bert-finetuned-ner
This model is a fine-tuned version of BAAI/bge-small-en-v1.5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0894
- Precision: 0.9085
- Recall: 0.9311
- F1: 0.9197
- Accuracy: 0.9832
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 OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0623 | 1.0 | 1251 | 0.0903 | 0.8639 | 0.9102 | 0.8864 | 0.9787 |
| 0.0459 | 2.0 | 2502 | 0.0869 | 0.8881 | 0.9131 | 0.9004 | 0.9801 |
| 0.0370 | 3.0 | 3753 | 0.0817 | 0.8838 | 0.9197 | 0.9014 | 0.9812 |
| 0.0301 | 4.0 | 5004 | 0.0805 | 0.9013 | 0.9241 | 0.9126 | 0.9819 |
| 0.0237 | 5.0 | 6255 | 0.0904 | 0.9010 | 0.9212 | 0.9110 | 0.9816 |
| 0.0199 | 6.0 | 7506 | 0.0889 | 0.9020 | 0.9265 | 0.9141 | 0.9825 |
| 0.0157 | 7.0 | 8757 | 0.0882 | 0.9008 | 0.9296 | 0.9149 | 0.9825 |
| 0.0123 | 8.0 | 10008 | 0.0882 | 0.9092 | 0.9321 | 0.9205 | 0.9834 |
| 0.0133 | 9.0 | 11259 | 0.0888 | 0.9051 | 0.9316 | 0.9182 | 0.9829 |
| 0.0125 | 10.0 | 12510 | 0.0894 | 0.9085 | 0.9311 | 0.9197 | 0.9832 |
Framework versions
- Transformers 5.19.0
- Pytorch 2.14.1+cu130
- Datasets 5.1.0
- Tokenizers 0.23.2