| 2023-10-25 11:49:28,311 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:49:28,312 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 11:49:28,312 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:49:28,312 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences | |
| - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator | |
| 2023-10-25 11:49:28,312 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:49:28,312 Train: 14465 sentences | |
| 2023-10-25 11:49:28,312 (train_with_dev=False, train_with_test=False) | |
| 2023-10-25 11:49:28,312 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:49:28,312 Training Params: | |
| 2023-10-25 11:49:28,312 - learning_rate: "5e-05" | |
| 2023-10-25 11:49:28,312 - mini_batch_size: "4" | |
| 2023-10-25 11:49:28,312 - max_epochs: "10" | |
| 2023-10-25 11:49:28,312 - shuffle: "True" | |
| 2023-10-25 11:49:28,312 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:49:28,312 Plugins: | |
| 2023-10-25 11:49:28,312 - TensorboardLogger | |
| 2023-10-25 11:49:28,312 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-25 11:49:28,312 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:49:28,312 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-25 11:49:28,312 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-25 11:49:28,312 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:49:28,312 Computation: | |
| 2023-10-25 11:49:28,312 - compute on device: cuda:0 | |
| 2023-10-25 11:49:28,312 - embedding storage: none | |
| 2023-10-25 11:49:28,312 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:49:28,313 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-25 11:49:28,313 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:49:28,313 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:49:28,313 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-25 11:49:50,809 epoch 1 - iter 361/3617 - loss 0.86993127 - time (sec): 22.50 - samples/sec: 1710.07 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 11:50:13,270 epoch 1 - iter 722/3617 - loss 0.52060995 - time (sec): 44.96 - samples/sec: 1692.19 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 11:50:35,928 epoch 1 - iter 1083/3617 - loss 0.39422738 - time (sec): 67.61 - samples/sec: 1687.75 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 11:50:58,635 epoch 1 - iter 1444/3617 - loss 0.32755860 - time (sec): 90.32 - samples/sec: 1677.54 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 11:51:20,989 epoch 1 - iter 1805/3617 - loss 0.28743077 - time (sec): 112.68 - samples/sec: 1664.91 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 11:51:43,571 epoch 1 - iter 2166/3617 - loss 0.25847487 - time (sec): 135.26 - samples/sec: 1665.35 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 11:52:06,563 epoch 1 - iter 2527/3617 - loss 0.23733988 - time (sec): 158.25 - samples/sec: 1674.91 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 11:52:29,326 epoch 1 - iter 2888/3617 - loss 0.22332063 - time (sec): 181.01 - samples/sec: 1678.95 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 11:52:51,919 epoch 1 - iter 3249/3617 - loss 0.21156741 - time (sec): 203.61 - samples/sec: 1675.79 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 11:53:14,580 epoch 1 - iter 3610/3617 - loss 0.20214765 - time (sec): 226.27 - samples/sec: 1676.00 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-25 11:53:15,001 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:53:15,001 EPOCH 1 done: loss 0.2021 - lr: 0.000050 | |
| 2023-10-25 11:53:19,501 DEV : loss 0.14469869434833527 - f1-score (micro avg) 0.5759 | |
| 2023-10-25 11:53:19,522 saving best model | |
