@article{straighttozerowhylinearlydecayingthe,
  title = {Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs},
  author = {Shane Bergsma and Nolan Dey and Gurpreet Gosal and Gavia Gray and Daria Soboleva and Joel Hestness},
  year = {2025},
  eprint = {2502.15938},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.15938v1},
}