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: 0.2039
- Precision: 0.8655
- Recall: 0.9024
- F1: 0.8836
- Accuracy: 0.9771
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: 16
- eval_batch_size: 16
- 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.9608 | 1.0 | 625 | 0.3898 | 0.7224 | 0.7630 | 0.7422 | 0.9539 |
| 0.3682 | 2.0 | 1250 | 0.2504 | 0.8391 | 0.8797 | 0.8589 | 0.9734 |
| 0.2582 | 3.0 | 1875 | 0.2132 | 0.8532 | 0.9002 | 0.8761 | 0.9757 |
| 0.1793 | 4.0 | 2500 | 0.2039 | 0.8655 | 0.9024 | 0.8836 | 0.9771 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.23.1