{"arc_easy": {"alias": "arc_easy", "acc,none": 0.3324915824915825, "acc_stderr,none": 0.009666892606130106, "acc_norm,none": 0.3274410774410774, "acc_norm_stderr,none": 0.009629415859100505}, "blimp": {"acc,none": 0.6876268656716418, "acc_stderr,none": 0.0016400121158043402, "alias": "blimp"}, "blimp_adjunct_island": {"alias": " - blimp_adjunct_island", "acc,none": 0.801, "acc_stderr,none": 0.01263164908309911}, "blimp_anaphor_gender_agreement": {"alias": " - blimp_anaphor_gender_agreement", "acc,none": 0.757, "acc_stderr,none": 0.013569640199177543}, "blimp_anaphor_number_agreement": {"alias": " - blimp_anaphor_number_agreement", "acc,none": 0.809, "acc_stderr,none": 0.012436787112179482}, "blimp_animate_subject_passive": {"alias": " - blimp_animate_subject_passive", "acc,none": 0.716, "acc_stderr,none": 0.014267009061031241}, "blimp_animate_subject_trans": {"alias": " - blimp_animate_subject_trans", "acc,none": 0.547, "acc_stderr,none": 0.015749255189977687}, "blimp_causative": {"alias": " - blimp_causative", "acc,none": 0.715, "acc_stderr,none": 0.014282120955200562}, "blimp_complex_NP_island": {"alias": " - blimp_complex_NP_island", "acc,none": 0.681, "acc_stderr,none": 0.014746404865473363}, "blimp_coordinate_structure_constraint_complex_left_branch": {"alias": " - blimp_coordinate_structure_constraint_complex_left_branch", "acc,none": 0.647, "acc_stderr,none": 0.015120172605483696}, "blimp_coordinate_structure_constraint_object_extraction": {"alias": " - blimp_coordinate_structure_constraint_object_extraction", "acc,none": 0.636, "acc_stderr,none": 0.015222868840522005}, "blimp_determiner_noun_agreement_1": {"alias": " - blimp_determiner_noun_agreement_1", "acc,none": 0.95, "acc_stderr,none": 0.006895472974897918}, "blimp_determiner_noun_agreement_2": {"alias": " - blimp_determiner_noun_agreement_2", "acc,none": 0.868, "acc_stderr,none": 0.010709373963527965}, "blimp_determiner_noun_agreement_irregular_1": {"alias": " - blimp_determiner_noun_agreement_irregular_1", "acc,none": 0.865, "acc_stderr,none": 0.010811655372416006}, "blimp_determiner_noun_agreement_irregular_2": {"alias": " - blimp_determiner_noun_agreement_irregular_2", "acc,none": 0.824, "acc_stderr,none": 0.012048616898597498}, "blimp_determiner_noun_agreement_with_adj_2": {"alias": " - blimp_determiner_noun_agreement_with_adj_2", "acc,none": 0.811, "acc_stderr,none": 0.01238678458811779}, "blimp_determiner_noun_agreement_with_adj_irregular_1": {"alias": " - blimp_determiner_noun_agreement_with_adj_irregular_1", "acc,none": 0.8, "acc_stderr,none": 0.012655439943366653}, "blimp_determiner_noun_agreement_with_adj_irregular_2": {"alias": " - blimp_determiner_noun_agreement_with_adj_irregular_2", "acc,none": 0.719, "acc_stderr,none": 0.01422115470843494}, "blimp_determiner_noun_agreement_with_adjective_1": {"alias": " - blimp_determiner_noun_agreement_with_adjective_1", "acc,none": 0.877, "acc_stderr,none": 0.010391293421849803}, "blimp_distractor_agreement_relational_noun": {"alias": " - blimp_distractor_agreement_relational_noun", "acc,none": 0.662, "acc_stderr,none": 0.014965960710224385}, "blimp_distractor_agreement_relative_clause": {"alias": " - blimp_distractor_agreement_relative_clause", "acc,none": 0.574, "acc_stderr,none": 0.015645087688113762}, "blimp_drop_argument": {"alias": " - blimp_drop_argument", "acc,none": 0.743, "acc_stderr,none": 0.013825416526895026}, "blimp_ellipsis_n_bar_1": {"alias": " - blimp_ellipsis_n_bar_1", "acc,none": 0.804, "acc_stderr,none": 0.012559527926707347}, "blimp_ellipsis_n_bar_2": {"alias": " - blimp_ellipsis_n_bar_2", "acc,none": 0.892, "acc_stderr,none": 0.009820001651345708}, "blimp_existential_there_object_raising": {"alias": " - blimp_existential_there_object_raising", "acc,none": 0.751, "acc_stderr,none": 0.013681600278702275}, "blimp_existential_there_quantifiers_1": {"alias": " - blimp_existential_there_quantifiers_1", "acc,none": 0.896, "acc_stderr,none": 0.009658016218524242}, "blimp_existential_there_quantifiers_2": {"alias": " - blimp_existential_there_quantifiers_2", "acc,none": 0.443, "acc_stderr,none": 0.015716169953204184}, "blimp_existential_there_subject_raising": {"alias": " - blimp_existential_there_subject_raising", "acc,none": 0.651, "acc_stderr,none": 0.015080663991563052}, "blimp_expletive_it_object_raising": {"alias": " - blimp_expletive_it_object_raising", "acc,none": 0.618, "acc_stderr,none": 0.015372453034968502}, "blimp_inchoative": {"alias": " - blimp_inchoative", "acc,none": 0.784, "acc_stderr,none": 0.013019735539307761}, "blimp_intransitive": {"alias": " - blimp_intransitive", "acc,none": 0.86, "acc_stderr,none": 0.010978183844357888}, "blimp_irregular_past_participle_adjectives": {"alias": " - blimp_irregular_past_participle_adjectives", "acc,none": 0.972, "acc_stderr,none": 0.005219506034410081}, "blimp_irregular_past_participle_verbs": {"alias": " - blimp_irregular_past_participle_verbs", "acc,none": 0.548, "acc_stderr,none": 0.01574623586588058}, "blimp_irregular_plural_subject_verb_agreement_1": {"alias": " - blimp_irregular_plural_subject_verb_agreement_1", "acc,none": 0.742, "acc_stderr,none": 0.013842963108656601}, "blimp_irregular_plural_subject_verb_agreement_2": {"alias": " - blimp_irregular_plural_subject_verb_agreement_2", "acc,none": 0.671, "acc_stderr,none": 0.014865395385928355}, "blimp_left_branch_island_echo_question": {"alias": " - blimp_left_branch_island_echo_question", "acc,none": 0.158, "acc_stderr,none": 0.011539894677559635}, "blimp_left_branch_island_simple_question": {"alias": " - blimp_left_branch_island_simple_question", "acc,none": 0.692, "acc_stderr,none": 0.01460648312734278}, "blimp_matrix_question_npi_licensor_present": {"alias": " - blimp_matrix_question_npi_licensor_present", "acc,none": 0.947, "acc_stderr,none": 0.00708810561724649}, "blimp_npi_present_1": {"alias": " - blimp_npi_present_1", "acc,none": 0.443, "acc_stderr,none": 0.015716169953204184}, "blimp_npi_present_2": {"alias": " - blimp_npi_present_2", "acc,none": 0.296, "acc_stderr,none": 0.01444273494157504}, "blimp_only_npi_licensor_present": {"alias": " - blimp_only_npi_licensor_present", "acc,none": 0.965, "acc_stderr,none": 0.005814534272734903}, "blimp_only_npi_scope": {"alias": " - blimp_only_npi_scope", "acc,none": 0.679, "acc_stderr,none": 0.01477082181793475}, "blimp_passive_1": {"alias": " - blimp_passive_1", "acc,none": 0.72, "acc_stderr,none": 0.014205696104091548}, "blimp_passive_2": {"alias": " - blimp_passive_2", "acc,none": 0.76, "acc_stderr,none": 0.013512312258920847}, "blimp_principle_A_c_command": {"alias": " - blimp_principle_A_c_command", "acc,none": 0.545, "acc_stderr,none": 0.015755101498347232}, "blimp_principle_A_case_1": {"alias": " - blimp_principle_A_case_1", "acc,none": 1.0, "acc_stderr,none": 0.0}, "blimp_principle_A_case_2": {"alias": " - blimp_principle_A_case_2", "acc,none": 0.841, "acc_stderr,none": 0.011569479368271195}, "blimp_principle_A_domain_1": {"alias": " - blimp_principle_A_domain_1", "acc,none": 0.946, "acc_stderr,none": 0.007150883521295473}, "blimp_principle_A_domain_2": {"alias": " - blimp_principle_A_domain_2", "acc,none": 0.724, "acc_stderr,none": 0.01414298497574059}, "blimp_principle_A_domain_3": {"alias": " - blimp_principle_A_domain_3", "acc,none": 0.559, "acc_stderr,none": 