Codemind-study / m24 /benchmark_results.json
B4K2xx's picture
Add m24 weights and results
8d097f8 verified
Raw
History Blame Contribute Delete
18.5 kB
{
"model_id": "m24",
"checkpoint": "results/m24/final.pt",
"trained_step": 15258,
"num_fewshot": 0,
"limit": null,
"results": {
"lambada_openai": {
"name": "lambada_openai",
"alias": "lambada_openai",
"sample_len": 5153,
"perplexity,none": 715.919138924658,
"perplexity_stderr,none": 39.81174831263173,
"acc,none": 0.1684455656898894,
"acc_stderr,none": 0.00521419424647801
},
"hellaswag": {
"name": "hellaswag",
"alias": "hellaswag",
"sample_len": 10042,
"acc,none": 0.2719577773351922,
"acc_stderr,none": 0.004440588618232529,
"acc_norm,none": 0.27504481179047996,
"acc_norm_stderr,none": 0.004456242601950599
},
"piqa": {
"name": "piqa",
"alias": "piqa",
"sample_len": 1838,
"acc,none": 0.5973884657236126,
"acc_stderr,none": 0.011442395233488875,
"acc_norm,none": 0.588683351468988,
"acc_norm_stderr,none": 0.01148086057719274
},
"sciq": {
"name": "sciq",
"alias": "sciq",
"sample_len": 1000,
"acc,none": 0.646,
"acc_stderr,none": 0.015129868238451812,
"acc_norm,none": 0.572,
"acc_norm_stderr,none": 0.015654426245029267
},
"arc_easy": {
"name": "arc_easy",
"alias": "arc_easy",
"sample_len": 2376,
"acc,none": 0.44107744107744107,
"acc_stderr,none": 0.010188293221040614,
"acc_norm,none": 0.40235690235690236,
"acc_norm_stderr,none": 0.01006224471101146
},
"winogrande": {
"name": "winogrande",
"alias": "winogrande",
"sample_len": 1267,
"acc,none": 0.5201262825572218,
"acc_stderr,none": 0.014041096664344348
},
"blimp_adjunct_island": {
"name": "blimp_adjunct_island",
"alias": "blimp_adjunct_island",
"sample_len": 1000,
"acc,none": 0.744,
"acc_stderr,none": 0.013807775152234145
},
"blimp_anaphor_gender_agreement": {
"name": "blimp_anaphor_gender_agreement",
"alias": "blimp_anaphor_gender_agreement",
"sample_len": 1000,
"acc,none": 0.814,
"acc_stderr,none": 0.012310790208412926
},
"blimp_anaphor_number_agreement": {
"name": "blimp_anaphor_number_agreement",
"alias": "blimp_anaphor_number_agreement",
"sample_len": 1000,
"acc,none": 0.982,
"acc_stderr,none": 0.00420638724961144
},
"blimp_animate_subject_passive": {
"name": "blimp_animate_subject_passive",
"alias": "blimp_animate_subject_passive",
"sample_len": 1000,
"acc,none": 0.698,
"acc_stderr,none": 0.014526080235459496
},
"blimp_animate_subject_trans": {
"name": "blimp_animate_subject_trans",
"alias": "blimp_animate_subject_trans",
"sample_len": 1000,
"acc,none": 0.908,
"acc_stderr,none": 0.009144376393151129
},
"blimp_causative": {
"name": "blimp_causative",
"alias": "blimp_causative",
"sample_len": 1000,
"acc,none": 0.657,
"acc_stderr,none": 0.015019206922357005
},
"blimp_complex_NP_island": {
"name": "blimp_complex_NP_island",
"alias": "blimp_complex_NP_island",
"sample_len": 1000,
"acc,none": 0.488,
"acc_stderr,none": 0.015814743314581686
},
"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": 0.439,
"acc_stderr,none": 0.015701131345400736
},
"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": 0.774,
"acc_stderr,none": 0.013232501619085452
},
"blimp_determiner_noun_agreement_1": {
"name": "blimp_determiner_noun_agreement_1",
"alias": "blimp_determiner_noun_agreement_1",
"sample_len": 1000,
"acc,none": 0.953,
"acc_stderr,none": 0.006695956678163013
},
"blimp_determiner_noun_agreement_2": {
"name": "blimp_determiner_noun_agreement_2",
"alias": "blimp_determiner_noun_agreement_2",
"sample_len": 1000,
"acc,none": 0.921,
"acc_stderr,none": 0.00853415677333337
},
"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": 0.839,
"acc_stderr,none": 0.011628164696727263
},
"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": 0.889,
"acc_stderr,none": 0.009938701010583716
},
"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": 0.885,
"acc_stderr,none": 0.010093407594904551
},
"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": 0.825,
"acc_stderr,none": 0.012021627157731998
},
"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": 0.861,
