metadata
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: []
PII-Binary-Filter-Extreme-Recall
This model is a fine-tuned version of 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