✳flâneur — a map of the web's best reading

[2403.05812] Algorithmic progress in language models

arxiv.org · 648 words · saved by 1 readers

Abstract:We investigate the rate at which algorithms for pre-training language models have improved since the advent of deep learning. Using a dataset of over 200 language model evaluations on Wikitext and Penn Treebank spanning 2012-2023, we find that the compute required to reach a set performance threshold has halved approximately every 8 months, with a 95% confidence interval of around 5 to 14 months, substantially faster than hardware gains per Moore's Law. We estimate augmented scaling laws, which enable us to quantify algorithmic progress and determine the relative contributions of scaling models versus innovations in training algorithms. Despite the rapid pace of algorithmic progress and the development of new architectures such as the transformer, our analysis reveals that the increase in compute made an even larger contribution to overall performance improvements over this time period. Though limited by noisy benchmark data, our analysis quantifies the rapid progress in language modeling, shedding light on the relative contributions from compute and algorithms.

[2403.05812] Algorithmic progress in language models Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2403.05812 (cs) [Submitted on 9 Mar 2024] Title: Algorithmic progress in language models Authors: Anson Ho , Tamay Besiroglu , Ege Erdil , David Owen , Robi Rahman , Zifan Carl Guo , David Atkinson , Neil Thompson , Jaime Sevilla View a PDF of the paper titled Algorithmic progress in language models, by Anson Ho and 8 other authors View PDF HTML (exper

Explore this link on the map →

related reading