Skip to content
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

Add split_eval_set command #1609

Closed
wants to merge 23 commits into from
Closed

Add split_eval_set command #1609

wants to merge 23 commits into from

Conversation

jimmyxu-db
Copy link

No description provided.

@jimmyxu-db jimmyxu-db requested a review from a team as a code owner October 22, 2024 21:45
@jimmyxu-db jimmyxu-db changed the title Jimmy/data split Add split_eval_set command Oct 25, 2024
Copy link
Collaborator

@dakinggg dakinggg left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks reasonable, would want to also see a test run on MCT using this script

llmfoundry/command_utils/data_prep/split_eval_set.py Outdated Show resolved Hide resolved
llmfoundry/command_utils/data_prep/split_eval_set.py Outdated Show resolved Hide resolved
tests/a_scripts/data_prep/test_split_eval_set.py Outdated Show resolved Hide resolved
tests/a_scripts/data_prep/test_split_eval_set.py Outdated Show resolved Hide resolved
tests/a_scripts/data_prep/test_split_eval_set.py Outdated Show resolved Hide resolved
llmfoundry/command_utils/data_prep/split_eval_set.py Outdated Show resolved Hide resolved
llmfoundry/command_utils/data_prep/split_eval_set.py Outdated Show resolved Hide resolved
llmfoundry/command_utils/data_prep/split_eval_set.py Outdated Show resolved Hide resolved
llmfoundry/command_utils/data_prep/split_eval_set.py Outdated Show resolved Hide resolved
@dakinggg
Copy link
Collaborator

Please also add a PR description (describing the functionality added, not any downstream API needs).


log = logging.getLogger(__name__)

LOCAL_PATH = 'tmp-t'
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't think you want to hardcode this. Should this not just be a fallback to assume local path?

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

im not too familiar, is it acceptable to have

if remote object store:
  remote object store:
else:
  local path

i.e. have it be the defualt?

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

seems ok? just note that is what it defaults to

llmfoundry/command_utils/data_prep/split_eval_set.py Outdated Show resolved Hide resolved
llmfoundry/command_utils/data_prep/split_eval_set.py Outdated Show resolved Hide resolved
Signed-off-by: Jimmy Xu <[email protected]>
Signed-off-by: Jimmy Xu <[email protected]>
@jimmyxu-db
Copy link
Author

closing this PR as we are re-prioritizing the long term workflows solution over pushing out a sweep/eval PuPr asap, which this PR was meant to do

@jimmyxu-db jimmyxu-db closed this Nov 5, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants