@article{spikenomorestabilizingthepretrainingof, title = {Spike No More: Stabilizing the Pre-training of Large Language Models}, author = {Sho Takase and Shun Kiyono and Sosuke Kobayashi and Jun Suzuki}, year = {2023}, eprint = {2312.16903}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.16903v3}, }