| 2023-10-25 00:11:18,614 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:11:18,615 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=13, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-25 00:11:18,615 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:11:18,615 MultiCorpus: 5777 train + 722 dev + 723 test sentences | |
| - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /home/ubuntu/.flair/datasets/ner_icdar_europeana/nl | |
| 2023-10-25 00:11:18,615 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:11:18,616 Train: 5777 sentences | |
| 2023-10-25 00:11:18,616 (train_with_dev=False, train_with_test=False) | |
| 2023-10-25 00:11:18,616 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:11:18,616 Training Params: | |
| 2023-10-25 00:11:18,616 - learning_rate: "3e-05" | |
| 2023-10-25 00:11:18,616 - mini_batch_size: "4" | |
| 2023-10-25 00:11:18,616 - max_epochs: "10" | |
| 2023-10-25 00:11:18,616 - shuffle: "True" | |
| 2023-10-25 00:11:18,616 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:11:18,616 Plugins: | |
| 2023-10-25 00:11:18,616 - TensorboardLogger | |
| 2023-10-25 00:11:18,616 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-25 00:11:18,616 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:11:18,616 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-25 00:11:18,616 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-25 00:11:18,616 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:11:18,616 Computation: | |
| 2023-10-25 00:11:18,616 - compute on device: cuda:0 | |
| 2023-10-25 00:11:18,616 - embedding storage: none | |
| 2023-10-25 00:11:18,616 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:11:18,616 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-25 00:11:18,616 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:11:18,616 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:11:18,616 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-25 00:11:29,321 epoch 1 - iter 144/1445 - loss 1.38938163 - time (sec): 10.70 - samples/sec: 1720.98 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 00:11:39,360 epoch 1 - iter 288/1445 - loss 0.87654160 - time (sec): 20.74 - samples/sec: 1667.66 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 00:11:49,875 epoch 1 - iter 432/1445 - loss 0.65410083 - time (sec): 31.26 - samples/sec: 1658.76 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 00:12:00,072 epoch 1 - iter 576/1445 - loss 0.53644177 - time (sec): 41.45 - samples/sec: 1661.93 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 00:12:11,122 epoch 1 - iter 720/1445 - loss 0.45401570 - time (sec): 52.51 - samples/sec: 1670.87 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 00:12:21,401 epoch 1 - iter 864/1445 - loss 0.40781351 - time (sec): 62.78 - samples/sec: 1664.14 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 00:12:32,044 epoch 1 - iter 1008/1445 - loss 0.36577446 - time (sec): 73.43 - samples/sec: 1667.51 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 00:12:42,531 epoch 1 - iter 1152/1445 - loss 0.33817906 - time (sec): 83.91 - samples/sec: 1670.17 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 00:12:53,139 epoch 1 - iter 1296/1445 - loss 0.31541819 - time (sec): 94.52 - samples/sec: 1670.96 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 00:13:03,644 epoch 1 - iter 1440/1445 - loss 0.29840554 - time (sec): 105.03 - samples/sec: 1671.49 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 00:13:04,067 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:13:04,067 EPOCH 1 done: loss 0.2976 - lr: 0.000030 | |
| 2023-10-25 00:13:07,349 DEV : loss 0.13481558859348297 - f1-score (micro avg) 0.5007 | |
| 2023-10-25 00:13:07,360 saving best model | |
