| 2023-10-23 20:26:31,123 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:26:31,124 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=21, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-23 20:26:31,124 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:26:31,124 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences | |
| - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator | |
| 2023-10-23 20:26:31,124 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:26:31,124 Train: 3575 sentences | |
| 2023-10-23 20:26:31,124 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 20:26:31,124 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:26:31,124 Training Params: | |
| 2023-10-23 20:26:31,124 - learning_rate: "3e-05" | |
| 2023-10-23 20:26:31,124 - mini_batch_size: "8" | |
| 2023-10-23 20:26:31,124 - max_epochs: "10" | |
| 2023-10-23 20:26:31,124 - shuffle: "True" | |
| 2023-10-23 20:26:31,124 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:26:31,125 Plugins: | |
| 2023-10-23 20:26:31,125 - TensorboardLogger | |
| 2023-10-23 20:26:31,125 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 20:26:31,125 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:26:31,125 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 20:26:31,125 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 20:26:31,125 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:26:31,125 Computation: | |
| 2023-10-23 20:26:31,125 - compute on device: cuda:0 | |
| 2023-10-23 20:26:31,125 - embedding storage: none | |
| 2023-10-23 20:26:31,125 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:26:31,125 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-23 20:26:31,125 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:26:31,125 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:26:31,125 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 20:26:35,069 epoch 1 - iter 44/447 - loss 3.40559275 - time (sec): 3.94 - samples/sec: 2157.26 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 20:26:38,774 epoch 1 - iter 88/447 - loss 2.27066127 - time (sec): 7.65 - samples/sec: 2138.15 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 20:26:42,689 epoch 1 - iter 132/447 - loss 1.64802661 - time (sec): 11.56 - samples/sec: 2165.17 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 20:26:46,722 epoch 1 - iter 176/447 - loss 1.32711622 - time (sec): 15.60 - samples/sec: 2129.40 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 20:26:50,516 epoch 1 - iter 220/447 - loss 1.13112757 - time (sec): 19.39 - samples/sec: 2148.76 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 20:26:54,391 epoch 1 - iter 264/447 - loss 0.98605246 - time (sec): 23.27 - samples/sec: 2138.84 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 20:26:58,431 epoch 1 - iter 308/447 - loss 0.87774702 - time (sec): 27.31 - samples/sec: 2133.43 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 20:27:02,860 epoch 1 - iter 352/447 - loss 0.79068129 - time (sec): 31.73 - samples/sec: 2140.14 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 20:27:06,854 epoch 1 - iter 396/447 - loss 0.72548100 - time (sec): 35.73 - samples/sec: 2149.02 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 20:27:10,849 epoch 1 - iter 440/447 - loss 0.67813581 - time (sec): 39.72 - samples/sec: 2149.35 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 20:27:11,419 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:27:11,420 EPOCH 1 done: loss 0.6706 - lr: 0.000029 | |
| 2023-10-23 20:27:16,228 DEV : loss 0.1458185613155365 - f1-score (micro avg) 0.6581 | |
| 2023-10-23 20:27:16,248 saving best model | |
