{"arc_easy": {"alias": "arc_easy", "acc,none": 0.3143939393939394, "acc_stderr,none": 0.00952670242316272, "acc_norm,none": 0.31397306397306396, "acc_norm_stderr,none": 0.009523245335215693}, "blimp": {"acc,none": 0.6181044776119402, "acc_stderr,none": 0.0016918211440994926, "alias": "blimp"}, "blimp_adjunct_island": {"alias": " - blimp_adjunct_island", "acc,none": 0.926, "acc_stderr,none": 0.0082820645127041}, "blimp_anaphor_gender_agreement": {"alias": " - blimp_anaphor_gender_agreement", "acc,none": 0.822, "acc_stderr,none": 0.012102167676183571}, "blimp_anaphor_number_agreement": {"alias": " - blimp_anaphor_number_agreement", "acc,none": 0.877, "acc_stderr,none": 0.010391293421849803}, "blimp_animate_subject_passive": {"alias": " - blimp_animate_subject_passive", "acc,none": 0.657, "acc_stderr,none": 0.015019206922357005}, "blimp_animate_subject_trans": {"alias": " - blimp_animate_subject_trans", "acc,none": 0.48, "acc_stderr,none": 0.015806639423035177}, "blimp_causative": {"alias": " - blimp_causative", "acc,none": 0.567, "acc_stderr,none": 0.01567663091218125}, "blimp_complex_NP_island": {"alias": " - blimp_complex_NP_island", "acc,none": 0.647, "acc_stderr,none": 0.015120172605483696}, "blimp_coordinate_structure_constraint_complex_left_branch": {"alias": " - blimp_coordinate_structure_constraint_complex_left_branch", "acc,none": 0.723, "acc_stderr,none": 0.014158794845306273}, "blimp_coordinate_structure_constraint_object_extraction": {"alias": " - blimp_coordinate_structure_constraint_object_extraction", "acc,none": 0.486, "acc_stderr,none": 0.01581309754773093}, "blimp_determiner_noun_agreement_1": {"alias": " - blimp_determiner_noun_agreement_1", "acc,none": 0.897, "acc_stderr,none": 0.009616833339695739}, "blimp_determiner_noun_agreement_2": {"alias": " - blimp_determiner_noun_agreement_2", "acc,none": 0.855, "acc_stderr,none": 0.0111399775178902}, "blimp_determiner_noun_agreement_irregular_1": {"alias": " - blimp_determiner_noun_agreement_irregular_1", "acc,none": 0.863, "acc_stderr,none": 0.01087884871433321}, "blimp_determiner_noun_agreement_irregular_2": {"alias": " - blimp_determiner_noun_agreement_irregular_2", "acc,none": 0.811, "acc_stderr,none": 0.01238678458811779}, "blimp_determiner_noun_agreement_with_adj_2": {"alias": " - blimp_determiner_noun_agreement_with_adj_2", "acc,none": 0.72, "acc_stderr,none": 0.014205696104091548}, "blimp_determiner_noun_agreement_with_adj_irregular_1": {"alias": " - blimp_determiner_noun_agreement_with_adj_irregular_1", "acc,none": 0.64, "acc_stderr,none": 0.015186527932039985}, "blimp_determiner_noun_agreement_with_adj_irregular_2": {"alias": " - blimp_determiner_noun_agreement_with_adj_irregular_2", "acc,none": 0.575, "acc_stderr,none": 0.01564032031704017}, "blimp_determiner_noun_agreement_with_adjective_1": {"alias": " - blimp_determiner_noun_agreement_with_adjective_1", "acc,none": 0.732, "acc_stderr,none": 0.014013292702729519}, "blimp_distractor_agreement_relational_noun": {"alias": " - blimp_distractor_agreement_relational_noun", "acc,none": 0.592, "acc_stderr,none": 0.015549205052920803}, "blimp_distractor_agreement_relative_clause": {"alias": " - blimp_distractor_agreement_relative_clause", "acc,none": 0.475, "acc_stderr,none": 0.015799513429996023}, "blimp_drop_argument": {"alias": " - blimp_drop_argument", "acc,none": 0.793, "acc_stderr,none": 0.012818553557844009}, "blimp_ellipsis_n_bar_1": {"alias": " - blimp_ellipsis_n_bar_1", "acc,none": 0.889, "acc_stderr,none": 0.009938701010583716}, "blimp_ellipsis_n_bar_2": {"alias": " - blimp_ellipsis_n_bar_2", "acc,none": 0.729, "acc_stderr,none": 