cluster_loras / 29 /mmlu /metrics.json
Muqeeth's picture
Upload folder using huggingface_hub
9224edf verified
raw
history blame
3 kB
{"average_acc": 0.41660732089445945, "subcat_acc": {"math": 0.2800751879699248, "health": 0.4347560975609756, "physics": 0.346875, "business": 0.5766590389016019, "biology": 0.45374449339207046, "chemistry": 0.32673267326732675, "computer science": 0.38349514563106796, "economics": 0.3881401617250674, "engineering": 0.38620689655172413, "philosophy": 0.35785288270377735, "other": 0.4738197424892704, "history": 0.49032258064516127, "geography": 0.4898989898989899, "politics": 0.5401234567901234, "psychology": 0.4675885911840968, "culture": 0.5572289156626506, "law": 0.37266023823028926}, "cat_acc": {"STEM": 0.3442677269715043, "humanities": 0.3895855472901169, "social sciences": 0.4748131296717582, "other (business, health, misc.)": 0.4679210363972856}, "subjects": {"abstract_algebra": 0.23, "anatomy": 0.4740740740740741, "astronomy": 0.40131578947368424, "business_ethics": 0.47, "clinical_knowledge": 0.4528301886792453, "college_biology": 0.4513888888888889, "college_chemistry": 0.42, "college_computer_science": 0.36, "college_mathematics": 0.33, "college_medicine": 0.4277456647398844, "college_physics": 0.27450980392156865, "computer_security": 0.48, "conceptual_physics": 0.33617021276595743, "econometrics": 0.2807017543859649, "electrical_engineering": 0.38620689655172413, "elementary_mathematics": 0.25396825396825395, "formal_logic": 0.3888888888888889, "global_facts": 0.25, "high_school_biology": 0.45483870967741935, "high_school_chemistry": 0.28078817733990147, "high_school_computer_science": 0.33, "high_school_european_history": 0.5333333333333333, "high_school_geography": 0.4898989898989899, "high_school_government_and_politics": 0.6010362694300518, "high_school_macroeconomics": 0.4128205128205128, "high_school_mathematics": 0.23703703703703705, "high_school_microeconomics": 0.39915966386554624, "high_school_physics": 0.3576158940397351, "high_school_psychology": 0.5339449541284403, "high_school_statistics": 0.37962962962962965, "high_school_us_history": 0.5049019607843137, "high_school_world_history": 0.5316455696202531, "human_aging": 0.3991031390134529, "human_sexuality": 0.4732824427480916, "international_law": 0.5206611570247934, "jurisprudence": 0.4444444444444444, "logical_fallacies": 0.4601226993865031, "machine_learning": 0.36607142857142855, "management": 0.49514563106796117, "marketing": 0.6581196581196581, "medical_genetics": 0.48, "miscellaneous": 0.5478927203065134, "moral_disputes": 0.3815028901734104, "moral_scenarios": 0.23798882681564246, "nutrition": 0.43137254901960786, "philosophy": 0.47266881028938906, "prehistory": 0.42901234567901236, "professional_accounting": 0.3475177304964539, "professional_law": 0.3559322033898305, "professional_medicine": 0.4485294117647059, "professional_psychology": 0.4084967320261438, "public_relations": 0.44545454545454544, "security_studies": 0.5306122448979592, "sociology": 0.6119402985074627, "us_foreign_policy": 0.55, "virology": 0.3855421686746988, "world_religions": 0.6081871345029239}}