@article{curriculumlearningaregularizationmethod, title = {The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models}, author = {Conglong Li and Minjia Zhang and Yuxiong He}, year = {2021}, eprint = {2108.06084}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2108.06084v4}, }