Training Improvements V245

Training improvements: LR warmup, validation intervals, reward weights. Trigger when: (1) training unstable in early epochs, (2) need more validation visibility, (3) model too conservative.

smith6jt-cop Updated 4 repo stars

File contents

smith6jt-cop/Skills_Registry commit 45cb55ea9a

Frequently asked questions

npx get-skill add smith6jt-cop/training-improvements-v245