| 2023-10-23 19:51:00,417 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:00,418 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=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-23 19:51:00,418 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:00,418 MultiCorpus: 966 train + 219 dev + 204 test sentences | |
| - NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator | |
| 2023-10-23 19:51:00,418 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:00,418 Train: 966 sentences | |
| 2023-10-23 19:51:00,418 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 19:51:00,418 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:00,418 Training Params: | |
| 2023-10-23 19:51:00,418 - learning_rate: "3e-05" | |
| 2023-10-23 19:51:00,418 - mini_batch_size: "4" | |
| 2023-10-23 19:51:00,418 - max_epochs: "10" | |
| 2023-10-23 19:51:00,418 - shuffle: "True" | |
| 2023-10-23 19:51:00,418 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:00,418 Plugins: | |
| 2023-10-23 19:51:00,418 - TensorboardLogger | |
| 2023-10-23 19:51:00,418 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 19:51:00,418 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:00,418 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 19:51:00,418 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 19:51:00,419 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:00,419 Computation: | |
| 2023-10-23 19:51:00,419 - compute on device: cuda:0 | |
| 2023-10-23 19:51:00,419 - embedding storage: none | |
| 2023-10-23 19:51:00,419 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:00,419 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-23 19:51:00,419 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:00,419 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:00,419 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 19:51:01,874 epoch 1 - iter 24/242 - loss 3.19223754 - time (sec): 1.45 - samples/sec: 1580.94 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 19:51:03,430 epoch 1 - iter 48/242 - loss 2.40588811 - time (sec): 3.01 - samples/sec: 1709.78 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 19:51:04,914 epoch 1 - iter 72/242 - loss 1.84035746 - time (sec): 4.49 - samples/sec: 1664.08 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 19:51:06,427 epoch 1 - iter 96/242 - loss 1.51170565 - time (sec): 6.01 - samples/sec: 1655.46 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 19:51:07,973 epoch 1 - iter 120/242 - loss 1.31512225 - time (sec): 7.55 - samples/sec: 1645.64 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 19:51:09,511 epoch 1 - iter 144/242 - loss 1.18607233 - time (sec): 9.09 - samples/sec: 1622.96 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 19:51:11,033 epoch 1 - iter 168/242 - loss 1.06918175 - time (sec): 10.61 - samples/sec: 1627.64 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 19:51:12,551 epoch 1 - iter 192/242 - loss 0.97368169 - time (sec): 12.13 - samples/sec: 1625.95 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:51:14,111 epoch 1 - iter 216/242 - loss 0.89392525 - time (sec): 13.69 - samples/sec: 1619.11 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 19:51:15,587 epoch 1 - iter 240/242 - loss 0.82808428 - time (sec): 15.17 - samples/sec: 1614.38 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 19:51:15,708 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:15,708 EPOCH 1 done: loss 0.8216 - lr: 0.000030 | |
| 2023-10-23 19:51:16,520 DEV : loss 0.1904076784849167 - f1-score (micro avg) 0.625 | |
| 2023-10-23 19:51:16,525 saving best model | |
