| 2023-10-23 22:49:30,395 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:49:30,396 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 22:49:30,396 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:49:30,396 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 22:49:30,396 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:49:30,396 Train: 3575 sentences | |
| 2023-10-23 22:49:30,396 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 22:49:30,396 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:49:30,396 Training Params: | |
| 2023-10-23 22:49:30,396 - learning_rate: "5e-05" | |
| 2023-10-23 22:49:30,396 - mini_batch_size: "4" | |
| 2023-10-23 22:49:30,396 - max_epochs: "10" | |
| 2023-10-23 22:49:30,396 - shuffle: "True" | |
| 2023-10-23 22:49:30,396 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:49:30,396 Plugins: | |
| 2023-10-23 22:49:30,396 - TensorboardLogger | |
| 2023-10-23 22:49:30,396 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 22:49:30,396 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:49:30,396 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 22:49:30,396 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 22:49:30,396 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:49:30,396 Computation: | |
| 2023-10-23 22:49:30,396 - compute on device: cuda:0 | |
| 2023-10-23 22:49:30,396 - embedding storage: none | |
| 2023-10-23 22:49:30,396 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:49:30,397 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-23 22:49:30,397 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:49:30,397 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:49:30,397 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 22:49:36,155 epoch 1 - iter 89/894 - loss 1.89230113 - time (sec): 5.76 - samples/sec: 1568.36 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 22:49:41,729 epoch 1 - iter 178/894 - loss 1.23768734 - time (sec): 11.33 - samples/sec: 1548.16 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 22:49:47,374 epoch 1 - iter 267/894 - loss 0.95322455 - time (sec): 16.98 - samples/sec: 1551.87 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 22:49:52,890 epoch 1 - iter 356/894 - loss 0.79934855 - time (sec): 22.49 - samples/sec: 1549.24 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 22:49:58,835 epoch 1 - iter 445/894 - loss 0.68662881 - time (sec): 28.44 - samples/sec: 1552.64 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 22:50:04,386 epoch 1 - iter 534/894 - loss 0.61468447 - time (sec): 33.99 - samples/sec: 1538.57 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 22:50:09,991 epoch 1 - iter 623/894 - loss 0.56293072 - time (sec): 39.59 - samples/sec: 1526.39 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-23 22:50:15,496 epoch 1 - iter 712/894 - loss 0.52064238 - time (sec): 45.10 - samples/sec: 1510.27 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-23 22:50:21,261 epoch 1 - iter 801/894 - loss 0.48300698 - time (sec): 50.86 - samples/sec: 1525.07 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-23 22:50:26,941 epoch 1 - iter 890/894 - loss 0.45116414 - time (sec): 56.54 - samples/sec: 1526.00 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-23 22:50:27,178 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:50:27,179 EPOCH 1 done: loss 0.4508 - lr: 0.000050 | |
| 2023-10-23 22:50:32,016 DEV : loss 0.20658902823925018 - f1-score (micro avg) 0.6099 | |
| 2023-10-23 22:50:32,036 saving best model | |
| 2023-10-23 22:50:32,505 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:50:38,267 epoch 2 - iter 89/894 - loss 0.15434962 - time (sec): 5.76 - samples/sec: 1489.64 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 22:50:43,999 epoch 2 - iter 178/894 - loss 0.17011126 - time (sec): 11.49 - samples/sec: 1526.50 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 22:50:49,620 epoch 2 - iter 267/894 - loss 0.16331287 - time (sec): 17.11 - samples/sec: 1509.50 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-23 22:50:55,433 epoch 2 - iter 356/894 - loss 0.15935409 - time (sec): 22.93 - samples/sec: 1523.36 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-23 