Changes to hint losses, mostly for decode_diffs=True. Before, only one of the terms of the MASK type loss was masked by gt_diff. Also, the loss was averaged over all time steps, including steps without diffs and therefore contributing 0 to the loss. Now we average only over the non-zero-diff steps.#57
Merged
copybara-service[bot] merged 1 commit intomasterfrom Feb 27, 2022
Merged
Changes to hint losses, mostly for decode_diffs=True. Before, only one of the terms of the MASK type loss was masked by gt_diff. Also, the loss was averaged over all time steps, including steps without diffs and therefore contributing 0 to the loss. Now we average only over the non-zero-diff steps.#57copybara-service[bot] merged 1 commit intomasterfrom
copybara-service[bot] merged 1 commit intomasterfrom
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). For more information, open the CLA check for this pull request. |
copybara-service
bot
force-pushed
the
test_431003851
branch
from
05aa57a to
3a23acd
Compare
…e of the terms of the MASK type loss was masked by gt_diff. Also, the loss was averaged over all time steps, including steps without diffs and therefore contributing 0 to the loss. Now we average only over the non-zero-diff steps. With this, the chunked and non-chunked code of the losses can be shared more. PiperOrigin-RevId: 431292151
copybara-service
bot
force-pushed
the
test_431003851
branch
from
3a23acd to
25a7cbb
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Changes to hint losses, mostly for decode_diffs=True. Before, only one of the terms of the MASK type loss was masked by gt_diff. Also, the loss was averaged over all time steps, including steps without diffs and therefore contributing 0 to the loss. Now we average only over the non-zero-diff steps.
With this, the chunked and non-chunked code of the losses can be shared more.