Fix Issue regarding stderr (#1327)

* add fix fordeciding if stderr is N/A or not

* process N/A

lm_eval/evaluator.py

@@ -492,17 +492,23 @@ def evaluate(
                         ]:
                             stderr = "_stderr,".join(metric.split(","))
                             stderr_score = results[task][stderr]
+                            if stderr_score == "N/A":
+                                var_score = "N/A"
+                            else:
                                 var_score = stderr_score**2
-                            metric_score = results[task][metric]
-
                                 all_stderr.append(stderr)
 
+                            metric_score = results[task][metric]
+
                             if metric in results[group]:
                                 results[group][metric] = (
                                     results[group][metric] * total_size
                                     + metric_score * current_size
                                 ) / (total_size + current_size)
                                 # $$s_z^2 = \frac{(n-1) s_x^2 + (m-1) s_y^2}{n+m-1} + \frac{nm(\bar x - \bar y)^2}{(n+m)(n+m-1)}.$$
+                                if var_score == "N/A":
+                                    results[group][stderr] = "N/A"
+                                else:
                                     results[group][stderr] = (
                                         (total_size - 1) * results[group][stderr]
                                         + (current_size - 1) * var_score
@@ -511,7 +517,9 @@ def evaluate(
                                     ) + total_size * current_size / (
                                         (total_size + current_size)
                                         * (total_size + current_size - 1)
-                                ) * (results[group][metric] - metric_score) ** 2
+                                    ) * (
+                                        results[group][metric] - metric_score
+                                    ) ** 2
                             else:
                                 results[group][metric] = metric_score
                                 results[group][stderr] = var_score