Skip to content
Open
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
6 changes: 4 additions & 2 deletions apps/grpo/main.py
Original file line number Diff line number Diff line change
Expand Up @@ -267,6 +267,7 @@ class DatasetActor(ForgeActor):
data_split: str = "train"
streaming: bool = True
model: str = "Qwen/Qwen3-1.7B"
seed: int = 36

@endpoint
async def setup(self):
Expand Down Expand Up @@ -301,7 +302,8 @@ def gsm8k_transform(sample):
self.path, self.revision, split=self.data_split, streaming=self.streaming
)
self._base_dataset = self._base_dataset.map(gsm8k_transform)
self._base_dataset = self._base_dataset.shuffle()
self._base_dataset = self._base_dataset.shuffle(seed=self.seed)
self._base_dataset.set_epoch(self._epoch) # for determinism
self._iterator = iter(self._base_dataset)

@endpoint
Expand Down Expand Up @@ -329,7 +331,7 @@ async def sample(self) -> dict[str, str] | None:
print(
f"Dataset epoch {self._epoch - 1} completed. Starting epoch {self._epoch}"
)
self._base_dataset.set_epoch(self._epoch)
self._base_dataset.set_epoch(self._epoch) # for determinism
self._iterator = iter(self._base_dataset)
return next(self._iterator)

Expand Down