22:51:01,011 epoch 2 - iter 445/894 - loss 0.15771296 - time (sec): 28.50 - samples/sec: 1518.48 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-23 22:51:06,621 epoch 2 - iter 534/894 - loss 0.15628055 - time (sec): 34.12 - samples/sec: 1518.62 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-23 22:51:12,176 epoch 2 - iter 623/894 - loss 0.15337233 - time (sec): 39.67 - samples/sec: 1515.60 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-23 22:51:17,915 epoch 2 - iter 712/894 - loss 0.14878889 - time (sec): 45.41 - samples/sec: 1526.53 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-23 22:51:23,512 epoch 2 - iter 801/894 - loss 0.14702059 - time (sec): 51.01 - samples/sec: 1520.68 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-23 22:51:29,174 epoch 2 - iter 890/894 - loss 0.14567783 - time (sec): 56.67 - samples/sec: 1521.37 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-23 22:51:29,414 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:51:29,414 EPOCH 2 done: loss 0.1465 - lr: 0.000044 | |
| 2023-10-23 22:51:35,915 DEV : loss 0.17153306305408478 - f1-score (micro avg) 0.6876 | |
| 2023-10-23 22:51:35,936 saving best model | |
| 2023-10-23 22:51:36,525 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:51:42,471 epoch 3 - iter 89/894 - loss 0.11549407 - time (sec): 5.94 - samples/sec: 1624.10 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-23 22:51:48,118 epoch 3 - iter 178/894 - loss 0.10047040 - time (sec): 11.59 - samples/sec: 1614.35 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-23 22:51:53,800 epoch 3 - iter 267/894 - loss 0.10381143 - time (sec): 17.27 - samples/sec: 1594.33 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-23 22:51:59,265 epoch 3 - iter 356/894 - loss 0.09976007 - time (sec): 22.74 - samples/sec: 1563.08 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-23 22:52:05,191 epoch 3 - iter 445/894 - loss 0.09852416 - time (sec): 28.66 - samples/sec: 1567.70 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-23 22:52:11,121 epoch 3 - iter 534/894 - loss 0.09587092 - time (sec): 34.59 - samples/sec: 1572.55 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-23 22:52:16,611 epoch 3 - iter 623/894 - loss 0.09686006 - time (sec): 40.08 - samples/sec: 1551.20 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-23 22:52:22,100 epoch 3 - iter 712/894 - loss 0.09757567 - time (sec): 45.57 - samples/sec: 1533.14 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-23 22:52:27,745 epoch 3 - iter 801/894 - loss 0.09644605 - time (sec): 51.22 - samples/sec: 1536.12 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-23 22:52:33,154 epoch 3 - iter 890/894 - loss 0.09578227 - time (sec): 56.63 - samples/sec: 1521.18 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-23 22:52:33,398 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:52:33,398 EPOCH 3 done: loss 0.0958 - lr: 0.000039 | |
| 2023-10-23 22:52:39,875 DEV : loss 0.19253584742546082 - f1-score (micro avg) 0.6924 | |
| 2023-10-23 22:52:39,895 saving best model | |
| 2023-10-23 22:52:40,469 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:52:46,035 epoch 4 - iter 89/894 - loss 0.05340071 - time (sec): 5.57 - samples/sec: 1522.95 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-23 22:52:51,880 epoch 4 - iter 178/894 - loss 0.06546909 - time (sec): 11.41 - samples/sec: 1556.05 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-23 22:52:57,704 epoch 4 - iter 267/894 - loss 0.06397801 - time (sec): 17.23 - samples/sec: 1550.01 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-23 22:53:03,184 epoch 4 - iter 356/894 - loss 0.06168127 - time (sec): 22.71 - samples/sec: 1511.94 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-23 22:53:09,248 epoch 4 - iter 445/894 - loss 0.06400375 - time (sec): 28.78 - samples/sec: 1527.61 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-23 22:53:14,803 epoch 4 - iter 534/894 - loss 0.06406170 - time (sec): 34.33 - samples/sec: 1512.72 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-23 22:53:20,518 epoch 4 - iter 623/894 - loss 0.06767318 - time (sec): 40.05 - samples/sec: 1530.84 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-23 22:53:26,118 epoch 4 - iter 712/894 - loss 0.06818413 - time (sec): 45.65 - samples/sec: 1527.17 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 22:53:31,676 epoch 4 - iter 801/894 - loss 0.06652914 - time (sec): 51.21 - samples/sec: 1525.97 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 22:53:37,205 epoch 4 - iter 890/894 - loss 0.06661341 - time (sec): 56.74 - samples/sec: 1517.64 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-23 22:53:37,460 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:53:37,460 EPOCH 4 done: loss 0.0667 - lr: 0.000033 | |
