metadata

base_model: Qwen/Qwen2.5-7B-Instruct
library_name: transformers
license: apache-2.0
tags:
  - llama-factory
  - generated_from_trainer
pipeline_tag: text-generation
model-index:
  - name: WritingBench-Critic-Model-Qwen-7B
    results: []

WritingBench-Critic-Model-Qwen-7B

📃 [Paper] • 🚀 [Github Repo] • 📏 [Critic Model] • ✍️ [Writer-7B] [Writer-32B]

This model is fine-tuned from Qwen/Qwen2.5-7B-Instruct on a 50K SFT dataset for writing evaluation tasks.

For each criterion, the evaluator independently assigns a score on a 10-point scale to a response, providing both a score and a justification.

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: 8
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 64
optimizer: Use OptimizerNames.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: 3

Framework versions

Transformers 4.46.1
Pytorch 2.5.1+cu124
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}, 
}