| --- |
| library_name: transformers |
| license: mit |
| base_model: BAAI/bge-small-en-v1.5 |
| tags: |
| - generated_from_trainer |
| metrics: |
| - precision |
| - recall |
| - f1 |
| - accuracy |
| model-index: |
| - name: dl2_ner_hw2 |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # dl2_ner_hw2 |
|
|
| This model is a fine-tuned version of [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0814 |
| - Precision: 0.8982 |
| - Recall: 0.9239 |
| - F1: 0.9109 |
| - Accuracy: 0.9814 |
|
|
| ## 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 | |
| |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
| | 0.4629 | 1.0 | 625 | 0.1731 | 0.7698 | 0.8211 | 0.7946 | 0.9629 | |
| | 0.1715 | 2.0 | 1250 | 0.1127 | 0.8544 | 0.8921 | 0.8729 | 0.9757 | |
| | 0.1158 | 3.0 | 1875 | 0.0934 | 0.8609 | 0.9093 | 0.8844 | 0.9774 | |
| | 0.0687 | 4.0 | 2500 | 0.0858 | 0.8854 | 0.9150 | 0.8999 | 0.9803 | |
| | 0.0559 | 5.0 | 3125 | 0.0845 | 0.8817 | 0.9185 | 0.8998 | 0.9790 | |
| | 0.0454 | 6.0 | 3750 | 0.0811 | 0.8853 | 0.9196 | 0.9021 | 0.9798 | |
| | 0.0432 | 7.0 | 4375 | 0.0816 | 0.8876 | 0.9226 | 0.9048 | 0.9802 | |
| | 0.0336 | 8.0 | 5000 | 0.0815 | 0.8983 | 0.9231 | 0.9105 | 0.9813 | |
| | 0.0304 | 9.0 | 5625 | 0.0816 | 0.9005 | 0.9241 | 0.9121 | 0.9815 | |
| | 0.0296 | 10.0 | 6250 | 0.0814 | 0.8982 | 0.9239 | 0.9109 | 0.9814 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.51.3 |
| - Pytorch 2.11.0+cu128 |
| - Datasets 3.4.1 |
| - Tokenizers 0.21.4 |
|
|
