Skip to content

Weights reload configuration #1635

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
samsja merged 3 commits into from
Jan 22, 2026
Merged

Weights reload configuration #1635

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
51bbca7
Make reload weights optional on start
cursoragent Jan 21, 2026
031f76c
Default reload weights to true
cursoragent Jan 22, 2026
ef0da2e
Merge branch 'main' into cursor/weights-reload-configuration-26a4
samsja Jan 22, 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
8 changes: 8 additions & 0 deletions src/prime_rl/orchestrator/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -647,6 +647,14 @@ class OrchestratorConfig(BaseSettings):
# The checkpoint configuration
ckpt: CheckpointConfig | None = None

# Whether to reset inference weights to base model when starting from scratch
reload_weights_on_start: Annotated[
bool,
Field(
description="Whether to reset inference weights to the base model when starting from scratch."
),
] = False

# The validation configuration
val: ValConfig | None = None

Expand Down
11 changes: 8 additions & 3 deletions src/prime_rl/orchestrator/orchestrator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -236,9 +236,14 @@ async def orchestrate(config: OrchestratorConfig):
lora_name=config.model.lora.name if config.model.lora else None,
)
else:
logger.info("Training from scratch. Resetting weights to base model")
if config.model.lora is None:
await reload_weights(admin_clients)
if config.reload_weights_on_start:
if config.model.lora is None:
logger.info("Training from scratch. Resetting weights to base model")
await reload_weights(admin_clients)
else:
logger.info("Training from scratch. Skipping base weight reload because LoRA is enabled")
else:
logger.info("Training from scratch. Skipping base weight reload")

# Iterate over dataset in batches
max_steps = config.max_steps or int(1e9)
Expand Down