BibTeX record journals/corr/abs-2309-14322

• > Home > journals/corr/abs-2309-14322

@article{DBLP:journals/corr/abs-2309-14322,
  author       = {Mitchell Wortsman and
                  Peter J. Liu and
                  Lechao Xiao and
                  Katie Everett and
                  Alex Alemi and
                  Ben Adlam and
                  John D. Co{-}Reyes and
                  Izzeddin Gur and
                  Abhishek Kumar and
                  Roman Novak and
                  Jeffrey Pennington and
                  Jascha Sohl{-}Dickstein and
                  Kelvin Xu and
                  Jaehoon Lee and
                  Justin Gilmer and
                  Simon Kornblith},
  title        = {Small-scale proxies for large-scale Transformer training instabilities},
  journal      = {CoRR},
  volume       = {abs/2309.14322},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2309.14322},
  doi          = {10.48550/ARXIV.2309.14322},
  eprinttype    = {arXiv},
  eprint       = {2309.14322},
  timestamp    = {Thu, 04 Jan 2024 13:52:57 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2309-14322.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}