cluster_loras / 24 /mmlu /metrics.json
Muqeeth's picture
Upload folder using huggingface_hub
9224edf verified
{"average_acc": 0.4077766699900299, "subcat_acc": {"math": 0.26221804511278196, "health": 0.43841463414634146, "physics": 0.328125, "business": 0.540045766590389, "biology": 0.44493392070484583, "chemistry": 0.3201320132013201, "computer science": 0.3859223300970874, "economics": 0.3746630727762803, "engineering": 0.4068965517241379, "philosophy": 0.3533797216699801, "other": 0.463519313304721, "history": 0.47956989247311826, "geography": 0.47474747474747475, "politics": 0.5308641975308642, "psychology": 0.4511668107173725, "culture": 0.5481927710843374, "law": 0.36755530346001136}, "cat_acc": {"STEM": 0.3333333333333333, "humanities": 0.383634431455898, "social sciences": 0.4614884627884303, "other (business, health, misc.)": 0.4611351017890191}, "subjects": {"abstract_algebra": 0.24, "anatomy": 0.4148148148148148, "astronomy": 0.39473684210526316, "business_ethics": 0.44, "clinical_knowledge": 0.45660377358490567, "college_biology": 0.4513888888888889, "college_chemistry": 0.38, "college_computer_science": 0.35, "college_mathematics": 0.3, "college_medicine": 0.4508670520231214, "college_physics": 0.20588235294117646, "computer_security": 0.4, "conceptual_physics": 0.37446808510638296, "econometrics": 0.2807017543859649, "electrical_engineering": 0.4068965517241379, "elementary_mathematics": 0.23544973544973544, "formal_logic": 0.38095238095238093, "global_facts": 0.29, "high_school_biology": 0.44193548387096776, "high_school_chemistry": 0.29064039408866993, "high_school_computer_science": 0.42, "high_school_european_history": 0.5454545454545454, "high_school_geography": 0.47474747474747475, "high_school_government_and_politics": 0.5906735751295337, "high_school_macroeconomics": 0.39487179487179486, "high_school_mathematics": 0.25555555555555554, "high_school_microeconomics": 0.3865546218487395, "high_school_physics": 0.271523178807947, "high_school_psychology": 0.5100917431192661, "high_school_statistics": 0.3101851851851852, "high_school_us_history": 0.4803921568627451, "high_school_world_history": 0.5316455696202531, "human_aging": 0.3811659192825112, "human_sexuality": 0.48091603053435117, "international_law": 0.5041322314049587, "jurisprudence": 0.46296296296296297, "logical_fallacies": 0.4539877300613497, "machine_learning": 0.375, "management": 0.42718446601941745, "marketing": 0.6324786324786325, "medical_genetics": 0.47, "miscellaneous": 0.5197956577266922, "moral_disputes": 0.36127167630057805, "moral_scenarios": 0.23910614525139665, "nutrition": 0.45098039215686275, "philosophy": 0.4887459807073955, "prehistory": 0.4074074074074074, "professional_accounting": 0.36879432624113473, "professional_law": 0.3500651890482399, "professional_medicine": 0.4632352941176471, "professional_psychology": 0.39869281045751637, "public_relations": 0.43636363636363634, "security_studies": 0.4897959183673469, "sociology": 0.5920398009950248, "us_foreign_policy": 0.62, "virology": 0.40963855421686746, "world_religions": 0.5730994152046783}}