@inproceedings{mircea-etal-2025-training,
    title = "Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning",
    author = "Mircea, Andrei  and
      Chakraborty, Supriyo  and
      Chitsazan, Nima  and
      Rish, Irina  and
      Lobacheva, Ekaterina",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1366/",
    pages = "28154--28188",
    ISBN = "979-8-89176-251-0"
}