Skip to content

Require --env-url in the Wordle GRPO script #1537

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

Open
sergiopaniego wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Require --env-url in the Wordle GRPO script #1537

Show file tree
Hide file tree
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
3 changes: 2 additions & 1 deletion examples/wordle/evaluate.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -200,7 +200,8 @@ def main():
)
model = AutoModelForCausalLM.from_pretrained(args.model, dtype=dtype).to(device)
# A private Space needs your token. A public one ignores it.
headers = {"Authorization": f"Bearer {get_token()}"} if get_token() else None
token = get_token()
headers = {"Authorization": f"Bearer {token}"} if token else None

if args.secrets:
secrets = args.secrets.split(",")
Expand Down
5 changes: 3 additions & 2 deletions examples/wordle/grpo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,13 +65,14 @@ def main():
parser = argparse.ArgumentParser()
parser.add_argument("--model", required=True)
parser.add_argument("--hub-model-id", required=True)
parser.add_argument("--env-url", default="https://openenv-wordle.hf.space")
parser.add_argument("--env-url", required=True)

@cursor cursor Bot Oct 30, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Required flag breaks GRPO tests

High Severity

Making --env-url required causes test_grpo_rollout_budget to fail at startup. run_training still invokes grpo.py with only --model and --hub-model-id, so parse_args() exits before any rollout logic runs.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 3158933. Configure here.

parser.add_argument("--max-steps", type=int, default=150)
parser.add_argument("--trackio-space-id", default=None)
args = parser.parse_args()
env_url = args.env_url
# A private Space needs your token. A public one ignores it.
headers = {"Authorization": f"Bearer {get_token()}"} if get_token() else None
token = get_token()
headers = {"Authorization": f"Bearer {token}"} if token else None

class WordleEnv:
def __init__(self):
Expand Down
Loading