dl2-hw-02
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: 0.0787
- Precision: 0.8971
- Recall: 0.9243
- F1: 0.9105
- 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: 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4845 | 1.0 | 626 | 0.1735 | 0.7777 | 0.8219 | 0.7992 | 0.9627 |
| 0.1738 | 2.0 | 1252 | 0.1128 | 0.8438 | 0.8940 | 0.8682 | 0.9749 |
| 0.1142 | 3.0 | 1878 | 0.0947 | 0.8677 | 0.9007 | 0.8839 | 0.9776 |
| 0.0683 | 4.0 | 2504 | 0.0832 | 0.8937 | 0.9165 | 0.9050 | 0.9809 |
| 0.0552 | 5.0 | 3130 | 0.0833 | 0.8777 | 0.9175 | 0.8972 | 0.9792 |
| 0.0469 | 6.0 | 3756 | 0.0809 | 0.8853 | 0.9172 | 0.9010 | 0.9803 |
| 0.0431 | 7.0 | 4382 | 0.0799 | 0.8927 | 0.9202 | 0.9063 | 0.9814 |
| 0.0341 | 8.0 | 5008 | 0.0778 | 0.8917 | 0.9226 | 0.9069 | 0.9817 |
| 0.03 | 9.0 | 5634 | 0.0786 | 0.8926 | 0.9244 | 0.9082 | 0.9814 |
| 0.0275 | 10.0 | 6260 | 0.0787 | 0.8971 | 0.9243 | 0.9105 | 0.9820 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.11.0+cu128
- Datasets 3.4.1
- Tokenizers 0.21.4