{ "results": { "hendrycksTest-us_foreign_policy": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "hendrycksTest-high_school_mathematics": { "acc": 0.2518518518518518, "acc_stderr": 0.026466117538959912, "acc_norm": 0.3037037037037037, "acc_norm_stderr": 0.028037929969114993 }, "hendrycksTest-human_aging": { "acc": 0.2556053811659193, "acc_stderr": 0.029275891003969923, "acc_norm": 0.22869955156950672, "acc_norm_stderr": 0.028188240046929193 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.2689075630252101, "acc_stderr": 0.028801392193631276, "acc_norm": 0.3445378151260504, "acc_norm_stderr": 0.030868682604121622 }, "hendrycksTest-college_mathematics": { "acc": 0.22, "acc_stderr": 0.041633319989322695, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "hendrycksTest-college_computer_science": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "hendrycksTest-management": { "acc": 0.27184466019417475, "acc_stderr": 0.044052680241409216, "acc_norm": 0.3592233009708738, "acc_norm_stderr": 0.04750458399041694 }, "piqa": { "acc": 0.7758433079434167, "acc_stderr": 0.009729897956410044, "acc_norm": 0.7812840043525572, "acc_norm_stderr": 0.009644731932667563 }, "hendrycksTest-professional_law": { "acc": 0.2757496740547588, "acc_stderr": 0.011413813609161003, "acc_norm": 0.2842242503259452, "acc_norm_stderr": 0.011519880596516072 }, "hendrycksTest-public_relations": { "acc": 0.2818181818181818, "acc_stderr": 0.043091187099464585, "acc_norm": 0.2, "acc_norm_stderr": 0.038313051408846034 }, "hendrycksTest-sociology": { "acc": 0.2537313432835821, "acc_stderr": 0.030769444967296014, "acc_norm": 0.22388059701492538, "acc_norm_stderr": 0.029475250236017176 }, "hendrycksTest-anatomy": { "acc": 0.24444444444444444, "acc_stderr": 0.037125378336148665, "acc_norm": 0.2074074074074074, "acc_norm_stderr": 0.03502553170678316 }, "sciq": { "acc": 0.911, "acc_stderr": 0.009008893392651535, "acc_norm": 0.882, "acc_norm_stderr": 0.010206869264381791 }, "hendrycksTest-high_school_european_history": { "acc": 0.22424242424242424, "acc_stderr": 0.032568666616811015, "acc_norm": 0.2606060606060606, "acc_norm_stderr": 0.03427743175816524 }, "logiqa": { "acc": 0.21658986175115208, "acc_stderr": 0.016156860583178303, "acc_norm": 0.28417818740399386, "acc_norm_stderr": 0.017690542680190765 }, "hendrycksTest-philosophy": { "acc": 0.29260450160771706, "acc_stderr": 0.025839898334877983, "acc_norm": 0.33440514469453375, "acc_norm_stderr": 0.026795422327893944 }, "hendrycksTest-high_school_geography": { "acc": 0.26262626262626265, "acc_stderr": 0.03135305009533084, "acc_norm": 0.2878787878787879, "acc_norm_stderr": 0.03225883512300992 }, "hendrycksTest-logical_fallacies": { "acc": 0.3006134969325153, "acc_stderr": 0.03602511318806771, "acc_norm": 0.34355828220858897, "acc_norm_stderr": 0.03731133519673893 }, "hendrycksTest-jurisprudence": { "acc": 0.35185185185185186, "acc_stderr": 0.04616631111801713, "acc_norm": 0.4351851851851852, "acc_norm_stderr": 0.04792898170907062 }, "hendrycksTest-college_chemistry": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "hendrycksTest-conceptual_physics": { "acc": 0.24680851063829787, "acc_stderr": 0.02818544130123409, "acc_norm": 0.2, "acc_norm_stderr": 0.026148818018424502 }, "hendrycksTest-medical_genetics": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "hendrycksTest-abstract_algebra": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "lambada_openai": { "ppl": 3.6290590138646768, "ppl_stderr": 0.07410155740289663, "acc": 0.7145352222006598, "acc_stderr": 0.006292165813769917 }, "hendrycksTest-nutrition": { "acc": 0.30392156862745096, "acc_stderr": 0.026336613469046644, "acc_norm": 0.40522875816993464, "acc_norm_stderr": 0.028110928492809075 }, "hendrycksTest-business_ethics": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.24870466321243523, "acc_stderr": 0.031195840877700286, "acc_norm": 0.24870466321243523, "acc_norm_stderr": 0.031195840877700286 }, "wsc": { "acc": 0.5961538461538461, "acc_stderr": 0.048346889526540184 }, "hendrycksTest-college_biology": { "acc": 0.2708333333333333, "acc_stderr": 0.03716177437566016, "acc_norm": 0.2847222222222222, "acc_norm_stderr": 0.037738099906869355 }, "hendrycksTest-high_school_physics": { "acc": 