| 2023-10-25 00:13:07,833 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:13:18,284 epoch 2 - iter 144/1445 - loss 0.11213883 - time (sec): 10.45 - samples/sec: 1656.80 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 00:13:29,023 epoch 2 - iter 288/1445 - loss 0.12245620 - time (sec): 21.19 - samples/sec: 1687.57 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 00:13:39,836 epoch 2 - iter 432/1445 - loss 0.11723412 - time (sec): 32.00 - samples/sec: 1687.73 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 00:13:50,678 epoch 2 - iter 576/1445 - loss 0.11064019 - time (sec): 42.84 - samples/sec: 1685.23 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 00:14:01,208 epoch 2 - iter 720/1445 - loss 0.10928472 - time (sec): 53.37 - samples/sec: 1672.93 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 00:14:11,856 epoch 2 - iter 864/1445 - loss 0.10679391 - time (sec): 64.02 - samples/sec: 1678.60 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 00:14:22,186 epoch 2 - iter 1008/1445 - loss 0.10555065 - time (sec): 74.35 - samples/sec: 1666.89 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 00:14:32,456 epoch 2 - iter 1152/1445 - loss 0.10376908 - time (sec): 84.62 - samples/sec: 1666.77 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 00:14:42,859 epoch 2 - iter 1296/1445 - loss 0.10361640 - time (sec): 95.03 - samples/sec: 1664.12 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 00:14:53,345 epoch 2 - iter 1440/1445 - loss 0.10081503 - time (sec): 105.51 - samples/sec: 1664.11 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 00:14:53,797 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:14:53,798 EPOCH 2 done: loss 0.1006 - lr: 0.000027 | |
| 2023-10-25 00:14:57,509 DEV : loss 0.09922739118337631 - f1-score (micro avg) 0.7789 | |
| 2023-10-25 00:14:57,521 saving best model | |
| 2023-10-25 00:14:58,112 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:15:08,688 epoch 3 - iter 144/1445 - loss 0.07401386 - time (sec): 10.58 - samples/sec: 1626.38 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 00:15:19,237 epoch 3 - iter 288/1445 - loss 0.07036989 - time (sec): 21.12 - samples/sec: 1663.55 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 00:15:29,743 epoch 3 - iter 432/1445 - loss 0.07228507 - time (sec): 31.63 - samples/sec: 1660.81 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 00:15:40,193 epoch 3 - iter 576/1445 - loss 0.06975233 - time (sec): 42.08 - samples/sec: 1661.84 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 00:15:50,838 epoch 3 - iter 720/1445 - loss 0.07320523 - time (sec): 52.72 - samples/sec: 1659.56 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 00:16:01,293 epoch 3 - iter 864/1445 - loss 0.07136932 - time (sec): 63.18 - samples/sec: 1654.97 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 00:16:11,569 epoch 3 - iter 1008/1445 - loss 0.07073740 - time (sec): 73.46 - samples/sec: 1657.77 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 00:16:22,487 epoch 3 - iter 1152/1445 - loss 0.06940519 - time (sec): 84.37 - samples/sec: 1667.92 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 00:16:33,200 epoch 3 - iter 1296/1445 - loss 0.06930457 - time (sec): 95.09 - samples/sec: 1665.11 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 00:16:43,676 epoch 3 - iter 1440/1445 - loss 0.06923652 - time (sec): 105.56 - samples/sec: 1664.57 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 00:16:44,021 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:16:44,021 EPOCH 3 done: loss 0.0692 - lr: 0.000023 | |
| 2023-10-25 00:16:47,446 DEV : loss 0.13537803292274475 - f1-score (micro avg) 0.7799 | |
| 2023-10-25 00:16:47,458 saving best model | |
| 2023-10-25 00:16:48,053 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:16:58,764 epoch 4 - iter 144/1445 - loss 0.05989448 - time (sec): 10.71 - samples/sec: 1663.20 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 00:17:09,630 epoch 4 - iter 288/1445 - loss 0.05059786 - time (sec): 21.58 - samples/sec: 1620.12 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 00:17:20,376 epoch 4 - iter 432/1445 - loss 0.04777464 - time (sec): 32.32 - samples/sec: 1653.35 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 00:17:31,029 epoch 4 - iter 576/1445 - loss 0.04689286 - time (sec): 42.98 - samples/sec: 1668.10 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 00:17:41,011 epoch 4 - iter 720/1445 - loss 0.04834085 - time (sec): 52.96 - samples/sec: 1655.32 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 00:17:51,641 epoch 4 - iter 864/1445 - loss 0.04645510 - time (sec): 63.59 - samples/sec: 1654.41 