fix output type.

lingo_judge_metric.py

@@ -32,6 +32,15 @@ Args:
 Returns:
     `scores` (list of float): Score indicating truthfulness.
 
+Examples:
+    
+    Example 1
+        >>> metric = evaluate.load("maysonma/lingo_judge_metric")
+        >>> questions = ["Are there any traffic lights present? If yes, what is their color?"]
+        >>> references = [["Yes, green."]]
+        >>> predictions = ["No."]
+        >>> results = metric.compute(questions=questions, predictions=predictions, references=references)
+        >>> print(results)
 """
 
 
@@ -61,4 +70,5 @@ class LingoJudgeMetric(evaluate.Metric):
 
     def _compute(self, questions, predictions, references):
         """Returns the scores"""
-        return self.scorer.compute(questions, references, predictions)
+        scores = self.scorer.compute(questions, references, predictions)
+        return scores.cpu().tolist()