cluster_loras / 13 /mmlu /metrics.json
Muqeeth's picture
Upload folder using huggingface_hub
9224edf verified
{"average_acc": 0.42956843754450935, "subcat_acc": {"math": 0.30639097744360905, "health": 0.45121951219512196, "physics": 0.3453125, "business": 0.5675057208237986, "biology": 0.4647577092511013, "chemistry": 0.34983498349834985, "computer science": 0.36650485436893204, "economics": 0.40431266846361186, "engineering": 0.3931034482758621, "philosophy": 0.36530815109343934, "other": 0.49098712446351933, "history": 0.5182795698924731, "geography": 0.5202020202020202, "politics": 0.5354938271604939, "psychology": 0.47709593777009507, "culture": 0.5783132530120482, "law": 0.3908111174134997}, "cat_acc": {"STEM": 0.35520212060967526, "humanities": 0.40510095642933047, "social sciences": 0.4855378615534612, "other (business, health, misc.)": 0.4811844540407156}, "subjects": {"abstract_algebra": 0.26, "anatomy": 0.5037037037037037, "astronomy": 0.4276315789473684, "business_ethics": 0.47, "clinical_knowledge": 0.4641509433962264, "college_biology": 0.4444444444444444, "college_chemistry": 0.43, "college_computer_science": 0.34, "college_mathematics": 0.36, "college_medicine": 0.42196531791907516, "college_physics": 0.27450980392156865, "computer_security": 0.52, "conceptual_physics": 0.3276595744680851, "econometrics": 0.2807017543859649, "electrical_engineering": 0.3931034482758621, "elementary_mathematics": 0.2698412698412698, "formal_logic": 0.3888888888888889, "global_facts": 0.23, "high_school_biology": 0.47419354838709676, "high_school_chemistry": 0.3103448275862069, "high_school_computer_science": 0.33, "high_school_european_history": 0.5696969696969697, "high_school_geography": 0.5202020202020202, "high_school_government_and_politics": 0.6010362694300518, "high_school_macroeconomics": 0.43846153846153846, "high_school_mathematics": 0.2777777777777778, "high_school_microeconomics": 0.40756302521008403, "high_school_physics": 0.33774834437086093, "high_school_psychology": 0.5486238532110091, "high_school_statistics": 0.4027777777777778, "high_school_us_history": 0.5294117647058824, "high_school_world_history": 0.569620253164557, "human_aging": 0.42152466367713004, "human_sexuality": 0.5190839694656488, "international_law": 0.5619834710743802, "jurisprudence": 0.5, "logical_fallacies": 0.4723926380368098, "machine_learning": 0.2857142857142857, "management": 0.4854368932038835, "marketing": 0.6452991452991453, "medical_genetics": 0.47, "miscellaneous": 0.5810983397190294, "moral_disputes": 0.3786127167630058, "moral_scenarios": 0.25139664804469275, "nutrition": 0.4477124183006536, "philosophy": 0.4694533762057878, "prehistory": 0.44753086419753085, "professional_accounting": 0.3333333333333333, "professional_law": 0.36962190352020863, "professional_medicine": 0.4742647058823529, "professional_psychology": 0.4133986928104575, "public_relations": 0.44545454545454544, "security_studies": 0.5061224489795918, "sociology": 0.6169154228855721, "us_foreign_policy": 0.58, "virology": 0.41566265060240964, "world_religions": 0.6257309941520468}}