| 2023-10-25 11:53:20,071 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:53:42,599 epoch 2 - iter 361/3617 - loss 0.10828242 - time (sec): 22.53 - samples/sec: 1681.04 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 11:54:05,556 epoch 2 - iter 722/3617 - loss 0.11062343 - time (sec): 45.48 - samples/sec: 1692.62 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 11:54:28,432 epoch 2 - iter 1083/3617 - loss 0.11343990 - time (sec): 68.36 - samples/sec: 1689.62 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 11:54:51,191 epoch 2 - iter 1444/3617 - loss 0.11147450 - time (sec): 91.12 - samples/sec: 1693.49 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 11:55:13,719 epoch 2 - iter 1805/3617 - loss 0.11268183 - time (sec): 113.65 - samples/sec: 1686.21 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 11:55:36,251 epoch 2 - iter 2166/3617 - loss 0.11108706 - time (sec): 136.18 - samples/sec: 1685.34 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 11:55:58,771 epoch 2 - iter 2527/3617 - loss 0.10962742 - time (sec): 158.70 - samples/sec: 1678.37 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 11:56:21,330 epoch 2 - iter 2888/3617 - loss 0.10930890 - time (sec): 181.26 - samples/sec: 1677.39 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 11:56:43,852 epoch 2 - iter 3249/3617 - loss 0.10745796 - time (sec): 203.78 - samples/sec: 1678.49 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 11:57:06,613 epoch 2 - iter 3610/3617 - loss 0.10586077 - time (sec): 226.54 - samples/sec: 1673.92 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 11:57:07,071 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:57:07,071 EPOCH 2 done: loss 0.1058 - lr: 0.000044 | |
| 2023-10-25 11:57:12,310 DEV : loss 0.14430101215839386 - f1-score (micro avg) 0.6079 | |
| 2023-10-25 11:57:12,332 saving best model | |
| 2023-10-25 11:57:13,111 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:57:35,931 epoch 3 - iter 361/3617 - loss 0.07144153 - time (sec): 22.82 - samples/sec: 1734.60 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 11:57:58,787 epoch 3 - iter 722/3617 - loss 0.08074855 - time (sec): 45.68 - samples/sec: 1719.95 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 11:58:21,681 epoch 3 - iter 1083/3617 - loss 0.08263674 - time (sec): 68.57 - samples/sec: 1716.05 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 11:58:44,087 epoch 3 - iter 1444/3617 - loss 0.08288668 - time (sec): 90.97 - samples/sec: 1695.55 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 11:59:06,702 epoch 3 - iter 1805/3617 - loss 0.10363913 - time (sec): 113.59 - samples/sec: 1690.82 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 11:59:29,167 epoch 3 - iter 2166/3617 - loss 0.13603267 - time (sec): 136.06 - samples/sec: 1683.24 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 11:59:51,558 epoch 3 - iter 2527/3617 - loss 0.15873752 - time (sec): 158.45 - samples/sec: 1675.58 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 12:00:14,538 epoch 3 - iter 2888/3617 - loss 0.17453687 - time (sec): 181.43 - samples/sec: 1674.80 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 12:00:37,065 epoch 3 - iter 3249/3617 - loss 0.18855528 - time (sec): 203.95 - samples/sec: 1676.48 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 12:00:59,529 epoch 3 - iter 3610/3617 - loss 0.20118879 - time (sec): 226.42 - samples/sec: 1675.07 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 12:00:59,959 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:00:59,960 EPOCH 3 done: loss 0.2013 - lr: 0.000039 | |
| 2023-10-25 12:01:05,163 DEV : loss 0.2843758761882782 - f1-score (micro avg) 0.0046 | |
| 2023-10-25 12:01:05,185 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:01:27,882 epoch 4 - iter 361/3617 - loss 0.31486142 - time (sec): 22.70 - samples/sec: 1706.40 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 12:01:50,468 epoch 4 - iter 722/3617 - loss 0.30266314 - time (sec): 45.28 - samples/sec: 1686.83 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 12:02:13,127 epoch 4 - iter 1083/3617 - loss 0.30220104 - time (sec): 67.94 - samples/sec: 1689.02 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 12:02:35,756 epoch 4 - iter 1444/3617 - loss 0.29844936 - time (sec): 90.57 - samples/sec: 1670.74 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 12:02:58,524 epoch 4 - iter 1805/3617 - loss 0.29550689 - time (sec): 113.34 - samples/sec: 1672.63 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 12:03:21,138 epoch 4 - iter 2166/3617 - loss 0.29482135 - time (sec): 135.95 - samples/sec: 1663.58 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 12:03:43,665 epoch 