{ "results": { "hendrycksTest-abstract_algebra": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "hendrycksTest-anatomy": { "acc": 0.4, "acc_stderr": 0.04232073695151589, "acc_norm": 0.4, "acc_norm_stderr": 0.04232073695151589 }, "hendrycksTest-astronomy": { "acc": 0.3684210526315789, "acc_stderr": 0.03925523381052932, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.03925523381052932 }, "hendrycksTest-business_ethics": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "hendrycksTest-clinical_knowledge": { "acc": 0.42641509433962266, "acc_stderr": 0.030437794342983045, "acc_norm": 0.42641509433962266, "acc_norm_stderr": 0.030437794342983045 }, "hendrycksTest-college_biology": { "acc": 0.3680555555555556, "acc_stderr": 0.040329990539607195, "acc_norm": 0.3680555555555556, "acc_norm_stderr": 0.040329990539607195 }, "hendrycksTest-college_chemistry": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "hendrycksTest-college_computer_science": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "hendrycksTest-college_mathematics": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "hendrycksTest-college_medicine": { "acc": 0.3063583815028902, "acc_stderr": 0.03514942551267437, "acc_norm": 0.3063583815028902, "acc_norm_stderr": 0.03514942551267437 }, "hendrycksTest-college_physics": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171453, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171453 }, "hendrycksTest-computer_security": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "hendrycksTest-conceptual_physics": { "acc": 0.3617021276595745, "acc_stderr": 0.03141082197596239, "acc_norm": 0.3617021276595745, "acc_norm_stderr": 0.03141082197596239 }, "hendrycksTest-econometrics": { "acc": 0.2982456140350877, "acc_stderr": 0.043036840335373146, "acc_norm": 0.2982456140350877, "acc_norm_stderr": 0.043036840335373146 }, "hendrycksTest-electrical_engineering": { "acc": 0.4, "acc_stderr": 0.04082482904638629, "acc_norm": 0.4, "acc_norm_stderr": 0.04082482904638629 }, "hendrycksTest-elementary_mathematics": { "acc": 0.2698412698412698, "acc_stderr": 0.02286083830923207, "acc_norm": 0.2698412698412698, "acc_norm_stderr": 0.02286083830923207 }, "hendrycksTest-formal_logic": { "acc": 0.2777777777777778, "acc_stderr": 0.04006168083848876, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.04006168083848876 }, "hendrycksTest-global_facts": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "hendrycksTest-high_school_biology": { "acc": 0.43870967741935485, "acc_stderr": 0.028229497320317213, "acc_norm": 0.43870967741935485, "acc_norm_stderr": 0.028229497320317213 }, "hendrycksTest-high_school_chemistry": { "acc": 0.27586206896551724, "acc_stderr": 0.03144712581678241, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.03144712581678241 }, "hendrycksTest-high_school_computer_science": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "hendrycksTest-high_school_european_history": { "acc": 0.5636363636363636, "acc_stderr": 0.03872592983524754, "acc_norm": 0.5636363636363636, "acc_norm_stderr": 0.03872592983524754 }, "hendrycksTest-high_school_geography": { "acc": 0.4494949494949495, "acc_stderr": 0.0354413249194797, "acc_norm": 0.4494949494949495, "acc_norm_stderr": 0.0354413249194797 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.533678756476684, "acc_stderr": 0.036002440698671784, "acc_norm": 0.533678756476684, "acc_norm_stderr": 0.036002440698671784 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.3230769230769231, "acc_stderr": 0.023710888501970562, "acc_norm": 0.3230769230769231, "acc_norm_stderr": 0.023710888501970562 }, "hendrycksTest-high_school_mathematics": { "acc": 0.24814814814814815, "acc_stderr": 0.0263357394040558, "acc_norm": 0.24814814814814815, "acc_norm_stderr": 0.0263357394040558 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.3739495798319328, "acc_stderr": 