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: 0.0816
- Precision: 0.9010
- Recall: 0.9246
- F1: 0.9126
- 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: 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 |
|---|---|---|---|---|---|---|---|
| 0.0977 | 1.0 | 625 | 0.1068 | 0.8300 | 0.9058 | 0.8662 | 0.9729 |
| 0.0638 | 2.0 | 1250 | 0.0855 | 0.8875 | 0.9120 | 0.8996 | 0.9796 |
| 0.0524 | 3.0 | 1875 | 0.0798 | 0.8663 | 0.9157 | 0.8903 | 0.9787 |
| 0.0405 | 4.0 | 2500 | 0.0768 | 0.8966 | 0.9207 | 0.9085 | 0.9819 |
| 0.0331 | 5.0 | 3125 | 0.0803 | 0.8944 | 0.9226 | 0.9083 | 0.9813 |
| 0.0283 | 6.0 | 3750 | 0.0756 | 0.8989 | 0.9260 | 0.9122 | 0.9823 |
| 0.0266 | 7.0 | 4375 | 0.0784 | 0.8966 | 0.9276 | 0.9118 | 0.9822 |
| 0.0207 | 8.0 | 5000 | 0.0816 | 0.9010 | 0.9246 | 0.9126 | 0.9823 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.10.0+cu128
- Datasets 3.4.1
- Tokenizers 0.21.4