bge-small-en-v1.5-ner-hw2
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: 0.0945
- Precision: 0.9032
- Recall: 0.9246
- F1: 0.9138
- Accuracy: 0.9814
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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2176 | 1.0 | 625 | 0.1723 | 0.7719 | 0.8245 | 0.7973 | 0.9632 |
| 0.117 | 2.0 | 1250 | 0.1127 | 0.8549 | 0.8935 | 0.8738 | 0.9757 |
| 0.1078 | 3.0 | 1875 | 0.0930 | 0.8645 | 0.9101 | 0.8867 | 0.9778 |
| 0.0555 | 4.0 | 2500 | 0.0892 | 0.8839 | 0.9162 | 0.8998 | 0.9802 |
| 0.049 | 5.0 | 3125 | 0.0868 | 0.8902 | 0.9212 | 0.9055 | 0.9803 |
| 0.0482 | 6.0 | 3750 | 0.0851 | 0.8919 | 0.9224 | 0.9069 | 0.9802 |
| 0.0403 | 7.0 | 4375 | 0.0917 | 0.8889 | 0.9234 | 0.9058 | 0.9799 |
| 0.0262 | 8.0 | 5000 | 0.0945 | 0.9032 | 0.9246 | 0.9138 | 0.9814 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 4.8.5
- Tokenizers 0.21.4