cluster_loras / 14 /mmlu /metrics.json
Muqeeth's picture
Upload folder using huggingface_hub
9224edf verified
raw
history blame
2.98 kB
{"average_acc": 0.4205953567867825, "subcat_acc": {"math": 0.2725563909774436, "health": 0.44085365853658537, "physics": 0.3234375, "business": 0.551487414187643, "biology": 0.4669603524229075, "chemistry": 0.2871287128712871, "computer science": 0.39563106796116504, "economics": 0.38544474393531, "engineering": 0.42758620689655175, "philosophy": 0.36133200795228626, "other": 0.4978540772532189, "history": 0.5182795698924731, "geography": 0.51010101010101, "politics": 0.5370370370370371, "psychology": 0.46153846153846156, "culture": 0.5873493975903614, "law": 0.37889960294951786}, "cat_acc": {"STEM": 0.3383035122597747, "humanities": 0.3989373007438895, "social sciences": 0.4757881052973676, "other (business, health, misc.)": 0.47624922887106724}, "subjects": {"abstract_algebra": 0.24, "anatomy": 0.45925925925925926, "astronomy": 0.40789473684210525, "business_ethics": 0.46, "clinical_knowledge": 0.44528301886792454, "college_biology": 0.4583333333333333, "college_chemistry": 0.36, "college_computer_science": 0.34, "college_mathematics": 0.32, "college_medicine": 0.41040462427745666, "college_physics": 0.21568627450980393, "computer_security": 0.48, "conceptual_physics": 0.3446808510638298, "econometrics": 0.2543859649122807, "electrical_engineering": 0.42758620689655175, "elementary_mathematics": 0.2566137566137566, "formal_logic": 0.40476190476190477, "global_facts": 0.23, "high_school_biology": 0.47096774193548385, "high_school_chemistry": 0.2512315270935961, "high_school_computer_science": 0.4, "high_school_european_history": 0.5818181818181818, "high_school_geography": 0.51010101010101, "high_school_government_and_politics": 0.5854922279792746, "high_school_macroeconomics": 0.41794871794871796, "high_school_mathematics": 0.22962962962962963, "high_school_microeconomics": 0.3949579831932773, "high_school_physics": 0.2781456953642384, "high_school_psychology": 0.5321100917431193, "high_school_statistics": 0.3472222222222222, "high_school_us_history": 0.5098039215686274, "high_school_world_history": 0.569620253164557, "human_aging": 0.4260089686098655, "human_sexuality": 0.5190839694656488, "international_law": 0.5537190082644629, "jurisprudence": 0.5, "logical_fallacies": 0.4785276073619632, "machine_learning": 0.36607142857142855, "management": 0.46601941747572817, "marketing": 0.6282051282051282, "medical_genetics": 0.48, "miscellaneous": 0.5708812260536399, "moral_disputes": 0.3786127167630058, "moral_scenarios": 0.23798882681564246, "nutrition": 0.4477124183006536, "philosophy": 0.4887459807073955, "prehistory": 0.4537037037037037, "professional_accounting": 0.3900709219858156, "professional_law": 0.35658409387222945, "professional_medicine": 0.45955882352941174, "professional_psychology": 0.39869281045751637, "public_relations": 0.43636363636363634, "security_studies": 0.5224489795918368, "sociology": 0.6318407960199005, "us_foreign_policy": 0.59, "virology": 0.4036144578313253, "world_religions": 0.5964912280701754}}