QFFT-S1-7B

<!-- 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. -->

7b_isntruct_pretrain

This model is a fine-tuned version of Qwen2.5-7B-Instruct on the S1_QFFT dataset.

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: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 1
• total_train_batch_size: 8
• total_eval_batch_size: 32
• 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: 6

Training results

Framework versions

• Transformers 4.48.2
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0

📖 Citation

@misc{liu2025qfft,
  title={QFFT, Question-Free Fine-Tuning for Adaptive Reasoning},
  author={Wanlong Liu and Junxiao Xu and Fei Yu and Yukang Lin and Ke Ji and Wenyu Chen and Yan Xu and Yasheng Wang and Lifeng Shang and Benyou Wang},
  year={2025},
  eprint={2506.12860},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2506.12860},
}