"test/vscode:/vscode.git/clone" did not exist on "27598fab2274e3bb1d5318832e9efcac37d7166f"
  1. 16 Apr, 2019 1 commit
    • Abhi Sharma's avatar
      Fix gradient overflow issue during attention mask · 9e666aaa
      Abhi Sharma authored
      This fix is in reference to issue #382. GPT2 can now be trained in mixed precision, which I've confirmed with testing. I also tested unconditional generation on multiple seeds before and after changing 1e10 to 1e4 and there was no difference. Please let me know if there is anything else I can do to make this pull request better. Thanks for all your work!
      9e666aaa
  2. 15 Apr, 2019 3 commits
  3. 27 Mar, 2019 1 commit
  4. 24 Mar, 2019 5 commits
  5. 14 Mar, 2019 1 commit
  6. 06 Mar, 2019 1 commit
  7. 23 Feb, 2019 1 commit
  8. 22 Feb, 2019 1 commit
  9. 18 Feb, 2019 2 commits
  10. 17 Feb, 2019 3 commits
  11. 09 Feb, 2019 1 commit
  12. 08 Feb, 2019 3 commits
  13. 07 Feb, 2019 1 commit
  14. 05 Feb, 2019 1 commit
  15. 29 Jan, 2019 3 commits
  16. 28 Jan, 2019 3 commits
  17. 15 Jan, 2019 1 commit
  18. 08 Jan, 2019 4 commits
  19. 07 Jan, 2019 1 commit