💡 Fix type hint in _generate_and_score_completions (huggingface#3336)

Author: syt-nju

trl/trainer/grpo_trainer.py

@@ -899,7 +899,7 @@ def _prepare_inputs(
         return inputs
 
     def _generate_and_score_completions(
-        self, inputs: dict[str, Union[torch.Tensor, Any]]
+        self, inputs: list[dict[str, Union[torch.Tensor, Any]]]
     ) -> dict[str, Union[torch.Tensor, Any]]:
         device = self.accelerator.device
         mode = "eval" if self.control.should_evaluate else "train"