learning rate

1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Oct 20, 2025 by Elie Bakouch · across every show →

Everything said about learning rate, oldest first

Oct 20, 2025

Insight

Bakouch: Optimizer ablations must wait for full learning rate decay

“Especially when doing optimizer ablation, you never want to look at early curve, and you want to, like, wait for the long rate to have fully decay, and, like, do anything to be to zero, or whatever value.”

Elie Bakouch Oct 20, 2025 ▶ 19:01 ⚡ Open Model Pretraining Masterclass — Elie Bakouch, HuggingFace SmolLM 3, FineWeb, FinePDF

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

learning rate

Everything said about learning rate, oldest first

Turn any episode into a week of clips.