update

src/backend/envs.py

@@ -25,9 +25,9 @@ class Tasks(Enum):
     task2 = Task("truthfulqa_mc1", "mc1", "TruthfulQA MC1", 0)
     task3 = Task("truthfulqa_mc2", "mc2", "TruthfulQA MC2", 0)  # TruthfulQA is intended as a zero-shot benchmark [5, 47]. https://owainevans.github.io/pdfs/truthfulQA_lin_evans.pdf
 
-
 # NUM_FEWSHOT = 64  # Change with your few shot
 
+
 EVAL_REQUESTS_PATH_BACKEND = os.path.join(CACHE_PATH, "eval-queue-bk")
 EVAL_RESULTS_PATH_BACKEND = os.path.join(CACHE_PATH, "eval-results-bk")
 

src/leaderboard/read_evals.py

@@ -201,9 +201,6 @@ def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResu
         except dateutil.parser._parser.ParserError:
             files = [files[-1]]
 
-        # if '125m' in root:
-        #     breakpoint()
-
         for file in files:
             model_result_filepaths.append(os.path.join(root, file))