@article{chang-etal-2024-characterizing,
    title = "Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability",
    author = "Chang, Tyler A.  and
      Tu, Zhuowen  and
      Bergen, Benjamin K.",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "12",
    year = "2024",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.tacl-1.74/",
    doi = "10.1162/tacl_a_00708",
    pages = "1346--1362"
}