|
2023-10-25 00:29:57,767 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:29:57,768 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 00:29:57,768 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:29:57,768 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 00:29:57,768 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:29:57,768 Train: 5777 sentences |
|
2023-10-25 00:29:57,768 (train_with_dev=False, train_with_test=False) |
|
2023-10-25 00:29:57,768 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:29:57,768 Training Params: |
|
2023-10-25 00:29:57,768 - learning_rate: "5e-05" |
|
2023-10-25 00:29:57,768 - mini_batch_size: "4" |
|
2023-10-25 00:29:57,768 - max_epochs: "10" |
|
2023-10-25 00:29:57,768 - shuffle: "True" |
|
2023-10-25 00:29:57,768 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:29:57,768 Plugins: |
|
2023-10-25 00:29:57,768 - TensorboardLogger |
|
2023-10-25 00:29:57,768 - LinearScheduler | warmup_fraction: '0.1' |
|
2023-10-25 00:29:57,768 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:29:57,768 Final evaluation on model from best epoch (best-model.pt) |
|
2023-10-25 00:29:57,769 - metric: "('micro avg', 'f1-score')" |
|
2023-10-25 00:29:57,769 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:29:57,769 Computation: |
|
2023-10-25 00:29:57,769 - compute on device: cuda:0 |
|
2023-10-25 00:29:57,769 - embedding storage: none |
|
2023-10-25 00:29:57,769 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:29:57,769 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" |
|
2023-10-25 00:29:57,769 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:29:57,769 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:29:57,769 Logging anything other than scalars to TensorBoard is currently not supported. |
|
2023-10-25 00:30:08,483 epoch 1 - iter 144/1445 - loss 1.13091869 - time (sec): 10.71 - samples/sec: 1719.44 - lr: 0.000005 - momentum: 0.000000 |
|
2023-10-25 00:30:18,522 epoch 1 - iter 288/1445 - loss 0.72717807 - time (sec): 20.75 - samples/sec: 1666.89 - lr: 0.000010 - momentum: 0.000000 |
|
2023-10-25 00:30:29,027 epoch 1 - iter 432/1445 - loss 0.54910845 - time (sec): 31.26 - samples/sec: 1658.78 - lr: 0.000015 - momentum: 0.000000 |
|
2023-10-25 00:30:39,228 epoch 1 - iter 576/1445 - loss 0.45352713 - time (sec): 41.46 - samples/sec: 1661.76 - lr: 0.000020 - momentum: 0.000000 |
|
2023-10-25 00:30:50,269 epoch 1 - iter 720/1445 - loss 0.38715891 - time (sec): 52.50 - samples/sec: 1671.06 - lr: 0.000025 - momentum: 0.000000 |
|
2023-10-25 00:31:00,544 epoch 1 - iter 864/1445 - loss 0.35135159 - time (sec): 62.77 - samples/sec: 1664.41 - lr: 0.000030 - momentum: 0.000000 |
|
2023-10-25 00:31:11,168 epoch 1 - iter 1008/1445 - loss 0.31692907 - time (sec): 73.40 - samples/sec: 1668.17 - lr: 0.000035 - momentum: 0.000000 |
|
2023-10-25 00:31:21,635 epoch 1 - iter 1152/1445 - loss 0.29432473 - time (sec): 83.87 - samples/sec: 1671.13 - lr: 0.000040 - momentum: 0.000000 |
