learn.ifs.name

OLMo: Accelerating the Science of Language Models

Groeneveld et al., 2024, OLMo (Proceedings of the 62nd Annual Meeting of ACL (Volume 1: Long Papers))

Subscriber deck — free during early access

1 cards in “4.2 Intrinsic language modeling evaluation” · whole deck

4.2 Intrinsic language modeling evaluation

  1. What did Paloma show about sample efficiency across text sources?
    Models fit best the kinds of text they were trained on: OLMo-7B was best on C4 (close to its Common-Crawl-heavy data) but less efficient on Wikipedia and scientific papers, which are scarcer than web text; keeping fit to such curated sources will be hard as corpora scale.
    • Groeneveld et al., 2024, OLMo (Proceedings of the 62nd Annual Meeting of ACL (Volume 1: Long Papers)), §4.2, p. 15795

Source

  • Dirk Groeneveld, Iz Beltagy, Evan Walsh, Akshita Bhagia, Rodney Kinney, Oyvind Tafjord, Ananya Jha, Hamish Ivison, Ian Magnusson, Yizhong Wang, Shane Arora, David Atkinson, Russell Authur, Khyathi Chandu, Arman Cohan, Jennifer Dumas, Yanai Elazar, Yuling Gu, Jack Hessel, Tushar Khot, William Merrill, Jacob Morrison, Niklas Muennighoff, Aakanksha Naik, Crystal Nam, Matthew Peters, Valentina Pyatkin, Abhilasha Ravichander, Dustin Schwenk, Saurabh Shah, William Smith, Emma Strubell, Nishant Subramani, Mitchell Wortsman, Pradeep Dasigi, Nathan Lambert, Kyle Richardson, Luke Zettlemoyer, Jesse Dodge, Kyle Lo, Luca Soldaini, Noah Smith and Hannaneh Hajishirzi. 2024. OLMo: Accelerating the Science of Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 15789–15809. License: CC BY 4.0. Flashcards adapted from this work. doi:10.18653/v1/2024.acl-long.841 https://aclanthology.org/2024.acl-long.841/