Skip to content

Conversation

@jonathanlastmileai
Copy link
Contributor

[V2][RFC][wip] make room for batch eval

This moves the existing eval library to "test_suite_eval" and starts the equivalent
for batch runs. Also makes the interface a little clearer.

Essentially, the differences are:

  • each metric runs on a list of inputs, not just one
  • each input can be paired with a reference. This is possible in the "test suite"
    setup, but it is clunkier.

This moves the existing eval library to "test_suite_eval" and starts the equivalent
for batch runs. Also makes the interface a little clearer.

Essentially, the differences are:
- each metric runs on a _list_ of inputs, not just one
- each input can be paired with a reference. This is possible in the "test suite"
setup, but it is clunkier.
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.

2 participants