| 2023-10-23 22:53:43,960 DEV : loss 0.22617001831531525 - f1-score (micro avg) 0.732 | |
| 2023-10-23 22:53:43,981 saving best model | |
| 2023-10-23 22:53:44,563 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:53:50,150 epoch 5 - iter 89/894 - loss 0.03847375 - time (sec): 5.59 - samples/sec: 1548.11 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-23 22:53:56,003 epoch 5 - iter 178/894 - loss 0.04130081 - time (sec): 11.44 - samples/sec: 1543.93 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-23 22:54:01,533 epoch 5 - iter 267/894 - loss 0.04400346 - time (sec): 16.97 - samples/sec: 1523.98 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-23 22:54:07,074 epoch 5 - iter 356/894 - loss 0.04504201 - time (sec): 22.51 - samples/sec: 1515.87 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-23 22:54:12,796 epoch 5 - iter 445/894 - loss 0.04515784 - time (sec): 28.23 - samples/sec: 1509.00 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-23 22:54:18,507 epoch 5 - iter 534/894 - loss 0.04312426 - time (sec): 33.94 - samples/sec: 1507.17 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 22:54:24,019 epoch 5 - iter 623/894 - loss 0.04439914 - time (sec): 39.45 - samples/sec: 1507.54 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 22:54:29,902 epoch 5 - iter 712/894 - loss 0.04626351 - time (sec): 45.34 - samples/sec: 1516.83 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 22:54:35,470 epoch 5 - iter 801/894 - loss 0.04521734 - time (sec): 50.91 - samples/sec: 1521.82 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 22:54:41,097 epoch 5 - iter 890/894 - loss 0.04347528 - time (sec): 56.53 - samples/sec: 1522.53 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 22:54:41,362 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:54:41,362 EPOCH 5 done: loss 0.0436 - lr: 0.000028 | |
| 2023-10-23 22:54:47,838 DEV : loss 0.22702528536319733 - f1-score (micro avg) 0.7545 | |
| 2023-10-23 22:54:47,858 saving best model | |
| 2023-10-23 22:54:48,441 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:54:54,178 epoch 6 - iter 89/894 - loss 0.02705068 - time (sec): 5.74 - samples/sec: 1466.90 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 22:54:59,948 epoch 6 - iter 178/894 - loss 0.02543707 - time (sec): 11.51 - samples/sec: 1485.52 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 22:55:05,992 epoch 6 - iter 267/894 - loss 0.02928149 - time (sec): 17.55 - samples/sec: 1533.87 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 22:55:11,509 epoch 6 - iter 356/894 - loss 0.03037954 - time (sec): 23.07 - samples/sec: 1527.13 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 22:55:17,078 epoch 6 - iter 445/894 - loss 0.03095994 - time (sec): 28.64 - samples/sec: 1521.48 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 22:55:22,726 epoch 6 - iter 534/894 - loss 0.02994244 - time (sec): 34.28 - samples/sec: 1518.85 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 22:55:28,164 epoch 6 - iter 623/894 - loss 0.03058719 - time (sec): 39.72 - samples/sec: 1508.59 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 22:55:33,615 epoch 6 - iter 712/894 - loss 0.03030287 - time (sec): 45.17 - samples/sec: 1504.23 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 22:55:39,332 epoch 6 - iter 801/894 - loss 0.02985015 - time (sec): 50.89 - samples/sec: 1509.85 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 22:55:45,019 epoch 6 - iter 890/894 - loss 0.02948320 - time (sec): 56.58 - samples/sec: 1523.21 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 22:55:45,264 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:55:45,264 EPOCH 6 done: loss 0.0294 - lr: 0.000022 | |