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 00:18:02,147 epoch 4 - iter 1008/1445 - loss 0.04662996 - time (sec): 74.09 - samples/sec: 1654.67 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 00:18:12,811 epoch 4 - iter 1152/1445 - loss 0.04833320 - time (sec): 84.76 - samples/sec: 1657.00 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 00:18:23,313 epoch 4 - iter 1296/1445 - loss 0.04773193 - time (sec): 95.26 - samples/sec: 1661.15 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 00:18:33,848 epoch 4 - iter 1440/1445 - loss 0.04746787 - time (sec): 105.79 - samples/sec: 1661.63 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 00:18:34,192 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:18:34,192 EPOCH 4 done: loss 0.0475 - lr: 0.000020 | |
| 2023-10-25 00:18:37,622 DEV : loss 0.12032151222229004 - f1-score (micro avg) 0.8011 | |
| 2023-10-25 00:18:37,634 saving best model | |
| 2023-10-25 00:18:38,207 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:18:48,599 epoch 5 - iter 144/1445 - loss 0.02983013 - time (sec): 10.39 - samples/sec: 1631.93 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 00:18:58,968 epoch 5 - iter 288/1445 - loss 0.02899526 - time (sec): 20.76 - samples/sec: 1639.27 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 00:19:09,760 epoch 5 - iter 432/1445 - loss 0.03130541 - time (sec): 31.55 - samples/sec: 1659.53 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 00:19:20,186 epoch 5 - iter 576/1445 - loss 0.03109030 - time (sec): 41.98 - samples/sec: 1650.29 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 00:19:30,854 epoch 5 - iter 720/1445 - loss 0.03453446 - time (sec): 52.65 - samples/sec: 1651.54 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 00:19:41,861 epoch 5 - iter 864/1445 - loss 0.03446052 - time (sec): 63.65 - samples/sec: 1662.69 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 00:19:52,258 epoch 5 - iter 1008/1445 - loss 0.03609405 - time (sec): 74.05 - samples/sec: 1661.99 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 00:20:02,565 epoch 5 - iter 1152/1445 - loss 0.03627626 - time (sec): 84.36 - samples/sec: 1661.97 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 00:20:13,190 epoch 5 - iter 1296/1445 - loss 0.03556309 - time (sec): 94.98 - samples/sec: 1666.39 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 00:20:23,734 epoch 5 - iter 1440/1445 - loss 0.03679685 - time (sec): 105.53 - samples/sec: 1665.75 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 00:20:24,070 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:20:24,070 EPOCH 5 done: loss 0.0368 - lr: 0.000017 | |
| 2023-10-25 00:20:27,795 DEV : loss 0.1298297941684723 - f1-score (micro avg) 0.8238 | |
| 2023-10-25 00:20:27,807 saving best model | |
| 2023-10-25 00:20:28,405 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:20:39,126 epoch 6 - iter 144/1445 - loss 0.01601013 - time (sec): 10.72 - samples/sec: 1683.95 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 00:20:49,460 epoch 6 - iter 288/1445 - loss 0.02373592 - time (sec): 21.05 - samples/sec: 1666.69 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 00:20:59,889 epoch 6 - iter 432/1445 - loss 0.02608343 - time (sec): 31.48 - samples/sec: 1673.09 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 00:21:10,404 epoch 6 - iter 576/1445 - loss 0.02606470 - time (sec): 42.00 - samples/sec: 1670.48 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 00:21:21,085 epoch 6 - iter 720/1445 - loss 0.02539757 - time (sec): 52.68 - samples/sec: 1672.76 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 00:21:31,532 epoch 6 - iter 864/1445 - loss 0.02480823 - time (sec): 63.13 - samples/sec: 1668.80 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 00:21:41,901 epoch 6 - iter 1008/1445 - loss 0.02490080 - time (sec): 73.50 - samples/sec: 1665.35 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 00:21:52,431 epoch 6 - iter 1152/1445 - loss 0.02503213 - time (sec): 84.03 - samples/sec: 1667.30 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 00:22:03,316 epoch 6 - iter 1296/1445 - loss 0.02496600 - time (sec): 94.91 - samples/sec: 1676.20 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 00:22:13,716 epoch 6 - iter 1440/1445 - loss 0.02479026 - time (sec): 105.31 - samples/sec: 1669.96 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 00:22:14,016 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:22:14,017 EPOCH 6 done: loss 0.0249 - lr: 0.000013 | |
