---
license: mit
datasets:
- UCLA-AGI/SPIN_iter1
language:
- en
base_model: alignment-handbook/zephyr-7b-sft-full
pipeline_tag: text-generation
---
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models (https://arxiv.org/abs/2401.01335)

# zephyr-7b-sft-full-spin-iter1

This model is a self-play fine-tuned model at iteration 1 from [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) using synthetic data based on on the [HuggingFaceH4/ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) dataset.

## Model Details

### Model Description

- Model type: A 7B parameter GPT-like model fine-tuned on synthetic datasets.
- Language(s) (NLP): Primarily English
- License: MIT
- Finetuned from model: alignment-handbook/zephyr-7b-sft-full (based on mistralai/Mistral-7B-v0.1)

### Training hyperparameters
The following hyperparameters were used during training:

- learning_rate: 5e-07
- train_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- optimizer: RMSProp 
- lr_scheduler_type: linear 
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2.0

## [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_UCLA-AGI__zephyr-7b-sft-full-spin-iter1)
| Metric                | Value                     |
|-----------------------|---------------------------|
| Avg.                  | 62.86   |
| ARC (25-shot)         | 65.87          |
| HellaSwag (10-shot)   | 85.44    |
| MMLU (5-shot)         | 60.95         |
| TruthfulQA (0-shot)   | 57.39   |
| Winogrande (5-shot)   | 76.64   |
| GSM8K (5-shot)        | 30.86        |
  
## Citation
```
@misc{chen2024selfplay,
      title={Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models}, 
      author={Zixiang Chen and Yihe Deng and Huizhuo Yuan and Kaixuan Ji and Quanquan Gu},
      year={2024},
      eprint={2401.01335},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}
```