| 2023-10-23 19:51:16,994 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:18,513 epoch 2 - iter 24/242 - loss 0.22047277 - time (sec): 1.52 - samples/sec: 1646.87 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 19:51:20,045 epoch 2 - iter 48/242 - loss 0.20656689 - time (sec): 3.05 - samples/sec: 1619.39 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 19:51:21,553 epoch 2 - iter 72/242 - loss 0.19524453 - time (sec): 4.56 - samples/sec: 1643.69 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 19:51:23,051 epoch 2 - iter 96/242 - loss 0.19474375 - time (sec): 6.06 - samples/sec: 1632.18 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 19:51:24,592 epoch 2 - iter 120/242 - loss 0.18071586 - time (sec): 7.60 - samples/sec: 1623.07 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 19:51:26,112 epoch 2 - iter 144/242 - loss 0.16705783 - time (sec): 9.12 - samples/sec: 1613.35 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 19:51:27,640 epoch 2 - iter 168/242 - loss 0.16801971 - time (sec): 10.65 - samples/sec: 1621.31 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 19:51:29,168 epoch 2 - iter 192/242 - loss 0.16601404 - time (sec): 12.17 - samples/sec: 1617.57 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 19:51:30,652 epoch 2 - iter 216/242 - loss 0.16087158 - time (sec): 13.66 - samples/sec: 1618.42 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 19:51:32,151 epoch 2 - iter 240/242 - loss 0.16125830 - time (sec): 15.16 - samples/sec: 1618.95 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 19:51:32,278 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:32,278 EPOCH 2 done: loss 0.1619 - lr: 0.000027 | |
| 2023-10-23 19:51:32,968 DEV : loss 0.12492977827787399 - f1-score (micro avg) 0.7722 | |
| 2023-10-23 19:51:32,971 saving best model | |
| 2023-10-23 19:51:33,599 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:35,073 epoch 3 - iter 24/242 - loss 0.08228198 - time (sec): 1.47 - samples/sec: 1552.71 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 19:51:36,602 epoch 3 - iter 48/242 - loss 0.09788978 - time (sec): 3.00 - samples/sec: 1525.66 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 19:51:38,188 epoch 3 - iter 72/242 - loss 0.09220848 - time (sec): 4.59 - samples/sec: 1586.49 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 19:51:39,708 epoch 3 - iter 96/242 - loss 0.08666506 - time (sec): 6.11 - samples/sec: 1576.05 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 19:51:41,227 epoch 3 - iter 120/242 - loss 0.09418845 - time (sec): 7.63 - samples/sec: 1615.54 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 19:51:42,734 epoch 3 - iter 144/242 - loss 0.09427390 - time (sec): 9.13 - samples/sec: 1593.25 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 19:51:44,275 epoch 3 - iter 168/242 - loss 0.09486656 - time (sec): 10.68 - samples/sec: 1613.18 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:51:45,765 epoch 3 - iter 192/242 - loss 0.09311269 - time (sec): 12.17 - samples/sec: 1605.05 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:51:47,288 epoch 3 - iter 216/242 - loss 0.09060481 - time (sec): 13.69 - samples/sec: 1599.99 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:51:48,825 epoch 3 - iter 240/242 - loss 0.09054203 - time (sec): 15.23 - samples/sec: 1613.16 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 19:51:48,950 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:48,950 EPOCH 3 done: loss 0.0903 - lr: 0.000023 | |
| 2023-10-23 19:51:49,642 DEV : loss 0.12668359279632568 - f1-score (micro avg) 0.8466 | |
| 2023-10-23 19:51:49,646 saving best model | |
| 2023-10-23 19:51:50,265 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:51:51,739 epoch 4 - iter 24/242 - loss 0.05375865 - time (sec): 1.47 - samples/sec: 1585.68 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 19:51:53,289 epoch 4 - iter 48/242 - loss 0.07423702 - time (sec): 3.02 - samples/sec: 1610.56 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 19:51:54,783 epoch 4 - iter 72/242 - loss 0.06761474 - time (sec): 4.52 - samples/sec: 1589.93 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 19:51:56,299 epoch 4 - iter 96/242 - loss 0.06999735 - time (sec): 6.03 - samples/sec: 1585.83 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 19:51:57,818 epoch 4 - iter 120/242 - loss 0.06846459 - time (sec): 7.55 - samples/sec: 1590.12 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 19:51:59,309 epoch 4 - iter 144/242 - loss 0.06195957 - time (sec): 9.04 - samples/sec: 1564.54 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 19:52:00,821 epoch 4 - iter 168/242 - loss 0.06057882 - time (sec): 10.55 - samples/sec: 1556.71 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 19:52:02,395 epoch 4 - iter 192/242 - loss 0.06467063 - time (sec): 12.13 - samples/sec: 1589.37 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 19:52:03,966 epoch 4 - iter 216/242 - loss 0.06723331 - time (sec): 13.70 - samples/sec: 1606.84 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 19:52:05,508 epoch 4 - iter 240/242 - loss 0.06588115 - time (sec): 15.24 - samples/sec: 1612.51 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 19:52:05,632 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:52:05,632 EPOCH 4 done: loss 0.0661 - lr: 0.000020 | |
| 2023-10-23 19:52:06,328 DEV : loss 0.14996084570884705 - f1-score (micro avg) 0.8433 | |
| 2023-10-23 19:52:06,332 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:52:07,845 epoch 5 - iter 24/242 - loss 0.03040416 - time (sec): 1.51 - samples/sec: 1661.72 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 19:52:09,375 epoch 5 - iter 48/242 - loss 0.02794239 - time (sec): 3.04 - samples/sec: 1650.07 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 19:52:10,919 epoch 5 - iter 72/242 - loss 0.03380901 - time (sec): 4.59 - samples/sec: 1646.76 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 19:52:12,408 epoch 5 - iter 96/242 - loss 0.03631379 - time (sec): 6.08 - samples/sec: 1643.93 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 19:52:13,940 epoch 5 - iter 120/242 - loss 0.03974207 - time (sec): 7.61 - samples/sec: 1658.61 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 19:52:15,416 epoch 5 - iter 144/242 - loss 0.04254043 - time (sec): 9.08 - samples/sec: 1642.07 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 19:52:16,944 epoch 5 - iter 168/242 - loss 0.04360087 - time (sec): 10.61 - samples/sec: 1633.29 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 19:52:18,446 epoch 5 - iter 192/242 - loss 0.04259084 - time (sec): 12.11 - samples/sec: 1639.22 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 19:52:20,011 epoch 5 - iter 216/242 - loss 0.04883753 - time (sec): 13.68 - samples/sec: 1642.98 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 19:52:21,547 epoch 5 - iter 240/242 - loss 0.04851010 - time (sec): 15.21 - samples/sec: 1621.60 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 19:52:21,656 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:52:21,656 EPOCH 5 done: loss 0.0485 - lr: 0.000017 | |
| 2023-10-23 19:52:22,354 DEV : loss 0.1554577797651291 - f1-score (micro avg) 0.8468 | |
| 2023-10-23 19:52:22,358 saving best model | |
| 2023-10-23 19:52:22,980 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:52:24,496 epoch 6 - iter 24/242 - loss 0.03258603 - time (sec): 1.52 - samples/sec: 1736.41 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 19:52:26,041 epoch 6 - iter 48/242 - loss 0.03134851 - time (sec): 3.06 - samples/sec: 1627.53 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 19:52:27,593 epoch 6 - iter 72/242 - loss 0.02940348 - time (sec): 4.61 - samples/sec: 1646.75 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 19:52:29,102 epoch 6 - iter 96/242 - loss 0.03693120 - time (sec): 6.12 - samples/sec: 1658.87 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 19:52:30,618 epoch 6 - iter 120/242 - loss 0.03724375 - time (sec): 7.64 - samples/sec: 1627.48 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 19:52:32,150 epoch 6 - iter 144/242 - loss 0.03517163 - time (sec): 9.17 - samples/sec: 1611.73 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 19:52:33,649 epoch 6 - iter 168/242 - loss 0.03754916 - time (sec): 10.67 - samples/sec: 1615.39 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 19:52:35,155 epoch 6 - iter 192/242 - loss 0.03910231 - time (sec): 12.17 - samples/sec: 1608.28 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 19:52:36,685 epoch 6 - iter 216/242 - loss 0.03635218 - time (sec): 13.70 - samples/sec: 1602.92 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 19:52:38,190 epoch 6 - iter 240/242 - loss 0.03612874 - time (sec): 15.21 - samples/sec: 1615.01 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 19:52:38,313 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:52:38,313 EPOCH 6 done: loss 0.0359 - lr: 0.000013 | |