|
2023-10-25 00:31:32,225 epoch 1 - iter 1296/1445 - loss 0.27636030 - time (sec): 94.46 - samples/sec: 1672.14 - lr: 0.000045 - momentum: 0.000000 |
|
2023-10-25 00:31:42,720 epoch 1 - iter 1440/1445 - loss 0.26352308 - time (sec): 104.95 - samples/sec: 1672.70 - lr: 0.000050 - momentum: 0.000000 |
|
2023-10-25 00:31:43,146 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:31:43,146 EPOCH 1 done: loss 0.2629 - lr: 0.000050 |
|
2023-10-25 00:31:46,441 DEV : loss 0.13238754868507385 - f1-score (micro avg) 0.5901 |
|
2023-10-25 00:31:46,453 saving best model |
|
2023-10-25 00:31:46,923 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:31:57,360 epoch 2 - iter 144/1445 - loss 0.12906717 - time (sec): 10.44 - samples/sec: 1658.88 - lr: 0.000049 - momentum: 0.000000 |
|
2023-10-25 00:32:08,086 epoch 2 - iter 288/1445 - loss 0.14175462 - time (sec): 21.16 - samples/sec: 1689.68 - lr: 0.000049 - momentum: 0.000000 |
|
2023-10-25 00:32:18,875 epoch 2 - iter 432/1445 - loss 0.13484474 - time (sec): 31.95 - samples/sec: 1690.38 - lr: 0.000048 - momentum: 0.000000 |
|
2023-10-25 00:32:29,699 epoch 2 - iter 576/1445 - loss 0.13523074 - time (sec): 42.78 - samples/sec: 1687.93 - lr: 0.000048 - momentum: 0.000000 |
|
2023-10-25 00:32:40,217 epoch 2 - iter 720/1445 - loss 0.13579670 - time (sec): 53.29 - samples/sec: 1675.45 - lr: 0.000047 - momentum: 0.000000 |
|
2023-10-25 00:32:50,849 epoch 2 - iter 864/1445 - loss 0.12989016 - time (sec): 63.93 - samples/sec: 1681.13 - lr: 0.000047 - momentum: 0.000000 |
|
2023-10-25 00:33:01,166 epoch 2 - iter 1008/1445 - loss 0.12722975 - time (sec): 74.24 - samples/sec: 1669.36 - lr: 0.000046 - momentum: 0.000000 |
|
2023-10-25 00:33:11,424 epoch 2 - iter 1152/1445 - loss 0.12445561 - time (sec): 84.50 - samples/sec: 1669.17 - lr: 0.000046 - momentum: 0.000000 |
|
2023-10-25 00:33:21,822 epoch 2 - iter 1296/1445 - loss 0.12416360 - time (sec): 94.90 - samples/sec: 1666.34 - lr: 0.000045 - momentum: 0.000000 |
|
2023-10-25 00:33:32,265 epoch 2 - iter 1440/1445 - loss 0.12060820 - time (sec): 105.34 - samples/sec: 1666.79 - lr: 0.000044 - momentum: 0.000000 |
|
2023-10-25 00:33:32,719 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:33:32,720 EPOCH 2 done: loss 0.1204 - lr: 0.000044 |
|
2023-10-25 00:33:36,444 DEV : loss 0.1637599915266037 - f1-score (micro avg) 0.6825 |
|
2023-10-25 00:33:36,455 saving best model |
|
2023-10-25 00:33:37,058 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:33:47,599 epoch 3 - iter 144/1445 - loss 0.09252725 - time (sec): 10.54 - samples/sec: 1631.77 - lr: 0.000044 - momentum: 0.000000 |
|
2023-10-25 00:33:58,124 epoch 3 - iter 288/1445 - loss 0.08159190 - time (sec): 21.06 - samples/sec: 1668.26 - lr: 0.000043 - momentum: 0.000000 |
|
2023-10-25 00:34:08,594 epoch 3 - iter 432/1445 - loss 0.09199990 - time (sec): 31.53 - samples/sec: 1665.85 - lr: 0.000043 - momentum: 0.000000 |
