Skip to content

chore: improvements to command line arguments #781

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.

Sign up for GitHub

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

Merged
jemeza-codegen merged 1 commit into from
Mar 8, 2025
Merged

chore: improvements to command line arguments #781

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions codegen-examples/examples/swebench_agent_run/run_eval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -269,14 +269,14 @@ def process_batch_local(examples: list[SweBenchExample], model: str, num_workers


async def run_eval(
use_existing_preds: str | None,
dataset: str,
length: int,
use_existing_preds: str | None = None,
length: int | None = None,
instance_id: str | None = None,
local: bool = False,
codebases: dict[str, Codebase] = {},
repo: str | None = None,
num_workers: int = 5,
num_workers: int = 2,
model: str = "claude-3-7-sonnet-latest",
):
run_id = use_existing_preds or str(uuid.uuid4())
Expand Down Expand Up @@ -353,20 +353,20 @@ async def run_eval(


@click.command()
@click.option("--use-existing-preds", help="The run ID of the existing predictions to use.", type=str, default=None)
@click.option("--dataset", help="The dataset to use.", type=click.Choice(["lite", "full", "verified", "lite_small", "lite_medium", "lite_large"]), default="lite")
@click.option("--length", help="The number of examples to process.", type=int, default=10)
@click.option("--use-existing-preds", help="The run ID of the existing predictions to use.", type=str, default=None)
@click.option("--length", help="The number of examples to process.", type=int, default=None)
@click.option("--instance-id", help="The instance ID of the example to process.", type=str, default=None)
@click.option("--local", help="Run the evaluation locally.", is_flag=True, default=False)
@click.option("--repo", help="The repo to use.", type=str, default=None)
@click.option(
"--num-workers", help="The number of workers to use. This is the number of examples that will be processed concurrently. A large number may lead to rate limiting issues.", type=int, default=5
)
@click.option("--model", help="The model to use.", type=str, default="claude-3-7-sonnet-latest")
def run_eval_command(use_existing_preds, dataset, length, instance_id, local, repo, num_workers, model):
def run_eval_command(dataset, use_existing_preds, length, instance_id, local, repo, num_workers, model):
print(f"Repo: {repo}")
print(f"Model: {model}")
asyncio.run(run_eval(use_existing_preds=use_existing_preds, dataset=dataset, length=length, instance_id=instance_id, codebases=None, local=local, repo=repo, num_workers=num_workers, model=model))
asyncio.run(run_eval(dataset=dataset, use_existing_preds=use_existing_preds, length=length, instance_id=instance_id, local=local, repo=repo, num_workers=num_workers, model=model))


if __name__ == "__main__":
Expand Down
Loading