cluster_loras / 23 /mmlu /metrics.json
Muqeeth's picture
Upload folder using huggingface_hub
9224edf verified
raw
history blame
2.97 kB
{"average_acc": 0.41774675972083747, "subcat_acc": {"math": 0.28477443609022557, "health": 0.4451219512195122, "physics": 0.3328125, "business": 0.5583524027459954, "biology": 0.45154185022026433, "chemistry": 0.32673267326732675, "computer science": 0.36893203883495146, "economics": 0.3935309973045822, "engineering": 0.3931034482758621, "philosophy": 0.3518886679920477, "other": 0.47296137339055794, "history": 0.5075268817204301, "geography": 0.46464646464646464, "politics": 0.5169753086419753, "psychology": 0.4788245462402766, "culture": 0.608433734939759, "law": 0.37266023823028926}, "cat_acc": {"STEM": 0.34095427435387676, "humanities": 0.3904357066950053, "social sciences": 0.4793630159246019, "other (business, health, misc.)": 0.4703886489821098}, "subjects": {"abstract_algebra": 0.26, "anatomy": 0.4888888888888889, "astronomy": 0.4407894736842105, "business_ethics": 0.49, "clinical_knowledge": 0.45660377358490567, "college_biology": 0.4652777777777778, "college_chemistry": 0.36, "college_computer_science": 0.35, "college_mathematics": 0.33, "college_medicine": 0.44508670520231214, "college_physics": 0.19607843137254902, "computer_security": 0.42, "conceptual_physics": 0.3617021276595745, "econometrics": 0.2719298245614035, "electrical_engineering": 0.3931034482758621, "elementary_mathematics": 0.26455026455026454, "formal_logic": 0.3333333333333333, "global_facts": 0.32, "high_school_biology": 0.44516129032258067, "high_school_chemistry": 0.3103448275862069, "high_school_computer_science": 0.41, "high_school_european_history": 0.5515151515151515, "high_school_geography": 0.46464646464646464, "high_school_government_and_politics": 0.5906735751295337, "high_school_macroeconomics": 0.4256410256410256, "high_school_mathematics": 0.25555555555555554, "high_school_microeconomics": 0.39915966386554624, "high_school_physics": 0.271523178807947, "high_school_psychology": 0.544954128440367, "high_school_statistics": 0.3472222222222222, "high_school_us_history": 0.5, "high_school_world_history": 0.569620253164557, "human_aging": 0.3991031390134529, "human_sexuality": 0.5343511450381679, "international_law": 0.5702479338842975, "jurisprudence": 0.4537037037037037, "logical_fallacies": 0.48466257668711654, "machine_learning": 0.30357142857142855, "management": 0.46601941747572817, "marketing": 0.6282051282051282, "medical_genetics": 0.46, "miscellaneous": 0.5287356321839081, "moral_disputes": 0.37283236994219654, "moral_scenarios": 0.23798882681564246, "nutrition": 0.46078431372549017, "philosophy": 0.4694533762057878, "prehistory": 0.4444444444444444, "professional_accounting": 0.3723404255319149, "professional_law": 0.3513689700130378, "professional_medicine": 0.4411764705882353, "professional_psychology": 0.4199346405228758, "public_relations": 0.4, "security_studies": 0.47346938775510206, "sociology": 0.6567164179104478, "us_foreign_policy": 0.61, "virology": 0.42168674698795183, "world_religions": 0.5789473684210527}}