{ "results": { "arc_challenge": { "alias": "arc_challenge", "acc,none": 0.2167235494880546, "acc_stderr,none": 0.01204015671348119, "acc_norm,none": 0.24658703071672355, "acc_norm_stderr,none": 0.012595726268790115 }, "arc_easy": { "alias": "arc_easy", "acc,none": 0.27314814814814814, "acc_stderr,none": 0.009143032718360342, "acc_norm,none": 0.2521043771043771, "acc_norm_stderr,none": 0.008910024163218178 }, "blimp": { "acc,none": 0.5265522388059701, "acc_stderr,none": 0.0018732846331904836, "alias": "blimp" }, "blimp_adjunct_island": { "alias": " - blimp_adjunct_island", "acc,none": 0.535, "acc_stderr,none": 0.015780495050030156 }, "blimp_anaphor_gender_agreement": { "alias": " - blimp_anaphor_gender_agreement", "acc,none": 0.617, "acc_stderr,none": 0.015380102325652708 }, "blimp_anaphor_number_agreement": { "alias": " - blimp_anaphor_number_agreement", "acc,none": 0.563, "acc_stderr,none": 0.015693223928730373 }, "blimp_animate_subject_passive": { "alias": " - blimp_animate_subject_passive", "acc,none": 0.606, "acc_stderr,none": 0.015459721957493377 }, "blimp_animate_subject_trans": { "alias": " - blimp_animate_subject_trans", "acc,none": 0.802, "acc_stderr,none": 0.0126077339341753 }, "blimp_causative": { "alias": " - blimp_causative", "acc,none": 0.395, "acc_stderr,none": 0.015466551464829345 }, "blimp_complex_NP_island": { "alias": " - blimp_complex_NP_island", "acc,none": 0.472, "acc_stderr,none": 0.015794475789511476 }, "blimp_coordinate_structure_constraint_complex_left_branch": { "alias": " - blimp_coordinate_structure_constraint_complex_left_branch", "acc,none": 0.526, "acc_stderr,none": 0.015797897758042766 }, "blimp_coordinate_structure_constraint_object_extraction": { "alias": " - blimp_coordinate_structure_constraint_object_extraction", "acc,none": 0.632, "acc_stderr,none": 0.0152580735615218 }, "blimp_determiner_noun_agreement_1": { "alias": " - blimp_determiner_noun_agreement_1", "acc,none": 0.51, "acc_stderr,none": 0.0158161357527732 }, "blimp_determiner_noun_agreement_2": { "alias": " - blimp_determiner_noun_agreement_2", "acc,none": 0.516, "acc_stderr,none": 0.015811198373114878 }, "blimp_determiner_noun_agreement_irregular_1": { "alias": " - blimp_determiner_noun_agreement_irregular_1", "acc,none": 0.494, "acc_stderr,none": 0.015818160898606715 }, "blimp_determiner_noun_agreement_irregular_2": { "alias": " - blimp_determiner_noun_agreement_irregular_2", "acc,none": 0.487, "acc_stderr,none": 0.015813952101896626 }, "blimp_determiner_noun_agreement_with_adj_2": { "alias": " - blimp_determiner_noun_agreement_with_adj_2", "acc,none": 0.509, "acc_stderr,none": 0.015816736995005392 }, "blimp_determiner_noun_agreement_with_adj_irregular_1": { "alias": " - blimp_determiner_noun_agreement_with_adj_irregular_1", "acc,none": 0.491, "acc_stderr,none": 0.015816736995005392 }, "blimp_determiner_noun_agreement_with_adj_irregular_2": { "alias": " - blimp_determiner_noun_agreement_with_adj_irregular_2", "acc,none": 0.495, "acc_stderr,none": 0.01581850894443666 }, "blimp_determiner_noun_agreement_with_adjective_1": { "alias": " - blimp_determiner_noun_agreement_with_adjective_1", "acc,none": 0.51, "acc_stderr,none": 0.0158161357527732 }, "blimp_distractor_agreement_relational_noun": { "alias": " - blimp_distractor_agreement_relational_noun", "acc,none": 0.511, "acc_stderr,none": 0.015815471195292682 }, "blimp_distractor_agreement_relative_clause": { "alias": " - blimp_distractor_agreement_relative_clause", "acc,none": 0.496, "acc_stderr,none": 0.015818793703510886 }, "blimp_drop_argument": { "alias": " - blimp_drop_argument", "acc,none": 0.663, "acc_stderr,none": 0.014955087918653607 }, "blimp_ellipsis_n_bar_1": { "alias": " - blimp_ellipsis_n_bar_1", "acc,none": 0.493, "acc_stderr,none": 0.01581774956184357 }, "blimp_ellipsis_n_bar_2": { "alias": " - blimp_ellipsis_n_bar_2", "acc,none": 0.327, "acc_stderr,none": 0.014842213153411245 }, "blimp_existential_there_object_raising": { "alias": " - blimp_existential_there_object_raising", "acc,none": 0.612, "acc_stderr,none": 0.015417317979911077 }, "blimp_existential_there_quantifiers_1": { "alias": " - blimp_existential_there_quantifiers_1", "acc,none": 0.908, "acc_stderr,none": 0.00914437639315112 }, "blimp_existential_there_quantifiers_2": { "alias": " - blimp_existential_there_quantifiers_2", "acc,none": 0.611, "acc_stderr,none": 0.015424555647308495 }, "blimp_existential_there_subject_raising": { "alias": " - blimp_existential_there_subject_raising", "acc,none": 0.533, "acc_stderr,none": 0.01578480789113878 }, "blimp_expletive_it_object_raising": { "alias": " - blimp_expletive_it_object_raising", "acc,none": 0.569, "acc_stderr,none": 0.015667944488173494 }, "blimp_inchoative": { "alias": " - blimp_inchoative", "acc,none": 0.388, "acc_stderr,none": 0.015417317979911081 }, "blimp_intransitive": { "alias": " - blimp_intransitive", "acc,none": 0.557, "acc_stderr,none": 0.015716169953204105 }, "blimp_irregular_past_participle_adjectives": { "alias": " - blimp_irregular_past_participle_adjectives", "acc,none": 0.294, "acc_stderr,none": 0.01441429054000822 }, "blimp_irregular_past_participle_verbs": { "alias": " - blimp_irregular_past_participle_verbs", "acc,none": 0.464, "acc_stderr,none": 0.015778243024904586 }, "blimp_irregular_plural_subject_verb_agreement_1": { "alias": " - blimp_irregular_plural_subject_verb_agreement_1", "acc,none": 0.496, "acc_stderr,none": 0.015818793703510886 }, "blimp_irregular_plural_subject_verb_agreement_2": { "alias": " - blimp_irregular_plural_subject_verb_agreement_2", "acc,none": 0.525, "acc_stderr,none": 0.015799513429996026 }, "blimp_left_branch_island_echo_question": { "alias": " - blimp_left_branch_island_echo_question", "acc,none": 0.597, "acc_stderr,none": 0.015518757419066533 }, "blimp_left_branch_island_simple_question": { "alias": " - blimp_left_branch_island_simple_question", "acc,none": 0.511, "acc_stderr,none": 0.01581547119529269 }, "blimp_matrix_question_npi_licensor_present": { "alias": " - blimp_matrix_question_npi_licensor_present", "acc,none": 0.353, "acc_stderr,none": 0.015120172605483687 }, "blimp_npi_present_1": { "alias": " - blimp_npi_present_1", "acc,none": 0.401, "acc_stderr,none": 0.015506109745498322 }, "blimp_npi_present_2": { "alias": " - blimp_npi_present_2", "acc,none": 0.335, "acc_stderr,none": 0.014933117490932577 }, "blimp_only_npi_licensor_present": { "alias": " - blimp_only_npi_licensor_present", "acc,none": 0.377, "acc_stderr,none": 0.015333170125779855 }, "blimp_only_npi_scope": { "alias": " - blimp_only_npi_scope", "acc,none": 0.598, "acc_stderr,none": 0.01551246713571508 }, "blimp_passive_1": { "alias": " - blimp_passive_1", "acc,none": 0.661, "acc_stderr,none": 0.014976758771620345 }, "blimp_passive_2": { "alias": " - blimp_passive_2", "acc,none": 0.602, "acc_stderr,none": 0.01548663410285892 }, "blimp_principle_A_c_command": { "alias": " - blimp_principle_A_c_command", "acc,none": 0.318, "acc_stderr,none": 0.014734079309311903 }, "blimp_principle_A_case_1": { "alias": " - blimp_principle_A_case_1", "acc,none": 0.846, "acc_stderr,none": 0.011419913065098704 }, "blimp_principle_A_case_2": { "alias": " - blimp_principle_A_case_2", "acc,none": 0.5, "acc_stderr,none": 0.015819299929208316 }, "blimp_principle_A_domain_1": { "alias": " - blimp_principle_A_domain_1", "acc,none": 0.526, "acc_stderr,none": 0.01579789775804274 }, "blimp_principle_A_domain_2": { "alias": " - blimp_principle_A_domain_2", "acc,none": 0.512, "acc_stderr,none": 0.015814743314581818 }, "blimp_principle_A_domain_3": { "alias": " - blimp_principle_A_domain_3", "acc,none": 0.509, "acc_stderr,none": 0.015816736995005392 }, "blimp_principle_A_reconstruction": { "alias": " - blimp_principle_A_reconstruction", "acc,none": 0.448, "acc_stderr,none": 0.015733516566347833 }, "blimp_regular_plural_subject_verb_agreement_1": { "alias": " - blimp_regular_plural_subject_verb_agreement_1", "acc,none": 0.387, "acc_stderr,none": 0.015410011955493933 }, "blimp_regular_plural_subject_verb_agreement_2": { "alias": " - blimp_regular_plural_subject_verb_agreement_2", "acc,none": 0.514, "acc_stderr,none": 0.01581309754773099 }, "blimp_sentential_negation_npi_licensor_present": { "alias": " - blimp_sentential_negation_npi_licensor_present", "acc,none": 0.641, "acc_stderr,none": 0.0151772642247986 }, "blimp_sentential_negation_npi_scope": { "alias": " - blimp_sentential_negation_npi_scope", "acc,none": 0.724, "acc_stderr,none": 0.014142984975740673 }, "blimp_sentential_subject_island": { "alias": " - blimp_sentential_subject_island", "acc,none": 0.461, "acc_stderr,none": 0.01577110420128319 }, "blimp_superlative_quantifiers_1": { "alias": " - blimp_superlative_quantifiers_1", "acc,none": 0.782, "acc_stderr,none": 0.013063179040595282 }, "blimp_superlative_quantifiers_2": { "alias": " - blimp_superlative_quantifiers_2", "acc,none": 0.62, "acc_stderr,none": 0.015356947477797585 }, "blimp_tough_vs_raising_1": { "alias": " - blimp_tough_vs_raising_1", "acc,none": 0.413, "acc_stderr,none": 0.01557798682993653 }, "blimp_tough_vs_raising_2": { "alias": " - blimp_tough_vs_raising_2", "acc,none": 0.614, "acc_stderr,none": 0.01540263747678438 }, "blimp_transitive": { "alias": " - blimp_transitive", "acc,none": 0.518, "acc_stderr,none": 0.015809045699406728 }, "blimp_wh_island": { "alias": " - blimp_wh_island", "acc,none": 0.612, "acc_stderr,none": 0.015417317979911077 }, "blimp_wh_questions_object_gap": { "alias": " - blimp_wh_questions_object_gap", "acc,none": 0.485, "acc_stderr,none": 0.015812179641814902 }, "blimp_wh_questions_subject_gap": { "alias": " - blimp_wh_questions_subject_gap", "acc,none": 0.44, "acc_stderr,none": 0.015704987954361798 }, "blimp_wh_questions_subject_gap_long_distance": { "alias": " - blimp_wh_questions_subject_gap_long_distance", "acc,none": 0.408, "acc_stderr,none": 0.015549205052920675 }, "blimp_wh_vs_that_no_gap": { "alias": " - blimp_wh_vs_that_no_gap", "acc,none": 0.375, "acc_stderr,none": 0.015316971293620996 }, "blimp_wh_vs_that_no_gap_long_distance": { "alias": " - blimp_wh_vs_that_no_gap_long_distance", "acc,none": 0.418, "acc_stderr,none": 0.01560511196754195 }, "blimp_wh_vs_that_with_gap": { "alias": " - blimp_wh_vs_that_with_gap", "acc,none": 0.604, "acc_stderr,none": 0.015473313265859406 }, "blimp_wh_vs_that_with_gap_long_distance": { "alias": " - blimp_wh_vs_that_with_gap_long_distance", "acc,none": 0.562, "acc_stderr,none": 0.01569721001969469 }, "lambada_openai": { "alias": "lambada_openai", "perplexity,none": 3684151.0754114343, "perplexity_stderr,none": 360810.5027218676, "acc,none": 0.0, "acc_stderr,none": 0.0 }, "logiqa": { "alias": "logiqa", "acc,none": 0.22734254992319508, "acc_stderr,none": 0.016439067675117738, "acc_norm,none": 0.2457757296466974, "acc_norm_stderr,none": 0.016887410894296923 }, "mmlu": { "acc,none": 0.24675972083748754, "acc_stderr,none": 0.003636283084413651, "alias": "mmlu" }, "mmlu_humanities": { "acc,none": 0.24463336875664188, "acc_stderr,none": 0.006270617619969035, "alias": " - humanities" }, "mmlu_formal_logic": { "alias": " - formal_logic", "acc,none": 0.2619047619047619, "acc_stderr,none": 0.0393253768039287 }, "mmlu_high_school_european_history": { "alias": " - high_school_european_history", "acc,none": 0.2545454545454545, "acc_stderr,none": 0.034015067152490405 }, "mmlu_high_school_us_history": { "alias": " - high_school_us_history", "acc,none": 0.23039215686274508, "acc_stderr,none": 0.029554292605695066 }, "mmlu_high_school_world_history": { "alias": " - high_school_world_history", "acc,none": 0.25738396624472576, "acc_stderr,none": 0.02845882099146031 }, "mmlu_international_law": { "alias": " - international_law", "acc,none": 0.2727272727272727, "acc_stderr,none": 0.04065578140908705 }, "mmlu_jurisprudence": { "alias": " - jurisprudence", "acc,none": 0.28703703703703703, "acc_stderr,none": 0.043733130409147614 }, "mmlu_logical_fallacies": { "alias": " - logical_fallacies", "acc,none": 0.24539877300613497, "acc_stderr,none": 0.03380939813943354 }, "mmlu_moral_disputes": { "alias": " - moral_disputes", "acc,none": 0.2658959537572254, "acc_stderr,none": 0.023786203255508297 }, "mmlu_moral_scenarios": { "alias": " - moral_scenarios", "acc,none": 0.2446927374301676, "acc_stderr,none": 0.014378169884098417 }, "mmlu_philosophy": { "alias": " - philosophy", "acc,none": 0.2765273311897106, "acc_stderr,none": 0.02540383297817961 }, "mmlu_prehistory": { "alias": " - prehistory", "acc,none": 0.24074074074074073, "acc_stderr,none": 0.02378858355165854 }, "mmlu_professional_law": { "alias": " - professional_law", "acc,none": 0.22685788787483702, "acc_stderr,none": 0.010696348133569929 }, "mmlu_world_religions": { "alias": " - world_religions", "acc,none": 0.23976608187134502, "acc_stderr,none": 0.03274485211946956 }, "mmlu_other": { "acc,none": 0.25523012552301255, "acc_stderr,none": 0.007795728061570978, "alias": " - other" }, "mmlu_business_ethics": { "alias": " - business_ethics", "acc,none": 0.24, "acc_stderr,none": 0.04292346959909284 }, "mmlu_clinical_knowledge": { "alias": " - clinical_knowledge", "acc,none": 0.17358490566037735, "acc_stderr,none": 0.02331058302600627 }, "mmlu_college_medicine": { "alias": " - college_medicine", "acc,none": 0.20809248554913296, "acc_stderr,none": 0.030952890217749895 }, "mmlu_global_facts": { "alias": " - global_facts", "acc,none": 0.27, "acc_stderr,none": 0.044619604333847394 }, "mmlu_human_aging": { "alias": " - human_aging", "acc,none": 0.3542600896860987, "acc_stderr,none": 0.03210062154134987 }, "mmlu_management": { "alias": " - management", "acc,none": 0.18446601941747573, "acc_stderr,none": 0.03840423627288276 }, "mmlu_marketing": { "alias": " - marketing", "acc,none": 0.25213675213675213, "acc_stderr,none": 0.028447965476231008 }, "mmlu_medical_genetics": { "alias": " - medical_genetics", "acc,none": 0.22, "acc_stderr,none": 0.04163331998932269 }, "mmlu_miscellaneous": { "alias": " - miscellaneous", "acc,none": 0.28735632183908044, "acc_stderr,none": 0.0161824107306827 }, "mmlu_nutrition": { "alias": " - nutrition", "acc,none": 0.23529411764705882, "acc_stderr,none": 0.024288619466046112 }, "mmlu_professional_accounting": { "alias": " - professional_accounting", "acc,none": 0.2730496453900709, "acc_stderr,none": 0.026577860943307857 }, "mmlu_professional_medicine": { "alias": " - professional_medicine", "acc,none": 0.22426470588235295, "acc_stderr,none": 0.025336848563332386 }, "mmlu_virology": { "alias": " - virology", "acc,none": 0.27710843373493976, "acc_stderr,none": 0.03484331592680588 }, "mmlu_social_sciences": { "acc,none": 0.23594410139746505, "acc_stderr,none": 0.007657341507140387, "alias": " - social sciences" }, "mmlu_econometrics": { "alias": " - econometrics", "acc,none": 0.21929824561403508, "acc_stderr,none": 0.03892431106518753 }, "mmlu_high_school_geography": { "alias": " - high_school_geography", "acc,none": 0.21212121212121213, "acc_stderr,none": 0.029126522834586815 }, "mmlu_high_school_government_and_politics": { "alias": " - high_school_government_and_politics", "acc,none": 0.20725388601036268, "acc_stderr,none": 0.029252823291803624 }, "mmlu_high_school_macroeconomics": { "alias": " - high_school_macroeconomics", "acc,none": 0.23333333333333334, "acc_stderr,none": 0.02144454730156048 }, "mmlu_high_school_microeconomics": { "alias": " - high_school_microeconomics", "acc,none": 0.23949579831932774, "acc_stderr,none": 0.027722065493361252 }, "mmlu_high_school_psychology": { "alias": " - high_school_psychology", "acc,none": 0.24770642201834864, "acc_stderr,none": 0.0185081436025478 }, "mmlu_human_sexuality": { "alias": " - human_sexuality", "acc,none": 0.22900763358778625, "acc_stderr,none": 0.036853466317118506 }, "mmlu_professional_psychology": { "alias": " - professional_psychology", "acc,none": 0.26143790849673204, "acc_stderr,none": 0.017776947157528044 }, "mmlu_public_relations": { "alias": " - public_relations", "acc,none": 0.2545454545454545, "acc_stderr,none": 0.041723430387053825 }, "mmlu_security_studies": { "alias": " - security_studies", "acc,none": 0.1836734693877551, "acc_stderr,none": 0.024789071332007636 }, "mmlu_sociology": { "alias": " - sociology", "acc,none": 0.22388059701492538, "acc_stderr,none": 0.02947525023601719 }, "mmlu_us_foreign_policy": { "alias": " - us_foreign_policy", "acc,none": 0.28, "acc_stderr,none": 0.045126085985421255 }, "mmlu_stem": { "acc,none": 0.2521408182683159, "acc_stderr,none": 0.00773602786019127, "alias": " - stem" }, "mmlu_abstract_algebra": { "alias": " - abstract_algebra", "acc,none": 0.32, "acc_stderr,none": 0.04688261722621504 }, "mmlu_anatomy": { "alias": " - anatomy", "acc,none": 0.28888888888888886, "acc_stderr,none": 0.0391545063041425 }, "mmlu_astronomy": { "alias": " - astronomy", "acc,none": 0.23026315789473684, "acc_stderr,none": 0.034260594244031654 }, "mmlu_college_biology": { "alias": " - college_biology", "acc,none": 0.25, "acc_stderr,none": 0.03621034121889507 }, "mmlu_college_chemistry": { "alias": " - college_chemistry", "acc,none": 0.26, "acc_stderr,none": 0.0440844002276808 }, "mmlu_college_computer_science": { "alias": " - college_computer_science", "acc,none": 0.18, "acc_stderr,none": 0.03861229196653695 }, "mmlu_college_mathematics": { "alias": " - college_mathematics", "acc,none": 0.24, "acc_stderr,none": 0.04292346959909281 }, "mmlu_college_physics": { "alias": " - college_physics", "acc,none": 0.28431372549019607, "acc_stderr,none": 0.04488482852329017 }, "mmlu_computer_security": { "alias": " - computer_security", "acc,none": 0.25, "acc_stderr,none": 0.04351941398892446 }, "mmlu_conceptual_physics": { "alias": " - conceptual_physics", "acc,none": 0.28085106382978725, "acc_stderr,none": 0.029379170464124815 }, "mmlu_electrical_engineering": { "alias": " - electrical_engineering", "acc,none": 0.23448275862068965, "acc_stderr,none": 0.035306258743465914 }, "mmlu_elementary_mathematics": { "alias": " - elementary_mathematics", "acc,none": 0.2751322751322751, "acc_stderr,none": 0.02300008685906865 }, "mmlu_high_school_biology": { "alias": " - high_school_biology", "acc,none": 0.24838709677419354, "acc_stderr,none": 0.024580028921481006 }, "mmlu_high_school_chemistry": { "alias": " - high_school_chemistry", "acc,none": 0.2660098522167488, "acc_stderr,none": 0.03108982600293752 }, "mmlu_high_school_computer_science": { "alias": " - high_school_computer_science", "acc,none": 0.27, "acc_stderr,none": 0.0446196043338474 }, "mmlu_high_school_mathematics": { "alias": " - high_school_mathematics", "acc,none": 0.26666666666666666, "acc_stderr,none": 0.026962424325073828 }, "mmlu_high_school_physics": { "alias": " - high_school_physics", "acc,none": 0.2119205298013245, "acc_stderr,none": 0.03336767086567977 }, "mmlu_high_school_statistics": { "alias": " - high_school_statistics", "acc,none": 0.18981481481481483, "acc_stderr,none": 0.026744714834691916 }, "mmlu_machine_learning": { "alias": " - machine_learning", "acc,none": 0.21428571428571427, "acc_stderr,none": 0.038946411200447915 }, "piqa": { "alias": "piqa", "acc,none": 0.5239390642002176, "acc_stderr,none": 0.011652445621079262, "acc_norm,none": 0.5190424374319913, "acc_norm_stderr,none": 0.011657360703051449 }, "sciq": { "alias": "sciq", "acc,none": 0.195, "acc_stderr,none": 0.012535235623319334, "acc_norm,none": 0.216, "acc_norm_stderr,none": 0.013019735539307803 }, "wikitext": { "alias": "wikitext", "word_perplexity,none": 327420.7518447254, "word_perplexity_stderr,none": "N/A", "byte_perplexity,none": 10.748613041120647, "byte_perplexity_stderr,none": "N/A", "bits_per_byte,none": 3.4260786070007456, "bits_per_byte_stderr,none": "N/A" }, "winogrande": { "alias": "winogrande", "acc,none": 0.4980268350434096, "acc_stderr,none": 0.014052376259225629 }, "wsc": { "alias": "wsc", "acc,none": 0.5865384615384616, "acc_stderr,none": 0.04852294969729053 } }, "groups": { "blimp": { "acc,none": 0.5265522388059701, "acc_stderr,none": 0.0018732846331904836, "alias": "blimp" }, "mmlu": { "acc,none": 0.24675972083748754, "acc_stderr,none": 0.003636283084413651, "alias": "mmlu" }, "mmlu_humanities": { "acc,none": 0.24463336875664188, "acc_stderr,none": 0.006270617619969035, "alias": " - humanities" }, "mmlu_other": { "acc,none": 0.25523012552301255, "acc_stderr,none": 0.007795728061570978, "alias": " - other" }, "mmlu_social_sciences": { "acc,none": 0.23594410139746505, "acc_stderr,none": 0.007657341507140387, "alias": " - social sciences" }, "mmlu_stem": { "acc,none": 0.2521408182683159, "acc_stderr,none": 0.00773602786019127, "alias": " - stem" } }, "group_subtasks": { "arc_easy": [], "arc_challenge": [], "blimp": [ "blimp_adjunct_island", "blimp_anaphor_gender_agreement", "blimp_anaphor_number_agreement", "blimp_animate_subject_passive", "blimp_animate_subject_trans", "blimp_causative", "blimp_complex_NP_island", "blimp_coordinate_structure_constraint_complex_left_branch", "blimp_coordinate_structure_constraint_object_extraction", "blimp_determiner_noun_agreement_1", "blimp_determiner_noun_agreement_2", "blimp_determiner_noun_agreement_irregular_1", "blimp_determiner_noun_agreement_irregular_2", "blimp_determiner_noun_agreement_with_adj_2", "blimp_determiner_noun_agreement_with_adj_irregular_1", "blimp_determiner_noun_agreement_with_adj_irregular_2", "blimp_determiner_noun_agreement_with_adjective_1", "blimp_distractor_agreement_relational_noun", "blimp_distractor_agreement_relative_clause", "blimp_drop_argument", "blimp_ellipsis_n_bar_1", "blimp_ellipsis_n_bar_2", "blimp_existential_there_object_raising", "blimp_existential_there_quantifiers_1", "blimp_existential_there_quantifiers_2", "blimp_existential_there_subject_raising", "blimp_expletive_it_object_raising", "blimp_inchoative", "blimp_intransitive", "blimp_irregular_past_participle_adjectives", "blimp_irregular_past_participle_verbs", "blimp_irregular_plural_subject_verb_agreement_1", "blimp_irregular_plural_subject_verb_agreement_2", "blimp_left_branch_island_echo_question", "blimp_left_branch_island_simple_question", "blimp_matrix_question_npi_licensor_present", "blimp_npi_present_1", "blimp_npi_present_2", "blimp_only_npi_licensor_present", "blimp_only_npi_scope", "blimp_passive_1", "blimp_passive_2", "blimp_principle_A_c_command", "blimp_principle_A_case_1", "blimp_principle_A_case_2", "blimp_principle_A_domain_1", "blimp_principle_A_domain_2", "blimp_principle_A_domain_3", "blimp_principle_A_reconstruction", "blimp_regular_plural_subject_verb_agreement_1", "blimp_regular_plural_subject_verb_agreement_2", "blimp_sentential_negation_npi_licensor_present", "blimp_sentential_negation_npi_scope", "blimp_sentential_subject_island", "blimp_superlative_quantifiers_1", "blimp_superlative_quantifiers_2", "blimp_tough_vs_raising_1", "blimp_tough_vs_raising_2", "blimp_transitive", "blimp_wh_island", "blimp_wh_questions_object_gap", "blimp_wh_questions_subject_gap", "blimp_wh_questions_subject_gap_long_distance", "blimp_wh_vs_that_no_gap", "blimp_wh_vs_that_no_gap_long_distance", "blimp_wh_vs_that_with_gap", "blimp_wh_vs_that_with_gap_long_distance" ], "lambada_openai": [], "logiqa": [], "mmlu_humanities": [ "mmlu_moral_disputes", "mmlu_high_school_world_history", "mmlu_jurisprudence", "mmlu_philosophy", "mmlu_high_school_us_history", "mmlu_professional_law", "mmlu_logical_fallacies", "mmlu_moral_scenarios", "mmlu_formal_logic", "mmlu_prehistory", "mmlu_high_school_european_history", "mmlu_world_religions", "mmlu_international_law" ], "mmlu_social_sciences": [ "mmlu_us_foreign_policy", "mmlu_sociology", "mmlu_econometrics", "mmlu_security_studies", "mmlu_high_school_geography", "mmlu_public_relations", "mmlu_high_school_microeconomics", "mmlu_professional_psychology", "mmlu_high_school_macroeconomics", "mmlu_human_sexuality", "mmlu_high_school_government_and_politics", "mmlu_high_school_psychology" ], "mmlu_other": [ "mmlu_college_medicine", "mmlu_medical_genetics", "mmlu_business_ethics", "mmlu_miscellaneous", "mmlu_nutrition", "mmlu_clinical_knowledge", "mmlu_human_aging", "mmlu_professional_accounting", "mmlu_marketing", "mmlu_global_facts", "mmlu_professional_medicine", "mmlu_virology", "mmlu_management" ], "mmlu_stem": [ "mmlu_elementary_mathematics", "mmlu_electrical_engineering", "mmlu_high_school_computer_science", "mmlu_high_school_physics", "mmlu_college_mathematics", "mmlu_college_chemistry", "mmlu_machine_learning", "mmlu_high_school_mathematics", "mmlu_computer_security", "mmlu_conceptual_physics", "mmlu_high_school_statistics", "mmlu_high_school_biology", "mmlu_astronomy", "mmlu_college_computer_science", "mmlu_college_biology", "mmlu_college_physics", "mmlu_anatomy", "mmlu_high_school_chemistry", "mmlu_abstract_algebra" ], "mmlu": [ "mmlu_stem", "mmlu_other", "mmlu_social_sciences", "mmlu_humanities" ], "piqa": [], "sciq": [], "wikitext": [], "winogrande": [], "wsc": [] }, "configs": { "arc_challenge": { "task": "arc_challenge", "tag": [ "ai2_arc" ], "dataset_path": "allenai/ai2_arc", "dataset_name": "ARC-Challenge", "training_split": "train", "validation_split": "validation", "test_split": "test", "doc_to_text": "Question: {{question}}\nAnswer:", "doc_to_target": "{{choices.label.index(answerKey)}}", "doc_to_choice": "{{choices.text}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true }, { "metric": "acc_norm", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "Question: {{question}}\nAnswer:", "metadata": { "version": 1.0 } }, "arc_easy": { "task": "arc_easy", "tag": [ "ai2_arc" ], "dataset_path": "allenai/ai2_arc", "dataset_name": "ARC-Easy", "training_split": "train", "validation_split": "validation", "test_split": "test", "doc_to_text": "Question: {{question}}\nAnswer:", "doc_to_target": "{{choices.label.index(answerKey)}}", "doc_to_choice": "{{choices.text}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true }, { "metric": "acc_norm", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "Question: {{question}}\nAnswer:", "metadata": { "version": 1.0 } }, "blimp_adjunct_island": { "task": "blimp_adjunct_island", "dataset_path": "blimp", "dataset_name": "adjunct_island", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_anaphor_gender_agreement": { "task": "blimp_anaphor_gender_agreement", "dataset_path": "blimp", "dataset_name": "anaphor_gender_agreement", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_anaphor_number_agreement": { "task": "blimp_anaphor_number_agreement", "dataset_path": "blimp", "dataset_name": "anaphor_number_agreement", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_animate_subject_passive": { "task": "blimp_animate_subject_passive", "dataset_path": "blimp", "dataset_name": "animate_subject_passive", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_animate_subject_trans": { "task": "blimp_animate_subject_trans", "dataset_path": "blimp", "dataset_name": "animate_subject_trans", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_causative": { "task": "blimp_causative", "dataset_path": "blimp", "dataset_name": "causative", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_complex_NP_island": { "task": "blimp_complex_NP_island", "dataset_path": "blimp", "dataset_name": "complex_NP_island", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_coordinate_structure_constraint_complex_left_branch": { "task": "blimp_coordinate_structure_constraint_complex_left_branch", "dataset_path": "blimp", "dataset_name": "coordinate_structure_constraint_complex_left_branch", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_coordinate_structure_constraint_object_extraction": { "task": "blimp_coordinate_structure_constraint_object_extraction", "dataset_path": "blimp", "dataset_name": "coordinate_structure_constraint_object_extraction", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_determiner_noun_agreement_1": { "task": "blimp_determiner_noun_agreement_1", "dataset_path": "blimp", "dataset_name": "determiner_noun_agreement_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_determiner_noun_agreement_2": { "task": "blimp_determiner_noun_agreement_2", "dataset_path": "blimp", "dataset_name": "determiner_noun_agreement_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_determiner_noun_agreement_irregular_1": { "task": "blimp_determiner_noun_agreement_irregular_1", "dataset_path": "blimp", "dataset_name": "determiner_noun_agreement_irregular_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_determiner_noun_agreement_irregular_2": { "task": "blimp_determiner_noun_agreement_irregular_2", "dataset_path": "blimp", "dataset_name": "determiner_noun_agreement_irregular_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_determiner_noun_agreement_with_adj_2": { "task": "blimp_determiner_noun_agreement_with_adj_2", "dataset_path": "blimp", "dataset_name": "determiner_noun_agreement_with_adj_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_determiner_noun_agreement_with_adj_irregular_1": { "task": "blimp_determiner_noun_agreement_with_adj_irregular_1", "dataset_path": "blimp", "dataset_name": "determiner_noun_agreement_with_adj_irregular_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_determiner_noun_agreement_with_adj_irregular_2": { "task": "blimp_determiner_noun_agreement_with_adj_irregular_2", "dataset_path": "blimp", "dataset_name": "determiner_noun_agreement_with_adj_irregular_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_determiner_noun_agreement_with_adjective_1": { "task": "blimp_determiner_noun_agreement_with_adjective_1", "dataset_path": "blimp", "dataset_name": "determiner_noun_agreement_with_adjective_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_distractor_agreement_relational_noun": { "task": "blimp_distractor_agreement_relational_noun", "dataset_path": "blimp", "dataset_name": "distractor_agreement_relational_noun", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_distractor_agreement_relative_clause": { "task": "blimp_distractor_agreement_relative_clause", "dataset_path": "blimp", "dataset_name": "distractor_agreement_relative_clause", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_drop_argument": { "task": "blimp_drop_argument", "dataset_path": "blimp", "dataset_name": "drop_argument", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_ellipsis_n_bar_1": { "task": "blimp_ellipsis_n_bar_1", "dataset_path": "blimp", "dataset_name": "ellipsis_n_bar_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_ellipsis_n_bar_2": { "task": "blimp_ellipsis_n_bar_2", "dataset_path": "blimp", "dataset_name": "ellipsis_n_bar_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_existential_there_object_raising": { "task": "blimp_existential_there_object_raising", "dataset_path": "blimp", "dataset_name": "existential_there_object_raising", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_existential_there_quantifiers_1": { "task": "blimp_existential_there_quantifiers_1", "dataset_path": "blimp", "dataset_name": "existential_there_quantifiers_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_existential_there_quantifiers_2": { "task": "blimp_existential_there_quantifiers_2", "dataset_path": "blimp", "dataset_name": "existential_there_quantifiers_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_existential_there_subject_raising": { "task": "blimp_existential_there_subject_raising", "dataset_path": "blimp", "dataset_name": "existential_there_subject_raising", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_expletive_it_object_raising": { "task": "blimp_expletive_it_object_raising", "dataset_path": "blimp", "dataset_name": "expletive_it_object_raising", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_inchoative": { "task": "blimp_inchoative", "dataset_path": "blimp", "dataset_name": "inchoative", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_intransitive": { "task": "blimp_intransitive", "dataset_path": "blimp", "dataset_name": "intransitive", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_irregular_past_participle_adjectives": { "task": "blimp_irregular_past_participle_adjectives", "dataset_path": "blimp", "dataset_name": "irregular_past_participle_adjectives", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_irregular_past_participle_verbs": { "task": "blimp_irregular_past_participle_verbs", "dataset_path": "blimp", "dataset_name": "irregular_past_participle_verbs", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_irregular_plural_subject_verb_agreement_1": { "task": "blimp_irregular_plural_subject_verb_agreement_1", "dataset_path": "blimp", "dataset_name": "irregular_plural_subject_verb_agreement_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_irregular_plural_subject_verb_agreement_2": { "task": "blimp_irregular_plural_subject_verb_agreement_2", "dataset_path": "blimp", "dataset_name": "irregular_plural_subject_verb_agreement_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_left_branch_island_echo_question": { "task": "blimp_left_branch_island_echo_question", "dataset_path": "blimp", "dataset_name": "left_branch_island_echo_question", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_left_branch_island_simple_question": { "task": "blimp_left_branch_island_simple_question", "dataset_path": "blimp", "dataset_name": "left_branch_island_simple_question", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_matrix_question_npi_licensor_present": { "task": "blimp_matrix_question_npi_licensor_present", "dataset_path": "blimp", "dataset_name": "matrix_question_npi_licensor_present", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_npi_present_1": { "task": "blimp_npi_present_1", "dataset_path": "blimp", "dataset_name": "npi_present_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_npi_present_2": { "task": "blimp_npi_present_2", "dataset_path": "blimp", "dataset_name": "npi_present_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_only_npi_licensor_present": { "task": "blimp_only_npi_licensor_present", "dataset_path": "blimp", "dataset_name": "only_npi_licensor_present", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_only_npi_scope