Skip to main content

Scaling Laws

3 selectedDifficulty 5-63 unseenView topic
IntermediateNew
0 answered
3 intermediateAdapts to your performance
Question 1 of 3
120sintermediate (5/10)conceptual
The Chinchilla scaling law (Hoffmann et al., 2022) found that compute-optimal training allocates a fixed ratio between model parameters and training tokens . What is the approximate relationship?