--- language: - en license: apache-2.0 datasets: - openbmb/UltraFeedback pipeline_tag: text-generation model-index: - name: Mistral7B-PairRM-SPPO-Iter1 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: 50.47 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=UCLA-AGI/Mistral7B-PairRM-SPPO-Iter1 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: 22.93 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=UCLA-AGI/Mistral7B-PairRM-SPPO-Iter1 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: 2.19 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=UCLA-AGI/Mistral7B-PairRM-SPPO-Iter1 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: 4.47 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=UCLA-AGI/Mistral7B-PairRM-SPPO-Iter1 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: 8.3 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=UCLA-AGI/Mistral7B-PairRM-SPPO-Iter1 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: 18.84 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=UCLA-AGI/Mistral7B-PairRM-SPPO-Iter1 name: Open LLM Leaderboard --- Self-Play Preference Optimization for Language Model Alignment (https://arxiv.org/abs/2405.00675) # Mistral7B-PairRM-SPPO-Iter1 This model was developed using [Self-Play Preference Optimization](https://arxiv.org/abs/2405.00675) at iteration 1, based on the [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) architecture as starting point. We utilized the prompt sets from the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, splited to 3 parts for 3 iterations by [snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset](https://huggingface.co/datasets/snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset). All responses used are synthetic. **This is the model reported in the paper** , with K=5 (generate 5 responses per iteration). We attached the Arena-Hard eval results in this model page. ## Links to Other Models - [Mistral7B-PairRM-SPPO-Iter1](https://huggingface.co/UCLA-AGI/Mistral7B-PairRM-SPPO-Iter1) - [Mistral7B-PairRM-SPPO-Iter2](https://huggingface.co/UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2) - [Mistral7B-PairRM-SPPO-Iter3](https://huggingface.co/UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3) - [Mistral7B-PairRM-SPPO](https://huggingface.co/UCLA-AGI/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](https://tatsu-lab.github.io/alpaca_eval/) | Model | LC. Win Rate | Win Rate | Avg. Length | |-------------------------------------------|:------------:|:--------:|:-----------:| | Mistral7B-PairRM-SPPO Iter 1 | 24.79 | 23.51 | 1855 | | Mistral7B-PairRM-SPPO Iter 2 | 26.89 | 27.62 | 2019 | | Mistral7B-PairRM-SPPO Iter 3 | 28.53 | 31.02 | 2163 | | Mistral7B-PairRM-SPPO Iter 1 (best-of-16) | 28.71 | 27.77 | 1901 | | Mistral7B-PairRM-SPPO Iter 2 (best-of-16) | 31.23 | 32.12 | 2035 | | Mistral7B-PairRM-SPPO Iter 3 (best-of-16) | 32.13 | 34.94 | 2174 | ## [Arena-Hard Evaluation Results](https://github.com/lm-sys/arena-hard) Model | Score | 95% CI | average \# Tokens | |----------|-----------|--------------|-----------| Mistral7B-PairRM-SPPO-Iter3| 23.3 | (-1.8, 1.8)|578| ## [Open LLM Leaderboard Evaluation Results](https://github.com/EleutherAI/lm-evaluation-harness) Results are reported by using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) v0.4.1 | | arc_challenge | truthfulqa_mc2 | winogrande | gsm8k | hellaswag | mmlu | average | |--------|---------------|----------------|------------|-------|-----------|-------|---------| | Mistral7B-PairRM-SPPO Iter 1 | 65.02 | 69.4 | 77.82 | 43.82 | 85.11 | 58.84 | 66.67 | | Mistral7B-PairRM-SPPO Iter 2 | 65.53 | 69.55 | 77.03 | 44.35 | 85.29 | 58.72 | 66.75 | | Mistral7B-PairRM-SPPO Iter 3 | 65.36 | 69.97 | 76.8 | 42.68 | 85.16 | 58.45 | 66.4 | ## [MT-Bench Evaluation Results](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge) | | 1st Turn | 2nd Turn | Average | |--------|----------|----------|---------| | Mistral7B-PairRM-SPPO Iter 1 | 7.63 | 6.79 | 7.21 | | Mistral7B-PairRM-SPPO Iter 2 | 7.90 | 7.08 | 7.49 | | Mistral7B-PairRM-SPPO Iter 3 | 7.84 | 7.34 | 7.59 | ### 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: 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} } ``` # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_UCLA-AGI__Mistral7B-PairRM-SPPO-Iter1) | Metric |Value| |-------------------|----:| |Avg. |17.87| |IFEval (0-Shot) |50.47| |BBH (3-Shot) |22.93| |MATH Lvl 5 (4-Shot)| 2.19| |GPQA (0-shot) | 4.47| |MuSR (0-shot) | 8.30| |MMLU-PRO (5-shot) |18.84|