flâneur — a map of the web's best reading

The Practitioner's Guide to the Maximal Update Parameterization | EleutherAI Blog

blog.eleuther.ai · 5,057 words · saved by 3 readers

Exploring the implementation details of muTransfer

Table of Contents Introduction Why you should use μP 1. Stable optimum HPs across scale (μTransfer) 2. Improved loss at large scale due to improved HP tuning 3. Stable training - significantly decreased danger of instability at large scale 4. More predictable scaling due to μTransfer μP enables better research A Simple Approach to the μP Math Basic Building Block: Controlled Activation Magnitudes Operations in a training step Practitioner's guide to μP Implementation Coordinate check test μTransfer test Transferring optimal HPs from a small scale to a large scale Conclusion Citation Footnotes

Explore this link on the map →

saved by

related reading