| 2023-10-24 17:53:07,606 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:53:07,607 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() | |
| )" | |
| 2023-10-24 17:53:07,607 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:53:07,607 MultiCorpus: 7936 train + 992 dev + 992 test sentences | |
| - NER_ICDAR_EUROPEANA Corpus: 7936 train + 992 dev + 992 test sentences - /home/ubuntu/.flair/datasets/ner_icdar_europeana/fr | |
| 2023-10-24 17:53:07,607 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:53:07,607 Train: 7936 sentences | |
| 2023-10-24 17:53:07,607 (train_with_dev=False, train_with_test=False) | |
| 2023-10-24 17:53:07,607 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:53:07,607 Training Params: | |
| 2023-10-24 17:53:07,607 - learning_rate: "5e-05" | |
| 2023-10-24 17:53:07,607 - mini_batch_size: "8" | |
| 2023-10-24 17:53:07,607 - max_epochs: "10" | |
| 2023-10-24 17:53:07,607 - shuffle: "True" | |
| 2023-10-24 17:53:07,607 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:53:07,607 Plugins: | |
| 2023-10-24 17:53:07,607 - TensorboardLogger | |
| 2023-10-24 17:53:07,607 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-24 17:53:07,607 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:53:07,607 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-24 17:53:07,608 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-24 17:53:07,608 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:53:07,608 Computation: | |
| 2023-10-24 17:53:07,608 - compute on device: cuda:0 | |
| 2023-10-24 17:53:07,608 - embedding storage: none | |
| 2023-10-24 17:53:07,608 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:53:07,608 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-24 17:53:07,608 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:53:07,608 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:53:07,608 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-24 17:53:16,110 epoch 1 - iter 99/992 - loss 1.45019353 - time (sec): 8.50 - samples/sec: 2052.11 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-24 17:53:24,479 epoch 1 - iter 198/992 - loss 0.90651188 - time (sec): 16.87 - samples/sec: 1995.74 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-24 17:53:32,526 epoch 1 - iter 297/992 - loss 0.68242155 - time (sec): 24.92 - samples/sec: 1970.50 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-24 17:53:40,903 epoch 1 - iter 396/992 - loss 0.55232472 - time (sec): 33.29 - samples/sec: 1971.25 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-24 17:53:49,010 epoch 1 - iter 495/992 - loss 0.47511537 - time (sec): 41.40 - samples/sec: 1964.36 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-24 17:53:57,155 epoch 1 - iter 594/992 - loss 0.42026811 - time (sec): 49.55 - samples/sec: 1960.16 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-24 17:54:05,777 epoch 1 - iter 693/992 - loss 0.37516782 - time (sec): 58.17 - samples/sec: 1957.77 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-24 17:54:14,242 epoch 1 - iter 792/992 - loss 0.34277188 - time (sec): 66.63 - samples/sec: 1955.19 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-24 17:54:22,644 epoch 1 - iter 891/992 - loss 0.32033942 - time (sec): 75.04 - samples/sec: 1963.07 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-24 17:54:31,054 epoch 1 - iter 990/992 - loss 0.30228680 - time (sec): 83.45 - samples/sec: 1960.73 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-24 17:54:31,234 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:54:31,235 EPOCH 1 done: loss 0.3019 - lr: 0.000050 | |
| 2023-10-24 17:54:34,306 DEV : loss 0.08691307157278061 - f1-score (micro avg) 0.7201 | |
| 2023-10-24 17:54:34,321 saving best model | |
