{ "results": { "hendrycksTest-abstract_algebra": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "hendrycksTest-anatomy": { "acc": 0.45185185185185184, "acc_stderr": 0.04299268905480864, "acc_norm": 0.45185185185185184, "acc_norm_stderr": 0.04299268905480864 }, "hendrycksTest-astronomy": { "acc": 0.42105263157894735, "acc_stderr": 0.040179012759817494, "acc_norm": 0.42105263157894735, "acc_norm_stderr": 0.040179012759817494 }, "hendrycksTest-business_ethics": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "hendrycksTest-clinical_knowledge": { "acc": 0.4679245283018868, "acc_stderr": 0.030709486992556545, "acc_norm": 0.4679245283018868, "acc_norm_stderr": 0.030709486992556545 }, "hendrycksTest-college_biology": { "acc": 0.4513888888888889, "acc_stderr": 0.04161402398403279, "acc_norm": 0.4513888888888889, "acc_norm_stderr": 0.04161402398403279 }, "hendrycksTest-college_chemistry": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "hendrycksTest-college_computer_science": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "hendrycksTest-college_mathematics": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "hendrycksTest-college_medicine": { "acc": 0.4161849710982659, "acc_stderr": 0.03758517775404947, "acc_norm": 0.4161849710982659, "acc_norm_stderr": 0.03758517775404947 }, "hendrycksTest-college_physics": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617746, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617746 }, "hendrycksTest-computer_security": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "hendrycksTest-conceptual_physics": { "acc": 0.37872340425531914, "acc_stderr": 0.03170995606040655, "acc_norm": 0.37872340425531914, "acc_norm_stderr": 0.03170995606040655 }, "hendrycksTest-econometrics": { "acc": 0.3333333333333333, "acc_stderr": 0.044346007015849245, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.044346007015849245 }, "hendrycksTest-electrical_engineering": { "acc": 0.38620689655172413, "acc_stderr": 0.04057324734419035, "acc_norm": 0.38620689655172413, "acc_norm_stderr": 0.04057324734419035 }, "hendrycksTest-elementary_mathematics": { "acc": 0.2830687830687831, "acc_stderr": 0.023201392938194974, "acc_norm": 0.2830687830687831, "acc_norm_stderr": 0.023201392938194974 }, "hendrycksTest-formal_logic": { "acc": 0.2222222222222222, "acc_stderr": 0.037184890068181146, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.037184890068181146 }, "hendrycksTest-global_facts": { "acc": 0.34, "acc_stderr": 0.047609522856952365, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952365 }, "hendrycksTest-high_school_biology": { "acc": 0.4838709677419355, "acc_stderr": 0.028429203176724555, "acc_norm": 0.4838709677419355, "acc_norm_stderr": 0.028429203176724555 }, "hendrycksTest-high_school_chemistry": { "acc": 0.28078817733990147, "acc_stderr": 0.03161856335358608, "acc_norm": 0.28078817733990147, "acc_norm_stderr": 0.03161856335358608 }, "hendrycksTest-high_school_computer_science": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "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": 0.4898989898989899, "acc_stderr": 0.035616254886737454, "acc_norm": 0.4898989898989899, "acc_norm_stderr": 0.035616254886737454 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.6787564766839378, "acc_stderr": 0.033699508685490674, "acc_norm": 0.6787564766839378, "acc_norm_stderr": 0.033699508685490674 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.4, "acc_stderr": 0.024838811988033165, "acc_norm": 0.4, "acc_norm_stderr": 0.024838811988033165 }, "hendrycksTest-high_school_mathematics": { "acc": 0.2740740740740741, "acc_stderr": 0.027195934804085622, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.027195934804085622 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.3865546218487395, "acc_stderr": 0.0316314580755238, "acc_norm": 0.3865546218487395, "acc_norm_stderr": 0.0316314580755238 }, "hendrycksTest-high_school_physics": { "acc": 0.2847682119205298, "acc_stderr": 0.03684881521389023, "acc_norm": 0.2847682119205298, "acc_norm_stderr": 0.03684881521389023 }, "hendrycksTest-high_school_psychology": { "acc": 0.6073394495412844, "acc_stderr": 0.020937505161201096, "acc_norm": 0.6073394495412844, "acc_norm_stderr": 0.020937505161201096 }, "hendrycksTest-high_school_statistics": { "acc": 0.4027777777777778, "acc_stderr": 0.03344887382997866, "acc_norm": 0.4027777777777778, "acc_norm_stderr": 0.03344887382997866 }, "hendrycksTest-high_school_us_history": { "acc": 0.5490196078431373, "acc_stderr": 0.03492406104163613, "acc_norm": 0.5490196078431373, "acc_norm_stderr": 0.03492406104163613 }, "hendrycksTest-high_school_world_history": { "acc": 0.6244725738396625, "acc_stderr": 0.03152256243091156, "acc_norm": 0.6244725738396625, "acc_norm_stderr": 0.03152256243091156 }, "hendrycksTest-human_aging": { "acc": 0.48878923766816146, "acc_stderr": 0.033549366530984746, "acc_norm": 0.48878923766816146, "acc_norm_stderr": 0.033549366530984746 }, "hendrycksTest-human_sexuality": { "acc": 0.4961832061068702, "acc_stderr": 0.04385162325601553, "acc_norm": 0.4961832061068702, "acc_norm_stderr": 0.04385162325601553 }, "hendrycksTest-international_law": { "acc": 0.6446280991735537, "acc_stderr": 0.04369236326573981, "acc_norm": 0.6446280991735537, "acc_norm_stderr": 0.04369236326573981 }, "hendrycksTest-jurisprudence": { "acc": 0.48148148148148145, "acc_stderr": 0.04830366024635331, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.04830366024635331 }, "hendrycksTest-logical_fallacies": { "acc": 0.4171779141104294, "acc_stderr": 0.038741028598180814, "acc_norm": 0.4171779141104294, "acc_norm_stderr": 0.038741028598180814 }, "hendrycksTest-machine_learning": { "acc": 0.3125, "acc_stderr": 0.043994650575715215, "acc_norm": 0.3125, "acc_norm_stderr": 0.043994650575715215 }, "hendrycksTest-management": { "acc": 0.5242718446601942, "acc_stderr": 0.049449010929737795, "acc_norm": 0.5242718446601942, "acc_norm_stderr": 0.049449010929737795 }, "hendrycksTest-marketing": { "acc": 0.6581196581196581, "acc_stderr": 0.03107502852650775, "acc_norm": 0.6581196581196581, "acc_norm_stderr": 0.03107502852650775 }, "hendrycksTest-medical_genetics": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "hendrycksTest-miscellaneous": { "acc": 0.5938697318007663, "acc_stderr": 0.017562037406478916, "acc_norm": 0.5938697318007663, "acc_norm_stderr": 0.017562037406478916 }, "hendrycksTest-moral_disputes": { "acc": 0.4884393063583815, "acc_stderr": 0.026911898686377906, "acc_norm": 0.4884393063583815, "acc_norm_stderr": 0.026911898686377906 }, "hendrycksTest-moral_scenarios": { "acc": 0.23798882681564246, "acc_stderr": 0.014242630070574915, "acc_norm": 0.23798882681564246, "acc_norm_stderr": 0.014242630070574915 }, "hendrycksTest-nutrition": { "acc": 0.5065359477124183, "acc_stderr": 0.028627470550556047, "acc_norm": 0.5065359477124183, "acc_norm_stderr": 0.028627470550556047 }, "hendrycksTest-philosophy": { "acc": 0.5562700964630225, "acc_stderr": 0.02821768355665231, "acc_norm": 0.5562700964630225, "acc_norm_stderr": 0.02821768355665231 }, "hendrycksTest-prehistory": { "acc": 0.49382716049382713, "acc_stderr": 0.027818623962583295, "acc_norm": 0.49382716049382713, "acc_norm_stderr": 0.027818623962583295 }, "hendrycksTest-professional_accounting": { "acc": 0.3404255319148936, "acc_stderr": 0.028267657482650144, "acc_norm": 0.3404255319148936, "acc_norm_stderr": 0.028267657482650144 }, "hendrycksTest-professional_law": { "acc": 0.3318122555410691, "acc_stderr": 0.012026088259897632, "acc_norm": 0.3318122555410691, "acc_norm_stderr": 0.012026088259897632 }, "hendrycksTest-professional_medicine": { "acc": 0.4963235294117647, "acc_stderr": 0.030372015885428195, "acc_norm": 0.4963235294117647, "acc_norm_stderr": 0.030372015885428195 }, "hendrycksTest-professional_psychology": { "acc": 0.39215686274509803, "acc_stderr": 0.01975172650876263, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.01975172650876263 }, "hendrycksTest-public_relations": { "acc": 0.5454545454545454, "acc_stderr": 0.04769300568972743, "acc_norm": 0.5454545454545454, "acc_norm_stderr": 0.04769300568972743 }, "hendrycksTest-security_studies": { "acc": 0.46530612244897956, "acc_stderr": 0.03193207024425314, "acc_norm": 0.46530612244897956, "acc_norm_stderr": 0.03193207024425314 }, "hendrycksTest-sociology": { "acc": 0.5671641791044776, "acc_stderr": 0.03503490923673281, "acc_norm": 0.5671641791044776, "acc_norm_stderr": 0.03503490923673281 }, "hendrycksTest-us_foreign_policy": { "acc": 0.68, "acc_stderr": 0.04688261722621504, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621504 }, "hendrycksTest-virology": { "acc": 0.39156626506024095, "acc_stderr": 0.037998574544796375, "acc_norm": 0.39156626506024095, "acc_norm_stderr": 0.037998574544796375 }, "hendrycksTest-world_religions": { "acc": 0.6549707602339181, "acc_stderr": 0.03645981377388807, "acc_norm": 0.6549707602339181, "acc_norm_stderr": 0.03645981377388807 } }, "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": "hf-causal-experimental", "model_args": { "pretrained": "/network/alexandre/research/cerebras/retrained_s50", "trust_remote_code": true, "dtype": "bfloat16" }, "num_fewshot": 5, "batch_size": "4", "batch_sizes": [], "device": "cuda:0", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }