0.000000 | |
| 2023-10-24 11:05:39,016 DEV : loss 0.30029311776161194 - f1-score (micro avg) 0.7695 | |
| 2023-10-24 11:05:39,590 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 11:05:39,590 Loading model from best epoch ... | |
| 2023-10-24 11:05:41,453 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod | |
| 2023-10-24 11:05:47,732 | |
| Results: | |
| - F-score (micro) 0.7379 | |
| - F-score (macro) 0.6047 | |
| - Accuracy 0.6102 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8307 0.8520 0.8412 858 | |
| pers 0.6764 0.6927 0.6845 537 | |
| org 0.4410 0.5379 0.4846 132 | |
| time 0.5147 0.6481 0.5738 54 | |
| prod 0.6667 0.3279 0.4396 61 | |
| micro avg 0.7276 0.7485 0.7379 1642 | |
| macro avg 0.6259 0.6117 0.6047 1642 | |
| weighted avg 0.7324 0.7485 0.7376 1642 | |
| 2023-10-24 11:05:47,732 ---------------------------------------------------------------------------------------------------- | |