| 2023-10-23 22:38:32,825 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:38:32,826 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 22:38:32,826 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:38:32,827 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 22:38:32,827 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:38:32,827 Train: 3575 sentences | |
| 2023-10-23 22:38:32,827 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 22:38:32,827 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:38:32,827 Training Params: | |
| 2023-10-23 22:38:32,827 - learning_rate: "3e-05" | |
| 2023-10-23 22:38:32,827 - mini_batch_size: "4" | |
| 2023-10-23 22:38:32,827 - max_epochs: "10" | |
| 2023-10-23 22:38:32,827 - shuffle: "True" | |
| 2023-10-23 22:38:32,827 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:38:32,827 Plugins: | |
| 2023-10-23 22:38:32,827 - TensorboardLogger | |
| 2023-10-23 22:38:32,827 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 22:38:32,827 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:38:32,827 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 22:38:32,827 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 22:38:32,827 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:38:32,827 Computation: | |
| 2023-10-23 22:38:32,827 - compute on device: cuda:0 | |
| 2023-10-23 22:38:32,827 - embedding storage: none | |
| 2023-10-23 22:38:32,827 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:38:32,827 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-23 22:38:32,827 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:38:32,827 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:38:32,827 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 22:38:38,597 epoch 1 - iter 89/894 - loss 2.19658834 - time (sec): 5.77 - samples/sec: 1565.10 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 22:38:44,180 epoch 1 - iter 178/894 - loss 1.42684353 - time (sec): 11.35 - samples/sec: 1545.34 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 22:38:49,819 epoch 1 - iter 267/894 - loss 1.10437214 - time (sec): 16.99 - samples/sec: 1550.56 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 22:38:55,340 epoch 1 - iter 356/894 - loss 0.92546222 - time (sec): 22.51 - samples/sec: 1547.85 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 22:39:01,285 epoch 1 - iter 445/894 - loss 0.79270530 - time (sec): 28.46 - samples/sec: 1551.58 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 22:39:06,846 epoch 1 - iter 534/894 - loss 0.70887847 - time (sec): 34.02 - samples/sec: 1537.26 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 22:39:12,449 epoch 1 - iter 623/894 - loss 0.64668937 - time (sec): 39.62 - samples/sec: 1525.30 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 22:39:17,955 epoch 1 - iter 712/894 - loss 0.59748589 - time (sec): 45.13 - samples/sec: 1509.33 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 22:39:23,729 epoch 1 - iter 801/894 - loss 0.55098950 - time (sec): 50.90 - samples/sec: 1523.94 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 22:39:29,420 epoch 1 - iter 890/894 - loss 0.51190763 - time (sec): 56.59 - samples/sec: 1524.69 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 22:39:29,659 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:39:29,659 EPOCH 1 done: loss 0.5116 - lr: 0.000030 | |
| 2023-10-23 22:39:34,496 DEV : loss 0.17914246022701263 - f1-score (micro avg) 0.6504 | |
| 2023-10-23 22:39:34,517 saving best model | |
| 2023-10-23 22:39:34,994 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:39:40,776 epoch 2 - iter 89/894 - loss 0.14849414 - time (sec): 5.78 - samples/sec: 1484.55 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 22:39:46,513 epoch 2 - iter 178/894 - loss 0.16030660 - time (sec): 11.52 - samples/sec: 1523.25 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 22:39:52,146 epoch 2 - iter 267/894 - loss 0.15694845 - time (sec): 17.15 - samples/sec: 1506.24 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 22:39:57,974 epoch 2 - iter 356/894 - loss 0.15586715 - time (sec): 22.98 - samples/sec: 1519.90 