Adding support for custom eval configs

[yasser-sulaiman]

by adding include_path to EleutherAI specific eval args section in eleuther_evaluation.yaml file, custom lm-eval file can be used

Context

What is the purpose of this PR? Is it to

• add a new feature
• fix a bug
• update tests and/or documentation
• other (please add here)

Please link to any issues this PR addresses.
solves #1054

Changelog

What are the changes made in this PR?

Test plan

Please make sure to do each of the following if applicable to your PR. (If you're not sure about any one of these just ask and we will happily help.)

• run pre-commit hooks and linters (make sure you've first installed via pre-commit install)
• add unit tests for any new functionality
• update docstrings for any new or updated methods or classes
• run unit tests via pytest tests
• run recipe tests via pytest tests -m integration_test
• manually run any new or modified recipes with sufficient proof of correctness
  • include relevant commands and any other artifacts in this summary (pastes of loss curves, eval results, etc.)

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchtune/1055

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit 4b8a092 with merge base f9cb9e6 ():
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[ebsmothers]

@yasser-sulaiman thanks for the PR! Overall the changes look good to me. Can you update the test plan with a sanity check demonstrating that you're now able to load a custom task by passing include_path?

[yasser-sulaiman]

@yasser-sulaiman thanks for the PR! Overall the changes look good to me. Can you update the test plan with a sanity check demonstrating that you're now able to load a custom task by passing include_path?

Hello,
I am not sure I understood it, should I include an example demonstrating how it works or should I add a unit test for it?

[joecummings]

@yasser-sulaiman thanks for the PR! Overall the changes look good to me. Can you update the test plan with a sanity check demonstrating that you're now able to load a custom task by passing include_path?

Hello,

I am not sure I understood it, should I include an example demonstrating how it works or should I add a unit test for it?

A code example demonstrating it works as expected (in the form of a Gist) is good.

[yasser-sulaiman]

@yasser-sulaiman thanks for the PR! Overall the changes look good to me. Can you update the test plan with a sanity check demonstrating that you're now able to load a custom task by passing include_path?

Hello,
I am not sure I understood it, should I include an example demonstrating how it works or should I add a unit test for it?

A code example demonstrating it works as expected (in the form of a Gist) is good.

thanks for the suggestion, here is the link to an example configuration that demonstrates it works as expected

[RdoubleA]

Thanks for providing the code snippet! Left one minor comment

[RdoubleA]

can we do something like this?

task_manager = TaskManager(include_path=self._cfg.get("include_path", None))
task_dict = get_task_dict(self._tasks, task_manager)

[yasser-sulaiman]

I applied the minor comment but did not know how to write a test case for it :(