dl-hw2-bge-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: 0.0991
- Precision: 0.8633
- Recall: 0.9012
- F1: 0.8818
- Accuracy: 0.9772
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2202 | 1.0 | 1250 | 0.1415 | 0.8074 | 0.8743 | 0.8395 | 0.9690 |
| 0.1091 | 2.0 | 2500 | 0.1064 | 0.8639 | 0.8977 | 0.8805 | 0.9768 |
| 0.0802 | 3.0 | 3750 | 0.0991 | 0.8633 | 0.9012 | 0.8818 | 0.9772 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0
- Datasets 3.4.1
- Tokenizers 0.21.4