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 22:40:03,546 epoch 2 - iter 445/894 - loss 0.15381150 - time (sec): 28.55 - samples/sec: 1516.02 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 22:40:09,151 epoch 2 - iter 534/894 - loss 0.15159799 - time (sec): 34.16 - samples/sec: 1516.82 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 22:40:14,705 epoch 2 - iter 623/894 - loss 0.14575727 - time (sec): 39.71 - samples/sec: 1514.08 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 22:40:20,441 epoch 2 - iter 712/894 - loss 0.14248398 - time (sec): 45.45 - samples/sec: 1525.30 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 22:40:26,037 epoch 2 - iter 801/894 - loss 0.14143481 - time (sec): 51.04 - samples/sec: 1519.62 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 22:40:31,697 epoch 2 - iter 890/894 - loss 0.13933960 - time (sec): 56.70 - samples/sec: 1520.47 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 22:40:31,937 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:40:31,938 EPOCH 2 done: loss 0.1397 - lr: 0.000027 | |
| 2023-10-23 22:40:38,442 DEV : loss 0.161593958735466 - f1-score (micro avg) 0.6957 | |
| 2023-10-23 22:40:38,463 saving best model | |
| 2023-10-23 22:40:39,056 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:40:44,992 epoch 3 - iter 89/894 - loss 0.09507660 - time (sec): 5.93 - samples/sec: 1626.66 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 22:40:50,634 epoch 3 - iter 178/894 - loss 0.08959201 - time (sec): 11.58 - samples/sec: 1616.43 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 22:40:56,328 epoch 3 - iter 267/894 - loss 0.08944180 - time (sec): 17.27 - samples/sec: 1594.58 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 22:41:01,809 epoch 3 - iter 356/894 - loss 0.08534777 - time (sec): 22.75 - samples/sec: 1562.15 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 22:41:07,752 epoch 3 - iter 445/894 - loss 0.08007011 - time (sec): 28.69 - samples/sec: 1566.08 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 22:41:13,689 epoch 3 - iter 534/894 - loss 0.07925379 - time (sec): 34.63 - samples/sec: 1570.82 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 22:41:19,195 epoch 3 - iter 623/894 - loss 0.08066880 - time (sec): 40.14 - samples/sec: 1549.12 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 22:41:24,702 epoch 3 - iter 712/894 - loss 0.08288875 - time (sec): 45.64 - samples/sec: 1530.74 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 22:41:30,366 epoch 3 - iter 801/894 - loss 0.08332226 - time (sec): 51.31 - samples/sec: 1533.41 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 22:41:35,789 epoch 3 - iter 890/894 - loss 0.08304645 - time (sec): 56.73 - samples/sec: 1518.37 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 22:41:36,035 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:41:36,035 EPOCH 3 done: loss 0.0830 - lr: 0.000023 | |
| 2023-10-23 22:41:42,527 DEV : loss 0.1837383210659027 - f1-score (micro avg) 0.742 | |
| 2023-10-23 22:41:42,548 saving best model | |
| 2023-10-23 22:41:43,143 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:41:48,721 epoch 4 - iter 89/894 - loss 0.04033953 - time (sec): 5.58 - samples/sec: 1519.97 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 22:41:54,565 epoch 4 - iter 178/894 - loss 0.04576950 - time (sec): 11.42 - samples/sec: 1554.52 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 22:42:00,391 epoch 4 - iter 267/894 - loss 0.04855522 - time (sec): 17.25 - samples/sec: 1548.91 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 22:42:05,867 epoch 4 - iter 356/894 - loss 0.04981395 - time (sec): 22.72 - samples/sec: 1511.43 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 22:42:11,932 epoch 4 - iter 445/894 - loss 0.05343608 - time (sec): 28.79 - samples/sec: 1527.14 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 22:42:17,488 epoch 4 - iter 534/894 - loss 0.05227533 - time (sec): 34.34 - samples/sec: 1512.25 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 22:42:23,203 epoch 4 - iter 623/894 - loss 0.05475064 - time (sec): 40.06 - samples/sec: 1530.47 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 22:42:28,803 epoch 4 - iter 712/894 - loss 0.05378347 - time (sec): 45.66 - samples/sec: 1526.79 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 22:42:34,361 epoch 4 - iter 801/894 - loss 0.05333509 - time (sec): 51.22 - samples/sec: 1525.65 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 22:42:39,890 epoch 4 - iter 890/894 - loss 0.05299308 - time (sec): 56.75 - samples/sec: 1517.37 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 22:42:40,145 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:42:40,145 EPOCH 4 done: loss 0.0530 - lr: 0.000020 | |