| 2023-10-23 19:52:39,009 DEV : loss 0.178489550948143 - f1-score (micro avg) 0.8529 | |
| 2023-10-23 19:52:39,013 saving best model | |
| 2023-10-23 19:52:39,713 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:52:41,201 epoch 7 - iter 24/242 - loss 0.02150878 - time (sec): 1.49 - samples/sec: 1605.08 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 19:52:42,695 epoch 7 - iter 48/242 - loss 0.01844868 - time (sec): 2.98 - samples/sec: 1543.27 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 19:52:44,236 epoch 7 - iter 72/242 - loss 0.02196696 - time (sec): 4.52 - samples/sec: 1538.15 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 19:52:45,738 epoch 7 - iter 96/242 - loss 0.01979708 - time (sec): 6.02 - samples/sec: 1537.86 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 19:52:47,212 epoch 7 - iter 120/242 - loss 0.02718489 - time (sec): 7.50 - samples/sec: 1540.47 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 19:52:48,774 epoch 7 - iter 144/242 - loss 0.02457534 - time (sec): 9.06 - samples/sec: 1574.81 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 19:52:50,354 epoch 7 - iter 168/242 - loss 0.02497261 - time (sec): 10.64 - samples/sec: 1598.71 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 19:52:51,860 epoch 7 - iter 192/242 - loss 0.02243602 - time (sec): 12.15 - samples/sec: 1599.45 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 19:52:53,426 epoch 7 - iter 216/242 - loss 0.02458389 - time (sec): 13.71 - samples/sec: 1609.59 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 19:52:54,959 epoch 7 - iter 240/242 - loss 0.02548208 - time (sec): 15.24 - samples/sec: 1615.89 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 19:52:55,074 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:52:55,075 EPOCH 7 done: loss 0.0265 - lr: 0.000010 | |
| 2023-10-23 19:52:55,767 DEV : loss 0.1920190155506134 - f1-score (micro avg) 0.847 | |
| 2023-10-23 19:52:55,770 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:52:57,301 epoch 8 - iter 24/242 - loss 0.02151881 - time (sec): 1.53 - samples/sec: 1623.18 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 19:52:58,781 epoch 8 - iter 48/242 - loss 0.02073414 - time (sec): 3.01 - samples/sec: 1623.83 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 19:53:00,304 epoch 8 - iter 72/242 - loss 0.01991517 - time (sec): 4.53 - samples/sec: 1684.27 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 19:53:01,830 epoch 8 - iter 96/242 - loss 0.01720566 - time (sec): 6.06 - samples/sec: 1665.22 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 19:53:03,308 epoch 8 - iter 120/242 - loss 0.01675706 - time (sec): 7.54 - samples/sec: 1640.96 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 19:53:04,816 epoch 8 - iter 144/242 - loss 0.01692203 - time (sec): 9.04 - samples/sec: 1624.27 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 19:53:06,370 epoch 8 - iter 168/242 - loss 0.01690889 - time (sec): 10.60 - samples/sec: 1620.66 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 19:53:07,930 epoch 8 - iter 192/242 - loss 0.01728285 - time (sec): 12.16 - samples/sec: 1635.44 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 19:53:09,442 epoch 8 - iter 216/242 - loss 0.01730991 - time (sec): 13.67 - samples/sec: 1630.31 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 19:53:10,974 epoch 8 - iter 240/242 - loss 0.01675284 - time (sec): 15.20 - samples/sec: 1621.37 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 19:53:11,086 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:53:11,087 EPOCH 8 done: loss 0.0167 - lr: 0.000007 | |
| 2023-10-23 19:53:11,908 DEV : loss 0.18184901773929596 - f1-score (micro avg) 0.8501 | |
