update

src/leaderboard/read_evals.py

@@ -88,6 +88,12 @@ class EvalResult:
             print("task", task, "task.metric",task.metric, "task.benchmark", task.benchmark)
             # We average all scores of a given metric (not all metrics are present in all files)
             accs = np.array([v.get(task.metric, None) for k, v in data["results"].items() if task.benchmark == k])
+            
+	    for k, v in data["results"].items():
+                print("k,v,benchmark,metic",k,v, task.benchmark,task.metric)
+		if task.benchmark == k:
+                    print(v.get(task.metric, None))
+            print("accs", accs)
             if accs.size == 0 or any([acc is None for acc in accs]):
                 continue