├── evaluation-harness ├── lm_eval │ ├── __init__.py │ ├── datasets │ │ ├── __init__.py │ │ ├── asdiv │ │ │ └── __init__.py │ │ ├── coqa │ │ │ └── __init__.py │ │ ├── drop │ │ │ └── __init__.py │ │ ├── pile │ │ │ └── __init__.py │ │ ├── quac │ │ │ └── __init__.py │ │ ├── headqa │ │ │ └── __init__.py │ │ ├── logiqa │ │ │ └── __init__.py │ │ ├── mutual │ │ │ └── __init__.py │ │ ├── unscramble │ │ │ └── __init__.py │ │ ├── hendrycks_math │ │ │ └── __init__.py │ │ ├── sat_analogies │ │ │ └── __init__.py │ │ ├── bigbench_resources │ │ │ └── __init__.py │ │ └── hendrycks_ethics │ │ │ └── __init__.py │ └── decontamination │ │ └── __init__.py ├── scripts │ ├── __init__.py │ └── clean_training_data │ │ └── __init__.py ├── requirements.txt ├── CODEOWNERS ├── ignore.txt ├── tests │ └── testdata │ │ ├── cb-v0-loglikelihood │ │ ├── cb-v1-loglikelihood │ │ ├── coqa-v0-greedy_until │ │ ├── coqa-v1-greedy_until │ │ ├── drop-v0-greedy_until │ │ ├── drop-v1-greedy_until │ │ ├── qqp-v0-loglikelihood │ │ ├── rte-v0-loglikelihood │ │ ├── sst-v0-loglikelihood │ │ ├── wic-v0-loglikelihood │ │ ├── wsc-v0-loglikelihood │ │ ├── anagrams1-v0-greedy_until │ │ ├── anagrams2-v0-greedy_until │ │ ├── anli_r1-v0-loglikelihood │ │ ├── anli_r2-v0-loglikelihood │ │ ├── anli_r3-v0-loglikelihood │ │ ├── arc_easy-v0-loglikelihood │ │ ├── boolq-v0-loglikelihood │ │ ├── boolq-v1-loglikelihood │ │ ├── cola-v0-loglikelihood │ │ ├── copa-v0-loglikelihood │ │ ├── gsm8k-v0-greedy_until │ │ ├── headqa-v0-loglikelihood │ │ ├── lambada-v0-loglikelihood │ │ ├── logiqa-v0-loglikelihood │ │ ├── mathqa-v0-loglikelihood │ │ ├── mc_taco-v0-loglikelihood │ │ ├── mnli-v0-loglikelihood │ │ ├── mrpc-v0-loglikelihood │ │ ├── multirc-v0-loglikelihood │ │ ├── multirc-v1-loglikelihood │ │ ├── mutual-v0-loglikelihood │ │ ├── mutual-v1-loglikelihood │ │ ├── piqa-v0-loglikelihood │ │ ├── prost-v0-loglikelihood │ │ ├── pubmedqa-v0-loglikelihood │ │ ├── qnli-v0-loglikelihood │ │ ├── race-v0-loglikelihood │ │ ├── record-v0-loglikelihood │ │ ├── sciq-v0-loglikelihood │ │ ├── squad2-v0-greedy_until │ │ ├── squad2-v0-loglikelihood │ │ ├── squad2-v1-greedy_until │ │ ├── squad2-v1-loglikelihood │ │ ├── swag-v0-loglikelihood │ │ ├── toxigen-v0-loglikelihood │ │ ├── triviaqa-v0-loglikelihood │ │ ├── triviaqa-v1-loglikelihood │ │ ├── webqs-v0-loglikelihood │ │ ├── wnli-v0-loglikelihood │ │ ├── wnli-v1-loglikelihood │ │ ├── wsc273-v0-loglikelihood │ │ ├── arc_challenge-v0-loglikelihood │ │ ├── cycle_letters-v0-greedy_until │ │ ├── ethics_cm-v0-loglikelihood │ │ ├── ethics_virtue-v0-loglikelihood │ │ ├── headqa_en-v0-loglikelihood │ │ ├── headqa_es-v0-loglikelihood │ │ ├── hellaswag-v0-loglikelihood │ │ ├── iwslt17-ar-en-v0-greedy_until │ │ ├── iwslt17-en-ar-v0-greedy_until │ │ ├── lambada_cloze-v0-loglikelihood │ │ ├── lambada_mt_de-v0-loglikelihood │ │ ├── lambada_mt_en-v0-loglikelihood │ │ ├── lambada_mt_es-v0-loglikelihood │ │ ├── lambada_mt_fr-v0-loglikelihood │ │ ├── lambada_mt_it-v0-loglikelihood │ │ ├── math_algebra-v0-greedy_until │ │ ├── math_algebra-v1-greedy_until │ │ ├── math_geometry-v0-greedy_until │ │ ├── math_geometry-v1-greedy_until │ │ ├── math_precalc-v0-greedy_until │ │ ├── math_precalc-v1-greedy_until │ │ ├── mutual_plus-v0-loglikelihood │ │ ├── mutual_plus-v1-loglikelihood │ │ ├── openbookqa-v0-loglikelihood │ │ ├── qa4mre_2011-v0-loglikelihood │ │ ├── qa4mre_2012-v0-loglikelihood │ │ ├── qa4mre_2013-v0-loglikelihood │ │ ├── reversed_words-v0-greedy_until │ │ ├── truthfulqa_gen-v0-greedy_until │ │ ├── truthfulqa_gen-v1-greedy_until │ │ ├── truthfulqa_mc-v0-loglikelihood │ │ ├── truthfulqa_mc-v1-loglikelihood │ │ ├── winogrande-v0-loglikelihood │ │ ├── wmt14-en-fr-v0-greedy_until │ │ ├── wmt14-fr-en-v0-greedy_until │ │ ├── wmt16-de-en-v0-greedy_until │ │ ├── wmt16-en-de-v0-greedy_until │ │ ├── wmt16-en-ro-v0-greedy_until │ │ ├── wmt16-ro-en-v0-greedy_until │ │ ├── wmt20-cs-en-v0-greedy_until │ │ ├── wmt20-de-en-v0-greedy_until │ │ ├── wmt20-de-fr-v0-greedy_until │ │ ├── wmt20-en-cs-v0-greedy_until │ │ ├── wmt20-en-de-v0-greedy_until │ │ ├── wmt20-en-iu-v0-greedy_until │ │ ├── wmt20-en-ja-v0-greedy_until │ │ ├── wmt20-en-ja-v1-greedy_until │ │ ├── wmt20-en-km-v0-greedy_until │ │ ├── wmt20-en-pl-v0-greedy_until │ │ ├── wmt20-en-ps-v0-greedy_until │ │ ├── wmt20-en-ru-v0-greedy_until │ │ ├── wmt20-en-ta-v0-greedy_until │ │ ├── wmt20-en-zh-v0-greedy_until │ │ ├── wmt20-en-zh-v1-greedy_until │ │ ├── wmt20-fr-de-v0-greedy_until │ │ ├── wmt20-iu-en-v0-greedy_until │ │ ├── wmt20-ja-en-v0-greedy_until │ │ ├── wmt20-km-en-v0-greedy_until │ │ ├── wmt20-pl-en-v0-greedy_until │ │ ├── wmt20-ps-en-v0-greedy_until │ │ ├── wmt20-ru-en-v0-greedy_until │ │ ├── wmt20-ta-en-v0-greedy_until │ │ ├── wmt20-zh-en-v0-greedy_until │ │ ├── arithmetic_1dc-v0-loglikelihood │ │ ├── arithmetic_2da-v0-loglikelihood │ │ ├── arithmetic_2dm-v0-loglikelihood │ │ ├── arithmetic_2ds-v0-loglikelihood │ │ ├── arithmetic_3da-v0-loglikelihood │ │ ├── arithmetic_3ds-v0-loglikelihood │ │ ├── arithmetic_4da-v0-loglikelihood │ │ ├── arithmetic_4ds-v0-loglikelihood │ │ ├── arithmetic_5da-v0-loglikelihood │ │ ├── arithmetic_5ds-v0-loglikelihood │ │ ├── blimp_causative-v0-loglikelihood │ │ ├── blimp_inchoative-v0-loglikelihood │ │ ├── blimp_intransitive-v0-loglikelihood │ │ ├── blimp_passive_1-v0-loglikelihood │ │ ├── blimp_passive_2-v0-loglikelihood │ │ ├── blimp_transitive-v0-loglikelihood │ │ ├── blimp_wh_island-v0-loglikelihood │ │ ├── crows_pairs_french-v0-loglikelihood │ │ ├── ethics_deontology-v0-loglikelihood │ │ ├── ethics_justice-v0-loglikelihood │ │ ├── gsm8k-v0-res.json │ │ ├── lambada_openai-v0-loglikelihood │ │ ├── lambada_standard-v0-loglikelihood │ │ ├── math_num_theory-v0-greedy_until │ │ ├── math_num_theory-v1-greedy_until │ │ ├── math_prealgebra-v0-greedy_until │ │ ├── math_prealgebra-v1-greedy_until │ │ ├── mnli_mismatched-v0-loglikelihood │ │ ├── pile_arxiv-v0-loglikelihood_rolling │ │ ├── pile_arxiv-v1-loglikelihood_rolling │ │ ├── pile_enron-v0-loglikelihood_rolling │ │ ├── pile_enron-v1-loglikelihood_rolling │ │ ├── pile_uspto-v0-loglikelihood_rolling │ │ ├── pile_uspto-v1-loglikelihood_rolling │ │ ├── random_insertion-v0-greedy_until │ │ ├── webqs-v0-res.json │ │ ├── wikitext-v0-loglikelihood_rolling │ │ ├── wikitext-v1-loglikelihood_rolling │ │ ├── blimp_adjunct_island-v0-loglikelihood │ │ ├── blimp_complex_NP_island-v0-loglikelihood │ │ ├── blimp_drop_argument-v0-loglikelihood │ │ ├── blimp_ellipsis_n_bar_1-v0-loglikelihood │ │ ├── blimp_ellipsis_n_bar_2-v0-loglikelihood │ │ ├── blimp_npi_present_1-v0-loglikelihood │ │ ├── blimp_npi_present_2-v0-loglikelihood │ │ ├── blimp_only_npi_scope-v0-loglikelihood │ │ ├── blimp_wh_vs_that_no_gap-v0-loglikelihood │ │ ├── crows_pairs_english-v0-loglikelihood │ │ ├── crows_pairs_english_age-v0-loglikelihood │ │ ├── crows_pairs_french_age-v0-loglikelihood │ │ ├── ethics_utilitarianism-v0-loglikelihood │ │ ├── hendrycksTest-anatomy-v0-loglikelihood │ │ ├── hendrycksTest-astronomy-v0-loglikelihood │ │ ├── hendrycksTest-marketing-v0-loglikelihood │ │ ├── hendrycksTest-nutrition-v0-loglikelihood │ │ ├── hendrycksTest-sociology-v0-loglikelihood │ │ ├── hendrycksTest-virology-v0-loglikelihood │ │ ├── lambada_openai_cloze-v0-loglikelihood │ │ ├── lambada_openai_mt_de-v0-loglikelihood │ │ ├── lambada_openai_mt_en-v0-loglikelihood │ │ ├── lambada_openai_mt_es-v0-loglikelihood │ │ ├── lambada_openai_mt_fr-v0-loglikelihood │ │ ├── lambada_openai_mt_it-v0-loglikelihood │ │ ├── lambada_standard_cloze-v0-loglikelihood │ │ ├── math_counting_and_prob-v0-greedy_until │ │ ├── math_counting_and_prob-v1-greedy_until │ │ ├── pile_books3-v0-loglikelihood_rolling │ │ ├── pile_books3-v1-loglikelihood_rolling │ │ ├── pile_europarl-v0-loglikelihood_rolling │ │ ├── pile_europarl-v1-loglikelihood_rolling │ │ ├── pile_freelaw-v0-loglikelihood_rolling │ │ ├── pile_freelaw-v1-loglikelihood_rolling │ │ ├── pile_github-v0-loglikelihood_rolling │ │ ├── pile_github-v1-loglikelihood_rolling │ │ ├── pile_gutenberg-v0-loglikelihood_rolling │ │ ├── pile_gutenberg-v1-loglikelihood_rolling │ │ ├── pile_hackernews-v0-loglikelihood_rolling │ │ ├── pile_hackernews-v1-loglikelihood_rolling │ │ ├── pile_philpapers-v0-loglikelihood_rolling │ │ ├── pile_philpapers-v1-loglikelihood_rolling │ │ ├── pile_pile-cc-v0-loglikelihood_rolling │ │ ├── pile_pile-cc-v1-loglikelihood_rolling │ │ ├── pile_ubuntu-irc-v0-loglikelihood_rolling │ │ ├── pile_ubuntu-irc-v1-loglikelihood_rolling │ │ ├── pile_wikipedia-v0-loglikelihood_rolling │ │ ├── pile_wikipedia-v1-loglikelihood_rolling │ │ ├── blimp_animate_subject_trans-v0-loglikelihood │ │ ├── blimp_principle_A_c_command-v0-loglikelihood │ │ ├── blimp_principle_A_case_1-v0-loglikelihood │ │ ├── blimp_principle_A_case_2-v0-loglikelihood │ │ ├── blimp_principle_A_domain_1-v0-loglikelihood │ │ ├── blimp_principle_A_domain_2-v0-loglikelihood │ │ ├── blimp_principle_A_domain_3-v0-loglikelihood │ │ ├── blimp_tough_vs_raising_1-v0-loglikelihood │ │ ├── blimp_tough_vs_raising_2-v0-loglikelihood │ │ ├── blimp_wh_vs_that_with_gap-v0-loglikelihood │ │ ├── crows_pairs_english_autre-v0-loglikelihood │ │ ├── crows_pairs_english_gender-v0-loglikelihood │ │ ├── crows_pairs_english_religion-v0-loglikelihood │ │ ├── crows_pairs_french_autre-v0-loglikelihood │ │ ├── crows_pairs_french_gender-v0-loglikelihood │ │ ├── crows_pairs_french_religion-v0-loglikelihood │ │ ├── hendrycksTest-econometrics-v0-loglikelihood │ │ ├── hendrycksTest-formal_logic-v0-loglikelihood │ │ ├── hendrycksTest-global_facts-v0-loglikelihood │ │ ├── hendrycksTest-human_aging-v0-loglikelihood │ │ ├── hendrycksTest-jurisprudence-v0-loglikelihood │ │ ├── hendrycksTest-management-v0-loglikelihood │ │ ├── hendrycksTest-miscellaneous-v0-loglikelihood │ │ ├── hendrycksTest-moral_disputes-v0-loglikelihood │ │ ├── hendrycksTest-philosophy-v0-loglikelihood │ │ ├── hendrycksTest-prehistory-v0-loglikelihood │ │ ├── math_intermediate_algebra-v0-greedy_until │ │ ├── math_intermediate_algebra-v1-greedy_until │ │ ├── pile_bookcorpus2-v0-loglikelihood_rolling │ │ ├── pile_bookcorpus2-v1-loglikelihood_rolling │ │ ├── pile_dm-mathematics-v0-loglikelihood_rolling │ │ ├── pile_dm-mathematics-v1-loglikelihood_rolling │ │ ├── pile_nih-exporter-v0-loglikelihood_rolling │ │ ├── pile_nih-exporter-v1-loglikelihood_rolling │ │ ├── pile_opensubtitles-v0-loglikelihood_rolling │ │ ├── pile_opensubtitles-v1-loglikelihood_rolling │ │ ├── pile_openwebtext2-v0-loglikelihood_rolling │ │ ├── pile_openwebtext2-v1-loglikelihood_rolling │ │ ├── pile_pubmed-central-v0-loglikelihood_rolling │ │ ├── pile_pubmed-central-v1-loglikelihood_rolling │ │ ├── pile_stackexchange-v0-loglikelihood_rolling │ │ ├── pile_stackexchange-v1-loglikelihood_rolling │ │ ├── triviaqa-v0-res.json │ │ ├── triviaqa-v1-res.json │ │ ├── anagrams1-v0-res.json │ │ ├── anagrams2-v0-res.json │ │ ├── blimp_anaphor_gender_agreement-v0-loglikelihood │ │ ├── blimp_anaphor_number_agreement-v0-loglikelihood │ │ ├── blimp_animate_subject_passive-v0-loglikelihood │ │ ├── blimp_determiner_noun_agreement_1-v0-loglikelihood │ │ ├── blimp_determiner_noun_agreement_2-v0-loglikelihood │ │ ├── blimp_expletive_it_object_raising-v0-loglikelihood │ │ ├── blimp_only_npi_licensor_present-v0-loglikelihood │ │ ├── blimp_principle_A_reconstruction-v0-loglikelihood │ │ ├── blimp_sentential_subject_island-v0-loglikelihood │ │ ├── blimp_superlative_quantifiers_1-v0-loglikelihood │ │ ├── blimp_superlative_quantifiers_2-v0-loglikelihood │ │ ├── blimp_wh_questions_object_gap-v0-loglikelihood │ │ ├── blimp_wh_questions_subject_gap-v0-loglikelihood │ │ ├── copa-v0-res.json │ │ ├── crows_pairs_english_disability-v0-loglikelihood │ │ ├── crows_pairs_english_nationality-v0-loglikelihood │ │ ├── crows_pairs_english_race_color-v0-loglikelihood │ │ ├── crows_pairs_english_socioeconomic-v0-loglikelihood │ │ ├── crows_pairs_french_disability-v0-loglikelihood │ │ ├── crows_pairs_french_nationality-v0-loglikelihood │ │ ├── crows_pairs_french_race_color-v0-loglikelihood │ │ ├── crows_pairs_french_socioeconomic-v0-loglikelihood │ │ ├── ethics_utilitarianism_original-v0-loglikelihood │ │ ├── hendrycksTest-abstract_algebra-v0-loglikelihood │ │ ├── hendrycksTest-business_ethics-v0-loglikelihood │ │ ├── hendrycksTest-clinical_knowledge-v0-loglikelihood │ │ ├── hendrycksTest-college_biology-v0-loglikelihood │ │ ├── hendrycksTest-college_chemistry-v0-loglikelihood │ │ ├── hendrycksTest-college_mathematics-v0-loglikelihood │ │ ├── hendrycksTest-college_medicine-v0-loglikelihood │ │ ├── hendrycksTest-college_physics-v0-loglikelihood │ │ ├── hendrycksTest-computer_security-v0-loglikelihood │ │ ├── hendrycksTest-conceptual_physics-v0-loglikelihood │ │ ├── hendrycksTest-high_school_biology-v0-loglikelihood │ │ ├── hendrycksTest-high_school_physics-v0-loglikelihood │ │ ├── hendrycksTest-human_sexuality-v0-loglikelihood │ │ ├── hendrycksTest-international_law-v0-loglikelihood │ │ ├── hendrycksTest-logical_fallacies-v0-loglikelihood │ │ ├── hendrycksTest-machine_learning-v0-loglikelihood │ │ ├── hendrycksTest-medical_genetics-v0-loglikelihood │ │ ├── hendrycksTest-moral_scenarios-v0-loglikelihood │ │ ├── hendrycksTest-professional_law-v0-loglikelihood │ │ ├── hendrycksTest-public_relations-v0-loglikelihood │ │ ├── hendrycksTest-security_studies-v0-loglikelihood │ │ ├── hendrycksTest-us_foreign_policy-v0-loglikelihood │ │ ├── hendrycksTest-world_religions-v0-loglikelihood │ │ ├── pile_pubmed-abstracts-v0-loglikelihood_rolling │ │ ├── pile_pubmed-abstracts-v1-loglikelihood_rolling │ │ ├── pile_youtubesubtitles-v0-loglikelihood_rolling │ │ ├── pile_youtubesubtitles-v1-loglikelihood_rolling │ │ ├── blimp_existential_there_object_raising-v0-loglikelihood │ │ ├── blimp_existential_there_quantifiers_1-v0-loglikelihood │ │ ├── blimp_existential_there_quantifiers_2-v0-loglikelihood │ │ ├── blimp_irregular_past_participle_verbs-v0-loglikelihood │ │ ├── blimp_left_branch_island_echo_question-v0-loglikelihood │ │ ├── blimp_sentential_negation_npi_scope-v0-loglikelihood │ │ ├── blimp_wh_vs_that_no_gap_long_distance-v0-loglikelihood │ │ ├── crows_pairs_english_sexual_orientation-v0-loglikelihood │ │ ├── crows_pairs_french_physical_appearance-v0-loglikelihood │ │ ├── crows_pairs_french_sexual_orientation-v0-loglikelihood │ │ ├── hendrycksTest-college_computer_science-v0-loglikelihood │ │ ├── hendrycksTest-electrical_engineering-v0-loglikelihood │ │ ├── hendrycksTest-elementary_mathematics-v0-loglikelihood │ │ ├── hendrycksTest-high_school_chemistry-v0-loglikelihood │ │ ├── hendrycksTest-high_school_geography-v0-loglikelihood │ │ ├── hendrycksTest-high_school_mathematics-v0-loglikelihood │ │ ├── hendrycksTest-high_school_psychology-v0-loglikelihood │ │ ├── hendrycksTest-high_school_statistics-v0-loglikelihood │ │ ├── hendrycksTest-high_school_us_history-v0-loglikelihood │ │ ├── hendrycksTest-professional_accounting-v0-loglikelihood │ │ ├── hendrycksTest-professional_medicine-v0-loglikelihood │ │ ├── hendrycksTest-professional_psychology-v0-loglikelihood │ │ ├── math_algebra-v0-res.json │ │ ├── math_algebra-v1-res.json │ │ ├── math_precalc-v0-res.json │ │ ├── math_precalc-v1-res.json │ │ ├── anli_r1-v0-res.json │ │ ├── anli_r2-v0-res.json │ │ ├── blimp_determiner_noun_agreement_irregular_1-v0-loglikelihood │ │ ├── blimp_determiner_noun_agreement_irregular_2-v0-loglikelihood │ │ ├── blimp_determiner_noun_agreement_with_adj_2-v0-loglikelihood │ │ ├── blimp_distractor_agreement_relational_noun-v0-loglikelihood │ │ ├── blimp_distractor_agreement_relative_clause-v0-loglikelihood │ │ ├── blimp_existential_there_subject_raising-v0-loglikelihood │ │ ├── blimp_irregular_past_participle_adjectives-v0-loglikelihood │ │ ├── blimp_left_branch_island_simple_question-v0-loglikelihood │ │ ├── blimp_matrix_question_npi_licensor_present-v0-loglikelihood │ │ ├── blimp_wh_vs_that_with_gap_long_distance-v0-loglikelihood │ │ ├── coqa-v0-res.json │ │ ├── coqa-v1-res.json │ │ ├── crows_pairs_english_physical_appearance-v0-loglikelihood │ │ ├── cycle_letters-v0-res.json │ │ ├── drop-v0-res.json │ │ ├── drop-v1-res.json │ │ ├── hendrycksTest-high_school_computer_science-v0-loglikelihood │ │ ├── hendrycksTest-high_school_european_history-v0-loglikelihood │ │ ├── hendrycksTest-high_school_macroeconomics-v0-loglikelihood │ │ ├── hendrycksTest-high_school_microeconomics-v0-loglikelihood │ │ ├── hendrycksTest-high_school_world_history-v0-loglikelihood │ │ ├── math_geometry-v0-res.json │ │ ├── math_geometry-v1-res.json │ │ ├── rte-v0-res.json │ │ ├── sst-v0-res.json │ │ ├── wic-v0-res.json │ │ ├── wsc-v0-res.json │ │ ├── arithmetic_1dc-v0-res.json │ │ ├── arithmetic_2da-v0-res.json │ │ ├── arithmetic_2dm-v0-res.json │ │ ├── arithmetic_2ds-v0-res.json │ │ ├── arithmetic_3da-v0-res.json │ │ ├── arithmetic_3ds-v0-res.json │ │ ├── arithmetic_4da-v0-res.json │ │ ├── arithmetic_4ds-v0-res.json │ │ ├── arithmetic_5da-v0-res.json │ │ ├── arithmetic_5ds-v0-res.json │ │ ├── blimp_determiner_noun_agreement_with_adjective_1-v0-loglikelihood │ │ ├── blimp_irregular_plural_subject_verb_agreement_1-v0-loglikelihood │ │ ├── blimp_irregular_plural_subject_verb_agreement_2-v0-loglikelihood │ │ ├── blimp_regular_plural_subject_verb_agreement_1-v0-loglikelihood │ │ ├── blimp_regular_plural_subject_verb_agreement_2-v0-loglikelihood │ │ ├── blimp_sentential_negation_npi_licensor_present-v0-loglikelihood │ │ ├── blimp_wh_questions_subject_gap_long_distance-v0-loglikelihood │ │ ├── boolq-v0-res.json │ │ ├── boolq-v1-res.json │ │ ├── cola-v0-res.json │ │ ├── math_num_theory-v0-res.json │ │ ├── math_num_theory-v1-res.json │ │ ├── math_prealgebra-v0-res.json │ │ ├── math_prealgebra-v1-res.json │ │ ├── mc_taco-v0-res.json │ │ ├── mnli-v0-res.json │ │ ├── pubmedqa-v0-res.json │ │ ├── qnli-v0-res.json │ │ ├── race-v0-res.json │ │ ├── reversed_words-v0-res.json │ │ ├── wnli-v0-res.json │ │ ├── wnli-v1-res.json │ │ ├── blimp_determiner_noun_agreement_with_adj_irregular_1-v0-loglikelihood │ │ ├── blimp_determiner_noun_agreement_with_adj_irregular_2-v0-loglikelihood │ │ ├── hendrycksTest-high_school_government_and_politics-v0-loglikelihood │ │ ├── random_insertion-v0-res.json │ │ ├── wsc273-v0-res.json │ │ ├── anli_r3-v0-res.json │ │ ├── blimp_coordinate_structure_constraint_complex_left_branch-v0-loglikelihood │ │ ├── blimp_coordinate_structure_constraint_object_extraction-v0-loglikelihood │ │ ├── multirc-v0-res.json │ │ ├── multirc-v1-res.json │ │ ├── ethics_cm-v0-res.json │ │ ├── winogrande-v0-res.json │ │ ├── blimp_causative-v0-res.json │ │ ├── blimp_inchoative-v0-res.json │ │ ├── blimp_passive_1-v0-res.json │ │ ├── blimp_passive_2-v0-res.json │ │ ├── blimp_transitive-v0-res.json │ │ ├── blimp_wh_island-v0-res.json │ │ ├── cb-v0-res.json │ │ ├── cb-v1-res.json │ │ ├── math_counting_and_prob-v0-res.json │ │ ├── math_counting_and_prob-v1-res.json │ │ ├── blimp_intransitive-v0-res.json │ │ ├── blimp_drop_argument-v0-res.json │ │ ├── blimp_npi_present_1-v0-res.json │ │ ├── blimp_npi_present_2-v0-res.json │ │ ├── math_intermediate_algebra-v0-res.json │ │ ├── math_intermediate_algebra-v1-res.json │ │ ├── blimp_adjunct_island-v0-res.json │ │ ├── blimp_only_npi_scope-v0-res.json │ │ ├── mnli_mismatched-v0-res.json │ │ ├── blimp_complex_NP_island-v0-res.json │ │ ├── blimp_ellipsis_n_bar_1-v0-res.json │ │ ├── blimp_ellipsis_n_bar_2-v0-res.json │ │ ├── blimp_wh_vs_that_no_gap-v0-res.json │ │ ├── lambada-v0-res.json │ │ ├── blimp_principle_A_case_1-v0-res.json │ │ ├── blimp_principle_A_case_2-v0-res.json │ │ ├── blimp_tough_vs_raising_1-v0-res.json │ │ ├── blimp_tough_vs_raising_2-v0-res.json │ │ ├── sciq-v0-res.json │ │ ├── blimp_principle_A_domain_1-v0-res.json │ │ ├── blimp_principle_A_domain_2-v0-res.json │ │ ├── blimp_principle_A_domain_3-v0-res.json │ │ ├── blimp_wh_vs_that_with_gap-v0-res.json │ │ ├── ethics_utilitarianism-v0-res.json │ │ ├── blimp_animate_subject_trans-v0-res.json │ │ ├── blimp_principle_A_c_command-v0-res.json │ │ ├── ethics_virtue-v0-res.json │ │ ├── record-v0-res.json │ │ ├── wmt20-en-ta-v0-res.json │ │ ├── blimp_animate_subject_passive-v0-res.json │ │ ├── blimp_wh_questions_object_gap-v0-res.json │ │ ├── ethics_justice-v0-res.json │ │ ├── iwslt17-en-ar-v0-res.json │ │ ├── lambada_cloze-v0-res.json │ │ ├── lambada_mt_de-v0-res.json │ │ ├── lambada_mt_en-v0-res.json │ │ ├── lambada_mt_es-v0-res.json │ │ ├── lambada_mt_fr-v0-res.json │ │ ├── lambada_mt_it-v0-res.json │ │ ├── lambada_openai-v0-res.json │ │ ├── mrpc-v0-res.json │ │ ├── qqp-v0-res.json │ │ ├── blimp_anaphor_gender_agreement-v0-res.json │ │ ├── blimp_anaphor_number_agreement-v0-res.json │ │ ├── blimp_only_npi_licensor_present-v0-res.json │ │ ├── blimp_sentential_subject_island-v0-res.json │ │ ├── blimp_superlative_quantifiers_1-v0-res.json │ │ ├── blimp_superlative_quantifiers_2-v0-res.json │ │ ├── blimp_wh_questions_subject_gap-v0-res.json │ │ ├── ethics_deontology-v0-res.json │ │ ├── lambada_standard-v0-res.json │ │ ├── openbookqa-v0-res.json │ │ ├── wikitext-v0-res.json │ │ ├── wikitext-v1-res.json │ │ ├── blimp_determiner_noun_agreement_1-v0-res.json │ │ ├── blimp_determiner_noun_agreement_2-v0-res.json │ │ ├── blimp_expletive_it_object_raising-v0-res.json │ │ ├── blimp_principle_A_reconstruction-v0-res.json │ │ ├── pile_arxiv-v1-res.json │ │ ├── pile_enron-v0-res.json │ │ ├── pile_enron-v1-res.json │ │ ├── pile_uspto-v0-res.json │ │ ├── pile_uspto-v1-res.json │ │ ├── piqa-v0-res.json │ │ ├── qa4mre_2012-v0-res.json │ │ ├── pile_arxiv-v0-res.json │ │ ├── pile_books3-v0-res.json │ │ ├── pile_books3-v1-res.json │ │ ├── pile_freelaw-v0-res.json │ │ ├── pile_github-v0-res.json │ │ ├── pile_github-v1-res.json │ │ ├── prost-v0-res.json │ │ ├── swag-v0-res.json │ │ ├── blimp_sentential_negation_npi_scope-v0-res.json │ │ ├── ethics_utilitarianism_original-v0-res.json │ │ ├── headqa-v0-res.json │ │ ├── lambada_openai_cloze-v0-res.json │ │ ├── lambada_openai_mt_de-v0-res.json │ │ ├── lambada_openai_mt_en-v0-res.json │ │ ├── lambada_openai_mt_es-v0-res.json │ │ ├── lambada_openai_mt_fr-v0-res.json │ │ ├── lambada_openai_mt_it-v0-res.json │ │ ├── logiqa-v0-res.json │ │ ├── mathqa-v0-res.json │ │ ├── pile_europarl-v0-res.json │ │ ├── pile_europarl-v1-res.json │ │ ├── pile_freelaw-v1-res.json │ │ ├── pile_pile-cc-v0-res.json │ │ ├── pile_pile-cc-v1-res.json │ │ ├── qa4mre_2011-v0-res.json │ │ ├── arc_easy-v0-res.json │ │ ├── blimp_existential_there_object_raising-v0-res.json │ │ ├── blimp_existential_there_quantifiers_1-v0-res.json │ │ ├── blimp_existential_there_quantifiers_2-v0-res.json │ │ ├── blimp_irregular_past_participle_verbs-v0-res.json │ │ ├── blimp_left_branch_island_echo_question-v0-res.json │ │ ├── blimp_wh_vs_that_no_gap_long_distance-v0-res.json │ │ ├── headqa_es-v0-res.json │ │ ├── lambada_standard_cloze-v0-res.json │ │ ├── pile_gutenberg-v0-res.json │ │ ├── pile_gutenberg-v1-res.json │ │ ├── pile_wikipedia-v0-res.json │ │ ├── pile_wikipedia-v1-res.json │ │ ├── toxigen-v0-res.json │ │ ├── blimp_existential_there_subject_raising-v0-res.json │ │ ├── blimp_wh_vs_that_with_gap_long_distance-v0-res.json │ │ ├── headqa_en-v0-res.json │ │ ├── hellaswag-v0-res.json │ │ ├── pile_bookcorpus2-v0-res.json │ │ ├── pile_bookcorpus2-v1-res.json │ │ ├── pile_hackernews-v0-res.json │ │ ├── pile_hackernews-v1-res.json │ │ ├── pile_openwebtext2-v1-res.json │ │ ├── pile_philpapers-v0-res.json │ │ ├── pile_philpapers-v1-res.json │ │ ├── pile_ubuntu-irc-v0-res.json │ │ ├── pile_ubuntu-irc-v1-res.json │ │ ├── truthfulqa_mc-v0-res.json │ │ ├── truthfulqa_mc-v1-res.json │ │ ├── wmt14-en-fr-v0-res.json │ │ ├── wmt14-fr-en-v0-res.json │ │ ├── wmt16-de-en-v0-res.json │ │ ├── wmt16-en-de-v0-res.json │ │ ├── wmt16-en-ro-v0-res.json │ │ ├── wmt16-ro-en-v0-res.json │ │ ├── wmt20-cs-en-v0-res.json │ │ ├── wmt20-de-en-v0-res.json │ │ ├── wmt20-de-fr-v0-res.json │ │ ├── wmt20-en-cs-v0-res.json │ │ ├── wmt20-en-de-v0-res.json │ │ ├── wmt20-en-iu-v0-res.json │ │ ├── wmt20-en-km-v0-res.json │ │ ├── wmt20-en-pl-v0-res.json │ │ ├── wmt20-en-ps-v0-res.json │ │ ├── wmt20-en-ru-v0-res.json │ │ ├── wmt20-en-zh-v0-res.json │ │ ├── wmt20-en-zh-v1-res.json │ │ ├── wmt20-fr-de-v0-res.json │ │ ├── wmt20-iu-en-v0-res.json │ │ ├── wmt20-ja-en-v0-res.json │ │ ├── wmt20-km-en-v0-res.json │ │ ├── wmt20-pl-en-v0-res.json │ │ ├── wmt20-ps-en-v0-res.json │ │ ├── wmt20-ru-en-v0-res.json │ │ ├── wmt20-ta-en-v0-res.json │ │ ├── wmt20-zh-en-v0-res.json │ │ ├── blimp_left_branch_island_simple_question-v0-res.json │ │ ├── iwslt17-ar-en-v0-res.json │ │ ├── pile_nih-exporter-v0-res.json │ │ ├── pile_nih-exporter-v1-res.json │ │ ├── pile_openwebtext2-v0-res.json │ │ ├── pile_stackexchange-v0-res.json │ │ ├── pile_stackexchange-v1-res.json │ │ ├── qa4mre_2013-v0-res.json │ │ ├── wmt20-en-ja-v0-res.json │ │ ├── wmt20-en-ja-v1-res.json │ │ ├── arc_challenge-v0-res.json │ │ ├── blimp_determiner_noun_agreement_irregular_1-v0-res.json │ │ ├── blimp_determiner_noun_agreement_irregular_2-v0-res.json │ │ ├── blimp_determiner_noun_agreement_with_adj_2-v0-res.json │ │ ├── blimp_distractor_agreement_relational_noun-v0-res.json │ │ ├── blimp_distractor_agreement_relative_clause-v0-res.json │ │ ├── blimp_irregular_past_participle_adjectives-v0-res.json │ │ ├── blimp_matrix_question_npi_licensor_present-v0-res.json │ │ ├── pile_dm-mathematics-v0-res.json │ │ ├── pile_dm-mathematics-v1-res.json │ │ ├── pile_opensubtitles-v0-res.json │ │ ├── pile_opensubtitles-v1-res.json │ │ ├── pile_pubmed-central-v0-res.json │ │ ├── pile_pubmed-central-v1-res.json │ │ ├── blimp_wh_questions_subject_gap_long_distance-v0-res.json │ │ ├── pile_pubmed-abstracts-v0-res.json │ │ ├── pile_pubmed-abstracts-v1-res.json │ │ ├── pile_youtubesubtitles-v0-res.json │ │ ├── pile_youtubesubtitles-v1-res.json │ │ ├── squad2-v0-res.json │ │ ├── squad2-v1-res.json │ │ ├── blimp_regular_plural_subject_verb_agreement_1-v0-res.json │ │ ├── blimp_regular_plural_subject_verb_agreement_2-v0-res.json │ │ ├── blimp_sentential_negation_npi_licensor_present-v0-res.json │ │ ├── hendrycksTest-global_facts-v0-res.json │ │ ├── blimp_determiner_noun_agreement_with_adjective_1-v0-res.json │ │ ├── blimp_irregular_plural_subject_verb_agreement_1-v0-res.json │ │ ├── blimp_irregular_plural_subject_verb_agreement_2-v0-res.json │ │ ├── gpt3_test_0deb8e9bde8e8327bbc48157f638ff3ba06b0cd816dad2beb8ad90f7fbe795c7.pkl │ │ ├── gpt3_test_8025023377febbd8c5f2b9f26705c394ff375d0cad7c89c10fd9b8e1eb66ff1c.pkl │ │ ├── gpt3_test_bb2cc49115e88788ed870ad0716eb00b280a885f91c7ed6e1e864435e5e2b6ac.pkl │ │ ├── gpt3_test_cfd11f555a5a63b6dfa114a55a932e51b724cdd44d4842586b9ce37260bf7aaa.pkl │ │ ├── gpt3_test_f307d52964c295e2005c5e782b688c24388e0cecadf29f1e6fc7f394236ea9c0.pkl │ │ ├── hendrycksTest-abstract_algebra-v0-res.json │ │ ├── hendrycksTest-anatomy-v0-res.json │ │ ├── hendrycksTest-business_ethics-v0-res.json │ │ ├── hendrycksTest-medical_genetics-v0-res.json │ │ ├── hendrycksTest-college_chemistry-v0-res.json │ │ ├── hendrycksTest-computer_security-v0-res.json │ │ ├── hendrycksTest-jurisprudence-v0-res.json │ │ ├── hendrycksTest-us_foreign_policy-v0-res.json │ │ ├── hendrycksTest-virology-v0-res.json │ │ ├── textsynth_test_0a89c2739f9598b4be2674b0a8e43931d7f3f0b696970bcba31f9b52bdf12297.pkl │ │ ├── textsynth_test_0c1c14571add7903b89e588c8212572b95bb57b334fc0752c89a7e045a5f63ae.pkl │ │ ├── textsynth_test_3092d07756f3e1d010c07524cc8a2ecba7f0c19f9e39f2aaf2bf440bfe328004.pkl │ │ ├── textsynth_test_434076260b6af3a46b7a5eaceec3306a5872c400a3872f744280b237455a0f8e.pkl │ │ ├── textsynth_test_49c47ae40e11f349f2f6b492128188b1b2bc103a421c676ee4b2142a68b43516.pkl │ │ ├── textsynth_test_4fd8d66a6dad7f602b40e5d7dc298d6fe329299d086a4659743a41f4a4012659.pkl │ │ ├── textsynth_test_51b5302f157cf224f694ccad973f255ae19e9e061d533256bdf75b04e0a917ab.pkl │ │ ├── textsynth_test_6d6c62dd70caaa208712bf766deaf419cfac89538d4ab7745621e339394c0c23.pkl │ │ ├── textsynth_test_7209c4617547bfe17cb9e7f5f735fe35822d650aefdc5fbeeaf0c1724effbe09.pkl │ │ ├── textsynth_test_7afdc285388e51094e12645f305328c759574fa3ec9751631025f8ad5ebf9f3e.pkl │ │ ├── textsynth_test_9d5f33dbfe1e254928c89f5ed85e4c010d888065f55a8f1b863bc1eb0340a5f2.pkl │ │ ├── textsynth_test_abcbcba648d89e5d81a50511a6d24ddeb538de2ffe108c1370dd74ce6ac8038d.pkl │ │ ├── textsynth_test_b1cbb29666cce5e31a1e97695858137398a0885ca5d5d98f515404fb6aeb99e7.pkl │ │ ├── textsynth_test_e7ad1e9f52a39e1ddd1e50f3c57ffa4546728dd150a67c0a0ddc8675c04e15d1.pkl │ │ ├── textsynth_test_f4bfe4beb605bd52a8ab6be3c9293639e7e2261d98de58159d15ccb83131bf4e.pkl │ │ ├── blimp_determiner_noun_agreement_with_adj_irregular_1-v0-res.json │ │ ├── blimp_determiner_noun_agreement_with_adj_irregular_2-v0-res.json │ │ ├── hendrycksTest-astronomy-v0-res.json │ │ ├── hendrycksTest-college_mathematics-v0-res.json │ │ ├── hendrycksTest-marketing-v0-res.json │ │ ├── hendrycksTest-nutrition-v0-res.json │ │ ├── hendrycksTest-philosophy-v0-res.json │ │ ├── hendrycksTest-sociology-v0-res.json │ │ ├── mutual_plus-v1-res.json │ │ ├── hendrycksTest-human_aging-v0-res.json │ │ ├── hendrycksTest-management-v0-res.json │ │ ├── hendrycksTest-prehistory-v0-res.json │ │ ├── mutual-v0-res.json │ │ ├── mutual-v1-res.json │ │ ├── blimp_coordinate_structure_constraint_object_extraction-v0-res.json │ │ ├── hendrycksTest-econometrics-v0-res.json │ │ ├── hendrycksTest-formal_logic-v0-res.json │ │ ├── blimp_coordinate_structure_constraint_complex_left_branch-v0-res.json │ │ ├── hendrycksTest-college_biology-v0-res.json │ │ ├── hendrycksTest-college_computer_science-v0-res.json │ │ ├── hendrycksTest-miscellaneous-v0-res.json │ │ ├── hendrycksTest-moral_disputes-v0-res.json │ │ ├── mutual_plus-v0-res.json │ │ ├── hendrycksTest-college_medicine-v0-res.json │ │ ├── hendrycksTest-college_physics-v0-res.json │ │ ├── hendrycksTest-human_sexuality-v0-res.json │ │ ├── hendrycksTest-machine_learning-v0-res.json │ │ ├── hendrycksTest-moral_scenarios-v0-res.json │ │ ├── hendrycksTest-professional_law-v0-res.json │ │ ├── hendrycksTest-public_relations-v0-res.json │ │ ├── hendrycksTest-security_studies-v0-res.json │ │ ├── hendrycksTest-world_religions-v0-res.json │ │ ├── hendrycksTest-conceptual_physics-v0-res.json │ │ ├── hendrycksTest-high_school_computer_science-v0-res.json │ │ ├── hendrycksTest-international_law-v0-res.json │ │ ├── hendrycksTest-logical_fallacies-v0-res.json │ │ ├── hendrycksTest-clinical_knowledge-v0-res.json │ │ ├── hendrycksTest-high_school_biology-v0-res.json │ │ ├── hendrycksTest-high_school_physics-v0-res.json │ │ ├── crows_pairs_english-v0-res.json │ │ ├── crows_pairs_french-v0-res.json │ │ ├── hendrycksTest-high_school_chemistry-v0-res.json │ │ ├── hendrycksTest-high_school_geography-v0-res.json │ │ ├── hendrycksTest-high_school_statistics-v0-res.json │ │ ├── hendrycksTest-professional_medicine-v0-res.json │ │ ├── hendrycksTest-electrical_engineering-v0-res.json │ │ └── hendrycksTest-elementary_mathematics-v0-res.json └── docs │ └── img │ └── fewshot_example_gpt3.png ├── bigcode-evaluation-harness ├── bigcode_eval │ ├── __init__.py │ └── tasks │ │ └── custom_metrics │ │ ├── __init__.py │ │ ├── pal_metric │ │ └── __init__.py │ │ └── multiple_metrics │ │ ├── __init__.py │ │ └── safe_subprocess │ │ ├── .gitignore │ │ └── evil_programs │ │ ├── block_on_inputs.py │ │ ├── fork_bomb.py │ │ ├── sleep_forever.py │ │ ├── unbounded_output.py │ │ ├── fork_once.py │ │ └── close_outputs.py ├── requirements.txt └── Dockerfile ├── figure2.png ├── langbridge └── __init__.py └── requirements.txt /evaluation-harness/lm_eval/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/scripts/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/requirements.txt: -------------------------------------------------------------------------------- 1 | -e . 2 | -------------------------------------------------------------------------------- /bigcode-evaluation-harness/bigcode_eval/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/asdiv/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/coqa/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/drop/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/pile/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/quac/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/headqa/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/logiqa/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/mutual/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/unscramble/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/decontamination/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/scripts/clean_training_data/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/hendrycks_math/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/sat_analogies/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/bigbench_resources/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/lm_eval/datasets/hendrycks_ethics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /bigcode-evaluation-harness/bigcode_eval/tasks/custom_metrics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/CODEOWNERS: -------------------------------------------------------------------------------- 1 | * @haileyschoelkopf @lintangsutawika 2 | -------------------------------------------------------------------------------- /figure2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/figure2.png -------------------------------------------------------------------------------- /bigcode-evaluation-harness/bigcode_eval/tasks/custom_metrics/pal_metric/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/ignore.txt: -------------------------------------------------------------------------------- 1 | ROUGE 2 | rouge 3 | nin 4 | maka 5 | mor 6 | te 7 | -------------------------------------------------------------------------------- /bigcode-evaluation-harness/bigcode_eval/tasks/custom_metrics/multiple_metrics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/cb-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ec3b1bbb9561e39c43c6f77a23b4060b15c606141c5346e3d0791b3e92aaa5d0 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/cb-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | 77b11f4348eb8a7f57faf95c531fda01ab4bf0e729f91a82451ed8e71ec8e66d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/coqa-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 4a8605d5deed0423ec095700251ed93325b45d320aca35d4ce1e94702094435e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/coqa-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 57581470b921435d40da97872bb1cfda6ecf963ccc4b0240a3b04e3fea8c8e3a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/drop-v0-greedy_until: -------------------------------------------------------------------------------- 1 | ca566c630d8ac853d5785d4b5c40a5137172c34b48af3350e1f79e6d548b36ba -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/drop-v1-greedy_until: -------------------------------------------------------------------------------- 1 | a670f911ab2999d72db15f534b22703d19e7837edbda4f9f199ad587f7aae6b2 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/qqp-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 97b551b0fc3d239aad4929a2e8e79c986891aefd9fcd19441fea0382d507889e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/rte-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | c80ce13c8c736087f1557f8736d5d318b540ff01e4bb7f55e568890dc8b0393e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/sst-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d2ebe3a63517d1d481aa1513bebe124c57a0904554a1e95f566979cfe67b1a7f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wic-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 403a08da05e4c44d7e3dd3358382a7ba489c41d223e24cd1a9ed82ef1a2d004b -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wsc-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 45865468eff5ca31e6a050947a6b3310d9d5ed19d0f2e578a32ecaf1c768600f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/anagrams1-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 7c0c5246d3f751f39119a5629ac1d4b2c6fd2a315f78d6de9b2c387e24e3fef1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/anagrams2-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 6700a3c44e48abe8337238dcbe3b54cf4abafe0c204c52d921e590872fbd05e7 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/anli_r1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 3a84baf2f170e138c6ce0bc9f06f905def35d705fa2b8781f10c87aef404c4cb -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/anli_r2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d0ea3c3e09d533982c15b4c034439896d6af4bbafb2254d305e20215534a251d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/anli_r3-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6b6e5c6a794f2fbff78b7aa24fe0c90156039334bbd1cb34f7af9fc6e6183845 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arc_easy-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ffa6e39a35a16299dcb015f17f986aaa598ad8b4840c4cebe0339a7042232741 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/boolq-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | de5aa6f77a2e0fd050b9c272f10c4d5d5581e4f75ffa60926f79e60ae1738960 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/boolq-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | 6577e0d88572772ef08e64f624c0e3df0953286ae1f118ccef15623b59ffeabf -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/cola-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | e8635578ed8ee70b707a666d35e468b9321db24470f80c92080651e2bfa01751 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/copa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 66276b9045b5300cba4b81340db06f674f031fa0b8883714ad0d03be464cd799 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/gsm8k-v0-greedy_until: -------------------------------------------------------------------------------- 1 | e7292dbdd7fd8419ba954f2e0701e04c8d0e8842fe053dbf2fe47d926630e35e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/headqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 767ca34d9714edd9fb030ddbcc35a64e5180d1e247b0cb557fbb22fdf971ad1f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6829e6a8aa5922e6c92dd31403cc060f242dc0ede4a775e085a70da095ab2e20 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/logiqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 12495c50454ba5e1ce0753bd18c09aaca516bebd27648d815e37b15229dbf198 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mathqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a45260e49f02c7cb8886b3746db4d388890860b202dd8a9f0267e3c324e0af13 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mc_taco-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 1811808ef05afd5f30ffc3471622a3dd7a1b681b17a2f7616695ad6b2a45943c -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mnli-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4fc7b56b8f1e37e38f4a052b227baec2df914c898c3405d3e994726ba4fba976 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mrpc-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 9f54cbff8d6accba99cfa2c4c4b359563313941018173d7dcf9e32dc28c06583 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/multirc-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | cdb026c027437a8b4653212d0944d36fc16f49921dcb8e4bef899d15a55e9f80 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/multirc-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | 0e793bd6f637a70a04c6f2cda080188fc037961b2f909095fe63f7bdbc4a90c6 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mutual-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f759213a28f0412510bf1a24c9cab0dae64bdee902d42a26225295445e7779db -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mutual-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | f759213a28f0412510bf1a24c9cab0dae64bdee902d42a26225295445e7779db -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/piqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6048a3a2bb3ad1e6a3d98139618e06b4d7de766edd685bd38837596199c3f69f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/prost-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7c475f5b36a8b79f94c2be035441e7fd59dac021b0713b1fc72d256424c70b0b -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pubmedqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7a04a1fb1d2b19db84fd15c224015d6c0306a41195a4e71fe6abd48fb4d53b9f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/qnli-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4281d4ff5cf1244358b0ea0220c67863c69fbade850696b43e8ff05138e01e12 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/race-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | bdfdfab7fa1c7af0c1e161785e347b1b8071a15cbf971f6f2a9ae8c8e845199f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/record-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a3e378fbde4e28f375cac1561bbfc7d7673c2af193628a774ad012d5192393aa -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/sciq-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 71cbb6e2a7ac4512c3761ea801d420eb3fac49d158c7e4deaa3ab8727bea923c -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/squad2-v0-greedy_until: -------------------------------------------------------------------------------- 1 | b261e8885c11750ce6911bb11e8693de03d53758297c26fb14cfc1ef508862cb -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/squad2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 287e87cc6878debcc80d9b6df4e2d0a74ed29068e0e0a80906c8441843a17cee -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/squad2-v1-greedy_until: -------------------------------------------------------------------------------- 1 | e17e3d85c1d5adaf2d6b4b752c4babc2e0b3a6e144e6de70cb3b2287e85109b8 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/squad2-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | f5da6173402b274dc89130755c222c6ca6b2a3bacaaa4e4ab07be9322b7bad65 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/swag-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | be4fcbad876124c4ba3c71970538a97fec0e36a9cc677c70b6c9243a7bcee0ec -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/toxigen-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7fedd930bafa92b9cca615a93ba92a4413244d2b77cf3f421a186815d721e0fa -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/triviaqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f8ec05b306b9f6187c0f8117cae441fb85a7a2e4670f4f9a1a3b632b1978421a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/triviaqa-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | f8ec05b306b9f6187c0f8117cae441fb85a7a2e4670f4f9a1a3b632b1978421a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/webqs-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 96b218173468cc94552a0b946193bda89faba51f1bfc3e7945531f9dff8d6fe9 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wnli-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2ffd304d6096416eb29607e2e7642b1d6043163624967bcf4c4fc00fddc6c721 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wnli-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | 8a0f81661d2ab2334bbc8031fac31c0c8882f1d9271dd51599d21dfdbb726dea -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wsc273-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 26450d414c4581feb51a09882080e7a9b95882e7eab47b1751a4a6024b5a60ee -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arc_challenge-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 41c34c96cca8ace661911d0033d630c554b283f5a3953bcdc50720ae6b00a9c1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/cycle_letters-v0-greedy_until: -------------------------------------------------------------------------------- 1 | eb23f7d5de7528eefd8ed5f8054c402ff947319cccfef7195995946f99389201 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/ethics_cm-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 92d136ebb2bd86cd036e61699ad9a1417dbb48651f0a3afa5045cf57cef5a3f6 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/ethics_virtue-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8021db8de46850090ddae6e6ec2d382029c3027b7c69884607503f916d09b709 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/headqa_en-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 09da45119b12a0144e3081f8fb790c2a22af7b9c3aac42f54423d348a711fbf5 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/headqa_es-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 767ca34d9714edd9fb030ddbcc35a64e5180d1e247b0cb557fbb22fdf971ad1f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hellaswag-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | abb808c97d6529eda6c11067837a132c62d25cba0394d720f80cca6df9f7196e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/iwslt17-ar-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | e94d310de91fad7ce36f4cf3305552020221482c5588f2efcefaa019893504f1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/iwslt17-en-ar-v0-greedy_until: -------------------------------------------------------------------------------- 1 | b20adbcd2c6d135e28600b427113532c5df624cb3a90e8c5e48715c09a3a38fa -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_cloze-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7655e748b63ae7e9911411d2d2a2577221d6c861ca4448509992541294d689f3 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_mt_de-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 5ad125e1708499832b2cee8c3388f89f9c0277010fd96fbd3359039ce8105984 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_mt_en-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6829e6a8aa5922e6c92dd31403cc060f242dc0ede4a775e085a70da095ab2e20 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_mt_es-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4a88f4b316c72fe0396c382d6cbb33568ac4d0ad225150d3536635c085359fc9 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_mt_fr-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 5d16f4a0c51dc6d7b6df2ebeba2bbfa51e700b843779b559b3d90183d7b02a11 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_mt_it-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fd87c6c5cf4e0499c5f9f80e5bd7ee6a4f3d2991902a0cc3ec9e6eaf22d6760a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_algebra-v0-greedy_until: -------------------------------------------------------------------------------- 1 | f19182ce697a2c095d9e5b56ee6659dc38c93994b69ca75d7c3d3f5fd87572b4 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_algebra-v1-greedy_until: -------------------------------------------------------------------------------- 1 | f19182ce697a2c095d9e5b56ee6659dc38c93994b69ca75d7c3d3f5fd87572b4 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_geometry-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 46bc4cb219b6903397da782699a684bdbb982c0c954ff82e6beeed5c84878f42 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_geometry-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 46bc4cb219b6903397da782699a684bdbb982c0c954ff82e6beeed5c84878f42 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_precalc-v0-greedy_until: -------------------------------------------------------------------------------- 1 | bc834b06fd79473ca6fe38a51b714aad0bf0478c1b0eec787eca34dbdf69cb71 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_precalc-v1-greedy_until: -------------------------------------------------------------------------------- 1 | bc834b06fd79473ca6fe38a51b714aad0bf0478c1b0eec787eca34dbdf69cb71 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mutual_plus-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b846bb9db109535f59a93d1ce340cf09f68bdf4fed5b8decd168784220fe07fa -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mutual_plus-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | b846bb9db109535f59a93d1ce340cf09f68bdf4fed5b8decd168784220fe07fa -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/openbookqa-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 78a49a0ca1a47373adb33463b1d092e6bc0d8f4b01bcb380ada48065037849d7 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/qa4mre_2011-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0d09f17c65768e797633494d2d218e4e46a26f718cab8b0bf3d156b073a8c437 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/qa4mre_2012-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7e17261820acb365966cb9431d93aec983b14393eaeefbc96e30a11cf58bc6df -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/qa4mre_2013-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 52fc431e94c67f983e28ebc70cf45e6c14116b0ae77dc1bf22347c705a65d054 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/reversed_words-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 1d79fc4f0177f9624a487b9973f4e0e1d3f8404993b419a7b807a690ebbbb290 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/truthfulqa_gen-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 0d7c56e1aa71ffd8f94bde28f6e8dfdd35f7aaadffa0620bd2a27704253d6c14 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/truthfulqa_gen-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 1a280973bbac2b7ac29dd64dddac474fb4749585f7de893483b4034814466c67 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/truthfulqa_mc-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 226a6783976177dc9ceda5688623ff37023242eff30ddf270b886bf7b9b32228 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/truthfulqa_mc-v1-loglikelihood: -------------------------------------------------------------------------------- 1 | 1e07020e9cf41d46ed65312eb39d2b8e6599673d4f0d6b67c0d0eba0efb493bb -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/winogrande-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 90a3eff49de9173964d46f5ed57bcf9a78a72dd1bfe0e5323b25cebb40b49ea9 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt14-en-fr-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 368ae7eec0f902b5123f2d5197caa5109a23942011c53fe68d9eaeee20180e46 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt14-fr-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | c1d9f7283755fbdd7ecd6cc4278b0ac25a80ac256b7071ea5f839ccd038e5974 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt16-de-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | d30e23e38d9a45b9c31e1dfd14b58d0b7020df4b9c8a1c697aa6bc5fba8ce08a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt16-en-de-v0-greedy_until: -------------------------------------------------------------------------------- 1 | d71e2074af3770e9b29ac561caf2e1c29ad6b0dc50ec2e7bcc5501747b11f0da -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt16-en-ro-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 4be7fdda313394f19b5995b00ada1dfa3bb158ee1f020ef8d07ecea260fa60b2 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt16-ro-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | d1b7c50751b0d5d7470b7f49f2bab9d09792c91460fc92cc34f06617013d7c65 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-cs-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | bfead9efdb1b2402a414c55929c8d8f956585f938a35466931d44e81d89cfe00 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-de-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | d13b5a6915ca86ac6c6ebc50d9be0d0be3dfca600c12e896df53190d875de74d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-de-fr-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 7f197bc281d6dbf9425900ef0dee7175021c43e355050f149f43b161c52bf0b0 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-cs-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 5a34e6863bf6965afd31653de50bac5fecf58db65dbaba46921504a2b7463786 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-de-v0-greedy_until: -------------------------------------------------------------------------------- 1 | b6e9c305766ea23ce1027309f83c6d4c2ce8948d70b63a7858586ca34050d7fb -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-iu-v0-greedy_until: -------------------------------------------------------------------------------- 1 | f5688199890a48f73f2cc04a2152e35190f0e0ddd40e629fa24ee39d423ea389 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-ja-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 7fe61f5847a51e93e97c84b39f4420978727754e4b6cf636a27851c615857530 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-ja-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 7fe61f5847a51e93e97c84b39f4420978727754e4b6cf636a27851c615857530 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-km-v0-greedy_until: -------------------------------------------------------------------------------- 1 | eb5365c46f22ffec9a157991627d6e1fd1117fccffaedfc73619e93bafb5a408 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-pl-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 952f02575d4936d93c4d2808d86c4bf5f1f3a0901212acee6cbc1f9cbd30d39e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-ps-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 8411c2cb73114cbd0c6e0f17eab2625d486cc3a601105deb0ea1338a401df689 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-ru-v0-greedy_until: -------------------------------------------------------------------------------- 1 | a1613831f69c1679a54670092af40ce76617b79d7cc837984803b0fc52bb8bde -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-ta-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 5fc556fa90bca7f1b1396e97e392eac8080b0ad53488358799b8fc0b21a94cb1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-zh-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 67f0333ddbcb07d7a9ac12919129a18fe4fea24e4826a11bbdde4fd5ed5ed83f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-zh-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 67f0333ddbcb07d7a9ac12919129a18fe4fea24e4826a11bbdde4fd5ed5ed83f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-fr-de-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 8a4b65c59dcac6591d46261909ee92ebcf41c19ee7442b12842302b2d8aeb36f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-iu-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 97bf664a8efa54b5366b8341f77b418106dd0cb26169d5b2d0144e4d3d2bc5c9 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-ja-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 1fd846f3c0104e794eb380dae7f648592092ab8bf59234c26d0a671bbbc28df1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-km-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | fb4ec81bb89c70df7e21b43e0e882915b7b71a2a85bb8d4b59e0c7938baaa4c2 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-pl-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 89274499d84176b1ffe4eaec06f2c89ca807342384dc946c2e348d00116aaade -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-ps-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | c3976465e3709b4bc371175cc1494c69fe096ea4ba7d114da779d2baa0a47466 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-ru-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 1477ab6542c26bd0222cc1aded174f33bf8d04d1cf6a1c0959aeca4ff3779adc -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-ta-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 111ea3efdc08f1cf536631b9426c3a20e482c575d009d2a8c71f59c027578eec -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-zh-en-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 07dbadfd6f2b2b9462ab6187dbfaabae6e5192ab89a8e4ede9237834b9364dd1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_1dc-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 04c3a63a6b3c579bd3775d92b3076ba9130041d5ce7cf9244d3f86e95c804387 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_2da-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6ca1ca6ebd7cac4420d5005f7f35b0edbc921377f5e4f8874cc176e4fb6d79d4 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_2dm-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 14ac5e510cdf82967d6827a9ca059906ee1db2e347be1b17f36403a157e73552 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_2ds-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 66f7ff3b40251ee38fadcbee658e309a200224356fc3efa07d0a490a2c24bfa3 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_3da-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | c421f9cd5a5001b80e528441da925128177a04db8526ebcdab543a90b33c9ce2 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_3ds-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d3d8bad8827d4530945a1d8b3c7589c0235bbed0bc89e7561a6fdac678f6ce5c -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_4da-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d3557beb8b9e5704122c2fc6362b11fbe2c3f2f3cb72aed4462b208767c40e01 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_4ds-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d915830b8621e66331383bb2ae4c60acebf008e2f94741092ef4c33ea5441037 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_5da-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 49edb1e735660631ea6cc309721e6c0b80b7106a613a6959514852ca48f1130e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_5ds-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2888d6d098a5ef8c1e7f0d8295ba80826e2e04e431f57508dfb71d53e1cd4604 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_causative-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 3d67ad025185dbb0808ebd7f508edcb5750c18fc3c01ad91f20fda80780c916c -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_inchoative-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 3ff73629fb4473986a0e8ae2fcb7c40e88292189ab0d8755d20836c5aa5a2f99 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_intransitive-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6469ae3b0d46b008846b5fd132f2d2b26ea2858745d056df1470b89aa97a790f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_passive_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fa4addddd8e380031b8e0871776cabcb707c0f21dcaf5d8b3defec66cce55043 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_passive_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 755bdfe2c89737c43001ff1dc83d68ad33e444aaf0669af66aaf82dcd09f2eca -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_transitive-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d0d47fe40a7ee558ba782edbc4f49f7d9123c8472a36decc97f8ab142b45b9d8 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_island-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 91a9e4b60b0f3572a7fdbd7648d0e69f36e5eb34db715315b0082558d7ed8b65 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_french-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4fb61dcf4d2c59d6470b297a01d5f429ee442864e225e1760fbf191b2a0901cd -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/ethics_deontology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 74ecebe322457d70afc16fde848978410a09b854dc65c47f428d100bd1593248 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/ethics_justice-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d7dfc44fea507b5c5c3a8218f79ed8197da8599ebb396d85feb91c25512126b6 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/gsm8k-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"gsm8k": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"gsm8k": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6829e6a8aa5922e6c92dd31403cc060f242dc0ede4a775e085a70da095ab2e20 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_standard-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8958d9f8d8145046b692fadd8a9cc9c8bad5617c10774280cf7c24c21d2be160 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_num_theory-v0-greedy_until: -------------------------------------------------------------------------------- 1 | b920ccb507afdcf3ef6f4c04891913731e9f32ec914801791c6d9f8abf6e1897 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_num_theory-v1-greedy_until: -------------------------------------------------------------------------------- 1 | b920ccb507afdcf3ef6f4c04891913731e9f32ec914801791c6d9f8abf6e1897 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_prealgebra-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 752cdf343d7152e476b0273065024f6ea0e0f47ea385c6bdf9067736cb39724a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_prealgebra-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 752cdf343d7152e476b0273065024f6ea0e0f47ea385c6bdf9067736cb39724a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mnli_mismatched-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 3784acf322e79f31702a7a0612030e4ba5c4fc466ad976a34ee3f3d7278c01f0 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_arxiv-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 814f9954e44368559602c00f7e85fa3971acdfd0315f508ec7df6318a79c55ec -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_arxiv-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 814f9954e44368559602c00f7e85fa3971acdfd0315f508ec7df6318a79c55ec -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_enron-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 4baa6ccdc9e3aa9921675ab4400d5e89d7b546b844a8ea28f6461d649066418a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_enron-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 4baa6ccdc9e3aa9921675ab4400d5e89d7b546b844a8ea28f6461d649066418a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_uspto-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 789b2bdb31564d512b70f801316f49320a26c83ba361226bac0afb255341d477 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_uspto-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 789b2bdb31564d512b70f801316f49320a26c83ba361226bac0afb255341d477 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/random_insertion-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 6c48baa6924f3635120f33062251c4b571b3d4e9fe46b14d91f54ddd1c857997 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/webqs-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"webqs": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"webqs": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wikitext-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | b6f83e6cf7535ee41b0057c3e2ec2cf7f2fa5a9119b305c479a83091d1142b2c -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wikitext-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | b6f83e6cf7535ee41b0057c3e2ec2cf7f2fa5a9119b305c479a83091d1142b2c -------------------------------------------------------------------------------- /bigcode-evaluation-harness/bigcode_eval/tasks/custom_metrics/multiple_metrics/safe_subprocess/.gitignore: -------------------------------------------------------------------------------- 1 | /__pycache__ 2 | /.pytest_cache -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_adjunct_island-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 976a5cac4bdb724632eebd4cb9e522203ce3da8d5525288a597c86e80469f3f2 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_complex_NP_island-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f46cfcc7e43050a235fd2a6b989cabbfbcce76786df74db9f0d4a9cd1caa1628 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_drop_argument-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 616109e63f162dcd31a632943e7ef0c9e0431afeb179e83e9b04b39007b16f5b -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_ellipsis_n_bar_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d14e4b7fcdd68991eb39b9cf3ade4b37dee9ddd39b688f861d81a327e47a969f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_ellipsis_n_bar_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0523771a217759f0b22b89807694ee7f6381ce98a584b1fd070ba96194a3273b -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_npi_present_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 3ef532a85e0ee8f8ff779bc7ddc873d515969a708da84a4eb4a85b7c843cf244 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_npi_present_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fdb688ac6259bb65d234ef0a36e9a9ee449f9608f633b12e1943b462aead8e17 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_only_npi_scope-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fc0be817478c212327050fa297ef61ad214f4847dbff61d4e0fe7914c06a1691 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_vs_that_no_gap-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d1d3e439b2020ef5ed232bfebbcc9634adc5117e9eb61e38fdbbe2c8ea128d54 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_english-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ee3ce1ddb8071d4189e5b06e7f3c618a434221ac52935d0f434c4d183f01458a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_english_age-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | de74d2ac7f926f2f486c045d84aae8f71711102f9d77b31f758fd148810d13d3 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_french_age-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b14a5769f415a234abe89063a1b546aa4a990c84217e5d4a697874cd7f85af35 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/ethics_utilitarianism-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 88872f1ed1b203f9649a4ced4fb4627d18c17af455d713de6e17c05eced4ec60 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-anatomy-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | bf05e04ed8cf61cf3aad294ed3f5a16137775ffdd20f1b129022ddffc1251768 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-astronomy-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | bed1e47127cc2893c6aef63b9a0909cca31aa351a703da2a166b01cae03c3311 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-marketing-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b4fa0681fe54671a80509779d4338d744097a7206687f62977df7145dfa74a66 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-nutrition-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 19e49d218f55ed5ec4bd1a6cd3f3388c6f620b81484e7abe8b298e5481c3044d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-sociology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f99a3caece11169f2a5cc951001f92027104afd25d29b2a399883bd4bf118605 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-virology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0ffa491f7bad2abbb64ecd752a295729167599b3815238cab0ecf4cb08bba9b6 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai_cloze-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7655e748b63ae7e9911411d2d2a2577221d6c861ca4448509992541294d689f3 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai_mt_de-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 5ad125e1708499832b2cee8c3388f89f9c0277010fd96fbd3359039ce8105984 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai_mt_en-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6829e6a8aa5922e6c92dd31403cc060f242dc0ede4a775e085a70da095ab2e20 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai_mt_es-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4a88f4b316c72fe0396c382d6cbb33568ac4d0ad225150d3536635c085359fc9 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai_mt_fr-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 5d16f4a0c51dc6d7b6df2ebeba2bbfa51e700b843779b559b3d90183d7b02a11 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai_mt_it-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fd87c6c5cf4e0499c5f9f80e5bd7ee6a4f3d2991902a0cc3ec9e6eaf22d6760a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_standard_cloze-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b604f00bc9f2a77ef41f8cfdb5a8509b3ae9266893b9e90abc665f5399ecba4e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_counting_and_prob-v0-greedy_until: -------------------------------------------------------------------------------- 1 | 2aa9ae43ee9dbb2457525247d7b65358632c5eaa9cbfc40cf95a4f17f5d942ad -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_counting_and_prob-v1-greedy_until: -------------------------------------------------------------------------------- 1 | 2aa9ae43ee9dbb2457525247d7b65358632c5eaa9cbfc40cf95a4f17f5d942ad -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_books3-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 0f8f36f705b999b6d55fa72ff89a82793dd1cb568ab1f8727a6a2086a12b9410 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_books3-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 0f8f36f705b999b6d55fa72ff89a82793dd1cb568ab1f8727a6a2086a12b9410 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_europarl-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | e67d3dbccd47d308bfc5b0e66b76d0dfc5e386ebfa94e056562c2281c395543f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_europarl-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | e67d3dbccd47d308bfc5b0e66b76d0dfc5e386ebfa94e056562c2281c395543f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_freelaw-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | d77f3f68aadd6cbf1290c2f6737b2ed5d5c2a60e4c81a65c280f207783caabe1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_freelaw-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | d77f3f68aadd6cbf1290c2f6737b2ed5d5c2a60e4c81a65c280f207783caabe1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_github-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | df384c3df3d8f53273e97127c5bb84c17e638acad7d6bc9c91f6dee96d43b639 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_github-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | df384c3df3d8f53273e97127c5bb84c17e638acad7d6bc9c91f6dee96d43b639 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_gutenberg-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 02a559f74a9105145e7d4d9c5ddea372b5b4938f5368dc8ffafc39cbe3b4c7ef -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_gutenberg-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 02a559f74a9105145e7d4d9c5ddea372b5b4938f5368dc8ffafc39cbe3b4c7ef -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_hackernews-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | ec1082ee5a5326e0d57aa4e73b634937140c1de9af95f154e8ab57b05d9b422b -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_hackernews-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | ec1082ee5a5326e0d57aa4e73b634937140c1de9af95f154e8ab57b05d9b422b -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_philpapers-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 339ba5d8c044c4a3ff9b9a8eaa24da1d6c01b72972074eb671a7da049eeb7047 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_philpapers-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 339ba5d8c044c4a3ff9b9a8eaa24da1d6c01b72972074eb671a7da049eeb7047 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_pile-cc-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 731fdef4a43949b179ba0c540148ebc2fa41583dd583ef580dd812076c66a451 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_pile-cc-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 731fdef4a43949b179ba0c540148ebc2fa41583dd583ef580dd812076c66a451 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_ubuntu-irc-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 4eb69e314f0864ec8890e2323d7e76f8a8309692c4f090e2b41bf4be681a811d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_ubuntu-irc-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 4eb69e314f0864ec8890e2323d7e76f8a8309692c4f090e2b41bf4be681a811d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_wikipedia-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | ef9ec0dd408316ca6537228a6812e839f14b30608973081d41efc47c138338da -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_wikipedia-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | ef9ec0dd408316ca6537228a6812e839f14b30608973081d41efc47c138338da -------------------------------------------------------------------------------- /langbridge/__init__.py: -------------------------------------------------------------------------------- 1 | from .configuration_langbridge import LangBridgeConfig 2 | from .modeling_langbridge import LangBridgeModel 3 | -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_animate_subject_trans-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2a84231e7b79f517427e57e2099c88fed3d60a7efab4ef9506e263b4091d5cfa -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_c_command-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7c2ed82612af9175052cd44d8e178b6dd084c04eb462a3d88fcacfad2df8be8e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_case_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 49d2b8ce6667a6166fdc2a2e5dbe7ff07d9b8415e9f33482aef15956b3ebc24a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_case_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | cd68adb65c891d672e22bf53c054b2083ab08bc1da43951732b409c942d14bc7 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_domain_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 290e7eddacea4ec16989af697f2ee3373fdd9aef4b452bf887184c6e2f6e7d9d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_domain_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | eb5ddf0a97982373ab1a4e58267cfcdebdecdb86c376dfd5ebf46737c9d3ee12 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_domain_3-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 38454befedcf1f3f6ef27d3bef9ccfdfb3e94a7ab32d86a63493a920d2d50093 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_tough_vs_raising_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 973fe56534fdef1207f0fc08dd09a210304c55f33c6cbb17552754bf54f11c86 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_tough_vs_raising_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d255a10a34f14d77d9526604a17b0f6747d32f62fc2e3a09e9ab10054535fd45 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_vs_that_with_gap-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d41a9b85e4c31e445bf9b46b8642df02203ccc02b4a9b254bf76066d5c54b4b7 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_english_autre-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a197ccc8538231404a8e43f5ed0fbbfb2c317b4da337f6e7aa9642131aeb426a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_english_gender-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2bf62b7cc678f64ffad4a6e6715ff76a2b984bfe8d1165da4b76b3b4dfafb2f9 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_english_religion-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2ed57377174adaf0fb30037eb055eafdd02cd46e57bc32066d5fecd90a14b6e1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_french_autre-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f145ad5086da0bf8c76f0730258529fa243efe32b7ab792d3c4716284b4b5495 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_french_gender-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 010b8404655911c86555616da23afffce9dc3981e1acbbfdb022d9c474430209 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_french_religion-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8af6445eeb634dad5f0723e40615afe993e1e3f129a4f314fe4117e633c2efd3 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-econometrics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | cde76ba2c7382b4876e17136c94f52aca2774e50342ab757b2a2d18da370dcb6 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-formal_logic-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | c0d0f0c008a5f3faf2f6f4268d87bbc09c40bb66ae08cf38eea0bf2e519c5a59 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-global_facts-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 9fdc85240b8170839278b1e883ee0868611d84dce202cb8aa037c841ec76d089 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-human_aging-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0880b3a78f8d7b17ffc612031427b9085367cf65dabe2a68c4b64e3171d17e88 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-jurisprudence-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | cac440189f1ec778e82f4975d88b74689553ecc5116aaa7f76587a50c1a610e0 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-management-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 355489f4bd176ab84db5ef4c03d56ddeeeb1b0ad69827122b2d800e1cdc7e5f0 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-miscellaneous-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 972dd88dbbaf09d14766e243cfc233425e7c01a26dbc61bdb9eeefa788822331 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-moral_disputes-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d6ef028022c02b69d1516973e08bebaa14d8debcf2589a2bb124823178202d20 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-philosophy-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a419204da36c2b7a70fa8909a3a804260cc3283c7e07917534dfb76216c77f46 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-prehistory-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6983c560a562749f4f702249a3a6ae51fa495acc0643a980bf2cf52c6c5d4b95 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_intermediate_algebra-v0-greedy_until: -------------------------------------------------------------------------------- 1 | d53c699de272d517ed7ad783b4e692302be9f9f97a8d4ac7a6541e538a7cabe0 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_intermediate_algebra-v1-greedy_until: -------------------------------------------------------------------------------- 1 | d53c699de272d517ed7ad783b4e692302be9f9f97a8d4ac7a6541e538a7cabe0 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_bookcorpus2-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 5c17ddfebeab8c41dabadb6fc216ceda91e3fe5dc95aaf1b2c843d7f11828b03 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_bookcorpus2-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 5c17ddfebeab8c41dabadb6fc216ceda91e3fe5dc95aaf1b2c843d7f11828b03 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_dm-mathematics-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | d5b7967c0ece8b816f3921a8bd0fad23365349e935b491595e2ad1135af42da6 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_dm-mathematics-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | d5b7967c0ece8b816f3921a8bd0fad23365349e935b491595e2ad1135af42da6 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_nih-exporter-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 520ea6e04e8a39dc0b5f63a837429a78a40e63d39d109096101feb8c5b2cf8d8 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_nih-exporter-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 520ea6e04e8a39dc0b5f63a837429a78a40e63d39d109096101feb8c5b2cf8d8 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_opensubtitles-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 0f1c23a1f4ddec0c2b1ff34de8d1505b0eb9e2868d8edbcc1b6de13d02f32036 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_opensubtitles-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 0f1c23a1f4ddec0c2b1ff34de8d1505b0eb9e2868d8edbcc1b6de13d02f32036 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_openwebtext2-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 5d6c19665f429ab1ccbe027da67f42bdaf219f819ab093673976eee55e015ff4 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_openwebtext2-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 5d6c19665f429ab1ccbe027da67f42bdaf219f819ab093673976eee55e015ff4 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_pubmed-central-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 40b39d120d99a145690444e86acc3e3e24d41e6e0538a75e26929ad84926e5e0 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_pubmed-central-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 40b39d120d99a145690444e86acc3e3e24d41e6e0538a75e26929ad84926e5e0 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_stackexchange-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | e524bfb3e21cbdaddc117403a50df598520c7bf5b2c60ad8f2372cfa564e79be -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_stackexchange-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | e524bfb3e21cbdaddc117403a50df598520c7bf5b2c60ad8f2372cfa564e79be -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/triviaqa-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"triviaqa": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"triviaqa": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/triviaqa-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"triviaqa": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"triviaqa": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/anagrams1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"anagrams1": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"anagrams1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/anagrams2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"anagrams2": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"anagrams2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_anaphor_gender_agreement-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2d8964e56a17661502ecf3f09c0befba63915360ddf2145b0bd845816950515d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_anaphor_number_agreement-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0bdad31c974ba064e1f1ba931841ec2ba7461e8b0ca54ea5f79f08b6bae0bab5 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_animate_subject_passive-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 064c38fcd072b8bd12f54ea4f8e41599ed4e11dc386e93b77e1fc07967d1f960 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2df8cc7f17089f7e8c7d974dcb324c809d30ef059a5be22aed6b69f44230809f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 123e2acd00fbba60aba1fbae607c79a062e512c9e79c7d8dfafff63e30111d76 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_expletive_it_object_raising-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ceede5b38248a62125a74a8332602b8eac5ef40864f071ad8d86e7971e07219d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_only_npi_licensor_present-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d2d0711611b5b218c6fa8c7278494749252b7868c396451919b761303556bd66 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_reconstruction-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 894efedfd8750d5b8de6157f9b2ed2b51b5290d3a78ea9b041fc62d34e96efbc -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_sentential_subject_island-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 80f5f98fad26240de2767fe58c4b18d864df41cbfa76f06c84c3fce9f14f4833 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_superlative_quantifiers_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8a01f6a5ea87a01c0c9b0c7b3bc4de4711bf0ff050976976651182b9ed34a0d4 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_superlative_quantifiers_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 59c20ff0f632cf42afc74ecc682cf92e5e740417b01e6cf9a610a3bc544d2ea5 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_questions_object_gap-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4d4aaa0274ccd485ff8430ed61b8f83806febe18c16616c7d050f637a0463eba -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_questions_subject_gap-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d5486ffcc075cad4302e37ece9bbf5b2063c0b5a48e76c8e1dd365e22a5a48fc -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/copa-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"copa": {"acc": 0.48, "acc_stderr": 0.050211673156867795}}, "versions": {"copa": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_english_disability-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 90c1bcfdeec0ff51d891ee8cf00ae2a5ec61bab6739faea9865809b8ffed2cdb -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_english_nationality-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b85bc849811ccfa9971a6ee3fca7342752c314c0cb6f126e10d9ec4d0450c541 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_english_race_color-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0a750596d77cd96502dc414ff699a399b1b91c2078adeec1d3dd982b3d591089 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_english_socioeconomic-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | c309eabfd247a702e32efc4e08211f9a72693d38995be5dd444d497b476396bd -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_french_disability-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fa1e5fc7492a66c9a90765e605003c38408347617db5ecf36706f1d374af5d42 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_french_nationality-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 146eb60c8796fe3f25307a6776337f0b077b58ce02edec64c99df4b906c19b9f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_french_race_color-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6f9119026abff33c5c882d6172e092e806a8b21bd86864022978b1961839350f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_french_socioeconomic-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8ba0a525c65f795c99f6416e70c998e75e4b6cc43bf9a4bd7ccacd3c3591e9cb -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/ethics_utilitarianism_original-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 5b42ba1faf5ece6a6ec9a3976ce79c1fac8df5b98272aab85457188c2142693c -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-abstract_algebra-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | e35d1eeb356ac1084d4e9773f028cb3c81ba1c6e5574d598ac4a78aa467cd797 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-business_ethics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b3b27e9dbad587377d3c8cab1072782de883e245da93a563bd8b3099017b1fc0 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-clinical_knowledge-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | fbcb7ce507e0675d811e71e10a67c8d05a6605e29036f46776e04a6588cefbda -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-college_biology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | c29e4e67ff91af29b9434884874414d1b1b32ccc32903c6b1639469b19907419 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-college_chemistry-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 044752b21540db95118b8cbe7e75c4c9b8758e27df56543deaeadec7f749a28d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-college_mathematics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | e9fe80752686527281f834d2397875b4580581434b94799f9de6aaa450bd73ff -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-college_medicine-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | dd6e0a9be1407890e9f8cd4434fb6aa4752ab3d2473837fd465ad99f60ad685e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-college_physics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 704a7671ef981fb95594782bc446dd632e87ebdbe89436a0603b714fb5786c75 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-computer_security-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a8a1892d1906cc3e7ffd321043f0a60f3b8b69ef76e5c6ff03c6ea41dc87d0cb -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-conceptual_physics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 622f191ccfc7a597d99f39897ebe3f95a9ddce0e662fcfb411aa554b289bb355 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_biology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d4dc051f37a49dc75c218741e87bc826fd44f31ee1309b55e0f33bd191c1bc78 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_physics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | dae59e82d3d4d8dec82239d9620b72cc47bb6efbe2f1c2f9b9d23e849c9c5e32 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-human_sexuality-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4b07922fa1d549b655c21440b13d869263ce7dd9771d8147c450f11c91d26c10 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-international_law-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ea9b2cefd27959db564168f6ad1169a5eaa012fc5a5d5b8faf9e34d94e335dc1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-logical_fallacies-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2e9449dd803f9e2334dc562d9f04031fd013ed36b883b44ab500533a5dbbface -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-machine_learning-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7a7138821a66ef946e427b40344cf7f1a916a2926995a85ef731a3bee40cb7ce -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-medical_genetics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | db6141246889a19dd3f6b9109f314d49c1a70f7a98795858804378b095c4a2fe -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-moral_scenarios-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a8e1882e77728b53c8b86312254d08320d8363fb606d746a8dd145b812f62cf5 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-professional_law-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | c38c9d5d84eeb7a5f3c4a34d6e70d7e15847b3c38f26e4b119c982bb935e118f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-public_relations-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ab70f500cf24e876f6ae6bdc27525a1d6074fa9b6ea97770255d9fc2559b36ff -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-security_studies-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 92dfffe2acf3278256486d3e1cf1edb5a739ad0a54c0f9c67695f7a411ed5f76 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-us_foreign_policy-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a1a338d0083a21054f74d36a296d6bd8e2e457327c0fd630bebcc61ed758044d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-world_religions-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 97a0f68ba30ea3a6ef1db1a2925c964b09ecc54455a0a930da083e52677815bd -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_pubmed-abstracts-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 66436569a43163afb2caf422d32c5f329899e74c49865d4d13881fd465fd9976 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_pubmed-abstracts-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 66436569a43163afb2caf422d32c5f329899e74c49865d4d13881fd465fd9976 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_youtubesubtitles-v0-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 68263c52adc0086011e2220b619983935cabb1cc1f5f9f8ee1a74ab2a7457967 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_youtubesubtitles-v1-loglikelihood_rolling: -------------------------------------------------------------------------------- 1 | 68263c52adc0086011e2220b619983935cabb1cc1f5f9f8ee1a74ab2a7457967 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_existential_there_object_raising-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 63567712076256f373131971676c1c6d711efef73cd0e4de3cc639bc631a2413 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_existential_there_quantifiers_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d77594382e6d9af31a8b8ef00ba1ef6c29d6be6d0ddb7a9c27ef25ace654e05a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_existential_there_quantifiers_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6e6add7baff4217f383425bef58288202018e041b24084edcaa5df8af08f820c -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_irregular_past_participle_verbs-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 63ec733873f94ace71cb34112d1c3cd5bb768c26b975fb90acc9b8ba3f4e938e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_left_branch_island_echo_question-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 9852b38612db8c6adf938a5d8a7a9e5ce9e655259d6cc806b142506fcaff0ed4 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_sentential_negation_npi_scope-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 32fcbd0a1c6e664af2751bad552587b5ca3911973b07f4fb2cf0a2acd3de5349 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_vs_that_no_gap_long_distance-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a142cc2a6fcd93230b650927b07367cad957b8f3f42cb4072151da53dea301df -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_english_sexual_orientation-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | e754a309296b157677dfba6e6feef983d1ce38dd0169ae726265621a7b573163 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_french_physical_appearance-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ea61eaad64e9292790d4bbef955ffeebed7a595de098bc5ac726a6e51f27f9af -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_french_sexual_orientation-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 2ce823fdb93d325aa8fb40db5d335b093b4b69792763532d940a752440ee3a76 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-college_computer_science-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 4ea26ad780290429ac5a3317559c154848d662bd40532c966458ba6f2a32d0a3 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-electrical_engineering-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | b9b5d8b8bb02696302ec6bc2a99bf987a5504d3bae0e529d2c8f263538c97518 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-elementary_mathematics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6b21f5cd5606268421a667152ec989424b66905c02adbab8d4ff6bb9d21b77d1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_chemistry-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f4f338e45415c4b5ee7f1d249155bcd910c8401bd1436760a5ec61cb6bb211b6 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_geography-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | add45970ea3865be7c7a31f788a835949f6937ac73f699b122ca56a3431e95f8 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_mathematics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ab368d16fc4648ad27940f71abd266366663f51db612f732a0b9b0eea28de9f8 