Apparently today is the 4th year anniversary of GPT-3! https://
arxiv.org/abs/2005.14165 Which I am accidentally celebrating by re-training the smallest model in the miniseries right now :). HellaSwag 33.7 (Appendix H) almost reached this a few steps ago (though this is only 45% of the
GPT-3 4th Anniversary: Re-training Smallest Model Achievement
By
–
