Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, Dario Amodei

arXiv preprint

Establishes power-law scaling relationships between language model performance and model size, dataset size, and compute, spanning seven orders of magnitude.

https://arxiv.org/abs/2001.08361