cluster_loras / 10 /mmlu /metrics.json
Muqeeth's picture
Upload folder using huggingface_hub
9224edf verified
raw
history blame
2.98 kB
{"average_acc": 0.4350519868964535, "subcat_acc": {"math": 0.28853383458646614, "health": 0.4548780487804878, "physics": 0.3375, "business": 0.5881006864988558, "biology": 0.47577092511013214, "chemistry": 0.34983498349834985, "computer science": 0.4053398058252427, "economics": 0.38274932614555257, "engineering": 0.43448275862068964, "philosophy": 0.3841948310139165, "other": 0.5201716738197425, "history": 0.524731182795699, "geography": 0.5050505050505051, "politics": 0.49382716049382713, "psychology": 0.49870354364736386, "culture": 0.6385542168674698, "law": 0.38060124787294386}, "cat_acc": {"STEM": 0.35619615639496355, "humanities": 0.4106269925611052, "social sciences": 0.48521286967825805, "other (business, health, misc.)": 0.4962985811227637}, "subjects": {"abstract_algebra": 0.23, "anatomy": 0.4888888888888889, "astronomy": 0.47368421052631576, "business_ethics": 0.47, "clinical_knowledge": 0.47547169811320755, "college_biology": 0.4097222222222222, "college_chemistry": 0.39, "college_computer_science": 0.35, "college_mathematics": 0.33, "college_medicine": 0.42196531791907516, "college_physics": 0.16666666666666666, "computer_security": 0.51, "conceptual_physics": 0.33617021276595743, "econometrics": 0.2631578947368421, "electrical_engineering": 0.43448275862068964, "elementary_mathematics": 0.2962962962962963, "formal_logic": 0.3333333333333333, "global_facts": 0.3, "high_school_biology": 0.5064516129032258, "high_school_chemistry": 0.33004926108374383, "high_school_computer_science": 0.43, "high_school_european_history": 0.5575757575757576, "high_school_geography": 0.5050505050505051, "high_school_government_and_politics": 0.5906735751295337, "high_school_macroeconomics": 0.4205128205128205, "high_school_mathematics": 0.26666666666666666, "high_school_microeconomics": 0.37815126050420167, "high_school_physics": 0.31788079470198677, "high_school_psychology": 0.5908256880733945, "high_school_statistics": 0.3101851851851852, "high_school_us_history": 0.5294117647058824, "high_school_world_history": 0.5485232067510548, "human_aging": 0.4349775784753363, "human_sexuality": 0.5648854961832062, "international_law": 0.5950413223140496, "jurisprudence": 0.4722222222222222, "logical_fallacies": 0.5460122699386503, "machine_learning": 0.3392857142857143, "management": 0.5339805825242718, "marketing": 0.6623931623931624, "medical_genetics": 0.57, "miscellaneous": 0.6028097062579821, "moral_disputes": 0.41329479768786126, "moral_scenarios": 0.2424581005586592, "nutrition": 0.4477124183006536, "philosophy": 0.5562700964630225, "prehistory": 0.4876543209876543, "professional_accounting": 0.36879432624113473, "professional_law": 0.35723598435462844, "professional_medicine": 0.4338235294117647, "professional_psychology": 0.4166666666666667, "public_relations": 0.44545454545454544, "security_studies": 0.4, "sociology": 0.6865671641791045, "us_foreign_policy": 0.59, "virology": 0.43373493975903615, "world_religions": 0.6374269005847953}}