| 2023-10-23 22:42:46,604 DEV : loss 0.21632781624794006 - f1-score (micro avg) 0.7595 | |
| 2023-10-23 22:42:46,624 saving best model | |
| 2023-10-23 22:42:47,215 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:42:52,801 epoch 5 - iter 89/894 - loss 0.03559663 - time (sec): 5.59 - samples/sec: 1548.30 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 22:42:58,651 epoch 5 - iter 178/894 - loss 0.03236078 - time (sec): 11.43 - samples/sec: 1544.48 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 22:43:04,179 epoch 5 - iter 267/894 - loss 0.02994001 - time (sec): 16.96 - samples/sec: 1524.48 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 22:43:09,721 epoch 5 - iter 356/894 - loss 0.03122186 - time (sec): 22.51 - samples/sec: 1516.21 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 22:43:15,445 epoch 5 - iter 445/894 - loss 0.03227968 - time (sec): 28.23 - samples/sec: 1509.16 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 22:43:21,155 epoch 5 - iter 534/894 - loss 0.03088626 - time (sec): 33.94 - samples/sec: 1507.36 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 22:43:26,666 epoch 5 - iter 623/894 - loss 0.03520768 - time (sec): 39.45 - samples/sec: 1507.71 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 22:43:32,555 epoch 5 - iter 712/894 - loss 0.03651354 - time (sec): 45.34 - samples/sec: 1516.80 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 22:43:38,120 epoch 5 - iter 801/894 - loss 0.03535800 - time (sec): 50.90 - samples/sec: 1521.88 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 22:43:43,750 epoch 5 - iter 890/894 - loss 0.03467838 - time (sec): 56.53 - samples/sec: 1522.51 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 22:43:44,017 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:43:44,017 EPOCH 5 done: loss 0.0346 - lr: 0.000017 | |
| 2023-10-23 22:43:50,506 DEV : loss 0.23189181089401245 - f1-score (micro avg) 0.7573 | |
| 2023-10-23 22:43:50,527 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:43:56,264 epoch 6 - iter 89/894 - loss 0.02532279 - time (sec): 5.74 - samples/sec: 1466.77 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 22:44:02,035 epoch 6 - iter 178/894 - loss 0.02807963 - time (sec): 11.51 - samples/sec: 1485.35 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 22:44:08,080 epoch 6 - iter 267/894 - loss 0.02735131 - time (sec): 17.55 - samples/sec: 1533.60 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 22:44:13,605 epoch 6 - iter 356/894 - loss 0.02484311 - time (sec): 23.08 - samples/sec: 1526.45 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 22:44:19,179 epoch 6 - iter 445/894 - loss 0.02606946 - time (sec): 28.65 - samples/sec: 1520.66 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 22:44:24,833 epoch 6 - iter 534/894 - loss 0.02445808 - time (sec): 34.31 - samples/sec: 1517.91 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 22:44:30,281 epoch 6 - iter 623/894 - loss 0.02488802 - time (sec): 39.75 - samples/sec: 1507.43 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 22:44:35,737 epoch 6 - iter 712/894 - loss 0.02351730 - time (sec): 45.21 - samples/sec: 1503.02 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 22:44:41,459 epoch 6 - iter 801/894 - loss 0.02489985 - time (sec): 50.93 - samples/sec: 1508.61 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 22:44:47,149 epoch 6 - iter 890/894 - loss 0.02565738 - time (sec): 56.62 - samples/sec: 1522.00 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 22:44:47,395 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:44:47,395 EPOCH 6 done: loss 0.0256 - lr: 0.000013 | |