| 2023-10-24 17:54:34,791 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:54:42,930 epoch 2 - iter 99/992 - loss 0.09527419 - time (sec): 8.14 - samples/sec: 2003.53 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-24 17:54:51,239 epoch 2 - iter 198/992 - loss 0.09556154 - time (sec): 16.45 - samples/sec: 1975.24 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-24 17:54:59,412 epoch 2 - iter 297/992 - loss 0.09905757 - time (sec): 24.62 - samples/sec: 1984.65 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-24 17:55:07,962 epoch 2 - iter 396/992 - loss 0.10241445 - time (sec): 33.17 - samples/sec: 1977.76 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-24 17:55:16,323 epoch 2 - iter 495/992 - loss 0.10157096 - time (sec): 41.53 - samples/sec: 1984.19 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-24 17:55:24,569 epoch 2 - iter 594/992 - loss 0.10195348 - time (sec): 49.78 - samples/sec: 1983.29 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-24 17:55:33,030 epoch 2 - iter 693/992 - loss 0.10065037 - time (sec): 58.24 - samples/sec: 1983.87 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-24 17:55:41,369 epoch 2 - iter 792/992 - loss 0.09922714 - time (sec): 66.58 - samples/sec: 1970.91 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-24 17:55:49,709 epoch 2 - iter 891/992 - loss 0.09994013 - time (sec): 74.92 - samples/sec: 1964.70 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-24 17:55:58,196 epoch 2 - iter 990/992 - loss 0.10114388 - time (sec): 83.40 - samples/sec: 1963.04 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-24 17:55:58,341 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:55:58,341 EPOCH 2 done: loss 0.1011 - lr: 0.000044 | |
| 2023-10-24 17:56:01,444 DEV : loss 0.09098362177610397 - f1-score (micro avg) 0.743 | |
| 2023-10-24 17:56:01,459 saving best model | |
| 2023-10-24 17:56:02,049 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:56:10,259 epoch 3 - iter 99/992 - loss 0.06165896 - time (sec): 8.21 - samples/sec: 1971.22 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-24 17:56:18,758 epoch 3 - iter 198/992 - loss 0.06593462 - time (sec): 16.71 - samples/sec: 1971.74 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-24 17:56:27,234 epoch 3 - iter 297/992 - loss 0.07089123 - time (sec): 25.18 - samples/sec: 1940.51 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-24 17:56:35,331 epoch 3 - iter 396/992 - loss 0.06905276 - time (sec): 33.28 - samples/sec: 1946.67 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-24 17:56:44,066 epoch 3 - iter 495/992 - loss 0.06665018 - time (sec): 42.02 - samples/sec: 1961.30 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-24 17:56:52,473 epoch 3 - iter 594/992 - loss 0.06883315 - time (sec): 50.42 - samples/sec: 1959.12 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-24 17:57:00,614 epoch 3 - iter 693/992 - loss 0.06972989 - time (sec): 58.56 - samples/sec: 1959.41 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-24 17:57:09,003 epoch 3 - iter 792/992 - loss 0.06920701 - time (sec): 66.95 - samples/sec: 1961.79 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-24 17:57:17,427 epoch 3 - iter 891/992 - loss 0.06875715 - time (sec): 75.38 - samples/sec: 1961.18 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-24 17:57:25,554 epoch 3 - iter 990/992 - loss 0.06866266 - time (sec): 83.50 - samples/sec: 1960.90 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-24 17:57:25,711 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:57:25,711 EPOCH 3 done: loss 0.0686 - lr: 0.000039 | |
| 2023-10-24 17:57:28,825 DEV : loss 0.10797995328903198 - f1-score (micro avg) 0.7225 | |
| 2023-10-24 17:57:28,840 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:57:36,940 epoch 4 - iter 99/992 - loss 0.04262884 - time (sec): 8.10 - samples/sec: 1951.86 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-24 17:57:45,681 epoch 4 - iter 198/992 - loss 0.04995344 - time (sec): 16.84 - samples/sec: 1947.00 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-24 17:57:54,126 epoch 4 - iter 297/992 - loss 0.04925014 - time (sec): 25.28 - samples/sec: 1947.25 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-24 17:58:02,267 epoch 4 - iter 396/992 - loss 0.05068279 - time (sec): 33.43 - samples/sec: 1948.76 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-24 17:58:10,475 epoch 4 - iter 495/992 - loss 0.05043456 - time (sec): 41.63 - samples/sec: 1960.24 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-24 17:58:18,115 epoch 4 - iter 594/992 - loss 0.04948632 - time (sec): 49.27 - samples/sec: 1955.28 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-24 17:58:26,645 