| 2023-10-23 19:29:49,570 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:49,571 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 19:29:49,571 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:49,571 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 19:29:49,571 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:49,571 Train: 966 sentences | |
| 2023-10-23 19:29:49,571 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 19:29:49,571 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:49,571 Training Params: | |
| 2023-10-23 19:29:49,571 - learning_rate: "3e-05" | |
| 2023-10-23 19:29:49,571 - mini_batch_size: "4" | |
| 2023-10-23 19:29:49,571 - max_epochs: "10" | |
| 2023-10-23 19:29:49,571 - shuffle: "True" | |
| 2023-10-23 19:29:49,571 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:49,571 Plugins: | |
| 2023-10-23 19:29:49,571 - TensorboardLogger | |
| 2023-10-23 19:29:49,571 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 19:29:49,571 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:49,572 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 19:29:49,572 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 19:29:49,572 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:49,572 Computation: | |
| 2023-10-23 19:29:49,572 - compute on device: cuda:0 | |
| 2023-10-23 19:29:49,572 - embedding storage: none | |
| 2023-10-23 19:29:49,572 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:49,572 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-23 19:29:49,572 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:49,572 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:49,572 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 19:29:51,021 epoch 1 - iter 24/242 - loss 2.98287844 - time (sec): 1.45 - samples/sec: 1489.27 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 19:29:52,539 epoch 1 - iter 48/242 - loss 2.26117522 - time (sec): 2.97 - samples/sec: 1617.92 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 19:29:54,030 epoch 1 - iter 72/242 - loss 1.76926638 - time (sec): 4.46 - samples/sec: 1573.78 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 19:29:55,538 epoch 1 - iter 96/242 - loss 1.46345492 - time (sec): 5.97 - samples/sec: 1585.41 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 19:29:57,026 epoch 1 - iter 120/242 - loss 1.25478029 - time (sec): 7.45 - samples/sec: 1587.11 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 19:29:58,565 epoch 1 - iter 144/242 - loss 1.09074253 - time (sec): 8.99 - samples/sec: 1608.26 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 19:30:00,155 epoch 1 - iter 168/242 - loss 0.98154842 - time (sec): 10.58 - samples/sec: 1618.75 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 19:30:01,639 epoch 1 - iter 192/242 - loss 0.89632668 - time (sec): 12.07 - samples/sec: 1618.33 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:30:03,136 epoch 1 - iter 216/242 - loss 0.82169295 - time (sec): 13.56 - samples/sec: 1612.00 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 19:30:04,692 epoch 1 - iter 240/242 - loss 0.75910623 - time (sec): 15.12 - samples/sec: 1620.78 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 19:30:04,820 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:30:04,820 EPOCH 1 done: loss 0.7531 - lr: 0.000030 | |
| 2023-10-23 19:30:05,632 DEV : loss 0.1827384978532791 - f1-score (micro avg) 0.6213 | |
| 2023-10-23 19:30:05,636 saving best model | |
| 2023-10-23 19:30:06,104 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:30:07,610 epoch 2 - iter 24/242 - loss 0.13604524 - time (sec): 1.51 - samples/sec: 1685.70 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 19:30:09,092 epoch 2 - iter 48/242 - loss 0.16051416 - time (sec): 2.99 - samples/sec: 1606.50 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 19:30:10,571 epoch 2 - iter 72/242 - loss 0.16266687 - time (sec): 4.47 - samples/sec: 1587.93 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 19:30:12,084 epoch 2 - iter 96/242 - loss 0.16915945 - time (sec): 5.98 - samples/sec: 1586.67 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 