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_psychology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 0e4c8d13806d3696167e40544d2d114c557c10c74bc61fcb9c51bbfced0266ef -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_statistics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 33d1d6eaaa2c3a944bf49d3f220a4efc328d7c3b3465b7cec40ae36d8984b75f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_us_history-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8c65c1a28330dd001d395ac11f1bb80c3b33f5935f503e74067aef6e9e1d9d9b -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-professional_accounting-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 847418f7b22cd9b499e95fd73c40a2fbc40076895280cc2c560199c0c4c4f433 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-professional_medicine-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7a30599858398169cde61430c18efdd7fb4dcd09c34aa9baba70f0f8cf17a9f1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-professional_psychology-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 92a5fad6e9ec700f84946faeccd399dda3569fb71837c9fb0c5c87f5ec29c43e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_algebra-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_algebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_algebra": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_algebra-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_algebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_algebra": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_precalc-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_precalc": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_precalc": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_precalc-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_precalc": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_precalc": 1}} -------------------------------------------------------------------------------- /bigcode-evaluation-harness/bigcode_eval/tasks/custom_metrics/multiple_metrics/safe_subprocess/evil_programs/block_on_inputs.py: -------------------------------------------------------------------------------- 1 | while True: 2 | input() 3 | -------------------------------------------------------------------------------- /evaluation-harness/docs/img/fewshot_example_gpt3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/docs/img/fewshot_example_gpt3.png -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/anli_r1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"anli_r1": {"acc": 0.334, "acc_stderr": 0.014922019523732967}}, "versions": {"anli_r1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/anli_r2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"anli_r2": {"acc": 0.356, "acc_stderr": 0.015149042659306628}}, "versions": {"anli_r2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_irregular_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7fab9f02e71a224ae7931aa77f8a9a61d887a7480756adc965d4746e97fb04a5 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_irregular_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ddb24ddfaebe076b3aa7107937d71bf5f4503a78283bc889e39200368603681e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_with_adj_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 95acb74fac7d57ae2c9d208361a5f8ad36b0b19a055f02e648ed8e99505f4b43 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_distractor_agreement_relational_noun-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 8aab641bd5933f84f46a14f5c1208a3c855cace7e67b44abcd5aff8fec96717d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_distractor_agreement_relative_clause-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | bf78e2b53c0f3531303c668c96bd3897a0a35e960da37439e63724ecba4e371a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_existential_there_subject_raising-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 9b324b28ae3e1b5d49ecf4b7b2a16c7bbc8ff38d000cf216fab75df633da2084 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_irregular_past_participle_adjectives-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 47c56f336df11924d8b97feb46339ce55bea4b216b6fd13946cc999ea36a4a95 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_left_branch_island_simple_question-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 6cb36bbdae7754f8832f50872c3dd511ce12547e00fa0771deb747be3355eb85 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_matrix_question_npi_licensor_present-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | a3a702a3335c79b02b36caf37c68069050c2a8a3a03c3610c09afc39d2b83fb1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_vs_that_with_gap_long_distance-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | eed67491bdf493a1dad8f1d9766bc7bd0e79946365b833c0f7eb81ac998e3dca -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/coqa-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"coqa": {"em": 0.0, "em_stderr": 0.0, "f1": 0.0, "f1_stderr": 0.0}}, "versions": {"coqa": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/coqa-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"coqa": {"em": 0.0, "em_stderr": 0.0, "f1": 0.0, "f1_stderr": 0.0}}, "versions": {"coqa": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_english_physical_appearance-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d1823f5038afafa7a5338e42531720480c8ccf4e177789526caf294d52d56e89 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/cycle_letters-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"cycle_letters": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"cycle_letters": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/drop-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"drop": {"em": 0.0, "em_stderr": 0.0, "f1": 0.0, "f1_stderr": 0.0}}, "versions": {"drop": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/drop-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"drop": {"em": 0.0, "em_stderr": 0.0, "f1": 0.0, "f1_stderr": 0.0}}, "versions": {"drop": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_computer_science-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 870d5a6300c527077aaf6baa3e750e75fa840b41657cf82549f39b768b14862d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_european_history-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | d8070e113be9d420fef5578cb69c70df4ea5118f9b18553023fd9efd5ff0b7f4 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_macroeconomics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ce4faae2fb6628caa48f6fc74cbc848880db49e6ff51079392778a2322bcefef -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_microeconomics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 513b998585ebc1ebdefca6435b7c84fd73dc36fc80321a22503467f04efed23e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_world_history-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 1c8b994bd9a63ec874fc8d0e3a27077118b7adc472306b2fd6c55635a78b9d52 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_geometry-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_geometry": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_geometry": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_geometry-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_geometry": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_geometry": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/rte-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"rte": {"acc": 0.5379061371841155, "acc_stderr": 0.030009848912529117}}, "versions": {"rte": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/sst-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"sst": {"acc": 0.5172018348623854, "acc_stderr": 0.016931824425903734}}, "versions": {"sst": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wic-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wic": {"acc": 0.49216300940438873, "acc_stderr": 0.01980828765781383}}, "versions": {"wic": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wsc-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wsc": {"acc": 0.5480769230769231, "acc_stderr": 0.049038186969314335}}, "versions": {"wsc": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_1dc-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_1dc": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_1dc": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_2da-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_2da": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_2da": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_2dm-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_2dm": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_2dm": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_2ds-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_2ds": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_2ds": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_3da-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_3da": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_3da": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_3ds-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_3ds": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_3ds": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_4da-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_4da": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_4da": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_4ds-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_4ds": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_4ds": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_5da-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_5da": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_5da": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arithmetic_5ds-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arithmetic_5ds": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"arithmetic_5ds": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_with_adjective_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 007c47e5fbf88119c5180feef75e1345d448e56adcd4c7ab2d52fb8d67350d34 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_irregular_plural_subject_verb_agreement_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7084358b1b7dd7fb5ead1a58f4b499d6f7610eca897bfac25a986d0f9a91aa5d -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_irregular_plural_subject_verb_agreement_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 9534751f83a86b6cbe1fb12fb9feb827b0b7836a663108928b4ecc1d70b08871 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_regular_plural_subject_verb_agreement_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 5bc0441f31e32443cf761bca6e961d504e1e84b15aa4e1d79e5c8ed5b4c2aa3a -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_regular_plural_subject_verb_agreement_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | f69d9891f59872538962221fccc425b07df7cfbd83cdc546ce83e6b0e9a93f7c -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_sentential_negation_npi_licensor_present-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | e6666c5657215ff4bfd646b8ee3ae6df956e71c0be9ab1c287fb1b68291dd0d1 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_questions_subject_gap_long_distance-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 37483dfda688b62ad27161c9fc1e1e7710c5a6e6a7cd3474df119bcafd30e97f -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/boolq-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"boolq": {"acc": 0.5048929663608562, "acc_stderr": 0.00874463623355505}}, "versions": {"boolq": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/boolq-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"boolq": {"acc": 0.5048929663608562, "acc_stderr": 0.00874463623355505}}, "versions": {"boolq": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/cola-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"cola": {"mcc": -0.04538802810223175, "mcc_stderr": 0.023100371589225246}}, "versions": {"cola": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_num_theory-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_num_theory": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_num_theory": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_num_theory-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_num_theory": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_num_theory": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_prealgebra-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_prealgebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_prealgebra": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_prealgebra-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_prealgebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_prealgebra": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mc_taco-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"mc_taco": {"em": 0.07732732732732733, "f1": 0.41600515965511614}}, "versions": {"mc_taco": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mnli-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"mnli": {"acc": 0.32868059093224655, "acc_stderr": 0.004741640290753859}}, "versions": {"mnli": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pubmedqa-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pubmedqa": {"acc": 0.324, "acc_stderr": 0.01480686473373886}}, "versions": {"pubmedqa": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/qnli-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"qnli": {"acc": 0.5108914515833791, "acc_stderr": 0.00676380528502966}}, "versions": {"qnli": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/race-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"race": {"acc": 0.23253588516746412, "acc_stderr": 0.013074460615265295}}, "versions": {"race": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/reversed_words-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"reversed_words": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"reversed_words": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wnli-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wnli": {"acc": 0.3380281690140845, "acc_stderr": 0.05653887739133514}}, "versions": {"wnli": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wnli-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wnli": {"acc": 0.5633802816901409, "acc_stderr": 0.0592793555841297}}, "versions": {"wnli": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_with_adj_irregular_1-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ad61c619aa79433d02f1aeacde2ab87291fd5d5c370032c24d41c4f0065ed1f9 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_with_adj_irregular_2-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | ccc64b4d5e80c081d5161aae5828212ba49d277ca8c5a4281f181744727a6a99 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_government_and_politics-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 11f40d8f48ba5cd739e21d54c3c04d3761f81df5cb7ddd77df868d24ced44b49 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/random_insertion-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"random_insertion": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"random_insertion": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wsc273-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wsc273": {"acc": 0.5164835164835165, "acc_stderr": 0.0303004740355766}}, "versions": {"wsc273": 0}} -------------------------------------------------------------------------------- /bigcode-evaluation-harness/bigcode_eval/tasks/custom_metrics/multiple_metrics/safe_subprocess/evil_programs/fork_bomb.py: -------------------------------------------------------------------------------- 1 | import os 2 | 3 | while True: 4 | os.fork() 5 | -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/anli_r3-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"anli_r3": {"acc": 0.31916666666666665, "acc_stderr": 0.01346230971200514}}, "versions": {"anli_r3": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_coordinate_structure_constraint_complex_left_branch-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 7e1cc5b9f71abfbe56c4bdf343a1e5632785b66a986b8e904a41ed8f45a2c33e -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_coordinate_structure_constraint_object_extraction-v0-loglikelihood: -------------------------------------------------------------------------------- 1 | 23ddafdff7b1ebe331b146e23b2c21aa109fe57aa1ce8ca201a0d239fcbdd166 -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/multirc-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"multirc": {"acc": 0.07450157397691501, "acc_stderr": 0.008510441526175931}}, "versions": {"multirc": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/multirc-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"multirc": {"acc": 0.046169989506820566, "acc_stderr": 0.006801377886208738}}, "versions": {"multirc": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/ethics_cm-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"ethics_cm": {"acc": 0.49987129987129986, "acc_stderr": 0.008022881531793336}}, "versions": {"ethics_cm": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/winogrande-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"winogrande": {"acc": 0.516179952644041, "acc_stderr": 0.014045126130978606}}, "versions": {"winogrande": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_causative-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_causative": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_causative": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_inchoative-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_inchoative": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_inchoative": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_passive_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_passive_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_passive_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_passive_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_passive_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_passive_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_transitive-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_transitive": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_transitive": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_island-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_wh_island": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_wh_island": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/cb-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"cb": {"acc": 0.3392857142857143, "acc_stderr": 0.06384226561930825, "f1": 0.2819143819143819}}, "versions": {"cb": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/cb-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"cb": {"acc": 0.3392857142857143, "acc_stderr": 0.06384226561930825, "f1": 0.2819143819143819}}, "versions": {"cb": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_counting_and_prob-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_counting_and_prob": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_counting_and_prob": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_counting_and_prob-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_counting_and_prob": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_counting_and_prob": 1}} -------------------------------------------------------------------------------- /bigcode-evaluation-harness/bigcode_eval/tasks/custom_metrics/multiple_metrics/safe_subprocess/evil_programs/sleep_forever.py: -------------------------------------------------------------------------------- 1 | import time 2 | 3 | while True: 4 | time.sleep(60) 5 | -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_intransitive-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_intransitive": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_intransitive": 0}} -------------------------------------------------------------------------------- /bigcode-evaluation-harness/bigcode_eval/tasks/custom_metrics/multiple_metrics/safe_subprocess/evil_programs/unbounded_output.py: -------------------------------------------------------------------------------- 1 | b = True 2 | while True: 3 | print(b) 4 | b = not b 5 | -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_drop_argument-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_drop_argument": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_drop_argument": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_npi_present_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_npi_present_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_npi_present_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_npi_present_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_npi_present_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_npi_present_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_intermediate_algebra-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_intermediate_algebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_intermediate_algebra": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/math_intermediate_algebra-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"math_intermediate_algebra": {"acc": 0.0, "acc_stderr": 0.0}}, "versions": {"math_intermediate_algebra": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_adjunct_island-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_adjunct_island": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_adjunct_island": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_only_npi_scope-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_only_npi_scope": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_only_npi_scope": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mnli_mismatched-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"mnli_mismatched": {"acc": 0.3360455655004068, "acc_stderr": 0.004763973908606819}}, "versions": {"mnli_mismatched": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_complex_NP_island-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_complex_NP_island": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_complex_NP_island": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_ellipsis_n_bar_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_ellipsis_n_bar_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_ellipsis_n_bar_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_ellipsis_n_bar_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_ellipsis_n_bar_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_ellipsis_n_bar_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_vs_that_no_gap-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_wh_vs_that_no_gap": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_wh_vs_that_no_gap": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada": 0}} -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | datasets 2 | deepspeed 3 | einops 4 | einops-exts 5 | huggingface-hub 6 | pandas 7 | pytorch-lightning 8 | sentencepiece 9 | torchinfo 10 | transformers==4.37.2 11 | wandb 12 | -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_case_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_principle_A_case_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_principle_A_case_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_case_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_principle_A_case_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_principle_A_case_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_tough_vs_raising_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_tough_vs_raising_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_tough_vs_raising_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_tough_vs_raising_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_tough_vs_raising_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_tough_vs_raising_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/sciq-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"sciq": {"acc": 0.234, "acc_norm": 0.239, "acc_norm_stderr": 0.01349300044693758, "acc_stderr": 0.01339490288966001}}, "versions": {"sciq": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_domain_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_principle_A_domain_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_principle_A_domain_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_domain_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_principle_A_domain_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_principle_A_domain_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_domain_3-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_principle_A_domain_3": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_principle_A_domain_3": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_vs_that_with_gap-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_wh_vs_that_with_gap": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_wh_vs_that_with_gap": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/ethics_utilitarianism-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"ethics_utilitarianism": {"acc": 0.49771214642262895, "acc_stderr": 0.007211546310787838}}, "versions": {"ethics_utilitarianism": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_animate_subject_trans-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_animate_subject_trans": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_animate_subject_trans": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_c_command-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_principle_A_c_command": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_principle_A_c_command": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/ethics_virtue-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"ethics_virtue": {"acc": 0.5035175879396985, "acc_stderr": 0.0070893491553555765, "em": 0.036180904522613064}}, "versions": {"ethics_virtue": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/record-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"record": {"em": 0.1521, "em_stderr": 0.0035913575128186616, "f1": 0.1581870634920636, "f1_stderr": 0.0036146895141474576}}, "versions": {"record": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-ta-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-en-ta": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.0, "chrf_stderr": 0.0, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-ta": 0}} -------------------------------------------------------------------------------- /bigcode-evaluation-harness/requirements.txt: -------------------------------------------------------------------------------- 1 | transformers>=4.25.1 2 | accelerate>=0.13.2 3 | datasets>=2.6.1 4 | evaluate>=0.3.0 5 | pyext==0.7 6 | mosestokenizer==1.0.0 7 | huggingface_hub>=0.11.1 8 | fsspec<2023.10.0 9 | -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_animate_subject_passive-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_animate_subject_passive": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_animate_subject_passive": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_questions_object_gap-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_wh_questions_object_gap": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_wh_questions_object_gap": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/ethics_justice-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"ethics_justice": {"acc": 0.49556213017751477, "acc_stderr": 0.009616784279885177, "em": 0.057692307692307696}}, "versions": {"ethics_justice": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/iwslt17-en-ar-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"iwslt17-en-ar": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.0, "chrf_stderr": 0.0, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"iwslt17-en-ar": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_cloze-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_cloze": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_cloze": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_mt_de-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_mt_de": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_mt_de": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_mt_en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_mt_en": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_mt_en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_mt_es-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_mt_es": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_mt_es": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_mt_fr-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_mt_fr": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_mt_fr": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_mt_it-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_mt_it": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_mt_it": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_openai": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_openai": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mrpc-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"mrpc": {"acc": 0.5392156862745098, "acc_stderr": 0.024707732873723128, "f1": 0.5982905982905982, "f1_stderr": 0.028928325246283727}}, "versions": {"mrpc": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/qqp-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"qqp": {"acc": 0.49782339846648527, "acc_stderr": 0.0024866770696239894, "f1": 0.42322661288031593, "f1_stderr": 0.002695903831328166}}, "versions": {"qqp": 0}} -------------------------------------------------------------------------------- /bigcode-evaluation-harness/bigcode_eval/tasks/custom_metrics/multiple_metrics/safe_subprocess/evil_programs/fork_once.py: -------------------------------------------------------------------------------- 1 | import os 2 | import time 3 | 4 | if os.fork() == 0: 5 | while True: 6 | time.sleep(60) 7 | -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_anaphor_gender_agreement-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_anaphor_gender_agreement": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_anaphor_gender_agreement": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_anaphor_number_agreement-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_anaphor_number_agreement": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_anaphor_number_agreement": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_only_npi_licensor_present-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_only_npi_licensor_present": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_only_npi_licensor_present": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_sentential_subject_island-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_sentential_subject_island": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_sentential_subject_island": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_superlative_quantifiers_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_superlative_quantifiers_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_superlative_quantifiers_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_superlative_quantifiers_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_superlative_quantifiers_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_superlative_quantifiers_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_questions_subject_gap-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_wh_questions_subject_gap": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_wh_questions_subject_gap": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/ethics_deontology-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"ethics_deontology": {"acc": 0.503615127919911, "acc_stderr": 0.008338908432085105, "em": 0.07119021134593993}}, "versions": {"ethics_deontology": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_standard-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_standard": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_standard": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/openbookqa-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"openbookqa": {"acc": 0.214, "acc_norm": 0.276, "acc_norm_stderr": 0.020011219298073517, "acc_stderr": 0.018359797502387046}}, "versions": {"openbookqa": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wikitext-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wikitext": {"bits_per_byte": 2.219817611605802e-05, "byte_perplexity": 1.0000221984224973, "word_perplexity": 1.000118710696617}}, "versions": {"wikitext": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wikitext-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wikitext": {"bits_per_byte": 3.202519859941674e-05, "byte_perplexity": 1.0000221984224973, "word_perplexity": 1.000118710696617}}, "versions": {"wikitext": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_determiner_noun_agreement_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_determiner_noun_agreement_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_expletive_it_object_raising-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_expletive_it_object_raising": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_expletive_it_object_raising": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_principle_A_reconstruction-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_principle_A_reconstruction": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_principle_A_reconstruction": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_arxiv-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_arxiv": {"bits_per_byte": 1.55095665856779e-05, "byte_perplexity": 1.0000107504701365, "word_perplexity": 1.0000819333090385}}, "versions": {"pile_arxiv": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_enron-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_enron": {"bits_per_byte": 0.0003163902828673244, "byte_perplexity": 1.000316440339552, "word_perplexity": 1.00224668051869}}, "versions": {"pile_enron": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_enron-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_enron": {"bits_per_byte": 0.0004564546920781453, "byte_perplexity": 1.000316440339552, "word_perplexity": 1.00224668051869}}, "versions": {"pile_enron": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_uspto-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_uspto": {"bits_per_byte": 0.00012062434384130924, "byte_perplexity": 1.00012063161925, "word_perplexity": 1.0007716198916954}}, "versions": {"pile_uspto": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_uspto-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_uspto": {"bits_per_byte": 0.000174024142670342, "byte_perplexity": 1.00012063161925, "word_perplexity": 1.0007716198916954}}, "versions": {"pile_uspto": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/piqa-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"piqa": {"acc": 0.514145810663765, "acc_norm": 0.5114254624591947, "acc_norm_stderr": 0.01166277802645167, "acc_stderr": 0.011661154475524836}}, "versions": {"piqa": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/qa4mre_2012-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"qa4mre_2012": {"acc": 0.15625, "acc_norm": 0.16875, "acc_norm_stderr": 0.029702236908328808, "acc_stderr": 0.02879508360159146}}, "versions": {"qa4mre_2012": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_arxiv-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_arxiv": {"bits_per_byte": 1.0750412350569374e-05, "byte_perplexity": 1.0000107504701365, "word_perplexity": 1.0000819333090385}}, "versions": {"pile_arxiv": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_books3-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_books3": {"bits_per_byte": 8.942486206275221e-07, "byte_perplexity": 1.0000008942490204, "word_perplexity": 1.0000052870063607}}, "versions": {"pile_books3": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_books3-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_books3": {"bits_per_byte": 1.2901280503011222e-06, "byte_perplexity": 1.0000008942490204, "word_perplexity": 1.0000052870063607}}, "versions": {"pile_books3": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_freelaw-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_freelaw": {"bits_per_byte": 3.16238943008513e-05, "byte_perplexity": 1.0000316243943415, "word_perplexity": 1.000203169094218}}, "versions": {"pile_freelaw": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_github-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_github": {"bits_per_byte": 9.540627613754646e-05, "byte_perplexity": 1.0000954108274611, "word_perplexity": 1.0009643183931227}}, "versions": {"pile_github": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_github-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_github": {"bits_per_byte": 0.00013764216145332133, "byte_perplexity": 1.0000954108274611, "word_perplexity": 1.0009643183931227}}, "versions": {"pile_github": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/prost-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"prost": {"acc": 0.24631725021349274, "acc_norm": 0.2581127241673783, "acc_norm_stderr": 0.00319703079646546, "acc_stderr": 0.003147855968061357}}, "versions": {"prost": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/swag-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"swag": {"acc": 0.2482255323402979, "acc_norm": 0.24882535239428172, "acc_norm_stderr": 0.00305666959496067, "acc_stderr": 0.003054201832644171}}, "versions": {"swag": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_sentential_negation_npi_scope-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_sentential_negation_npi_scope": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_sentential_negation_npi_scope": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/ethics_utilitarianism_original-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"ethics_utilitarianism_original": {"acc": 0.5214226289517471, "acc_stderr": 0.007204999520618661}}, "versions": {"ethics_utilitarianism_original": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/headqa-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"headqa": {"acc": 0.23559445660102116, "acc_norm": 0.25018234865062, "acc_norm_stderr": 0.008272783230806014, "acc_stderr": 0.008105688874297972}}, "versions": {"headqa": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai_cloze-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_openai_cloze": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_openai_cloze": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai_mt_de-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_openai_mt_de": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_openai_mt_de": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai_mt_en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_openai_mt_en": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_openai_mt_en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai_mt_es-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_openai_mt_es": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_openai_mt_es": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai_mt_fr-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_openai_mt_fr": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_openai_mt_fr": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_openai_mt_it-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_openai_mt_it": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_openai_mt_it": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/logiqa-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"logiqa": {"acc": 0.25806451612903225, "acc_norm": 0.2764976958525346, "acc_norm_stderr": 0.017543209075825194, "acc_stderr": 0.017162894755127077}}, "versions": {"logiqa": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mathqa-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"mathqa": {"acc": 0.20770519262981574, "acc_norm": 0.2050251256281407, "acc_norm_stderr": 0.007390619359738901, "acc_stderr": 0.007426217631188539}}, "versions": {"mathqa": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_europarl-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_europarl": {"bits_per_byte": 8.648858203555344e-06, "byte_perplexity": 1.000008648895605, "word_perplexity": 1.000063506523818}}, "versions": {"pile_europarl": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_europarl-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_europarl": {"bits_per_byte": 1.2477664839621123e-05, "byte_perplexity": 1.000008648895605, "word_perplexity": 1.000063506523818}}, "versions": {"pile_europarl": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_freelaw-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_freelaw": {"bits_per_byte": 4.5623635481434923e-05, "byte_perplexity": 1.0000316243943415, "word_perplexity": 1.000203169094218}}, "versions": {"pile_freelaw": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_pile-cc-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_pile-cc": {"bits_per_byte": 0.00011234131907228174, "byte_perplexity": 1.0001123476295946, "word_perplexity": 1.0006738958554477}}, "versions": {"pile_pile-cc": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_pile-cc-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_pile-cc": {"bits_per_byte": 0.0001620742639125056, "byte_perplexity": 1.0001123476295946, "word_perplexity": 1.0006738958554477}}, "versions": {"pile_pile-cc": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/qa4mre_2011-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"qa4mre_2011": {"acc": 0.225, "acc_norm": 0.23333333333333334, "acc_norm_stderr": 0.03877199986918664, "acc_stderr": 0.0382797091741014}}, "versions": {"qa4mre_2011": 0}} -------------------------------------------------------------------------------- /bigcode-evaluation-harness/bigcode_eval/tasks/custom_metrics/multiple_metrics/safe_subprocess/evil_programs/close_outputs.py: -------------------------------------------------------------------------------- 1 | import sys 2 | 3 | print("This is the end") 4 | sys.stdout.close() 5 | sys.stderr.close() 6 | while True: 7 | pass 8 | -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arc_easy-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arc_easy": {"acc": 0.2474747474747475, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.008772796145221907, "acc_stderr": 0.008855114414834707}}, "versions": {"arc_easy": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_existential_there_object_raising-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_existential_there_object_raising": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_existential_there_object_raising": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_existential_there_quantifiers_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_existential_there_quantifiers_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_existential_there_quantifiers_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_existential_there_quantifiers_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_existential_there_quantifiers_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_existential_there_quantifiers_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_irregular_past_participle_verbs-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_irregular_past_participle_verbs": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_irregular_past_participle_verbs": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_left_branch_island_echo_question-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_left_branch_island_echo_question": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_left_branch_island_echo_question": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_vs_that_no_gap_long_distance-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_wh_vs_that_no_gap_long_distance": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_wh_vs_that_no_gap_long_distance": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/headqa_es-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"headqa_es": {"acc": 0.23559445660102116, "acc_norm": 0.25018234865062, "acc_norm_stderr": 0.008272783230806014, "acc_stderr": 0.008105688874297972}}, "versions": {"headqa_es": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/lambada_standard_cloze-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"lambada_standard_cloze": {"acc": 0.0, "acc_stderr": 0.0, "ppl": 1.6479047769869253, "ppl_stderr": 0.006497321146240192}}, "versions": {"lambada_standard_cloze": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_gutenberg-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_gutenberg": {"bits_per_byte": 1.2443606332351536e-06, "byte_perplexity": 1.0000012443614075, "word_perplexity": 1.0000072174665404}}, "versions": {"pile_gutenberg": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_gutenberg-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_gutenberg": {"bits_per_byte": 1.7952329146458065e-06, "byte_perplexity": 1.0000012443614075, "word_perplexity": 1.0000072174665404}}, "versions": {"pile_gutenberg": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_wikipedia-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_wikipedia": {"bits_per_byte": 0.00016834722287561703, "byte_perplexity": 1.0001683613940646, "word_perplexity": 1.001084677949439}}, "versions": {"pile_wikipedia": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_wikipedia-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_wikipedia": {"bits_per_byte": 0.00024287370359008176, "byte_perplexity": 1.0001683613940646, "word_perplexity": 1.001084677949439}}, "versions": {"pile_wikipedia": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/toxigen-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"toxigen": {"acc": 0.5053191489361702, "acc_norm": 0.46808510638297873, "acc_norm_stderr": 0.016283609940023203, "acc_stderr": 