EPISODE · Apr 26, 2026 · 11 MIN
Training Compute-Optimal Large Language Models: The Chinchilla Lesson
from Mastering Language Models: From Architecture to Optimization
A deep dive into Chinchilla and compute-optimal training, explaining why many large models were undertrained and why tokens should scale with parameters.
NOW PLAYING
Training Compute-Optimal Large Language Models: The Chinchilla Lesson
No transcript for this episode yet
Similar Episodes
Mar 26, 2026 ·1m
Mar 19, 2026 ·34m
Feb 18, 2026 ·11m
Feb 11, 2026 ·45m