@misc{dl-05-1,
  title = {{Scaling Laws for Neural Language Models}},
  author = {Kaplan, Jared and McCandlish, Sam and Henighan, Tom and Brown, Tom B. and Chess, Benjamin and Child, Rewon and Gray, Scott and Radford, Alec and Wu, Jeffrey and Amodei, Dario},
  howpublished = {arXiv:2001.08361},
  year = {2020},
  doi = {10.48550/arXiv.2001.08361},
  url = {https://arxiv.org/abs/2001.08361}
}

@misc{dl-05-2,
  title = {{Training Compute-Optimal Large Language Models}},
  author = {Hoffmann, Jordan and Borgeaud, Sebastian and Mensch, Arthur and Buchatskaya, Elena and Cai, Trevor and Rutherford, Eliza and de Las Casas, Diego and Hendricks, Lisa Anne and Welbl, Johannes and Clark, Aidan and Hennigan, Tom and Noland, Eric and Millican, Katie and van den Driessche, George and Damoc, Bogdan and Guy, Aurelia and Osindero, Simon and Simonyan, Karen and Elsen, Erich and Rae, Jack W. and Vinyals, Oriol and Sifre, Laurent},
  howpublished = {arXiv:2203.15556},
  year = {2022},
  doi = {10.48550/arXiv.2203.15556},
  url = {https://arxiv.org/abs/2203.15556}
}

@article{dl-05-3,
  title = {{Explaining Neural Scaling Laws}},
  author = {Bahri, Yasaman and Dyer, Ethan and Kaplan, Jared and Lee, Jaehoon and Sharma, Utkarsh},
  journal = {Proceedings of the National Academy of Sciences 121(27), e2311878121},
  year = {2024},
  doi = {10.1073/pnas.2311878121},
  url = {https://arxiv.org/abs/2102.06701}
}