Zebulon Goriely
Upload models
ed6e9a8
{
"results": {
"blimp": {
"acc,none": 0.7812835820895526,
"acc_stderr,none": 0.001417250797428721,
"alias": "blimp"
},
"blimp_adjunct_island": {
"alias": " - blimp_adjunct_island",
"acc,none": 0.759,
"acc_stderr,none": 0.01353152253451543
},
"blimp_anaphor_gender_agreement": {
"alias": " - blimp_anaphor_gender_agreement",
"acc,none": 0.895,
"acc_stderr,none": 0.009698921026024944
},
"blimp_anaphor_number_agreement": {
"alias": " - blimp_anaphor_number_agreement",
"acc,none": 0.982,
"acc_stderr,none": 0.004206387249611461
},
"blimp_animate_subject_passive": {
"alias": " - blimp_animate_subject_passive",
"acc,none": 0.78,
"acc_stderr,none": 0.013106173040661782
},
"blimp_animate_subject_trans": {
"alias": " - blimp_animate_subject_trans",
"acc,none": 0.878,
"acc_stderr,none": 0.010354864712936722
},
"blimp_causative": {
"alias": " - blimp_causative",
"acc,none": 0.754,
"acc_stderr,none": 0.01362606581775064
},
"blimp_complex_NP_island": {
"alias": " - blimp_complex_NP_island",
"acc,none": 0.483,
"acc_stderr,none": 0.015810153729833427
},
"blimp_coordinate_structure_constraint_complex_left_branch": {
"alias": " - blimp_coordinate_structure_constraint_complex_left_branch",
"acc,none": 0.537,
"acc_stderr,none": 0.01577592722726242
},
"blimp_coordinate_structure_constraint_object_extraction": {
"alias": " - blimp_coordinate_structure_constraint_object_extraction",
"acc,none": 0.803,
"acc_stderr,none": 0.012583693787968133
},
"blimp_determiner_noun_agreement_1": {
"alias": " - blimp_determiner_noun_agreement_1",
"acc,none": 0.987,
"acc_stderr,none": 0.0035838308894036415
},
"blimp_determiner_noun_agreement_2": {
"alias": " - blimp_determiner_noun_agreement_2",
"acc,none": 0.988,
"acc_stderr,none": 0.0034449771940998413
},
"blimp_determiner_noun_agreement_irregular_1": {
"alias": " - blimp_determiner_noun_agreement_irregular_1",
"acc,none": 0.932,
"acc_stderr,none": 0.007964887911291603
},
"blimp_determiner_noun_agreement_irregular_2": {
"alias": " - blimp_determiner_noun_agreement_irregular_2",
"acc,none": 0.968,
"acc_stderr,none": 0.005568393575081352
},
"blimp_determiner_noun_agreement_with_adj_2": {
"alias": " - blimp_determiner_noun_agreement_with_adj_2",
"acc,none": 0.942,
"acc_stderr,none": 0.007395315455792946
},
"blimp_determiner_noun_agreement_with_adj_irregular_1": {
"alias": " - blimp_determiner_noun_agreement_with_adj_irregular_1",
"acc,none": 0.917,
"acc_stderr,none": 0.008728527206074792
},
"blimp_determiner_noun_agreement_with_adj_irregular_2": {
"alias": " - blimp_determiner_noun_agreement_with_adj_irregular_2",
"acc,none": 0.915,
"acc_stderr,none": 0.008823426366942317
},
"blimp_determiner_noun_agreement_with_adjective_1": {
"alias": " - blimp_determiner_noun_agreement_with_adjective_1",
"acc,none": 0.955,
"acc_stderr,none": 0.00655881224140609
},
"blimp_distractor_agreement_relational_noun": {
"alias": " - blimp_distractor_agreement_relational_noun",
"acc,none": 0.856,
"acc_stderr,none": 0.01110798754893915
},
"blimp_distractor_agreement_relative_clause": {
"alias": " - blimp_distractor_agreement_relative_clause",
"acc,none": 0.768,
"acc_stderr,none": 0.013354937452281576
},
"blimp_drop_argument": {
"alias": " - blimp_drop_argument",
"acc,none": 0.778,
"acc_stderr,none": 0.013148721948877364
},
"blimp_ellipsis_n_bar_1": {
"alias": " - blimp_ellipsis_n_bar_1",
"acc,none": 0.822,
"acc_stderr,none": 0.012102167676183589
},
"blimp_ellipsis_n_bar_2": {
"alias": " - blimp_ellipsis_n_bar_2",
"acc,none": 0.907,
"acc_stderr,none": 0.009188875634996685
},
"blimp_existential_there_object_raising": {
"alias": " - blimp_existential_there_object_raising",
"acc,none": 0.814,
"acc_stderr,none": 0.012310790208412796
},
"blimp_existential_there_quantifiers_1": {
"alias": " - blimp_existential_there_quantifiers_1",
"acc,none": 0.954,
"acc_stderr,none": 0.006627814717380709
},
"blimp_existential_there_quantifiers_2": {
"alias": " - blimp_existential_there_quantifiers_2",
"acc,none": 0.234,
"acc_stderr,none": 0.013394902889660007
},
"blimp_existential_there_subject_raising": {
"alias": " - blimp_existential_there_subject_raising",
"acc,none": 0.893,
"acc_stderr,none": 0.009779910359847169
},
"blimp_expletive_it_object_raising": {
"alias": " - blimp_expletive_it_object_raising",
"acc,none": 0.788,
"acc_stderr,none": 0.012931481864938046
},
"blimp_inchoative": {
"alias": " - blimp_inchoative",
"acc,none": 0.672,
"acc_stderr,none": 0.014853842487270336
},
"blimp_intransitive": {
"alias": " - blimp_intransitive",
"acc,none": 0.793,
"acc_stderr,none": 0.012818553557843967
},
"blimp_irregular_past_participle_adjectives": {
"alias": " - blimp_irregular_past_participle_adjectives",
"acc,none": 0.968,
"acc_stderr,none": 0.005568393575081358
},
"blimp_irregular_past_participle_verbs": {
"alias": " - blimp_irregular_past_participle_verbs",
"acc,none": 0.875,
"acc_stderr,none": 0.010463483381956722
},
"blimp_irregular_plural_subject_verb_agreement_1": {
"alias": " - blimp_irregular_plural_subject_verb_agreement_1",
"acc,none": 0.891,
"acc_stderr,none": 0.009859828407037188
},
"blimp_irregular_plural_subject_verb_agreement_2": {
"alias": " - blimp_irregular_plural_subject_verb_agreement_2",
