Codemind-study / m29 /benchmark_results.json
B4K2xx's picture
Add m29
0f7e07d verified
Raw
History Blame Contribute Delete
18.5 kB
{
"model_id": "m29",
"checkpoint": "results/m29/final.pt",
"trained_step": 15258,
"num_fewshot": 0,
"limit": null,
"results": {
"lambada_openai": {
"name": "lambada_openai",
"alias": "lambada_openai",
"sample_len": 5153,
"perplexity,none": 580.781945907576,
"perplexity_stderr,none": 32.536453548312494,
"acc,none": 0.1841645643314574,
"acc_stderr,none": 0.005400281393204285
},
"hellaswag": {
"name": "hellaswag",
"alias": "hellaswag",
"sample_len": 10042,
"acc,none": 0.2727544313881697,
"acc_stderr,none": 0.004444654076551038,
"acc_norm,none": 0.28201553475403307,
"acc_norm_stderr,none": 0.004490612245335525
},
"piqa": {
"name": "piqa",
"alias": "piqa",
"sample_len": 1838,
"acc,none": 0.5919477693144722,
"acc_stderr,none": 0.011466872778651143,
"acc_norm,none": 0.5919477693144722,
"acc_norm_stderr,none": 0.011466872778651143
},
"sciq": {
"name": "sciq",
"alias": "sciq",
"sample_len": 1000,
"acc,none": 0.694,
"acc_stderr,none": 0.014580006055436898,
"acc_norm,none": 0.599,
"acc_norm_stderr,none": 0.015506109745498368
},
"arc_easy": {
"name": "arc_easy",
"alias": "arc_easy",
"sample_len": 2376,
"acc,none": 0.4701178451178451,
"acc_stderr,none": 0.010241444322886225,
"acc_norm,none": 0.4158249158249158,
"acc_norm_stderr,none": 0.01011334824464792
},
"winogrande": {
"name": "winogrande",
"alias": "winogrande",
"sample_len": 1267,
"acc,none": 0.5272296764009471,
"acc_stderr,none": 0.01403163162982771
},
"blimp_adjunct_island": {
"name": "blimp_adjunct_island",
"alias": "blimp_adjunct_island",
"sample_len": 1000,
"acc,none": 0.768,
"acc_stderr,none": 0.013354937452281623
},
"blimp_anaphor_gender_agreement": {
"name": "blimp_anaphor_gender_agreement",
"alias": "blimp_anaphor_gender_agreement",
"sample_len": 1000,
"acc,none": 0.887,
"acc_stderr,none": 0.010016552866696773
},
"blimp_anaphor_number_agreement": {
"name": "blimp_anaphor_number_agreement",
"alias": "blimp_anaphor_number_agreement",
"sample_len": 1000,
"acc,none": 0.978,
"acc_stderr,none": 0.004640855259274689
},
"blimp_animate_subject_passive": {
"name": "blimp_animate_subject_passive",
"alias": "blimp_animate_subject_passive",
"sample_len": 1000,
"acc,none": 0.715,
"acc_stderr,none": 0.014282120955200562
},
"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": 0.708,
"acc_stderr,none": 0.014385511563477433
},
"blimp_complex_NP_island": {
"name": "blimp_complex_NP_island",
"alias": "blimp_complex_NP_island",
"sample_len": 1000,
"acc,none": 0.506,
"acc_stderr,none": 0.015818160898606836
},
"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": 0.393,
"acc_stderr,none": 0.015452824654081525
},
"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": 0.786,
"acc_stderr,none": 0.012975838021968847
},
"blimp_determiner_noun_agreement_1": {
"name": "blimp_determiner_noun_agreement_1",
"alias": "blimp_determiner_noun_agreement_1",
"sample_len": 1000,
"acc,none": 0.973,
"acc_stderr,none": 0.005128089049275305
},
"blimp_determiner_noun_agreement_2": {
"name": "blimp_determiner_noun_agreement_2",
"alias": "blimp_determiner_noun_agreement_2",
"sample_len": 1000,
"acc,none": 0.97,
"acc_stderr,none": 0.0053971408290991564
},
"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": 0.916,
"acc_stderr,none": 0.008776162089491113
},
"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": 0.953,
"acc_stderr,none": 0.006695956678163013
},
"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": 0.932,
"acc_stderr,none": 0.007964887911291624
},
"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": 0.885,
"acc_stderr,none": 0.010093407594904551
},
"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": 0.909,
"acc_stderr,none": 0.009099549538400337
},
"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": 0.943,
"acc_stderr,none": 0.007335175853706905
},
"blimp_distractor_agreement_relational_noun": {
"name": "blimp_distractor_agreement_relational_noun",
"alias": "blimp_distractor_agreement_relational_noun",
"sample_len": 1000,
"acc,none": 0.863,
"acc_stderr,none": 0.01087884871433321
},
"blimp_distractor_agreement_relative_clause": {
"name": "blimp_distractor_agreement_relative_clause",
"alias": "blimp_distractor_agreement_relative_clause",
"sample_len": 1000,
"acc,none": 0.713,
"acc_stderr,none": 0.014312087053810001
},
"blimp_drop_argument": {
"name": "blimp_drop_argument",
"alias": "blimp_drop_argument",
"sample_len": 1000,
"acc,none": 0.766,
"acc_stderr,none": 0.01339490288966006
},
"blimp_ellipsis_n_bar_1": {
"name": "blimp_ellipsis_n_bar_1",
"alias": "blimp_ellipsis_n_bar_1",
"sample_len": 1000,
"acc,none": 0.709,
"acc_stderr,none": 0.014370995982378032
},
"blimp_ellipsis_n_bar_2": {
"name": "blimp_ellipsis_n_bar_2",
"alias": "blimp_ellipsis_n_bar_2",
"sample_len": 1000,
"acc,none": 0.853,
"acc_stderr,none": 0.011203415395160376
},
"blimp_existential_there_object_raising": {
"name": "blimp_existential_there_object_raising",
"alias": "blimp_existential_there_object_raising",
"sample_len": 1000,
"acc,none": 0.703,
"acc_stderr,none": 0.01445683229480096
},
"blimp_existential_there_quantifiers_1": {
"name": "blimp_existential_there_quantifiers_1",
"alias": "blimp_existential_there_quantifiers_1",
"sample_len": 1000,
"acc,none": 0.973,
"acc_stderr,none": 0.005128089049275305
},
"blimp_existential_there_quantifiers_2": {
"name": "blimp_existential_there_quantifiers_2",
"alias": "blimp_existential_there_quantifiers_2",
"sample_len": 1000,
"acc,none": 0.308,
"acc_stderr,none": 0.01460648312734278
},
"blimp_existential_there_subject_raising": {
"name": "blimp_existential_there_subject_raising",
"alias": "blimp_existential_there_subject_raising",
"sample_len": 1000,
"acc,none": 0.866,
"acc_stderr,none": 0.010777762298369738
},
"blimp_expletive_it_object_raising": {
"name": "blimp_expletive_it_object_raising",
"alias": "blimp_expletive_it_object_raising",
"sample_len": 1000,
"acc,none": 0.714,
"acc_stderr,none": 0.014297146862518003
},
"blimp_inchoative": {
"name": "blimp_inchoative",
"alias": "blimp_inchoative",
"sample_len": 1000,
"acc,none": 0.69,
"acc_stderr,none": 0.014632638658632766
},
"blimp_intransitive": {
"name": "blimp_intransitive",
"alias": "blimp_intransitive",
"sample_len": 1000,
"acc,none": 0.782,
"acc_stderr,none": 0.013063179040595235
},
"blimp_irregular_past_participle_adjectives": {
"name": "blimp_irregular_past_participle_adjectives",
"alias": "blimp_irregular_past_participle_adjectives",
"sample_len": 1000,
"acc,none": 0.746,
"acc_stderr,none": 0.013772206565168622
},
"blimp_irregular_past_participle_verbs": {
"name": "blimp_irregular_past_participle_verbs",
"alias": "blimp_irregular_past_participle_verbs",
"sample_len": 1000,
"acc,none": 0.867,
"acc_stderr,none": 0.010743669132397295
},
"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": 0.913,
"acc_stderr,none": 0.008916866630745944
},
"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": 0.903,
"acc_stderr,none": 0.009363689373248062
},
"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": 0.42,
"acc_stderr,none": 0.015615500115072968
},
"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": 0.502,
"acc_stderr,none": 0.01581917337430266
},
"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": 0.52,
"acc_stderr,none": 0.015806639423035177
},
"blimp_npi_present_1": {
"name": "blimp_npi_present_1",
"alias": "blimp_npi_present_1",
"sample_len": 1000,
"acc,none": 0.499,
"acc_stderr,none": 0.015819268290576817
},
"blimp_npi_present_2": {
"name": "blimp_npi_present_2",
"alias": "blimp_npi_present_2",
"sample_len": 1000,
"acc,none": 0.616,
"acc_stderr,none": 0.015387682761896958
},
"blimp_only_npi_licensor_present": {
"name": "blimp_only_npi_licensor_present",
"alias": "blimp_only_npi_licensor_present",
"sample_len": 1000,
"acc,none": 0.913,
"acc_stderr,none": 0.008916866630745944
},
"blimp_only_npi_scope": {
"name": "blimp_only_npi_scope",
"alias": "blimp_only_npi_scope",
"sample_len": 1000,
"acc,none": 0.627,
"acc_stderr,none": 0.015300493622922927
},
"blimp_passive_1": {
"name": "blimp_passive_1",
"alias": "blimp_passive_1",
"sample_len": 1000,
"acc,none": 0.871,
"acc_stderr,none": 0.010605256784796466
},
"blimp_passive_2": {
"name": "blimp_passive_2",
"alias": "blimp_passive_2",
"sample_len": 1000,
"acc,none": 0.869,
"acc_stderr,none": 0.0106748748448379
},
"blimp_principle_A_c_command": {
"name": "blimp_principle_A_c_command",
"alias": "blimp_principle_A_c_command",
"sample_len": 1000,
"acc,none": 0.618,
"acc_stderr,none": 0.015372453034968502
},
"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": 0.956,
"acc_stderr,none": 0.006488921798427387
},
"blimp_principle_A_domain_2": {
"name": "blimp_principle_A_domain_2",
"alias": "blimp_principle_A_domain_2",
"sample_len": 1000,
"acc,none": 0.765,
"acc_stderr,none": 0.013414729030247124
},
"blimp_principle_A_domain_3": {
"name": "blimp_principle_A_domain_3",
"alias": "blimp_principle_A_domain_3",
"sample_len": 1000,
"acc,none": 0.635,
"acc_stderr,none": 0.015231776226264848
},
"blimp_principle_A_reconstruction": {
"name": "blimp_principle_A_reconstruction",
"alias": "blimp_principle_A_reconstruction",
"sample_len": 1000,
"acc,none": 0.299,
"acc_stderr,none": 0.014484778521220435
},
"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": 0.9,
"acc_stderr,none": 0.00949157995752499
},
"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": 0.902,
"acc_stderr,none": 0.009406619184621247
},
"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": 0.98,
"acc_stderr,none": 0.004429403980178329
},
"blimp_sentential_negation_npi_scope": {
"name": "blimp_sentential_negation_npi_scope",
"alias": "blimp_sentential_negation_npi_scope",
"sample_len": 1000,
"acc,none": 0.555,
"acc_stderr,none": 0.015723301886761007
},
"blimp_sentential_subject_island": {
"name": "blimp_sentential_subject_island",
"alias": "blimp_sentential_subject_island",
"sample_len": 1000,
"acc,none": 0.453,
"acc_stderr,none": 0.015749255189977683
},
"blimp_superlative_quantifiers_1": {
"name": "blimp_superlative_quantifiers_1",
"alias": "blimp_superlative_quantifiers_1",
"sample_len": 1000,
"acc,none": 0.783,
"acc_stderr,none": 0.013041513757270706
},
"blimp_superlative_quantifiers_2": {
"name": "blimp_superlative_quantifiers_2",
"alias": "blimp_superlative_quantifiers_2",
"sample_len": 1000,
"acc,none": 0.693,
"acc_stderr,none": 0.01459328489285274
},
"blimp_tough_vs_raising_1": {
"name": "blimp_tough_vs_raising_1",
"alias": "blimp_tough_vs_raising_1",
"sample_len": 1000,
"acc,none": 0.6,
"acc_stderr,none": 0.015499685165842571
},
"blimp_tough_vs_raising_2": {
"name": "blimp_tough_vs_raising_2",
"alias": "blimp_tough_vs_raising_2",
"sample_len": 1000,
"acc,none": 0.879,
"acc_stderr,none": 0.010318210380946179
},
"blimp_transitive": {
"name": "blimp_transitive",
"alias": "blimp_transitive",
"sample_len": 1000,
"acc,none": 0.818,
"acc_stderr,none": 0.0122075806376622
},
"blimp_wh_island": {
"name": "blimp_wh_island",
"alias": "blimp_wh_island",
"sample_len": 1000,
"acc,none": 0.724,
"acc_stderr,none": 0.01414298497574059
},
"blimp_wh_questions_object_gap": {
"name": "blimp_wh_questions_object_gap",
"alias": "blimp_wh_questions_object_gap",
"sample_len": 1000,
"acc,none": 0.769,
"acc_stderr,none": 0.013334797216936478
},
"blimp_wh_questions_subject_gap": {
"name": "blimp_wh_questions_subject_gap",
"alias": "blimp_wh_questions_subject_gap",
"sample_len": 1000,
"acc,none": 0.945,
"acc_stderr,none": 0.0072129762946392
},
"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": 0.909,
"acc_stderr,none": 0.009099549538400337
},
"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": 0.967,
"acc_stderr,none": 0.005651808820452346
},
"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": 0.984,
"acc_stderr,none": 0.003969856390319398
},
"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": 0.533,
"acc_stderr,none": 0.015784807891138876
},
"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": 0.177,
"acc_stderr,none": 0.012075463420375087
},
"blimp": {
"alias": "blimp",
"name": "blimp",
"sample_len": 67000,
"acc,none": 0.7626567164179104,
"acc_stderr,none": 0.0014674121164425231,
"sample_count": {
"acc,none": 67000
}
}
}
}