| 2023-10-23 22:55:51,747 DEV : loss 0.26115021109580994 - f1-score (micro avg) 0.7395 | |
| 2023-10-23 22:55:51,767 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:55:57,666 epoch 7 - iter 89/894 - loss 0.01502691 - time (sec): 5.90 - samples/sec: 1560.68 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 22:56:03,318 epoch 7 - iter 178/894 - loss 0.02355773 - time (sec): 11.55 - samples/sec: 1543.95 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 22:56:08,854 epoch 7 - iter 267/894 - loss 0.02081776 - time (sec): 17.09 - samples/sec: 1526.58 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 22:56:14,634 epoch 7 - iter 356/894 - loss 0.02157166 - time (sec): 22.87 - samples/sec: 1562.10 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 22:56:20,252 epoch 7 - iter 445/894 - loss 0.02168071 - time (sec): 28.48 - samples/sec: 1541.80 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 22:56:25,970 epoch 7 - iter 534/894 - loss 0.01981735 - time (sec): 34.20 - samples/sec: 1533.84 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 22:56:31,600 epoch 7 - iter 623/894 - loss 0.02156934 - time (sec): 39.83 - samples/sec: 1534.52 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 22:56:37,370 epoch 7 - iter 712/894 - loss 0.02161565 - time (sec): 45.60 - samples/sec: 1541.51 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 22:56:43,079 epoch 7 - iter 801/894 - loss 0.02136584 - time (sec): 51.31 - samples/sec: 1536.33 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 22:56:48,442 epoch 7 - iter 890/894 - loss 0.02065920 - time (sec): 56.67 - samples/sec: 1521.22 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 22:56:48,681 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:56:48,681 EPOCH 7 done: loss 0.0206 - lr: 0.000017 | |
| 2023-10-23 22:56:55,183 DEV : loss 0.26584720611572266 - f1-score (micro avg) 0.755 | |
| 2023-10-23 22:56:55,203 saving best model | |
| 2023-10-23 22:56:55,785 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:57:01,368 epoch 8 - iter 89/894 - loss 0.01810547 - time (sec): 5.58 - samples/sec: 1535.70 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 22:57:07,270 epoch 8 - iter 178/894 - loss 0.01401670 - time (sec): 11.48 - samples/sec: 1550.83 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 22:57:12,806 epoch 8 - iter 267/894 - loss 0.01102657 - time (sec): 17.02 - samples/sec: 1540.87 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 22:57:18,438 epoch 8 - iter 356/894 - loss 0.01297886 - time (sec): 22.65 - samples/sec: 1510.22 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 22:57:24,046 epoch 8 - iter 445/894 - loss 0.01401949 - time (sec): 28.26 - samples/sec: 1507.99 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 22:57:29,518 epoch 8 - iter 534/894 - loss 0.01265375 - time (sec): 33.73 - samples/sec: 1503.43 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 22:57:35,357 epoch 8 - iter 623/894 - loss 0.01275932 - time (sec): 39.57 - samples/sec: 1516.55 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 22:57:41,261 epoch 8 - iter 712/894 - loss 0.01174535 - time (sec): 45.47 - samples/sec: 1524.32 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 22:57:46,854 epoch 8 - iter 801/894 - loss 0.01245907 - time (sec): 51.07 - samples/sec: 1528.48 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 22:57:52,395 epoch 8 - iter 890/894 - loss 0.01185428 - time (sec): 56.61 - samples/sec: 1523.16 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 22:57:52,640 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:57:52,640 EPOCH 8 done: loss 0.0121 - lr: 0.000011 | |
| 2023-10-23 22:57:59,144 DEV : loss 0.2595275938510895 - f1-score (micro avg) 0.7686 | |
| 2023-10-23 22:57:59,165 saving best model | |
