Saved in:
Bibliographic Details
Main Author: Defazio, Aaron
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.02285
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • During long-duration Large Language Model (LLM) training runs the gradient norm increases rapidly near the end of training. In this short note, we show that this increase is due to an unintended interaction between weight decay, normalization layers, and the learning rate schedule. We propose a simple correction that fixes this behavior while also resulting in lower loss values throughout training.