dl-2-hw-2-bert-finetuned-ner-baseline
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: 0.0923
- Precision: 0.8692
- Recall: 0.9116
- F1: 0.8899
- Accuracy: 0.9786
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 128
- 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.7734 | 1.0 | 313 | 0.3862 | 0.4400 | 0.5485 | 0.4883 | 0.9180 |
| 0.3147 | 2.0 | 626 | 0.2288 | 0.7071 | 0.7460 | 0.7261 | 0.9521 |
| 0.2179 | 3.0 | 939 | 0.1746 | 0.7651 | 0.8270 | 0.7948 | 0.9630 |
| 0.1701 | 4.0 | 1252 | 0.1426 | 0.8250 | 0.8728 | 0.8482 | 0.9717 |
| 0.1407 | 5.0 | 1565 | 0.1252 | 0.8413 | 0.8877 | 0.8639 | 0.9742 |
| 0.1186 | 6.0 | 1878 | 0.1132 | 0.8546 | 0.8958 | 0.8747 | 0.9761 |
| 0.1039 | 7.0 | 2191 | 0.1064 | 0.8552 | 0.9004 | 0.8772 | 0.9768 |
| 0.093 | 8.0 | 2504 | 0.1023 | 0.8536 | 0.9015 | 0.8769 | 0.9769 |
| 0.0837 | 9.0 | 2817 | 0.0961 | 0.8680 | 0.9056 | 0.8864 | 0.9789 |
| 0.0775 | 10.0 | 3130 | 0.0953 | 0.8716 | 0.9079 | 0.8894 | 0.9787 |
| 0.0731 | 11.0 | 3443 | 0.0950 | 0.8638 | 0.9081 | 0.8854 | 0.9778 |
| 0.0688 | 12.0 | 3756 | 0.0923 | 0.8692 | 0.9116 | 0.8899 | 0.9786 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.11.0+cu128
- Datasets 3.4.1
- Tokenizers 0.21.4