| 2023-10-23 19:53:11,912 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:53:13,455 epoch 9 - iter 24/242 - loss 0.00672192 - time (sec): 1.54 - samples/sec: 1686.59 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 19:53:14,978 epoch 9 - iter 48/242 - loss 0.00495635 - time (sec): 3.07 - samples/sec: 1663.03 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 19:53:16,509 epoch 9 - iter 72/242 - loss 0.01198613 - time (sec): 4.60 - samples/sec: 1638.27 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 19:53:18,013 epoch 9 - iter 96/242 - loss 0.01151938 - time (sec): 6.10 - samples/sec: 1613.86 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 19:53:19,476 epoch 9 - iter 120/242 - loss 0.01046535 - time (sec): 7.56 - samples/sec: 1571.19 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 19:53:21,035 epoch 9 - iter 144/242 - loss 0.01032059 - time (sec): 9.12 - samples/sec: 1589.91 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 19:53:22,534 epoch 9 - iter 168/242 - loss 0.01270544 - time (sec): 10.62 - samples/sec: 1591.14 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 19:53:24,111 epoch 9 - iter 192/242 - loss 0.01126915 - time (sec): 12.20 - samples/sec: 1598.34 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 19:53:25,651 epoch 9 - iter 216/242 - loss 0.01188979 - time (sec): 13.74 - samples/sec: 1594.49 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 19:53:27,186 epoch 9 - iter 240/242 - loss 0.01147686 - time (sec): 15.27 - samples/sec: 1611.90 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 19:53:27,298 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:53:27,298 EPOCH 9 done: loss 0.0114 - lr: 0.000003 | |
| 2023-10-23 19:53:27,996 DEV : loss 0.20280949771404266 - f1-score (micro avg) 0.8432 | |
| 2023-10-23 19:53:28,000 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:53:29,539 epoch 10 - iter 24/242 - loss 0.01646384 - time (sec): 1.54 - samples/sec: 1579.90 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 19:53:31,030 epoch 10 - iter 48/242 - loss 0.01825067 - time (sec): 3.03 - samples/sec: 1500.23 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 19:53:32,543 epoch 10 - iter 72/242 - loss 0.01305417 - time (sec): 4.54 - samples/sec: 1545.99 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 19:53:34,136 epoch 10 - iter 96/242 - loss 0.01266924 - time (sec): 6.13 - samples/sec: 1567.26 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 19:53:35,629 epoch 10 - iter 120/242 - loss 0.01209649 - time (sec): 7.63 - samples/sec: 1574.74 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 19:53:37,156 epoch 10 - iter 144/242 - loss 0.01165806 - time (sec): 9.16 - samples/sec: 1586.89 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 19:53:38,724 epoch 10 - iter 168/242 - loss 0.01084567 - time (sec): 10.72 - samples/sec: 1607.40 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 19:53:40,273 epoch 10 - iter 192/242 - loss 0.00982812 - time (sec): 12.27 - samples/sec: 1602.62 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 19:53:41,814 epoch 10 - iter 216/242 - loss 0.00942024 - time (sec): 13.81 - samples/sec: 1619.41 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 19:53:43,325 epoch 10 - iter 240/242 - loss 0.00884086 - time (sec): 15.32 - samples/sec: 1608.24 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 19:53:43,436 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:53:43,436 EPOCH 10 done: loss 0.0088 - lr: 0.000000 | |
| 2023-10-23 19:53:44,137 DEV : loss 0.2002663016319275 - f1-score (micro avg) 0.8483 | |
| 2023-10-23 19:53:44,610 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:53:44,611 Loading model from best epoch ... | |
| 2023-10-23 19:53:46,074 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date | |
| 2023-10-23 19:53:46,809 | |
| Results: | |
| - F-score (micro) 0.7866 | |
| - F-score (macro) 0.5592 | |
| - Accuracy 0.6705 | |
| By class: | |
| precision recall f1-score support | |
| pers 0.8345 0.8705 0.8521 139 | |
| scope 0.7832 0.8682 0.8235 129 | |
| work 0.6129 0.7125 0.6590 80 | |
| loc 0.7500 0.3333 0.4615 9 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.7610 0.8139 0.7866 360 | |
| macro avg 0.5961 0.5569 0.5592 360 | |
| weighted avg 0.7578 0.8139 0.7821 360 | |
| 2023-10-23 19:53:46,809 ---------------------------------------------------------------------------------------------------- | |