Gemma 2 9B It SPPO Iter3

🚀 Gemma-2-9B-It-SPPO-Iter3

This model is developed using Self-Play Preference Optimization to fine - tune language models, offering high - quality text generation capabilities.

🚀 Quick Start

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

This model was developed using Self-Play Preference Optimization at iteration 3, based on the google/gemma-2-9b-it 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.

Terms of Use: Terms

✨ Features

Links to Other Models

• Gemma-2-9B-It-SPPO-Iter1
• Gemma-2-9B-It-SPPO-Iter2
• Gemma-2-9B-It-SPPO-Iter3

Model Description

AlpacaEval Leaderboard Evaluation Results

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-07
• eta: 1000
• per_device_train_batch_size: 8
• gradient_accumulation_steps: 1
• seed: 42
• distributed_type: deepspeed_zero3
• num_devices: 8
• optimizer: RMSProp
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_train_epochs: 1.0

📄 License

The model is under the Apache - 2.0 license.

📚 Documentation

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}
}