"acc,none": 0.928,
"acc_stderr,none": 0.008178195576218681
},
"blimp_left_branch_island_echo_question": {
"alias": " - blimp_left_branch_island_echo_question",
"acc,none": 0.532,
"acc_stderr,none": 0.015786868759359016
},
"blimp_left_branch_island_simple_question": {
"alias": " - blimp_left_branch_island_simple_question",
"acc,none": 0.598,
"acc_stderr,none": 0.015512467135715077
},
"blimp_matrix_question_npi_licensor_present": {
"alias": " - blimp_matrix_question_npi_licensor_present",
"acc,none": 0.567,
"acc_stderr,none": 0.01567663091218133
},
"blimp_npi_present_1": {
"alias": " - blimp_npi_present_1",
"acc,none": 0.673,
"acc_stderr,none": 0.01484221315341124
},
"blimp_npi_present_2": {
"alias": " - blimp_npi_present_2",
"acc,none": 0.681,
"acc_stderr,none": 0.014746404865473487
},
"blimp_only_npi_licensor_present": {
"alias": " - blimp_only_npi_licensor_present",
"acc,none": 0.692,
"acc_stderr,none": 0.01460648312734276
},
"blimp_only_npi_scope": {
"alias": " - blimp_only_npi_scope",
"acc,none": 0.28,
"acc_stderr,none": 0.014205696104091508
},
"blimp_passive_1": {
"alias": " - blimp_passive_1",
"acc,none": 0.888,
"acc_stderr,none": 0.009977753031397238
},
"blimp_passive_2": {
"alias": " - blimp_passive_2",
"acc,none": 0.895,
"acc_stderr,none": 0.009698921026024957
},
"blimp_principle_A_c_command": {
"alias": " - blimp_principle_A_c_command",
"acc,none": 0.707,
"acc_stderr,none": 0.014399942998441271
},
"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": 0.965,
"acc_stderr,none": 0.005814534272734965
},
"blimp_principle_A_domain_1": {
"alias": " - blimp_principle_A_domain_1",
"acc,none": 0.945,
"acc_stderr,none": 0.007212976294639241
},
"blimp_principle_A_domain_2": {
"alias": " - blimp_principle_A_domain_2",
"acc,none": 0.844,
"acc_stderr,none": 0.011480235006122368
},
"blimp_principle_A_domain_3": {
"alias": " - blimp_principle_A_domain_3",
"acc,none": 0.681,
"acc_stderr,none": 0.014746404865473493
},
"blimp_principle_A_reconstruction": {
"alias": " - blimp_principle_A_reconstruction",
"acc,none": 0.374,
"acc_stderr,none": 0.015308767369006363
},
"blimp_regular_plural_subject_verb_agreement_1": {
"alias": " - blimp_regular_plural_subject_verb_agreement_1",
"acc,none": 0.934,
"acc_stderr,none": 0.007855297938697608
},
"blimp_regular_plural_subject_verb_agreement_2": {
"alias": " - blimp_regular_plural_subject_verb_agreement_2",
"acc,none": 0.895,
"acc_stderr,none": 0.009698921026024971
},
"blimp_sentential_negation_npi_licensor_present": {
"alias": " - blimp_sentential_negation_npi_licensor_present",
"acc,none": 0.965,
"acc_stderr,none": 0.00581453427273496
},
"blimp_sentential_negation_npi_scope": {
"alias": " - blimp_sentential_negation_npi_scope",
"acc,none": 0.707,
"acc_stderr,none": 0.014399942998441273
},
"blimp_sentential_subject_island": {
"alias": " - blimp_sentential_subject_island",
"acc,none": 0.375,
"acc_stderr,none": 0.015316971293620996
},
"blimp_superlative_quantifiers_1": {
"alias": " - blimp_superlative_quantifiers_1",
"acc,none": 0.828,
"acc_stderr,none": 0.011939788882495321
},
"blimp_superlative_quantifiers_2": {
"alias": " - blimp_superlative_quantifiers_2",
"acc,none": 0.574,
"acc_stderr,none": 0.01564508768811381
},
"blimp_tough_vs_raising_1": {
"alias": " - blimp_tough_vs_raising_1",
"acc,none": 0.562,
"acc_stderr,none": 0.01569721001969469
},
"blimp_tough_vs_raising_2": {
"alias": " - blimp_tough_vs_raising_2",
"acc,none": 0.906,
"acc_stderr,none": 0.009233052000787731
},
"blimp_transitive": {
"alias": " - blimp_transitive",
"acc,none": 0.851,
"acc_stderr,none": 0.011266140684632176
},
"blimp_wh_island": {
"alias": " - blimp_wh_island",
"acc,none": 0.719,
"acc_stderr,none": 0.014221154708434946
},
"blimp_wh_questions_object_gap": {
"alias": " - blimp_wh_questions_object_gap",
"acc,none": 0.763,
"acc_stderr,none": 0.013454070462577938
},
"blimp_wh_questions_subject_gap": {
"alias": " - blimp_wh_questions_subject_gap",
"acc,none": 0.944,
"acc_stderr,none": 0.007274401481697063
},
"blimp_wh_questions_subject_gap_long_distance": {
"alias": " - blimp_wh_questions_subject_gap_long_distance",
"acc,none": 0.844,
"acc_stderr,none": 0.011480235006122372
},
"blimp_wh_vs_that_no_gap": {
"alias": " - blimp_wh_vs_that_no_gap",
"acc,none": 0.984,
"acc_stderr,none": 0.00396985639031941
},
"blimp_wh_vs_that_no_gap_long_distance": {
"alias": " - blimp_wh_vs_that_no_gap_long_distance",
"acc,none": 0.975,
"acc_stderr,none": 0.004939574819698458
},
"blimp_wh_vs_that_with_gap": {
"alias": " - blimp_wh_vs_that_with_gap",
"acc,none": 0.503,
"acc_stderr,none": 0.015819015179246724
},
"blimp_wh_vs_that_with_gap_long_distance": {
"alias": " - blimp_wh_vs_that_with_gap_long_distance",
"acc,none": 0.279,
"acc_stderr,none": 0.014190150117612028
}
},
"groups": {
"blimp": {
"acc,none": 0.7812835820895526,
"acc_stderr,none": 0.001417250797428721,
"alias": "blimp"
}
},
"group_subtasks": {
"blimp": [
"blimp_adjunct_island",
"blimp_anaphor_gender_agreement",
"blimp_anaphor_number_agreement",
"blimp_animate_subject_passive",
"blimp_animate_subject_trans",
"blimp_causative",
"blimp_complex_NP_island",
"blimp_coordinate_structure_constraint_complex_left_branch",
