---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2-0.5B-Instruct
tags:
- trl
- reward-trainer
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Qwen2-0.5B-Reward
  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. -->

# Qwen2-0.5B-Reward

This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5139
- Accuracy: 0.723

## 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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 0.6426        | 0.0516 | 50   | 0.6197          | 0.664    |
| 0.5877        | 0.1032 | 100  | 0.6080          | 0.662    |
| 0.5902        | 0.1548 | 150  | 0.5787          | 0.697    |
| 0.5582        | 0.2064 | 200  | 0.5555          | 0.694    |
| 0.5664        | 0.2580 | 250  | 0.5441          | 0.699    |
| 0.5638        | 0.3096 | 300  | 0.5290          | 0.716    |
| 0.5375        | 0.3612 | 350  | 0.5315          | 0.729    |
| 0.5233        | 0.4128 | 400  | 0.5380          | 0.718    |
| 0.5375        | 0.4644 | 450  | 0.5482          | 0.71     |
| 0.5223        | 0.5160 | 500  | 0.5352          | 0.72     |
| 0.5229        | 0.5676 | 550  | 0.5251          | 0.724    |
| 0.5173        | 0.6192 | 600  | 0.5181          | 0.717    |
| 0.5227        | 0.6708 | 650  | 0.5178          | 0.724    |
| 0.5103        | 0.7224 | 700  | 0.5153          | 0.728    |
| 0.5178        | 0.7740 | 750  | 0.5198          | 0.725    |
| 0.5072        | 0.8256 | 800  | 0.5195          | 0.722    |
| 0.5137        | 0.8772 | 850  | 0.5168          | 0.725    |
| 0.4995        | 0.9288 | 900  | 0.5146          | 0.724    |
| 0.4988        | 0.9804 | 950  | 0.5135          | 0.723    |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1