|
2023-10-25 00:34:19,013 epoch 3 - iter 576/1445 - loss 0.09014343 - time (sec): 41.95 - samples/sec: 1666.84 - lr: 0.000042 - momentum: 0.000000 |
|
2023-10-25 00:34:29,607 epoch 3 - iter 720/1445 - loss 0.09202289 - time (sec): 52.55 - samples/sec: 1665.15 - lr: 0.000042 - momentum: 0.000000 |
|
2023-10-25 00:34:40,027 epoch 3 - iter 864/1445 - loss 0.09036717 - time (sec): 62.97 - samples/sec: 1660.55 - lr: 0.000041 - momentum: 0.000000 |
|
2023-10-25 00:34:50,290 epoch 3 - iter 1008/1445 - loss 0.08832233 - time (sec): 73.23 - samples/sec: 1662.88 - lr: 0.000041 - momentum: 0.000000 |
|
2023-10-25 00:35:01,191 epoch 3 - iter 1152/1445 - loss 0.08608658 - time (sec): 84.13 - samples/sec: 1672.73 - lr: 0.000040 - momentum: 0.000000 |
|
2023-10-25 00:35:11,880 epoch 3 - iter 1296/1445 - loss 0.08602045 - time (sec): 94.82 - samples/sec: 1669.79 - lr: 0.000039 - momentum: 0.000000 |
|
2023-10-25 00:35:22,330 epoch 3 - iter 1440/1445 - loss 0.08535530 - time (sec): 105.27 - samples/sec: 1669.20 - lr: 0.000039 - momentum: 0.000000 |
|
2023-10-25 00:35:22,675 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:35:22,675 EPOCH 3 done: loss 0.0853 - lr: 0.000039 |
|
2023-10-25 00:35:26,095 DEV : loss 0.1368260681629181 - f1-score (micro avg) 0.7569 |
|
2023-10-25 00:35:26,107 saving best model |
|
2023-10-25 00:35:26,700 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:35:37,399 epoch 4 - iter 144/1445 - loss 0.08517308 - time (sec): 10.70 - samples/sec: 1665.20 - lr: 0.000038 - momentum: 0.000000 |
|
2023-10-25 00:35:48,228 epoch 4 - iter 288/1445 - loss 0.07160188 - time (sec): 21.53 - samples/sec: 1623.93 - lr: 0.000038 - momentum: 0.000000 |
|
2023-10-25 00:35:58,950 epoch 4 - iter 432/1445 - loss 0.06482124 - time (sec): 32.25 - samples/sec: 1657.16 - lr: 0.000037 - momentum: 0.000000 |
|
2023-10-25 00:36:09,580 epoch 4 - iter 576/1445 - loss 0.06463501 - time (sec): 42.88 - samples/sec: 1671.84 - lr: 0.000037 - momentum: 0.000000 |
|
2023-10-25 00:36:19,554 epoch 4 - iter 720/1445 - loss 0.06508227 - time (sec): 52.85 - samples/sec: 1658.63 - lr: 0.000036 - momentum: 0.000000 |
|
2023-10-25 00:36:30,170 epoch 4 - iter 864/1445 - loss 0.06327221 - time (sec): 63.47 - samples/sec: 1657.51 - lr: 0.000036 - momentum: 0.000000 |
|
2023-10-25 00:36:40,675 epoch 4 - iter 1008/1445 - loss 0.06131219 - time (sec): 73.97 - samples/sec: 1657.34 - lr: 0.000035 - momentum: 0.000000 |
|
2023-10-25 00:36:51,338 epoch 4 - iter 1152/1445 - loss 0.06139464 - time (sec): 84.64 - samples/sec: 1659.37 - lr: 0.000034 - momentum: 0.000000 |
|
2023-10-25 00:37:01,830 epoch 4 - iter 1296/1445 - loss 0.06039656 - time (sec): 95.13 - samples/sec: 1663.43 - lr: 0.000034 - momentum: 0.000000 |
|
2023-10-25 00:37:12,353 epoch 4 - iter 1440/1445 - loss 0.06062947 - time (sec): 105.65 - samples/sec: 1663.86 - lr: 0.000033 - momentum: 0.000000 |
|
2023-10-25 00:37:12,695 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:37:12,695 EPOCH 4 done: loss 0.0607 - lr: 0.000033 |
|
2023-10-25 00:37:16,133 DEV : loss 0.1350499838590622 - f1-score (micro avg) 0.7793 |
|
2023-10-25 00:37:16,144 saving best model |
|
2023-10-25 00:37:16,730 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:37:27,107 epoch 5 - iter 144/1445 - loss 0.03770201 - time (sec): 10.38 - samples/sec: 1634.19 - lr: 0.000033 - momentum: 0.000000 |
|
2023-10-25 00:37:37,462 epoch 5 - iter 288/1445 - loss 0.04227467 - time (sec): 20.73 - samples/sec: 1641.50 - lr: 0.000032 - momentum: 0.000000 |
|
2023-10-25 00:37:48,263 epoch 5 - iter 432/1445 - loss 0.04356669 - time (sec): 31.53 - samples/sec: 1660.55 - lr: 0.000032 - momentum: 0.000000 |
|
2023-10-25 00:37:58,664 epoch 5 - iter 576/1445 - loss 0.04538220 - time (sec): 41.93 - samples/sec: 1652.07 - lr: 0.000031 - momentum: 0.000000 |
|
2023-10-25 00:38:09,318 epoch 5 - iter 720/1445 - loss 0.04687059 - time (sec): 52.59 - samples/sec: 1653.41 - lr: 0.000031 - momentum: 0.000000 |
|
2023-10-25 00:38:20,315 epoch 5 - iter 864/1445 - loss 0.04652460 - time (sec): 63.58 - samples/sec: 1664.50 - lr: 0.000030 - momentum: 0.000000 |
|
2023-10-25 00:38:30,690 epoch 5 - iter 1008/1445 - loss 0.04827220 - time (sec): 73.96 - samples/sec: 1664.02 - lr: 0.000029 - momentum: 0.000000 |
|
2023-10-25 00:38:40,992 epoch 5 - iter 1152/1445 - loss 0.04889898 - time (sec): 84.26 - samples/sec: 1663.85 - lr: 0.000029 - momentum: 0.000000 |
|
2023-10-25 00:38:51,608 epoch 5 - iter 1296/1445 - loss 0.04736250 - time (sec): 94.88 - samples/sec: 1668.24 - lr: 0.000028 - momentum: 0.000000 |
|
2023-10-25 00:39:02,140 epoch 5 - iter 1440/1445 - loss 0.04811777 - time (sec): 105.41 - samples/sec: 1667.61 - lr: 0.000028 - momentum: 0.000000 |
|
2023-10-25 00:39:02,475 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:39:02,475 EPOCH 5 done: loss 0.0481 - lr: 0.000028 |
|
2023-10-25 00:39:06,189 DEV : loss 0.13506022095680237 - f1-score (micro avg) 0.7887 |
|
2023-10-25 00:39:06,201 saving best model |
|
2023-10-25 00:39:06,787 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:39:17,489 epoch 6 - iter 144/1445 - loss 0.03429093 - time (sec): 10.70 - samples/sec: 1687.02 - lr: 0.000027 - momentum: 0.000000 |
|
2023-10-25 00:39:27,824 epoch 6 - iter 288/1445 - loss 0.03652817 - time (sec): 21.04 - samples/sec: 1668.17 - lr: 0.000027 - momentum: 0.000000 |
|
2023-10-25 00:39:38,257 epoch 6 - iter 432/1445 - loss 0.03570699 - time (sec): 31.47 - samples/sec: 1673.84 - lr: 0.000026 - momentum: 0.000000 |
|
2023-10-25 00:39:48,773 epoch 6 - iter 576/1445 - loss 0.03442253 - time (sec): 41.98 - samples/sec: 1671.05 - lr: 0.000026 - momentum: 0.000000 |
|
2023-10-25 00:39:59,454 epoch 6 - iter 720/1445 - loss 0.03455656 - time (sec): 52.67 - samples/sec: 1673.20 - lr: 0.000025 - momentum: 0.000000 |
|
2023-10-25 00:40:09,905 epoch 6 - iter 864/1445 - loss 0.03359336 - time (sec): 63.12 - samples/sec: 1669.08 - lr: 0.000024 - momentum: 0.000000 |