19:30:13,664 epoch 2 - iter 120/242 - loss 0.16054725 - time (sec): 7.56 - samples/sec: 1614.35 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 19:30:15,218 epoch 2 - iter 144/242 - loss 0.15751912 - time (sec): 9.11 - samples/sec: 1619.90 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 19:30:16,764 epoch 2 - iter 168/242 - loss 0.15934129 - time (sec): 10.66 - samples/sec: 1625.26 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 19:30:18,272 epoch 2 - iter 192/242 - loss 0.15641142 - time (sec): 12.17 - samples/sec: 1617.13 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 19:30:19,801 epoch 2 - iter 216/242 - loss 0.15506669 - time (sec): 13.70 - samples/sec: 1623.99 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 19:30:21,317 epoch 2 - iter 240/242 - loss 0.15220355 - time (sec): 15.21 - samples/sec: 1617.97 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 19:30:21,431 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:30:21,431 EPOCH 2 done: loss 0.1516 - lr: 0.000027 | |
| 2023-10-23 19:30:22,122 DEV : loss 0.12770959734916687 - f1-score (micro avg) 0.7935 | |
| 2023-10-23 19:30:22,125 saving best model | |
| 2023-10-23 19:30:22,824 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:30:24,302 epoch 3 - iter 24/242 - loss 0.12719161 - time (sec): 1.48 - samples/sec: 1577.87 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 19:30:25,824 epoch 3 - iter 48/242 - loss 0.11257977 - time (sec): 3.00 - samples/sec: 1578.28 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 19:30:27,346 epoch 3 - iter 72/242 - loss 0.11151491 - time (sec): 4.52 - samples/sec: 1628.09 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 19:30:28,909 epoch 3 - iter 96/242 - loss 0.10559088 - time (sec): 6.08 - samples/sec: 1644.85 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 19:30:30,427 epoch 3 - iter 120/242 - loss 0.09317932 - time (sec): 7.60 - samples/sec: 1671.53 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 19:30:31,909 epoch 3 - iter 144/242 - loss 0.09460460 - time (sec): 9.08 - samples/sec: 1652.42 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 19:30:33,459 epoch 3 - iter 168/242 - loss 0.09435856 - time (sec): 10.63 - samples/sec: 1643.72 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:30:34,949 epoch 3 - iter 192/242 - loss 0.09314101 - time (sec): 12.12 - samples/sec: 1621.29 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:30:36,529 epoch 3 - iter 216/242 - loss 0.10155585 - time (sec): 13.70 - samples/sec: 1619.78 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:30:38,045 epoch 3 - iter 240/242 - loss 0.09838725 - time (sec): 15.22 - samples/sec: 1619.20 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 19:30:38,158 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:30:38,159 EPOCH 3 done: loss 0.0980 - lr: 0.000023 | |
| 2023-10-23 19:30:38,852 DEV : loss 0.1285228729248047 - f1-score (micro avg) 0.8362 | |
| 2023-10-23 19:30:38,856 saving best model | |
| 2023-10-23 19:30:39,547 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:30:41,015 epoch 4 - iter 24/242 - loss 0.04685614 - time (sec): 1.47 - samples/sec: 1580.95 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 19:30:42,569 epoch 4 - iter 48/242 - loss 0.08110896 - time (sec): 3.02 - samples/sec: 1600.25 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 19:30:44,072 epoch 4 - iter 72/242 - loss 0.07997580 - time (sec): 4.52 - samples/sec: 1640.82 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 19:30:45,644 epoch 4 - iter 96/242 - loss 0.07417430 - time (sec): 6.10 - samples/sec: 1628.90 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 19:30:47,137 epoch 4 - iter 120/242 - loss 0.06583957 - time (sec): 7.59 - samples/sec: 1608.25 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 19:30:48,700 epoch 4 - iter 144/242 - loss 0.06891605 - time (sec): 9.15 - samples/sec: 1633.63 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 19:30:50,232 epoch 4 - iter 168/242 - loss 0.06741911 - time (sec): 10.68 - samples/sec: 1628.92 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 19:30:51,785 epoch 4 - iter 192/242 - loss 0.06826652 - time (sec): 12.24 - samples/sec: 1620.78 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 19:30:53,271 epoch 4 - iter 216/242 - loss 0.06909254 - time (sec): 13.72 - samples/sec: 1608.79 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 19:30:54,785 epoch 4 - iter 240/242 - loss 0.06791650 - time (sec): 15.24 - samples/sec: 1612.41 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 19:30:54,901 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:30:54,902 EPOCH 4 done: loss 0.0675 - lr: 0.000020 | |
