cluster_loras / 1 /mmlu /metrics.json
Muqeeth's picture
Upload folder using huggingface_hub
9224edf verified
{"average_acc": 0.4063523714570574, "subcat_acc": {"math": 0.2791353383458647, "health": 0.4121951219512195, "physics": 0.315625, "business": 0.5354691075514875, "biology": 0.4251101321585903, "chemistry": 0.3102310231023102, "computer science": 0.3762135922330097, "economics": 0.37601078167115903, "engineering": 0.3310344827586207, "philosophy": 0.34443339960238567, "other": 0.4798283261802575, "history": 0.5, "geography": 0.4444444444444444, "politics": 0.5123456790123457, "psychology": 0.452895419187554, "culture": 0.5993975903614458, "law": 0.37889960294951786}, "cat_acc": {"STEM": 0.3277004638833665, "humanities": 0.3880977683315622, "social sciences": 0.4621384465388365, "other (business, health, misc.)": 0.45311536088834053}, "subjects": {"abstract_algebra": 0.28, "anatomy": 0.4888888888888889, "astronomy": 0.40131578947368424, "business_ethics": 0.41, "clinical_knowledge": 0.41509433962264153, "college_biology": 0.4097222222222222, "college_chemistry": 0.39, "college_computer_science": 0.34, "college_mathematics": 0.32, "college_medicine": 0.4046242774566474, "college_physics": 0.21568627450980393, "computer_security": 0.45, "conceptual_physics": 0.3446808510638298, "econometrics": 0.2543859649122807, "electrical_engineering": 0.3310344827586207, "elementary_mathematics": 0.2751322751322751, "formal_logic": 0.35714285714285715, "global_facts": 0.22, "high_school_biology": 0.432258064516129, "high_school_chemistry": 0.270935960591133, "high_school_computer_science": 0.39, "high_school_european_history": 0.6, "high_school_geography": 0.4444444444444444, "high_school_government_and_politics": 0.5492227979274611, "high_school_macroeconomics": 0.4282051282051282, "high_school_mathematics": 0.24444444444444444, "high_school_microeconomics": 0.3487394957983193, "high_school_physics": 0.25165562913907286, "high_school_psychology": 0.5137614678899083, "high_school_statistics": 0.3101851851851852, "high_school_us_history": 0.5049019607843137, "high_school_world_history": 0.5443037974683544, "human_aging": 0.3632286995515695, "human_sexuality": 0.48854961832061067, "international_law": 0.5537190082644629, "jurisprudence": 0.4722222222222222, "logical_fallacies": 0.4662576687116564, "machine_learning": 0.33035714285714285, "management": 0.4563106796116505, "marketing": 0.6239316239316239, "medical_genetics": 0.45, "miscellaneous": 0.5632183908045977, "moral_disputes": 0.3699421965317919, "moral_scenarios": 0.23798882681564246, "nutrition": 0.41830065359477125, "philosophy": 0.43729903536977494, "prehistory": 0.41358024691358025, "professional_accounting": 0.3404255319148936, "professional_law": 0.35853976531942633, "professional_medicine": 0.4227941176470588, "professional_psychology": 0.39869281045751637, "public_relations": 0.4, "security_studies": 0.5020408163265306, "sociology": 0.6716417910447762, "us_foreign_policy": 0.59, "virology": 0.3674698795180723, "world_religions": 0.5555555555555556}}