| --- |
| library_name: transformers |
| license: mit |
| base_model: microsoft/deberta-v3-small |
| tags: |
| - generated_from_trainer |
| metrics: |
| - recall |
| - precision |
| model-index: |
| - name: PII-Binary-Filter-Extreme-Recall |
| 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. --> |
|
|
| # PII-Binary-Filter-Extreme-Recall |
|
|
| This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 2.8377 |
| - F1 At 10 Thresh: 0.7490 |
| - Recall: 0.9871 |
| - Precision: 0.6035 |
| - Trash Caught: 0.1396 |
|
|
| ## 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: 16 |
| - eval_batch_size: 32 |
| - 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: 5 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | F1 At 10 Thresh | Recall | Precision | Trash Caught | |
| |:-------------:|:-----:|:----:|:---------------:|:---------------:|:------:|:---------:|:------------:| |
| | 0.1651 | 1.0 | 1569 | 2.0216 | 0.7403 | 0.9908 | 0.5909 | 0.0900 | |
| | 0.1066 | 2.0 | 3138 | 2.6117 | 0.7482 | 0.9906 | 0.6011 | 0.1279 | |
| | 0.0671 | 3.0 | 4707 | 2.8377 | 0.7490 | 0.9871 | 0.6035 | 0.1396 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.56.0 |
| - Pytorch 2.8.0+cu129 |
| - Tokenizers 0.22.0 |
| |