|
2023-10-25 00:40:20,292 epoch 6 - iter 1008/1445 - loss 0.03330739 - time (sec): 73.50 - samples/sec: 1665.16 - lr: 0.000024 - momentum: 0.000000 |
|
2023-10-25 00:40:30,836 epoch 6 - iter 1152/1445 - loss 0.03333880 - time (sec): 84.05 - samples/sec: 1666.86 - lr: 0.000023 - momentum: 0.000000 |
|
2023-10-25 00:40:41,721 epoch 6 - iter 1296/1445 - loss 0.03257001 - time (sec): 94.93 - samples/sec: 1675.79 - lr: 0.000023 - momentum: 0.000000 |
|
2023-10-25 00:40:52,117 epoch 6 - iter 1440/1445 - loss 0.03449800 - time (sec): 105.33 - samples/sec: 1669.68 - lr: 0.000022 - momentum: 0.000000 |
|
2023-10-25 00:40:52,417 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:40:52,417 EPOCH 6 done: loss 0.0349 - lr: 0.000022 |
|
2023-10-25 00:40:55,844 DEV : loss 0.17813748121261597 - f1-score (micro avg) 0.8122 |
|
2023-10-25 00:40:55,856 saving best model |
|
2023-10-25 00:40:56,427 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:41:07,205 epoch 7 - iter 144/1445 - loss 0.02288004 - time (sec): 10.78 - samples/sec: 1620.04 - lr: 0.000022 - momentum: 0.000000 |
|
2023-10-25 00:41:17,397 epoch 7 - iter 288/1445 - loss 0.02402014 - time (sec): 20.97 - samples/sec: 1618.32 - lr: 0.000021 - momentum: 0.000000 |
|
2023-10-25 00:41:28,527 epoch 7 - iter 432/1445 - loss 0.02416563 - time (sec): 32.10 - samples/sec: 1677.87 - lr: 0.000021 - momentum: 0.000000 |
|
2023-10-25 00:41:38,953 epoch 7 - iter 576/1445 - loss 0.02788157 - time (sec): 42.53 - samples/sec: 1674.58 - lr: 0.000020 - momentum: 0.000000 |
|
2023-10-25 00:41:49,841 epoch 7 - iter 720/1445 - loss 0.02776146 - time (sec): 53.41 - samples/sec: 1672.98 - lr: 0.000019 - momentum: 0.000000 |
|
2023-10-25 00:42:00,020 epoch 7 - iter 864/1445 - loss 0.02734694 - time (sec): 63.59 - samples/sec: 1664.61 - lr: 0.000019 - momentum: 0.000000 |
|
2023-10-25 00:42:11,191 epoch 7 - iter 1008/1445 - loss 0.02724829 - time (sec): 74.76 - samples/sec: 1670.39 - lr: 0.000018 - momentum: 0.000000 |
|
2023-10-25 00:42:21,437 epoch 7 - iter 1152/1445 - loss 0.02691804 - time (sec): 85.01 - samples/sec: 1658.85 - lr: 0.000018 - momentum: 0.000000 |
|
2023-10-25 00:42:32,045 epoch 7 - iter 1296/1445 - loss 0.02686164 - time (sec): 95.62 - samples/sec: 1658.82 - lr: 0.000017 - momentum: 0.000000 |
|
2023-10-25 00:42:42,131 epoch 7 - iter 1440/1445 - loss 0.02571918 - time (sec): 105.70 - samples/sec: 1662.41 - lr: 0.000017 - momentum: 0.000000 |
|
2023-10-25 00:42:42,453 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:42:42,453 EPOCH 7 done: loss 0.0257 - lr: 0.000017 |
|
2023-10-25 00:42:45,898 DEV : loss 0.20423908531665802 - f1-score (micro avg) 0.7991 |
|
2023-10-25 00:42:45,910 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:42:56,220 epoch 8 - iter 144/1445 - loss 0.01419746 - time (sec): 10.31 - samples/sec: 1634.27 - lr: 0.000016 - momentum: 0.000000 |
|
