New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Execution Prediction #2659
Open
bmosaicml
wants to merge
22
commits into
mosaicml:dev
Choose a base branch
from
bmosaicml:codetracing
base: dev
Could not load branches
Branch not found: {{ refName }}
Could not load tags
Nothing to show
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Execution Prediction #2659
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
* Seed the fewshot sampling in the ICL datasets (mosaicml#2100) * merge * add ece for lm and mc * fetch upstream * fetch upstream * Apply suggestions from code review Co-authored-by: Daniel King <43149077+dakinggg@users.noreply.github.com> * incorporate comments * incorporate comments * de;ete multi gpu --------- Co-authored-by: Daniel King <43149077+dakinggg@users.noreply.github.com>
Looks good to me. Once my branch is approved I'll probably redo it to inherit from other classes etc but seems good for now! |
@maxisawesome @bmosaicml What do you want to do for merge order here? Should we merge Max's and then update this PR to use Max's? or the other way around? |
Let's merge this in, then I can rebase and format it into the new version in my PR. That seems easier to me. |
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Outdated suggestions cannot be applied.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?
This PR introduces the execution prediction task. It is an auxiliary task compatible with any code evaluation dataset that requires the model to inspect a piece of code, and complete assert test statements by predicting the code's output on a given input.
Tested with this run:
exec-prediction-has8Hy
It is slightly more challenging than human eval but still meaningful signal for 30B models.
Below is an example of how the execution prediction task is formatted:
The model would then be expected to continue the line such that the
test
function succeeds.What issue(s) does this change relate to?
Before submitting
pre-commit
on your change? (see thepre-commit
section of prerequisites)