| 2023-10-23 19:30:55,598 DEV : loss 0.16268931329250336 - f1-score (micro avg) 0.8259 | |
| 2023-10-23 19:30:55,602 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:30:57,140 epoch 5 - iter 24/242 - loss 0.05705890 - time (sec): 1.54 - samples/sec: 1606.57 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 19:30:58,668 epoch 5 - iter 48/242 - loss 0.05415032 - time (sec): 3.07 - samples/sec: 1623.01 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 19:31:00,159 epoch 5 - iter 72/242 - loss 0.05768220 - time (sec): 4.56 - samples/sec: 1624.60 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 19:31:01,659 epoch 5 - iter 96/242 - loss 0.05428573 - time (sec): 6.06 - samples/sec: 1634.34 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 19:31:03,167 epoch 5 - iter 120/242 - loss 0.05240841 - time (sec): 7.56 - samples/sec: 1637.80 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 19:31:04,711 epoch 5 - iter 144/242 - loss 0.04914866 - time (sec): 9.11 - samples/sec: 1636.15 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 19:31:06,237 epoch 5 - iter 168/242 - loss 0.04959201 - time (sec): 10.64 - samples/sec: 1630.73 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 19:31:07,753 epoch 5 - iter 192/242 - loss 0.04995992 - time (sec): 12.15 - samples/sec: 1605.06 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 19:31:09,284 epoch 5 - iter 216/242 - loss 0.04891403 - time (sec): 13.68 - samples/sec: 1612.94 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 19:31:10,852 epoch 5 - iter 240/242 - loss 0.04560757 - time (sec): 15.25 - samples/sec: 1615.49 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 19:31:10,962 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:31:10,962 EPOCH 5 done: loss 0.0457 - lr: 0.000017 | |
| 2023-10-23 19:31:11,659 DEV : loss 0.1693263053894043 - f1-score (micro avg) 0.8425 | |
| 2023-10-23 19:31:11,663 saving best model | |
| 2023-10-23 19:31:12,458 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:31:13,964 epoch 6 - iter 24/242 - loss 0.00754029 - time (sec): 1.50 - samples/sec: 1492.40 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 19:31:15,436 epoch 6 - iter 48/242 - loss 0.02913193 - time (sec): 2.98 - samples/sec: 1546.80 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 19:31:16,992 epoch 6 - iter 72/242 - loss 0.03202316 - time (sec): 4.53 - samples/sec: 1616.66 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 19:31:18,538 epoch 6 - iter 96/242 - loss 0.03013955 - time (sec): 6.08 - samples/sec: 1599.96 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 19:31:20,088 epoch 6 - iter 120/242 - loss 0.03080415 - time (sec): 7.63 - samples/sec: 1645.91 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 19:31:21,638 epoch 6 - iter 144/242 - loss 0.03003144 - time (sec): 9.18 - samples/sec: 1655.31 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 19:31:23,126 epoch 6 - iter 168/242 - loss 0.03283920 - time (sec): 10.67 - samples/sec: 1630.94 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 19:31:24,642 epoch 6 - iter 192/242 - loss 0.03395577 - time (sec): 12.18 - samples/sec: 1627.18 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 19:31:26,111 epoch 6 - iter 216/242 - loss 0.03345099 - time (sec): 13.65 - samples/sec: 1613.56 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 19:31:27,662 epoch 6 - iter 240/242 - loss 0.03181677 - time (sec): 15.20 - samples/sec: 1615.60 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 19:31:27,785 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:31:27,786 EPOCH 6 done: loss 0.0322 - lr: 0.000013 | |