"blimp_coordinate_structure_constraint_object_extraction",
"blimp_determiner_noun_agreement_1",
"blimp_determiner_noun_agreement_2",
"blimp_determiner_noun_agreement_irregular_1",
"blimp_determiner_noun_agreement_irregular_2",
"blimp_determiner_noun_agreement_with_adj_2",
"blimp_determiner_noun_agreement_with_adj_irregular_1",
"blimp_determiner_noun_agreement_with_adj_irregular_2",
"blimp_determiner_noun_agreement_with_adjective_1",
"blimp_distractor_agreement_relational_noun",
"blimp_distractor_agreement_relative_clause",
"blimp_drop_argument",
"blimp_ellipsis_n_bar_1",
"blimp_ellipsis_n_bar_2",
"blimp_existential_there_object_raising",
"blimp_existential_there_quantifiers_1",
"blimp_existential_there_quantifiers_2",
"blimp_existential_there_subject_raising",
"blimp_expletive_it_object_raising",
"blimp_inchoative",
"blimp_intransitive",
"blimp_irregular_past_participle_adjectives",
"blimp_irregular_past_participle_verbs",
"blimp_irregular_plural_subject_verb_agreement_1",
"blimp_irregular_plural_subject_verb_agreement_2",
"blimp_left_branch_island_echo_question",
"blimp_left_branch_island_simple_question",
"blimp_matrix_question_npi_licensor_present",
"blimp_npi_present_1",
"blimp_npi_present_2",
"blimp_only_npi_licensor_present",
"blimp_only_npi_scope",
"blimp_passive_1",
"blimp_passive_2",
"blimp_principle_A_c_command",
"blimp_principle_A_case_1",
"blimp_principle_A_case_2",
"blimp_principle_A_domain_1",
"blimp_principle_A_domain_2",
"blimp_principle_A_domain_3",
"blimp_principle_A_reconstruction",
"blimp_regular_plural_subject_verb_agreement_1",
"blimp_regular_plural_subject_verb_agreement_2",
"blimp_sentential_negation_npi_licensor_present",
"blimp_sentential_negation_npi_scope",
"blimp_sentential_subject_island",
"blimp_superlative_quantifiers_1",
"blimp_superlative_quantifiers_2",
"blimp_tough_vs_raising_1",
"blimp_tough_vs_raising_2",
"blimp_transitive",
"blimp_wh_island",
"blimp_wh_questions_object_gap",
"blimp_wh_questions_subject_gap",
"blimp_wh_questions_subject_gap_long_distance",
"blimp_wh_vs_that_no_gap",
"blimp_wh_vs_that_no_gap_long_distance",
"blimp_wh_vs_that_with_gap",
"blimp_wh_vs_that_with_gap_long_distance"
]
},
"configs": {
"blimp_adjunct_island": {
"task": "blimp_adjunct_island",
"dataset_path": "blimp",
"dataset_name": "adjunct_island",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_anaphor_gender_agreement": {
"task": "blimp_anaphor_gender_agreement",
"dataset_path": "blimp",
"dataset_name": "anaphor_gender_agreement",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_anaphor_number_agreement": {
"task": "blimp_anaphor_number_agreement",
"dataset_path": "blimp",
"dataset_name": "anaphor_number_agreement",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_animate_subject_passive": {
"task": "blimp_animate_subject_passive",
"dataset_path": "blimp",
"dataset_name": "animate_subject_passive",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_animate_subject_trans": {
"task": "blimp_animate_subject_trans",
"dataset_path": "blimp",
"dataset_name": "animate_subject_trans",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_causative": {
"task": "blimp_causative",
"dataset_path": "blimp",
"dataset_name": "causative",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_complex_NP_island": {
"task": "blimp_complex_NP_island",
"dataset_path": "blimp",
"dataset_name": "complex_NP_island",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_coordinate_structure_constraint_complex_left_branch": {
"task": "blimp_coordinate_structure_constraint_complex_left_branch",
"dataset_path": "blimp",
"dataset_name": "coordinate_structure_constraint_complex_left_branch",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_coordinate_structure_constraint_object_extraction": {
"task": "blimp_coordinate_structure_constraint_object_extraction",
"dataset_path": "blimp",
"dataset_name": "coordinate_structure_constraint_object_extraction",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_determiner_noun_agreement_1": {
"task": "blimp_determiner_noun_agreement_1",
"dataset_path": "blimp",
"dataset_name": "determiner_noun_agreement_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_determiner_noun_agreement_2": {
"task": "blimp_determiner_noun_agreement_2",
"dataset_path": "blimp",
"dataset_name": "determiner_noun_agreement_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_determiner_noun_agreement_irregular_1": {
"task": "blimp_determiner_noun_agreement_irregular_1",
"dataset_path": "blimp",
"dataset_name": "determiner_noun_agreement_irregular_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_determiner_noun_agreement_irregular_2": {
"task": "blimp_determiner_noun_agreement_irregular_2",
"dataset_path": "blimp",
"dataset_name": "determiner_noun_agreement_irregular_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_determiner_noun_agreement_with_adj_2": {
"task": "blimp_determiner_noun_agreement_with_adj_2",
"dataset_path": "blimp",
"dataset_name": "determiner_noun_agreement_with_adj_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_determiner_noun_agreement_with_adj_irregular_1": {
"task": "blimp_determiner_noun_agreement_with_adj_irregular_1",
