@article{scalinglawforlanguagemodelstraining,
  title = {Scaling Law for Language Models Training Considering Batch Size},
  author = {Xian Shuai and Yiding Wang and Yimeng Wu and Xin Jiang and Xiaozhe Ren},
  year = {2024},
  eprint = {2412.01505},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.01505v1},
}