{ "results": { "hendrycksTest-abstract_algebra": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "hendrycksTest-anatomy": { "acc": 0.4444444444444444, "acc_stderr": 0.04292596718256981, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.04292596718256981 }, "hendrycksTest-astronomy": { "acc": 0.4473684210526316, "acc_stderr": 0.04046336883978251, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04046336883978251 }, "hendrycksTest-business_ethics": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "hendrycksTest-clinical_knowledge": { "acc": 0.4528301886792453, "acc_stderr": 0.030635627957961823, "acc_norm": 0.4528301886792453, "acc_norm_stderr": 0.030635627957961823 }, "hendrycksTest-college_biology": { "acc": 0.4513888888888889, "acc_stderr": 0.04161402398403279, "acc_norm": 0.4513888888888889, "acc_norm_stderr": 0.04161402398403279 }, "hendrycksTest-college_chemistry": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "hendrycksTest-college_computer_science": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "hendrycksTest-college_mathematics": { "acc": 0.23, "acc_stderr": 0.04229525846816508, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816508 }, "hendrycksTest-college_medicine": { "acc": 0.3699421965317919, "acc_stderr": 0.036812296333943194, "acc_norm": 0.3699421965317919, "acc_norm_stderr": 0.036812296333943194 }, "hendrycksTest-college_physics": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617746, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617746 }, "hendrycksTest-computer_security": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "hendrycksTest-conceptual_physics": { "acc": 0.39148936170212767, "acc_stderr": 0.03190701242326812, "acc_norm": 0.39148936170212767, "acc_norm_stderr": 0.03190701242326812 }, "hendrycksTest-econometrics": { "acc": 0.2719298245614035, "acc_stderr": 0.04185774424022056, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.04185774424022056 }, "hendrycksTest-electrical_engineering": { "acc": 0.42758620689655175, "acc_stderr": 0.04122737111370333, "acc_norm": 0.42758620689655175, "acc_norm_stderr": 0.04122737111370333 }, "hendrycksTest-elementary_mathematics": { "acc": 0.3148148148148148, "acc_stderr": 0.02391998416404773, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.02391998416404773 }, "hendrycksTest-formal_logic": { "acc": 0.2777777777777778, "acc_stderr": 0.04006168083848878, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.04006168083848878 }, "hendrycksTest-global_facts": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "hendrycksTest-high_school_biology": { "acc": 0.5, "acc_stderr": 0.028444006199428714, "acc_norm": 0.5, "acc_norm_stderr": 0.028444006199428714 }, "hendrycksTest-high_school_chemistry": { "acc": 0.31527093596059114, "acc_stderr": 0.03269080871970186, "acc_norm": 0.31527093596059114, "acc_norm_stderr": 0.03269080871970186 }, "hendrycksTest-high_school_computer_science": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "hendrycksTest-high_school_european_history": { "acc": 0.593939393939394, "acc_stderr": 0.03834816355401181, "acc_norm": 0.593939393939394, "acc_norm_stderr": 0.03834816355401181 }, "hendrycksTest-high_school_geography": { "acc": 0.48484848484848486, "acc_stderr": 0.03560716516531061, "acc_norm": 0.48484848484848486, "acc_norm_stderr": 0.03560716516531061 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.6269430051813472, "acc_stderr": 0.03490205592048573, "acc_norm": 0.6269430051813472, "acc_norm_stderr": 0.03490205592048573 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.3871794871794872, "acc_stderr": 0.02469721693087894, "acc_norm": 0.3871794871794872, "acc_norm_stderr": 0.02469721693087894 }, "hendrycksTest-high_school_mathematics": { "acc": 0.2851851851851852, "acc_stderr": 0.027528599210340496, "acc_norm": 0.2851851851851852, "acc_norm_stderr": 0.027528599210340496 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.42436974789915966, "acc_stderr": 0.032104790510157764, "acc_norm": 0.42436974789915966, "acc_norm_stderr": 0.032104790510157764 }, "hendrycksTest-high_school_physics": { "acc": 0.31788079470198677, "acc_stderr": 0.03802039760107903, "acc_norm": 0.31788079470198677, "acc_norm_stderr": 0.03802039760107903 }, "hendrycksTest-high_school_psychology": { "acc": 0.5743119266055046, "acc_stderr": 0.0211992359724708, "acc_norm": 0.5743119266055046, "acc_norm_stderr": 0.0211992359724708 }, "hendrycksTest-high_school_statistics": { "acc": 0.35648148148148145, "acc_stderr": 0.03266478331527272, "acc_norm": 0.35648148148148145, "acc_norm_stderr": 0.03266478331527272 }, "hendrycksTest-high_school_us_history": { "acc": 