"dataset_path": "blimp",
"dataset_name": "determiner_noun_agreement_with_adj_irregular_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_determiner_noun_agreement_with_adj_irregular_2": {
"task": "blimp_determiner_noun_agreement_with_adj_irregular_2",
"dataset_path": "blimp",
"dataset_name": "determiner_noun_agreement_with_adj_irregular_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_determiner_noun_agreement_with_adjective_1": {
"task": "blimp_determiner_noun_agreement_with_adjective_1",
"dataset_path": "blimp",
"dataset_name": "determiner_noun_agreement_with_adjective_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_distractor_agreement_relational_noun": {
"task": "blimp_distractor_agreement_relational_noun",
"dataset_path": "blimp",
"dataset_name": "distractor_agreement_relational_noun",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_distractor_agreement_relative_clause": {
"task": "blimp_distractor_agreement_relative_clause",
"dataset_path": "blimp",
"dataset_name": "distractor_agreement_relative_clause",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_drop_argument": {
"task": "blimp_drop_argument",
"dataset_path": "blimp",
"dataset_name": "drop_argument",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_ellipsis_n_bar_1": {
"task": "blimp_ellipsis_n_bar_1",
"dataset_path": "blimp",
"dataset_name": "ellipsis_n_bar_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_ellipsis_n_bar_2": {
"task": "blimp_ellipsis_n_bar_2",
"dataset_path": "blimp",
"dataset_name": "ellipsis_n_bar_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_existential_there_object_raising": {
"task": "blimp_existential_there_object_raising",
"dataset_path": "blimp",
"dataset_name": "existential_there_object_raising",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_existential_there_quantifiers_1": {
"task": "blimp_existential_there_quantifiers_1",
"dataset_path": "blimp",
"dataset_name": "existential_there_quantifiers_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_existential_there_quantifiers_2": {
"task": "blimp_existential_there_quantifiers_2",
"dataset_path": "blimp",
"dataset_name": "existential_there_quantifiers_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_existential_there_subject_raising": {
"task": "blimp_existential_there_subject_raising",
"dataset_path": "blimp",
"dataset_name": "existential_there_subject_raising",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_expletive_it_object_raising": {
"task": "blimp_expletive_it_object_raising",
"dataset_path": "blimp",
"dataset_name": "expletive_it_object_raising",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_inchoative": {
"task": "blimp_inchoative",
"dataset_path": "blimp",
"dataset_name": "inchoative",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_intransitive": {
"task": "blimp_intransitive",
"dataset_path": "blimp",
"dataset_name": "intransitive",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_irregular_past_participle_adjectives": {
"task": "blimp_irregular_past_participle_adjectives",
"dataset_path": "blimp",
"dataset_name": "irregular_past_participle_adjectives",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_irregular_past_participle_verbs": {
"task": "blimp_irregular_past_participle_verbs",
"dataset_path": "blimp",
"dataset_name": "irregular_past_participle_verbs",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_irregular_plural_subject_verb_agreement_1": {
"task": "blimp_irregular_plural_subject_verb_agreement_1",
"dataset_path": "blimp",
"dataset_name": "irregular_plural_subject_verb_agreement_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_irregular_plural_subject_verb_agreement_2": {
"task": "blimp_irregular_plural_subject_verb_agreement_2",
"dataset_path": "blimp",
"dataset_name": "irregular_plural_subject_verb_agreement_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_left_branch_island_echo_question": {
"task": "blimp_left_branch_island_echo_question",
"dataset_path": "blimp",
"dataset_name": "left_branch_island_echo_question",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_left_branch_island_simple_question": {
"task": "blimp_left_branch_island_simple_question",
"dataset_path": "blimp",
"dataset_name": "left_branch_island_simple_question",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_matrix_question_npi_licensor_present": {
"task": "blimp_matrix_question_npi_licensor_present",
"dataset_path": "blimp",
"dataset_name": "matrix_question_npi_licensor_present",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_npi_present_1": {
"task": "blimp_npi_present_1",
"dataset_path": "blimp",
"dataset_name": "npi_present_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_npi_present_2": {
"task": "blimp_npi_present_2",
"dataset_path": "blimp",
"dataset_name": "npi_present_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_only_npi_licensor_present": {
"task": "blimp_only_npi_licensor_present",
"dataset_path": "blimp",
"dataset_name": "only_npi_licensor_present",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_only_npi_scope": {
"task": "blimp_only_npi_scope",
"dataset_path": "blimp",
