College biology isn't medicine

src/backend/run_eval_suite.py

@@ -72,7 +72,7 @@ def run_evaluation(eval_request: EvalRequest, task_names, num_fewshot, batch_siz
         print(
             "WARNING: --limit SHOULD ONLY BE USED FOR TESTING. REAL METRICS SHOULD NOT BE COMPUTED USING LIMIT."
         )
-    task_names = ["medmcqa", "medqa_4options", "mmlu_anatomy", "mmlu_clinical_knowledge", "mmlu_college_biology", "mmlu_college_medicine", "mmlu_medical_genetics", "mmlu_professional_medicine", "pubmedqa"]
+    task_names = ["medmcqa", "medqa_4options", "mmlu_anatomy", "mmlu_clinical_knowledge", "mmlu_college_medicine", "mmlu_medical_genetics", "mmlu_professional_medicine", "pubmedqa"]
 
   
     print(f"Selected Tasks: {task_names}")