0.016315959984563776}}, "versions": {"toxigen": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_existential_there_subject_raising-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_existential_there_subject_raising": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_existential_there_subject_raising": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_vs_that_with_gap_long_distance-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_wh_vs_that_with_gap_long_distance": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_wh_vs_that_with_gap_long_distance": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/headqa_en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"headqa_en": {"acc": 0.23559445660102116, "acc_norm": 0.2447118891320204, "acc_norm_stderr": 0.008211629406841468, "acc_stderr": 0.008105688874297972}}, "versions": {"headqa_en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hellaswag-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hellaswag": {"acc": 0.24965146385182235, "acc_norm": 0.24756024696275641, "acc_norm_stderr": 0.004307128573285236, "acc_stderr": 0.004319267432460666}}, "versions": {"hellaswag": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_bookcorpus2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_bookcorpus2": {"bits_per_byte": 1.1631037706429144e-06, "byte_perplexity": 1.000001163104447, "word_perplexity": 1.0000066499426599}}, "versions": {"pile_bookcorpus2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_bookcorpus2-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_bookcorpus2": {"bits_per_byte": 1.6780040419457868e-06, "byte_perplexity": 1.000001163104447, "word_perplexity": 1.0000066499426599}}, "versions": {"pile_bookcorpus2": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_hackernews-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_hackernews": {"bits_per_byte": 0.00010170276359193358, "byte_perplexity": 1.0001017079354932, "word_perplexity": 1.0006273924348839}}, "versions": {"pile_hackernews": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_hackernews-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_hackernews": {"bits_per_byte": 0.00014672607267878518, "byte_perplexity": 1.0001017079354932, "word_perplexity": 1.0006273924348839}}, "versions": {"pile_hackernews": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_openwebtext2-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_openwebtext2": {"bits_per_byte": 0.000184802319359215, "byte_perplexity": 1.000128103411166, "word_perplexity": 1.0007951516532847}}, "versions": {"pile_openwebtext2": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_philpapers-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_philpapers": {"bits_per_byte": 6.241575895982095e-06, "byte_perplexity": 1.0000062415953748, "word_perplexity": 1.0000409888564146}}, "versions": {"pile_philpapers": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_philpapers-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_philpapers": {"bits_per_byte": 9.004690592465457e-06, "byte_perplexity": 1.0000062415953748, "word_perplexity": 1.0000409888564146}}, "versions": {"pile_philpapers": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_ubuntu-irc-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_ubuntu-irc": {"bits_per_byte": 1.6298315496830533e-06, "byte_perplexity": 1.0000016298328778, "word_perplexity": 1.0000108866656874}}, "versions": {"pile_ubuntu-irc": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_ubuntu-irc-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_ubuntu-irc": {"bits_per_byte": 2.3513498942121155e-06, "byte_perplexity": 1.0000016298328778, "word_perplexity": 1.0000108866656874}}, "versions": {"pile_ubuntu-irc": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/truthfulqa_mc-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"truthfulqa_mc": {"mc1": 0.2141982864137087, "mc1_stderr": 0.01436214815569045, "mc2": 0.465436996173817, "mc2_stderr": 0.0048422530880316405}}, "versions": {"truthfulqa_mc": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/truthfulqa_mc-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"truthfulqa_mc": {"mc1": 0.23255813953488372, "mc1_stderr": 0.01478915753108052, "mc2": 0.4462325560722362, "mc2_stderr": 0.004986523944692003}}, "versions": {"truthfulqa_mc": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt14-en-fr-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt14-en-fr": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.011284118461117099, "chrf_stderr": 7.340651275964445e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt14-en-fr": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt14-fr-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt14-fr-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.01275083169440515, "chrf_stderr": 8.45474998563806e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt14-fr-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt16-de-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt16-de-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.013700416764482968, "chrf_stderr": 0.00016071651360909355, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt16-de-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt16-en-de-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt16-en-de": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.010909486120840577, "chrf_stderr": 0.000122611124711072, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt16-en-de": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt16-en-ro-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt16-en-ro": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.012004814364156886, "chrf_stderr": 6.424423961332661e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt16-en-ro": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt16-ro-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt16-ro-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.01262029828861831, "chrf_stderr": 0.00014507496111350828, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt16-ro-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-cs-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-cs-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.006212086270964023, "chrf_stderr": 0.0001119165191795531, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-cs-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-de-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-de-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.006703243310670055, "chrf_stderr": 0.0001292711927988445, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-de-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-de-fr-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-de-fr": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.011897164096796364, "chrf_stderr": 0.00010158164726118333, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-de-fr": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-cs-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-en-cs": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.009879653442394573, "chrf_stderr": 8.210293331159994e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-cs": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-de-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-en-de": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.007148103038872972, "chrf_stderr": 9.594096858911254e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-de": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-iu-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-en-iu": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.00011803644548940443, "chrf_stderr": 2.175287038623409e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-iu": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-km-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-en-km": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 1.9008351315007364e-05, "chrf_stderr": 7.136657625458525e-06, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-km": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-pl-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-en-pl": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.009006977773147825, "chrf_stderr": 0.00023387733367766675, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-pl": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-ps-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-en-ps": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 2.1193813610582323e-06, "chrf_stderr": 2.113911466119111e-06, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-ps": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-ru-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-en-ru": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.0007327811114614671, "chrf_stderr": 4.43155903515048e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-ru": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-zh-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-en-zh": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.00014170297316825535, "chrf_stderr": 6.590669847391838e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-zh": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-zh-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-en-zh": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.00014170297316825535, "chrf_stderr": 6.590669847391838e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-zh": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-fr-de-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-fr-de": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.01143193767396364, "chrf_stderr": 0.00012555271954563658, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-fr-de": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-iu-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-iu-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.012204628007572778, "chrf_stderr": 8.944407532175802e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-iu-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-ja-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-ja-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.010703148854351403, "chrf_stderr": 0.00022242113108130186, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-ja-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-km-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-km-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.015142474534585969, "chrf_stderr": 0.0001518735048829897, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-km-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-pl-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-pl-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.01353367757716276, "chrf_stderr": 0.00018386199249976465, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-pl-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-ps-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-ps-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.015192865365105723, "chrf_stderr": 0.00011334541381539086, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-ps-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-ru-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-ru-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.013344639906399232, "chrf_stderr": 7.583552652374546e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-ru-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-ta-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-ta-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.013841110664859798, "chrf_stderr": 0.00018476696850880766, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-ta-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-zh-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-zh-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.008438201290981157, "chrf_stderr": 0.0001109053964076822, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-zh-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_left_branch_island_simple_question-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_left_branch_island_simple_question": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_left_branch_island_simple_question": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/iwslt17-ar-en-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"iwslt17-ar-en": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 0.015049895477752772, "chrf_stderr": 0.0002940315671893584, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"iwslt17-ar-en": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_nih-exporter-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_nih-exporter": {"bits_per_byte": 0.00024394433346975716, "byte_perplexity": 1.0002439740903082, "word_perplexity": 1.0016712202288802}}, "versions": {"pile_nih-exporter": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_nih-exporter-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_nih-exporter": {"bits_per_byte": 0.00035193728014978225, "byte_perplexity": 1.0002439740903082, "word_perplexity": 1.0016712202288802}}, "versions": {"pile_nih-exporter": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_openwebtext2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_openwebtext2": {"bits_per_byte": 0.00012809520662477846, "byte_perplexity": 1.000128103411166, "word_perplexity": 1.0007951516532847}}, "versions": {"pile_openwebtext2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_stackexchange-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_stackexchange": {"bits_per_byte": 0.0002288815898835956, "byte_perplexity": 1.0002289077852733, "word_perplexity": 1.0016993562258851}}, "versions": {"pile_stackexchange": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_stackexchange-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_stackexchange": {"bits_per_byte": 0.0003302063346758449, "byte_perplexity": 1.0002289077852733, "word_perplexity": 1.0016993562258851}}, "versions": {"pile_stackexchange": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/qa4mre_2013-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"qa4mre_2013": {"acc": 0.18309859154929578, "acc_norm": 0.22183098591549297, "acc_norm_stderr": 0.02469760575535269, "acc_stderr": 0.022989742475464973}}, "versions": {"qa4mre_2013": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-ja-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-en-ja": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 4.1308658294778584e-05, "chrf_stderr": 2.0456539027807417e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-ja": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/wmt20-en-ja-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"wmt20-en-ja": {"bleu": 0.0, "bleu_stderr": 0.0, "chrf": 4.1305928226819116e-05, "chrf_stderr": 2.0455354158878388e-05, "ter": 1.0, "ter_stderr": 0.0}}, "versions": {"wmt20-en-ja": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/arc_challenge-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"arc_challenge": {"acc": 0.24488054607508533, "acc_norm": 0.2440273037542662, "acc_norm_stderr": 0.012551447627856257, "acc_stderr": 0.012566273985131354}}, "versions": {"arc_challenge": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_irregular_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_determiner_noun_agreement_irregular_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_irregular_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_irregular_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_determiner_noun_agreement_irregular_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_irregular_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_with_adj_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_determiner_noun_agreement_with_adj_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_with_adj_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_distractor_agreement_relational_noun-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_distractor_agreement_relational_noun": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_distractor_agreement_relational_noun": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_distractor_agreement_relative_clause-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_distractor_agreement_relative_clause": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_distractor_agreement_relative_clause": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_irregular_past_participle_adjectives-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_irregular_past_participle_adjectives": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_irregular_past_participle_adjectives": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_matrix_question_npi_licensor_present-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_matrix_question_npi_licensor_present": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_matrix_question_npi_licensor_present": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_dm-mathematics-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_dm-mathematics": {"bits_per_byte": 6.176600873627999e-05, "byte_perplexity": 1.0000617679162955, "word_perplexity": 1.0002875035042451}}, "versions": {"pile_dm-mathematics": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_dm-mathematics-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_dm-mathematics": {"bits_per_byte": 8.910951449933553e-05, "byte_perplexity": 1.0000617679162955, "word_perplexity": 1.0002875035042451}}, "versions": {"pile_dm-mathematics": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_opensubtitles-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_opensubtitles": {"bits_per_byte": 1.5213441136639177e-05, "byte_perplexity": 1.0000152135568616, "word_perplexity": 1.0000856162053249}}, "versions": {"pile_opensubtitles": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_opensubtitles-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_opensubtitles": {"bits_per_byte": 2.1948356082685497e-05, "byte_perplexity": 1.0000152135568616, "word_perplexity": 1.0000856162053249}}, "versions": {"pile_opensubtitles": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_pubmed-central-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_pubmed-central": {"bits_per_byte": 1.5812411832795375e-05, "byte_perplexity": 1.0000158125368497, "word_perplexity": 1.000123107107861}}, "versions": {"pile_pubmed-central": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_pubmed-central-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_pubmed-central": {"bits_per_byte": 2.2812488135667854e-05, "byte_perplexity": 1.0000158125368497, "word_perplexity": 1.000123107107861}}, "versions": {"pile_pubmed-central": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_wh_questions_subject_gap_long_distance-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_wh_questions_subject_gap_long_distance": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_wh_questions_subject_gap_long_distance": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_pubmed-abstracts-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_pubmed-abstracts": {"bits_per_byte": 0.00037553733051528816, "byte_perplexity": 1.0003756078534862, "word_perplexity": 1.0025884332779}}, "versions": {"pile_pubmed-abstracts": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_pubmed-abstracts-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_pubmed-abstracts": {"bits_per_byte": 0.0005417858444030858, "byte_perplexity": 1.0003756078534862, "word_perplexity": 1.0025884332779}}, "versions": {"pile_pubmed-abstracts": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_youtubesubtitles-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_youtubesubtitles": {"bits_per_byte": 2.3447170928931888e-05, "byte_perplexity": 1.000023447445816, "word_perplexity": 1.0001529192262875}}, "versions": {"pile_youtubesubtitles": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/pile_youtubesubtitles-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"pile_youtubesubtitles": {"bits_per_byte": 3.3827117222045906e-05, "byte_perplexity": 1.000023447445816, "word_perplexity": 1.0001529192262875}}, "versions": {"pile_youtubesubtitles": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/squad2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"squad2": {"HasAns_exact": 0.0, "HasAns_f1": 0.0, "NoAns_exact": 0.0, "NoAns_f1": 0.0, "best_exact": 50.07159100480081, "best_f1": 50.07159100480081, "exact": 0.0, "f1": 0.0}}, "versions": {"squad2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/squad2-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"squad2": {"HasAns_exact": 0.0, "HasAns_f1": 0.0, "NoAns_exact": 0.0, "NoAns_f1": 0.0, "best_exact": 50.07159100480081, "best_f1": 50.07159100480081, "exact": 0.0, "f1": 0.0}}, "versions": {"squad2": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_regular_plural_subject_verb_agreement_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_regular_plural_subject_verb_agreement_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_regular_plural_subject_verb_agreement_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_regular_plural_subject_verb_agreement_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_regular_plural_subject_verb_agreement_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_regular_plural_subject_verb_agreement_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_sentential_negation_npi_licensor_present-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_sentential_negation_npi_licensor_present": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_sentential_negation_npi_licensor_present": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-global_facts-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-global_facts": {"acc": 0.23, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816507, "acc_stderr": 0.04229525846816507}}, "versions": {"hendrycksTest-global_facts": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_with_adjective_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_determiner_noun_agreement_with_adjective_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_with_adjective_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_irregular_plural_subject_verb_agreement_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_irregular_plural_subject_verb_agreement_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_irregular_plural_subject_verb_agreement_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_irregular_plural_subject_verb_agreement_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_irregular_plural_subject_verb_agreement_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_irregular_plural_subject_verb_agreement_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/gpt3_test_0deb8e9bde8e8327bbc48157f638ff3ba06b0cd816dad2beb8ad90f7fbe795c7.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/gpt3_test_0deb8e9bde8e8327bbc48157f638ff3ba06b0cd816dad2beb8ad90f7fbe795c7.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/gpt3_test_8025023377febbd8c5f2b9f26705c394ff375d0cad7c89c10fd9b8e1eb66ff1c.