0.03142946637883708, "acc_norm": 0.3739495798319328, "acc_norm_stderr": 0.03142946637883708 }, "hendrycksTest-high_school_physics": { "acc": 0.304635761589404, "acc_stderr": 0.037579499229433426, "acc_norm": 0.304635761589404, "acc_norm_stderr": 0.037579499229433426 }, "hendrycksTest-high_school_psychology": { "acc": 0.4990825688073395, "acc_stderr": 0.021437287056051215, "acc_norm": 0.4990825688073395, "acc_norm_stderr": 0.021437287056051215 }, "hendrycksTest-high_school_statistics": { "acc": 0.27314814814814814, "acc_stderr": 0.030388051301678116, "acc_norm": 0.27314814814814814, "acc_norm_stderr": 0.030388051301678116 }, "hendrycksTest-high_school_us_history": { "acc": 0.5147058823529411, "acc_stderr": 0.03507793834791323, "acc_norm": 0.5147058823529411, "acc_norm_stderr": 0.03507793834791323 }, "hendrycksTest-high_school_world_history": { "acc": 0.5611814345991561, "acc_stderr": 0.032302649315470375, "acc_norm": 0.5611814345991561, "acc_norm_stderr": 0.032302649315470375 }, "hendrycksTest-human_aging": { "acc": 0.47085201793721976, "acc_stderr": 0.03350073248773404, "acc_norm": 0.47085201793721976, "acc_norm_stderr": 0.03350073248773404 }, "hendrycksTest-human_sexuality": { "acc": 0.45038167938931295, "acc_stderr": 0.04363643698524779, "acc_norm": 0.45038167938931295, "acc_norm_stderr": 0.04363643698524779 }, "hendrycksTest-international_law": { "acc": 0.628099173553719, "acc_stderr": 0.04412015806624504, "acc_norm": 0.628099173553719, "acc_norm_stderr": 0.04412015806624504 }, "hendrycksTest-jurisprudence": { "acc": 0.4074074074074074, "acc_stderr": 0.04750077341199986, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.04750077341199986 }, "hendrycksTest-logical_fallacies": { "acc": 0.48466257668711654, "acc_stderr": 0.03926522378708843, "acc_norm": 0.48466257668711654, "acc_norm_stderr": 0.03926522378708843 }, "hendrycksTest-machine_learning": { "acc": 0.4107142857142857, "acc_stderr": 0.04669510663875191, "acc_norm": 0.4107142857142857, "acc_norm_stderr": 0.04669510663875191 }, "hendrycksTest-management": { "acc": 0.4563106796116505, "acc_stderr": 0.049318019942204146, "acc_norm": 0.4563106796116505, "acc_norm_stderr": 0.049318019942204146 }, "hendrycksTest-marketing": { "acc": 0.6367521367521367, "acc_stderr": 0.03150712523091264, "acc_norm": 0.6367521367521367, "acc_norm_stderr": 0.03150712523091264 }, "hendrycksTest-medical_genetics": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "hendrycksTest-miscellaneous": { "acc": 0.5606641123882503, "acc_stderr": 0.017747874245683606, "acc_norm": 0.5606641123882503, "acc_norm_stderr": 0.017747874245683606 }, "hendrycksTest-moral_disputes": { "acc": 0.47109826589595377, "acc_stderr": 0.026874085883518348, "acc_norm": 0.47109826589595377, "acc_norm_stderr": 0.026874085883518348 }, "hendrycksTest-moral_scenarios": { "acc": 0.23798882681564246, "acc_stderr": 0.014242630070574915, "acc_norm": 0.23798882681564246, "acc_norm_stderr": 0.014242630070574915 }, "hendrycksTest-nutrition": { "acc": 0.434640522875817, "acc_stderr": 0.028384256704883037, "acc_norm": 0.434640522875817, "acc_norm_stderr": 0.028384256704883037 }, "hendrycksTest-philosophy": { "acc": 0.4758842443729904, "acc_stderr": 0.028365041542564577, "acc_norm": 0.4758842443729904, "acc_norm_stderr": 0.028365041542564577 }, "hendrycksTest-prehistory": { "acc": 0.4537037037037037, "acc_stderr": 0.027701228468542602, "acc_norm": 0.4537037037037037, "acc_norm_stderr": 0.027701228468542602 }, "hendrycksTest-professional_accounting": { "acc": 0.32978723404255317, "acc_stderr": 0.028045946942042398, "acc_norm": 0.32978723404255317, "acc_norm_stderr": 0.028045946942042398 }, "hendrycksTest-professional_law": { "acc": 0.3494132985658409, "acc_stderr": 0.012177306252786686, "acc_norm": 0.3494132985658409, "acc_norm_stderr": 0.012177306252786686 }, "hendrycksTest-professional_medicine": { "acc": 0.39705882352941174, "acc_stderr": 0.029722152099280058, "acc_norm": 0.39705882352941174, "acc_norm_stderr": 0.029722152099280058 }, "hendrycksTest-professional_psychology": { "acc": 0.41013071895424835, "acc_stderr": 0.019898412717635913, "acc_norm": 0.41013071895424835, "acc_norm_stderr": 0.019898412717635913 }, "hendrycksTest-public_relations": { "acc": 0.4727272727272727, "acc_stderr": 0.04782001791380063, "acc_norm": 0.4727272727272727, "acc_norm_stderr": 0.04782001791380063 }, "hendrycksTest-security_studies": { "acc": 0.4163265306122449, "acc_stderr": 0.03155782816556164, "acc_norm": 0.4163265306122449, "acc_norm_stderr": 0.03155782816556164 }, "hendrycksTest-sociology": { "acc": 0.5422885572139303, "acc_stderr": 0.03522865864099597, "acc_norm": 0.5422885572139303, "acc_norm_stderr": 0.03522865864099597 }, "hendrycksTest-us_foreign_policy": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "hendrycksTest-virology": { "acc": 0.4397590361445783, "acc_stderr": 0.03864139923699121, "acc_norm": 0.4397590361445783, "acc_norm_stderr": 0.03864139923699121 }, "hendrycksTest-world_religions": { "acc": 0.5789473684210527, "acc_stderr": 0.03786720706234214, "acc_norm": 0.5789473684210527, "acc_norm_stderr": 0.03786720706234214 } }, "versions": { "hendrycksTest-abstract_algebra": 1, "hendrycksTest-anatomy": 1, "hendrycksTest-astronomy": 1, "hendrycksTest-business_ethics": 1, "hendrycksTest-clinical_knowledge": 1, "hendrycksTest-college_biology": 1, "hendrycksTest-college_chemistry": 1, "hendrycksTest-college_computer_science": 1, "hendrycksTest-college_mathematics": 1, "hendrycksTest-college_medicine": 1, "hendrycksTest-college_physics": 1, "hendrycksTest-computer_security": 1, "hendrycksTest-conceptual_physics": 1, "hendrycksTest-econometrics": 1, "hendrycksTest-electrical_engineering": 1, "hendrycksTest-elementary_mathematics": 1, "hendrycksTest-formal_logic": 1, "hendrycksTest-global_facts": 1, "hendrycksTest-high_school_biology": 1, "hendrycksTest-high_school_chemistry": 1, "hendrycksTest-high_school_computer_science": 1, "hendrycksTest-high_school_european_history": 1, "hendrycksTest-high_school_geography": 1, "hendrycksTest-high_school_government_and_politics": 1, "hendrycksTest-high_school_macroeconomics": 1, "hendrycksTest-high_school_mathematics": 1, "hendrycksTest-high_school_microeconomics": 1, "hendrycksTest-high_school_physics": 1, "hendrycksTest-high_school_psychology": 1, "hendrycksTest-high_school_statistics": 1, "hendrycksTest-high_school_us_history": 1, "hendrycksTest-high_school_world_history": 1, "hendrycksTest-human_aging": 1, "hendrycksTest-human_sexuality": 1, "hendrycksTest-international_law": 1, "hendrycksTest-jurisprudence": 1, "hendrycksTest-logical_fallacies": 1, "hendrycksTest-machine_learning": 1, "hendrycksTest-management": 1, "hendrycksTest-marketing": 1, "hendrycksTest-medical_genetics": 1, "hendrycksTest-miscellaneous": 1, "hendrycksTest-moral_disputes": 1, "hendrycksTest-moral_scenarios": 1, "hendrycksTest-nutrition": 1, "hendrycksTest-philosophy": 1, "hendrycksTest-prehistory": 1, "hendrycksTest-professional_accounting": 1, "hendrycksTest-professional_law": 1, "hendrycksTest-professional_medicine": 1, "hendrycksTest-professional_psychology": 1, "hendrycksTest-public_relations": 1, "hendrycksTest-security_studies": 1, "hendrycksTest-sociology": 1, "hendrycksTest-us_foreign_policy": 1, "hendrycksTest-virology": 1, "hendrycksTest-world_religions": 1 }, "config": { "model": "sparseml", "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse50_45B_retrained/ultrachat200k/llama2_7B_45B_sparse50_LR2e-4_GC2_E2/training,dtype=bfloat16", "num_fewshot": 5, "batch_size": "4", "batch_sizes": [], "device": "cuda:6", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }