<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
KLUE-BERT-BASE-NER-kluedata
This model is a fine-tuned version of klue/bert-base on the klue dataset. It achieves the following results on the evaluation set:
- Loss: 0.2098
- Precision: 0.7925
- Recall: 0.8169
- F1: 0.8045
- Accuracy: 0.9598
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 656
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2252 | 1.0 | 329 | 0.2217 | 0.5880 | 0.6798 | 0.6306 | 0.9262 |
0.1414 | 2.0 | 658 | 0.1665 | 0.7082 | 0.7468 | 0.7270 | 0.9476 |
0.0993 | 3.0 | 987 | 0.1469 | 0.7405 | 0.7873 | 0.7632 | 0.9542 |
0.0617 | 4.0 | 1316 | 0.1522 | 0.7534 | 0.8149 | 0.7830 | 0.9556 |
0.0448 | 5.0 | 1645 | 0.1630 | 0.7804 | 0.8042 | 0.7922 | 0.9585 |
0.0321 | 6.0 | 1974 | 0.1765 | 0.7811 | 0.8173 | 0.7988 | 0.9586 |
0.0227 | 7.0 | 2303 | 0.1810 | 0.7871 | 0.8136 | 0.8001 | 0.9594 |
0.017 | 8.0 | 2632 | 0.1929 | 0.7895 | 0.8176 | 0.8033 | 0.9603 |
0.0147 | 9.0 | 2961 | 0.1983 | 0.7956 | 0.8196 | 0.8074 | 0.9601 |
0.0114 | 10.0 | 3290 | 0.2098 | 0.7925 | 0.8169 | 0.8045 | 0.9598 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2