Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
4 changes: 4 additions & 0 deletions packages/prime/src/prime_cli/api/rl.py
Original file line number Diff line number Diff line change
Expand Up @@ -131,6 +131,7 @@ def create_run(
oversampling_factor: Optional[float] = None,
max_async_level: Optional[int] = None,
checkpoints_config: Optional[Dict[str, Any]] = None,
adapters_config: Optional[Dict[str, Any]] = None,
checkpoint_id: Optional[str] = None,
cluster_name: Optional[str] = None,
) -> RLRun:
Expand Down Expand Up @@ -197,6 +198,9 @@ def create_run(
if checkpoints_config:
payload["checkpoints"] = checkpoints_config

if adapters_config:
payload["adapters"] = adapters_config

if checkpoint_id:
payload["checkpoint_id"] = checkpoint_id

Expand Down
22 changes: 22 additions & 0 deletions packages/prime/src/prime_cli/commands/rl.py
Original file line number Diff line number Diff line change
Expand Up @@ -197,6 +197,11 @@ def generate_rl_config_template(environment: str | None = None) -> str:
# [checkpoints]
# interval = 100 # Save checkpoint every N steps
# keep_cloud = 5 # Keep N checkpoints in cloud (-1 = keep all)

# Optional: adapter upload configuration
# [adapters]
# interval = 0 # Upload adapter every N steps (0 = only at run end)
# keep_last = 3 # Keep N adapters in cloud (-1 = keep all)
'''


Expand Down Expand Up @@ -369,6 +374,21 @@ def to_api_dict(self) -> Dict[str, Any] | None:
return result if result else None


class AdaptersConfig(BaseModel):
model_config = ConfigDict(extra="forbid")

interval: int | None = None # Upload adapter every N steps (0 = only at run end)
keep_last: int | None = None # Keep N adapters in cloud (-1 = keep all)

def to_api_dict(self) -> Dict[str, Any] | None:
result: Dict[str, Any] = {}
if self.interval is not None:
result["interval"] = self.interval
if self.keep_last is not None:
result["keep_last"] = self.keep_last
return result if result else None


class RLConfig(BaseModel):
model_config = ConfigDict(extra="forbid")

Expand All @@ -390,6 +410,7 @@ class RLConfig(BaseModel):
buffer: BufferConfig = Field(default_factory=BufferConfig)
wandb: WandbConfig = Field(default_factory=WandbConfig)
checkpoints: CheckpointsConfig = Field(default_factory=CheckpointsConfig)
adapters: AdaptersConfig = Field(default_factory=AdaptersConfig)
env_file: List[str] = Field(default_factory=list) # deprecated, use env_files
env_files: List[str] = Field(default_factory=list)

Expand Down Expand Up @@ -724,6 +745,7 @@ def warn(msg: str) -> None:
oversampling_factor=cfg.oversampling_factor,
max_async_level=cfg.max_async_level,
checkpoints_config=cfg.checkpoints.to_api_dict(),
adapters_config=cfg.adapters.to_api_dict(),
checkpoint_id=cfg.checkpoint_id,
cluster_name=cfg.cluster_name,
)
Expand Down