-
Notifications
You must be signed in to change notification settings - Fork 362
Fix caching logic #994
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
base: main
Are you sure you want to change the base?
Fix caching logic #994
Conversation
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! |
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. |
Can you fix the tests before I take a look? |
should be fixed! |
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}"] | ||
) |
There was a problem hiding this comment.
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) |
There was a problem hiding this comment.
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
Right now the code throws an error if you try to evaluate the same dataset with different numbers of shots. My PR fixes that.