4 - iter 2527/3617 - loss 0.29559234 - time (sec): 158.48 - samples/sec: 1663.63 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 12:04:06,283 epoch 4 - iter 2888/3617 - loss 0.29737787 - time (sec): 181.10 - samples/sec: 1660.70 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 12:04:29,216 epoch 4 - iter 3249/3617 - loss 0.29938044 - time (sec): 204.03 - samples/sec: 1667.11 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 12:04:52,016 epoch 4 - iter 3610/3617 - loss 0.29694305 - time (sec): 226.83 - samples/sec: 1672.49 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 12:04:52,435 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:04:52,436 EPOCH 4 done: loss 0.2968 - lr: 0.000033 | |
| 2023-10-25 12:04:57,151 DEV : loss 0.2834990918636322 - f1-score (micro avg) 0.0023 | |
| 2023-10-25 12:04:57,173 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:05:20,646 epoch 5 - iter 361/3617 - loss 0.30958497 - time (sec): 23.47 - samples/sec: 1681.65 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 12:05:43,246 epoch 5 - iter 722/3617 - loss 0.29814374 - time (sec): 46.07 - samples/sec: 1668.88 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 12:06:05,856 epoch 5 - iter 1083/3617 - loss 0.29063581 - time (sec): 68.68 - samples/sec: 1663.40 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 12:06:28,402 epoch 5 - iter 1444/3617 - loss 0.28726657 - time (sec): 91.23 - samples/sec: 1668.57 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 12:06:50,962 epoch 5 - iter 1805/3617 - loss 0.28881196 - time (sec): 113.79 - samples/sec: 1669.95 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 12:07:13,960 epoch 5 - iter 2166/3617 - loss 0.28967773 - time (sec): 136.79 - samples/sec: 1673.87 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 12:07:36,621 epoch 5 - iter 2527/3617 - loss 0.29134561 - time (sec): 159.45 - samples/sec: 1668.53 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 12:07:59,257 epoch 5 - iter 2888/3617 - loss 0.29414601 - time (sec): 182.08 - samples/sec: 1667.95 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 12:08:21,892 epoch 5 - iter 3249/3617 - loss 0.29373568 - time (sec): 204.72 - samples/sec: 1663.60 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 12:08:44,658 epoch 5 - iter 3610/3617 - loss 0.29343011 - time (sec): 227.48 - samples/sec: 1667.69 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 12:08:45,069 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:08:45,069 EPOCH 5 done: loss 0.2934 - lr: 0.000028 | |
| 2023-10-25 12:08:49,763 DEV : loss 0.27164599299430847 - f1-score (micro avg) 0.0 | |
| 2023-10-25 12:08:49,785 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:09:12,514 epoch 6 - iter 361/3617 - loss 0.31431851 - time (sec): 22.73 - samples/sec: 1671.84 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 12:09:35,378 epoch 6 - iter 722/3617 - loss 0.29910863 - time (sec): 45.59 - samples/sec: 1692.45 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 12:09:58,193 epoch 6 - iter 1083/3617 - loss 0.29460583 - time (sec): 68.41 - samples/sec: 1692.25 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 12:10:20,897 epoch 6 - iter 1444/3617 - loss 0.29799880 - time (sec): 91.11 - samples/sec: 1687.46 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 12:10:43,359 epoch 6 - iter 1805/3617 - loss 0.29509303 - time (sec): 113.57 - samples/sec: 1680.84 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 12:11:05,929 epoch 6 - iter 2166/3617 - loss 0.29227878 - time (sec): 136.14 - samples/sec: 1674.83 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 12:11:28,526 epoch 6 - iter 2527/3617 - loss 0.29220228 - time (sec): 158.74 - samples/sec: 1669.69 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 12:11:51,388 epoch 6 - iter 2888/3617 - loss 0.28976457 - time (sec): 181.60 - samples/sec: 1677.10 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 12:12:13,993 epoch 6 - iter 3249/3617 - loss 0.28949741 - time (sec): 204.21 - samples/sec: 1674.39 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 12:12:36,781 epoch 6 - iter 3610/3617 - loss 0.29047095 - time (sec): 226.99 - samples/sec: 1670.50 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 12:12:37,217 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:12:37,218 EPOCH 6 done: loss 0.2905 - lr: 0.000022 | |