| 2023-10-23 20:27:16,801 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:27:21,278 epoch 2 - iter 44/447 - loss 0.17898902 - time (sec): 4.48 - samples/sec: 2130.94 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 20:27:25,147 epoch 2 - iter 88/447 - loss 0.16047620 - time (sec): 8.34 - samples/sec: 2134.89 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 20:27:29,240 epoch 2 - iter 132/447 - loss 0.15610822 - time (sec): 12.44 - samples/sec: 2100.29 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 20:27:33,013 epoch 2 - iter 176/447 - loss 0.15494224 - time (sec): 16.21 - samples/sec: 2123.66 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 20:27:36,858 epoch 2 - iter 220/447 - loss 0.15138265 - time (sec): 20.06 - samples/sec: 2114.73 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 20:27:40,890 epoch 2 - iter 264/447 - loss 0.15125402 - time (sec): 24.09 - samples/sec: 2123.99 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 20:27:44,988 epoch 2 - iter 308/447 - loss 0.14586521 - time (sec): 28.19 - samples/sec: 2130.87 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 20:27:49,182 epoch 2 - iter 352/447 - loss 0.14365652 - time (sec): 32.38 - samples/sec: 2125.78 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 20:27:53,057 epoch 2 - iter 396/447 - loss 0.14023517 - time (sec): 36.25 - samples/sec: 2119.73 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 20:27:56,855 epoch 2 - iter 440/447 - loss 0.13550428 - time (sec): 40.05 - samples/sec: 2126.38 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 20:27:57,477 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:27:57,477 EPOCH 2 done: loss 0.1349 - lr: 0.000027 | |
| 2023-10-23 20:28:03,938 DEV : loss 0.12103226780891418 - f1-score (micro avg) 0.7163 | |
| 2023-10-23 20:28:03,958 saving best model | |
| 2023-10-23 20:28:04,777 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:28:08,610 epoch 3 - iter 44/447 - loss 0.07460696 - time (sec): 3.83 - samples/sec: 2099.40 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 20:28:12,723 epoch 3 - iter 88/447 - loss 0.06922936 - time (sec): 7.94 - samples/sec: 2150.34 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 20:28:16,744 epoch 3 - iter 132/447 - loss 0.06704794 - time (sec): 11.97 - samples/sec: 2105.48 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 20:28:20,633 epoch 3 - iter 176/447 - loss 0.07184773 - time (sec): 15.86 - samples/sec: 2121.83 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 20:28:24,327 epoch 3 - iter 220/447 - loss 0.07620919 - time (sec): 19.55 - samples/sec: 2112.93 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 20:28:28,243 epoch 3 - iter 264/447 - loss 0.07384269 - time (sec): 23.46 - samples/sec: 2133.46 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 20:28:32,208 epoch 3 - iter 308/447 - loss 0.07454931 - time (sec): 27.43 - samples/sec: 2134.92 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 20:28:36,018 epoch 3 - iter 352/447 - loss 0.07264295 - time (sec): 31.24 - samples/sec: 2132.00 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 20:28:40,250 epoch 3 - iter 396/447 - loss 0.07353915 - time (sec): 35.47 - samples/sec: 2126.24 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 20:28:44,114 epoch 3 - iter 440/447 - loss 0.07338628 - time (sec): 39.34 - samples/sec: 2139.02 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 20:28:45,093 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:28:45,093 EPOCH 3 done: loss 0.0736 - lr: 0.000023 | |
| 2023-10-23 20:28:51,584 DEV : loss 0.1441224366426468 - f1-score (micro avg) 0.7494 | |
| 2023-10-23 20:28:51,604 saving best model | |
| 2023-10-23 20:28:52,282 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:28:56,486 epoch 4 - iter 44/447 - loss 0.05528108 - time (sec): 4.20 - samples/sec: 2143.25 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 20:29:00,275 epoch 4 - iter 88/447 - loss 0.04748136 - time (sec): 7.99 - samples/sec: 2162.51 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 20:29:04,126 epoch 4 - iter 132/447 - loss 0.04748733 - time (sec): 11.84 - samples/sec: 2157.90 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 20:29:07,812 epoch 4 - iter 176/447 - loss 0.04536813 - time (sec): 15.53 - samples/sec: 2159.73 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 20:29:12,061 epoch 4 - iter 220/447 - loss 0.04421550 - time (sec): 19.78 - samples/sec: 2153.18 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 20:29:15,847 epoch 4 - iter 264/447 - loss 0.04719171 - time (sec): 23.56 - samples/sec: 2133.66 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 20:29:19,658 epoch 4 - iter 308/447 - loss 0.04624824 - time (sec): 27.37 - samples/sec: 2138.24 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 20:29:23,597 epoch 4 - iter 352/447 - loss 0.04553819 - time (sec): 31.31 - samples/sec: 2133.66 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 20:29:28,135 epoch 4 - iter 396/447 - loss 0.04771921 - time (sec): 35.85 - samples/sec: 2130.52 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 20:29:32,088 epoch 4 - iter 440/447 - loss 0.04663221 - time (sec): 39.80 - samples/sec: 2138.66 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 20:29:32,771 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:29:32,771 EPOCH 4 done: loss 0.0463 - lr: 0.000020 | |
| 2023-10-23 20:29:39,240 DEV : loss 0.18340256810188293 - f1-score (micro avg) 0.7452 | |
| 2023-10-23 20:29:39,261 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:29:42,916 epoch 5 - iter 44/447 - loss 0.02363584 - time (sec): 3.65 - samples/sec: 2091.42 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 20:29:46,763 epoch 5 - iter 88/447 - loss 0.02708204 - time (sec): 7.50 - samples/sec: 2105.34 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 20:29:51,070 epoch 5 - iter 132/447 - loss 0.03019743 - time (sec): 11.81 - samples/sec: 2099.11 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 20:29:54,880 epoch 5 - iter 176/447 - loss 0.02987305 - time (sec): 15.62 - samples/sec: 2119.68 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 20:29:58,600 epoch 5 - iter 220/447 - loss 0.03110977 - time (sec): 19.34 - samples/sec: 2130.38 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 20:30:03,050 epoch 5 - iter 264/447 - loss 0.03146956 - time (sec): 23.79 - samples/sec: 2134.65 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 20:30:06,749 epoch 5 - iter 308/447 - loss 0.03134889 - time (sec): 27.49 - samples/sec: 2146.21 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 20:30:10,791 epoch 5 - iter 352/447 - loss 0.03066796 - time (sec): 31.53 - samples/sec: 2157.24 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 20:30:14,570 epoch 5 - iter 396/447 - loss 0.02912833 - time (sec): 35.31 - samples/sec: 2147.67 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 20:30:19,140 epoch 5 - iter 440/447 - loss 0.02919446 - time (sec): 39.88 - samples/sec: 2137.98 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 20:30:19,753 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:30:19,753 EPOCH 5 done: loss 0.0298 - lr: 0.000017 | |
| 2023-10-23 20:30:26,235 DEV : loss 0.18645448982715607 - f1-score (micro avg) 0.7792 | |
| 2023-10-23 20:30:26,255 saving best model | |
| 2023-10-23 20:30:27,018 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:30:30,775 epoch 6 - iter 44/447 - loss 0.01761254 - time (sec): 3.76 - samples/sec: 2202.78 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 20:30:34,641 epoch 6 - iter 88/447 - loss 0.01949947 - time (sec): 7.62 - samples/sec: 2184.21 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 20:30:39,203 epoch 6 - iter 132/447 - loss 0.01802132 - time (sec): 12.18 - samples/sec: 2166.88 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 20:30:43,540 epoch 6 - iter 176/447 - loss 0.01924059 - time (sec): 16.52 - samples/sec: 2136.18 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 20:30:47,667 epoch 6 - iter 220/447 - loss 0.01755935 - time (sec): 20.65 - samples/sec: 2133.50 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 20:30:51,710 epoch 6 - iter 264/447 - loss 0.01763127 - time (sec): 24.69 - samples/sec: 2136.95 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 20:30:55,340 epoch 6 - iter 308/447 - loss 0.01793616 - time (sec): 28.32 - samples/sec: 2125.68 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 20:30:59,084 epoch 6 - iter 352/447 - loss 0.02009423 - time (sec): 32.06 - samples/sec: 2133.18 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 20:31:03,014 epoch 6 - iter 396/447 - loss 0.02001702 - time (sec): 35.99 - samples/sec: 2130.93 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 20:31:06,935 epoch 6 - iter 440/447 - loss 0.01927894 - time (sec): 39.92 - samples/sec: 2138.15 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 20:31:07,561 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:31:07,561 EPOCH 6 done: loss 0.0193 - lr: 0.000013 | |