"dataset_name": "only_npi_scope",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_passive_1": {
"task": "blimp_passive_1",
"dataset_path": "blimp",
"dataset_name": "passive_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_passive_2": {
"task": "blimp_passive_2",
"dataset_path": "blimp",
"dataset_name": "passive_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_principle_A_c_command": {
"task": "blimp_principle_A_c_command",
"dataset_path": "blimp",
"dataset_name": "principle_A_c_command",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_principle_A_case_1": {
"task": "blimp_principle_A_case_1",
"dataset_path": "blimp",
"dataset_name": "principle_A_case_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_principle_A_case_2": {
"task": "blimp_principle_A_case_2",
"dataset_path": "blimp",
"dataset_name": "principle_A_case_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_principle_A_domain_1": {
"task": "blimp_principle_A_domain_1",
"dataset_path": "blimp",
"dataset_name": "principle_A_domain_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_principle_A_domain_2": {
"task": "blimp_principle_A_domain_2",
"dataset_path": "blimp",
"dataset_name": "principle_A_domain_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_principle_A_domain_3": {
"task": "blimp_principle_A_domain_3",
"dataset_path": "blimp",
"dataset_name": "principle_A_domain_3",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_principle_A_reconstruction": {
"task": "blimp_principle_A_reconstruction",
"dataset_path": "blimp",
"dataset_name": "principle_A_reconstruction",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_regular_plural_subject_verb_agreement_1": {
"task": "blimp_regular_plural_subject_verb_agreement_1",
"dataset_path": "blimp",
"dataset_name": "regular_plural_subject_verb_agreement_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_regular_plural_subject_verb_agreement_2": {
"task": "blimp_regular_plural_subject_verb_agreement_2",
"dataset_path": "blimp",
"dataset_name": "regular_plural_subject_verb_agreement_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_sentential_negation_npi_licensor_present": {
"task": "blimp_sentential_negation_npi_licensor_present",
"dataset_path": "blimp",
"dataset_name": "sentential_negation_npi_licensor_present",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_sentential_negation_npi_scope": {
"task": "blimp_sentential_negation_npi_scope",
"dataset_path": "blimp",
"dataset_name": "sentential_negation_npi_scope",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_sentential_subject_island": {
"task": "blimp_sentential_subject_island",
"dataset_path": "blimp",
"dataset_name": "sentential_subject_island",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_superlative_quantifiers_1": {
"task": "blimp_superlative_quantifiers_1",
"dataset_path": "blimp",
"dataset_name": "superlative_quantifiers_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_superlative_quantifiers_2": {
"task": "blimp_superlative_quantifiers_2",
"dataset_path": "blimp",
"dataset_name": "superlative_quantifiers_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_tough_vs_raising_1": {
"task": "blimp_tough_vs_raising_1",
"dataset_path": "blimp",
"dataset_name": "tough_vs_raising_1",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_tough_vs_raising_2": {
"task": "blimp_tough_vs_raising_2",
"dataset_path": "blimp",
"dataset_name": "tough_vs_raising_2",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_transitive": {
"task": "blimp_transitive",
"dataset_path": "blimp",
"dataset_name": "transitive",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_wh_island": {
"task": "blimp_wh_island",
"dataset_path": "blimp",
"dataset_name": "wh_island",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_wh_questions_object_gap": {
"task": "blimp_wh_questions_object_gap",
"dataset_path": "blimp",
"dataset_name": "wh_questions_object_gap",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_wh_questions_subject_gap": {
"task": "blimp_wh_questions_subject_gap",
"dataset_path": "blimp",
"dataset_name": "wh_questions_subject_gap",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_wh_questions_subject_gap_long_distance": {
"task": "blimp_wh_questions_subject_gap_long_distance",
"dataset_path": "blimp",
"dataset_name": "wh_questions_subject_gap_long_distance",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_wh_vs_that_no_gap": {
"task": "blimp_wh_vs_that_no_gap",
"dataset_path": "blimp",
"dataset_name": "wh_vs_that_no_gap",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_wh_vs_that_no_gap_long_distance": {
"task": "blimp_wh_vs_that_no_gap_long_distance",
"dataset_path": "blimp",
"dataset_name": "wh_vs_that_no_gap_long_distance",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_wh_vs_that_with_gap": {
"task": "blimp_wh_vs_that_with_gap",
"dataset_path": "blimp",
"dataset_name": "wh_vs_that_with_gap",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
},
"blimp_wh_vs_that_with_gap_long_distance": {
"task": "blimp_wh_vs_that_with_gap_long_distance",
"dataset_path": "blimp",
"dataset_name": "wh_vs_that_with_gap_long_distance",
"validation_split": "train",
"doc_to_text": "",
