TheRealAIGuy commited on
Commit
ee1bcdc
·
1 Parent(s): 1c0bef3

openenv.yaml format fix & graders fix & inference.py fix output format

Browse files
graders/grader_classification.py CHANGED
@@ -59,9 +59,3 @@ class MediumClassificationGrader:
59
  }
60
  return score
61
 
62
-
63
- # Add this wrapper function to the bottom of grader_classification.py
64
- def grade_task2_medium(state: Any = None, ground_truth: dict[str, Any] | None = None) -> float:
65
- """Instantiates the MediumClassificationGrader and executes the validation."""
66
- grader = MediumClassificationGrader()
67
- return grader.grade(state, ground_truth)
 
59
  }
60
  return score
61
 
 
 
 
 
 
 
graders/grader_detection.py CHANGED
@@ -59,10 +59,3 @@ class EasyDetectionGrader:
59
  "score": round(score, 4),
60
  }
61
  return score
62
-
63
-
64
- # Add this wrapper function to the bottom of grader_detection.py
65
- def grade_task1_easy(state: Any = None, ground_truth: dict[str, Any] | None = None) -> float:
66
- """Instantiates the EasyDetectionGrader and executes the validation."""
67
- grader = EasyDetectionGrader()
68
- return grader.grade(state, ground_truth)
 
59
  "score": round(score, 4),
60
  }
61
  return score
 
 
 
 
 
 
 
graders/grader_fix.py CHANGED
@@ -59,8 +59,3 @@ class HardFixGrader:
59
  "score": round(score, 4),
60
  }
61
  return score
62
-
63
- # Add this wrapper function to the bottom of the file
64
- def grade_task3_hard(state: Any = None, ground_truth: dict[str, Any] | None = None) -> float:
65
- grader = HardFixGrader()
66
- return grader.grade(state, ground_truth)
 
59
  "score": round(score, 4),
60
  }
61
  return score
 
 
 
 
 
inference.py CHANGED
@@ -225,6 +225,7 @@ def run_inference() -> None:
225
  except Exception as exc:
226
  traceback.print_exc(file=sys.stderr)
227
  finally:
 
228
  # Get the final step's reward as the overall score
229
  raw_score = all_rewards[-1] if all_rewards else 0.1
230
 
 
225
  except Exception as exc:
226
  traceback.print_exc(file=sys.stderr)
227
  finally:
228
+
229
  # Get the final step's reward as the overall score
230
  raw_score = all_rewards[-1] if all_rewards else 0.1
231