| 2023-10-23 22:57:59,748 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:58:05,352 epoch 9 - iter 89/894 - loss 0.01175348 - time (sec): 5.60 - samples/sec: 1497.38 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 22:58:11,152 epoch 9 - iter 178/894 - loss 0.00798146 - time (sec): 11.40 - samples/sec: 1518.95 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 22:58:16,871 epoch 9 - iter 267/894 - loss 0.00715061 - time (sec): 17.12 - samples/sec: 1546.45 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 22:58:22,431 epoch 9 - iter 356/894 - loss 0.00696113 - time (sec): 22.68 - samples/sec: 1527.76 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 22:58:27,985 epoch 9 - iter 445/894 - loss 0.00575510 - time (sec): 28.24 - samples/sec: 1524.56 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 22:58:33,621 epoch 9 - iter 534/894 - loss 0.00572485 - time (sec): 33.87 - samples/sec: 1515.62 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 22:58:39,174 epoch 9 - iter 623/894 - loss 0.00639103 - time (sec): 39.42 - samples/sec: 1516.00 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 22:58:45,197 epoch 9 - iter 712/894 - loss 0.00630826 - time (sec): 45.45 - samples/sec: 1532.85 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 22:58:50,684 epoch 9 - iter 801/894 - loss 0.00607735 - time (sec): 50.94 - samples/sec: 1521.19 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 22:58:56,358 epoch 9 - iter 890/894 - loss 0.00584459 - time (sec): 56.61 - samples/sec: 1519.82 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 22:58:56,610 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:58:56,610 EPOCH 9 done: loss 0.0058 - lr: 0.000006 | |
| 2023-10-23 22:59:02,842 DEV : loss 0.2801297605037689 - f1-score (micro avg) 0.7709 | |
| 2023-10-23 22:59:02,862 saving best model | |
| 2023-10-23 22:59:03,447 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:59:08,960 epoch 10 - iter 89/894 - loss 0.00751582 - time (sec): 5.51 - samples/sec: 1457.49 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 22:59:14,726 epoch 10 - iter 178/894 - loss 0.00514737 - time (sec): 11.28 - samples/sec: 1426.06 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 22:59:20,482 epoch 10 - iter 267/894 - loss 0.00386344 - time (sec): 17.03 - samples/sec: 1472.62 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 22:59:26,373 epoch 10 - iter 356/894 - loss 0.00357614 - time (sec): 22.92 - samples/sec: 1491.44 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 22:59:32,181 epoch 10 - iter 445/894 - loss 0.00379262 - time (sec): 28.73 - samples/sec: 1513.79 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 22:59:37,772 epoch 10 - iter 534/894 - loss 0.00335340 - time (sec): 34.32 - samples/sec: 1505.86 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 22:59:43,297 epoch 10 - iter 623/894 - loss 0.00404005 - time (sec): 39.85 - samples/sec: 1497.43 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 22:59:48,901 epoch 10 - iter 712/894 - loss 0.00415591 - time (sec): 45.45 - samples/sec: 1505.67 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 22:59:54,556 epoch 10 - iter 801/894 - loss 0.00448379 - time (sec): 51.11 - samples/sec: 1509.84 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 23:00:00,418 epoch 10 - iter 890/894 - loss 0.00481143 - time (sec): 56.97 - samples/sec: 1511.26 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 23:00:00,668 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:00:00,668 EPOCH 10 done: loss 0.0048 - lr: 0.000000 | |
| 2023-10-23 23:00:06,899 DEV : loss 0.2858913242816925 - f1-score (micro avg) 0.7746 | |
| 2023-10-23 23:00:06,919 saving best model | |
| 2023-10-23 23:00:07,980 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:00:07,980 Loading model from best epoch ... | |
| 2023-10-23 23:00:09,643 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 23:00:14,469 | |
| Results: | |
| - F-score (micro) 0.7476 | |
| - F-score (macro) 0.6761 | |
| - Accuracy 0.6143 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8271 0.8507 0.8387 596 | |
| pers 0.6623 0.7538 0.7051 333 | |
| org 0.5268 0.4470 0.4836 132 | |
| prod 0.7674 0.5000 0.6055 66 | |
| time 0.7400 0.7551 0.7475 49 | |
| micro avg 0.7410 0.7543 0.7476 1176 | |
| macro avg 0.7047 0.6613 0.6761 1176 | |
| weighted avg 0.7397 0.7543 0.7441 1176 | |
| 2023-10-23 23:00:14,470 ---------------------------------------------------------------------------------------------------- | |