epoch 4 - iter 693/992 - loss 0.05029241 - time (sec): 57.80 - samples/sec: 1963.09 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-24 17:58:35,036 epoch 4 - iter 792/992 - loss 0.05054238 - time (sec): 66.19 - samples/sec: 1959.75 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-24 17:58:43,142 epoch 4 - iter 891/992 - loss 0.04973429 - time (sec): 74.30 - samples/sec: 1968.56 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-24 17:58:52,072 epoch 4 - iter 990/992 - loss 0.04918421 - time (sec): 83.23 - samples/sec: 1966.28 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-24 17:58:52,222 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:58:52,222 EPOCH 4 done: loss 0.0491 - lr: 0.000033 | |
| 2023-10-24 17:58:55,339 DEV : loss 0.16018341481685638 - f1-score (micro avg) 0.7368 | |
| 2023-10-24 17:58:55,354 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 17:59:03,855 epoch 5 - iter 99/992 - loss 0.03275354 - time (sec): 8.50 - samples/sec: 1998.54 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-24 17:59:12,128 epoch 5 - iter 198/992 - loss 0.03475824 - time (sec): 16.77 - samples/sec: 1968.33 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-24 17:59:20,968 epoch 5 - iter 297/992 - loss 0.03421394 - time (sec): 25.61 - samples/sec: 1935.93 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-24 17:59:29,192 epoch 5 - iter 396/992 - loss 0.03443327 - time (sec): 33.84 - samples/sec: 1928.20 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-24 17:59:37,436 epoch 5 - iter 495/992 - loss 0.03822480 - time (sec): 42.08 - samples/sec: 1946.88 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-24 17:59:45,453 epoch 5 - iter 594/992 - loss 0.03666575 - time (sec): 50.10 - samples/sec: 1952.70 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-24 17:59:54,159 epoch 5 - iter 693/992 - loss 0.03753706 - time (sec): 58.80 - samples/sec: 1951.41 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-24 18:00:02,511 epoch 5 - iter 792/992 - loss 0.03848741 - time (sec): 67.16 - samples/sec: 1952.21 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-24 18:00:10,602 epoch 5 - iter 891/992 - loss 0.03850444 - time (sec): 75.25 - samples/sec: 1953.08 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-24 18:00:19,094 epoch 5 - iter 990/992 - loss 0.03746891 - time (sec): 83.74 - samples/sec: 1954.15 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-24 18:00:19,260 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 18:00:19,260 EPOCH 5 done: loss 0.0374 - lr: 0.000028 | |
| 2023-10-24 18:00:22,383 DEV : loss 0.17979347705841064 - f1-score (micro avg) 0.7377 | |
| 2023-10-24 18:00:22,399 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 18:00:30,989 epoch 6 - iter 99/992 - loss 0.02323895 - time (sec): 8.59 - samples/sec: 1890.29 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-24 18:00:39,421 epoch 6 - iter 198/992 - loss 0.02299469 - time (sec): 17.02 - samples/sec: 1940.04 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-24 18:00:47,699 epoch 6 - iter 297/992 - loss 0.02440000 - time (sec): 25.30 - samples/sec: 1959.56 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-24 18:00:55,811 epoch 6 - iter 396/992 - loss 0.02517086 - time (sec): 33.41 - samples/sec: 1970.95 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-24 18:01:04,347 epoch 6 - iter 495/992 - loss 0.02699649 - time (sec): 41.95 - samples/sec: 1970.74 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-24 18:01:12,638 epoch 6 - iter 594/992 - loss 0.02691355 - time (sec): 50.24 - samples/sec: 1963.22 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-24 18:01:20,840 epoch 6 - iter 693/992 - loss 0.02767072 - time (sec): 58.44 - samples/sec: 1957.76 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-24 18:01:29,206 epoch 6 - iter 792/992 - loss 0.02671390 - time (sec): 66.81 - samples/sec: 1956.90 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-24 18:01:37,458 epoch 6 - iter 891/992 - loss 0.02828160 - time (sec): 75.06 - samples/sec: 1948.57 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-24 18:01:45,697 epoch 6 - iter 990/992 - loss 0.02810958 - time (sec): 83.30 - samples/sec: 1965.05 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-24 18:01:45,857 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 18:01:45,857 EPOCH 6 done: loss 0.0281 - lr: 0.000022 | |
| 2023-10-24 18:01:48,981 DEV : loss 0.18152180314064026 - f1-score (micro avg) 0.7691 | |
| 2023-10-24 18:01:48,996 saving best model | |
| 2023-10-24 18:01:49,629 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 18:01:58,369 epoch 7 - iter 99/992 - loss 0.02452345 - time (sec): 8.74 - samples/sec: 1920.30 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-24 18:02:06,462 epoch 7 - iter 198/992 - loss 0.02583170 - time (sec): 16.83 - samples/sec: 1928.62 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-24 18:02:15,105 epoch 7 - iter 297/992 - loss 0.02293195 - time (sec): 25.48 - samples/sec: 1913.00 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-24 18:02:23,523 epoch 7 - iter 396/992 - loss 0.01981722 - time (sec): 33.89 - samples/sec: 1901.12 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-24 18:02:31,697 epoch 7 - iter 495/992 - loss 0.01985616 - time (sec): 42.07 - samples/sec: 1910.50 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-24 18:02:40,392 epoch 7 - iter 594/992 - loss 0.01977100 - time (sec): 50.76 - samples/sec: 1926.84 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-24 18:02:48,921 epoch 7 - iter 693/992 - loss 0.02041123 - time (sec): 59.29 - samples/sec: 1935.23 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-24 18:02:57,131 epoch 7 - iter 792/992 - loss 0.02070652 - time (sec): 67.50 - samples/sec: 1941.00 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-24 18:03:05,223 epoch 7 - iter 891/992 - loss 0.02081829 - time (sec): 75.59 - samples/sec: 1949.40 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-24 18:03:13,362 epoch 7 - iter 990/992 - loss 0.02144692 - time (sec): 83.73 - samples/sec: 1952.78 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-24 18:03:13,536 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 18:03:13,536 EPOCH 7 done: loss 0.0214 - lr: 0.000017 | |
| 2023-10-24 18:03:16,649 DEV : loss 0.18771061301231384 - f1-score (micro avg) 0.7667 | |
| 2023-10-24 18:03:16,664 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 18:03:25,249 epoch 8 - iter 99/992 - loss 0.01897961 - time (sec): 8.58 - samples/sec: 2021.42 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-24 18:03:33,938 epoch 8 - iter 198/992 - loss 0.01571900 - time (sec): 17.27 - samples/sec: 1977.75 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-24 18:03:42,080 epoch 8 - iter 297/992 - loss 0.01464608 - time (sec): 25.41 - samples/sec: 1955.74 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-24 18:03:50,487 epoch 8 - iter 396/992 - loss 0.01451842 - time (sec): 33.82 - samples/sec: 1945.87 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-24 18:03:58,546 epoch 8 - iter 495/992 - loss 0.01464158 - time (sec): 41.88 - samples/sec: 1950.62 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-24 18:04:07,019 epoch 8 - iter 594/992 - loss 0.01494271 - time (sec): 50.35 - samples/sec: 1962.71 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-24 18:04:15,324 epoch 8 - iter 693/992 - loss 0.01427937 - time (sec): 58.66 - samples/sec: 1965.49 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-24 18:04:23,141 epoch 8 - iter 792/992 - loss 0.01444238 - time (sec): 66.48 - samples/sec: 1961.96 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-24 18:04:31,590 epoch 8 - iter 891/992 - loss 0.01470428 - time (sec): 74.93 - samples/sec: 1960.87 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-24 18:04:39,955 epoch 8 - iter 990/992 - loss 0.01468421 - time (sec): 83.29 - samples/sec: 1964.56 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-24 18:04:40,104 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 18:04:40,104 EPOCH 8 done: loss 0.0147 - lr: 0.000011 | |
| 2023-10-24 18:04:43,222 DEV : loss 0.2224731296300888 - f1-score (micro avg) 0.7444 | |