": { "task": "blimp_only_npi_scope", "dataset_path": "blimp", "dataset_name": "only_npi_scope", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_passive_1": { "task": "blimp_passive_1", "dataset_path": "blimp", "dataset_name": "passive_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_passive_2": { "task": "blimp_passive_2", "dataset_path": "blimp", "dataset_name": "passive_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_principle_A_c_command": { "task": "blimp_principle_A_c_command", "dataset_path": "blimp", "dataset_name": "principle_A_c_command", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_principle_A_case_1": { "task": "blimp_principle_A_case_1", "dataset_path": "blimp", "dataset_name": "principle_A_case_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_principle_A_case_2": { "task": "blimp_principle_A_case_2", "dataset_path": "blimp", "dataset_name": "principle_A_case_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_principle_A_domain_1": { "task": "blimp_principle_A_domain_1", "dataset_path": "blimp", "dataset_name": "principle_A_domain_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_principle_A_domain_2": { "task": "blimp_principle_A_domain_2", "dataset_path": "blimp", "dataset_name": "principle_A_domain_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_principle_A_domain_3": { "task": "blimp_principle_A_domain_3", "dataset_path": "blimp", "dataset_name": "principle_A_domain_3", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_principle_A_reconstruction": { "task": "blimp_principle_A_reconstruction", "dataset_path": "blimp", "dataset_name": "principle_A_reconstruction", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_regular_plural_subject_verb_agreement_1": { "task": "blimp_regular_plural_subject_verb_agreement_1", "dataset_path": "blimp", "dataset_name": "regular_plural_subject_verb_agreement_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_regular_plural_subject_verb_agreement_2": { "task": "blimp_regular_plural_subject_verb_agreement_2", "dataset_path": "blimp", "dataset_name": "regular_plural_subject_verb_agreement_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_sentential_negation_npi_licensor_present": { "task": "blimp_sentential_negation_npi_licensor_present", "dataset_path": "blimp", "dataset_name": "sentential_negation_npi_licensor_present", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_sentential_negation_npi_scope": { "task": "blimp_sentential_negation_npi_scope", "dataset_path": "blimp", "dataset_name": "sentential_negation_npi_scope", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_sentential_subject_island": { "task": "blimp_sentential_subject_island", "dataset_path": "blimp", "dataset_name": "sentential_subject_island", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_superlative_quantifiers_1": { "task": "blimp_superlative_quantifiers_1", "dataset_path": "blimp", "dataset_name": "superlative_quantifiers_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_superlative_quantifiers_2": { "task": "blimp_superlative_quantifiers_2", "dataset_path": "blimp", "dataset_name": "superlative_quantifiers_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_tough_vs_raising_1": { "task": "blimp_tough_vs_raising_1", "dataset_path": "blimp", "dataset_name": "tough_vs_raising_1", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_tough_vs_raising_2": { "task": "blimp_tough_vs_raising_2", "dataset_path": "blimp", "dataset_name": "tough_vs_raising_2", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_transitive": { "task": "blimp_transitive", "dataset_path": "blimp", "dataset_name": "transitive", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_wh_island": { "task": "blimp_wh_island", "dataset_path": "blimp", "dataset_name": "wh_island", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_wh_questions_object_gap": { "task": "blimp_wh_questions_object_gap", "dataset_path": "blimp", "dataset_name": "wh_questions_object_gap", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_wh_questions_subject_gap": { "task": "blimp_wh_questions_subject_gap", "dataset_path": "blimp", "dataset_name": "wh_questions_subject_gap", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_wh_questions_subject_gap_long_distance": { "task": "blimp_wh_questions_subject_gap_long_distance", "dataset_path": "blimp", "dataset_name": "wh_questions_subject_gap_long_distance", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_wh_vs_that_no_gap": { "task": "blimp_wh_vs_that_no_gap", "dataset_path": "blimp", "dataset_name": "wh_vs_that_no_gap", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_wh_vs_that_no_gap_long_distance": { "task": "blimp_wh_vs_that_no_gap_long_distance", "dataset_path": "blimp", "dataset_name": "wh_vs_that_no_gap_long_distance", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_wh_vs_that_with_gap": { "task": "blimp_wh_vs_that_with_gap", "dataset_path": "blimp", "dataset_name": "wh_vs_that_with_gap", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "blimp_wh_vs_that_with_gap_long_distance": { "task": "blimp_wh_vs_that_with_gap_long_distance", "dataset_path": "blimp", "dataset_name": "wh_vs_that_with_gap_long_distance", "validation_split": "train", "doc_to_text": "", "doc_to_target": 0, "doc_to_choice": "{{[sentence_good, sentence_bad]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}", "metadata": { "version": 1.0 } }, "lambada_openai": { "task": "lambada_openai", "tag": [ "lambada" ], "dataset_path": "EleutherAI/lambada_openai", "dataset_name": "default", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "doc_to_text": "{{text.split(' ')[:-1]|join(' ')}}", "doc_to_target": "{{' '+text.split(' ')[-1]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "perplexity", "aggregation": "perplexity", "higher_is_better": false }, { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "loglikelihood", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{text}}", "metadata": { "version": 1.0 } }, "logiqa": { "task": "logiqa", "dataset_path": "EleutherAI/logiqa", "dataset_name": "logiqa", "dataset_kwargs": { "trust_remote_code": true }, "training_split": "train", "validation_split": "validation", "test_split": "test", "doc_to_text": "def doc_to_text(doc) -> str:\n \"\"\"\n Passage: \n Question: \n Choices:\n A. \n B. \n C. \n D. \n Answer:\n \"\"\"\n choices = [\"a\", \"b\", \"c\", \"d\"]\n prompt = \"Passage: \" + doc[\"context\"] + \"\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\nChoices:\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"Answer:\"\n return prompt\n", "doc_to_target": "def doc_to_target(doc) -> int:\n choices = [\"a\", \"b\", \"c\", \"d\"]\n return choices.index(doc[\"label\"].strip())\n", "doc_to_choice": "{{options}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true }, { "metric": "acc_norm", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{context}}", "metadata": { "version": 1.0 } }, "mmlu_abstract_algebra": { "task": "mmlu_abstract_algebra", "task_alias": "abstract_algebra", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "abstract_algebra", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about abstract algebra.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_anatomy": { "task": "mmlu_anatomy", "task_alias": "anatomy", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "anatomy", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about anatomy.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_astronomy": { "task": "mmlu_astronomy", "task_alias": "astronomy", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "astronomy", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about astronomy.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_business_ethics": { "task": "mmlu_business_ethics", "task_alias": "business_ethics", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "business_ethics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about business ethics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_clinical_knowledge": { "task": "mmlu_clinical_knowledge", "task_alias": "clinical_knowledge", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "clinical_knowledge", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about clinical knowledge.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_college_biology": { "task": "mmlu_college_biology", "task_alias": "college_biology", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_biology", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about college biology.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_college_chemistry": { "task": "mmlu_college_chemistry", "task_alias": "college_chemistry", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_chemistry", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about college chemistry.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_college_computer_science": { "task": "mmlu_college_computer_science", "task_alias": "college_computer_science", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_computer_science", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about college computer science.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_college_mathematics": { "task": "mmlu_college_mathematics", "task_alias": "college_mathematics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_mathematics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about college mathematics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_college_medicine": { "task": "mmlu_college_medicine", "task_alias": "college_medicine", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_medicine", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about college medicine.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_college_physics": { "task": "mmlu_college_physics", "task_alias": "college_physics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_physics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about college physics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_computer_security": { "task": "mmlu_computer_security", "task_alias": "computer_security", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "computer_security", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about computer security.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_conceptual_physics": { "task": "mmlu_conceptual_physics", "task_alias": "conceptual_physics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "conceptual_physics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about conceptual physics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_econometrics": { "task": "mmlu_econometrics", "task_alias": "econometrics", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "econometrics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about econometrics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_electrical_engineering": { "task": "mmlu_electrical_engineering", "task_alias": "electrical_engineering", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "electrical_engineering", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about electrical engineering.