lf run

Create and run an evaluation along with its dependencies (models, model adapters, dataset generators, datasets, and tasks) as specified in a run config YAML file. You can optionally validate the configuration.

Usage
lf run [OPTIONS]
Options
Name Type Description Default
--file, -f path Path to a single run config.
-v, --validate boolean Whether to only validate the config file without creating or updating any entities. False
--wait, -w boolean Block until the evaluation finishes, printing progress every 10 seconds. False
--no-update boolean Whether to force skip updating the existing entities. False
--id text Evaluation ID to re-run.
--use-latest-entities boolean If True, use the latest version of the tasks/datasets/models/model adapters. Otherwise, use the versions used in the evaluation being re-run. Only relevant when re-running an evaluation. False