GitHub Trending repo Repositories Sep 10 4 views

Alpha-Park/genpark-adamw-decoupled-weight-decay-skill: AdamW optimizer engine decoupling L2 weight decay regularization from adaptive gradient first and second moments.

by Alpha-Park

AdamW optimizer engine decoupling L2 weight decay regularization from adaptive gradient first and second moments.

Read Original

Metadata

Stars
7
Language
Python
Watchers
7

Related