"doc_to_target": 0,
"unsafe_code": false,
"doc_to_choice": "{{[sentence_good, sentence_bad]}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
"metadata": {
"version": 1.0
}
}
},
"versions": {
"blimp": 2.0,
"blimp_adjunct_island": 1.0,
"blimp_anaphor_gender_agreement": 1.0,
"blimp_anaphor_number_agreement": 1.0,
"blimp_animate_subject_passive": 1.0,
"blimp_animate_subject_trans": 1.0,
"blimp_causative": 1.0,
"blimp_complex_NP_island": 1.0,
"blimp_coordinate_structure_constraint_complex_left_branch": 1.0,
"blimp_coordinate_structure_constraint_object_extraction": 1.0,
"blimp_determiner_noun_agreement_1": 1.0,
"blimp_determiner_noun_agreement_2": 1.0,
"blimp_determiner_noun_agreement_irregular_1": 1.0,
"blimp_determiner_noun_agreement_irregular_2": 1.0,
"blimp_determiner_noun_agreement_with_adj_2": 1.0,
"blimp_determiner_noun_agreement_with_adj_irregular_1": 1.0,
"blimp_determiner_noun_agreement_with_adj_irregular_2": 1.0,
"blimp_determiner_noun_agreement_with_adjective_1": 1.0,
"blimp_distractor_agreement_relational_noun": 1.0,
"blimp_distractor_agreement_relative_clause": 1.0,
"blimp_drop_argument": 1.0,
"blimp_ellipsis_n_bar_1": 1.0,
"blimp_ellipsis_n_bar_2": 1.0,
"blimp_existential_there_object_raising": 1.0,
"blimp_existential_there_quantifiers_1": 1.0,
"blimp_existential_there_quantifiers_2": 1.0,
"blimp_existential_there_subject_raising": 1.0,
"blimp_expletive_it_object_raising": 1.0,
"blimp_inchoative": 1.0,
"blimp_intransitive": 1.0,
"blimp_irregular_past_participle_adjectives": 1.0,
"blimp_irregular_past_participle_verbs": 1.0,
"blimp_irregular_plural_subject_verb_agreement_1": 1.0,
"blimp_irregular_plural_subject_verb_agreement_2": 1.0,
"blimp_left_branch_island_echo_question": 1.0,
"blimp_left_branch_island_simple_question": 1.0,
"blimp_matrix_question_npi_licensor_present": 1.0,
"blimp_npi_present_1": 1.0,
"blimp_npi_present_2": 1.0,
"blimp_only_npi_licensor_present": 1.0,
"blimp_only_npi_scope": 1.0,
"blimp_passive_1": 1.0,
"blimp_passive_2": 1.0,
"blimp_principle_A_c_command": 1.0,
"blimp_principle_A_case_1": 1.0,
"blimp_principle_A_case_2": 1.0,
"blimp_principle_A_domain_1": 1.0,
"blimp_principle_A_domain_2": 1.0,
"blimp_principle_A_domain_3": 1.0,
"blimp_principle_A_reconstruction": 1.0,
"blimp_regular_plural_subject_verb_agreement_1": 1.0,
"blimp_regular_plural_subject_verb_agreement_2": 1.0,
"blimp_sentential_negation_npi_licensor_present": 1.0,
"blimp_sentential_negation_npi_scope": 1.0,
"blimp_sentential_subject_island": 1.0,
"blimp_superlative_quantifiers_1": 1.0,
"blimp_superlative_quantifiers_2": 1.0,
"blimp_tough_vs_raising_1": 1.0,
"blimp_tough_vs_raising_2": 1.0,
"blimp_transitive": 1.0,
"blimp_wh_island": 1.0,
"blimp_wh_questions_object_gap": 1.0,
"blimp_wh_questions_subject_gap": 1.0,
"blimp_wh_questions_subject_gap_long_distance": 1.0,
"blimp_wh_vs_that_no_gap": 1.0,
"blimp_wh_vs_that_no_gap_long_distance": 1.0,
"blimp_wh_vs_that_with_gap": 1.0,
"blimp_wh_vs_that_with_gap_long_distance": 1.0
},
"n-shot": {
"blimp_adjunct_island": 0,
"blimp_anaphor_gender_agreement": 0,
"blimp_anaphor_number_agreement": 0,
"blimp_animate_subject_passive": 0,
"blimp_animate_subject_trans": 0,
"blimp_causative": 0,
"blimp_complex_NP_island": 0,
"blimp_coordinate_structure_constraint_complex_left_branch": 0,
"blimp_coordinate_structure_constraint_object_extraction": 0,
"blimp_determiner_noun_agreement_1": 0,
"blimp_determiner_noun_agreement_2": 0,
"blimp_determiner_noun_agreement_irregular_1": 0,
"blimp_determiner_noun_agreement_irregular_2": 0,
"blimp_determiner_noun_agreement_with_adj_2": 0,
"blimp_determiner_noun_agreement_with_adj_irregular_1": 0,
"blimp_determiner_noun_agreement_with_adj_irregular_2": 0,
"blimp_determiner_noun_agreement_with_adjective_1": 0,
"blimp_distractor_agreement_relational_noun": 0,
"blimp_distractor_agreement_relative_clause": 0,
"blimp_drop_argument": 0,
"blimp_ellipsis_n_bar_1": 0,
"blimp_ellipsis_n_bar_2": 0,
"blimp_existential_there_object_raising": 0,
"blimp_existential_there_quantifiers_1": 0,
"blimp_existential_there_quantifiers_2": 0,
"blimp_existential_there_subject_raising": 0,
"blimp_expletive_it_object_raising": 0,
"blimp_inchoative": 0,
"blimp_intransitive": 0,
"blimp_irregular_past_participle_adjectives": 0,
"blimp_irregular_past_participle_verbs": 0,
"blimp_irregular_plural_subject_verb_agreement_1": 0,
"blimp_irregular_plural_subject_verb_agreement_2": 0,
"blimp_left_branch_island_echo_question": 0,
"blimp_left_branch_island_simple_question": 0,
"blimp_matrix_question_npi_licensor_present": 0,
"blimp_npi_present_1": 0,
"blimp_npi_present_2": 0,
"blimp_only_npi_licensor_present": 0,
"blimp_only_npi_scope": 0,
"blimp_passive_1": 0,
"blimp_passive_2": 0,
"blimp_principle_A_c_command": 0,
"blimp_principle_A_case_1": 0,
"blimp_principle_A_case_2": 0,
"blimp_principle_A_domain_1": 0,
"blimp_principle_A_domain_2": 0,
"blimp_principle_A_domain_3": 0,
"blimp_principle_A_reconstruction": 0,
"blimp_regular_plural_subject_verb_agreement_1": 0,
"blimp_regular_plural_subject_verb_agreement_2": 0,
"blimp_sentential_negation_npi_licensor_present": 0,
"blimp_sentential_negation_npi_scope": 0,
"blimp_sentential_subject_island": 0,
