• Model creator: https://huggingface.co/UCLA-AGI/
• Original model: https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3/

Original model description:

• en license: apache-2.0 datasets:
• openbmb/UltraFeedback pipeline_tag: text-generation model-index:
• name: Llama-3-Instruct-8B-SPPO-Iter3 results:
  • task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics:
    • type: inst_level_strict_acc and prompt_level_strict_acc value: 68.28 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics:
    • type: acc_norm value: 29.74 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics:
    • type: exact_match value: 7.33 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics:
    • type: acc_norm value: 2.01 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics:
    • type: acc_norm value: 3.09 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics:
    • type: acc value: 29.38 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 name: Open LLM Leaderboard

Llama-3-Instruct-8B-SPPO-Iter3

Links to Other Models

• Llama-3-Instruct-8B-SPPO-Iter1
• Llama-3-Instruct-8B-SPPO-Iter2
• Llama-3-Instruct-8B-SPPO-Iter3

Model Description

• Model type: A 8B parameter GPT-like model fine-tuned on synthetic datasets.
• Language(s) (NLP): Primarily English
• License: Apache-2.0
• Finetuned from model: meta-llama/Meta-Llama-3-8B-Instruct

AlpacaEval Leaderboard Evaluation Results

Open LLM Leaderboard Evaluation Results

Open LLM Leaderboard 2 Evaluation Results

Training hyperparameters

• 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: 6.0 (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}
}