2023-10-25 00:43:06,898 epoch 8 - iter 288/1445 - loss 0.01872915 - time (sec): 20.99 - samples/sec: 1633.41 - lr: 0.000016 - momentum: 0.000000 |
|
2023-10-25 00:43:17,153 epoch 8 - iter 432/1445 - loss 0.01882768 - time (sec): 31.24 - samples/sec: 1619.53 - lr: 0.000015 - momentum: 0.000000 |
|
2023-10-25 00:43:28,475 epoch 8 - iter 576/1445 - loss 0.01715183 - time (sec): 42.56 - samples/sec: 1649.09 - lr: 0.000014 - momentum: 0.000000 |
|
2023-10-25 00:43:38,899 epoch 8 - iter 720/1445 - loss 0.01605795 - time (sec): 52.99 - samples/sec: 1654.35 - lr: 0.000014 - momentum: 0.000000 |
|
2023-10-25 00:43:49,434 epoch 8 - iter 864/1445 - loss 0.01572662 - time (sec): 63.52 - samples/sec: 1656.43 - lr: 0.000013 - momentum: 0.000000 |
|
2023-10-25 00:43:59,983 epoch 8 - iter 1008/1445 - loss 0.01541509 - time (sec): 74.07 - samples/sec: 1660.92 - lr: 0.000013 - momentum: 0.000000 |
|
2023-10-25 00:44:10,528 epoch 8 - iter 1152/1445 - loss 0.01658134 - time (sec): 84.62 - samples/sec: 1660.61 - lr: 0.000012 - momentum: 0.000000 |
|
2023-10-25 00:44:20,923 epoch 8 - iter 1296/1445 - loss 0.01652177 - time (sec): 95.01 - samples/sec: 1660.23 - lr: 0.000012 - momentum: 0.000000 |
|
2023-10-25 00:44:31,493 epoch 8 - iter 1440/1445 - loss 0.01699937 - time (sec): 105.58 - samples/sec: 1664.77 - lr: 0.000011 - momentum: 0.000000 |
|
2023-10-25 00:44:31,823 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:44:31,823 EPOCH 8 done: loss 0.0171 - lr: 0.000011 |
|
2023-10-25 00:44:35,557 DEV : loss 0.1795710176229477 - f1-score (micro avg) 0.8066 |
|
2023-10-25 00:44:35,568 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:44:46,211 epoch 9 - iter 144/1445 - loss 0.00815765 - time (sec): 10.64 - samples/sec: 1686.24 - lr: 0.000011 - momentum: 0.000000 |
|
2023-10-25 00:44:56,650 epoch 9 - iter 288/1445 - loss 0.01010417 - time (sec): 21.08 - samples/sec: 1674.85 - lr: 0.000010 - momentum: 0.000000 |
|
2023-10-25 00:45:07,355 epoch 9 - iter 432/1445 - loss 0.00976722 - time (sec): 31.79 - samples/sec: 1668.08 - lr: 0.000009 - momentum: 0.000000 |
|
2023-10-25 00:45:18,162 epoch 9 - iter 576/1445 - loss 0.00952883 - time (sec): 42.59 - samples/sec: 1679.74 - lr: 0.000009 - momentum: 0.000000 |
|
2023-10-25 00:45:28,578 epoch 9 - iter 720/1445 - loss 0.01073242 - time (sec): 53.01 - samples/sec: 1667.70 - lr: 0.000008 - momentum: 0.000000 |
|
2023-10-25 00:45:39,020 epoch 9 - iter 864/1445 - loss 0.01041652 - time (sec): 63.45 - samples/sec: 1660.78 - lr: 0.000008 - momentum: 0.000000 |
|
2023-10-25 00:45:49,541 epoch 9 - iter 1008/1445 - loss 0.01035641 - time (sec): 73.97 - samples/sec: 1664.31 - lr: 0.000007 - momentum: 0.000000 |
|
2023-10-25 00:46:00,398 epoch 9 - iter 1152/1445 - loss 0.01101056 - time (sec): 84.83 - samples/sec: 1669.19 - lr: 0.000007 - momentum: 0.000000 |
|
2023-10-25 00:46:10,698 epoch 9 - iter 1296/1445 - loss 0.01189976 - time (sec): 95.13 - samples/sec: 1664.03 - lr: 0.000006 - momentum: 0.000000 |
|
