Improvements to random sampling at decode time. #1174
Merged
Conversation
This file contains 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
Merge master back into our fork.
…e, random sampling is done by default when the beam_size = 1 and the sampling_temp > 0.
merging master back in
|
looks good thanks. However if you include such a test in the pull_request_check, maybe we can do something similar in travis.yml so that it catches random sampling too. |
|
Added. |
|
merging, thanks |
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Outdated suggestions cannot be applied.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.
This pull request does the following things:
pull_request_chk.shto hopefully prevent such bugs in the future.train_single.pywhich sets the random seed.One other unrelated change: I swapped the references to
max_shard_sizeinpull_request_chk.shtoshard_sizebecause at least on my machine, the test script fails otherwise.