{ "model_id": "m08", "checkpoint": "results/m08/final.pt", "trained_step": 15258, "num_fewshot": 0, "limit": null, "results": { "lambada_openai": { "name": "lambada_openai", "alias": "lambada_openai", "sample_len": 5153, "perplexity,none": 660.9984145594016, "perplexity_stderr,none": 35.57789788830106, "acc,none": 0.172132738210751, "acc_stderr,none": 0.005259254241062246 }, "hellaswag": { "name": "hellaswag", "alias": "hellaswag", "sample_len": 10042, "acc,none": 0.27394941246763593, "acc_stderr,none": 0.004450718673552817, "acc_norm,none": 0.277733519219279, "acc_norm_stderr,none": 0.004469659042824522 }, "piqa": { "name": "piqa", "alias": "piqa", "sample_len": 1838, "acc,none": 0.5990206746463548, "acc_stderr,none": 0.011434766962108364, "acc_norm,none": 0.5805223068552775, "acc_norm_stderr,none": 0.011513551649399906 }, "sciq": { "name": "sciq", "alias": "sciq", "sample_len": 1000, "acc,none": 0.664, "acc_stderr,none": 0.014944140233794895, "acc_norm,none": 0.585, "acc_norm_stderr,none": 0.015589035185604594 }, "arc_easy": { "name": "arc_easy", "alias": "arc_easy", "sample_len": 2376, "acc,none": 0.4574915824915825, "acc_stderr,none": 0.010222638127749506, "acc_norm,none": 0.4116161616161616, "acc_norm_stderr,none": 0.010098218646714813 }, "winogrande": { "name": "winogrande", "alias": "winogrande", "sample_len": 1267, "acc,none": 0.5288082083662194, "acc_stderr,none": 0.014029141615909664 }, "blimp_adjunct_island": { "name": "blimp_adjunct_island", "alias": "blimp_adjunct_island", "sample_len": 1000, "acc,none": 0.848, "acc_stderr,none": 0.01135891830347525 }, "blimp_anaphor_gender_agreement": { "name": "blimp_anaphor_gender_agreement", "alias": "blimp_anaphor_gender_agreement", "sample_len": 1000, "acc,none": 0.856, "acc_stderr,none": 0.01110798754893916 }, "blimp_anaphor_number_agreement": { "name": "blimp_anaphor_number_agreement", "alias": "blimp_anaphor_number_agreement", "sample_len": 1000, "acc,none": 0.966, "acc_stderr,none": 0.0057338361396953854 }, "blimp_animate_subject_passive": { "name": "blimp_animate_subject_passive", "alias": "blimp_animate_subject_passive", "sample_len": 1000, "acc,none": 0.747, "acc_stderr,none": 0.013754278613587126 }, "blimp_animate_subject_trans": { "name": "blimp_animate_subject_trans", "alias": "blimp_animate_subject_trans", "sample_len": 1000, "acc,none": 0.913, "acc_stderr,none": 0.008916866630745944 }, "blimp_causative": { "name": "blimp_causative", "alias": "blimp_causative", "sample_len": 1000, "acc,none": 0.663, "acc_stderr,none": 0.01495508791865346 }, "blimp_complex_NP_island": { "name": "blimp_complex_NP_island", "alias": "blimp_complex_NP_island", "sample_len": 1000, "acc,none": 0.517, "acc_stderr,none": 0.015810153729833274 }, "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": 0.48, "acc_stderr,none": 0.015806639423035177 }, "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": 0.772, "acc_stderr,none": 0.013273740700804434 }, "blimp_determiner_noun_agreement_1": { "name": "blimp_determiner_noun_agreement_1", "alias": "blimp_determiner_noun_agreement_1", "sample_len": 1000, "acc,none": 0.966, "acc_stderr,none": 0.0057338361396953854 }, "blimp_determiner_noun_agreement_2": { "name": "blimp_determiner_noun_agreement_2", "alias": "blimp_determiner_noun_agreement_2", "sample_len": 1000, "acc,none": 0.958, "acc_stderr,none": 0.006346359293033784 }, "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": 0.872, "acc_stderr,none": 0.010570133761108595 }, "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": 0.927, "acc_stderr,none": 0.008230354715243976 }, "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": 0.919, "acc_stderr,none": 0.008632121032139986 }, "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": 0.826, "acc_stderr,none": 0.011994493230973447 }, "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": 0.916, "acc_stderr,none": 0.008776162089491113 }, "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": 0.942, "acc_stderr,none": 0.0073953154557929906 }, "blimp_distractor_agreement_relational_noun": { "name": "blimp_distractor_agreement_relational_noun", "alias": "blimp_distractor_agreement_relational_noun", "sample_len": 1000, "acc,none": 0.855, "acc_stderr,none": 0.0111399775178902 }, "blimp_distractor_agreement_relative_clause": { "name": "blimp_distractor_agreement_relative_clause", "alias": "blimp_distractor_agreement_relative_clause", "sample_len": 1000, "acc,none": 0.687, "acc_stderr,none": 0.014671272822977775 }, "blimp_drop_argument": { "name": "blimp_drop_argument", "alias": "blimp_drop_argument", "sample_len": 1000, "acc,none": 0.742, "acc_stderr,none": 0.013842963108656601 }, "blimp_ellipsis_n_bar_1": { "name": "blimp_ellipsis_n_bar_1", "alias": "blimp_ellipsis_n_bar_1", "sample_len": 1000, "acc,none": 0.777, "acc_stderr,none": 0.013169830843425608 }, "blimp_ellipsis_n_bar_2": { "name": "blimp_ellipsis_n_bar_2", "alias": "blimp_ellipsis_n_bar_2", "sample_len": 1000, "acc,none": 0.837, "acc_stderr,none": 0.011686212712746913 }, "blimp_existential_there_object_raising": { "name": "blimp_existential_there_object_raising", "alias": "blimp_existential_there_object_raising", "sample_len": 1000, "acc,none": 0.786, "acc_stderr,none": 0.012975838021968847 }, "blimp_existential_there_quantifiers_1": { "name": "blimp_existential_there_quantifiers_1", "alias": "blimp_existential_there_quantifiers_1", "sample_len": 1000, "acc,none": 0.962, "acc_stderr,none": 0.0060491811505849775 }, "blimp_existential_there_quantifiers_2": { "name": "blimp_existential_there_quantifiers_2", "alias": "blimp_existential_there_quantifiers_2", "sample_len": 1000, "acc,none": 0.229, "acc_stderr,none": 0.013294199326613684 }, "blimp_existential_there_subject_raising": { "name": "blimp_existential_there_subject_raising", "alias": "blimp_existential_there_subject_raising", "sample_len": 1000, "acc,none": 0.87, "acc_stderr,none": 0.010640169792499236 }, "blimp_expletive_it_object_raising": { "name": "blimp_expletive_it_object_raising", "alias": "blimp_expletive_it_object_raising", "sample_len": 1000, "acc,none": 0.765, "acc_stderr,none": 0.013414729030247124 }, "blimp_inchoative": { "name": "blimp_inchoative", "alias": "blimp_inchoative", "sample_len": 1000, "acc,none": 0.657, "acc_stderr,none": 0.015019206922357005 }, "blimp_intransitive": { "name": "blimp_intransitive", "alias": "blimp_intransitive", "sample_len": 1000, "acc,none": 0.72, "acc_stderr,none": 0.014205696104091548 }, "blimp_irregular_past_participle_adjectives": { "name": "blimp_irregular_past_participle_adjectives", "alias": "blimp_irregular_past_participle_adjectives", "sample_len": 1000, "acc,none": 0.901, "acc_stderr,none": 0.009449248027662746 }, "blimp_irregular_past_participle_verbs": { "name": "blimp_irregular_past_participle_verbs", "alias": "blimp_irregular_past_participle_verbs", "sample_len": 1000, "acc,none": 0.946, "acc_stderr,none": 0.007150883521295473 }, "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": 0.882, "acc_stderr,none": 0.010206869264381718 }, "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": 0.877, "acc_stderr,none": 0.010391293421849803 }, "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": 0.526, "acc_stderr,none": 0.015797897758042797 }, "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": 0.584, "acc_stderr,none": 0.015594460144140522 }, "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": 0.458, "acc_stderr,none": 0.015763390640483554 }, "blimp_npi_present_1": { "name": "blimp_npi_present_1", "alias": "blimp_npi_present_1", "sample_len": 1000, "acc,none": 0.536, "acc_stderr,none": 0.015778243024904673 }, "blimp_npi_present_2": { "name": "blimp_npi_present_2", "alias": "blimp_npi_present_2", "sample_len": 1000, "acc,none": 0.554, "acc_stderr,none": 0.01572677116675039 }, "blimp_only_npi_licensor_present": { "name": "blimp_only_npi_licensor_present", "alias": "blimp_only_npi_licensor_present", "sample_len": 1000, "acc,none": 0.964, "acc_stderr,none": 0.00589395781616553 }, "blimp_only_npi_scope": { "name": "blimp_only_npi_scope", "alias": "blimp_only_npi_scope", "sample_len": 1000, "acc,none": 0.542, "acc_stderr,none": 0.015763390640483554 }, "blimp_passive_1": { "name": "blimp_passive_1", "alias": "blimp_passive_1", "sample_len": 1000, "acc,none": 0.879, "acc_stderr,none": 0.010318210380946179 }, "blimp_passive_2": { "name": "blimp_passive_2", "alias": "blimp_passive_2", "sample_len": 1000, "acc,none": 0.894, "acc_stderr,none": 0.00973955126578524 }, "blimp_principle_A_c_command": { "name": "blimp_principle_A_c_command", "alias": "blimp_principle_A_c_command", "sample_len": 1000, "acc,none": 0.634, "acc_stderr,none": 0.0152406127264056 }, "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": 0.925, "acc_stderr,none": 0.008333333333333333 }, "blimp_principle_A_domain_1": { "name": "blimp_principle_A_domain_1", "alias": "blimp_principle_A_domain_1", "sample_len": 1000, "acc,none": 0.904, "acc_stderr,none": 0.009320454434783257 }, "blimp_principle_A_domain_2": { "name": "blimp_principle_A_domain_2", "alias": "blimp_principle_A_domain_2", "sample_len": 1000, "acc,none": 0.735, "acc_stderr,none": 0.013963164754810064 }, "blimp_principle_A_domain_3": { "name": "blimp_principle_A_domain_3", "alias": "blimp_principle_A_domain_3", "sample_len": 1000, "acc,none": 0.615, "acc_stderr,none": 0.015395194445410945 }, "blimp_principle_A_reconstruction": { "name": "blimp_principle_A_reconstruction", "alias": "blimp_principle_A_reconstruction", "sample_len": 1000, "acc,none": 0.534, "acc_stderr,none": 0.01578268332993769 }, "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": 0.891, "acc_stderr,none": 0.009859828407037124 }, "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": 0.875, "acc_stderr,none": 0.010463483381956722 }, "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": 0.996, "acc_stderr,none": 0.001996994739098726 }, "blimp_sentential_negation_npi_scope": { "name": "blimp_sentential_negation_npi_scope", "alias": "blimp_sentential_negation_npi_scope", "sample_len": 1000, "acc,none": 0.509, "acc_stderr,none": 0.0158167369950053 }, "blimp_sentential_subject_island": { "name": "blimp_sentential_subject_island", "alias": "blimp_sentential_subject_island", "sample_len": 1000, "acc,none": 0.514, "acc_stderr,none": 0.01581309754773093 }, "blimp_superlative_quantifiers_1": { "name": "blimp_superlative_quantifiers_1", "alias": "blimp_superlative_quantifiers_1", "sample_len": 1000, "acc,none": 0.83, "acc_stderr,none": 0.011884495834541793 }, "blimp_superlative_quantifiers_2": { "name": "blimp_superlative_quantifiers_2", "alias": "blimp_superlative_quantifiers_2", "sample_len": 1000, "acc,none": 0.681, "acc_stderr,none": 0.014746404865473363 }, "blimp_tough_vs_raising_1": { "name": "blimp_tough_vs_raising_1", "alias": "blimp_tough_vs_raising_1", "sample_len": 1000, "acc,none": 0.542, "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": 0.923, "acc_stderr,none": 0.00843458014024066 }, "blimp_transitive": { "name": "blimp_transitive", "alias": "blimp_transitive", "sample_len": 1000, "acc,none": 0.777, "acc_stderr,none": 0.013169830843425608 }, "blimp_wh_island": { "name": "blimp_wh_island", "alias": "blimp_wh_island", "sample_len": 1000, "acc,none": 0.729, "acc_stderr,none": 0.014062601350986125 }, "blimp_wh_questions_object_gap": { "name": "blimp_wh_questions_object_gap", "alias": "blimp_wh_questions_object_gap", "sample_len": 1000, "acc,none": 0.765, "acc_stderr,none": 0.013414729030247124 }, "blimp_wh_questions_subject_gap": { "name": "blimp_wh_questions_subject_gap", "alias": "blimp_wh_questions_subject_gap", "sample_len": 1000, "acc,none": 0.913, "acc_stderr,none": 0.008916866630745944 }, "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": 0.911, "acc_stderr,none": 0.009008893392651516 }, "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": 0.969, "acc_stderr,none": 0.005483527064679181 }, "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": 0.983, "acc_stderr,none": 0.004089954489689063 }, "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": 0.487, "acc_stderr,none": 0.015813952101896636 }, "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": 0.7658208955223881, "acc_stderr,none": 0.001467664198474099, "sample_count": { "acc,none": 67000 } } } }