@misc{gao2024train,
  title={How to Train Long-Context Language Models (Effectively)},
  author={Tianyu Gao and Alexander Wettig and Howard Yen and Danqi Chen},
  year={2024},
  eprint={2410.02660},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2410.02660}
}