@article{powerschedulerabatchsizeandtokennumber, title = {Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler}, author = {Yikang Shen and Matthew Stallone and Mayank Mishra and Gaoyuan Zhang and Shawn Tan and Aditya Prasad and Adriana Meza Soria and David D. Cox and Rameswar Panda}, year = {2024}, eprint = {2408.13359}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.13359v2}, }