cs.AI updates on arXiv.org 22小时前
EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

文章提出了一种名为BEMA的偏置校正指数移动平均方法,用于解决语言模型微调中的随机性问题,通过实验证明其相较于传统EMA和vanilla训练,在多种标准语言模型基准测试中具有更快的收敛速度和更高的最终性能。

arXiv:2508.00180v1 Announce Type: cross Abstract: Stochasticity in language model fine-tuning, often caused by the small batch sizes typically used in this regime, can destabilize training by introducing large oscillations in generation quality. A popular approach to mitigating this instability is to take an Exponential moving average (EMA) of weights throughout training. While EMA reduces stochasticity, thereby smoothing training, the introduction of bias from old iterates often creates a lag in optimization relative to vanilla training. In this work, we propose the Bias-Corrected Exponential Moving Average (BEMA), a simple and practical augmentation of EMA that retains variance-reduction benefits while eliminating bias. BEMA is motivated by a simple theoretical model wherein we demonstrate provable acceleration of BEMA over both a standard EMA and vanilla training. Through an extensive suite of experiments on Language Models, we show that BEMA leads to significantly improved convergence rates and final performance over both EMA and vanilla training in a variety of standard LM benchmarks, making BEMA a practical and theoretically motivated intervention for more stable and efficient fine-tuning.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

BEMA 语言模型微调 随机性 指数移动平均 优化
相关文章