<!-- 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-data60
This model is a fine-tuned version of klue/bert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2994
- Precision: 0.9092
- Recall: 0.9252
- F1: 0.9171
- Accuracy: 0.9571
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 3394
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2185 | 1.0 | 1698 | 0.1995 | 0.8549 | 0.8951 | 0.8745 | 0.9416 |
0.1782 | 2.0 | 3396 | 0.1777 | 0.8786 | 0.9120 | 0.8950 | 0.9489 |
0.1133 | 3.0 | 5094 | 0.1831 | 0.8990 | 0.9155 | 0.9072 | 0.9528 |
0.062 | 4.0 | 6792 | 0.2053 | 0.8971 | 0.9214 | 0.9091 | 0.9530 |
0.0396 | 5.0 | 8490 | 0.2135 | 0.9019 | 0.9207 | 0.9112 | 0.9535 |
0.0255 | 6.0 | 10188 | 0.2346 | 0.9049 | 0.9229 | 0.9138 | 0.9551 |
0.0159 | 7.0 | 11886 | 0.2536 | 0.9092 | 0.9232 | 0.9161 | 0.9563 |
0.0081 | 8.0 | 13584 | 0.2791 | 0.9100 | 0.9249 | 0.9174 | 0.9567 |
0.0037 | 9.0 | 15282 | 0.3040 | 0.9095 | 0.9252 | 0.9173 | 0.9565 |
0.0023 | 10.0 | 16980 | 0.2994 | 0.9092 | 0.9252 | 0.9171 | 0.9571 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2