| 2023-10-23 22:44:53,878 DEV : loss 0.22867470979690552 - f1-score (micro avg) 0.7792 | |
| 2023-10-23 22:44:53,899 saving best model | |
| 2023-10-23 22:44:54,488 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:45:00,386 epoch 7 - iter 89/894 - loss 0.01077021 - time (sec): 5.90 - samples/sec: 1560.90 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 22:45:06,031 epoch 7 - iter 178/894 - loss 0.01430220 - time (sec): 11.54 - samples/sec: 1545.05 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 22:45:11,563 epoch 7 - iter 267/894 - loss 0.01639112 - time (sec): 17.07 - samples/sec: 1527.65 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 22:45:17,350 epoch 7 - iter 356/894 - loss 0.01528920 - time (sec): 22.86 - samples/sec: 1562.40 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 22:45:22,971 epoch 7 - iter 445/894 - loss 0.01559562 - time (sec): 28.48 - samples/sec: 1541.88 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 22:45:28,693 epoch 7 - iter 534/894 - loss 0.01482951 - time (sec): 34.20 - samples/sec: 1533.75 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 22:45:34,323 epoch 7 - iter 623/894 - loss 0.01485682 - time (sec): 39.83 - samples/sec: 1534.43 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 22:45:40,101 epoch 7 - iter 712/894 - loss 0.01527614 - time (sec): 45.61 - samples/sec: 1541.19 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 22:45:45,810 epoch 7 - iter 801/894 - loss 0.01551461 - time (sec): 51.32 - samples/sec: 1536.03 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 22:45:51,180 epoch 7 - iter 890/894 - loss 0.01536354 - time (sec): 56.69 - samples/sec: 1520.76 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 22:45:51,418 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:45:51,419 EPOCH 7 done: loss 0.0155 - lr: 0.000010 | |
| 2023-10-23 22:45:57,916 DEV : loss 0.28836268186569214 - f1-score (micro avg) 0.7771 | |
| 2023-10-23 22:45:57,937 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:46:03,516 epoch 8 - iter 89/894 - loss 0.01163123 - time (sec): 5.58 - samples/sec: 1536.51 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 22:46:09,438 epoch 8 - iter 178/894 - loss 0.00810689 - time (sec): 11.50 - samples/sec: 1548.67 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 22:46:14,981 epoch 8 - iter 267/894 - loss 0.00784824 - time (sec): 17.04 - samples/sec: 1538.69 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 22:46:20,608 epoch 8 - iter 356/894 - loss 0.01197846 - time (sec): 22.67 - samples/sec: 1508.98 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 22:46:26,221 epoch 8 - iter 445/894 - loss 0.01161327 - time (sec): 28.28 - samples/sec: 1506.75 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 22:46:31,703 epoch 8 - iter 534/894 - loss 0.01039741 - time (sec): 33.77 - samples/sec: 1501.93 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 22:46:37,545 epoch 8 - iter 623/894 - loss 0.01046625 - time (sec): 39.61 - samples/sec: 1515.15 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 22:46:43,449 epoch 8 - iter 712/894 - loss 0.01054270 - time (sec): 45.51 - samples/sec: 1523.09 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 22:46:49,045 epoch 8 - iter 801/894 - loss 0.01117368 - time (sec): 51.11 - samples/sec: 1527.30 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 22:46:54,587 epoch 8 - iter 890/894 - loss 0.01090378 - time (sec): 56.65 - samples/sec: 1522.06 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 22:46:54,833 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:46:54,834 EPOCH 8 done: loss 0.0112 - lr: 0.000007 | |
| 2023-10-23 22:47:01,339 DEV : loss 0.2503233850002289 - f1-score (micro avg) 0.7723 | |
