---
base_model: Qwen/Qwen2.5-1.5B
library_name: peft
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: qwen2.5-hh-rm
  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. -->

# qwen2.5-hh-rm

This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8474
- Accuracy: 0.5493

## 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: 0.0003
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 8
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.5645        | 1.0   | 5310  | 0.7363          | 0.5588   |
| 0.6449        | 2.0   | 10620 | 0.7377          | 0.5521   |
| 0.6083        | 3.0   | 15930 | 0.7829          | 0.5561   |
| 0.6265        | 4.0   | 21240 | 0.7739          | 0.5490   |
| 0.4989        | 5.0   | 26550 | 0.8474          | 0.5493   |


### Framework versions

- PEFT 0.12.0
- Transformers 4.37.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.5
- Tokenizers 0.15.2