Beta. Content is under active construction and has not been peer-reviewed. Report errors on GitHub.Disclaimer

Scaling Laws

3 questionsDifficulty 5-6View topic
Intermediate
0 / 3
3 intermediateAdapts to your performance
1 / 3
intermediate (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?