"acc_stderr,none": 0.010945263761042892
},
"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": 0.832,
"acc_stderr,none": 0.011828605831454352
},
"blimp_distractor_agreement_relative_clause": {
"name": "blimp_distractor_agreement_relative_clause",
"alias": "blimp_distractor_agreement_relative_clause",
"sample_len": 1000,
"acc,none": 0.706,
"acc_stderr,none": 0.014414290540008265
},
"blimp_drop_argument": {
"name": "blimp_drop_argument",
"alias": "blimp_drop_argument",
"sample_len": 1000,
"acc,none": 0.745,
"acc_stderr,none": 0.013790038620872863
},
"blimp_ellipsis_n_bar_1": {
"name": "blimp_ellipsis_n_bar_1",
"alias": "blimp_ellipsis_n_bar_1",
"sample_len": 1000,
"acc,none": 0.738,
"acc_stderr,none": 0.013912208651021217
},
"blimp_ellipsis_n_bar_2": {
"name": "blimp_ellipsis_n_bar_2",
"alias": "blimp_ellipsis_n_bar_2",
"sample_len": 1000,
"acc,none": 0.83,
"acc_stderr,none": 0.011884495834541793
},
"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": 0.975,
"acc_stderr,none": 0.004939574819698493
},
"blimp_existential_there_quantifiers_2": {
"name": "blimp_existential_there_quantifiers_2",
"alias": "blimp_existential_there_quantifiers_2",
"sample_len": 1000,
"acc,none": 0.431,
"acc_stderr,none": 0.01566794448817344
},
"blimp_existential_there_subject_raising": {
"name": "blimp_existential_there_subject_raising",
"alias": "blimp_existential_there_subject_raising",
"sample_len": 1000,
"acc,none": 0.82,
"acc_stderr,none": 0.012155153135512022
},
"blimp_expletive_it_object_raising": {
"name": "blimp_expletive_it_object_raising",
"alias": "blimp_expletive_it_object_raising",
"sample_len": 1000,
"acc,none": 0.8,
"acc_stderr,none": 0.012655439943366653
},
"blimp_inchoative": {
"name": "blimp_inchoative",
"alias": "blimp_inchoative",
"sample_len": 1000,
"acc,none": 0.668,
"acc_stderr,none": 0.014899597242811567
},
"blimp_intransitive": {
"name": "blimp_intransitive",
"alias": "blimp_intransitive",
"sample_len": 1000,
"acc,none": 0.751,
"acc_stderr,none": 0.013681600278702275
},
"blimp_irregular_past_participle_adjectives": {
"name": "blimp_irregular_past_participle_adjectives",
"alias": "blimp_irregular_past_participle_adjectives",
"sample_len": 1000,
"acc,none": 0.817,
"acc_stderr,none": 0.012233587399477745
},
"blimp_irregular_past_participle_verbs": {
"name": "blimp_irregular_past_participle_verbs",
"alias": "blimp_irregular_past_participle_verbs",
"sample_len": 1000,
"acc,none": 0.851,
"acc_stderr,none": 0.011266140684632246
},
"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": 0.849,
"acc_stderr,none": 0.011328165223341657
},
"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": 0.875,
"acc_stderr,none": 0.010463483381956722
},
"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": 0.528,
"acc_stderr,none": 0.015794475789511517
},
"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": 0.514,
"acc_stderr,none": 0.01581309754773093
},
"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": 0.448,
"acc_stderr,none": 0.01573351656634789
},
"blimp_npi_present_1": {
"name": "blimp_npi_present_1",
"alias": "blimp_npi_present_1",
"sample_len": 1000,
"acc,none": 0.634,
"acc_stderr,none": 0.0152406127264056
},
"blimp_npi_present_2": {
"name": "blimp_npi_present_2",
"alias": "blimp_npi_present_2",
"sample_len": 1000,
"acc,none": 0.697,
"acc_stderr,none": 0.014539683710535193
},
"blimp_only_npi_licensor_present": {
"name": "blimp_only_npi_licensor_present",
"alias": "blimp_only_npi_licensor_present",
"sample_len": 1000,
"acc,none": 0.993,
"acc_stderr,none": 0.002637794146243781
},
"blimp_only_npi_scope": {
"name": "blimp_only_npi_scope",
"alias": "blimp_only_npi_scope",
"sample_len": 1000,
"acc,none": 0.548,
"acc_stderr,none": 0.01574623586588058
},
"blimp_passive_1": {
"name": "blimp_passive_1",
"alias": "blimp_passive_1",
"sample_len": 1000,
"acc,none": 0.869,
"acc_stderr,none": 0.0106748748448379
},
"blimp_passive_2": {
"name": "blimp_passive_2",
"alias": "blimp_passive_2",
"sample_len": 1000,
"acc,none": 0.837,
"acc_stderr,none": 0.011686212712746913
},
