Skip to content

Conversation

jxmorris12
Copy link

Right now the code throws an error if you try to evaluate the same dataset with different numbers of shots. My PR fixes that.

@clefourrier
Copy link
Member

Hi! Thanks for the PR - for viz, the team is at a conference, but I'll take a look next Mon, feel free to ping me then if needed!

@HuggingFaceDocBuilderDev
Copy link
Collaborator

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@clefourrier
Copy link
Member

Can you fix the tests before I take a look?

@jxmorris12
Copy link
Author

should be fixed!

Comment on lines +166 to +169
task_suite, task_name, few_shot = full_task_name.split("|")
task_configs: list[LightevalTaskConfig] = sorted(
self.registry.task_to_configs[f"{task_suite}|{task_name}|{few_shot}"]
)
Copy link
Member

Choose a reason for hiding this comment

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

might as well use the full task name then ^^

)

task_to_configs[expanded_task].append(config)
task_to_configs[expanded_task + f"|{few_shot}"].append(config)
Copy link
Member

Choose a reason for hiding this comment

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

you'll likely need to update the logic throughout to use the full task name with few shots in all the code

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