This model was developed using Self-Play Preference Optimization at iteration 3, based on the meta-llama/Meta-Llama-3-8B-Instruct 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.

Links to Other Models

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

Model	LC. Win Rate	Win Rate	Avg. Length
Llama-3-8B-SPPO Iter1	31.73	31.74	1962
Llama-3-8B-SPPO Iter2	35.15	35.98	2021
Llama-3-8B-SPPO Iter3	38.77	39.85	2066

Open LLM Leaderboard Evaluation Results

Results are reported by using lm-evaluation-harness v0.4.1

	arc_challenge	truthfulqa_mc2	winogrande	gsm8k	hellaswag	mmlu	average
Llama-3-8B-SPPO Iter1	63.82	54.96	76.40	75.44	79.80	65.65	69.35
Llama-3-8B-SPPO Iter2	64.93	56.48	76.87	75.13	80.39	65.67	69.91
Llama-3-8B-SPPO Iter3	65.19	58.04	77.11	74.91	80.86	65.60	70.29

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: 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}
}

bullerwins/Llama-3-Instruct-8B-SPPO-Iter3-exl2_5.0bpw

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