---
library_name: transformers
license: other
base_model: Qwen/Qwen2.5-3B-Instruct
tags:
- trl
- reward-trainer
- generated_from_trainer
model-index:
- name: Qwen2.5-3B-MP-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. -->

# Qwen2.5-3B-MP-RM

This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the [iqwiki-kor/MP-86k](https://huggingface.co/datasets/iqwiki-kor/MP-86k) dataset.

## RewardBench Evaluation
| Model                                                                                               | Chat | Chat-Hard | Safety | Reasoning | Avg. |
|-----------------------------------------------------------------------------------------------------|---------:|-------:|------:|--------:|--------:|
| [iqwiki-kor/Qwen2.5-3B-MP-RM](https://huggingface.co/iqwiki-kor/Qwen2.5-3B-MP-RM)        |89.1| 75.2| 87.3| 95.4| 86.8|
| [RLHFlow/ArmoRM-Llama3-8B-v0.1](https://huggingface.co/RLHFlow/ArmoRM-Llama3-8B-v0.1)                         |96.9 |76.8 |90.5 |97.3 |90.4|



### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1