bert-finetuned-ner
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0589
- Precision: 0.9345
- Recall: 0.9505
- F1: 0.9424
- Accuracy: 0.9868
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0752 | 1.0 | 1756 | 0.0624 | 0.9086 | 0.9366 | 0.9224 | 0.9823 |
| 0.0356 | 2.0 | 3512 | 0.0639 | 0.9320 | 0.9456 | 0.9388 | 0.9854 |
| 0.0208 | 3.0 | 5268 | 0.0589 | 0.9345 | 0.9505 | 0.9424 | 0.9868 |
Framework versions
- Transformers 5.13.0
- Pytorch 2.7.1+cu118
- Datasets 5.0.0
- Tokenizers 0.22.2