cluster_loras / 17 /mmlu /metrics.json
Muqeeth's picture
Upload folder using huggingface_hub
9224edf verified
{"average_acc": 0.4143284432417035, "subcat_acc": {"math": 0.29135338345864664, "health": 0.4304878048780488, "physics": 0.34375, "business": 0.5835240274599542, "biology": 0.4581497797356828, "chemistry": 0.31353135313531355, "computer science": 0.3786407766990291, "economics": 0.3948787061994609, "engineering": 0.36551724137931035, "philosophy": 0.3474155069582505, "other": 0.4660944206008584, "history": 0.4956989247311828, "geography": 0.5, "politics": 0.529320987654321, "psychology": 0.46672428694900603, "culture": 0.5783132530120482, "law": 0.36585365853658536}, "cat_acc": {"STEM": 0.3452617627567926, "humanities": 0.383634431455898, "social sciences": 0.4767630809229769, "other (business, health, misc.)": 0.4639111659469463}, "subjects": {"abstract_algebra": 0.21, "anatomy": 0.45185185185185184, "astronomy": 0.40789473684210525, "business_ethics": 0.48, "clinical_knowledge": 0.4339622641509434, "college_biology": 0.4652777777777778, "college_chemistry": 0.39, "college_computer_science": 0.36, "college_mathematics": 0.33, "college_medicine": 0.4161849710982659, "college_physics": 0.28431372549019607, "computer_security": 0.47, "conceptual_physics": 0.3617021276595745, "econometrics": 0.2894736842105263, "electrical_engineering": 0.36551724137931035, "elementary_mathematics": 0.2724867724867725, "formal_logic": 0.3968253968253968, "global_facts": 0.21, "high_school_biology": 0.45483870967741935, "high_school_chemistry": 0.27586206896551724, "high_school_computer_science": 0.34, "high_school_european_history": 0.5757575757575758, "high_school_geography": 0.5, "high_school_government_and_politics": 0.5906735751295337, "high_school_macroeconomics": 0.4153846153846154, "high_school_mathematics": 0.2518518518518518, "high_school_microeconomics": 0.4117647058823529, "high_school_physics": 0.2913907284768212, "high_school_psychology": 0.5339449541284403, "high_school_statistics": 0.39351851851851855, "high_school_us_history": 0.47549019607843135, "high_school_world_history": 0.5443037974683544, "human_aging": 0.39461883408071746, "human_sexuality": 0.48091603053435117, "international_law": 0.512396694214876, "jurisprudence": 0.48148148148148145, "logical_fallacies": 0.43558282208588955, "machine_learning": 0.3482142857142857, "management": 0.5242718446601942, "marketing": 0.6538461538461539, "medical_genetics": 0.47, "miscellaneous": 0.5427841634738186, "moral_disputes": 0.33815028901734107, "moral_scenarios": 0.23798882681564246, "nutrition": 0.4084967320261438, "philosophy": 0.47266881028938906, "prehistory": 0.43209876543209874, "professional_accounting": 0.34397163120567376, "professional_law": 0.34615384615384615, "professional_medicine": 0.4963235294117647, "professional_psychology": 0.4068627450980392, "public_relations": 0.41818181818181815, "security_studies": 0.5102040816326531, "sociology": 0.6417910447761194, "us_foreign_policy": 0.58, "virology": 0.3795180722891566, "world_religions": 0.5906432748538012}}