README.md

---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- llama-factory
- generated_from_trainer
model-index:
- name: WritingBench-Writing-Model-7b
  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. -->

# Writing-Model-Qwen-7b

<p align="center">
  📃 <a href="https://arxiv.org/abs/2503.05244" target="_blank">[Paper]</a> • 🚀 <a href="https://github.com/X-PLUG/WritingBench" target="_blank">[Github Repo]</a> • 📏 <a href="https://huggingface.co/AQuarterMile/WritingBench-Critic-Model-Qwen-7B" target="_blank">[Critic Model]</a> • ✍️ <a href="https://huggingface.co/AQuarterMile/Writing-Model-Qwen-7B" target="_blank">[Writing Model]</a>
</p>

This model is fine-tuned from [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on a 12K SFT dataset for writing evaluation tasks.


## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 7e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 256
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5

### Framework versions

- Transformers 4.46.1
- Pytorch 2.4.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3

## 📝 Citation

```
@misc{wu2025writingbench,
      title={WritingBench: A Comprehensive Benchmark for Generative Writing}, 
      author={Yuning Wu and Jiahao Mei and Ming Yan and Chenliang Li and SHaopeng Lai and Yuran Ren and Zijia Wang and Ji Zhang and Mengyue Wu and Qin Jin and Fei Huang},
      year={2025},
      url={https://arxiv.org/abs/2503.05244}, 
}
```