The
Step 1 — measure loss against one knob, holding the others abundant. Vary the
parameter count
where
Step 2 — take logs, and the curve becomes a line. A power law is a straight
line in log–log coordinates. Take
Read it as
Step 3 — read off the payoff per 10×. Because the relationship is a power law,
every factor-of-ten increase in
With a typical
Step 4 — the Chinchilla correction: grow N and D together. Given a
fixed compute budget
In practice this lands near 20 training tokens per parameter. The headline finding was that the giant models of the day were badly over-parameterised and under-trained: for the same compute, a smaller model fed far more data wins.
The reason scaling laws are a planning tool, not just an observation, is that a
straight line extrapolates. Fit the loss at a handful of small, cheap models, draw the line on
log–log axes, and extend it: you get a quantitative forecast of the loss at a model
But a power law in test loss is not a power law in usefulness. The smooth loss curve
hides discontinuities in behaviour: some abilities stay flat then jump (emergence), and the
line eventually bends — you hit the
irreducible loss (the entropy of language itself, a constant added term
A smooth power law in test loss is real and well-documented — but it is a claim about loss, not a guarantee about every skill you might care about. It is tempting to read “loss improves predictably with scale” as “every downstream task improves predictably with scale”, and that second claim does not automatically follow.
On some benchmarks, measured accuracy stays near chance for a long stretch of scale and then rises sharply once the model crosses some threshold, rather than climbing smoothly the whole way — sometimes called an emergent ability. Whether this is a genuine discontinuity in the underlying capability, or an artefact of how the metric is scored (a smooth improvement in probability can look like a sudden jump if the score is a hard right/wrong count), is an active and debated question among researchers. Either way, the practical lesson is caution: a beautifully straight line for loss does not license extrapolating a straight line for “can this model do my task” — that has to be measured, not assumed.
Both axes are logarithmic: the horizontal is