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_elementary_mathematics": { "task": "mmlu_elementary_mathematics", "task_alias": "elementary_mathematics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "elementary_mathematics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about elementary mathematics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_formal_logic": { "task": "mmlu_formal_logic", "task_alias": "formal_logic", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "formal_logic", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about formal logic.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_global_facts": { "task": "mmlu_global_facts", "task_alias": "global_facts", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "global_facts", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about global facts.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_biology": { "task": "mmlu_high_school_biology", "task_alias": "high_school_biology", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_biology", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school biology.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_chemistry": { "task": "mmlu_high_school_chemistry", "task_alias": "high_school_chemistry", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_chemistry", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school chemistry.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_computer_science": { "task": "mmlu_high_school_computer_science", "task_alias": "high_school_computer_science", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_computer_science", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school computer science.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_european_history": { "task": "mmlu_high_school_european_history", "task_alias": "high_school_european_history", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_european_history", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school european history.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_geography": { "task": "mmlu_high_school_geography", "task_alias": "high_school_geography", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_geography", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school geography.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_government_and_politics": { "task": "mmlu_high_school_government_and_politics", "task_alias": "high_school_government_and_politics", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_government_and_politics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school government and politics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_macroeconomics": { "task": "mmlu_high_school_macroeconomics", "task_alias": "high_school_macroeconomics", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_macroeconomics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school macroeconomics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_mathematics": { "task": "mmlu_high_school_mathematics", "task_alias": "high_school_mathematics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_mathematics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school mathematics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_microeconomics": { "task": "mmlu_high_school_microeconomics", "task_alias": "high_school_microeconomics", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_microeconomics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school microeconomics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_physics": { "task": "mmlu_high_school_physics", "task_alias": "high_school_physics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_physics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school physics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_psychology": { "task": "mmlu_high_school_psychology", "task_alias": "high_school_psychology", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_psychology", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school psychology.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_statistics": { "task": "mmlu_high_school_statistics", "task_alias": "high_school_statistics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_statistics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school statistics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_us_history": { "task": "mmlu_high_school_us_history", "task_alias": "high_school_us_history", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_us_history", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school us history.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_world_history": { "task": "mmlu_high_school_world_history", "task_alias": "high_school_world_history", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_world_history", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school world history.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_human_aging": { "task": "mmlu_human_aging", "task_alias": "human_aging", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "human_aging", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about human aging.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_human_sexuality": { "task": "mmlu_human_sexuality", "task_alias": "human_sexuality", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "human_sexuality", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about human sexuality.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_international_law": { "task": "mmlu_international_law", "task_alias": "international_law", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "international_law", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about international law.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_jurisprudence": { "task": "mmlu_jurisprudence", "task_alias": "jurisprudence", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "jurisprudence", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about jurisprudence.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_logical_fallacies": { "task": "mmlu_logical_fallacies", "task_alias": "logical_fallacies", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "logical_fallacies", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about logical fallacies.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_machine_learning": { "task": "mmlu_machine_learning", "task_alias": "machine_learning", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "machine_learning", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about machine learning.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_management": { "task": "mmlu_management", "task_alias": "management", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "management", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about management.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_marketing": { "task": "mmlu_marketing", "task_alias": "marketing", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "marketing", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about marketing.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_medical_genetics": { "task": "mmlu_medical_genetics", "task_alias": "medical_genetics", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "medical_genetics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about medical genetics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_miscellaneous": { "task": "mmlu_miscellaneous", "task_alias": "miscellaneous", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "miscellaneous", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about miscellaneous.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_moral_disputes": { "task": "mmlu_moral_disputes", "task_alias": "moral_disputes", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "moral_disputes", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about moral disputes.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_moral_scenarios": { "task": "mmlu_moral_scenarios", "task_alias": "moral_scenarios", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "moral_scenarios", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about moral scenarios.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_nutrition": { "task": "mmlu_nutrition", "task_alias": "nutrition", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "nutrition", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about nutrition.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_philosophy": { "task": "mmlu_philosophy", "task_alias": "philosophy", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "philosophy", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about philosophy.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_prehistory": { "task": "mmlu_prehistory", "task_alias": "prehistory", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "prehistory", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about prehistory.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_professional_accounting": { "task": "mmlu_professional_accounting", "task_alias": "professional_accounting", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_accounting", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about professional accounting.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_professional_law": { "task": "mmlu_professional_law", "task_alias": "professional_law", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_law", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about professional law.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_professional_medicine": { "task": "mmlu_professional_medicine", "task_alias": "professional_medicine", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_medicine", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about professional medicine.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_professional_psychology": { "task": "mmlu_professional_psychology", "task_alias": "professional_psychology", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_psychology", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about professional psychology.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_public_relations": { "task": "mmlu_public_relations", "task_alias": "public_relations", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "public_relations", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about public relations.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_security_studies": { "task": "mmlu_security_studies", "task_alias": "security_studies", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "security_studies", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about security studies.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_sociology": { "task": "mmlu_sociology", "task_alias": "sociology", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "sociology", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about sociology.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_us_foreign_policy": { "task": "mmlu_us_foreign_policy", "task_alias": "us_foreign_policy", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "us_foreign_policy", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about us foreign policy.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_virology": { "task": "mmlu_virology", "task_alias": "virology", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "virology", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about virology.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_world_religions": { "task": "mmlu_world_religions", "task_alias": "world_religions", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "world_religions", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about world religions.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "piqa": { "task": "piqa", "dataset_path": "piqa", "dataset_kwargs": { "trust_remote_code": true }, "training_split": "train", "validation_split": "validation", "doc_to_text": "Question: {{goal}}\nAnswer:", "doc_to_target": "label", "doc_to_choice": "{{[sol1, sol2]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true }, { "metric": "acc_norm", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "goal", "metadata": { "version": 1.0 } }, "sciq": { "task": "sciq", "dataset_path": "sciq", "training_split": "train", "validation_split": "validation", "test_split": "test", "doc_to_text": "{{support.lstrip()}}\nQuestion: {{question}}\nAnswer:", "doc_to_target": 3, "doc_to_choice": "{{[distractor1, distractor2, distractor3, correct_answer]}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true }, { "metric": "acc_norm", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{support}} {{question}}", "metadata": { "version": 1.0 } }, "wikitext": { "task": "wikitext", "dataset_path": "EleutherAI/wikitext_document_level", "dataset_name": "wikitext-2-raw-v1", "dataset_kwargs": { "trust_remote_code": true }, "training_split": "train", "validation_split": "validation", "test_split": "test", "doc_to_text": "", "doc_to_target": "def wikitext_detokenizer(doc):\n string = doc[\"page\"]\n # contractions\n string = string.replace(\"s '\", \"s'\")\n string = re.sub(r\"/' [0-9]/\", r\"/'[0-9]/\", string)\n # number separators\n string = string.replace(\" @-@ \", \"-\")\n string = string.replace(\" @,@ \", \",\")\n string = string.replace(\" @.@ \", \".\")\n # punctuation\n string = string.replace(\" : \", \": \")\n string = string.replace(\" ; \", \"; \")\n string = string.replace(\" . \", \". \")\n string = string.replace(\" ! \", \"! \")\n string = string.replace(\" ? \", \"? \")\n string = string.replace(\" , \", \", \")\n # double brackets\n string = re.sub(r\"\\(\\s*([^\\)]*?)\\s*\\)\", r\"(\\1)\", string)\n string = re.sub(r\"\\[\\s*([^\\]]*?)\\s*\\]\", r\"[\\1]\", string)\n string = re.sub(r\"{\\s*([^}]*?)\\s*}\", r\"{\\1}\", string)\n string = re.sub(r\"\\\"\\s*([^\\\"]*?)\\s*\\\"\", r'\"\\1\"', string)\n string = re.sub(r\"'\\s*([^']*?)\\s*'\", r\"'\\1'\", string)\n # miscellaneous\n string = string.replace(\"= = = =\", \"====\")\n string = string.replace(\"= = =\", \"===\")\n string = string.replace(\"= =\", \"==\")\n string = string.replace(\" \" + chr(176) + \" \", chr(176))\n string = string.replace(\" \\n\", \"\\n\")\n string = string.replace(\"\\n \", \"\\n\")\n string = string.replace(\" N \", \" 1 \")\n string = string.replace(\" 's\", \"'s\")\n\n return string\n", "process_results": "def process_results(doc, results):\n (loglikelihood,) = results\n # IMPORTANT: wikitext counts number of words in *original doc before detokenization*\n _words = len(re.split(r\"\\s+\", doc[\"page\"]))\n _bytes = len(doc[\"page\"].encode(\"utf-8\"))\n return {\n \"word_perplexity\": (loglikelihood, _words),\n \"byte_perplexity\": (loglikelihood, _bytes),\n \"bits_per_byte\": (loglikelihood, _bytes),\n }\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "word_perplexity" }, { "metric": "byte_perplexity" }, { "metric": "bits_per_byte" } ], "output_type": "loglikelihood_rolling", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "{{page}}", "metadata": { "version": 2.0 } }, "winogrande": { "task": "winogrande", "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "dataset_kwargs": { "trust_remote_code": true }, "training_split": "train", "validation_split": "validation", "doc_to_text": "def doc_to_text(doc):\n answer_to_num = {\"1\": 0, \"2\": 1}\n return answer_to_num[doc[\"answer\"]]\n", "doc_to_target": "def doc_to_target(doc):\n idx = doc[\"sentence\"].index(\"_\") + 1\n return doc[\"sentence\"][idx:].strip()\n", "doc_to_choice": "def doc_to_choice(doc):\n idx = doc[\"sentence\"].index(\"_\")\n options = [doc[\"option1\"], doc[\"option2\"]]\n return [doc[\"sentence\"][:idx] + opt for opt in options]\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": true, "doc_to_decontamination_query": "sentence", "metadata": { "version": 1.0 } }, "wsc": { "task": "wsc", "tag": [ "super-glue-lm-eval-v1" ], "dataset_path": "super_glue", "dataset_name": "wsc.fixed", "training_split": "train", "validation_split": "validation", "doc_to_text": "def default_doc_to_text(x):\n raw_passage = x[\"text\"]\n # NOTE: HuggingFace span indices are word-based not character-based.\n pre = \" \".join(raw_passage.split()[: x[\"span2_index\"]])\n post = raw_passage[len(pre) + len(x[\"span2_text\"]) + 1 :]\n passage = general_detokenize(pre + \" *{}*\".format(x[\"span2_text\"]) + post)\n noun = x[\"span1_text\"]\n pronoun = x[\"span2_text\"]\n text = (\n f\"Passage: {passage}\\n\"\n + f'Question: In the passage above, does the pronoun \"*{pronoun}*\" refer to \"*{noun}*\"?\\n'\n + \"Answer:\"\n )\n return text\n", "doc_to_target": "label", "doc_to_choice": [ "no", "yes" ], "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "num_fewshot": 0, "metric_list": [ { "metric": "acc" } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } } }, "versions": { "arc_challenge": 1.0, "arc_easy": 1.0, "blimp": 2.0, "blimp_adjunct_island": 1.0, "blimp_anaphor_gender_agreement": 1.0, "blimp_anaphor_number_agreement": 1.0, "blimp_animate_subject_passive": 1.0, "blimp_animate_subject_trans": 1.0, "blimp_causative": 1.0, "blimp_complex_NP_island": 1.0, "blimp_coordinate_structure_constraint_complex_left_branch": 1.0, "blimp_coordinate_structure_constraint_object_extraction": 1.0, "blimp_determiner_noun_agreement_1": 1.0, "blimp_determiner_noun_agreement_2": 1.0, "blimp_determiner_noun_agreement_irregular_1": 1.0, "blimp_determiner_noun_agreement_irregular_2": 1.0, "blimp_determiner_noun_agreement_with_adj_2": 1.0, "blimp_determiner_noun_agreement_with_adj_irregular_1": 1.0, "blimp_determiner_noun_agreement_with_adj_irregular_2": 1.0, "blimp_determiner_noun_agreement_with_adjective_1": 1.0, "blimp_distractor_agreement_relational_noun": 1.0, "blimp_distractor_agreement_relative_clause": 1.0, "blimp_drop_argument": 1.0, "blimp_ellipsis_n_bar_1": 1.0, "blimp_ellipsis_n_bar_2": 1.0, "blimp_existential_there_object_raising": 1.0, "blimp_existential_there_quantifiers_1": 1.0, "blimp_existential_there_quantifiers_2": 1.0, "blimp_existential_there_subject_raising": 1.0, "blimp_expletive_it_object_raising": 1.0, "blimp_inchoative": 1.0, "blimp_intransitive": 1.0, "blimp_irregular_past_participle_adjectives": 1.0, "blimp_irregular_past_participle_verbs": 1.0, "blimp_irregular_plural_subject_verb_agreement_1": 1.0, "blimp_irregular_plural_subject_verb_agreement_2": 1.0, "blimp_left_branch_island_echo_question": 1.0, "blimp_left_branch_island_simple_question": 1.0, "blimp_matrix_question_npi_licensor_present": 1.0, "blimp_npi_present_1": 1.0, "blimp_npi_present_2": 1.0, "blimp_only_npi_licensor_present": 1.0, "blimp_only_npi_scope": 1.0, "blimp_passive_1": 1.0, "blimp_passive_2": 1.0, "blimp_principle_A_c_command": 1.0, "blimp_principle_A_case_1": 1.0, "blimp_principle_A_case_2": 1.0, "blimp_principle_A_domain_1": 1.0, "blimp_principle_A_domain_2": 1.0, "blimp_principle_A_domain_3": 1.0, "blimp_principle_A_reconstruction": 1.0, "blimp_regular_plural_subject_verb_agreement_1": 1.0, "blimp_regular_plural_subject_verb_agreement_2": 1.0, "blimp_sentential_negation_npi_licensor_present": 1.0, "blimp_sentential_negation_npi_scope": 1.0, "blimp_sentential_subject_island": 1.0, "blimp_superlative_quantifiers_1": 1.0, "blimp_superlative_quantifiers_2": 1.0, "blimp_tough_vs_raising_1": 1.0, "blimp_tough_vs_raising_2": 1.0, "blimp_transitive": 1.0, "blimp_wh_island": 1.0, "blimp_wh_questions_object_gap": 1.0, "blimp_wh_questions_subject_gap": 1.0, "blimp_wh_questions_subject_gap_long_distance": 1.0, "blimp_wh_vs_that_no_gap": 1.0, "blimp_wh_vs_that_no_gap_long_distance": 1.0, "blimp_wh_vs_that_with_gap": 1.0, "blimp_wh_vs_that_with_gap_long_distance": 1.0, "lambada_openai": 1.0, "logiqa": 1.0, "mmlu": 2, "mmlu_abstract_algebra": 1.0, "mmlu_anatomy": 1.0, "mmlu_astronomy": 1.0, "mmlu_business_ethics": 1.0, "mmlu_clinical_knowledge": 1.0, "mmlu_college_biology": 1.0, "mmlu_college_chemistry": 1.0, "mmlu_college_computer_science": 1.0, "mmlu_college_mathematics": 1.0, "mmlu_college_medicine": 1.0, "mmlu_college_physics": 1.0, "mmlu_computer_security": 1.0, "mmlu_conceptual_physics": 1.0, "mmlu_econometrics": 1.0, "mmlu_electrical_engineering": 1.0, "mmlu_elementary_mathematics": 1.0, "mmlu_formal_logic": 1.0, "mmlu_global_facts": 1.0, "mmlu_high_school_biology": 1.0, "mmlu_high_school_chemistry": 1.0, "mmlu_high_school_computer_science": 1.0, "mmlu_high_school_european_history": 1.0, "mmlu_high_school_geography": 1.0, "mmlu_high_school_government_and_politics": 1.0, "mmlu_high_school_macroeconomics": 1.0, "mmlu_high_school_mathematics": 1.0, "mmlu_high_school_microeconomics": 1.0, "mmlu_high_school_physics": 1.0, "mmlu_high_school_psychology": 1.0, "mmlu_high_school_statistics": 1.0, "mmlu_high_school_us_history": 1.0, "mmlu_high_school_world_history": 1.0, "mmlu_human_aging": 1.0, "mmlu_human_sexuality": 1.0, "mmlu_humanities": 2, "mmlu_international_law": 1.0, "mmlu_jurisprudence": 1.0, "mmlu_logical_fallacies": 1.0, "mmlu_machine_learning": 1.0, "mmlu_management": 1.0, "mmlu_marketing": 1.0, "mmlu_medical_genetics": 1.0, "mmlu_miscellaneous": 1.0, "mmlu_moral_disputes": 1.0, "mmlu_moral_scenarios": 1.0, "mmlu_nutrition": 1.0, "mmlu_other": 2, "mmlu_philosophy": 1.0, "mmlu_prehistory": 1.0, "mmlu_professional_accounting": 1.0, "mmlu_professional_law": 1.0, "mmlu_professional_medicine": 1.0, "mmlu_professional_psychology": 1.0, "mmlu_public_relations": 1.0, "mmlu_security_studies": 1.0, "mmlu_social_sciences": 2, "mmlu_sociology": 1.0, "mmlu_stem": 2, "mmlu_us_foreign_policy": 1.0, "mmlu_virology": 1.0, "mmlu_world_religions": 1.0, "piqa": 1.0, "sciq": 1.0, "wikitext": 2.0, "winogrande": 1.0, "wsc": 1.0 }, "n-shot": { "arc_challenge": 0, "arc_easy": 0, "blimp_adjunct_island": 0, "blimp_anaphor_gender_agreement": 0, "blimp_anaphor_number_agreement": 0, "blimp_animate_subject_passive": 0, "blimp_animate_subject_trans": 0, "blimp_causative": 0, "blimp_complex_NP_island": 0, "blimp_coordinate_structure_constraint_complex_left_branch": 0, "blimp_coordinate_structure_constraint_object_extraction": 0, "blimp_determiner_noun_agreement_1": 0, "blimp_determiner_noun_agreement_2": 0, "blimp_determiner_noun_agreement_irregular_1": 0, "blimp_determiner_noun_agreement_irregular_2": 0, "blimp_determiner_noun_agreement_with_adj_2": 0, "blimp_determiner_noun_agreement_with_adj_irregular_1": 0, "blimp_determiner_noun_agreement_with_adj_irregular_2": 0, "blimp_determiner_noun_agreement_with_adjective_1": 0, "blimp_distractor_agreement_relational_noun": 0, "blimp_distractor_agreement_relative_clause": 0, "blimp_drop_argument": 0, "blimp_ellipsis_n_bar_1": 0, "blimp_ellipsis_n_bar_2": 