2023-10-25 00:46:21,185 epoch 9 - iter 1440/1445 - loss 0.01169615 - time (sec): 105.62 - samples/sec: 1663.47 - lr: 0.000006 - momentum: 0.000000 |
|
2023-10-25 00:46:21,512 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:46:21,512 EPOCH 9 done: loss 0.0118 - lr: 0.000006 |
|
2023-10-25 00:46:24,954 DEV : loss 0.19641432166099548 - f1-score (micro avg) 0.8118 |
|
2023-10-25 00:46:24,966 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:46:35,460 epoch 10 - iter 144/1445 - loss 0.00338488 - time (sec): 10.49 - samples/sec: 1647.23 - lr: 0.000005 - momentum: 0.000000 |
|
2023-10-25 00:46:46,223 epoch 10 - iter 288/1445 - loss 0.00548054 - time (sec): 21.26 - samples/sec: 1642.79 - lr: 0.000004 - momentum: 0.000000 |
|
2023-10-25 00:46:56,875 epoch 10 - iter 432/1445 - loss 0.00608528 - time (sec): 31.91 - samples/sec: 1632.64 - lr: 0.000004 - momentum: 0.000000 |
|
2023-10-25 00:47:07,440 epoch 10 - iter 576/1445 - loss 0.00590010 - time (sec): 42.47 - samples/sec: 1649.27 - lr: 0.000003 - momentum: 0.000000 |
|
2023-10-25 00:47:17,886 epoch 10 - iter 720/1445 - loss 0.00593391 - time (sec): 52.92 - samples/sec: 1651.24 - lr: 0.000003 - momentum: 0.000000 |
|
2023-10-25 00:47:29,138 epoch 10 - iter 864/1445 - loss 0.00753050 - time (sec): 64.17 - samples/sec: 1667.46 - lr: 0.000002 - momentum: 0.000000 |
|
2023-10-25 00:47:39,700 epoch 10 - iter 1008/1445 - loss 0.00729756 - time (sec): 74.73 - samples/sec: 1667.19 - lr: 0.000002 - momentum: 0.000000 |
|
2023-10-25 00:47:50,246 epoch 10 - iter 1152/1445 - loss 0.00723039 - time (sec): 85.28 - samples/sec: 1669.34 - lr: 0.000001 - momentum: 0.000000 |
|
2023-10-25 00:48:00,375 epoch 10 - iter 1296/1445 - loss 0.00720144 - time (sec): 95.41 - samples/sec: 1661.98 - lr: 0.000001 - momentum: 0.000000 |
|
2023-10-25 00:48:10,884 epoch 10 - iter 1440/1445 - loss 0.00722585 - time (sec): 105.92 - samples/sec: 1660.10 - lr: 0.000000 - momentum: 0.000000 |
|
2023-10-25 00:48:11,189 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:48:11,189 EPOCH 10 done: loss 0.0072 - lr: 0.000000 |
|
2023-10-25 00:48:14,630 DEV : loss 0.2083994448184967 - f1-score (micro avg) 0.8164 |
|
2023-10-25 00:48:14,643 saving best model |
|
2023-10-25 00:48:15,714 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 00:48:15,714 Loading model from best epoch ... |
|
2023-10-25 00:48:17,464 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 00:48:21,018 |
|
Results: |
|
- F-score (micro) 0.7987 |
|
- F-score (macro) 0.7004 |
|
- Accuracy 0.6738 |
|
|
|
By class: |
|
precision recall f1-score support |
|
|
|
PER 0.8539 0.7759 0.8130 482 |
|
LOC 0.8942 0.7751 0.8304 458 |
|
ORG 0.5510 0.3913 0.4576 69 |
|
|
|
micro avg 0.8552 0.7493 0.7987 1009 |
|
macro avg 0.7664 0.6474 0.7004 1009 |
|
weighted avg 0.8515 0.7493 0.7966 1009 |
|
|
|
2023-10-25 00:48:21,018 ---------------------------------------------------------------------------------------------------- |
|
|