chinchilla-scaling-law-constants

IN premiseentries/2026/06/21/wiki-Large_language_model-chunk-2.md

Created 2026-06-21T09:50:09+00:00

The Chinchilla scaling law is L = A/N^alpha + B/D^beta + L0 with alpha=0.34, beta=0.28, L0=1.69, and training cost C = 6·N·D FLOPs.

Summary

These are the specific numbers that let the system calculate, for any chosen model size and training budget, exactly how much quality to expect and how much compute it will cost. Without them fixed, any trade-off reasoning between building a bigger model, collecting more data, or spending more compute would have no quantitative anchor.

Dependents

These beliefs depend on this one: