← All works
Research paper

Scaling Laws for Neural Language Models

At a glance

Measured predictable links between language-model performance, model size, data and computation.

In one paragraph

Measured how language model performance changes with model size, training data and computation, finding predictable relationships that helped guide how to allocate resources for training.

Authors 10

  1. Jared Kaplan
  2. Sam McCandlish
  3. Tom Henighan
  4. Tom Brown
  5. Benjamin Chess
  6. Rewon Child
  7. Scott Gray
  8. Alec Radford
  9. Jeffrey Wu
  10. Dario Amodei