Fix: --disable_group_texts 1 keep short samples
#649
Merged
+33
−11
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
`--disable_group_texts 1` would discard short samples with length smaller than
`model_max_length` or `--block_size`. Now the behavior is changed to what is
expected:
- The short samples will be right padded to `model_max_length`
- The long samples will be truncated to `model_max_length`
Along with the corresponding cache mechanism (new cache will be generated once
`--disable_group_texts` argument is different from previous caches)
Closed
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Outdated suggestions cannot be applied.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.
--disable_group_texts 1would discard short samples with length smaller thanmodel_max_lengthor--block_size, and long samples will be cut into blocks, with last block being discarded. Now the behavior is changed to what is expected:model_max_lengthmodel_max_lengthAlong with the corresponding cache mechanism (new cache will be generated once
--disable_group_textsargument is different from previous caches)