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: 0.0833
- Precision: 0.8969
- Recall: 0.9265
- F1: 0.9114
- Accuracy: 0.9815
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 |
|---|---|---|---|---|---|---|---|
| 0.2107 | 1.0 | 1252 | 0.1308 | 0.8340 | 0.8682 | 0.8508 | 0.9712 |
| 0.0991 | 2.0 | 2504 | 0.0964 | 0.8637 | 0.9064 | 0.8845 | 0.9773 |
| 0.0696 | 3.0 | 3756 | 0.0857 | 0.8951 | 0.9175 | 0.9062 | 0.9809 |
| 0.0468 | 4.0 | 5008 | 0.0807 | 0.9082 | 0.9246 | 0.9164 | 0.9819 |
| 0.0393 | 5.0 | 6260 | 0.0796 | 0.8976 | 0.9266 | 0.9119 | 0.9813 |
| 0.0318 | 6.0 | 7512 | 0.0833 | 0.8969 | 0.9265 | 0.9114 | 0.9815 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2