bge-small-en-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: 0.0826
- Precision: 0.9015
- Recall: 0.9254
- F1: 0.9133
- Accuracy: 0.9820
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 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 |
|---|---|---|---|---|---|---|---|
| 0.1469 | 1.0 | 1250 | 0.1297 | 0.8158 | 0.8760 | 0.8448 | 0.9708 |
| 0.0892 | 2.0 | 2500 | 0.0924 | 0.8707 | 0.9074 | 0.8887 | 0.9782 |
| 0.0683 | 3.0 | 3750 | 0.0809 | 0.8823 | 0.9159 | 0.8988 | 0.9801 |
| 0.0408 | 4.0 | 5000 | 0.0842 | 0.8909 | 0.9236 | 0.9070 | 0.9807 |
| 0.0286 | 5.0 | 6250 | 0.0843 | 0.9028 | 0.9234 | 0.9130 | 0.9818 |
| 0.0244 | 6.0 | 7500 | 0.0814 | 0.8990 | 0.9233 | 0.9110 | 0.9812 |
| 0.0309 | 7.0 | 8750 | 0.0826 | 0.9015 | 0.9254 | 0.9133 | 0.9820 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.11.0+cu130
- Datasets 3.4.1
- Tokenizers 0.21.4