Effective Learning Rate Governs Loss Dynamics in Language Model Pretraining
Ranking
Overall
89
Content
100
Popularity
64
Observed public metrics from 1 member.
Merged summary
TL;DR - This paper finds that language-model pretraining loss dynamics are governed mainly by the effective learning rate (ELR), defined as the learning rate relative to parameter norm. Using ELR as a shared coordinate could make scaling laws and training schedules more transferable across optimization and norm-control methods.
- Matching ELR produces nearly identical loss trajectories despite substantially different raw learning rates and parameter norms.
- The effect holds across optimizers, architectures, datasets, and model scales, with typical mean collapse errors of a few Ă— 10^-3.
- Normalization design and the timescale of learning-rate and norm variation determine how precisely trajectories collapse.
- ELR explains how weight decay and Hyperball shape loss dynamics and enables a fitted scaling law to transfer across norm-control methods, including delayed acceleration.
Sources (1)
Effective Learning Rate Governs Loss Dynamics in Language Model Pretraining
Public signals
Semantic Scholar citations 3 · Semantic Scholar influential citations 0
TL;DR - This paper finds that language-model pretraining loss dynamics are governed mainly by the effective learning rate (ELR), defined as the learning rate relative to parameter norm. Using ELR as a shared coordinate could make scaling laws and training schedules more transferable across optimization and norm-control methods.
- Matching ELR produces nearly identical loss trajectories despite substantially different raw learning rates and parameter norms.
- The effect holds across optimizers, architectures, datasets, and model scales, with typical mean collapse errors of a few Ă— 10^-3.
- Normalization design and the timescale of learning-rate and norm variation determine how precisely trajectories collapse.
- ELR explains how weight decay and Hyperball shape loss dynamics and enables a fitted scaling law to transfer across norm-control methods, including delayed acceleration.