tiny fix

chenlk96 · May 28, 2023 · a09bb2d · a09bb2d
1 parent 7fc792d
commit a09bb2d
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/src/utils/ppo.py b/src/utils/ppo.py
@@ -157,8 +157,8 @@ def ppo_train(self, max_target_length: int) -> None:
 
                 stats = self.step(queries, responses, rewards)
 
-                loss_meter.update(stats["ppo/loss/total"])
-                reward_meter.update(torch.tensor(rewards).sum().item(), n=len(rewards))
+                loss_meter.update(stats["ppo/loss/total"], n=len(rewards))
+                reward_meter.update(torch.stack(rewards).mean().item(), n=len(rewards))
 
                 if steps_trained == len_dataloader:
                     dataiter = iter(self.dataloader)