"blimp_principle_A_c_command": {
"name": "blimp_principle_A_c_command",
"alias": "blimp_principle_A_c_command",
"sample_len": 1000,
"acc,none": 0.628,
"acc_stderr,none": 0.01529214994204052
},
"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": 0.878,
"acc_stderr,none": 0.010354864712936776
},
"blimp_principle_A_domain_1": {
"name": "blimp_principle_A_domain_1",
"alias": "blimp_principle_A_domain_1",
"sample_len": 1000,
"acc,none": 0.968,
"acc_stderr,none": 0.005568393575081328
},
"blimp_principle_A_domain_2": {
"name": "blimp_principle_A_domain_2",
"alias": "blimp_principle_A_domain_2",
"sample_len": 1000,
"acc,none": 0.674,
"acc_stderr,none": 0.014830507204541049
},
"blimp_principle_A_domain_3": {
"name": "blimp_principle_A_domain_3",
"alias": "blimp_principle_A_domain_3",
"sample_len": 1000,
"acc,none": 0.603,
"acc_stderr,none": 0.015480007449307982
},
"blimp_principle_A_reconstruction": {
"name": "blimp_principle_A_reconstruction",
"alias": "blimp_principle_A_reconstruction",
"sample_len": 1000,
"acc,none": 0.485,
"acc_stderr,none": 0.01581217964181488
},
"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": 0.87,
"acc_stderr,none": 0.010640169792499236
},
"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": 0.882,
"acc_stderr,none": 0.010206869264381718
},
"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": 0.999,
"acc_stderr,none": 0.001
},
"blimp_sentential_negation_npi_scope": {
"name": "blimp_sentential_negation_npi_scope",
"alias": "blimp_sentential_negation_npi_scope",
"sample_len": 1000,
"acc,none": 0.675,
"acc_stderr,none": 0.01481872445909548
},
"blimp_sentential_subject_island": {
"name": "blimp_sentential_subject_island",
"alias": "blimp_sentential_subject_island",
"sample_len": 1000,
"acc,none": 0.481,
"acc_stderr,none": 0.015807874268505835
},
"blimp_superlative_quantifiers_1": {
"name": "blimp_superlative_quantifiers_1",
"alias": "blimp_superlative_quantifiers_1",
"sample_len": 1000,
"acc,none": 0.902,
"acc_stderr,none": 0.009406619184621247
},
"blimp_superlative_quantifiers_2": {
"name": "blimp_superlative_quantifiers_2",
"alias": "blimp_superlative_quantifiers_2",
"sample_len": 1000,
"acc,none": 0.741,
"acc_stderr,none": 0.013860415257527861
},
"blimp_tough_vs_raising_1": {
"name": "blimp_tough_vs_raising_1",
"alias": "blimp_tough_vs_raising_1",
"sample_len": 1000,
"acc,none": 0.578,
"acc_stderr,none": 0.015625625112620622
},
"blimp_tough_vs_raising_2": {
"name": "blimp_tough_vs_raising_2",
"alias": "blimp_tough_vs_raising_2",
"sample_len": 1000,
"acc,none": 0.834,
"acc_stderr,none": 0.011772110370812133
},
"blimp_transitive": {
"name": "blimp_transitive",
"alias": "blimp_transitive",
"sample_len": 1000,
"acc,none": 0.785,
"acc_stderr,none": 0.01299784381903183
},
"blimp_wh_island": {
"name": "blimp_wh_island",
"alias": "blimp_wh_island",
"sample_len": 1000,
"acc,none": 0.71,
"acc_stderr,none": 0.014356395999905621
},
"blimp_wh_questions_object_gap": {
"name": "blimp_wh_questions_object_gap",
"alias": "blimp_wh_questions_object_gap",
"sample_len": 1000,
"acc,none": 0.685,
"acc_stderr,none": 0.014696631960792617
},
"blimp_wh_questions_subject_gap": {
"name": "blimp_wh_questions_subject_gap",
"alias": "blimp_wh_questions_subject_gap",
"sample_len": 1000,
"acc,none": 0.885,
"acc_stderr,none": 0.010093407594904551
},
"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": 0.785,
"acc_stderr,none": 0.01299784381903183
},
"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": 0.957,
"acc_stderr,none": 0.006418114379799739
},
"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": 0.97,
"acc_stderr,none": 0.0053971408290991564
},
"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": 0.516,
"acc_stderr,none": 0.015811198373114985
},
"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": 0.226,
"acc_stderr,none": 0.013232501619085452
},
"blimp": {
"alias": "blimp",
"name": "blimp",
"sample_len": 67000,
"acc,none": 0.7588955223880597,
"acc_stderr,none": 0.0015206604479324375,
"sample_count": {
"acc,none": 67000
}
}
}
}