arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.01003cs.LGcs.AI
收藏

ESSAM:一种用于内存高效的LLM微调的强化学习竞争进化策略方法

ESSAM: A Novel Competitive Evolution Strategies Approach to Reinforcement Learning for Memory Efficient LLMs Fine-Tuning

Xi’an Jiaotong University(西安交通大学);SGIT AI Lab(SGIT人工智能实验室)

Zhishen Sun, Sizhe Dang, Guang Dai, Haishan Ye

AI总结:

本文提出ESSAM,结合进化策略的零阶搜索与SAM提升泛化能力,实现低内存高精度的LLM微调,实验显示其在GSM8K任务中表现优异,内存使用显著降低。

摘要:

强化学习(RL)已成为提升大语言模型(LLM)数学推理能力的关键训练步骤,但通常具有高GPU内存使用率,限制了资源受限环境的应用。为解决这些问题,我们提出了进化策略与尖锐度感知最大化(ESSAM),一种完全参数微调框架,紧密结合进化策略(ES)中的参数空间零阶搜索与SAM,以提高泛化能力。我们在主流数学推理任务GSM8K上进行了微调实验。结果表明,ESSAM在所有模型上的平均准确率为78.27%,其整体性能与RL方法相当。它在准确率为77.72%时优于经典RL算法PPO,并在准确率为78.34%时与GRPO相当,甚至在某些模型上超越它们。进一步的泛化实验显示,使用ESSAM训练的模型表现出更强的泛化能力。它们的平均性能在6个数据集中有5个取得最佳结果,表明ESSAM能有效提升微调模型的泛化性能。在GPU内存使用方面,与PPO相比,ESSAM将平均GPU内存使用减少了18倍,与GRPO相比减少了10倍,实现了极低的GPU内存使用。此外,我们设计了一种加速的ESSAM变体,实现了近两倍的速度提升,同时保持与ESSAM相同的GPU内存使用,平均准确率为78.02%,优于PPO。代码:https://github.com/szs777/ESSAM

英文摘要:

Reinforcement learning (RL) has become a key training step for improving mathematical reasoning in large language models (LLMs), but it often has high GPU memory usage, which makes it hard to use in settings with limited resources. To reduce these issues, we propose Evolution Strategies with Sharpness-Aware Maximization (ESSAM), a full parameter fine-tuning framework that tightly combines the zero-order search in parameter space from Evolution Strategies (ES) with the Sharpness-Aware Maximization (SAM) to improve generalization. We conduct fine-tuning experiments on the mainstream mathematica reasoning task GSM8K. The results show that ESSAM achieves an average accuracy of 78.27\% across all models and its overall performance is comparable to RL methods. It surpasses classic RL algorithm PPO with an accuracy of 77.72\% and is comparable to GRPO with an accuracy of 78.34\%, and even surpassing them on some models. Further generalization experiments show that the models trained with ESSAM exhibit stronger generalization ability. Their average performance achieves the best results on 5 out of 6 datasets, indicating that ESSAM can effectively improve the generalization performance of fine-tuned models. In terms of GPU memory usage, ESSAM reduces the average GPU memory usage by $18\times$ compared to PPO and by $10\times$ compared to GRPO, achieving an extremely low GPU memory usage. In addition, we design an accelerated variant of ESSAM, which achieves nearly a twofold speedup while maintaining the same GPU memory usage as ESSAM, and attains an average accuracy of 78.02\% across all models, outperforming PPO. Code: https://github.com/szs777/ESSAM

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