0, "blimp_existential_there_object_raising": 0, "blimp_existential_there_quantifiers_1": 0, "blimp_existential_there_quantifiers_2": 0, "blimp_existential_there_subject_raising": 0, "blimp_expletive_it_object_raising": 0, "blimp_inchoative": 0, "blimp_intransitive": 0, "blimp_irregular_past_participle_adjectives": 0, "blimp_irregular_past_participle_verbs": 0, "blimp_irregular_plural_subject_verb_agreement_1": 0, "blimp_irregular_plural_subject_verb_agreement_2": 0, "blimp_left_branch_island_echo_question": 0, "blimp_left_branch_island_simple_question": 0, "blimp_matrix_question_npi_licensor_present": 0, "blimp_npi_present_1": 0, "blimp_npi_present_2": 0, "blimp_only_npi_licensor_present": 0, "blimp_only_npi_scope": 0, "blimp_passive_1": 0, "blimp_passive_2": 0, "blimp_principle_A_c_command": 0, "blimp_principle_A_case_1": 0, "blimp_principle_A_case_2": 0, "blimp_principle_A_domain_1": 0, "blimp_principle_A_domain_2": 0, "blimp_principle_A_domain_3": 0, "blimp_principle_A_reconstruction": 0, "blimp_regular_plural_subject_verb_agreement_1": 0, "blimp_regular_plural_subject_verb_agreement_2": 0, "blimp_sentential_negation_npi_licensor_present": 0, "blimp_sentential_negation_npi_scope": 0, "blimp_sentential_subject_island": 0, "blimp_superlative_quantifiers_1": 0, "blimp_superlative_quantifiers_2": 0, "blimp_tough_vs_raising_1": 0, "blimp_tough_vs_raising_2": 0, "blimp_transitive": 0, "blimp_wh_island": 0, "blimp_wh_questions_object_gap": 0, "blimp_wh_questions_subject_gap": 0, "blimp_wh_questions_subject_gap_long_distance": 0, "blimp_wh_vs_that_no_gap": 0, "blimp_wh_vs_that_no_gap_long_distance": 0, "blimp_wh_vs_that_with_gap": 0, "blimp_wh_vs_that_with_gap_long_distance": 0, "lambada_openai": 0, "logiqa": 0, "mmlu_abstract_algebra": 0, "mmlu_anatomy": 0, "mmlu_astronomy": 0, "mmlu_business_ethics": 0, "mmlu_clinical_knowledge": 0, "mmlu_college_biology": 0, "mmlu_college_chemistry": 0, "mmlu_college_computer_science": 0, "mmlu_college_mathematics": 0, "mmlu_college_medicine": 0, "mmlu_college_physics": 0, "mmlu_computer_security": 0, "mmlu_conceptual_physics": 0, "mmlu_econometrics": 0, "mmlu_electrical_engineering": 0, "mmlu_elementary_mathematics": 0, "mmlu_formal_logic": 0, "mmlu_global_facts": 0, "mmlu_high_school_biology": 0, "mmlu_high_school_chemistry": 0, "mmlu_high_school_computer_science": 0, "mmlu_high_school_european_history": 0, "mmlu_high_school_geography": 0, "mmlu_high_school_government_and_politics": 0, "mmlu_high_school_macroeconomics": 0, "mmlu_high_school_mathematics": 0, "mmlu_high_school_microeconomics": 0, "mmlu_high_school_physics": 0, "mmlu_high_school_psychology": 0, "mmlu_high_school_statistics": 0, "mmlu_high_school_us_history": 0, "mmlu_high_school_world_history": 0, "mmlu_human_aging": 0, "mmlu_human_sexuality": 0, "mmlu_international_law": 0, "mmlu_jurisprudence": 0, "mmlu_logical_fallacies": 0, "mmlu_machine_learning": 0, "mmlu_management": 0, "mmlu_marketing": 0, "mmlu_medical_genetics": 0, "mmlu_miscellaneous": 0, "mmlu_moral_disputes": 0, "mmlu_moral_scenarios": 0, "mmlu_nutrition": 0, "mmlu_philosophy": 0, "mmlu_prehistory": 0, "mmlu_professional_accounting": 0, "mmlu_professional_law": 0, "mmlu_professional_medicine": 0, "mmlu_professional_psychology": 0, "mmlu_public_relations": 0, "mmlu_security_studies": 0, "mmlu_sociology": 0, "mmlu_us_foreign_policy": 0, "mmlu_virology": 0, "mmlu_world_religions": 0, "piqa": 0, "sciq": 0, "wikitext": 0, "winogrande": 0, "wsc": 0 }, "higher_is_better": { "arc_challenge": { "acc": true, "acc_norm": true }, "arc_easy": { "acc": true, "acc_norm": true }, "blimp": { "acc": true }, "blimp_adjunct_island": { "acc": true }, "blimp_anaphor_gender_agreement": { "acc": true }, "blimp_anaphor_number_agreement": { "acc": true }, "blimp_animate_subject_passive": { "acc": true }, "blimp_animate_subject_trans": { "acc": true }, "blimp_causative": { "acc": true }, "blimp_complex_NP_island": { "acc": true }, "blimp_coordinate_structure_constraint_complex_left_branch": { "acc": true }, "blimp_coordinate_structure_constraint_object_extraction": { "acc": true }, "blimp_determiner_noun_agreement_1": { "acc": true }, "blimp_determiner_noun_agreement_2": { "acc": true }, "blimp_determiner_noun_agreement_irregular_1": { "acc": true }, "blimp_determiner_noun_agreement_irregular_2": { "acc": true }, "blimp_determiner_noun_agreement_with_adj_2": { "acc": true }, "blimp_determiner_noun_agreement_with_adj_irregular_1": { "acc": true }, "blimp_determiner_noun_agreement_with_adj_irregular_2": { "acc": true }, "blimp_determiner_noun_agreement_with_adjective_1": { "acc": true }, "blimp_distractor_agreement_relational_noun": { "acc": true }, "blimp_distractor_agreement_relative_clause": { "acc": true }, "blimp_drop_argument": { "acc": true }, "blimp_ellipsis_n_bar_1": { "acc": true }, "blimp_ellipsis_n_bar_2": { "acc": true }, "blimp_existential_there_object_raising": { "acc": true }, "blimp_existential_there_quantifiers_1": { "acc": true }, "blimp_existential_there_quantifiers_2": { "acc": true }, "blimp_existential_there_subject_raising": { "acc": true }, "blimp_expletive_it_object_raising": { "acc": true }, "blimp_inchoative": { "acc": true }, "blimp_intransitive": { "acc": true }, "blimp_irregular_past_participle_adjectives": { "acc": true }, "blimp_irregular_past_participle_verbs": { "acc": true }, "blimp_irregular_plural_subject_verb_agreement_1": { "acc": true }, "blimp_irregular_plural_subject_verb_agreement_2": { "acc": true }, "blimp_left_branch_island_echo_question": { "acc": true }, "blimp_left_branch_island_simple_question": { "acc": true }, "blimp_matrix_question_npi_licensor_present": { "acc": true }, "blimp_npi_present_1": { "acc": true }, "blimp_npi_present_2": { "acc": true }, "blimp_only_npi_licensor_present": { "acc": true }, "blimp_only_npi_scope": { "acc": true }, "blimp_passive_1": { "acc": true }, "blimp_passive_2": { "acc": true }, "blimp_principle_A_c_command": { "acc": true }, "blimp_principle_A_case_1": { "acc": true }, "blimp_principle_A_case_2": { "acc": true }, "blimp_principle_A_domain_1": { "acc": true }, "blimp_principle_A_domain_2": { "acc": true }, "blimp_principle_A_domain_3": { "acc": true }, "blimp_principle_A_reconstruction": { "acc": true }, "blimp_regular_plural_subject_verb_agreement_1": { "acc": true }, "blimp_regular_plural_subject_verb_agreement_2": { "acc": true }, "blimp_sentential_negation_npi_licensor_present": { "acc": true }, "blimp_sentential_negation_npi_scope": { "acc": true }, "blimp_sentential_subject_island": { "acc": true }, "blimp_superlative_quantifiers_1": { "acc": true }, "blimp_superlative_quantifiers_2": { "acc": true }, "blimp_tough_vs_raising_1": { "acc": true }, "blimp_tough_vs_raising_2": { "acc": true }, "blimp_transitive": { "acc": true }, "blimp_wh_island": { "acc": true }, "blimp_wh_questions_object_gap": { "acc": true }, "blimp_wh_questions_subject_gap": { "acc": true }, "blimp_wh_questions_subject_gap_long_distance": { "acc": true }, "blimp_wh_vs_that_no_gap": { "acc": true }, "blimp_wh_vs_that_no_gap_long_distance": { "acc": true }, "blimp_wh_vs_that_with_gap": { "acc": true }, "blimp_wh_vs_that_with_gap_long_distance": { "acc": true }, "lambada_openai": { "perplexity": false, "acc": true }, "logiqa": { "acc": true, "acc_norm": true }, "mmlu": { "acc": true }, "mmlu_abstract_algebra": { "acc": true }, "mmlu_anatomy": { "acc": true }, "mmlu_astronomy": { "acc": true }, "mmlu_business_ethics": { "acc": true }, "mmlu_clinical_knowledge": { "acc": true }, "mmlu_college_biology": { "acc": true }, "mmlu_college_chemistry": { "acc": true }, "mmlu_college_computer_science": { "acc": true }, "mmlu_college_mathematics": { "acc": true }, "mmlu_college_medicine": { "acc": true }, "mmlu_college_physics": { "acc": true }, "mmlu_computer_security": { "acc": true }, "mmlu_conceptual_physics": { "acc": true }, "mmlu_econometrics": { "acc": true }, "mmlu_electrical_engineering": { "acc": true }, "mmlu_elementary_mathematics": { "acc": true }, "mmlu_formal_logic": { "acc": true }, "mmlu_global_facts": { "acc": true }, "mmlu_high_school_biology": { "acc": true }, "mmlu_high_school_chemistry": { "acc": true }, "mmlu_high_school_computer_science": { "acc": true }, "mmlu_high_school_european_history": { "acc": true }, "mmlu_high_school_geography": { "acc": true }, "mmlu_high_school_government_and_politics": { "acc": true }, "mmlu_high_school_macroeconomics": { "acc": true }, "mmlu_high_school_mathematics": { "acc": true }, "mmlu_high_school_microeconomics": { "acc": true }, "mmlu_high_school_physics": { "acc": true }, "mmlu_high_school_psychology": { "acc": true }, "mmlu_high_school_statistics": { "acc": true }, "mmlu_high_school_us_history": { "acc": true }, "mmlu_high_school_world_history": { "acc": true }, "mmlu_human_aging": { "acc": true }, "mmlu_human_sexuality": { "acc": true }, "mmlu_humanities": { "acc": true }, "mmlu_international_law": { "acc": true }, "mmlu_jurisprudence": { "acc": true }, "mmlu_logical_fallacies": { "acc": true }, "mmlu_machine_learning": { "acc": true }, "mmlu_management": { "acc": true }, "mmlu_marketing": { "acc": true }, "mmlu_medical_genetics": { "acc": true }, "mmlu_miscellaneous": { "acc": true }, "mmlu_moral_disputes": { "acc": true }, "mmlu_moral_scenarios": { "acc": true }, "mmlu_nutrition": { "acc": true }, "mmlu_other": { "acc": true }, "mmlu_philosophy": { "acc": true }, "mmlu_prehistory": { "acc": true }, "mmlu_professional_accounting": { "acc": true }, "mmlu_professional_law": { "acc": true }, "mmlu_professional_medicine": { "acc": true }, "mmlu_professional_psychology": { "acc": true }, "mmlu_public_relations": { "acc": true }, "mmlu_security_studies": { "acc": true }, "mmlu_social_sciences": { "acc": true }, "mmlu_sociology": { "acc": true }, "mmlu_stem": { "acc": true }, "mmlu_us_foreign_policy": { "acc": true }, "mmlu_virology": { "acc": true }, "mmlu_world_religions": { "acc": true }, "piqa": { "acc": true, "acc_norm": true }, "sciq": { "acc": true, "acc_norm": true }, "wikitext": { "word_perplexity": false, "byte_perplexity": false, "bits_per_byte": false }, "winogrande": { "acc": true }, "wsc": { "acc": true } }, "n-samples": { "wsc": { "original": 104, "effective": 104 }, "winogrande": { "original": 1267, "effective": 1267 }, "wikitext": { "original": 62, "effective": 62 }, "sciq": { "original": 1000, "effective": 1000 }, "piqa": { "original": 1838, "effective": 1838 }, "mmlu_elementary_mathematics": { "original": 378, "effective": 378 }, "mmlu_electrical_engineering": { "original": 145, "effective": 145 }, "mmlu_high_school_computer_science": { "original": 100, "effective": 100 }, "mmlu_high_school_physics": { "original": 151, "effective": 151 }, "mmlu_college_mathematics": { "original": 100, "effective": 100 }, "mmlu_college_chemistry": { "original": 100, "effective": 100 }, "mmlu_machine_learning": { "original": 112, "effective": 112 }, "mmlu_high_school_mathematics": { "original": 270, "effective": 270 }, "mmlu_computer_security": { "original": 100, "effective": 100 }, "mmlu_conceptual_physics": { "original": 235, "effective": 235 }, "mmlu_high_school_statistics": { "original": 216, "effective": 216 }, "mmlu_high_school_biology": { "original": 310, "effective": 310 }, "mmlu_astronomy": { "original": 152, "effective": 152 }, "mmlu_college_computer_science": { "original": 