"blimp_superlative_quantifiers_1": 0,
"blimp_superlative_quantifiers_2": 0,
"blimp_tough_vs_raising_1": 0,
"blimp_tough_vs_raising_2": 0,
"blimp_transitive": 0,
"blimp_wh_island": 0,
"blimp_wh_questions_object_gap": 0,
"blimp_wh_questions_subject_gap": 0,
"blimp_wh_questions_subject_gap_long_distance": 0,
"blimp_wh_vs_that_no_gap": 0,
"blimp_wh_vs_that_no_gap_long_distance": 0,
"blimp_wh_vs_that_with_gap": 0,
"blimp_wh_vs_that_with_gap_long_distance": 0
},
"higher_is_better": {
"blimp": {
"acc": true
},
"blimp_adjunct_island": {
"acc": true
},
"blimp_anaphor_gender_agreement": {
"acc": true
},
"blimp_anaphor_number_agreement": {
"acc": true
},
"blimp_animate_subject_passive": {
"acc": true
},
"blimp_animate_subject_trans": {
"acc": true
},
"blimp_causative": {
"acc": true
},
"blimp_complex_NP_island": {
"acc": true
},
"blimp_coordinate_structure_constraint_complex_left_branch": {
"acc": true
},
"blimp_coordinate_structure_constraint_object_extraction": {
"acc": true
},
"blimp_determiner_noun_agreement_1": {
"acc": true
},
"blimp_determiner_noun_agreement_2": {
"acc": true
},
"blimp_determiner_noun_agreement_irregular_1": {
"acc": true
},
"blimp_determiner_noun_agreement_irregular_2": {
"acc": true
},
"blimp_determiner_noun_agreement_with_adj_2": {
"acc": true
},
"blimp_determiner_noun_agreement_with_adj_irregular_1": {
"acc": true
},
"blimp_determiner_noun_agreement_with_adj_irregular_2": {
"acc": true
},
"blimp_determiner_noun_agreement_with_adjective_1": {
"acc": true
},
"blimp_distractor_agreement_relational_noun": {
"acc": true
},
"blimp_distractor_agreement_relative_clause": {
"acc": true
},
"blimp_drop_argument": {
"acc": true
},
"blimp_ellipsis_n_bar_1": {
"acc": true
},
"blimp_ellipsis_n_bar_2": {
"acc": true
},
"blimp_existential_there_object_raising": {
"acc": true
},
"blimp_existential_there_quantifiers_1": {
"acc": true
},
"blimp_existential_there_quantifiers_2": {
"acc": true
},
"blimp_existential_there_subject_raising": {
"acc": true
},
"blimp_expletive_it_object_raising": {
"acc": true
},
"blimp_inchoative": {
"acc": true
},
"blimp_intransitive": {
"acc": true
},
"blimp_irregular_past_participle_adjectives": {
"acc": true
},
"blimp_irregular_past_participle_verbs": {
"acc": true
},
"blimp_irregular_plural_subject_verb_agreement_1": {
"acc": true
},
"blimp_irregular_plural_subject_verb_agreement_2": {
"acc": true
},
"blimp_left_branch_island_echo_question": {
"acc": true
},
"blimp_left_branch_island_simple_question": {
"acc": true
},
"blimp_matrix_question_npi_licensor_present": {
"acc": true
},
"blimp_npi_present_1": {
"acc": true
},
"blimp_npi_present_2": {
"acc": true
},
"blimp_only_npi_licensor_present": {
"acc": true
},
"blimp_only_npi_scope": {
"acc": true
},
"blimp_passive_1": {
"acc": true
},
"blimp_passive_2": {
"acc": true
},
"blimp_principle_A_c_command": {
"acc": true
},
"blimp_principle_A_case_1": {
"acc": true
},
"blimp_principle_A_case_2": {
"acc": true
},
"blimp_principle_A_domain_1": {
"acc": true
},
"blimp_principle_A_domain_2": {
"acc": true
},
"blimp_principle_A_domain_3": {
"acc": true
},
"blimp_principle_A_reconstruction": {
"acc": true
},
"blimp_regular_plural_subject_verb_agreement_1": {
"acc": true
},
"blimp_regular_plural_subject_verb_agreement_2": {
"acc": true
},
"blimp_sentential_negation_npi_licensor_present": {
"acc": true
},
"blimp_sentential_negation_npi_scope": {
"acc": true
},
"blimp_sentential_subject_island": {
"acc": true
},
"blimp_superlative_quantifiers_1": {
"acc": true
},
"blimp_superlative_quantifiers_2": {
"acc": true
},
"blimp_tough_vs_raising_1": {
"acc": true
},
"blimp_tough_vs_raising_2": {
"acc": true
},
"blimp_transitive": {
"acc": true
},
"blimp_wh_island": {
"acc": true
},
"blimp_wh_questions_object_gap": {
"acc": true
},
"blimp_wh_questions_subject_gap": {
"acc": true
},
"blimp_wh_questions_subject_gap_long_distance": {
"acc": true
},
"blimp_wh_vs_that_no_gap": {
"acc": true
},
"blimp_wh_vs_that_no_gap_long_distance": {
"acc": true
},
"blimp_wh_vs_that_with_gap": {
"acc": true
},
"blimp_wh_vs_that_with_gap_long_distance": {
"acc": true
}
},
"n-samples": {
"blimp_adjunct_island": {
"original": 1000,
"effective": 1000
},
"blimp_anaphor_gender_agreement": {
"original": 1000,
"effective": 1000
},
"blimp_anaphor_number_agreement": {
"original": 1000,
"effective": 1000
},
"blimp_animate_subject_passive": {
"original": 1000,
"effective": 1000
},
"blimp_animate_subject_trans": {
"original": 1000,
"effective": 1000
},
"blimp_causative": {
"original": 1000,
"effective": 1000
},
"blimp_complex_NP_island": {
"original": 1000,
"effective": 1000
},
"blimp_coordinate_structure_constraint_complex_left_branch": {
"original": 1000,
"effective": 1000
},
"blimp_coordinate_structure_constraint_object_extraction": {
"original": 1000,
"effective": 1000
},
"blimp_determiner_noun_agreement_1": {
"original": 1000,
"effective": 1000
},
"blimp_determiner_noun_agreement_2": {
"original": 1000,
"effective": 1000
},
"blimp_determiner_noun_agreement_irregular_1": {
"original": 1000,
"effective": 1000
},
"blimp_determiner_noun_agreement_irregular_2": {
"original": 1000,
"effective": 1000
},
"blimp_determiner_noun_agreement_with_adj_2": {
