Skip to content

GitLab

"tests/test_modeling_tf_distilbert.py" did not exist on "067395d5c56ef9026c442e691b6458ac196e3cf9"
Switch branch/tag
  1. 17 Jun, 2019 1 commit
  3. 14 Jun, 2019 1 commit
  5. 01 Jun, 2019 2 commits
  7. 08 May, 2019 3 commits
  9. 07 May, 2019 2 commits
  11. 30 Apr, 2019 3 commits
  13. 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
  15. 15 Apr, 2019 3 commits
  17. 27 Mar, 2019 1 commit
  19. 24 Mar, 2019 5 commits
  21. 14 Mar, 2019 1 commit
  23. 06 Mar, 2019 1 commit
  25. 23 Feb, 2019 1 commit
  27. 22 Feb, 2019 1 commit
  29. 18 Feb, 2019 2 commits
  31. 17 Feb, 2019 3 commits
  33. 09 Feb, 2019 1 commit
  35. 08 Feb, 2019 3 commits
  37. 07 Feb, 2019 1 commit
  39. 05 Feb, 2019 1 commit
  41. 29 Jan, 2019 3 commits