0.014062601350986125}, "blimp_existential_there_object_raising": {"alias": " - blimp_existential_there_object_raising", "acc,none": 0.53, "acc_stderr,none": 0.015790799515836725}, "blimp_existential_there_quantifiers_1": {"alias": " - blimp_existential_there_quantifiers_1", "acc,none": 0.591, "acc_stderr,none": 0.015555094373257946}, "blimp_existential_there_quantifiers_2": {"alias": " - blimp_existential_there_quantifiers_2", "acc,none": 0.47, "acc_stderr,none": 0.015790799515836725}, "blimp_existential_there_subject_raising": {"alias": " - blimp_existential_there_subject_raising", "acc,none": 0.485, "acc_stderr,none": 0.01581217964181488}, "blimp_expletive_it_object_raising": {"alias": " - blimp_expletive_it_object_raising", "acc,none": 0.393, "acc_stderr,none": 0.015452824654081525}, "blimp_inchoative": {"alias": " - blimp_inchoative", "acc,none": 0.791, "acc_stderr,none": 0.012864077288499337}, "blimp_intransitive": {"alias": " - blimp_intransitive", "acc,none": 0.888, "acc_stderr,none": 0.009977753031397177}, "blimp_irregular_past_participle_adjectives": {"alias": " - blimp_irregular_past_participle_adjectives", "acc,none": 0.896, "acc_stderr,none": 0.009658016218524242}, "blimp_irregular_past_participle_verbs": {"alias": " - blimp_irregular_past_participle_verbs", "acc,none": 0.68, "acc_stderr,none": 0.014758652303574938}, "blimp_irregular_plural_subject_verb_agreement_1": {"alias": " - blimp_irregular_plural_subject_verb_agreement_1", "acc,none": 0.632, "acc_stderr,none": 0.015258073561521743}, "blimp_irregular_plural_subject_verb_agreement_2": {"alias": " - blimp_irregular_plural_subject_verb_agreement_2", "acc,none": 0.577, "acc_stderr,none": 0.015630589090476255}, "blimp_left_branch_island_echo_question": {"alias": " - blimp_left_branch_island_echo_question", "acc,none": 0.182, "acc_stderr,none": 0.0122075806376622}, "blimp_left_branch_island_simple_question": {"alias": " - blimp_left_branch_island_simple_question", "acc,none": 0.528, "acc_stderr,none": 0.015794475789511517}, "blimp_matrix_question_npi_licensor_present": {"alias": " - blimp_matrix_question_npi_licensor_present", "acc,none": 0.568, "acc_stderr,none": 0.01567232023733632}, "blimp_npi_present_1": {"alias": " - blimp_npi_present_1", "acc,none": 0.115, "acc_stderr,none": 0.010093407594904551}, "blimp_npi_present_2": {"alias": " - blimp_npi_present_2", "acc,none": 0.122, "acc_stderr,none": 0.010354864712936776}, "blimp_only_npi_licensor_present": {"alias": " - blimp_only_npi_licensor_present", "acc,none": 0.71, "acc_stderr,none": 0.014356395999905621}, "blimp_only_npi_scope": {"alias": " - blimp_only_npi_scope", "acc,none": 0.495, "acc_stderr,none": 0.015818508944436743}, "blimp_passive_1": {"alias": " - blimp_passive_1", "acc,none": 0.501, "acc_stderr,none": 0.015819268290576817}, "blimp_passive_2": {"alias": " - blimp_passive_2", "acc,none": 0.714, "acc_stderr,none": 0.014297146862518003}, "blimp_principle_A_c_command": {"alias": " - blimp_principle_A_c_command", "acc,none": 0.641, "acc_stderr,none": 0.01517726422479853}, "blimp_principle_A_case_1": {"alias": " - blimp_principle_A_case_1", "acc,none": 0.981, "acc_stderr,none": 0.004319451082910613}, "blimp_principle_A_case_2": {"alias": " - blimp_principle_A_case_2", "acc,none": 0.568, "acc_stderr,none": 0.01567232023733632}, "blimp_principle_A_domain_1": {"alias": " - blimp_principle_A_domain_1", "acc,none": 0.835, "acc_stderr,none": 0.011743632866916136}, "blimp_principle_A_domain_2": {"alias": " - blimp_principle_A_domain_2", "acc,none": 0.788, "acc_stderr,none": 0.01293148186493811}, "blimp_principle_A_domain_3": {"alias": " - blimp_principle_A_domain_3", "acc,none": 0.635, "acc_stderr,none": 