@article{communicationefficientlanguagemodel, title = {Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo}, author = {Zachary Charles and Gabriel Teston and Lucio Dery and Keith Rush and Nova Fallen and Zachary Garrett and Arthur Szlam and Arthur Douillard}, year = {2025}, eprint = {2503.09799}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.09799v1}, }