0.6029411764705882, "acc_stderr": 0.0343413116471913, "acc_norm": 0.6029411764705882, "acc_norm_stderr": 0.0343413116471913 }, "hendrycksTest-high_school_world_history": { "acc": 0.6666666666666666, "acc_stderr": 0.0306858205966108, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.0306858205966108 }, "hendrycksTest-human_aging": { "acc": 0.5426008968609866, "acc_stderr": 0.033435777055830646, "acc_norm": 0.5426008968609866, "acc_norm_stderr": 0.033435777055830646 }, "hendrycksTest-human_sexuality": { "acc": 0.4732824427480916, "acc_stderr": 0.04379024936553894, "acc_norm": 0.4732824427480916, "acc_norm_stderr": 0.04379024936553894 }, "hendrycksTest-international_law": { "acc": 0.6776859504132231, "acc_stderr": 0.04266416363352167, "acc_norm": 0.6776859504132231, "acc_norm_stderr": 0.04266416363352167 }, "hendrycksTest-jurisprudence": { "acc": 0.5370370370370371, "acc_stderr": 0.04820403072760627, "acc_norm": 0.5370370370370371, "acc_norm_stderr": 0.04820403072760627 }, "hendrycksTest-logical_fallacies": { "acc": 0.4601226993865031, "acc_stderr": 0.03915857291436971, "acc_norm": 0.4601226993865031, "acc_norm_stderr": 0.03915857291436971 }, "hendrycksTest-machine_learning": { "acc": 0.35714285714285715, "acc_stderr": 0.04547960999764376, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.04547960999764376 }, "hendrycksTest-management": { "acc": 0.5825242718446602, "acc_stderr": 0.048828405482122375, "acc_norm": 0.5825242718446602, "acc_norm_stderr": 0.048828405482122375 }, "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": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "hendrycksTest-miscellaneous": { "acc": 0.6245210727969349, "acc_stderr": 0.017316613197182786, "acc_norm": 0.6245210727969349, "acc_norm_stderr": 0.017316613197182786 }, "hendrycksTest-moral_disputes": { "acc": 0.5086705202312138, "acc_stderr": 0.026915047355369818, "acc_norm": 0.5086705202312138, "acc_norm_stderr": 0.026915047355369818 }, "hendrycksTest-moral_scenarios": { "acc": 0.24134078212290502, "acc_stderr": 0.014310999547961447, "acc_norm": 0.24134078212290502, "acc_norm_stderr": 0.014310999547961447 }, "hendrycksTest-nutrition": { "acc": 0.4869281045751634, "acc_stderr": 0.028620130800700246, "acc_norm": 0.4869281045751634, "acc_norm_stderr": 0.028620130800700246 }, "hendrycksTest-philosophy": { "acc": 0.5466237942122186, "acc_stderr": 0.028274359854894238, "acc_norm": 0.5466237942122186, "acc_norm_stderr": 0.028274359854894238 }, "hendrycksTest-prehistory": { "acc": 0.5061728395061729, "acc_stderr": 0.027818623962583295, "acc_norm": 0.5061728395061729, "acc_norm_stderr": 0.027818623962583295 }, "hendrycksTest-professional_accounting": { "acc": 0.3617021276595745, "acc_stderr": 0.0286638201471995, "acc_norm": 0.3617021276595745, "acc_norm_stderr": 0.0286638201471995 }, "hendrycksTest-professional_law": { "acc": 0.3741851368970013, "acc_stderr": 0.012359335618172061, "acc_norm": 0.3741851368970013, "acc_norm_stderr": 0.012359335618172061 }, "hendrycksTest-professional_medicine": { "acc": 0.45588235294117646, "acc_stderr": 0.030254372573976687, "acc_norm": 0.45588235294117646, "acc_norm_stderr": 0.030254372573976687 }, "hendrycksTest-professional_psychology": { "acc": 0.43300653594771243, "acc_stderr": 0.020045442473324227, "acc_norm": 0.43300653594771243, "acc_norm_stderr": 0.020045442473324227 }, "hendrycksTest-public_relations": { "acc": 0.4818181818181818, "acc_stderr": 0.04785964010794916, "acc_norm": 0.4818181818181818, "acc_norm_stderr": 0.04785964010794916 }, "hendrycksTest-security_studies": { "acc": 0.5020408163265306, "acc_stderr": 0.0320089533497105, "acc_norm": 0.5020408163265306, "acc_norm_stderr": 0.0320089533497105 }, "hendrycksTest-sociology": { "acc": 0.5671641791044776, "acc_stderr": 0.03503490923673281, "acc_norm": 0.5671641791044776, "acc_norm_stderr": 0.03503490923673281 }, "hendrycksTest-us_foreign_policy": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "hendrycksTest-virology": { "acc": 0.3795180722891566, "acc_stderr": 0.03777798822748018, "acc_norm": 0.3795180722891566, "acc_norm_stderr": 0.03777798822748018 }, "hendrycksTest-world_religions": { "acc": 0.6783625730994152, "acc_stderr": 0.03582529442573122, "acc_norm": 0.6783625730994152, "acc_norm_stderr": 0.03582529442573122 } }, "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=/nm/drive1/shubhra/cerebras/experiments/spft-retrained_sparse50_llama2_DATAUpdated_KDFalse_GCTrue_LR1e-4_E2-/combined/,trust_remote_code=True", "num_fewshot": 5, "batch_size": "6", "batch_sizes": [], "device": "cuda:0", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }