Scaling laws for neural language models
Captured source
source ↗Scaling laws for neural language models | OpenAI
January 23, 2020
Scaling laws for neural language models
Loading…
Share
Abstract
We study empirical scaling laws for language model performance on the cross-entropy loss. The loss scales as a power-law with model size, dataset size, and the amount of compute used for training, with some trends spanning more than seven orders of magnitude. Other architectural details such as network width or depth have minimal effects within a wide range. Simple equations govern the dependence of overfitting on model/dataset size and the dependence of training speed on model size. These relationships allow us to determine the optimal allocation of a fixed compute budget. Larger models are significantly more sample-efficient, such that optimally compute-efficient training involves training very large models on a relatively modest amount of data and stopping significantly before convergence.
Authors
Jared Kaplan, Sam McCandlish, Tom Henighan, Tom Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, Dario Amodei
Related articles
Deep double descentPublicationDec 5, 2019
How AI training scalesMilestoneDec 14, 2018
Embedding AI into developer softwareMar 21, 2024