{ "results": { "hendrycksTest-abstract_algebra": { "acc": 0.28, "acc_stderr": 0.04512608598542129, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542129 }, "hendrycksTest-anatomy": { "acc": 0.45925925925925926, "acc_stderr": 0.04304979692464242, "acc_norm": 0.45925925925925926, "acc_norm_stderr": 0.04304979692464242 }, "hendrycksTest-astronomy": { "acc": 0.47368421052631576, "acc_stderr": 0.040633027314866725, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.040633027314866725 }, "hendrycksTest-business_ethics": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "hendrycksTest-clinical_knowledge": { "acc": 0.4339622641509434, "acc_stderr": 0.030503292013342596, "acc_norm": 0.4339622641509434, "acc_norm_stderr": 0.030503292013342596 }, "hendrycksTest-college_biology": { "acc": 0.3680555555555556, "acc_stderr": 0.040329990539607195, "acc_norm": 0.3680555555555556, "acc_norm_stderr": 0.040329990539607195 }, "hendrycksTest-college_chemistry": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "hendrycksTest-college_computer_science": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "hendrycksTest-college_mathematics": { "acc": 0.2, "acc_stderr": 0.040201512610368466, "acc_norm": 0.2, "acc_norm_stderr": 0.040201512610368466 }, "hendrycksTest-college_medicine": { "acc": 0.3930635838150289, "acc_stderr": 0.0372424959581773, "acc_norm": 0.3930635838150289, "acc_norm_stderr": 0.0372424959581773 }, "hendrycksTest-college_physics": { "acc": 0.18627450980392157, "acc_stderr": 0.038739587141493524, "acc_norm": 0.18627450980392157, "acc_norm_stderr": 0.038739587141493524 }, "hendrycksTest-computer_security": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "hendrycksTest-conceptual_physics": { "acc": 0.37872340425531914, "acc_stderr": 0.03170995606040655, "acc_norm": 0.37872340425531914, "acc_norm_stderr": 0.03170995606040655 }, "hendrycksTest-econometrics": { "acc": 0.2894736842105263, "acc_stderr": 0.04266339443159394, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.04266339443159394 }, "hendrycksTest-electrical_engineering": { "acc": 0.4206896551724138, "acc_stderr": 0.0411391498118926, "acc_norm": 0.4206896551724138, "acc_norm_stderr": 0.0411391498118926 }, "hendrycksTest-elementary_mathematics": { "acc": 0.30158730158730157, "acc_stderr": 0.02363697599610179, "acc_norm": 0.30158730158730157, "acc_norm_stderr": 0.02363697599610179 }, "hendrycksTest-formal_logic": { "acc": 0.25396825396825395, "acc_stderr": 0.03893259610604674, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.03893259610604674 }, "hendrycksTest-global_facts": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "hendrycksTest-high_school_biology": { "acc": 0.4806451612903226, "acc_stderr": 0.02842268740431211, "acc_norm": 0.4806451612903226, "acc_norm_stderr": 0.02842268740431211 }, "hendrycksTest-high_school_chemistry": { "acc": 0.33004926108374383, "acc_stderr": 0.033085304262282574, "acc_norm": 0.33004926108374383, "acc_norm_stderr": 0.033085304262282574 }, "hendrycksTest-high_school_computer_science": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "hendrycksTest-high_school_european_history": { "acc": 0.5151515151515151, "acc_stderr": 0.03902551007374448, "acc_norm": 0.5151515151515151, "acc_norm_stderr": 0.03902551007374448 }, "hendrycksTest-high_school_geography": { "acc": 0.4444444444444444, "acc_stderr": 0.035402943770953675, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.035402943770953675 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.5906735751295337, "acc_stderr": 0.03548608168860806, "acc_norm": 0.5906735751295337, "acc_norm_stderr": 0.03548608168860806 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.36666666666666664, "acc_stderr": 0.024433016466052455, "acc_norm": 0.36666666666666664, "acc_norm_stderr": 0.024433016466052455 }, "hendrycksTest-high_school_mathematics": { "acc": 0.27037037037037037, "acc_stderr": 0.02708037281514568, "acc_norm": 0.27037037037037037, "acc_norm_stderr": 0.02708037281514568 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.38235294117647056, "acc_stderr": 0.03156663099215416, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.03156663099215416 }, "hendrycksTest-high_school_physics": { "acc": 0.32450331125827814, "acc_stderr": 0.03822746937658754, "acc_norm": 0.32450331125827814, "acc_norm_stderr": 0.03822746937658754 }, "hendrycksTest-high_school_psychology": { "acc": 0.5027522935779817, "acc_stderr": 0.021436998359765317, "acc_norm": 0.5027522935779817, "acc_norm_stderr": 0.021436998359765317 }, "hendrycksTest-high_school_statistics": { "acc": 0.33796296296296297, "acc_stderr": 0.03225941352631295, "acc_norm": 0.33796296296296297, "acc_norm_stderr": 0.03225941352631295 }, "hendrycksTest-high_school_us_history": { "acc": 0.5637254901960784, "acc_stderr": 0.034806931384570396, "acc_norm": 0.5637254901960784, "acc_norm_stderr": 0.034806931384570396 }, "hendrycksTest-high_school_world_history": { "acc": 0.6329113924050633, "acc_stderr": 0.03137624072561619, "acc_norm": 0.6329113924050633, "acc_norm_stderr": 0.03137624072561619 }, "hendrycksTest-human_aging": { "acc": 0.4439461883408072, "acc_stderr": 0.03334625674242728, "acc_norm": 0.4439461883408072, "acc_norm_stderr": 0.03334625674242728 }, "hendrycksTest-human_sexuality": { "acc": 0.4351145038167939, "acc_stderr": 0.04348208051644858, "acc_norm": 0.4351145038167939, "acc_norm_stderr": 0.04348208051644858 }, "hendrycksTest-international_law": { "acc": 0.5619834710743802, "acc_stderr": 0.045291468044357915, "acc_norm": 0.5619834710743802, "acc_norm_stderr": 0.045291468044357915 }, "hendrycksTest-jurisprudence": { "acc": 0.48148148148148145, "acc_stderr": 0.04830366024635331, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.04830366024635331 }, "hendrycksTest-logical_fallacies": { "acc": 0.4539877300613497, "acc_stderr": 0.0391170190467718, "acc_norm": 0.4539877300613497, "acc_norm_stderr": 0.0391170190467718 }, "hendrycksTest-machine_learning": { "acc": 0.2857142857142857, "acc_stderr": 0.04287858751340456, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.04287858751340456 }, "hendrycksTest-management": { "acc": 0.49514563106796117, "acc_stderr": 0.049505043821289195, "acc_norm": 0.49514563106796117, "acc_norm_stderr": 0.049505043821289195 }, "hendrycksTest-marketing": { "acc": 0.594017094017094, "acc_stderr": 0.03217180182641087, "acc_norm": 0.594017094017094, "acc_norm_stderr": 0.03217180182641087 }, "hendrycksTest-medical_genetics": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "hendrycksTest-miscellaneous": { "acc": 0.5530012771392082, "acc_stderr": 0.017779225233394223, "acc_norm": 0.5530012771392082, "acc_norm_stderr": 0.017779225233394223 }, "hendrycksTest-moral_disputes": { "acc": 0.4479768786127168, "acc_stderr": 0.026772990653361816, "acc_norm": 0.4479768786127168, "acc_norm_stderr": 0.026772990653361816 }, "hendrycksTest-moral_scenarios": { "acc": 0.2558659217877095, "acc_stderr": 0.014593620923210728, "acc_norm": 0.2558659217877095, "acc_norm_stderr": 0.014593620923210728 }, "hendrycksTest-nutrition": { "acc": 0.49019607843137253, "acc_stderr": 0.02862441255016795, "acc_norm": 0.49019607843137253, "acc_norm_stderr": 0.02862441255016795 }, "hendrycksTest-philosophy": { "acc": 0.5401929260450161, "acc_stderr": 0.028306190403305696, "acc_norm": 0.5401929260450161, "acc_norm_stderr": 0.028306190403305696 }, "hendrycksTest-prehistory": { "acc": 0.49074074074074076, "acc_stderr": 0.027815973433878014, "acc_norm": 0.49074074074074076, "acc_norm_stderr": 0.027815973433878014 }, "hendrycksTest-professional_accounting": { "acc": 0.31560283687943264, "acc_stderr": 0.02772498944950931, "acc_norm": 0.31560283687943264, "acc_norm_stderr": 0.02772498944950931 }, "hendrycksTest-professional_law": { "acc": 0.3409387222946545, "acc_stderr": 0.01210681720306721, "acc_norm": 0.3409387222946545, "acc_norm_stderr": 0.01210681720306721 }, "hendrycksTest-professional_medicine": { "acc": 0.39338235294117646, "acc_stderr": 0.029674288281311172, "acc_norm": 0.39338235294117646, "acc_norm_stderr": 0.029674288281311172 }, "hendrycksTest-professional_psychology": { "acc": 0.4215686274509804, "acc_stderr": 0.01997742260022747, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.01997742260022747 }, "hendrycksTest-public_relations": { "acc": 0.42727272727272725, "acc_stderr": 0.04738198703545483, "acc_norm": 0.42727272727272725, "acc_norm_stderr": 0.04738198703545483 }, "hendrycksTest-security_studies": { "acc": 0.43673469387755104, "acc_stderr": 0.031751952375833226, "acc_norm": 0.43673469387755104, "acc_norm_stderr": 0.031751952375833226 }, "hendrycksTest-sociology": { "acc": 0.5572139303482587, "acc_stderr": 0.03512310964123936, "acc_norm": 0.5572139303482587, "acc_norm_stderr": 0.03512310964123936 }, "hendrycksTest-us_foreign_policy": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "hendrycksTest-virology": { "acc": 0.3855421686746988, "acc_stderr": 0.037891344246115496, "acc_norm": 0.3855421686746988, "acc_norm_stderr": 0.037891344246115496 }, "hendrycksTest-world_religions": { "acc": 0.5672514619883041, "acc_stderr": 0.03799978644370607, "acc_norm": 0.5672514619883041, "acc_norm_stderr": 0.03799978644370607 } }, "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=/cerebras/experiments/spft-retrained_sparse70_llama2_DATAUpdated_KDFalse_GCTrue_LR1e-4_E6-/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": {} } }