| 2023-10-24 18:04:43,237 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 18:04:51,724 epoch 9 - iter 99/992 - loss 0.01508641 - time (sec): 8.49 - samples/sec: 1869.36 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-24 18:04:59,936 epoch 9 - iter 198/992 - loss 0.01126348 - time (sec): 16.70 - samples/sec: 1893.49 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-24 18:05:08,057 epoch 9 - iter 297/992 - loss 0.01011817 - time (sec): 24.82 - samples/sec: 1903.84 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-24 18:05:17,194 epoch 9 - iter 396/992 - loss 0.01014998 - time (sec): 33.96 - samples/sec: 1904.20 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-24 18:05:25,870 epoch 9 - iter 495/992 - loss 0.00901112 - time (sec): 42.63 - samples/sec: 1918.22 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-24 18:05:34,447 epoch 9 - iter 594/992 - loss 0.00957614 - time (sec): 51.21 - samples/sec: 1921.71 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-24 18:05:42,470 epoch 9 - iter 693/992 - loss 0.00985237 - time (sec): 59.23 - samples/sec: 1932.18 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-24 18:05:50,719 epoch 9 - iter 792/992 - loss 0.00966421 - time (sec): 67.48 - samples/sec: 1935.77 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-24 18:05:58,741 epoch 9 - iter 891/992 - loss 0.00952795 - time (sec): 75.50 - samples/sec: 1944.93 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-24 18:06:06,945 epoch 9 - iter 990/992 - loss 0.00951350 - time (sec): 83.71 - samples/sec: 1955.66 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-24 18:06:07,091 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 18:06:07,092 EPOCH 9 done: loss 0.0095 - lr: 0.000006 | |
| 2023-10-24 18:06:10,221 DEV : loss 0.2356439083814621 - f1-score (micro avg) 0.7551 | |
| 2023-10-24 18:06:10,236 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 18:06:18,255 epoch 10 - iter 99/992 - loss 0.00471428 - time (sec): 8.02 - samples/sec: 2021.65 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-24 18:06:26,499 epoch 10 - iter 198/992 - loss 0.00492676 - time (sec): 16.26 - samples/sec: 1988.79 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-24 18:06:34,960 epoch 10 - iter 297/992 - loss 0.00537611 - time (sec): 24.72 - samples/sec: 1985.92 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-24 18:06:43,429 epoch 10 - iter 396/992 - loss 0.00591290 - time (sec): 33.19 - samples/sec: 1993.67 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-24 18:06:51,659 epoch 10 - iter 495/992 - loss 0.00619826 - time (sec): 41.42 - samples/sec: 1987.82 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-24 18:07:00,038 epoch 10 - iter 594/992 - loss 0.00579102 - time (sec): 49.80 - samples/sec: 1972.80 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-24 18:07:08,440 epoch 10 - iter 693/992 - loss 0.00584032 - time (sec): 58.20 - samples/sec: 1968.97 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-24 18:07:16,506 epoch 10 - iter 792/992 - loss 0.00552839 - time (sec): 66.27 - samples/sec: 1964.77 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-24 18:07:25,019 epoch 10 - iter 891/992 - loss 0.00572974 - time (sec): 74.78 - samples/sec: 1962.97 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-24 18:07:33,501 epoch 10 - iter 990/992 - loss 0.00560021 - time (sec): 83.26 - samples/sec: 1965.24 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-24 18:07:33,670 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 18:07:33,671 EPOCH 10 done: loss 0.0056 - lr: 0.000000 | |
| 2023-10-24 18:07:36,792 DEV : loss 0.24207349121570587 - f1-score (micro avg) 0.7541 | |
| 2023-10-24 18:07:37,277 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-24 18:07:37,277 Loading model from best epoch ... | |
| 2023-10-24 18:07:39,090 SequenceTagger predicts: Dictionary with 13 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG | |
| 2023-10-24 18:07:41,834 | |
| Results: | |
| - F-score (micro) 0.7721 | |
| - F-score (macro) 0.6822 | |
| - Accuracy 0.6487 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.8067 0.8473 0.8265 655 | |
| PER 0.6980 0.7982 0.7448 223 | |
| ORG 0.6400 0.3780 0.4752 127 | |
| micro avg 0.7672 0.7771 0.7721 1005 | |
| macro avg 0.7149 0.6745 0.6822 1005 | |
| weighted avg 0.7615 0.7771 0.7640 1005 | |
| 2023-10-24 18:07:41,834 ---------------------------------------------------------------------------------------------------- | |