hse-dl2-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: 0.0897
- Precision: 0.8773
- Recall: 0.9123
- F1: 0.8945
- Accuracy: 0.9794
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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.5738 | 1.0 | 313 | 0.2447 | 0.6849 | 0.7326 | 0.7079 | 0.9502 |
| 0.2038 | 2.0 | 626 | 0.1492 | 0.8145 | 0.8600 | 0.8366 | 0.9705 |
| 0.1377 | 3.0 | 939 | 0.1212 | 0.8278 | 0.8918 | 0.8586 | 0.9735 |
| 0.1046 | 4.0 | 1252 | 0.1037 | 0.8565 | 0.9012 | 0.8783 | 0.9775 |
| 0.086 | 5.0 | 1565 | 0.0980 | 0.8649 | 0.9063 | 0.8851 | 0.9780 |
| 0.0731 | 6.0 | 1878 | 0.0920 | 0.8748 | 0.9115 | 0.8928 | 0.9791 |
| 0.0666 | 7.0 | 2191 | 0.0904 | 0.8752 | 0.9135 | 0.8939 | 0.9792 |
| 0.0628 | 8.0 | 2504 | 0.0897 | 0.8773 | 0.9123 | 0.8945 | 0.9794 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.11.0+cu128
- Datasets 3.4.1
- Tokenizers 0.21.4