| 2023-10-23 22:47:01,359 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:47:06,960 epoch 9 - iter 89/894 - loss 0.00515796 - time (sec): 5.60 - samples/sec: 1498.16 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 22:47:12,763 epoch 9 - iter 178/894 - loss 0.00448032 - time (sec): 11.40 - samples/sec: 1518.92 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 22:47:18,481 epoch 9 - iter 267/894 - loss 0.00703261 - time (sec): 17.12 - samples/sec: 1546.46 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 22:47:24,038 epoch 9 - iter 356/894 - loss 0.00706641 - time (sec): 22.68 - samples/sec: 1527.96 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 22:47:29,594 epoch 9 - iter 445/894 - loss 0.00762180 - time (sec): 28.23 - samples/sec: 1524.64 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 22:47:35,235 epoch 9 - iter 534/894 - loss 0.00723271 - time (sec): 33.88 - samples/sec: 1515.45 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 22:47:40,790 epoch 9 - iter 623/894 - loss 0.00692797 - time (sec): 39.43 - samples/sec: 1515.79 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 22:47:46,801 epoch 9 - iter 712/894 - loss 0.00622829 - time (sec): 45.44 - samples/sec: 1533.09 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 22:47:52,292 epoch 9 - iter 801/894 - loss 0.00704424 - time (sec): 50.93 - samples/sec: 1521.27 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 22:47:57,969 epoch 9 - iter 890/894 - loss 0.00672045 - time (sec): 56.61 - samples/sec: 1519.79 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 22:47:58,222 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:47:58,223 EPOCH 9 done: loss 0.0068 - lr: 0.000003 | |
| 2023-10-23 22:48:04,439 DEV : loss 0.2725300192832947 - f1-score (micro avg) 0.7826 | |
| 2023-10-23 22:48:04,460 saving best model | |
| 2023-10-23 22:48:05,049 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:48:10,568 epoch 10 - iter 89/894 - loss 0.00606623 - time (sec): 5.52 - samples/sec: 1456.07 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 22:48:16,338 epoch 10 - iter 178/894 - loss 0.00324980 - time (sec): 11.29 - samples/sec: 1424.87 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 22:48:22,097 epoch 10 - iter 267/894 - loss 0.00269239 - time (sec): 17.05 - samples/sec: 1471.54 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 22:48:27,990 epoch 10 - iter 356/894 - loss 0.00292304 - time (sec): 22.94 - samples/sec: 1490.43 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 22:48:33,804 epoch 10 - iter 445/894 - loss 0.00241672 - time (sec): 28.75 - samples/sec: 1512.69 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 22:48:39,393 epoch 10 - iter 534/894 - loss 0.00222088 - time (sec): 34.34 - samples/sec: 1505.01 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 22:48:44,925 epoch 10 - iter 623/894 - loss 0.00269017 - time (sec): 39.88 - samples/sec: 1496.46 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 22:48:50,533 epoch 10 - iter 712/894 - loss 0.00259172 - time (sec): 45.48 - samples/sec: 1504.68 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 22:48:56,193 epoch 10 - iter 801/894 - loss 0.00296873 - time (sec): 51.14 - samples/sec: 1508.81 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 22:49:02,060 epoch 10 - iter 890/894 - loss 0.00316216 - time (sec): 57.01 - samples/sec: 1510.20 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 22:49:02,310 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:49:02,310 EPOCH 10 done: loss 0.0031 - lr: 0.000000 | |
| 2023-10-23 22:49:08,530 DEV : loss 0.2750208377838135 - f1-score (micro avg) 0.7822 | |
| 2023-10-23 22:49:09,022 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:49:09,023 Loading model from best epoch ... | |
| 2023-10-23 22:49:10,707 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 22:49:15,538 | |
| Results: | |
| - F-score (micro) 0.7568 | |
| - F-score (macro) 0.6789 | |
| - Accuracy 0.6261 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8285 0.8591 0.8435 596 | |
| pers 0.6838 0.7598 0.7198 333 | |
| org 0.5702 0.5227 0.5455 132 | |
| prod 0.6531 0.4848 0.5565 66 | |
| time 0.7447 0.7143 0.7292 49 | |
| micro avg 0.7477 0.7662 0.7568 1176 | |
| macro avg 0.6961 0.6681 0.6789 1176 | |
| weighted avg 0.7452 0.7662 0.7541 1176 | |
| 2023-10-23 22:49:15,538 ---------------------------------------------------------------------------------------------------- | |