bert-finetuned-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: 0.0880
- Precision: 0.9070
- Recall: 0.9285
- F1: 0.9176
- Accuracy: 0.9823
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 |
|---|---|---|---|---|---|---|---|
| 0.2068 | 1.0 | 1252 | 0.1312 | 0.8322 | 0.8699 | 0.8507 | 0.9714 |
| 0.0975 | 2.0 | 2504 | 0.0960 | 0.8579 | 0.9051 | 0.8808 | 0.9768 |
| 0.0664 | 3.0 | 3756 | 0.0831 | 0.8948 | 0.9150 | 0.9048 | 0.9807 |
| 0.0457 | 4.0 | 5008 | 0.0790 | 0.8990 | 0.9233 | 0.9110 | 0.9820 |
| 0.0377 | 5.0 | 6260 | 0.0807 | 0.8922 | 0.9219 | 0.9068 | 0.9812 |
| 0.0301 | 6.0 | 7512 | 0.0852 | 0.8998 | 0.9263 | 0.9128 | 0.9814 |
| 0.0225 | 7.0 | 8764 | 0.0875 | 0.9083 | 0.9249 | 0.9165 | 0.9822 |
| 0.0195 | 8.0 | 10016 | 0.0872 | 0.9009 | 0.9266 | 0.9136 | 0.9819 |
| 0.0163 | 9.0 | 11268 | 0.0874 | 0.9063 | 0.9278 | 0.9169 | 0.9825 |
| 0.0186 | 10.0 | 12520 | 0.0880 | 0.9070 | 0.9285 | 0.9176 | 0.9823 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.11.0+cu130
- Datasets 3.4.1
- Tokenizers 0.21.4