{ "results": { "hendrycksTest-abstract_algebra": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "hendrycksTest-anatomy": { "acc": 0.3111111111111111, "acc_stderr": 0.039992628766177214, "acc_norm": 0.3111111111111111, "acc_norm_stderr": 0.039992628766177214 }, "hendrycksTest-astronomy": { "acc": 0.24342105263157895, "acc_stderr": 0.034923496688842384, "acc_norm": 0.24342105263157895, "acc_norm_stderr": 0.034923496688842384 }, "hendrycksTest-business_ethics": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "hendrycksTest-clinical_knowledge": { "acc": 0.3018867924528302, "acc_stderr": 0.028254200344438655, "acc_norm": 0.3018867924528302, "acc_norm_stderr": 0.028254200344438655 }, "hendrycksTest-college_biology": { "acc": 0.2916666666666667, "acc_stderr": 0.03800968060554857, "acc_norm": 0.2916666666666667, "acc_norm_stderr": 0.03800968060554857 }, "hendrycksTest-college_chemistry": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "hendrycksTest-college_computer_science": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "hendrycksTest-college_mathematics": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "hendrycksTest-college_medicine": { "acc": 0.2543352601156069, "acc_stderr": 0.0332055644308557, "acc_norm": 0.2543352601156069, "acc_norm_stderr": 0.0332055644308557 }, "hendrycksTest-college_physics": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171452, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171452 }, "hendrycksTest-computer_security": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "hendrycksTest-conceptual_physics": { "acc": 0.31063829787234043, "acc_stderr": 0.03025123757921317, "acc_norm": 0.31063829787234043, "acc_norm_stderr": 0.03025123757921317 }, "hendrycksTest-econometrics": { "acc": 0.2894736842105263, "acc_stderr": 0.04266339443159394, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.04266339443159394 }, "hendrycksTest-electrical_engineering": { "acc": 0.3103448275862069, "acc_stderr": 0.038552896163789485, "acc_norm": 0.3103448275862069, "acc_norm_stderr": 0.038552896163789485 }, "hendrycksTest-elementary_mathematics": { "acc": 0.2804232804232804, "acc_stderr": 0.023135287974325628, "acc_norm": 0.2804232804232804, "acc_norm_stderr": 0.023135287974325628 }, "hendrycksTest-formal_logic": { "acc": 0.18253968253968253, "acc_stderr": 0.03455071019102146, "acc_norm": 0.18253968253968253, "acc_norm_stderr": 0.03455071019102146 }, "hendrycksTest-global_facts": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "hendrycksTest-high_school_biology": { "acc": 0.31290322580645163, "acc_stderr": 0.02637756702864586, "acc_norm": 0.31290322580645163, "acc_norm_stderr": 0.02637756702864586 }, "hendrycksTest-high_school_chemistry": { "acc": 0.2512315270935961, "acc_stderr": 0.030516530732694433, "acc_norm": 0.2512315270935961, "acc_norm_stderr": 0.030516530732694433 }, "hendrycksTest-high_school_computer_science": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "hendrycksTest-high_school_european_history": { "acc": 0.3090909090909091, "acc_stderr": 0.036085410115739666, "acc_norm": 0.3090909090909091, "acc_norm_stderr": 0.036085410115739666 }, "hendrycksTest-high_school_geography": { "acc": 0.32323232323232326, "acc_stderr": 0.033322999210706444, "acc_norm": 0.32323232323232326, "acc_norm_stderr": 0.033322999210706444 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.32124352331606215, "acc_stderr": 0.033699508685490674, "acc_norm": 0.32124352331606215, "acc_norm_stderr": 0.033699508685490674 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.3076923076923077, "acc_stderr": 0.023400928918310502, "acc_norm": 0.3076923076923077, "acc_norm_stderr": 0.023400928918310502 }, "hendrycksTest-high_school_mathematics": { "acc": 0.25925925925925924, "acc_stderr": 0.026719240783712177, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.026719240783712177 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.25630252100840334, "acc_stderr": 0.02835962087053395, "acc_norm": 0.25630252100840334, "acc_norm_stderr": 0.02835962087053395 }, "hendrycksTest-high_school_physics": { "acc": 0.271523178807947, "acc_stderr": 0.036313298039696545, "acc_norm": 0.271523178807947, "acc_norm_stderr": 0.036313298039696545 }, "hendrycksTest-high_school_psychology": { "acc": 0.27339449541284405, "acc_stderr": 0.01910929984609828, "acc_norm": 0.27339449541284405, "acc_norm_stderr": 0.01910929984609828 }, "hendrycksTest-high_school_statistics": { "acc": 0.21296296296296297, "acc_stderr": 0.027920963147993666, "acc_norm": 0.21296296296296297, "acc_norm_stderr": 0.027920963147993666 }, "hendrycksTest-high_school_us_history": { "acc": 0.25, "acc_stderr": 0.03039153369274154, "acc_norm": 0.25, "acc_norm_stderr": 