0.015708779894242766}, "blimp_principle_A_reconstruction": {"alias": " - blimp_principle_A_reconstruction", "acc,none": 0.136, "acc_stderr,none": 0.01084535023047304}, "blimp_regular_plural_subject_verb_agreement_1": {"alias": " - blimp_regular_plural_subject_verb_agreement_1", "acc,none": 0.588, "acc_stderr,none": 0.015572363292015072}, "blimp_regular_plural_subject_verb_agreement_2": {"alias": " - blimp_regular_plural_subject_verb_agreement_2", "acc,none": 0.686, "acc_stderr,none": 0.014683991951088084}, "blimp_sentential_negation_npi_licensor_present": {"alias": " - blimp_sentential_negation_npi_licensor_present", "acc,none": 0.895, "acc_stderr,none": 0.00969892102602496}, "blimp_sentential_negation_npi_scope": {"alias": " - blimp_sentential_negation_npi_scope", "acc,none": 0.449, "acc_stderr,none": 0.015736792768752044}, "blimp_sentential_subject_island": {"alias": " - blimp_sentential_subject_island", "acc,none": 0.342, "acc_stderr,none": 0.015008706182121804}, "blimp_superlative_quantifiers_1": {"alias": " - blimp_superlative_quantifiers_1", "acc,none": 0.69, "acc_stderr,none": 0.014632638658632766}, "blimp_superlative_quantifiers_2": {"alias": " - blimp_superlative_quantifiers_2", "acc,none": 0.395, "acc_stderr,none": 0.015466551464829328}, "blimp_tough_vs_raising_1": {"alias": " - blimp_tough_vs_raising_1", "acc,none": 0.809, "acc_stderr,none": 0.012436787112179482}, "blimp_tough_vs_raising_2": {"alias": " - blimp_tough_vs_raising_2", "acc,none": 0.479, "acc_stderr,none": 0.015805341148131185}, "blimp_transitive": {"alias": " - blimp_transitive", "acc,none": 0.675, "acc_stderr,none": 0.01481872445909548}, "blimp_wh_island": {"alias": " - blimp_wh_island", "acc,none": 0.787, "acc_stderr,none": 0.012953717566737312}, "blimp_wh_questions_object_gap": {"alias": " - blimp_wh_questions_object_gap", "acc,none": 0.38, "acc_stderr,none": 0.015356947477797658}, "blimp_wh_questions_subject_gap": {"alias": " - blimp_wh_questions_subject_gap", "acc,none": 0.688, "acc_stderr,none": 0.014658474370509057}, "blimp_wh_questions_subject_gap_long_distance": {"alias": " - blimp_wh_questions_subject_gap_long_distance", "acc,none": 0.569, "acc_stderr,none": 0.015667944488173442}, "blimp_wh_vs_that_no_gap": {"alias": " - blimp_wh_vs_that_no_gap", "acc,none": 0.541, "acc_stderr,none": 0.015766025737882314}, "blimp_wh_vs_that_no_gap_long_distance": {"alias": " - blimp_wh_vs_that_no_gap_long_distance", "acc,none": 0.62, "acc_stderr,none": 0.015356947477797658}, "blimp_wh_vs_that_with_gap": {"alias": " - blimp_wh_vs_that_with_gap", "acc,none": 0.845, "acc_stderr,none": 0.011450157470799522}, "blimp_wh_vs_that_with_gap_long_distance": {"alias": " - blimp_wh_vs_that_with_gap_long_distance", "acc,none": 0.588, "acc_stderr,none": 0.015572363292015072}, "c4": {"alias": "c4", "word_perplexity,none": 676.435189917389, "word_perplexity_stderr,none": "N/A", "byte_perplexity,none": 2.970678263145432, "byte_perplexity_stderr,none": "N/A", "bits_per_byte,none": 1.5707923637396943, "bits_per_byte_stderr,none": "N/A"}, "hellaswag": {"alias": "hellaswag", "acc,none": 0.27086237801234814, "acc_stderr,none": 0.004434969257446433, "acc_norm,none": 0.29067914758016333, "acc_norm_stderr,none": 0.004531477407589249}, "piqa": {"alias": "piqa", "acc,none": 0.6278563656147987, "acc_stderr,none": 0.011277968313592804, "acc_norm,none": 0.6218715995647442, "acc_norm_stderr,none": 0.011313980666854472}, "wikitext": {"alias": "wikitext", "word_perplexity,none": 610.3257436370111, "word_perplexity_stderr,none": "N/A", "byte_perplexity,none": 3.31828711073885, "byte_perplexity_stderr,none": "N/A", "bits_per_byte,none": 1.730438719120467, "bits_per_byte_stderr,none": "N/A"}}