0.015231776226264848}, "blimp_principle_A_reconstruction": {"alias": " - blimp_principle_A_reconstruction", "acc,none": 0.174, "acc_stderr,none": 0.011994493230973449}, "blimp_regular_plural_subject_verb_agreement_1": {"alias": " - blimp_regular_plural_subject_verb_agreement_1", "acc,none": 0.486, "acc_stderr,none": 0.01581309754773093}, "blimp_regular_plural_subject_verb_agreement_2": {"alias": " - blimp_regular_plural_subject_verb_agreement_2", "acc,none": 0.565, "acc_stderr,none": 0.015685057252717346}, "blimp_sentential_negation_npi_licensor_present": {"alias": " - blimp_sentential_negation_npi_licensor_present", "acc,none": 0.862, "acc_stderr,none": 0.010912152632504508}, "blimp_sentential_negation_npi_scope": {"alias": " - blimp_sentential_negation_npi_scope", "acc,none": 0.414, "acc_stderr,none": 0.015583544104177552}, "blimp_sentential_subject_island": {"alias": " - blimp_sentential_subject_island", "acc,none": 0.159, "acc_stderr,none": 0.011569479368271195}, "blimp_superlative_quantifiers_1": {"alias": " - blimp_superlative_quantifiers_1", "acc,none": 0.563, "acc_stderr,none": 0.01569322392873043}, "blimp_superlative_quantifiers_2": {"alias": " - blimp_superlative_quantifiers_2", "acc,none": 0.176, "acc_stderr,none": 0.012048616898597498}, "blimp_tough_vs_raising_1": {"alias": " - blimp_tough_vs_raising_1", "acc,none": 0.81, "acc_stderr,none": 0.012411851354816254}, "blimp_tough_vs_raising_2": {"alias": " - blimp_tough_vs_raising_2", "acc,none": 0.484, "acc_stderr,none": 0.015811198373114985}, "blimp_transitive": {"alias": " - blimp_transitive", "acc,none": 0.471, "acc_stderr,none": 0.015792669451628764}, "blimp_wh_island": {"alias": " - blimp_wh_island", "acc,none": 0.835, "acc_stderr,none": 0.011743632866916136}, "blimp_wh_questions_object_gap": {"alias": " - blimp_wh_questions_object_gap", "acc,none": 0.53, "acc_stderr,none": 0.015790799515836725}, "blimp_wh_questions_subject_gap": {"alias": " - blimp_wh_questions_subject_gap", "acc,none": 0.647, "acc_stderr,none": 0.015120172605483696}, "blimp_wh_questions_subject_gap_long_distance": {"alias": " - blimp_wh_questions_subject_gap_long_distance", "acc,none": 0.604, "acc_stderr,none": 0.015473313265859495}, "blimp_wh_vs_that_no_gap": {"alias": " - blimp_wh_vs_that_no_gap", "acc,none": 0.44, "acc_stderr,none": 0.015704987954361718}, "blimp_wh_vs_that_no_gap_long_distance": {"alias": " - blimp_wh_vs_that_no_gap_long_distance", "acc,none": 0.376, "acc_stderr,none": 0.0153251055088981}, "blimp_wh_vs_that_with_gap": {"alias": " - blimp_wh_vs_that_with_gap", "acc,none": 0.934, "acc_stderr,none": 0.007855297938697532}, "blimp_wh_vs_that_with_gap_long_distance": {"alias": " - blimp_wh_vs_that_with_gap_long_distance", "acc,none": 0.811, "acc_stderr,none": 0.01238678458811779}, "c4": {"alias": "c4", "word_perplexity,none": 544.6924403682459, "word_perplexity_stderr,none": "N/A", "byte_perplexity,none": 2.8650896168008617, "byte_perplexity_stderr,none": "N/A", "bits_per_byte,none": 1.5185802655762968, "bits_per_byte_stderr,none": "N/A"}, "hellaswag": {"alias": "hellaswag", "acc,none": 0.2667795259908385, "acc_stderr,none": 0.0044137228230535, "acc_norm,none": 0.280920135431189, "acc_norm_stderr,none": 0.004485300194072218}, "piqa": {"alias": "piqa", "acc,none": 0.5990206746463548, "acc_stderr,none": 0.011434766962108364, "acc_norm,none": 0.5903155603917302, "acc_norm_stderr,none": 0.011473932007187755}, "wikitext": {"alias": "wikitext", "word_perplexity,none": 551.2592677360941, "word_perplexity_stderr,none": "N/A", "byte_perplexity,none": 3.255721573605653, "byte_perplexity_stderr,none": "N/A", "bits_per_byte,none": 1.7029773268910977, "bits_per_byte_stderr,none": "N/A"}}