100, "effective": 100 }, "mmlu_college_biology": { "original": 144, "effective": 144 }, "mmlu_college_physics": { "original": 102, "effective": 102 }, "mmlu_anatomy": { "original": 135, "effective": 135 }, "mmlu_high_school_chemistry": { "original": 203, "effective": 203 }, "mmlu_abstract_algebra": { "original": 100, "effective": 100 }, "mmlu_college_medicine": { "original": 173, "effective": 173 }, "mmlu_medical_genetics": { "original": 100, "effective": 100 }, "mmlu_business_ethics": { "original": 100, "effective": 100 }, "mmlu_miscellaneous": { "original": 783, "effective": 783 }, "mmlu_nutrition": { "original": 306, "effective": 306 }, "mmlu_clinical_knowledge": { "original": 265, "effective": 265 }, "mmlu_human_aging": { "original": 223, "effective": 223 }, "mmlu_professional_accounting": { "original": 282, "effective": 282 }, "mmlu_marketing": { "original": 234, "effective": 234 }, "mmlu_global_facts": { "original": 100, "effective": 100 }, "mmlu_professional_medicine": { "original": 272, "effective": 272 }, "mmlu_virology": { "original": 166, "effective": 166 }, "mmlu_management": { "original": 103, "effective": 103 }, "mmlu_us_foreign_policy": { "original": 100, "effective": 100 }, "mmlu_sociology": { "original": 201, "effective": 201 }, "mmlu_econometrics": { "original": 114, "effective": 114 }, "mmlu_security_studies": { "original": 245, "effective": 245 }, "mmlu_high_school_geography": { "original": 198, "effective": 198 }, "mmlu_public_relations": { "original": 110, "effective": 110 }, "mmlu_high_school_microeconomics": { "original": 238, "effective": 238 }, "mmlu_professional_psychology": { "original": 612, "effective": 612 }, "mmlu_high_school_macroeconomics": { "original": 390, "effective": 390 }, "mmlu_human_sexuality": { "original": 131, "effective": 131 }, "mmlu_high_school_government_and_politics": { "original": 193, "effective": 193 }, "mmlu_high_school_psychology": { "original": 545, "effective": 545 }, "mmlu_moral_disputes": { "original": 346, "effective": 346 }, "mmlu_high_school_world_history": { "original": 237, "effective": 237 }, "mmlu_jurisprudence": { "original": 108, "effective": 108 }, "mmlu_philosophy": { "original": 311, "effective": 311 }, "mmlu_high_school_us_history": { "original": 204, "effective": 204 }, "mmlu_professional_law": { "original": 1534, "effective": 1534 }, "mmlu_logical_fallacies": { "original": 163, "effective": 163 }, "mmlu_moral_scenarios": { "original": 895, "effective": 895 }, "mmlu_formal_logic": { "original": 126, "effective": 126 }, "mmlu_prehistory": { "original": 324, "effective": 324 }, "mmlu_high_school_european_history": { "original": 165, "effective": 165 }, "mmlu_world_religions": { "original": 171, "effective": 171 }, "mmlu_international_law": { "original": 121, "effective": 121 }, "logiqa": { "original": 651, "effective": 651 }, "lambada_openai": { "original": 5153, "effective": 5153 }, "blimp_adjunct_island": { "original": 1000, "effective": 1000 }, "blimp_anaphor_gender_agreement": { "original": 1000, "effective": 1000 }, "blimp_anaphor_number_agreement": { "original": 1000, "effective": 1000 }, "blimp_animate_subject_passive": { "original": 1000, "effective": 1000 }, "blimp_animate_subject_trans": { "original": 1000, "effective": 1000 }, "blimp_causative": { "original": 1000, "effective": 1000 }, "blimp_complex_NP_island": { "original": 1000, "effective": 1000 }, "blimp_coordinate_structure_constraint_complex_left_branch": { "original": 1000, "effective": 1000 }, "blimp_coordinate_structure_constraint_object_extraction": { "original": 1000, "effective": 1000 }, "blimp_determiner_noun_agreement_1": { "original": 1000, "effective": 1000 }, "blimp_determiner_noun_agreement_2": { "original": 1000, "effective": 1000 }, "blimp_determiner_noun_agreement_irregular_1": { "original": 1000, "effective": 1000 }, "blimp_determiner_noun_agreement_irregular_2": { "original": 1000, "effective": 1000 }, "blimp_determiner_noun_agreement_with_adj_2": { "original": 1000, "effective": 1000 }, "blimp_determiner_noun_agreement_with_adj_irregular_1": { "original": 1000, "effective": 1000 }, "blimp_determiner_noun_agreement_with_adj_irregular_2": { "original": 1000, "effective": 1000 }, "blimp_determiner_noun_agreement_with_adjective_1": { "original": 1000, "effective": 1000 }, "blimp_distractor_agreement_relational_noun": { "original": 1000, "effective": 1000 }, "blimp_distractor_agreement_relative_clause": { "original": 1000, "effective": 1000 }, "blimp_drop_argument": { "original": 1000, "effective": 1000 }, "blimp_ellipsis_n_bar_1": { "original": 1000, "effective": 1000 }, "blimp_ellipsis_n_bar_2": { "original": 1000, "effective": 1000 }, "blimp_existential_there_object_raising": { "original": 1000, "effective": 1000 }, "blimp_existential_there_quantifiers_1": { "original": 1000, "effective": 1000 }, "blimp_existential_there_quantifiers_2": { "original": 1000, "effective": 1000 }, "blimp_existential_there_subject_raising": { "original": 1000, "effective": 1000 }, "blimp_expletive_it_object_raising": { "original": 1000, "effective": 1000 }, "blimp_inchoative": { "original": 1000, "effective": 1000 }, "blimp_intransitive": { "original": 1000, "effective": 1000 }, "blimp_irregular_past_participle_adjectives": { "original": 1000, "effective": 1000 }, "blimp_irregular_past_participle_verbs": { "original": 1000, "effective": 1000 }, "blimp_irregular_plural_subject_verb_agreement_1": { "original": 1000, "effective": 1000 }, "blimp_irregular_plural_subject_verb_agreement_2": { "original": 1000, "effective": 1000 }, "blimp_left_branch_island_echo_question": { "original": 1000, "effective": 1000 }, "blimp_left_branch_island_simple_question": { "original": 1000, "effective": 1000 }, "blimp_matrix_question_npi_licensor_present": { "original": 1000, "effective": 1000 }, "blimp_npi_present_1": { "original": 1000, "effective": 1000 }, "blimp_npi_present_2": { "original": 1000, "effective": 1000 }, "blimp_only_npi_licensor_present": { "original": 1000, "effective": 1000 }, "blimp_only_npi_scope": { "original": 1000, "effective": 1000 }, "blimp_passive_1": { "original": 1000, "effective": 1000 }, "blimp_passive_2": { "original": 1000, "effective": 1000 }, "blimp_principle_A_c_command": { "original": 1000, "effective": 1000 }, "blimp_principle_A_case_1": { "original": 1000, "effective": 1000 }, "blimp_principle_A_case_2": { "original": 1000, "effective": 1000 }, "blimp_principle_A_domain_1": { "original": 1000, "effective": 1000 }, "blimp_principle_A_domain_2": { "original": 1000, "effective": 1000 }, "blimp_principle_A_domain_3": { "original": 1000, "effective": 1000 }, "blimp_principle_A_reconstruction": { "original": 1000, "effective": 1000 }, "blimp_regular_plural_subject_verb_agreement_1": { "original": 1000, "effective": 1000 }, "blimp_regular_plural_subject_verb_agreement_2": { "original": 1000, "effective": 1000 }, "blimp_sentential_negation_npi_licensor_present": { "original": 1000, "effective": 1000 }, "blimp_sentential_negation_npi_scope": { "original": 1000, "effective": 1000 }, "blimp_sentential_subject_island": { "original": 1000, "effective": 1000 }, "blimp_superlative_quantifiers_1": { "original": 1000, "effective": 1000 }, "blimp_superlative_quantifiers_2": { "original": 1000, "effective": 1000 }, "blimp_tough_vs_raising_1": { "original": 1000, "effective": 1000 }, "blimp_tough_vs_raising_2": { "original": 1000, "effective": 1000 }, "blimp_transitive": { "original": 1000, "effective": 1000 }, "blimp_wh_island": { "original": 1000, "effective": 1000 }, "blimp_wh_questions_object_gap": { "original": 1000, "effective": 1000 }, "blimp_wh_questions_subject_gap": { "original": 1000, "effective": 1000 }, "blimp_wh_questions_subject_gap_long_distance": { "original": 1000, "effective": 1000 }, "blimp_wh_vs_that_no_gap": { "original": 1000, "effective": 1000 }, "blimp_wh_vs_that_no_gap_long_distance": { "original": 1000, "effective": 1000 }, "blimp_wh_vs_that_with_gap": { "original": 1000, "effective": 1000 }, "blimp_wh_vs_that_with_gap_long_distance": { "original": 1000, "effective": 1000 }, "arc_challenge": { "original": 1172, "effective": 1172 }, "arc_easy": { "original": 2376, "effective": 2376 } }, "config": { "model": "hf", "model_args": "pretrained=EleutherAI/pythia-70m,revision=step0,dtype=float,trust_remote_code=True", "model_num_parameters": 70426624, "model_dtype": "torch.float32", "model_revision": "step0", "model_sha": "61c46343f90c4d113efdfe09eb195382dd242200", "batch_size": "8", "batch_sizes": [], "device": "cuda:0", "use_cache": null, "limit": null, "bootstrap_iters": 100000, "gen_kwargs": null, "random_seed": 0, "numpy_seed": 1234, "torch_seed": 1234, "fewshot_seed": 1234 }, "git_hash": "a5b7c41", "date": 1729865321.050335, "pretty_env_info": "PyTorch version: 2.5.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: 14.0.0-1ubuntu1.1\nCMake version: version 3.30.5\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-6.1.85+-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.140\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: GPU 0: NVIDIA A100-SXM4-40GB\nNvidia driver version: 535.104.05\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.6\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.6\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 46 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 12\nOn-line CPU(s) list: 0-11\nVendor ID: GenuineIntel\nModel name: Intel(R) Xeon(R) CPU @ 2.20GHz\nCPU family: 6\nModel: 85\nThread(s) per core: 2\nCore(s) per socket: 6\nSocket(s): 1\nStepping: 7\nBogoMIPS: 4400.30\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves arat avx512_vnni md_clear arch_capabilities\nHypervisor vendor: KVM\nVirtualization type: full\nL1d cache: 192 KiB (6 instances)\nL1i cache: 192 KiB (6 instances)\nL2 cache: 6 MiB (6 instances)\nL3 cache: 38.5 MiB (1 instance)\nNUMA node(s): 1\nNUMA node0 CPU(s): 0-11\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Vulnerable\nVulnerability Reg file data sampling: Not affected\nVulnerability Retbleed: Vulnerable\nVulnerability Spec rstack overflow: Not affected\nVulnerability Spec store bypass: Vulnerable\nVulnerability Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers\nVulnerability Spectre v2: Vulnerable; IBPB: disabled; STIBP: disabled; PBRSB-eIBRS: Vulnerable; BHI: Vulnerable (Syscall hardening enabled)\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Vulnerable\n\nVersions of relevant libraries:\n[pip3] mypy==1.13.0\n[pip3] mypy-extensions==1.0.0\n[pip3] numpy==1.26.4\n[pip3] optree==0.13.0\n[pip3] torch==2.5.0+cu121\n[pip3] torchaudio==2.5.0+cu121\n[pip3] torchsummary==1.5.1\n[pip3] torchvision==0.20.0+cu121\n[conda] Could not collect", "transformers_version": "4.44.2", "upper_git_hash": null, "tokenizer_pad_token": [ "<|endoftext|>", "0" ], "tokenizer_eos_token": [ "<|endoftext|>", "0" ], "tokenizer_bos_token": [ "<|endoftext|>", "0" ], "eot_token_id": 0, "max_length": 2048, "task_hashes": {}, "model_source": "hf", "model_name": "EleutherAI/pythia-70m", "model_name_sanitized": "EleutherAI__pythia-70m", "system_instruction": null, "system_instruction_sha": null, "fewshot_as_multiturn": false, "chat_template": null, "chat_template_sha": null, "start_time": 202.657694869, "end_time": 850.09258029, "total_evaluation_time_seconds": "647.434885421" }