"...lm-evaluation-harness.git" did not exist on "5a5442ffae2a5173ec06600479e62e14d8336d2e"
  1. 15 Apr, 2021 1 commit
  2. 13 Apr, 2021 2 commits
    • A. Unique TensorFlower's avatar
      Internal change · b1aa44d9
      A. Unique TensorFlower authored
      PiperOrigin-RevId: 368260712
      b1aa44d9
    • Reed Wanderman-Milne's avatar
      Use nonexperimental mixed precision API. · 4334a892
      Reed Wanderman-Milne authored
      This replaces symbols in tf.keras.mixed_precision.experimental with the corresponding nonexperimental symbols. In some cases, passing a Policy is replaced with passing a policy name for conciseness.
      
      Additionally, for the Shakespeare model, the loss_scale flag is removed, since supporting it with the nonexperimental API is slightly more verbose and it is recommended users use the default loss scale.
      
      PiperOrigin-RevId: 368123944
      4334a892
  3. 06 Apr, 2021 1 commit
    • Jeremiah Liu's avatar
      Disable temperature scaling during training. · fab47e9e
      Jeremiah Liu authored
      For the `GaussianProcessClassificationHead`, the temperature scaling needs to be disabled during training to avoid unexpected modification to the learning rate, which harms model quality. (Unfortunately, this seems to require adding `training` to the `call` method).
      
      Also set the default of `gp_cov_ridge_penalty` in `RandomFeatureGaussianProcess` to 1 to be consistent with that in the `GaussianProcessClassificationHead`.
      
      PiperOrigin-RevId: 366917075
      fab47e9e
  4. 05 Apr, 2021 1 commit
    • Jeremiah Liu's avatar
      Adds `call()` method to `GaussianProcessClassificationHead`. · 2ae06c8a
      Jeremiah Liu authored
      This change allows `GaussianProcessClassificationHead` to output only the predictive logits during training and evaluation (instead of outputting a tuple  `(logits, covmat)`). The goal is to make the layer more compatible with `SentencePredictionTask` and Keras' `model.fit()` API.
      
      PiperOrigin-RevId: 366891298
      2ae06c8a
  5. 01 Apr, 2021 3 commits
  6. 24 Mar, 2021 1 commit
  7. 22 Mar, 2021 3 commits
  8. 20 Mar, 2021 1 commit
  9. 17 Mar, 2021 1 commit
  10. 16 Mar, 2021 1 commit
  11. 12 Mar, 2021 2 commits
  12. 10 Mar, 2021 1 commit
  13. 09 Mar, 2021 1 commit
  14. 08 Mar, 2021 1 commit
  15. 04 Mar, 2021 1 commit
  16. 02 Mar, 2021 1 commit
  17. 26 Feb, 2021 1 commit
  18. 23 Feb, 2021 1 commit
  19. 16 Feb, 2021 2 commits
  20. 28 Jan, 2021 1 commit
  21. 19 Jan, 2021 1 commit
  22. 14 Jan, 2021 2 commits
  23. 12 Jan, 2021 1 commit
  24. 08 Jan, 2021 1 commit
  25. 05 Jan, 2021 1 commit
  26. 21 Dec, 2020 1 commit
  27. 10 Dec, 2020 1 commit
  28. 09 Dec, 2020 1 commit
  29. 01 Dec, 2020 1 commit
  30. 25 Nov, 2020 1 commit
  31. 16 Nov, 2020 1 commit
  32. 11 Nov, 2020 1 commit