bge-small-en-v1.5-conll2003-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: 0.0995
- Precision: 0.9085
- Recall: 0.9293
- F1: 0.9188
- Accuracy: 0.9825
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1549 | 1.0 | 1250 | 0.0981 | 0.8417 | 0.8973 | 0.8686 | 0.9751 |
| 0.0682 | 2.0 | 2500 | 0.0856 | 0.8979 | 0.9122 | 0.9050 | 0.9802 |
| 0.0422 | 3.0 | 3750 | 0.0822 | 0.9059 | 0.9219 | 0.9138 | 0.9820 |
| 0.0324 | 4.0 | 5000 | 0.0874 | 0.9137 | 0.9249 | 0.9193 | 0.9826 |
| 0.0261 | 5.0 | 6250 | 0.1002 | 0.9071 | 0.9271 | 0.9170 | 0.9822 |
| 0.0199 | 6.0 | 7500 | 0.0975 | 0.9084 | 0.9244 | 0.9163 | 0.9816 |
| 0.0139 | 7.0 | 8750 | 0.0995 | 0.9085 | 0.9293 | 0.9188 | 0.9825 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.7.1+cu128
- Datasets 3.4.1
- Tokenizers 0.21.1