{ "model_id": "m18", "checkpoint": "results/m18/final.pt", "trained_step": 15258, "num_fewshot": 0, "limit": null, "results": { "lambada_openai": { "name": "lambada_openai", "alias": "lambada_openai", "sample_len": 5153, "perplexity,none": 1004.0061038384438, "perplexity_stderr,none": 54.23896500033554, "acc,none": 0.1568018629924316, "acc_stderr,none": 0.005065852040981164 }, "hellaswag": { "name": "hellaswag", "alias": "hellaswag", "sample_len": 10042, "acc,none": 0.27016530571599284, "acc_stderr,none": 0.004431375549911545, "acc_norm,none": 0.26976697868950406, "acc_norm_stderr,none": 0.004429315788310707 }, "piqa": { "name": "piqa", "alias": "piqa", "sample_len": 1838, "acc,none": 0.5859630032644179, "acc_stderr,none": 0.011492118481417717, "acc_norm,none": 0.588139281828074, "acc_norm_stderr,none": 0.011483141106304523 }, "sciq": { "name": "sciq", "alias": "sciq", "sample_len": 1000, "acc,none": 0.69, "acc_stderr,none": 0.014632638658632766, "acc_norm,none": 0.622, "acc_norm_stderr,none": 0.015341165254026547 }, "arc_easy": { "name": "arc_easy", "alias": "arc_easy", "sample_len": 2376, "acc,none": 0.4414983164983165, "acc_stderr,none": 0.010189314382749861, "acc_norm,none": 0.3968855218855219, "acc_norm_stderr,none": 0.010039236800583027 }, "winogrande": { "name": "winogrande", "alias": "winogrande", "sample_len": 1267, "acc,none": 0.500394632991318, "acc_stderr,none": 0.01405248130604961 }, "blimp_adjunct_island": { "name": "blimp_adjunct_island", "alias": "blimp_adjunct_island", "sample_len": 1000, "acc,none": 0.712, "acc_stderr,none": 0.01432694179723158 }, "blimp_anaphor_gender_agreement": { "name": "blimp_anaphor_gender_agreement", "alias": "blimp_anaphor_gender_agreement", "sample_len": 1000, "acc,none": 0.826, "acc_stderr,none": 0.011994493230973447 }, "blimp_anaphor_number_agreement": { "name": "blimp_anaphor_number_agreement", "alias": "blimp_anaphor_number_agreement", "sample_len": 1000, "acc,none": 0.977, "acc_stderr,none": 0.004742730594656784 }, "blimp_animate_subject_passive": { "name": "blimp_animate_subject_passive", "alias": "blimp_animate_subject_passive", "sample_len": 1000, "acc,none": 0.708, "acc_stderr,none": 0.014385511563477433 }, "blimp_animate_subject_trans": { "name": "blimp_animate_subject_trans", "alias": "blimp_animate_subject_trans", "sample_len": 1000, "acc,none": 0.901, "acc_stderr,none": 0.009449248027662746 }, "blimp_causative": { "name": "blimp_causative", "alias": "blimp_causative", "sample_len": 1000, "acc,none": 0.679, "acc_stderr,none": 0.01477082181793475 }, "blimp_complex_NP_island": { "name": "blimp_complex_NP_island", "alias": "blimp_complex_NP_island", "sample_len": 1000, "acc,none": 0.528, "acc_stderr,none": 0.015794475789511517 }, "blimp_coordinate_structure_constraint_complex_left_branch": { "name": "blimp_coordinate_structure_constraint_complex_left_branch", "alias": "blimp_coordinate_structure_constraint_complex_left_branch", "sample_len": 1000, "acc,none": 0.314, "acc_stderr,none": 0.014683991951088084 }, "blimp_coordinate_structure_constraint_object_extraction": { "name": "blimp_coordinate_structure_constraint_object_extraction", "alias": "blimp_coordinate_structure_constraint_object_extraction", "sample_len": 1000, "acc,none": 0.745, "acc_stderr,none": 0.013790038620872863 }, "blimp_determiner_noun_agreement_1": { "name": "blimp_determiner_noun_agreement_1", "alias": "blimp_determiner_noun_agreement_1", "sample_len": 1000, "acc,none": 0.963, "acc_stderr,none": 0.0059721576223896395 }, "blimp_determiner_noun_agreement_2": { "name": "blimp_determiner_noun_agreement_2", "alias": "blimp_determiner_noun_agreement_2", "sample_len": 1000, "acc,none": 0.938, "acc_stderr,none": 0.007629823996280269 }, "blimp_determiner_noun_agreement_irregular_1": { "name": "blimp_determiner_noun_agreement_irregular_1", "alias": "blimp_determiner_noun_agreement_irregular_1", "sample_len": 1000, "acc,none": 0.864, "acc_stderr,none": 0.01084535023047304 }, "blimp_determiner_noun_agreement_irregular_2": { "name": "blimp_determiner_noun_agreement_irregular_2", "alias": "blimp_determiner_noun_agreement_irregular_2", "sample_len": 1000, "acc,none": 0.911, "acc_stderr,none": 0.009008893392651516 }, "blimp_determiner_noun_agreement_with_adj_2": { "name": "blimp_determiner_noun_agreement_with_adj_2", "alias": "blimp_determiner_noun_agreement_with_adj_2", "sample_len": 1000, "acc,none": 0.896, "acc_stderr,none": 0.009658016218524242 }, "blimp_determiner_noun_agreement_with_adj_irregular_1": { "name": "blimp_determiner_noun_agreement_with_adj_irregular_1", "alias": "blimp_determiner_noun_agreement_with_adj_irregular_1", "sample_len": 1000, "acc,none": 0.815, "acc_stderr,none": 0.012285191326386656 }, "blimp_determiner_noun_agreement_with_adj_irregular_2": { "name": "blimp_determiner_noun_agreement_with_adj_irregular_2", "alias": "blimp_determiner_noun_agreement_with_adj_irregular_2", "sample_len": 1000, "acc,none": 0.874, "acc_stderr,none": 0.010499249222407964 }, "blimp_determiner_noun_agreement_with_adjective_1": { "name": "blimp_determiner_noun_agreement_with_adjective_1", "alias": "blimp_determiner_noun_agreement_with_adjective_1", "sample_len": 1000, "acc,none": 0.91, "acc_stderr,none": 0.009054390204866477 }, "blimp_distractor_agreement_relational_noun": { "name": "blimp_distractor_agreement_relational_noun", "alias": "blimp_distractor_agreement_relational_noun", "sample_len": 1000, "acc,none": 0.776, "acc_stderr,none": 0.013190830072364589 }, "blimp_distractor_agreement_relative_clause": { "name": "blimp_distractor_agreement_relative_clause", "alias": "blimp_distractor_agreement_relative_clause", "sample_len": 1000, "acc,none": 0.632, "acc_stderr,none": 0.015258073561521743 }, "blimp_drop_argument": { "name": "blimp_drop_argument", "alias": "blimp_drop_argument", "sample_len": 1000, "acc,none": 0.756, "acc_stderr,none": 0.013588548437881386 }, "blimp_ellipsis_n_bar_1": { "name": "blimp_ellipsis_n_bar_1", "alias": "blimp_ellipsis_n_bar_1", "sample_len": 1000, "acc,none": 0.741, "acc_stderr,none": 0.013860415257527861 }, "blimp_ellipsis_n_bar_2": { "name": "blimp_ellipsis_n_bar_2", "alias": "blimp_ellipsis_n_bar_2", "sample_len": 1000, "acc,none": 0.825, "acc_stderr,none": 0.012021627157731998 }, "blimp_existential_there_object_raising": { "name": "blimp_existential_there_object_raising", "alias": "blimp_existential_there_object_raising", "sample_len": 1000, "acc,none": 0.767, "acc_stderr,none": 0.01337497251921999 }, "blimp_existential_there_quantifiers_1": { "name": "blimp_existential_there_quantifiers_1", "alias": "blimp_existential_there_quantifiers_1", "sample_len": 1000, "acc,none": 0.979, "acc_stderr,none": 0.0045364721513065165 }, "blimp_existential_there_quantifiers_2": { "name": "blimp_existential_there_quantifiers_2", "alias": "blimp_existential_there_quantifiers_2", "sample_len": 1000, "acc,none": 0.412, "acc_stderr,none": 0.015572363292015074 }, "blimp_existential_there_subject_raising": { "name": "blimp_existential_there_subject_raising", "alias": "blimp_existential_there_subject_raising", "sample_len": 1000, "acc,none": 0.848, "acc_stderr,none": 0.01135891830347525 }, "blimp_expletive_it_object_raising": { "name": "blimp_expletive_it_object_raising", "alias": "blimp_expletive_it_object_raising", "sample_len": 1000, "acc,none": 0.746, "acc_stderr,none": 0.013772206565168622 }, "blimp_inchoative": { "name": "blimp_inchoative", "alias": "blimp_inchoative", "sample_len": 1000, "acc,none": 0.607, "acc_stderr,none": 0.015452824654081525 }, "blimp_intransitive": { "name": "blimp_intransitive", "alias": "blimp_intransitive", "sample_len": 1000, "acc,none": 0.723, "acc_stderr,none": 0.014158794845306273 }, "blimp_irregular_past_participle_adjectives": { "name": "blimp_irregular_past_participle_adjectives", "alias": "blimp_irregular_past_participle_adjectives", "sample_len": 