cluster_loras / 30 /mmlu /metrics.json
Muqeeth's picture
Upload folder using huggingface_hub
9224edf verified
{"average_acc": 0.4038598490243555, "subcat_acc": {"math": 0.29793233082706766, "health": 0.424390243902439, "physics": 0.35, "business": 0.5583524027459954, "biology": 0.44933920704845814, "chemistry": 0.35313531353135313, "computer science": 0.36650485436893204, "economics": 0.41778975741239893, "engineering": 0.41379310344827586, "philosophy": 0.3364811133200795, "other": 0.4532188841201717, "history": 0.432258064516129, "geography": 0.45454545454545453, "politics": 0.5061728395061729, "psychology": 0.45721694036300775, "culture": 0.5210843373493976, "law": 0.3579126488939308}, "cat_acc": {"STEM": 0.35222001325381047, "humanities": 0.36344314558979807, "social sciences": 0.4647383815404615, "other (business, health, misc.)": 0.4528069093152375}, "subjects": {"abstract_algebra": 0.29, "anatomy": 0.45925925925925926, "astronomy": 0.4407894736842105, "business_ethics": 0.43, "clinical_knowledge": 0.4490566037735849, "college_biology": 0.4583333333333333, "college_chemistry": 0.42, "college_computer_science": 0.32, "college_mathematics": 0.32, "college_medicine": 0.45664739884393063, "college_physics": 0.2647058823529412, "computer_security": 0.43, "conceptual_physics": 0.3446808510638298, "econometrics": 0.2807017543859649, "electrical_engineering": 0.41379310344827586, "elementary_mathematics": 0.2671957671957672, "formal_logic": 0.35714285714285715, "global_facts": 0.26, "high_school_biology": 0.44516129032258067, "high_school_chemistry": 0.32019704433497537, "high_school_computer_science": 0.38, "high_school_european_history": 0.47878787878787876, "high_school_geography": 0.45454545454545453, "high_school_government_and_politics": 0.5751295336787565, "high_school_macroeconomics": 0.44871794871794873, "high_school_mathematics": 0.26296296296296295, "high_school_microeconomics": 0.4327731092436975, "high_school_physics": 0.32450331125827814, "high_school_psychology": 0.5577981651376147, "high_school_statistics": 0.3888888888888889, "high_school_us_history": 0.46078431372549017, "high_school_world_history": 0.4388185654008439, "human_aging": 0.3183856502242152, "human_sexuality": 0.4732824427480916, "international_law": 0.4049586776859504, "jurisprudence": 0.3888888888888889, "logical_fallacies": 0.38650306748466257, "machine_learning": 0.3392857142857143, "management": 0.47572815533980584, "marketing": 0.6495726495726496, "medical_genetics": 0.39, "miscellaneous": 0.5274584929757343, "moral_disputes": 0.3179190751445087, "moral_scenarios": 0.2424581005586592, "nutrition": 0.4542483660130719, "philosophy": 0.4662379421221865, "prehistory": 0.38580246913580246, "professional_accounting": 0.31560283687943264, "professional_law": 0.3520208604954368, "professional_medicine": 0.47058823529411764, "professional_psychology": 0.36764705882352944, "public_relations": 0.4727272727272727, "security_studies": 0.46122448979591835, "sociology": 0.5522388059701493, "us_foreign_policy": 0.52, "virology": 0.35542168674698793, "world_religions": 0.5672514619883041}}