@article{hagele2024scaling, Author = {Alexander H\"agele and Elie Bakouch and Atli Kosson and Loubna Ben Allal and Leandro Von Werra and Martin Jaggi}, Title = {{Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations}}, Eprint = {2405.18392v1}, ArchivePrefix = {arXiv}, PrimaryClass = {cs.LG}, Year = {2024}, Month = {May}, Url = {http://arxiv.org/abs/2405.18392}, File = {2405.18392v1.pdf} }