bert-finetuned-ner-wandb
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: 0.1690
- Precision: 0.8887
- Recall: 0.9221
- F1: 0.9051
- Accuracy: 0.9802
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_FUSED 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 |
|---|---|---|---|---|---|---|---|
| 0.9256 | 1.0 | 625 | 0.3445 | 0.7719 | 0.8245 | 0.7973 | 0.9632 |
| 0.3420 | 2.0 | 1250 | 0.2251 | 0.8576 | 0.8948 | 0.8758 | 0.9759 |
| 0.2296 | 3.0 | 1875 | 0.1861 | 0.8642 | 0.9103 | 0.8866 | 0.9776 |
| 0.1373 | 4.0 | 2500 | 0.1760 | 0.8876 | 0.9172 | 0.9022 | 0.9803 |
| 0.1117 | 5.0 | 3125 | 0.1694 | 0.8899 | 0.9212 | 0.9053 | 0.9803 |
| 0.0905 | 6.0 | 3750 | 0.1654 | 0.8878 | 0.9201 | 0.9036 | 0.9800 |
| 0.0871 | 7.0 | 4375 | 0.1690 | 0.8887 | 0.9221 | 0.9051 | 0.9802 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.23.1