Fix test_eos_token_id_int_and_list_top_k_top_sampling
#22826
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
|
The documentation is not available anymore as the PR was closed or merged. |
sgugger
approved these changes
Apr 18, 2023
novice03
pushed a commit
to novice03/transformers
that referenced
this pull request
Jun 23, 2023
…22826) * fix --------- Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
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Outdated suggestions cannot be applied.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.
What does this PR do?
In #22204, I updated the expected value in
test_eos_token_id_int_and_list_top_k_top_samplingto pass theCircleCI. However, the daily CI fails with that new value. It turns out that we need a seed that could give the same (generation) output (at minimum, the same output length) on both CPU/GPU machines. The difference is very likely coming from somehow larger numerical differences after certain generation steps.remark
With seed
0, the outputgenerated_tokens[0]is:cpu:[ 40, 416, 79, 12, 230, 89, 231, 432, 301, 212, 933, 225, 33, 33, 846]gpu:[ 40, 416, 79, 12, 230, 89, 231, 432, 301, 212, 933, 225, 476, 682, 319, 832, 873, 853, 873, 832]