Skip to content

bump oversampling defaults #512

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
Jackmin801 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

bump oversampling defaults #512

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
eb351f3
bump oversampling defaults
Jackmin801 Apr 13, 2026
a48e7ee
Change max_async_level default to None
Jackmin801 Apr 13, 2026
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
6 changes: 3 additions & 3 deletions packages/prime/src/prime_cli/commands/rl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -182,8 +182,8 @@ def generate_rl_config_template(environment: str | None = None) -> str:
rollouts_per_example = 8
# learning_rate = 1e-6
# lora_alpha = 16
# oversampling_factor = 1.0
# max_async_level = 4
# oversampling_factor = 1.5
# max_async_level = 2

# Optional: warm-start from an existing checkpoint
# checkpoint_id = "..."
Expand Down Expand Up @@ -485,7 +485,7 @@ class RLConfig(BaseModel):
rollouts_per_example: int = 8
learning_rate: float | None = None
lora_alpha: int | None = None
oversampling_factor: float | None = None
oversampling_factor: float | None = 1.5
Comment thread
Jackmin801 marked this conversation as resolved.
max_async_level: int | None = None
checkpoint_id: str | None = None # Warm-start from an existing checkpoint
cluster_name: str | None = None # Admin-only: target a specific cluster by name
Expand Down
Loading