| 2023-10-23 19:31:28,484 DEV : loss 0.1637829840183258 - f1-score (micro avg) 0.8688 | |
| 2023-10-23 19:31:28,488 saving best model | |
| 2023-10-23 19:31:29,085 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:31:30,628 epoch 7 - iter 24/242 - loss 0.01992873 - time (sec): 1.54 - samples/sec: 1671.67 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 19:31:32,109 epoch 7 - iter 48/242 - loss 0.01958366 - time (sec): 3.02 - samples/sec: 1562.88 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 19:31:33,628 epoch 7 - iter 72/242 - loss 0.02160298 - time (sec): 4.54 - samples/sec: 1544.62 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 19:31:35,152 epoch 7 - iter 96/242 - loss 0.03093927 - time (sec): 6.07 - samples/sec: 1567.90 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 19:31:36,645 epoch 7 - iter 120/242 - loss 0.02876334 - time (sec): 7.56 - samples/sec: 1534.47 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 19:31:38,197 epoch 7 - iter 144/242 - loss 0.02510561 - time (sec): 9.11 - samples/sec: 1585.38 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 19:31:39,738 epoch 7 - iter 168/242 - loss 0.02481182 - time (sec): 10.65 - samples/sec: 1606.81 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 19:31:41,220 epoch 7 - iter 192/242 - loss 0.02407380 - time (sec): 12.13 - samples/sec: 1599.71 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 19:31:42,729 epoch 7 - iter 216/242 - loss 0.02445811 - time (sec): 13.64 - samples/sec: 1601.31 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 19:31:44,297 epoch 7 - iter 240/242 - loss 0.02432614 - time (sec): 15.21 - samples/sec: 1611.23 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 19:31:44,421 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:31:44,422 EPOCH 7 done: loss 0.0241 - lr: 0.000010 | |
| 2023-10-23 19:31:45,119 DEV : loss 0.17772217094898224 - f1-score (micro avg) 0.86 | |
| 2023-10-23 19:31:45,122 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:31:46,627 epoch 8 - iter 24/242 - loss 0.03288147 - time (sec): 1.50 - samples/sec: 1679.19 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 19:31:48,138 epoch 8 - iter 48/242 - loss 0.01853878 - time (sec): 3.01 - samples/sec: 1642.54 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 19:31:49,644 epoch 8 - iter 72/242 - loss 0.01634984 - time (sec): 4.52 - samples/sec: 1632.94 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 19:31:51,166 epoch 8 - iter 96/242 - loss 0.01817815 - time (sec): 6.04 - samples/sec: 1617.32 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 19:31:52,747 epoch 8 - iter 120/242 - loss 0.02189944 - time (sec): 7.62 - samples/sec: 1621.72 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 19:31:54,346 epoch 8 - iter 144/242 - loss 0.01859034 - time (sec): 9.22 - samples/sec: 1630.24 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 19:31:55,804 epoch 8 - iter 168/242 - loss 0.02102774 - time (sec): 10.68 - samples/sec: 1616.58 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 19:31:57,342 epoch 8 - iter 192/242 - loss 0.01985651 - time (sec): 12.22 - samples/sec: 1609.44 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 19:31:58,848 epoch 8 - iter 216/242 - loss 0.01865202 - time (sec): 13.73 - samples/sec: 1609.88 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 19:32:00,386 epoch 8 - iter 240/242 - loss 0.01800372 - time (sec): 15.26 - samples/sec: 1606.30 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 19:32:00,506 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:32:00,507 EPOCH 8 done: loss 0.0178 - lr: 0.000007 | |
| 2023-10-23 19:32:01,209 DEV : loss 0.194981187582016 - f1-score (micro avg) 0.8373 | |
| 2023-10-23 19:32:01,213 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:32:02,754 epoch 9 - iter 24/242 - loss 0.02859587 - time (sec): 1.54 - samples/sec: 1628.93 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 19:32:04,317 epoch 9 - iter 48/242 - loss 0.02766799 - time (sec): 3.10 - samples/sec: 1579.06 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 19:32:05,850 epoch 9 - iter 72/242 - loss 0.02277408 - time (sec): 4.64 - samples/sec: 1589.03 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 19:32:07,389 epoch 9 - iter 96/242 - loss 0.01930538 - time (sec): 6.18 - samples/sec: 1617.33 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 19:32:08,917 epoch 9 - iter 120/242 - loss 0.01681611 - time (sec): 7.70 - samples/sec: 1623.29 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 19:32:10,404 epoch 9 - iter 144/242 - loss 0.01500288 - time (sec): 9.19 - samples/sec: 1618.61 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 19:32:11,935 epoch 9 - iter 168/242 - loss 0.01351396 - time (sec): 10.72 - samples/sec: 1600.59 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 19:32:13,428 epoch 9 - iter 192/242 - loss 0.01220532 - time (sec): 12.21 - samples/sec: 1592.90 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 19:32:14,944 epoch 9 - iter 216/242 - loss 0.01149296 - time (sec): 13.73 - samples/sec: 1606.89 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 19:32:16,481 epoch 9 - iter 240/242 - loss 0.01091838 - time (sec): 15.27 - samples/sec: 1613.65 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 19:32:16,595 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:32:16,596 EPOCH 9 done: loss 0.0109 - lr: 0.000003 | |
| 2023-10-23 19:32:17,294 DEV : loss 0.1826126128435135 - f1-score (micro avg) 0.8607 | |
| 2023-10-23 19:32:17,298 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:32:18,855 epoch 10 - iter 24/242 - loss 0.01137724 - time (sec): 1.56 - samples/sec: 1703.46 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 19:32:20,347 epoch 10 - iter 48/242 - loss 0.00797534 - time (sec): 3.05 - samples/sec: 1654.01 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 19:32:21,927 epoch 10 - iter 72/242 - loss 0.00713636 - time (sec): 4.63 - samples/sec: 1662.10 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 19:32:23,402 epoch 10 - iter 96/242 - loss 0.00601590 - time (sec): 6.10 - samples/sec: 1594.00 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 19:32:24,907 epoch 10 - iter 120/242 - loss 0.00677766 - time (sec): 7.61 - samples/sec: 1612.58 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 19:32:26,407 epoch 10 - iter 144/242 - loss 0.00631534 - time (sec): 9.11 - samples/sec: 1625.46 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 19:32:27,926 epoch 10 - iter 168/242 - loss 0.00589143 - time (sec): 10.63 - samples/sec: 1622.92 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 19:32:29,420 epoch 10 - iter 192/242 - loss 0.00766039 - time (sec): 12.12 - samples/sec: 1617.90 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 19:32:31,004 epoch 10 - iter 216/242 - loss 0.00876882 - time (sec): 13.71 - samples/sec: 1621.94 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 19:32:32,544 epoch 10 - iter 240/242 - loss 0.00939067 - time (sec): 15.25 - samples/sec: 1610.64 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 19:32:32,664 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:32:32,665 EPOCH 10 done: loss 0.0093 - lr: 0.000000 | |
| 2023-10-23 19:32:33,365 DEV : loss 0.18982915580272675 - f1-score (micro avg) 0.8546 | |
| 2023-10-23 19:32:33,839 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:32:33,840 Loading model from best epoch ... | |
| 2023-10-23 19:32:35,389 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 19:32:36,253 | |
| Results: | |
| - F-score (micro) 0.8154 | |
| - F-score (macro) 0.5535 | |
| - Accuracy 0.7064 | |
| By class: | |
| precision recall f1-score support | |
| pers 0.8777 0.8777 0.8777 139 | |
| scope 0.8421 0.8682 0.8550 129 | |
| work 0.6593 0.7500 0.7018 80 | |
| loc 0.6667 0.2222 0.3333 9 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.8087 0.8222 0.8154 360 | |
| macro avg 0.6092 0.5436 0.5535 360 | |
| weighted avg 0.8038 0.8222 0.8095 360 | |
| 2023-10-23 19:32:36,253 ---------------------------------------------------------------------------------------------------- | |