0.25165562913907286, "acc_stderr": 0.035433042343899844, "acc_norm": 0.25165562913907286, "acc_norm_stderr": 0.035433042343899844 }, "hendrycksTest-clinical_knowledge": { "acc": 0.25660377358490566, "acc_stderr": 0.02688064788905198, "acc_norm": 0.30943396226415093, "acc_norm_stderr": 0.028450154794118627 }, "hendrycksTest-astronomy": { "acc": 0.3092105263157895, "acc_stderr": 0.03761070869867479, "acc_norm": 0.375, "acc_norm_stderr": 0.039397364351956274 }, "hendrycksTest-high_school_psychology": { "acc": 0.24403669724770644, "acc_stderr": 0.018415286351416402, "acc_norm": 0.24587155963302754, "acc_norm_stderr": 0.01846194096870845 }, "hendrycksTest-moral_disputes": { "acc": 0.2832369942196532, "acc_stderr": 0.02425790170532337, "acc_norm": 0.3352601156069364, "acc_norm_stderr": 0.025416003773165555 }, "hendrycksTest-marketing": { "acc": 0.2564102564102564, "acc_stderr": 0.028605953702004264, "acc_norm": 0.3076923076923077, "acc_norm_stderr": 0.030236389942173116 }, "hendrycksTest-global_facts": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "arc_easy": { "acc": 0.6999158249158249, "acc_stderr": 0.009404000558513353, "acc_norm": 0.6536195286195287, "acc_norm_stderr": 0.00976354207569573 }, "hendrycksTest-electrical_engineering": { "acc": 0.31724137931034485, "acc_stderr": 0.03878352372138622, "acc_norm": 0.3310344827586207, "acc_norm_stderr": 0.039215453124671215 }, "hendrycksTest-formal_logic": { "acc": 0.30952380952380953, "acc_stderr": 0.04134913018303316, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.03932537680392869 }, "hendrycksTest-high_school_computer_science": { "acc": 0.24, "acc_stderr": 0.04292346959909284, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "hendrycksTest-high_school_us_history": { "acc": 0.28431372549019607, "acc_stderr": 0.03166009679399812, "acc_norm": 0.25980392156862747, "acc_norm_stderr": 0.03077855467869326 }, "hendrycksTest-college_medicine": { "acc": 0.24277456647398843, "acc_stderr": 0.0326926380614177, "acc_norm": 0.27167630057803466, "acc_norm_stderr": 0.03391750322321659 }, "hendrycksTest-machine_learning": { "acc": 0.24107142857142858, "acc_stderr": 0.04059867246952685, "acc_norm": 0.23214285714285715, "acc_norm_stderr": 0.04007341809755807 }, "hendrycksTest-professional_accounting": { "acc": 0.21631205673758866, "acc_stderr": 0.024561720560562796, "acc_norm": 0.2553191489361702, "acc_norm_stderr": 0.026011992930902013 }, "hendrycksTest-professional_medicine": { "acc": 0.2757352941176471, "acc_stderr": 0.02714627193662517, "acc_norm": 0.2757352941176471, "acc_norm_stderr": 0.027146271936625166 }, "hendrycksTest-virology": { "acc": 0.3253012048192771, "acc_stderr": 0.036471685236832266, "acc_norm": 0.2710843373493976, "acc_norm_stderr": 0.034605799075530276 }, "hendrycksTest-world_religions": { "acc": 0.3216374269005848, "acc_stderr": 0.03582529442573122, "acc_norm": 0.391812865497076, "acc_norm_stderr": 0.037439798259263996 }, "hendrycksTest-computer_security": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "hendrycksTest-high_school_chemistry": { "acc": 0.2660098522167488, "acc_stderr": 0.03108982600293752, "acc_norm": 0.3103448275862069, "acc_norm_stderr": 0.03255086769970103 }, "hendrycksTest-econometrics": { "acc": 0.2631578947368421, "acc_stderr": 0.041424397194893624, "acc_norm": 0.21052631578947367, "acc_norm_stderr": 0.038351539543994194 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.2846153846153846, "acc_stderr": 0.022878322799706297, "acc_norm": 0.28205128205128205, "acc_norm_stderr": 0.0228158130988966 }, "hendrycksTest-high_school_biology": { "acc": 0.2806451612903226, "acc_stderr": 0.025560604721022884, "acc_norm": 0.3032258064516129, "acc_norm_stderr": 0.026148685930671746 }, "hendrycksTest-prehistory": { "acc": 0.24074074074074073, "acc_stderr": 0.023788583551658544, "acc_norm": 0.17901234567901234, "acc_norm_stderr": 0.021330868762127045 }, "hendrycksTest-human_sexuality": { "acc": 0.37404580152671757, "acc_stderr": 0.042438692422305246, "acc_norm": 0.31297709923664124, "acc_norm_stderr": 0.04066962905677697 }, "hendrycksTest-professional_psychology": { "acc": 0.27941176470588236, "acc_stderr": 0.018152871051538802, "acc_norm": 0.272875816993464, "acc_norm_stderr": 0.018020474148393577 }, "hendrycksTest-international_law": { "acc": 0.256198347107438, "acc_stderr": 0.03984979653302871, "acc_norm": 0.5371900826446281, "acc_norm_stderr": 0.04551711196104218 }, "arc_challenge": { "acc": 0.3464163822525597, "acc_stderr": 0.013905011180063256, "acc_norm": 0.3796928327645051, "acc_norm_stderr": 0.014182119866974872 }, "hendrycksTest-elementary_mathematics": { "acc": 0.2671957671957672, "acc_stderr": 0.02278967314577656, "acc_norm": 0.2724867724867725, "acc_norm_stderr": 0.022930973071633345 }, "hendrycksTest-high_school_statistics": { "acc": 0.3425925925925926, "acc_stderr": 0.03236585252602158, "acc_norm": 0.3611111111111111, "acc_norm_stderr": 0.032757734861009996 }, "hendrycksTest-miscellaneous": { "acc": 0.3116219667943806, "acc_stderr": 0.016562433867284176, "acc_norm": 0.280970625798212, "acc_norm_stderr": 0.016073127851221235 }, "hendrycksTest-high_school_world_history": { "acc": 0.2616033755274262, "acc_stderr": 0.028609516716994934, "acc_norm": 0.270042194092827, "acc_norm_stderr": 0.028900721906293426 }, "hendrycksTest-moral_scenarios": { "acc": 0.24692737430167597, "acc_stderr": 0.014422292204808835, "acc_norm": 0.2446927374301676, "acc_norm_stderr": 0.014378169884098405 }, "winogrande": { "acc": 0.6819258089976322, "acc_stderr": 0.013089285079884685 }, "hendrycksTest-security_studies": { "acc": 0.3795918367346939, "acc_stderr": 0.031067211262872468, "acc_norm": 0.34285714285714286, "acc_norm_stderr": 0.03038726291954773 }, "hendrycksTest-college_physics": { "acc": 0.27450980392156865, "acc_stderr": 0.04440521906179326, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.0438986995680878 } }, "versions": { "hendrycksTest-us_foreign_policy": 0, "hendrycksTest-high_school_mathematics": 0, "hendrycksTest-human_aging": 0, "hendrycksTest-high_school_microeconomics": 0, "hendrycksTest-college_mathematics": 0, "hendrycksTest-college_computer_science": 0, "hendrycksTest-management": 0, "piqa": 0, "hendrycksTest-professional_law": 0, "hendrycksTest-public_relations": 0, "hendrycksTest-sociology": 0, "hendrycksTest-anatomy": 0, "sciq": 0, "hendrycksTest-high_school_european_history": 0, "logiqa": 0, "hendrycksTest-philosophy": 0, "hendrycksTest-high_school_geography": 0, "hendrycksTest-logical_fallacies": 0, "hendrycksTest-jurisprudence": 0, "hendrycksTest-college_chemistry": 0, "hendrycksTest-conceptual_physics": 0, "hendrycksTest-medical_genetics": 0, "hendrycksTest-abstract_algebra": 0, "lambada_openai": 0, "hendrycksTest-nutrition": 0, "hendrycksTest-business_ethics": 0, "hendrycksTest-high_school_government_and_politics": 0, "wsc": 0, "hendrycksTest-college_biology": 0, "hendrycksTest-high_school_physics": 0, "hendrycksTest-clinical_knowledge": 0, "hendrycksTest-astronomy": 0, "hendrycksTest-high_school_psychology": 0, "hendrycksTest-moral_disputes": 0, "hendrycksTest-marketing": 0, "hendrycksTest-global_facts": 0, "arc_easy": 0, "hendrycksTest-electrical_engineering": 0, "hendrycksTest-formal_logic": 0, "hendrycksTest-high_school_computer_science": 0, "hendrycksTest-high_school_us_history": 0, "hendrycksTest-college_medicine": 0, "hendrycksTest-machine_learning": 0, "hendrycksTest-professional_accounting": 0, "hendrycksTest-professional_medicine": 0, "hendrycksTest-virology": 0, "hendrycksTest-world_religions": 0, "hendrycksTest-computer_security": 0, "hendrycksTest-high_school_chemistry": 0, "hendrycksTest-econometrics": 0, "hendrycksTest-high_school_macroeconomics": 0, "hendrycksTest-high_school_biology": 0, "hendrycksTest-prehistory": 0, "hendrycksTest-human_sexuality": 0, "hendrycksTest-professional_psychology": 0, "hendrycksTest-international_law": 0, "arc_challenge": 0, "hendrycksTest-elementary_mathematics": 0, "hendrycksTest-high_school_statistics": 0, "hendrycksTest-miscellaneous": 0, "hendrycksTest-high_school_world_history": 0, "hendrycksTest-moral_scenarios": 0, "winogrande": 0, "hendrycksTest-security_studies": 0, "hendrycksTest-college_physics": 0 }, "config": { "model": "hf-causal", "model_args": "pretrained=facebook/opt-30b,use_accelerate=True,device_map_option=sequential,max_memory_per_gpu=40GIB", "num_fewshot": 0, "batch_size": 1, "device": "cuda", "no_cache": false, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }