Scaling Compute-Optimal Training

2 selectedDifficulty 5-52 unseenView topic

IntermediateNew

0 answered

2 intermediateAdapts to your performance

Question 1 of 2

120sintermediate (5/10)conceptual

The Chinchilla scaling law (Hoffmann et al., 2022) found that compute-optimal training allocates a fixed ratio between model parameters N and training tokens D . What is the approximate relationship?