---
license: mit
base_model: microsoft/deberta-v3-large
tags:
- trl
- reward-trainer
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: deberta-v3-large-reward-model
  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. -->

# deberta-v3-large-reward-model

This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co./microsoft/deberta-v3-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0106
- Accuracy: 0.995

## 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: 1.41e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.0213        | 2.0   | 100  | 0.0205          | 0.995    |
| 0.002         | 4.0   | 200  | 0.0128          | 0.995    |
| 0.0005        | 6.0   | 300  | 0.0107          | 0.995    |
| 0.0001        | 8.0   | 400  | 0.0110          | 0.995    |
| 0.0001        | 10.0  | 500  | 0.0106          | 0.995    |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1