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: 0.0807
- Precision: 0.8905
- Recall: 0.9222
- F1: 0.9061
- Accuracy: 0.9811
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 |
|---|---|---|---|---|---|---|---|
| 0.2068 | 1.0 | 1252 | 0.1311 | 0.8309 | 0.8692 | 0.8496 | 0.9713 |
| 0.0974 | 2.0 | 2504 | 0.0960 | 0.8565 | 0.9047 | 0.8799 | 0.9768 |
| 0.0666 | 3.0 | 3756 | 0.0828 | 0.8948 | 0.9152 | 0.9049 | 0.9807 |
| 0.0459 | 4.0 | 5008 | 0.0787 | 0.9003 | 0.9244 | 0.9122 | 0.9820 |
| 0.0377 | 5.0 | 6260 | 0.0807 | 0.8905 | 0.9222 | 0.9061 | 0.9811 |
Framework versions
- Transformers 5.18.0
- Pytorch 2.11.0+cu130
- Datasets 4.8.5
- Tokenizers 0.23.2