0.03039153369274154 }, "hendrycksTest-high_school_world_history": { "acc": 0.2742616033755274, "acc_stderr": 0.029041333510598025, "acc_norm": 0.2742616033755274, "acc_norm_stderr": 0.029041333510598025 }, "hendrycksTest-human_aging": { "acc": 0.36771300448430494, "acc_stderr": 0.03236198350928276, "acc_norm": 0.36771300448430494, "acc_norm_stderr": 0.03236198350928276 }, "hendrycksTest-human_sexuality": { "acc": 0.33587786259541985, "acc_stderr": 0.04142313771996665, "acc_norm": 0.33587786259541985, "acc_norm_stderr": 0.04142313771996665 }, "hendrycksTest-international_law": { "acc": 0.4214876033057851, "acc_stderr": 0.045077322787750944, "acc_norm": 0.4214876033057851, "acc_norm_stderr": 0.045077322787750944 }, "hendrycksTest-jurisprudence": { "acc": 0.3333333333333333, "acc_stderr": 0.04557239513497752, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04557239513497752 }, "hendrycksTest-logical_fallacies": { "acc": 0.27607361963190186, "acc_stderr": 0.0351238528370505, "acc_norm": 0.27607361963190186, "acc_norm_stderr": 0.0351238528370505 }, "hendrycksTest-machine_learning": { "acc": 0.35714285714285715, "acc_stderr": 0.04547960999764376, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.04547960999764376 }, "hendrycksTest-management": { "acc": 0.30097087378640774, "acc_stderr": 0.045416094465039476, "acc_norm": 0.30097087378640774, "acc_norm_stderr": 0.045416094465039476 }, "hendrycksTest-marketing": { "acc": 0.2863247863247863, "acc_stderr": 0.029614323690456648, "acc_norm": 0.2863247863247863, "acc_norm_stderr": 0.029614323690456648 }, "hendrycksTest-medical_genetics": { "acc": 0.28, "acc_stderr": 0.045126085985421255, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421255 }, "hendrycksTest-miscellaneous": { "acc": 0.30395913154533843, "acc_stderr": 0.016448321686769043, "acc_norm": 0.30395913154533843, "acc_norm_stderr": 0.016448321686769043 }, "hendrycksTest-moral_disputes": { "acc": 0.2832369942196532, "acc_stderr": 0.02425790170532337, "acc_norm": 0.2832369942196532, "acc_norm_stderr": 0.02425790170532337 }, "hendrycksTest-moral_scenarios": { "acc": 0.2424581005586592, "acc_stderr": 0.014333522059217889, "acc_norm": 0.2424581005586592, "acc_norm_stderr": 0.014333522059217889 }, "hendrycksTest-nutrition": { "acc": 0.2908496732026144, "acc_stderr": 0.026004800363952113, "acc_norm": 0.2908496732026144, "acc_norm_stderr": 0.026004800363952113 }, "hendrycksTest-philosophy": { "acc": 0.28938906752411575, "acc_stderr": 0.02575586592263294, "acc_norm": 0.28938906752411575, "acc_norm_stderr": 0.02575586592263294 }, "hendrycksTest-prehistory": { "acc": 0.2808641975308642, "acc_stderr": 0.025006469755799204, "acc_norm": 0.2808641975308642, "acc_norm_stderr": 0.025006469755799204 }, "hendrycksTest-professional_accounting": { "acc": 0.2872340425531915, "acc_stderr": 0.026992199173064356, "acc_norm": 0.2872340425531915, "acc_norm_stderr": 0.026992199173064356 }, "hendrycksTest-professional_law": { "acc": 0.26401564537157757, "acc_stderr": 0.011258435537723821, "acc_norm": 0.26401564537157757, "acc_norm_stderr": 0.011258435537723821 }, "hendrycksTest-professional_medicine": { "acc": 0.20588235294117646, "acc_stderr": 0.024562204314142317, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.024562204314142317 }, "hendrycksTest-professional_psychology": { "acc": 0.2826797385620915, "acc_stderr": 0.018217269552053432, "acc_norm": 0.2826797385620915, "acc_norm_stderr": 0.018217269552053432 }, "hendrycksTest-public_relations": { "acc": 0.32727272727272727, "acc_stderr": 0.04494290866252089, "acc_norm": 0.32727272727272727, "acc_norm_stderr": 0.04494290866252089 }, "hendrycksTest-security_studies": { "acc": 0.3020408163265306, "acc_stderr": 0.02939360931987981, "acc_norm": 0.3020408163265306, "acc_norm_stderr": 0.02939360931987981 }, "hendrycksTest-sociology": { "acc": 0.27860696517412936, "acc_stderr": 0.03170056183497308, "acc_norm": 0.27860696517412936, "acc_norm_stderr": 0.03170056183497308 }, "hendrycksTest-us_foreign_policy": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "hendrycksTest-virology": { "acc": 0.3313253012048193, "acc_stderr": 0.036643147772880864, "acc_norm": 0.3313253012048193, "acc_norm_stderr": 0.036643147772880864 }, "hendrycksTest-world_religions": { "acc": 0.2573099415204678, "acc_stderr": 0.03352799844161865, "acc_norm": 0.2573099415204678, "acc_norm_stderr": 0.03352799844161865 } }, "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=/home/vmagent/app/data/mpt-7b-delta-tune-model-div-sal/merged_model,use_accelerate=True,trust_remote_code=True,dtype=float16", "num_fewshot": 5, "batch_size": "auto", "batch_sizes": [ 16 ], "device": null, "no_cache": false, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }