add

src/leaderboard/read_evals.py

@@ -130,6 +130,7 @@ class EvalResult:
             try:
                 data_dict[task.value.col_name] = self.results[task.value.benchmark]
             except KeyError as e:
+                print(e)
                 print(self.results.keys())
 
         return data_dict
@@ -189,12 +190,12 @@ def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResu
             eval_results[eval_name].results.update({k: v for k, v in eval_result.results.items() if v is not None})
         else:
             eval_results[eval_name] = eval_result
-    print(eval_results)
+    # print(eval_results)
 
     results = []
     for v in eval_results.values():
         try:
-            # v.to_dict() # we test if the dict version is complete
+            v.to_dict() # we test if the dict version is complete
             results.append(v)
         except KeyError as e:  # not all eval values present
             print(e)