---
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Prompt-Guard-finetuned-ctf-86M
  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. -->

# Prompt-Guard-finetuned-ctf-86M

This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0921
- Accuracy: 0.9821

## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6515        | 1.0   | 57   | 0.7140          | 0.4643   |
| 0.5774        | 2.0   | 114  | 0.5967          | 0.5848   |
| 0.4838        | 3.0   | 171  | 0.4644          | 0.8661   |
| 0.4139        | 4.0   | 228  | 0.3317          | 0.9196   |
| 0.308         | 5.0   | 285  | 0.2373          | 0.9420   |
| 0.3184        | 6.0   | 342  | 0.2032          | 0.9464   |
| 0.2798        | 7.0   | 399  | 0.1511          | 0.9643   |
| 0.2094        | 8.0   | 456  | 0.1347          | 0.9643   |
| 0.1627        | 9.0   | 513  | 0.0921          | 0.9821   |
| 0.1539        | 10.0  | 570  | 0.0948          | 0.9777   |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.5.0+cu124
- Datasets 2.18.0
- Tokenizers 0.19.1