cluster_loras / 19 /mmlu /metrics.json
Muqeeth's picture
Upload folder using huggingface_hub
9224edf verified
{"average_acc": 0.4169633955277026, "subcat_acc": {"math": 0.3092105263157895, "health": 0.43597560975609756, "physics": 0.340625, "business": 0.5675057208237986, "biology": 0.460352422907489, "chemistry": 0.36633663366336633, "computer science": 0.3325242718446602, "economics": 0.42048517520215634, "engineering": 0.3931034482758621, "philosophy": 0.34840954274353875, "other": 0.47296137339055794, "history": 0.46344086021505376, "geography": 0.4696969696969697, "politics": 0.529320987654321, "psychology": 0.4762316335350043, "culture": 0.5421686746987951, "law": 0.37946681792399317}, "cat_acc": {"STEM": 0.35155732273028495, "humanities": 0.38278427205100957, "social sciences": 0.48066298342541436, "other (business, health, misc.)": 0.46699568167797656}, "subjects": {"abstract_algebra": 0.28, "anatomy": 0.4740740740740741, "astronomy": 0.40789473684210525, "business_ethics": 0.42, "clinical_knowledge": 0.4679245283018868, "college_biology": 0.4444444444444444, "college_chemistry": 0.44, "college_computer_science": 0.32, "college_mathematics": 0.33, "college_medicine": 0.4508670520231214, "college_physics": 0.28431372549019607, "computer_security": 0.45, "conceptual_physics": 0.32340425531914896, "econometrics": 0.2894736842105263, "electrical_engineering": 0.3931034482758621, "elementary_mathematics": 0.29894179894179895, "formal_logic": 0.3492063492063492, "global_facts": 0.23, "high_school_biology": 0.46774193548387094, "high_school_chemistry": 0.33004926108374383, "high_school_computer_science": 0.31, "high_school_european_history": 0.5212121212121212, "high_school_geography": 0.4696969696969697, "high_school_government_and_politics": 0.5958549222797928, "high_school_macroeconomics": 0.45897435897435895, "high_school_mathematics": 0.24814814814814815, "high_school_microeconomics": 0.42016806722689076, "high_school_physics": 0.33774834437086093, "high_school_psychology": 0.5706422018348624, "high_school_statistics": 0.4074074074074074, "high_school_us_history": 0.46568627450980393, "high_school_world_history": 0.4641350210970464, "human_aging": 0.34080717488789236, "human_sexuality": 0.48854961832061067, "international_law": 0.49586776859504134, "jurisprudence": 0.4537037037037037, "logical_fallacies": 0.44171779141104295, "machine_learning": 0.25892857142857145, "management": 0.5242718446601942, "marketing": 0.6495726495726496, "medical_genetics": 0.47, "miscellaneous": 0.5568326947637292, "moral_disputes": 0.34971098265895956, "moral_scenarios": 0.24804469273743016, "nutrition": 0.4411764705882353, "philosophy": 0.4565916398713826, "prehistory": 0.43209876543209874, "professional_accounting": 0.3262411347517731, "professional_law": 0.3650586701434159, "professional_medicine": 0.4522058823529412, "professional_psychology": 0.39215686274509803, "public_relations": 0.45454545454545453, "security_studies": 0.49795918367346936, "sociology": 0.5771144278606966, "us_foreign_policy": 0.56, "virology": 0.40963855421686746, "world_religions": 0.5847953216374269}}