cluster_loras / 3 /mmlu /metrics.json
Muqeeth's picture
Upload folder using huggingface_hub
9224edf verified
raw
history blame
2.98 kB
{"average_acc": 0.4114086312491098, "subcat_acc": {"math": 0.2819548872180451, "health": 0.42865853658536585, "physics": 0.3390625, "business": 0.5469107551487414, "biology": 0.44493392070484583, "chemistry": 0.3102310231023102, "computer science": 0.3907766990291262, "economics": 0.38140161725067384, "engineering": 0.35172413793103446, "philosophy": 0.35685884691848907, "other": 0.4678111587982833, "history": 0.4935483870967742, "geography": 0.4797979797979798, "politics": 0.5185185185185185, "psychology": 0.45030250648228176, "culture": 0.5813253012048193, "law": 0.37436188315371527}, "cat_acc": {"STEM": 0.3396288933068257, "humanities": 0.3904357066950053, "social sciences": 0.46408839779005523, "other (business, health, misc.)": 0.4586674892041949}, "subjects": {"abstract_algebra": 0.24, "anatomy": 0.4222222222222222, "astronomy": 0.40131578947368424, "business_ethics": 0.44, "clinical_knowledge": 0.4490566037735849, "college_biology": 0.4375, "college_chemistry": 0.39, "college_computer_science": 0.33, "college_mathematics": 0.32, "college_medicine": 0.43352601156069365, "college_physics": 0.20588235294117646, "computer_security": 0.48, "conceptual_physics": 0.3617021276595745, "econometrics": 0.2894736842105263, "electrical_engineering": 0.35172413793103446, "elementary_mathematics": 0.26455026455026454, "formal_logic": 0.3888888888888889, "global_facts": 0.25, "high_school_biology": 0.4483870967741935, "high_school_chemistry": 0.270935960591133, "high_school_computer_science": 0.39, "high_school_european_history": 0.5272727272727272, "high_school_geography": 0.4797979797979798, "high_school_government_and_politics": 0.5647668393782384, "high_school_macroeconomics": 0.3974358974358974, "high_school_mathematics": 0.2518518518518518, "high_school_microeconomics": 0.39915966386554624, "high_school_physics": 0.33112582781456956, "high_school_psychology": 0.5082568807339449, "high_school_statistics": 0.35185185185185186, "high_school_us_history": 0.5, "high_school_world_history": 0.5443037974683544, "human_aging": 0.4125560538116592, "human_sexuality": 0.5114503816793893, "international_law": 0.5289256198347108, "jurisprudence": 0.4351851851851852, "logical_fallacies": 0.44171779141104295, "machine_learning": 0.36607142857142855, "management": 0.44660194174757284, "marketing": 0.6367521367521367, "medical_genetics": 0.46, "miscellaneous": 0.5402298850574713, "moral_disputes": 0.3930635838150289, "moral_scenarios": 0.23798882681564246, "nutrition": 0.42810457516339867, "philosophy": 0.47266881028938906, "prehistory": 0.4351851851851852, "professional_accounting": 0.34397163120567376, "professional_law": 0.3578878748370274, "professional_medicine": 0.4117647058823529, "professional_psychology": 0.39869281045751637, "public_relations": 0.4090909090909091, "security_studies": 0.5102040816326531, "sociology": 0.6268656716417911, "us_foreign_policy": 0.57, "virology": 0.42771084337349397, "world_religions": 0.5906432748538012}}