| 2023-10-25 00:22:17,443 DEV : loss 0.20431096851825714 - f1-score (micro avg) 0.7895 | |
| 2023-10-25 00:22:17,455 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:22:27,950 epoch 7 - iter 144/1445 - loss 0.01117684 - time (sec): 10.49 - samples/sec: 1663.75 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 00:22:38,150 epoch 7 - iter 288/1445 - loss 0.01571047 - time (sec): 20.69 - samples/sec: 1639.81 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 00:22:49,582 epoch 7 - iter 432/1445 - loss 0.01656906 - time (sec): 32.13 - samples/sec: 1676.46 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 00:23:00,018 epoch 7 - iter 576/1445 - loss 0.01503815 - time (sec): 42.56 - samples/sec: 1673.14 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 00:23:10,915 epoch 7 - iter 720/1445 - loss 0.01601736 - time (sec): 53.46 - samples/sec: 1671.50 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 00:23:21,092 epoch 7 - iter 864/1445 - loss 0.01576845 - time (sec): 63.64 - samples/sec: 1663.45 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 00:23:32,263 epoch 7 - iter 1008/1445 - loss 0.01739489 - time (sec): 74.81 - samples/sec: 1669.40 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 00:23:42,513 epoch 7 - iter 1152/1445 - loss 0.01767123 - time (sec): 85.06 - samples/sec: 1657.92 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 00:23:53,120 epoch 7 - iter 1296/1445 - loss 0.01754927 - time (sec): 95.66 - samples/sec: 1658.01 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 00:24:03,214 epoch 7 - iter 1440/1445 - loss 0.01693935 - time (sec): 105.76 - samples/sec: 1661.54 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 00:24:03,537 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:24:03,538 EPOCH 7 done: loss 0.0169 - lr: 0.000010 | |
| 2023-10-25 00:24:06,979 DEV : loss 0.18424199521541595 - f1-score (micro avg) 0.8119 | |
| 2023-10-25 00:24:06,991 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:24:17,311 epoch 8 - iter 144/1445 - loss 0.00930858 - time (sec): 10.32 - samples/sec: 1632.76 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 00:24:27,987 epoch 8 - iter 288/1445 - loss 0.01249980 - time (sec): 21.00 - samples/sec: 1632.85 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 00:24:38,238 epoch 8 - iter 432/1445 - loss 0.01219123 - time (sec): 31.25 - samples/sec: 1619.39 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 00:24:49,551 epoch 8 - iter 576/1445 - loss 0.01174793 - time (sec): 42.56 - samples/sec: 1649.32 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 00:24:59,973 epoch 8 - iter 720/1445 - loss 0.01162494 - time (sec): 52.98 - samples/sec: 1654.59 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 00:25:10,506 epoch 8 - iter 864/1445 - loss 0.01127335 - time (sec): 63.51 - samples/sec: 1656.66 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 00:25:21,054 epoch 8 - iter 1008/1445 - loss 0.01257425 - time (sec): 74.06 - samples/sec: 1661.14 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 00:25:31,601 epoch 8 - iter 1152/1445 - loss 0.01352298 - time (sec): 84.61 - samples/sec: 1660.77 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 00:25:41,995 epoch 8 - iter 1296/1445 - loss 0.01297552 - time (sec): 95.00 - samples/sec: 1660.40 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 00:25:52,563 epoch 8 - iter 1440/1445 - loss 0.01308558 - time (sec): 105.57 - samples/sec: 1664.94 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 00:25:52,893 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:25:52,894 EPOCH 8 done: loss 0.0132 - lr: 0.000007 | |
| 2023-10-25 00:25:56,623 DEV : loss 0.18342554569244385 - f1-score (micro avg) 0.8154 | |
