Skip to content

Fix train_rl and rl.yml paths #1198

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
alfredyu-cienet merged 1 commit into from
Mar 1, 2026
Merged

Fix train_rl and rl.yml paths #1198

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
2 changes: 1 addition & 1 deletion dags/post_training/maxtext_rl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,7 @@
f"{test_config_util.DEFAULT_BUCKET}/llama3.1-70b-Instruct/"
"scanned-pathways/0/items/"
),
rl_config_path="src/MaxText/configs/rl.yml",
rl_config_path="src/maxtext/configs/post_train/rl.yml",
loss_algos=[
test_config_util.LossAlgo.GRPO,
test_config_util.LossAlgo.GSPO,
Expand Down
6 changes: 3 additions & 3 deletions dags/post_training/util/test_config_util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,7 @@ class RLTestConfig:
tokenizer_path: str
load_parameters_path: str
loss_algos: list[LossAlgo]
rl_config_path: str = "src/MaxText/configs/rl.yml"
rl_config_path: str = "src/maxtext/configs/post_train/rl.yml"

def __init__(
self,
Expand All @@ -100,7 +100,7 @@ def __init__(
tokenizer_path: str,
load_parameters_path: str,
loss_algos: list[LossAlgo],
rl_config_path: str = "src/MaxText/configs/rl.yml",
rl_config_path: str = "src/maxtext/configs/post_train/rl.yml",
):
"""Initializes the RL test configurations.

Expand Down Expand Up @@ -158,7 +158,7 @@ def generate_rl_training_command(
])

rl_command = (
"python -m src.MaxText.rl.train_rl "
"python -m src.maxtext.rl.train_rl "
f"{self.rl_config_path} " + " ".join(command_params)
)

Expand Down
Loading