bge-small-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: 0.0852
- Precision: 0.8827
- Recall: 0.9145
- F1: 0.8983
- Accuracy: 0.9799
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0381 | 1.0 | 625 | 0.0901 | 0.8775 | 0.9125 | 0.8946 | 0.9789 |
| 0.0402 | 2.0 | 1250 | 0.0859 | 0.8804 | 0.9147 | 0.8972 | 0.9793 |
| 0.0515 | 3.0 | 1875 | 0.0852 | 0.8827 | 0.9145 | 0.8983 | 0.9799 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.11.0+cu128
- Datasets 3.4.1
- Tokenizers 0.21.4