step1: evaluate code: fix a small bug

step1_evaluate_code.py

@@ -67,9 +67,8 @@ def test_generation(args, debug=False):
             print(f"Compilation failed, test framework exception = {repr(e)}{e}\n")
     finally:
         assert isinstance(curr_res, list)
-        problem_results = np.asarray(curr_res)
 
-    code_sample["eval_result"] = bool(np.all(problem_results > 0))
+    code_sample["eval_result"] = curr_res
 
     return code_sample