@article{analyzingreducingtheneedforlearningrate, title = {Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training}, author = {Atli Kosson and Bettina Messmer and Martin Jaggi}, year = {2024}, eprint = {2410.23922}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.23922v1}, }