Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bergsma, Shane, Dey, Nolan, Gosal, Gurpreet, Gray, Gavia, Soboleva, Daria, Hestness, Joel
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language Neural and Evolutionary Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.15938