feat: display running average of metrics during vf-eval

[anakin87]

Description

Fixes #416.

When running vf-eval, the average reward and completion length are now displayed in the progress bar as rollouts complete.
To do this, I added a tqdm_gather_with_metrics utility function that aggregates metrics during async task execution. This function is used in a_generate to show running averages.

(@mikasenghaas take a look)

Example output

vfscreen.mov

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Test improvement

Testing

• All existing tests pass when running uv run pytest locally.
• New tests have been added to cover the changes

Checklist

• My code follows the style guidelines of this project as outlined in AGENTS.md
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• Any dependent changes have been merged and published

Additional Notes

[anakin87]

@willccbb I'd appreciate your feedback

[anakin87]

Closing. Implemented in #693.