UCLA-AGI/Mistral7B-PairRM-SPPO

Self-Play Preference Optimization for Language Model Alignment (https://arxiv.org/abs/2405.00675)

Mistral7B-PairRM-SPPO

This model was developed using Self-Play Preference Optimization, based on the mistralai/Mistral-7B-Instruct-v0.2 architecture as starting point. We utilized the prompt sets from the openbmb/UltraFeedback dataset, splited to 3 parts for 3 iterations by snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset. All responses used are synthetic.

While K = 5, this model uses three samples to estimate the soft probabilities P(yw > yl) and P(yl > yw). These samples include the winner, the loser, and another random sample. This approach has shown to deliver better performance on AlpacaEval 2.0 compared to the results reported in our paper.

❗Please refer to the original checkpoint at **UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3** as reported in our paper. We anticipate that the version in the paper demonstrates a more consistent performance improvement across all evaluation tasks.

Links to Other Models

• —Mistral7B-PairRM-SPPO-Iter1
• —Mistral7B-PairRM-SPPO-Iter2
• —Mistral7B-PairRM-SPPO-Iter3
• —Mistral7B-PairRM-SPPO

Model Description

• —Model type: A 7B parameter GPT-like model fine-tuned on synthetic datasets.
• —Language(s) (NLP): Primarily English
• —License: Apache-2.0
• —Finetuned from model: mistralai/Mistral-7B-Instruct-v0.2

AlpacaEval Leaderboard Evaluation Results

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 5e-07
• —eta: 1000
• —perdevicetrainbatchsize: 8
• —gradientaccumulationsteps: 1
• —seed: 42
• —distributedtype: deepspeedzero3
• —num_devices: 8
• —optimizer: RMSProp
• —lrschedulertype: linear
• —lrschedulerwarmup_ratio: 0.1
• —numtrainepochs: 18.0 (stop at epoch=1.0)

Citation

@misc{wu2024self,
      title={Self-Play Preference Optimization for Language Model Alignment}, 
      author={Wu, Yue and Sun, Zhiqing and Yuan, Huizhuo and Ji, Kaixuan and Yang, Yiming and Gu, Quanquan},
      year={2024},
      eprint={2405.00675},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}