task3_5-bge-small-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: 0.2216
- Precision: 0.8531
- Recall: 0.8973
- F1: 0.8747
- Accuracy: 0.9761
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: 32
- eval_batch_size: 64
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.5887 | 1.0 | 313 | 0.4976 | 0.6700 | 0.7228 | 0.6954 | 0.9472 |
| 0.3827 | 2.0 | 626 | 0.3198 | 0.7869 | 0.8378 | 0.8115 | 0.9666 |
| 0.2713 | 3.0 | 939 | 0.2528 | 0.8336 | 0.8817 | 0.8570 | 0.9722 |
| 0.2227 | 4.0 | 1252 | 0.2282 | 0.8530 | 0.8955 | 0.8737 | 0.9760 |
| 0.2082 | 5.0 | 1565 | 0.2216 | 0.8531 | 0.8973 | 0.8747 | 0.9761 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.4
- Tokenizers 0.22.2