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/gpt3_test_8025023377febbd8c5f2b9f26705c394ff375d0cad7c89c10fd9b8e1eb66ff1c.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/gpt3_test_bb2cc49115e88788ed870ad0716eb00b280a885f91c7ed6e1e864435e5e2b6ac.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/gpt3_test_bb2cc49115e88788ed870ad0716eb00b280a885f91c7ed6e1e864435e5e2b6ac.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/gpt3_test_cfd11f555a5a63b6dfa114a55a932e51b724cdd44d4842586b9ce37260bf7aaa.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/gpt3_test_cfd11f555a5a63b6dfa114a55a932e51b724cdd44d4842586b9ce37260bf7aaa.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/gpt3_test_f307d52964c295e2005c5e782b688c24388e0cecadf29f1e6fc7f394236ea9c0.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/gpt3_test_f307d52964c295e2005c5e782b688c24388e0cecadf29f1e6fc7f394236ea9c0.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-abstract_algebra-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-abstract_algebra": {"acc": 0.32, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235, "acc_stderr": 0.04688261722621504}}, "versions": {"hendrycksTest-abstract_algebra": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-anatomy-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-anatomy": {"acc": 0.2222222222222222, "acc_norm": 0.23703703703703705, "acc_norm_stderr": 0.03673731683969506, "acc_stderr": 0.0359144408419697}}, "versions": {"hendrycksTest-anatomy": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-business_ethics-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-business_ethics": {"acc": 0.29, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394, "acc_stderr": 0.045604802157206845}}, "versions": {"hendrycksTest-business_ethics": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-medical_genetics-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-medical_genetics": {"acc": 0.27, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684, "acc_stderr": 0.0446196043338474}}, "versions": {"hendrycksTest-medical_genetics": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-college_chemistry-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-college_chemistry": {"acc": 0.28, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078, "acc_stderr": 0.04512608598542127}}, "versions": {"hendrycksTest-college_chemistry": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-computer_security-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-computer_security": {"acc": 0.24, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394, "acc_stderr": 0.042923469599092816}}, "versions": {"hendrycksTest-computer_security": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-jurisprudence-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-jurisprudence": {"acc": 0.25, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.04489931073591312, "acc_stderr": 0.04186091791394607}}, "versions": {"hendrycksTest-jurisprudence": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-us_foreign_policy-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-us_foreign_policy": {"acc": 0.2, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283, "acc_stderr": 0.040201512610368445}}, "versions": {"hendrycksTest-us_foreign_policy": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-virology-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-virology": {"acc": 0.27710843373493976, "acc_norm": 0.2710843373493976, "acc_norm_stderr": 0.03460579907553027, "acc_stderr": 0.034843315926805875}}, "versions": {"hendrycksTest-virology": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_0a89c2739f9598b4be2674b0a8e43931d7f3f0b696970bcba31f9b52bdf12297.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_0a89c2739f9598b4be2674b0a8e43931d7f3f0b696970bcba31f9b52bdf12297.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_0c1c14571add7903b89e588c8212572b95bb57b334fc0752c89a7e045a5f63ae.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_0c1c14571add7903b89e588c8212572b95bb57b334fc0752c89a7e045a5f63ae.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_3092d07756f3e1d010c07524cc8a2ecba7f0c19f9e39f2aaf2bf440bfe328004.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_3092d07756f3e1d010c07524cc8a2ecba7f0c19f9e39f2aaf2bf440bfe328004.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_434076260b6af3a46b7a5eaceec3306a5872c400a3872f744280b237455a0f8e.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_434076260b6af3a46b7a5eaceec3306a5872c400a3872f744280b237455a0f8e.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_49c47ae40e11f349f2f6b492128188b1b2bc103a421c676ee4b2142a68b43516.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_49c47ae40e11f349f2f6b492128188b1b2bc103a421c676ee4b2142a68b43516.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_4fd8d66a6dad7f602b40e5d7dc298d6fe329299d086a4659743a41f4a4012659.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_4fd8d66a6dad7f602b40e5d7dc298d6fe329299d086a4659743a41f4a4012659.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_51b5302f157cf224f694ccad973f255ae19e9e061d533256bdf75b04e0a917ab.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_51b5302f157cf224f694ccad973f255ae19e9e061d533256bdf75b04e0a917ab.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_6d6c62dd70caaa208712bf766deaf419cfac89538d4ab7745621e339394c0c23.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_6d6c62dd70caaa208712bf766deaf419cfac89538d4ab7745621e339394c0c23.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_7209c4617547bfe17cb9e7f5f735fe35822d650aefdc5fbeeaf0c1724effbe09.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_7209c4617547bfe17cb9e7f5f735fe35822d650aefdc5fbeeaf0c1724effbe09.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_7afdc285388e51094e12645f305328c759574fa3ec9751631025f8ad5ebf9f3e.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_7afdc285388e51094e12645f305328c759574fa3ec9751631025f8ad5ebf9f3e.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_9d5f33dbfe1e254928c89f5ed85e4c010d888065f55a8f1b863bc1eb0340a5f2.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_9d5f33dbfe1e254928c89f5ed85e4c010d888065f55a8f1b863bc1eb0340a5f2.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_abcbcba648d89e5d81a50511a6d24ddeb538de2ffe108c1370dd74ce6ac8038d.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_abcbcba648d89e5d81a50511a6d24ddeb538de2ffe108c1370dd74ce6ac8038d.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_b1cbb29666cce5e31a1e97695858137398a0885ca5d5d98f515404fb6aeb99e7.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_b1cbb29666cce5e31a1e97695858137398a0885ca5d5d98f515404fb6aeb99e7.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_e7ad1e9f52a39e1ddd1e50f3c57ffa4546728dd150a67c0a0ddc8675c04e15d1.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_e7ad1e9f52a39e1ddd1e50f3c57ffa4546728dd150a67c0a0ddc8675c04e15d1.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/textsynth_test_f4bfe4beb605bd52a8ab6be3c9293639e7e2261d98de58159d15ccb83131bf4e.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kaistAI/LangBridge/HEAD/evaluation-harness/tests/testdata/textsynth_test_f4bfe4beb605bd52a8ab6be3c9293639e7e2261d98de58159d15ccb83131bf4e.pkl -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_with_adj_irregular_1-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_determiner_noun_agreement_with_adj_irregular_1": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_with_adj_irregular_1": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_determiner_noun_agreement_with_adj_irregular_2-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_determiner_noun_agreement_with_adj_irregular_2": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_determiner_noun_agreement_with_adj_irregular_2": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-astronomy-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-astronomy": {"acc": 0.2565789473684211, "acc_norm": 0.29605263157894735, "acc_norm_stderr": 0.03715062154998904, "acc_stderr": 0.0355418036802569}}, "versions": {"hendrycksTest-astronomy": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-college_mathematics-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-college_mathematics": {"acc": 0.18, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036844, "acc_stderr": 0.038612291966536955}}, "versions": {"hendrycksTest-college_mathematics": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-marketing-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-marketing": {"acc": 0.2863247863247863, "acc_norm": 0.2905982905982906, "acc_norm_stderr": 0.029745048572674043, "acc_stderr": 0.029614323690456648}}, "versions": {"hendrycksTest-marketing": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-nutrition-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-nutrition": {"acc": 0.24509803921568626, "acc_norm": 0.28104575163398693, "acc_norm_stderr": 0.025738854797818723, "acc_stderr": 0.02463004897982476}}, "versions": {"hendrycksTest-nutrition": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-philosophy-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-philosophy": {"acc": 0.26366559485530544, "acc_norm": 0.2733118971061093, "acc_norm_stderr": 0.02531176597542612, "acc_stderr": 0.02502553850053234}}, "versions": {"hendrycksTest-philosophy": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-sociology-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-sociology": {"acc": 0.23383084577114427, "acc_norm": 0.24875621890547264, "acc_norm_stderr": 0.030567675938916707, "acc_stderr": 0.02992941540834838}}, "versions": {"hendrycksTest-sociology": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mutual_plus-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"mutual_plus": {"mrr": 0.5275583145221953, "mrr_stderr": 0.009940894824430708, "r@1": 0.26297968397291194, "r@1_stderr": 0.01479889176605113, "r@2": 0.5, "r@2_stderr": 0.01680731613632036}}, "versions": {"mutual_plus": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-human_aging-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-human_aging": {"acc": 0.21524663677130046, "acc_norm": 0.17937219730941703, "acc_norm_stderr": 0.025749819569192804, "acc_stderr": 0.02758406660220827}}, "versions": {"hendrycksTest-human_aging": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-management-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-management": {"acc": 0.24271844660194175, "acc_norm": 0.2621359223300971, "acc_norm_stderr": 0.043546310772605956, "acc_stderr": 0.04245022486384495}}, "versions": {"hendrycksTest-management": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-prehistory-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-prehistory": {"acc": 0.2623456790123457, "acc_norm": 0.26851851851851855, "acc_norm_stderr": 0.024659685185967277, "acc_stderr": 0.02447722285613511}}, "versions": {"hendrycksTest-prehistory": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mutual-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"mutual": {"mrr": 0.5023513920240772, "mrr_stderr": 0.009501864812936679, "r@1": 0.22573363431151242, "r@1_stderr": 0.014053085820407457, "r@2": 0.4221218961625282, "r@2_stderr": 0.016602191705517556}}, "versions": {"mutual": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mutual-v1-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"mutual": {"mrr": 0.5023513920240772, "mrr_stderr": 0.009501864812936679, "r@1": 0.22460496613995484, "r@1_stderr": 0.014028122493992806, "r@2": 0.4706546275395034, "r@2_stderr": 0.016778343895001414}}, "versions": {"mutual": 1}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_coordinate_structure_constraint_object_extraction-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_coordinate_structure_constraint_object_extraction": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_coordinate_structure_constraint_object_extraction": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-econometrics-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-econometrics": {"acc": 0.24561403508771928, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.04049339297748142, "acc_stderr": 0.040493392977481425}}, "versions": {"hendrycksTest-econometrics": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-formal_logic-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-formal_logic": {"acc": 0.25396825396825395, "acc_norm": 0.2698412698412698, "acc_norm_stderr": 0.03970158273235172, "acc_stderr": 0.03893259610604674}}, "versions": {"hendrycksTest-formal_logic": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/blimp_coordinate_structure_constraint_complex_left_branch-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"blimp_coordinate_structure_constraint_complex_left_branch": {"acc": 0.485, "acc_stderr": 0.0158121796418149}}, "versions": {"blimp_coordinate_structure_constraint_complex_left_branch": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-college_biology-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-college_biology": {"acc": 0.24305555555555555, "acc_norm": 0.2361111111111111, "acc_norm_stderr": 0.03551446610810826, "acc_stderr": 0.03586879280080341}}, "versions": {"hendrycksTest-college_biology": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-college_computer_science-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-college_computer_science": {"acc": 0.22, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909282, "acc_stderr": 0.041633319989322695}}, "versions": {"hendrycksTest-college_computer_science": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-miscellaneous-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-miscellaneous": {"acc": 0.23499361430395913, "acc_norm": 0.2515964240102171, "acc_norm_stderr": 0.015517322365529622, "acc_stderr": 0.015162024152278445}}, "versions": {"hendrycksTest-miscellaneous": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-moral_disputes-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-moral_disputes": {"acc": 0.24855491329479767, "acc_norm": 0.27167630057803466, "acc_norm_stderr": 0.023948512905468365, "acc_stderr": 0.023267528432100174}}, "versions": {"hendrycksTest-moral_disputes": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/mutual_plus-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"mutual_plus": {"mrr": 0.5275583145221953, "mrr_stderr": 0.009940894824430708, "r@1": 0.2595936794582393, "r@1_stderr": 0.014737047402750955, "r@2": 0.45372460496614, "r@2_stderr": 0.01673517854461967}}, "versions": {"mutual_plus": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-college_medicine-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-college_medicine": {"acc": 0.27167630057803466, "acc_norm": 0.2543352601156069, "acc_norm_stderr": 0.0332055644308557, "acc_stderr": 0.03391750322321659}}, "versions": {"hendrycksTest-college_medicine": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-college_physics-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-college_physics": {"acc": 0.23529411764705882, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171453, "acc_stderr": 0.04220773659171452}}, "versions": {"hendrycksTest-college_physics": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-human_sexuality-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-human_sexuality": {"acc": 0.22137404580152673, "acc_norm": 0.22900763358778625, "acc_norm_stderr": 0.036853466317118506, "acc_stderr": 0.0364129708131373}}, "versions": {"hendrycksTest-human_sexuality": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-machine_learning-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-machine_learning": {"acc": 0.23214285714285715, "acc_norm": 0.22321428571428573, "acc_norm_stderr": 0.039523019677025116, "acc_stderr": 0.04007341809755806}}, "versions": {"hendrycksTest-machine_learning": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-moral_scenarios-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-moral_scenarios": {"acc": 0.2547486033519553, "acc_norm": 0.25251396648044694, "acc_norm_stderr": 0.014530330201468654, "acc_stderr": 0.014572650383409158}}, "versions": {"hendrycksTest-moral_scenarios": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-professional_law-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-professional_law": {"acc": 0.2561929595827901, "acc_norm": 0.2470664928292047, "acc_norm_stderr": 0.011015752255279352, "acc_stderr": 0.011149173153110582}}, "versions": {"hendrycksTest-professional_law": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-public_relations-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-public_relations": {"acc": 0.3090909090909091, "acc_norm": 0.2636363636363636, "acc_norm_stderr": 0.04220224692971987, "acc_stderr": 0.044262946482000985}}, "versions": {"hendrycksTest-public_relations": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-security_studies-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-security_studies": {"acc": 0.2979591836734694, "acc_norm": 0.2693877551020408, "acc_norm_stderr": 0.02840125202902294, "acc_stderr": 0.029279567411065674}}, "versions": {"hendrycksTest-security_studies": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-world_religions-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-world_religions": {"acc": 0.21637426900584794, "acc_norm": 0.22807017543859648, "acc_norm_stderr": 0.03218093795602357, "acc_stderr": 0.03158149539338734}}, "versions": {"hendrycksTest-world_religions": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-conceptual_physics-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-conceptual_physics": {"acc": 0.2680851063829787, "acc_norm": 0.2553191489361702, "acc_norm_stderr": 0.028504856470514185, "acc_stderr": 0.028957342788342347}}, "versions": {"hendrycksTest-conceptual_physics": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_computer_science-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-high_school_computer_science": {"acc": 0.2, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269, "acc_stderr": 0.04020151261036845}}, "versions": {"hendrycksTest-high_school_computer_science": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-international_law-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-international_law": {"acc": 0.2396694214876033, "acc_norm": 0.3140495867768595, "acc_norm_stderr": 0.042369647530410164, "acc_stderr": 0.03896878985070417}}, "versions": {"hendrycksTest-international_law": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-logical_fallacies-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-logical_fallacies": {"acc": 0.20245398773006135, "acc_norm": 0.2147239263803681, "acc_norm_stderr": 0.03226219377286774, "acc_stderr": 0.03157065078911902}}, "versions": {"hendrycksTest-logical_fallacies": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-clinical_knowledge-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-clinical_knowledge": {"acc": 0.23773584905660378, "acc_norm": 0.27169811320754716, "acc_norm_stderr": 0.027377706624670713, "acc_stderr": 0.02619980880756191}}, "versions": {"hendrycksTest-clinical_knowledge": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_biology-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-high_school_biology": {"acc": 0.23870967741935484, "acc_norm": 0.2709677419354839, "acc_norm_stderr": 0.025284416114900152, "acc_stderr": 0.024251071262208834}}, "versions": {"hendrycksTest-high_school_biology": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_physics-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-high_school_physics": {"acc": 0.2582781456953642, "acc_norm": 0.271523178807947, "acc_norm_stderr": 0.03631329803969653, "acc_stderr": 0.035737053147634576}}, "versions": {"hendrycksTest-high_school_physics": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_english-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"crows_pairs_english": {"likelihood_difference": 0.3367363060632734, "likelihood_difference_stderr": 0.005827747024053628, "pct_stereotype": 0.5062611806797853, "pct_stereotype_stderr": 0.012212341600228745}}, "versions": {"crows_pairs_english": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/crows_pairs_french-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"crows_pairs_french": {"likelihood_difference": 0.3367363060632734, "likelihood_difference_stderr": 0.005827747024053628, "pct_stereotype": 0.5062611806797853, "pct_stereotype_stderr": 0.012212341600228745}}, "versions": {"crows_pairs_french": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_chemistry-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-high_school_chemistry": {"acc": 0.2857142857142857, "acc_norm": 0.2660098522167488, "acc_norm_stderr": 0.031089826002937523, "acc_stderr": 0.031785297106427496}}, "versions": {"hendrycksTest-high_school_chemistry": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_geography-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-high_school_geography": {"acc": 0.2474747474747475, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.03191178226713547, "acc_stderr": 0.03074630074212452}}, "versions": {"hendrycksTest-high_school_geography": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-high_school_statistics-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-high_school_statistics": {"acc": 0.2962962962962963, "acc_norm": 0.3055555555555556, "acc_norm_stderr": 0.03141554629402544, "acc_stderr": 0.03114144782353604}}, "versions": {"hendrycksTest-high_school_statistics": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-professional_medicine-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-professional_medicine": {"acc": 0.23161764705882354, "acc_norm": 0.2536764705882353, "acc_norm_stderr": 0.02643132987078953, "acc_stderr": 0.025626533803777562}}, "versions": {"hendrycksTest-professional_medicine": 0}} -------------------------------------------------------------------------------- /bigcode-evaluation-harness/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM ubuntu:22.04 2 | 3 | RUN apt-get update && apt-get install -y python3 python3-pip 4 | 5 | COPY . /app 6 | 7 | WORKDIR /app 8 | 9 | RUN test -f /app/generations.json && rm /app/generations.json || true 10 | 11 | RUN pip3 install . 12 | 13 | CMD ["python3", "main.py"] 14 | -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-electrical_engineering-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-electrical_engineering": {"acc": 0.2689655172413793, "acc_norm": 0.2827586206896552, "acc_norm_stderr": 0.037528339580033376, "acc_stderr": 0.036951833116502325}}, "versions": {"hendrycksTest-electrical_engineering": 0}} -------------------------------------------------------------------------------- /evaluation-harness/tests/testdata/hendrycksTest-elementary_mathematics-v0-res.json: -------------------------------------------------------------------------------- 1 | {"results": {"hendrycksTest-elementary_mathematics": {"acc": 0.2724867724867725, "acc_norm": 0.2830687830687831, "acc_norm_stderr": 0.023201392938194978, "acc_stderr": 0.022930973071633345}}, "versions": {"hendrycksTest-elementary_mathematics": 0}} --------------------------------------------------------------------------------