| 2023-10-25 00:25:56,635 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:26:07,274 epoch 9 - iter 144/1445 - loss 0.00487700 - time (sec): 10.64 - samples/sec: 1686.80 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 00:26:17,719 epoch 9 - iter 288/1445 - loss 0.00618271 - time (sec): 21.08 - samples/sec: 1674.65 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 00:26:28,409 epoch 9 - iter 432/1445 - loss 0.00694467 - time (sec): 31.77 - samples/sec: 1668.72 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 00:26:39,233 epoch 9 - iter 576/1445 - loss 0.00703293 - time (sec): 42.60 - samples/sec: 1679.56 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 00:26:49,652 epoch 9 - iter 720/1445 - loss 0.00748005 - time (sec): 53.02 - samples/sec: 1667.43 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 00:27:00,096 epoch 9 - iter 864/1445 - loss 0.00812538 - time (sec): 63.46 - samples/sec: 1660.54 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 00:27:10,612 epoch 9 - iter 1008/1445 - loss 0.00850011 - time (sec): 73.98 - samples/sec: 1664.19 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 00:27:21,467 epoch 9 - iter 1152/1445 - loss 0.00876078 - time (sec): 84.83 - samples/sec: 1669.13 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 00:27:31,749 epoch 9 - iter 1296/1445 - loss 0.00983545 - time (sec): 95.11 - samples/sec: 1664.29 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 00:27:42,233 epoch 9 - iter 1440/1445 - loss 0.00953351 - time (sec): 105.60 - samples/sec: 1663.77 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 00:27:42,560 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:27:42,560 EPOCH 9 done: loss 0.0097 - lr: 0.000003 | |
| 2023-10-25 00:27:45,993 DEV : loss 0.18781644105911255 - f1-score (micro avg) 0.823 | |
| 2023-10-25 00:27:46,005 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:27:56,502 epoch 10 - iter 144/1445 - loss 0.00437476 - time (sec): 10.50 - samples/sec: 1646.85 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 00:28:07,554 epoch 10 - iter 288/1445 - loss 0.00845703 - time (sec): 21.55 - samples/sec: 1620.52 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 00:28:17,904 epoch 10 - iter 432/1445 - loss 0.00618837 - time (sec): 31.90 - samples/sec: 1633.18 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 00:28:28,473 epoch 10 - iter 576/1445 - loss 0.00597168 - time (sec): 42.47 - samples/sec: 1649.52 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 00:28:38,916 epoch 10 - iter 720/1445 - loss 0.00539134 - time (sec): 52.91 - samples/sec: 1651.52 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 00:28:50,172 epoch 10 - iter 864/1445 - loss 0.00625082 - time (sec): 64.17 - samples/sec: 1667.60 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 00:29:00,734 epoch 10 - iter 1008/1445 - loss 0.00634905 - time (sec): 74.73 - samples/sec: 1667.31 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 00:29:11,282 epoch 10 - iter 1152/1445 - loss 0.00643576 - time (sec): 85.28 - samples/sec: 1669.39 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 00:29:21,407 epoch 10 - iter 1296/1445 - loss 0.00623537 - time (sec): 95.40 - samples/sec: 1662.12 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 00:29:31,911 epoch 10 - iter 1440/1445 - loss 0.00626251 - time (sec): 105.90 - samples/sec: 1660.30 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 00:29:32,215 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:29:32,216 EPOCH 10 done: loss 0.0063 - lr: 0.000000 | |
| 2023-10-25 00:29:35,646 DEV : loss 0.19258512556552887 - f1-score (micro avg) 0.8221 | |
| 2023-10-25 00:29:36,125 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 00:29:36,126 Loading model from best epoch ... | |
| 2023-10-25 00:29:37,790 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG | |
| 2023-10-25 00:29:41,330 | |
| Results: | |
| - F-score (micro) 0.7947 | |
| - F-score (macro) 0.6981 | |
| - Accuracy 0.6764 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.7939 0.8071 0.8004 482 | |
| LOC 0.8662 0.8057 0.8348 458 | |
| ORG 0.5283 0.4058 0.4590 69 | |
| micro avg 0.8111 0.7790 0.7947 1009 | |
| macro avg 0.7295 0.6728 0.6981 1009 | |
| weighted avg 0.8085 0.7790 0.7927 1009 | |
| 2023-10-25 00:29:41,330 ---------------------------------------------------------------------------------------------------- | |