1000, "acc,none": 0.864, "acc_stderr,none": 0.01084535023047304 }, "blimp_irregular_past_participle_verbs": { "name": "blimp_irregular_past_participle_verbs", "alias": "blimp_irregular_past_participle_verbs", "sample_len": 1000, "acc,none": 0.858, "acc_stderr,none": 0.011043457699378305 }, "blimp_irregular_plural_subject_verb_agreement_1": { "name": "blimp_irregular_plural_subject_verb_agreement_1", "alias": "blimp_irregular_plural_subject_verb_agreement_1", "sample_len": 1000, "acc,none": 0.87, "acc_stderr,none": 0.010640169792499236 }, "blimp_irregular_plural_subject_verb_agreement_2": { "name": "blimp_irregular_plural_subject_verb_agreement_2", "alias": "blimp_irregular_plural_subject_verb_agreement_2", "sample_len": 1000, "acc,none": 0.872, "acc_stderr,none": 0.010570133761108595 }, "blimp_left_branch_island_echo_question": { "name": "blimp_left_branch_island_echo_question", "alias": "blimp_left_branch_island_echo_question", "sample_len": 1000, "acc,none": 0.435, "acc_stderr,none": 0.015685057252717346 }, "blimp_left_branch_island_simple_question": { "name": "blimp_left_branch_island_simple_question", "alias": "blimp_left_branch_island_simple_question", "sample_len": 1000, "acc,none": 0.373, "acc_stderr,none": 0.015300493622922927 }, "blimp_matrix_question_npi_licensor_present": { "name": "blimp_matrix_question_npi_licensor_present", "alias": "blimp_matrix_question_npi_licensor_present", "sample_len": 1000, "acc,none": 0.503, "acc_stderr,none": 0.01581901517924682 }, "blimp_npi_present_1": { "name": "blimp_npi_present_1", "alias": "blimp_npi_present_1", "sample_len": 1000, "acc,none": 0.516, "acc_stderr,none": 0.015811198373114985 }, "blimp_npi_present_2": { "name": "blimp_npi_present_2", "alias": "blimp_npi_present_2", "sample_len": 1000, "acc,none": 0.607, "acc_stderr,none": 0.015452824654081525 }, "blimp_only_npi_licensor_present": { "name": "blimp_only_npi_licensor_present", "alias": "blimp_only_npi_licensor_present", "sample_len": 1000, "acc,none": 0.765, "acc_stderr,none": 0.013414729030247124 }, "blimp_only_npi_scope": { "name": "blimp_only_npi_scope", "alias": "blimp_only_npi_scope", "sample_len": 1000, "acc,none": 0.42, "acc_stderr,none": 0.015615500115072968 }, "blimp_passive_1": { "name": "blimp_passive_1", "alias": "blimp_passive_1", "sample_len": 1000, "acc,none": 0.85, "acc_stderr,none": 0.011297239823409418 }, "blimp_passive_2": { "name": "blimp_passive_2", "alias": "blimp_passive_2", "sample_len": 1000, "acc,none": 0.87, "acc_stderr,none": 0.010640169792499236 }, "blimp_principle_A_c_command": { "name": "blimp_principle_A_c_command", "alias": "blimp_principle_A_c_command", "sample_len": 1000, "acc,none": 0.498, "acc_stderr,none": 0.01581917337430266 }, "blimp_principle_A_case_1": { "name": "blimp_principle_A_case_1", "alias": "blimp_principle_A_case_1", "sample_len": 1000, "acc,none": 1.0, "acc_stderr,none": 0.0 }, "blimp_principle_A_case_2": { "name": "blimp_principle_A_case_2", "alias": "blimp_principle_A_case_2", "sample_len": 1000, "acc,none": 0.892, "acc_stderr,none": 0.009820001651345708 }, "blimp_principle_A_domain_1": { "name": "blimp_principle_A_domain_1", "alias": "blimp_principle_A_domain_1", "sample_len": 1000, "acc,none": 0.931, "acc_stderr,none": 0.008018934050315124 }, "blimp_principle_A_domain_2": { "name": "blimp_principle_A_domain_2", "alias": "blimp_principle_A_domain_2", "sample_len": 1000, "acc,none": 0.754, "acc_stderr,none": 0.01362606581775054 }, "blimp_principle_A_domain_3": { "name": "blimp_principle_A_domain_3", "alias": "blimp_principle_A_domain_3", "sample_len": 1000, "acc,none": 0.656, "acc_stderr,none": 0.015029633724408919 }, "blimp_principle_A_reconstruction": { "name": "blimp_principle_A_reconstruction", "alias": "blimp_principle_A_reconstruction", "sample_len": 1000, "acc,none": 0.49, "acc_stderr,none": 0.015816135752773183 }, "blimp_regular_plural_subject_verb_agreement_1": { "name": "blimp_regular_plural_subject_verb_agreement_1", "alias": "blimp_regular_plural_subject_verb_agreement_1", "sample_len": 1000, "acc,none": 0.893, "acc_stderr,none": 0.009779910359847203 }, "blimp_regular_plural_subject_verb_agreement_2": { "name": "blimp_regular_plural_subject_verb_agreement_2", "alias": "blimp_regular_plural_subject_verb_agreement_2", "sample_len": 1000, "acc,none": 0.893, "acc_stderr,none": 0.009779910359847203 }, "blimp_sentential_negation_npi_licensor_present": { "name": "blimp_sentential_negation_npi_licensor_present", "alias": "blimp_sentential_negation_npi_licensor_present", "sample_len": 1000, "acc,none": 0.995, "acc_stderr,none": 0.0022315868748448895 }, "blimp_sentential_negation_npi_scope": { "name": "blimp_sentential_negation_npi_scope", "alias": "blimp_sentential_negation_npi_scope", "sample_len": 1000, "acc,none": 0.554, "acc_stderr,none": 0.01572677116675039 }, "blimp_sentential_subject_island": { "name": "blimp_sentential_subject_island", "alias": "blimp_sentential_subject_island", "sample_len": 1000, "acc,none": 0.335, "acc_stderr,none": 0.014933117490932629 }, "blimp_superlative_quantifiers_1": { "name": "blimp_superlative_quantifiers_1", "alias": "blimp_superlative_quantifiers_1", "sample_len": 1000, "acc,none": 0.821, "acc_stderr,none": 0.012128730605719056 }, "blimp_superlative_quantifiers_2": { "name": "blimp_superlative_quantifiers_2", "alias": "blimp_superlative_quantifiers_2", "sample_len": 1000, "acc,none": 0.799, "acc_stderr,none": 0.012679107214617274 }, "blimp_tough_vs_raising_1": { "name": "blimp_tough_vs_raising_1", "alias": "blimp_tough_vs_raising_1", "sample_len": 1000, "acc,none": 0.458, "acc_stderr,none": 0.015763390640483554 }, "blimp_tough_vs_raising_2": { "name": "blimp_tough_vs_raising_2", "alias": "blimp_tough_vs_raising_2", "sample_len": 1000, "acc,none": 0.922, "acc_stderr,none": 0.00848457353011853 }, "blimp_transitive": { "name": "blimp_transitive", "alias": "blimp_transitive", "sample_len": 1000, "acc,none": 0.808, "acc_stderr,none": 0.012461592646660028 }, "blimp_wh_island": { "name": "blimp_wh_island", "alias": "blimp_wh_island", "sample_len": 1000, "acc,none": 0.794, "acc_stderr,none": 0.012795613612786522 }, "blimp_wh_questions_object_gap": { "name": "blimp_wh_questions_object_gap", "alias": "blimp_wh_questions_object_gap", "sample_len": 1000, "acc,none": 0.642, "acc_stderr,none": 0.015167928865407633 }, "blimp_wh_questions_subject_gap": { "name": "blimp_wh_questions_subject_gap", "alias": "blimp_wh_questions_subject_gap", "sample_len": 1000, "acc,none": 0.874, "acc_stderr,none": 0.010499249222407964 }, "blimp_wh_questions_subject_gap_long_distance": { "name": "blimp_wh_questions_subject_gap_long_distance", "alias": "blimp_wh_questions_subject_gap_long_distance", "sample_len": 1000, "acc,none": 0.862, "acc_stderr,none": 0.010912152632504508 }, "blimp_wh_vs_that_no_gap": { "name": "blimp_wh_vs_that_no_gap", "alias": "blimp_wh_vs_that_no_gap", "sample_len": 1000, "acc,none": 0.951, "acc_stderr,none": 0.006829761756140959 }, "blimp_wh_vs_that_no_gap_long_distance": { "name": "blimp_wh_vs_that_no_gap_long_distance", "alias": "blimp_wh_vs_that_no_gap_long_distance", "sample_len": 1000, "acc,none": 0.987, "acc_stderr,none": 0.003583830889403662 }, "blimp_wh_vs_that_with_gap": { "name": "blimp_wh_vs_that_with_gap", "alias": "blimp_wh_vs_that_with_gap", "sample_len": 1000, "acc,none": 0.452, "acc_stderr,none": 0.01574623586588058 }, "blimp_wh_vs_that_with_gap_long_distance": { "name": "blimp_wh_vs_that_with_gap_long_distance", "alias": "blimp_wh_vs_that_with_gap_long_distance", "sample_len": 1000, "acc,none": 0.15, "acc_stderr,none": 0.011297239823409416 }, "blimp": { "alias": "blimp", "name": "blimp", "sample_len": 67000, "acc,none": 0.7401044776119403, "acc_stderr,none": 0.0015168010428542197, "sample_count": { "acc,none": 67000 } } } }