| 2023-10-25 12:12:42,446 DEV : loss 0.2741363048553467 - f1-score (micro avg) 0.0 | |
| 2023-10-25 12:12:42,469 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:13:05,031 epoch 7 - iter 361/3617 - loss 0.28801601 - time (sec): 22.56 - samples/sec: 1668.20 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 12:13:27,676 epoch 7 - iter 722/3617 - loss 0.28684817 - time (sec): 45.21 - samples/sec: 1642.00 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 12:13:50,389 epoch 7 - iter 1083/3617 - loss 0.28911761 - time (sec): 67.92 - samples/sec: 1636.66 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 12:14:12,991 epoch 7 - iter 1444/3617 - loss 0.28494759 - time (sec): 90.52 - samples/sec: 1647.46 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 12:14:35,764 epoch 7 - iter 1805/3617 - loss 0.28299654 - time (sec): 113.29 - samples/sec: 1651.43 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 12:14:58,250 epoch 7 - iter 2166/3617 - loss 0.28544928 - time (sec): 135.78 - samples/sec: 1648.64 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 12:15:21,100 epoch 7 - iter 2527/3617 - loss 0.28500039 - time (sec): 158.63 - samples/sec: 1656.30 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 12:15:44,065 epoch 7 - iter 2888/3617 - loss 0.28630743 - time (sec): 181.60 - samples/sec: 1662.84 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 12:16:06,597 epoch 7 - iter 3249/3617 - loss 0.28966796 - time (sec): 204.13 - samples/sec: 1667.85 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 12:16:29,444 epoch 7 - iter 3610/3617 - loss 0.29008210 - time (sec): 226.97 - samples/sec: 1671.33 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 12:16:29,851 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:16:29,852 EPOCH 7 done: loss 0.2903 - lr: 0.000017 | |
| 2023-10-25 12:16:35,059 DEV : loss 0.26774144172668457 - f1-score (micro avg) 0.0 | |
| 2023-10-25 12:16:35,081 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:16:57,825 epoch 8 - iter 361/3617 - loss 0.27660386 - time (sec): 22.74 - samples/sec: 1704.22 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 12:17:20,392 epoch 8 - iter 722/3617 - loss 0.28079844 - time (sec): 45.31 - samples/sec: 1685.49 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 12:17:43,247 epoch 8 - iter 1083/3617 - loss 0.29020034 - time (sec): 68.17 - samples/sec: 1680.45 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 12:18:05,766 epoch 8 - iter 1444/3617 - loss 0.29429510 - time (sec): 90.68 - samples/sec: 1672.78 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 12:18:28,476 epoch 8 - iter 1805/3617 - loss 0.29349848 - time (sec): 113.39 - samples/sec: 1670.15 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 12:18:51,283 epoch 8 - iter 2166/3617 - loss 0.29446113 - time (sec): 136.20 - samples/sec: 1679.67 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 12:19:13,886 epoch 8 - iter 2527/3617 - loss 0.29023797 - time (sec): 158.80 - samples/sec: 1679.28 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 12:19:36,555 epoch 8 - iter 2888/3617 - loss 0.28871733 - time (sec): 181.47 - samples/sec: 1680.37 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 12:19:59,060 epoch 8 - iter 3249/3617 - loss 0.29028619 - time (sec): 203.98 - samples/sec: 1678.18 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 12:20:21,609 epoch 8 - iter 3610/3617 - loss 0.28929915 - time (sec): 226.53 - samples/sec: 1673.87 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 12:20:22,052 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:20:22,052 EPOCH 8 done: loss 0.2893 - lr: 0.000011 | |
| 2023-10-25 12:20:27,261 DEV : loss 0.2751471996307373 - f1-score (micro avg) 0.0 | |
