Skip to content

Conversation

@SumanthRH
Copy link
Member

What does this PR do?

In #71 , the output format is a dictionary id_to_results mapping an index (string) -> entry. In process_remaining_data, we should convert to string rather than int.

Signed-off-by: SumanthRH <[email protected]>
@SumanthRH SumanthRH changed the title [Bugfix] Fix index type in process_remaining_data Fix index type in process_remaining_data and repeated CI triggers Feb 20, 2025
@SumanthRH SumanthRH force-pushed the sumanthrh/minor-fix-generation branch from c76a40f to 8e3daad Compare February 20, 2025 21:50
@SumanthRH SumanthRH changed the title Fix index type in process_remaining_data and repeated CI triggers Fix index type in process_remaining_data Feb 20, 2025
x
Signed-off-by: SumanthRH <[email protected]>
@SumanthRH SumanthRH changed the title Fix index type in process_remaining_data Minor fixes Feb 21, 2025
x
Signed-off-by: SumanthRH <[email protected]>
x
Signed-off-by: SumanthRH <[email protected]>
Signed-off-by: SumanthRH <[email protected]>
x
Signed-off-by: SumanthRH <[email protected]>
x
Signed-off-by: SumanthRH <[email protected]>
x
Signed-off-by: SumanthRH <[email protected]>
Signed-off-by: SumanthRH <[email protected]>
@SumanthRH SumanthRH changed the title Minor fixes Fixes before release Feb 21, 2025
@SumanthRH SumanthRH merged commit 69ea553 into main Feb 21, 2025
2 of 4 checks passed
SumanthRH added a commit that referenced this pull request Feb 21, 2025
- Fixes some broken links after #77 . `skythought_evals` has been renamed to `evals` and the package name is `skythought`.
- Added separate yamls for Numina for a better quickstart experience. Ideally, we shouldn't have to keep adding yamls for all the training datasets in the evaluation library, and should instead provide APIs for standalone scripts. For now we do this to support reproduction of Sky-T1 models.

Signed-off-by: SumanthRH <[email protected]>
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