Why it matters
Chinchilla revised scaling. Understanding shapes modern training.
Advertisement
The architecture
Fit L(N, D) properly.
Optimize under fixed compute.
N proportional to sqrt(C), D proportional to sqrt(C).
Advertisement
How it works end to end
Rerun Kaplan with proper HP tuning.
Chinchilla 70B > Gopher 280B on same compute.
~20 tokens/param compute-optimal.