"original": 1000,
"effective": 1000
},
"blimp_determiner_noun_agreement_with_adj_irregular_1": {
"original": 1000,
"effective": 1000
},
"blimp_determiner_noun_agreement_with_adj_irregular_2": {
"original": 1000,
"effective": 1000
},
"blimp_determiner_noun_agreement_with_adjective_1": {
"original": 1000,
"effective": 1000
},
"blimp_distractor_agreement_relational_noun": {
"original": 1000,
"effective": 1000
},
"blimp_distractor_agreement_relative_clause": {
"original": 1000,
"effective": 1000
},
"blimp_drop_argument": {
"original": 1000,
"effective": 1000
},
"blimp_ellipsis_n_bar_1": {
"original": 1000,
"effective": 1000
},
"blimp_ellipsis_n_bar_2": {
"original": 1000,
"effective": 1000
},
"blimp_existential_there_object_raising": {
"original": 1000,
"effective": 1000
},
"blimp_existential_there_quantifiers_1": {
"original": 1000,
"effective": 1000
},
"blimp_existential_there_quantifiers_2": {
"original": 1000,
"effective": 1000
},
"blimp_existential_there_subject_raising": {
"original": 1000,
"effective": 1000
},
"blimp_expletive_it_object_raising": {
"original": 1000,
"effective": 1000
},
"blimp_inchoative": {
"original": 1000,
"effective": 1000
},
"blimp_intransitive": {
"original": 1000,
"effective": 1000
},
"blimp_irregular_past_participle_adjectives": {
"original": 1000,
"effective": 1000
},
"blimp_irregular_past_participle_verbs": {
"original": 1000,
"effective": 1000
},
"blimp_irregular_plural_subject_verb_agreement_1": {
"original": 1000,
"effective": 1000
},
"blimp_irregular_plural_subject_verb_agreement_2": {
"original": 1000,
"effective": 1000
},
"blimp_left_branch_island_echo_question": {
"original": 1000,
"effective": 1000
},
"blimp_left_branch_island_simple_question": {
"original": 1000,
"effective": 1000
},
"blimp_matrix_question_npi_licensor_present": {
"original": 1000,
"effective": 1000
},
"blimp_npi_present_1": {
"original": 1000,
"effective": 1000
},
"blimp_npi_present_2": {
"original": 1000,
"effective": 1000
},
"blimp_only_npi_licensor_present": {
"original": 1000,
"effective": 1000
},
"blimp_only_npi_scope": {
"original": 1000,
"effective": 1000
},
"blimp_passive_1": {
"original": 1000,
"effective": 1000
},
"blimp_passive_2": {
"original": 1000,
"effective": 1000
},
"blimp_principle_A_c_command": {
"original": 1000,
"effective": 1000
},
"blimp_principle_A_case_1": {
"original": 1000,
"effective": 1000
},
"blimp_principle_A_case_2": {
"original": 1000,
"effective": 1000
},
"blimp_principle_A_domain_1": {
"original": 1000,
"effective": 1000
},
"blimp_principle_A_domain_2": {
"original": 1000,
"effective": 1000
},
"blimp_principle_A_domain_3": {
"original": 1000,
"effective": 1000
},
"blimp_principle_A_reconstruction": {
"original": 1000,
"effective": 1000
},
"blimp_regular_plural_subject_verb_agreement_1": {
"original": 1000,
"effective": 1000
},
"blimp_regular_plural_subject_verb_agreement_2": {
"original": 1000,
"effective": 1000
},
"blimp_sentential_negation_npi_licensor_present": {
"original": 1000,
"effective": 1000
},
"blimp_sentential_negation_npi_scope": {
"original": 1000,
"effective": 1000
},
"blimp_sentential_subject_island": {
"original": 1000,
"effective": 1000
},
"blimp_superlative_quantifiers_1": {
"original": 1000,
"effective": 1000
},
"blimp_superlative_quantifiers_2": {
"original": 1000,
"effective": 1000
},
"blimp_tough_vs_raising_1": {
"original": 1000,
"effective": 1000
},
"blimp_tough_vs_raising_2": {
"original": 1000,
"effective": 1000
},
"blimp_transitive": {
"original": 1000,
"effective": 1000
},
"blimp_wh_island": {
"original": 1000,
"effective": 1000
},
"blimp_wh_questions_object_gap": {
"original": 1000,
"effective": 1000
},
"blimp_wh_questions_subject_gap": {
"original": 1000,
"effective": 1000
},
"blimp_wh_questions_subject_gap_long_distance": {
"original": 1000,
"effective": 1000
},
"blimp_wh_vs_that_no_gap": {
"original": 1000,
"effective": 1000
},
"blimp_wh_vs_that_no_gap_long_distance": {
"original": 1000,
"effective": 1000
},
"blimp_wh_vs_that_with_gap": {
"original": 1000,
"effective": 1000
},
"blimp_wh_vs_that_with_gap_long_distance": {
"original": 1000,
"effective": 1000
}
},
"config": {
"model": "hf",
"model_args": "pretrained=outputs/fw57M-tied/42/fw57M_Surprisal_bytespanP1-0T30_64000/.cache/eval_model",
"model_num_parameters": 105785088,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "",
"batch_size": 1,
"batch_sizes": [],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "778f288",
"date": 1749638040.021471,
"pretty_env_info": "'NoneType' object has no attribute 'splitlines'",
"transformers_version": "4.52.4",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<|padding|>",
"0"
],
"tokenizer_eos_token": [
"<|endoftext|>",
"1"
],
"tokenizer_bos_token": [
"<|endoftext|>",
"1"
],
"eot_token_id": 1,
"max_length": 2048,
"task_hashes": {},
"model_source": "hf",
"model_name": "outputs/fw57M-tied/42/fw57M_Surprisal_bytespanP1-0T30_64000/.cache/eval_model",
"model_name_sanitized": "outputs__fw57M-tied__42__fw57M_Surprisal_bytespanP1-0T30_64000__.cache__eval_model",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 211176.158305025,
"end_time": 212750.291630051,
"total_evaluation_time_seconds": "1574.1333250260213"
}