Conda: Column-Normalized Adam for Training Large Language Models Faster

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Junjie, Zhou, Pan, Dong, Yiming, Li, Huan, Li, Jia, Zhou, Xun, Lao, Qicheng, Fang, Cong, Lin, Zhouchen
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.24218