| 2023-10-23 20:31:14,030 DEV : loss 0.20568153262138367 - f1-score (micro avg) 0.773 | |
| 2023-10-23 20:31:14,050 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:31:18,387 epoch 7 - iter 44/447 - loss 0.01648589 - time (sec): 4.34 - samples/sec: 2168.11 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 20:31:22,525 epoch 7 - iter 88/447 - loss 0.01190539 - time (sec): 8.47 - samples/sec: 2107.89 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 20:31:26,739 epoch 7 - iter 132/447 - loss 0.01255698 - time (sec): 12.69 - samples/sec: 2130.35 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 20:31:30,553 epoch 7 - iter 176/447 - loss 0.01161302 - time (sec): 16.50 - samples/sec: 2123.07 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 20:31:34,386 epoch 7 - iter 220/447 - loss 0.01153263 - time (sec): 20.34 - samples/sec: 2113.34 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 20:31:38,216 epoch 7 - iter 264/447 - loss 0.01117656 - time (sec): 24.16 - samples/sec: 2124.89 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 20:31:42,456 epoch 7 - iter 308/447 - loss 0.01123172 - time (sec): 28.41 - samples/sec: 2127.68 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 20:31:46,184 epoch 7 - iter 352/447 - loss 0.01157591 - time (sec): 32.13 - samples/sec: 2146.42 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 20:31:50,167 epoch 7 - iter 396/447 - loss 0.01235896 - time (sec): 36.12 - samples/sec: 2129.42 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 20:31:54,022 epoch 7 - iter 440/447 - loss 0.01199197 - time (sec): 39.97 - samples/sec: 2140.09 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 20:31:54,542 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:31:54,543 EPOCH 7 done: loss 0.0119 - lr: 0.000010 | |
| 2023-10-23 20:32:01,006 DEV : loss 0.2467608004808426 - f1-score (micro avg) 0.7781 | |
| 2023-10-23 20:32:01,026 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:32:04,886 epoch 8 - iter 44/447 - loss 0.00812035 - time (sec): 3.86 - samples/sec: 2155.78 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 20:32:08,714 epoch 8 - iter 88/447 - loss 0.00675385 - time (sec): 7.69 - samples/sec: 2183.54 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 20:32:13,296 epoch 8 - iter 132/447 - loss 0.00807939 - time (sec): 12.27 - samples/sec: 2125.04 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 20:32:17,004 epoch 8 - iter 176/447 - loss 0.00904526 - time (sec): 15.98 - samples/sec: 2150.50 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 20:32:21,106 epoch 8 - iter 220/447 - loss 0.00833139 - time (sec): 20.08 - samples/sec: 2144.12 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 20:32:24,757 epoch 8 - iter 264/447 - loss 0.00759400 - time (sec): 23.73 - samples/sec: 2134.79 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 20:32:28,731 epoch 8 - iter 308/447 - loss 0.00798396 - time (sec): 27.70 - samples/sec: 2129.98 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 20:32:32,682 epoch 8 - iter 352/447 - loss 0.00793679 - time (sec): 31.65 - samples/sec: 2137.04 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 20:32:36,651 epoch 8 - iter 396/447 - loss 0.00768071 - time (sec): 35.62 - samples/sec: 2138.79 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 20:32:40,934 epoch 8 - iter 440/447 - loss 0.00822976 - time (sec): 39.91 - samples/sec: 2135.70 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 20:32:41,549 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:32:41,549 EPOCH 8 done: loss 0.0082 - lr: 0.000007 | |
| 2023-10-23 20:32:48,045 DEV : loss 0.2412562370300293 - f1-score (micro avg) 0.7825 | |
| 2023-10-23 20:32:48,065 saving best model | |