| 2023-10-25 12:20:27,283 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:20:49,886 epoch 9 - iter 361/3617 - loss 0.30361453 - time (sec): 22.60 - samples/sec: 1645.83 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 12:21:12,574 epoch 9 - iter 722/3617 - loss 0.29195695 - time (sec): 45.29 - samples/sec: 1654.32 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 12:21:35,215 epoch 9 - iter 1083/3617 - loss 0.29457114 - time (sec): 67.93 - samples/sec: 1652.12 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 12:21:58,034 epoch 9 - iter 1444/3617 - loss 0.29407289 - time (sec): 90.75 - samples/sec: 1668.14 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 12:22:20,669 epoch 9 - iter 1805/3617 - loss 0.29048332 - time (sec): 113.39 - samples/sec: 1671.64 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 12:22:43,706 epoch 9 - iter 2166/3617 - loss 0.28277675 - time (sec): 136.42 - samples/sec: 1676.87 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 12:23:06,481 epoch 9 - iter 2527/3617 - loss 0.28719758 - time (sec): 159.20 - samples/sec: 1675.04 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 12:23:29,126 epoch 9 - iter 2888/3617 - loss 0.28670629 - time (sec): 181.84 - samples/sec: 1677.11 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 12:23:51,359 epoch 9 - iter 3249/3617 - loss 0.28859893 - time (sec): 204.08 - samples/sec: 1670.16 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 12:24:14,063 epoch 9 - iter 3610/3617 - loss 0.28826189 - time (sec): 226.78 - samples/sec: 1672.48 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 12:24:14,484 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:24:14,484 EPOCH 9 done: loss 0.2882 - lr: 0.000006 | |
| 2023-10-25 12:24:19,699 DEV : loss 0.27169540524482727 - f1-score (micro avg) 0.0 | |
| 2023-10-25 12:24:19,721 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:24:42,190 epoch 10 - iter 361/3617 - loss 0.26792150 - time (sec): 22.47 - samples/sec: 1653.50 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 12:25:05,071 epoch 10 - iter 722/3617 - loss 0.27746427 - time (sec): 45.35 - samples/sec: 1662.83 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 12:25:28,013 epoch 10 - iter 1083/3617 - loss 0.27477559 - time (sec): 68.29 - samples/sec: 1680.32 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 12:25:50,616 epoch 10 - iter 1444/3617 - loss 0.27361481 - time (sec): 90.89 - samples/sec: 1678.02 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 12:26:13,325 epoch 10 - iter 1805/3617 - loss 0.27593718 - time (sec): 113.60 - samples/sec: 1684.69 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 12:26:35,800 epoch 10 - iter 2166/3617 - loss 0.28020518 - time (sec): 136.08 - samples/sec: 1674.36 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 12:26:58,435 epoch 10 - iter 2527/3617 - loss 0.28002646 - time (sec): 158.71 - samples/sec: 1673.74 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 12:27:21,055 epoch 10 - iter 2888/3617 - loss 0.27933392 - time (sec): 181.33 - samples/sec: 1673.50 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 12:27:43,896 epoch 10 - iter 3249/3617 - loss 0.28251991 - time (sec): 204.17 - samples/sec: 1677.60 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 12:28:06,393 epoch 10 - iter 3610/3617 - loss 0.28721607 - time (sec): 226.67 - samples/sec: 1673.50 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 12:28:06,815 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:28:06,815 EPOCH 10 done: loss 0.2873 - lr: 0.000000 | |
| 2023-10-25 12:28:11,509 DEV : loss 0.27294182777404785 - f1-score (micro avg) 0.0 | |
| 2023-10-25 12:28:12,086 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:28:12,087 Loading model from best epoch ... | |
| 2023-10-25 12:28:13,838 SequenceTagger predicts: Dictionary with 13 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 | |
| 2023-10-25 12:28:20,073 | |
| Results: | |
| - F-score (micro) 0.639 | |
| - F-score (macro) 0.4364 | |
| - Accuracy 0.4803 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.6601 0.7360 0.6960 591 | |
| pers 0.5473 0.6975 0.6133 357 | |
| org 0.0000 0.0000 0.0000 79 | |
| micro avg 0.6140 0.6660 0.6390 1027 | |
| macro avg 0.4024 0.4778 0.4364 1027 | |
| weighted avg 0.5701 0.6660 0.6137 1027 | |
| 2023-10-25 12:28:20,073 ---------------------------------------------------------------------------------------------------- | |