Conversation
…ry Binary Classifier
Contributor
Author
|
… into dev/fecheng
… into dev/fecheng
… into dev/fecheng
Contributor
Author
|
New auto-test result @adolphk-yk tasks GPU/CPU old accuracy/AUC new accuracy/AUC
english_text_matching GPU 0.96655 0.97075
english_text_matching CPU 0.96655 0.97075
chinese_text_matching GPU 0.70001 0.7
chinese_text_matching CPU 0.70001 0.7
quora_question_pairs GPU 0.72596 0.721861
quora_question_pairs CPU 0.72596 0.721861
knowledge_distillation CPU 0.66329 0.6580784722222223 |
adolphk-yk
approved these changes
Aug 2, 2019
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
There are two major updates in this PR.
Now encoding cache mechanism is supported. It's a lazy-build progress. So we will build it in the first epoch and then reuse it in the rest epoch.
We will load chunk_size cases to train in every part of an epoch avoiding out of memory in large training data