| 2023-10-23 20:32:48,761 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:32:52,934 epoch 9 - iter 44/447 - loss 0.00453444 - time (sec): 4.17 - samples/sec: 2140.52 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 20:32:57,201 epoch 9 - iter 88/447 - loss 0.00439378 - time (sec): 8.44 - samples/sec: 2135.90 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 20:33:01,259 epoch 9 - iter 132/447 - loss 0.00408738 - time (sec): 12.50 - samples/sec: 2109.13 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 20:33:04,933 epoch 9 - iter 176/447 - loss 0.00432207 - time (sec): 16.17 - samples/sec: 2090.21 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 20:33:08,650 epoch 9 - iter 220/447 - loss 0.00390841 - time (sec): 19.89 - samples/sec: 2097.07 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 20:33:12,736 epoch 9 - iter 264/447 - loss 0.00480594 - time (sec): 23.97 - samples/sec: 2102.34 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 20:33:16,421 epoch 9 - iter 308/447 - loss 0.00437718 - time (sec): 27.66 - samples/sec: 2117.89 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 20:33:21,027 epoch 9 - iter 352/447 - loss 0.00480072 - time (sec): 32.27 - samples/sec: 2146.99 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 20:33:24,776 epoch 9 - iter 396/447 - loss 0.00441195 - time (sec): 36.01 - samples/sec: 2152.58 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 20:33:28,519 epoch 9 - iter 440/447 - loss 0.00446100 - time (sec): 39.76 - samples/sec: 2147.70 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 20:33:29,100 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:33:29,101 EPOCH 9 done: loss 0.0044 - lr: 0.000003 | |
| 2023-10-23 20:33:35,299 DEV : loss 0.2651752233505249 - f1-score (micro avg) 0.7869 | |
| 2023-10-23 20:33:35,319 saving best model | |
| 2023-10-23 20:33:36,292 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:33:40,432 epoch 10 - iter 44/447 - loss 0.00222507 - time (sec): 4.14 - samples/sec: 2060.04 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 20:33:44,280 epoch 10 - iter 88/447 - loss 0.00222432 - time (sec): 7.99 - samples/sec: 2140.99 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 20:33:48,091 epoch 10 - iter 132/447 - loss 0.00195111 - time (sec): 11.80 - samples/sec: 2135.65 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 20:33:51,921 epoch 10 - iter 176/447 - loss 0.00167208 - time (sec): 15.63 - samples/sec: 2132.03 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 20:33:55,720 epoch 10 - iter 220/447 - loss 0.00201678 - time (sec): 19.43 - samples/sec: 2129.34 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 20:33:59,624 epoch 10 - iter 264/447 - loss 0.00281450 - time (sec): 23.33 - samples/sec: 2129.36 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 20:34:03,473 epoch 10 - iter 308/447 - loss 0.00267761 - time (sec): 27.18 - samples/sec: 2122.63 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 20:34:07,179 epoch 10 - iter 352/447 - loss 0.00267766 - time (sec): 30.89 - samples/sec: 2136.70 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 20:34:11,837 epoch 10 - iter 396/447 - loss 0.00272475 - time (sec): 35.54 - samples/sec: 2151.82 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 20:34:15,662 epoch 10 - iter 440/447 - loss 0.00324245 - time (sec): 39.37 - samples/sec: 2146.57 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 20:34:16,577 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:34:16,577 EPOCH 10 done: loss 0.0032 - lr: 0.000000 | |
| 2023-10-23 20:34:22,820 DEV : loss 0.2557121813297272 - f1-score (micro avg) 0.7858 | |
| 2023-10-23 20:34:23,391 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 20:34:23,392 Loading model from best epoch ... | |
| 2023-10-23 20:34:25,437 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time | |
| 2023-10-23 20:34:29,973 | |
| Results: | |
| - F-score (micro) 0.747 | |
| - F-score (macro) 0.6687 | |
| - Accuracy 0.6144 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8336 0.8406 0.8371 596 | |
| pers 0.6838 0.7598 0.7198 333 | |
| org 0.5126 0.4621 0.4861 132 | |
| prod 0.6271 0.5606 0.5920 66 | |
| time 0.7234 0.6939 0.7083 49 | |
| micro avg 0.7408 0.7534 0.7470 1176 | |
| macro avg 0.6761 0.6634 0.6687 1176 | |
| weighted avg 0.7390 0.7534 0.7453 1176 | |
| 2023-10-23 20:34:29,973 ---------------------------------------------------------------------------------------------------- | |